From 4db7384ce55c4d7bfb9876fabd8d8778b2ff90ff Mon Sep 17 00:00:00 2001
From: Josef Bacik <josef@toxicpanda.com>
Date: Mon, 19 May 2025 14:03:01 -0400
Subject: [PATCH 0001/1334] btrfs: don't drop a reference if
 btrfs_check_write_meta_pointer() fails

In the zoned mode there's a bug in the extent buffer tree conversion to
xarray. The reference for eb is dropped and code continues but the
references get dropped by releasing the batch.

Reported-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Fixes: 19d7f65f032f ("btrfs: convert the buffer_radix to an xarray")
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Tested-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/extent_io.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index e43f6280f954..849199768664 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -2189,7 +2189,6 @@ retry:
 					done = 1;
 					break;
 				}
-				free_extent_buffer(eb);
 				continue;
 			}
 

From 8a3514d348de87a9d5e2ac00fbac4faae0b97996 Mon Sep 17 00:00:00 2001
From: Sanjeev Yadav <sanjeev.y@mediatek.com>
Date: Fri, 23 May 2025 13:14:01 -0700
Subject: [PATCH 0002/1334] scsi: core: ufs: Fix a hang in the error handler

ufshcd_err_handling_prepare() calls ufshcd_rpm_get_sync(). The latter
function can only succeed if UFSHCD_EH_IN_PROGRESS is not set because
resuming involves submitting a SCSI command and ufshcd_queuecommand()
returns SCSI_MLQUEUE_HOST_BUSY if UFSHCD_EH_IN_PROGRESS is set. Fix this
hang by setting UFSHCD_EH_IN_PROGRESS after ufshcd_rpm_get_sync() has
been called instead of before.

Backtrace:
__switch_to+0x174/0x338
__schedule+0x600/0x9e4
schedule+0x7c/0xe8
schedule_timeout+0xa4/0x1c8
io_schedule_timeout+0x48/0x70
wait_for_common_io+0xa8/0x160 //waiting on START_STOP
wait_for_completion_io_timeout+0x10/0x20
blk_execute_rq+0xe4/0x1e4
scsi_execute_cmd+0x108/0x244
ufshcd_set_dev_pwr_mode+0xe8/0x250
__ufshcd_wl_resume+0x94/0x354
ufshcd_wl_runtime_resume+0x3c/0x174
scsi_runtime_resume+0x64/0xa4
rpm_resume+0x15c/0xa1c
__pm_runtime_resume+0x4c/0x90 // Runtime resume ongoing
ufshcd_err_handler+0x1a0/0xd08
process_one_work+0x174/0x808
worker_thread+0x15c/0x490
kthread+0xf4/0x1ec
ret_from_fork+0x10/0x20

Signed-off-by: Sanjeev Yadav <sanjeev.y@mediatek.com>
[ bvanassche: rewrote patch description ]
Fixes: 62694735ca95 ("[SCSI] ufs: Add runtime PM support for UFS host controller driver")
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Link: https://lore.kernel.org/r/20250523201409.1676055-1-bvanassche@acm.org
Reviewed-by: Peter Wang <peter.wang@mediatek.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/ufs/core/ufshcd.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index a7513f256057..a1d7c8660c1b 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -6623,9 +6623,14 @@ static void ufshcd_err_handler(struct work_struct *work)
 		up(&hba->host_sem);
 		return;
 	}
+	spin_unlock_irqrestore(hba->host->host_lock, flags);
+
+	ufshcd_err_handling_prepare(hba);
+
+	spin_lock_irqsave(hba->host->host_lock, flags);
 	ufshcd_set_eh_in_progress(hba);
 	spin_unlock_irqrestore(hba->host->host_lock, flags);
-	ufshcd_err_handling_prepare(hba);
+
 	/* Complete requests that have door-bell cleared by h/w */
 	ufshcd_complete_requests(hba, false);
 	spin_lock_irqsave(hba->host->host_lock, flags);

From 1ac9aa41c6af7949a040f87cf1ed4bc4cac296bf Mon Sep 17 00:00:00 2001
From: Jeff LaBundy <jeff@labundy.com>
Date: Sun, 5 Jan 2025 12:56:48 -0600
Subject: [PATCH 0003/1334] Input: iqs626a - replace snprintf() with
 scnprintf()

W=1 builds warn that the data written to 'tc_name' is truncated for
theoretical strings such as "channel-2147483646".

Solve this problem by replacing snprintf() with scnprintf() so that
the return value corresponds to what was actually written.

In practice, the largest string that will be written is "channel-8",
and the return value is not actually evaluated. Instead, this patch
ultimately removes the warning without unnecessarily increasing the
size of 'tc_name' from 10 bytes.

Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202412221136.0S4kRoCC-lkp@intel.com/
Signed-off-by: Jeff LaBundy <jeff@labundy.com>
Link: https://lore.kernel.org/r/Z3rV8GTHxLyjBQ5I@nixie71
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/misc/iqs626a.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/input/misc/iqs626a.c b/drivers/input/misc/iqs626a.c
index 7a6e6927f331..7fba4a8edceb 100644
--- a/drivers/input/misc/iqs626a.c
+++ b/drivers/input/misc/iqs626a.c
@@ -771,7 +771,7 @@ static int iqs626_parse_trackpad(struct iqs626_private *iqs626,
 		u8 *thresh = &sys_reg->tp_grp_reg.ch_reg_tp[i].thresh;
 		char tc_name[10];
 
-		snprintf(tc_name, sizeof(tc_name), "channel-%d", i);
+		scnprintf(tc_name, sizeof(tc_name), "channel-%d", i);
 
 		struct fwnode_handle *tc_node __free(fwnode_handle) =
 				fwnode_get_named_child_node(ch_node, tc_name);

From 05286c5d7e72a543a12a62904a221825d72f20e9 Mon Sep 17 00:00:00 2001
From: Markus Koch <markus@notsyncing.net>
Date: Tue, 3 Jun 2025 21:36:44 -0700
Subject: [PATCH 0004/1334] Input: fsia6b - suppress buffer truncation warning
 for phys

Switch the driver to use scnprintf() to avoid warnings about potential
truncation of "phys" field which we can tolerate.

Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202501020303.1WtxWWTu-lkp@intel.com/
Signed-off-by: Markus Koch <markus@notsyncing.net>
Link: https://lore.kernel.org/r/20250602175710.61583-4-markus@notsyncing.net
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/joystick/fsia6b.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/input/joystick/fsia6b.c b/drivers/input/joystick/fsia6b.c
index 76ffdec5c183..7e3bc99d766f 100644
--- a/drivers/input/joystick/fsia6b.c
+++ b/drivers/input/joystick/fsia6b.c
@@ -149,7 +149,7 @@ static int fsia6b_serio_connect(struct serio *serio, struct serio_driver *drv)
 	}
 	fsia6b->dev = input_dev;
 
-	snprintf(fsia6b->phys, sizeof(fsia6b->phys), "%s/input0", serio->phys);
+	scnprintf(fsia6b->phys, sizeof(fsia6b->phys), "%s/input0", serio->phys);
 
 	input_dev->name = DRIVER_DESC;
 	input_dev->phys = fsia6b->phys;

From 4ecc7317700a0f402e301380300328141b332170 Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Tue, 3 Jun 2025 21:45:44 -0700
Subject: [PATCH 0005/1334] Input: atkbd - switch to use scnprintf() to
 suppress truncation warning

Switch the driver to use scnprintf() to avoid warnings about potential
truncation of "phys" field which we can tolerate.

Reported-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/keyboard/atkbd.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/input/keyboard/atkbd.c b/drivers/input/keyboard/atkbd.c
index 3ff2fcf05ad5..c9e1127578b9 100644
--- a/drivers/input/keyboard/atkbd.c
+++ b/drivers/input/keyboard/atkbd.c
@@ -1191,8 +1191,8 @@ static void atkbd_set_device_attrs(struct atkbd *atkbd)
 			 "AT %s Set %d keyboard",
 			 atkbd->translated ? "Translated" : "Raw", atkbd->set);
 
-	snprintf(atkbd->phys, sizeof(atkbd->phys),
-		 "%s/input0", atkbd->ps2dev.serio->phys);
+	scnprintf(atkbd->phys, sizeof(atkbd->phys),
+		  "%s/input0", atkbd->ps2dev.serio->phys);
 
 	input_dev->name = atkbd->name;
 	input_dev->phys = atkbd->phys;

From 1babc858cce111d744baf9a015ec65a19aafbbea Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Tue, 3 Jun 2025 21:42:51 -0700
Subject: [PATCH 0006/1334] Input: alps - switch to use scnprintf() to suppress
 truncation warning

Switch the driver to use scnprintf() to avoid warnings about potential
truncation of "phys" field which we can tolerate.

Reported-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/mouse/alps.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/input/mouse/alps.c b/drivers/input/mouse/alps.c
index 0bd7b09b0aa3..01f270509f03 100644
--- a/drivers/input/mouse/alps.c
+++ b/drivers/input/mouse/alps.c
@@ -1408,9 +1408,9 @@ static int alps_do_register_bare_ps2_mouse(struct alps_data *priv)
 		return -ENOMEM;
 	}
 
-	snprintf(priv->phys3, sizeof(priv->phys3), "%s/%s",
-		 psmouse->ps2dev.serio->phys,
-		 (priv->dev2 ? "input2" : "input1"));
+	scnprintf(priv->phys3, sizeof(priv->phys3), "%s/%s",
+		  psmouse->ps2dev.serio->phys,
+		  (priv->dev2 ? "input2" : "input1"));
 	dev3->phys = priv->phys3;
 
 	/*

From ce098f2aded8d0f6f41bb9ab069c3f3c8ef5fc42 Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Tue, 3 Jun 2025 21:49:21 -0700
Subject: [PATCH 0007/1334] Input: lifebook - switch to use scnprintf() to
 suppress truncation warning

Switch the driver to use scnprintf() to avoid warnings about potential
truncation of "phys" field which we can tolerate.

Reported-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/mouse/lifebook.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/input/mouse/lifebook.c b/drivers/input/mouse/lifebook.c
index 7147dacc404f..283ef46f039f 100644
--- a/drivers/input/mouse/lifebook.c
+++ b/drivers/input/mouse/lifebook.c
@@ -279,8 +279,8 @@ static int lifebook_create_relative_device(struct psmouse *psmouse)
 		goto err_out;
 
 	priv->dev2 = dev2;
-	snprintf(priv->phys, sizeof(priv->phys),
-		 "%s/input1", psmouse->ps2dev.serio->phys);
+	scnprintf(priv->phys, sizeof(priv->phys),
+		  "%s/input1", psmouse->ps2dev.serio->phys);
 
 	dev2->phys = priv->phys;
 	dev2->name = "LBPS/2 Fujitsu Lifebook Touchpad";

From 805f5bbaa507a7e15333ad7bb34d517251de4eb9 Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Tue, 3 Jun 2025 21:47:36 -0700
Subject: [PATCH 0008/1334] Input: psmouse - switch to use scnprintf() to
 suppress truncation warning

Switch the driver to use scnprintf() to avoid warnings about potential
truncation of "phys" field which we can tolerate.

Reported-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/mouse/psmouse-base.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/input/mouse/psmouse-base.c b/drivers/input/mouse/psmouse-base.c
index a2c9f7144864..77ea7da3b1c5 100644
--- a/drivers/input/mouse/psmouse-base.c
+++ b/drivers/input/mouse/psmouse-base.c
@@ -1600,7 +1600,7 @@ static int psmouse_connect(struct serio *serio, struct serio_driver *drv)
 		 psmouse_pre_receive_byte, psmouse_receive_byte);
 	INIT_DELAYED_WORK(&psmouse->resync_work, psmouse_resync);
 	psmouse->dev = input_dev;
-	snprintf(psmouse->phys, sizeof(psmouse->phys), "%s/input0", serio->phys);
+	scnprintf(psmouse->phys, sizeof(psmouse->phys), "%s/input0", serio->phys);
 
 	psmouse_set_state(psmouse, PSMOUSE_INITIALIZING);
 

From b55eb6eb2a7427428c59b293a0900131fc849595 Mon Sep 17 00:00:00 2001
From: Mike Yuan <me@yhndnzj.com>
Date: Wed, 4 Jun 2025 15:03:42 +0000
Subject: [PATCH 0009/1334] pidfs: never refuse ppid == 0 in PIDFD_GET_INFO

In systemd we spotted an issue after switching to ioctl(PIDFD_GET_INFO)
for obtaining pid number the pidfd refers to, that for processes
with a parent from outer pidns PIDFD_GET_INFO unexpectedly yields
-ESRCH [1]. It turned out that there's an arbitrary check blocking
this, which is not really sensible given getppid() happily returns
0 for such processes. Just drop the spurious check and userspace
ought to handle ppid == 0 properly everywhere.

[1] https://github.com/systemd/systemd/issues/37715

Fixes: cdda1f26e74b ("pidfd: add ioctl to retrieve pid info")
Signed-off-by: Mike Yuan <me@yhndnzj.com>
Link: https://lore.kernel.org/20250604150238.42664-1-me@yhndnzj.com
Cc: Christian Brauner <brauner@kernel.org>
Cc: Luca Boccassi <luca.boccassi@gmail.com>
Cc: stable@vger.kernel.org
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/pidfs.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/pidfs.c b/fs/pidfs.c
index c1f0a067be40..69919be1c9d8 100644
--- a/fs/pidfs.c
+++ b/fs/pidfs.c
@@ -366,7 +366,7 @@ static long pidfd_info(struct file *file, unsigned int cmd, unsigned long arg)
 	kinfo.pid = task_pid_vnr(task);
 	kinfo.mask |= PIDFD_INFO_PID;
 
-	if (kinfo.pid == 0 || kinfo.tgid == 0 || (kinfo.ppid == 0 && kinfo.pid != 1))
+	if (kinfo.pid == 0 || kinfo.tgid == 0)
 		return -ESRCH;
 
 copy_out:

From 714d02b41939d2720379e11ef25227aec4e5bec9 Mon Sep 17 00:00:00 2001
From: Amir Goldstein <amir73il@gmail.com>
Date: Thu, 5 Jun 2025 12:15:30 +0200
Subject: [PATCH 0010/1334] ovl: fix regression caused by lookup helpers API
 changes

The lookup helpers API was changed by merge of vfs-6.16-rc1.async.dir to
pass a non-const qstr pointer argument to lookup_one*() helpers.

All of the callers of this API were changed to pass a pointer to temp
copy of qstr, except overlays that was passing a const pointer to
dentry->d_name that was changed to pass a non-const copy instead
when doing a lookup in lower layer which is not the fs of said dentry.

This wrong use of the API caused a regression in fstest overlay/012.

Fix the regression by making a non-const copy of dentry->d_name prior
to calling the lookup API, but the API should be fixed to not allow this
class of bugs.

Cc: NeilBrown <neilb@suse.de>
Fixes: 5741909697a3 ("VFS: improve interface for lookup_one functions")
Fixes: 390e34bc1490 ("VFS: change lookup_one_common and lookup_noperm_common to take a qstr")
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Link: https://lore.kernel.org/20250605101530.2336320-1-amir73il@gmail.com
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/overlayfs/namei.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/fs/overlayfs/namei.c b/fs/overlayfs/namei.c
index bf722daf19a9..f75c49ceb460 100644
--- a/fs/overlayfs/namei.c
+++ b/fs/overlayfs/namei.c
@@ -1371,7 +1371,7 @@ out:
 bool ovl_lower_positive(struct dentry *dentry)
 {
 	struct ovl_entry *poe = OVL_E(dentry->d_parent);
-	struct qstr *name = &dentry->d_name;
+	const struct qstr *name = &dentry->d_name;
 	const struct cred *old_cred;
 	unsigned int i;
 	bool positive = false;
@@ -1394,9 +1394,15 @@ bool ovl_lower_positive(struct dentry *dentry)
 		struct dentry *this;
 		struct ovl_path *parentpath = &ovl_lowerstack(poe)[i];
 
+		/*
+		 * We need to make a non-const copy of dentry->d_name,
+		 * because lookup_one_positive_unlocked() will hash name
+		 * with parentpath base, which is on another (lower fs).
+		 */
 		this = lookup_one_positive_unlocked(
 				mnt_idmap(parentpath->layer->mnt),
-				name, parentpath->dentry);
+				&QSTR_LEN(name->name, name->len),
+				parentpath->dentry);
 		if (IS_ERR(this)) {
 			switch (PTR_ERR(this)) {
 			case -ENOENT:

From 4f6fc782128355931527cefe3eb45338abd8ab39 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Thu, 5 Jun 2025 12:31:45 +0200
Subject: [PATCH 0011/1334] perf: Fix sample vs do_exit()

Baisheng Gao reported an ARM64 crash, which Mark decoded as being a
synchronous external abort -- most likely due to trying to access
MMIO in bad ways.

The crash further shows perf trying to do a user stack sample while in
exit_mmap()'s tlb_finish_mmu() -- i.e. while tearing down the address
space it is trying to access.

It turns out that we stop perf after we tear down the userspace mm; a
receipie for disaster, since perf likes to access userspace for
various reasons.

Flip this order by moving up where we stop perf in do_exit().

Additionally, harden PERF_SAMPLE_CALLCHAIN and PERF_SAMPLE_STACK_USER
to abort when the current task does not have an mm (exit_mm() makes
sure to set current->mm = NULL; before commencing with the actual
teardown). Such that CPU wide events don't trip on this same problem.

Fixes: c5ebcedb566e ("perf: Add ability to attach user stack dump to sample")
Reported-by: Baisheng Gao <baisheng.gao@unisoc.com>
Suggested-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20250605110815.GQ39944@noisy.programming.kicks-ass.net
---
 kernel/events/core.c |  7 +++++++
 kernel/exit.c        | 17 +++++++++--------
 2 files changed, 16 insertions(+), 8 deletions(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index f34c99f8ce8f..26dec1d8a5ab 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -7439,6 +7439,10 @@ perf_sample_ustack_size(u16 stack_size, u16 header_size,
 	if (!regs)
 		return 0;
 
+	/* No mm, no stack, no dump. */
+	if (!current->mm)
+		return 0;
+
 	/*
 	 * Check if we fit in with the requested stack size into the:
 	 * - TASK_SIZE
@@ -8150,6 +8154,9 @@ perf_callchain(struct perf_event *event, struct pt_regs *regs)
 	const u32 max_stack = event->attr.sample_max_stack;
 	struct perf_callchain_entry *callchain;
 
+	if (!current->mm)
+		user = false;
+
 	if (!kernel && !user)
 		return &__empty_callchain;
 
diff --git a/kernel/exit.c b/kernel/exit.c
index 38645039dd8f..1883150c9422 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -944,6 +944,15 @@ void __noreturn do_exit(long code)
 	taskstats_exit(tsk, group_dead);
 	trace_sched_process_exit(tsk, group_dead);
 
+	/*
+	 * Since sampling can touch ->mm, make sure to stop everything before we
+	 * tear it down.
+	 *
+	 * Also flushes inherited counters to the parent - before the parent
+	 * gets woken up by child-exit notifications.
+	 */
+	perf_event_exit_task(tsk);
+
 	exit_mm();
 
 	if (group_dead)
@@ -959,14 +968,6 @@ void __noreturn do_exit(long code)
 	exit_task_work(tsk);
 	exit_thread(tsk);
 
-	/*
-	 * Flush inherited counters to the parent - before the parent
-	 * gets woken up by child-exit notifications.
-	 *
-	 * because of cgroup mode, must be called before cgroup_exit()
-	 */
-	perf_event_exit_task(tsk);
-
 	sched_autogroup_exit_task(tsk);
 	cgroup_exit(tsk);
 

From 61988e36dc5457cdff7ae7927e8d9ad1419ee998 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Thu, 5 Jun 2025 12:37:11 +0200
Subject: [PATCH 0012/1334] perf: Fix cgroup state vs ERROR

While chasing down a missing perf_cgroup_event_disable() elsewhere,
Leo Yan found that both perf_put_aux_event() and
perf_remove_sibling_event() were also missing one.

Specifically, the rule is that events that switch to OFF,ERROR need to
call perf_cgroup_event_disable().

Unify the disable paths to ensure this.

Fixes: ab43762ef010 ("perf: Allow normal events to output AUX data")
Fixes: 9f0c4fa111dc ("perf/core: Add a new PERF_EV_CAP_SIBLING event capability")
Reported-by: Leo Yan <leo.yan@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20250605123343.GD35970@noisy.programming.kicks-ass.net
---
 kernel/events/core.c | 51 ++++++++++++++++++++++++++------------------
 1 file changed, 30 insertions(+), 21 deletions(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 26dec1d8a5ab..1cc98b9b3c0b 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -2149,8 +2149,9 @@ perf_aux_output_match(struct perf_event *event, struct perf_event *aux_event)
 }
 
 static void put_event(struct perf_event *event);
-static void event_sched_out(struct perf_event *event,
-			    struct perf_event_context *ctx);
+static void __event_disable(struct perf_event *event,
+			    struct perf_event_context *ctx,
+			    enum perf_event_state state);
 
 static void perf_put_aux_event(struct perf_event *event)
 {
@@ -2183,8 +2184,7 @@ static void perf_put_aux_event(struct perf_event *event)
 		 * state so that we don't try to schedule it again. Note
 		 * that perf_event_enable() will clear the ERROR status.
 		 */
-		event_sched_out(iter, ctx);
-		perf_event_set_state(event, PERF_EVENT_STATE_ERROR);
+		__event_disable(iter, ctx, PERF_EVENT_STATE_ERROR);
 	}
 }
 
@@ -2242,18 +2242,6 @@ static inline struct list_head *get_event_list(struct perf_event *event)
 				    &event->pmu_ctx->flexible_active;
 }
 
-/*
- * Events that have PERF_EV_CAP_SIBLING require being part of a group and
- * cannot exist on their own, schedule them out and move them into the ERROR
- * state. Also see _perf_event_enable(), it will not be able to recover
- * this ERROR state.
- */
-static inline void perf_remove_sibling_event(struct perf_event *event)
-{
-	event_sched_out(event, event->ctx);
-	perf_event_set_state(event, PERF_EVENT_STATE_ERROR);
-}
-
 static void perf_group_detach(struct perf_event *event)
 {
 	struct perf_event *leader = event->group_leader;
@@ -2289,8 +2277,15 @@ static void perf_group_detach(struct perf_event *event)
 	 */
 	list_for_each_entry_safe(sibling, tmp, &event->sibling_list, sibling_list) {
 
+		/*
+		 * Events that have PERF_EV_CAP_SIBLING require being part of
+		 * a group and cannot exist on their own, schedule them out
+		 * and move them into the ERROR state. Also see
+		 * _perf_event_enable(), it will not be able to recover this
+		 * ERROR state.
+		 */
 		if (sibling->event_caps & PERF_EV_CAP_SIBLING)
-			perf_remove_sibling_event(sibling);
+			__event_disable(sibling, ctx, PERF_EVENT_STATE_ERROR);
 
 		sibling->group_leader = sibling;
 		list_del_init(&sibling->sibling_list);
@@ -2562,6 +2557,15 @@ static void perf_remove_from_context(struct perf_event *event, unsigned long fla
 	event_function_call(event, __perf_remove_from_context, (void *)flags);
 }
 
+static void __event_disable(struct perf_event *event,
+			    struct perf_event_context *ctx,
+			    enum perf_event_state state)
+{
+	event_sched_out(event, ctx);
+	perf_cgroup_event_disable(event, ctx);
+	perf_event_set_state(event, state);
+}
+
 /*
  * Cross CPU call to disable a performance event
  */
@@ -2576,13 +2580,18 @@ static void __perf_event_disable(struct perf_event *event,
 	perf_pmu_disable(event->pmu_ctx->pmu);
 	ctx_time_update_event(ctx, event);
 
+	/*
+	 * When disabling a group leader, the whole group becomes ineligible
+	 * to run, so schedule out the full group.
+	 */
 	if (event == event->group_leader)
 		group_sched_out(event, ctx);
-	else
-		event_sched_out(event, ctx);
 
-	perf_event_set_state(event, PERF_EVENT_STATE_OFF);
-	perf_cgroup_event_disable(event, ctx);
+	/*
+	 * But only mark the leader OFF; the siblings will remain
+	 * INACTIVE.
+	 */
+	__event_disable(event, ctx, PERF_EVENT_STATE_OFF);
 
 	perf_pmu_enable(event->pmu_ctx->pmu);
 }

From 3b7a34aebbdf2a4b7295205bf0c654294283ec82 Mon Sep 17 00:00:00 2001
From: Yeoreum Yun <yeoreum.yun@arm.com>
Date: Mon, 2 Jun 2025 19:40:49 +0100
Subject: [PATCH 0013/1334] perf: Fix dangling cgroup pointer in cpuctx

Commit a3c3c6667("perf/core: Fix child_total_time_enabled accounting
bug at task exit") moves the event->state update to before
list_del_event(). This makes the event->state test in list_del_event()
always false; never calling perf_cgroup_event_disable().

As a result, cpuctx->cgrp won't be cleared properly; causing havoc.

Fixes: a3c3c6667("perf/core: Fix child_total_time_enabled accounting bug at task exit")
Signed-off-by: Yeoreum Yun <yeoreum.yun@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: David Wang <00107082@163.com>
Link: https://lore.kernel.org/all/aD2TspKH%2F7yvfYoO@e129823.arm.com/
---
 kernel/events/core.c | 21 ++++++---------------
 1 file changed, 6 insertions(+), 15 deletions(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 1cc98b9b3c0b..d78608323916 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -2120,18 +2120,6 @@ list_del_event(struct perf_event *event, struct perf_event_context *ctx)
 	if (event->group_leader == event)
 		del_event_from_groups(event, ctx);
 
-	/*
-	 * If event was in error state, then keep it
-	 * that way, otherwise bogus counts will be
-	 * returned on read(). The only way to get out
-	 * of error state is by explicit re-enabling
-	 * of the event
-	 */
-	if (event->state > PERF_EVENT_STATE_OFF) {
-		perf_cgroup_event_disable(event, ctx);
-		perf_event_set_state(event, PERF_EVENT_STATE_OFF);
-	}
-
 	ctx->generation++;
 	event->pmu_ctx->nr_events--;
 }
@@ -2488,11 +2476,14 @@ __perf_remove_from_context(struct perf_event *event,
 		state = PERF_EVENT_STATE_EXIT;
 	if (flags & DETACH_REVOKE)
 		state = PERF_EVENT_STATE_REVOKED;
-	if (flags & DETACH_DEAD) {
-		event->pending_disable = 1;
+	if (flags & DETACH_DEAD)
 		state = PERF_EVENT_STATE_DEAD;
-	}
+
 	event_sched_out(event, ctx);
+
+	if (event->state > PERF_EVENT_STATE_OFF)
+		perf_cgroup_event_disable(event, ctx);
+
 	perf_event_set_state(event, min(event->state, state));
 
 	if (flags & DETACH_GROUP)

From 3172fb986666dfb71bf483b6d3539e1e587fa197 Mon Sep 17 00:00:00 2001
From: Luo Gengkun <luogengkun@huaweicloud.com>
Date: Wed, 4 Jun 2025 03:39:24 +0000
Subject: [PATCH 0014/1334] perf/core: Fix WARN in perf_cgroup_switch()

There may be concurrency between perf_cgroup_switch and
perf_cgroup_event_disable. Consider the following scenario: after a new
perf cgroup event is created on CPU0, the new event may not trigger
a reprogramming, causing ctx->is_active to be 0. In this case, when CPU1
disables this perf event, it executes __perf_remove_from_context->
list _del_event->perf_cgroup_event_disable on CPU1, which causes a race
with perf_cgroup_switch running on CPU0.

The following describes the details of this concurrency scenario:

CPU0						CPU1

perf_cgroup_switch:
   ...
   # cpuctx->cgrp is not NULL here
   if (READ_ONCE(cpuctx->cgrp) == NULL)
   	return;

						perf_remove_from_context:
						   ...
						   raw_spin_lock_irq(&ctx->lock);
						   ...
						   # ctx->is_active == 0 because reprogramm is not
						   # tigger, so CPU1 can do __perf_remove_from_context
						   # for CPU0
						   __perf_remove_from_context:
						         perf_cgroup_event_disable:
							    ...
							    if (--ctx->nr_cgroups)
							    ...

   # this warning will happened because CPU1 changed
   # ctx.nr_cgroups to 0.
   WARN_ON_ONCE(cpuctx->ctx.nr_cgroups == 0);

[peterz: use guard instead of goto unlock]
Fixes: db4a835601b7 ("perf/core: Set cgroup in CPU contexts for new cgroup events")
Signed-off-by: Luo Gengkun <luogengkun@huaweicloud.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20250604033924.3914647-3-luogengkun@huaweicloud.com
---
 kernel/events/core.c | 22 ++++++++++++++++++++--
 1 file changed, 20 insertions(+), 2 deletions(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index d78608323916..d7cf008f3d75 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -207,6 +207,19 @@ static void perf_ctx_unlock(struct perf_cpu_context *cpuctx,
 	__perf_ctx_unlock(&cpuctx->ctx);
 }
 
+typedef struct {
+	struct perf_cpu_context *cpuctx;
+	struct perf_event_context *ctx;
+} class_perf_ctx_lock_t;
+
+static inline void class_perf_ctx_lock_destructor(class_perf_ctx_lock_t *_T)
+{ perf_ctx_unlock(_T->cpuctx, _T->ctx); }
+
+static inline class_perf_ctx_lock_t
+class_perf_ctx_lock_constructor(struct perf_cpu_context *cpuctx,
+				struct perf_event_context *ctx)
+{ perf_ctx_lock(cpuctx, ctx); return (class_perf_ctx_lock_t){ cpuctx, ctx }; }
+
 #define TASK_TOMBSTONE ((void *)-1L)
 
 static bool is_kernel_event(struct perf_event *event)
@@ -944,7 +957,13 @@ static void perf_cgroup_switch(struct task_struct *task)
 	if (READ_ONCE(cpuctx->cgrp) == cgrp)
 		return;
 
-	perf_ctx_lock(cpuctx, cpuctx->task_ctx);
+	guard(perf_ctx_lock)(cpuctx, cpuctx->task_ctx);
+	/*
+	 * Re-check, could've raced vs perf_remove_from_context().
+	 */
+	if (READ_ONCE(cpuctx->cgrp) == NULL)
+		return;
+
 	perf_ctx_disable(&cpuctx->ctx, true);
 
 	ctx_sched_out(&cpuctx->ctx, NULL, EVENT_ALL|EVENT_CGROUP);
@@ -962,7 +981,6 @@ static void perf_cgroup_switch(struct task_struct *task)
 	ctx_sched_in(&cpuctx->ctx, NULL, EVENT_ALL|EVENT_CGROUP);
 
 	perf_ctx_enable(&cpuctx->ctx, true);
-	perf_ctx_unlock(cpuctx, cpuctx->task_ctx);
 }
 
 static int perf_cgroup_ensure_storage(struct perf_event *event,

From 49b393af3130c7712c7e8f215f4126c9a8060fa6 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Wed, 4 Jun 2025 10:21:38 +0200
Subject: [PATCH 0015/1334] perf: Add comment to enum perf_event_state

Better describe the event states.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Leo Yan <leo.yan@arm.com>
Link: https://lkml.kernel.org/r/20250604135801.GK38114@noisy.programming.kicks-ass.net
---
 include/linux/perf_event.h | 42 ++++++++++++++++++++++++++++++++++++--
 1 file changed, 40 insertions(+), 2 deletions(-)

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 52dc7cfab0e0..ec9d96025683 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -635,8 +635,46 @@ struct perf_addr_filter_range {
 	unsigned long			size;
 };
 
-/**
- * enum perf_event_state - the states of an event:
+/*
+ * The normal states are:
+ *
+ *            ACTIVE    --.
+ *               ^        |
+ *               |        |
+ *       sched_{in,out}() |
+ *               |        |
+ *               v        |
+ *      ,---> INACTIVE  --+ <-.
+ *      |                 |   |
+ *      |                {dis,en}able()
+ *   sched_in()           |   |
+ *      |       OFF    <--' --+
+ *      |                     |
+ *      `--->  ERROR    ------'
+ *
+ * That is:
+ *
+ * sched_in:       INACTIVE          -> {ACTIVE,ERROR}
+ * sched_out:      ACTIVE            -> INACTIVE
+ * disable:        {ACTIVE,INACTIVE} -> OFF
+ * enable:         {OFF,ERROR}       -> INACTIVE
+ *
+ * Where {OFF,ERROR} are disabled states.
+ *
+ * Then we have the {EXIT,REVOKED,DEAD} states which are various shades of
+ * defunct events:
+ *
+ *  - EXIT means task that the even was assigned to died, but child events
+ *    still live, and further children can still be created. But the event
+ *    itself will never be active again. It can only transition to
+ *    {REVOKED,DEAD};
+ *
+ *  - REVOKED means the PMU the event was associated with is gone; all
+ *    functionality is stopped but the event is still alive. Can only
+ *    transition to DEAD;
+ *
+ *  - DEAD event really is DYING tearing down state and freeing bits.
+ *
  */
 enum perf_event_state {
 	PERF_EVENT_STATE_DEAD		= -5,

From 1a9dcf69c7a97e733aa2fc026db22f22928ca7b7 Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Wed, 28 May 2025 10:55:19 +0200
Subject: [PATCH 0016/1334] selftests/futex: getopt() requires int as return
 value.

Mark reported that futex_priv_hash fails on ARM64.
It turns out that the command line parsing does not terminate properly
and ends in the default case assuming an invalid option was passed.

Use an int as the return type for getopt().

Closes: https://lore.kernel.org/all/31869a69-063f-44a3-a079-ba71b2506cce@sirena.org.uk/
Fixes: 3163369407baf ("selftests/futex: Add futex_numa_mpol")
Fixes: cda95faef7bcf ("selftests/futex: Add futex_priv_hash")
Reported-by: Mark Brown <broonie@kernel.org>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20250528085521.1938355-2-bigeasy@linutronix.de
---
 tools/testing/selftests/futex/functional/futex_numa_mpol.c | 2 +-
 tools/testing/selftests/futex/functional/futex_priv_hash.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/futex/functional/futex_numa_mpol.c b/tools/testing/selftests/futex/functional/futex_numa_mpol.c
index 20a9d3ecf743..564dbd02d2f4 100644
--- a/tools/testing/selftests/futex/functional/futex_numa_mpol.c
+++ b/tools/testing/selftests/futex/functional/futex_numa_mpol.c
@@ -144,7 +144,7 @@ int main(int argc, char *argv[])
 	struct futex32_numa *futex_numa;
 	int mem_size, i;
 	void *futex_ptr;
-	char c;
+	int c;
 
 	while ((c = getopt(argc, argv, "chv:")) != -1) {
 		switch (c) {
diff --git a/tools/testing/selftests/futex/functional/futex_priv_hash.c b/tools/testing/selftests/futex/functional/futex_priv_hash.c
index 2dca18fefedc..24a92dc94eb8 100644
--- a/tools/testing/selftests/futex/functional/futex_priv_hash.c
+++ b/tools/testing/selftests/futex/functional/futex_priv_hash.c
@@ -130,7 +130,7 @@ int main(int argc, char *argv[])
 	pthread_mutexattr_t mutex_attr_pi;
 	int use_global_hash = 0;
 	int ret;
-	char c;
+	int c;
 
 	while ((c = getopt(argc, argv, "cghv:")) != -1) {
 		switch (c) {

From 0ecb4232fc65e659ca7020f8bb2e0fc347acfb7d Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Wed, 28 May 2025 10:55:20 +0200
Subject: [PATCH 0017/1334] selftests/futex: Set the home_node in
 futex_numa_mpol

The test fails at the MPOL step if multiple nodes are available. The
reason is that mbind() sets the policy but the home_node, which is
retrieved by the futex code, is not set. This causes to retrieve the
current node and with multiple nodes it fails on one of the iterations.

Use numa_set_mempolicy_home_node() to set the expected node.
Use ksft_exit_fail_msg() to fail and exit in order not to confuse ktap.

Fixes: 3163369407baf ("selftests/futex: Add futex_numa_mpol")
Suggested-by: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20250528085521.1938355-3-bigeasy@linutronix.de
---
 .../testing/selftests/futex/functional/futex_numa_mpol.c  | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/futex/functional/futex_numa_mpol.c b/tools/testing/selftests/futex/functional/futex_numa_mpol.c
index 564dbd02d2f4..a9ecfb2d3932 100644
--- a/tools/testing/selftests/futex/functional/futex_numa_mpol.c
+++ b/tools/testing/selftests/futex/functional/futex_numa_mpol.c
@@ -210,6 +210,10 @@ int main(int argc, char *argv[])
 		ret = mbind(futex_ptr, mem_size, MPOL_BIND, &nodemask,
 			    sizeof(nodemask) * 8, 0);
 		if (ret == 0) {
+			ret = numa_set_mempolicy_home_node(futex_ptr, mem_size, i, 0);
+			if (ret != 0)
+				ksft_exit_fail_msg("Failed to set home node: %m, %d\n", errno);
+
 			ksft_print_msg("Node %d test\n", i);
 			futex_numa->futex = 0;
 			futex_numa->numa = FUTEX_NO_NODE;
@@ -220,8 +224,8 @@ int main(int argc, char *argv[])
 			if (0)
 				test_futex_mpol(futex_numa, 0);
 			if (futex_numa->numa != i) {
-				ksft_test_result_fail("Returned NUMA node is %d expected %d\n",
-						      futex_numa->numa, i);
+				ksft_exit_fail_msg("Returned NUMA node is %d expected %d\n",
+						   futex_numa->numa, i);
 			}
 		}
 	}

From 8337204c58899fe422db765b481711eb2d95eb0b Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Wed, 28 May 2025 10:55:21 +0200
Subject: [PATCH 0018/1334] futex: Handle invalid node numbers supplied by user

syzbot used a negative node number which was not rejected early and led
to invalid memory access in node_possible().

Reject negative node numbers except for FUTEX_NO_NODE.

[bigeasy: Keep the FUTEX_NO_NODE check]

Closes: https://lore.kernel.org/all/6835bfe3.a70a0220.253bc2.00b5.GAE@google.com/
Fixes: cec199c5e39bd ("futex: Implement FUTEX2_NUMA")
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reported-by: syzbot+9afaf6749e3a7aa1bdf3@syzkaller.appspotmail.com
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20250528085521.1938355-4-bigeasy@linutronix.de
---
 kernel/futex/core.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/kernel/futex/core.c b/kernel/futex/core.c
index 565f9717c6ca..b652d2f60c40 100644
--- a/kernel/futex/core.c
+++ b/kernel/futex/core.c
@@ -583,8 +583,8 @@ int get_futex_key(u32 __user *uaddr, unsigned int flags, union futex_key *key,
 		if (futex_get_value(&node, naddr))
 			return -EFAULT;
 
-		if (node != FUTEX_NO_NODE &&
-		    (node >= MAX_NUMNODES || !node_possible(node)))
+		if ((node != FUTEX_NO_NODE) &&
+		    ((unsigned int)node >= MAX_NUMNODES || !node_possible(node)))
 			return -EINVAL;
 	}
 

From 6678791ee3da0b78c28fe7d77814097f53cbb8df Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Tue, 3 Jun 2025 08:08:21 +0100
Subject: [PATCH 0019/1334] KVM: arm64: Add assignment-specific sysreg accessor

Assigning a value to a system register doesn't do what it is
supposed to be doing if that register is one that has RESx bits.

The main problem is that we use __vcpu_sys_reg(), which can be used
both as a lvalue and rvalue. When used as a lvalue, the bit masking
occurs *before* the new value is assigned, meaning that we (1) do
pointless work on the old cvalue, and (2) potentially assign an
invalid value as we fail to apply the masks to it.

Fix this by providing a new __vcpu_assign_sys_reg() that does
what it says on the tin, and sanitises the *new* value instead of
the old one. This comes with a significant amount of churn.

Reviewed-by: Miguel Luis <miguel.luis@oracle.com>
Reviewed-by: Oliver Upton <oliver.upton@linux.dev>
Link: https://lore.kernel.org/r/20250603070824.1192795-2-maz@kernel.org
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/kvm_host.h          | 11 ++++++
 arch/arm64/kvm/arch_timer.c                | 16 ++++-----
 arch/arm64/kvm/hyp/exception.c             |  4 +--
 arch/arm64/kvm/hyp/include/hyp/switch.h    |  4 +--
 arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h |  6 ++--
 arch/arm64/kvm/hyp/nvhe/hyp-main.c         |  4 +--
 arch/arm64/kvm/hyp/vhe/switch.c            |  4 +--
 arch/arm64/kvm/hyp/vhe/sysreg-sr.c         | 42 +++++++++++-----------
 arch/arm64/kvm/pmu-emul.c                  | 14 ++++----
 arch/arm64/kvm/sys_regs.c                  | 38 ++++++++++----------
 arch/arm64/kvm/sys_regs.h                  |  4 +--
 arch/arm64/kvm/vgic/vgic-v3-nested.c       | 10 +++---
 12 files changed, 85 insertions(+), 72 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index d941abc6b5ee..3b84ad91116b 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -1107,6 +1107,17 @@ static inline u64 *___ctxt_sys_reg(const struct kvm_cpu_context *ctxt, int r)
 #define ctxt_sys_reg(c,r)	(*__ctxt_sys_reg(c,r))
 
 u64 kvm_vcpu_apply_reg_masks(const struct kvm_vcpu *, enum vcpu_sysreg, u64);
+
+#define __vcpu_assign_sys_reg(v, r, val)				\
+	do {								\
+		const struct kvm_cpu_context *ctxt = &(v)->arch.ctxt;	\
+		u64 __v = (val);					\
+		if (vcpu_has_nv((v)) && (r) >= __SANITISED_REG_START__)	\
+			__v = kvm_vcpu_apply_reg_masks((v), (r), __v);	\
+									\
+		ctxt_sys_reg(ctxt, (r)) = __v;				\
+	} while (0)
+
 #define __vcpu_sys_reg(v,r)						\
 	(*({								\
 		const struct kvm_cpu_context *ctxt = &(v)->arch.ctxt;	\
diff --git a/arch/arm64/kvm/arch_timer.c b/arch/arm64/kvm/arch_timer.c
index 5133dcbfe9f7..5a67a6d4d95b 100644
--- a/arch/arm64/kvm/arch_timer.c
+++ b/arch/arm64/kvm/arch_timer.c
@@ -108,16 +108,16 @@ static void timer_set_ctl(struct arch_timer_context *ctxt, u32 ctl)
 
 	switch(arch_timer_ctx_index(ctxt)) {
 	case TIMER_VTIMER:
-		__vcpu_sys_reg(vcpu, CNTV_CTL_EL0) = ctl;
+		__vcpu_assign_sys_reg(vcpu, CNTV_CTL_EL0, ctl);
 		break;
 	case TIMER_PTIMER:
-		__vcpu_sys_reg(vcpu, CNTP_CTL_EL0) = ctl;
+		__vcpu_assign_sys_reg(vcpu, CNTP_CTL_EL0, ctl);
 		break;
 	case TIMER_HVTIMER:
-		__vcpu_sys_reg(vcpu, CNTHV_CTL_EL2) = ctl;
+		__vcpu_assign_sys_reg(vcpu, CNTHV_CTL_EL2, ctl);
 		break;
 	case TIMER_HPTIMER:
-		__vcpu_sys_reg(vcpu, CNTHP_CTL_EL2) = ctl;
+		__vcpu_assign_sys_reg(vcpu, CNTHP_CTL_EL2, ctl);
 		break;
 	default:
 		WARN_ON(1);
@@ -130,16 +130,16 @@ static void timer_set_cval(struct arch_timer_context *ctxt, u64 cval)
 
 	switch(arch_timer_ctx_index(ctxt)) {
 	case TIMER_VTIMER:
-		__vcpu_sys_reg(vcpu, CNTV_CVAL_EL0) = cval;
+		__vcpu_assign_sys_reg(vcpu, CNTV_CVAL_EL0, cval);
 		break;
 	case TIMER_PTIMER:
-		__vcpu_sys_reg(vcpu, CNTP_CVAL_EL0) = cval;
+		__vcpu_assign_sys_reg(vcpu, CNTP_CVAL_EL0, cval);
 		break;
 	case TIMER_HVTIMER:
-		__vcpu_sys_reg(vcpu, CNTHV_CVAL_EL2) = cval;
+		__vcpu_assign_sys_reg(vcpu, CNTHV_CVAL_EL2, cval);
 		break;
 	case TIMER_HPTIMER:
-		__vcpu_sys_reg(vcpu, CNTHP_CVAL_EL2) = cval;
+		__vcpu_assign_sys_reg(vcpu, CNTHP_CVAL_EL2, cval);
 		break;
 	default:
 		WARN_ON(1);
diff --git a/arch/arm64/kvm/hyp/exception.c b/arch/arm64/kvm/hyp/exception.c
index 424a5107cddb..6a2a899a344e 100644
--- a/arch/arm64/kvm/hyp/exception.c
+++ b/arch/arm64/kvm/hyp/exception.c
@@ -37,7 +37,7 @@ static inline void __vcpu_write_sys_reg(struct kvm_vcpu *vcpu, u64 val, int reg)
 	if (unlikely(vcpu_has_nv(vcpu)))
 		vcpu_write_sys_reg(vcpu, val, reg);
 	else if (!__vcpu_write_sys_reg_to_cpu(val, reg))
-		__vcpu_sys_reg(vcpu, reg) = val;
+		__vcpu_assign_sys_reg(vcpu, reg, val);
 }
 
 static void __vcpu_write_spsr(struct kvm_vcpu *vcpu, unsigned long target_mode,
@@ -51,7 +51,7 @@ static void __vcpu_write_spsr(struct kvm_vcpu *vcpu, unsigned long target_mode,
 	} else if (has_vhe()) {
 		write_sysreg_el1(val, SYS_SPSR);
 	} else {
-		__vcpu_sys_reg(vcpu, SPSR_EL1) = val;
+		__vcpu_assign_sys_reg(vcpu, SPSR_EL1, val);
 	}
 }
 
diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h
index eef310cdbdbd..aa5b561b9218 100644
--- a/arch/arm64/kvm/hyp/include/hyp/switch.h
+++ b/arch/arm64/kvm/hyp/include/hyp/switch.h
@@ -45,7 +45,7 @@ static inline void __fpsimd_save_fpexc32(struct kvm_vcpu *vcpu)
 	if (!vcpu_el1_is_32bit(vcpu))
 		return;
 
-	__vcpu_sys_reg(vcpu, FPEXC32_EL2) = read_sysreg(fpexc32_el2);
+	__vcpu_assign_sys_reg(vcpu, FPEXC32_EL2, read_sysreg(fpexc32_el2));
 }
 
 static inline void __activate_traps_fpsimd32(struct kvm_vcpu *vcpu)
@@ -457,7 +457,7 @@ static inline void fpsimd_lazy_switch_to_host(struct kvm_vcpu *vcpu)
 	 */
 	if (vcpu_has_sve(vcpu)) {
 		zcr_el1 = read_sysreg_el1(SYS_ZCR);
-		__vcpu_sys_reg(vcpu, vcpu_sve_zcr_elx(vcpu)) = zcr_el1;
+		__vcpu_assign_sys_reg(vcpu, vcpu_sve_zcr_elx(vcpu), zcr_el1);
 
 		/*
 		 * The guest's state is always saved using the guest's max VL.
diff --git a/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
index b9cff893bbe0..4d0dbea4c56f 100644
--- a/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
+++ b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
@@ -307,11 +307,11 @@ static inline void __sysreg32_save_state(struct kvm_vcpu *vcpu)
 	vcpu->arch.ctxt.spsr_irq = read_sysreg(spsr_irq);
 	vcpu->arch.ctxt.spsr_fiq = read_sysreg(spsr_fiq);
 
-	__vcpu_sys_reg(vcpu, DACR32_EL2) = read_sysreg(dacr32_el2);
-	__vcpu_sys_reg(vcpu, IFSR32_EL2) = read_sysreg(ifsr32_el2);
+	__vcpu_assign_sys_reg(vcpu, DACR32_EL2, read_sysreg(dacr32_el2));
+	__vcpu_assign_sys_reg(vcpu, IFSR32_EL2, read_sysreg(ifsr32_el2));
 
 	if (has_vhe() || kvm_debug_regs_in_use(vcpu))
-		__vcpu_sys_reg(vcpu, DBGVCR32_EL2) = read_sysreg(dbgvcr32_el2);
+		__vcpu_assign_sys_reg(vcpu, DBGVCR32_EL2, read_sysreg(dbgvcr32_el2));
 }
 
 static inline void __sysreg32_restore_state(struct kvm_vcpu *vcpu)
diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
index 8e8848de4d47..e9198e56e784 100644
--- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c
+++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
@@ -26,7 +26,7 @@ void __kvm_hyp_host_forward_smc(struct kvm_cpu_context *host_ctxt);
 
 static void __hyp_sve_save_guest(struct kvm_vcpu *vcpu)
 {
-	__vcpu_sys_reg(vcpu, ZCR_EL1) = read_sysreg_el1(SYS_ZCR);
+	__vcpu_assign_sys_reg(vcpu, ZCR_EL1, read_sysreg_el1(SYS_ZCR));
 	/*
 	 * On saving/restoring guest sve state, always use the maximum VL for
 	 * the guest. The layout of the data when saving the sve state depends
@@ -79,7 +79,7 @@ static void fpsimd_sve_sync(struct kvm_vcpu *vcpu)
 
 	has_fpmr = kvm_has_fpmr(kern_hyp_va(vcpu->kvm));
 	if (has_fpmr)
-		__vcpu_sys_reg(vcpu, FPMR) = read_sysreg_s(SYS_FPMR);
+		__vcpu_assign_sys_reg(vcpu, FPMR, read_sysreg_s(SYS_FPMR));
 
 	if (system_supports_sve())
 		__hyp_sve_restore_host();
diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c
index c9b330dc2066..09df2b42bc1b 100644
--- a/arch/arm64/kvm/hyp/vhe/switch.c
+++ b/arch/arm64/kvm/hyp/vhe/switch.c
@@ -223,9 +223,9 @@ static void __deactivate_traps(struct kvm_vcpu *vcpu)
 		 */
 		val = read_sysreg_el0(SYS_CNTP_CVAL);
 		if (map.direct_ptimer == vcpu_ptimer(vcpu))
-			__vcpu_sys_reg(vcpu, CNTP_CVAL_EL0) = val;
+			__vcpu_assign_sys_reg(vcpu, CNTP_CVAL_EL0, val);
 		if (map.direct_ptimer == vcpu_hptimer(vcpu))
-			__vcpu_sys_reg(vcpu, CNTHP_CVAL_EL2) = val;
+			__vcpu_assign_sys_reg(vcpu, CNTHP_CVAL_EL2, val);
 
 		offset = read_sysreg_s(SYS_CNTPOFF_EL2);
 
diff --git a/arch/arm64/kvm/hyp/vhe/sysreg-sr.c b/arch/arm64/kvm/hyp/vhe/sysreg-sr.c
index 3814b0b2c937..34c7bf7fe9de 100644
--- a/arch/arm64/kvm/hyp/vhe/sysreg-sr.c
+++ b/arch/arm64/kvm/hyp/vhe/sysreg-sr.c
@@ -18,17 +18,17 @@
 static void __sysreg_save_vel2_state(struct kvm_vcpu *vcpu)
 {
 	/* These registers are common with EL1 */
-	__vcpu_sys_reg(vcpu, PAR_EL1)	= read_sysreg(par_el1);
-	__vcpu_sys_reg(vcpu, TPIDR_EL1)	= read_sysreg(tpidr_el1);
+	__vcpu_assign_sys_reg(vcpu, PAR_EL1,	 read_sysreg(par_el1));
+	__vcpu_assign_sys_reg(vcpu, TPIDR_EL1,	 read_sysreg(tpidr_el1));
 
-	__vcpu_sys_reg(vcpu, ESR_EL2)	= read_sysreg_el1(SYS_ESR);
-	__vcpu_sys_reg(vcpu, AFSR0_EL2)	= read_sysreg_el1(SYS_AFSR0);
-	__vcpu_sys_reg(vcpu, AFSR1_EL2)	= read_sysreg_el1(SYS_AFSR1);
-	__vcpu_sys_reg(vcpu, FAR_EL2)	= read_sysreg_el1(SYS_FAR);
-	__vcpu_sys_reg(vcpu, MAIR_EL2)	= read_sysreg_el1(SYS_MAIR);
-	__vcpu_sys_reg(vcpu, VBAR_EL2)	= read_sysreg_el1(SYS_VBAR);
-	__vcpu_sys_reg(vcpu, CONTEXTIDR_EL2) = read_sysreg_el1(SYS_CONTEXTIDR);
-	__vcpu_sys_reg(vcpu, AMAIR_EL2)	= read_sysreg_el1(SYS_AMAIR);
+	__vcpu_assign_sys_reg(vcpu, ESR_EL2,	 read_sysreg_el1(SYS_ESR));
+	__vcpu_assign_sys_reg(vcpu, AFSR0_EL2,	 read_sysreg_el1(SYS_AFSR0));
+	__vcpu_assign_sys_reg(vcpu, AFSR1_EL2,	 read_sysreg_el1(SYS_AFSR1));
+	__vcpu_assign_sys_reg(vcpu, FAR_EL2,	 read_sysreg_el1(SYS_FAR));
+	__vcpu_assign_sys_reg(vcpu, MAIR_EL2,	 read_sysreg_el1(SYS_MAIR));
+	__vcpu_assign_sys_reg(vcpu, VBAR_EL2,	 read_sysreg_el1(SYS_VBAR));
+	__vcpu_assign_sys_reg(vcpu, CONTEXTIDR_EL2, read_sysreg_el1(SYS_CONTEXTIDR));
+	__vcpu_assign_sys_reg(vcpu, AMAIR_EL2,	 read_sysreg_el1(SYS_AMAIR));
 
 	/*
 	 * In VHE mode those registers are compatible between EL1 and EL2,
@@ -46,21 +46,21 @@ static void __sysreg_save_vel2_state(struct kvm_vcpu *vcpu)
 		 * are always trapped, ensuring that the in-memory
 		 * copy is always up-to-date. A small blessing...
 		 */
-		__vcpu_sys_reg(vcpu, SCTLR_EL2)	= read_sysreg_el1(SYS_SCTLR);
-		__vcpu_sys_reg(vcpu, TTBR0_EL2)	= read_sysreg_el1(SYS_TTBR0);
-		__vcpu_sys_reg(vcpu, TTBR1_EL2)	= read_sysreg_el1(SYS_TTBR1);
-		__vcpu_sys_reg(vcpu, TCR_EL2)	= read_sysreg_el1(SYS_TCR);
+		__vcpu_assign_sys_reg(vcpu, SCTLR_EL2,	 read_sysreg_el1(SYS_SCTLR));
+		__vcpu_assign_sys_reg(vcpu, TTBR0_EL2,	 read_sysreg_el1(SYS_TTBR0));
+		__vcpu_assign_sys_reg(vcpu, TTBR1_EL2,	 read_sysreg_el1(SYS_TTBR1));
+		__vcpu_assign_sys_reg(vcpu, TCR_EL2,	 read_sysreg_el1(SYS_TCR));
 
 		if (ctxt_has_tcrx(&vcpu->arch.ctxt)) {
-			__vcpu_sys_reg(vcpu, TCR2_EL2) = read_sysreg_el1(SYS_TCR2);
+			__vcpu_assign_sys_reg(vcpu, TCR2_EL2, read_sysreg_el1(SYS_TCR2));
 
 			if (ctxt_has_s1pie(&vcpu->arch.ctxt)) {
-				__vcpu_sys_reg(vcpu, PIRE0_EL2) = read_sysreg_el1(SYS_PIRE0);
-				__vcpu_sys_reg(vcpu, PIR_EL2) = read_sysreg_el1(SYS_PIR);
+				__vcpu_assign_sys_reg(vcpu, PIRE0_EL2, read_sysreg_el1(SYS_PIRE0));
+				__vcpu_assign_sys_reg(vcpu, PIR_EL2, read_sysreg_el1(SYS_PIR));
 			}
 
 			if (ctxt_has_s1poe(&vcpu->arch.ctxt))
-				__vcpu_sys_reg(vcpu, POR_EL2) = read_sysreg_el1(SYS_POR);
+				__vcpu_assign_sys_reg(vcpu, POR_EL2, read_sysreg_el1(SYS_POR));
 		}
 
 		/*
@@ -74,9 +74,9 @@ static void __sysreg_save_vel2_state(struct kvm_vcpu *vcpu)
 		__vcpu_sys_reg(vcpu, CNTHCTL_EL2) |= val;
 	}
 
-	__vcpu_sys_reg(vcpu, SP_EL2)	= read_sysreg(sp_el1);
-	__vcpu_sys_reg(vcpu, ELR_EL2)	= read_sysreg_el1(SYS_ELR);
-	__vcpu_sys_reg(vcpu, SPSR_EL2)	= read_sysreg_el1(SYS_SPSR);
+	__vcpu_assign_sys_reg(vcpu, SP_EL2,	 read_sysreg(sp_el1));
+	__vcpu_assign_sys_reg(vcpu, ELR_EL2,	 read_sysreg_el1(SYS_ELR));
+	__vcpu_assign_sys_reg(vcpu, SPSR_EL2,	 read_sysreg_el1(SYS_SPSR));
 }
 
 static void __sysreg_restore_vel2_state(struct kvm_vcpu *vcpu)
diff --git a/arch/arm64/kvm/pmu-emul.c b/arch/arm64/kvm/pmu-emul.c
index 25c29107f13f..4f0ae8073f78 100644
--- a/arch/arm64/kvm/pmu-emul.c
+++ b/arch/arm64/kvm/pmu-emul.c
@@ -178,7 +178,7 @@ static void kvm_pmu_set_pmc_value(struct kvm_pmc *pmc, u64 val, bool force)
 		val |= lower_32_bits(val);
 	}
 
-	__vcpu_sys_reg(vcpu, reg) = val;
+	__vcpu_assign_sys_reg(vcpu, reg, val);
 
 	/* Recreate the perf event to reflect the updated sample_period */
 	kvm_pmu_create_perf_event(pmc);
@@ -204,7 +204,7 @@ void kvm_pmu_set_counter_value(struct kvm_vcpu *vcpu, u64 select_idx, u64 val)
 void kvm_pmu_set_counter_value_user(struct kvm_vcpu *vcpu, u64 select_idx, u64 val)
 {
 	kvm_pmu_release_perf_event(kvm_vcpu_idx_to_pmc(vcpu, select_idx));
-	__vcpu_sys_reg(vcpu, counter_index_to_reg(select_idx)) = val;
+	__vcpu_assign_sys_reg(vcpu, counter_index_to_reg(select_idx), val);
 	kvm_make_request(KVM_REQ_RELOAD_PMU, vcpu);
 }
 
@@ -239,7 +239,7 @@ static void kvm_pmu_stop_counter(struct kvm_pmc *pmc)
 
 	reg = counter_index_to_reg(pmc->idx);
 
-	__vcpu_sys_reg(vcpu, reg) = val;
+	__vcpu_assign_sys_reg(vcpu, reg, val);
 
 	kvm_pmu_release_perf_event(pmc);
 }
@@ -503,7 +503,7 @@ static void kvm_pmu_counter_increment(struct kvm_vcpu *vcpu,
 		reg = __vcpu_sys_reg(vcpu, counter_index_to_reg(i)) + 1;
 		if (!kvm_pmc_is_64bit(pmc))
 			reg = lower_32_bits(reg);
-		__vcpu_sys_reg(vcpu, counter_index_to_reg(i)) = reg;
+		__vcpu_assign_sys_reg(vcpu, counter_index_to_reg(i), reg);
 
 		/* No overflow? move on */
 		if (kvm_pmc_has_64bit_overflow(pmc) ? reg : lower_32_bits(reg))
@@ -602,7 +602,7 @@ void kvm_pmu_handle_pmcr(struct kvm_vcpu *vcpu, u64 val)
 		kvm_make_request(KVM_REQ_RELOAD_PMU, vcpu);
 
 	/* The reset bits don't indicate any state, and shouldn't be saved. */
-	__vcpu_sys_reg(vcpu, PMCR_EL0) = val & ~(ARMV8_PMU_PMCR_C | ARMV8_PMU_PMCR_P);
+	__vcpu_assign_sys_reg(vcpu, PMCR_EL0, (val & ~(ARMV8_PMU_PMCR_C | ARMV8_PMU_PMCR_P)));
 
 	if (val & ARMV8_PMU_PMCR_C)
 		kvm_pmu_set_counter_value(vcpu, ARMV8_PMU_CYCLE_IDX, 0);
@@ -779,7 +779,7 @@ void kvm_pmu_set_counter_event_type(struct kvm_vcpu *vcpu, u64 data,
 	u64 reg;
 
 	reg = counter_index_to_evtreg(pmc->idx);
-	__vcpu_sys_reg(vcpu, reg) = data & kvm_pmu_evtyper_mask(vcpu->kvm);
+	__vcpu_assign_sys_reg(vcpu, reg, (data & kvm_pmu_evtyper_mask(vcpu->kvm)));
 
 	kvm_pmu_create_perf_event(pmc);
 }
@@ -1038,7 +1038,7 @@ static void kvm_arm_set_nr_counters(struct kvm *kvm, unsigned int nr)
 			u64 val = __vcpu_sys_reg(vcpu, MDCR_EL2);
 			val &= ~MDCR_EL2_HPMN;
 			val |= FIELD_PREP(MDCR_EL2_HPMN, kvm->arch.nr_pmu_counters);
-			__vcpu_sys_reg(vcpu, MDCR_EL2) = val;
+			__vcpu_assign_sys_reg(vcpu, MDCR_EL2, val);
 		}
 	}
 }
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 707c651aff03..93d0ca7ed936 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -228,7 +228,7 @@ void vcpu_write_sys_reg(struct kvm_vcpu *vcpu, u64 val, int reg)
 		 * to reverse-translate virtual EL2 system registers for a
 		 * non-VHE guest hypervisor.
 		 */
-		__vcpu_sys_reg(vcpu, reg) = val;
+		__vcpu_assign_sys_reg(vcpu, reg, val);
 
 		switch (reg) {
 		case CNTHCTL_EL2:
@@ -263,7 +263,7 @@ void vcpu_write_sys_reg(struct kvm_vcpu *vcpu, u64 val, int reg)
 		return;
 
 memory_write:
-	 __vcpu_sys_reg(vcpu, reg) = val;
+	__vcpu_assign_sys_reg(vcpu, reg, val);
 }
 
 /* CSSELR values; used to index KVM_REG_ARM_DEMUX_ID_CCSIDR */
@@ -605,7 +605,7 @@ static int set_oslsr_el1(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd,
 	if ((val ^ rd->val) & ~OSLSR_EL1_OSLK)
 		return -EINVAL;
 
-	__vcpu_sys_reg(vcpu, rd->reg) = val;
+	__vcpu_assign_sys_reg(vcpu, rd->reg, val);
 	return 0;
 }
 
@@ -835,7 +835,7 @@ static u64 reset_pmcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
 	 * The value of PMCR.N field is included when the
 	 * vCPU register is read via kvm_vcpu_read_pmcr().
 	 */
-	__vcpu_sys_reg(vcpu, r->reg) = pmcr;
+	__vcpu_assign_sys_reg(vcpu, r->reg, pmcr);
 
 	return __vcpu_sys_reg(vcpu, r->reg);
 }
@@ -907,7 +907,7 @@ static bool access_pmselr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 		return false;
 
 	if (p->is_write)
-		__vcpu_sys_reg(vcpu, PMSELR_EL0) = p->regval;
+		__vcpu_assign_sys_reg(vcpu, PMSELR_EL0, p->regval);
 	else
 		/* return PMSELR.SEL field */
 		p->regval = __vcpu_sys_reg(vcpu, PMSELR_EL0)
@@ -1076,7 +1076,7 @@ static int set_pmreg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r, u64 va
 {
 	u64 mask = kvm_pmu_accessible_counter_mask(vcpu);
 
-	__vcpu_sys_reg(vcpu, r->reg) = val & mask;
+	__vcpu_assign_sys_reg(vcpu, r->reg, val & mask);
 	kvm_make_request(KVM_REQ_RELOAD_PMU, vcpu);
 
 	return 0;
@@ -1185,8 +1185,8 @@ static bool access_pmuserenr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 		if (!vcpu_mode_priv(vcpu))
 			return undef_access(vcpu, p, r);
 
-		__vcpu_sys_reg(vcpu, PMUSERENR_EL0) =
-			       p->regval & ARMV8_PMU_USERENR_MASK;
+		__vcpu_assign_sys_reg(vcpu, PMUSERENR_EL0,
+				      (p->regval & ARMV8_PMU_USERENR_MASK));
 	} else {
 		p->regval = __vcpu_sys_reg(vcpu, PMUSERENR_EL0)
 			    & ARMV8_PMU_USERENR_MASK;
@@ -1237,7 +1237,7 @@ static int set_pmcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r,
 	if (!kvm_supports_32bit_el0())
 		val |= ARMV8_PMU_PMCR_LC;
 
-	__vcpu_sys_reg(vcpu, r->reg) = val;
+	__vcpu_assign_sys_reg(vcpu, r->reg, val);
 	kvm_make_request(KVM_REQ_RELOAD_PMU, vcpu);
 
 	return 0;
@@ -2207,7 +2207,7 @@ static u64 reset_clidr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
 	if (kvm_has_mte(vcpu->kvm))
 		clidr |= 2ULL << CLIDR_TTYPE_SHIFT(loc);
 
-	__vcpu_sys_reg(vcpu, r->reg) = clidr;
+	__vcpu_assign_sys_reg(vcpu, r->reg, clidr);
 
 	return __vcpu_sys_reg(vcpu, r->reg);
 }
@@ -2221,7 +2221,7 @@ static int set_clidr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd,
 	if ((val & CLIDR_EL1_RES0) || (!(ctr_el0 & CTR_EL0_IDC) && idc))
 		return -EINVAL;
 
-	__vcpu_sys_reg(vcpu, rd->reg) = val;
+	__vcpu_assign_sys_reg(vcpu, rd->reg, val);
 
 	return 0;
 }
@@ -2398,7 +2398,7 @@ static bool access_sp_el1(struct kvm_vcpu *vcpu,
 			  const struct sys_reg_desc *r)
 {
 	if (p->is_write)
-		__vcpu_sys_reg(vcpu, SP_EL1) = p->regval;
+		__vcpu_assign_sys_reg(vcpu, SP_EL1, p->regval);
 	else
 		p->regval = __vcpu_sys_reg(vcpu, SP_EL1);
 
@@ -2422,7 +2422,7 @@ static bool access_spsr(struct kvm_vcpu *vcpu,
 			const struct sys_reg_desc *r)
 {
 	if (p->is_write)
-		__vcpu_sys_reg(vcpu, SPSR_EL1) = p->regval;
+		__vcpu_assign_sys_reg(vcpu, SPSR_EL1, p->regval);
 	else
 		p->regval = __vcpu_sys_reg(vcpu, SPSR_EL1);
 
@@ -2434,7 +2434,7 @@ static bool access_cntkctl_el12(struct kvm_vcpu *vcpu,
 				const struct sys_reg_desc *r)
 {
 	if (p->is_write)
-		__vcpu_sys_reg(vcpu, CNTKCTL_EL1) = p->regval;
+		__vcpu_assign_sys_reg(vcpu, CNTKCTL_EL1, p->regval);
 	else
 		p->regval = __vcpu_sys_reg(vcpu, CNTKCTL_EL1);
 
@@ -2448,7 +2448,9 @@ static u64 reset_hcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
 	if (!cpus_have_final_cap(ARM64_HAS_HCR_NV1))
 		val |= HCR_E2H;
 
-	return __vcpu_sys_reg(vcpu, r->reg) = val;
+	__vcpu_assign_sys_reg(vcpu, r->reg, val);
+
+	return __vcpu_sys_reg(vcpu, r->reg);
 }
 
 static unsigned int __el2_visibility(const struct kvm_vcpu *vcpu,
@@ -2619,7 +2621,7 @@ static bool access_mdcr(struct kvm_vcpu *vcpu,
 		u64_replace_bits(val, hpmn, MDCR_EL2_HPMN);
 	}
 
-	__vcpu_sys_reg(vcpu, MDCR_EL2) = val;
+	__vcpu_assign_sys_reg(vcpu, MDCR_EL2, val);
 
 	/*
 	 * Request a reload of the PMU to enable/disable the counters
@@ -2748,7 +2750,7 @@ static int set_imp_id_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r,
 
 static u64 reset_mdcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
 {
-	__vcpu_sys_reg(vcpu, r->reg) = vcpu->kvm->arch.nr_pmu_counters;
+	__vcpu_assign_sys_reg(vcpu, r->reg, vcpu->kvm->arch.nr_pmu_counters);
 	return vcpu->kvm->arch.nr_pmu_counters;
 }
 
@@ -5006,7 +5008,7 @@ int kvm_sys_reg_set_user(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg,
 	if (r->set_user) {
 		ret = (r->set_user)(vcpu, r, val);
 	} else {
-		__vcpu_sys_reg(vcpu, r->reg) = val;
+		__vcpu_assign_sys_reg(vcpu, r->reg, val);
 		ret = 0;
 	}
 
diff --git a/arch/arm64/kvm/sys_regs.h b/arch/arm64/kvm/sys_regs.h
index cc6338d38766..ef97d9fc67cc 100644
--- a/arch/arm64/kvm/sys_regs.h
+++ b/arch/arm64/kvm/sys_regs.h
@@ -137,7 +137,7 @@ static inline u64 reset_unknown(struct kvm_vcpu *vcpu,
 {
 	BUG_ON(!r->reg);
 	BUG_ON(r->reg >= NR_SYS_REGS);
-	__vcpu_sys_reg(vcpu, r->reg) = 0x1de7ec7edbadc0deULL;
+	__vcpu_assign_sys_reg(vcpu, r->reg, 0x1de7ec7edbadc0deULL);
 	return __vcpu_sys_reg(vcpu, r->reg);
 }
 
@@ -145,7 +145,7 @@ static inline u64 reset_val(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
 {
 	BUG_ON(!r->reg);
 	BUG_ON(r->reg >= NR_SYS_REGS);
-	__vcpu_sys_reg(vcpu, r->reg) = r->val;
+	__vcpu_assign_sys_reg(vcpu, r->reg, r->val);
 	return __vcpu_sys_reg(vcpu, r->reg);
 }
 
diff --git a/arch/arm64/kvm/vgic/vgic-v3-nested.c b/arch/arm64/kvm/vgic/vgic-v3-nested.c
index 4f6954c30674..d22a8ad7bcc5 100644
--- a/arch/arm64/kvm/vgic/vgic-v3-nested.c
+++ b/arch/arm64/kvm/vgic/vgic-v3-nested.c
@@ -356,12 +356,12 @@ void vgic_v3_put_nested(struct kvm_vcpu *vcpu)
 	val = __vcpu_sys_reg(vcpu, ICH_HCR_EL2);
 	val &= ~ICH_HCR_EL2_EOIcount_MASK;
 	val |= (s_cpu_if->vgic_hcr & ICH_HCR_EL2_EOIcount_MASK);
-	__vcpu_sys_reg(vcpu, ICH_HCR_EL2) = val;
-	__vcpu_sys_reg(vcpu, ICH_VMCR_EL2) = s_cpu_if->vgic_vmcr;
+	__vcpu_assign_sys_reg(vcpu, ICH_HCR_EL2, val);
+	__vcpu_assign_sys_reg(vcpu, ICH_VMCR_EL2, s_cpu_if->vgic_vmcr);
 
 	for (i = 0; i < 4; i++) {
-		__vcpu_sys_reg(vcpu, ICH_AP0RN(i)) = s_cpu_if->vgic_ap0r[i];
-		__vcpu_sys_reg(vcpu, ICH_AP1RN(i)) = s_cpu_if->vgic_ap1r[i];
+		__vcpu_assign_sys_reg(vcpu, ICH_AP0RN(i), s_cpu_if->vgic_ap0r[i]);
+		__vcpu_assign_sys_reg(vcpu, ICH_AP1RN(i), s_cpu_if->vgic_ap1r[i]);
 	}
 
 	for_each_set_bit(i, &shadow_if->lr_map, kvm_vgic_global_state.nr_lr) {
@@ -370,7 +370,7 @@ void vgic_v3_put_nested(struct kvm_vcpu *vcpu)
 		val &= ~ICH_LR_STATE;
 		val |= s_cpu_if->vgic_lr[i] & ICH_LR_STATE;
 
-		__vcpu_sys_reg(vcpu, ICH_LRN(i)) = val;
+		__vcpu_assign_sys_reg(vcpu, ICH_LRN(i), val);
 		s_cpu_if->vgic_lr[i] = 0;
 	}
 

From 8800b7c4bbede3cd40831726d3f98e8080baf4df Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Tue, 3 Jun 2025 08:08:22 +0100
Subject: [PATCH 0020/1334] KVM: arm64: Add RMW specific sysreg accessor

In a number of cases, we perform a Read-Modify-Write operation on
a system register, meaning that we would apply the RESx masks twice.

Instead, provide a new accessor that performs this RMW operation,
allowing the masks to be applied exactly once per operation.

Reviewed-by: Miguel Luis <miguel.luis@oracle.com>
Reviewed-by: Oliver Upton <oliver.upton@linux.dev>
Link: https://lore.kernel.org/r/20250603070824.1192795-3-maz@kernel.org
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/kvm_host.h  | 11 +++++++++++
 arch/arm64/kvm/debug.c             |  4 ++--
 arch/arm64/kvm/hyp/vhe/sysreg-sr.c |  4 ++--
 arch/arm64/kvm/nested.c            |  2 +-
 arch/arm64/kvm/pmu-emul.c          | 10 +++++-----
 arch/arm64/kvm/sys_regs.c          | 22 +++++++++++-----------
 6 files changed, 32 insertions(+), 21 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 3b84ad91116b..8b8c649f225b 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -1118,6 +1118,17 @@ u64 kvm_vcpu_apply_reg_masks(const struct kvm_vcpu *, enum vcpu_sysreg, u64);
 		ctxt_sys_reg(ctxt, (r)) = __v;				\
 	} while (0)
 
+#define __vcpu_rmw_sys_reg(v, r, op, val)				\
+	do {								\
+		const struct kvm_cpu_context *ctxt = &(v)->arch.ctxt;	\
+		u64 __v = ctxt_sys_reg(ctxt, (r));			\
+		__v op (val);						\
+		if (vcpu_has_nv((v)) && (r) >= __SANITISED_REG_START__)	\
+			__v = kvm_vcpu_apply_reg_masks((v), (r), __v);	\
+									\
+		ctxt_sys_reg(ctxt, (r)) = __v;				\
+	} while (0)
+
 #define __vcpu_sys_reg(v,r)						\
 	(*({								\
 		const struct kvm_cpu_context *ctxt = &(v)->arch.ctxt;	\
diff --git a/arch/arm64/kvm/debug.c b/arch/arm64/kvm/debug.c
index 0e4c805e7e89..1a7dab333f55 100644
--- a/arch/arm64/kvm/debug.c
+++ b/arch/arm64/kvm/debug.c
@@ -216,9 +216,9 @@ void kvm_debug_set_guest_ownership(struct kvm_vcpu *vcpu)
 void kvm_debug_handle_oslar(struct kvm_vcpu *vcpu, u64 val)
 {
 	if (val & OSLAR_EL1_OSLK)
-		__vcpu_sys_reg(vcpu, OSLSR_EL1) |= OSLSR_EL1_OSLK;
+		__vcpu_rmw_sys_reg(vcpu, OSLSR_EL1, |=, OSLSR_EL1_OSLK);
 	else
-		__vcpu_sys_reg(vcpu, OSLSR_EL1) &= ~OSLSR_EL1_OSLK;
+		__vcpu_rmw_sys_reg(vcpu, OSLSR_EL1, &=, ~OSLSR_EL1_OSLK);
 
 	preempt_disable();
 	kvm_arch_vcpu_put(vcpu);
diff --git a/arch/arm64/kvm/hyp/vhe/sysreg-sr.c b/arch/arm64/kvm/hyp/vhe/sysreg-sr.c
index 34c7bf7fe9de..73e4bc7fde9e 100644
--- a/arch/arm64/kvm/hyp/vhe/sysreg-sr.c
+++ b/arch/arm64/kvm/hyp/vhe/sysreg-sr.c
@@ -70,8 +70,8 @@ static void __sysreg_save_vel2_state(struct kvm_vcpu *vcpu)
 		 */
 		val = read_sysreg_el1(SYS_CNTKCTL);
 		val &= CNTKCTL_VALID_BITS;
-		__vcpu_sys_reg(vcpu, CNTHCTL_EL2) &= ~CNTKCTL_VALID_BITS;
-		__vcpu_sys_reg(vcpu, CNTHCTL_EL2) |= val;
+		__vcpu_rmw_sys_reg(vcpu, CNTHCTL_EL2, &=, ~CNTKCTL_VALID_BITS);
+		__vcpu_rmw_sys_reg(vcpu, CNTHCTL_EL2, |=, val);
 	}
 
 	__vcpu_assign_sys_reg(vcpu, SP_EL2,	 read_sysreg(sp_el1));
diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c
index 4a53e4147fb0..5b191f4dc566 100644
--- a/arch/arm64/kvm/nested.c
+++ b/arch/arm64/kvm/nested.c
@@ -1757,7 +1757,7 @@ int kvm_init_nv_sysregs(struct kvm_vcpu *vcpu)
 
 out:
 	for (enum vcpu_sysreg sr = __SANITISED_REG_START__; sr < NR_SYS_REGS; sr++)
-		(void)__vcpu_sys_reg(vcpu, sr);
+		__vcpu_rmw_sys_reg(vcpu, sr, |=, 0);
 
 	return 0;
 }
diff --git a/arch/arm64/kvm/pmu-emul.c b/arch/arm64/kvm/pmu-emul.c
index 4f0ae8073f78..b03dbda7f1ab 100644
--- a/arch/arm64/kvm/pmu-emul.c
+++ b/arch/arm64/kvm/pmu-emul.c
@@ -510,7 +510,7 @@ static void kvm_pmu_counter_increment(struct kvm_vcpu *vcpu,
 			continue;
 
 		/* Mark overflow */
-		__vcpu_sys_reg(vcpu, PMOVSSET_EL0) |= BIT(i);
+		__vcpu_rmw_sys_reg(vcpu, PMOVSSET_EL0, |=, BIT(i));
 
 		if (kvm_pmu_counter_can_chain(pmc))
 			kvm_pmu_counter_increment(vcpu, BIT(i + 1),
@@ -556,7 +556,7 @@ static void kvm_pmu_perf_overflow(struct perf_event *perf_event,
 	perf_event->attr.sample_period = period;
 	perf_event->hw.sample_period = period;
 
-	__vcpu_sys_reg(vcpu, PMOVSSET_EL0) |= BIT(idx);
+	__vcpu_rmw_sys_reg(vcpu, PMOVSSET_EL0, |=, BIT(idx));
 
 	if (kvm_pmu_counter_can_chain(pmc))
 		kvm_pmu_counter_increment(vcpu, BIT(idx + 1),
@@ -914,9 +914,9 @@ void kvm_vcpu_reload_pmu(struct kvm_vcpu *vcpu)
 {
 	u64 mask = kvm_pmu_implemented_counter_mask(vcpu);
 
-	__vcpu_sys_reg(vcpu, PMOVSSET_EL0) &= mask;
-	__vcpu_sys_reg(vcpu, PMINTENSET_EL1) &= mask;
-	__vcpu_sys_reg(vcpu, PMCNTENSET_EL0) &= mask;
+	__vcpu_rmw_sys_reg(vcpu, PMOVSSET_EL0, &=, mask);
+	__vcpu_rmw_sys_reg(vcpu, PMINTENSET_EL1, &=, mask);
+	__vcpu_rmw_sys_reg(vcpu, PMCNTENSET_EL0, &=, mask);
 
 	kvm_pmu_reprogram_counter_mask(vcpu, mask);
 }
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 93d0ca7ed936..e89d345e42d0 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -791,7 +791,7 @@ static u64 reset_pmu_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
 		mask |= GENMASK(n - 1, 0);
 
 	reset_unknown(vcpu, r);
-	__vcpu_sys_reg(vcpu, r->reg) &= mask;
+	__vcpu_rmw_sys_reg(vcpu, r->reg, &=, mask);
 
 	return __vcpu_sys_reg(vcpu, r->reg);
 }
@@ -799,7 +799,7 @@ static u64 reset_pmu_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
 static u64 reset_pmevcntr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
 {
 	reset_unknown(vcpu, r);
-	__vcpu_sys_reg(vcpu, r->reg) &= GENMASK(31, 0);
+	__vcpu_rmw_sys_reg(vcpu, r->reg, &=, GENMASK(31, 0));
 
 	return __vcpu_sys_reg(vcpu, r->reg);
 }
@@ -811,7 +811,7 @@ static u64 reset_pmevtyper(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
 		return 0;
 
 	reset_unknown(vcpu, r);
-	__vcpu_sys_reg(vcpu, r->reg) &= kvm_pmu_evtyper_mask(vcpu->kvm);
+	__vcpu_rmw_sys_reg(vcpu, r->reg, &=, kvm_pmu_evtyper_mask(vcpu->kvm));
 
 	return __vcpu_sys_reg(vcpu, r->reg);
 }
@@ -819,7 +819,7 @@ static u64 reset_pmevtyper(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
 static u64 reset_pmselr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
 {
 	reset_unknown(vcpu, r);
-	__vcpu_sys_reg(vcpu, r->reg) &= PMSELR_EL0_SEL_MASK;
+	__vcpu_rmw_sys_reg(vcpu, r->reg, &=, PMSELR_EL0_SEL_MASK);
 
 	return __vcpu_sys_reg(vcpu, r->reg);
 }
@@ -1103,10 +1103,10 @@ static bool access_pmcnten(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 		val = p->regval & mask;
 		if (r->Op2 & 0x1)
 			/* accessing PMCNTENSET_EL0 */
-			__vcpu_sys_reg(vcpu, PMCNTENSET_EL0) |= val;
+			__vcpu_rmw_sys_reg(vcpu, PMCNTENSET_EL0, |=, val);
 		else
 			/* accessing PMCNTENCLR_EL0 */
-			__vcpu_sys_reg(vcpu, PMCNTENSET_EL0) &= ~val;
+			__vcpu_rmw_sys_reg(vcpu, PMCNTENSET_EL0, &=, ~val);
 
 		kvm_pmu_reprogram_counter_mask(vcpu, val);
 	} else {
@@ -1129,10 +1129,10 @@ static bool access_pminten(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 
 		if (r->Op2 & 0x1)
 			/* accessing PMINTENSET_EL1 */
-			__vcpu_sys_reg(vcpu, PMINTENSET_EL1) |= val;
+			__vcpu_rmw_sys_reg(vcpu, PMINTENSET_EL1, |=, val);
 		else
 			/* accessing PMINTENCLR_EL1 */
-			__vcpu_sys_reg(vcpu, PMINTENSET_EL1) &= ~val;
+			__vcpu_rmw_sys_reg(vcpu, PMINTENSET_EL1, &=, ~val);
 	} else {
 		p->regval = __vcpu_sys_reg(vcpu, PMINTENSET_EL1);
 	}
@@ -1151,10 +1151,10 @@ static bool access_pmovs(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 	if (p->is_write) {
 		if (r->CRm & 0x2)
 			/* accessing PMOVSSET_EL0 */
-			__vcpu_sys_reg(vcpu, PMOVSSET_EL0) |= (p->regval & mask);
+			__vcpu_rmw_sys_reg(vcpu, PMOVSSET_EL0, |=, (p->regval & mask));
 		else
 			/* accessing PMOVSCLR_EL0 */
-			__vcpu_sys_reg(vcpu, PMOVSSET_EL0) &= ~(p->regval & mask);
+			__vcpu_rmw_sys_reg(vcpu, PMOVSSET_EL0, &=, ~(p->regval & mask));
 	} else {
 		p->regval = __vcpu_sys_reg(vcpu, PMOVSSET_EL0);
 	}
@@ -4786,7 +4786,7 @@ void kvm_reset_sys_regs(struct kvm_vcpu *vcpu)
 			r->reset(vcpu, r);
 
 		if (r->reg >= __SANITISED_REG_START__ && r->reg < NR_SYS_REGS)
-			(void)__vcpu_sys_reg(vcpu, r->reg);
+			__vcpu_rmw_sys_reg(vcpu, r->reg, |=, 0);
 	}
 
 	set_bit(KVM_ARCH_FLAG_ID_REGS_INITIALIZED, &kvm->arch.flags);

From b61fae4ee120f337b8700dff43b2fd639f3bf6a5 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Tue, 3 Jun 2025 08:08:23 +0100
Subject: [PATCH 0021/1334] KVM: arm64: Don't use __vcpu_sys_reg() to get the
 address of a sysreg

We are about to prevent the use of __vcpu_sys_reg() as a lvalue,
and getting the address of a rvalue is not a thing.

Update the couple of places where we do this to use the __ctxt_sys_reg()
accessor, which return the address of a register.

Reviewed-by: Miguel Luis <miguel.luis@oracle.com>
Reviewed-by: Oliver Upton <oliver.upton@linux.dev>
Link: https://lore.kernel.org/r/20250603070824.1192795-4-maz@kernel.org
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/kvm/arch_timer.c | 2 +-
 arch/arm64/kvm/fpsimd.c     | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/arch/arm64/kvm/arch_timer.c b/arch/arm64/kvm/arch_timer.c
index 5a67a6d4d95b..c6b4fb4c8e08 100644
--- a/arch/arm64/kvm/arch_timer.c
+++ b/arch/arm64/kvm/arch_timer.c
@@ -1036,7 +1036,7 @@ void kvm_timer_vcpu_reset(struct kvm_vcpu *vcpu)
 	if (vcpu_has_nv(vcpu)) {
 		struct arch_timer_offset *offs = &vcpu_vtimer(vcpu)->offset;
 
-		offs->vcpu_offset = &__vcpu_sys_reg(vcpu, CNTVOFF_EL2);
+		offs->vcpu_offset = __ctxt_sys_reg(&vcpu->arch.ctxt, CNTVOFF_EL2);
 		offs->vm_offset = &vcpu->kvm->arch.timer_data.poffset;
 	}
 
diff --git a/arch/arm64/kvm/fpsimd.c b/arch/arm64/kvm/fpsimd.c
index 7f6e43d25691..8f6c8f57c6b9 100644
--- a/arch/arm64/kvm/fpsimd.c
+++ b/arch/arm64/kvm/fpsimd.c
@@ -103,8 +103,8 @@ void kvm_arch_vcpu_ctxsync_fp(struct kvm_vcpu *vcpu)
 		fp_state.sve_state = vcpu->arch.sve_state;
 		fp_state.sve_vl = vcpu->arch.sve_max_vl;
 		fp_state.sme_state = NULL;
-		fp_state.svcr = &__vcpu_sys_reg(vcpu, SVCR);
-		fp_state.fpmr = &__vcpu_sys_reg(vcpu, FPMR);
+		fp_state.svcr = __ctxt_sys_reg(&vcpu->arch.ctxt, SVCR);
+		fp_state.fpmr = __ctxt_sys_reg(&vcpu->arch.ctxt, FPMR);
 		fp_state.fp_type = &vcpu->arch.fp_type;
 
 		if (vcpu_has_sve(vcpu))

From b5fa1f91e11fdf74ad4e2ac6dae246a57cbd2d95 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Tue, 3 Jun 2025 08:08:24 +0100
Subject: [PATCH 0022/1334] KVM: arm64: Make __vcpu_sys_reg() a pure rvalue
 operand

Now that we don't have any use of __vcpu_sys_reg() as a lvalue,
remove the in-place update, and directly return the sanitised
value.

Reviewed-by: Miguel Luis <miguel.luis@oracle.com>
Reviewed-by: Oliver Upton <oliver.upton@linux.dev>
Link: https://lore.kernel.org/r/20250603070824.1192795-5-maz@kernel.org
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/kvm_host.h | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 8b8c649f225b..382b382d14da 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -1130,13 +1130,13 @@ u64 kvm_vcpu_apply_reg_masks(const struct kvm_vcpu *, enum vcpu_sysreg, u64);
 	} while (0)
 
 #define __vcpu_sys_reg(v,r)						\
-	(*({								\
+	({								\
 		const struct kvm_cpu_context *ctxt = &(v)->arch.ctxt;	\
-		u64 *__r = __ctxt_sys_reg(ctxt, (r));			\
+		u64 __v = ctxt_sys_reg(ctxt, (r));			\
 		if (vcpu_has_nv((v)) && (r) >= __SANITISED_REG_START__)	\
-			*__r = kvm_vcpu_apply_reg_masks((v), (r), *__r);\
-		__r;							\
-	}))
+			__v = kvm_vcpu_apply_reg_masks((v), (r), __v);	\
+		__v;							\
+	})
 
 u64 vcpu_read_sys_reg(const struct kvm_vcpu *vcpu, int reg);
 void vcpu_write_sys_reg(struct kvm_vcpu *vcpu, u64 val, int reg);

From 9a9864fd09c7e52440c05e70609bf5ee8da425d0 Mon Sep 17 00:00:00 2001
From: Sebastian Ott <sebott@redhat.com>
Date: Thu, 5 Jun 2025 12:36:10 +0200
Subject: [PATCH 0023/1334] KVM: arm64: selftests: Fix help text for
 arch_timer_edge_cases

Fix the help text for arch_timer_edge_cases to show the correct
option for setting the wait time.

Signed-off-by: Sebastian Ott <sebott@redhat.com>
Link: https://lore.kernel.org/r/20250605103613.14544-2-sebott@redhat.com
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 tools/testing/selftests/kvm/arm64/arch_timer_edge_cases.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/kvm/arm64/arch_timer_edge_cases.c b/tools/testing/selftests/kvm/arm64/arch_timer_edge_cases.c
index a36a7e2db434..c4716e0c1438 100644
--- a/tools/testing/selftests/kvm/arm64/arch_timer_edge_cases.c
+++ b/tools/testing/selftests/kvm/arm64/arch_timer_edge_cases.c
@@ -986,7 +986,7 @@ static void test_print_help(char *name)
 	pr_info("\t-b: Test both physical and virtual timers (default: true)\n");
 	pr_info("\t-l: Delta (in ms) used for long wait time test (default: %u)\n",
 	     LONG_WAIT_TEST_MS);
-	pr_info("\t-l: Delta (in ms) used for wait times (default: %u)\n",
+	pr_info("\t-w: Delta (in ms) used for wait times (default: %u)\n",
 		WAIT_TEST_MS);
 	pr_info("\t-p: Test physical timer (default: true)\n");
 	pr_info("\t-v: Test virtual timer (default: true)\n");

From 050632ae6571d0f148fa0d4b90b6409a12645461 Mon Sep 17 00:00:00 2001
From: Sebastian Ott <sebott@redhat.com>
Date: Thu, 5 Jun 2025 12:36:11 +0200
Subject: [PATCH 0024/1334] KVM: arm64: selftests: Fix thread migration in
 arch_timer_edge_cases

arch_timer_edge_cases tries to migrate itself across host cpus. Before
the first test, it migrates to cpu 0 by setting up an affinity mask with
only bit 0 set. After that it looks for the next possible cpu in the
current affinity mask which still has only bit 0 set. So there is no
migration at all.

Fix this by reading the default mask at start and use this to find
the next cpu in each iteration.

Signed-off-by: Sebastian Ott <sebott@redhat.com>
Link: https://lore.kernel.org/r/20250605103613.14544-3-sebott@redhat.com
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 tools/testing/selftests/kvm/arm64/arch_timer_edge_cases.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/tools/testing/selftests/kvm/arm64/arch_timer_edge_cases.c b/tools/testing/selftests/kvm/arm64/arch_timer_edge_cases.c
index c4716e0c1438..a813b4c6c817 100644
--- a/tools/testing/selftests/kvm/arm64/arch_timer_edge_cases.c
+++ b/tools/testing/selftests/kvm/arm64/arch_timer_edge_cases.c
@@ -849,17 +849,17 @@ static void guest_code(enum arch_timer timer)
 	GUEST_DONE();
 }
 
+static cpu_set_t default_cpuset;
+
 static uint32_t next_pcpu(void)
 {
 	uint32_t max = get_nprocs();
 	uint32_t cur = sched_getcpu();
 	uint32_t next = cur;
-	cpu_set_t cpuset;
+	cpu_set_t cpuset = default_cpuset;
 
 	TEST_ASSERT(max > 1, "Need at least two physical cpus");
 
-	sched_getaffinity(0, sizeof(cpuset), &cpuset);
-
 	do {
 		next = (next + 1) % CPU_SETSIZE;
 	} while (!CPU_ISSET(next, &cpuset));
@@ -1046,6 +1046,8 @@ int main(int argc, char *argv[])
 	if (!parse_args(argc, argv))
 		exit(KSFT_SKIP);
 
+	sched_getaffinity(0, sizeof(default_cpuset), &default_cpuset);
+
 	if (test_args.test_virtual) {
 		test_vm_create(&vm, &vcpu, VIRTUAL);
 		test_run(vm, vcpu);

From 05ce38d489dbc96eb1dd700b287f949cb8cc0610 Mon Sep 17 00:00:00 2001
From: Sebastian Ott <sebott@redhat.com>
Date: Thu, 5 Jun 2025 12:36:12 +0200
Subject: [PATCH 0025/1334] KVM: arm64: selftests: Fix xVAL init in
 arch_timer_edge_cases

arch_timer_edge_cases hits the following assertion in < 10% of the test runs:

==== Test Assertion Failure ====
  arm64/arch_timer_edge_cases.c:490: timer_get_cntct(timer) >= DEF_CNT + (timer_get_cntfrq() * (uint64_t)(delta_2_ms) / 1000)
  pid=17110 tid=17110 errno=4 - Interrupted system call
     1  0x0000000000404ec7: test_run at arch_timer_edge_cases.c:945
     2  0x0000000000401fa3: main at arch_timer_edge_cases.c:1074
     3  0x0000ffffa774b587: ?? ??:0
     4  0x0000ffffa774b65f: ?? ??:0
     5  0x000000000040206f: _start at ??:?
  timer_get_cntct(timer) >= DEF_CNT + msec_to_cycles(delta_2_ms)

Enabling the timer without proper xval initialization in set_tval_irq()
resulted in an early interrupt during timer reprogramming. Make sure
to set the xval before setting the enable bit.

Signed-off-by: Sebastian Ott <sebott@redhat.com>
Link: https://lore.kernel.org/r/20250605103613.14544-4-sebott@redhat.com
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 tools/testing/selftests/kvm/arm64/arch_timer_edge_cases.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/kvm/arm64/arch_timer_edge_cases.c b/tools/testing/selftests/kvm/arm64/arch_timer_edge_cases.c
index a813b4c6c817..be8bbedc933b 100644
--- a/tools/testing/selftests/kvm/arm64/arch_timer_edge_cases.c
+++ b/tools/testing/selftests/kvm/arm64/arch_timer_edge_cases.c
@@ -191,8 +191,8 @@ static void set_tval_irq(enum arch_timer timer, uint64_t tval_cycles,
 {
 	atomic_set(&shared_data.handled, 0);
 	atomic_set(&shared_data.spurious, 0);
-	timer_set_ctl(timer, ctl);
 	timer_set_tval(timer, tval_cycles);
+	timer_set_ctl(timer, ctl);
 }
 
 static void set_xval_irq(enum arch_timer timer, uint64_t xval, uint32_t ctl,

From fad4cf944839da7f5c3376243aa353295c88f588 Mon Sep 17 00:00:00 2001
From: Sebastian Ott <sebott@redhat.com>
Date: Thu, 5 Jun 2025 12:36:13 +0200
Subject: [PATCH 0026/1334] KVM: arm64: selftests: Determine effective counter
 width in arch_timer_edge_cases

arch_timer_edge_cases uses ~0 as the maximum counter value, however there's
no architectural guarantee that this is valid.

Figure out the effective counter width based on the effective frequency
like it's done by the kernel.

This also serves as a workaround for AC03_CPU_14 that led to the
following assertion failure on ampere-one machines:

==== Test Assertion Failure ====
  arm64/arch_timer_edge_cases.c:169: timer_condition == istatus
  pid=11236 tid=11236 errno=4 - Interrupted system call
     1  0x0000000000404ce7: test_run at arch_timer_edge_cases.c:938
     2  0x0000000000401ebb: main at arch_timer_edge_cases.c:1053
     3  0x0000ffff9fa8625b: ?? ??:0
     4  0x0000ffff9fa8633b: ?? ??:0
     5  0x0000000000401fef: _start at ??:?
  0x1 != 0x0 (timer_condition != istatus)

Note that the following subtest only worked since the counter initialized
with CVAL_MAX would instantly overflow (which is no longer the case):

	test_set_cnt_after_cval_no_irq(timer, 0, DEF_CNT, CVAL_MAX, sm);

To fix this we could swap CVAL_MAX for 0 here but since that is already
done by test_move_counters_behind_timers() let's remove that subtest.

Link: https://lore.kernel.org/kvmarm/ac1de1d2-ef2b-d439-dc48-8615e121b07b@redhat.com
Link: https://amperecomputing.com/assets/AmpereOne_Developer_ER_v0_80_20240823_28945022f4.pdf
Signed-off-by: Sebastian Ott <sebott@redhat.com>
Link: https://lore.kernel.org/r/20250605103613.14544-5-sebott@redhat.com
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 .../kvm/arm64/arch_timer_edge_cases.c         | 27 ++++++++++++-------
 1 file changed, 18 insertions(+), 9 deletions(-)

diff --git a/tools/testing/selftests/kvm/arm64/arch_timer_edge_cases.c b/tools/testing/selftests/kvm/arm64/arch_timer_edge_cases.c
index be8bbedc933b..b4d22b3ab7cc 100644
--- a/tools/testing/selftests/kvm/arm64/arch_timer_edge_cases.c
+++ b/tools/testing/selftests/kvm/arm64/arch_timer_edge_cases.c
@@ -22,7 +22,8 @@
 #include "gic.h"
 #include "vgic.h"
 
-static const uint64_t CVAL_MAX = ~0ULL;
+/* Depends on counter width. */
+static uint64_t CVAL_MAX;
 /* tval is a signed 32-bit int. */
 static const int32_t TVAL_MAX = INT32_MAX;
 static const int32_t TVAL_MIN = INT32_MIN;
@@ -30,8 +31,8 @@ static const int32_t TVAL_MIN = INT32_MIN;
 /* After how much time we say there is no IRQ. */
 static const uint32_t TIMEOUT_NO_IRQ_US = 50000;
 
-/* A nice counter value to use as the starting one for most tests. */
-static const uint64_t DEF_CNT = (CVAL_MAX / 2);
+/* Counter value to use as the starting one for most tests. Set to CVAL_MAX/2 */
+static uint64_t DEF_CNT;
 
 /* Number of runs. */
 static const uint32_t NR_TEST_ITERS_DEF = 5;
@@ -732,12 +733,6 @@ static void test_move_counters_ahead_of_timers(enum arch_timer timer)
 		test_set_cnt_after_tval(timer, 0, tval, (uint64_t) tval + 1,
 					wm);
 	}
-
-	for (i = 0; i < ARRAY_SIZE(sleep_method); i++) {
-		sleep_method_t sm = sleep_method[i];
-
-		test_set_cnt_after_cval_no_irq(timer, 0, DEF_CNT, CVAL_MAX, sm);
-	}
 }
 
 /*
@@ -975,6 +970,8 @@ static void test_vm_create(struct kvm_vm **vm, struct kvm_vcpu **vcpu,
 	test_init_timer_irq(*vm, *vcpu);
 	vgic_v3_setup(*vm, 1, 64);
 	sync_global_to_guest(*vm, test_args);
+	sync_global_to_guest(*vm, CVAL_MAX);
+	sync_global_to_guest(*vm, DEF_CNT);
 }
 
 static void test_print_help(char *name)
@@ -1035,6 +1032,17 @@ static bool parse_args(int argc, char *argv[])
 	return false;
 }
 
+static void set_counter_defaults(void)
+{
+	const uint64_t MIN_ROLLOVER_SECS = 40ULL * 365 * 24 * 3600;
+	uint64_t freq = read_sysreg(CNTFRQ_EL0);
+	uint64_t width = ilog2(MIN_ROLLOVER_SECS * freq);
+
+	width = clamp(width, 56, 64);
+	CVAL_MAX = GENMASK_ULL(width - 1, 0);
+	DEF_CNT = CVAL_MAX / 2;
+}
+
 int main(int argc, char *argv[])
 {
 	struct kvm_vcpu *vcpu;
@@ -1047,6 +1055,7 @@ int main(int argc, char *argv[])
 		exit(KSFT_SKIP);
 
 	sched_getaffinity(0, sizeof(default_cpuset), &default_cpuset);
+	set_counter_defaults();
 
 	if (test_args.test_virtual) {
 		test_vm_create(&vm, &vcpu, VIRTUAL);

From 308a3a8ce8ea41b26c46169f3263e50f5997c28e Mon Sep 17 00:00:00 2001
From: Pauli Virtanen <pav@iki.fi>
Date: Sat, 31 May 2025 18:24:58 +0300
Subject: [PATCH 0027/1334] Bluetooth: hci_core: fix list_for_each_entry_rcu
 usage

Releasing + re-acquiring RCU lock inside list_for_each_entry_rcu() loop
body is not correct.

Fix by taking the update-side hdev->lock instead.

Fixes: c7eaf80bfb0c ("Bluetooth: Fix hci_link_tx_to RCU lock usage")
Signed-off-by: Pauli Virtanen <pav@iki.fi>
Reviewed-by: Paul Menzel <pmenzel@molgen.mpg.de>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/hci_core.c | 11 +++--------
 1 file changed, 3 insertions(+), 8 deletions(-)

diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index 3b49828160b7..04845ff3ad57 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -3417,23 +3417,18 @@ static void hci_link_tx_to(struct hci_dev *hdev, __u8 type)
 
 	bt_dev_err(hdev, "link tx timeout");
 
-	rcu_read_lock();
+	hci_dev_lock(hdev);
 
 	/* Kill stalled connections */
-	list_for_each_entry_rcu(c, &h->list, list) {
+	list_for_each_entry(c, &h->list, list) {
 		if (c->type == type && c->sent) {
 			bt_dev_err(hdev, "killing stalled connection %pMR",
 				   &c->dst);
-			/* hci_disconnect might sleep, so, we have to release
-			 * the RCU read lock before calling it.
-			 */
-			rcu_read_unlock();
 			hci_disconnect(c, HCI_ERROR_REMOTE_USER_TERM);
-			rcu_read_lock();
 		}
 	}
 
-	rcu_read_unlock();
+	hci_dev_unlock(hdev);
 }
 
 static struct hci_chan *hci_chan_sent(struct hci_dev *hdev, __u8 type,

From daabd276985055250528da97e9ce6d277d7009c2 Mon Sep 17 00:00:00 2001
From: Kiran K <kiran.k@intel.com>
Date: Tue, 3 Jun 2025 15:34:38 +0530
Subject: [PATCH 0028/1334] Bluetooth: btintel_pcie: Fix driver not posting
 maximum rx buffers
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The driver was posting only 6 rx buffers, despite the maximum rx buffers
being defined as 16. Having fewer RX buffers caused firmware exceptions
in HID use cases when events arrived in bursts.

Exception seen on android 6.12 kernel.

E Bluetooth: hci0: Received hw exception interrupt
E Bluetooth: hci0: Received gp1 mailbox interrupt
D Bluetooth: hci0: 00000000: ff 3e 87 80 03 01 01 01 03 01 0c 0d 02 1c 10 0e
D Bluetooth: hci0: 00000010: 01 00 05 14 66 b0 28 b0 c0 b0 28 b0 ac af 28 b0
D Bluetooth: hci0: 00000020: 14 f1 28 b0 00 00 00 00 fa 04 00 00 00 00 40 10
D Bluetooth: hci0: 00000030: 08 00 00 00 7a 7a 7a 7a 47 00 fb a0 10 00 00 00
D Bluetooth: hci0: 00000000: 10 01 0a
E Bluetooth: hci0: ---- Dump of debug registers —
E Bluetooth: hci0: boot stage: 0xe0fb0047
E Bluetooth: hci0: ipc status: 0x00000004
E Bluetooth: hci0: ipc control: 0x00000000
E Bluetooth: hci0: ipc sleep control: 0x00000000
E Bluetooth: hci0: mbox_1: 0x00badbad
E Bluetooth: hci0: mbox_2: 0x0000101c
E Bluetooth: hci0: mbox_3: 0x00000008
E Bluetooth: hci0: mbox_4: 0x7a7a7a7a

Signed-off-by: Chandrashekar Devegowda <chandrashekar.devegowda@intel.com>
Signed-off-by: Kiran K <kiran.k@intel.com>
Fixes: c2b636b3f788 ("Bluetooth: btintel_pcie: Add support for PCIe transport")
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/btintel_pcie.c | 3 ++-
 drivers/bluetooth/btintel_pcie.h | 3 ---
 2 files changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/bluetooth/btintel_pcie.c b/drivers/bluetooth/btintel_pcie.c
index 50fe17f1e1d1..2c7731803c9f 100644
--- a/drivers/bluetooth/btintel_pcie.c
+++ b/drivers/bluetooth/btintel_pcie.c
@@ -396,8 +396,9 @@ static int btintel_pcie_submit_rx(struct btintel_pcie_data *data)
 static int btintel_pcie_start_rx(struct btintel_pcie_data *data)
 {
 	int i, ret;
+	struct rxq *rxq = &data->rxq;
 
-	for (i = 0; i < BTINTEL_PCIE_RX_MAX_QUEUE; i++) {
+	for (i = 0; i < rxq->count; i++) {
 		ret = btintel_pcie_submit_rx(data);
 		if (ret)
 			return ret;
diff --git a/drivers/bluetooth/btintel_pcie.h b/drivers/bluetooth/btintel_pcie.h
index 21b964b15c1c..5ddd6d7d8d45 100644
--- a/drivers/bluetooth/btintel_pcie.h
+++ b/drivers/bluetooth/btintel_pcie.h
@@ -177,9 +177,6 @@ enum {
 /* Doorbell vector for TFD */
 #define BTINTEL_PCIE_TX_DB_VEC	0
 
-/* Number of pending RX requests for downlink */
-#define BTINTEL_PCIE_RX_MAX_QUEUE	6
-
 /* Doorbell vector for FRBD */
 #define BTINTEL_PCIE_RX_DB_VEC	513
 

From 2dd711102ce69ae41f65d09c012441227d4aa983 Mon Sep 17 00:00:00 2001
From: Chandrashekar Devegowda <chandrashekar.devegowda@intel.com>
Date: Tue, 3 Jun 2025 15:34:39 +0530
Subject: [PATCH 0029/1334] Bluetooth: btintel_pcie: Increase the tx and rx
 descriptor count

This change addresses latency issues observed in HID use cases where
events arrive in bursts. By increasing the Rx descriptor count to 64,
the firmware can handle bursty data more effectively, reducing latency
and preventing buffer overflows.

Signed-off-by: Chandrashekar Devegowda <chandrashekar.devegowda@intel.com>
Signed-off-by: Kiran K <kiran.k@intel.com>
Fixes: c2b636b3f788 ("Bluetooth: btintel_pcie: Add support for PCIe transport")
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/btintel_pcie.c | 24 ++++++++++++------------
 drivers/bluetooth/btintel_pcie.h |  7 +++++--
 2 files changed, 17 insertions(+), 14 deletions(-)

diff --git a/drivers/bluetooth/btintel_pcie.c b/drivers/bluetooth/btintel_pcie.c
index 2c7731803c9f..03f13de4a723 100644
--- a/drivers/bluetooth/btintel_pcie.c
+++ b/drivers/bluetooth/btintel_pcie.c
@@ -1783,8 +1783,8 @@ static int btintel_pcie_alloc(struct btintel_pcie_data *data)
 	 *  + size of index * Number of queues(2) * type of index array(4)
 	 *  + size of context information
 	 */
-	total = (sizeof(struct tfd) + sizeof(struct urbd0) + sizeof(struct frbd)
-		+ sizeof(struct urbd1)) * BTINTEL_DESCS_COUNT;
+	total = (sizeof(struct tfd) + sizeof(struct urbd0)) * BTINTEL_PCIE_TX_DESCS_COUNT;
+	total += (sizeof(struct frbd) + sizeof(struct urbd1)) * BTINTEL_PCIE_RX_DESCS_COUNT;
 
 	/* Add the sum of size of index array and size of ci struct */
 	total += (sizeof(u16) * BTINTEL_PCIE_NUM_QUEUES * 4) + sizeof(struct ctx_info);
@@ -1809,36 +1809,36 @@ static int btintel_pcie_alloc(struct btintel_pcie_data *data)
 	data->dma_v_addr = v_addr;
 
 	/* Setup descriptor count */
-	data->txq.count = BTINTEL_DESCS_COUNT;
-	data->rxq.count = BTINTEL_DESCS_COUNT;
+	data->txq.count = BTINTEL_PCIE_TX_DESCS_COUNT;
+	data->rxq.count = BTINTEL_PCIE_RX_DESCS_COUNT;
 
 	/* Setup tfds */
 	data->txq.tfds_p_addr = p_addr;
 	data->txq.tfds = v_addr;
 
-	p_addr += (sizeof(struct tfd) * BTINTEL_DESCS_COUNT);
-	v_addr += (sizeof(struct tfd) * BTINTEL_DESCS_COUNT);
+	p_addr += (sizeof(struct tfd) * BTINTEL_PCIE_TX_DESCS_COUNT);
+	v_addr += (sizeof(struct tfd) * BTINTEL_PCIE_TX_DESCS_COUNT);
 
 	/* Setup urbd0 */
 	data->txq.urbd0s_p_addr = p_addr;
 	data->txq.urbd0s = v_addr;
 
-	p_addr += (sizeof(struct urbd0) * BTINTEL_DESCS_COUNT);
-	v_addr += (sizeof(struct urbd0) * BTINTEL_DESCS_COUNT);
+	p_addr += (sizeof(struct urbd0) * BTINTEL_PCIE_TX_DESCS_COUNT);
+	v_addr += (sizeof(struct urbd0) * BTINTEL_PCIE_TX_DESCS_COUNT);
 
 	/* Setup FRBD*/
 	data->rxq.frbds_p_addr = p_addr;
 	data->rxq.frbds = v_addr;
 
-	p_addr += (sizeof(struct frbd) * BTINTEL_DESCS_COUNT);
-	v_addr += (sizeof(struct frbd) * BTINTEL_DESCS_COUNT);
+	p_addr += (sizeof(struct frbd) * BTINTEL_PCIE_RX_DESCS_COUNT);
+	v_addr += (sizeof(struct frbd) * BTINTEL_PCIE_RX_DESCS_COUNT);
 
 	/* Setup urbd1 */
 	data->rxq.urbd1s_p_addr = p_addr;
 	data->rxq.urbd1s = v_addr;
 
-	p_addr += (sizeof(struct urbd1) * BTINTEL_DESCS_COUNT);
-	v_addr += (sizeof(struct urbd1) * BTINTEL_DESCS_COUNT);
+	p_addr += (sizeof(struct urbd1) * BTINTEL_PCIE_RX_DESCS_COUNT);
+	v_addr += (sizeof(struct urbd1) * BTINTEL_PCIE_RX_DESCS_COUNT);
 
 	/* Setup data buffers for txq */
 	err = btintel_pcie_setup_txq_bufs(data, &data->txq);
diff --git a/drivers/bluetooth/btintel_pcie.h b/drivers/bluetooth/btintel_pcie.h
index 5ddd6d7d8d45..7dad4523236c 100644
--- a/drivers/bluetooth/btintel_pcie.h
+++ b/drivers/bluetooth/btintel_pcie.h
@@ -154,8 +154,11 @@ enum msix_mbox_int_causes {
 /* Default interrupt timeout in msec */
 #define BTINTEL_DEFAULT_INTR_TIMEOUT_MS	3000
 
-/* The number of descriptors in TX/RX queues */
-#define BTINTEL_DESCS_COUNT	16
+/* The number of descriptors in TX queues */
+#define BTINTEL_PCIE_TX_DESCS_COUNT	32
+
+/* The number of descriptors in RX queues */
+#define BTINTEL_PCIE_RX_DESCS_COUNT	64
 
 /* Number of Queue for TX and RX
  * It indicates the index of the IA(Index Array)

From bf2ffc4d14db29cab781549912d2dc69127f4d3e Mon Sep 17 00:00:00 2001
From: Chandrashekar Devegowda <chandrashekar.devegowda@intel.com>
Date: Tue, 3 Jun 2025 15:34:40 +0530
Subject: [PATCH 0030/1334] Bluetooth: btintel_pcie: Reduce driver buffer
 posting to prevent race condition

Modify the driver to post 3 fewer buffers than the maximum rx buffers
(64) allowed for the firmware. This change mitigates a hardware issue
causing a race condition in the firmware, improving stability and data
handling.

Signed-off-by: Chandrashekar Devegowda <chandrashekar.devegowda@intel.com>
Signed-off-by: Kiran K <kiran.k@intel.com>
Fixes: c2b636b3f788 ("Bluetooth: btintel_pcie: Add support for PCIe transport")
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/btintel_pcie.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/bluetooth/btintel_pcie.c b/drivers/bluetooth/btintel_pcie.c
index 03f13de4a723..563165c5efae 100644
--- a/drivers/bluetooth/btintel_pcie.c
+++ b/drivers/bluetooth/btintel_pcie.c
@@ -398,7 +398,11 @@ static int btintel_pcie_start_rx(struct btintel_pcie_data *data)
 	int i, ret;
 	struct rxq *rxq = &data->rxq;
 
-	for (i = 0; i < rxq->count; i++) {
+	/* Post (BTINTEL_PCIE_RX_DESCS_COUNT - 3) buffers to overcome the
+	 * hardware issues leading to race condition at the firmware.
+	 */
+
+	for (i = 0; i < rxq->count - 3; i++) {
 		ret = btintel_pcie_submit_rx(data);
 		if (ret)
 			return ret;

From e6ed54e86aae9e4f7286ce8d5c73780f91b48d1c Mon Sep 17 00:00:00 2001
From: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Date: Tue, 3 Jun 2025 16:12:39 -0400
Subject: [PATCH 0031/1334] Bluetooth: MGMT: Fix UAF on
 mgmt_remove_adv_monitor_complete

This reworks MGMT_OP_REMOVE_ADV_MONITOR to not use mgmt_pending_add to
avoid crashes like bellow:

==================================================================
BUG: KASAN: slab-use-after-free in mgmt_remove_adv_monitor_complete+0xe5/0x540 net/bluetooth/mgmt.c:5406
Read of size 8 at addr ffff88801c53f318 by task kworker/u5:5/5341

CPU: 0 UID: 0 PID: 5341 Comm: kworker/u5:5 Not tainted 6.15.0-syzkaller-10402-g4cb6c8af8591 #0 PREEMPT(full)
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.3-debian-1.16.3-2~bpo12+1 04/01/2014
Workqueue: hci0 hci_cmd_sync_work
Call Trace:
 <TASK>
 dump_stack_lvl+0x189/0x250 lib/dump_stack.c:120
 print_address_description mm/kasan/report.c:408 [inline]
 print_report+0xd2/0x2b0 mm/kasan/report.c:521
 kasan_report+0x118/0x150 mm/kasan/report.c:634
 mgmt_remove_adv_monitor_complete+0xe5/0x540 net/bluetooth/mgmt.c:5406
 hci_cmd_sync_work+0x261/0x3a0 net/bluetooth/hci_sync.c:334
 process_one_work kernel/workqueue.c:3238 [inline]
 process_scheduled_works+0xade/0x17b0 kernel/workqueue.c:3321
 worker_thread+0x8a0/0xda0 kernel/workqueue.c:3402
 kthread+0x711/0x8a0 kernel/kthread.c:464
 ret_from_fork+0x3fc/0x770 arch/x86/kernel/process.c:148
 ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:245
 </TASK>

Allocated by task 5987:
 kasan_save_stack mm/kasan/common.c:47 [inline]
 kasan_save_track+0x3e/0x80 mm/kasan/common.c:68
 poison_kmalloc_redzone mm/kasan/common.c:377 [inline]
 __kasan_kmalloc+0x93/0xb0 mm/kasan/common.c:394
 kasan_kmalloc include/linux/kasan.h:260 [inline]
 __kmalloc_cache_noprof+0x230/0x3d0 mm/slub.c:4358
 kmalloc_noprof include/linux/slab.h:905 [inline]
 kzalloc_noprof include/linux/slab.h:1039 [inline]
 mgmt_pending_new+0x65/0x240 net/bluetooth/mgmt_util.c:252
 mgmt_pending_add+0x34/0x120 net/bluetooth/mgmt_util.c:279
 remove_adv_monitor+0x103/0x1b0 net/bluetooth/mgmt.c:5454
 hci_mgmt_cmd+0x9c9/0xef0 net/bluetooth/hci_sock.c:1719
 hci_sock_sendmsg+0x6ca/0xef0 net/bluetooth/hci_sock.c:1839
 sock_sendmsg_nosec net/socket.c:712 [inline]
 __sock_sendmsg+0x219/0x270 net/socket.c:727
 sock_write_iter+0x258/0x330 net/socket.c:1131
 new_sync_write fs/read_write.c:593 [inline]
 vfs_write+0x548/0xa90 fs/read_write.c:686
 ksys_write+0x145/0x250 fs/read_write.c:738
 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline]
 do_syscall_64+0xfa/0x3b0 arch/x86/entry/syscall_64.c:94
 entry_SYSCALL_64_after_hwframe+0x77/0x7f

Freed by task 5989:
 kasan_save_stack mm/kasan/common.c:47 [inline]
 kasan_save_track+0x3e/0x80 mm/kasan/common.c:68
 kasan_save_free_info+0x46/0x50 mm/kasan/generic.c:576
 poison_slab_object mm/kasan/common.c:247 [inline]
 __kasan_slab_free+0x62/0x70 mm/kasan/common.c:264
 kasan_slab_free include/linux/kasan.h:233 [inline]
 slab_free_hook mm/slub.c:2380 [inline]
 slab_free mm/slub.c:4642 [inline]
 kfree+0x18e/0x440 mm/slub.c:4841
 mgmt_pending_foreach+0xc9/0x120 net/bluetooth/mgmt_util.c:242
 mgmt_index_removed+0x10d/0x2f0 net/bluetooth/mgmt.c:9366
 hci_sock_bind+0xbe9/0x1000 net/bluetooth/hci_sock.c:1314
 __sys_bind_socket net/socket.c:1810 [inline]
 __sys_bind+0x2c3/0x3e0 net/socket.c:1841
 __do_sys_bind net/socket.c:1846 [inline]
 __se_sys_bind net/socket.c:1844 [inline]
 __x64_sys_bind+0x7a/0x90 net/socket.c:1844
 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline]
 do_syscall_64+0xfa/0x3b0 arch/x86/entry/syscall_64.c:94
 entry_SYSCALL_64_after_hwframe+0x77/0x7f

Fixes: 66bd095ab5d4 ("Bluetooth: advmon offload MSFT remove monitor")
Closes: https://syzkaller.appspot.com/bug?extid=feb0dc579bbe30a13190
Reported-by: syzbot+feb0dc579bbe30a13190@syzkaller.appspotmail.com
Tested-by: syzbot+feb0dc579bbe30a13190@syzkaller.appspotmail.com
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 include/net/bluetooth/hci_core.h |  1 -
 net/bluetooth/hci_core.c         |  4 +---
 net/bluetooth/mgmt.c             | 37 ++++++++++----------------------
 3 files changed, 12 insertions(+), 30 deletions(-)

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 2b261e74e2c4..93fcb659f0d4 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -2400,7 +2400,6 @@ void mgmt_advertising_added(struct sock *sk, struct hci_dev *hdev,
 			    u8 instance);
 void mgmt_advertising_removed(struct sock *sk, struct hci_dev *hdev,
 			      u8 instance);
-void mgmt_adv_monitor_removed(struct hci_dev *hdev, u16 handle);
 int mgmt_phy_configuration_changed(struct hci_dev *hdev, struct sock *skip);
 void mgmt_adv_monitor_device_lost(struct hci_dev *hdev, u16 handle,
 				  bdaddr_t *bdaddr, u8 addr_type);
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index 04845ff3ad57..aeda2e4557d5 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -1877,10 +1877,8 @@ void hci_free_adv_monitor(struct hci_dev *hdev, struct adv_monitor *monitor)
 	if (monitor->handle)
 		idr_remove(&hdev->adv_monitors_idr, monitor->handle);
 
-	if (monitor->state != ADV_MONITOR_STATE_NOT_REGISTERED) {
+	if (monitor->state != ADV_MONITOR_STATE_NOT_REGISTERED)
 		hdev->adv_monitors_cnt--;
-		mgmt_adv_monitor_removed(hdev, monitor->handle);
-	}
 
 	kfree(monitor);
 }
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 14a9462fced5..feaeec2423ae 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -5108,24 +5108,14 @@ static void mgmt_adv_monitor_added(struct sock *sk, struct hci_dev *hdev,
 	mgmt_event(MGMT_EV_ADV_MONITOR_ADDED, hdev, &ev, sizeof(ev), sk);
 }
 
-void mgmt_adv_monitor_removed(struct hci_dev *hdev, u16 handle)
+static void mgmt_adv_monitor_removed(struct sock *sk, struct hci_dev *hdev,
+				     u16 handle)
 {
 	struct mgmt_ev_adv_monitor_removed ev;
-	struct mgmt_pending_cmd *cmd;
-	struct sock *sk_skip = NULL;
-	struct mgmt_cp_remove_adv_monitor *cp;
-
-	cmd = pending_find(MGMT_OP_REMOVE_ADV_MONITOR, hdev);
-	if (cmd) {
-		cp = cmd->param;
-
-		if (cp->monitor_handle)
-			sk_skip = cmd->sk;
-	}
 
 	ev.monitor_handle = cpu_to_le16(handle);
 
-	mgmt_event(MGMT_EV_ADV_MONITOR_REMOVED, hdev, &ev, sizeof(ev), sk_skip);
+	mgmt_event(MGMT_EV_ADV_MONITOR_REMOVED, hdev, &ev, sizeof(ev), sk);
 }
 
 static int read_adv_mon_features(struct sock *sk, struct hci_dev *hdev,
@@ -5227,8 +5217,7 @@ static int __add_adv_patterns_monitor(struct sock *sk, struct hci_dev *hdev,
 
 	if (pending_find(MGMT_OP_SET_LE, hdev) ||
 	    pending_find(MGMT_OP_ADD_ADV_PATTERNS_MONITOR, hdev) ||
-	    pending_find(MGMT_OP_ADD_ADV_PATTERNS_MONITOR_RSSI, hdev) ||
-	    pending_find(MGMT_OP_REMOVE_ADV_MONITOR, hdev)) {
+	    pending_find(MGMT_OP_ADD_ADV_PATTERNS_MONITOR_RSSI, hdev)) {
 		status = MGMT_STATUS_BUSY;
 		goto unlock;
 	}
@@ -5398,8 +5387,7 @@ static void mgmt_remove_adv_monitor_complete(struct hci_dev *hdev,
 	struct mgmt_pending_cmd *cmd = data;
 	struct mgmt_cp_remove_adv_monitor *cp;
 
-	if (status == -ECANCELED ||
-	    cmd != pending_find(MGMT_OP_REMOVE_ADV_MONITOR, hdev))
+	if (status == -ECANCELED)
 		return;
 
 	hci_dev_lock(hdev);
@@ -5408,12 +5396,14 @@ static void mgmt_remove_adv_monitor_complete(struct hci_dev *hdev,
 
 	rp.monitor_handle = cp->monitor_handle;
 
-	if (!status)
+	if (!status) {
+		mgmt_adv_monitor_removed(cmd->sk, hdev, cp->monitor_handle);
 		hci_update_passive_scan(hdev);
+	}
 
 	mgmt_cmd_complete(cmd->sk, cmd->index, cmd->opcode,
 			  mgmt_status(status), &rp, sizeof(rp));
-	mgmt_pending_remove(cmd);
+	mgmt_pending_free(cmd);
 
 	hci_dev_unlock(hdev);
 	bt_dev_dbg(hdev, "remove monitor %d complete, status %d",
@@ -5423,10 +5413,6 @@ static void mgmt_remove_adv_monitor_complete(struct hci_dev *hdev,
 static int mgmt_remove_adv_monitor_sync(struct hci_dev *hdev, void *data)
 {
 	struct mgmt_pending_cmd *cmd = data;
-
-	if (cmd != pending_find(MGMT_OP_REMOVE_ADV_MONITOR, hdev))
-		return -ECANCELED;
-
 	struct mgmt_cp_remove_adv_monitor *cp = cmd->param;
 	u16 handle = __le16_to_cpu(cp->monitor_handle);
 
@@ -5445,14 +5431,13 @@ static int remove_adv_monitor(struct sock *sk, struct hci_dev *hdev,
 	hci_dev_lock(hdev);
 
 	if (pending_find(MGMT_OP_SET_LE, hdev) ||
-	    pending_find(MGMT_OP_REMOVE_ADV_MONITOR, hdev) ||
 	    pending_find(MGMT_OP_ADD_ADV_PATTERNS_MONITOR, hdev) ||
 	    pending_find(MGMT_OP_ADD_ADV_PATTERNS_MONITOR_RSSI, hdev)) {
 		status = MGMT_STATUS_BUSY;
 		goto unlock;
 	}
 
-	cmd = mgmt_pending_add(sk, MGMT_OP_REMOVE_ADV_MONITOR, hdev, data, len);
+	cmd = mgmt_pending_new(sk, MGMT_OP_REMOVE_ADV_MONITOR, hdev, data, len);
 	if (!cmd) {
 		status = MGMT_STATUS_NO_RESOURCES;
 		goto unlock;
@@ -5462,7 +5447,7 @@ static int remove_adv_monitor(struct sock *sk, struct hci_dev *hdev,
 				  mgmt_remove_adv_monitor_complete);
 
 	if (err) {
-		mgmt_pending_remove(cmd);
+		mgmt_pending_free(cmd);
 
 		if (err == -ENOMEM)
 			status = MGMT_STATUS_NO_RESOURCES;

From 6fe26f694c824b8a4dbf50c635bee1302e3f099c Mon Sep 17 00:00:00 2001
From: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Date: Tue, 20 May 2025 15:42:21 -0400
Subject: [PATCH 0032/1334] Bluetooth: MGMT: Protect mgmt_pending list with its
 own lock

This uses a mutex to protect from concurrent access of mgmt_pending
list which can cause crashes like:

==================================================================
BUG: KASAN: slab-use-after-free in hci_sock_get_channel+0x60/0x68 net/bluetooth/hci_sock.c:91
Read of size 2 at addr ffff0000c48885b2 by task syz.4.334/7318

CPU: 0 UID: 0 PID: 7318 Comm: syz.4.334 Not tainted 6.15.0-rc7-syzkaller-g187899f4124a #0 PREEMPT
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 02/12/2025
Call trace:
 show_stack+0x2c/0x3c arch/arm64/kernel/stacktrace.c:466 (C)
 __dump_stack+0x30/0x40 lib/dump_stack.c:94
 dump_stack_lvl+0xd8/0x12c lib/dump_stack.c:120
 print_address_description+0xa8/0x254 mm/kasan/report.c:408
 print_report+0x68/0x84 mm/kasan/report.c:521
 kasan_report+0xb0/0x110 mm/kasan/report.c:634
 __asan_report_load2_noabort+0x20/0x2c mm/kasan/report_generic.c:379
 hci_sock_get_channel+0x60/0x68 net/bluetooth/hci_sock.c:91
 mgmt_pending_find+0x7c/0x140 net/bluetooth/mgmt_util.c:223
 pending_find net/bluetooth/mgmt.c:947 [inline]
 remove_adv_monitor+0x44/0x1a4 net/bluetooth/mgmt.c:5445
 hci_mgmt_cmd+0x780/0xc00 net/bluetooth/hci_sock.c:1712
 hci_sock_sendmsg+0x544/0xbb0 net/bluetooth/hci_sock.c:1832
 sock_sendmsg_nosec net/socket.c:712 [inline]
 __sock_sendmsg net/socket.c:727 [inline]
 sock_write_iter+0x25c/0x378 net/socket.c:1131
 new_sync_write fs/read_write.c:591 [inline]
 vfs_write+0x62c/0x97c fs/read_write.c:684
 ksys_write+0x120/0x210 fs/read_write.c:736
 __do_sys_write fs/read_write.c:747 [inline]
 __se_sys_write fs/read_write.c:744 [inline]
 __arm64_sys_write+0x7c/0x90 fs/read_write.c:744
 __invoke_syscall arch/arm64/kernel/syscall.c:35 [inline]
 invoke_syscall+0x98/0x2b8 arch/arm64/kernel/syscall.c:49
 el0_svc_common+0x130/0x23c arch/arm64/kernel/syscall.c:132
 do_el0_svc+0x48/0x58 arch/arm64/kernel/syscall.c:151
 el0_svc+0x58/0x17c arch/arm64/kernel/entry-common.c:767
 el0t_64_sync_handler+0x78/0x108 arch/arm64/kernel/entry-common.c:786
 el0t_64_sync+0x198/0x19c arch/arm64/kernel/entry.S:600

Allocated by task 7037:
 kasan_save_stack mm/kasan/common.c:47 [inline]
 kasan_save_track+0x40/0x78 mm/kasan/common.c:68
 kasan_save_alloc_info+0x44/0x54 mm/kasan/generic.c:562
 poison_kmalloc_redzone mm/kasan/common.c:377 [inline]
 __kasan_kmalloc+0x9c/0xb4 mm/kasan/common.c:394
 kasan_kmalloc include/linux/kasan.h:260 [inline]
 __do_kmalloc_node mm/slub.c:4327 [inline]
 __kmalloc_noprof+0x2fc/0x4c8 mm/slub.c:4339
 kmalloc_noprof include/linux/slab.h:909 [inline]
 sk_prot_alloc+0xc4/0x1f0 net/core/sock.c:2198
 sk_alloc+0x44/0x3ac net/core/sock.c:2254
 bt_sock_alloc+0x4c/0x300 net/bluetooth/af_bluetooth.c:148
 hci_sock_create+0xa8/0x194 net/bluetooth/hci_sock.c:2202
 bt_sock_create+0x14c/0x24c net/bluetooth/af_bluetooth.c:132
 __sock_create+0x43c/0x91c net/socket.c:1541
 sock_create net/socket.c:1599 [inline]
 __sys_socket_create net/socket.c:1636 [inline]
 __sys_socket+0xd4/0x1c0 net/socket.c:1683
 __do_sys_socket net/socket.c:1697 [inline]
 __se_sys_socket net/socket.c:1695 [inline]
 __arm64_sys_socket+0x7c/0x94 net/socket.c:1695
 __invoke_syscall arch/arm64/kernel/syscall.c:35 [inline]
 invoke_syscall+0x98/0x2b8 arch/arm64/kernel/syscall.c:49
 el0_svc_common+0x130/0x23c arch/arm64/kernel/syscall.c:132
 do_el0_svc+0x48/0x58 arch/arm64/kernel/syscall.c:151
 el0_svc+0x58/0x17c arch/arm64/kernel/entry-common.c:767
 el0t_64_sync_handler+0x78/0x108 arch/arm64/kernel/entry-common.c:786
 el0t_64_sync+0x198/0x19c arch/arm64/kernel/entry.S:600

Freed by task 6607:
 kasan_save_stack mm/kasan/common.c:47 [inline]
 kasan_save_track+0x40/0x78 mm/kasan/common.c:68
 kasan_save_free_info+0x58/0x70 mm/kasan/generic.c:576
 poison_slab_object mm/kasan/common.c:247 [inline]
 __kasan_slab_free+0x68/0x88 mm/kasan/common.c:264
 kasan_slab_free include/linux/kasan.h:233 [inline]
 slab_free_hook mm/slub.c:2380 [inline]
 slab_free mm/slub.c:4642 [inline]
 kfree+0x17c/0x474 mm/slub.c:4841
 sk_prot_free net/core/sock.c:2237 [inline]
 __sk_destruct+0x4f4/0x760 net/core/sock.c:2332
 sk_destruct net/core/sock.c:2360 [inline]
 __sk_free+0x320/0x430 net/core/sock.c:2371
 sk_free+0x60/0xc8 net/core/sock.c:2382
 sock_put include/net/sock.h:1944 [inline]
 mgmt_pending_free+0x88/0x118 net/bluetooth/mgmt_util.c:290
 mgmt_pending_remove+0xec/0x104 net/bluetooth/mgmt_util.c:298
 mgmt_set_powered_complete+0x418/0x5cc net/bluetooth/mgmt.c:1355
 hci_cmd_sync_work+0x204/0x33c net/bluetooth/hci_sync.c:334
 process_one_work+0x7e8/0x156c kernel/workqueue.c:3238
 process_scheduled_works kernel/workqueue.c:3319 [inline]
 worker_thread+0x958/0xed8 kernel/workqueue.c:3400
 kthread+0x5fc/0x75c kernel/kthread.c:464
 ret_from_fork+0x10/0x20 arch/arm64/kernel/entry.S:847

Fixes: a380b6cff1a2 ("Bluetooth: Add generic mgmt helper API")
Closes: https://syzkaller.appspot.com/bug?extid=0a7039d5d9986ff4ecec
Closes: https://syzkaller.appspot.com/bug?extid=cc0cc52e7f43dc9e6df1
Reported-by: syzbot+0a7039d5d9986ff4ecec@syzkaller.appspotmail.com
Tested-by: syzbot+0a7039d5d9986ff4ecec@syzkaller.appspotmail.com
Tested-by: syzbot+cc0cc52e7f43dc9e6df1@syzkaller.appspotmail.com
Signed-off-by: Dmitry Antipov <dmantipov@yandex.ru>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 include/net/bluetooth/hci_core.h |   1 +
 net/bluetooth/hci_core.c         |   1 +
 net/bluetooth/mgmt.c             | 101 +++++++++++++++----------------
 net/bluetooth/mgmt_util.c        |  32 ++++++++--
 net/bluetooth/mgmt_util.h        |   4 +-
 5 files changed, 80 insertions(+), 59 deletions(-)

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 93fcb659f0d4..f7b1a9eb9543 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -546,6 +546,7 @@ struct hci_dev {
 	struct hci_conn_hash	conn_hash;
 
 	struct list_head	mesh_pending;
+	struct mutex		mgmt_pending_lock;
 	struct list_head	mgmt_pending;
 	struct list_head	reject_list;
 	struct list_head	accept_list;
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index aeda2e4557d5..487c045a7ba8 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -2485,6 +2485,7 @@ struct hci_dev *hci_alloc_dev_priv(int sizeof_priv)
 
 	mutex_init(&hdev->lock);
 	mutex_init(&hdev->req_lock);
+	mutex_init(&hdev->mgmt_pending_lock);
 
 	ida_init(&hdev->unset_handle_ida);
 
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index feaeec2423ae..de7adb9a47f9 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -1447,22 +1447,17 @@ static void settings_rsp(struct mgmt_pending_cmd *cmd, void *data)
 
 	send_settings_rsp(cmd->sk, cmd->opcode, match->hdev);
 
-	list_del(&cmd->list);
-
 	if (match->sk == NULL) {
 		match->sk = cmd->sk;
 		sock_hold(match->sk);
 	}
-
-	mgmt_pending_free(cmd);
 }
 
 static void cmd_status_rsp(struct mgmt_pending_cmd *cmd, void *data)
 {
 	u8 *status = data;
 
-	mgmt_cmd_status(cmd->sk, cmd->index, cmd->opcode, *status);
-	mgmt_pending_remove(cmd);
+	mgmt_cmd_status(cmd->sk, cmd->hdev->id, cmd->opcode, *status);
 }
 
 static void cmd_complete_rsp(struct mgmt_pending_cmd *cmd, void *data)
@@ -1476,8 +1471,6 @@ static void cmd_complete_rsp(struct mgmt_pending_cmd *cmd, void *data)
 
 	if (cmd->cmd_complete) {
 		cmd->cmd_complete(cmd, match->mgmt_status);
-		mgmt_pending_remove(cmd);
-
 		return;
 	}
 
@@ -1486,13 +1479,13 @@ static void cmd_complete_rsp(struct mgmt_pending_cmd *cmd, void *data)
 
 static int generic_cmd_complete(struct mgmt_pending_cmd *cmd, u8 status)
 {
-	return mgmt_cmd_complete(cmd->sk, cmd->index, cmd->opcode, status,
+	return mgmt_cmd_complete(cmd->sk, cmd->hdev->id, cmd->opcode, status,
 				 cmd->param, cmd->param_len);
 }
 
 static int addr_cmd_complete(struct mgmt_pending_cmd *cmd, u8 status)
 {
-	return mgmt_cmd_complete(cmd->sk, cmd->index, cmd->opcode, status,
+	return mgmt_cmd_complete(cmd->sk, cmd->hdev->id, cmd->opcode, status,
 				 cmd->param, sizeof(struct mgmt_addr_info));
 }
 
@@ -1532,7 +1525,7 @@ static void mgmt_set_discoverable_complete(struct hci_dev *hdev, void *data,
 
 	if (err) {
 		u8 mgmt_err = mgmt_status(err);
-		mgmt_cmd_status(cmd->sk, cmd->index, cmd->opcode, mgmt_err);
+		mgmt_cmd_status(cmd->sk, cmd->hdev->id, cmd->opcode, mgmt_err);
 		hci_dev_clear_flag(hdev, HCI_LIMITED_DISCOVERABLE);
 		goto done;
 	}
@@ -1707,7 +1700,7 @@ static void mgmt_set_connectable_complete(struct hci_dev *hdev, void *data,
 
 	if (err) {
 		u8 mgmt_err = mgmt_status(err);
-		mgmt_cmd_status(cmd->sk, cmd->index, cmd->opcode, mgmt_err);
+		mgmt_cmd_status(cmd->sk, cmd->hdev->id, cmd->opcode, mgmt_err);
 		goto done;
 	}
 
@@ -1943,8 +1936,8 @@ static void set_ssp_complete(struct hci_dev *hdev, void *data, int err)
 			new_settings(hdev, NULL);
 		}
 
-		mgmt_pending_foreach(MGMT_OP_SET_SSP, hdev, cmd_status_rsp,
-				     &mgmt_err);
+		mgmt_pending_foreach(MGMT_OP_SET_SSP, hdev, true,
+				     cmd_status_rsp, &mgmt_err);
 		return;
 	}
 
@@ -1954,7 +1947,7 @@ static void set_ssp_complete(struct hci_dev *hdev, void *data, int err)
 		changed = hci_dev_test_and_clear_flag(hdev, HCI_SSP_ENABLED);
 	}
 
-	mgmt_pending_foreach(MGMT_OP_SET_SSP, hdev, settings_rsp, &match);
+	mgmt_pending_foreach(MGMT_OP_SET_SSP, hdev, true, settings_rsp, &match);
 
 	if (changed)
 		new_settings(hdev, match.sk);
@@ -2074,12 +2067,12 @@ static void set_le_complete(struct hci_dev *hdev, void *data, int err)
 	bt_dev_dbg(hdev, "err %d", err);
 
 	if (status) {
-		mgmt_pending_foreach(MGMT_OP_SET_LE, hdev, cmd_status_rsp,
-							&status);
+		mgmt_pending_foreach(MGMT_OP_SET_LE, hdev, true, cmd_status_rsp,
+				     &status);
 		return;
 	}
 
-	mgmt_pending_foreach(MGMT_OP_SET_LE, hdev, settings_rsp, &match);
+	mgmt_pending_foreach(MGMT_OP_SET_LE, hdev, true, settings_rsp, &match);
 
 	new_settings(hdev, match.sk);
 
@@ -2138,7 +2131,7 @@ static void set_mesh_complete(struct hci_dev *hdev, void *data, int err)
 	struct sock *sk = cmd->sk;
 
 	if (status) {
-		mgmt_pending_foreach(MGMT_OP_SET_MESH_RECEIVER, hdev,
+		mgmt_pending_foreach(MGMT_OP_SET_MESH_RECEIVER, hdev, true,
 				     cmd_status_rsp, &status);
 		return;
 	}
@@ -2638,7 +2631,7 @@ static void mgmt_class_complete(struct hci_dev *hdev, void *data, int err)
 
 	bt_dev_dbg(hdev, "err %d", err);
 
-	mgmt_cmd_complete(cmd->sk, cmd->index, cmd->opcode,
+	mgmt_cmd_complete(cmd->sk, cmd->hdev->id, cmd->opcode,
 			  mgmt_status(err), hdev->dev_class, 3);
 
 	mgmt_pending_free(cmd);
@@ -3427,7 +3420,7 @@ static int pairing_complete(struct mgmt_pending_cmd *cmd, u8 status)
 	bacpy(&rp.addr.bdaddr, &conn->dst);
 	rp.addr.type = link_to_bdaddr(conn->type, conn->dst_type);
 
-	err = mgmt_cmd_complete(cmd->sk, cmd->index, MGMT_OP_PAIR_DEVICE,
+	err = mgmt_cmd_complete(cmd->sk, cmd->hdev->id, MGMT_OP_PAIR_DEVICE,
 				status, &rp, sizeof(rp));
 
 	/* So we don't get further callbacks for this connection */
@@ -5186,7 +5179,7 @@ static void mgmt_add_adv_patterns_monitor_complete(struct hci_dev *hdev,
 		hci_update_passive_scan(hdev);
 	}
 
-	mgmt_cmd_complete(cmd->sk, cmd->index, cmd->opcode,
+	mgmt_cmd_complete(cmd->sk, cmd->hdev->id, cmd->opcode,
 			  mgmt_status(status), &rp, sizeof(rp));
 	mgmt_pending_remove(cmd);
 
@@ -5401,7 +5394,7 @@ static void mgmt_remove_adv_monitor_complete(struct hci_dev *hdev,
 		hci_update_passive_scan(hdev);
 	}
 
-	mgmt_cmd_complete(cmd->sk, cmd->index, cmd->opcode,
+	mgmt_cmd_complete(cmd->sk, cmd->hdev->id, cmd->opcode,
 			  mgmt_status(status), &rp, sizeof(rp));
 	mgmt_pending_free(cmd);
 
@@ -5777,7 +5770,7 @@ static void start_discovery_complete(struct hci_dev *hdev, void *data, int err)
 	    cmd != pending_find(MGMT_OP_START_SERVICE_DISCOVERY, hdev))
 		return;
 
-	mgmt_cmd_complete(cmd->sk, cmd->index, cmd->opcode, mgmt_status(err),
+	mgmt_cmd_complete(cmd->sk, cmd->hdev->id, cmd->opcode, mgmt_status(err),
 			  cmd->param, 1);
 	mgmt_pending_remove(cmd);
 
@@ -5998,7 +5991,7 @@ static void stop_discovery_complete(struct hci_dev *hdev, void *data, int err)
 
 	bt_dev_dbg(hdev, "err %d", err);
 
-	mgmt_cmd_complete(cmd->sk, cmd->index, cmd->opcode, mgmt_status(err),
+	mgmt_cmd_complete(cmd->sk, cmd->hdev->id, cmd->opcode, mgmt_status(err),
 			  cmd->param, 1);
 	mgmt_pending_remove(cmd);
 
@@ -6223,7 +6216,7 @@ static void set_advertising_complete(struct hci_dev *hdev, void *data, int err)
 	u8 status = mgmt_status(err);
 
 	if (status) {
-		mgmt_pending_foreach(MGMT_OP_SET_ADVERTISING, hdev,
+		mgmt_pending_foreach(MGMT_OP_SET_ADVERTISING, hdev, true,
 				     cmd_status_rsp, &status);
 		return;
 	}
@@ -6233,7 +6226,7 @@ static void set_advertising_complete(struct hci_dev *hdev, void *data, int err)
 	else
 		hci_dev_clear_flag(hdev, HCI_ADVERTISING);
 
-	mgmt_pending_foreach(MGMT_OP_SET_ADVERTISING, hdev, settings_rsp,
+	mgmt_pending_foreach(MGMT_OP_SET_ADVERTISING, hdev, true, settings_rsp,
 			     &match);
 
 	new_settings(hdev, match.sk);
@@ -6577,7 +6570,7 @@ static void set_bredr_complete(struct hci_dev *hdev, void *data, int err)
 		 */
 		hci_dev_clear_flag(hdev, HCI_BREDR_ENABLED);
 
-		mgmt_cmd_status(cmd->sk, cmd->index, cmd->opcode, mgmt_err);
+		mgmt_cmd_status(cmd->sk, cmd->hdev->id, cmd->opcode, mgmt_err);
 	} else {
 		send_settings_rsp(cmd->sk, MGMT_OP_SET_BREDR, hdev);
 		new_settings(hdev, cmd->sk);
@@ -6714,7 +6707,7 @@ static void set_secure_conn_complete(struct hci_dev *hdev, void *data, int err)
 	if (err) {
 		u8 mgmt_err = mgmt_status(err);
 
-		mgmt_cmd_status(cmd->sk, cmd->index, cmd->opcode, mgmt_err);
+		mgmt_cmd_status(cmd->sk, cmd->hdev->id, cmd->opcode, mgmt_err);
 		goto done;
 	}
 
@@ -7161,7 +7154,7 @@ static void get_conn_info_complete(struct hci_dev *hdev, void *data, int err)
 		rp.max_tx_power = HCI_TX_POWER_INVALID;
 	}
 
-	mgmt_cmd_complete(cmd->sk, cmd->index, MGMT_OP_GET_CONN_INFO, status,
+	mgmt_cmd_complete(cmd->sk, cmd->hdev->id, MGMT_OP_GET_CONN_INFO, status,
 			  &rp, sizeof(rp));
 
 	mgmt_pending_free(cmd);
@@ -7321,7 +7314,7 @@ static void get_clock_info_complete(struct hci_dev *hdev, void *data, int err)
 	}
 
 complete:
-	mgmt_cmd_complete(cmd->sk, cmd->index, cmd->opcode, status, &rp,
+	mgmt_cmd_complete(cmd->sk, cmd->hdev->id, cmd->opcode, status, &rp,
 			  sizeof(rp));
 
 	mgmt_pending_free(cmd);
@@ -8571,10 +8564,10 @@ static void add_advertising_complete(struct hci_dev *hdev, void *data, int err)
 	rp.instance = cp->instance;
 
 	if (err)
-		mgmt_cmd_status(cmd->sk, cmd->index, cmd->opcode,
+		mgmt_cmd_status(cmd->sk, cmd->hdev->id, cmd->opcode,
 				mgmt_status(err));
 	else
-		mgmt_cmd_complete(cmd->sk, cmd->index, cmd->opcode,
+		mgmt_cmd_complete(cmd->sk, cmd->hdev->id, cmd->opcode,
 				  mgmt_status(err), &rp, sizeof(rp));
 
 	add_adv_complete(hdev, cmd->sk, cp->instance, err);
@@ -8762,10 +8755,10 @@ static void add_ext_adv_params_complete(struct hci_dev *hdev, void *data,
 
 		hci_remove_adv_instance(hdev, cp->instance);
 
-		mgmt_cmd_status(cmd->sk, cmd->index, cmd->opcode,
+		mgmt_cmd_status(cmd->sk, cmd->hdev->id, cmd->opcode,
 				mgmt_status(err));
 	} else {
-		mgmt_cmd_complete(cmd->sk, cmd->index, cmd->opcode,
+		mgmt_cmd_complete(cmd->sk, cmd->hdev->id, cmd->opcode,
 				  mgmt_status(err), &rp, sizeof(rp));
 	}
 
@@ -8912,10 +8905,10 @@ static void add_ext_adv_data_complete(struct hci_dev *hdev, void *data, int err)
 	rp.instance = cp->instance;
 
 	if (err)
-		mgmt_cmd_status(cmd->sk, cmd->index, cmd->opcode,
+		mgmt_cmd_status(cmd->sk, cmd->hdev->id, cmd->opcode,
 				mgmt_status(err));
 	else
-		mgmt_cmd_complete(cmd->sk, cmd->index, cmd->opcode,
+		mgmt_cmd_complete(cmd->sk, cmd->hdev->id, cmd->opcode,
 				  mgmt_status(err), &rp, sizeof(rp));
 
 	mgmt_pending_free(cmd);
@@ -9074,10 +9067,10 @@ static void remove_advertising_complete(struct hci_dev *hdev, void *data,
 	rp.instance = cp->instance;
 
 	if (err)
-		mgmt_cmd_status(cmd->sk, cmd->index, cmd->opcode,
+		mgmt_cmd_status(cmd->sk, cmd->hdev->id, cmd->opcode,
 				mgmt_status(err));
 	else
-		mgmt_cmd_complete(cmd->sk, cmd->index, cmd->opcode,
+		mgmt_cmd_complete(cmd->sk, cmd->hdev->id, cmd->opcode,
 				  MGMT_STATUS_SUCCESS, &rp, sizeof(rp));
 
 	mgmt_pending_free(cmd);
@@ -9349,7 +9342,7 @@ void mgmt_index_removed(struct hci_dev *hdev)
 	if (test_bit(HCI_QUIRK_RAW_DEVICE, &hdev->quirks))
 		return;
 
-	mgmt_pending_foreach(0, hdev, cmd_complete_rsp, &match);
+	mgmt_pending_foreach(0, hdev, true, cmd_complete_rsp, &match);
 
 	if (hci_dev_test_flag(hdev, HCI_UNCONFIGURED)) {
 		mgmt_index_event(MGMT_EV_UNCONF_INDEX_REMOVED, hdev, NULL, 0,
@@ -9387,7 +9380,8 @@ void mgmt_power_on(struct hci_dev *hdev, int err)
 		hci_update_passive_scan(hdev);
 	}
 
-	mgmt_pending_foreach(MGMT_OP_SET_POWERED, hdev, settings_rsp, &match);
+	mgmt_pending_foreach(MGMT_OP_SET_POWERED, hdev, true, settings_rsp,
+			     &match);
 
 	new_settings(hdev, match.sk);
 
@@ -9402,7 +9396,8 @@ void __mgmt_power_off(struct hci_dev *hdev)
 	struct cmd_lookup match = { NULL, hdev };
 	u8 zero_cod[] = { 0, 0, 0 };
 
-	mgmt_pending_foreach(MGMT_OP_SET_POWERED, hdev, settings_rsp, &match);
+	mgmt_pending_foreach(MGMT_OP_SET_POWERED, hdev, true, settings_rsp,
+			     &match);
 
 	/* If the power off is because of hdev unregistration let
 	 * use the appropriate INVALID_INDEX status. Otherwise use
@@ -9416,7 +9411,7 @@ void __mgmt_power_off(struct hci_dev *hdev)
 	else
 		match.mgmt_status = MGMT_STATUS_NOT_POWERED;
 
-	mgmt_pending_foreach(0, hdev, cmd_complete_rsp, &match);
+	mgmt_pending_foreach(0, hdev, true, cmd_complete_rsp, &match);
 
 	if (memcmp(hdev->dev_class, zero_cod, sizeof(zero_cod)) != 0) {
 		mgmt_limited_event(MGMT_EV_CLASS_OF_DEV_CHANGED, hdev,
@@ -9657,7 +9652,6 @@ static void unpair_device_rsp(struct mgmt_pending_cmd *cmd, void *data)
 	device_unpaired(hdev, &cp->addr.bdaddr, cp->addr.type, cmd->sk);
 
 	cmd->cmd_complete(cmd, 0);
-	mgmt_pending_remove(cmd);
 }
 
 bool mgmt_powering_down(struct hci_dev *hdev)
@@ -9713,8 +9707,8 @@ void mgmt_disconnect_failed(struct hci_dev *hdev, bdaddr_t *bdaddr,
 	struct mgmt_cp_disconnect *cp;
 	struct mgmt_pending_cmd *cmd;
 
-	mgmt_pending_foreach(MGMT_OP_UNPAIR_DEVICE, hdev, unpair_device_rsp,
-			     hdev);
+	mgmt_pending_foreach(MGMT_OP_UNPAIR_DEVICE, hdev, true,
+			     unpair_device_rsp, hdev);
 
 	cmd = pending_find(MGMT_OP_DISCONNECT, hdev);
 	if (!cmd)
@@ -9907,7 +9901,7 @@ void mgmt_auth_enable_complete(struct hci_dev *hdev, u8 status)
 
 	if (status) {
 		u8 mgmt_err = mgmt_status(status);
-		mgmt_pending_foreach(MGMT_OP_SET_LINK_SECURITY, hdev,
+		mgmt_pending_foreach(MGMT_OP_SET_LINK_SECURITY, hdev, true,
 				     cmd_status_rsp, &mgmt_err);
 		return;
 	}
@@ -9917,8 +9911,8 @@ void mgmt_auth_enable_complete(struct hci_dev *hdev, u8 status)
 	else
 		changed = hci_dev_test_and_clear_flag(hdev, HCI_LINK_SECURITY);
 
-	mgmt_pending_foreach(MGMT_OP_SET_LINK_SECURITY, hdev, settings_rsp,
-			     &match);
+	mgmt_pending_foreach(MGMT_OP_SET_LINK_SECURITY, hdev, true,
+			     settings_rsp, &match);
 
 	if (changed)
 		new_settings(hdev, match.sk);
@@ -9942,9 +9936,12 @@ void mgmt_set_class_of_dev_complete(struct hci_dev *hdev, u8 *dev_class,
 {
 	struct cmd_lookup match = { NULL, hdev, mgmt_status(status) };
 
-	mgmt_pending_foreach(MGMT_OP_SET_DEV_CLASS, hdev, sk_lookup, &match);
-	mgmt_pending_foreach(MGMT_OP_ADD_UUID, hdev, sk_lookup, &match);
-	mgmt_pending_foreach(MGMT_OP_REMOVE_UUID, hdev, sk_lookup, &match);
+	mgmt_pending_foreach(MGMT_OP_SET_DEV_CLASS, hdev, false, sk_lookup,
+			     &match);
+	mgmt_pending_foreach(MGMT_OP_ADD_UUID, hdev, false, sk_lookup,
+			     &match);
+	mgmt_pending_foreach(MGMT_OP_REMOVE_UUID, hdev, false, sk_lookup,
+			     &match);
 
 	if (!status) {
 		mgmt_limited_event(MGMT_EV_CLASS_OF_DEV_CHANGED, hdev, dev_class,
diff --git a/net/bluetooth/mgmt_util.c b/net/bluetooth/mgmt_util.c
index 3713ff490c65..a88a07da3947 100644
--- a/net/bluetooth/mgmt_util.c
+++ b/net/bluetooth/mgmt_util.c
@@ -217,30 +217,47 @@ int mgmt_cmd_complete(struct sock *sk, u16 index, u16 cmd, u8 status,
 struct mgmt_pending_cmd *mgmt_pending_find(unsigned short channel, u16 opcode,
 					   struct hci_dev *hdev)
 {
-	struct mgmt_pending_cmd *cmd;
+	struct mgmt_pending_cmd *cmd, *tmp;
 
-	list_for_each_entry(cmd, &hdev->mgmt_pending, list) {
+	mutex_lock(&hdev->mgmt_pending_lock);
+
+	list_for_each_entry_safe(cmd, tmp, &hdev->mgmt_pending, list) {
 		if (hci_sock_get_channel(cmd->sk) != channel)
 			continue;
-		if (cmd->opcode == opcode)
+
+		if (cmd->opcode == opcode) {
+			mutex_unlock(&hdev->mgmt_pending_lock);
 			return cmd;
+		}
 	}
 
+	mutex_unlock(&hdev->mgmt_pending_lock);
+
 	return NULL;
 }
 
-void mgmt_pending_foreach(u16 opcode, struct hci_dev *hdev,
+void mgmt_pending_foreach(u16 opcode, struct hci_dev *hdev, bool remove,
 			  void (*cb)(struct mgmt_pending_cmd *cmd, void *data),
 			  void *data)
 {
 	struct mgmt_pending_cmd *cmd, *tmp;
 
+	mutex_lock(&hdev->mgmt_pending_lock);
+
 	list_for_each_entry_safe(cmd, tmp, &hdev->mgmt_pending, list) {
 		if (opcode > 0 && cmd->opcode != opcode)
 			continue;
 
+		if (remove)
+			list_del(&cmd->list);
+
 		cb(cmd, data);
+
+		if (remove)
+			mgmt_pending_free(cmd);
 	}
+
+	mutex_unlock(&hdev->mgmt_pending_lock);
 }
 
 struct mgmt_pending_cmd *mgmt_pending_new(struct sock *sk, u16 opcode,
@@ -254,7 +271,7 @@ struct mgmt_pending_cmd *mgmt_pending_new(struct sock *sk, u16 opcode,
 		return NULL;
 
 	cmd->opcode = opcode;
-	cmd->index = hdev->id;
+	cmd->hdev = hdev;
 
 	cmd->param = kmemdup(data, len, GFP_KERNEL);
 	if (!cmd->param) {
@@ -280,7 +297,9 @@ struct mgmt_pending_cmd *mgmt_pending_add(struct sock *sk, u16 opcode,
 	if (!cmd)
 		return NULL;
 
+	mutex_lock(&hdev->mgmt_pending_lock);
 	list_add_tail(&cmd->list, &hdev->mgmt_pending);
+	mutex_unlock(&hdev->mgmt_pending_lock);
 
 	return cmd;
 }
@@ -294,7 +313,10 @@ void mgmt_pending_free(struct mgmt_pending_cmd *cmd)
 
 void mgmt_pending_remove(struct mgmt_pending_cmd *cmd)
 {
+	mutex_lock(&cmd->hdev->mgmt_pending_lock);
 	list_del(&cmd->list);
+	mutex_unlock(&cmd->hdev->mgmt_pending_lock);
+
 	mgmt_pending_free(cmd);
 }
 
diff --git a/net/bluetooth/mgmt_util.h b/net/bluetooth/mgmt_util.h
index f2ba994ab1d8..024e51dd6937 100644
--- a/net/bluetooth/mgmt_util.h
+++ b/net/bluetooth/mgmt_util.h
@@ -33,7 +33,7 @@ struct mgmt_mesh_tx {
 struct mgmt_pending_cmd {
 	struct list_head list;
 	u16 opcode;
-	int index;
+	struct hci_dev *hdev;
 	void *param;
 	size_t param_len;
 	struct sock *sk;
@@ -54,7 +54,7 @@ int mgmt_cmd_complete(struct sock *sk, u16 index, u16 cmd, u8 status,
 
 struct mgmt_pending_cmd *mgmt_pending_find(unsigned short channel, u16 opcode,
 					   struct hci_dev *hdev);
-void mgmt_pending_foreach(u16 opcode, struct hci_dev *hdev,
+void mgmt_pending_foreach(u16 opcode, struct hci_dev *hdev, bool remove,
 			  void (*cb)(struct mgmt_pending_cmd *cmd, void *data),
 			  void *data);
 struct mgmt_pending_cmd *mgmt_pending_add(struct sock *sk, u16 opcode,

From 400123bd0107175e92a9780b97f7a5934eb0a991 Mon Sep 17 00:00:00 2001
From: Andrej Picej <andrej.picej@norik.com>
Date: Thu, 29 May 2025 07:36:53 +0200
Subject: [PATCH 0033/1334] dt-bindings: drm/bridge: ti-sn65dsi83: drop $ref to
 fix lvds-vod* warnings

The kernel test robot reported a warning related to the use of "$ref"
type definitions for custom endpoint properties
- "ti,lvds-vod-swing-clock-microvolt" and
- "ti,lvds-vod-swing-data-microvolt".

Using "$ref" with "uint32-array" is not correctly handled in this
context. Removing "$ref" and relying solely on "maxItems: 2" enforces
the intended requirement of specifying exactly two values, without
triggering a schema validation warning.

Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202505021937.efnQPPqx-lkp@intel.com/
Signed-off-by: Andrej Picej <andrej.picej@norik.com>
Link: https://lore.kernel.org/r/20250529053654.1754926-1-andrej.picej@norik.com
Signed-off-by: Rob Herring (Arm) <robh@kernel.org>
---
 .../devicetree/bindings/display/bridge/ti,sn65dsi83.yaml      | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/Documentation/devicetree/bindings/display/bridge/ti,sn65dsi83.yaml b/Documentation/devicetree/bindings/display/bridge/ti,sn65dsi83.yaml
index 9b5f3f3eab19..e69b6343a8eb 100644
--- a/Documentation/devicetree/bindings/display/bridge/ti,sn65dsi83.yaml
+++ b/Documentation/devicetree/bindings/display/bridge/ti,sn65dsi83.yaml
@@ -118,15 +118,11 @@ $defs:
           ti,lvds-vod-swing-clock-microvolt:
             description: LVDS diferential output voltage <min max> for clock
               lanes in microvolts.
-            $ref: /schemas/types.yaml#/definitions/uint32-array
-            minItems: 2
             maxItems: 2
 
           ti,lvds-vod-swing-data-microvolt:
             description: LVDS diferential output voltage <min max> for data
               lanes in microvolts.
-            $ref: /schemas/types.yaml#/definitions/uint32-array
-            minItems: 2
             maxItems: 2
 
 allOf:

From 692eb9f8a5b71d852e873375d20cf5da7a046ea6 Mon Sep 17 00:00:00 2001
From: Jonas Gorski <jonas.gorski@gmail.com>
Date: Mon, 2 Jun 2025 21:49:14 +0200
Subject: [PATCH 0034/1334] net: dsa: b53: fix untagged traffic sent via cpu
 tagged with VID 0

When Linux sends out untagged traffic from a port, it will enter the CPU
port without any VLAN tag, even if the port is a member of a vlan
filtering bridge with a PVID egress untagged VLAN.

This makes the CPU port's PVID take effect, and the PVID's VLAN
table entry controls if the packet will be tagged on egress.

Since commit 45e9d59d3950 ("net: dsa: b53: do not allow to configure
VLAN 0") we remove bridged ports from VLAN 0 when joining or leaving a
VLAN aware bridge. But we also clear the untagged bit, causing untagged
traffic from the controller to become tagged with VID 0 (and priority
0).

Fix this by not touching the untagged map of VLAN 0. Additionally,
always keep the CPU port as a member, as the untag map is only effective
as long as there is at least one member, and we would remove it when
bridging all ports and leaving no standalone ports.

Since Linux (and the switch) treats VLAN 0 tagged traffic like untagged,
the actual impact of this is rather low, but this also prevented earlier
detection of the issue.

Fixes: 45e9d59d3950 ("net: dsa: b53: do not allow to configure VLAN 0")
Signed-off-by: Jonas Gorski <jonas.gorski@gmail.com>
Reviewed-by: Florian Fainelli <florian.fainelli@broadcom.com>
Reviewed-by: Vladimir Oltean <olteanv@gmail.com>
Link: https://patch.msgid.link/20250602194914.1011890-1-jonas.gorski@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/dsa/b53/b53_common.c | 6 +-----
 1 file changed, 1 insertion(+), 5 deletions(-)

diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c
index 862bdccb7439..dc2f4adac9bc 100644
--- a/drivers/net/dsa/b53/b53_common.c
+++ b/drivers/net/dsa/b53/b53_common.c
@@ -2034,9 +2034,6 @@ int b53_br_join(struct dsa_switch *ds, int port, struct dsa_bridge bridge,
 
 		b53_get_vlan_entry(dev, pvid, vl);
 		vl->members &= ~BIT(port);
-		if (vl->members == BIT(cpu_port))
-			vl->members &= ~BIT(cpu_port);
-		vl->untag = vl->members;
 		b53_set_vlan_entry(dev, pvid, vl);
 	}
 
@@ -2115,8 +2112,7 @@ void b53_br_leave(struct dsa_switch *ds, int port, struct dsa_bridge bridge)
 		}
 
 		b53_get_vlan_entry(dev, pvid, vl);
-		vl->members |= BIT(port) | BIT(cpu_port);
-		vl->untag |= BIT(port) | BIT(cpu_port);
+		vl->members |= BIT(port);
 		b53_set_vlan_entry(dev, pvid, vl);
 	}
 }

From 87f7ce260a3c838b49e1dc1ceedf1006795157a2 Mon Sep 17 00:00:00 2001
From: Jeongjun Park <aha310510@gmail.com>
Date: Wed, 21 May 2025 01:07:17 +0900
Subject: [PATCH 0035/1334] ptp: remove ptp->n_vclocks check logic in
 ptp_vclock_in_use()

There is no disagreement that we should check both ptp->is_virtual_clock
and ptp->n_vclocks to check if the ptp virtual clock is in use.

However, when we acquire ptp->n_vclocks_mux to read ptp->n_vclocks in
ptp_vclock_in_use(), we observe a recursive lock in the call trace
starting from n_vclocks_store().

============================================
WARNING: possible recursive locking detected
6.15.0-rc6 #1 Not tainted
--------------------------------------------
syz.0.1540/13807 is trying to acquire lock:
ffff888035a24868 (&ptp->n_vclocks_mux){+.+.}-{4:4}, at:
 ptp_vclock_in_use drivers/ptp/ptp_private.h:103 [inline]
ffff888035a24868 (&ptp->n_vclocks_mux){+.+.}-{4:4}, at:
 ptp_clock_unregister+0x21/0x250 drivers/ptp/ptp_clock.c:415

but task is already holding lock:
ffff888030704868 (&ptp->n_vclocks_mux){+.+.}-{4:4}, at:
 n_vclocks_store+0xf1/0x6d0 drivers/ptp/ptp_sysfs.c:215

other info that might help us debug this:
 Possible unsafe locking scenario:

       CPU0
       ----
  lock(&ptp->n_vclocks_mux);
  lock(&ptp->n_vclocks_mux);

 *** DEADLOCK ***
....
============================================

The best way to solve this is to remove the logic that checks
ptp->n_vclocks in ptp_vclock_in_use().

The reason why this is appropriate is that any path that uses
ptp->n_vclocks must unconditionally check if ptp->n_vclocks is greater
than 0 before unregistering vclocks, and all functions are already
written this way. And in the function that uses ptp->n_vclocks, we
already get ptp->n_vclocks_mux before unregistering vclocks.

Therefore, we need to remove the redundant check for ptp->n_vclocks in
ptp_vclock_in_use() to prevent recursive locking.

Fixes: 73f37068d540 ("ptp: support ptp physical/virtual clocks conversion")
Signed-off-by: Jeongjun Park <aha310510@gmail.com>
Acked-by: Richard Cochran <richardcochran@gmail.com>
Link: https://patch.msgid.link/20250520160717.7350-1-aha310510@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/ptp/ptp_private.h | 12 +-----------
 1 file changed, 1 insertion(+), 11 deletions(-)

diff --git a/drivers/ptp/ptp_private.h b/drivers/ptp/ptp_private.h
index 18934e28469e..528d86a33f37 100644
--- a/drivers/ptp/ptp_private.h
+++ b/drivers/ptp/ptp_private.h
@@ -98,17 +98,7 @@ static inline int queue_cnt(const struct timestamp_event_queue *q)
 /* Check if ptp virtual clock is in use */
 static inline bool ptp_vclock_in_use(struct ptp_clock *ptp)
 {
-	bool in_use = false;
-
-	if (mutex_lock_interruptible(&ptp->n_vclocks_mux))
-		return true;
-
-	if (!ptp->is_virtual_clock && ptp->n_vclocks)
-		in_use = true;
-
-	mutex_unlock(&ptp->n_vclocks_mux);
-
-	return in_use;
+	return !ptp->is_virtual_clock;
 }
 
 /* Check if ptp clock shall be free running */

From 800d0b9b6a8b1b354637b4194cc167ad1ce2bdd3 Mon Sep 17 00:00:00 2001
From: Stephen Smalley <stephen.smalley.work@gmail.com>
Date: Thu, 5 Jun 2025 12:51:16 -0400
Subject: [PATCH 0036/1334] fs/xattr.c: fix simple_xattr_list()

commit 8b0ba61df5a1 ("fs/xattr.c: fix simple_xattr_list to always
include security.* xattrs") failed to reset err after the call to
security_inode_listsecurity(), which returns the length of the
returned xattr name. This results in simple_xattr_list() incorrectly
returning this length even if a POSIX acl is also set on the inode.

Reported-by: Collin Funk <collin.funk1@gmail.com>
Closes: https://lore.kernel.org/selinux/8734ceal7q.fsf@gmail.com/
Reported-by: Paul Eggert <eggert@cs.ucla.edu>
Closes: https://bugzilla.redhat.com/show_bug.cgi?id=2369561
Fixes: 8b0ba61df5a1 ("fs/xattr.c: fix simple_xattr_list to always include security.* xattrs")

Signed-off-by: Stephen Smalley <stephen.smalley.work@gmail.com>
Link: https://lore.kernel.org/20250605165116.2063-1-stephen.smalley.work@gmail.com
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/xattr.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/fs/xattr.c b/fs/xattr.c
index 8ec5b0204bfd..600ae97969cf 100644
--- a/fs/xattr.c
+++ b/fs/xattr.c
@@ -1479,6 +1479,7 @@ ssize_t simple_xattr_list(struct inode *inode, struct simple_xattrs *xattrs,
 		buffer += err;
 	}
 	remaining_size -= err;
+	err = 0;
 
 	read_lock(&xattrs->lock);
 	for (rbp = rb_first(&xattrs->rb_root); rbp; rbp = rb_next(rbp)) {

From 82cbd06f327f3c2ccdee990bd356c9303ae168f9 Mon Sep 17 00:00:00 2001
From: Wei Fang <wei.fang@nxp.com>
Date: Thu, 5 Jun 2025 14:08:36 +0800
Subject: [PATCH 0037/1334] net: enetc: fix the netc-lib driver build
 dependency

The kernel robot reported the following errors when the netc-lib driver
was compiled as a loadable module and the enetc-core driver was built-in.

ld.lld: error: undefined symbol: ntmp_init_cbdr
referenced by enetc_cbdr.c:88 (drivers/net/ethernet/freescale/enetc/enetc_cbdr.c:88)
ld.lld: error: undefined symbol: ntmp_free_cbdr
referenced by enetc_cbdr.c:96 (drivers/net/ethernet/freescale/enetc/enetc_cbdr.c:96)

Simply changing "tristate" to "bool" can fix this issue, but considering
that the netc-lib driver needs to support being compiled as a loadable
module and LS1028 does not need the netc-lib driver. Therefore, we add a
boolean symbol 'NXP_NTMP' to enable 'NXP_NETC_LIB' as needed. And when
adding NETC switch driver support in the future, there is no need to
modify the dependency, just select "NXP_NTMP" and "NXP_NETC_LIB" at the
same time.

Reported-by: Arnd Bergmann <arnd@kernel.org>
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202505220734.x6TF6oHR-lkp@intel.com/
Fixes: 4701073c3deb ("net: enetc: add initial netc-lib driver to support NTMP")
Suggested-by: Arnd Bergmann <arnd@kernel.org>
Signed-off-by: Wei Fang <wei.fang@nxp.com>
Reviewed-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/enetc/Kconfig | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/freescale/enetc/Kconfig b/drivers/net/ethernet/freescale/enetc/Kconfig
index e917132d3714..54b0f0a5a6bb 100644
--- a/drivers/net/ethernet/freescale/enetc/Kconfig
+++ b/drivers/net/ethernet/freescale/enetc/Kconfig
@@ -1,6 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 config FSL_ENETC_CORE
 	tristate
+	select NXP_NETC_LIB if NXP_NTMP
 	help
 	  This module supports common functionality between the PF and VF
 	  drivers for the NXP ENETC controller.
@@ -22,6 +23,9 @@ config NXP_NETC_LIB
 	  Switch, such as NETC Table Management Protocol (NTMP) 2.0, common tc
 	  flower and debugfs interfaces and so on.
 
+config NXP_NTMP
+	bool
+
 config FSL_ENETC
 	tristate "ENETC PF driver"
 	depends on PCI_MSI
@@ -45,7 +49,7 @@ config NXP_ENETC4
 	select FSL_ENETC_CORE
 	select FSL_ENETC_MDIO
 	select NXP_ENETC_PF_COMMON
-	select NXP_NETC_LIB
+	select NXP_NTMP
 	select PHYLINK
 	select DIMLIB
 	help

From 11fcf368506d347088e613edf6cd2604d70c454f Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= <thomas.weissschuh@linutronix.de>
Date: Fri, 6 Jun 2025 10:23:57 +0200
Subject: [PATCH 0038/1334] uapi: bitops: use UAPI-safe variant of
 BITS_PER_LONG again
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Commit 1e7933a575ed ("uapi: Revert "bitops: avoid integer overflow in GENMASK(_ULL)"")
did not take in account that the usage of BITS_PER_LONG in __GENMASK() was
changed to __BITS_PER_LONG for UAPI-safety in
commit 3c7a8e190bc5 ("uapi: introduce uapi-friendly macros for GENMASK").
BITS_PER_LONG can not be used in UAPI headers as it derives from the kernel
configuration and not from the current compiler invocation.
When building compat userspace code or a compat vDSO its value will be
incorrect.

Switch back to __BITS_PER_LONG.

Fixes: 1e7933a575ed ("uapi: Revert "bitops: avoid integer overflow in GENMASK(_ULL)"")
Cc: stable@vger.kernel.org
Signed-off-by: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Signed-off-by: Yury Norov [NVIDIA] <yury.norov@gmail.com>
---
 include/uapi/linux/bits.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/include/uapi/linux/bits.h b/include/uapi/linux/bits.h
index 682b406e1067..a04afef9efca 100644
--- a/include/uapi/linux/bits.h
+++ b/include/uapi/linux/bits.h
@@ -4,9 +4,9 @@
 #ifndef _UAPI_LINUX_BITS_H
 #define _UAPI_LINUX_BITS_H
 
-#define __GENMASK(h, l) (((~_UL(0)) << (l)) & (~_UL(0) >> (BITS_PER_LONG - 1 - (h))))
+#define __GENMASK(h, l) (((~_UL(0)) << (l)) & (~_UL(0) >> (__BITS_PER_LONG - 1 - (h))))
 
-#define __GENMASK_ULL(h, l) (((~_ULL(0)) << (l)) & (~_ULL(0) >> (BITS_PER_LONG_LONG - 1 - (h))))
+#define __GENMASK_ULL(h, l) (((~_ULL(0)) << (l)) & (~_ULL(0) >> (__BITS_PER_LONG_LONG - 1 - (h))))
 
 #define __GENMASK_U128(h, l) \
 	((_BIT128((h)) << 1) - (_BIT128(l)))

From c0f691388992c708436ab5f6e810865be6ddf5c6 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Thu, 5 Jun 2025 17:04:11 +0200
Subject: [PATCH 0039/1334] intel_idle: Use subsys_initcall_sync() for
 initialization

It is not necessary to wait until the device_initcall() stage with
intel_idle initialization.  All of its dependencies are met after
all subsys_initcall()s have run, so subsys_initcall_sync() can be
used for initializing it.

It is also better to ensure that intel_idle will always initialize
before the ACPI processor driver that uses module_init() for its
initialization.

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Tested-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
Link: https://patch.msgid.link/2994397.e9J7NaK4W3@rjwysocki.net
---
 drivers/idle/intel_idle.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
index 8ccb483204fa..64ac4da08094 100644
--- a/drivers/idle/intel_idle.c
+++ b/drivers/idle/intel_idle.c
@@ -2518,7 +2518,7 @@ init_driver_fail:
 	return retval;
 
 }
-device_initcall(intel_idle_init);
+subsys_initcall_sync(intel_idle_init);
 
 /*
  * We are not really modular, but we used to support that.  Meaning we also

From 02670deede2288d8e4e3d800477b27c091080fae Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Fri, 6 Jun 2025 13:21:34 -0700
Subject: [PATCH 0040/1334] libbpf: Handle unsupported mmap-based
 /sys/kernel/btf/vmlinux correctly

libbpf_err_ptr() helpers are meant to return NULL and set errno, if
there is an error. But btf_parse_raw_mmap() is meant to be used
internally and is expected to return ERR_PTR() values. Because of this
mismatch, when libbpf tries to mmap /sys/kernel/btf/vmlinux, we don't
detect the error correctly with IS_ERR() check, and never fallback to
old non-mmap-based way of loading vmlinux BTF.

Fix this by using proper ERR_PTR() returns internally.

Reported-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Reviewed-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Fixes: 3c0421c93ce4 ("libbpf: Use mmap to parse vmlinux BTF from sysfs")
Cc: Lorenz Bauer <lmb@isovalent.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/r/20250606202134.2738910-1-andrii@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/lib/bpf/btf.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c
index f1d495dc66bb..37682908cb0f 100644
--- a/tools/lib/bpf/btf.c
+++ b/tools/lib/bpf/btf.c
@@ -1384,12 +1384,12 @@ static struct btf *btf_parse_raw_mmap(const char *path, struct btf *base_btf)
 
 	fd = open(path, O_RDONLY);
 	if (fd < 0)
-		return libbpf_err_ptr(-errno);
+		return ERR_PTR(-errno);
 
 	if (fstat(fd, &st) < 0) {
 		err = -errno;
 		close(fd);
-		return libbpf_err_ptr(err);
+		return ERR_PTR(err);
 	}
 
 	data = mmap(NULL, st.st_size, PROT_READ, MAP_PRIVATE, fd, 0);
@@ -1397,7 +1397,7 @@ static struct btf *btf_parse_raw_mmap(const char *path, struct btf *base_btf)
 	close(fd);
 
 	if (data == MAP_FAILED)
-		return libbpf_err_ptr(err);
+		return ERR_PTR(err);
 
 	btf = btf_new(data, st.st_size, base_btf, true);
 	if (IS_ERR(btf))

From 4c529a4a7260776bb4abe264498857b4537aa70d Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Sat, 7 Jun 2025 14:22:56 +0200
Subject: [PATCH 0041/1334] x86/smp: PM/hibernate: Split arch_resume_nosmt()

Move the inner part of the arch_resume_nosmt() code into a separate
function called arch_cpu_rescan_dead_smt_siblings(), so it can be
used in other places where "dead" SMT siblings may need to be taken
online and offline again in order to get into deep idle states.

No intentional functional impact.

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Dave Hansen <dave.hansen@linux.intel.com>
Tested-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
Link: https://patch.msgid.link/3361688.44csPzL39Z@rjwysocki.net
[ rjw: Prevent build issues with CONFIG_SMP unset ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 arch/x86/kernel/smp.c      | 24 ++++++++++++++++++++++++
 arch/x86/power/hibernate.c | 17 +++++------------
 include/linux/cpu.h        |  3 +++
 3 files changed, 32 insertions(+), 12 deletions(-)

diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c
index 18266cc3d98c..b014e6d229f9 100644
--- a/arch/x86/kernel/smp.c
+++ b/arch/x86/kernel/smp.c
@@ -299,3 +299,27 @@ struct smp_ops smp_ops = {
 	.send_call_func_single_ipi = native_send_call_func_single_ipi,
 };
 EXPORT_SYMBOL_GPL(smp_ops);
+
+int arch_cpu_rescan_dead_smt_siblings(void)
+{
+	enum cpuhp_smt_control old = cpu_smt_control;
+	int ret;
+
+	/*
+	 * If SMT has been disabled and SMT siblings are in HLT, bring them back
+	 * online and offline them again so that they end up in MWAIT proper.
+	 *
+	 * Called with hotplug enabled.
+	 */
+	if (old != CPU_SMT_DISABLED && old != CPU_SMT_FORCE_DISABLED)
+		return 0;
+
+	ret = cpuhp_smt_enable();
+	if (ret)
+		return ret;
+
+	ret = cpuhp_smt_disable(old);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(arch_cpu_rescan_dead_smt_siblings);
diff --git a/arch/x86/power/hibernate.c b/arch/x86/power/hibernate.c
index a7c23f2a58c9..a2294c1649f6 100644
--- a/arch/x86/power/hibernate.c
+++ b/arch/x86/power/hibernate.c
@@ -192,7 +192,8 @@ out:
 
 int arch_resume_nosmt(void)
 {
-	int ret = 0;
+	int ret;
+
 	/*
 	 * We reached this while coming out of hibernation. This means
 	 * that SMT siblings are sleeping in hlt, as mwait is not safe
@@ -206,18 +207,10 @@ int arch_resume_nosmt(void)
 	 * Called with hotplug disabled.
 	 */
 	cpu_hotplug_enable();
-	if (cpu_smt_control == CPU_SMT_DISABLED ||
-			cpu_smt_control == CPU_SMT_FORCE_DISABLED) {
-		enum cpuhp_smt_control old = cpu_smt_control;
 
-		ret = cpuhp_smt_enable();
-		if (ret)
-			goto out;
-		ret = cpuhp_smt_disable(old);
-		if (ret)
-			goto out;
-	}
-out:
+	ret = arch_cpu_rescan_dead_smt_siblings();
+
 	cpu_hotplug_disable();
+
 	return ret;
 }
diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index e6089abc28e2..96a3a0d6a60e 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -120,6 +120,7 @@ extern void cpu_maps_update_begin(void);
 extern void cpu_maps_update_done(void);
 int bringup_hibernate_cpu(unsigned int sleep_cpu);
 void bringup_nonboot_cpus(unsigned int max_cpus);
+int arch_cpu_rescan_dead_smt_siblings(void);
 
 #else	/* CONFIG_SMP */
 #define cpuhp_tasks_frozen	0
@@ -134,6 +135,8 @@ static inline void cpu_maps_update_done(void)
 
 static inline int add_cpu(unsigned int cpu) { return 0;}
 
+static inline int arch_cpu_rescan_dead_smt_siblings(void) { return 0; }
+
 #endif /* CONFIG_SMP */
 extern const struct bus_type cpu_subsys;
 

From a430c11f401589a0f4f57fd398271a5d85142c7a Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Thu, 5 Jun 2025 17:06:08 +0200
Subject: [PATCH 0042/1334] intel_idle: Rescan "dead" SMT siblings during
 initialization

Make intel_idle_init() call arch_cpu_rescan_dead_smt_siblings() after
successfully registering intel_idle as the cpuidle driver so as to
allow the "dead" SMT siblings (if any) to go into deep idle states.

This is necessary for the processor to be able to reach deep package
C-states (like PC10) going forward which is requisite for reducing
power sufficiently in suspend-to-idle, among other things.

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Tested-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
Link: https://patch.msgid.link/10669885.nUPlyArG6x@rjwysocki.net
---
 drivers/idle/intel_idle.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
index 64ac4da08094..63565814c7e5 100644
--- a/drivers/idle/intel_idle.c
+++ b/drivers/idle/intel_idle.c
@@ -2507,6 +2507,8 @@ static int __init intel_idle_init(void)
 	pr_debug("Local APIC timer is reliable in %s\n",
 		 boot_cpu_has(X86_FEATURE_ARAT) ? "all C-states" : "C1");
 
+	arch_cpu_rescan_dead_smt_siblings();
+
 	return 0;
 
 hp_setup_fail:

From f694481b1d3177144fcac4242eb750cfcb9f7bd5 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Thu, 5 Jun 2025 17:07:31 +0200
Subject: [PATCH 0043/1334] ACPI: processor: Rescan "dead" SMT siblings during
 initialization

Make acpi_processor_driver_init() call arch_cpu_rescan_dead_smt_siblings(),
via a new wrapper function called acpi_idle_rescan_dead_smt_siblings(),
after successfully initializing the driver, to allow the "dead" SMT
siblings to go into deep idle states, which is necessary for the
processor to be able to reach deep package C-states (like PC10) going
forward, so that power can be reduced sufficiently in suspend-to-idle,
among other things.

However, do it only if the ACPI idle driver is the current cpuidle
driver (otherwise it is assumed that another cpuidle driver will take
care of this) and avoid doing it on architectures other than x86.

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Tested-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
Link: https://patch.msgid.link/2005721.PYKUYFuaPT@rjwysocki.net
---
 drivers/acpi/internal.h         | 6 ++++++
 drivers/acpi/processor_driver.c | 3 +++
 drivers/acpi/processor_idle.c   | 8 ++++++++
 3 files changed, 17 insertions(+)

diff --git a/drivers/acpi/internal.h b/drivers/acpi/internal.h
index 00910ccd7eda..e2781864fdce 100644
--- a/drivers/acpi/internal.h
+++ b/drivers/acpi/internal.h
@@ -175,6 +175,12 @@ bool processor_physically_present(acpi_handle handle);
 static inline void acpi_early_processor_control_setup(void) {}
 #endif
 
+#ifdef CONFIG_ACPI_PROCESSOR_CSTATE
+void acpi_idle_rescan_dead_smt_siblings(void);
+#else
+static inline void acpi_idle_rescan_dead_smt_siblings(void) {}
+#endif
+
 /* --------------------------------------------------------------------------
                                   Embedded Controller
    -------------------------------------------------------------------------- */
diff --git a/drivers/acpi/processor_driver.c b/drivers/acpi/processor_driver.c
index 3b281bc1e73c..65e779be64ff 100644
--- a/drivers/acpi/processor_driver.c
+++ b/drivers/acpi/processor_driver.c
@@ -279,6 +279,9 @@ static int __init acpi_processor_driver_init(void)
 	 * after acpi_cppc_processor_probe() has been called for all online CPUs
 	 */
 	acpi_processor_init_invariance_cppc();
+
+	acpi_idle_rescan_dead_smt_siblings();
+
 	return 0;
 err:
 	driver_unregister(&acpi_processor_driver);
diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c
index e2febca2ec13..2c2dc559e0f8 100644
--- a/drivers/acpi/processor_idle.c
+++ b/drivers/acpi/processor_idle.c
@@ -24,6 +24,8 @@
 #include <acpi/processor.h>
 #include <linux/context_tracking.h>
 
+#include "internal.h"
+
 /*
  * Include the apic definitions for x86 to have the APIC timer related defines
  * available also for UP (on SMP it gets magically included via linux/smp.h).
@@ -55,6 +57,12 @@ struct cpuidle_driver acpi_idle_driver = {
 };
 
 #ifdef CONFIG_ACPI_PROCESSOR_CSTATE
+void acpi_idle_rescan_dead_smt_siblings(void)
+{
+	if (cpuidle_get_driver() == &acpi_idle_driver)
+		arch_cpu_rescan_dead_smt_siblings();
+}
+
 static
 DEFINE_PER_CPU(struct acpi_processor_cx * [CPUIDLE_STATE_MAX], acpi_cstate);
 

From a18d098f2aab82abde1d59c56aef9beca01c892b Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Thu, 5 Jun 2025 17:09:35 +0200
Subject: [PATCH 0044/1334] Reapply "x86/smp: Eliminate
 mwait_play_dead_cpuid_hint()"

Revert commit 70523f335734 ("Revert "x86/smp: Eliminate
mwait_play_dead_cpuid_hint()"") to reapply the changes from commit
96040f7273e2 ("x86/smp: Eliminate mwait_play_dead_cpuid_hint()")
reverted by it.

Previously, these changes caused idle power to rise on systems booting
with "nosmt" in the kernel command line because they effectively caused
"dead" SMT siblings to remain in idle state C1 after executing the HLT
instruction, which prevented the processor from reaching package idle
states deeper than PC2 going forward.

Now, the "dead" SMT siblings are rescanned after initializing a proper
cpuidle driver for the processor (either intel_idle or ACPI idle), at
which point they are able to enter a sufficiently deep idle state
in native_play_dead() via cpuidle, so the code changes in question can
be reapplied.

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Dave Hansen <dave.hansen@linux.intel.com>
Tested-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
Link: https://patch.msgid.link/7813065.EvYhyI6sBW@rjwysocki.net
---
 arch/x86/kernel/smpboot.c | 54 +++++----------------------------------
 1 file changed, 7 insertions(+), 47 deletions(-)

diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index fc78c2325fd2..58ede3fa6a75 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -1244,6 +1244,10 @@ void play_dead_common(void)
 	local_irq_disable();
 }
 
+/*
+ * We need to flush the caches before going to sleep, lest we have
+ * dirty data in our caches when we come back up.
+ */
 void __noreturn mwait_play_dead(unsigned int eax_hint)
 {
 	struct mwait_cpu_dead *md = this_cpu_ptr(&mwait_cpu_dead);
@@ -1289,50 +1293,6 @@ void __noreturn mwait_play_dead(unsigned int eax_hint)
 	}
 }
 
-/*
- * We need to flush the caches before going to sleep, lest we have
- * dirty data in our caches when we come back up.
- */
-static inline void mwait_play_dead_cpuid_hint(void)
-{
-	unsigned int eax, ebx, ecx, edx;
-	unsigned int highest_cstate = 0;
-	unsigned int highest_subcstate = 0;
-	int i;
-
-	if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD ||
-	    boot_cpu_data.x86_vendor == X86_VENDOR_HYGON)
-		return;
-	if (!this_cpu_has(X86_FEATURE_MWAIT))
-		return;
-	if (!this_cpu_has(X86_FEATURE_CLFLUSH))
-		return;
-
-	eax = CPUID_LEAF_MWAIT;
-	ecx = 0;
-	native_cpuid(&eax, &ebx, &ecx, &edx);
-
-	/*
-	 * eax will be 0 if EDX enumeration is not valid.
-	 * Initialized below to cstate, sub_cstate value when EDX is valid.
-	 */
-	if (!(ecx & CPUID5_ECX_EXTENSIONS_SUPPORTED)) {
-		eax = 0;
-	} else {
-		edx >>= MWAIT_SUBSTATE_SIZE;
-		for (i = 0; i < 7 && edx; i++, edx >>= MWAIT_SUBSTATE_SIZE) {
-			if (edx & MWAIT_SUBSTATE_MASK) {
-				highest_cstate = i;
-				highest_subcstate = edx & MWAIT_SUBSTATE_MASK;
-			}
-		}
-		eax = (highest_cstate << MWAIT_SUBSTATE_SIZE) |
-			(highest_subcstate - 1);
-	}
-
-	mwait_play_dead(eax);
-}
-
 /*
  * Kick all "offline" CPUs out of mwait on kexec(). See comment in
  * mwait_play_dead().
@@ -1383,9 +1343,9 @@ void native_play_dead(void)
 	play_dead_common();
 	tboot_shutdown(TB_SHUTDOWN_WFS);
 
-	mwait_play_dead_cpuid_hint();
-	if (cpuidle_play_dead())
-		hlt_play_dead();
+	/* Below returns only on error. */
+	cpuidle_play_dead();
+	hlt_play_dead();
 }
 
 #else /* ... !CONFIG_HOTPLUG_CPU */

From 1650d32b92b01db03a1a95d69ee74fcbc34d4b00 Mon Sep 17 00:00:00 2001
From: Caleb Connolly <caleb.connolly@linaro.org>
Date: Tue, 18 Mar 2025 20:50:27 +0000
Subject: [PATCH 0045/1334] ath10k: snoc: fix unbalanced IRQ enable in crash
 recovery

In ath10k_snoc_hif_stop() we skip disabling the IRQs in the crash
recovery flow, but we still unconditionally call enable again in
ath10k_snoc_hif_start().

We can't check the ATH10K_FLAG_CRASH_FLUSH bit since it is cleared
before hif_start() is called, so instead check the
ATH10K_SNOC_FLAG_RECOVERY flag and skip enabling the IRQs during crash
recovery.

This fixes unbalanced IRQ enable splats that happen after recovering from
a crash.

Fixes: 0e622f67e041 ("ath10k: add support for WCN3990 firmware crash recovery")
Signed-off-by: Caleb Connolly <caleb.connolly@linaro.org>
Tested-by: Loic Poulain <loic.poulain@oss.qualcomm.com>
Link: https://patch.msgid.link/20250318205043.1043148-1-caleb.connolly@linaro.org
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath10k/snoc.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/ath10k/snoc.c b/drivers/net/wireless/ath/ath10k/snoc.c
index 866bad2db334..65673b1aba55 100644
--- a/drivers/net/wireless/ath/ath10k/snoc.c
+++ b/drivers/net/wireless/ath/ath10k/snoc.c
@@ -937,7 +937,9 @@ static int ath10k_snoc_hif_start(struct ath10k *ar)
 
 	dev_set_threaded(ar->napi_dev, true);
 	ath10k_core_napi_enable(ar);
-	ath10k_snoc_irq_enable(ar);
+	/* IRQs are left enabled when we restart due to a firmware crash */
+	if (!test_bit(ATH10K_SNOC_FLAG_RECOVERY, &ar_snoc->flags))
+		ath10k_snoc_irq_enable(ar);
 	ath10k_snoc_rx_post(ar);
 
 	clear_bit(ATH10K_SNOC_FLAG_RECOVERY, &ar_snoc->flags);

From dc9c4252fe0d7a7f1ee904405ea91534277305bf Mon Sep 17 00:00:00 2001
From: Loic Poulain <loic.poulain@oss.qualcomm.com>
Date: Thu, 22 May 2025 15:17:04 +0200
Subject: [PATCH 0046/1334] wifi: ath10k: Avoid vdev delete timeout when
 firmware is already down

In some scenarios, the firmware may be stopped before the interface is
removed, either due to a crash or because the remoteproc (e.g., MPSS)
is shut down early during system reboot or shutdown.

This leads to a delay during interface teardown, as the driver waits for
a vdev delete response that never arrives, eventually timing out.

Example (SNOC):
$ echo stop > /sys/class/remoteproc/remoteproc0/state
[ 71.64] remoteproc remoteproc0: stopped remote processor modem
$ reboot
[ 74.84] ath10k_snoc c800000.wifi: failed to transmit packet, dropping: -108
[ 74.84] ath10k_snoc c800000.wifi: failed to submit frame: -108
[...]
[ 82.39] ath10k_snoc c800000.wifi: Timeout in receiving vdev delete response

To avoid this, skip waiting for the vdev delete response if the firmware is
already marked as unreachable (`ATH10K_FLAG_CRASH_FLUSH`), similar to how
`ath10k_mac_wait_tx_complete()` and `ath10k_vdev_setup_sync()` handle this case.

Signed-off-by: Loic Poulain <loic.poulain@oss.qualcomm.com>
Link: https://patch.msgid.link/20250522131704.612206-1-loic.poulain@oss.qualcomm.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath10k/mac.c | 33 ++++++++++++++++++++-------
 1 file changed, 25 insertions(+), 8 deletions(-)

diff --git a/drivers/net/wireless/ath/ath10k/mac.c b/drivers/net/wireless/ath/ath10k/mac.c
index 8c7ffea0fa44..07fe05384cdf 100644
--- a/drivers/net/wireless/ath/ath10k/mac.c
+++ b/drivers/net/wireless/ath/ath10k/mac.c
@@ -4,6 +4,7 @@
  * Copyright (c) 2011-2017 Qualcomm Atheros, Inc.
  * Copyright (c) 2018-2019, The Linux Foundation. All rights reserved.
  * Copyright (c) 2021-2024 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) Qualcomm Technologies, Inc. and/or its subsidiaries.
  */
 
 #include "mac.h"
@@ -1022,6 +1023,26 @@ static inline int ath10k_vdev_setup_sync(struct ath10k *ar)
 	return ar->last_wmi_vdev_start_status;
 }
 
+static inline int ath10k_vdev_delete_sync(struct ath10k *ar)
+{
+	unsigned long time_left;
+
+	lockdep_assert_held(&ar->conf_mutex);
+
+	if (!test_bit(WMI_SERVICE_SYNC_DELETE_CMDS, ar->wmi.svc_map))
+		return 0;
+
+	if (test_bit(ATH10K_FLAG_CRASH_FLUSH, &ar->dev_flags))
+		return -ESHUTDOWN;
+
+	time_left = wait_for_completion_timeout(&ar->vdev_delete_done,
+						ATH10K_VDEV_DELETE_TIMEOUT_HZ);
+	if (time_left == 0)
+		return -ETIMEDOUT;
+
+	return 0;
+}
+
 static int ath10k_monitor_vdev_start(struct ath10k *ar, int vdev_id)
 {
 	struct cfg80211_chan_def *chandef = NULL;
@@ -5900,7 +5921,6 @@ static void ath10k_remove_interface(struct ieee80211_hw *hw,
 	struct ath10k *ar = hw->priv;
 	struct ath10k_vif *arvif = (void *)vif->drv_priv;
 	struct ath10k_peer *peer;
-	unsigned long time_left;
 	int ret;
 	int i;
 
@@ -5940,13 +5960,10 @@ static void ath10k_remove_interface(struct ieee80211_hw *hw,
 		ath10k_warn(ar, "failed to delete WMI vdev %i: %d\n",
 			    arvif->vdev_id, ret);
 
-	if (test_bit(WMI_SERVICE_SYNC_DELETE_CMDS, ar->wmi.svc_map)) {
-		time_left = wait_for_completion_timeout(&ar->vdev_delete_done,
-							ATH10K_VDEV_DELETE_TIMEOUT_HZ);
-		if (time_left == 0) {
-			ath10k_warn(ar, "Timeout in receiving vdev delete response\n");
-			goto out;
-		}
+	ret = ath10k_vdev_delete_sync(ar);
+	if (ret) {
+		ath10k_warn(ar, "Error in receiving vdev delete response: %d\n", ret);
+		goto out;
 	}
 
 	/* Some firmware revisions don't notify host about self-peer removal

From 593963660919a97a4546acfd706dac93625724f5 Mon Sep 17 00:00:00 2001
From: Sebastian Gottschall <s.gottschall@dd-wrt.com>
Date: Tue, 4 Mar 2025 08:21:31 +0700
Subject: [PATCH 0047/1334] wil6210: fix support for sparrow chipsets

the wil6210 driver irq handling code is unconditionally writing
edma irq registers which are supposed to be only used on Talyn chipsets.
This however leade to a chipset hang on the older sparrow chipset
generation and firmware will not even boot.
Fix that by simply checking for edma support before handling these
registers.

Tested on Netgear R9000

Signed-off-by: Sebastian Gottschall <s.gottschall@dd-wrt.com>
Link: https://patch.msgid.link/20250304012131.25970-2-s.gottschall@dd-wrt.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/wil6210/interrupt.c | 26 ++++++++++++--------
 1 file changed, 16 insertions(+), 10 deletions(-)

diff --git a/drivers/net/wireless/ath/wil6210/interrupt.c b/drivers/net/wireless/ath/wil6210/interrupt.c
index 67172385a5d6..89d4394cedcf 100644
--- a/drivers/net/wireless/ath/wil6210/interrupt.c
+++ b/drivers/net/wireless/ath/wil6210/interrupt.c
@@ -179,9 +179,11 @@ void wil_mask_irq(struct wil6210_priv *wil)
 	wil_dbg_irq(wil, "mask_irq\n");
 
 	wil6210_mask_irq_tx(wil);
-	wil6210_mask_irq_tx_edma(wil);
+	if (wil->use_enhanced_dma_hw)
+		wil6210_mask_irq_tx_edma(wil);
 	wil6210_mask_irq_rx(wil);
-	wil6210_mask_irq_rx_edma(wil);
+	if (wil->use_enhanced_dma_hw)
+		wil6210_mask_irq_rx_edma(wil);
 	wil6210_mask_irq_misc(wil, true);
 	wil6210_mask_irq_pseudo(wil);
 }
@@ -190,10 +192,12 @@ void wil_unmask_irq(struct wil6210_priv *wil)
 {
 	wil_dbg_irq(wil, "unmask_irq\n");
 
-	wil_w(wil, RGF_DMA_EP_RX_ICR + offsetof(struct RGF_ICR, ICC),
-	      WIL_ICR_ICC_VALUE);
-	wil_w(wil, RGF_DMA_EP_TX_ICR + offsetof(struct RGF_ICR, ICC),
-	      WIL_ICR_ICC_VALUE);
+	if (wil->use_enhanced_dma_hw) {
+		wil_w(wil, RGF_DMA_EP_RX_ICR + offsetof(struct RGF_ICR, ICC),
+		      WIL_ICR_ICC_VALUE);
+		wil_w(wil, RGF_DMA_EP_TX_ICR + offsetof(struct RGF_ICR, ICC),
+		      WIL_ICR_ICC_VALUE);
+	}
 	wil_w(wil, RGF_DMA_EP_MISC_ICR + offsetof(struct RGF_ICR, ICC),
 	      WIL_ICR_ICC_MISC_VALUE);
 	wil_w(wil, RGF_INT_GEN_TX_ICR + offsetof(struct RGF_ICR, ICC),
@@ -845,10 +849,12 @@ void wil6210_clear_irq(struct wil6210_priv *wil)
 		    offsetof(struct RGF_ICR, ICR));
 	wil_clear32(wil->csr + HOSTADDR(RGF_DMA_EP_TX_ICR) +
 		    offsetof(struct RGF_ICR, ICR));
-	wil_clear32(wil->csr + HOSTADDR(RGF_INT_GEN_RX_ICR) +
-		    offsetof(struct RGF_ICR, ICR));
-	wil_clear32(wil->csr + HOSTADDR(RGF_INT_GEN_TX_ICR) +
-		    offsetof(struct RGF_ICR, ICR));
+	if (wil->use_enhanced_dma_hw) {
+		wil_clear32(wil->csr + HOSTADDR(RGF_INT_GEN_RX_ICR) +
+			    offsetof(struct RGF_ICR, ICR));
+		wil_clear32(wil->csr + HOSTADDR(RGF_INT_GEN_TX_ICR) +
+			    offsetof(struct RGF_ICR, ICR));
+	}
 	wil_clear32(wil->csr + HOSTADDR(RGF_DMA_EP_MISC_ICR) +
 		    offsetof(struct RGF_ICR, ICR));
 	wmb(); /* make sure write completed */

From 9f6e82d11bb9692a90d20b10f87345598945c803 Mon Sep 17 00:00:00 2001
From: Baochen Qiang <quic_bqiang@quicinc.com>
Date: Thu, 20 Feb 2025 16:24:42 +0800
Subject: [PATCH 0048/1334] wifi: ath11k: avoid burning CPU in
 ath11k_debugfs_fw_stats_request()

We get report [1] that CPU is running a hot loop in
ath11k_debugfs_fw_stats_request():

94.60%     0.00%  i3status         [kernel.kallsyms]                 [k] do_syscall_64
        |
         --94.60%--do_syscall_64
                   |
                    --94.55%--__sys_sendmsg
                              ___sys_sendmsg
                              ____sys_sendmsg
                              netlink_sendmsg
                              netlink_unicast
                              genl_rcv
                              netlink_rcv_skb
                              genl_rcv_msg
                              |
                               --94.55%--genl_family_rcv_msg_dumpit
                                         __netlink_dump_start
                                         netlink_dump
                                         genl_dumpit
                                         nl80211_dump_station
                                         |
                                          --94.55%--ieee80211_dump_station
                                                    sta_set_sinfo
                                                    |
                                                     --94.55%--ath11k_mac_op_sta_statistics
                                                               ath11k_debugfs_get_fw_stats
                                                               |
                                                                --94.55%--ath11k_debugfs_fw_stats_request
                                                                          |
                                                                          |--41.73%--_raw_spin_lock_bh
                                                                          |
                                                                          |--22.74%--__local_bh_enable_ip
                                                                          |
                                                                          |--9.22%--_raw_spin_unlock_bh
                                                                          |
                                                                           --6.66%--srso_alias_safe_ret

This is because, if for whatever reason ar->fw_stats_done is not set by
ath11k_update_stats_event(), ath11k_debugfs_fw_stats_request() won't yield
CPU before an up to 3s timeout.

Change to completion mechanism to avoid CPU burning.

Tested-on: WCN6855 hw2.0 PCI WLAN.HSP.1.1-03125-QCAHSPSWPL_V1_V2_SILICONZ_LITE-3.6510.37

Fixes: d5c65159f289 ("ath11k: driver for Qualcomm IEEE 802.11ax devices")
Reported-by: Yury Vostrikov <mon@unformed.ru>
Closes: https://lore.kernel.org/all/7324ac7a-8b7a-42a5-aa19-de52138ff638@app.fastmail.com/ # [1]
Signed-off-by: Baochen Qiang <quic_bqiang@quicinc.com>
Reviewed-by: Vasanthakumar Thiagarajan <vasanthakumar.thiagarajan@oss.qualcomm.com>
Link: https://patch.msgid.link/20250220082448.31039-2-quic_bqiang@quicinc.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath11k/core.c    |  1 +
 drivers/net/wireless/ath/ath11k/core.h    |  2 +-
 drivers/net/wireless/ath/ath11k/debugfs.c | 38 +++++++++--------------
 drivers/net/wireless/ath/ath11k/mac.c     |  2 +-
 drivers/net/wireless/ath/ath11k/wmi.c     |  2 +-
 5 files changed, 18 insertions(+), 27 deletions(-)

diff --git a/drivers/net/wireless/ath/ath11k/core.c b/drivers/net/wireless/ath/ath11k/core.c
index 2e9f8a5e61e4..c8c5008be7f2 100644
--- a/drivers/net/wireless/ath/ath11k/core.c
+++ b/drivers/net/wireless/ath/ath11k/core.c
@@ -990,6 +990,7 @@ void ath11k_fw_stats_init(struct ath11k *ar)
 	INIT_LIST_HEAD(&ar->fw_stats.bcn);
 
 	init_completion(&ar->fw_stats_complete);
+	init_completion(&ar->fw_stats_done);
 }
 
 void ath11k_fw_stats_free(struct ath11k_fw_stats *stats)
diff --git a/drivers/net/wireless/ath/ath11k/core.h b/drivers/net/wireless/ath/ath11k/core.h
index 339d4fca1ed5..41bb81d00189 100644
--- a/drivers/net/wireless/ath/ath11k/core.h
+++ b/drivers/net/wireless/ath/ath11k/core.h
@@ -784,7 +784,7 @@ struct ath11k {
 	u8 alpha2[REG_ALPHA2_LEN + 1];
 	struct ath11k_fw_stats fw_stats;
 	struct completion fw_stats_complete;
-	bool fw_stats_done;
+	struct completion fw_stats_done;
 
 	/* protected by conf_mutex */
 	bool ps_state_enable;
diff --git a/drivers/net/wireless/ath/ath11k/debugfs.c b/drivers/net/wireless/ath/ath11k/debugfs.c
index bf192529e3fe..1d03e3aab011 100644
--- a/drivers/net/wireless/ath/ath11k/debugfs.c
+++ b/drivers/net/wireless/ath/ath11k/debugfs.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: BSD-3-Clause-Clear
 /*
  * Copyright (c) 2018-2020 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2024 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2025 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #include <linux/vmalloc.h>
@@ -96,7 +96,6 @@ void ath11k_debugfs_add_dbring_entry(struct ath11k *ar,
 static void ath11k_debugfs_fw_stats_reset(struct ath11k *ar)
 {
 	spin_lock_bh(&ar->data_lock);
-	ar->fw_stats_done = false;
 	ath11k_fw_stats_pdevs_free(&ar->fw_stats.pdevs);
 	ath11k_fw_stats_vdevs_free(&ar->fw_stats.vdevs);
 	spin_unlock_bh(&ar->data_lock);
@@ -114,7 +113,7 @@ void ath11k_debugfs_fw_stats_process(struct ath11k *ar, struct ath11k_fw_stats *
 	/* WMI_REQUEST_PDEV_STAT request has been already processed */
 
 	if (stats->stats_id == WMI_REQUEST_RSSI_PER_CHAIN_STAT) {
-		ar->fw_stats_done = true;
+		complete(&ar->fw_stats_done);
 		return;
 	}
 
@@ -138,7 +137,7 @@ void ath11k_debugfs_fw_stats_process(struct ath11k *ar, struct ath11k_fw_stats *
 				      &ar->fw_stats.vdevs);
 
 		if (is_end) {
-			ar->fw_stats_done = true;
+			complete(&ar->fw_stats_done);
 			num_vdev = 0;
 		}
 		return;
@@ -158,7 +157,7 @@ void ath11k_debugfs_fw_stats_process(struct ath11k *ar, struct ath11k_fw_stats *
 				      &ar->fw_stats.bcn);
 
 		if (is_end) {
-			ar->fw_stats_done = true;
+			complete(&ar->fw_stats_done);
 			num_bcn = 0;
 		}
 	}
@@ -168,21 +167,15 @@ static int ath11k_debugfs_fw_stats_request(struct ath11k *ar,
 					   struct stats_request_params *req_param)
 {
 	struct ath11k_base *ab = ar->ab;
-	unsigned long timeout, time_left;
+	unsigned long time_left;
 	int ret;
 
 	lockdep_assert_held(&ar->conf_mutex);
 
-	/* FW stats can get split when exceeding the stats data buffer limit.
-	 * In that case, since there is no end marking for the back-to-back
-	 * received 'update stats' event, we keep a 3 seconds timeout in case,
-	 * fw_stats_done is not marked yet
-	 */
-	timeout = jiffies + secs_to_jiffies(3);
-
 	ath11k_debugfs_fw_stats_reset(ar);
 
 	reinit_completion(&ar->fw_stats_complete);
+	reinit_completion(&ar->fw_stats_done);
 
 	ret = ath11k_wmi_send_stats_request_cmd(ar, req_param);
 
@@ -193,21 +186,18 @@ static int ath11k_debugfs_fw_stats_request(struct ath11k *ar,
 	}
 
 	time_left = wait_for_completion_timeout(&ar->fw_stats_complete, 1 * HZ);
-
 	if (!time_left)
 		return -ETIMEDOUT;
 
-	for (;;) {
-		if (time_after(jiffies, timeout))
-			break;
+	/* FW stats can get split when exceeding the stats data buffer limit.
+	 * In that case, since there is no end marking for the back-to-back
+	 * received 'update stats' event, we keep a 3 seconds timeout in case,
+	 * fw_stats_done is not marked yet
+	 */
+	time_left = wait_for_completion_timeout(&ar->fw_stats_done, 3 * HZ);
+	if (!time_left)
+		return -ETIMEDOUT;
 
-		spin_lock_bh(&ar->data_lock);
-		if (ar->fw_stats_done) {
-			spin_unlock_bh(&ar->data_lock);
-			break;
-		}
-		spin_unlock_bh(&ar->data_lock);
-	}
 	return 0;
 }
 
diff --git a/drivers/net/wireless/ath/ath11k/mac.c b/drivers/net/wireless/ath/ath11k/mac.c
index 08d7b136851f..9ab501cd4f47 100644
--- a/drivers/net/wireless/ath/ath11k/mac.c
+++ b/drivers/net/wireless/ath/ath11k/mac.c
@@ -9390,11 +9390,11 @@ static int ath11k_fw_stats_request(struct ath11k *ar,
 	lockdep_assert_held(&ar->conf_mutex);
 
 	spin_lock_bh(&ar->data_lock);
-	ar->fw_stats_done = false;
 	ath11k_fw_stats_pdevs_free(&ar->fw_stats.pdevs);
 	spin_unlock_bh(&ar->data_lock);
 
 	reinit_completion(&ar->fw_stats_complete);
+	reinit_completion(&ar->fw_stats_done);
 
 	ret = ath11k_wmi_send_stats_request_cmd(ar, req_param);
 	if (ret) {
diff --git a/drivers/net/wireless/ath/ath11k/wmi.c b/drivers/net/wireless/ath/ath11k/wmi.c
index d7f852bebf4a..27cb0bb06b93 100644
--- a/drivers/net/wireless/ath/ath11k/wmi.c
+++ b/drivers/net/wireless/ath/ath11k/wmi.c
@@ -8189,7 +8189,7 @@ static void ath11k_update_stats_event(struct ath11k_base *ab, struct sk_buff *sk
 	 */
 	if (stats.stats_id == WMI_REQUEST_PDEV_STAT) {
 		list_splice_tail_init(&stats.pdevs, &ar->fw_stats.pdevs);
-		ar->fw_stats_done = true;
+		complete(&ar->fw_stats_done);
 		goto complete;
 	}
 

From 2bcf73b2612dda7432f2c2eaad6679bd291791f2 Mon Sep 17 00:00:00 2001
From: Baochen Qiang <quic_bqiang@quicinc.com>
Date: Thu, 20 Feb 2025 16:24:43 +0800
Subject: [PATCH 0049/1334] wifi: ath11k: don't use static variables in
 ath11k_debugfs_fw_stats_process()

Currently ath11k_debugfs_fw_stats_process() is using static variables to count
firmware stat events. Taking num_vdev as an example, if for whatever reason (
say ar->num_started_vdevs is 0 or firmware bug etc.) the following condition

	(++num_vdev) == total_vdevs_started

is not met, is_end is not set thus num_vdev won't be cleared. Next time when
firmware stats is requested again, even if everything is working fine, we will
fail due to the condition above will never be satisfied.

The same applies to num_bcn as well.

Change to use non-static counters so that we have a chance to clear them each
time firmware stats is requested. Currently only ath11k_fw_stats_request() and
ath11k_debugfs_fw_stats_request() are requesting firmware stats, so clear
counters there.

Tested-on: WCN6855 hw2.0 PCI WLAN.HSP.1.1-03125-QCAHSPSWPL_V1_V2_SILICONZ_LITE-3.6510.37

Fixes: da3a9d3c1576 ("ath11k: refactor debugfs code into debugfs.c")
Signed-off-by: Baochen Qiang <quic_bqiang@quicinc.com>
Acked-by: Kalle Valo <kvalo@kernel.org>
Reviewed-by: Vasanthakumar Thiagarajan <vasanthakumar.thiagarajan@oss.qualcomm.com>
Link: https://patch.msgid.link/20250220082448.31039-3-quic_bqiang@quicinc.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath11k/core.h    |  2 ++
 drivers/net/wireless/ath/ath11k/debugfs.c | 16 +++++++---------
 drivers/net/wireless/ath/ath11k/mac.c     |  2 ++
 3 files changed, 11 insertions(+), 9 deletions(-)

diff --git a/drivers/net/wireless/ath/ath11k/core.h b/drivers/net/wireless/ath/ath11k/core.h
index 41bb81d00189..6b2f207975e3 100644
--- a/drivers/net/wireless/ath/ath11k/core.h
+++ b/drivers/net/wireless/ath/ath11k/core.h
@@ -600,6 +600,8 @@ struct ath11k_fw_stats {
 	struct list_head pdevs;
 	struct list_head vdevs;
 	struct list_head bcn;
+	u32 num_vdev_recvd;
+	u32 num_bcn_recvd;
 };
 
 struct ath11k_dbg_htt_stats {
diff --git a/drivers/net/wireless/ath/ath11k/debugfs.c b/drivers/net/wireless/ath/ath11k/debugfs.c
index 1d03e3aab011..27c93c0b4c22 100644
--- a/drivers/net/wireless/ath/ath11k/debugfs.c
+++ b/drivers/net/wireless/ath/ath11k/debugfs.c
@@ -98,6 +98,8 @@ static void ath11k_debugfs_fw_stats_reset(struct ath11k *ar)
 	spin_lock_bh(&ar->data_lock);
 	ath11k_fw_stats_pdevs_free(&ar->fw_stats.pdevs);
 	ath11k_fw_stats_vdevs_free(&ar->fw_stats.vdevs);
+	ar->fw_stats.num_vdev_recvd = 0;
+	ar->fw_stats.num_bcn_recvd = 0;
 	spin_unlock_bh(&ar->data_lock);
 }
 
@@ -106,7 +108,6 @@ void ath11k_debugfs_fw_stats_process(struct ath11k *ar, struct ath11k_fw_stats *
 	struct ath11k_base *ab = ar->ab;
 	struct ath11k_pdev *pdev;
 	bool is_end;
-	static unsigned int num_vdev, num_bcn;
 	size_t total_vdevs_started = 0;
 	int i;
 
@@ -131,15 +132,14 @@ void ath11k_debugfs_fw_stats_process(struct ath11k *ar, struct ath11k_fw_stats *
 				total_vdevs_started += ar->num_started_vdevs;
 		}
 
-		is_end = ((++num_vdev) == total_vdevs_started);
+		is_end = ((++ar->fw_stats.num_vdev_recvd) == total_vdevs_started);
 
 		list_splice_tail_init(&stats->vdevs,
 				      &ar->fw_stats.vdevs);
 
-		if (is_end) {
+		if (is_end)
 			complete(&ar->fw_stats_done);
-			num_vdev = 0;
-		}
+
 		return;
 	}
 
@@ -151,15 +151,13 @@ void ath11k_debugfs_fw_stats_process(struct ath11k *ar, struct ath11k_fw_stats *
 		/* Mark end until we reached the count of all started VDEVs
 		 * within the PDEV
 		 */
-		is_end = ((++num_bcn) == ar->num_started_vdevs);
+		is_end = ((++ar->fw_stats.num_bcn_recvd) == ar->num_started_vdevs);
 
 		list_splice_tail_init(&stats->bcn,
 				      &ar->fw_stats.bcn);
 
-		if (is_end) {
+		if (is_end)
 			complete(&ar->fw_stats_done);
-			num_bcn = 0;
-		}
 	}
 }
 
diff --git a/drivers/net/wireless/ath/ath11k/mac.c b/drivers/net/wireless/ath/ath11k/mac.c
index 9ab501cd4f47..5e098780cf23 100644
--- a/drivers/net/wireless/ath/ath11k/mac.c
+++ b/drivers/net/wireless/ath/ath11k/mac.c
@@ -9391,6 +9391,8 @@ static int ath11k_fw_stats_request(struct ath11k *ar,
 
 	spin_lock_bh(&ar->data_lock);
 	ath11k_fw_stats_pdevs_free(&ar->fw_stats.pdevs);
+	ar->fw_stats.num_vdev_recvd = 0;
+	ar->fw_stats.num_bcn_recvd = 0;
 	spin_unlock_bh(&ar->data_lock);
 
 	reinit_completion(&ar->fw_stats_complete);

From 3b6d00fa883075dcaf49221538230e038a9c0b43 Mon Sep 17 00:00:00 2001
From: Baochen Qiang <quic_bqiang@quicinc.com>
Date: Thu, 20 Feb 2025 16:24:44 +0800
Subject: [PATCH 0050/1334] wifi: ath11k: don't wait when there is no vdev
 started

For WMI_REQUEST_VDEV_STAT request, firmware might split response into
multiple events dut to buffer limit, hence currently in
ath11k_debugfs_fw_stats_process() we wait until all events received.
In case there is no vdev started, this results in that below condition
would never get satisfied

	((++ar->fw_stats.num_vdev_recvd) == total_vdevs_started)

finally the requestor would be blocked until wait time out.

The same applies to WMI_REQUEST_BCN_STAT request as well due to:

	((++ar->fw_stats.num_bcn_recvd) == ar->num_started_vdevs)

Change to check the number of started vdev first: if it is zero, finish
wait directly; if not, follow the old way.

Tested-on: WCN6855 hw2.0 PCI WLAN.HSP.1.1-03125-QCAHSPSWPL_V1_V2_SILICONZ_LITE-3.6510.37

Fixes: d5c65159f289 ("ath11k: driver for Qualcomm IEEE 802.11ax devices")
Signed-off-by: Baochen Qiang <quic_bqiang@quicinc.com>
Reviewed-by: Vasanthakumar Thiagarajan <vasanthakumar.thiagarajan@oss.qualcomm.com>
Link: https://patch.msgid.link/20250220082448.31039-4-quic_bqiang@quicinc.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath11k/debugfs.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/ath/ath11k/debugfs.c b/drivers/net/wireless/ath/ath11k/debugfs.c
index 27c93c0b4c22..ccf0e62c7d7a 100644
--- a/drivers/net/wireless/ath/ath11k/debugfs.c
+++ b/drivers/net/wireless/ath/ath11k/debugfs.c
@@ -107,7 +107,7 @@ void ath11k_debugfs_fw_stats_process(struct ath11k *ar, struct ath11k_fw_stats *
 {
 	struct ath11k_base *ab = ar->ab;
 	struct ath11k_pdev *pdev;
-	bool is_end;
+	bool is_end = true;
 	size_t total_vdevs_started = 0;
 	int i;
 
@@ -132,7 +132,9 @@ void ath11k_debugfs_fw_stats_process(struct ath11k *ar, struct ath11k_fw_stats *
 				total_vdevs_started += ar->num_started_vdevs;
 		}
 
-		is_end = ((++ar->fw_stats.num_vdev_recvd) == total_vdevs_started);
+		if (total_vdevs_started)
+			is_end = ((++ar->fw_stats.num_vdev_recvd) ==
+				  total_vdevs_started);
 
 		list_splice_tail_init(&stats->vdevs,
 				      &ar->fw_stats.vdevs);
@@ -151,7 +153,9 @@ void ath11k_debugfs_fw_stats_process(struct ath11k *ar, struct ath11k_fw_stats *
 		/* Mark end until we reached the count of all started VDEVs
 		 * within the PDEV
 		 */
-		is_end = ((++ar->fw_stats.num_bcn_recvd) == ar->num_started_vdevs);
+		if (ar->num_started_vdevs)
+			is_end = ((++ar->fw_stats.num_bcn_recvd) ==
+				  ar->num_started_vdevs);
 
 		list_splice_tail_init(&stats->bcn,
 				      &ar->fw_stats.bcn);

From 72610ed7d79da17ee09102534d6c696a4ea8a08e Mon Sep 17 00:00:00 2001
From: Baochen Qiang <quic_bqiang@quicinc.com>
Date: Thu, 20 Feb 2025 16:24:45 +0800
Subject: [PATCH 0051/1334] wifi: ath11k: move some firmware stats related
 functions outside of debugfs

Commit b488c766442f ("ath11k: report rssi of each chain to mac80211 for QCA6390/WCN6855")
and commit c3b39553fc77 ("ath11k: add signal report to mac80211 for QCA6390 and WCN6855")
call debugfs functions in mac ops. Those functions are no-ops if CONFIG_ATH11K_DEBUGFS is
not enabled, thus cause wrong status reported.

Move them to mac.c.

Besides, since WMI_REQUEST_RSSI_PER_CHAIN_STAT and WMI_REQUEST_VDEV_STAT stats could also
be requested via mac ops, process them directly in ath11k_update_stats_event().

Tested-on: WCN6855 hw2.0 PCI WLAN.HSP.1.1-03125-QCAHSPSWPL_V1_V2_SILICONZ_LITE-3.6510.37

Fixes: b488c766442f ("ath11k: report rssi of each chain to mac80211 for QCA6390/WCN6855")
Fixes: c3b39553fc77 ("ath11k: add signal report to mac80211 for QCA6390 and WCN6855")
Signed-off-by: Baochen Qiang <quic_bqiang@quicinc.com>
Reviewed-by: Vasanthakumar Thiagarajan <vasanthakumar.thiagarajan@oss.qualcomm.com>
Link: https://patch.msgid.link/20250220082448.31039-5-quic_bqiang@quicinc.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath11k/debugfs.c | 126 ++--------------------
 drivers/net/wireless/ath/ath11k/debugfs.h |  10 +-
 drivers/net/wireless/ath/ath11k/mac.c     |  88 ++++++++++++++-
 drivers/net/wireless/ath/ath11k/mac.h     |   4 +-
 drivers/net/wireless/ath/ath11k/wmi.c     |  45 +++++++-
 5 files changed, 135 insertions(+), 138 deletions(-)

diff --git a/drivers/net/wireless/ath/ath11k/debugfs.c b/drivers/net/wireless/ath/ath11k/debugfs.c
index ccf0e62c7d7a..5d46f8e4c231 100644
--- a/drivers/net/wireless/ath/ath11k/debugfs.c
+++ b/drivers/net/wireless/ath/ath11k/debugfs.c
@@ -93,58 +93,14 @@ void ath11k_debugfs_add_dbring_entry(struct ath11k *ar,
 	spin_unlock_bh(&dbr_data->lock);
 }
 
-static void ath11k_debugfs_fw_stats_reset(struct ath11k *ar)
-{
-	spin_lock_bh(&ar->data_lock);
-	ath11k_fw_stats_pdevs_free(&ar->fw_stats.pdevs);
-	ath11k_fw_stats_vdevs_free(&ar->fw_stats.vdevs);
-	ar->fw_stats.num_vdev_recvd = 0;
-	ar->fw_stats.num_bcn_recvd = 0;
-	spin_unlock_bh(&ar->data_lock);
-}
-
 void ath11k_debugfs_fw_stats_process(struct ath11k *ar, struct ath11k_fw_stats *stats)
 {
 	struct ath11k_base *ab = ar->ab;
-	struct ath11k_pdev *pdev;
 	bool is_end = true;
-	size_t total_vdevs_started = 0;
-	int i;
-
-	/* WMI_REQUEST_PDEV_STAT request has been already processed */
-
-	if (stats->stats_id == WMI_REQUEST_RSSI_PER_CHAIN_STAT) {
-		complete(&ar->fw_stats_done);
-		return;
-	}
-
-	if (stats->stats_id == WMI_REQUEST_VDEV_STAT) {
-		if (list_empty(&stats->vdevs)) {
-			ath11k_warn(ab, "empty vdev stats");
-			return;
-		}
-		/* FW sends all the active VDEV stats irrespective of PDEV,
-		 * hence limit until the count of all VDEVs started
-		 */
-		for (i = 0; i < ab->num_radios; i++) {
-			pdev = rcu_dereference(ab->pdevs_active[i]);
-			if (pdev && pdev->ar)
-				total_vdevs_started += ar->num_started_vdevs;
-		}
-
-		if (total_vdevs_started)
-			is_end = ((++ar->fw_stats.num_vdev_recvd) ==
-				  total_vdevs_started);
-
-		list_splice_tail_init(&stats->vdevs,
-				      &ar->fw_stats.vdevs);
-
-		if (is_end)
-			complete(&ar->fw_stats_done);
-
-		return;
-	}
 
+	/* WMI_REQUEST_PDEV_STAT, WMI_REQUEST_RSSI_PER_CHAIN_STAT and
+	 * WMI_REQUEST_VDEV_STAT requests have been already processed.
+	 */
 	if (stats->stats_id == WMI_REQUEST_BCN_STAT) {
 		if (list_empty(&stats->bcn)) {
 			ath11k_warn(ab, "empty bcn stats");
@@ -165,76 +121,6 @@ void ath11k_debugfs_fw_stats_process(struct ath11k *ar, struct ath11k_fw_stats *
 	}
 }
 
-static int ath11k_debugfs_fw_stats_request(struct ath11k *ar,
-					   struct stats_request_params *req_param)
-{
-	struct ath11k_base *ab = ar->ab;
-	unsigned long time_left;
-	int ret;
-
-	lockdep_assert_held(&ar->conf_mutex);
-
-	ath11k_debugfs_fw_stats_reset(ar);
-
-	reinit_completion(&ar->fw_stats_complete);
-	reinit_completion(&ar->fw_stats_done);
-
-	ret = ath11k_wmi_send_stats_request_cmd(ar, req_param);
-
-	if (ret) {
-		ath11k_warn(ab, "could not request fw stats (%d)\n",
-			    ret);
-		return ret;
-	}
-
-	time_left = wait_for_completion_timeout(&ar->fw_stats_complete, 1 * HZ);
-	if (!time_left)
-		return -ETIMEDOUT;
-
-	/* FW stats can get split when exceeding the stats data buffer limit.
-	 * In that case, since there is no end marking for the back-to-back
-	 * received 'update stats' event, we keep a 3 seconds timeout in case,
-	 * fw_stats_done is not marked yet
-	 */
-	time_left = wait_for_completion_timeout(&ar->fw_stats_done, 3 * HZ);
-	if (!time_left)
-		return -ETIMEDOUT;
-
-	return 0;
-}
-
-int ath11k_debugfs_get_fw_stats(struct ath11k *ar, u32 pdev_id,
-				u32 vdev_id, u32 stats_id)
-{
-	struct ath11k_base *ab = ar->ab;
-	struct stats_request_params req_param;
-	int ret;
-
-	mutex_lock(&ar->conf_mutex);
-
-	if (ar->state != ATH11K_STATE_ON) {
-		ret = -ENETDOWN;
-		goto err_unlock;
-	}
-
-	req_param.pdev_id = pdev_id;
-	req_param.vdev_id = vdev_id;
-	req_param.stats_id = stats_id;
-
-	ret = ath11k_debugfs_fw_stats_request(ar, &req_param);
-	if (ret)
-		ath11k_warn(ab, "failed to request fw stats: %d\n", ret);
-
-	ath11k_dbg(ab, ATH11K_DBG_WMI,
-		   "debug get fw stat pdev id %d vdev id %d stats id 0x%x\n",
-		   pdev_id, vdev_id, stats_id);
-
-err_unlock:
-	mutex_unlock(&ar->conf_mutex);
-
-	return ret;
-}
-
 static int ath11k_open_pdev_stats(struct inode *inode, struct file *file)
 {
 	struct ath11k *ar = inode->i_private;
@@ -260,7 +146,7 @@ static int ath11k_open_pdev_stats(struct inode *inode, struct file *file)
 	req_param.vdev_id = 0;
 	req_param.stats_id = WMI_REQUEST_PDEV_STAT;
 
-	ret = ath11k_debugfs_fw_stats_request(ar, &req_param);
+	ret = ath11k_mac_fw_stats_request(ar, &req_param);
 	if (ret) {
 		ath11k_warn(ab, "failed to request fw pdev stats: %d\n", ret);
 		goto err_free;
@@ -331,7 +217,7 @@ static int ath11k_open_vdev_stats(struct inode *inode, struct file *file)
 	req_param.vdev_id = 0;
 	req_param.stats_id = WMI_REQUEST_VDEV_STAT;
 
-	ret = ath11k_debugfs_fw_stats_request(ar, &req_param);
+	ret = ath11k_mac_fw_stats_request(ar, &req_param);
 	if (ret) {
 		ath11k_warn(ar->ab, "failed to request fw vdev stats: %d\n", ret);
 		goto err_free;
@@ -407,7 +293,7 @@ static int ath11k_open_bcn_stats(struct inode *inode, struct file *file)
 			continue;
 
 		req_param.vdev_id = arvif->vdev_id;
-		ret = ath11k_debugfs_fw_stats_request(ar, &req_param);
+		ret = ath11k_mac_fw_stats_request(ar, &req_param);
 		if (ret) {
 			ath11k_warn(ar->ab, "failed to request fw bcn stats: %d\n", ret);
 			goto err_free;
diff --git a/drivers/net/wireless/ath/ath11k/debugfs.h b/drivers/net/wireless/ath/ath11k/debugfs.h
index a39e458637b0..ed7fec177588 100644
--- a/drivers/net/wireless/ath/ath11k/debugfs.h
+++ b/drivers/net/wireless/ath/ath11k/debugfs.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: BSD-3-Clause-Clear */
 /*
  * Copyright (c) 2018-2019 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2022 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2022, 2025 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #ifndef _ATH11K_DEBUGFS_H_
@@ -273,8 +273,6 @@ void ath11k_debugfs_unregister(struct ath11k *ar);
 void ath11k_debugfs_fw_stats_process(struct ath11k *ar, struct ath11k_fw_stats *stats);
 
 void ath11k_debugfs_fw_stats_init(struct ath11k *ar);
-int ath11k_debugfs_get_fw_stats(struct ath11k *ar, u32 pdev_id,
-				u32 vdev_id, u32 stats_id);
 
 static inline bool ath11k_debugfs_is_pktlog_lite_mode_enabled(struct ath11k *ar)
 {
@@ -381,12 +379,6 @@ static inline int ath11k_debugfs_rx_filter(struct ath11k *ar)
 	return 0;
 }
 
-static inline int ath11k_debugfs_get_fw_stats(struct ath11k *ar,
-					      u32 pdev_id, u32 vdev_id, u32 stats_id)
-{
-	return 0;
-}
-
 static inline void
 ath11k_debugfs_add_dbring_entry(struct ath11k *ar,
 				enum wmi_direct_buffer_module id,
diff --git a/drivers/net/wireless/ath/ath11k/mac.c b/drivers/net/wireless/ath/ath11k/mac.c
index 5e098780cf23..1550533b5587 100644
--- a/drivers/net/wireless/ath/ath11k/mac.c
+++ b/drivers/net/wireless/ath/ath11k/mac.c
@@ -8997,6 +8997,86 @@ static void ath11k_mac_put_chain_rssi(struct station_info *sinfo,
 	}
 }
 
+static void ath11k_mac_fw_stats_reset(struct ath11k *ar)
+{
+	spin_lock_bh(&ar->data_lock);
+	ath11k_fw_stats_pdevs_free(&ar->fw_stats.pdevs);
+	ath11k_fw_stats_vdevs_free(&ar->fw_stats.vdevs);
+	ar->fw_stats.num_vdev_recvd = 0;
+	ar->fw_stats.num_bcn_recvd = 0;
+	spin_unlock_bh(&ar->data_lock);
+}
+
+int ath11k_mac_fw_stats_request(struct ath11k *ar,
+				struct stats_request_params *req_param)
+{
+	struct ath11k_base *ab = ar->ab;
+	unsigned long time_left;
+	int ret;
+
+	lockdep_assert_held(&ar->conf_mutex);
+
+	ath11k_mac_fw_stats_reset(ar);
+
+	reinit_completion(&ar->fw_stats_complete);
+	reinit_completion(&ar->fw_stats_done);
+
+	ret = ath11k_wmi_send_stats_request_cmd(ar, req_param);
+
+	if (ret) {
+		ath11k_warn(ab, "could not request fw stats (%d)\n",
+			    ret);
+		return ret;
+	}
+
+	time_left = wait_for_completion_timeout(&ar->fw_stats_complete, 1 * HZ);
+	if (!time_left)
+		return -ETIMEDOUT;
+
+	/* FW stats can get split when exceeding the stats data buffer limit.
+	 * In that case, since there is no end marking for the back-to-back
+	 * received 'update stats' event, we keep a 3 seconds timeout in case,
+	 * fw_stats_done is not marked yet
+	 */
+	time_left = wait_for_completion_timeout(&ar->fw_stats_done, 3 * HZ);
+	if (!time_left)
+		return -ETIMEDOUT;
+
+	return 0;
+}
+
+static int ath11k_mac_get_fw_stats(struct ath11k *ar, u32 pdev_id,
+				   u32 vdev_id, u32 stats_id)
+{
+	struct ath11k_base *ab = ar->ab;
+	struct stats_request_params req_param;
+	int ret;
+
+	mutex_lock(&ar->conf_mutex);
+
+	if (ar->state != ATH11K_STATE_ON) {
+		ret = -ENETDOWN;
+		goto err_unlock;
+	}
+
+	req_param.pdev_id = pdev_id;
+	req_param.vdev_id = vdev_id;
+	req_param.stats_id = stats_id;
+
+	ret = ath11k_mac_fw_stats_request(ar, &req_param);
+	if (ret)
+		ath11k_warn(ab, "failed to request fw stats: %d\n", ret);
+
+	ath11k_dbg(ab, ATH11K_DBG_WMI,
+		   "debug get fw stat pdev id %d vdev id %d stats id 0x%x\n",
+		   pdev_id, vdev_id, stats_id);
+
+err_unlock:
+	mutex_unlock(&ar->conf_mutex);
+
+	return ret;
+}
+
 static void ath11k_mac_op_sta_statistics(struct ieee80211_hw *hw,
 					 struct ieee80211_vif *vif,
 					 struct ieee80211_sta *sta,
@@ -9034,8 +9114,8 @@ static void ath11k_mac_op_sta_statistics(struct ieee80211_hw *hw,
 	if (!(sinfo->filled & BIT_ULL(NL80211_STA_INFO_CHAIN_SIGNAL)) &&
 	    arsta->arvif->vdev_type == WMI_VDEV_TYPE_STA &&
 	    ar->ab->hw_params.supports_rssi_stats &&
-	    !ath11k_debugfs_get_fw_stats(ar, ar->pdev->pdev_id, 0,
-					 WMI_REQUEST_RSSI_PER_CHAIN_STAT)) {
+	    !ath11k_mac_get_fw_stats(ar, ar->pdev->pdev_id, 0,
+				     WMI_REQUEST_RSSI_PER_CHAIN_STAT)) {
 		ath11k_mac_put_chain_rssi(sinfo, arsta, "fw stats", true);
 	}
 
@@ -9043,8 +9123,8 @@ static void ath11k_mac_op_sta_statistics(struct ieee80211_hw *hw,
 	if (!signal &&
 	    arsta->arvif->vdev_type == WMI_VDEV_TYPE_STA &&
 	    ar->ab->hw_params.supports_rssi_stats &&
-	    !(ath11k_debugfs_get_fw_stats(ar, ar->pdev->pdev_id, 0,
-					WMI_REQUEST_VDEV_STAT)))
+	    !(ath11k_mac_get_fw_stats(ar, ar->pdev->pdev_id, 0,
+				      WMI_REQUEST_VDEV_STAT)))
 		signal = arsta->rssi_beacon;
 
 	ath11k_dbg(ar->ab, ATH11K_DBG_MAC,
diff --git a/drivers/net/wireless/ath/ath11k/mac.h b/drivers/net/wireless/ath/ath11k/mac.h
index f5800fbecff8..5e61eea1bb03 100644
--- a/drivers/net/wireless/ath/ath11k/mac.h
+++ b/drivers/net/wireless/ath/ath11k/mac.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: BSD-3-Clause-Clear */
 /*
  * Copyright (c) 2018-2019 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2023 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2023, 2025 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #ifndef ATH11K_MAC_H
@@ -179,4 +179,6 @@ int ath11k_mac_vif_set_keepalive(struct ath11k_vif *arvif,
 void ath11k_mac_fill_reg_tpc_info(struct ath11k *ar,
 				  struct ieee80211_vif *vif,
 				  struct ieee80211_chanctx_conf *ctx);
+int ath11k_mac_fw_stats_request(struct ath11k *ar,
+				struct stats_request_params *req_param);
 #endif
diff --git a/drivers/net/wireless/ath/ath11k/wmi.c b/drivers/net/wireless/ath/ath11k/wmi.c
index 27cb0bb06b93..98811726d33b 100644
--- a/drivers/net/wireless/ath/ath11k/wmi.c
+++ b/drivers/net/wireless/ath/ath11k/wmi.c
@@ -8158,6 +8158,11 @@ static void ath11k_peer_assoc_conf_event(struct ath11k_base *ab, struct sk_buff
 static void ath11k_update_stats_event(struct ath11k_base *ab, struct sk_buff *skb)
 {
 	struct ath11k_fw_stats stats = {};
+	size_t total_vdevs_started = 0;
+	struct ath11k_pdev *pdev;
+	bool is_end = true;
+	int i;
+
 	struct ath11k *ar;
 	int ret;
 
@@ -8184,7 +8189,8 @@ static void ath11k_update_stats_event(struct ath11k_base *ab, struct sk_buff *sk
 
 	spin_lock_bh(&ar->data_lock);
 
-	/* WMI_REQUEST_PDEV_STAT can be requested via .get_txpower mac ops or via
+	/* WMI_REQUEST_PDEV_STAT, WMI_REQUEST_VDEV_STAT and
+	 * WMI_REQUEST_RSSI_PER_CHAIN_STAT can be requested via mac ops or via
 	 * debugfs fw stats. Therefore, processing it separately.
 	 */
 	if (stats.stats_id == WMI_REQUEST_PDEV_STAT) {
@@ -8193,9 +8199,40 @@ static void ath11k_update_stats_event(struct ath11k_base *ab, struct sk_buff *sk
 		goto complete;
 	}
 
-	/* WMI_REQUEST_VDEV_STAT, WMI_REQUEST_BCN_STAT and WMI_REQUEST_RSSI_PER_CHAIN_STAT
-	 * are currently requested only via debugfs fw stats. Hence, processing these
-	 * in debugfs context
+	if (stats.stats_id == WMI_REQUEST_RSSI_PER_CHAIN_STAT) {
+		complete(&ar->fw_stats_done);
+		goto complete;
+	}
+
+	if (stats.stats_id == WMI_REQUEST_VDEV_STAT) {
+		if (list_empty(&stats.vdevs)) {
+			ath11k_warn(ab, "empty vdev stats");
+			goto complete;
+		}
+		/* FW sends all the active VDEV stats irrespective of PDEV,
+		 * hence limit until the count of all VDEVs started
+		 */
+		for (i = 0; i < ab->num_radios; i++) {
+			pdev = rcu_dereference(ab->pdevs_active[i]);
+			if (pdev && pdev->ar)
+				total_vdevs_started += ar->num_started_vdevs;
+		}
+
+		if (total_vdevs_started)
+			is_end = ((++ar->fw_stats.num_vdev_recvd) ==
+				  total_vdevs_started);
+
+		list_splice_tail_init(&stats.vdevs,
+				      &ar->fw_stats.vdevs);
+
+		if (is_end)
+			complete(&ar->fw_stats_done);
+
+		goto complete;
+	}
+
+	/* WMI_REQUEST_BCN_STAT is currently requested only via debugfs fw stats.
+	 * Hence, processing it in debugfs context
 	 */
 	ath11k_debugfs_fw_stats_process(ar, &stats);
 

From 81f64165c9dc2d9b070d8240dd369974ebe188d3 Mon Sep 17 00:00:00 2001
From: Baochen Qiang <quic_bqiang@quicinc.com>
Date: Thu, 20 Feb 2025 16:24:46 +0800
Subject: [PATCH 0052/1334] wifi: ath11k: adjust unlock sequence in
 ath11k_update_stats_event()

Currently RCU lock and ar->data_lock are acquired in a sequence of

	rcu_read_lock()
	spin_lock_bh(&ar->data_lock)

but released in a sequence of

	rcu_read_unlock()
	spin_unlock_bh(&ar->data_lock)

Although there are no apparent issues with this, reorder them to
achieve symmetry.

Tested-on: WCN6855 hw2.0 PCI WLAN.HSP.1.1-03125-QCAHSPSWPL_V1_V2_SILICONZ_LITE-3.6510.37

Signed-off-by: Baochen Qiang <quic_bqiang@quicinc.com>
Acked-by: Kalle Valo <kvalo@kernel.org>
Reviewed-by: Vasanthakumar Thiagarajan <vasanthakumar.thiagarajan@oss.qualcomm.com>
Link: https://patch.msgid.link/20250220082448.31039-6-quic_bqiang@quicinc.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath11k/wmi.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/ath11k/wmi.c b/drivers/net/wireless/ath/ath11k/wmi.c
index 98811726d33b..56af2e9634f4 100644
--- a/drivers/net/wireless/ath/ath11k/wmi.c
+++ b/drivers/net/wireless/ath/ath11k/wmi.c
@@ -8238,8 +8238,8 @@ static void ath11k_update_stats_event(struct ath11k_base *ab, struct sk_buff *sk
 
 complete:
 	complete(&ar->fw_stats_complete);
-	rcu_read_unlock();
 	spin_unlock_bh(&ar->data_lock);
+	rcu_read_unlock();
 
 	/* Since the stats's pdev, vdev and beacon list are spliced and reinitialised
 	 * at this point, no need to free the individual list.

From c5b92a2c18938ebb08e8d4062408ab1524da31c3 Mon Sep 17 00:00:00 2001
From: Baochen Qiang <quic_bqiang@quicinc.com>
Date: Thu, 20 Feb 2025 16:24:47 +0800
Subject: [PATCH 0053/1334] wifi: ath11k: move locking outside of
 ath11k_mac_get_fw_stats()

Currently ath11k_mac_get_fw_stats() is acquiring/releasing ar->conf_mutex by itself.
In order to reuse this function in a context where that lock is already taken, move
lock handling to its callers, then the function itself only has to assert it.

There is only one caller now, i.e., ath11k_mac_op_sta_statistics(), so add lock handling
there.

Tested-on: WCN6855 hw2.0 PCI WLAN.HSP.1.1-03125-QCAHSPSWPL_V1_V2_SILICONZ_LITE-3.6510.37

Signed-off-by: Baochen Qiang <quic_bqiang@quicinc.com>
Reviewed-by: Vasanthakumar Thiagarajan <vasanthakumar.thiagarajan@oss.qualcomm.com>
Link: https://patch.msgid.link/20250220082448.31039-7-quic_bqiang@quicinc.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath11k/mac.c | 13 +++++--------
 1 file changed, 5 insertions(+), 8 deletions(-)

diff --git a/drivers/net/wireless/ath/ath11k/mac.c b/drivers/net/wireless/ath/ath11k/mac.c
index 1550533b5587..18e1d78cac45 100644
--- a/drivers/net/wireless/ath/ath11k/mac.c
+++ b/drivers/net/wireless/ath/ath11k/mac.c
@@ -9052,12 +9052,10 @@ static int ath11k_mac_get_fw_stats(struct ath11k *ar, u32 pdev_id,
 	struct stats_request_params req_param;
 	int ret;
 
-	mutex_lock(&ar->conf_mutex);
+	lockdep_assert_held(&ar->conf_mutex);
 
-	if (ar->state != ATH11K_STATE_ON) {
-		ret = -ENETDOWN;
-		goto err_unlock;
-	}
+	if (ar->state != ATH11K_STATE_ON)
+		return -ENETDOWN;
 
 	req_param.pdev_id = pdev_id;
 	req_param.vdev_id = vdev_id;
@@ -9071,9 +9069,6 @@ static int ath11k_mac_get_fw_stats(struct ath11k *ar, u32 pdev_id,
 		   "debug get fw stat pdev id %d vdev id %d stats id 0x%x\n",
 		   pdev_id, vdev_id, stats_id);
 
-err_unlock:
-	mutex_unlock(&ar->conf_mutex);
-
 	return ret;
 }
 
@@ -9111,6 +9106,7 @@ static void ath11k_mac_op_sta_statistics(struct ieee80211_hw *hw,
 
 	ath11k_mac_put_chain_rssi(sinfo, arsta, "ppdu", false);
 
+	mutex_lock(&ar->conf_mutex);
 	if (!(sinfo->filled & BIT_ULL(NL80211_STA_INFO_CHAIN_SIGNAL)) &&
 	    arsta->arvif->vdev_type == WMI_VDEV_TYPE_STA &&
 	    ar->ab->hw_params.supports_rssi_stats &&
@@ -9126,6 +9122,7 @@ static void ath11k_mac_op_sta_statistics(struct ieee80211_hw *hw,
 	    !(ath11k_mac_get_fw_stats(ar, ar->pdev->pdev_id, 0,
 				      WMI_REQUEST_VDEV_STAT)))
 		signal = arsta->rssi_beacon;
+	mutex_unlock(&ar->conf_mutex);
 
 	ath11k_dbg(ar->ab, ATH11K_DBG_MAC,
 		   "sta statistics db2dbm %u rssi comb %d rssi beacon %d\n",

From 29e2adf2ef2966379bd3fe002530b10dfc3030ba Mon Sep 17 00:00:00 2001
From: Baochen Qiang <quic_bqiang@quicinc.com>
Date: Thu, 20 Feb 2025 16:24:48 +0800
Subject: [PATCH 0054/1334] wifi: ath11k: consistently use
 ath11k_mac_get_fw_stats()

Currently to get firmware stats, ath11k_mac_op_get_txpower() calls
ath11k_fw_stats_request() and ath11k_mac_op_sta_statistics() calls
ath11k_mac_get_fw_stats(). Those two helpers are basically doing
the same, except for:

1. ath11k_mac_get_fw_stats() verifies ar->state inside itself.
2. ath11k_mac_get_fw_stats() calls ath11k_mac_fw_stats_request()
   which then calls ath11k_mac_fw_stats_reset() to free pdev/vdev
   stats whereas only pdev stats are freed by ath11k_fw_stats_request().
3. ath11k_mac_get_fw_stats() waits for ar->fw_stats_complete and
   ar->fw_stats_done, whereas ath11k_fw_stats_request() only waits for
   ar->fw_stats_complete.

Change to call ath11k_mac_get_fw_stats() in ath11k_mac_op_get_txpower().
This is valid because:

1. ath11k_mac_op_get_txpower() also has the same request on ar->state.
2. it is harmless to call ath11k_fw_stats_vdevs_free() since
   ar->fw_stats.vdevs should be empty and there should be no one
   expecting it at that time.
3. ath11k_mac_op_get_txpower() only needs pdev stats. For pdev stats,
   ar->fw_stats_done is set to true whenever ar->fw_stats_complete is
   set to true in ath11k_update_stats_event(). So additional wait on
   ar->fw_stats_done does not wast any time.

Tested-on: WCN6855 hw2.0 PCI WLAN.HSP.1.1-03125-QCAHSPSWPL_V1_V2_SILICONZ_LITE-3.6510.37

Signed-off-by: Baochen Qiang <quic_bqiang@quicinc.com>
Reviewed-by: Vasanthakumar Thiagarajan <vasanthakumar.thiagarajan@oss.qualcomm.com>
Link: https://patch.msgid.link/20250220082448.31039-8-quic_bqiang@quicinc.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath11k/mac.c | 44 ++-------------------------
 1 file changed, 2 insertions(+), 42 deletions(-)

diff --git a/drivers/net/wireless/ath/ath11k/mac.c b/drivers/net/wireless/ath/ath11k/mac.c
index 18e1d78cac45..13301ca317a5 100644
--- a/drivers/net/wireless/ath/ath11k/mac.c
+++ b/drivers/net/wireless/ath/ath11k/mac.c
@@ -9457,40 +9457,6 @@ exit:
 	return ret;
 }
 
-static int ath11k_fw_stats_request(struct ath11k *ar,
-				   struct stats_request_params *req_param)
-{
-	struct ath11k_base *ab = ar->ab;
-	unsigned long time_left;
-	int ret;
-
-	lockdep_assert_held(&ar->conf_mutex);
-
-	spin_lock_bh(&ar->data_lock);
-	ath11k_fw_stats_pdevs_free(&ar->fw_stats.pdevs);
-	ar->fw_stats.num_vdev_recvd = 0;
-	ar->fw_stats.num_bcn_recvd = 0;
-	spin_unlock_bh(&ar->data_lock);
-
-	reinit_completion(&ar->fw_stats_complete);
-	reinit_completion(&ar->fw_stats_done);
-
-	ret = ath11k_wmi_send_stats_request_cmd(ar, req_param);
-	if (ret) {
-		ath11k_warn(ab, "could not request fw stats (%d)\n",
-			    ret);
-		return ret;
-	}
-
-	time_left = wait_for_completion_timeout(&ar->fw_stats_complete,
-						1 * HZ);
-
-	if (!time_left)
-		return -ETIMEDOUT;
-
-	return 0;
-}
-
 static int ath11k_mac_op_get_txpower(struct ieee80211_hw *hw,
 				     struct ieee80211_vif *vif,
 				     unsigned int link_id,
@@ -9498,7 +9464,6 @@ static int ath11k_mac_op_get_txpower(struct ieee80211_hw *hw,
 {
 	struct ath11k *ar = hw->priv;
 	struct ath11k_base *ab = ar->ab;
-	struct stats_request_params req_param = {0};
 	struct ath11k_fw_stats_pdev *pdev;
 	int ret;
 
@@ -9510,9 +9475,6 @@ static int ath11k_mac_op_get_txpower(struct ieee80211_hw *hw,
 	 */
 	mutex_lock(&ar->conf_mutex);
 
-	if (ar->state != ATH11K_STATE_ON)
-		goto err_fallback;
-
 	/* Firmware doesn't provide Tx power during CAC hence no need to fetch
 	 * the stats.
 	 */
@@ -9521,10 +9483,8 @@ static int ath11k_mac_op_get_txpower(struct ieee80211_hw *hw,
 		return -EAGAIN;
 	}
 
-	req_param.pdev_id = ar->pdev->pdev_id;
-	req_param.stats_id = WMI_REQUEST_PDEV_STAT;
-
-	ret = ath11k_fw_stats_request(ar, &req_param);
+	ret = ath11k_mac_get_fw_stats(ar, ar->pdev->pdev_id, 0,
+				      WMI_REQUEST_PDEV_STAT);
 	if (ret) {
 		ath11k_warn(ab, "failed to request fw pdev stats: %d\n", ret);
 		goto err_fallback;

From b0d226a60856a1b765bb9a3848c7b2322fd08c47 Mon Sep 17 00:00:00 2001
From: Rodrigo Gobbi <rodrigo.gobbi.7@gmail.com>
Date: Thu, 22 May 2025 17:01:12 -0300
Subject: [PATCH 0055/1334] wifi: ath11k: validate ath11k_crypto_mode on top of
 ath11k_core_qmi_firmware_ready

if ath11k_crypto_mode is invalid (not ATH11K_CRYPT_MODE_SW/ATH11K_CRYPT_MODE_HW),
ath11k_core_qmi_firmware_ready() will not undo some actions that was previously
started/configured. Do the validation as soon as possible in order to avoid
undoing actions in that case and also to fix the following smatch warning:

drivers/net/wireless/ath/ath11k/core.c:2166 ath11k_core_qmi_firmware_ready()
warn: missing unwind goto?

Signed-off-by: Rodrigo Gobbi <rodrigo.gobbi.7@gmail.com>
Reported-by: kernel test robot <lkp@intel.com>
Reported-by: Dan Carpenter <error27@gmail.com>
Closes: https://lore.kernel.org/r/202304151955.oqAetVFd-lkp@intel.com/
Fixes: aa2092a9bab3 ("ath11k: add raw mode and software crypto support")
Reviewed-by: Baochen Qiang <quic_bqiang@quicinc.com>
Link: https://patch.msgid.link/20250522200519.16858-1-rodrigo.gobbi.7@gmail.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath11k/core.c | 28 +++++++++++++-------------
 1 file changed, 14 insertions(+), 14 deletions(-)

diff --git a/drivers/net/wireless/ath/ath11k/core.c b/drivers/net/wireless/ath/ath11k/core.c
index c8c5008be7f2..22a101136135 100644
--- a/drivers/net/wireless/ath/ath11k/core.c
+++ b/drivers/net/wireless/ath/ath11k/core.c
@@ -2135,6 +2135,20 @@ int ath11k_core_qmi_firmware_ready(struct ath11k_base *ab)
 {
 	int ret;
 
+	switch (ath11k_crypto_mode) {
+	case ATH11K_CRYPT_MODE_SW:
+		set_bit(ATH11K_FLAG_HW_CRYPTO_DISABLED, &ab->dev_flags);
+		set_bit(ATH11K_FLAG_RAW_MODE, &ab->dev_flags);
+		break;
+	case ATH11K_CRYPT_MODE_HW:
+		clear_bit(ATH11K_FLAG_HW_CRYPTO_DISABLED, &ab->dev_flags);
+		clear_bit(ATH11K_FLAG_RAW_MODE, &ab->dev_flags);
+		break;
+	default:
+		ath11k_info(ab, "invalid crypto_mode: %d\n", ath11k_crypto_mode);
+		return -EINVAL;
+	}
+
 	ret = ath11k_core_start_firmware(ab, ab->fw_mode);
 	if (ret) {
 		ath11k_err(ab, "failed to start firmware: %d\n", ret);
@@ -2153,20 +2167,6 @@ int ath11k_core_qmi_firmware_ready(struct ath11k_base *ab)
 		goto err_firmware_stop;
 	}
 
-	switch (ath11k_crypto_mode) {
-	case ATH11K_CRYPT_MODE_SW:
-		set_bit(ATH11K_FLAG_HW_CRYPTO_DISABLED, &ab->dev_flags);
-		set_bit(ATH11K_FLAG_RAW_MODE, &ab->dev_flags);
-		break;
-	case ATH11K_CRYPT_MODE_HW:
-		clear_bit(ATH11K_FLAG_HW_CRYPTO_DISABLED, &ab->dev_flags);
-		clear_bit(ATH11K_FLAG_RAW_MODE, &ab->dev_flags);
-		break;
-	default:
-		ath11k_info(ab, "invalid crypto_mode: %d\n", ath11k_crypto_mode);
-		return -EINVAL;
-	}
-
 	if (ath11k_frame_mode == ATH11K_HW_TXRX_RAW)
 		set_bit(ATH11K_FLAG_RAW_MODE, &ab->dev_flags);
 

From 7588a893cde5385ad308400ff167d29a29913b3a Mon Sep 17 00:00:00 2001
From: Baochen Qiang <quic_bqiang@quicinc.com>
Date: Fri, 23 May 2025 10:23:05 +0800
Subject: [PATCH 0056/1334] wifi: ath12k: fix GCC_GCC_PCIE_HOT_RST definition
 for WCN7850

GCC_GCC_PCIE_HOT_RST is wrongly defined for WCN7850, causing kernel crash
on some specific platforms.

Since this register is divergent for WCN7850 and QCN9274, move it to
register table to allow different definitions. Then correct the register
address for WCN7850 to fix this issue.

Note IPQ5332 is not affected as it is not PCIe based device.

Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.0.c5-00481-QCAHMTSWPL_V1.0_V2.0_SILICONZ-3

Signed-off-by: Baochen Qiang <quic_bqiang@quicinc.com>
Reviewed-by: Vasanthakumar Thiagarajan <vasanthakumar.thiagarajan@oss.qualcomm.com>
Reported-by: Parth Pancholi <parth.pancholi@toradex.com>
Closes: https://lore.kernel.org/all/86899b2235a59c9134603beebe08f2bb0b244ea0.camel@gmail.com
Fixes: d889913205cf ("wifi: ath12k: driver for Qualcomm Wi-Fi 7 devices")
Tested-by: Parth Pancholi <parth.pancholi@toradex.com>
Link: https://patch.msgid.link/20250523-ath12k-wrong-global-reset-addr-v1-1-3b06eb556196@quicinc.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/hw.c  | 6 ++++++
 drivers/net/wireless/ath/ath12k/hw.h  | 2 ++
 drivers/net/wireless/ath/ath12k/pci.c | 6 +++---
 drivers/net/wireless/ath/ath12k/pci.h | 4 +++-
 4 files changed, 14 insertions(+), 4 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/hw.c b/drivers/net/wireless/ath/ath12k/hw.c
index 7e2cf0fb2085..8254dc10b53b 100644
--- a/drivers/net/wireless/ath/ath12k/hw.c
+++ b/drivers/net/wireless/ath/ath12k/hw.c
@@ -951,6 +951,8 @@ static const struct ath12k_hw_regs qcn9274_v1_regs = {
 	.hal_umac_ce0_dest_reg_base = 0x01b81000,
 	.hal_umac_ce1_src_reg_base = 0x01b82000,
 	.hal_umac_ce1_dest_reg_base = 0x01b83000,
+
+	.gcc_gcc_pcie_hot_rst = 0x1e38338,
 };
 
 static const struct ath12k_hw_regs qcn9274_v2_regs = {
@@ -1042,6 +1044,8 @@ static const struct ath12k_hw_regs qcn9274_v2_regs = {
 	.hal_umac_ce0_dest_reg_base = 0x01b81000,
 	.hal_umac_ce1_src_reg_base = 0x01b82000,
 	.hal_umac_ce1_dest_reg_base = 0x01b83000,
+
+	.gcc_gcc_pcie_hot_rst = 0x1e38338,
 };
 
 static const struct ath12k_hw_regs ipq5332_regs = {
@@ -1215,6 +1219,8 @@ static const struct ath12k_hw_regs wcn7850_regs = {
 	.hal_umac_ce0_dest_reg_base = 0x01b81000,
 	.hal_umac_ce1_src_reg_base = 0x01b82000,
 	.hal_umac_ce1_dest_reg_base = 0x01b83000,
+
+	.gcc_gcc_pcie_hot_rst = 0x1e40304,
 };
 
 static const struct ath12k_hw_hal_params ath12k_hw_hal_params_qcn9274 = {
diff --git a/drivers/net/wireless/ath/ath12k/hw.h b/drivers/net/wireless/ath/ath12k/hw.h
index 0fbc17649df4..0a75bc5abfa2 100644
--- a/drivers/net/wireless/ath/ath12k/hw.h
+++ b/drivers/net/wireless/ath/ath12k/hw.h
@@ -375,6 +375,8 @@ struct ath12k_hw_regs {
 	u32 hal_reo_cmd_ring_base;
 
 	u32 hal_reo_status_ring_base;
+
+	u32 gcc_gcc_pcie_hot_rst;
 };
 
 static inline const char *ath12k_bd_ie_type_str(enum ath12k_bd_ie_type type)
diff --git a/drivers/net/wireless/ath/ath12k/pci.c b/drivers/net/wireless/ath/ath12k/pci.c
index 489d546390fc..1f3cfd9b89fd 100644
--- a/drivers/net/wireless/ath/ath12k/pci.c
+++ b/drivers/net/wireless/ath/ath12k/pci.c
@@ -292,10 +292,10 @@ static void ath12k_pci_enable_ltssm(struct ath12k_base *ab)
 
 	ath12k_dbg(ab, ATH12K_DBG_PCI, "pci ltssm 0x%x\n", val);
 
-	val = ath12k_pci_read32(ab, GCC_GCC_PCIE_HOT_RST);
+	val = ath12k_pci_read32(ab, GCC_GCC_PCIE_HOT_RST(ab));
 	val |= GCC_GCC_PCIE_HOT_RST_VAL;
-	ath12k_pci_write32(ab, GCC_GCC_PCIE_HOT_RST, val);
-	val = ath12k_pci_read32(ab, GCC_GCC_PCIE_HOT_RST);
+	ath12k_pci_write32(ab, GCC_GCC_PCIE_HOT_RST(ab), val);
+	val = ath12k_pci_read32(ab, GCC_GCC_PCIE_HOT_RST(ab));
 
 	ath12k_dbg(ab, ATH12K_DBG_PCI, "pci pcie_hot_rst 0x%x\n", val);
 
diff --git a/drivers/net/wireless/ath/ath12k/pci.h b/drivers/net/wireless/ath/ath12k/pci.h
index 0b4c459d6d8e..d1ec8aad7f6c 100644
--- a/drivers/net/wireless/ath/ath12k/pci.h
+++ b/drivers/net/wireless/ath/ath12k/pci.h
@@ -28,7 +28,9 @@
 #define PCIE_PCIE_PARF_LTSSM			0x1e081b0
 #define PARM_LTSSM_VALUE			0x111
 
-#define GCC_GCC_PCIE_HOT_RST			0x1e38338
+#define GCC_GCC_PCIE_HOT_RST(ab) \
+	((ab)->hw_params->regs->gcc_gcc_pcie_hot_rst)
+
 #define GCC_GCC_PCIE_HOT_RST_VAL		0x10
 
 #define PCIE_PCIE_INT_ALL_CLEAR			0x1e08228

From b6bca6d7149e0bc1a56e831af0296d45688945ec Mon Sep 17 00:00:00 2001
From: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
Date: Thu, 5 Jun 2025 10:27:22 -0700
Subject: [PATCH 0057/1334] wifi: ath12k: Fix hal_reo_cmd_status kernel-doc

Currently a warning is reported when running:

% scripts/kernel-doc -Wall -Werror -none drivers/net/wireless/ath/ath12k/hal.h
Warning: drivers/net/wireless/ath/ath12k/hal.h:596 Enum value 'HAL_REO_CMD_RESOURCE_BLOCKED' not described in enum 'hal_reo_cmd_status'

Add the missing description of HAL_REO_CMD_RESOURCE_BLOCKED.

Link: https://patch.msgid.link/20250605-hal_reo_cmd_status-kdoc-v1-1-e59f4b814b88@oss.qualcomm.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/hal.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/ath12k/hal.h b/drivers/net/wireless/ath/ath12k/hal.h
index 0ee9c6b26dab..c1750b5dc03c 100644
--- a/drivers/net/wireless/ath/ath12k/hal.h
+++ b/drivers/net/wireless/ath/ath12k/hal.h
@@ -585,7 +585,8 @@ enum hal_reo_cmd_type {
  *			 or cache was blocked
  * @HAL_REO_CMD_FAILED: Command execution failed, could be due to
  *			invalid queue desc
- * @HAL_REO_CMD_RESOURCE_BLOCKED:
+ * @HAL_REO_CMD_RESOURCE_BLOCKED: Command could not be executed because
+ *				  one or more descriptors were blocked
  * @HAL_REO_CMD_DRAIN:
  */
 enum hal_reo_cmd_status {

From f3fe49dbddd73f0155a8935af47cb63693069dbe Mon Sep 17 00:00:00 2001
From: Miaoqing Pan <miaoqing.pan@oss.qualcomm.com>
Date: Wed, 4 Jun 2025 13:52:50 +0800
Subject: [PATCH 0058/1334] wifi: ath12k: fix uaf in ath12k_core_init()

When the execution of ath12k_core_hw_group_assign() or
ath12k_core_hw_group_create() fails, the registered notifier chain is not
unregistered properly. Its memory is freed after rmmod, which may trigger
to a use-after-free (UAF) issue if there is a subsequent access to this
notifier chain.

Fixes the issue by calling ath12k_core_panic_notifier_unregister() in
failure cases.

Call trace:
 notifier_chain_register+0x4c/0x1f0 (P)
 atomic_notifier_chain_register+0x38/0x68
 ath12k_core_init+0x50/0x4e8 [ath12k]
 ath12k_pci_probe+0x5f8/0xc28 [ath12k]
 pci_device_probe+0xbc/0x1a8
 really_probe+0xc8/0x3a0
 __driver_probe_device+0x84/0x1b0
 driver_probe_device+0x44/0x130
 __driver_attach+0xcc/0x208
 bus_for_each_dev+0x84/0x100
 driver_attach+0x2c/0x40
 bus_add_driver+0x130/0x260
 driver_register+0x70/0x138
 __pci_register_driver+0x68/0x80
 ath12k_pci_init+0x30/0x68 [ath12k]
 ath12k_init+0x28/0x78 [ath12k]

Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.0.c5-00481-QCAHMTSWPL_V1.0_V2.0_SILICONZ-3

Fixes: 6f245ea0ec6c ("wifi: ath12k: introduce device group abstraction")
Signed-off-by: Miaoqing Pan <miaoqing.pan@oss.qualcomm.com>
Reviewed-by: Baochen Qiang <quic_bqiang@quicinc.com>
Link: https://patch.msgid.link/20250604055250.1228501-1-miaoqing.pan@oss.qualcomm.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/core.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/core.c b/drivers/net/wireless/ath/ath12k/core.c
index 31d851d8e688..ebc0560d40e3 100644
--- a/drivers/net/wireless/ath/ath12k/core.c
+++ b/drivers/net/wireless/ath/ath12k/core.c
@@ -2129,7 +2129,8 @@ int ath12k_core_init(struct ath12k_base *ab)
 	if (!ag) {
 		mutex_unlock(&ath12k_hw_group_mutex);
 		ath12k_warn(ab, "unable to get hw group\n");
-		return -ENODEV;
+		ret = -ENODEV;
+		goto err_unregister_notifier;
 	}
 
 	mutex_unlock(&ath12k_hw_group_mutex);
@@ -2144,7 +2145,7 @@ int ath12k_core_init(struct ath12k_base *ab)
 		if (ret) {
 			mutex_unlock(&ag->mutex);
 			ath12k_warn(ab, "unable to create hw group\n");
-			goto err;
+			goto err_destroy_hw_group;
 		}
 	}
 
@@ -2152,9 +2153,12 @@ int ath12k_core_init(struct ath12k_base *ab)
 
 	return 0;
 
-err:
+err_destroy_hw_group:
 	ath12k_core_hw_group_destroy(ab->ag);
 	ath12k_core_hw_group_unassign(ab);
+err_unregister_notifier:
+	ath12k_core_panic_notifier_unregister(ab);
+
 	return ret;
 }
 

From 22188b9df60dde48eaba276da22062aaf8e12dfe Mon Sep 17 00:00:00 2001
From: Harshit Mogalapalli <harshit.m.mogalapalli@oracle.com>
Date: Tue, 3 Jun 2025 14:48:13 -0700
Subject: [PATCH 0059/1334] ASoC: cs48l32: Fix a signedness bug in
 cs48l32_hw_params()

There is a type promotion that can happen when freq(u32) variable is
comapared with sclk_target(integer), when sclk_target is a negative
value it promotes to a large postive integer which might not be a
problem in this particular case as the condition evaluates to false
when that happens, but bail out early when sclk_target has negative
error codes.

	cs48l32_sclk_rates[i].freq >= sclk_target

Fix this by adding a negative error check when
snd_soc_tdm_params_to_bclk() fails

Fixes: e2bcbf99d045 ("ASoC: cs48l32: Add driver for Cirrus Logic CS48L32 audio DSP")
Signed-off-by: Harshit Mogalapalli <harshit.m.mogalapalli@oracle.com>
Link: https://patch.msgid.link/20250603214813.197346-1-harshit.m.mogalapalli@oracle.com
Reviewed-by: Richard Fitzgerald <rf@opensource.cirrus.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/cs48l32.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/sound/soc/codecs/cs48l32.c b/sound/soc/codecs/cs48l32.c
index 90a795230d27..9bdd48aab42a 100644
--- a/sound/soc/codecs/cs48l32.c
+++ b/sound/soc/codecs/cs48l32.c
@@ -2162,6 +2162,10 @@ static int cs48l32_hw_params(struct snd_pcm_substream *substream,
 		n_slots_multiple = 1;
 
 	sclk_target = snd_soc_tdm_params_to_bclk(params, slotw, n_slots, n_slots_multiple);
+	if (sclk_target < 0) {
+		cs48l32_asp_err(dai, "Invalid parameters\n");
+		return sclk_target;
+	}
 
 	for (i = 0; i < ARRAY_SIZE(cs48l32_sclk_rates); i++) {
 		if ((cs48l32_sclk_rates[i].freq >= sclk_target) &&

From b44b2694005b501b2eaeb56aa778f3ca22de4659 Mon Sep 17 00:00:00 2001
From: Zhang Yi <zhangyi@everest-semi.com>
Date: Wed, 4 Jun 2025 14:18:21 +0800
Subject: [PATCH 0060/1334] ASoC: codecs: ES8326: Modify initialization
 configuration

Modify the value of ES8326_SDINOUT1_IO in the initialization

Signed-off-by: Zhang Yi <zhangyi@everest-semi.com>
Link: https://patch.msgid.link/20250604061821.2678-1-zhangyi@everest-semi.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/es8326.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/sound/soc/codecs/es8326.c b/sound/soc/codecs/es8326.c
index 066d92b54312..78c4e68f6002 100644
--- a/sound/soc/codecs/es8326.c
+++ b/sound/soc/codecs/es8326.c
@@ -1079,8 +1079,7 @@ static void es8326_init(struct snd_soc_component *component)
 	regmap_update_bits(es8326->regmap, ES8326_HPDET_TYPE, 0x03, 0x00);
 	regmap_write(es8326->regmap, ES8326_INTOUT_IO,
 		     es8326->interrupt_clk);
-	regmap_write(es8326->regmap, ES8326_SDINOUT1_IO,
-		    (ES8326_IO_DMIC_CLK << ES8326_SDINOUT1_SHIFT));
+	regmap_write(es8326->regmap, ES8326_SDINOUT1_IO, ES8326_IO_INPUT);
 	regmap_write(es8326->regmap, ES8326_SDINOUT23_IO, ES8326_IO_INPUT);
 
 	regmap_write(es8326->regmap, ES8326_ANA_PDN, 0x00);

From a4e469c1e2e0ec7f08fff9ed29f5500f187ba9f2 Mon Sep 17 00:00:00 2001
From: Huacai Chen <chenhuacai@loongson.cn>
Date: Sun, 8 Jun 2025 22:27:37 +0800
Subject: [PATCH 0061/1334] ASoC: loongson: Fix build warnings about export.h

After commit 25704938c86d7b2 ("scripts/misc-check: check missing #include
<linux/export.h> when W=1") and 1239f681359926101e ("scripts/misc-check:
check unnecessary #include <linux/export.h> when W=1"), we get some build
warnings with W=1:

sound/soc/loongson/loongson_i2s.c: warning: EXPORT_SYMBOL() is used, but #include <linux/export.h> is missing

So fix these build warnings for ASoC/Loongson.

Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
Link: https://patch.msgid.link/20250608142737.168829-1-chenhuacai@loongson.cn
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/loongson/loongson_i2s.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/soc/loongson/loongson_i2s.c b/sound/soc/loongson/loongson_i2s.c
index e8852a30f213..e336656e13eb 100644
--- a/sound/soc/loongson/loongson_i2s.c
+++ b/sound/soc/loongson/loongson_i2s.c
@@ -9,6 +9,7 @@
 #include <linux/module.h>
 #include <linux/platform_device.h>
 #include <linux/delay.h>
+#include <linux/export.h>
 #include <linux/pm_runtime.h>
 #include <linux/dma-mapping.h>
 #include <sound/soc.h>

From 06118ae36855b7d3d22688298e74a766ccf0cb7a Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Tue, 27 May 2025 08:44:14 +0300
Subject: [PATCH 0062/1334] regulator: max20086: Fix refcount leak in
 max20086_parse_regulators_dt()

There is a missing call to of_node_put() if devm_kcalloc() fails.
Fix this by changing the code to use cleanup.h magic to drop the
refcount.

Fixes: 6b0cd72757c6 ("regulator: max20086: fix invalid memory access")
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Link: https://patch.msgid.link/aDVRLqgJWMxYU03G@stanley.mountain
Reviewed-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/regulator/max20086-regulator.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/regulator/max20086-regulator.c b/drivers/regulator/max20086-regulator.c
index b4fe76e33ff2..fcdd2d0317a5 100644
--- a/drivers/regulator/max20086-regulator.c
+++ b/drivers/regulator/max20086-regulator.c
@@ -5,6 +5,7 @@
 // Copyright (C) 2022 Laurent Pinchart <laurent.pinchart@idesonboard.com>
 // Copyright (C) 2018 Avnet, Inc.
 
+#include <linux/cleanup.h>
 #include <linux/err.h>
 #include <linux/gpio/consumer.h>
 #include <linux/i2c.h>
@@ -133,11 +134,11 @@ static int max20086_regulators_register(struct max20086 *chip)
 static int max20086_parse_regulators_dt(struct max20086 *chip, bool *boot_on)
 {
 	struct of_regulator_match *matches;
-	struct device_node *node;
 	unsigned int i;
 	int ret;
 
-	node = of_get_child_by_name(chip->dev->of_node, "regulators");
+	struct device_node *node __free(device_node) =
+		of_get_child_by_name(chip->dev->of_node, "regulators");
 	if (!node) {
 		dev_err(chip->dev, "regulators node not found\n");
 		return -ENODEV;
@@ -153,7 +154,6 @@ static int max20086_parse_regulators_dt(struct max20086 *chip, bool *boot_on)
 
 	ret = of_regulator_match(chip->dev, node, matches,
 				 chip->info->num_outputs);
-	of_node_put(node);
 	if (ret < 0) {
 		dev_err(chip->dev, "Failed to match regulators\n");
 		return -EINVAL;

From a5bf5272295d3f058adeee025d2a0b6625f8ba7b Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?F=C3=A9lix=20Pi=C3=A9dallu?= <felix.piedallu@non.se.com>
Date: Fri, 6 Jun 2025 15:37:24 +0200
Subject: [PATCH 0063/1334] spi: omap2-mcspi: Disable multi mode when CS should
 be kept asserted after message
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When the last transfer of a SPI message has the cs_change flag, the CS is kept
asserted after the message.
Multi-mode can't respect this as CS is deasserted by the hardware at the end of
the message.

Disable multi-mode when not applicable to the current message.

Fixes: d153ff4056cb ("spi: omap2-mcspi: Add support for MULTI-mode")
Signed-off-by: Félix Piédallu <felix.piedallu@non.se.com>
Link: https://patch.msgid.link/20250606-cs_change_fix-v1-1-27191a98a2e5@non.se.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-omap2-mcspi.c | 12 +++++++++---
 1 file changed, 9 insertions(+), 3 deletions(-)

diff --git a/drivers/spi/spi-omap2-mcspi.c b/drivers/spi/spi-omap2-mcspi.c
index 29c616e2c408..e834fb42fd4b 100644
--- a/drivers/spi/spi-omap2-mcspi.c
+++ b/drivers/spi/spi-omap2-mcspi.c
@@ -1287,9 +1287,15 @@ static int omap2_mcspi_prepare_message(struct spi_controller *ctlr,
 			mcspi->use_multi_mode = false;
 		}
 
-		/* Check if transfer asks to change the CS status after the transfer */
-		if (!tr->cs_change)
-			mcspi->use_multi_mode = false;
+		if (list_is_last(&tr->transfer_list, &msg->transfers)) {
+			/* Check if transfer asks to keep the CS status after the whole message */
+			if (tr->cs_change)
+				mcspi->use_multi_mode = false;
+		} else {
+			/* Check if transfer asks to change the CS status after the transfer */
+			if (!tr->cs_change)
+				mcspi->use_multi_mode = false;
+		}
 
 		/*
 		 * If at least one message is not compatible, switch back to single mode

From 10c24e0d2f7cd2bc8a847cf750f01301ce67dbc8 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?F=C3=A9lix=20Pi=C3=A9dallu?= <felix.piedallu@non.se.com>
Date: Fri, 6 Jun 2025 15:37:25 +0200
Subject: [PATCH 0064/1334] spi: omap2-mcspi: Disable multi-mode when the
 previous message kept CS asserted
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When the last transfer of a SPI message has the cs_change flag, the CS is kept
asserted after the message.
The next message can't use multi-mode because the CS will be briefly deasserted
before the first transfer.

Remove the early exit of the list_for_each_entry because the last transfer
actually needs to be always checked.

Fixes: d153ff4056cb ("spi: omap2-mcspi: Add support for MULTI-mode")
Signed-off-by: Félix Piédallu <felix.piedallu@non.se.com>
Link: https://patch.msgid.link/20250606-cs_change_fix-v1-2-27191a98a2e5@non.se.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-omap2-mcspi.c | 20 ++++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

diff --git a/drivers/spi/spi-omap2-mcspi.c b/drivers/spi/spi-omap2-mcspi.c
index e834fb42fd4b..70bb74b3bd9c 100644
--- a/drivers/spi/spi-omap2-mcspi.c
+++ b/drivers/spi/spi-omap2-mcspi.c
@@ -134,6 +134,7 @@ struct omap2_mcspi {
 	size_t			max_xfer_len;
 	u32			ref_clk_hz;
 	bool			use_multi_mode;
+	bool			last_msg_kept_cs;
 };
 
 struct omap2_mcspi_cs {
@@ -1269,6 +1270,10 @@ static int omap2_mcspi_prepare_message(struct spi_controller *ctlr,
 	 * multi-mode is applicable.
 	 */
 	mcspi->use_multi_mode = true;
+
+	if (mcspi->last_msg_kept_cs)
+		mcspi->use_multi_mode = false;
+
 	list_for_each_entry(tr, &msg->transfers, transfer_list) {
 		if (!tr->bits_per_word)
 			bits_per_word = msg->spi->bits_per_word;
@@ -1289,22 +1294,17 @@ static int omap2_mcspi_prepare_message(struct spi_controller *ctlr,
 
 		if (list_is_last(&tr->transfer_list, &msg->transfers)) {
 			/* Check if transfer asks to keep the CS status after the whole message */
-			if (tr->cs_change)
+			if (tr->cs_change) {
 				mcspi->use_multi_mode = false;
+				mcspi->last_msg_kept_cs = true;
+			} else {
+				mcspi->last_msg_kept_cs = false;
+			}
 		} else {
 			/* Check if transfer asks to change the CS status after the transfer */
 			if (!tr->cs_change)
 				mcspi->use_multi_mode = false;
 		}
-
-		/*
-		 * If at least one message is not compatible, switch back to single mode
-		 *
-		 * The bits_per_word of certain transfer can be different, but it will have no
-		 * impact on the signal itself.
-		 */
-		if (!mcspi->use_multi_mode)
-			break;
 	}
 
 	omap2_mcspi_set_mode(ctlr);

From 1dd630088332b5b310f3dd7eaacae9f3c4465651 Mon Sep 17 00:00:00 2001
From: Huacai Chen <chenhuacai@loongson.cn>
Date: Sun, 8 Jun 2025 22:29:39 +0800
Subject: [PATCH 0065/1334] spi: loongson: Fix build warnings about export.h

After commit a934a57a42f64a4 ("scripts/misc-check: check missing #include
<linux/export.h> when W=1") and 7d95680d64ac8e836c ("scripts/misc-check:
check unnecessary #include <linux/export.h> when W=1"), we get some build
warnings with W=1:

drivers/spi/spi-loongson-core.c: warning: EXPORT_SYMBOL() is used, but #include <linux/export.h> is missing

So fix these build warnings for SPI/Loongson.

Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
Link: https://patch.msgid.link/20250608142939.172108-1-chenhuacai@loongson.cn
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-loongson-core.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/spi/spi-loongson-core.c b/drivers/spi/spi-loongson-core.c
index 4fec226456d1..b46f072a0387 100644
--- a/drivers/spi/spi-loongson-core.c
+++ b/drivers/spi/spi-loongson-core.c
@@ -5,6 +5,7 @@
 #include <linux/clk.h>
 #include <linux/delay.h>
 #include <linux/err.h>
+#include <linux/export.h>
 #include <linux/init.h>
 #include <linux/interrupt.h>
 #include <linux/io.h>

From 2b74aea6d078ade810a3b0f7d1bcfcba2eaad416 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Fri, 6 Jun 2025 12:04:14 +0300
Subject: [PATCH 0066/1334] spi: spi-pci1xxxx: Fix error code in probe

Return the error code if pci_alloc_irq_vectors() fails.  Don't return
success.

Fixes: b4608e944177 ("spi: spi-pci1xxxx: Fix Probe failure with Dual SPI instance with INTx interrupts")
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Reviewed-by: Thangaraj Samynathan <thangaraj.s@microchip.com>
Link: https://patch.msgid.link/aEKvDrUxD19GWi0u@stanley.mountain
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-pci1xxxx.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/spi/spi-pci1xxxx.c b/drivers/spi/spi-pci1xxxx.c
index c6489e90b8b9..9112d8a1a0c8 100644
--- a/drivers/spi/spi-pci1xxxx.c
+++ b/drivers/spi/spi-pci1xxxx.c
@@ -765,7 +765,7 @@ static int pci1xxxx_spi_probe(struct pci_dev *pdev, const struct pci_device_id *
 							   PCI_IRQ_ALL_TYPES);
 			if (num_vector < 0) {
 				dev_err(&pdev->dev, "Error allocating MSI vectors\n");
-				return ret;
+				return num_vector;
 			}
 
 			init_completion(&spi_sub_ptr->spi_xfer_done);

From 83c4c67076c209787515e06fffd41dd0bdab09b9 Mon Sep 17 00:00:00 2001
From: "James A. MacInnes" <james.a.macinnes@gmail.com>
Date: Wed, 12 Feb 2025 15:03:46 -0800
Subject: [PATCH 0067/1334] drm/msm/dp: Disable wide bus support for SDM845

When widebus was enabled for DisplayPort in commit c7c412202623
("drm/msm/dp: enable widebus on all relevant chipsets") it was clarified
that it is only supported on DPU 5.0.0 onwards which includes SC7180 on
DPU revision 6.2.  However, this patch missed that the description
structure for SC7180 is also reused for SDM845 (because of identical
io_start address) which is only DPU 4.0.0, leading to a wrongly enbled
widebus feature and corruption on that platform.

Create a separate msm_dp_desc_sdm845 structure for this SoC compatible,
with the wide_bus_supported flag turned off.

Fixes: c7c412202623 ("drm/msm/dp: enable widebus on all relevant chipsets")
Signed-off-by: James A. MacInnes <james.a.macinnes@gmail.com>
[DB: reworded commit text following Marijn's suggestion]
Reviewed-by: Abhinav Kumar <quic_abhinavk@quicinc.com>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Patchwork: https://patchwork.freedesktop.org/patch/636944/
Link: https://lore.kernel.org/r/20250212-sdm845_dp-v2-1-4954e51458f4@gmail.com
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
---
 drivers/gpu/drm/msm/dp/dp_display.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/msm/dp/dp_display.c b/drivers/gpu/drm/msm/dp/dp_display.c
index 386c4669c831..a48e6db4f156 100644
--- a/drivers/gpu/drm/msm/dp/dp_display.c
+++ b/drivers/gpu/drm/msm/dp/dp_display.c
@@ -128,6 +128,11 @@ static const struct msm_dp_desc msm_dp_desc_sa8775p[] = {
 	{}
 };
 
+static const struct msm_dp_desc msm_dp_desc_sdm845[] = {
+	{ .io_start = 0x0ae90000, .id = MSM_DP_CONTROLLER_0 },
+	{}
+};
+
 static const struct msm_dp_desc msm_dp_desc_sc7180[] = {
 	{ .io_start = 0x0ae90000, .id = MSM_DP_CONTROLLER_0, .wide_bus_supported = true },
 	{}
@@ -180,7 +185,7 @@ static const struct of_device_id msm_dp_dt_match[] = {
 	{ .compatible = "qcom,sc8180x-edp", .data = &msm_dp_desc_sc8180x },
 	{ .compatible = "qcom,sc8280xp-dp", .data = &msm_dp_desc_sc8280xp },
 	{ .compatible = "qcom,sc8280xp-edp", .data = &msm_dp_desc_sc8280xp },
-	{ .compatible = "qcom,sdm845-dp", .data = &msm_dp_desc_sc7180 },
+	{ .compatible = "qcom,sdm845-dp", .data = &msm_dp_desc_sdm845 },
 	{ .compatible = "qcom,sm8350-dp", .data = &msm_dp_desc_sc7180 },
 	{ .compatible = "qcom,sm8650-dp", .data = &msm_dp_desc_sm8650 },
 	{ .compatible = "qcom,x1e80100-dp", .data = &msm_dp_desc_x1e80100 },

From 146e87f3e11de0dfa091ff87e34b4bc6eec761a4 Mon Sep 17 00:00:00 2001
From: "James A. MacInnes" <james.a.macinnes@gmail.com>
Date: Wed, 12 Feb 2025 15:03:47 -0800
Subject: [PATCH 0068/1334] drm/msm/disp: Correct porch timing for SDM845

Type-C DisplayPort inoperable due to incorrect porch settings.
- Re-used wide_bus_en as flag to prevent porch shifting

Fixes: c943b4948b58 ("drm/msm/dp: add displayPort driver support")
Signed-off-by: James A. MacInnes <james.a.macinnes@gmail.com>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
Patchwork: https://patchwork.freedesktop.org/patch/636945/
Link: https://lore.kernel.org/r/20250212-sdm845_dp-v2-2-4954e51458f4@gmail.com
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
---
 .../gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c   | 14 +++++++++-----
 1 file changed, 9 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c
index 8a618841e3ea..1c468ca5d692 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c
@@ -94,17 +94,21 @@ static void drm_mode_to_intf_timing_params(
 		timing->vsync_polarity = 0;
 	}
 
-	/* for DP/EDP, Shift timings to align it to bottom right */
-	if (phys_enc->hw_intf->cap->type == INTF_DP) {
+	timing->wide_bus_en = dpu_encoder_is_widebus_enabled(phys_enc->parent);
+	timing->compression_en = dpu_encoder_is_dsc_enabled(phys_enc->parent);
+
+	/*
+	 *  For DP/EDP, Shift timings to align it to bottom right.
+	 *  wide_bus_en is set for everything excluding SDM845 &
+	 *  porch changes cause DisplayPort failure and HDMI tearing.
+	 */
+	if (phys_enc->hw_intf->cap->type == INTF_DP && timing->wide_bus_en) {
 		timing->h_back_porch += timing->h_front_porch;
 		timing->h_front_porch = 0;
 		timing->v_back_porch += timing->v_front_porch;
 		timing->v_front_porch = 0;
 	}
 
-	timing->wide_bus_en = dpu_encoder_is_widebus_enabled(phys_enc->parent);
-	timing->compression_en = dpu_encoder_is_dsc_enabled(phys_enc->parent);
-
 	/*
 	 * for DP, divide the horizonal parameters by 2 when
 	 * widebus is enabled

From 8a48e35becb214743214f5504e726c3ec131cd6d Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Tue, 20 May 2025 13:13:26 +0200
Subject: [PATCH 0069/1334] drm/msm/dsi/dsi_phy_10nm: Fix missing initial VCO
 rate

Driver unconditionally saves current state on first init in
dsi_pll_10nm_init(), but does not save the VCO rate, only some of the
divider registers.  The state is then restored during probe/enable via
msm_dsi_phy_enable() -> msm_dsi_phy_pll_restore_state() ->
dsi_10nm_pll_restore_state().

Restoring calls dsi_pll_10nm_vco_set_rate() with
pll_10nm->vco_current_rate=0, which basically overwrites existing rate of
VCO and messes with clock hierarchy, by setting frequency to 0 to clock
tree.  This makes anyway little sense - VCO rate was not saved, so
should not be restored.

If PLL was not configured configure it to minimum rate to avoid glitches
and configuring entire in clock hierarchy to 0 Hz.

Suggested-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
Link: https://lore.kernel.org/r/sz4kbwy5nwsebgf64ia7uq4ee7wbsa5uy3xmlqwcstsbntzcov@ew3dcyjdzmi2/
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Fixes: a4ccc37693a2 ("drm/msm/dsi_pll_10nm: restore VCO rate during
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
Patchwork: https://patchwork.freedesktop.org/patch/654796/
Link: https://lore.kernel.org/r/20250520111325.92352-2-krzysztof.kozlowski@linaro.org
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
---
 drivers/gpu/drm/msm/dsi/phy/dsi_phy_10nm.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_10nm.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_10nm.c
index 9812b4d69197..af2e30f3f842 100644
--- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_10nm.c
+++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_10nm.c
@@ -704,6 +704,13 @@ static int dsi_pll_10nm_init(struct msm_dsi_phy *phy)
 	/* TODO: Remove this when we have proper display handover support */
 	msm_dsi_phy_pll_save_state(phy);
 
+	/*
+	 * Store also proper vco_current_rate, because its value will be used in
+	 * dsi_10nm_pll_restore_state().
+	 */
+	if (!dsi_pll_10nm_vco_recalc_rate(&pll_10nm->clk_hw, VCO_REF_CLK_RATE))
+		pll_10nm->vco_current_rate = pll_10nm->phy->cfg->min_pll_rate;
+
 	return 0;
 }
 

From 5808c34216954cd832bd4b8bc52dfa287049122b Mon Sep 17 00:00:00 2001
From: Rong Zhang <i@rong.moe>
Date: Mon, 26 May 2025 04:18:07 +0800
Subject: [PATCH 0070/1334] platform/x86: ideapad-laptop: use usleep_range()
 for EC polling
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

It was reported that ideapad-laptop sometimes causes some recent (since
2024) Lenovo ThinkBook models shut down when:
 - suspending/resuming
 - closing/opening the lid
 - (dis)connecting a charger
 - reading/writing some sysfs properties, e.g., fan_mode, touchpad
 - pressing down some Fn keys, e.g., Brightness Up/Down (Fn+F5/F6)
 - (seldom) loading the kmod

The issue has existed since the launch day of such models, and there
have been some out-of-tree workarounds (see Link:) for the issue. One
disables some functionalities, while another one simply shortens
IDEAPAD_EC_TIMEOUT. The disabled functionalities have read_ec_data() in
their call chains, which calls schedule() between each poll.

It turns out that these models suffer from the indeterminacy of
schedule() because of their low tolerance for being polled too
frequently. Sometimes schedule() returns too soon due to the lack of
ready tasks, causing the margin between two polls to be too short.
In this case, the command is somehow aborted, and too many subsequent
polls (they poll for "nothing!") may eventually break the state machine
in the EC, resulting in a hard shutdown. This explains why shortening
IDEAPAD_EC_TIMEOUT works around the issue - it reduces the total number
of polls sent to the EC.

Even when it doesn't lead to a shutdown, frequent polls may also disturb
the ongoing operation and notably delay (+ 10-20ms) the availability of
EC response. This phenomenon is unlikely to be exclusive to the models
mentioned above, so dropping the schedule() manner should also slightly
improve the responsiveness of various models.

Fix these issues by migrating to usleep_range(150, 300). The interval is
chosen to add some margin to the minimal 50us and considering EC
responses are usually available after 150-2500us based on my test. It
should be enough to fix these issues on all models subject to the EC bug
without introducing latency on other models.

Tested on ThinkBook 14 G7+ ASP and solved both issues. No regression was
introduced in the test on a model without the EC bug (ThinkBook X IMH,
thanks Eric).

Link: https://github.com/ty2/ideapad-laptop-tb2024g6plus/commit/6c5db18c9e8109873c2c90a7d2d7f552148f7ad4
Link: https://github.com/ferstar/ideapad-laptop-tb/commit/42d1e68e5009529d31bd23f978f636f79c023e80
Closes: https://bugzilla.kernel.org/show_bug.cgi?id=218771
Fixes: 6a09f21dd1e2 ("ideapad: add ACPI helpers")
Cc: stable@vger.kernel.org
Tested-by: Felix Yan <felixonmars@archlinux.org>
Tested-by: Eric Long <i@hack3r.moe>
Tested-by: Jianfei Zhang <zhangjianfei3@gmail.com>
Tested-by: Mingcong Bai <jeffbai@aosc.io>
Tested-by: Minh Le <minhld139@gmail.com>
Tested-by: Sicheng Zhu <Emmet_Z@outlook.com>
Signed-off-by: Rong Zhang <i@rong.moe>
Link: https://lore.kernel.org/r/20250525201833.37939-1-i@rong.moe
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/ideapad-laptop.c | 19 +++++++++++++++++--
 1 file changed, 17 insertions(+), 2 deletions(-)

diff --git a/drivers/platform/x86/ideapad-laptop.c b/drivers/platform/x86/ideapad-laptop.c
index ede483573fe0..b5e4da6a6779 100644
--- a/drivers/platform/x86/ideapad-laptop.c
+++ b/drivers/platform/x86/ideapad-laptop.c
@@ -15,6 +15,7 @@
 #include <linux/bug.h>
 #include <linux/cleanup.h>
 #include <linux/debugfs.h>
+#include <linux/delay.h>
 #include <linux/device.h>
 #include <linux/dmi.h>
 #include <linux/i8042.h>
@@ -267,6 +268,20 @@ static void ideapad_shared_exit(struct ideapad_private *priv)
  */
 #define IDEAPAD_EC_TIMEOUT 200 /* in ms */
 
+/*
+ * Some models (e.g., ThinkBook since 2024) have a low tolerance for being
+ * polled too frequently. Doing so may break the state machine in the EC,
+ * resulting in a hard shutdown.
+ *
+ * It is also observed that frequent polls may disturb the ongoing operation
+ * and notably delay the availability of EC response.
+ *
+ * These values are used as the delay before the first poll and the interval
+ * between subsequent polls to solve the above issues.
+ */
+#define IDEAPAD_EC_POLL_MIN_US 150
+#define IDEAPAD_EC_POLL_MAX_US 300
+
 static int eval_int(acpi_handle handle, const char *name, unsigned long *res)
 {
 	unsigned long long result;
@@ -383,7 +398,7 @@ static int read_ec_data(acpi_handle handle, unsigned long cmd, unsigned long *da
 	end_jiffies = jiffies + msecs_to_jiffies(IDEAPAD_EC_TIMEOUT) + 1;
 
 	while (time_before(jiffies, end_jiffies)) {
-		schedule();
+		usleep_range(IDEAPAD_EC_POLL_MIN_US, IDEAPAD_EC_POLL_MAX_US);
 
 		err = eval_vpcr(handle, 1, &val);
 		if (err)
@@ -414,7 +429,7 @@ static int write_ec_cmd(acpi_handle handle, unsigned long cmd, unsigned long dat
 	end_jiffies = jiffies + msecs_to_jiffies(IDEAPAD_EC_TIMEOUT) + 1;
 
 	while (time_before(jiffies, end_jiffies)) {
-		schedule();
+		usleep_range(IDEAPAD_EC_POLL_MIN_US, IDEAPAD_EC_POLL_MAX_US);
 
 		err = eval_vpcr(handle, 1, &val);
 		if (err)

From 685f88c72a0c4d12d3bd2ff50286938f14486f85 Mon Sep 17 00:00:00 2001
From: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Date: Fri, 6 Jun 2025 13:53:00 -0700
Subject: [PATCH 0071/1334] platform/x86/intel-uncore-freq: Fail module load
 when plat_info is NULL
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Address a Smatch static checker warning regarding an unchecked
dereference in the function call:
set_cdie_id(i, cluster_info, plat_info)
when plat_info is NULL.

Instead of addressing this one case, in general if plat_info is NULL
then it can cause other issues. For example in a two package system it
will give warning for duplicate sysfs entry as package ID will be always
zero for both packages when creating string for attribute group name.

plat_info is derived from TPMI ID TPMI_BUS_INFO, which is integral to
the core TPMI design. Therefore, it should not be NULL on a production
platform. Consequently, the module should fail to load if plat_info is
NULL.

Reported-by: Dan Carpenter <dan.carpenter@linaro.org>
Closes: https://lore.kernel.org/platform-driver-x86/aEKvGCLd1qmX04Tc@stanley.mountain/T/#u
Fixes: 8a54e2253e4c ("platform/x86/intel-uncore-freq: Uncore frequency control via TPMI")
Signed-off-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20250606205300.2384494-1-srinivas.pandruvada@linux.intel.com
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 .../x86/intel/uncore-frequency/uncore-frequency-tpmi.c   | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-tpmi.c b/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-tpmi.c
index 1c7b2f2716ca..44d9948ed224 100644
--- a/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-tpmi.c
+++ b/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-tpmi.c
@@ -511,10 +511,13 @@ static int uncore_probe(struct auxiliary_device *auxdev, const struct auxiliary_
 
 	/* Get the package ID from the TPMI core */
 	plat_info = tpmi_get_platform_data(auxdev);
-	if (plat_info)
-		pkg = plat_info->package_id;
-	else
+	if (unlikely(!plat_info)) {
 		dev_info(&auxdev->dev, "Platform information is NULL\n");
+		ret = -ENODEV;
+		goto err_rem_common;
+	}
+
+	pkg = plat_info->package_id;
 
 	for (i = 0; i < num_resources; ++i) {
 		struct tpmi_uncore_power_domain_info *pd_info;

From c987a390f1b3b8bdac11031d7004e3410fe259bd Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Sun, 8 Jun 2025 11:14:14 +0200
Subject: [PATCH 0072/1334] ALSA: hda/intel: Add Thinkpad E15 to PM deny list

Lenovo Thinkpad E15 with Conexant CX8070 codec seems causing ugly
noises after runtime-PM suspend.  Disable the codec runtime PM as a
workaround.

Link: https://bugzilla.kernel.org/show_bug.cgi?id=220210
Cc: <stable@vger.kernel.org>
Link: https://patch.msgid.link/20250608091415.21170-1-tiwai@suse.de
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/hda_intel.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c
index e5210ed48ddf..439cf1bda6e6 100644
--- a/sound/pci/hda/hda_intel.c
+++ b/sound/pci/hda/hda_intel.c
@@ -2283,6 +2283,8 @@ static const struct snd_pci_quirk power_save_denylist[] = {
 	SND_PCI_QUIRK(0x1734, 0x1232, "KONTRON SinglePC", 0),
 	/* Dell ALC3271 */
 	SND_PCI_QUIRK(0x1028, 0x0962, "Dell ALC3271", 0),
+	/* https://bugzilla.kernel.org/show_bug.cgi?id=220210 */
+	SND_PCI_QUIRK(0x17aa, 0x5079, "Lenovo Thinkpad E15", 0),
 	{}
 };
 

From afbdc4bbb3a6418778cf969b0795bbaa8237cdd3 Mon Sep 17 00:00:00 2001
From: Joshua Grisham <josh@joshuagrisham.com>
Date: Fri, 6 Jun 2025 15:09:08 +0200
Subject: [PATCH 0073/1334] platform/x86: samsung-galaxybook: Add SAM0426
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add device ID SAM0426 (Notebook 9 Pro and similar devices) as reported
and tested by GitHub user "diego-karsa" [1].

[1]: https://github.com/joshuagrisham/samsung-galaxybook-extras/issues/69

Signed-off-by: Joshua Grisham <josh@joshuagrisham.com>
Reviewed-by: Armin Wolf <W_Armin@gmx.de>
Link: https://lore.kernel.org/r/20250606130909.207047-1-josh@joshuagrisham.com
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/samsung-galaxybook.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/platform/x86/samsung-galaxybook.c b/drivers/platform/x86/samsung-galaxybook.c
index 5878a351993e..3c13e13d4885 100644
--- a/drivers/platform/x86/samsung-galaxybook.c
+++ b/drivers/platform/x86/samsung-galaxybook.c
@@ -1403,6 +1403,7 @@ static int galaxybook_probe(struct platform_device *pdev)
 }
 
 static const struct acpi_device_id galaxybook_device_ids[] = {
+	{ "SAM0426" },
 	{ "SAM0427" },
 	{ "SAM0428" },
 	{ "SAM0429" },

From 1d0a61940e22e165e6acc4a9c6fb26edbe69112e Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Fri, 6 Jun 2025 12:04:32 +0300
Subject: [PATCH 0074/1334] platform/x86/intel: power-domains: Fix error code
 in tpmi_init()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Return -ENOMEM instead of success if kcalloc() fails.

Fixes: e37be5d85c60 ("platform/x86/intel: power-domains: Add interface to get Linux die ID")
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Link: https://lore.kernel.org/r/aEKvIGCt6d8Gcx4S@stanley.mountain
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/intel/tpmi_power_domains.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/platform/x86/intel/tpmi_power_domains.c b/drivers/platform/x86/intel/tpmi_power_domains.c
index 0c5c88eb7baf..9d8247bb9cfa 100644
--- a/drivers/platform/x86/intel/tpmi_power_domains.c
+++ b/drivers/platform/x86/intel/tpmi_power_domains.c
@@ -228,8 +228,10 @@ static int __init tpmi_init(void)
 
 	domain_die_map = kcalloc(size_mul(topology_max_packages(), MAX_POWER_DOMAINS),
 				 sizeof(*domain_die_map), GFP_KERNEL);
-	if (!domain_die_map)
+	if (!domain_die_map) {
+		ret = -ENOMEM;
 		goto free_domain_mask;
+	}
 
 	ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN,
 				"platform/x86/tpmi_power_domains:online",

From 4dbd11796f3a8eb95647507befc41995458a4023 Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Tue, 3 Jun 2025 08:24:08 -0500
Subject: [PATCH 0075/1334] platform/x86/amd: pmc: Clear metrics table at start
 of cycle
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The area of memory that contains the metrics table may contain garbage
when the cycle starts.  This normally doesn't matter because the cycle
itself will populate it with valid data, however commit 9f5595d5f03fd
("platform/x86/amd: pmc: Require at least 2.5 seconds between HW sleep
cycles") started to use it during the check() phase.  Depending upon
what garbage is in the table it's possible that the system will wait
2.5 seconds for even the first cycle, which will be visible to a user.

To prevent this from happening explicitly clear the table when logging
is started.

Fixes: 9f5595d5f03fd ("platform/x86/amd: pmc: Require at least 2.5 seconds between HW sleep cycles")
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Link: https://lore.kernel.org/r/20250603132412.3555302-1-superm1@kernel.org
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/amd/pmc/pmc.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/platform/x86/amd/pmc/pmc.c b/drivers/platform/x86/amd/pmc/pmc.c
index 37c7a57afee5..0b9b23eb7c2c 100644
--- a/drivers/platform/x86/amd/pmc/pmc.c
+++ b/drivers/platform/x86/amd/pmc/pmc.c
@@ -157,6 +157,8 @@ static int amd_pmc_setup_smu_logging(struct amd_pmc_dev *dev)
 			return -ENOMEM;
 	}
 
+	memset_io(dev->smu_virt_addr, 0, sizeof(struct smu_metrics));
+
 	/* Start the logging */
 	amd_pmc_send_cmd(dev, 0, NULL, SMU_MSG_LOG_RESET, false);
 	amd_pmc_send_cmd(dev, 0, NULL, SMU_MSG_LOG_START, false);

From f8afb12a2d7503de6558c23cacd7acbf6e9fe678 Mon Sep 17 00:00:00 2001
From: Jake Hillion <jake@hillion.co.uk>
Date: Thu, 5 Jun 2025 19:09:26 +0100
Subject: [PATCH 0076/1334] x86/platform/amd: move final timeout check to after
 final sleep
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

__hsmp_send_message sleeps between result read attempts and has a
timeout of 100ms. Under extreme load it's possible for these sleeps to
take a long time, exceeding the 100ms. In this case the current code
does not check the register and fails with ETIMEDOUT.

Refactor the loop to ensure there is at least one read of the register
after a sleep of any duration. This removes instances of ETIMEDOUT with
a single caller, even with a misbehaving scheduler. Tested on AMD
Bergamo machines.

Suggested-by: Blaise Sanouillet <linux@blaise.sanouillet.com>
Reviewed-by: Suma Hegde <suma.hegde@amd.com>
Tested-by: Suma Hegde <suma.hegde@amd.com>
Signed-off-by: Jake Hillion <jake@hillion.co.uk>
Link: https://lore.kernel.org/r/20250605-amd-hsmp-v2-1-a811bc3dd74a@hillion.co.uk
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/amd/hsmp/hsmp.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/platform/x86/amd/hsmp/hsmp.c b/drivers/platform/x86/amd/hsmp/hsmp.c
index 538b36b97095..fa8bd5839dd2 100644
--- a/drivers/platform/x86/amd/hsmp/hsmp.c
+++ b/drivers/platform/x86/amd/hsmp/hsmp.c
@@ -97,7 +97,7 @@ static int __hsmp_send_message(struct hsmp_socket *sock, struct hsmp_message *ms
 	short_sleep = jiffies + msecs_to_jiffies(HSMP_SHORT_SLEEP);
 	timeout	= jiffies + msecs_to_jiffies(HSMP_MSG_TIMEOUT);
 
-	while (time_before(jiffies, timeout)) {
+	while (true) {
 		ret = sock->amd_hsmp_rdwr(sock, mbinfo->msg_resp_off, &mbox_status, HSMP_RD);
 		if (ret) {
 			dev_err(sock->dev, "Error %d reading mailbox status\n", ret);
@@ -106,6 +106,10 @@ static int __hsmp_send_message(struct hsmp_socket *sock, struct hsmp_message *ms
 
 		if (mbox_status != HSMP_STATUS_NOT_READY)
 			break;
+
+		if (!time_before(jiffies, timeout))
+			break;
+
 		if (time_before(jiffies, short_sleep))
 			usleep_range(50, 100);
 		else

From 784e48a82976ee0b645788750343cd1b28a372f3 Mon Sep 17 00:00:00 2001
From: Jake Hillion <jake@hillion.co.uk>
Date: Thu, 5 Jun 2025 19:09:27 +0100
Subject: [PATCH 0077/1334] x86/platform/amd: replace down_timeout() with
 down_interruptible()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Currently hsmp_send_message() uses down_timeout() with a 100ms timeout
to take the semaphore. However __hsmp_send_message(), the content of the
critical section, has a sleep in it. On systems with significantly
delayed scheduling behaviour this may take over 100ms.

Convert this method to down_interruptible(). Leave the error handling
the same as the documentation currently is not specific about what error
is returned.

Previous behaviour: a caller who competes with another caller stuck in
the critical section due to scheduler delays would receive -ETIME.

New behaviour: a caller who competes with another caller stuck in the
critical section due to scheduler delays will complete successfully.

Reviewed-by: Suma Hegde <suma.hegde@amd.com>
Tested-by: Suma Hegde <suma.hegde@amd.com>
Signed-off-by: Jake Hillion <jake@hillion.co.uk>
Link: https://lore.kernel.org/r/20250605-amd-hsmp-v2-2-a811bc3dd74a@hillion.co.uk
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/amd/hsmp/hsmp.c | 8 +-------
 1 file changed, 1 insertion(+), 7 deletions(-)

diff --git a/drivers/platform/x86/amd/hsmp/hsmp.c b/drivers/platform/x86/amd/hsmp/hsmp.c
index fa8bd5839dd2..885e2f8136fd 100644
--- a/drivers/platform/x86/amd/hsmp/hsmp.c
+++ b/drivers/platform/x86/amd/hsmp/hsmp.c
@@ -214,13 +214,7 @@ int hsmp_send_message(struct hsmp_message *msg)
 		return -ENODEV;
 	sock = &hsmp_pdev.sock[msg->sock_ind];
 
-	/*
-	 * The time taken by smu operation to complete is between
-	 * 10us to 1ms. Sometime it may take more time.
-	 * In SMP system timeout of 100 millisecs should
-	 * be enough for the previous thread to finish the operation
-	 */
-	ret = down_timeout(&sock->hsmp_sem, msecs_to_jiffies(HSMP_MSG_TIMEOUT));
+	ret = down_interruptible(&sock->hsmp_sem);
 	if (ret < 0)
 		return ret;
 

From f00de8e82cab24ef2e2cae0b297b4dc46c3e37ca Mon Sep 17 00:00:00 2001
From: Brahmajit Das <listout@listout.xyz>
Date: Sat, 7 Jun 2025 02:10:00 +0530
Subject: [PATCH 0078/1334] ALSA: ctxfi: Replace deprecated strcpy() with
 strscpy()

strcpy() is deprecated; use strscpy() instead. Use strscpy() to copy the
long name because there's no string to format with sprintf().

No functional changes intended.

Link: https://github.com/KSPP/linux/issues/88

Signed-off-by: Brahmajit Das <listout@listout.xyz>
Link: https://patch.msgid.link/20250606204000.8156-1-listout@listout.xyz
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/ctxfi/xfi.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/sound/pci/ctxfi/xfi.c b/sound/pci/ctxfi/xfi.c
index 713d36ea40cb..d8dd84d41c87 100644
--- a/sound/pci/ctxfi/xfi.c
+++ b/sound/pci/ctxfi/xfi.c
@@ -98,8 +98,8 @@ ct_card_probe(struct pci_dev *pci, const struct pci_device_id *pci_id)
 	if (err < 0)
 		goto error;
 
-	strcpy(card->driver, "SB-XFi");
-	strcpy(card->shortname, "Creative X-Fi");
+	strscpy(card->driver, "SB-XFi");
+	strscpy(card->shortname, "Creative X-Fi");
 	snprintf(card->longname, sizeof(card->longname), "%s %s %s",
 		 card->shortname, atc->chip_name, atc->model_name);
 

From a0914bf56e26d2cf457690602883f9cd2ec2c646 Mon Sep 17 00:00:00 2001
From: Edip Hazuri <edip@medip.dev>
Date: Mon, 9 Jun 2025 10:59:44 +0300
Subject: [PATCH 0079/1334] ALSA: hda/realtek - Add mute LED support for HP
 Victus 16-s1xxx and HP Victus 15-fa1xxx

The mute led on those laptops is using ALC245 but requires a quirk to work
This patch enables the existing quirk for the devices.

Tested on my Victus 16-s1011nt Laptop and my friend's Victus
15-fa1xxx. The LED behaviour works as intended.

Cc: <stable@vger.kernel.org>
Signed-off-by: Edip Hazuri <edip@medip.dev>
Link: https://patch.msgid.link/20250609075943.13934-2-edip@medip.dev
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/patch_realtek.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index cd0d7ba7320e..c70bee62653e 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -10787,6 +10787,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x103c, 0x8b97, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF),
 	SND_PCI_QUIRK(0x103c, 0x8bb3, "HP Slim OMEN", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x103c, 0x8bb4, "HP Slim OMEN", ALC287_FIXUP_CS35L41_I2C_2),
+	SND_PCI_QUIRK(0x103c, 0x8bc8, "HP Victus 15-fa1xxx", ALC245_FIXUP_HP_MUTE_LED_COEFBIT),
 	SND_PCI_QUIRK(0x103c, 0x8bcd, "HP Omen 16-xd0xxx", ALC245_FIXUP_HP_MUTE_LED_V1_COEFBIT),
 	SND_PCI_QUIRK(0x103c, 0x8bdd, "HP Envy 17", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x103c, 0x8bde, "HP Envy 17", ALC287_FIXUP_CS35L41_I2C_2),
@@ -10840,6 +10841,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x103c, 0x8c91, "HP EliteBook 660", ALC236_FIXUP_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8c96, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF),
 	SND_PCI_QUIRK(0x103c, 0x8c97, "HP ZBook", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF),
+	SND_PCI_QUIRK(0x103c, 0x8c9c, "HP Victus 16-s1xxx (MB 8C9C)", ALC245_FIXUP_HP_MUTE_LED_COEFBIT),
 	SND_PCI_QUIRK(0x103c, 0x8ca1, "HP ZBook Power", ALC236_FIXUP_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8ca2, "HP ZBook Power", ALC236_FIXUP_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8ca4, "HP ZBook Fury", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),

From 56ec63a6e107e724619e61c7e605b49d365dfa07 Mon Sep 17 00:00:00 2001
From: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
Date: Tue, 13 May 2025 21:38:59 +0300
Subject: [PATCH 0080/1334] pinctrl: qcom: switch to devm_gpiochip_add_data()

In order to simplify cleanup actions, use devres-enabled version of
gpiochip_add_data().  As the msm_pinctrl_remove() function is now empty,
drop it and all its calls from the corresponding pinctrl drivers.

Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
Link: https://lore.kernel.org/20250513-pinctrl-msm-fix-v2-3-249999af0fc1@oss.qualcomm.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/qcom/pinctrl-apq8064.c  |  1 -
 drivers/pinctrl/qcom/pinctrl-apq8084.c  |  1 -
 drivers/pinctrl/qcom/pinctrl-ipq4019.c  |  1 -
 drivers/pinctrl/qcom/pinctrl-ipq5018.c  |  1 -
 drivers/pinctrl/qcom/pinctrl-ipq5332.c  |  1 -
 drivers/pinctrl/qcom/pinctrl-ipq5424.c  |  1 -
 drivers/pinctrl/qcom/pinctrl-ipq6018.c  |  1 -
 drivers/pinctrl/qcom/pinctrl-ipq8064.c  |  1 -
 drivers/pinctrl/qcom/pinctrl-ipq8074.c  |  1 -
 drivers/pinctrl/qcom/pinctrl-ipq9574.c  |  1 -
 drivers/pinctrl/qcom/pinctrl-mdm9607.c  |  1 -
 drivers/pinctrl/qcom/pinctrl-mdm9615.c  |  1 -
 drivers/pinctrl/qcom/pinctrl-msm.c      | 11 +----------
 drivers/pinctrl/qcom/pinctrl-msm.h      |  1 -
 drivers/pinctrl/qcom/pinctrl-msm8226.c  |  1 -
 drivers/pinctrl/qcom/pinctrl-msm8660.c  |  1 -
 drivers/pinctrl/qcom/pinctrl-msm8909.c  |  1 -
 drivers/pinctrl/qcom/pinctrl-msm8916.c  |  1 -
 drivers/pinctrl/qcom/pinctrl-msm8917.c  |  1 -
 drivers/pinctrl/qcom/pinctrl-msm8953.c  |  1 -
 drivers/pinctrl/qcom/pinctrl-msm8960.c  |  1 -
 drivers/pinctrl/qcom/pinctrl-msm8976.c  |  1 -
 drivers/pinctrl/qcom/pinctrl-msm8994.c  |  1 -
 drivers/pinctrl/qcom/pinctrl-msm8996.c  |  1 -
 drivers/pinctrl/qcom/pinctrl-msm8998.c  |  1 -
 drivers/pinctrl/qcom/pinctrl-msm8x74.c  |  1 -
 drivers/pinctrl/qcom/pinctrl-qcm2290.c  |  1 -
 drivers/pinctrl/qcom/pinctrl-qcs404.c   |  1 -
 drivers/pinctrl/qcom/pinctrl-qcs615.c   |  1 -
 drivers/pinctrl/qcom/pinctrl-qcs8300.c  |  1 -
 drivers/pinctrl/qcom/pinctrl-qdf2xxx.c  |  1 -
 drivers/pinctrl/qcom/pinctrl-qdu1000.c  |  1 -
 drivers/pinctrl/qcom/pinctrl-sa8775p.c  |  1 -
 drivers/pinctrl/qcom/pinctrl-sar2130p.c |  1 -
 drivers/pinctrl/qcom/pinctrl-sc7180.c   |  1 -
 drivers/pinctrl/qcom/pinctrl-sc7280.c   |  1 -
 drivers/pinctrl/qcom/pinctrl-sc8180x.c  |  1 -
 drivers/pinctrl/qcom/pinctrl-sc8280xp.c |  1 -
 drivers/pinctrl/qcom/pinctrl-sdm660.c   |  1 -
 drivers/pinctrl/qcom/pinctrl-sdm670.c   |  1 -
 drivers/pinctrl/qcom/pinctrl-sdm845.c   |  1 -
 drivers/pinctrl/qcom/pinctrl-sdx55.c    |  1 -
 drivers/pinctrl/qcom/pinctrl-sdx65.c    |  1 -
 drivers/pinctrl/qcom/pinctrl-sdx75.c    |  1 -
 drivers/pinctrl/qcom/pinctrl-sm4450.c   |  1 -
 drivers/pinctrl/qcom/pinctrl-sm6115.c   |  1 -
 drivers/pinctrl/qcom/pinctrl-sm6125.c   |  1 -
 drivers/pinctrl/qcom/pinctrl-sm6350.c   |  1 -
 drivers/pinctrl/qcom/pinctrl-sm6375.c   |  1 -
 drivers/pinctrl/qcom/pinctrl-sm7150.c   |  1 -
 drivers/pinctrl/qcom/pinctrl-sm8150.c   |  1 -
 drivers/pinctrl/qcom/pinctrl-sm8250.c   |  1 -
 drivers/pinctrl/qcom/pinctrl-sm8350.c   |  1 -
 drivers/pinctrl/qcom/pinctrl-sm8450.c   |  1 -
 drivers/pinctrl/qcom/pinctrl-sm8550.c   |  1 -
 drivers/pinctrl/qcom/pinctrl-sm8650.c   |  1 -
 drivers/pinctrl/qcom/pinctrl-sm8750.c   |  1 -
 drivers/pinctrl/qcom/pinctrl-x1e80100.c |  1 -
 58 files changed, 1 insertion(+), 67 deletions(-)

diff --git a/drivers/pinctrl/qcom/pinctrl-apq8064.c b/drivers/pinctrl/qcom/pinctrl-apq8064.c
index 20c3b9025044..3654913f1ae5 100644
--- a/drivers/pinctrl/qcom/pinctrl-apq8064.c
+++ b/drivers/pinctrl/qcom/pinctrl-apq8064.c
@@ -629,7 +629,6 @@ static struct platform_driver apq8064_pinctrl_driver = {
 		.of_match_table = apq8064_pinctrl_of_match,
 	},
 	.probe = apq8064_pinctrl_probe,
-	.remove = msm_pinctrl_remove,
 };
 
 static int __init apq8064_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-apq8084.c b/drivers/pinctrl/qcom/pinctrl-apq8084.c
index 3fc0a40762b6..27693cd64881 100644
--- a/drivers/pinctrl/qcom/pinctrl-apq8084.c
+++ b/drivers/pinctrl/qcom/pinctrl-apq8084.c
@@ -1207,7 +1207,6 @@ static struct platform_driver apq8084_pinctrl_driver = {
 		.of_match_table = apq8084_pinctrl_of_match,
 	},
 	.probe = apq8084_pinctrl_probe,
-	.remove = msm_pinctrl_remove,
 };
 
 static int __init apq8084_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-ipq4019.c b/drivers/pinctrl/qcom/pinctrl-ipq4019.c
index 1f7944dd829d..6ede3149b6e1 100644
--- a/drivers/pinctrl/qcom/pinctrl-ipq4019.c
+++ b/drivers/pinctrl/qcom/pinctrl-ipq4019.c
@@ -710,7 +710,6 @@ static struct platform_driver ipq4019_pinctrl_driver = {
 		.of_match_table = ipq4019_pinctrl_of_match,
 	},
 	.probe = ipq4019_pinctrl_probe,
-	.remove = msm_pinctrl_remove,
 };
 
 static int __init ipq4019_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-ipq5018.c b/drivers/pinctrl/qcom/pinctrl-ipq5018.c
index e2951f81c3ee..10b99d5d8a11 100644
--- a/drivers/pinctrl/qcom/pinctrl-ipq5018.c
+++ b/drivers/pinctrl/qcom/pinctrl-ipq5018.c
@@ -754,7 +754,6 @@ static struct platform_driver ipq5018_pinctrl_driver = {
 		.of_match_table = ipq5018_pinctrl_of_match,
 	},
 	.probe = ipq5018_pinctrl_probe,
-	.remove = msm_pinctrl_remove,
 };
 
 static int __init ipq5018_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-ipq5332.c b/drivers/pinctrl/qcom/pinctrl-ipq5332.c
index 625f8014051f..1ac2fc09c119 100644
--- a/drivers/pinctrl/qcom/pinctrl-ipq5332.c
+++ b/drivers/pinctrl/qcom/pinctrl-ipq5332.c
@@ -834,7 +834,6 @@ static struct platform_driver ipq5332_pinctrl_driver = {
 		.of_match_table = ipq5332_pinctrl_of_match,
 	},
 	.probe = ipq5332_pinctrl_probe,
-	.remove = msm_pinctrl_remove,
 };
 
 static int __init ipq5332_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-ipq5424.c b/drivers/pinctrl/qcom/pinctrl-ipq5424.c
index 0d610b076da3..7ff1f8acc1a3 100644
--- a/drivers/pinctrl/qcom/pinctrl-ipq5424.c
+++ b/drivers/pinctrl/qcom/pinctrl-ipq5424.c
@@ -791,7 +791,6 @@ static struct platform_driver ipq5424_pinctrl_driver = {
 		.of_match_table = ipq5424_pinctrl_of_match,
 	},
 	.probe = ipq5424_pinctrl_probe,
-	.remove = msm_pinctrl_remove,
 };
 
 static int __init ipq5424_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-ipq6018.c b/drivers/pinctrl/qcom/pinctrl-ipq6018.c
index 0ad08647dbcd..a4ba980252e1 100644
--- a/drivers/pinctrl/qcom/pinctrl-ipq6018.c
+++ b/drivers/pinctrl/qcom/pinctrl-ipq6018.c
@@ -1080,7 +1080,6 @@ static struct platform_driver ipq6018_pinctrl_driver = {
 		.of_match_table = ipq6018_pinctrl_of_match,
 	},
 	.probe = ipq6018_pinctrl_probe,
-	.remove = msm_pinctrl_remove,
 };
 
 static int __init ipq6018_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-ipq8064.c b/drivers/pinctrl/qcom/pinctrl-ipq8064.c
index e2bb94e86aef..0a9e357e64c6 100644
--- a/drivers/pinctrl/qcom/pinctrl-ipq8064.c
+++ b/drivers/pinctrl/qcom/pinctrl-ipq8064.c
@@ -631,7 +631,6 @@ static struct platform_driver ipq8064_pinctrl_driver = {
 		.of_match_table = ipq8064_pinctrl_of_match,
 	},
 	.probe = ipq8064_pinctrl_probe,
-	.remove = msm_pinctrl_remove,
 };
 
 static int __init ipq8064_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-ipq8074.c b/drivers/pinctrl/qcom/pinctrl-ipq8074.c
index 337f3a1c92c1..482f13282fc2 100644
--- a/drivers/pinctrl/qcom/pinctrl-ipq8074.c
+++ b/drivers/pinctrl/qcom/pinctrl-ipq8074.c
@@ -1041,7 +1041,6 @@ static struct platform_driver ipq8074_pinctrl_driver = {
 		.of_match_table = ipq8074_pinctrl_of_match,
 	},
 	.probe = ipq8074_pinctrl_probe,
-	.remove = msm_pinctrl_remove,
 };
 
 static int __init ipq8074_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-ipq9574.c b/drivers/pinctrl/qcom/pinctrl-ipq9574.c
index e2491617b236..89c05d8eb550 100644
--- a/drivers/pinctrl/qcom/pinctrl-ipq9574.c
+++ b/drivers/pinctrl/qcom/pinctrl-ipq9574.c
@@ -799,7 +799,6 @@ static struct platform_driver ipq9574_pinctrl_driver = {
 		.of_match_table = ipq9574_pinctrl_of_match,
 	},
 	.probe = ipq9574_pinctrl_probe,
-	.remove = msm_pinctrl_remove,
 };
 
 static int __init ipq9574_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-mdm9607.c b/drivers/pinctrl/qcom/pinctrl-mdm9607.c
index e7cd3ef1cf3e..3e18ba124fed 100644
--- a/drivers/pinctrl/qcom/pinctrl-mdm9607.c
+++ b/drivers/pinctrl/qcom/pinctrl-mdm9607.c
@@ -1059,7 +1059,6 @@ static struct platform_driver mdm9607_pinctrl_driver = {
 		.of_match_table = mdm9607_pinctrl_of_match,
 	},
 	.probe = mdm9607_pinctrl_probe,
-	.remove = msm_pinctrl_remove,
 };
 
 static int __init mdm9607_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-mdm9615.c b/drivers/pinctrl/qcom/pinctrl-mdm9615.c
index 0a2ae383d3d5..bea1ca3d1b7f 100644
--- a/drivers/pinctrl/qcom/pinctrl-mdm9615.c
+++ b/drivers/pinctrl/qcom/pinctrl-mdm9615.c
@@ -446,7 +446,6 @@ static struct platform_driver mdm9615_pinctrl_driver = {
 		.of_match_table = mdm9615_pinctrl_of_match,
 	},
 	.probe = mdm9615_pinctrl_probe,
-	.remove = msm_pinctrl_remove,
 };
 
 static int __init mdm9615_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-msm.c b/drivers/pinctrl/qcom/pinctrl-msm.c
index f012ea88aa22..5c4687de1464 100644
--- a/drivers/pinctrl/qcom/pinctrl-msm.c
+++ b/drivers/pinctrl/qcom/pinctrl-msm.c
@@ -1442,7 +1442,7 @@ static int msm_gpio_init(struct msm_pinctrl *pctrl)
 	girq->handler = handle_bad_irq;
 	girq->parents[0] = pctrl->irq;
 
-	ret = gpiochip_add_data(&pctrl->chip, pctrl);
+	ret = devm_gpiochip_add_data(pctrl->dev, &pctrl->chip, pctrl);
 	if (ret) {
 		dev_err(pctrl->dev, "Failed register gpiochip\n");
 		return ret;
@@ -1463,7 +1463,6 @@ static int msm_gpio_init(struct msm_pinctrl *pctrl)
 			dev_name(pctrl->dev), 0, 0, chip->ngpio);
 		if (ret) {
 			dev_err(pctrl->dev, "Failed to add pin range\n");
-			gpiochip_remove(&pctrl->chip);
 			return ret;
 		}
 	}
@@ -1599,13 +1598,5 @@ int msm_pinctrl_probe(struct platform_device *pdev,
 }
 EXPORT_SYMBOL(msm_pinctrl_probe);
 
-void msm_pinctrl_remove(struct platform_device *pdev)
-{
-	struct msm_pinctrl *pctrl = platform_get_drvdata(pdev);
-
-	gpiochip_remove(&pctrl->chip);
-}
-EXPORT_SYMBOL(msm_pinctrl_remove);
-
 MODULE_DESCRIPTION("Qualcomm Technologies, Inc. TLMM driver");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/pinctrl/qcom/pinctrl-msm.h b/drivers/pinctrl/qcom/pinctrl-msm.h
index 63852ed70295..d7dc0947bb16 100644
--- a/drivers/pinctrl/qcom/pinctrl-msm.h
+++ b/drivers/pinctrl/qcom/pinctrl-msm.h
@@ -171,6 +171,5 @@ extern const struct dev_pm_ops msm_pinctrl_dev_pm_ops;
 
 int msm_pinctrl_probe(struct platform_device *pdev,
 		      const struct msm_pinctrl_soc_data *soc_data);
-void msm_pinctrl_remove(struct platform_device *pdev);
 
 #endif
diff --git a/drivers/pinctrl/qcom/pinctrl-msm8226.c b/drivers/pinctrl/qcom/pinctrl-msm8226.c
index 64fee70f1772..f9a957347340 100644
--- a/drivers/pinctrl/qcom/pinctrl-msm8226.c
+++ b/drivers/pinctrl/qcom/pinctrl-msm8226.c
@@ -654,7 +654,6 @@ static struct platform_driver msm8226_pinctrl_driver = {
 		.of_match_table = msm8226_pinctrl_of_match,
 	},
 	.probe = msm8226_pinctrl_probe,
-	.remove = msm_pinctrl_remove,
 };
 
 static int __init msm8226_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-msm8660.c b/drivers/pinctrl/qcom/pinctrl-msm8660.c
index 999a5f867eb5..4dbc19ffd80e 100644
--- a/drivers/pinctrl/qcom/pinctrl-msm8660.c
+++ b/drivers/pinctrl/qcom/pinctrl-msm8660.c
@@ -981,7 +981,6 @@ static struct platform_driver msm8660_pinctrl_driver = {
 		.of_match_table = msm8660_pinctrl_of_match,
 	},
 	.probe = msm8660_pinctrl_probe,
-	.remove = msm_pinctrl_remove,
 };
 
 static int __init msm8660_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-msm8909.c b/drivers/pinctrl/qcom/pinctrl-msm8909.c
index 756856d20d6b..0aa4f77b774f 100644
--- a/drivers/pinctrl/qcom/pinctrl-msm8909.c
+++ b/drivers/pinctrl/qcom/pinctrl-msm8909.c
@@ -929,7 +929,6 @@ static struct platform_driver msm8909_pinctrl_driver = {
 		.of_match_table = msm8909_pinctrl_of_match,
 	},
 	.probe = msm8909_pinctrl_probe,
-	.remove = msm_pinctrl_remove,
 };
 
 static int __init msm8909_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-msm8916.c b/drivers/pinctrl/qcom/pinctrl-msm8916.c
index cea5c54f92fe..0dfc6dd33d58 100644
--- a/drivers/pinctrl/qcom/pinctrl-msm8916.c
+++ b/drivers/pinctrl/qcom/pinctrl-msm8916.c
@@ -969,7 +969,6 @@ static struct platform_driver msm8916_pinctrl_driver = {
 		.of_match_table = msm8916_pinctrl_of_match,
 	},
 	.probe = msm8916_pinctrl_probe,
-	.remove = msm_pinctrl_remove,
 };
 
 static int __init msm8916_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-msm8917.c b/drivers/pinctrl/qcom/pinctrl-msm8917.c
index 350636807b07..2e1a94ab18b2 100644
--- a/drivers/pinctrl/qcom/pinctrl-msm8917.c
+++ b/drivers/pinctrl/qcom/pinctrl-msm8917.c
@@ -1607,7 +1607,6 @@ static struct platform_driver msm8917_pinctrl_driver = {
 		.of_match_table = msm8917_pinctrl_of_match,
 	},
 	.probe = msm8917_pinctrl_probe,
-	.remove = msm_pinctrl_remove,
 };
 
 static int __init msm8917_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-msm8953.c b/drivers/pinctrl/qcom/pinctrl-msm8953.c
index 998351bdfee1..956383341a7a 100644
--- a/drivers/pinctrl/qcom/pinctrl-msm8953.c
+++ b/drivers/pinctrl/qcom/pinctrl-msm8953.c
@@ -1816,7 +1816,6 @@ static struct platform_driver msm8953_pinctrl_driver = {
 		.of_match_table = msm8953_pinctrl_of_match,
 	},
 	.probe = msm8953_pinctrl_probe,
-	.remove = msm_pinctrl_remove,
 };
 
 static int __init msm8953_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-msm8960.c b/drivers/pinctrl/qcom/pinctrl-msm8960.c
index ebe230b3b437..a937ea867de7 100644
--- a/drivers/pinctrl/qcom/pinctrl-msm8960.c
+++ b/drivers/pinctrl/qcom/pinctrl-msm8960.c
@@ -1246,7 +1246,6 @@ static struct platform_driver msm8960_pinctrl_driver = {
 		.of_match_table = msm8960_pinctrl_of_match,
 	},
 	.probe = msm8960_pinctrl_probe,
-	.remove = msm_pinctrl_remove,
 };
 
 static int __init msm8960_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-msm8976.c b/drivers/pinctrl/qcom/pinctrl-msm8976.c
index c30d80e4e98c..3bcb03387781 100644
--- a/drivers/pinctrl/qcom/pinctrl-msm8976.c
+++ b/drivers/pinctrl/qcom/pinctrl-msm8976.c
@@ -1096,7 +1096,6 @@ static struct platform_driver msm8976_pinctrl_driver = {
 		.of_match_table = msm8976_pinctrl_of_match,
 	},
 	.probe = msm8976_pinctrl_probe,
-	.remove = msm_pinctrl_remove,
 };
 
 static int __init msm8976_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-msm8994.c b/drivers/pinctrl/qcom/pinctrl-msm8994.c
index b1a6759ab4a5..7a3b6cbccb68 100644
--- a/drivers/pinctrl/qcom/pinctrl-msm8994.c
+++ b/drivers/pinctrl/qcom/pinctrl-msm8994.c
@@ -1343,7 +1343,6 @@ static struct platform_driver msm8994_pinctrl_driver = {
 		.of_match_table = msm8994_pinctrl_of_match,
 	},
 	.probe = msm8994_pinctrl_probe,
-	.remove = msm_pinctrl_remove,
 };
 
 static int __init msm8994_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-msm8996.c b/drivers/pinctrl/qcom/pinctrl-msm8996.c
index 1b5d80eaab83..d86d83106d3b 100644
--- a/drivers/pinctrl/qcom/pinctrl-msm8996.c
+++ b/drivers/pinctrl/qcom/pinctrl-msm8996.c
@@ -1920,7 +1920,6 @@ static struct platform_driver msm8996_pinctrl_driver = {
 		.of_match_table = msm8996_pinctrl_of_match,
 	},
 	.probe = msm8996_pinctrl_probe,
-	.remove = msm_pinctrl_remove,
 };
 
 static int __init msm8996_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-msm8998.c b/drivers/pinctrl/qcom/pinctrl-msm8998.c
index b7cbf32b3125..1daee815888f 100644
--- a/drivers/pinctrl/qcom/pinctrl-msm8998.c
+++ b/drivers/pinctrl/qcom/pinctrl-msm8998.c
@@ -1535,7 +1535,6 @@ static struct platform_driver msm8998_pinctrl_driver = {
 		.of_match_table = msm8998_pinctrl_of_match,
 	},
 	.probe = msm8998_pinctrl_probe,
-	.remove = msm_pinctrl_remove,
 };
 
 static int __init msm8998_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-msm8x74.c b/drivers/pinctrl/qcom/pinctrl-msm8x74.c
index 238c83f6ec4f..8253aa25775b 100644
--- a/drivers/pinctrl/qcom/pinctrl-msm8x74.c
+++ b/drivers/pinctrl/qcom/pinctrl-msm8x74.c
@@ -1083,7 +1083,6 @@ static struct platform_driver msm8x74_pinctrl_driver = {
 		.of_match_table = msm8x74_pinctrl_of_match,
 	},
 	.probe = msm8x74_pinctrl_probe,
-	.remove = msm_pinctrl_remove,
 };
 
 static int __init msm8x74_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-qcm2290.c b/drivers/pinctrl/qcom/pinctrl-qcm2290.c
index f885af571ec9..85c951305abd 100644
--- a/drivers/pinctrl/qcom/pinctrl-qcm2290.c
+++ b/drivers/pinctrl/qcom/pinctrl-qcm2290.c
@@ -1125,7 +1125,6 @@ static struct platform_driver qcm2290_pinctrl_driver = {
 		.of_match_table = qcm2290_pinctrl_of_match,
 	},
 	.probe = qcm2290_pinctrl_probe,
-	.remove = msm_pinctrl_remove,
 };
 
 static int __init qcm2290_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-qcs404.c b/drivers/pinctrl/qcom/pinctrl-qcs404.c
index ae7224012f8a..54e3b4435349 100644
--- a/drivers/pinctrl/qcom/pinctrl-qcs404.c
+++ b/drivers/pinctrl/qcom/pinctrl-qcs404.c
@@ -1644,7 +1644,6 @@ static struct platform_driver qcs404_pinctrl_driver = {
 		.of_match_table = qcs404_pinctrl_of_match,
 	},
 	.probe = qcs404_pinctrl_probe,
-	.remove = msm_pinctrl_remove,
 };
 
 static int __init qcs404_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-qcs615.c b/drivers/pinctrl/qcom/pinctrl-qcs615.c
index 17ca743c2210..2a943bc46a62 100644
--- a/drivers/pinctrl/qcom/pinctrl-qcs615.c
+++ b/drivers/pinctrl/qcom/pinctrl-qcs615.c
@@ -1087,7 +1087,6 @@ static struct platform_driver qcs615_tlmm_driver = {
 		.of_match_table = qcs615_tlmm_of_match,
 	},
 	.probe = qcs615_tlmm_probe,
-	.remove = msm_pinctrl_remove,
 };
 
 static int __init qcs615_tlmm_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-qcs8300.c b/drivers/pinctrl/qcom/pinctrl-qcs8300.c
index 5f5f7c4ac644..d6437e26392b 100644
--- a/drivers/pinctrl/qcom/pinctrl-qcs8300.c
+++ b/drivers/pinctrl/qcom/pinctrl-qcs8300.c
@@ -1227,7 +1227,6 @@ static struct platform_driver qcs8300_pinctrl_driver = {
 		.of_match_table = qcs8300_pinctrl_of_match,
 	},
 	.probe = qcs8300_pinctrl_probe,
-	.remove = msm_pinctrl_remove,
 };
 
 static int __init qcs8300_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-qdf2xxx.c b/drivers/pinctrl/qcom/pinctrl-qdf2xxx.c
index b5808fcfb13c..9ecc4d40e4dc 100644
--- a/drivers/pinctrl/qcom/pinctrl-qdf2xxx.c
+++ b/drivers/pinctrl/qcom/pinctrl-qdf2xxx.c
@@ -145,7 +145,6 @@ static struct platform_driver qdf2xxx_pinctrl_driver = {
 		.acpi_match_table = qdf2xxx_acpi_ids,
 	},
 	.probe = qdf2xxx_pinctrl_probe,
-	.remove = msm_pinctrl_remove,
 };
 
 static int __init qdf2xxx_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-qdu1000.c b/drivers/pinctrl/qcom/pinctrl-qdu1000.c
index 47bc529ef550..eacb89fa3888 100644
--- a/drivers/pinctrl/qcom/pinctrl-qdu1000.c
+++ b/drivers/pinctrl/qcom/pinctrl-qdu1000.c
@@ -1248,7 +1248,6 @@ static struct platform_driver qdu1000_tlmm_driver = {
 		.of_match_table = qdu1000_tlmm_of_match,
 	},
 	.probe = qdu1000_tlmm_probe,
-	.remove = msm_pinctrl_remove,
 };
 
 static int __init qdu1000_tlmm_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-sa8775p.c b/drivers/pinctrl/qcom/pinctrl-sa8775p.c
index a5b38221aea8..1b62eb3e6620 100644
--- a/drivers/pinctrl/qcom/pinctrl-sa8775p.c
+++ b/drivers/pinctrl/qcom/pinctrl-sa8775p.c
@@ -1540,7 +1540,6 @@ static struct platform_driver sa8775p_pinctrl_driver = {
 		.of_match_table = sa8775p_pinctrl_of_match,
 	},
 	.probe = sa8775p_pinctrl_probe,
-	.remove = msm_pinctrl_remove,
 };
 
 static int __init sa8775p_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-sar2130p.c b/drivers/pinctrl/qcom/pinctrl-sar2130p.c
index 19a2e37826c7..3dd1b5e5cfee 100644
--- a/drivers/pinctrl/qcom/pinctrl-sar2130p.c
+++ b/drivers/pinctrl/qcom/pinctrl-sar2130p.c
@@ -1486,7 +1486,6 @@ static struct platform_driver sar2130p_tlmm_driver = {
 		.of_match_table = sar2130p_tlmm_of_match,
 	},
 	.probe = sar2130p_tlmm_probe,
-	.remove = msm_pinctrl_remove,
 };
 
 static int __init sar2130p_tlmm_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-sc7180.c b/drivers/pinctrl/qcom/pinctrl-sc7180.c
index 6eb0c73791c0..c43fe10b71ad 100644
--- a/drivers/pinctrl/qcom/pinctrl-sc7180.c
+++ b/drivers/pinctrl/qcom/pinctrl-sc7180.c
@@ -1159,7 +1159,6 @@ static struct platform_driver sc7180_pinctrl_driver = {
 		.of_match_table = sc7180_pinctrl_of_match,
 	},
 	.probe = sc7180_pinctrl_probe,
-	.remove = msm_pinctrl_remove,
 };
 
 static int __init sc7180_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-sc7280.c b/drivers/pinctrl/qcom/pinctrl-sc7280.c
index 0c10eeb60b55..1b070e9d41f5 100644
--- a/drivers/pinctrl/qcom/pinctrl-sc7280.c
+++ b/drivers/pinctrl/qcom/pinctrl-sc7280.c
@@ -1505,7 +1505,6 @@ static struct platform_driver sc7280_pinctrl_driver = {
 		.of_match_table = sc7280_pinctrl_of_match,
 	},
 	.probe = sc7280_pinctrl_probe,
-	.remove = msm_pinctrl_remove,
 };
 
 static int __init sc7280_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-sc8180x.c b/drivers/pinctrl/qcom/pinctrl-sc8180x.c
index d6a79ad41a40..26dd165d1543 100644
--- a/drivers/pinctrl/qcom/pinctrl-sc8180x.c
+++ b/drivers/pinctrl/qcom/pinctrl-sc8180x.c
@@ -1720,7 +1720,6 @@ static struct platform_driver sc8180x_pinctrl_driver = {
 		.acpi_match_table = sc8180x_pinctrl_acpi_match,
 	},
 	.probe = sc8180x_pinctrl_probe,
-	.remove = msm_pinctrl_remove,
 };
 
 static int __init sc8180x_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-sc8280xp.c b/drivers/pinctrl/qcom/pinctrl-sc8280xp.c
index 96f4fb5a5d29..6ccd7e5648d4 100644
--- a/drivers/pinctrl/qcom/pinctrl-sc8280xp.c
+++ b/drivers/pinctrl/qcom/pinctrl-sc8280xp.c
@@ -1926,7 +1926,6 @@ static struct platform_driver sc8280xp_pinctrl_driver = {
 		.of_match_table = sc8280xp_pinctrl_of_match,
 	},
 	.probe = sc8280xp_pinctrl_probe,
-	.remove = msm_pinctrl_remove,
 };
 
 static int __init sc8280xp_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-sdm660.c b/drivers/pinctrl/qcom/pinctrl-sdm660.c
index 907e4ffca5e7..1a78288f1bc8 100644
--- a/drivers/pinctrl/qcom/pinctrl-sdm660.c
+++ b/drivers/pinctrl/qcom/pinctrl-sdm660.c
@@ -1442,7 +1442,6 @@ static struct platform_driver sdm660_pinctrl_driver = {
 		.of_match_table = sdm660_pinctrl_of_match,
 	},
 	.probe = sdm660_pinctrl_probe,
-	.remove = msm_pinctrl_remove,
 };
 
 static int __init sdm660_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-sdm670.c b/drivers/pinctrl/qcom/pinctrl-sdm670.c
index c76183ba95e1..0fe1fa94cd6d 100644
--- a/drivers/pinctrl/qcom/pinctrl-sdm670.c
+++ b/drivers/pinctrl/qcom/pinctrl-sdm670.c
@@ -1337,7 +1337,6 @@ static struct platform_driver sdm670_pinctrl_driver = {
 		.of_match_table = sdm670_pinctrl_of_match,
 	},
 	.probe = sdm670_pinctrl_probe,
-	.remove = msm_pinctrl_remove,
 };
 
 static int __init sdm670_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-sdm845.c b/drivers/pinctrl/qcom/pinctrl-sdm845.c
index cc05c415ed15..0446e291aa48 100644
--- a/drivers/pinctrl/qcom/pinctrl-sdm845.c
+++ b/drivers/pinctrl/qcom/pinctrl-sdm845.c
@@ -1351,7 +1351,6 @@ static struct platform_driver sdm845_pinctrl_driver = {
 		.acpi_match_table = ACPI_PTR(sdm845_pinctrl_acpi_match),
 	},
 	.probe = sdm845_pinctrl_probe,
-	.remove = msm_pinctrl_remove,
 };
 
 static int __init sdm845_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-sdx55.c b/drivers/pinctrl/qcom/pinctrl-sdx55.c
index 8826db9d21d0..2c17bf889146 100644
--- a/drivers/pinctrl/qcom/pinctrl-sdx55.c
+++ b/drivers/pinctrl/qcom/pinctrl-sdx55.c
@@ -990,7 +990,6 @@ static struct platform_driver sdx55_pinctrl_driver = {
 		.of_match_table = sdx55_pinctrl_of_match,
 	},
 	.probe = sdx55_pinctrl_probe,
-	.remove = msm_pinctrl_remove,
 };
 
 static int __init sdx55_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-sdx65.c b/drivers/pinctrl/qcom/pinctrl-sdx65.c
index f6f319c997fc..85b5c0206dbd 100644
--- a/drivers/pinctrl/qcom/pinctrl-sdx65.c
+++ b/drivers/pinctrl/qcom/pinctrl-sdx65.c
@@ -939,7 +939,6 @@ static struct platform_driver sdx65_pinctrl_driver = {
 		.of_match_table = sdx65_pinctrl_of_match,
 	},
 	.probe = sdx65_pinctrl_probe,
-	.remove = msm_pinctrl_remove,
 };
 
 static int __init sdx65_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-sdx75.c b/drivers/pinctrl/qcom/pinctrl-sdx75.c
index 3cfe8c7f04df..ab13a3a57a83 100644
--- a/drivers/pinctrl/qcom/pinctrl-sdx75.c
+++ b/drivers/pinctrl/qcom/pinctrl-sdx75.c
@@ -1124,7 +1124,6 @@ static struct platform_driver sdx75_pinctrl_driver = {
 		.of_match_table = sdx75_pinctrl_of_match,
 	},
 	.probe = sdx75_pinctrl_probe,
-	.remove = msm_pinctrl_remove,
 };
 
 static int __init sdx75_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-sm4450.c b/drivers/pinctrl/qcom/pinctrl-sm4450.c
index 622f20e6f6f8..1ecdf1ab4f27 100644
--- a/drivers/pinctrl/qcom/pinctrl-sm4450.c
+++ b/drivers/pinctrl/qcom/pinctrl-sm4450.c
@@ -994,7 +994,6 @@ static struct platform_driver sm4450_tlmm_driver = {
 		.of_match_table = sm4450_tlmm_of_match,
 	},
 	.probe = sm4450_tlmm_probe,
-	.remove = msm_pinctrl_remove,
 };
 MODULE_DEVICE_TABLE(of, sm4450_tlmm_of_match);
 
diff --git a/drivers/pinctrl/qcom/pinctrl-sm6115.c b/drivers/pinctrl/qcom/pinctrl-sm6115.c
index 4e91c75ad952..c273efa43996 100644
--- a/drivers/pinctrl/qcom/pinctrl-sm6115.c
+++ b/drivers/pinctrl/qcom/pinctrl-sm6115.c
@@ -907,7 +907,6 @@ static struct platform_driver sm6115_tlmm_driver = {
 		.of_match_table = sm6115_tlmm_of_match,
 	},
 	.probe = sm6115_tlmm_probe,
-	.remove = msm_pinctrl_remove,
 };
 
 static int __init sm6115_tlmm_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-sm6125.c b/drivers/pinctrl/qcom/pinctrl-sm6125.c
index c188842047aa..5092f20e0c1b 100644
--- a/drivers/pinctrl/qcom/pinctrl-sm6125.c
+++ b/drivers/pinctrl/qcom/pinctrl-sm6125.c
@@ -1266,7 +1266,6 @@ static struct platform_driver sm6125_tlmm_driver = {
 		.of_match_table = sm6125_tlmm_of_match,
 	},
 	.probe = sm6125_tlmm_probe,
-	.remove = msm_pinctrl_remove,
 };
 
 static int __init sm6125_tlmm_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-sm6350.c b/drivers/pinctrl/qcom/pinctrl-sm6350.c
index f3828c07b134..ba4686c86c54 100644
--- a/drivers/pinctrl/qcom/pinctrl-sm6350.c
+++ b/drivers/pinctrl/qcom/pinctrl-sm6350.c
@@ -1373,7 +1373,6 @@ static struct platform_driver sm6350_tlmm_driver = {
 		.of_match_table = sm6350_tlmm_of_match,
 	},
 	.probe = sm6350_tlmm_probe,
-	.remove = msm_pinctrl_remove,
 };
 
 static int __init sm6350_tlmm_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-sm6375.c b/drivers/pinctrl/qcom/pinctrl-sm6375.c
index c82c8516932e..49031571e65e 100644
--- a/drivers/pinctrl/qcom/pinctrl-sm6375.c
+++ b/drivers/pinctrl/qcom/pinctrl-sm6375.c
@@ -1516,7 +1516,6 @@ static struct platform_driver sm6375_tlmm_driver = {
 		.of_match_table = sm6375_tlmm_of_match,
 	},
 	.probe = sm6375_tlmm_probe,
-	.remove = msm_pinctrl_remove,
 };
 
 static int __init sm6375_tlmm_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-sm7150.c b/drivers/pinctrl/qcom/pinctrl-sm7150.c
index 3c7fd8af6635..6e89966cd70e 100644
--- a/drivers/pinctrl/qcom/pinctrl-sm7150.c
+++ b/drivers/pinctrl/qcom/pinctrl-sm7150.c
@@ -1255,7 +1255,6 @@ static struct platform_driver sm7150_tlmm_driver = {
 		.of_match_table = sm7150_tlmm_of_match,
 	},
 	.probe = sm7150_tlmm_probe,
-	.remove = msm_pinctrl_remove,
 };
 
 static int __init sm7150_tlmm_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-sm8150.c b/drivers/pinctrl/qcom/pinctrl-sm8150.c
index 01aea9c70b7a..794ed99463f7 100644
--- a/drivers/pinctrl/qcom/pinctrl-sm8150.c
+++ b/drivers/pinctrl/qcom/pinctrl-sm8150.c
@@ -1542,7 +1542,6 @@ static struct platform_driver sm8150_pinctrl_driver = {
 		.of_match_table = sm8150_pinctrl_of_match,
 	},
 	.probe = sm8150_pinctrl_probe,
-	.remove = msm_pinctrl_remove,
 };
 
 static int __init sm8150_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-sm8250.c b/drivers/pinctrl/qcom/pinctrl-sm8250.c
index e9961a49ff98..fb6f005d64f5 100644
--- a/drivers/pinctrl/qcom/pinctrl-sm8250.c
+++ b/drivers/pinctrl/qcom/pinctrl-sm8250.c
@@ -1351,7 +1351,6 @@ static struct platform_driver sm8250_pinctrl_driver = {
 		.of_match_table = sm8250_pinctrl_of_match,
 	},
 	.probe = sm8250_pinctrl_probe,
-	.remove = msm_pinctrl_remove,
 };
 
 static int __init sm8250_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-sm8350.c b/drivers/pinctrl/qcom/pinctrl-sm8350.c
index 9c69458bd910..c8a3f39ce6f1 100644
--- a/drivers/pinctrl/qcom/pinctrl-sm8350.c
+++ b/drivers/pinctrl/qcom/pinctrl-sm8350.c
@@ -1642,7 +1642,6 @@ static struct platform_driver sm8350_tlmm_driver = {
 		.of_match_table = sm8350_tlmm_of_match,
 	},
 	.probe = sm8350_tlmm_probe,
-	.remove = msm_pinctrl_remove,
 };
 
 static int __init sm8350_tlmm_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-sm8450.c b/drivers/pinctrl/qcom/pinctrl-sm8450.c
index d11bb1ee9e3d..f2e52d5a0f93 100644
--- a/drivers/pinctrl/qcom/pinctrl-sm8450.c
+++ b/drivers/pinctrl/qcom/pinctrl-sm8450.c
@@ -1677,7 +1677,6 @@ static struct platform_driver sm8450_tlmm_driver = {
 		.of_match_table = sm8450_tlmm_of_match,
 	},
 	.probe = sm8450_tlmm_probe,
-	.remove = msm_pinctrl_remove,
 };
 
 static int __init sm8450_tlmm_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-sm8550.c b/drivers/pinctrl/qcom/pinctrl-sm8550.c
index 3c847d9cb5d9..1b4496cb39eb 100644
--- a/drivers/pinctrl/qcom/pinctrl-sm8550.c
+++ b/drivers/pinctrl/qcom/pinctrl-sm8550.c
@@ -1762,7 +1762,6 @@ static struct platform_driver sm8550_tlmm_driver = {
 		.of_match_table = sm8550_tlmm_of_match,
 	},
 	.probe = sm8550_tlmm_probe,
-	.remove = msm_pinctrl_remove,
 };
 
 static int __init sm8550_tlmm_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-sm8650.c b/drivers/pinctrl/qcom/pinctrl-sm8650.c
index 104708252d12..449a0077f4b1 100644
--- a/drivers/pinctrl/qcom/pinctrl-sm8650.c
+++ b/drivers/pinctrl/qcom/pinctrl-sm8650.c
@@ -1742,7 +1742,6 @@ static struct platform_driver sm8650_tlmm_driver = {
 		.of_match_table = sm8650_tlmm_of_match,
 	},
 	.probe = sm8650_tlmm_probe,
-	.remove = msm_pinctrl_remove,
 };
 
 static int __init sm8650_tlmm_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-sm8750.c b/drivers/pinctrl/qcom/pinctrl-sm8750.c
index b94fb4ee0ec3..8516693d1db5 100644
--- a/drivers/pinctrl/qcom/pinctrl-sm8750.c
+++ b/drivers/pinctrl/qcom/pinctrl-sm8750.c
@@ -1711,7 +1711,6 @@ static struct platform_driver sm8750_tlmm_driver = {
 		.of_match_table = sm8750_tlmm_of_match,
 	},
 	.probe = sm8750_tlmm_probe,
-	.remove = msm_pinctrl_remove,
 };
 
 static int __init sm8750_tlmm_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-x1e80100.c b/drivers/pinctrl/qcom/pinctrl-x1e80100.c
index 419cb8facb2f..d4b215f34c39 100644
--- a/drivers/pinctrl/qcom/pinctrl-x1e80100.c
+++ b/drivers/pinctrl/qcom/pinctrl-x1e80100.c
@@ -1861,7 +1861,6 @@ static struct platform_driver x1e80100_pinctrl_driver = {
 		.of_match_table = x1e80100_pinctrl_of_match,
 	},
 	.probe = x1e80100_pinctrl_probe,
-	.remove = msm_pinctrl_remove,
 };
 
 static int __init x1e80100_pinctrl_init(void)

From 315345610faee8a0568b522dba9e35067d1732ab Mon Sep 17 00:00:00 2001
From: Wojciech Slenska <wojciech.slenska@gmail.com>
Date: Fri, 23 May 2025 12:14:37 +0200
Subject: [PATCH 0081/1334] pinctrl: qcom: pinctrl-qcm2290: Add missing pins

Added the missing pins to the qcm2290_pins table.

Signed-off-by: Wojciech Slenska <wojciech.slenska@gmail.com>
Fixes: 48e049ef1238 ("pinctrl: qcom: Add QCM2290 pinctrl driver")
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
Link: https://lore.kernel.org/20250523101437.59092-1-wojciech.slenska@gmail.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/qcom/pinctrl-qcm2290.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/drivers/pinctrl/qcom/pinctrl-qcm2290.c b/drivers/pinctrl/qcom/pinctrl-qcm2290.c
index 85c951305abd..eeeec6434f6a 100644
--- a/drivers/pinctrl/qcom/pinctrl-qcm2290.c
+++ b/drivers/pinctrl/qcom/pinctrl-qcm2290.c
@@ -167,6 +167,10 @@ static const struct pinctrl_pin_desc qcm2290_pins[] = {
 	PINCTRL_PIN(62, "GPIO_62"),
 	PINCTRL_PIN(63, "GPIO_63"),
 	PINCTRL_PIN(64, "GPIO_64"),
+	PINCTRL_PIN(65, "GPIO_65"),
+	PINCTRL_PIN(66, "GPIO_66"),
+	PINCTRL_PIN(67, "GPIO_67"),
+	PINCTRL_PIN(68, "GPIO_68"),
 	PINCTRL_PIN(69, "GPIO_69"),
 	PINCTRL_PIN(70, "GPIO_70"),
 	PINCTRL_PIN(71, "GPIO_71"),
@@ -181,12 +185,17 @@ static const struct pinctrl_pin_desc qcm2290_pins[] = {
 	PINCTRL_PIN(80, "GPIO_80"),
 	PINCTRL_PIN(81, "GPIO_81"),
 	PINCTRL_PIN(82, "GPIO_82"),
+	PINCTRL_PIN(83, "GPIO_83"),
+	PINCTRL_PIN(84, "GPIO_84"),
+	PINCTRL_PIN(85, "GPIO_85"),
 	PINCTRL_PIN(86, "GPIO_86"),
 	PINCTRL_PIN(87, "GPIO_87"),
 	PINCTRL_PIN(88, "GPIO_88"),
 	PINCTRL_PIN(89, "GPIO_89"),
 	PINCTRL_PIN(90, "GPIO_90"),
 	PINCTRL_PIN(91, "GPIO_91"),
+	PINCTRL_PIN(92, "GPIO_92"),
+	PINCTRL_PIN(93, "GPIO_93"),
 	PINCTRL_PIN(94, "GPIO_94"),
 	PINCTRL_PIN(95, "GPIO_95"),
 	PINCTRL_PIN(96, "GPIO_96"),

From fcd65d65fd85dbde090ef8c2615760ebc5ccf9e3 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Wed, 28 May 2025 11:22:02 +0200
Subject: [PATCH 0082/1334] pinctrl: st: Drop unused st_gpio_bank() function

Static inline st_gpio_bank() function is not referenced:

  pinctrl-st.c:377:19: error: unused function 'st_gpio_bank' [-Werror,-Wunused-function]

Fixes: 701016c0cba5 ("pinctrl: st: Add pinctrl and pinconf support.")
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/20250528092201.52132-2-krzysztof.kozlowski@linaro.org
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/pinctrl-st.c | 5 -----
 1 file changed, 5 deletions(-)

diff --git a/drivers/pinctrl/pinctrl-st.c b/drivers/pinctrl/pinctrl-st.c
index fe2d52e434db..8a2ef74862d3 100644
--- a/drivers/pinctrl/pinctrl-st.c
+++ b/drivers/pinctrl/pinctrl-st.c
@@ -374,11 +374,6 @@ static struct st_pio_control *st_get_pio_control(
 }
 
 /* Low level functions.. */
-static inline int st_gpio_bank(int gpio)
-{
-	return gpio/ST_GPIO_PINS_PER_BANK;
-}
-
 static inline int st_gpio_pin(int gpio)
 {
 	return gpio%ST_GPIO_PINS_PER_BANK;

From d38e00c417e1ca0c586802e47ad7d54347c91f67 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Wed, 28 May 2025 12:45:15 +0200
Subject: [PATCH 0083/1334] pinctrl: MAINTAINERS: Drop bouncing Jianlong Huang

Emails to Jianlong Huang bounce since 9 months, so drop the person from
maintainers:

  550 5.4.1 Recipient address rejected: Access denied.

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/20250528104514.184122-2-krzysztof.kozlowski@linaro.org
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 .../bindings/pinctrl/starfive,jh7110-aon-pinctrl.yaml           | 2 +-
 .../bindings/pinctrl/starfive,jh7110-sys-pinctrl.yaml           | 2 +-
 MAINTAINERS                                                     | 1 -
 3 files changed, 2 insertions(+), 3 deletions(-)

diff --git a/Documentation/devicetree/bindings/pinctrl/starfive,jh7110-aon-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/starfive,jh7110-aon-pinctrl.yaml
index b470901f5f56..4dbef86bd958 100644
--- a/Documentation/devicetree/bindings/pinctrl/starfive,jh7110-aon-pinctrl.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/starfive,jh7110-aon-pinctrl.yaml
@@ -15,7 +15,7 @@ description: |
   Some peripherals such as PWM have their I/O go through the 4 "GPIOs".
 
 maintainers:
-  - Jianlong Huang <jianlong.huang@starfivetech.com>
+  - Hal Feng <hal.feng@starfivetech.com>
 
 properties:
   compatible:
diff --git a/Documentation/devicetree/bindings/pinctrl/starfive,jh7110-sys-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/starfive,jh7110-sys-pinctrl.yaml
index 222b9e240f8a..e2a25a20f6a6 100644
--- a/Documentation/devicetree/bindings/pinctrl/starfive,jh7110-sys-pinctrl.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/starfive,jh7110-sys-pinctrl.yaml
@@ -18,7 +18,7 @@ description: |
   any GPIO can be set up to be controlled by any of the peripherals.
 
 maintainers:
-  - Jianlong Huang <jianlong.huang@starfivetech.com>
+  - Hal Feng <hal.feng@starfivetech.com>
 
 properties:
   compatible:
diff --git a/MAINTAINERS b/MAINTAINERS
index a92290fffa16..4f17af5d7240 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -23661,7 +23661,6 @@ F:	include/dt-bindings/clock/starfive?jh71*.h
 
 STARFIVE JH71X0 PINCTRL DRIVERS
 M:	Emil Renner Berthing <kernel@esmil.dk>
-M:	Jianlong Huang <jianlong.huang@starfivetech.com>
 M:	Hal Feng <hal.feng@starfivetech.com>
 L:	linux-gpio@vger.kernel.org
 S:	Maintained

From 24b0277c1c539cd41539d9297baafc62df04464a Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Sun, 1 Jun 2025 12:51:01 +0200
Subject: [PATCH 0084/1334] pinctrl: tb10x: Drop of_match_ptr for ID table

The driver can match only via the DT table so the table should be always
used and the of_match_ptr does not have any sense (this also allows ACPI
matching via PRP0001, even though it might not be relevant here).  This
also fixes !CONFIG_OF warning:

  pinctrl-tb10x.c:815:34: warning: unused variable 'tb10x_pinctrl_dt_ids' [-Wunused-const-variable]

Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202505301317.EI1caRC0-lkp@intel.com/
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/20250601105100.27927-2-krzysztof.kozlowski@linaro.org
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/pinctrl-tb10x.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/pinctrl/pinctrl-tb10x.c b/drivers/pinctrl/pinctrl-tb10x.c
index d6bb8f58978d..4edb20e61951 100644
--- a/drivers/pinctrl/pinctrl-tb10x.c
+++ b/drivers/pinctrl/pinctrl-tb10x.c
@@ -823,7 +823,7 @@ static struct platform_driver tb10x_pinctrl_pdrv = {
 	.remove  = tb10x_pinctrl_remove,
 	.driver  = {
 		.name  = "tb10x_pinctrl",
-		.of_match_table = of_match_ptr(tb10x_pinctrl_dt_ids),
+		.of_match_table = tb10x_pinctrl_dt_ids,
 	}
 };
 

From a833d31ad867103ba72a0b73f3606f4ab8601719 Mon Sep 17 00:00:00 2001
From: Sudeep Holla <sudeep.holla@arm.com>
Date: Wed, 28 May 2025 09:49:41 +0100
Subject: [PATCH 0085/1334] firmware: arm_ffa: Fix memory leak by freeing
 notifier callback node

Commit e0573444edbf ("firmware: arm_ffa: Add interfaces to request
notification callbacks") adds support for notifier callbacks by allocating
and inserting a callback node into a hashtable during registration of
notifiers. However, during unregistration, the code only removes the
node from the hashtable without freeing the associated memory, resulting
in a memory leak.

Resolve the memory leak issue by ensuring the allocated notifier callback
node is properly freed after it is removed from the hashtable entry.

Fixes: e0573444edbf ("firmware: arm_ffa: Add interfaces to request notification callbacks")
Message-Id: <20250528-ffa_notif_fix-v1-1-5ed7bc7f8437@arm.com>
Reviewed-by: Jens Wiklander <jens.wiklander@linaro.org>
Signed-off-by: Sudeep Holla <sudeep.holla@arm.com>
---
 drivers/firmware/arm_ffa/driver.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/firmware/arm_ffa/driver.c b/drivers/firmware/arm_ffa/driver.c
index fe55613a8ea9..6f75cdf29720 100644
--- a/drivers/firmware/arm_ffa/driver.c
+++ b/drivers/firmware/arm_ffa/driver.c
@@ -1284,6 +1284,7 @@ update_notifier_cb(struct ffa_device *dev, int notify_id, void *cb,
 		hash_add(drv_info->notifier_hash, &cb_info->hnode, notify_id);
 	} else {
 		hash_del(&cb_info->hnode);
+		kfree(cb_info);
 	}
 
 	return 0;

From 27e850c88df0e25474a8caeb2903e2e90b62c1dc Mon Sep 17 00:00:00 2001
From: Sudeep Holla <sudeep.holla@arm.com>
Date: Wed, 28 May 2025 09:49:42 +0100
Subject: [PATCH 0086/1334] firmware: arm_ffa: Move memory allocation outside
 the mutex locking

The notifier callback node allocation is currently done while holding
the notify_lock mutex. While this is safe even if memory allocation may
sleep, we need to move the allocation outside the locked region in
preparation to move from using muxtes to rwlocks.

Move the memory allocation to avoid potential sleeping in atomic context
once the locks are moved from mutex to rwlocks.

Fixes: e0573444edbf ("firmware: arm_ffa: Add interfaces to request notification callbacks")
Message-Id: <20250528-ffa_notif_fix-v1-2-5ed7bc7f8437@arm.com>
Reviewed-by: Jens Wiklander <jens.wiklander@linaro.org>
Signed-off-by: Sudeep Holla <sudeep.holla@arm.com>
---
 drivers/firmware/arm_ffa/driver.c | 48 +++++++++++++++----------------
 1 file changed, 24 insertions(+), 24 deletions(-)

diff --git a/drivers/firmware/arm_ffa/driver.c b/drivers/firmware/arm_ffa/driver.c
index 6f75cdf29720..44eecb786e67 100644
--- a/drivers/firmware/arm_ffa/driver.c
+++ b/drivers/firmware/arm_ffa/driver.c
@@ -1250,13 +1250,12 @@ notifier_hnode_get_by_type(u16 notify_id, enum notify_type type)
 	return NULL;
 }
 
-static int
-update_notifier_cb(struct ffa_device *dev, int notify_id, void *cb,
-		   void *cb_data, bool is_registration, bool is_framework)
+static int update_notifier_cb(struct ffa_device *dev, int notify_id,
+			      struct notifier_cb_info *cb, bool is_framework)
 {
 	struct notifier_cb_info *cb_info = NULL;
 	enum notify_type type = ffa_notify_type_get(dev->vm_id);
-	bool cb_found;
+	bool cb_found, is_registration = !!cb;
 
 	if (is_framework)
 		cb_info = notifier_hnode_get_by_vmid_uuid(notify_id, dev->vm_id,
@@ -1270,18 +1269,7 @@ update_notifier_cb(struct ffa_device *dev, int notify_id, void *cb,
 		return -EINVAL;
 
 	if (is_registration) {
-		cb_info = kzalloc(sizeof(*cb_info), GFP_KERNEL);
-		if (!cb_info)
-			return -ENOMEM;
-
-		cb_info->dev = dev;
-		cb_info->cb_data = cb_data;
-		if (is_framework)
-			cb_info->fwk_cb = cb;
-		else
-			cb_info->cb = cb;
-
-		hash_add(drv_info->notifier_hash, &cb_info->hnode, notify_id);
+		hash_add(drv_info->notifier_hash, &cb->hnode, notify_id);
 	} else {
 		hash_del(&cb_info->hnode);
 		kfree(cb_info);
@@ -1303,8 +1291,7 @@ static int __ffa_notify_relinquish(struct ffa_device *dev, int notify_id,
 
 	mutex_lock(&drv_info->notify_lock);
 
-	rc = update_notifier_cb(dev, notify_id, NULL, NULL, false,
-				is_framework);
+	rc = update_notifier_cb(dev, notify_id, NULL, is_framework);
 	if (rc) {
 		pr_err("Could not unregister notification callback\n");
 		mutex_unlock(&drv_info->notify_lock);
@@ -1335,6 +1322,7 @@ static int __ffa_notify_request(struct ffa_device *dev, bool is_per_vcpu,
 {
 	int rc;
 	u32 flags = 0;
+	struct notifier_cb_info *cb_info = NULL;
 
 	if (ffa_notifications_disabled())
 		return -EOPNOTSUPP;
@@ -1342,6 +1330,17 @@ static int __ffa_notify_request(struct ffa_device *dev, bool is_per_vcpu,
 	if (notify_id >= FFA_MAX_NOTIFICATIONS)
 		return -EINVAL;
 
+	cb_info = kzalloc(sizeof(*cb_info), GFP_KERNEL);
+	if (!cb_info)
+		return -ENOMEM;
+
+	cb_info->dev = dev;
+	cb_info->cb_data = cb_data;
+	if (is_framework)
+		cb_info->fwk_cb = cb;
+	else
+		cb_info->cb = cb;
+
 	mutex_lock(&drv_info->notify_lock);
 
 	if (!is_framework) {
@@ -1349,21 +1348,22 @@ static int __ffa_notify_request(struct ffa_device *dev, bool is_per_vcpu,
 			flags = PER_VCPU_NOTIFICATION_FLAG;
 
 		rc = ffa_notification_bind(dev->vm_id, BIT(notify_id), flags);
-		if (rc) {
-			mutex_unlock(&drv_info->notify_lock);
-			return rc;
-		}
+		if (rc)
+			goto out_unlock_free;
 	}
 
-	rc = update_notifier_cb(dev, notify_id, cb, cb_data, true,
-				is_framework);
+	rc = update_notifier_cb(dev, notify_id, cb_info, is_framework);
 	if (rc) {
 		pr_err("Failed to register callback for %d - %d\n",
 		       notify_id, rc);
 		if (!is_framework)
 			ffa_notification_unbind(dev->vm_id, BIT(notify_id));
 	}
+
+out_unlock_free:
 	mutex_unlock(&drv_info->notify_lock);
+	if (rc)
+		kfree(cb_info);
 
 	return rc;
 }

From 9ca7a421229bbdfbe2e1e628cff5cfa782720a10 Mon Sep 17 00:00:00 2001
From: Sudeep Holla <sudeep.holla@arm.com>
Date: Wed, 28 May 2025 09:49:43 +0100
Subject: [PATCH 0087/1334] firmware: arm_ffa: Replace mutex with rwlock to
 avoid sleep in atomic context
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The current use of a mutex to protect the notifier hashtable accesses
can lead to issues in the atomic context. It results in the below
kernel warnings:

  |  BUG: sleeping function called from invalid context at kernel/locking/mutex.c:258
  |  in_atomic(): 1, irqs_disabled(): 1, non_block: 0, pid: 9, name: kworker/0:0
  |  preempt_count: 1, expected: 0
  |  RCU nest depth: 0, expected: 0
  |  CPU: 0 UID: 0 PID: 9 Comm: kworker/0:0 Not tainted 6.14.0 #4
  |  Workqueue: ffa_pcpu_irq_notification notif_pcpu_irq_work_fn
  |  Call trace:
  |   show_stack+0x18/0x24 (C)
  |   dump_stack_lvl+0x78/0x90
  |   dump_stack+0x18/0x24
  |   __might_resched+0x114/0x170
  |   __might_sleep+0x48/0x98
  |   mutex_lock+0x24/0x80
  |   handle_notif_callbacks+0x54/0xe0
  |   notif_get_and_handle+0x40/0x88
  |   generic_exec_single+0x80/0xc0
  |   smp_call_function_single+0xfc/0x1a0
  |   notif_pcpu_irq_work_fn+0x2c/0x38
  |   process_one_work+0x14c/0x2b4
  |   worker_thread+0x2e4/0x3e0
  |   kthread+0x13c/0x210
  |   ret_from_fork+0x10/0x20

To address this, replace the mutex with an rwlock to protect the notifier
hashtable accesses. This ensures that read-side locking does not sleep and
multiple readers can acquire the lock concurrently, avoiding unnecessary
contention and potential deadlocks. Writer access remains exclusive,
preserving correctness.

This change resolves warnings from lockdep about potential sleep in
atomic context.

Cc: Jens Wiklander <jens.wiklander@linaro.org>
Reported-by: Jérôme Forissier <jerome.forissier@linaro.org>
Closes: https://github.com/OP-TEE/optee_os/issues/7394
Fixes: e0573444edbf ("firmware: arm_ffa: Add interfaces to request notification callbacks")
Message-Id: <20250528-ffa_notif_fix-v1-3-5ed7bc7f8437@arm.com>
Reviewed-by: Jens Wiklander <jens.wiklander@linaro.org>
Tested-by: Jens Wiklander <jens.wiklander@linaro.org>
Signed-off-by: Sudeep Holla <sudeep.holla@arm.com>
---
 drivers/firmware/arm_ffa/driver.c | 22 +++++++++++-----------
 1 file changed, 11 insertions(+), 11 deletions(-)

diff --git a/drivers/firmware/arm_ffa/driver.c b/drivers/firmware/arm_ffa/driver.c
index 44eecb786e67..37eb2e6c2f9f 100644
--- a/drivers/firmware/arm_ffa/driver.c
+++ b/drivers/firmware/arm_ffa/driver.c
@@ -110,7 +110,7 @@ struct ffa_drv_info {
 	struct work_struct sched_recv_irq_work;
 	struct xarray partition_info;
 	DECLARE_HASHTABLE(notifier_hash, ilog2(FFA_MAX_NOTIFICATIONS));
-	struct mutex notify_lock; /* lock to protect notifier hashtable  */
+	rwlock_t notify_lock; /* lock to protect notifier hashtable  */
 };
 
 static struct ffa_drv_info *drv_info;
@@ -1289,19 +1289,19 @@ static int __ffa_notify_relinquish(struct ffa_device *dev, int notify_id,
 	if (notify_id >= FFA_MAX_NOTIFICATIONS)
 		return -EINVAL;
 
-	mutex_lock(&drv_info->notify_lock);
+	write_lock(&drv_info->notify_lock);
 
 	rc = update_notifier_cb(dev, notify_id, NULL, is_framework);
 	if (rc) {
 		pr_err("Could not unregister notification callback\n");
-		mutex_unlock(&drv_info->notify_lock);
+		write_unlock(&drv_info->notify_lock);
 		return rc;
 	}
 
 	if (!is_framework)
 		rc = ffa_notification_unbind(dev->vm_id, BIT(notify_id));
 
-	mutex_unlock(&drv_info->notify_lock);
+	write_unlock(&drv_info->notify_lock);
 
 	return rc;
 }
@@ -1341,7 +1341,7 @@ static int __ffa_notify_request(struct ffa_device *dev, bool is_per_vcpu,
 	else
 		cb_info->cb = cb;
 
-	mutex_lock(&drv_info->notify_lock);
+	write_lock(&drv_info->notify_lock);
 
 	if (!is_framework) {
 		if (is_per_vcpu)
@@ -1361,7 +1361,7 @@ static int __ffa_notify_request(struct ffa_device *dev, bool is_per_vcpu,
 	}
 
 out_unlock_free:
-	mutex_unlock(&drv_info->notify_lock);
+	write_unlock(&drv_info->notify_lock);
 	if (rc)
 		kfree(cb_info);
 
@@ -1407,9 +1407,9 @@ static void handle_notif_callbacks(u64 bitmap, enum notify_type type)
 		if (!(bitmap & 1))
 			continue;
 
-		mutex_lock(&drv_info->notify_lock);
+		read_lock(&drv_info->notify_lock);
 		cb_info = notifier_hnode_get_by_type(notify_id, type);
-		mutex_unlock(&drv_info->notify_lock);
+		read_unlock(&drv_info->notify_lock);
 
 		if (cb_info && cb_info->cb)
 			cb_info->cb(notify_id, cb_info->cb_data);
@@ -1447,9 +1447,9 @@ static void handle_fwk_notif_callbacks(u32 bitmap)
 
 	ffa_rx_release();
 
-	mutex_lock(&drv_info->notify_lock);
+	read_lock(&drv_info->notify_lock);
 	cb_info = notifier_hnode_get_by_vmid_uuid(notify_id, target, &uuid);
-	mutex_unlock(&drv_info->notify_lock);
+	read_unlock(&drv_info->notify_lock);
 
 	if (cb_info && cb_info->fwk_cb)
 		cb_info->fwk_cb(notify_id, cb_info->cb_data, buf);
@@ -1974,7 +1974,7 @@ static void ffa_notifications_setup(void)
 		goto cleanup;
 
 	hash_init(drv_info->notifier_hash);
-	mutex_init(&drv_info->notify_lock);
+	rwlock_init(&drv_info->notify_lock);
 
 	drv_info->notif_enabled = true;
 	return;

From 4c46a471be12216347ba707f8eadadbf5d68e698 Mon Sep 17 00:00:00 2001
From: Viresh Kumar <viresh.kumar@linaro.org>
Date: Tue, 3 Jun 2025 16:38:53 +0530
Subject: [PATCH 0088/1334] firmware: arm_ffa: Fix the missing entry in struct
 ffa_indirect_msg_hdr

As per the spec, one 32 bit reserved entry is missing here, add it.

Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Fixes: 910cc1acc9b4 ("firmware: arm_ffa: Add support for passing UUID in FFA_MSG_SEND2")
Reviewed-by: Bertrand Marquis <bertrand.marquis@arm.com>
Message-Id: <28a624fbf416975de4fbe08cfbf7c2db89cb630e.1748948911.git.viresh.kumar@linaro.org>
Signed-off-by: Sudeep Holla <sudeep.holla@arm.com>
---
 include/linux/arm_ffa.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/include/linux/arm_ffa.h b/include/linux/arm_ffa.h
index 5bded24dc24f..e1634897e159 100644
--- a/include/linux/arm_ffa.h
+++ b/include/linux/arm_ffa.h
@@ -283,6 +283,7 @@ struct ffa_indirect_msg_hdr {
 	u32 offset;
 	u32 send_recv_id;
 	u32 size;
+	u32 res1;
 	uuid_t uuid;
 };
 

From e51a086117ed857ea455c9ea774dbfb82f53e517 Mon Sep 17 00:00:00 2001
From: Andres Urian Florez <andres.emb.sys@gmail.com>
Date: Sun, 8 Jun 2025 18:04:21 -0500
Subject: [PATCH 0089/1334] spi: offload: check offload ops existence before
 disabling the trigger

Add a safe guard in spi_offload_trigger to check the existence of
offload->ops before invoking the trigger_disable callback

Signed-off-by: Andres Urian Florez <andres.emb.sys@gmail.com>
Link: https://patch.msgid.link/20250608230422.325360-1-andres.emb.sys@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-offload.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/spi/spi-offload.c b/drivers/spi/spi-offload.c
index e674097bf3be..d336f4d228d5 100644
--- a/drivers/spi/spi-offload.c
+++ b/drivers/spi/spi-offload.c
@@ -297,7 +297,7 @@ int spi_offload_trigger_enable(struct spi_offload *offload,
 	if (trigger->ops->enable) {
 		ret = trigger->ops->enable(trigger, config);
 		if (ret) {
-			if (offload->ops->trigger_disable)
+			if (offload->ops && offload->ops->trigger_disable)
 				offload->ops->trigger_disable(offload);
 			return ret;
 		}

From 009c3a4bc41e855fd76f92727f9fbae4e5917d7f Mon Sep 17 00:00:00 2001
From: Avri Altman <avri.altman@sandisk.com>
Date: Mon, 26 May 2025 14:44:45 +0300
Subject: [PATCH 0090/1334] mmc: core: sd: Apply BROKEN_SD_DISCARD quirk
 earlier

Move the BROKEN_SD_DISCARD quirk for certain SanDisk SD cards from the
`mmc_blk_fixups[]` to `mmc_sd_fixups[]`. This ensures the quirk is
applied earlier in the device initialization process, aligning with the
reasoning in [1]. Applying the quirk sooner prevents the kernel from
incorrectly enabling discard support on affected cards during initial
setup.

[1] https://lore.kernel.org/all/20240820230631.GA436523@sony.com

Fixes: 07d2872bf4c8 ("mmc: core: Add SD card quirk for broken discard")
Signed-off-by: Avri Altman <avri.altman@sandisk.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20250526114445.675548-1-avri.altman@sandisk.com
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/core/quirks.h | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/mmc/core/quirks.h b/drivers/mmc/core/quirks.h
index 7f893bafaa60..c417ed34c057 100644
--- a/drivers/mmc/core/quirks.h
+++ b/drivers/mmc/core/quirks.h
@@ -44,6 +44,12 @@ static const struct mmc_fixup __maybe_unused mmc_sd_fixups[] = {
 		   0, -1ull, SDIO_ANY_ID, SDIO_ANY_ID, add_quirk_sd,
 		   MMC_QUIRK_NO_UHS_DDR50_TUNING, EXT_CSD_REV_ANY),
 
+	/*
+	 * Some SD cards reports discard support while they don't
+	 */
+	MMC_FIXUP(CID_NAME_ANY, CID_MANFID_SANDISK_SD, 0x5344, add_quirk_sd,
+		  MMC_QUIRK_BROKEN_SD_DISCARD),
+
 	END_FIXUP
 };
 
@@ -147,12 +153,6 @@ static const struct mmc_fixup __maybe_unused mmc_blk_fixups[] = {
 	MMC_FIXUP("M62704", CID_MANFID_KINGSTON, 0x0100, add_quirk_mmc,
 		  MMC_QUIRK_TRIM_BROKEN),
 
-	/*
-	 * Some SD cards reports discard support while they don't
-	 */
-	MMC_FIXUP(CID_NAME_ANY, CID_MANFID_SANDISK_SD, 0x5344, add_quirk_sd,
-		  MMC_QUIRK_BROKEN_SD_DISCARD),
-
 	END_FIXUP
 };
 

From 3358b836d4369ad47823c26834b3613778fe75b2 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Tue, 27 May 2025 08:55:01 +0300
Subject: [PATCH 0091/1334] mmc: sdhci-of-k1: Fix error code in probe()

If spacemit_sdhci_get_clocks() fails, then propagate the error code.
Don't return success.

Fixes: e5502d15b0f3 ("mmc: sdhci-of-k1: add support for SpacemiT K1 SoC")
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Reviewed-by: Yixun Lan <dlan@gentoo.org>
Acked-by: Adrian Hunter <adrian.hunter@intel.com>
Link: https://lore.kernel.org/r/aDVTtQdXVtRhxOrb@stanley.mountain
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/host/sdhci-of-k1.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/mmc/host/sdhci-of-k1.c b/drivers/mmc/host/sdhci-of-k1.c
index 6880d3e9ab62..2e5da7c5834c 100644
--- a/drivers/mmc/host/sdhci-of-k1.c
+++ b/drivers/mmc/host/sdhci-of-k1.c
@@ -276,7 +276,8 @@ static int spacemit_sdhci_probe(struct platform_device *pdev)
 
 	host->mmc->caps |= MMC_CAP_NEED_RSP_BUSY;
 
-	if (spacemit_sdhci_get_clocks(dev, pltfm_host))
+	ret = spacemit_sdhci_get_clocks(dev, pltfm_host);
+	if (ret)
 		goto err_pltfm;
 
 	ret = sdhci_add_host(host);

From 539d80575b810c7a5987c7ac8915e3bc99c03695 Mon Sep 17 00:00:00 2001
From: "Masami Hiramatsu (Google)" <mhiramat@kernel.org>
Date: Thu, 5 Jun 2025 10:07:38 +0900
Subject: [PATCH 0092/1334] mtk-sd: Fix a pagefault in dma_unmap_sg() for not
 prepared data

When swiotlb buffer is full, the dma_map_sg() returns 0 to
msdc_prepare_data(), but it does not check it and sets the
MSDC_PREPARE_FLAG.

swiotlb_tbl_map_single() /* prints "swiotlb buffer is full" */
  <-swiotlb_map()
    <-dma_direct_map_page()
      <-dma_direct_map_sg()
        <-__dma_map_sg_attrs()
          <-dma_map_sg_attrs()
            <-dma_map_sg()  /* returns 0 (pages mapped) */
              <-msdc_prepare_data()

Then, the msdc_unprepare_data() checks MSDC_PREPARE_FLAG and calls
dma_unmap_sg() with unmapped pages. It causes a page fault.

To fix this problem, Do not set MSDC_PREPARE_FLAG if dma_map_sg()
fails because this is not prepared.

Fixes: 208489032bdd ("mmc: mediatek: Add Mediatek MMC driver")
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Tested-by: Sergey Senozhatsky <senozhatsky@chromium.org>
Reviewed-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/174908565814.4056588.769599127120955383.stgit@mhiramat.tok.corp.google.com
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/host/mtk-sd.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/mmc/host/mtk-sd.c b/drivers/mmc/host/mtk-sd.c
index 31eb90536bce..b1d1586cf1fc 100644
--- a/drivers/mmc/host/mtk-sd.c
+++ b/drivers/mmc/host/mtk-sd.c
@@ -846,9 +846,10 @@ static inline void msdc_dma_setup(struct msdc_host *host, struct msdc_dma *dma,
 static void msdc_prepare_data(struct msdc_host *host, struct mmc_data *data)
 {
 	if (!(data->host_cookie & MSDC_PREPARE_FLAG)) {
-		data->host_cookie |= MSDC_PREPARE_FLAG;
 		data->sg_count = dma_map_sg(host->dev, data->sg, data->sg_len,
 					    mmc_get_dma_dir(data));
+		if (data->sg_count)
+			data->host_cookie |= MSDC_PREPARE_FLAG;
 	}
 }
 

From 779a0c9e06a91d0007f2a4f4071e3b9a8102b15e Mon Sep 17 00:00:00 2001
From: Lizhi Hou <lizhi.hou@amd.com>
Date: Wed, 4 Jun 2025 07:32:17 -0700
Subject: [PATCH 0093/1334] accel/amdxdna: Fix incorrect PSP firmware size

The incorrect PSP firmware size is used for initializing. It may
cause error for newer version firmware.

Fixes: 8c9ff1b181ba ("accel/amdxdna: Add a new driver for AMD AI Engine")
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Lizhi Hou <lizhi.hou@amd.com>
Link: https://lore.kernel.org/r/20250604143217.1386272-1-lizhi.hou@amd.com
---
 drivers/accel/amdxdna/aie2_psp.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/accel/amdxdna/aie2_psp.c b/drivers/accel/amdxdna/aie2_psp.c
index dc3a072ce3b6..f28a060a8810 100644
--- a/drivers/accel/amdxdna/aie2_psp.c
+++ b/drivers/accel/amdxdna/aie2_psp.c
@@ -126,8 +126,8 @@ struct psp_device *aie2m_psp_create(struct drm_device *ddev, struct psp_config *
 	psp->ddev = ddev;
 	memcpy(psp->psp_regs, conf->psp_regs, sizeof(psp->psp_regs));
 
-	psp->fw_buf_sz = ALIGN(conf->fw_size, PSP_FW_ALIGN) + PSP_FW_ALIGN;
-	psp->fw_buffer = drmm_kmalloc(ddev, psp->fw_buf_sz, GFP_KERNEL);
+	psp->fw_buf_sz = ALIGN(conf->fw_size, PSP_FW_ALIGN);
+	psp->fw_buffer = drmm_kmalloc(ddev, psp->fw_buf_sz + PSP_FW_ALIGN, GFP_KERNEL);
 	if (!psp->fw_buffer) {
 		drm_err(ddev, "no memory for fw buffer");
 		return NULL;

From d53fd59707c402d03ec740b4e90a2ddcb5312006 Mon Sep 17 00:00:00 2001
From: "Rob Herring (Arm)" <robh@kernel.org>
Date: Wed, 7 May 2025 16:59:02 -0500
Subject: [PATCH 0094/1334] dt-bindings: soc: fsl,ls1028a-reset: Drop extra "/"
 in $id

The $id value has a double "//". Drop it.

Fixes: 9ca5a7d9d2e0 ("dt-bindings: soc: fsl: Add fsl,ls1028a-reset for reset syscon node")
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20250507215903.2748698-1-robh@kernel.org
Signed-off-by: Rob Herring (Arm) <robh@kernel.org>
---
 .../devicetree/bindings/soc/fsl/fsl,ls1028a-reset.yaml          | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/soc/fsl/fsl,ls1028a-reset.yaml b/Documentation/devicetree/bindings/soc/fsl/fsl,ls1028a-reset.yaml
index 31295be91013..558a8c7aab9c 100644
--- a/Documentation/devicetree/bindings/soc/fsl/fsl,ls1028a-reset.yaml
+++ b/Documentation/devicetree/bindings/soc/fsl/fsl,ls1028a-reset.yaml
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
 %YAML 1.2
 ---
-$id: http://devicetree.org/schemas//soc/fsl/fsl,ls1028a-reset.yaml#
+$id: http://devicetree.org/schemas/soc/fsl/fsl,ls1028a-reset.yaml#
 $schema: http://devicetree.org/meta-schemas/core.yaml#
 
 title: Freescale Layerscape Reset Registers Module

From d6fb4f01736a1d18cc981eb04fa2907a7121fc27 Mon Sep 17 00:00:00 2001
From: Maarten Lankhorst <dev@lankhorst.se>
Date: Wed, 21 May 2025 11:01:02 +0200
Subject: [PATCH 0095/1334] drm/xe/svm: Fix regression disallowing 64K SVM
 migration
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When changing the condition from >= SZ_64K, it was changed to <= SZ_64K.
This disallows migration of 64K, which is the exact minimum allowed.

Closes: https://gitlab.freedesktop.org/drm/xe/kernel/-/issues/5057
Fixes: 794f5493f518 ("drm/xe: Strict migration policy for atomic SVM faults")
Cc: stable@vger.kernel.org
Cc: Matthew Brost <matthew.brost@intel.com>
Cc: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
Reviewed-by: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
Signed-off-by: Maarten Lankhorst <dev@lankhorst.se>
Link: https://lore.kernel.org/r/20250521090102.2965100-1-dev@lankhorst.se
(cherry picked from commit 531bef26d189b28bf0d694878c0e064b30990b6c)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
---
 drivers/gpu/drm/xe/xe_svm.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/xe/xe_svm.c b/drivers/gpu/drm/xe/xe_svm.c
index 6345896585de..f0b167b3fb6a 100644
--- a/drivers/gpu/drm/xe/xe_svm.c
+++ b/drivers/gpu/drm/xe/xe_svm.c
@@ -764,7 +764,7 @@ static bool xe_svm_range_needs_migrate_to_vram(struct xe_svm_range *range,
 		return false;
 	}
 
-	if (range_size <= SZ_64K && !supports_4K_migration(vm->xe)) {
+	if (range_size < SZ_64K && !supports_4K_migration(vm->xe)) {
 		drm_dbg(&vm->xe->drm, "Platform doesn't support SZ_4K range migration\n");
 		return false;
 	}

From cf2c3eceb757e3f28e6f1034f9bc178e1535f5cc Mon Sep 17 00:00:00 2001
From: Patrice Chotard <patrice.chotard@foss.st.com>
Date: Mon, 9 Jun 2025 17:05:04 +0200
Subject: [PATCH 0096/1334] spi: stm32-ospi: Make usage of
 reset_control_acquire/release() API

As ospi reset is consumed by both OMM and OSPI drivers, use the reset
acquire/release mechanism which ensure exclusive reset usage.

This avoid to call reset_control_get/put() in OMM driver each time
we need to reset OSPI children and guarantee the reset line stays
deasserted.

During resume, OMM driver takes temporarily control of reset.

Fixes: 79b8a705e26c ("spi: stm32: Add OSPI driver")
Signed-off-by: Patrice Chotard <patrice.chotard@foss.st.com>
Reviewed-by: Philipp Zabel <p.zabel@pengutronix.de>
Link: https://patch.msgid.link/20250609-b4-upstream_ospi_reset_update-v6-1-5b602b567e8a@foss.st.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-stm32-ospi.c | 24 ++++++++++++++++++------
 1 file changed, 18 insertions(+), 6 deletions(-)

diff --git a/drivers/spi/spi-stm32-ospi.c b/drivers/spi/spi-stm32-ospi.c
index 7c1fa55fbc47..db6b1cfc970f 100644
--- a/drivers/spi/spi-stm32-ospi.c
+++ b/drivers/spi/spi-stm32-ospi.c
@@ -804,7 +804,7 @@ static int stm32_ospi_get_resources(struct platform_device *pdev)
 		return ret;
 	}
 
-	ospi->rstc = devm_reset_control_array_get_exclusive(dev);
+	ospi->rstc = devm_reset_control_array_get_exclusive_released(dev);
 	if (IS_ERR(ospi->rstc))
 		return dev_err_probe(dev, PTR_ERR(ospi->rstc),
 				     "Can't get reset\n");
@@ -936,11 +936,13 @@ static int stm32_ospi_probe(struct platform_device *pdev)
 	if (ret < 0)
 		goto err_pm_enable;
 
-	if (ospi->rstc) {
-		reset_control_assert(ospi->rstc);
-		udelay(2);
-		reset_control_deassert(ospi->rstc);
-	}
+	ret = reset_control_acquire(ospi->rstc);
+	if (ret)
+		return dev_err_probe(dev, ret, "Can not acquire reset %d\n", ret);
+
+	reset_control_assert(ospi->rstc);
+	udelay(2);
+	reset_control_deassert(ospi->rstc);
 
 	ret = spi_register_controller(ctrl);
 	if (ret) {
@@ -987,6 +989,8 @@ static void stm32_ospi_remove(struct platform_device *pdev)
 	if (ospi->dma_chrx)
 		dma_release_channel(ospi->dma_chrx);
 
+	reset_control_release(ospi->rstc);
+
 	pm_runtime_put_sync_suspend(ospi->dev);
 	pm_runtime_force_suspend(ospi->dev);
 }
@@ -997,6 +1001,8 @@ static int __maybe_unused stm32_ospi_suspend(struct device *dev)
 
 	pinctrl_pm_select_sleep_state(dev);
 
+	reset_control_release(ospi->rstc);
+
 	return pm_runtime_force_suspend(ospi->dev);
 }
 
@@ -1016,6 +1022,12 @@ static int __maybe_unused stm32_ospi_resume(struct device *dev)
 	if (ret < 0)
 		return ret;
 
+	ret = reset_control_acquire(ospi->rstc);
+	if (ret) {
+		dev_err(dev, "Can not acquire reset\n");
+		return ret;
+	}
+
 	writel_relaxed(ospi->cr_reg, regs_base + OSPI_CR);
 	writel_relaxed(ospi->dcr_reg, regs_base + OSPI_DCR1);
 	pm_runtime_mark_last_busy(ospi->dev);

From e34dbbc85d64af59176fe59fad7b4122f4330fe2 Mon Sep 17 00:00:00 2001
From: "Xin Li (Intel)" <xin@zytor.com>
Date: Mon, 9 Jun 2025 01:40:53 -0700
Subject: [PATCH 0097/1334] x86/fred/signal: Prevent immediate repeat of single
 step trap on return from SIGTRAP handler

Clear the software event flag in the augmented SS to prevent immediate
repeat of single step trap on return from SIGTRAP handler if the trap
flag (TF) is set without an external debugger attached.

Following is a typical single-stepping flow for a user process:

1) The user process is prepared for single-stepping by setting
   RFLAGS.TF = 1.
2) When any instruction in user space completes, a #DB is triggered.
3) The kernel handles the #DB and returns to user space, invoking the
   SIGTRAP handler with RFLAGS.TF = 0.
4) After the SIGTRAP handler finishes, the user process performs a
   sigreturn syscall, restoring the original state, including
   RFLAGS.TF = 1.
5) Goto step 2.

According to the FRED specification:

A) Bit 17 in the augmented SS is designated as the software event
   flag, which is set to 1 for FRED event delivery of SYSCALL,
   SYSENTER, or INT n.
B) If bit 17 of the augmented SS is 1 and ERETU would result in
   RFLAGS.TF = 1, a single-step trap will be pending upon completion
   of ERETU.

In step 4) above, the software event flag is set upon the sigreturn
syscall, and its corresponding ERETU would restore RFLAGS.TF = 1.
This combination causes a pending single-step trap upon completion of
ERETU.  Therefore, another #DB is triggered before any user space
instruction is executed, which leads to an infinite loop in which the
SIGTRAP handler keeps being invoked on the same user space IP.

Fixes: 14619d912b65 ("x86/fred: FRED entry/exit and dispatch code")
Suggested-by: H. Peter Anvin (Intel) <hpa@zytor.com>
Signed-off-by: Xin Li (Intel) <xin@zytor.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Tested-by: Sohil Mehta <sohil.mehta@intel.com>
Cc:stable@vger.kernel.org
Link: https://lore.kernel.org/all/20250609084054.2083189-2-xin%40zytor.com
---
 arch/x86/include/asm/sighandling.h | 22 ++++++++++++++++++++++
 arch/x86/kernel/signal_32.c        |  4 ++++
 arch/x86/kernel/signal_64.c        |  4 ++++
 3 files changed, 30 insertions(+)

diff --git a/arch/x86/include/asm/sighandling.h b/arch/x86/include/asm/sighandling.h
index e770c4fc47f4..8727c7e21dd1 100644
--- a/arch/x86/include/asm/sighandling.h
+++ b/arch/x86/include/asm/sighandling.h
@@ -24,4 +24,26 @@ int ia32_setup_rt_frame(struct ksignal *ksig, struct pt_regs *regs);
 int x64_setup_rt_frame(struct ksignal *ksig, struct pt_regs *regs);
 int x32_setup_rt_frame(struct ksignal *ksig, struct pt_regs *regs);
 
+/*
+ * To prevent immediate repeat of single step trap on return from SIGTRAP
+ * handler if the trap flag (TF) is set without an external debugger attached,
+ * clear the software event flag in the augmented SS, ensuring no single-step
+ * trap is pending upon ERETU completion.
+ *
+ * Note, this function should be called in sigreturn() before the original
+ * state is restored to make sure the TF is read from the entry frame.
+ */
+static __always_inline void prevent_single_step_upon_eretu(struct pt_regs *regs)
+{
+	/*
+	 * If the trap flag (TF) is set, i.e., the sigreturn() SYSCALL instruction
+	 * is being single-stepped, do not clear the software event flag in the
+	 * augmented SS, thus a debugger won't skip over the following instruction.
+	 */
+#ifdef CONFIG_X86_FRED
+	if (!(regs->flags & X86_EFLAGS_TF))
+		regs->fred_ss.swevent = 0;
+#endif
+}
+
 #endif /* _ASM_X86_SIGHANDLING_H */
diff --git a/arch/x86/kernel/signal_32.c b/arch/x86/kernel/signal_32.c
index 98123ff10506..42bbc42bd350 100644
--- a/arch/x86/kernel/signal_32.c
+++ b/arch/x86/kernel/signal_32.c
@@ -152,6 +152,8 @@ SYSCALL32_DEFINE0(sigreturn)
 	struct sigframe_ia32 __user *frame = (struct sigframe_ia32 __user *)(regs->sp-8);
 	sigset_t set;
 
+	prevent_single_step_upon_eretu(regs);
+
 	if (!access_ok(frame, sizeof(*frame)))
 		goto badframe;
 	if (__get_user(set.sig[0], &frame->sc.oldmask)
@@ -175,6 +177,8 @@ SYSCALL32_DEFINE0(rt_sigreturn)
 	struct rt_sigframe_ia32 __user *frame;
 	sigset_t set;
 
+	prevent_single_step_upon_eretu(regs);
+
 	frame = (struct rt_sigframe_ia32 __user *)(regs->sp - 4);
 
 	if (!access_ok(frame, sizeof(*frame)))
diff --git a/arch/x86/kernel/signal_64.c b/arch/x86/kernel/signal_64.c
index ee9453891901..d483b585c6c6 100644
--- a/arch/x86/kernel/signal_64.c
+++ b/arch/x86/kernel/signal_64.c
@@ -250,6 +250,8 @@ SYSCALL_DEFINE0(rt_sigreturn)
 	sigset_t set;
 	unsigned long uc_flags;
 
+	prevent_single_step_upon_eretu(regs);
+
 	frame = (struct rt_sigframe __user *)(regs->sp - sizeof(long));
 	if (!access_ok(frame, sizeof(*frame)))
 		goto badframe;
@@ -366,6 +368,8 @@ COMPAT_SYSCALL_DEFINE0(x32_rt_sigreturn)
 	sigset_t set;
 	unsigned long uc_flags;
 
+	prevent_single_step_upon_eretu(regs);
+
 	frame = (struct rt_sigframe_x32 __user *)(regs->sp - 8);
 
 	if (!access_ok(frame, sizeof(*frame)))

From f287822688eeb44ae1cf6ac45701d965efc33218 Mon Sep 17 00:00:00 2001
From: "Xin Li (Intel)" <xin@zytor.com>
Date: Mon, 9 Jun 2025 01:40:54 -0700
Subject: [PATCH 0098/1334] selftests/x86: Add a test to detect infinite
 SIGTRAP handler loop
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When FRED is enabled, if the Trap Flag (TF) is set without an external
debugger attached, it can lead to an infinite loop in the SIGTRAP
handler.  To avoid this, the software event flag in the augmented SS
must be cleared, ensuring that no single-step trap remains pending when
ERETU completes.

This test checks for that specific scenario—verifying whether the kernel
correctly prevents an infinite SIGTRAP loop in this edge case when FRED
is enabled.

The test should _always_ pass with IDT event delivery, thus no need to
disable the test even when FRED is not enabled.

Signed-off-by: Xin Li (Intel) <xin@zytor.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Tested-by: Sohil Mehta <sohil.mehta@intel.com>
Cc:stable@vger.kernel.org
Link: https://lore.kernel.org/all/20250609084054.2083189-3-xin%40zytor.com
---
 tools/testing/selftests/x86/Makefile       |   2 +-
 tools/testing/selftests/x86/sigtrap_loop.c | 101 +++++++++++++++++++++
 2 files changed, 102 insertions(+), 1 deletion(-)
 create mode 100644 tools/testing/selftests/x86/sigtrap_loop.c

diff --git a/tools/testing/selftests/x86/Makefile b/tools/testing/selftests/x86/Makefile
index f703fcfe9f7c..83148875a12c 100644
--- a/tools/testing/selftests/x86/Makefile
+++ b/tools/testing/selftests/x86/Makefile
@@ -12,7 +12,7 @@ CAN_BUILD_WITH_NOPIE := $(shell ./check_cc.sh "$(CC)" trivial_program.c -no-pie)
 
 TARGETS_C_BOTHBITS := single_step_syscall sysret_ss_attrs syscall_nt test_mremap_vdso \
 			check_initial_reg_state sigreturn iopl ioperm \
-			test_vsyscall mov_ss_trap \
+			test_vsyscall mov_ss_trap sigtrap_loop \
 			syscall_arg_fault fsgsbase_restore sigaltstack
 TARGETS_C_BOTHBITS += nx_stack
 TARGETS_C_32BIT_ONLY := entry_from_vm86 test_syscall_vdso unwind_vdso \
diff --git a/tools/testing/selftests/x86/sigtrap_loop.c b/tools/testing/selftests/x86/sigtrap_loop.c
new file mode 100644
index 000000000000..9d065479e89f
--- /dev/null
+++ b/tools/testing/selftests/x86/sigtrap_loop.c
@@ -0,0 +1,101 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2025 Intel Corporation
+ */
+#define _GNU_SOURCE
+
+#include <err.h>
+#include <signal.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/ucontext.h>
+
+#ifdef __x86_64__
+# define REG_IP REG_RIP
+#else
+# define REG_IP REG_EIP
+#endif
+
+static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *), int flags)
+{
+	struct sigaction sa;
+
+	memset(&sa, 0, sizeof(sa));
+	sa.sa_sigaction = handler;
+	sa.sa_flags = SA_SIGINFO | flags;
+	sigemptyset(&sa.sa_mask);
+
+	if (sigaction(sig, &sa, 0))
+		err(1, "sigaction");
+
+	return;
+}
+
+static void sigtrap(int sig, siginfo_t *info, void *ctx_void)
+{
+	ucontext_t *ctx = (ucontext_t *)ctx_void;
+	static unsigned int loop_count_on_same_ip;
+	static unsigned long last_trap_ip;
+
+	if (last_trap_ip == ctx->uc_mcontext.gregs[REG_IP]) {
+		printf("\tTrapped at %016lx\n", last_trap_ip);
+
+		/*
+		 * If the same IP is hit more than 10 times in a row, it is
+		 * _considered_ an infinite loop.
+		 */
+		if (++loop_count_on_same_ip > 10) {
+			printf("[FAIL]\tDetected SIGTRAP infinite loop\n");
+			exit(1);
+		}
+
+		return;
+	}
+
+	loop_count_on_same_ip = 0;
+	last_trap_ip = ctx->uc_mcontext.gregs[REG_IP];
+	printf("\tTrapped at %016lx\n", last_trap_ip);
+}
+
+int main(int argc, char *argv[])
+{
+	sethandler(SIGTRAP, sigtrap, 0);
+
+	/*
+	 * Set the Trap Flag (TF) to single-step the test code, therefore to
+	 * trigger a SIGTRAP signal after each instruction until the TF is
+	 * cleared.
+	 *
+	 * Because the arithmetic flags are not significant here, the TF is
+	 * set by pushing 0x302 onto the stack and then popping it into the
+	 * flags register.
+	 *
+	 * Four instructions in the following asm code are executed with the
+	 * TF set, thus the SIGTRAP handler is expected to run four times.
+	 */
+	printf("[RUN]\tSIGTRAP infinite loop detection\n");
+	asm volatile(
+#ifdef __x86_64__
+		/*
+		 * Avoid clobbering the redzone
+		 *
+		 * Equivalent to "sub $128, %rsp", however -128 can be encoded
+		 * in a single byte immediate while 128 uses 4 bytes.
+		 */
+		"add $-128, %rsp\n\t"
+#endif
+		"push $0x302\n\t"
+		"popf\n\t"
+		"nop\n\t"
+		"nop\n\t"
+		"push $0x202\n\t"
+		"popf\n\t"
+#ifdef __x86_64__
+		"sub $-128, %rsp\n\t"
+#endif
+	);
+
+	printf("[OK]\tNo SIGTRAP infinite loop detected\n");
+	return 0;
+}

From e044b8a9545cd8265c7110c179aeec2624c16455 Mon Sep 17 00:00:00 2001
From: "Francesco Poli (wintermute)" <invernomuto@paranoici.org>
Date: Wed, 21 May 2025 23:14:39 +0200
Subject: [PATCH 0099/1334] cpupower: split unitdir from libdir in Makefile

Improve the installation procedure for the systemd service unit
'cpupower.service', to be more flexible. Some distros install libraries
to /usr/lib64/, but systemd service units have to be installed to
/usr/lib/systemd/system: as a consequence, the installation procedure
should not assume that systemd service units can be installed to
${libdir}/systemd/system ...
Define a dedicated variable ("unitdir") in the Makefile.

Link: https://lore.kernel.org/linux-pm/260b6d79-ab61-43b7-a0eb-813e257bc028@leemhuis.info/T/#m0601940ab439d5cbd288819d2af190ce59e810e6

Fixes: 9c70b779ad91 ("cpupower: add a systemd service to run cpupower")

Link: https://lore.kernel.org/r/20250521211656.65646-1-invernomuto@paranoici.org
Signed-off-by: Francesco Poli (wintermute) <invernomuto@paranoici.org>
Tested-by: Thorsten Leemhuis <linux@leemhuis.info>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
---
 tools/power/cpupower/Makefile | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/tools/power/cpupower/Makefile b/tools/power/cpupower/Makefile
index be8dfac14076..c43db1c41205 100644
--- a/tools/power/cpupower/Makefile
+++ b/tools/power/cpupower/Makefile
@@ -73,6 +73,7 @@ sbindir ?=	/usr/sbin
 mandir ?=	/usr/man
 libdir ?=	/usr/lib
 libexecdir ?=	/usr/libexec
+unitdir ?=	/usr/lib/systemd/system
 includedir ?=	/usr/include
 localedir ?=	/usr/share/locale
 docdir ?=       /usr/share/doc/packages/cpupower
@@ -309,9 +310,9 @@ install-tools: $(OUTPUT)cpupower
 	$(INSTALL_DATA) cpupower-service.conf '$(DESTDIR)${confdir}'
 	$(INSTALL) -d $(DESTDIR)${libexecdir}
 	$(INSTALL_PROGRAM) cpupower.sh '$(DESTDIR)${libexecdir}/cpupower'
-	$(INSTALL) -d $(DESTDIR)${libdir}/systemd/system
-	sed 's|___CDIR___|${confdir}|; s|___LDIR___|${libexecdir}|' cpupower.service.in > '$(DESTDIR)${libdir}/systemd/system/cpupower.service'
-	$(SETPERM_DATA) '$(DESTDIR)${libdir}/systemd/system/cpupower.service'
+	$(INSTALL) -d $(DESTDIR)${unitdir}
+	sed 's|___CDIR___|${confdir}|; s|___LDIR___|${libexecdir}|' cpupower.service.in > '$(DESTDIR)${unitdir}/cpupower.service'
+	$(SETPERM_DATA) '$(DESTDIR)${unitdir}/cpupower.service'
 
 install-man:
 	$(INSTALL_DATA) -D man/cpupower.1 $(DESTDIR)${mandir}/man1/cpupower.1
@@ -348,7 +349,7 @@ uninstall:
 	- rm -f $(DESTDIR)${bindir}/utils/cpupower
 	- rm -f $(DESTDIR)${confdir}cpupower-service.conf
 	- rm -f $(DESTDIR)${libexecdir}/cpupower
-	- rm -f $(DESTDIR)${libdir}/systemd/system/cpupower.service
+	- rm -f $(DESTDIR)${unitdir}/cpupower.service
 	- rm -f $(DESTDIR)${mandir}/man1/cpupower.1
 	- rm -f $(DESTDIR)${mandir}/man1/cpupower-frequency-set.1
 	- rm -f $(DESTDIR)${mandir}/man1/cpupower-frequency-info.1

From ea7caffedd011f7d40abe93a884ffbe46f122535 Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@nvidia.com>
Date: Tue, 8 Apr 2025 14:22:56 -0300
Subject: [PATCH 0100/1334] ARC: atomics: Implement arch_atomic64_cmpxchg using
 _relaxed

The core atomic code has a number of macros where it elaborates
architecture primitives into more functions. ARC uses
arch_atomic64_cmpxchg() as it's architecture primitive which disable alot
of the additional functions.

Instead provide arch_cmpxchg64_relaxed() as the primitive and rely on the
core macros to create arch_cmpxchg64().

The macros will also provide other functions, for instance,
try_cmpxchg64_release(), giving a more complete implementation.

Suggested-by: Mark Rutland <mark.rutland@arm.com>
Link: https://lore.kernel.org/r/Z0747n5bSep4_1VX@J2N7QTR9R3
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Vineet Gupta <vgupta@kernel.org>
---
 arch/arc/include/asm/atomic64-arcv2.h | 15 +++++----------
 1 file changed, 5 insertions(+), 10 deletions(-)

diff --git a/arch/arc/include/asm/atomic64-arcv2.h b/arch/arc/include/asm/atomic64-arcv2.h
index 9b5791b85471..73080a664369 100644
--- a/arch/arc/include/asm/atomic64-arcv2.h
+++ b/arch/arc/include/asm/atomic64-arcv2.h
@@ -137,12 +137,9 @@ ATOMIC64_OPS(xor, xor, xor)
 #undef ATOMIC64_OP_RETURN
 #undef ATOMIC64_OP
 
-static inline s64
-arch_atomic64_cmpxchg(atomic64_t *ptr, s64 expected, s64 new)
+static inline u64 __arch_cmpxchg64_relaxed(volatile void *ptr, u64 old, u64 new)
 {
-	s64 prev;
-
-	smp_mb();
+	u64 prev;
 
 	__asm__ __volatile__(
 	"1:	llockd  %0, [%1]	\n"
@@ -152,14 +149,12 @@ arch_atomic64_cmpxchg(atomic64_t *ptr, s64 expected, s64 new)
 	"	bnz     1b		\n"
 	"2:				\n"
 	: "=&r"(prev)
-	: "r"(ptr), "ir"(expected), "r"(new)
-	: "cc");	/* memory clobber comes from smp_mb() */
-
-	smp_mb();
+	: "r"(ptr), "ir"(old), "r"(new)
+	: "memory", "cc");
 
 	return prev;
 }
-#define arch_atomic64_cmpxchg arch_atomic64_cmpxchg
+#define arch_cmpxchg64_relaxed __arch_cmpxchg64_relaxed
 
 static inline s64 arch_atomic64_xchg(atomic64_t *ptr, s64 new)
 {

From 857f4517965b282234e12f6bca0c21ef10eec09b Mon Sep 17 00:00:00 2001
From: Yu-Chun Lin <eleanor15x@gmail.com>
Date: Thu, 10 Apr 2025 01:11:16 +0800
Subject: [PATCH 0101/1334] ARC: unwind: Use built-in sort swap to reduce code
 size and improve performance

The custom swap function used in sort() was identical to the default
built-in sort swap. Remove the custom swap function and passes NULL to
sort(), allowing it to use the default swap function.

This change reduces code size and improves performance, particularly when
CONFIG_MITIGATION_RETPOLINE is enabled. With RETPOLINE mitigation, indirect
function calls incur significant overhead, and using the default swap
function avoids this cost.

$ ./scripts/bloat-o-meter ./unwind.o.old ./unwind.o.new
add/remove: 0/1 grow/shrink: 0/1 up/down: 0/-22 (-22)
Function                                     old     new   delta
init_unwind_hdr.constprop                    544     540      -4
swap_eh_frame_hdr_table_entries               18       -     -18
Total: Before=4410, After=4388, chg -0.50%

Signed-off-by: Yu-Chun Lin <eleanor15x@gmail.com>
Signed-off-by: Vineet Gupta <vgupta@kernel.org>
---
 arch/arc/kernel/unwind.c | 11 +----------
 1 file changed, 1 insertion(+), 10 deletions(-)

diff --git a/arch/arc/kernel/unwind.c b/arch/arc/kernel/unwind.c
index d8969dab12d4..789cfb9ea14e 100644
--- a/arch/arc/kernel/unwind.c
+++ b/arch/arc/kernel/unwind.c
@@ -241,15 +241,6 @@ static int cmp_eh_frame_hdr_table_entries(const void *p1, const void *p2)
 	return (e1->start > e2->start) - (e1->start < e2->start);
 }
 
-static void swap_eh_frame_hdr_table_entries(void *p1, void *p2, int size)
-{
-	struct eh_frame_hdr_table_entry *e1 = p1;
-	struct eh_frame_hdr_table_entry *e2 = p2;
-
-	swap(e1->start, e2->start);
-	swap(e1->fde, e2->fde);
-}
-
 static void init_unwind_hdr(struct unwind_table *table,
 			    void *(*alloc) (unsigned long))
 {
@@ -345,7 +336,7 @@ static void init_unwind_hdr(struct unwind_table *table,
 	sort(header->table,
 	     n,
 	     sizeof(*header->table),
-	     cmp_eh_frame_hdr_table_entries, swap_eh_frame_hdr_table_entries);
+	     cmp_eh_frame_hdr_table_entries, NULL);
 
 	table->hdrsz = hdrSize;
 	smp_wmb();

From 2cb74be378675c860af0fcaf1ec2801beebdf028 Mon Sep 17 00:00:00 2001
From: Thomas Huth <thuth@redhat.com>
Date: Fri, 14 Mar 2025 08:09:35 +0100
Subject: [PATCH 0102/1334] ARC: Replace __ASSEMBLY__ with __ASSEMBLER__ in
 uapi headers

__ASSEMBLY__ is only defined by the Makefile of the kernel, so
this is not really useful for uapi headers (unless the userspace
Makefile defines it, too). Let's switch to __ASSEMBLER__ which
gets set automatically by the compiler when compiling assembly
code.

Cc: linux-snps-arc@lists.infradead.org
Signed-off-by: Thomas Huth <thuth@redhat.com>
Signed-off-by: Vineet Gupta <vgupta@kernel.org>
---
 arch/arc/include/uapi/asm/ptrace.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/arc/include/uapi/asm/ptrace.h b/arch/arc/include/uapi/asm/ptrace.h
index 2a6eff57f6dd..3ae832db278c 100644
--- a/arch/arc/include/uapi/asm/ptrace.h
+++ b/arch/arc/include/uapi/asm/ptrace.h
@@ -14,7 +14,7 @@
 
 #define PTRACE_GET_THREAD_AREA	25
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 /*
  * Userspace ABI: Register state needed by
  *  -ptrace (gdbserver)
@@ -53,6 +53,6 @@ struct user_regs_arcv2 {
 	unsigned long r30, r58, r59;
 };
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
 #endif /* _UAPI__ASM_ARC_PTRACE_H */

From 179e949719fe81219a3e23f1e716ac2d02eea845 Mon Sep 17 00:00:00 2001
From: Thomas Huth <thuth@redhat.com>
Date: Fri, 14 Mar 2025 08:09:36 +0100
Subject: [PATCH 0103/1334] ARC: Replace __ASSEMBLY__ with __ASSEMBLER__ in the
 non-uapi headers

While the GCC and Clang compilers already define __ASSEMBLER__
automatically when compiling assembly code, __ASSEMBLY__ is a
macro that only gets defined by the Makefiles in the kernel.
This can be very confusing when switching between userspace
and kernelspace coding, or when dealing with uapi headers that
rather should use __ASSEMBLER__ instead. So let's standardize on
the __ASSEMBLER__ macro that is provided by the compilers now.

This is a completely mechanical patch (done with a simple "sed -i"
statement).

Cc: linux-snps-arc@lists.infradead.org
Signed-off-by: Thomas Huth <thuth@redhat.com>
Signed-off-by: Vineet Gupta <vgupta@kernel.org>
---
 arch/arc/include/asm/arcregs.h            | 2 +-
 arch/arc/include/asm/atomic.h             | 4 ++--
 arch/arc/include/asm/bitops.h             | 4 ++--
 arch/arc/include/asm/bug.h                | 4 ++--
 arch/arc/include/asm/cache.h              | 4 ++--
 arch/arc/include/asm/current.h            | 4 ++--
 arch/arc/include/asm/dsp-impl.h           | 2 +-
 arch/arc/include/asm/dsp.h                | 4 ++--
 arch/arc/include/asm/dwarf.h              | 4 ++--
 arch/arc/include/asm/entry.h              | 4 ++--
 arch/arc/include/asm/irqflags-arcv2.h     | 4 ++--
 arch/arc/include/asm/irqflags-compact.h   | 4 ++--
 arch/arc/include/asm/jump_label.h         | 4 ++--
 arch/arc/include/asm/linkage.h            | 6 +++---
 arch/arc/include/asm/mmu-arcv2.h          | 4 ++--
 arch/arc/include/asm/mmu.h                | 2 +-
 arch/arc/include/asm/page.h               | 4 ++--
 arch/arc/include/asm/pgtable-bits-arcv2.h | 4 ++--
 arch/arc/include/asm/pgtable-levels.h     | 4 ++--
 arch/arc/include/asm/pgtable.h            | 4 ++--
 arch/arc/include/asm/processor.h          | 4 ++--
 arch/arc/include/asm/ptrace.h             | 4 ++--
 arch/arc/include/asm/switch_to.h          | 2 +-
 arch/arc/include/asm/thread_info.h        | 4 ++--
 24 files changed, 45 insertions(+), 45 deletions(-)

diff --git a/arch/arc/include/asm/arcregs.h b/arch/arc/include/asm/arcregs.h
index 005d9e4d187a..a31bbf5c8bbc 100644
--- a/arch/arc/include/asm/arcregs.h
+++ b/arch/arc/include/asm/arcregs.h
@@ -144,7 +144,7 @@
 #define ARC_AUX_AGU_MOD2	0x5E2
 #define ARC_AUX_AGU_MOD3	0x5E3
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <soc/arc/arc_aux.h>
 
diff --git a/arch/arc/include/asm/atomic.h b/arch/arc/include/asm/atomic.h
index 592d7fffc223..e615c42b93ba 100644
--- a/arch/arc/include/asm/atomic.h
+++ b/arch/arc/include/asm/atomic.h
@@ -6,7 +6,7 @@
 #ifndef _ASM_ARC_ATOMIC_H
 #define _ASM_ARC_ATOMIC_H
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/types.h>
 #include <linux/compiler.h>
@@ -31,6 +31,6 @@
 #include <asm/atomic64-arcv2.h>
 #endif
 
-#endif	/* !__ASSEMBLY__ */
+#endif	/* !__ASSEMBLER__ */
 
 #endif
diff --git a/arch/arc/include/asm/bitops.h b/arch/arc/include/asm/bitops.h
index f5a936496f06..5340c2871392 100644
--- a/arch/arc/include/asm/bitops.h
+++ b/arch/arc/include/asm/bitops.h
@@ -10,7 +10,7 @@
 #error only <linux/bitops.h> can be included directly
 #endif
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/types.h>
 #include <linux/compiler.h>
@@ -192,6 +192,6 @@ static inline __attribute__ ((const)) unsigned long __ffs(unsigned long x)
 #include <asm-generic/bitops/le.h>
 #include <asm-generic/bitops/ext2-atomic-setbit.h>
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
 #endif
diff --git a/arch/arc/include/asm/bug.h b/arch/arc/include/asm/bug.h
index 4c453ba96c51..171c16021f70 100644
--- a/arch/arc/include/asm/bug.h
+++ b/arch/arc/include/asm/bug.h
@@ -6,7 +6,7 @@
 #ifndef _ASM_ARC_BUG_H
 #define _ASM_ARC_BUG_H
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <asm/ptrace.h>
 
@@ -29,6 +29,6 @@ void die(const char *str, struct pt_regs *regs, unsigned long address);
 
 #include <asm-generic/bug.h>
 
-#endif	/* !__ASSEMBLY__ */
+#endif	/* !__ASSEMBLER__ */
 
 #endif
diff --git a/arch/arc/include/asm/cache.h b/arch/arc/include/asm/cache.h
index f0f1fc5d62b6..040a97f4dd82 100644
--- a/arch/arc/include/asm/cache.h
+++ b/arch/arc/include/asm/cache.h
@@ -23,7 +23,7 @@
  */
 #define ARC_UNCACHED_ADDR_SPACE	0xc0000000
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/build_bug.h>
 
@@ -65,7 +65,7 @@
 extern int ioc_enable;
 extern unsigned long perip_base, perip_end;
 
-#endif	/* !__ASSEMBLY__ */
+#endif	/* !__ASSEMBLER__ */
 
 /* Instruction cache related Auxiliary registers */
 #define ARC_REG_IC_BCR		0x77	/* Build Config reg */
diff --git a/arch/arc/include/asm/current.h b/arch/arc/include/asm/current.h
index 06be89f6f2f0..03ffd005f3fa 100644
--- a/arch/arc/include/asm/current.h
+++ b/arch/arc/include/asm/current.h
@@ -9,7 +9,7 @@
 #ifndef _ASM_ARC_CURRENT_H
 #define _ASM_ARC_CURRENT_H
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #ifdef CONFIG_ARC_CURR_IN_REG
 
@@ -20,6 +20,6 @@ register struct task_struct *curr_arc asm("gp");
 #include <asm-generic/current.h>
 #endif /* ! CONFIG_ARC_CURR_IN_REG */
 
-#endif /* ! __ASSEMBLY__ */
+#endif /* ! __ASSEMBLER__ */
 
 #endif /* _ASM_ARC_CURRENT_H */
diff --git a/arch/arc/include/asm/dsp-impl.h b/arch/arc/include/asm/dsp-impl.h
index cd5636dfeb6f..fd5fdaad90c1 100644
--- a/arch/arc/include/asm/dsp-impl.h
+++ b/arch/arc/include/asm/dsp-impl.h
@@ -11,7 +11,7 @@
 
 #define DSP_CTRL_DISABLED_ALL		0
 
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 
 /* clobbers r5 register */
 .macro DSP_EARLY_INIT
diff --git a/arch/arc/include/asm/dsp.h b/arch/arc/include/asm/dsp.h
index f496dbc4640b..eeaaf4e4eabd 100644
--- a/arch/arc/include/asm/dsp.h
+++ b/arch/arc/include/asm/dsp.h
@@ -7,7 +7,7 @@
 #ifndef __ASM_ARC_DSP_H
 #define __ASM_ARC_DSP_H
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 /*
  * DSP-related saved registers - need to be saved only when you are
@@ -24,6 +24,6 @@ struct dsp_callee_regs {
 #endif
 };
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
 #endif /* __ASM_ARC_DSP_H */
diff --git a/arch/arc/include/asm/dwarf.h b/arch/arc/include/asm/dwarf.h
index a0d5ebe1bc3f..1524c5cf8b59 100644
--- a/arch/arc/include/asm/dwarf.h
+++ b/arch/arc/include/asm/dwarf.h
@@ -6,7 +6,7 @@
 #ifndef _ASM_ARC_DWARF_H
 #define _ASM_ARC_DWARF_H
 
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 
 #ifdef ARC_DW2_UNWIND_AS_CFI
 
@@ -38,6 +38,6 @@
 
 #endif	/* !ARC_DW2_UNWIND_AS_CFI */
 
-#endif	/* __ASSEMBLY__ */
+#endif	/* __ASSEMBLER__ */
 
 #endif	/* _ASM_ARC_DWARF_H */
diff --git a/arch/arc/include/asm/entry.h b/arch/arc/include/asm/entry.h
index 38c35722cebf..f453af251a1a 100644
--- a/arch/arc/include/asm/entry.h
+++ b/arch/arc/include/asm/entry.h
@@ -13,7 +13,7 @@
 #include <asm/processor.h>	/* For VMALLOC_START */
 #include <asm/mmu.h>
 
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 
 #ifdef CONFIG_ISA_ARCOMPACT
 #include <asm/entry-compact.h>	/* ISA specific bits */
@@ -146,7 +146,7 @@
 
 #endif	/* CONFIG_ARC_CURR_IN_REG */
 
-#else	/* !__ASSEMBLY__ */
+#else	/* !__ASSEMBLER__ */
 
 extern void do_signal(struct pt_regs *);
 extern void do_notify_resume(struct pt_regs *);
diff --git a/arch/arc/include/asm/irqflags-arcv2.h b/arch/arc/include/asm/irqflags-arcv2.h
index fb3c21f1a238..30aea562f8aa 100644
--- a/arch/arc/include/asm/irqflags-arcv2.h
+++ b/arch/arc/include/asm/irqflags-arcv2.h
@@ -50,7 +50,7 @@
 #define ISA_INIT_STATUS_BITS	(STATUS_IE_MASK | __AD_ENB | \
 					(ARCV2_IRQ_DEF_PRIO << 1))
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 /*
  * Save IRQ state and disable IRQs
@@ -170,6 +170,6 @@ static inline void arc_softirq_clear(int irq)
 	seti
 .endm
 
-#endif	/* __ASSEMBLY__ */
+#endif	/* __ASSEMBLER__ */
 
 #endif
diff --git a/arch/arc/include/asm/irqflags-compact.h b/arch/arc/include/asm/irqflags-compact.h
index 936a2f21f315..85c2f6bcde0c 100644
--- a/arch/arc/include/asm/irqflags-compact.h
+++ b/arch/arc/include/asm/irqflags-compact.h
@@ -40,7 +40,7 @@
 
 #define ISA_INIT_STATUS_BITS	STATUS_IE_MASK
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 /******************************************************************
  * IRQ Control Macros
@@ -196,6 +196,6 @@ static inline int arch_irqs_disabled(void)
 	flag	\scratch
 .endm
 
-#endif	/* __ASSEMBLY__ */
+#endif	/* __ASSEMBLER__ */
 
 #endif
diff --git a/arch/arc/include/asm/jump_label.h b/arch/arc/include/asm/jump_label.h
index a339223d9e05..66ead75784d9 100644
--- a/arch/arc/include/asm/jump_label.h
+++ b/arch/arc/include/asm/jump_label.h
@@ -2,7 +2,7 @@
 #ifndef _ASM_ARC_JUMP_LABEL_H
 #define _ASM_ARC_JUMP_LABEL_H
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/stringify.h>
 #include <linux/types.h>
@@ -68,5 +68,5 @@ struct jump_entry {
 	jump_label_t key;
 };
 
-#endif  /* __ASSEMBLY__ */
+#endif  /* __ASSEMBLER__ */
 #endif
diff --git a/arch/arc/include/asm/linkage.h b/arch/arc/include/asm/linkage.h
index 8a3fb71e9cfa..ba3cb65b5eaa 100644
--- a/arch/arc/include/asm/linkage.h
+++ b/arch/arc/include/asm/linkage.h
@@ -12,7 +12,7 @@
 #define __ALIGN		.align 4
 #define __ALIGN_STR	__stringify(__ALIGN)
 
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 
 .macro ST2 e, o, off
 #ifdef CONFIG_ARC_HAS_LL64
@@ -61,7 +61,7 @@
 	CFI_ENDPROC ASM_NL	\
 	.size name, .-name
 
-#else	/* !__ASSEMBLY__ */
+#else	/* !__ASSEMBLER__ */
 
 #ifdef CONFIG_ARC_HAS_ICCM
 #define __arcfp_code __section(".text.arcfp")
@@ -75,6 +75,6 @@
 #define __arcfp_data __section(".data")
 #endif
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif
diff --git a/arch/arc/include/asm/mmu-arcv2.h b/arch/arc/include/asm/mmu-arcv2.h
index 41412642f279..5e5482026ac9 100644
--- a/arch/arc/include/asm/mmu-arcv2.h
+++ b/arch/arc/include/asm/mmu-arcv2.h
@@ -69,7 +69,7 @@
 
 #define PTE_BITS_NON_RWX_IN_PD1	(PAGE_MASK_PHYS | _PAGE_CACHEABLE)
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 struct mm_struct;
 extern int pae40_exist_but_not_enab(void);
@@ -100,6 +100,6 @@ static inline void mmu_setup_pgd(struct mm_struct *mm, void *pgd)
 	sr \reg, [ARC_REG_PID]
 .endm
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
 #endif
diff --git a/arch/arc/include/asm/mmu.h b/arch/arc/include/asm/mmu.h
index 4ae2db59d494..e3b35ceab582 100644
--- a/arch/arc/include/asm/mmu.h
+++ b/arch/arc/include/asm/mmu.h
@@ -6,7 +6,7 @@
 #ifndef _ASM_ARC_MMU_H
 #define _ASM_ARC_MMU_H
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/threads.h>	/* NR_CPUS */
 
diff --git a/arch/arc/include/asm/page.h b/arch/arc/include/asm/page.h
index def0dfb95b43..9720fe6b2c24 100644
--- a/arch/arc/include/asm/page.h
+++ b/arch/arc/include/asm/page.h
@@ -19,7 +19,7 @@
 
 #endif /* CONFIG_ARC_HAS_PAE40 */
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #define clear_page(paddr)		memset((paddr), 0, PAGE_SIZE)
 #define copy_user_page(to, from, vaddr, pg)	copy_page(to, from)
@@ -136,6 +136,6 @@ static inline unsigned long virt_to_pfn(const void *kaddr)
 #include <asm-generic/memory_model.h>   /* page_to_pfn, pfn_to_page */
 #include <asm-generic/getorder.h>
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
 #endif
diff --git a/arch/arc/include/asm/pgtable-bits-arcv2.h b/arch/arc/include/asm/pgtable-bits-arcv2.h
index 8ebec1b21d24..a8fdb4fe1fbd 100644
--- a/arch/arc/include/asm/pgtable-bits-arcv2.h
+++ b/arch/arc/include/asm/pgtable-bits-arcv2.h
@@ -75,7 +75,7 @@
  *     This is to enable COW mechanism
  */
 	/* xwr */
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #define pte_write(pte)		(pte_val(pte) & _PAGE_WRITE)
 #define pte_dirty(pte)		(pte_val(pte) & _PAGE_DIRTY)
@@ -142,6 +142,6 @@ PTE_BIT_FUNC(swp_clear_exclusive, &= ~(_PAGE_SWP_EXCLUSIVE));
 #include <asm/hugepage.h>
 #endif
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif
diff --git a/arch/arc/include/asm/pgtable-levels.h b/arch/arc/include/asm/pgtable-levels.h
index d1ce4b0f1071..c8f9273372c0 100644
--- a/arch/arc/include/asm/pgtable-levels.h
+++ b/arch/arc/include/asm/pgtable-levels.h
@@ -85,7 +85,7 @@
 
 #define PTRS_PER_PTE		BIT(PMD_SHIFT - PAGE_SHIFT)
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #if CONFIG_PGTABLE_LEVELS > 3
 #include <asm-generic/pgtable-nop4d.h>
@@ -181,6 +181,6 @@
 #define pmd_leaf(x)		(pmd_val(x) & _PAGE_HW_SZ)
 #endif
 
-#endif	/* !__ASSEMBLY__ */
+#endif	/* !__ASSEMBLER__ */
 
 #endif
diff --git a/arch/arc/include/asm/pgtable.h b/arch/arc/include/asm/pgtable.h
index 4cf45a99fd79..bd580e2b62d7 100644
--- a/arch/arc/include/asm/pgtable.h
+++ b/arch/arc/include/asm/pgtable.h
@@ -19,7 +19,7 @@
  */
 #define	USER_PTRS_PER_PGD	(TASK_SIZE / PGDIR_SIZE)
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 extern char empty_zero_page[PAGE_SIZE];
 #define ZERO_PAGE(vaddr)	(virt_to_page(empty_zero_page))
@@ -29,6 +29,6 @@ extern pgd_t swapper_pg_dir[] __aligned(PAGE_SIZE);
 /* to cope with aliasing VIPT cache */
 #define HAVE_ARCH_UNMAPPED_AREA
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif
diff --git a/arch/arc/include/asm/processor.h b/arch/arc/include/asm/processor.h
index d606658e2fe7..7f7901ac6643 100644
--- a/arch/arc/include/asm/processor.h
+++ b/arch/arc/include/asm/processor.h
@@ -11,7 +11,7 @@
 #ifndef __ASM_ARC_PROCESSOR_H
 #define __ASM_ARC_PROCESSOR_H
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <asm/ptrace.h>
 #include <asm/dsp.h>
@@ -66,7 +66,7 @@ extern void start_thread(struct pt_regs * regs, unsigned long pc,
 
 extern unsigned int __get_wchan(struct task_struct *p);
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
 /*
  * Default System Memory Map on ARC
diff --git a/arch/arc/include/asm/ptrace.h b/arch/arc/include/asm/ptrace.h
index cf79df0b2570..f6c052af8f4d 100644
--- a/arch/arc/include/asm/ptrace.h
+++ b/arch/arc/include/asm/ptrace.h
@@ -10,7 +10,7 @@
 #include <uapi/asm/ptrace.h>
 #include <linux/compiler.h>
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 typedef union {
 	struct {
@@ -172,6 +172,6 @@ static inline unsigned long regs_get_register(struct pt_regs *regs,
 extern int syscall_trace_enter(struct pt_regs *);
 extern void syscall_trace_exit(struct pt_regs *);
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
 #endif /* __ASM_PTRACE_H */
diff --git a/arch/arc/include/asm/switch_to.h b/arch/arc/include/asm/switch_to.h
index 1f85de8288b1..5806106a65f9 100644
--- a/arch/arc/include/asm/switch_to.h
+++ b/arch/arc/include/asm/switch_to.h
@@ -6,7 +6,7 @@
 #ifndef _ASM_ARC_SWITCH_TO_H
 #define _ASM_ARC_SWITCH_TO_H
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/sched.h>
 #include <asm/dsp-impl.h>
diff --git a/arch/arc/include/asm/thread_info.h b/arch/arc/include/asm/thread_info.h
index 12daaf3a61ea..255d2c774219 100644
--- a/arch/arc/include/asm/thread_info.h
+++ b/arch/arc/include/asm/thread_info.h
@@ -24,7 +24,7 @@
 #define THREAD_SIZE     (PAGE_SIZE << THREAD_SIZE_ORDER)
 #define THREAD_SHIFT	(PAGE_SHIFT << THREAD_SIZE_ORDER)
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/thread_info.h>
 
@@ -62,7 +62,7 @@ static inline __attribute_const__ struct thread_info *current_thread_info(void)
 	return (struct thread_info *)(sp & ~(THREAD_SIZE - 1));
 }
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
 /*
  * thread information flags

From 87b42c114cdda76c8ad3002f2096699ad5146cb3 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Wed, 28 May 2025 11:11:41 +0300
Subject: [PATCH 0104/1334] cxl: fix return value in
 cxlctl_validate_set_features()

The cxlctl_validate_set_features() function is type bool.  It's supposed
to return true for valid requests and false for invalid.  However, this
error path returns ERR_PTR(-EINVAL) which is true when it was intended to
return false.

The incorrect return will result in kernel failing to prevent a
incorrect op_size passed in from userspace to be detected.

[ dj: Add user impact to commit log ]

Fixes: f76e0bbc8bc3 ("cxl: Update prototype of function get_support_feature_info()")
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Reviewed-by: Ira Weiny <ira.weiny@intel.com>
Link: https://patch.msgid.link/aDbFPSCujpJLY1if@stanley.mountain
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
---
 drivers/cxl/core/features.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/cxl/core/features.c b/drivers/cxl/core/features.c
index 6f2eae1eb126..7c750599ea69 100644
--- a/drivers/cxl/core/features.c
+++ b/drivers/cxl/core/features.c
@@ -544,7 +544,7 @@ static bool cxlctl_validate_set_features(struct cxl_features_state *cxlfs,
 	u32 flags;
 
 	if (rpc_in->op_size < sizeof(uuid_t))
-		return ERR_PTR(-EINVAL);
+		return false;
 
 	feat = cxl_feature_info(cxlfs, &rpc_in->set_feat_in.uuid);
 	if (IS_ERR(feat))

From 5d319f75ccf7f0927425a7545aa1a22b3eedc189 Mon Sep 17 00:00:00 2001
From: Rob Clark <robdclark@chromium.org>
Date: Wed, 14 May 2025 09:33:32 -0700
Subject: [PATCH 0105/1334] drm/msm: Fix a fence leak in submit error path

In error paths, we could unref the submit without calling
drm_sched_entity_push_job(), so msm_job_free() will never get
called.  Since drm_sched_job_cleanup() will NULL out the
s_fence, we can use that to detect this case.

Signed-off-by: Rob Clark <robdclark@chromium.org>
Patchwork: https://patchwork.freedesktop.org/patch/653584/
Signed-off-by: Rob Clark <robin.clark@oss.qualcomm.com>
---
 drivers/gpu/drm/msm/msm_gem_submit.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c
index 3e9aa2cc38ef..b2aeaecaa39b 100644
--- a/drivers/gpu/drm/msm/msm_gem_submit.c
+++ b/drivers/gpu/drm/msm/msm_gem_submit.c
@@ -85,6 +85,15 @@ void __msm_gem_submit_destroy(struct kref *kref)
 			container_of(kref, struct msm_gem_submit, ref);
 	unsigned i;
 
+	/*
+	 * In error paths, we could unref the submit without calling
+	 * drm_sched_entity_push_job(), so msm_job_free() will never
+	 * get called.  Since drm_sched_job_cleanup() will NULL out
+	 * s_fence, we can use that to detect this case.
+	 */
+	if (submit->base.s_fence)
+		drm_sched_job_cleanup(&submit->base);
+
 	if (submit->fence_id) {
 		spin_lock(&submit->queue->idr_lock);
 		idr_remove(&submit->queue->fence_idr, submit->fence_id);

From f681c2aa8676a890eacc84044717ab0fd26e058f Mon Sep 17 00:00:00 2001
From: Rob Clark <robdclark@chromium.org>
Date: Wed, 14 May 2025 09:33:33 -0700
Subject: [PATCH 0106/1334] drm/msm: Fix another leak in the submit error path

put_unused_fd() doesn't free the installed file, if we've already done
fd_install().  So we need to also free the sync_file.

Signed-off-by: Rob Clark <robdclark@chromium.org>
Patchwork: https://patchwork.freedesktop.org/patch/653583/
Signed-off-by: Rob Clark <robin.clark@oss.qualcomm.com>
---
 drivers/gpu/drm/msm/msm_gem_submit.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c
index b2aeaecaa39b..d4f71bb54e84 100644
--- a/drivers/gpu/drm/msm/msm_gem_submit.c
+++ b/drivers/gpu/drm/msm/msm_gem_submit.c
@@ -658,6 +658,7 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data,
 	struct msm_ringbuffer *ring;
 	struct msm_submit_post_dep *post_deps = NULL;
 	struct drm_syncobj **syncobjs_to_reset = NULL;
+	struct sync_file *sync_file = NULL;
 	int out_fence_fd = -1;
 	unsigned i;
 	int ret;
@@ -867,7 +868,7 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data,
 	}
 
 	if (ret == 0 && args->flags & MSM_SUBMIT_FENCE_FD_OUT) {
-		struct sync_file *sync_file = sync_file_create(submit->user_fence);
+		sync_file = sync_file_create(submit->user_fence);
 		if (!sync_file) {
 			ret = -ENOMEM;
 		} else {
@@ -901,8 +902,11 @@ out:
 out_unlock:
 	mutex_unlock(&queue->lock);
 out_post_unlock:
-	if (ret && (out_fence_fd >= 0))
+	if (ret && (out_fence_fd >= 0)) {
 		put_unused_fd(out_fence_fd);
+		if (sync_file)
+			fput(sync_file->file);
+	}
 
 	if (!IS_ERR_OR_NULL(submit)) {
 		msm_gem_submit_put(submit);

From 0c5fea1eb0dc234cd321bcd19a6bd0f51273b4c6 Mon Sep 17 00:00:00 2001
From: Connor Abbott <cwabbott0@gmail.com>
Date: Tue, 20 May 2025 15:08:57 -0400
Subject: [PATCH 0107/1334] drm/msm: Don't use a worker to capture fault
 devcoredump

Now that we use a threaded IRQ, it should be safe to do this in the
fault handler.

We can also remove fault_info from struct msm_gpu and just pass it
directly.

Signed-off-by: Connor Abbott <cwabbott0@gmail.com>
Patchwork: https://patchwork.freedesktop.org/patch/654889/
Signed-off-by: Rob Clark <robin.clark@oss.qualcomm.com>
---
 drivers/gpu/drm/msm/adreno/adreno_gpu.c | 22 ++++++++--------------
 drivers/gpu/drm/msm/msm_gpu.c           | 20 +++++++++-----------
 drivers/gpu/drm/msm/msm_gpu.h           |  8 ++------
 3 files changed, 19 insertions(+), 31 deletions(-)

diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
index 2348ffb35f7e..5ebd5a6ea143 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
@@ -270,14 +270,6 @@ int adreno_fault_handler(struct msm_gpu *gpu, unsigned long iova, int flags,
 	const char *type = "UNKNOWN";
 	bool do_devcoredump = info && !READ_ONCE(gpu->crashstate);
 
-	/*
-	 * If we aren't going to be resuming later from fault_worker, then do
-	 * it now.
-	 */
-	if (!do_devcoredump) {
-		gpu->aspace->mmu->funcs->resume_translation(gpu->aspace->mmu);
-	}
-
 	/*
 	 * Print a default message if we couldn't get the data from the
 	 * adreno-smmu-priv
@@ -304,16 +296,18 @@ int adreno_fault_handler(struct msm_gpu *gpu, unsigned long iova, int flags,
 			scratch[0], scratch[1], scratch[2], scratch[3]);
 
 	if (do_devcoredump) {
+		struct msm_gpu_fault_info fault_info = {};
+
 		/* Turn off the hangcheck timer to keep it from bothering us */
 		timer_delete(&gpu->hangcheck_timer);
 
-		gpu->fault_info.ttbr0 = info->ttbr0;
-		gpu->fault_info.iova  = iova;
-		gpu->fault_info.flags = flags;
-		gpu->fault_info.type  = type;
-		gpu->fault_info.block = block;
+		fault_info.ttbr0 = info->ttbr0;
+		fault_info.iova  = iova;
+		fault_info.flags = flags;
+		fault_info.type  = type;
+		fault_info.block = block;
 
-		kthread_queue_work(gpu->worker, &gpu->fault_work);
+		msm_gpu_fault_crashstate_capture(gpu, &fault_info);
 	}
 
 	return 0;
diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c
index c380d9d9f5af..457f019d507e 100644
--- a/drivers/gpu/drm/msm/msm_gpu.c
+++ b/drivers/gpu/drm/msm/msm_gpu.c
@@ -257,7 +257,8 @@ out:
 }
 
 static void msm_gpu_crashstate_capture(struct msm_gpu *gpu,
-		struct msm_gem_submit *submit, char *comm, char *cmd)
+		struct msm_gem_submit *submit, struct msm_gpu_fault_info *fault_info,
+		char *comm, char *cmd)
 {
 	struct msm_gpu_state *state;
 
@@ -276,7 +277,8 @@ static void msm_gpu_crashstate_capture(struct msm_gpu *gpu,
 	/* Fill in the additional crash state information */
 	state->comm = kstrdup(comm, GFP_KERNEL);
 	state->cmd = kstrdup(cmd, GFP_KERNEL);
-	state->fault_info = gpu->fault_info;
+	if (fault_info)
+		state->fault_info = *fault_info;
 
 	if (submit) {
 		int i;
@@ -308,7 +310,8 @@ static void msm_gpu_crashstate_capture(struct msm_gpu *gpu,
 }
 #else
 static void msm_gpu_crashstate_capture(struct msm_gpu *gpu,
-		struct msm_gem_submit *submit, char *comm, char *cmd)
+		struct msm_gem_submit *submit, struct msm_gpu_fault_info *fault_info,
+		char *comm, char *cmd)
 {
 }
 #endif
@@ -405,7 +408,7 @@ static void recover_worker(struct kthread_work *work)
 
 	/* Record the crash state */
 	pm_runtime_get_sync(&gpu->pdev->dev);
-	msm_gpu_crashstate_capture(gpu, submit, comm, cmd);
+	msm_gpu_crashstate_capture(gpu, submit, NULL, comm, cmd);
 
 	kfree(cmd);
 	kfree(comm);
@@ -459,9 +462,8 @@ out_unlock:
 	msm_gpu_retire(gpu);
 }
 
-static void fault_worker(struct kthread_work *work)
+void msm_gpu_fault_crashstate_capture(struct msm_gpu *gpu, struct msm_gpu_fault_info *fault_info)
 {
-	struct msm_gpu *gpu = container_of(work, struct msm_gpu, fault_work);
 	struct msm_gem_submit *submit;
 	struct msm_ringbuffer *cur_ring = gpu->funcs->active_ring(gpu);
 	char *comm = NULL, *cmd = NULL;
@@ -484,16 +486,13 @@ static void fault_worker(struct kthread_work *work)
 
 	/* Record the crash state */
 	pm_runtime_get_sync(&gpu->pdev->dev);
-	msm_gpu_crashstate_capture(gpu, submit, comm, cmd);
+	msm_gpu_crashstate_capture(gpu, submit, fault_info, comm, cmd);
 	pm_runtime_put_sync(&gpu->pdev->dev);
 
 	kfree(cmd);
 	kfree(comm);
 
 resume_smmu:
-	memset(&gpu->fault_info, 0, sizeof(gpu->fault_info));
-	gpu->aspace->mmu->funcs->resume_translation(gpu->aspace->mmu);
-
 	mutex_unlock(&gpu->lock);
 }
 
@@ -882,7 +881,6 @@ int msm_gpu_init(struct drm_device *drm, struct platform_device *pdev,
 	init_waitqueue_head(&gpu->retire_event);
 	kthread_init_work(&gpu->retire_work, retire_worker);
 	kthread_init_work(&gpu->recover_work, recover_worker);
-	kthread_init_work(&gpu->fault_work, fault_worker);
 
 	priv->hangcheck_period = DRM_MSM_HANGCHECK_DEFAULT_PERIOD;
 
diff --git a/drivers/gpu/drm/msm/msm_gpu.h b/drivers/gpu/drm/msm/msm_gpu.h
index e25009150579..bed0692f5adb 100644
--- a/drivers/gpu/drm/msm/msm_gpu.h
+++ b/drivers/gpu/drm/msm/msm_gpu.h
@@ -253,12 +253,6 @@ struct msm_gpu {
 #define DRM_MSM_HANGCHECK_PROGRESS_RETRIES 3
 	struct timer_list hangcheck_timer;
 
-	/* Fault info for most recent iova fault: */
-	struct msm_gpu_fault_info fault_info;
-
-	/* work for handling GPU ioval faults: */
-	struct kthread_work fault_work;
-
 	/* work for handling GPU recovery: */
 	struct kthread_work recover_work;
 
@@ -705,6 +699,8 @@ static inline void msm_gpu_crashstate_put(struct msm_gpu *gpu)
 	mutex_unlock(&gpu->lock);
 }
 
+void msm_gpu_fault_crashstate_capture(struct msm_gpu *gpu, struct msm_gpu_fault_info *fault_info);
+
 /*
  * Simple macro to semi-cleanly add the MAP_PRIV flag for targets that can
  * support expanded privileges

From dedf404be8cf97e6fabbed7ad97000ab816897eb Mon Sep 17 00:00:00 2001
From: Connor Abbott <cwabbott0@gmail.com>
Date: Tue, 20 May 2025 15:08:58 -0400
Subject: [PATCH 0108/1334] drm/msm: Delete resume_translation()

Unused since the previous commit.

Signed-off-by: Connor Abbott <cwabbott0@gmail.com>
Patchwork: https://patchwork.freedesktop.org/patch/654890/
Signed-off-by: Rob Clark <robin.clark@oss.qualcomm.com>
---
 drivers/gpu/drm/msm/adreno/a2xx_gpummu.c |  5 -----
 drivers/gpu/drm/msm/msm_iommu.c          | 13 -------------
 drivers/gpu/drm/msm/msm_mmu.h            |  1 -
 3 files changed, 19 deletions(-)

diff --git a/drivers/gpu/drm/msm/adreno/a2xx_gpummu.c b/drivers/gpu/drm/msm/adreno/a2xx_gpummu.c
index 39641551eeb6..4280f71e472a 100644
--- a/drivers/gpu/drm/msm/adreno/a2xx_gpummu.c
+++ b/drivers/gpu/drm/msm/adreno/a2xx_gpummu.c
@@ -71,10 +71,6 @@ static int a2xx_gpummu_unmap(struct msm_mmu *mmu, uint64_t iova, size_t len)
 	return 0;
 }
 
-static void a2xx_gpummu_resume_translation(struct msm_mmu *mmu)
-{
-}
-
 static void a2xx_gpummu_destroy(struct msm_mmu *mmu)
 {
 	struct a2xx_gpummu *gpummu = to_a2xx_gpummu(mmu);
@@ -90,7 +86,6 @@ static const struct msm_mmu_funcs funcs = {
 		.map = a2xx_gpummu_map,
 		.unmap = a2xx_gpummu_unmap,
 		.destroy = a2xx_gpummu_destroy,
-		.resume_translation = a2xx_gpummu_resume_translation,
 };
 
 struct msm_mmu *a2xx_gpummu_new(struct device *dev, struct msm_gpu *gpu)
diff --git a/drivers/gpu/drm/msm/msm_iommu.c b/drivers/gpu/drm/msm/msm_iommu.c
index fd73dcd3f30e..aae885d048d0 100644
--- a/drivers/gpu/drm/msm/msm_iommu.c
+++ b/drivers/gpu/drm/msm/msm_iommu.c
@@ -345,7 +345,6 @@ static int msm_gpu_fault_handler(struct iommu_domain *domain, struct device *dev
 		unsigned long iova, int flags, void *arg)
 {
 	struct msm_iommu *iommu = arg;
-	struct msm_mmu *mmu = &iommu->base;
 	struct adreno_smmu_priv *adreno_smmu = dev_get_drvdata(iommu->base.dev);
 	struct adreno_smmu_fault_info info, *ptr = NULL;
 
@@ -359,9 +358,6 @@ static int msm_gpu_fault_handler(struct iommu_domain *domain, struct device *dev
 
 	pr_warn_ratelimited("*** fault: iova=%16lx, flags=%d\n", iova, flags);
 
-	if (mmu->funcs->resume_translation)
-		mmu->funcs->resume_translation(mmu);
-
 	return 0;
 }
 
@@ -376,14 +372,6 @@ static int msm_disp_fault_handler(struct iommu_domain *domain, struct device *de
 	return -ENOSYS;
 }
 
-static void msm_iommu_resume_translation(struct msm_mmu *mmu)
-{
-	struct adreno_smmu_priv *adreno_smmu = dev_get_drvdata(mmu->dev);
-
-	if (adreno_smmu->resume_translation)
-		adreno_smmu->resume_translation(adreno_smmu->cookie, true);
-}
-
 static void msm_iommu_detach(struct msm_mmu *mmu)
 {
 	struct msm_iommu *iommu = to_msm_iommu(mmu);
@@ -431,7 +419,6 @@ static const struct msm_mmu_funcs funcs = {
 		.map = msm_iommu_map,
 		.unmap = msm_iommu_unmap,
 		.destroy = msm_iommu_destroy,
-		.resume_translation = msm_iommu_resume_translation,
 };
 
 struct msm_mmu *msm_iommu_new(struct device *dev, unsigned long quirks)
diff --git a/drivers/gpu/drm/msm/msm_mmu.h b/drivers/gpu/drm/msm/msm_mmu.h
index daf91529e02b..c3d17aae88b0 100644
--- a/drivers/gpu/drm/msm/msm_mmu.h
+++ b/drivers/gpu/drm/msm/msm_mmu.h
@@ -15,7 +15,6 @@ struct msm_mmu_funcs {
 			size_t len, int prot);
 	int (*unmap)(struct msm_mmu *mmu, uint64_t iova, size_t len);
 	void (*destroy)(struct msm_mmu *mmu);
-	void (*resume_translation)(struct msm_mmu *mmu);
 };
 
 enum msm_mmu_type {

From b13044092c1e30453d2f7e9be596d3a2616582a0 Mon Sep 17 00:00:00 2001
From: Connor Abbott <cwabbott0@gmail.com>
Date: Tue, 20 May 2025 15:08:59 -0400
Subject: [PATCH 0109/1334] drm/msm: Temporarily disable stall-on-fault after a
 page fault

When things go wrong, the GPU is capable of quickly generating millions
of faulting translation requests per second. When that happens, in the
stall-on-fault model each access will stall until it wins the race to
signal the fault and then the RESUME register is written. This slows
processing page faults to a crawl as the GPU can generate faults much
faster than the CPU can acknowledge them. It also means that all
available resources in the SMMU are saturated waiting for the stalled
transactions, so that other transactions such as transactions generated
by the GMU, which shares translation resources with the GPU, cannot
proceed. This causes a GMU watchdog timeout, which leads to a failed
reset because GX cannot collapse when there is a transaction pending and
a permanently hung GPU.

On older platforms with qcom,smmu-v2, it seems that when one transaction
is stalled subsequent faulting transactions are terminated, which avoids
this problem, but the MMU-500 follows the spec here.

To work around these problems, disable stall-on-fault as soon as we get a
page fault until a cooldown period after pagefaults stop. This allows
the GMU some guaranteed time to continue working. We only use
stall-on-fault to halt the GPU while we collect a devcoredump and we
always terminate the transaction afterward, so it's fine to miss some
subsequent page faults. We also keep it disabled so long as the current
devcoredump hasn't been deleted, because in that case we likely won't
capture another one if there's a fault.

After this commit HFI messages still occasionally time out, because the
crashdump handler doesn't run fast enough to let the GMU resume, but the
driver seems to recover from it. This will probably go away after the
HFI timeout is increased.

Signed-off-by: Connor Abbott <cwabbott0@gmail.com>
Reviewed-by: Rob Clark <robdclark@gmail.com>
Patchwork: https://patchwork.freedesktop.org/patch/654891/
Signed-off-by: Rob Clark <robin.clark@oss.qualcomm.com>
---
 drivers/gpu/drm/msm/adreno/a5xx_gpu.c   |  2 ++
 drivers/gpu/drm/msm/adreno/a6xx_gpu.c   |  4 +++
 drivers/gpu/drm/msm/adreno/adreno_gpu.c | 40 ++++++++++++++++++++++++-
 drivers/gpu/drm/msm/adreno/adreno_gpu.h |  2 ++
 drivers/gpu/drm/msm/msm_debugfs.c       | 32 ++++++++++++++++++++
 drivers/gpu/drm/msm/msm_drv.c           |  4 +++
 drivers/gpu/drm/msm/msm_drv.h           | 23 ++++++++++++++
 drivers/gpu/drm/msm/msm_iommu.c         |  9 ++++++
 drivers/gpu/drm/msm/msm_mmu.h           |  1 +
 9 files changed, 116 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
index 650e5bac225f..60aef0796236 100644
--- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
@@ -131,6 +131,8 @@ static void a5xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit)
 	struct msm_ringbuffer *ring = submit->ring;
 	unsigned int i, ibs = 0;
 
+	adreno_check_and_reenable_stall(adreno_gpu);
+
 	if (IS_ENABLED(CONFIG_DRM_MSM_GPU_SUDO) && submit->in_rb) {
 		ring->cur_ctx_seqno = 0;
 		a5xx_submit_in_rb(gpu, submit);
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
index bf3758f010f4..a7ffd92de3bb 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
@@ -212,6 +212,8 @@ static void a6xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit)
 	struct msm_ringbuffer *ring = submit->ring;
 	unsigned int i, ibs = 0;
 
+	adreno_check_and_reenable_stall(adreno_gpu);
+
 	a6xx_set_pagetable(a6xx_gpu, ring, submit);
 
 	get_stats_counter(ring, REG_A6XX_RBBM_PERFCTR_CP(0),
@@ -335,6 +337,8 @@ static void a7xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit)
 	struct msm_ringbuffer *ring = submit->ring;
 	unsigned int i, ibs = 0;
 
+	adreno_check_and_reenable_stall(adreno_gpu);
+
 	/*
 	 * Toggle concurrent binning for pagetable switch and set the thread to
 	 * BR since only it can execute the pagetable switch packets.
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
index 5ebd5a6ea143..86bff915c3e7 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
@@ -259,16 +259,54 @@ u64 adreno_private_address_space_size(struct msm_gpu *gpu)
 	return BIT(ttbr1_cfg->ias) - ADRENO_VM_START;
 }
 
+void adreno_check_and_reenable_stall(struct adreno_gpu *adreno_gpu)
+{
+	struct msm_gpu *gpu = &adreno_gpu->base;
+	struct msm_drm_private *priv = gpu->dev->dev_private;
+	unsigned long flags;
+
+	/*
+	 * Wait until the cooldown period has passed and we would actually
+	 * collect a crashdump to re-enable stall-on-fault.
+	 */
+	spin_lock_irqsave(&priv->fault_stall_lock, flags);
+	if (!priv->stall_enabled &&
+			ktime_after(ktime_get(), priv->stall_reenable_time) &&
+			!READ_ONCE(gpu->crashstate)) {
+		priv->stall_enabled = true;
+
+		gpu->aspace->mmu->funcs->set_stall(gpu->aspace->mmu, true);
+	}
+	spin_unlock_irqrestore(&priv->fault_stall_lock, flags);
+}
+
 #define ARM_SMMU_FSR_TF                 BIT(1)
 #define ARM_SMMU_FSR_PF			BIT(3)
 #define ARM_SMMU_FSR_EF			BIT(4)
+#define ARM_SMMU_FSR_SS			BIT(30)
 
 int adreno_fault_handler(struct msm_gpu *gpu, unsigned long iova, int flags,
 			 struct adreno_smmu_fault_info *info, const char *block,
 			 u32 scratch[4])
 {
+	struct msm_drm_private *priv = gpu->dev->dev_private;
 	const char *type = "UNKNOWN";
-	bool do_devcoredump = info && !READ_ONCE(gpu->crashstate);
+	bool do_devcoredump = info && (info->fsr & ARM_SMMU_FSR_SS) &&
+		!READ_ONCE(gpu->crashstate);
+	unsigned long irq_flags;
+
+	/*
+	 * In case there is a subsequent storm of pagefaults, disable
+	 * stall-on-fault for at least half a second.
+	 */
+	spin_lock_irqsave(&priv->fault_stall_lock, irq_flags);
+	if (priv->stall_enabled) {
+		priv->stall_enabled = false;
+
+		gpu->aspace->mmu->funcs->set_stall(gpu->aspace->mmu, false);
+	}
+	priv->stall_reenable_time = ktime_add_ms(ktime_get(), 500);
+	spin_unlock_irqrestore(&priv->fault_stall_lock, irq_flags);
 
 	/*
 	 * Print a default message if we couldn't get the data from the
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.h b/drivers/gpu/drm/msm/adreno/adreno_gpu.h
index a8f4bf416e64..bc063594a359 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.h
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.h
@@ -636,6 +636,8 @@ int adreno_fault_handler(struct msm_gpu *gpu, unsigned long iova, int flags,
 			 struct adreno_smmu_fault_info *info, const char *block,
 			 u32 scratch[4]);
 
+void adreno_check_and_reenable_stall(struct adreno_gpu *gpu);
+
 int adreno_read_speedbin(struct device *dev, u32 *speedbin);
 
 /*
diff --git a/drivers/gpu/drm/msm/msm_debugfs.c b/drivers/gpu/drm/msm/msm_debugfs.c
index 7ab607252d18..6af72162cda4 100644
--- a/drivers/gpu/drm/msm/msm_debugfs.c
+++ b/drivers/gpu/drm/msm/msm_debugfs.c
@@ -208,6 +208,35 @@ DEFINE_DEBUGFS_ATTRIBUTE(shrink_fops,
 			 shrink_get, shrink_set,
 			 "0x%08llx\n");
 
+/*
+ * Return the number of microseconds to wait until stall-on-fault is
+ * re-enabled. If 0 then it is already enabled or will be re-enabled on the
+ * next submit (unless there's a leftover devcoredump). This is useful for
+ * kernel tests that intentionally produce a fault and check the devcoredump to
+ * wait until the cooldown period is over.
+ */
+
+static int
+stall_reenable_time_get(void *data, u64 *val)
+{
+	struct msm_drm_private *priv = data;
+	unsigned long irq_flags;
+
+	spin_lock_irqsave(&priv->fault_stall_lock, irq_flags);
+
+	if (priv->stall_enabled)
+		*val = 0;
+	else
+		*val = max(ktime_us_delta(priv->stall_reenable_time, ktime_get()), 0);
+
+	spin_unlock_irqrestore(&priv->fault_stall_lock, irq_flags);
+
+	return 0;
+}
+
+DEFINE_DEBUGFS_ATTRIBUTE(stall_reenable_time_fops,
+			 stall_reenable_time_get, NULL,
+			 "%lld\n");
 
 static int msm_gem_show(struct seq_file *m, void *arg)
 {
@@ -319,6 +348,9 @@ static void msm_debugfs_gpu_init(struct drm_minor *minor)
 	debugfs_create_bool("disable_err_irq", 0600, minor->debugfs_root,
 		&priv->disable_err_irq);
 
+	debugfs_create_file("stall_reenable_time_us", 0400, minor->debugfs_root,
+		priv, &stall_reenable_time_fops);
+
 	gpu_devfreq = debugfs_create_dir("devfreq", minor->debugfs_root);
 
 	debugfs_create_bool("idle_clamp",0600, gpu_devfreq,
diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c
index f316e6776f67..132d4cac3587 100644
--- a/drivers/gpu/drm/msm/msm_drv.c
+++ b/drivers/gpu/drm/msm/msm_drv.c
@@ -245,6 +245,10 @@ static int msm_drm_init(struct device *dev, const struct drm_driver *drv)
 	drm_gem_lru_init(&priv->lru.willneed, &priv->lru.lock);
 	drm_gem_lru_init(&priv->lru.dontneed, &priv->lru.lock);
 
+	/* Initialize stall-on-fault */
+	spin_lock_init(&priv->fault_stall_lock);
+	priv->stall_enabled = true;
+
 	/* Teach lockdep about lock ordering wrt. shrinker: */
 	fs_reclaim_acquire(GFP_KERNEL);
 	might_lock(&priv->lru.lock);
diff --git a/drivers/gpu/drm/msm/msm_drv.h b/drivers/gpu/drm/msm/msm_drv.h
index a65077855201..c8afb1ea6040 100644
--- a/drivers/gpu/drm/msm/msm_drv.h
+++ b/drivers/gpu/drm/msm/msm_drv.h
@@ -222,6 +222,29 @@ struct msm_drm_private {
 	 * the sw hangcheck mechanism.
 	 */
 	bool disable_err_irq;
+
+	/**
+	 * @fault_stall_lock:
+	 *
+	 * Serialize changes to stall-on-fault state.
+	 */
+	spinlock_t fault_stall_lock;
+
+	/**
+	 * @fault_stall_reenable_time:
+	 *
+	 * If stall_enabled is false, when to reenable stall-on-fault.
+	 * Protected by @fault_stall_lock.
+	 */
+	ktime_t stall_reenable_time;
+
+	/**
+	 * @stall_enabled:
+	 *
+	 * Whether stall-on-fault is currently enabled. Protected by
+	 * @fault_stall_lock.
+	 */
+	bool stall_enabled;
 };
 
 const struct msm_format *mdp_get_format(struct msm_kms *kms, uint32_t format, uint64_t modifier);
diff --git a/drivers/gpu/drm/msm/msm_iommu.c b/drivers/gpu/drm/msm/msm_iommu.c
index aae885d048d0..739ce2c283a4 100644
--- a/drivers/gpu/drm/msm/msm_iommu.c
+++ b/drivers/gpu/drm/msm/msm_iommu.c
@@ -372,6 +372,14 @@ static int msm_disp_fault_handler(struct iommu_domain *domain, struct device *de
 	return -ENOSYS;
 }
 
+static void msm_iommu_set_stall(struct msm_mmu *mmu, bool enable)
+{
+	struct adreno_smmu_priv *adreno_smmu = dev_get_drvdata(mmu->dev);
+
+	if (adreno_smmu->set_stall)
+		adreno_smmu->set_stall(adreno_smmu->cookie, enable);
+}
+
 static void msm_iommu_detach(struct msm_mmu *mmu)
 {
 	struct msm_iommu *iommu = to_msm_iommu(mmu);
@@ -419,6 +427,7 @@ static const struct msm_mmu_funcs funcs = {
 		.map = msm_iommu_map,
 		.unmap = msm_iommu_unmap,
 		.destroy = msm_iommu_destroy,
+		.set_stall = msm_iommu_set_stall,
 };
 
 struct msm_mmu *msm_iommu_new(struct device *dev, unsigned long quirks)
diff --git a/drivers/gpu/drm/msm/msm_mmu.h b/drivers/gpu/drm/msm/msm_mmu.h
index c3d17aae88b0..0c694907140d 100644
--- a/drivers/gpu/drm/msm/msm_mmu.h
+++ b/drivers/gpu/drm/msm/msm_mmu.h
@@ -15,6 +15,7 @@ struct msm_mmu_funcs {
 			size_t len, int prot);
 	int (*unmap)(struct msm_mmu *mmu, uint64_t iova, size_t len);
 	void (*destroy)(struct msm_mmu *mmu);
+	void (*set_stall)(struct msm_mmu *mmu, bool enable);
 };
 
 enum msm_mmu_type {

From ad0f54842cd23127070d8c310dd06d8f7add025c Mon Sep 17 00:00:00 2001
From: Ankit Chauhan <ankitchauhan2065@gmail.com>
Date: Wed, 28 May 2025 16:36:04 +0530
Subject: [PATCH 0110/1334] scsi: mvsas: Fix typos in per-phy comments and SAS
 cmd port registers

Spelling fixes:
Deocder --> Decoder
Memroy --> Memory

This is a non-functional change aimed at improving code clarity.

Signed-off-by: Ankit Chauhan <ankitchauhan2065@gmail.com>
Link: https://lore.kernel.org/r/20250528110604.59528-1-ankitchauhan2065@gmail.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/mvsas/mv_defs.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/scsi/mvsas/mv_defs.h b/drivers/scsi/mvsas/mv_defs.h
index 8ef174cd4d37..3e4124177b2a 100644
--- a/drivers/scsi/mvsas/mv_defs.h
+++ b/drivers/scsi/mvsas/mv_defs.h
@@ -215,7 +215,7 @@ enum hw_register_bits {
 
 	/* MVS_Px_INT_STAT, MVS_Px_INT_MASK (per-phy events) */
 	PHYEV_DEC_ERR		= (1U << 24),	/* Phy Decoding Error */
-	PHYEV_DCDR_ERR		= (1U << 23),	/* STP Deocder Error */
+	PHYEV_DCDR_ERR		= (1U << 23),	/* STP Decoder Error */
 	PHYEV_CRC_ERR		= (1U << 22),	/* STP CRC Error */
 	PHYEV_UNASSOC_FIS	= (1U << 19),	/* unassociated FIS rx'd */
 	PHYEV_AN		= (1U << 18),	/* SATA async notification */
@@ -347,7 +347,7 @@ enum sas_cmd_port_registers {
 	CMD_SATA_PORT_MEM_CTL0	= 0x158, /* SATA Port Memory Control 0 */
 	CMD_SATA_PORT_MEM_CTL1	= 0x15c, /* SATA Port Memory Control 1 */
 	CMD_XOR_MEM_BIST_CTL	= 0x160, /* XOR Memory BIST Control */
-	CMD_XOR_MEM_BIST_STAT	= 0x164, /* XOR Memroy BIST Status */
+	CMD_XOR_MEM_BIST_STAT	= 0x164, /* XOR Memory BIST Status */
 	CMD_DMA_MEM_BIST_CTL	= 0x168, /* DMA Memory BIST Control */
 	CMD_DMA_MEM_BIST_STAT	= 0x16c, /* DMA Memory BIST Status */
 	CMD_PORT_MEM_BIST_CTL	= 0x170, /* Port Memory BIST Control */

From 9b17621366d210ffee83262a8754086ebbde5e55 Mon Sep 17 00:00:00 2001
From: Alok Tiwari <alok.a.tiwari@oracle.com>
Date: Fri, 30 May 2025 12:29:35 -0700
Subject: [PATCH 0111/1334] scsi: iscsi: Fix incorrect error path labels for
 flashnode operations

Correct the error handling goto labels used when host lookup fails in
various flashnode-related event handlers:

 - iscsi_new_flashnode()
 - iscsi_del_flashnode()
 - iscsi_login_flashnode()
 - iscsi_logout_flashnode()
 - iscsi_logout_flashnode_sid()

scsi_host_put() is not required when shost is NULL, so jumping to the
correct label avoids unnecessary operations. These functions previously
jumped to the wrong goto label (put_host), which did not match the
intended cleanup logic.

Use the correct exit labels (exit_new_fnode, exit_del_fnode, etc.) to
ensure proper error handling.  Also remove the unused put_host label
under iscsi_new_flashnode() as it is no longer needed.

No functional changes beyond accurate error path correction.

Fixes: c6a4bb2ef596 ("[SCSI] scsi_transport_iscsi: Add flash node mgmt support")
Signed-off-by: Alok Tiwari <alok.a.tiwari@oracle.com>
Link: https://lore.kernel.org/r/20250530193012.3312911-1-alok.a.tiwari@oracle.com
Reviewed-by: Mike Christie <michael.christie@oracle.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/scsi_transport_iscsi.c | 11 +++++------
 1 file changed, 5 insertions(+), 6 deletions(-)

diff --git a/drivers/scsi/scsi_transport_iscsi.c b/drivers/scsi/scsi_transport_iscsi.c
index 0b8c91bf793f..c75a806496d6 100644
--- a/drivers/scsi/scsi_transport_iscsi.c
+++ b/drivers/scsi/scsi_transport_iscsi.c
@@ -3499,7 +3499,7 @@ static int iscsi_new_flashnode(struct iscsi_transport *transport,
 		pr_err("%s could not find host no %u\n",
 		       __func__, ev->u.new_flashnode.host_no);
 		err = -ENODEV;
-		goto put_host;
+		goto exit_new_fnode;
 	}
 
 	index = transport->new_flashnode(shost, data, len);
@@ -3509,7 +3509,6 @@ static int iscsi_new_flashnode(struct iscsi_transport *transport,
 	else
 		err = -EIO;
 
-put_host:
 	scsi_host_put(shost);
 
 exit_new_fnode:
@@ -3534,7 +3533,7 @@ static int iscsi_del_flashnode(struct iscsi_transport *transport,
 		pr_err("%s could not find host no %u\n",
 		       __func__, ev->u.del_flashnode.host_no);
 		err = -ENODEV;
-		goto put_host;
+		goto exit_del_fnode;
 	}
 
 	idx = ev->u.del_flashnode.flashnode_idx;
@@ -3576,7 +3575,7 @@ static int iscsi_login_flashnode(struct iscsi_transport *transport,
 		pr_err("%s could not find host no %u\n",
 		       __func__, ev->u.login_flashnode.host_no);
 		err = -ENODEV;
-		goto put_host;
+		goto exit_login_fnode;
 	}
 
 	idx = ev->u.login_flashnode.flashnode_idx;
@@ -3628,7 +3627,7 @@ static int iscsi_logout_flashnode(struct iscsi_transport *transport,
 		pr_err("%s could not find host no %u\n",
 		       __func__, ev->u.logout_flashnode.host_no);
 		err = -ENODEV;
-		goto put_host;
+		goto exit_logout_fnode;
 	}
 
 	idx = ev->u.logout_flashnode.flashnode_idx;
@@ -3678,7 +3677,7 @@ static int iscsi_logout_flashnode_sid(struct iscsi_transport *transport,
 		pr_err("%s could not find host no %u\n",
 		       __func__, ev->u.logout_flashnode.host_no);
 		err = -ENODEV;
-		goto put_host;
+		goto exit_logout_sid;
 	}
 
 	session = iscsi_session_lookup(ev->u.logout_flashnode_sid.sid);

From 9697ca0d53e3db357be26d2414276143c4a2cd49 Mon Sep 17 00:00:00 2001
From: Peter Oberparleiter <oberpar@linux.ibm.com>
Date: Tue, 3 Jun 2025 20:21:56 +0200
Subject: [PATCH 0112/1334] scsi: s390: zfcp: Ensure synchronous unit_add

Improve the usability of the unit_add sysfs attribute by ensuring that
the associated FCP LUN scan processing is completed synchronously.  This
enables configuration tooling to consistently determine the end of the
scan process to allow for serialization of follow-on actions.

While the scan process associated with unit_add typically completes
synchronously, it is deferred to an asynchronous background process if
unit_add is used before initial remote port scanning has completed.  This
occurs when unit_add is used immediately after setting the associated FCP
device online.

To ensure synchronous unit_add processing, wait for remote port scanning
to complete before initiating the FCP LUN scan.

Cc: stable@vger.kernel.org
Reviewed-by: M Nikhil <nikh1092@linux.ibm.com>
Reviewed-by: Nihar Panda <niharp@linux.ibm.com>
Signed-off-by: Peter Oberparleiter <oberpar@linux.ibm.com>
Signed-off-by: Nihar Panda <niharp@linux.ibm.com>
Link: https://lore.kernel.org/r/20250603182252.2287285-2-niharp@linux.ibm.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/s390/scsi/zfcp_sysfs.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/s390/scsi/zfcp_sysfs.c b/drivers/s390/scsi/zfcp_sysfs.c
index 41e36af35488..90a84ae98b97 100644
--- a/drivers/s390/scsi/zfcp_sysfs.c
+++ b/drivers/s390/scsi/zfcp_sysfs.c
@@ -449,6 +449,8 @@ static ssize_t zfcp_sysfs_unit_add_store(struct device *dev,
 	if (kstrtoull(buf, 0, (unsigned long long *) &fcp_lun))
 		return -EINVAL;
 
+	flush_work(&port->rport_work);
+
 	retval = zfcp_unit_add(port, fcp_lun);
 	if (retval)
 		return retval;

From b1c9e797ad37d188675505b66a3a4bbeea5d9560 Mon Sep 17 00:00:00 2001
From: Connor Abbott <cwabbott0@gmail.com>
Date: Tue, 20 May 2025 18:28:05 -0400
Subject: [PATCH 0113/1334] drm/msm: Fix CP_RESET_CONTEXT_STATE bitfield names

Based on kgsl.

Fixes: af66706accdf ("drm/msm/a6xx: Add skeleton A7xx support")
Signed-off-by: Connor Abbott <cwabbott0@gmail.com>
Patchwork: https://patchwork.freedesktop.org/patch/654922/
Signed-off-by: Rob Clark <robin.clark@oss.qualcomm.com>
---
 drivers/gpu/drm/msm/registers/adreno/adreno_pm4.xml | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/msm/registers/adreno/adreno_pm4.xml b/drivers/gpu/drm/msm/registers/adreno/adreno_pm4.xml
index 5a6ae9fc3194..462713401622 100644
--- a/drivers/gpu/drm/msm/registers/adreno/adreno_pm4.xml
+++ b/drivers/gpu/drm/msm/registers/adreno/adreno_pm4.xml
@@ -2255,7 +2255,8 @@ opcode: CP_LOAD_STATE4 (30) (4 dwords)
 	<reg32 offset="0" name="0">
 		<bitfield name="CLEAR_ON_CHIP_TS" pos="0" type="boolean"/>
 		<bitfield name="CLEAR_RESOURCE_TABLE" pos="1" type="boolean"/>
-		<bitfield name="CLEAR_GLOBAL_LOCAL_TS" pos="2" type="boolean"/>
+		<bitfield name="CLEAR_BV_BR_COUNTER" pos="2" type="boolean"/>
+		<bitfield name="RESET_GLOBAL_LOCAL_TS" pos="3" type="boolean"/>
 	</reg32>
 </domain>
 

From 2b520c6104f34e3a548525173c38ebca4402cac3 Mon Sep 17 00:00:00 2001
From: Connor Abbott <cwabbott0@gmail.com>
Date: Tue, 20 May 2025 18:28:06 -0400
Subject: [PATCH 0114/1334] drm/msm/a7xx: Call CP_RESET_CONTEXT_STATE

Calling this packet is necessary when we switch contexts because there
are various pieces of state used by userspace to synchronize between BR
and BV that are persistent across submits and we need to make sure that
they are in a "safe" state when switching contexts. Otherwise a
userspace submission in one context could cause another context to
function incorrectly and hang, effectively a denial of service (although
without leaking data). This was missed during initial a7xx bringup.

Fixes: af66706accdf ("drm/msm/a6xx: Add skeleton A7xx support")
Signed-off-by: Connor Abbott <cwabbott0@gmail.com>
Patchwork: https://patchwork.freedesktop.org/patch/654924/
Signed-off-by: Rob Clark <robin.clark@oss.qualcomm.com>
---
 drivers/gpu/drm/msm/adreno/a6xx_gpu.c | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
index a7ffd92de3bb..491fde0083a2 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
@@ -130,6 +130,20 @@ static void a6xx_set_pagetable(struct a6xx_gpu *a6xx_gpu,
 		OUT_RING(ring, lower_32_bits(rbmemptr(ring, fence)));
 		OUT_RING(ring, upper_32_bits(rbmemptr(ring, fence)));
 		OUT_RING(ring, submit->seqno - 1);
+
+		OUT_PKT7(ring, CP_THREAD_CONTROL, 1);
+		OUT_RING(ring, CP_SET_THREAD_BOTH);
+
+		/* Reset state used to synchronize BR and BV */
+		OUT_PKT7(ring, CP_RESET_CONTEXT_STATE, 1);
+		OUT_RING(ring,
+			 CP_RESET_CONTEXT_STATE_0_CLEAR_ON_CHIP_TS |
+			 CP_RESET_CONTEXT_STATE_0_CLEAR_RESOURCE_TABLE |
+			 CP_RESET_CONTEXT_STATE_0_CLEAR_BV_BR_COUNTER |
+			 CP_RESET_CONTEXT_STATE_0_RESET_GLOBAL_LOCAL_TS);
+
+		OUT_PKT7(ring, CP_THREAD_CONTROL, 1);
+		OUT_RING(ring, CP_SET_THREAD_BR);
 	}
 
 	if (!sysprof) {

From ba64c6737f8656aa86e9fbcc1ff56e56316e62f6 Mon Sep 17 00:00:00 2001
From: Ryan Eatmon <reatmon@ti.com>
Date: Sat, 24 May 2025 21:25:37 +0530
Subject: [PATCH 0115/1334] drivers: gpu: drm: msm: registers: improve
 reproducibility

The files generated by gen_header.py capture the source path to the
input files and the date.  While that can be informative, it varies
based on where and when the kernel was built as the full path is
captured.

Since all of the files that this tool is run on is under the drivers
directory, this modifies the application to strip all of the path before
drivers.  Additionally it prints <stripped> instead of the date.

Signed-off-by: Ryan Eatmon <reatmon@ti.com>
Signed-off-by: Bruce Ashfield <bruce.ashfield@gmail.com>
Signed-off-by: Viswanath Kraleti <viswanath.kraleti@oss.qualcomm.com>
Acked-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
Patchwork: https://patchwork.freedesktop.org/patch/655599/
Signed-off-by: Rob Clark <robin.clark@oss.qualcomm.com>
---
 drivers/gpu/drm/msm/registers/gen_header.py | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/msm/registers/gen_header.py b/drivers/gpu/drm/msm/registers/gen_header.py
index 3926485bb197..a409404627c7 100644
--- a/drivers/gpu/drm/msm/registers/gen_header.py
+++ b/drivers/gpu/drm/msm/registers/gen_header.py
@@ -11,6 +11,7 @@ import collections
 import argparse
 import time
 import datetime
+import re
 
 class Error(Exception):
 	def __init__(self, message):
@@ -877,13 +878,14 @@ The rules-ng-ng source files this header was generated from are:
 """)
 	maxlen = 0
 	for filepath in p.xml_files:
-		maxlen = max(maxlen, len(filepath))
+		new_filepath = re.sub("^.+drivers","drivers",filepath)
+		maxlen = max(maxlen, len(new_filepath))
 	for filepath in p.xml_files:
-		pad = " " * (maxlen - len(filepath))
+		pad = " " * (maxlen - len(new_filepath))
 		filesize = str(os.path.getsize(filepath))
 		filesize = " " * (7 - len(filesize)) + filesize
 		filetime = time.ctime(os.path.getmtime(filepath))
-		print("- " + filepath + pad + " (" + filesize + " bytes, from " + filetime + ")")
+		print("- " + new_filepath + pad + " (" + filesize + " bytes, from <stripped>)")
 	if p.copyright_year:
 		current_year = str(datetime.date.today().year)
 		print()

From 1453b532d193a0b1b94429c657365e14dd4f361e Mon Sep 17 00:00:00 2001
From: Rob Clark <robin.clark@oss.qualcomm.com>
Date: Mon, 9 Jun 2025 11:24:35 -0700
Subject: [PATCH 0116/1334] drm/msm: Rename add_components_mdp()

To better match add_gpu_components().

Signed-off-by: Rob Clark <robin.clark@oss.qualcomm.com>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
Patchwork: https://patchwork.freedesktop.org/patch/657700/
---
 drivers/gpu/drm/msm/msm_drv.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c
index 132d4cac3587..8eeb54a367f0 100644
--- a/drivers/gpu/drm/msm/msm_drv.c
+++ b/drivers/gpu/drm/msm/msm_drv.c
@@ -930,7 +930,7 @@ static const struct drm_driver msm_driver = {
  * is no external component that we need to add since LVDS is within MDP4
  * itself.
  */
-static int add_components_mdp(struct device *master_dev,
+static int add_mdp_components(struct device *master_dev,
 			      struct component_match **matchptr)
 {
 	struct device_node *np = master_dev->of_node;
@@ -1075,7 +1075,7 @@ int msm_drv_probe(struct device *master_dev,
 
 	/* Add mdp components if we have KMS. */
 	if (kms_init) {
-		ret = add_components_mdp(master_dev, &match);
+		ret = add_mdp_components(master_dev, &match);
 		if (ret)
 			return ret;
 	}

From 1efb73791c828f3d1ac68ebbc5eddc35a562f9d0 Mon Sep 17 00:00:00 2001
From: Rob Clark <robin.clark@oss.qualcomm.com>
Date: Mon, 9 Jun 2025 11:24:36 -0700
Subject: [PATCH 0117/1334] drm/msm/adreno: Pass device_node to find_chipid()

We are going to want to re-use this before the component is bound, when
we don't yet have the device pointer (but we do have the of node).

v2: use %pOF

Signed-off-by: Rob Clark <robin.clark@oss.qualcomm.com>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
Patchwork: https://patchwork.freedesktop.org/patch/657705/
---
 drivers/gpu/drm/msm/adreno/adreno_device.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/msm/adreno/adreno_device.c b/drivers/gpu/drm/msm/adreno/adreno_device.c
index f5e1490d07c1..f176796e238d 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_device.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_device.c
@@ -137,9 +137,8 @@ err_disable_rpm:
 	return NULL;
 }
 
-static int find_chipid(struct device *dev, uint32_t *chipid)
+static int find_chipid(struct device_node *node, uint32_t *chipid)
 {
-	struct device_node *node = dev->of_node;
 	const char *compat;
 	int ret;
 
@@ -173,11 +172,12 @@ static int find_chipid(struct device *dev, uint32_t *chipid)
 	/* and if that fails, fall back to legacy "qcom,chipid" property: */
 	ret = of_property_read_u32(node, "qcom,chipid", chipid);
 	if (ret) {
-		DRM_DEV_ERROR(dev, "could not parse qcom,chipid: %d\n", ret);
+		DRM_ERROR("%pOF: could not parse qcom,chipid: %d\n",
+			  node, ret);
 		return ret;
 	}
 
-	dev_warn(dev, "Using legacy qcom,chipid binding!\n");
+	pr_warn("%pOF: Using legacy qcom,chipid binding!\n", node);
 
 	return 0;
 }
@@ -191,7 +191,7 @@ static int adreno_bind(struct device *dev, struct device *master, void *data)
 	struct msm_gpu *gpu;
 	int ret;
 
-	ret = find_chipid(dev, &config.chip_id);
+	ret = find_chipid(dev->of_node, &config.chip_id);
 	if (ret)
 		return ret;
 

From 93310053663ba647e402ef67e4bb18ec06ff8dc4 Mon Sep 17 00:00:00 2001
From: Philipp Kerling <pkerling@casix.org>
Date: Sun, 8 Jun 2025 20:59:00 +0200
Subject: [PATCH 0118/1334] smb: client: disable path remapping with POSIX
 extensions

If SMB 3.1.1 POSIX Extensions are available and negotiated, the client
should be able to use all characters and not remap anything. Currently, the
user has to explicitly request this behavior by specifying the "nomapposix"
mount option.

Link: https://lore.kernel.org/4195bb677b33d680e77549890a4f4dd3b474ceaf.camel@rx2.rx-server.de
Signed-off-by: Philipp Kerling <pkerling@casix.org>
Reviewed-by: Namjae Jeon <linkinjeon@kernel.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 Documentation/admin-guide/cifs/usage.rst |  2 ++
 fs/smb/client/connect.c                  | 10 ++++++++--
 2 files changed, 10 insertions(+), 2 deletions(-)

diff --git a/Documentation/admin-guide/cifs/usage.rst b/Documentation/admin-guide/cifs/usage.rst
index c09674a75a9e..d989ae5778ba 100644
--- a/Documentation/admin-guide/cifs/usage.rst
+++ b/Documentation/admin-guide/cifs/usage.rst
@@ -270,6 +270,8 @@ configured for Unix Extensions (and the client has not disabled
 illegal Windows/NTFS/SMB characters to a remap range (this mount parameter
 is the default for SMB3). This remap (``mapposix``) range is also
 compatible with Mac (and "Services for Mac" on some older Windows).
+When POSIX Extensions for SMB 3.1.1 are negotiated, remapping is automatically
+disabled.
 
 CIFS VFS Mount Options
 ======================
diff --git a/fs/smb/client/connect.c b/fs/smb/client/connect.c
index 28bc33496623..c4fb80b37738 100644
--- a/fs/smb/client/connect.c
+++ b/fs/smb/client/connect.c
@@ -3718,9 +3718,15 @@ int cifs_mount_get_tcon(struct cifs_mount_ctx *mnt_ctx)
 		goto out;
 	}
 
-	/* if new SMB3.11 POSIX extensions are supported do not remap / and \ */
-	if (tcon->posix_extensions)
+	/*
+	 * if new SMB3.11 POSIX extensions are supported, do not change anything in the
+	 * path (i.e., do not remap / and \ and do not map any special characters)
+	 */
+	if (tcon->posix_extensions) {
 		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_POSIX_PATHS;
+		cifs_sb->mnt_cifs_flags &= ~(CIFS_MOUNT_MAP_SFM_CHR |
+					     CIFS_MOUNT_MAP_SPECIAL_CHR);
+	}
 
 #ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY
 	/* tell server which Unix caps we support */

From 82ffbe7776d0ac084031f114167712269bf3d832 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 6 Jun 2025 16:51:27 +0000
Subject: [PATCH 0119/1334] net_sched: sch_sfq: fix a potential crash on
 gso_skb handling
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

SFQ has an assumption of always being able to queue at least one packet.

However, after the blamed commit, sch->q.len can be inflated by packets
in sch->gso_skb, and an enqueue() on an empty SFQ qdisc can be followed
by an immediate drop.

Fix sfq_drop() to properly clear q->tail in this situation.

Tested:

ip netns add lb
ip link add dev to-lb type veth peer name in-lb netns lb
ethtool -K to-lb tso off                 # force qdisc to requeue gso_skb
ip netns exec lb ethtool -K in-lb gro on # enable NAPI
ip link set dev to-lb up
ip -netns lb link set dev in-lb up
ip addr add dev to-lb 192.168.20.1/24
ip -netns lb addr add dev in-lb 192.168.20.2/24
tc qdisc replace dev to-lb root sfq limit 100

ip netns exec lb netserver

netperf -H 192.168.20.2 -l 100 &
netperf -H 192.168.20.2 -l 100 &
netperf -H 192.168.20.2 -l 100 &
netperf -H 192.168.20.2 -l 100 &

Fixes: a53851e2c321 ("net: sched: explicit locking in gso_cpu fallback")
Reported-by: Marcus Wichelmann <marcus.wichelmann@hetzner-cloud.de>
Closes: https://lore.kernel.org/netdev/9da42688-bfaa-4364-8797-e9271f3bdaef@hetzner-cloud.de/
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Link: https://patch.msgid.link/20250606165127.3629486-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/sched/sch_sfq.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c
index b912ad99aa15..77fa02f2bfcd 100644
--- a/net/sched/sch_sfq.c
+++ b/net/sched/sch_sfq.c
@@ -310,7 +310,10 @@ drop:
 		/* It is difficult to believe, but ALL THE SLOTS HAVE LENGTH 1. */
 		x = q->tail->next;
 		slot = &q->slots[x];
-		q->tail->next = slot->next;
+		if (slot->next == x)
+			q->tail = NULL; /* no more active slots */
+		else
+			q->tail->next = slot->next;
 		q->ht[slot->hash] = SFQ_EMPTY_SLOT;
 		goto drop;
 	}

From 0838fc3e6718743d595bf26e0e69ae55aa51fad1 Mon Sep 17 00:00:00 2001
From: Rob Clark <robin.clark@oss.qualcomm.com>
Date: Mon, 9 Jun 2025 11:24:37 -0700
Subject: [PATCH 0120/1334] drm/msm/adreno: Check for recognized GPU before
 bind

If we have a newer dtb than kernel, we could end up in a situation where
the GPU device is present in the dtb, but not in the drivers device
table.  We don't want this to prevent the display from probing.  So
check that we recognize the GPU before adding the GPU component.

v2: use %pOF

Signed-off-by: Rob Clark <robin.clark@oss.qualcomm.com>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
Patchwork: https://patchwork.freedesktop.org/patch/657701/
---
 drivers/gpu/drm/msm/adreno/adreno_device.c | 29 ++++++++++++++++++----
 drivers/gpu/drm/msm/msm_drv.c              |  2 +-
 drivers/gpu/drm/msm/msm_gpu.h              |  1 +
 3 files changed, 26 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/msm/adreno/adreno_device.c b/drivers/gpu/drm/msm/adreno/adreno_device.c
index f176796e238d..5e7307567239 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_device.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_device.c
@@ -182,6 +182,26 @@ static int find_chipid(struct device_node *node, uint32_t *chipid)
 	return 0;
 }
 
+bool adreno_has_gpu(struct device_node *node)
+{
+	const struct adreno_info *info;
+	uint32_t chip_id;
+	int ret;
+
+	ret = find_chipid(node, &chip_id);
+	if (ret)
+		return false;
+
+	info = adreno_info(chip_id);
+	if (!info) {
+		pr_warn("%pOF: Unknown GPU revision: %"ADRENO_CHIPID_FMT"\n",
+			node, ADRENO_CHIPID_ARGS(chip_id));
+		return false;
+	}
+
+	return true;
+}
+
 static int adreno_bind(struct device *dev, struct device *master, void *data)
 {
 	static struct adreno_platform_config config = {};
@@ -192,18 +212,17 @@ static int adreno_bind(struct device *dev, struct device *master, void *data)
 	int ret;
 
 	ret = find_chipid(dev->of_node, &config.chip_id);
-	if (ret)
+	/* We shouldn't have gotten this far if we can't parse the chip_id */
+	if (WARN_ON(ret))
 		return ret;
 
 	dev->platform_data = &config;
 	priv->gpu_pdev = to_platform_device(dev);
 
 	info = adreno_info(config.chip_id);
-	if (!info) {
-		dev_warn(drm->dev, "Unknown GPU revision: %"ADRENO_CHIPID_FMT"\n",
-			ADRENO_CHIPID_ARGS(config.chip_id));
+	/* We shouldn't have gotten this far if we don't recognize the GPU: */
+	if (!WARN_ON(info))
 		return -ENXIO;
-	}
 
 	config.info = info;
 
diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c
index 8eeb54a367f0..d007687c2446 100644
--- a/drivers/gpu/drm/msm/msm_drv.c
+++ b/drivers/gpu/drm/msm/msm_drv.c
@@ -1034,7 +1034,7 @@ static int add_gpu_components(struct device *dev,
 	if (!np)
 		return 0;
 
-	if (of_device_is_available(np))
+	if (of_device_is_available(np) && adreno_has_gpu(np))
 		drm_of_component_match_add(dev, matchptr, component_compare_of, np);
 
 	of_node_put(np);
diff --git a/drivers/gpu/drm/msm/msm_gpu.h b/drivers/gpu/drm/msm/msm_gpu.h
index bed0692f5adb..5bf7cd985b9c 100644
--- a/drivers/gpu/drm/msm/msm_gpu.h
+++ b/drivers/gpu/drm/msm/msm_gpu.h
@@ -662,6 +662,7 @@ msm_gpu_create_private_address_space(struct msm_gpu *gpu, struct task_struct *ta
 void msm_gpu_cleanup(struct msm_gpu *gpu);
 
 struct msm_gpu *adreno_load_gpu(struct drm_device *dev);
+bool adreno_has_gpu(struct device_node *node);
 void __init adreno_register(void);
 void __exit adreno_unregister(void);
 

From b2f966568faaad326de97481096d0f3dc0971c43 Mon Sep 17 00:00:00 2001
From: Dexuan Cui <decui@microsoft.com>
Date: Fri, 6 Jun 2025 13:57:39 -0700
Subject: [PATCH 0121/1334] scsi: storvsc: Increase the timeouts to
 storvsc_timeout

Currently storvsc_timeout is only used in storvsc_sdev_configure(), and
5s and 10s are used elsewhere. It turns out that rarely the 5s is not
enough on Azure, so let's use storvsc_timeout everywhere.

In case a timeout happens and storvsc_channel_init() returns an error,
close the VMBus channel so that any host-to-guest messages in the
channel's ringbuffer, which might come late, can be safely ignored.

Add a "const" to storvsc_timeout.

Cc: stable@kernel.org
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Link: https://lore.kernel.org/r/1749243459-10419-1-git-send-email-decui@microsoft.com
Reviewed-by: Long Li <longli@microsoft.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/storvsc_drv.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c
index 2e6b2412d2c9..d9e59204a9c3 100644
--- a/drivers/scsi/storvsc_drv.c
+++ b/drivers/scsi/storvsc_drv.c
@@ -362,7 +362,7 @@ MODULE_PARM_DESC(ring_avail_percent_lowater,
 /*
  * Timeout in seconds for all devices managed by this driver.
  */
-static int storvsc_timeout = 180;
+static const int storvsc_timeout = 180;
 
 #if IS_ENABLED(CONFIG_SCSI_FC_ATTRS)
 static struct scsi_transport_template *fc_transport_template;
@@ -768,7 +768,7 @@ static void  handle_multichannel_storage(struct hv_device *device, int max_chns)
 		return;
 	}
 
-	t = wait_for_completion_timeout(&request->wait_event, 10*HZ);
+	t = wait_for_completion_timeout(&request->wait_event, storvsc_timeout * HZ);
 	if (t == 0) {
 		dev_err(dev, "Failed to create sub-channel: timed out\n");
 		return;
@@ -833,7 +833,7 @@ static int storvsc_execute_vstor_op(struct hv_device *device,
 	if (ret != 0)
 		return ret;
 
-	t = wait_for_completion_timeout(&request->wait_event, 5*HZ);
+	t = wait_for_completion_timeout(&request->wait_event, storvsc_timeout * HZ);
 	if (t == 0)
 		return -ETIMEDOUT;
 
@@ -1350,6 +1350,8 @@ static int storvsc_connect_to_vsp(struct hv_device *device, u32 ring_size,
 		return ret;
 
 	ret = storvsc_channel_init(device, is_fc);
+	if (ret)
+		vmbus_close(device->channel);
 
 	return ret;
 }
@@ -1668,7 +1670,7 @@ static int storvsc_host_reset_handler(struct scsi_cmnd *scmnd)
 	if (ret != 0)
 		return FAILED;
 
-	t = wait_for_completion_timeout(&request->wait_event, 5*HZ);
+	t = wait_for_completion_timeout(&request->wait_event, storvsc_timeout * HZ);
 	if (t == 0)
 		return TIMEOUT_ERROR;
 

From 5c3ba81923e02adae354ec8afd006f93289b4a3c Mon Sep 17 00:00:00 2001
From: Rajashekhar M A <rajs@netapp.com>
Date: Fri, 6 Jun 2025 15:59:24 +0200
Subject: [PATCH 0122/1334] scsi: error: alua: I/O errors for ALUA state
 transitions

When a host is configured with a few LUNs and I/O is running, injecting
FC faults repeatedly leads to path recovery problems.  The LUNs have 4
paths each and 3 of them come back active after say an FC fault which
makes 2 of the paths go down, instead of all 4. This happens after
several iterations of continuous FC faults.

Reason here is that we're returning an I/O error whenever we're
encountering sense code 06/04/0a (LOGICAL UNIT NOT ACCESSIBLE, ASYMMETRIC
ACCESS STATE TRANSITION) instead of retrying.

Signed-off-by: Rajashekhar M A <rajs@netapp.com>
Signed-off-by: Hannes Reinecke <hare@suse.de>
Link: https://lore.kernel.org/r/20250606135924.27397-1-hare@kernel.org
Reviewed-by: Lee Duncan <lduncan@suse.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/scsi_error.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c
index 376b8897ab90..746ff6a1f309 100644
--- a/drivers/scsi/scsi_error.c
+++ b/drivers/scsi/scsi_error.c
@@ -665,7 +665,8 @@ enum scsi_disposition scsi_check_sense(struct scsi_cmnd *scmd)
 		 * if the device is in the process of becoming ready, we
 		 * should retry.
 		 */
-		if ((sshdr.asc == 0x04) && (sshdr.ascq == 0x01))
+		if ((sshdr.asc == 0x04) &&
+		    (sshdr.ascq == 0x01 || sshdr.ascq == 0x0a))
 			return NEEDS_RETRY;
 		/*
 		 * if the device is not started, we need to wake

From cd097df4596f3a1e9d75eb8520162de1eb8485b2 Mon Sep 17 00:00:00 2001
From: "Ritesh Harjani (IBM)" <ritesh.list@gmail.com>
Date: Tue, 10 Jun 2025 07:42:26 +0530
Subject: [PATCH 0123/1334] powerpc/powernv/memtrace: Fix out of bounds issue
 in memtrace mmap

memtrace mmap issue has an out of bounds issue. This patch fixes the by
checking that the requested mapping region size should stay within the
allocated region size.

Reported-by: Jonathan Greental <yonatan02greental@gmail.com>
Fixes: 08a022ad3dfa ("powerpc/powernv/memtrace: Allow mmaping trace buffers")
Signed-off-by: Ritesh Harjani (IBM) <ritesh.list@gmail.com>
Signed-off-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Link: https://patch.msgid.link/20250610021227.361980-1-maddy@linux.ibm.com
---
 arch/powerpc/platforms/powernv/memtrace.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/arch/powerpc/platforms/powernv/memtrace.c b/arch/powerpc/platforms/powernv/memtrace.c
index 4ac9808e55a4..2ea30b343354 100644
--- a/arch/powerpc/platforms/powernv/memtrace.c
+++ b/arch/powerpc/platforms/powernv/memtrace.c
@@ -48,11 +48,15 @@ static ssize_t memtrace_read(struct file *filp, char __user *ubuf,
 static int memtrace_mmap(struct file *filp, struct vm_area_struct *vma)
 {
 	struct memtrace_entry *ent = filp->private_data;
+	unsigned long ent_nrpages = ent->size >> PAGE_SHIFT;
+	unsigned long vma_nrpages = vma_pages(vma);
 
-	if (ent->size < vma->vm_end - vma->vm_start)
+	/* The requested page offset should be within object's page count */
+	if (vma->vm_pgoff >= ent_nrpages)
 		return -EINVAL;
 
-	if (vma->vm_pgoff << PAGE_SHIFT >= ent->size)
+	/* The requested mapping range should remain within the bounds */
+	if (vma_nrpages > ent_nrpages - vma->vm_pgoff)
 		return -EINVAL;
 
 	vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);

From 0d67f0dee6c9176bc09a5482dd7346e3a0f14d0b Mon Sep 17 00:00:00 2001
From: Haren Myneni <haren@linux.ibm.com>
Date: Tue, 10 Jun 2025 07:42:27 +0530
Subject: [PATCH 0124/1334] powerpc/vas: Return -EINVAL if the offset is
 non-zero in mmap()

The user space calls mmap() to map VAS window paste address
and the kernel returns the complete mapped page for each
window. So return -EINVAL if non-zero is passed for offset
parameter to mmap().

See Documentation/arch/powerpc/vas-api.rst for mmap()
restrictions.

Co-developed-by: Jonathan Greental <yonatan02greental@gmail.com>
Signed-off-by: Jonathan Greental <yonatan02greental@gmail.com>
Reported-by: Jonathan Greental <yonatan02greental@gmail.com>
Fixes: dda44eb29c23 ("powerpc/vas: Add VAS user space API")
Signed-off-by: Haren Myneni <haren@linux.ibm.com>
Signed-off-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Link: https://patch.msgid.link/20250610021227.361980-2-maddy@linux.ibm.com
---
 arch/powerpc/platforms/book3s/vas-api.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/arch/powerpc/platforms/book3s/vas-api.c b/arch/powerpc/platforms/book3s/vas-api.c
index 0b6365d85d11..dc6f75d3ac6e 100644
--- a/arch/powerpc/platforms/book3s/vas-api.c
+++ b/arch/powerpc/platforms/book3s/vas-api.c
@@ -521,6 +521,15 @@ static int coproc_mmap(struct file *fp, struct vm_area_struct *vma)
 		return -EINVAL;
 	}
 
+	/*
+	 * Map complete page to the paste address. So the user
+	 * space should pass 0ULL to the offset parameter.
+	 */
+	if (vma->vm_pgoff) {
+		pr_debug("Page offset unsupported to map paste address\n");
+		return -EINVAL;
+	}
+
 	/* Ensure instance has an open send window */
 	if (!txwin) {
 		pr_err("No send window open?\n");

From c6451a7325874c119def1d4094f6815c0c8fdc23 Mon Sep 17 00:00:00 2001
From: Chris Chiu <chris.chiu@canonical.com>
Date: Tue, 10 Jun 2025 11:56:07 +0800
Subject: [PATCH 0125/1334] ALSA: hda/realtek: Fix built-in mic on ASUS
 VivoBook X513EA

The built-in mic of ASUS VivoBook X513EA is broken recently by the
fix of the pin sort. The fixup ALC256_FIXUP_ASUS_MIC_NO_PRESENCE
is working for addressing the regression, too.

Fixes: 3b4309546b48 ("ALSA: hda: Fix headset detection failure due to unstable sort")
Signed-off-by: Chris Chiu <chris.chiu@canonical.com>
Cc: <stable@vger.kernel.org>
Link: https://patch.msgid.link/20250610035607.690771-1-chris.chiu@canonical.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/patch_realtek.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index c70bee62653e..e296429c67d5 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -10906,6 +10906,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x103c, 0x8e60, "HP Trekker ", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x103c, 0x8e61, "HP Trekker ", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x103c, 0x8e62, "HP Trekker ", ALC287_FIXUP_CS35L41_I2C_2),
+	SND_PCI_QUIRK(0x1043, 0x1032, "ASUS VivoBook X513EA", ALC256_FIXUP_ASUS_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1043, 0x103e, "ASUS X540SA", ALC256_FIXUP_ASUS_MIC),
 	SND_PCI_QUIRK(0x1043, 0x103f, "ASUS TX300", ALC282_FIXUP_ASUS_TX300),
 	SND_PCI_QUIRK(0x1043, 0x1054, "ASUS G614FH/FM/FP", ALC287_FIXUP_CS35L41_I2C_2),

From 7b23887a0c70d15459f02c51651a111e9e5cab86 Mon Sep 17 00:00:00 2001
From: Richard Fitzgerald <rf@opensource.cirrus.com>
Date: Mon, 9 Jun 2025 11:21:25 +0100
Subject: [PATCH 0126/1334] ALSA: hda/realtek: Add quirk for Asus GU605C

The GU605C has similar audio hardware to the GU605M so apply the
same quirk.

Note that in the linked bugzilla there are two separate problems
with the GU605C. This patch fixes one of the problems, so I haven't
added a Closes: tag.

Signed-off-by: Richard Fitzgerald <rf@opensource.cirrus.com>
Reported-by: Nick Karaolidis <nick@karaolidis.com>
Link: https://bugzilla.kernel.org/show_bug.cgi?id=220152
Cc: <stable@vger.kernel.org>
Link: https://patch.msgid.link/20250609102125.63196-1-rf@opensource.cirrus.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/patch_realtek.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index e296429c67d5..bca725bb8281 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -10907,6 +10907,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x103c, 0x8e61, "HP Trekker ", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x103c, 0x8e62, "HP Trekker ", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x1043, 0x1032, "ASUS VivoBook X513EA", ALC256_FIXUP_ASUS_MIC_NO_PRESENCE),
+	SND_PCI_QUIRK(0x1043, 0x1034, "ASUS GU605C", ALC285_FIXUP_ASUS_GU605_SPI_SPEAKER2_TO_DAC1),
 	SND_PCI_QUIRK(0x1043, 0x103e, "ASUS X540SA", ALC256_FIXUP_ASUS_MIC),
 	SND_PCI_QUIRK(0x1043, 0x103f, "ASUS TX300", ALC282_FIXUP_ASUS_TX300),
 	SND_PCI_QUIRK(0x1043, 0x1054, "ASUS G614FH/FM/FP", ALC287_FIXUP_CS35L41_I2C_2),

From ed29e073ba93f2d52832804cabdd831d5d357d33 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Tue, 10 Jun 2025 08:43:19 +0200
Subject: [PATCH 0127/1334] ALSA: sb: Don't allow changing the DMA mode during
 operations

When a PCM stream is already running, one shouldn't change the DMA
mode via kcontrol, which may screw up the hardware.  Return -EBUSY
instead.

Link: https://bugzilla.kernel.org/show_bug.cgi?id=218185
Link: https://patch.msgid.link/20250610064322.26787-1-tiwai@suse.de
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/isa/sb/sb16_main.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/sound/isa/sb/sb16_main.c b/sound/isa/sb/sb16_main.c
index 74db11525003..c4930efd44e3 100644
--- a/sound/isa/sb/sb16_main.c
+++ b/sound/isa/sb/sb16_main.c
@@ -703,6 +703,9 @@ static int snd_sb16_dma_control_put(struct snd_kcontrol *kcontrol, struct snd_ct
 	unsigned char nval, oval;
 	int change;
 	
+	if (chip->mode & (SB_MODE_PLAYBACK | SB_MODE_CAPTURE))
+		return -EBUSY;
+
 	nval = ucontrol->value.enumerated.item[0];
 	if (nval > 2)
 		return -EINVAL;

From 4c267ae2ef349639b4d9ebf00dd28586a82fdbe6 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Tue, 10 Jun 2025 08:43:20 +0200
Subject: [PATCH 0128/1334] ALSA: sb: Force to disable DMAs once when DMA mode
 is changed

When the DMA mode is changed on the (still real!) SB AWE32 after
playing a stream and closing, the previous DMA setup was still
silently kept, and it can confuse the hardware, resulting in the
unexpected noises.  As a workaround, enforce the disablement of DMA
setups when the DMA setup is changed by the kcontrol.

https://bugzilla.kernel.org/show_bug.cgi?id=218185
Link: https://patch.msgid.link/20250610064322.26787-2-tiwai@suse.de
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/isa/sb/sb16_main.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/sound/isa/sb/sb16_main.c b/sound/isa/sb/sb16_main.c
index c4930efd44e3..5a083eecaa6b 100644
--- a/sound/isa/sb/sb16_main.c
+++ b/sound/isa/sb/sb16_main.c
@@ -714,6 +714,10 @@ static int snd_sb16_dma_control_put(struct snd_kcontrol *kcontrol, struct snd_ct
 	change = nval != oval;
 	snd_sb16_set_dma_mode(chip, nval);
 	spin_unlock_irqrestore(&chip->reg_lock, flags);
+	if (change) {
+		snd_dma_disable(chip->dma8);
+		snd_dma_disable(chip->dma16);
+	}
 	return change;
 }
 

From d9db3a941270d92bbd1a6a6b54a10324484f2f2d Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Wed, 21 May 2025 19:34:55 -0500
Subject: [PATCH 0129/1334] platform/x86/amd: pmf: Use device managed
 allocations
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

If setting up smart PC fails for any reason then this can lead to
a double free when unloading amd-pmf.  This is because dev->buf was
freed but never set to NULL and is again freed in amd_pmf_remove().

To avoid subtle allocation bugs in failures leading to a double free
change all allocations into device managed allocations.

Fixes: 5b1122fc4995f ("platform/x86/amd/pmf: fix cleanup in amd_pmf_init_smart_pc()")
Link: https://lore.kernel.org/r/20250512211154.2510397-2-superm1@kernel.org
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Link: https://lore.kernel.org/r/20250522003457.1516679-2-superm1@kernel.org
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/amd/pmf/core.c   |  3 +-
 drivers/platform/x86/amd/pmf/tee-if.c | 56 ++++++++++-----------------
 2 files changed, 22 insertions(+), 37 deletions(-)

diff --git a/drivers/platform/x86/amd/pmf/core.c b/drivers/platform/x86/amd/pmf/core.c
index 76910601cac8..ef988605c4da 100644
--- a/drivers/platform/x86/amd/pmf/core.c
+++ b/drivers/platform/x86/amd/pmf/core.c
@@ -280,7 +280,7 @@ int amd_pmf_set_dram_addr(struct amd_pmf_dev *dev, bool alloc_buffer)
 			dev_err(dev->dev, "Invalid CPU id: 0x%x", dev->cpu_id);
 		}
 
-		dev->buf = kzalloc(dev->mtable_size, GFP_KERNEL);
+		dev->buf = devm_kzalloc(dev->dev, dev->mtable_size, GFP_KERNEL);
 		if (!dev->buf)
 			return -ENOMEM;
 	}
@@ -493,7 +493,6 @@ static void amd_pmf_remove(struct platform_device *pdev)
 	mutex_destroy(&dev->lock);
 	mutex_destroy(&dev->update_mutex);
 	mutex_destroy(&dev->cb_mutex);
-	kfree(dev->buf);
 }
 
 static const struct attribute_group *amd_pmf_driver_groups[] = {
diff --git a/drivers/platform/x86/amd/pmf/tee-if.c b/drivers/platform/x86/amd/pmf/tee-if.c
index d3bd12ad036a..027e992b7147 100644
--- a/drivers/platform/x86/amd/pmf/tee-if.c
+++ b/drivers/platform/x86/amd/pmf/tee-if.c
@@ -358,30 +358,28 @@ static ssize_t amd_pmf_get_pb_data(struct file *filp, const char __user *buf,
 		return -EINVAL;
 
 	/* re-alloc to the new buffer length of the policy binary */
-	new_policy_buf = memdup_user(buf, length);
-	if (IS_ERR(new_policy_buf))
-		return PTR_ERR(new_policy_buf);
+	new_policy_buf = devm_kzalloc(dev->dev, length, GFP_KERNEL);
+	if (!new_policy_buf)
+		return -ENOMEM;
 
-	kfree(dev->policy_buf);
+	if (copy_from_user(new_policy_buf, buf, length)) {
+		devm_kfree(dev->dev, new_policy_buf);
+		return -EFAULT;
+	}
+
+	devm_kfree(dev->dev, dev->policy_buf);
 	dev->policy_buf = new_policy_buf;
 	dev->policy_sz = length;
 
-	if (!amd_pmf_pb_valid(dev)) {
-		ret = -EINVAL;
-		goto cleanup;
-	}
+	if (!amd_pmf_pb_valid(dev))
+		return -EINVAL;
 
 	amd_pmf_hex_dump_pb(dev);
 	ret = amd_pmf_start_policy_engine(dev);
 	if (ret < 0)
-		goto cleanup;
+		return ret;
 
 	return length;
-
-cleanup:
-	kfree(dev->policy_buf);
-	dev->policy_buf = NULL;
-	return ret;
 }
 
 static const struct file_operations pb_fops = {
@@ -532,13 +530,13 @@ int amd_pmf_init_smart_pc(struct amd_pmf_dev *dev)
 	dev->policy_base = devm_ioremap_resource(dev->dev, dev->res);
 	if (IS_ERR(dev->policy_base)) {
 		ret = PTR_ERR(dev->policy_base);
-		goto err_free_dram_buf;
+		goto err_cancel_work;
 	}
 
-	dev->policy_buf = kzalloc(dev->policy_sz, GFP_KERNEL);
+	dev->policy_buf = devm_kzalloc(dev->dev, dev->policy_sz, GFP_KERNEL);
 	if (!dev->policy_buf) {
 		ret = -ENOMEM;
-		goto err_free_dram_buf;
+		goto err_cancel_work;
 	}
 
 	memcpy_fromio(dev->policy_buf, dev->policy_base, dev->policy_sz);
@@ -546,21 +544,21 @@ int amd_pmf_init_smart_pc(struct amd_pmf_dev *dev)
 	if (!amd_pmf_pb_valid(dev)) {
 		dev_info(dev->dev, "No Smart PC policy present\n");
 		ret = -EINVAL;
-		goto err_free_policy;
+		goto err_cancel_work;
 	}
 
 	amd_pmf_hex_dump_pb(dev);
 
-	dev->prev_data = kzalloc(sizeof(*dev->prev_data), GFP_KERNEL);
+	dev->prev_data = devm_kzalloc(dev->dev, sizeof(*dev->prev_data), GFP_KERNEL);
 	if (!dev->prev_data) {
 		ret = -ENOMEM;
-		goto err_free_policy;
+		goto err_cancel_work;
 	}
 
 	for (i = 0; i < ARRAY_SIZE(amd_pmf_ta_uuid); i++) {
 		ret = amd_pmf_tee_init(dev, &amd_pmf_ta_uuid[i]);
 		if (ret)
-			goto err_free_prev_data;
+			goto err_cancel_work;
 
 		ret = amd_pmf_start_policy_engine(dev);
 		switch (ret) {
@@ -575,7 +573,7 @@ int amd_pmf_init_smart_pc(struct amd_pmf_dev *dev)
 		default:
 			ret = -EINVAL;
 			amd_pmf_tee_deinit(dev);
-			goto err_free_prev_data;
+			goto err_cancel_work;
 		}
 
 		if (status)
@@ -584,7 +582,7 @@ int amd_pmf_init_smart_pc(struct amd_pmf_dev *dev)
 
 	if (!status && !pb_side_load) {
 		ret = -EINVAL;
-		goto err_free_prev_data;
+		goto err_cancel_work;
 	}
 
 	if (pb_side_load)
@@ -600,12 +598,6 @@ err_pmf_remove_pb:
 	if (pb_side_load && dev->esbin)
 		amd_pmf_remove_pb(dev);
 	amd_pmf_tee_deinit(dev);
-err_free_prev_data:
-	kfree(dev->prev_data);
-err_free_policy:
-	kfree(dev->policy_buf);
-err_free_dram_buf:
-	kfree(dev->buf);
 err_cancel_work:
 	cancel_delayed_work_sync(&dev->pb_work);
 
@@ -621,11 +613,5 @@ void amd_pmf_deinit_smart_pc(struct amd_pmf_dev *dev)
 		amd_pmf_remove_pb(dev);
 
 	cancel_delayed_work_sync(&dev->pb_work);
-	kfree(dev->prev_data);
-	dev->prev_data = NULL;
-	kfree(dev->policy_buf);
-	dev->policy_buf = NULL;
-	kfree(dev->buf);
-	dev->buf = NULL;
 	amd_pmf_tee_deinit(dev);
 }

From 93103d56650d7a38ed37ba4041578310f82776ae Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Wed, 21 May 2025 19:34:56 -0500
Subject: [PATCH 0130/1334] platform/x86/amd: pmf: Prevent amd_pmf_tee_deinit()
 from running twice
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

If any of the tee init fails, pass up the errors and clear the tee_ctx
pointer. This will prevent cleaning up multiple times.

Fixes: ac052d8c08f9d ("platform/x86/amd/pmf: Add PMF TEE interface")
Suggested-by: Dan Carpenter <dan.carpenter@linaro.org>
Link: https://lore.kernel.org/r/20250512211154.2510397-3-superm1@kernel.org
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Link: https://lore.kernel.org/r/20250522003457.1516679-3-superm1@kernel.org
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/amd/pmf/tee-if.c | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/drivers/platform/x86/amd/pmf/tee-if.c b/drivers/platform/x86/amd/pmf/tee-if.c
index 027e992b7147..76efce48a45c 100644
--- a/drivers/platform/x86/amd/pmf/tee-if.c
+++ b/drivers/platform/x86/amd/pmf/tee-if.c
@@ -420,12 +420,12 @@ static int amd_pmf_ta_open_session(struct tee_context *ctx, u32 *id, const uuid_
 	rc = tee_client_open_session(ctx, &sess_arg, NULL);
 	if (rc < 0 || sess_arg.ret != 0) {
 		pr_err("Failed to open TEE session err:%#x, rc:%d\n", sess_arg.ret, rc);
-		return rc;
+		return rc ?: -EINVAL;
 	}
 
 	*id = sess_arg.session;
 
-	return rc;
+	return 0;
 }
 
 static int amd_pmf_register_input_device(struct amd_pmf_dev *dev)
@@ -460,7 +460,9 @@ static int amd_pmf_tee_init(struct amd_pmf_dev *dev, const uuid_t *uuid)
 	dev->tee_ctx = tee_client_open_context(NULL, amd_pmf_amdtee_ta_match, NULL, NULL);
 	if (IS_ERR(dev->tee_ctx)) {
 		dev_err(dev->dev, "Failed to open TEE context\n");
-		return PTR_ERR(dev->tee_ctx);
+		ret = PTR_ERR(dev->tee_ctx);
+		dev->tee_ctx = NULL;
+		return ret;
 	}
 
 	ret = amd_pmf_ta_open_session(dev->tee_ctx, &dev->session_id, uuid);
@@ -500,9 +502,12 @@ out_ctx:
 
 static void amd_pmf_tee_deinit(struct amd_pmf_dev *dev)
 {
+	if (!dev->tee_ctx)
+		return;
 	tee_shm_free(dev->fw_shm_pool);
 	tee_client_close_session(dev->tee_ctx, dev->session_id);
 	tee_client_close_context(dev->tee_ctx);
+	dev->tee_ctx = NULL;
 }
 
 int amd_pmf_init_smart_pc(struct amd_pmf_dev *dev)

From d7186dfd41924ef01ef490be5b82ab63cc417b31 Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Wed, 21 May 2025 19:34:57 -0500
Subject: [PATCH 0131/1334] platform/x86/amd: pmf: Simplify error flow in
 amd_pmf_init_smart_pc()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

commit 5b1122fc4995f ("platform/x86/amd/pmf: fix cleanup in
amd_pmf_init_smart_pc()") adjusted the error handling flow to use a ladder
but this isn't actually needed because work is only scheduled in
amd_pmf_start_policy_engine() and with device managed cleanups pointers
for allocations don't need to be freed.

Adjust the error flow to a single call to amd_pmf_deinit_smart_pc() for
the cases that need to clean up.

Cc: Dan Carpenter <dan.carpenter@linaro.org>
Link: https://lore.kernel.org/r/20250512211154.2510397-4-superm1@kernel.org
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Link: https://lore.kernel.org/r/20250522003457.1516679-4-superm1@kernel.org
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/amd/pmf/tee-if.c | 55 ++++++++-------------------
 1 file changed, 16 insertions(+), 39 deletions(-)

diff --git a/drivers/platform/x86/amd/pmf/tee-if.c b/drivers/platform/x86/amd/pmf/tee-if.c
index 76efce48a45c..4f626ebcb619 100644
--- a/drivers/platform/x86/amd/pmf/tee-if.c
+++ b/drivers/platform/x86/amd/pmf/tee-if.c
@@ -530,64 +530,45 @@ int amd_pmf_init_smart_pc(struct amd_pmf_dev *dev)
 
 	ret = amd_pmf_set_dram_addr(dev, true);
 	if (ret)
-		goto err_cancel_work;
+		return ret;
 
 	dev->policy_base = devm_ioremap_resource(dev->dev, dev->res);
-	if (IS_ERR(dev->policy_base)) {
-		ret = PTR_ERR(dev->policy_base);
-		goto err_cancel_work;
-	}
+	if (IS_ERR(dev->policy_base))
+		return PTR_ERR(dev->policy_base);
 
 	dev->policy_buf = devm_kzalloc(dev->dev, dev->policy_sz, GFP_KERNEL);
-	if (!dev->policy_buf) {
-		ret = -ENOMEM;
-		goto err_cancel_work;
-	}
+	if (!dev->policy_buf)
+		return -ENOMEM;
 
 	memcpy_fromio(dev->policy_buf, dev->policy_base, dev->policy_sz);
 
 	if (!amd_pmf_pb_valid(dev)) {
 		dev_info(dev->dev, "No Smart PC policy present\n");
-		ret = -EINVAL;
-		goto err_cancel_work;
+		return -EINVAL;
 	}
 
 	amd_pmf_hex_dump_pb(dev);
 
 	dev->prev_data = devm_kzalloc(dev->dev, sizeof(*dev->prev_data), GFP_KERNEL);
-	if (!dev->prev_data) {
-		ret = -ENOMEM;
-		goto err_cancel_work;
-	}
+	if (!dev->prev_data)
+		return -ENOMEM;
 
 	for (i = 0; i < ARRAY_SIZE(amd_pmf_ta_uuid); i++) {
 		ret = amd_pmf_tee_init(dev, &amd_pmf_ta_uuid[i]);
 		if (ret)
-			goto err_cancel_work;
+			return ret;
 
 		ret = amd_pmf_start_policy_engine(dev);
-		switch (ret) {
-		case TA_PMF_TYPE_SUCCESS:
-			status = true;
-			break;
-		case TA_ERROR_CRYPTO_INVALID_PARAM:
-		case TA_ERROR_CRYPTO_BIN_TOO_LARGE:
-			amd_pmf_tee_deinit(dev);
-			status = false;
-			break;
-		default:
-			ret = -EINVAL;
-			amd_pmf_tee_deinit(dev);
-			goto err_cancel_work;
-		}
-
+		dev_dbg(dev->dev, "start policy engine ret: %d\n", ret);
+		status = ret == TA_PMF_TYPE_SUCCESS;
 		if (status)
 			break;
+		amd_pmf_tee_deinit(dev);
 	}
 
 	if (!status && !pb_side_load) {
 		ret = -EINVAL;
-		goto err_cancel_work;
+		goto err;
 	}
 
 	if (pb_side_load)
@@ -595,16 +576,12 @@ int amd_pmf_init_smart_pc(struct amd_pmf_dev *dev)
 
 	ret = amd_pmf_register_input_device(dev);
 	if (ret)
-		goto err_pmf_remove_pb;
+		goto err;
 
 	return 0;
 
-err_pmf_remove_pb:
-	if (pb_side_load && dev->esbin)
-		amd_pmf_remove_pb(dev);
-	amd_pmf_tee_deinit(dev);
-err_cancel_work:
-	cancel_delayed_work_sync(&dev->pb_work);
+err:
+	amd_pmf_deinit_smart_pc(dev);
 
 	return ret;
 }

From a2f32c7467e843727f20cae0e9b1545e1504a977 Mon Sep 17 00:00:00 2001
From: Stuart Hayes <stuart.w.hayes@gmail.com>
Date: Mon, 9 Jun 2025 13:46:55 -0500
Subject: [PATCH 0132/1334] platform/x86: dell_rbu: Fix lock context warning
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Fix a sparse lock context warning.

Signed-off-by: Stuart Hayes <stuart.w.hayes@gmail.com>
Link: https://lore.kernel.org/r/20250609184659.7210-2-stuart.w.hayes@gmail.com
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/dell/dell_rbu.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/platform/x86/dell/dell_rbu.c b/drivers/platform/x86/dell/dell_rbu.c
index e30ca325938c..7b019fb72e86 100644
--- a/drivers/platform/x86/dell/dell_rbu.c
+++ b/drivers/platform/x86/dell/dell_rbu.c
@@ -91,7 +91,7 @@ static void init_packet_head(void)
 	rbu_data.imagesize = 0;
 }
 
-static int create_packet(void *data, size_t length)
+static int create_packet(void *data, size_t length) __must_hold(&rbu_data.lock)
 {
 	struct packet_data *newpacket;
 	int ordernum = 0;

From 61ce04601e0d8265ec6d2ffa6df5a7e1bce64854 Mon Sep 17 00:00:00 2001
From: Stuart Hayes <stuart.w.hayes@gmail.com>
Date: Mon, 9 Jun 2025 13:46:56 -0500
Subject: [PATCH 0133/1334] platform/x86: dell_rbu: Fix list usage
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Pass the correct list head to list_for_each_entry*() when looping through
the packet list.

Without this patch, reading the packet data via sysfs will show the data
incorrectly (because it starts at the wrong packet), and clearing the
packet list will result in a NULL pointer dereference.

Fixes: d19f359fbdc6 ("platform/x86: dell_rbu: don't open code list_for_each_entry*()")
Signed-off-by: Stuart Hayes <stuart.w.hayes@gmail.com>
Link: https://lore.kernel.org/r/20250609184659.7210-3-stuart.w.hayes@gmail.com
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/dell/dell_rbu.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/platform/x86/dell/dell_rbu.c b/drivers/platform/x86/dell/dell_rbu.c
index 7b019fb72e86..722979b19e0e 100644
--- a/drivers/platform/x86/dell/dell_rbu.c
+++ b/drivers/platform/x86/dell/dell_rbu.c
@@ -292,7 +292,7 @@ static int packet_read_list(char *data, size_t * pread_length)
 	remaining_bytes = *pread_length;
 	bytes_read = rbu_data.packet_read_count;
 
-	list_for_each_entry(newpacket, (&packet_data_head.list)->next, list) {
+	list_for_each_entry(newpacket, &packet_data_head.list, list) {
 		bytes_copied = do_packet_read(pdest, newpacket,
 			remaining_bytes, bytes_read, &temp_count);
 		remaining_bytes -= bytes_copied;
@@ -315,7 +315,7 @@ static void packet_empty_list(void)
 {
 	struct packet_data *newpacket, *tmp;
 
-	list_for_each_entry_safe(newpacket, tmp, (&packet_data_head.list)->next, list) {
+	list_for_each_entry_safe(newpacket, tmp, &packet_data_head.list, list) {
 		list_del(&newpacket->list);
 
 		/*

From f4b0fa38d5fefe9aed6ed831f3bd3538c168ee19 Mon Sep 17 00:00:00 2001
From: Stuart Hayes <stuart.w.hayes@gmail.com>
Date: Mon, 9 Jun 2025 13:46:58 -0500
Subject: [PATCH 0134/1334] platform/x86: dell_rbu: Stop overwriting data
 buffer
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The dell_rbu driver will use memset() to clear the data held by each
packet when it is no longer needed (when the driver is unloaded, the
packet size is changed, etc).

The amount of memory that is cleared (before this patch) is the normal
packet size. However, the last packet in the list may be smaller.

Fix this to only clear the memory actually used by each packet, to prevent
it from writing past the end of data buffer.

Because the packet data buffers are allocated with __get_free_pages() (in
page-sized increments), this bug could only result in a buffer being
overwritten when a packet size larger than one page is used. The only user
of the dell_rbu module should be the Dell BIOS update program, which uses
a packet size of 4096, so no issues should be seen without the patch, it
just blocks the possiblity.

Fixes: 6c54c28e69f2 ("[PATCH] dell_rbu: new Dell BIOS update driver")
Signed-off-by: Stuart Hayes <stuart.w.hayes@gmail.com>
Link: https://lore.kernel.org/r/20250609184659.7210-5-stuart.w.hayes@gmail.com
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/dell/dell_rbu.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/platform/x86/dell/dell_rbu.c b/drivers/platform/x86/dell/dell_rbu.c
index 722979b19e0e..eb3534ff8dad 100644
--- a/drivers/platform/x86/dell/dell_rbu.c
+++ b/drivers/platform/x86/dell/dell_rbu.c
@@ -322,7 +322,7 @@ static void packet_empty_list(void)
 		 * zero out the RBU packet memory before freeing
 		 * to make sure there are no stale RBU packets left in memory
 		 */
-		memset(newpacket->data, 0, rbu_data.packetsize);
+		memset(newpacket->data, 0, newpacket->length);
 		set_memory_wb((unsigned long)newpacket->data,
 			1 << newpacket->ordernum);
 		free_pages((unsigned long) newpacket->data,

From ea7af94548159c57747aa8e86408a19192a1e1fe Mon Sep 17 00:00:00 2001
From: Stuart Hayes <stuart.w.hayes@gmail.com>
Date: Mon, 9 Jun 2025 13:46:59 -0500
Subject: [PATCH 0135/1334] platform/x86: dell_rbu: Bump version
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Bump the module version.

Signed-off-by: Stuart Hayes <stuart.w.hayes@gmail.com>
Link: https://lore.kernel.org/r/20250609184659.7210-6-stuart.w.hayes@gmail.com
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/dell/dell_rbu.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/platform/x86/dell/dell_rbu.c b/drivers/platform/x86/dell/dell_rbu.c
index eb3534ff8dad..9dd9f2cb074f 100644
--- a/drivers/platform/x86/dell/dell_rbu.c
+++ b/drivers/platform/x86/dell/dell_rbu.c
@@ -45,7 +45,7 @@
 MODULE_AUTHOR("Abhay Salunke <abhay_salunke@dell.com>");
 MODULE_DESCRIPTION("Driver for updating BIOS image on DELL systems");
 MODULE_LICENSE("GPL");
-MODULE_VERSION("3.2");
+MODULE_VERSION("3.3");
 
 #define BIOS_SCAN_LIMIT 0xffffffff
 #define MAX_IMAGE_LENGTH 16

From 3fbf25ecf8b7b524b4774b427657d30a24e696ef Mon Sep 17 00:00:00 2001
From: Hans de Goede <hansg@kernel.org>
Date: Mon, 9 Jun 2025 16:35:57 +0200
Subject: [PATCH 0136/1334] MAINTAINERS: .mailmap: Update Hans de Goede's email
 address
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

I'm moving all my kernel work over to using my kernel.org email address.
Update .mailmap and MAINTAINER entries still using hdegoede@redhat.com.

Signed-off-by: Hans de Goede <hansg@kernel.org>
Link: https://lore.kernel.org/r/20250609143558.42941-2-hansg@kernel.org
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 .mailmap    |  1 +
 MAINTAINERS | 72 ++++++++++++++++++++++++++---------------------------
 2 files changed, 37 insertions(+), 36 deletions(-)

diff --git a/.mailmap b/.mailmap
index c8a21d72241f..645294560b19 100644
--- a/.mailmap
+++ b/.mailmap
@@ -282,6 +282,7 @@ Gustavo Padovan <gustavo@las.ic.unicamp.br>
 Gustavo Padovan <padovan@profusion.mobi>
 Hamza Mahfooz <hamzamahfooz@linux.microsoft.com> <hamza.mahfooz@amd.com>
 Hanjun Guo <guohanjun@huawei.com> <hanjun.guo@linaro.org>
+Hans de Goede <hansg@kernel.org> <hdegoede@redhat.com>
 Hans Verkuil <hverkuil@xs4all.nl> <hansverk@cisco.com>
 Hans Verkuil <hverkuil@xs4all.nl> <hverkuil-cisco@xs4all.nl>
 Harry Yoo <harry.yoo@oracle.com> <42.hyeyoo@gmail.com>
diff --git a/MAINTAINERS b/MAINTAINERS
index a92290fffa16..e8f3dc93a569 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -207,7 +207,7 @@ X:	arch/*/include/uapi/
 X:	include/uapi/
 
 ABIT UGURU 1,2 HARDWARE MONITOR DRIVER
-M:	Hans de Goede <hdegoede@redhat.com>
+M:	Hans de Goede <hansg@kernel.org>
 L:	linux-hwmon@vger.kernel.org
 S:	Maintained
 F:	drivers/hwmon/abituguru.c
@@ -371,7 +371,7 @@ S:	Maintained
 F:	drivers/platform/x86/quickstart.c
 
 ACPI SERIAL MULTI INSTANTIATE DRIVER
-M:	Hans de Goede <hdegoede@redhat.com>
+M:	Hans de Goede <hansg@kernel.org>
 L:	platform-driver-x86@vger.kernel.org
 S:	Maintained
 F:	drivers/platform/x86/serial-multi-instantiate.c
@@ -3551,7 +3551,7 @@ F:	arch/arm64/boot/Makefile
 F:	scripts/make_fit.py
 
 ARM64 PLATFORM DRIVERS
-M:	Hans de Goede <hdegoede@redhat.com>
+M:	Hans de Goede <hansg@kernel.org>
 M:	Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
 R:	Bryan O'Donoghue <bryan.odonoghue@linaro.org>
 L:	platform-driver-x86@vger.kernel.org
@@ -3712,7 +3712,7 @@ F:	drivers/platform/x86/asus*.c
 F:	drivers/platform/x86/eeepc*.c
 
 ASUS TF103C DOCK DRIVER
-M:	Hans de Goede <hdegoede@redhat.com>
+M:	Hans de Goede <hansg@kernel.org>
 L:	platform-driver-x86@vger.kernel.org
 S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/pdx86/platform-drivers-x86.git
@@ -5613,14 +5613,14 @@ T:	git git://git.kernel.org/pub/scm/linux/kernel/git/peter.chen/usb.git
 F:	drivers/usb/chipidea/
 
 CHIPONE ICN8318 I2C TOUCHSCREEN DRIVER
-M:	Hans de Goede <hdegoede@redhat.com>
+M:	Hans de Goede <hansg@kernel.org>
 L:	linux-input@vger.kernel.org
 S:	Maintained
 F:	Documentation/devicetree/bindings/input/touchscreen/chipone,icn8318.yaml
 F:	drivers/input/touchscreen/chipone_icn8318.c
 
 CHIPONE ICN8505 I2C TOUCHSCREEN DRIVER
-M:	Hans de Goede <hdegoede@redhat.com>
+M:	Hans de Goede <hansg@kernel.org>
 L:	linux-input@vger.kernel.org
 S:	Maintained
 F:	drivers/input/touchscreen/chipone_icn8505.c
@@ -6917,7 +6917,7 @@ F:	include/dt-bindings/pmu/exynos_ppmu.h
 F:	include/linux/devfreq-event.h
 
 DEVICE RESOURCE MANAGEMENT HELPERS
-M:	Hans de Goede <hdegoede@redhat.com>
+M:	Hans de Goede <hansg@kernel.org>
 R:	Matti Vaittinen <mazziesaccount@gmail.com>
 S:	Maintained
 F:	include/linux/devm-helpers.h
@@ -7516,7 +7516,7 @@ F:	drivers/gpu/drm/gud/
 F:	include/drm/gud.h
 
 DRM DRIVER FOR GRAIN MEDIA GM12U320 PROJECTORS
-M:	Hans de Goede <hdegoede@redhat.com>
+M:	Hans de Goede <hansg@kernel.org>
 S:	Maintained
 T:	git https://gitlab.freedesktop.org/drm/misc/kernel.git
 F:	drivers/gpu/drm/tiny/gm12u320.c
@@ -7916,7 +7916,7 @@ F:	drivers/gpu/drm/ci/xfails/vkms*
 F:	drivers/gpu/drm/vkms/
 
 DRM DRIVER FOR VIRTUALBOX VIRTUAL GPU
-M:	Hans de Goede <hdegoede@redhat.com>
+M:	Hans de Goede <hansg@kernel.org>
 L:	dri-devel@lists.freedesktop.org
 S:	Maintained
 T:	git https://gitlab.freedesktop.org/drm/misc/kernel.git
@@ -8317,7 +8317,7 @@ F:	drivers/gpu/drm/panel/
 F:	include/drm/drm_panel.h
 
 DRM PRIVACY-SCREEN CLASS
-M:	Hans de Goede <hdegoede@redhat.com>
+M:	Hans de Goede <hansg@kernel.org>
 L:	dri-devel@lists.freedesktop.org
 S:	Maintained
 T:	git https://gitlab.freedesktop.org/drm/misc/kernel.git
@@ -10221,7 +10221,7 @@ S:	Maintained
 F:	Documentation/devicetree/bindings/connector/gocontroll,moduline-module-slot.yaml
 
 GOODIX TOUCHSCREEN
-M:	Hans de Goede <hdegoede@redhat.com>
+M:	Hans de Goede <hansg@kernel.org>
 L:	linux-input@vger.kernel.org
 S:	Maintained
 F:	drivers/input/touchscreen/goodix*
@@ -10260,7 +10260,7 @@ F:	include/dt-bindings/clock/google,gs101.h
 K:	[gG]oogle.?[tT]ensor
 
 GPD POCKET FAN DRIVER
-M:	Hans de Goede <hdegoede@redhat.com>
+M:	Hans de Goede <hansg@kernel.org>
 L:	platform-driver-x86@vger.kernel.org
 S:	Maintained
 F:	drivers/platform/x86/gpd-pocket-fan.c
@@ -11421,7 +11421,7 @@ F:	drivers/i2c/busses/i2c-via.c
 F:	drivers/i2c/busses/i2c-viapro.c
 
 I2C/SMBUS INTEL CHT WHISKEY COVE PMIC DRIVER
-M:	Hans de Goede <hdegoede@redhat.com>
+M:	Hans de Goede <hansg@kernel.org>
 L:	linux-i2c@vger.kernel.org
 S:	Maintained
 F:	drivers/i2c/busses/i2c-cht-wc.c
@@ -12011,13 +12011,13 @@ S:	Supported
 F:	sound/soc/intel/
 
 INTEL ATOMISP2 DUMMY / POWER-MANAGEMENT DRIVER
-M:	Hans de Goede <hdegoede@redhat.com>
+M:	Hans de Goede <hansg@kernel.org>
 L:	platform-driver-x86@vger.kernel.org
 S:	Maintained
 F:	drivers/platform/x86/intel/atomisp2/pm.c
 
 INTEL ATOMISP2 LED DRIVER
-M:	Hans de Goede <hdegoede@redhat.com>
+M:	Hans de Goede <hansg@kernel.org>
 L:	platform-driver-x86@vger.kernel.org
 S:	Maintained
 F:	drivers/platform/x86/intel/atomisp2/led.c
@@ -13678,7 +13678,7 @@ S:	Maintained
 F:	drivers/platform/x86/lenovo-wmi-hotkey-utilities.c
 
 LETSKETCH HID TABLET DRIVER
-M:	Hans de Goede <hdegoede@redhat.com>
+M:	Hans de Goede <hansg@kernel.org>
 L:	linux-input@vger.kernel.org
 S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/hid/hid.git
@@ -13728,7 +13728,7 @@ F:	drivers/ata/sata_gemini.c
 F:	drivers/ata/sata_gemini.h
 
 LIBATA SATA AHCI PLATFORM devices support
-M:	Hans de Goede <hdegoede@redhat.com>
+M:	Hans de Goede <hansg@kernel.org>
 L:	linux-ide@vger.kernel.org
 S:	Maintained
 F:	drivers/ata/ahci_platform.c
@@ -14098,7 +14098,7 @@ F:	Documentation/admin-guide/ldm.rst
 F:	block/partitions/ldm.*
 
 LOGITECH HID GAMING KEYBOARDS
-M:	Hans de Goede <hdegoede@redhat.com>
+M:	Hans de Goede <hansg@kernel.org>
 L:	linux-input@vger.kernel.org
 S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/hid/hid.git
@@ -14780,7 +14780,7 @@ F:	Documentation/devicetree/bindings/power/supply/maxim,max17040.yaml
 F:	drivers/power/supply/max17040_battery.c
 
 MAXIM MAX17042 FAMILY FUEL GAUGE DRIVERS
-R:	Hans de Goede <hdegoede@redhat.com>
+R:	Hans de Goede <hansg@kernel.org>
 R:	Krzysztof Kozlowski <krzk@kernel.org>
 R:	Marek Szyprowski <m.szyprowski@samsung.com>
 R:	Sebastian Krzyszkowiak <sebastian.krzyszkowiak@puri.sm>
@@ -15582,7 +15582,7 @@ Q:	https://patchwork.kernel.org/project/netdevbpf/list/
 F:	drivers/net/ethernet/mellanox/mlxfw/
 
 MELLANOX HARDWARE PLATFORM SUPPORT
-M:	Hans de Goede <hdegoede@redhat.com>
+M:	Hans de Goede <hansg@kernel.org>
 M:	Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
 M:	Vadim Pasternak <vadimp@nvidia.com>
 L:	platform-driver-x86@vger.kernel.org
@@ -16538,7 +16538,7 @@ S:	Maintained
 F:	drivers/platform/surface/surface_gpe.c
 
 MICROSOFT SURFACE HARDWARE PLATFORM SUPPORT
-M:	Hans de Goede <hdegoede@redhat.com>
+M:	Hans de Goede <hansg@kernel.org>
 M:	Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
 M:	Maximilian Luz <luzmaximilian@gmail.com>
 L:	platform-driver-x86@vger.kernel.org
@@ -17706,7 +17706,7 @@ F:	tools/include/nolibc/
 F:	tools/testing/selftests/nolibc/
 
 NOVATEK NVT-TS I2C TOUCHSCREEN DRIVER
-M:	Hans de Goede <hdegoede@redhat.com>
+M:	Hans de Goede <hansg@kernel.org>
 L:	linux-input@vger.kernel.org
 S:	Maintained
 F:	Documentation/devicetree/bindings/input/touchscreen/novatek,nvt-ts.yaml
@@ -22708,7 +22708,7 @@ K:	fu[57]40
 K:	[^@]sifive
 
 SILEAD TOUCHSCREEN DRIVER
-M:	Hans de Goede <hdegoede@redhat.com>
+M:	Hans de Goede <hansg@kernel.org>
 L:	linux-input@vger.kernel.org
 L:	platform-driver-x86@vger.kernel.org
 S:	Maintained
@@ -22741,7 +22741,7 @@ F:	Documentation/devicetree/bindings/i3c/silvaco,i3c-master.yaml
 F:	drivers/i3c/master/svc-i3c-master.c
 
 SIMPLEFB FB DRIVER
-M:	Hans de Goede <hdegoede@redhat.com>
+M:	Hans de Goede <hansg@kernel.org>
 L:	linux-fbdev@vger.kernel.org
 S:	Maintained
 F:	Documentation/devicetree/bindings/display/simple-framebuffer.yaml
@@ -22870,7 +22870,7 @@ F:	Documentation/hwmon/emc2103.rst
 F:	drivers/hwmon/emc2103.c
 
 SMSC SCH5627 HARDWARE MONITOR DRIVER
-M:	Hans de Goede <hdegoede@redhat.com>
+M:	Hans de Goede <hansg@kernel.org>
 L:	linux-hwmon@vger.kernel.org
 S:	Supported
 F:	Documentation/hwmon/sch5627.rst
@@ -23525,7 +23525,7 @@ S:	Supported
 F:	Documentation/process/stable-kernel-rules.rst
 
 STAGING - ATOMISP DRIVER
-M:	Hans de Goede <hdegoede@redhat.com>
+M:	Hans de Goede <hansg@kernel.org>
 M:	Mauro Carvalho Chehab <mchehab@kernel.org>
 R:	Sakari Ailus <sakari.ailus@linux.intel.com>
 L:	linux-media@vger.kernel.org
@@ -23822,7 +23822,7 @@ F:	arch/m68k/sun3*/
 F:	drivers/net/ethernet/i825xx/sun3*
 
 SUN4I LOW RES ADC ATTACHED TABLET KEYS DRIVER
-M:	Hans de Goede <hdegoede@redhat.com>
+M:	Hans de Goede <hansg@kernel.org>
 L:	linux-input@vger.kernel.org
 S:	Maintained
 F:	Documentation/devicetree/bindings/input/allwinner,sun4i-a10-lradc-keys.yaml
@@ -25590,7 +25590,7 @@ F:	Documentation/hid/hiddev.rst
 F:	drivers/hid/usbhid/
 
 USB INTEL XHCI ROLE MUX DRIVER
-M:	Hans de Goede <hdegoede@redhat.com>
+M:	Hans de Goede <hansg@kernel.org>
 L:	linux-usb@vger.kernel.org
 S:	Maintained
 F:	drivers/usb/roles/intel-xhci-usb-role-switch.c
@@ -25781,7 +25781,7 @@ F:	Documentation/firmware-guide/acpi/intel-pmc-mux.rst
 F:	drivers/usb/typec/mux/intel_pmc_mux.c
 
 USB TYPEC PI3USB30532 MUX DRIVER
-M:	Hans de Goede <hdegoede@redhat.com>
+M:	Hans de Goede <hansg@kernel.org>
 L:	linux-usb@vger.kernel.org
 S:	Maintained
 F:	drivers/usb/typec/mux/pi3usb30532.c
@@ -25810,7 +25810,7 @@ F:	drivers/usb/host/uhci*
 
 USB VIDEO CLASS
 M:	Laurent Pinchart <laurent.pinchart@ideasonboard.com>
-M:	Hans de Goede <hdegoede@redhat.com>
+M:	Hans de Goede <hansg@kernel.org>
 L:	linux-media@vger.kernel.org
 S:	Maintained
 W:	http://www.ideasonboard.org/uvc/
@@ -26341,7 +26341,7 @@ F:	include/uapi/linux/virtio_snd.h
 F:	sound/virtio/*
 
 VIRTUAL BOX GUEST DEVICE DRIVER
-M:	Hans de Goede <hdegoede@redhat.com>
+M:	Hans de Goede <hansg@kernel.org>
 M:	Arnd Bergmann <arnd@arndb.de>
 M:	Greg Kroah-Hartman <gregkh@linuxfoundation.org>
 S:	Maintained
@@ -26350,7 +26350,7 @@ F:	include/linux/vbox_utils.h
 F:	include/uapi/linux/vbox*.h
 
 VIRTUAL BOX SHARED FOLDER VFS DRIVER
-M:	Hans de Goede <hdegoede@redhat.com>
+M:	Hans de Goede <hansg@kernel.org>
 L:	linux-fsdevel@vger.kernel.org
 S:	Maintained
 F:	fs/vboxsf/*
@@ -26604,7 +26604,7 @@ F:	drivers/mmc/host/wbsd.*
 
 WACOM PROTOCOL 4 SERIAL TABLETS
 M:	Julian Squires <julian@cipht.net>
-M:	Hans de Goede <hdegoede@redhat.com>
+M:	Hans de Goede <hansg@kernel.org>
 L:	linux-input@vger.kernel.org
 S:	Maintained
 F:	drivers/input/tablet/wacom_serial4.c
@@ -26771,7 +26771,7 @@ F:	include/linux/wwan.h
 F:	include/uapi/linux/wwan.h
 
 X-POWERS AXP288 PMIC DRIVERS
-M:	Hans de Goede <hdegoede@redhat.com>
+M:	Hans de Goede <hansg@kernel.org>
 S:	Maintained
 F:	drivers/acpi/pmic/intel_pmic_xpower.c
 N:	axp288
@@ -26863,14 +26863,14 @@ T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git x86/mm
 F:	arch/x86/mm/
 
 X86 PLATFORM ANDROID TABLETS DSDT FIXUP DRIVER
-M:	Hans de Goede <hdegoede@redhat.com>
+M:	Hans de Goede <hansg@kernel.org>
 L:	platform-driver-x86@vger.kernel.org
 S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/pdx86/platform-drivers-x86.git
 F:	drivers/platform/x86/x86-android-tablets/
 
 X86 PLATFORM DRIVERS
-M:	Hans de Goede <hdegoede@redhat.com>
+M:	Hans de Goede <hansg@kernel.org>
 M:	Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
 L:	platform-driver-x86@vger.kernel.org
 S:	Maintained

From e0d4a0f1d066f14522049e827107a577444d9183 Mon Sep 17 00:00:00 2001
From: Yang Shen <shenyang39@huawei.com>
Date: Thu, 29 May 2025 11:40:23 +0800
Subject: [PATCH 0137/1334] MAINTAINERS: Update HiSilicon GPIO driver
 maintainer

Add Yang Shen as the maintainer of the HiSilicon GPIO driver,
replacing Jay Fang.

Signed-off-by: Yang Shen <shenyang39@huawei.com>
Reviewed-by: Jay Fang <f.fangjian@huawei.com>
Link: https://lore.kernel.org/r/20250529034023.3780376-1-shenyang39@huawei.com
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
---
 MAINTAINERS | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index a92290fffa16..04734120b522 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -10839,7 +10839,7 @@ S:	Maintained
 F:	drivers/dma/hisi_dma.c
 
 HISILICON GPIO DRIVER
-M:	Jay Fang <f.fangjian@huawei.com>
+M:	Yang Shen <shenyang39@huawei.com>
 L:	linux-gpio@vger.kernel.org
 S:	Maintained
 F:	Documentation/devicetree/bindings/gpio/hisilicon,ascend910-gpio.yaml

From f17d5b90947a7b89a27913abf47cb0c7063b3430 Mon Sep 17 00:00:00 2001
From: Casey Connolly <casey.connolly@linaro.org>
Date: Fri, 23 May 2025 13:55:34 +0200
Subject: [PATCH 0138/1334] arm64: defconfig: update renamed PHY_SNPS_EUSB2

This config option was renamed, update the defconfig to match.

Fixes: 8d3b5f637546 ("phy: move phy-qcom-snps-eusb2 out of its vendor sub-directory")
Signed-off-by: Casey Connolly <casey.connolly@linaro.org>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
Link: https://lore.kernel.org/r/20250523115630.459249-3-casey.connolly@linaro.org
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
---
 arch/arm64/configs/defconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig
index 897fc686e6a9..7e04a2905ce4 100644
--- a/arch/arm64/configs/defconfig
+++ b/arch/arm64/configs/defconfig
@@ -1573,6 +1573,7 @@ CONFIG_RESET_QCOM_AOSS=y
 CONFIG_RESET_QCOM_PDC=m
 CONFIG_RESET_RZG2L_USBPHY_CTRL=y
 CONFIG_RESET_TI_SCI=y
+CONFIG_PHY_SNPS_EUSB2=m
 CONFIG_PHY_XGENE=y
 CONFIG_PHY_CAN_TRANSCEIVER=m
 CONFIG_PHY_NXP_PTN3222=m
@@ -1597,7 +1598,6 @@ CONFIG_PHY_QCOM_EDP=m
 CONFIG_PHY_QCOM_PCIE2=m
 CONFIG_PHY_QCOM_QMP=m
 CONFIG_PHY_QCOM_QUSB2=m
-CONFIG_PHY_QCOM_SNPS_EUSB2=m
 CONFIG_PHY_QCOM_EUSB2_REPEATER=m
 CONFIG_PHY_QCOM_M31_USB=m
 CONFIG_PHY_QCOM_USB_HS=m

From 8d2c2fa2209e83d0eb10f7330d8a0bbdc1df32ff Mon Sep 17 00:00:00 2001
From: Tudor Ambarus <tudor.ambarus@linaro.org>
Date: Fri, 6 Jun 2025 10:45:37 +0000
Subject: [PATCH 0139/1334] firmware: exynos-acpm: fix timeouts on xfers
 handling
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The mailbox framework has a single inflight request at a time. If
a request is sent while another is still active, it will be queued
to the mailbox core ring buffer.

ACPM protocol did not serialize the calls to the mailbox subsystem so we
could start the timeout ticks in parallel for multiple requests, while
just one was being inflight.

Consider a hypothetical case where the xfer timeout is 100ms and an ACPM
transaction takes 90ms:
      | 0ms: Message #0 is queued in mailbox layer and sent out, then sits
      |      at acpm_dequeue_by_polling() with a timeout of 100ms
      | 1ms: Message #1 is queued in mailbox layer but not sent out yet.
      |      Since send_message() doesn't block, it also sits at
      |      acpm_dequeue_by_polling() with a timeout of 100ms
      |  ...
      | 90ms: Message #0 is completed, txdone is called and message #1 is sent
      | 101ms: Message #1 times out since the count started at 1ms. Even though
      |       it has only been inflight for 11ms.

Fix the problem by moving mbox_send_message() and mbox_client_txdone()
immediately after the message has been written to the TX queue and while
still keeping the ACPM TX queue lock. We thus tie together the TX write
with the doorbell ring and mark the TX as done after the doorbell has
been rung. This guarantees that the doorbell has been rang before
starting the timeout ticks. We should also see some performance
improvement as we no longer wait to receive a response before ringing
the doorbell for the next request, so the ACPM firmware shall be able to
drain faster the TX queue. Another benefit is that requests are no
longer able to ring the doorbell one for the other, so it eases
debugging. Finally, the mailbox software queue will always contain a
single doorbell request due to the serialization done at the ACPM TX
queue level. Protocols like ACPM, that handle their own hardware queues
need a passthrough mailbox API, where they are able to just ring the
doorbell or flip a bit directly into the mailbox controller. The mailbox
software queue mechanism, the locking done into the mailbox core is not
really needed, so hopefully this lays the foundation for a passthrough
mailbox API.

Reported-by: André Draszik <andre.draszik@linaro.org>
Fixes: a88927b534ba ("firmware: add Exynos ACPM protocol driver")
Signed-off-by: Tudor Ambarus <tudor.ambarus@linaro.org>
Link: https://lore.kernel.org/r/20250606-acpm-timeout-v2-1-306b1aa07a6c@linaro.org
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
---
 drivers/firmware/samsung/exynos-acpm.c | 27 ++++++++++----------------
 1 file changed, 10 insertions(+), 17 deletions(-)

diff --git a/drivers/firmware/samsung/exynos-acpm.c b/drivers/firmware/samsung/exynos-acpm.c
index e02f14f4bd7c..3a69fe3234c7 100644
--- a/drivers/firmware/samsung/exynos-acpm.c
+++ b/drivers/firmware/samsung/exynos-acpm.c
@@ -430,6 +430,9 @@ int acpm_do_xfer(const struct acpm_handle *handle, const struct acpm_xfer *xfer)
 		return -EOPNOTSUPP;
 	}
 
+	msg.chan_id = xfer->acpm_chan_id;
+	msg.chan_type = EXYNOS_MBOX_CHAN_TYPE_DOORBELL;
+
 	scoped_guard(mutex, &achan->tx_lock) {
 		tx_front = readl(achan->tx.front);
 		idx = (tx_front + 1) % achan->qlen;
@@ -446,25 +449,15 @@ int acpm_do_xfer(const struct acpm_handle *handle, const struct acpm_xfer *xfer)
 
 		/* Advance TX front. */
 		writel(idx, achan->tx.front);
+
+		ret = mbox_send_message(achan->chan, (void *)&msg);
+		if (ret < 0)
+			return ret;
+
+		mbox_client_txdone(achan->chan, 0);
 	}
 
-	msg.chan_id = xfer->acpm_chan_id;
-	msg.chan_type = EXYNOS_MBOX_CHAN_TYPE_DOORBELL;
-	ret = mbox_send_message(achan->chan, (void *)&msg);
-	if (ret < 0)
-		return ret;
-
-	ret = acpm_wait_for_message_response(achan, xfer);
-
-	/*
-	 * NOTE: we might prefer not to need the mailbox ticker to manage the
-	 * transfer queueing since the protocol layer queues things by itself.
-	 * Unfortunately, we have to kick the mailbox framework after we have
-	 * received our message.
-	 */
-	mbox_client_txdone(achan->chan, ret);
-
-	return ret;
+	return acpm_wait_for_message_response(achan, xfer);
 }
 
 /**

From c0317ad44f45b3c1f0ff46a4e28d14c7bccdedf4 Mon Sep 17 00:00:00 2001
From: Gabriel Dalimonte <gabriel.dalimonte@gmail.com>
Date: Sun, 1 Jun 2025 12:45:36 -0400
Subject: [PATCH 0140/1334] drm/vc4: fix infinite EPROBE_DEFER loop

`vc4_hdmi_audio_init` calls `devm_snd_dmaengine_pcm_register` which may
return EPROBE_DEFER. Calling `drm_connector_hdmi_audio_init` adds a
child device. The driver model docs[1] state that adding a child device
prior to returning EPROBE_DEFER may result in an infinite loop.

[1] https://www.kernel.org/doc/html/v6.14/driver-api/driver-model/driver.html

Fixes: 9640f1437a88 ("drm/vc4: hdmi: switch to using generic HDMI Codec infrastructure")
Signed-off-by: Gabriel Dalimonte <gabriel.dalimonte@gmail.com>
Link: https://lore.kernel.org/r/20250601-vc4-audio-inf-probe-v2-1-9ad43c7b6147@gmail.com
Signed-off-by: Maxime Ripard <mripard@kernel.org>
---
 drivers/gpu/drm/vc4/vc4_hdmi.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/vc4/vc4_hdmi.c b/drivers/gpu/drm/vc4/vc4_hdmi.c
index a29a6ef266f9..163d092bd973 100644
--- a/drivers/gpu/drm/vc4/vc4_hdmi.c
+++ b/drivers/gpu/drm/vc4/vc4_hdmi.c
@@ -560,12 +560,6 @@ static int vc4_hdmi_connector_init(struct drm_device *dev,
 	if (ret)
 		return ret;
 
-	ret = drm_connector_hdmi_audio_init(connector, dev->dev,
-					    &vc4_hdmi_audio_funcs,
-					    8, false, -1);
-	if (ret)
-		return ret;
-
 	drm_connector_helper_add(connector, &vc4_hdmi_connector_helper_funcs);
 
 	/*
@@ -2291,6 +2285,12 @@ static int vc4_hdmi_audio_init(struct vc4_hdmi *vc4_hdmi)
 		return ret;
 	}
 
+	ret = drm_connector_hdmi_audio_init(&vc4_hdmi->connector, dev,
+					    &vc4_hdmi_audio_funcs, 8, false,
+					    -1);
+	if (ret)
+		return ret;
+
 	dai_link->cpus		= &vc4_hdmi->audio.cpu;
 	dai_link->codecs	= &vc4_hdmi->audio.codec;
 	dai_link->platforms	= &vc4_hdmi->audio.platform;

From 4823a58093c6dfa20df62b5c18da613621b9716e Mon Sep 17 00:00:00 2001
From: Viresh Kumar <viresh.kumar@linaro.org>
Date: Tue, 10 Jun 2025 16:38:56 +0530
Subject: [PATCH 0141/1334] cpufreq: Convert `/// SAFETY` lines to `# Safety`
 sections

Replace `/// SAFETY` comments in doc comments with proper `# Safety`
sections, as per rustdoc conventions.

Also mark the C FFI callbacks as `unsafe` to correctly reflect their
safety requirements.

Reported-by: Miguel Ojeda <ojeda@kernel.org>
Closes: https://github.com/Rust-for-Linux/linux/issues/1169
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
---
 rust/kernel/cpufreq.rs | 146 ++++++++++++++++++++++++++++++-----------
 1 file changed, 109 insertions(+), 37 deletions(-)

diff --git a/rust/kernel/cpufreq.rs b/rust/kernel/cpufreq.rs
index b0a9c6182aec..9b995f18aac6 100644
--- a/rust/kernel/cpufreq.rs
+++ b/rust/kernel/cpufreq.rs
@@ -1055,8 +1055,11 @@ impl<T: Driver> Registration<T> {
 impl<T: Driver> Registration<T> {
     /// Driver's `init` callback.
     ///
-    /// SAFETY: Called from C. Inputs must be valid pointers.
-    extern "C" fn init_callback(ptr: *mut bindings::cpufreq_policy) -> kernel::ffi::c_int {
+    /// # Safety
+    ///
+    /// - This function may only be called from the cpufreq C infrastructure.
+    /// - The pointer arguments must be valid pointers.
+    unsafe extern "C" fn init_callback(ptr: *mut bindings::cpufreq_policy) -> kernel::ffi::c_int {
         from_result(|| {
             // SAFETY: The `ptr` is guaranteed to be valid by the contract with the C code for the
             // lifetime of `policy`.
@@ -1070,8 +1073,11 @@ impl<T: Driver> Registration<T> {
 
     /// Driver's `exit` callback.
     ///
-    /// SAFETY: Called from C. Inputs must be valid pointers.
-    extern "C" fn exit_callback(ptr: *mut bindings::cpufreq_policy) {
+    /// # Safety
+    ///
+    /// - This function may only be called from the cpufreq C infrastructure.
+    /// - The pointer arguments must be valid pointers.
+    unsafe extern "C" fn exit_callback(ptr: *mut bindings::cpufreq_policy) {
         // SAFETY: The `ptr` is guaranteed to be valid by the contract with the C code for the
         // lifetime of `policy`.
         let policy = unsafe { Policy::from_raw_mut(ptr) };
@@ -1082,8 +1088,11 @@ impl<T: Driver> Registration<T> {
 
     /// Driver's `online` callback.
     ///
-    /// SAFETY: Called from C. Inputs must be valid pointers.
-    extern "C" fn online_callback(ptr: *mut bindings::cpufreq_policy) -> kernel::ffi::c_int {
+    /// # Safety
+    ///
+    /// - This function may only be called from the cpufreq C infrastructure.
+    /// - The pointer arguments must be valid pointers.
+    unsafe extern "C" fn online_callback(ptr: *mut bindings::cpufreq_policy) -> kernel::ffi::c_int {
         from_result(|| {
             // SAFETY: The `ptr` is guaranteed to be valid by the contract with the C code for the
             // lifetime of `policy`.
@@ -1094,8 +1103,13 @@ impl<T: Driver> Registration<T> {
 
     /// Driver's `offline` callback.
     ///
-    /// SAFETY: Called from C. Inputs must be valid pointers.
-    extern "C" fn offline_callback(ptr: *mut bindings::cpufreq_policy) -> kernel::ffi::c_int {
+    /// # Safety
+    ///
+    /// - This function may only be called from the cpufreq C infrastructure.
+    /// - The pointer arguments must be valid pointers.
+    unsafe extern "C" fn offline_callback(
+        ptr: *mut bindings::cpufreq_policy,
+    ) -> kernel::ffi::c_int {
         from_result(|| {
             // SAFETY: The `ptr` is guaranteed to be valid by the contract with the C code for the
             // lifetime of `policy`.
@@ -1106,8 +1120,13 @@ impl<T: Driver> Registration<T> {
 
     /// Driver's `suspend` callback.
     ///
-    /// SAFETY: Called from C. Inputs must be valid pointers.
-    extern "C" fn suspend_callback(ptr: *mut bindings::cpufreq_policy) -> kernel::ffi::c_int {
+    /// # Safety
+    ///
+    /// - This function may only be called from the cpufreq C infrastructure.
+    /// - The pointer arguments must be valid pointers.
+    unsafe extern "C" fn suspend_callback(
+        ptr: *mut bindings::cpufreq_policy,
+    ) -> kernel::ffi::c_int {
         from_result(|| {
             // SAFETY: The `ptr` is guaranteed to be valid by the contract with the C code for the
             // lifetime of `policy`.
@@ -1118,8 +1137,11 @@ impl<T: Driver> Registration<T> {
 
     /// Driver's `resume` callback.
     ///
-    /// SAFETY: Called from C. Inputs must be valid pointers.
-    extern "C" fn resume_callback(ptr: *mut bindings::cpufreq_policy) -> kernel::ffi::c_int {
+    /// # Safety
+    ///
+    /// - This function may only be called from the cpufreq C infrastructure.
+    /// - The pointer arguments must be valid pointers.
+    unsafe extern "C" fn resume_callback(ptr: *mut bindings::cpufreq_policy) -> kernel::ffi::c_int {
         from_result(|| {
             // SAFETY: The `ptr` is guaranteed to be valid by the contract with the C code for the
             // lifetime of `policy`.
@@ -1130,8 +1152,11 @@ impl<T: Driver> Registration<T> {
 
     /// Driver's `ready` callback.
     ///
-    /// SAFETY: Called from C. Inputs must be valid pointers.
-    extern "C" fn ready_callback(ptr: *mut bindings::cpufreq_policy) {
+    /// # Safety
+    ///
+    /// - This function may only be called from the cpufreq C infrastructure.
+    /// - The pointer arguments must be valid pointers.
+    unsafe extern "C" fn ready_callback(ptr: *mut bindings::cpufreq_policy) {
         // SAFETY: The `ptr` is guaranteed to be valid by the contract with the C code for the
         // lifetime of `policy`.
         let policy = unsafe { Policy::from_raw_mut(ptr) };
@@ -1140,8 +1165,13 @@ impl<T: Driver> Registration<T> {
 
     /// Driver's `verify` callback.
     ///
-    /// SAFETY: Called from C. Inputs must be valid pointers.
-    extern "C" fn verify_callback(ptr: *mut bindings::cpufreq_policy_data) -> kernel::ffi::c_int {
+    /// # Safety
+    ///
+    /// - This function may only be called from the cpufreq C infrastructure.
+    /// - The pointer arguments must be valid pointers.
+    unsafe extern "C" fn verify_callback(
+        ptr: *mut bindings::cpufreq_policy_data,
+    ) -> kernel::ffi::c_int {
         from_result(|| {
             // SAFETY: The `ptr` is guaranteed to be valid by the contract with the C code for the
             // lifetime of `policy`.
@@ -1152,8 +1182,13 @@ impl<T: Driver> Registration<T> {
 
     /// Driver's `setpolicy` callback.
     ///
-    /// SAFETY: Called from C. Inputs must be valid pointers.
-    extern "C" fn setpolicy_callback(ptr: *mut bindings::cpufreq_policy) -> kernel::ffi::c_int {
+    /// # Safety
+    ///
+    /// - This function may only be called from the cpufreq C infrastructure.
+    /// - The pointer arguments must be valid pointers.
+    unsafe extern "C" fn setpolicy_callback(
+        ptr: *mut bindings::cpufreq_policy,
+    ) -> kernel::ffi::c_int {
         from_result(|| {
             // SAFETY: The `ptr` is guaranteed to be valid by the contract with the C code for the
             // lifetime of `policy`.
@@ -1164,8 +1199,11 @@ impl<T: Driver> Registration<T> {
 
     /// Driver's `target` callback.
     ///
-    /// SAFETY: Called from C. Inputs must be valid pointers.
-    extern "C" fn target_callback(
+    /// # Safety
+    ///
+    /// - This function may only be called from the cpufreq C infrastructure.
+    /// - The pointer arguments must be valid pointers.
+    unsafe extern "C" fn target_callback(
         ptr: *mut bindings::cpufreq_policy,
         target_freq: u32,
         relation: u32,
@@ -1180,8 +1218,11 @@ impl<T: Driver> Registration<T> {
 
     /// Driver's `target_index` callback.
     ///
-    /// SAFETY: Called from C. Inputs must be valid pointers.
-    extern "C" fn target_index_callback(
+    /// # Safety
+    ///
+    /// - This function may only be called from the cpufreq C infrastructure.
+    /// - The pointer arguments must be valid pointers.
+    unsafe extern "C" fn target_index_callback(
         ptr: *mut bindings::cpufreq_policy,
         index: u32,
     ) -> kernel::ffi::c_int {
@@ -1200,8 +1241,11 @@ impl<T: Driver> Registration<T> {
 
     /// Driver's `fast_switch` callback.
     ///
-    /// SAFETY: Called from C. Inputs must be valid pointers.
-    extern "C" fn fast_switch_callback(
+    /// # Safety
+    ///
+    /// - This function may only be called from the cpufreq C infrastructure.
+    /// - The pointer arguments must be valid pointers.
+    unsafe extern "C" fn fast_switch_callback(
         ptr: *mut bindings::cpufreq_policy,
         target_freq: u32,
     ) -> kernel::ffi::c_uint {
@@ -1212,7 +1256,11 @@ impl<T: Driver> Registration<T> {
     }
 
     /// Driver's `adjust_perf` callback.
-    extern "C" fn adjust_perf_callback(
+    ///
+    /// # Safety
+    ///
+    /// - This function may only be called from the cpufreq C infrastructure.
+    unsafe extern "C" fn adjust_perf_callback(
         cpu: u32,
         min_perf: usize,
         target_perf: usize,
@@ -1225,8 +1273,11 @@ impl<T: Driver> Registration<T> {
 
     /// Driver's `get_intermediate` callback.
     ///
-    /// SAFETY: Called from C. Inputs must be valid pointers.
-    extern "C" fn get_intermediate_callback(
+    /// # Safety
+    ///
+    /// - This function may only be called from the cpufreq C infrastructure.
+    /// - The pointer arguments must be valid pointers.
+    unsafe extern "C" fn get_intermediate_callback(
         ptr: *mut bindings::cpufreq_policy,
         index: u32,
     ) -> kernel::ffi::c_uint {
@@ -1243,8 +1294,11 @@ impl<T: Driver> Registration<T> {
 
     /// Driver's `target_intermediate` callback.
     ///
-    /// SAFETY: Called from C. Inputs must be valid pointers.
-    extern "C" fn target_intermediate_callback(
+    /// # Safety
+    ///
+    /// - This function may only be called from the cpufreq C infrastructure.
+    /// - The pointer arguments must be valid pointers.
+    unsafe extern "C" fn target_intermediate_callback(
         ptr: *mut bindings::cpufreq_policy,
         index: u32,
     ) -> kernel::ffi::c_int {
@@ -1262,12 +1316,21 @@ impl<T: Driver> Registration<T> {
     }
 
     /// Driver's `get` callback.
-    extern "C" fn get_callback(cpu: u32) -> kernel::ffi::c_uint {
+    ///
+    /// # Safety
+    ///
+    /// - This function may only be called from the cpufreq C infrastructure.
+    unsafe extern "C" fn get_callback(cpu: u32) -> kernel::ffi::c_uint {
         PolicyCpu::from_cpu(cpu).map_or(0, |mut policy| T::get(&mut policy).map_or(0, |f| f))
     }
 
     /// Driver's `update_limit` callback.
-    extern "C" fn update_limits_callback(ptr: *mut bindings::cpufreq_policy) {
+    ///
+    /// # Safety
+    ///
+    /// - This function may only be called from the cpufreq C infrastructure.
+    /// - The pointer arguments must be valid pointers.
+    unsafe extern "C" fn update_limits_callback(ptr: *mut bindings::cpufreq_policy) {
         // SAFETY: The `ptr` is guaranteed to be valid by the contract with the C code for the
         // lifetime of `policy`.
         let policy = unsafe { Policy::from_raw_mut(ptr) };
@@ -1276,8 +1339,11 @@ impl<T: Driver> Registration<T> {
 
     /// Driver's `bios_limit` callback.
     ///
-    /// SAFETY: Called from C. Inputs must be valid pointers.
-    extern "C" fn bios_limit_callback(cpu: i32, limit: *mut u32) -> kernel::ffi::c_int {
+    /// # Safety
+    ///
+    /// - This function may only be called from the cpufreq C infrastructure.
+    /// - The pointer arguments must be valid pointers.
+    unsafe extern "C" fn bios_limit_callback(cpu: i32, limit: *mut u32) -> kernel::ffi::c_int {
         from_result(|| {
             let mut policy = PolicyCpu::from_cpu(cpu as u32)?;
 
@@ -1288,8 +1354,11 @@ impl<T: Driver> Registration<T> {
 
     /// Driver's `set_boost` callback.
     ///
-    /// SAFETY: Called from C. Inputs must be valid pointers.
-    extern "C" fn set_boost_callback(
+    /// # Safety
+    ///
+    /// - This function may only be called from the cpufreq C infrastructure.
+    /// - The pointer arguments must be valid pointers.
+    unsafe extern "C" fn set_boost_callback(
         ptr: *mut bindings::cpufreq_policy,
         state: i32,
     ) -> kernel::ffi::c_int {
@@ -1303,8 +1372,11 @@ impl<T: Driver> Registration<T> {
 
     /// Driver's `register_em` callback.
     ///
-    /// SAFETY: Called from C. Inputs must be valid pointers.
-    extern "C" fn register_em_callback(ptr: *mut bindings::cpufreq_policy) {
+    /// # Safety
+    ///
+    /// - This function may only be called from the cpufreq C infrastructure.
+    /// - The pointer arguments must be valid pointers.
+    unsafe extern "C" fn register_em_callback(ptr: *mut bindings::cpufreq_policy) {
         // SAFETY: The `ptr` is guaranteed to be valid by the contract with the C code for the
         // lifetime of `policy`.
         let policy = unsafe { Policy::from_raw_mut(ptr) };

From 6325766d69900d1aa9733fc7572456fc4427b708 Mon Sep 17 00:00:00 2001
From: Thorsten Blum <thorsten.blum@linux.dev>
Date: Tue, 10 Jun 2025 12:32:16 +0200
Subject: [PATCH 0142/1334] ASoC: sdw_utils: Fix potential NULL pointer deref
 in is_sdca_endpoint_present()

Check the return value of kzalloc() and exit early to avoid a potential
NULL pointer dereference.

Cc: stable@vger.kernel.org
Fixes: 4f8ef33dd44a ("ASoC: soc_sdw_utils: skip the endpoint that doesn't present")
Signed-off-by: Thorsten Blum <thorsten.blum@linux.dev>
Link: https://patch.msgid.link/20250610103225.1475-2-thorsten.blum@linux.dev
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/sdw_utils/soc_sdw_utils.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/sound/soc/sdw_utils/soc_sdw_utils.c b/sound/soc/sdw_utils/soc_sdw_utils.c
index b7060b746356..d75e7292240b 100644
--- a/sound/soc/sdw_utils/soc_sdw_utils.c
+++ b/sound/soc/sdw_utils/soc_sdw_utils.c
@@ -1205,6 +1205,8 @@ static int is_sdca_endpoint_present(struct device *dev,
 	int i;
 
 	dlc = kzalloc(sizeof(*dlc), GFP_KERNEL);
+	if (!dlc)
+		return -ENOMEM;
 
 	adr_end = &adr_dev->endpoints[end_index];
 	dai_info = &codec_info->dais[adr_end->num];

From d29fc02caad7f94b62d56ee1b01c954f9c961ba7 Mon Sep 17 00:00:00 2001
From: Tasos Sahanidis <tasos@tasossah.com>
Date: Mon, 19 May 2025 11:49:45 +0300
Subject: [PATCH 0143/1334] ata: pata_via: Force PIO for ATAPI devices on
 VT6415/VT6330

The controller has a hardware bug that can hard hang the system when
doing ATAPI DMAs without any trace of what happened. Depending on the
device attached, it can also prevent the system from booting.

In this case, the system hangs when reading the ATIP from optical media
with cdrecord -vvv -atip on an _NEC DVD_RW ND-4571A 1-01 and an
Optiarc DVD RW AD-7200A 1.06 attached to an ASRock 990FX Extreme 4,
running at UDMA/33.

The issue can be reproduced by running the same command with a cygwin
build of cdrecord on WinXP, although it requires more attempts to cause
it. The hang in that case is also resolved by forcing PIO. It doesn't
appear that VIA has produced any drivers for that OS, thus no known
workaround exists.

HDDs attached to the controller do not suffer from any DMA issues.

Cc: stable@vger.kernel.org
Link: https://bugs.launchpad.net/ubuntu/+source/linux/+bug/916677
Signed-off-by: Tasos Sahanidis <tasos@tasossah.com>
Link: https://lore.kernel.org/r/20250519085508.1398701-1-tasos@tasossah.com
Signed-off-by: Niklas Cassel <cassel@kernel.org>
---
 drivers/ata/pata_via.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/ata/pata_via.c b/drivers/ata/pata_via.c
index 696b99720dcb..d82728a01832 100644
--- a/drivers/ata/pata_via.c
+++ b/drivers/ata/pata_via.c
@@ -368,7 +368,8 @@ static unsigned int via_mode_filter(struct ata_device *dev, unsigned int mask)
 	}
 
 	if (dev->class == ATA_DEV_ATAPI &&
-	    dmi_check_system(no_atapi_dma_dmi_table)) {
+	    (dmi_check_system(no_atapi_dma_dmi_table) ||
+	     config->id == PCI_DEVICE_ID_VIA_6415)) {
 		ata_dev_warn(dev, "controller locks up on ATAPI DMA, forcing PIO\n");
 		mask &= ATA_MASK_PIO;
 	}

From 33877220b8641b4cde474a4229ea92c0e3637883 Mon Sep 17 00:00:00 2001
From: Tasos Sahanidis <tasos@tasossah.com>
Date: Mon, 19 May 2025 11:56:55 +0300
Subject: [PATCH 0144/1334] ata: libata-acpi: Do not assume 40 wire cable if no
 devices are enabled

On at least an ASRock 990FX Extreme 4 with a VIA VT6330, the devices
have not yet been enabled by the first time ata_acpi_cbl_80wire() is
called. This means that the ata_for_each_dev loop is never entered,
and a 40 wire cable is assumed.

The VIA controller on this board does not report the cable in the PCI
config space, thus having to fall back to ACPI even though no SATA
bridge is present.

The _GTM values are correctly reported by the firmware through ACPI,
which has already set up faster transfer modes, but due to the above
the controller is forced down to a maximum of UDMA/33.

Resolve this by modifying ata_acpi_cbl_80wire() to directly return the
cable type. First, an unknown cable is assumed which preserves the mode
set by the firmware, and then on subsequent calls when the devices have
been enabled, an 80 wire cable is correctly detected.

Since the function now directly returns the cable type, it is renamed
to ata_acpi_cbl_pata_type().

Signed-off-by: Tasos Sahanidis <tasos@tasossah.com>
Link: https://lore.kernel.org/r/20250519085945.1399466-1-tasos@tasossah.com
Signed-off-by: Niklas Cassel <cassel@kernel.org>
---
 drivers/ata/libata-acpi.c | 24 ++++++++++++++++--------
 drivers/ata/pata_via.c    |  6 ++----
 include/linux/libata.h    |  7 +++----
 3 files changed, 21 insertions(+), 16 deletions(-)

diff --git a/drivers/ata/libata-acpi.c b/drivers/ata/libata-acpi.c
index b7f0bf795521..f2140fc06ba0 100644
--- a/drivers/ata/libata-acpi.c
+++ b/drivers/ata/libata-acpi.c
@@ -514,15 +514,19 @@ unsigned int ata_acpi_gtm_xfermask(struct ata_device *dev,
 EXPORT_SYMBOL_GPL(ata_acpi_gtm_xfermask);
 
 /**
- * ata_acpi_cbl_80wire		-	Check for 80 wire cable
+ * ata_acpi_cbl_pata_type - Return PATA cable type
  * @ap: Port to check
- * @gtm: GTM data to use
  *
- * Return 1 if the @gtm indicates the BIOS selected an 80wire mode.
+ * Return ATA_CBL_PATA* according to the transfer mode selected by BIOS
  */
-int ata_acpi_cbl_80wire(struct ata_port *ap, const struct ata_acpi_gtm *gtm)
+int ata_acpi_cbl_pata_type(struct ata_port *ap)
 {
 	struct ata_device *dev;
+	int ret = ATA_CBL_PATA_UNK;
+	const struct ata_acpi_gtm *gtm = ata_acpi_init_gtm(ap);
+
+	if (!gtm)
+		return ATA_CBL_PATA40;
 
 	ata_for_each_dev(dev, &ap->link, ENABLED) {
 		unsigned int xfer_mask, udma_mask;
@@ -530,13 +534,17 @@ int ata_acpi_cbl_80wire(struct ata_port *ap, const struct ata_acpi_gtm *gtm)
 		xfer_mask = ata_acpi_gtm_xfermask(dev, gtm);
 		ata_unpack_xfermask(xfer_mask, NULL, NULL, &udma_mask);
 
-		if (udma_mask & ~ATA_UDMA_MASK_40C)
-			return 1;
+		ret = ATA_CBL_PATA40;
+
+		if (udma_mask & ~ATA_UDMA_MASK_40C) {
+			ret = ATA_CBL_PATA80;
+			break;
+		}
 	}
 
-	return 0;
+	return ret;
 }
-EXPORT_SYMBOL_GPL(ata_acpi_cbl_80wire);
+EXPORT_SYMBOL_GPL(ata_acpi_cbl_pata_type);
 
 static void ata_acpi_gtf_to_tf(struct ata_device *dev,
 			       const struct ata_acpi_gtf *gtf,
diff --git a/drivers/ata/pata_via.c b/drivers/ata/pata_via.c
index d82728a01832..bb80e7800dcb 100644
--- a/drivers/ata/pata_via.c
+++ b/drivers/ata/pata_via.c
@@ -201,11 +201,9 @@ static int via_cable_detect(struct ata_port *ap) {
 	   two drives */
 	if (ata66 & (0x10100000 >> (16 * ap->port_no)))
 		return ATA_CBL_PATA80;
+
 	/* Check with ACPI so we can spot BIOS reported SATA bridges */
-	if (ata_acpi_init_gtm(ap) &&
-	    ata_acpi_cbl_80wire(ap, ata_acpi_init_gtm(ap)))
-		return ATA_CBL_PATA80;
-	return ATA_CBL_PATA40;
+	return ata_acpi_cbl_pata_type(ap);
 }
 
 static int via_pre_reset(struct ata_link *link, unsigned long deadline)
diff --git a/include/linux/libata.h b/include/linux/libata.h
index 31be45fd47a6..1e5aec839041 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -1352,7 +1352,7 @@ int ata_acpi_stm(struct ata_port *ap, const struct ata_acpi_gtm *stm);
 int ata_acpi_gtm(struct ata_port *ap, struct ata_acpi_gtm *stm);
 unsigned int ata_acpi_gtm_xfermask(struct ata_device *dev,
 				   const struct ata_acpi_gtm *gtm);
-int ata_acpi_cbl_80wire(struct ata_port *ap, const struct ata_acpi_gtm *gtm);
+int ata_acpi_cbl_pata_type(struct ata_port *ap);
 #else
 static inline const struct ata_acpi_gtm *ata_acpi_init_gtm(struct ata_port *ap)
 {
@@ -1377,10 +1377,9 @@ static inline unsigned int ata_acpi_gtm_xfermask(struct ata_device *dev,
 	return 0;
 }
 
-static inline int ata_acpi_cbl_80wire(struct ata_port *ap,
-				      const struct ata_acpi_gtm *gtm)
+static inline int ata_acpi_cbl_pata_type(struct ata_port *ap)
 {
-	return 0;
+	return ATA_CBL_PATA40;
 }
 #endif
 

From d17e61ab63fb7747b340d6a66bf1408cd5c6562b Mon Sep 17 00:00:00 2001
From: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
Date: Fri, 6 Jun 2025 22:37:29 +0200
Subject: [PATCH 0145/1334] drm/meson: fix debug log statement when setting the
 HDMI clocks

The "phy" and "vclk" frequency labels were swapped, making it more
difficult to debug driver errors. Swap the label order to make them
match with the actual frequencies printed to correct this.

Fixes: e5fab2ec9ca4 ("drm/meson: vclk: add support for YUV420 setup")
Signed-off-by: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
Reviewed-by: Neil Armstrong <neil.armstrong@linaro.org>
Signed-off-by: Neil Armstrong <neil.armstrong@linaro.org>
Link: https://lore.kernel.org/r/20250606203729.3311592-1-martin.blumenstingl@googlemail.com
---
 drivers/gpu/drm/meson/meson_encoder_hdmi.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/meson/meson_encoder_hdmi.c b/drivers/gpu/drm/meson/meson_encoder_hdmi.c
index 47136bbbe8c6..ab08d690d882 100644
--- a/drivers/gpu/drm/meson/meson_encoder_hdmi.c
+++ b/drivers/gpu/drm/meson/meson_encoder_hdmi.c
@@ -109,7 +109,7 @@ static void meson_encoder_hdmi_set_vclk(struct meson_encoder_hdmi *encoder_hdmi,
 		venc_freq /= 2;
 
 	dev_dbg(priv->dev,
-		"vclk:%lluHz phy=%lluHz venc=%lluHz hdmi=%lluHz enci=%d\n",
+		"phy:%lluHz vclk=%lluHz venc=%lluHz hdmi=%lluHz enci=%d\n",
 		phy_freq, vclk_freq, venc_freq, hdmi_freq,
 		priv->venc.hdmi_use_enci);
 

From faf2f8382088e8c74bd6eeb236c8c9190e61615e Mon Sep 17 00:00:00 2001
From: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
Date: Sat, 7 Jun 2025 00:10:31 +0200
Subject: [PATCH 0146/1334] drm/meson: use vclk_freq instead of pixel_freq in
 debug print

meson_vclk_vic_supported_freq() has a debug print which includes the
pixel freq. However, within the whole function the pixel freq is
irrelevant, other than checking the end of the params array. Switch to
printing the vclk_freq which is being compared / matched against the
inputs to the function to avoid confusion when analyzing error reports
from users.

Fixes: e5fab2ec9ca4 ("drm/meson: vclk: add support for YUV420 setup")
Signed-off-by: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
Reviewed-by: Neil Armstrong <neil.armstrong@linaro.org>
Signed-off-by: Neil Armstrong <neil.armstrong@linaro.org>
Link: https://lore.kernel.org/r/20250606221031.3419353-1-martin.blumenstingl@googlemail.com
---
 drivers/gpu/drm/meson/meson_vclk.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/meson/meson_vclk.c b/drivers/gpu/drm/meson/meson_vclk.c
index 3325580d885d..c4123bb958e4 100644
--- a/drivers/gpu/drm/meson/meson_vclk.c
+++ b/drivers/gpu/drm/meson/meson_vclk.c
@@ -790,9 +790,9 @@ meson_vclk_vic_supported_freq(struct meson_drm *priv,
 	}
 
 	for (i = 0 ; params[i].pixel_freq ; ++i) {
-		DRM_DEBUG_DRIVER("i = %d pixel_freq = %lluHz alt = %lluHz\n",
-				 i, params[i].pixel_freq,
-				 PIXEL_FREQ_1000_1001(params[i].pixel_freq));
+		DRM_DEBUG_DRIVER("i = %d vclk_freq = %lluHz alt = %lluHz\n",
+				 i, params[i].vclk_freq,
+				 PIXEL_FREQ_1000_1001(params[i].vclk_freq));
 		DRM_DEBUG_DRIVER("i = %d phy_freq = %lluHz alt = %lluHz\n",
 				 i, params[i].phy_freq,
 				 PHY_FREQ_1000_1001(params[i].phy_freq));

From 0cee6c4d3518b2e757aedae78771f17149f57653 Mon Sep 17 00:00:00 2001
From: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
Date: Mon, 9 Jun 2025 22:27:51 +0200
Subject: [PATCH 0147/1334] drm/meson: fix more rounding issues with 59.94Hz
 modes

Commit 1017560164b6 ("drm/meson: use unsigned long long / Hz for
frequency types") attempts to resolve video playback using 59.94Hz.
 using YUV420 by changing the clock calculation to use
Hz instead of kHz (thus yielding more precision).

The basic calculation itself is correct, however the comparisions in
meson_vclk_vic_supported_freq() and meson_vclk_setup() don't work
anymore for 59.94Hz modes (using the freq * 1000 / 1001 logic). For
example, drm/edid specifies a 593407kHz clock for 3840x2160@59.94Hz.
With the mentioend commit we convert this to Hz. Then meson_vclk
tries to find a matchig "params" entry (as the clock setup code
currently only supports specific frequencies) by taking the venc_freq
from the params and calculating the "alt frequency" (used for the
59.94Hz modes) from it, which is:
  (594000000Hz * 1000) / 1001 = 593406593Hz

Similar calculation is applied to the phy_freq (TMDS clock), which is 10
times the pixel clock.

Implement a new meson_vclk_freqs_are_matching_param() function whose
purpose is to compare if the requested and calculated frequencies. They
may not match exactly (for the reasons mentioned above). Allow the
clocks to deviate slightly to make the 59.94Hz modes again.

Fixes: 1017560164b6 ("drm/meson: use unsigned long long / Hz for frequency types")
Reported-by: Christian Hewitt <christianshewitt@gmail.com>
Signed-off-by: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
Reviewed-by: Neil Armstrong <neil.armstrong@linaro.org>
Signed-off-by: Neil Armstrong <neil.armstrong@linaro.org>
Link: https://lore.kernel.org/r/20250609202751.962208-1-martin.blumenstingl@googlemail.com
---
 drivers/gpu/drm/meson/meson_vclk.c | 55 ++++++++++++++++++------------
 1 file changed, 34 insertions(+), 21 deletions(-)

diff --git a/drivers/gpu/drm/meson/meson_vclk.c b/drivers/gpu/drm/meson/meson_vclk.c
index c4123bb958e4..dfe0c28a0f05 100644
--- a/drivers/gpu/drm/meson/meson_vclk.c
+++ b/drivers/gpu/drm/meson/meson_vclk.c
@@ -110,10 +110,7 @@
 #define HDMI_PLL_LOCK		BIT(31)
 #define HDMI_PLL_LOCK_G12A	(3 << 30)
 
-#define PIXEL_FREQ_1000_1001(_freq)	\
-	DIV_ROUND_CLOSEST_ULL((_freq) * 1000ULL, 1001ULL)
-#define PHY_FREQ_1000_1001(_freq)	\
-	(PIXEL_FREQ_1000_1001(DIV_ROUND_DOWN_ULL(_freq, 10ULL)) * 10)
+#define FREQ_1000_1001(_freq)	DIV_ROUND_CLOSEST_ULL((_freq) * 1000ULL, 1001ULL)
 
 /* VID PLL Dividers */
 enum {
@@ -772,6 +769,36 @@ static void meson_hdmi_pll_generic_set(struct meson_drm *priv,
 		  pll_freq);
 }
 
+static bool meson_vclk_freqs_are_matching_param(unsigned int idx,
+						unsigned long long phy_freq,
+						unsigned long long vclk_freq)
+{
+	DRM_DEBUG_DRIVER("i = %d vclk_freq = %lluHz alt = %lluHz\n",
+			 idx, params[idx].vclk_freq,
+			 FREQ_1000_1001(params[idx].vclk_freq));
+	DRM_DEBUG_DRIVER("i = %d phy_freq = %lluHz alt = %lluHz\n",
+			 idx, params[idx].phy_freq,
+			 FREQ_1000_1001(params[idx].phy_freq));
+
+	/* Match strict frequency */
+	if (phy_freq == params[idx].phy_freq &&
+	    vclk_freq == params[idx].vclk_freq)
+		return true;
+
+	/* Match 1000/1001 variant: vclk deviation has to be less than 1kHz
+	 * (drm EDID is defined in 1kHz steps, so everything smaller must be
+	 * rounding error) and the PHY freq deviation has to be less than
+	 * 10kHz (as the TMDS clock is 10 times the pixel clock, so anything
+	 * smaller must be rounding error as well).
+	 */
+	if (abs(vclk_freq - FREQ_1000_1001(params[idx].vclk_freq)) < 1000 &&
+	    abs(phy_freq - FREQ_1000_1001(params[idx].phy_freq)) < 10000)
+		return true;
+
+	/* no match */
+	return false;
+}
+
 enum drm_mode_status
 meson_vclk_vic_supported_freq(struct meson_drm *priv,
 			      unsigned long long phy_freq,
@@ -790,19 +817,7 @@ meson_vclk_vic_supported_freq(struct meson_drm *priv,
 	}
 
 	for (i = 0 ; params[i].pixel_freq ; ++i) {
-		DRM_DEBUG_DRIVER("i = %d vclk_freq = %lluHz alt = %lluHz\n",
-				 i, params[i].vclk_freq,
-				 PIXEL_FREQ_1000_1001(params[i].vclk_freq));
-		DRM_DEBUG_DRIVER("i = %d phy_freq = %lluHz alt = %lluHz\n",
-				 i, params[i].phy_freq,
-				 PHY_FREQ_1000_1001(params[i].phy_freq));
-		/* Match strict frequency */
-		if (phy_freq == params[i].phy_freq &&
-		    vclk_freq == params[i].vclk_freq)
-			return MODE_OK;
-		/* Match 1000/1001 variant */
-		if (phy_freq == PHY_FREQ_1000_1001(params[i].phy_freq) &&
-		    vclk_freq == PIXEL_FREQ_1000_1001(params[i].vclk_freq))
+		if (meson_vclk_freqs_are_matching_param(i, phy_freq, vclk_freq))
 			return MODE_OK;
 	}
 
@@ -1075,10 +1090,8 @@ void meson_vclk_setup(struct meson_drm *priv, unsigned int target,
 	}
 
 	for (freq = 0 ; params[freq].pixel_freq ; ++freq) {
-		if ((phy_freq == params[freq].phy_freq ||
-		     phy_freq == PHY_FREQ_1000_1001(params[freq].phy_freq)) &&
-		    (vclk_freq == params[freq].vclk_freq ||
-		     vclk_freq == PIXEL_FREQ_1000_1001(params[freq].vclk_freq))) {
+		if (meson_vclk_freqs_are_matching_param(freq, phy_freq,
+							vclk_freq)) {
 			if (vclk_freq != params[freq].vclk_freq)
 				vic_alternate_clock = true;
 			else

From fe5b391fc56f77cf3c22a9dd4f0ce20db0e3533f Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Fri, 6 Jun 2025 11:01:11 +0200
Subject: [PATCH 0148/1334] ata: pata_cs5536: fix build on 32-bit UML

On 32-bit ARCH=um, CONFIG_X86_32 is still defined, so it
doesn't indicate building on real X86 machines. There's
no MSR on UML though, so add a check for CONFIG_X86.

Reported-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Link: https://lore.kernel.org/r/20250606090110.15784-2-johannes@sipsolutions.net
Signed-off-by: Niklas Cassel <cassel@kernel.org>
---
 drivers/ata/pata_cs5536.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/ata/pata_cs5536.c b/drivers/ata/pata_cs5536.c
index b811efd2cc34..73e81e160c91 100644
--- a/drivers/ata/pata_cs5536.c
+++ b/drivers/ata/pata_cs5536.c
@@ -27,7 +27,7 @@
 #include <scsi/scsi_host.h>
 #include <linux/dmi.h>
 
-#ifdef CONFIG_X86_32
+#if defined(CONFIG_X86) && defined(CONFIG_X86_32)
 #include <asm/msr.h>
 static int use_msr;
 module_param_named(msr, use_msr, int, 0644);

From 5558f27a58459a4038ebb23bcb5bd40c1e345c57 Mon Sep 17 00:00:00 2001
From: Chen-Yu Tsai <wens@csie.org>
Date: Sat, 7 Jun 2025 21:52:03 +0800
Subject: [PATCH 0149/1334] pinctrl: sunxi: dt: Consider pin base when
 calculating bank number from pin

In prepare_function_table() when the pinctrl function table IRQ entries
are generated, the pin bank is calculated from the absolute pin number;
however the IRQ bank mux array is indexed from the first pin bank of the
controller. For R_PIO controllers, this means the absolute pin bank is
way off from the relative pin bank used for array indexing.

Correct this by taking into account the pin base of the controller.

Fixes: f5e2cd34b12f ("pinctrl: sunxi: allow reading mux values from DT")
Signed-off-by: Chen-Yu Tsai <wens@csie.org>
Link: https://lore.kernel.org/20250607135203.2085226-1-wens@kernel.org
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/sunxi/pinctrl-sunxi-dt.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/pinctrl/sunxi/pinctrl-sunxi-dt.c b/drivers/pinctrl/sunxi/pinctrl-sunxi-dt.c
index 1833078f6877..4e34b0cd3b73 100644
--- a/drivers/pinctrl/sunxi/pinctrl-sunxi-dt.c
+++ b/drivers/pinctrl/sunxi/pinctrl-sunxi-dt.c
@@ -143,7 +143,7 @@ static struct sunxi_desc_pin *init_pins_table(struct device *dev,
  */
 static int prepare_function_table(struct device *dev, struct device_node *pnode,
 				  struct sunxi_desc_pin *pins, int npins,
-				  const u8 *irq_bank_muxes)
+				  unsigned pin_base, const u8 *irq_bank_muxes)
 {
 	struct device_node *node;
 	struct property *prop;
@@ -166,7 +166,7 @@ static int prepare_function_table(struct device *dev, struct device_node *pnode,
 	 */
 	for (i = 0; i < npins; i++) {
 		struct sunxi_desc_pin *pin = &pins[i];
-		int bank = pin->pin.number / PINS_PER_BANK;
+		int bank = (pin->pin.number - pin_base) / PINS_PER_BANK;
 
 		if (irq_bank_muxes[bank]) {
 			pin->variant++;
@@ -211,7 +211,7 @@ static int prepare_function_table(struct device *dev, struct device_node *pnode,
 	last_bank = 0;
 	for (i = 0; i < npins; i++) {
 		struct sunxi_desc_pin *pin = &pins[i];
-		int bank = pin->pin.number / PINS_PER_BANK;
+		int bank = (pin->pin.number - pin_base) / PINS_PER_BANK;
 		int lastfunc = pin->variant + 1;
 		int irq_mux = irq_bank_muxes[bank];
 
@@ -353,7 +353,7 @@ int sunxi_pinctrl_dt_table_init(struct platform_device *pdev,
 		return PTR_ERR(pins);
 
 	ret = prepare_function_table(&pdev->dev, pnode, pins, desc->npins,
-				     irq_bank_muxes);
+				     desc->pin_base, irq_bank_muxes);
 	if (ret)
 		return ret;
 

From 8a157d8a00e815cab4432653cb50c9cedbbb4931 Mon Sep 17 00:00:00 2001
From: Steven Rostedt <rostedt@goodmis.org>
Date: Tue, 10 Jun 2025 09:33:48 -0400
Subject: [PATCH 0150/1334] tracing: Do not free "head" on error path of
 filter_free_subsystem_filters()

The variable "head" is allocated and initialized as a list before
allocating the first "item" for the list. If the allocation of "item"
fails, it frees "head" and then jumps to the label "free_now" which will
process head and free it.

This will cause a UAF of "head", and it doesn't need to free it before
jumping to the "free_now" label as that code will free it.

Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Link: https://lore.kernel.org/20250610093348.33c5643a@gandalf.local.home
Fixes: a9d0aab5eb33 ("tracing: Fix regression of filter waiting a long time on RCU synchronization")
Reported-by: kernel test robot <lkp@intel.com>
Reported-by: Dan Carpenter <dan.carpenter@linaro.org>
Closes: https://lore.kernel.org/r/202506070424.lCiNreTI-lkp@intel.com/
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/trace_events_filter.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index ea8b364b6818..08141f105c95 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -1437,10 +1437,8 @@ static void filter_free_subsystem_filters(struct trace_subsystem_dir *dir,
 	INIT_LIST_HEAD(&head->list);
 
 	item = kmalloc(sizeof(*item), GFP_KERNEL);
-	if (!item) {
-		kfree(head);
+	if (!item)
 		goto free_now;
-	}
 
 	item->filter = filter;
 	list_add_tail(&item->list, &head->list);

From 6dea74e454c260cd757b53a2f6861fffe6d83308 Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Sun, 1 Jun 2025 01:26:54 +0100
Subject: [PATCH 0151/1334] f2fs: Fix __write_node_folio() conversion

This conversion moved the folio_unlock() to inside __write_node_folio(),
but missed one caller so we had a double-unlock on this path.

Cc: Christoph Hellwig <hch@lst.de>
Cc: Chao Yu <chao@kernel.org>
Cc: Jaegeuk Kim <jaegeuk@kernel.org>
Reported-by: syzbot+c0dc46208750f063d0e0@syzkaller.appspotmail.com
Fixes: 80f31d2a7e5f (f2fs: return bool from __write_node_folio)
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/node.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
index 1cb4cba7f961..bfe104db284e 100644
--- a/fs/f2fs/node.c
+++ b/fs/f2fs/node.c
@@ -2078,7 +2078,6 @@ write_node:
 
 			if (!__write_node_folio(folio, false, &submitted,
 					wbc, do_balance, io_type, NULL)) {
-				folio_unlock(folio);
 				folio_batch_release(&fbatch);
 				ret = -EIO;
 				goto out;

From a298bbab903e3fb4cbe16d36d6195e68fad1b776 Mon Sep 17 00:00:00 2001
From: Suleiman Souhlal <suleiman@google.com>
Date: Fri, 6 Jun 2025 16:45:38 +0900
Subject: [PATCH 0152/1334] tools/resolve_btfids: Fix build when cross
 compiling kernel with clang.

When cross compiling the kernel with clang, we need to override
CLANG_CROSS_FLAGS when preparing the step libraries.

Prior to commit d1d096312176 ("tools: fix annoying "mkdir -p ..." logs
when building tools in parallel"), MAKEFLAGS would have been set to a
value that wouldn't set a value for CLANG_CROSS_FLAGS, hiding the
fact that we weren't properly overriding it.

Fixes: 56a2df7615fa ("tools/resolve_btfids: Compile resolve_btfids as host program")
Signed-off-by: Suleiman Souhlal <suleiman@google.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/bpf/20250606074538.1608546-1-suleiman@google.com
---
 tools/bpf/resolve_btfids/Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/bpf/resolve_btfids/Makefile b/tools/bpf/resolve_btfids/Makefile
index afbddea3a39c..ce1b556dfa90 100644
--- a/tools/bpf/resolve_btfids/Makefile
+++ b/tools/bpf/resolve_btfids/Makefile
@@ -17,7 +17,7 @@ endif
 
 # Overrides for the prepare step libraries.
 HOST_OVERRIDES := AR="$(HOSTAR)" CC="$(HOSTCC)" LD="$(HOSTLD)" ARCH="$(HOSTARCH)" \
-		  CROSS_COMPILE="" EXTRA_CFLAGS="$(HOSTCFLAGS)"
+		  CROSS_COMPILE="" CLANG_CROSS_FLAGS="" EXTRA_CFLAGS="$(HOSTCFLAGS)"
 
 RM      ?= rm
 HOSTCC  ?= gcc

From a2c90d63b71223d69a813333c1abf4fdacddbbe5 Mon Sep 17 00:00:00 2001
From: Robert Malz <robert.malz@canonical.com>
Date: Tue, 20 May 2025 10:31:51 +0200
Subject: [PATCH 0153/1334] i40e: return false from i40e_reset_vf if reset is
 in progress

The function i40e_vc_reset_vf attempts, up to 20 times, to handle a
VF reset request, using the return value of i40e_reset_vf as an indicator
of whether the reset was successfully triggered. Currently, i40e_reset_vf
always returns true, which causes new reset requests to be ignored if a
different VF reset is already in progress.

This patch updates the return value of i40e_reset_vf to reflect when
another VF reset is in progress, allowing the caller to properly use
the retry mechanism.

Fixes: 52424f974bc5 ("i40e: Fix VF hang when reset is triggered on another VF")
Signed-off-by: Robert Malz <robert.malz@canonical.com>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
index 1120f8e4bb67..22d5b1ec2289 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
@@ -1546,8 +1546,8 @@ static void i40e_cleanup_reset_vf(struct i40e_vf *vf)
  * @vf: pointer to the VF structure
  * @flr: VFLR was issued or not
  *
- * Returns true if the VF is in reset, resets successfully, or resets
- * are disabled and false otherwise.
+ * Return: True if reset was performed successfully or if resets are disabled.
+ * False if reset is already in progress.
  **/
 bool i40e_reset_vf(struct i40e_vf *vf, bool flr)
 {
@@ -1566,7 +1566,7 @@ bool i40e_reset_vf(struct i40e_vf *vf, bool flr)
 
 	/* If VF is being reset already we don't need to continue. */
 	if (test_and_set_bit(I40E_VF_STATE_RESETTING, &vf->vf_states))
-		return true;
+		return false;
 
 	i40e_trigger_vf_reset(vf, flr);
 

From fb4e9239e029954a37a00818b21e837cebf2aa10 Mon Sep 17 00:00:00 2001
From: Robert Malz <robert.malz@canonical.com>
Date: Tue, 20 May 2025 10:31:52 +0200
Subject: [PATCH 0154/1334] i40e: retry VFLR handling if there is ongoing VF
 reset

When a VFLR interrupt is received during a VF reset initiated from a
different source, the VFLR may be not fully handled. This can
leave the VF in an undefined state.
To address this, set the I40E_VFLR_EVENT_PENDING bit again during VFLR
handling if the reset is not yet complete. This ensures the driver
will properly complete the VF reset in such scenarios.

Fixes: 52424f974bc5 ("i40e: Fix VF hang when reset is triggered on another VF")
Signed-off-by: Robert Malz <robert.malz@canonical.com>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
index 22d5b1ec2289..88e6bef69342 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
@@ -4328,7 +4328,10 @@ int i40e_vc_process_vflr_event(struct i40e_pf *pf)
 		reg = rd32(hw, I40E_GLGEN_VFLRSTAT(reg_idx));
 		if (reg & BIT(bit_idx))
 			/* i40e_reset_vf will clear the bit in GLGEN_VFLRSTAT */
-			i40e_reset_vf(vf, true);
+			if (!i40e_reset_vf(vf, true)) {
+				/* At least one VF did not finish resetting, retry next time */
+				set_bit(__I40E_VFLR_EVENT_PENDING, pf->state);
+			}
 	}
 
 	return 0;

From 0c6f4631436ecea841f1583b98255aedd7495b18 Mon Sep 17 00:00:00 2001
From: Ahmed Zaki <ahmed.zaki@intel.com>
Date: Thu, 24 Apr 2025 15:50:13 +0200
Subject: [PATCH 0155/1334] iavf: fix reset_task for early reset event

If a reset event is received from the PF early in the init cycle, the
state machine hangs for about 25 seconds.

Reproducer:
  echo 1 > /sys/class/net/$PF0/device/sriov_numvfs
  ip link set dev $PF0 vf 0 mac $NEW_MAC

The log shows:
  [792.620416] ice 0000:5e:00.0: Enabling 1 VFs
  [792.738812] iavf 0000:5e:01.0: enabling device (0000 -> 0002)
  [792.744182] ice 0000:5e:00.0: Enabling 1 VFs with 17 vectors and 16 queues per VF
  [792.839964] ice 0000:5e:00.0: Setting MAC 52:54:00:00:00:11 on VF 0. VF driver will be reinitialized
  [813.389684] iavf 0000:5e:01.0: Failed to communicate with PF; waiting before retry
  [818.635918] iavf 0000:5e:01.0: Hardware came out of reset. Attempting reinit.
  [818.766273] iavf 0000:5e:01.0: Multiqueue Enabled: Queue pair count = 16

Fix it by scheduling the reset task and making the reset task capable of
resetting early in the init cycle.

Fixes: ef8693eb90ae3 ("i40evf: refactor reset handling")
Signed-off-by: Ahmed Zaki <ahmed.zaki@intel.com>
Tested-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Signed-off-by: Marcin Szycik <marcin.szycik@linux.intel.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/iavf/iavf_main.c     | 11 +++++++++++
 drivers/net/ethernet/intel/iavf/iavf_virtchnl.c | 17 +++++++++++++++++
 2 files changed, 28 insertions(+)

diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c
index 2c0bb41809a4..81d7249d1149 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_main.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_main.c
@@ -3209,6 +3209,17 @@ static void iavf_reset_task(struct work_struct *work)
 	}
 
 continue_reset:
+	/* If we are still early in the state machine, just restart. */
+	if (adapter->state <= __IAVF_INIT_FAILED) {
+		iavf_shutdown_adminq(hw);
+		iavf_change_state(adapter, __IAVF_STARTUP);
+		iavf_startup(adapter);
+		queue_delayed_work(adapter->wq, &adapter->watchdog_task,
+				   msecs_to_jiffies(30));
+		netdev_unlock(netdev);
+		return;
+	}
+
 	/* We don't use netif_running() because it may be true prior to
 	 * ndo_open() returning, so we can't assume it means all our open
 	 * tasks have finished, since we're not holding the rtnl_lock here.
diff --git a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
index a6f0e5990be2..07f0d0a0f1e2 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
@@ -79,6 +79,23 @@ iavf_poll_virtchnl_msg(struct iavf_hw *hw, struct iavf_arq_event_info *event,
 			return iavf_status_to_errno(status);
 		received_op =
 		    (enum virtchnl_ops)le32_to_cpu(event->desc.cookie_high);
+
+		if (received_op == VIRTCHNL_OP_EVENT) {
+			struct iavf_adapter *adapter = hw->back;
+			struct virtchnl_pf_event *vpe =
+				(struct virtchnl_pf_event *)event->msg_buf;
+
+			if (vpe->event != VIRTCHNL_EVENT_RESET_IMPENDING)
+				continue;
+
+			dev_info(&adapter->pdev->dev, "Reset indication received from the PF\n");
+			if (!(adapter->flags & IAVF_FLAG_RESET_PENDING))
+				iavf_schedule_reset(adapter,
+						    IAVF_FLAG_RESET_PENDING);
+
+			return -EIO;
+		}
+
 		if (op_to_poll == received_op)
 			break;
 	}

From a5a441ae283d54ec329aadc7426991dc32786d52 Mon Sep 17 00:00:00 2001
From: Anton Nadezhdin <anton.nadezhdin@intel.com>
Date: Tue, 20 May 2025 10:42:16 +0200
Subject: [PATCH 0156/1334] ice/ptp: fix crosstimestamp reporting

Set use_nsecs=true as timestamp is reported in ns. Lack of this result
in smaller timestamp error window which cause error during phc2sys
execution on E825 NICs:
phc2sys[1768.256]: ioctl PTP_SYS_OFFSET_PRECISE: Invalid argument

This problem was introduced in the cited commit which omitted setting
use_nsecs to true when converting the ice driver to use
convert_base_to_cs().

Testing hints (ethX is PF netdev):
phc2sys -s ethX -c CLOCK_REALTIME  -O 37 -m
phc2sys[1769.256]: CLOCK_REALTIME phc offset -5 s0 freq      -0 delay    0

Fixes: d4bea547ebb57 ("ice/ptp: Remove convert_art_to_tsc()")
Signed-off-by: Anton Nadezhdin <anton.nadezhdin@intel.com>
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Reviewed-by: Arkadiusz Kubalewski <arkadiusz.kubalewski@intel.com>
Tested-by: Rinitha S <sx.rinitha@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_ptp.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c
index b79a148ed0f2..55cad824c5b9 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp.c
+++ b/drivers/net/ethernet/intel/ice/ice_ptp.c
@@ -2299,6 +2299,7 @@ static int ice_capture_crosststamp(ktime_t *device,
 	ts = ((u64)ts_hi << 32) | ts_lo;
 	system->cycles = ts;
 	system->cs_id = CSID_X86_ART;
+	system->use_nsecs = true;
 
 	/* Read Device source clock time */
 	ts_lo = rd32(hw, cfg->dev_time_l[tmr_idx]);

From b4a8085ceefb7bbb12c2b71c55e71fc946c6929f Mon Sep 17 00:00:00 2001
From: Joe Damato <jdamato@fastly.com>
Date: Tue, 3 Jun 2025 16:34:01 +0000
Subject: [PATCH 0157/1334] e1000: Move cancel_work_sync to avoid deadlock

Previously, e1000_down called cancel_work_sync for the e1000 reset task
(via e1000_down_and_stop), which takes RTNL.

As reported by users and syzbot, a deadlock is possible in the following
scenario:

CPU 0:
  - RTNL is held
  - e1000_close
  - e1000_down
  - cancel_work_sync (cancel / wait for e1000_reset_task())

CPU 1:
  - process_one_work
  - e1000_reset_task
  - take RTNL

To remedy this, avoid calling cancel_work_sync from e1000_down
(e1000_reset_task does nothing if the device is down anyway). Instead,
call cancel_work_sync for e1000_reset_task when the device is being
removed.

Fixes: e400c7444d84 ("e1000: Hold RTNL when e1000_down can be called")
Reported-by: syzbot+846bb38dc67fe62cc733@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/netdev/683837bf.a00a0220.52848.0003.GAE@google.com/
Reported-by: John <john.cs.hey@gmail.com>
Closes: https://lore.kernel.org/netdev/CAP=Rh=OEsn4y_2LvkO3UtDWurKcGPnZ_NPSXK=FbgygNXL37Sw@mail.gmail.com/
Signed-off-by: Joe Damato <jdamato@fastly.com>
Acked-by: Stanislav Fomichev <sdf@fomichev.me>
Acked-by: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/e1000/e1000_main.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/intel/e1000/e1000_main.c b/drivers/net/ethernet/intel/e1000/e1000_main.c
index 3f089c3d47b2..d8595e84326d 100644
--- a/drivers/net/ethernet/intel/e1000/e1000_main.c
+++ b/drivers/net/ethernet/intel/e1000/e1000_main.c
@@ -477,10 +477,6 @@ static void e1000_down_and_stop(struct e1000_adapter *adapter)
 
 	cancel_delayed_work_sync(&adapter->phy_info_task);
 	cancel_delayed_work_sync(&adapter->fifo_stall_task);
-
-	/* Only kill reset task if adapter is not resetting */
-	if (!test_bit(__E1000_RESETTING, &adapter->flags))
-		cancel_work_sync(&adapter->reset_task);
 }
 
 void e1000_down(struct e1000_adapter *adapter)
@@ -1266,6 +1262,10 @@ static void e1000_remove(struct pci_dev *pdev)
 
 	unregister_netdev(netdev);
 
+	/* Only kill reset task if adapter is not resetting */
+	if (!test_bit(__E1000_RESETTING, &adapter->flags))
+		cancel_work_sync(&adapter->reset_task);
+
 	e1000_phy_hw_reset(hw);
 
 	kfree(adapter->tx_ring);

From c33453d08a56a45c2e72f9f56043610b8f7449c7 Mon Sep 17 00:00:00 2001
From: Vitaly Kuznetsov <vkuznets@redhat.com>
Date: Fri, 6 Jun 2025 17:41:12 +0200
Subject: [PATCH 0158/1334] efi: Drop preprocessor directives from zboot.lds

Older versions of `ld` don't seem to support preprocessor directives in
linker scripts, e.g. on RHEL9's ld-2.35.2-63.el9 the build fails with:

 ld:./drivers/firmware/efi/libstub/zboot.lds:32: ignoring invalid character `#' in expression
 ld:./drivers/firmware/efi/libstub/zboot.lds:33: syntax error

We don't seem to need these '#ifdef', no empty .sbat section is created
when CONFIG_EFI_SBAT_FILE="":

 # objdump -h arch/arm64/boot/vmlinuz.efi

 arch/arm64/boot/vmlinuz.efi:     file format pei-aarch64-little

 Sections:
 Idx Name          Size      VMA               LMA               File off  Algn
   0 .text         00b94000  0000000000001000  0000000000001000  00001000  2**2
                   CONTENTS, ALLOC, LOAD, READONLY, CODE
   1 .data         00000200  0000000000b95000  0000000000b95000  00b95000  2**2
                   CONTENTS, ALLOC, LOAD, DATA

Fixes: 0f9a1739dd0e ("efi: zboot specific mechanism for embedding SBAT section")
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
 drivers/firmware/efi/libstub/zboot.lds | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/firmware/efi/libstub/zboot.lds b/drivers/firmware/efi/libstub/zboot.lds
index c3a166675450..4b8d5cd3dfa2 100644
--- a/drivers/firmware/efi/libstub/zboot.lds
+++ b/drivers/firmware/efi/libstub/zboot.lds
@@ -29,14 +29,12 @@ SECTIONS
 		. = _etext;
 	}
 
-#ifdef CONFIG_EFI_SBAT
         .sbat : ALIGN(4096) {
 		_sbat = .;
 		*(.sbat)
 		_esbat = ALIGN(4096);
 		. = _esbat;
 	}
-#endif
 
 	.data : ALIGN(4096) {
 		_data = .;

From ac0b8b327a5677dc6fecdf353d808161525b1ff0 Mon Sep 17 00:00:00 2001
From: Penglei Jiang <superman.xpt@gmail.com>
Date: Tue, 10 Jun 2025 10:18:01 -0700
Subject: [PATCH 0159/1334] io_uring: fix use-after-free of sq->thread in
 __io_uring_show_fdinfo()

syzbot reports:

BUG: KASAN: slab-use-after-free in getrusage+0x1109/0x1a60
Read of size 8 at addr ffff88810de2d2c8 by task a.out/304

CPU: 0 UID: 0 PID: 304 Comm: a.out Not tainted 6.16.0-rc1 #1 PREEMPT(voluntary)
Hardware name: QEMU Ubuntu 24.04 PC (i440FX + PIIX, 1996), BIOS 1.16.3-debian-1.16.3-2 04/01/2014
Call Trace:
 <TASK>
 dump_stack_lvl+0x53/0x70
 print_report+0xd0/0x670
 ? __pfx__raw_spin_lock_irqsave+0x10/0x10
 ? getrusage+0x1109/0x1a60
 kasan_report+0xce/0x100
 ? getrusage+0x1109/0x1a60
 getrusage+0x1109/0x1a60
 ? __pfx_getrusage+0x10/0x10
 __io_uring_show_fdinfo+0x9fe/0x1790
 ? ksys_read+0xf7/0x1c0
 ? do_syscall_64+0xa4/0x260
 ? vsnprintf+0x591/0x1100
 ? __pfx___io_uring_show_fdinfo+0x10/0x10
 ? __pfx_vsnprintf+0x10/0x10
 ? mutex_trylock+0xcf/0x130
 ? __pfx_mutex_trylock+0x10/0x10
 ? __pfx_show_fd_locks+0x10/0x10
 ? io_uring_show_fdinfo+0x57/0x80
 io_uring_show_fdinfo+0x57/0x80
 seq_show+0x38c/0x690
 seq_read_iter+0x3f7/0x1180
 ? inode_set_ctime_current+0x160/0x4b0
 seq_read+0x271/0x3e0
 ? __pfx_seq_read+0x10/0x10
 ? __pfx__raw_spin_lock+0x10/0x10
 ? __mark_inode_dirty+0x402/0x810
 ? selinux_file_permission+0x368/0x500
 ? file_update_time+0x10f/0x160
 vfs_read+0x177/0xa40
 ? __pfx___handle_mm_fault+0x10/0x10
 ? __pfx_vfs_read+0x10/0x10
 ? mutex_lock+0x81/0xe0
 ? __pfx_mutex_lock+0x10/0x10
 ? fdget_pos+0x24d/0x4b0
 ksys_read+0xf7/0x1c0
 ? __pfx_ksys_read+0x10/0x10
 ? do_user_addr_fault+0x43b/0x9c0
 do_syscall_64+0xa4/0x260
 entry_SYSCALL_64_after_hwframe+0x77/0x7f
RIP: 0033:0x7f0f74170fc9
Code: 00 c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 8
RSP: 002b:00007fffece049e8 EFLAGS: 00000206 ORIG_RAX: 0000000000000000
RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f0f74170fc9
RDX: 0000000000001000 RSI: 00007fffece049f0 RDI: 0000000000000004
RBP: 00007fffece05ad0 R08: 0000000000000000 R09: 00007fffece04d90
R10: 0000000000000000 R11: 0000000000000206 R12: 00005651720a1100
R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000
 </TASK>

Allocated by task 298:
 kasan_save_stack+0x33/0x60
 kasan_save_track+0x14/0x30
 __kasan_slab_alloc+0x6e/0x70
 kmem_cache_alloc_node_noprof+0xe8/0x330
 copy_process+0x376/0x5e00
 create_io_thread+0xab/0xf0
 io_sq_offload_create+0x9ed/0xf20
 io_uring_setup+0x12b0/0x1cc0
 do_syscall_64+0xa4/0x260
 entry_SYSCALL_64_after_hwframe+0x77/0x7f

Freed by task 22:
 kasan_save_stack+0x33/0x60
 kasan_save_track+0x14/0x30
 kasan_save_free_info+0x3b/0x60
 __kasan_slab_free+0x37/0x50
 kmem_cache_free+0xc4/0x360
 rcu_core+0x5ff/0x19f0
 handle_softirqs+0x18c/0x530
 run_ksoftirqd+0x20/0x30
 smpboot_thread_fn+0x287/0x6c0
 kthread+0x30d/0x630
 ret_from_fork+0xef/0x1a0
 ret_from_fork_asm+0x1a/0x30

Last potentially related work creation:
 kasan_save_stack+0x33/0x60
 kasan_record_aux_stack+0x8c/0xa0
 __call_rcu_common.constprop.0+0x68/0x940
 __schedule+0xff2/0x2930
 __cond_resched+0x4c/0x80
 mutex_lock+0x5c/0xe0
 io_uring_del_tctx_node+0xe1/0x2b0
 io_uring_clean_tctx+0xb7/0x160
 io_uring_cancel_generic+0x34e/0x760
 do_exit+0x240/0x2350
 do_group_exit+0xab/0x220
 __x64_sys_exit_group+0x39/0x40
 x64_sys_call+0x1243/0x1840
 do_syscall_64+0xa4/0x260
 entry_SYSCALL_64_after_hwframe+0x77/0x7f

The buggy address belongs to the object at ffff88810de2cb00
 which belongs to the cache task_struct of size 3712
The buggy address is located 1992 bytes inside of
 freed 3712-byte region [ffff88810de2cb00, ffff88810de2d980)

which is caused by the task_struct pointed to by sq->thread being
released while it is being used in the function
__io_uring_show_fdinfo(). Holding ctx->uring_lock does not prevent ehre
relase or exit of sq->thread.

Fix this by assigning and looking up ->thread under RCU, and grabbing a
reference to the task_struct. This ensures that it cannot get released
while fdinfo is using it.

Reported-by: syzbot+531502bbbe51d2f769f4@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/all/682b06a5.a70a0220.3849cf.00b3.GAE@google.com
Fixes: 3fcb9d17206e ("io_uring/sqpoll: statistics of the true utilization of sq threads")
Signed-off-by: Penglei Jiang <superman.xpt@gmail.com>
Link: https://lore.kernel.org/r/20250610171801.70960-1-superman.xpt@gmail.com
[axboe: massage commit message]
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/fdinfo.c | 12 ++++++++++--
 io_uring/sqpoll.c |  9 ++++-----
 2 files changed, 14 insertions(+), 7 deletions(-)

diff --git a/io_uring/fdinfo.c b/io_uring/fdinfo.c
index e9355276ab5d..9798d6fb4ec7 100644
--- a/io_uring/fdinfo.c
+++ b/io_uring/fdinfo.c
@@ -141,18 +141,26 @@ static void __io_uring_show_fdinfo(struct io_ring_ctx *ctx, struct seq_file *m)
 
 	if (ctx->flags & IORING_SETUP_SQPOLL) {
 		struct io_sq_data *sq = ctx->sq_data;
+		struct task_struct *tsk;
 
+		rcu_read_lock();
+		tsk = rcu_dereference(sq->thread);
 		/*
 		 * sq->thread might be NULL if we raced with the sqpoll
 		 * thread termination.
 		 */
-		if (sq->thread) {
+		if (tsk) {
+			get_task_struct(tsk);
+			rcu_read_unlock();
+			getrusage(tsk, RUSAGE_SELF, &sq_usage);
+			put_task_struct(tsk);
 			sq_pid = sq->task_pid;
 			sq_cpu = sq->sq_cpu;
-			getrusage(sq->thread, RUSAGE_SELF, &sq_usage);
 			sq_total_time = (sq_usage.ru_stime.tv_sec * 1000000
 					 + sq_usage.ru_stime.tv_usec);
 			sq_work_time = sq->work_time;
+		} else {
+			rcu_read_unlock();
 		}
 	}
 
diff --git a/io_uring/sqpoll.c b/io_uring/sqpoll.c
index 03c699493b5a..0625a421626f 100644
--- a/io_uring/sqpoll.c
+++ b/io_uring/sqpoll.c
@@ -270,7 +270,8 @@ static int io_sq_thread(void *data)
 	/* offload context creation failed, just exit */
 	if (!current->io_uring) {
 		mutex_lock(&sqd->lock);
-		sqd->thread = NULL;
+		rcu_assign_pointer(sqd->thread, NULL);
+		put_task_struct(current);
 		mutex_unlock(&sqd->lock);
 		goto err_out;
 	}
@@ -379,7 +380,8 @@ static int io_sq_thread(void *data)
 		io_sq_tw(&retry_list, UINT_MAX);
 
 	io_uring_cancel_generic(true, sqd);
-	sqd->thread = NULL;
+	rcu_assign_pointer(sqd->thread, NULL);
+	put_task_struct(current);
 	list_for_each_entry(ctx, &sqd->ctx_list, sqd_list)
 		atomic_or(IORING_SQ_NEED_WAKEUP, &ctx->rings->sq_flags);
 	io_run_task_work();
@@ -495,9 +497,6 @@ __cold int io_sq_offload_create(struct io_ring_ctx *ctx,
 		ret = -EINVAL;
 		goto err;
 	}
-
-	if (task_to_put)
-		put_task_struct(task_to_put);
 	return 0;
 err_sqpoll:
 	complete(&ctx->sq_data->exited);

From aef17cb3d3c43854002956f24c24ec8e1a0e3546 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Tue, 10 Jun 2025 10:22:15 -0700
Subject: [PATCH 0160/1334] Revert "mm/damon/Kconfig: enable CONFIG_DAMON by
 default"

This reverts commit 28615e6eed152f2fda5486680090b74aeed7b554.

No, we don't make random features default to being on.

Reported-by: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: SeongJae Park <sj@kernel.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/damon/Kconfig | 1 -
 1 file changed, 1 deletion(-)

diff --git a/mm/damon/Kconfig b/mm/damon/Kconfig
index 551745df011b..c93d0c56b963 100644
--- a/mm/damon/Kconfig
+++ b/mm/damon/Kconfig
@@ -4,7 +4,6 @@ menu "Data Access Monitoring"
 
 config DAMON
 	bool "DAMON: Data Access Monitoring Framework"
-	default y
 	help
 	  This builds a framework that allows kernel subsystems to monitor
 	  access frequency of each memory region. The information can be useful

From c393befa14ab26596fb86d702566d648832dae06 Mon Sep 17 00:00:00 2001
From: Dan Williams <dan.j.williams@intel.com>
Date: Fri, 6 Jun 2025 20:32:26 -0700
Subject: [PATCH 0161/1334] driver core: faux: Suppress bind attributes

faux_device_create() is almost a suitable candidate to replace
platform_driver_probe() if not for the fact that faux_device_create()
supports dynamic attach/detach of the driver.

Drop the bind attributes with the expectation that simple faux devices can
always assume that the device is permanently bound at create, and only
unbound at 'destroy'.

The acpi-einj driver depends on static bind.

Fixes: 6cb9441bfe8d ("ACPI: APEI: EINJ: Transition to the faux device interface")
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Link: https://patch.msgid.link/20250607033228.1475625-2-dan.j.williams@intel.com
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/base/faux.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/base/faux.c b/drivers/base/faux.c
index 9054d346bd7f..934da77ca48b 100644
--- a/drivers/base/faux.c
+++ b/drivers/base/faux.c
@@ -86,6 +86,7 @@ static struct device_driver faux_driver = {
 	.name		= "faux_driver",
 	.bus		= &faux_bus_type,
 	.probe_type	= PROBE_FORCE_SYNCHRONOUS,
+	.suppress_bind_attrs = true,
 };
 
 static void faux_device_release(struct device *dev)

From ff53a6e247285687df1a71d8ee5c457939792c13 Mon Sep 17 00:00:00 2001
From: Dan Williams <dan.j.williams@intel.com>
Date: Fri, 6 Jun 2025 20:32:27 -0700
Subject: [PATCH 0162/1334] driver core: faux: Quiet probe failures

The acpi-einj conversion to faux_device_create() leads to a noisy error
message when the error injection facility is disabled. Quiet the error as
CXL error injection via ACPI expects the module to stay loaded even if the
error injection facility is disabled.

This situation arose because CXL knows proper kernel named objects to
trigger errors against, but acpi-einj knows how to perform the error
injection. The injection mechanism is shared with non-CXL use cases. The
result is CXL now has a module dependency on einj-core.ko, and init/probe
failures are handled at runtime.

Fixes: 6cb9441bfe8d ("ACPI: APEI: EINJ: Transition to the faux device interface")
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Link: https://patch.msgid.link/20250607033228.1475625-3-dan.j.williams@intel.com
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/base/faux.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/base/faux.c b/drivers/base/faux.c
index 934da77ca48b..f5fbda0a9a44 100644
--- a/drivers/base/faux.c
+++ b/drivers/base/faux.c
@@ -170,7 +170,7 @@ struct faux_device *faux_device_create_with_groups(const char *name,
 	 * successful is almost impossible to determine by the caller.
 	 */
 	if (!dev->driver) {
-		dev_err(dev, "probe did not succeed, tearing down the device\n");
+		dev_dbg(dev, "probe did not succeed, tearing down the device\n");
 		faux_device_destroy(faux_dev);
 		faux_dev = NULL;
 	}

From 162457f5853ce3348e7956666916f5e5e31be51f Mon Sep 17 00:00:00 2001
From: Dan Williams <dan.j.williams@intel.com>
Date: Fri, 6 Jun 2025 20:32:28 -0700
Subject: [PATCH 0163/1334] ACPI: APEI: EINJ: Do not fail einj_init() on
 faux_device_create() failure

CXL has a symbol dependency on einj_core.ko, so if einj_init() fails then
cxl_core.ko fails to load. Prior to the faux_device_create() conversion,
einj_probe() failures were tracked by the einj_initialized flag without
failing einj_init().

Revert to that behavior and always succeed einj_init() given there is no
way, and no pressing need, to discern faux device-create vs device-probe
failures.

This situation arose because CXL knows proper kernel named objects to
trigger errors against, but acpi-einj knows how to perform the error
injection. The injection mechanism is shared with non-CXL use cases. The
result is CXL now has a module dependency on einj-core.ko, and init/probe
failures are handled at runtime.

Fixes: 6cb9441bfe8d ("ACPI: APEI: EINJ: Transition to the faux device interface")
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Reviewed-by: Ben Cheatham <benjamin.cheatham@amd.com>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Link: https://patch.msgid.link/20250607033228.1475625-4-dan.j.williams@intel.com
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/apei/einj-core.c | 9 +++------
 1 file changed, 3 insertions(+), 6 deletions(-)

diff --git a/drivers/acpi/apei/einj-core.c b/drivers/acpi/apei/einj-core.c
index fea11a35eea3..9b041415a9d0 100644
--- a/drivers/acpi/apei/einj-core.c
+++ b/drivers/acpi/apei/einj-core.c
@@ -883,19 +883,16 @@ static int __init einj_init(void)
 	}
 
 	einj_dev = faux_device_create("acpi-einj", NULL, &einj_device_ops);
-	if (!einj_dev)
-		return -ENODEV;
 
-	einj_initialized = true;
+	if (einj_dev)
+		einj_initialized = true;
 
 	return 0;
 }
 
 static void __exit einj_exit(void)
 {
-	if (einj_initialized)
-		faux_device_destroy(einj_dev);
-
+	faux_device_destroy(einj_dev);
 }
 
 module_init(einj_init);

From 5b2d595efbfc9c46823bdb9ef11e1f9fa46adf9d Mon Sep 17 00:00:00 2001
From: FUJITA Tomonori <fujita.tomonori@gmail.com>
Date: Fri, 6 Jun 2025 11:05:05 +0900
Subject: [PATCH 0164/1334] rust: time: Fix compile error in impl_has_hr_timer
 macro

Fix a compile error in the `impl_has_hr_timer!` macro as follows:

error[E0599]: no method named cast_mut found for raw pointer *mut Foo in the current scope

The `container_of!` macro already returns a mutable pointer when used
in a `*mut T` context so the `.cast_mut()` method is not available.

[ We missed this one because there is no caller yet and it is
  a macro. - Miguel ]

Fixes: 74d6a606c2b3 ("rust: retain pointer mut-ness in `container_of!`")
Signed-off-by: FUJITA Tomonori <fujita.tomonori@gmail.com>
Reviewed-by: Benno Lossin <lossin@kernel.org>
Acked-by: Andreas Hindborg <a.hindborg@kernel.org>
Link: https://lore.kernel.org/r/20250606020505.3186533-1-fujita.tomonori@gmail.com
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 rust/kernel/time/hrtimer.rs | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/rust/kernel/time/hrtimer.rs b/rust/kernel/time/hrtimer.rs
index 9df3dcd2fa39..36e1290cd079 100644
--- a/rust/kernel/time/hrtimer.rs
+++ b/rust/kernel/time/hrtimer.rs
@@ -517,7 +517,7 @@ macro_rules! impl_has_hr_timer {
             ) -> *mut Self {
                 // SAFETY: As per the safety requirement of this function, `ptr`
                 // is pointing inside a `$timer_type`.
-                unsafe { ::kernel::container_of!(ptr, $timer_type, $field).cast_mut() }
+                unsafe { ::kernel::container_of!(ptr, $timer_type, $field) }
             }
         }
     }

From 2f76d269073bdb2971b253ef87d1f96f1a94c50e Mon Sep 17 00:00:00 2001
From: Uros Bizjak <ubizjak@gmail.com>
Date: Mon, 9 Jun 2025 08:42:06 +0200
Subject: [PATCH 0165/1334] ACPI: PAD: Update arguments of
 mwait_idle_with_hints()

Commit a17b37a3f416 ("x86/idle: Change arguments of mwait_idle_with_hints()
to u32") changed the type of arguments of mwait_idle_with_hints() from
unsigned long to u32.

Change the type of variables in the call to mwait_idle_with_hints() to
unsigned int to follow the change.

Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
Link: https://patch.msgid.link/20250609064235.49146-1-ubizjak@gmail.com
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/acpi_pad.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/acpi/acpi_pad.c b/drivers/acpi/acpi_pad.c
index 6f8bbe1247a5..c9a0bcaba2e4 100644
--- a/drivers/acpi/acpi_pad.c
+++ b/drivers/acpi/acpi_pad.c
@@ -33,7 +33,7 @@
 static DEFINE_MUTEX(isolated_cpus_lock);
 static DEFINE_MUTEX(round_robin_lock);
 
-static unsigned long power_saving_mwait_eax;
+static unsigned int power_saving_mwait_eax;
 
 static unsigned char tsc_detected_unstable;
 static unsigned char tsc_marked_unstable;

From 15eece6c5b05e5f9db0711978c3e3b7f1a2cfe12 Mon Sep 17 00:00:00 2001
From: Yunhui Cui <cuiyunhui@bytedance.com>
Date: Wed, 4 Jun 2025 10:30:36 +0800
Subject: [PATCH 0166/1334] ACPI: CPPC: Fix NULL pointer dereference when nosmp
 is used

With nosmp in cmdline, other CPUs are not brought up, leaving
their cpc_desc_ptr NULL. CPU0's iteration via for_each_possible_cpu()
dereferences these NULL pointers, causing panic.

Panic backtrace:

[    0.401123] Unable to handle kernel NULL pointer dereference at virtual address 00000000000000b8
...
[    0.403255] [<ffffffff809a5818>] cppc_allow_fast_switch+0x6a/0xd4
...
Kernel panic - not syncing: Attempted to kill init!

Fixes: 3cc30dd00a58 ("cpufreq: CPPC: Enable fast_switch")
Reported-by: Xu Lu <luxu.kernel@bytedance.com>
Signed-off-by: Yunhui Cui <cuiyunhui@bytedance.com>
Link: https://patch.msgid.link/20250604023036.99553-1-cuiyunhui@bytedance.com
[ rjw: New subject ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/cppc_acpi.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/acpi/cppc_acpi.c b/drivers/acpi/cppc_acpi.c
index a9ae2fd62863..6b649031808f 100644
--- a/drivers/acpi/cppc_acpi.c
+++ b/drivers/acpi/cppc_acpi.c
@@ -476,7 +476,7 @@ bool cppc_allow_fast_switch(void)
 	struct cpc_desc *cpc_ptr;
 	int cpu;
 
-	for_each_possible_cpu(cpu) {
+	for_each_present_cpu(cpu) {
 		cpc_ptr = per_cpu(cpc_desc_ptr, cpu);
 		desired_reg = &cpc_ptr->cpc_regs[DESIRED_PERF];
 		if (!CPC_IN_SYSTEM_MEMORY(desired_reg) &&

From 7a0d59f6a913a2bc7680c663b8cf1e45d1bdbf26 Mon Sep 17 00:00:00 2001
From: Armin Wolf <W_Armin@gmx.de>
Date: Fri, 30 May 2025 01:53:10 +0200
Subject: [PATCH 0167/1334] ACPI: EC: Ignore ECDT tables with an invalid ID
 string

On the MSI Modern 14 C5M the ECDT table contains invalid data:

	UID : 00000000
 GPE Number : 00	/* Invalid, 03 would be correct */
   Namepath : ""	/* Invalid, "\_SB.PCI0.SBRG.EC" would
			 * be correct
			 */

This slows down the EC access as the wrong GPE event is used for
communication. Additionally the ID string is invalid.

Ignore such faulty ECDT tables by verifying that the ID string has
a valid format.

Tested-by: glpnk@proton.me
Signed-off-by: Armin Wolf <W_Armin@gmx.de>
Link: https://patch.msgid.link/20250529235310.540530-1-W_Armin@gmx.de
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/ec.c | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)

diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c
index 6f4203716b53..75c7db8b156a 100644
--- a/drivers/acpi/ec.c
+++ b/drivers/acpi/ec.c
@@ -23,8 +23,10 @@
 #include <linux/delay.h>
 #include <linux/interrupt.h>
 #include <linux/list.h>
+#include <linux/printk.h>
 #include <linux/spinlock.h>
 #include <linux/slab.h>
+#include <linux/string.h>
 #include <linux/suspend.h>
 #include <linux/acpi.h>
 #include <linux/dmi.h>
@@ -2031,6 +2033,21 @@ void __init acpi_ec_ecdt_probe(void)
 		goto out;
 	}
 
+	if (!strstarts(ecdt_ptr->id, "\\")) {
+		/*
+		 * The ECDT table on some MSI notebooks contains invalid data, together
+		 * with an empty ID string ("").
+		 *
+		 * Section 5.2.15 of the ACPI specification requires the ID string to be
+		 * a "fully qualified reference to the (...) embedded controller device",
+		 * so this string always has to start with a backslash.
+		 *
+		 * By verifying this we can avoid such faulty ECDT tables in a safe way.
+		 */
+		pr_err(FW_BUG "Ignoring ECDT due to invalid ID string \"%s\"\n", ecdt_ptr->id);
+		goto out;
+	}
+
 	ec = acpi_ec_alloc();
 	if (!ec)
 		goto out;

From c99ad987d3e9b550e9839d5df22de97d90462e5f Mon Sep 17 00:00:00 2001
From: Wentao Guan <guanwentao@uniontech.com>
Date: Tue, 3 Jun 2025 20:20:59 +0800
Subject: [PATCH 0168/1334] ACPI: resource: Use IRQ override on MACHENIKE 16P

Use ACPI IRQ override on MACHENIKE laptop to make the internal
keyboard work.

Add a new entry to the irq1_edge_low_force_override structure, similar
to the existing ones.

Link: https://bbs.deepin.org.cn/zh/post/287628
Signed-off-by: Wentao Guan <guanwentao@uniontech.com>
Link: https://patch.msgid.link/20250603122059.1072790-1-guanwentao@uniontech.com
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/resource.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/acpi/resource.c b/drivers/acpi/resource.c
index 7d59c6c9185f..b1ab192d7a08 100644
--- a/drivers/acpi/resource.c
+++ b/drivers/acpi/resource.c
@@ -666,6 +666,13 @@ static const struct dmi_system_id irq1_edge_low_force_override[] = {
 			DMI_MATCH(DMI_BOARD_NAME, "GMxHGxx"),
 		},
 	},
+	{
+		/* MACHENIKE L16P/L16P */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "MACHENIKE"),
+			DMI_MATCH(DMI_BOARD_NAME, "L16P"),
+		},
+	},
 	{
 		/*
 		 * TongFang GM5HG0A in case of the SKIKK Vanaheim relabel the

From 72840238e2bcb8fb24cb35d8d1d5a822c04e62a4 Mon Sep 17 00:00:00 2001
From: Uros Bizjak <ubizjak@gmail.com>
Date: Mon, 9 Jun 2025 08:35:01 +0200
Subject: [PATCH 0169/1334] intel_idle: Update arguments of
 mwait_idle_with_hints()

Commit a17b37a3f416 ("x86/idle: Change arguments of mwait_idle_with_hints()
to u32") changed the type of arguments of mwait_idle_with_hints() from
unsigned long to u32.

Change the type of variables in the call to mwait_idle_with_hints() to
unsigned int to follow the change.

Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
Reviewed-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
Link: https://patch.msgid.link/20250609063528.48715-1-ubizjak@gmail.com
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/idle/intel_idle.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
index 63565814c7e5..73747d20df85 100644
--- a/drivers/idle/intel_idle.c
+++ b/drivers/idle/intel_idle.c
@@ -152,8 +152,8 @@ static __always_inline int __intel_idle(struct cpuidle_device *dev,
 					int index, bool irqoff)
 {
 	struct cpuidle_state *state = &drv->states[index];
-	unsigned long eax = flg2MWAIT(state->flags);
-	unsigned long ecx = 1*irqoff; /* break on interrupt flag */
+	unsigned int eax = flg2MWAIT(state->flags);
+	unsigned int ecx = 1*irqoff; /* break on interrupt flag */
 
 	mwait_idle_with_hints(eax, ecx);
 
@@ -226,9 +226,9 @@ static __cpuidle int intel_idle_xstate(struct cpuidle_device *dev,
 static __cpuidle int intel_idle_s2idle(struct cpuidle_device *dev,
 				       struct cpuidle_driver *drv, int index)
 {
-	unsigned long ecx = 1; /* break on interrupt flag */
 	struct cpuidle_state *state = &drv->states[index];
-	unsigned long eax = flg2MWAIT(state->flags);
+	unsigned int eax = flg2MWAIT(state->flags);
+	unsigned int ecx = 1; /* break on interrupt flag */
 
 	if (state->flags & CPUIDLE_FLAG_INIT_XSTATE)
 		fpu_idle_fpregs();

From 5ae416c5b1e2e816aee7b3fc8347adf70afabb4c Mon Sep 17 00:00:00 2001
From: Qasim Ijaz <qasdev00@gmail.com>
Date: Fri, 6 Jun 2025 19:49:57 +0100
Subject: [PATCH 0170/1334] HID: wacom: fix memory leak on kobject creation
 failure

During wacom_initialize_remotes() a fifo buffer is allocated
with kfifo_alloc() and later a cleanup action is registered
during devm_add_action_or_reset() to clean it up.

However if the code fails to create a kobject and register it
with sysfs the code simply returns -ENOMEM before the cleanup
action is registered leading to a memory leak.

Fix this by ensuring the fifo is freed when the kobject creation
and registration process fails.

Fixes: 83e6b40e2de6 ("HID: wacom: EKR: have the wacom resources dynamically allocated")
Reviewed-by: Ping Cheng <ping.cheng@wacom.com>
Cc: stable@vger.kernel.org
Signed-off-by: Qasim Ijaz <qasdev00@gmail.com>
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
 drivers/hid/wacom_sys.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/hid/wacom_sys.c b/drivers/hid/wacom_sys.c
index eaf099b2efdb..ec5282bc69d6 100644
--- a/drivers/hid/wacom_sys.c
+++ b/drivers/hid/wacom_sys.c
@@ -2048,8 +2048,10 @@ static int wacom_initialize_remotes(struct wacom *wacom)
 
 	remote->remote_dir = kobject_create_and_add("wacom_remote",
 						    &wacom->hdev->dev.kobj);
-	if (!remote->remote_dir)
+	if (!remote->remote_dir) {
+		kfifo_free(&remote->remote_fifo);
 		return -ENOMEM;
+	}
 
 	error = sysfs_create_files(remote->remote_dir, remote_unpair_attrs);
 

From 1a19ae437ca5d5c7d9ec2678946fb339b1c706bf Mon Sep 17 00:00:00 2001
From: Qasim Ijaz <qasdev00@gmail.com>
Date: Fri, 6 Jun 2025 19:49:58 +0100
Subject: [PATCH 0171/1334] HID: wacom: fix memory leak on sysfs attribute
 creation failure

When sysfs_create_files() fails during wacom_initialize_remotes() the
fifo buffer is not freed leading to a memory leak.

Fix this by calling kfifo_free() before returning.

Fixes: 83e6b40e2de6 ("HID: wacom: EKR: have the wacom resources dynamically allocated")
Reviewed-by: Ping Cheng <ping.cheng@wacom.com>
Cc: stable@vger.kernel.org
Signed-off-by: Qasim Ijaz <qasdev00@gmail.com>
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
 drivers/hid/wacom_sys.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/hid/wacom_sys.c b/drivers/hid/wacom_sys.c
index ec5282bc69d6..58cbd43a37e9 100644
--- a/drivers/hid/wacom_sys.c
+++ b/drivers/hid/wacom_sys.c
@@ -2058,6 +2058,7 @@ static int wacom_initialize_remotes(struct wacom *wacom)
 	if (error) {
 		hid_err(wacom->hdev,
 			"cannot create sysfs group err: %d\n", error);
+		kfifo_free(&remote->remote_fifo);
 		return error;
 	}
 

From 85a720f4337f0ddf1603c8b75a8f1ffbbe022ef9 Mon Sep 17 00:00:00 2001
From: Qasim Ijaz <qasdev00@gmail.com>
Date: Fri, 6 Jun 2025 19:49:59 +0100
Subject: [PATCH 0172/1334] HID: wacom: fix kobject reference count leak

When sysfs_create_files() fails in wacom_initialize_remotes() the error
is returned and the cleanup action will not have been registered yet.

As a result the kobject???s refcount is never dropped, so the
kobject can never be freed leading to a reference leak.

Fix this by calling kobject_put() before returning.

Fixes: 83e6b40e2de6 ("HID: wacom: EKR: have the wacom resources dynamically allocated")
Acked-by: Ping Cheng <ping.cheng@wacom.com>
Cc: stable@vger.kernel.org
Signed-off-by: Qasim Ijaz <qasdev00@gmail.com>
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
 drivers/hid/wacom_sys.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/hid/wacom_sys.c b/drivers/hid/wacom_sys.c
index 58cbd43a37e9..1257131b1e34 100644
--- a/drivers/hid/wacom_sys.c
+++ b/drivers/hid/wacom_sys.c
@@ -2059,6 +2059,7 @@ static int wacom_initialize_remotes(struct wacom *wacom)
 		hid_err(wacom->hdev,
 			"cannot create sysfs group err: %d\n", error);
 		kfifo_free(&remote->remote_fifo);
+		kobject_put(remote->remote_dir);
 		return error;
 	}
 

From 4a0381080397e77792a5168069f174d3e56175ff Mon Sep 17 00:00:00 2001
From: "Daniel J. Ogorchock" <djogorchock@gmail.com>
Date: Tue, 13 May 2025 03:47:00 -0400
Subject: [PATCH 0173/1334] HID: nintendo: avoid bluetooth suspend/resume
 stalls

Ensure we don't stall or panic the kernel when using bluetooth-connected
controllers. This was reported as an issue on android devices using
kernel 6.6 due to the resume hook which had been added for usb joycons.

First, set a new state value to JOYCON_CTLR_STATE_SUSPENDED in a
newly-added nintendo_hid_suspend. This makes sure we will not stall out
the kernel waiting for input reports during led classdev suspend. The
stalls could happen if connectivity is unreliable or lost to the
controller prior to suspend.

Second, since we lose connectivity during suspend, do not try
joycon_init() for bluetooth controllers in the nintendo_hid_resume path.

Tested via multiple suspend/resume flows when using the controller both
in USB and bluetooth modes.

Signed-off-by: Daniel J. Ogorchock <djogorchock@gmail.com>
Reviewed-by: Silvan Jegen <s.jegen@gmail.com>
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
 drivers/hid/hid-nintendo.c | 38 ++++++++++++++++++++++++++++++++++++--
 1 file changed, 36 insertions(+), 2 deletions(-)

diff --git a/drivers/hid/hid-nintendo.c b/drivers/hid/hid-nintendo.c
index 839d5bcd72b1..fb4985988615 100644
--- a/drivers/hid/hid-nintendo.c
+++ b/drivers/hid/hid-nintendo.c
@@ -308,6 +308,7 @@ enum joycon_ctlr_state {
 	JOYCON_CTLR_STATE_INIT,
 	JOYCON_CTLR_STATE_READ,
 	JOYCON_CTLR_STATE_REMOVED,
+	JOYCON_CTLR_STATE_SUSPENDED,
 };
 
 /* Controller type received as part of device info */
@@ -2750,14 +2751,46 @@ static void nintendo_hid_remove(struct hid_device *hdev)
 
 static int nintendo_hid_resume(struct hid_device *hdev)
 {
-	int ret = joycon_init(hdev);
+	struct joycon_ctlr *ctlr = hid_get_drvdata(hdev);
+	int ret;
 
+	hid_dbg(hdev, "resume\n");
+	if (!joycon_using_usb(ctlr)) {
+		hid_dbg(hdev, "no-op resume for bt ctlr\n");
+		ctlr->ctlr_state = JOYCON_CTLR_STATE_READ;
+		return 0;
+	}
+
+	ret = joycon_init(hdev);
 	if (ret)
-		hid_err(hdev, "Failed to restore controller after resume");
+		hid_err(hdev,
+			"Failed to restore controller after resume: %d\n",
+			ret);
+	else
+		ctlr->ctlr_state = JOYCON_CTLR_STATE_READ;
 
 	return ret;
 }
 
+static int nintendo_hid_suspend(struct hid_device *hdev, pm_message_t message)
+{
+	struct joycon_ctlr *ctlr = hid_get_drvdata(hdev);
+
+	hid_dbg(hdev, "suspend: %d\n", message.event);
+	/*
+	 * Avoid any blocking loops in suspend/resume transitions.
+	 *
+	 * joycon_enforce_subcmd_rate() can result in repeated retries if for
+	 * whatever reason the controller stops providing input reports.
+	 *
+	 * This has been observed with bluetooth controllers which lose
+	 * connectivity prior to suspend (but not long enough to result in
+	 * complete disconnection).
+	 */
+	ctlr->ctlr_state = JOYCON_CTLR_STATE_SUSPENDED;
+	return 0;
+}
+
 #endif
 
 static const struct hid_device_id nintendo_hid_devices[] = {
@@ -2796,6 +2829,7 @@ static struct hid_driver nintendo_hid_driver = {
 
 #ifdef CONFIG_PM
 	.resume		= nintendo_hid_resume,
+	.suspend	= nintendo_hid_suspend,
 #endif
 };
 static int __init nintendo_init(void)

From 73f3a7415d93cf418c7625d03bce72da84344406 Mon Sep 17 00:00:00 2001
From: Even Xu <even.xu@intel.com>
Date: Wed, 14 May 2025 14:26:38 +0800
Subject: [PATCH 0174/1334] HID: Intel-thc-hid: Intel-quicki2c: Enhance
 QuickI2C reset flow

During customer board enabling, it was found: some touch devices
prepared reset response, but either forgot sending interrupt or
THC missed reset interrupt because of timing issue. THC QuickI2C
driver depends on interrupt to read reset response, in this case,
it will cause driver waiting timeout.

This patch enhances the flow by adding manually reset response
reading after waiting for reset interrupt timeout.

Signed-off-by: Even Xu <even.xu@intel.com>
Tested-by: Chong Han <chong.han@intel.com>
Fixes: 66b59bfce6d9 ("HID: intel-thc-hid: intel-quicki2c: Complete THC QuickI2C driver")
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
 .../intel-quicki2c/quicki2c-protocol.c        | 26 ++++++++++++++++++-
 1 file changed, 25 insertions(+), 1 deletion(-)

diff --git a/drivers/hid/intel-thc-hid/intel-quicki2c/quicki2c-protocol.c b/drivers/hid/intel-thc-hid/intel-quicki2c/quicki2c-protocol.c
index f493df0d5dc4..a63f8c833252 100644
--- a/drivers/hid/intel-thc-hid/intel-quicki2c/quicki2c-protocol.c
+++ b/drivers/hid/intel-thc-hid/intel-quicki2c/quicki2c-protocol.c
@@ -4,6 +4,7 @@
 #include <linux/bitfield.h>
 #include <linux/hid.h>
 #include <linux/hid-over-i2c.h>
+#include <linux/unaligned.h>
 
 #include "intel-thc-dev.h"
 #include "intel-thc-dma.h"
@@ -200,6 +201,9 @@ int quicki2c_set_report(struct quicki2c_device *qcdev, u8 report_type,
 
 int quicki2c_reset(struct quicki2c_device *qcdev)
 {
+	u16 input_reg = le16_to_cpu(qcdev->dev_desc.input_reg);
+	size_t read_len = HIDI2C_LENGTH_LEN;
+	u32 prd_len = read_len;
 	int ret;
 
 	qcdev->reset_ack = false;
@@ -213,12 +217,32 @@ int quicki2c_reset(struct quicki2c_device *qcdev)
 
 	ret = wait_event_interruptible_timeout(qcdev->reset_ack_wq, qcdev->reset_ack,
 					       HIDI2C_RESET_TIMEOUT * HZ);
-	if (ret <= 0 || !qcdev->reset_ack) {
+	if (qcdev->reset_ack)
+		return 0;
+
+	/*
+	 * Manually read reset response if it wasn't received, in case reset interrupt
+	 * was missed by touch device or THC hardware.
+	 */
+	ret = thc_tic_pio_read(qcdev->thc_hw, input_reg, read_len, &prd_len,
+			       (u32 *)qcdev->input_buf);
+	if (ret) {
+		dev_err_once(qcdev->dev, "Read Reset Response failed, ret %d\n", ret);
+		return ret;
+	}
+
+	/*
+	 * Check response packet length, it's first 16 bits of packet.
+	 * If response packet length is zero, it's reset response, otherwise not.
+	 */
+	if (get_unaligned_le16(qcdev->input_buf)) {
 		dev_err_once(qcdev->dev,
 			     "Wait reset response timed out ret:%d timeout:%ds\n",
 			     ret, HIDI2C_RESET_TIMEOUT);
 		return -ETIMEDOUT;
 	}
 
+	qcdev->reset_ack = true;
+
 	return 0;
 }

From 0b3bc018e86afdc0cbfef61328c63d5c08f8b370 Mon Sep 17 00:00:00 2001
From: Kai Huang <kai.huang@intel.com>
Date: Sat, 7 Jun 2025 01:07:37 +1200
Subject: [PATCH 0175/1334] x86/virt/tdx: Avoid indirect calls to TDX assembly
 functions

Two 'static inline' TDX helper functions (sc_retry() and
sc_retry_prerr()) take function pointer arguments which refer to
assembly functions.  Normally, the compiler inlines the TDX helper,
realizes that the function pointer targets are completely static --
thus can be resolved at compile time -- and generates direct call
instructions.

But, other times (like when CONFIG_CC_OPTIMIZE_FOR_SIZE=y), the
compiler declines to inline the helpers and will instead generate
indirect call instructions.

Indirect calls to assembly functions require special annotation (for
various Control Flow Integrity mechanisms).  But TDX assembly
functions lack the special annotations and can only be called
directly.

Annotate both the helpers as '__always_inline' to prod the compiler
into maintaining the direct calls. There is no guarantee here, but
Peter has volunteered to report the compiler bug if this assumption
ever breaks[1].

Fixes: 1e66a7e27539 ("x86/virt/tdx: Handle SEAMCALL no entropy error in common code")
Fixes: df01f5ae07dd ("x86/virt/tdx: Add SEAMCALL error printing for module initialization")
Signed-off-by: Kai Huang <kai.huang@intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/lkml/20250605145914.GW39944@noisy.programming.kicks-ass.net/ [1]
Link: https://lore.kernel.org/all/20250606130737.30713-1-kai.huang%40intel.com
---
 arch/x86/include/asm/tdx.h  | 2 +-
 arch/x86/virt/vmx/tdx/tdx.c | 5 +++--
 2 files changed, 4 insertions(+), 3 deletions(-)

diff --git a/arch/x86/include/asm/tdx.h b/arch/x86/include/asm/tdx.h
index 8b19294600c4..7ddef3a69866 100644
--- a/arch/x86/include/asm/tdx.h
+++ b/arch/x86/include/asm/tdx.h
@@ -106,7 +106,7 @@ void tdx_init(void);
 
 typedef u64 (*sc_func_t)(u64 fn, struct tdx_module_args *args);
 
-static inline u64 sc_retry(sc_func_t func, u64 fn,
+static __always_inline u64 sc_retry(sc_func_t func, u64 fn,
 			   struct tdx_module_args *args)
 {
 	int retry = RDRAND_RETRY_LOOPS;
diff --git a/arch/x86/virt/vmx/tdx/tdx.c b/arch/x86/virt/vmx/tdx/tdx.c
index 2457d13c3f9e..c7a9a087ccaf 100644
--- a/arch/x86/virt/vmx/tdx/tdx.c
+++ b/arch/x86/virt/vmx/tdx/tdx.c
@@ -75,8 +75,9 @@ static inline void seamcall_err_ret(u64 fn, u64 err,
 			args->r9, args->r10, args->r11);
 }
 
-static inline int sc_retry_prerr(sc_func_t func, sc_err_func_t err_func,
-				 u64 fn, struct tdx_module_args *args)
+static __always_inline int sc_retry_prerr(sc_func_t func,
+					  sc_err_func_t err_func,
+					  u64 fn, struct tdx_module_args *args)
 {
 	u64 sret = sc_retry(func, fn, args);
 

From 54bae4c17c11688339eb73a04fd24203bb6e7494 Mon Sep 17 00:00:00 2001
From: "Chia-Lin Kao (AceLan)" <acelan.kao@canonical.com>
Date: Tue, 6 May 2025 13:50:15 +0800
Subject: [PATCH 0176/1334] HID: quirks: Add quirk for 2 Chicony Electronics HP
 5MP Cameras

The Chicony Electronics HP 5MP Cameras (USB ID 04F2:B824 & 04F2:B82C)
report a HID sensor interface that is not actually implemented.
Attempting to access this non-functional sensor via iio_info causes
system hangs as runtime PM tries to wake up an unresponsive sensor.

Add these 2 devices to the HID ignore list since the sensor interface is
non-functional by design and should not be exposed to userspace.

Signed-off-by: Chia-Lin Kao (AceLan) <acelan.kao@canonical.com>
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
 drivers/hid/hid-ids.h    | 2 ++
 drivers/hid/hid-quirks.c | 2 ++
 2 files changed, 4 insertions(+)

diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h
index e3fb4e2fe911..f1e00641e26e 100644
--- a/drivers/hid/hid-ids.h
+++ b/drivers/hid/hid-ids.h
@@ -312,6 +312,8 @@
 #define USB_DEVICE_ID_ASUS_AK1D		0x1125
 #define USB_DEVICE_ID_CHICONY_TOSHIBA_WT10A	0x1408
 #define USB_DEVICE_ID_CHICONY_ACER_SWITCH12	0x1421
+#define USB_DEVICE_ID_CHICONY_HP_5MP_CAMERA	0xb824
+#define USB_DEVICE_ID_CHICONY_HP_5MP_CAMERA2	0xb82c
 
 #define USB_VENDOR_ID_CHUNGHWAT		0x2247
 #define USB_DEVICE_ID_CHUNGHWAT_MULTITOUCH	0x0001
diff --git a/drivers/hid/hid-quirks.c b/drivers/hid/hid-quirks.c
index 7fefeb413ec3..96f3c712acc8 100644
--- a/drivers/hid/hid-quirks.c
+++ b/drivers/hid/hid-quirks.c
@@ -757,6 +757,8 @@ static const struct hid_device_id hid_ignore_list[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_AVERMEDIA, USB_DEVICE_ID_AVER_FM_MR800) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_AXENTIA, USB_DEVICE_ID_AXENTIA_FM_RADIO) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_BERKSHIRE, USB_DEVICE_ID_BERKSHIRE_PCWD) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_CHICONY, USB_DEVICE_ID_CHICONY_HP_5MP_CAMERA) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_CHICONY, USB_DEVICE_ID_CHICONY_HP_5MP_CAMERA2) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_CIDC, 0x0103) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_CYGNAL, USB_DEVICE_ID_CYGNAL_RADIO_SI470X) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_CYGNAL, USB_DEVICE_ID_CYGNAL_RADIO_SI4713) },

From fa10d4515817274a50af510d5d283d3c7fffc1ae Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Fri, 23 May 2025 11:10:07 -0500
Subject: [PATCH 0177/1334] HID: input: lower message severity of 'No inputs
 registered, leaving' to debug

Plugging in a "Blue snowball" microphone always shows the
error 'No inputs registered, leaving', but the device functions as
intended.

When a HID device is started using the function hid_hw_start() and
the argument HID_CONNECT_DEFAULT it will try all various hid connect
requests. Not all devices will create an input device and so the
message is needlessly noisy.  Decrease it to debug instead.

[jkosina@suse.com: edit shortlog]
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
 drivers/hid/hid-input.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c
index 9d80635a91eb..ff1784b5c2a4 100644
--- a/drivers/hid/hid-input.c
+++ b/drivers/hid/hid-input.c
@@ -2343,7 +2343,7 @@ int hidinput_connect(struct hid_device *hid, unsigned int force)
 	}
 
 	if (list_empty(&hid->inputs)) {
-		hid_err(hid, "No inputs registered, leaving\n");
+		hid_dbg(hid, "No inputs registered, leaving\n");
 		goto out_unwind;
 	}
 

From 9cf1e25053c269d64b9e9fa25e8697d6d58028d4 Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <stfomichev@gmail.com>
Date: Tue, 10 Jun 2025 10:54:37 -0700
Subject: [PATCH 0178/1334] MAINTAINERS: Add myself as bpf networking reviewer

I've been focusing on networking BPF bits lately, add myself as a
reviewer.

Signed-off-by: Stanislav Fomichev <stfomichev@gmail.com>
Acked-by: KP Singh <kpsingh@kernel.org>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Jakub Kicinski <kuba@kernel.org>
Link: https://lore.kernel.org/r/20250610175442.2138504-1-stfomichev@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 .mailmap    | 1 +
 MAINTAINERS | 3 +++
 2 files changed, 4 insertions(+)

diff --git a/.mailmap b/.mailmap
index 77bb62564ef7..7641338b8d3f 100644
--- a/.mailmap
+++ b/.mailmap
@@ -712,6 +712,7 @@ Srinivas Ramana <quic_sramana@quicinc.com> <sramana@codeaurora.org>
 Sriram R <quic_srirrama@quicinc.com> <srirrama@codeaurora.org>
 Sriram Yagnaraman <sriram.yagnaraman@ericsson.com> <sriram.yagnaraman@est.tech>
 Stanislav Fomichev <sdf@fomichev.me> <sdf@google.com>
+Stanislav Fomichev <sdf@fomichev.me> <stfomichev@gmail.com>
 Stefan Wahren <wahrenst@gmx.net> <stefan.wahren@i2se.com>
 Stéphane Witzmann <stephane.witzmann@ubpmes.univ-bpclermont.fr>
 Stephen Hemminger <stephen@networkplumber.org> <shemminger@linux-foundation.org>
diff --git a/MAINTAINERS b/MAINTAINERS
index 8d314e169486..8e109f4436eb 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -4555,6 +4555,7 @@ BPF [NETWORKING] (tcx & tc BPF, sock_addr)
 M:	Martin KaFai Lau <martin.lau@linux.dev>
 M:	Daniel Borkmann <daniel@iogearbox.net>
 R:	John Fastabend <john.fastabend@gmail.com>
+R:	Stanislav Fomichev <sdf@fomichev.me>
 L:	bpf@vger.kernel.org
 L:	netdev@vger.kernel.org
 S:	Maintained
@@ -26948,6 +26949,7 @@ M:	David S. Miller <davem@davemloft.net>
 M:	Jakub Kicinski <kuba@kernel.org>
 M:	Jesper Dangaard Brouer <hawk@kernel.org>
 M:	John Fastabend <john.fastabend@gmail.com>
+R:	Stanislav Fomichev <sdf@fomichev.me>
 L:	netdev@vger.kernel.org
 L:	bpf@vger.kernel.org
 S:	Supported
@@ -26969,6 +26971,7 @@ M:	Björn Töpel <bjorn@kernel.org>
 M:	Magnus Karlsson <magnus.karlsson@intel.com>
 M:	Maciej Fijalkowski <maciej.fijalkowski@intel.com>
 R:	Jonathan Lemon <jonathan.lemon@gmail.com>
+R:	Stanislav Fomichev <sdf@fomichev.me>
 L:	netdev@vger.kernel.org
 L:	bpf@vger.kernel.org
 S:	Maintained

From 1a8953f4f7746c6a515989774fe03047c522c613 Mon Sep 17 00:00:00 2001
From: Zhang Heng <zhangheng@kylinos.cn>
Date: Thu, 5 Jun 2025 15:29:59 +0800
Subject: [PATCH 0179/1334] HID: Add IGNORE quirk for SMARTLINKTECHNOLOGY

MARTLINKTECHNOLOGY is a microphone device, when the HID interface in an
audio device is requested to get specific report id, the following error
may occur.

[  562.939373] usb 1-1.4.1.2: new full-speed USB device number 21 using xhci_hcd
[  563.104908] usb 1-1.4.1.2: New USB device found, idVendor=4c4a, idProduct=4155, bcdDevice= 1.00
[  563.104910] usb 1-1.4.1.2: New USB device strings: Mfr=1, Product=2, SerialNumber=3
[  563.104911] usb 1-1.4.1.2: Product: USB Composite Device
[  563.104912] usb 1-1.4.1.2: Manufacturer: SmartlinkTechnology
[  563.104913] usb 1-1.4.1.2: SerialNumber: 20201111000001
[  563.229499] input: SmartlinkTechnology USB Composite Device as /devices/pci0000:00/0000:00:07.1/0000:04:00.3/usb1/1-1/1-1.4/1-1.4.1/1-1.4.1.2/1-1.4.1.2:1.2/0003:4C4A:4155.000F/input/input35
[  563.291505] hid-generic 0003:4C4A:4155.000F: input,hidraw2: USB HID v2.01 Keyboard [SmartlinkTechnology USB Composite Device] on usb-0000:04:00.3-1.4.1.2/input2
[  563.291557] usbhid 1-1.4.1.2:1.3: couldn't find an input interrupt endpoint
[  568.506654] usb 1-1.4.1.2: 1:1: usb_set_interface failed (-110)
[  573.626656] usb 1-1.4.1.2: 1:1: usb_set_interface failed (-110)
[  578.746657] usb 1-1.4.1.2: 1:1: usb_set_interface failed (-110)
[  583.866655] usb 1-1.4.1.2: 1:1: usb_set_interface failed (-110)
[  588.986657] usb 1-1.4.1.2: 1:1: usb_set_interface failed (-110)

Ignore HID interface. The device is working properly.

Signed-off-by: Zhang Heng <zhangheng@kylinos.cn>
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
 drivers/hid/hid-ids.h    | 3 +++
 drivers/hid/hid-quirks.c | 1 +
 2 files changed, 4 insertions(+)

diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h
index f1e00641e26e..2d3769405ec3 100644
--- a/drivers/hid/hid-ids.h
+++ b/drivers/hid/hid-ids.h
@@ -1527,4 +1527,7 @@
 #define USB_VENDOR_ID_SIGNOTEC			0x2133
 #define USB_DEVICE_ID_SIGNOTEC_VIEWSONIC_PD1011	0x0018
 
+#define USB_VENDOR_ID_SMARTLINKTECHNOLOGY              0x4c4a
+#define USB_DEVICE_ID_SMARTLINKTECHNOLOGY_4155         0x4155
+
 #endif
diff --git a/drivers/hid/hid-quirks.c b/drivers/hid/hid-quirks.c
index 96f3c712acc8..31508da93ba2 100644
--- a/drivers/hid/hid-quirks.c
+++ b/drivers/hid/hid-quirks.c
@@ -906,6 +906,7 @@ static const struct hid_device_id hid_ignore_list[] = {
 #endif
 	{ HID_USB_DEVICE(USB_VENDOR_ID_YEALINK, USB_DEVICE_ID_YEALINK_P1K_P4K_B2K) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_QUANTA, USB_DEVICE_ID_QUANTA_HP_5MP_CAMERA_5473) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_SMARTLINKTECHNOLOGY, USB_DEVICE_ID_SMARTLINKTECHNOLOGY_4155) },
 	{ }
 };
 

From 9327e3ee5b077c4ab4495a09b67624f670ed88b6 Mon Sep 17 00:00:00 2001
From: Iusico Maxim <iusico.maxim@libero.it>
Date: Thu, 5 Jun 2025 19:55:50 +0200
Subject: [PATCH 0180/1334] HID: lenovo: Restrict F7/9/11 mode to compact
 keyboards only

Commit 2f2bd7cbd1d1 ("hid: lenovo: Resend all settings on reset_resume
for compact keyboards") introduced a regression for ThinkPad TrackPoint
Keyboard II by removing the conditional check for enabling F7/9/11 mode
needed for compact keyboards only. As a result, the non-compact
keyboards can no longer toggle Fn-lock via Fn+Esc, although it can be
controlled via sysfs knob that directly sends raw commands.

This patch restores the previous conditional check without any
additions.

Cc: stable@vger.kernel.org
Fixes: 2f2bd7cbd1d1 ("hid: lenovo: Resend all settings on reset_resume for compact keyboards")
Signed-off-by: Iusico Maxim <iusico.maxim@libero.it>
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
 drivers/hid/hid-lenovo.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/drivers/hid/hid-lenovo.c b/drivers/hid/hid-lenovo.c
index af29ba840522..a3c23a72316a 100644
--- a/drivers/hid/hid-lenovo.c
+++ b/drivers/hid/hid-lenovo.c
@@ -548,11 +548,14 @@ static void lenovo_features_set_cptkbd(struct hid_device *hdev)
 
 	/*
 	 * Tell the keyboard a driver understands it, and turn F7, F9, F11 into
-	 * regular keys
+	 * regular keys (Compact only)
 	 */
-	ret = lenovo_send_cmd_cptkbd(hdev, 0x01, 0x03);
-	if (ret)
-		hid_warn(hdev, "Failed to switch F7/9/11 mode: %d\n", ret);
+	if (hdev->product == USB_DEVICE_ID_LENOVO_CUSBKBD ||
+	    hdev->product == USB_DEVICE_ID_LENOVO_CBTKBD) {
+		ret = lenovo_send_cmd_cptkbd(hdev, 0x01, 0x03);
+		if (ret)
+			hid_warn(hdev, "Failed to switch F7/9/11 mode: %d\n", ret);
+	}
 
 	/* Switch middle button to native mode */
 	ret = lenovo_send_cmd_cptkbd(hdev, 0x09, 0x01);

From 0e97f5b6a0808fa2ea865280708511c817d4bca3 Mon Sep 17 00:00:00 2001
From: Zhang Lixu <lixu.zhang@intel.com>
Date: Tue, 10 Jun 2025 10:01:31 +0800
Subject: [PATCH 0181/1334] hid: intel-ish-hid: Use PCI_DEVICE_DATA() macro for
 ISH device table

Replace the usage of PCI_VDEVICE() with driver_data assignment in the ISH
PCI device table with the PCI_DEVICE_DATA() macro. This improves code
readability.

Signed-off-by: Zhang Lixu <lixu.zhang@intel.com>
Acked-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
 drivers/hid/intel-ish-hid/ipc/pci-ish.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/hid/intel-ish-hid/ipc/pci-ish.c b/drivers/hid/intel-ish-hid/ipc/pci-ish.c
index ff0fc8010072..0db41ed74a14 100644
--- a/drivers/hid/intel-ish-hid/ipc/pci-ish.c
+++ b/drivers/hid/intel-ish-hid/ipc/pci-ish.c
@@ -67,9 +67,9 @@ static const struct pci_device_id ish_pci_tbl[] = {
 	{PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_ISH_MTL_P)},
 	{PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_ISH_ARL_H)},
 	{PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_ISH_ARL_S)},
-	{PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_ISH_LNL_M), .driver_data = ISHTP_DRIVER_DATA_LNL_M},
-	{PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_ISH_PTL_H), .driver_data = ISHTP_DRIVER_DATA_PTL},
-	{PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_ISH_PTL_P), .driver_data = ISHTP_DRIVER_DATA_PTL},
+	{PCI_DEVICE_DATA(INTEL, ISH_LNL_M, ISHTP_DRIVER_DATA_LNL_M)},
+	{PCI_DEVICE_DATA(INTEL, ISH_PTL_H, ISHTP_DRIVER_DATA_PTL)},
+	{PCI_DEVICE_DATA(INTEL, ISH_PTL_P, ISHTP_DRIVER_DATA_PTL)},
 	{}
 };
 MODULE_DEVICE_TABLE(pci, ish_pci_tbl);

From 5cdb49a680b45f467e9d915c0e74756bc0c67c57 Mon Sep 17 00:00:00 2001
From: Zhang Lixu <lixu.zhang@intel.com>
Date: Tue, 10 Jun 2025 10:01:32 +0800
Subject: [PATCH 0182/1334] HID: intel-ish-hid: ipc: Add Wildcat Lake PCI
 device ID

Add device ID of Wildcat Lake into ishtp support list.

Signed-off-by: Zhang Lixu <lixu.zhang@intel.com>
Acked-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
 drivers/hid/intel-ish-hid/ipc/hw-ish.h  | 1 +
 drivers/hid/intel-ish-hid/ipc/pci-ish.c | 6 ++++++
 2 files changed, 7 insertions(+)

diff --git a/drivers/hid/intel-ish-hid/ipc/hw-ish.h b/drivers/hid/intel-ish-hid/ipc/hw-ish.h
index 07e90d51f073..fa5d68c36313 100644
--- a/drivers/hid/intel-ish-hid/ipc/hw-ish.h
+++ b/drivers/hid/intel-ish-hid/ipc/hw-ish.h
@@ -38,6 +38,7 @@
 #define PCI_DEVICE_ID_INTEL_ISH_LNL_M		0xA845
 #define PCI_DEVICE_ID_INTEL_ISH_PTL_H		0xE345
 #define PCI_DEVICE_ID_INTEL_ISH_PTL_P		0xE445
+#define PCI_DEVICE_ID_INTEL_ISH_WCL		0x4D45
 
 #define	REVISION_ID_CHT_A0	0x6
 #define	REVISION_ID_CHT_Ax_SI	0x0
diff --git a/drivers/hid/intel-ish-hid/ipc/pci-ish.c b/drivers/hid/intel-ish-hid/ipc/pci-ish.c
index 0db41ed74a14..c57483224db6 100644
--- a/drivers/hid/intel-ish-hid/ipc/pci-ish.c
+++ b/drivers/hid/intel-ish-hid/ipc/pci-ish.c
@@ -27,10 +27,12 @@ enum ishtp_driver_data_index {
 	ISHTP_DRIVER_DATA_NONE,
 	ISHTP_DRIVER_DATA_LNL_M,
 	ISHTP_DRIVER_DATA_PTL,
+	ISHTP_DRIVER_DATA_WCL,
 };
 
 #define ISH_FW_GEN_LNL_M "lnlm"
 #define ISH_FW_GEN_PTL "ptl"
+#define ISH_FW_GEN_WCL "wcl"
 
 #define ISH_FIRMWARE_PATH(gen) "intel/ish/ish_" gen ".bin"
 #define ISH_FIRMWARE_PATH_ALL "intel/ish/ish_*.bin"
@@ -42,6 +44,9 @@ static struct ishtp_driver_data ishtp_driver_data[] = {
 	[ISHTP_DRIVER_DATA_PTL] = {
 		.fw_generation = ISH_FW_GEN_PTL,
 	},
+	[ISHTP_DRIVER_DATA_WCL] = {
+		.fw_generation = ISH_FW_GEN_WCL,
+	},
 };
 
 static const struct pci_device_id ish_pci_tbl[] = {
@@ -70,6 +75,7 @@ static const struct pci_device_id ish_pci_tbl[] = {
 	{PCI_DEVICE_DATA(INTEL, ISH_LNL_M, ISHTP_DRIVER_DATA_LNL_M)},
 	{PCI_DEVICE_DATA(INTEL, ISH_PTL_H, ISHTP_DRIVER_DATA_PTL)},
 	{PCI_DEVICE_DATA(INTEL, ISH_PTL_P, ISHTP_DRIVER_DATA_PTL)},
+	{PCI_DEVICE_DATA(INTEL, ISH_WCL, ISHTP_DRIVER_DATA_WCL)},
 	{}
 };
 MODULE_DEVICE_TABLE(pci, ish_pci_tbl);

From e0eb1b6b0cd29ca7793c501d5960fd36ba11f110 Mon Sep 17 00:00:00 2001
From: Fangrui Song <i@maskray.me>
Date: Mon, 2 Jun 2025 20:48:44 -0700
Subject: [PATCH 0183/1334] riscv: vdso: Exclude .rodata from the PT_DYNAMIC
 segment

.rodata is implicitly included in the PT_DYNAMIC segment due to
inheriting the segment of the preceding .dynamic section (in both GNU ld
and LLD).  When the .rodata section's size is not a multiple of 16
bytes on riscv64, llvm-readelf will report a "PT_DYNAMIC dynamic table
is invalid" warning.  Note: in the presence of the .dynamic section, GNU
readelf and llvm-readelf's -d option decodes the dynamic section using
the section.

This issue arose after commit 8f8c1ff879fab60f80f3a7aec3000f47e5b03ba9
("riscv: vdso.lds.S: remove hardcoded 0x800 .text start addr"), which
placed .rodata directly after .dynamic by removing .eh_frame.

This patch resolves the implicit inclusion into PT_DYNAMIC by explicitly
specifying the :text output section phdr.

Reported-by: Nathan Chancellor <nathan@kernel.org>
Closes: https://github.com/ClangBuiltLinux/linux/issues/2093
Signed-off-by: Fangrui Song <i@maskray.me>
Tested-by: Nathan Chancellor <nathan@kernel.org>
Link: https://lore.kernel.org/r/20250602-riscv-vdso-v1-1-0620cf63cff0@maskray.me
Signed-off-by: Palmer Dabbelt <palmer@dabbelt.com>
---
 arch/riscv/kernel/vdso/vdso.lds.S | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/riscv/kernel/vdso/vdso.lds.S b/arch/riscv/kernel/vdso/vdso.lds.S
index 7c15b0f4ee3b..c29ef12a63bb 100644
--- a/arch/riscv/kernel/vdso/vdso.lds.S
+++ b/arch/riscv/kernel/vdso/vdso.lds.S
@@ -30,7 +30,7 @@ SECTIONS
 		*(.data .data.* .gnu.linkonce.d.*)
 		*(.dynbss)
 		*(.bss .bss.* .gnu.linkonce.b.*)
-	}
+	}						:text
 
 	.note		: { *(.note.*) }		:text	:note
 

From fdc9be90929081ed5a9658583aa5f3121d5e8365 Mon Sep 17 00:00:00 2001
From: Li Ming <ming.li@zohomail.com>
Date: Tue, 3 Jun 2025 18:43:13 +0800
Subject: [PATCH 0184/1334] cxl/edac: Fix the min_scrub_cycle of a region
 miscalculation

When trying to update the scrub_cycle value of a cxl region, which means
updating the scrub_cycle value of each memdev under a cxl region. cxl
driver needs to guarantee the new scrub_cycle value is greater than the
min_scrub_cycle value of a memdev, otherwise the updating operation will
fail(Per Table 8-223 in CXL r3.2 section 8.2.10.9.11.1).

Current implementation logic of getting the min_scrub_cycle value of a
cxl region is that getting the min_scrub_cycle value of each memdevs
under the cxl region, then using the minimum min_scrub_cycle value as
the region's min_scrub_cycle. Checking if the new scrub_cycle value is
greater than this value. If yes, updating the new scrub_cycle value to
each memdevs. The issue is that the new scrub_cycle value is possibly
greater than the minimum min_scrub_cycle value of all memdevs but less
than the maximum min_scrub_cycle value of all memdevs if memdevs have
a different min_scrub_cycle value. The updating operation will always
fail on these memdevs which have a greater min_scrub_cycle than the new
scrub_cycle.

The correct implementation logic is to get the maximum value of these
memdevs' min_scrub_cycle, check if the new scrub_cycle value is greater
than the value. If yes, the new scrub_cycle value is fit for the region.

The change also impacts the result of
cxl_patrol_scrub_get_min_scrub_cycle(), the interface returned the
minimum min_scrub_cycle value among all memdevs under the region before
the change. The interface will return the maximum min_scrub_cycle value
among all memdevs under the region with the change.

Signed-off-by: Li Ming <ming.li@zohomail.com>
Reviewed-by: Jonathan Cameron <jonathan.cameron@huawei.com>
Reviewed-by: Dave Jiang <dave.jiang@intel.com>
Reviewed-by: Shiju Jose <shiju.jose@huawei.com>
Reviewed-by: Davidlohr Bueso <dave@stgolabs.net>
Link: https://patch.msgid.link/20250603104314.25569-1-ming.li@zohomail.com
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
---
 drivers/cxl/core/edac.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/cxl/core/edac.c b/drivers/cxl/core/edac.c
index 2cbc664e5d62..0ef245d0bd9f 100644
--- a/drivers/cxl/core/edac.c
+++ b/drivers/cxl/core/edac.c
@@ -103,10 +103,10 @@ static int cxl_scrub_get_attrbs(struct cxl_patrol_scrub_context *cxl_ps_ctx,
 				u8 *cap, u16 *cycle, u8 *flags, u8 *min_cycle)
 {
 	struct cxl_mailbox *cxl_mbox;
-	u8 min_scrub_cycle = U8_MAX;
 	struct cxl_region_params *p;
 	struct cxl_memdev *cxlmd;
 	struct cxl_region *cxlr;
+	u8 min_scrub_cycle = 0;
 	int i, ret;
 
 	if (!cxl_ps_ctx->cxlr) {
@@ -133,8 +133,12 @@ static int cxl_scrub_get_attrbs(struct cxl_patrol_scrub_context *cxl_ps_ctx,
 		if (ret)
 			return ret;
 
+		/*
+		 * The min_scrub_cycle of a region is the max of minimum scrub
+		 * cycles supported by memdevs that back the region.
+		 */
 		if (min_cycle)
-			min_scrub_cycle = min(*min_cycle, min_scrub_cycle);
+			min_scrub_cycle = max(*min_cycle, min_scrub_cycle);
 	}
 
 	if (min_cycle)

From 85cc50bfcb8b08c9304925b66cd2bc83c1c765bf Mon Sep 17 00:00:00 2001
From: Li Ming <ming.li@zohomail.com>
Date: Tue, 3 Jun 2025 18:43:14 +0800
Subject: [PATCH 0185/1334] cxl/Documentation: Add more description about
 min/max scrub cycle

user can configurare scrub cycle for a region or a memory device via
sysfs interface. Currently, these interfaces have not enough description
for the return value. So adding return value description to these
interfaces.

Suggested-by: Alison Schofield <alison.schofield@intel.com>
Signed-off-by: Shiju Jose <shiju.jose@huawei.com>
Signed-off-by: Li Ming <ming.li@zohomail.com>
Reviewed-by: Jonathan Cameron <jonathan.cameron@huawei.com>
Reviewed-by: Dave Jiang <dave.jiang@intel.com>
Reviewed-by: Davidlohr Bueso <dave@stgolabs.net>
Link: https://patch.msgid.link/20250603104314.25569-2-ming.li@zohomail.com
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
---
 Documentation/ABI/testing/sysfs-edac-scrub | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/Documentation/ABI/testing/sysfs-edac-scrub b/Documentation/ABI/testing/sysfs-edac-scrub
index c43be90deab4..ab6014743da5 100644
--- a/Documentation/ABI/testing/sysfs-edac-scrub
+++ b/Documentation/ABI/testing/sysfs-edac-scrub
@@ -49,6 +49,12 @@ Description:
 		(RO) Supported minimum scrub cycle duration in seconds
 		by the memory scrubber.
 
+		Device-based scrub: returns the minimum scrub cycle
+		supported by the memory device.
+
+		Region-based scrub: returns the max of minimum scrub cycles
+		supported by individual memory devices that back the region.
+
 What:		/sys/bus/edac/devices/<dev-name>/scrubX/max_cycle_duration
 Date:		March 2025
 KernelVersion:	6.15
@@ -57,6 +63,16 @@ Description:
 		(RO) Supported maximum scrub cycle duration in seconds
 		by the memory scrubber.
 
+		Device-based scrub: returns the maximum scrub cycle supported
+		by the memory device.
+
+		Region-based scrub: returns the min of maximum scrub cycles
+		supported by individual memory devices that back the region.
+
+		If the memory device does not provide maximum scrub cycle
+		information, return the maximum supported value of the scrub
+		cycle field.
+
 What:		/sys/bus/edac/devices/<dev-name>/scrubX/current_cycle_duration
 Date:		March 2025
 KernelVersion:	6.15

From dc9c67820f81ee0d34f9095195228fcb828315ff Mon Sep 17 00:00:00 2001
From: Lucas Sanchez Sagrado <lucsansag@gmail.com>
Date: Mon, 9 Jun 2025 16:55:36 +0200
Subject: [PATCH 0186/1334] net: usb: r8152: Add device ID for TP-Link UE200

The TP-Link UE200 is a RTL8152B based USB 2.0 Fast Ethernet adapter. This
patch adds its device ID. It has been tested on Ubuntu 22.04.5.

Signed-off-by: Lucas Sanchez Sagrado <lucsansag@gmail.com>
Reviewed-by: Subbaraya Sundeep <sbhatta@marvell.com>
Link: https://patch.msgid.link/20250609145536.26648-1-lucsansag@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/usb/r8152.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index d6589b24c68d..44cba7acfe7d 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -10054,6 +10054,7 @@ static const struct usb_device_id rtl8152_table[] = {
 	{ USB_DEVICE(VENDOR_ID_LINKSYS, 0x0041) },
 	{ USB_DEVICE(VENDOR_ID_NVIDIA,  0x09ff) },
 	{ USB_DEVICE(VENDOR_ID_TPLINK,  0x0601) },
+	{ USB_DEVICE(VENDOR_ID_TPLINK,  0x0602) },
 	{ USB_DEVICE(VENDOR_ID_DLINK,   0xb301) },
 	{ USB_DEVICE(VENDOR_ID_DELL,    0xb097) },
 	{ USB_DEVICE(VENDOR_ID_ASUS,    0x1976) },

From f3054152c12e2eed1e72704aff47b0ea58229584 Mon Sep 17 00:00:00 2001
From: Thomas Zeitlhofer <thomas.zeitlhofer+lkml@ze-it.at>
Date: Mon, 19 May 2025 10:54:46 +0200
Subject: [PATCH 0187/1334] HID: wacom: fix crash in
 wacom_aes_battery_handler()

Commit fd2a9b29dc9c ("HID: wacom: Remove AES power_supply after extended
inactivity") introduced wacom_aes_battery_handler() which is scheduled
as a delayed work (aes_battery_work).

In wacom_remove(), aes_battery_work is not canceled. Consequently, if
the device is removed while aes_battery_work is still pending, then hard
crashes or "Oops: general protection fault..." are experienced when
wacom_aes_battery_handler() is finally called. E.g., this happens with
built-in USB devices after resume from hibernate when aes_battery_work
was still pending at the time of hibernation.

So, take care to cancel aes_battery_work in wacom_remove().

Fixes: fd2a9b29dc9c ("HID: wacom: Remove AES power_supply after extended inactivity")
Signed-off-by: Thomas Zeitlhofer <thomas.zeitlhofer+lkml@ze-it.at>
Acked-by: Ping Cheng <ping.cheng@wacom.com>
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
 drivers/hid/wacom_sys.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/hid/wacom_sys.c b/drivers/hid/wacom_sys.c
index 1257131b1e34..9a57504e51a1 100644
--- a/drivers/hid/wacom_sys.c
+++ b/drivers/hid/wacom_sys.c
@@ -2905,6 +2905,7 @@ static void wacom_remove(struct hid_device *hdev)
 	hid_hw_stop(hdev);
 
 	cancel_delayed_work_sync(&wacom->init_work);
+	cancel_delayed_work_sync(&wacom->aes_battery_work);
 	cancel_work_sync(&wacom->wireless_work);
 	cancel_work_sync(&wacom->battery_work);
 	cancel_work_sync(&wacom->remote_work);

From 2660a544fdc0940bba15f70508a46cf9a6491230 Mon Sep 17 00:00:00 2001
From: Michal Luczaj <mhal@rbox.co>
Date: Mon, 9 Jun 2025 19:08:03 +0200
Subject: [PATCH 0188/1334] net: Fix TOCTOU issue in sk_is_readable()

sk->sk_prot->sock_is_readable is a valid function pointer when sk resides
in a sockmap. After the last sk_psock_put() (which usually happens when
socket is removed from sockmap), sk->sk_prot gets restored and
sk->sk_prot->sock_is_readable becomes NULL.

This makes sk_is_readable() racy, if the value of sk->sk_prot is reloaded
after the initial check. Which in turn may lead to a null pointer
dereference.

Ensure the function pointer does not turn NULL after the check.

Fixes: 8934ce2fd081 ("bpf: sockmap redirect ingress support")
Suggested-by: Jakub Sitnicki <jakub@cloudflare.com>
Signed-off-by: Michal Luczaj <mhal@rbox.co>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://patch.msgid.link/20250609-skisreadable-toctou-v1-1-d0dfb2d62c37@rbox.co
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/sock.h | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/include/net/sock.h b/include/net/sock.h
index 92e7c1aae3cc..4c37015b7cf7 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -3010,8 +3010,11 @@ int sock_ioctl_inout(struct sock *sk, unsigned int cmd,
 int sk_ioctl(struct sock *sk, unsigned int cmd, void __user *arg);
 static inline bool sk_is_readable(struct sock *sk)
 {
-	if (sk->sk_prot->sock_is_readable)
-		return sk->sk_prot->sock_is_readable(sk);
+	const struct proto *prot = READ_ONCE(sk->sk_prot);
+
+	if (prot->sock_is_readable)
+		return prot->sock_is_readable(sk);
+
 	return false;
 }
 #endif	/* _SOCK_H */

From c85bf1975108d2e2431c11d1cb7e95aca587dfbe Mon Sep 17 00:00:00 2001
From: Gustavo Luiz Duarte <gustavold@gmail.com>
Date: Mon, 9 Jun 2025 11:24:20 -0700
Subject: [PATCH 0189/1334] netconsole: fix appending sysdata when
 sysdata_fields == SYSDATA_RELEASE

Before appending sysdata, prepare_extradata() checks if any feature is
enabled in sysdata_fields (and exits early if none is enabled).

When SYSDATA_RELEASE was introduced, we missed adding it to the list of
features being checked against sysdata_fields in prepare_extradata().
The result was that, if only SYSDATA_RELEASE is enabled in
sysdata_fields, we incorreclty exit early and fail to append the
release.

Instead of checking specific bits in sysdata_fields, check if
sysdata_fields has ALL bit zeroed and exit early if true. This fixes
case when only SYSDATA_RELEASE enabled and makes the code more general /
less error prone in future feature implementation.

Signed-off-by: Gustavo Luiz Duarte <gustavold@gmail.com>
Reviewed-by: Breno Leitao <leitao@debian.org>
Fixes: cfcc9239e78a ("netconsole: append release to sysdata")
Link: https://patch.msgid.link/20250609-netconsole-fix-v1-1-17543611ae31@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/netconsole.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/netconsole.c b/drivers/net/netconsole.c
index 4289ccd3e41b..176935a8645f 100644
--- a/drivers/net/netconsole.c
+++ b/drivers/net/netconsole.c
@@ -1252,7 +1252,6 @@ static int sysdata_append_release(struct netconsole_target *nt, int offset)
  */
 static int prepare_extradata(struct netconsole_target *nt)
 {
-	u32 fields = SYSDATA_CPU_NR | SYSDATA_TASKNAME;
 	int extradata_len;
 
 	/* userdata was appended when configfs write helper was called
@@ -1260,7 +1259,7 @@ static int prepare_extradata(struct netconsole_target *nt)
 	 */
 	extradata_len = nt->userdata_length;
 
-	if (!(nt->sysdata_fields & fields))
+	if (!nt->sysdata_fields)
 		goto out;
 
 	if (nt->sysdata_fields & SYSDATA_CPU_NR)

From f478d68b653323b691280b40fbd3b8ca1ac75aa2 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Mon, 9 Jun 2025 22:40:35 +0200
Subject: [PATCH 0190/1334] net: airoha: Enable RX queues 16-31

Fix RX_DONE_INT_MASK definition in order to enable RX queues 16-31.

Fixes: f252493e18353 ("net: airoha: Enable multiple IRQ lines support in airoha_eth driver.")
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Link: https://patch.msgid.link/20250609-aioha-fix-rx-queue-mask-v1-1-f33706a06fa2@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/airoha/airoha_regs.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/airoha/airoha_regs.h b/drivers/net/ethernet/airoha/airoha_regs.h
index 04187eb40ec6..150c85995cc1 100644
--- a/drivers/net/ethernet/airoha/airoha_regs.h
+++ b/drivers/net/ethernet/airoha/airoha_regs.h
@@ -614,8 +614,9 @@
 	 RX19_DONE_INT_MASK | RX18_DONE_INT_MASK |	\
 	 RX17_DONE_INT_MASK | RX16_DONE_INT_MASK)
 
-#define RX_DONE_INT_MASK	(RX_DONE_HIGH_INT_MASK | RX_DONE_LOW_INT_MASK)
 #define RX_DONE_HIGH_OFFSET	fls(RX_DONE_HIGH_INT_MASK)
+#define RX_DONE_INT_MASK	\
+	((RX_DONE_HIGH_INT_MASK << RX_DONE_HIGH_OFFSET) | RX_DONE_LOW_INT_MASK)
 
 #define INT_RX2_MASK(_n)				\
 	((RX_NO_CPU_DSCP_HIGH_INT_MASK & (_n)) |	\

From 8d90d9872edae7e78c3a12b98e239bfaa66f3639 Mon Sep 17 00:00:00 2001
From: Charles Mirabile <cmirabil@redhat.com>
Date: Fri, 30 May 2025 17:14:22 -0400
Subject: [PATCH 0191/1334] riscv: fix runtime constant support for nommu
 kernels

the `__runtime_fixup_32` function does not handle the case where `val` is
zero correctly (as might occur when patching a nommu kernel and referring
to a physical address below the 4GiB boundary whose upper 32 bits are all
zero) because nothing in the existing logic prevents the code from taking
the `else` branch of both nop-checks and emitting two `nop` instructions.

This leaves random garbage in the register that is supposed to receive the
upper 32 bits of the pointer instead of zero that when combined with the
value for the lower 32 bits yields an invalid pointer and causes a kernel
panic when that pointer is eventually accessed.

The author clearly considered the fact that if the `lui` is converted into
a `nop` that the second instruction needs to be adjusted to become an `li`
instead of an `addi`, hence introducing the `addi_insn_mask` variable, but
didn't follow that logic through fully to the case where the `else` branch
executes. To fix it just adjust the logic to ensure that the second `else`
branch is not taken if the first instruction will be patched to a `nop`.

Fixes: a44fb5722199 ("riscv: Add runtime constant support")

Signed-off-by: Charles Mirabile <cmirabil@redhat.com>
Reviewed-by: Charlie Jenkins <charlie@rivosinc.com>
Tested-by: Charlie Jenkins <charlie@rivosinc.com>
Link: https://lore.kernel.org/r/20250530211422.784415-2-cmirabil@redhat.com
Signed-off-by: Palmer Dabbelt <palmer@dabbelt.com>
---
 arch/riscv/include/asm/runtime-const.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/riscv/include/asm/runtime-const.h b/arch/riscv/include/asm/runtime-const.h
index 451fd76b8811..d766e2b9e6df 100644
--- a/arch/riscv/include/asm/runtime-const.h
+++ b/arch/riscv/include/asm/runtime-const.h
@@ -206,7 +206,7 @@ static inline void __runtime_fixup_32(__le16 *lui_parcel, __le16 *addi_parcel, u
 		addi_insn_mask &= 0x07fff;
 	}
 
-	if (lower_immediate & 0x00000fff) {
+	if (lower_immediate & 0x00000fff || lui_insn == RISCV_INSN_NOP4) {
 		/* replace upper 12 bits of addi with lower 12 bits of val */
 		addi_insn &= addi_insn_mask;
 		addi_insn |= (lower_immediate & 0x00000fff) << 20;

From 40a98e702b528c631094f2e524d309faf33dc774 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Tue, 10 Jun 2025 12:16:00 -0700
Subject: [PATCH 0192/1334] crypto: hkdf - move to late_initcall

The HKDF self-tests depend on the HMAC algorithms being registered.
HMAC is now registered at module_init, which put it at the same level as
HKDF.  Move HKDF to late_initcall so that it runs afterwards.

Fixes: ef93f1562803 ("Revert "crypto: run initcalls for generic implementations earlier"")
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 crypto/hkdf.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/crypto/hkdf.c b/crypto/hkdf.c
index f24c2a8d4df9..82d1b32ca6ce 100644
--- a/crypto/hkdf.c
+++ b/crypto/hkdf.c
@@ -566,7 +566,7 @@ static int __init crypto_hkdf_module_init(void)
 
 static void __exit crypto_hkdf_module_exit(void) {}
 
-module_init(crypto_hkdf_module_init);
+late_initcall(crypto_hkdf_module_init);
 module_exit(crypto_hkdf_module_exit);
 
 MODULE_LICENSE("GPL");

From b8d3291d3185b5c69ba36362ae1a370f06a33e5c Mon Sep 17 00:00:00 2001
From: Nathan Chancellor <nathan@kernel.org>
Date: Tue, 10 Jun 2025 12:40:38 -0700
Subject: [PATCH 0193/1334] drm/sitronix: st7571-i2c: Select VIDEOMODE_HELPERS

This driver requires of_get_display_timing() from
CONFIG_VIDEOMODE_HELPERS but does not select it. If no other driver
selects it, there will be a failure from the linker if the driver is
built in or modpost if it is a module.

  ERROR: modpost: "of_get_display_timing" [drivers/gpu/drm/sitronix/st7571-i2c.ko] undefined!

Select CONFIG_VIDEOMODE_HELPERS to resolve the build failure.

Fixes: 4b35f0f41ee2 ("drm/st7571-i2c: add support for Sitronix ST7571 LCD controller")
Signed-off-by: Nathan Chancellor <nathan@kernel.org>
Link: https://lore.kernel.org/r/20250610-drm-st7571-i2c-select-videomode-helpers-v1-1-d30b50ff6e64@kernel.org
Signed-off-by: Maxime Ripard <mripard@kernel.org>
---
 drivers/gpu/drm/sitronix/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/sitronix/Kconfig b/drivers/gpu/drm/sitronix/Kconfig
index c069d0d41775..741d1bb4b83f 100644
--- a/drivers/gpu/drm/sitronix/Kconfig
+++ b/drivers/gpu/drm/sitronix/Kconfig
@@ -5,6 +5,7 @@ config DRM_ST7571_I2C
 	select DRM_GEM_SHMEM_HELPER
 	select DRM_KMS_HELPER
 	select REGMAP_I2C
+	select VIDEOMODE_HELPERS
 	help
 	  DRM driver for Sitronix ST7571 panels controlled over I2C.
 

From d9816ec74e6d6aa29219d010bba3f780ba1d9d75 Mon Sep 17 00:00:00 2001
From: Carlos Fernandez <carlos.fernandez@technica-engineering.de>
Date: Mon, 9 Jun 2025 09:26:26 +0200
Subject: [PATCH 0194/1334] macsec: MACsec SCI assignment for ES = 0

According to 802.1AE standard, when ES and SC flags in TCI are zero,
used SCI should be the current active SC_RX. Current code uses the
header MAC address. Without this patch, when ES flag is 0 (using a
bridge or switch), header MAC will not fit the SCI and MACSec frames
will be discarted.

In order to test this issue, MACsec link should be stablished between
two interfaces, setting SC and ES flags to zero and a port identifier
different than one. For example, using ip macsec tools:

ip link add link $ETH0 macsec0 type macsec port 11 send_sci off
end_station off
ip macsec add macsec0 tx sa 0 pn 2 on key 01 $ETH1_KEY
ip macsec add macsec0 rx port 11 address $ETH1_MAC
ip macsec add macsec0 rx port 11 address $ETH1_MAC sa 0 pn 2 on key 02
ip link set dev macsec0 up

ip link add link $ETH1 macsec1 type macsec port 11 send_sci off
end_station off
ip macsec add macsec1 tx sa 0 pn 2 on key 01 $ETH0_KEY
ip macsec add macsec1 rx port 11 address $ETH0_MAC
ip macsec add macsec1 rx port 11 address $ETH0_MAC sa 0 pn 2 on key 02
ip link set dev macsec1 up

Fixes: c09440f7dcb3 ("macsec: introduce IEEE 802.1AE driver")
Co-developed-by: Andreu Montiel <Andreu.Montiel@technica-engineering.de>
Signed-off-by: Andreu Montiel <Andreu.Montiel@technica-engineering.de>
Signed-off-by: Carlos Fernandez <carlos.fernandez@technica-engineering.de>
Reviewed-by: Subbaraya Sundeep <sbhatta@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/macsec.c | 40 ++++++++++++++++++++++++++++++++++------
 1 file changed, 34 insertions(+), 6 deletions(-)

diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c
index 3d315e30ee47..7edbe76b5455 100644
--- a/drivers/net/macsec.c
+++ b/drivers/net/macsec.c
@@ -247,15 +247,39 @@ static sci_t make_sci(const u8 *addr, __be16 port)
 	return sci;
 }
 
-static sci_t macsec_frame_sci(struct macsec_eth_header *hdr, bool sci_present)
+static sci_t macsec_active_sci(struct macsec_secy *secy)
 {
-	sci_t sci;
+	struct macsec_rx_sc *rx_sc = rcu_dereference_bh(secy->rx_sc);
 
-	if (sci_present)
+	/* Case single RX SC */
+	if (rx_sc && !rcu_dereference_bh(rx_sc->next))
+		return (rx_sc->active) ? rx_sc->sci : 0;
+	/* Case no RX SC or multiple */
+	else
+		return 0;
+}
+
+static sci_t macsec_frame_sci(struct macsec_eth_header *hdr, bool sci_present,
+			      struct macsec_rxh_data *rxd)
+{
+	struct macsec_dev *macsec;
+	sci_t sci = 0;
+
+	/* SC = 1 */
+	if (sci_present) {
 		memcpy(&sci, hdr->secure_channel_id,
 		       sizeof(hdr->secure_channel_id));
-	else
+	/* SC = 0; ES = 0 */
+	} else if ((!(hdr->tci_an & (MACSEC_TCI_ES | MACSEC_TCI_SC))) &&
+		   (list_is_singular(&rxd->secys))) {
+		/* Only one SECY should exist on this scenario */
+		macsec = list_first_or_null_rcu(&rxd->secys, struct macsec_dev,
+						secys);
+		if (macsec)
+			return macsec_active_sci(&macsec->secy);
+	} else {
 		sci = make_sci(hdr->eth.h_source, MACSEC_PORT_ES);
+	}
 
 	return sci;
 }
@@ -1109,7 +1133,7 @@ static rx_handler_result_t macsec_handle_frame(struct sk_buff **pskb)
 	struct macsec_rxh_data *rxd;
 	struct macsec_dev *macsec;
 	unsigned int len;
-	sci_t sci;
+	sci_t sci = 0;
 	u32 hdr_pn;
 	bool cbit;
 	struct pcpu_rx_sc_stats *rxsc_stats;
@@ -1156,11 +1180,14 @@ static rx_handler_result_t macsec_handle_frame(struct sk_buff **pskb)
 
 	macsec_skb_cb(skb)->has_sci = !!(hdr->tci_an & MACSEC_TCI_SC);
 	macsec_skb_cb(skb)->assoc_num = hdr->tci_an & MACSEC_AN_MASK;
-	sci = macsec_frame_sci(hdr, macsec_skb_cb(skb)->has_sci);
 
 	rcu_read_lock();
 	rxd = macsec_data_rcu(skb->dev);
 
+	sci = macsec_frame_sci(hdr, macsec_skb_cb(skb)->has_sci, rxd);
+	if (!sci)
+		goto drop_nosc;
+
 	list_for_each_entry_rcu(macsec, &rxd->secys, secys) {
 		struct macsec_rx_sc *sc = find_rx_sc(&macsec->secy, sci);
 
@@ -1283,6 +1310,7 @@ drop:
 	macsec_rxsa_put(rx_sa);
 drop_nosa:
 	macsec_rxsc_put(rx_sc);
+drop_nosc:
 	rcu_read_unlock();
 drop_direct:
 	kfree_skb(skb);

From 1dbf30fdb5e57fb2c39f17f35f2b544d5de34397 Mon Sep 17 00:00:00 2001
From: Juergen Gross <jgross@suse.com>
Date: Tue, 3 Jun 2025 14:14:41 +0300
Subject: [PATCH 0195/1334] x86/mm/pat: don't collapse pages without PSE set

Collapsing pages to a leaf PMD or PUD should be done only if
X86_FEATURE_PSE is available, which is not the case when running e.g.
as a Xen PV guest.

Fixes: 41d88484c71c ("x86/mm/pat: restore large ROX pages after fragmentation")
Signed-off-by: Juergen Gross <jgross@suse.com>
Signed-off-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20250528123557.12847-3-jgross@suse.com
---
 arch/x86/mm/pat/set_memory.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c
index 46edc11726b7..8834c76f91c9 100644
--- a/arch/x86/mm/pat/set_memory.c
+++ b/arch/x86/mm/pat/set_memory.c
@@ -1257,6 +1257,9 @@ static int collapse_pmd_page(pmd_t *pmd, unsigned long addr,
 	pgprot_t pgprot;
 	int i = 0;
 
+	if (!cpu_feature_enabled(X86_FEATURE_PSE))
+		return 0;
+
 	addr &= PMD_MASK;
 	pte = pte_offset_kernel(pmd, addr);
 	first = *pte;

From 47410d839fcda6890cb82828f874f97710982f24 Mon Sep 17 00:00:00 2001
From: "Mike Rapoport (Microsoft)" <rppt@kernel.org>
Date: Tue, 3 Jun 2025 14:14:42 +0300
Subject: [PATCH 0196/1334] x86/Kconfig: only enable ROX cache in execmem when
 STRICT_MODULE_RWX is set

Currently ROX cache in execmem is enabled regardless of
STRICT_MODULE_RWX setting. This breaks an assumption that module memory
is writable when STRICT_MODULE_RWX is disabled, for instance for kernel
debuggin.

Only enable ROX cache in execmem when STRICT_MODULE_RWX is set to
restore the original behaviour of module text permissions.

Fixes: 64f6a4e10c05 ("x86: re-enable EXECMEM_ROX support")
Signed-off-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: stable@vger.kernel.org
Link: https://lkml.kernel.org/r/20250603111446.2609381-3-rppt@kernel.org
---
 arch/x86/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 340e5468980e..71019b3b54ea 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -89,7 +89,7 @@ config X86
 	select ARCH_HAS_DMA_OPS			if GART_IOMMU || XEN
 	select ARCH_HAS_EARLY_DEBUG		if KGDB
 	select ARCH_HAS_ELF_RANDOMIZE
-	select ARCH_HAS_EXECMEM_ROX		if X86_64
+	select ARCH_HAS_EXECMEM_ROX		if X86_64 && STRICT_MODULE_RWX
 	select ARCH_HAS_FAST_MULTIPLIER
 	select ARCH_HAS_FORTIFY_SOURCE
 	select ARCH_HAS_GCOV_PROFILE_ALL

From 0b0cae7119a0ec9449d7261b5e672a5fed765068 Mon Sep 17 00:00:00 2001
From: "Mike Rapoport (Microsoft)" <rppt@kernel.org>
Date: Tue, 3 Jun 2025 14:14:43 +0300
Subject: [PATCH 0197/1334] x86/its: move its_pages array to struct
 mod_arch_specific

The of pages with ITS thunks allocated for modules are tracked by an
array in 'struct module'.

Since this is very architecture specific data structure, move it to
'struct mod_arch_specific'.

No functional changes.

Fixes: 872df34d7c51 ("x86/its: Use dynamic thunks for indirect branches")
Suggested-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: stable@vger.kernel.org
Link: https://lkml.kernel.org/r/20250603111446.2609381-4-rppt@kernel.org
---
 arch/x86/include/asm/module.h |  8 ++++++++
 arch/x86/kernel/alternative.c | 19 ++++++++++---------
 include/linux/module.h        |  5 -----
 3 files changed, 18 insertions(+), 14 deletions(-)

diff --git a/arch/x86/include/asm/module.h b/arch/x86/include/asm/module.h
index e988bac0a4a1..3c2de4ce3b10 100644
--- a/arch/x86/include/asm/module.h
+++ b/arch/x86/include/asm/module.h
@@ -5,12 +5,20 @@
 #include <asm-generic/module.h>
 #include <asm/orc_types.h>
 
+struct its_array {
+#ifdef CONFIG_MITIGATION_ITS
+	void **pages;
+	int num;
+#endif
+};
+
 struct mod_arch_specific {
 #ifdef CONFIG_UNWINDER_ORC
 	unsigned int num_orcs;
 	int *orc_unwind_ip;
 	struct orc_entry *orc_unwind;
 #endif
+	struct its_array its_pages;
 };
 
 #endif /* _ASM_X86_MODULE_H */
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index ecfe7b497cad..b50fe6ce4655 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -173,8 +173,8 @@ void its_fini_mod(struct module *mod)
 	its_page = NULL;
 	mutex_unlock(&text_mutex);
 
-	for (int i = 0; i < mod->its_num_pages; i++) {
-		void *page = mod->its_page_array[i];
+	for (int i = 0; i < mod->arch.its_pages.num; i++) {
+		void *page = mod->arch.its_pages.pages[i];
 		execmem_restore_rox(page, PAGE_SIZE);
 	}
 }
@@ -184,11 +184,11 @@ void its_free_mod(struct module *mod)
 	if (!cpu_feature_enabled(X86_FEATURE_INDIRECT_THUNK_ITS))
 		return;
 
-	for (int i = 0; i < mod->its_num_pages; i++) {
-		void *page = mod->its_page_array[i];
+	for (int i = 0; i < mod->arch.its_pages.num; i++) {
+		void *page = mod->arch.its_pages.pages[i];
 		execmem_free(page);
 	}
-	kfree(mod->its_page_array);
+	kfree(mod->arch.its_pages.pages);
 }
 #endif /* CONFIG_MODULES */
 
@@ -201,14 +201,15 @@ static void *its_alloc(void)
 
 #ifdef CONFIG_MODULES
 	if (its_mod) {
-		void *tmp = krealloc(its_mod->its_page_array,
-				     (its_mod->its_num_pages+1) * sizeof(void *),
+		struct its_array *pages = &its_mod->arch.its_pages;
+		void *tmp = krealloc(pages->pages,
+				     (pages->num+1) * sizeof(void *),
 				     GFP_KERNEL);
 		if (!tmp)
 			return NULL;
 
-		its_mod->its_page_array = tmp;
-		its_mod->its_page_array[its_mod->its_num_pages++] = page;
+		pages->pages = tmp;
+		pages->pages[pages->num++] = page;
 
 		execmem_make_temp_rw(page, PAGE_SIZE);
 	}
diff --git a/include/linux/module.h b/include/linux/module.h
index 92e1420fccdf..5faa1fb1f4b4 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -586,11 +586,6 @@ struct module {
 	atomic_t refcnt;
 #endif
 
-#ifdef CONFIG_MITIGATION_ITS
-	int its_num_pages;
-	void **its_page_array;
-#endif
-
 #ifdef CONFIG_CONSTRUCTORS
 	/* Constructor functions. */
 	ctor_fn_t *ctors;

From a82b26451de126a5ae130361081986bc459afe9b Mon Sep 17 00:00:00 2001
From: "Peter Zijlstra (Intel)" <peterz@infradead.org>
Date: Tue, 3 Jun 2025 14:14:44 +0300
Subject: [PATCH 0198/1334] x86/its: explicitly manage permissions for ITS
 pages

execmem_alloc() sets permissions differently depending on the kernel
configuration, CPU support for PSE and whether a page is allocated
before or after mark_rodata_ro().

Add tracking for pages allocated for ITS when patching the core kernel
and make sure the permissions for ITS pages are explicitly managed for
both kernel and module allocations.

Fixes: 872df34d7c51 ("x86/its: Use dynamic thunks for indirect branches")
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Co-developed-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
Signed-off-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Nikolay Borisov <nik.borisov@suse.com>
Cc: stable@vger.kernel.org
Link: https://lkml.kernel.org/r/20250603111446.2609381-5-rppt@kernel.org
---
 arch/x86/kernel/alternative.c | 74 ++++++++++++++++++++++++-----------
 1 file changed, 52 insertions(+), 22 deletions(-)

diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index b50fe6ce4655..6455f7f751b3 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -116,6 +116,24 @@ static struct module *its_mod;
 #endif
 static void *its_page;
 static unsigned int its_offset;
+struct its_array its_pages;
+
+static void *__its_alloc(struct its_array *pages)
+{
+	void *page __free(execmem) = execmem_alloc(EXECMEM_MODULE_TEXT, PAGE_SIZE);
+	if (!page)
+		return NULL;
+
+	void *tmp = krealloc(pages->pages, (pages->num+1) * sizeof(void *),
+			     GFP_KERNEL);
+	if (!tmp)
+		return NULL;
+
+	pages->pages = tmp;
+	pages->pages[pages->num++] = page;
+
+	return no_free_ptr(page);
+}
 
 /* Initialize a thunk with the "jmp *reg; int3" instructions. */
 static void *its_init_thunk(void *thunk, int reg)
@@ -151,6 +169,21 @@ static void *its_init_thunk(void *thunk, int reg)
 	return thunk + offset;
 }
 
+static void its_pages_protect(struct its_array *pages)
+{
+	for (int i = 0; i < pages->num; i++) {
+		void *page = pages->pages[i];
+		execmem_restore_rox(page, PAGE_SIZE);
+	}
+}
+
+static void its_fini_core(void)
+{
+	if (IS_ENABLED(CONFIG_STRICT_KERNEL_RWX))
+		its_pages_protect(&its_pages);
+	kfree(its_pages.pages);
+}
+
 #ifdef CONFIG_MODULES
 void its_init_mod(struct module *mod)
 {
@@ -173,10 +206,8 @@ void its_fini_mod(struct module *mod)
 	its_page = NULL;
 	mutex_unlock(&text_mutex);
 
-	for (int i = 0; i < mod->arch.its_pages.num; i++) {
-		void *page = mod->arch.its_pages.pages[i];
-		execmem_restore_rox(page, PAGE_SIZE);
-	}
+	if (IS_ENABLED(CONFIG_STRICT_MODULE_RWX))
+		its_pages_protect(&mod->arch.its_pages);
 }
 
 void its_free_mod(struct module *mod)
@@ -194,28 +225,23 @@ void its_free_mod(struct module *mod)
 
 static void *its_alloc(void)
 {
-	void *page __free(execmem) = execmem_alloc(EXECMEM_MODULE_TEXT, PAGE_SIZE);
+	struct its_array *pages = &its_pages;
+	void *page;
 
+#ifdef CONFIG_MODULE
+	if (its_mod)
+		pages = &its_mod->arch.its_pages;
+#endif
+
+	page = __its_alloc(pages);
 	if (!page)
 		return NULL;
 
-#ifdef CONFIG_MODULES
-	if (its_mod) {
-		struct its_array *pages = &its_mod->arch.its_pages;
-		void *tmp = krealloc(pages->pages,
-				     (pages->num+1) * sizeof(void *),
-				     GFP_KERNEL);
-		if (!tmp)
-			return NULL;
+	execmem_make_temp_rw(page, PAGE_SIZE);
+	if (pages == &its_pages)
+		set_memory_x((unsigned long)page, 1);
 
-		pages->pages = tmp;
-		pages->pages[pages->num++] = page;
-
-		execmem_make_temp_rw(page, PAGE_SIZE);
-	}
-#endif /* CONFIG_MODULES */
-
-	return no_free_ptr(page);
+	return page;
 }
 
 static void *its_allocate_thunk(int reg)
@@ -269,7 +295,9 @@ u8 *its_static_thunk(int reg)
 	return thunk;
 }
 
-#endif
+#else
+static inline void its_fini_core(void) {}
+#endif /* CONFIG_MITIGATION_ITS */
 
 /*
  * Nomenclature for variable names to simplify and clarify this code and ease
@@ -2339,6 +2367,8 @@ void __init alternative_instructions(void)
 	apply_retpolines(__retpoline_sites, __retpoline_sites_end);
 	apply_returns(__return_sites, __return_sites_end);
 
+	its_fini_core();
+
 	/*
 	 * Adjust all CALL instructions to point to func()-10, including
 	 * those in .altinstr_replacement.

From 7cd9a11dd0c3d1dd225795ed1b5b53132888e7b5 Mon Sep 17 00:00:00 2001
From: "Mike Rapoport (Microsoft)" <rppt@kernel.org>
Date: Tue, 3 Jun 2025 14:14:45 +0300
Subject: [PATCH 0199/1334] Revert "mm/execmem: Unify early execmem_cache
 behaviour"

The commit d6d1e3e6580c ("mm/execmem: Unify early execmem_cache
behaviour") changed early behaviour of execemem ROX cache to allow its
usage in early x86 code that allocates text pages when
CONFIG_MITGATION_ITS is enabled.

The permission management of the pages allocated from execmem for ITS
mitigation is now completely contained in arch/x86/kernel/alternatives.c
and therefore there is no need to special case early allocations in
execmem.

This reverts commit d6d1e3e6580ca35071ad474381f053cbf1fb6414.

Signed-off-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: stable@vger.kernel.org
Link: https://lkml.kernel.org/r/20250603111446.2609381-6-rppt@kernel.org
---
 arch/x86/mm/init_32.c   |  3 ---
 arch/x86/mm/init_64.c   |  3 ---
 include/linux/execmem.h |  8 +-------
 mm/execmem.c            | 40 +++-------------------------------------
 4 files changed, 4 insertions(+), 50 deletions(-)

diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 607d6a2e66e2..8a34fff6ab2b 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -30,7 +30,6 @@
 #include <linux/initrd.h>
 #include <linux/cpumask.h>
 #include <linux/gfp.h>
-#include <linux/execmem.h>
 
 #include <asm/asm.h>
 #include <asm/bios_ebda.h>
@@ -749,8 +748,6 @@ void mark_rodata_ro(void)
 	pr_info("Write protecting kernel text and read-only data: %luk\n",
 		size >> 10);
 
-	execmem_cache_make_ro();
-
 	kernel_set_to_readonly = 1;
 
 #ifdef CONFIG_CPA_DEBUG
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index ee66fae9ebcc..fdb6cab524f0 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -34,7 +34,6 @@
 #include <linux/gfp.h>
 #include <linux/kcore.h>
 #include <linux/bootmem_info.h>
-#include <linux/execmem.h>
 
 #include <asm/processor.h>
 #include <asm/bios_ebda.h>
@@ -1392,8 +1391,6 @@ void mark_rodata_ro(void)
 	       (end - start) >> 10);
 	set_memory_ro(start, (end - start) >> PAGE_SHIFT);
 
-	execmem_cache_make_ro();
-
 	kernel_set_to_readonly = 1;
 
 	/*
diff --git a/include/linux/execmem.h b/include/linux/execmem.h
index ca42d5e46ccc..3be35680a54f 100644
--- a/include/linux/execmem.h
+++ b/include/linux/execmem.h
@@ -54,7 +54,7 @@ enum execmem_range_flags {
 	EXECMEM_ROX_CACHE	= (1 << 1),
 };
 
-#if defined(CONFIG_ARCH_HAS_EXECMEM_ROX) && defined(CONFIG_EXECMEM)
+#ifdef CONFIG_ARCH_HAS_EXECMEM_ROX
 /**
  * execmem_fill_trapping_insns - set memory to contain instructions that
  *				 will trap
@@ -94,15 +94,9 @@ int execmem_make_temp_rw(void *ptr, size_t size);
  * Return: 0 on success or negative error code on failure.
  */
 int execmem_restore_rox(void *ptr, size_t size);
-
-/*
- * Called from mark_readonly(), where the system transitions to ROX.
- */
-void execmem_cache_make_ro(void);
 #else
 static inline int execmem_make_temp_rw(void *ptr, size_t size) { return 0; }
 static inline int execmem_restore_rox(void *ptr, size_t size) { return 0; }
-static inline void execmem_cache_make_ro(void) { }
 #endif
 
 /**
diff --git a/mm/execmem.c b/mm/execmem.c
index 9720ac2dfa41..2b683e7d864d 100644
--- a/mm/execmem.c
+++ b/mm/execmem.c
@@ -254,34 +254,6 @@ out_unlock:
 	return ptr;
 }
 
-static bool execmem_cache_rox = false;
-
-void execmem_cache_make_ro(void)
-{
-	struct maple_tree *free_areas = &execmem_cache.free_areas;
-	struct maple_tree *busy_areas = &execmem_cache.busy_areas;
-	MA_STATE(mas_free, free_areas, 0, ULONG_MAX);
-	MA_STATE(mas_busy, busy_areas, 0, ULONG_MAX);
-	struct mutex *mutex = &execmem_cache.mutex;
-	void *area;
-
-	execmem_cache_rox = true;
-
-	mutex_lock(mutex);
-
-	mas_for_each(&mas_free, area, ULONG_MAX) {
-		unsigned long pages = mas_range_len(&mas_free) >> PAGE_SHIFT;
-		set_memory_ro(mas_free.index, pages);
-	}
-
-	mas_for_each(&mas_busy, area, ULONG_MAX) {
-		unsigned long pages = mas_range_len(&mas_busy) >> PAGE_SHIFT;
-		set_memory_ro(mas_busy.index, pages);
-	}
-
-	mutex_unlock(mutex);
-}
-
 static int execmem_cache_populate(struct execmem_range *range, size_t size)
 {
 	unsigned long vm_flags = VM_ALLOW_HUGE_VMAP;
@@ -302,15 +274,9 @@ static int execmem_cache_populate(struct execmem_range *range, size_t size)
 	/* fill memory with instructions that will trap */
 	execmem_fill_trapping_insns(p, alloc_size, /* writable = */ true);
 
-	if (execmem_cache_rox) {
-		err = set_memory_rox((unsigned long)p, vm->nr_pages);
-		if (err)
-			goto err_free_mem;
-	} else {
-		err = set_memory_x((unsigned long)p, vm->nr_pages);
-		if (err)
-			goto err_free_mem;
-	}
+	err = set_memory_rox((unsigned long)p, vm->nr_pages);
+	if (err)
+		goto err_free_mem;
 
 	err = execmem_cache_add(p, alloc_size);
 	if (err)

From 570896604f47d44d4ff6882d2a588428d2a6ef17 Mon Sep 17 00:00:00 2001
From: Francesco Dolcini <francesco.dolcini@toradex.com>
Date: Thu, 5 Jun 2025 15:03:02 +0200
Subject: [PATCH 0200/1334] Revert "wifi: mwifiex: Fix HT40 bandwidth issue."

This reverts commit 4fcfcbe45734 ("wifi: mwifiex: Fix HT40 bandwidth
issue.")

That commit introduces a regression, when HT40 mode is enabled,
received packets are lost, this was experience with W8997 with both
SDIO-UART and SDIO-SDIO variants. From an initial investigation the
issue solves on its own after some time, but it's not clear what is
the reason. Given that this was just a performance optimization, let's
revert it till we have a better understanding of the issue and a proper
fix.

Cc: Jeff Chen <jeff.chen_1@nxp.com>
Cc: stable@vger.kernel.org
Fixes: 4fcfcbe45734 ("wifi: mwifiex: Fix HT40 bandwidth issue.")
Closes: https://lore.kernel.org/all/20250603203337.GA109929@francesco-nb/
Signed-off-by: Francesco Dolcini <francesco.dolcini@toradex.com>
Link: https://patch.msgid.link/20250605130302.55555-1-francesco@dolcini.it
[fix commit reference format]
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/marvell/mwifiex/11n.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/net/wireless/marvell/mwifiex/11n.c b/drivers/net/wireless/marvell/mwifiex/11n.c
index 738bafc3749b..66f0f5377ac1 100644
--- a/drivers/net/wireless/marvell/mwifiex/11n.c
+++ b/drivers/net/wireless/marvell/mwifiex/11n.c
@@ -403,14 +403,12 @@ mwifiex_cmd_append_11n_tlv(struct mwifiex_private *priv,
 
 		if (sband->ht_cap.cap & IEEE80211_HT_CAP_SUP_WIDTH_20_40 &&
 		    bss_desc->bcn_ht_oper->ht_param &
-		    IEEE80211_HT_PARAM_CHAN_WIDTH_ANY) {
-			chan_list->chan_scan_param[0].radio_type |=
-				CHAN_BW_40MHZ << 2;
+		    IEEE80211_HT_PARAM_CHAN_WIDTH_ANY)
 			SET_SECONDARYCHAN(chan_list->chan_scan_param[0].
 					  radio_type,
 					  (bss_desc->bcn_ht_oper->ht_param &
 					  IEEE80211_HT_PARAM_CHA_SEC_OFFSET));
-		}
+
 		*buffer += struct_size(chan_list, chan_scan_param, 1);
 		ret_len += struct_size(chan_list, chan_scan_param, 1);
 	}

From 6a0f81c549a00f87865ff0ad2400944ca0726868 Mon Sep 17 00:00:00 2001
From: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Date: Tue, 3 Jun 2025 12:17:54 +0300
Subject: [PATCH 0201/1334] wifi: iwlwifi: fix merge damage related to
 iwl_pci_resume

The changes I made in
wifi: iwlwifi: don't warn if the NIC is gone in resume
conflicted with a major rework done in this area.
The merge de-facto removed my changes.
Re-add them.

Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Link: https://patch.msgid.link/20250603091754.70182-1-emmanuel.grumbach@intel.com
Fixes: 06c4b2036818 ("Merge tag 'iwlwifi-next-2025-05-15' of https://git.kernel.org/pub/scm/linux/kernel/git/iwlwifi/iwlwifi-next")
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/pcie/drv.c | 24 +++++++++++++++----
 1 file changed, 20 insertions(+), 4 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
index 656f8b06c27b..0a9e0dbb58fb 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
@@ -1501,11 +1501,27 @@ static int _iwl_pci_resume(struct device *device, bool restore)
 	 * Scratch value was altered, this means the device was powered off, we
 	 * need to reset it completely.
 	 * Note: MAC (bits 0:7) will be cleared upon suspend even with wowlan,
-	 * so assume that any bits there mean that the device is usable.
+	 * but not bits [15:8]. So if we have bits set in lower word, assume
+	 * the device is alive.
+	 * For older devices, just try silently to grab the NIC.
 	 */
-	if (trans->mac_cfg->device_family >= IWL_DEVICE_FAMILY_BZ &&
-	    !iwl_read32(trans, CSR_FUNC_SCRATCH))
-		device_was_powered_off = true;
+	if (trans->mac_cfg->device_family >= IWL_DEVICE_FAMILY_BZ) {
+		if (!(iwl_read32(trans, CSR_FUNC_SCRATCH) &
+		      CSR_FUNC_SCRATCH_POWER_OFF_MASK))
+			device_was_powered_off = true;
+	} else {
+		/*
+		 * bh are re-enabled by iwl_trans_pcie_release_nic_access,
+		 * so re-enable them if _iwl_trans_pcie_grab_nic_access fails.
+		 */
+		local_bh_disable();
+		if (_iwl_trans_pcie_grab_nic_access(trans, true)) {
+			iwl_trans_pcie_release_nic_access(trans);
+		} else {
+			device_was_powered_off = true;
+			local_bh_enable();
+		}
+	}
 
 	if (restore || device_was_powered_off) {
 		trans->state = IWL_TRANS_NO_FW;

From f87586598fffac31afc1141471b789251b030a76 Mon Sep 17 00:00:00 2001
From: Zilin Guan <zilin@seu.edu.cn>
Date: Fri, 23 May 2025 11:01:56 +0000
Subject: [PATCH 0202/1334] wifi: cfg80211: use kfree_sensitive() for connkeys
 cleanup

The nl80211_parse_connkeys() function currently uses kfree() to release
the 'result' structure in error handling paths. However, if an error
occurs due to result->def being less than 0, the 'result' structure may
contain sensitive information.

To prevent potential leakage of sensitive data, replace kfree() with
kfree_sensitive() when freeing 'result'. This change aligns with the
approach used in its caller, nl80211_join_ibss(), enhancing the overall
security of the wireless subsystem.

Signed-off-by: Zilin Guan <zilin@seu.edu.cn>
Link: https://patch.msgid.link/20250523110156.4017111-1-zilin@seu.edu.cn
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/wireless/nl80211.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index fd5f79266471..85f139016da2 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -1583,7 +1583,7 @@ nl80211_parse_connkeys(struct cfg80211_registered_device *rdev,
 
 	return result;
  error:
-	kfree(result);
+	kfree_sensitive(result);
 	return ERR_PTR(err);
 }
 

From aa3f93cd75bf8195e434deefff853d70d723d6f0 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Christian=20K=C3=B6nig?= <christian.koenig@amd.com>
Date: Thu, 5 Jun 2025 10:38:30 +0200
Subject: [PATCH 0203/1334] dma-buf: fix compare in WARN_ON_ONCE
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Smatch pointed out this trivial typo:
	drivers/dma-buf/dma-buf.c:1123 dma_buf_map_attachment()
	warn: passing positive error code '16' to 'ERR_PTR'

drivers/dma-buf/dma-buf.c
    1113         dma_resv_assert_held(attach->dmabuf->resv);
    1114
    1115         if (dma_buf_pin_on_map(attach)) {
    1116                 ret = attach->dmabuf->ops->pin(attach);
    1117                 /*
    1118                  * Catch exporters making buffers inaccessible even when
    1119                  * attachments preventing that exist.
    1120                  */
    1121                 WARN_ON_ONCE(ret == EBUSY);
                                             ^^^^^
This was probably intended to be -EBUSY?

    1122                 if (ret)
--> 1123                         return ERR_PTR(ret);
                                                ^^^
Otherwise we will eventually crash.

    1124         }
    1125
    1126         sg_table = attach->dmabuf->ops->map_dma_buf(attach, direction);
    1127         if (!sg_table)
    1128                 sg_table = ERR_PTR(-ENOMEM);
    1129         if (IS_ERR(sg_table))
    1130                 goto error_unpin;
    1131

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@igalia.com>
Link: https://lore.kernel.org/r/20250605085336.62156-1-christian.koenig@amd.com
---
 drivers/dma-buf/dma-buf.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c
index 890ecac04dac..2bcf9ceca997 100644
--- a/drivers/dma-buf/dma-buf.c
+++ b/drivers/dma-buf/dma-buf.c
@@ -1118,7 +1118,7 @@ struct sg_table *dma_buf_map_attachment(struct dma_buf_attachment *attach,
 		 * Catch exporters making buffers inaccessible even when
 		 * attachments preventing that exist.
 		 */
-		WARN_ON_ONCE(ret == EBUSY);
+		WARN_ON_ONCE(ret == -EBUSY);
 		if (ret)
 			return ERR_PTR(ret);
 	}

From 6bdd3a01fe4627ad7a562ba38eb759eba715b671 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 10 Jun 2025 16:00:20 +0200
Subject: [PATCH 0204/1334] fs: add missing values to TRACE_IOCB_STRINGS

Make sure all values are covered.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/20250610140020.2227932-1-hch@lst.de
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 include/linux/fs.h | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/include/linux/fs.h b/include/linux/fs.h
index 96c7925a6551..d27c402f1162 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -399,7 +399,9 @@ struct readahead_control;
 	{ IOCB_WAITQ,		"WAITQ" }, \
 	{ IOCB_NOIO,		"NOIO" }, \
 	{ IOCB_ALLOC_CACHE,	"ALLOC_CACHE" }, \
-	{ IOCB_DIO_CALLER_COMP,	"CALLER_COMP" }
+	{ IOCB_DIO_CALLER_COMP,	"CALLER_COMP" }, \
+	{ IOCB_AIO_RW,		"AIO_RW" }, \
+	{ IOCB_HAS_METADATA,	"AIO_HAS_METADATA" }
 
 struct kiocb {
 	struct file		*ki_filp;

From ad5a0351064c8f744416df3a49156d2c61af5bc0 Mon Sep 17 00:00:00 2001
From: NeilBrown <neil@brown.name>
Date: Tue, 10 Jun 2025 11:04:04 +1000
Subject: [PATCH 0205/1334] VFS: change try_lookup_noperm() to skip
 revalidation

The recent change from using d_hash_and_lookup() to using
try_lookup_noperm() inadvertently introduce a d_revalidate() call when
the lookup was successful.  Steven French reports that this resulted in
worse than halving of performance in some cases.

Prior to the offending patch the only caller of try_lookup_noperm() was
autofs which does not need the d_revalidate().  So it is safe to remove
the d_revalidate() call providing we stop using try_lookup_noperm() to
implement lookup_noperm().

The "try_" in the name is strongly suggestive that the caller isn't
expecting much effort, so it seems reasonable to avoid the effort of
d_revalidate().

Fixes: 06c567403ae5 ("Use try_lookup_noperm() instead of d_hash_and_lookup() outside of VFS")
Reported-by: Steve French <smfrench@gmail.com>
Link: https://lore.kernel.org/all/CAH2r5mu5SfBrdc2CFHwzft8=n9koPMk+Jzwpy-oUMx-wCRCesQ@mail.gmail.com/
Signed-off-by: NeilBrown <neil@brown.name>
Link: https://lore.kernel.org/174951744454.608730.18354002683881684261@noble.neil.brown.name
Tested-by: Steve French <stfrench@microsoft.com>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/namei.c | 17 +++++++++++++----
 1 file changed, 13 insertions(+), 4 deletions(-)

diff --git a/fs/namei.c b/fs/namei.c
index 4bb889fc980b..f761cafaeaad 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -2917,7 +2917,8 @@ static int lookup_one_common(struct mnt_idmap *idmap,
  * @base:	base directory to lookup from
  *
  * Look up a dentry by name in the dcache, returning NULL if it does not
- * currently exist.  The function does not try to create a dentry.
+ * currently exist.  The function does not try to create a dentry and if one
+ * is found it doesn't try to revalidate it.
  *
  * Note that this routine is purely a helper for filesystem usage and should
  * not be called by generic code.  It does no permission checking.
@@ -2933,7 +2934,7 @@ struct dentry *try_lookup_noperm(struct qstr *name, struct dentry *base)
 	if (err)
 		return ERR_PTR(err);
 
-	return lookup_dcache(name, base, 0);
+	return d_lookup(base, name);
 }
 EXPORT_SYMBOL(try_lookup_noperm);
 
@@ -3057,14 +3058,22 @@ EXPORT_SYMBOL(lookup_one_positive_unlocked);
  * Note that this routine is purely a helper for filesystem usage and should
  * not be called by generic code. It does no permission checking.
  *
- * Unlike lookup_noperm, it should be called without the parent
+ * Unlike lookup_noperm(), it should be called without the parent
  * i_rwsem held, and will take the i_rwsem itself if necessary.
+ *
+ * Unlike try_lookup_noperm() it *does* revalidate the dentry if it already
+ * existed.
  */
 struct dentry *lookup_noperm_unlocked(struct qstr *name, struct dentry *base)
 {
 	struct dentry *ret;
+	int err;
 
-	ret = try_lookup_noperm(name, base);
+	err = lookup_noperm_common(name, base);
+	if (err)
+		return ERR_PTR(err);
+
+	ret = lookup_dcache(name, base, 0);
 	if (!ret)
 		ret = lookup_slow(name, base, 0);
 	return ret;

From 3e5378779091c2f9a96d4404066e1923c92ceb8b Mon Sep 17 00:00:00 2001
From: Philipp Stanner <phasta@kernel.org>
Date: Tue, 10 Jun 2025 15:54:14 +0200
Subject: [PATCH 0206/1334] ata: pata_macio: Fix PCI region leak

pci_request_regions() became a managed devres functions if the PCI
device was enabled with pcim_enable_device(), which is the case for
pata_macio.

The PCI subsystem recently removed this hybrid feature from
pci_request_region(). When doing so, pata_macio was forgotten to be
ported to use pcim_request_all_regions(). If that function is not used,
pata_macio will fail on driver-reload because the PCI regions will
remain blocked.

Fix the region leak by replacing pci_request_regions() with its managed
counterpart, pcim_request_all_regions().

Fixes: 51f6aec99cb0 ("PCI: Remove hybrid devres nature from request functions")
Signed-off-by: Philipp Stanner <phasta@kernel.org>
Reviewed-by: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@linux.intel.com>
Reviewed-by: Damien Le Moal <dlemoal@kernel.org>
Link: https://lore.kernel.org/r/20250610135413.35930-2-phasta@kernel.org
Signed-off-by: Niklas Cassel <cassel@kernel.org>
---
 drivers/ata/pata_macio.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/ata/pata_macio.c b/drivers/ata/pata_macio.c
index fbf5f07ea357..f7a933eefe05 100644
--- a/drivers/ata/pata_macio.c
+++ b/drivers/ata/pata_macio.c
@@ -1298,7 +1298,7 @@ static int pata_macio_pci_attach(struct pci_dev *pdev,
 	priv->dev = &pdev->dev;
 
 	/* Get MMIO regions */
-	if (pci_request_regions(pdev, "pata-macio")) {
+	if (pcim_request_all_regions(pdev, "pata-macio")) {
 		dev_err(&pdev->dev,
 			"Cannot obtain PCI resources\n");
 		return -EBUSY;

From 6f29d393061c2c1fa30a72a0e9b01e15e09dae34 Mon Sep 17 00:00:00 2001
From: Niklas Cassel <cassel@kernel.org>
Date: Tue, 10 Jun 2025 13:07:59 +0200
Subject: [PATCH 0207/1334] ata: ahci: Use correct BIOS build date for ThinkPad
 W541 quirk

Fix the TODO in ahci_broken_lpm() by using the proper BIOS build date.

The proper BIOS build date was provided by Hans, see Link.

Link: https://lore.kernel.org/linux-ide/6ea509c8-b38d-4941-8a29-c1117ff3dd5b@redhat.com/
Reviewed-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Hans de Goede <hansg@kernel.org>
Link: https://lore.kernel.org/r/20250610110757.1318959-6-cassel@kernel.org
Signed-off-by: Niklas Cassel <cassel@kernel.org>
---
 drivers/ata/ahci.c | 8 +-------
 1 file changed, 1 insertion(+), 7 deletions(-)

diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c
index 163ac909bd06..e7c8357cbc54 100644
--- a/drivers/ata/ahci.c
+++ b/drivers/ata/ahci.c
@@ -1438,13 +1438,7 @@ static bool ahci_broken_lpm(struct pci_dev *pdev)
 				DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
 				DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad W541"),
 			},
-			/*
-			 * Note date based on release notes, 2.35 has been
-			 * reported to be good, but I've been unable to get
-			 * a hold of the reporter to get the DMI BIOS date.
-			 * TODO: fix this.
-			 */
-			.driver_data = "20180310", /* 2.35 */
+			.driver_data = "20180409", /* 2.35 */
 		},
 		{ }	/* terminate list */
 	};

From afe382843717d44b24ef5014d57dcbaab75a4052 Mon Sep 17 00:00:00 2001
From: Marek Szyprowski <m.szyprowski@samsung.com>
Date: Wed, 7 May 2025 18:09:12 +0200
Subject: [PATCH 0208/1334] udmabuf: use sgtable-based scatterlist wrappers
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Use common wrappers operating directly on the struct sg_table objects to
fix incorrect use of scatterlists sync calls. dma_sync_sg_for_*()
functions have to be called with the number of elements originally passed
to dma_map_sg_*() function, not the one returned in sgtable's nents.

Fixes: 1ffe09590121 ("udmabuf: fix dma-buf cpu access")
CC: stable@vger.kernel.org
Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>
Acked-by: Vivek Kasireddy <vivek.kasireddy@intel.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Christian König <christian.koenig@amd.com>
Link: https://lore.kernel.org/r/20250507160913.2084079-3-m.szyprowski@samsung.com
---
 drivers/dma-buf/udmabuf.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/dma-buf/udmabuf.c b/drivers/dma-buf/udmabuf.c
index 7eee3eb47a8e..c9d0c68d2fcb 100644
--- a/drivers/dma-buf/udmabuf.c
+++ b/drivers/dma-buf/udmabuf.c
@@ -264,8 +264,7 @@ static int begin_cpu_udmabuf(struct dma_buf *buf,
 			ubuf->sg = NULL;
 		}
 	} else {
-		dma_sync_sg_for_cpu(dev, ubuf->sg->sgl, ubuf->sg->nents,
-				    direction);
+		dma_sync_sgtable_for_cpu(dev, ubuf->sg, direction);
 	}
 
 	return ret;
@@ -280,7 +279,7 @@ static int end_cpu_udmabuf(struct dma_buf *buf,
 	if (!ubuf->sg)
 		return -EINVAL;
 
-	dma_sync_sg_for_device(dev, ubuf->sg->sgl, ubuf->sg->nents, direction);
+	dma_sync_sgtable_for_device(dev, ubuf->sg, direction);
 	return 0;
 }
 

From 0e629694126ca388916f059453a1c36adde219c4 Mon Sep 17 00:00:00 2001
From: Jakub Raczynski <j.raczynski@samsung.com>
Date: Mon, 9 Jun 2025 17:31:46 +0200
Subject: [PATCH 0209/1334] net/mdiobus: Fix potential out-of-bounds read/write
 access

When using publicly available tools like 'mdio-tools' to read/write data
from/to network interface and its PHY via mdiobus, there is no verification of
parameters passed to the ioctl and it accepts any mdio address.
Currently there is support for 32 addresses in kernel via PHY_MAX_ADDR define,
but it is possible to pass higher value than that via ioctl.
While read/write operation should generally fail in this case,
mdiobus provides stats array, where wrong address may allow out-of-bounds
read/write.

Fix that by adding address verification before read/write operation.
While this excludes this access from any statistics, it improves security of
read/write operation.

Fixes: 080bb352fad00 ("net: phy: Maintain MDIO device and bus statistics")
Signed-off-by: Jakub Raczynski <j.raczynski@samsung.com>
Reported-by: Wenjing Shan <wenjing.shan@samsung.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/mdio_bus.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c
index a6bcb0fee863..60fd0cd7cb9c 100644
--- a/drivers/net/phy/mdio_bus.c
+++ b/drivers/net/phy/mdio_bus.c
@@ -445,6 +445,9 @@ int __mdiobus_read(struct mii_bus *bus, int addr, u32 regnum)
 
 	lockdep_assert_held_once(&bus->mdio_lock);
 
+	if (addr >= PHY_MAX_ADDR)
+		return -ENXIO;
+
 	if (bus->read)
 		retval = bus->read(bus, addr, regnum);
 	else
@@ -474,6 +477,9 @@ int __mdiobus_write(struct mii_bus *bus, int addr, u32 regnum, u16 val)
 
 	lockdep_assert_held_once(&bus->mdio_lock);
 
+	if (addr >= PHY_MAX_ADDR)
+		return -ENXIO;
+
 	if (bus->write)
 		err = bus->write(bus, addr, regnum, val);
 	else

From 260388f79e94fb3026c419a208ece8358bb7b555 Mon Sep 17 00:00:00 2001
From: Jakub Raczynski <j.raczynski@samsung.com>
Date: Mon, 9 Jun 2025 17:31:47 +0200
Subject: [PATCH 0210/1334] net/mdiobus: Fix potential out-of-bounds clause 45
 read/write access

When using publicly available tools like 'mdio-tools' to read/write data
from/to network interface and its PHY via C45 (clause 45) mdiobus,
there is no verification of parameters passed to the ioctl and
it accepts any mdio address.
Currently there is support for 32 addresses in kernel via PHY_MAX_ADDR define,
but it is possible to pass higher value than that via ioctl.
While read/write operation should generally fail in this case,
mdiobus provides stats array, where wrong address may allow out-of-bounds
read/write.

Fix that by adding address verification before C45 read/write operation.
While this excludes this access from any statistics, it improves security of
read/write operation.

Fixes: 4e4aafcddbbf ("net: mdio: Add dedicated C45 API to MDIO bus drivers")
Signed-off-by: Jakub Raczynski <j.raczynski@samsung.com>
Reported-by: Wenjing Shan <wenjing.shan@samsung.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/mdio_bus.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c
index 60fd0cd7cb9c..fda2e27c1810 100644
--- a/drivers/net/phy/mdio_bus.c
+++ b/drivers/net/phy/mdio_bus.c
@@ -541,6 +541,9 @@ int __mdiobus_c45_read(struct mii_bus *bus, int addr, int devad, u32 regnum)
 
 	lockdep_assert_held_once(&bus->mdio_lock);
 
+	if (addr >= PHY_MAX_ADDR)
+		return -ENXIO;
+
 	if (bus->read_c45)
 		retval = bus->read_c45(bus, addr, devad, regnum);
 	else
@@ -572,6 +575,9 @@ int __mdiobus_c45_write(struct mii_bus *bus, int addr, int devad, u32 regnum,
 
 	lockdep_assert_held_once(&bus->mdio_lock);
 
+	if (addr >= PHY_MAX_ADDR)
+		return -ENXIO;
+
 	if (bus->write_c45)
 		err = bus->write_c45(bus, addr, devad, regnum, val);
 	else

From bc4394e5e79cdda1b0997e0be1d65e242f523f02 Mon Sep 17 00:00:00 2001
From: Kan Liang <kan.liang@linux.intel.com>
Date: Fri, 6 Jun 2025 12:25:46 -0700
Subject: [PATCH 0211/1334] perf: Fix the throttle error of some clock events

Both ARM and IBM CI reports RCU stall, which can be reproduced by the
below perf command.
  perf record -a -e cpu-clock -- sleep 2

The issue is introduced by the generic throttle patch set, which
unconditionally invoke the event_stop() when throttle is triggered.

The cpu-clock and task-clock are two special SW events, which rely on
the hrtimer. The throttle is invoked in the hrtimer handler. The
event_stop()->hrtimer_cancel() waits for the handler to finish, which is
a deadlock. Instead of invoking the stop(), the HRTIMER_NORESTART should
be used to stop the timer.

There may be two ways to fix it:
 - Introduce a PMU flag to track the case. Avoid the event_stop in
   perf_event_throttle() if the flag is detected.
   It has been implemented in the
   https://lore.kernel.org/lkml/20250528175832.2999139-1-kan.liang@linux.intel.com/
   The new flag was thought to be an overkill for the issue.
 - Add a check in the event_stop. Return immediately if the throttle is
   invoked in the hrtimer handler. Rely on the existing HRTIMER_NORESTART
   method to stop the timer.

The latter is implemented here.

Move event->hw.interrupts = MAX_INTERRUPTS before the stop(). It makes
the order the same as perf_event_unthrottle(). Except the patch, no one
checks the hw.interrupts in the stop(). There is no impact from the
order change.

When stops in the throttle, the event should not be updated,
stop(event, 0). But the cpu_clock_event_stop() doesn't handle the flag.
In logic, it's wrong. But it didn't bring any problems with the old
code, because the stop() was not invoked when handling the throttle.
Checking the flag before updating the event.

Fixes: 9734e25fbf5a ("perf: Fix the throttle logic for a group")
Closes: https://lore.kernel.org/lkml/20250527161656.GJ2566836@e132581.arm.com/
Closes: https://lore.kernel.org/lkml/djxlh5fx326gcenwrr52ry3pk4wxmugu4jccdjysza7tlc5fef@ktp4rffawgcw/
Closes: https://lore.kernel.org/lkml/8e8f51d8-af64-4d9e-934b-c0ee9f131293@linux.ibm.com/
Closes: https://lore.kernel.org/lkml/4ce106d0-950c-aadc-0b6a-f0215cd39913@maine.edu/
Reported-by: Leo Yan <leo.yan@arm.com>
Reported-by: Aishwarya TCV <aishwarya.tcv@arm.com>
Reported-by: Alexei Starovoitov <alexei.starovoitov@gmail.com>
Reported-by: Venkat Rao Bagalkote <venkat88@linux.ibm.com>
Reported-by: Vince Weaver <vincent.weaver@maine.edu>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Ian Rogers <irogers@google.com>
Link: https://lkml.kernel.org/r/20250606192546.915765-1-kan.liang@linux.intel.com
---
 kernel/events/core.c | 15 +++++++++++----
 1 file changed, 11 insertions(+), 4 deletions(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index d7cf008f3d75..1f746469fda5 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -2674,8 +2674,8 @@ static void perf_event_unthrottle(struct perf_event *event, bool start)
 
 static void perf_event_throttle(struct perf_event *event)
 {
-	event->pmu->stop(event, 0);
 	event->hw.interrupts = MAX_INTERRUPTS;
+	event->pmu->stop(event, 0);
 	if (event == event->group_leader)
 		perf_log_throttle(event, 0);
 }
@@ -11774,7 +11774,12 @@ static void perf_swevent_cancel_hrtimer(struct perf_event *event)
 {
 	struct hw_perf_event *hwc = &event->hw;
 
-	if (is_sampling_event(event)) {
+	/*
+	 * The throttle can be triggered in the hrtimer handler.
+	 * The HRTIMER_NORESTART should be used to stop the timer,
+	 * rather than hrtimer_cancel(). See perf_swevent_hrtimer()
+	 */
+	if (is_sampling_event(event) && (hwc->interrupts != MAX_INTERRUPTS)) {
 		ktime_t remaining = hrtimer_get_remaining(&hwc->hrtimer);
 		local64_set(&hwc->period_left, ktime_to_ns(remaining));
 
@@ -11829,7 +11834,8 @@ static void cpu_clock_event_start(struct perf_event *event, int flags)
 static void cpu_clock_event_stop(struct perf_event *event, int flags)
 {
 	perf_swevent_cancel_hrtimer(event);
-	cpu_clock_event_update(event);
+	if (flags & PERF_EF_UPDATE)
+		cpu_clock_event_update(event);
 }
 
 static int cpu_clock_event_add(struct perf_event *event, int flags)
@@ -11907,7 +11913,8 @@ static void task_clock_event_start(struct perf_event *event, int flags)
 static void task_clock_event_stop(struct perf_event *event, int flags)
 {
 	perf_swevent_cancel_hrtimer(event);
-	task_clock_event_update(event, event->ctx->time);
+	if (flags & PERF_EF_UPDATE)
+		task_clock_event_update(event, event->ctx->time);
 }
 
 static int task_clock_event_add(struct perf_event *event, int flags)

From 72f37957007d25f4290e3ba40d40aaec1dd0b0cf Mon Sep 17 00:00:00 2001
From: Binbin Zhou <zhoubinbin@loongson.cn>
Date: Tue, 10 Jun 2025 19:59:26 +0800
Subject: [PATCH 0212/1334] gpio: loongson-64bit: Correct Loongson-7A2000 ACPI
 GPIO access mode

According to the description of the Loongson-7A2000 ACPI GPIO register in
the manual, its access mode should be BIT_CTRL_MODE, otherwise there maybe
some unpredictable behavior.

Cc: stable@vger.kernel.org
Fixes: 44fe79020b91 ("gpio: loongson-64bit: Add more gpio chip support")
Signed-off-by: Binbin Zhou <zhoubinbin@loongson.cn>
Reviewed-by: Huacai Chen <chenhuacai@loongson.cn>
Link: https://lore.kernel.org/r/20250610115926.347845-1-zhoubinbin@loongson.cn
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
---
 drivers/gpio/gpio-loongson-64bit.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpio/gpio-loongson-64bit.c b/drivers/gpio/gpio-loongson-64bit.c
index 26227669f026..70a01c5b8ad1 100644
--- a/drivers/gpio/gpio-loongson-64bit.c
+++ b/drivers/gpio/gpio-loongson-64bit.c
@@ -268,7 +268,7 @@ static const struct loongson_gpio_chip_data loongson_gpio_ls7a2000_data0 = {
 /* LS7A2000 ACPI GPIO */
 static const struct loongson_gpio_chip_data loongson_gpio_ls7a2000_data1 = {
 	.label = "ls7a2000_gpio",
-	.mode = BYTE_CTRL_MODE,
+	.mode = BIT_CTRL_MODE,
 	.conf_offset = 0x4,
 	.in_offset = 0x8,
 	.out_offset = 0x0,

From 4bb08cf974c54adc321b8505ce82720c2a15c451 Mon Sep 17 00:00:00 2001
From: Ming Lei <ming.lei@redhat.com>
Date: Wed, 11 Jun 2025 16:49:38 +0800
Subject: [PATCH 0213/1334] loop: move lo_set_size() out of queue freeze

It isn't necessary to freeze queue for updating disk size given submit_bio()
doesn't grab queue usage counter for checking eod.

Also many driver won't freeze queue for calling set_capacity_and_notify().

Move lo_set_size() out of queue freeze for fixing many lockdep warning
report.

Link: https://lore.kernel.org/linux-block/67ea99e0.050a0220.3c3d88.0042.GAE@google.com/
Reported-by: syzbot+9dd7dbb1a4b915dee638@syzkaller.appspotmail.com
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/20250611084938.108829-1-ming.lei@redhat.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/loop.c | 11 +++++------
 1 file changed, 5 insertions(+), 6 deletions(-)

diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index f8d136684109..500840e4a74e 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -1248,12 +1248,6 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info)
 	lo->lo_flags &= ~LOOP_SET_STATUS_CLEARABLE_FLAGS;
 	lo->lo_flags |= (info->lo_flags & LOOP_SET_STATUS_SETTABLE_FLAGS);
 
-	if (size_changed) {
-		loff_t new_size = get_size(lo->lo_offset, lo->lo_sizelimit,
-					   lo->lo_backing_file);
-		loop_set_size(lo, new_size);
-	}
-
 	/* update the direct I/O flag if lo_offset changed */
 	loop_update_dio(lo);
 
@@ -1261,6 +1255,11 @@ out_unfreeze:
 	blk_mq_unfreeze_queue(lo->lo_queue, memflags);
 	if (partscan)
 		clear_bit(GD_SUPPRESS_PART_SCAN, &lo->lo_disk->state);
+	if (!err && size_changed) {
+		loff_t new_size = get_size(lo->lo_offset, lo->lo_sizelimit,
+					   lo->lo_backing_file);
+		loop_set_size(lo, new_size);
+	}
 out_unlock:
 	mutex_unlock(&lo->lo_mutex);
 	if (partscan)

From ff20c516485efbeb5c32bcb6aa5a24f73774185b Mon Sep 17 00:00:00 2001
From: Ming Lei <ming.lei@redhat.com>
Date: Wed, 11 Jun 2025 16:56:32 +0800
Subject: [PATCH 0214/1334] ublk: document auto buffer
 registration(UBLK_F_AUTO_BUF_REG)

Document recently merged feature auto buffer registration(UBLK_F_AUTO_BUF_REG).

Cc: Caleb Sander Mateos <csander@purestorage.com>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/20250611085632.109719-1-ming.lei@redhat.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 Documentation/block/ublk.rst | 75 ++++++++++++++++++++++++++++++++++++
 1 file changed, 75 insertions(+)

diff --git a/Documentation/block/ublk.rst b/Documentation/block/ublk.rst
index c368e1081b41..abec524a04ed 100644
--- a/Documentation/block/ublk.rst
+++ b/Documentation/block/ublk.rst
@@ -352,6 +352,81 @@ For reaching best IO performance, ublk server should align its segment
 parameter of `struct ublk_param_segment` with backend for avoiding
 unnecessary IO split, which usually hurts io_uring performance.
 
+Auto Buffer Registration
+------------------------
+
+The ``UBLK_F_AUTO_BUF_REG`` feature automatically handles buffer registration
+and unregistration for I/O requests, which simplifies the buffer management
+process and reduces overhead in the ublk server implementation.
+
+This is another feature flag for using zero copy, and it is compatible with
+``UBLK_F_SUPPORT_ZERO_COPY``.
+
+Feature Overview
+~~~~~~~~~~~~~~~~
+
+This feature automatically registers request buffers to the io_uring context
+before delivering I/O commands to the ublk server and unregisters them when
+completing I/O commands. This eliminates the need for manual buffer
+registration/unregistration via ``UBLK_IO_REGISTER_IO_BUF`` and
+``UBLK_IO_UNREGISTER_IO_BUF`` commands, then IO handling in ublk server
+can avoid dependency on the two uring_cmd operations.
+
+IOs can't be issued concurrently to io_uring if there is any dependency
+among these IOs. So this way not only simplifies ublk server implementation,
+but also makes concurrent IO handling becomes possible by removing the
+dependency on buffer registration & unregistration commands.
+
+Usage Requirements
+~~~~~~~~~~~~~~~~~~
+
+1. The ublk server must create a sparse buffer table on the same ``io_ring_ctx``
+   used for ``UBLK_IO_FETCH_REQ`` and ``UBLK_IO_COMMIT_AND_FETCH_REQ``. If
+   uring_cmd is issued on a different ``io_ring_ctx``, manual buffer
+   unregistration is required.
+
+2. Buffer registration data must be passed via uring_cmd's ``sqe->addr`` with the
+   following structure::
+
+    struct ublk_auto_buf_reg {
+        __u16 index;      /* Buffer index for registration */
+        __u8 flags;       /* Registration flags */
+        __u8 reserved0;   /* Reserved for future use */
+        __u32 reserved1;  /* Reserved for future use */
+    };
+
+   ublk_auto_buf_reg_to_sqe_addr() is for converting the above structure into
+   ``sqe->addr``.
+
+3. All reserved fields in ``ublk_auto_buf_reg`` must be zeroed.
+
+4. Optional flags can be passed via ``ublk_auto_buf_reg.flags``.
+
+Fallback Behavior
+~~~~~~~~~~~~~~~~~
+
+If auto buffer registration fails:
+
+1. When ``UBLK_AUTO_BUF_REG_FALLBACK`` is enabled:
+   - The uring_cmd is completed
+   - ``UBLK_IO_F_NEED_REG_BUF`` is set in ``ublksrv_io_desc.op_flags``
+   - The ublk server must manually deal with the failure, such as, register
+     the buffer manually, or using user copy feature for retrieving the data
+     for handling ublk IO
+
+2. If fallback is not enabled:
+   - The ublk I/O request fails silently
+   - The uring_cmd won't be completed
+
+Limitations
+~~~~~~~~~~~
+
+- Requires same ``io_ring_ctx`` for all operations
+- May require manual buffer management in fallback cases
+- io_ring_ctx buffer table has a max size of 16K, which may not be enough
+  in case that too many ublk devices are handled by this single io_ring_ctx
+  and each one has very large queue depth
+
 References
 ==========
 

From f705d33c2f0353039d03e5d6f18f70467d86080e Mon Sep 17 00:00:00 2001
From: Damien Le Moal <dlemoal@kernel.org>
Date: Wed, 11 Jun 2025 09:59:15 +0900
Subject: [PATCH 0215/1334] block: Clear BIO_EMULATES_ZONE_APPEND flag on BIO
 completion

When blk_zone_write_plug_bio_endio() is called for a regular write BIO
used to emulate a zone append operation, that is, a BIO flagged with
BIO_EMULATES_ZONE_APPEND, the BIO operation code is restored to the
original REQ_OP_ZONE_APPEND but the BIO_EMULATES_ZONE_APPEND flag is not
cleared. Clear it to fully return the BIO to its orginal definition.

Fixes: 9b1ce7f0c6f8 ("block: Implement zone append emulation")
Cc: stable@vger.kernel.org
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20250611005915.89843-1-dlemoal@kernel.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-zoned.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/block/blk-zoned.c b/block/blk-zoned.c
index 8f15d1aa6eb8..cee7a0774a9b 100644
--- a/block/blk-zoned.c
+++ b/block/blk-zoned.c
@@ -1225,6 +1225,7 @@ void blk_zone_write_plug_bio_endio(struct bio *bio)
 	if (bio_flagged(bio, BIO_EMULATES_ZONE_APPEND)) {
 		bio->bi_opf &= ~REQ_OP_MASK;
 		bio->bi_opf |= REQ_OP_ZONE_APPEND;
+		bio_clear_flag(bio, BIO_EMULATES_ZONE_APPEND);
 	}
 
 	/*

From cf625013d8741c01407bbb4a60c111b61b9fa69d Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 11 Jun 2025 06:44:16 +0200
Subject: [PATCH 0216/1334] block: don't use submit_bio_noacct_nocheck in
 blk_zone_wplug_bio_work

Bios queued up in the zone write plug have already gone through all all
preparation in the submit_bio path, including the freeze protection.

Submitting them through submit_bio_noacct_nocheck duplicates the work
and can can cause deadlocks when freezing a queue with pending bio
write plugs.

Go straight to ->submit_bio or blk_mq_submit_bio to bypass the
superfluous extra freeze protection and checks.

Fixes: 9b1ce7f0c6f8 ("block: Implement zone append emulation")
Reported-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Damien Le Moal <dlemoal@kernel.org>
Tested-by: Damien Le Moal <dlemoal@kernel.org>
Link: https://lore.kernel.org/r/20250611044416.2351850-1-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-zoned.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/block/blk-zoned.c b/block/blk-zoned.c
index cee7a0774a9b..351d659280e1 100644
--- a/block/blk-zoned.c
+++ b/block/blk-zoned.c
@@ -1307,7 +1307,6 @@ again:
 	spin_unlock_irqrestore(&zwplug->lock, flags);
 
 	bdev = bio->bi_bdev;
-	submit_bio_noacct_nocheck(bio);
 
 	/*
 	 * blk-mq devices will reuse the extra reference on the request queue
@@ -1315,8 +1314,12 @@ again:
 	 * path for BIO-based devices will not do that. So drop this extra
 	 * reference here.
 	 */
-	if (bdev_test_flag(bdev, BD_HAS_SUBMIT_BIO))
+	if (bdev_test_flag(bdev, BD_HAS_SUBMIT_BIO)) {
+		bdev->bd_disk->fops->submit_bio(bio);
 		blk_queue_exit(bdev->bd_disk->queue);
+	} else {
+		blk_mq_submit_bio(bio);
+	}
 
 put_zwplug:
 	/* Drop the reference we took in disk_zone_wplug_schedule_bio_work(). */

From 961296e89dc3800e6a3abc3f5d5bb4192cf31e98 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Wed, 11 Jun 2025 08:48:46 -0600
Subject: [PATCH 0217/1334] block: use plug request list tail for one-shot
 backmerge attempt

Previously, the block layer stored the requests in the plug list in
LIFO order. For this reason, blk_attempt_plug_merge() would check
just the head entry for a back merge attempt, and abort after that
unless requests for multiple queues existed in the plug list. If more
than one request is present in the plug list, this makes the one-shot
back merging less useful than before, as it'll always fail to find a
quick merge candidate.

Use the tail entry for the one-shot merge attempt, which is the last
added request in the list. If that fails, abort immediately unless
there are multiple queues available. If multiple queues are available,
then scan the list. Ideally the latter scan would be a backwards scan
of the list, but as it currently stands, the plug list is singly linked
and hence this isn't easily feasible.

Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/linux-block/20250611121626.7252-1-abuehaze@amazon.com/
Reported-by: Hazem Mohamed Abuelfotoh <abuehaze@amazon.com>
Fixes: e70c301faece ("block: don't reorder requests in blk_add_rq_to_plug")
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-merge.c | 26 +++++++++++++-------------
 1 file changed, 13 insertions(+), 13 deletions(-)

diff --git a/block/blk-merge.c b/block/blk-merge.c
index 3af1d284add5..70d704615be5 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -998,20 +998,20 @@ bool blk_attempt_plug_merge(struct request_queue *q, struct bio *bio,
 	if (!plug || rq_list_empty(&plug->mq_list))
 		return false;
 
-	rq_list_for_each(&plug->mq_list, rq) {
-		if (rq->q == q) {
-			if (blk_attempt_bio_merge(q, rq, bio, nr_segs, false) ==
-			    BIO_MERGE_OK)
-				return true;
-			break;
-		}
+	rq = plug->mq_list.tail;
+	if (rq->q == q)
+		return blk_attempt_bio_merge(q, rq, bio, nr_segs, false) ==
+			BIO_MERGE_OK;
+	else if (!plug->multiple_queues)
+		return false;
 
-		/*
-		 * Only keep iterating plug list for merges if we have multiple
-		 * queues
-		 */
-		if (!plug->multiple_queues)
-			break;
+	rq_list_for_each(&plug->mq_list, rq) {
+		if (rq->q != q)
+			continue;
+		if (blk_attempt_bio_merge(q, rq, bio, nr_segs, false) ==
+		    BIO_MERGE_OK)
+			return true;
+		break;
 	}
 	return false;
 }

From 69a14d146f3b87819f3fb73ed5d1de3e1fa680c1 Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Mon, 2 Jun 2025 13:00:27 +0200
Subject: [PATCH 0218/1334] futex: Verify under the lock if hash can be
 replaced

Once the global hash is requested there is no way back to switch back to
the per-task private hash. This is checked at the begin of the function.

It is possible that two threads simultaneously request the global hash
and both pass the initial check and block later on the
mm::futex_hash_lock. In this case the first thread performs the switch
to the global hash. The second thread will also attempt to switch to the
global hash and while doing so, accessing the nonexisting slot 1 of the
struct futex_private_hash.
The same applies if the hash is made immutable: There is no reference
counting and the hash must not be replaced.

Verify under mm_struct::futex_phash that neither the global hash nor an
immutable hash in use.

Tested-by: "Lai, Yi" <yi1.lai@linux.intel.com>
Reported-by: "Lai, Yi" <yi1.lai@linux.intel.com>
Closes: https://lore.kernel.org/all/aDwDw9Aygqo6oAx+@ly-workstation/
Fixes: bd54df5ea7cad ("futex: Allow to resize the private local hash")
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/all/20250610104400.1077266-5-bigeasy@linutronix.de/
---
 kernel/futex/core.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/kernel/futex/core.c b/kernel/futex/core.c
index b652d2f60c40..90d53fb0ee9e 100644
--- a/kernel/futex/core.c
+++ b/kernel/futex/core.c
@@ -1629,6 +1629,16 @@ again:
 		mm->futex_phash_new = NULL;
 
 		if (fph) {
+			if (cur && (!cur->hash_mask || cur->immutable)) {
+				/*
+				 * If two threads simultaneously request the global
+				 * hash then the first one performs the switch,
+				 * the second one returns here.
+				 */
+				free = fph;
+				mm->futex_phash_new = new;
+				return -EBUSY;
+			}
 			if (cur && !new) {
 				/*
 				 * If we have an existing hash, but do not yet have

From 83f066fac3c231e58e9adf3b307e96fee172dfb3 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Wed, 11 Jun 2025 16:09:45 +0300
Subject: [PATCH 0219/1334] spi: stm32-ospi: clean up on error in probe()

If reset_control_acquire() fails, then we can't return directly.
We need to do a little clean up first.

Fixes: cf2c3eceb757 ("spi: stm32-ospi: Make usage of reset_control_acquire/release() API")
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Link: https://patch.msgid.link/aEmAGTUzzKZlLe3K@stanley.mountain
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-stm32-ospi.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/spi/spi-stm32-ospi.c b/drivers/spi/spi-stm32-ospi.c
index db6b1cfc970f..4ab7e86f4bd5 100644
--- a/drivers/spi/spi-stm32-ospi.c
+++ b/drivers/spi/spi-stm32-ospi.c
@@ -937,8 +937,10 @@ static int stm32_ospi_probe(struct platform_device *pdev)
 		goto err_pm_enable;
 
 	ret = reset_control_acquire(ospi->rstc);
-	if (ret)
-		return dev_err_probe(dev, ret, "Can not acquire reset %d\n", ret);
+	if (ret) {
+		dev_err_probe(dev, ret, "Can not acquire reset %d\n", ret);
+		goto err_pm_resume;
+	}
 
 	reset_control_assert(ospi->rstc);
 	udelay(2);

From 179a8427fcbffe36ccfed5e138d7c9b6180caff9 Mon Sep 17 00:00:00 2001
From: Ashish Kalra <ashish.kalra@amd.com>
Date: Mon, 12 May 2025 22:16:34 +0000
Subject: [PATCH 0220/1334] KVM: SEV: Disable SEV-SNP support on initialization
 failure

During platform init, SNP initialization may fail for several reasons,
such as firmware command failures and incompatible versions. However,
the KVM capability may continue to advertise support for it.

The platform may have SNP enabled but if SNP_INIT fails then SNP is
not supported by KVM.

During KVM module initialization query the SNP platform status to obtain
the SNP initialization state and use it as an additional condition to
determine support for SEV-SNP.

Co-developed-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Co-developed-by: Pratik R. Sampat <prsampat@amd.com>
Signed-off-by: Pratik R. Sampat <prsampat@amd.com>
Reviewed-by: Tom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: Ashish Kalra <ashish.kalra@amd.com>
Reviewed-by: Pankaj Gupta <pankaj.gupta@amd.com>
Reviewed-by: Pavan Kumar Paluri <papaluri@amd.com>
Message-ID: <20250512221634.12045-1-Ashish.Kalra@amd.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/svm/sev.c | 44 +++++++++++++++++++++++++++++++++---------
 1 file changed, 35 insertions(+), 9 deletions(-)

diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 5a69b657dae9..459c3b791fd4 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -2871,6 +2871,33 @@ void __init sev_set_cpu_caps(void)
 	}
 }
 
+static bool is_sev_snp_initialized(void)
+{
+	struct sev_user_data_snp_status *status;
+	struct sev_data_snp_addr buf;
+	bool initialized = false;
+	int ret, error = 0;
+
+	status = snp_alloc_firmware_page(GFP_KERNEL | __GFP_ZERO);
+	if (!status)
+		return false;
+
+	buf.address = __psp_pa(status);
+	ret = sev_do_cmd(SEV_CMD_SNP_PLATFORM_STATUS, &buf, &error);
+	if (ret) {
+		pr_err("SEV: SNP_PLATFORM_STATUS failed ret=%d, fw_error=%d (%#x)\n",
+		       ret, error, error);
+		goto out;
+	}
+
+	initialized = !!status->state;
+
+out:
+	snp_free_firmware_page(status);
+
+	return initialized;
+}
+
 void __init sev_hardware_setup(void)
 {
 	unsigned int eax, ebx, ecx, edx, sev_asid_count, sev_es_asid_count;
@@ -2975,6 +3002,14 @@ void __init sev_hardware_setup(void)
 	sev_snp_supported = sev_snp_enabled && cc_platform_has(CC_ATTR_HOST_SEV_SNP);
 
 out:
+	if (sev_enabled) {
+		init_args.probe = true;
+		if (sev_platform_init(&init_args))
+			sev_supported = sev_es_supported = sev_snp_supported = false;
+		else if (sev_snp_supported)
+			sev_snp_supported = is_sev_snp_initialized();
+	}
+
 	if (boot_cpu_has(X86_FEATURE_SEV))
 		pr_info("SEV %s (ASIDs %u - %u)\n",
 			sev_supported ? min_sev_asid <= max_sev_asid ? "enabled" :
@@ -3001,15 +3036,6 @@ out:
 	sev_supported_vmsa_features = 0;
 	if (sev_es_debug_swap_enabled)
 		sev_supported_vmsa_features |= SVM_SEV_FEAT_DEBUG_SWAP;
-
-	if (!sev_enabled)
-		return;
-
-	/*
-	 * Do both SNP and SEV initialization at KVM module load.
-	 */
-	init_args.probe = true;
-	sev_platform_init(&init_args);
 }
 
 void sev_hardware_unsetup(void)

From 488ef3560196ee10fc1c5547e1574a87068c3494 Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Wed, 28 May 2025 13:18:17 +0100
Subject: [PATCH 0221/1334] KEYS: Invert FINAL_PUT bit

Invert the FINAL_PUT bit so that test_bit_acquire and clear_bit_unlock
can be used instead of smp_mb.

Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Jarkko Sakkinen <jarkko@kernel.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/key.h | 2 +-
 security/keys/gc.c  | 4 ++--
 security/keys/key.c | 5 +++--
 3 files changed, 6 insertions(+), 5 deletions(-)

diff --git a/include/linux/key.h b/include/linux/key.h
index ba05de8579ec..81b8f05c6898 100644
--- a/include/linux/key.h
+++ b/include/linux/key.h
@@ -236,7 +236,7 @@ struct key {
 #define KEY_FLAG_ROOT_CAN_INVAL	7	/* set if key can be invalidated by root without permission */
 #define KEY_FLAG_KEEP		8	/* set if key should not be removed */
 #define KEY_FLAG_UID_KEYRING	9	/* set if key is a user or user session keyring */
-#define KEY_FLAG_FINAL_PUT	10	/* set if final put has happened on key */
+#define KEY_FLAG_USER_ALIVE	10	/* set if final put has not happened on key yet */
 
 	/* the key type and key description string
 	 * - the desc is used to match a key against search criteria
diff --git a/security/keys/gc.c b/security/keys/gc.c
index f27223ea4578..748e83818a76 100644
--- a/security/keys/gc.c
+++ b/security/keys/gc.c
@@ -218,8 +218,8 @@ continue_scanning:
 		key = rb_entry(cursor, struct key, serial_node);
 		cursor = rb_next(cursor);
 
-		if (test_bit(KEY_FLAG_FINAL_PUT, &key->flags)) {
-			smp_mb(); /* Clobber key->user after FINAL_PUT seen. */
+		if (!test_bit_acquire(KEY_FLAG_USER_ALIVE, &key->flags)) {
+			/* Clobber key->user after final put seen. */
 			goto found_unreferenced_key;
 		}
 
diff --git a/security/keys/key.c b/security/keys/key.c
index 7198cd2ac3a3..3bbdde778631 100644
--- a/security/keys/key.c
+++ b/security/keys/key.c
@@ -298,6 +298,7 @@ struct key *key_alloc(struct key_type *type, const char *desc,
 	key->restrict_link = restrict_link;
 	key->last_used_at = ktime_get_real_seconds();
 
+	key->flags |= 1 << KEY_FLAG_USER_ALIVE;
 	if (!(flags & KEY_ALLOC_NOT_IN_QUOTA))
 		key->flags |= 1 << KEY_FLAG_IN_QUOTA;
 	if (flags & KEY_ALLOC_BUILT_IN)
@@ -658,8 +659,8 @@ void key_put(struct key *key)
 				key->user->qnbytes -= key->quotalen;
 				spin_unlock_irqrestore(&key->user->lock, flags);
 			}
-			smp_mb(); /* key->user before FINAL_PUT set. */
-			set_bit(KEY_FLAG_FINAL_PUT, &key->flags);
+			/* Mark key as safe for GC after key->user done. */
+			clear_bit_unlock(KEY_FLAG_USER_ALIVE, &key->flags);
 			schedule_work(&key_gc_work);
 		}
 	}

From 62a65b32bddb0f242b106b8c464913f2f01c108d Mon Sep 17 00:00:00 2001
From: Drew Fustini <drew@pdp7.com>
Date: Fri, 6 Jun 2025 11:11:17 -0700
Subject: [PATCH 0222/1334] dt-bindings: pmem: Convert binding to YAML

Convert the PMEM device tree binding from text to YAML. This will allow
device trees with pmem-region nodes to pass dtbs_check.

[iweiny: fix ups from Rob/Drew]

Acked-by: Conor Dooley <conor.dooley@microchip.com>
Acked-by: Oliver O'Halloran <oohall@gmail.com>
Signed-off-by: Drew Fustini <drew@pdp7.com>
Acked-by: Dan Williams <dan.j.williams@intel.com>
Link: https://patch.msgid.link/20250606184405.359812-4-drew@pdp7.com
Signed-off-by: Ira Weiny <ira.weiny@intel.com>
---
 .../devicetree/bindings/pmem/pmem-region.txt  | 65 -------------------
 .../devicetree/bindings/pmem/pmem-region.yaml | 48 ++++++++++++++
 MAINTAINERS                                   |  2 +-
 3 files changed, 49 insertions(+), 66 deletions(-)
 delete mode 100644 Documentation/devicetree/bindings/pmem/pmem-region.txt
 create mode 100644 Documentation/devicetree/bindings/pmem/pmem-region.yaml

diff --git a/Documentation/devicetree/bindings/pmem/pmem-region.txt b/Documentation/devicetree/bindings/pmem/pmem-region.txt
deleted file mode 100644
index cd79975e85ec..000000000000
--- a/Documentation/devicetree/bindings/pmem/pmem-region.txt
+++ /dev/null
@@ -1,65 +0,0 @@
-Device-tree bindings for persistent memory regions
------------------------------------------------------
-
-Persistent memory refers to a class of memory devices that are:
-
-	a) Usable as main system memory (i.e. cacheable), and
-	b) Retain their contents across power failure.
-
-Given b) it is best to think of persistent memory as a kind of memory mapped
-storage device. To ensure data integrity the operating system needs to manage
-persistent regions separately to the normal memory pool. To aid with that this
-binding provides a standardised interface for discovering where persistent
-memory regions exist inside the physical address space.
-
-Bindings for the region nodes:
------------------------------
-
-Required properties:
-	- compatible = "pmem-region"
-
-	- reg = <base, size>;
-		The reg property should specify an address range that is
-		translatable to a system physical address range. This address
-		range should be mappable as normal system memory would be
-		(i.e cacheable).
-
-		If the reg property contains multiple address ranges
-		each address range will be treated as though it was specified
-		in a separate device node. Having multiple address ranges in a
-		node implies no special relationship between the two ranges.
-
-Optional properties:
-	- Any relevant NUMA associativity properties for the target platform.
-
-	- volatile; This property indicates that this region is actually
-	  backed by non-persistent memory. This lets the OS know that it
-	  may skip the cache flushes required to ensure data is made
-	  persistent after a write.
-
-	  If this property is absent then the OS must assume that the region
-	  is backed by non-volatile memory.
-
-Examples:
---------------------
-
-	/*
-	 * This node specifies one 4KB region spanning from
-	 * 0x5000 to 0x5fff that is backed by non-volatile memory.
-	 */
-	pmem@5000 {
-		compatible = "pmem-region";
-		reg = <0x00005000 0x00001000>;
-	};
-
-	/*
-	 * This node specifies two 4KB regions that are backed by
-	 * volatile (normal) memory.
-	 */
-	pmem@6000 {
-		compatible = "pmem-region";
-		reg = < 0x00006000 0x00001000
-			0x00008000 0x00001000 >;
-		volatile;
-	};
-
diff --git a/Documentation/devicetree/bindings/pmem/pmem-region.yaml b/Documentation/devicetree/bindings/pmem/pmem-region.yaml
new file mode 100644
index 000000000000..bd0f0c793f03
--- /dev/null
+++ b/Documentation/devicetree/bindings/pmem/pmem-region.yaml
@@ -0,0 +1,48 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/pmem-region.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+maintainers:
+  - Oliver O'Halloran <oohall@gmail.com>
+
+title: Persistent Memory Regions
+
+description: |
+  Persistent memory refers to a class of memory devices that are:
+
+    a) Usable as main system memory (i.e. cacheable), and
+    b) Retain their contents across power failure.
+
+  Given b) it is best to think of persistent memory as a kind of memory mapped
+  storage device. To ensure data integrity the operating system needs to manage
+  persistent regions separately to the normal memory pool. To aid with that this
+  binding provides a standardised interface for discovering where persistent
+  memory regions exist inside the physical address space.
+
+properties:
+  compatible:
+    const: pmem-region
+
+  reg:
+    maxItems: 1
+
+  volatile:
+    description:
+      Indicates the region is volatile (non-persistent) and the OS can skip
+      cache flushes for writes
+    type: boolean
+
+required:
+  - compatible
+  - reg
+
+additionalProperties: false
+
+examples:
+  - |
+    pmem@5000 {
+        compatible = "pmem-region";
+        reg = <0x00005000 0x00001000>;
+    };
diff --git a/MAINTAINERS b/MAINTAINERS
index a92290fffa16..73ded8134ffd 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -13798,7 +13798,7 @@ M:	Oliver O'Halloran <oohall@gmail.com>
 L:	nvdimm@lists.linux.dev
 S:	Supported
 Q:	https://patchwork.kernel.org/project/linux-nvdimm/list/
-F:	Documentation/devicetree/bindings/pmem/pmem-region.txt
+F:	Documentation/devicetree/bindings/pmem/pmem-region.yaml
 F:	drivers/nvdimm/of_pmem.c
 
 LIBNVDIMM: NON-VOLATILE MEMORY DEVICE SUBSYSTEM

From 20a2aa01f5aeb6daad9aeaa7c33dd512c58d81eb Mon Sep 17 00:00:00 2001
From: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Date: Thu, 5 Jun 2025 11:14:25 -0400
Subject: [PATCH 0223/1334] Bluetooth: Fix NULL pointer deference on
 eir_get_service_data

The len parameter is considered optional so it can be NULL so it cannot
be used for skipping to next entry of EIR_SERVICE_DATA.

Fixes: 8f9ae5b3ae80 ("Bluetooth: eir: Add helpers for managing service data")
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/eir.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/net/bluetooth/eir.c b/net/bluetooth/eir.c
index 1bc51e2b05a3..3e1713673ecc 100644
--- a/net/bluetooth/eir.c
+++ b/net/bluetooth/eir.c
@@ -366,17 +366,19 @@ u8 eir_create_scan_rsp(struct hci_dev *hdev, u8 instance, u8 *ptr)
 
 void *eir_get_service_data(u8 *eir, size_t eir_len, u16 uuid, size_t *len)
 {
-	while ((eir = eir_get_data(eir, eir_len, EIR_SERVICE_DATA, len))) {
+	size_t dlen;
+
+	while ((eir = eir_get_data(eir, eir_len, EIR_SERVICE_DATA, &dlen))) {
 		u16 value = get_unaligned_le16(eir);
 
 		if (uuid == value) {
 			if (len)
-				*len -= 2;
+				*len = dlen - 2;
 			return &eir[2];
 		}
 
-		eir += *len;
-		eir_len -= *len;
+		eir += dlen;
+		eir_len -= dlen;
 	}
 
 	return NULL;

From 5725bc608252050ed8a4d47d59225b7dd73474c8 Mon Sep 17 00:00:00 2001
From: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Date: Thu, 5 Jun 2025 11:15:16 -0400
Subject: [PATCH 0224/1334] Bluetooth: hci_sync: Fix broadcast/PA when using an
 existing instance

When using and existing adv_info instance for broadcast source it
needs to be updated to periodic first before it can be reused, also in
case the existing instance already have data hci_set_adv_instance_data
cannot be used directly since it would overwrite the existing data so
this reappend the original data after the Broadcast ID, if one was
generated.

Example:

bluetoothctl># Add PBP to EA so it can be later referenced as the BIS ID
bluetoothctl> advertise.service 0x1856 0x00 0x00
bluetoothctl> advertise on
...
< HCI Command: LE Set Extended Advertising Data (0x08|0x0037) plen 13
        Handle: 0x01
        Operation: Complete extended advertising data (0x03)
        Fragment preference: Minimize fragmentation (0x01)
        Data length: 0x09
        Service Data: Public Broadcast Announcement (0x1856)
          Data[2]: 0000
        Flags: 0x06
          LE General Discoverable Mode
          BR/EDR Not Supported
...
bluetoothctl># Attempt to acquire Broadcast Source transport
bluetoothctl>transport.acquire /org/bluez/hci0/pac_bcast0/fd0
...
< HCI Command: LE Set Extended Advertising Data (0x08|0x0037) plen 255
        Handle: 0x01
        Operation: Complete extended advertising data (0x03)
        Fragment preference: Minimize fragmentation (0x01)
        Data length: 0x0e
        Service Data: Broadcast Audio Announcement (0x1852)
        Broadcast ID: 11371620 (0xad8464)
        Service Data: Public Broadcast Announcement (0x1856)
          Data[2]: 0000
        Flags: 0x06
          LE General Discoverable Mode
          BR/EDR Not Supported

Link: https://github.com/bluez/bluez/issues/1117
Fixes: eca0ae4aea66 ("Bluetooth: Add initial implementation of BIS connections")
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/hci_sync.c | 20 +++++++++++++++-----
 1 file changed, 15 insertions(+), 5 deletions(-)

diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c
index 62d1ff951ebe..8ba1c3aa7801 100644
--- a/net/bluetooth/hci_sync.c
+++ b/net/bluetooth/hci_sync.c
@@ -1559,7 +1559,8 @@ static int hci_enable_per_advertising_sync(struct hci_dev *hdev, u8 instance)
 static int hci_adv_bcast_annoucement(struct hci_dev *hdev, struct adv_info *adv)
 {
 	u8 bid[3];
-	u8 ad[4 + 3];
+	u8 ad[HCI_MAX_EXT_AD_LENGTH];
+	u8 len;
 
 	/* Skip if NULL adv as instance 0x00 is used for general purpose
 	 * advertising so it cannot used for the likes of Broadcast Announcement
@@ -1585,8 +1586,10 @@ static int hci_adv_bcast_annoucement(struct hci_dev *hdev, struct adv_info *adv)
 
 	/* Generate Broadcast ID */
 	get_random_bytes(bid, sizeof(bid));
-	eir_append_service_data(ad, 0, 0x1852, bid, sizeof(bid));
-	hci_set_adv_instance_data(hdev, adv->instance, sizeof(ad), ad, 0, NULL);
+	len = eir_append_service_data(ad, 0, 0x1852, bid, sizeof(bid));
+	memcpy(ad + len, adv->adv_data, adv->adv_data_len);
+	hci_set_adv_instance_data(hdev, adv->instance, len + adv->adv_data_len,
+				  ad, 0, NULL);
 
 	return hci_update_adv_data_sync(hdev, adv->instance);
 }
@@ -1603,8 +1606,15 @@ int hci_start_per_adv_sync(struct hci_dev *hdev, u8 instance, u8 data_len,
 
 	if (instance) {
 		adv = hci_find_adv_instance(hdev, instance);
-		/* Create an instance if that could not be found */
-		if (!adv) {
+		if (adv) {
+			/* Turn it into periodic advertising */
+			adv->periodic = true;
+			adv->per_adv_data_len = data_len;
+			if (data)
+				memcpy(adv->per_adv_data, data, data_len);
+			adv->flags = flags;
+		} else if (!adv) {
+			/* Create an instance if that could not be found */
 			adv = hci_add_per_instance(hdev, instance, flags,
 						   data_len, data,
 						   sync_interval,

From 47c03902269aff377f959dc3fd94a9733aa31d6e Mon Sep 17 00:00:00 2001
From: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Date: Tue, 10 Jun 2025 10:14:35 -0400
Subject: [PATCH 0225/1334] Bluetooth: eir: Fix possible crashes on
 eir_create_adv_data

eir_create_adv_data may attempt to add EIR_FLAGS and EIR_TX_POWER
without checking if that would fit.

Link: https://github.com/bluez/bluez/issues/1117#issuecomment-2958244066
Fixes: 01ce70b0a274 ("Bluetooth: eir: Move EIR/Adv Data functions to its own file")
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/eir.c      | 7 ++++---
 net/bluetooth/eir.h      | 2 +-
 net/bluetooth/hci_sync.c | 5 +++--
 3 files changed, 8 insertions(+), 6 deletions(-)

diff --git a/net/bluetooth/eir.c b/net/bluetooth/eir.c
index 3e1713673ecc..3f72111ba651 100644
--- a/net/bluetooth/eir.c
+++ b/net/bluetooth/eir.c
@@ -242,7 +242,7 @@ u8 eir_create_per_adv_data(struct hci_dev *hdev, u8 instance, u8 *ptr)
 	return ad_len;
 }
 
-u8 eir_create_adv_data(struct hci_dev *hdev, u8 instance, u8 *ptr)
+u8 eir_create_adv_data(struct hci_dev *hdev, u8 instance, u8 *ptr, u8 size)
 {
 	struct adv_info *adv = NULL;
 	u8 ad_len = 0, flags = 0;
@@ -286,7 +286,7 @@ u8 eir_create_adv_data(struct hci_dev *hdev, u8 instance, u8 *ptr)
 		/* If flags would still be empty, then there is no need to
 		 * include the "Flags" AD field".
 		 */
-		if (flags) {
+		if (flags && (ad_len + eir_precalc_len(1) <= size)) {
 			ptr[0] = 0x02;
 			ptr[1] = EIR_FLAGS;
 			ptr[2] = flags;
@@ -316,7 +316,8 @@ skip_flags:
 		}
 
 		/* Provide Tx Power only if we can provide a valid value for it */
-		if (adv_tx_power != HCI_TX_POWER_INVALID) {
+		if (adv_tx_power != HCI_TX_POWER_INVALID &&
+		    (ad_len + eir_precalc_len(1) <= size)) {
 			ptr[0] = 0x02;
 			ptr[1] = EIR_TX_POWER;
 			ptr[2] = (u8)adv_tx_power;
diff --git a/net/bluetooth/eir.h b/net/bluetooth/eir.h
index 5c89a05e8b29..9372db83f912 100644
--- a/net/bluetooth/eir.h
+++ b/net/bluetooth/eir.h
@@ -9,7 +9,7 @@
 
 void eir_create(struct hci_dev *hdev, u8 *data);
 
-u8 eir_create_adv_data(struct hci_dev *hdev, u8 instance, u8 *ptr);
+u8 eir_create_adv_data(struct hci_dev *hdev, u8 instance, u8 *ptr, u8 size);
 u8 eir_create_scan_rsp(struct hci_dev *hdev, u8 instance, u8 *ptr);
 u8 eir_create_per_adv_data(struct hci_dev *hdev, u8 instance, u8 *ptr);
 
diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c
index 8ba1c3aa7801..83de3847c8ea 100644
--- a/net/bluetooth/hci_sync.c
+++ b/net/bluetooth/hci_sync.c
@@ -1822,7 +1822,8 @@ static int hci_set_ext_adv_data_sync(struct hci_dev *hdev, u8 instance)
 			return 0;
 	}
 
-	len = eir_create_adv_data(hdev, instance, pdu->data);
+	len = eir_create_adv_data(hdev, instance, pdu->data,
+				  HCI_MAX_EXT_AD_LENGTH);
 
 	pdu->length = len;
 	pdu->handle = adv ? adv->handle : instance;
@@ -1853,7 +1854,7 @@ static int hci_set_adv_data_sync(struct hci_dev *hdev, u8 instance)
 
 	memset(&cp, 0, sizeof(cp));
 
-	len = eir_create_adv_data(hdev, instance, cp.data);
+	len = eir_create_adv_data(hdev, instance, cp.data, sizeof(cp.data));
 
 	/* There's nothing to do if the data hasn't changed */
 	if (hdev->adv_data_len == len &&

From 2df108c227b266a9ec9e3fda3828d2ac9662aa33 Mon Sep 17 00:00:00 2001
From: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Date: Mon, 9 Jun 2025 14:53:53 -0400
Subject: [PATCH 0226/1334] Bluetooth: ISO: Fix using BT_SK_PA_SYNC to detect
 BIS sockets

BT_SK_PA_SYNC is only valid for Broadcast Sinks which means socket used
for Broadcast Sources wouldn't be able to use the likes of getpeername
to read out the sockaddr_iso_bc fields which may have been update (e.g.
bc_sid).

Fixes: 0a766a0affb5 ("Bluetooth: ISO: Fix getpeername not returning sockaddr_iso_bc fields")
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/iso.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/net/bluetooth/iso.c b/net/bluetooth/iso.c
index 6e2c752aaa8f..affa2077e3a2 100644
--- a/net/bluetooth/iso.c
+++ b/net/bluetooth/iso.c
@@ -1337,10 +1337,13 @@ static int iso_sock_getname(struct socket *sock, struct sockaddr *addr,
 	addr->sa_family = AF_BLUETOOTH;
 
 	if (peer) {
+		struct hci_conn *hcon = iso_pi(sk)->conn ?
+					iso_pi(sk)->conn->hcon : NULL;
+
 		bacpy(&sa->iso_bdaddr, &iso_pi(sk)->dst);
 		sa->iso_bdaddr_type = iso_pi(sk)->dst_type;
 
-		if (test_bit(BT_SK_PA_SYNC, &iso_pi(sk)->flags)) {
+		if (hcon && hcon->type == BIS_LINK) {
 			sa->iso_bc->bc_sid = iso_pi(sk)->bc_sid;
 			sa->iso_bc->bc_num_bis = iso_pi(sk)->bc_num_bis;
 			memcpy(sa->iso_bc->bc_bis, iso_pi(sk)->bc_bis,

From 5842c01a9ed1d515c8ba2d6d3733eac78ace89c1 Mon Sep 17 00:00:00 2001
From: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Date: Fri, 6 Jun 2025 14:32:49 -0400
Subject: [PATCH 0227/1334] Bluetooth: ISO: Fix not using bc_sid as
 advertisement SID

Currently bc_sid is being ignore when acting as Broadcast Source role,
so this fix it by passing the bc_sid and then use it when programming
the PA:

< HCI Command: LE Set Exte.. (0x08|0x0036) plen 25
        Handle: 0x01
        Properties: 0x0000
        Min advertising interval: 140.000 msec (0x00e0)
        Max advertising interval: 140.000 msec (0x00e0)
        Channel map: 37, 38, 39 (0x07)
        Own address type: Random (0x01)
        Peer address type: Public (0x00)
        Peer address: 00:00:00:00:00:00 (OUI 00-00-00)
        Filter policy: Allow Scan Request from Any, Allow Connect Request from Any (0x00)
        TX power: Host has no preference (0x7f)
        Primary PHY: LE 1M (0x01)
        Secondary max skip: 0x00
        Secondary PHY: LE 2M (0x02)
        SID: 0x01
        Scan request notifications: Disabled (0x00)

Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 include/net/bluetooth/hci_core.h |  9 ++++++---
 include/net/bluetooth/hci_sync.h |  4 ++--
 net/bluetooth/hci_conn.c         | 31 ++++++++++++++++++++++++-------
 net/bluetooth/hci_core.c         | 16 +++++++++++++++-
 net/bluetooth/hci_sync.c         | 20 +++++++++++++++++---
 net/bluetooth/iso.c              | 12 ++++++++----
 6 files changed, 72 insertions(+), 20 deletions(-)

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index f7b1a9eb9543..a760f05fa3fb 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -242,6 +242,7 @@ struct adv_info {
 	__u8	mesh;
 	__u8	instance;
 	__u8	handle;
+	__u8	sid;
 	__u32	flags;
 	__u16	timeout;
 	__u16	remaining_time;
@@ -1551,13 +1552,14 @@ struct hci_conn *hci_connect_sco(struct hci_dev *hdev, int type, bdaddr_t *dst,
 				 u16 timeout);
 struct hci_conn *hci_bind_cis(struct hci_dev *hdev, bdaddr_t *dst,
 			      __u8 dst_type, struct bt_iso_qos *qos);
-struct hci_conn *hci_bind_bis(struct hci_dev *hdev, bdaddr_t *dst,
+struct hci_conn *hci_bind_bis(struct hci_dev *hdev, bdaddr_t *dst, __u8 sid,
 			      struct bt_iso_qos *qos,
 			      __u8 base_len, __u8 *base);
 struct hci_conn *hci_connect_cis(struct hci_dev *hdev, bdaddr_t *dst,
 				 __u8 dst_type, struct bt_iso_qos *qos);
 struct hci_conn *hci_connect_bis(struct hci_dev *hdev, bdaddr_t *dst,
-				 __u8 dst_type, struct bt_iso_qos *qos,
+				 __u8 dst_type, __u8 sid,
+				 struct bt_iso_qos *qos,
 				 __u8 data_len, __u8 *data);
 struct hci_conn *hci_pa_create_sync(struct hci_dev *hdev, bdaddr_t *dst,
 		       __u8 dst_type, __u8 sid, struct bt_iso_qos *qos);
@@ -1832,6 +1834,7 @@ int hci_remove_remote_oob_data(struct hci_dev *hdev, bdaddr_t *bdaddr,
 
 void hci_adv_instances_clear(struct hci_dev *hdev);
 struct adv_info *hci_find_adv_instance(struct hci_dev *hdev, u8 instance);
+struct adv_info *hci_find_adv_sid(struct hci_dev *hdev, u8 sid);
 struct adv_info *hci_get_next_instance(struct hci_dev *hdev, u8 instance);
 struct adv_info *hci_add_adv_instance(struct hci_dev *hdev, u8 instance,
 				      u32 flags, u16 adv_data_len, u8 *adv_data,
@@ -1839,7 +1842,7 @@ struct adv_info *hci_add_adv_instance(struct hci_dev *hdev, u8 instance,
 				      u16 timeout, u16 duration, s8 tx_power,
 				      u32 min_interval, u32 max_interval,
 				      u8 mesh_handle);
-struct adv_info *hci_add_per_instance(struct hci_dev *hdev, u8 instance,
+struct adv_info *hci_add_per_instance(struct hci_dev *hdev, u8 instance, u8 sid,
 				      u32 flags, u8 data_len, u8 *data,
 				      u32 min_interval, u32 max_interval);
 int hci_set_adv_instance_data(struct hci_dev *hdev, u8 instance,
diff --git a/include/net/bluetooth/hci_sync.h b/include/net/bluetooth/hci_sync.h
index 72558c826aa1..5224f57f6af2 100644
--- a/include/net/bluetooth/hci_sync.h
+++ b/include/net/bluetooth/hci_sync.h
@@ -115,8 +115,8 @@ int hci_enable_ext_advertising_sync(struct hci_dev *hdev, u8 instance);
 int hci_enable_advertising_sync(struct hci_dev *hdev);
 int hci_enable_advertising(struct hci_dev *hdev);
 
-int hci_start_per_adv_sync(struct hci_dev *hdev, u8 instance, u8 data_len,
-			   u8 *data, u32 flags, u16 min_interval,
+int hci_start_per_adv_sync(struct hci_dev *hdev, u8 instance, u8 sid,
+			   u8 data_len, u8 *data, u32 flags, u16 min_interval,
 			   u16 max_interval, u16 sync_interval);
 
 int hci_disable_per_advertising_sync(struct hci_dev *hdev, u8 instance);
diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index 99efeed6a766..4f379184df5b 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -1501,8 +1501,8 @@ static int qos_set_bis(struct hci_dev *hdev, struct bt_iso_qos *qos)
 
 /* This function requires the caller holds hdev->lock */
 static struct hci_conn *hci_add_bis(struct hci_dev *hdev, bdaddr_t *dst,
-				    struct bt_iso_qos *qos, __u8 base_len,
-				    __u8 *base)
+				    __u8 sid, struct bt_iso_qos *qos,
+				    __u8 base_len, __u8 *base)
 {
 	struct hci_conn *conn;
 	int err;
@@ -1543,6 +1543,7 @@ static struct hci_conn *hci_add_bis(struct hci_dev *hdev, bdaddr_t *dst,
 		return conn;
 
 	conn->state = BT_CONNECT;
+	conn->sid = sid;
 
 	hci_conn_hold(conn);
 	return conn;
@@ -2062,7 +2063,8 @@ static int create_big_sync(struct hci_dev *hdev, void *data)
 	if (qos->bcast.bis)
 		sync_interval = interval * 4;
 
-	err = hci_start_per_adv_sync(hdev, qos->bcast.bis, conn->le_per_adv_data_len,
+	err = hci_start_per_adv_sync(hdev, qos->bcast.bis, conn->sid,
+				     conn->le_per_adv_data_len,
 				     conn->le_per_adv_data, flags, interval,
 				     interval, sync_interval);
 	if (err)
@@ -2134,7 +2136,7 @@ static void create_big_complete(struct hci_dev *hdev, void *data, int err)
 	}
 }
 
-struct hci_conn *hci_bind_bis(struct hci_dev *hdev, bdaddr_t *dst,
+struct hci_conn *hci_bind_bis(struct hci_dev *hdev, bdaddr_t *dst, __u8 sid,
 			      struct bt_iso_qos *qos,
 			      __u8 base_len, __u8 *base)
 {
@@ -2156,7 +2158,7 @@ struct hci_conn *hci_bind_bis(struct hci_dev *hdev, bdaddr_t *dst,
 						   base, base_len);
 
 	/* We need hci_conn object using the BDADDR_ANY as dst */
-	conn = hci_add_bis(hdev, dst, qos, base_len, eir);
+	conn = hci_add_bis(hdev, dst, sid, qos, base_len, eir);
 	if (IS_ERR(conn))
 		return conn;
 
@@ -2207,20 +2209,35 @@ static void bis_mark_per_adv(struct hci_conn *conn, void *data)
 }
 
 struct hci_conn *hci_connect_bis(struct hci_dev *hdev, bdaddr_t *dst,
-				 __u8 dst_type, struct bt_iso_qos *qos,
+				 __u8 dst_type, __u8 sid,
+				 struct bt_iso_qos *qos,
 				 __u8 base_len, __u8 *base)
 {
 	struct hci_conn *conn;
 	int err;
 	struct iso_list_data data;
 
-	conn = hci_bind_bis(hdev, dst, qos, base_len, base);
+	conn = hci_bind_bis(hdev, dst, sid, qos, base_len, base);
 	if (IS_ERR(conn))
 		return conn;
 
 	if (conn->state == BT_CONNECTED)
 		return conn;
 
+	/* Check if SID needs to be allocated then search for the first
+	 * available.
+	 */
+	if (conn->sid == HCI_SID_INVALID) {
+		u8 sid;
+
+		for (sid = 0; sid <= 0x0f; sid++) {
+			if (!hci_find_adv_sid(hdev, sid)) {
+				conn->sid = sid;
+				break;
+			}
+		}
+	}
+
 	data.big = qos->bcast.big;
 	data.bis = qos->bcast.bis;
 
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index 487c045a7ba8..07a8b4281a39 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -1584,6 +1584,19 @@ struct adv_info *hci_find_adv_instance(struct hci_dev *hdev, u8 instance)
 	return NULL;
 }
 
+/* This function requires the caller holds hdev->lock */
+struct adv_info *hci_find_adv_sid(struct hci_dev *hdev, u8 sid)
+{
+	struct adv_info *adv;
+
+	list_for_each_entry(adv, &hdev->adv_instances, list) {
+		if (adv->sid == sid)
+			return adv;
+	}
+
+	return NULL;
+}
+
 /* This function requires the caller holds hdev->lock */
 struct adv_info *hci_get_next_instance(struct hci_dev *hdev, u8 instance)
 {
@@ -1736,7 +1749,7 @@ struct adv_info *hci_add_adv_instance(struct hci_dev *hdev, u8 instance,
 }
 
 /* This function requires the caller holds hdev->lock */
-struct adv_info *hci_add_per_instance(struct hci_dev *hdev, u8 instance,
+struct adv_info *hci_add_per_instance(struct hci_dev *hdev, u8 instance, u8 sid,
 				      u32 flags, u8 data_len, u8 *data,
 				      u32 min_interval, u32 max_interval)
 {
@@ -1748,6 +1761,7 @@ struct adv_info *hci_add_per_instance(struct hci_dev *hdev, u8 instance,
 	if (IS_ERR(adv))
 		return adv;
 
+	adv->sid = sid;
 	adv->periodic = true;
 	adv->per_adv_data_len = data_len;
 
diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c
index 83de3847c8ea..6687f2a4d1eb 100644
--- a/net/bluetooth/hci_sync.c
+++ b/net/bluetooth/hci_sync.c
@@ -1261,10 +1261,12 @@ int hci_setup_ext_adv_instance_sync(struct hci_dev *hdev, u8 instance)
 		hci_cpu_to_le24(adv->min_interval, cp.min_interval);
 		hci_cpu_to_le24(adv->max_interval, cp.max_interval);
 		cp.tx_power = adv->tx_power;
+		cp.sid = adv->sid;
 	} else {
 		hci_cpu_to_le24(hdev->le_adv_min_interval, cp.min_interval);
 		hci_cpu_to_le24(hdev->le_adv_max_interval, cp.max_interval);
 		cp.tx_power = HCI_ADV_TX_POWER_NO_PREFERENCE;
+		cp.sid = 0x00;
 	}
 
 	secondary_adv = (flags & MGMT_ADV_FLAG_SEC_MASK);
@@ -1594,8 +1596,8 @@ static int hci_adv_bcast_annoucement(struct hci_dev *hdev, struct adv_info *adv)
 	return hci_update_adv_data_sync(hdev, adv->instance);
 }
 
-int hci_start_per_adv_sync(struct hci_dev *hdev, u8 instance, u8 data_len,
-			   u8 *data, u32 flags, u16 min_interval,
+int hci_start_per_adv_sync(struct hci_dev *hdev, u8 instance, u8 sid,
+			   u8 data_len, u8 *data, u32 flags, u16 min_interval,
 			   u16 max_interval, u16 sync_interval)
 {
 	struct adv_info *adv = NULL;
@@ -1607,6 +1609,18 @@ int hci_start_per_adv_sync(struct hci_dev *hdev, u8 instance, u8 data_len,
 	if (instance) {
 		adv = hci_find_adv_instance(hdev, instance);
 		if (adv) {
+			if (sid != HCI_SID_INVALID && adv->sid != sid) {
+				/* If the SID don't match attempt to find by
+				 * SID.
+				 */
+				adv = hci_find_adv_sid(hdev, sid);
+				if (!adv) {
+					bt_dev_err(hdev,
+						   "Unable to find adv_info");
+					return -EINVAL;
+				}
+			}
+
 			/* Turn it into periodic advertising */
 			adv->periodic = true;
 			adv->per_adv_data_len = data_len;
@@ -1615,7 +1629,7 @@ int hci_start_per_adv_sync(struct hci_dev *hdev, u8 instance, u8 data_len,
 			adv->flags = flags;
 		} else if (!adv) {
 			/* Create an instance if that could not be found */
-			adv = hci_add_per_instance(hdev, instance, flags,
+			adv = hci_add_per_instance(hdev, instance, sid, flags,
 						   data_len, data,
 						   sync_interval,
 						   sync_interval);
diff --git a/net/bluetooth/iso.c b/net/bluetooth/iso.c
index affa2077e3a2..3c2c98eecc62 100644
--- a/net/bluetooth/iso.c
+++ b/net/bluetooth/iso.c
@@ -336,7 +336,7 @@ static int iso_connect_bis(struct sock *sk)
 	struct hci_dev  *hdev;
 	int err;
 
-	BT_DBG("%pMR", &iso_pi(sk)->src);
+	BT_DBG("%pMR (SID 0x%2.2x)", &iso_pi(sk)->src, iso_pi(sk)->bc_sid);
 
 	hdev = hci_get_route(&iso_pi(sk)->dst, &iso_pi(sk)->src,
 			     iso_pi(sk)->src_type);
@@ -365,7 +365,7 @@ static int iso_connect_bis(struct sock *sk)
 
 	/* Just bind if DEFER_SETUP has been set */
 	if (test_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags)) {
-		hcon = hci_bind_bis(hdev, &iso_pi(sk)->dst,
+		hcon = hci_bind_bis(hdev, &iso_pi(sk)->dst, iso_pi(sk)->bc_sid,
 				    &iso_pi(sk)->qos, iso_pi(sk)->base_len,
 				    iso_pi(sk)->base);
 		if (IS_ERR(hcon)) {
@@ -375,12 +375,16 @@ static int iso_connect_bis(struct sock *sk)
 	} else {
 		hcon = hci_connect_bis(hdev, &iso_pi(sk)->dst,
 				       le_addr_type(iso_pi(sk)->dst_type),
-				       &iso_pi(sk)->qos, iso_pi(sk)->base_len,
-				       iso_pi(sk)->base);
+				       iso_pi(sk)->bc_sid, &iso_pi(sk)->qos,
+				       iso_pi(sk)->base_len, iso_pi(sk)->base);
 		if (IS_ERR(hcon)) {
 			err = PTR_ERR(hcon);
 			goto unlock;
 		}
+
+		/* Update SID if it was not set */
+		if (iso_pi(sk)->bc_sid == HCI_SID_INVALID)
+			iso_pi(sk)->bc_sid = hcon->sid;
 	}
 
 	conn = iso_conn_add(hcon);

From 7dd38ba4acbea9875b4ee061e20a26413e39d9f4 Mon Sep 17 00:00:00 2001
From: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Date: Wed, 11 Jun 2025 16:36:27 -0400
Subject: [PATCH 0228/1334] Bluetooth: MGMT: Fix sparse errors

This fixes the following errors:

net/bluetooth/mgmt.c:5400:59: sparse: sparse: incorrect type in argument 3
(different base types) @@     expected unsigned short [usertype] handle @@
got restricted __le16 [usertype] monitor_handle @@
net/bluetooth/mgmt.c:5400:59: sparse:     expected unsigned short [usertype] handle
net/bluetooth/mgmt.c:5400:59: sparse:     got restricted __le16 [usertype] monitor_handle

Fixes: e6ed54e86aae ("Bluetooth: MGMT: Fix UAF on mgmt_remove_adv_monitor_complete")
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202506060347.ux2O1p7L-lkp@intel.com/
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/mgmt.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index de7adb9a47f9..d540f7b4f75f 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -5102,11 +5102,11 @@ static void mgmt_adv_monitor_added(struct sock *sk, struct hci_dev *hdev,
 }
 
 static void mgmt_adv_monitor_removed(struct sock *sk, struct hci_dev *hdev,
-				     u16 handle)
+				     __le16 handle)
 {
 	struct mgmt_ev_adv_monitor_removed ev;
 
-	ev.monitor_handle = cpu_to_le16(handle);
+	ev.monitor_handle = handle;
 
 	mgmt_event(MGMT_EV_ADV_MONITOR_REMOVED, hdev, &ev, sizeof(ev), sk);
 }

From 47096d301e39f96962ca1fd6c7b71bfa796c53db Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Wed, 11 Jun 2025 11:05:16 -1000
Subject: [PATCH 0229/1334] sched_ext: Update mailing list entry in MAINTAINERS

Use sched-ext@lists.linux.dev instead of LKML.

Signed-off-by: Tejun Heo <tj@kernel.org>
---
 MAINTAINERS | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index a92290fffa16..8841f24d408b 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -22171,7 +22171,7 @@ R:	Tejun Heo <tj@kernel.org>
 R:	David Vernet <void@manifault.com>
 R:	Andrea Righi <arighi@nvidia.com>
 R:	Changwoo Min <changwoo@igalia.com>
-L:	linux-kernel@vger.kernel.org
+L:	sched-ext@lists.linux.dev
 S:	Maintained
 W:	https://github.com/sched-ext/scx
 T:	git://git.kernel.org/pub/scm/linux/kernel/git/tj/sched_ext.git

From f37258133c1e95e61db532e14067e28b4881bf24 Mon Sep 17 00:00:00 2001
From: Moshe Shemesh <moshe@nvidia.com>
Date: Tue, 10 Jun 2025 18:15:06 +0300
Subject: [PATCH 0230/1334] net/mlx5: Ensure fw pages are always allocated on
 same NUMA

When firmware asks the driver to allocate more pages, using event of
give_pages, the driver should always allocate it from same NUMA, the
original device NUMA. Current code uses dev_to_node() which can result
in different NUMA as it is changed by other driver flows, such as
mlx5_dma_zalloc_coherent_node(). Instead, use saved numa node for
allocating firmware pages.

Fixes: 311c7c71c9bb ("net/mlx5e: Allocate DMA coherent memory on reader NUMA node")
Signed-off-by: Moshe Shemesh <moshe@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Mark Bloch <mbloch@nvidia.com>
Link: https://patch.msgid.link/20250610151514.1094735-2-mbloch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
index 972e8e9df585..9bc9bd83c232 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
@@ -291,7 +291,7 @@ static void free_4k(struct mlx5_core_dev *dev, u64 addr, u32 function)
 static int alloc_system_page(struct mlx5_core_dev *dev, u32 function)
 {
 	struct device *device = mlx5_core_dma_dev(dev);
-	int nid = dev_to_node(device);
+	int nid = dev->priv.numa_node;
 	struct page *page;
 	u64 zero_addr = 1;
 	u64 addr;

From 687560d8a9a2d654829ad0da1ec24242f1de711d Mon Sep 17 00:00:00 2001
From: Amir Tzin <amirtz@nvidia.com>
Date: Tue, 10 Jun 2025 18:15:07 +0300
Subject: [PATCH 0231/1334] net/mlx5: Fix ECVF vports unload on shutdown flow

Fix shutdown flow UAF when a virtual function is created on the embedded
chip (ECVF) of a BlueField device. In such case the vport acl ingress
table is not properly destroyed.

ECVF functionality is independent of ecpf_vport_exists capability and
thus functions mlx5_eswitch_(enable|disable)_pf_vf_vports() should not
test it when enabling/disabling ECVF vports.

kernel log:
[] refcount_t: underflow; use-after-free.
[] WARNING: CPU: 3 PID: 1 at lib/refcount.c:28
   refcount_warn_saturate+0x124/0x220
----------------
[] Call trace:
[] refcount_warn_saturate+0x124/0x220
[] tree_put_node+0x164/0x1e0 [mlx5_core]
[] mlx5_destroy_flow_table+0x98/0x2c0 [mlx5_core]
[] esw_acl_ingress_table_destroy+0x28/0x40 [mlx5_core]
[] esw_acl_ingress_lgcy_cleanup+0x80/0xf4 [mlx5_core]
[] esw_legacy_vport_acl_cleanup+0x44/0x60 [mlx5_core]
[] esw_vport_cleanup+0x64/0x90 [mlx5_core]
[] mlx5_esw_vport_disable+0xc0/0x1d0 [mlx5_core]
[] mlx5_eswitch_unload_ec_vf_vports+0xcc/0x150 [mlx5_core]
[] mlx5_eswitch_disable_sriov+0x198/0x2a0 [mlx5_core]
[] mlx5_device_disable_sriov+0xb8/0x1e0 [mlx5_core]
[] mlx5_sriov_detach+0x40/0x50 [mlx5_core]
[] mlx5_unload+0x40/0xc4 [mlx5_core]
[] mlx5_unload_one_devl_locked+0x6c/0xe4 [mlx5_core]
[] mlx5_unload_one+0x3c/0x60 [mlx5_core]
[] shutdown+0x7c/0xa4 [mlx5_core]
[] pci_device_shutdown+0x3c/0xa0
[] device_shutdown+0x170/0x340
[] __do_sys_reboot+0x1f4/0x2a0
[] __arm64_sys_reboot+0x2c/0x40
[] invoke_syscall+0x78/0x100
[] el0_svc_common.constprop.0+0x54/0x184
[] do_el0_svc+0x30/0xac
[] el0_svc+0x48/0x160
[] el0t_64_sync_handler+0xa4/0x12c
[] el0t_64_sync+0x1a4/0x1a8
[] --[ end trace 9c4601d68c70030e ]---

Fixes: a7719b29a821 ("net/mlx5: Add management of EC VF vports")
Reviewed-by: Daniel Jurgens <danielj@nvidia.com>
Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
Signed-off-by: Amir Tzin <amirtz@nvidia.com>
Signed-off-by: Mark Bloch <mbloch@nvidia.com>
Link: https://patch.msgid.link/20250610151514.1094735-3-mbloch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/ethernet/mellanox/mlx5/core/eswitch.c | 21 ++++++++++++-------
 1 file changed, 13 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index 7fb8a3381f84..4917d185d0c3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -1295,12 +1295,15 @@ mlx5_eswitch_enable_pf_vf_vports(struct mlx5_eswitch *esw,
 		ret = mlx5_eswitch_load_pf_vf_vport(esw, MLX5_VPORT_ECPF, enabled_events);
 		if (ret)
 			goto ecpf_err;
-		if (mlx5_core_ec_sriov_enabled(esw->dev)) {
-			ret = mlx5_eswitch_load_ec_vf_vports(esw, esw->esw_funcs.num_ec_vfs,
-							     enabled_events);
-			if (ret)
-				goto ec_vf_err;
-		}
+	}
+
+	/* Enable ECVF vports */
+	if (mlx5_core_ec_sriov_enabled(esw->dev)) {
+		ret = mlx5_eswitch_load_ec_vf_vports(esw,
+						     esw->esw_funcs.num_ec_vfs,
+						     enabled_events);
+		if (ret)
+			goto ec_vf_err;
 	}
 
 	/* Enable VF vports */
@@ -1331,9 +1334,11 @@ void mlx5_eswitch_disable_pf_vf_vports(struct mlx5_eswitch *esw)
 {
 	mlx5_eswitch_unload_vf_vports(esw, esw->esw_funcs.num_vfs);
 
+	if (mlx5_core_ec_sriov_enabled(esw->dev))
+		mlx5_eswitch_unload_ec_vf_vports(esw,
+						 esw->esw_funcs.num_ec_vfs);
+
 	if (mlx5_ecpf_vport_exists(esw->dev)) {
-		if (mlx5_core_ec_sriov_enabled(esw->dev))
-			mlx5_eswitch_unload_ec_vf_vports(esw, esw->esw_funcs.num_vfs);
 		mlx5_eswitch_unload_pf_vf_vport(esw, MLX5_VPORT_ECPF);
 	}
 

From 8ec40e3f1f72bf8f8accf18020d487caa99f46a4 Mon Sep 17 00:00:00 2001
From: Patrisious Haddad <phaddad@nvidia.com>
Date: Tue, 10 Jun 2025 18:15:08 +0300
Subject: [PATCH 0232/1334] net/mlx5: Fix return value when searching for
 existing flow group

When attempting to add a rule to an existing flow group, if a matching
flow group exists but is not active, the error code returned should be
EAGAIN, so that the rule can be added to the matching flow group once
it is active, rather than ENOENT, which indicates that no matching
flow group was found.

Fixes: bd71b08ec2ee ("net/mlx5: Support multiple updates of steering rules in parallel")
Signed-off-by: Gavi Teitz <gavi@nvidia.com>
Signed-off-by: Roi Dayan <roid@nvidia.com>
Signed-off-by: Patrisious Haddad <phaddad@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Mark Bloch <mbloch@nvidia.com>
Link: https://patch.msgid.link/20250610151514.1094735-4-mbloch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index 23a7e8e7adfa..a8046200d376 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -2228,6 +2228,7 @@ try_add_to_existing_fg(struct mlx5_flow_table *ft,
 	struct mlx5_flow_handle *rule;
 	struct match_list *iter;
 	bool take_write = false;
+	bool try_again = false;
 	struct fs_fte *fte;
 	u64  version = 0;
 	int err;
@@ -2292,6 +2293,7 @@ skip_search:
 		nested_down_write_ref_node(&g->node, FS_LOCK_PARENT);
 
 		if (!g->node.active) {
+			try_again = true;
 			up_write_ref_node(&g->node, false);
 			continue;
 		}
@@ -2313,7 +2315,8 @@ skip_search:
 			tree_put_node(&fte->node, false);
 		return rule;
 	}
-	rule = ERR_PTR(-ENOENT);
+	err = try_again ? -EAGAIN : -ENOENT;
+	rule = ERR_PTR(err);
 out:
 	kmem_cache_free(steering->ftes_cache, fte);
 	return rule;

From a002602676cdae0c9996adb75b9310559b718a93 Mon Sep 17 00:00:00 2001
From: Vlad Dogaru <vdogaru@nvidia.com>
Date: Tue, 10 Jun 2025 18:15:09 +0300
Subject: [PATCH 0233/1334] net/mlx5: HWS, Init mutex on the correct path

The newly introduced mutex is only used for reformat actions, but it was
initialized for modify header instead.

The struct that contains the mutex is zero-initialized and an all-zero
mutex is valid, so the issue only shows up with CONFIG_DEBUG_MUTEXES.

Fixes: b206d9ec19df ("net/mlx5: HWS, register reformat actions with fw")
Signed-off-by: Vlad Dogaru <vdogaru@nvidia.com>
Reviewed-by: Yevgeny Kliteynik <kliteyn@nvidia.com>
Signed-off-by: Mark Bloch <mbloch@nvidia.com>
Link: https://patch.msgid.link/20250610151514.1094735-5-mbloch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws.c
index 9d1c0e4b224a..372e2be90706 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws.c
@@ -1357,6 +1357,7 @@ mlx5_cmd_hws_packet_reformat_alloc(struct mlx5_flow_root_namespace *ns,
 		pkt_reformat->fs_hws_action.pr_data = pr_data;
 	}
 
+	mutex_init(&pkt_reformat->fs_hws_action.lock);
 	pkt_reformat->owner = MLX5_FLOW_RESOURCE_OWNER_HWS;
 	pkt_reformat->fs_hws_action.hws_action = hws_action;
 	return 0;
@@ -1503,7 +1504,6 @@ static int mlx5_cmd_hws_modify_header_alloc(struct mlx5_flow_root_namespace *ns,
 		err = -ENOMEM;
 		goto release_mh;
 	}
-	mutex_init(&modify_hdr->fs_hws_action.lock);
 	modify_hdr->fs_hws_action.mh_data = mh_data;
 	modify_hdr->fs_hws_action.fs_pool = pool;
 	modify_hdr->owner = MLX5_FLOW_RESOURCE_OWNER_SW;

From b5e3c76f35ee7e814c2469c73406c5bbf110d89c Mon Sep 17 00:00:00 2001
From: Yevgeny Kliteynik <kliteyn@nvidia.com>
Date: Tue, 10 Jun 2025 18:15:10 +0300
Subject: [PATCH 0234/1334] net/mlx5: HWS, fix missing ip_version handling in
 definer

Fix missing field handling in definer - outer IP version.

Fixes: 74a778b4a63f ("net/mlx5: HWS, added definers handling")
Signed-off-by: Yevgeny Kliteynik <kliteyn@nvidia.com>
Signed-off-by: Mark Bloch <mbloch@nvidia.com>
Link: https://patch.msgid.link/20250610151514.1094735-6-mbloch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/steering/hws/definer.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/definer.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/definer.c
index 5cc0dc002ac1..d45e1145d197 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/definer.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/definer.c
@@ -785,6 +785,9 @@ hws_definer_conv_outer(struct mlx5hws_definer_conv_data *cd,
 	HWS_SET_HDR(fc, match_param, IP_PROTOCOL_O,
 		    outer_headers.ip_protocol,
 		    eth_l3_outer.protocol_next_header);
+	HWS_SET_HDR(fc, match_param, IP_VERSION_O,
+		    outer_headers.ip_version,
+		    eth_l3_outer.ip_version);
 	HWS_SET_HDR(fc, match_param, IP_TTL_O,
 		    outer_headers.ttl_hoplimit,
 		    eth_l3_outer.time_to_live_hop_limit);

From b8335829518ec5988294280e37d735799209d70d Mon Sep 17 00:00:00 2001
From: Vlad Dogaru <vdogaru@nvidia.com>
Date: Tue, 10 Jun 2025 18:15:11 +0300
Subject: [PATCH 0235/1334] net/mlx5: HWS, make sure the uplink is the last
 destination

When there are more than one destinations, we create a FW flow
table and provide it with all the destinations. FW requires to
have wire as the last destination in the list (if it exists),
otherwise the operation fails with FW syndrome.

This patch fixes the destination array action creation: if it
contains a wire destination, it is moved to the end.

Fixes: 504e536d9010 ("net/mlx5: HWS, added actions handling")
Signed-off-by: Vlad Dogaru <vdogaru@nvidia.com>
Reviewed-by: Yevgeny Kliteynik <kliteyn@nvidia.com>
Signed-off-by: Mark Bloch <mbloch@nvidia.com>
Link: https://patch.msgid.link/20250610151514.1094735-7-mbloch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../mellanox/mlx5/core/steering/hws/action.c       | 14 +++++++-------
 .../mellanox/mlx5/core/steering/hws/fs_hws.c       |  3 +++
 .../mellanox/mlx5/core/steering/hws/mlx5hws.h      |  1 +
 3 files changed, 11 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/action.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/action.c
index fb62f3bc4bd4..447ea3f8722c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/action.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/action.c
@@ -1370,8 +1370,8 @@ mlx5hws_action_create_dest_array(struct mlx5hws_context *ctx,
 	struct mlx5hws_cmd_set_fte_attr fte_attr = {0};
 	struct mlx5hws_cmd_forward_tbl *fw_island;
 	struct mlx5hws_action *action;
-	u32 i /*, packet_reformat_id*/;
-	int ret;
+	int ret, last_dest_idx = -1;
+	u32 i;
 
 	if (num_dest <= 1) {
 		mlx5hws_err(ctx, "Action must have multiple dests\n");
@@ -1401,11 +1401,8 @@ mlx5hws_action_create_dest_array(struct mlx5hws_context *ctx,
 			dest_list[i].destination_id = dests[i].dest->dest_obj.obj_id;
 			fte_attr.action_flags |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
 			fte_attr.ignore_flow_level = ignore_flow_level;
-			/* ToDo: In SW steering we have a handling of 'go to WIRE'
-			 * destination here by upper layer setting 'is_wire_ft' flag
-			 * if the destination is wire.
-			 * This is because uplink should be last dest in the list.
-			 */
+			if (dests[i].is_wire_ft)
+				last_dest_idx = i;
 			break;
 		case MLX5HWS_ACTION_TYP_VPORT:
 			dest_list[i].destination_type = MLX5_FLOW_DESTINATION_TYPE_VPORT;
@@ -1429,6 +1426,9 @@ mlx5hws_action_create_dest_array(struct mlx5hws_context *ctx,
 		}
 	}
 
+	if (last_dest_idx != -1)
+		swap(dest_list[last_dest_idx], dest_list[num_dest - 1]);
+
 	fte_attr.dests_num = num_dest;
 	fte_attr.dests = dest_list;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws.c
index 372e2be90706..bf4643d0ce17 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws.c
@@ -966,6 +966,9 @@ static int mlx5_fs_fte_get_hws_actions(struct mlx5_flow_root_namespace *ns,
 			switch (attr->type) {
 			case MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE:
 				dest_action = mlx5_fs_get_dest_action_ft(fs_ctx, dst);
+				if (dst->dest_attr.ft->flags &
+				    MLX5_FLOW_TABLE_UPLINK_VPORT)
+					dest_actions[num_dest_actions].is_wire_ft = true;
 				break;
 			case MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE_NUM:
 				dest_action = mlx5_fs_get_dest_action_table_num(fs_ctx,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws.h
index 9bbadc4d8a0b..d8ac6c196211 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws.h
@@ -213,6 +213,7 @@ struct mlx5hws_action_dest_attr {
 	struct mlx5hws_action *dest;
 	/* Optional reformat action */
 	struct mlx5hws_action *reformat;
+	bool is_wire_ft;
 };
 
 /**

From aa9c44b842096c553871bc68a8cebc7861fa192b Mon Sep 17 00:00:00 2001
From: Jianbo Liu <jianbol@nvidia.com>
Date: Tue, 10 Jun 2025 18:15:13 +0300
Subject: [PATCH 0236/1334] net/mlx5e: Fix leak of Geneve TLV option object

Previously, a unique tunnel id was added for the matching on TC
non-zero chains, to support inner header rewrite with goto action.
Later, it was used to support VF tunnel offload for vxlan, then for
Geneve and GRE. To support VF tunnel, a temporary mlx5_flow_spec is
used to parse tunnel options. For Geneve, if there is TLV option, a
object is created, or refcnt is added if already exists. But the
temporary mlx5_flow_spec is directly freed after parsing, which causes
the leak because no information regarding the object is saved in
flow's mlx5_flow_spec, which is used to free the object when deleting
the flow.

To fix the leak, call mlx5_geneve_tlv_option_del() before free the
temporary spec if it has TLV object.

Fixes: 521933cdc4aa ("net/mlx5e: Support Geneve and GRE with VF tunnel offload")
Signed-off-by: Jianbo Liu <jianbol@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Alex Lazar <alazar@nvidia.com>
Signed-off-by: Mark Bloch <mbloch@nvidia.com>
Link: https://patch.msgid.link/20250610151514.1094735-9-mbloch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index f1d908f61134..fef418e1ed1a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -2028,9 +2028,8 @@ err_out:
 	return err;
 }
 
-static bool mlx5_flow_has_geneve_opt(struct mlx5e_tc_flow *flow)
+static bool mlx5_flow_has_geneve_opt(struct mlx5_flow_spec *spec)
 {
-	struct mlx5_flow_spec *spec = &flow->attr->parse_attr->spec;
 	void *headers_v = MLX5_ADDR_OF(fte_match_param,
 				       spec->match_value,
 				       misc_parameters_3);
@@ -2069,7 +2068,7 @@ static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv,
 	}
 	complete_all(&flow->del_hw_done);
 
-	if (mlx5_flow_has_geneve_opt(flow))
+	if (mlx5_flow_has_geneve_opt(&attr->parse_attr->spec))
 		mlx5_geneve_tlv_option_del(priv->mdev->geneve);
 
 	if (flow->decap_route)
@@ -2574,12 +2573,13 @@ static int parse_tunnel_attr(struct mlx5e_priv *priv,
 
 		err = mlx5e_tc_tun_parse(filter_dev, priv, tmp_spec, f, match_level);
 		if (err) {
-			kvfree(tmp_spec);
 			NL_SET_ERR_MSG_MOD(extack, "Failed to parse tunnel attributes");
 			netdev_warn(priv->netdev, "Failed to parse tunnel attributes");
-			return err;
+		} else {
+			err = mlx5e_tc_set_attr_rx_tun(flow, tmp_spec);
 		}
-		err = mlx5e_tc_set_attr_rx_tun(flow, tmp_spec);
+		if (mlx5_flow_has_geneve_opt(tmp_spec))
+			mlx5_geneve_tlv_option_del(priv->mdev->geneve);
 		kvfree(tmp_spec);
 		if (err)
 			return err;

From 875d7c160d60616ff06dedb70470ad199661efe7 Mon Sep 17 00:00:00 2001
From: Shahar Shitrit <shshitrit@nvidia.com>
Date: Tue, 10 Jun 2025 18:15:14 +0300
Subject: [PATCH 0237/1334] net/mlx5e: Fix number of lanes to UNKNOWN when
 using data_rate_oper

When the link is up, either eth_proto_oper or ext_eth_proto_oper
typically reports the active link protocol, from which both speed
and number of lanes can be retrieved. However, in certain cases,
such as when a NIC is connected via a non-standard cable, the
firmware may not report the protocol.

In such scenarios, the speed can still be obtained from the
data_rate_oper field in PTYS register. Since data_rate_oper
provides only speed information and lacks lane details, it is
incorrect to derive the number of lanes from it.

This patch corrects the behavior by setting the number of lanes to
UNKNOWN instead of incorrectly using MAX_LANES when relying on
data_rate_oper.

Fixes: 7e959797f021 ("net/mlx5e: Enable lanes configuration when auto-negotiation is off")
Signed-off-by: Shahar Shitrit <shshitrit@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Mark Bloch <mbloch@nvidia.com>
Link: https://patch.msgid.link/20250610151514.1094735-10-mbloch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index ea078c9f5d15..3cb8d3bf9044 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -43,7 +43,6 @@
 #include "en/fs_ethtool.h"
 
 #define LANES_UNKNOWN		 0
-#define MAX_LANES		 8
 
 void mlx5e_ethtool_get_drvinfo(struct mlx5e_priv *priv,
 			       struct ethtool_drvinfo *drvinfo)
@@ -1098,10 +1097,8 @@ static void get_link_properties(struct net_device *netdev,
 		speed = info->speed;
 		lanes = info->lanes;
 		duplex = DUPLEX_FULL;
-	} else if (data_rate_oper) {
+	} else if (data_rate_oper)
 		speed = 100 * data_rate_oper;
-		lanes = MAX_LANES;
-	}
 
 out:
 	link_ksettings->base.duplex = duplex;

From 403d1338a4a59cfebb4ded53fa35fbd5119f36b1 Mon Sep 17 00:00:00 2001
From: Magnus Lindholm <linmag7@gmail.com>
Date: Tue, 18 Feb 2025 18:55:14 +0100
Subject: [PATCH 0238/1334] mm: pgtable: fix pte_swp_exclusive

Make pte_swp_exclusive return bool instead of int.  This will better
reflect how pte_swp_exclusive is actually used in the code.

This fixes swap/swapoff problems on Alpha due pte_swp_exclusive not
returning correct values when _PAGE_SWP_EXCLUSIVE bit resides in upper
32-bits of PTE (like on alpha).

Suggested-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Magnus Lindholm <linmag7@gmail.com>
Cc: Sam James <sam@gentoo.org>
Link: https://lore.kernel.org/lkml/20250218175735.19882-2-linmag7@gmail.com/
Link: https://lore.kernel.org/lkml/20250602041118.GA2675383@ZenIV/
[ Applied as the 'sed' script Al suggested   - Linus ]
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/alpha/include/asm/pgtable.h             | 2 +-
 arch/arc/include/asm/pgtable-bits-arcv2.h    | 2 +-
 arch/arm/include/asm/pgtable.h               | 2 +-
 arch/arm64/include/asm/pgtable.h             | 2 +-
 arch/csky/include/asm/pgtable.h              | 2 +-
 arch/hexagon/include/asm/pgtable.h           | 2 +-
 arch/loongarch/include/asm/pgtable.h         | 2 +-
 arch/m68k/include/asm/mcf_pgtable.h          | 2 +-
 arch/m68k/include/asm/motorola_pgtable.h     | 2 +-
 arch/m68k/include/asm/sun3_pgtable.h         | 2 +-
 arch/microblaze/include/asm/pgtable.h        | 2 +-
 arch/mips/include/asm/pgtable.h              | 4 ++--
 arch/nios2/include/asm/pgtable.h             | 2 +-
 arch/openrisc/include/asm/pgtable.h          | 2 +-
 arch/parisc/include/asm/pgtable.h            | 2 +-
 arch/powerpc/include/asm/book3s/32/pgtable.h | 2 +-
 arch/powerpc/include/asm/book3s/64/pgtable.h | 2 +-
 arch/powerpc/include/asm/nohash/pgtable.h    | 2 +-
 arch/riscv/include/asm/pgtable.h             | 2 +-
 arch/s390/include/asm/pgtable.h              | 2 +-
 arch/sh/include/asm/pgtable_32.h             | 2 +-
 arch/sparc/include/asm/pgtable_32.h          | 2 +-
 arch/sparc/include/asm/pgtable_64.h          | 2 +-
 arch/um/include/asm/pgtable.h                | 2 +-
 arch/x86/include/asm/pgtable.h               | 2 +-
 arch/xtensa/include/asm/pgtable.h            | 2 +-
 26 files changed, 27 insertions(+), 27 deletions(-)

diff --git a/arch/alpha/include/asm/pgtable.h b/arch/alpha/include/asm/pgtable.h
index 2676017f42f1..44e7aedac6e8 100644
--- a/arch/alpha/include/asm/pgtable.h
+++ b/arch/alpha/include/asm/pgtable.h
@@ -327,7 +327,7 @@ extern inline pte_t mk_swap_pte(unsigned long type, unsigned long offset)
 #define __pte_to_swp_entry(pte)	((swp_entry_t) { pte_val(pte) })
 #define __swp_entry_to_pte(x)	((pte_t) { (x).val })
 
-static inline int pte_swp_exclusive(pte_t pte)
+static inline bool pte_swp_exclusive(pte_t pte)
 {
 	return pte_val(pte) & _PAGE_SWP_EXCLUSIVE;
 }
diff --git a/arch/arc/include/asm/pgtable-bits-arcv2.h b/arch/arc/include/asm/pgtable-bits-arcv2.h
index 8ebec1b21d24..3084c53f402d 100644
--- a/arch/arc/include/asm/pgtable-bits-arcv2.h
+++ b/arch/arc/include/asm/pgtable-bits-arcv2.h
@@ -130,7 +130,7 @@ void update_mmu_cache_range(struct vm_fault *vmf, struct vm_area_struct *vma,
 #define __pte_to_swp_entry(pte)		((swp_entry_t) { pte_val(pte) })
 #define __swp_entry_to_pte(x)		((pte_t) { (x).val })
 
-static inline int pte_swp_exclusive(pte_t pte)
+static inline bool pte_swp_exclusive(pte_t pte)
 {
 	return pte_val(pte) & _PAGE_SWP_EXCLUSIVE;
 }
diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h
index 7f1c3b4e3e04..86378eec7757 100644
--- a/arch/arm/include/asm/pgtable.h
+++ b/arch/arm/include/asm/pgtable.h
@@ -301,7 +301,7 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 #define __pte_to_swp_entry(pte)	((swp_entry_t) { pte_val(pte) })
 #define __swp_entry_to_pte(swp)	__pte((swp).val)
 
-static inline int pte_swp_exclusive(pte_t pte)
+static inline bool pte_swp_exclusive(pte_t pte)
 {
 	return pte_isset(pte, L_PTE_SWP_EXCLUSIVE);
 }
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index 88db8a0c0b37..192d86e1cc76 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -563,7 +563,7 @@ static inline pte_t pte_swp_mkexclusive(pte_t pte)
 	return set_pte_bit(pte, __pgprot(PTE_SWP_EXCLUSIVE));
 }
 
-static inline int pte_swp_exclusive(pte_t pte)
+static inline bool pte_swp_exclusive(pte_t pte)
 {
 	return pte_val(pte) & PTE_SWP_EXCLUSIVE;
 }
diff --git a/arch/csky/include/asm/pgtable.h b/arch/csky/include/asm/pgtable.h
index b8378431aeff..5a394be09c35 100644
--- a/arch/csky/include/asm/pgtable.h
+++ b/arch/csky/include/asm/pgtable.h
@@ -200,7 +200,7 @@ static inline pte_t pte_mkyoung(pte_t pte)
 	return pte;
 }
 
-static inline int pte_swp_exclusive(pte_t pte)
+static inline bool pte_swp_exclusive(pte_t pte)
 {
 	return pte_val(pte) & _PAGE_SWP_EXCLUSIVE;
 }
diff --git a/arch/hexagon/include/asm/pgtable.h b/arch/hexagon/include/asm/pgtable.h
index 9fbdfdbc539f..fbf24d1d1ca6 100644
--- a/arch/hexagon/include/asm/pgtable.h
+++ b/arch/hexagon/include/asm/pgtable.h
@@ -387,7 +387,7 @@ static inline unsigned long pmd_page_vaddr(pmd_t pmd)
 		(((type & 0x1f) << 1) | \
 		 ((offset & 0x3ffff8) << 10) | ((offset & 0x7) << 7)) })
 
-static inline int pte_swp_exclusive(pte_t pte)
+static inline bool pte_swp_exclusive(pte_t pte)
 {
 	return pte_val(pte) & _PAGE_SWP_EXCLUSIVE;
 }
diff --git a/arch/loongarch/include/asm/pgtable.h b/arch/loongarch/include/asm/pgtable.h
index a3f17914dbab..b30185302c07 100644
--- a/arch/loongarch/include/asm/pgtable.h
+++ b/arch/loongarch/include/asm/pgtable.h
@@ -301,7 +301,7 @@ static inline pte_t mk_swap_pte(unsigned long type, unsigned long offset)
 #define __pmd_to_swp_entry(pmd) ((swp_entry_t) { pmd_val(pmd) })
 #define __swp_entry_to_pmd(x)	((pmd_t) { (x).val | _PAGE_HUGE })
 
-static inline int pte_swp_exclusive(pte_t pte)
+static inline bool pte_swp_exclusive(pte_t pte)
 {
 	return pte_val(pte) & _PAGE_SWP_EXCLUSIVE;
 }
diff --git a/arch/m68k/include/asm/mcf_pgtable.h b/arch/m68k/include/asm/mcf_pgtable.h
index f5c596b211d4..d79fef609194 100644
--- a/arch/m68k/include/asm/mcf_pgtable.h
+++ b/arch/m68k/include/asm/mcf_pgtable.h
@@ -268,7 +268,7 @@ extern pgd_t kernel_pg_dir[PTRS_PER_PGD];
 #define __pte_to_swp_entry(pte)	((swp_entry_t) { pte_val(pte) })
 #define __swp_entry_to_pte(x)	(__pte((x).val))
 
-static inline int pte_swp_exclusive(pte_t pte)
+static inline bool pte_swp_exclusive(pte_t pte)
 {
 	return pte_val(pte) & _PAGE_SWP_EXCLUSIVE;
 }
diff --git a/arch/m68k/include/asm/motorola_pgtable.h b/arch/m68k/include/asm/motorola_pgtable.h
index 040ac3bad713..14fee64d3e60 100644
--- a/arch/m68k/include/asm/motorola_pgtable.h
+++ b/arch/m68k/include/asm/motorola_pgtable.h
@@ -185,7 +185,7 @@ extern pgd_t kernel_pg_dir[128];
 #define __pte_to_swp_entry(pte)	((swp_entry_t) { pte_val(pte) })
 #define __swp_entry_to_pte(x)	((pte_t) { (x).val })
 
-static inline int pte_swp_exclusive(pte_t pte)
+static inline bool pte_swp_exclusive(pte_t pte)
 {
 	return pte_val(pte) & _PAGE_SWP_EXCLUSIVE;
 }
diff --git a/arch/m68k/include/asm/sun3_pgtable.h b/arch/m68k/include/asm/sun3_pgtable.h
index 73745dc0ec0e..858cbe936f5b 100644
--- a/arch/m68k/include/asm/sun3_pgtable.h
+++ b/arch/m68k/include/asm/sun3_pgtable.h
@@ -169,7 +169,7 @@ extern pgd_t kernel_pg_dir[PTRS_PER_PGD];
 #define __pte_to_swp_entry(pte)	((swp_entry_t) { pte_val(pte) })
 #define __swp_entry_to_pte(x)	((pte_t) { (x).val })
 
-static inline int pte_swp_exclusive(pte_t pte)
+static inline bool pte_swp_exclusive(pte_t pte)
 {
 	return pte_val(pte) & _PAGE_SWP_EXCLUSIVE;
 }
diff --git a/arch/microblaze/include/asm/pgtable.h b/arch/microblaze/include/asm/pgtable.h
index b1bb2c65dd04..bae1abfa6f6b 100644
--- a/arch/microblaze/include/asm/pgtable.h
+++ b/arch/microblaze/include/asm/pgtable.h
@@ -398,7 +398,7 @@ extern pgd_t swapper_pg_dir[PTRS_PER_PGD];
 #define __pte_to_swp_entry(pte)	((swp_entry_t) { pte_val(pte) >> 2 })
 #define __swp_entry_to_pte(x)	((pte_t) { (x).val << 2 })
 
-static inline int pte_swp_exclusive(pte_t pte)
+static inline bool pte_swp_exclusive(pte_t pte)
 {
 	return pte_val(pte) & _PAGE_SWP_EXCLUSIVE;
 }
diff --git a/arch/mips/include/asm/pgtable.h b/arch/mips/include/asm/pgtable.h
index 4852b005a72d..ae73ecf4c41a 100644
--- a/arch/mips/include/asm/pgtable.h
+++ b/arch/mips/include/asm/pgtable.h
@@ -534,7 +534,7 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 #endif
 
 #if defined(CONFIG_PHYS_ADDR_T_64BIT) && defined(CONFIG_CPU_MIPS32)
-static inline int pte_swp_exclusive(pte_t pte)
+static inline bool pte_swp_exclusive(pte_t pte)
 {
 	return pte.pte_low & _PAGE_SWP_EXCLUSIVE;
 }
@@ -551,7 +551,7 @@ static inline pte_t pte_swp_clear_exclusive(pte_t pte)
 	return pte;
 }
 #else
-static inline int pte_swp_exclusive(pte_t pte)
+static inline bool pte_swp_exclusive(pte_t pte)
 {
 	return pte_val(pte) & _PAGE_SWP_EXCLUSIVE;
 }
diff --git a/arch/nios2/include/asm/pgtable.h b/arch/nios2/include/asm/pgtable.h
index e98578e27e26..844dce55569f 100644
--- a/arch/nios2/include/asm/pgtable.h
+++ b/arch/nios2/include/asm/pgtable.h
@@ -259,7 +259,7 @@ static inline unsigned long pmd_page_vaddr(pmd_t pmd)
 #define __swp_entry_to_pte(swp)	((pte_t) { (swp).val })
 #define __pte_to_swp_entry(pte)	((swp_entry_t) { pte_val(pte) })
 
-static inline int pte_swp_exclusive(pte_t pte)
+static inline bool pte_swp_exclusive(pte_t pte)
 {
 	return pte_val(pte) & _PAGE_SWP_EXCLUSIVE;
 }
diff --git a/arch/openrisc/include/asm/pgtable.h b/arch/openrisc/include/asm/pgtable.h
index 71bfb8c8c482..5bd6463bd514 100644
--- a/arch/openrisc/include/asm/pgtable.h
+++ b/arch/openrisc/include/asm/pgtable.h
@@ -411,7 +411,7 @@ static inline void update_mmu_cache_range(struct vm_fault *vmf,
 #define __pte_to_swp_entry(pte)		((swp_entry_t) { pte_val(pte) })
 #define __swp_entry_to_pte(x)		((pte_t) { (x).val })
 
-static inline int pte_swp_exclusive(pte_t pte)
+static inline bool pte_swp_exclusive(pte_t pte)
 {
 	return pte_val(pte) & _PAGE_SWP_EXCLUSIVE;
 }
diff --git a/arch/parisc/include/asm/pgtable.h b/arch/parisc/include/asm/pgtable.h
index 80f5e2a28413..1a86a4370b29 100644
--- a/arch/parisc/include/asm/pgtable.h
+++ b/arch/parisc/include/asm/pgtable.h
@@ -425,7 +425,7 @@ static inline void set_ptes(struct mm_struct *mm, unsigned long addr,
 #define __pte_to_swp_entry(pte)		((swp_entry_t) { pte_val(pte) })
 #define __swp_entry_to_pte(x)		((pte_t) { (x).val })
 
-static inline int pte_swp_exclusive(pte_t pte)
+static inline bool pte_swp_exclusive(pte_t pte)
 {
 	return pte_val(pte) & _PAGE_SWP_EXCLUSIVE;
 }
diff --git a/arch/powerpc/include/asm/book3s/32/pgtable.h b/arch/powerpc/include/asm/book3s/32/pgtable.h
index 42c3af90d1f0..92d21c6faf1e 100644
--- a/arch/powerpc/include/asm/book3s/32/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/32/pgtable.h
@@ -365,7 +365,7 @@ static inline void __ptep_set_access_flags(struct vm_area_struct *vma,
 #define __pte_to_swp_entry(pte)		((swp_entry_t) { pte_val(pte) >> 3 })
 #define __swp_entry_to_pte(x)		((pte_t) { (x).val << 3 })
 
-static inline int pte_swp_exclusive(pte_t pte)
+static inline bool pte_swp_exclusive(pte_t pte)
 {
 	return pte_val(pte) & _PAGE_SWP_EXCLUSIVE;
 }
diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h
index 6ed93e290c2f..a2ddcbb3fcb9 100644
--- a/arch/powerpc/include/asm/book3s/64/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/64/pgtable.h
@@ -693,7 +693,7 @@ static inline pte_t pte_swp_mkexclusive(pte_t pte)
 	return __pte_raw(pte_raw(pte) | cpu_to_be64(_PAGE_SWP_EXCLUSIVE));
 }
 
-static inline int pte_swp_exclusive(pte_t pte)
+static inline bool pte_swp_exclusive(pte_t pte)
 {
 	return !!(pte_raw(pte) & cpu_to_be64(_PAGE_SWP_EXCLUSIVE));
 }
diff --git a/arch/powerpc/include/asm/nohash/pgtable.h b/arch/powerpc/include/asm/nohash/pgtable.h
index 8d1f0b7062eb..7d6b9e5b286e 100644
--- a/arch/powerpc/include/asm/nohash/pgtable.h
+++ b/arch/powerpc/include/asm/nohash/pgtable.h
@@ -286,7 +286,7 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 	return __pte((pte_val(pte) & _PAGE_CHG_MASK) | pgprot_val(newprot));
 }
 
-static inline int pte_swp_exclusive(pte_t pte)
+static inline bool pte_swp_exclusive(pte_t pte)
 {
 	return pte_val(pte) & _PAGE_SWP_EXCLUSIVE;
 }
diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h
index a11816bbf9e7..438ce7df24c3 100644
--- a/arch/riscv/include/asm/pgtable.h
+++ b/arch/riscv/include/asm/pgtable.h
@@ -1028,7 +1028,7 @@ static inline pud_t pud_modify(pud_t pud, pgprot_t newprot)
 #define __pte_to_swp_entry(pte)	((swp_entry_t) { pte_val(pte) })
 #define __swp_entry_to_pte(x)	((pte_t) { (x).val })
 
-static inline int pte_swp_exclusive(pte_t pte)
+static inline bool pte_swp_exclusive(pte_t pte)
 {
 	return pte_val(pte) & _PAGE_SWP_EXCLUSIVE;
 }
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index 1c661ac62ce8..6d8bc27a366e 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -915,7 +915,7 @@ static inline int pmd_protnone(pmd_t pmd)
 }
 #endif
 
-static inline int pte_swp_exclusive(pte_t pte)
+static inline bool pte_swp_exclusive(pte_t pte)
 {
 	return pte_val(pte) & _PAGE_SWP_EXCLUSIVE;
 }
diff --git a/arch/sh/include/asm/pgtable_32.h b/arch/sh/include/asm/pgtable_32.h
index 71b18741cc11..5f51af18997b 100644
--- a/arch/sh/include/asm/pgtable_32.h
+++ b/arch/sh/include/asm/pgtable_32.h
@@ -470,7 +470,7 @@ static inline unsigned long pmd_page_vaddr(pmd_t pmd)
 /* In both cases, we borrow bit 6 to store the exclusive marker in swap PTEs. */
 #define _PAGE_SWP_EXCLUSIVE	_PAGE_USER
 
-static inline int pte_swp_exclusive(pte_t pte)
+static inline bool pte_swp_exclusive(pte_t pte)
 {
 	return pte.pte_low & _PAGE_SWP_EXCLUSIVE;
 }
diff --git a/arch/sparc/include/asm/pgtable_32.h b/arch/sparc/include/asm/pgtable_32.h
index 1454ebe91539..7c199c003ffe 100644
--- a/arch/sparc/include/asm/pgtable_32.h
+++ b/arch/sparc/include/asm/pgtable_32.h
@@ -348,7 +348,7 @@ static inline swp_entry_t __swp_entry(unsigned long type, unsigned long offset)
 #define __pte_to_swp_entry(pte)		((swp_entry_t) { pte_val(pte) })
 #define __swp_entry_to_pte(x)		((pte_t) { (x).val })
 
-static inline int pte_swp_exclusive(pte_t pte)
+static inline bool pte_swp_exclusive(pte_t pte)
 {
 	return pte_val(pte) & SRMMU_SWP_EXCLUSIVE;
 }
diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h
index 4af03e3c161b..669cd02469a1 100644
--- a/arch/sparc/include/asm/pgtable_64.h
+++ b/arch/sparc/include/asm/pgtable_64.h
@@ -1023,7 +1023,7 @@ pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp);
 #define __pte_to_swp_entry(pte)		((swp_entry_t) { pte_val(pte) })
 #define __swp_entry_to_pte(x)		((pte_t) { (x).val })
 
-static inline int pte_swp_exclusive(pte_t pte)
+static inline bool pte_swp_exclusive(pte_t pte)
 {
 	return pte_val(pte) & _PAGE_SWP_EXCLUSIVE;
 }
diff --git a/arch/um/include/asm/pgtable.h b/arch/um/include/asm/pgtable.h
index ca2a519d53ab..24fdea6f88c3 100644
--- a/arch/um/include/asm/pgtable.h
+++ b/arch/um/include/asm/pgtable.h
@@ -314,7 +314,7 @@ extern pte_t *virt_to_pte(struct mm_struct *mm, unsigned long addr);
 	((swp_entry_t) { pte_val(pte_mkuptodate(pte)) })
 #define __swp_entry_to_pte(x)		((pte_t) { (x).val })
 
-static inline int pte_swp_exclusive(pte_t pte)
+static inline bool pte_swp_exclusive(pte_t pte)
 {
 	return pte_get_bits(pte, _PAGE_SWP_EXCLUSIVE);
 }
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 774430c3abff..97954c936c54 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -1561,7 +1561,7 @@ static inline pte_t pte_swp_mkexclusive(pte_t pte)
 	return pte_set_flags(pte, _PAGE_SWP_EXCLUSIVE);
 }
 
-static inline int pte_swp_exclusive(pte_t pte)
+static inline bool pte_swp_exclusive(pte_t pte)
 {
 	return pte_flags(pte) & _PAGE_SWP_EXCLUSIVE;
 }
diff --git a/arch/xtensa/include/asm/pgtable.h b/arch/xtensa/include/asm/pgtable.h
index cb1725c40e36..d62aa1c316fc 100644
--- a/arch/xtensa/include/asm/pgtable.h
+++ b/arch/xtensa/include/asm/pgtable.h
@@ -349,7 +349,7 @@ ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
 #define __pte_to_swp_entry(pte)	((swp_entry_t) { pte_val(pte) })
 #define __swp_entry_to_pte(x)	((pte_t) { (x).val })
 
-static inline int pte_swp_exclusive(pte_t pte)
+static inline bool pte_swp_exclusive(pte_t pte)
 {
 	return pte_val(pte) & _PAGE_SWP_EXCLUSIVE;
 }

From ed2a6ff0234e21cd5e56b63d8bff80120bbe5f15 Mon Sep 17 00:00:00 2001
From: "Rob Herring (Arm)" <robh@kernel.org>
Date: Thu, 1 May 2025 20:14:26 -0500
Subject: [PATCH 0239/1334] dt-bindings: serial: Convert altr,juart-1.0 to DT
 schema

Convert the Altera JTAG UART binding to DT schema. The "ALTR,juart-1.0"
compatible has long been deprecated, so drop it.

Signed-off-by: Rob Herring (Arm) <robh@kernel.org>
---
 .../bindings/serial/altera_jtaguart.txt       |  5 -----
 .../bindings/serial/altr,juart-1.0.yaml       | 19 +++++++++++++++++++
 2 files changed, 19 insertions(+), 5 deletions(-)
 delete mode 100644 Documentation/devicetree/bindings/serial/altera_jtaguart.txt
 create mode 100644 Documentation/devicetree/bindings/serial/altr,juart-1.0.yaml

diff --git a/Documentation/devicetree/bindings/serial/altera_jtaguart.txt b/Documentation/devicetree/bindings/serial/altera_jtaguart.txt
deleted file mode 100644
index 55a901051e8f..000000000000
--- a/Documentation/devicetree/bindings/serial/altera_jtaguart.txt
+++ /dev/null
@@ -1,5 +0,0 @@
-Altera JTAG UART
-
-Required properties:
-- compatible : should be "ALTR,juart-1.0" <DEPRECATED>
-- compatible : should be "altr,juart-1.0"
diff --git a/Documentation/devicetree/bindings/serial/altr,juart-1.0.yaml b/Documentation/devicetree/bindings/serial/altr,juart-1.0.yaml
new file mode 100644
index 000000000000..02e20fa591da
--- /dev/null
+++ b/Documentation/devicetree/bindings/serial/altr,juart-1.0.yaml
@@ -0,0 +1,19 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/serial/altr,juart-1.0.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Altera JTAG UART
+
+maintainers:
+  - Dinh Nguyen <dinguyen@kernel.org>
+
+properties:
+  compatible:
+    const: altr,juart-1.0
+
+required:
+  - compatible
+
+additionalProperties: false

From f75794b6077ec729f57de9a1ad24f14d288a68bb Mon Sep 17 00:00:00 2001
From: "Rob Herring (Arm)" <robh@kernel.org>
Date: Thu, 1 May 2025 20:15:40 -0500
Subject: [PATCH 0240/1334] dt-bindings: serial: Convert altr,uart-1.0 to DT
 schema

Convert the Altera JTAG UART binding to DT schema. The "ALTR,uart-1.0"
compatible has long been deprecated, so drop it.

Signed-off-by: Rob Herring (Arm) <robh@kernel.org>
---
 .../bindings/serial/altera_uart.txt           |  8 ------
 .../bindings/serial/altr,uart-1.0.yaml        | 25 +++++++++++++++++++
 2 files changed, 25 insertions(+), 8 deletions(-)
 delete mode 100644 Documentation/devicetree/bindings/serial/altera_uart.txt
 create mode 100644 Documentation/devicetree/bindings/serial/altr,uart-1.0.yaml

diff --git a/Documentation/devicetree/bindings/serial/altera_uart.txt b/Documentation/devicetree/bindings/serial/altera_uart.txt
deleted file mode 100644
index 81bf7ffb1a81..000000000000
--- a/Documentation/devicetree/bindings/serial/altera_uart.txt
+++ /dev/null
@@ -1,8 +0,0 @@
-Altera UART
-
-Required properties:
-- compatible : should be "ALTR,uart-1.0" <DEPRECATED>
-- compatible : should be "altr,uart-1.0"
-
-Optional properties:
-- clock-frequency : frequency of the clock input to the UART
diff --git a/Documentation/devicetree/bindings/serial/altr,uart-1.0.yaml b/Documentation/devicetree/bindings/serial/altr,uart-1.0.yaml
new file mode 100644
index 000000000000..72d4972e1e22
--- /dev/null
+++ b/Documentation/devicetree/bindings/serial/altr,uart-1.0.yaml
@@ -0,0 +1,25 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/serial/altr,uart-1.0.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Altera UART
+
+maintainers:
+  - Dinh Nguyen <dinguyen@kernel.org>
+
+allOf:
+  - $ref: /schemas/serial/serial.yaml#
+
+properties:
+  compatible:
+    const: altr,uart-1.0
+
+  clock-frequency:
+    description: Frequency of the clock input to the UART.
+
+required:
+  - compatible
+
+unevaluatedProperties: false

From ba9db6f907ac02215e30128770f85fbd7db2fcf9 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Mon, 9 Jun 2025 17:12:44 -0700
Subject: [PATCH 0241/1334] net: clear the dst when changing skb protocol
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

A not-so-careful NAT46 BPF program can crash the kernel
if it indiscriminately flips ingress packets from v4 to v6:

  BUG: kernel NULL pointer dereference, address: 0000000000000000
    ip6_rcv_core (net/ipv6/ip6_input.c:190:20)
    ipv6_rcv (net/ipv6/ip6_input.c:306:8)
    process_backlog (net/core/dev.c:6186:4)
    napi_poll (net/core/dev.c:6906:9)
    net_rx_action (net/core/dev.c:7028:13)
    do_softirq (kernel/softirq.c:462:3)
    netif_rx (net/core/dev.c:5326:3)
    dev_loopback_xmit (net/core/dev.c:4015:2)
    ip_mc_finish_output (net/ipv4/ip_output.c:363:8)
    NF_HOOK (./include/linux/netfilter.h:314:9)
    ip_mc_output (net/ipv4/ip_output.c:400:5)
    dst_output (./include/net/dst.h:459:9)
    ip_local_out (net/ipv4/ip_output.c:130:9)
    ip_send_skb (net/ipv4/ip_output.c:1496:8)
    udp_send_skb (net/ipv4/udp.c:1040:8)
    udp_sendmsg (net/ipv4/udp.c:1328:10)

The output interface has a 4->6 program attached at ingress.
We try to loop the multicast skb back to the sending socket.
Ingress BPF runs as part of netif_rx(), pushes a valid v6 hdr
and changes skb->protocol to v6. We enter ip6_rcv_core which
tries to use skb_dst(). But the dst is still an IPv4 one left
after IPv4 mcast output.

Clear the dst in all BPF helpers which change the protocol.
Try to preserve metadata dsts, those may carry non-routing
metadata.

Cc: stable@vger.kernel.org
Reviewed-by: Maciej Żenczykowski <maze@google.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Fixes: d219df60a70e ("bpf: Add ipip6 and ip6ip decap support for bpf_skb_adjust_room()")
Fixes: 1b00e0dfe7d0 ("bpf: update skb->protocol in bpf_skb_net_grow")
Fixes: 6578171a7ff0 ("bpf: add bpf_skb_change_proto helper")
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://patch.msgid.link/20250610001245.1981782-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/filter.c | 19 +++++++++++++------
 1 file changed, 13 insertions(+), 6 deletions(-)

diff --git a/net/core/filter.c b/net/core/filter.c
index 327ca73f9cd7..7a72f766aacf 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -3233,6 +3233,13 @@ static const struct bpf_func_proto bpf_skb_vlan_pop_proto = {
 	.arg1_type      = ARG_PTR_TO_CTX,
 };
 
+static void bpf_skb_change_protocol(struct sk_buff *skb, u16 proto)
+{
+	skb->protocol = htons(proto);
+	if (skb_valid_dst(skb))
+		skb_dst_drop(skb);
+}
+
 static int bpf_skb_generic_push(struct sk_buff *skb, u32 off, u32 len)
 {
 	/* Caller already did skb_cow() with len as headroom,
@@ -3329,7 +3336,7 @@ static int bpf_skb_proto_4_to_6(struct sk_buff *skb)
 		}
 	}
 
-	skb->protocol = htons(ETH_P_IPV6);
+	bpf_skb_change_protocol(skb, ETH_P_IPV6);
 	skb_clear_hash(skb);
 
 	return 0;
@@ -3359,7 +3366,7 @@ static int bpf_skb_proto_6_to_4(struct sk_buff *skb)
 		}
 	}
 
-	skb->protocol = htons(ETH_P_IP);
+	bpf_skb_change_protocol(skb, ETH_P_IP);
 	skb_clear_hash(skb);
 
 	return 0;
@@ -3550,10 +3557,10 @@ static int bpf_skb_net_grow(struct sk_buff *skb, u32 off, u32 len_diff,
 		/* Match skb->protocol to new outer l3 protocol */
 		if (skb->protocol == htons(ETH_P_IP) &&
 		    flags & BPF_F_ADJ_ROOM_ENCAP_L3_IPV6)
-			skb->protocol = htons(ETH_P_IPV6);
+			bpf_skb_change_protocol(skb, ETH_P_IPV6);
 		else if (skb->protocol == htons(ETH_P_IPV6) &&
 			 flags & BPF_F_ADJ_ROOM_ENCAP_L3_IPV4)
-			skb->protocol = htons(ETH_P_IP);
+			bpf_skb_change_protocol(skb, ETH_P_IP);
 	}
 
 	if (skb_is_gso(skb)) {
@@ -3606,10 +3613,10 @@ static int bpf_skb_net_shrink(struct sk_buff *skb, u32 off, u32 len_diff,
 	/* Match skb->protocol to new outer l3 protocol */
 	if (skb->protocol == htons(ETH_P_IP) &&
 	    flags & BPF_F_ADJ_ROOM_DECAP_L3_IPV6)
-		skb->protocol = htons(ETH_P_IPV6);
+		bpf_skb_change_protocol(skb, ETH_P_IPV6);
 	else if (skb->protocol == htons(ETH_P_IPV6) &&
 		 flags & BPF_F_ADJ_ROOM_DECAP_L3_IPV4)
-		skb->protocol = htons(ETH_P_IP);
+		bpf_skb_change_protocol(skb, ETH_P_IP);
 
 	if (skb_is_gso(skb)) {
 		struct skb_shared_info *shinfo = skb_shinfo(skb);

From 567766954b2d5d6c29f568ad4382d6351ea48079 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Mon, 9 Jun 2025 17:12:45 -0700
Subject: [PATCH 0242/1334] selftests: net: add test case for NAT46 looping
 back dst

Simple test for crash involving multicast loopback and stale dst.
Reuse exising NAT46 program.

Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://patch.msgid.link/20250610001245.1981782-2-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/Makefile   |  1 +
 tools/testing/selftests/net/nat6to4.sh | 15 +++++++++++++++
 2 files changed, 16 insertions(+)
 create mode 100755 tools/testing/selftests/net/nat6to4.sh

diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index ea84b88bcb30..ab996bd22a5f 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -27,6 +27,7 @@ TEST_PROGS += amt.sh
 TEST_PROGS += unicast_extensions.sh
 TEST_PROGS += udpgro_fwd.sh
 TEST_PROGS += udpgro_frglist.sh
+TEST_PROGS += nat6to4.sh
 TEST_PROGS += veth.sh
 TEST_PROGS += ioam6.sh
 TEST_PROGS += gro.sh
diff --git a/tools/testing/selftests/net/nat6to4.sh b/tools/testing/selftests/net/nat6to4.sh
new file mode 100755
index 000000000000..0ee859b622a4
--- /dev/null
+++ b/tools/testing/selftests/net/nat6to4.sh
@@ -0,0 +1,15 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+NS="ns-peer-$(mktemp -u XXXXXX)"
+
+ip netns add "${NS}"
+ip -netns "${NS}" link set lo up
+ip -netns "${NS}" route add default via 127.0.0.2 dev lo
+
+tc -n "${NS}" qdisc add dev lo ingress
+tc -n "${NS}" filter add dev lo ingress prio 4 protocol ip \
+   bpf object-file nat6to4.bpf.o section schedcls/egress4/snat4 direct-action
+
+ip netns exec "${NS}" \
+   bash -c 'echo 012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789abc | socat - UDP4-DATAGRAM:224.1.0.1:6666,ip-multicast-loop=1'

From 27cea0e419d2f9dc6f51bbce5a44c70bc3774b9a Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@google.com>
Date: Tue, 10 Jun 2025 23:56:58 +0000
Subject: [PATCH 0243/1334] MAINTAINERS: Update Kuniyuki Iwashima's email
 address.

I left Amazon and joined Google, so let's map the email
addresses accordingly.

Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Link: https://patch.msgid.link/20250610235734.88540-1-kuniyu@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .mailmap    | 3 +++
 MAINTAINERS | 6 +++---
 2 files changed, 6 insertions(+), 3 deletions(-)

diff --git a/.mailmap b/.mailmap
index 074082ce9299..7890b69a9b6e 100644
--- a/.mailmap
+++ b/.mailmap
@@ -424,6 +424,9 @@ Krzysztof Wilczyński <kwilczynski@kernel.org> <krzysztof.wilczynski@linux.com>
 Krzysztof Wilczyński <kwilczynski@kernel.org> <kw@linux.com>
 Kshitiz Godara <quic_kgodara@quicinc.com> <kgodara@codeaurora.org>
 Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
+Kuniyuki Iwashima <kuniyu@google.com> <kuniyu@amazon.com>
+Kuniyuki Iwashima <kuniyu@google.com> <kuniyu@amazon.co.jp>
+Kuniyuki Iwashima <kuniyu@google.com> <kuni1840@gmail.com>
 Kuogee Hsieh <quic_khsieh@quicinc.com> <khsieh@codeaurora.org>
 Lee Jones <lee@kernel.org> <joneslee@google.com>
 Lee Jones <lee@kernel.org> <lee.jones@canonical.com>
diff --git a/MAINTAINERS b/MAINTAINERS
index f2668b81115c..bd09337f178d 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -17420,7 +17420,7 @@ F:	tools/testing/selftests/net/srv6*
 NETWORKING [TCP]
 M:	Eric Dumazet <edumazet@google.com>
 M:	Neal Cardwell <ncardwell@google.com>
-R:	Kuniyuki Iwashima <kuniyu@amazon.com>
+R:	Kuniyuki Iwashima <kuniyu@google.com>
 L:	netdev@vger.kernel.org
 S:	Maintained
 F:	Documentation/networking/net_cachelines/tcp_sock.rst
@@ -17450,7 +17450,7 @@ F:	net/tls/*
 
 NETWORKING [SOCKETS]
 M:	Eric Dumazet <edumazet@google.com>
-M:	Kuniyuki Iwashima <kuniyu@amazon.com>
+M:	Kuniyuki Iwashima <kuniyu@google.com>
 M:	Paolo Abeni <pabeni@redhat.com>
 M:	Willem de Bruijn <willemb@google.com>
 S:	Maintained
@@ -17465,7 +17465,7 @@ F:	net/core/scm.c
 F:	net/socket.c
 
 NETWORKING [UNIX SOCKETS]
-M:	Kuniyuki Iwashima <kuniyu@amazon.com>
+M:	Kuniyuki Iwashima <kuniyu@google.com>
 S:	Maintained
 F:	include/net/af_unix.h
 F:	include/net/netns/unix.h

From 903cc7096db22f889d48e2cee8840709ce04fdac Mon Sep 17 00:00:00 2001
From: Akhil R <akhilrajeev@nvidia.com>
Date: Tue, 3 Jun 2025 21:00:20 +0530
Subject: [PATCH 0244/1334] dt-bindings: i2c: nvidia,tegra20-i2c: Specify the
 required properties
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Specify the properties which are essential and which are not for the
Tegra I2C driver to function correctly. This was not added correctly when
the TXT binding was converted to yaml. All the existing DT nodes have
these properties already and hence this does not break the ABI.

dmas and dma-names which were specified as a must in the TXT binding
is now made optional since the driver can work in PIO mode if dmas are
missing.

Fixes: f10a9b722f80 ("dt-bindings: i2c: tegra: Convert to json-schema”)
Signed-off-by: Akhil R <akhilrajeev@nvidia.com>
Cc: <stable@vger.kernel.org> # v5.17+
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: Andi Shyti <andi@smida.it>
Link: https://lore.kernel.org/r/20250603153022.39434-1-akhilrajeev@nvidia.com
---
 .../bindings/i2c/nvidia,tegra20-i2c.yaml      | 24 ++++++++++++++++++-
 1 file changed, 23 insertions(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/i2c/nvidia,tegra20-i2c.yaml b/Documentation/devicetree/bindings/i2c/nvidia,tegra20-i2c.yaml
index b57ae6963e62..6b6f6762d122 100644
--- a/Documentation/devicetree/bindings/i2c/nvidia,tegra20-i2c.yaml
+++ b/Documentation/devicetree/bindings/i2c/nvidia,tegra20-i2c.yaml
@@ -97,7 +97,10 @@ properties:
 
   resets:
     items:
-      - description: module reset
+      - description:
+          Module reset. This property is optional for controllers in Tegra194,
+          Tegra234 etc where an internal software reset is available as an
+          alternative.
 
   reset-names:
     items:
@@ -116,6 +119,13 @@ properties:
       - const: rx
       - const: tx
 
+required:
+  - compatible
+  - reg
+  - interrupts
+  - clocks
+  - clock-names
+
 allOf:
   - $ref: /schemas/i2c/i2c-controller.yaml
   - if:
@@ -169,6 +179,18 @@ allOf:
       properties:
         power-domains: false
 
+  - if:
+      not:
+        properties:
+          compatible:
+            contains:
+              enum:
+                - nvidia,tegra194-i2c
+    then:
+      required:
+        - resets
+        - reset-names
+
 unevaluatedProperties: false
 
 examples:

From ebf2e500e06f707654572bc7d8bc569a8caa51aa Mon Sep 17 00:00:00 2001
From: Viresh Kumar <viresh.kumar@linaro.org>
Date: Mon, 9 Jun 2025 12:38:43 +0530
Subject: [PATCH 0245/1334] rust: cpu: Introduce CpuId abstraction

This adds abstraction for representing a CPU identifier.

Suggested-by: Boqun Feng <boqun.feng@gmail.com>
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Reviewed-by: Boqun Feng <boqun.feng@gmail.com>
---
 rust/kernel/cpu.rs | 110 +++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 110 insertions(+)

diff --git a/rust/kernel/cpu.rs b/rust/kernel/cpu.rs
index 10c5c3b25873..6a3aecb12468 100644
--- a/rust/kernel/cpu.rs
+++ b/rust/kernel/cpu.rs
@@ -6,6 +6,116 @@
 
 use crate::{bindings, device::Device, error::Result, prelude::ENODEV};
 
+/// Returns the maximum number of possible CPUs in the current system configuration.
+#[inline]
+pub fn nr_cpu_ids() -> u32 {
+    #[cfg(any(NR_CPUS_1, CONFIG_FORCE_NR_CPUS))]
+    {
+        bindings::NR_CPUS
+    }
+
+    #[cfg(not(any(NR_CPUS_1, CONFIG_FORCE_NR_CPUS)))]
+    // SAFETY: `nr_cpu_ids` is a valid global provided by the kernel.
+    unsafe {
+        bindings::nr_cpu_ids
+    }
+}
+
+/// The CPU ID.
+///
+/// Represents a CPU identifier as a wrapper around an [`u32`].
+///
+/// # Invariants
+///
+/// The CPU ID lies within the range `[0, nr_cpu_ids())`.
+///
+/// # Examples
+///
+/// ```
+/// use kernel::cpu::CpuId;
+///
+/// let cpu = 0;
+///
+/// // SAFETY: 0 is always a valid CPU number.
+/// let id = unsafe { CpuId::from_u32_unchecked(cpu) };
+///
+/// assert_eq!(id.as_u32(), cpu);
+/// assert!(CpuId::from_i32(0).is_some());
+/// assert!(CpuId::from_i32(-1).is_none());
+/// ```
+#[derive(Copy, Clone, PartialEq, Eq, Debug)]
+pub struct CpuId(u32);
+
+impl CpuId {
+    /// Creates a new [`CpuId`] from the given `id` without checking bounds.
+    ///
+    /// # Safety
+    ///
+    /// The caller must ensure that `id` is a valid CPU ID (i.e., `0 <= id < nr_cpu_ids()`).
+    #[inline]
+    pub unsafe fn from_i32_unchecked(id: i32) -> Self {
+        debug_assert!(id >= 0);
+        debug_assert!((id as u32) < nr_cpu_ids());
+
+        // INVARIANT: The function safety guarantees `id` is a valid CPU id.
+        Self(id as u32)
+    }
+
+    /// Creates a new [`CpuId`] from the given `id`, checking that it is valid.
+    pub fn from_i32(id: i32) -> Option<Self> {
+        if id < 0 || id as u32 >= nr_cpu_ids() {
+            None
+        } else {
+            // INVARIANT: `id` has just been checked as a valid CPU ID.
+            Some(Self(id as u32))
+        }
+    }
+
+    /// Creates a new [`CpuId`] from the given `id` without checking bounds.
+    ///
+    /// # Safety
+    ///
+    /// The caller must ensure that `id` is a valid CPU ID (i.e., `0 <= id < nr_cpu_ids()`).
+    #[inline]
+    pub unsafe fn from_u32_unchecked(id: u32) -> Self {
+        debug_assert!(id < nr_cpu_ids());
+
+        // Ensure the `id` fits in an [`i32`] as it's also representable that way.
+        debug_assert!(id <= i32::MAX as u32);
+
+        // INVARIANT: The function safety guarantees `id` is a valid CPU id.
+        Self(id)
+    }
+
+    /// Creates a new [`CpuId`] from the given `id`, checking that it is valid.
+    pub fn from_u32(id: u32) -> Option<Self> {
+        if id >= nr_cpu_ids() {
+            None
+        } else {
+            // INVARIANT: `id` has just been checked as a valid CPU ID.
+            Some(Self(id))
+        }
+    }
+
+    /// Returns CPU number.
+    #[inline]
+    pub fn as_u32(&self) -> u32 {
+        self.0
+    }
+}
+
+impl From<CpuId> for u32 {
+    fn from(id: CpuId) -> Self {
+        id.as_u32()
+    }
+}
+
+impl From<CpuId> for i32 {
+    fn from(id: CpuId) -> Self {
+        id.as_u32() as i32
+    }
+}
+
 /// Creates a new instance of CPU's device.
 ///
 /// # Safety

From 47fe65b105f29ef22f463c17ab8a4c0eeb741045 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Sun, 1 Jun 2025 20:22:17 -0400
Subject: [PATCH 0246/1334] bcachefs: Add missing restart handling to
 check_topology()

The next patch will add logging of the specific error being corrected in
repair paths to the journal; this means __bch2_fsck_err() can return
transaction restarts in places that previously weren't expecting them.

check_topology() is old code that doesn't use btree iterators for btree
node locking - it'll have to be rewritten in the future to work online.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/btree_gc.c | 95 ++++++++++++++++++++++++++----------------
 1 file changed, 60 insertions(+), 35 deletions(-)

diff --git a/fs/bcachefs/btree_gc.c b/fs/bcachefs/btree_gc.c
index 9ddcbe1bda78..e92cf3928c63 100644
--- a/fs/bcachefs/btree_gc.c
+++ b/fs/bcachefs/btree_gc.c
@@ -397,7 +397,11 @@ again:
 			continue;
 		}
 
-		ret = btree_check_node_boundaries(trans, b, prev, cur, pulled_from_scan);
+		ret = lockrestart_do(trans,
+			btree_check_node_boundaries(trans, b, prev, cur, pulled_from_scan));
+		if (ret < 0)
+			goto err;
+
 		if (ret == DID_FILL_FROM_SCAN) {
 			new_pass = true;
 			ret = 0;
@@ -438,7 +442,8 @@ again:
 
 	if (!ret && !IS_ERR_OR_NULL(prev)) {
 		BUG_ON(cur);
-		ret = btree_repair_node_end(trans, b, prev, pulled_from_scan);
+		ret = lockrestart_do(trans,
+			btree_repair_node_end(trans, b, prev, pulled_from_scan));
 		if (ret == DID_FILL_FROM_SCAN) {
 			new_pass = true;
 			ret = 0;
@@ -519,6 +524,46 @@ fsck_err:
 	bch2_bkey_buf_exit(&prev_k, c);
 	bch2_bkey_buf_exit(&cur_k, c);
 	printbuf_exit(&buf);
+	bch_err_fn(c, ret);
+	return ret;
+}
+
+static int bch2_check_root(struct btree_trans *trans, enum btree_id i,
+			   bool *reconstructed_root)
+{
+	struct bch_fs *c = trans->c;
+	struct btree_root *r = bch2_btree_id_root(c, i);
+	struct printbuf buf = PRINTBUF;
+	int ret = 0;
+
+	bch2_btree_id_to_text(&buf, i);
+
+	if (r->error) {
+		bch_info(c, "btree root %s unreadable, must recover from scan", buf.buf);
+
+		r->alive = false;
+		r->error = 0;
+
+		if (!bch2_btree_has_scanned_nodes(c, i)) {
+			__fsck_err(trans,
+				   FSCK_CAN_FIX|(!btree_id_important(i) ? FSCK_AUTOFIX : 0),
+				   btree_root_unreadable_and_scan_found_nothing,
+				   "no nodes found for btree %s, continue?", buf.buf);
+			bch2_btree_root_alloc_fake_trans(trans, i, 0);
+		} else {
+			bch2_btree_root_alloc_fake_trans(trans, i, 1);
+			bch2_shoot_down_journal_keys(c, i, 1, BTREE_MAX_DEPTH, POS_MIN, SPOS_MAX);
+			ret = bch2_get_scanned_nodes(c, i, 0, POS_MIN, SPOS_MAX);
+			if (ret)
+				goto err;
+		}
+
+		*reconstructed_root = true;
+	}
+err:
+fsck_err:
+	printbuf_exit(&buf);
+	bch_err_fn(c, ret);
 	return ret;
 }
 
@@ -526,42 +571,18 @@ int bch2_check_topology(struct bch_fs *c)
 {
 	struct btree_trans *trans = bch2_trans_get(c);
 	struct bpos pulled_from_scan = POS_MIN;
-	struct printbuf buf = PRINTBUF;
 	int ret = 0;
 
 	bch2_trans_srcu_unlock(trans);
 
 	for (unsigned i = 0; i < btree_id_nr_alive(c) && !ret; i++) {
-		struct btree_root *r = bch2_btree_id_root(c, i);
 		bool reconstructed_root = false;
+recover:
+		ret = lockrestart_do(trans, bch2_check_root(trans, i, &reconstructed_root));
+		if (ret)
+			break;
 
-		printbuf_reset(&buf);
-		bch2_btree_id_to_text(&buf, i);
-
-		if (r->error) {
-reconstruct_root:
-			bch_info(c, "btree root %s unreadable, must recover from scan", buf.buf);
-
-			r->alive = false;
-			r->error = 0;
-
-			if (!bch2_btree_has_scanned_nodes(c, i)) {
-				__fsck_err(trans,
-					   FSCK_CAN_FIX|(!btree_id_important(i) ? FSCK_AUTOFIX : 0),
-					   btree_root_unreadable_and_scan_found_nothing,
-					   "no nodes found for btree %s, continue?", buf.buf);
-				bch2_btree_root_alloc_fake_trans(trans, i, 0);
-			} else {
-				bch2_btree_root_alloc_fake_trans(trans, i, 1);
-				bch2_shoot_down_journal_keys(c, i, 1, BTREE_MAX_DEPTH, POS_MIN, SPOS_MAX);
-				ret = bch2_get_scanned_nodes(c, i, 0, POS_MIN, SPOS_MAX);
-				if (ret)
-					break;
-			}
-
-			reconstructed_root = true;
-		}
-
+		struct btree_root *r = bch2_btree_id_root(c, i);
 		struct btree *b = r->b;
 
 		btree_node_lock_nopath_nofail(trans, &b->c, SIX_LOCK_read);
@@ -575,17 +596,21 @@ reconstruct_root:
 
 			r->b = NULL;
 
-			if (!reconstructed_root)
-				goto reconstruct_root;
+			if (!reconstructed_root) {
+				r->error = -EIO;
+				goto recover;
+			}
 
+			struct printbuf buf = PRINTBUF;
+			bch2_btree_id_to_text(&buf, i);
 			bch_err(c, "empty btree root %s", buf.buf);
+			printbuf_exit(&buf);
 			bch2_btree_root_alloc_fake_trans(trans, i, 0);
 			r->alive = false;
 			ret = 0;
 		}
 	}
-fsck_err:
-	printbuf_exit(&buf);
+
 	bch2_trans_put(trans);
 	return ret;
 }

From b43f724927686387589b98eb762e1a4109bb1bac Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Sun, 1 Jun 2025 13:07:31 -0400
Subject: [PATCH 0247/1334] bcachefs: Log fsck errors in the journal

Log the specific error being corrected in the journal when we're
repairing, this helps greatly with 'bcachefs list_journal' analysis.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/error.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/fs/bcachefs/error.c b/fs/bcachefs/error.c
index 63951e293c47..ff49cebfd0e8 100644
--- a/fs/bcachefs/error.c
+++ b/fs/bcachefs/error.c
@@ -620,6 +620,9 @@ print:
 
 	if (s)
 		s->ret = ret;
+
+	if (trans)
+		ret = bch2_trans_log_str(trans, bch2_sb_error_strs[err]) ?: ret;
 err_unlock:
 	mutex_unlock(&c->fsck_error_msgs_lock);
 err:

From c7e351be7aa4e176223f0128e4d1b959ffad9598 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Thu, 5 Jun 2025 19:00:11 -0400
Subject: [PATCH 0248/1334] bcachefs: Add range being updated to
 btree_update_to_text()

We had a deadlock during recovery where interior btree updates became
wedged and all open_buckets were consumed; start adding more
introspection.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/btree_update_interior.c | 26 ++++++++++++++++++++++++--
 fs/bcachefs/btree_update_interior.h |  7 +++++++
 2 files changed, 31 insertions(+), 2 deletions(-)

diff --git a/fs/bcachefs/btree_update_interior.c b/fs/bcachefs/btree_update_interior.c
index d2ecb782919b..340812b28d08 100644
--- a/fs/bcachefs/btree_update_interior.c
+++ b/fs/bcachefs/btree_update_interior.c
@@ -1232,6 +1232,15 @@ bch2_btree_update_start(struct btree_trans *trans, struct btree_path *path,
 	list_add_tail(&as->list, &c->btree_interior_update_list);
 	mutex_unlock(&c->btree_interior_update_lock);
 
+	struct btree *b = btree_path_node(path, path->level);
+	as->node_start	= b->data->min_key;
+	as->node_end	= b->data->max_key;
+	as->node_needed_rewrite = btree_node_need_rewrite(b);
+	as->node_written = b->written;
+	as->node_sectors = btree_buf_bytes(b) >> 9;
+	as->node_remaining = __bch2_btree_u64s_remaining(b,
+				btree_bkey_last(b, bset_tree_last(b)));
+
 	/*
 	 * We don't want to allocate if we're in an error state, that can cause
 	 * deadlock on emergency shutdown due to open buckets getting stuck in
@@ -2108,6 +2117,9 @@ int __bch2_foreground_maybe_merge(struct btree_trans *trans,
 	if (ret)
 		goto err;
 
+	as->node_start	= prev->data->min_key;
+	as->node_end	= next->data->max_key;
+
 	trace_and_count(c, btree_node_merge, trans, b);
 
 	n = bch2_btree_node_alloc(as, trans, b->c.level);
@@ -2681,9 +2693,19 @@ static void bch2_btree_update_to_text(struct printbuf *out, struct btree_update
 
 	prt_str(out, " ");
 	bch2_btree_id_to_text(out, as->btree_id);
-	prt_printf(out, " l=%u-%u mode=%s nodes_written=%u cl.remaining=%u journal_seq=%llu\n",
+	prt_printf(out, " l=%u-%u ",
 		   as->update_level_start,
-		   as->update_level_end,
+		   as->update_level_end);
+	bch2_bpos_to_text(out, as->node_start);
+	prt_char(out, ' ');
+	bch2_bpos_to_text(out, as->node_end);
+	prt_printf(out, "\nwritten %u/%u u64s_remaining %u need_rewrite %u",
+		   as->node_written,
+		   as->node_sectors,
+		   as->node_remaining,
+		   as->node_needed_rewrite);
+
+	prt_printf(out, "\nmode=%s nodes_written=%u cl.remaining=%u journal_seq=%llu\n",
 		   bch2_btree_update_modes[as->mode],
 		   as->nodes_written,
 		   closure_nr_remaining(&as->cl),
diff --git a/fs/bcachefs/btree_update_interior.h b/fs/bcachefs/btree_update_interior.h
index 7fe793788a79..85682a13de4d 100644
--- a/fs/bcachefs/btree_update_interior.h
+++ b/fs/bcachefs/btree_update_interior.h
@@ -57,6 +57,13 @@ struct btree_update {
 	unsigned			took_gc_lock:1;
 
 	enum btree_id			btree_id;
+	struct bpos			node_start;
+	struct bpos			node_end;
+	bool				node_needed_rewrite;
+	u16				node_written;
+	u16				node_sectors;
+	u16				node_remaining;
+
 	unsigned			update_level_start;
 	unsigned			update_level_end;
 

From b76cce12700b8bb8d59b9ff444504b94db96dd4b Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Thu, 5 Jun 2025 20:53:01 -0400
Subject: [PATCH 0249/1334] bcachefs: Add more flags to btree nodes for rewrite
 reason

It seems excessive forced btree node rewrites can cause interior btree
updates to become wedged during recovery, before we're using the write
buffer for backpointer updates.

Add more flags so we can determine where these are coming from.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/btree_io.c              | 10 ++++++++--
 fs/bcachefs/btree_types.h           | 29 +++++++++++++++++++++++++++++
 fs/bcachefs/btree_update_interior.c | 13 ++++++++++---
 fs/bcachefs/btree_update_interior.h |  2 +-
 4 files changed, 48 insertions(+), 6 deletions(-)

diff --git a/fs/bcachefs/btree_io.c b/fs/bcachefs/btree_io.c
index 57eff3012a7b..6787d5b91eab 100644
--- a/fs/bcachefs/btree_io.c
+++ b/fs/bcachefs/btree_io.c
@@ -1045,6 +1045,7 @@ got_good_key:
 		le16_add_cpu(&i->u64s, -next_good_key);
 		memmove_u64s_down(k, (u64 *) k + next_good_key, (u64 *) vstruct_end(i) - (u64 *) k);
 		set_btree_node_need_rewrite(b);
+		set_btree_node_need_rewrite_error(b);
 	}
 fsck_err:
 	printbuf_exit(&buf);
@@ -1305,6 +1306,7 @@ int bch2_btree_node_read_done(struct bch_fs *c, struct bch_dev *ca,
 					  (u64 *) vstruct_end(i) - (u64 *) k);
 			set_btree_bset_end(b, b->set);
 			set_btree_node_need_rewrite(b);
+			set_btree_node_need_rewrite_error(b);
 			continue;
 		}
 		if (ret)
@@ -1329,12 +1331,16 @@ int bch2_btree_node_read_done(struct bch_fs *c, struct bch_dev *ca,
 		bkey_for_each_ptr(bch2_bkey_ptrs(bkey_i_to_s(&b->key)), ptr) {
 			struct bch_dev *ca2 = bch2_dev_rcu(c, ptr->dev);
 
-			if (!ca2 || ca2->mi.state != BCH_MEMBER_STATE_rw)
+			if (!ca2 || ca2->mi.state != BCH_MEMBER_STATE_rw) {
 				set_btree_node_need_rewrite(b);
+				set_btree_node_need_rewrite_degraded(b);
+			}
 		}
 
-	if (!ptr_written)
+	if (!ptr_written) {
 		set_btree_node_need_rewrite(b);
+		set_btree_node_need_rewrite_ptr_written_zero(b);
+	}
 fsck_err:
 	mempool_free(iter, &c->fill_iter);
 	printbuf_exit(&buf);
diff --git a/fs/bcachefs/btree_types.h b/fs/bcachefs/btree_types.h
index c61c4171ae50..3aa4a602bd02 100644
--- a/fs/bcachefs/btree_types.h
+++ b/fs/bcachefs/btree_types.h
@@ -617,6 +617,9 @@ enum btree_write_type {
 	x(dying)							\
 	x(fake)								\
 	x(need_rewrite)							\
+	x(need_rewrite_error)						\
+	x(need_rewrite_degraded)					\
+	x(need_rewrite_ptr_written_zero)				\
 	x(never_write)							\
 	x(pinned)
 
@@ -641,6 +644,32 @@ static inline void clear_btree_node_ ## flag(struct btree *b)		\
 BTREE_FLAGS()
 #undef x
 
+#define BTREE_NODE_REWRITE_REASON()					\
+	x(none)								\
+	x(unknown)							\
+	x(error)							\
+	x(degraded)							\
+	x(ptr_written_zero)
+
+enum btree_node_rewrite_reason {
+#define x(n)	BTREE_NODE_REWRITE_##n,
+	BTREE_NODE_REWRITE_REASON()
+#undef x
+};
+
+static inline enum btree_node_rewrite_reason btree_node_rewrite_reason(struct btree *b)
+{
+	if (btree_node_need_rewrite_ptr_written_zero(b))
+		return BTREE_NODE_REWRITE_ptr_written_zero;
+	if (btree_node_need_rewrite_degraded(b))
+		return BTREE_NODE_REWRITE_degraded;
+	if (btree_node_need_rewrite_error(b))
+		return BTREE_NODE_REWRITE_error;
+	if (btree_node_need_rewrite(b))
+		return BTREE_NODE_REWRITE_unknown;
+	return BTREE_NODE_REWRITE_none;
+}
+
 static inline struct btree_write *btree_current_write(struct btree *b)
 {
 	return b->writes + btree_node_write_idx(b);
diff --git a/fs/bcachefs/btree_update_interior.c b/fs/bcachefs/btree_update_interior.c
index 340812b28d08..e77584607f0d 100644
--- a/fs/bcachefs/btree_update_interior.c
+++ b/fs/bcachefs/btree_update_interior.c
@@ -1138,6 +1138,13 @@ static void bch2_btree_update_done(struct btree_update *as, struct btree_trans *
 			       start_time);
 }
 
+static const char * const btree_node_reawrite_reason_strs[] = {
+#define x(n)	#n,
+	BTREE_NODE_REWRITE_REASON()
+#undef x
+	NULL,
+};
+
 static struct btree_update *
 bch2_btree_update_start(struct btree_trans *trans, struct btree_path *path,
 			unsigned level_start, bool split,
@@ -1235,7 +1242,7 @@ bch2_btree_update_start(struct btree_trans *trans, struct btree_path *path,
 	struct btree *b = btree_path_node(path, path->level);
 	as->node_start	= b->data->min_key;
 	as->node_end	= b->data->max_key;
-	as->node_needed_rewrite = btree_node_need_rewrite(b);
+	as->node_needed_rewrite = btree_node_rewrite_reason(b);
 	as->node_written = b->written;
 	as->node_sectors = btree_buf_bytes(b) >> 9;
 	as->node_remaining = __bch2_btree_u64s_remaining(b,
@@ -2699,11 +2706,11 @@ static void bch2_btree_update_to_text(struct printbuf *out, struct btree_update
 	bch2_bpos_to_text(out, as->node_start);
 	prt_char(out, ' ');
 	bch2_bpos_to_text(out, as->node_end);
-	prt_printf(out, "\nwritten %u/%u u64s_remaining %u need_rewrite %u",
+	prt_printf(out, "\nwritten %u/%u u64s_remaining %u need_rewrite %s",
 		   as->node_written,
 		   as->node_sectors,
 		   as->node_remaining,
-		   as->node_needed_rewrite);
+		   btree_node_reawrite_reason_strs[as->node_needed_rewrite]);
 
 	prt_printf(out, "\nmode=%s nodes_written=%u cl.remaining=%u journal_seq=%llu\n",
 		   bch2_btree_update_modes[as->mode],
diff --git a/fs/bcachefs/btree_update_interior.h b/fs/bcachefs/btree_update_interior.h
index 85682a13de4d..b649c36c3fbb 100644
--- a/fs/bcachefs/btree_update_interior.h
+++ b/fs/bcachefs/btree_update_interior.h
@@ -59,7 +59,7 @@ struct btree_update {
 	enum btree_id			btree_id;
 	struct bpos			node_start;
 	struct bpos			node_end;
-	bool				node_needed_rewrite;
+	enum btree_node_rewrite_reason	node_needed_rewrite;
 	u16				node_written;
 	u16				node_sectors;
 	u16				node_remaining;

From af5b88618a38371545251ad92ce42bc4bfa1142a Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Sat, 7 Jun 2025 12:01:22 -0400
Subject: [PATCH 0250/1334] bcachefs: Update /dev/disk/by-uuid on device add

Invalidate pagecache after we write the new superblock and send a
uevent.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/super.c | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/fs/bcachefs/super.c b/fs/bcachefs/super.c
index 397a69da5a75..8648f22411be 100644
--- a/fs/bcachefs/super.c
+++ b/fs/bcachefs/super.c
@@ -1995,6 +1995,22 @@ int bch2_dev_add(struct bch_fs *c, const char *path)
 			goto err_late;
 	}
 
+	/*
+	 * We just changed the superblock UUID, invalidate cache and send a
+	 * uevent to update /dev/disk/by-uuid
+	 */
+	invalidate_bdev(ca->disk_sb.bdev);
+
+	char uuid_str[37];
+	snprintf(uuid_str, sizeof(uuid_str), "UUID=%pUb", &c->sb.uuid);
+
+	char *envp[] = {
+		"CHANGE=uuid",
+		uuid_str,
+		NULL,
+	};
+	kobject_uevent_env(&ca->disk_sb.bdev->bd_device.kobj, KOBJ_CHANGE, envp);
+
 	up_write(&c->state_lock);
 out:
 	printbuf_exit(&label);

From 7b0e6b198e4ef39ec89285d953778c5a3a04d390 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Sat, 7 Jun 2025 12:56:15 -0400
Subject: [PATCH 0251/1334] bcachefs: Mark need_discard_freespace_key_bad
 autofix

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/sb-errors_format.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/bcachefs/sb-errors_format.h b/fs/bcachefs/sb-errors_format.h
index 6fdbf265e4c0..90c878f289b2 100644
--- a/fs/bcachefs/sb-errors_format.h
+++ b/fs/bcachefs/sb-errors_format.h
@@ -134,7 +134,7 @@ enum bch_fsck_flags {
 	x(bucket_gens_to_invalid_buckets,			121,	FSCK_AUTOFIX)	\
 	x(bucket_gens_nonzero_for_invalid_buckets,		122,	FSCK_AUTOFIX)	\
 	x(need_discard_freespace_key_to_invalid_dev_bucket,	123,	0)		\
-	x(need_discard_freespace_key_bad,			124,	0)		\
+	x(need_discard_freespace_key_bad,			124,	FSCK_AUTOFIX)	\
 	x(discarding_bucket_not_in_need_discard_btree,		291,	0)		\
 	x(backpointer_bucket_offset_wrong,			125,	0)		\
 	x(backpointer_level_bad,				294,	0)		\

From b47a82ff4772ea9d7091b85ef5f34dc78c866a02 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Sat, 7 Jun 2025 12:56:33 -0400
Subject: [PATCH 0252/1334] bcachefs: Only run 'increase_depth' for keys from
 btree node csan

bch2_btree_increase_depth() was originally for disaster recovery, to get
some data back from the journal when a btree root was bad.

We don't need it for that purpose anymore; on bad btree root we'll
launch btree node scan and reconstruct all the interior nodes.

If there's a key in the journal for a depth that doesn't exists, and
it's not from check_topology/btree node scan, we should just ignore it.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/recovery.c | 13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

diff --git a/fs/bcachefs/recovery.c b/fs/bcachefs/recovery.c
index 1e68e61f08e8..dbd066260725 100644
--- a/fs/bcachefs/recovery.c
+++ b/fs/bcachefs/recovery.c
@@ -271,13 +271,24 @@ static int bch2_journal_replay_key(struct btree_trans *trans,
 		goto out;
 
 	struct btree_path *path = btree_iter_path(trans, &iter);
-	if (unlikely(!btree_path_node(path, k->level))) {
+	if (unlikely(!btree_path_node(path, k->level) &&
+		     !k->allocated)) {
+		struct bch_fs *c = trans->c;
+
+		if (!(c->recovery.passes_complete & (BIT_ULL(BCH_RECOVERY_PASS_scan_for_btree_nodes)|
+						     BIT_ULL(BCH_RECOVERY_PASS_check_topology)))) {
+			bch_err(c, "have key in journal replay for btree depth that does not exist, confused");
+			ret = -EINVAL;
+		}
+#if 0
 		bch2_trans_iter_exit(trans, &iter);
 		bch2_trans_node_iter_init(trans, &iter, k->btree_id, k->k->k.p,
 					  BTREE_MAX_DEPTH, 0, iter_flags);
 		ret =   bch2_btree_iter_traverse(trans, &iter) ?:
 			bch2_btree_increase_depth(trans, iter.path, 0) ?:
 			-BCH_ERR_transaction_restart_nested;
+#endif
+		k->overwritten = true;
 		goto out;
 	}
 

From dd22844f48a71a414bd7e08cd4a9a5847974c07e Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Sat, 7 Jun 2025 14:22:24 -0400
Subject: [PATCH 0253/1334] bcachefs: Read error message now prints if self
 healing

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/io_read.c | 11 +++++++++--
 fs/bcachefs/io_read.h |  1 +
 2 files changed, 10 insertions(+), 2 deletions(-)

diff --git a/fs/bcachefs/io_read.c b/fs/bcachefs/io_read.c
index a77779afad01..04bbdcf58e40 100644
--- a/fs/bcachefs/io_read.c
+++ b/fs/bcachefs/io_read.c
@@ -343,6 +343,10 @@ static struct bch_read_bio *promote_alloc(struct btree_trans *trans,
 
 	*bounce		= true;
 	*read_full	= promote_full;
+
+	if (have_io_error(failed))
+		orig->self_healing = true;
+
 	return promote;
 nopromote:
 	trace_io_read_nopromote(c, ret);
@@ -635,12 +639,15 @@ static void bch2_rbio_retry(struct work_struct *work)
 			prt_str(&buf, "(internal move) ");
 
 		prt_str(&buf, "data read error, ");
-		if (!ret)
+		if (!ret) {
 			prt_str(&buf, "successful retry");
-		else
+			if (rbio->self_healing)
+				prt_str(&buf, ", self healing");
+		} else
 			prt_str(&buf, bch2_err_str(ret));
 		prt_newline(&buf);
 
+
 		if (!bkey_deleted(&sk.k->k)) {
 			bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(sk.k));
 			prt_newline(&buf);
diff --git a/fs/bcachefs/io_read.h b/fs/bcachefs/io_read.h
index 45c959018919..9c5ddbf861b3 100644
--- a/fs/bcachefs/io_read.h
+++ b/fs/bcachefs/io_read.h
@@ -44,6 +44,7 @@ struct bch_read_bio {
 				have_ioref:1,
 				narrow_crcs:1,
 				saw_error:1,
+				self_healing:1,
 				context:2;
 	};
 	u16			_state;

From 263561649ee5875a922f4358e96d3deb17a91021 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Sat, 7 Jun 2025 14:27:35 -0400
Subject: [PATCH 0254/1334] bcachefs: Don't persistently run
 scan_for_btree_nodes

bch2_btree_lost_data() gets called on btree node read error, but the
error might be transient.

btree_node_scan is expensive, and there's no need to run it persistently
(marking it in the superblock as required to run) - check_topology
will run it if required, via bch2_get_scanned_nodes().

Running it non-persistently is fine, to avoid check_topology having to
rewind recovery to run it.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/recovery.c        |  2 ++
 fs/bcachefs/recovery_passes.c | 14 +++++++++++---
 2 files changed, 13 insertions(+), 3 deletions(-)

diff --git a/fs/bcachefs/recovery.c b/fs/bcachefs/recovery.c
index dbd066260725..06d0ba0fbffb 100644
--- a/fs/bcachefs/recovery.c
+++ b/fs/bcachefs/recovery.c
@@ -99,9 +99,11 @@ int bch2_btree_lost_data(struct bch_fs *c,
 		goto out;
 	case BTREE_ID_snapshots:
 		ret = __bch2_run_explicit_recovery_pass(c, msg, BCH_RECOVERY_PASS_reconstruct_snapshots, 0) ?: ret;
+		ret = __bch2_run_explicit_recovery_pass(c, msg, BCH_RECOVERY_PASS_check_topology, 0) ?: ret;
 		ret = __bch2_run_explicit_recovery_pass(c, msg, BCH_RECOVERY_PASS_scan_for_btree_nodes, 0) ?: ret;
 		goto out;
 	default:
+		ret = __bch2_run_explicit_recovery_pass(c, msg, BCH_RECOVERY_PASS_check_topology, 0) ?: ret;
 		ret = __bch2_run_explicit_recovery_pass(c, msg, BCH_RECOVERY_PASS_scan_for_btree_nodes, 0) ?: ret;
 		goto out;
 	}
diff --git a/fs/bcachefs/recovery_passes.c b/fs/bcachefs/recovery_passes.c
index 605588e33fb3..35ac0d64d73a 100644
--- a/fs/bcachefs/recovery_passes.c
+++ b/fs/bcachefs/recovery_passes.c
@@ -294,8 +294,13 @@ static bool recovery_pass_needs_set(struct bch_fs *c,
 				    enum bch_run_recovery_pass_flags *flags)
 {
 	struct bch_fs_recovery *r = &c->recovery;
-	bool in_recovery = test_bit(BCH_FS_in_recovery, &c->flags);
-	bool persistent = !in_recovery || !(*flags & RUN_RECOVERY_PASS_nopersistent);
+
+	/*
+	 * Never run scan_for_btree_nodes persistently: check_topology will run
+	 * it if required
+	 */
+	if (pass == BCH_RECOVERY_PASS_scan_for_btree_nodes)
+		*flags |= RUN_RECOVERY_PASS_nopersistent;
 
 	if ((*flags & RUN_RECOVERY_PASS_ratelimit) &&
 	    !bch2_recovery_pass_want_ratelimit(c, pass))
@@ -310,6 +315,8 @@ static bool recovery_pass_needs_set(struct bch_fs *c,
 	 * Otherwise, we run run_explicit_recovery_pass when we find damage, so
 	 * it should run again even if it's already run:
 	 */
+	bool in_recovery = test_bit(BCH_FS_in_recovery, &c->flags);
+	bool persistent = !in_recovery || !(*flags & RUN_RECOVERY_PASS_nopersistent);
 
 	if (persistent
 	    ? !(c->sb.recovery_passes_required & BIT_ULL(pass))
@@ -334,6 +341,7 @@ int __bch2_run_explicit_recovery_pass(struct bch_fs *c,
 	struct bch_fs_recovery *r = &c->recovery;
 	int ret = 0;
 
+
 	lockdep_assert_held(&c->sb_lock);
 
 	bch2_printbuf_make_room(out, 1024);
@@ -446,7 +454,7 @@ int bch2_require_recovery_pass(struct bch_fs *c,
 
 int bch2_run_print_explicit_recovery_pass(struct bch_fs *c, enum bch_recovery_pass pass)
 {
-	enum bch_run_recovery_pass_flags flags = RUN_RECOVERY_PASS_nopersistent;
+	enum bch_run_recovery_pass_flags flags = 0;
 
 	if (!recovery_pass_needs_set(c, pass, &flags))
 		return 0;

From 3315113af178041ab474723804e1322cee7d0a97 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Sat, 7 Jun 2025 18:56:28 -0400
Subject: [PATCH 0255/1334] bcachefs: mark more errors autofix

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/sb-errors_format.h | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/fs/bcachefs/sb-errors_format.h b/fs/bcachefs/sb-errors_format.h
index 90c878f289b2..d06e73884871 100644
--- a/fs/bcachefs/sb-errors_format.h
+++ b/fs/bcachefs/sb-errors_format.h
@@ -165,7 +165,7 @@ enum bch_fsck_flags {
 	x(ptr_to_missing_replicas_entry,			149,	FSCK_AUTOFIX)	\
 	x(ptr_to_missing_stripe,				150,	0)		\
 	x(ptr_to_incorrect_stripe,				151,	0)		\
-	x(ptr_gen_newer_than_bucket_gen,			152,	0)		\
+	x(ptr_gen_newer_than_bucket_gen,			152,	FSCK_AUTOFIX)		\
 	x(ptr_too_stale,					153,	0)		\
 	x(stale_dirty_ptr,					154,	FSCK_AUTOFIX)	\
 	x(ptr_bucket_data_type_mismatch,			155,	0)		\
@@ -236,7 +236,7 @@ enum bch_fsck_flags {
 	x(inode_multiple_links_but_nlink_0,			207,	FSCK_AUTOFIX)	\
 	x(inode_wrong_backpointer,				208,	FSCK_AUTOFIX)	\
 	x(inode_wrong_nlink,					209,	FSCK_AUTOFIX)	\
-	x(inode_has_child_snapshots_wrong,			287,	0)		\
+	x(inode_has_child_snapshots_wrong,			287,	FSCK_AUTOFIX)	\
 	x(inode_unreachable,					210,	FSCK_AUTOFIX)	\
 	x(inode_journal_seq_in_future,				299,	FSCK_AUTOFIX)	\
 	x(inode_i_sectors_underflow,				312,	FSCK_AUTOFIX)	\
@@ -279,8 +279,8 @@ enum bch_fsck_flags {
 	x(root_dir_missing,					239,	0)		\
 	x(root_inode_not_dir,					240,	0)		\
 	x(dir_loop,						241,	0)		\
-	x(hash_table_key_duplicate,				242,	0)		\
-	x(hash_table_key_wrong_offset,				243,	0)		\
+	x(hash_table_key_duplicate,				242,	FSCK_AUTOFIX)	\
+	x(hash_table_key_wrong_offset,				243,	FSCK_AUTOFIX)	\
 	x(unlinked_inode_not_on_deleted_list,			244,	FSCK_AUTOFIX)	\
 	x(reflink_p_front_pad_bad,				245,	0)		\
 	x(journal_entry_dup_same_device,			246,	0)		\

From 0acb385ec19c99b213d28a309a941790758c53a8 Mon Sep 17 00:00:00 2001
From: Alan Huang <mmpgouride@gmail.com>
Date: Tue, 20 May 2025 15:34:28 +0800
Subject: [PATCH 0256/1334] bcachefs: Fix possible console lock involved
 deadlock

Link: https://lore.kernel.org/all/6822ab02.050a0220.f2294.00cb.GAE@google.com/T/
Reported-by: syzbot+2c3ef91c9523c3d1a25c@syzkaller.appspotmail.com
Signed-off-by: Alan Huang <mmpgouride@gmail.com>
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/bcachefs.h      |  1 -
 fs/bcachefs/btree_locking.c |  2 +-
 fs/bcachefs/error.c         |  2 +-
 fs/bcachefs/super.c         | 11 +++--------
 fs/bcachefs/util.c          | 10 ++--------
 fs/bcachefs/util.h          |  2 +-
 6 files changed, 8 insertions(+), 20 deletions(-)

diff --git a/fs/bcachefs/bcachefs.h b/fs/bcachefs/bcachefs.h
index 3651a296d506..5a1cede2febf 100644
--- a/fs/bcachefs/bcachefs.h
+++ b/fs/bcachefs/bcachefs.h
@@ -296,7 +296,6 @@ do {									\
 #define bch2_fmt(_c, fmt)		bch2_log_msg(_c, fmt "\n")
 
 void bch2_print_str(struct bch_fs *, const char *, const char *);
-void bch2_print_str_nonblocking(struct bch_fs *, const char *, const char *);
 
 __printf(2, 3)
 void bch2_print_opts(struct bch_opts *, const char *, ...);
diff --git a/fs/bcachefs/btree_locking.c b/fs/bcachefs/btree_locking.c
index 47035aae232e..91a51aef82f1 100644
--- a/fs/bcachefs/btree_locking.c
+++ b/fs/bcachefs/btree_locking.c
@@ -213,7 +213,7 @@ static noinline __noreturn void break_cycle_fail(struct lock_graph *g)
 		prt_newline(&buf);
 	}
 
-	bch2_print_str_nonblocking(g->g->trans->c, KERN_ERR, buf.buf);
+	bch2_print_str(g->g->trans->c, KERN_ERR, buf.buf);
 	printbuf_exit(&buf);
 	BUG();
 }
diff --git a/fs/bcachefs/error.c b/fs/bcachefs/error.c
index ff49cebfd0e8..a8ec6aae5738 100644
--- a/fs/bcachefs/error.c
+++ b/fs/bcachefs/error.c
@@ -69,7 +69,7 @@ static bool bch2_fs_trans_inconsistent(struct bch_fs *c, struct btree_trans *tra
 	if (trans)
 		bch2_trans_updates_to_text(&buf, trans);
 	bool ret = __bch2_inconsistent_error(c, &buf);
-	bch2_print_str_nonblocking(c, KERN_ERR, buf.buf);
+	bch2_print_str(c, KERN_ERR, buf.buf);
 
 	printbuf_exit(&buf);
 	return ret;
diff --git a/fs/bcachefs/super.c b/fs/bcachefs/super.c
index 8648f22411be..ae8fa58a208d 100644
--- a/fs/bcachefs/super.c
+++ b/fs/bcachefs/super.c
@@ -104,7 +104,7 @@ const char * const bch2_dev_write_refs[] = {
 #undef x
 
 static void __bch2_print_str(struct bch_fs *c, const char *prefix,
-			     const char *str, bool nonblocking)
+			     const char *str)
 {
 #ifdef __KERNEL__
 	struct stdio_redirect *stdio = bch2_fs_stdio_redirect(c);
@@ -114,17 +114,12 @@ static void __bch2_print_str(struct bch_fs *c, const char *prefix,
 		return;
 	}
 #endif
-	bch2_print_string_as_lines(KERN_ERR, str, nonblocking);
+	bch2_print_string_as_lines(KERN_ERR, str);
 }
 
 void bch2_print_str(struct bch_fs *c, const char *prefix, const char *str)
 {
-	__bch2_print_str(c, prefix, str, false);
-}
-
-void bch2_print_str_nonblocking(struct bch_fs *c, const char *prefix, const char *str)
-{
-	__bch2_print_str(c, prefix, str, true);
+	__bch2_print_str(c, prefix, str);
 }
 
 __printf(2, 0)
diff --git a/fs/bcachefs/util.c b/fs/bcachefs/util.c
index dc3817f545fa..df9a6071fe18 100644
--- a/fs/bcachefs/util.c
+++ b/fs/bcachefs/util.c
@@ -262,8 +262,7 @@ static bool string_is_spaces(const char *str)
 	return true;
 }
 
-void bch2_print_string_as_lines(const char *prefix, const char *lines,
-				bool nonblocking)
+void bch2_print_string_as_lines(const char *prefix, const char *lines)
 {
 	bool locked = false;
 	const char *p;
@@ -273,12 +272,7 @@ void bch2_print_string_as_lines(const char *prefix, const char *lines,
 		return;
 	}
 
-	if (!nonblocking) {
-		console_lock();
-		locked = true;
-	} else {
-		locked = console_trylock();
-	}
+	locked = console_trylock();
 
 	while (*lines) {
 		p = strchrnul(lines, '\n');
diff --git a/fs/bcachefs/util.h b/fs/bcachefs/util.h
index 0a4b1d433621..6488f098d140 100644
--- a/fs/bcachefs/util.h
+++ b/fs/bcachefs/util.h
@@ -214,7 +214,7 @@ u64 bch2_read_flag_list(const char *, const char * const[]);
 void bch2_prt_u64_base2_nbits(struct printbuf *, u64, unsigned);
 void bch2_prt_u64_base2(struct printbuf *, u64);
 
-void bch2_print_string_as_lines(const char *, const char *, bool);
+void bch2_print_string_as_lines(const char *, const char *);
 
 typedef DARRAY(unsigned long) bch_stacktrace;
 int bch2_save_backtrace(bch_stacktrace *stack, struct task_struct *, unsigned, gfp_t);

From f946ce0be45e75801583a5371fccf7466961d9d0 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Sat, 7 Jun 2025 20:18:16 -0400
Subject: [PATCH 0257/1334] bcachefs: Make sure opts.read_only gets propagated
 back to VFS

If we think we're read-only but the VFS doesn't, fun will ensue.

And now that we know we have to be able to do this safely, just make
nochanges imply ro.

Reported-by: syzbot+a7d6ceaba099cc21dee4@syzkaller.appspotmail.com
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/fs.c       | 8 ++++++++
 fs/bcachefs/recovery.c | 4 +++-
 2 files changed, 11 insertions(+), 1 deletion(-)

diff --git a/fs/bcachefs/fs.c b/fs/bcachefs/fs.c
index 85d13f800165..3063a8ddc2df 100644
--- a/fs/bcachefs/fs.c
+++ b/fs/bcachefs/fs.c
@@ -2490,6 +2490,14 @@ static int bch2_fs_get_tree(struct fs_context *fc)
 	if (ret)
 		goto err_stop_fs;
 
+	/*
+	 * We might be doing a RO mount because other options required it, or we
+	 * have no alloc info and it's a small image with no room to regenerate
+	 * it
+	 */
+	if (c->opts.read_only)
+		fc->sb_flags |= SB_RDONLY;
+
 	sb = sget(fc->fs_type, NULL, bch2_set_super, fc->sb_flags|SB_NOSEC, c);
 	ret = PTR_ERR_OR_ZERO(sb);
 	if (ret)
diff --git a/fs/bcachefs/recovery.c b/fs/bcachefs/recovery.c
index 06d0ba0fbffb..520eb72c4971 100644
--- a/fs/bcachefs/recovery.c
+++ b/fs/bcachefs/recovery.c
@@ -752,9 +752,11 @@ int bch2_fs_recovery(struct bch_fs *c)
 			? min(c->opts.recovery_pass_last, BCH_RECOVERY_PASS_snapshots_read)
 			: BCH_RECOVERY_PASS_snapshots_read;
 		c->opts.nochanges = true;
-		c->opts.read_only = true;
 	}
 
+	if (c->opts.nochanges)
+		c->opts.read_only = true;
+
 	mutex_lock(&c->sb_lock);
 	struct bch_sb_field_ext *ext = bch2_sb_field_get(c->disk_sb.sb, ext);
 	bool write_sb = false;

From 757601ef853359fe2d57d75c00b5045f62efc608 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Sun, 8 Jun 2025 11:40:00 -0400
Subject: [PATCH 0258/1334] bcachefs: Don't put rhashtable on stack

Object debugging generally needs special provisions for putting said
objects on the stack, which rhashtable does not have.

Reported-by: syzbot+bcc38a9556d0324c2ec2@syzkaller.appspotmail.com
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/movinggc.c | 22 +++++++++++++---------
 1 file changed, 13 insertions(+), 9 deletions(-)

diff --git a/fs/bcachefs/movinggc.c b/fs/bcachefs/movinggc.c
index 6d7b1d5f7697..27e68d470ad0 100644
--- a/fs/bcachefs/movinggc.c
+++ b/fs/bcachefs/movinggc.c
@@ -28,7 +28,7 @@
 #include <linux/wait.h>
 
 struct buckets_in_flight {
-	struct rhashtable	table;
+	struct rhashtable	*table;
 	struct move_bucket	*first;
 	struct move_bucket	*last;
 	size_t			nr;
@@ -98,7 +98,7 @@ out:
 static void move_bucket_free(struct buckets_in_flight *list,
 			     struct move_bucket *b)
 {
-	int ret = rhashtable_remove_fast(&list->table, &b->hash,
+	int ret = rhashtable_remove_fast(list->table, &b->hash,
 					 bch_move_bucket_params);
 	BUG_ON(ret);
 	kfree(b);
@@ -133,7 +133,7 @@ static void move_buckets_wait(struct moving_context *ctxt,
 static bool bucket_in_flight(struct buckets_in_flight *list,
 			     struct move_bucket_key k)
 {
-	return rhashtable_lookup_fast(&list->table, &k, bch_move_bucket_params);
+	return rhashtable_lookup_fast(list->table, &k, bch_move_bucket_params);
 }
 
 static int bch2_copygc_get_buckets(struct moving_context *ctxt,
@@ -185,7 +185,7 @@ static int bch2_copygc_get_buckets(struct moving_context *ctxt,
 				goto err;
 			}
 
-			ret2 = rhashtable_lookup_insert_fast(&buckets_in_flight->table, &b_i->hash,
+			ret2 = rhashtable_lookup_insert_fast(buckets_in_flight->table, &b_i->hash,
 							     bch_move_bucket_params);
 			BUG_ON(ret2);
 
@@ -350,10 +350,13 @@ static int bch2_copygc_thread(void *arg)
 	struct buckets_in_flight buckets = {};
 	u64 last, wait;
 
-	int ret = rhashtable_init(&buckets.table, &bch_move_bucket_params);
+	buckets.table = kzalloc(sizeof(*buckets.table), GFP_KERNEL);
+	int ret = !buckets.table
+		? -ENOMEM
+		: rhashtable_init(buckets.table, &bch_move_bucket_params);
 	bch_err_msg(c, ret, "allocating copygc buckets in flight");
 	if (ret)
-		return ret;
+		goto err;
 
 	set_freezable();
 
@@ -421,11 +424,12 @@ static int bch2_copygc_thread(void *arg)
 	}
 
 	move_buckets_wait(&ctxt, &buckets, true);
-	rhashtable_destroy(&buckets.table);
+	rhashtable_destroy(buckets.table);
 	bch2_moving_ctxt_exit(&ctxt);
 	bch2_move_stats_exit(&move_stats, c);
-
-	return 0;
+err:
+	kfree(buckets.table);
+	return ret;
 }
 
 void bch2_copygc_stop(struct bch_fs *c)

From 082c74411491f8b0d31465fc104b8342e66c4056 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Sun, 8 Jun 2025 11:58:59 -0400
Subject: [PATCH 0259/1334] bcachefs: Fix downgrade_table_extra()

Fix a UAF: we were calling darray_make_room() and retaining a pointer to
the old buffer.

And fix an UBSAN warning: struct bch_sb_field_downgrade_entry uses
__counted_by, so set dst->nr_errors before assigning to the array entry.

Reported-by: syzbot+14c52d86ddbd89bea13e@syzkaller.appspotmail.com
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/sb-downgrade.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/fs/bcachefs/sb-downgrade.c b/fs/bcachefs/sb-downgrade.c
index b61f88450a6d..1506d05e0665 100644
--- a/fs/bcachefs/sb-downgrade.c
+++ b/fs/bcachefs/sb-downgrade.c
@@ -253,6 +253,7 @@ DOWNGRADE_TABLE()
 
 static int downgrade_table_extra(struct bch_fs *c, darray_char *table)
 {
+	unsigned dst_offset = table->nr;
 	struct bch_sb_field_downgrade_entry *dst = (void *) &darray_top(*table);
 	unsigned bytes = sizeof(*dst) + sizeof(dst->errors[0]) * le16_to_cpu(dst->nr_errors);
 	int ret = 0;
@@ -268,6 +269,9 @@ static int downgrade_table_extra(struct bch_fs *c, darray_char *table)
 			if (ret)
 				return ret;
 
+			dst = (void *) &table->data[dst_offset];
+			dst->nr_errors = cpu_to_le16(nr_errors + 1);
+
 			/* open coded __set_bit_le64, as dst is packed and
 			 * dst->recovery_passes is misaligned */
 			unsigned b = BCH_RECOVERY_PASS_STABLE_check_allocations;
@@ -278,7 +282,6 @@ static int downgrade_table_extra(struct bch_fs *c, darray_char *table)
 		break;
 	}
 
-	dst->nr_errors = cpu_to_le16(nr_errors);
 	return ret;
 }
 

From 54aacfe3976893ee04582a0bd61967bbee5a7e04 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Sun, 8 Jun 2025 12:17:02 -0400
Subject: [PATCH 0260/1334] bcachefs: Fix rcu_pending for PREEMPT_RT

PREEMPT_RT redefines how standard spinlocks work, so local_irq_save() +
spin_lock() is no longer equivalent to spin_lock_irqsave(). Fortunately,
we don't strictly need to do it that way.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/rcu_pending.c | 22 +++++++++++-----------
 1 file changed, 11 insertions(+), 11 deletions(-)

diff --git a/fs/bcachefs/rcu_pending.c b/fs/bcachefs/rcu_pending.c
index bef2aa1b8bcd..b1438be9d690 100644
--- a/fs/bcachefs/rcu_pending.c
+++ b/fs/bcachefs/rcu_pending.c
@@ -182,11 +182,6 @@ static inline void kfree_bulk(size_t nr, void ** p)
 	while (nr--)
 		kfree(*p);
 }
-
-#define local_irq_save(flags)		\
-do {					\
-	flags = 0;			\
-} while (0)
 #endif
 
 static noinline void __process_finished_items(struct rcu_pending *pending,
@@ -429,9 +424,15 @@ __rcu_pending_enqueue(struct rcu_pending *pending, struct rcu_head *head,
 
 	BUG_ON((ptr != NULL) != (pending->process == RCU_PENDING_KVFREE_FN));
 
-	local_irq_save(flags);
-	p = this_cpu_ptr(pending->p);
-	spin_lock(&p->lock);
+	/* We could technically be scheduled before taking the lock and end up
+	 * using a different cpu's rcu_pending_pcpu: that's ok, it needs a lock
+	 * anyways
+	 *
+	 * And we have to do it this way to avoid breaking PREEMPT_RT, which
+	 * redefines how spinlocks work:
+	 */
+	p = raw_cpu_ptr(pending->p);
+	spin_lock_irqsave(&p->lock, flags);
 	rcu_gp_poll_state_t seq = __get_state_synchronize_rcu(pending->srcu);
 restart:
 	if (may_sleep &&
@@ -520,9 +521,8 @@ check_expired:
 		goto free_node;
 	}
 
-	local_irq_save(flags);
-	p = this_cpu_ptr(pending->p);
-	spin_lock(&p->lock);
+	p = raw_cpu_ptr(pending->p);
+	spin_lock_irqsave(&p->lock, flags);
 	goto restart;
 }
 

From 9e48f574e55731106b26dc33d8b0be1adedf3f20 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Mon, 9 Jun 2025 17:30:40 -0400
Subject: [PATCH 0261/1334] bcachefs: Fix leak in bch2_fs_recovery() error path

Fix a small leak of the superblock 'clean' section.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/recovery.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/fs/bcachefs/recovery.c b/fs/bcachefs/recovery.c
index 520eb72c4971..0b21fa6ff062 100644
--- a/fs/bcachefs/recovery.c
+++ b/fs/bcachefs/recovery.c
@@ -1108,9 +1108,6 @@ use_clean:
 out:
 	bch2_flush_fsck_errs(c);
 
-	if (!IS_ERR(clean))
-		kfree(clean);
-
 	if (!ret &&
 	    test_bit(BCH_FS_need_delete_dead_snapshots, &c->flags) &&
 	    !c->opts.nochanges) {
@@ -1119,6 +1116,9 @@ out:
 	}
 
 	bch_err_fn(c, ret);
+final_out:
+	if (!IS_ERR(clean))
+		kfree(clean);
 	return ret;
 err:
 fsck_err:
@@ -1132,7 +1132,7 @@ fsck_err:
 		bch2_print_str(c, KERN_ERR, buf.buf);
 		printbuf_exit(&buf);
 	}
-	return ret;
+	goto final_out;
 }
 
 int bch2_fs_initialize(struct bch_fs *c)

From c3dd25319c1818e067f41f41127f935f153498e6 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Mon, 9 Jun 2025 17:28:00 -0400
Subject: [PATCH 0262/1334] bcachefs: Don't pass trans to fsck_err() in
 gc_accounting_done

fsck_err() can return a transaction restart if passed a transaction
object - this has always been true when it has to drop locks to prompt
for user input, but we're seeing this more now that we're logging the
error being corrected in the journal.

gc_accounting_done() doesn't call fsck_err() from an actual commit loop,
and it doesn't need to be holding btree locks when it calls fsck_err(),
so the easy fix here for the unhandled transaction restart is to just
not pass it the transaction object. We'll miss out on the fancy new
logging, but that's ok.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/disk_accounting.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/fs/bcachefs/disk_accounting.c b/fs/bcachefs/disk_accounting.c
index 3d59a57a5256..f7528cd69c73 100644
--- a/fs/bcachefs/disk_accounting.c
+++ b/fs/bcachefs/disk_accounting.c
@@ -618,7 +618,9 @@ int bch2_gc_accounting_done(struct bch_fs *c)
 			for (unsigned j = 0; j < nr; j++)
 				src_v[j] -= dst_v[j];
 
-			if (fsck_err(trans, accounting_mismatch, "%s", buf.buf)) {
+			bch2_trans_unlock_long(trans);
+
+			if (fsck_err(c, accounting_mismatch, "%s", buf.buf)) {
 				percpu_up_write(&c->mark_lock);
 				ret = commit_do(trans, NULL, NULL, 0,
 						bch2_disk_accounting_mod(trans, &acc_k, src_v, nr, false));

From e82b3a63a9a91cc5c585efb3e28f32100f24e3e1 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 10 Jun 2025 11:24:04 +0200
Subject: [PATCH 0263/1334] bcachefs: ioctl: avoid stack overflow warning

Multiple ioctl handlers individually use a lot of stack space, and clang chooses
to inline them into the bch2_fs_ioctl() function, blowing through the warning
limit:

fs/bcachefs/chardev.c:655:6: error: stack frame size (1032) exceeds limit (1024) in 'bch2_fs_ioctl' [-Werror,-Wframe-larger-than]
  655 | long bch2_fs_ioctl(struct bch_fs *c, unsigned cmd, void __user *arg)

By marking the largest two of them as noinline_for_stack, no indidual code path
ends up using this much, which avoids the warning and reduces the possible
total stack usage in the ioctl handler.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/chardev.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/fs/bcachefs/chardev.c b/fs/bcachefs/chardev.c
index 2d38466eddfd..fde3c2380e28 100644
--- a/fs/bcachefs/chardev.c
+++ b/fs/bcachefs/chardev.c
@@ -399,7 +399,7 @@ static long bch2_ioctl_data(struct bch_fs *c,
 	return ret;
 }
 
-static long bch2_ioctl_fs_usage(struct bch_fs *c,
+static noinline_for_stack long bch2_ioctl_fs_usage(struct bch_fs *c,
 				struct bch_ioctl_fs_usage __user *user_arg)
 {
 	struct bch_ioctl_fs_usage arg = {};
@@ -469,7 +469,7 @@ err:
 }
 
 /* obsolete, didn't allow for new data types: */
-static long bch2_ioctl_dev_usage(struct bch_fs *c,
+static noinline_for_stack long bch2_ioctl_dev_usage(struct bch_fs *c,
 				 struct bch_ioctl_dev_usage __user *user_arg)
 {
 	struct bch_ioctl_dev_usage arg;

From 625c494db95624f09f5e7b81b64d4da34e45bd2a Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Wed, 11 Jun 2025 13:32:58 -0400
Subject: [PATCH 0264/1334] bcachefs: Fix version checks in validate_bset()

It seems btree node scan picked up a partially overwritten btree node,
and corrected the "bset version older than sb version_min" error -
resulting in an invalid superblock with a bad version_min field.

Don't run this check at all when we're in btree node scan, and when we
do run it, do something saner if the bset version is totally crazy.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/btree_io.c | 16 +++++++++++-----
 1 file changed, 11 insertions(+), 5 deletions(-)

diff --git a/fs/bcachefs/btree_io.c b/fs/bcachefs/btree_io.c
index 6787d5b91eab..d8f3c4c65e90 100644
--- a/fs/bcachefs/btree_io.c
+++ b/fs/bcachefs/btree_io.c
@@ -741,16 +741,22 @@ static int validate_bset(struct bch_fs *c, struct bch_dev *ca,
 		     BCH_VERSION_MAJOR(version),
 		     BCH_VERSION_MINOR(version));
 
-	if (btree_err_on(version < c->sb.version_min,
+	if (c->recovery.curr_pass != BCH_RECOVERY_PASS_scan_for_btree_nodes &&
+	    btree_err_on(version < c->sb.version_min,
 			 -BCH_ERR_btree_node_read_err_fixable,
 			 c, NULL, b, i, NULL,
 			 btree_node_bset_older_than_sb_min,
 			 "bset version %u older than superblock version_min %u",
 			 version, c->sb.version_min)) {
-		mutex_lock(&c->sb_lock);
-		c->disk_sb.sb->version_min = cpu_to_le16(version);
-		bch2_write_super(c);
-		mutex_unlock(&c->sb_lock);
+		if (bch2_version_compatible(version)) {
+			mutex_lock(&c->sb_lock);
+			c->disk_sb.sb->version_min = cpu_to_le16(version);
+			bch2_write_super(c);
+			mutex_unlock(&c->sb_lock);
+		} else {
+			/* We have no idea what's going on: */
+			i->version = cpu_to_le16(c->sb.version);
+		}
 	}
 
 	if (btree_err_on(BCH_VERSION_MAJOR(version) >

From 205da7c026739d965e605d39001049c7b6728e87 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Sun, 8 Jun 2025 11:31:23 -0400
Subject: [PATCH 0265/1334] bcachefs: Don't trust sb->nr_devices in
 members_to_text()

We have to be able to print superblock sections even if they fail to
validate (for debugging), so we have to calculate the number of entries
from the field size.

Reported-by: syzbot+5138f00559ffb3cb3610@syzkaller.appspotmail.com
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/sb-members.c | 34 ++++++++++++++++++++++++++++++----
 1 file changed, 30 insertions(+), 4 deletions(-)

diff --git a/fs/bcachefs/sb-members.c b/fs/bcachefs/sb-members.c
index 363eb0c6eb7c..6245e342a8a8 100644
--- a/fs/bcachefs/sb-members.c
+++ b/fs/bcachefs/sb-members.c
@@ -325,9 +325,17 @@ static void bch2_sb_members_v1_to_text(struct printbuf *out, struct bch_sb *sb,
 {
 	struct bch_sb_field_members_v1 *mi = field_to_type(f, members_v1);
 	struct bch_sb_field_disk_groups *gi = bch2_sb_field_get(sb, disk_groups);
-	unsigned i;
 
-	for (i = 0; i < sb->nr_devices; i++)
+	if (vstruct_end(&mi->field) <= (void *) &mi->_members[0]) {
+		prt_printf(out, "field ends before start of entries");
+		return;
+	}
+
+	unsigned nr = (vstruct_end(&mi->field) - (void *) &mi->_members[0]) / sizeof(mi->_members[0]);
+	if (nr != sb->nr_devices)
+		prt_printf(out, "nr_devices mismatch: have %i entries, should be %u", nr, sb->nr_devices);
+
+	for (unsigned i = 0; i < min(sb->nr_devices, nr); i++)
 		member_to_text(out, members_v1_get(mi, i), gi, sb, i);
 }
 
@@ -341,9 +349,27 @@ static void bch2_sb_members_v2_to_text(struct printbuf *out, struct bch_sb *sb,
 {
 	struct bch_sb_field_members_v2 *mi = field_to_type(f, members_v2);
 	struct bch_sb_field_disk_groups *gi = bch2_sb_field_get(sb, disk_groups);
-	unsigned i;
 
-	for (i = 0; i < sb->nr_devices; i++)
+	if (vstruct_end(&mi->field) <= (void *) &mi->_members[0]) {
+		prt_printf(out, "field ends before start of entries");
+		return;
+	}
+
+	if (!le16_to_cpu(mi->member_bytes)) {
+		prt_printf(out, "member_bytes 0");
+		return;
+	}
+
+	unsigned nr = (vstruct_end(&mi->field) - (void *) &mi->_members[0]) / le16_to_cpu(mi->member_bytes);
+	if (nr != sb->nr_devices)
+		prt_printf(out, "nr_devices mismatch: have %i entries, should be %u", nr, sb->nr_devices);
+
+	/*
+	 * We call to_text() on superblock sections that haven't passed
+	 * validate, so we can't trust sb->nr_devices.
+	 */
+
+	for (unsigned i = 0; i < min(sb->nr_devices, nr); i++)
 		member_to_text(out, members_v2_get(mi, i), gi, sb, i);
 }
 

From b68baf9a87330148d3ad074e48503a4e9c5c3929 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Wed, 11 Jun 2025 15:57:48 -0400
Subject: [PATCH 0266/1334] bcachefs: Print devices we're mounting on multi
 device filesystems

Previously, we only ever logged the filesystem UUID.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/super.c | 20 ++++++++++++++------
 1 file changed, 14 insertions(+), 6 deletions(-)

diff --git a/fs/bcachefs/super.c b/fs/bcachefs/super.c
index ae8fa58a208d..a5b97c9c5163 100644
--- a/fs/bcachefs/super.c
+++ b/fs/bcachefs/super.c
@@ -1067,12 +1067,13 @@ noinline_for_stack
 static void print_mount_opts(struct bch_fs *c)
 {
 	enum bch_opt_id i;
-	struct printbuf p = PRINTBUF;
-	bool first = true;
+	CLASS(printbuf, p)();
+	bch2_log_msg_start(c, &p);
 
 	prt_str(&p, "starting version ");
 	bch2_version_to_text(&p, c->sb.version);
 
+	bool first = true;
 	for (i = 0; i < bch2_opts_nr; i++) {
 		const struct bch_option *opt = &bch2_opt_table[i];
 		u64 v = bch2_opt_get_by_id(&c->opts, i);
@@ -1089,17 +1090,24 @@ static void print_mount_opts(struct bch_fs *c)
 	}
 
 	if (c->sb.version_incompat_allowed != c->sb.version) {
-		prt_printf(&p, "\n  allowing incompatible features above ");
+		prt_printf(&p, "\nallowing incompatible features above ");
 		bch2_version_to_text(&p, c->sb.version_incompat_allowed);
 	}
 
 	if (c->opts.verbose) {
-		prt_printf(&p, "\n  features: ");
+		prt_printf(&p, "\nfeatures: ");
 		prt_bitflags(&p, bch2_sb_features, c->sb.features);
 	}
 
-	bch_info(c, "%s", p.buf);
-	printbuf_exit(&p);
+	if (c->sb.multi_device) {
+		prt_printf(&p, "\nwith devices");
+		for_each_online_member(c, ca, BCH_DEV_READ_REF_bch2_online_devs) {
+			prt_char(&p, ' ');
+			prt_str(&p, ca->name);
+		}
+	}
+
+	bch2_print_str(c, KERN_INFO, p.buf);
 }
 
 static bool bch2_fs_may_start(struct bch_fs *c)

From cd1124244be30fd3e87da9186508aab371e9307d Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Sun, 8 Jun 2025 12:35:20 -0400
Subject: [PATCH 0267/1334] bcachefs: Ensure that snapshot creation propagates
 has_case_insensitive

We normally can't create a new directory with the case-insensitive
option already set - except when we're creating a snapshot.

And if casefolding is enabled filesystem wide, we should still set it
even though not strictly required, for consistency.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/namei.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/fs/bcachefs/namei.c b/fs/bcachefs/namei.c
index 24120037c031..779c22eb3979 100644
--- a/fs/bcachefs/namei.c
+++ b/fs/bcachefs/namei.c
@@ -175,6 +175,16 @@ int bch2_create_trans(struct btree_trans *trans,
 		new_inode->bi_dir_offset	= dir_offset;
 	}
 
+	if (S_ISDIR(mode)) {
+		ret = bch2_maybe_propagate_has_case_insensitive(trans,
+				(subvol_inum) {
+					new_inode->bi_subvol ?: dir.subvol,
+					new_inode->bi_inum },
+				new_inode);
+		if (ret)
+			goto err;
+	}
+
 	if (S_ISDIR(mode) &&
 	    !new_inode->bi_subvol)
 		new_inode->bi_depth = dir_u->bi_depth + 1;

From aef22f6fe7a630d536f9eaa0a7a2ed0f90ea369e Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Tue, 10 Jun 2025 22:32:14 -0400
Subject: [PATCH 0268/1334] bcachefs: Don't trace should_be_locked unless
 changing

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/btree_locking.h | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/fs/bcachefs/btree_locking.h b/fs/bcachefs/btree_locking.h
index 9adca77e2580..f2173a3316f4 100644
--- a/fs/bcachefs/btree_locking.h
+++ b/fs/bcachefs/btree_locking.h
@@ -417,8 +417,10 @@ static inline void btree_path_set_should_be_locked(struct btree_trans *trans, st
 	EBUG_ON(!btree_node_locked(path, path->level));
 	EBUG_ON(path->uptodate);
 
-	path->should_be_locked = true;
-	trace_btree_path_should_be_locked(trans, path);
+	if (!path->should_be_locked) {
+		path->should_be_locked = true;
+		trace_btree_path_should_be_locked(trans, path);
+	}
 }
 
 static inline void __btree_path_set_level_up(struct btree_trans *trans,

From aa2024c01a9afba6728b362626f868811ca872ee Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Tue, 10 Jun 2025 20:10:18 -0400
Subject: [PATCH 0269/1334] KVM: x86/mmu: Embed direct bits into gpa for
 KVM_PRE_FAULT_MEMORY

Bug[*] reported for TDX case when enabling KVM_PRE_FAULT_MEMORY in QEMU.

It turns out that @gpa passed to kvm_mmu_do_page_fault() doesn't have
shared bit set when the memory attribute of it is shared, and it leads
to wrong root in tdp_mmu_get_root_for_fault().

Fix it by embedding the direct bits in the gpa that is passed to
kvm_tdp_map_page(), when the memory of the gpa is not private.

[*] https://lore.kernel.org/qemu-devel/4a757796-11c2-47f1-ae0d-335626e818fd@intel.com/

Reported-by: Xiaoyao Li <xiaoyao.li@intel.com>
Closes: https://lore.kernel.org/qemu-devel/4a757796-11c2-47f1-ae0d-335626e818fd@intel.com/
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Xiaoyao Li <xiaoyao.li@intel.com>
Message-ID: <20250611001018.2179964-1-xiaoyao.li@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/mmu/mmu.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index cbc84c6abc2e..a4040578b537 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -4896,6 +4896,7 @@ long kvm_arch_vcpu_pre_fault_memory(struct kvm_vcpu *vcpu,
 {
 	u64 error_code = PFERR_GUEST_FINAL_MASK;
 	u8 level = PG_LEVEL_4K;
+	u64 direct_bits;
 	u64 end;
 	int r;
 
@@ -4910,15 +4911,18 @@ long kvm_arch_vcpu_pre_fault_memory(struct kvm_vcpu *vcpu,
 	if (r)
 		return r;
 
+	direct_bits = 0;
 	if (kvm_arch_has_private_mem(vcpu->kvm) &&
 	    kvm_mem_is_private(vcpu->kvm, gpa_to_gfn(range->gpa)))
 		error_code |= PFERR_PRIVATE_ACCESS;
+	else
+		direct_bits = gfn_to_gpa(kvm_gfn_direct_bits(vcpu->kvm));
 
 	/*
 	 * Shadow paging uses GVA for kvm page fault, so restrict to
 	 * two-dimensional paging.
 	 */
-	r = kvm_tdp_map_page(vcpu, range->gpa, error_code, &level);
+	r = kvm_tdp_map_page(vcpu, range->gpa | direct_bits, error_code, &level);
 	if (r < 0)
 		return r;
 

From 8046d29dde17002523f94d3e6e0ebe486ce52166 Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Thu, 12 Jun 2025 00:47:44 -0400
Subject: [PATCH 0270/1334] KVM: x86/mmu: Reject direct bits in gpa passed to
 KVM_PRE_FAULT_MEMORY

Only let userspace pass the same addresses that were used in KVM_SET_USER_MEMORY_REGION
(or KVM_SET_USER_MEMORY_REGION2); gpas in the the upper half of the address space
are an implementation detail of TDX and KVM.

Extracted from a patch by Sean Christopherson <seanjc@google.com>.

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/mmu/mmu.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index a4040578b537..4e06e2e89a8f 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -4903,6 +4903,9 @@ long kvm_arch_vcpu_pre_fault_memory(struct kvm_vcpu *vcpu,
 	if (!vcpu->kvm->arch.pre_fault_allowed)
 		return -EOPNOTSUPP;
 
+	if (kvm_is_gfn_alias(vcpu->kvm, gpa_to_gfn(range->gpa)))
+		return -EINVAL;
+
 	/*
 	 * reload is efficient when called repeatedly, so we can do it on
 	 * every iteration.

From 33db8c97b4cfa0328054fb755dfbcd6e7f3c7a9d Mon Sep 17 00:00:00 2001
From: Viresh Kumar <viresh.kumar@linaro.org>
Date: Mon, 9 Jun 2025 14:26:54 +0530
Subject: [PATCH 0271/1334] rust: Use CpuId in place of raw CPU numbers
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Use the newly defined `CpuId` abstraction instead of raw CPU numbers.

This also fixes a doctest failure for configurations where `nr_cpu_ids <
4`.

The C `cpumask_{set|clear}_cpu()` APIs emit a warning when given an
invalid CPU number — but only if `CONFIG_DEBUG_PER_CPU_MAPS=y` is set.

Meanwhile, `cpumask_weight()` only considers CPUs up to `nr_cpu_ids`,
which can cause inconsistencies: a CPU number greater than `nr_cpu_ids`
may be set in the mask, yet the weight calculation won't reflect it.

This leads to doctest failures when `nr_cpu_ids < 4`, as the test tries
to set CPUs 2 and 3:

  rust_doctest_kernel_cpumask_rs_0.location: rust/kernel/cpumask.rs:180
  rust_doctest_kernel_cpumask_rs_0: ASSERTION FAILED at rust/kernel/cpumask.rs:190

Fixes: 8961b8cb3099 ("rust: cpumask: Add initial abstractions")
Reported-by: Miguel Ojeda <ojeda@kernel.org>
Closes: https://lore.kernel.org/rust-for-linux/CANiq72k3ozKkLMinTLQwvkyg9K=BeRxs1oYZSKhJHY-veEyZdg@mail.gmail.com/
Reported-by: Andreas Hindborg <a.hindborg@kernel.org>
Closes: https://lore.kernel.org/all/87qzzy3ric.fsf@kernel.org/
Suggested-by: Boqun Feng <boqun.feng@gmail.com>
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Reviewed-by: Boqun Feng <boqun.feng@gmail.com>
---
 drivers/cpufreq/rcpufreq_dt.rs |  4 +--
 rust/kernel/cpu.rs             |  4 +--
 rust/kernel/cpufreq.rs         | 27 ++++++++++++------
 rust/kernel/cpumask.rs         | 51 ++++++++++++++++++++++++----------
 4 files changed, 59 insertions(+), 27 deletions(-)

diff --git a/drivers/cpufreq/rcpufreq_dt.rs b/drivers/cpufreq/rcpufreq_dt.rs
index 94ed81644fe1..43c87d0259b6 100644
--- a/drivers/cpufreq/rcpufreq_dt.rs
+++ b/drivers/cpufreq/rcpufreq_dt.rs
@@ -26,9 +26,9 @@ fn find_supply_name_exact(dev: &Device, name: &str) -> Option<CString> {
 }
 
 /// Finds supply name for the CPU from DT.
-fn find_supply_names(dev: &Device, cpu: u32) -> Option<KVec<CString>> {
+fn find_supply_names(dev: &Device, cpu: cpu::CpuId) -> Option<KVec<CString>> {
     // Try "cpu0" for older DTs, fallback to "cpu".
-    let name = (cpu == 0)
+    let name = (cpu.as_u32() == 0)
         .then(|| find_supply_name_exact(dev, "cpu0"))
         .flatten()
         .or_else(|| find_supply_name_exact(dev, "cpu"))?;
diff --git a/rust/kernel/cpu.rs b/rust/kernel/cpu.rs
index 6a3aecb12468..abc780d7a8ec 100644
--- a/rust/kernel/cpu.rs
+++ b/rust/kernel/cpu.rs
@@ -127,9 +127,9 @@ impl From<CpuId> for i32 {
 /// Callers must ensure that the CPU device is not used after it has been unregistered.
 /// This can be achieved, for example, by registering a CPU hotplug notifier and removing
 /// any references to the CPU device within the notifier's callback.
-pub unsafe fn from_cpu(cpu: u32) -> Result<&'static Device> {
+pub unsafe fn from_cpu(cpu: CpuId) -> Result<&'static Device> {
     // SAFETY: It is safe to call `get_cpu_device()` for any CPU.
-    let ptr = unsafe { bindings::get_cpu_device(cpu) };
+    let ptr = unsafe { bindings::get_cpu_device(u32::from(cpu)) };
     if ptr.is_null() {
         return Err(ENODEV);
     }
diff --git a/rust/kernel/cpufreq.rs b/rust/kernel/cpufreq.rs
index 9b995f18aac6..11b03e9d7e89 100644
--- a/rust/kernel/cpufreq.rs
+++ b/rust/kernel/cpufreq.rs
@@ -10,6 +10,7 @@
 
 use crate::{
     clk::Hertz,
+    cpu::CpuId,
     cpumask,
     device::{Bound, Device},
     devres::Devres,
@@ -465,8 +466,9 @@ impl Policy {
 
     /// Returns the primary CPU for the [`Policy`].
     #[inline]
-    pub fn cpu(&self) -> u32 {
-        self.as_ref().cpu
+    pub fn cpu(&self) -> CpuId {
+        // SAFETY: The C API guarantees that `cpu` refers to a valid CPU number.
+        unsafe { CpuId::from_u32_unchecked(self.as_ref().cpu) }
     }
 
     /// Returns the minimum frequency for the [`Policy`].
@@ -525,7 +527,7 @@ impl Policy {
     #[inline]
     pub fn generic_get(&self) -> Result<u32> {
         // SAFETY: By the type invariant, the pointer stored in `self` is valid.
-        Ok(unsafe { bindings::cpufreq_generic_get(self.cpu()) })
+        Ok(unsafe { bindings::cpufreq_generic_get(u32::from(self.cpu())) })
     }
 
     /// Provides a wrapper to the register with energy model using the OPP core.
@@ -678,9 +680,9 @@ impl Policy {
 struct PolicyCpu<'a>(&'a mut Policy);
 
 impl<'a> PolicyCpu<'a> {
-    fn from_cpu(cpu: u32) -> Result<Self> {
+    fn from_cpu(cpu: CpuId) -> Result<Self> {
         // SAFETY: It is safe to call `cpufreq_cpu_get` for any valid CPU.
-        let ptr = from_err_ptr(unsafe { bindings::cpufreq_cpu_get(cpu) })?;
+        let ptr = from_err_ptr(unsafe { bindings::cpufreq_cpu_get(u32::from(cpu)) })?;
 
         Ok(Self(
             // SAFETY: The `ptr` is guaranteed to be valid and remains valid for the lifetime of
@@ -1266,7 +1268,10 @@ impl<T: Driver> Registration<T> {
         target_perf: usize,
         capacity: usize,
     ) {
-        if let Ok(mut policy) = PolicyCpu::from_cpu(cpu) {
+        // SAFETY: The C API guarantees that `cpu` refers to a valid CPU number.
+        let cpu_id = unsafe { CpuId::from_u32_unchecked(cpu) };
+
+        if let Ok(mut policy) = PolicyCpu::from_cpu(cpu_id) {
             T::adjust_perf(&mut policy, min_perf, target_perf, capacity);
         }
     }
@@ -1321,7 +1326,10 @@ impl<T: Driver> Registration<T> {
     ///
     /// - This function may only be called from the cpufreq C infrastructure.
     unsafe extern "C" fn get_callback(cpu: u32) -> kernel::ffi::c_uint {
-        PolicyCpu::from_cpu(cpu).map_or(0, |mut policy| T::get(&mut policy).map_or(0, |f| f))
+        // SAFETY: The C API guarantees that `cpu` refers to a valid CPU number.
+        let cpu_id = unsafe { CpuId::from_u32_unchecked(cpu) };
+
+        PolicyCpu::from_cpu(cpu_id).map_or(0, |mut policy| T::get(&mut policy).map_or(0, |f| f))
     }
 
     /// Driver's `update_limit` callback.
@@ -1344,8 +1352,11 @@ impl<T: Driver> Registration<T> {
     /// - This function may only be called from the cpufreq C infrastructure.
     /// - The pointer arguments must be valid pointers.
     unsafe extern "C" fn bios_limit_callback(cpu: i32, limit: *mut u32) -> kernel::ffi::c_int {
+        // SAFETY: The C API guarantees that `cpu` refers to a valid CPU number.
+        let cpu_id = unsafe { CpuId::from_i32_unchecked(cpu) };
+
         from_result(|| {
-            let mut policy = PolicyCpu::from_cpu(cpu as u32)?;
+            let mut policy = PolicyCpu::from_cpu(cpu_id)?;
 
             // SAFETY: `limit` is guaranteed by the C code to be valid.
             T::bios_limit(&mut policy, &mut (unsafe { *limit })).map(|()| 0)
diff --git a/rust/kernel/cpumask.rs b/rust/kernel/cpumask.rs
index c90bfac9346a..19c607709b5f 100644
--- a/rust/kernel/cpumask.rs
+++ b/rust/kernel/cpumask.rs
@@ -6,6 +6,7 @@
 
 use crate::{
     alloc::{AllocError, Flags},
+    cpu::CpuId,
     prelude::*,
     types::Opaque,
 };
@@ -35,9 +36,10 @@ use core::ops::{Deref, DerefMut};
 ///
 /// ```
 /// use kernel::bindings;
+/// use kernel::cpu::CpuId;
 /// use kernel::cpumask::Cpumask;
 ///
-/// fn set_clear_cpu(ptr: *mut bindings::cpumask, set_cpu: u32, clear_cpu: i32) {
+/// fn set_clear_cpu(ptr: *mut bindings::cpumask, set_cpu: CpuId, clear_cpu: CpuId) {
 ///     // SAFETY: The `ptr` is valid for writing and remains valid for the lifetime of the
 ///     // returned reference.
 ///     let mask = unsafe { Cpumask::as_mut_ref(ptr) };
@@ -90,9 +92,9 @@ impl Cpumask {
     /// This mismatches kernel naming convention and corresponds to the C
     /// function `__cpumask_set_cpu()`.
     #[inline]
-    pub fn set(&mut self, cpu: u32) {
+    pub fn set(&mut self, cpu: CpuId) {
         // SAFETY: By the type invariant, `self.as_raw` is a valid argument to `__cpumask_set_cpu`.
-        unsafe { bindings::__cpumask_set_cpu(cpu, self.as_raw()) };
+        unsafe { bindings::__cpumask_set_cpu(u32::from(cpu), self.as_raw()) };
     }
 
     /// Clear `cpu` in the cpumask.
@@ -101,19 +103,19 @@ impl Cpumask {
     /// This mismatches kernel naming convention and corresponds to the C
     /// function `__cpumask_clear_cpu()`.
     #[inline]
-    pub fn clear(&mut self, cpu: i32) {
+    pub fn clear(&mut self, cpu: CpuId) {
         // SAFETY: By the type invariant, `self.as_raw` is a valid argument to
         // `__cpumask_clear_cpu`.
-        unsafe { bindings::__cpumask_clear_cpu(cpu, self.as_raw()) };
+        unsafe { bindings::__cpumask_clear_cpu(i32::from(cpu), self.as_raw()) };
     }
 
     /// Test `cpu` in the cpumask.
     ///
     /// Equivalent to the kernel's `cpumask_test_cpu` API.
     #[inline]
-    pub fn test(&self, cpu: i32) -> bool {
+    pub fn test(&self, cpu: CpuId) -> bool {
         // SAFETY: By the type invariant, `self.as_raw` is a valid argument to `cpumask_test_cpu`.
-        unsafe { bindings::cpumask_test_cpu(cpu, self.as_raw()) }
+        unsafe { bindings::cpumask_test_cpu(i32::from(cpu), self.as_raw()) }
     }
 
     /// Set all CPUs in the cpumask.
@@ -178,21 +180,40 @@ impl Cpumask {
 /// The following example demonstrates how to create and update a [`CpumaskVar`].
 ///
 /// ```
+/// use kernel::cpu::CpuId;
 /// use kernel::cpumask::CpumaskVar;
 ///
 /// let mut mask = CpumaskVar::new_zero(GFP_KERNEL).unwrap();
 ///
 /// assert!(mask.empty());
-/// mask.set(2);
-/// assert!(mask.test(2));
-/// mask.set(3);
-/// assert!(mask.test(3));
-/// assert_eq!(mask.weight(), 2);
+/// let mut count = 0;
+///
+/// let cpu2 = CpuId::from_u32(2);
+/// if let Some(cpu) = cpu2 {
+///     mask.set(cpu);
+///     assert!(mask.test(cpu));
+///     count += 1;
+/// }
+///
+/// let cpu3 = CpuId::from_u32(3);
+/// if let Some(cpu) = cpu3 {
+///     mask.set(cpu);
+///     assert!(mask.test(cpu));
+///     count += 1;
+/// }
+///
+/// assert_eq!(mask.weight(), count);
 ///
 /// let mask2 = CpumaskVar::try_clone(&mask).unwrap();
-/// assert!(mask2.test(2));
-/// assert!(mask2.test(3));
-/// assert_eq!(mask2.weight(), 2);
+///
+/// if let Some(cpu) = cpu2 {
+///     assert!(mask2.test(cpu));
+/// }
+///
+/// if let Some(cpu) = cpu3 {
+///     assert!(mask2.test(cpu));
+/// }
+/// assert_eq!(mask2.weight(), count);
 /// ```
 pub struct CpumaskVar {
     #[cfg(CONFIG_CPUMASK_OFFSTACK)]

From c7f005f70d22cd5613cac30bf6d34867189e36a9 Mon Sep 17 00:00:00 2001
From: Viresh Kumar <viresh.kumar@linaro.org>
Date: Mon, 9 Jun 2025 16:44:16 +0530
Subject: [PATCH 0272/1334] rust: cpu: Add CpuId::current() to retrieve current
 CPU ID

Introduce `CpuId::current()`, a constructor that wraps the C function
`raw_smp_processor_id()` to retrieve the current CPU identifier without
guaranteeing stability.

This function should be used only when the caller can ensure that
the CPU ID won't change unexpectedly due to preemption or migration.

Suggested-by: Boqun Feng <boqun.feng@gmail.com>
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Reviewed-by: Boqun Feng <boqun.feng@gmail.com>
---
 MAINTAINERS            |  1 +
 rust/helpers/cpu.c     |  8 ++++++++
 rust/helpers/helpers.c |  1 +
 rust/kernel/cpu.rs     | 11 +++++++++++
 4 files changed, 21 insertions(+)
 create mode 100644 rust/helpers/cpu.c

diff --git a/MAINTAINERS b/MAINTAINERS
index a92290fffa16..4255186784c4 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -6254,6 +6254,7 @@ F:	include/linux/cpuhotplug.h
 F:	include/linux/smpboot.h
 F:	kernel/cpu.c
 F:	kernel/smpboot.*
+F:	rust/helper/cpu.c
 F:	rust/kernel/cpu.rs
 
 CPU IDLE TIME MANAGEMENT FRAMEWORK
diff --git a/rust/helpers/cpu.c b/rust/helpers/cpu.c
new file mode 100644
index 000000000000..824e0adb19d4
--- /dev/null
+++ b/rust/helpers/cpu.c
@@ -0,0 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/smp.h>
+
+unsigned int rust_helper_raw_smp_processor_id(void)
+{
+	return raw_smp_processor_id();
+}
diff --git a/rust/helpers/helpers.c b/rust/helpers/helpers.c
index 0f1b5d115985..16fa9bca5949 100644
--- a/rust/helpers/helpers.c
+++ b/rust/helpers/helpers.c
@@ -13,6 +13,7 @@
 #include "build_assert.c"
 #include "build_bug.c"
 #include "clk.c"
+#include "cpu.c"
 #include "cpufreq.c"
 #include "cpumask.c"
 #include "cred.c"
diff --git a/rust/kernel/cpu.rs b/rust/kernel/cpu.rs
index abc780d7a8ec..b75403b0eb56 100644
--- a/rust/kernel/cpu.rs
+++ b/rust/kernel/cpu.rs
@@ -102,6 +102,17 @@ impl CpuId {
     pub fn as_u32(&self) -> u32 {
         self.0
     }
+
+    /// Returns the ID of the CPU the code is currently running on.
+    ///
+    /// The returned value is considered unstable because it may change
+    /// unexpectedly due to preemption or CPU migration. It should only be
+    /// used when the context ensures that the task remains on the same CPU
+    /// or the users could use a stale (yet valid) CPU ID.
+    pub fn current() -> Self {
+        // SAFETY: raw_smp_processor_id() always returns a valid CPU ID.
+        unsafe { Self::from_u32_unchecked(bindings::raw_smp_processor_id()) }
+    }
 }
 
 impl From<CpuId> for u32 {

From b1a529bdb9641392b4f5fc91545598793c0b3b96 Mon Sep 17 00:00:00 2001
From: Mark Brown <broonie@kernel.org>
Date: Thu, 5 Jun 2025 22:34:31 +0100
Subject: [PATCH 0273/1334] selftests/mm: skip failed memfd setups in
 gup_longterm

Unlike the other cases gup_longterm's memfd tests previously skipped the
test when failing to set up the file descriptor to test.  Restore this
behavior to avoid hitting failures when hugetlb isn't configured.

Link: https://lkml.kernel.org/r/20250605-selftest-mm-gup-longterm-tweaks-v1-1-2fae34b05958@kernel.org
Fixes: 66bce7afbaca ("selftests/mm: fix test result reporting in gup_longterm")
Signed-off-by: Mark Brown <broonie@kernel.org>
Reported-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Closes: https://lkml.kernel.org/r/a76fc252-0fe3-4d4b-a9a1-4a2895c2680d@lucifer.local
Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Tested-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Acked-by: David Hildenbrand <david@redhat.com>
Cc: Shuah Khan <shuah@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 tools/testing/selftests/mm/gup_longterm.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/mm/gup_longterm.c b/tools/testing/selftests/mm/gup_longterm.c
index 8a97ac5176a4..29047d2e0c49 100644
--- a/tools/testing/selftests/mm/gup_longterm.c
+++ b/tools/testing/selftests/mm/gup_longterm.c
@@ -298,8 +298,11 @@ static void run_with_memfd(test_fn fn, const char *desc)
 	log_test_start("%s ... with memfd", desc);
 
 	fd = memfd_create("test", 0);
-	if (fd < 0)
+	if (fd < 0) {
 		ksft_print_msg("memfd_create() failed (%s)\n", strerror(errno));
+		log_test_result(KSFT_SKIP);
+		return;
+	}
 
 	fn(fd, pagesize);
 	close(fd);
@@ -366,6 +369,8 @@ static void run_with_memfd_hugetlb(test_fn fn, const char *desc,
 	fd = memfd_create("test", flags);
 	if (fd < 0) {
 		ksft_print_msg("memfd_create() failed (%s)\n", strerror(errno));
+		log_test_result(KSFT_SKIP);
+		return;
 	}
 
 	fn(fd, hugetlbsize);

From 331843c845d15413e9d89fd91cdcfa6912e291c3 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Wed, 4 Jun 2025 17:23:37 -0700
Subject: [PATCH 0274/1334] scatterlist: fix extraneous '@'-sign kernel-doc
 notation

Using "@argname@" in kernel-doc produces "argname****" (with "argname" in
bold) in the generated html output, so use the expected kernel-doc
notation of just "@argname" instead.

"Fixes:" lines are added in case Matthew's patch [1] is backported.

Link: https://lkml.kernel.org/r/20250605002337.2842659-1-rdunlap@infradead.org
Link: https://lore.kernel.org/linux-doc/3bc4e779-7a79-42c1-8867-024f643a22fc@infradead.org/T/#m5d2bd9d21fb34f297aa4e7db069f09bc27b89007 [1]
Fixes: 0db9299f48eb ("SG: Move functions to lib/scatterlist.c and add sg chaining allocator helpers")
Fixes: 8d1d4b538bb1 ("scatterlist: inline sg_next()")
Fixes: 18dabf473e15 ("Change table chaining layout")
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Reviewed-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/scatterlist.h | 4 ++--
 lib/scatterlist.c           | 8 ++++----
 2 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/include/linux/scatterlist.h b/include/linux/scatterlist.h
index 0cdbfc42f153..6f8a4965f9b9 100644
--- a/include/linux/scatterlist.h
+++ b/include/linux/scatterlist.h
@@ -99,7 +99,7 @@ static inline bool sg_is_last(struct scatterlist *sg)
  * @sg:		The current sg entry
  *
  * Description:
- *   Usually the next entry will be @sg@ + 1, but if this sg element is part
+ *   Usually the next entry will be @sg + 1, but if this sg element is part
  *   of a chained scatterlist, it could jump to the start of a new
  *   scatterlist array.
  *
@@ -254,7 +254,7 @@ static inline void __sg_chain(struct scatterlist *chain_sg,
  * @sgl:	Second scatterlist
  *
  * Description:
- *   Links @prv@ and @sgl@ together, to form a longer scatterlist.
+ *   Links @prv and @sgl together, to form a longer scatterlist.
  *
  **/
 static inline void sg_chain(struct scatterlist *prv, unsigned int prv_nents,
diff --git a/lib/scatterlist.c b/lib/scatterlist.c
index 7582dfab7fe3..4af1c8b0775a 100644
--- a/lib/scatterlist.c
+++ b/lib/scatterlist.c
@@ -73,9 +73,9 @@ EXPORT_SYMBOL(sg_nents_for_len);
  *   Should only be used casually, it (currently) scans the entire list
  *   to get the last entry.
  *
- *   Note that the @sgl@ pointer passed in need not be the first one,
- *   the important bit is that @nents@ denotes the number of entries that
- *   exist from @sgl@.
+ *   Note that the @sgl pointer passed in need not be the first one,
+ *   the important bit is that @nents denotes the number of entries that
+ *   exist from @sgl.
  *
  **/
 struct scatterlist *sg_last(struct scatterlist *sgl, unsigned int nents)
@@ -345,7 +345,7 @@ EXPORT_SYMBOL(__sg_alloc_table);
  * @gfp_mask:	GFP allocation mask
  *
  *  Description:
- *    Allocate and initialize an sg table. If @nents@ is larger than
+ *    Allocate and initialize an sg table. If @nents is larger than
  *    SG_MAX_SINGLE_ALLOC a chained sg table will be setup.
  *
  **/

From 1b8e4091ffb4655c761354eb33f41b618e809427 Mon Sep 17 00:00:00 2001
From: wangfushuai <wangfushuai@baidu.com>
Date: Sat, 7 Jun 2025 23:36:14 +0800
Subject: [PATCH 0275/1334] docs: proc: update VmFlags documentation in smaps

Remove outdated VM_DENYWRITE("dw") reference and add missing
VM_LOCKONFAULT("lf") and VM_UFFD_MINOR("ui") flags.

[akpm@linux-foundation.org: add "dp" (VM_DROPPABLE), per Tal]
Link: https://lkml.kernel.org/r/20250607153614.81914-1-wangfushuai@baidu.com
Signed-off-by: wangfushuai <wangfushuai@baidu.com>
Cc: Andrii Nakryiko <andrii@kernel.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Mariano Pache <npache@redhat.com>
Cc: xu xin <xu.xin16@zte.com.cn>
Cc: Tal Zussman <tz2294@columbia.edu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 Documentation/filesystems/proc.rst | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/Documentation/filesystems/proc.rst b/Documentation/filesystems/proc.rst
index 2a17865dfe39..5236cb52e357 100644
--- a/Documentation/filesystems/proc.rst
+++ b/Documentation/filesystems/proc.rst
@@ -584,7 +584,6 @@ encoded manner. The codes are the following:
     ms    may share
     gd    stack segment growns down
     pf    pure PFN range
-    dw    disabled write to the mapped file
     lo    pages are locked in memory
     io    memory mapped I/O area
     sr    sequential read advise provided
@@ -607,8 +606,11 @@ encoded manner. The codes are the following:
     mt    arm64 MTE allocation tags are enabled
     um    userfaultfd missing tracking
     uw    userfaultfd wr-protect tracking
+    ui    userfaultfd minor fault
     ss    shadow/guarded control stack page
     sl    sealed
+    lf    lock on fault pages
+    dp    always lazily freeable mapping
     ==    =======================================
 
 Note that there is no guarantee that every flag and associated mnemonic will

From 0cf4b1687a187ba9247c71721d8b064634eda1f7 Mon Sep 17 00:00:00 2001
From: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Date: Fri, 6 Jun 2025 13:50:32 +0100
Subject: [PATCH 0276/1334] mm/vma: reset VMA iterator on commit_merge() OOM
 failure

While an OOM failure in commit_merge() isn't really feasible due to the
allocation which might fail (a maple tree pre-allocation) being 'too small
to fail', we do need to handle this case correctly regardless.

In vma_merge_existing_range(), we can theoretically encounter failures
which result in an OOM error in two ways - firstly dup_anon_vma() might
fail with an OOM error, and secondly commit_merge() failing, ultimately,
to pre-allocate a maple tree node.

The abort logic for dup_anon_vma() resets the VMA iterator to the initial
range, ensuring that any logic looping on this iterator will correctly
proceed to the next VMA.

However the commit_merge() abort logic does not do the same thing.  This
resulted in a syzbot report occurring because mlockall() iterates through
VMAs, is tolerant of errors, but ended up with an incorrect previous VMA
being specified due to incorrect iterator state.

While making this change, it became apparent we are duplicating logic -
the logic introduced in commit 41e6ddcaa0f1 ("mm/vma: add give_up_on_oom
option on modify/merge, use in uffd release") duplicates the
vmg->give_up_on_oom check in both abort branches.

Additionally, we observe that we can perform the anon_dup check safely on
dup_anon_vma() failure, as this will not be modified should this call
fail.

Finally, we need to reset the iterator in both cases, so now we can simply
use the exact same code to abort for both.

We remove the VM_WARN_ON(err != -ENOMEM) as it would be silly for this to
be otherwise and it allows us to implement the abort check more neatly.

Link: https://lkml.kernel.org/r/20250606125032.164249-1-lorenzo.stoakes@oracle.com
Fixes: 47b16d0462a4 ("mm: abort vma_modify() on merge out of memory failure")
Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Reported-by: syzbot+d16409ea9ecc16ed261a@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/linux-mm/6842cc67.a00a0220.29ac89.003b.GAE@google.com/
Reviewed-by: Pedro Falcato <pfalcato@suse.de>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Liam R. Howlett <Liam.Howlett@oracle.com>
Cc: Jann Horn <jannh@google.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/vma.c | 22 ++++------------------
 1 file changed, 4 insertions(+), 18 deletions(-)

diff --git a/mm/vma.c b/mm/vma.c
index 726b2a31ce59..0fb9b2c7b734 100644
--- a/mm/vma.c
+++ b/mm/vma.c
@@ -967,26 +967,9 @@ static __must_check struct vm_area_struct *vma_merge_existing_range(
 		err = dup_anon_vma(next, middle, &anon_dup);
 	}
 
-	if (err)
+	if (err || commit_merge(vmg))
 		goto abort;
 
-	err = commit_merge(vmg);
-	if (err) {
-		VM_WARN_ON(err != -ENOMEM);
-
-		if (anon_dup)
-			unlink_anon_vmas(anon_dup);
-
-		/*
-		 * We've cleaned up any cloned anon_vma's, no VMAs have been
-		 * modified, no harm no foul if the user requests that we not
-		 * report this and just give up, leaving the VMAs unmerged.
-		 */
-		if (!vmg->give_up_on_oom)
-			vmg->state = VMA_MERGE_ERROR_NOMEM;
-		return NULL;
-	}
-
 	khugepaged_enter_vma(vmg->target, vmg->flags);
 	vmg->state = VMA_MERGE_SUCCESS;
 	return vmg->target;
@@ -995,6 +978,9 @@ abort:
 	vma_iter_set(vmg->vmi, start);
 	vma_iter_load(vmg->vmi);
 
+	if (anon_dup)
+		unlink_anon_vmas(anon_dup);
+
 	/*
 	 * This means we have failed to clone anon_vma's correctly, but no
 	 * actual changes to VMAs have occurred, so no harm no foul - if the

From 383c4613c67c26e90e8eebb72e3083457d02033f Mon Sep 17 00:00:00 2001
From: Ryan Roberts <ryan.roberts@arm.com>
Date: Fri, 6 Jun 2025 10:28:07 +0100
Subject: [PATCH 0277/1334] mm: close theoretical race where stale TLB entries
 could linger

Commit 3ea277194daa ("mm, mprotect: flush TLB if potentially racing with a
parallel reclaim leaving stale TLB entries") described a theoretical race
as such:


"""
Nadav Amit identified a theoretical race between page reclaim and mprotect
due to TLB flushes being batched outside of the PTL being held.

He described the race as follows:

	CPU0                            CPU1
	----                            ----
					user accesses memory using RW PTE
					[PTE now cached in TLB]
	try_to_unmap_one()
	==> ptep_get_and_clear()
	==> set_tlb_ubc_flush_pending()
					mprotect(addr, PROT_READ)
					==> change_pte_range()
					==> [ PTE non-present - no flush ]

					user writes using cached RW PTE
	...

	try_to_unmap_flush()

The same type of race exists for reads when protecting for PROT_NONE and
also exists for operations that can leave an old TLB entry behind such as
munmap, mremap and madvise.
"""

The solution was to introduce flush_tlb_batched_pending() and call it
under the PTL from mprotect/madvise/munmap/mremap to complete any pending
tlb flushes.

However, while madvise_free_pte_range() and
madvise_cold_or_pageout_pte_range() were both retro-fitted to call
flush_tlb_batched_pending() immediately after initially acquiring the PTL,
they both temporarily release the PTL to split a large folio if they
stumble upon one.  In this case, where re-acquiring the PTL
flush_tlb_batched_pending() must be called again, but it previously was
not.  Let's fix that.

There are 2 Fixes: tags here: the first is the commit that fixed
madvise_free_pte_range().  The second is the commit that added
madvise_cold_or_pageout_pte_range(), which looks like it copy/pasted the
faulty pattern from madvise_free_pte_range().

This is a theoretical bug discovered during code review.

Link: https://lkml.kernel.org/r/20250606092809.4194056-1-ryan.roberts@arm.com
Fixes: 3ea277194daa ("mm, mprotect: flush TLB if potentially racing with a parallel reclaim leaving stale TLB entries")
Fixes: 9c276cc65a58 ("mm: introduce MADV_COLD")
Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>
Reviewed-by: Jann Horn <jannh@google.com>
Acked-by: David Hildenbrand <david@redhat.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Mel Gorman <mgorman <mgorman@suse.de>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/madvise.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/mm/madvise.c b/mm/madvise.c
index 5f7a66a1617e..1d44a35ae85c 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -508,6 +508,7 @@ restart:
 					pte_offset_map_lock(mm, pmd, addr, &ptl);
 				if (!start_pte)
 					break;
+				flush_tlb_batched_pending(mm);
 				arch_enter_lazy_mmu_mode();
 				if (!err)
 					nr = 0;
@@ -741,6 +742,7 @@ static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr,
 				start_pte = pte;
 				if (!start_pte)
 					break;
+				flush_tlb_batched_pending(mm);
 				arch_enter_lazy_mmu_mode();
 				if (!err)
 					nr = 0;

From 50695153d7ddde3b1696dbf0085be0033bf3ddb3 Mon Sep 17 00:00:00 2001
From: Andrew Morton <akpm@linux-foundation.org>
Date: Sat, 7 Jun 2025 17:43:18 -0700
Subject: [PATCH 0278/1334] drivers/rapidio/rio_cm.c: prevent possible heap
 overwrite

In

riocm_cdev_ioctl(RIO_CM_CHAN_SEND)
   -> cm_chan_msg_send()
      -> riocm_ch_send()

cm_chan_msg_send() checks that userspace didn't send too much data but
riocm_ch_send() failed to check that userspace sent sufficient data.  The
result is that riocm_ch_send() can write to fields in the rio_ch_chan_hdr
which were outside the bounds of the space which cm_chan_msg_send()
allocated.

Address this by teaching riocm_ch_send() to check that the entire
rio_ch_chan_hdr was copied in from userspace.

Reported-by: maher azz <maherazz04@gmail.com>
Cc: Matt Porter <mporter@kernel.crashing.org>
Cc: Alexandre Bounine <alex.bou9@gmail.com>
Cc: Linus Torvalds <torvalds@linuxfoundation.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 drivers/rapidio/rio_cm.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/rapidio/rio_cm.c b/drivers/rapidio/rio_cm.c
index 97287e838ce1..66464674223f 100644
--- a/drivers/rapidio/rio_cm.c
+++ b/drivers/rapidio/rio_cm.c
@@ -783,6 +783,9 @@ static int riocm_ch_send(u16 ch_id, void *buf, int len)
 	if (buf == NULL || ch_id == 0 || len == 0 || len > RIO_MAX_MSG_SIZE)
 		return -EINVAL;
 
+	if (len < sizeof(struct rio_ch_chan_hdr))
+		return -EINVAL;		/* insufficient data from user */
+
 	ch = riocm_get_channel(ch_id);
 	if (!ch) {
 		riocm_error("%s(%d) ch_%d not found", current->comm,

From 02fb36505c61c35d5fd879f5a66a97935dbcb2ee Mon Sep 17 00:00:00 2001
From: Barry Song <baohua@kernel.org>
Date: Mon, 9 Jun 2025 12:24:42 +1200
Subject: [PATCH 0279/1334] MAINTAINERS: add Barry as a THP reviewer

I have been actively contributing to mTHP and reviewing related patches
for an extended period, and I would like to continue supporting patch
reviews.

Link: https://lkml.kernel.org/r/20250609002442.1856-1-21cnbao@gmail.com
Signed-off-by: Barry Song <baohua@kernel.org>
Acked-by: Zi Yan <ziy@nvidia.com>
Acked-by: Baolin Wang <baolin.wang@linux.alibaba.com>
Acked-by: Dev Jain <dev.jain@arm.com>
Acked-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Reviewed-by: Ryan Roberts <ryan.roberts@arm.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Liam R. Howlett <Liam.Howlett@oracle.com>
Cc: Nico Pache <npache@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 MAINTAINERS | 1 +
 1 file changed, 1 insertion(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index a92290fffa16..8315c84df075 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -15919,6 +15919,7 @@ R:	Liam R. Howlett <Liam.Howlett@oracle.com>
 R:	Nico Pache <npache@redhat.com>
 R:	Ryan Roberts <ryan.roberts@arm.com>
 R:	Dev Jain <dev.jain@arm.com>
+R:	Barry Song <baohua@kernel.org>
 L:	linux-mm@kvack.org
 S:	Maintained
 W:	http://www.linux-mm.org

From 66ac1a4d366d3faa95fcf6082b555f8d77f1e8db Mon Sep 17 00:00:00 2001
From: Huacai Chen <chenhuacai@loongson.cn>
Date: Sun, 8 Jun 2025 22:12:35 +0800
Subject: [PATCH 0280/1334] init: fix build warnings about export.h

After commit a934a57a42f64a4 ("scripts/misc-check: check missing #include
<linux/export.h> when W=1") and 7d95680d64ac8e836c ("scripts/misc-check:
check unnecessary #include <linux/export.h> when W=1"), we get some build
warnings with W=1:

init/main.c: warning: EXPORT_SYMBOL() is used, but #include <linux/export.h> is missing
init/initramfs.c: warning: EXPORT_SYMBOL() is used, but #include <linux/export.h> is missing

So fix these build warnings for the init code.

Link: https://lkml.kernel.org/r/20250608141235.155206-1-chenhuacai@loongson.cn
Fixes: a934a57a42f6 ("scripts/misc-check: check missing #include <linux/export.h> when W=1")
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
Reviewed-by: Masahiro Yamada <masahiroy@kernel.org>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Jan Kara <jack@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 init/initramfs.c | 1 +
 init/main.c      | 1 +
 2 files changed, 2 insertions(+)

diff --git a/init/initramfs.c b/init/initramfs.c
index 72bad44a1d41..097673b97784 100644
--- a/init/initramfs.c
+++ b/init/initramfs.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/init.h>
 #include <linux/async.h>
+#include <linux/export.h>
 #include <linux/fs.h>
 #include <linux/slab.h>
 #include <linux/types.h>
diff --git a/init/main.c b/init/main.c
index ed576c7f475d..225a58279acd 100644
--- a/init/main.c
+++ b/init/main.c
@@ -13,6 +13,7 @@
 #define DEBUG		/* Enable initcall_debug */
 
 #include <linux/types.h>
+#include <linux/export.h>
 #include <linux/extable.h>
 #include <linux/module.h>
 #include <linux/proc_fs.h>

From aa807b9f22df2eee28593cbbabba0f93f4aa26c1 Mon Sep 17 00:00:00 2001
From: Feng Tang <feng.tang@linux.alibaba.com>
Date: Thu, 12 Jun 2025 10:14:17 +0800
Subject: [PATCH 0281/1334] dma-contiguous: hornor the cma address limit setup
 by user

When porting a cma related usage from x86_64 server to arm64 server,
the "cma=4G@4G" setup failed on arm64. The reason is arm64 and some
other architectures have specific physical address limit for reserved
cma area, like 4GB due to the device's need for 32 bit dma. Actually
lots of platforms of those architectures don't have this device dma
limit, but still have to obey it, and are not able to reserve a huge
cma pool.

This situation could be improved by honoring the user input cma
physical address than the arch limit. As when users specify it, they
already knows what the default is which probably can't suit them.

Suggested-by: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Feng Tang <feng.tang@linux.alibaba.com>
Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>
Link: https://lore.kernel.org/r/20250612021417.44929-1-feng.tang@linux.alibaba.com
---
 kernel/dma/contiguous.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/kernel/dma/contiguous.c b/kernel/dma/contiguous.c
index 8df0dfaaca18..67af8a55185d 100644
--- a/kernel/dma/contiguous.c
+++ b/kernel/dma/contiguous.c
@@ -222,7 +222,10 @@ void __init dma_contiguous_reserve(phys_addr_t limit)
 	if (size_cmdline != -1) {
 		selected_size = size_cmdline;
 		selected_base = base_cmdline;
-		selected_limit = min_not_zero(limit_cmdline, limit);
+
+		/* Hornor the user setup dma address limit */
+		selected_limit = limit_cmdline ?: limit;
+
 		if (base_cmdline + size_cmdline == limit_cmdline)
 			fixed = true;
 	} else {

From 614b1c3cbfb0ecbafd40284d2f8e67c865818714 Mon Sep 17 00:00:00 2001
From: Wolfram Sang <wsa+renesas@sang-engineering.com>
Date: Thu, 12 Jun 2025 09:27:22 +0200
Subject: [PATCH 0282/1334] i2c: use inclusive callbacks in struct
 i2c_algorithm

Convert the I2C subsystem to drop using the 'master_'-prefixed callbacks
in favor of the simplified ones. Fix alignment of '=' while here.

Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
---
 drivers/i2c/algos/i2c-algo-bit.c           |  4 ++--
 drivers/i2c/algos/i2c-algo-pca.c           |  4 ++--
 drivers/i2c/algos/i2c-algo-pcf.c           |  4 ++--
 drivers/i2c/busses/i2c-amd-mp2-plat.c      |  2 +-
 drivers/i2c/busses/i2c-aspeed.c            |  8 ++++----
 drivers/i2c/busses/i2c-at91-master.c       |  4 ++--
 drivers/i2c/busses/i2c-axxia.c             |  2 +-
 drivers/i2c/busses/i2c-bcm-iproc.c         |  2 +-
 drivers/i2c/busses/i2c-cadence.c           | 10 +++++-----
 drivers/i2c/busses/i2c-cgbc.c              |  4 ++--
 drivers/i2c/busses/i2c-eg20t.c             |  2 +-
 drivers/i2c/busses/i2c-emev2.c             |  6 +++---
 drivers/i2c/busses/i2c-exynos5.c           |  6 +++---
 drivers/i2c/busses/i2c-gxp.c               |  6 +++---
 drivers/i2c/busses/i2c-img-scb.c           |  2 +-
 drivers/i2c/busses/i2c-imx-lpi2c.c         |  8 ++++----
 drivers/i2c/busses/i2c-imx.c               |  8 ++++----
 drivers/i2c/busses/i2c-keba.c              |  2 +-
 drivers/i2c/busses/i2c-mchp-pci1xxxx.c     |  2 +-
 drivers/i2c/busses/i2c-meson.c             |  4 ++--
 drivers/i2c/busses/i2c-microchip-corei2c.c |  2 +-
 drivers/i2c/busses/i2c-mt65xx.c            |  2 +-
 drivers/i2c/busses/i2c-mxs.c               |  2 +-
 drivers/i2c/busses/i2c-nomadik.c           |  4 ++--
 drivers/i2c/busses/i2c-npcm7xx.c           |  6 +++---
 drivers/i2c/busses/i2c-omap.c              |  6 +++---
 drivers/i2c/busses/i2c-pnx.c               |  2 +-
 drivers/i2c/busses/i2c-pxa.c               | 16 ++++++++--------
 drivers/i2c/busses/i2c-qcom-cci.c          |  4 ++--
 drivers/i2c/busses/i2c-qcom-geni.c         |  4 ++--
 drivers/i2c/busses/i2c-qup.c               |  8 ++++----
 drivers/i2c/busses/i2c-rcar.c              | 10 +++++-----
 drivers/i2c/busses/i2c-s3c2410.c           |  6 +++---
 drivers/i2c/busses/i2c-sh7760.c            |  4 ++--
 drivers/i2c/busses/i2c-sh_mobile.c         |  4 ++--
 drivers/i2c/busses/i2c-stm32f7.c           |  4 ++--
 drivers/i2c/busses/i2c-synquacer.c         |  4 ++--
 drivers/i2c/busses/i2c-tegra.c             |  6 +++---
 drivers/i2c/busses/i2c-xiic.c              |  4 ++--
 drivers/i2c/busses/i2c-xlp9xx.c            |  2 +-
 drivers/i2c/i2c-atr.c                      |  2 +-
 drivers/i2c/i2c-mux.c                      |  6 +++---
 drivers/i2c/muxes/i2c-demux-pinctrl.c      |  4 ++--
 43 files changed, 101 insertions(+), 101 deletions(-)

diff --git a/drivers/i2c/algos/i2c-algo-bit.c b/drivers/i2c/algos/i2c-algo-bit.c
index eddf25b90ca8..6544d27e4419 100644
--- a/drivers/i2c/algos/i2c-algo-bit.c
+++ b/drivers/i2c/algos/i2c-algo-bit.c
@@ -619,8 +619,8 @@ static u32 bit_func(struct i2c_adapter *adap)
 /* -----exported algorithm data: -------------------------------------	*/
 
 const struct i2c_algorithm i2c_bit_algo = {
-	.master_xfer = bit_xfer,
-	.master_xfer_atomic = bit_xfer_atomic,
+	.xfer = bit_xfer,
+	.xfer_atomic = bit_xfer_atomic,
 	.functionality = bit_func,
 };
 EXPORT_SYMBOL(i2c_bit_algo);
diff --git a/drivers/i2c/algos/i2c-algo-pca.c b/drivers/i2c/algos/i2c-algo-pca.c
index 384af88e58ad..74b66aec33d4 100644
--- a/drivers/i2c/algos/i2c-algo-pca.c
+++ b/drivers/i2c/algos/i2c-algo-pca.c
@@ -361,8 +361,8 @@ static u32 pca_func(struct i2c_adapter *adap)
 }
 
 static const struct i2c_algorithm pca_algo = {
-	.master_xfer	= pca_xfer,
-	.functionality	= pca_func,
+	.xfer = pca_xfer,
+	.functionality = pca_func,
 };
 
 static unsigned int pca_probe_chip(struct i2c_adapter *adap)
diff --git a/drivers/i2c/algos/i2c-algo-pcf.c b/drivers/i2c/algos/i2c-algo-pcf.c
index 740066ceaea3..fd563e845d4b 100644
--- a/drivers/i2c/algos/i2c-algo-pcf.c
+++ b/drivers/i2c/algos/i2c-algo-pcf.c
@@ -389,8 +389,8 @@ static u32 pcf_func(struct i2c_adapter *adap)
 
 /* exported algorithm data: */
 static const struct i2c_algorithm pcf_algo = {
-	.master_xfer	= pcf_xfer,
-	.functionality	= pcf_func,
+	.xfer = pcf_xfer,
+	.functionality = pcf_func,
 };
 
 /*
diff --git a/drivers/i2c/busses/i2c-amd-mp2-plat.c b/drivers/i2c/busses/i2c-amd-mp2-plat.c
index d9dd0e475d1a..188e24cc4d35 100644
--- a/drivers/i2c/busses/i2c-amd-mp2-plat.c
+++ b/drivers/i2c/busses/i2c-amd-mp2-plat.c
@@ -179,7 +179,7 @@ static u32 i2c_amd_func(struct i2c_adapter *a)
 }
 
 static const struct i2c_algorithm i2c_amd_algorithm = {
-	.master_xfer = i2c_amd_xfer,
+	.xfer = i2c_amd_xfer,
 	.functionality = i2c_amd_func,
 };
 
diff --git a/drivers/i2c/busses/i2c-aspeed.c b/drivers/i2c/busses/i2c-aspeed.c
index 1550d3d552ae..a26b74c71206 100644
--- a/drivers/i2c/busses/i2c-aspeed.c
+++ b/drivers/i2c/busses/i2c-aspeed.c
@@ -814,11 +814,11 @@ static int aspeed_i2c_unreg_slave(struct i2c_client *client)
 #endif /* CONFIG_I2C_SLAVE */
 
 static const struct i2c_algorithm aspeed_i2c_algo = {
-	.master_xfer	= aspeed_i2c_master_xfer,
-	.functionality	= aspeed_i2c_functionality,
+	.xfer = aspeed_i2c_master_xfer,
+	.functionality = aspeed_i2c_functionality,
 #if IS_ENABLED(CONFIG_I2C_SLAVE)
-	.reg_slave	= aspeed_i2c_reg_slave,
-	.unreg_slave	= aspeed_i2c_unreg_slave,
+	.reg_slave = aspeed_i2c_reg_slave,
+	.unreg_slave = aspeed_i2c_unreg_slave,
 #endif /* CONFIG_I2C_SLAVE */
 };
 
diff --git a/drivers/i2c/busses/i2c-at91-master.c b/drivers/i2c/busses/i2c-at91-master.c
index 374fc50bb205..59795c1c24ff 100644
--- a/drivers/i2c/busses/i2c-at91-master.c
+++ b/drivers/i2c/busses/i2c-at91-master.c
@@ -739,8 +739,8 @@ static u32 at91_twi_func(struct i2c_adapter *adapter)
 }
 
 static const struct i2c_algorithm at91_twi_algorithm = {
-	.master_xfer	= at91_twi_xfer,
-	.functionality	= at91_twi_func,
+	.xfer = at91_twi_xfer,
+	.functionality = at91_twi_func,
 };
 
 static int at91_twi_configure_dma(struct at91_twi_dev *dev, u32 phy_addr)
diff --git a/drivers/i2c/busses/i2c-axxia.c b/drivers/i2c/busses/i2c-axxia.c
index 50030256cd85..0555eeb6903a 100644
--- a/drivers/i2c/busses/i2c-axxia.c
+++ b/drivers/i2c/busses/i2c-axxia.c
@@ -706,7 +706,7 @@ static int axxia_i2c_unreg_slave(struct i2c_client *slave)
 }
 
 static const struct i2c_algorithm axxia_i2c_algo = {
-	.master_xfer = axxia_i2c_xfer,
+	.xfer = axxia_i2c_xfer,
 	.functionality = axxia_i2c_func,
 	.reg_slave = axxia_i2c_reg_slave,
 	.unreg_slave = axxia_i2c_unreg_slave,
diff --git a/drivers/i2c/busses/i2c-bcm-iproc.c b/drivers/i2c/busses/i2c-bcm-iproc.c
index 63bc3c8f49d3..e418a4f23f15 100644
--- a/drivers/i2c/busses/i2c-bcm-iproc.c
+++ b/drivers/i2c/busses/i2c-bcm-iproc.c
@@ -1041,7 +1041,7 @@ static int bcm_iproc_i2c_unreg_slave(struct i2c_client *slave)
 }
 
 static struct i2c_algorithm bcm_iproc_algo = {
-	.master_xfer = bcm_iproc_i2c_xfer,
+	.xfer = bcm_iproc_i2c_xfer,
 	.functionality = bcm_iproc_i2c_functionality,
 	.reg_slave = bcm_iproc_i2c_reg_slave,
 	.unreg_slave = bcm_iproc_i2c_unreg_slave,
diff --git a/drivers/i2c/busses/i2c-cadence.c b/drivers/i2c/busses/i2c-cadence.c
index 8df63aaf2a80..697d095afbe4 100644
--- a/drivers/i2c/busses/i2c-cadence.c
+++ b/drivers/i2c/busses/i2c-cadence.c
@@ -1231,12 +1231,12 @@ static int cdns_unreg_slave(struct i2c_client *slave)
 #endif
 
 static const struct i2c_algorithm cdns_i2c_algo = {
-	.master_xfer	= cdns_i2c_master_xfer,
-	.master_xfer_atomic = cdns_i2c_master_xfer_atomic,
-	.functionality	= cdns_i2c_func,
+	.xfer = cdns_i2c_master_xfer,
+	.xfer_atomic = cdns_i2c_master_xfer_atomic,
+	.functionality = cdns_i2c_func,
 #if IS_ENABLED(CONFIG_I2C_SLAVE)
-	.reg_slave	= cdns_reg_slave,
-	.unreg_slave	= cdns_unreg_slave,
+	.reg_slave = cdns_reg_slave,
+	.unreg_slave = cdns_unreg_slave,
 #endif
 };
 
diff --git a/drivers/i2c/busses/i2c-cgbc.c b/drivers/i2c/busses/i2c-cgbc.c
index f054d167ac47..25a74fa51aa0 100644
--- a/drivers/i2c/busses/i2c-cgbc.c
+++ b/drivers/i2c/busses/i2c-cgbc.c
@@ -331,8 +331,8 @@ static u32 cgbc_i2c_func(struct i2c_adapter *adap)
 }
 
 static const struct i2c_algorithm cgbc_i2c_algorithm = {
-	.master_xfer	= cgbc_i2c_xfer,
-	.functionality	= cgbc_i2c_func,
+	.xfer = cgbc_i2c_xfer,
+	.functionality = cgbc_i2c_func,
 };
 
 static struct i2c_algo_cgbc_data cgbc_i2c_algo_data[] = {
diff --git a/drivers/i2c/busses/i2c-eg20t.c b/drivers/i2c/busses/i2c-eg20t.c
index efdaddf99f9e..27ea3c130a16 100644
--- a/drivers/i2c/busses/i2c-eg20t.c
+++ b/drivers/i2c/busses/i2c-eg20t.c
@@ -690,7 +690,7 @@ static u32 pch_i2c_func(struct i2c_adapter *adap)
 }
 
 static const struct i2c_algorithm pch_algorithm = {
-	.master_xfer = pch_i2c_xfer,
+	.xfer = pch_i2c_xfer,
 	.functionality = pch_i2c_func
 };
 
diff --git a/drivers/i2c/busses/i2c-emev2.c b/drivers/i2c/busses/i2c-emev2.c
index 2512cef8e2a2..ece019b3d066 100644
--- a/drivers/i2c/busses/i2c-emev2.c
+++ b/drivers/i2c/busses/i2c-emev2.c
@@ -351,10 +351,10 @@ static int em_i2c_unreg_slave(struct i2c_client *slave)
 }
 
 static const struct i2c_algorithm em_i2c_algo = {
-	.master_xfer = em_i2c_xfer,
+	.xfer = em_i2c_xfer,
 	.functionality = em_i2c_func,
-	.reg_slave      = em_i2c_reg_slave,
-	.unreg_slave    = em_i2c_unreg_slave,
+	.reg_slave = em_i2c_reg_slave,
+	.unreg_slave = em_i2c_unreg_slave,
 };
 
 static int em_i2c_probe(struct platform_device *pdev)
diff --git a/drivers/i2c/busses/i2c-exynos5.c b/drivers/i2c/busses/i2c-exynos5.c
index 02f24479aa07..9c1c5f3c09f6 100644
--- a/drivers/i2c/busses/i2c-exynos5.c
+++ b/drivers/i2c/busses/i2c-exynos5.c
@@ -879,9 +879,9 @@ static u32 exynos5_i2c_func(struct i2c_adapter *adap)
 }
 
 static const struct i2c_algorithm exynos5_i2c_algorithm = {
-	.master_xfer		= exynos5_i2c_xfer,
-	.master_xfer_atomic	= exynos5_i2c_xfer_atomic,
-	.functionality		= exynos5_i2c_func,
+	.xfer = exynos5_i2c_xfer,
+	.xfer_atomic = exynos5_i2c_xfer_atomic,
+	.functionality = exynos5_i2c_func,
 };
 
 static int exynos5_i2c_probe(struct platform_device *pdev)
diff --git a/drivers/i2c/busses/i2c-gxp.c b/drivers/i2c/busses/i2c-gxp.c
index 0fc39caa6c87..2d117e7e3cb6 100644
--- a/drivers/i2c/busses/i2c-gxp.c
+++ b/drivers/i2c/busses/i2c-gxp.c
@@ -184,11 +184,11 @@ static int gxp_i2c_unreg_slave(struct i2c_client *slave)
 #endif
 
 static const struct i2c_algorithm gxp_i2c_algo = {
-	.master_xfer   = gxp_i2c_master_xfer,
+	.xfer = gxp_i2c_master_xfer,
 	.functionality = gxp_i2c_func,
 #if IS_ENABLED(CONFIG_I2C_SLAVE)
-	.reg_slave     = gxp_i2c_reg_slave,
-	.unreg_slave   = gxp_i2c_unreg_slave,
+	.reg_slave = gxp_i2c_reg_slave,
+	.unreg_slave = gxp_i2c_unreg_slave,
 #endif
 };
 
diff --git a/drivers/i2c/busses/i2c-img-scb.c b/drivers/i2c/busses/i2c-img-scb.c
index 3278707bb885..a454f9f25146 100644
--- a/drivers/i2c/busses/i2c-img-scb.c
+++ b/drivers/i2c/busses/i2c-img-scb.c
@@ -1143,7 +1143,7 @@ static u32 img_i2c_func(struct i2c_adapter *adap)
 }
 
 static const struct i2c_algorithm img_i2c_algo = {
-	.master_xfer = img_i2c_xfer,
+	.xfer = img_i2c_xfer,
 	.functionality = img_i2c_func,
 };
 
diff --git a/drivers/i2c/busses/i2c-imx-lpi2c.c b/drivers/i2c/busses/i2c-imx-lpi2c.c
index 342d47e67586..064bc83840a6 100644
--- a/drivers/i2c/busses/i2c-imx-lpi2c.c
+++ b/drivers/i2c/busses/i2c-imx-lpi2c.c
@@ -1268,10 +1268,10 @@ static u32 lpi2c_imx_func(struct i2c_adapter *adapter)
 }
 
 static const struct i2c_algorithm lpi2c_imx_algo = {
-	.master_xfer	= lpi2c_imx_xfer,
-	.functionality	= lpi2c_imx_func,
-	.reg_target	= lpi2c_imx_register_target,
-	.unreg_target	= lpi2c_imx_unregister_target,
+	.xfer = lpi2c_imx_xfer,
+	.functionality = lpi2c_imx_func,
+	.reg_target = lpi2c_imx_register_target,
+	.unreg_target = lpi2c_imx_unregister_target,
 };
 
 static const struct of_device_id lpi2c_imx_of_match[] = {
diff --git a/drivers/i2c/busses/i2c-imx.c b/drivers/i2c/busses/i2c-imx.c
index de01dfecb16e..e5732b0557fb 100644
--- a/drivers/i2c/busses/i2c-imx.c
+++ b/drivers/i2c/busses/i2c-imx.c
@@ -1692,11 +1692,11 @@ static u32 i2c_imx_func(struct i2c_adapter *adapter)
 }
 
 static const struct i2c_algorithm i2c_imx_algo = {
-	.master_xfer = i2c_imx_xfer,
-	.master_xfer_atomic = i2c_imx_xfer_atomic,
+	.xfer = i2c_imx_xfer,
+	.xfer_atomic = i2c_imx_xfer_atomic,
 	.functionality = i2c_imx_func,
-	.reg_slave	= i2c_imx_reg_slave,
-	.unreg_slave	= i2c_imx_unreg_slave,
+	.reg_slave = i2c_imx_reg_slave,
+	.unreg_slave = i2c_imx_unreg_slave,
 };
 
 static int i2c_imx_probe(struct platform_device *pdev)
diff --git a/drivers/i2c/busses/i2c-keba.c b/drivers/i2c/busses/i2c-keba.c
index 7b9ed2592f5b..9420c8b342b5 100644
--- a/drivers/i2c/busses/i2c-keba.c
+++ b/drivers/i2c/busses/i2c-keba.c
@@ -500,7 +500,7 @@ static u32 ki2c_func(struct i2c_adapter *adap)
 }
 
 static const struct i2c_algorithm ki2c_algo = {
-	.master_xfer   = ki2c_xfer,
+	.xfer = ki2c_xfer,
 	.functionality = ki2c_func,
 };
 
diff --git a/drivers/i2c/busses/i2c-mchp-pci1xxxx.c b/drivers/i2c/busses/i2c-mchp-pci1xxxx.c
index 5ef136c3ecb1..bc0f1a0c8ee1 100644
--- a/drivers/i2c/busses/i2c-mchp-pci1xxxx.c
+++ b/drivers/i2c/busses/i2c-mchp-pci1xxxx.c
@@ -1048,7 +1048,7 @@ static u32 pci1xxxx_i2c_get_funcs(struct i2c_adapter *adap)
 }
 
 static const struct i2c_algorithm pci1xxxx_i2c_algo = {
-	.master_xfer = pci1xxxx_i2c_xfer,
+	.xfer = pci1xxxx_i2c_xfer,
 	.functionality = pci1xxxx_i2c_get_funcs,
 };
 
diff --git a/drivers/i2c/busses/i2c-meson.c b/drivers/i2c/busses/i2c-meson.c
index e1d69537353b..0d9032953e48 100644
--- a/drivers/i2c/busses/i2c-meson.c
+++ b/drivers/i2c/busses/i2c-meson.c
@@ -448,8 +448,8 @@ static u32 meson_i2c_func(struct i2c_adapter *adap)
 }
 
 static const struct i2c_algorithm meson_i2c_algorithm = {
-	.master_xfer = meson_i2c_xfer,
-	.master_xfer_atomic = meson_i2c_xfer_atomic,
+	.xfer = meson_i2c_xfer,
+	.xfer_atomic = meson_i2c_xfer_atomic,
 	.functionality = meson_i2c_func,
 };
 
diff --git a/drivers/i2c/busses/i2c-microchip-corei2c.c b/drivers/i2c/busses/i2c-microchip-corei2c.c
index 492bf4c34722..f173bda1c98c 100644
--- a/drivers/i2c/busses/i2c-microchip-corei2c.c
+++ b/drivers/i2c/busses/i2c-microchip-corei2c.c
@@ -526,7 +526,7 @@ static int mchp_corei2c_smbus_xfer(struct i2c_adapter *adap, u16 addr, unsigned
 }
 
 static const struct i2c_algorithm mchp_corei2c_algo = {
-	.master_xfer = mchp_corei2c_xfer,
+	.xfer = mchp_corei2c_xfer,
 	.functionality = mchp_corei2c_func,
 	.smbus_xfer = mchp_corei2c_smbus_xfer,
 };
diff --git a/drivers/i2c/busses/i2c-mt65xx.c b/drivers/i2c/busses/i2c-mt65xx.c
index 5bd342047d59..ab456c3717db 100644
--- a/drivers/i2c/busses/i2c-mt65xx.c
+++ b/drivers/i2c/busses/i2c-mt65xx.c
@@ -1342,7 +1342,7 @@ static u32 mtk_i2c_functionality(struct i2c_adapter *adap)
 }
 
 static const struct i2c_algorithm mtk_i2c_algorithm = {
-	.master_xfer = mtk_i2c_transfer,
+	.xfer = mtk_i2c_transfer,
 	.functionality = mtk_i2c_functionality,
 };
 
diff --git a/drivers/i2c/busses/i2c-mxs.c b/drivers/i2c/busses/i2c-mxs.c
index ad62d56b2186..08c9091a1e35 100644
--- a/drivers/i2c/busses/i2c-mxs.c
+++ b/drivers/i2c/busses/i2c-mxs.c
@@ -687,7 +687,7 @@ static irqreturn_t mxs_i2c_isr(int this_irq, void *dev_id)
 }
 
 static const struct i2c_algorithm mxs_i2c_algo = {
-	.master_xfer = mxs_i2c_xfer,
+	.xfer = mxs_i2c_xfer,
 	.functionality = mxs_i2c_func,
 };
 
diff --git a/drivers/i2c/busses/i2c-nomadik.c b/drivers/i2c/busses/i2c-nomadik.c
index d2877e4cc28d..19b648fc094d 100644
--- a/drivers/i2c/busses/i2c-nomadik.c
+++ b/drivers/i2c/busses/i2c-nomadik.c
@@ -996,8 +996,8 @@ static unsigned int nmk_i2c_functionality(struct i2c_adapter *adap)
 }
 
 static const struct i2c_algorithm nmk_i2c_algo = {
-	.master_xfer	= nmk_i2c_xfer,
-	.functionality	= nmk_i2c_functionality
+	.xfer = nmk_i2c_xfer,
+	.functionality = nmk_i2c_functionality
 };
 
 static void nmk_i2c_of_probe(struct device_node *np,
diff --git a/drivers/i2c/busses/i2c-npcm7xx.c b/drivers/i2c/busses/i2c-npcm7xx.c
index 892e2d2988a7..8b7e15240fb0 100644
--- a/drivers/i2c/busses/i2c-npcm7xx.c
+++ b/drivers/i2c/busses/i2c-npcm7xx.c
@@ -2470,11 +2470,11 @@ static const struct i2c_adapter_quirks npcm_i2c_quirks = {
 };
 
 static const struct i2c_algorithm npcm_i2c_algo = {
-	.master_xfer = npcm_i2c_master_xfer,
+	.xfer = npcm_i2c_master_xfer,
 	.functionality = npcm_i2c_functionality,
 #if IS_ENABLED(CONFIG_I2C_SLAVE)
-	.reg_slave	= npcm_i2c_reg_slave,
-	.unreg_slave	= npcm_i2c_unreg_slave,
+	.reg_slave = npcm_i2c_reg_slave,
+	.unreg_slave = npcm_i2c_unreg_slave,
 #endif
 };
 
diff --git a/drivers/i2c/busses/i2c-omap.c b/drivers/i2c/busses/i2c-omap.c
index 876791d20ed5..f1cc26ac5b80 100644
--- a/drivers/i2c/busses/i2c-omap.c
+++ b/drivers/i2c/busses/i2c-omap.c
@@ -1201,9 +1201,9 @@ omap_i2c_isr_thread(int this_irq, void *dev_id)
 }
 
 static const struct i2c_algorithm omap_i2c_algo = {
-	.master_xfer	= omap_i2c_xfer_irq,
-	.master_xfer_atomic	= omap_i2c_xfer_polling,
-	.functionality	= omap_i2c_func,
+	.xfer = omap_i2c_xfer_irq,
+	.xfer_atomic = omap_i2c_xfer_polling,
+	.functionality = omap_i2c_func,
 };
 
 static const struct i2c_adapter_quirks omap_i2c_quirks = {
diff --git a/drivers/i2c/busses/i2c-pnx.c b/drivers/i2c/busses/i2c-pnx.c
index 9a1af5bbd604..8daa0008bd05 100644
--- a/drivers/i2c/busses/i2c-pnx.c
+++ b/drivers/i2c/busses/i2c-pnx.c
@@ -580,7 +580,7 @@ static u32 i2c_pnx_func(struct i2c_adapter *adapter)
 }
 
 static const struct i2c_algorithm pnx_algorithm = {
-	.master_xfer = i2c_pnx_xfer,
+	.xfer = i2c_pnx_xfer,
 	.functionality = i2c_pnx_func,
 };
 
diff --git a/drivers/i2c/busses/i2c-pxa.c b/drivers/i2c/busses/i2c-pxa.c
index 4415a29f749b..968a8b8794da 100644
--- a/drivers/i2c/busses/i2c-pxa.c
+++ b/drivers/i2c/busses/i2c-pxa.c
@@ -1154,11 +1154,11 @@ static u32 i2c_pxa_functionality(struct i2c_adapter *adap)
 }
 
 static const struct i2c_algorithm i2c_pxa_algorithm = {
-	.master_xfer	= i2c_pxa_xfer,
-	.functionality	= i2c_pxa_functionality,
+	.xfer = i2c_pxa_xfer,
+	.functionality = i2c_pxa_functionality,
 #ifdef CONFIG_I2C_PXA_SLAVE
-	.reg_slave	= i2c_pxa_slave_reg,
-	.unreg_slave	= i2c_pxa_slave_unreg,
+	.reg_slave = i2c_pxa_slave_reg,
+	.unreg_slave = i2c_pxa_slave_unreg,
 #endif
 };
 
@@ -1244,11 +1244,11 @@ static int i2c_pxa_pio_xfer(struct i2c_adapter *adap,
 }
 
 static const struct i2c_algorithm i2c_pxa_pio_algorithm = {
-	.master_xfer	= i2c_pxa_pio_xfer,
-	.functionality	= i2c_pxa_functionality,
+	.xfer = i2c_pxa_pio_xfer,
+	.functionality = i2c_pxa_functionality,
 #ifdef CONFIG_I2C_PXA_SLAVE
-	.reg_slave	= i2c_pxa_slave_reg,
-	.unreg_slave	= i2c_pxa_slave_unreg,
+	.reg_slave = i2c_pxa_slave_reg,
+	.unreg_slave = i2c_pxa_slave_unreg,
 #endif
 };
 
diff --git a/drivers/i2c/busses/i2c-qcom-cci.c b/drivers/i2c/busses/i2c-qcom-cci.c
index 05b73326afd4..a3afa11a71a1 100644
--- a/drivers/i2c/busses/i2c-qcom-cci.c
+++ b/drivers/i2c/busses/i2c-qcom-cci.c
@@ -462,8 +462,8 @@ static u32 cci_func(struct i2c_adapter *adap)
 }
 
 static const struct i2c_algorithm cci_algo = {
-	.master_xfer	= cci_xfer,
-	.functionality	= cci_func,
+	.xfer = cci_xfer,
+	.functionality = cci_func,
 };
 
 static int cci_enable_clocks(struct cci *cci)
diff --git a/drivers/i2c/busses/i2c-qcom-geni.c b/drivers/i2c/busses/i2c-qcom-geni.c
index ccea575fb783..13889f52b6f7 100644
--- a/drivers/i2c/busses/i2c-qcom-geni.c
+++ b/drivers/i2c/busses/i2c-qcom-geni.c
@@ -727,8 +727,8 @@ static u32 geni_i2c_func(struct i2c_adapter *adap)
 }
 
 static const struct i2c_algorithm geni_i2c_algo = {
-	.master_xfer	= geni_i2c_xfer,
-	.functionality	= geni_i2c_func,
+	.xfer = geni_i2c_xfer,
+	.functionality = geni_i2c_func,
 };
 
 #ifdef CONFIG_ACPI
diff --git a/drivers/i2c/busses/i2c-qup.c b/drivers/i2c/busses/i2c-qup.c
index 3a36d682ed57..6059f585843e 100644
--- a/drivers/i2c/busses/i2c-qup.c
+++ b/drivers/i2c/busses/i2c-qup.c
@@ -1634,13 +1634,13 @@ static u32 qup_i2c_func(struct i2c_adapter *adap)
 }
 
 static const struct i2c_algorithm qup_i2c_algo = {
-	.master_xfer	= qup_i2c_xfer,
-	.functionality	= qup_i2c_func,
+	.xfer = qup_i2c_xfer,
+	.functionality = qup_i2c_func,
 };
 
 static const struct i2c_algorithm qup_i2c_algo_v2 = {
-	.master_xfer	= qup_i2c_xfer_v2,
-	.functionality	= qup_i2c_func,
+	.xfer = qup_i2c_xfer_v2,
+	.functionality = qup_i2c_func,
 };
 
 /*
diff --git a/drivers/i2c/busses/i2c-rcar.c b/drivers/i2c/busses/i2c-rcar.c
index 5693a38da7b5..d51884ab99f4 100644
--- a/drivers/i2c/busses/i2c-rcar.c
+++ b/drivers/i2c/busses/i2c-rcar.c
@@ -1084,11 +1084,11 @@ static u32 rcar_i2c_func(struct i2c_adapter *adap)
 }
 
 static const struct i2c_algorithm rcar_i2c_algo = {
-	.master_xfer	= rcar_i2c_master_xfer,
-	.master_xfer_atomic = rcar_i2c_master_xfer_atomic,
-	.functionality	= rcar_i2c_func,
-	.reg_slave	= rcar_reg_slave,
-	.unreg_slave	= rcar_unreg_slave,
+	.xfer = rcar_i2c_master_xfer,
+	.xfer_atomic = rcar_i2c_master_xfer_atomic,
+	.functionality = rcar_i2c_func,
+	.reg_slave = rcar_reg_slave,
+	.unreg_slave = rcar_unreg_slave,
 };
 
 static const struct i2c_adapter_quirks rcar_i2c_quirks = {
diff --git a/drivers/i2c/busses/i2c-s3c2410.c b/drivers/i2c/busses/i2c-s3c2410.c
index 0f3cf500df68..f4fa4703acbd 100644
--- a/drivers/i2c/busses/i2c-s3c2410.c
+++ b/drivers/i2c/busses/i2c-s3c2410.c
@@ -800,9 +800,9 @@ static u32 s3c24xx_i2c_func(struct i2c_adapter *adap)
 
 /* i2c bus registration info */
 static const struct i2c_algorithm s3c24xx_i2c_algorithm = {
-	.master_xfer		= s3c24xx_i2c_xfer,
-	.master_xfer_atomic     = s3c24xx_i2c_xfer_atomic,
-	.functionality		= s3c24xx_i2c_func,
+	.xfer = s3c24xx_i2c_xfer,
+	.xfer_atomic = s3c24xx_i2c_xfer_atomic,
+	.functionality = s3c24xx_i2c_func,
 };
 
 /*
diff --git a/drivers/i2c/busses/i2c-sh7760.c b/drivers/i2c/busses/i2c-sh7760.c
index 620f12596763..43f33988b98f 100644
--- a/drivers/i2c/busses/i2c-sh7760.c
+++ b/drivers/i2c/busses/i2c-sh7760.c
@@ -379,8 +379,8 @@ static u32 sh7760_i2c_func(struct i2c_adapter *adap)
 }
 
 static const struct i2c_algorithm sh7760_i2c_algo = {
-	.master_xfer	= sh7760_i2c_master_xfer,
-	.functionality	= sh7760_i2c_func,
+	.xfer = sh7760_i2c_master_xfer,
+	.functionality = sh7760_i2c_func,
 };
 
 /* calculate CCR register setting for a desired scl clock.  SCL clock is
diff --git a/drivers/i2c/busses/i2c-sh_mobile.c b/drivers/i2c/busses/i2c-sh_mobile.c
index adfcee6c9fdc..dae8967f8749 100644
--- a/drivers/i2c/busses/i2c-sh_mobile.c
+++ b/drivers/i2c/busses/i2c-sh_mobile.c
@@ -740,8 +740,8 @@ static u32 sh_mobile_i2c_func(struct i2c_adapter *adapter)
 
 static const struct i2c_algorithm sh_mobile_i2c_algorithm = {
 	.functionality = sh_mobile_i2c_func,
-	.master_xfer = sh_mobile_i2c_xfer,
-	.master_xfer_atomic = sh_mobile_i2c_xfer_atomic,
+	.xfer = sh_mobile_i2c_xfer,
+	.xfer_atomic = sh_mobile_i2c_xfer_atomic,
 };
 
 static const struct i2c_adapter_quirks sh_mobile_i2c_quirks = {
diff --git a/drivers/i2c/busses/i2c-stm32f7.c b/drivers/i2c/busses/i2c-stm32f7.c
index 973a3a8c6d4a..e4aaeb2262d0 100644
--- a/drivers/i2c/busses/i2c-stm32f7.c
+++ b/drivers/i2c/busses/i2c-stm32f7.c
@@ -2151,8 +2151,8 @@ static u32 stm32f7_i2c_func(struct i2c_adapter *adap)
 }
 
 static const struct i2c_algorithm stm32f7_i2c_algo = {
-	.master_xfer = stm32f7_i2c_xfer,
-	.master_xfer_atomic = stm32f7_i2c_xfer_atomic,
+	.xfer = stm32f7_i2c_xfer,
+	.xfer_atomic = stm32f7_i2c_xfer_atomic,
 	.smbus_xfer = stm32f7_i2c_smbus_xfer,
 	.functionality = stm32f7_i2c_func,
 	.reg_slave = stm32f7_i2c_reg_slave,
diff --git a/drivers/i2c/busses/i2c-synquacer.c b/drivers/i2c/busses/i2c-synquacer.c
index 31f8d08e32a4..1230f51e1624 100644
--- a/drivers/i2c/busses/i2c-synquacer.c
+++ b/drivers/i2c/busses/i2c-synquacer.c
@@ -520,8 +520,8 @@ static u32 synquacer_i2c_functionality(struct i2c_adapter *adap)
 }
 
 static const struct i2c_algorithm synquacer_i2c_algo = {
-	.master_xfer	= synquacer_i2c_xfer,
-	.functionality	= synquacer_i2c_functionality,
+	.xfer = synquacer_i2c_xfer,
+	.functionality = synquacer_i2c_functionality,
 };
 
 static const struct i2c_adapter synquacer_i2c_ops = {
diff --git a/drivers/i2c/busses/i2c-tegra.c b/drivers/i2c/busses/i2c-tegra.c
index 049b4d154c23..0862b98007f5 100644
--- a/drivers/i2c/busses/i2c-tegra.c
+++ b/drivers/i2c/busses/i2c-tegra.c
@@ -1440,9 +1440,9 @@ static u32 tegra_i2c_func(struct i2c_adapter *adap)
 }
 
 static const struct i2c_algorithm tegra_i2c_algo = {
-	.master_xfer		= tegra_i2c_xfer,
-	.master_xfer_atomic	= tegra_i2c_xfer_atomic,
-	.functionality		= tegra_i2c_func,
+	.xfer = tegra_i2c_xfer,
+	.xfer_atomic = tegra_i2c_xfer_atomic,
+	.functionality = tegra_i2c_func,
 };
 
 /* payload size is only 12 bit */
diff --git a/drivers/i2c/busses/i2c-xiic.c b/drivers/i2c/busses/i2c-xiic.c
index 6bc1575cea6c..607026c921d6 100644
--- a/drivers/i2c/busses/i2c-xiic.c
+++ b/drivers/i2c/busses/i2c-xiic.c
@@ -1398,8 +1398,8 @@ static u32 xiic_func(struct i2c_adapter *adap)
 }
 
 static const struct i2c_algorithm xiic_algorithm = {
-	.master_xfer = xiic_xfer,
-	.master_xfer_atomic = xiic_xfer_atomic,
+	.xfer = xiic_xfer,
+	.xfer_atomic = xiic_xfer_atomic,
 	.functionality = xiic_func,
 };
 
diff --git a/drivers/i2c/busses/i2c-xlp9xx.c b/drivers/i2c/busses/i2c-xlp9xx.c
index 4d5e49b6321b..ddb1c3e8bc9d 100644
--- a/drivers/i2c/busses/i2c-xlp9xx.c
+++ b/drivers/i2c/busses/i2c-xlp9xx.c
@@ -452,7 +452,7 @@ static u32 xlp9xx_i2c_functionality(struct i2c_adapter *adapter)
 }
 
 static const struct i2c_algorithm xlp9xx_i2c_algo = {
-	.master_xfer = xlp9xx_i2c_xfer,
+	.xfer = xlp9xx_i2c_xfer,
 	.functionality = xlp9xx_i2c_functionality,
 };
 
diff --git a/drivers/i2c/i2c-atr.c b/drivers/i2c/i2c-atr.c
index be7d6d41e0b2..dd194476b118 100644
--- a/drivers/i2c/i2c-atr.c
+++ b/drivers/i2c/i2c-atr.c
@@ -738,7 +738,7 @@ struct i2c_atr *i2c_atr_new(struct i2c_adapter *parent, struct device *dev,
 	atr->flags = flags;
 
 	if (parent->algo->master_xfer)
-		atr->algo.master_xfer = i2c_atr_master_xfer;
+		atr->algo.xfer = i2c_atr_master_xfer;
 	if (parent->algo->smbus_xfer)
 		atr->algo.smbus_xfer = i2c_atr_smbus_xfer;
 	atr->algo.functionality = i2c_atr_functionality;
diff --git a/drivers/i2c/i2c-mux.c b/drivers/i2c/i2c-mux.c
index fda72e8be885..4d8690981a55 100644
--- a/drivers/i2c/i2c-mux.c
+++ b/drivers/i2c/i2c-mux.c
@@ -293,12 +293,12 @@ int i2c_mux_add_adapter(struct i2c_mux_core *muxc,
 	 */
 	if (parent->algo->master_xfer) {
 		if (muxc->mux_locked)
-			priv->algo.master_xfer = i2c_mux_master_xfer;
+			priv->algo.xfer = i2c_mux_master_xfer;
 		else
-			priv->algo.master_xfer = __i2c_mux_master_xfer;
+			priv->algo.xfer = __i2c_mux_master_xfer;
 	}
 	if (parent->algo->master_xfer_atomic)
-		priv->algo.master_xfer_atomic = priv->algo.master_xfer;
+		priv->algo.xfer_atomic = priv->algo.master_xfer;
 
 	if (parent->algo->smbus_xfer) {
 		if (muxc->mux_locked)
diff --git a/drivers/i2c/muxes/i2c-demux-pinctrl.c b/drivers/i2c/muxes/i2c-demux-pinctrl.c
index 77a740561fd7..f2a1f4744978 100644
--- a/drivers/i2c/muxes/i2c-demux-pinctrl.c
+++ b/drivers/i2c/muxes/i2c-demux-pinctrl.c
@@ -95,9 +95,9 @@ static int i2c_demux_activate_master(struct i2c_demux_pinctrl_priv *priv, u32 ne
 	priv->cur_chan = new_chan;
 
 	/* Now fill out current adapter structure. cur_chan must be up to date */
-	priv->algo.master_xfer = i2c_demux_master_xfer;
+	priv->algo.xfer = i2c_demux_master_xfer;
 	if (adap->algo->master_xfer_atomic)
-		priv->algo.master_xfer_atomic = i2c_demux_master_xfer;
+		priv->algo.xfer_atomic = i2c_demux_master_xfer;
 	priv->algo.functionality = i2c_demux_functionality;
 
 	snprintf(priv->cur_adap.name, sizeof(priv->cur_adap.name),

From b26852daaa83f535109253d114426d1fa674155d Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 10 Jun 2025 11:28:42 +0200
Subject: [PATCH 0283/1334] RDMA/mlx5: reduce stack usage in
 mlx5_ib_ufile_hw_cleanup

This function has an array of eight mlx5_async_cmd structures, which
often fits on the stack, but depending on the configuration can
end up blowing the stack frame warning limit:

drivers/infiniband/hw/mlx5/devx.c:2670:6: error: stack frame size (1392) exceeds limit (1280) in 'mlx5_ib_ufile_hw_cleanup' [-Werror,-Wframe-larger-than]

Change this to a dynamic allocation instead. While a kmalloc()
can theoretically fail, a GFP_KERNEL allocation under a page will
block until memory has been freed up, so in the worst case, this
only adds extra time in an already constrained environment.

Fixes: 7c891a4dbcc1 ("RDMA/mlx5: Add implementation for ufile_hw_cleanup device operation")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Link: https://patch.msgid.link/20250610092846.2642535-1-arnd@kernel.org
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/hw/mlx5/devx.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/drivers/infiniband/hw/mlx5/devx.c b/drivers/infiniband/hw/mlx5/devx.c
index 2479da8620ca..bceae1c1f980 100644
--- a/drivers/infiniband/hw/mlx5/devx.c
+++ b/drivers/infiniband/hw/mlx5/devx.c
@@ -2669,7 +2669,7 @@ static void devx_wait_async_destroy(struct mlx5_async_cmd *cmd)
 
 void mlx5_ib_ufile_hw_cleanup(struct ib_uverbs_file *ufile)
 {
-	struct mlx5_async_cmd async_cmd[MAX_ASYNC_CMDS];
+	struct mlx5_async_cmd *async_cmd;
 	struct ib_ucontext *ucontext = ufile->ucontext;
 	struct ib_device *device = ucontext->device;
 	struct mlx5_ib_dev *dev = to_mdev(device);
@@ -2678,6 +2678,10 @@ void mlx5_ib_ufile_hw_cleanup(struct ib_uverbs_file *ufile)
 	int head = 0;
 	int tail = 0;
 
+	async_cmd = kcalloc(MAX_ASYNC_CMDS, sizeof(*async_cmd), GFP_KERNEL);
+	if (!async_cmd)
+		return;
+
 	list_for_each_entry(uobject, &ufile->uobjects, list) {
 		WARN_ON(uverbs_try_lock_object(uobject, UVERBS_LOOKUP_WRITE));
 
@@ -2713,6 +2717,8 @@ void mlx5_ib_ufile_hw_cleanup(struct ib_uverbs_file *ufile)
 		devx_wait_async_destroy(&async_cmd[head % MAX_ASYNC_CMDS]);
 		head++;
 	}
+
+	kfree(async_cmd);
 }
 
 static ssize_t devx_async_cmd_event_read(struct file *filp, char __user *buf,

From 2d5a84c3ecc075d87bcb16c1cc80277b5837c153 Mon Sep 17 00:00:00 2001
From: Xi Pardee <xi.pardee@linux.intel.com>
Date: Tue, 10 Jun 2025 16:04:06 -0700
Subject: [PATCH 0284/1334] platform/x86/intel/pmc: Add Lunar Lake support to
 Intel PMC SSRAM Telemetry
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add Lunar Lake support to Intel PMC SSRAM Telemetry driver.

Signed-off-by: Xi Pardee <xi.pardee@linux.intel.com>
Link: https://lore.kernel.org/r/20250610230416.622970-1-xi.pardee@linux.intel.com
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/intel/pmc/core.h            | 3 +++
 drivers/platform/x86/intel/pmc/ssram_telemetry.c | 1 +
 2 files changed, 4 insertions(+)

diff --git a/drivers/platform/x86/intel/pmc/core.h b/drivers/platform/x86/intel/pmc/core.h
index e136d18b1d38..c1db41cb8334 100644
--- a/drivers/platform/x86/intel/pmc/core.h
+++ b/drivers/platform/x86/intel/pmc/core.h
@@ -299,6 +299,9 @@ enum ppfear_regs {
 #define PTL_PCD_PMC_MMIO_REG_LEN		0x31A8
 
 /* SSRAM PMC Device ID */
+/* LNL */
+#define PMC_DEVID_LNL_SOCM	0xa87f
+
 /* ARL */
 #define PMC_DEVID_ARL_SOCM	0x777f
 #define PMC_DEVID_ARL_SOCS	0xae7f
diff --git a/drivers/platform/x86/intel/pmc/ssram_telemetry.c b/drivers/platform/x86/intel/pmc/ssram_telemetry.c
index b207247eb5dd..24d5d01805c8 100644
--- a/drivers/platform/x86/intel/pmc/ssram_telemetry.c
+++ b/drivers/platform/x86/intel/pmc/ssram_telemetry.c
@@ -187,6 +187,7 @@ static const struct pci_device_id intel_pmc_ssram_telemetry_pci_ids[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PMC_DEVID_MTL_SOCM) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PMC_DEVID_ARL_SOCS) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PMC_DEVID_ARL_SOCM) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PMC_DEVID_LNL_SOCM) },
 	{ }
 };
 MODULE_DEVICE_TABLE(pci, intel_pmc_ssram_telemetry_pci_ids);

From be574d5eee9808a422cff0293da9b08c0e434ed0 Mon Sep 17 00:00:00 2001
From: Xi Pardee <xi.pardee@linux.intel.com>
Date: Tue, 10 Jun 2025 16:04:07 -0700
Subject: [PATCH 0285/1334] platform/x86/intel/pmc: Add Panther Lake support to
 Intel PMC SSRAM Telemetry
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add Panther Lake support to Intel PMC SSRAM Telemetry driver.

Signed-off-by: Xi Pardee <xi.pardee@linux.intel.com>
Link: https://lore.kernel.org/r/20250610230416.622970-2-xi.pardee@linux.intel.com
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/intel/pmc/core.h            | 4 ++++
 drivers/platform/x86/intel/pmc/ssram_telemetry.c | 2 ++
 2 files changed, 6 insertions(+)

diff --git a/drivers/platform/x86/intel/pmc/core.h b/drivers/platform/x86/intel/pmc/core.h
index c1db41cb8334..4a94a4ee031e 100644
--- a/drivers/platform/x86/intel/pmc/core.h
+++ b/drivers/platform/x86/intel/pmc/core.h
@@ -302,6 +302,10 @@ enum ppfear_regs {
 /* LNL */
 #define PMC_DEVID_LNL_SOCM	0xa87f
 
+/* PTL */
+#define PMC_DEVID_PTL_PCDH	0xe37f
+#define PMC_DEVID_PTL_PCDP	0xe47f
+
 /* ARL */
 #define PMC_DEVID_ARL_SOCM	0x777f
 #define PMC_DEVID_ARL_SOCS	0xae7f
diff --git a/drivers/platform/x86/intel/pmc/ssram_telemetry.c b/drivers/platform/x86/intel/pmc/ssram_telemetry.c
index 24d5d01805c8..93579152188e 100644
--- a/drivers/platform/x86/intel/pmc/ssram_telemetry.c
+++ b/drivers/platform/x86/intel/pmc/ssram_telemetry.c
@@ -188,6 +188,8 @@ static const struct pci_device_id intel_pmc_ssram_telemetry_pci_ids[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PMC_DEVID_ARL_SOCS) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PMC_DEVID_ARL_SOCM) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PMC_DEVID_LNL_SOCM) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PMC_DEVID_PTL_PCDH) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PMC_DEVID_PTL_PCDP) },
 	{ }
 };
 MODULE_DEVICE_TABLE(pci, intel_pmc_ssram_telemetry_pci_ids);

From 0c44b46f51a17baa7ab67de1464427116e9c4eaa Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 10 Jun 2025 11:34:55 +0200
Subject: [PATCH 0286/1334] platform/x86/intel-uncore-freq: avoid non-literal
 format string
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Using a string variable in place of a format string causes a W=1 build warning:

drivers/platform/x86/intel/uncore-frequency/uncore-frequency-common.c:61:40: error: format string is not a string literal (potentially insecure) [-Werror,-Wformat-security]
   61 |                 length += sysfs_emit_at(buf, length, agent_name[agent]);
      |                                                      ^~~~~~~~~~~~~~~~~

Use the safer "%s" format string to print it instead.

Fixes: b98fa870fce2 ("platform/x86/intel-uncore-freq: Add attributes to show agent types")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Tested-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Link: https://lore.kernel.org/r/20250610093459.2646337-1-arnd@kernel.org
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 .../x86/intel/uncore-frequency/uncore-frequency-common.c        | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-common.c b/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-common.c
index 0f8aea18275b..65897fae17df 100644
--- a/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-common.c
+++ b/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-common.c
@@ -58,7 +58,7 @@ static ssize_t show_agent_types(struct kobject *kobj, struct kobj_attribute *att
 		if (length)
 			length += sysfs_emit_at(buf, length, " ");
 
-		length += sysfs_emit_at(buf, length, agent_name[agent]);
+		length += sysfs_emit_at(buf, length, "%s", agent_name[agent]);
 	}
 
 	length += sysfs_emit_at(buf, length, "\n");

From 312d02adb959ea199372f375ada06e0186f651e4 Mon Sep 17 00:00:00 2001
From: Jens Wiklander <jens.wiklander@linaro.org>
Date: Mon, 2 Jun 2025 14:04:35 +0200
Subject: [PATCH 0287/1334] optee: ffa: fix sleep in atomic context

The OP-TEE driver registers the function notif_callback() for FF-A
notifications. However, this function is called in an atomic context
leading to errors like this when processing asynchronous notifications:

 | BUG: sleeping function called from invalid context at kernel/locking/mutex.c:258
 | in_atomic(): 1, irqs_disabled(): 1, non_block: 0, pid: 9, name: kworker/0:0
 | preempt_count: 1, expected: 0
 | RCU nest depth: 0, expected: 0
 | CPU: 0 UID: 0 PID: 9 Comm: kworker/0:0 Not tainted 6.14.0-00019-g657536ebe0aa #13
 | Hardware name: linux,dummy-virt (DT)
 | Workqueue: ffa_pcpu_irq_notification notif_pcpu_irq_work_fn
 | Call trace:
 |  show_stack+0x18/0x24 (C)
 |  dump_stack_lvl+0x78/0x90
 |  dump_stack+0x18/0x24
 |  __might_resched+0x114/0x170
 |  __might_sleep+0x48/0x98
 |  mutex_lock+0x24/0x80
 |  optee_get_msg_arg+0x7c/0x21c
 |  simple_call_with_arg+0x50/0xc0
 |  optee_do_bottom_half+0x14/0x20
 |  notif_callback+0x3c/0x48
 |  handle_notif_callbacks+0x9c/0xe0
 |  notif_get_and_handle+0x40/0x88
 |  generic_exec_single+0x80/0xc0
 |  smp_call_function_single+0xfc/0x1a0
 |  notif_pcpu_irq_work_fn+0x2c/0x38
 |  process_one_work+0x14c/0x2b4
 |  worker_thread+0x2e4/0x3e0
 |  kthread+0x13c/0x210
 |  ret_from_fork+0x10/0x20

Fix this by adding work queue to process the notification in a
non-atomic context.

Fixes: d0476a59de06 ("optee: ffa_abi: add asynchronous notifications")
Cc: stable@vger.kernel.org
Reviewed-by: Sumit Garg <sumit.garg@oss.qualcomm.com>
Tested-by: Sudeep Holla <sudeep.holla@arm.com>
Link: https://lore.kernel.org/r/20250602120452.2507084-1-jens.wiklander@linaro.org
Signed-off-by: Jens Wiklander <jens.wiklander@linaro.org>
---
 drivers/tee/optee/ffa_abi.c       | 41 ++++++++++++++++++++++++-------
 drivers/tee/optee/optee_private.h |  2 ++
 2 files changed, 34 insertions(+), 9 deletions(-)

diff --git a/drivers/tee/optee/ffa_abi.c b/drivers/tee/optee/ffa_abi.c
index f3af5666bb11..f9ef7d94cebd 100644
--- a/drivers/tee/optee/ffa_abi.c
+++ b/drivers/tee/optee/ffa_abi.c
@@ -728,12 +728,21 @@ static bool optee_ffa_exchange_caps(struct ffa_device *ffa_dev,
 	return true;
 }
 
+static void notif_work_fn(struct work_struct *work)
+{
+	struct optee_ffa *optee_ffa = container_of(work, struct optee_ffa,
+						   notif_work);
+	struct optee *optee = container_of(optee_ffa, struct optee, ffa);
+
+	optee_do_bottom_half(optee->ctx);
+}
+
 static void notif_callback(int notify_id, void *cb_data)
 {
 	struct optee *optee = cb_data;
 
 	if (notify_id == optee->ffa.bottom_half_value)
-		optee_do_bottom_half(optee->ctx);
+		queue_work(optee->ffa.notif_wq, &optee->ffa.notif_work);
 	else
 		optee_notif_send(optee, notify_id);
 }
@@ -817,9 +826,11 @@ static void optee_ffa_remove(struct ffa_device *ffa_dev)
 	struct optee *optee = ffa_dev_get_drvdata(ffa_dev);
 	u32 bottom_half_id = optee->ffa.bottom_half_value;
 
-	if (bottom_half_id != U32_MAX)
+	if (bottom_half_id != U32_MAX) {
 		ffa_dev->ops->notifier_ops->notify_relinquish(ffa_dev,
 							      bottom_half_id);
+		destroy_workqueue(optee->ffa.notif_wq);
+	}
 	optee_remove_common(optee);
 
 	mutex_destroy(&optee->ffa.mutex);
@@ -835,6 +846,13 @@ static int optee_ffa_async_notif_init(struct ffa_device *ffa_dev,
 	u32 notif_id = 0;
 	int rc;
 
+	INIT_WORK(&optee->ffa.notif_work, notif_work_fn);
+	optee->ffa.notif_wq = create_workqueue("optee_notification");
+	if (!optee->ffa.notif_wq) {
+		rc = -EINVAL;
+		goto err;
+	}
+
 	while (true) {
 		rc = ffa_dev->ops->notifier_ops->notify_request(ffa_dev,
 								is_per_vcpu,
@@ -851,19 +869,24 @@ static int optee_ffa_async_notif_init(struct ffa_device *ffa_dev,
 		 * notifications in that case.
 		 */
 		if (rc != -EACCES)
-			return rc;
+			goto err_wq;
 		notif_id++;
 		if (notif_id >= OPTEE_FFA_MAX_ASYNC_NOTIF_VALUE)
-			return rc;
+			goto err_wq;
 	}
 	optee->ffa.bottom_half_value = notif_id;
 
 	rc = enable_async_notif(optee);
-	if (rc < 0) {
-		ffa_dev->ops->notifier_ops->notify_relinquish(ffa_dev,
-							      notif_id);
-		optee->ffa.bottom_half_value = U32_MAX;
-	}
+	if (rc < 0)
+		goto err_rel;
+
+	return 0;
+err_rel:
+	ffa_dev->ops->notifier_ops->notify_relinquish(ffa_dev, notif_id);
+err_wq:
+	destroy_workqueue(optee->ffa.notif_wq);
+err:
+	optee->ffa.bottom_half_value = U32_MAX;
 
 	return rc;
 }
diff --git a/drivers/tee/optee/optee_private.h b/drivers/tee/optee/optee_private.h
index dc0f355ef72a..9526087f0e68 100644
--- a/drivers/tee/optee/optee_private.h
+++ b/drivers/tee/optee/optee_private.h
@@ -165,6 +165,8 @@ struct optee_ffa {
 	/* Serializes access to @global_ids */
 	struct mutex mutex;
 	struct rhashtable global_ids;
+	struct workqueue_struct *notif_wq;
+	struct work_struct notif_work;
 };
 
 struct optee;

From e479da4054875c4cc53a7fb956ebff03d2dac939 Mon Sep 17 00:00:00 2001
From: John Keeping <jkeeping@inmusicbrands.com>
Date: Wed, 11 Jun 2025 12:13:06 +0100
Subject: [PATCH 0288/1334] drm/ssd130x: fix ssd132x_clear_screen() columns

The number of columns relates to the width, not the height.  Use the
correct variable.

Signed-off-by: John Keeping <jkeeping@inmusicbrands.com>
Reviewed-by: Javier Martinez Canillas <javierm@redhat.com>
Fixes: fdd591e00a9c ("drm/ssd130x: Add support for the SSD132x OLED controller family")
Link: https://lore.kernel.org/r/20250611111307.1814876-1-jkeeping@inmusicbrands.com
Signed-off-by: Javier Martinez Canillas <javierm@redhat.com>
---
 drivers/gpu/drm/solomon/ssd130x.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/solomon/ssd130x.c b/drivers/gpu/drm/solomon/ssd130x.c
index dd2006d51c7a..eec43d1a5595 100644
--- a/drivers/gpu/drm/solomon/ssd130x.c
+++ b/drivers/gpu/drm/solomon/ssd130x.c
@@ -974,7 +974,7 @@ static void ssd130x_clear_screen(struct ssd130x_device *ssd130x, u8 *data_array)
 
 static void ssd132x_clear_screen(struct ssd130x_device *ssd130x, u8 *data_array)
 {
-	unsigned int columns = DIV_ROUND_UP(ssd130x->height, SSD132X_SEGMENT_WIDTH);
+	unsigned int columns = DIV_ROUND_UP(ssd130x->width, SSD132X_SEGMENT_WIDTH);
 	unsigned int height = ssd130x->height;
 
 	memset(data_array, 0, columns * height);

From 8ecbad4853f83d9853d7bb0c2d8373afab8851d3 Mon Sep 17 00:00:00 2001
From: Alexander Stein <alexander.stein@ew.tq-group.com>
Date: Fri, 23 May 2025 08:40:41 +0200
Subject: [PATCH 0289/1334] drm/arm/malidp: Silence informational message

When checking for unsupported expect an error is printed every time.
This spams the log for platforms where this is expected, e.g. ls1028a
having a Vivante (etnaviv) GPU and Mali display processor.

Signed-off-by: Alexander Stein <alexander.stein@ew.tq-group.com>
Signed-off-by: Liviu Dudau <liviu.dudau@arm.com>
Link: https://lore.kernel.org/r/20250523064042.3275926-1-alexander.stein@ew.tq-group.com
---
 drivers/gpu/drm/arm/malidp_planes.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/arm/malidp_planes.c b/drivers/gpu/drm/arm/malidp_planes.c
index 34547edf1ee3..87f2e5ee8790 100644
--- a/drivers/gpu/drm/arm/malidp_planes.c
+++ b/drivers/gpu/drm/arm/malidp_planes.c
@@ -159,7 +159,7 @@ bool malidp_format_mod_supported(struct drm_device *drm,
 	}
 
 	if (!fourcc_mod_is_vendor(modifier, ARM)) {
-		DRM_ERROR("Unknown modifier (not Arm)\n");
+		DRM_DEBUG_KMS("Unknown modifier (not Arm)\n");
 		return false;
 	}
 

From d1fc7687959b0fbf335815a8d808e6076b969309 Mon Sep 17 00:00:00 2001
From: Richard Fitzgerald <rf@opensource.cirrus.com>
Date: Thu, 12 Jun 2025 13:14:26 +0100
Subject: [PATCH 0290/1334] ASoC: cs35l56: Use SoundWire address as firmware
 name suffix for new silicon

Use the SoundWire link number and device unique ID as the firmware file
qualifier suffix on CS35L57, CS35L63 and revisions of CS35L56 after B0. The
change in wm_adsp needed to support this has been included in this patch
because it is fairly trivial.

Originally, the firmware file names indicated which amplifier instance they
were for by appending the ALSA prefix string. This is the standard ASoC way
of distinguishing different instances of the same device. However, on
SoundWire systems the SoundWire physical unique address is available as a
unique identifier for each amp, and this address is hardwired by a pin on
the amp.

The firmware files are specific for each physical amp so they must be
applied to that amp. Using the ALSA prefix for the filename qualifier means
that to name a firmware file it must be determined what prefix string the
machine driver will assign to each device and then use that to name the
firmware file correctly. This is straightforward in traditional ASoC
systems where the machine driver is specific to a particular piece of
hardware. But on SoundWire the machine driver is generic and can handle a
very wide range of hardware. It is more difficult to determine exactly what
the prefix will be on any particular production device, and more prone to
mistakes. Also, when the machine driver switches to generating this
automatically from SDCA properties in ACPI, there is an additional layer of
complexity in determining the mapping. This uncertainty is unnecessary
because the firmware is built for a specific amp. with known address, so we
can use that directly instead of introducing the redundant intermediate
alias. This ensures the firmware is applied to the amp it was intended for.

There have not been any firmwares published for CS35L57 or CS35L63, so
these can safely be switched to using the SoundWire unique address as the
suffix string. Also note that the machine driver in older kernel version
only has match entries for the CS35L56 Soundwire identity so any future
product with a cs35L57 or CS35L63 would require a new kernel anyway.

There are already many published firmware for CS35L56 B0 silicon so this
keeps the original naming scheme on those, to preserve backward
compatibility.

Note that although sdw_slave.id contains a unique_id field, this cannot
be trusted because the SoundWire core code also puts magic values into it
that it uses as a flag. So the unique ID is read from the chip register.

Signed-off-by: Richard Fitzgerald <rf@opensource.cirrus.com>
Link: https://patch.msgid.link/20250612121428.1667-2-rf@opensource.cirrus.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/cs35l56-sdw.c | 18 ++++++++++--------
 sound/soc/codecs/cs35l56.c     | 29 +++++++++++++++++++++++++++++
 sound/soc/codecs/cs35l56.h     |  2 ++
 sound/soc/codecs/wm_adsp.c     | 21 ++++++++++++---------
 sound/soc/codecs/wm_adsp.h     |  1 +
 5 files changed, 54 insertions(+), 17 deletions(-)

diff --git a/sound/soc/codecs/cs35l56-sdw.c b/sound/soc/codecs/cs35l56-sdw.c
index 13f602f51bf3..fa9693af3722 100644
--- a/sound/soc/codecs/cs35l56-sdw.c
+++ b/sound/soc/codecs/cs35l56-sdw.c
@@ -238,16 +238,15 @@ static const struct regmap_bus cs35l56_regmap_bus_sdw = {
 	.val_format_endian_default = REGMAP_ENDIAN_BIG,
 };
 
-static int cs35l56_sdw_set_cal_index(struct cs35l56_private *cs35l56)
+static int cs35l56_sdw_get_unique_id(struct cs35l56_private *cs35l56)
 {
 	int ret;
 
-	/* SoundWire UniqueId is used to index the calibration array */
 	ret = sdw_read_no_pm(cs35l56->sdw_peripheral, SDW_SCP_DEVID_0);
 	if (ret < 0)
 		return ret;
 
-	cs35l56->base.cal_index = ret & 0xf;
+	cs35l56->sdw_unique_id = ret & 0xf;
 
 	return 0;
 }
@@ -259,11 +258,13 @@ static void cs35l56_sdw_init(struct sdw_slave *peripheral)
 
 	pm_runtime_get_noresume(cs35l56->base.dev);
 
-	if (cs35l56->base.cal_index < 0) {
-		ret = cs35l56_sdw_set_cal_index(cs35l56);
-		if (ret < 0)
-			goto out;
-	}
+	ret = cs35l56_sdw_get_unique_id(cs35l56);
+	if (ret)
+		goto out;
+
+	/* SoundWire UniqueId is used to index the calibration array */
+	if (cs35l56->base.cal_index < 0)
+		cs35l56->base.cal_index = cs35l56->sdw_unique_id;
 
 	ret = cs35l56_init(cs35l56);
 	if (ret < 0) {
@@ -587,6 +588,7 @@ static int cs35l56_sdw_probe(struct sdw_slave *peripheral, const struct sdw_devi
 
 	cs35l56->base.dev = dev;
 	cs35l56->sdw_peripheral = peripheral;
+	cs35l56->sdw_link_num = peripheral->bus->link_id;
 	INIT_WORK(&cs35l56->sdw_irq_work, cs35l56_sdw_irq_work);
 
 	dev_set_drvdata(dev, cs35l56);
diff --git a/sound/soc/codecs/cs35l56.c b/sound/soc/codecs/cs35l56.c
index c78e4746e428..6e6120c39965 100644
--- a/sound/soc/codecs/cs35l56.c
+++ b/sound/soc/codecs/cs35l56.c
@@ -853,6 +853,31 @@ err:
 	pm_runtime_put_autosuspend(cs35l56->base.dev);
 }
 
+static int cs35l56_set_fw_suffix(struct cs35l56_private *cs35l56)
+{
+	if (cs35l56->dsp.fwf_suffix)
+		return 0;
+
+	if (!cs35l56->sdw_peripheral)
+		return 0;
+
+	/*
+	 * There are published firmware files for L56 B0 silicon using
+	 * the default wm_adsp name suffixing so don't change those.
+	 */
+	if ((cs35l56->base.type == 0x56) && (cs35l56->base.rev == 0xb0))
+		return 0;
+
+	cs35l56->dsp.fwf_suffix = devm_kasprintf(cs35l56->base.dev, GFP_KERNEL,
+						 "l%uu%u",
+						 cs35l56->sdw_link_num,
+						 cs35l56->sdw_unique_id);
+	if (!cs35l56->dsp.fwf_suffix)
+		return -ENOMEM;
+
+	return 0;
+}
+
 static int cs35l56_component_probe(struct snd_soc_component *component)
 {
 	struct cs35l56_private *cs35l56 = snd_soc_component_get_drvdata(component);
@@ -891,6 +916,10 @@ static int cs35l56_component_probe(struct snd_soc_component *component)
 	if (!cs35l56->dsp.part)
 		return -ENOMEM;
 
+	ret = cs35l56_set_fw_suffix(cs35l56);
+	if (ret)
+		return ret;
+
 	cs35l56->component = component;
 	wm_adsp2_component_probe(&cs35l56->dsp, component);
 
diff --git a/sound/soc/codecs/cs35l56.h b/sound/soc/codecs/cs35l56.h
index 200f695efca3..a84c83eb2d7c 100644
--- a/sound/soc/codecs/cs35l56.h
+++ b/sound/soc/codecs/cs35l56.h
@@ -52,6 +52,8 @@ struct cs35l56_private {
 	bool tdm_mode;
 	bool sysclk_set;
 	u8 old_sdw_clock_scale;
+	u8 sdw_link_num;
+	u8 sdw_unique_id;
 };
 
 extern const struct dev_pm_ops cs35l56_pm_ops_i2c_spi;
diff --git a/sound/soc/codecs/wm_adsp.c b/sound/soc/codecs/wm_adsp.c
index 3c580faab3b7..13db9c6650d5 100644
--- a/sound/soc/codecs/wm_adsp.c
+++ b/sound/soc/codecs/wm_adsp.c
@@ -783,16 +783,19 @@ static int wm_adsp_request_firmware_files(struct wm_adsp *dsp,
 					  char **coeff_filename)
 {
 	const char *system_name = dsp->system_name;
-	const char *asoc_component_prefix = dsp->component->name_prefix;
+	const char *suffix = dsp->component->name_prefix;
 	int ret = 0;
 
-	if (system_name && asoc_component_prefix) {
+	if (dsp->fwf_suffix)
+		suffix = dsp->fwf_suffix;
+
+	if (system_name && suffix) {
 		if (!wm_adsp_request_firmware_file(dsp, wmfw_firmware, wmfw_filename,
 						   cirrus_dir, system_name,
-						   asoc_component_prefix, "wmfw")) {
+						   suffix, "wmfw")) {
 			wm_adsp_request_firmware_file(dsp, coeff_firmware, coeff_filename,
 						      cirrus_dir, system_name,
-						      asoc_component_prefix, "bin");
+						      suffix, "bin");
 			return 0;
 		}
 	}
@@ -801,10 +804,10 @@ static int wm_adsp_request_firmware_files(struct wm_adsp *dsp,
 		if (!wm_adsp_request_firmware_file(dsp, wmfw_firmware, wmfw_filename,
 						   cirrus_dir, system_name,
 						   NULL, "wmfw")) {
-			if (asoc_component_prefix)
+			if (suffix)
 				wm_adsp_request_firmware_file(dsp, coeff_firmware, coeff_filename,
 							      cirrus_dir, system_name,
-							      asoc_component_prefix, "bin");
+							      suffix, "bin");
 
 			if (!*coeff_firmware)
 				wm_adsp_request_firmware_file(dsp, coeff_firmware, coeff_filename,
@@ -816,10 +819,10 @@ static int wm_adsp_request_firmware_files(struct wm_adsp *dsp,
 
 	/* Check system-specific bin without wmfw before falling back to generic */
 	if (dsp->wmfw_optional && system_name) {
-		if (asoc_component_prefix)
+		if (suffix)
 			wm_adsp_request_firmware_file(dsp, coeff_firmware, coeff_filename,
 						      cirrus_dir, system_name,
-						      asoc_component_prefix, "bin");
+						      suffix, "bin");
 
 		if (!*coeff_firmware)
 			wm_adsp_request_firmware_file(dsp, coeff_firmware, coeff_filename,
@@ -850,7 +853,7 @@ static int wm_adsp_request_firmware_files(struct wm_adsp *dsp,
 	adsp_err(dsp, "Failed to request firmware <%s>%s-%s-%s<-%s<%s>>.wmfw\n",
 		 cirrus_dir, dsp->part,
 		 dsp->fwf_name ? dsp->fwf_name : dsp->cs_dsp.name,
-		 wm_adsp_fw[dsp->fw].file, system_name, asoc_component_prefix);
+		 wm_adsp_fw[dsp->fw].file, system_name, suffix);
 
 	return -ENOENT;
 }
diff --git a/sound/soc/codecs/wm_adsp.h b/sound/soc/codecs/wm_adsp.h
index edc5b02ae765..075ea0bd06eb 100644
--- a/sound/soc/codecs/wm_adsp.h
+++ b/sound/soc/codecs/wm_adsp.h
@@ -29,6 +29,7 @@ struct wm_adsp {
 	const char *part;
 	const char *fwf_name;
 	const char *system_name;
+	const char *fwf_suffix;
 	struct snd_soc_component *component;
 
 	unsigned int sys_config_size;

From e5d5b3aebdc8acf9f52d1369a7744a2ab9ca591c Mon Sep 17 00:00:00 2001
From: Richard Fitzgerald <rf@opensource.cirrus.com>
Date: Thu, 12 Jun 2025 13:14:27 +0100
Subject: [PATCH 0291/1334] ASoC: cs35l56: Use SoundWire address as alternate
 firmware suffix on L56 B0

Use the SoundWire link number and device unique ID as the firmware file
qualifier suffix on CS35L56 B0 if .bin files are not found with the older
suffix. Some changes in wm_adsp needed to support this have been included
in this patch because they are trivial.

The allows future products with CS35L56 B0 silicon to use the same firmware
file naming as CS35L57 and cs35L63, while retaining backward compatibility
for firmware that has already been published with the old naming scheme.

The old suffix is searched first, partly because there are already many
files using that naming scheme, but also because they are a smaller subset
of all the possible fallback name options offered by wm_adsp so we know
that it will either find the qualified files or fail. All the firmware
files already published have the wmfw qualified with only the ACPI SSID and
the bin files qualified with both SSID and the suffix.

Originally, the firmware file names indicated which amplifier instance they
were for by appending the ALSA prefix string. This is the standard ASoC way
of distinguishing different instances of the same device. However, on
SoundWire systems the SoundWire physical unique address is available as a
unique identifier for each amp, and this address is hardwired by the
address pin on the amp.

The firmware files are specific for each physical amp so they must be
applied to that amp. Using the ALSA prefix for the filename qualifier means
that to name a firmware file it must be determined what prefix string the
machine driver will assign to each device and then use that to name the
firmware file correctly. This is straightforward in traditional ASoC
systems where the machine driver is specific to a particular piece of
hardware. But on SoundWire the machine driver is generic and can handle a
very wide range of hardware. It is more difficult to determine exactly what
the prefix will be on any particular production device, and more prone to
mistakes. Also, when the machine driver switches to generating this
automatically from SDCA properties in ACPI, there is an additional layer of
complexity in determining the mapping. This uncertainty is unnecessary
because the firmware is built for a specific amp. with known address, so we
can use that directly instead of introducing a redundant intermediate
alias. This ensures the firmware is applied to the amp it was intended for.

There are already many published firmware for CS35L56 B0 silicon so this
first looks for the original name suffix, to keep backward compatibility.
If this doesn't find .bin files it will switch to using the new name suffix
so that future products using CS35L56 B0 can start to use the new suffix.

Signed-off-by: Richard Fitzgerald <rf@opensource.cirrus.com>
Link: https://patch.msgid.link/20250612121428.1667-3-rf@opensource.cirrus.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/cs35l56.c | 59 +++++++++++++++++++++++++++-----------
 sound/soc/codecs/cs35l56.h |  1 +
 sound/soc/codecs/wm_adsp.c |  6 ++++
 sound/soc/codecs/wm_adsp.h |  1 +
 4 files changed, 50 insertions(+), 17 deletions(-)

diff --git a/sound/soc/codecs/cs35l56.c b/sound/soc/codecs/cs35l56.c
index 6e6120c39965..1b42586794ad 100644
--- a/sound/soc/codecs/cs35l56.c
+++ b/sound/soc/codecs/cs35l56.c
@@ -706,16 +706,40 @@ static int cs35l56_write_cal(struct cs35l56_private *cs35l56)
 	return ret;
 }
 
+static int cs35l56_dsp_download_and_power_up(struct cs35l56_private *cs35l56,
+					     bool load_firmware)
+{
+	int ret;
+
+	/*
+	 * Abort the first load if it didn't find the suffixed bins and
+	 * we have an alternate fallback suffix.
+	 */
+	cs35l56->dsp.bin_mandatory = (load_firmware && cs35l56->fallback_fw_suffix);
+
+	ret = wm_adsp_power_up(&cs35l56->dsp, load_firmware);
+	if ((ret == -ENOENT) && cs35l56->dsp.bin_mandatory) {
+		cs35l56->dsp.fwf_suffix = cs35l56->fallback_fw_suffix;
+		cs35l56->fallback_fw_suffix = NULL;
+		cs35l56->dsp.bin_mandatory = false;
+		ret = wm_adsp_power_up(&cs35l56->dsp, load_firmware);
+	}
+
+	if (ret) {
+		dev_dbg(cs35l56->base.dev, "wm_adsp_power_up ret %d\n", ret);
+		return ret;
+	}
+
+	return 0;
+}
+
 static void cs35l56_reinit_patch(struct cs35l56_private *cs35l56)
 {
 	int ret;
 
-	/* Use wm_adsp to load and apply the firmware patch and coefficient files */
-	ret = wm_adsp_power_up(&cs35l56->dsp, true);
-	if (ret) {
-		dev_dbg(cs35l56->base.dev, "%s: wm_adsp_power_up ret %d\n", __func__, ret);
+	ret = cs35l56_dsp_download_and_power_up(cs35l56, true);
+	if (ret)
 		return;
-	}
 
 	cs35l56_write_cal(cs35l56);
 
@@ -750,11 +774,9 @@ static void cs35l56_patch(struct cs35l56_private *cs35l56, bool firmware_missing
 	 * but only if firmware is missing. If firmware is already patched just
 	 * power-up wm_adsp without downloading firmware.
 	 */
-	ret = wm_adsp_power_up(&cs35l56->dsp, !!firmware_missing);
-	if (ret) {
-		dev_dbg(cs35l56->base.dev, "%s: wm_adsp_power_up ret %d\n", __func__, ret);
+	ret = cs35l56_dsp_download_and_power_up(cs35l56, firmware_missing);
+	if (ret)
 		goto err;
-	}
 
 	mutex_lock(&cs35l56->base.irq_lock);
 
@@ -861,13 +883,6 @@ static int cs35l56_set_fw_suffix(struct cs35l56_private *cs35l56)
 	if (!cs35l56->sdw_peripheral)
 		return 0;
 
-	/*
-	 * There are published firmware files for L56 B0 silicon using
-	 * the default wm_adsp name suffixing so don't change those.
-	 */
-	if ((cs35l56->base.type == 0x56) && (cs35l56->base.rev == 0xb0))
-		return 0;
-
 	cs35l56->dsp.fwf_suffix = devm_kasprintf(cs35l56->base.dev, GFP_KERNEL,
 						 "l%uu%u",
 						 cs35l56->sdw_link_num,
@@ -875,6 +890,16 @@ static int cs35l56_set_fw_suffix(struct cs35l56_private *cs35l56)
 	if (!cs35l56->dsp.fwf_suffix)
 		return -ENOMEM;
 
+	/*
+	 * There are published firmware files for L56 B0 silicon using
+	 * the ALSA prefix as the filename suffix. Default to trying these
+	 * first, with the new name as an alternate.
+	 */
+	if ((cs35l56->base.type == 0x56) && (cs35l56->base.rev == 0xb0)) {
+		cs35l56->fallback_fw_suffix = cs35l56->dsp.fwf_suffix;
+		cs35l56->dsp.fwf_suffix = cs35l56->component->name_prefix;
+	}
+
 	return 0;
 }
 
@@ -916,11 +941,11 @@ static int cs35l56_component_probe(struct snd_soc_component *component)
 	if (!cs35l56->dsp.part)
 		return -ENOMEM;
 
+	cs35l56->component = component;
 	ret = cs35l56_set_fw_suffix(cs35l56);
 	if (ret)
 		return ret;
 
-	cs35l56->component = component;
 	wm_adsp2_component_probe(&cs35l56->dsp, component);
 
 	debugfs_create_bool("init_done", 0444, debugfs_root, &cs35l56->base.init_done);
diff --git a/sound/soc/codecs/cs35l56.h b/sound/soc/codecs/cs35l56.h
index a84c83eb2d7c..bd77a57249d7 100644
--- a/sound/soc/codecs/cs35l56.h
+++ b/sound/soc/codecs/cs35l56.h
@@ -38,6 +38,7 @@ struct cs35l56_private {
 	struct snd_soc_component *component;
 	struct regulator_bulk_data supplies[CS35L56_NUM_BULK_SUPPLIES];
 	struct sdw_slave *sdw_peripheral;
+	const char *fallback_fw_suffix;
 	struct work_struct sdw_irq_work;
 	bool sdw_irq_no_unmask;
 	bool soft_resetting;
diff --git a/sound/soc/codecs/wm_adsp.c b/sound/soc/codecs/wm_adsp.c
index 13db9c6650d5..8a1d5cc75d6c 100644
--- a/sound/soc/codecs/wm_adsp.c
+++ b/sound/soc/codecs/wm_adsp.c
@@ -1000,11 +1000,17 @@ int wm_adsp_power_up(struct wm_adsp *dsp, bool load_firmware)
 			return ret;
 	}
 
+	if (dsp->bin_mandatory && !coeff_firmware) {
+		ret = -ENOENT;
+		goto err;
+	}
+
 	ret = cs_dsp_power_up(&dsp->cs_dsp,
 			      wmfw_firmware, wmfw_filename,
 			      coeff_firmware, coeff_filename,
 			      wm_adsp_fw_text[dsp->fw]);
 
+err:
 	wm_adsp_release_firmware_files(dsp,
 				       wmfw_firmware, wmfw_filename,
 				       coeff_firmware, coeff_filename);
diff --git a/sound/soc/codecs/wm_adsp.h b/sound/soc/codecs/wm_adsp.h
index 075ea0bd06eb..25210d404bf1 100644
--- a/sound/soc/codecs/wm_adsp.h
+++ b/sound/soc/codecs/wm_adsp.h
@@ -36,6 +36,7 @@ struct wm_adsp {
 
 	int fw;
 	bool wmfw_optional;
+	bool bin_mandatory;
 
 	struct work_struct boot_work;
 	int (*control_add)(struct wm_adsp *dsp, struct cs_dsp_coeff_ctl *cs_ctl);

From fa8fae5f82e48db1a06ba570a2a3fdc087fc93c0 Mon Sep 17 00:00:00 2001
From: Richard Fitzgerald <rf@opensource.cirrus.com>
Date: Thu, 12 Jun 2025 13:14:28 +0100
Subject: [PATCH 0292/1334] ASoC: doc: cs35l56: Update to add new SoundWire
 firmware filename suffix

Add the new firmware filename suffix used for SoundWire systems with
CS35L57, CS35L63 or CS35L56 later than B0 silicon. This uses the SoundWire
physical address of the amp to identify which firmware file to load on that
amp.

Signed-off-by: Richard Fitzgerald <rf@opensource.cirrus.com>
Link: https://patch.msgid.link/20250612121428.1667-4-rf@opensource.cirrus.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 Documentation/sound/codecs/cs35l56.rst | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/Documentation/sound/codecs/cs35l56.rst b/Documentation/sound/codecs/cs35l56.rst
index 98c6f6c74394..7db9f93d9be5 100644
--- a/Documentation/sound/codecs/cs35l56.rst
+++ b/Documentation/sound/codecs/cs35l56.rst
@@ -104,6 +104,13 @@ In this example the SSID is 10280c63.
 
 The format of the firmware file names is:
 
+SoundWire (except CS35L56 Rev B0):
+    cs35lxx-b0-dsp1-misc-SSID[-spkidX]-l?u?
+
+SoundWire CS35L56 Rev B0:
+    cs35lxx-b0-dsp1-misc-SSID[-spkidX]-ampN
+
+Non-SoundWire (HDA and I2S):
     cs35lxx-b0-dsp1-misc-SSID[-spkidX]-ampN
 
 Where:
@@ -111,12 +118,18 @@ Where:
   * cs35lxx-b0 is the amplifier model and silicon revision. This information
     is logged by the driver during initialization.
   * SSID is the 8-digit hexadecimal SSID value.
+  * l?u? is the physical address on the SoundWire bus of the amp this
+    file applies to.
   * ampN is the amplifier number (for example amp1). This is the same as
     the prefix on the ALSA control names except that it is always lower-case
     in the file name.
   * spkidX is an optional part, used for laptops that have firmware
     configurations for different makes and models of internal speakers.
 
+The CS35L56 Rev B0 continues to use the old filename scheme because a
+large number of firmware files have already been published with these
+names.
+
 Sound Open Firmware and ALSA topology files
 -------------------------------------------
 

From 527c88d8390d6c0358dea4d71696795c05328925 Mon Sep 17 00:00:00 2001
From: Amir Goldstein <amir73il@gmail.com>
Date: Thu, 12 Jun 2025 09:22:45 +0200
Subject: [PATCH 0293/1334] ovl: fix debug print in case of mkdir error

We want to print the name in case of mkdir failure and now we will
get a cryptic (efault) as name.

Fixes: c54b386969a5 ("VFS: Change vfs_mkdir() to return the dentry.")
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Link: https://lore.kernel.org/20250612072245.2825938-1-amir73il@gmail.com
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/overlayfs/overlayfs.h | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h
index 8baaba0a3fe5..497323128e5f 100644
--- a/fs/overlayfs/overlayfs.h
+++ b/fs/overlayfs/overlayfs.h
@@ -246,9 +246,11 @@ static inline struct dentry *ovl_do_mkdir(struct ovl_fs *ofs,
 					  struct dentry *dentry,
 					  umode_t mode)
 {
-	dentry = vfs_mkdir(ovl_upper_mnt_idmap(ofs), dir, dentry, mode);
-	pr_debug("mkdir(%pd2, 0%o) = %i\n", dentry, mode, PTR_ERR_OR_ZERO(dentry));
-	return dentry;
+	struct dentry *ret;
+
+	ret = vfs_mkdir(ovl_upper_mnt_idmap(ofs), dir, dentry, mode);
+	pr_debug("mkdir(%pd2, 0%o) = %i\n", dentry, mode, PTR_ERR_OR_ZERO(ret));
+	return ret;
 }
 
 static inline int ovl_do_mknod(struct ovl_fs *ofs,

From 0b9d62a47149083d581d8b2abb04124b6175cb29 Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <djwong@kernel.org>
Date: Wed, 11 Jun 2025 09:40:44 -0700
Subject: [PATCH 0294/1334] fs: unlock the superblock during
 iterate_supers_type

This function takes super_lock in shared mode, so it should release the
same lock.

Cc: stable@vger.kernel.org # v6.16-rc1
Fixes: af7551cf13cf7f ("super: remove pointless s_root checks")
Signed-off-by: "Darrick J. Wong" <djwong@kernel.org>
Link: https://lore.kernel.org/20250611164044.GF6138@frogsfrogsfrogs
Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/super.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/fs/super.c b/fs/super.c
index 21799e213fd7..80418ca8e215 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -964,8 +964,10 @@ void iterate_supers_type(struct file_system_type *type,
 		spin_unlock(&sb_lock);
 
 		locked = super_lock_shared(sb);
-		if (locked)
+		if (locked) {
 			f(sb, arg);
+			super_unlock_shared(sb);
+		}
 
 		spin_lock(&sb_lock);
 		if (p)

From ba06528ad5a31923efc24324706116ccd17e12d8 Mon Sep 17 00:00:00 2001
From: Gabriel Santese <santesegabriel@gmail.com>
Date: Fri, 30 May 2025 02:52:32 +0200
Subject: [PATCH 0295/1334] ASoC: amd: yc: Add quirk for MSI Bravo 17 D7VF
 internal mic

MSI Bravo 17 (D7VF), like other laptops from the family,
has broken ACPI tables and needs a quirk for internal mic
to work properly.

Signed-off-by: Gabriel Santese <santesegabriel@gmail.com>
Link: https://patch.msgid.link/20250530005444.23398-1-santesegabriel@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/amd/yc/acp6x-mach.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/sound/soc/amd/yc/acp6x-mach.c b/sound/soc/amd/yc/acp6x-mach.c
index 7e62445e02c1..c9387d6fbf18 100644
--- a/sound/soc/amd/yc/acp6x-mach.c
+++ b/sound/soc/amd/yc/acp6x-mach.c
@@ -451,6 +451,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "Bravo 17 D7VEK"),
 		}
 	},
+	{
+		.driver_data = &acp6x_card,
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "Micro-Star International Co., Ltd."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Bravo 17 D7VF"),
+		}
+	},
 	{
 		.driver_data = &acp6x_card,
 		.matches = {

From c538f400fae22725580842deb2bef546701b64bd Mon Sep 17 00:00:00 2001
From: Keith Busch <kbusch@kernel.org>
Date: Wed, 11 Jun 2025 13:53:43 -0700
Subject: [PATCH 0296/1334] io_uring: consistently use rcu semantics with
 sqpoll thread

The sqpoll thread is dereferenced with rcu read protection in one place,
so it needs to be annotated as an __rcu type, and should consistently
use rcu helpers for access and assignment to make sparse happy.

Since most of the accesses occur under the sqd->lock, we can use
rcu_dereference_protected() without declaring an rcu read section.
Provide a simple helper to get the thread from a locked context.

Fixes: ac0b8b327a5677d ("io_uring: fix use-after-free of sq->thread in __io_uring_show_fdinfo()")
Signed-off-by: Keith Busch <kbusch@kernel.org>
Link: https://lore.kernel.org/r/20250611205343.1821117-1-kbusch@meta.com
[axboe: fold in fix for register.c]
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/io_uring.c |  4 ++--
 io_uring/register.c |  7 +++++--
 io_uring/sqpoll.c   | 34 ++++++++++++++++++++++++----------
 io_uring/sqpoll.h   |  8 +++++++-
 4 files changed, 38 insertions(+), 15 deletions(-)

diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index cf759c172083..4e32f808d07d 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -2906,7 +2906,7 @@ static __cold void io_ring_exit_work(struct work_struct *work)
 			struct task_struct *tsk;
 
 			io_sq_thread_park(sqd);
-			tsk = sqd->thread;
+			tsk = sqpoll_task_locked(sqd);
 			if (tsk && tsk->io_uring && tsk->io_uring->io_wq)
 				io_wq_cancel_cb(tsk->io_uring->io_wq,
 						io_cancel_ctx_cb, ctx, true);
@@ -3142,7 +3142,7 @@ __cold void io_uring_cancel_generic(bool cancel_all, struct io_sq_data *sqd)
 	s64 inflight;
 	DEFINE_WAIT(wait);
 
-	WARN_ON_ONCE(sqd && sqd->thread != current);
+	WARN_ON_ONCE(sqd && sqpoll_task_locked(sqd) != current);
 
 	if (!current->io_uring)
 		return;
diff --git a/io_uring/register.c b/io_uring/register.c
index cc23a4c205cd..a59589249fce 100644
--- a/io_uring/register.c
+++ b/io_uring/register.c
@@ -273,6 +273,8 @@ static __cold int io_register_iowq_max_workers(struct io_ring_ctx *ctx,
 	if (ctx->flags & IORING_SETUP_SQPOLL) {
 		sqd = ctx->sq_data;
 		if (sqd) {
+			struct task_struct *tsk;
+
 			/*
 			 * Observe the correct sqd->lock -> ctx->uring_lock
 			 * ordering. Fine to drop uring_lock here, we hold
@@ -282,8 +284,9 @@ static __cold int io_register_iowq_max_workers(struct io_ring_ctx *ctx,
 			mutex_unlock(&ctx->uring_lock);
 			mutex_lock(&sqd->lock);
 			mutex_lock(&ctx->uring_lock);
-			if (sqd->thread)
-				tctx = sqd->thread->io_uring;
+			tsk = sqpoll_task_locked(sqd);
+			if (tsk)
+				tctx = tsk->io_uring;
 		}
 	} else {
 		tctx = current->io_uring;
diff --git a/io_uring/sqpoll.c b/io_uring/sqpoll.c
index 0625a421626f..268d2fbe6160 100644
--- a/io_uring/sqpoll.c
+++ b/io_uring/sqpoll.c
@@ -30,7 +30,7 @@ enum {
 void io_sq_thread_unpark(struct io_sq_data *sqd)
 	__releases(&sqd->lock)
 {
-	WARN_ON_ONCE(sqd->thread == current);
+	WARN_ON_ONCE(sqpoll_task_locked(sqd) == current);
 
 	/*
 	 * Do the dance but not conditional clear_bit() because it'd race with
@@ -46,24 +46,32 @@ void io_sq_thread_unpark(struct io_sq_data *sqd)
 void io_sq_thread_park(struct io_sq_data *sqd)
 	__acquires(&sqd->lock)
 {
-	WARN_ON_ONCE(data_race(sqd->thread) == current);
+	struct task_struct *tsk;
 
 	atomic_inc(&sqd->park_pending);
 	set_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state);
 	mutex_lock(&sqd->lock);
-	if (sqd->thread)
-		wake_up_process(sqd->thread);
+
+	tsk = sqpoll_task_locked(sqd);
+	if (tsk) {
+		WARN_ON_ONCE(tsk == current);
+		wake_up_process(tsk);
+	}
 }
 
 void io_sq_thread_stop(struct io_sq_data *sqd)
 {
-	WARN_ON_ONCE(sqd->thread == current);
+	struct task_struct *tsk;
+
 	WARN_ON_ONCE(test_bit(IO_SQ_THREAD_SHOULD_STOP, &sqd->state));
 
 	set_bit(IO_SQ_THREAD_SHOULD_STOP, &sqd->state);
 	mutex_lock(&sqd->lock);
-	if (sqd->thread)
-		wake_up_process(sqd->thread);
+	tsk = sqpoll_task_locked(sqd);
+	if (tsk) {
+		WARN_ON_ONCE(tsk == current);
+		wake_up_process(tsk);
+	}
 	mutex_unlock(&sqd->lock);
 	wait_for_completion(&sqd->exited);
 }
@@ -486,7 +494,10 @@ __cold int io_sq_offload_create(struct io_ring_ctx *ctx,
 			goto err_sqpoll;
 		}
 
-		sqd->thread = tsk;
+		mutex_lock(&sqd->lock);
+		rcu_assign_pointer(sqd->thread, tsk);
+		mutex_unlock(&sqd->lock);
+
 		task_to_put = get_task_struct(tsk);
 		ret = io_uring_alloc_task_context(tsk, ctx);
 		wake_up_new_task(tsk);
@@ -514,10 +525,13 @@ __cold int io_sqpoll_wq_cpu_affinity(struct io_ring_ctx *ctx,
 	int ret = -EINVAL;
 
 	if (sqd) {
+		struct task_struct *tsk;
+
 		io_sq_thread_park(sqd);
 		/* Don't set affinity for a dying thread */
-		if (sqd->thread)
-			ret = io_wq_cpu_affinity(sqd->thread->io_uring, mask);
+		tsk = sqpoll_task_locked(sqd);
+		if (tsk)
+			ret = io_wq_cpu_affinity(tsk->io_uring, mask);
 		io_sq_thread_unpark(sqd);
 	}
 
diff --git a/io_uring/sqpoll.h b/io_uring/sqpoll.h
index 4171666b1cf4..b83dcdec9765 100644
--- a/io_uring/sqpoll.h
+++ b/io_uring/sqpoll.h
@@ -8,7 +8,7 @@ struct io_sq_data {
 	/* ctx's that are using this sqd */
 	struct list_head	ctx_list;
 
-	struct task_struct	*thread;
+	struct task_struct __rcu *thread;
 	struct wait_queue_head	wait;
 
 	unsigned		sq_thread_idle;
@@ -29,3 +29,9 @@ void io_sq_thread_unpark(struct io_sq_data *sqd);
 void io_put_sq_data(struct io_sq_data *sqd);
 void io_sqpoll_wait_sq(struct io_ring_ctx *ctx);
 int io_sqpoll_wq_cpu_affinity(struct io_ring_ctx *ctx, cpumask_var_t mask);
+
+static inline struct task_struct *sqpoll_task_locked(struct io_sq_data *sqd)
+{
+	return rcu_dereference_protected(sqd->thread,
+					 lockdep_is_held(&sqd->lock));
+}

From c0c7fa4e7a512006710c8e4d6b6f7b40c9f786cd Mon Sep 17 00:00:00 2001
From: Lorenzo Pieralisi <lpieralisi@kernel.org>
Date: Tue, 10 Jun 2025 14:09:35 +0200
Subject: [PATCH 0297/1334] docs: arm64: Fix ICC_SRE_EL2 register typo in
 booting.rst

Fix trivial ICC_SRE_EL2 register spelling typo in booting.rst.

Signed-off-by: Lorenzo Pieralisi <lpieralisi@kernel.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Will Deacon <will@kernel.org>
CC: Catalin Marinas <catalin.marinas@arm.com>
Link: https://lore.kernel.org/r/20250610120935.852034-1-lpieralisi@kernel.org
Signed-off-by: Will Deacon <will@kernel.org>
---
 Documentation/arch/arm64/booting.rst | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/arch/arm64/booting.rst b/Documentation/arch/arm64/booting.rst
index dee7b6de864f..ee9b790c0d72 100644
--- a/Documentation/arch/arm64/booting.rst
+++ b/Documentation/arch/arm64/booting.rst
@@ -234,7 +234,7 @@ Before jumping into the kernel, the following conditions must be met:
 
   - If the kernel is entered at EL1:
 
-      - ICC.SRE_EL2.Enable (bit 3) must be initialised to 0b1
+      - ICC_SRE_EL2.Enable (bit 3) must be initialised to 0b1
       - ICC_SRE_EL2.SRE (bit 0) must be initialised to 0b1.
 
   - The DT or ACPI tables must describe a GICv3 interrupt controller.

From 650768c512faba8070bf4cfbb28c95eb5cd203f3 Mon Sep 17 00:00:00 2001
From: Dev Jain <dev.jain@arm.com>
Date: Tue, 27 May 2025 13:56:33 +0530
Subject: [PATCH 0298/1334] arm64: Restrict pagetable teardown to avoid false
 warning

Commit 9c006972c3fe ("arm64: mmu: drop pXd_present() checks from
pXd_free_pYd_table()") removes the pxd_present() checks because the
caller checks pxd_present(). But, in case of vmap_try_huge_pud(), the
caller only checks pud_present(); pud_free_pmd_page() recurses on each
pmd through pmd_free_pte_page(), wherein the pmd may be none. Thus it is
possible to hit a warning in the latter, since pmd_none => !pmd_table().
Thus, add a pmd_present() check in pud_free_pmd_page().

This problem was found by code inspection.

Fixes: 9c006972c3fe ("arm64: mmu: drop pXd_present() checks from pXd_free_pYd_table()")
Cc: stable@vger.kernel.org
Reported-by: Ryan Roberts <ryan.roberts@arm.com>
Acked-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Dev Jain <dev.jain@arm.com>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Reviewed-by: Anshuman Khandual <anshuman.khandual@arm.com>
Reviewed-by: Ryan Roberts <ryan.roberts@arm.com>
Link: https://lore.kernel.org/r/20250527082633.61073-1-dev.jain@arm.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/mm/mmu.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 8fcf59ba39db..00ab1d648db6 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -1305,7 +1305,8 @@ int pud_free_pmd_page(pud_t *pudp, unsigned long addr)
 	next = addr;
 	end = addr + PUD_SIZE;
 	do {
-		pmd_free_pte_page(pmdp, next);
+		if (pmd_present(pmdp_get(pmdp)))
+			pmd_free_pte_page(pmdp, next);
 	} while (pmdp++, next += PMD_SIZE, next != end);
 
 	pud_clear(pudp);

From d4e6cb324dcc952618fec6b25aa3fc7bfc2750b4 Mon Sep 17 00:00:00 2001
From: Maxime Chevallier <maxime.chevallier@bootlin.com>
Date: Fri, 6 Jun 2025 11:43:20 +0200
Subject: [PATCH 0299/1334] net: phy: phy_caps: Don't skip better duplex macth
 on non-exact match

When performing a non-exact phy_caps lookup, we are looking for a
supported mode that matches as closely as possible the passed speed/duplex.

Blamed patch broke that logic by returning a match too early in case
the caller asks for half-duplex, as a full-duplex linkmode may match
first, and returned as a non-exact match without even trying to mach on
half-duplex modes.

Reported-by: Jijie Shao <shaojijie@huawei.com>
Closes: https://lore.kernel.org/netdev/20250603102500.4ec743cf@fedora/T/#m22ed60ca635c67dc7d9cbb47e8995b2beb5c1576
Tested-by: Jijie Shao <shaojijie@huawei.com>
Reviewed-by: Larysa Zaremba <larysa.zaremba@intel.com>
Fixes: fc81e257d19f ("net: phy: phy_caps: Allow looking-up link caps based on speed and duplex")
Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Link: https://patch.msgid.link/20250606094321.483602-1-maxime.chevallier@bootlin.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/phy_caps.c | 18 ++++++++++++------
 1 file changed, 12 insertions(+), 6 deletions(-)

diff --git a/drivers/net/phy/phy_caps.c b/drivers/net/phy/phy_caps.c
index 703321689726..38417e288611 100644
--- a/drivers/net/phy/phy_caps.c
+++ b/drivers/net/phy/phy_caps.c
@@ -188,6 +188,9 @@ phy_caps_lookup_by_linkmode_rev(const unsigned long *linkmodes, bool fdx_only)
  * When @exact is not set, we return either an exact match, or matching capabilities
  * at lower speed, or the lowest matching speed, or NULL.
  *
+ * Non-exact matches will try to return an exact speed and duplex match, but may
+ * return matching capabilities with same speed but a different duplex.
+ *
  * Returns: a matched link_capabilities according to the above process, NULL
  *	    otherwise.
  */
@@ -195,7 +198,7 @@ const struct link_capabilities *
 phy_caps_lookup(int speed, unsigned int duplex, const unsigned long *supported,
 		bool exact)
 {
-	const struct link_capabilities *lcap, *last = NULL;
+	const struct link_capabilities *lcap, *match = NULL, *last = NULL;
 
 	for_each_link_caps_desc_speed(lcap) {
 		if (linkmode_intersects(lcap->linkmodes, supported)) {
@@ -204,16 +207,19 @@ phy_caps_lookup(int speed, unsigned int duplex, const unsigned long *supported,
 			if (lcap->speed == speed && lcap->duplex == duplex) {
 				return lcap;
 			} else if (!exact) {
-				if (lcap->speed <= speed)
-					return lcap;
+				if (!match && lcap->speed <= speed)
+					match = lcap;
+
+				if (lcap->speed < speed)
+					break;
 			}
 		}
 	}
 
-	if (!exact)
-		return last;
+	if (!match && !exact)
+		match = last;
 
-	return NULL;
+	return match;
 }
 EXPORT_SYMBOL_GPL(phy_caps_lookup);
 

From 7ca52541c05c832d32b112274f81a985101f9ba8 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 11 Jun 2025 08:35:01 +0000
Subject: [PATCH 0300/1334] net_sched: sch_sfq: reject invalid perturb period

Gerrard Tai reported that SFQ perturb_period has no range check yet,
and this can be used to trigger a race condition fixed in a separate patch.

We want to make sure ctl->perturb_period * HZ will not overflow
and is positive.

Tested:

tc qd add dev lo root sfq perturb -10   # negative value : error
Error: sch_sfq: invalid perturb period.

tc qd add dev lo root sfq perturb 1000000000 # too big : error
Error: sch_sfq: invalid perturb period.

tc qd add dev lo root sfq perturb 2000000 # acceptable value
tc -s -d qd sh dev lo
qdisc sfq 8005: root refcnt 2 limit 127p quantum 64Kb depth 127 flows 128 divisor 1024 perturb 2000000sec
 Sent 0 bytes 0 pkt (dropped 0, overlimits 0 requeues 0)
 backlog 0b 0p requeues 0

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Reported-by: Gerrard Tai <gerrard.tai@starlabs.sg>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: stable@vger.kernel.org
Link: https://patch.msgid.link/20250611083501.1810459-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/sched/sch_sfq.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c
index 77fa02f2bfcd..a8cca549b5a2 100644
--- a/net/sched/sch_sfq.c
+++ b/net/sched/sch_sfq.c
@@ -656,6 +656,14 @@ static int sfq_change(struct Qdisc *sch, struct nlattr *opt,
 		NL_SET_ERR_MSG_MOD(extack, "invalid quantum");
 		return -EINVAL;
 	}
+
+	if (ctl->perturb_period < 0 ||
+	    ctl->perturb_period > INT_MAX / HZ) {
+		NL_SET_ERR_MSG_MOD(extack, "invalid perturb period");
+		return -EINVAL;
+	}
+	perturb_period = ctl->perturb_period * HZ;
+
 	if (ctl_v1 && !red_check_params(ctl_v1->qth_min, ctl_v1->qth_max,
 					ctl_v1->Wlog, ctl_v1->Scell_log, NULL))
 		return -EINVAL;
@@ -672,14 +680,12 @@ static int sfq_change(struct Qdisc *sch, struct nlattr *opt,
 	headdrop = q->headdrop;
 	maxdepth = q->maxdepth;
 	maxflows = q->maxflows;
-	perturb_period = q->perturb_period;
 	quantum = q->quantum;
 	flags = q->flags;
 
 	/* update and validate configuration */
 	if (ctl->quantum)
 		quantum = ctl->quantum;
-	perturb_period = ctl->perturb_period * HZ;
 	if (ctl->flows)
 		maxflows = min_t(u32, ctl->flows, SFQ_MAX_FLOWS);
 	if (ctl->divisor) {

From d35acc1be3480505b5931f17e4ea9b7617fea4d3 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 11 Jun 2025 11:15:11 +0000
Subject: [PATCH 0301/1334] net_sched: prio: fix a race in prio_tune()

Gerrard Tai reported a race condition in PRIO, whenever SFQ perturb timer
fires at the wrong time.

The race is as follows:

CPU 0                                 CPU 1
[1]: lock root
[2]: qdisc_tree_flush_backlog()
[3]: unlock root
 |
 |                                    [5]: lock root
 |                                    [6]: rehash
 |                                    [7]: qdisc_tree_reduce_backlog()
 |
[4]: qdisc_put()

This can be abused to underflow a parent's qlen.

Calling qdisc_purge_queue() instead of qdisc_tree_flush_backlog()
should fix the race, because all packets will be purged from the qdisc
before releasing the lock.

Fixes: 7b8e0b6e6599 ("net: sched: prio: delay destroying child qdiscs on change")
Reported-by: Gerrard Tai <gerrard.tai@starlabs.sg>
Suggested-by: Gerrard Tai <gerrard.tai@starlabs.sg>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20250611111515.1983366-2-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/sched/sch_prio.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c
index cc30f7a32f1a..9e2b9a490db2 100644
--- a/net/sched/sch_prio.c
+++ b/net/sched/sch_prio.c
@@ -211,7 +211,7 @@ static int prio_tune(struct Qdisc *sch, struct nlattr *opt,
 	memcpy(q->prio2band, qopt->priomap, TC_PRIO_MAX+1);
 
 	for (i = q->bands; i < oldbands; i++)
-		qdisc_tree_flush_backlog(q->queues[i]);
+		qdisc_purge_queue(q->queues[i]);
 
 	for (i = oldbands; i < q->bands; i++) {
 		q->queues[i] = queues[i];

From 85a3e0ede38450ea3053b8c45d28cf55208409b8 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 11 Jun 2025 11:15:12 +0000
Subject: [PATCH 0302/1334] net_sched: red: fix a race in __red_change()

Gerrard Tai reported a race condition in RED, whenever SFQ perturb timer
fires at the wrong time.

The race is as follows:

CPU 0                                 CPU 1
[1]: lock root
[2]: qdisc_tree_flush_backlog()
[3]: unlock root
 |
 |                                    [5]: lock root
 |                                    [6]: rehash
 |                                    [7]: qdisc_tree_reduce_backlog()
 |
[4]: qdisc_put()

This can be abused to underflow a parent's qlen.

Calling qdisc_purge_queue() instead of qdisc_tree_flush_backlog()
should fix the race, because all packets will be purged from the qdisc
before releasing the lock.

Fixes: 0c8d13ac9607 ("net: sched: red: delay destroying child qdisc on replace")
Reported-by: Gerrard Tai <gerrard.tai@starlabs.sg>
Suggested-by: Gerrard Tai <gerrard.tai@starlabs.sg>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20250611111515.1983366-3-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/sched/sch_red.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c
index 1ba3e0bba54f..4696c893cf55 100644
--- a/net/sched/sch_red.c
+++ b/net/sched/sch_red.c
@@ -285,7 +285,7 @@ static int __red_change(struct Qdisc *sch, struct nlattr **tb,
 	q->userbits = userbits;
 	q->limit = ctl->limit;
 	if (child) {
-		qdisc_tree_flush_backlog(q->qdisc);
+		qdisc_purge_queue(q->qdisc);
 		old_child = q->qdisc;
 		q->qdisc = child;
 	}

From 43eb466041216d25dedaef1c383ad7bd89929cbc Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 11 Jun 2025 11:15:13 +0000
Subject: [PATCH 0303/1334] net_sched: tbf: fix a race in tbf_change()

Gerrard Tai reported a race condition in TBF, whenever SFQ perturb timer
fires at the wrong time.

The race is as follows:

CPU 0                                 CPU 1
[1]: lock root
[2]: qdisc_tree_flush_backlog()
[3]: unlock root
 |
 |                                    [5]: lock root
 |                                    [6]: rehash
 |                                    [7]: qdisc_tree_reduce_backlog()
 |
[4]: qdisc_put()

This can be abused to underflow a parent's qlen.

Calling qdisc_purge_queue() instead of qdisc_tree_flush_backlog()
should fix the race, because all packets will be purged from the qdisc
before releasing the lock.

Fixes: b05972f01e7d ("net: sched: tbf: don't call qdisc_put() while holding tree lock")
Reported-by: Gerrard Tai <gerrard.tai@starlabs.sg>
Suggested-by: Gerrard Tai <gerrard.tai@starlabs.sg>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Zhengchao Shao <shaozhengchao@huawei.com>
Link: https://patch.msgid.link/20250611111515.1983366-4-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/sched/sch_tbf.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c
index dc26b22d53c7..4c977f049670 100644
--- a/net/sched/sch_tbf.c
+++ b/net/sched/sch_tbf.c
@@ -452,7 +452,7 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt,
 
 	sch_tree_lock(sch);
 	if (child) {
-		qdisc_tree_flush_backlog(q->qdisc);
+		qdisc_purge_queue(q->qdisc);
 		old = q->qdisc;
 		q->qdisc = child;
 	}

From d92adacdd8c2960be856e0b82acc5b7c5395fddb Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 11 Jun 2025 11:15:14 +0000
Subject: [PATCH 0304/1334] net_sched: ets: fix a race in ets_qdisc_change()

Gerrard Tai reported a race condition in ETS, whenever SFQ perturb timer
fires at the wrong time.

The race is as follows:

CPU 0                                 CPU 1
[1]: lock root
[2]: qdisc_tree_flush_backlog()
[3]: unlock root
 |
 |                                    [5]: lock root
 |                                    [6]: rehash
 |                                    [7]: qdisc_tree_reduce_backlog()
 |
[4]: qdisc_put()

This can be abused to underflow a parent's qlen.

Calling qdisc_purge_queue() instead of qdisc_tree_flush_backlog()
should fix the race, because all packets will be purged from the qdisc
before releasing the lock.

Fixes: b05972f01e7d ("net: sched: tbf: don't call qdisc_put() while holding tree lock")
Reported-by: Gerrard Tai <gerrard.tai@starlabs.sg>
Suggested-by: Gerrard Tai <gerrard.tai@starlabs.sg>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20250611111515.1983366-5-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/sched/sch_ets.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/sched/sch_ets.c b/net/sched/sch_ets.c
index 2c069f0181c6..037f764822b9 100644
--- a/net/sched/sch_ets.c
+++ b/net/sched/sch_ets.c
@@ -661,7 +661,7 @@ static int ets_qdisc_change(struct Qdisc *sch, struct nlattr *opt,
 	for (i = q->nbands; i < oldbands; i++) {
 		if (i >= q->nstrict && q->classes[i].qdisc->q.qlen)
 			list_del_init(&q->classes[i].alist);
-		qdisc_tree_flush_backlog(q->classes[i].qdisc);
+		qdisc_purge_queue(q->classes[i].qdisc);
 	}
 	WRITE_ONCE(q->nstrict, nstrict);
 	memcpy(q->prio2band, priomap, sizeof(priomap));

From adcaa890c7a4a91a422168d8fb629183fff07b2f Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 11 Jun 2025 11:15:15 +0000
Subject: [PATCH 0305/1334] net_sched: remove qdisc_tree_flush_backlog()

This function is no longer used after the four prior fixes.

Given all prior uses were wrong, it seems better to remove it.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20250611111515.1983366-6-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/sch_generic.h | 8 --------
 1 file changed, 8 deletions(-)

diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 629368ab2787..638948be4c50 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -973,14 +973,6 @@ static inline void qdisc_qstats_qlen_backlog(struct Qdisc *sch,  __u32 *qlen,
 	*backlog = qstats.backlog;
 }
 
-static inline void qdisc_tree_flush_backlog(struct Qdisc *sch)
-{
-	__u32 qlen, backlog;
-
-	qdisc_qstats_qlen_backlog(sch, &qlen, &backlog);
-	qdisc_tree_reduce_backlog(sch, qlen, backlog);
-}
-
 static inline void qdisc_purge_queue(struct Qdisc *sch)
 {
 	__u32 qlen, backlog;

From 9337c54401a5bb6ac3c9f6c71dd2a9130cfba82e Mon Sep 17 00:00:00 2001
From: Jesper Dangaard Brouer <hawk@kernel.org>
Date: Wed, 11 Jun 2025 14:40:04 +0200
Subject: [PATCH 0306/1334] veth: prevent NULL pointer dereference in
 veth_xdp_rcv

The veth peer device is RCU protected, but when the peer device gets
deleted (veth_dellink) then the pointer is assigned NULL (via
RCU_INIT_POINTER).

This patch adds a necessary NULL check in veth_xdp_rcv when accessing
the veth peer net_device.

This fixes a bug introduced in commit dc82a33297fc ("veth: apply qdisc
backpressure on full ptr_ring to reduce TX drops"). The bug is a race
and only triggers when having inflight packets on a veth that is being
deleted.

Reported-by: Ihor Solodrai <ihor.solodrai@linux.dev>
Closes: https://lore.kernel.org/all/fecfcad0-7a16-42b8-bff2-66ee83a6e5c4@linux.dev/
Reported-by: syzbot+c4c7bf27f6b0c4bd97fe@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/all/683da55e.a00a0220.d8eae.0052.GAE@google.com/
Fixes: dc82a33297fc ("veth: apply qdisc backpressure on full ptr_ring to reduce TX drops")
Signed-off-by: Jesper Dangaard Brouer <hawk@kernel.org>
Acked-by: Ihor Solodrai <ihor.solodrai@linux.dev>
Link: https://patch.msgid.link/174964557873.519608.10855046105237280978.stgit@firesoul
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/veth.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index e58a0f1b5c5b..a3046142cb8e 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -909,7 +909,7 @@ static int veth_xdp_rcv(struct veth_rq *rq, int budget,
 
 	/* NAPI functions as RCU section */
 	peer_dev = rcu_dereference_check(priv->peer, rcu_read_lock_bh_held());
-	peer_txq = netdev_get_tx_queue(peer_dev, queue_idx);
+	peer_txq = peer_dev ? netdev_get_tx_queue(peer_dev, queue_idx) : NULL;
 
 	for (i = 0; i < budget; i++) {
 		void *ptr = __ptr_ring_consume(&rq->xdp_ring);
@@ -959,7 +959,7 @@ static int veth_xdp_rcv(struct veth_rq *rq, int budget,
 	rq->stats.vs.xdp_packets += done;
 	u64_stats_update_end(&rq->stats.syncp);
 
-	if (unlikely(netif_tx_queue_stopped(peer_txq)))
+	if (peer_txq && unlikely(netif_tx_queue_stopped(peer_txq)))
 		netif_tx_wake_queue(peer_txq);
 
 	return done;

From 1619bdf4389c829f16af5c7d5b4fa5f1673614d7 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Wed, 11 Jun 2025 16:14:32 +0300
Subject: [PATCH 0307/1334] net/mlx5: HWS, Add error checking to
 hws_bwc_rule_complex_hash_node_get()

Check for if ida_alloc() or rhashtable_lookup_get_insert_fast() fails.

Fixes: 17e0accac577 ("net/mlx5: HWS, support complex matchers")
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Reviewed-by: Yevgeny Kliteynik <kliteyn@nvidia.com>
Link: https://patch.msgid.link/aEmBONjyiF6z5yCV@stanley.mountain
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../mlx5/core/steering/hws/bwc_complex.c      | 19 +++++++++++++++++--
 1 file changed, 17 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc_complex.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc_complex.c
index 70768953a4f6..ca7501c57468 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc_complex.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc_complex.c
@@ -1070,7 +1070,7 @@ hws_bwc_rule_complex_hash_node_get(struct mlx5hws_bwc_rule *bwc_rule,
 	struct mlx5hws_bwc_matcher *bwc_matcher = bwc_rule->bwc_matcher;
 	struct mlx5hws_bwc_complex_rule_hash_node *node, *old_node;
 	struct rhashtable *refcount_hash;
-	int i;
+	int ret, i;
 
 	bwc_rule->complex_hash_node = NULL;
 
@@ -1078,7 +1078,11 @@ hws_bwc_rule_complex_hash_node_get(struct mlx5hws_bwc_rule *bwc_rule,
 	if (unlikely(!node))
 		return -ENOMEM;
 
-	node->tag = ida_alloc(&bwc_matcher->complex->metadata_ida, GFP_KERNEL);
+	ret = ida_alloc(&bwc_matcher->complex->metadata_ida, GFP_KERNEL);
+	if (ret < 0)
+		goto err_free_node;
+	node->tag = ret;
+
 	refcount_set(&node->refcount, 1);
 
 	/* Clear match buffer - turn off all the unrelated fields
@@ -1094,6 +1098,11 @@ hws_bwc_rule_complex_hash_node_get(struct mlx5hws_bwc_rule *bwc_rule,
 	old_node = rhashtable_lookup_get_insert_fast(refcount_hash,
 						     &node->hash_node,
 						     hws_refcount_hash);
+	if (IS_ERR(old_node)) {
+		ret = PTR_ERR(old_node);
+		goto err_free_ida;
+	}
+
 	if (old_node) {
 		/* Rule with the same tag already exists - update refcount */
 		refcount_inc(&old_node->refcount);
@@ -1112,6 +1121,12 @@ hws_bwc_rule_complex_hash_node_get(struct mlx5hws_bwc_rule *bwc_rule,
 
 	bwc_rule->complex_hash_node = node;
 	return 0;
+
+err_free_ida:
+	ida_free(&bwc_matcher->complex->metadata_ida, node->tag);
+err_free_node:
+	kfree(node);
+	return ret;
 }
 
 static void

From 1264971017b4d7141352a7fe29021bdfce5d885d Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Wed, 11 Jun 2025 10:46:43 -0700
Subject: [PATCH 0308/1334] net: drv: netdevsim: don't napi_complete() from
 netpoll

netdevsim supports netpoll. Make sure we don't call napi_complete()
from it, since it may not be scheduled. Breno reports hitting a
warning in napi_complete_done():

WARNING: CPU: 14 PID: 104 at net/core/dev.c:6592 napi_complete_done+0x2cc/0x560
  __napi_poll+0x2d8/0x3a0
  handle_softirqs+0x1fe/0x710

This is presumably after netpoll stole the SCHED bit prematurely.

Reported-by: Breno Leitao <leitao@debian.org>
Fixes: 3762ec05a9fb ("netdevsim: add NAPI support")
Tested-by: Breno Leitao <leitao@debian.org>
Link: https://patch.msgid.link/20250611174643.2769263-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/netdevsim/netdev.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/netdevsim/netdev.c b/drivers/net/netdevsim/netdev.c
index af545d42961c..fa5fbd97ad69 100644
--- a/drivers/net/netdevsim/netdev.c
+++ b/drivers/net/netdevsim/netdev.c
@@ -371,7 +371,8 @@ static int nsim_poll(struct napi_struct *napi, int budget)
 	int done;
 
 	done = nsim_rcv(rq, budget);
-	napi_complete(napi);
+	if (done < budget)
+		napi_complete_done(napi, done);
 
 	return done;
 }

From b3979e3d2fc92bf1a2da614fc383b75b9859ef58 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@google.com>
Date: Wed, 11 Jun 2025 12:35:02 -0700
Subject: [PATCH 0309/1334] ipv6: Move fib6_config_validate() to
 ip6_route_add().

syzkaller created an IPv6 route from a malformed packet, which has
a prefix len > 128, triggering the splat below. [0]

This is a similar issue fixed by commit 586ceac9acb7 ("ipv6: Restore
fib6_config validation for SIOCADDRT.").

The cited commit removed fib6_config validation from some callers
of ip6_add_route().

Let's move the validation back to ip6_route_add() and
ip6_route_multipath_add().

[0]:
UBSAN: array-index-out-of-bounds in ./include/net/ipv6.h:616:34
index 20 is out of range for type '__u8 [16]'
CPU: 1 UID: 0 PID: 7444 Comm: syz.0.708 Not tainted 6.16.0-rc1-syzkaller-g19272b37aa4f #0 PREEMPT
Hardware name: riscv-virtio,qemu (DT)
Call Trace:
[<ffffffff80078a80>] dump_backtrace+0x2e/0x3c arch/riscv/kernel/stacktrace.c:132
[<ffffffff8000327a>] show_stack+0x30/0x3c arch/riscv/kernel/stacktrace.c:138
[<ffffffff80061012>] __dump_stack lib/dump_stack.c:94 [inline]
[<ffffffff80061012>] dump_stack_lvl+0x12e/0x1a6 lib/dump_stack.c:120
[<ffffffff800610a6>] dump_stack+0x1c/0x24 lib/dump_stack.c:129
[<ffffffff8001c0ea>] ubsan_epilogue+0x14/0x46 lib/ubsan.c:233
[<ffffffff819ba290>] __ubsan_handle_out_of_bounds+0xf6/0xf8 lib/ubsan.c:455
[<ffffffff85b363a4>] ipv6_addr_prefix include/net/ipv6.h:616 [inline]
[<ffffffff85b363a4>] ip6_route_info_create+0x8f8/0x96e net/ipv6/route.c:3793
[<ffffffff85b635da>] ip6_route_add+0x2a/0x1aa net/ipv6/route.c:3889
[<ffffffff85b02e08>] addrconf_prefix_route+0x2c4/0x4e8 net/ipv6/addrconf.c:2487
[<ffffffff85b23bb2>] addrconf_prefix_rcv+0x1720/0x1e62 net/ipv6/addrconf.c:2878
[<ffffffff85b92664>] ndisc_router_discovery+0x1a06/0x3504 net/ipv6/ndisc.c:1570
[<ffffffff85b99038>] ndisc_rcv+0x500/0x600 net/ipv6/ndisc.c:1874
[<ffffffff85bc2c18>] icmpv6_rcv+0x145e/0x1e0a net/ipv6/icmp.c:988
[<ffffffff85af6798>] ip6_protocol_deliver_rcu+0x18a/0x1976 net/ipv6/ip6_input.c:436
[<ffffffff85af8078>] ip6_input_finish+0xf4/0x174 net/ipv6/ip6_input.c:480
[<ffffffff85af8262>] NF_HOOK include/linux/netfilter.h:317 [inline]
[<ffffffff85af8262>] NF_HOOK include/linux/netfilter.h:311 [inline]
[<ffffffff85af8262>] ip6_input+0x16a/0x70c net/ipv6/ip6_input.c:491
[<ffffffff85af8dcc>] ip6_mc_input+0x5c8/0x1268 net/ipv6/ip6_input.c:588
[<ffffffff85af6112>] dst_input include/net/dst.h:469 [inline]
[<ffffffff85af6112>] ip6_rcv_finish net/ipv6/ip6_input.c:79 [inline]
[<ffffffff85af6112>] NF_HOOK include/linux/netfilter.h:317 [inline]
[<ffffffff85af6112>] NF_HOOK include/linux/netfilter.h:311 [inline]
[<ffffffff85af6112>] ipv6_rcv+0x5ae/0x6e0 net/ipv6/ip6_input.c:309
[<ffffffff85087e84>] __netif_receive_skb_one_core+0x106/0x16e net/core/dev.c:5977
[<ffffffff85088104>] __netif_receive_skb+0x2c/0x144 net/core/dev.c:6090
[<ffffffff850883c6>] netif_receive_skb_internal net/core/dev.c:6176 [inline]
[<ffffffff850883c6>] netif_receive_skb+0x1aa/0xbf2 net/core/dev.c:6235
[<ffffffff8328656e>] tun_rx_batched.isra.0+0x430/0x686 drivers/net/tun.c:1485
[<ffffffff8329ed3a>] tun_get_user+0x2952/0x3d6c drivers/net/tun.c:1938
[<ffffffff832a21e0>] tun_chr_write_iter+0xc4/0x21c drivers/net/tun.c:1984
[<ffffffff80b9b9ae>] new_sync_write fs/read_write.c:593 [inline]
[<ffffffff80b9b9ae>] vfs_write+0x56c/0xa9a fs/read_write.c:686
[<ffffffff80b9c2be>] ksys_write+0x126/0x228 fs/read_write.c:738
[<ffffffff80b9c42e>] __do_sys_write fs/read_write.c:749 [inline]
[<ffffffff80b9c42e>] __se_sys_write fs/read_write.c:746 [inline]
[<ffffffff80b9c42e>] __riscv_sys_write+0x6e/0x94 fs/read_write.c:746
[<ffffffff80076912>] syscall_handler+0x94/0x118 arch/riscv/include/asm/syscall.h:112
[<ffffffff8637e31e>] do_trap_ecall_u+0x396/0x530 arch/riscv/kernel/traps.c:341
[<ffffffff863a69e2>] handle_exception+0x146/0x152 arch/riscv/kernel/entry.S:197

Fixes: fa76c1674f2e ("ipv6: Move some validation from ip6_route_info_create() to rtm_to_fib6_config().")
Reported-by: syzbot+4c2358694722d304c44e@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/netdev/6849b8c3.a00a0220.1eb5f5.00f0.GAE@google.com/
Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20250611193551.2999991-1-kuni1840@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv6/route.c | 110 +++++++++++++++++++++++------------------------
 1 file changed, 55 insertions(+), 55 deletions(-)

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 0143262094b0..79c8f1acf8a3 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -3737,6 +3737,53 @@ void fib6_nh_release_dsts(struct fib6_nh *fib6_nh)
 	}
 }
 
+static int fib6_config_validate(struct fib6_config *cfg,
+				struct netlink_ext_ack *extack)
+{
+	/* RTF_PCPU is an internal flag; can not be set by userspace */
+	if (cfg->fc_flags & RTF_PCPU) {
+		NL_SET_ERR_MSG(extack, "Userspace can not set RTF_PCPU");
+		goto errout;
+	}
+
+	/* RTF_CACHE is an internal flag; can not be set by userspace */
+	if (cfg->fc_flags & RTF_CACHE) {
+		NL_SET_ERR_MSG(extack, "Userspace can not set RTF_CACHE");
+		goto errout;
+	}
+
+	if (cfg->fc_type > RTN_MAX) {
+		NL_SET_ERR_MSG(extack, "Invalid route type");
+		goto errout;
+	}
+
+	if (cfg->fc_dst_len > 128) {
+		NL_SET_ERR_MSG(extack, "Invalid prefix length");
+		goto errout;
+	}
+
+#ifdef CONFIG_IPV6_SUBTREES
+	if (cfg->fc_src_len > 128) {
+		NL_SET_ERR_MSG(extack, "Invalid source address length");
+		goto errout;
+	}
+
+	if (cfg->fc_nh_id && cfg->fc_src_len) {
+		NL_SET_ERR_MSG(extack, "Nexthops can not be used with source routing");
+		goto errout;
+	}
+#else
+	if (cfg->fc_src_len) {
+		NL_SET_ERR_MSG(extack,
+			       "Specifying source address requires IPV6_SUBTREES to be enabled");
+		goto errout;
+	}
+#endif
+	return 0;
+errout:
+	return -EINVAL;
+}
+
 static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg,
 					       gfp_t gfp_flags,
 					       struct netlink_ext_ack *extack)
@@ -3886,6 +3933,10 @@ int ip6_route_add(struct fib6_config *cfg, gfp_t gfp_flags,
 	struct fib6_info *rt;
 	int err;
 
+	err = fib6_config_validate(cfg, extack);
+	if (err)
+		return err;
+
 	rt = ip6_route_info_create(cfg, gfp_flags, extack);
 	if (IS_ERR(rt))
 		return PTR_ERR(rt);
@@ -4479,53 +4530,6 @@ void rt6_purge_dflt_routers(struct net *net)
 	rcu_read_unlock();
 }
 
-static int fib6_config_validate(struct fib6_config *cfg,
-				struct netlink_ext_ack *extack)
-{
-	/* RTF_PCPU is an internal flag; can not be set by userspace */
-	if (cfg->fc_flags & RTF_PCPU) {
-		NL_SET_ERR_MSG(extack, "Userspace can not set RTF_PCPU");
-		goto errout;
-	}
-
-	/* RTF_CACHE is an internal flag; can not be set by userspace */
-	if (cfg->fc_flags & RTF_CACHE) {
-		NL_SET_ERR_MSG(extack, "Userspace can not set RTF_CACHE");
-		goto errout;
-	}
-
-	if (cfg->fc_type > RTN_MAX) {
-		NL_SET_ERR_MSG(extack, "Invalid route type");
-		goto errout;
-	}
-
-	if (cfg->fc_dst_len > 128) {
-		NL_SET_ERR_MSG(extack, "Invalid prefix length");
-		goto errout;
-	}
-
-#ifdef CONFIG_IPV6_SUBTREES
-	if (cfg->fc_src_len > 128) {
-		NL_SET_ERR_MSG(extack, "Invalid source address length");
-		goto errout;
-	}
-
-	if (cfg->fc_nh_id && cfg->fc_src_len) {
-		NL_SET_ERR_MSG(extack, "Nexthops can not be used with source routing");
-		goto errout;
-	}
-#else
-	if (cfg->fc_src_len) {
-		NL_SET_ERR_MSG(extack,
-			       "Specifying source address requires IPV6_SUBTREES to be enabled");
-		goto errout;
-	}
-#endif
-	return 0;
-errout:
-	return -EINVAL;
-}
-
 static void rtmsg_to_fib6_config(struct net *net,
 				 struct in6_rtmsg *rtmsg,
 				 struct fib6_config *cfg)
@@ -4563,10 +4567,6 @@ int ipv6_route_ioctl(struct net *net, unsigned int cmd, struct in6_rtmsg *rtmsg)
 
 	switch (cmd) {
 	case SIOCADDRT:
-		err = fib6_config_validate(&cfg, NULL);
-		if (err)
-			break;
-
 		/* Only do the default setting of fc_metric in route adding */
 		if (cfg.fc_metric == 0)
 			cfg.fc_metric = IP6_RT_PRIO_USER;
@@ -5402,6 +5402,10 @@ static int ip6_route_multipath_add(struct fib6_config *cfg,
 	int nhn = 0;
 	int err;
 
+	err = fib6_config_validate(cfg, extack);
+	if (err)
+		return err;
+
 	replace = (cfg->fc_nlinfo.nlh &&
 		   (cfg->fc_nlinfo.nlh->nlmsg_flags & NLM_F_REPLACE));
 
@@ -5636,10 +5640,6 @@ static int inet6_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh,
 	if (err < 0)
 		return err;
 
-	err = fib6_config_validate(&cfg, extack);
-	if (err)
-		return err;
-
 	if (cfg.fc_metric == 0)
 		cfg.fc_metric = IP6_RT_PRIO_USER;
 

From 43fb2b30eea7cfc40214484935b026ec29838a91 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@google.com>
Date: Wed, 11 Jun 2025 13:27:35 -0700
Subject: [PATCH 0310/1334] af_unix: Allow passing cred for embryo without
 SO_PASSCRED/SO_PASSPIDFD.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Before the cited commit, the kernel unconditionally embedded SCM
credentials to skb for embryo sockets even when both the sender
and listener disabled SO_PASSCRED and SO_PASSPIDFD.

Now, the credentials are added to skb only when configured by the
sender or the listener.

However, as reported in the link below, it caused a regression for
some programs that assume credentials are included in every skb,
but sometimes not now.

The only problematic scenario would be that a socket starts listening
before setting the option.  Then, there will be 2 types of non-small
race window, where a client can send skb without credentials, which
the peer receives as an "invalid" message (and aborts the connection
it seems ?):

  Client                    Server
  ------                    ------
                            s1.listen()  <-- No SO_PASS{CRED,PIDFD}
  s2.connect()
  s2.send()  <-- w/o cred
                            s1.setsockopt(SO_PASS{CRED,PIDFD})
  s2.send()  <-- w/  cred

or

  Client                    Server
  ------                    ------
                            s1.listen()  <-- No SO_PASS{CRED,PIDFD}
  s2.connect()
  s2.send()  <-- w/o cred
                            s3, _ = s1.accept()  <-- Inherit cred options
  s2.send()  <-- w/o cred                            but not set yet

                            s3.setsockopt(SO_PASS{CRED,PIDFD})
  s2.send()  <-- w/  cred

It's unfortunate that buggy programs depend on the behaviour,
but let's restore the previous behaviour.

Fixes: 3f84d577b79d ("af_unix: Inherit sk_flags at connect().")
Reported-by: Jacek Łuczak <difrost.kernel@gmail.com>
Closes: https://lore.kernel.org/all/68d38b0b-1666-4974-85d4-15575789c8d4@gmail.com/
Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Tested-by: Christian Heusel <christian@heusel.eu>
Tested-by: André Almeida <andrealmeid@igalia.com>
Tested-by: Jacek Łuczak <difrost.kernel@gmail.com>
Link: https://patch.msgid.link/20250611202758.3075858-1-kuni1840@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/unix/af_unix.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 2e2e9997a68e..22e170fb5dda 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -1971,7 +1971,8 @@ static void unix_maybe_add_creds(struct sk_buff *skb, const struct sock *sk,
 	if (UNIXCB(skb).pid)
 		return;
 
-	if (unix_may_passcred(sk) || unix_may_passcred(other)) {
+	if (unix_may_passcred(sk) || unix_may_passcred(other) ||
+	    !other->sk_socket) {
 		UNIXCB(skb).pid = get_pid(task_tgid(current));
 		current_uid_gid(&UNIXCB(skb).uid, &UNIXCB(skb).gid);
 	}

From d78ebc772c7ceccf6e655ddb93099f49a1268af4 Mon Sep 17 00:00:00 2001
From: Gal Pressman <gal@nvidia.com>
Date: Thu, 12 Jun 2025 10:19:57 +0300
Subject: [PATCH 0311/1334] net: ethtool: Don't check if RSS context exists in
 case of context 0

Context 0 (default context) always exists, there is no need to check
whether it exists or not when adding a flow steering rule.

The existing check fails when creating a flow steering rule for context
0 as it is not stored in the rss_ctx xarray.

For example:
$ ethtool --config-ntuple eth2 flow-type tcp4 dst-ip 194.237.147.23 dst-port 19983 context 0 loc 618
rmgr: Cannot insert RX class rule: Invalid argument
Cannot insert classification rule

An example usecase for this could be:
- A high-priority rule (loc 0) directing specific port traffic to
  context 0.
- A low-priority rule (loc 1) directing all other TCP traffic to context
  1.

This is a user-visible regression that was caught in our testing
environment, it was not reported by a user yet.

Fixes: de7f7582dff2 ("net: ethtool: prevent flow steering to RSS contexts which don't exist")
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Nimrod Oren <noren@nvidia.com>
Signed-off-by: Gal Pressman <gal@nvidia.com>
Reviewed-by: Joe Damato <jdamato@fastly.com>
Reviewed-by: Edward Cree <ecree.xilinx@gmail.com>
Link: https://patch.msgid.link/20250612071958.1696361-2-gal@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ethtool/ioctl.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c
index 39ec920f5de7..71c828d0bf31 100644
--- a/net/ethtool/ioctl.c
+++ b/net/ethtool/ioctl.c
@@ -1083,7 +1083,8 @@ static noinline_for_stack int ethtool_set_rxnfc(struct net_device *dev,
 		    ethtool_get_flow_spec_ring(info.fs.ring_cookie))
 			return -EINVAL;
 
-		if (!xa_load(&dev->ethtool->rss_ctx, info.rss_context))
+		if (info.rss_context &&
+		    !xa_load(&dev->ethtool->rss_ctx, info.rss_context))
 			return -EINVAL;
 	}
 

From 56c5d291e88538621029e5c7c5f60540d37846a8 Mon Sep 17 00:00:00 2001
From: Gal Pressman <gal@nvidia.com>
Date: Thu, 12 Jun 2025 10:19:58 +0300
Subject: [PATCH 0312/1334] selftests: drv-net: rss_ctx: Add test for ntuple
 rules targeting default RSS context

Add test_rss_default_context_rule() to verify that ntuple rules can
correctly direct traffic to the default RSS context (context 0).

The test creates two ntuple rules with explicit location priorities:
- A high-priority rule (loc 0) directing specific port traffic to
  context 0.
- A low-priority rule (loc 1) directing all other TCP traffic to context
  1.

This validates that:
1. Rules targeting the default context function properly.
2. Traffic steering works as expected when mixing default and
   additional RSS contexts.

The test was written by AI, and reviewed by humans.

Reviewed-by: Nimrod Oren <noren@nvidia.com>
Signed-off-by: Gal Pressman <gal@nvidia.com>
Link: https://patch.msgid.link/20250612071958.1696361-3-gal@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../selftests/drivers/net/hw/rss_ctx.py       | 59 ++++++++++++++++++-
 1 file changed, 58 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/drivers/net/hw/rss_ctx.py b/tools/testing/selftests/drivers/net/hw/rss_ctx.py
index ca60ae325c22..7bb552f8b182 100755
--- a/tools/testing/selftests/drivers/net/hw/rss_ctx.py
+++ b/tools/testing/selftests/drivers/net/hw/rss_ctx.py
@@ -747,6 +747,62 @@ def test_rss_ntuple_addition(cfg):
                                                           'noise' : (0,) })
 
 
+def test_rss_default_context_rule(cfg):
+    """
+    Allocate a port, direct this port to context 0, then create a new RSS
+    context and steer all TCP traffic to it (context 1).  Verify that:
+      * Traffic to the specific port continues to use queues of the main
+        context (0/1).
+      * Traffic to any other TCP port is redirected to the new context
+        (queues 2/3).
+    """
+
+    require_ntuple(cfg)
+
+    queue_cnt = len(_get_rx_cnts(cfg))
+    if queue_cnt < 4:
+        try:
+            ksft_pr(f"Increasing queue count {queue_cnt} -> 4")
+            ethtool(f"-L {cfg.ifname} combined 4")
+            defer(ethtool, f"-L {cfg.ifname} combined {queue_cnt}")
+        except Exception as exc:
+            raise KsftSkipEx("Not enough queues for the test") from exc
+
+    # Use queues 0 and 1 for the main context
+    ethtool(f"-X {cfg.ifname} equal 2")
+    defer(ethtool, f"-X {cfg.ifname} default")
+
+    # Create a new RSS context that uses queues 2 and 3
+    ctx_id = ethtool_create(cfg, "-X", "context new start 2 equal 2")
+    defer(ethtool, f"-X {cfg.ifname} context {ctx_id} delete")
+
+    # Generic low-priority rule: redirect all TCP traffic to the new context.
+    # Give it an explicit higher location number (lower priority).
+    flow_generic = f"flow-type tcp{cfg.addr_ipver} dst-ip {cfg.addr} context {ctx_id} loc 1"
+    ethtool(f"-N {cfg.ifname} {flow_generic}")
+    defer(ethtool, f"-N {cfg.ifname} delete 1")
+
+    # Specific high-priority rule for a random port that should stay on context 0.
+    # Assign loc 0 so it is evaluated before the generic rule.
+    port_main = rand_port()
+    flow_main = f"flow-type tcp{cfg.addr_ipver} dst-ip {cfg.addr} dst-port {port_main} context 0 loc 0"
+    ethtool(f"-N {cfg.ifname} {flow_main}")
+    defer(ethtool, f"-N {cfg.ifname} delete 0")
+
+    _ntuple_rule_check(cfg, 1, ctx_id)
+
+    # Verify that traffic matching the specific rule still goes to queues 0/1
+    _send_traffic_check(cfg, port_main, "context 0",
+                        { 'target': (0, 1),
+                          'empty' : (2, 3) })
+
+    # And that traffic for any other port is steered to the new context
+    port_other = rand_port()
+    _send_traffic_check(cfg, port_other, f"context {ctx_id}",
+                        { 'target': (2, 3),
+                          'noise' : (0, 1) })
+
+
 def main() -> None:
     with NetDrvEpEnv(__file__, nsim_test=False) as cfg:
         cfg.context_cnt = None
@@ -760,7 +816,8 @@ def main() -> None:
                   test_rss_context_overlap, test_rss_context_overlap2,
                   test_rss_context_out_of_order, test_rss_context4_create_with_cfg,
                   test_flow_add_context_missing,
-                  test_delete_rss_context_busy, test_rss_ntuple_addition],
+                  test_delete_rss_context_busy, test_rss_ntuple_addition,
+                  test_rss_default_context_rule],
                  args=(cfg, ))
     ksft_exit()
 

From 9c7632faad434c98f1f2cc06f3647a5a5d05ddbf Mon Sep 17 00:00:00 2001
From: Lucas De Marchi <lucas.demarchi@intel.com>
Date: Wed, 4 Jun 2025 08:03:05 -0700
Subject: [PATCH 0313/1334] drm/xe/lrc: Use a temporary buffer for WA BB
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In case the BO is in iomem, we can't simply take the vaddr and write to
it. Instead, prepare a separate buffer that is later copied into io
memory. Right now it's just a few words that could be using
xe_map_write32(), but the intention is to grow the WA BB for other
uses.

Fixes: 617d824c5323 ("drm/xe: Add WA BB to capture active context utilization")
Cc: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@igalia.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Link: https://lore.kernel.org/r/20250604-wa-bb-fix-v1-1-0dfc5dafcef0@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
(cherry picked from commit ef48715b2d3df17c060e23b9aa636af3d95652f8)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
---
 drivers/gpu/drm/xe/xe_lrc.c | 24 ++++++++++++++++++++----
 1 file changed, 20 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_lrc.c b/drivers/gpu/drm/xe/xe_lrc.c
index 63d74e27f54c..bf7c3981897d 100644
--- a/drivers/gpu/drm/xe/xe_lrc.c
+++ b/drivers/gpu/drm/xe/xe_lrc.c
@@ -941,11 +941,18 @@ static void xe_lrc_finish(struct xe_lrc *lrc)
  * store it in the PPHSWP.
  */
 #define CONTEXT_ACTIVE 1ULL
-static void xe_lrc_setup_utilization(struct xe_lrc *lrc)
+static int xe_lrc_setup_utilization(struct xe_lrc *lrc)
 {
-	u32 *cmd;
+	u32 *cmd, *buf = NULL;
 
-	cmd = lrc->bb_per_ctx_bo->vmap.vaddr;
+	if (lrc->bb_per_ctx_bo->vmap.is_iomem) {
+		buf = kmalloc(lrc->bb_per_ctx_bo->size, GFP_KERNEL);
+		if (!buf)
+			return -ENOMEM;
+		cmd = buf;
+	} else {
+		cmd = lrc->bb_per_ctx_bo->vmap.vaddr;
+	}
 
 	*cmd++ = MI_STORE_REGISTER_MEM | MI_SRM_USE_GGTT | MI_SRM_ADD_CS_OFFSET;
 	*cmd++ = ENGINE_ID(0).addr;
@@ -966,9 +973,16 @@ static void xe_lrc_setup_utilization(struct xe_lrc *lrc)
 
 	*cmd++ = MI_BATCH_BUFFER_END;
 
+	if (buf) {
+		xe_map_memcpy_to(gt_to_xe(lrc->gt), &lrc->bb_per_ctx_bo->vmap, 0,
+				 buf, (cmd - buf) * sizeof(*cmd));
+		kfree(buf);
+	}
+
 	xe_lrc_write_ctx_reg(lrc, CTX_BB_PER_CTX_PTR,
 			     xe_bo_ggtt_addr(lrc->bb_per_ctx_bo) | 1);
 
+	return 0;
 }
 
 #define PVC_CTX_ASID		(0x2e + 1)
@@ -1125,7 +1139,9 @@ static int xe_lrc_init(struct xe_lrc *lrc, struct xe_hw_engine *hwe,
 	map = __xe_lrc_start_seqno_map(lrc);
 	xe_map_write32(lrc_to_xe(lrc), &map, lrc->fence_ctx.next_seqno - 1);
 
-	xe_lrc_setup_utilization(lrc);
+	err = xe_lrc_setup_utilization(lrc);
+	if (err)
+		goto err_lrc_finish;
 
 	return 0;
 

From d2be3270f40b1330f8c1c9512c59dd085a758ac0 Mon Sep 17 00:00:00 2001
From: Mark Brown <broonie@kernel.org>
Date: Wed, 11 Jun 2025 17:28:13 +0100
Subject: [PATCH 0314/1334] arm64/gcs: Don't call gcs_free() during flush_gcs()

Currently we call gcs_free() during flush_gcs() to reset the thread
state for GCS. This includes unmapping any kernel allocated GCS, but
this is redundant when doing a flush_thread() since we are
reinitialising the thread memory too. Inline the reinitialisation of the
thread struct.

Signed-off-by: Mark Brown <broonie@kernel.org>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Link: https://lore.kernel.org/r/20250611-arm64-gcs-flush-thread-v1-1-cc26feeddabd@kernel.org
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/kernel/process.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index a5ca15daeb8a..5954cec19660 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -288,7 +288,9 @@ static void flush_gcs(void)
 	if (!system_supports_gcs())
 		return;
 
-	gcs_free(current);
+	current->thread.gcspr_el0 = 0;
+	current->thread.gcs_base = 0;
+	current->thread.gcs_size = 0;
 	current->thread.gcs_el0_mode = 0;
 	write_sysreg_s(GCSCRE0_EL1_nTR, SYS_GCSCRE0_EL1);
 	write_sysreg_s(0, SYS_GCSPR_EL0);

From 39dfc971e42d886e7df01371cd1bef505076d84c Mon Sep 17 00:00:00 2001
From: Tengda Wu <wutengda@huaweicloud.com>
Date: Wed, 4 Jun 2025 00:55:33 +0000
Subject: [PATCH 0315/1334] arm64/ptrace: Fix stack-out-of-bounds read in
 regs_get_kernel_stack_nth()

KASAN reports a stack-out-of-bounds read in regs_get_kernel_stack_nth().

Call Trace:
[   97.283505] BUG: KASAN: stack-out-of-bounds in regs_get_kernel_stack_nth+0xa8/0xc8
[   97.284677] Read of size 8 at addr ffff800089277c10 by task 1.sh/2550
[   97.285732]
[   97.286067] CPU: 7 PID: 2550 Comm: 1.sh Not tainted 6.6.0+ #11
[   97.287032] Hardware name: linux,dummy-virt (DT)
[   97.287815] Call trace:
[   97.288279]  dump_backtrace+0xa0/0x128
[   97.288946]  show_stack+0x20/0x38
[   97.289551]  dump_stack_lvl+0x78/0xc8
[   97.290203]  print_address_description.constprop.0+0x84/0x3c8
[   97.291159]  print_report+0xb0/0x280
[   97.291792]  kasan_report+0x84/0xd0
[   97.292421]  __asan_load8+0x9c/0xc0
[   97.293042]  regs_get_kernel_stack_nth+0xa8/0xc8
[   97.293835]  process_fetch_insn+0x770/0xa30
[   97.294562]  kprobe_trace_func+0x254/0x3b0
[   97.295271]  kprobe_dispatcher+0x98/0xe0
[   97.295955]  kprobe_breakpoint_handler+0x1b0/0x210
[   97.296774]  call_break_hook+0xc4/0x100
[   97.297451]  brk_handler+0x24/0x78
[   97.298073]  do_debug_exception+0xac/0x178
[   97.298785]  el1_dbg+0x70/0x90
[   97.299344]  el1h_64_sync_handler+0xcc/0xe8
[   97.300066]  el1h_64_sync+0x78/0x80
[   97.300699]  kernel_clone+0x0/0x500
[   97.301331]  __arm64_sys_clone+0x70/0x90
[   97.302084]  invoke_syscall+0x68/0x198
[   97.302746]  el0_svc_common.constprop.0+0x11c/0x150
[   97.303569]  do_el0_svc+0x38/0x50
[   97.304164]  el0_svc+0x44/0x1d8
[   97.304749]  el0t_64_sync_handler+0x100/0x130
[   97.305500]  el0t_64_sync+0x188/0x190
[   97.306151]
[   97.306475] The buggy address belongs to stack of task 1.sh/2550
[   97.307461]  and is located at offset 0 in frame:
[   97.308257]  __se_sys_clone+0x0/0x138
[   97.308910]
[   97.309241] This frame has 1 object:
[   97.309873]  [48, 184) 'args'
[   97.309876]
[   97.310749] The buggy address belongs to the virtual mapping at
[   97.310749]  [ffff800089270000, ffff800089279000) created by:
[   97.310749]  dup_task_struct+0xc0/0x2e8
[   97.313347]
[   97.313674] The buggy address belongs to the physical page:
[   97.314604] page: refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x14f69a
[   97.315885] flags: 0x15ffffe00000000(node=1|zone=2|lastcpupid=0xfffff)
[   97.316957] raw: 015ffffe00000000 0000000000000000 dead000000000122 0000000000000000
[   97.318207] raw: 0000000000000000 0000000000000000 00000001ffffffff 0000000000000000
[   97.319445] page dumped because: kasan: bad access detected
[   97.320371]
[   97.320694] Memory state around the buggy address:
[   97.321511]  ffff800089277b00: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
[   97.322681]  ffff800089277b80: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
[   97.323846] >ffff800089277c00: 00 00 f1 f1 f1 f1 f1 f1 00 00 00 00 00 00 00 00
[   97.325023]                          ^
[   97.325683]  ffff800089277c80: 00 00 00 00 00 00 00 00 00 f3 f3 f3 f3 f3 f3 f3
[   97.326856]  ffff800089277d00: f3 f3 00 00 00 00 00 00 00 00 00 00 00 00 00 00

This issue seems to be related to the behavior of some gcc compilers and
was also fixed on the s390 architecture before:

 commit d93a855c31b7 ("s390/ptrace: Avoid KASAN false positives in regs_get_kernel_stack_nth()")

As described in that commit, regs_get_kernel_stack_nth() has confirmed that
`addr` is on the stack, so reading the value at `*addr` should be allowed.
Use READ_ONCE_NOCHECK() helper to silence the KASAN check for this case.

Fixes: 0a8ea52c3eb1 ("arm64: Add HAVE_REGS_AND_STACK_ACCESS_API feature")
Signed-off-by: Tengda Wu <wutengda@huaweicloud.com>
Link: https://lore.kernel.org/r/20250604005533.1278992-1-wutengda@huaweicloud.com
[will: Use '*addr' as the argument to READ_ONCE_NOCHECK()]
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/kernel/ptrace.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index a360e52db02f..ee94b72bf8fb 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -141,7 +141,7 @@ unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs, unsigned int n)
 
 	addr += n;
 	if (regs_within_kernel_stack(regs, (unsigned long)addr))
-		return *addr;
+		return READ_ONCE_NOCHECK(*addr);
 	else
 		return 0;
 }

From b64af6bcd3b0f3fc633d6a70adb0991737abfef4 Mon Sep 17 00:00:00 2001
From: Paulo Alcantara <pc@manguebit.org>
Date: Thu, 12 Jun 2025 12:45:04 -0300
Subject: [PATCH 0316/1334] smb: client: fix perf regression with deferred
 closes

Customer reported that one of their applications started failing to
open files with STATUS_INSUFFICIENT_RESOURCES due to NetApp server
hitting the maximum number of opens to same file that it would allow
for a single client connection.

It turned out the client was failing to reuse open handles with
deferred closes because matching ->f_flags directly without masking
off O_CREAT|O_EXCL|O_TRUNC bits first broke the comparision and then
client ended up with thousands of deferred closes to same file.  Those
bits are already satisfied on the original open, so no need to check
them against existing open handles.

Reproducer:

 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
 #include <unistd.h>
 #include <fcntl.h>
 #include <pthread.h>

 #define NR_THREADS      4
 #define NR_ITERATIONS   2500
 #define TEST_FILE       "/mnt/1/test/dir/foo"

 static char buf[64];

 static void *worker(void *arg)
 {
         int i, j;
         int fd;

         for (i = 0; i < NR_ITERATIONS; i++) {
                 fd = open(TEST_FILE, O_WRONLY|O_CREAT|O_APPEND, 0666);
                 for (j = 0; j < 16; j++)
                         write(fd, buf, sizeof(buf));
                 close(fd);
         }
 }

 int main(int argc, char *argv[])
 {
         pthread_t t[NR_THREADS];
         int fd;
         int i;

         fd = open(TEST_FILE, O_WRONLY|O_CREAT|O_TRUNC, 0666);
         close(fd);
         memset(buf, 'a', sizeof(buf));
         for (i = 0; i < NR_THREADS; i++)
                 pthread_create(&t[i], NULL, worker, NULL);
         for (i = 0; i < NR_THREADS; i++)
                 pthread_join(t[i], NULL);
         return 0;
 }

Before patch:

$ mount.cifs //srv/share /mnt/1 -o ...
$ mkdir -p /mnt/1/test/dir
$ gcc repro.c && ./a.out
...
number of opens: 1391

After patch:

$ mount.cifs //srv/share /mnt/1 -o ...
$ mkdir -p /mnt/1/test/dir
$ gcc repro.c && ./a.out
...
number of opens: 1

Cc: linux-cifs@vger.kernel.org
Cc: David Howells <dhowells@redhat.com>
Cc: Jay Shin <jaeshin@redhat.com>
Cc: Pierguido Lambri <plambri@redhat.com>
Fixes: b8ea3b1ff544 ("smb: enable reuse of deferred file handles for write operations")
Acked-by: Shyam Prasad N <sprasad@microsoft.com>
Signed-off-by: Paulo Alcantara (Red Hat) <pc@manguebit.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/file.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c
index d2df10b8e6fd..9835672267d2 100644
--- a/fs/smb/client/file.c
+++ b/fs/smb/client/file.c
@@ -999,15 +999,18 @@ int cifs_open(struct inode *inode, struct file *file)
 		rc = cifs_get_readable_path(tcon, full_path, &cfile);
 	}
 	if (rc == 0) {
-		if (file->f_flags == cfile->f_flags) {
+		unsigned int oflags = file->f_flags & ~(O_CREAT|O_EXCL|O_TRUNC);
+		unsigned int cflags = cfile->f_flags & ~(O_CREAT|O_EXCL|O_TRUNC);
+
+		if (cifs_convert_flags(oflags, 0) == cifs_convert_flags(cflags, 0) &&
+		    (oflags & (O_SYNC|O_DIRECT)) == (cflags & (O_SYNC|O_DIRECT))) {
 			file->private_data = cfile;
 			spin_lock(&CIFS_I(inode)->deferred_lock);
 			cifs_del_deferred_close(cfile);
 			spin_unlock(&CIFS_I(inode)->deferred_lock);
 			goto use_cache;
-		} else {
-			_cifsFileInfo_put(cfile, true, false);
 		}
+		_cifsFileInfo_put(cfile, true, false);
 	} else {
 		/* hard link on the defeered close file */
 		rc = cifs_get_hardlink_path(tcon, inode, file);

From 72dd7961a4bb4fa1fc456169a61dd12e68e50645 Mon Sep 17 00:00:00 2001
From: Bharath SM <bharathsm.hsk@gmail.com>
Date: Wed, 11 Jun 2025 16:59:02 +0530
Subject: [PATCH 0317/1334] smb: improve directory cache reuse for readdir
 operations

Currently, cached directory contents were not reused across subsequent
'ls' operations because the cache validity check relied on comparing
the ctx pointer, which changes with each readdir invocation. As a
result, the cached dir entries was not marked as valid and the cache was
not utilized for subsequent 'ls' operations.

This change uses the file pointer, which remains consistent across all
readdir calls for a given directory instance, to associate and validate
the cache. As a result, cached directory contents can now be
correctly reused, improving performance for repeated directory listings.

Performance gains with local windows SMB server:

Without the patch and default actimeo=1:
 1000 directory enumeration operations on dir with 10k files took 135.0s

With this patch and actimeo=0:
 1000 directory enumeration operations on dir with 10k files took just 5.1s

Signed-off-by: Bharath SM <bharathsm@microsoft.com>
Reviewed-by: Shyam Prasad N <sprasad@microsoft.com>
Cc: stable@vger.kernel.org
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/cached_dir.h |  8 ++++----
 fs/smb/client/readdir.c    | 28 +++++++++++++++-------------
 2 files changed, 19 insertions(+), 17 deletions(-)

diff --git a/fs/smb/client/cached_dir.h b/fs/smb/client/cached_dir.h
index 1dfe79d947a6..bc8a812ff95f 100644
--- a/fs/smb/client/cached_dir.h
+++ b/fs/smb/client/cached_dir.h
@@ -21,10 +21,10 @@ struct cached_dirent {
 struct cached_dirents {
 	bool is_valid:1;
 	bool is_failed:1;
-	struct dir_context *ctx; /*
-				  * Only used to make sure we only take entries
-				  * from a single context. Never dereferenced.
-				  */
+	struct file *file; /*
+			    * Used to associate the cache with a single
+			    * open file instance.
+			    */
 	struct mutex de_mutex;
 	int pos;		 /* Expected ctx->pos */
 	struct list_head entries;
diff --git a/fs/smb/client/readdir.c b/fs/smb/client/readdir.c
index f9f11cbf89be..ba0193cf9033 100644
--- a/fs/smb/client/readdir.c
+++ b/fs/smb/client/readdir.c
@@ -851,9 +851,9 @@ static bool emit_cached_dirents(struct cached_dirents *cde,
 }
 
 static void update_cached_dirents_count(struct cached_dirents *cde,
-					struct dir_context *ctx)
+					struct file *file)
 {
-	if (cde->ctx != ctx)
+	if (cde->file != file)
 		return;
 	if (cde->is_valid || cde->is_failed)
 		return;
@@ -862,9 +862,9 @@ static void update_cached_dirents_count(struct cached_dirents *cde,
 }
 
 static void finished_cached_dirents_count(struct cached_dirents *cde,
-					struct dir_context *ctx)
+					struct dir_context *ctx, struct file *file)
 {
-	if (cde->ctx != ctx)
+	if (cde->file != file)
 		return;
 	if (cde->is_valid || cde->is_failed)
 		return;
@@ -877,11 +877,12 @@ static void finished_cached_dirents_count(struct cached_dirents *cde,
 static void add_cached_dirent(struct cached_dirents *cde,
 			      struct dir_context *ctx,
 			      const char *name, int namelen,
-			      struct cifs_fattr *fattr)
+			      struct cifs_fattr *fattr,
+				  struct file *file)
 {
 	struct cached_dirent *de;
 
-	if (cde->ctx != ctx)
+	if (cde->file != file)
 		return;
 	if (cde->is_valid || cde->is_failed)
 		return;
@@ -911,7 +912,8 @@ static void add_cached_dirent(struct cached_dirents *cde,
 static bool cifs_dir_emit(struct dir_context *ctx,
 			  const char *name, int namelen,
 			  struct cifs_fattr *fattr,
-			  struct cached_fid *cfid)
+			  struct cached_fid *cfid,
+			  struct file *file)
 {
 	bool rc;
 	ino_t ino = cifs_uniqueid_to_ino_t(fattr->cf_uniqueid);
@@ -923,7 +925,7 @@ static bool cifs_dir_emit(struct dir_context *ctx,
 	if (cfid) {
 		mutex_lock(&cfid->dirents.de_mutex);
 		add_cached_dirent(&cfid->dirents, ctx, name, namelen,
-				  fattr);
+				  fattr, file);
 		mutex_unlock(&cfid->dirents.de_mutex);
 	}
 
@@ -1023,7 +1025,7 @@ static int cifs_filldir(char *find_entry, struct file *file,
 	cifs_prime_dcache(file_dentry(file), &name, &fattr);
 
 	return !cifs_dir_emit(ctx, name.name, name.len,
-			      &fattr, cfid);
+			      &fattr, cfid, file);
 }
 
 
@@ -1074,8 +1076,8 @@ int cifs_readdir(struct file *file, struct dir_context *ctx)
 	 * we need to initialize scanning and storing the
 	 * directory content.
 	 */
-	if (ctx->pos == 0 && cfid->dirents.ctx == NULL) {
-		cfid->dirents.ctx = ctx;
+	if (ctx->pos == 0 && cfid->dirents.file == NULL) {
+		cfid->dirents.file = file;
 		cfid->dirents.pos = 2;
 	}
 	/*
@@ -1143,7 +1145,7 @@ int cifs_readdir(struct file *file, struct dir_context *ctx)
 	} else {
 		if (cfid) {
 			mutex_lock(&cfid->dirents.de_mutex);
-			finished_cached_dirents_count(&cfid->dirents, ctx);
+			finished_cached_dirents_count(&cfid->dirents, ctx, file);
 			mutex_unlock(&cfid->dirents.de_mutex);
 		}
 		cifs_dbg(FYI, "Could not find entry\n");
@@ -1184,7 +1186,7 @@ int cifs_readdir(struct file *file, struct dir_context *ctx)
 		ctx->pos++;
 		if (cfid) {
 			mutex_lock(&cfid->dirents.de_mutex);
-			update_cached_dirents_count(&cfid->dirents, ctx);
+			update_cached_dirents_count(&cfid->dirents, file);
 			mutex_unlock(&cfid->dirents.de_mutex);
 		}
 

From 4262bd0d9cc704ea1365ac00afc1272400c2cbef Mon Sep 17 00:00:00 2001
From: Han Gao <rabenda.cn@gmail.com>
Date: Fri, 23 May 2025 18:25:56 +0800
Subject: [PATCH 0318/1334] riscv: vector: Fix context save/restore with
 xtheadvector

Previously only v0-v7 were correctly saved/restored,
and the context of v8-v31 are damanged.
Correctly save/restore v8-v31 to avoid breaking userspace.

Fixes: d863910eabaf ("riscv: vector: Support xtheadvector save/restore")
Cc: stable@vger.kernel.org
Signed-off-by: Han Gao <rabenda.cn@gmail.com>
Tested-by: Xiongchuan Tan <tanxiongchuan@isrc.iscas.ac.cn>
Reviewed-by: Charlie Jenkins <charlie@rivosinc.com>
Reviewed-by: Yanteng Si <si.yanteng@linux.dev>
Reviewed-by: Andy Chiu <andybnac@gmail.com>
Link: https://lore.kernel.org/r/9b9eb2337f3d5336ce813721f8ebea51e0b2b553.1747994822.git.rabenda.cn@gmail.com
Signed-off-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Signed-off-by: Palmer Dabbelt <palmer@dabbelt.com>
---
 arch/riscv/include/asm/vector.h | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/arch/riscv/include/asm/vector.h b/arch/riscv/include/asm/vector.h
index 45c9b426fcc5..b61786d43c20 100644
--- a/arch/riscv/include/asm/vector.h
+++ b/arch/riscv/include/asm/vector.h
@@ -205,11 +205,11 @@ static inline void __riscv_v_vstate_save(struct __riscv_v_ext_state *save_to,
 			THEAD_VSETVLI_T4X0E8M8D1
 			THEAD_VSB_V_V0T0
 			"add		t0, t0, t4\n\t"
-			THEAD_VSB_V_V0T0
+			THEAD_VSB_V_V8T0
 			"add		t0, t0, t4\n\t"
-			THEAD_VSB_V_V0T0
+			THEAD_VSB_V_V16T0
 			"add		t0, t0, t4\n\t"
-			THEAD_VSB_V_V0T0
+			THEAD_VSB_V_V24T0
 			: : "r" (datap) : "memory", "t0", "t4");
 	} else {
 		asm volatile (
@@ -241,11 +241,11 @@ static inline void __riscv_v_vstate_restore(struct __riscv_v_ext_state *restore_
 			THEAD_VSETVLI_T4X0E8M8D1
 			THEAD_VLB_V_V0T0
 			"add		t0, t0, t4\n\t"
-			THEAD_VLB_V_V0T0
+			THEAD_VLB_V_V8T0
 			"add		t0, t0, t4\n\t"
-			THEAD_VLB_V_V0T0
+			THEAD_VLB_V_V16T0
 			"add		t0, t0, t4\n\t"
-			THEAD_VLB_V_V0T0
+			THEAD_VLB_V_V24T0
 			: : "r" (datap) : "memory", "t0", "t4");
 	} else {
 		asm volatile (

From 2b9518684f8558cd61a7c608cc03a27822cf7b03 Mon Sep 17 00:00:00 2001
From: Xi Ruoyao <xry111@xry111.site>
Date: Fri, 6 Jun 2025 17:24:44 +0800
Subject: [PATCH 0319/1334] RISC-V: vDSO: Correct inline assembly constraints
 in the getrandom syscall wrapper
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

As recently pointed out by Thomas, if a register is forced for two
different register variables, among them one is used as "+" (both input
and output) and another is only used as input, Clang would treat the
conflicting input parameters as undefined behaviour and optimize away
the argument assignment.

Instead use "=r" (only output) for the output parameter and "r" (only
input) for the input parameter.
While the example from the GCC documentation uses "0" for the input
parameter, this is not necessary as confirmed by the GCC developers and "r"
matches what the other architectures' vDSO implementations are using.

[ alex: Update log to match v2 (Thomas) ]

Link: https://lore.kernel.org/all/20250603-loongarch-vdso-syscall-v1-1-6d12d6dfbdd0@linutronix.de/
Link: https://gcc.gnu.org/onlinedocs/gcc-15.1.0/gcc/Local-Register-Variables.html
Link: https://gcc.gnu.org/pipermail/gcc-help/2025-June/144266.html
Cc: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Cc: Nathan Chancellor <nathan@kernel.org>
Signed-off-by: Xi Ruoyao <xry111@xry111.site>
Reviewed-by: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Fixes: ee0d03053e70 ("RISC-V: vDSO: Wire up getrandom() vDSO")
Link: https://lore.kernel.org/r/20250606092443.73650-2-xry111@xry111.site
Signed-off-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Signed-off-by: Palmer Dabbelt <palmer@dabbelt.com>
---
 arch/riscv/include/asm/vdso/getrandom.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/riscv/include/asm/vdso/getrandom.h b/arch/riscv/include/asm/vdso/getrandom.h
index 8dc92441702a..c6d66895c1f5 100644
--- a/arch/riscv/include/asm/vdso/getrandom.h
+++ b/arch/riscv/include/asm/vdso/getrandom.h
@@ -18,7 +18,7 @@ static __always_inline ssize_t getrandom_syscall(void *_buffer, size_t _len, uns
 	register unsigned int flags asm("a2") = _flags;
 
 	asm volatile ("ecall\n"
-		      : "+r" (ret)
+		      : "=r" (ret)
 		      : "r" (nr), "r" (buffer), "r" (len), "r" (flags)
 		      : "memory");
 

From bc75552b80e6683b2def5a0459433607ea4788f5 Mon Sep 17 00:00:00 2001
From: Chunyan Zhang <zhangchunyan@iscas.ac.cn>
Date: Tue, 10 Jun 2025 18:12:32 +0800
Subject: [PATCH 0320/1334] raid6: riscv: Fix NULL pointer dereference caused
 by a missing clobber

When running the raid6 user-space test program on RISC-V QEMU, there's a
segmentation fault which seems caused by accessing a NULL pointer,
which is the pointer variable p/q in raid6_rvv*_gen/xor_syndrome_real(),
p/q should have been equal to dptr[x], but when I use GDB command to
see its value, which was 0x10 like below:

"
Program received signal SIGSEGV, Segmentation fault.
0x0000000000011062 in raid6_rvv2_xor_syndrome_real (disks=<optimized out>, start=0, stop=<optimized out>, bytes=4096, ptrs=<optimized out>) at rvv.c:386
(gdb) p p
$1 = (u8 *) 0x10 <error: Cannot access memory at address 0x10>
"

The issue was found to be related with:
1) Compile optimization
   There's no segmentation fault if compiling the raid6test program with
   the optimization flag -O0.
2) The RISC-V vector command vsetvli
   If not used t0 as the first parameter in vsetvli, there's no
   segmentation fault either.

This patch selects the 2nd solution to fix the issue.

[Palmer: The actual issue here is a missing clobber in the vsetvli code.
It's a little tricky: we've already probed for VLENB so we don't need to
look at the output register, we just need to have an X register in the
instruction as that's the form required to actually set VL.  Thus we
clobber a register, and without describing that we end up breaking
compilers.]

Fixes: 6093faaf9593 ("raid6: Add RISC-V SIMD syndrome and recovery calculations")
Signed-off-by: Chunyan Zhang <zhangchunyan@iscas.ac.cn>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20250610101234.1100660-3-zhangchunyan@iscas.ac.cn
Signed-off-by: Palmer Dabbelt <palmer@dabbelt.com>
---
 lib/raid6/rvv.c | 48 ++++++++++++++++++++++++++++--------------------
 1 file changed, 28 insertions(+), 20 deletions(-)

diff --git a/lib/raid6/rvv.c b/lib/raid6/rvv.c
index f0887344b274..7d82efa5b14f 100644
--- a/lib/raid6/rvv.c
+++ b/lib/raid6/rvv.c
@@ -26,9 +26,9 @@ static int rvv_has_vector(void)
 static void raid6_rvv1_gen_syndrome_real(int disks, unsigned long bytes, void **ptrs)
 {
 	u8 **dptr = (u8 **)ptrs;
-	unsigned long d;
-	int z, z0;
 	u8 *p, *q;
+	unsigned long vl, d;
+	int z, z0;
 
 	z0 = disks - 3;		/* Highest data disk */
 	p = dptr[z0 + 1];		/* XOR parity */
@@ -36,8 +36,9 @@ static void raid6_rvv1_gen_syndrome_real(int disks, unsigned long bytes, void **
 
 	asm volatile (".option	push\n"
 		      ".option	arch,+v\n"
-		      "vsetvli	t0, x0, e8, m1, ta, ma\n"
+		      "vsetvli	%0, x0, e8, m1, ta, ma\n"
 		      ".option	pop\n"
+		      : "=&r" (vl)
 	);
 
 	 /* v0:wp0, v1:wq0, v2:wd0/w20, v3:w10 */
@@ -99,7 +100,7 @@ static void raid6_rvv1_xor_syndrome_real(int disks, int start, int stop,
 {
 	u8 **dptr = (u8 **)ptrs;
 	u8 *p, *q;
-	unsigned long d;
+	unsigned long vl, d;
 	int z, z0;
 
 	z0 = stop;		/* P/Q right side optimization */
@@ -108,8 +109,9 @@ static void raid6_rvv1_xor_syndrome_real(int disks, int start, int stop,
 
 	asm volatile (".option	push\n"
 		      ".option	arch,+v\n"
-		      "vsetvli	t0, x0, e8, m1, ta, ma\n"
+		      "vsetvli	%0, x0, e8, m1, ta, ma\n"
 		      ".option	pop\n"
+		      : "=&r" (vl)
 	);
 
 	/* v0:wp0, v1:wq0, v2:wd0/w20, v3:w10 */
@@ -195,9 +197,9 @@ static void raid6_rvv1_xor_syndrome_real(int disks, int start, int stop,
 static void raid6_rvv2_gen_syndrome_real(int disks, unsigned long bytes, void **ptrs)
 {
 	u8 **dptr = (u8 **)ptrs;
-	unsigned long d;
-	int z, z0;
 	u8 *p, *q;
+	unsigned long vl, d;
+	int z, z0;
 
 	z0 = disks - 3;		/* Highest data disk */
 	p = dptr[z0 + 1];		/* XOR parity */
@@ -205,8 +207,9 @@ static void raid6_rvv2_gen_syndrome_real(int disks, unsigned long bytes, void **
 
 	asm volatile (".option	push\n"
 		      ".option	arch,+v\n"
-		      "vsetvli	t0, x0, e8, m1, ta, ma\n"
+		      "vsetvli	%0, x0, e8, m1, ta, ma\n"
 		      ".option	pop\n"
+		      : "=&r" (vl)
 	);
 
 	/*
@@ -287,7 +290,7 @@ static void raid6_rvv2_xor_syndrome_real(int disks, int start, int stop,
 {
 	u8 **dptr = (u8 **)ptrs;
 	u8 *p, *q;
-	unsigned long d;
+	unsigned long vl, d;
 	int z, z0;
 
 	z0 = stop;		/* P/Q right side optimization */
@@ -296,8 +299,9 @@ static void raid6_rvv2_xor_syndrome_real(int disks, int start, int stop,
 
 	asm volatile (".option	push\n"
 		      ".option	arch,+v\n"
-		      "vsetvli	t0, x0, e8, m1, ta, ma\n"
+		      "vsetvli	%0, x0, e8, m1, ta, ma\n"
 		      ".option	pop\n"
+		      : "=&r" (vl)
 	);
 
 	/*
@@ -413,9 +417,9 @@ static void raid6_rvv2_xor_syndrome_real(int disks, int start, int stop,
 static void raid6_rvv4_gen_syndrome_real(int disks, unsigned long bytes, void **ptrs)
 {
 	u8 **dptr = (u8 **)ptrs;
-	unsigned long d;
-	int z, z0;
 	u8 *p, *q;
+	unsigned long vl, d;
+	int z, z0;
 
 	z0 = disks - 3;	/* Highest data disk */
 	p = dptr[z0 + 1];	/* XOR parity */
@@ -423,8 +427,9 @@ static void raid6_rvv4_gen_syndrome_real(int disks, unsigned long bytes, void **
 
 	asm volatile (".option	push\n"
 		      ".option	arch,+v\n"
-		      "vsetvli	t0, x0, e8, m1, ta, ma\n"
+		      "vsetvli	%0, x0, e8, m1, ta, ma\n"
 		      ".option	pop\n"
+		      : "=&r" (vl)
 	);
 
 	/*
@@ -539,7 +544,7 @@ static void raid6_rvv4_xor_syndrome_real(int disks, int start, int stop,
 {
 	u8 **dptr = (u8 **)ptrs;
 	u8 *p, *q;
-	unsigned long d;
+	unsigned long vl, d;
 	int z, z0;
 
 	z0 = stop;		/* P/Q right side optimization */
@@ -548,8 +553,9 @@ static void raid6_rvv4_xor_syndrome_real(int disks, int start, int stop,
 
 	asm volatile (".option	push\n"
 		      ".option	arch,+v\n"
-		      "vsetvli	t0, x0, e8, m1, ta, ma\n"
+		      "vsetvli	%0, x0, e8, m1, ta, ma\n"
 		      ".option	pop\n"
+		      : "=&r" (vl)
 	);
 
 	/*
@@ -721,9 +727,9 @@ static void raid6_rvv4_xor_syndrome_real(int disks, int start, int stop,
 static void raid6_rvv8_gen_syndrome_real(int disks, unsigned long bytes, void **ptrs)
 {
 	u8 **dptr = (u8 **)ptrs;
-	unsigned long d;
-	int z, z0;
 	u8 *p, *q;
+	unsigned long vl, d;
+	int z, z0;
 
 	z0 = disks - 3;	/* Highest data disk */
 	p = dptr[z0 + 1];	/* XOR parity */
@@ -731,8 +737,9 @@ static void raid6_rvv8_gen_syndrome_real(int disks, unsigned long bytes, void **
 
 	asm volatile (".option	push\n"
 		      ".option	arch,+v\n"
-		      "vsetvli	t0, x0, e8, m1, ta, ma\n"
+		      "vsetvli	%0, x0, e8, m1, ta, ma\n"
 		      ".option	pop\n"
+		      : "=&r" (vl)
 	);
 
 	/*
@@ -915,7 +922,7 @@ static void raid6_rvv8_xor_syndrome_real(int disks, int start, int stop,
 {
 	u8 **dptr = (u8 **)ptrs;
 	u8 *p, *q;
-	unsigned long d;
+	unsigned long vl, d;
 	int z, z0;
 
 	z0 = stop;		/* P/Q right side optimization */
@@ -924,8 +931,9 @@ static void raid6_rvv8_xor_syndrome_real(int disks, int start, int stop,
 
 	asm volatile (".option	push\n"
 		      ".option	arch,+v\n"
-		      "vsetvli	t0, x0, e8, m1, ta, ma\n"
+		      "vsetvli	%0, x0, e8, m1, ta, ma\n"
 		      ".option	pop\n"
+		      : "=&r" (vl)
 	);
 
 	/*

From 2aa5801ada29948ce510fc8b1e3b3ec8162423e2 Mon Sep 17 00:00:00 2001
From: Palmer Dabbelt <palmer@dabbelt.com>
Date: Tue, 10 Jun 2025 14:30:58 -0700
Subject: [PATCH 0321/1334] RISC-V: uaccess: Wrap the get_user_8 uaccess macro

I must have lost this rebasing things during the merge window, I know I
got it at some point but it's not here now.  Without this I get warnings
along the lines of

    include/linux/fs.h:3975:15: warning: label followed by a declaration is a C23 extension [-Wc23-extensions]
     3975 |         if (unlikely(get_user(c, path)))
          |                      ^
    arch/riscv/include/asm/uaccess.h:274:3: note: expanded from macro 'get_user'
      274 |                 __get_user((x), __p) :                          \
          |                 ^
    arch/riscv/include/asm/uaccess.h:244:2: note: expanded from macro '__get_user'
      244 |         __get_user_error(__gu_val, __gu_ptr, __gu_err);         \
          |         ^
    arch/riscv/include/asm/uaccess.h:207:2: note: expanded from macro '__get_user_error'
      207 |         __ge  LD [M]  net/802/psnap.ko
    t_user_nocheck(x, ptr, __gu_failed);                        \
          |         ^
    arch/riscv/include/asm/uaccess.h:196:3: note: expanded from macro '__get_user_nocheck'
      196 |                 __get_user_8((x), __gu_ptr, label);             \
          |                 ^
    arch/riscv/include/asm/uaccess.h:130:2: note: expanded from macro '__get_user_8'
      130 |         u32 __user *__ptr = (u32 __user *)(ptr);                \
          |         ^

Link: https://lore.kernel.org/r/20250610213058.24852-1-palmer@dabbelt.com
Reviewed-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Cc: stable@vger.kernel.org
Fixes: f6bff7827a48 ("riscv: uaccess: use 'asm_goto_output' for get_user()")
Signed-off-by: Palmer Dabbelt <palmer@dabbelt.com>
---
 arch/riscv/include/asm/uaccess.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/arch/riscv/include/asm/uaccess.h b/arch/riscv/include/asm/uaccess.h
index d472da4450e6..525e50db24f7 100644
--- a/arch/riscv/include/asm/uaccess.h
+++ b/arch/riscv/include/asm/uaccess.h
@@ -127,6 +127,7 @@ do {								\
 
 #ifdef CONFIG_CC_HAS_ASM_GOTO_OUTPUT
 #define __get_user_8(x, ptr, label)				\
+do {								\
 	u32 __user *__ptr = (u32 __user *)(ptr);		\
 	u32 __lo, __hi;						\
 	asm_goto_output(					\
@@ -141,7 +142,7 @@ do {								\
 		: : label);                                     \
 	(x) = (__typeof__(x))((__typeof__((x) - (x)))(		\
 		(((u64)__hi << 32) | __lo)));			\
-
+} while (0)
 #else /* !CONFIG_CC_HAS_ASM_GOTO_OUTPUT */
 #define __get_user_8(x, ptr, label)				\
 do {								\

From 32ce6b3a83b71d8abf0c0837dc78775f16c9902f Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Sun, 8 Jun 2025 18:08:51 -0400
Subject: [PATCH 0322/1334] NFSD: Avoid corruption of a referring call list

The new code neglects to remove a freshly-allocated RCL from the
callback's referring call list when no matching referring call is
found.

Reported-by: kernel test robot <lkp@intel.com>
Reported-by: Dan Carpenter <dan.carpenter@linaro.org>
Closes: https://lore.kernel.org/r/202505171002.cE46sdj5-lkp@intel.com/
Fixes: 4f3c8d8c9e10 ("NFSD: Implement CB_SEQUENCE referring call lists")
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 fs/nfsd/nfs4callback.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c
index ccb00aa93be0..e00b2aea8da2 100644
--- a/fs/nfsd/nfs4callback.c
+++ b/fs/nfsd/nfs4callback.c
@@ -1409,6 +1409,7 @@ void nfsd41_cb_referring_call(struct nfsd4_callback *cb,
 out:
 	if (!rcl->__nr_referring_calls) {
 		cb->cb_nr_referring_call_list--;
+		list_del(&rcl->__list);
 		kfree(rcl);
 	}
 }

From 8b3ac9fabaa825b7bae850ee7b4580c5cba32699 Mon Sep 17 00:00:00 2001
From: Benjamin Coddington <bcodding@redhat.com>
Date: Mon, 9 Jun 2025 13:21:56 -0400
Subject: [PATCH 0323/1334] SUNRPC: Cleanup/fix initial rq_pages allocation

While investigating some reports of memory-constrained NUMA machines
failing to mount v3 and v4.0 nfs mounts, we found that svc_init_buffer()
was not attempting to retry allocations from the bulk page allocator.
Typically, this results in a single page allocation being returned and
the mount attempt fails with -ENOMEM.  A retry would have allowed the mount
to succeed.

Additionally, it seems that the bulk allocation in svc_init_buffer() is
redundant because svc_alloc_arg() will perform the required allocation and
does the correct thing to retry the allocations.

The call to allocate memory in svc_alloc_arg() drops the preferred node
argument, but I expect we'll still allocate on the preferred node because
the allocation call happens within the svc thread context, which chooses
the node with memory closest to the current thread's execution.

This patch cleans out the bulk allocation in svc_init_buffer() to allow
svc_alloc_arg() to handle the allocation/retry logic for rq_pages.

Signed-off-by: Benjamin Coddington <bcodding@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Fixes: ed603bcf4fea ("sunrpc: Replace the rq_pages array with dynamically-allocated memory")
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 net/sunrpc/svc.c | 6 +-----
 1 file changed, 1 insertion(+), 5 deletions(-)

diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index 939b6239df8a..ef8a05aac87f 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -638,8 +638,6 @@ EXPORT_SYMBOL_GPL(svc_destroy);
 static bool
 svc_init_buffer(struct svc_rqst *rqstp, const struct svc_serv *serv, int node)
 {
-	unsigned long ret;
-
 	rqstp->rq_maxpages = svc_serv_maxpages(serv);
 
 	/* rq_pages' last entry is NULL for historical reasons. */
@@ -649,9 +647,7 @@ svc_init_buffer(struct svc_rqst *rqstp, const struct svc_serv *serv, int node)
 	if (!rqstp->rq_pages)
 		return false;
 
-	ret = alloc_pages_bulk_node(GFP_KERNEL, node, rqstp->rq_maxpages,
-				    rqstp->rq_pages);
-	return ret == rqstp->rq_maxpages;
+	return true;
 }
 
 /*

From 5466491c9e3309ed5c7adbb8fad6e93fcc9a8fe9 Mon Sep 17 00:00:00 2001
From: Brett Creeley <brett.creeley@amd.com>
Date: Mon, 9 Jun 2025 14:28:27 -0700
Subject: [PATCH 0324/1334] ionic: Prevent driver/fw getting out of sync on
 devcmd(s)

Some stress/negative firmware testing around devcmd(s) returning
EAGAIN found that the done bit could get out of sync in the
firmware when it wasn't cleared in a retry case.

While here, change the type of the local done variable to a bool
to match the return type from ionic_dev_cmd_done().

Fixes: ec8ee714736e ("ionic: stretch heartbeat detection")
Signed-off-by: Brett Creeley <brett.creeley@amd.com>
Signed-off-by: Shannon Nelson <shannon.nelson@amd.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250609212827.53842-1-shannon.nelson@amd.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/pensando/ionic/ionic_main.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/pensando/ionic/ionic_main.c b/drivers/net/ethernet/pensando/ionic/ionic_main.c
index daf1e82cb76b..0e60a6bef99a 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_main.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_main.c
@@ -516,9 +516,9 @@ static int __ionic_dev_cmd_wait(struct ionic *ionic, unsigned long max_seconds,
 	unsigned long start_time;
 	unsigned long max_wait;
 	unsigned long duration;
-	int done = 0;
 	bool fw_up;
 	int opcode;
+	bool done;
 	int err;
 
 	/* Wait for dev cmd to complete, retrying if we get EAGAIN,
@@ -526,6 +526,7 @@ static int __ionic_dev_cmd_wait(struct ionic *ionic, unsigned long max_seconds,
 	 */
 	max_wait = jiffies + (max_seconds * HZ);
 try_again:
+	done = false;
 	opcode = idev->opcode;
 	start_time = jiffies;
 	for (fw_up = ionic_is_fw_running(idev);

From bb666b7c27073b986b75699e51a7102910f58060 Mon Sep 17 00:00:00 2001
From: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Date: Mon, 9 Jun 2025 17:57:49 +0100
Subject: [PATCH 0325/1334] mm: add mmap_prepare() compatibility layer for
 nested file systems

Nested file systems, that is those which invoke call_mmap() within their
own f_op->mmap() handlers, may encounter underlying file systems which
provide the f_op->mmap_prepare() hook introduced by commit c84bf6dd2b83
("mm: introduce new .mmap_prepare() file callback").

We have a chicken-and-egg scenario here - until all file systems are
converted to using .mmap_prepare(), we cannot convert these nested
handlers, as we can't call f_op->mmap from an .mmap_prepare() hook.

So we have to do it the other way round - invoke the .mmap_prepare() hook
from an .mmap() one.

in order to do so, we need to convert VMA state into a struct vm_area_desc
descriptor, invoking the underlying file system's f_op->mmap_prepare()
callback passing a pointer to this, and then setting VMA state accordingly
and safely.

This patch achieves this via the compat_vma_mmap_prepare() function, which
we invoke from call_mmap() if f_op->mmap_prepare() is specified in the
passed in file pointer.

We place the fundamental logic into mm/vma.h where VMA manipulation
belongs.  We also update the VMA userland tests to accommodate the
changes.

The compat_vma_mmap_prepare() function and its associated machinery is
temporary, and will be removed once the conversion of file systems is
complete.

We carefully place this code so it can be used with CONFIG_MMU and also
with cutting edge nommu silicon.

[akpm@linux-foundation.org: export compat_vma_mmap_prepare tp fix build]
[lorenzo.stoakes@oracle.com: remove unused declarations]
  Link: https://lkml.kernel.org/r/ac3ae324-4c65-432a-8c6d-2af988b18ac8@lucifer.local
Link: https://lkml.kernel.org/r/20250609165749.344976-1-lorenzo.stoakes@oracle.com
Fixes: c84bf6dd2b83 ("mm: introduce new .mmap_prepare() file callback").
Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Reported-by: Jann Horn <jannh@google.com>
Closes: https://lore.kernel.org/linux-mm/CAG48ez04yOEVx1ekzOChARDDBZzAKwet8PEoPM4Ln3_rk91AzQ@mail.gmail.com/
Reviewed-by: Pedro Falcato <pfalcato@suse.de>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Jan Kara <jack@suse.cz>
Cc: Jann Horn <jannh@google.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/fs.h               |  6 ++--
 mm/util.c                        | 40 +++++++++++++++++++++++++++
 mm/vma.c                         |  1 -
 mm/vma.h                         | 47 ++++++++++++++++++++++++++++++++
 tools/testing/vma/vma_internal.h | 16 +++++++++++
 5 files changed, 107 insertions(+), 3 deletions(-)

diff --git a/include/linux/fs.h b/include/linux/fs.h
index 96c7925a6551..4ec77da65f14 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2274,10 +2274,12 @@ static inline bool file_has_valid_mmap_hooks(struct file *file)
 	return true;
 }
 
+int compat_vma_mmap_prepare(struct file *file, struct vm_area_struct *vma);
+
 static inline int call_mmap(struct file *file, struct vm_area_struct *vma)
 {
-	if (WARN_ON_ONCE(file->f_op->mmap_prepare))
-		return -EINVAL;
+	if (file->f_op->mmap_prepare)
+		return compat_vma_mmap_prepare(file, vma);
 
 	return file->f_op->mmap(file, vma);
 }
diff --git a/mm/util.c b/mm/util.c
index 448117da071f..0b270c43d7d1 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -1131,3 +1131,43 @@ void flush_dcache_folio(struct folio *folio)
 }
 EXPORT_SYMBOL(flush_dcache_folio);
 #endif
+
+/**
+ * compat_vma_mmap_prepare() - Apply the file's .mmap_prepare() hook to an
+ * existing VMA
+ * @file: The file which possesss an f_op->mmap_prepare() hook
+ * @vma: The VMA to apply the .mmap_prepare() hook to.
+ *
+ * Ordinarily, .mmap_prepare() is invoked directly upon mmap(). However, certain
+ * 'wrapper' file systems invoke a nested mmap hook of an underlying file.
+ *
+ * Until all filesystems are converted to use .mmap_prepare(), we must be
+ * conservative and continue to invoke these 'wrapper' filesystems using the
+ * deprecated .mmap() hook.
+ *
+ * However we have a problem if the underlying file system possesses an
+ * .mmap_prepare() hook, as we are in a different context when we invoke the
+ * .mmap() hook, already having a VMA to deal with.
+ *
+ * compat_vma_mmap_prepare() is a compatibility function that takes VMA state,
+ * establishes a struct vm_area_desc descriptor, passes to the underlying
+ * .mmap_prepare() hook and applies any changes performed by it.
+ *
+ * Once the conversion of filesystems is complete this function will no longer
+ * be required and will be removed.
+ *
+ * Returns: 0 on success or error.
+ */
+int compat_vma_mmap_prepare(struct file *file, struct vm_area_struct *vma)
+{
+	struct vm_area_desc desc;
+	int err;
+
+	err = file->f_op->mmap_prepare(vma_to_desc(vma, &desc));
+	if (err)
+		return err;
+	set_vma_from_desc(vma, &desc);
+
+	return 0;
+}
+EXPORT_SYMBOL(compat_vma_mmap_prepare);
diff --git a/mm/vma.c b/mm/vma.c
index 0fb9b2c7b734..fef67a66a095 100644
--- a/mm/vma.c
+++ b/mm/vma.c
@@ -3113,7 +3113,6 @@ int __vm_munmap(unsigned long start, size_t len, bool unlock)
 	return ret;
 }
 
-
 /* Insert vm structure into process list sorted by address
  * and into the inode's i_mmap tree.  If vm_file is non-NULL
  * then i_mmap_rwsem is taken here.
diff --git a/mm/vma.h b/mm/vma.h
index 0db066e7a45d..f47112a352db 100644
--- a/mm/vma.h
+++ b/mm/vma.h
@@ -222,6 +222,53 @@ static inline int vma_iter_store_gfp(struct vma_iterator *vmi,
 	return 0;
 }
 
+
+/*
+ * Temporary helper functions for file systems which wrap an invocation of
+ * f_op->mmap() but which might have an underlying file system which implements
+ * f_op->mmap_prepare().
+ */
+
+static inline struct vm_area_desc *vma_to_desc(struct vm_area_struct *vma,
+		struct vm_area_desc *desc)
+{
+	desc->mm = vma->vm_mm;
+	desc->start = vma->vm_start;
+	desc->end = vma->vm_end;
+
+	desc->pgoff = vma->vm_pgoff;
+	desc->file = vma->vm_file;
+	desc->vm_flags = vma->vm_flags;
+	desc->page_prot = vma->vm_page_prot;
+
+	desc->vm_ops = NULL;
+	desc->private_data = NULL;
+
+	return desc;
+}
+
+static inline void set_vma_from_desc(struct vm_area_struct *vma,
+		struct vm_area_desc *desc)
+{
+	/*
+	 * Since we're invoking .mmap_prepare() despite having a partially
+	 * established VMA, we must take care to handle setting fields
+	 * correctly.
+	 */
+
+	/* Mutable fields. Populated with initial state. */
+	vma->vm_pgoff = desc->pgoff;
+	if (vma->vm_file != desc->file)
+		vma_set_file(vma, desc->file);
+	if (vma->vm_flags != desc->vm_flags)
+		vm_flags_set(vma, desc->vm_flags);
+	vma->vm_page_prot = desc->page_prot;
+
+	/* User-defined fields. */
+	vma->vm_ops = desc->vm_ops;
+	vma->vm_private_data = desc->private_data;
+}
+
 int
 do_vmi_align_munmap(struct vma_iterator *vmi, struct vm_area_struct *vma,
 		    struct mm_struct *mm, unsigned long start,
diff --git a/tools/testing/vma/vma_internal.h b/tools/testing/vma/vma_internal.h
index 4505b1c31be1..14718ca23a05 100644
--- a/tools/testing/vma/vma_internal.h
+++ b/tools/testing/vma/vma_internal.h
@@ -159,6 +159,14 @@ typedef __bitwise unsigned int vm_fault_t;
 
 #define ASSERT_EXCLUSIVE_WRITER(x)
 
+/**
+ * swap - swap values of @a and @b
+ * @a: first value
+ * @b: second value
+ */
+#define swap(a, b) \
+	do { typeof(a) __tmp = (a); (a) = (b); (b) = __tmp; } while (0)
+
 struct kref {
 	refcount_t refcount;
 };
@@ -1468,4 +1476,12 @@ static inline void fixup_hugetlb_reservations(struct vm_area_struct *vma)
 	(void)vma;
 }
 
+static inline void vma_set_file(struct vm_area_struct *vma, struct file *file)
+{
+	/* Changing an anonymous vma with this is illegal */
+	get_file(file);
+	swap(vma->vm_file, file);
+	fput(file);
+}
+
 #endif	/* __MM_VMA_INTERNAL_H */

From d742f3ec1cb91c4dd86b981f55cd291e07f03094 Mon Sep 17 00:00:00 2001
From: Thomas Zimmermann <tzimmermann@suse.de>
Date: Thu, 12 Jun 2025 10:42:55 +0200
Subject: [PATCH 0326/1334] drm/ast: Do not include <linux/export.h>

Fix the compile-time warning

  drivers/gpu/drm/ast/ast_mode.c: warning: EXPORT_SYMBOL() is not used, but #include <linux/export.h> is present

Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>
Reviewed-by: Jocelyn Falempe <jfalempe@redhat.com>
Link: https://lore.kernel.org/r/20250612084257.200907-1-tzimmermann@suse.de
---
 drivers/gpu/drm/ast/ast_mode.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/gpu/drm/ast/ast_mode.c b/drivers/gpu/drm/ast/ast_mode.c
index 1de832964e92..031980d8f3ab 100644
--- a/drivers/gpu/drm/ast/ast_mode.c
+++ b/drivers/gpu/drm/ast/ast_mode.c
@@ -29,7 +29,6 @@
  */
 
 #include <linux/delay.h>
-#include <linux/export.h>
 #include <linux/pci.h>
 
 #include <drm/drm_atomic.h>

From 2e3395ab2a358ba8d1c80d8df35dcfb882cfc28e Mon Sep 17 00:00:00 2001
From: Thomas Zimmermann <tzimmermann@suse.de>
Date: Thu, 12 Jun 2025 10:53:02 +0200
Subject: [PATCH 0327/1334] drm/mgag200: Do not include <linux/export.h>

Fix the compile-time warning

  drivers/gpu/drm/mgag200/mgag200_ddc.c: warning: EXPORT_SYMBOL() is not used, but #include <linux/export.h> is present

Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>
Reviewed-by: Jocelyn Falempe <jfalempe@redhat.com>
Link: https://lore.kernel.org/r/20250612085308.203861-1-tzimmermann@suse.de
---
 drivers/gpu/drm/mgag200/mgag200_ddc.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/gpu/drm/mgag200/mgag200_ddc.c b/drivers/gpu/drm/mgag200/mgag200_ddc.c
index 6d81ea8931e8..c31673eaa554 100644
--- a/drivers/gpu/drm/mgag200/mgag200_ddc.c
+++ b/drivers/gpu/drm/mgag200/mgag200_ddc.c
@@ -26,7 +26,6 @@
  * Authors: Dave Airlie <airlied@redhat.com>
  */
 
-#include <linux/export.h>
 #include <linux/i2c-algo-bit.h>
 #include <linux/i2c.h>
 #include <linux/pci.h>

From b93755f408325170edb2156c6a894ed1cae5f4f6 Mon Sep 17 00:00:00 2001
From: Christophe Leroy <christophe.leroy@csgroup.eu>
Date: Mon, 12 May 2025 20:14:55 +0200
Subject: [PATCH 0328/1334] powerpc/vdso: Fix build of VDSO32 with pcrel

Building vdso32 on power10 with pcrel leads to following errors:

	  VDSO32A arch/powerpc/kernel/vdso/gettimeofday-32.o
	arch/powerpc/kernel/vdso/gettimeofday.S: Assembler messages:
	arch/powerpc/kernel/vdso/gettimeofday.S:40: Error: syntax error; found `@', expected `,'
	arch/powerpc/kernel/vdso/gettimeofday.S:71:  Info: macro invoked from here
	arch/powerpc/kernel/vdso/gettimeofday.S:40: Error: junk at end of line: `@notoc'
	arch/powerpc/kernel/vdso/gettimeofday.S:71:  Info: macro invoked from here
	 ...
	make[2]: *** [arch/powerpc/kernel/vdso/Makefile:85: arch/powerpc/kernel/vdso/gettimeofday-32.o] Error 1
	make[1]: *** [arch/powerpc/Makefile:388: vdso_prepare] Error 2

Once the above is fixed, the following happens:

	  VDSO32C arch/powerpc/kernel/vdso/vgettimeofday-32.o
	cc1: error: '-mpcrel' requires '-mcmodel=medium'
	make[2]: *** [arch/powerpc/kernel/vdso/Makefile:89: arch/powerpc/kernel/vdso/vgettimeofday-32.o] Error 1
	make[1]: *** [arch/powerpc/Makefile:388: vdso_prepare] Error 2
	make: *** [Makefile:251: __sub-make] Error 2

Make sure pcrel version of CFUNC() macro is used only for powerpc64
builds and remove -mpcrel for powerpc32 builds.

Fixes: 7e3a68be42e1 ("powerpc/64: vmlinux support building with PCREL addresing")
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Signed-off-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Link: https://patch.msgid.link/1fa3453f07d42a50a70114da9905bf7b73304fca.1747073669.git.christophe.leroy@csgroup.eu
---
 arch/powerpc/include/asm/ppc_asm.h | 2 +-
 arch/powerpc/kernel/vdso/Makefile  | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/powerpc/include/asm/ppc_asm.h b/arch/powerpc/include/asm/ppc_asm.h
index 02897f4b0dbf..b891910fce8a 100644
--- a/arch/powerpc/include/asm/ppc_asm.h
+++ b/arch/powerpc/include/asm/ppc_asm.h
@@ -183,7 +183,7 @@
 /*
  * Used to name C functions called from asm
  */
-#ifdef CONFIG_PPC_KERNEL_PCREL
+#if defined(__powerpc64__) && defined(CONFIG_PPC_KERNEL_PCREL)
 #define CFUNC(name) name@notoc
 #else
 #define CFUNC(name) name
diff --git a/arch/powerpc/kernel/vdso/Makefile b/arch/powerpc/kernel/vdso/Makefile
index e8824f933326..8834dfe9d727 100644
--- a/arch/powerpc/kernel/vdso/Makefile
+++ b/arch/powerpc/kernel/vdso/Makefile
@@ -53,7 +53,7 @@ ldflags-$(CONFIG_LD_ORPHAN_WARN) += -Wl,--orphan-handling=$(CONFIG_LD_ORPHAN_WAR
 ldflags-y += $(filter-out $(CC_AUTO_VAR_INIT_ZERO_ENABLER) $(CC_FLAGS_FTRACE) -Wa$(comma)%, $(KBUILD_CPPFLAGS) $(KBUILD_CFLAGS))
 
 CC32FLAGS := -m32
-CC32FLAGSREMOVE := -mcmodel=medium -mabi=elfv1 -mabi=elfv2 -mcall-aixdesc
+CC32FLAGSREMOVE := -mcmodel=medium -mabi=elfv1 -mabi=elfv2 -mcall-aixdesc -mpcrel
 ifdef CONFIG_CC_IS_CLANG
 # This flag is supported by clang for 64-bit but not 32-bit so it will cause
 # an unused command line flag warning for this file.

From 33bc69cf6655cf60829a803a45275f11a74899e5 Mon Sep 17 00:00:00 2001
From: Narayana Murty N <nnmlinux@linux.ibm.com>
Date: Thu, 8 May 2025 02:29:28 -0400
Subject: [PATCH 0329/1334] powerpc/eeh: Fix missing PE bridge reconfiguration
 during VFIO EEH recovery

VFIO EEH recovery for PCI passthrough devices fails on PowerNV and pseries
platforms due to missing host-side PE bridge reconfiguration. In the
current implementation, eeh_pe_configure() only performs RTAS or OPAL-based
bridge reconfiguration for native host devices, but skips it entirely for
PEs managed through VFIO in guest passthrough scenarios.

This leads to incomplete EEH recovery when a PCI error affects a
passthrough device assigned to a QEMU/KVM guest. Although VFIO triggers the
EEH recovery flow through VFIO_EEH_PE_ENABLE ioctl, the platform-specific
bridge reconfiguration step is silently bypassed. As a result, the PE's
config space is not fully restored, causing subsequent config space access
failures or EEH freeze-on-access errors inside the guest.

This patch fixes the issue by ensuring that eeh_pe_configure() always
invokes the platform's configure_bridge() callback (e.g.,
pseries_eeh_phb_configure_bridge) even for VFIO-managed PEs. This ensures
that RTAS or OPAL calls to reconfigure the PE bridge are correctly issued
on the host side, restoring the PE's configuration space after an EEH
event.

This fix is essential for reliable EEH recovery in QEMU/KVM guests using
VFIO PCI passthrough on PowerNV and pseries systems.

Tested with:
- QEMU/KVM guest using VFIO passthrough (IBM Power9,(lpar)Power11 host)
- Injected EEH errors with pseries EEH errinjct tool on host, recovery
  verified on qemu guest.
- Verified successful config space access and CAP_EXP DevCtl restoration
  after recovery

Fixes: 212d16cdca2d ("powerpc/eeh: EEH support for VFIO PCI device")
Signed-off-by: Narayana Murty N <nnmlinux@linux.ibm.com>
Reviewed-by: Vaibhav Jain <vaibhav@linux.ibm.com>
Reviewed-by: Ganesh Goudar <ganeshgr@linux.ibm.com>
Signed-off-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Link: https://patch.msgid.link/20250508062928.146043-1-nnmlinux@linux.ibm.com
---
 arch/powerpc/kernel/eeh.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c
index 83fe99861eb1..ca7f7bb2b478 100644
--- a/arch/powerpc/kernel/eeh.c
+++ b/arch/powerpc/kernel/eeh.c
@@ -1509,6 +1509,8 @@ int eeh_pe_configure(struct eeh_pe *pe)
 	/* Invalid PE ? */
 	if (!pe)
 		return -ENODEV;
+	else
+		ret = eeh_ops->configure_bridge(pe);
 
 	return ret;
 }

From 4e6d080acfda5344ccbc63afe778830e22be4be9 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?J=2E=20Neusch=C3=A4fer?= <j.ne@posteo.net>
Date: Wed, 11 Jun 2025 23:07:49 +0200
Subject: [PATCH 0330/1334] powerpc/microwatt: Fix model property in device
 tree
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The standard property for the model name is called "model".

Signed-off-by: J. Neuschäfer <j.ne@posteo.net>
Signed-off-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Link: https://patch.msgid.link/20250611-microwatt-v2-1-80847bbc5f9c@posteo.net
---
 arch/powerpc/boot/dts/microwatt.dts | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/powerpc/boot/dts/microwatt.dts b/arch/powerpc/boot/dts/microwatt.dts
index c4e4d2a9b460..b7eac4e56019 100644
--- a/arch/powerpc/boot/dts/microwatt.dts
+++ b/arch/powerpc/boot/dts/microwatt.dts
@@ -4,7 +4,7 @@
 / {
 	#size-cells = <0x02>;
 	#address-cells = <0x02>;
-	model-name = "microwatt";
+	model = "microwatt";
 	compatible = "microwatt-soc";
 
 	aliases {

From e75cb6010838f61b9d63e921d1763a8ab177e38e Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?J=2E=20Neusch=C3=A4fer?= <j.ne@posteo.net>
Date: Wed, 11 Jun 2025 21:01:01 +0200
Subject: [PATCH 0331/1334] powerpc: dts: mpc8315erdb: Add GPIO controller node
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The MPC8315E SoC and variants have a GPIO controller at IMMR + 0xc00.
This node was previously missing from the device tree.

Signed-off-by: J. Neuschäfer <j.ne@posteo.net>
Signed-off-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Link: https://patch.msgid.link/20250611-mpc-gpio-v1-1-02d1f75336e2@posteo.net
---
 arch/powerpc/boot/dts/mpc8315erdb.dts | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/arch/powerpc/boot/dts/mpc8315erdb.dts b/arch/powerpc/boot/dts/mpc8315erdb.dts
index e09b37d7489d..a89cb3139ca8 100644
--- a/arch/powerpc/boot/dts/mpc8315erdb.dts
+++ b/arch/powerpc/boot/dts/mpc8315erdb.dts
@@ -6,6 +6,7 @@
  */
 
 /dts-v1/;
+#include <dt-bindings/interrupt-controller/irq.h>
 
 / {
 	compatible = "fsl,mpc8315erdb";
@@ -358,6 +359,15 @@
 			interrupt-parent = <&ipic>;
 			fsl,mpc8313-wakeup-timer = <&gtm1>;
 		};
+
+		gpio: gpio-controller@c00 {
+			compatible = "fsl,mpc8314-gpio";
+			reg = <0xc00 0x100>;
+			interrupts = <74 IRQ_TYPE_LEVEL_LOW>;
+			interrupt-parent = <&ipic>;
+			gpio-controller;
+			#gpio-cells = <2>;
+		};
 	};
 
 	pci0: pci@e0008500 {

From b0823d5fbacb1c551d793cbfe7af24e0d1fa45ed Mon Sep 17 00:00:00 2001
From: Kan Liang <kan.liang@linux.intel.com>
Date: Thu, 12 Jun 2025 07:38:18 -0700
Subject: [PATCH 0332/1334] perf/x86/intel: Fix crash in
 icl_update_topdown_event()

The perf_fuzzer found a hard-lockup crash on a RaptorLake machine:

  Oops: general protection fault, maybe for address 0xffff89aeceab400: 0000
  CPU: 23 UID: 0 PID: 0 Comm: swapper/23
  Tainted: [W]=WARN
  Hardware name: Dell Inc. Precision 9660/0VJ762
  RIP: 0010:native_read_pmc+0x7/0x40
  Code: cc e8 8d a9 01 00 48 89 03 5b cd cc cc cc cc 0f 1f ...
  RSP: 000:fffb03100273de8 EFLAGS: 00010046
  ....
  Call Trace:
    <TASK>
    icl_update_topdown_event+0x165/0x190
    ? ktime_get+0x38/0xd0
    intel_pmu_read_event+0xf9/0x210
    __perf_event_read+0xf9/0x210

CPUs 16-23 are E-core CPUs that don't support the perf metrics feature.
The icl_update_topdown_event() should not be invoked on these CPUs.

It's a regression of commit:

  f9bdf1f95339 ("perf/x86/intel: Avoid disable PMU if !cpuc->enabled in sample read")

The bug introduced by that commit is that the is_topdown_event() function
is mistakenly used to replace the is_topdown_count() call to check if the
topdown functions for the perf metrics feature should be invoked.

Fix it.

Fixes: f9bdf1f95339 ("perf/x86/intel: Avoid disable PMU if !cpuc->enabled in sample read")
Closes: https://lore.kernel.org/lkml/352f0709-f026-cd45-e60c-60dfd97f73f3@maine.edu/
Reported-by: Vince Weaver <vincent.weaver@maine.edu>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Tested-by: Vince Weaver <vincent.weaver@maine.edu>
Cc: stable@vger.kernel.org # v6.15+
Link: https://lore.kernel.org/r/20250612143818.2889040-1-kan.liang@linux.intel.com
---
 arch/x86/events/intel/core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 741b229f0718..c2fb729c270e 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -2826,7 +2826,7 @@ static void intel_pmu_read_event(struct perf_event *event)
 		 * If the PEBS counters snapshotting is enabled,
 		 * the topdown event is available in PEBS records.
 		 */
-		if (is_topdown_event(event) && !is_pebs_counter_event_group(event))
+		if (is_topdown_count(event) && !is_pebs_counter_event_group(event))
 			static_call(intel_pmu_update_topdown_event)(event, NULL);
 		else
 			intel_pmu_drain_pebs_buffer();

From 93adf20ff4d6e865e0b974110d3cf2f07c057177 Mon Sep 17 00:00:00 2001
From: wangdicheng <wangdicheng@kylinos.cn>
Date: Fri, 13 Jun 2025 14:36:36 +0800
Subject: [PATCH 0333/1334] ALSA: usb-audio: Rename ALSA kcontrol PCM and PCM1
 for the KTMicro sound card

PCM1 not in Pulseaudio's control list; standardize control to
"Speaker" and "Headphone".

Signed-off-by: wangdicheng <wangdicheng@kylinos.cn>
Cc: <stable@vger.kernel.org>
Link: https://patch.msgid.link/20250613063636.239683-1-wangdich9700@163.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/usb/mixer_maps.c | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/sound/usb/mixer_maps.c b/sound/usb/mixer_maps.c
index 0e9b5431a47f..faac7df1fbcf 100644
--- a/sound/usb/mixer_maps.c
+++ b/sound/usb/mixer_maps.c
@@ -383,6 +383,13 @@ static const struct usbmix_name_map ms_usb_link_map[] = {
 	{ 0 }   /* terminator */
 };
 
+/* KTMicro USB */
+static struct usbmix_name_map s31b2_0022_map[] = {
+	{ 23, "Speaker Playback" },
+	{ 18, "Headphone Playback" },
+	{ 0 }
+};
+
 /* ASUS ROG Zenith II with Realtek ALC1220-VB */
 static const struct usbmix_name_map asus_zenith_ii_map[] = {
 	{ 19, NULL, 12 }, /* FU, Input Gain Pad - broken response, disabled */
@@ -692,6 +699,11 @@ static const struct usbmix_ctl_map usbmix_ctl_maps[] = {
 		.id = USB_ID(0x045e, 0x083c),
 		.map = ms_usb_link_map,
 	},
+	{
+		/* KTMicro USB */
+		.id = USB_ID(0X31b2, 0x0022),
+		.map = s31b2_0022_map,
+	},
 	{ 0 } /* terminator */
 };
 

From ac90aad0e9bf7c37e706fdc08ce763a553890bdf Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Thu, 12 Jun 2025 10:47:09 -0700
Subject: [PATCH 0334/1334] crypto: testmgr - reinstate kconfig control over
 full self-tests

Commit 698de822780f ("crypto: testmgr - make it easier to enable the
full set of tests") removed support for building kernels that run only
the "fast" set of crypto self-tests by default.  This assumed that
nearly everyone actually wanted the full set of tests, *if* they had
already chosen to enable the tests at all.

Unfortunately, it turns out that both Debian and Fedora intentionally
have the crypto self-tests enabled in their production kernels.  And for
production kernels we do need to keep the testing time down, which
implies just running the "fast" tests, not the full set of tests.

For Fedora, a reason for enabling the tests in production is that they
are being (mis)used to meet the FIPS 140-3 pre-operational testing
requirement.

However, the other reason for enabling the tests in production, which
applies to both distros, is that they provide some value in protecting
users from buggy drivers.  Unfortunately, the crypto/ subsystem has many
buggy and untested drivers for off-CPU hardware accelerators on rare
platforms.  These broken drivers get shipped to users, and there have
been multiple examples of the tests preventing these buggy drivers from
being used.  So effectively, the tests are being relied on in production
kernels.  I think this is kind of crazy (untested drivers should just
not be enabled at all), but that seems to be how things work currently.

Thus, reintroduce a kconfig option that controls the level of testing.
Call it CRYPTO_SELFTESTS_FULL instead of the original name
CRYPTO_MANAGER_EXTRA_TESTS, which was slightly misleading.

Moreover, given the "production kernel" use case, make CRYPTO_SELFTESTS
depend on EXPERT instead of DEBUG_KERNEL.

I also haven't reinstated all the #ifdefs in crypto/testmgr.c.  Instead,
just rely on the compiler to optimize out unused code.

Fixes: 40b9969796bf ("crypto: testmgr - replace CRYPTO_MANAGER_DISABLE_TESTS with CRYPTO_SELFTESTS")
Fixes: 698de822780f ("crypto: testmgr - make it easier to enable the full set of tests")
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 crypto/Kconfig                 | 25 +++++++++++++++++++++----
 crypto/testmgr.c               | 15 ++++++++++++---
 include/crypto/internal/simd.h |  6 ++++--
 lib/crypto/Makefile            |  2 +-
 4 files changed, 38 insertions(+), 10 deletions(-)

diff --git a/crypto/Kconfig b/crypto/Kconfig
index e9fee7818e27..e1cfd0d4cc8f 100644
--- a/crypto/Kconfig
+++ b/crypto/Kconfig
@@ -176,16 +176,33 @@ config CRYPTO_USER
 
 config CRYPTO_SELFTESTS
 	bool "Enable cryptographic self-tests"
-	depends on DEBUG_KERNEL
+	depends on EXPERT
 	help
 	  Enable the cryptographic self-tests.
 
 	  The cryptographic self-tests run at boot time, or at algorithm
 	  registration time if algorithms are dynamically loaded later.
 
-	  This is primarily intended for developer use.  It should not be
-	  enabled in production kernels, unless you are trying to use these
-	  tests to fulfill a FIPS testing requirement.
+	  There are two main use cases for these tests:
+
+	  - Development and pre-release testing.  In this case, also enable
+	    CRYPTO_SELFTESTS_FULL to get the full set of tests.  All crypto code
+	    in the kernel is expected to pass the full set of tests.
+
+	  - Production kernels, to help prevent buggy drivers from being used
+	    and/or meet FIPS 140-3 pre-operational testing requirements.  In
+	    this case, enable CRYPTO_SELFTESTS but not CRYPTO_SELFTESTS_FULL.
+
+config CRYPTO_SELFTESTS_FULL
+	bool "Enable the full set of cryptographic self-tests"
+	depends on CRYPTO_SELFTESTS
+	help
+	  Enable the full set of cryptographic self-tests for each algorithm.
+
+	  The full set of tests should be enabled for development and
+	  pre-release testing, but not in production kernels.
+
+	  All crypto code in the kernel is expected to pass the full tests.
 
 config CRYPTO_NULL
 	tristate "Null algorithms"
diff --git a/crypto/testmgr.c b/crypto/testmgr.c
index 72005074a5c2..32f753d6c430 100644
--- a/crypto/testmgr.c
+++ b/crypto/testmgr.c
@@ -45,6 +45,7 @@ static bool notests;
 module_param(notests, bool, 0644);
 MODULE_PARM_DESC(notests, "disable all crypto self-tests");
 
+#ifdef CONFIG_CRYPTO_SELFTESTS_FULL
 static bool noslowtests;
 module_param(noslowtests, bool, 0644);
 MODULE_PARM_DESC(noslowtests, "disable slow crypto self-tests");
@@ -52,6 +53,10 @@ MODULE_PARM_DESC(noslowtests, "disable slow crypto self-tests");
 static unsigned int fuzz_iterations = 100;
 module_param(fuzz_iterations, uint, 0644);
 MODULE_PARM_DESC(fuzz_iterations, "number of fuzz test iterations");
+#else
+#define noslowtests 1
+#define fuzz_iterations 0
+#endif
 
 #ifndef CONFIG_CRYPTO_SELFTESTS
 
@@ -319,9 +324,9 @@ struct testvec_config {
 
 /*
  * The following are the lists of testvec_configs to test for each algorithm
- * type when the fast crypto self-tests are enabled.  They aim to provide good
- * test coverage, while keeping the test time much shorter than the full tests
- * so that the fast tests can be used to fulfill FIPS 140 testing requirements.
+ * type when the "fast" crypto self-tests are enabled.  They aim to provide good
+ * test coverage, while keeping the test time much shorter than the "full" tests
+ * so that the "fast" tests can be enabled in a wider range of circumstances.
  */
 
 /* Configs for skciphers and aeads */
@@ -1183,14 +1188,18 @@ static void generate_random_testvec_config(struct rnd_state *rng,
 
 static void crypto_disable_simd_for_test(void)
 {
+#ifdef CONFIG_CRYPTO_SELFTESTS_FULL
 	migrate_disable();
 	__this_cpu_write(crypto_simd_disabled_for_test, true);
+#endif
 }
 
 static void crypto_reenable_simd_for_test(void)
 {
+#ifdef CONFIG_CRYPTO_SELFTESTS_FULL
 	__this_cpu_write(crypto_simd_disabled_for_test, false);
 	migrate_enable();
+#endif
 }
 
 /*
diff --git a/include/crypto/internal/simd.h b/include/crypto/internal/simd.h
index 7e7f1ac3b7fd..9e338e7aafbd 100644
--- a/include/crypto/internal/simd.h
+++ b/include/crypto/internal/simd.h
@@ -44,9 +44,11 @@ void simd_unregister_aeads(struct aead_alg *algs, int count,
  *
  * This delegates to may_use_simd(), except that this also returns false if SIMD
  * in crypto code has been temporarily disabled on this CPU by the crypto
- * self-tests, in order to test the no-SIMD fallback code.
+ * self-tests, in order to test the no-SIMD fallback code.  This override is
+ * currently limited to configurations where the "full" self-tests are enabled,
+ * because it might be a bit too invasive to be part of the "fast" self-tests.
  */
-#ifdef CONFIG_CRYPTO_SELFTESTS
+#ifdef CONFIG_CRYPTO_SELFTESTS_FULL
 DECLARE_PER_CPU(bool, crypto_simd_disabled_for_test);
 #define crypto_simd_usable() \
 	(may_use_simd() && !this_cpu_read(crypto_simd_disabled_for_test))
diff --git a/lib/crypto/Makefile b/lib/crypto/Makefile
index 3e79283b617d..f9e44aac6619 100644
--- a/lib/crypto/Makefile
+++ b/lib/crypto/Makefile
@@ -62,7 +62,7 @@ libsha256-generic-y				:= sha256-generic.o
 
 obj-$(CONFIG_MPILIB) += mpi/
 
-obj-$(CONFIG_CRYPTO_SELFTESTS)			+= simd.o
+obj-$(CONFIG_CRYPTO_SELFTESTS_FULL)		+= simd.o
 
 obj-$(CONFIG_CRYPTO_LIB_SM3)			+= libsm3.o
 libsm3-y					:= sm3.o

From f59427932885f9b47b22b532b079478905b9ad08 Mon Sep 17 00:00:00 2001
From: Sven Peter <sven@kernel.org>
Date: Thu, 12 Jun 2025 21:11:34 +0000
Subject: [PATCH 0335/1334] ASoC: apple: mca: Drop default ARCH_APPLE in
 Kconfig

When the first driver for Apple Silicon was upstreamed we accidentally
included `default ARCH_APPLE` in its Kconfig which then spread to almost
every subsequent driver. As soon as ARCH_APPLE is set to y this will
pull in many drivers as built-ins which is not what we want.
Thus, drop `default ARCH_APPLE` from Kconfig.

Signed-off-by: Sven Peter <sven@kernel.org>
Reviewed-by: Janne Grunau <j@jannau.net>
Link: https://patch.msgid.link/20250612-apple-kconfig-defconfig-v1-10-0e6f9cb512c1@kernel.org
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/apple/Kconfig | 1 -
 1 file changed, 1 deletion(-)

diff --git a/sound/soc/apple/Kconfig b/sound/soc/apple/Kconfig
index 793f7782e0d7..e9c777cdb6e3 100644
--- a/sound/soc/apple/Kconfig
+++ b/sound/soc/apple/Kconfig
@@ -2,7 +2,6 @@ config SND_SOC_APPLE_MCA
 	tristate "Apple Silicon MCA driver"
 	depends on ARCH_APPLE || COMPILE_TEST
 	select SND_DMAENGINE_PCM
-	default ARCH_APPLE
 	help
 	  This option enables an ASoC platform driver for MCA peripherals found
 	  on Apple Silicon SoCs.

From 9f0ad43b158d07bc7144d219ceabdea36e28e392 Mon Sep 17 00:00:00 2001
From: Thangaraj Samynathan <thangaraj.s@microchip.com>
Date: Thu, 12 Jun 2025 08:00:59 +0530
Subject: [PATCH 0336/1334] spi: spi-pci1xxxx: Drop MSI-X usage as unsupported
 by DMA engine

Removes MSI-X from the interrupt request path, as the DMA engine used by
the SPI controller does not support MSI-X interrupts.

Signed-off-by: Thangaraj Samynathan <thangaraj.s@microchip.com>
Link: https://patch.msgid.link/20250612023059.71726-1-thangaraj.s@microchip.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-pci1xxxx.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/spi/spi-pci1xxxx.c b/drivers/spi/spi-pci1xxxx.c
index 9112d8a1a0c8..e27642c4dea4 100644
--- a/drivers/spi/spi-pci1xxxx.c
+++ b/drivers/spi/spi-pci1xxxx.c
@@ -762,7 +762,7 @@ static int pci1xxxx_spi_probe(struct pci_dev *pdev, const struct pci_device_id *
 				return -EINVAL;
 
 			num_vector = pci_alloc_irq_vectors(pdev, 1, hw_inst_cnt,
-							   PCI_IRQ_ALL_TYPES);
+							   PCI_IRQ_INTX | PCI_IRQ_MSI);
 			if (num_vector < 0) {
 				dev_err(&pdev->dev, "Error allocating MSI vectors\n");
 				return num_vector;

From 9ba75ccad85708c5a484637dccc1fc59295b0a83 Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Wed, 11 Jun 2025 15:33:40 -0500
Subject: [PATCH 0337/1334] platform/x86/amd/pmc: Add PCSpecialist Lafite Pro V
 14M to 8042 quirks list
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Every other s2idle cycle fails to reach hardware sleep when keyboard
wakeup is enabled.  This appears to be an EC bug, but the vendor
refuses to fix it.

It was confirmed that turning off i8042 wakeup avoids ths issue
(albeit keyboard wakeup is disabled).  Take the lesser of two evils
and add it to the i8042 quirk list.

Reported-by: Raoul <ein4rth@gmail.com>
Closes: https://bugzilla.kernel.org/show_bug.cgi?id=220116
Tested-by: Raoul <ein4rth@gmail.com>
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Link: https://lore.kernel.org/r/20250611203341.3733478-1-superm1@kernel.org
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/amd/pmc/pmc-quirks.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/drivers/platform/x86/amd/pmc/pmc-quirks.c b/drivers/platform/x86/amd/pmc/pmc-quirks.c
index 5c7c01f66cde..f292111bd065 100644
--- a/drivers/platform/x86/amd/pmc/pmc-quirks.c
+++ b/drivers/platform/x86/amd/pmc/pmc-quirks.c
@@ -225,6 +225,15 @@ static const struct dmi_system_id fwbug_list[] = {
 			DMI_MATCH(DMI_BOARD_NAME, "WUJIE14-GX4HRXL"),
 		}
 	},
+	/* https://bugzilla.kernel.org/show_bug.cgi?id=220116 */
+	{
+		.ident = "PCSpecialist Lafite Pro V 14M",
+		.driver_data = &quirk_spurious_8042,
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "PCSpecialist"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Lafite Pro V 14M"),
+		}
+	},
 	{}
 };
 

From e2468dc700743683e1d1793bbd855e2536fd3de2 Mon Sep 17 00:00:00 2001
From: Kurt Borja <kuurtb@gmail.com>
Date: Wed, 11 Jun 2025 18:30:40 -0300
Subject: [PATCH 0338/1334] Revert "platform/x86: alienware-wmi-wmax: Add
 G-Mode support to Alienware m16 R1"
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This reverts commit 5ff79cabb23a2f14d2ed29e9596aec908905a0e6.

Although the Alienware m16 R1 AMD model supports G-Mode, it actually has
a lower power ceiling than plain "performance" profile, which results in
lower performance.

Reported-by: Cihan Ozakca <cozakca@outlook.com>
Cc: stable@vger.kernel.org # 6.15.x
Signed-off-by: Kurt Borja <kuurtb@gmail.com>
Link: https://lore.kernel.org/r/20250611-m16-rev-v1-1-72d13bad03c9@gmail.com
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/dell/alienware-wmi-wmax.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/platform/x86/dell/alienware-wmi-wmax.c b/drivers/platform/x86/dell/alienware-wmi-wmax.c
index c42f9228b0b2..20ec122a9fe0 100644
--- a/drivers/platform/x86/dell/alienware-wmi-wmax.c
+++ b/drivers/platform/x86/dell/alienware-wmi-wmax.c
@@ -119,7 +119,7 @@ static const struct dmi_system_id awcc_dmi_table[] __initconst = {
 			DMI_MATCH(DMI_SYS_VENDOR, "Alienware"),
 			DMI_MATCH(DMI_PRODUCT_NAME, "Alienware m16 R1 AMD"),
 		},
-		.driver_data = &g_series_quirks,
+		.driver_data = &generic_quirks,
 	},
 	{
 		.ident = "Alienware m16 R2",

From f826ec7966a63d48e16e0868af4e038bf9a1a3ae Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Thu, 12 Jun 2025 15:41:25 +0100
Subject: [PATCH 0339/1334] bio: Fix bio_first_folio() for SPARSEMEM without
 VMEMMAP

It is possible for physically contiguous folios to have discontiguous
struct pages if SPARSEMEM is enabled and SPARSEMEM_VMEMMAP is not.
This is correctly handled by folio_page_idx(), so remove this open-coded
implementation.

Fixes: 640d1930bef4 (block: Add bio_for_each_folio_all())
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Link: https://lore.kernel.org/r/20250612144126.2849931-1-willy@infradead.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/bio.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/linux/bio.h b/include/linux/bio.h
index 9c37c66ef9ca..46ffac5caab7 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -291,7 +291,7 @@ static inline void bio_first_folio(struct folio_iter *fi, struct bio *bio,
 
 	fi->folio = page_folio(bvec->bv_page);
 	fi->offset = bvec->bv_offset +
-			PAGE_SIZE * (bvec->bv_page - &fi->folio->page);
+			PAGE_SIZE * folio_page_idx(fi->folio, bvec->bv_page);
 	fi->_seg_count = bvec->bv_len;
 	fi->length = min(folio_size(fi->folio) - fi->offset, fi->_seg_count);
 	fi->_next = folio_next(fi->folio);

From 5e223e06ee7c6d8f630041a0645ac90e39a42cc6 Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Thu, 12 Jun 2025 15:42:53 +0100
Subject: [PATCH 0340/1334] block: Fix bvec_set_folio() for very large folios

Similarly to 26064d3e2b4d ("block: fix adding folio to bio"), if
we attempt to add a folio that is larger than 4GB, we'll silently
truncate the offset and len.  Widen the parameters to size_t, assert
that the length is less than 4GB and set the first page that contains
the interesting data rather than the first page of the folio.

Fixes: 26db5ee15851 (block: add a bvec_set_folio helper)
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Link: https://lore.kernel.org/r/20250612144255.2850278-1-willy@infradead.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/bvec.h | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/include/linux/bvec.h b/include/linux/bvec.h
index 204b22a99c4b..0a80e1f9aa20 100644
--- a/include/linux/bvec.h
+++ b/include/linux/bvec.h
@@ -57,9 +57,12 @@ static inline void bvec_set_page(struct bio_vec *bv, struct page *page,
  * @offset:	offset into the folio
  */
 static inline void bvec_set_folio(struct bio_vec *bv, struct folio *folio,
-		unsigned int len, unsigned int offset)
+		size_t len, size_t offset)
 {
-	bvec_set_page(bv, &folio->page, len, offset);
+	unsigned long nr = offset / PAGE_SIZE;
+
+	WARN_ON_ONCE(len > UINT_MAX);
+	bvec_set_page(bv, folio_page(folio, nr), len, offset % PAGE_SIZE);
 }
 
 /**

From b5acc3628898baa63658bc4125f9525f9b3dd4f3 Mon Sep 17 00:00:00 2001
From: Niklas Cassel <cassel@kernel.org>
Date: Thu, 12 Jun 2025 16:17:51 +0200
Subject: [PATCH 0341/1334] ata: ahci: Disallow LPM for ASUSPRO-D840SA
 motherboard

A user has bisected a regression which causes graphical corruptions on his
screen to commit 7627a0edef54 ("ata: ahci: Drop low power policy board
type").

Simply reverting commit 7627a0edef54 ("ata: ahci: Drop low power policy
board type") makes the graphical corruptions on his screen to go away.
(Note: there are no visible messages in dmesg that indicates a problem
with AHCI.)

The user also reports that the problem occurs regardless if there is an
HDD or an SSD connected via AHCI, so the problem is not device related.

The devices also work fine on other motherboards, so it seems specific to
the ASUSPRO-D840SA motherboard.

While enabling low power modes for AHCI is not supposed to affect
completely unrelated hardware, like a graphics card, it does however
allow the system to enter deeper PC-states, which could expose ACPI issues
that were previously not visible (because the system never entered these
lower power states before).

There are previous examples where enabling LPM exposed serious BIOS/ACPI
bugs, see e.g. commit 240630e61870 ("ahci: Disable LPM on Lenovo 50 series
laptops with a too old BIOS").

Since there hasn't been any BIOS update in years for the ASUSPRO-D840SA
motherboard, disable LPM for this board, in order to avoid entering lower
PC-states, which triggers graphical corruptions.

Cc: stable@vger.kernel.org
Reported-by: Andy Yang <andyybtc79@gmail.com>
Closes: https://bugzilla.kernel.org/show_bug.cgi?id=220111
Fixes: 7627a0edef54 ("ata: ahci: Drop low power policy board type")
Reviewed-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Hans de Goede <hansg@kernel.org>
Link: https://lore.kernel.org/r/20250612141750.2108342-2-cassel@kernel.org
Signed-off-by: Niklas Cassel <cassel@kernel.org>
---
 drivers/ata/ahci.c | 19 ++++++++++++++++++-
 1 file changed, 18 insertions(+), 1 deletion(-)

diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c
index e7c8357cbc54..c8ad8ace7496 100644
--- a/drivers/ata/ahci.c
+++ b/drivers/ata/ahci.c
@@ -1410,8 +1410,15 @@ static bool ahci_broken_suspend(struct pci_dev *pdev)
 
 static bool ahci_broken_lpm(struct pci_dev *pdev)
 {
+	/*
+	 * Platforms with LPM problems.
+	 * If driver_data is NULL, there is no existing BIOS version with
+	 * functioning LPM.
+	 * If driver_data is non-NULL, then driver_data contains the DMI BIOS
+	 * build date of the first BIOS version with functioning LPM (i.e. older
+	 * BIOS versions have broken LPM).
+	 */
 	static const struct dmi_system_id sysids[] = {
-		/* Various Lenovo 50 series have LPM issues with older BIOSen */
 		{
 			.matches = {
 				DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
@@ -1440,6 +1447,13 @@ static bool ahci_broken_lpm(struct pci_dev *pdev)
 			},
 			.driver_data = "20180409", /* 2.35 */
 		},
+		{
+			.matches = {
+				DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+				DMI_MATCH(DMI_PRODUCT_VERSION, "ASUSPRO D840MB_M840SA"),
+			},
+			/* 320 is broken, there is no known good version yet. */
+		},
 		{ }	/* terminate list */
 	};
 	const struct dmi_system_id *dmi = dmi_first_match(sysids);
@@ -1449,6 +1463,9 @@ static bool ahci_broken_lpm(struct pci_dev *pdev)
 	if (!dmi)
 		return false;
 
+	if (!dmi->driver_data)
+		return true;
+
 	dmi_get_date(DMI_BIOS_DATE, &year, &month, &date);
 	snprintf(buf, sizeof(buf), "%04d%02d%02d", year, month, date);
 

From 2b32fc8ff08deac3aa509f321a28e21b1eea5525 Mon Sep 17 00:00:00 2001
From: Brian Norris <briannorris@chromium.org>
Date: Thu, 12 Jun 2025 11:32:51 -0700
Subject: [PATCH 0342/1334] genirq/cpuhotplug: Rebalance managed interrupts
 across multi-CPU hotplug

Commit 788019eb559f ("genirq: Retain disable depth for managed interrupts
across CPU hotplug") intended to only decrement the disable depth once per
managed shutdown, but instead it decrements for each CPU hotplug in the
affinity mask, until its depth reaches a point where it finally gets
re-started.

For example, consider:

1. Interrupt is affine to CPU {M,N}
2. disable_irq() -> depth is 1
3. CPU M goes offline -> interrupt migrates to CPU N / depth is still 1
4. CPU N goes offline -> irq_shutdown() / depth is 2
5. CPU N goes online
    -> irq_restore_affinity_of_irq()
       -> irqd_is_managed_and_shutdown()==true
          -> irq_startup_managed() -> depth is 1
6. CPU M goes online
    -> irq_restore_affinity_of_irq()
       -> irqd_is_managed_and_shutdown()==true
          -> irq_startup_managed() -> depth is 0
          *** BUG: driver expects the interrupt is still disabled ***
             -> irq_startup() -> irqd_clr_managed_shutdown()
7. enable_irq() -> depth underflow / unbalanced enable_irq() warning

This should clear the managed-shutdown flag at step 6, so that further
hotplugs don't cause further imbalance.

Note: It might be cleaner to also remove the irqd_clr_managed_shutdown()
invocation from __irq_startup_managed(). But this is currently not possible
because of irq_update_affinity_desc() as it sets IRQD_MANAGED_SHUTDOWN and
expects irq_startup() to clear it.

Fixes: 788019eb559f ("genirq: Retain disable depth for managed interrupts across CPU hotplug")
Reported-by: Aleksandrs Vinarskis <alex.vinarskis@gmail.com>
Signed-off-by: Brian Norris <briannorris@chromium.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Aleksandrs Vinarskis <alex.vinarskis@gmail.com>
Link: https://lore.kernel.org/all/20250612183303.3433234-2-briannorris@chromium.org
---
 kernel/irq/chip.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index b0e0a7332993..2b274007e8ba 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -205,6 +205,14 @@ __irq_startup_managed(struct irq_desc *desc, const struct cpumask *aff,
 
 void irq_startup_managed(struct irq_desc *desc)
 {
+	struct irq_data *d = irq_desc_get_irq_data(desc);
+
+	/*
+	 * Clear managed-shutdown flag, so we don't repeat managed-startup for
+	 * multiple hotplugs, and cause imbalanced disable depth.
+	 */
+	irqd_clr_managed_shutdown(d);
+
 	/*
 	 * Only start it up when the disable depth is 1, so that a disable,
 	 * hotunplug, hotplug sequence does not end up enabling it during

From 72218d74c9c57b8ea36c2a58875dff406fc10462 Mon Sep 17 00:00:00 2001
From: Brian Norris <briannorris@chromium.org>
Date: Thu, 12 Jun 2025 11:32:52 -0700
Subject: [PATCH 0343/1334] genirq/cpuhotplug: Restore affinity even for
 suspended IRQ

Commit 788019eb559f ("genirq: Retain disable depth for managed interrupts
across CPU hotplug") tried to make managed shutdown/startup properly
reference counted, but it missed the fact that the unplug and hotplug code
has an intentional imbalance by skipping IRQS_SUSPENDED interrupts on
the "restore" path.

This means that if a managed-affinity interrupt was both suspended and
managed-shutdown (such as may happen during system suspend / S3), resume
skips calling irq_startup_managed(), and would again have an unbalanced
depth this time, with a positive value (i.e., remaining unexpectedly
masked).

This IRQS_SUSPENDED check was introduced in commit a60dd06af674
("genirq/cpuhotplug: Skip suspended interrupts when restoring affinity")
for essentially the same reason as commit 788019eb559f, to prevent that
irq_startup() would unconditionally re-enable an interrupt too early.

Because irq_startup_managed() now respsects the disable-depth count, the
IRQS_SUSPENDED check is not longer needed, and instead, it causes harm.

Thus, drop the IRQS_SUSPENDED check, and restore balance.

This effectively reverts commit a60dd06af674 ("genirq/cpuhotplug: Skip
suspended interrupts when restoring affinity"), because it is replaced
by commit 788019eb559f ("genirq: Retain disable depth for managed
interrupts across CPU hotplug").

Fixes: 788019eb559f ("genirq: Retain disable depth for managed interrupts across CPU hotplug")
Reported-by: Aleksandrs Vinarskis <alex.vinarskis@gmail.com>
Signed-off-by: Brian Norris <briannorris@chromium.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Aleksandrs Vinarskis <alex.vinarskis@gmail.com>
Link: https://lore.kernel.org/all/20250612183303.3433234-3-briannorris@chromium.org
Closes: https://lore.kernel.org/lkml/24ec4adc-7c80-49e9-93ee-19908a97ab84@gmail.com/
---
 kernel/irq/cpuhotplug.c | 7 -------
 1 file changed, 7 deletions(-)

diff --git a/kernel/irq/cpuhotplug.c b/kernel/irq/cpuhotplug.c
index f07529ae4895..755346ea9819 100644
--- a/kernel/irq/cpuhotplug.c
+++ b/kernel/irq/cpuhotplug.c
@@ -210,13 +210,6 @@ static void irq_restore_affinity_of_irq(struct irq_desc *desc, unsigned int cpu)
 	    !irq_data_get_irq_chip(data) || !cpumask_test_cpu(cpu, affinity))
 		return;
 
-	/*
-	 * Don't restore suspended interrupts here when a system comes back
-	 * from S3. They are reenabled via resume_device_irqs().
-	 */
-	if (desc->istate & IRQS_SUSPENDED)
-		return;
-
 	if (irqd_is_managed_and_shutdown(data))
 		irq_startup_managed(desc);
 

From 8a2277a3c9e4cc5398f80821afe7ecbe9bdf2819 Mon Sep 17 00:00:00 2001
From: Gyeyoung Baek <gye976@gmail.com>
Date: Thu, 12 Jun 2025 21:48:27 +0900
Subject: [PATCH 0344/1334] genirq/irq_sim: Initialize work context pointers
 properly

Initialize `ops` member's pointers properly by using kzalloc() instead of
kmalloc() when allocating the simulation work context. Otherwise the
pointers contain random content leading to invalid dereferencing.

Signed-off-by: Gyeyoung Baek <gye976@gmail.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/20250612124827.63259-1-gye976@gmail.com
---
 kernel/irq/irq_sim.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/irq/irq_sim.c b/kernel/irq/irq_sim.c
index 1a3d483548e2..ae4c9cbd1b4b 100644
--- a/kernel/irq/irq_sim.c
+++ b/kernel/irq/irq_sim.c
@@ -202,7 +202,7 @@ struct irq_domain *irq_domain_create_sim_full(struct fwnode_handle *fwnode,
 					      void *data)
 {
 	struct irq_sim_work_ctx *work_ctx __free(kfree) =
-				kmalloc(sizeof(*work_ctx), GFP_KERNEL);
+				kzalloc(sizeof(*work_ctx), GFP_KERNEL);
 
 	if (!work_ctx)
 		return ERR_PTR(-ENOMEM);

From 80626ae6ffe57917915c6e6d8ea1e908689954fd Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.i.king@gmail.com>
Date: Thu, 22 May 2025 14:15:12 +0100
Subject: [PATCH 0345/1334] drm/nouveau/gsp: Fix potential integer overflow on
 integer shifts

The left shift int 32 bit integer constants 1 is evaluated using 32 bit
arithmetic and then assigned to a 64 bit unsigned integer. In the case
where the shift is 32 or more this can lead to an overflow. Avoid this
by shifting using the BIT_ULL macro instead.

Fixes: 6c3ac7bcfcff ("drm/nouveau/gsp: support deeper page tables in COPY_SERVER_RESERVED_PDES")
Signed-off-by: Colin Ian King <colin.i.king@gmail.com>
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
Link: https://lore.kernel.org/r/20250522131512.2768310-1-colin.i.king@gmail.com
---
 drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/vmm.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/vmm.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/vmm.c
index 52f2e5f14517..f25ea610cd99 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/vmm.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/vmm.c
@@ -121,7 +121,7 @@ r535_mmu_vaspace_new(struct nvkm_vmm *vmm, u32 handle, bool external)
 			page_shift -= desc->bits;
 
 			ctrl->levels[i].physAddress = pd->pt[0]->addr;
-			ctrl->levels[i].size = (1 << desc->bits) * desc->size;
+			ctrl->levels[i].size = BIT_ULL(desc->bits) * desc->size;
 			ctrl->levels[i].aperture = 1;
 			ctrl->levels[i].pageShift = page_shift;
 

From ac1daa91e9370e3b88ef7826a73d62a4d09e2717 Mon Sep 17 00:00:00 2001
From: Janne Grunau <j@jannau.net>
Date: Wed, 11 Jun 2025 22:30:31 +0200
Subject: [PATCH 0346/1334] arm64: dts: apple: t8103: Fix PCIe BCM4377 nodename

Fix the following `make dtbs_check` warnings for all t8103 based devices:

arch/arm64/boot/dts/apple/t8103-j274.dtb: network@0,0: $nodename:0: 'network@0,0' does not match '^wifi(@.*)?$'
        from schema $id: http://devicetree.org/schemas/net/wireless/brcm,bcm4329-fmac.yaml#
arch/arm64/boot/dts/apple/t8103-j274.dtb: network@0,0: Unevaluated properties are not allowed ('local-mac-address' was unexpected)
        from schema $id: http://devicetree.org/schemas/net/wireless/brcm,bcm4329-fmac.yaml#

Fixes: bf2c05b619ff ("arm64: dts: apple: t8103: Expose PCI node for the WiFi MAC address")
Signed-off-by: Janne Grunau <j@jannau.net>
Reviewed-by: Sven Peter <sven@kernel.org>
Link: https://lore.kernel.org/r/20250611-arm64_dts_apple_wifi-v1-1-fb959d8e1eb4@jannau.net
Signed-off-by: Sven Peter <sven@kernel.org>
---
 arch/arm64/boot/dts/apple/t8103-jxxx.dtsi | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/arm64/boot/dts/apple/t8103-jxxx.dtsi b/arch/arm64/boot/dts/apple/t8103-jxxx.dtsi
index 8e82231acab5..0c8206156bfe 100644
--- a/arch/arm64/boot/dts/apple/t8103-jxxx.dtsi
+++ b/arch/arm64/boot/dts/apple/t8103-jxxx.dtsi
@@ -71,7 +71,7 @@
  */
 &port00 {
 	bus-range = <1 1>;
-	wifi0: network@0,0 {
+	wifi0: wifi@0,0 {
 		compatible = "pci14e4,4425";
 		reg = <0x10000 0x0 0x0 0x0 0x0>;
 		/* To be filled by the loader */

From 811a909978bf59caa25359e0aca4e30500dcff26 Mon Sep 17 00:00:00 2001
From: Sven Peter <sven@kernel.org>
Date: Tue, 10 Jun 2025 19:19:24 +0000
Subject: [PATCH 0347/1334] arm64: dts: apple: Drop {address,size}-cells from
 SPI NOR

Fix the following warning by dropping #{address,size}-cells from the SPI
NOR node which only has a single child node without reg property:

spi1-nvram.dtsi:19.10-38.4: Warning (avoid_unnecessary_addr_size): /soc/spi@235104000/flash@0: unnecessary #address-cells/#size-cells without "ranges", "dma-ranges" or child "reg" property

Fixes: 3febe9de5ca5 ("arm64: dts: apple: Add SPI NOR nvram partition to all devices")
Reviewed-by: Janne Grunau <j@jannau.net>
Link: https://lore.kernel.org/r/20250610-apple-dts-warnings-v1-1-70b53e8108a0@kernel.org
Signed-off-by: Sven Peter <sven@kernel.org>
---
 arch/arm64/boot/dts/apple/spi1-nvram.dtsi | 2 --
 1 file changed, 2 deletions(-)

diff --git a/arch/arm64/boot/dts/apple/spi1-nvram.dtsi b/arch/arm64/boot/dts/apple/spi1-nvram.dtsi
index 3df2fd3993b5..9740fbf200f0 100644
--- a/arch/arm64/boot/dts/apple/spi1-nvram.dtsi
+++ b/arch/arm64/boot/dts/apple/spi1-nvram.dtsi
@@ -20,8 +20,6 @@
 		compatible = "jedec,spi-nor";
 		reg = <0x0>;
 		spi-max-frequency = <25000000>;
-		#address-cells = <1>;
-		#size-cells = <1>;
 
 		partitions {
 			compatible = "fixed-partitions";

From 08a0d93c353bd55de8b5fb77b464d89425be0215 Mon Sep 17 00:00:00 2001
From: Sven Peter <sven@kernel.org>
Date: Wed, 11 Jun 2025 15:18:53 +0000
Subject: [PATCH 0348/1334] arm64: dts: apple: Move touchbar mipi
 {address,size}-cells from dtsi to dts

Move the {address,size}-cells property from the (disabled) touchbar screen
mipi node inside the dtsi file to the model-specific dts file where it's
enabled to fix the following W=1 warnings:

t8103.dtsi:404.34-433.5: Warning (avoid_unnecessary_addr_size): /soc/dsi@228600000: unnecessary #address-cells/#size-cells without "ranges", "dma-ranges" or child "reg" property
t8112.dtsi:419.34-448.5: Warning (avoid_unnecessary_addr_size): /soc/dsi@228600000: unnecessary #address-cells/#size-cells without "ranges", "dma-ranges" or child "reg" property

Fixes: 7275e795e520 ("arm64: dts: apple: Add touchbar screen nodes")
Reviewed-by: Janne Grunau <j@jannau.net>
Link: https://lore.kernel.org/r/20250611-display-pipe-mipi-warning-v1-1-bd80ba2c0eea@kernel.org
Signed-off-by: Sven Peter <sven@kernel.org>
---
 arch/arm64/boot/dts/apple/t8103-j293.dts | 2 ++
 arch/arm64/boot/dts/apple/t8103.dtsi     | 2 --
 arch/arm64/boot/dts/apple/t8112-j493.dts | 2 ++
 arch/arm64/boot/dts/apple/t8112.dtsi     | 2 --
 4 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/arch/arm64/boot/dts/apple/t8103-j293.dts b/arch/arm64/boot/dts/apple/t8103-j293.dts
index e2d9439397f7..5b3c42e9f0e6 100644
--- a/arch/arm64/boot/dts/apple/t8103-j293.dts
+++ b/arch/arm64/boot/dts/apple/t8103-j293.dts
@@ -100,6 +100,8 @@
 
 &displaydfr_mipi {
 	status = "okay";
+	#address-cells = <1>;
+	#size-cells = <0>;
 
 	dfr_panel: panel@0 {
 		compatible = "apple,j293-summit", "apple,summit";
diff --git a/arch/arm64/boot/dts/apple/t8103.dtsi b/arch/arm64/boot/dts/apple/t8103.dtsi
index 20faf0c0d809..3a204845b85b 100644
--- a/arch/arm64/boot/dts/apple/t8103.dtsi
+++ b/arch/arm64/boot/dts/apple/t8103.dtsi
@@ -405,8 +405,6 @@
 			compatible = "apple,t8103-display-pipe-mipi", "apple,h7-display-pipe-mipi";
 			reg = <0x2 0x28600000 0x0 0x100000>;
 			power-domains = <&ps_mipi_dsi>;
-			#address-cells = <1>;
-			#size-cells = <0>;
 			status = "disabled";
 
 			ports {
diff --git a/arch/arm64/boot/dts/apple/t8112-j493.dts b/arch/arm64/boot/dts/apple/t8112-j493.dts
index be86d34c6696..fb8ad7d4c65a 100644
--- a/arch/arm64/boot/dts/apple/t8112-j493.dts
+++ b/arch/arm64/boot/dts/apple/t8112-j493.dts
@@ -63,6 +63,8 @@
 
 &displaydfr_mipi {
 	status = "okay";
+	#address-cells = <1>;
+	#size-cells = <0>;
 
 	dfr_panel: panel@0 {
 		compatible = "apple,j493-summit", "apple,summit";
diff --git a/arch/arm64/boot/dts/apple/t8112.dtsi b/arch/arm64/boot/dts/apple/t8112.dtsi
index e95711d8337f..f68354194355 100644
--- a/arch/arm64/boot/dts/apple/t8112.dtsi
+++ b/arch/arm64/boot/dts/apple/t8112.dtsi
@@ -420,8 +420,6 @@
 			compatible = "apple,t8112-display-pipe-mipi", "apple,h7-display-pipe-mipi";
 			reg = <0x2 0x28600000 0x0 0x100000>;
 			power-domains = <&ps_mipi_dsi>;
-			#address-cells = <1>;
-			#size-cells = <0>;
 			status = "disabled";
 
 			ports {

From 9802f0a63b641f4cddb2139c814c2e95cb825099 Mon Sep 17 00:00:00 2001
From: Zhi Wang <zhiw@nvidia.com>
Date: Tue, 27 May 2025 16:37:12 +0000
Subject: [PATCH 0349/1334] drm/nouveau: fix a use-after-free in
 r535_gsp_rpc_push()

The RPC container is released after being passed to r535_gsp_rpc_send().

When sending the initial fragment of a large RPC and passing the
caller's RPC container, the container will be freed prematurely. Subsequent
attempts to send remaining fragments will therefore result in a
use-after-free.

Allocate a temporary RPC container for holding the initial fragment of a
large RPC when sending. Free the caller's container when all fragments
are successfully sent.

Fixes: 176fdcbddfd2 ("drm/nouveau/gsp/r535: add support for booting GSP-RM")
Signed-off-by: Zhi Wang <zhiw@nvidia.com>
Link: https://lore.kernel.org/r/20250527163712.3444-1-zhiw@nvidia.com
[ Rebase onto Blackwell changes. - Danilo ]
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
---
 .../drm/nouveau/nvkm/subdev/gsp/rm/r535/rpc.c   | 17 ++++++++++++-----
 1 file changed, 12 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/rpc.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/rpc.c
index 5acb98d137bd..9d06ff722fea 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/rpc.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/rpc.c
@@ -637,12 +637,18 @@ r535_gsp_rpc_push(struct nvkm_gsp *gsp, void *payload,
 	if (payload_size > max_payload_size) {
 		const u32 fn = rpc->function;
 		u32 remain_payload_size = payload_size;
+		void *next;
 
-		/* Adjust length, and send initial RPC. */
-		rpc->length = sizeof(*rpc) + max_payload_size;
-		msg->checksum = rpc->length;
+		/* Send initial RPC. */
+		next = r535_gsp_rpc_get(gsp, fn, max_payload_size);
+		if (IS_ERR(next)) {
+			repv = next;
+			goto done;
+		}
 
-		repv = r535_gsp_rpc_send(gsp, payload, NVKM_GSP_RPC_REPLY_NOWAIT, 0);
+		memcpy(next, payload, max_payload_size);
+
+		repv = r535_gsp_rpc_send(gsp, next, NVKM_GSP_RPC_REPLY_NOWAIT, 0);
 		if (IS_ERR(repv))
 			goto done;
 
@@ -653,7 +659,6 @@ r535_gsp_rpc_push(struct nvkm_gsp *gsp, void *payload,
 		while (remain_payload_size) {
 			u32 size = min(remain_payload_size,
 				       max_payload_size);
-			void *next;
 
 			next = r535_gsp_rpc_get(gsp, NV_VGPU_MSG_FUNCTION_CONTINUATION_RECORD, size);
 			if (IS_ERR(next)) {
@@ -674,6 +679,8 @@ r535_gsp_rpc_push(struct nvkm_gsp *gsp, void *payload,
 		/* Wait for reply. */
 		repv = r535_gsp_rpc_handle_reply(gsp, fn, policy, payload_size +
 						 sizeof(*rpc));
+		if (!IS_ERR(repv))
+			kvfree(msg);
 	} else {
 		repv = r535_gsp_rpc_send(gsp, payload, policy, gsp_rpc_len);
 	}

From 61b2b3737499f1fb361a54a16828db24a8345e85 Mon Sep 17 00:00:00 2001
From: Jacob Keller <jacob.e.keller@intel.com>
Date: Tue, 10 Jun 2025 14:54:51 -0700
Subject: [PATCH 0350/1334] drm/nouveau/bl: increase buffer size to avoid
 truncate warning
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The nouveau_get_backlight_name() function generates a unique name for the
backlight interface, appending an id from 1 to 99 for all backlight devices
after the first.

GCC 15 (and likely other compilers) produce the following
-Wformat-truncation warning:

nouveau_backlight.c: In function ‘nouveau_backlight_init’:
nouveau_backlight.c:56:69: error: ‘%d’ directive output may be truncated writing between 1 and 10 bytes into a region of size 3 [-Werror=format-truncation=]
   56 |                 snprintf(backlight_name, BL_NAME_SIZE, "nv_backlight%d", nb);
      |                                                                     ^~
In function ‘nouveau_get_backlight_name’,
    inlined from ‘nouveau_backlight_init’ at nouveau_backlight.c:351:7:
nouveau_backlight.c:56:56: note: directive argument in the range [1, 2147483647]
   56 |                 snprintf(backlight_name, BL_NAME_SIZE, "nv_backlight%d", nb);
      |                                                        ^~~~~~~~~~~~~~~~
nouveau_backlight.c:56:17: note: ‘snprintf’ output between 14 and 23 bytes into a destination of size 15
   56 |                 snprintf(backlight_name, BL_NAME_SIZE, "nv_backlight%d", nb);
      |                 ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

The warning started appearing after commit ab244be47a8f ("drm/nouveau:
Fix a potential theorical leak in nouveau_get_backlight_name()") This fix
for the ida usage removed the explicit value check for ids larger than 99.
The compiler is unable to intuit that the ida_alloc_max() limits the
returned value range between 0 and 99.

Because the compiler can no longer infer that the number ranges from 0 to
99, it thinks that it could use as many as 11 digits (10 + the potential -
sign for negative numbers).

The warning has gone unfixed for some time, with at least one kernel test
robot report. The code breaks W=1 builds, which is especially frustrating
with the introduction of CONFIG_WERROR.

The string is stored temporarily on the stack and then copied into the
device name. Its not a big deal to use 11 more bytes of stack rounding out
to an even 24 bytes. Increase BL_NAME_SIZE to 24 to avoid the truncation
warning. This fixes the W=1 builds that include this driver.

Compile tested only.

Fixes: ab244be47a8f ("drm/nouveau: Fix a potential theorical leak in nouveau_get_backlight_name()")
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202312050324.0kv4PnfZ-lkp@intel.com/
Suggested-by: Timur Tabi <ttabi@nvidia.com>
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://lore.kernel.org/r/20250610-jk-nouveua-drm-bl-snprintf-fix-v2-1-7fdd4b84b48e@intel.com
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
---
 drivers/gpu/drm/nouveau/nouveau_backlight.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/nouveau/nouveau_backlight.c b/drivers/gpu/drm/nouveau/nouveau_backlight.c
index d47442125fa1..9aae26eb7d8f 100644
--- a/drivers/gpu/drm/nouveau/nouveau_backlight.c
+++ b/drivers/gpu/drm/nouveau/nouveau_backlight.c
@@ -42,7 +42,7 @@
 #include "nouveau_acpi.h"
 
 static struct ida bl_ida;
-#define BL_NAME_SIZE 15 // 12 for name + 2 for digits + 1 for '\0'
+#define BL_NAME_SIZE 24 // 12 for name + 11 for digits + 1 for '\0'
 
 static bool
 nouveau_get_backlight_name(char backlight_name[BL_NAME_SIZE],

From 553ab30a181043f01b99a493ba13f9c011eb75ae Mon Sep 17 00:00:00 2001
From: Bagas Sanjaya <bagasdotme@gmail.com>
Date: Wed, 11 Jun 2025 09:08:06 +0700
Subject: [PATCH 0351/1334] Documentation: nouveau: Update GSP message queue
 kernel-doc reference

GSP message queue docs has been moved following RPC handling split in
commit 8a8b1ec5261f20 ("drm/nouveau/gsp: split rpc handling out on its
own"), before GSP-RM implementation is versioned in commit c472d828348caf
("drm/nouveau/gsp: move subdev/engine impls to subdev/gsp/rm/r535/").
However, the kernel-doc reference in nouveau docs is left behind, which
triggers htmldocs warnings:

ERROR: Cannot find file ./drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c
WARNING: No kernel-doc for file ./drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c

Update the reference.

Fixes: c472d828348c ("drm/nouveau/gsp: move subdev/engine impls to subdev/gsp/rm/r535/")
Fixes: 8a8b1ec5261f ("drm/nouveau/gsp: split rpc handling out on its own")
Signed-off-by: Bagas Sanjaya <bagasdotme@gmail.com>
Acked-by: Randy Dunlap <rdunlap@infradead.org>
Tested-by: Randy Dunlap <rdunlap@infradead.org>
Link: https://lore.kernel.org/r/20250611020805.22418-2-bagasdotme@gmail.com
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
---
 Documentation/gpu/nouveau.rst | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/gpu/nouveau.rst b/Documentation/gpu/nouveau.rst
index b8c801e0068c..cab2e81013bc 100644
--- a/Documentation/gpu/nouveau.rst
+++ b/Documentation/gpu/nouveau.rst
@@ -25,7 +25,7 @@ providing a consistent API to upper layers of the driver stack.
 GSP Support
 ------------------------
 
-.. kernel-doc:: drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c
+.. kernel-doc:: drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/rpc.c
    :doc: GSP message queue element
 
 .. kernel-doc:: drivers/gpu/drm/nouveau/include/nvkm/subdev/gsp.h

From f9705d66fa7107fcd619083f7aae2afb0554a593 Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@nvidia.com>
Date: Tue, 3 Jun 2025 16:14:45 -0300
Subject: [PATCH 0352/1334] iommu/tegra: Fix incorrect size calculation

This driver uses a mixture of ways to get the size of a PTE,
tegra_smmu_set_pde() did it as sizeof(*pd) which became wrong when pd
switched to a struct tegra_pd.

Switch pd back to a u32* in tegra_smmu_set_pde() so the sizeof(*pd)
returns 4.

Fixes: 50568f87d1e2 ("iommu/terga: Do not use struct page as the handle for as->pd memory")
Reported-by: Diogo Ivo <diogo.ivo@tecnico.ulisboa.pt>
Closes: https://lore.kernel.org/all/62e7f7fe-6200-4e4f-ad42-d58ad272baa6@tecnico.ulisboa.pt/
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Acked-by: Thierry Reding <treding@nvidia.com>
Reviewed-by: Jerry Snitselaar <jsnitsel@redhat.com>
Tested-by: Diogo Ivo <diogo.ivo@tecnico.ulisboa.pt>
Link: https://lore.kernel.org/r/0-v1-da7b8b3d57eb+ce-iommu_terga_sizeof_jgg@nvidia.com
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
---
 drivers/iommu/tegra-smmu.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/iommu/tegra-smmu.c b/drivers/iommu/tegra-smmu.c
index 61897d50162d..e58fe9d8b9e7 100644
--- a/drivers/iommu/tegra-smmu.c
+++ b/drivers/iommu/tegra-smmu.c
@@ -559,11 +559,11 @@ static void tegra_smmu_set_pde(struct tegra_smmu_as *as, unsigned long iova,
 {
 	unsigned int pd_index = iova_pd_index(iova);
 	struct tegra_smmu *smmu = as->smmu;
-	struct tegra_pd *pd = as->pd;
+	u32 *pd = &as->pd->val[pd_index];
 	unsigned long offset = pd_index * sizeof(*pd);
 
 	/* Set the page directory entry first */
-	pd->val[pd_index] = value;
+	*pd = value;
 
 	/* The flush the page directory entry from caches */
 	dma_sync_single_range_for_device(smmu->dev, as->pd_dma, offset,

From db3dfae1a2f662e69d535827703bcdbb04b8d72b Mon Sep 17 00:00:00 2001
From: Bagas Sanjaya <bagasdotme@gmail.com>
Date: Fri, 13 Jun 2025 09:38:57 +0700
Subject: [PATCH 0353/1334] Documentation: ublk: Separate UBLK_F_AUTO_BUF_REG
 fallback behavior sublists

Stephen Rothwell reports htmldocs warning on ublk docs:

Documentation/block/ublk.rst:414: ERROR: Unexpected indentation. [docutils]

Fix the warning by separating sublists of auto buffer registration
fallback behavior from their appropriate parent list item.

Fixes: ff20c516485e ("ublk: document auto buffer registration(UBLK_F_AUTO_BUF_REG)")
Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Closes: https://lore.kernel.org/linux-next/20250612132638.193de386@canb.auug.org.au/
Signed-off-by: Bagas Sanjaya <bagasdotme@gmail.com>
Link: https://lore.kernel.org/r/20250613023857.15971-1-bagasdotme@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 Documentation/block/ublk.rst | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/Documentation/block/ublk.rst b/Documentation/block/ublk.rst
index abec524a04ed..8c4030bcabb6 100644
--- a/Documentation/block/ublk.rst
+++ b/Documentation/block/ublk.rst
@@ -408,6 +408,7 @@ Fallback Behavior
 If auto buffer registration fails:
 
 1. When ``UBLK_AUTO_BUF_REG_FALLBACK`` is enabled:
+
    - The uring_cmd is completed
    - ``UBLK_IO_F_NEED_REG_BUF`` is set in ``ublksrv_io_desc.op_flags``
    - The ublk server must manually deal with the failure, such as, register
@@ -415,6 +416,7 @@ If auto buffer registration fails:
      for handling ublk IO
 
 2. If fallback is not enabled:
+
    - The ublk I/O request fails silently
    - The uring_cmd won't be completed
 

From a403fe6c0b17f472e01246eb350f5eef105243ac Mon Sep 17 00:00:00 2001
From: Li Ming <ming.li@zohomail.com>
Date: Fri, 13 Jun 2025 09:16:48 +0800
Subject: [PATCH 0354/1334] cxl/edac: Fix potential memory leak issues

In cxl_store_rec_gen_media() and cxl_store_rec_dram(), use kmemdup() to
duplicate a cxl gen_media/dram event to store the event in a xarray by
xa_store(). The cxl gen_media/dram event allocated by kmemdup() should
be freed in the case that the xa_store() fails.

Fixes: 0b5ccb0de1e2 ("cxl/edac: Support for finding memory operation attributes from the current boot")
Signed-off-by: Li Ming <ming.li@zohomail.com>
Tested-by: Shiju Jose <shiju.jose@huawei.com>
Reviewed-by: Shiju Jose <shiju.jose@huawei.com>
Reviewed-by: Ira Weiny <ira.weiny@intel.com>
Reviewed-by: Jonathan Cameron <jonathan.cameron@huawei.com>
Link: https://patch.msgid.link/20250613011648.102840-1-ming.li@zohomail.com
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
---
 drivers/cxl/core/edac.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/cxl/core/edac.c b/drivers/cxl/core/edac.c
index 0ef245d0bd9f..d725ee954199 100644
--- a/drivers/cxl/core/edac.c
+++ b/drivers/cxl/core/edac.c
@@ -1103,8 +1103,10 @@ int cxl_store_rec_gen_media(struct cxl_memdev *cxlmd, union cxl_event *evt)
 	old_rec = xa_store(&array_rec->rec_gen_media,
 			   le64_to_cpu(rec->media_hdr.phys_addr), rec,
 			   GFP_KERNEL);
-	if (xa_is_err(old_rec))
+	if (xa_is_err(old_rec)) {
+		kfree(rec);
 		return xa_err(old_rec);
+	}
 
 	kfree(old_rec);
 
@@ -1131,8 +1133,10 @@ int cxl_store_rec_dram(struct cxl_memdev *cxlmd, union cxl_event *evt)
 	old_rec = xa_store(&array_rec->rec_dram,
 			   le64_to_cpu(rec->media_hdr.phys_addr), rec,
 			   GFP_KERNEL);
-	if (xa_is_err(old_rec))
+	if (xa_is_err(old_rec)) {
+		kfree(rec);
 		return xa_err(old_rec);
+	}
 
 	kfree(old_rec);
 

From 3c70ec71abdaf4e4fa48cd8fdfbbd864d78235a8 Mon Sep 17 00:00:00 2001
From: Dan Williams <dan.j.williams@intel.com>
Date: Thu, 12 Jun 2025 12:20:43 -0700
Subject: [PATCH 0355/1334] cxl/ras: Fix CPER handler device confusion

By inspection, cxl_cper_handle_prot_err() is making a series of fragile
assumptions that can lead to crashes:

1/ It assumes that endpoints identified in the record are a CXL-type-3
   device, nothing guarantees that.

2/ It assumes that the device is bound to the cxl_pci driver, nothing
   guarantees that.

3/ Minor, it holds the device lock over the switch-port tracing for no
   reason as the trace is 100% generated from data in the record.

Correct those by checking that the PCIe endpoint parents a cxl_memdev
before assuming the format of the driver data, and move the lock to where
it is required. Consequently this also makes the implementation ready for
CXL accelerators that are not bound to cxl_pci.

Fixes: 36f257e3b0ba ("acpi/ghes, cxl/pci: Process CXL CPER Protocol Errors")
Cc: Terry Bowman <terry.bowman@amd.com>
Cc: Li Ming <ming.li@zohomail.com>
Cc: Alison Schofield <alison.schofield@intel.com>
Cc: Ira Weiny <ira.weiny@intel.com>
Cc: Tony Luck <tony.luck@intel.com>
Reviewed-by: Smita Koralahalli <Smita.KoralahalliChannabasappa@amd.com>
Reviewed-by: Dave Jiang <dave.jiang@intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Reviewed-by: Jonathan Cameron <jonathan.cameron@huawei.com>
Reviewed-by: Li Ming <ming.li@zohomail.com>
Link: https://patch.msgid.link/20250612192043.2254617-1-dan.j.williams@intel.com
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
---
 drivers/cxl/core/ras.c | 47 ++++++++++++++++++++++++------------------
 1 file changed, 27 insertions(+), 20 deletions(-)

diff --git a/drivers/cxl/core/ras.c b/drivers/cxl/core/ras.c
index 485a831695c7..2731ba3a0799 100644
--- a/drivers/cxl/core/ras.c
+++ b/drivers/cxl/core/ras.c
@@ -31,40 +31,38 @@ static void cxl_cper_trace_uncorr_port_prot_err(struct pci_dev *pdev,
 					       ras_cap.header_log);
 }
 
-static void cxl_cper_trace_corr_prot_err(struct pci_dev *pdev,
-				  struct cxl_ras_capability_regs ras_cap)
+static void cxl_cper_trace_corr_prot_err(struct cxl_memdev *cxlmd,
+					 struct cxl_ras_capability_regs ras_cap)
 {
 	u32 status = ras_cap.cor_status & ~ras_cap.cor_mask;
-	struct cxl_dev_state *cxlds;
 
-	cxlds = pci_get_drvdata(pdev);
-	if (!cxlds)
-		return;
-
-	trace_cxl_aer_correctable_error(cxlds->cxlmd, status);
+	trace_cxl_aer_correctable_error(cxlmd, status);
 }
 
-static void cxl_cper_trace_uncorr_prot_err(struct pci_dev *pdev,
-				    struct cxl_ras_capability_regs ras_cap)
+static void
+cxl_cper_trace_uncorr_prot_err(struct cxl_memdev *cxlmd,
+			       struct cxl_ras_capability_regs ras_cap)
 {
 	u32 status = ras_cap.uncor_status & ~ras_cap.uncor_mask;
-	struct cxl_dev_state *cxlds;
 	u32 fe;
 
-	cxlds = pci_get_drvdata(pdev);
-	if (!cxlds)
-		return;
-
 	if (hweight32(status) > 1)
 		fe = BIT(FIELD_GET(CXL_RAS_CAP_CONTROL_FE_MASK,
 				   ras_cap.cap_control));
 	else
 		fe = status;
 
-	trace_cxl_aer_uncorrectable_error(cxlds->cxlmd, status, fe,
+	trace_cxl_aer_uncorrectable_error(cxlmd, status, fe,
 					  ras_cap.header_log);
 }
 
+static int match_memdev_by_parent(struct device *dev, const void *uport)
+{
+	if (is_cxl_memdev(dev) && dev->parent == uport)
+		return 1;
+	return 0;
+}
+
 static void cxl_cper_handle_prot_err(struct cxl_cper_prot_err_work_data *data)
 {
 	unsigned int devfn = PCI_DEVFN(data->prot_err.agent_addr.device,
@@ -73,13 +71,12 @@ static void cxl_cper_handle_prot_err(struct cxl_cper_prot_err_work_data *data)
 		pci_get_domain_bus_and_slot(data->prot_err.agent_addr.segment,
 					    data->prot_err.agent_addr.bus,
 					    devfn);
+	struct cxl_memdev *cxlmd;
 	int port_type;
 
 	if (!pdev)
 		return;
 
-	guard(device)(&pdev->dev);
-
 	port_type = pci_pcie_type(pdev);
 	if (port_type == PCI_EXP_TYPE_ROOT_PORT ||
 	    port_type == PCI_EXP_TYPE_DOWNSTREAM ||
@@ -92,10 +89,20 @@ static void cxl_cper_handle_prot_err(struct cxl_cper_prot_err_work_data *data)
 		return;
 	}
 
+	guard(device)(&pdev->dev);
+	if (!pdev->dev.driver)
+		return;
+
+	struct device *mem_dev __free(put_device) = bus_find_device(
+		&cxl_bus_type, NULL, pdev, match_memdev_by_parent);
+	if (!mem_dev)
+		return;
+
+	cxlmd = to_cxl_memdev(mem_dev);
 	if (data->severity == AER_CORRECTABLE)
-		cxl_cper_trace_corr_prot_err(pdev, data->ras_cap);
+		cxl_cper_trace_corr_prot_err(cxlmd, data->ras_cap);
 	else
-		cxl_cper_trace_uncorr_prot_err(pdev, data->ras_cap);
+		cxl_cper_trace_uncorr_prot_err(cxlmd, data->ras_cap);
 }
 
 static void cxl_cper_prot_err_work_fn(struct work_struct *work)

From d57e92dd660014ccac884eda616cafc7b04601e0 Mon Sep 17 00:00:00 2001
From: Thierry Reding <treding@nvidia.com>
Date: Fri, 13 Jun 2025 14:30:37 +0200
Subject: [PATCH 0356/1334] spi: tegra210-qspi: Remove cache operations

The DMA memory for this driver is allocated using dma_alloc_coherent(),
which ends up mapping the allocated memory as uncached. Performing the
various dma_sync_*() operations on this memory causes issues during SPI
flashing:

[    7.818017] pc : dcache_inval_poc+0x40/0x58
[    7.822128] lr : arch_sync_dma_for_cpu+0x2c/0x4c
[    7.826854] sp : ffff80008193bcf0
[    7.830267] x29: ffff80008193bcf0 x28: ffffa3fe5ff1e908 x27: ffffa3fe627bb130
[    7.837528] x26: ffff000086952180 x25: ffff00008015c8ac x24: ffff000086c9b480
[    7.844878] x23: ffff00008015c800 x22: 0000000000000002 x21: 0000000000010000
[    7.852229] x20: 0000000106dae000 x19: ffff000080112410 x18: 0000000000000001
[    7.859580] x17: ffff000080159400 x16: ffffa3fe607a9bd8 x15: ffff0000eac1b180
[    7.866753] x14: 000000000000000c x13: 0000000000000001 x12: 000000000000025a
[    7.874104] x11: 0000000000000000 x10: 7f73e96357f6a07f x9 : db1fc8072a7f5e3a
[    7.881365] x8 : ffff000086c9c588 x7 : ffffa3fe607a9bd8 x6 : ffff80008193bc28
[    7.888630] x5 : 000000000000ffff x4 : 0000000000000009 x3 : 000000000000003f
[    7.895892] x2 : 0000000000000040 x1 : ffff000086dbe000 x0 : ffff000086db0000
[    7.903155] Call trace:
[    7.905606]  dcache_inval_poc+0x40/0x58 (P)
[    7.909804]  iommu_dma_sync_single_for_cpu+0xb4/0xb8
[    7.914617]  __dma_sync_single_for_cpu+0x158/0x194
[    7.919428]  __this_module+0x5b020/0x5baf8 [spi_tegra210_quad]
[    7.925291]  irq_thread_fn+0x2c/0xc0
[    7.928966]  irq_thread+0x16c/0x318
[    7.932467]  kthread+0x12c/0x214

Fix this by removing all calls to the dma_sync_*() functions. This isn't
ideal because DMA is used only for relatively large (> 64 words or 256
bytes) and using uncached memory for this might be slow. Reworking this
to use cached memory for faster access and reintroducing the cache
maintenance calls is probably worth a follow-up patch.

Reported-by: Brad Griffis <bgriffis@nvidia.com>
Fixes: 017f1b0bae08 ("spi: tegra210-quad: Add support for internal DMA")
Signed-off-by: Thierry Reding <treding@nvidia.com>
Link: https://patch.msgid.link/20250613123037.2082788-1-thierry.reding@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-tegra210-quad.c | 14 --------------
 1 file changed, 14 deletions(-)

diff --git a/drivers/spi/spi-tegra210-quad.c b/drivers/spi/spi-tegra210-quad.c
index 3581757a269b..3be7499db21e 100644
--- a/drivers/spi/spi-tegra210-quad.c
+++ b/drivers/spi/spi-tegra210-quad.c
@@ -407,9 +407,6 @@ tegra_qspi_read_rx_fifo_to_client_rxbuf(struct tegra_qspi *tqspi, struct spi_tra
 static void
 tegra_qspi_copy_client_txbuf_to_qspi_txbuf(struct tegra_qspi *tqspi, struct spi_transfer *t)
 {
-	dma_sync_single_for_cpu(tqspi->dev, tqspi->tx_dma_phys,
-				tqspi->dma_buf_size, DMA_TO_DEVICE);
-
 	/*
 	 * In packed mode, each word in FIFO may contain multiple packets
 	 * based on bits per word. So all bytes in each FIFO word are valid.
@@ -442,17 +439,11 @@ tegra_qspi_copy_client_txbuf_to_qspi_txbuf(struct tegra_qspi *tqspi, struct spi_
 
 		tqspi->cur_tx_pos += write_bytes;
 	}
-
-	dma_sync_single_for_device(tqspi->dev, tqspi->tx_dma_phys,
-				   tqspi->dma_buf_size, DMA_TO_DEVICE);
 }
 
 static void
 tegra_qspi_copy_qspi_rxbuf_to_client_rxbuf(struct tegra_qspi *tqspi, struct spi_transfer *t)
 {
-	dma_sync_single_for_cpu(tqspi->dev, tqspi->rx_dma_phys,
-				tqspi->dma_buf_size, DMA_FROM_DEVICE);
-
 	if (tqspi->is_packed) {
 		tqspi->cur_rx_pos += tqspi->curr_dma_words * tqspi->bytes_per_word;
 	} else {
@@ -478,9 +469,6 @@ tegra_qspi_copy_qspi_rxbuf_to_client_rxbuf(struct tegra_qspi *tqspi, struct spi_
 
 		tqspi->cur_rx_pos += read_bytes;
 	}
-
-	dma_sync_single_for_device(tqspi->dev, tqspi->rx_dma_phys,
-				   tqspi->dma_buf_size, DMA_FROM_DEVICE);
 }
 
 static void tegra_qspi_dma_complete(void *args)
@@ -701,8 +689,6 @@ static int tegra_qspi_start_dma_based_transfer(struct tegra_qspi *tqspi, struct
 				return ret;
 			}
 
-			dma_sync_single_for_device(tqspi->dev, tqspi->rx_dma_phys,
-						   tqspi->dma_buf_size, DMA_FROM_DEVICE);
 			ret = tegra_qspi_start_rx_dma(tqspi, t, len);
 			if (ret < 0) {
 				dev_err(tqspi->dev, "failed to start RX DMA: %d\n", ret);

From ab107276607af90b13a5994997e19b7b9731e251 Mon Sep 17 00:00:00 2001
From: Madhavan Srinivasan <maddy@linux.ibm.com>
Date: Sat, 17 May 2025 19:52:37 +0530
Subject: [PATCH 0357/1334] powerpc: Fix struct termio related ioctl macros

Since termio interface is now obsolete, include/uapi/asm/ioctls.h
has some constant macros referring to "struct termio", this caused
build failure at userspace.

In file included from /usr/include/asm/ioctl.h:12,
                 from /usr/include/asm/ioctls.h:5,
                 from tst-ioctls.c:3:
tst-ioctls.c: In function 'get_TCGETA':
tst-ioctls.c:12:10: error: invalid application of 'sizeof' to incomplete type 'struct termio'
   12 |   return TCGETA;
      |          ^~~~~~

Even though termios.h provides "struct termio", trying to juggle definitions around to
make it compile could introduce regressions. So better to open code it.

Reported-by: Tulio Magno <tuliom@ascii.art.br>
Suggested-by: Nicholas Piggin <npiggin@gmail.com>
Tested-by: Justin M. Forbes <jforbes@fedoraproject.org>
Reviewed-by: Michael Ellerman <mpe@ellerman.id.au>
Closes: https://lore.kernel.org/linuxppc-dev/8734dji5wl.fsf@ascii.art.br/
Signed-off-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Link: https://patch.msgid.link/20250517142237.156665-1-maddy@linux.ibm.com
---
 arch/powerpc/include/uapi/asm/ioctls.h | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/arch/powerpc/include/uapi/asm/ioctls.h b/arch/powerpc/include/uapi/asm/ioctls.h
index 2c145da3b774..b5211e413829 100644
--- a/arch/powerpc/include/uapi/asm/ioctls.h
+++ b/arch/powerpc/include/uapi/asm/ioctls.h
@@ -23,10 +23,10 @@
 #define TCSETSW		_IOW('t', 21, struct termios)
 #define TCSETSF		_IOW('t', 22, struct termios)
 
-#define TCGETA		_IOR('t', 23, struct termio)
-#define TCSETA		_IOW('t', 24, struct termio)
-#define TCSETAW		_IOW('t', 25, struct termio)
-#define TCSETAF		_IOW('t', 28, struct termio)
+#define TCGETA		0x40147417 /* _IOR('t', 23, struct termio) */
+#define TCSETA		0x80147418 /* _IOW('t', 24, struct termio) */
+#define TCSETAW		0x80147419 /* _IOW('t', 25, struct termio) */
+#define TCSETAF		0x8014741c /* _IOW('t', 28, struct termio) */
 
 #define TCSBRK		_IO('t', 29)
 #define TCXONC		_IO('t', 30)

From 26ec15e4b0c1d7b25214d9c0be1d50492e2f006c Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Fri, 13 Jun 2025 11:01:49 -0600
Subject: [PATCH 0358/1334] io_uring/kbuf: don't truncate end buffer for
 multiple buffer peeks

If peeking a bunch of buffers, normally io_ring_buffers_peek() will
truncate the end buffer. This isn't optimal as presumably more data will
be arriving later, and hence it's better to stop with the last full
buffer rather than truncate the end buffer.

Cc: stable@vger.kernel.org
Fixes: 35c8711c8fc4 ("io_uring/kbuf: add helpers for getting/peeking multiple buffers")
Reported-by: Christian Mazakas <christian.mazakas@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/kbuf.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/io_uring/kbuf.c b/io_uring/kbuf.c
index 2ea65f3cef72..ce95e3af44a9 100644
--- a/io_uring/kbuf.c
+++ b/io_uring/kbuf.c
@@ -270,8 +270,11 @@ static int io_ring_buffers_peek(struct io_kiocb *req, struct buf_sel_arg *arg,
 		/* truncate end piece, if needed, for non partial buffers */
 		if (len > arg->max_len) {
 			len = arg->max_len;
-			if (!(bl->flags & IOBL_INC))
+			if (!(bl->flags & IOBL_INC)) {
+				if (iov != arg->iovs)
+					break;
 				buf->len = len;
+			}
 		}
 
 		iov->iov_base = u64_to_user_ptr(buf->addr);

From 13b86ea92ebf0fa587fbadfb8a60ca2e9993203f Mon Sep 17 00:00:00 2001
From: Raven Black <ravenblack@gmail.com>
Date: Fri, 13 Jun 2025 07:51:25 -0400
Subject: [PATCH 0359/1334] ASoC: amd: yc: update quirk data for HP Victus

Make the internal microphone work on HP Victus laptops.

Signed-off-by: Raven Black <ravenblack@gmail.com>
Link: https://patch.msgid.link/20250613-support-hp-victus-microphone-v1-1-bebc4c3a2041@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/amd/yc/acp6x-mach.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/sound/soc/amd/yc/acp6x-mach.c b/sound/soc/amd/yc/acp6x-mach.c
index c9387d6fbf18..98022e5fd428 100644
--- a/sound/soc/amd/yc/acp6x-mach.c
+++ b/sound/soc/amd/yc/acp6x-mach.c
@@ -521,6 +521,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "OMEN by HP Gaming Laptop 16z-n000"),
 		}
 	},
+	{
+		.driver_data = &acp6x_card,
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "HP"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Victus by HP Gaming Laptop 15-fb2xxx"),
+		}
+	},
 	{
 		.driver_data = &acp6x_card,
 		.matches = {

From f90fff1e152dedf52b932240ebbd670d83330eca Mon Sep 17 00:00:00 2001
From: Oleg Nesterov <oleg@redhat.com>
Date: Fri, 13 Jun 2025 19:26:50 +0200
Subject: [PATCH 0360/1334] posix-cpu-timers: fix race between
 handle_posix_cpu_timers() and posix_cpu_timer_del()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

If an exiting non-autoreaping task has already passed exit_notify() and
calls handle_posix_cpu_timers() from IRQ, it can be reaped by its parent
or debugger right after unlock_task_sighand().

If a concurrent posix_cpu_timer_del() runs at that moment, it won't be
able to detect timer->it.cpu.firing != 0: cpu_timer_task_rcu() and/or
lock_task_sighand() will fail.

Add the tsk->exit_state check into run_posix_cpu_timers() to fix this.

This fix is not needed if CONFIG_POSIX_CPU_TIMERS_TASK_WORK=y, because
exit_task_work() is called before exit_notify(). But the check still
makes sense, task_work_add(&tsk->posix_cputimers_work.work) will fail
anyway in this case.

Cc: stable@vger.kernel.org
Reported-by: Benoît Sevens <bsevens@google.com>
Fixes: 0bdd2ed4138e ("sched: run_posix_cpu_timers: Don't check ->exit_state, use lock_task_sighand()")
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 kernel/time/posix-cpu-timers.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c
index 50e8d04ab661..2e5b89d7d866 100644
--- a/kernel/time/posix-cpu-timers.c
+++ b/kernel/time/posix-cpu-timers.c
@@ -1405,6 +1405,15 @@ void run_posix_cpu_timers(void)
 
 	lockdep_assert_irqs_disabled();
 
+	/*
+	 * Ensure that release_task(tsk) can't happen while
+	 * handle_posix_cpu_timers() is running. Otherwise, a concurrent
+	 * posix_cpu_timer_del() may fail to lock_task_sighand(tsk) and
+	 * miss timer->it.cpu.firing != 0.
+	 */
+	if (tsk->exit_state)
+		return;
+
 	/*
 	 * If the actual expiry is deferred to task work context and the
 	 * work is already scheduled there is no point to do anything here.

From 907a7a2e5bf40c6a359b2f6cc53d6fdca04009e0 Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Wed, 11 Jun 2025 18:31:16 -0500
Subject: [PATCH 0361/1334] PCI/PM: Set up runtime PM even for devices without
 PCI PM

4d4c10f763d7 ("PCI: Explicitly put devices into D0 when initializing")
intended to put PCI devices into D0, but in doing so unintentionally
changed runtime PM initialization not to occur on devices that don't
support PCI PM.  This caused a regression in vfio-pci due to an imbalance
with its use.

Adjust the logic in pci_pm_init() so that even if PCI PM isn't supported
runtime PM is still initialized.

Fixes: 4d4c10f763d7 ("PCI: Explicitly put devices into D0 when initializing")
Reported-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Closes: https://lore.kernel.org/linux-pci/20250424043232.1848107-1-superm1@kernel.org/T/#m7e8929d6421690dc8bd6dc639d86c2b4db27cbc4
Reported-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Closes: https://lore.kernel.org/linux-pci/20250424043232.1848107-1-superm1@kernel.org/T/#m40d277dcdb9be64a1609a82412d1aa906263e201
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Tested-by: Giovanni Cabiddu <giovanni.cabiddu@intel.com>
Tested-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Reviewed-by: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@linux.intel.com>
Acked-by: Rafael J. Wysocki <rafael@kernel.org>
Cc: Alex Williamson <alex.williamson@redhat.com>
Link: https://patch.msgid.link/20250611233117.61810-1-superm1@kernel.org
---
 drivers/pci/pci.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index e9448d55113b..9e42090fb108 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -3217,14 +3217,14 @@ void pci_pm_init(struct pci_dev *dev)
 	/* find PCI PM capability in list */
 	pm = pci_find_capability(dev, PCI_CAP_ID_PM);
 	if (!pm)
-		return;
+		goto poweron;
 	/* Check device's ability to generate PME# */
 	pci_read_config_word(dev, pm + PCI_PM_PMC, &pmc);
 
 	if ((pmc & PCI_PM_CAP_VER_MASK) > 3) {
 		pci_err(dev, "unsupported PM cap regs version (%u)\n",
 			pmc & PCI_PM_CAP_VER_MASK);
-		return;
+		goto poweron;
 	}
 
 	dev->pm_cap = pm;
@@ -3269,6 +3269,7 @@ void pci_pm_init(struct pci_dev *dev)
 	pci_read_config_word(dev, PCI_STATUS, &status);
 	if (status & PCI_STATUS_IMM_READY)
 		dev->imm_ready = 1;
+poweron:
 	pci_pm_power_up_and_verify_state(dev);
 	pm_runtime_forbid(&dev->dev);
 	pm_runtime_set_active(&dev->dev);

From 9ce6c9875f3e995be5fd720b65835291f8a609b1 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Fri, 13 Jun 2025 13:37:41 -0600
Subject: [PATCH 0362/1334] nvme: always punt polled uring_cmd end_io work to
 task_work

Currently NVMe uring_cmd completions will complete locally, if they are
polled. This is done because those completions are always invoked from
task context. And while that is true, there's no guarantee that it's
invoked under the right ring context, or even task. If someone does
NVMe passthrough via multiple threads and with a limited number of
poll queues, then ringA may find completions from ringB. For that case,
completing the request may not be sound.

Always just punt the passthrough completions via task_work, which will
redirect the completion, if needed.

Cc: stable@vger.kernel.org
Fixes: 585079b6e425 ("nvme: wire up async polling for io passthrough commands")
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/nvme/host/ioctl.c | 21 +++++++--------------
 1 file changed, 7 insertions(+), 14 deletions(-)

diff --git a/drivers/nvme/host/ioctl.c b/drivers/nvme/host/ioctl.c
index 0b50da2f1175..6b3ac8ae3f34 100644
--- a/drivers/nvme/host/ioctl.c
+++ b/drivers/nvme/host/ioctl.c
@@ -429,21 +429,14 @@ static enum rq_end_io_ret nvme_uring_cmd_end_io(struct request *req,
 	pdu->result = le64_to_cpu(nvme_req(req)->result.u64);
 
 	/*
-	 * For iopoll, complete it directly. Note that using the uring_cmd
-	 * helper for this is safe only because we check blk_rq_is_poll().
-	 * As that returns false if we're NOT on a polled queue, then it's
-	 * safe to use the polled completion helper.
-	 *
-	 * Otherwise, move the completion to task work.
+	 * IOPOLL could potentially complete this request directly, but
+	 * if multiple rings are polling on the same queue, then it's possible
+	 * for one ring to find completions for another ring. Punting the
+	 * completion via task_work will always direct it to the right
+	 * location, rather than potentially complete requests for ringA
+	 * under iopoll invocations from ringB.
 	 */
-	if (blk_rq_is_poll(req)) {
-		if (pdu->bio)
-			blk_rq_unmap_user(pdu->bio);
-		io_uring_cmd_iopoll_done(ioucmd, pdu->result, pdu->status);
-	} else {
-		io_uring_cmd_do_in_task_lazy(ioucmd, nvme_uring_task_cb);
-	}
-
+	io_uring_cmd_do_in_task_lazy(ioucmd, nvme_uring_task_cb);
 	return RQ_END_IO_FREE;
 }
 

From b62e0efd8a8571460d05922862a451855ebdf3c6 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Fri, 13 Jun 2025 15:24:53 -0600
Subject: [PATCH 0363/1334] io_uring: run local task_work from ring exit IOPOLL
 reaping

In preparation for needing to shift NVMe passthrough to always use
task_work for polled IO completions, ensure that those are suitably
run at exit time. See commit:

9ce6c9875f3e ("nvme: always punt polled uring_cmd end_io work to task_work")

for details on why that is necessary.

Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/io_uring.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index 4e32f808d07d..5111ec040c53 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -1523,6 +1523,9 @@ static __cold void io_iopoll_try_reap_events(struct io_ring_ctx *ctx)
 		}
 	}
 	mutex_unlock(&ctx->uring_lock);
+
+	if (ctx->flags & IORING_SETUP_DEFER_TASKRUN)
+		io_move_task_work_from_local(ctx);
 }
 
 static int io_iopoll_check(struct io_ring_ctx *ctx, unsigned int min_events)

From 1b56e765bf8990f1f60e124926c11fc4ac63d752 Mon Sep 17 00:00:00 2001
From: Danilo Krummrich <dakr@kernel.org>
Date: Thu, 12 Jun 2025 14:17:13 +0200
Subject: [PATCH 0364/1334] rust: completion: implement initial abstraction

Implement a minimal abstraction for the completion synchronization
primitive.

This initial abstraction only adds complete_all() and
wait_for_completion(), since that is what is required for the subsequent
Devres patch.

Cc: Ingo Molnar <mingo@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Juri Lelli <juri.lelli@redhat.com>
Cc: Vincent Guittot <vincent.guittot@linaro.org>
Cc: Dietmar Eggemann <dietmar.eggemann@arm.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Ben Segall <bsegall@google.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Valentin Schneider <vschneid@redhat.com>
Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Reviewed-by: Boqun Feng <boqun.feng@gmail.com>
Reviewed-by: Benno Lossin <lossin@kernel.org>
Acked-by: Miguel Ojeda <ojeda@kernel.org>
Link: https://lore.kernel.org/r/20250612121817.1621-2-dakr@kernel.org
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
---
 rust/bindings/bindings_helper.h |   1 +
 rust/helpers/completion.c       |   8 +++
 rust/helpers/helpers.c          |   1 +
 rust/kernel/sync.rs             |   2 +
 rust/kernel/sync/completion.rs  | 112 ++++++++++++++++++++++++++++++++
 5 files changed, 124 insertions(+)
 create mode 100644 rust/helpers/completion.c
 create mode 100644 rust/kernel/sync/completion.rs

diff --git a/rust/bindings/bindings_helper.h b/rust/bindings/bindings_helper.h
index bc494745f67b..8cbb660e2ec2 100644
--- a/rust/bindings/bindings_helper.h
+++ b/rust/bindings/bindings_helper.h
@@ -39,6 +39,7 @@
 #include <linux/blk_types.h>
 #include <linux/blkdev.h>
 #include <linux/clk.h>
+#include <linux/completion.h>
 #include <linux/configfs.h>
 #include <linux/cpu.h>
 #include <linux/cpufreq.h>
diff --git a/rust/helpers/completion.c b/rust/helpers/completion.c
new file mode 100644
index 000000000000..b2443262a2ae
--- /dev/null
+++ b/rust/helpers/completion.c
@@ -0,0 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/completion.h>
+
+void rust_helper_init_completion(struct completion *x)
+{
+	init_completion(x);
+}
diff --git a/rust/helpers/helpers.c b/rust/helpers/helpers.c
index 0f1b5d115985..6451cfd94a8d 100644
--- a/rust/helpers/helpers.c
+++ b/rust/helpers/helpers.c
@@ -13,6 +13,7 @@
 #include "build_assert.c"
 #include "build_bug.c"
 #include "clk.c"
+#include "completion.c"
 #include "cpufreq.c"
 #include "cpumask.c"
 #include "cred.c"
diff --git a/rust/kernel/sync.rs b/rust/kernel/sync.rs
index 36a719015583..c23a12639924 100644
--- a/rust/kernel/sync.rs
+++ b/rust/kernel/sync.rs
@@ -10,6 +10,7 @@ use crate::types::Opaque;
 use pin_init;
 
 mod arc;
+pub mod completion;
 mod condvar;
 pub mod lock;
 mod locked_by;
@@ -17,6 +18,7 @@ pub mod poll;
 pub mod rcu;
 
 pub use arc::{Arc, ArcBorrow, UniqueArc};
+pub use completion::Completion;
 pub use condvar::{new_condvar, CondVar, CondVarTimeoutResult};
 pub use lock::global::{global_lock, GlobalGuard, GlobalLock, GlobalLockBackend, GlobalLockedBy};
 pub use lock::mutex::{new_mutex, Mutex, MutexGuard};
diff --git a/rust/kernel/sync/completion.rs b/rust/kernel/sync/completion.rs
new file mode 100644
index 000000000000..c50012a940a3
--- /dev/null
+++ b/rust/kernel/sync/completion.rs
@@ -0,0 +1,112 @@
+// SPDX-License-Identifier: GPL-2.0
+
+//! Completion support.
+//!
+//! Reference: <https://docs.kernel.org/scheduler/completion.html>
+//!
+//! C header: [`include/linux/completion.h`](srctree/include/linux/completion.h)
+
+use crate::{bindings, prelude::*, types::Opaque};
+
+/// Synchronization primitive to signal when a certain task has been completed.
+///
+/// The [`Completion`] synchronization primitive signals when a certain task has been completed by
+/// waking up other tasks that have been queued up to wait for the [`Completion`] to be completed.
+///
+/// # Examples
+///
+/// ```
+/// use kernel::sync::{Arc, Completion};
+/// use kernel::workqueue::{self, impl_has_work, new_work, Work, WorkItem};
+///
+/// #[pin_data]
+/// struct MyTask {
+///     #[pin]
+///     work: Work<MyTask>,
+///     #[pin]
+///     done: Completion,
+/// }
+///
+/// impl_has_work! {
+///     impl HasWork<Self> for MyTask { self.work }
+/// }
+///
+/// impl MyTask {
+///     fn new() -> Result<Arc<Self>> {
+///         let this = Arc::pin_init(pin_init!(MyTask {
+///             work <- new_work!("MyTask::work"),
+///             done <- Completion::new(),
+///         }), GFP_KERNEL)?;
+///
+///         let _ = workqueue::system().enqueue(this.clone());
+///
+///         Ok(this)
+///     }
+///
+///     fn wait_for_completion(&self) {
+///         self.done.wait_for_completion();
+///
+///         pr_info!("Completion: task complete\n");
+///     }
+/// }
+///
+/// impl WorkItem for MyTask {
+///     type Pointer = Arc<MyTask>;
+///
+///     fn run(this: Arc<MyTask>) {
+///         // process this task
+///         this.done.complete_all();
+///     }
+/// }
+///
+/// let task = MyTask::new()?;
+/// task.wait_for_completion();
+/// # Ok::<(), Error>(())
+/// ```
+#[pin_data]
+pub struct Completion {
+    #[pin]
+    inner: Opaque<bindings::completion>,
+}
+
+// SAFETY: `Completion` is safe to be send to any task.
+unsafe impl Send for Completion {}
+
+// SAFETY: `Completion` is safe to be accessed concurrently.
+unsafe impl Sync for Completion {}
+
+impl Completion {
+    /// Create an initializer for a new [`Completion`].
+    pub fn new() -> impl PinInit<Self> {
+        pin_init!(Self {
+            inner <- Opaque::ffi_init(|slot: *mut bindings::completion| {
+                // SAFETY: `slot` is a valid pointer to an uninitialized `struct completion`.
+                unsafe { bindings::init_completion(slot) };
+            }),
+        })
+    }
+
+    fn as_raw(&self) -> *mut bindings::completion {
+        self.inner.get()
+    }
+
+    /// Signal all tasks waiting on this completion.
+    ///
+    /// This method wakes up all tasks waiting on this completion; after this operation the
+    /// completion is permanently done, i.e. signals all current and future waiters.
+    pub fn complete_all(&self) {
+        // SAFETY: `self.as_raw()` is a pointer to a valid `struct completion`.
+        unsafe { bindings::complete_all(self.as_raw()) };
+    }
+
+    /// Wait for completion of a task.
+    ///
+    /// This method waits for the completion of a task; it is not interruptible and there is no
+    /// timeout.
+    ///
+    /// See also [`Completion::complete_all`].
+    pub fn wait_for_completion(&self) {
+        // SAFETY: `self.as_raw()` is a pointer to a valid `struct completion`.
+        unsafe { bindings::wait_for_completion(self.as_raw()) };
+    }
+}

From 4b76fafb20dd4a2becb94949d78e86bc88006509 Mon Sep 17 00:00:00 2001
From: Danilo Krummrich <dakr@kernel.org>
Date: Thu, 12 Jun 2025 14:17:14 +0200
Subject: [PATCH 0365/1334] rust: revocable: indicate whether `data` has been
 revoked already

Return a boolean from Revocable::revoke() and Revocable::revoke_nosync()
to indicate whether the data has been revoked already.

Return true if the data hasn't been revoked yet (i.e. this call revoked
the data), false otherwise.

This is required by Devres in order to synchronize the completion of the
revoke process.

Reviewed-by: Benno Lossin <lossin@kernel.org>
Acked-by: Miguel Ojeda <ojeda@kernel.org>
Link: https://lore.kernel.org/r/20250612121817.1621-3-dakr@kernel.org
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
---
 rust/kernel/revocable.rs | 18 ++++++++++++++----
 1 file changed, 14 insertions(+), 4 deletions(-)

diff --git a/rust/kernel/revocable.rs b/rust/kernel/revocable.rs
index db4aa46bb121..06a3cdfce344 100644
--- a/rust/kernel/revocable.rs
+++ b/rust/kernel/revocable.rs
@@ -154,8 +154,10 @@ impl<T> Revocable<T> {
     /// # Safety
     ///
     /// Callers must ensure that there are no more concurrent users of the revocable object.
-    unsafe fn revoke_internal<const SYNC: bool>(&self) {
-        if self.is_available.swap(false, Ordering::Relaxed) {
+    unsafe fn revoke_internal<const SYNC: bool>(&self) -> bool {
+        let revoke = self.is_available.swap(false, Ordering::Relaxed);
+
+        if revoke {
             if SYNC {
                 // SAFETY: Just an FFI call, there are no further requirements.
                 unsafe { bindings::synchronize_rcu() };
@@ -165,6 +167,8 @@ impl<T> Revocable<T> {
             // `compare_exchange` above that takes `is_available` from `true` to `false`.
             unsafe { drop_in_place(self.data.get()) };
         }
+
+        revoke
     }
 
     /// Revokes access to and drops the wrapped object.
@@ -172,10 +176,13 @@ impl<T> Revocable<T> {
     /// Access to the object is revoked immediately to new callers of [`Revocable::try_access`],
     /// expecting that there are no concurrent users of the object.
     ///
+    /// Returns `true` if `&self` has been revoked with this call, `false` if it was revoked
+    /// already.
+    ///
     /// # Safety
     ///
     /// Callers must ensure that there are no more concurrent users of the revocable object.
-    pub unsafe fn revoke_nosync(&self) {
+    pub unsafe fn revoke_nosync(&self) -> bool {
         // SAFETY: By the safety requirement of this function, the caller ensures that nobody is
         // accessing the data anymore and hence we don't have to wait for the grace period to
         // finish.
@@ -189,7 +196,10 @@ impl<T> Revocable<T> {
     /// If there are concurrent users of the object (i.e., ones that called
     /// [`Revocable::try_access`] beforehand and still haven't dropped the returned guard), this
     /// function waits for the concurrent access to complete before dropping the wrapped object.
-    pub fn revoke(&self) {
+    ///
+    /// Returns `true` if `&self` has been revoked with this call, `false` if it was revoked
+    /// already.
+    pub fn revoke(&self) -> bool {
         // SAFETY: By passing `true` we ask `revoke_internal` to wait for the grace period to
         // finish.
         unsafe { self.revoke_internal::<true>() }

From f744201c6159fc7323c40936fd079525f7063598 Mon Sep 17 00:00:00 2001
From: Danilo Krummrich <dakr@kernel.org>
Date: Thu, 12 Jun 2025 14:17:15 +0200
Subject: [PATCH 0366/1334] rust: devres: fix race in Devres::drop()

In Devres::drop() we first remove the devres action and then drop the
wrapped device resource.

The design goal is to give the owner of a Devres object control over when
the device resource is dropped, but limit the overall scope to the
corresponding device being bound to a driver.

However, there's a race that was introduced with commit 8ff656643d30
("rust: devres: remove action in `Devres::drop`"), but also has been
(partially) present from the initial version on.

In Devres::drop(), the devres action is removed successfully and
subsequently the destructor of the wrapped device resource runs.
However, there is no guarantee that the destructor of the wrapped device
resource completes before the driver core is done unbinding the
corresponding device.

If in Devres::drop(), the devres action can't be removed, it means that
the devres callback has been executed already, or is still running
concurrently. In case of the latter, either Devres::drop() wins revoking
the Revocable or the devres callback wins revoking the Revocable. If
Devres::drop() wins, we (again) have no guarantee that the destructor of
the wrapped device resource completes before the driver core is done
unbinding the corresponding device.

CPU0					CPU1
------------------------------------------------------------------------
Devres::drop() {			Devres::devres_callback() {
   self.data.revoke() {			   this.data.revoke() {
      is_available.swap() == true
					      is_available.swap == false
					   }
					}

					// [...]
					// device fully unbound
      drop_in_place() {
         // release device resource
      }
   }
}

Depending on the specific device resource, this can potentially lead to
user-after-free bugs.

In order to fix this, implement the following logic.

In the devres callback, we're always good when we get to revoke the
device resource ourselves, i.e. Revocable::revoke() returns true.

If Revocable::revoke() returns false, it means that Devres::drop(),
concurrently, already drops the device resource and we have to wait for
Devres::drop() to signal that it finished dropping the device resource.

Note that if we hit the case where we need to wait for the completion of
Devres::drop() in the devres callback, it means that we're actually
racing with a concurrent Devres::drop() call, which already started
revoking the device resource for us. This is rather unlikely and means
that the concurrent Devres::drop() already started doing our work and we
just need to wait for it to complete it for us. Hence, there should not
be any additional overhead from that.

(Actually, for now it's even better if Devres::drop() does the work for
us, since it can bypass the synchronize_rcu() call implied by
Revocable::revoke(), but this goes away anyways once I get to implement
the split devres callback approach, which allows us to first flip the
atomics of all registered Devres objects of a certain device, execute a
single synchronize_rcu() and then drop all revocable objects.)

In Devres::drop() we try to revoke the device resource. If that is *not*
successful, it means that the devres callback already did and we're good.

Otherwise, we try to remove the devres action, which, if successful,
means that we're good, since the device resource has just been revoked
by us *before* we removed the devres action successfully.

If the devres action could not be removed, it means that the devres
callback must be running concurrently, hence we signal that the device
resource has been revoked by us, using the completion.

This makes it safe to drop a Devres object from any task and at any point
of time, which is one of the design goals.

Fixes: 76c01ded724b ("rust: add devres abstraction")
Reported-by: Alice Ryhl <aliceryhl@google.com>
Closes: https://lore.kernel.org/lkml/aD64YNuqbPPZHAa5@google.com/
Reviewed-by: Benno Lossin <lossin@kernel.org>
Link: https://lore.kernel.org/r/20250612121817.1621-4-dakr@kernel.org
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
---
 rust/kernel/devres.rs | 37 +++++++++++++++++++++++++++++--------
 1 file changed, 29 insertions(+), 8 deletions(-)

diff --git a/rust/kernel/devres.rs b/rust/kernel/devres.rs
index 0f79a2ec9474..2f74bce5ed9d 100644
--- a/rust/kernel/devres.rs
+++ b/rust/kernel/devres.rs
@@ -13,7 +13,7 @@ use crate::{
     ffi::c_void,
     prelude::*,
     revocable::Revocable,
-    sync::Arc,
+    sync::{Arc, Completion},
     types::ARef,
 };
 
@@ -25,13 +25,17 @@ struct DevresInner<T> {
     callback: unsafe extern "C" fn(*mut c_void),
     #[pin]
     data: Revocable<T>,
+    #[pin]
+    revoke: Completion,
 }
 
 /// This abstraction is meant to be used by subsystems to containerize [`Device`] bound resources to
 /// manage their lifetime.
 ///
 /// [`Device`] bound resources should be freed when either the resource goes out of scope or the
-/// [`Device`] is unbound respectively, depending on what happens first.
+/// [`Device`] is unbound respectively, depending on what happens first. In any case, it is always
+/// guaranteed that revoking the device resource is completed before the corresponding [`Device`]
+/// is unbound.
 ///
 /// To achieve that [`Devres`] registers a devres callback on creation, which is called once the
 /// [`Device`] is unbound, revoking access to the encapsulated resource (see also [`Revocable`]).
@@ -102,6 +106,7 @@ impl<T> DevresInner<T> {
                 dev: dev.into(),
                 callback: Self::devres_callback,
                 data <- Revocable::new(data),
+                revoke <- Completion::new(),
             }),
             flags,
         )?;
@@ -130,26 +135,28 @@ impl<T> DevresInner<T> {
         self as _
     }
 
-    fn remove_action(this: &Arc<Self>) {
+    fn remove_action(this: &Arc<Self>) -> bool {
         // SAFETY:
         // - `self.inner.dev` is a valid `Device`,
         // - the `action` and `data` pointers are the exact same ones as given to devm_add_action()
         //   previously,
         // - `self` is always valid, even if the action has been released already.
-        let ret = unsafe {
+        let success = unsafe {
             bindings::devm_remove_action_nowarn(
                 this.dev.as_raw(),
                 Some(this.callback),
                 this.as_ptr() as _,
             )
-        };
+        } == 0;
 
-        if ret == 0 {
+        if success {
             // SAFETY: We leaked an `Arc` reference to devm_add_action() in `DevresInner::new`; if
             // devm_remove_action_nowarn() was successful we can (and have to) claim back ownership
             // of this reference.
             let _ = unsafe { Arc::from_raw(this.as_ptr()) };
         }
+
+        success
     }
 
     #[allow(clippy::missing_safety_doc)]
@@ -161,7 +168,12 @@ impl<T> DevresInner<T> {
         //         `DevresInner::new`.
         let inner = unsafe { Arc::from_raw(ptr) };
 
-        inner.data.revoke();
+        if !inner.data.revoke() {
+            // If `revoke()` returns false, it means that `Devres::drop` already started revoking
+            // `inner.data` for us. Hence we have to wait until `Devres::drop()` signals that it
+            // completed revoking `inner.data`.
+            inner.revoke.wait_for_completion();
+        }
     }
 }
 
@@ -232,6 +244,15 @@ impl<T> Deref for Devres<T> {
 
 impl<T> Drop for Devres<T> {
     fn drop(&mut self) {
-        DevresInner::remove_action(&self.0);
+        // SAFETY: When `drop` runs, it is guaranteed that nobody is accessing the revocable data
+        // anymore, hence it is safe not to wait for the grace period to finish.
+        if unsafe { self.revoke_nosync() } {
+            // We revoked `self.0.data` before the devres action did, hence try to remove it.
+            if !DevresInner::remove_action(&self.0) {
+                // We could not remove the devres action, which means that it now runs concurrently,
+                // hence signal that `self.0.data` has been revoked successfully.
+                self.0.revoke.complete_all();
+            }
+        }
     }
 }

From 20c96ed278e362ae4e324ed7d8c69fb48c508d3c Mon Sep 17 00:00:00 2001
From: Danilo Krummrich <dakr@kernel.org>
Date: Wed, 11 Jun 2025 19:48:25 +0200
Subject: [PATCH 0367/1334] rust: devres: do not dereference to the internal
 Revocable

We can't expose direct access to the internal Revocable, since this
allows users to directly revoke the internal Revocable without Devres
having the chance to synchronize with the devres callback -- we have to
guarantee that the internal Revocable has been fully revoked before
the device is fully unbound.

Hence, remove the corresponding Deref implementation and, instead,
provide indirect accessors for the internal Revocable.

Note that we can still support Devres::revoke() by implementing the
required synchronization (which would be almost identical to the
synchronization in Devres::drop()).

Fixes: 76c01ded724b ("rust: add devres abstraction")
Reviewed-by: Benno Lossin <lossin@kernel.org>
Link: https://lore.kernel.org/r/20250611174827.380555-1-dakr@kernel.org
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
---
 rust/kernel/devres.rs | 27 ++++++++++++++++-----------
 1 file changed, 16 insertions(+), 11 deletions(-)

diff --git a/rust/kernel/devres.rs b/rust/kernel/devres.rs
index 2f74bce5ed9d..57502534d985 100644
--- a/rust/kernel/devres.rs
+++ b/rust/kernel/devres.rs
@@ -12,13 +12,11 @@ use crate::{
     error::{Error, Result},
     ffi::c_void,
     prelude::*,
-    revocable::Revocable,
-    sync::{Arc, Completion},
+    revocable::{Revocable, RevocableGuard},
+    sync::{rcu, Arc, Completion},
     types::ARef,
 };
 
-use core::ops::Deref;
-
 #[pin_data]
 struct DevresInner<T> {
     dev: ARef<Device>,
@@ -230,15 +228,22 @@ impl<T> Devres<T> {
         // SAFETY: `dev` being the same device as the device this `Devres` has been created for
         // proves that `self.0.data` hasn't been revoked and is guaranteed to not be revoked as
         // long as `dev` lives; `dev` lives at least as long as `self`.
-        Ok(unsafe { self.deref().access() })
+        Ok(unsafe { self.0.data.access() })
     }
-}
 
-impl<T> Deref for Devres<T> {
-    type Target = Revocable<T>;
+    /// [`Devres`] accessor for [`Revocable::try_access`].
+    pub fn try_access(&self) -> Option<RevocableGuard<'_, T>> {
+        self.0.data.try_access()
+    }
 
-    fn deref(&self) -> &Self::Target {
-        &self.0.data
+    /// [`Devres`] accessor for [`Revocable::try_access_with`].
+    pub fn try_access_with<R, F: FnOnce(&T) -> R>(&self, f: F) -> Option<R> {
+        self.0.data.try_access_with(f)
+    }
+
+    /// [`Devres`] accessor for [`Revocable::try_access_with_guard`].
+    pub fn try_access_with_guard<'a>(&'a self, guard: &'a rcu::Guard) -> Option<&'a T> {
+        self.0.data.try_access_with_guard(guard)
     }
 }
 
@@ -246,7 +251,7 @@ impl<T> Drop for Devres<T> {
     fn drop(&mut self) {
         // SAFETY: When `drop` runs, it is guaranteed that nobody is accessing the revocable data
         // anymore, hence it is safe not to wait for the grace period to finish.
-        if unsafe { self.revoke_nosync() } {
+        if unsafe { self.0.data.revoke_nosync() } {
             // We revoked `self.0.data` before the devres action did, hence try to remove it.
             if !DevresInner::remove_action(&self.0) {
                 // We could not remove the devres action, which means that it now runs concurrently,

From efa6bdf1bc75e26cafaa5f1d775e8bb7c5b0c431 Mon Sep 17 00:00:00 2001
From: Jonathan Lane <jon@borg.moe>
Date: Wed, 11 Jun 2025 12:31:25 -0700
Subject: [PATCH 0368/1334] ALSA: hda/realtek: enable headset mic on Latitude
 5420 Rugged

Like many Dell laptops, the 3.5mm port by default can not detect a
combined headphones+mic headset or even a pure microphone.  This
change enables the port's functionality.

Signed-off-by: Jonathan Lane <jon@borg.moe>
Cc: <stable@vger.kernel.org>
Link: https://patch.msgid.link/20250611193124.26141-2-jon@borg.moe
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/patch_realtek.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index bca725bb8281..02a424b7a992 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -10509,6 +10509,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1028, 0x0871, "Dell Precision 3630", ALC255_FIXUP_DELL_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1028, 0x0872, "Dell Precision 3630", ALC255_FIXUP_DELL_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1028, 0x0873, "Dell Precision 3930", ALC255_FIXUP_DUMMY_LINEOUT_VERB),
+	SND_PCI_QUIRK(0x1028, 0x0879, "Dell Latitude 5420 Rugged", ALC269_FIXUP_DELL4_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x08ad, "Dell WYSE AIO", ALC225_FIXUP_DELL_WYSE_AIO_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x08ae, "Dell WYSE NB", ALC225_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x0935, "Dell", ALC274_FIXUP_DELL_AIO_LINEOUT_VERB),

From 60599e4f8a041d1186afe4bcf12ba522afe4c5bc Mon Sep 17 00:00:00 2001
From: Simon Trimmer <simont@opensource.cirrus.com>
Date: Fri, 13 Jun 2025 14:52:51 +0000
Subject: [PATCH 0369/1334] ALSA: hda/realtek: Add quirk for Asus GA605K

The GA605K has similar audio hardware to the GA403U so apply the
same quirk.

Signed-off-by: Simon Trimmer <simont@opensource.cirrus.com>
Tested-by: Timofey Titovets <nefelim4ag@gmail.com>
Link: https://github.com/alsa-project/alsa-ucm-conf/issues/578
Link: https://patch.msgid.link/20250613145251.397500-1-simont@opensource.cirrus.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/patch_realtek.c | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)

diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 02a424b7a992..76cc908d4957 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -8030,6 +8030,8 @@ enum {
 	ALC294_FIXUP_ASUS_CS35L41_SPI_2,
 	ALC274_FIXUP_HP_AIO_BIND_DACS,
 	ALC287_FIXUP_PREDATOR_SPK_CS35L41_I2C_2,
+	ALC285_FIXUP_ASUS_GA605K_HEADSET_MIC,
+	ALC285_FIXUP_ASUS_GA605K_I2C_SPEAKER2_TO_DAC1,
 };
 
 /* A special fixup for Lenovo C940 and Yoga Duet 7;
@@ -10414,6 +10416,20 @@ static const struct hda_fixup alc269_fixups[] = {
 		.type = HDA_FIXUP_FUNC,
 		.v.func = alc274_fixup_hp_aio_bind_dacs,
 	},
+	[ALC285_FIXUP_ASUS_GA605K_HEADSET_MIC] = {
+		.type = HDA_FIXUP_PINS,
+		.v.pins = (const struct hda_pintbl[]) {
+			{ 0x19, 0x03a11050 },
+			{ 0x1b, 0x03a11c30 },
+			{ }
+		},
+		.chained = true,
+		.chain_id = ALC285_FIXUP_ASUS_GA605K_I2C_SPEAKER2_TO_DAC1
+	},
+	[ALC285_FIXUP_ASUS_GA605K_I2C_SPEAKER2_TO_DAC1] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc285_fixup_speaker2_to_dac1,
+	},
 };
 
 static const struct hda_quirk alc269_fixup_tbl[] = {
@@ -10937,6 +10953,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1043, 0x12e0, "ASUS X541SA", ALC256_FIXUP_ASUS_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1043, 0x12f0, "ASUS X541UV", ALC256_FIXUP_ASUS_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1043, 0x1313, "Asus K42JZ", ALC269VB_FIXUP_ASUS_MIC_NO_PRESENCE),
+	SND_PCI_QUIRK(0x1043, 0x1314, "ASUS GA605K", ALC285_FIXUP_ASUS_GA605K_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1043, 0x13b0, "ASUS Z550SA", ALC256_FIXUP_ASUS_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1043, 0x1427, "Asus Zenbook UX31E", ALC269VB_FIXUP_ASUS_ZENBOOK),
 	SND_PCI_QUIRK(0x1043, 0x1433, "ASUS GX650PY/PZ/PV/PU/PYV/PZV/PIV/PVV", ALC285_FIXUP_ASUS_I2C_HEADSET_MIC),

From d3deabe4c619875714b9a844b1a3d9752dbae1dd Mon Sep 17 00:00:00 2001
From: Rob Clark <robin.clark@oss.qualcomm.com>
Date: Fri, 13 Jun 2025 07:41:44 -0700
Subject: [PATCH 0370/1334] drm/msm: Fix inverted WARN_ON() logic

We want to WARN_ON() if info is NULL.

Suggested-by: Konrad Dybcio <konrad.dybcio@oss.qualcomm.com>
Fixes: 0838fc3e6718 ("drm/msm/adreno: Check for recognized GPU before bind")
Tested-by: Neil Armstrong <neil.armstrong@linaro.org>
Signed-off-by: Rob Clark <robin.clark@oss.qualcomm.com>
Reported-by: Alexey Klimov <alexey.klimov@linaro.org>
Reviewed-by: Konrad Dybcio <konrad.dybcio@oss.qualcomm.com>
Patchwork: https://patchwork.freedesktop.org/patch/658631/
---
 drivers/gpu/drm/msm/adreno/adreno_device.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/msm/adreno/adreno_device.c b/drivers/gpu/drm/msm/adreno/adreno_device.c
index 5e7307567239..16e7ac444efd 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_device.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_device.c
@@ -221,7 +221,7 @@ static int adreno_bind(struct device *dev, struct device *master, void *data)
 
 	info = adreno_info(config.chip_id);
 	/* We shouldn't have gotten this far if we don't recognize the GPU: */
-	if (!WARN_ON(info))
+	if (WARN_ON(!info))
 		return -ENXIO;
 
 	config.info = info;

From 1d27f11bf02b38c431e49a17dee5c10a2b4c2e28 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Sun, 15 Jun 2025 08:09:14 -0600
Subject: [PATCH 0371/1334] io_uring/rsrc: validate buffer count with offset
 for cloning

syzbot reports that it can trigger a WARN_ON() for kmalloc() attempt
that's too big:

WARNING: CPU: 0 PID: 6488 at mm/slub.c:5024 __kvmalloc_node_noprof+0x520/0x640 mm/slub.c:5024
Modules linked in:
CPU: 0 UID: 0 PID: 6488 Comm: syz-executor312 Not tainted 6.15.0-rc7-syzkaller-gd7fa1af5b33e #0 PREEMPT
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 05/07/2025
pstate: 20400005 (nzCv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--)
pc : __kvmalloc_node_noprof+0x520/0x640 mm/slub.c:5024
lr : __do_kmalloc_node mm/slub.c:-1 [inline]
lr : __kvmalloc_node_noprof+0x3b4/0x640 mm/slub.c:5012
sp : ffff80009cfd7a90
x29: ffff80009cfd7ac0 x28: ffff0000dd52a120 x27: 0000000000412dc0
x26: 0000000000000178 x25: ffff7000139faf70 x24: 0000000000000000
x23: ffff800082f4cea8 x22: 00000000ffffffff x21: 000000010cd004a8
x20: ffff0000d75816c0 x19: ffff0000dd52a000 x18: 00000000ffffffff
x17: ffff800092f39000 x16: ffff80008adbe9e4 x15: 0000000000000005
x14: 1ffff000139faf1c x13: 0000000000000000 x12: 0000000000000000
x11: ffff7000139faf21 x10: 0000000000000003 x9 : ffff80008f27b938
x8 : 0000000000000002 x7 : 0000000000000000 x6 : 0000000000000000
x5 : 00000000ffffffff x4 : 0000000000400dc0 x3 : 0000000200000000
x2 : 000000010cd004a8 x1 : ffff80008b3ebc40 x0 : 0000000000000001
Call trace:
 __kvmalloc_node_noprof+0x520/0x640 mm/slub.c:5024 (P)
 kvmalloc_array_node_noprof include/linux/slab.h:1065 [inline]
 io_rsrc_data_alloc io_uring/rsrc.c:206 [inline]
 io_clone_buffers io_uring/rsrc.c:1178 [inline]
 io_register_clone_buffers+0x484/0xa14 io_uring/rsrc.c:1287
 __io_uring_register io_uring/register.c:815 [inline]
 __do_sys_io_uring_register io_uring/register.c:926 [inline]
 __se_sys_io_uring_register io_uring/register.c:903 [inline]
 __arm64_sys_io_uring_register+0x42c/0xea8 io_uring/register.c:903
 __invoke_syscall arch/arm64/kernel/syscall.c:35 [inline]
 invoke_syscall+0x98/0x2b8 arch/arm64/kernel/syscall.c:49
 el0_svc_common+0x130/0x23c arch/arm64/kernel/syscall.c:132
 do_el0_svc+0x48/0x58 arch/arm64/kernel/syscall.c:151
 el0_svc+0x58/0x17c arch/arm64/kernel/entry-common.c:767
 el0t_64_sync_handler+0x78/0x108 arch/arm64/kernel/entry-common.c:786
 el0t_64_sync+0x198/0x19c arch/arm64/kernel/entry.S:600

which is due to offset + buffer_count being too large. The registration
code checks only the total count of buffers, but given that the indexing
is an array, it should also check offset + count. That can't exceed
IORING_MAX_REG_BUFFERS either, as there's no way to reach buffers beyond
that limit.

There's no issue with registrering a table this large, outside of the
fact that it's pointless to register buffers that cannot be reached, and
that it can trigger this kmalloc() warning for attempting an allocation
that is too large.

Cc: stable@vger.kernel.org
Fixes: b16e920a1909 ("io_uring/rsrc: allow cloning at an offset")
Reported-by: syzbot+cb4bf3cb653be0d25de8@syzkaller.appspotmail.com
Link: https://lore.kernel.org/io-uring/684e77bd.a00a0220.279073.0029.GAE@google.com/
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/rsrc.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/io_uring/rsrc.c b/io_uring/rsrc.c
index c592ceace97d..94a9db030e0e 100644
--- a/io_uring/rsrc.c
+++ b/io_uring/rsrc.c
@@ -1177,6 +1177,8 @@ static int io_clone_buffers(struct io_ring_ctx *ctx, struct io_ring_ctx *src_ctx
 		return -EINVAL;
 	if (check_add_overflow(arg->nr, arg->dst_off, &nbufs))
 		return -EOVERFLOW;
+	if (nbufs > IORING_MAX_REG_BUFFERS)
+		return -EINVAL;
 
 	ret = io_rsrc_data_alloc(&data, max(nbufs, ctx->buf_table.nr));
 	if (ret)

From a6a7946bd691940cfe7289ae6dfb1f077516df72 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <masahiroy@kernel.org>
Date: Fri, 13 Jun 2025 01:08:48 +0900
Subject: [PATCH 0372/1334] kbuild: move warnings about linux/export.h from W=1
 to W=2

This hides excessive warnings, as nobody builds with W=2.

Fixes: a934a57a42f6 ("scripts/misc-check: check missing #include <linux/export.h> when W=1")
Fixes: 7d95680d64ac ("scripts/misc-check: check unnecessary #include <linux/export.h> when W=1")
Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Nathan Chancellor <nathan@kernel.org>
Acked-by: Heiko Carstens <hca@linux.ibm.com>
---
 Makefile           |  3 ---
 scripts/misc-check | 15 ++++++++++++---
 2 files changed, 12 insertions(+), 6 deletions(-)

diff --git a/Makefile b/Makefile
index 35e6e5240c61..69c534982415 100644
--- a/Makefile
+++ b/Makefile
@@ -1832,12 +1832,9 @@ rustfmtcheck: rustfmt
 # Misc
 # ---------------------------------------------------------------------------
 
-# Run misc checks when ${KBUILD_EXTRA_WARN} contains 1
 PHONY += misc-check
-ifneq ($(findstring 1,$(KBUILD_EXTRA_WARN)),)
 misc-check:
 	$(Q)$(srctree)/scripts/misc-check
-endif
 
 all: misc-check
 
diff --git a/scripts/misc-check b/scripts/misc-check
index a74450e799d1..84f08da17b2c 100755
--- a/scripts/misc-check
+++ b/scripts/misc-check
@@ -62,6 +62,15 @@ check_unnecessary_include_linux_export_h () {
 	xargs -r printf "%s: warning: EXPORT_SYMBOL() is not used, but #include <linux/export.h> is present\n" >&2
 }
 
-check_tracked_ignored_files
-check_missing_include_linux_export_h
-check_unnecessary_include_linux_export_h
+case "${KBUILD_EXTRA_WARN}" in
+*1*)
+	check_tracked_ignored_files
+	;;
+esac
+
+case "${KBUILD_EXTRA_WARN}" in
+*2*)
+	check_missing_include_linux_export_h
+	check_unnecessary_include_linux_export_h
+	;;
+esac

From 2f6b47b295518c3ba16fabb1dddbe6a319899acb Mon Sep 17 00:00:00 2001
From: Sami Tolvanen <samitolvanen@google.com>
Date: Sat, 14 Jun 2025 00:55:33 +0000
Subject: [PATCH 0373/1334] gendwarfksyms: Fix structure type overrides

As we always iterate through the entire die_map when expanding
type strings, recursively processing referenced types in
type_expand_child() is not actually necessary. Furthermore,
the type_string kABI rule added in commit c9083467f7b9
("gendwarfksyms: Add a kABI rule to override type strings") can
fail to override type strings for structures due to a missing
kabi_get_type_string() check in this function.

Fix the issue by dropping the unnecessary recursion and moving
the override check to type_expand(). Note that symbol versions
are otherwise unchanged with this patch.

Fixes: c9083467f7b9 ("gendwarfksyms: Add a kABI rule to override type strings")
Reported-by: Giuliano Procida <gprocida@google.com>
Signed-off-by: Sami Tolvanen <samitolvanen@google.com>
Reviewed-by: Petr Pavlu <petr.pavlu@suse.com>
Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
---
 scripts/gendwarfksyms/gendwarfksyms.h | 14 +-----
 scripts/gendwarfksyms/types.c         | 65 ++++++++-------------------
 2 files changed, 21 insertions(+), 58 deletions(-)

diff --git a/scripts/gendwarfksyms/gendwarfksyms.h b/scripts/gendwarfksyms/gendwarfksyms.h
index 7dd03ffe0c5c..d9c06d2cb1df 100644
--- a/scripts/gendwarfksyms/gendwarfksyms.h
+++ b/scripts/gendwarfksyms/gendwarfksyms.h
@@ -216,24 +216,14 @@ int cache_get(struct cache *cache, unsigned long key);
 void cache_init(struct cache *cache);
 void cache_free(struct cache *cache);
 
-static inline void __cache_mark_expanded(struct cache *cache, uintptr_t addr)
-{
-	cache_set(cache, addr, 1);
-}
-
-static inline bool __cache_was_expanded(struct cache *cache, uintptr_t addr)
-{
-	return cache_get(cache, addr) == 1;
-}
-
 static inline void cache_mark_expanded(struct cache *cache, void *addr)
 {
-	__cache_mark_expanded(cache, (uintptr_t)addr);
+	cache_set(cache, (unsigned long)addr, 1);
 }
 
 static inline bool cache_was_expanded(struct cache *cache, void *addr)
 {
-	return __cache_was_expanded(cache, (uintptr_t)addr);
+	return cache_get(cache, (unsigned long)addr) == 1;
 }
 
 /*
diff --git a/scripts/gendwarfksyms/types.c b/scripts/gendwarfksyms/types.c
index 39ce1770e463..7bd459ea6c59 100644
--- a/scripts/gendwarfksyms/types.c
+++ b/scripts/gendwarfksyms/types.c
@@ -333,37 +333,11 @@ static void calculate_version(struct version *version,
 	cache_free(&expansion_cache);
 }
 
-static void __type_expand(struct die *cache, struct type_expansion *type,
-			  bool recursive);
-
-static void type_expand_child(struct die *cache, struct type_expansion *type,
-			      bool recursive)
-{
-	struct type_expansion child;
-	char *name;
-
-	name = get_type_name(cache);
-	if (!name) {
-		__type_expand(cache, type, recursive);
-		return;
-	}
-
-	if (recursive && !__cache_was_expanded(&expansion_cache, cache->addr)) {
-		__cache_mark_expanded(&expansion_cache, cache->addr);
-		type_expansion_init(&child);
-		__type_expand(cache, &child, true);
-		type_map_add(name, &child);
-		type_expansion_free(&child);
-	}
-
-	type_expansion_append(type, name, name);
-}
-
-static void __type_expand(struct die *cache, struct type_expansion *type,
-			  bool recursive)
+static void __type_expand(struct die *cache, struct type_expansion *type)
 {
 	struct die_fragment *df;
 	struct die *child;
+	char *name;
 
 	list_for_each_entry(df, &cache->fragments, list) {
 		switch (df->type) {
@@ -379,7 +353,12 @@ static void __type_expand(struct die *cache, struct type_expansion *type,
 				error("unknown child: %" PRIxPTR,
 				      df->data.addr);
 
-			type_expand_child(child, type, recursive);
+			name = get_type_name(child);
+			if (name)
+				type_expansion_append(type, name, name);
+			else
+				__type_expand(child, type);
+
 			break;
 		case FRAGMENT_LINEBREAK:
 			/*
@@ -397,12 +376,17 @@ static void __type_expand(struct die *cache, struct type_expansion *type,
 	}
 }
 
-static void type_expand(struct die *cache, struct type_expansion *type,
-			bool recursive)
+static void type_expand(const char *name, struct die *cache,
+			struct type_expansion *type)
 {
+	const char *override;
+
 	type_expansion_init(type);
-	__type_expand(cache, type, recursive);
-	cache_free(&expansion_cache);
+
+	if (stable && kabi_get_type_string(name, &override))
+		type_parse(name, override, type);
+	else
+		__type_expand(cache, type);
 }
 
 static void type_parse(const char *name, const char *str,
@@ -416,8 +400,6 @@ static void type_parse(const char *name, const char *str,
 	if (!*str)
 		error("empty type string override for '%s'", name);
 
-	type_expansion_init(type);
-
 	for (pos = 0; str[pos]; ++pos) {
 		bool empty;
 		char marker = ' ';
@@ -478,7 +460,6 @@ static void type_parse(const char *name, const char *str,
 static void expand_type(struct die *cache, void *arg)
 {
 	struct type_expansion type;
-	const char *override;
 	char *name;
 
 	if (cache->mapped)
@@ -504,11 +485,7 @@ static void expand_type(struct die *cache, void *arg)
 
 	debug("%s", name);
 
-	if (stable && kabi_get_type_string(name, &override))
-		type_parse(name, override, &type);
-	else
-		type_expand(cache, &type, true);
-
+	type_expand(name, cache, &type);
 	type_map_add(name, &type);
 	type_expansion_free(&type);
 	free(name);
@@ -518,7 +495,6 @@ static void expand_symbol(struct symbol *sym, void *arg)
 {
 	struct type_expansion type;
 	struct version version;
-	const char *override;
 	struct die *cache;
 
 	/*
@@ -532,10 +508,7 @@ static void expand_symbol(struct symbol *sym, void *arg)
 	if (__die_map_get(sym->die_addr, DIE_SYMBOL, &cache))
 		return; /* We'll warn about missing CRCs later. */
 
-	if (stable && kabi_get_type_string(sym->name, &override))
-		type_parse(sym->name, override, &type);
-	else
-		type_expand(cache, &type, false);
+	type_expand(sym->name, cache, &type);
 
 	/* If the symbol already has a version, don't calculate it again. */
 	if (sym->state != SYMBOL_PROCESSED) {

From 89465d923bda180299e69ee2800aab84ad0ba689 Mon Sep 17 00:00:00 2001
From: Penglei Jiang <superman.xpt@gmail.com>
Date: Sun, 15 Jun 2025 09:39:06 -0700
Subject: [PATCH 0374/1334] io_uring: fix task leak issue in io_wq_create()

Add missing put_task_struct() in the error path

Cc: stable@vger.kernel.org
Fixes: 0f8baa3c9802 ("io-wq: fully initialize wqe before calling cpuhp_state_add_instance_nocalls()")
Signed-off-by: Penglei Jiang <superman.xpt@gmail.com>
Link: https://lore.kernel.org/r/20250615163906.2367-1-superman.xpt@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/io-wq.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/io_uring/io-wq.c b/io_uring/io-wq.c
index cd1fcb115739..be91edf34f01 100644
--- a/io_uring/io-wq.c
+++ b/io_uring/io-wq.c
@@ -1259,8 +1259,10 @@ struct io_wq *io_wq_create(unsigned bounded, struct io_wq_data *data)
 	atomic_set(&wq->worker_refs, 1);
 	init_completion(&wq->worker_done);
 	ret = cpuhp_state_add_instance_nocalls(io_wq_online, &wq->cpuhp_node);
-	if (ret)
+	if (ret) {
+		put_task_struct(wq->task);
 		goto err;
+	}
 
 	return wq;
 err:

From e04c78d86a9699d136910cfc0bdcf01087e3267e Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Sun, 15 Jun 2025 13:49:41 -0700
Subject: [PATCH 0375/1334] Linux 6.16-rc2

---
 Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Makefile b/Makefile
index 69c534982415..ba0827a1fccd 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
 VERSION = 6
 PATCHLEVEL = 16
 SUBLEVEL = 0
-EXTRAVERSION = -rc1
+EXTRAVERSION = -rc2
 NAME = Baby Opossum Posse
 
 # *DOCUMENTATION*

From e202196b8aa249d78ab87eae56bbe0e71e3dc39c Mon Sep 17 00:00:00 2001
From: Kees Cook <kees@kernel.org>
Date: Thu, 29 May 2025 10:31:17 -0700
Subject: [PATCH 0376/1334] lib/crypto: Annotate crypto strings with nonstring

Annotate various keys, ivs, and other byte arrays with __nonstring so
that static initializers will not complain about truncating the trailing
NUL byte under GCC 15 with -Wunterminated-string-initialization enabled.
Silences many warnings like:

../lib/crypto/aesgcm.c:642:27: warning: initializer-string for array of 'unsigned char' truncates NUL terminator but destination lacks 'nonstring' attribute (13 chars into 12 available) [-Wunterminated-string-initialization]
  642 |                 .iv     = "\xca\xfe\xba\xbe\xfa\xce\xdb\xad"
      |                           ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

Signed-off-by: Kees Cook <kees@kernel.org>
Link: https://lore.kernel.org/r/20250529173113.work.760-kees@kernel.org
Signed-off-by: Eric Biggers <ebiggers@google.com>
---
 lib/crypto/aescfb.c |  8 ++++----
 lib/crypto/aesgcm.c | 46 ++++++++++++++++++++++-----------------------
 2 files changed, 27 insertions(+), 27 deletions(-)

diff --git a/lib/crypto/aescfb.c b/lib/crypto/aescfb.c
index 437613265e14..2f09ae92ffa0 100644
--- a/lib/crypto/aescfb.c
+++ b/lib/crypto/aescfb.c
@@ -106,11 +106,11 @@ MODULE_LICENSE("GPL");
  */
 
 static struct {
-	u8	ptext[64];
-	u8	ctext[64];
+	u8	ptext[64] __nonstring;
+	u8	ctext[64] __nonstring;
 
-	u8	key[AES_MAX_KEY_SIZE];
-	u8	iv[AES_BLOCK_SIZE];
+	u8	key[AES_MAX_KEY_SIZE] __nonstring;
+	u8	iv[AES_BLOCK_SIZE] __nonstring;
 
 	int	klen;
 	int	len;
diff --git a/lib/crypto/aesgcm.c b/lib/crypto/aesgcm.c
index 277824d6b4af..faa4dee9bb1b 100644
--- a/lib/crypto/aesgcm.c
+++ b/lib/crypto/aesgcm.c
@@ -205,19 +205,19 @@ MODULE_LICENSE("GPL");
  * Test code below. Vectors taken from crypto/testmgr.h
  */
 
-static const u8 __initconst ctext0[16] =
+static const u8 __initconst ctext0[16] __nonstring =
 	"\x58\xe2\xfc\xce\xfa\x7e\x30\x61"
 	"\x36\x7f\x1d\x57\xa4\xe7\x45\x5a";
 
 static const u8 __initconst ptext1[16];
 
-static const u8 __initconst ctext1[32] =
+static const u8 __initconst ctext1[32] __nonstring =
 	"\x03\x88\xda\xce\x60\xb6\xa3\x92"
 	"\xf3\x28\xc2\xb9\x71\xb2\xfe\x78"
 	"\xab\x6e\x47\xd4\x2c\xec\x13\xbd"
 	"\xf5\x3a\x67\xb2\x12\x57\xbd\xdf";
 
-static const u8 __initconst ptext2[64] =
+static const u8 __initconst ptext2[64] __nonstring =
 	"\xd9\x31\x32\x25\xf8\x84\x06\xe5"
 	"\xa5\x59\x09\xc5\xaf\xf5\x26\x9a"
 	"\x86\xa7\xa9\x53\x15\x34\xf7\xda"
@@ -227,7 +227,7 @@ static const u8 __initconst ptext2[64] =
 	"\xb1\x6a\xed\xf5\xaa\x0d\xe6\x57"
 	"\xba\x63\x7b\x39\x1a\xaf\xd2\x55";
 
-static const u8 __initconst ctext2[80] =
+static const u8 __initconst ctext2[80] __nonstring =
 	"\x42\x83\x1e\xc2\x21\x77\x74\x24"
 	"\x4b\x72\x21\xb7\x84\xd0\xd4\x9c"
 	"\xe3\xaa\x21\x2f\x2c\x02\xa4\xe0"
@@ -239,7 +239,7 @@ static const u8 __initconst ctext2[80] =
 	"\x4d\x5c\x2a\xf3\x27\xcd\x64\xa6"
 	"\x2c\xf3\x5a\xbd\x2b\xa6\xfa\xb4";
 
-static const u8 __initconst ptext3[60] =
+static const u8 __initconst ptext3[60] __nonstring =
 	"\xd9\x31\x32\x25\xf8\x84\x06\xe5"
 	"\xa5\x59\x09\xc5\xaf\xf5\x26\x9a"
 	"\x86\xa7\xa9\x53\x15\x34\xf7\xda"
@@ -249,7 +249,7 @@ static const u8 __initconst ptext3[60] =
 	"\xb1\x6a\xed\xf5\xaa\x0d\xe6\x57"
 	"\xba\x63\x7b\x39";
 
-static const u8 __initconst ctext3[76] =
+static const u8 __initconst ctext3[76] __nonstring =
 	"\x42\x83\x1e\xc2\x21\x77\x74\x24"
 	"\x4b\x72\x21\xb7\x84\xd0\xd4\x9c"
 	"\xe3\xaa\x21\x2f\x2c\x02\xa4\xe0"
@@ -261,17 +261,17 @@ static const u8 __initconst ctext3[76] =
 	"\x5b\xc9\x4f\xbc\x32\x21\xa5\xdb"
 	"\x94\xfa\xe9\x5a\xe7\x12\x1a\x47";
 
-static const u8 __initconst ctext4[16] =
+static const u8 __initconst ctext4[16] __nonstring =
 	"\xcd\x33\xb2\x8a\xc7\x73\xf7\x4b"
 	"\xa0\x0e\xd1\xf3\x12\x57\x24\x35";
 
-static const u8 __initconst ctext5[32] =
+static const u8 __initconst ctext5[32] __nonstring =
 	"\x98\xe7\x24\x7c\x07\xf0\xfe\x41"
 	"\x1c\x26\x7e\x43\x84\xb0\xf6\x00"
 	"\x2f\xf5\x8d\x80\x03\x39\x27\xab"
 	"\x8e\xf4\xd4\x58\x75\x14\xf0\xfb";
 
-static const u8 __initconst ptext6[64] =
+static const u8 __initconst ptext6[64] __nonstring =
 	"\xd9\x31\x32\x25\xf8\x84\x06\xe5"
 	"\xa5\x59\x09\xc5\xaf\xf5\x26\x9a"
 	"\x86\xa7\xa9\x53\x15\x34\xf7\xda"
@@ -281,7 +281,7 @@ static const u8 __initconst ptext6[64] =
 	"\xb1\x6a\xed\xf5\xaa\x0d\xe6\x57"
 	"\xba\x63\x7b\x39\x1a\xaf\xd2\x55";
 
-static const u8 __initconst ctext6[80] =
+static const u8 __initconst ctext6[80] __nonstring =
 	"\x39\x80\xca\x0b\x3c\x00\xe8\x41"
 	"\xeb\x06\xfa\xc4\x87\x2a\x27\x57"
 	"\x85\x9e\x1c\xea\xa6\xef\xd9\x84"
@@ -293,17 +293,17 @@ static const u8 __initconst ctext6[80] =
 	"\x99\x24\xa7\xc8\x58\x73\x36\xbf"
 	"\xb1\x18\x02\x4d\xb8\x67\x4a\x14";
 
-static const u8 __initconst ctext7[16] =
+static const u8 __initconst ctext7[16] __nonstring =
 	"\x53\x0f\x8a\xfb\xc7\x45\x36\xb9"
 	"\xa9\x63\xb4\xf1\xc4\xcb\x73\x8b";
 
-static const u8 __initconst ctext8[32] =
+static const u8 __initconst ctext8[32] __nonstring =
 	"\xce\xa7\x40\x3d\x4d\x60\x6b\x6e"
 	"\x07\x4e\xc5\xd3\xba\xf3\x9d\x18"
 	"\xd0\xd1\xc8\xa7\x99\x99\x6b\xf0"
 	"\x26\x5b\x98\xb5\xd4\x8a\xb9\x19";
 
-static const u8 __initconst ptext9[64] =
+static const u8 __initconst ptext9[64] __nonstring =
 	"\xd9\x31\x32\x25\xf8\x84\x06\xe5"
 	"\xa5\x59\x09\xc5\xaf\xf5\x26\x9a"
 	"\x86\xa7\xa9\x53\x15\x34\xf7\xda"
@@ -313,7 +313,7 @@ static const u8 __initconst ptext9[64] =
 	"\xb1\x6a\xed\xf5\xaa\x0d\xe6\x57"
 	"\xba\x63\x7b\x39\x1a\xaf\xd2\x55";
 
-static const u8 __initconst ctext9[80] =
+static const u8 __initconst ctext9[80] __nonstring =
 	"\x52\x2d\xc1\xf0\x99\x56\x7d\x07"
 	"\xf4\x7f\x37\xa3\x2a\x84\x42\x7d"
 	"\x64\x3a\x8c\xdc\xbf\xe5\xc0\xc9"
@@ -325,7 +325,7 @@ static const u8 __initconst ctext9[80] =
 	"\xb0\x94\xda\xc5\xd9\x34\x71\xbd"
 	"\xec\x1a\x50\x22\x70\xe3\xcc\x6c";
 
-static const u8 __initconst ptext10[60] =
+static const u8 __initconst ptext10[60] __nonstring =
 	"\xd9\x31\x32\x25\xf8\x84\x06\xe5"
 	"\xa5\x59\x09\xc5\xaf\xf5\x26\x9a"
 	"\x86\xa7\xa9\x53\x15\x34\xf7\xda"
@@ -335,7 +335,7 @@ static const u8 __initconst ptext10[60] =
 	"\xb1\x6a\xed\xf5\xaa\x0d\xe6\x57"
 	"\xba\x63\x7b\x39";
 
-static const u8 __initconst ctext10[76] =
+static const u8 __initconst ctext10[76] __nonstring =
 	"\x52\x2d\xc1\xf0\x99\x56\x7d\x07"
 	"\xf4\x7f\x37\xa3\x2a\x84\x42\x7d"
 	"\x64\x3a\x8c\xdc\xbf\xe5\xc0\xc9"
@@ -347,7 +347,7 @@ static const u8 __initconst ctext10[76] =
 	"\x76\xfc\x6e\xce\x0f\x4e\x17\x68"
 	"\xcd\xdf\x88\x53\xbb\x2d\x55\x1b";
 
-static const u8 __initconst ptext11[60] =
+static const u8 __initconst ptext11[60] __nonstring =
 	"\xd9\x31\x32\x25\xf8\x84\x06\xe5"
 	"\xa5\x59\x09\xc5\xaf\xf5\x26\x9a"
 	"\x86\xa7\xa9\x53\x15\x34\xf7\xda"
@@ -357,7 +357,7 @@ static const u8 __initconst ptext11[60] =
 	"\xb1\x6a\xed\xf5\xaa\x0d\xe6\x57"
 	"\xba\x63\x7b\x39";
 
-static const u8 __initconst ctext11[76] =
+static const u8 __initconst ctext11[76] __nonstring =
 	"\x39\x80\xca\x0b\x3c\x00\xe8\x41"
 	"\xeb\x06\xfa\xc4\x87\x2a\x27\x57"
 	"\x85\x9e\x1c\xea\xa6\xef\xd9\x84"
@@ -369,7 +369,7 @@ static const u8 __initconst ctext11[76] =
 	"\x25\x19\x49\x8e\x80\xf1\x47\x8f"
 	"\x37\xba\x55\xbd\x6d\x27\x61\x8c";
 
-static const u8 __initconst ptext12[719] =
+static const u8 __initconst ptext12[719] __nonstring =
 	"\x42\xc1\xcc\x08\x48\x6f\x41\x3f"
 	"\x2f\x11\x66\x8b\x2a\x16\xf0\xe0"
 	"\x58\x83\xf0\xc3\x70\x14\xc0\x5b"
@@ -461,7 +461,7 @@ static const u8 __initconst ptext12[719] =
 	"\x59\xfa\xfa\xaa\x44\x04\x01\xa7"
 	"\xa4\x78\xdb\x74\x3d\x8b\xb5";
 
-static const u8 __initconst ctext12[735] =
+static const u8 __initconst ctext12[735] __nonstring =
 	"\x84\x0b\xdb\xd5\xb7\xa8\xfe\x20"
 	"\xbb\xb1\x12\x7f\x41\xea\xb3\xc0"
 	"\xa2\xb4\x37\x19\x11\x58\xb6\x0b"
@@ -559,9 +559,9 @@ static struct {
 	const u8	*ptext;
 	const u8	*ctext;
 
-	u8		key[AES_MAX_KEY_SIZE];
-	u8		iv[GCM_AES_IV_SIZE];
-	u8		assoc[20];
+	u8		key[AES_MAX_KEY_SIZE] __nonstring;
+	u8		iv[GCM_AES_IV_SIZE] __nonstring;
+	u8		assoc[20] __nonstring;
 
 	int		klen;
 	int		clen;

From 2f13daee2a72bb962f5fd356c3a263a6f16da965 Mon Sep 17 00:00:00 2001
From: Nathan Chancellor <nathan@kernel.org>
Date: Mon, 9 Jun 2025 15:45:20 -0700
Subject: [PATCH 0377/1334] lib/crypto/curve25519-hacl64: Disable KASAN with
 clang-17 and older

After commit 6f110a5e4f99 ("Disable SLUB_TINY for build testing"), which
causes CONFIG_KASAN to be enabled in allmodconfig again, arm64
allmodconfig builds with clang-17 and older show an instance of
-Wframe-larger-than (which breaks the build with CONFIG_WERROR=y):

  lib/crypto/curve25519-hacl64.c:757:6: error: stack frame size (2336) exceeds limit (2048) in 'curve25519_generic' [-Werror,-Wframe-larger-than]
    757 | void curve25519_generic(u8 mypublic[CURVE25519_KEY_SIZE],
        |      ^

When KASAN is disabled, the stack usage is roughly quartered:

  lib/crypto/curve25519-hacl64.c:757:6: error: stack frame size (608) exceeds limit (128) in 'curve25519_generic' [-Werror,-Wframe-larger-than]
    757 | void curve25519_generic(u8 mypublic[CURVE25519_KEY_SIZE],
        |      ^

Using '-Rpass-analysis=stack-frame-layout' shows the following variables
and many, many 8-byte spills when KASAN is enabled:

  Offset: [SP-144], Type: Variable, Align: 8, Size: 40
  Offset: [SP-464], Type: Variable, Align: 8, Size: 320
  Offset: [SP-784], Type: Variable, Align: 8, Size: 320
  Offset: [SP-864], Type: Variable, Align: 32, Size: 80
  Offset: [SP-896], Type: Variable, Align: 32, Size: 32
  Offset: [SP-1016], Type: Variable, Align: 8, Size: 120

When KASAN is disabled, there are still spills but not at many and the
variables list is smaller:

  Offset: [SP-192], Type: Variable, Align: 32, Size: 80
  Offset: [SP-224], Type: Variable, Align: 32, Size: 32
  Offset: [SP-344], Type: Variable, Align: 8, Size: 120

Disable KASAN for this file when using clang-17 or older to avoid
blowing out the stack, clearing up the warning.

Signed-off-by: Nathan Chancellor <nathan@kernel.org>
Acked-by: "Jason A. Donenfeld" <Jason@zx2c4.com>
Acked-by: Ard Biesheuvel <ardb@kernel.org>
Link: https://lore.kernel.org/r/20250609-curve25519-hacl64-disable-kasan-clang-v1-1-08ea0ac5ccff@kernel.org
Signed-off-by: Eric Biggers <ebiggers@google.com>
---
 lib/crypto/Makefile | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/lib/crypto/Makefile b/lib/crypto/Makefile
index 3e79283b617d..18664127ecd6 100644
--- a/lib/crypto/Makefile
+++ b/lib/crypto/Makefile
@@ -35,6 +35,10 @@ obj-$(CONFIG_CRYPTO_LIB_CURVE25519_GENERIC)	+= libcurve25519-generic.o
 libcurve25519-generic-y				:= curve25519-fiat32.o
 libcurve25519-generic-$(CONFIG_ARCH_SUPPORTS_INT128)	:= curve25519-hacl64.o
 libcurve25519-generic-y				+= curve25519-generic.o
+# clang versions prior to 18 may blow out the stack with KASAN
+ifeq ($(call clang-min-version, 180000),)
+KASAN_SANITIZE_curve25519-hacl64.o := n
+endif
 
 obj-$(CONFIG_CRYPTO_LIB_CURVE25519)		+= libcurve25519.o
 libcurve25519-y					+= curve25519.o

From 0f4dd2ce352d38c7ecf1b3821c908816eb6376a7 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Thu, 12 Jun 2025 18:26:48 -0400
Subject: [PATCH 0378/1334] bcachefs: trace_extent_trim_atomic

Add a tracepoint for when we insert only part of an extent, due to too
many overwrites.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/extent_update.c | 13 ++++++++++++-
 fs/bcachefs/trace.h         |  5 +++++
 2 files changed, 17 insertions(+), 1 deletion(-)

diff --git a/fs/bcachefs/extent_update.c b/fs/bcachefs/extent_update.c
index b899ee75f5b9..e76e58a568bf 100644
--- a/fs/bcachefs/extent_update.c
+++ b/fs/bcachefs/extent_update.c
@@ -139,6 +139,17 @@ int bch2_extent_trim_atomic(struct btree_trans *trans,
 	if (ret)
 		return ret;
 
-	bch2_cut_back(end, k);
+	/* tracepoint */
+
+	if (bpos_lt(end, k->k.p)) {
+		if (trace_extent_trim_atomic_enabled()) {
+			CLASS(printbuf, buf)();
+			bch2_bpos_to_text(&buf, end);
+			prt_newline(&buf);
+			bch2_bkey_val_to_text(&buf, trans->c, bkey_i_to_s_c(k));
+			trace_extent_trim_atomic(trans->c, buf.buf);
+		}
+		bch2_cut_back(end, k);
+	}
 	return 0;
 }
diff --git a/fs/bcachefs/trace.h b/fs/bcachefs/trace.h
index dc09532796af..41efebdd06ef 100644
--- a/fs/bcachefs/trace.h
+++ b/fs/bcachefs/trace.h
@@ -1490,6 +1490,11 @@ DEFINE_EVENT(fs_str, io_move_evacuate_bucket,
 	TP_ARGS(c, str)
 );
 
+DEFINE_EVENT(fs_str, extent_trim_atomic,
+	TP_PROTO(struct bch_fs *c, const char *str),
+	TP_ARGS(c, str)
+);
+
 #ifdef CONFIG_BCACHEFS_PATH_TRACEPOINTS
 
 TRACE_EVENT(update_by_path,

From 3bd6f8aeae3d3f8121cbae5a8650a46622aa4e07 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Thu, 12 Jun 2025 18:27:37 -0400
Subject: [PATCH 0379/1334] bcachefs: btree iter tracepoints

We've been seeing some livelock-ish behavior in the index update part of
the main write path, and while we've got low level btree path
tracepoints, we've been lacking high level btree iterator tracepoints.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/btree_iter.c | 67 +++++++++++++++++++++++++++++++++++++---
 fs/bcachefs/trace.h      | 20 ++++++++++++
 2 files changed, 82 insertions(+), 5 deletions(-)

diff --git a/fs/bcachefs/btree_iter.c b/fs/bcachefs/btree_iter.c
index b78403376c07..b586ecf2fdfa 100644
--- a/fs/bcachefs/btree_iter.c
+++ b/fs/bcachefs/btree_iter.c
@@ -2326,6 +2326,20 @@ static struct bkey_s_c __bch2_btree_iter_peek(struct btree_trans *trans, struct
 	}
 
 	bch2_btree_iter_verify(trans, iter);
+
+	if (trace___btree_iter_peek_enabled()) {
+		CLASS(printbuf, buf)();
+
+		int ret = bkey_err(k);
+		if (ret)
+			prt_str(&buf, bch2_err_str(ret));
+		else if (k.k)
+			bch2_bkey_val_to_text(&buf, trans->c, k);
+		else
+			prt_str(&buf, "(null)");
+		trace___btree_iter_peek(trans->c, buf.buf);
+	}
+
 	return k;
 }
 
@@ -2484,6 +2498,19 @@ out_no_locked:
 
 	bch2_btree_iter_verify_entry_exit(iter);
 
+	if (trace_btree_iter_peek_max_enabled()) {
+		CLASS(printbuf, buf)();
+
+		int ret = bkey_err(k);
+		if (ret)
+			prt_str(&buf, bch2_err_str(ret));
+		else if (k.k)
+			bch2_bkey_val_to_text(&buf, trans->c, k);
+		else
+			prt_str(&buf, "(null)");
+		trace_btree_iter_peek_max(trans->c, buf.buf);
+	}
+
 	return k;
 end:
 	bch2_btree_iter_set_pos(trans, iter, end);
@@ -2724,6 +2751,19 @@ out_no_locked:
 
 	bch2_btree_iter_verify_entry_exit(iter);
 	bch2_btree_iter_verify(trans, iter);
+
+	if (trace_btree_iter_peek_prev_min_enabled()) {
+		CLASS(printbuf, buf)();
+
+		int ret = bkey_err(k);
+		if (ret)
+			prt_str(&buf, bch2_err_str(ret));
+		else if (k.k)
+			bch2_bkey_val_to_text(&buf, trans->c, k);
+		else
+			prt_str(&buf, "(null)");
+		trace_btree_iter_peek_prev_min(trans->c, buf.buf);
+	}
 	return k;
 end:
 	bch2_btree_iter_set_pos(trans, iter, end);
@@ -2767,8 +2807,10 @@ struct bkey_s_c bch2_btree_iter_peek_slot(struct btree_trans *trans, struct btre
 	/* extents can't span inode numbers: */
 	if ((iter->flags & BTREE_ITER_is_extents) &&
 	    unlikely(iter->pos.offset == KEY_OFFSET_MAX)) {
-		if (iter->pos.inode == KEY_INODE_MAX)
-			return bkey_s_c_null;
+		if (iter->pos.inode == KEY_INODE_MAX) {
+			k = bkey_s_c_null;
+			goto out2;
+		}
 
 		bch2_btree_iter_set_pos(trans, iter, bpos_nosnap_successor(iter->pos));
 	}
@@ -2785,8 +2827,10 @@ struct bkey_s_c bch2_btree_iter_peek_slot(struct btree_trans *trans, struct btre
 	}
 
 	struct btree_path *path = btree_iter_path(trans, iter);
-	if (unlikely(!btree_path_node(path, path->level)))
-		return bkey_s_c_null;
+	if (unlikely(!btree_path_node(path, path->level))) {
+		k = bkey_s_c_null;
+		goto out2;
+	}
 
 	btree_path_set_should_be_locked(trans, path);
 
@@ -2879,7 +2923,20 @@ out:
 	bch2_btree_iter_verify(trans, iter);
 	ret = bch2_btree_iter_verify_ret(trans, iter, k);
 	if (unlikely(ret))
-		return bkey_s_c_err(ret);
+		k = bkey_s_c_err(ret);
+out2:
+	if (trace_btree_iter_peek_slot_enabled()) {
+		CLASS(printbuf, buf)();
+
+		int ret = bkey_err(k);
+		if (ret)
+			prt_str(&buf, bch2_err_str(ret));
+		else if (k.k)
+			bch2_bkey_val_to_text(&buf, trans->c, k);
+		else
+			prt_str(&buf, "(null)");
+		trace_btree_iter_peek_slot(trans->c, buf.buf);
+	}
 
 	return k;
 }
diff --git a/fs/bcachefs/trace.h b/fs/bcachefs/trace.h
index 41efebdd06ef..e759c9ff3965 100644
--- a/fs/bcachefs/trace.h
+++ b/fs/bcachefs/trace.h
@@ -1495,6 +1495,26 @@ DEFINE_EVENT(fs_str, extent_trim_atomic,
 	TP_ARGS(c, str)
 );
 
+DEFINE_EVENT(fs_str, btree_iter_peek_slot,
+	TP_PROTO(struct bch_fs *c, const char *str),
+	TP_ARGS(c, str)
+);
+
+DEFINE_EVENT(fs_str, __btree_iter_peek,
+	TP_PROTO(struct bch_fs *c, const char *str),
+	TP_ARGS(c, str)
+);
+
+DEFINE_EVENT(fs_str, btree_iter_peek_max,
+	TP_PROTO(struct bch_fs *c, const char *str),
+	TP_ARGS(c, str)
+);
+
+DEFINE_EVENT(fs_str, btree_iter_peek_prev_min,
+	TP_PROTO(struct bch_fs *c, const char *str),
+	TP_ARGS(c, str)
+);
+
 #ifdef CONFIG_BCACHEFS_PATH_TRACEPOINTS
 
 TRACE_EVENT(update_by_path,

From 9b9a3270092bf8030dbe21ce90b2d0c8d98d33c7 Mon Sep 17 00:00:00 2001
From: Alan Huang <mmpgouride@gmail.com>
Date: Fri, 13 Jun 2025 21:19:50 +0800
Subject: [PATCH 0380/1334] bcachefs: Don't allocate new memory when mempool is
 exhausted

Allocating new memory when mempool is exhausted is too complicated, just
return ENOMEM is fine. memcpy is not needed, since there might be
pointers point to the old memory, that's the bug.

Signed-off-by: Alan Huang <mmpgouride@gmail.com>
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/btree_iter.c | 29 ++++-------------------------
 1 file changed, 4 insertions(+), 25 deletions(-)

diff --git a/fs/bcachefs/btree_iter.c b/fs/bcachefs/btree_iter.c
index b586ecf2fdfa..55de2e474705 100644
--- a/fs/bcachefs/btree_iter.c
+++ b/fs/bcachefs/btree_iter.c
@@ -3217,28 +3217,8 @@ void *__bch2_trans_kmalloc(struct btree_trans *trans, size_t size, unsigned long
 	}
 
 	if (trans->used_mempool) {
-		if (trans->mem_bytes >= new_bytes)
-			goto out_change_top;
-
-		/* No more space from mempool item, need malloc new one */
-		new_mem = kmalloc(new_bytes, GFP_NOWAIT|__GFP_NOWARN);
-		if (unlikely(!new_mem)) {
-			bch2_trans_unlock(trans);
-
-			new_mem = kmalloc(new_bytes, GFP_KERNEL);
-			if (!new_mem)
-				return ERR_PTR(-BCH_ERR_ENOMEM_trans_kmalloc);
-
-			ret = bch2_trans_relock(trans);
-			if (ret) {
-				kfree(new_mem);
-				return ERR_PTR(ret);
-			}
-		}
-		memcpy(new_mem, trans->mem, trans->mem_top);
-		trans->used_mempool = false;
-		mempool_free(trans->mem, &c->btree_trans_mem_pool);
-		goto out_new_mem;
+		EBUG_ON(trans->mem_bytes >= new_bytes);
+		return ERR_PTR(-BCH_ERR_ENOMEM_trans_kmalloc);
 	}
 
 	new_mem = krealloc(trans->mem, new_bytes, GFP_NOWAIT|__GFP_NOWARN);
@@ -3249,7 +3229,6 @@ void *__bch2_trans_kmalloc(struct btree_trans *trans, size_t size, unsigned long
 		if (!new_mem && new_bytes <= BTREE_TRANS_MEM_MAX) {
 			new_mem = mempool_alloc(&c->btree_trans_mem_pool, GFP_KERNEL);
 			new_bytes = BTREE_TRANS_MEM_MAX;
-			memcpy(new_mem, trans->mem, trans->mem_top);
 			trans->used_mempool = true;
 			kfree(trans->mem);
 		}
@@ -3264,7 +3243,7 @@ void *__bch2_trans_kmalloc(struct btree_trans *trans, size_t size, unsigned long
 		if (ret)
 			return ERR_PTR(ret);
 	}
-out_new_mem:
+
 	trans->mem = new_mem;
 	trans->mem_bytes = new_bytes;
 
@@ -3273,7 +3252,7 @@ out_new_mem:
 		return ERR_PTR(btree_trans_restart_ip(trans,
 					BCH_ERR_transaction_restart_mem_realloced, _RET_IP_));
 	}
-out_change_top:
+
 	bch2_trans_kmalloc_trace(trans, size, ip);
 
 	p = trans->mem + trans->mem_top;

From 9b54efe66c9b44e7446e8a81a058c014cd43661d Mon Sep 17 00:00:00 2001
From: Alan Huang <mmpgouride@gmail.com>
Date: Fri, 13 Jun 2025 22:54:59 +0800
Subject: [PATCH 0381/1334] bcachefs: Fix alloc_req use after free

Now the alloc_req is allocated from the bump allocator, if there is
reallocation, the memory of alloc_req would be frees, fix by delaying the
reallocation to transaction restart, it has to restart anyway.

Reported-by: syzbot+2887a13a5c387e616a68@syzkaller.appspotmail.com
Signed-off-by: Alan Huang <mmpgouride@gmail.com>
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/btree_iter.c  | 48 +++++++++++++++++++++++++++------------
 fs/bcachefs/btree_types.h |  1 +
 2 files changed, 35 insertions(+), 14 deletions(-)

diff --git a/fs/bcachefs/btree_iter.c b/fs/bcachefs/btree_iter.c
index 55de2e474705..e2747c57ba2a 100644
--- a/fs/bcachefs/btree_iter.c
+++ b/fs/bcachefs/btree_iter.c
@@ -3216,25 +3216,32 @@ void *__bch2_trans_kmalloc(struct btree_trans *trans, size_t size, unsigned long
 		mutex_unlock(&s->lock);
 	}
 
-	if (trans->used_mempool) {
+	if (trans->used_mempool || new_bytes > BTREE_TRANS_MEM_MAX) {
 		EBUG_ON(trans->mem_bytes >= new_bytes);
 		return ERR_PTR(-BCH_ERR_ENOMEM_trans_kmalloc);
 	}
 
-	new_mem = krealloc(trans->mem, new_bytes, GFP_NOWAIT|__GFP_NOWARN);
+	if (old_bytes) {
+		trans->realloc_bytes_required = new_bytes;
+		trace_and_count(c, trans_restart_mem_realloced, trans, _RET_IP_, new_bytes);
+		return ERR_PTR(btree_trans_restart_ip(trans,
+					BCH_ERR_transaction_restart_mem_realloced, _RET_IP_));
+	}
+
+	EBUG_ON(trans->mem);
+
+	new_mem = kmalloc(new_bytes, GFP_NOWAIT|__GFP_NOWARN);
 	if (unlikely(!new_mem)) {
 		bch2_trans_unlock(trans);
 
-		new_mem = krealloc(trans->mem, new_bytes, GFP_KERNEL);
+		new_mem = kmalloc(new_bytes, GFP_KERNEL);
 		if (!new_mem && new_bytes <= BTREE_TRANS_MEM_MAX) {
 			new_mem = mempool_alloc(&c->btree_trans_mem_pool, GFP_KERNEL);
 			new_bytes = BTREE_TRANS_MEM_MAX;
 			trans->used_mempool = true;
-			kfree(trans->mem);
 		}
 
-		if (!new_mem)
-			return ERR_PTR(-BCH_ERR_ENOMEM_trans_kmalloc);
+		EBUG_ON(!new_mem);
 
 		trans->mem = new_mem;
 		trans->mem_bytes = new_bytes;
@@ -3247,14 +3254,6 @@ void *__bch2_trans_kmalloc(struct btree_trans *trans, size_t size, unsigned long
 	trans->mem = new_mem;
 	trans->mem_bytes = new_bytes;
 
-	if (old_bytes) {
-		trace_and_count(c, trans_restart_mem_realloced, trans, _RET_IP_, new_bytes);
-		return ERR_PTR(btree_trans_restart_ip(trans,
-					BCH_ERR_transaction_restart_mem_realloced, _RET_IP_));
-	}
-
-	bch2_trans_kmalloc_trace(trans, size, ip);
-
 	p = trans->mem + trans->mem_top;
 	trans->mem_top += size;
 	memset(p, 0, size);
@@ -3315,6 +3314,27 @@ u32 bch2_trans_begin(struct btree_trans *trans)
 	trans->restart_count++;
 	trans->mem_top			= 0;
 
+	if (trans->restarted == BCH_ERR_transaction_restart_mem_realloced) {
+		EBUG_ON(!trans->mem || !trans->mem_bytes);
+		unsigned new_bytes = trans->realloc_bytes_required;
+		void *new_mem = krealloc(trans->mem, new_bytes, GFP_NOWAIT|__GFP_NOWARN);
+		if (unlikely(!new_mem)) {
+			bch2_trans_unlock(trans);
+			new_mem = krealloc(trans->mem, new_bytes, GFP_KERNEL);
+
+			EBUG_ON(new_bytes > BTREE_TRANS_MEM_MAX);
+
+			if (!new_mem) {
+				new_mem = mempool_alloc(&trans->c->btree_trans_mem_pool, GFP_KERNEL);
+				new_bytes = BTREE_TRANS_MEM_MAX;
+				trans->used_mempool = true;
+				kfree(trans->mem);
+			}
+                }
+		trans->mem = new_mem;
+		trans->mem_bytes = new_bytes;
+	}
+
 	trans_for_each_path(trans, path, i) {
 		path->should_be_locked = false;
 
diff --git a/fs/bcachefs/btree_types.h b/fs/bcachefs/btree_types.h
index 3aa4a602bd02..112170fd9c8f 100644
--- a/fs/bcachefs/btree_types.h
+++ b/fs/bcachefs/btree_types.h
@@ -497,6 +497,7 @@ struct btree_trans {
 	void			*mem;
 	unsigned		mem_top;
 	unsigned		mem_bytes;
+	unsigned		realloc_bytes_required;
 #ifdef CONFIG_BCACHEFS_TRANS_KMALLOC_TRACE
 	darray_trans_kmalloc_trace trans_kmalloc_trace;
 #endif

From e31144f8cbe041a572ca64d9261ceeb647ccf557 Mon Sep 17 00:00:00 2001
From: Alan Huang <mmpgouride@gmail.com>
Date: Fri, 13 Jun 2025 03:01:58 +0800
Subject: [PATCH 0382/1334] bcachefs: Add missing EBUG_ON

Just like the EBUG_ON in bch2_journal_add_entry().

Signed-off-by: Alan Huang <mmpgouride@gmail.com>
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/btree_trans_commit.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/fs/bcachefs/btree_trans_commit.c b/fs/bcachefs/btree_trans_commit.c
index d9710801e3ee..55952143f0d3 100644
--- a/fs/bcachefs/btree_trans_commit.c
+++ b/fs/bcachefs/btree_trans_commit.c
@@ -757,6 +757,8 @@ bch2_trans_commit_write_locked(struct btree_trans *trans, unsigned flags,
 				  btree_trans_journal_entries_start(trans),
 				  trans->journal_entries.u64s);
 
+		EBUG_ON(trans->journal_res.u64s < trans->journal_entries.u64s);
+
 		trans->journal_res.offset	+= trans->journal_entries.u64s;
 		trans->journal_res.u64s		-= trans->journal_entries.u64s;
 

From 0dc8eaebed99ea323ab3be7cf1438277f990189d Mon Sep 17 00:00:00 2001
From: Alan Huang <mmpgouride@gmail.com>
Date: Fri, 13 Jun 2025 03:01:59 +0800
Subject: [PATCH 0383/1334] bcachefs: Delay calculation of trans->journal_u64s

When there is commit error that need split btree leaf, fsck might change
the value of trans->journal_entries.u64s, when retry commit, the value of
trans->journal_u64s would be incorrect, which will lead to trans->journal_res.u64s
underflow, and then out of bounds write will occur:

[  464.496970][T11969] Call trace:
[  464.496973][T11969]  show_stack+0x3c/0x88 (C)
[  464.496995][T11969]  dump_stack_lvl+0xf8/0x178
[  464.497014][T11969]  dump_stack+0x20/0x30
[  464.497031][T11969]  __bch2_trans_log_str+0x344/0x350
[  464.497048][T11969]  bch2_trans_log_str+0x3c/0x60
[  464.497065][T11969]  __bch2_fsck_err+0x11bc/0x1390
[  464.497083][T11969]  bch2_check_discard_freespace_key+0xad4/0x10d0
[  464.497100][T11969]  bch2_bucket_alloc_freelist+0x99c/0x1130
[  464.497117][T11969]  bch2_bucket_alloc_trans+0x79c/0xcb8
[  464.497133][T11969]  bch2_bucket_alloc_set_trans+0x378/0xc20
[  464.497151][T11969]  __open_bucket_add_buckets+0x7fc/0x1c00
[  464.497168][T11969]  open_bucket_add_buckets+0x184/0x3a8
[  464.497185][T11969]  bch2_alloc_sectors_start_trans+0xa04/0x1da0
[  464.497203][T11969]  bch2_btree_reserve_get+0x6e0/0xef0
[  464.497220][T11969]  bch2_btree_update_start+0x1618/0x2600
[  464.497239][T11969]  bch2_btree_split_leaf+0xcc/0x730
[  464.497258][T11969]  bch2_trans_commit_error+0x22c/0xc30
[  464.497276][T11969]  __bch2_trans_commit+0x207c/0x4e30
[  464.497292][T11969]  bch2_journal_replay+0x9e0/0x1420
[  464.497305][T11969]  __bch2_run_recovery_passes+0x458/0xf98
[  464.497318][T11969]  bch2_run_recovery_passes+0x280/0x478
[  464.497331][T11969]  bch2_fs_recovery+0x24f0/0x3a28
[  464.497344][T11969]  bch2_fs_start+0xb80/0x1248
[  464.497358][T11969]  bch2_fs_get_tree+0xe94/0x1708
[  464.497377][T11969]  vfs_get_tree+0x84/0x2d0

Signed-off-by: Alan Huang <mmpgouride@gmail.com>
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/btree_trans_commit.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/fs/bcachefs/btree_trans_commit.c b/fs/bcachefs/btree_trans_commit.c
index 55952143f0d3..61107f2310ab 100644
--- a/fs/bcachefs/btree_trans_commit.c
+++ b/fs/bcachefs/btree_trans_commit.c
@@ -1005,6 +1005,7 @@ int __bch2_trans_commit(struct btree_trans *trans, unsigned flags)
 {
 	struct btree_insert_entry *errored_at = NULL;
 	struct bch_fs *c = trans->c;
+	unsigned journal_u64s = 0;
 	int ret = 0;
 
 	bch2_trans_verify_not_unlocked_or_in_restart(trans);
@@ -1033,10 +1034,10 @@ int __bch2_trans_commit(struct btree_trans *trans, unsigned flags)
 
 	EBUG_ON(test_bit(BCH_FS_clean_shutdown, &c->flags));
 
-	trans->journal_u64s		= trans->journal_entries.u64s + jset_u64s(trans->accounting.u64s);
+	journal_u64s = jset_u64s(trans->accounting.u64s);
 	trans->journal_transaction_names = READ_ONCE(c->opts.journal_transaction_names);
 	if (trans->journal_transaction_names)
-		trans->journal_u64s += jset_u64s(JSET_ENTRY_LOG_U64s);
+		journal_u64s += jset_u64s(JSET_ENTRY_LOG_U64s);
 
 	trans_for_each_update(trans, i) {
 		struct btree_path *path = trans->paths + i->path;
@@ -1056,11 +1057,11 @@ int __bch2_trans_commit(struct btree_trans *trans, unsigned flags)
 			continue;
 
 		/* we're going to journal the key being updated: */
-		trans->journal_u64s += jset_u64s(i->k->k.u64s);
+		journal_u64s += jset_u64s(i->k->k.u64s);
 
 		/* and we're also going to log the overwrite: */
 		if (trans->journal_transaction_names)
-			trans->journal_u64s += jset_u64s(i->old_k.u64s);
+			journal_u64s += jset_u64s(i->old_k.u64s);
 	}
 
 	if (trans->extra_disk_res) {
@@ -1078,6 +1079,8 @@ retry:
 		memset(&trans->journal_res, 0, sizeof(trans->journal_res));
 	memset(&trans->fs_usage_delta, 0, sizeof(trans->fs_usage_delta));
 
+	trans->journal_u64s = journal_u64s + trans->journal_entries.u64s;
+
 	ret = do_bch2_trans_commit(trans, flags, &errored_at, _RET_IP_);
 
 	/* make sure we didn't drop or screw up locks: */

From 0e62fca2a6dbfcedaab4919d7ad2044f20fdf889 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Fri, 13 Jun 2025 14:53:42 -0400
Subject: [PATCH 0384/1334] bcachefs: Fix bch2_journal_keys_peek_prev_min()

this code is rarely invoked, so - we had a few bugs left from basing it
off of bch2_journal_keys_peek_max()...

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/btree_journal_iter.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/fs/bcachefs/btree_journal_iter.c b/fs/bcachefs/btree_journal_iter.c
index cf7398751644..de996c848e43 100644
--- a/fs/bcachefs/btree_journal_iter.c
+++ b/fs/bcachefs/btree_journal_iter.c
@@ -141,8 +141,8 @@ search:
 	if (!*idx)
 		*idx = __bch2_journal_key_search(keys, btree_id, level, pos);
 
-	while (*idx &&
-	       __journal_key_cmp(btree_id, level, end_pos, idx_to_key(keys, *idx - 1)) <= 0) {
+	while (*idx < keys->nr &&
+	       __journal_key_cmp(btree_id, level, end_pos, idx_to_key(keys, *idx - 1)) >= 0) {
 		(*idx)++;
 		iters++;
 		if (iters == 10) {

From 425da82c63e3ac06b2f8780879e83463e88cbf9f Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Fri, 13 Jun 2025 14:57:34 -0400
Subject: [PATCH 0385/1334] bcachefs: btree_iter: fix updates, journal overlay

We need to start searching from search_key - _not_ path->pos, which will
point to the key we found in the btree

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/btree_iter.c | 29 +++++++++++++++++------------
 1 file changed, 17 insertions(+), 12 deletions(-)

diff --git a/fs/bcachefs/btree_iter.c b/fs/bcachefs/btree_iter.c
index e2747c57ba2a..061603999ae5 100644
--- a/fs/bcachefs/btree_iter.c
+++ b/fs/bcachefs/btree_iter.c
@@ -2076,14 +2076,14 @@ inline bool bch2_btree_iter_rewind(struct btree_trans *trans, struct btree_iter
 
 static noinline
 void bch2_btree_trans_peek_prev_updates(struct btree_trans *trans, struct btree_iter *iter,
-					struct bkey_s_c *k)
+					struct bpos search_key, struct bkey_s_c *k)
 {
 	struct bpos end = path_l(btree_iter_path(trans, iter))->b->data->min_key;
 
 	trans_for_each_update(trans, i)
 		if (!i->key_cache_already_flushed &&
 		    i->btree_id == iter->btree_id &&
-		    bpos_le(i->k->k.p, iter->pos) &&
+		    bpos_le(i->k->k.p, search_key) &&
 		    bpos_ge(i->k->k.p, k->k ? k->k->p : end)) {
 			iter->k = i->k->k;
 			*k = bkey_i_to_s_c(i->k);
@@ -2092,6 +2092,7 @@ void bch2_btree_trans_peek_prev_updates(struct btree_trans *trans, struct btree_
 
 static noinline
 void bch2_btree_trans_peek_updates(struct btree_trans *trans, struct btree_iter *iter,
+				   struct bpos search_key,
 				   struct bkey_s_c *k)
 {
 	struct btree_path *path = btree_iter_path(trans, iter);
@@ -2100,7 +2101,7 @@ void bch2_btree_trans_peek_updates(struct btree_trans *trans, struct btree_iter
 	trans_for_each_update(trans, i)
 		if (!i->key_cache_already_flushed &&
 		    i->btree_id == iter->btree_id &&
-		    bpos_ge(i->k->k.p, path->pos) &&
+		    bpos_ge(i->k->k.p, search_key) &&
 		    bpos_le(i->k->k.p, k->k ? k->k->p : end)) {
 			iter->k = i->k->k;
 			*k = bkey_i_to_s_c(i->k);
@@ -2122,13 +2123,14 @@ void bch2_btree_trans_peek_slot_updates(struct btree_trans *trans, struct btree_
 
 static struct bkey_i *bch2_btree_journal_peek(struct btree_trans *trans,
 					      struct btree_iter *iter,
+					      struct bpos search_pos,
 					      struct bpos end_pos)
 {
 	struct btree_path *path = btree_iter_path(trans, iter);
 
 	return bch2_journal_keys_peek_max(trans->c, iter->btree_id,
 					   path->level,
-					   path->pos,
+					   search_pos,
 					   end_pos,
 					   &iter->journal_idx);
 }
@@ -2138,7 +2140,7 @@ struct bkey_s_c btree_trans_peek_slot_journal(struct btree_trans *trans,
 					      struct btree_iter *iter)
 {
 	struct btree_path *path = btree_iter_path(trans, iter);
-	struct bkey_i *k = bch2_btree_journal_peek(trans, iter, path->pos);
+	struct bkey_i *k = bch2_btree_journal_peek(trans, iter, path->pos, path->pos);
 
 	if (k) {
 		iter->k = k->k;
@@ -2151,11 +2153,12 @@ struct bkey_s_c btree_trans_peek_slot_journal(struct btree_trans *trans,
 static noinline
 void btree_trans_peek_journal(struct btree_trans *trans,
 			      struct btree_iter *iter,
+			      struct bpos search_key,
 			      struct bkey_s_c *k)
 {
 	struct btree_path *path = btree_iter_path(trans, iter);
 	struct bkey_i *next_journal =
-		bch2_btree_journal_peek(trans, iter,
+		bch2_btree_journal_peek(trans, iter, search_key,
 				k->k ? k->k->p : path_l(path)->b->key.k.p);
 	if (next_journal) {
 		iter->k = next_journal->k;
@@ -2165,13 +2168,14 @@ void btree_trans_peek_journal(struct btree_trans *trans,
 
 static struct bkey_i *bch2_btree_journal_peek_prev(struct btree_trans *trans,
 					      struct btree_iter *iter,
+					      struct bpos search_key,
 					      struct bpos end_pos)
 {
 	struct btree_path *path = btree_iter_path(trans, iter);
 
 	return bch2_journal_keys_peek_prev_min(trans->c, iter->btree_id,
 					   path->level,
-					   path->pos,
+					   search_key,
 					   end_pos,
 					   &iter->journal_idx);
 }
@@ -2179,11 +2183,12 @@ static struct bkey_i *bch2_btree_journal_peek_prev(struct btree_trans *trans,
 static noinline
 void btree_trans_peek_prev_journal(struct btree_trans *trans,
 				   struct btree_iter *iter,
+				   struct bpos search_key,
 				   struct bkey_s_c *k)
 {
 	struct btree_path *path = btree_iter_path(trans, iter);
 	struct bkey_i *next_journal =
-		bch2_btree_journal_peek_prev(trans, iter,
+		bch2_btree_journal_peek_prev(trans, iter, search_key,
 				k->k ? k->k->p : path_l(path)->b->key.k.p);
 
 	if (next_journal) {
@@ -2292,11 +2297,11 @@ static struct bkey_s_c __bch2_btree_iter_peek(struct btree_trans *trans, struct
 		}
 
 		if (unlikely(iter->flags & BTREE_ITER_with_journal))
-			btree_trans_peek_journal(trans, iter, &k);
+			btree_trans_peek_journal(trans, iter, search_key, &k);
 
 		if (unlikely((iter->flags & BTREE_ITER_with_updates) &&
 			     trans->nr_updates))
-			bch2_btree_trans_peek_updates(trans, iter, &k);
+			bch2_btree_trans_peek_updates(trans, iter, search_key, &k);
 
 		if (k.k && bkey_deleted(k.k)) {
 			/*
@@ -2584,11 +2589,11 @@ static struct bkey_s_c __bch2_btree_iter_peek_prev(struct btree_trans *trans, st
 		}
 
 		if (unlikely(iter->flags & BTREE_ITER_with_journal))
-			btree_trans_peek_prev_journal(trans, iter, &k);
+			btree_trans_peek_prev_journal(trans, iter, search_key, &k);
 
 		if (unlikely((iter->flags & BTREE_ITER_with_updates) &&
 			     trans->nr_updates))
-			bch2_btree_trans_peek_prev_updates(trans, iter, &k);
+			bch2_btree_trans_peek_prev_updates(trans, iter, search_key, &k);
 
 		if (likely(k.k && !bkey_deleted(k.k))) {
 			break;

From f2ed0892732d470abde7a1af360bd670dc8a68c6 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Fri, 13 Jun 2025 15:17:37 -0400
Subject: [PATCH 0386/1334] bcachefs: better __bch2_snapshot_is_ancestor()
 assert

Previously, we weren't checking the result of the skiplist walk, just
the is_ancestor bitmap.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/snapshot.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/fs/bcachefs/snapshot.c b/fs/bcachefs/snapshot.c
index 23a332d76b32..38aeaa128d27 100644
--- a/fs/bcachefs/snapshot.c
+++ b/fs/bcachefs/snapshot.c
@@ -135,7 +135,9 @@ static bool test_ancestor_bitmap(struct snapshot_table *t, u32 id, u32 ancestor)
 
 bool __bch2_snapshot_is_ancestor(struct bch_fs *c, u32 id, u32 ancestor)
 {
-	bool ret;
+#ifdef CONFIG_BCACHEFS_DEBUG
+	u32 orig_id = id;
+#endif
 
 	guard(rcu)();
 	struct snapshot_table *t = rcu_dereference(c->snapshots);
@@ -147,11 +149,11 @@ bool __bch2_snapshot_is_ancestor(struct bch_fs *c, u32 id, u32 ancestor)
 		while (id && id < ancestor - IS_ANCESTOR_BITMAP)
 			id = get_ancestor_below(t, id, ancestor);
 
-	ret = id && id < ancestor
+	bool ret = id && id < ancestor
 		? test_ancestor_bitmap(t, id, ancestor)
 		: id == ancestor;
 
-	EBUG_ON(ret != __bch2_snapshot_is_ancestor_early(t, id, ancestor));
+	EBUG_ON(ret != __bch2_snapshot_is_ancestor_early(t, orig_id, ancestor));
 	return ret;
 }
 

From 2ba562cc04dc22d01750e80d0638cc1d91fdd95c Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Fri, 13 Jun 2025 15:15:09 -0400
Subject: [PATCH 0387/1334] bcachefs: pass last_seq into fs_journal_start()

Prep work for journal rewind, where the seq we're replaying from may be
different than the last journal entry's last_seq.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/journal.c  | 18 ++++++------------
 fs/bcachefs/journal.h  |  2 +-
 fs/bcachefs/recovery.c |  4 ++--
 3 files changed, 9 insertions(+), 15 deletions(-)

diff --git a/fs/bcachefs/journal.c b/fs/bcachefs/journal.c
index dda802a656cf..df71af0013ba 100644
--- a/fs/bcachefs/journal.c
+++ b/fs/bcachefs/journal.c
@@ -1474,14 +1474,13 @@ void bch2_fs_journal_stop(struct journal *j)
 		clear_bit(JOURNAL_running, &j->flags);
 }
 
-int bch2_fs_journal_start(struct journal *j, u64 cur_seq)
+int bch2_fs_journal_start(struct journal *j, u64 last_seq, u64 cur_seq)
 {
 	struct bch_fs *c = container_of(j, struct bch_fs, journal);
 	struct journal_entry_pin_list *p;
 	struct journal_replay *i, **_i;
 	struct genradix_iter iter;
 	bool had_entries = false;
-	u64 last_seq = cur_seq, nr, seq;
 
 	/*
 	 *
@@ -1495,17 +1494,11 @@ int bch2_fs_journal_start(struct journal *j, u64 cur_seq)
 		return -EINVAL;
 	}
 
-	genradix_for_each_reverse(&c->journal_entries, iter, _i) {
-		i = *_i;
+	/* Clean filesystem? */
+	if (!last_seq)
+		last_seq = cur_seq;
 
-		if (journal_replay_ignore(i))
-			continue;
-
-		last_seq = le64_to_cpu(i->j.last_seq);
-		break;
-	}
-
-	nr = cur_seq - last_seq;
+	u64 nr = cur_seq - last_seq;
 
 	/*
 	 * Extra fudge factor, in case we crashed when the journal pin fifo was
@@ -1532,6 +1525,7 @@ int bch2_fs_journal_start(struct journal *j, u64 cur_seq)
 	j->pin.back		= cur_seq;
 	atomic64_set(&j->seq, cur_seq - 1);
 
+	u64 seq;
 	fifo_for_each_entry_ptr(p, &j->pin, seq)
 		journal_pin_list_init(p, 1);
 
diff --git a/fs/bcachefs/journal.h b/fs/bcachefs/journal.h
index 83734fe4331f..977907038d98 100644
--- a/fs/bcachefs/journal.h
+++ b/fs/bcachefs/journal.h
@@ -453,7 +453,7 @@ int bch2_fs_journal_alloc(struct bch_fs *);
 void bch2_dev_journal_stop(struct journal *, struct bch_dev *);
 
 void bch2_fs_journal_stop(struct journal *);
-int bch2_fs_journal_start(struct journal *, u64);
+int bch2_fs_journal_start(struct journal *, u64, u64);
 void bch2_journal_set_replay_done(struct journal *);
 
 void bch2_dev_journal_exit(struct bch_dev *);
diff --git a/fs/bcachefs/recovery.c b/fs/bcachefs/recovery.c
index 0b21fa6ff062..6aef8b101820 100644
--- a/fs/bcachefs/recovery.c
+++ b/fs/bcachefs/recovery.c
@@ -965,7 +965,7 @@ use_clean:
 
 	ret =   bch2_journal_log_msg(c, "starting journal at entry %llu, replaying %llu-%llu",
 				     journal_seq, last_seq, blacklist_seq - 1) ?:
-		bch2_fs_journal_start(&c->journal, journal_seq);
+		bch2_fs_journal_start(&c->journal, last_seq, journal_seq);
 	if (ret)
 		goto err;
 
@@ -1181,7 +1181,7 @@ int bch2_fs_initialize(struct bch_fs *c)
 	 * journal_res_get() will crash if called before this has
 	 * set up the journal.pin FIFO and journal.cur pointer:
 	 */
-	ret = bch2_fs_journal_start(&c->journal, 1);
+	ret = bch2_fs_journal_start(&c->journal, 1, 1);
 	if (ret)
 		goto err;
 

From c1ccd43b357e157d78c899e61764fc83b4d1dbaa Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Fri, 13 Jun 2025 17:47:07 -0400
Subject: [PATCH 0388/1334] bcachefs: Fix "now allowing incompatible features"
 message

Check against version_incompat_allowed, not version_incompat.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/recovery.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/bcachefs/recovery.c b/fs/bcachefs/recovery.c
index 6aef8b101820..820249e9c5ea 100644
--- a/fs/bcachefs/recovery.c
+++ b/fs/bcachefs/recovery.c
@@ -692,7 +692,7 @@ static bool check_version_upgrade(struct bch_fs *c)
 		ret = true;
 	}
 
-	if (new_version > c->sb.version_incompat &&
+	if (new_version > c->sb.version_incompat_allowed &&
 	    c->opts.version_upgrade == BCH_VERSION_UPGRADE_incompatible) {
 		struct printbuf buf = PRINTBUF;
 

From c27e5782d957c7242e9cb6405a395b89e8e1d573 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Fri, 13 Jun 2025 18:27:33 -0400
Subject: [PATCH 0389/1334] bcachefs: Fix snapshot_key_missing_inode_snapshot
 repair

When the inode was a whiteout, we were inserting a new whiteout at the
wrong (old) snapshot.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/fsck.c | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

diff --git a/fs/bcachefs/fsck.c b/fs/bcachefs/fsck.c
index 68ed69a255e1..b80a56e19b40 100644
--- a/fs/bcachefs/fsck.c
+++ b/fs/bcachefs/fsck.c
@@ -903,17 +903,15 @@ lookup_inode_for_snapshot(struct btree_trans *trans, struct inode_walker *w, str
 			 w->last_pos.inode, k.k->p.snapshot, i->inode.bi_snapshot,
 			 (bch2_bkey_val_to_text(&buf, c, k),
 			  buf.buf))) {
-		struct bch_inode_unpacked new = i->inode;
-		struct bkey_i whiteout;
-
-		new.bi_snapshot = k.k->p.snapshot;
-
 		if (!i->whiteout) {
+			struct bch_inode_unpacked new = i->inode;
+			new.bi_snapshot = k.k->p.snapshot;
 			ret = __bch2_fsck_write_inode(trans, &new);
 		} else {
+			struct bkey_i whiteout;
 			bkey_init(&whiteout.k);
 			whiteout.k.type = KEY_TYPE_whiteout;
-			whiteout.k.p = SPOS(0, i->inode.bi_inum, i->inode.bi_snapshot);
+			whiteout.k.p = SPOS(0, i->inode.bi_inum, k.k->p.snapshot);
 			ret = bch2_btree_insert_nonextent(trans, BTREE_ID_inodes,
 							  &whiteout,
 							  BTREE_UPDATE_internal_snapshot_node);

From b17d7bdb128c50025fc3eb7a9e57b3c7caa4a5ac Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Fri, 13 Jun 2025 18:49:54 -0400
Subject: [PATCH 0390/1334] bcachefs: fsck: fix add_inode()

the inode btree uses the offset field for the inum, not the inode field.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/fsck.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/bcachefs/fsck.c b/fs/bcachefs/fsck.c
index b80a56e19b40..28ca07c0e029 100644
--- a/fs/bcachefs/fsck.c
+++ b/fs/bcachefs/fsck.c
@@ -806,7 +806,7 @@ static int add_inode(struct bch_fs *c, struct inode_walker *w,
 	if (!n->whiteout) {
 		return bch2_inode_unpack(inode, &n->inode);
 	} else {
-		n->inode.bi_inum	= inode.k->p.inode;
+		n->inode.bi_inum	= inode.k->p.offset;
 		n->inode.bi_snapshot	= inode.k->p.snapshot;
 		return 0;
 	}

From 191334400d8031df367eb74b6ab49bc163f6f821 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Fri, 13 Jun 2025 18:58:57 -0400
Subject: [PATCH 0391/1334] bcachefs: fsck: fix extent past end of inode repair

Fix the case where we're deleting in a different snapshot and need to
emit a whiteout - that requires a regular BTREE_ITER_filter_snapshots
iterator.

Also, only delete the part of the extent that extents past i_size.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/fsck.c | 31 ++++++++++++++++++++++++++-----
 1 file changed, 26 insertions(+), 5 deletions(-)

diff --git a/fs/bcachefs/fsck.c b/fs/bcachefs/fsck.c
index 28ca07c0e029..48810a8e5d4b 100644
--- a/fs/bcachefs/fsck.c
+++ b/fs/bcachefs/fsck.c
@@ -1820,18 +1820,39 @@ static int check_extent(struct btree_trans *trans, struct btree_iter *iter,
 			    !key_visible_in_snapshot(c, s, i->inode.bi_snapshot, k.k->p.snapshot))
 				continue;
 
-			if (fsck_err_on(k.k->p.offset > round_up(i->inode.bi_size, block_bytes(c)) >> 9 &&
+			u64 last_block = round_up(i->inode.bi_size, block_bytes(c)) >> 9;
+
+			if (fsck_err_on(k.k->p.offset > last_block &&
 					!bkey_extent_is_reservation(k),
 					trans, extent_past_end_of_inode,
 					"extent type past end of inode %llu:%u, i_size %llu\n%s",
 					i->inode.bi_inum, i->inode.bi_snapshot, i->inode.bi_size,
 					(bch2_bkey_val_to_text(&buf, c, k), buf.buf))) {
-				struct btree_iter iter2;
+				struct bkey_i *whiteout = bch2_trans_kmalloc(trans, sizeof(*whiteout));
+				ret = PTR_ERR_OR_ZERO(whiteout);
+				if (ret)
+					goto err;
 
-				bch2_trans_copy_iter(trans, &iter2, iter);
-				bch2_btree_iter_set_snapshot(trans, &iter2, i->inode.bi_snapshot);
+				bkey_init(&whiteout->k);
+				whiteout->k.p = SPOS(k.k->p.inode,
+						     last_block,
+						     i->inode.bi_snapshot);
+				bch2_key_resize(&whiteout->k,
+						min(KEY_SIZE_MAX & (~0 << c->block_bits),
+						    U64_MAX - whiteout->k.p.offset));
+
+
+				/*
+				 * Need a normal (not BTREE_ITER_all_snapshots)
+				 * iterator, if we're deleting in a different
+				 * snapshot and need to emit a whiteout
+				 */
+				struct btree_iter iter2;
+				bch2_trans_iter_init(trans, &iter2, BTREE_ID_extents,
+						     bkey_start_pos(&whiteout->k),
+						     BTREE_ITER_intent);
 				ret =   bch2_btree_iter_traverse(trans, &iter2) ?:
-					bch2_btree_delete_at(trans, &iter2,
+					bch2_trans_update(trans, &iter2, whiteout,
 						BTREE_UPDATE_internal_snapshot_node);
 				bch2_trans_iter_exit(trans, &iter2);
 				if (ret)

From a7137b1825b535eb7258b25beeb0d5425e0037d2 Mon Sep 17 00:00:00 2001
From: Tzung-Bi Shih <tzungbi@kernel.org>
Date: Thu, 12 Jun 2025 08:30:23 +0000
Subject: [PATCH 0392/1334] drm/i915/pmu: Fix build error with GCOV and AutoFDO
 enabled

i915_pmu.c may fail to build with GCOV and AutoFDO enabled.

../drivers/gpu/drm/i915/i915_pmu.c:116:3: error: call to '__compiletime_assert_487' declared with 'error' attribute: BUILD_BUG_ON failed: bit > BITS_PER_TYPE(typeof_member(struct i915_pmu, enable)) - 1
  116 |                 BUILD_BUG_ON(bit >
      |                 ^

Here is a way to reproduce the issue:
$ git checkout v6.15
$ mkdir build
$ ./scripts/kconfig/merge_config.sh -O build -n -m <(cat <<EOF
CONFIG_DRM=y
CONFIG_PCI=y
CONFIG_DRM_I915=y

CONFIG_PERF_EVENTS=y

CONFIG_DEBUG_FS=y
CONFIG_GCOV_KERNEL=y
CONFIG_GCOV_PROFILE_ALL=y

CONFIG_AUTOFDO_CLANG=y
EOF
)
$ PATH=${PATH}:${HOME}/llvm-20.1.5-x86_64/bin make LLVM=1 O=build \
       olddefconfig
$ PATH=${PATH}:${HOME}/llvm-20.1.5-x86_64/bin make LLVM=1 O=build \
       CLANG_AUTOFDO_PROFILE=...PATH_TO_SOME_AFDO_PROFILE... \
       drivers/gpu/drm/i915/i915_pmu.o

Although not super sure what happened, by reviewing the code, it should
depend on `__builtin_constant_p(bit)` directly instead of assuming
`__builtin_constant_p(config)` makes `bit` a builtin constant.

Also fix a nit, to reuse the `bit` local variable.

Fixes: a644fde77ff7 ("drm/i915/pmu: Change bitmask of enabled events to u32")
Reviewed-by: Nathan Chancellor <nathan@kernel.org>
Signed-off-by: Tzung-Bi Shih <tzungbi@kernel.org>
Signed-off-by: Tvrtko Ursulin <tursulin@ursulin.net>
Link: https://lore.kernel.org/r/20250612083023.562585-1-tzungbi@kernel.org
(cherry picked from commit 686d773186bf72b739bab7e12eb8665d914676ee)
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
---
 drivers/gpu/drm/i915/i915_pmu.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_pmu.c b/drivers/gpu/drm/i915/i915_pmu.c
index e5a188ce3185..990bfaba3ce4 100644
--- a/drivers/gpu/drm/i915/i915_pmu.c
+++ b/drivers/gpu/drm/i915/i915_pmu.c
@@ -112,7 +112,7 @@ static u32 config_mask(const u64 config)
 {
 	unsigned int bit = config_bit(config);
 
-	if (__builtin_constant_p(config))
+	if (__builtin_constant_p(bit))
 		BUILD_BUG_ON(bit >
 			     BITS_PER_TYPE(typeof_member(struct i915_pmu,
 							 enable)) - 1);
@@ -121,7 +121,7 @@ static u32 config_mask(const u64 config)
 			     BITS_PER_TYPE(typeof_member(struct i915_pmu,
 							 enable)) - 1);
 
-	return BIT(config_bit(config));
+	return BIT(bit);
 }
 
 static bool is_engine_event(struct perf_event *event)

From c464ce6af332e7c802c36cd337cacf81db05400c Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= <ville.syrjala@linux.intel.com>
Date: Fri, 14 Mar 2025 17:01:34 +0200
Subject: [PATCH 0393/1334] drm/i915/dsi: Fix off by one in
 BXT_MIPI_TRANS_VTOTAL
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

BXT_MIPI_TRANS_VTOTAL must be programmed with vtotal-1
instead of vtotal. Make it so.

Cc: stable@vger.kernel.org
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250314150136.22564-1-ville.syrjala@linux.intel.com
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
(cherry picked from commit 7b3685c9b38c3097f465efec8b24dbed63258cf6)
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
---
 drivers/gpu/drm/i915/display/vlv_dsi.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/vlv_dsi.c b/drivers/gpu/drm/i915/display/vlv_dsi.c
index 346737f15fa9..21c1e10caf68 100644
--- a/drivers/gpu/drm/i915/display/vlv_dsi.c
+++ b/drivers/gpu/drm/i915/display/vlv_dsi.c
@@ -1056,7 +1056,7 @@ static void bxt_dsi_get_pipe_config(struct intel_encoder *encoder,
 				              BXT_MIPI_TRANS_VACTIVE(port));
 	adjusted_mode->crtc_vtotal =
 				intel_de_read(display,
-				              BXT_MIPI_TRANS_VTOTAL(port));
+				              BXT_MIPI_TRANS_VTOTAL(port)) + 1;
 
 	hactive = adjusted_mode->crtc_hdisplay;
 	hfp = intel_de_read(display, MIPI_HFP_COUNT(display, port));
@@ -1260,7 +1260,7 @@ static void set_dsi_timings(struct intel_encoder *encoder,
 			intel_de_write(display, BXT_MIPI_TRANS_VACTIVE(port),
 				       adjusted_mode->crtc_vdisplay);
 			intel_de_write(display, BXT_MIPI_TRANS_VTOTAL(port),
-				       adjusted_mode->crtc_vtotal);
+				       adjusted_mode->crtc_vtotal - 1);
 		}
 
 		intel_de_write(display, MIPI_HACTIVE_AREA_COUNT(display, port),

From e6382fcf989074566bb9a54bbd3c514d7bb99397 Mon Sep 17 00:00:00 2001
From: Vivian Wang <wangruikang@iscas.ac.cn>
Date: Fri, 13 Jun 2025 17:25:33 +0800
Subject: [PATCH 0394/1334] gpio: spacemit: Add missing MODULE_DEVICE_TABLE

The gpio-spacemit-k1 driver can be compiled as a module. Add missing
MODULE_DEVICE_TABLE so it can be matched by modalias and automatically
loaded by udev.

Fixes: d00553240ef8 ("gpio: spacemit: add support for K1 SoC")
Signed-off-by: Vivian Wang <wangruikang@iscas.ac.cn>
Reviewed-by: Yixun Lan <dlan@gentoo.org>
Link: https://lore.kernel.org/r/20250613-k1-gpio-of-table-v1-1-9015da8fdfdb@iscas.ac.cn
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
---
 drivers/gpio/gpio-spacemit-k1.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpio/gpio-spacemit-k1.c b/drivers/gpio/gpio-spacemit-k1.c
index f027066365ff..3cc75c701ec4 100644
--- a/drivers/gpio/gpio-spacemit-k1.c
+++ b/drivers/gpio/gpio-spacemit-k1.c
@@ -278,6 +278,7 @@ static const struct of_device_id spacemit_gpio_dt_ids[] = {
 	{ .compatible = "spacemit,k1-gpio" },
 	{ /* sentinel */ }
 };
+MODULE_DEVICE_TABLE(of, spacemit_gpio_dt_ids);
 
 static struct platform_driver spacemit_gpio_driver = {
 	.probe		= spacemit_gpio_probe,

From dd2d6b7f6f519d078a866a36a625b0297d81c5bc Mon Sep 17 00:00:00 2001
From: Luis Henriques <luis@igalia.com>
Date: Fri, 13 Jun 2025 11:11:11 +0100
Subject: [PATCH 0395/1334] fs: drop assert in file_seek_cur_needs_f_lock

The assert in function file_seek_cur_needs_f_lock() can be triggered very
easily because there are many users of vfs_llseek() (such as overlayfs)
that do their custom locking around llseek instead of relying on
fdget_pos(). Just drop the overzealous assertion.

Fixes: da06e3c51794 ("fs: don't needlessly acquire f_lock")
Suggested-by: Jan Kara <jack@suse.cz>
Suggested-by: Mateusz Guzik <mjguzik@gmail.com>
Signed-off-by: Luis Henriques <luis@igalia.com>
Link: https://lore.kernel.org/20250613101111.17716-1-luis@igalia.com
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/file.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/fs/file.c b/fs/file.c
index 3a3146664cf3..b6db031545e6 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -1198,8 +1198,12 @@ bool file_seek_cur_needs_f_lock(struct file *file)
 	if (!(file->f_mode & FMODE_ATOMIC_POS) && !file->f_op->iterate_shared)
 		return false;
 
-	VFS_WARN_ON_ONCE((file_count(file) > 1) &&
-			 !mutex_is_locked(&file->f_pos_lock));
+	/*
+	 * Note that we are not guaranteed to be called after fdget_pos() on
+	 * this file obj, in which case the caller is expected to provide the
+	 * appropriate locking.
+	 */
+
 	return true;
 }
 

From b0f77d301eb2b4e1fc816f33ade8519ae7f894f4 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 5 Jun 2025 08:16:27 +0200
Subject: [PATCH 0396/1334] xfs: check for shutdown before going to sleep in
 xfs_select_zone

Ensure the file system hasn't been shut down before waiting for a free
zone to become available, because that won't happen on a shut down
file system.  Without this processes can occasionally get stuck in
the allocator wait loop when racing with a file system shutdown.
This sporadically happens when running generic/388 or generic/475.

Fixes: 4e4d52075577 ("xfs: add the zoned space allocator")
Reported-by: Shinichiro Kawasaki <shinichiro.kawasaki@wdc.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Hans Holmberg <hans.holmberg@wdc.com>
Tested-by: Shin'ichiro Kawasaki <shinichiro.kawasaki@wdc.com>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 fs/xfs/xfs_zone_alloc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/xfs/xfs_zone_alloc.c b/fs/xfs/xfs_zone_alloc.c
index 80add26c0111..0de6f64b3169 100644
--- a/fs/xfs/xfs_zone_alloc.c
+++ b/fs/xfs/xfs_zone_alloc.c
@@ -727,7 +727,7 @@ xfs_select_zone(
 	for (;;) {
 		prepare_to_wait(&zi->zi_zone_wait, &wait, TASK_UNINTERRUPTIBLE);
 		oz = xfs_select_zone_nowait(mp, write_hint, pack_tight);
-		if (oz)
+		if (oz || xfs_is_shutdown(mp))
 			break;
 		schedule();
 	}

From a593c89ac5a417605b165cbc9768b3663ab4d8ad Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 5 Jun 2025 08:16:28 +0200
Subject: [PATCH 0397/1334] xfs: remove NULL pointer checks in
 xfs_mru_cache_insert

Remove the check for a NULL mru or mru->list in xfs_mru_cache_insert
as this API misused lead to a direct NULL pointer dereference on first
use and is not user triggerable.  As a smatch run by Dan points out
with the recent cleanup it would otherwise try to free the object we
just determined to be NULL for this impossible to reach case.

Fixes: 70b95cb86513 ("xfs: free the item in xfs_mru_cache_insert on failure")
Reported-by: Dan Carpenter <dan.carpenter@linaro.org>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Hans Holmberg <hans.holmberg@wdc.com>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 fs/xfs/xfs_mru_cache.c | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/fs/xfs/xfs_mru_cache.c b/fs/xfs/xfs_mru_cache.c
index 08443ceec329..c95401de8397 100644
--- a/fs/xfs/xfs_mru_cache.c
+++ b/fs/xfs/xfs_mru_cache.c
@@ -425,10 +425,6 @@ xfs_mru_cache_insert(
 {
 	int			error = -EINVAL;
 
-	ASSERT(mru && mru->lists);
-	if (!mru || !mru->lists)
-		goto out_free;
-
 	error = -ENOMEM;
 	if (radix_tree_preload(GFP_KERNEL))
 		goto out_free;

From df3b7e2b56d271f93e2d1f395c13235a1a277639 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 5 Jun 2025 08:16:29 +0200
Subject: [PATCH 0398/1334] xfs: use xfs_readonly_buftarg in xfs_remount_rw

Use xfs_readonly_buftarg instead of open coding it.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Hans Holmberg <hans.holmberg@wdc.com>
Reviewed-by: John Garry <john.g.garry@oracle.com>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 fs/xfs/xfs_super.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index 0bc4b5489078..bb0a82635a77 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -2020,14 +2020,13 @@ xfs_remount_rw(
 	int error;
 
 	if (mp->m_logdev_targp && mp->m_logdev_targp != mp->m_ddev_targp &&
-	    bdev_read_only(mp->m_logdev_targp->bt_bdev)) {
+	    xfs_readonly_buftarg(mp->m_logdev_targp)) {
 		xfs_warn(mp,
 			"ro->rw transition prohibited by read-only logdev");
 		return -EACCES;
 	}
 
-	if (mp->m_rtdev_targp &&
-	    bdev_read_only(mp->m_rtdev_targp->bt_bdev)) {
+	if (mp->m_rtdev_targp && xfs_readonly_buftarg(mp->m_rtdev_targp)) {
 		xfs_warn(mp,
 			"ro->rw transition prohibited by read-only rtdev");
 		return -EACCES;

From 0989dfa61f438150c4f1110604ba0787856fe8b0 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 5 Jun 2025 08:16:30 +0200
Subject: [PATCH 0399/1334] xfs: move xfs_submit_zoned_bio a bit

Commit f3e2e53823b9 ("xfs: add inode to zone caching for data placement")
add the new code right between xfs_submit_zoned_bio and
xfs_zone_alloc_and_submit which implement the main zoned write path.
Move xfs_submit_zoned_bio down to keep it together again.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>
Reviewed-by: Hans Holmberg <hans.holmberg@wdc.com>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 fs/xfs/xfs_zone_alloc.c | 40 ++++++++++++++++++++--------------------
 1 file changed, 20 insertions(+), 20 deletions(-)

diff --git a/fs/xfs/xfs_zone_alloc.c b/fs/xfs/xfs_zone_alloc.c
index 0de6f64b3169..01315ed75502 100644
--- a/fs/xfs/xfs_zone_alloc.c
+++ b/fs/xfs/xfs_zone_alloc.c
@@ -777,26 +777,6 @@ xfs_mark_rtg_boundary(
 		ioend->io_flags |= IOMAP_IOEND_BOUNDARY;
 }
 
-static void
-xfs_submit_zoned_bio(
-	struct iomap_ioend	*ioend,
-	struct xfs_open_zone	*oz,
-	bool			is_seq)
-{
-	ioend->io_bio.bi_iter.bi_sector = ioend->io_sector;
-	ioend->io_private = oz;
-	atomic_inc(&oz->oz_ref); /* for xfs_zoned_end_io */
-
-	if (is_seq) {
-		ioend->io_bio.bi_opf &= ~REQ_OP_WRITE;
-		ioend->io_bio.bi_opf |= REQ_OP_ZONE_APPEND;
-	} else {
-		xfs_mark_rtg_boundary(ioend);
-	}
-
-	submit_bio(&ioend->io_bio);
-}
-
 /*
  * Cache the last zone written to for an inode so that it is considered first
  * for subsequent writes.
@@ -891,6 +871,26 @@ xfs_zone_cache_create_association(
 	xfs_mru_cache_insert(mp->m_zone_cache, ip->i_ino, &item->mru);
 }
 
+static void
+xfs_submit_zoned_bio(
+	struct iomap_ioend	*ioend,
+	struct xfs_open_zone	*oz,
+	bool			is_seq)
+{
+	ioend->io_bio.bi_iter.bi_sector = ioend->io_sector;
+	ioend->io_private = oz;
+	atomic_inc(&oz->oz_ref); /* for xfs_zoned_end_io */
+
+	if (is_seq) {
+		ioend->io_bio.bi_opf &= ~REQ_OP_WRITE;
+		ioend->io_bio.bi_opf |= REQ_OP_ZONE_APPEND;
+	} else {
+		xfs_mark_rtg_boundary(ioend);
+	}
+
+	submit_bio(&ioend->io_bio);
+}
+
 void
 xfs_zone_alloc_and_submit(
 	struct iomap_ioend	*ioend,

From 19fa6e493a933c095f164230d3393d504216e052 Mon Sep 17 00:00:00 2001
From: Markus Elfring <elfring@users.sourceforge.net>
Date: Tue, 10 Jun 2025 14:50:07 +0200
Subject: [PATCH 0400/1334] xfs: Improve error handling in
 xfs_mru_cache_create()

Simplify error handling in this function implementation.

* Delete unnecessary pointer checks and variable assignments.

* Omit a redundant function call.

This issue was detected by using the Coccinelle software.

Signed-off-by: Markus Elfring <elfring@users.sourceforge.net>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 fs/xfs/xfs_mru_cache.c | 15 ++++-----------
 1 file changed, 4 insertions(+), 11 deletions(-)

diff --git a/fs/xfs/xfs_mru_cache.c b/fs/xfs/xfs_mru_cache.c
index c95401de8397..866c71d9fbae 100644
--- a/fs/xfs/xfs_mru_cache.c
+++ b/fs/xfs/xfs_mru_cache.c
@@ -320,7 +320,7 @@ xfs_mru_cache_create(
 	xfs_mru_cache_free_func_t free_func)
 {
 	struct xfs_mru_cache	*mru = NULL;
-	int			err = 0, grp;
+	int			grp;
 	unsigned int		grp_time;
 
 	if (mrup)
@@ -341,8 +341,8 @@ xfs_mru_cache_create(
 	mru->lists = kzalloc(mru->grp_count * sizeof(*mru->lists),
 				GFP_KERNEL | __GFP_NOFAIL);
 	if (!mru->lists) {
-		err = -ENOMEM;
-		goto exit;
+		kfree(mru);
+		return -ENOMEM;
 	}
 
 	for (grp = 0; grp < mru->grp_count; grp++)
@@ -361,14 +361,7 @@ xfs_mru_cache_create(
 	mru->free_func = free_func;
 	mru->data = data;
 	*mrup = mru;
-
-exit:
-	if (err && mru && mru->lists)
-		kfree(mru->lists);
-	if (err && mru)
-		kfree(mru);
-
-	return err;
+	return 0;
 }
 
 /*

From db44d088a5ab030b741a3adf2e7b181a8a6dcfbe Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <djwong@kernel.org>
Date: Thu, 12 Jun 2025 10:51:12 -0700
Subject: [PATCH 0401/1334] xfs: actually use the xfs_growfs_check_rtgeom
 tracepoint

We created a new tracepoint but forgot to put it in.  Fix that.

Cc: rostedt@goodmis.org
Cc: stable@vger.kernel.org # v6.14
Fixes: 59a57acbce282d ("xfs: check that the rtrmapbt maxlevels doesn't increase when growing fs")
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>
Reported-by: Steven Rostedt <rostedt@goodmis.org>
Closes: https://lore.kernel.org/all/20250612131021.114e6ec8@batman.local.home/
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 fs/xfs/xfs_rtalloc.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c
index 6484c596ecea..736eb0924573 100644
--- a/fs/xfs/xfs_rtalloc.c
+++ b/fs/xfs/xfs_rtalloc.c
@@ -1259,6 +1259,8 @@ xfs_growfs_check_rtgeom(
 
 	kfree(nmp);
 
+	trace_xfs_growfs_check_rtgeom(mp, min_logfsbs);
+
 	if (min_logfsbs > mp->m_sb.sb_logblocks)
 		return -EINVAL;
 

From b8b8663ac82a2595a0922d30014f60c5547084de Mon Sep 17 00:00:00 2001
From: Danilo Krummrich <dakr@kernel.org>
Date: Sat, 14 Jun 2025 11:20:23 +0200
Subject: [PATCH 0402/1334] mailmap: add entry for Danilo Krummrich

Add an entry to remap my Red Hat address.

Link: https://lore.kernel.org/r/20250614092054.161658-1-dakr@kernel.org
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
---
 .mailmap | 1 +
 1 file changed, 1 insertion(+)

diff --git a/.mailmap b/.mailmap
index c8a21d72241f..8b0aac19efcd 100644
--- a/.mailmap
+++ b/.mailmap
@@ -197,6 +197,7 @@ Daniel Borkmann <daniel@iogearbox.net> <daniel.borkmann@tik.ee.ethz.ch>
 Daniel Borkmann <daniel@iogearbox.net> <dborkmann@redhat.com>
 Daniel Borkmann <daniel@iogearbox.net> <dborkman@redhat.com>
 Daniel Borkmann <daniel@iogearbox.net> <dxchgb@gmail.com>
+Danilo Krummrich <dakr@kernel.org> <dakr@redhat.com>
 David Brownell <david-b@pacbell.net>
 David Collins <quic_collinsd@quicinc.com> <collinsd@codeaurora.org>
 David Heidelberg <david@ixit.cz> <d.okias@gmail.com>

From b081d8564e4a396843a78788476fdcbf70efed06 Mon Sep 17 00:00:00 2001
From: Laurentiu Mihalcea <laurentiu.mihalcea@nxp.com>
Date: Fri, 13 Jun 2025 15:43:10 -0400
Subject: [PATCH 0403/1334] ASoC: SOF: imx8: add core shutdown operation for
 imx8/imx8x

Currently, the DSP core from i.MX8QM/i.MX8QXP is able to operate while the
firmware image is being loaded. Because of this, the DSP may change the
content of the firmware data just after it was loaded, thus leading to the
data having unexpected values when the DSP is reset (via run()).

Fix this by implementing the core_shutdown() operation that will put the
DSP in stall during suspend(). The stall will be removed during the run()
opertion, thus guaranteeing that the DSP core will not be able to run
while the firmware image is being loaded.

Signed-off-by: Laurentiu Mihalcea <laurentiu.mihalcea@nxp.com>
Reviewed-by: Daniel Baluta <daniel.baluta@nxp.com>
Link: https://patch.msgid.link/20250613194310.1128733-1-laurentiumihalcea111@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/sof/imx/imx8.c | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

diff --git a/sound/soc/sof/imx/imx8.c b/sound/soc/sof/imx/imx8.c
index a40a8047873e..b73dd91bd529 100644
--- a/sound/soc/sof/imx/imx8.c
+++ b/sound/soc/sof/imx/imx8.c
@@ -40,6 +40,19 @@ struct imx8m_chip_data {
 	struct reset_control *run_stall;
 };
 
+static int imx8_shutdown(struct snd_sof_dev *sdev)
+{
+	/*
+	 * Force the DSP to stall. After the firmware image is loaded,
+	 * the stall will be removed during run() by a matching
+	 * imx_sc_pm_cpu_start() call.
+	 */
+	imx_sc_pm_cpu_start(get_chip_pdata(sdev), IMX_SC_R_DSP, false,
+			    RESET_VECTOR_VADDR);
+
+	return 0;
+}
+
 /*
  * DSP control.
  */
@@ -281,11 +294,13 @@ static int imx8_ops_init(struct snd_sof_dev *sdev)
 static const struct imx_chip_ops imx8_chip_ops = {
 	.probe = imx8_probe,
 	.core_kick = imx8_run,
+	.core_shutdown = imx8_shutdown,
 };
 
 static const struct imx_chip_ops imx8x_chip_ops = {
 	.probe = imx8_probe,
 	.core_kick = imx8x_run,
+	.core_shutdown = imx8_shutdown,
 };
 
 static const struct imx_chip_ops imx8m_chip_ops = {

From 8acfb165a492251a08a22a4fa6497a131e8c2609 Mon Sep 17 00:00:00 2001
From: Heiko Stuebner <heiko@sntech.de>
Date: Fri, 6 Jun 2025 21:04:18 +0200
Subject: [PATCH 0404/1334] regulator: fan53555: add enable_time support and
 soft-start times

The datasheets for all the fan53555 variants (and clones using the same
interface) define so called soft start times, from enabling the regulator
until at least some percentage of the output (i.e. 92% for the rk860x
types) are available.

The regulator framework supports this with the enable_time property
but currently the fan53555 driver does not define enable_times for any
variant.

I ran into a problem with this while testing the new driver for the
Rockchip NPUs (rocket), which does runtime-pm including disabling and
enabling a rk8602 as needed. When reenabling the regulator while running
a load, fatal hangs could be observed while enabling the associated
power-domain, which the regulator supplies.

Experimentally setting the regulator to always-on, made the issue
disappear, leading to the missing delay to let power stabilize.
And as expected, setting the enable-time to a non-zero value
according to the datasheet also resolved the regulator-issue.

The datasheets in nearly all cases only specify "typical" values,
except for the fan53555 type 08. There both a typical and maximum
value are listed - 40uS apart.

For all typical values I've added 100uS to be on the safe side.
Individual details for the relevant regulators below:

- fan53526:
  The datasheet for all variants lists a typical value of 150uS, so
  make that 250uS with safety margin.
- fan53555:
  types 08 and 18 (unsupported) are given a typical enable time of 135uS
  but also a maximum of 175uS so use that value. All the other types only
  have a typical time in the datasheet of 300uS, so give a bit margin by
  setting it to 400uS.
- rk8600 + rk8602:
  Datasheet reports a typical value of 260us, so use 360uS to be safe.
- syr82x + syr83x:
  All datasheets report typical soft-start values of 300uS for these
  regulators, so use 400uS.
- tcs452x:
  Datasheet sadly does not report a soft-start time, so I've not set
  an enable-time

Signed-off-by: Heiko Stuebner <heiko@sntech.de>
Link: https://patch.msgid.link/20250606190418.478633-1-heiko@sntech.de
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/regulator/fan53555.c | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/drivers/regulator/fan53555.c b/drivers/regulator/fan53555.c
index bd9447dac596..c282236959b1 100644
--- a/drivers/regulator/fan53555.c
+++ b/drivers/regulator/fan53555.c
@@ -147,6 +147,7 @@ struct fan53555_device_info {
 	unsigned int slew_mask;
 	const unsigned int *ramp_delay_table;
 	unsigned int n_ramp_values;
+	unsigned int enable_time;
 	unsigned int slew_rate;
 };
 
@@ -282,6 +283,7 @@ static int fan53526_voltages_setup_fairchild(struct fan53555_device_info *di)
 	di->slew_mask = CTL_SLEW_MASK;
 	di->ramp_delay_table = slew_rates;
 	di->n_ramp_values = ARRAY_SIZE(slew_rates);
+	di->enable_time = 250;
 	di->vsel_count = FAN53526_NVOLTAGES;
 
 	return 0;
@@ -296,10 +298,12 @@ static int fan53555_voltages_setup_fairchild(struct fan53555_device_info *di)
 		case FAN53555_CHIP_REV_00:
 			di->vsel_min = 600000;
 			di->vsel_step = 10000;
+			di->enable_time = 400;
 			break;
 		case FAN53555_CHIP_REV_13:
 			di->vsel_min = 800000;
 			di->vsel_step = 10000;
+			di->enable_time = 400;
 			break;
 		default:
 			dev_err(di->dev,
@@ -311,13 +315,19 @@ static int fan53555_voltages_setup_fairchild(struct fan53555_device_info *di)
 	case FAN53555_CHIP_ID_01:
 	case FAN53555_CHIP_ID_03:
 	case FAN53555_CHIP_ID_05:
+		di->vsel_min = 600000;
+		di->vsel_step = 10000;
+		di->enable_time = 400;
+		break;
 	case FAN53555_CHIP_ID_08:
 		di->vsel_min = 600000;
 		di->vsel_step = 10000;
+		di->enable_time = 175;
 		break;
 	case FAN53555_CHIP_ID_04:
 		di->vsel_min = 603000;
 		di->vsel_step = 12826;
+		di->enable_time = 400;
 		break;
 	default:
 		dev_err(di->dev,
@@ -350,6 +360,7 @@ static int fan53555_voltages_setup_rockchip(struct fan53555_device_info *di)
 	di->slew_mask = CTL_SLEW_MASK;
 	di->ramp_delay_table = slew_rates;
 	di->n_ramp_values = ARRAY_SIZE(slew_rates);
+	di->enable_time = 360;
 	di->vsel_count = FAN53555_NVOLTAGES;
 
 	return 0;
@@ -372,6 +383,7 @@ static int rk8602_voltages_setup_rockchip(struct fan53555_device_info *di)
 	di->slew_mask = CTL_SLEW_MASK;
 	di->ramp_delay_table = slew_rates;
 	di->n_ramp_values = ARRAY_SIZE(slew_rates);
+	di->enable_time = 360;
 	di->vsel_count = RK8602_NVOLTAGES;
 
 	return 0;
@@ -395,6 +407,7 @@ static int fan53555_voltages_setup_silergy(struct fan53555_device_info *di)
 	di->slew_mask = CTL_SLEW_MASK;
 	di->ramp_delay_table = slew_rates;
 	di->n_ramp_values = ARRAY_SIZE(slew_rates);
+	di->enable_time = 400;
 	di->vsel_count = FAN53555_NVOLTAGES;
 
 	return 0;
@@ -594,6 +607,7 @@ static int fan53555_regulator_register(struct fan53555_device_info *di,
 	rdesc->ramp_mask = di->slew_mask;
 	rdesc->ramp_delay_table = di->ramp_delay_table;
 	rdesc->n_ramp_values = di->n_ramp_values;
+	rdesc->enable_time = di->enable_time;
 	rdesc->owner = THIS_MODULE;
 
 	rdev = devm_regulator_register(di->dev, &di->desc, config);

From 14c9ede9ca4cd078ad76a6ab9617b81074eb58bf Mon Sep 17 00:00:00 2001
From: Gui-Dong Han <hanguidong02@gmail.com>
Date: Fri, 6 Jun 2025 07:16:40 +0000
Subject: [PATCH 0405/1334] hwmon: (ftsteutates) Fix TOCTOU race in fts_read()

In the fts_read() function, when handling hwmon_pwm_auto_channels_temp,
the code accesses the shared variable data->fan_source[channel] twice
without holding any locks. It is first checked against
FTS_FAN_SOURCE_INVALID, and if the check passes, it is read again
when used as an argument to the BIT() macro.

This creates a Time-of-Check to Time-of-Use (TOCTOU) race condition.
Another thread executing fts_update_device() can modify the value of
data->fan_source[channel] between the check and its use. If the value
is changed to FTS_FAN_SOURCE_INVALID (0xff) during this window, the
BIT() macro will be called with a large shift value (BIT(255)).
A bit shift by a value greater than or equal to the type width is
undefined behavior and can lead to a crash or incorrect values being
returned to userspace.

Fix this by reading data->fan_source[channel] into a local variable
once, eliminating the race condition. Additionally, add a bounds check
to ensure the value is less than BITS_PER_LONG before passing it to
the BIT() macro, making the code more robust against undefined behavior.

This possible bug was found by an experimental static analysis tool
developed by our team.

Fixes: 1c5759d8ce05 ("hwmon: (ftsteutates) Replace fanX_source with pwmX_auto_channels_temp")
Cc: stable@vger.kernel.org
Signed-off-by: Gui-Dong Han <hanguidong02@gmail.com>
Link: https://lore.kernel.org/r/20250606071640.501262-1-hanguidong02@gmail.com
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/hwmon/ftsteutates.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/drivers/hwmon/ftsteutates.c b/drivers/hwmon/ftsteutates.c
index a3a07662e491..8aeec16a7a90 100644
--- a/drivers/hwmon/ftsteutates.c
+++ b/drivers/hwmon/ftsteutates.c
@@ -423,13 +423,16 @@ static int fts_read(struct device *dev, enum hwmon_sensor_types type, u32 attr,
 		break;
 	case hwmon_pwm:
 		switch (attr) {
-		case hwmon_pwm_auto_channels_temp:
-			if (data->fan_source[channel] == FTS_FAN_SOURCE_INVALID)
+		case hwmon_pwm_auto_channels_temp: {
+			u8 fan_source = data->fan_source[channel];
+
+			if (fan_source == FTS_FAN_SOURCE_INVALID || fan_source >= BITS_PER_LONG)
 				*val = 0;
 			else
-				*val = BIT(data->fan_source[channel]);
+				*val = BIT(fan_source);
 
 			return 0;
+		}
 		default:
 			break;
 		}

From 744c2fe950e936c4d62430de899d6253424200ed Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 10 Jun 2025 11:23:06 +0200
Subject: [PATCH 0406/1334] hwmon: (occ) Rework attribute registration for
 stack usage

clang produces an output with excessive stack usage when building the
occ_setup_sensor_attrs() function, apparently the result of having
a lot of struct literals and building with the -fno-strict-overflow
option that leads clang to skip some optimization in case the 'attr'
pointer overruns:

drivers/hwmon/occ/common.c:775:12: error: stack frame size (1392) exceeds limit (1280) in 'occ_setup_sensor_attrs' [-Werror,-Wframe-larger-than]

Replace the custom macros for initializing the attributes with a
simpler function call that does not run into this corner case.

Link: https://godbolt.org/z/Wf1Yx76a5
Fixes: 54076cb3b5ff ("hwmon (occ): Add sensor attributes and register hwmon device")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Link: https://lore.kernel.org/r/20250610092315.2640039-1-arnd@kernel.org
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/hwmon/occ/common.c | 210 +++++++++++++++----------------------
 1 file changed, 84 insertions(+), 126 deletions(-)

diff --git a/drivers/hwmon/occ/common.c b/drivers/hwmon/occ/common.c
index 9486db249c64..9029ad53790b 100644
--- a/drivers/hwmon/occ/common.c
+++ b/drivers/hwmon/occ/common.c
@@ -747,28 +747,29 @@ static ssize_t occ_show_extended(struct device *dev,
 }
 
 /*
- * Some helper macros to make it easier to define an occ_attribute. Since these
- * are dynamically allocated, we shouldn't use the existing kernel macros which
+ * A helper to make it easier to define an occ_attribute. Since these
+ * are dynamically allocated, we cannot use the existing kernel macros which
  * stringify the name argument.
  */
-#define ATTR_OCC(_name, _mode, _show, _store) {				\
-	.attr	= {							\
-		.name = _name,						\
-		.mode = VERIFY_OCTAL_PERMISSIONS(_mode),		\
-	},								\
-	.show	= _show,						\
-	.store	= _store,						\
-}
+static void occ_init_attribute(struct occ_attribute *attr, int mode,
+	ssize_t (*show)(struct device *dev, struct device_attribute *attr, char *buf),
+	ssize_t (*store)(struct device *dev, struct device_attribute *attr,
+				   const char *buf, size_t count),
+	int nr, int index, const char *fmt, ...)
+{
+	va_list args;
 
-#define SENSOR_ATTR_OCC(_name, _mode, _show, _store, _nr, _index) {	\
-	.dev_attr	= ATTR_OCC(_name, _mode, _show, _store),	\
-	.index		= _index,					\
-	.nr		= _nr,						\
-}
+	va_start(args, fmt);
+	vsnprintf(attr->name, sizeof(attr->name), fmt, args);
+	va_end(args);
 
-#define OCC_INIT_ATTR(_name, _mode, _show, _store, _nr, _index)		\
-	((struct sensor_device_attribute_2)				\
-		SENSOR_ATTR_OCC(_name, _mode, _show, _store, _nr, _index))
+	attr->sensor.dev_attr.attr.name = attr->name;
+	attr->sensor.dev_attr.attr.mode = mode;
+	attr->sensor.dev_attr.show = show;
+	attr->sensor.dev_attr.store = store;
+	attr->sensor.index = index;
+	attr->sensor.nr = nr;
+}
 
 /*
  * Allocate and instatiate sensor_device_attribute_2s. It's most efficient to
@@ -855,14 +856,15 @@ static int occ_setup_sensor_attrs(struct occ *occ)
 		sensors->extended.num_sensors = 0;
 	}
 
-	occ->attrs = devm_kzalloc(dev, sizeof(*occ->attrs) * num_attrs,
+	occ->attrs = devm_kcalloc(dev, num_attrs, sizeof(*occ->attrs),
 				  GFP_KERNEL);
 	if (!occ->attrs)
 		return -ENOMEM;
 
 	/* null-terminated list */
-	occ->group.attrs = devm_kzalloc(dev, sizeof(*occ->group.attrs) *
-					num_attrs + 1, GFP_KERNEL);
+	occ->group.attrs = devm_kcalloc(dev, num_attrs + 1,
+					sizeof(*occ->group.attrs),
+					GFP_KERNEL);
 	if (!occ->group.attrs)
 		return -ENOMEM;
 
@@ -872,43 +874,33 @@ static int occ_setup_sensor_attrs(struct occ *occ)
 		s = i + 1;
 		temp = ((struct temp_sensor_2 *)sensors->temp.data) + i;
 
-		snprintf(attr->name, sizeof(attr->name), "temp%d_label", s);
-		attr->sensor = OCC_INIT_ATTR(attr->name, 0444, show_temp, NULL,
-					     0, i);
+		occ_init_attribute(attr, 0444, show_temp, NULL,
+				   0, i, "temp%d_label", s);
 		attr++;
 
 		if (sensors->temp.version == 2 &&
 		    temp->fru_type == OCC_FRU_TYPE_VRM) {
-			snprintf(attr->name, sizeof(attr->name),
-				 "temp%d_alarm", s);
+			occ_init_attribute(attr, 0444, show_temp, NULL,
+					   1, i, "temp%d_alarm", s);
 		} else {
-			snprintf(attr->name, sizeof(attr->name),
-				 "temp%d_input", s);
+			occ_init_attribute(attr, 0444, show_temp, NULL,
+					   1, i, "temp%d_input", s);
 		}
 
-		attr->sensor = OCC_INIT_ATTR(attr->name, 0444, show_temp, NULL,
-					     1, i);
 		attr++;
 
 		if (sensors->temp.version > 1) {
-			snprintf(attr->name, sizeof(attr->name),
-				 "temp%d_fru_type", s);
-			attr->sensor = OCC_INIT_ATTR(attr->name, 0444,
-						     show_temp, NULL, 2, i);
+			occ_init_attribute(attr, 0444, show_temp, NULL,
+					   2, i, "temp%d_fru_type", s);
 			attr++;
 
-			snprintf(attr->name, sizeof(attr->name),
-				 "temp%d_fault", s);
-			attr->sensor = OCC_INIT_ATTR(attr->name, 0444,
-						     show_temp, NULL, 3, i);
+			occ_init_attribute(attr, 0444, show_temp, NULL,
+					   3, i, "temp%d_fault", s);
 			attr++;
 
 			if (sensors->temp.version == 0x10) {
-				snprintf(attr->name, sizeof(attr->name),
-					 "temp%d_max", s);
-				attr->sensor = OCC_INIT_ATTR(attr->name, 0444,
-							     show_temp, NULL,
-							     4, i);
+				occ_init_attribute(attr, 0444, show_temp, NULL,
+						   4, i, "temp%d_max", s);
 				attr++;
 			}
 		}
@@ -917,14 +909,12 @@ static int occ_setup_sensor_attrs(struct occ *occ)
 	for (i = 0; i < sensors->freq.num_sensors; ++i) {
 		s = i + 1;
 
-		snprintf(attr->name, sizeof(attr->name), "freq%d_label", s);
-		attr->sensor = OCC_INIT_ATTR(attr->name, 0444, show_freq, NULL,
-					     0, i);
+		occ_init_attribute(attr, 0444, show_freq, NULL,
+				   0, i, "freq%d_label", s);
 		attr++;
 
-		snprintf(attr->name, sizeof(attr->name), "freq%d_input", s);
-		attr->sensor = OCC_INIT_ATTR(attr->name, 0444, show_freq, NULL,
-					     1, i);
+		occ_init_attribute(attr, 0444, show_freq, NULL,
+				   1, i, "freq%d_input", s);
 		attr++;
 	}
 
@@ -940,32 +930,24 @@ static int occ_setup_sensor_attrs(struct occ *occ)
 			s = (i * 4) + 1;
 
 			for (j = 0; j < 4; ++j) {
-				snprintf(attr->name, sizeof(attr->name),
-					 "power%d_label", s);
-				attr->sensor = OCC_INIT_ATTR(attr->name, 0444,
-							     show_power, NULL,
-							     nr++, i);
+				occ_init_attribute(attr, 0444, show_power,
+						   NULL, nr++, i,
+						   "power%d_label", s);
 				attr++;
 
-				snprintf(attr->name, sizeof(attr->name),
-					 "power%d_average", s);
-				attr->sensor = OCC_INIT_ATTR(attr->name, 0444,
-							     show_power, NULL,
-							     nr++, i);
+				occ_init_attribute(attr, 0444, show_power,
+						   NULL, nr++, i,
+						   "power%d_average", s);
 				attr++;
 
-				snprintf(attr->name, sizeof(attr->name),
-					 "power%d_average_interval", s);
-				attr->sensor = OCC_INIT_ATTR(attr->name, 0444,
-							     show_power, NULL,
-							     nr++, i);
+				occ_init_attribute(attr, 0444, show_power,
+						   NULL, nr++, i,
+						   "power%d_average_interval", s);
 				attr++;
 
-				snprintf(attr->name, sizeof(attr->name),
-					 "power%d_input", s);
-				attr->sensor = OCC_INIT_ATTR(attr->name, 0444,
-							     show_power, NULL,
-							     nr++, i);
+				occ_init_attribute(attr, 0444, show_power,
+						   NULL, nr++, i,
+						   "power%d_input", s);
 				attr++;
 
 				s++;
@@ -977,28 +959,20 @@ static int occ_setup_sensor_attrs(struct occ *occ)
 		for (i = 0; i < sensors->power.num_sensors; ++i) {
 			s = i + 1;
 
-			snprintf(attr->name, sizeof(attr->name),
-				 "power%d_label", s);
-			attr->sensor = OCC_INIT_ATTR(attr->name, 0444,
-						     show_power, NULL, 0, i);
+			occ_init_attribute(attr, 0444, show_power, NULL,
+					   0, i, "power%d_label", s);
 			attr++;
 
-			snprintf(attr->name, sizeof(attr->name),
-				 "power%d_average", s);
-			attr->sensor = OCC_INIT_ATTR(attr->name, 0444,
-						     show_power, NULL, 1, i);
+			occ_init_attribute(attr, 0444, show_power, NULL,
+					   1, i, "power%d_average", s);
 			attr++;
 
-			snprintf(attr->name, sizeof(attr->name),
-				 "power%d_average_interval", s);
-			attr->sensor = OCC_INIT_ATTR(attr->name, 0444,
-						     show_power, NULL, 2, i);
+			occ_init_attribute(attr, 0444, show_power, NULL,
+					   2, i, "power%d_average_interval", s);
 			attr++;
 
-			snprintf(attr->name, sizeof(attr->name),
-				 "power%d_input", s);
-			attr->sensor = OCC_INIT_ATTR(attr->name, 0444,
-						     show_power, NULL, 3, i);
+			occ_init_attribute(attr, 0444, show_power, NULL,
+					   3, i, "power%d_input", s);
 			attr++;
 		}
 
@@ -1006,56 +980,43 @@ static int occ_setup_sensor_attrs(struct occ *occ)
 	}
 
 	if (sensors->caps.num_sensors >= 1) {
-		snprintf(attr->name, sizeof(attr->name), "power%d_label", s);
-		attr->sensor = OCC_INIT_ATTR(attr->name, 0444, show_caps, NULL,
-					     0, 0);
+		occ_init_attribute(attr, 0444, show_caps, NULL,
+				   0, 0, "power%d_label", s);
 		attr++;
 
-		snprintf(attr->name, sizeof(attr->name), "power%d_cap", s);
-		attr->sensor = OCC_INIT_ATTR(attr->name, 0444, show_caps, NULL,
-					     1, 0);
+		occ_init_attribute(attr, 0444, show_caps, NULL,
+				   1, 0, "power%d_cap", s);
 		attr++;
 
-		snprintf(attr->name, sizeof(attr->name), "power%d_input", s);
-		attr->sensor = OCC_INIT_ATTR(attr->name, 0444, show_caps, NULL,
-					     2, 0);
+		occ_init_attribute(attr, 0444, show_caps, NULL,
+				   2, 0, "power%d_input", s);
 		attr++;
 
-		snprintf(attr->name, sizeof(attr->name),
-			 "power%d_cap_not_redundant", s);
-		attr->sensor = OCC_INIT_ATTR(attr->name, 0444, show_caps, NULL,
-					     3, 0);
+		occ_init_attribute(attr, 0444, show_caps, NULL,
+				   3, 0, "power%d_cap_not_redundant", s);
 		attr++;
 
-		snprintf(attr->name, sizeof(attr->name), "power%d_cap_max", s);
-		attr->sensor = OCC_INIT_ATTR(attr->name, 0444, show_caps, NULL,
-					     4, 0);
+		occ_init_attribute(attr, 0444, show_caps, NULL,
+				   4, 0, "power%d_cap_max", s);
 		attr++;
 
-		snprintf(attr->name, sizeof(attr->name), "power%d_cap_min", s);
-		attr->sensor = OCC_INIT_ATTR(attr->name, 0444, show_caps, NULL,
-					     5, 0);
+		occ_init_attribute(attr, 0444, show_caps, NULL,
+				   5, 0, "power%d_cap_min", s);
 		attr++;
 
-		snprintf(attr->name, sizeof(attr->name), "power%d_cap_user",
-			 s);
-		attr->sensor = OCC_INIT_ATTR(attr->name, 0644, show_caps,
-					     occ_store_caps_user, 6, 0);
+		occ_init_attribute(attr, 0644, show_caps, occ_store_caps_user,
+				   6, 0, "power%d_cap_user", s);
 		attr++;
 
 		if (sensors->caps.version > 1) {
-			snprintf(attr->name, sizeof(attr->name),
-				 "power%d_cap_user_source", s);
-			attr->sensor = OCC_INIT_ATTR(attr->name, 0444,
-						     show_caps, NULL, 7, 0);
+			occ_init_attribute(attr, 0444, show_caps, NULL,
+					   7, 0, "power%d_cap_user_source", s);
 			attr++;
 
 			if (sensors->caps.version > 2) {
-				snprintf(attr->name, sizeof(attr->name),
-					 "power%d_cap_min_soft", s);
-				attr->sensor = OCC_INIT_ATTR(attr->name, 0444,
-							     show_caps, NULL,
-							     8, 0);
+				occ_init_attribute(attr, 0444, show_caps, NULL,
+						   8, 0,
+						   "power%d_cap_min_soft", s);
 				attr++;
 			}
 		}
@@ -1064,19 +1025,16 @@ static int occ_setup_sensor_attrs(struct occ *occ)
 	for (i = 0; i < sensors->extended.num_sensors; ++i) {
 		s = i + 1;
 
-		snprintf(attr->name, sizeof(attr->name), "extn%d_label", s);
-		attr->sensor = OCC_INIT_ATTR(attr->name, 0444,
-					     occ_show_extended, NULL, 0, i);
+		occ_init_attribute(attr, 0444, occ_show_extended, NULL,
+				   0, i, "extn%d_label", s);
 		attr++;
 
-		snprintf(attr->name, sizeof(attr->name), "extn%d_flags", s);
-		attr->sensor = OCC_INIT_ATTR(attr->name, 0444,
-					     occ_show_extended, NULL, 1, i);
+		occ_init_attribute(attr, 0444, occ_show_extended, NULL,
+				   1, i, "extn%d_flags", s);
 		attr++;
 
-		snprintf(attr->name, sizeof(attr->name), "extn%d_input", s);
-		attr->sensor = OCC_INIT_ATTR(attr->name, 0444,
-					     occ_show_extended, NULL, 2, i);
+		occ_init_attribute(attr, 0444, occ_show_extended, NULL,
+				   2, i, "extn%d_input", s);
 		attr++;
 	}
 

From 2c021b45c154958566aad0cae9f74ab26a2d5732 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 10 Jun 2025 11:25:49 +0200
Subject: [PATCH 0407/1334] hwmon: (occ) fix unaligned accesses

Passing a pointer to an unaligned integer as a function argument is
undefined behavior:

drivers/hwmon/occ/common.c:492:27: warning: taking address of packed member 'accumulator' of class or structure 'power_sensor_2' may result in an unaligned pointer value [-Waddress-of-packed-member]
  492 |   val = occ_get_powr_avg(&power->accumulator,
      |                           ^~~~~~~~~~~~~~~~~~
drivers/hwmon/occ/common.c:493:13: warning: taking address of packed member 'update_tag' of class or structure 'power_sensor_2' may result in an unaligned pointer value [-Waddress-of-packed-member]
  493 |            &power->update_tag);
      |             ^~~~~~~~~~~~~~~~~

Move the get_unaligned() calls out of the function and pass these
through argument registers instead.

Fixes: c10e753d43eb ("hwmon (occ): Add sensor types and versions")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Link: https://lore.kernel.org/r/20250610092553.2641094-1-arnd@kernel.org
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/hwmon/occ/common.c | 28 +++++++++++++---------------
 1 file changed, 13 insertions(+), 15 deletions(-)

diff --git a/drivers/hwmon/occ/common.c b/drivers/hwmon/occ/common.c
index 9029ad53790b..b3694a4209b9 100644
--- a/drivers/hwmon/occ/common.c
+++ b/drivers/hwmon/occ/common.c
@@ -459,12 +459,10 @@ static ssize_t occ_show_power_1(struct device *dev,
 	return sysfs_emit(buf, "%llu\n", val);
 }
 
-static u64 occ_get_powr_avg(u64 *accum, u32 *samples)
+static u64 occ_get_powr_avg(u64 accum, u32 samples)
 {
-	u64 divisor = get_unaligned_be32(samples);
-
-	return (divisor == 0) ? 0 :
-		div64_u64(get_unaligned_be64(accum) * 1000000ULL, divisor);
+	return (samples == 0) ? 0 :
+		mul_u64_u32_div(accum, 1000000UL, samples);
 }
 
 static ssize_t occ_show_power_2(struct device *dev,
@@ -489,8 +487,8 @@ static ssize_t occ_show_power_2(struct device *dev,
 				  get_unaligned_be32(&power->sensor_id),
 				  power->function_id, power->apss_channel);
 	case 1:
-		val = occ_get_powr_avg(&power->accumulator,
-				       &power->update_tag);
+		val = occ_get_powr_avg(get_unaligned_be64(&power->accumulator),
+				       get_unaligned_be32(&power->update_tag));
 		break;
 	case 2:
 		val = (u64)get_unaligned_be32(&power->update_tag) *
@@ -527,8 +525,8 @@ static ssize_t occ_show_power_a0(struct device *dev,
 		return sysfs_emit(buf, "%u_system\n",
 				  get_unaligned_be32(&power->sensor_id));
 	case 1:
-		val = occ_get_powr_avg(&power->system.accumulator,
-				       &power->system.update_tag);
+		val = occ_get_powr_avg(get_unaligned_be64(&power->system.accumulator),
+				       get_unaligned_be32(&power->system.update_tag));
 		break;
 	case 2:
 		val = (u64)get_unaligned_be32(&power->system.update_tag) *
@@ -541,8 +539,8 @@ static ssize_t occ_show_power_a0(struct device *dev,
 		return sysfs_emit(buf, "%u_proc\n",
 				  get_unaligned_be32(&power->sensor_id));
 	case 5:
-		val = occ_get_powr_avg(&power->proc.accumulator,
-				       &power->proc.update_tag);
+		val = occ_get_powr_avg(get_unaligned_be64(&power->proc.accumulator),
+				       get_unaligned_be32(&power->proc.update_tag));
 		break;
 	case 6:
 		val = (u64)get_unaligned_be32(&power->proc.update_tag) *
@@ -555,8 +553,8 @@ static ssize_t occ_show_power_a0(struct device *dev,
 		return sysfs_emit(buf, "%u_vdd\n",
 				  get_unaligned_be32(&power->sensor_id));
 	case 9:
-		val = occ_get_powr_avg(&power->vdd.accumulator,
-				       &power->vdd.update_tag);
+		val = occ_get_powr_avg(get_unaligned_be64(&power->vdd.accumulator),
+				       get_unaligned_be32(&power->vdd.update_tag));
 		break;
 	case 10:
 		val = (u64)get_unaligned_be32(&power->vdd.update_tag) *
@@ -569,8 +567,8 @@ static ssize_t occ_show_power_a0(struct device *dev,
 		return sysfs_emit(buf, "%u_vdn\n",
 				  get_unaligned_be32(&power->sensor_id));
 	case 13:
-		val = occ_get_powr_avg(&power->vdn.accumulator,
-				       &power->vdn.update_tag);
+		val = occ_get_powr_avg(get_unaligned_be64(&power->vdn.accumulator),
+				       get_unaligned_be32(&power->vdn.update_tag));
 		break;
 	case 14:
 		val = (u64)get_unaligned_be32(&power->vdn.update_tag) *

From c25892b7a1744355e16281cd24a9b59ec15ec974 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Nuno=20S=C3=A1?= <nuno.sa@analog.com>
Date: Wed, 11 Jun 2025 17:26:12 +0100
Subject: [PATCH 0408/1334] hwmon: (ltc4282) avoid repeated register write
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The fault enabled bits were being mistankenly enabled twice in case the FW
property is present. Remove one of the writes.

Fixes: cbc29538dbf7 ("hwmon: Add driver for LTC4282")
Signed-off-by: Nuno Sá <nuno.sa@analog.com>
Link: https://lore.kernel.org/r/20250611-fix-ltc4282-repetead-write-v1-1-fe46edd08cf1@analog.com
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/hwmon/ltc4282.c | 7 -------
 1 file changed, 7 deletions(-)

diff --git a/drivers/hwmon/ltc4282.c b/drivers/hwmon/ltc4282.c
index 7f38d2696239..f607fe8f7937 100644
--- a/drivers/hwmon/ltc4282.c
+++ b/drivers/hwmon/ltc4282.c
@@ -1511,13 +1511,6 @@ static int ltc4282_setup(struct ltc4282_state *st, struct device *dev)
 			return ret;
 	}
 
-	if (device_property_read_bool(dev, "adi,fault-log-enable")) {
-		ret = regmap_set_bits(st->map, LTC4282_ADC_CTRL,
-				      LTC4282_FAULT_LOG_EN_MASK);
-		if (ret)
-			return ret;
-	}
-
 	if (device_property_read_bool(dev, "adi,fault-log-enable")) {
 		ret = regmap_set_bits(st->map, LTC4282_ADC_CTRL, LTC4282_FAULT_LOG_EN_MASK);
 		if (ret)

From 7360ee47599af91a1d5f4e74d635d9408a54e489 Mon Sep 17 00:00:00 2001
From: Fedor Pchelkin <pchelkin@ispras.ru>
Date: Wed, 11 Jun 2025 22:20:10 +0300
Subject: [PATCH 0409/1334] s390/pkey: Prevent overflow in size calculation for
 memdup_user()

Number of apqn target list entries contained in 'nr_apqns' variable is
determined by userspace via an ioctl call so the result of the product in
calculation of size passed to memdup_user() may overflow.

In this case the actual size of the allocated area and the value
describing it won't be in sync leading to various types of unpredictable
behaviour later.

Use a proper memdup_array_user() helper which returns an error if an
overflow is detected. Note that it is different from when nr_apqns is
initially zero - that case is considered valid and should be handled in
subsequent pkey_handler implementations.

Found by Linux Verification Center (linuxtesting.org).

Fixes: f2bbc96e7cfa ("s390/pkey: add CCA AES cipher key support")
Cc: stable@vger.kernel.org
Signed-off-by: Fedor Pchelkin <pchelkin@ispras.ru>
Reviewed-by: Holger Dengler <dengler@linux.ibm.com>
Reviewed-by: Heiko Carstens <hca@linux.ibm.com>
Link: https://lore.kernel.org/r/20250611192011.206057-1-pchelkin@ispras.ru
Signed-off-by: Alexander Gordeev <agordeev@linux.ibm.com>
---
 drivers/s390/crypto/pkey_api.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/s390/crypto/pkey_api.c b/drivers/s390/crypto/pkey_api.c
index cef60770f68b..b3fcdcae379e 100644
--- a/drivers/s390/crypto/pkey_api.c
+++ b/drivers/s390/crypto/pkey_api.c
@@ -86,7 +86,7 @@ static void *_copy_apqns_from_user(void __user *uapqns, size_t nr_apqns)
 	if (!uapqns || nr_apqns == 0)
 		return NULL;
 
-	return memdup_user(uapqns, nr_apqns * sizeof(struct pkey_apqn));
+	return memdup_array_user(uapqns, nr_apqns, sizeof(struct pkey_apqn));
 }
 
 static int pkey_ioctl_genseck(struct pkey_genseck __user *ugs)

From f9af88a3d384c8b55beb5dc5483e5da0135fadbd Mon Sep 17 00:00:00 2001
From: "Borislav Petkov (AMD)" <bp@alien8.de>
Date: Wed, 11 Sep 2024 05:13:46 +0200
Subject: [PATCH 0410/1334] x86/bugs: Rename MDS machinery to something more
 generic

It will be used by other x86 mitigations.

No functional changes.

Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Pawan Gupta <pawan.kumar.gupta@linux.intel.com>
---
 .../hw-vuln/processor_mmio_stale_data.rst     |  4 +--
 Documentation/arch/x86/mds.rst                |  8 ++---
 arch/x86/entry/entry.S                        |  8 ++---
 arch/x86/include/asm/irqflags.h               |  4 +--
 arch/x86/include/asm/mwait.h                  |  4 +--
 arch/x86/include/asm/nospec-branch.h          | 29 ++++++++++---------
 arch/x86/kernel/cpu/bugs.c                    | 12 ++++----
 arch/x86/kvm/vmx/vmx.c                        |  2 +-
 8 files changed, 35 insertions(+), 36 deletions(-)

diff --git a/Documentation/admin-guide/hw-vuln/processor_mmio_stale_data.rst b/Documentation/admin-guide/hw-vuln/processor_mmio_stale_data.rst
index 1302fd1b55e8..6dba18dbb9ab 100644
--- a/Documentation/admin-guide/hw-vuln/processor_mmio_stale_data.rst
+++ b/Documentation/admin-guide/hw-vuln/processor_mmio_stale_data.rst
@@ -157,9 +157,7 @@ This is achieved by using the otherwise unused and obsolete VERW instruction in
 combination with a microcode update. The microcode clears the affected CPU
 buffers when the VERW instruction is executed.
 
-Kernel reuses the MDS function to invoke the buffer clearing:
-
-	mds_clear_cpu_buffers()
+Kernel does the buffer clearing with x86_clear_cpu_buffers().
 
 On MDS affected CPUs, the kernel already invokes CPU buffer clear on
 kernel/userspace, hypervisor/guest and C-state (idle) transitions. No
diff --git a/Documentation/arch/x86/mds.rst b/Documentation/arch/x86/mds.rst
index 5a2e6c0ef04a..3518671e1a85 100644
--- a/Documentation/arch/x86/mds.rst
+++ b/Documentation/arch/x86/mds.rst
@@ -93,7 +93,7 @@ enters a C-state.
 
 The kernel provides a function to invoke the buffer clearing:
 
-    mds_clear_cpu_buffers()
+    x86_clear_cpu_buffers()
 
 Also macro CLEAR_CPU_BUFFERS can be used in ASM late in exit-to-user path.
 Other than CFLAGS.ZF, this macro doesn't clobber any registers.
@@ -185,9 +185,9 @@ Mitigation points
    idle clearing would be a window dressing exercise and is therefore not
    activated.
 
-   The invocation is controlled by the static key mds_idle_clear which is
-   switched depending on the chosen mitigation mode and the SMT state of
-   the system.
+   The invocation is controlled by the static key cpu_buf_idle_clear which is
+   switched depending on the chosen mitigation mode and the SMT state of the
+   system.
 
    The buffer clear is only invoked before entering the C-State to prevent
    that stale data from the idling CPU from spilling to the Hyper-Thread
diff --git a/arch/x86/entry/entry.S b/arch/x86/entry/entry.S
index 175958b02f2b..8e9a0cc20a4a 100644
--- a/arch/x86/entry/entry.S
+++ b/arch/x86/entry/entry.S
@@ -36,20 +36,20 @@ EXPORT_SYMBOL_GPL(write_ibpb);
 
 /*
  * Define the VERW operand that is disguised as entry code so that
- * it can be referenced with KPTI enabled. This ensure VERW can be
+ * it can be referenced with KPTI enabled. This ensures VERW can be
  * used late in exit-to-user path after page tables are switched.
  */
 .pushsection .entry.text, "ax"
 
 .align L1_CACHE_BYTES, 0xcc
-SYM_CODE_START_NOALIGN(mds_verw_sel)
+SYM_CODE_START_NOALIGN(x86_verw_sel)
 	UNWIND_HINT_UNDEFINED
 	ANNOTATE_NOENDBR
 	.word __KERNEL_DS
 .align L1_CACHE_BYTES, 0xcc
-SYM_CODE_END(mds_verw_sel);
+SYM_CODE_END(x86_verw_sel);
 /* For KVM */
-EXPORT_SYMBOL_GPL(mds_verw_sel);
+EXPORT_SYMBOL_GPL(x86_verw_sel);
 
 .popsection
 
diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h
index 9a9b21b78905..b30e5474c18e 100644
--- a/arch/x86/include/asm/irqflags.h
+++ b/arch/x86/include/asm/irqflags.h
@@ -44,13 +44,13 @@ static __always_inline void native_irq_enable(void)
 
 static __always_inline void native_safe_halt(void)
 {
-	mds_idle_clear_cpu_buffers();
+	x86_idle_clear_cpu_buffers();
 	asm volatile("sti; hlt": : :"memory");
 }
 
 static __always_inline void native_halt(void)
 {
-	mds_idle_clear_cpu_buffers();
+	x86_idle_clear_cpu_buffers();
 	asm volatile("hlt": : :"memory");
 }
 
diff --git a/arch/x86/include/asm/mwait.h b/arch/x86/include/asm/mwait.h
index dd2b129b0418..cc34c3fd197b 100644
--- a/arch/x86/include/asm/mwait.h
+++ b/arch/x86/include/asm/mwait.h
@@ -43,7 +43,7 @@ static __always_inline void __monitorx(const void *eax, u32 ecx, u32 edx)
 
 static __always_inline void __mwait(u32 eax, u32 ecx)
 {
-	mds_idle_clear_cpu_buffers();
+	x86_idle_clear_cpu_buffers();
 
 	/*
 	 * Use the instruction mnemonic with implicit operands, as the LLVM
@@ -98,7 +98,7 @@ static __always_inline void __mwaitx(u32 eax, u32 ebx, u32 ecx)
  */
 static __always_inline void __sti_mwait(u32 eax, u32 ecx)
 {
-	mds_idle_clear_cpu_buffers();
+	x86_idle_clear_cpu_buffers();
 
 	asm volatile("sti; mwait" :: "a" (eax), "c" (ecx));
 }
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index 20d754b98f3f..5dcd75bb5e0d 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -302,22 +302,22 @@
 .endm
 
 /*
- * Macro to execute VERW instruction that mitigate transient data sampling
- * attacks such as MDS. On affected systems a microcode update overloaded VERW
- * instruction to also clear the CPU buffers. VERW clobbers CFLAGS.ZF.
- *
+ * Macro to execute VERW insns that mitigate transient data sampling
+ * attacks such as MDS or TSA. On affected systems a microcode update
+ * overloaded VERW insns to also clear the CPU buffers. VERW clobbers
+ * CFLAGS.ZF.
  * Note: Only the memory operand variant of VERW clears the CPU buffers.
  */
 .macro CLEAR_CPU_BUFFERS
 #ifdef CONFIG_X86_64
-	ALTERNATIVE "", "verw mds_verw_sel(%rip)", X86_FEATURE_CLEAR_CPU_BUF
+	ALTERNATIVE "", "verw x86_verw_sel(%rip)", X86_FEATURE_CLEAR_CPU_BUF
 #else
 	/*
 	 * In 32bit mode, the memory operand must be a %cs reference. The data
 	 * segments may not be usable (vm86 mode), and the stack segment may not
 	 * be flat (ESPFIX32).
 	 */
-	ALTERNATIVE "", "verw %cs:mds_verw_sel", X86_FEATURE_CLEAR_CPU_BUF
+	ALTERNATIVE "", "verw %cs:x86_verw_sel", X86_FEATURE_CLEAR_CPU_BUF
 #endif
 .endm
 
@@ -567,24 +567,24 @@ DECLARE_STATIC_KEY_FALSE(switch_mm_always_ibpb);
 
 DECLARE_STATIC_KEY_FALSE(switch_vcpu_ibpb);
 
-DECLARE_STATIC_KEY_FALSE(mds_idle_clear);
+DECLARE_STATIC_KEY_FALSE(cpu_buf_idle_clear);
 
 DECLARE_STATIC_KEY_FALSE(switch_mm_cond_l1d_flush);
 
 DECLARE_STATIC_KEY_FALSE(cpu_buf_vm_clear);
 
-extern u16 mds_verw_sel;
+extern u16 x86_verw_sel;
 
 #include <asm/segment.h>
 
 /**
- * mds_clear_cpu_buffers - Mitigation for MDS and TAA vulnerability
+ * x86_clear_cpu_buffers - Buffer clearing support for different x86 CPU vulns
  *
  * This uses the otherwise unused and obsolete VERW instruction in
  * combination with microcode which triggers a CPU buffer flush when the
  * instruction is executed.
  */
-static __always_inline void mds_clear_cpu_buffers(void)
+static __always_inline void x86_clear_cpu_buffers(void)
 {
 	static const u16 ds = __KERNEL_DS;
 
@@ -601,14 +601,15 @@ static __always_inline void mds_clear_cpu_buffers(void)
 }
 
 /**
- * mds_idle_clear_cpu_buffers - Mitigation for MDS vulnerability
+ * x86_idle_clear_cpu_buffers - Buffer clearing support in idle for the MDS
+ * vulnerability
  *
  * Clear CPU buffers if the corresponding static key is enabled
  */
-static __always_inline void mds_idle_clear_cpu_buffers(void)
+static __always_inline void x86_idle_clear_cpu_buffers(void)
 {
-	if (static_branch_likely(&mds_idle_clear))
-		mds_clear_cpu_buffers();
+	if (static_branch_likely(&cpu_buf_idle_clear))
+		x86_clear_cpu_buffers();
 }
 
 #endif /* __ASSEMBLER__ */
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 7f94e6a5497d..258ed3d2b6a9 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -169,9 +169,9 @@ DEFINE_STATIC_KEY_FALSE(switch_mm_always_ibpb);
 DEFINE_STATIC_KEY_FALSE(switch_vcpu_ibpb);
 EXPORT_SYMBOL_GPL(switch_vcpu_ibpb);
 
-/* Control MDS CPU buffer clear before idling (halt, mwait) */
-DEFINE_STATIC_KEY_FALSE(mds_idle_clear);
-EXPORT_SYMBOL_GPL(mds_idle_clear);
+/* Control CPU buffer clear before idling (halt, mwait) */
+DEFINE_STATIC_KEY_FALSE(cpu_buf_idle_clear);
+EXPORT_SYMBOL_GPL(cpu_buf_idle_clear);
 
 /*
  * Controls whether l1d flush based mitigations are enabled,
@@ -637,7 +637,7 @@ static void __init mmio_apply_mitigation(void)
 	 * is required irrespective of SMT state.
 	 */
 	if (!(x86_arch_cap_msr & ARCH_CAP_FBSDP_NO))
-		static_branch_enable(&mds_idle_clear);
+		static_branch_enable(&cpu_buf_idle_clear);
 
 	if (mmio_nosmt || cpu_mitigations_auto_nosmt())
 		cpu_smt_disable(false);
@@ -2249,10 +2249,10 @@ static void update_mds_branch_idle(void)
 		return;
 
 	if (sched_smt_active()) {
-		static_branch_enable(&mds_idle_clear);
+		static_branch_enable(&cpu_buf_idle_clear);
 	} else if (mmio_mitigation == MMIO_MITIGATION_OFF ||
 		   (x86_arch_cap_msr & ARCH_CAP_FBSDP_NO)) {
-		static_branch_disable(&mds_idle_clear);
+		static_branch_disable(&cpu_buf_idle_clear);
 	}
 }
 
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 4953846cb30d..191a9ed0da22 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -7291,7 +7291,7 @@ static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu,
 		vmx_l1d_flush(vcpu);
 	else if (static_branch_unlikely(&cpu_buf_vm_clear) &&
 		 kvm_arch_has_assigned_device(vcpu->kvm))
-		mds_clear_cpu_buffers();
+		x86_clear_cpu_buffers();
 
 	vmx_disable_fb_clear(vmx);
 

From 070b315333ee942f2cc69d02a864945c9bc27ef2 Mon Sep 17 00:00:00 2001
From: Chun-Tse Shao <ctshao@google.com>
Date: Wed, 21 May 2025 15:44:44 -0700
Subject: [PATCH 0411/1334] perf test: Restrict uniquifying test to machines
 with 'uncore_imc'

The test would fail if target machine does not have 'uncore_imc'
devices.

Since event uniquifying behavior is similar among different
architectures, we are restricting the test to only run on machines with
`uncore_imc` devices.

Suggested-by: Ian Rogers <irogers@google.com>
Signed-off-by: Chun-Tse Shao <ctshao@google.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20250521224513.1104129-1-ctshao@google.com
[ Skip the test, i.e. return 2, instead of returning 0 as if the test had succeed ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/shell/stat+event_uniquifying.sh | 12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)

diff --git a/tools/perf/tests/shell/stat+event_uniquifying.sh b/tools/perf/tests/shell/stat+event_uniquifying.sh
index 5ec35c52b7d9..bf54bd6c3e2e 100755
--- a/tools/perf/tests/shell/stat+event_uniquifying.sh
+++ b/tools/perf/tests/shell/stat+event_uniquifying.sh
@@ -9,7 +9,8 @@ perf_tool=perf
 err=0
 
 test_event_uniquifying() {
-  # We use `clockticks` to verify the uniquify behavior.
+  # We use `clockticks` in `uncore_imc` to verify the uniquify behavior.
+  pmu="uncore_imc"
   event="clockticks"
 
   # If the `-A` option is added, the event should be uniquified.
@@ -43,11 +44,18 @@ test_event_uniquifying() {
   echo "stat event uniquifying test"
   uniquified_event_array=()
 
+  # Skip if the machine does not have `uncore_imc` device.
+  if ! ${perf_tool} list pmu | grep -q ${pmu}; then
+    echo "Target does not support PMU ${pmu} [Skipped]"
+    err=2
+    return
+  fi
+
   # Check how many uniquified events.
   while IFS= read -r line; do
     uniquified_event=$(echo "$line" | awk '{print $1}')
     uniquified_event_array+=("${uniquified_event}")
-  done < <(${perf_tool} list -v ${event} | grep "\[Kernel PMU event\]")
+  done < <(${perf_tool} list -v ${event} | grep ${pmu})
 
   perf_command="${perf_tool} stat -e $event -A -o ${stat_output} -- true"
   $perf_command

From 11cfaf37d6a79447bde8192e2e3bb2877932b82b Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Mon, 9 Jun 2025 12:32:06 -0300
Subject: [PATCH 0412/1334] tools headers: Update the fs headers with the
 kernel sources

To pick up changes from:

  5d894321c49e6137 ("fs: add atomic write unit max opt to statx")
  a516403787e08119 ("fs/proc: extend the PAGEMAP_SCAN ioctl to report guard regions")
  c07d3aede2b26830 ("fscrypt: add support for hardware-wrapped keys")

These are used to beautify fs syscall arguments, albeit the changes in
this update are not affecting those beautifiers.

This addresses these tools/ build warnings:

  Warning: Kernel ABI header differences:
  diff -u tools/include/uapi/linux/fscrypt.h include/uapi/linux/fscrypt.h
  diff -u tools/include/uapi/linux/stat.h include/uapi/linux/stat.h
  diff -u tools/perf/trace/beauty/include/uapi/linux/fs.h include/uapi/linux/fs.h
  diff -u tools/perf/trace/beauty/include/uapi/linux/stat.h include/uapi/linux/stat.h

Please see tools/include/uapi/README for details (it's in the first patch
of this series).

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andrei Vagin <avagin@gmail.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Andrii Nakryiko <andrii@kernel.org>
Cc: Darrick J. Wong <djwong@kernel.org>
Cc: Eric Biggers <ebiggers@google.com>
Cc: Ian Rogers <irogers@google.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Liam R. Howlett <liam.howlett@oracle.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/r/aEce1keWdO-vGeqe@x1
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/include/uapi/linux/fscrypt.h                | 6 ++++--
 tools/include/uapi/linux/stat.h                   | 8 ++++++--
 tools/perf/trace/beauty/include/uapi/linux/fs.h   | 1 +
 tools/perf/trace/beauty/include/uapi/linux/stat.h | 8 ++++++--
 4 files changed, 17 insertions(+), 6 deletions(-)

diff --git a/tools/include/uapi/linux/fscrypt.h b/tools/include/uapi/linux/fscrypt.h
index 7a8f4c290187..3aff99f2696a 100644
--- a/tools/include/uapi/linux/fscrypt.h
+++ b/tools/include/uapi/linux/fscrypt.h
@@ -119,7 +119,7 @@ struct fscrypt_key_specifier {
  */
 struct fscrypt_provisioning_key_payload {
 	__u32 type;
-	__u32 __reserved;
+	__u32 flags;
 	__u8 raw[];
 };
 
@@ -128,7 +128,9 @@ struct fscrypt_add_key_arg {
 	struct fscrypt_key_specifier key_spec;
 	__u32 raw_size;
 	__u32 key_id;
-	__u32 __reserved[8];
+#define FSCRYPT_ADD_KEY_FLAG_HW_WRAPPED	0x00000001
+	__u32 flags;
+	__u32 __reserved[7];
 	__u8 raw[];
 };
 
diff --git a/tools/include/uapi/linux/stat.h b/tools/include/uapi/linux/stat.h
index f78ee3670dd5..1686861aae20 100644
--- a/tools/include/uapi/linux/stat.h
+++ b/tools/include/uapi/linux/stat.h
@@ -182,8 +182,12 @@ struct statx {
 	/* File offset alignment for direct I/O reads */
 	__u32	stx_dio_read_offset_align;
 
-	/* 0xb8 */
-	__u64	__spare3[9];	/* Spare space for future expansion */
+	/* Optimised max atomic write unit in bytes */
+	__u32	stx_atomic_write_unit_max_opt;
+	__u32	__spare2[1];
+
+	/* 0xc0 */
+	__u64	__spare3[8];	/* Spare space for future expansion */
 
 	/* 0x100 */
 };
diff --git a/tools/perf/trace/beauty/include/uapi/linux/fs.h b/tools/perf/trace/beauty/include/uapi/linux/fs.h
index e762e1af650c..0098b0ce8ccb 100644
--- a/tools/perf/trace/beauty/include/uapi/linux/fs.h
+++ b/tools/perf/trace/beauty/include/uapi/linux/fs.h
@@ -361,6 +361,7 @@ typedef int __bitwise __kernel_rwf_t;
 #define PAGE_IS_PFNZERO		(1 << 5)
 #define PAGE_IS_HUGE		(1 << 6)
 #define PAGE_IS_SOFT_DIRTY	(1 << 7)
+#define PAGE_IS_GUARD		(1 << 8)
 
 /*
  * struct page_region - Page region with flags
diff --git a/tools/perf/trace/beauty/include/uapi/linux/stat.h b/tools/perf/trace/beauty/include/uapi/linux/stat.h
index f78ee3670dd5..1686861aae20 100644
--- a/tools/perf/trace/beauty/include/uapi/linux/stat.h
+++ b/tools/perf/trace/beauty/include/uapi/linux/stat.h
@@ -182,8 +182,12 @@ struct statx {
 	/* File offset alignment for direct I/O reads */
 	__u32	stx_dio_read_offset_align;
 
-	/* 0xb8 */
-	__u64	__spare3[9];	/* Spare space for future expansion */
+	/* Optimised max atomic write unit in bytes */
+	__u32	stx_atomic_write_unit_max_opt;
+	__u32	__spare2[1];
+
+	/* 0xc0 */
+	__u64	__spare3[8];	/* Spare space for future expansion */
 
 	/* 0x100 */
 };

From bbeb1088a40b0da8b832d72e05e1c1cb71535712 Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung@kernel.org>
Date: Mon, 9 Jun 2025 17:57:42 -0700
Subject: [PATCH 0413/1334] perf mem: Document new output fields (op, cache,
 mem, dtlb, snoop)

Update the documentation of the new fields with examples and caveats.

Also update the related documentation for AMD IBS.

Reviewed-by: Ravi Bangoria <ravi.bangoria@amd.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20250610005742.2173050-1-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/Documentation/perf-amd-ibs.txt | 57 ++++++++++++++++-------
 tools/perf/Documentation/perf-mem.txt     | 50 ++++++++++++++++++++
 2 files changed, 91 insertions(+), 16 deletions(-)

diff --git a/tools/perf/Documentation/perf-amd-ibs.txt b/tools/perf/Documentation/perf-amd-ibs.txt
index 55f80beae037..548549935760 100644
--- a/tools/perf/Documentation/perf-amd-ibs.txt
+++ b/tools/perf/Documentation/perf-amd-ibs.txt
@@ -171,23 +171,48 @@ Below is a simple example of the perf mem tool.
 	# perf mem report
 
 A normal perf mem report output will provide detailed memory access profile.
-However, it can also be aggregated based on output fields. For example:
+New output fields will show related access info together.  For example:
 
-	# perf mem report -F mem,sample,snoop
-	Samples: 3M of event 'ibs_op//', Event count (approx.): 23524876
-	Memory access                                 Samples  Snoop
-	N/A                                           1903343  N/A
-	L1 hit                                        1056754  N/A
-	L2 hit                                          75231  N/A
-	L3 hit                                           9496  HitM
-	L3 hit                                           2270  N/A
-	RAM hit                                          8710  N/A
-	Remote node, same socket RAM hit                 3241  N/A
-	Remote core, same node Any cache hit             1572  HitM
-	Remote core, same node Any cache hit              514  N/A
-	Remote node, same socket Any cache hit           1216  HitM
-	Remote node, same socket Any cache hit            350  N/A
-	Uncached hit                                       18  N/A
+	# perf mem report -F overhead,cache,snoop,comm
+	...
+	# Samples: 92K of event 'ibs_op//'
+	# Total weight : 531104
+	#
+	#           ---------- Cache -----------  --- Snoop ----
+	# Overhead       L1     L2 L1-buf  Other     HitM  Other  Command
+	# ........  ............................  ..............  ..........
+	#
+	    76.07%     5.8%  35.7%   0.0%  34.6%    23.3%  52.8%  cc1
+	     5.79%     0.2%   0.0%   0.0%   5.6%     0.1%   5.7%  make
+	     5.78%     0.1%   4.4%   0.0%   1.2%     0.5%   5.3%  gcc
+	     5.33%     0.3%   3.9%   0.0%   1.1%     0.2%   5.2%  as
+	     5.00%     0.1%   3.8%   0.0%   1.0%     0.3%   4.7%  sh
+	     1.56%     0.1%   0.1%   0.0%   1.4%     0.6%   0.9%  ld
+	     0.28%     0.1%   0.0%   0.0%   0.2%     0.1%   0.2%  pkg-config
+	     0.09%     0.0%   0.0%   0.0%   0.1%     0.0%   0.1%  git
+	     0.03%     0.0%   0.0%   0.0%   0.0%     0.0%   0.0%  rm
+	     ...
+
+Also, it can be aggregated based on various memory access info using the
+sort keys.  For example:
+
+	# perf mem report -s mem,snoop
+	...
+	# Samples: 92K of event 'ibs_op//'
+	# Total weight : 531104
+	# Sort order   : mem,snoop
+	#
+	# Overhead       Samples  Memory access                            Snoop
+	# ........  ............  .......................................  ............
+	#
+	    47.99%          1509  L2 hit                                   N/A
+	    25.08%           338  core, same node Any cache hit            HitM
+	    10.24%         54374  N/A                                      N/A
+	     6.77%         35938  L1 hit                                   N/A
+	     6.39%           101  core, same node Any cache hit            N/A
+	     3.50%            69  RAM hit                                  N/A
+	     0.03%           158  LFB/MAB hit                              N/A
+	     0.00%             2  Uncached hit                             N/A
 
 Please refer to their man page for more detail.
 
diff --git a/tools/perf/Documentation/perf-mem.txt b/tools/perf/Documentation/perf-mem.txt
index 965e73d37772..4d164836d094 100644
--- a/tools/perf/Documentation/perf-mem.txt
+++ b/tools/perf/Documentation/perf-mem.txt
@@ -119,6 +119,22 @@ REPORT OPTIONS
 	And the default sort keys are changed to local_weight, mem, sym, dso,
 	symbol_daddr, dso_daddr, snoop, tlb, locked, blocked, local_ins_lat.
 
+-F::
+--fields=::
+	Specify output field - multiple keys can be specified in CSV format.
+	Please see linkperf:perf-report[1] for details.
+
+	In addition to the default fields, 'perf mem report' will provide the
+	following fields to break down sample periods.
+
+	- op: operation in the sample instruction (load, store, prefetch, ...)
+	- cache: location in CPU cache (L1, L2, ...) where the sample hit
+	- mem: location in memory or other places the sample hit
+	- dtlb: location in Data TLB (L1, L2) where the sample hit
+	- snoop: snoop result for the sampled data access
+
+	Please take a look at the OUTPUT FIELD SELECTION section for caveats.
+
 -T::
 --type-profile::
 	Show data-type profile result instead of code symbols.  This requires
@@ -156,6 +172,40 @@ but one sample with weight 180 and the other with weight 20:
   90%   [k] memcpy
   10%   [.] strcmp
 
+OUTPUT FIELD SELECTION
+----------------------
+"perf mem report" adds a number of new output fields specific to data source
+information in the sample.  Some of them have the same name with the existing
+sort keys ("mem" and "snoop").  So unlike other fields and sort keys, they'll
+behave differently when it's used by -F/--fields or -s/--sort.
+
+Using those two as output fields will aggregate samples altogether and show
+breakdown.
+
+  $ perf mem report -F mem,snoop
+  ...
+  # ------ Memory -------  --- Snoop ----
+  #     RAM Uncach  Other     HitM  Other
+  # .....................  ..............
+  #
+       3.5%   0.0%  96.5%    25.1%  74.9%
+
+But using the same name for sort keys will aggregate samples for each type
+separately.
+
+  $ perf mem report -s mem,snoop
+  # Overhead       Samples  Memory access                            Snoop
+  # ........  ............  .......................................  ............
+  #
+      47.99%          1509  L2 hit                                   N/A
+      25.08%           338  core, same node Any cache hit            HitM
+      10.24%         54374  N/A                                      N/A
+       6.77%         35938  L1 hit                                   N/A
+       6.39%           101  core, same node Any cache hit            N/A
+       3.50%            69  RAM hit                                  N/A
+       0.03%           158  LFB/MAB hit                              N/A
+       0.00%             2  Uncached hit                             N/A
+
 SEE ALSO
 --------
 linkperf:perf-record[1], linkperf:perf-report[1], linkperf:perf-arm-spe[1]

From 3ce66a48a685f27a931e5bdffb637751c58df7d9 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Mon, 9 Jun 2025 15:02:17 -0300
Subject: [PATCH 0414/1334] tools headers UAPI: Sync linux/prctl.h with the
 kernel sources to pick FUTEX knob

To pick the changes in:

  63e8595c060a1fef ("futex: Allow to make the private hash immutable")
  80367ad01d93ac78 ("futex: Add basic infrastructure for local task local hash")

That adds a FUTEX knob:

  $ tools/perf/trace/beauty/prctl_option.sh > before
  $ cp include/uapi/linux/prctl.h tools/perf/trace/beauty/include/uapi/linux/prctl.h
  $ tools/perf/trace/beauty/prctl_option.sh > after
  $ diff -u before after
  --- before	2025-06-09 14:50:45.162579336 -0300
  +++ after	2025-06-09 14:50:52.797660024 -0300
  @@ -72,6 +72,7 @@
   	[75] = "SET_SHADOW_STACK_STATUS",
   	[76] = "LOCK_SHADOW_STACK_STATUS",
   	[77] = "TIMER_CREATE_RESTORE_IDS",
  +	[78] = "FUTEX_HASH",
   };
   static const char *prctl_set_mm_options[] = {
   	[1] = "START_CODE",
  $

That now will be used to decode the syscall option and also to compose
filters, for instance:

  [root@five ~]# perf trace -e syscalls:sys_enter_prctl --filter option==SET_NAME
       0.000 Isolated Servi/3474327 syscalls:sys_enter_prctl(option: SET_NAME, arg2: 0x7f23f13b7aee)
       0.032 DOM Worker/3474327 syscalls:sys_enter_prctl(option: SET_NAME, arg2: 0x7f23deb25670)
       7.920 :3474328/3474328 syscalls:sys_enter_prctl(option: SET_NAME, arg2: 0x7f23e24fbb10)
       7.935 StreamT~s #374/3474328 syscalls:sys_enter_prctl(option: SET_NAME, arg2: 0x7f23e24fb970)
       8.400 Isolated Servi/3474329 syscalls:sys_enter_prctl(option: SET_NAME, arg2: 0x7f23e24bab10)
       8.418 StreamT~s #374/3474329 syscalls:sys_enter_prctl(option: SET_NAME, arg2: 0x7f23e24ba970)
  ^C[root@five ~]#

This addresses this perf build warning:

  Warning: Kernel ABI header differences:
    diff -u tools/perf/trace/beauty/include/uapi/linux/prctl.h include/uapi/linux/prctl.h

Acked-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/aEiYOtKkrVDT03hZ@x1
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/trace/beauty/include/uapi/linux/prctl.h | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/tools/perf/trace/beauty/include/uapi/linux/prctl.h b/tools/perf/trace/beauty/include/uapi/linux/prctl.h
index 15c18ef4eb11..43dec6eed559 100644
--- a/tools/perf/trace/beauty/include/uapi/linux/prctl.h
+++ b/tools/perf/trace/beauty/include/uapi/linux/prctl.h
@@ -364,4 +364,11 @@ struct prctl_mm_map {
 # define PR_TIMER_CREATE_RESTORE_IDS_ON		1
 # define PR_TIMER_CREATE_RESTORE_IDS_GET	2
 
+/* FUTEX hash management */
+#define PR_FUTEX_HASH			78
+# define PR_FUTEX_HASH_SET_SLOTS	1
+# define FH_FLAG_IMMUTABLE		(1ULL << 0)
+# define PR_FUTEX_HASH_GET_SLOTS	2
+# define PR_FUTEX_HASH_GET_IMMUTABLE	3
+
 #endif /* _LINUX_PRCTL_H */

From f1e30a4269f9636ffe6b0556f336633fac524ba7 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 10 Jun 2025 17:46:03 -0300
Subject: [PATCH 0415/1334] tools kvm headers arm64: Update KVM header from the
 kernel sources

To pick the changes from:

  b7628c7973765c85 ("KVM: arm64: Allow userspace to limit the number of PMU counters for EL2 VMs")

That doesn't result in any changes in tooling (built on a Raspberry PI 5
running Debian GNU/Linux 12 (bookworm)), only addresses this perf build
warning:

Warning: Kernel ABI header differences:
  diff -u tools/arch/arm64/include/uapi/asm/kvm.h arch/arm64/include/uapi/asm/kvm.h

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Marc Zyngier <maz@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/r/
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/arch/arm64/include/uapi/asm/kvm.h | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h
index af9d9acaf997..ed5f3892674c 100644
--- a/tools/arch/arm64/include/uapi/asm/kvm.h
+++ b/tools/arch/arm64/include/uapi/asm/kvm.h
@@ -431,10 +431,11 @@ enum {
 
 /* Device Control API on vcpu fd */
 #define KVM_ARM_VCPU_PMU_V3_CTRL	0
-#define   KVM_ARM_VCPU_PMU_V3_IRQ	0
-#define   KVM_ARM_VCPU_PMU_V3_INIT	1
-#define   KVM_ARM_VCPU_PMU_V3_FILTER	2
-#define   KVM_ARM_VCPU_PMU_V3_SET_PMU	3
+#define   KVM_ARM_VCPU_PMU_V3_IRQ		0
+#define   KVM_ARM_VCPU_PMU_V3_INIT		1
+#define   KVM_ARM_VCPU_PMU_V3_FILTER		2
+#define   KVM_ARM_VCPU_PMU_V3_SET_PMU		3
+#define   KVM_ARM_VCPU_PMU_V3_SET_NR_COUNTERS	4
 #define KVM_ARM_VCPU_TIMER_CTRL		1
 #define   KVM_ARM_VCPU_TIMER_IRQ_VTIMER		0
 #define   KVM_ARM_VCPU_TIMER_IRQ_PTIMER		1

From c30c18709587bba7753f8ee2419bacc9100d6b40 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Thu, 12 Jun 2025 10:44:07 -0300
Subject: [PATCH 0416/1334] tools headers UAPI: Sync KVM's vmx.h header with
 the kernel sources

To pick the changes in:

  6c441e4d6e729616 ("KVM: TDX: Handle EXIT_REASON_OTHER_SMI")
  c42856af8f70d983 ("KVM: TDX: Add a place holder for handler of TDX hypercalls (TDG.VP.VMCALL)")

That makes 'perf kvm-stat' aware of this new TDCALL exit reason, thus
addressing the following perf build warning:

  Warning: Kernel ABI header differences:
    diff -u tools/arch/x86/include/uapi/asm/vmx.h arch/x86/include/uapi/asm/vmx.h

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Isaku Yamahata <isaku.yamahata@intel.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Link: https://lore.kernel.org/r/aErcVn_4plQyODR1@x1
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/arch/x86/include/uapi/asm/vmx.h | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/tools/arch/x86/include/uapi/asm/vmx.h b/tools/arch/x86/include/uapi/asm/vmx.h
index a5faf6d88f1b..f0f4a4cf84a7 100644
--- a/tools/arch/x86/include/uapi/asm/vmx.h
+++ b/tools/arch/x86/include/uapi/asm/vmx.h
@@ -34,6 +34,7 @@
 #define EXIT_REASON_TRIPLE_FAULT        2
 #define EXIT_REASON_INIT_SIGNAL			3
 #define EXIT_REASON_SIPI_SIGNAL         4
+#define EXIT_REASON_OTHER_SMI           6
 
 #define EXIT_REASON_INTERRUPT_WINDOW    7
 #define EXIT_REASON_NMI_WINDOW          8
@@ -92,6 +93,7 @@
 #define EXIT_REASON_TPAUSE              68
 #define EXIT_REASON_BUS_LOCK            74
 #define EXIT_REASON_NOTIFY              75
+#define EXIT_REASON_TDCALL              77
 
 #define VMX_EXIT_REASONS \
 	{ EXIT_REASON_EXCEPTION_NMI,         "EXCEPTION_NMI" }, \
@@ -155,7 +157,8 @@
 	{ EXIT_REASON_UMWAIT,                "UMWAIT" }, \
 	{ EXIT_REASON_TPAUSE,                "TPAUSE" }, \
 	{ EXIT_REASON_BUS_LOCK,              "BUS_LOCK" }, \
-	{ EXIT_REASON_NOTIFY,                "NOTIFY" }
+	{ EXIT_REASON_NOTIFY,                "NOTIFY" }, \
+	{ EXIT_REASON_TDCALL,                "TDCALL" }
 
 #define VMX_EXIT_REASON_FLAGS \
 	{ VMX_EXIT_REASONS_FAILED_VMENTRY,	"FAILED_VMENTRY" }

From da845e4bf4587cf4a212b607b6d508b00eab5217 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Thu, 12 Jun 2025 10:49:47 -0300
Subject: [PATCH 0417/1334] tools headers x86 svm: Sync svm headers with the
 kernel sources

To pick the changes in:

  827547bc3a2a2af6 ("KVM: SVM: Add architectural definitions/assets for Bus Lock Threshold")

That triggers:

  CC      /tmp/build/perf-tools/arch/x86/util/kvm-stat.o
  LD      /tmp/build/perf-tools/arch/x86/util/perf-util-in.o
  LD      /tmp/build/perf-tools/arch/x86/perf-util-in.o
  LD      /tmp/build/perf-tools/arch/perf-util-in.o
  LD      /tmp/build/perf-tools/perf-util-in.o
  AR      /tmp/build/perf-tools/libperf-util.a
  LINK    /tmp/build/perf-tools/perf

The SVM_EXIT_BUS_LOCK exit reason was added to SVM_EXIT_REASONS, used in
kvm-stat.c.

This addresses this perf build warning:

 Warning: Kernel ABI header differences:
  diff -u tools/arch/x86/include/uapi/asm/svm.h arch/x86/include/uapi/asm/svm.h

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Nikunj A Dadhania <nikunj@amd.com>
Cc: Sean Christopherson <seanjc@google.com>
Link: https://lore.kernel.org/r/aErcjuTTCVEZ-8Nb@x1
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/arch/x86/include/uapi/asm/svm.h | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/tools/arch/x86/include/uapi/asm/svm.h b/tools/arch/x86/include/uapi/asm/svm.h
index ec1321248dac..9c640a521a67 100644
--- a/tools/arch/x86/include/uapi/asm/svm.h
+++ b/tools/arch/x86/include/uapi/asm/svm.h
@@ -95,6 +95,7 @@
 #define SVM_EXIT_CR14_WRITE_TRAP		0x09e
 #define SVM_EXIT_CR15_WRITE_TRAP		0x09f
 #define SVM_EXIT_INVPCID       0x0a2
+#define SVM_EXIT_BUS_LOCK			0x0a5
 #define SVM_EXIT_IDLE_HLT      0x0a6
 #define SVM_EXIT_NPF           0x400
 #define SVM_EXIT_AVIC_INCOMPLETE_IPI		0x401
@@ -225,6 +226,7 @@
 	{ SVM_EXIT_CR4_WRITE_TRAP,	"write_cr4_trap" }, \
 	{ SVM_EXIT_CR8_WRITE_TRAP,	"write_cr8_trap" }, \
 	{ SVM_EXIT_INVPCID,     "invpcid" }, \
+	{ SVM_EXIT_BUS_LOCK,     "buslock" }, \
 	{ SVM_EXIT_IDLE_HLT,     "idle-halt" }, \
 	{ SVM_EXIT_NPF,         "npf" }, \
 	{ SVM_EXIT_AVIC_INCOMPLETE_IPI,		"avic_incomplete_ipi" }, \

From 8fc50bec411e9cc7bba441dc6f7de9af30ea9cbb Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Thu, 12 Jun 2025 11:31:41 -0300
Subject: [PATCH 0418/1334] tools headers UAPI: Sync kvm header with the kernel
 sources

To pick the changes in:

  c9c1e20b4c7d60fa ("KVM: x86: Introduce Intel specific quirk KVM_X86_QUIRK_IGNORE_GUEST_PAT")
  012426d6f59cab21 ("KVM: TDX: Finalize VM initialization")
  c846b451d3c5d4ba ("KVM: TDX: Add an ioctl to create initial guest memory")
  488808e682e72bdb ("KVM: x86: Introduce KVM_TDX_GET_CPUID")
  a50f673f25e0ba2b ("KVM: TDX: Do TDX specific vcpu initialization")
  0186dd29a251866d ("KVM: TDX: add ioctl to initialize VM with TDX specific parameters")
  61bb28279623b636 ("KVM: TDX: Get system-wide info about TDX module on initialization")
  b2aaf38ced6905b8 ("KVM: TDX: Add place holder for TDX VM specific mem_enc_op ioctl")

This addresses these perf build warnings:

  Warning: Kernel ABI header differences:
    diff -u tools/arch/x86/include/uapi/asm/kvm.h arch/x86/include/uapi/asm/kvm.h

Please see tools/include/uapi/README for further details.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Isaku Yamahata <isaku.yamahata@intel.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Xiaoyao Li <xiaoyao.li@intel.com>
Cc: Yan Zhao <yan.y.zhao@intel.com>
Link: https://lore.kernel.org/r/aErqLPktXIzGyS-m@x1
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/arch/x86/include/uapi/asm/kvm.h | 71 +++++++++++++++++++++++++++
 1 file changed, 71 insertions(+)

diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h
index b663d916f162..6f3499507c5e 100644
--- a/tools/arch/x86/include/uapi/asm/kvm.h
+++ b/tools/arch/x86/include/uapi/asm/kvm.h
@@ -441,6 +441,7 @@ struct kvm_sync_regs {
 #define KVM_X86_QUIRK_MWAIT_NEVER_UD_FAULTS	(1 << 6)
 #define KVM_X86_QUIRK_SLOT_ZAP_ALL		(1 << 7)
 #define KVM_X86_QUIRK_STUFF_FEATURE_MSRS	(1 << 8)
+#define KVM_X86_QUIRK_IGNORE_GUEST_PAT		(1 << 9)
 
 #define KVM_STATE_NESTED_FORMAT_VMX	0
 #define KVM_STATE_NESTED_FORMAT_SVM	1
@@ -931,4 +932,74 @@ struct kvm_hyperv_eventfd {
 #define KVM_X86_SNP_VM		4
 #define KVM_X86_TDX_VM		5
 
+/* Trust Domain eXtension sub-ioctl() commands. */
+enum kvm_tdx_cmd_id {
+	KVM_TDX_CAPABILITIES = 0,
+	KVM_TDX_INIT_VM,
+	KVM_TDX_INIT_VCPU,
+	KVM_TDX_INIT_MEM_REGION,
+	KVM_TDX_FINALIZE_VM,
+	KVM_TDX_GET_CPUID,
+
+	KVM_TDX_CMD_NR_MAX,
+};
+
+struct kvm_tdx_cmd {
+	/* enum kvm_tdx_cmd_id */
+	__u32 id;
+	/* flags for sub-commend. If sub-command doesn't use this, set zero. */
+	__u32 flags;
+	/*
+	 * data for each sub-command. An immediate or a pointer to the actual
+	 * data in process virtual address.  If sub-command doesn't use it,
+	 * set zero.
+	 */
+	__u64 data;
+	/*
+	 * Auxiliary error code.  The sub-command may return TDX SEAMCALL
+	 * status code in addition to -Exxx.
+	 */
+	__u64 hw_error;
+};
+
+struct kvm_tdx_capabilities {
+	__u64 supported_attrs;
+	__u64 supported_xfam;
+	__u64 reserved[254];
+
+	/* Configurable CPUID bits for userspace */
+	struct kvm_cpuid2 cpuid;
+};
+
+struct kvm_tdx_init_vm {
+	__u64 attributes;
+	__u64 xfam;
+	__u64 mrconfigid[6];	/* sha384 digest */
+	__u64 mrowner[6];	/* sha384 digest */
+	__u64 mrownerconfig[6];	/* sha384 digest */
+
+	/* The total space for TD_PARAMS before the CPUIDs is 256 bytes */
+	__u64 reserved[12];
+
+	/*
+	 * Call KVM_TDX_INIT_VM before vcpu creation, thus before
+	 * KVM_SET_CPUID2.
+	 * This configuration supersedes KVM_SET_CPUID2s for VCPUs because the
+	 * TDX module directly virtualizes those CPUIDs without VMM.  The user
+	 * space VMM, e.g. qemu, should make KVM_SET_CPUID2 consistent with
+	 * those values.  If it doesn't, KVM may have wrong idea of vCPUIDs of
+	 * the guest, and KVM may wrongly emulate CPUIDs or MSRs that the TDX
+	 * module doesn't virtualize.
+	 */
+	struct kvm_cpuid2 cpuid;
+};
+
+#define KVM_TDX_MEASURE_MEMORY_REGION   _BITULL(0)
+
+struct kvm_tdx_init_mem_region {
+	__u64 source_addr;
+	__u64 gpa;
+	__u64 nr_pages;
+};
+
 #endif /* _ASM_X86_KVM_H */

From 47684bfb7c3405aa8f7bfb31f2aa642ffd2b640f Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Thu, 12 Jun 2025 11:55:54 -0300
Subject: [PATCH 0419/1334] perf beauty: Update copy of linux/socket.h with the
 kernel sources

To pick the changes in:

  b1e904999542ad67 ("net: pass const to msg_data_left()")

That don't result in any changes in the tables generated from that
header.

This silences this perf build warning:

  Warning: Kernel ABI header differences:
    diff -u tools/perf/trace/beauty/include/linux/socket.h include/linux/socket.h

Please see tools/include/uapi/README for details.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Breno Leitao <leitao@debian.org>
Cc: Ian Rogers <irogers@google.com>
Cc: Jakub Kicinski <kuba@kernel.org>
Cc: James Clark <james.clark@linaro.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/r/aErrK24XLUILFH_P@x1
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/trace/beauty/include/linux/socket.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/trace/beauty/include/linux/socket.h b/tools/perf/trace/beauty/include/linux/socket.h
index c3322eb3d686..3b262487ec06 100644
--- a/tools/perf/trace/beauty/include/linux/socket.h
+++ b/tools/perf/trace/beauty/include/linux/socket.h
@@ -168,7 +168,7 @@ static inline struct cmsghdr * cmsg_nxthdr (struct msghdr *__msg, struct cmsghdr
 	return __cmsg_nxthdr(__msg->msg_control, __msg->msg_controllen, __cmsg);
 }
 
-static inline size_t msg_data_left(struct msghdr *msg)
+static inline size_t msg_data_left(const struct msghdr *msg)
 {
 	return iov_iter_count(&msg->msg_iter);
 }

From c71bc5995409395d5c9094144534912886fd09a7 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Thu, 12 Jun 2025 12:03:28 -0300
Subject: [PATCH 0420/1334] tools headers UAPI: Sync the drm/drm.h with the
 kernel sources
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Picking the changes from:

  c2d3a730069545f2 ("drm/syncobj: Extend EXPORT_SYNC_FILE for timeline syncobjs")

Silencing these perf build warnings:

  Warning: Kernel ABI header differences:
    diff -u tools/include/uapi/drm/drm.h include/uapi/drm/drm.h

No changes in tooling as these are just C comment documentation changes:

  $ tools/perf/trace/beauty/drm_ioctl.sh > before
  $ cp include/uapi/drm/drm.h tools/include/uapi/drm/drm.h
  $ tools/perf/trace/beauty/drm_ioctl.sh > after
  $ diff -u before after
  $

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Christian König <christian.koenig@amd.com>
Cc: Ian Rogers <irogers@google.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Rob Clark <robin.clark@oss.qualcomm.com>
Link: https://lore.kernel.org/r/aErtHs3T2hdPjjHx@x1
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/include/uapi/drm/drm.h | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/tools/include/uapi/drm/drm.h b/tools/include/uapi/drm/drm.h
index 7fba37b94401..e63a71d3c607 100644
--- a/tools/include/uapi/drm/drm.h
+++ b/tools/include/uapi/drm/drm.h
@@ -905,13 +905,17 @@ struct drm_syncobj_destroy {
 };
 
 #define DRM_SYNCOBJ_FD_TO_HANDLE_FLAGS_IMPORT_SYNC_FILE (1 << 0)
+#define DRM_SYNCOBJ_FD_TO_HANDLE_FLAGS_TIMELINE         (1 << 1)
 #define DRM_SYNCOBJ_HANDLE_TO_FD_FLAGS_EXPORT_SYNC_FILE (1 << 0)
+#define DRM_SYNCOBJ_HANDLE_TO_FD_FLAGS_TIMELINE         (1 << 1)
 struct drm_syncobj_handle {
 	__u32 handle;
 	__u32 flags;
 
 	__s32 fd;
 	__u32 pad;
+
+	__u64 point;
 };
 
 struct drm_syncobj_transfer {

From aa69783a5920d5924d95a198917fa3dd9c2c84a3 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Thu, 12 Jun 2025 12:08:45 -0300
Subject: [PATCH 0421/1334] tools headers UAPI: Sync linux/kvm.h with the
 kernel sources
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

To pick the changes in:

  5b9db9c16f428ada ("RISC-V: KVM: add KVM_CAP_RISCV_MP_STATE_RESET")
  a7484c80e5ca1ae0 ("KVM: arm64: Allow userspace to request KVM_ARM_VCPU_EL2*")
  79462faa2b2aa89d ("KVM: TDX: Handle TDG.VP.VMCALL<ReportFatalError>")

That just rebuilds perf, as these patches don't add any new KVM ioctl to
be harvested for the the 'perf trace' ioctl syscall argument
beautifiers.

This addresses this perf build warning:

  Warning: Kernel ABI header differences:
    diff -u tools/include/uapi/linux/kvm.h include/uapi/linux/kvm.h

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Anup Patel <anup@brainfault.org>
Cc: Binbin Wu <binbin.wu@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Marc Zyngier <maz@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Radim Krčmář <rkrcmar@ventanamicro.com>
Link: https://lore.kernel.org/r/aEruUUJvR0bfCg7_@x1
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/include/uapi/linux/kvm.h | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index b6ae8ad8934b..d00b85cb168c 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -375,6 +375,7 @@ struct kvm_run {
 #define KVM_SYSTEM_EVENT_WAKEUP         4
 #define KVM_SYSTEM_EVENT_SUSPEND        5
 #define KVM_SYSTEM_EVENT_SEV_TERM       6
+#define KVM_SYSTEM_EVENT_TDX_FATAL      7
 			__u32 type;
 			__u32 ndata;
 			union {
@@ -930,6 +931,9 @@ struct kvm_enable_cap {
 #define KVM_CAP_X86_APIC_BUS_CYCLES_NS 237
 #define KVM_CAP_X86_GUEST_MODE 238
 #define KVM_CAP_ARM_WRITABLE_IMP_ID_REGS 239
+#define KVM_CAP_ARM_EL2 240
+#define KVM_CAP_ARM_EL2_E2H0 241
+#define KVM_CAP_RISCV_MP_STATE_RESET 242
 
 struct kvm_irq_routing_irqchip {
 	__u32 irqchip;

From 00c8fde72fe2cdbd3892fbdc338c2d3a66ec8db3 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Thu, 12 Jun 2025 12:29:23 -0300
Subject: [PATCH 0422/1334] tools headers: Update the copy of x86's
 mem{cpy,set}_64.S used in 'perf bench'

Also add SYM_PIC_ALIAS() to tools/perf/util/include/linux/linkage.h.

This is to get the changes from:

  419cbaf6a56a6e4b ("x86/boot: Add a bunch of PIC aliases")

That addresses these perf tools build warning:

  Warning: Kernel ABI header differences:
    diff -u tools/arch/x86/lib/memcpy_64.S arch/x86/lib/memcpy_64.S
    diff -u tools/arch/x86/lib/memset_64.S arch/x86/lib/memset_64.S

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ard Biesheuvel <ardb@kernel.org>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: James Clark <james.clark@linaro.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/r/aEry7L3fibwIG5au@x1
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/arch/x86/lib/memcpy_64.S          | 1 +
 tools/arch/x86/lib/memset_64.S          | 1 +
 tools/perf/util/include/linux/linkage.h | 4 ++++
 3 files changed, 6 insertions(+)

diff --git a/tools/arch/x86/lib/memcpy_64.S b/tools/arch/x86/lib/memcpy_64.S
index 59cf6f9065aa..ccc3d923fc1e 100644
--- a/tools/arch/x86/lib/memcpy_64.S
+++ b/tools/arch/x86/lib/memcpy_64.S
@@ -40,6 +40,7 @@ SYM_FUNC_END(__memcpy)
 EXPORT_SYMBOL(__memcpy)
 
 SYM_FUNC_ALIAS_MEMFUNC(memcpy, __memcpy)
+SYM_PIC_ALIAS(memcpy)
 EXPORT_SYMBOL(memcpy)
 
 SYM_FUNC_START_LOCAL(memcpy_orig)
diff --git a/tools/arch/x86/lib/memset_64.S b/tools/arch/x86/lib/memset_64.S
index d66b710d628f..fb5a03cf5ab7 100644
--- a/tools/arch/x86/lib/memset_64.S
+++ b/tools/arch/x86/lib/memset_64.S
@@ -42,6 +42,7 @@ SYM_FUNC_END(__memset)
 EXPORT_SYMBOL(__memset)
 
 SYM_FUNC_ALIAS_MEMFUNC(memset, __memset)
+SYM_PIC_ALIAS(memset)
 EXPORT_SYMBOL(memset)
 
 SYM_FUNC_START_LOCAL(memset_orig)
diff --git a/tools/perf/util/include/linux/linkage.h b/tools/perf/util/include/linux/linkage.h
index 178b00205fe6..89979ca23c3f 100644
--- a/tools/perf/util/include/linux/linkage.h
+++ b/tools/perf/util/include/linux/linkage.h
@@ -132,4 +132,8 @@
         SYM_TYPED_START(name, SYM_L_GLOBAL, SYM_A_ALIGN)
 #endif
 
+#ifndef SYM_PIC_ALIAS
+#define SYM_PIC_ALIAS(sym)	SYM_ALIAS(__pi_ ## sym, sym, SYM_T_FUNC, SYM_L_GLOBAL)
+#endif
+
 #endif	/* PERF_LINUX_LINKAGE_H_ */

From 3417404c6f83c5d72d69ae81ded914bdc3841a49 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Thu, 12 Jun 2025 12:53:37 -0300
Subject: [PATCH 0423/1334] tools headers: Syncronize linux/build_bug.h with
 the kernel sources

To pick up the changes in:

  243c90e917f5cfc9 ("build_bug.h: more user friendly error messages in BUILD_BUG_ON_ZERO()")

This also needed to pick the __BUILD_BUG_ON_ZERO_MSG() in
linux/compiler.h, that needed to be polished to avoid hitting old clang
problems with _Static_assert on arrays of structs:

  Debian clang version 11.0.1-2~deb10u1

  Debian clang version 11.0.1-2~deb10u1
  $ make NO_LIBTRACEEVENT=1 ARCH= CROSS_COMPILE= EXTRA_CFLAGS= -C tools/perf O=/tmp/build/perf CC=clang
  <SNIP>
  btf_dump.c:895:18: error: type name does not allow storage class to be specified
          for (i = 0; i < ARRAY_SIZE(pads); i++) {
                          ^
  /git/perf-6.16.0-rc1/tools/include/linux/kernel.h:91:59: note: expanded from macro 'ARRAY_SIZE'
  #define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0]) + __must_be_array(arr))
                                                            ^
  /git/perf-6.16.0-rc1/tools/include/linux/compiler-gcc.h:26:28: note: expanded from macro '__must_be_array'
  #define __must_be_array(a)      BUILD_BUG_ON_ZERO(__same_type((a), &(a)[0]))
                                  ^
  /git/perf-6.16.0-rc1/tools/include/linux/build_bug.h:17:2: note: expanded from macro 'BUILD_BUG_ON_ZERO'
          __BUILD_BUG_ON_ZERO_MSG(e, ##__VA_ARGS__, #e " is true")
          ^
  /git/perf-6.16.0-rc1/tools/include/linux/compiler.h:248:67: note: expanded from macro '__BUILD_BUG_ON_ZERO_MSG'
  #define __BUILD_BUG_ON_ZERO_MSG(e, msg, ...) ((int)sizeof(struct {_Static_assert(!(e), msg);}))
                                                                    ^
  /usr/include/x86_64-linux-gnu/sys/cdefs.h:438:5: note: expanded from macro '_Static_assert'
      extern int (*__Static_assert_function (void)) \
      ^

These also failed:

toolsbuilder@five:~$ grep FAIL dm.log/summary | grep clang
   1    72.87 almalinux:8    : FAIL clang version 19.1.7 ( 19.1.7-2.module_el8.10.0+3990+33d0d926)
  15    73.39 centos:stream  : FAIL clang version 17.0.6 (Red Hat 17.0.6-1.module_el8+767+9fa966b8)
  36    87.14 opensuse:15.4  : FAIL clang version 15.0.7
  37    80.08 opensuse:15.5  : FAIL clang version 15.0.7
  40    72.12 oraclelinux:8  : FAIL clang version 16.0.6 (Red Hat 16.0.6-2.0.1.module+el8.9.0+90129+d3ee8717)
  42    74.12 rockylinux:8   : FAIL clang version 16.0.6 (Red Hat 16.0.6-2.module+el8.9.0+1651+e10a8f6d)
toolsbuilder@five:~$

This addresses this perf build warning:

  Warning: Kernel ABI header differences:
    diff -u tools/include/linux/build_bug.h include/linux/build_bug.h

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Vincent Mailhol <mailhol.vincent@wanadoo.fr>
Cc: Yury Norov <yury.norov@gmail.com>
Link: https://lore.kernel.org/r/aEszb7SSIJB6Lp6f@x1
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/include/linux/build_bug.h | 10 +++++-----
 tools/include/linux/compiler.h  |  8 ++++++++
 2 files changed, 13 insertions(+), 5 deletions(-)

diff --git a/tools/include/linux/build_bug.h b/tools/include/linux/build_bug.h
index b4898ff085de..ab2aa97bd8ce 100644
--- a/tools/include/linux/build_bug.h
+++ b/tools/include/linux/build_bug.h
@@ -4,17 +4,17 @@
 
 #include <linux/compiler.h>
 
-#ifdef __CHECKER__
-#define BUILD_BUG_ON_ZERO(e) (0)
-#else /* __CHECKER__ */
 /*
  * Force a compilation error if condition is true, but also produce a
  * result (of value 0 and type int), so the expression can be used
  * e.g. in a structure initializer (or where-ever else comma expressions
  * aren't permitted).
+ *
+ * Take an error message as an optional second argument. If omitted,
+ * default to the stringification of the tested expression.
  */
-#define BUILD_BUG_ON_ZERO(e) ((int)(sizeof(struct { int:(-!!(e)); })))
-#endif /* __CHECKER__ */
+#define BUILD_BUG_ON_ZERO(e, ...) \
+	__BUILD_BUG_ON_ZERO_MSG(e, ##__VA_ARGS__, #e " is true")
 
 /* Force a compilation error if a constant expression is not a power of 2 */
 #define __BUILD_BUG_ON_NOT_POWER_OF_2(n)	\
diff --git a/tools/include/linux/compiler.h b/tools/include/linux/compiler.h
index d627e66a04a6..33411ca0cc90 100644
--- a/tools/include/linux/compiler.h
+++ b/tools/include/linux/compiler.h
@@ -244,6 +244,14 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s
 	__asm__ ("" : "=r" (var) : "0" (var))
 #endif
 
+#ifndef __BUILD_BUG_ON_ZERO_MSG
+#if defined(__clang__)
+#define __BUILD_BUG_ON_ZERO_MSG(e, msg, ...) ((int)(sizeof(struct { int:(-!!(e)); })))
+#else
+#define __BUILD_BUG_ON_ZERO_MSG(e, msg, ...) ((int)sizeof(struct {_Static_assert(!(e), msg);}))
+#endif
+#endif
+
 #endif /* __ASSEMBLY__ */
 
 #endif /* _TOOLS_LINUX_COMPILER_H */

From 6143374c6dc874d301dc16612aed144bf4544bae Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Thu, 12 Jun 2025 17:58:05 -0300
Subject: [PATCH 0424/1334] tools arch x86: Sync the msr-index.h copy with the
 kernel sources

To pick up the changes from these csets:

  159013a7ca18c271 ("x86/its: Enumerate Indirect Target Selection (ITS) bug")
  f4138de5e41fae1a ("x86/msr: Standardize on u64 in <asm/msr-index.h>")
  ec980e4facef8110 ("perf/x86/intel: Support auto counter reload")

That cause no changes to tooling as it doesn't include a new MSR to be
captured by the tools/perf/trace/beauty/tracepoints/x86_msr.sh script.

Just silences this perf build warning:

  Warning: Kernel ABI header differences:
    diff -u tools/arch/x86/include/asm/msr-index.h arch/x86/include/asm/msr-index.h

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: James Clark <james.clark@linaro.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Pawan Gupta <pawan.kumar.gupta@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/aEtAUg83OQGx8Kay@x1
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/arch/x86/include/asm/msr-index.h | 16 ++++++++++------
 1 file changed, 10 insertions(+), 6 deletions(-)

diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h
index e7d2f460fcc6..b7dded3c8113 100644
--- a/tools/arch/x86/include/asm/msr-index.h
+++ b/tools/arch/x86/include/asm/msr-index.h
@@ -533,7 +533,7 @@
 #define MSR_HWP_CAPABILITIES		0x00000771
 #define MSR_HWP_REQUEST_PKG		0x00000772
 #define MSR_HWP_INTERRUPT		0x00000773
-#define MSR_HWP_REQUEST 		0x00000774
+#define MSR_HWP_REQUEST			0x00000774
 #define MSR_HWP_STATUS			0x00000777
 
 /* CPUID.6.EAX */
@@ -550,16 +550,16 @@
 #define HWP_LOWEST_PERF(x)		(((x) >> 24) & 0xff)
 
 /* IA32_HWP_REQUEST */
-#define HWP_MIN_PERF(x) 		(x & 0xff)
-#define HWP_MAX_PERF(x) 		((x & 0xff) << 8)
+#define HWP_MIN_PERF(x)			(x & 0xff)
+#define HWP_MAX_PERF(x)			((x & 0xff) << 8)
 #define HWP_DESIRED_PERF(x)		((x & 0xff) << 16)
-#define HWP_ENERGY_PERF_PREFERENCE(x)	(((unsigned long long) x & 0xff) << 24)
+#define HWP_ENERGY_PERF_PREFERENCE(x)	(((u64)x & 0xff) << 24)
 #define HWP_EPP_PERFORMANCE		0x00
 #define HWP_EPP_BALANCE_PERFORMANCE	0x80
 #define HWP_EPP_BALANCE_POWERSAVE	0xC0
 #define HWP_EPP_POWERSAVE		0xFF
-#define HWP_ACTIVITY_WINDOW(x)		((unsigned long long)(x & 0xff3) << 32)
-#define HWP_PACKAGE_CONTROL(x)		((unsigned long long)(x & 0x1) << 42)
+#define HWP_ACTIVITY_WINDOW(x)		((u64)(x & 0xff3) << 32)
+#define HWP_PACKAGE_CONTROL(x)		((u64)(x & 0x1) << 42)
 
 /* IA32_HWP_STATUS */
 #define HWP_GUARANTEED_CHANGE(x)	(x & 0x1)
@@ -602,7 +602,11 @@
 /* V6 PMON MSR range */
 #define MSR_IA32_PMC_V6_GP0_CTR		0x1900
 #define MSR_IA32_PMC_V6_GP0_CFG_A	0x1901
+#define MSR_IA32_PMC_V6_GP0_CFG_B	0x1902
+#define MSR_IA32_PMC_V6_GP0_CFG_C	0x1903
 #define MSR_IA32_PMC_V6_FX0_CTR		0x1980
+#define MSR_IA32_PMC_V6_FX0_CFG_B	0x1982
+#define MSR_IA32_PMC_V6_FX0_CFG_C	0x1983
 #define MSR_IA32_PMC_V6_STEP		4
 
 /* KeyID partitioning between MKTME and TDX */

From d8ab68bdb294b09a761e967dad374f2965e1913f Mon Sep 17 00:00:00 2001
From: Maurizio Lombardi <mlombard@redhat.com>
Date: Thu, 12 Jun 2025 12:15:56 +0200
Subject: [PATCH 0425/1334] scsi: target: Fix NULL pointer dereference in
 core_scsi3_decode_spec_i_port()

The function core_scsi3_decode_spec_i_port(), in its error code path,
unconditionally calls core_scsi3_lunacl_undepend_item() passing the
dest_se_deve pointer, which may be NULL.

This can lead to a NULL pointer dereference if dest_se_deve remains
unset.

SPC-3 PR SPEC_I_PT: Unable to locate dest_tpg
Unable to handle kernel paging request at virtual address dfff800000000012
Call trace:
  core_scsi3_lunacl_undepend_item+0x2c/0xf0 [target_core_mod] (P)
  core_scsi3_decode_spec_i_port+0x120c/0x1c30 [target_core_mod]
  core_scsi3_emulate_pro_register+0x6b8/0xcd8 [target_core_mod]
  target_scsi3_emulate_pr_out+0x56c/0x840 [target_core_mod]

Fix this by adding a NULL check before calling
core_scsi3_lunacl_undepend_item()

Signed-off-by: Maurizio Lombardi <mlombard@redhat.com>
Link: https://lore.kernel.org/r/20250612101556.24829-1-mlombard@redhat.com
Reviewed-by: Mike Christie <michael.christie@oracle.com>
Reviewed-by: John Meneghini <jmeneghi@redhat.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/target/target_core_pr.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/target/target_core_pr.c b/drivers/target/target_core_pr.c
index 34cf2c399b39..70905805cb17 100644
--- a/drivers/target/target_core_pr.c
+++ b/drivers/target/target_core_pr.c
@@ -1842,7 +1842,9 @@ out:
 		}
 
 		kmem_cache_free(t10_pr_reg_cache, dest_pr_reg);
-		core_scsi3_lunacl_undepend_item(dest_se_deve);
+
+		if (dest_se_deve)
+			core_scsi3_lunacl_undepend_item(dest_se_deve);
 
 		if (is_local)
 			continue;

From 594902c986e269660302f09df9ec4bf1cf017b77 Mon Sep 17 00:00:00 2001
From: Qinyun Tan <qinyuntan@linux.alibaba.com>
Date: Sat, 31 May 2025 02:20:53 +0800
Subject: [PATCH 0426/1334] x86,fs/resctrl: Remove inappropriate references to
 cacheinfo in the resctrl subsystem

In the resctrl subsystem's Sub-NUMA Cluster (SNC) mode, the rdt_mon_domain
structure representing a NUMA node relies on the cacheinfo interface
(rdt_mon_domain::ci) to store L3 cache information (e.g., shared_cpu_map)
for monitoring. The L3 cache information of a SNC NUMA node determines
which domains are summed for the "top level" L3-scoped events.

rdt_mon_domain::ci is initialized using the first online CPU of a NUMA
node. When this CPU goes offline, its shared_cpu_map is cleared to contain
only the offline CPU itself. Subsequently, attempting to read counters
via smp_call_on_cpu(offline_cpu) fails (and error ignored), returning
zero values for "top-level events" without any error indication.

Replace the cacheinfo references in struct rdt_mon_domain and struct
rmid_read with the cacheinfo ID (a unique identifier for the L3 cache).

rdt_domain_hdr::cpu_mask contains the online CPUs associated with that
domain. When reading "top-level events", select a CPU from
rdt_domain_hdr::cpu_mask and utilize its L3 shared_cpu_map to determine
valid CPUs for reading RMID counter via the MSR interface.

Considering all CPUs associated with the L3 cache improves the chances
of picking a housekeeping CPU on which the counter reading work can be
queued, avoiding an unnecessary IPI.

Fixes: 328ea68874642 ("x86/resctrl: Prepare for new Sub-NUMA Cluster (SNC) monitor files")
Signed-off-by: Qinyun Tan <qinyuntan@linux.alibaba.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Tested-by: Tony Luck <tony.luck@intel.com>
Link: https://lore.kernel.org/20250530182053.37502-2-qinyuntan@linux.alibaba.com
---
 arch/x86/kernel/cpu/resctrl/core.c |  6 ++++--
 fs/resctrl/ctrlmondata.c           | 13 +++++++++----
 fs/resctrl/internal.h              |  4 ++--
 fs/resctrl/monitor.c               |  6 ++++--
 fs/resctrl/rdtgroup.c              |  6 +++---
 include/linux/resctrl.h            |  4 ++--
 6 files changed, 24 insertions(+), 15 deletions(-)

diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index 7109cbfcad4f..187d527ef73b 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -498,6 +498,7 @@ static void domain_add_cpu_mon(int cpu, struct rdt_resource *r)
 	struct rdt_hw_mon_domain *hw_dom;
 	struct rdt_domain_hdr *hdr;
 	struct rdt_mon_domain *d;
+	struct cacheinfo *ci;
 	int err;
 
 	lockdep_assert_held(&domain_list_lock);
@@ -525,12 +526,13 @@ static void domain_add_cpu_mon(int cpu, struct rdt_resource *r)
 	d = &hw_dom->d_resctrl;
 	d->hdr.id = id;
 	d->hdr.type = RESCTRL_MON_DOMAIN;
-	d->ci = get_cpu_cacheinfo_level(cpu, RESCTRL_L3_CACHE);
-	if (!d->ci) {
+	ci = get_cpu_cacheinfo_level(cpu, RESCTRL_L3_CACHE);
+	if (!ci) {
 		pr_warn_once("Can't find L3 cache for CPU:%d resource %s\n", cpu, r->name);
 		mon_domain_free(hw_dom);
 		return;
 	}
+	d->ci_id = ci->id;
 	cpumask_set_cpu(cpu, &d->hdr.cpu_mask);
 
 	arch_mon_domain_online(r, d);
diff --git a/fs/resctrl/ctrlmondata.c b/fs/resctrl/ctrlmondata.c
index 6ed2dfd4dbbd..d98e0d2de09f 100644
--- a/fs/resctrl/ctrlmondata.c
+++ b/fs/resctrl/ctrlmondata.c
@@ -594,9 +594,10 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg)
 	struct rmid_read rr = {0};
 	struct rdt_mon_domain *d;
 	struct rdtgroup *rdtgrp;
+	int domid, cpu, ret = 0;
 	struct rdt_resource *r;
+	struct cacheinfo *ci;
 	struct mon_data *md;
-	int domid, ret = 0;
 
 	rdtgrp = rdtgroup_kn_lock_live(of->kn);
 	if (!rdtgrp) {
@@ -623,10 +624,14 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg)
 		 * one that matches this cache id.
 		 */
 		list_for_each_entry(d, &r->mon_domains, hdr.list) {
-			if (d->ci->id == domid) {
-				rr.ci = d->ci;
+			if (d->ci_id == domid) {
+				rr.ci_id = d->ci_id;
+				cpu = cpumask_any(&d->hdr.cpu_mask);
+				ci = get_cpu_cacheinfo_level(cpu, RESCTRL_L3_CACHE);
+				if (!ci)
+					continue;
 				mon_event_read(&rr, r, NULL, rdtgrp,
-					       &d->ci->shared_cpu_map, evtid, false);
+					       &ci->shared_cpu_map, evtid, false);
 				goto checkresult;
 			}
 		}
diff --git a/fs/resctrl/internal.h b/fs/resctrl/internal.h
index 9a8cf6f11151..0a1eedba2b03 100644
--- a/fs/resctrl/internal.h
+++ b/fs/resctrl/internal.h
@@ -98,7 +98,7 @@ struct mon_data {
  *	   domains in @r sharing L3 @ci.id
  * @evtid: Which monitor event to read.
  * @first: Initialize MBM counter when true.
- * @ci:    Cacheinfo for L3. Only set when @d is NULL. Used when summing domains.
+ * @ci_id: Cacheinfo id for L3. Only set when @d is NULL. Used when summing domains.
  * @err:   Error encountered when reading counter.
  * @val:   Returned value of event counter. If @rgrp is a parent resource group,
  *	   @val includes the sum of event counts from its child resource groups.
@@ -112,7 +112,7 @@ struct rmid_read {
 	struct rdt_mon_domain	*d;
 	enum resctrl_event_id	evtid;
 	bool			first;
-	struct cacheinfo	*ci;
+	unsigned int		ci_id;
 	int			err;
 	u64			val;
 	void			*arch_mon_ctx;
diff --git a/fs/resctrl/monitor.c b/fs/resctrl/monitor.c
index bde2801289d3..f5637855c3ac 100644
--- a/fs/resctrl/monitor.c
+++ b/fs/resctrl/monitor.c
@@ -361,6 +361,7 @@ static int __mon_event_count(u32 closid, u32 rmid, struct rmid_read *rr)
 {
 	int cpu = smp_processor_id();
 	struct rdt_mon_domain *d;
+	struct cacheinfo *ci;
 	struct mbm_state *m;
 	int err, ret;
 	u64 tval = 0;
@@ -388,7 +389,8 @@ static int __mon_event_count(u32 closid, u32 rmid, struct rmid_read *rr)
 	}
 
 	/* Summing domains that share a cache, must be on a CPU for that cache. */
-	if (!cpumask_test_cpu(cpu, &rr->ci->shared_cpu_map))
+	ci = get_cpu_cacheinfo_level(cpu, RESCTRL_L3_CACHE);
+	if (!ci || ci->id != rr->ci_id)
 		return -EINVAL;
 
 	/*
@@ -400,7 +402,7 @@ static int __mon_event_count(u32 closid, u32 rmid, struct rmid_read *rr)
 	 */
 	ret = -EINVAL;
 	list_for_each_entry(d, &rr->r->mon_domains, hdr.list) {
-		if (d->ci->id != rr->ci->id)
+		if (d->ci_id != rr->ci_id)
 			continue;
 		err = resctrl_arch_rmid_read(rr->r, d, closid, rmid,
 					     rr->evtid, &tval, rr->arch_mon_ctx);
diff --git a/fs/resctrl/rdtgroup.c b/fs/resctrl/rdtgroup.c
index 1beb124e25f6..77d08229d855 100644
--- a/fs/resctrl/rdtgroup.c
+++ b/fs/resctrl/rdtgroup.c
@@ -3036,7 +3036,7 @@ static void rmdir_mondata_subdir_allrdtgrp(struct rdt_resource *r,
 	char name[32];
 
 	snc_mode = r->mon_scope == RESCTRL_L3_NODE;
-	sprintf(name, "mon_%s_%02d", r->name, snc_mode ? d->ci->id : d->hdr.id);
+	sprintf(name, "mon_%s_%02d", r->name, snc_mode ? d->ci_id : d->hdr.id);
 	if (snc_mode)
 		sprintf(subname, "mon_sub_%s_%02d", r->name, d->hdr.id);
 
@@ -3061,7 +3061,7 @@ static int mon_add_all_files(struct kernfs_node *kn, struct rdt_mon_domain *d,
 		return -EPERM;
 
 	list_for_each_entry(mevt, &r->evt_list, list) {
-		domid = do_sum ? d->ci->id : d->hdr.id;
+		domid = do_sum ? d->ci_id : d->hdr.id;
 		priv = mon_get_kn_priv(r->rid, domid, mevt, do_sum);
 		if (WARN_ON_ONCE(!priv))
 			return -EINVAL;
@@ -3089,7 +3089,7 @@ static int mkdir_mondata_subdir(struct kernfs_node *parent_kn,
 	lockdep_assert_held(&rdtgroup_mutex);
 
 	snc_mode = r->mon_scope == RESCTRL_L3_NODE;
-	sprintf(name, "mon_%s_%02d", r->name, snc_mode ? d->ci->id : d->hdr.id);
+	sprintf(name, "mon_%s_%02d", r->name, snc_mode ? d->ci_id : d->hdr.id);
 	kn = kernfs_find_and_get(parent_kn, name);
 	if (kn) {
 		/*
diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h
index 9ba771f2ddea..6fb4894b8cfd 100644
--- a/include/linux/resctrl.h
+++ b/include/linux/resctrl.h
@@ -159,7 +159,7 @@ struct rdt_ctrl_domain {
 /**
  * struct rdt_mon_domain - group of CPUs sharing a resctrl monitor resource
  * @hdr:		common header for different domain types
- * @ci:			cache info for this domain
+ * @ci_id:		cache info id for this domain
  * @rmid_busy_llc:	bitmap of which limbo RMIDs are above threshold
  * @mbm_total:		saved state for MBM total bandwidth
  * @mbm_local:		saved state for MBM local bandwidth
@@ -170,7 +170,7 @@ struct rdt_ctrl_domain {
  */
 struct rdt_mon_domain {
 	struct rdt_domain_hdr		hdr;
-	struct cacheinfo		*ci;
+	unsigned int			ci_id;
 	unsigned long			*rmid_busy_llc;
 	struct mbm_state		*mbm_total;
 	struct mbm_state		*mbm_local;

From 9d4204a8106fe7dc80e3f2e440c8f2ba1ba47319 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Sun, 15 Jun 2025 18:06:54 -0700
Subject: [PATCH 0427/1334] lib/crypto/poly1305: Fix arm64's
 poly1305_blocks_arch()

For some reason arm64's Poly1305 code got changed to ignore the padbit
argument.  As a result, the output is incorrect when the message length
is not a multiple of 16 (which is not reached with the standard
ChaCha20Poly1305, but bcachefs could reach this).  Fix this.

Fixes: a59e5468a921 ("crypto: arm64/poly1305 - Add block-only interface")
Reported-by: Kent Overstreet <kent.overstreet@linux.dev>
Tested-by: Kent Overstreet <kent.overstreet@linux.dev>
Link: https://lore.kernel.org/r/20250616010654.367302-1-ebiggers@kernel.org
Signed-off-by: Eric Biggers <ebiggers@google.com>
---
 arch/arm64/lib/crypto/poly1305-glue.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/arm64/lib/crypto/poly1305-glue.c b/arch/arm64/lib/crypto/poly1305-glue.c
index 6a661cf04821..c9a74766785b 100644
--- a/arch/arm64/lib/crypto/poly1305-glue.c
+++ b/arch/arm64/lib/crypto/poly1305-glue.c
@@ -38,14 +38,14 @@ void poly1305_blocks_arch(struct poly1305_block_state *state, const u8 *src,
 			unsigned int todo = min_t(unsigned int, len, SZ_4K);
 
 			kernel_neon_begin();
-			poly1305_blocks_neon(state, src, todo, 1);
+			poly1305_blocks_neon(state, src, todo, padbit);
 			kernel_neon_end();
 
 			len -= todo;
 			src += todo;
 		} while (len);
 	} else
-		poly1305_blocks(state, src, len, 1);
+		poly1305_blocks(state, src, len, padbit);
 }
 EXPORT_SYMBOL_GPL(poly1305_blocks_arch);
 

From b2e673ae53ef4b943f68585207a5f21cfc9a0714 Mon Sep 17 00:00:00 2001
From: Avadhut Naik <avadhut.naik@amd.com>
Date: Fri, 13 Jun 2025 00:51:35 +0000
Subject: [PATCH 0428/1334] EDAC/amd64: Correct number of UMCs for family 19h
 models 70h-7fh

AMD's Family 19h-based Models 70h-7fh support 4 unified memory controllers
(UMC) per processor die.

The amd64_edac driver, however, assumes only 2 UMCs are supported since
max_mcs variable for the models has not been explicitly set to 4. The same
results in incomplete or incorrect memory information being logged to dmesg by
the module during initialization in some instances.

Fixes: 6c79e42169fe ("EDAC/amd64: Add support for ECC on family 19h model 60h-7Fh")
Closes: https://lore.kernel.org/all/27dc093f-ce27-4c71-9e81-786150a040b6@reox.at/
Reported-by: reox <mailinglist@reox.at>
Signed-off-by: Avadhut Naik <avadhut.naik@amd.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Cc: stable@kernel.org
Link: https://lore.kernel.org/20250613005233.2330627-1-avadhut.naik@amd.com
---
 drivers/edac/amd64_edac.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c
index 58b1482a0fbb..b681c0663203 100644
--- a/drivers/edac/amd64_edac.c
+++ b/drivers/edac/amd64_edac.c
@@ -3879,6 +3879,7 @@ static int per_family_init(struct amd64_pvt *pvt)
 			break;
 		case 0x70 ... 0x7f:
 			pvt->ctl_name			= "F19h_M70h";
+			pvt->max_mcs			= 4;
 			pvt->flags.zn_regs_v2		= 1;
 			break;
 		case 0x90 ... 0x9f:

From 1224b218a4b9203656ecc932152f4c81a97b4fcc Mon Sep 17 00:00:00 2001
From: Simon Horman <horms@kernel.org>
Date: Fri, 13 Jun 2025 17:46:20 +0100
Subject: [PATCH 0429/1334] pldmfw: Select CRC32 when PLDMFW is selected

pldmfw calls crc32 code and depends on it being enabled, else
there is a link error as follows. So PLDMFW should select CRC32.

  lib/pldmfw/pldmfw.o: In function `pldmfw_flash_image':
  pldmfw.c:(.text+0x70f): undefined reference to `crc32_le_base'

This problem was introduced by commit b8265621f488 ("Add pldmfw library
for PLDM firmware update").

It manifests as of commit d69ea414c9b4 ("ice: implement device flash
update via devlink").

And is more likely to occur as of commit 9ad19171b6d6 ("lib/crc: remove
unnecessary prompt for CONFIG_CRC32 and drop 'default y'").

Found by chance while exercising builds based on tinyconfig.

Fixes: b8265621f488 ("Add pldmfw library for PLDM firmware update")
Signed-off-by: Simon Horman <horms@kernel.org>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://patch.msgid.link/20250613-pldmfw-crc32-v1-1-f3fad109eee6@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 lib/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/lib/Kconfig b/lib/Kconfig
index 6c1b8f184267..37db228f70a9 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -716,6 +716,7 @@ config GENERIC_LIB_DEVMEM_IS_ALLOWED
 
 config PLDMFW
 	bool
+	select CRC32
 	default n
 
 config ASN1_ENCODER

From 2a8a5a5dd06eef580f9818567773fd75057cb875 Mon Sep 17 00:00:00 2001
From: Vitaliy Shevtsov <v.shevtsov@mt-integration.ru>
Date: Thu, 12 Jun 2025 21:35:18 +0500
Subject: [PATCH 0430/1334] scsi: elx: efct: Fix memory leak in
 efct_hw_parse_filter()

strsep() modifies the address of the pointer passed to it so that it no
longer points to the original address. This means kfree() gets the wrong
pointer.

Fix this by passing unmodified pointer returned from kstrdup() to
kfree().

Found by Linux Verification Center (linuxtesting.org) with Svace.

Fixes: 4df84e846624 ("scsi: elx: efct: Driver initialization routines")
Signed-off-by: Vitaliy Shevtsov <v.shevtsov@mt-integration.ru>
Link: https://lore.kernel.org/r/20250612163616.24298-1-v.shevtsov@mt-integration.ru
Reviewed-by: Daniel Wagner <dwagner@suse.de>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/elx/efct/efct_hw.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/scsi/elx/efct/efct_hw.c b/drivers/scsi/elx/efct/efct_hw.c
index 5a5525054d71..5b079b8b7a08 100644
--- a/drivers/scsi/elx/efct/efct_hw.c
+++ b/drivers/scsi/elx/efct/efct_hw.c
@@ -1120,7 +1120,7 @@ int
 efct_hw_parse_filter(struct efct_hw *hw, void *value)
 {
 	int rc = 0;
-	char *p = NULL;
+	char *p = NULL, *pp = NULL;
 	char *token;
 	u32 idx = 0;
 
@@ -1132,6 +1132,7 @@ efct_hw_parse_filter(struct efct_hw *hw, void *value)
 		efc_log_err(hw->os, "p is NULL\n");
 		return -ENOMEM;
 	}
+	pp = p;
 
 	idx = 0;
 	while ((token = strsep(&p, ",")) && *token) {
@@ -1144,7 +1145,7 @@ efct_hw_parse_filter(struct efct_hw *hw, void *value)
 		if (idx == ARRAY_SIZE(hw->config.filter_def))
 			break;
 	}
-	kfree(p);
+	kfree(pp);
 
 	return rc;
 }

From e1bc3a13bd775791cca0bb144d977b00f3598042 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ma=C3=ADra=20Canal?= <mcanal@igalia.com>
Date: Mon, 2 Jun 2025 12:14:02 -0300
Subject: [PATCH 0431/1334] drm/v3d: Avoid NULL pointer dereference in
 `v3d_job_update_stats()`
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The following kernel Oops was recently reported by Mesa CI:

[  800.139824] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000588
[  800.148619] Mem abort info:
[  800.151402]   ESR = 0x0000000096000005
[  800.155141]   EC = 0x25: DABT (current EL), IL = 32 bits
[  800.160444]   SET = 0, FnV = 0
[  800.163488]   EA = 0, S1PTW = 0
[  800.166619]   FSC = 0x05: level 1 translation fault
[  800.171487] Data abort info:
[  800.174357]   ISV = 0, ISS = 0x00000005, ISS2 = 0x00000000
[  800.179832]   CM = 0, WnR = 0, TnD = 0, TagAccess = 0
[  800.184873]   GCS = 0, Overlay = 0, DirtyBit = 0, Xs = 0
[  800.190176] user pgtable: 4k pages, 39-bit VAs, pgdp=00000001014c2000
[  800.196607] [0000000000000588] pgd=0000000000000000, p4d=0000000000000000, pud=0000000000000000
[  800.205305] Internal error: Oops: 0000000096000005 [#1] PREEMPT SMP
[  800.211564] Modules linked in: vc4 snd_soc_hdmi_codec drm_display_helper v3d cec gpu_sched drm_dma_helper drm_shmem_helper drm_kms_helper drm drm_panel_orientation_quirks snd_soc_core snd_compress snd_pcm_dmaengine snd_pcm i2c_brcmstb snd_timer snd backlight
[  800.234448] CPU: 0 UID: 0 PID: 0 Comm: swapper/0 Not tainted 6.12.25+rpt-rpi-v8 #1  Debian 1:6.12.25-1+rpt1
[  800.244182] Hardware name: Raspberry Pi 4 Model B Rev 1.4 (DT)
[  800.250005] pstate: 600000c5 (nZCv daIF -PAN -UAO -TCO -DIT -SSBS BTYPE=--)
[  800.256959] pc : v3d_job_update_stats+0x60/0x130 [v3d]
[  800.262112] lr : v3d_job_update_stats+0x48/0x130 [v3d]
[  800.267251] sp : ffffffc080003e60
[  800.270555] x29: ffffffc080003e60 x28: ffffffd842784980 x27: 0224012000000000
[  800.277687] x26: ffffffd84277f630 x25: ffffff81012fd800 x24: 0000000000000020
[  800.284818] x23: ffffff8040238b08 x22: 0000000000000570 x21: 0000000000000158
[  800.291948] x20: 0000000000000000 x19: ffffff8040238000 x18: 0000000000000000
[  800.299078] x17: ffffffa8c1bd2000 x16: ffffffc080000000 x15: 0000000000000000
[  800.306208] x14: 0000000000000000 x13: 0000000000000000 x12: 0000000000000000
[  800.313338] x11: 0000000000000040 x10: 0000000000001a40 x9 : ffffffd83b39757c
[  800.320468] x8 : ffffffd842786420 x7 : 7fffffffffffffff x6 : 0000000000ef32b0
[  800.327598] x5 : 00ffffffffffffff x4 : 0000000000000015 x3 : ffffffd842784980
[  800.334728] x2 : 0000000000000004 x1 : 0000000000010002 x0 : 000000ba4c0ca382
[  800.341859] Call trace:
[  800.344294]  v3d_job_update_stats+0x60/0x130 [v3d]
[  800.349086]  v3d_irq+0x124/0x2e0 [v3d]
[  800.352835]  __handle_irq_event_percpu+0x58/0x218
[  800.357539]  handle_irq_event+0x54/0xb8
[  800.361369]  handle_fasteoi_irq+0xac/0x240
[  800.365458]  handle_irq_desc+0x48/0x68
[  800.369200]  generic_handle_domain_irq+0x24/0x38
[  800.373810]  gic_handle_irq+0x48/0xd8
[  800.377464]  call_on_irq_stack+0x24/0x58
[  800.381379]  do_interrupt_handler+0x88/0x98
[  800.385554]  el1_interrupt+0x34/0x68
[  800.389123]  el1h_64_irq_handler+0x18/0x28
[  800.393211]  el1h_64_irq+0x64/0x68
[  800.396603]  default_idle_call+0x3c/0x168
[  800.400606]  do_idle+0x1fc/0x230
[  800.403827]  cpu_startup_entry+0x40/0x50
[  800.407742]  rest_init+0xe4/0xf0
[  800.410962]  start_kernel+0x5e8/0x790
[  800.414616]  __primary_switched+0x80/0x90
[  800.418622] Code: 8b170277 8b160296 11000421 b9000861 (b9401ac1)
[  800.424707] ---[ end trace 0000000000000000 ]---
[  800.457313] ---[ end Kernel panic - not syncing: Oops: Fatal exception in interrupt ]---

This issue happens when the file descriptor is closed before the jobs
submitted by it are completed. When the job completes, we update the
global GPU stats and the per-fd GPU stats, which are exposed through
fdinfo. If the file descriptor was closed, then the struct `v3d_file_priv`
and its stats were already freed and we can't update the per-fd stats.

Therefore, if the file descriptor was already closed, don't update the
per-fd GPU stats, only update the global ones.

Cc: stable@vger.kernel.org # v6.12+
Reviewed-by: Jose Maria Casanova Crespo <jmcasanova@igalia.com>
Link: https://lore.kernel.org/r/20250602151451.10161-1-mcanal@igalia.com
Signed-off-by: Maíra Canal <mcanal@igalia.com>
---
 drivers/gpu/drm/v3d/v3d_sched.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/v3d/v3d_sched.c b/drivers/gpu/drm/v3d/v3d_sched.c
index 35f131a46d07..42df9d3567e7 100644
--- a/drivers/gpu/drm/v3d/v3d_sched.c
+++ b/drivers/gpu/drm/v3d/v3d_sched.c
@@ -199,7 +199,6 @@ v3d_job_update_stats(struct v3d_job *job, enum v3d_queue queue)
 	struct v3d_dev *v3d = job->v3d;
 	struct v3d_file_priv *file = job->file->driver_priv;
 	struct v3d_stats *global_stats = &v3d->queue[queue].stats;
-	struct v3d_stats *local_stats = &file->stats[queue];
 	u64 now = local_clock();
 	unsigned long flags;
 
@@ -209,7 +208,12 @@ v3d_job_update_stats(struct v3d_job *job, enum v3d_queue queue)
 	else
 		preempt_disable();
 
-	v3d_stats_update(local_stats, now);
+	/* Don't update the local stats if the file context has already closed */
+	if (file)
+		v3d_stats_update(&file->stats[queue], now);
+	else
+		drm_dbg(&v3d->drm, "The file descriptor was closed before job completion\n");
+
 	v3d_stats_update(global_stats, now);
 
 	if (IS_ENABLED(CONFIG_LOCKDEP))

From 86c8db86af43f52f682e53a0f2f0828683be1e52 Mon Sep 17 00:00:00 2001
From: Stephen Smalley <stephen.smalley.work@gmail.com>
Date: Fri, 13 Jun 2025 15:37:05 -0400
Subject: [PATCH 0432/1334] selinux: fix selinux_xfrm_alloc_user() to set
 correct ctx_len
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We should count the terminating NUL byte as part of the ctx_len.
Otherwise, UBSAN logs a warning:
  UBSAN: array-index-out-of-bounds in security/selinux/xfrm.c:99:14
  index 60 is out of range for type 'char [*]'

The allocation itself is correct so there is no actual out of bounds
indexing, just a warning.

Cc: stable@vger.kernel.org
Suggested-by: Christian Göttsche <cgzones@googlemail.com>
Link: https://lore.kernel.org/selinux/CAEjxPJ6tA5+LxsGfOJokzdPeRomBHjKLBVR6zbrg+_w3ZZbM3A@mail.gmail.com/
Signed-off-by: Stephen Smalley <stephen.smalley.work@gmail.com>
Signed-off-by: Paul Moore <paul@paul-moore.com>
---
 security/selinux/xfrm.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/security/selinux/xfrm.c b/security/selinux/xfrm.c
index 90ec4ef1b082..61d56b0c2be1 100644
--- a/security/selinux/xfrm.c
+++ b/security/selinux/xfrm.c
@@ -94,7 +94,7 @@ static int selinux_xfrm_alloc_user(struct xfrm_sec_ctx **ctxp,
 
 	ctx->ctx_doi = XFRM_SC_DOI_LSM;
 	ctx->ctx_alg = XFRM_SC_ALG_SELINUX;
-	ctx->ctx_len = str_len;
+	ctx->ctx_len = str_len + 1;
 	memcpy(ctx->ctx_str, &uctx[1], str_len);
 	ctx->ctx_str[str_len] = '\0';
 	rc = security_context_to_sid(ctx->ctx_str, str_len,

From 17c3395e25f7db23fa5758c257a372d410d16cfd Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Sat, 7 Jun 2025 19:16:12 -0400
Subject: [PATCH 0433/1334] bcachefs: opts.journal_rewind

Add a mount option for rewinding the journal, bringing the entire
filesystem to where it was at a previous point in time.

This is for extreme disaster recovery scenarios - it's not intended as
an undelete operation.

The option takes a journal sequence number; the desired sequence number
can be determined with 'bcachefs list_journal'

Caveats:

- The 'journal_transaction_names' option must have been enabled (it's on
  by default). The option controls emitting of extra debug info in the
  journal, so we can see what individual transactions were doing;
  It also enables journalling of keys being overwritten, which is what
  we rely on here.

- A full fsck run will be automatically triggered since alloc info will
  be inconsistent. Only leaf node updates to non-alloc btrees are
  rewound, since rewinding interior btree updates isn't possible or
  desirable.

- We can't do anything about data that was deleted and overwritten.

  Lots of metadata updates after the point in time we're rewinding to
  shouldn't cause a problem, since we segragate data and metadata
  allocations (this is in order to make repair by btree node scan
  practical on larger filesystems; there's a small 64-bit per device
  bitmap in the superblock of device ranges with btree nodes, and we try
  to keep this small).

  However, having discards enabled will cause problems, since buckets
  are discarded as soon as they become empty (this is why we don't
  implement fstrim: we don't need it).

  Hopefully, this feature will be a one-off thing that's never used
  again: this was implemented for recovering from the "vfs i_nlink 0 ->
  subvol deletion" bug, and that bug was unusually disastrous and
  additional safeguards have since been implemented.

  But if it does turn out that we need this more in the future, I'll
  have to implement an option so that empty buckets aren't discarded
  immediately - lagging by perhaps 1% of device capacity.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/btree_journal_iter.c       | 56 +++++++++++++++++---------
 fs/bcachefs/btree_journal_iter_types.h |  5 ++-
 fs/bcachefs/journal_io.c               | 21 ++++++++--
 fs/bcachefs/opts.h                     |  5 +++
 fs/bcachefs/recovery.c                 |  5 +++
 5 files changed, 67 insertions(+), 25 deletions(-)

diff --git a/fs/bcachefs/btree_journal_iter.c b/fs/bcachefs/btree_journal_iter.c
index de996c848e43..a41fabd06332 100644
--- a/fs/bcachefs/btree_journal_iter.c
+++ b/fs/bcachefs/btree_journal_iter.c
@@ -641,10 +641,11 @@ static int journal_sort_key_cmp(const void *_l, const void *_r)
 {
 	const struct journal_key *l = _l;
 	const struct journal_key *r = _r;
+	int rewind = l->rewind && r->rewind ? -1 : 1;
 
 	return  journal_key_cmp(l, r) ?:
-		cmp_int(l->journal_seq, r->journal_seq) ?:
-		cmp_int(l->journal_offset, r->journal_offset);
+		((cmp_int(l->journal_seq, r->journal_seq) ?:
+		  cmp_int(l->journal_offset, r->journal_offset)) * rewind);
 }
 
 void bch2_journal_keys_put(struct bch_fs *c)
@@ -713,6 +714,8 @@ int bch2_journal_keys_sort(struct bch_fs *c)
 	struct journal_keys *keys = &c->journal_keys;
 	size_t nr_read = 0;
 
+	u64 rewind_seq = c->opts.journal_rewind ?: U64_MAX;
+
 	genradix_for_each(&c->journal_entries, iter, _i) {
 		i = *_i;
 
@@ -721,28 +724,43 @@ int bch2_journal_keys_sort(struct bch_fs *c)
 
 		cond_resched();
 
-		for_each_jset_key(k, entry, &i->j) {
-			struct journal_key n = (struct journal_key) {
-				.btree_id	= entry->btree_id,
-				.level		= entry->level,
-				.k		= k,
-				.journal_seq	= le64_to_cpu(i->j.seq),
-				.journal_offset	= k->_data - i->j._data,
-			};
+		vstruct_for_each(&i->j, entry) {
+			bool rewind = !entry->level &&
+				!btree_id_is_alloc(entry->btree_id) &&
+				le64_to_cpu(i->j.seq) >= rewind_seq;
 
-			if (darray_push(keys, n)) {
-				__journal_keys_sort(keys);
+			if (entry->type != (rewind
+					    ? BCH_JSET_ENTRY_overwrite
+					    : BCH_JSET_ENTRY_btree_keys))
+				continue;
 
-				if (keys->nr * 8 > keys->size * 7) {
-					bch_err(c, "Too many journal keys for slowpath; have %zu compacted, buf size %zu, processed %zu keys at seq %llu",
-						keys->nr, keys->size, nr_read, le64_to_cpu(i->j.seq));
-					return bch_err_throw(c, ENOMEM_journal_keys_sort);
+			if (!rewind && le64_to_cpu(i->j.seq) < c->journal_replay_seq_start)
+				continue;
+
+			jset_entry_for_each_key(entry, k) {
+				struct journal_key n = (struct journal_key) {
+					.btree_id	= entry->btree_id,
+					.level		= entry->level,
+					.rewind		= rewind,
+					.k		= k,
+					.journal_seq	= le64_to_cpu(i->j.seq),
+					.journal_offset	= k->_data - i->j._data,
+				};
+
+				if (darray_push(keys, n)) {
+					__journal_keys_sort(keys);
+
+					if (keys->nr * 8 > keys->size * 7) {
+						bch_err(c, "Too many journal keys for slowpath; have %zu compacted, buf size %zu, processed %zu keys at seq %llu",
+							keys->nr, keys->size, nr_read, le64_to_cpu(i->j.seq));
+						return bch_err_throw(c, ENOMEM_journal_keys_sort);
+					}
+
+					BUG_ON(darray_push(keys, n));
 				}
 
-				BUG_ON(darray_push(keys, n));
+				nr_read++;
 			}
-
-			nr_read++;
 		}
 	}
 
diff --git a/fs/bcachefs/btree_journal_iter_types.h b/fs/bcachefs/btree_journal_iter_types.h
index 8b773823704f..86aacb254fb2 100644
--- a/fs/bcachefs/btree_journal_iter_types.h
+++ b/fs/bcachefs/btree_journal_iter_types.h
@@ -11,8 +11,9 @@ struct journal_key {
 	u32			journal_offset;
 	enum btree_id		btree_id:8;
 	unsigned		level:8;
-	bool			allocated;
-	bool			overwritten;
+	bool			allocated:1;
+	bool			overwritten:1;
+	bool			rewind:1;
 	struct journal_key_range_overwritten __rcu *
 				overwritten_range;
 	struct bkey_i		*k;
diff --git a/fs/bcachefs/journal_io.c b/fs/bcachefs/journal_io.c
index 0b15d71a8d2d..afbf12e8f0c5 100644
--- a/fs/bcachefs/journal_io.c
+++ b/fs/bcachefs/journal_io.c
@@ -160,6 +160,9 @@ static int journal_entry_add(struct bch_fs *c, struct bch_dev *ca,
 	struct printbuf buf = PRINTBUF;
 	int ret = JOURNAL_ENTRY_ADD_OK;
 
+	if (last_seq && c->opts.journal_rewind)
+		last_seq = min(last_seq, c->opts.journal_rewind);
+
 	if (!c->journal.oldest_seq_found_ondisk ||
 	    le64_to_cpu(j->seq) < c->journal.oldest_seq_found_ondisk)
 		c->journal.oldest_seq_found_ondisk = le64_to_cpu(j->seq);
@@ -1430,11 +1433,21 @@ int bch2_journal_read(struct bch_fs *c,
 	printbuf_reset(&buf);
 	prt_printf(&buf, "journal read done, replaying entries %llu-%llu",
 		   *last_seq, *blacklist_seq - 1);
+
+	/*
+	 * Drop blacklisted entries and entries older than last_seq (or start of
+	 * journal rewind:
+	 */
+	u64 drop_before = *last_seq;
+	if (c->opts.journal_rewind) {
+		drop_before = min(drop_before, c->opts.journal_rewind);
+		prt_printf(&buf, " (rewinding from %llu)", c->opts.journal_rewind);
+	}
+
+	*last_seq = drop_before;
 	if (*start_seq != *blacklist_seq)
 		prt_printf(&buf, " (unflushed %llu-%llu)", *blacklist_seq, *start_seq - 1);
 	bch_info(c, "%s", buf.buf);
-
-	/* Drop blacklisted entries and entries older than last_seq: */
 	genradix_for_each(&c->journal_entries, radix_iter, _i) {
 		i = *_i;
 
@@ -1442,7 +1455,7 @@ int bch2_journal_read(struct bch_fs *c,
 			continue;
 
 		seq = le64_to_cpu(i->j.seq);
-		if (seq < *last_seq) {
+		if (seq < drop_before) {
 			journal_replay_free(c, i, false);
 			continue;
 		}
@@ -1455,7 +1468,7 @@ int bch2_journal_read(struct bch_fs *c,
 		}
 	}
 
-	ret = bch2_journal_check_for_missing(c, *last_seq, *blacklist_seq - 1);
+	ret = bch2_journal_check_for_missing(c, drop_before, *blacklist_seq - 1);
 	if (ret)
 		goto err;
 
diff --git a/fs/bcachefs/opts.h b/fs/bcachefs/opts.h
index 2a02606254b3..b0a76bd6d6f5 100644
--- a/fs/bcachefs/opts.h
+++ b/fs/bcachefs/opts.h
@@ -379,6 +379,11 @@ enum fsck_err_opts {
 	  OPT_BOOL(),							\
 	  BCH2_NO_SB_OPT,		false,				\
 	  NULL,		"Exit recovery immediately prior to journal replay")\
+	x(journal_rewind,		u64,				\
+	  OPT_FS|OPT_MOUNT,						\
+	  OPT_UINT(0, U64_MAX),						\
+	  BCH2_NO_SB_OPT,		0,				\
+	  NULL,		"Rewind journal")				\
 	x(recovery_passes,		u64,				\
 	  OPT_FS|OPT_MOUNT,						\
 	  OPT_BITFIELD(bch2_recovery_passes),				\
diff --git a/fs/bcachefs/recovery.c b/fs/bcachefs/recovery.c
index 820249e9c5ea..37f2cc1ec2f8 100644
--- a/fs/bcachefs/recovery.c
+++ b/fs/bcachefs/recovery.c
@@ -757,6 +757,11 @@ int bch2_fs_recovery(struct bch_fs *c)
 	if (c->opts.nochanges)
 		c->opts.read_only = true;
 
+	if (c->opts.journal_rewind) {
+		bch_info(c, "rewinding journal, fsck required");
+		c->opts.fsck = true;
+	}
+
 	mutex_lock(&c->sb_lock);
 	struct bch_sb_field_ext *ext = bch2_sb_field_get(c->disk_sb.sb, ext);
 	bool write_sb = false;

From 10dfe4926de30b550913409d107005278ab47911 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Fri, 13 Jun 2025 20:06:33 -0400
Subject: [PATCH 0434/1334] bcachefs: Kill unused tracepoints

Dead code cleanup.

Link: https://lore.kernel.org/linux-bcachefs/20250612224059.39fddd07@batman.local.home/
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/btree_trans_commit.c |   5 +-
 fs/bcachefs/btree_write_buffer.c |   3 +
 fs/bcachefs/errcode.h            |   5 --
 fs/bcachefs/trace.h              | 100 +------------------------------
 4 files changed, 9 insertions(+), 104 deletions(-)

diff --git a/fs/bcachefs/btree_trans_commit.c b/fs/bcachefs/btree_trans_commit.c
index 61107f2310ab..639ef75b3dbd 100644
--- a/fs/bcachefs/btree_trans_commit.c
+++ b/fs/bcachefs/btree_trans_commit.c
@@ -595,12 +595,13 @@ bch2_trans_commit_write_locked(struct btree_trans *trans, unsigned flags,
 	int ret = 0;
 
 	bch2_trans_verify_not_unlocked_or_in_restart(trans);
-
+#if 0
+	/* todo: bring back dynamic fault injection */
 	if (race_fault()) {
 		trace_and_count(c, trans_restart_fault_inject, trans, trace_ip);
 		return btree_trans_restart(trans, BCH_ERR_transaction_restart_fault_inject);
 	}
-
+#endif
 	/*
 	 * Check if the insert will fit in the leaf node with the write lock
 	 * held, otherwise another thread could write the node changing the
diff --git a/fs/bcachefs/btree_write_buffer.c b/fs/bcachefs/btree_write_buffer.c
index 90b21e61d2b6..21b5c03d1822 100644
--- a/fs/bcachefs/btree_write_buffer.c
+++ b/fs/bcachefs/btree_write_buffer.c
@@ -676,6 +676,9 @@ int bch2_btree_write_buffer_maybe_flush(struct btree_trans *trans,
 			goto err;
 
 		bch2_bkey_buf_copy(last_flushed, c, tmp.k);
+
+		/* can we avoid the unconditional restart? */
+		trace_and_count(c, trans_restart_write_buffer_flush, trans, _RET_IP_);
 		ret = bch_err_throw(c, transaction_restart_write_buffer_flush);
 	}
 err:
diff --git a/fs/bcachefs/errcode.h b/fs/bcachefs/errcode.h
index ac3264134a15..86a842f1e88e 100644
--- a/fs/bcachefs/errcode.h
+++ b/fs/bcachefs/errcode.h
@@ -137,7 +137,6 @@
 	x(BCH_ERR_transaction_restart,	transaction_restart_relock)		\
 	x(BCH_ERR_transaction_restart,	transaction_restart_relock_path)	\
 	x(BCH_ERR_transaction_restart,	transaction_restart_relock_path_intent)	\
-	x(BCH_ERR_transaction_restart,	transaction_restart_relock_after_fill)	\
 	x(BCH_ERR_transaction_restart,	transaction_restart_too_many_iters)	\
 	x(BCH_ERR_transaction_restart,	transaction_restart_lock_node_reused)	\
 	x(BCH_ERR_transaction_restart,	transaction_restart_fill_relock)	\
@@ -148,11 +147,8 @@
 	x(BCH_ERR_transaction_restart,	transaction_restart_would_deadlock_write)\
 	x(BCH_ERR_transaction_restart,	transaction_restart_deadlock_recursion_limit)\
 	x(BCH_ERR_transaction_restart,	transaction_restart_upgrade)		\
-	x(BCH_ERR_transaction_restart,	transaction_restart_key_cache_upgrade)	\
 	x(BCH_ERR_transaction_restart,	transaction_restart_key_cache_fill)	\
 	x(BCH_ERR_transaction_restart,	transaction_restart_key_cache_raced)	\
-	x(BCH_ERR_transaction_restart,	transaction_restart_key_cache_realloced)\
-	x(BCH_ERR_transaction_restart,	transaction_restart_journal_preres_get)	\
 	x(BCH_ERR_transaction_restart,	transaction_restart_split_race)		\
 	x(BCH_ERR_transaction_restart,	transaction_restart_write_buffer_flush)	\
 	x(BCH_ERR_transaction_restart,	transaction_restart_nested)		\
@@ -241,7 +237,6 @@
 	x(BCH_ERR_journal_res_blocked,	journal_buf_enomem)			\
 	x(BCH_ERR_journal_res_blocked,	journal_stuck)				\
 	x(BCH_ERR_journal_res_blocked,	journal_retry_open)			\
-	x(BCH_ERR_journal_res_blocked,	journal_preres_get_blocked)		\
 	x(BCH_ERR_journal_res_blocked,	bucket_alloc_blocked)			\
 	x(BCH_ERR_journal_res_blocked,	stripe_alloc_blocked)			\
 	x(BCH_ERR_invalid,		invalid_sb)				\
diff --git a/fs/bcachefs/trace.h b/fs/bcachefs/trace.h
index e759c9ff3965..9c5a9c551f03 100644
--- a/fs/bcachefs/trace.h
+++ b/fs/bcachefs/trace.h
@@ -1080,34 +1080,14 @@ TRACE_EVENT(trans_blocked_journal_reclaim,
 		  __entry->must_wait)
 );
 
-TRACE_EVENT(trans_restart_journal_preres_get,
-	TP_PROTO(struct btree_trans *trans,
-		 unsigned long caller_ip,
-		 unsigned flags),
-	TP_ARGS(trans, caller_ip, flags),
-
-	TP_STRUCT__entry(
-		__array(char,			trans_fn, 32	)
-		__field(unsigned long,		caller_ip	)
-		__field(unsigned,		flags		)
-	),
-
-	TP_fast_assign(
-		strscpy(__entry->trans_fn, trans->fn, sizeof(__entry->trans_fn));
-		__entry->caller_ip		= caller_ip;
-		__entry->flags			= flags;
-	),
-
-	TP_printk("%s %pS %x", __entry->trans_fn,
-		  (void *) __entry->caller_ip,
-		  __entry->flags)
-);
-
+#if 0
+/* todo: bring back dynamic fault injection */
 DEFINE_EVENT(transaction_event,	trans_restart_fault_inject,
 	TP_PROTO(struct btree_trans *trans,
 		 unsigned long caller_ip),
 	TP_ARGS(trans, caller_ip)
 );
+#endif
 
 DEFINE_EVENT(transaction_event,	trans_traverse_all,
 	TP_PROTO(struct btree_trans *trans,
@@ -1195,19 +1175,6 @@ DEFINE_EVENT(transaction_restart_iter,	trans_restart_relock_parent_for_fill,
 	TP_ARGS(trans, caller_ip, path)
 );
 
-DEFINE_EVENT(transaction_restart_iter,	trans_restart_relock_after_fill,
-	TP_PROTO(struct btree_trans *trans,
-		 unsigned long caller_ip,
-		 struct btree_path *path),
-	TP_ARGS(trans, caller_ip, path)
-);
-
-DEFINE_EVENT(transaction_event,	trans_restart_key_cache_upgrade,
-	TP_PROTO(struct btree_trans *trans,
-		 unsigned long caller_ip),
-	TP_ARGS(trans, caller_ip)
-);
-
 DEFINE_EVENT(transaction_restart_iter,	trans_restart_relock_key_cache_fill,
 	TP_PROTO(struct btree_trans *trans,
 		 unsigned long caller_ip,
@@ -1229,13 +1196,6 @@ DEFINE_EVENT(transaction_restart_iter,	trans_restart_relock_path_intent,
 	TP_ARGS(trans, caller_ip, path)
 );
 
-DEFINE_EVENT(transaction_restart_iter,	trans_restart_traverse,
-	TP_PROTO(struct btree_trans *trans,
-		 unsigned long caller_ip,
-		 struct btree_path *path),
-	TP_ARGS(trans, caller_ip, path)
-);
-
 DEFINE_EVENT(transaction_restart_iter,	trans_restart_memory_allocation_failure,
 	TP_PROTO(struct btree_trans *trans,
 		 unsigned long caller_ip,
@@ -1294,44 +1254,6 @@ TRACE_EVENT(trans_restart_mem_realloced,
 		  __entry->bytes)
 );
 
-TRACE_EVENT(trans_restart_key_cache_key_realloced,
-	TP_PROTO(struct btree_trans *trans,
-		 unsigned long caller_ip,
-		 struct btree_path *path,
-		 unsigned old_u64s,
-		 unsigned new_u64s),
-	TP_ARGS(trans, caller_ip, path, old_u64s, new_u64s),
-
-	TP_STRUCT__entry(
-		__array(char,			trans_fn, 32	)
-		__field(unsigned long,		caller_ip	)
-		__field(enum btree_id,		btree_id	)
-		TRACE_BPOS_entries(pos)
-		__field(u32,			old_u64s	)
-		__field(u32,			new_u64s	)
-	),
-
-	TP_fast_assign(
-		strscpy(__entry->trans_fn, trans->fn, sizeof(__entry->trans_fn));
-		__entry->caller_ip		= caller_ip;
-
-		__entry->btree_id	= path->btree_id;
-		TRACE_BPOS_assign(pos, path->pos);
-		__entry->old_u64s	= old_u64s;
-		__entry->new_u64s	= new_u64s;
-	),
-
-	TP_printk("%s %pS btree %s pos %llu:%llu:%u old_u64s %u new_u64s %u",
-		  __entry->trans_fn,
-		  (void *) __entry->caller_ip,
-		  bch2_btree_id_str(__entry->btree_id),
-		  __entry->pos_inode,
-		  __entry->pos_offset,
-		  __entry->pos_snapshot,
-		  __entry->old_u64s,
-		  __entry->new_u64s)
-);
-
 DEFINE_EVENT(transaction_event,	trans_restart_write_buffer_flush,
 	TP_PROTO(struct btree_trans *trans,
 		 unsigned long caller_ip),
@@ -1927,21 +1849,6 @@ TRACE_EVENT(btree_path_free,
 		  __entry->dup_locked)
 );
 
-TRACE_EVENT(btree_path_free_trans_begin,
-	TP_PROTO(btree_path_idx_t path),
-	TP_ARGS(path),
-
-	TP_STRUCT__entry(
-		__field(btree_path_idx_t,	idx		)
-	),
-
-	TP_fast_assign(
-		__entry->idx			= path;
-	),
-
-	TP_printk("   path %3u", __entry->idx)
-);
-
 #else /* CONFIG_BCACHEFS_PATH_TRACEPOINTS */
 #ifndef _TRACE_BCACHEFS_H
 
@@ -1959,7 +1866,6 @@ static inline void trace_btree_path_traverse_start(struct btree_trans *trans, st
 static inline void trace_btree_path_traverse_end(struct btree_trans *trans, struct btree_path *path) {}
 static inline void trace_btree_path_set_pos(struct btree_trans *trans, struct btree_path *path, struct bpos *new_pos) {}
 static inline void trace_btree_path_free(struct btree_trans *trans, btree_path_idx_t path, struct btree_path *dup) {}
-static inline void trace_btree_path_free_trans_begin(btree_path_idx_t path) {}
 
 #endif
 #endif /* CONFIG_BCACHEFS_PATH_TRACEPOINTS */

From 7c9cef5f8bf10a803fd0937ea071a93778f1108a Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Fri, 13 Jun 2025 18:01:25 -0400
Subject: [PATCH 0435/1334] bcachefs: mark more errors autofix

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/sb-errors_format.h | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/fs/bcachefs/sb-errors_format.h b/fs/bcachefs/sb-errors_format.h
index d06e73884871..56971ebe0f78 100644
--- a/fs/bcachefs/sb-errors_format.h
+++ b/fs/bcachefs/sb-errors_format.h
@@ -217,7 +217,7 @@ enum bch_fsck_flags {
 	x(inode_str_hash_invalid,				194,	0)		\
 	x(inode_v3_fields_start_bad,				195,	0)		\
 	x(inode_snapshot_mismatch,				196,	0)		\
-	x(snapshot_key_missing_inode_snapshot,			314,	0)		\
+	x(snapshot_key_missing_inode_snapshot,			314,	FSCK_AUTOFIX)	\
 	x(inode_unlinked_but_clean,				197,	0)		\
 	x(inode_unlinked_but_nlink_nonzero,			198,	0)		\
 	x(inode_unlinked_and_not_open,				281,	0)		\
@@ -253,18 +253,18 @@ enum bch_fsck_flags {
 	x(extent_overlapping,					215,	0)		\
 	x(key_in_missing_inode,					216,	0)		\
 	x(key_in_wrong_inode_type,				217,	0)		\
-	x(extent_past_end_of_inode,				218,	0)		\
+	x(extent_past_end_of_inode,				218,	FSCK_AUTOFIX)	\
 	x(dirent_empty_name,					219,	0)		\
 	x(dirent_val_too_big,					220,	0)		\
 	x(dirent_name_too_long,					221,	0)		\
 	x(dirent_name_embedded_nul,				222,	0)		\
 	x(dirent_name_dot_or_dotdot,				223,	0)		\
 	x(dirent_name_has_slash,				224,	0)		\
-	x(dirent_d_type_wrong,					225,	0)		\
+	x(dirent_d_type_wrong,					225,	FSCK_AUTOFIX)	\
 	x(inode_bi_parent_wrong,				226,	0)		\
 	x(dirent_in_missing_dir_inode,				227,	0)		\
 	x(dirent_in_non_dir_inode,				228,	0)		\
-	x(dirent_to_missing_inode,				229,	0)		\
+	x(dirent_to_missing_inode,				229,	FSCK_AUTOFIX)	\
 	x(dirent_to_overwritten_inode,				302,	0)		\
 	x(dirent_to_missing_subvol,				230,	0)		\
 	x(dirent_to_itself,					231,	0)		\

From d89a34b14df5c205de698c23c3950b2b947cdb97 Mon Sep 17 00:00:00 2001
From: Alan Huang <mmpgouride@gmail.com>
Date: Sat, 14 Jun 2025 17:18:07 +0800
Subject: [PATCH 0436/1334] bcachefs: Move bset size check before csum check

In syzbot's crash, the bset's u64s is larger than the btree node.

Reported-by: syzbot+bfaeaa8e26281970158d@syzkaller.appspotmail.com
Signed-off-by: Alan Huang <mmpgouride@gmail.com>
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/btree_io.c | 42 ++++++++++++++++++++++--------------------
 1 file changed, 22 insertions(+), 20 deletions(-)

diff --git a/fs/bcachefs/btree_io.c b/fs/bcachefs/btree_io.c
index d8f3c4c65e90..005d5c94edd0 100644
--- a/fs/bcachefs/btree_io.c
+++ b/fs/bcachefs/btree_io.c
@@ -723,12 +723,11 @@ void bch2_btree_node_drop_keys_outside_node(struct btree *b)
 
 static int validate_bset(struct bch_fs *c, struct bch_dev *ca,
 			 struct btree *b, struct bset *i,
-			 unsigned offset, unsigned sectors, int write,
+			 unsigned offset, int write,
 			 struct bch_io_failures *failed,
 			 struct printbuf *err_msg)
 {
 	unsigned version = le16_to_cpu(i->version);
-	unsigned ptr_written = btree_ptr_sectors_written(bkey_i_to_s_c(&b->key));
 	struct printbuf buf1 = PRINTBUF;
 	struct printbuf buf2 = PRINTBUF;
 	int ret = 0;
@@ -778,15 +777,6 @@ static int validate_bset(struct bch_fs *c, struct bch_dev *ca,
 		     btree_node_unsupported_version,
 		     "BSET_SEPARATE_WHITEOUTS no longer supported");
 
-	if (!write &&
-	    btree_err_on(offset + sectors > (ptr_written ?: btree_sectors(c)),
-			 -BCH_ERR_btree_node_read_err_fixable,
-			 c, ca, b, i, NULL,
-			 bset_past_end_of_btree_node,
-			 "bset past end of btree node (offset %u len %u but written %zu)",
-			 offset, sectors, ptr_written ?: btree_sectors(c)))
-		i->u64s = 0;
-
 	btree_err_on(offset && !i->u64s,
 		     -BCH_ERR_btree_node_read_err_fixable,
 		     c, ca, b, i, NULL,
@@ -1151,6 +1141,14 @@ int bch2_btree_node_read_done(struct bch_fs *c, struct bch_dev *ca,
 			     "unknown checksum type %llu", BSET_CSUM_TYPE(i));
 
 		if (first) {
+			sectors = vstruct_sectors(b->data, c->block_bits);
+			if (btree_err_on(b->written + sectors > (ptr_written ?: btree_sectors(c)),
+					 -BCH_ERR_btree_node_read_err_fixable,
+					 c, ca, b, i, NULL,
+					 bset_past_end_of_btree_node,
+					 "bset past end of btree node (offset %u len %u but written %zu)",
+					 b->written, sectors, ptr_written ?: btree_sectors(c)))
+				i->u64s = 0;
 			if (good_csum_type) {
 				struct bch_csum csum = csum_vstruct(c, BSET_CSUM_TYPE(i), nonce, b->data);
 				bool csum_bad = bch2_crc_cmp(b->data->csum, csum);
@@ -1178,9 +1176,15 @@ int bch2_btree_node_read_done(struct bch_fs *c, struct bch_dev *ca,
 				     c, NULL, b, NULL, NULL,
 				     btree_node_unsupported_version,
 				     "btree node does not have NEW_EXTENT_OVERWRITE set");
-
-			sectors = vstruct_sectors(b->data, c->block_bits);
 		} else {
+			sectors = vstruct_sectors(bne, c->block_bits);
+			if (btree_err_on(b->written + sectors > (ptr_written ?: btree_sectors(c)),
+					 -BCH_ERR_btree_node_read_err_fixable,
+					 c, ca, b, i, NULL,
+					 bset_past_end_of_btree_node,
+					 "bset past end of btree node (offset %u len %u but written %zu)",
+					 b->written, sectors, ptr_written ?: btree_sectors(c)))
+				i->u64s = 0;
 			if (good_csum_type) {
 				struct bch_csum csum = csum_vstruct(c, BSET_CSUM_TYPE(i), nonce, bne);
 				bool csum_bad = bch2_crc_cmp(bne->csum, csum);
@@ -1201,14 +1205,12 @@ int bch2_btree_node_read_done(struct bch_fs *c, struct bch_dev *ca,
 						"decrypting btree node: %s", bch2_err_str(ret)))
 					goto fsck_err;
 			}
-
-			sectors = vstruct_sectors(bne, c->block_bits);
 		}
 
 		b->version_ondisk = min(b->version_ondisk,
 					le16_to_cpu(i->version));
 
-		ret = validate_bset(c, ca, b, i, b->written, sectors, READ, failed, err_msg);
+		ret = validate_bset(c, ca, b, i, b->written, READ, failed, err_msg);
 		if (ret)
 			goto fsck_err;
 
@@ -2267,7 +2269,7 @@ static void btree_node_write_endio(struct bio *bio)
 }
 
 static int validate_bset_for_write(struct bch_fs *c, struct btree *b,
-				   struct bset *i, unsigned sectors)
+				   struct bset *i)
 {
 	int ret = bch2_bkey_validate(c, bkey_i_to_s_c(&b->key),
 				     (struct bkey_validate_context) {
@@ -2282,7 +2284,7 @@ static int validate_bset_for_write(struct bch_fs *c, struct btree *b,
 	}
 
 	ret = validate_bset_keys(c, b, i, WRITE, NULL, NULL) ?:
-		validate_bset(c, NULL, b, i, b->written, sectors, WRITE, NULL, NULL);
+		validate_bset(c, NULL, b, i, b->written, WRITE, NULL, NULL);
 	if (ret) {
 		bch2_inconsistent_error(c);
 		dump_stack();
@@ -2475,7 +2477,7 @@ do_write:
 
 	/* if we're going to be encrypting, check metadata validity first: */
 	if (validate_before_checksum &&
-	    validate_bset_for_write(c, b, i, sectors_to_write))
+	    validate_bset_for_write(c, b, i))
 		goto err;
 
 	ret = bset_encrypt(c, i, b->written << 9);
@@ -2492,7 +2494,7 @@ do_write:
 
 	/* if we're not encrypting, check metadata after checksumming: */
 	if (!validate_before_checksum &&
-	    validate_bset_for_write(c, b, i, sectors_to_write))
+	    validate_bset_for_write(c, b, i))
 		goto err;
 
 	/*

From 56be92c63f02e0f6fd855075acb1471ea1c68539 Mon Sep 17 00:00:00 2001
From: Alan Huang <mmpgouride@gmail.com>
Date: Sun, 15 Jun 2025 13:41:22 +0800
Subject: [PATCH 0437/1334] bcachefs: Fix pool->alloc NULL pointer dereference

btree_interior_update_pool has not been initialized before the
filesystem becomes read-write, thus mempool_alloc in bch2_btree_update_start
will trigger pool->alloc NULL pointer dereference in mempool_alloc_noprof

Reported-by: syzbot+2f3859bd28f20fa682e6@syzkaller.appspotmail.com
Signed-off-by: Alan Huang <mmpgouride@gmail.com>
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/bcachefs.h |  3 ++-
 fs/bcachefs/chardev.c  | 29 ++++++++++++++++++++++-------
 2 files changed, 24 insertions(+), 8 deletions(-)

diff --git a/fs/bcachefs/bcachefs.h b/fs/bcachefs/bcachefs.h
index 5a1cede2febf..8043943cdf6a 100644
--- a/fs/bcachefs/bcachefs.h
+++ b/fs/bcachefs/bcachefs.h
@@ -767,7 +767,8 @@ struct btree_trans_buf {
 	x(sysfs)							\
 	x(btree_write_buffer)						\
 	x(btree_node_scrub)						\
-	x(async_recovery_passes)
+	x(async_recovery_passes)					\
+	x(ioctl_data)
 
 enum bch_write_ref {
 #define x(n) BCH_WRITE_REF_##n,
diff --git a/fs/bcachefs/chardev.c b/fs/bcachefs/chardev.c
index fde3c2380e28..5ea89aa2b0c4 100644
--- a/fs/bcachefs/chardev.c
+++ b/fs/bcachefs/chardev.c
@@ -319,6 +319,7 @@ static int bch2_data_thread(void *arg)
 		ctx->stats.ret = BCH_IOCTL_DATA_EVENT_RET_done;
 		ctx->stats.data_type = (int) DATA_PROGRESS_DATA_TYPE_done;
 	}
+	enumerated_ref_put(&ctx->c->writes, BCH_WRITE_REF_ioctl_data);
 	return 0;
 }
 
@@ -378,15 +379,24 @@ static long bch2_ioctl_data(struct bch_fs *c,
 	struct bch_data_ctx *ctx;
 	int ret;
 
-	if (!capable(CAP_SYS_ADMIN))
-		return -EPERM;
+	if (!enumerated_ref_tryget(&c->writes, BCH_WRITE_REF_ioctl_data))
+		return -EROFS;
 
-	if (arg.op >= BCH_DATA_OP_NR || arg.flags)
-		return -EINVAL;
+	if (!capable(CAP_SYS_ADMIN)) {
+		ret = -EPERM;
+		goto put_ref;
+	}
+
+	if (arg.op >= BCH_DATA_OP_NR || arg.flags) {
+		ret = -EINVAL;
+		goto put_ref;
+	}
 
 	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
-	if (!ctx)
-		return -ENOMEM;
+	if (!ctx) {
+		ret = -ENOMEM;
+		goto put_ref;
+	}
 
 	ctx->c = c;
 	ctx->arg = arg;
@@ -395,7 +405,12 @@ static long bch2_ioctl_data(struct bch_fs *c,
 			&bcachefs_data_ops,
 			bch2_data_thread);
 	if (ret < 0)
-		kfree(ctx);
+		goto cleanup;
+	return ret;
+cleanup:
+	kfree(ctx);
+put_ref:
+	enumerated_ref_put(&c->writes, BCH_WRITE_REF_ioctl_data);
 	return ret;
 }
 

From 03208bd06a61bc2ebc423b6485cbcffecd37af36 Mon Sep 17 00:00:00 2001
From: Bharadwaj Raju <bharadwaj.raju777@gmail.com>
Date: Sun, 15 Jun 2025 22:15:38 +0530
Subject: [PATCH 0438/1334] bcachefs: don't return fsck_fix for unfixable node
 errors in __btree_err

After cd3cdb1ef706 ("Single err message for btree node reads"),
all errors caused __btree_err to return -BCH_ERR_fsck_fix no matter what
the actual error type was if the recovery pass was scanning for btree
nodes. This lead to the code continuing despite things like bad node
formats when they earlier would have caused a jump to fsck_err, because
btree_err only jumps when the return from __btree_err does not match
fsck_fix. Ultimately this lead to undefined behavior by attempting to
unpack a key based on an invalid format.

Make only errors of type -BCH_ERR_btree_node_read_err_fixable cause
__btree_err to return -BCH_ERR_fsck_fix when scanning for btree nodes.

Reported-by: syzbot+cfd994b9cdf00446fd54@syzkaller.appspotmail.com
Fixes: cd3cdb1ef706 ("bcachefs: Single err message for btree node reads")
Signed-off-by: Bharadwaj Raju <bharadwaj.raju777@gmail.com>
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/btree_io.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/fs/bcachefs/btree_io.c b/fs/bcachefs/btree_io.c
index 005d5c94edd0..dca5530a2f49 100644
--- a/fs/bcachefs/btree_io.c
+++ b/fs/bcachefs/btree_io.c
@@ -557,7 +557,9 @@ static int __btree_err(int ret,
 		       const char *fmt, ...)
 {
 	if (c->recovery.curr_pass == BCH_RECOVERY_PASS_scan_for_btree_nodes)
-		return bch_err_throw(c, fsck_fix);
+		return ret == -BCH_ERR_btree_node_read_err_fixable
+			? bch_err_throw(c, fsck_fix)
+			: ret;
 
 	bool have_retry = false;
 	int ret2;

From f2a701fd94f161bdca7537284ba218c20181451e Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Sun, 15 Jun 2025 12:09:24 -0400
Subject: [PATCH 0439/1334] bcachefs: fsck: Improve check_key_has_inode()

Print out more info when we find a key (extent, dirent, xattr) for a
missing inode - was there a good inode in an older snapshot, full(ish)
list of keys for that missing inode, so we can make better decisions on
how to repair.

If it looks like it should've been deleted, autofix it. If we ever hit
the non-autofix cases, we'll want to write more repair code (possibly
reconstituting the inode).

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/fsck.c             | 108 ++++++++++++++++++++++++++-------
 fs/bcachefs/sb-errors_format.h |   2 +-
 2 files changed, 88 insertions(+), 22 deletions(-)

diff --git a/fs/bcachefs/fsck.c b/fs/bcachefs/fsck.c
index 48810a8e5d4b..f25d33fb3e23 100644
--- a/fs/bcachefs/fsck.c
+++ b/fs/bcachefs/fsck.c
@@ -1436,6 +1436,7 @@ static int check_key_has_inode(struct btree_trans *trans,
 {
 	struct bch_fs *c = trans->c;
 	struct printbuf buf = PRINTBUF;
+	struct btree_iter iter2 = {};
 	int ret = PTR_ERR_OR_ZERO(i);
 	if (ret)
 		return ret;
@@ -1445,40 +1446,105 @@ static int check_key_has_inode(struct btree_trans *trans,
 
 	bool have_inode = i && !i->whiteout;
 
-	if (!have_inode && (c->sb.btrees_lost_data & BIT_ULL(BTREE_ID_inodes))) {
-		ret =   reconstruct_inode(trans, iter->btree_id, k.k->p.snapshot, k.k->p.inode) ?:
-			bch2_trans_commit(trans, NULL, NULL, BCH_TRANS_COMMIT_no_enospc);
-		if (ret)
-			goto err;
+	if (!have_inode && (c->sb.btrees_lost_data & BIT_ULL(BTREE_ID_inodes)))
+		goto reconstruct;
 
-		inode->last_pos.inode--;
-		ret = bch_err_throw(c, transaction_restart_nested);
-		goto err;
+	if (have_inode && btree_matches_i_mode(iter->btree_id, i->inode.bi_mode))
+		goto out;
+
+	prt_printf(&buf, ", ");
+
+	bool have_old_inode = false;
+	darray_for_each(inode->inodes, i2)
+		if (!i2->whiteout &&
+		    bch2_snapshot_is_ancestor(c, k.k->p.snapshot, i2->inode.bi_snapshot) &&
+		    btree_matches_i_mode(iter->btree_id, i2->inode.bi_mode)) {
+			prt_printf(&buf, "but found good inode in older snapshot\n");
+			bch2_inode_unpacked_to_text(&buf, &i2->inode);
+			prt_newline(&buf);
+			have_old_inode = true;
+			break;
+		}
+
+	struct bkey_s_c k2;
+	unsigned nr_keys = 0;
+
+	prt_printf(&buf, "found keys:\n");
+
+	for_each_btree_key_max_norestart(trans, iter2, iter->btree_id,
+					 SPOS(k.k->p.inode, 0, k.k->p.snapshot),
+					 POS(k.k->p.inode, U64_MAX),
+					 0, k2, ret) {
+		nr_keys++;
+		if (nr_keys <= 10) {
+			bch2_bkey_val_to_text(&buf, c, k2);
+			prt_newline(&buf);
+		}
+		if (nr_keys >= 100)
+			break;
 	}
 
-	if (fsck_err_on(!have_inode,
-			trans, key_in_missing_inode,
-			"key in missing inode:\n%s",
-			(printbuf_reset(&buf),
-			 bch2_bkey_val_to_text(&buf, c, k), buf.buf)))
-		goto delete;
+	if (ret)
+		goto err;
 
-	if (fsck_err_on(have_inode && !btree_matches_i_mode(iter->btree_id, i->inode.bi_mode),
-			trans, key_in_wrong_inode_type,
-			"key for wrong inode mode %o:\n%s",
-			i->inode.bi_mode,
-			(printbuf_reset(&buf),
-			 bch2_bkey_val_to_text(&buf, c, k), buf.buf)))
-		goto delete;
+	if (nr_keys > 100)
+		prt_printf(&buf, "found > %u keys for this missing inode\n", nr_keys);
+	else if (nr_keys > 10)
+		prt_printf(&buf, "found %u keys for this missing inode\n", nr_keys);
+
+	if (!have_inode) {
+		if (fsck_err_on(!have_inode,
+				trans, key_in_missing_inode,
+				"key in missing inode%s", buf.buf)) {
+			/*
+			 * Maybe a deletion that raced with data move, or something
+			 * weird like that? But if we know the inode was deleted, or
+			 * it's just a few keys, we can safely delete them.
+			 *
+			 * If it's many keys, we should probably recreate the inode
+			 */
+			if (have_old_inode || nr_keys <= 2)
+				goto delete;
+			else
+				goto reconstruct;
+		}
+	} else {
+		/*
+		 * not autofix, this one would be a giant wtf - bit error in the
+		 * inode corrupting i_mode?
+		 *
+		 * may want to try repairing inode instead of deleting
+		 */
+		if (fsck_err_on(!btree_matches_i_mode(iter->btree_id, i->inode.bi_mode),
+				trans, key_in_wrong_inode_type,
+				"key for wrong inode mode %o%s",
+				i->inode.bi_mode, buf.buf))
+			goto delete;
+	}
 out:
 err:
 fsck_err:
+	bch2_trans_iter_exit(trans, &iter2);
 	printbuf_exit(&buf);
 	bch_err_fn(c, ret);
 	return ret;
 delete:
+	/*
+	 * XXX: print out more info
+	 * count up extents for this inode, check if we have different inode in
+	 * an older snapshot version, perhaps decide if we want to reconstitute
+	 */
 	ret = bch2_btree_delete_at(trans, iter, BTREE_UPDATE_internal_snapshot_node);
 	goto out;
+reconstruct:
+	ret =   reconstruct_inode(trans, iter->btree_id, k.k->p.snapshot, k.k->p.inode) ?:
+		bch2_trans_commit(trans, NULL, NULL, BCH_TRANS_COMMIT_no_enospc);
+	if (ret)
+		goto err;
+
+	inode->last_pos.inode--;
+	ret = bch_err_throw(c, transaction_restart_nested);
+	goto out;
 }
 
 static int check_i_sectors_notnested(struct btree_trans *trans, struct inode_walker *w)
diff --git a/fs/bcachefs/sb-errors_format.h b/fs/bcachefs/sb-errors_format.h
index 56971ebe0f78..f1aa40542a0e 100644
--- a/fs/bcachefs/sb-errors_format.h
+++ b/fs/bcachefs/sb-errors_format.h
@@ -251,7 +251,7 @@ enum bch_fsck_flags {
 	x(deleted_inode_not_unlinked,				214,	FSCK_AUTOFIX)	\
 	x(deleted_inode_has_child_snapshots,			288,	FSCK_AUTOFIX)	\
 	x(extent_overlapping,					215,	0)		\
-	x(key_in_missing_inode,					216,	0)		\
+	x(key_in_missing_inode,					216,	FSCK_AUTOFIX)	\
 	x(key_in_wrong_inode_type,				217,	0)		\
 	x(extent_past_end_of_inode,				218,	FSCK_AUTOFIX)	\
 	x(dirent_empty_name,					219,	0)		\

From 1cddad0fcbccc7056036f2a83184a3ca5c62f7d3 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Sun, 15 Jun 2025 16:43:34 -0400
Subject: [PATCH 0440/1334] bcachefs: Call bch2_fs_init_rw() early if we'll be
 going rw

kthread creation checks for pending signals, which is _very_ annoying if
we have to do a long recovery and don't go rw until we've done
significant work.

Check if we'll be going rw and pre-allocate kthreads/workqueues.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/recovery.c        | 10 ++++++++++
 fs/bcachefs/recovery_passes.c |  6 +-----
 fs/bcachefs/recovery_passes.h |  9 +++++++++
 fs/bcachefs/super.c           | 13 +++++++++++--
 fs/bcachefs/super.h           |  1 +
 5 files changed, 32 insertions(+), 7 deletions(-)

diff --git a/fs/bcachefs/recovery.c b/fs/bcachefs/recovery.c
index 37f2cc1ec2f8..fa5d1ef5bea6 100644
--- a/fs/bcachefs/recovery.c
+++ b/fs/bcachefs/recovery.c
@@ -762,6 +762,16 @@ int bch2_fs_recovery(struct bch_fs *c)
 		c->opts.fsck = true;
 	}
 
+	if (go_rw_in_recovery(c)) {
+		/*
+		 * start workqueues/kworkers early - kthread creation checks for
+		 * pending signals, which is _very_ annoying
+		 */
+		ret = bch2_fs_init_rw(c);
+		if (ret)
+			goto err;
+	}
+
 	mutex_lock(&c->sb_lock);
 	struct bch_sb_field_ext *ext = bch2_sb_field_get(c->disk_sb.sb, ext);
 	bool write_sb = false;
diff --git a/fs/bcachefs/recovery_passes.c b/fs/bcachefs/recovery_passes.c
index 35ac0d64d73a..c2c18c0a5429 100644
--- a/fs/bcachefs/recovery_passes.c
+++ b/fs/bcachefs/recovery_passes.c
@@ -217,11 +217,7 @@ static int bch2_set_may_go_rw(struct bch_fs *c)
 
 	set_bit(BCH_FS_may_go_rw, &c->flags);
 
-	if (keys->nr ||
-	    !c->opts.read_only ||
-	    !c->sb.clean ||
-	    c->opts.recovery_passes ||
-	    (c->opts.fsck && !(c->sb.features & BIT_ULL(BCH_FEATURE_no_alloc_info)))) {
+	if (go_rw_in_recovery(c)) {
 		if (c->sb.features & BIT_ULL(BCH_FEATURE_no_alloc_info)) {
 			bch_info(c, "mounting a filesystem with no alloc info read-write; will recreate");
 			bch2_reconstruct_alloc(c);
diff --git a/fs/bcachefs/recovery_passes.h b/fs/bcachefs/recovery_passes.h
index 260571c7105e..2117f0ce1922 100644
--- a/fs/bcachefs/recovery_passes.h
+++ b/fs/bcachefs/recovery_passes.h
@@ -17,6 +17,15 @@ enum bch_run_recovery_pass_flags {
 	RUN_RECOVERY_PASS_ratelimit	= BIT(1),
 };
 
+static inline bool go_rw_in_recovery(struct bch_fs *c)
+{
+	return (c->journal_keys.nr ||
+		!c->opts.read_only ||
+		!c->sb.clean ||
+		c->opts.recovery_passes ||
+		(c->opts.fsck && !(c->sb.features & BIT_ULL(BCH_FEATURE_no_alloc_info))));
+}
+
 int bch2_run_print_explicit_recovery_pass(struct bch_fs *, enum bch_recovery_pass);
 
 int __bch2_run_explicit_recovery_pass(struct bch_fs *, struct printbuf *,
diff --git a/fs/bcachefs/super.c b/fs/bcachefs/super.c
index a5b97c9c5163..69c097ff54e7 100644
--- a/fs/bcachefs/super.c
+++ b/fs/bcachefs/super.c
@@ -210,7 +210,6 @@ static int bch2_dev_alloc(struct bch_fs *, unsigned);
 static int bch2_dev_sysfs_online(struct bch_fs *, struct bch_dev *);
 static void bch2_dev_io_ref_stop(struct bch_dev *, int);
 static void __bch2_dev_read_only(struct bch_fs *, struct bch_dev *);
-static int bch2_fs_init_rw(struct bch_fs *);
 
 struct bch_fs *bch2_dev_to_fs(dev_t dev)
 {
@@ -794,7 +793,7 @@ err:
 	return ret;
 }
 
-static int bch2_fs_init_rw(struct bch_fs *c)
+int bch2_fs_init_rw(struct bch_fs *c)
 {
 	if (test_bit(BCH_FS_rw_init_done, &c->flags))
 		return 0;
@@ -1015,6 +1014,16 @@ static struct bch_fs *bch2_fs_alloc(struct bch_sb *sb, struct bch_opts *opts,
 	if (ret)
 		goto err;
 
+	if (go_rw_in_recovery(c)) {
+		/*
+		 * start workqueues/kworkers early - kthread creation checks for
+		 * pending signals, which is _very_ annoying
+		 */
+		ret = bch2_fs_init_rw(c);
+		if (ret)
+			goto err;
+	}
+
 #ifdef CONFIG_UNICODE
 	/* Default encoding until we can potentially have more as an option. */
 	c->cf_encoding = utf8_load(BCH_FS_DEFAULT_UTF8_ENCODING);
diff --git a/fs/bcachefs/super.h b/fs/bcachefs/super.h
index dc52f06cb2b9..e90bab9afe78 100644
--- a/fs/bcachefs/super.h
+++ b/fs/bcachefs/super.h
@@ -46,6 +46,7 @@ void __bch2_fs_stop(struct bch_fs *);
 void bch2_fs_free(struct bch_fs *);
 void bch2_fs_stop(struct bch_fs *);
 
+int bch2_fs_init_rw(struct bch_fs *);
 int bch2_fs_start(struct bch_fs *);
 struct bch_fs *bch2_fs_open(darray_const_str *, struct bch_opts *);
 

From 9ba6930ef8e0e00102716f4627896e0be6358d7b Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Mon, 16 Jun 2025 14:00:40 -0400
Subject: [PATCH 0441/1334] bcachefs: Fix __bch2_inum_to_path() when crossing
 subvol boundaries

The bch2_subvolume_get_snapshot() call needs to happen before the dirent
lookup - the dirent is in the parent subvolume.

Also, check for loops.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/namei.c | 27 ++++++++++++++++++++++-----
 1 file changed, 22 insertions(+), 5 deletions(-)

diff --git a/fs/bcachefs/namei.c b/fs/bcachefs/namei.c
index 779c22eb3979..7d1068aa998f 100644
--- a/fs/bcachefs/namei.c
+++ b/fs/bcachefs/namei.c
@@ -625,14 +625,26 @@ static int __bch2_inum_to_path(struct btree_trans *trans,
 {
 	unsigned orig_pos = path->pos;
 	int ret = 0;
+	DARRAY(subvol_inum) inums = {};
+
+	if (!snapshot) {
+		ret = bch2_subvolume_get_snapshot(trans, subvol, &snapshot);
+		if (ret)
+			goto disconnected;
+	}
 
 	while (true) {
-		if (!snapshot) {
-			ret = bch2_subvolume_get_snapshot(trans, subvol, &snapshot);
-			if (ret)
-				goto disconnected;
+		subvol_inum n = (subvol_inum) { subvol ?: snapshot, inum };
+
+		if (darray_find_p(inums, i, i->subvol == n.subvol && i->inum == n.inum)) {
+			prt_str_reversed(path, "(loop)");
+			break;
 		}
 
+		ret = darray_push(&inums, n);
+		if (ret)
+			goto err;
+
 		struct bch_inode_unpacked inode;
 		ret = bch2_inode_find_by_inum_snapshot(trans, inum, snapshot, &inode, 0);
 		if (ret)
@@ -650,7 +662,9 @@ static int __bch2_inum_to_path(struct btree_trans *trans,
 		inum = inode.bi_dir;
 		if (inode.bi_parent_subvol) {
 			subvol = inode.bi_parent_subvol;
-			snapshot = 0;
+			ret = bch2_subvolume_get_snapshot(trans, inode.bi_parent_subvol, &snapshot);
+			if (ret)
+				goto disconnected;
 		}
 
 		struct btree_iter d_iter;
@@ -662,6 +676,7 @@ static int __bch2_inum_to_path(struct btree_trans *trans,
 			goto disconnected;
 
 		struct qstr dirent_name = bch2_dirent_get_name(d);
+
 		prt_bytes_reversed(path, dirent_name.name, dirent_name.len);
 
 		prt_char(path, '/');
@@ -677,8 +692,10 @@ out:
 		goto err;
 
 	reverse_bytes(path->buf + orig_pos, path->pos - orig_pos);
+	darray_exit(&inums);
 	return 0;
 err:
+	darray_exit(&inums);
 	return ret;
 disconnected:
 	if (bch2_err_matches(ret, BCH_ERR_transaction_restart))

From 7029cc4d13453499a88f512720d26c1a0c4e957b Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Sat, 7 Jun 2025 19:33:59 -0400
Subject: [PATCH 0442/1334] bcachefs: fsck: Print path when we find a subvol
 loop

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/fsck.c | 13 +++++++++----
 1 file changed, 9 insertions(+), 4 deletions(-)

diff --git a/fs/bcachefs/fsck.c b/fs/bcachefs/fsck.c
index f25d33fb3e23..0d87aa9b4f23 100644
--- a/fs/bcachefs/fsck.c
+++ b/fs/bcachefs/fsck.c
@@ -2578,6 +2578,11 @@ static int check_subvol_path(struct btree_trans *trans, struct btree_iter *iter,
 	if (k.k->type != KEY_TYPE_subvolume)
 		return 0;
 
+	subvol_inum start = {
+		.subvol = k.k->p.offset,
+		.inum	= le64_to_cpu(bkey_s_c_to_subvolume(k).v->inode),
+	};
+
 	while (k.k->p.offset != BCACHEFS_ROOT_SUBVOL) {
 		ret = darray_push(&subvol_path, k.k->p.offset);
 		if (ret)
@@ -2596,11 +2601,11 @@ static int check_subvol_path(struct btree_trans *trans, struct btree_iter *iter,
 
 		if (darray_u32_has(&subvol_path, parent)) {
 			printbuf_reset(&buf);
-			prt_printf(&buf, "subvolume loop:\n");
+			prt_printf(&buf, "subvolume loop: ");
 
-			darray_for_each_reverse(subvol_path, i)
-				prt_printf(&buf, "%u ", *i);
-			prt_printf(&buf, "%u", parent);
+			ret = bch2_inum_to_path(trans, start, &buf);
+			if (ret)
+				goto err;
 
 			if (fsck_err(trans, subvol_loop, "%s", buf.buf))
 				ret = reattach_subvol(trans, s);

From c1ca07a4dd1a1ab17ed651729c37b04af9f75ee8 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Mon, 16 Jun 2025 14:15:28 -0400
Subject: [PATCH 0443/1334] bcachefs: fsck: Fix remove_backpointer() for subvol
 roots

The dirent will be in a different snapshot if the inode is a subvolume
root.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/fsck.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/fs/bcachefs/fsck.c b/fs/bcachefs/fsck.c
index 0d87aa9b4f23..a3f73e7a2113 100644
--- a/fs/bcachefs/fsck.c
+++ b/fs/bcachefs/fsck.c
@@ -493,10 +493,18 @@ static int remove_backpointer(struct btree_trans *trans,
 	if (!inode->bi_dir)
 		return 0;
 
+	u32 snapshot = inode->bi_snapshot;
+
+	if (inode->bi_parent_subvol) {
+		int ret = bch2_subvolume_get_snapshot(trans, inode->bi_parent_subvol, &snapshot);
+		if (ret)
+			return ret;
+	}
+
 	struct bch_fs *c = trans->c;
 	struct btree_iter iter;
 	struct bkey_s_c_dirent d = dirent_get_by_pos(trans, &iter,
-				     SPOS(inode->bi_dir, inode->bi_dir_offset, inode->bi_snapshot));
+				     SPOS(inode->bi_dir, inode->bi_dir_offset, snapshot));
 	int ret = bkey_err(d) ?:
 		  dirent_points_to_inode(c, d, inode) ?:
 		  bch2_fsck_remove_dirent(trans, d.k->p);

From 9fb09ace59b2beab312ec225630ce87ddbec6d79 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Mon, 16 Jun 2025 14:41:27 -0400
Subject: [PATCH 0444/1334] bcachefs: fsck: Fix reattach_inode() for subvol
 roots

bch_subvolume.fs_path_parent needs to be updated as well, it should
match inode.bi_parent_subvol.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/fsck.c | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/fs/bcachefs/fsck.c b/fs/bcachefs/fsck.c
index a3f73e7a2113..6e64af4ccc36 100644
--- a/fs/bcachefs/fsck.c
+++ b/fs/bcachefs/fsck.c
@@ -372,6 +372,18 @@ static int reattach_inode(struct btree_trans *trans, struct bch_inode_unpacked *
 	if (inode->bi_subvol) {
 		inode->bi_parent_subvol = BCACHEFS_ROOT_SUBVOL;
 
+		struct btree_iter subvol_iter;
+		struct bkey_i_subvolume *subvol =
+			bch2_bkey_get_mut_typed(trans, &subvol_iter,
+						BTREE_ID_subvolumes, POS(0, inode->bi_subvol),
+						0, subvolume);
+		ret = PTR_ERR_OR_ZERO(subvol);
+		if (ret)
+			return ret;
+
+		subvol->v.fs_path_parent = BCACHEFS_ROOT_SUBVOL;
+		bch2_trans_iter_exit(trans, &subvol_iter);
+
 		u64 root_inum;
 		ret = subvol_lookup(trans, inode->bi_parent_subvol,
 				    &dirent_snapshot, &root_inum);

From 3e5ceaa5bfd71ae94d736426f8a27391023182ff Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Mon, 16 Jun 2025 16:13:02 -0400
Subject: [PATCH 0445/1334] bcachefs: fsck: check_directory_structure runs in
 reverse order

When we find a directory connectivity problem, we should do the repair
in the oldest snapshot that has the issue - so that we don't end up
duplicating work or making a real mess of things.

Oldest snapshot IDs have the highest integer value, so - just walk
inodes in reverse order.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/fsck.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/bcachefs/fsck.c b/fs/bcachefs/fsck.c
index 6e64af4ccc36..7414a16af990 100644
--- a/fs/bcachefs/fsck.c
+++ b/fs/bcachefs/fsck.c
@@ -2841,7 +2841,7 @@ fsck_err:
 int bch2_check_directory_structure(struct bch_fs *c)
 {
 	int ret = bch2_trans_run(c,
-		for_each_btree_key_commit(trans, iter, BTREE_ID_inodes, POS_MIN,
+		for_each_btree_key_reverse_commit(trans, iter, BTREE_ID_inodes, POS_MIN,
 					  BTREE_ITER_intent|
 					  BTREE_ITER_prefetch|
 					  BTREE_ITER_all_snapshots, k,

From 8d6ac82361df55d223186d8cd2ce884310ee5e6b Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Mon, 16 Jun 2025 16:14:59 -0400
Subject: [PATCH 0446/1334] bcachefs: fsck: additional diagnostics for
 reattach_inode()

Log the inode's new path.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/fsck.c | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/fs/bcachefs/fsck.c b/fs/bcachefs/fsck.c
index 7414a16af990..f2c8e904acab 100644
--- a/fs/bcachefs/fsck.c
+++ b/fs/bcachefs/fsck.c
@@ -399,6 +399,8 @@ static int reattach_inode(struct btree_trans *trans, struct bch_inode_unpacked *
 	if (ret)
 		return ret;
 
+	bch_verbose(c, "got lostfound inum %llu", lostfound.bi_inum);
+
 	lostfound.bi_nlink += S_ISDIR(inode->bi_mode);
 
 	/* ensure lost+found inode is also present in inode snapshot */
@@ -435,6 +437,16 @@ static int reattach_inode(struct btree_trans *trans, struct bch_inode_unpacked *
 	if (ret)
 		return ret;
 
+	{
+		CLASS(printbuf, buf)();
+		ret = bch2_inum_snapshot_to_path(trans, inode->bi_inum,
+						 inode->bi_snapshot, NULL, &buf);
+		if (ret)
+			return ret;
+
+		bch_info(c, "reattached at %s", buf.buf);
+	}
+
 	/*
 	 * Fix up inodes in child snapshots: if they should also be reattached
 	 * update the backpointer field, if they should not be we need to emit

From 583ba52a40dd1f9328e2626056f0797d273817e7 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Mon, 16 Jun 2025 16:15:41 -0400
Subject: [PATCH 0447/1334] bcachefs: fsck: check_subdir_count logs path

We can easily go from inode number -> path now, which makes for more
useful log messages.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/fsck.c | 24 ++++++++++++++++--------
 1 file changed, 16 insertions(+), 8 deletions(-)

diff --git a/fs/bcachefs/fsck.c b/fs/bcachefs/fsck.c
index f2c8e904acab..96b9ea58705f 100644
--- a/fs/bcachefs/fsck.c
+++ b/fs/bcachefs/fsck.c
@@ -2066,14 +2066,22 @@ static int check_subdir_count_notnested(struct btree_trans *trans, struct inode_
 				continue;
 		}
 
-		if (fsck_err_on(i->inode.bi_nlink != i->count,
-				trans, inode_dir_wrong_nlink,
-				"directory %llu:%u with wrong i_nlink: got %u, should be %llu",
-				w->last_pos.inode, i->inode.bi_snapshot, i->inode.bi_nlink, i->count)) {
-			i->inode.bi_nlink = i->count;
-			ret = bch2_fsck_write_inode(trans, &i->inode);
-			if (ret)
-				break;
+		if (i->inode.bi_nlink != i->count) {
+			CLASS(printbuf, buf)();
+
+			lockrestart_do(trans,
+				       bch2_inum_snapshot_to_path(trans, w->last_pos.inode,
+								  i->inode.bi_snapshot, NULL, &buf));
+
+			if (fsck_err_on(i->inode.bi_nlink != i->count,
+					trans, inode_dir_wrong_nlink,
+					"directory with wrong i_nlink: got %u, should be %llu\n%s",
+					i->inode.bi_nlink, i->count, buf.buf)) {
+				i->inode.bi_nlink = i->count;
+				ret = bch2_fsck_write_inode(trans, &i->inode);
+				if (ret)
+					break;
+			}
 		}
 	}
 fsck_err:

From 495ba899d5a163d4cd50627ab48e3edd80dfa3a4 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Mon, 16 Jun 2025 16:16:38 -0400
Subject: [PATCH 0448/1334] bcachefs: fsck: Fix check_path_loop() + snapshots

A path exists in a particular snapshot: we should do the pathwalk in the
snapshot ID of the inode we started from, _not_ change snapshot ID as we
walk inodes and dirents.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/fsck.c | 62 +++++++++++++++++++---------------------------
 1 file changed, 26 insertions(+), 36 deletions(-)

diff --git a/fs/bcachefs/fsck.c b/fs/bcachefs/fsck.c
index 96b9ea58705f..73cff24598ed 100644
--- a/fs/bcachefs/fsck.c
+++ b/fs/bcachefs/fsck.c
@@ -2689,19 +2689,13 @@ int bch2_check_subvolume_structure(struct bch_fs *c)
 	return ret;
 }
 
-struct pathbuf_entry {
-	u64	inum;
-	u32	snapshot;
-};
-
-typedef DARRAY(struct pathbuf_entry) pathbuf;
-
-static int bch2_bi_depth_renumber_one(struct btree_trans *trans, struct pathbuf_entry *p,
+static int bch2_bi_depth_renumber_one(struct btree_trans *trans,
+				      u64 inum, u32 snapshot,
 				      u32 new_depth)
 {
 	struct btree_iter iter;
 	struct bkey_s_c k = bch2_bkey_get_iter(trans, &iter, BTREE_ID_inodes,
-					       SPOS(0, p->inum, p->snapshot), 0);
+					       SPOS(0, inum, snapshot), 0);
 
 	struct bch_inode_unpacked inode;
 	int ret = bkey_err(k) ?:
@@ -2720,14 +2714,15 @@ err:
 	return ret;
 }
 
-static int bch2_bi_depth_renumber(struct btree_trans *trans, pathbuf *path, u32 new_bi_depth)
+static int bch2_bi_depth_renumber(struct btree_trans *trans, darray_u64 *path,
+				  u32 snapshot, u32 new_bi_depth)
 {
 	u32 restart_count = trans->restart_count;
 	int ret = 0;
 
 	darray_for_each_reverse(*path, i) {
 		ret = nested_lockrestart_do(trans,
-				bch2_bi_depth_renumber_one(trans, i, new_bi_depth));
+				bch2_bi_depth_renumber_one(trans, *i, snapshot, new_bi_depth));
 		bch_err_fn(trans->c, ret);
 		if (ret)
 			break;
@@ -2738,26 +2733,19 @@ static int bch2_bi_depth_renumber(struct btree_trans *trans, pathbuf *path, u32
 	return ret ?: trans_was_restarted(trans, restart_count);
 }
 
-static bool path_is_dup(pathbuf *p, u64 inum, u32 snapshot)
-{
-	darray_for_each(*p, i)
-		if (i->inum	== inum &&
-		    i->snapshot	== snapshot)
-			return true;
-	return false;
-}
-
 static int check_path_loop(struct btree_trans *trans, struct bkey_s_c inode_k)
 {
 	struct bch_fs *c = trans->c;
 	struct btree_iter inode_iter = {};
-	pathbuf path = {};
+	darray_u64 path = {};
 	struct printbuf buf = PRINTBUF;
 	u32 snapshot = inode_k.k->p.snapshot;
 	bool redo_bi_depth = false;
 	u32 min_bi_depth = U32_MAX;
 	int ret = 0;
 
+	struct bpos start = inode_k.k->p;
+
 	struct bch_inode_unpacked inode;
 	ret = bch2_inode_unpack(inode_k, &inode);
 	if (ret)
@@ -2766,9 +2754,9 @@ static int check_path_loop(struct btree_trans *trans, struct bkey_s_c inode_k)
 	while (!inode.bi_subvol) {
 		struct btree_iter dirent_iter;
 		struct bkey_s_c_dirent d;
-		u32 parent_snapshot = snapshot;
 
-		d = inode_get_dirent(trans, &dirent_iter, &inode, &parent_snapshot);
+		d = dirent_get_by_pos(trans, &dirent_iter,
+				      SPOS(inode.bi_dir, inode.bi_dir_offset, snapshot));
 		ret = bkey_err(d.s_c);
 		if (ret && !bch2_err_matches(ret, ENOENT))
 			goto out;
@@ -2786,15 +2774,10 @@ static int check_path_loop(struct btree_trans *trans, struct bkey_s_c inode_k)
 
 		bch2_trans_iter_exit(trans, &dirent_iter);
 
-		ret = darray_push(&path, ((struct pathbuf_entry) {
-			.inum		= inode.bi_inum,
-			.snapshot	= snapshot,
-		}));
+		ret = darray_push(&path, inode.bi_inum);
 		if (ret)
 			return ret;
 
-		snapshot = parent_snapshot;
-
 		bch2_trans_iter_exit(trans, &inode_iter);
 		inode_k = bch2_bkey_get_iter(trans, &inode_iter, BTREE_ID_inodes,
 					     SPOS(0, inode.bi_dir, snapshot), 0);
@@ -2816,15 +2799,22 @@ static int check_path_loop(struct btree_trans *trans, struct bkey_s_c inode_k)
 			break;
 
 		inode = parent_inode;
-		snapshot = inode_k.k->p.snapshot;
 		redo_bi_depth = true;
 
-		if (path_is_dup(&path, inode.bi_inum, snapshot)) {
+		if (darray_find(path, inode.bi_inum)) {
 			printbuf_reset(&buf);
-			prt_printf(&buf, "directory structure loop:\n");
-			darray_for_each_reverse(path, i)
-				prt_printf(&buf, "%llu:%u ", i->inum, i->snapshot);
-			prt_printf(&buf, "%llu:%u", inode.bi_inum, snapshot);
+			prt_printf(&buf, "directory structure loop in snapshot %u: ",
+				   snapshot);
+
+			ret = bch2_inum_snapshot_to_path(trans, start.offset, start.snapshot, NULL, &buf);
+			if (ret)
+				goto out;
+
+			if (c->opts.verbose) {
+				prt_newline(&buf);
+				darray_for_each(path, i)
+					prt_printf(&buf, "%llu ", *i);
+			}
 
 			if (fsck_err(trans, dir_loop, "%s", buf.buf)) {
 				ret = remove_backpointer(trans, &inode);
@@ -2844,7 +2834,7 @@ static int check_path_loop(struct btree_trans *trans, struct bkey_s_c inode_k)
 		min_bi_depth = 0;
 
 	if (redo_bi_depth)
-		ret = bch2_bi_depth_renumber(trans, &path, min_bi_depth);
+		ret = bch2_bi_depth_renumber(trans, &path, snapshot, min_bi_depth);
 out:
 fsck_err:
 	bch2_trans_iter_exit(trans, &inode_iter);

From 61ee19dedb8d753249e20308782bf4e9e2fb7344 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ma=C3=ADra=20Canal?= <mcanal@igalia.com>
Date: Mon, 2 Jun 2025 10:22:16 -0300
Subject: [PATCH 0449/1334] drm/etnaviv: Protect the scheduler's pending list
 with its lock
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Commit 704d3d60fec4 ("drm/etnaviv: don't block scheduler when GPU is still
active") ensured that active jobs are returned to the pending list when
extending the timeout. However, it didn't use the pending list's lock to
manipulate the list, which causes a race condition as the scheduler's
workqueues are running.

Hold the lock while manipulating the scheduler's pending list to prevent
a race.

Cc: stable@vger.kernel.org
Fixes: 704d3d60fec4 ("drm/etnaviv: don't block scheduler when GPU is still active")
Reported-by: Philipp Stanner <phasta@kernel.org>
Closes: https://lore.kernel.org/dri-devel/964e59ba1539083ef29b06d3c78f5e2e9b138ab8.camel@mailbox.org/
Reviewed-by: Lucas Stach <l.stach@pengutronix.de>
Reviewed-by: Philipp Stanner <phasta@kernel.org>
Link: https://lore.kernel.org/r/20250602132240.93314-1-mcanal@igalia.com
Signed-off-by: Maíra Canal <mcanal@igalia.com>
---
 drivers/gpu/drm/etnaviv/etnaviv_sched.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/etnaviv/etnaviv_sched.c b/drivers/gpu/drm/etnaviv/etnaviv_sched.c
index 76a3a3e517d8..71e2e6b9d713 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_sched.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_sched.c
@@ -35,6 +35,7 @@ static enum drm_gpu_sched_stat etnaviv_sched_timedout_job(struct drm_sched_job
 							  *sched_job)
 {
 	struct etnaviv_gem_submit *submit = to_etnaviv_submit(sched_job);
+	struct drm_gpu_scheduler *sched = sched_job->sched;
 	struct etnaviv_gpu *gpu = submit->gpu;
 	u32 dma_addr, primid = 0;
 	int change;
@@ -89,7 +90,9 @@ static enum drm_gpu_sched_stat etnaviv_sched_timedout_job(struct drm_sched_job
 	return DRM_GPU_SCHED_STAT_NOMINAL;
 
 out_no_timeout:
-	list_add(&sched_job->list, &sched_job->sched->pending_list);
+	spin_lock(&sched->job_list_lock);
+	list_add(&sched_job->list, &sched->pending_list);
+	spin_unlock(&sched->job_list_lock);
 	return DRM_GPU_SCHED_STAT_NOMINAL;
 }
 

From 6c4897caefc8e4c6f2bf08f8317b955672667909 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Mon, 16 Jun 2025 20:08:23 -0400
Subject: [PATCH 0450/1334] bcachefs: Fix bch2_read_bio_to_text()

We can only pass negative error codes to bch2_err_str(); if it's a
positive integer it's not an error and we trip an assert.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/io_read.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/fs/bcachefs/io_read.c b/fs/bcachefs/io_read.c
index 04bbdcf58e40..cd184b219a65 100644
--- a/fs/bcachefs/io_read.c
+++ b/fs/bcachefs/io_read.c
@@ -1491,7 +1491,12 @@ void bch2_read_bio_to_text(struct printbuf *out, struct bch_read_bio *rbio)
 	prt_printf(out, "have_ioref:\t%u\n",	rbio->have_ioref);
 	prt_printf(out, "narrow_crcs:\t%u\n",	rbio->narrow_crcs);
 	prt_printf(out, "context:\t%u\n",	rbio->context);
-	prt_printf(out, "ret:\t%s\n",		bch2_err_str(rbio->ret));
+
+	int ret = READ_ONCE(rbio->ret);
+	if (ret < 0)
+		prt_printf(out, "ret:\t%s\n",		bch2_err_str(ret));
+	else
+		prt_printf(out, "ret:\t%i\n",		ret);
 
 	prt_printf(out, "flags:\t");
 	bch2_prt_bitflags(out, bch2_read_bio_flags, rbio->flags);

From 6aba0cb5bba6141158d5449f2cf53187b7f755f9 Mon Sep 17 00:00:00 2001
From: Anup Patel <apatel@ventanamicro.com>
Date: Thu, 5 Jun 2025 11:44:46 +0530
Subject: [PATCH 0451/1334] RISC-V: KVM: Fix the size parameter check in SBI
 SFENCE calls

As-per the SBI specification, an SBI remote fence operation applies
to the entire address space if either:
1) start_addr and size are both 0
2) size is equal to 2^XLEN-1

>From the above, only #1 is checked by SBI SFENCE calls so fix the
size parameter check in SBI SFENCE calls to cover #2 as well.

Fixes: 13acfec2dbcc ("RISC-V: KVM: Add remote HFENCE functions based on VCPU requests")
Reviewed-by: Atish Patra <atishp@rivosinc.com>
Signed-off-by: Anup Patel <apatel@ventanamicro.com>
Link: https://lore.kernel.org/r/20250605061458.196003-2-apatel@ventanamicro.com
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 arch/riscv/kvm/vcpu_sbi_replace.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/riscv/kvm/vcpu_sbi_replace.c b/arch/riscv/kvm/vcpu_sbi_replace.c
index 5fbf3f94f1e8..9752d2ffff68 100644
--- a/arch/riscv/kvm/vcpu_sbi_replace.c
+++ b/arch/riscv/kvm/vcpu_sbi_replace.c
@@ -103,7 +103,7 @@ static int kvm_sbi_ext_rfence_handler(struct kvm_vcpu *vcpu, struct kvm_run *run
 		kvm_riscv_vcpu_pmu_incr_fw(vcpu, SBI_PMU_FW_FENCE_I_SENT);
 		break;
 	case SBI_EXT_RFENCE_REMOTE_SFENCE_VMA:
-		if (cp->a2 == 0 && cp->a3 == 0)
+		if ((cp->a2 == 0 && cp->a3 == 0) || cp->a3 == -1UL)
 			kvm_riscv_hfence_vvma_all(vcpu->kvm, hbase, hmask);
 		else
 			kvm_riscv_hfence_vvma_gva(vcpu->kvm, hbase, hmask,
@@ -111,7 +111,7 @@ static int kvm_sbi_ext_rfence_handler(struct kvm_vcpu *vcpu, struct kvm_run *run
 		kvm_riscv_vcpu_pmu_incr_fw(vcpu, SBI_PMU_FW_HFENCE_VVMA_SENT);
 		break;
 	case SBI_EXT_RFENCE_REMOTE_SFENCE_VMA_ASID:
-		if (cp->a2 == 0 && cp->a3 == 0)
+		if ((cp->a2 == 0 && cp->a3 == 0) || cp->a3 == -1UL)
 			kvm_riscv_hfence_vvma_asid_all(vcpu->kvm,
 						       hbase, hmask, cp->a4);
 		else

From 2e7be162996640bbe3b6da694cc064c511b8a5d9 Mon Sep 17 00:00:00 2001
From: Anup Patel <apatel@ventanamicro.com>
Date: Thu, 5 Jun 2025 11:44:47 +0530
Subject: [PATCH 0452/1334] RISC-V: KVM: Don't treat SBI HFENCE calls as NOPs
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The SBI specification clearly states that SBI HFENCE calls should
return SBI_ERR_NOT_SUPPORTED when one of the target hart doesn’t
support hypervisor extension (aka nested virtualization in-case
of KVM RISC-V).

Fixes: c7fa3c48de86 ("RISC-V: KVM: Treat SBI HFENCE calls as NOPs")
Reviewed-by: Atish Patra <atishp@rivosinc.com>
Signed-off-by: Anup Patel <apatel@ventanamicro.com>
Link: https://lore.kernel.org/r/20250605061458.196003-3-apatel@ventanamicro.com
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 arch/riscv/kvm/vcpu_sbi_replace.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/riscv/kvm/vcpu_sbi_replace.c b/arch/riscv/kvm/vcpu_sbi_replace.c
index 9752d2ffff68..b17fad091bab 100644
--- a/arch/riscv/kvm/vcpu_sbi_replace.c
+++ b/arch/riscv/kvm/vcpu_sbi_replace.c
@@ -127,9 +127,9 @@ static int kvm_sbi_ext_rfence_handler(struct kvm_vcpu *vcpu, struct kvm_run *run
 	case SBI_EXT_RFENCE_REMOTE_HFENCE_VVMA_ASID:
 		/*
 		 * Until nested virtualization is implemented, the
-		 * SBI HFENCE calls should be treated as NOPs
+		 * SBI HFENCE calls should return not supported
+		 * hence fallthrough.
 		 */
-		break;
 	default:
 		retdata->err_val = SBI_ERR_NOT_SUPPORTED;
 	}

From 0a1db19f66c0960eb00e1f2ccd40708b6747f5b1 Mon Sep 17 00:00:00 2001
From: Sascha Hauer <s.hauer@pengutronix.de>
Date: Mon, 16 Jun 2025 15:45:03 +0200
Subject: [PATCH 0453/1334] gpio: pca953x: fix wrong error probe return value

The second argument to dev_err_probe() is the error value. Pass the
return value of devm_request_threaded_irq() there instead of the irq
number.

Signed-off-by: Sascha Hauer <s.hauer@pengutronix.de>
Fixes: c47f7ff0fe61 ("gpio: pca953x: Utilise dev_err_probe() where it makes sense")
Link: https://lore.kernel.org/r/20250616134503.1201138-1-s.hauer@pengutronix.de
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
---
 drivers/gpio/gpio-pca953x.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpio/gpio-pca953x.c b/drivers/gpio/gpio-pca953x.c
index b852e4997629..e80a96f39788 100644
--- a/drivers/gpio/gpio-pca953x.c
+++ b/drivers/gpio/gpio-pca953x.c
@@ -974,7 +974,7 @@ static int pca953x_irq_setup(struct pca953x_chip *chip, int irq_base)
 					IRQF_ONESHOT | IRQF_SHARED, dev_name(dev),
 					chip);
 	if (ret)
-		return dev_err_probe(dev, client->irq, "failed to request irq\n");
+		return dev_err_probe(dev, ret, "failed to request irq\n");
 
 	return 0;
 }

From a7b3b77fd111d49f8e25624e4ea1046322a57baf Mon Sep 17 00:00:00 2001
From: Mikko Korhonen <mjkorhon@gmail.com>
Date: Tue, 17 Jun 2025 09:18:41 +0300
Subject: [PATCH 0454/1334] ata: ahci: Disallow LPM for Asus B550-F motherboard

Asus ROG STRIX B550-F GAMING (WI-FI) motherboard has problems on some
SATA ports with at least one hard drive model (WDC WD20EFAX-68FB5N0)
when LPM is enabled. Disabling LPM solves the issue.

Cc: stable@vger.kernel.org
Fixes: 7627a0edef54 ("ata: ahci: Drop low power policy board type")
Signed-off-by: Mikko Korhonen <mjkorhon@gmail.com>
Link: https://lore.kernel.org/r/20250617062055.784827-1-mjkorhon@gmail.com
[cassel: more detailed comment, make single line comments consistent]
Signed-off-by: Niklas Cassel <cassel@kernel.org>
---
 drivers/ata/ahci.c | 18 +++++++++++++++++-
 1 file changed, 17 insertions(+), 1 deletion(-)

diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c
index c8ad8ace7496..e5e5c2e81d09 100644
--- a/drivers/ata/ahci.c
+++ b/drivers/ata/ahci.c
@@ -1452,7 +1452,23 @@ static bool ahci_broken_lpm(struct pci_dev *pdev)
 				DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
 				DMI_MATCH(DMI_PRODUCT_VERSION, "ASUSPRO D840MB_M840SA"),
 			},
-			/* 320 is broken, there is no known good version yet. */
+			/* 320 is broken, there is no known good version. */
+		},
+		{
+			/*
+			 * AMD 500 Series Chipset SATA Controller [1022:43eb]
+			 * on this motherboard timeouts on ports 5 and 6 when
+			 * LPM is enabled, at least with WDC WD20EFAX-68FB5N0
+			 * hard drives. LPM with the same drive works fine on
+			 * all other ports on the same controller.
+			 */
+			.matches = {
+				DMI_MATCH(DMI_BOARD_VENDOR,
+					  "ASUSTeK COMPUTER INC."),
+				DMI_MATCH(DMI_BOARD_NAME,
+					  "ROG STRIX B550-F GAMING (WI-FI)"),
+			},
+			/* 3621 is broken, there is no known good version. */
 		},
 		{ }	/* terminate list */
 	};

From 7f90d45e57cb2ef1f0adcaf925ddffdfc5e680ca Mon Sep 17 00:00:00 2001
From: Justin Sanders <jsanders.devel@gmail.com>
Date: Tue, 10 Jun 2025 17:05:59 +0000
Subject: [PATCH 0455/1334] aoe: clean device rq_list in aoedev_downdev()

An aoe device's rq_list contains accepted block requests that are
waiting to be transmitted to the aoe target. This queue was added as
part of the conversion to blk_mq. However, the queue was not cleaned out
when an aoe device is downed which caused blk_mq_freeze_queue() to sleep
indefinitely waiting for those requests to complete, causing a hang. This
fix cleans out the queue before calling blk_mq_freeze_queue().

Link: https://bugzilla.kernel.org/show_bug.cgi?id=212665
Fixes: 3582dd291788 ("aoe: convert aoeblk to blk-mq")
Signed-off-by: Justin Sanders <jsanders.devel@gmail.com>
Link: https://lore.kernel.org/r/20250610170600.869-1-jsanders.devel@gmail.com
Tested-By: Valentin Kleibel <valentin@vrvis.at>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/aoe/aoedev.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/block/aoe/aoedev.c b/drivers/block/aoe/aoedev.c
index 141b2a0e03f2..8c18034cb3d6 100644
--- a/drivers/block/aoe/aoedev.c
+++ b/drivers/block/aoe/aoedev.c
@@ -198,6 +198,7 @@ aoedev_downdev(struct aoedev *d)
 {
 	struct aoetgt *t, **tt, **te;
 	struct list_head *head, *pos, *nx;
+	struct request *rq, *rqnext;
 	int i;
 
 	d->flags &= ~DEVFL_UP;
@@ -223,6 +224,13 @@ aoedev_downdev(struct aoedev *d)
 	/* clean out the in-process request (if any) */
 	aoe_failip(d);
 
+	/* clean out any queued block requests */
+	list_for_each_entry_safe(rq, rqnext, &d->rq_list, queuelist) {
+		list_del_init(&rq->queuelist);
+		blk_mq_start_request(rq);
+		blk_mq_end_request(rq, BLK_STS_IOERR);
+	}
+
 	/* fast fail all pending I/O */
 	if (d->blkq) {
 		/* UP is cleared, freeze+quiesce to insure all are errored */

From cffc873d68ab09a0432b8212008c5613f8a70a2c Mon Sep 17 00:00:00 2001
From: Justin Sanders <jsanders.devel@gmail.com>
Date: Tue, 10 Jun 2025 17:06:00 +0000
Subject: [PATCH 0456/1334] aoe: defer rexmit timer downdev work to workqueue

When aoe's rexmit_timer() notices that an aoe target fails to respond to
commands for more than aoe_deadsecs, it calls aoedev_downdev() which
cleans the outstanding aoe and block queues. This can involve sleeping,
such as in blk_mq_freeze_queue(), which should not occur in irq context.

This patch defers that aoedev_downdev() call to the aoe device's
workqueue.

Link: https://bugzilla.kernel.org/show_bug.cgi?id=212665
Signed-off-by: Justin Sanders <jsanders.devel@gmail.com>
Link: https://lore.kernel.org/r/20250610170600.869-2-jsanders.devel@gmail.com
Tested-By: Valentin Kleibel <valentin@vrvis.at>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/aoe/aoe.h    | 1 +
 drivers/block/aoe/aoecmd.c | 8 ++++++--
 drivers/block/aoe/aoedev.c | 5 ++++-
 3 files changed, 11 insertions(+), 3 deletions(-)

diff --git a/drivers/block/aoe/aoe.h b/drivers/block/aoe/aoe.h
index 749ae1246f4c..d35caa3c69e1 100644
--- a/drivers/block/aoe/aoe.h
+++ b/drivers/block/aoe/aoe.h
@@ -80,6 +80,7 @@ enum {
 	DEVFL_NEWSIZE = (1<<6),	/* need to update dev size in block layer */
 	DEVFL_FREEING = (1<<7),	/* set when device is being cleaned up */
 	DEVFL_FREED = (1<<8),	/* device has been cleaned up */
+	DEVFL_DEAD = (1<<9),	/* device has timed out of aoe_deadsecs */
 };
 
 enum {
diff --git a/drivers/block/aoe/aoecmd.c b/drivers/block/aoe/aoecmd.c
index 92b06d1de4cc..6c94cfd1c480 100644
--- a/drivers/block/aoe/aoecmd.c
+++ b/drivers/block/aoe/aoecmd.c
@@ -754,7 +754,7 @@ rexmit_timer(struct timer_list *timer)
 
 	utgts = count_targets(d, NULL);
 
-	if (d->flags & DEVFL_TKILL) {
+	if (d->flags & (DEVFL_TKILL | DEVFL_DEAD)) {
 		spin_unlock_irqrestore(&d->lock, flags);
 		return;
 	}
@@ -786,7 +786,8 @@ rexmit_timer(struct timer_list *timer)
 			 * to clean up.
 			 */
 			list_splice(&flist, &d->factive[0]);
-			aoedev_downdev(d);
+			d->flags |= DEVFL_DEAD;
+			queue_work(aoe_wq, &d->work);
 			goto out;
 		}
 
@@ -898,6 +899,9 @@ aoecmd_sleepwork(struct work_struct *work)
 {
 	struct aoedev *d = container_of(work, struct aoedev, work);
 
+	if (d->flags & DEVFL_DEAD)
+		aoedev_downdev(d);
+
 	if (d->flags & DEVFL_GDALLOC)
 		aoeblk_gdalloc(d);
 
diff --git a/drivers/block/aoe/aoedev.c b/drivers/block/aoe/aoedev.c
index 8c18034cb3d6..9b66f8ebce50 100644
--- a/drivers/block/aoe/aoedev.c
+++ b/drivers/block/aoe/aoedev.c
@@ -200,8 +200,11 @@ aoedev_downdev(struct aoedev *d)
 	struct list_head *head, *pos, *nx;
 	struct request *rq, *rqnext;
 	int i;
+	unsigned long flags;
 
-	d->flags &= ~DEVFL_UP;
+	spin_lock_irqsave(&d->lock, flags);
+	d->flags &= ~(DEVFL_UP | DEVFL_DEAD);
+	spin_unlock_irqrestore(&d->lock, flags);
 
 	/* clean out active and to-be-retransmitted buffers */
 	for (i = 0; i < NFACTIVE; i++) {

From a85b8544d46390469b6ca72d6bfd3ecb7be985ff Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Sat, 14 Jun 2025 00:30:37 +0200
Subject: [PATCH 0457/1334] wifi: remove zero-length arrays

All of these are really meant to be variable-length, and
in the case of s1g_beacon it's actually accessed. Make that
one in particular, and a couple of others (that aren't used
as arrays now), actually variable.

Reported-by: syzbot+fd222bb38e916df26fa4@syzkaller.appspotmail.com
Fixes: 1e1f706fc2ce ("wifi: cfg80211/mac80211: correctly parse S1G beacon optional elements")
Link: https://patch.msgid.link/20250614003037.a3e82e882251.I2e8b58e56ff2a9f8b06c66f036578b7c1d4e4685@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/linux/ieee80211.h | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index ce377f7fb912..22f39e5e2ff1 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -1278,7 +1278,7 @@ struct ieee80211_ext {
 			u8 sa[ETH_ALEN];
 			__le32 timestamp;
 			u8 change_seq;
-			u8 variable[0];
+			u8 variable[];
 		} __packed s1g_beacon;
 	} u;
 } __packed __aligned(2);
@@ -1536,7 +1536,7 @@ struct ieee80211_mgmt {
 					u8 action_code;
 					u8 dialog_token;
 					__le16 capability;
-					u8 variable[0];
+					u8 variable[];
 				} __packed tdls_discover_resp;
 				struct {
 					u8 action_code;
@@ -1721,35 +1721,35 @@ struct ieee80211_tdls_data {
 		struct {
 			u8 dialog_token;
 			__le16 capability;
-			u8 variable[0];
+			u8 variable[];
 		} __packed setup_req;
 		struct {
 			__le16 status_code;
 			u8 dialog_token;
 			__le16 capability;
-			u8 variable[0];
+			u8 variable[];
 		} __packed setup_resp;
 		struct {
 			__le16 status_code;
 			u8 dialog_token;
-			u8 variable[0];
+			u8 variable[];
 		} __packed setup_cfm;
 		struct {
 			__le16 reason_code;
-			u8 variable[0];
+			u8 variable[];
 		} __packed teardown;
 		struct {
 			u8 dialog_token;
-			u8 variable[0];
+			u8 variable[];
 		} __packed discover_req;
 		struct {
 			u8 target_channel;
 			u8 oper_class;
-			u8 variable[0];
+			u8 variable[];
 		} __packed chan_switch_req;
 		struct {
 			__le16 status_code;
-			u8 variable[0];
+			u8 variable[];
 		} __packed chan_switch_resp;
 	} u;
 } __packed;

From d1b1a5eb27c4948e8811cf4dbb05aaf3eb10700c Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Mon, 16 Jun 2025 17:18:38 +0200
Subject: [PATCH 0458/1334] wifi: mac80211: drop invalid source address OCB
 frames

In OCB, don't accept frames from invalid source addresses
(and in particular don't try to create stations for them),
drop the frames instead.

Reported-by: syzbot+8b512026a7ec10dcbdd9@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/r/6788d2d9.050a0220.20d369.0028.GAE@google.com/
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Tested-by: syzbot+8b512026a7ec10dcbdd9@syzkaller.appspotmail.com
Link: https://patch.msgid.link/20250616171838.7433379cab5d.I47444d63c72a0bd58d2e2b67bb99e1fea37eec6f@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/rx.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index 09beb65d6108..e73431549ce7 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -4432,6 +4432,10 @@ static bool ieee80211_accept_frame(struct ieee80211_rx_data *rx)
 		if (!multicast &&
 		    !ether_addr_equal(sdata->dev->dev_addr, hdr->addr1))
 			return false;
+		/* reject invalid/our STA address */
+		if (!is_valid_ether_addr(hdr->addr2) ||
+		    ether_addr_equal(sdata->dev->dev_addr, hdr->addr2))
+			return false;
 		if (!rx->sta) {
 			int rate_idx;
 			if (status->encoding != RX_ENC_LEGACY)

From d19bac3d4edc4ab92e90d1c6bf68620192254b4b Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Tue, 17 Jun 2025 10:49:01 +0200
Subject: [PATCH 0459/1334] wifi: mac80211: don't WARN for late channel/color
 switch

There's really no value in the WARN stack trace etc., the reason
for this happening isn't directly related to the calling function
anyway. Also, syzbot has been observing it constantly, and there's
no way we can resolve it there - those systems are just slow.

Instead print an error message (once) and add a comment about what
really causes this message.

Reported-by: syzbot+468656785707b0e995df@syzkaller.appspotmail.com
Reported-by: syzbot+18c783c5cf6a781e3e2c@syzkaller.appspotmail.com
Reported-by: syzbot+d5924d5cffddfccab68e@syzkaller.appspotmail.com
Reported-by: syzbot+7d73d99525d1ff7752ef@syzkaller.appspotmail.com
Reported-by: syzbot+8e6e002c74d1927edaf5@syzkaller.appspotmail.com
Reported-by: syzbot+97254a3b10c541879a65@syzkaller.appspotmail.com
Reported-by: syzbot+dfd1fd46a1960ad9c6ec@syzkaller.appspotmail.com
Reported-by: syzbot+85e0b8d12d9ca877d806@syzkaller.appspotmail.com
Link: https://patch.msgid.link/20250617104902.146e10919be1.I85f352ca4a2dce6f556e5ff45ceaa5f3769cb5ce@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/debug.h |  5 ++++-
 net/mac80211/tx.c    | 29 +++++++++++++++++++++--------
 2 files changed, 25 insertions(+), 9 deletions(-)

diff --git a/net/mac80211/debug.h b/net/mac80211/debug.h
index 5b81998cb0c9..ef7c1a68d88d 100644
--- a/net/mac80211/debug.h
+++ b/net/mac80211/debug.h
@@ -1,10 +1,11 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Portions
- * Copyright (C) 2022 - 2024 Intel Corporation
+ * Copyright (C) 2022 - 2025 Intel Corporation
  */
 #ifndef __MAC80211_DEBUG_H
 #define __MAC80211_DEBUG_H
+#include <linux/once_lite.h>
 #include <net/cfg80211.h>
 
 #ifdef CONFIG_MAC80211_OCB_DEBUG
@@ -152,6 +153,8 @@ do {									\
 		else							\
 			_sdata_err((link)->sdata, fmt, ##__VA_ARGS__);	\
 	} while (0)
+#define link_err_once(link, fmt, ...)					\
+	DO_ONCE_LITE(link_err, link, fmt, ##__VA_ARGS__)
 #define link_id_info(sdata, link_id, fmt, ...)				\
 	do {								\
 		if (ieee80211_vif_is_mld(&sdata->vif))			\
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index d8d4f3d7d7f2..d58b80813bdd 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -5,7 +5,7 @@
  * Copyright 2006-2007	Jiri Benc <jbenc@suse.cz>
  * Copyright 2007	Johannes Berg <johannes@sipsolutions.net>
  * Copyright 2013-2014  Intel Mobile Communications GmbH
- * Copyright (C) 2018-2024 Intel Corporation
+ * Copyright (C) 2018-2025 Intel Corporation
  *
  * Transmit and frame generation functions.
  */
@@ -5016,12 +5016,25 @@ static void ieee80211_set_beacon_cntdwn(struct ieee80211_sub_if_data *sdata,
 	}
 }
 
-static u8 __ieee80211_beacon_update_cntdwn(struct beacon_data *beacon)
+static u8 __ieee80211_beacon_update_cntdwn(struct ieee80211_link_data *link,
+					   struct beacon_data *beacon)
 {
-	beacon->cntdwn_current_counter--;
+	if (beacon->cntdwn_current_counter == 1) {
+		/*
+		 * Channel switch handling is done by a worker thread while
+		 * beacons get pulled from hardware timers. It's therefore
+		 * possible that software threads are slow enough to not be
+		 * able to complete CSA handling in a single beacon interval,
+		 * in which case we get here. There isn't much to do about
+		 * it, other than letting the user know that the AP isn't
+		 * behaving correctly.
+		 */
+		link_err_once(link,
+			      "beacon TX faster than countdown (channel/color switch) completion\n");
+		return 0;
+	}
 
-	/* the counter should never reach 0 */
-	WARN_ON_ONCE(!beacon->cntdwn_current_counter);
+	beacon->cntdwn_current_counter--;
 
 	return beacon->cntdwn_current_counter;
 }
@@ -5052,7 +5065,7 @@ u8 ieee80211_beacon_update_cntdwn(struct ieee80211_vif *vif, unsigned int link_i
 	if (!beacon)
 		goto unlock;
 
-	count = __ieee80211_beacon_update_cntdwn(beacon);
+	count = __ieee80211_beacon_update_cntdwn(link, beacon);
 
 unlock:
 	rcu_read_unlock();
@@ -5450,7 +5463,7 @@ __ieee80211_beacon_get(struct ieee80211_hw *hw,
 
 		if (beacon->cntdwn_counter_offsets[0]) {
 			if (!is_template)
-				__ieee80211_beacon_update_cntdwn(beacon);
+				__ieee80211_beacon_update_cntdwn(link, beacon);
 
 			ieee80211_set_beacon_cntdwn(sdata, beacon, link);
 		}
@@ -5482,7 +5495,7 @@ __ieee80211_beacon_get(struct ieee80211_hw *hw,
 				 * for now we leave it consistent with overall
 				 * mac80211's behavior.
 				 */
-				__ieee80211_beacon_update_cntdwn(beacon);
+				__ieee80211_beacon_update_cntdwn(link, beacon);
 
 			ieee80211_set_beacon_cntdwn(sdata, beacon, link);
 		}

From c8892c2a5b27d4026cda60409c393ba0d6c88df9 Mon Sep 17 00:00:00 2001
From: Ivan Hu <ivan.hu@canonical.com>
Date: Mon, 16 Jun 2025 15:48:19 +0800
Subject: [PATCH 0460/1334] platform/x86: portwell-ec: Move watchdog device
 under correct platform hierarchy
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Without explicitly setting a parent for the watchdog device, the device is
registered with a NULL parent. This causes device_add() (called internally
by devm_watchdog_register_device()) to register the device under
/sys/devices/virtual, since no parent is provided. The result is:

DEVPATH=/devices/virtual/watchdog/watchdog0

To fix this, assign &pdev->dev as the parent of the watchdog device before
calling devm_watchdog_register_device(). This ensures the device is
associated with the Portwell EC platform device and placed correctly in
sysfs as:

DEVPATH=/devices/platform/portwell-ec/watchdog/watchdog0

This aligns the device hierarchy with expectations and avoids misplacement
under the virtual class.

Fixes: 835796753310 ("platform/x86: portwell-ec: Add GPIO and WDT driver for Portwell EC")
Signed-off-by: Ivan Hu <ivan.hu@canonical.com>
Link: https://lore.kernel.org/r/20250616074819.63547-1-ivan.hu@canonical.com
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/portwell-ec.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/platform/x86/portwell-ec.c b/drivers/platform/x86/portwell-ec.c
index 8b788822237b..3e019c51913e 100644
--- a/drivers/platform/x86/portwell-ec.c
+++ b/drivers/platform/x86/portwell-ec.c
@@ -236,6 +236,7 @@ static int pwec_probe(struct platform_device *pdev)
 		return ret;
 	}
 
+	ec_wdt_dev.parent = &pdev->dev;
 	ret = devm_watchdog_register_device(&pdev->dev, &ec_wdt_dev);
 	if (ret < 0) {
 		dev_err(&pdev->dev, "failed to register Portwell EC Watchdog\n");

From 109f4d29dade8ae5b4ac6325af9d1bc24b4230f8 Mon Sep 17 00:00:00 2001
From: David Thompson <davthompson@nvidia.com>
Date: Fri, 13 Jun 2025 21:46:08 +0000
Subject: [PATCH 0461/1334] platform/mellanox: mlxbf-tmfifo: fix vring_desc.len
 assignment
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Fix warnings reported by sparse, related to incorrect type:
drivers/platform/mellanox/mlxbf-tmfifo.c:284:38: warning: incorrect type in assignment (different base types)
drivers/platform/mellanox/mlxbf-tmfifo.c:284:38:    expected restricted __virtio32 [usertype] len
drivers/platform/mellanox/mlxbf-tmfifo.c:284:38:    got unsigned long

Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202404040339.S7CUIgf3-lkp@intel.com/
Fixes: 78034cbece79 ("platform/mellanox: mlxbf-tmfifo: Drop the Rx packet if no more descriptors")
Signed-off-by: David Thompson <davthompson@nvidia.com>
Link: https://lore.kernel.org/r/20250613214608.2250130-1-davthompson@nvidia.com
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/mellanox/mlxbf-tmfifo.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/platform/mellanox/mlxbf-tmfifo.c b/drivers/platform/mellanox/mlxbf-tmfifo.c
index aae99adb29eb..70c58c4c6c84 100644
--- a/drivers/platform/mellanox/mlxbf-tmfifo.c
+++ b/drivers/platform/mellanox/mlxbf-tmfifo.c
@@ -281,7 +281,8 @@ static int mlxbf_tmfifo_alloc_vrings(struct mlxbf_tmfifo *fifo,
 		vring->align = SMP_CACHE_BYTES;
 		vring->index = i;
 		vring->vdev_id = tm_vdev->vdev.id.device;
-		vring->drop_desc.len = VRING_DROP_DESC_MAX_LEN;
+		vring->drop_desc.len = cpu_to_virtio32(&tm_vdev->vdev,
+						       VRING_DROP_DESC_MAX_LEN);
 		dev = &tm_vdev->vdev.dev;
 
 		size = vring_size(vring->num, vring->align);

From 91a7703a036b146481b8a0bd6efa6200d296ca5d Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Tue, 17 Jun 2025 06:41:48 -0600
Subject: [PATCH 0462/1334] io_uring: remove duplicate
 io_uring_alloc_task_context() definition

This function exists in both tctx.h (where it belongs) and in io_uring.h
as a remnant of before the tctx handling code got split out. Remove the
io_uring.h definition and ensure that sqpoll.c includes the tctx.h
header to get the definition.

Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/io_uring.h | 2 --
 io_uring/sqpoll.c   | 1 +
 2 files changed, 1 insertion(+), 2 deletions(-)

diff --git a/io_uring/io_uring.h b/io_uring/io_uring.h
index d59c12277d58..66c1ca73f55e 100644
--- a/io_uring/io_uring.h
+++ b/io_uring/io_uring.h
@@ -98,8 +98,6 @@ struct llist_node *io_handle_tw_list(struct llist_node *node, unsigned int *coun
 struct llist_node *tctx_task_work_run(struct io_uring_task *tctx, unsigned int max_entries, unsigned int *count);
 void tctx_task_work(struct callback_head *cb);
 __cold void io_uring_cancel_generic(bool cancel_all, struct io_sq_data *sqd);
-int io_uring_alloc_task_context(struct task_struct *task,
-				struct io_ring_ctx *ctx);
 
 int io_ring_add_registered_file(struct io_uring_task *tctx, struct file *file,
 				     int start, int end);
diff --git a/io_uring/sqpoll.c b/io_uring/sqpoll.c
index 268d2fbe6160..fa5a6750ee52 100644
--- a/io_uring/sqpoll.c
+++ b/io_uring/sqpoll.c
@@ -16,6 +16,7 @@
 #include <uapi/linux/io_uring.h>
 
 #include "io_uring.h"
+#include "tctx.h"
 #include "napi.h"
 #include "sqpoll.h"
 

From f2320f1dd6f6f82cb2c7aff23a12bab537bdea89 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Tue, 17 Jun 2025 06:43:18 -0600
Subject: [PATCH 0463/1334] io_uring/sqpoll: don't put task_struct on tctx
 setup failure

A recent commit moved the error handling of sqpoll thread and tctx
failures into the thread itself, as part of fixing an issue. However, it
missed that tctx allocation may also fail, and that
io_sq_offload_create() does its own error handling for the task_struct
in that case.

Remove the manual task putting in io_sq_offload_create(), as
io_sq_thread() will notice that the tctx did not get setup and hence it
should put itself and exit.

Reported-by: syzbot+763e12bbf004fb1062e4@syzkaller.appspotmail.com
Fixes: ac0b8b327a56 ("io_uring: fix use-after-free of sq->thread in __io_uring_show_fdinfo()")
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/sqpoll.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/io_uring/sqpoll.c b/io_uring/sqpoll.c
index fa5a6750ee52..a3f11349ce06 100644
--- a/io_uring/sqpoll.c
+++ b/io_uring/sqpoll.c
@@ -420,7 +420,6 @@ void io_sqpoll_wait_sq(struct io_ring_ctx *ctx)
 __cold int io_sq_offload_create(struct io_ring_ctx *ctx,
 				struct io_uring_params *p)
 {
-	struct task_struct *task_to_put = NULL;
 	int ret;
 
 	/* Retain compatibility with failing for an invalid attach attempt */
@@ -499,7 +498,7 @@ __cold int io_sq_offload_create(struct io_ring_ctx *ctx,
 		rcu_assign_pointer(sqd->thread, tsk);
 		mutex_unlock(&sqd->lock);
 
-		task_to_put = get_task_struct(tsk);
+		get_task_struct(tsk);
 		ret = io_uring_alloc_task_context(tsk, ctx);
 		wake_up_new_task(tsk);
 		if (ret)
@@ -514,8 +513,6 @@ err_sqpoll:
 	complete(&ctx->sq_data->exited);
 err:
 	io_sq_thread_finish(ctx);
-	if (task_to_put)
-		put_task_struct(task_to_put);
 	return ret;
 }
 

From 7b4ac12cc929e281cf7edc22203e0533790ebc2b Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Fri, 13 Jun 2025 14:36:29 +0200
Subject: [PATCH 0464/1334] openvswitch: Allocate struct ovs_pcpu_storage
 dynamically

PERCPU_MODULE_RESERVE defines the maximum size that can by used for the
per-CPU data size used by modules. This is 8KiB.

Commit 035fcdc4d240c ("openvswitch: Merge three per-CPU structures into
one") restructured the per-CPU memory allocation for the module and
moved the separate alloc_percpu() invocations at module init time to a
static per-CPU variable which is allocated by the module loader.

The size of the per-CPU data section for openvswitch is 6488 bytes which
is ~80% of the available per-CPU memory. Together with a few other
modules it is easy to exhaust the available 8KiB of memory.

Allocate ovs_pcpu_storage dynamically at module init time.

Reported-by: Gal Pressman <gal@nvidia.com>
Closes: https://lore.kernel.org/all/c401e017-f8db-4f57-a1cd-89beb979a277@nvidia.com
Fixes: 035fcdc4d240c ("openvswitch: Merge three per-CPU structures into one")
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Reviewed-by: Aaron Conole <aconole@redhat.com>
Link: https://patch.msgid.link/20250613123629.-XSoQTCu@linutronix.de
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/openvswitch/actions.c  | 23 +++++++++------------
 net/openvswitch/datapath.c | 42 +++++++++++++++++++++++++++++++-------
 net/openvswitch/datapath.h |  3 ++-
 3 files changed, 47 insertions(+), 21 deletions(-)

diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index e7269a3eec79..3add108340bf 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -39,16 +39,14 @@
 #include "flow_netlink.h"
 #include "openvswitch_trace.h"
 
-DEFINE_PER_CPU(struct ovs_pcpu_storage, ovs_pcpu_storage) = {
-	.bh_lock = INIT_LOCAL_LOCK(bh_lock),
-};
+struct ovs_pcpu_storage __percpu *ovs_pcpu_storage;
 
 /* Make a clone of the 'key', using the pre-allocated percpu 'flow_keys'
  * space. Return NULL if out of key spaces.
  */
 static struct sw_flow_key *clone_key(const struct sw_flow_key *key_)
 {
-	struct ovs_pcpu_storage *ovs_pcpu = this_cpu_ptr(&ovs_pcpu_storage);
+	struct ovs_pcpu_storage *ovs_pcpu = this_cpu_ptr(ovs_pcpu_storage);
 	struct action_flow_keys *keys = &ovs_pcpu->flow_keys;
 	int level = ovs_pcpu->exec_level;
 	struct sw_flow_key *key = NULL;
@@ -94,7 +92,7 @@ static struct deferred_action *add_deferred_actions(struct sk_buff *skb,
 				    const struct nlattr *actions,
 				    const int actions_len)
 {
-	struct action_fifo *fifo = this_cpu_ptr(&ovs_pcpu_storage.action_fifos);
+	struct action_fifo *fifo = this_cpu_ptr(&ovs_pcpu_storage->action_fifos);
 	struct deferred_action *da;
 
 	da = action_fifo_put(fifo);
@@ -755,7 +753,7 @@ static int set_sctp(struct sk_buff *skb, struct sw_flow_key *flow_key,
 static int ovs_vport_output(struct net *net, struct sock *sk,
 			    struct sk_buff *skb)
 {
-	struct ovs_frag_data *data = this_cpu_ptr(&ovs_pcpu_storage.frag_data);
+	struct ovs_frag_data *data = this_cpu_ptr(&ovs_pcpu_storage->frag_data);
 	struct vport *vport = data->vport;
 
 	if (skb_cow_head(skb, data->l2_len) < 0) {
@@ -807,7 +805,7 @@ static void prepare_frag(struct vport *vport, struct sk_buff *skb,
 	unsigned int hlen = skb_network_offset(skb);
 	struct ovs_frag_data *data;
 
-	data = this_cpu_ptr(&ovs_pcpu_storage.frag_data);
+	data = this_cpu_ptr(&ovs_pcpu_storage->frag_data);
 	data->dst = skb->_skb_refdst;
 	data->vport = vport;
 	data->cb = *OVS_CB(skb);
@@ -1566,16 +1564,15 @@ static int clone_execute(struct datapath *dp, struct sk_buff *skb,
 	clone = clone_flow_key ? clone_key(key) : key;
 	if (clone) {
 		int err = 0;
-
 		if (actions) { /* Sample action */
 			if (clone_flow_key)
-				__this_cpu_inc(ovs_pcpu_storage.exec_level);
+				__this_cpu_inc(ovs_pcpu_storage->exec_level);
 
 			err = do_execute_actions(dp, skb, clone,
 						 actions, len);
 
 			if (clone_flow_key)
-				__this_cpu_dec(ovs_pcpu_storage.exec_level);
+				__this_cpu_dec(ovs_pcpu_storage->exec_level);
 		} else { /* Recirc action */
 			clone->recirc_id = recirc_id;
 			ovs_dp_process_packet(skb, clone);
@@ -1611,7 +1608,7 @@ static int clone_execute(struct datapath *dp, struct sk_buff *skb,
 
 static void process_deferred_actions(struct datapath *dp)
 {
-	struct action_fifo *fifo = this_cpu_ptr(&ovs_pcpu_storage.action_fifos);
+	struct action_fifo *fifo = this_cpu_ptr(&ovs_pcpu_storage->action_fifos);
 
 	/* Do not touch the FIFO in case there is no deferred actions. */
 	if (action_fifo_is_empty(fifo))
@@ -1642,7 +1639,7 @@ int ovs_execute_actions(struct datapath *dp, struct sk_buff *skb,
 {
 	int err, level;
 
-	level = __this_cpu_inc_return(ovs_pcpu_storage.exec_level);
+	level = __this_cpu_inc_return(ovs_pcpu_storage->exec_level);
 	if (unlikely(level > OVS_RECURSION_LIMIT)) {
 		net_crit_ratelimited("ovs: recursion limit reached on datapath %s, probable configuration error\n",
 				     ovs_dp_name(dp));
@@ -1659,6 +1656,6 @@ int ovs_execute_actions(struct datapath *dp, struct sk_buff *skb,
 		process_deferred_actions(dp);
 
 out:
-	__this_cpu_dec(ovs_pcpu_storage.exec_level);
+	__this_cpu_dec(ovs_pcpu_storage->exec_level);
 	return err;
 }
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index 6a304ae2d959..b990dc83504f 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -244,7 +244,7 @@ void ovs_dp_detach_port(struct vport *p)
 /* Must be called with rcu_read_lock. */
 void ovs_dp_process_packet(struct sk_buff *skb, struct sw_flow_key *key)
 {
-	struct ovs_pcpu_storage *ovs_pcpu = this_cpu_ptr(&ovs_pcpu_storage);
+	struct ovs_pcpu_storage *ovs_pcpu = this_cpu_ptr(ovs_pcpu_storage);
 	const struct vport *p = OVS_CB(skb)->input_vport;
 	struct datapath *dp = p->dp;
 	struct sw_flow *flow;
@@ -299,7 +299,7 @@ void ovs_dp_process_packet(struct sk_buff *skb, struct sw_flow_key *key)
 	 * avoided.
 	 */
 	if (IS_ENABLED(CONFIG_PREEMPT_RT) && ovs_pcpu->owner != current) {
-		local_lock_nested_bh(&ovs_pcpu_storage.bh_lock);
+		local_lock_nested_bh(&ovs_pcpu_storage->bh_lock);
 		ovs_pcpu->owner = current;
 		ovs_pcpu_locked = true;
 	}
@@ -310,7 +310,7 @@ void ovs_dp_process_packet(struct sk_buff *skb, struct sw_flow_key *key)
 				    ovs_dp_name(dp), error);
 	if (ovs_pcpu_locked) {
 		ovs_pcpu->owner = NULL;
-		local_unlock_nested_bh(&ovs_pcpu_storage.bh_lock);
+		local_unlock_nested_bh(&ovs_pcpu_storage->bh_lock);
 	}
 
 	stats_counter = &stats->n_hit;
@@ -689,13 +689,13 @@ static int ovs_packet_cmd_execute(struct sk_buff *skb, struct genl_info *info)
 	sf_acts = rcu_dereference(flow->sf_acts);
 
 	local_bh_disable();
-	local_lock_nested_bh(&ovs_pcpu_storage.bh_lock);
+	local_lock_nested_bh(&ovs_pcpu_storage->bh_lock);
 	if (IS_ENABLED(CONFIG_PREEMPT_RT))
-		this_cpu_write(ovs_pcpu_storage.owner, current);
+		this_cpu_write(ovs_pcpu_storage->owner, current);
 	err = ovs_execute_actions(dp, packet, sf_acts, &flow->key);
 	if (IS_ENABLED(CONFIG_PREEMPT_RT))
-		this_cpu_write(ovs_pcpu_storage.owner, NULL);
-	local_unlock_nested_bh(&ovs_pcpu_storage.bh_lock);
+		this_cpu_write(ovs_pcpu_storage->owner, NULL);
+	local_unlock_nested_bh(&ovs_pcpu_storage->bh_lock);
 	local_bh_enable();
 	rcu_read_unlock();
 
@@ -2744,6 +2744,28 @@ static struct drop_reason_list drop_reason_list_ovs = {
 	.n_reasons = ARRAY_SIZE(ovs_drop_reasons),
 };
 
+static int __init ovs_alloc_percpu_storage(void)
+{
+	unsigned int cpu;
+
+	ovs_pcpu_storage = alloc_percpu(*ovs_pcpu_storage);
+	if (!ovs_pcpu_storage)
+		return -ENOMEM;
+
+	for_each_possible_cpu(cpu) {
+		struct ovs_pcpu_storage *ovs_pcpu;
+
+		ovs_pcpu = per_cpu_ptr(ovs_pcpu_storage, cpu);
+		local_lock_init(&ovs_pcpu->bh_lock);
+	}
+	return 0;
+}
+
+static void ovs_free_percpu_storage(void)
+{
+	free_percpu(ovs_pcpu_storage);
+}
+
 static int __init dp_init(void)
 {
 	int err;
@@ -2753,6 +2775,10 @@ static int __init dp_init(void)
 
 	pr_info("Open vSwitch switching datapath\n");
 
+	err = ovs_alloc_percpu_storage();
+	if (err)
+		goto error;
+
 	err = ovs_internal_dev_rtnl_link_register();
 	if (err)
 		goto error;
@@ -2799,6 +2825,7 @@ error_flow_exit:
 error_unreg_rtnl_link:
 	ovs_internal_dev_rtnl_link_unregister();
 error:
+	ovs_free_percpu_storage();
 	return err;
 }
 
@@ -2813,6 +2840,7 @@ static void dp_cleanup(void)
 	ovs_vport_exit();
 	ovs_flow_exit();
 	ovs_internal_dev_rtnl_link_unregister();
+	ovs_free_percpu_storage();
 }
 
 module_init(dp_init);
diff --git a/net/openvswitch/datapath.h b/net/openvswitch/datapath.h
index 1b5348b0f559..cfeb817a1889 100644
--- a/net/openvswitch/datapath.h
+++ b/net/openvswitch/datapath.h
@@ -220,7 +220,8 @@ struct ovs_pcpu_storage {
 	struct task_struct *owner;
 	local_lock_t bh_lock;
 };
-DECLARE_PER_CPU(struct ovs_pcpu_storage, ovs_pcpu_storage);
+
+extern struct ovs_pcpu_storage __percpu *ovs_pcpu_storage;
 
 /**
  * enum ovs_pkt_hash_types - hash info to include with a packet

From d8010d4ba43e9f790925375a7de100604a5e2dba Mon Sep 17 00:00:00 2001
From: "Borislav Petkov (AMD)" <bp@alien8.de>
Date: Wed, 11 Sep 2024 10:53:08 +0200
Subject: [PATCH 0465/1334] x86/bugs: Add a Transient Scheduler Attacks
 mitigation

Add the required features detection glue to bugs.c et all in order to
support the TSA mitigation.

Co-developed-by: Kim Phillips <kim.phillips@amd.com>
Signed-off-by: Kim Phillips <kim.phillips@amd.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Pawan Gupta <pawan.kumar.gupta@linux.intel.com>
---
 .../ABI/testing/sysfs-devices-system-cpu      |   1 +
 .../admin-guide/kernel-parameters.txt         |  13 ++
 arch/x86/Kconfig                              |   9 ++
 arch/x86/include/asm/cpufeatures.h            |   6 +-
 arch/x86/include/asm/mwait.h                  |   2 +-
 arch/x86/include/asm/nospec-branch.h          |  14 +-
 arch/x86/kernel/cpu/amd.c                     |  44 +++++++
 arch/x86/kernel/cpu/bugs.c                    | 124 ++++++++++++++++++
 arch/x86/kernel/cpu/common.c                  |  14 +-
 arch/x86/kernel/cpu/scattered.c               |   2 +
 arch/x86/kvm/svm/vmenter.S                    |   6 +
 drivers/base/cpu.c                            |   3 +
 include/linux/cpu.h                           |   1 +
 13 files changed, 232 insertions(+), 7 deletions(-)

diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu
index bf85f4de6862..ab8cd337f43a 100644
--- a/Documentation/ABI/testing/sysfs-devices-system-cpu
+++ b/Documentation/ABI/testing/sysfs-devices-system-cpu
@@ -584,6 +584,7 @@ What:		/sys/devices/system/cpu/vulnerabilities
 		/sys/devices/system/cpu/vulnerabilities/spectre_v1
 		/sys/devices/system/cpu/vulnerabilities/spectre_v2
 		/sys/devices/system/cpu/vulnerabilities/srbds
+		/sys/devices/system/cpu/vulnerabilities/tsa
 		/sys/devices/system/cpu/vulnerabilities/tsx_async_abort
 Date:		January 2018
 Contact:	Linux kernel mailing list <linux-kernel@vger.kernel.org>
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index f1f2c0874da9..07e22ba5bfe3 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -7488,6 +7488,19 @@
 			having this key zero'ed is acceptable. E.g. in testing
 			scenarios.
 
+	tsa=		[X86] Control mitigation for Transient Scheduler
+			Attacks on AMD CPUs. Search the following in your
+			favourite search engine for more details:
+
+			"Technical guidance for mitigating transient scheduler
+			attacks".
+
+			off		- disable the mitigation
+			on		- enable the mitigation (default)
+			user		- mitigate only user/kernel transitions
+			vm		- mitigate only guest/host transitions
+
+
 	tsc=		Disable clocksource stability checks for TSC.
 			Format: <string>
 			[x86] reliable: mark tsc clocksource as reliable, this
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 340e5468980e..71dfe7d7c786 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -2695,6 +2695,15 @@ config MITIGATION_ITS
 	  disabled, mitigation cannot be enabled via cmdline.
 	  See <file:Documentation/admin-guide/hw-vuln/indirect-target-selection.rst>
 
+config MITIGATION_TSA
+	bool "Mitigate Transient Scheduler Attacks"
+	depends on CPU_SUP_AMD
+	default y
+	help
+	  Enable mitigation for Transient Scheduler Attacks. TSA is a hardware
+	  security vulnerability on AMD CPUs which can lead to forwarding of
+	  invalid info to subsequent instructions and thus can affect their
+	  timing and thereby cause a leakage.
 endif
 
 config ARCH_HAS_ADD_PAGES
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index ee176236c2be..286d509f9363 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -456,6 +456,7 @@
 #define X86_FEATURE_NO_NESTED_DATA_BP	(20*32+ 0) /* No Nested Data Breakpoints */
 #define X86_FEATURE_WRMSR_XX_BASE_NS	(20*32+ 1) /* WRMSR to {FS,GS,KERNEL_GS}_BASE is non-serializing */
 #define X86_FEATURE_LFENCE_RDTSC	(20*32+ 2) /* LFENCE always serializing / synchronizes RDTSC */
+#define X86_FEATURE_VERW_CLEAR		(20*32+ 5) /* The memory form of VERW mitigates TSA */
 #define X86_FEATURE_NULL_SEL_CLR_BASE	(20*32+ 6) /* Null Selector Clears Base */
 #define X86_FEATURE_AUTOIBRS		(20*32+ 8) /* Automatic IBRS */
 #define X86_FEATURE_NO_SMM_CTL_MSR	(20*32+ 9) /* SMM_CTL MSR is not present */
@@ -487,6 +488,9 @@
 #define X86_FEATURE_PREFER_YMM		(21*32+ 8) /* Avoid ZMM registers due to downclocking */
 #define X86_FEATURE_APX			(21*32+ 9) /* Advanced Performance Extensions */
 #define X86_FEATURE_INDIRECT_THUNK_ITS	(21*32+10) /* Use thunk for indirect branches in lower half of cacheline */
+#define X86_FEATURE_TSA_SQ_NO		(21*32+11) /* AMD CPU not vulnerable to TSA-SQ */
+#define X86_FEATURE_TSA_L1_NO		(21*32+12) /* AMD CPU not vulnerable to TSA-L1 */
+#define X86_FEATURE_CLEAR_CPU_BUF_VM	(21*32+13) /* Clear CPU buffers using VERW before VMRUN */
 
 /*
  * BUG word(s)
@@ -542,5 +546,5 @@
 #define X86_BUG_OLD_MICROCODE		X86_BUG( 1*32+ 6) /* "old_microcode" CPU has old microcode, it is surely vulnerable to something */
 #define X86_BUG_ITS			X86_BUG( 1*32+ 7) /* "its" CPU is affected by Indirect Target Selection */
 #define X86_BUG_ITS_NATIVE_ONLY		X86_BUG( 1*32+ 8) /* "its_native_only" CPU is affected by ITS, VMX is not affected */
-
+#define X86_BUG_TSA			X86_BUG( 1*32+ 9) /* "tsa" CPU is affected by Transient Scheduler Attacks */
 #endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/arch/x86/include/asm/mwait.h b/arch/x86/include/asm/mwait.h
index cc34c3fd197b..82bd9eb73b3c 100644
--- a/arch/x86/include/asm/mwait.h
+++ b/arch/x86/include/asm/mwait.h
@@ -80,7 +80,7 @@ static __always_inline void __mwait(u32 eax, u32 ecx)
  */
 static __always_inline void __mwaitx(u32 eax, u32 ebx, u32 ecx)
 {
-	/* No MDS buffer clear as this is AMD/HYGON only */
+	/* No need for TSA buffer clearing on AMD */
 
 	/* "mwaitx %eax, %ebx, %ecx" */
 	asm volatile(".byte 0x0f, 0x01, 0xfb"
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index 5dcd75bb5e0d..10f261678749 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -308,19 +308,25 @@
  * CFLAGS.ZF.
  * Note: Only the memory operand variant of VERW clears the CPU buffers.
  */
-.macro CLEAR_CPU_BUFFERS
+.macro __CLEAR_CPU_BUFFERS feature
 #ifdef CONFIG_X86_64
-	ALTERNATIVE "", "verw x86_verw_sel(%rip)", X86_FEATURE_CLEAR_CPU_BUF
+	ALTERNATIVE "", "verw x86_verw_sel(%rip)", \feature
 #else
 	/*
 	 * In 32bit mode, the memory operand must be a %cs reference. The data
 	 * segments may not be usable (vm86 mode), and the stack segment may not
 	 * be flat (ESPFIX32).
 	 */
-	ALTERNATIVE "", "verw %cs:x86_verw_sel", X86_FEATURE_CLEAR_CPU_BUF
+	ALTERNATIVE "", "verw %cs:x86_verw_sel", \feature
 #endif
 .endm
 
+#define CLEAR_CPU_BUFFERS \
+	__CLEAR_CPU_BUFFERS X86_FEATURE_CLEAR_CPU_BUF
+
+#define VM_CLEAR_CPU_BUFFERS \
+	__CLEAR_CPU_BUFFERS X86_FEATURE_CLEAR_CPU_BUF_VM
+
 #ifdef CONFIG_X86_64
 .macro CLEAR_BRANCH_HISTORY
 	ALTERNATIVE "", "call clear_bhb_loop", X86_FEATURE_CLEAR_BHB_LOOP
@@ -602,7 +608,7 @@ static __always_inline void x86_clear_cpu_buffers(void)
 
 /**
  * x86_idle_clear_cpu_buffers - Buffer clearing support in idle for the MDS
- * vulnerability
+ * and TSA vulnerabilities.
  *
  * Clear CPU buffers if the corresponding static key is enabled
  */
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 93da466dfe2c..23c535871a7e 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -377,6 +377,47 @@ static void bsp_determine_snp(struct cpuinfo_x86 *c)
 #endif
 }
 
+#define ZEN_MODEL_STEP_UCODE(fam, model, step, ucode) \
+	X86_MATCH_VFM_STEPS(VFM_MAKE(X86_VENDOR_AMD, fam, model), \
+			    step, step, ucode)
+
+static const struct x86_cpu_id amd_tsa_microcode[] = {
+	ZEN_MODEL_STEP_UCODE(0x19, 0x01, 0x1, 0x0a0011d7),
+	ZEN_MODEL_STEP_UCODE(0x19, 0x01, 0x2, 0x0a00123b),
+	ZEN_MODEL_STEP_UCODE(0x19, 0x08, 0x2, 0x0a00820d),
+	ZEN_MODEL_STEP_UCODE(0x19, 0x11, 0x1, 0x0a10114c),
+	ZEN_MODEL_STEP_UCODE(0x19, 0x11, 0x2, 0x0a10124c),
+	ZEN_MODEL_STEP_UCODE(0x19, 0x18, 0x1, 0x0a108109),
+	ZEN_MODEL_STEP_UCODE(0x19, 0x21, 0x0, 0x0a20102e),
+	ZEN_MODEL_STEP_UCODE(0x19, 0x21, 0x2, 0x0a201211),
+	ZEN_MODEL_STEP_UCODE(0x19, 0x44, 0x1, 0x0a404108),
+	ZEN_MODEL_STEP_UCODE(0x19, 0x50, 0x0, 0x0a500012),
+	ZEN_MODEL_STEP_UCODE(0x19, 0x61, 0x2, 0x0a60120a),
+	ZEN_MODEL_STEP_UCODE(0x19, 0x74, 0x1, 0x0a704108),
+	ZEN_MODEL_STEP_UCODE(0x19, 0x75, 0x2, 0x0a705208),
+	ZEN_MODEL_STEP_UCODE(0x19, 0x78, 0x0, 0x0a708008),
+	ZEN_MODEL_STEP_UCODE(0x19, 0x7c, 0x0, 0x0a70c008),
+	ZEN_MODEL_STEP_UCODE(0x19, 0xa0, 0x2, 0x0aa00216),
+	{},
+};
+
+static void tsa_init(struct cpuinfo_x86 *c)
+{
+	if (cpu_has(c, X86_FEATURE_HYPERVISOR))
+		return;
+
+	if (cpu_has(c, X86_FEATURE_ZEN3) ||
+	    cpu_has(c, X86_FEATURE_ZEN4)) {
+		if (x86_match_min_microcode_rev(amd_tsa_microcode))
+			setup_force_cpu_cap(X86_FEATURE_VERW_CLEAR);
+		else
+			pr_debug("%s: current revision: 0x%x\n", __func__, c->microcode);
+	} else {
+		setup_force_cpu_cap(X86_FEATURE_TSA_SQ_NO);
+		setup_force_cpu_cap(X86_FEATURE_TSA_L1_NO);
+	}
+}
+
 static void bsp_init_amd(struct cpuinfo_x86 *c)
 {
 	if (cpu_has(c, X86_FEATURE_CONSTANT_TSC)) {
@@ -489,6 +530,9 @@ static void bsp_init_amd(struct cpuinfo_x86 *c)
 	}
 
 	bsp_determine_snp(c);
+
+	tsa_init(c);
+
 	return;
 
 warn:
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 258ed3d2b6a9..f4d3abb12317 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -94,6 +94,8 @@ static void __init bhi_apply_mitigation(void);
 static void __init its_select_mitigation(void);
 static void __init its_update_mitigation(void);
 static void __init its_apply_mitigation(void);
+static void __init tsa_select_mitigation(void);
+static void __init tsa_apply_mitigation(void);
 
 /* The base value of the SPEC_CTRL MSR without task-specific bits set */
 u64 x86_spec_ctrl_base;
@@ -225,6 +227,7 @@ void __init cpu_select_mitigations(void)
 	gds_select_mitigation();
 	its_select_mitigation();
 	bhi_select_mitigation();
+	tsa_select_mitigation();
 
 	/*
 	 * After mitigations are selected, some may need to update their
@@ -272,6 +275,7 @@ void __init cpu_select_mitigations(void)
 	gds_apply_mitigation();
 	its_apply_mitigation();
 	bhi_apply_mitigation();
+	tsa_apply_mitigation();
 }
 
 /*
@@ -1487,6 +1491,94 @@ static void __init its_apply_mitigation(void)
 	set_return_thunk(its_return_thunk);
 }
 
+#undef pr_fmt
+#define pr_fmt(fmt)	"Transient Scheduler Attacks: " fmt
+
+enum tsa_mitigations {
+	TSA_MITIGATION_NONE,
+	TSA_MITIGATION_AUTO,
+	TSA_MITIGATION_UCODE_NEEDED,
+	TSA_MITIGATION_USER_KERNEL,
+	TSA_MITIGATION_VM,
+	TSA_MITIGATION_FULL,
+};
+
+static const char * const tsa_strings[] = {
+	[TSA_MITIGATION_NONE]		= "Vulnerable",
+	[TSA_MITIGATION_UCODE_NEEDED]	= "Vulnerable: No microcode",
+	[TSA_MITIGATION_USER_KERNEL]	= "Mitigation: Clear CPU buffers: user/kernel boundary",
+	[TSA_MITIGATION_VM]		= "Mitigation: Clear CPU buffers: VM",
+	[TSA_MITIGATION_FULL]		= "Mitigation: Clear CPU buffers",
+};
+
+static enum tsa_mitigations tsa_mitigation __ro_after_init =
+	IS_ENABLED(CONFIG_MITIGATION_TSA) ? TSA_MITIGATION_AUTO : TSA_MITIGATION_NONE;
+
+static int __init tsa_parse_cmdline(char *str)
+{
+	if (!str)
+		return -EINVAL;
+
+	if (!strcmp(str, "off"))
+		tsa_mitigation = TSA_MITIGATION_NONE;
+	else if (!strcmp(str, "on"))
+		tsa_mitigation = TSA_MITIGATION_FULL;
+	else if (!strcmp(str, "user"))
+		tsa_mitigation = TSA_MITIGATION_USER_KERNEL;
+	else if (!strcmp(str, "vm"))
+		tsa_mitigation = TSA_MITIGATION_VM;
+	else
+		pr_err("Ignoring unknown tsa=%s option.\n", str);
+
+	return 0;
+}
+early_param("tsa", tsa_parse_cmdline);
+
+static void __init tsa_select_mitigation(void)
+{
+	if (cpu_mitigations_off() || !boot_cpu_has_bug(X86_BUG_TSA)) {
+		tsa_mitigation = TSA_MITIGATION_NONE;
+		return;
+	}
+
+	if (tsa_mitigation == TSA_MITIGATION_NONE)
+		return;
+
+	if (!boot_cpu_has(X86_FEATURE_VERW_CLEAR)) {
+		tsa_mitigation = TSA_MITIGATION_UCODE_NEEDED;
+		goto out;
+	}
+
+	if (tsa_mitigation == TSA_MITIGATION_AUTO)
+		tsa_mitigation = TSA_MITIGATION_FULL;
+
+	/*
+	 * No need to set verw_clear_cpu_buf_mitigation_selected - it
+	 * doesn't fit all cases here and it is not needed because this
+	 * is the only VERW-based mitigation on AMD.
+	 */
+out:
+	pr_info("%s\n", tsa_strings[tsa_mitigation]);
+}
+
+static void __init tsa_apply_mitigation(void)
+{
+	switch (tsa_mitigation) {
+	case TSA_MITIGATION_USER_KERNEL:
+		setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF);
+		break;
+	case TSA_MITIGATION_VM:
+		setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF_VM);
+		break;
+	case TSA_MITIGATION_FULL:
+		setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF);
+		setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF_VM);
+		break;
+	default:
+		break;
+	}
+}
+
 #undef pr_fmt
 #define pr_fmt(fmt)     "Spectre V2 : " fmt
 
@@ -2316,6 +2408,25 @@ void cpu_bugs_smt_update(void)
 		break;
 	}
 
+	switch (tsa_mitigation) {
+	case TSA_MITIGATION_USER_KERNEL:
+	case TSA_MITIGATION_VM:
+	case TSA_MITIGATION_AUTO:
+	case TSA_MITIGATION_FULL:
+		/*
+		 * TSA-SQ can potentially lead to info leakage between
+		 * SMT threads.
+		 */
+		if (sched_smt_active())
+			static_branch_enable(&cpu_buf_idle_clear);
+		else
+			static_branch_disable(&cpu_buf_idle_clear);
+		break;
+	case TSA_MITIGATION_NONE:
+	case TSA_MITIGATION_UCODE_NEEDED:
+		break;
+	}
+
 	mutex_unlock(&spec_ctrl_mutex);
 }
 
@@ -3265,6 +3376,11 @@ static ssize_t gds_show_state(char *buf)
 	return sysfs_emit(buf, "%s\n", gds_strings[gds_mitigation]);
 }
 
+static ssize_t tsa_show_state(char *buf)
+{
+	return sysfs_emit(buf, "%s\n", tsa_strings[tsa_mitigation]);
+}
+
 static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr,
 			       char *buf, unsigned int bug)
 {
@@ -3328,6 +3444,9 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr
 	case X86_BUG_ITS:
 		return its_show_state(buf);
 
+	case X86_BUG_TSA:
+		return tsa_show_state(buf);
+
 	default:
 		break;
 	}
@@ -3414,6 +3533,11 @@ ssize_t cpu_show_indirect_target_selection(struct device *dev, struct device_att
 {
 	return cpu_show_common(dev, attr, buf, X86_BUG_ITS);
 }
+
+ssize_t cpu_show_tsa(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	return cpu_show_common(dev, attr, buf, X86_BUG_TSA);
+}
 #endif
 
 void __warn_thunk(void)
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 8feb8fd2957a..f7b9fca82bda 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1233,6 +1233,8 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = {
 #define ITS		BIT(8)
 /* CPU is affected by Indirect Target Selection, but guest-host isolation is not affected */
 #define ITS_NATIVE_ONLY	BIT(9)
+/* CPU is affected by Transient Scheduler Attacks */
+#define TSA		BIT(10)
 
 static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = {
 	VULNBL_INTEL_STEPS(INTEL_IVYBRIDGE,	     X86_STEP_MAX,	SRBDS),
@@ -1280,7 +1282,7 @@ static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = {
 	VULNBL_AMD(0x16, RETBLEED),
 	VULNBL_AMD(0x17, RETBLEED | SMT_RSB | SRSO),
 	VULNBL_HYGON(0x18, RETBLEED | SMT_RSB | SRSO),
-	VULNBL_AMD(0x19, SRSO),
+	VULNBL_AMD(0x19, SRSO | TSA),
 	VULNBL_AMD(0x1a, SRSO),
 	{}
 };
@@ -1530,6 +1532,16 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
 			setup_force_cpu_bug(X86_BUG_ITS_NATIVE_ONLY);
 	}
 
+	if (c->x86_vendor == X86_VENDOR_AMD) {
+		if (!cpu_has(c, X86_FEATURE_TSA_SQ_NO) ||
+		    !cpu_has(c, X86_FEATURE_TSA_L1_NO)) {
+			if (cpu_matches(cpu_vuln_blacklist, TSA) ||
+			    /* Enable bug on Zen guests to allow for live migration. */
+			    (cpu_has(c, X86_FEATURE_HYPERVISOR) && cpu_has(c, X86_FEATURE_ZEN)))
+				setup_force_cpu_bug(X86_BUG_TSA);
+		}
+	}
+
 	if (cpu_matches(cpu_vuln_whitelist, NO_MELTDOWN))
 		return;
 
diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c
index dbf6d71bdf18..b4a1f6732a3a 100644
--- a/arch/x86/kernel/cpu/scattered.c
+++ b/arch/x86/kernel/cpu/scattered.c
@@ -50,6 +50,8 @@ static const struct cpuid_bit cpuid_bits[] = {
 	{ X86_FEATURE_MBA,			CPUID_EBX,  6, 0x80000008, 0 },
 	{ X86_FEATURE_SMBA,			CPUID_EBX,  2, 0x80000020, 0 },
 	{ X86_FEATURE_BMEC,			CPUID_EBX,  3, 0x80000020, 0 },
+	{ X86_FEATURE_TSA_SQ_NO,		CPUID_ECX,  1, 0x80000021, 0 },
+	{ X86_FEATURE_TSA_L1_NO,		CPUID_ECX,  2, 0x80000021, 0 },
 	{ X86_FEATURE_AMD_WORKLOAD_CLASS,	CPUID_EAX, 22, 0x80000021, 0 },
 	{ X86_FEATURE_PERFMON_V2,		CPUID_EAX,  0, 0x80000022, 0 },
 	{ X86_FEATURE_AMD_LBR_V2,		CPUID_EAX,  1, 0x80000022, 0 },
diff --git a/arch/x86/kvm/svm/vmenter.S b/arch/x86/kvm/svm/vmenter.S
index 0c61153b275f..235c4af6b692 100644
--- a/arch/x86/kvm/svm/vmenter.S
+++ b/arch/x86/kvm/svm/vmenter.S
@@ -169,6 +169,9 @@ SYM_FUNC_START(__svm_vcpu_run)
 #endif
 	mov VCPU_RDI(%_ASM_DI), %_ASM_DI
 
+	/* Clobbers EFLAGS.ZF */
+	VM_CLEAR_CPU_BUFFERS
+
 	/* Enter guest mode */
 3:	vmrun %_ASM_AX
 4:
@@ -335,6 +338,9 @@ SYM_FUNC_START(__svm_sev_es_vcpu_run)
 	mov SVM_current_vmcb(%rdi), %rax
 	mov KVM_VMCB_pa(%rax), %rax
 
+	/* Clobbers EFLAGS.ZF */
+	VM_CLEAR_CPU_BUFFERS
+
 	/* Enter guest mode */
 1:	vmrun %rax
 2:
diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c
index 7779ab0ca7ce..efc575a00edd 100644
--- a/drivers/base/cpu.c
+++ b/drivers/base/cpu.c
@@ -602,6 +602,7 @@ CPU_SHOW_VULN_FALLBACK(reg_file_data_sampling);
 CPU_SHOW_VULN_FALLBACK(ghostwrite);
 CPU_SHOW_VULN_FALLBACK(old_microcode);
 CPU_SHOW_VULN_FALLBACK(indirect_target_selection);
+CPU_SHOW_VULN_FALLBACK(tsa);
 
 static DEVICE_ATTR(meltdown, 0444, cpu_show_meltdown, NULL);
 static DEVICE_ATTR(spectre_v1, 0444, cpu_show_spectre_v1, NULL);
@@ -620,6 +621,7 @@ static DEVICE_ATTR(reg_file_data_sampling, 0444, cpu_show_reg_file_data_sampling
 static DEVICE_ATTR(ghostwrite, 0444, cpu_show_ghostwrite, NULL);
 static DEVICE_ATTR(old_microcode, 0444, cpu_show_old_microcode, NULL);
 static DEVICE_ATTR(indirect_target_selection, 0444, cpu_show_indirect_target_selection, NULL);
+static DEVICE_ATTR(tsa, 0444, cpu_show_tsa, NULL);
 
 static struct attribute *cpu_root_vulnerabilities_attrs[] = {
 	&dev_attr_meltdown.attr,
@@ -639,6 +641,7 @@ static struct attribute *cpu_root_vulnerabilities_attrs[] = {
 	&dev_attr_ghostwrite.attr,
 	&dev_attr_old_microcode.attr,
 	&dev_attr_indirect_target_selection.attr,
+	&dev_attr_tsa.attr,
 	NULL
 };
 
diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index 96a3a0d6a60e..6378370a952f 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -82,6 +82,7 @@ extern ssize_t cpu_show_old_microcode(struct device *dev,
 				      struct device_attribute *attr, char *buf);
 extern ssize_t cpu_show_indirect_target_selection(struct device *dev,
 						  struct device_attribute *attr, char *buf);
+extern ssize_t cpu_show_tsa(struct device *dev, struct device_attribute *attr, char *buf);
 
 extern __printf(4, 5)
 struct device *cpu_device_create(struct device *parent, void *drvdata,

From 31272abd5974b38ba312e9cf2ec2f09f9dd7dcba Mon Sep 17 00:00:00 2001
From: "Borislav Petkov (AMD)" <bp@alien8.de>
Date: Wed, 11 Sep 2024 11:00:50 +0200
Subject: [PATCH 0466/1334] KVM: SVM: Advertise TSA CPUID bits to guests

Synthesize the TSA CPUID feature bits for guests. Set TSA_{SQ,L1}_NO on
unaffected machines.

Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
---
 arch/x86/include/asm/kvm_host.h |  1 +
 arch/x86/kvm/cpuid.c            | 10 +++++++++-
 arch/x86/kvm/reverse_cpuid.h    |  7 +++++++
 3 files changed, 17 insertions(+), 1 deletion(-)

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index b4a391929cdb..eb559f3564c6 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -764,6 +764,7 @@ enum kvm_only_cpuid_leafs {
 	CPUID_8000_0022_EAX,
 	CPUID_7_2_EDX,
 	CPUID_24_0_EBX,
+	CPUID_8000_0021_ECX,
 	NR_KVM_CPU_CAPS,
 
 	NKVMCAPINTS = NR_KVM_CPU_CAPS - NCAPINTS,
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index b2d006756e02..f84bc0569c9c 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -1165,6 +1165,8 @@ void kvm_set_cpu_caps(void)
 		 */
 		SYNTHESIZED_F(LFENCE_RDTSC),
 		/* SmmPgCfgLock */
+		/* 4: Resv */
+		SYNTHESIZED_F(VERW_CLEAR),
 		F(NULL_SEL_CLR_BASE),
 		/* UpperAddressIgnore */
 		F(AUTOIBRS),
@@ -1179,6 +1181,11 @@ void kvm_set_cpu_caps(void)
 		F(SRSO_USER_KERNEL_NO),
 	);
 
+	kvm_cpu_cap_init(CPUID_8000_0021_ECX,
+		SYNTHESIZED_F(TSA_SQ_NO),
+		SYNTHESIZED_F(TSA_L1_NO),
+	);
+
 	kvm_cpu_cap_init(CPUID_8000_0022_EAX,
 		F(PERFMON_V2),
 	);
@@ -1748,8 +1755,9 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
 		entry->eax = entry->ebx = entry->ecx = entry->edx = 0;
 		break;
 	case 0x80000021:
-		entry->ebx = entry->ecx = entry->edx = 0;
+		entry->ebx = entry->edx = 0;
 		cpuid_entry_override(entry, CPUID_8000_0021_EAX);
+		cpuid_entry_override(entry, CPUID_8000_0021_ECX);
 		break;
 	/* AMD Extended Performance Monitoring and Debug */
 	case 0x80000022: {
diff --git a/arch/x86/kvm/reverse_cpuid.h b/arch/x86/kvm/reverse_cpuid.h
index fde0ae986003..c53b92379e6e 100644
--- a/arch/x86/kvm/reverse_cpuid.h
+++ b/arch/x86/kvm/reverse_cpuid.h
@@ -52,6 +52,10 @@
 /* CPUID level 0x80000022 (EAX) */
 #define KVM_X86_FEATURE_PERFMON_V2	KVM_X86_FEATURE(CPUID_8000_0022_EAX, 0)
 
+/* CPUID level 0x80000021 (ECX) */
+#define KVM_X86_FEATURE_TSA_SQ_NO	KVM_X86_FEATURE(CPUID_8000_0021_ECX, 1)
+#define KVM_X86_FEATURE_TSA_L1_NO	KVM_X86_FEATURE(CPUID_8000_0021_ECX, 2)
+
 struct cpuid_reg {
 	u32 function;
 	u32 index;
@@ -82,6 +86,7 @@ static const struct cpuid_reg reverse_cpuid[] = {
 	[CPUID_8000_0022_EAX] = {0x80000022, 0, CPUID_EAX},
 	[CPUID_7_2_EDX]       = {         7, 2, CPUID_EDX},
 	[CPUID_24_0_EBX]      = {      0x24, 0, CPUID_EBX},
+	[CPUID_8000_0021_ECX] = {0x80000021, 0, CPUID_ECX},
 };
 
 /*
@@ -121,6 +126,8 @@ static __always_inline u32 __feature_translate(int x86_feature)
 	KVM_X86_TRANSLATE_FEATURE(PERFMON_V2);
 	KVM_X86_TRANSLATE_FEATURE(RRSBA_CTRL);
 	KVM_X86_TRANSLATE_FEATURE(BHI_CTRL);
+	KVM_X86_TRANSLATE_FEATURE(TSA_SQ_NO);
+	KVM_X86_TRANSLATE_FEATURE(TSA_L1_NO);
 	default:
 		return x86_feature;
 	}

From 2329f250e04d3b8e78b36a68b9880ca7750a07ef Mon Sep 17 00:00:00 2001
From: "Borislav Petkov (AMD)" <bp@alien8.de>
Date: Thu, 27 Mar 2025 12:23:55 +0100
Subject: [PATCH 0467/1334] x86/microcode/AMD: Add TSA microcode SHAs

Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
---
 arch/x86/kernel/cpu/microcode/amd_shas.c | 112 +++++++++++++++++++++++
 1 file changed, 112 insertions(+)

diff --git a/arch/x86/kernel/cpu/microcode/amd_shas.c b/arch/x86/kernel/cpu/microcode/amd_shas.c
index 2a1655b1fdd8..1fd349cfc802 100644
--- a/arch/x86/kernel/cpu/microcode/amd_shas.c
+++ b/arch/x86/kernel/cpu/microcode/amd_shas.c
@@ -231,6 +231,13 @@ static const struct patch_digest phashes[] = {
 		0x0d,0x5b,0x65,0x34,0x69,0xb2,0x62,0x21,
 	}
  },
+ { 0xa0011d7, {
+                0x35,0x07,0xcd,0x40,0x94,0xbc,0x81,0x6b,
+                0xfc,0x61,0x56,0x1a,0xe2,0xdb,0x96,0x12,
+                0x1c,0x1c,0x31,0xb1,0x02,0x6f,0xe5,0xd2,
+                0xfe,0x1b,0x04,0x03,0x2c,0x8f,0x4c,0x36,
+        }
+ },
  { 0xa001223, {
 		0xfb,0x32,0x5f,0xc6,0x83,0x4f,0x8c,0xb8,
 		0xa4,0x05,0xf9,0x71,0x53,0x01,0x16,0xc4,
@@ -294,6 +301,13 @@ static const struct patch_digest phashes[] = {
 		0xc0,0xcd,0x33,0xf2,0x8d,0xf9,0xef,0x59,
 	}
  },
+ { 0xa00123b, {
+		0xef,0xa1,0x1e,0x71,0xf1,0xc3,0x2c,0xe2,
+		0xc3,0xef,0x69,0x41,0x7a,0x54,0xca,0xc3,
+		0x8f,0x62,0x84,0xee,0xc2,0x39,0xd9,0x28,
+		0x95,0xa7,0x12,0x49,0x1e,0x30,0x71,0x72,
+	}
+ },
  { 0xa00820c, {
 		0xa8,0x0c,0x81,0xc0,0xa6,0x00,0xe7,0xf3,
 		0x5f,0x65,0xd3,0xb9,0x6f,0xea,0x93,0x63,
@@ -301,6 +315,13 @@ static const struct patch_digest phashes[] = {
 		0xe1,0x3b,0x8d,0xb2,0xf8,0x22,0x03,0xe2,
 	}
  },
+ { 0xa00820d, {
+		0xf9,0x2a,0xc0,0xf4,0x9e,0xa4,0x87,0xa4,
+		0x7d,0x87,0x00,0xfd,0xab,0xda,0x19,0xca,
+		0x26,0x51,0x32,0xc1,0x57,0x91,0xdf,0xc1,
+		0x05,0xeb,0x01,0x7c,0x5a,0x95,0x21,0xb7,
+	}
+ },
  { 0xa10113e, {
 		0x05,0x3c,0x66,0xd7,0xa9,0x5a,0x33,0x10,
 		0x1b,0xf8,0x9c,0x8f,0xed,0xfc,0xa7,0xa0,
@@ -322,6 +343,13 @@ static const struct patch_digest phashes[] = {
 		0xf1,0x5e,0xb0,0xde,0xb4,0x98,0xae,0xc4,
 	}
  },
+ { 0xa10114c, {
+		0x9e,0xb6,0xa2,0xd9,0x87,0x38,0xc5,0x64,
+		0xd8,0x88,0xfa,0x78,0x98,0xf9,0x6f,0x74,
+		0x39,0x90,0x1b,0xa5,0xcf,0x5e,0xb4,0x2a,
+		0x02,0xff,0xd4,0x8c,0x71,0x8b,0xe2,0xc0,
+	}
+ },
  { 0xa10123e, {
 		0x03,0xb9,0x2c,0x76,0x48,0x93,0xc9,0x18,
 		0xfb,0x56,0xfd,0xf7,0xe2,0x1d,0xca,0x4d,
@@ -343,6 +371,13 @@ static const struct patch_digest phashes[] = {
 		0x1b,0x7d,0x64,0x9d,0x4b,0x53,0x13,0x75,
 	}
  },
+ { 0xa10124c, {
+		0x29,0xea,0xf1,0x2c,0xb2,0xe4,0xef,0x90,
+		0xa4,0xcd,0x1d,0x86,0x97,0x17,0x61,0x46,
+		0xfc,0x22,0xcb,0x57,0x75,0x19,0xc8,0xcc,
+		0x0c,0xf5,0xbc,0xac,0x81,0x9d,0x9a,0xd2,
+	}
+ },
  { 0xa108108, {
 		0xed,0xc2,0xec,0xa1,0x15,0xc6,0x65,0xe9,
 		0xd0,0xef,0x39,0xaa,0x7f,0x55,0x06,0xc6,
@@ -350,6 +385,13 @@ static const struct patch_digest phashes[] = {
 		0x28,0x1e,0x9c,0x59,0x69,0x99,0x4d,0x16,
 	}
  },
+ { 0xa108109, {
+		0x85,0xb4,0xbd,0x7c,0x49,0xa7,0xbd,0xfa,
+		0x49,0x36,0x80,0x81,0xc5,0xb7,0x39,0x1b,
+		0x9a,0xaa,0x50,0xde,0x9b,0xe9,0x32,0x35,
+		0x42,0x7e,0x51,0x4f,0x52,0x2c,0x28,0x59,
+	}
+ },
  { 0xa20102d, {
 		0xf9,0x6e,0xf2,0x32,0xd3,0x0f,0x5f,0x11,
 		0x59,0xa1,0xfe,0xcc,0xcd,0x9b,0x42,0x89,
@@ -357,6 +399,13 @@ static const struct patch_digest phashes[] = {
 		0x8c,0xe9,0x19,0x3e,0xcc,0x3f,0x7b,0xb4,
 	}
  },
+ { 0xa20102e, {
+		0xbe,0x1f,0x32,0x04,0x0d,0x3c,0x9c,0xdd,
+		0xe1,0xa4,0xbf,0x76,0x3a,0xec,0xc2,0xf6,
+		0x11,0x00,0xa7,0xaf,0x0f,0xe5,0x02,0xc5,
+		0x54,0x3a,0x1f,0x8c,0x16,0xb5,0xff,0xbe,
+	}
+ },
  { 0xa201210, {
 		0xe8,0x6d,0x51,0x6a,0x8e,0x72,0xf3,0xfe,
 		0x6e,0x16,0xbc,0x62,0x59,0x40,0x17,0xe9,
@@ -364,6 +413,13 @@ static const struct patch_digest phashes[] = {
 		0xf7,0x55,0xf0,0x13,0xbb,0x22,0xf6,0x41,
 	}
  },
+ { 0xa201211, {
+		0x69,0xa1,0x17,0xec,0xd0,0xf6,0x6c,0x95,
+		0xe2,0x1e,0xc5,0x59,0x1a,0x52,0x0a,0x27,
+		0xc4,0xed,0xd5,0x59,0x1f,0xbf,0x00,0xff,
+		0x08,0x88,0xb5,0xe1,0x12,0xb6,0xcc,0x27,
+	}
+ },
  { 0xa404107, {
 		0xbb,0x04,0x4e,0x47,0xdd,0x5e,0x26,0x45,
 		0x1a,0xc9,0x56,0x24,0xa4,0x4c,0x82,0xb0,
@@ -371,6 +427,13 @@ static const struct patch_digest phashes[] = {
 		0x13,0xbc,0xc5,0x25,0xe4,0xc5,0xc3,0x99,
 	}
  },
+ { 0xa404108, {
+		0x69,0x67,0x43,0x06,0xf8,0x0c,0x62,0xdc,
+		0xa4,0x21,0x30,0x4f,0x0f,0x21,0x2c,0xcb,
+		0xcc,0x37,0xf1,0x1c,0xc3,0xf8,0x2f,0x19,
+		0xdf,0x53,0x53,0x46,0xb1,0x15,0xea,0x00,
+	}
+ },
  { 0xa500011, {
 		0x23,0x3d,0x70,0x7d,0x03,0xc3,0xc4,0xf4,
 		0x2b,0x82,0xc6,0x05,0xda,0x80,0x0a,0xf1,
@@ -378,6 +441,13 @@ static const struct patch_digest phashes[] = {
 		0x11,0x5e,0x96,0x7e,0x71,0xe9,0xfc,0x74,
 	}
  },
+ { 0xa500012, {
+		0xeb,0x74,0x0d,0x47,0xa1,0x8e,0x09,0xe4,
+		0x93,0x4c,0xad,0x03,0x32,0x4c,0x38,0x16,
+		0x10,0x39,0xdd,0x06,0xaa,0xce,0xd6,0x0f,
+		0x62,0x83,0x9d,0x8e,0x64,0x55,0xbe,0x63,
+	}
+ },
  { 0xa601209, {
 		0x66,0x48,0xd4,0x09,0x05,0xcb,0x29,0x32,
 		0x66,0xb7,0x9a,0x76,0xcd,0x11,0xf3,0x30,
@@ -385,6 +455,13 @@ static const struct patch_digest phashes[] = {
 		0xe8,0x73,0xe2,0xd6,0xdb,0xd2,0x77,0x1d,
 	}
  },
+ { 0xa60120a, {
+		0x0c,0x8b,0x3d,0xfd,0x52,0x52,0x85,0x7d,
+		0x20,0x3a,0xe1,0x7e,0xa4,0x21,0x3b,0x7b,
+		0x17,0x86,0xae,0xac,0x13,0xb8,0x63,0x9d,
+		0x06,0x01,0xd0,0xa0,0x51,0x9a,0x91,0x2c,
+	}
+ },
  { 0xa704107, {
 		0xf3,0xc6,0x58,0x26,0xee,0xac,0x3f,0xd6,
 		0xce,0xa1,0x72,0x47,0x3b,0xba,0x2b,0x93,
@@ -392,6 +469,13 @@ static const struct patch_digest phashes[] = {
 		0x64,0x39,0x71,0x8c,0xce,0xe7,0x41,0x39,
 	}
  },
+ { 0xa704108, {
+		0xd7,0x55,0x15,0x2b,0xfe,0xc4,0xbc,0x93,
+		0xec,0x91,0xa0,0xae,0x45,0xb7,0xc3,0x98,
+		0x4e,0xff,0x61,0x77,0x88,0xc2,0x70,0x49,
+		0xe0,0x3a,0x1d,0x84,0x38,0x52,0xbf,0x5a,
+	}
+ },
  { 0xa705206, {
 		0x8d,0xc0,0x76,0xbd,0x58,0x9f,0x8f,0xa4,
 		0x12,0x9d,0x21,0xfb,0x48,0x21,0xbc,0xe7,
@@ -399,6 +483,13 @@ static const struct patch_digest phashes[] = {
 		0x03,0x35,0xe9,0xbe,0xfb,0x06,0xdf,0xfc,
 	}
  },
+ { 0xa705208, {
+		0x30,0x1d,0x55,0x24,0xbc,0x6b,0x5a,0x19,
+		0x0c,0x7d,0x1d,0x74,0xaa,0xd1,0xeb,0xd2,
+		0x16,0x62,0xf7,0x5b,0xe1,0x1f,0x18,0x11,
+		0x5c,0xf0,0x94,0x90,0x26,0xec,0x69,0xff,
+	}
+ },
  { 0xa708007, {
 		0x6b,0x76,0xcc,0x78,0xc5,0x8a,0xa3,0xe3,
 		0x32,0x2d,0x79,0xe4,0xc3,0x80,0xdb,0xb2,
@@ -406,6 +497,13 @@ static const struct patch_digest phashes[] = {
 		0xdf,0x92,0x73,0x84,0x87,0x3c,0x73,0x93,
 	}
  },
+ { 0xa708008, {
+		0x08,0x6e,0xf0,0x22,0x4b,0x8e,0xc4,0x46,
+		0x58,0x34,0xe6,0x47,0xa2,0x28,0xfd,0xab,
+		0x22,0x3d,0xdd,0xd8,0x52,0x9e,0x1d,0x16,
+		0xfa,0x01,0x68,0x14,0x79,0x3e,0xe8,0x6b,
+	}
+ },
  { 0xa70c005, {
 		0x88,0x5d,0xfb,0x79,0x64,0xd8,0x46,0x3b,
 		0x4a,0x83,0x8e,0x77,0x7e,0xcf,0xb3,0x0f,
@@ -413,6 +511,13 @@ static const struct patch_digest phashes[] = {
 		0xee,0x49,0xac,0xe1,0x8b,0x13,0xc5,0x13,
 	}
  },
+ { 0xa70c008, {
+		0x0f,0xdb,0x37,0xa1,0x10,0xaf,0xd4,0x21,
+		0x94,0x0d,0xa4,0xa2,0xe9,0x86,0x6c,0x0e,
+		0x85,0x7c,0x36,0x30,0xa3,0x3a,0x78,0x66,
+		0x18,0x10,0x60,0x0d,0x78,0x3d,0x44,0xd0,
+	}
+ },
  { 0xaa00116, {
 		0xe8,0x4c,0x2c,0x88,0xa1,0xac,0x24,0x63,
 		0x65,0xe5,0xaa,0x2d,0x16,0xa9,0xc3,0xf5,
@@ -441,4 +546,11 @@ static const struct patch_digest phashes[] = {
 		0x68,0x2f,0x46,0xee,0xfe,0xc6,0x6d,0xef,
 	}
  },
+ { 0xaa00216, {
+		0x79,0xfb,0x5b,0x9f,0xb6,0xe6,0xa8,0xf5,
+		0x4e,0x7c,0x4f,0x8e,0x1d,0xad,0xd0,0x08,
+		0xc2,0x43,0x7c,0x8b,0xe6,0xdb,0xd0,0xd2,
+		0xe8,0x39,0x26,0xc1,0xe5,0x5a,0x48,0xf1,
+	}
+ },
 };

From 8e786a85c0a3c0fffae6244733fb576eeabd9dec Mon Sep 17 00:00:00 2001
From: "Borislav Petkov (AMD)" <bp@alien8.de>
Date: Mon, 14 Apr 2025 15:33:19 +0200
Subject: [PATCH 0468/1334] x86/process: Move the buffer clearing before
 MONITOR

Move the VERW clearing before the MONITOR so that VERW doesn't disarm it
and the machine never enters C1.

Original idea by Kim Phillips <kim.phillips@amd.com>.

Suggested-by: Andrew Cooper <andrew.cooper3@citrix.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
---
 arch/x86/include/asm/mwait.h | 25 +++++++++++++++----------
 arch/x86/kernel/process.c    | 16 ++++++++++++----
 2 files changed, 27 insertions(+), 14 deletions(-)

diff --git a/arch/x86/include/asm/mwait.h b/arch/x86/include/asm/mwait.h
index 82bd9eb73b3c..6ca6516c7492 100644
--- a/arch/x86/include/asm/mwait.h
+++ b/arch/x86/include/asm/mwait.h
@@ -43,8 +43,6 @@ static __always_inline void __monitorx(const void *eax, u32 ecx, u32 edx)
 
 static __always_inline void __mwait(u32 eax, u32 ecx)
 {
-	x86_idle_clear_cpu_buffers();
-
 	/*
 	 * Use the instruction mnemonic with implicit operands, as the LLVM
 	 * assembler fails to assemble the mnemonic with explicit operands:
@@ -98,7 +96,6 @@ static __always_inline void __mwaitx(u32 eax, u32 ebx, u32 ecx)
  */
 static __always_inline void __sti_mwait(u32 eax, u32 ecx)
 {
-	x86_idle_clear_cpu_buffers();
 
 	asm volatile("sti; mwait" :: "a" (eax), "c" (ecx));
 }
@@ -115,21 +112,29 @@ static __always_inline void __sti_mwait(u32 eax, u32 ecx)
  */
 static __always_inline void mwait_idle_with_hints(u32 eax, u32 ecx)
 {
+	if (need_resched())
+		return;
+
+	x86_idle_clear_cpu_buffers();
+
 	if (static_cpu_has_bug(X86_BUG_MONITOR) || !current_set_polling_and_test()) {
 		const void *addr = &current_thread_info()->flags;
 
 		alternative_input("", "clflush (%[addr])", X86_BUG_CLFLUSH_MONITOR, [addr] "a" (addr));
 		__monitor(addr, 0, 0);
 
-		if (!need_resched()) {
-			if (ecx & 1) {
-				__mwait(eax, ecx);
-			} else {
-				__sti_mwait(eax, ecx);
-				raw_local_irq_disable();
-			}
+		if (need_resched())
+			goto out;
+
+		if (ecx & 1) {
+			__mwait(eax, ecx);
+		} else {
+			__sti_mwait(eax, ecx);
+			raw_local_irq_disable();
 		}
 	}
+
+out:
 	current_clr_polling();
 }
 
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 704883c21f3a..a838be04f874 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -907,16 +907,24 @@ static __init bool prefer_mwait_c1_over_halt(void)
  */
 static __cpuidle void mwait_idle(void)
 {
+	if (need_resched())
+		return;
+
+	x86_idle_clear_cpu_buffers();
+
 	if (!current_set_polling_and_test()) {
 		const void *addr = &current_thread_info()->flags;
 
 		alternative_input("", "clflush (%[addr])", X86_BUG_CLFLUSH_MONITOR, [addr] "a" (addr));
 		__monitor(addr, 0, 0);
-		if (!need_resched()) {
-			__sti_mwait(0, 0);
-			raw_local_irq_disable();
-		}
+		if (need_resched())
+			goto out;
+
+		__sti_mwait(0, 0);
+		raw_local_irq_disable();
 	}
+
+out:
 	__current_clr_polling();
 }
 

From a766cfbbeb3a74397965a8fa2e9a402026d3e1d8 Mon Sep 17 00:00:00 2001
From: Song Liu <song@kernel.org>
Date: Thu, 12 Jun 2025 22:28:56 -0700
Subject: [PATCH 0469/1334] bpf: Mark dentry->d_inode as trusted_or_null

LSM hooks such as security_path_mknod() and security_inode_rename() have
access to newly allocated negative dentry, which has NULL d_inode.
Therefore, it is necessary to do the NULL pointer check for d_inode.

Also add selftests that checks the verifier enforces the NULL pointer
check.

Signed-off-by: Song Liu <song@kernel.org>
Reviewed-by: Matt Bobrowski <mattbobrowski@google.com>
Link: https://lore.kernel.org/r/20250613052857.1992233-1-song@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/verifier.c                          |  5 ++---
 .../selftests/bpf/progs/verifier_vfs_accept.c  | 18 ++++++++++++++++++
 .../selftests/bpf/progs/verifier_vfs_reject.c  | 15 +++++++++++++++
 3 files changed, 35 insertions(+), 3 deletions(-)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index a7d6e0c5928b..169845710c7e 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -7027,8 +7027,7 @@ BTF_TYPE_SAFE_TRUSTED(struct file) {
 	struct inode *f_inode;
 };
 
-BTF_TYPE_SAFE_TRUSTED(struct dentry) {
-	/* no negative dentry-s in places where bpf can see it */
+BTF_TYPE_SAFE_TRUSTED_OR_NULL(struct dentry) {
 	struct inode *d_inode;
 };
 
@@ -7066,7 +7065,6 @@ static bool type_is_trusted(struct bpf_verifier_env *env,
 	BTF_TYPE_EMIT(BTF_TYPE_SAFE_TRUSTED(struct bpf_iter__task));
 	BTF_TYPE_EMIT(BTF_TYPE_SAFE_TRUSTED(struct linux_binprm));
 	BTF_TYPE_EMIT(BTF_TYPE_SAFE_TRUSTED(struct file));
-	BTF_TYPE_EMIT(BTF_TYPE_SAFE_TRUSTED(struct dentry));
 
 	return btf_nested_type_is_trusted(&env->log, reg, field_name, btf_id, "__safe_trusted");
 }
@@ -7076,6 +7074,7 @@ static bool type_is_trusted_or_null(struct bpf_verifier_env *env,
 				    const char *field_name, u32 btf_id)
 {
 	BTF_TYPE_EMIT(BTF_TYPE_SAFE_TRUSTED_OR_NULL(struct socket));
+	BTF_TYPE_EMIT(BTF_TYPE_SAFE_TRUSTED_OR_NULL(struct dentry));
 
 	return btf_nested_type_is_trusted(&env->log, reg, field_name, btf_id,
 					  "__safe_trusted_or_null");
diff --git a/tools/testing/selftests/bpf/progs/verifier_vfs_accept.c b/tools/testing/selftests/bpf/progs/verifier_vfs_accept.c
index a7c0a553aa50..3e2d76ee8050 100644
--- a/tools/testing/selftests/bpf/progs/verifier_vfs_accept.c
+++ b/tools/testing/selftests/bpf/progs/verifier_vfs_accept.c
@@ -2,6 +2,7 @@
 /* Copyright (c) 2024 Google LLC. */
 
 #include <vmlinux.h>
+#include <errno.h>
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
 
@@ -82,4 +83,21 @@ int BPF_PROG(path_d_path_from_file_argument, struct file *file)
 	return 0;
 }
 
+SEC("lsm.s/inode_rename")
+__success
+int BPF_PROG(inode_rename, struct inode *old_dir, struct dentry *old_dentry,
+	     struct inode *new_dir, struct dentry *new_dentry,
+	     unsigned int flags)
+{
+	struct inode *inode = new_dentry->d_inode;
+	ino_t ino;
+
+	if (!inode)
+		return 0;
+	ino = inode->i_ino;
+	if (ino == 0)
+		return -EACCES;
+	return 0;
+}
+
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_vfs_reject.c b/tools/testing/selftests/bpf/progs/verifier_vfs_reject.c
index d6d3f4fcb24c..4b392c6c8fc4 100644
--- a/tools/testing/selftests/bpf/progs/verifier_vfs_reject.c
+++ b/tools/testing/selftests/bpf/progs/verifier_vfs_reject.c
@@ -2,6 +2,7 @@
 /* Copyright (c) 2024 Google LLC. */
 
 #include <vmlinux.h>
+#include <errno.h>
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
 #include <linux/limits.h>
@@ -158,4 +159,18 @@ int BPF_PROG(path_d_path_kfunc_non_lsm, struct path *path, struct file *f)
 	return 0;
 }
 
+SEC("lsm.s/inode_rename")
+__failure __msg("invalid mem access 'trusted_ptr_or_null_'")
+int BPF_PROG(inode_rename, struct inode *old_dir, struct dentry *old_dentry,
+	     struct inode *new_dir, struct dentry *new_dentry,
+	     unsigned int flags)
+{
+	struct inode *inode = new_dentry->d_inode;
+	ino_t ino;
+
+	ino = inode->i_ino;
+	if (ino == 0)
+		return -EACCES;
+	return 0;
+}
 char _license[] SEC("license") = "GPL";

From e1f0e1a45a40f45ed615abf938cbdfeb7793a9ee Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Tue, 17 Jun 2025 10:23:53 -0400
Subject: [PATCH 0470/1334] bcachefs: Fix restart handling in
 btree_node_scrub_work()

btree node scrub was sometimes failing to rewrite nodes with errors;
bch2_btree_node_rewrite() can return a transaction restart and we
weren't checking - the lockrestart_do() needs to wrap the entire
operation.

And there's a better helper it should've been using,
bch2_btree_node_rewrite_key(), which makes all this more convenient.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/btree_io.c              | 28 ++++++----------------------
 fs/bcachefs/btree_update_interior.c | 11 +++++------
 fs/bcachefs/btree_update_interior.h |  3 +++
 3 files changed, 14 insertions(+), 28 deletions(-)

diff --git a/fs/bcachefs/btree_io.c b/fs/bcachefs/btree_io.c
index dca5530a2f49..08b22bddd747 100644
--- a/fs/bcachefs/btree_io.c
+++ b/fs/bcachefs/btree_io.c
@@ -1986,28 +1986,12 @@ static void btree_node_scrub_work(struct work_struct *work)
 	prt_newline(&err);
 
 	if (!btree_node_scrub_check(c, scrub->buf, scrub->written, &err)) {
-		struct btree_trans *trans = bch2_trans_get(c);
-
-		struct btree_iter iter;
-		bch2_trans_node_iter_init(trans, &iter, scrub->btree,
-					  scrub->key.k->k.p, 0, scrub->level - 1, 0);
-
-		struct btree *b;
-		int ret = lockrestart_do(trans,
-			PTR_ERR_OR_ZERO(b = bch2_btree_iter_peek_node(trans, &iter)));
-		if (ret)
-			goto err;
-
-		if (bkey_i_to_btree_ptr_v2(&b->key)->v.seq == scrub->seq) {
-			bch_err(c, "error validating btree node during scrub on %s at btree %s",
-				scrub->ca->name, err.buf);
-
-			ret = bch2_btree_node_rewrite(trans, &iter, b, 0, 0);
-		}
-err:
-		bch2_trans_iter_exit(trans, &iter);
-		bch2_trans_begin(trans);
-		bch2_trans_put(trans);
+		int ret = bch2_trans_do(c,
+			bch2_btree_node_rewrite_key(trans, scrub->btree, scrub->level - 1,
+						    scrub->key.k, 0));
+		if (!bch2_err_matches(ret, ENOENT) &&
+		    !bch2_err_matches(ret, EROFS))
+			bch_err_fn_ratelimited(c, ret);
 	}
 
 	printbuf_exit(&err);
diff --git a/fs/bcachefs/btree_update_interior.c b/fs/bcachefs/btree_update_interior.c
index e77584607f0d..7bf1bd6a6e92 100644
--- a/fs/bcachefs/btree_update_interior.c
+++ b/fs/bcachefs/btree_update_interior.c
@@ -2293,9 +2293,9 @@ err:
 	goto out;
 }
 
-static int bch2_btree_node_rewrite_key(struct btree_trans *trans,
-				       enum btree_id btree, unsigned level,
-				       struct bkey_i *k, unsigned flags)
+int bch2_btree_node_rewrite_key(struct btree_trans *trans,
+				enum btree_id btree, unsigned level,
+				struct bkey_i *k, unsigned flags)
 {
 	struct btree_iter iter;
 	bch2_trans_node_iter_init(trans, &iter,
@@ -2367,9 +2367,8 @@ static void async_btree_node_rewrite_work(struct work_struct *work)
 
 	int ret = bch2_trans_do(c, bch2_btree_node_rewrite_key(trans,
 						a->btree_id, a->level, a->key.k, 0));
-	if (ret != -ENOENT &&
-	    !bch2_err_matches(ret, EROFS) &&
-	    ret != -BCH_ERR_journal_shutdown)
+	if (!bch2_err_matches(ret, ENOENT) &&
+	    !bch2_err_matches(ret, EROFS))
 		bch_err_fn_ratelimited(c, ret);
 
 	spin_lock(&c->btree_node_rewrites_lock);
diff --git a/fs/bcachefs/btree_update_interior.h b/fs/bcachefs/btree_update_interior.h
index b649c36c3fbb..ac04e45a8515 100644
--- a/fs/bcachefs/btree_update_interior.h
+++ b/fs/bcachefs/btree_update_interior.h
@@ -176,6 +176,9 @@ static inline int bch2_foreground_maybe_merge(struct btree_trans *trans,
 
 int bch2_btree_node_rewrite(struct btree_trans *, struct btree_iter *,
 			    struct btree *, unsigned, unsigned);
+int bch2_btree_node_rewrite_key(struct btree_trans *,
+				enum btree_id, unsigned,
+				struct bkey_i *, unsigned);
 int bch2_btree_node_rewrite_pos(struct btree_trans *,
 				enum btree_id, unsigned,
 				struct bpos, unsigned, unsigned);

From db22720545207f734aaa9d9f71637bfc8b0155e0 Mon Sep 17 00:00:00 2001
From: Brett Werling <brett.werling@garmin.com>
Date: Thu, 12 Jun 2025 14:18:25 -0500
Subject: [PATCH 0471/1334] can: tcan4x5x: fix power regulator retrieval during
 probe

Fixes the power regulator retrieval in tcan4x5x_can_probe() by ensuring
the regulator pointer is not set to NULL in the successful return from
devm_regulator_get_optional().

Fixes: 3814ca3a10be ("can: tcan4x5x: tcan4x5x_can_probe(): turn on the power before parsing the config")
Signed-off-by: Brett Werling <brett.werling@garmin.com>
Link: https://patch.msgid.link/20250612191825.3646364-1-brett.werling@garmin.com
Cc: stable@vger.kernel.org
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/m_can/tcan4x5x-core.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/drivers/net/can/m_can/tcan4x5x-core.c b/drivers/net/can/m_can/tcan4x5x-core.c
index e5c162f8c589..8edaa339d590 100644
--- a/drivers/net/can/m_can/tcan4x5x-core.c
+++ b/drivers/net/can/m_can/tcan4x5x-core.c
@@ -411,10 +411,11 @@ static int tcan4x5x_can_probe(struct spi_device *spi)
 	priv = cdev_to_priv(mcan_class);
 
 	priv->power = devm_regulator_get_optional(&spi->dev, "vsup");
-	if (PTR_ERR(priv->power) == -EPROBE_DEFER) {
-		ret = -EPROBE_DEFER;
-		goto out_m_can_class_free_dev;
-	} else {
+	if (IS_ERR(priv->power)) {
+		if (PTR_ERR(priv->power) == -EPROBE_DEFER) {
+			ret = -EPROBE_DEFER;
+			goto out_m_can_class_free_dev;
+		}
 		priv->power = NULL;
 	}
 

From 7f8073cfb04a97842fe891ca50dad60afd1e3121 Mon Sep 17 00:00:00 2001
From: Heiko Carstens <hca@linux.ibm.com>
Date: Fri, 13 Jun 2025 17:53:04 +0200
Subject: [PATCH 0472/1334] s390/ptrace: Fix pointer dereferencing in
 regs_get_kernel_stack_nth()

The recent change which added READ_ONCE_NOCHECK() to read the nth entry
from the kernel stack incorrectly dropped dereferencing of the stack
pointer in order to read the requested entry.

In result the address of the entry is returned instead of its content.

Dereference the pointer again to fix this.

Reported-by: Will Deacon <will@kernel.org>
Closes: https://lore.kernel.org/r/20250612163331.GA13384@willie-the-truck
Fixes: d93a855c31b7 ("s390/ptrace: Avoid KASAN false positives in regs_get_kernel_stack_nth()")
Cc: stable@vger.kernel.org
Reviewed-by: Alexander Gordeev <agordeev@linux.ibm.com>
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
Signed-off-by: Alexander Gordeev <agordeev@linux.ibm.com>
---
 arch/s390/include/asm/ptrace.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/s390/include/asm/ptrace.h b/arch/s390/include/asm/ptrace.h
index 62c0ab4a4b9d..0905fa99a31e 100644
--- a/arch/s390/include/asm/ptrace.h
+++ b/arch/s390/include/asm/ptrace.h
@@ -265,7 +265,7 @@ static __always_inline unsigned long regs_get_kernel_stack_nth(struct pt_regs *r
 	addr = kernel_stack_pointer(regs) + n * sizeof(long);
 	if (!regs_within_kernel_stack(regs, addr))
 		return 0;
-	return READ_ONCE_NOCHECK(addr);
+	return READ_ONCE_NOCHECK(*(unsigned long *)addr);
 }
 
 /**

From 5d3bc9e5e725aa36cca9b794e340057feb6880b4 Mon Sep 17 00:00:00 2001
From: Krishna Kumar <krikku@gmail.com>
Date: Tue, 20 May 2025 22:36:56 +0530
Subject: [PATCH 0473/1334] net: ice: Perform accurate aRFS flow match

This patch fixes an issue seen in a large-scale deployment under heavy
incoming pkts where the aRFS flow wrongly matches a flow and reprograms the
NIC with wrong settings. That mis-steering causes RX-path latency spikes
and noisy neighbor effects when many connections collide on the same
hash (some of our production servers have 20-30K connections).

set_rps_cpu() calls ndo_rx_flow_steer() with flow_id that is calculated by
hashing the skb sized by the per rx-queue table size. This results in
multiple connections (even across different rx-queues) getting the same
hash value. The driver steer function modifies the wrong flow to use this
rx-queue, e.g.: Flow#1 is first added:
    Flow#1:  <ip1, port1, ip2, port2>, Hash 'h', q#10

Later when a new flow needs to be added:
	    Flow#2:  <ip3, port3, ip4, port4>, Hash 'h', q#20

The driver finds the hash 'h' from Flow#1 and updates it to use q#20. This
results in both flows getting un-optimized - packets for Flow#1 goes to
q#20, and then reprogrammed back to q#10 later and so on; and Flow #2
programming is never done as Flow#1 is matched first for all misses. Many
flows may wrongly share the same hash and reprogram rules of the original
flow each with their own q#.

Tested on two 144-core servers with 16K netperf sessions for 180s. Netperf
clients are pinned to cores 0-71 sequentially (so that wrong packets on q#s
72-143 can be measured). IRQs are set 1:1 for queues -> CPUs, enable XPS,
enable aRFS (global value is 144 * rps_flow_cnt).

Test notes about results from ice_rx_flow_steer():
---------------------------------------------------
1. "Skip:" counter increments here:
    if (fltr_info->q_index == rxq_idx ||
	arfs_entry->fltr_state != ICE_ARFS_ACTIVE)
	    goto out;
2. "Add:" counter increments here:
    ret = arfs_entry->fltr_info.fltr_id;
    INIT_HLIST_NODE(&arfs_entry->list_entry);
3. "Update:" counter increments here:
    /* update the queue to forward to on an already existing flow */

Runtime comparison: original code vs with the patch for different
rps_flow_cnt values.

+-------------------------------+--------------+--------------+
| rps_flow_cnt                  |      512     |    2048      |
+-------------------------------+--------------+--------------+
| Ratio of Pkts on Good:Bad q's | 214 vs 822K  | 1.1M vs 980K |
| Avoid wrong aRFS programming  | 0 vs 310K    | 0 vs 30K     |
| CPU User                      | 216 vs 183   | 216 vs 206   |
| CPU System                    | 1441 vs 1171 | 1447 vs 1320 |
| CPU Softirq                   | 1245 vs 920  | 1238 vs 961  |
| CPU Total                     | 29 vs 22.7   | 29 vs 24.9   |
| aRFS Update                   | 533K vs 59   | 521K vs 32   |
| aRFS Skip                     | 82M vs 77M   | 7.2M vs 4.5M |
+-------------------------------+--------------+--------------+

A separate TCP_STREAM and TCP_RR with 1,4,8,16,64,128,256,512 connections
showed no performance degradation.

Some points on the patch/aRFS behavior:
1. Enabling full tuple matching ensures flows are always correctly matched,
   even with smaller hash sizes.
2. 5-6% drop in CPU utilization as the packets arrive at the correct CPUs
   and fewer calls to driver for programming on misses.
3. Larger hash tables reduces mis-steering due to more unique flow hashes,
   but still has clashes. However, with larger per-device rps_flow_cnt, old
   flows take more time to expire and new aRFS flows cannot be added if h/w
   limits are reached (rps_may_expire_flow() succeeds when 10*rps_flow_cnt
   pkts have been processed by this cpu that are not part of the flow).

Fixes: 28bf26724fdb0 ("ice: Implement aRFS")
Signed-off-by: Krishna Kumar <krikku@gmail.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Tested-by: Rinitha S <sx.rinitha@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_arfs.c | 48 +++++++++++++++++++++++
 1 file changed, 48 insertions(+)

diff --git a/drivers/net/ethernet/intel/ice/ice_arfs.c b/drivers/net/ethernet/intel/ice/ice_arfs.c
index 2bc5c7f59844..1f7834c03550 100644
--- a/drivers/net/ethernet/intel/ice/ice_arfs.c
+++ b/drivers/net/ethernet/intel/ice/ice_arfs.c
@@ -377,6 +377,50 @@ ice_arfs_is_perfect_flow_set(struct ice_hw *hw, __be16 l3_proto, u8 l4_proto)
 	return false;
 }
 
+/**
+ * ice_arfs_cmp - Check if aRFS filter matches this flow.
+ * @fltr_info: filter info of the saved ARFS entry.
+ * @fk: flow dissector keys.
+ * @n_proto:  One of htons(ETH_P_IP) or htons(ETH_P_IPV6).
+ * @ip_proto: One of IPPROTO_TCP or IPPROTO_UDP.
+ *
+ * Since this function assumes limited values for n_proto and ip_proto, it
+ * is meant to be called only from ice_rx_flow_steer().
+ *
+ * Return:
+ * * true	- fltr_info refers to the same flow as fk.
+ * * false	- fltr_info and fk refer to different flows.
+ */
+static bool
+ice_arfs_cmp(const struct ice_fdir_fltr *fltr_info, const struct flow_keys *fk,
+	     __be16 n_proto, u8 ip_proto)
+{
+	/* Determine if the filter is for IPv4 or IPv6 based on flow_type,
+	 * which is one of ICE_FLTR_PTYPE_NONF_IPV{4,6}_{TCP,UDP}.
+	 */
+	bool is_v4 = fltr_info->flow_type == ICE_FLTR_PTYPE_NONF_IPV4_TCP ||
+		     fltr_info->flow_type == ICE_FLTR_PTYPE_NONF_IPV4_UDP;
+
+	/* Following checks are arranged in the quickest and most discriminative
+	 * fields first for early failure.
+	 */
+	if (is_v4)
+		return n_proto == htons(ETH_P_IP) &&
+			fltr_info->ip.v4.src_port == fk->ports.src &&
+			fltr_info->ip.v4.dst_port == fk->ports.dst &&
+			fltr_info->ip.v4.src_ip == fk->addrs.v4addrs.src &&
+			fltr_info->ip.v4.dst_ip == fk->addrs.v4addrs.dst &&
+			fltr_info->ip.v4.proto == ip_proto;
+
+	return fltr_info->ip.v6.src_port == fk->ports.src &&
+		fltr_info->ip.v6.dst_port == fk->ports.dst &&
+		fltr_info->ip.v6.proto == ip_proto &&
+		!memcmp(&fltr_info->ip.v6.src_ip, &fk->addrs.v6addrs.src,
+			sizeof(struct in6_addr)) &&
+		!memcmp(&fltr_info->ip.v6.dst_ip, &fk->addrs.v6addrs.dst,
+			sizeof(struct in6_addr));
+}
+
 /**
  * ice_rx_flow_steer - steer the Rx flow to where application is being run
  * @netdev: ptr to the netdev being adjusted
@@ -448,6 +492,10 @@ ice_rx_flow_steer(struct net_device *netdev, const struct sk_buff *skb,
 			continue;
 
 		fltr_info = &arfs_entry->fltr_info;
+
+		if (!ice_arfs_cmp(fltr_info, &fk, n_proto, ip_proto))
+			continue;
+
 		ret = fltr_info->fltr_id;
 
 		if (fltr_info->q_index == rxq_idx ||

From 48c8b214974dc55283bd5f12e3a483b27c403bbc Mon Sep 17 00:00:00 2001
From: Grzegorz Nitka <grzegorz.nitka@intel.com>
Date: Fri, 16 May 2025 15:09:07 +0200
Subject: [PATCH 0474/1334] ice: fix eswitch code memory leak in reset scenario

Add simple eswitch mode checker in attaching VF procedure and allocate
required port representor memory structures only in switchdev mode.
The reset flows triggers VF (if present) detach/attach procedure.
It might involve VF port representor(s) re-creation if the device is
configured is switchdev mode (not legacy one).
The memory was blindly allocated in current implementation,
regardless of the mode and not freed if in legacy mode.

Kmemeleak trace:
unreferenced object (percpu) 0x7e3bce5b888458 (size 40):
  comm "bash", pid 1784, jiffies 4295743894
  hex dump (first 32 bytes on cpu 45):
    00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
    00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
  backtrace (crc 0):
    pcpu_alloc_noprof+0x4c4/0x7c0
    ice_repr_create+0x66/0x130 [ice]
    ice_repr_create_vf+0x22/0x70 [ice]
    ice_eswitch_attach_vf+0x1b/0xa0 [ice]
    ice_reset_all_vfs+0x1dd/0x2f0 [ice]
    ice_pci_err_resume+0x3b/0xb0 [ice]
    pci_reset_function+0x8f/0x120
    reset_store+0x56/0xa0
    kernfs_fop_write_iter+0x120/0x1b0
    vfs_write+0x31c/0x430
    ksys_write+0x61/0xd0
    do_syscall_64+0x5b/0x180
    entry_SYSCALL_64_after_hwframe+0x76/0x7e

Testing hints (ethX is PF netdev):
- create at least one VF
    echo 1 > /sys/class/net/ethX/device/sriov_numvfs
- trigger the reset
    echo 1 > /sys/class/net/ethX/device/reset

Fixes: 415db8399d06 ("ice: make representor code generic")
Signed-off-by: Grzegorz Nitka <grzegorz.nitka@intel.com>
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Tested-by: Rinitha S <sx.rinitha@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_eswitch.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch.c b/drivers/net/ethernet/intel/ice/ice_eswitch.c
index 6aae03771746..2e4f0969035f 100644
--- a/drivers/net/ethernet/intel/ice/ice_eswitch.c
+++ b/drivers/net/ethernet/intel/ice/ice_eswitch.c
@@ -508,10 +508,14 @@ err_create_repr:
  */
 int ice_eswitch_attach_vf(struct ice_pf *pf, struct ice_vf *vf)
 {
-	struct ice_repr *repr = ice_repr_create_vf(vf);
 	struct devlink *devlink = priv_to_devlink(pf);
+	struct ice_repr *repr;
 	int err;
 
+	if (!ice_is_eswitch_mode_switchdev(pf))
+		return 0;
+
+	repr = ice_repr_create_vf(vf);
 	if (IS_ERR(repr))
 		return PTR_ERR(repr);
 

From 688a0d61b2d7427189c4eb036ce485d8fc957cbb Mon Sep 17 00:00:00 2001
From: Vitaly Lifshits <vitaly.lifshits@intel.com>
Date: Sun, 25 May 2025 11:38:43 +0300
Subject: [PATCH 0475/1334] e1000e: set fixed clock frequency indication for
 Nahum 11 and Nahum 13

On some systems with Nahum 11 and Nahum 13 the value of the XTAL clock in
the software STRAP is incorrect. This causes the PTP timer to run at the
wrong rate and can lead to synchronization issues.

The STRAP value is configured by the system firmware, and a firmware
update is not always possible. Since the XTAL clock on these systems
always runs at 38.4MHz, the driver may ignore the STRAP and just set
the correct value.

Fixes: cc23f4f0b6b9 ("e1000e: Add support for Meteor Lake")
Signed-off-by: Vitaly Lifshits <vitaly.lifshits@intel.com>
Tested-by: Mor Bar-Gabay <morx.bar.gabay@intel.com>
Reviewed-by: Gil Fine <gil.fine@linux.intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/e1000e/netdev.c | 14 +++++++++++---
 drivers/net/ethernet/intel/e1000e/ptp.c    |  8 +++++---
 2 files changed, 16 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c
index a96f4cfa6e17..7719e15813ee 100644
--- a/drivers/net/ethernet/intel/e1000e/netdev.c
+++ b/drivers/net/ethernet/intel/e1000e/netdev.c
@@ -3534,9 +3534,6 @@ s32 e1000e_get_base_timinca(struct e1000_adapter *adapter, u32 *timinca)
 	case e1000_pch_cnp:
 	case e1000_pch_tgp:
 	case e1000_pch_adp:
-	case e1000_pch_mtp:
-	case e1000_pch_lnp:
-	case e1000_pch_ptp:
 	case e1000_pch_nvp:
 		if (er32(TSYNCRXCTL) & E1000_TSYNCRXCTL_SYSCFI) {
 			/* Stable 24MHz frequency */
@@ -3552,6 +3549,17 @@ s32 e1000e_get_base_timinca(struct e1000_adapter *adapter, u32 *timinca)
 			adapter->cc.shift = shift;
 		}
 		break;
+	case e1000_pch_mtp:
+	case e1000_pch_lnp:
+	case e1000_pch_ptp:
+		/* System firmware can misreport this value, so set it to a
+		 * stable 38400KHz frequency.
+		 */
+		incperiod = INCPERIOD_38400KHZ;
+		incvalue = INCVALUE_38400KHZ;
+		shift = INCVALUE_SHIFT_38400KHZ;
+		adapter->cc.shift = shift;
+		break;
 	case e1000_82574:
 	case e1000_82583:
 		/* Stable 25MHz frequency */
diff --git a/drivers/net/ethernet/intel/e1000e/ptp.c b/drivers/net/ethernet/intel/e1000e/ptp.c
index 89d57dd911dc..ea3c3eb2ef20 100644
--- a/drivers/net/ethernet/intel/e1000e/ptp.c
+++ b/drivers/net/ethernet/intel/e1000e/ptp.c
@@ -295,15 +295,17 @@ void e1000e_ptp_init(struct e1000_adapter *adapter)
 	case e1000_pch_cnp:
 	case e1000_pch_tgp:
 	case e1000_pch_adp:
-	case e1000_pch_mtp:
-	case e1000_pch_lnp:
-	case e1000_pch_ptp:
 	case e1000_pch_nvp:
 		if (er32(TSYNCRXCTL) & E1000_TSYNCRXCTL_SYSCFI)
 			adapter->ptp_clock_info.max_adj = MAX_PPB_24MHZ;
 		else
 			adapter->ptp_clock_info.max_adj = MAX_PPB_38400KHZ;
 		break;
+	case e1000_pch_mtp:
+	case e1000_pch_lnp:
+	case e1000_pch_ptp:
+		adapter->ptp_clock_info.max_adj = MAX_PPB_38400KHZ;
+		break;
 	case e1000_82574:
 	case e1000_82583:
 		adapter->ptp_clock_info.max_adj = MAX_PPB_25MHZ;

From 2c6b640ea08bff1a192bf87fa45246ff1e40767c Mon Sep 17 00:00:00 2001
From: Or Har-Toov <ohartoov@nvidia.com>
Date: Mon, 16 Jun 2025 11:17:01 +0300
Subject: [PATCH 0476/1334] RDMA/mlx5: Fix unsafe xarray access in implicit ODP
 handling

__xa_store() and __xa_erase() were used without holding the proper lock,
which led to a lockdep warning due to unsafe RCU usage.  This patch
replaces them with xa_store() and xa_erase(), which perform the necessary
locking internally.

  =============================
  WARNING: suspicious RCPU usage
  6.14.0-rc7_for_upstream_debug_2025_03_18_15_01 #1 Not tainted
  -----------------------------
  ./include/linux/xarray.h:1211 suspicious rcu_dereference_protected() usage!

  other info that might help us debug this:

  rcu_scheduler_active = 2, debug_locks = 1
  3 locks held by kworker/u136:0/219:
      at: process_one_work+0xbe4/0x15f0
      process_one_work+0x75c/0x15f0
      pagefault_mr+0x9a5/0x1390 [mlx5_ib]

  stack backtrace:
  CPU: 14 UID: 0 PID: 219 Comm: kworker/u136:0 Not tainted
  6.14.0-rc7_for_upstream_debug_2025_03_18_15_01 #1
  Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS
  rel-1.16.0-0-gd239552ce722-prebuilt.qemu.org 04/01/2014
  Workqueue: mlx5_ib_page_fault mlx5_ib_eqe_pf_action [mlx5_ib]
  Call Trace:
   dump_stack_lvl+0xa8/0xc0
   lockdep_rcu_suspicious+0x1e6/0x260
   xas_create+0xb8a/0xee0
   xas_store+0x73/0x14c0
   __xa_store+0x13c/0x220
   ? xa_store_range+0x390/0x390
   ? spin_bug+0x1d0/0x1d0
   pagefault_mr+0xcb5/0x1390 [mlx5_ib]
   ? _raw_spin_unlock+0x1f/0x30
   mlx5_ib_eqe_pf_action+0x3be/0x2620 [mlx5_ib]
   ? lockdep_hardirqs_on_prepare+0x400/0x400
   ? mlx5_ib_invalidate_range+0xcb0/0xcb0 [mlx5_ib]
   process_one_work+0x7db/0x15f0
   ? pwq_dec_nr_in_flight+0xda0/0xda0
   ? assign_work+0x168/0x240
   worker_thread+0x57d/0xcd0
   ? rescuer_thread+0xc40/0xc40
   kthread+0x3b3/0x800
   ? kthread_is_per_cpu+0xb0/0xb0
   ? lock_downgrade+0x680/0x680
   ? do_raw_spin_lock+0x12d/0x270
   ? spin_bug+0x1d0/0x1d0
   ? finish_task_switch.isra.0+0x284/0x9e0
   ? lockdep_hardirqs_on_prepare+0x284/0x400
   ? kthread_is_per_cpu+0xb0/0xb0
   ret_from_fork+0x2d/0x70
   ? kthread_is_per_cpu+0xb0/0xb0
   ret_from_fork_asm+0x11/0x20

Fixes: d3d930411ce3 ("RDMA/mlx5: Fix implicit ODP use after free")
Link: https://patch.msgid.link/r/a85ddd16f45c8cb2bc0a188c2b0fcedfce975eb8.1750061791.git.leon@kernel.org
Signed-off-by: Or Har-Toov <ohartoov@nvidia.com>
Reviewed-by: Patrisious Haddad <phaddad@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/infiniband/hw/mlx5/odp.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/infiniband/hw/mlx5/odp.c b/drivers/infiniband/hw/mlx5/odp.c
index eaa2f9f5f3a9..f6abd64f07f7 100644
--- a/drivers/infiniband/hw/mlx5/odp.c
+++ b/drivers/infiniband/hw/mlx5/odp.c
@@ -259,8 +259,8 @@ static void destroy_unused_implicit_child_mr(struct mlx5_ib_mr *mr)
 	}
 
 	if (MLX5_CAP_ODP(mr_to_mdev(mr)->mdev, mem_page_fault))
-		__xa_erase(&mr_to_mdev(mr)->odp_mkeys,
-			   mlx5_base_mkey(mr->mmkey.key));
+		xa_erase(&mr_to_mdev(mr)->odp_mkeys,
+			 mlx5_base_mkey(mr->mmkey.key));
 	xa_unlock(&imr->implicit_children);
 
 	/* Freeing a MR is a sleeping operation, so bounce to a work queue */
@@ -532,8 +532,8 @@ static struct mlx5_ib_mr *implicit_get_child_mr(struct mlx5_ib_mr *imr,
 	}
 
 	if (MLX5_CAP_ODP(dev->mdev, mem_page_fault)) {
-		ret = __xa_store(&dev->odp_mkeys, mlx5_base_mkey(mr->mmkey.key),
-				 &mr->mmkey, GFP_KERNEL);
+		ret = xa_store(&dev->odp_mkeys, mlx5_base_mkey(mr->mmkey.key),
+			       &mr->mmkey, GFP_KERNEL);
 		if (xa_is_err(ret)) {
 			ret = ERR_PTR(xa_err(ret));
 			__xa_erase(&imr->implicit_children, idx);

From 333e4d79316c9ed5877d7aac8b8ed22efc74e96d Mon Sep 17 00:00:00 2001
From: Maor Gottlieb <maorg@nvidia.com>
Date: Mon, 16 Jun 2025 11:26:21 +0300
Subject: [PATCH 0477/1334] RDMA/core: Rate limit GID cache warning messages

The GID cache warning messages can flood the kernel log when there are
multiple failed attempts to add GIDs. This can happen when creating many
virtual interfaces without having enough space for their GIDs in the GID
table.

Change pr_warn to pr_warn_ratelimited to prevent log flooding while still
maintaining visibility of the issue.

Link: https://patch.msgid.link/r/fd45ed4a1078e743f498b234c3ae816610ba1b18.1750062357.git.leon@kernel.org
Signed-off-by: Maor Gottlieb <maorg@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/infiniband/core/cache.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/infiniband/core/cache.c b/drivers/infiniband/core/cache.c
index 9979a351577f..81cf3c902e81 100644
--- a/drivers/infiniband/core/cache.c
+++ b/drivers/infiniband/core/cache.c
@@ -582,8 +582,8 @@ static int __ib_cache_gid_add(struct ib_device *ib_dev, u32 port,
 out_unlock:
 	mutex_unlock(&table->lock);
 	if (ret)
-		pr_warn("%s: unable to add gid %pI6 error=%d\n",
-			__func__, gid->raw, ret);
+		pr_warn_ratelimited("%s: unable to add gid %pI6 error=%d\n",
+				    __func__, gid->raw, ret);
 	return ret;
 }
 

From 8edab8a72d67742f87e9dc2e2b0cdfddda5dc29a Mon Sep 17 00:00:00 2001
From: Mark Zhang <markzhang@nvidia.com>
Date: Tue, 17 Jun 2025 11:13:55 +0300
Subject: [PATCH 0478/1334] RDMA/mlx5: Initialize obj_event->obj_sub_list
 before xa_insert

The obj_event may be loaded immediately after inserted, then if the
list_head is not initialized then we may get a poisonous pointer.  This
fixes the crash below:

 mlx5_core 0000:03:00.0: MLX5E: StrdRq(1) RqSz(8) StrdSz(2048) RxCqeCmprss(0 enhanced)
 mlx5_core.sf mlx5_core.sf.4: firmware version: 32.38.3056
 mlx5_core 0000:03:00.0 en3f0pf0sf2002: renamed from eth0
 mlx5_core.sf mlx5_core.sf.4: Rate limit: 127 rates are supported, range: 0Mbps to 195312Mbps
 IPv6: ADDRCONF(NETDEV_CHANGE): en3f0pf0sf2002: link becomes ready
 Unable to handle kernel NULL pointer dereference at virtual address 0000000000000060
 Mem abort info:
   ESR = 0x96000006
   EC = 0x25: DABT (current EL), IL = 32 bits
   SET = 0, FnV = 0
   EA = 0, S1PTW = 0
 Data abort info:
   ISV = 0, ISS = 0x00000006
   CM = 0, WnR = 0
 user pgtable: 4k pages, 48-bit VAs, pgdp=00000007760fb000
 [0000000000000060] pgd=000000076f6d7003, p4d=000000076f6d7003, pud=0000000777841003, pmd=0000000000000000
 Internal error: Oops: 96000006 [#1] SMP
 Modules linked in: ipmb_host(OE) act_mirred(E) cls_flower(E) sch_ingress(E) mptcp_diag(E) udp_diag(E) raw_diag(E) unix_diag(E) tcp_diag(E) inet_diag(E) binfmt_misc(E) bonding(OE) rdma_ucm(OE) rdma_cm(OE) iw_cm(OE) ib_ipoib(OE) ib_cm(OE) isofs(E) cdrom(E) mst_pciconf(OE) ib_umad(OE) mlx5_ib(OE) ipmb_dev_int(OE) mlx5_core(OE) kpatch_15237886(OEK) mlxdevm(OE) auxiliary(OE) ib_uverbs(OE) ib_core(OE) psample(E) mlxfw(OE) tls(E) sunrpc(E) vfat(E) fat(E) crct10dif_ce(E) ghash_ce(E) sha1_ce(E) sbsa_gwdt(E) virtio_console(E) ext4(E) mbcache(E) jbd2(E) xfs(E) libcrc32c(E) mmc_block(E) virtio_net(E) net_failover(E) failover(E) sha2_ce(E) sha256_arm64(E) nvme(OE) nvme_core(OE) gpio_mlxbf3(OE) mlx_compat(OE) mlxbf_pmc(OE) i2c_mlxbf(OE) sdhci_of_dwcmshc(OE) pinctrl_mlxbf3(OE) mlxbf_pka(OE) gpio_generic(E) i2c_core(E) mmc_core(E) mlxbf_gige(OE) vitesse(E) pwr_mlxbf(OE) mlxbf_tmfifo(OE) micrel(E) mlxbf_bootctl(OE) virtio_ring(E) virtio(E) ipmi_devintf(E) ipmi_msghandler(E)
  [last unloaded: mst_pci]
 CPU: 11 PID: 20913 Comm: rte-worker-11 Kdump: loaded Tainted: G           OE K   5.10.134-13.1.an8.aarch64 #1
 Hardware name: https://www.mellanox.com BlueField-3 SmartNIC Main Card/BlueField-3 SmartNIC Main Card, BIOS 4.2.2.12968 Oct 26 2023
 pstate: a0400089 (NzCv daIf +PAN -UAO -TCO BTYPE=--)
 pc : dispatch_event_fd+0x68/0x300 [mlx5_ib]
 lr : devx_event_notifier+0xcc/0x228 [mlx5_ib]
 sp : ffff80001005bcf0
 x29: ffff80001005bcf0 x28: 0000000000000001
 x27: ffff244e0740a1d8 x26: ffff244e0740a1d0
 x25: ffffda56beff5ae0 x24: ffffda56bf911618
 x23: ffff244e0596a480 x22: ffff244e0596a480
 x21: ffff244d8312ad90 x20: ffff244e0596a480
 x19: fffffffffffffff0 x18: 0000000000000000
 x17: 0000000000000000 x16: ffffda56be66d620
 x15: 0000000000000000 x14: 0000000000000000
 x13: 0000000000000000 x12: 0000000000000000
 x11: 0000000000000040 x10: ffffda56bfcafb50
 x9 : ffffda5655c25f2c x8 : 0000000000000010
 x7 : 0000000000000000 x6 : ffff24545a2e24b8
 x5 : 0000000000000003 x4 : ffff80001005bd28
 x3 : 0000000000000000 x2 : 0000000000000000
 x1 : ffff244e0596a480 x0 : ffff244d8312ad90
 Call trace:
  dispatch_event_fd+0x68/0x300 [mlx5_ib]
  devx_event_notifier+0xcc/0x228 [mlx5_ib]
  atomic_notifier_call_chain+0x58/0x80
  mlx5_eq_async_int+0x148/0x2b0 [mlx5_core]
  atomic_notifier_call_chain+0x58/0x80
  irq_int_handler+0x20/0x30 [mlx5_core]
  __handle_irq_event_percpu+0x60/0x220
  handle_irq_event_percpu+0x3c/0x90
  handle_irq_event+0x58/0x158
  handle_fasteoi_irq+0xfc/0x188
  generic_handle_irq+0x34/0x48
  ...

Fixes: 759738537142 ("IB/mlx5: Enable subscription for device events over DEVX")
Link: https://patch.msgid.link/r/3ce7f20e0d1a03dc7de6e57494ec4b8eaf1f05c2.1750147949.git.leon@kernel.org
Signed-off-by: Mark Zhang <markzhang@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/infiniband/hw/mlx5/devx.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/infiniband/hw/mlx5/devx.c b/drivers/infiniband/hw/mlx5/devx.c
index bceae1c1f980..843dcd312242 100644
--- a/drivers/infiniband/hw/mlx5/devx.c
+++ b/drivers/infiniband/hw/mlx5/devx.c
@@ -1958,6 +1958,7 @@ subscribe_event_xa_alloc(struct mlx5_devx_event_table *devx_event_table,
 			/* Level1 is valid for future use, no need to free */
 			return -ENOMEM;
 
+		INIT_LIST_HEAD(&obj_event->obj_sub_list);
 		err = xa_insert(&event->object_ids,
 				key_level2,
 				obj_event,
@@ -1966,7 +1967,6 @@ subscribe_event_xa_alloc(struct mlx5_devx_event_table *devx_event_table,
 			kfree(obj_event);
 			return err;
 		}
-		INIT_LIST_HEAD(&obj_event->obj_sub_list);
 	}
 
 	return 0;

From bbc3a0b17a890aa19bddd0f9b08e8af488f1ec94 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Tue, 17 Jun 2025 13:08:35 -0400
Subject: [PATCH 0479/1334] bcachefs: fsck: Fix check_directory_structure when
 no check_dirents

check_directory_structure runs after check_dirents, so it expects that
it won't see any inodes with missing backpointers - normally.

But online fsck can't run check_dirents yet, or the user might only be
running a specific pass, so we need to be careful that this isn't an
error. If an inode is unreachable, that's handled by a separate pass.

Also, add a new 'bch2_inode_has_backpointer()' helper, since we were
doing this inconsistently.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/fsck.c  | 18 +++++++++++++-----
 fs/bcachefs/inode.h |  5 +++++
 fs/bcachefs/namei.c |  3 +--
 3 files changed, 19 insertions(+), 7 deletions(-)

diff --git a/fs/bcachefs/fsck.c b/fs/bcachefs/fsck.c
index 73cff24598ed..57ddc20a5cce 100644
--- a/fs/bcachefs/fsck.c
+++ b/fs/bcachefs/fsck.c
@@ -327,7 +327,8 @@ static inline bool inode_should_reattach(struct bch_inode_unpacked *inode)
 	    (inode->bi_flags & BCH_INODE_has_child_snapshot))
 		return false;
 
-	return !inode->bi_dir && !(inode->bi_flags & BCH_INODE_unlinked);
+	return !bch2_inode_has_backpointer(inode) &&
+		!(inode->bi_flags & BCH_INODE_unlinked);
 }
 
 static int maybe_delete_dirent(struct btree_trans *trans, struct bpos d_pos, u32 snapshot)
@@ -514,7 +515,7 @@ static struct bkey_s_c_dirent dirent_get_by_pos(struct btree_trans *trans,
 static int remove_backpointer(struct btree_trans *trans,
 			      struct bch_inode_unpacked *inode)
 {
-	if (!inode->bi_dir)
+	if (!bch2_inode_has_backpointer(inode))
 		return 0;
 
 	u32 snapshot = inode->bi_snapshot;
@@ -1165,13 +1166,14 @@ static int check_inode(struct btree_trans *trans,
 	if (ret)
 		goto err;
 
-	if (u.bi_dir || u.bi_dir_offset) {
+	if (bch2_inode_has_backpointer(&u)) {
 		ret = check_inode_dirent_inode(trans, &u, &do_update);
 		if (ret)
 			goto err;
 	}
 
-	if (fsck_err_on(u.bi_dir && (u.bi_flags & BCH_INODE_unlinked),
+	if (fsck_err_on(bch2_inode_has_backpointer(&u) &&
+			(u.bi_flags & BCH_INODE_unlinked),
 			trans, inode_unlinked_but_has_dirent,
 			"inode unlinked but has dirent\n%s",
 			(printbuf_reset(&buf),
@@ -2751,7 +2753,13 @@ static int check_path_loop(struct btree_trans *trans, struct bkey_s_c inode_k)
 	if (ret)
 		return ret;
 
-	while (!inode.bi_subvol) {
+	/*
+	 * If we're running full fsck, check_dirents() will have already ran,
+	 * and we shouldn't see any missing backpointers here - otherwise that's
+	 * handled separately, by check_unreachable_inodes
+	 */
+	while (!inode.bi_subvol &&
+	       bch2_inode_has_backpointer(&inode)) {
 		struct btree_iter dirent_iter;
 		struct bkey_s_c_dirent d;
 
diff --git a/fs/bcachefs/inode.h b/fs/bcachefs/inode.h
index 82cec2836cbd..b8ec3e628d90 100644
--- a/fs/bcachefs/inode.h
+++ b/fs/bcachefs/inode.h
@@ -254,6 +254,11 @@ static inline bool bch2_inode_casefold(struct bch_fs *c, const struct bch_inode_
 		: c->opts.casefold;
 }
 
+static inline bool bch2_inode_has_backpointer(const struct bch_inode_unpacked *bi)
+{
+	return bi->bi_dir || bi->bi_dir_offset;
+}
+
 /* i_nlink: */
 
 static inline unsigned nlink_bias(umode_t mode)
diff --git a/fs/bcachefs/namei.c b/fs/bcachefs/namei.c
index 7d1068aa998f..c3f87c59922d 100644
--- a/fs/bcachefs/namei.c
+++ b/fs/bcachefs/namei.c
@@ -734,8 +734,7 @@ static int bch2_check_dirent_inode_dirent(struct btree_trans *trans,
 	if (inode_points_to_dirent(target, d))
 		return 0;
 
-	if (!target->bi_dir &&
-	    !target->bi_dir_offset) {
+	if (!bch2_inode_has_backpointer(target)) {
 		fsck_err_on(S_ISDIR(target->bi_mode),
 			    trans, inode_dir_missing_backpointer,
 			    "directory with missing backpointer\n%s",

From c50784e99f0e7199cdb12dbddf02229b102744ef Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Fri, 13 Jun 2025 13:23:07 -1000
Subject: [PATCH 0480/1334] sched_ext: Make scx_group_set_weight() always
 update tg->scx.weight

Otherwise, tg->scx.weight can go out of sync while scx_cgroup is not enabled
and ops.cgroup_init() may be called with a stale weight value.

Signed-off-by: Tejun Heo <tj@kernel.org>
Fixes: 819513666966 ("sched_ext: Add cgroup support")
Cc: stable@vger.kernel.org # v6.12+
---
 kernel/sched/ext.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index 2c41c78be61e..33a0d8c6ff95 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -4241,12 +4241,12 @@ void scx_group_set_weight(struct task_group *tg, unsigned long weight)
 
 	percpu_down_read(&scx_cgroup_rwsem);
 
-	if (scx_cgroup_enabled && tg->scx_weight != weight) {
-		if (SCX_HAS_OP(sch, cgroup_set_weight))
-			SCX_CALL_OP(sch, SCX_KF_UNLOCKED, cgroup_set_weight, NULL,
-				    tg_cgrp(tg), weight);
-		tg->scx_weight = weight;
-	}
+	if (scx_cgroup_enabled && SCX_HAS_OP(sch, cgroup_set_weight) &&
+	    tg->scx_weight != weight)
+		SCX_CALL_OP(sch, SCX_KF_UNLOCKED, cgroup_set_weight, NULL,
+			    tg_cgrp(tg), weight);
+
+	tg->scx_weight = weight;
 
 	percpu_up_read(&scx_cgroup_rwsem);
 }

From 33796b91871ad4010c8188372dd1faf97cf0f1c0 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Mon, 16 Jun 2025 10:13:25 -1000
Subject: [PATCH 0481/1334] sched_ext, sched/core: Don't call
 scx_group_set_weight() prematurely from sched_create_group()

During task_group creation, sched_create_group() calls
scx_group_set_weight() with CGROUP_WEIGHT_DFL to initialize the sched_ext
portion. This is premature and ends up calling ops.cgroup_set_weight() with
an incorrect @cgrp before ops.cgroup_init() is called.

sched_create_group() should just initialize SCX related fields in the new
task_group. Fix it by factoring out scx_tg_init() from sched_init() and
making sched_create_group() call that function instead of
scx_group_set_weight().

v2: Retain CONFIG_EXT_GROUP_SCHED ifdef in sched_init() as removing it leads
    to build failures on !CONFIG_GROUP_SCHED configs.

Signed-off-by: Tejun Heo <tj@kernel.org>
Fixes: 819513666966 ("sched_ext: Add cgroup support")
Cc: stable@vger.kernel.org # v6.12+
---
 kernel/sched/core.c | 4 ++--
 kernel/sched/ext.c  | 5 +++++
 kernel/sched/ext.h  | 2 ++
 3 files changed, 9 insertions(+), 2 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index dce50fa57471..8988d38d46a3 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -8545,7 +8545,7 @@ void __init sched_init(void)
 		init_cfs_bandwidth(&root_task_group.cfs_bandwidth, NULL);
 #endif /* CONFIG_FAIR_GROUP_SCHED */
 #ifdef CONFIG_EXT_GROUP_SCHED
-		root_task_group.scx_weight = CGROUP_WEIGHT_DFL;
+		scx_tg_init(&root_task_group);
 #endif /* CONFIG_EXT_GROUP_SCHED */
 #ifdef CONFIG_RT_GROUP_SCHED
 		root_task_group.rt_se = (struct sched_rt_entity **)ptr;
@@ -8985,7 +8985,7 @@ struct task_group *sched_create_group(struct task_group *parent)
 	if (!alloc_rt_sched_group(tg, parent))
 		goto err;
 
-	scx_group_set_weight(tg, CGROUP_WEIGHT_DFL);
+	scx_tg_init(tg);
 	alloc_uclamp_sched_group(tg, parent);
 
 	return tg;
diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index 33a0d8c6ff95..b498d867ba21 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -4092,6 +4092,11 @@ bool scx_can_stop_tick(struct rq *rq)
 DEFINE_STATIC_PERCPU_RWSEM(scx_cgroup_rwsem);
 static bool scx_cgroup_enabled;
 
+void scx_tg_init(struct task_group *tg)
+{
+	tg->scx_weight = CGROUP_WEIGHT_DFL;
+}
+
 int scx_tg_online(struct task_group *tg)
 {
 	struct scx_sched *sch = scx_root;
diff --git a/kernel/sched/ext.h b/kernel/sched/ext.h
index 6e5072f57771..a75835c23f15 100644
--- a/kernel/sched/ext.h
+++ b/kernel/sched/ext.h
@@ -79,6 +79,7 @@ static inline void scx_update_idle(struct rq *rq, bool idle, bool do_notify) {}
 
 #ifdef CONFIG_CGROUP_SCHED
 #ifdef CONFIG_EXT_GROUP_SCHED
+void scx_tg_init(struct task_group *tg);
 int scx_tg_online(struct task_group *tg);
 void scx_tg_offline(struct task_group *tg);
 int scx_cgroup_can_attach(struct cgroup_taskset *tset);
@@ -88,6 +89,7 @@ void scx_cgroup_cancel_attach(struct cgroup_taskset *tset);
 void scx_group_set_weight(struct task_group *tg, unsigned long cgrp_weight);
 void scx_group_set_idle(struct task_group *tg, bool idle);
 #else	/* CONFIG_EXT_GROUP_SCHED */
+static inline void scx_tg_init(struct task_group *tg) {}
 static inline int scx_tg_online(struct task_group *tg) { return 0; }
 static inline void scx_tg_offline(struct task_group *tg) {}
 static inline int scx_cgroup_can_attach(struct cgroup_taskset *tset) { return 0; }

From 261dce3d64021e7ec828a17b4975ce9182e54ceb Mon Sep 17 00:00:00 2001
From: Chuyi Zhou <zhouchuyi@bytedance.com>
Date: Tue, 17 Jun 2025 12:42:16 +0800
Subject: [PATCH 0482/1334] workqueue: Initialize wq_isolated_cpumask in
 workqueue_init_early()

Now when isolcpus is enabled via the cmdline, wq_isolated_cpumask does
not include these isolated CPUs, even wq_unbound_cpumask has already
excluded them. It is only when we successfully configure an isolate cpuset
partition that wq_isolated_cpumask gets overwritten by
workqueue_unbound_exclude_cpumask(), including both the cmdline-specified
isolated CPUs and the isolated CPUs within the cpuset partitions.

Fix this issue by initializing wq_isolated_cpumask properly in
workqueue_init_early().

Fixes: fe28f631fa94 ("workqueue: Add workqueue_unbound_exclude_cpumask() to exclude CPUs from wq_unbound_cpumask")
Signed-off-by: Chuyi Zhou <zhouchuyi@bytedance.com>
Reviewed-by: Waiman Long <longman@redhat.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 kernel/workqueue.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 97f37b5bae66..9f9148075828 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -7767,7 +7767,8 @@ void __init workqueue_init_early(void)
 		restrict_unbound_cpumask("workqueue.unbound_cpus", &wq_cmdline_cpumask);
 
 	cpumask_copy(wq_requested_unbound_cpumask, wq_unbound_cpumask);
-
+	cpumask_andnot(wq_isolated_cpumask, cpu_possible_mask,
+						housekeeping_cpumask(HK_TYPE_DOMAIN));
 	pwq_cache = KMEM_CACHE(pool_workqueue, SLAB_PANIC);
 
 	unbound_wq_update_pwq_attrs_buf = alloc_workqueue_attrs();

From bb6b4143503750318a3f85975186db899a3caaf2 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Thu, 12 Jun 2025 18:08:40 -0300
Subject: [PATCH 0483/1334] tools arch amd ibs: Sync ibs.h with the kernel
 sources

To pick up the changes from:

  861c6b1185fbb2e3 ("x86/platform/amd: Add standard header guards to <asm/amd/ibs.h>")

A small change to tools/perf/check-headers.sh was made to cope with the
move of this header done in:

  3846389c03a85188 ("x86/platform/amd: Move the <asm/amd-ibs.h> header to <asm/amd/ibs.h>")

That don't result in any changes in the tools, just address this perf
build warning:

Warning: Kernel ABI header differences:
  diff -u tools/arch/x86/include/asm/amd/ibs.h arch/x86/include/asm/amd/ibs.h

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: James Clark <james.clark@linaro.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/r/aEtCi0pup5FEwnzn@x1
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/arch/x86/include/asm/amd/ibs.h | 5 +++++
 tools/perf/check-headers.sh          | 2 +-
 2 files changed, 6 insertions(+), 1 deletion(-)

diff --git a/tools/arch/x86/include/asm/amd/ibs.h b/tools/arch/x86/include/asm/amd/ibs.h
index 300b6e0765b2..cbce54fec7b9 100644
--- a/tools/arch/x86/include/asm/amd/ibs.h
+++ b/tools/arch/x86/include/asm/amd/ibs.h
@@ -1,4 +1,7 @@
 /* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_X86_AMD_IBS_H
+#define _ASM_X86_AMD_IBS_H
+
 /*
  * From PPR Vol 1 for AMD Family 19h Model 01h B1
  * 55898 Rev 0.35 - Feb 5, 2021
@@ -151,3 +154,5 @@ struct perf_ibs_data {
 	};
 	u64		regs[MSR_AMD64_IBS_REG_COUNT_MAX];
 };
+
+#endif /* _ASM_X86_AMD_IBS_H */
diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh
index e9fab20e9330..8085e4d1d8af 100755
--- a/tools/perf/check-headers.sh
+++ b/tools/perf/check-headers.sh
@@ -186,7 +186,7 @@ done
 # diff with extra ignore lines
 check arch/x86/lib/memcpy_64.S        '-I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>" -I"^SYM_FUNC_START\(_LOCAL\)*(memcpy_\(erms\|orig\))" -I"^#include <linux/cfi_types.h>"'
 check arch/x86/lib/memset_64.S        '-I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>" -I"^SYM_FUNC_START\(_LOCAL\)*(memset_\(erms\|orig\))"'
-check arch/x86/include/asm/amd/ibs.h  '-I "^#include [<\"]\(asm/\)*msr-index.h"'
+check arch/x86/include/asm/amd/ibs.h  '-I "^#include .*/msr-index.h"'
 check arch/arm64/include/asm/cputype.h '-I "^#include [<\"]\(asm/\)*sysreg.h"'
 check include/linux/unaligned.h '-I "^#include <linux/unaligned/packed_struct.h>" -I "^#include <asm/byteorder.h>" -I "^#pragma GCC diagnostic"'
 check include/uapi/asm-generic/mman.h '-I "^#include <\(uapi/\)*asm-generic/mman-common\(-tools\)*.h>"'

From fc92099902fbf21000554678a47654b029c15a4d Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Thu, 12 Jun 2025 12:36:06 -0300
Subject: [PATCH 0484/1334] tools headers: Synchronize linux/bits.h with the
 kernel sources

To pick up the changes in this cset:

  1e7933a575ed8af4 ("uapi: Revert "bitops: avoid integer overflow in GENMASK(_ULL)"")
  5b572e8a9f3dcd6e ("bits: introduce fixed-type BIT_U*()")
  19408200c094858d ("bits: introduce fixed-type GENMASK_U*()")
  31299a5e02112411 ("bits: add comments and newlines to #if, #else and #endif directives")

This addresses these perf build warnings:

  Warning: Kernel ABI header differences:
    diff -u tools/include/linux/bits.h include/linux/bits.h

Please see tools/include/uapi/README for further details.

Acked-by: Vincent Mailhol <mailhol.vincent@wanadoo.fr>
Cc: I Hsin Cheng <richard120310@gmail.com>
Cc: Yury Norov <yury.norov@gmail.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Lucas De Marchi <lucas.demarchi@intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Yury Norov <yury.norov@gmail.com>
Link: https://lore.kernel.org/r/aEr0ZJ60EbshEy6p@x1
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 include/uapi/linux/bits.h  |  4 +--
 tools/include/linux/bits.h | 57 ++++++++++++++++++++++++++++++++++++--
 2 files changed, 57 insertions(+), 4 deletions(-)

diff --git a/include/uapi/linux/bits.h b/include/uapi/linux/bits.h
index a04afef9efca..682b406e1067 100644
--- a/include/uapi/linux/bits.h
+++ b/include/uapi/linux/bits.h
@@ -4,9 +4,9 @@
 #ifndef _UAPI_LINUX_BITS_H
 #define _UAPI_LINUX_BITS_H
 
-#define __GENMASK(h, l) (((~_UL(0)) << (l)) & (~_UL(0) >> (__BITS_PER_LONG - 1 - (h))))
+#define __GENMASK(h, l) (((~_UL(0)) << (l)) & (~_UL(0) >> (BITS_PER_LONG - 1 - (h))))
 
-#define __GENMASK_ULL(h, l) (((~_ULL(0)) << (l)) & (~_ULL(0) >> (__BITS_PER_LONG_LONG - 1 - (h))))
+#define __GENMASK_ULL(h, l) (((~_ULL(0)) << (l)) & (~_ULL(0) >> (BITS_PER_LONG_LONG - 1 - (h))))
 
 #define __GENMASK_U128(h, l) \
 	((_BIT128((h)) << 1) - (_BIT128(l)))
diff --git a/tools/include/linux/bits.h b/tools/include/linux/bits.h
index 14fd0ca9a6cd..7ad056219115 100644
--- a/tools/include/linux/bits.h
+++ b/tools/include/linux/bits.h
@@ -12,6 +12,7 @@
 #define BIT_ULL_MASK(nr)	(ULL(1) << ((nr) % BITS_PER_LONG_LONG))
 #define BIT_ULL_WORD(nr)	((nr) / BITS_PER_LONG_LONG)
 #define BITS_PER_BYTE		8
+#define BITS_PER_TYPE(type)	(sizeof(type) * BITS_PER_BYTE)
 
 /*
  * Create a contiguous bitmask starting at bit position @l and ending at
@@ -19,16 +20,68 @@
  * GENMASK_ULL(39, 21) gives us the 64bit vector 0x000000ffffe00000.
  */
 #if !defined(__ASSEMBLY__)
+
+/*
+ * Missing asm support
+ *
+ * GENMASK_U*() and BIT_U*() depend on BITS_PER_TYPE() which relies on sizeof(),
+ * something not available in asm. Nevertheless, fixed width integers is a C
+ * concept. Assembly code can rely on the long and long long versions instead.
+ */
+
 #include <linux/build_bug.h>
 #include <linux/compiler.h>
+#include <linux/overflow.h>
+
 #define GENMASK_INPUT_CHECK(h, l) BUILD_BUG_ON_ZERO(const_true((l) > (h)))
-#else
+
+/*
+ * Generate a mask for the specified type @t. Additional checks are made to
+ * guarantee the value returned fits in that type, relying on
+ * -Wshift-count-overflow compiler check to detect incompatible arguments.
+ * For example, all these create build errors or warnings:
+ *
+ * - GENMASK(15, 20): wrong argument order
+ * - GENMASK(72, 15): doesn't fit unsigned long
+ * - GENMASK_U32(33, 15): doesn't fit in a u32
+ */
+#define GENMASK_TYPE(t, h, l)					\
+	((t)(GENMASK_INPUT_CHECK(h, l) +			\
+	     (type_max(t) << (l) &				\
+	      type_max(t) >> (BITS_PER_TYPE(t) - 1 - (h)))))
+
+#define GENMASK_U8(h, l)	GENMASK_TYPE(u8, h, l)
+#define GENMASK_U16(h, l)	GENMASK_TYPE(u16, h, l)
+#define GENMASK_U32(h, l)	GENMASK_TYPE(u32, h, l)
+#define GENMASK_U64(h, l)	GENMASK_TYPE(u64, h, l)
+
+/*
+ * Fixed-type variants of BIT(), with additional checks like GENMASK_TYPE(). The
+ * following examples generate compiler warnings due to -Wshift-count-overflow:
+ *
+ * - BIT_U8(8)
+ * - BIT_U32(-1)
+ * - BIT_U32(40)
+ */
+#define BIT_INPUT_CHECK(type, nr) \
+	BUILD_BUG_ON_ZERO(const_true((nr) >= BITS_PER_TYPE(type)))
+
+#define BIT_TYPE(type, nr) ((type)(BIT_INPUT_CHECK(type, nr) + BIT_ULL(nr)))
+
+#define BIT_U8(nr)	BIT_TYPE(u8, nr)
+#define BIT_U16(nr)	BIT_TYPE(u16, nr)
+#define BIT_U32(nr)	BIT_TYPE(u32, nr)
+#define BIT_U64(nr)	BIT_TYPE(u64, nr)
+
+#else /* defined(__ASSEMBLY__) */
+
 /*
  * BUILD_BUG_ON_ZERO is not available in h files included from asm files,
  * disable the input check if that is the case.
  */
 #define GENMASK_INPUT_CHECK(h, l) 0
-#endif
+
+#endif /* !defined(__ASSEMBLY__) */
 
 #define GENMASK(h, l) \
 	(GENMASK_INPUT_CHECK(h, l) + __GENMASK(h, l))

From ebec62bc7ec435b475722a5467d67c720a1ad79f Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Fri, 13 Jun 2025 17:41:05 -0700
Subject: [PATCH 0485/1334] perf evsel: Missed close() when probing hybrid core
 PMUs

Add missing close() to avoid leaking perf events.

In past perfs this mattered little as the function was just used by 'perf
list'.

As the function is now used to detect hybrid PMUs leaking the perf event
is somewhat more painful.

Fixes: b41f1cec91c37eee ("perf list: Skip unsupported events")
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiapeng Chong <jiapeng.chong@linux.alibaba.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Michael Petlan <mpetlan@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Namhyung Kim <namhyung.kim@lge.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Tiezhu Yang <yangtiezhu@loongson.cn>
Link: https://lore.kernel.org/r/20250614004108.1650988-2-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/print-events.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/perf/util/print-events.c b/tools/perf/util/print-events.c
index a786cbfb0ff5..83aaf7cda635 100644
--- a/tools/perf/util/print-events.c
+++ b/tools/perf/util/print-events.c
@@ -268,6 +268,7 @@ bool is_event_supported(u8 type, u64 config)
 			ret = evsel__open(evsel, NULL, tmap) >= 0;
 		}
 
+		evsel__close(evsel);
 		evsel__delete(evsel);
 	}
 

From c44f79cbd305e7a8c2548b4fa3b42b865611bada Mon Sep 17 00:00:00 2001
From: Chen-Yu Tsai <wenst@chromium.org>
Date: Tue, 17 Jun 2025 16:19:58 +0800
Subject: [PATCH 0486/1334] dt-bindings: HID: i2c-hid: elan: Introduce Elan
 eKTH8D18

The Elan eKTH8D18 touchscreen controller is an I2C HID device with a
longer boot-up time. Power sequence timing wise it is compatible with
the eKTH6A12NAY, with a power-on delay of at least 5ms, 20ms
out-of-reset for I2C ack response, and 150ms out-of-reset for I2C HID
enumeration, both shorter than what the eKTH6A12NAY requires.
Enumeration and subsequent operation follows the I2C HID standard.

Add a compatible string for it with the ekth6a12nay one as a fallback.
No enum was used as it is rare to actually add new entries. These
chips are commonly completely backward compatible, and unless the
power sequencing delays change, there is no real effort being made to
keep track of new parts, which come out constantly.

Also drop the constraints on the I2C address since it's not really
part of the binding.

Reviewed-by: Douglas Anderson <dianders@chromium.org>
Reviewed-by: Rob Herring (Arm) <robh@kernel.org>
Reviewed-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
Signed-off-by: Chen-Yu Tsai <wenst@chromium.org>
Link: https://lore.kernel.org/r/20250617082004.1653492-2-wenst@chromium.org
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 .../devicetree/bindings/input/elan,ekth6915.yaml     | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/Documentation/devicetree/bindings/input/elan,ekth6915.yaml b/Documentation/devicetree/bindings/input/elan,ekth6915.yaml
index cb3e1801b0d3..0840e4ab28b7 100644
--- a/Documentation/devicetree/bindings/input/elan,ekth6915.yaml
+++ b/Documentation/devicetree/bindings/input/elan,ekth6915.yaml
@@ -4,14 +4,14 @@
 $id: http://devicetree.org/schemas/input/elan,ekth6915.yaml#
 $schema: http://devicetree.org/meta-schemas/core.yaml#
 
-title: Elan eKTH6915 touchscreen controller
+title: Elan I2C-HID touchscreen controllers
 
 maintainers:
   - Douglas Anderson <dianders@chromium.org>
 
 description:
-  Supports the Elan eKTH6915 touchscreen controller.
-  This touchscreen controller uses the i2c-hid protocol with a reset GPIO.
+  Supports the Elan eKTH6915 and other I2C-HID touchscreen controllers.
+  These touchscreen controller use the i2c-hid protocol with a reset GPIO.
 
 allOf:
   - $ref: /schemas/input/touchscreen/touchscreen.yaml#
@@ -23,12 +23,14 @@ properties:
           - enum:
               - elan,ekth5015m
           - const: elan,ekth6915
+      - items:
+          - const: elan,ekth8d18
+          - const: elan,ekth6a12nay
       - enum:
           - elan,ekth6915
           - elan,ekth6a12nay
 
-  reg:
-    const: 0x10
+  reg: true
 
   interrupts:
     maxItems: 1

From 155c1e5a92bebff36cc033c9eb9bb3f76712af44 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Fri, 13 Jun 2025 09:16:54 +0200
Subject: [PATCH 0487/1334] Input: Fully open-code compatible for grepping

It is very useful to find driver implementing compatibles with `git grep
compatible`, so driver should not use defines for that string, even if
this means string will be effectively duplicated.

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20250613071653.46809-2-krzysztof.kozlowski@linaro.org
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/misc/gpio-beeper.c        | 2 +-
 drivers/input/touchscreen/melfas_mip4.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/input/misc/gpio-beeper.c b/drivers/input/misc/gpio-beeper.c
index d2d2954e2f79..3d65cb4f4ef3 100644
--- a/drivers/input/misc/gpio-beeper.c
+++ b/drivers/input/misc/gpio-beeper.c
@@ -94,7 +94,7 @@ static int gpio_beeper_probe(struct platform_device *pdev)
 
 #ifdef CONFIG_OF
 static const struct of_device_id gpio_beeper_of_match[] = {
-	{ .compatible = BEEPER_MODNAME, },
+	{ .compatible = "gpio-beeper", },
 	{ }
 };
 MODULE_DEVICE_TABLE(of, gpio_beeper_of_match);
diff --git a/drivers/input/touchscreen/melfas_mip4.c b/drivers/input/touchscreen/melfas_mip4.c
index a6946e3d8376..869884219908 100644
--- a/drivers/input/touchscreen/melfas_mip4.c
+++ b/drivers/input/touchscreen/melfas_mip4.c
@@ -1554,7 +1554,7 @@ static DEFINE_SIMPLE_DEV_PM_OPS(mip4_pm_ops, mip4_suspend, mip4_resume);
 
 #ifdef CONFIG_OF
 static const struct of_device_id mip4_of_match[] = {
-	{ .compatible = "melfas,"MIP4_DEVICE_NAME, },
+	{ .compatible = "melfas,mip4_ts", },
 	{ },
 };
 MODULE_DEVICE_TABLE(of, mip4_of_match);

From a89f5fae998bdc4d0505306f93844c9ae059d50c Mon Sep 17 00:00:00 2001
From: Namjae Jeon <linkinjeon@kernel.org>
Date: Tue, 10 Jun 2025 18:52:56 +0900
Subject: [PATCH 0488/1334] ksmbd: add free_transport ops in ksmbd connection

free_transport function for tcp connection can be called from smbdirect.
It will cause kernel oops. This patch add free_transport ops in ksmbd
connection, and add each free_transports for tcp and smbdirect.

Fixes: 21a4e47578d4 ("ksmbd: fix use-after-free in __smb2_lease_break_noti()")
Reviewed-by: Stefan Metzmacher <metze@samba.org>
Signed-off-by: Namjae Jeon <linkinjeon@kernel.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/server/connection.c     |  2 +-
 fs/smb/server/connection.h     |  1 +
 fs/smb/server/transport_rdma.c | 10 ++++++++--
 fs/smb/server/transport_tcp.c  |  3 ++-
 4 files changed, 12 insertions(+), 4 deletions(-)

diff --git a/fs/smb/server/connection.c b/fs/smb/server/connection.c
index 83764c230e9d..3f04a2977ba8 100644
--- a/fs/smb/server/connection.c
+++ b/fs/smb/server/connection.c
@@ -40,7 +40,7 @@ void ksmbd_conn_free(struct ksmbd_conn *conn)
 	kvfree(conn->request_buf);
 	kfree(conn->preauth_info);
 	if (atomic_dec_and_test(&conn->refcnt)) {
-		ksmbd_free_transport(conn->transport);
+		conn->transport->ops->free_transport(conn->transport);
 		kfree(conn);
 	}
 }
diff --git a/fs/smb/server/connection.h b/fs/smb/server/connection.h
index 6efed923bd68..dd3e0e3f7bf0 100644
--- a/fs/smb/server/connection.h
+++ b/fs/smb/server/connection.h
@@ -133,6 +133,7 @@ struct ksmbd_transport_ops {
 			  void *buf, unsigned int len,
 			  struct smb2_buffer_desc_v1 *desc,
 			  unsigned int desc_len);
+	void (*free_transport)(struct ksmbd_transport *kt);
 };
 
 struct ksmbd_transport {
diff --git a/fs/smb/server/transport_rdma.c b/fs/smb/server/transport_rdma.c
index 4998df04ab95..64a428a06ace 100644
--- a/fs/smb/server/transport_rdma.c
+++ b/fs/smb/server/transport_rdma.c
@@ -159,7 +159,8 @@ struct smb_direct_transport {
 };
 
 #define KSMBD_TRANS(t) ((struct ksmbd_transport *)&((t)->transport))
-
+#define SMBD_TRANS(t)	((struct smb_direct_transport *)container_of(t, \
+				struct smb_direct_transport, transport))
 enum {
 	SMB_DIRECT_MSG_NEGOTIATE_REQ = 0,
 	SMB_DIRECT_MSG_DATA_TRANSFER
@@ -410,6 +411,11 @@ err:
 	return NULL;
 }
 
+static void smb_direct_free_transport(struct ksmbd_transport *kt)
+{
+	kfree(SMBD_TRANS(kt));
+}
+
 static void free_transport(struct smb_direct_transport *t)
 {
 	struct smb_direct_recvmsg *recvmsg;
@@ -455,7 +461,6 @@ static void free_transport(struct smb_direct_transport *t)
 
 	smb_direct_destroy_pools(t);
 	ksmbd_conn_free(KSMBD_TRANS(t)->conn);
-	kfree(t);
 }
 
 static struct smb_direct_sendmsg
@@ -2281,4 +2286,5 @@ static const struct ksmbd_transport_ops ksmbd_smb_direct_transport_ops = {
 	.read		= smb_direct_read,
 	.rdma_read	= smb_direct_rdma_read,
 	.rdma_write	= smb_direct_rdma_write,
+	.free_transport = smb_direct_free_transport,
 };
diff --git a/fs/smb/server/transport_tcp.c b/fs/smb/server/transport_tcp.c
index abedf510899a..4e9f98db9ff4 100644
--- a/fs/smb/server/transport_tcp.c
+++ b/fs/smb/server/transport_tcp.c
@@ -93,7 +93,7 @@ static struct tcp_transport *alloc_transport(struct socket *client_sk)
 	return t;
 }
 
-void ksmbd_free_transport(struct ksmbd_transport *kt)
+static void ksmbd_tcp_free_transport(struct ksmbd_transport *kt)
 {
 	struct tcp_transport *t = TCP_TRANS(kt);
 
@@ -656,4 +656,5 @@ static const struct ksmbd_transport_ops ksmbd_tcp_transport_ops = {
 	.read		= ksmbd_tcp_read,
 	.writev		= ksmbd_tcp_writev,
 	.disconnect	= ksmbd_tcp_disconnect,
+	.free_transport = ksmbd_tcp_free_transport,
 };

From 7ac5b66acafcc9292fb935d7e03790f2b8b2dc0e Mon Sep 17 00:00:00 2001
From: Namjae Jeon <linkinjeon@kernel.org>
Date: Fri, 13 Jun 2025 10:12:43 +0900
Subject: [PATCH 0489/1334] ksmbd: fix null pointer dereference in
 destroy_previous_session

If client set ->PreviousSessionId on kerberos session setup stage,
NULL pointer dereference error will happen. Since sess->user is not
set yet, It can pass the user argument as NULL to destroy_previous_session.
sess->user will be set in ksmbd_krb5_authenticate(). So this patch move
calling destroy_previous_session() after ksmbd_krb5_authenticate().

Cc: stable@vger.kernel.org
Reported-by: zdi-disclosures@trendmicro.com # ZDI-CAN-27391
Signed-off-by: Namjae Jeon <linkinjeon@kernel.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/server/smb2pdu.c | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c
index 1a308171b599..6645d8fd772e 100644
--- a/fs/smb/server/smb2pdu.c
+++ b/fs/smb/server/smb2pdu.c
@@ -1607,17 +1607,18 @@ static int krb5_authenticate(struct ksmbd_work *work,
 	out_len = work->response_sz -
 		(le16_to_cpu(rsp->SecurityBufferOffset) + 4);
 
-	/* Check previous session */
-	prev_sess_id = le64_to_cpu(req->PreviousSessionId);
-	if (prev_sess_id && prev_sess_id != sess->id)
-		destroy_previous_session(conn, sess->user, prev_sess_id);
-
 	retval = ksmbd_krb5_authenticate(sess, in_blob, in_len,
 					 out_blob, &out_len);
 	if (retval) {
 		ksmbd_debug(SMB, "krb5 authentication failed\n");
 		return -EINVAL;
 	}
+
+	/* Check previous session */
+	prev_sess_id = le64_to_cpu(req->PreviousSessionId);
+	if (prev_sess_id && prev_sess_id != sess->id)
+		destroy_previous_session(conn, sess->user, prev_sess_id);
+
 	rsp->SecurityBufferLength = cpu_to_le16(out_len);
 
 	if ((conn->sign || server_conf.enforced_signing) ||

From 4ea0bb8aaedfad8e695429cda6bd1c8b0dad0844 Mon Sep 17 00:00:00 2001
From: Namjae Jeon <linkinjeon@kernel.org>
Date: Fri, 13 Jun 2025 11:51:29 +0900
Subject: [PATCH 0490/1334] ksmbd: handle set/get info file for streamed file

The bug only appears when:
 - windows 11 copies a file that has an alternate data stream
 - streams_xattr is enabled on the share configuration.

Microsoft Edge adds a ZoneIdentifier data stream containing the URL
for files it downloads.

Another way to create a test file:
 - open cmd.exe
 - echo "hello from default data stream" > hello.txt
 - echo "hello again from ads" > hello.txt:ads.txt

If you open the file using notepad, we'll see the first message.
If you run "notepad hello.txt:ads.txt" in cmd.exe, we should see
the second message.

dir /s /r should least all streams for the file.

The truncation happens because the windows 11 client sends
a SetInfo/EndOfFile message on the ADS, but it is instead applied
on the main file, because we don't check fp->stream.

When receiving set/get info file for a stream file, Change to process
requests using stream position and size.
Truncate is unnecessary for stream files, so we skip
set_file_allocation_info and set_end_of_file_info operations.

Reported-by: Marios Makassikis <mmakassikis@freebox.fr>
Signed-off-by: Namjae Jeon <linkinjeon@kernel.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/server/smb2pdu.c   | 63 +++++++++++++++++++++++++++++++--------
 fs/smb/server/vfs.c       |  5 ++--
 fs/smb/server/vfs_cache.h |  1 +
 3 files changed, 54 insertions(+), 15 deletions(-)

diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c
index 6645d8fd772e..fafa86273f12 100644
--- a/fs/smb/server/smb2pdu.c
+++ b/fs/smb/server/smb2pdu.c
@@ -4872,8 +4872,13 @@ static int get_file_standard_info(struct smb2_query_info_rsp *rsp,
 	sinfo = (struct smb2_file_standard_info *)rsp->Buffer;
 	delete_pending = ksmbd_inode_pending_delete(fp);
 
-	sinfo->AllocationSize = cpu_to_le64(stat.blocks << 9);
-	sinfo->EndOfFile = S_ISDIR(stat.mode) ? 0 : cpu_to_le64(stat.size);
+	if (ksmbd_stream_fd(fp) == false) {
+		sinfo->AllocationSize = cpu_to_le64(stat.blocks << 9);
+		sinfo->EndOfFile = S_ISDIR(stat.mode) ? 0 : cpu_to_le64(stat.size);
+	} else {
+		sinfo->AllocationSize = cpu_to_le64(fp->stream.size);
+		sinfo->EndOfFile = cpu_to_le64(fp->stream.size);
+	}
 	sinfo->NumberOfLinks = cpu_to_le32(get_nlink(&stat) - delete_pending);
 	sinfo->DeletePending = delete_pending;
 	sinfo->Directory = S_ISDIR(stat.mode) ? 1 : 0;
@@ -4936,9 +4941,14 @@ static int get_file_all_info(struct ksmbd_work *work,
 	file_info->ChangeTime = cpu_to_le64(time);
 	file_info->Attributes = fp->f_ci->m_fattr;
 	file_info->Pad1 = 0;
-	file_info->AllocationSize =
-		cpu_to_le64(stat.blocks << 9);
-	file_info->EndOfFile = S_ISDIR(stat.mode) ? 0 : cpu_to_le64(stat.size);
+	if (ksmbd_stream_fd(fp) == false) {
+		file_info->AllocationSize =
+			cpu_to_le64(stat.blocks << 9);
+		file_info->EndOfFile = S_ISDIR(stat.mode) ? 0 : cpu_to_le64(stat.size);
+	} else {
+		file_info->AllocationSize = cpu_to_le64(fp->stream.size);
+		file_info->EndOfFile = cpu_to_le64(fp->stream.size);
+	}
 	file_info->NumberOfLinks =
 			cpu_to_le32(get_nlink(&stat) - delete_pending);
 	file_info->DeletePending = delete_pending;
@@ -4947,7 +4957,10 @@ static int get_file_all_info(struct ksmbd_work *work,
 	file_info->IndexNumber = cpu_to_le64(stat.ino);
 	file_info->EASize = 0;
 	file_info->AccessFlags = fp->daccess;
-	file_info->CurrentByteOffset = cpu_to_le64(fp->filp->f_pos);
+	if (ksmbd_stream_fd(fp) == false)
+		file_info->CurrentByteOffset = cpu_to_le64(fp->filp->f_pos);
+	else
+		file_info->CurrentByteOffset = cpu_to_le64(fp->stream.pos);
 	file_info->Mode = fp->coption;
 	file_info->AlignmentRequirement = 0;
 	conv_len = smbConvertToUTF16((__le16 *)file_info->FileName, filename,
@@ -5135,8 +5148,13 @@ static int get_file_network_open_info(struct smb2_query_info_rsp *rsp,
 	time = ksmbd_UnixTimeToNT(stat.ctime);
 	file_info->ChangeTime = cpu_to_le64(time);
 	file_info->Attributes = fp->f_ci->m_fattr;
-	file_info->AllocationSize = cpu_to_le64(stat.blocks << 9);
-	file_info->EndOfFile = S_ISDIR(stat.mode) ? 0 : cpu_to_le64(stat.size);
+	if (ksmbd_stream_fd(fp) == false) {
+		file_info->AllocationSize = cpu_to_le64(stat.blocks << 9);
+		file_info->EndOfFile = S_ISDIR(stat.mode) ? 0 : cpu_to_le64(stat.size);
+	} else {
+		file_info->AllocationSize = cpu_to_le64(fp->stream.size);
+		file_info->EndOfFile = cpu_to_le64(fp->stream.size);
+	}
 	file_info->Reserved = cpu_to_le32(0);
 	rsp->OutputBufferLength =
 		cpu_to_le32(sizeof(struct smb2_file_ntwrk_info));
@@ -5159,7 +5177,11 @@ static void get_file_position_info(struct smb2_query_info_rsp *rsp,
 	struct smb2_file_pos_info *file_info;
 
 	file_info = (struct smb2_file_pos_info *)rsp->Buffer;
-	file_info->CurrentByteOffset = cpu_to_le64(fp->filp->f_pos);
+	if (ksmbd_stream_fd(fp) == false)
+		file_info->CurrentByteOffset = cpu_to_le64(fp->filp->f_pos);
+	else
+		file_info->CurrentByteOffset = cpu_to_le64(fp->stream.pos);
+
 	rsp->OutputBufferLength =
 		cpu_to_le32(sizeof(struct smb2_file_pos_info));
 }
@@ -5248,8 +5270,13 @@ static int find_file_posix_info(struct smb2_query_info_rsp *rsp,
 	file_info->ChangeTime = cpu_to_le64(time);
 	file_info->DosAttributes = fp->f_ci->m_fattr;
 	file_info->Inode = cpu_to_le64(stat.ino);
-	file_info->EndOfFile = cpu_to_le64(stat.size);
-	file_info->AllocationSize = cpu_to_le64(stat.blocks << 9);
+	if (ksmbd_stream_fd(fp) == false) {
+		file_info->EndOfFile = cpu_to_le64(stat.size);
+		file_info->AllocationSize = cpu_to_le64(stat.blocks << 9);
+	} else {
+		file_info->EndOfFile = cpu_to_le64(fp->stream.size);
+		file_info->AllocationSize = cpu_to_le64(fp->stream.size);
+	}
 	file_info->HardLinks = cpu_to_le32(stat.nlink);
 	file_info->Mode = cpu_to_le32(stat.mode & 0777);
 	switch (stat.mode & S_IFMT) {
@@ -6191,6 +6218,9 @@ static int set_file_allocation_info(struct ksmbd_work *work,
 	if (!(fp->daccess & FILE_WRITE_DATA_LE))
 		return -EACCES;
 
+	if (ksmbd_stream_fd(fp) == true)
+		return 0;
+
 	rc = vfs_getattr(&fp->filp->f_path, &stat, STATX_BASIC_STATS,
 			 AT_STATX_SYNC_AS_STAT);
 	if (rc)
@@ -6249,7 +6279,8 @@ static int set_end_of_file_info(struct ksmbd_work *work, struct ksmbd_file *fp,
 	 * truncate of some filesystem like FAT32 fill zero data in
 	 * truncated range.
 	 */
-	if (inode->i_sb->s_magic != MSDOS_SUPER_MAGIC) {
+	if (inode->i_sb->s_magic != MSDOS_SUPER_MAGIC &&
+	    ksmbd_stream_fd(fp) == false) {
 		ksmbd_debug(SMB, "truncated to newsize %lld\n", newsize);
 		rc = ksmbd_vfs_truncate(work, fp, newsize);
 		if (rc) {
@@ -6322,7 +6353,13 @@ static int set_file_position_info(struct ksmbd_file *fp,
 		return -EINVAL;
 	}
 
-	fp->filp->f_pos = current_byte_offset;
+	if (ksmbd_stream_fd(fp) == false)
+		fp->filp->f_pos = current_byte_offset;
+	else {
+		if (current_byte_offset > XATTR_SIZE_MAX)
+			current_byte_offset = XATTR_SIZE_MAX;
+		fp->stream.pos = current_byte_offset;
+	}
 	return 0;
 }
 
diff --git a/fs/smb/server/vfs.c b/fs/smb/server/vfs.c
index ba45e809555a..0f3aad12e495 100644
--- a/fs/smb/server/vfs.c
+++ b/fs/smb/server/vfs.c
@@ -293,6 +293,7 @@ static int ksmbd_vfs_stream_read(struct ksmbd_file *fp, char *buf, loff_t *pos,
 
 	if (v_len - *pos < count)
 		count = v_len - *pos;
+	fp->stream.pos = v_len;
 
 	memcpy(buf, &stream_buf[*pos], count);
 
@@ -456,8 +457,8 @@ static int ksmbd_vfs_stream_write(struct ksmbd_file *fp, char *buf, loff_t *pos,
 				 true);
 	if (err < 0)
 		goto out;
-
-	fp->filp->f_pos = *pos;
+	else
+		fp->stream.pos = size;
 	err = 0;
 out:
 	kvfree(stream_buf);
diff --git a/fs/smb/server/vfs_cache.h b/fs/smb/server/vfs_cache.h
index 5bbb179736c2..0708155b5caf 100644
--- a/fs/smb/server/vfs_cache.h
+++ b/fs/smb/server/vfs_cache.h
@@ -44,6 +44,7 @@ struct ksmbd_lock {
 struct stream {
 	char *name;
 	ssize_t size;
+	loff_t pos;
 };
 
 struct ksmbd_inode {

From 19f4422d485b2d0a935117a1a16015328f99be25 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Fri, 13 Jun 2025 17:41:04 -0700
Subject: [PATCH 0491/1334] perf test: Directory file descriptor leak

Add missed close when iterating over the script directories.

Fixes: f3295f5b067d3c26 ("perf tests: Use scandirat for shell script finding")
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiapeng Chong <jiapeng.chong@linux.alibaba.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Michael Petlan <mpetlan@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Tiezhu Yang <yangtiezhu@loongson.cn>
Link: https://lore.kernel.org/r/20250614004108.1650988-1-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/tests-scripts.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/perf/tests/tests-scripts.c b/tools/perf/tests/tests-scripts.c
index 1d5759d08141..3a2a8438f9af 100644
--- a/tools/perf/tests/tests-scripts.c
+++ b/tools/perf/tests/tests-scripts.c
@@ -260,6 +260,7 @@ static void append_scripts_in_dir(int dir_fd,
 			continue; /* Skip scripts that have a separate driver. */
 		fd = openat(dir_fd, ent->d_name, O_PATH);
 		append_scripts_in_dir(fd, result, result_sz);
+		close(fd);
 	}
 	for (i = 0; i < n_dirs; i++) /* Clean up */
 		zfree(&entlist[i]);

From 1c85c94b3767895d70b7a5a49b111f974f5660ec Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Mon, 16 Jun 2025 14:33:17 -0300
Subject: [PATCH 0492/1334] perf bench futex: Fix prctl include in musl libc

Namhyung Kim reported:

  I've updated the perf-tools-next to v6.16-rc1 and found a build error
  like below on alpine linux 3.18.

    In file included from bench/futex.c:6:
    /usr/include/sys/prctl.h:88:8: error: redefinition of 'struct prctl_mm_map'
       88 | struct prctl_mm_map {
          |        ^~~~~~~~~~~~
    In file included from bench/futex.c:5:
    /linux/tools/include/uapi/linux/prctl.h:134:8: note: originally defined here
      134 | struct prctl_mm_map {
          |        ^~~~~~~~~~~~
    make[4]: *** [/linux/tools/build/Makefile.build:86: /build/bench/futex.o] Error 1

  git bisect says it's the first commit introduced the failure.

So both /usr/include/sys/prctl.h and /linux/tools/include/uapi/linux/prctl.h
provide struct prctl_mm_map but their include guard must be different.

/usr/include/sys/prctl.h provided by glibc contains the
prctl() declaration. It includes also linux/prctl.h.

The /usr/include/sys/prctl.h on alpine linux is different. This is
probably coming from musl. It contains the PR_* definition and the
prctl() declaration.  So it clashes here because now the one struct is
available twice.

The man page for prctl(2) says:

|       #include <linux/prctl.h>  /* Definition of PR_* constants */
|       #include <sys/prctl.h>

so musl doesn't follow this.

So don't include linux/prctl.h explicitely and add some new defines
needed if they aren't available.

Acked-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Reported-by: Namhyung Kim <namhyung@kernel.org>
Closes: https://lore.kernel.org/r/20250611092542.F4ooE2FL@linutronix.de
Link: https://www.openwall.com/lists/musl/2025/06/12/11
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/bench/futex-hash.c | 1 -
 tools/perf/bench/futex.c      | 9 ++++++++-
 2 files changed, 8 insertions(+), 2 deletions(-)

diff --git a/tools/perf/bench/futex-hash.c b/tools/perf/bench/futex-hash.c
index fdf133c9520f..d2d6d7f3ea33 100644
--- a/tools/perf/bench/futex-hash.c
+++ b/tools/perf/bench/futex-hash.c
@@ -18,7 +18,6 @@
 #include <stdlib.h>
 #include <linux/compiler.h>
 #include <linux/kernel.h>
-#include <linux/prctl.h>
 #include <linux/zalloc.h>
 #include <sys/time.h>
 #include <sys/mman.h>
diff --git a/tools/perf/bench/futex.c b/tools/perf/bench/futex.c
index 26382e4d8d4c..4c4fee107e59 100644
--- a/tools/perf/bench/futex.c
+++ b/tools/perf/bench/futex.c
@@ -2,11 +2,18 @@
 #include <err.h>
 #include <stdio.h>
 #include <stdlib.h>
-#include <linux/prctl.h>
 #include <sys/prctl.h>
 
 #include "futex.h"
 
+#ifndef PR_FUTEX_HASH
+#define PR_FUTEX_HASH                   78
+# define PR_FUTEX_HASH_SET_SLOTS        1
+# define FH_FLAG_IMMUTABLE              (1ULL << 0)
+# define PR_FUTEX_HASH_GET_SLOTS        2
+# define PR_FUTEX_HASH_GET_IMMUTABLE    3
+#endif // PR_FUTEX_HASH
+
 void futex_set_nbuckets_param(struct bench_futex_parameters *params)
 {
 	unsigned long flags;

From d222b6e6fb31e320eca506e665694d8ddf459157 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Mon, 16 Jun 2025 14:18:55 -0300
Subject: [PATCH 0493/1334] tools headers x86 cpufeatures: Sync with the kernel
 sources

To pick the changes from:

  faad6645e1128ec2 ("x86/cpufeatures: Add CPUID feature bit for the Bus Lock Threshold")
  159013a7ca18c271 ("x86/its: Enumerate Indirect Target Selection (ITS) bug")
  f9f27c4a377a8b45 ("x86/cpufeatures: Add "Allowed SEV Features" Feature")
  b02dc185ee86836c ("x86/cpufeatures: Add X86_FEATURE_APX")
  d88bb2ded2efdc38 ("KVM: x86: Advertise support for AMD's PREFETCHI")

This causes these perf files to be rebuilt and brings some X86_FEATURE
that may be used by:

      CC       /tmp/build/perf/bench/mem-memcpy-x86-64-asm.o
      CC       /tmp/build/perf/bench/mem-memset-x86-64-asm.o

And addresses this perf build warning:

  Warning: Kernel ABI header differences:
    diff -u tools/arch/x86/include/asm/cpufeatures.h arch/x86/include/asm/cpufeatures.h

Please see tools/include/uapi/README for further details.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Babu Moger <babu.moger@amd.com>
Cc: Chang S. Bae <chang.seok.bae@intel.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: James Clark <james.clark@linaro.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Kishon Vijay Abraham I <kvijayab@amd.com>
Cc: Manali Shukla <manali.shukla@amd.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Pawan Gupta <pawan.kumar.gupta@linux.intel.com>
Cc: Sean Christopherson <seanjc@google.com>
Link: https://lore.kernel.org/r/aFBWAI3kHYX5aL9G@x1
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/arch/x86/include/asm/cpufeatures.h | 14 ++++++++++----
 1 file changed, 10 insertions(+), 4 deletions(-)

diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index e02be2962a01..ee176236c2be 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -336,7 +336,7 @@
 #define X86_FEATURE_AMD_IBRS		(13*32+14) /* Indirect Branch Restricted Speculation */
 #define X86_FEATURE_AMD_STIBP		(13*32+15) /* Single Thread Indirect Branch Predictors */
 #define X86_FEATURE_AMD_STIBP_ALWAYS_ON	(13*32+17) /* Single Thread Indirect Branch Predictors always-on preferred */
-#define X86_FEATURE_AMD_IBRS_SAME_MODE (13*32+19) /* Indirect Branch Restricted Speculation same mode protection*/
+#define X86_FEATURE_AMD_IBRS_SAME_MODE	(13*32+19) /* Indirect Branch Restricted Speculation same mode protection*/
 #define X86_FEATURE_AMD_PPIN		(13*32+23) /* "amd_ppin" Protected Processor Inventory Number */
 #define X86_FEATURE_AMD_SSBD		(13*32+24) /* Speculative Store Bypass Disable */
 #define X86_FEATURE_VIRT_SSBD		(13*32+25) /* "virt_ssbd" Virtualized Speculative Store Bypass Disable */
@@ -379,6 +379,7 @@
 #define X86_FEATURE_V_SPEC_CTRL		(15*32+20) /* "v_spec_ctrl" Virtual SPEC_CTRL */
 #define X86_FEATURE_VNMI		(15*32+25) /* "vnmi" Virtual NMI */
 #define X86_FEATURE_SVME_ADDR_CHK	(15*32+28) /* SVME addr check */
+#define X86_FEATURE_BUS_LOCK_THRESHOLD	(15*32+29) /* Bus lock threshold */
 #define X86_FEATURE_IDLE_HLT		(15*32+30) /* IDLE HLT intercept */
 
 /* Intel-defined CPU features, CPUID level 0x00000007:0 (ECX), word 16 */
@@ -447,6 +448,7 @@
 #define X86_FEATURE_DEBUG_SWAP		(19*32+14) /* "debug_swap" SEV-ES full debug state swap support */
 #define X86_FEATURE_RMPREAD		(19*32+21) /* RMPREAD instruction */
 #define X86_FEATURE_SEGMENTED_RMP	(19*32+23) /* Segmented RMP support */
+#define X86_FEATURE_ALLOWED_SEV_FEATURES (19*32+27) /* Allowed SEV Features */
 #define X86_FEATURE_SVSM		(19*32+28) /* "svsm" SVSM present */
 #define X86_FEATURE_HV_INUSE_WR_ALLOWED	(19*32+30) /* Allow Write to in-use hypervisor-owned pages */
 
@@ -458,6 +460,7 @@
 #define X86_FEATURE_AUTOIBRS		(20*32+ 8) /* Automatic IBRS */
 #define X86_FEATURE_NO_SMM_CTL_MSR	(20*32+ 9) /* SMM_CTL MSR is not present */
 
+#define X86_FEATURE_PREFETCHI		(20*32+20) /* Prefetch Data/Instruction to Cache Level */
 #define X86_FEATURE_SBPB		(20*32+27) /* Selective Branch Prediction Barrier */
 #define X86_FEATURE_IBPB_BRTYPE		(20*32+28) /* MSR_PRED_CMD[IBPB] flushes all branch type predictions */
 #define X86_FEATURE_SRSO_NO		(20*32+29) /* CPU is not affected by SRSO */
@@ -482,7 +485,8 @@
 #define X86_FEATURE_AMD_HTR_CORES	(21*32+ 6) /* Heterogeneous Core Topology */
 #define X86_FEATURE_AMD_WORKLOAD_CLASS	(21*32+ 7) /* Workload Classification */
 #define X86_FEATURE_PREFER_YMM		(21*32+ 8) /* Avoid ZMM registers due to downclocking */
-#define X86_FEATURE_INDIRECT_THUNK_ITS	(21*32+ 9) /* Use thunk for indirect branches in lower half of cacheline */
+#define X86_FEATURE_APX			(21*32+ 9) /* Advanced Performance Extensions */
+#define X86_FEATURE_INDIRECT_THUNK_ITS	(21*32+10) /* Use thunk for indirect branches in lower half of cacheline */
 
 /*
  * BUG word(s)
@@ -535,6 +539,8 @@
 #define X86_BUG_BHI			X86_BUG( 1*32+ 3) /* "bhi" CPU is affected by Branch History Injection */
 #define X86_BUG_IBPB_NO_RET		X86_BUG( 1*32+ 4) /* "ibpb_no_ret" IBPB omits return target predictions */
 #define X86_BUG_SPECTRE_V2_USER		X86_BUG( 1*32+ 5) /* "spectre_v2_user" CPU is affected by Spectre variant 2 attack between user processes */
-#define X86_BUG_ITS			X86_BUG( 1*32+ 6) /* "its" CPU is affected by Indirect Target Selection */
-#define X86_BUG_ITS_NATIVE_ONLY		X86_BUG( 1*32+ 7) /* "its_native_only" CPU is affected by ITS, VMX is not affected */
+#define X86_BUG_OLD_MICROCODE		X86_BUG( 1*32+ 6) /* "old_microcode" CPU has old microcode, it is surely vulnerable to something */
+#define X86_BUG_ITS			X86_BUG( 1*32+ 7) /* "its" CPU is affected by Indirect Target Selection */
+#define X86_BUG_ITS_NATIVE_ONLY		X86_BUG( 1*32+ 8) /* "its_native_only" CPU is affected by ITS, VMX is not affected */
+
 #endif /* _ASM_X86_CPUFEATURES_H */

From f4b048a6a34af9ad14a3a4a82902748f6cea6872 Mon Sep 17 00:00:00 2001
From: Sven Peter <sven@kernel.org>
Date: Thu, 12 Jun 2025 21:11:32 +0000
Subject: [PATCH 0494/1334] Input: apple_z2 - drop default ARCH_APPLE in
 Kconfig

When the first driver for Apple Silicon was upstreamed we accidentally
included `default ARCH_APPLE` in its Kconfig which then spread to almost
every subsequent driver. As soon as ARCH_APPLE is set to y this will
pull in many drivers as built-ins which is not what we want.
Thus, drop `default ARCH_APPLE` from Kconfig.

Signed-off-by: Sven Peter <sven@kernel.org>
Link: https://lore.kernel.org/r/20250612-apple-kconfig-defconfig-v1-8-0e6f9cb512c1@kernel.org
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/touchscreen/Kconfig | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/input/touchscreen/Kconfig b/drivers/input/touchscreen/Kconfig
index 91a2b584dab1..196905162945 100644
--- a/drivers/input/touchscreen/Kconfig
+++ b/drivers/input/touchscreen/Kconfig
@@ -105,7 +105,6 @@ config TOUCHSCREEN_ADC
 
 config TOUCHSCREEN_APPLE_Z2
 	tristate "Apple Z2 touchscreens"
-	default ARCH_APPLE
 	depends on SPI && (ARCH_APPLE || COMPILE_TEST)
 	help
 	  Say Y here if you have an ARM Apple device with

From 60524f1d2bdf222db6dc3f680e0272441f697fe4 Mon Sep 17 00:00:00 2001
From: Meghana Malladi <m-malladi@ti.com>
Date: Mon, 16 Jun 2025 12:03:19 +0530
Subject: [PATCH 0495/1334] net: ti: icssg-prueth: Fix packet handling for
 XDP_TX

While transmitting XDP frames for XDP_TX, page_pool is
used to get the DMA buffers (already mapped to the pages)
and need to be freed/reycled once the transmission is complete.
This need not be explicitly done by the driver as this is handled
more gracefully by the xdp driver while returning the xdp frame.
__xdp_return() frees the XDP memory based on its memory type,
under which page_pool memory is also handled. This change fixes
the transmit queue timeout while running XDP_TX.

logs:
[  309.069682] icssg-prueth icssg1-eth eth2: NETDEV WATCHDOG: CPU: 0: transmit queue 0 timed out 45860 ms
[  313.933780] icssg-prueth icssg1-eth eth2: NETDEV WATCHDOG: CPU: 0: transmit queue 0 timed out 50724 ms
[  319.053656] icssg-prueth icssg1-eth eth2: NETDEV WATCHDOG: CPU: 0: transmit queue 0 timed out 55844 ms
...

Fixes: 62aa3246f462 ("net: ti: icssg-prueth: Add XDP support")
Signed-off-by: Meghana Malladi <m-malladi@ti.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://patch.msgid.link/20250616063319.3347541-1-m-malladi@ti.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/ti/icssg/icssg_common.c | 19 ++-----------------
 1 file changed, 2 insertions(+), 17 deletions(-)

diff --git a/drivers/net/ethernet/ti/icssg/icssg_common.c b/drivers/net/ethernet/ti/icssg/icssg_common.c
index 5b8fdb882172..12f25cec6255 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_common.c
+++ b/drivers/net/ethernet/ti/icssg/icssg_common.c
@@ -98,20 +98,11 @@ void prueth_xmit_free(struct prueth_tx_chn *tx_chn,
 {
 	struct cppi5_host_desc_t *first_desc, *next_desc;
 	dma_addr_t buf_dma, next_desc_dma;
-	struct prueth_swdata *swdata;
-	struct page *page;
 	u32 buf_dma_len;
 
 	first_desc = desc;
 	next_desc = first_desc;
 
-	swdata = cppi5_hdesc_get_swdata(desc);
-	if (swdata->type == PRUETH_SWDATA_PAGE) {
-		page = swdata->data.page;
-		page_pool_recycle_direct(page->pp, swdata->data.page);
-		goto free_desc;
-	}
-
 	cppi5_hdesc_get_obuf(first_desc, &buf_dma, &buf_dma_len);
 	k3_udma_glue_tx_cppi5_to_dma_addr(tx_chn->tx_chn, &buf_dma);
 
@@ -135,7 +126,6 @@ void prueth_xmit_free(struct prueth_tx_chn *tx_chn,
 		k3_cppi_desc_pool_free(tx_chn->desc_pool, next_desc);
 	}
 
-free_desc:
 	k3_cppi_desc_pool_free(tx_chn->desc_pool, first_desc);
 }
 EXPORT_SYMBOL_GPL(prueth_xmit_free);
@@ -612,13 +602,8 @@ u32 emac_xmit_xdp_frame(struct prueth_emac *emac,
 	k3_udma_glue_tx_dma_to_cppi5_addr(tx_chn->tx_chn, &buf_dma);
 	cppi5_hdesc_attach_buf(first_desc, buf_dma, xdpf->len, buf_dma, xdpf->len);
 	swdata = cppi5_hdesc_get_swdata(first_desc);
-	if (page) {
-		swdata->type = PRUETH_SWDATA_PAGE;
-		swdata->data.page = page;
-	} else {
-		swdata->type = PRUETH_SWDATA_XDPF;
-		swdata->data.xdpf = xdpf;
-	}
+	swdata->type = PRUETH_SWDATA_XDPF;
+	swdata->data.xdpf = xdpf;
 
 	/* Report BQL before sending the packet */
 	netif_txq = netdev_get_tx_queue(ndev, tx_chn->id);

From 94a17f2dc90bc7eae36c0f478515d4bd1c23e877 Mon Sep 17 00:00:00 2001
From: Dave Hansen <dave.hansen@linux.intel.com>
Date: Tue, 10 Jun 2025 15:24:20 -0700
Subject: [PATCH 0496/1334] x86/mm: Disable INVLPGB when PTI is enabled

PTI uses separate ASIDs (aka. PCIDs) for kernel and user address
spaces. When the kernel needs to flush the user address space, it
just sets a bit in a bitmap and then flushes the entire PCID on
the next switch to userspace.

This bitmap is a single 'unsigned long' which is plenty for all 6
dynamic ASIDs. But, unfortunately, the INVLPGB support brings along a
bunch more user ASIDs, as many as ~2k more. The bitmap can't address
that many.

Fortunately, the bitmap is only needed for PTI and all the CPUs
with INVLPGB are AMD CPUs that aren't vulnerable to Meltdown and
don't need PTI. The only way someone can run into an issue in
practice is by booting with pti=on on a newer AMD CPU.

Disable INVLPGB if PTI is enabled. Avoid overrunning the small
bitmap.

Note: this will be fixed up properly by making the bitmap bigger.
For now, just avoid the mostly theoretical bug.

Fixes: 4afeb0ed1753 ("x86/mm: Enable broadcast TLB invalidation for multi-threaded processes")
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Acked-by: Rik van Riel <riel@surriel.com>
Cc:stable@vger.kernel.org
Link: https://lore.kernel.org/all/20250610222420.E8CBF472%40davehans-spike.ostc.intel.com
---
 arch/x86/mm/pti.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/arch/x86/mm/pti.c b/arch/x86/mm/pti.c
index 190299834011..c0c40b67524e 100644
--- a/arch/x86/mm/pti.c
+++ b/arch/x86/mm/pti.c
@@ -98,6 +98,11 @@ void __init pti_check_boottime_disable(void)
 		return;
 
 	setup_force_cpu_cap(X86_FEATURE_PTI);
+
+	if (cpu_feature_enabled(X86_FEATURE_INVLPGB)) {
+		pr_debug("PTI enabled, disabling INVLPGB\n");
+		setup_clear_cpu_cap(X86_FEATURE_INVLPGB);
+	}
 }
 
 static int __init pti_parse_cmdline(char *arg)

From 6f793a1d053775f8324b8dba1e7ed224f8b0166f Mon Sep 17 00:00:00 2001
From: Mina Almasry <almasrymina@google.com>
Date: Sun, 15 Jun 2025 20:07:33 +0000
Subject: [PATCH 0497/1334] net: netmem: fix skb_ensure_writable with
 unreadable skbs

skb_ensure_writable should succeed when it's trying to write to the
header of the unreadable skbs, so it doesn't need an unconditional
skb_frags_readable check. The preceding pskb_may_pull() call will
succeed if write_len is within the head and fail if we're trying to
write to the unreadable payload, so we don't need an additional check.

Removing this check restores DSCP functionality with unreadable skbs as
it's called from dscp_tg.

Cc: willemb@google.com
Cc: asml.silence@gmail.com
Fixes: 65249feb6b3d ("net: add support for skbs with unreadable frags")
Signed-off-by: Mina Almasry <almasrymina@google.com>
Acked-by: Stanislav Fomichev <sdf@fomichev.me>
Link: https://patch.msgid.link/20250615200733.520113-1-almasrymina@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/skbuff.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 85fc82f72d26..d6420b74ea9c 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -6261,9 +6261,6 @@ int skb_ensure_writable(struct sk_buff *skb, unsigned int write_len)
 	if (!pskb_may_pull(skb, write_len))
 		return -ENOMEM;
 
-	if (!skb_frags_readable(skb))
-		return -EFAULT;
-
 	if (!skb_cloned(skb) || skb_clone_writable(skb, write_len))
 		return 0;
 

From 1e9ac33fa271be0d2480fd732f9642d81542500b Mon Sep 17 00:00:00 2001
From: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Date: Fri, 13 Jun 2025 16:18:39 -0700
Subject: [PATCH 0498/1334] bnxt_en: Fix double invocation of
 bnxt_ulp_stop()/bnxt_ulp_start()

Before the commit under the Fixes tag below, bnxt_ulp_stop() and
bnxt_ulp_start() were always invoked in pairs.  After that commit,
the new bnxt_ulp_restart() can be invoked after bnxt_ulp_stop()
has been called.  This may result in the RoCE driver's aux driver
.suspend() method being invoked twice.  The 2nd bnxt_re_suspend()
call will crash when it dereferences a NULL pointer:

(NULL ib_device): Handle device suspend call
BUG: kernel NULL pointer dereference, address: 0000000000000b78
PGD 0 P4D 0
Oops: Oops: 0000 [#1] SMP PTI
CPU: 20 UID: 0 PID: 181 Comm: kworker/u96:5 Tainted: G S                  6.15.0-rc1 #4 PREEMPT(voluntary)
Tainted: [S]=CPU_OUT_OF_SPEC
Hardware name: Dell Inc. PowerEdge R730/072T6D, BIOS 2.4.3 01/17/2017
Workqueue: bnxt_pf_wq bnxt_sp_task [bnxt_en]
RIP: 0010:bnxt_re_suspend+0x45/0x1f0 [bnxt_re]
Code: 8b 05 a7 3c 5b f5 48 89 44 24 18 31 c0 49 8b 5c 24 08 4d 8b 2c 24 e8 ea 06 0a f4 48 c7 c6 04 60 52 c0 48 89 df e8 1b ce f9 ff <48> 8b 83 78 0b 00 00 48 8b 80 38 03 00 00 a8 40 0f 85 b5 00 00 00
RSP: 0018:ffffa2e84084fd88 EFLAGS: 00010246
RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000000000001
RDX: 0000000000000000 RSI: ffffffffb4b6b934 RDI: 00000000ffffffff
RBP: ffffa1760954c9c0 R08: 0000000000000000 R09: c0000000ffffdfff
R10: 0000000000000001 R11: ffffa2e84084fb50 R12: ffffa176031ef070
R13: ffffa17609775000 R14: ffffa17603adc180 R15: 0000000000000000
FS:  0000000000000000(0000) GS:ffffa17daa397000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000000000000b78 CR3: 00000004aaa30003 CR4: 00000000003706f0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
<TASK>
bnxt_ulp_stop+0x69/0x90 [bnxt_en]
bnxt_sp_task+0x678/0x920 [bnxt_en]
? __schedule+0x514/0xf50
process_scheduled_works+0x9d/0x400
worker_thread+0x11c/0x260
? __pfx_worker_thread+0x10/0x10
kthread+0xfe/0x1e0
? __pfx_kthread+0x10/0x10
ret_from_fork+0x2b/0x40
? __pfx_kthread+0x10/0x10
ret_from_fork_asm+0x1a/0x30

Check the BNXT_EN_FLAG_ULP_STOPPED flag and do not proceed if the flag
is already set.  This will preserve the original symmetrical
bnxt_ulp_stop() and bnxt_ulp_start().

Also, inside bnxt_ulp_start(), clear the BNXT_EN_FLAG_ULP_STOPPED
flag after taking the mutex to avoid any race condition.  And for
symmetry, only proceed in bnxt_ulp_start() if the
BNXT_EN_FLAG_ULP_STOPPED is set.

Fixes: 3c163f35bd50 ("bnxt_en: Optimize recovery path ULP locking in the driver")
Signed-off-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Co-developed-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250613231841.377988-2-michael.chan@broadcom.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c | 24 ++++++++-----------
 1 file changed, 10 insertions(+), 14 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
index 84c4812414fd..2450a369b792 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
@@ -231,10 +231,9 @@ void bnxt_ulp_stop(struct bnxt *bp)
 		return;
 
 	mutex_lock(&edev->en_dev_lock);
-	if (!bnxt_ulp_registered(edev)) {
-		mutex_unlock(&edev->en_dev_lock);
-		return;
-	}
+	if (!bnxt_ulp_registered(edev) ||
+	    (edev->flags & BNXT_EN_FLAG_ULP_STOPPED))
+		goto ulp_stop_exit;
 
 	edev->flags |= BNXT_EN_FLAG_ULP_STOPPED;
 	if (aux_priv) {
@@ -250,6 +249,7 @@ void bnxt_ulp_stop(struct bnxt *bp)
 			adrv->suspend(adev, pm);
 		}
 	}
+ulp_stop_exit:
 	mutex_unlock(&edev->en_dev_lock);
 }
 
@@ -258,19 +258,13 @@ void bnxt_ulp_start(struct bnxt *bp, int err)
 	struct bnxt_aux_priv *aux_priv = bp->aux_priv;
 	struct bnxt_en_dev *edev = bp->edev;
 
-	if (!edev)
-		return;
-
-	edev->flags &= ~BNXT_EN_FLAG_ULP_STOPPED;
-
-	if (err)
+	if (!edev || err)
 		return;
 
 	mutex_lock(&edev->en_dev_lock);
-	if (!bnxt_ulp_registered(edev)) {
-		mutex_unlock(&edev->en_dev_lock);
-		return;
-	}
+	if (!bnxt_ulp_registered(edev) ||
+	    !(edev->flags & BNXT_EN_FLAG_ULP_STOPPED))
+		goto ulp_start_exit;
 
 	if (edev->ulp_tbl->msix_requested)
 		bnxt_fill_msix_vecs(bp, edev->msix_entries);
@@ -287,6 +281,8 @@ void bnxt_ulp_start(struct bnxt *bp, int err)
 			adrv->resume(adev);
 		}
 	}
+ulp_start_exit:
+	edev->flags &= ~BNXT_EN_FLAG_ULP_STOPPED;
 	mutex_unlock(&edev->en_dev_lock);
 }
 

From e11baaea94e2923739a98abeee85eb0667c04fd3 Mon Sep 17 00:00:00 2001
From: Pavan Chebbi <pavan.chebbi@broadcom.com>
Date: Fri, 13 Jun 2025 16:18:40 -0700
Subject: [PATCH 0499/1334] bnxt_en: Add a helper function to configure MRU and
 RSS

Add a new helper function that will configure MRU and RSS table
of a VNIC. This will be useful when we configure both on a VNIC
when resetting an RX ring.  This function will be used again in
the next bug fix patch where we have to reconfigure VNICs for RSS
contexts.

Suggested-by: Michael Chan <michael.chan@broadcom.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: David Wei <dw@davidwei.uk>
Signed-off-by: Pavan Chebbi <pavan.chebbi@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Link: https://patch.msgid.link/20250613231841.377988-3-michael.chan@broadcom.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 37 ++++++++++++++++-------
 1 file changed, 26 insertions(+), 11 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 869580b6f70d..dfd2366d4c8c 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -10780,6 +10780,26 @@ void bnxt_del_one_rss_ctx(struct bnxt *bp, struct bnxt_rss_ctx *rss_ctx,
 	bp->num_rss_ctx--;
 }
 
+static int bnxt_set_vnic_mru_p5(struct bnxt *bp, struct bnxt_vnic_info *vnic,
+				u16 mru)
+{
+	int rc;
+
+	if (mru) {
+		rc = bnxt_hwrm_vnic_set_rss_p5(bp, vnic, true);
+		if (rc) {
+			netdev_err(bp->dev, "hwrm vnic %d set rss failure rc: %d\n",
+				   vnic->vnic_id, rc);
+			return rc;
+		}
+	}
+	vnic->mru = mru;
+	bnxt_hwrm_vnic_update(bp, vnic,
+			      VNIC_UPDATE_REQ_ENABLES_MRU_VALID);
+
+	return 0;
+}
+
 static void bnxt_hwrm_realloc_rss_ctx_vnic(struct bnxt *bp)
 {
 	bool set_tpa = !!(bp->flags & BNXT_FLAG_TPA);
@@ -15927,6 +15947,7 @@ static int bnxt_queue_start(struct net_device *dev, void *qmem, int idx)
 	struct bnxt_vnic_info *vnic;
 	struct bnxt_napi *bnapi;
 	int i, rc;
+	u16 mru;
 
 	rxr = &bp->rx_ring[idx];
 	clone = qmem;
@@ -15977,18 +15998,13 @@ static int bnxt_queue_start(struct net_device *dev, void *qmem, int idx)
 	napi_enable_locked(&bnapi->napi);
 	bnxt_db_nq_arm(bp, &cpr->cp_db, cpr->cp_raw_cons);
 
+	mru = bp->dev->mtu + ETH_HLEN + VLAN_HLEN;
 	for (i = 0; i < bp->nr_vnics; i++) {
 		vnic = &bp->vnic_info[i];
 
-		rc = bnxt_hwrm_vnic_set_rss_p5(bp, vnic, true);
-		if (rc) {
-			netdev_err(bp->dev, "hwrm vnic %d set rss failure rc: %d\n",
-				   vnic->vnic_id, rc);
+		rc = bnxt_set_vnic_mru_p5(bp, vnic, mru);
+		if (rc)
 			return rc;
-		}
-		vnic->mru = bp->dev->mtu + ETH_HLEN + VLAN_HLEN;
-		bnxt_hwrm_vnic_update(bp, vnic,
-				      VNIC_UPDATE_REQ_ENABLES_MRU_VALID);
 	}
 
 	return 0;
@@ -16013,9 +16029,8 @@ static int bnxt_queue_stop(struct net_device *dev, void *qmem, int idx)
 
 	for (i = 0; i < bp->nr_vnics; i++) {
 		vnic = &bp->vnic_info[i];
-		vnic->mru = 0;
-		bnxt_hwrm_vnic_update(bp, vnic,
-				      VNIC_UPDATE_REQ_ENABLES_MRU_VALID);
+
+		bnxt_set_vnic_mru_p5(bp, vnic, 0);
 	}
 	/* Make sure NAPI sees that the VNIC is disabled */
 	synchronize_net();

From 5dacc94c6fe61cde6f700e95cf35af9944b022c4 Mon Sep 17 00:00:00 2001
From: Pavan Chebbi <pavan.chebbi@broadcom.com>
Date: Fri, 13 Jun 2025 16:18:41 -0700
Subject: [PATCH 0500/1334] bnxt_en: Update MRU and RSS table of RSS contexts
 on queue reset

The commit under the Fixes tag below which updates the VNICs' RSS
and MRU during .ndo_queue_start(), needs to be extended to cover any
non-default RSS contexts which have their own VNICs.  Without this
step, packets that are destined to a non-default RSS context may be
dropped after .ndo_queue_start().

We further optimize this scheme by updating the VNIC only if the
RX ring being restarted is in the RSS table of the VNIC.  Updating
the VNIC (in particular setting the MRU to 0) will momentarily stop
all traffic to all rings in the RSS table.  Any VNIC that has the
RX ring excluded from the RSS table can skip this step and avoid the
traffic disruption.

Note that this scheme is just an improvement.  A VNIC with multiple
rings in the RSS table will still see traffic disruptions to all rings
in the RSS table when one of the rings is being restarted.  We are
working on a FW scheme that will improve upon this further.

Fixes: 5ac066b7b062 ("bnxt_en: Fix queue start to update vnic RSS table")
Reported-by: David Wei <dw@davidwei.uk>
Signed-off-by: Pavan Chebbi <pavan.chebbi@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Link: https://patch.msgid.link/20250613231841.377988-4-michael.chan@broadcom.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 56 +++++++++++++++++++++--
 1 file changed, 51 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index dfd2366d4c8c..2cb3185c442c 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -10780,11 +10780,39 @@ void bnxt_del_one_rss_ctx(struct bnxt *bp, struct bnxt_rss_ctx *rss_ctx,
 	bp->num_rss_ctx--;
 }
 
+static bool bnxt_vnic_has_rx_ring(struct bnxt *bp, struct bnxt_vnic_info *vnic,
+				  int rxr_id)
+{
+	u16 tbl_size = bnxt_get_rxfh_indir_size(bp->dev);
+	int i, vnic_rx;
+
+	/* Ntuple VNIC always has all the rx rings. Any change of ring id
+	 * must be updated because a future filter may use it.
+	 */
+	if (vnic->flags & BNXT_VNIC_NTUPLE_FLAG)
+		return true;
+
+	for (i = 0; i < tbl_size; i++) {
+		if (vnic->flags & BNXT_VNIC_RSSCTX_FLAG)
+			vnic_rx = ethtool_rxfh_context_indir(vnic->rss_ctx)[i];
+		else
+			vnic_rx = bp->rss_indir_tbl[i];
+
+		if (rxr_id == vnic_rx)
+			return true;
+	}
+
+	return false;
+}
+
 static int bnxt_set_vnic_mru_p5(struct bnxt *bp, struct bnxt_vnic_info *vnic,
-				u16 mru)
+				u16 mru, int rxr_id)
 {
 	int rc;
 
+	if (!bnxt_vnic_has_rx_ring(bp, vnic, rxr_id))
+		return 0;
+
 	if (mru) {
 		rc = bnxt_hwrm_vnic_set_rss_p5(bp, vnic, true);
 		if (rc) {
@@ -10800,6 +10828,24 @@ static int bnxt_set_vnic_mru_p5(struct bnxt *bp, struct bnxt_vnic_info *vnic,
 	return 0;
 }
 
+static int bnxt_set_rss_ctx_vnic_mru(struct bnxt *bp, u16 mru, int rxr_id)
+{
+	struct ethtool_rxfh_context *ctx;
+	unsigned long context;
+	int rc;
+
+	xa_for_each(&bp->dev->ethtool->rss_ctx, context, ctx) {
+		struct bnxt_rss_ctx *rss_ctx = ethtool_rxfh_context_priv(ctx);
+		struct bnxt_vnic_info *vnic = &rss_ctx->vnic;
+
+		rc = bnxt_set_vnic_mru_p5(bp, vnic, mru, rxr_id);
+		if (rc)
+			return rc;
+	}
+
+	return 0;
+}
+
 static void bnxt_hwrm_realloc_rss_ctx_vnic(struct bnxt *bp)
 {
 	bool set_tpa = !!(bp->flags & BNXT_FLAG_TPA);
@@ -16002,12 +16048,11 @@ static int bnxt_queue_start(struct net_device *dev, void *qmem, int idx)
 	for (i = 0; i < bp->nr_vnics; i++) {
 		vnic = &bp->vnic_info[i];
 
-		rc = bnxt_set_vnic_mru_p5(bp, vnic, mru);
+		rc = bnxt_set_vnic_mru_p5(bp, vnic, mru, idx);
 		if (rc)
 			return rc;
 	}
-
-	return 0;
+	return bnxt_set_rss_ctx_vnic_mru(bp, mru, idx);
 
 err_reset:
 	netdev_err(bp->dev, "Unexpected HWRM error during queue start rc: %d\n",
@@ -16030,8 +16075,9 @@ static int bnxt_queue_stop(struct net_device *dev, void *qmem, int idx)
 	for (i = 0; i < bp->nr_vnics; i++) {
 		vnic = &bp->vnic_info[i];
 
-		bnxt_set_vnic_mru_p5(bp, vnic, 0);
+		bnxt_set_vnic_mru_p5(bp, vnic, 0, idx);
 	}
+	bnxt_set_rss_ctx_vnic_mru(bp, 0, idx);
 	/* Make sure NAPI sees that the VNIC is disabled */
 	synchronize_net();
 	rxr = &bp->rx_ring[idx];

From 3c902383f2da91cba3821b73aa6edd49f4db6023 Mon Sep 17 00:00:00 2001
From: Lukas Bulwahn <lukas.bulwahn@redhat.com>
Date: Mon, 16 Jun 2025 12:04:32 +0200
Subject: [PATCH 0501/1334] x86/its: Fix an ifdef typo in its_alloc()

Commit a82b26451de1 ("x86/its: explicitly manage permissions for ITS
pages") reworks its_alloc() and introduces a typo in an ifdef
conditional, referring to CONFIG_MODULE instead of CONFIG_MODULES.

Fix this typo in its_alloc().

Fixes: a82b26451de1 ("x86/its: explicitly manage permissions for ITS pages")
Signed-off-by: Lukas Bulwahn <lukas.bulwahn@redhat.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Link: https://lore.kernel.org/all/20250616100432.22941-1-lukas.bulwahn%40redhat.com
---
 arch/x86/kernel/alternative.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 6455f7f751b3..9ae80fa904a2 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -228,7 +228,7 @@ static void *its_alloc(void)
 	struct its_array *pages = &its_pages;
 	void *page;
 
-#ifdef CONFIG_MODULE
+#ifdef CONFIG_MODULES
 	if (its_mod)
 		pages = &its_mod->arch.its_pages;
 #endif

From 5ab73b010cad294851e558f1d4714a85c6f206c7 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Fri, 13 Jun 2025 20:47:48 +0300
Subject: [PATCH 0502/1334] ptp: fix breakage after ptp_vclock_in_use() rework

What is broken
--------------

ptp4l, and any other application which calls clock_adjtime() on a
physical clock, is greeted with error -EBUSY after commit 87f7ce260a3c
("ptp: remove ptp->n_vclocks check logic in ptp_vclock_in_use()").

Explanation for the breakage
----------------------------

The blamed commit was based on the false assumption that
ptp_vclock_in_use() callers already test for n_vclocks prior to calling
this function.

This is notably incorrect for the code path below, in which there is, in
fact, no n_vclocks test:

ptp_clock_adjtime()
-> ptp_clock_freerun()
   -> ptp_vclock_in_use()

The result is that any clock adjustment on any physical clock is now
impossible. This is _despite_ there not being any vclock over this
physical clock.

$ ptp4l -i eno0 -2 -P -m
ptp4l[58.425]: selected /dev/ptp0 as PTP clock
[   58.429749] ptp: physical clock is free running
ptp4l[58.431]: Failed to open /dev/ptp0: Device or resource busy
failed to create a clock
$ cat /sys/class/ptp/ptp0/n_vclocks
0

The patch makes the ptp_vclock_in_use() function say "if it's not a
virtual clock, then this physical clock does have virtual clocks on
top".

Then ptp_clock_freerun() uses this information to say "this physical
clock has virtual clocks on top, so it must stay free-running".

Then ptp_clock_adjtime() uses this information to say "well, if this
physical clock has to be free-running, I can't do it, return -EBUSY".

Simply put, ptp_vclock_in_use() cannot be simplified so as to remove the
test whether vclocks are in use.

What did the blamed commit intend to fix
----------------------------------------

The blamed commit presents a lockdep warning stating "possible recursive
locking detected", with the n_vclocks_store() and ptp_clock_unregister()
functions involved.

The recursive locking seems this:
n_vclocks_store()
-> mutex_lock_interruptible(&ptp->n_vclocks_mux) // 1
-> device_for_each_child_reverse(..., unregister_vclock)
   -> unregister_vclock()
      -> ptp_vclock_unregister()
         -> ptp_clock_unregister()
            -> ptp_vclock_in_use()
               -> mutex_lock_interruptible(&ptp->n_vclocks_mux) // 2

The issue can be triggered by creating and then deleting vclocks:
$ echo 2 > /sys/class/ptp/ptp0/n_vclocks
$ echo 0 > /sys/class/ptp/ptp0/n_vclocks

But note that in the original stack trace, the address of the first lock
is different from the address of the second lock. This is because at
step 1 marked above, &ptp->n_vclocks_mux is the lock of the parent
(physical) PTP clock, and at step 2, the lock is of the child (virtual)
PTP clock. They are different locks of different devices.

In this situation there is no real deadlock, the lockdep warning is
caused by the fact that the mutexes have the same lock class on both the
parent and the child. Functionally it is fine.

Proposed alternative solution
-----------------------------

We must reintroduce the body of ptp_vclock_in_use() mostly as it was
structured prior to the blamed commit, but avoid the lockdep warning.

Based on the fact that vclocks cannot be nested on top of one another
(ptp_is_attribute_visible() hides n_vclocks for virtual clocks), we
already know that ptp->n_vclocks is zero for a virtual clock. And
ptp->is_virtual_clock is a runtime invariant, established at
ptp_clock_register() time and never changed. There is no need to
serialize on any mutex in order to read ptp->is_virtual_clock, and we
take advantage of that by moving it outside the lock.

Thus, virtual clocks do not need to acquire &ptp->n_vclocks_mux at
all, and step 2 in the code walkthrough above can simply go away.
We can simply return false to the question "ptp_vclock_in_use(a virtual
clock)".

Other notes
-----------

Releasing &ptp->n_vclocks_mux before ptp_vclock_in_use() returns
execution seems racy, because the returned value can become stale as
soon as the function returns and before the return value is used (i.e.
n_vclocks_store() can run any time). The locking requirement should
somehow be transferred to the caller, to ensure a longer life time for
the returned value, but this seems out of scope for this severe bug fix.

Because we are also fixing up the logic from the original commit, there
is another Fixes: tag for that.

Fixes: 87f7ce260a3c ("ptp: remove ptp->n_vclocks check logic in ptp_vclock_in_use()")
Fixes: 73f37068d540 ("ptp: support ptp physical/virtual clocks conversion")
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Link: https://patch.msgid.link/20250613174749.406826-2-vladimir.oltean@nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/ptp/ptp_private.h | 22 +++++++++++++++++++++-
 1 file changed, 21 insertions(+), 1 deletion(-)

diff --git a/drivers/ptp/ptp_private.h b/drivers/ptp/ptp_private.h
index 528d86a33f37..a6aad743c282 100644
--- a/drivers/ptp/ptp_private.h
+++ b/drivers/ptp/ptp_private.h
@@ -98,7 +98,27 @@ static inline int queue_cnt(const struct timestamp_event_queue *q)
 /* Check if ptp virtual clock is in use */
 static inline bool ptp_vclock_in_use(struct ptp_clock *ptp)
 {
-	return !ptp->is_virtual_clock;
+	bool in_use = false;
+
+	/* Virtual clocks can't be stacked on top of virtual clocks.
+	 * Avoid acquiring the n_vclocks_mux on virtual clocks, to allow this
+	 * function to be called from code paths where the n_vclocks_mux of the
+	 * parent physical clock is already held. Functionally that's not an
+	 * issue, but lockdep would complain, because they have the same lock
+	 * class.
+	 */
+	if (ptp->is_virtual_clock)
+		return false;
+
+	if (mutex_lock_interruptible(&ptp->n_vclocks_mux))
+		return true;
+
+	if (ptp->n_vclocks)
+		in_use = true;
+
+	mutex_unlock(&ptp->n_vclocks_mux);
+
+	return in_use;
 }
 
 /* Check if ptp clock shall be free running */

From aa112cbc5f0ac6f3b44d829005bf34005d9fe9bb Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Fri, 13 Jun 2025 20:47:49 +0300
Subject: [PATCH 0503/1334] ptp: allow reading of currently dialed frequency to
 succeed on free-running clocks

There is a bug in ptp_clock_adjtime() which makes it refuse the
operation even if we just want to read the current clock dialed
frequency, not modify anything (tx->modes == 0). That should be possible
even if the clock is free-running. For context, the kernel UAPI is the
same for getting and setting the frequency of a POSIX clock.

For example, ptp4l errors out at clock_create() -> clockadj_get_freq()
-> clock_adjtime() time, when it should logically only have failed on
actual adjustments to the clock, aka if the clock was configured as
slave. But in master mode it should work.

This was discovered when examining the issue described in the previous
commit, where ptp_clock_freerun() returned true despite n_vclocks being
zero.

Fixes: 73f37068d540 ("ptp: support ptp physical/virtual clocks conversion")
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Link: https://patch.msgid.link/20250613174749.406826-3-vladimir.oltean@nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/ptp/ptp_clock.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/ptp/ptp_clock.c b/drivers/ptp/ptp_clock.c
index 35a5994bf64f..36f57d7b4a66 100644
--- a/drivers/ptp/ptp_clock.c
+++ b/drivers/ptp/ptp_clock.c
@@ -121,7 +121,8 @@ static int ptp_clock_adjtime(struct posix_clock *pc, struct __kernel_timex *tx)
 	struct ptp_clock_info *ops;
 	int err = -EOPNOTSUPP;
 
-	if (ptp_clock_freerun(ptp)) {
+	if (tx->modes & (ADJ_SETOFFSET | ADJ_FREQUENCY | ADJ_OFFSET) &&
+	    ptp_clock_freerun(ptp)) {
 		pr_err("ptp: physical clock is free running\n");
 		return -EBUSY;
 	}

From b160766e26d4e2e2d6fe2294e0b02f92baefcec5 Mon Sep 17 00:00:00 2001
From: Hyunwoo Kim <imv4bel@gmail.com>
Date: Fri, 13 Jun 2025 20:54:57 -0400
Subject: [PATCH 0504/1334] net/sched: fix use-after-free in
 taprio_dev_notifier
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Since taprio’s taprio_dev_notifier() isn’t protected by an
RCU read-side critical section, a race with advance_sched()
can lead to a use-after-free.

Adding rcu_read_lock() inside taprio_dev_notifier() prevents this.

Fixes: fed87cc6718a ("net/sched: taprio: automatically calculate queueMaxSDU based on TC gate durations")
Cc: stable@vger.kernel.org
Signed-off-by: Hyunwoo Kim <imv4bel@gmail.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/aEzIYYxt0is9upYG@v4bel-B760M-AORUS-ELITE-AX
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/sched/sch_taprio.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c
index 14021b812329..2b14c81a87e5 100644
--- a/net/sched/sch_taprio.c
+++ b/net/sched/sch_taprio.c
@@ -1328,13 +1328,15 @@ static int taprio_dev_notifier(struct notifier_block *nb, unsigned long event,
 
 		stab = rtnl_dereference(q->root->stab);
 
-		oper = rtnl_dereference(q->oper_sched);
+		rcu_read_lock();
+		oper = rcu_dereference(q->oper_sched);
 		if (oper)
 			taprio_update_queue_max_sdu(q, oper, stab);
 
-		admin = rtnl_dereference(q->admin_sched);
+		admin = rcu_dereference(q->admin_sched);
 		if (admin)
 			taprio_update_queue_max_sdu(q, admin, stab);
+		rcu_read_unlock();
 
 		break;
 	}

From 18ae7d0cdd76420e80f6ab15ada063708f14ba40 Mon Sep 17 00:00:00 2001
From: Bjorn Andersson <bjorn.andersson@oss.qualcomm.com>
Date: Mon, 9 Jun 2025 22:06:22 -0500
Subject: [PATCH 0505/1334] wifi: ath12k: Avoid CPU busy-wait by handling
 VDEV_STAT and BCN_STAT

When the ath12k driver is built without CONFIG_ATH12K_DEBUG, the
recently refactored stats code can cause any user space application
(such at NetworkManager) to consume 100% CPU for 3 seconds, every time
stats are read.

Commit 'b8a0d83fe4c7 ("wifi: ath12k: move firmware stats out of
debugfs")' moved ath12k_debugfs_fw_stats_request() out of debugfs, by
merging the additional logic into ath12k_mac_get_fw_stats().

Among the added responsibility of ath12k_mac_get_fw_stats() was the
busy-wait for `fw_stats_done`.

Signalling of `fw_stats_done` happens when one of the
WMI_REQUEST_PDEV_STAT, WMI_REQUEST_VDEV_STAT, and WMI_REQUEST_BCN_STAT
messages are received, but the handling of the latter two commands remained
in the debugfs code. As `fw_stats_done` isn't signalled, the calling
processes will spin until the timeout (3 seconds) is reached.

Moving the handling of these two additional responses out of debugfs
resolves the issue.

Fixes: b8a0d83fe4c7 ("wifi: ath12k: move firmware stats out of debugfs")
Signed-off-by: Bjorn Andersson <bjorn.andersson@oss.qualcomm.com>
Tested-by: Abel Vesa <abel.vesa@linaro.org>
Link: https://patch.msgid.link/20250609-ath12k-fw-stats-done-v1-1-2b3624656697@oss.qualcomm.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/debugfs.c | 58 --------------------
 drivers/net/wireless/ath/ath12k/debugfs.h |  7 ---
 drivers/net/wireless/ath/ath12k/wmi.c     | 67 ++++++++++++++++++++---
 3 files changed, 60 insertions(+), 72 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/debugfs.c b/drivers/net/wireless/ath/ath12k/debugfs.c
index dd624d73b8b2..23da93afaa5c 100644
--- a/drivers/net/wireless/ath/ath12k/debugfs.c
+++ b/drivers/net/wireless/ath/ath12k/debugfs.c
@@ -1251,64 +1251,6 @@ void ath12k_debugfs_soc_destroy(struct ath12k_base *ab)
 	 */
 }
 
-void
-ath12k_debugfs_fw_stats_process(struct ath12k *ar,
-				struct ath12k_fw_stats *stats)
-{
-	struct ath12k_base *ab = ar->ab;
-	struct ath12k_pdev *pdev;
-	bool is_end;
-	static unsigned int num_vdev, num_bcn;
-	size_t total_vdevs_started = 0;
-	int i;
-
-	if (stats->stats_id == WMI_REQUEST_VDEV_STAT) {
-		if (list_empty(&stats->vdevs)) {
-			ath12k_warn(ab, "empty vdev stats");
-			return;
-		}
-		/* FW sends all the active VDEV stats irrespective of PDEV,
-		 * hence limit until the count of all VDEVs started
-		 */
-		rcu_read_lock();
-		for (i = 0; i < ab->num_radios; i++) {
-			pdev = rcu_dereference(ab->pdevs_active[i]);
-			if (pdev && pdev->ar)
-				total_vdevs_started += pdev->ar->num_started_vdevs;
-		}
-		rcu_read_unlock();
-
-		is_end = ((++num_vdev) == total_vdevs_started);
-
-		list_splice_tail_init(&stats->vdevs,
-				      &ar->fw_stats.vdevs);
-
-		if (is_end) {
-			ar->fw_stats.fw_stats_done = true;
-			num_vdev = 0;
-		}
-		return;
-	}
-	if (stats->stats_id == WMI_REQUEST_BCN_STAT) {
-		if (list_empty(&stats->bcn)) {
-			ath12k_warn(ab, "empty beacon stats");
-			return;
-		}
-		/* Mark end until we reached the count of all started VDEVs
-		 * within the PDEV
-		 */
-		is_end = ((++num_bcn) == ar->num_started_vdevs);
-
-		list_splice_tail_init(&stats->bcn,
-				      &ar->fw_stats.bcn);
-
-		if (is_end) {
-			ar->fw_stats.fw_stats_done = true;
-			num_bcn = 0;
-		}
-	}
-}
-
 static int ath12k_open_vdev_stats(struct inode *inode, struct file *file)
 {
 	struct ath12k *ar = inode->i_private;
diff --git a/drivers/net/wireless/ath/ath12k/debugfs.h b/drivers/net/wireless/ath/ath12k/debugfs.h
index ebef7dace344..21641a8a0346 100644
--- a/drivers/net/wireless/ath/ath12k/debugfs.h
+++ b/drivers/net/wireless/ath/ath12k/debugfs.h
@@ -12,8 +12,6 @@ void ath12k_debugfs_soc_create(struct ath12k_base *ab);
 void ath12k_debugfs_soc_destroy(struct ath12k_base *ab);
 void ath12k_debugfs_register(struct ath12k *ar);
 void ath12k_debugfs_unregister(struct ath12k *ar);
-void ath12k_debugfs_fw_stats_process(struct ath12k *ar,
-				     struct ath12k_fw_stats *stats);
 void ath12k_debugfs_op_vif_add(struct ieee80211_hw *hw,
 			       struct ieee80211_vif *vif);
 void ath12k_debugfs_pdev_create(struct ath12k_base *ab);
@@ -126,11 +124,6 @@ static inline void ath12k_debugfs_unregister(struct ath12k *ar)
 {
 }
 
-static inline void ath12k_debugfs_fw_stats_process(struct ath12k *ar,
-						   struct ath12k_fw_stats *stats)
-{
-}
-
 static inline bool ath12k_debugfs_is_extd_rx_stats_enabled(struct ath12k *ar)
 {
 	return false;
diff --git a/drivers/net/wireless/ath/ath12k/wmi.c b/drivers/net/wireless/ath/ath12k/wmi.c
index 60e2444fe08c..2d2444417e2b 100644
--- a/drivers/net/wireless/ath/ath12k/wmi.c
+++ b/drivers/net/wireless/ath/ath12k/wmi.c
@@ -7626,6 +7626,63 @@ static int ath12k_wmi_pull_fw_stats(struct ath12k_base *ab, struct sk_buff *skb,
 				   &parse);
 }
 
+static void ath12k_wmi_fw_stats_process(struct ath12k *ar,
+					struct ath12k_fw_stats *stats)
+{
+	struct ath12k_base *ab = ar->ab;
+	struct ath12k_pdev *pdev;
+	bool is_end;
+	static unsigned int num_vdev, num_bcn;
+	size_t total_vdevs_started = 0;
+	int i;
+
+	if (stats->stats_id == WMI_REQUEST_VDEV_STAT) {
+		if (list_empty(&stats->vdevs)) {
+			ath12k_warn(ab, "empty vdev stats");
+			return;
+		}
+		/* FW sends all the active VDEV stats irrespective of PDEV,
+		 * hence limit until the count of all VDEVs started
+		 */
+		rcu_read_lock();
+		for (i = 0; i < ab->num_radios; i++) {
+			pdev = rcu_dereference(ab->pdevs_active[i]);
+			if (pdev && pdev->ar)
+				total_vdevs_started += pdev->ar->num_started_vdevs;
+		}
+		rcu_read_unlock();
+
+		is_end = ((++num_vdev) == total_vdevs_started);
+
+		list_splice_tail_init(&stats->vdevs,
+				      &ar->fw_stats.vdevs);
+
+		if (is_end) {
+			ar->fw_stats.fw_stats_done = true;
+			num_vdev = 0;
+		}
+		return;
+	}
+	if (stats->stats_id == WMI_REQUEST_BCN_STAT) {
+		if (list_empty(&stats->bcn)) {
+			ath12k_warn(ab, "empty beacon stats");
+			return;
+		}
+		/* Mark end until we reached the count of all started VDEVs
+		 * within the PDEV
+		 */
+		is_end = ((++num_bcn) == ar->num_started_vdevs);
+
+		list_splice_tail_init(&stats->bcn,
+				      &ar->fw_stats.bcn);
+
+		if (is_end) {
+			ar->fw_stats.fw_stats_done = true;
+			num_bcn = 0;
+		}
+	}
+}
+
 static void ath12k_update_stats_event(struct ath12k_base *ab, struct sk_buff *skb)
 {
 	struct ath12k_fw_stats stats = {};
@@ -7655,19 +7712,15 @@ static void ath12k_update_stats_event(struct ath12k_base *ab, struct sk_buff *sk
 
 	spin_lock_bh(&ar->data_lock);
 
-	/* WMI_REQUEST_PDEV_STAT can be requested via .get_txpower mac ops or via
-	 * debugfs fw stats. Therefore, processing it separately.
-	 */
+	/* Handle WMI_REQUEST_PDEV_STAT status update */
 	if (stats.stats_id == WMI_REQUEST_PDEV_STAT) {
 		list_splice_tail_init(&stats.pdevs, &ar->fw_stats.pdevs);
 		ar->fw_stats.fw_stats_done = true;
 		goto complete;
 	}
 
-	/* WMI_REQUEST_VDEV_STAT and WMI_REQUEST_BCN_STAT are currently requested only
-	 * via debugfs fw stats. Hence, processing these in debugfs context.
-	 */
-	ath12k_debugfs_fw_stats_process(ar, &stats);
+	/* Handle WMI_REQUEST_VDEV_STAT and WMI_REQUEST_BCN_STAT updates. */
+	ath12k_wmi_fw_stats_process(ar, &stats);
 
 complete:
 	complete(&ar->fw_stats_complete);

From 062ade23991e556a14bbb27c1cf873c34dbd9d28 Mon Sep 17 00:00:00 2001
From: Baochen Qiang <quic_bqiang@quicinc.com>
Date: Thu, 22 May 2025 16:54:10 +0800
Subject: [PATCH 0506/1334] wifi: ath12k: parse and save hardware mode info
 from WMI_SERVICE_READY_EXT_EVENTID event for later use

WLAN hardware might support various hardware modes such as DBS (dual
band simultaneously), SBS (single band simultaneously) and DBS_OR_SBS
etc, see enum wmi_host_hw_mode_config_type. Firmware advertises actual
supported modes in WMI_SERVICE_READY_EXT_EVENTID event. For each mode,
firmware advertises frequency range each hardware MAC can operate on.
In MLO case such information is necessary during vdev activation and
link selection (which is done in following patches), so add a new
structure ath12k_svc_ext_info to ath12k_wmi_base, then parse and save
those information to it for later use.

Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.1.c5-00284-QCAHMTSWPL_V1.0_V2.0_SILICONZ-1
Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.4.1-00199-QCAHKSWPL_SILICONZ-1

Signed-off-by: Baochen Qiang <quic_bqiang@quicinc.com>
Reviewed-by: Vasanthakumar Thiagarajan <vasanthakumar.thiagarajan@oss.qualcomm.com>
Link: https://patch.msgid.link/20250522-ath12k-sbs-dbs-v1-1-54a29e7a3a88@quicinc.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/wmi.c | 69 ++++++++++++++++++++++++++-
 drivers/net/wireless/ath/ath12k/wmi.h | 31 ++++++++++++
 2 files changed, 98 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/wmi.c b/drivers/net/wireless/ath/ath12k/wmi.c
index 2d2444417e2b..edb38fbb4ed4 100644
--- a/drivers/net/wireless/ath/ath12k/wmi.c
+++ b/drivers/net/wireless/ath/ath12k/wmi.c
@@ -4395,6 +4395,7 @@ static int ath12k_wmi_hw_mode_caps_parse(struct ath12k_base *soc,
 static int ath12k_wmi_hw_mode_caps(struct ath12k_base *soc,
 				   u16 len, const void *ptr, void *data)
 {
+	struct ath12k_svc_ext_info *svc_ext_info = &soc->wmi_ab.svc_ext_info;
 	struct ath12k_wmi_svc_rdy_ext_parse *svc_rdy_ext = data;
 	const struct ath12k_wmi_hw_mode_cap_params *hw_mode_caps;
 	enum wmi_host_hw_mode_config_type mode, pref;
@@ -4427,8 +4428,11 @@ static int ath12k_wmi_hw_mode_caps(struct ath12k_base *soc,
 		}
 	}
 
-	ath12k_dbg(soc, ATH12K_DBG_WMI, "preferred_hw_mode:%d\n",
-		   soc->wmi_ab.preferred_hw_mode);
+	svc_ext_info->num_hw_modes = svc_rdy_ext->n_hw_mode_caps;
+
+	ath12k_dbg(soc, ATH12K_DBG_WMI, "num hw modes %u preferred_hw_mode %d\n",
+		   svc_ext_info->num_hw_modes, soc->wmi_ab.preferred_hw_mode);
+
 	if (soc->wmi_ab.preferred_hw_mode == WMI_HOST_HW_MODE_MAX)
 		return -EINVAL;
 
@@ -4658,6 +4662,65 @@ free_dir_buff:
 	return ret;
 }
 
+static void
+ath12k_wmi_save_mac_phy_info(struct ath12k_base *ab,
+			     const struct ath12k_wmi_mac_phy_caps_params *mac_phy_cap,
+			     struct ath12k_svc_ext_mac_phy_info *mac_phy_info)
+{
+	mac_phy_info->phy_id = __le32_to_cpu(mac_phy_cap->phy_id);
+	mac_phy_info->supported_bands = __le32_to_cpu(mac_phy_cap->supported_bands);
+	mac_phy_info->hw_freq_range.low_2ghz_freq =
+					__le32_to_cpu(mac_phy_cap->low_2ghz_chan_freq);
+	mac_phy_info->hw_freq_range.high_2ghz_freq =
+					__le32_to_cpu(mac_phy_cap->high_2ghz_chan_freq);
+	mac_phy_info->hw_freq_range.low_5ghz_freq =
+					__le32_to_cpu(mac_phy_cap->low_5ghz_chan_freq);
+	mac_phy_info->hw_freq_range.high_5ghz_freq =
+					__le32_to_cpu(mac_phy_cap->high_5ghz_chan_freq);
+}
+
+static void
+ath12k_wmi_save_all_mac_phy_info(struct ath12k_base *ab,
+				 struct ath12k_wmi_svc_rdy_ext_parse *svc_rdy_ext)
+{
+	struct ath12k_svc_ext_info *svc_ext_info = &ab->wmi_ab.svc_ext_info;
+	const struct ath12k_wmi_mac_phy_caps_params *mac_phy_cap;
+	const struct ath12k_wmi_hw_mode_cap_params *hw_mode_cap;
+	struct ath12k_svc_ext_mac_phy_info *mac_phy_info;
+	u32 hw_mode_id, phy_bit_map;
+	u8 hw_idx;
+
+	mac_phy_info = &svc_ext_info->mac_phy_info[0];
+	mac_phy_cap = svc_rdy_ext->mac_phy_caps;
+
+	for (hw_idx = 0; hw_idx < svc_ext_info->num_hw_modes; hw_idx++) {
+		hw_mode_cap = &svc_rdy_ext->hw_mode_caps[hw_idx];
+		hw_mode_id = __le32_to_cpu(hw_mode_cap->hw_mode_id);
+		phy_bit_map = __le32_to_cpu(hw_mode_cap->phy_id_map);
+
+		while (phy_bit_map) {
+			ath12k_wmi_save_mac_phy_info(ab, mac_phy_cap, mac_phy_info);
+			mac_phy_info->hw_mode_config_type =
+					le32_get_bits(hw_mode_cap->hw_mode_config_type,
+						      WMI_HW_MODE_CAP_CFG_TYPE);
+			ath12k_dbg(ab, ATH12K_DBG_WMI,
+				   "hw_idx %u hw_mode_id %u hw_mode_config_type %u supported_bands %u phy_id %u 2 GHz [%u - %u] 5 GHz [%u - %u]\n",
+				   hw_idx, hw_mode_id,
+				   mac_phy_info->hw_mode_config_type,
+				   mac_phy_info->supported_bands, mac_phy_info->phy_id,
+				   mac_phy_info->hw_freq_range.low_2ghz_freq,
+				   mac_phy_info->hw_freq_range.high_2ghz_freq,
+				   mac_phy_info->hw_freq_range.low_5ghz_freq,
+				   mac_phy_info->hw_freq_range.high_5ghz_freq);
+
+			mac_phy_cap++;
+			mac_phy_info++;
+
+			phy_bit_map >>= 1;
+		}
+	}
+}
+
 static int ath12k_wmi_svc_rdy_ext_parse(struct ath12k_base *ab,
 					u16 tag, u16 len,
 					const void *ptr, void *data)
@@ -4706,6 +4769,8 @@ static int ath12k_wmi_svc_rdy_ext_parse(struct ath12k_base *ab,
 				return ret;
 			}
 
+			ath12k_wmi_save_all_mac_phy_info(ab, svc_rdy_ext);
+
 			svc_rdy_ext->mac_phy_done = true;
 		} else if (!svc_rdy_ext->ext_hal_reg_done) {
 			ret = ath12k_wmi_ext_hal_reg_caps(ab, len, ptr, svc_rdy_ext);
diff --git a/drivers/net/wireless/ath/ath12k/wmi.h b/drivers/net/wireless/ath/ath12k/wmi.h
index ac18f75e0449..96c31b7820ec 100644
--- a/drivers/net/wireless/ath/ath12k/wmi.h
+++ b/drivers/net/wireless/ath/ath12k/wmi.h
@@ -2617,6 +2617,8 @@ struct ath12k_wmi_soc_mac_phy_hw_mode_caps_params {
 	__le32 num_chainmask_tables;
 } __packed;
 
+#define WMI_HW_MODE_CAP_CFG_TYPE	GENMASK(27, 0)
+
 struct ath12k_wmi_hw_mode_cap_params {
 	__le32 tlv_header;
 	__le32 hw_mode_id;
@@ -2666,6 +2668,12 @@ struct ath12k_wmi_mac_phy_caps_params {
 	__le32 he_cap_info_2g_ext;
 	__le32 he_cap_info_5g_ext;
 	__le32 he_cap_info_internal;
+	__le32 wireless_modes;
+	__le32 low_2ghz_chan_freq;
+	__le32 high_2ghz_chan_freq;
+	__le32 low_5ghz_chan_freq;
+	__le32 high_5ghz_chan_freq;
+	__le32 nss_ratio;
 } __packed;
 
 struct ath12k_wmi_hal_reg_caps_ext_params {
@@ -5049,6 +5057,27 @@ struct ath12k_wmi_pdev {
 	u32 rx_decap_mode;
 };
 
+struct ath12k_hw_mode_freq_range_arg {
+	u32 low_2ghz_freq;
+	u32 high_2ghz_freq;
+	u32 low_5ghz_freq;
+	u32 high_5ghz_freq;
+};
+
+struct ath12k_svc_ext_mac_phy_info {
+	enum wmi_host_hw_mode_config_type hw_mode_config_type;
+	u32 phy_id;
+	u32 supported_bands;
+	struct ath12k_hw_mode_freq_range_arg hw_freq_range;
+};
+
+#define ATH12K_MAX_MAC_PHY_CAP	8
+
+struct ath12k_svc_ext_info {
+	u32 num_hw_modes;
+	struct ath12k_svc_ext_mac_phy_info mac_phy_info[ATH12K_MAX_MAC_PHY_CAP];
+};
+
 struct ath12k_wmi_base {
 	struct ath12k_base *ab;
 	struct ath12k_wmi_pdev wmi[MAX_RADIOS];
@@ -5066,6 +5095,8 @@ struct ath12k_wmi_base {
 	enum wmi_host_hw_mode_config_type preferred_hw_mode;
 
 	struct ath12k_wmi_target_cap_arg *targ_cap;
+
+	struct ath12k_svc_ext_info svc_ext_info;
 };
 
 struct wmi_pdev_set_bios_interface_cmd {

From 241d130f1419fd99923d99aff6e40490a4c34d93 Mon Sep 17 00:00:00 2001
From: Baochen Qiang <quic_bqiang@quicinc.com>
Date: Thu, 22 May 2025 16:54:11 +0800
Subject: [PATCH 0507/1334] wifi: ath12k: parse and save
 sbs_lower_band_end_freq from WMI_SERVICE_READY_EXT2_EVENTID event

Firmware sends the boundary between lower and higher bands in
ath12k_wmi_dbs_or_sbs_cap_params structure embedded in
WMI_SERVICE_READY_EXT2_EVENTID event. The boundary is needed when
updating frequency range in the following patch. So parse and save
it for later use. Note ath12k_wmi_dbs_or_sbs_cap_params is placed
after some other structures, so placeholders for them are added
as well.

Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.1.c5-00284-QCAHMTSWPL_V1.0_V2.0_SILICONZ-1
Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.4.1-00199-QCAHKSWPL_SILICONZ-1

Signed-off-by: Baochen Qiang <quic_bqiang@quicinc.com>
Reviewed-by: Vasanthakumar Thiagarajan <vasanthakumar.thiagarajan@oss.qualcomm.com>
Link: https://patch.msgid.link/20250522-ath12k-sbs-dbs-v1-2-54a29e7a3a88@quicinc.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/wmi.c | 23 +++++++++++++++++++++++
 drivers/net/wireless/ath/ath12k/wmi.h |  6 ++++++
 2 files changed, 29 insertions(+)

diff --git a/drivers/net/wireless/ath/ath12k/wmi.c b/drivers/net/wireless/ath/ath12k/wmi.c
index edb38fbb4ed4..824c910bf1d6 100644
--- a/drivers/net/wireless/ath/ath12k/wmi.c
+++ b/drivers/net/wireless/ath/ath12k/wmi.c
@@ -91,6 +91,11 @@ struct ath12k_wmi_svc_rdy_ext2_parse {
 	bool dma_ring_cap_done;
 	bool spectral_bin_scaling_done;
 	bool mac_phy_caps_ext_done;
+	bool hal_reg_caps_ext2_done;
+	bool scan_radio_caps_ext2_done;
+	bool twt_caps_done;
+	bool htt_msdu_idx_to_qtype_map_done;
+	bool dbs_or_sbs_cap_ext_done;
 };
 
 struct ath12k_wmi_rdy_parse {
@@ -4991,6 +4996,7 @@ static int ath12k_wmi_svc_rdy_ext2_parse(struct ath12k_base *ab,
 					 u16 tag, u16 len,
 					 const void *ptr, void *data)
 {
+	const struct ath12k_wmi_dbs_or_sbs_cap_params *dbs_or_sbs_caps;
 	struct ath12k_wmi_pdev *wmi_handle = &ab->wmi_ab.wmi[0];
 	struct ath12k_wmi_svc_rdy_ext2_parse *parse = data;
 	int ret;
@@ -5032,6 +5038,23 @@ static int ath12k_wmi_svc_rdy_ext2_parse(struct ath12k_base *ab,
 			}
 
 			parse->mac_phy_caps_ext_done = true;
+		} else if (!parse->hal_reg_caps_ext2_done) {
+			parse->hal_reg_caps_ext2_done = true;
+		} else if (!parse->scan_radio_caps_ext2_done) {
+			parse->scan_radio_caps_ext2_done = true;
+		} else if (!parse->twt_caps_done) {
+			parse->twt_caps_done = true;
+		} else if (!parse->htt_msdu_idx_to_qtype_map_done) {
+			parse->htt_msdu_idx_to_qtype_map_done = true;
+		} else if (!parse->dbs_or_sbs_cap_ext_done) {
+			dbs_or_sbs_caps = ptr;
+			ab->wmi_ab.sbs_lower_band_end_freq =
+				__le32_to_cpu(dbs_or_sbs_caps->sbs_lower_band_end_freq);
+
+			ath12k_dbg(ab, ATH12K_DBG_WMI, "sbs_lower_band_end_freq %u\n",
+				   ab->wmi_ab.sbs_lower_band_end_freq);
+
+			parse->dbs_or_sbs_cap_ext_done = true;
 		}
 		break;
 	default:
diff --git a/drivers/net/wireless/ath/ath12k/wmi.h b/drivers/net/wireless/ath/ath12k/wmi.h
index 96c31b7820ec..e69d53054f6d 100644
--- a/drivers/net/wireless/ath/ath12k/wmi.h
+++ b/drivers/net/wireless/ath/ath12k/wmi.h
@@ -2747,6 +2747,11 @@ struct wmi_service_ready_ext2_event {
 	__le32 default_num_msduq_supported_per_tid;
 } __packed;
 
+struct ath12k_wmi_dbs_or_sbs_cap_params {
+	__le32 hw_mode_id;
+	__le32 sbs_lower_band_end_freq;
+} __packed;
+
 struct ath12k_wmi_caps_ext_params {
 	__le32 hw_mode_id;
 	__le32 pdev_and_hw_link_ids;
@@ -5097,6 +5102,7 @@ struct ath12k_wmi_base {
 	struct ath12k_wmi_target_cap_arg *targ_cap;
 
 	struct ath12k_svc_ext_info svc_ext_info;
+	u32 sbs_lower_band_end_freq;
 };
 
 struct wmi_pdev_set_bios_interface_cmd {

From e47b11e3bd34177af6669ef0945eb23dd4da3bcb Mon Sep 17 00:00:00 2001
From: Baochen Qiang <quic_bqiang@quicinc.com>
Date: Thu, 22 May 2025 16:54:12 +0800
Subject: [PATCH 0508/1334] wifi: ath12k: update freq range for each hardware
 mode

Previous patches parse and save hardware MAC frequency range information
in ath12k_svc_ext_info structure. Such range represents hardware
capability hence needs to be updated based on host information, e.g. guard
the range based on host's low/high boundary.

So update frequency range. The updated range is saved in
ath12k_hw_mode_info structure and would be used when doing vdev activation
and link selection in following patches.

Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.1.c5-00284-QCAHMTSWPL_V1.0_V2.0_SILICONZ-1
Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.4.1-00199-QCAHKSWPL_SILICONZ-1

Signed-off-by: Baochen Qiang <quic_bqiang@quicinc.com>
Reviewed-by: Vasanthakumar Thiagarajan <vasanthakumar.thiagarajan@oss.qualcomm.com>
Link: https://patch.msgid.link/20250522-ath12k-sbs-dbs-v1-3-54a29e7a3a88@quicinc.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/wmi.c | 446 ++++++++++++++++++++++++++
 drivers/net/wireless/ath/ath12k/wmi.h |  27 ++
 2 files changed, 473 insertions(+)

diff --git a/drivers/net/wireless/ath/ath12k/wmi.c b/drivers/net/wireless/ath/ath12k/wmi.c
index 824c910bf1d6..034c18f6a2d2 100644
--- a/drivers/net/wireless/ath/ath12k/wmi.c
+++ b/drivers/net/wireless/ath/ath12k/wmi.c
@@ -4992,6 +4992,444 @@ static int ath12k_wmi_tlv_mac_phy_caps_ext(struct ath12k_base *ab, u16 tag,
 	return 0;
 }
 
+static void
+ath12k_wmi_update_freq_info(struct ath12k_base *ab,
+			    struct ath12k_svc_ext_mac_phy_info *mac_cap,
+			    enum ath12k_hw_mode mode,
+			    u32 phy_id)
+{
+	struct ath12k_hw_mode_info *hw_mode_info = &ab->wmi_ab.hw_mode_info;
+	struct ath12k_hw_mode_freq_range_arg *mac_range;
+
+	mac_range = &hw_mode_info->freq_range_caps[mode][phy_id];
+
+	if (mac_cap->supported_bands & WMI_HOST_WLAN_2GHZ_CAP) {
+		mac_range->low_2ghz_freq = max_t(u32,
+						 mac_cap->hw_freq_range.low_2ghz_freq,
+						 ATH12K_MIN_2GHZ_FREQ);
+		mac_range->high_2ghz_freq = mac_cap->hw_freq_range.high_2ghz_freq ?
+					    min_t(u32,
+						  mac_cap->hw_freq_range.high_2ghz_freq,
+						  ATH12K_MAX_2GHZ_FREQ) :
+					    ATH12K_MAX_2GHZ_FREQ;
+	}
+
+	if (mac_cap->supported_bands & WMI_HOST_WLAN_5GHZ_CAP) {
+		mac_range->low_5ghz_freq = max_t(u32,
+						 mac_cap->hw_freq_range.low_5ghz_freq,
+						 ATH12K_MIN_5GHZ_FREQ);
+		mac_range->high_5ghz_freq = mac_cap->hw_freq_range.high_5ghz_freq ?
+					    min_t(u32,
+						  mac_cap->hw_freq_range.high_5ghz_freq,
+						  ATH12K_MAX_6GHZ_FREQ) :
+					    ATH12K_MAX_6GHZ_FREQ;
+	}
+}
+
+static bool
+ath12k_wmi_all_phy_range_updated(struct ath12k_base *ab,
+				 enum ath12k_hw_mode hwmode)
+{
+	struct ath12k_hw_mode_info *hw_mode_info = &ab->wmi_ab.hw_mode_info;
+	struct ath12k_hw_mode_freq_range_arg *mac_range;
+	u8 phy_id;
+
+	for (phy_id = 0; phy_id < MAX_RADIOS; phy_id++) {
+		mac_range = &hw_mode_info->freq_range_caps[hwmode][phy_id];
+		/* modify SBS/DBS range only when both phy for DBS are filled */
+		if (!mac_range->low_2ghz_freq && !mac_range->low_5ghz_freq)
+			return false;
+	}
+
+	return true;
+}
+
+static void ath12k_wmi_update_dbs_freq_info(struct ath12k_base *ab)
+{
+	struct ath12k_hw_mode_info *hw_mode_info = &ab->wmi_ab.hw_mode_info;
+	struct ath12k_hw_mode_freq_range_arg *mac_range;
+	u8 phy_id;
+
+	mac_range = hw_mode_info->freq_range_caps[ATH12K_HW_MODE_DBS];
+	/* Reset 5 GHz range for shared mac for DBS */
+	for (phy_id = 0; phy_id < MAX_RADIOS; phy_id++) {
+		if (mac_range[phy_id].low_2ghz_freq &&
+		    mac_range[phy_id].low_5ghz_freq) {
+			mac_range[phy_id].low_5ghz_freq = 0;
+			mac_range[phy_id].high_5ghz_freq = 0;
+		}
+	}
+}
+
+static u32
+ath12k_wmi_get_highest_5ghz_freq_from_range(struct ath12k_hw_mode_freq_range_arg *range)
+{
+	u32 highest_freq = 0;
+	u8 phy_id;
+
+	for (phy_id = 0; phy_id < MAX_RADIOS; phy_id++) {
+		if (range[phy_id].high_5ghz_freq > highest_freq)
+			highest_freq = range[phy_id].high_5ghz_freq;
+	}
+
+	return highest_freq ? highest_freq : ATH12K_MAX_6GHZ_FREQ;
+}
+
+static u32
+ath12k_wmi_get_lowest_5ghz_freq_from_range(struct ath12k_hw_mode_freq_range_arg *range)
+{
+	u32 lowest_freq = 0;
+	u8 phy_id;
+
+	for (phy_id = 0; phy_id < MAX_RADIOS; phy_id++) {
+		if ((!lowest_freq && range[phy_id].low_5ghz_freq) ||
+		    range[phy_id].low_5ghz_freq < lowest_freq)
+			lowest_freq = range[phy_id].low_5ghz_freq;
+	}
+
+	return lowest_freq ? lowest_freq : ATH12K_MIN_5GHZ_FREQ;
+}
+
+static void
+ath12k_wmi_fill_upper_share_sbs_freq(struct ath12k_base *ab,
+				     u16 sbs_range_sep,
+				     struct ath12k_hw_mode_freq_range_arg *ref_freq)
+{
+	struct ath12k_hw_mode_info *hw_mode_info = &ab->wmi_ab.hw_mode_info;
+	struct ath12k_hw_mode_freq_range_arg *upper_sbs_freq_range;
+	u8 phy_id;
+
+	upper_sbs_freq_range =
+			hw_mode_info->freq_range_caps[ATH12K_HW_MODE_SBS_UPPER_SHARE];
+
+	for (phy_id = 0; phy_id < MAX_RADIOS; phy_id++) {
+		upper_sbs_freq_range[phy_id].low_2ghz_freq =
+						ref_freq[phy_id].low_2ghz_freq;
+		upper_sbs_freq_range[phy_id].high_2ghz_freq =
+						ref_freq[phy_id].high_2ghz_freq;
+
+		/* update for shared mac */
+		if (upper_sbs_freq_range[phy_id].low_2ghz_freq) {
+			upper_sbs_freq_range[phy_id].low_5ghz_freq = sbs_range_sep + 10;
+			upper_sbs_freq_range[phy_id].high_5ghz_freq =
+				ath12k_wmi_get_highest_5ghz_freq_from_range(ref_freq);
+		} else {
+			upper_sbs_freq_range[phy_id].low_5ghz_freq =
+				ath12k_wmi_get_lowest_5ghz_freq_from_range(ref_freq);
+			upper_sbs_freq_range[phy_id].high_5ghz_freq = sbs_range_sep;
+		}
+	}
+}
+
+static void
+ath12k_wmi_fill_lower_share_sbs_freq(struct ath12k_base *ab,
+				     u16 sbs_range_sep,
+				     struct ath12k_hw_mode_freq_range_arg *ref_freq)
+{
+	struct ath12k_hw_mode_info *hw_mode_info = &ab->wmi_ab.hw_mode_info;
+	struct ath12k_hw_mode_freq_range_arg *lower_sbs_freq_range;
+	u8 phy_id;
+
+	lower_sbs_freq_range =
+			hw_mode_info->freq_range_caps[ATH12K_HW_MODE_SBS_LOWER_SHARE];
+
+	for (phy_id = 0; phy_id < MAX_RADIOS; phy_id++) {
+		lower_sbs_freq_range[phy_id].low_2ghz_freq =
+						ref_freq[phy_id].low_2ghz_freq;
+		lower_sbs_freq_range[phy_id].high_2ghz_freq =
+						ref_freq[phy_id].high_2ghz_freq;
+
+		/* update for shared mac */
+		if (lower_sbs_freq_range[phy_id].low_2ghz_freq) {
+			lower_sbs_freq_range[phy_id].low_5ghz_freq =
+				ath12k_wmi_get_lowest_5ghz_freq_from_range(ref_freq);
+			lower_sbs_freq_range[phy_id].high_5ghz_freq = sbs_range_sep;
+		} else {
+			lower_sbs_freq_range[phy_id].low_5ghz_freq = sbs_range_sep + 10;
+			lower_sbs_freq_range[phy_id].high_5ghz_freq =
+				ath12k_wmi_get_highest_5ghz_freq_from_range(ref_freq);
+		}
+	}
+}
+
+static const char *ath12k_wmi_hw_mode_to_str(enum ath12k_hw_mode hw_mode)
+{
+	static const char * const mode_str[] = {
+		[ATH12K_HW_MODE_SMM] = "SMM",
+		[ATH12K_HW_MODE_DBS] = "DBS",
+		[ATH12K_HW_MODE_SBS] = "SBS",
+		[ATH12K_HW_MODE_SBS_UPPER_SHARE] = "SBS_UPPER_SHARE",
+		[ATH12K_HW_MODE_SBS_LOWER_SHARE] = "SBS_LOWER_SHARE",
+	};
+
+	if (hw_mode >= ARRAY_SIZE(mode_str))
+		return "Unknown";
+
+	return mode_str[hw_mode];
+}
+
+static void
+ath12k_wmi_dump_freq_range_per_mac(struct ath12k_base *ab,
+				   struct ath12k_hw_mode_freq_range_arg *freq_range,
+				   enum ath12k_hw_mode hw_mode)
+{
+	u8 i;
+
+	for (i = 0; i < MAX_RADIOS; i++)
+		if (freq_range[i].low_2ghz_freq || freq_range[i].low_5ghz_freq)
+			ath12k_dbg(ab, ATH12K_DBG_WMI,
+				   "frequency range: %s(%d) mac %d 2 GHz [%d - %d] 5 GHz [%d - %d]",
+				   ath12k_wmi_hw_mode_to_str(hw_mode),
+				   hw_mode, i,
+				   freq_range[i].low_2ghz_freq,
+				   freq_range[i].high_2ghz_freq,
+				   freq_range[i].low_5ghz_freq,
+				   freq_range[i].high_5ghz_freq);
+}
+
+static void ath12k_wmi_dump_freq_range(struct ath12k_base *ab)
+{
+	struct ath12k_hw_mode_freq_range_arg *freq_range;
+	u8 i;
+
+	for (i = ATH12K_HW_MODE_SMM; i < ATH12K_HW_MODE_MAX; i++) {
+		freq_range = ab->wmi_ab.hw_mode_info.freq_range_caps[i];
+		ath12k_wmi_dump_freq_range_per_mac(ab, freq_range, i);
+	}
+}
+
+static int ath12k_wmi_modify_sbs_freq(struct ath12k_base *ab, u8 phy_id)
+{
+	struct ath12k_hw_mode_info *hw_mode_info = &ab->wmi_ab.hw_mode_info;
+	struct ath12k_hw_mode_freq_range_arg *sbs_mac_range, *shared_mac_range;
+	struct ath12k_hw_mode_freq_range_arg *non_shared_range;
+	u8 shared_phy_id;
+
+	sbs_mac_range = &hw_mode_info->freq_range_caps[ATH12K_HW_MODE_SBS][phy_id];
+
+	/* if SBS mac range has both 2.4 and 5 GHz ranges, i.e. shared phy_id
+	 * keep the range as it is in SBS
+	 */
+	if (sbs_mac_range->low_2ghz_freq && sbs_mac_range->low_5ghz_freq)
+		return 0;
+
+	if (sbs_mac_range->low_2ghz_freq && !sbs_mac_range->low_5ghz_freq) {
+		ath12k_err(ab, "Invalid DBS/SBS mode with only 2.4Ghz");
+		ath12k_wmi_dump_freq_range_per_mac(ab, sbs_mac_range, ATH12K_HW_MODE_SBS);
+		return -EINVAL;
+	}
+
+	non_shared_range = sbs_mac_range;
+	/* if SBS mac range has only 5 GHz then it's the non-shared phy, so
+	 * modify the range as per the shared mac.
+	 */
+	shared_phy_id = phy_id ? 0 : 1;
+	shared_mac_range =
+		&hw_mode_info->freq_range_caps[ATH12K_HW_MODE_SBS][shared_phy_id];
+
+	if (shared_mac_range->low_5ghz_freq > non_shared_range->low_5ghz_freq) {
+		ath12k_dbg(ab, ATH12K_DBG_WMI, "high 5 GHz shared");
+		/* If the shared mac lower 5 GHz frequency is greater than
+		 * non-shared mac lower 5 GHz frequency then the shared mac has
+		 * high 5 GHz shared with 2.4 GHz. So non-shared mac's 5 GHz high
+		 * freq should be less than the shared mac's low 5 GHz freq.
+		 */
+		if (non_shared_range->high_5ghz_freq >=
+		    shared_mac_range->low_5ghz_freq)
+			non_shared_range->high_5ghz_freq =
+				max_t(u32, shared_mac_range->low_5ghz_freq - 10,
+				      non_shared_range->low_5ghz_freq);
+	} else if (shared_mac_range->high_5ghz_freq <
+		   non_shared_range->high_5ghz_freq) {
+		ath12k_dbg(ab, ATH12K_DBG_WMI, "low 5 GHz shared");
+		/* If the shared mac high 5 GHz frequency is less than
+		 * non-shared mac high 5 GHz frequency then the shared mac has
+		 * low 5 GHz shared with 2.4 GHz. So non-shared mac's 5 GHz low
+		 * freq should be greater than the shared mac's high 5 GHz freq.
+		 */
+		if (shared_mac_range->high_5ghz_freq >=
+		    non_shared_range->low_5ghz_freq)
+			non_shared_range->low_5ghz_freq =
+				min_t(u32, shared_mac_range->high_5ghz_freq + 10,
+				      non_shared_range->high_5ghz_freq);
+	} else {
+		ath12k_warn(ab, "invalid SBS range with all 5 GHz shared");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static void ath12k_wmi_update_sbs_freq_info(struct ath12k_base *ab)
+{
+	struct ath12k_hw_mode_info *hw_mode_info = &ab->wmi_ab.hw_mode_info;
+	struct ath12k_hw_mode_freq_range_arg *mac_range;
+	u16 sbs_range_sep;
+	u8 phy_id;
+	int ret;
+
+	mac_range = hw_mode_info->freq_range_caps[ATH12K_HW_MODE_SBS];
+
+	/* If sbs_lower_band_end_freq has a value, then the frequency range
+	 * will be split using that value.
+	 */
+	sbs_range_sep = ab->wmi_ab.sbs_lower_band_end_freq;
+	if (sbs_range_sep) {
+		ath12k_wmi_fill_upper_share_sbs_freq(ab, sbs_range_sep,
+						     mac_range);
+		ath12k_wmi_fill_lower_share_sbs_freq(ab, sbs_range_sep,
+						     mac_range);
+		/* Hardware specifies the range boundary with sbs_range_sep,
+		 * (i.e. the boundary between 5 GHz high and 5 GHz low),
+		 * reset the original one to make sure it will not get used.
+		 */
+		memset(mac_range, 0, sizeof(*mac_range) * MAX_RADIOS);
+		return;
+	}
+
+	/* If sbs_lower_band_end_freq is not set that means firmware will send one
+	 * shared mac range and one non-shared mac range. so update that freq.
+	 */
+	for (phy_id = 0; phy_id < MAX_RADIOS; phy_id++) {
+		ret = ath12k_wmi_modify_sbs_freq(ab, phy_id);
+		if (ret) {
+			memset(mac_range, 0, sizeof(*mac_range) * MAX_RADIOS);
+			break;
+		}
+	}
+}
+
+static void
+ath12k_wmi_update_mac_freq_info(struct ath12k_base *ab,
+				enum wmi_host_hw_mode_config_type hw_config_type,
+				u32 phy_id,
+				struct ath12k_svc_ext_mac_phy_info *mac_cap)
+{
+	if (phy_id >= MAX_RADIOS) {
+		ath12k_err(ab, "mac more than two not supported: %d", phy_id);
+		return;
+	}
+
+	ath12k_dbg(ab, ATH12K_DBG_WMI,
+		   "hw_mode_cfg %d mac %d band 0x%x SBS cutoff freq %d 2 GHz [%d - %d] 5 GHz [%d - %d]",
+		   hw_config_type, phy_id, mac_cap->supported_bands,
+		   ab->wmi_ab.sbs_lower_band_end_freq,
+		   mac_cap->hw_freq_range.low_2ghz_freq,
+		   mac_cap->hw_freq_range.high_2ghz_freq,
+		   mac_cap->hw_freq_range.low_5ghz_freq,
+		   mac_cap->hw_freq_range.high_5ghz_freq);
+
+	switch (hw_config_type) {
+	case WMI_HOST_HW_MODE_SINGLE:
+		if (phy_id) {
+			ath12k_dbg(ab, ATH12K_DBG_WMI, "mac phy 1 is not supported");
+			break;
+		}
+		ath12k_wmi_update_freq_info(ab, mac_cap, ATH12K_HW_MODE_SMM, phy_id);
+		break;
+
+	case WMI_HOST_HW_MODE_DBS:
+		if (!ath12k_wmi_all_phy_range_updated(ab, ATH12K_HW_MODE_DBS))
+			ath12k_wmi_update_freq_info(ab, mac_cap,
+						    ATH12K_HW_MODE_DBS, phy_id);
+		break;
+	case WMI_HOST_HW_MODE_DBS_SBS:
+	case WMI_HOST_HW_MODE_DBS_OR_SBS:
+		ath12k_wmi_update_freq_info(ab, mac_cap, ATH12K_HW_MODE_DBS, phy_id);
+		if (ab->wmi_ab.sbs_lower_band_end_freq ||
+		    mac_cap->hw_freq_range.low_5ghz_freq ||
+		    mac_cap->hw_freq_range.low_2ghz_freq)
+			ath12k_wmi_update_freq_info(ab, mac_cap, ATH12K_HW_MODE_SBS,
+						    phy_id);
+
+		if (ath12k_wmi_all_phy_range_updated(ab, ATH12K_HW_MODE_DBS))
+			ath12k_wmi_update_dbs_freq_info(ab);
+		if (ath12k_wmi_all_phy_range_updated(ab, ATH12K_HW_MODE_SBS))
+			ath12k_wmi_update_sbs_freq_info(ab);
+		break;
+	case WMI_HOST_HW_MODE_SBS:
+	case WMI_HOST_HW_MODE_SBS_PASSIVE:
+		ath12k_wmi_update_freq_info(ab, mac_cap, ATH12K_HW_MODE_SBS, phy_id);
+		if (ath12k_wmi_all_phy_range_updated(ab, ATH12K_HW_MODE_SBS))
+			ath12k_wmi_update_sbs_freq_info(ab);
+
+		break;
+	default:
+		break;
+	}
+}
+
+static bool ath12k_wmi_sbs_range_present(struct ath12k_base *ab)
+{
+	if (ath12k_wmi_all_phy_range_updated(ab, ATH12K_HW_MODE_SBS) ||
+	    (ab->wmi_ab.sbs_lower_band_end_freq &&
+	     ath12k_wmi_all_phy_range_updated(ab, ATH12K_HW_MODE_SBS_LOWER_SHARE) &&
+	     ath12k_wmi_all_phy_range_updated(ab, ATH12K_HW_MODE_SBS_UPPER_SHARE)))
+		return true;
+
+	return false;
+}
+
+static int ath12k_wmi_update_hw_mode_list(struct ath12k_base *ab)
+{
+	struct ath12k_svc_ext_info *svc_ext_info = &ab->wmi_ab.svc_ext_info;
+	struct ath12k_hw_mode_info *info = &ab->wmi_ab.hw_mode_info;
+	enum wmi_host_hw_mode_config_type hw_config_type;
+	struct ath12k_svc_ext_mac_phy_info *tmp;
+	bool dbs_mode = false, sbs_mode = false;
+	u32 i, j = 0;
+
+	if (!svc_ext_info->num_hw_modes) {
+		ath12k_err(ab, "invalid number of hw modes");
+		return -EINVAL;
+	}
+
+	ath12k_dbg(ab, ATH12K_DBG_WMI, "updated HW mode list: num modes %d",
+		   svc_ext_info->num_hw_modes);
+
+	memset(info->freq_range_caps, 0, sizeof(info->freq_range_caps));
+
+	for (i = 0; i < svc_ext_info->num_hw_modes; i++) {
+		if (j >= ATH12K_MAX_MAC_PHY_CAP)
+			return -EINVAL;
+
+		/* Update for MAC0 */
+		tmp = &svc_ext_info->mac_phy_info[j++];
+		hw_config_type = tmp->hw_mode_config_type;
+		ath12k_wmi_update_mac_freq_info(ab, hw_config_type, tmp->phy_id, tmp);
+
+		/* SBS and DBS have dual MAC. Up to 2 MACs are considered. */
+		if (hw_config_type == WMI_HOST_HW_MODE_DBS ||
+		    hw_config_type == WMI_HOST_HW_MODE_SBS_PASSIVE ||
+		    hw_config_type == WMI_HOST_HW_MODE_SBS ||
+		    hw_config_type == WMI_HOST_HW_MODE_DBS_OR_SBS) {
+			if (j >= ATH12K_MAX_MAC_PHY_CAP)
+				return -EINVAL;
+			/* Update for MAC1 */
+			tmp = &svc_ext_info->mac_phy_info[j++];
+			ath12k_wmi_update_mac_freq_info(ab, hw_config_type,
+							tmp->phy_id, tmp);
+
+			if (hw_config_type == WMI_HOST_HW_MODE_DBS ||
+			    hw_config_type == WMI_HOST_HW_MODE_DBS_OR_SBS)
+				dbs_mode = true;
+
+			if (ath12k_wmi_sbs_range_present(ab) &&
+			    (hw_config_type == WMI_HOST_HW_MODE_SBS_PASSIVE ||
+			     hw_config_type == WMI_HOST_HW_MODE_SBS ||
+			     hw_config_type == WMI_HOST_HW_MODE_DBS_OR_SBS))
+				sbs_mode = true;
+		}
+	}
+
+	info->support_dbs = dbs_mode;
+	info->support_sbs = sbs_mode;
+
+	ath12k_wmi_dump_freq_range(ab);
+
+	return 0;
+}
+
 static int ath12k_wmi_svc_rdy_ext2_parse(struct ath12k_base *ab,
 					 u16 tag, u16 len,
 					 const void *ptr, void *data)
@@ -5054,8 +5492,16 @@ static int ath12k_wmi_svc_rdy_ext2_parse(struct ath12k_base *ab,
 			ath12k_dbg(ab, ATH12K_DBG_WMI, "sbs_lower_band_end_freq %u\n",
 				   ab->wmi_ab.sbs_lower_band_end_freq);
 
+			ret = ath12k_wmi_update_hw_mode_list(ab);
+			if (ret) {
+				ath12k_warn(ab, "failed to update hw mode list: %d\n",
+					    ret);
+				return ret;
+			}
+
 			parse->dbs_or_sbs_cap_ext_done = true;
 		}
+
 		break;
 	default:
 		break;
diff --git a/drivers/net/wireless/ath/ath12k/wmi.h b/drivers/net/wireless/ath/ath12k/wmi.h
index e69d53054f6d..f2a04a7bd91a 100644
--- a/drivers/net/wireless/ath/ath12k/wmi.h
+++ b/drivers/net/wireless/ath/ath12k/wmi.h
@@ -5083,6 +5083,32 @@ struct ath12k_svc_ext_info {
 	struct ath12k_svc_ext_mac_phy_info mac_phy_info[ATH12K_MAX_MAC_PHY_CAP];
 };
 
+/**
+ * enum ath12k_hw_mode - enum for host mode
+ * @ATH12K_HW_MODE_SMM: Single mac mode
+ * @ATH12K_HW_MODE_DBS: DBS mode
+ * @ATH12K_HW_MODE_SBS: SBS mode with either high share or low share
+ * @ATH12K_HW_MODE_SBS_UPPER_SHARE: Higher 5 GHz shared with 2.4 GHz
+ * @ATH12K_HW_MODE_SBS_LOWER_SHARE: Lower 5 GHz shared with 2.4 GHz
+ * @ATH12K_HW_MODE_MAX: Max, used to indicate invalid mode
+ */
+enum ath12k_hw_mode {
+	ATH12K_HW_MODE_SMM,
+	ATH12K_HW_MODE_DBS,
+	ATH12K_HW_MODE_SBS,
+	ATH12K_HW_MODE_SBS_UPPER_SHARE,
+	ATH12K_HW_MODE_SBS_LOWER_SHARE,
+	ATH12K_HW_MODE_MAX,
+};
+
+struct ath12k_hw_mode_info {
+	bool support_dbs:1;
+	bool support_sbs:1;
+
+	struct ath12k_hw_mode_freq_range_arg freq_range_caps[ATH12K_HW_MODE_MAX]
+							    [MAX_RADIOS];
+};
+
 struct ath12k_wmi_base {
 	struct ath12k_base *ab;
 	struct ath12k_wmi_pdev wmi[MAX_RADIOS];
@@ -5103,6 +5129,7 @@ struct ath12k_wmi_base {
 
 	struct ath12k_svc_ext_info svc_ext_info;
 	u32 sbs_lower_band_end_freq;
+	struct ath12k_hw_mode_info hw_mode_info;
 };
 
 struct wmi_pdev_set_bios_interface_cmd {

From c36f2cd628f9df6ffb19c23eedaa666440b8f5c5 Mon Sep 17 00:00:00 2001
From: Baochen Qiang <quic_bqiang@quicinc.com>
Date: Thu, 22 May 2025 16:54:13 +0800
Subject: [PATCH 0509/1334] wifi: ath12k: support WMI_MLO_LINK_SET_ACTIVE_CMDID
 command

Add WMI_MLO_LINK_SET_ACTIVE_CMDID command. This command allows host to
send required link information to firmware such that firmware can make
decision on activating/deactivating links in various scenarios.

Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.1.c5-00284-QCAHMTSWPL_V1.0_V2.0_SILICONZ-1
Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.4.1-00199-QCAHKSWPL_SILICONZ-1

Signed-off-by: Baochen Qiang <quic_bqiang@quicinc.com>
Reviewed-by: Vasanthakumar Thiagarajan <vasanthakumar.thiagarajan@oss.qualcomm.com>
Link: https://patch.msgid.link/20250522-ath12k-sbs-dbs-v1-4-54a29e7a3a88@quicinc.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/wmi.c | 221 ++++++++++++++++++++++++++
 drivers/net/wireless/ath/ath12k/wmi.h | 116 +++++++++++++-
 2 files changed, 336 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/ath12k/wmi.c b/drivers/net/wireless/ath/ath12k/wmi.c
index 034c18f6a2d2..6dbd272db1d5 100644
--- a/drivers/net/wireless/ath/ath12k/wmi.c
+++ b/drivers/net/wireless/ath/ath12k/wmi.c
@@ -10498,3 +10498,224 @@ int ath12k_wmi_send_vdev_set_tpc_power(struct ath12k *ar,
 
 	return 0;
 }
+
+static int
+ath12k_wmi_fill_disallowed_bmap(struct ath12k_base *ab,
+				struct wmi_disallowed_mlo_mode_bitmap_params *dislw_bmap,
+				struct wmi_mlo_link_set_active_arg *arg)
+{
+	struct wmi_ml_disallow_mode_bmap_arg *dislw_bmap_arg;
+	u8 i;
+
+	if (arg->num_disallow_mode_comb >
+	    ARRAY_SIZE(arg->disallow_bmap)) {
+		ath12k_warn(ab, "invalid num_disallow_mode_comb: %d",
+			    arg->num_disallow_mode_comb);
+		return -EINVAL;
+	}
+
+	dislw_bmap_arg = &arg->disallow_bmap[0];
+	for (i = 0; i < arg->num_disallow_mode_comb; i++) {
+		dislw_bmap->tlv_header =
+				ath12k_wmi_tlv_cmd_hdr(0, sizeof(*dislw_bmap));
+		dislw_bmap->disallowed_mode_bitmap =
+				cpu_to_le32(dislw_bmap_arg->disallowed_mode);
+		dislw_bmap->ieee_link_id_comb =
+			le32_encode_bits(dislw_bmap_arg->ieee_link_id[0],
+					 WMI_DISALW_MLO_MODE_BMAP_IEEE_LINK_ID_COMB_1) |
+			le32_encode_bits(dislw_bmap_arg->ieee_link_id[1],
+					 WMI_DISALW_MLO_MODE_BMAP_IEEE_LINK_ID_COMB_2) |
+			le32_encode_bits(dislw_bmap_arg->ieee_link_id[2],
+					 WMI_DISALW_MLO_MODE_BMAP_IEEE_LINK_ID_COMB_3) |
+			le32_encode_bits(dislw_bmap_arg->ieee_link_id[3],
+					 WMI_DISALW_MLO_MODE_BMAP_IEEE_LINK_ID_COMB_4);
+
+		ath12k_dbg(ab, ATH12K_DBG_WMI,
+			   "entry %d disallowed_mode %d ieee_link_id_comb 0x%x",
+			   i, dislw_bmap_arg->disallowed_mode,
+			   dislw_bmap_arg->ieee_link_id_comb);
+		dislw_bmap++;
+		dislw_bmap_arg++;
+	}
+
+	return 0;
+}
+
+int ath12k_wmi_send_mlo_link_set_active_cmd(struct ath12k_base *ab,
+					    struct wmi_mlo_link_set_active_arg *arg)
+{
+	struct wmi_disallowed_mlo_mode_bitmap_params *disallowed_mode_bmap;
+	struct wmi_mlo_set_active_link_number_params *link_num_param;
+	u32 num_link_num_param = 0, num_vdev_bitmap = 0;
+	struct ath12k_wmi_base *wmi_ab = &ab->wmi_ab;
+	struct wmi_mlo_link_set_active_cmd *cmd;
+	u32 num_inactive_vdev_bitmap = 0;
+	u32 num_disallow_mode_comb = 0;
+	struct wmi_tlv *tlv;
+	struct sk_buff *skb;
+	__le32 *vdev_bitmap;
+	void *buf_ptr;
+	int i, ret;
+	u32 len;
+
+	if (!arg->num_vdev_bitmap && !arg->num_link_entry) {
+		ath12k_warn(ab, "Invalid num_vdev_bitmap and num_link_entry");
+		return -EINVAL;
+	}
+
+	switch (arg->force_mode) {
+	case WMI_MLO_LINK_FORCE_MODE_ACTIVE_LINK_NUM:
+	case WMI_MLO_LINK_FORCE_MODE_INACTIVE_LINK_NUM:
+		num_link_num_param = arg->num_link_entry;
+		fallthrough;
+	case WMI_MLO_LINK_FORCE_MODE_ACTIVE:
+	case WMI_MLO_LINK_FORCE_MODE_INACTIVE:
+	case WMI_MLO_LINK_FORCE_MODE_NO_FORCE:
+		num_vdev_bitmap = arg->num_vdev_bitmap;
+		break;
+	case WMI_MLO_LINK_FORCE_MODE_ACTIVE_INACTIVE:
+		num_vdev_bitmap = arg->num_vdev_bitmap;
+		num_inactive_vdev_bitmap = arg->num_inactive_vdev_bitmap;
+		break;
+	default:
+		ath12k_warn(ab, "Invalid force mode: %u", arg->force_mode);
+		return -EINVAL;
+	}
+
+	num_disallow_mode_comb = arg->num_disallow_mode_comb;
+	len = sizeof(*cmd) +
+	      TLV_HDR_SIZE + sizeof(*link_num_param) * num_link_num_param +
+	      TLV_HDR_SIZE + sizeof(*vdev_bitmap) * num_vdev_bitmap +
+	      TLV_HDR_SIZE + TLV_HDR_SIZE + TLV_HDR_SIZE +
+	      TLV_HDR_SIZE + sizeof(*disallowed_mode_bmap) * num_disallow_mode_comb;
+	if (arg->force_mode == WMI_MLO_LINK_FORCE_MODE_ACTIVE_INACTIVE)
+		len += sizeof(*vdev_bitmap) * num_inactive_vdev_bitmap;
+
+	skb = ath12k_wmi_alloc_skb(wmi_ab, len);
+	if (!skb)
+		return -ENOMEM;
+
+	cmd = (struct wmi_mlo_link_set_active_cmd *)skb->data;
+	cmd->tlv_header = ath12k_wmi_tlv_cmd_hdr(WMI_TAG_MLO_LINK_SET_ACTIVE_CMD,
+						 sizeof(*cmd));
+	cmd->force_mode = cpu_to_le32(arg->force_mode);
+	cmd->reason = cpu_to_le32(arg->reason);
+	ath12k_dbg(ab, ATH12K_DBG_WMI,
+		   "mode %d reason %d num_link_num_param %d num_vdev_bitmap %d inactive %d num_disallow_mode_comb %d",
+		   arg->force_mode, arg->reason, num_link_num_param,
+		   num_vdev_bitmap, num_inactive_vdev_bitmap,
+		   num_disallow_mode_comb);
+
+	buf_ptr = skb->data + sizeof(*cmd);
+	tlv = buf_ptr;
+	tlv->header = ath12k_wmi_tlv_hdr(WMI_TAG_ARRAY_STRUCT,
+					 sizeof(*link_num_param) * num_link_num_param);
+	buf_ptr += TLV_HDR_SIZE;
+
+	if (num_link_num_param) {
+		cmd->ctrl_flags =
+			le32_encode_bits(arg->ctrl_flags.dync_force_link_num ? 1 : 0,
+					 CRTL_F_DYNC_FORCE_LINK_NUM);
+
+		link_num_param = buf_ptr;
+		for (i = 0; i < num_link_num_param; i++) {
+			link_num_param->tlv_header =
+				ath12k_wmi_tlv_cmd_hdr(0, sizeof(*link_num_param));
+			link_num_param->num_of_link =
+				cpu_to_le32(arg->link_num[i].num_of_link);
+			link_num_param->vdev_type =
+				cpu_to_le32(arg->link_num[i].vdev_type);
+			link_num_param->vdev_subtype =
+				cpu_to_le32(arg->link_num[i].vdev_subtype);
+			link_num_param->home_freq =
+				cpu_to_le32(arg->link_num[i].home_freq);
+			ath12k_dbg(ab, ATH12K_DBG_WMI,
+				   "entry %d num_of_link %d vdev type %d subtype %d freq %d control_flags %d",
+				   i, arg->link_num[i].num_of_link,
+				   arg->link_num[i].vdev_type,
+				   arg->link_num[i].vdev_subtype,
+				   arg->link_num[i].home_freq,
+				   __le32_to_cpu(cmd->ctrl_flags));
+			link_num_param++;
+		}
+
+		buf_ptr += sizeof(*link_num_param) * num_link_num_param;
+	}
+
+	tlv = buf_ptr;
+	tlv->header = ath12k_wmi_tlv_hdr(WMI_TAG_ARRAY_UINT32,
+					 sizeof(*vdev_bitmap) * num_vdev_bitmap);
+	buf_ptr += TLV_HDR_SIZE;
+
+	if (num_vdev_bitmap) {
+		vdev_bitmap = buf_ptr;
+		for (i = 0; i < num_vdev_bitmap; i++) {
+			vdev_bitmap[i] = cpu_to_le32(arg->vdev_bitmap[i]);
+			ath12k_dbg(ab, ATH12K_DBG_WMI, "entry %d vdev_id_bitmap 0x%x",
+				   i, arg->vdev_bitmap[i]);
+		}
+
+		buf_ptr += sizeof(*vdev_bitmap) * num_vdev_bitmap;
+	}
+
+	if (arg->force_mode == WMI_MLO_LINK_FORCE_MODE_ACTIVE_INACTIVE) {
+		tlv = buf_ptr;
+		tlv->header = ath12k_wmi_tlv_hdr(WMI_TAG_ARRAY_UINT32,
+						 sizeof(*vdev_bitmap) *
+						 num_inactive_vdev_bitmap);
+		buf_ptr += TLV_HDR_SIZE;
+
+		if (num_inactive_vdev_bitmap) {
+			vdev_bitmap = buf_ptr;
+			for (i = 0; i < num_inactive_vdev_bitmap; i++) {
+				vdev_bitmap[i] =
+					cpu_to_le32(arg->inactive_vdev_bitmap[i]);
+				ath12k_dbg(ab, ATH12K_DBG_WMI,
+					   "entry %d inactive_vdev_id_bitmap 0x%x",
+					    i, arg->inactive_vdev_bitmap[i]);
+			}
+
+			buf_ptr += sizeof(*vdev_bitmap) * num_inactive_vdev_bitmap;
+		}
+	} else {
+		/* add empty vdev bitmap2 tlv */
+		tlv = buf_ptr;
+		tlv->header = ath12k_wmi_tlv_hdr(WMI_TAG_ARRAY_UINT32, 0);
+		buf_ptr += TLV_HDR_SIZE;
+	}
+
+	/* add empty ieee_link_id_bitmap tlv */
+	tlv = buf_ptr;
+	tlv->header = ath12k_wmi_tlv_hdr(WMI_TAG_ARRAY_UINT32, 0);
+	buf_ptr += TLV_HDR_SIZE;
+
+	/* add empty ieee_link_id_bitmap2 tlv */
+	tlv = buf_ptr;
+	tlv->header = ath12k_wmi_tlv_hdr(WMI_TAG_ARRAY_UINT32, 0);
+	buf_ptr += TLV_HDR_SIZE;
+
+	tlv = buf_ptr;
+	tlv->header = ath12k_wmi_tlv_hdr(WMI_TAG_ARRAY_STRUCT,
+					 sizeof(*disallowed_mode_bmap) *
+					 arg->num_disallow_mode_comb);
+	buf_ptr += TLV_HDR_SIZE;
+
+	ret = ath12k_wmi_fill_disallowed_bmap(ab, buf_ptr, arg);
+	if (ret)
+		goto free_skb;
+
+	ret = ath12k_wmi_cmd_send(&wmi_ab->wmi[0], skb, WMI_MLO_LINK_SET_ACTIVE_CMDID);
+	if (ret) {
+		ath12k_warn(ab,
+			    "failed to send WMI_MLO_LINK_SET_ACTIVE_CMDID: %d\n", ret);
+		goto free_skb;
+	}
+
+	ath12k_dbg(ab, ATH12K_DBG_WMI, "WMI mlo link set active cmd");
+
+	return ret;
+
+free_skb:
+	dev_kfree_skb(skb);
+	return ret;
+}
diff --git a/drivers/net/wireless/ath/ath12k/wmi.h b/drivers/net/wireless/ath/ath12k/wmi.h
index f2a04a7bd91a..c640ffa180c8 100644
--- a/drivers/net/wireless/ath/ath12k/wmi.h
+++ b/drivers/net/wireless/ath/ath12k/wmi.h
@@ -1974,6 +1974,7 @@ enum wmi_tlv_tag {
 	WMI_TAG_TPC_STATS_CTL_PWR_TABLE_EVENT,
 	WMI_TAG_VDEV_SET_TPC_POWER_CMD = 0x3B5,
 	WMI_TAG_VDEV_CH_POWER_INFO,
+	WMI_TAG_MLO_LINK_SET_ACTIVE_CMD = 0x3BE,
 	WMI_TAG_EHT_RATE_SET = 0x3C4,
 	WMI_TAG_DCS_AWGN_INT_TYPE = 0x3C5,
 	WMI_TAG_MLO_TX_SEND_PARAMS,
@@ -6061,6 +6062,118 @@ struct wmi_vdev_set_tpc_power_cmd {
 	 */
 } __packed;
 
+#define CRTL_F_DYNC_FORCE_LINK_NUM GENMASK(3, 2)
+
+struct wmi_mlo_link_set_active_cmd {
+	__le32 tlv_header;
+	__le32 force_mode;
+	__le32 reason;
+	__le32 use_ieee_link_id_bitmap;
+	struct ath12k_wmi_mac_addr_params ap_mld_mac_addr;
+	__le32 ctrl_flags;
+} __packed;
+
+struct wmi_mlo_set_active_link_number_params {
+	__le32 tlv_header;
+	__le32 num_of_link;
+	__le32 vdev_type;
+	__le32 vdev_subtype;
+	__le32 home_freq;
+} __packed;
+
+#define WMI_DISALW_MLO_MODE_BMAP_IEEE_LINK_ID_COMB_1 GENMASK(7, 0)
+#define WMI_DISALW_MLO_MODE_BMAP_IEEE_LINK_ID_COMB_2 GENMASK(15, 8)
+#define WMI_DISALW_MLO_MODE_BMAP_IEEE_LINK_ID_COMB_3 GENMASK(23, 16)
+#define WMI_DISALW_MLO_MODE_BMAP_IEEE_LINK_ID_COMB_4 GENMASK(31, 24)
+
+struct wmi_disallowed_mlo_mode_bitmap_params {
+	__le32 tlv_header;
+	__le32 disallowed_mode_bitmap;
+	__le32 ieee_link_id_comb;
+} __packed;
+
+enum wmi_mlo_link_force_mode {
+	WMI_MLO_LINK_FORCE_MODE_ACTIVE			= 1,
+	WMI_MLO_LINK_FORCE_MODE_INACTIVE		= 2,
+	WMI_MLO_LINK_FORCE_MODE_ACTIVE_LINK_NUM		= 3,
+	WMI_MLO_LINK_FORCE_MODE_INACTIVE_LINK_NUM	= 4,
+	WMI_MLO_LINK_FORCE_MODE_NO_FORCE		= 5,
+	WMI_MLO_LINK_FORCE_MODE_ACTIVE_INACTIVE		= 6,
+	WMI_MLO_LINK_FORCE_MODE_NON_FORCE_UPDATE	= 7,
+};
+
+enum wmi_mlo_link_force_reason {
+	WMI_MLO_LINK_FORCE_REASON_NEW_CONNECT		= 1,
+	WMI_MLO_LINK_FORCE_REASON_NEW_DISCONNECT	= 2,
+	WMI_MLO_LINK_FORCE_REASON_LINK_REMOVAL		= 3,
+	WMI_MLO_LINK_FORCE_REASON_TDLS			= 4,
+	WMI_MLO_LINK_FORCE_REASON_REVERT_FAILURE	= 5,
+	WMI_MLO_LINK_FORCE_REASON_LINK_DELETE		= 6,
+	WMI_MLO_LINK_FORCE_REASON_SINGLE_LINK_EMLSR_OP	= 7,
+};
+
+struct wmi_mlo_link_num_arg {
+	u32 num_of_link;
+	u32 vdev_type;
+	u32 vdev_subtype;
+	u32 home_freq;
+};
+
+struct wmi_mlo_control_flags_arg {
+	bool overwrite_force_active_bitmap;
+	bool overwrite_force_inactive_bitmap;
+	bool dync_force_link_num;
+	bool post_re_evaluate;
+	u8 post_re_evaluate_loops;
+	bool dont_reschedule_workqueue;
+};
+
+struct wmi_ml_link_force_cmd_arg {
+	u8 ap_mld_mac_addr[ETH_ALEN];
+	u16 ieee_link_id_bitmap;
+	u16 ieee_link_id_bitmap2;
+	u8 link_num;
+};
+
+struct wmi_ml_disallow_mode_bmap_arg {
+	u32 disallowed_mode;
+	union {
+		u32 ieee_link_id_comb;
+		u8 ieee_link_id[4];
+	};
+};
+
+/* maximum size of link number param array
+ * for MLO link set active command
+ */
+#define WMI_MLO_LINK_NUM_SZ 2
+
+/* maximum size of vdev bitmap array for
+ * MLO link set active command
+ */
+#define WMI_MLO_VDEV_BITMAP_SZ 2
+
+/* Max number of disallowed bitmap combination
+ * sent to firmware
+ */
+#define WMI_ML_MAX_DISALLOW_BMAP_COMB 4
+
+struct wmi_mlo_link_set_active_arg {
+	enum wmi_mlo_link_force_mode force_mode;
+	enum wmi_mlo_link_force_reason reason;
+	u32 num_link_entry;
+	u32 num_vdev_bitmap;
+	u32 num_inactive_vdev_bitmap;
+	struct wmi_mlo_link_num_arg link_num[WMI_MLO_LINK_NUM_SZ];
+	u32 vdev_bitmap[WMI_MLO_VDEV_BITMAP_SZ];
+	u32 inactive_vdev_bitmap[WMI_MLO_VDEV_BITMAP_SZ];
+	struct wmi_mlo_control_flags_arg ctrl_flags;
+	bool use_ieee_link_id;
+	struct wmi_ml_link_force_cmd_arg force_cmd;
+	u32 num_disallow_mode_comb;
+	struct wmi_ml_disallow_mode_bmap_arg disallow_bmap[WMI_ML_MAX_DISALLOW_BMAP_COMB];
+};
+
 void ath12k_wmi_init_qcn9274(struct ath12k_base *ab,
 			     struct ath12k_wmi_resource_config_arg *config);
 void ath12k_wmi_init_wcn7850(struct ath12k_base *ab,
@@ -6259,5 +6372,6 @@ bool ath12k_wmi_supports_6ghz_cc_ext(struct ath12k *ar);
 int ath12k_wmi_send_vdev_set_tpc_power(struct ath12k *ar,
 				       u32 vdev_id,
 				       struct ath12k_reg_tpc_power_info *param);
-
+int ath12k_wmi_send_mlo_link_set_active_cmd(struct ath12k_base *ab,
+					    struct wmi_mlo_link_set_active_arg *param);
 #endif

From 2296038fd35a6e57af77496affe9044293ed2947 Mon Sep 17 00:00:00 2001
From: Baochen Qiang <quic_bqiang@quicinc.com>
Date: Thu, 22 May 2025 16:54:14 +0800
Subject: [PATCH 0510/1334] wifi: ath12k: update link active in case two links
 fall on the same MAC

In case of two links established on the same device in an ML connection,
depending on device's hardware mode capability, it is possible that both
links fall on the same MAC. Currently, no specific action is taken to
address this but just keep both links active. However this would result
in lower throughput compared to even one link, because switching between
these two links on the resulted MAC significantly impacts throughput.

Check if both links fall in the frequency range of a single MAC. If
so, send WMI_MLO_LINK_SET_ACTIVE_CMDID command to firmware such that
firmware can deactivate one of them. Note the decision of which link
getting deactivated is made by firmware, host only sends the vdev
lists.

Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.1.c5-00284-QCAHMTSWPL_V1.0_V2.0_SILICONZ-1
Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.4.1-00199-QCAHKSWPL_SILICONZ-1

Signed-off-by: Baochen Qiang <quic_bqiang@quicinc.com>
Reviewed-by: Vasanthakumar Thiagarajan <vasanthakumar.thiagarajan@oss.qualcomm.com>
Link: https://patch.msgid.link/20250522-ath12k-sbs-dbs-v1-5-54a29e7a3a88@quicinc.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/mac.c | 227 +++++++++++++++++++++++++-
 drivers/net/wireless/ath/ath12k/mac.h |   2 +
 2 files changed, 228 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/ath12k/mac.c b/drivers/net/wireless/ath/ath12k/mac.c
index 88b59f3ff87a..2fae4b01ec90 100644
--- a/drivers/net/wireless/ath/ath12k/mac.c
+++ b/drivers/net/wireless/ath/ath12k/mac.c
@@ -5890,6 +5890,211 @@ exit:
 	return ret;
 }
 
+static bool ath12k_mac_is_freq_on_mac(struct ath12k_hw_mode_freq_range_arg *freq_range,
+				      u32 freq, u8 mac_id)
+{
+	return (freq >= freq_range[mac_id].low_2ghz_freq &&
+		freq <= freq_range[mac_id].high_2ghz_freq) ||
+	       (freq >= freq_range[mac_id].low_5ghz_freq &&
+		freq <= freq_range[mac_id].high_5ghz_freq);
+}
+
+static bool
+ath12k_mac_2_freq_same_mac_in_freq_range(struct ath12k_base *ab,
+					 struct ath12k_hw_mode_freq_range_arg *freq_range,
+					 u32 freq_link1, u32 freq_link2)
+{
+	u8 i;
+
+	for (i = 0; i < MAX_RADIOS; i++) {
+		if (ath12k_mac_is_freq_on_mac(freq_range, freq_link1, i) &&
+		    ath12k_mac_is_freq_on_mac(freq_range, freq_link2, i))
+			return true;
+	}
+
+	return false;
+}
+
+static bool ath12k_mac_is_hw_dbs_capable(struct ath12k_base *ab)
+{
+	return test_bit(WMI_TLV_SERVICE_DUAL_BAND_SIMULTANEOUS_SUPPORT,
+			ab->wmi_ab.svc_map) &&
+	       ab->wmi_ab.hw_mode_info.support_dbs;
+}
+
+static bool ath12k_mac_2_freq_same_mac_in_dbs(struct ath12k_base *ab,
+					      u32 freq_link1, u32 freq_link2)
+{
+	struct ath12k_hw_mode_freq_range_arg *freq_range;
+
+	if (!ath12k_mac_is_hw_dbs_capable(ab))
+		return true;
+
+	freq_range = ab->wmi_ab.hw_mode_info.freq_range_caps[ATH12K_HW_MODE_DBS];
+	return ath12k_mac_2_freq_same_mac_in_freq_range(ab, freq_range,
+							freq_link1, freq_link2);
+}
+
+static bool ath12k_mac_is_hw_sbs_capable(struct ath12k_base *ab)
+{
+	return test_bit(WMI_TLV_SERVICE_DUAL_BAND_SIMULTANEOUS_SUPPORT,
+			ab->wmi_ab.svc_map) &&
+	       ab->wmi_ab.hw_mode_info.support_sbs;
+}
+
+static bool ath12k_mac_2_freq_same_mac_in_sbs(struct ath12k_base *ab,
+					      u32 freq_link1, u32 freq_link2)
+{
+	struct ath12k_hw_mode_info *info = &ab->wmi_ab.hw_mode_info;
+	struct ath12k_hw_mode_freq_range_arg *sbs_uppr_share;
+	struct ath12k_hw_mode_freq_range_arg *sbs_low_share;
+	struct ath12k_hw_mode_freq_range_arg *sbs_range;
+
+	if (!ath12k_mac_is_hw_sbs_capable(ab))
+		return true;
+
+	if (ab->wmi_ab.sbs_lower_band_end_freq) {
+		sbs_uppr_share = info->freq_range_caps[ATH12K_HW_MODE_SBS_UPPER_SHARE];
+		sbs_low_share = info->freq_range_caps[ATH12K_HW_MODE_SBS_LOWER_SHARE];
+
+		return ath12k_mac_2_freq_same_mac_in_freq_range(ab, sbs_low_share,
+								freq_link1, freq_link2) ||
+		       ath12k_mac_2_freq_same_mac_in_freq_range(ab, sbs_uppr_share,
+								freq_link1, freq_link2);
+	}
+
+	sbs_range = info->freq_range_caps[ATH12K_HW_MODE_SBS];
+	return ath12k_mac_2_freq_same_mac_in_freq_range(ab, sbs_range,
+							freq_link1, freq_link2);
+}
+
+static bool ath12k_mac_freqs_on_same_mac(struct ath12k_base *ab,
+					 u32 freq_link1, u32 freq_link2)
+{
+	return ath12k_mac_2_freq_same_mac_in_dbs(ab, freq_link1, freq_link2) &&
+	       ath12k_mac_2_freq_same_mac_in_sbs(ab, freq_link1, freq_link2);
+}
+
+static int ath12k_mac_mlo_sta_set_link_active(struct ath12k_base *ab,
+					      enum wmi_mlo_link_force_reason reason,
+					      enum wmi_mlo_link_force_mode mode,
+					      u8 *mlo_vdev_id_lst,
+					      u8 num_mlo_vdev,
+					      u8 *mlo_inactive_vdev_lst,
+					      u8 num_mlo_inactive_vdev)
+{
+	struct wmi_mlo_link_set_active_arg param = {0};
+	u32 entry_idx, entry_offset, vdev_idx;
+	u8 vdev_id;
+
+	param.reason = reason;
+	param.force_mode = mode;
+
+	for (vdev_idx = 0; vdev_idx < num_mlo_vdev; vdev_idx++) {
+		vdev_id = mlo_vdev_id_lst[vdev_idx];
+		entry_idx = vdev_id / 32;
+		entry_offset = vdev_id % 32;
+		if (entry_idx >= WMI_MLO_LINK_NUM_SZ) {
+			ath12k_warn(ab, "Invalid entry_idx %d num_mlo_vdev %d vdev %d",
+				    entry_idx, num_mlo_vdev, vdev_id);
+			return -EINVAL;
+		}
+		param.vdev_bitmap[entry_idx] |= 1 << entry_offset;
+		/* update entry number if entry index changed */
+		if (param.num_vdev_bitmap < entry_idx + 1)
+			param.num_vdev_bitmap = entry_idx + 1;
+	}
+
+	ath12k_dbg(ab, ATH12K_DBG_MAC,
+		   "num_vdev_bitmap %d vdev_bitmap[0] = 0x%x, vdev_bitmap[1] = 0x%x",
+		   param.num_vdev_bitmap, param.vdev_bitmap[0], param.vdev_bitmap[1]);
+
+	if (mode == WMI_MLO_LINK_FORCE_MODE_ACTIVE_INACTIVE) {
+		for (vdev_idx = 0; vdev_idx < num_mlo_inactive_vdev; vdev_idx++) {
+			vdev_id = mlo_inactive_vdev_lst[vdev_idx];
+			entry_idx = vdev_id / 32;
+			entry_offset = vdev_id % 32;
+			if (entry_idx >= WMI_MLO_LINK_NUM_SZ) {
+				ath12k_warn(ab, "Invalid entry_idx %d num_mlo_vdev %d vdev %d",
+					    entry_idx, num_mlo_inactive_vdev, vdev_id);
+				return -EINVAL;
+			}
+			param.inactive_vdev_bitmap[entry_idx] |= 1 << entry_offset;
+			/* update entry number if entry index changed */
+			if (param.num_inactive_vdev_bitmap < entry_idx + 1)
+				param.num_inactive_vdev_bitmap = entry_idx + 1;
+		}
+
+		ath12k_dbg(ab, ATH12K_DBG_MAC,
+			   "num_vdev_bitmap %d inactive_vdev_bitmap[0] = 0x%x, inactive_vdev_bitmap[1] = 0x%x",
+			   param.num_inactive_vdev_bitmap,
+			   param.inactive_vdev_bitmap[0],
+			   param.inactive_vdev_bitmap[1]);
+	}
+
+	if (mode == WMI_MLO_LINK_FORCE_MODE_ACTIVE_LINK_NUM ||
+	    mode == WMI_MLO_LINK_FORCE_MODE_INACTIVE_LINK_NUM) {
+		param.num_link_entry = 1;
+		param.link_num[0].num_of_link = num_mlo_vdev - 1;
+	}
+
+	return ath12k_wmi_send_mlo_link_set_active_cmd(ab, &param);
+}
+
+static int ath12k_mac_mlo_sta_update_link_active(struct ath12k_base *ab,
+						 struct ieee80211_hw *hw,
+						 struct ath12k_vif *ahvif)
+{
+	u8 mlo_vdev_id_lst[IEEE80211_MLD_MAX_NUM_LINKS] = {0};
+	u32 mlo_freq_list[IEEE80211_MLD_MAX_NUM_LINKS] = {0};
+	unsigned long links = ahvif->links_map;
+	enum wmi_mlo_link_force_reason reason;
+	struct ieee80211_chanctx_conf *conf;
+	enum wmi_mlo_link_force_mode mode;
+	struct ieee80211_bss_conf *info;
+	struct ath12k_link_vif *arvif;
+	u8 num_mlo_vdev = 0;
+	u8 link_id;
+
+	for_each_set_bit(link_id, &links, IEEE80211_MLD_MAX_NUM_LINKS) {
+		arvif = wiphy_dereference(hw->wiphy, ahvif->link[link_id]);
+		/* make sure vdev is created on this device */
+		if (!arvif || !arvif->is_created || arvif->ar->ab != ab)
+			continue;
+
+		info = ath12k_mac_get_link_bss_conf(arvif);
+		conf = wiphy_dereference(hw->wiphy, info->chanctx_conf);
+		mlo_freq_list[num_mlo_vdev] = conf->def.chan->center_freq;
+
+		mlo_vdev_id_lst[num_mlo_vdev] = arvif->vdev_id;
+		num_mlo_vdev++;
+	}
+
+	/* It is not allowed to activate more links than a single device
+	 * supported. Something goes wrong if we reach here.
+	 */
+	if (num_mlo_vdev > ATH12K_NUM_MAX_ACTIVE_LINKS_PER_DEVICE) {
+		WARN_ON_ONCE(1);
+		return -EINVAL;
+	}
+
+	/* if 2 links are established and both link channels fall on the
+	 * same hardware MAC, send command to firmware to deactivate one
+	 * of them.
+	 */
+	if (num_mlo_vdev == 2 &&
+	    ath12k_mac_freqs_on_same_mac(ab, mlo_freq_list[0],
+					 mlo_freq_list[1])) {
+		mode = WMI_MLO_LINK_FORCE_MODE_INACTIVE_LINK_NUM;
+		reason = WMI_MLO_LINK_FORCE_REASON_NEW_CONNECT;
+		return ath12k_mac_mlo_sta_set_link_active(ab, reason, mode,
+							  mlo_vdev_id_lst, num_mlo_vdev,
+							  NULL, 0);
+	}
+
+	return 0;
+}
+
 static int ath12k_mac_op_sta_state(struct ieee80211_hw *hw,
 				   struct ieee80211_vif *vif,
 				   struct ieee80211_sta *sta,
@@ -5899,10 +6104,12 @@ static int ath12k_mac_op_sta_state(struct ieee80211_hw *hw,
 	struct ath12k_vif *ahvif = ath12k_vif_to_ahvif(vif);
 	struct ath12k_sta *ahsta = ath12k_sta_to_ahsta(sta);
 	struct ath12k_hw *ah = ath12k_hw_to_ah(hw);
+	struct ath12k_base *prev_ab = NULL, *ab;
 	struct ath12k_link_vif *arvif;
 	struct ath12k_link_sta *arsta;
 	unsigned long valid_links;
-	u8 link_id = 0;
+	u8 link_id = 0, i;
+	struct ath12k *ar;
 	int ret;
 
 	lockdep_assert_wiphy(hw->wiphy);
@@ -5997,6 +6204,24 @@ static int ath12k_mac_op_sta_state(struct ieee80211_hw *hw,
 		}
 	}
 
+	if (ieee80211_vif_is_mld(vif) && vif->type == NL80211_IFTYPE_STATION &&
+	    old_state == IEEE80211_STA_ASSOC && new_state == IEEE80211_STA_AUTHORIZED) {
+		for_each_ar(ah, ar, i) {
+			ab = ar->ab;
+			if (prev_ab == ab)
+				continue;
+
+			ret = ath12k_mac_mlo_sta_update_link_active(ab, hw, ahvif);
+			if (ret) {
+				ath12k_warn(ab,
+					    "failed to update link active state on connect %d\n",
+					    ret);
+				goto exit;
+			}
+
+			prev_ab = ab;
+		}
+	}
 	/* IEEE80211_STA_NONE -> IEEE80211_STA_NOTEXIST:
 	 * Remove the station from driver (handle ML sta here since that
 	 * needs special handling. Normal sta will be handled in generic
diff --git a/drivers/net/wireless/ath/ath12k/mac.h b/drivers/net/wireless/ath/ath12k/mac.h
index e6e74b45bfa4..cc81b1f5680f 100644
--- a/drivers/net/wireless/ath/ath12k/mac.h
+++ b/drivers/net/wireless/ath/ath12k/mac.h
@@ -54,6 +54,8 @@ struct ath12k_generic_iter {
 #define ATH12K_DEFAULT_SCAN_LINK	IEEE80211_MLD_MAX_NUM_LINKS
 #define ATH12K_NUM_MAX_LINKS		(IEEE80211_MLD_MAX_NUM_LINKS + 1)
 
+#define ATH12K_NUM_MAX_ACTIVE_LINKS_PER_DEVICE	2
+
 enum ath12k_supported_bw {
 	ATH12K_BW_20    = 0,
 	ATH12K_BW_40    = 1,

From d9dbc6b8b94ab41fb8b9dbb5a7be024029d46309 Mon Sep 17 00:00:00 2001
From: Baochen Qiang <quic_bqiang@quicinc.com>
Date: Thu, 22 May 2025 16:54:15 +0800
Subject: [PATCH 0511/1334] wifi: ath12k: don't activate more links than
 firmware supports

In case of ML connection, currently all useful links are activated at
ASSOC stage:

        ieee80211_set_active_links(vif, ieee80211_vif_usable_links(vif))

this results in firmware crash when the number of links activated on the
same device is more than supported.

Since firmware supports activating at most 2 links for a ML connection,
to avoid firmware crash, host needs to select 2 links out of the useful
links. As the assoc link has already been chosen, the question becomes
how to determine partner links. A straightforward principle applied
here is that the resulted combination should achieve the best throughput.
For that purpose, ideally various factors like bandwidth, RSSI etc should
be considered. But that would be too complicate. To make it easy, the
choice is to only take hardware modes into consideration.

The SBS (single band simultaneously) mode frequency range covers 5 GHz
and 6 GHz bands. In this mode, the two individual MACs are both active,
with one working on 5g-high band and the other on 5g-low band (from
hardware perspective 5 GHz and 6 GHz bands are referred to as a 'large'
single 5 GHz band). The DBS (dual band simultaneously) mode covers 2 GHz
band and the 'large' 5 GHz band, with one MAC working on 2 GHz band and
the other working on 5 GHz band or 6 GHz band. Since 5,6 GHz bands could
provide higher bandwidth than 2 GHz band, the preference is given to SBS
mode. Other hardware modes results in only one working MAC at any given
time, so it is chosen only when both SBS are DBS are not possible.

For each hardware mode, if there are more than one partner candidate,
just choose the first one.

For now only single device MLO case is handled as it is easy. Other cases
could be addressed in the future.

Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.1.c5-00284-QCAHMTSWPL_V1.0_V2.0_SILICONZ-1
Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.4.1-00199-QCAHKSWPL_SILICONZ-1

Signed-off-by: Baochen Qiang <quic_bqiang@quicinc.com>
Reviewed-by: Vasanthakumar Thiagarajan <vasanthakumar.thiagarajan@oss.qualcomm.com>
Link: https://patch.msgid.link/20250522-ath12k-sbs-dbs-v1-6-54a29e7a3a88@quicinc.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/core.h |   6 ++
 drivers/net/wireless/ath/ath12k/mac.c  | 137 ++++++++++++++++++++++++-
 2 files changed, 141 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/core.h b/drivers/net/wireless/ath/ath12k/core.h
index 941db6e49d6e..efbd6e8ce275 100644
--- a/drivers/net/wireless/ath/ath12k/core.h
+++ b/drivers/net/wireless/ath/ath12k/core.h
@@ -601,6 +601,12 @@ struct ath12k_sta {
 #define ATH12K_NUM_CHANS 101
 #define ATH12K_MAX_5GHZ_CHAN 173
 
+static inline bool ath12k_is_2ghz_channel_freq(u32 freq)
+{
+	return freq >= ATH12K_MIN_2GHZ_FREQ &&
+	       freq <= ATH12K_MAX_2GHZ_FREQ;
+}
+
 enum ath12k_hw_state {
 	ATH12K_HW_STATE_OFF,
 	ATH12K_HW_STATE_ON,
diff --git a/drivers/net/wireless/ath/ath12k/mac.c b/drivers/net/wireless/ath/ath12k/mac.c
index 2fae4b01ec90..b5b31cd8de99 100644
--- a/drivers/net/wireless/ath/ath12k/mac.c
+++ b/drivers/net/wireless/ath/ath12k/mac.c
@@ -6095,6 +6095,122 @@ static int ath12k_mac_mlo_sta_update_link_active(struct ath12k_base *ab,
 	return 0;
 }
 
+static bool ath12k_mac_are_sbs_chan(struct ath12k_base *ab, u32 freq_1, u32 freq_2)
+{
+	if (!ath12k_mac_is_hw_sbs_capable(ab))
+		return false;
+
+	if (ath12k_is_2ghz_channel_freq(freq_1) ||
+	    ath12k_is_2ghz_channel_freq(freq_2))
+		return false;
+
+	return !ath12k_mac_2_freq_same_mac_in_sbs(ab, freq_1, freq_2);
+}
+
+static bool ath12k_mac_are_dbs_chan(struct ath12k_base *ab, u32 freq_1, u32 freq_2)
+{
+	if (!ath12k_mac_is_hw_dbs_capable(ab))
+		return false;
+
+	return !ath12k_mac_2_freq_same_mac_in_dbs(ab, freq_1, freq_2);
+}
+
+static int ath12k_mac_select_links(struct ath12k_base *ab,
+				   struct ieee80211_vif *vif,
+				   struct ieee80211_hw *hw,
+				   u16 *selected_links)
+{
+	unsigned long useful_links = ieee80211_vif_usable_links(vif);
+	struct ath12k_vif *ahvif = ath12k_vif_to_ahvif(vif);
+	u8 num_useful_links = hweight_long(useful_links);
+	struct ieee80211_chanctx_conf *chanctx;
+	struct ath12k_link_vif *assoc_arvif;
+	u32 assoc_link_freq, partner_freq;
+	u16 sbs_links = 0, dbs_links = 0;
+	struct ieee80211_bss_conf *info;
+	struct ieee80211_channel *chan;
+	struct ieee80211_sta *sta;
+	struct ath12k_sta *ahsta;
+	u8 link_id;
+
+	/* activate all useful links if less than max supported */
+	if (num_useful_links <= ATH12K_NUM_MAX_ACTIVE_LINKS_PER_DEVICE) {
+		*selected_links = useful_links;
+		return 0;
+	}
+
+	/* only in station mode we can get here, so it's safe
+	 * to use ap_addr
+	 */
+	rcu_read_lock();
+	sta = ieee80211_find_sta(vif, vif->cfg.ap_addr);
+	if (!sta) {
+		rcu_read_unlock();
+		ath12k_warn(ab, "failed to find sta with addr %pM\n", vif->cfg.ap_addr);
+		return -EINVAL;
+	}
+
+	ahsta = ath12k_sta_to_ahsta(sta);
+	assoc_arvif = wiphy_dereference(hw->wiphy, ahvif->link[ahsta->assoc_link_id]);
+	info = ath12k_mac_get_link_bss_conf(assoc_arvif);
+	chanctx = rcu_dereference(info->chanctx_conf);
+	assoc_link_freq = chanctx->def.chan->center_freq;
+	rcu_read_unlock();
+	ath12k_dbg(ab, ATH12K_DBG_MAC, "assoc link %u freq %u\n",
+		   assoc_arvif->link_id, assoc_link_freq);
+
+	/* assoc link is already activated and has to be kept active,
+	 * only need to select a partner link from others.
+	 */
+	useful_links &= ~BIT(assoc_arvif->link_id);
+	for_each_set_bit(link_id, &useful_links, IEEE80211_MLD_MAX_NUM_LINKS) {
+		info = wiphy_dereference(hw->wiphy, vif->link_conf[link_id]);
+		if (!info) {
+			ath12k_warn(ab, "failed to get link info for link: %u\n",
+				    link_id);
+			return -ENOLINK;
+		}
+
+		chan = info->chanreq.oper.chan;
+		if (!chan) {
+			ath12k_warn(ab, "failed to get chan for link: %u\n", link_id);
+			return -EINVAL;
+		}
+
+		partner_freq = chan->center_freq;
+		if (ath12k_mac_are_sbs_chan(ab, assoc_link_freq, partner_freq)) {
+			sbs_links |= BIT(link_id);
+			ath12k_dbg(ab, ATH12K_DBG_MAC, "new SBS link %u freq %u\n",
+				   link_id, partner_freq);
+			continue;
+		}
+
+		if (ath12k_mac_are_dbs_chan(ab, assoc_link_freq, partner_freq)) {
+			dbs_links |= BIT(link_id);
+			ath12k_dbg(ab, ATH12K_DBG_MAC, "new DBS link %u freq %u\n",
+				   link_id, partner_freq);
+			continue;
+		}
+
+		ath12k_dbg(ab, ATH12K_DBG_MAC, "non DBS/SBS link %u freq %u\n",
+			   link_id, partner_freq);
+	}
+
+	/* choose the first candidate no matter how many is in the list */
+	if (sbs_links)
+		link_id = __ffs(sbs_links);
+	else if (dbs_links)
+		link_id = __ffs(dbs_links);
+	else
+		link_id = ffs(useful_links) - 1;
+
+	ath12k_dbg(ab, ATH12K_DBG_MAC, "select partner link %u\n", link_id);
+
+	*selected_links = BIT(assoc_arvif->link_id) | BIT(link_id);
+
+	return 0;
+}
+
 static int ath12k_mac_op_sta_state(struct ieee80211_hw *hw,
 				   struct ieee80211_vif *vif,
 				   struct ieee80211_sta *sta,
@@ -6108,6 +6224,7 @@ static int ath12k_mac_op_sta_state(struct ieee80211_hw *hw,
 	struct ath12k_link_vif *arvif;
 	struct ath12k_link_sta *arsta;
 	unsigned long valid_links;
+	u16 selected_links = 0;
 	u8 link_id = 0, i;
 	struct ath12k *ar;
 	int ret;
@@ -6179,8 +6296,24 @@ static int ath12k_mac_op_sta_state(struct ieee80211_hw *hw,
 	 * about to move to the associated state.
 	 */
 	if (ieee80211_vif_is_mld(vif) && vif->type == NL80211_IFTYPE_STATION &&
-	    old_state == IEEE80211_STA_AUTH && new_state == IEEE80211_STA_ASSOC)
-		ieee80211_set_active_links(vif, ieee80211_vif_usable_links(vif));
+	    old_state == IEEE80211_STA_AUTH && new_state == IEEE80211_STA_ASSOC) {
+		/* TODO: for now only do link selection for single device
+		 * MLO case. Other cases would be handled in the future.
+		 */
+		ab = ah->radio[0].ab;
+		if (ab->ag->num_devices == 1) {
+			ret = ath12k_mac_select_links(ab, vif, hw, &selected_links);
+			if (ret) {
+				ath12k_warn(ab,
+					    "failed to get selected links: %d\n", ret);
+				goto exit;
+			}
+		} else {
+			selected_links = ieee80211_vif_usable_links(vif);
+		}
+
+		ieee80211_set_active_links(vif, selected_links);
+	}
 
 	/* Handle all the other state transitions in generic way */
 	valid_links = ahsta->links_map;

From a48a931a32f88157db2baa31c10738a7fe660e93 Mon Sep 17 00:00:00 2001
From: Baochen Qiang <quic_bqiang@quicinc.com>
Date: Thu, 12 Jun 2025 09:31:49 +0800
Subject: [PATCH 0512/1334] wifi: ath12k: fix documentation on firmware stats

Regarding the firmware stats events handling, the comment in
ath12k_mac_get_fw_stats() says host determines whether all events have been
received based on 'end' tag in TLV. This is wrong as there is no such tag
at all, actually host makes the decision totally by itself based on the
stats type and active pdev/vdev counts etc.

Fix it to correctly reflect the logic.

Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.1.c5-00284.1-QCAHMTSWPL_V1.0_V2.0_SILICONZ-3
Tested-on: QCN9274 hw2.0 WLAN.WBE.1.5-01651-QCAHKSWPL_SILICONZ-1

Signed-off-by: Baochen Qiang <quic_bqiang@quicinc.com>
Link: https://patch.msgid.link/20250612-ath12k-fw-fixes-v1-1-12f594f3b857@quicinc.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/mac.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/mac.c b/drivers/net/wireless/ath/ath12k/mac.c
index b5b31cd8de99..581b6c9c84ea 100644
--- a/drivers/net/wireless/ath/ath12k/mac.c
+++ b/drivers/net/wireless/ath/ath12k/mac.c
@@ -4400,9 +4400,8 @@ int ath12k_mac_get_fw_stats(struct ath12k *ar,
 	/* Firmware sends WMI_UPDATE_STATS_EVENTID back-to-back
 	 * when stats data buffer limit is reached. fw_stats_complete
 	 * is completed once host receives first event from firmware, but
-	 * still end might not be marked in the TLV.
-	 * Below loop is to confirm that firmware completed sending all the event
-	 * and fw_stats_done is marked true when end is marked in the TLV.
+	 * still there could be more events following. Below loop is to wait
+	 * until firmware completes sending all the events.
 	 */
 	for (;;) {
 		if (time_after(jiffies, timeout))

From 9a353a4a11a475578be3c02dd17e70afe3a4a7f6 Mon Sep 17 00:00:00 2001
From: Baochen Qiang <quic_bqiang@quicinc.com>
Date: Thu, 12 Jun 2025 09:31:50 +0800
Subject: [PATCH 0513/1334] wifi: ath12k: avoid burning CPU while waiting for
 firmware stats
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

ath12k_mac_get_fw_stats() is busy polling fw_stats_done flag while waiting
firmware finishing sending all events. This is not good as CPU is
monopolized and kept burning during the wait.

Change to the completion mechanism to fix it.

Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.1.c5-00284.1-QCAHMTSWPL_V1.0_V2.0_SILICONZ-3
Tested-on: QCN9274 hw2.0 WLAN.WBE.1.5-01651-QCAHKSWPL_SILICONZ-1

Fixes: e367c924768b ("wifi: ath12k: Request vdev stats from firmware")
Reported-by: Grégoire Stein <gregoire.s93@live.fr>
Closes: https://lore.kernel.org/ath12k/AS8P190MB120575BBB25FCE697CD7D4988763A@AS8P190MB1205.EURP190.PROD.OUTLOOK.COM/
Signed-off-by: Baochen Qiang <quic_bqiang@quicinc.com>
Tested-by: Grégoire Stein <gregoire.s93@live.fr>
Link: https://patch.msgid.link/20250612-ath12k-fw-fixes-v1-2-12f594f3b857@quicinc.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/core.c |  2 +-
 drivers/net/wireless/ath/ath12k/core.h |  2 +-
 drivers/net/wireless/ath/ath12k/mac.c  | 27 ++++++++------------------
 drivers/net/wireless/ath/ath12k/wmi.c  |  7 ++++---
 4 files changed, 14 insertions(+), 24 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/core.c b/drivers/net/wireless/ath/ath12k/core.c
index ebc0560d40e3..fbc62209086f 100644
--- a/drivers/net/wireless/ath/ath12k/core.c
+++ b/drivers/net/wireless/ath/ath12k/core.c
@@ -1216,6 +1216,7 @@ void ath12k_fw_stats_init(struct ath12k *ar)
 	INIT_LIST_HEAD(&ar->fw_stats.pdevs);
 	INIT_LIST_HEAD(&ar->fw_stats.bcn);
 	init_completion(&ar->fw_stats_complete);
+	init_completion(&ar->fw_stats_done);
 }
 
 void ath12k_fw_stats_free(struct ath12k_fw_stats *stats)
@@ -1228,7 +1229,6 @@ void ath12k_fw_stats_free(struct ath12k_fw_stats *stats)
 void ath12k_fw_stats_reset(struct ath12k *ar)
 {
 	spin_lock_bh(&ar->data_lock);
-	ar->fw_stats.fw_stats_done = false;
 	ath12k_fw_stats_free(&ar->fw_stats);
 	spin_unlock_bh(&ar->data_lock);
 }
diff --git a/drivers/net/wireless/ath/ath12k/core.h b/drivers/net/wireless/ath/ath12k/core.h
index efbd6e8ce275..2b2e0c16b64e 100644
--- a/drivers/net/wireless/ath/ath12k/core.h
+++ b/drivers/net/wireless/ath/ath12k/core.h
@@ -632,7 +632,6 @@ struct ath12k_fw_stats {
 	struct list_head pdevs;
 	struct list_head vdevs;
 	struct list_head bcn;
-	bool fw_stats_done;
 };
 
 struct ath12k_dbg_htt_stats {
@@ -812,6 +811,7 @@ struct ath12k {
 	bool regdom_set_by_user;
 
 	struct completion fw_stats_complete;
+	struct completion fw_stats_done;
 
 	struct completion mlo_setup_done;
 	u32 mlo_setup_status;
diff --git a/drivers/net/wireless/ath/ath12k/mac.c b/drivers/net/wireless/ath/ath12k/mac.c
index 581b6c9c84ea..59ec422992d3 100644
--- a/drivers/net/wireless/ath/ath12k/mac.c
+++ b/drivers/net/wireless/ath/ath12k/mac.c
@@ -4360,7 +4360,7 @@ int ath12k_mac_get_fw_stats(struct ath12k *ar,
 {
 	struct ath12k_base *ab = ar->ab;
 	struct ath12k_hw *ah = ath12k_ar_to_ah(ar);
-	unsigned long timeout, time_left;
+	unsigned long time_left;
 	int ret;
 
 	guard(mutex)(&ah->hw_mutex);
@@ -4368,19 +4368,13 @@ int ath12k_mac_get_fw_stats(struct ath12k *ar,
 	if (ah->state != ATH12K_HW_STATE_ON)
 		return -ENETDOWN;
 
-	/* FW stats can get split when exceeding the stats data buffer limit.
-	 * In that case, since there is no end marking for the back-to-back
-	 * received 'update stats' event, we keep a 3 seconds timeout in case,
-	 * fw_stats_done is not marked yet
-	 */
-	timeout = jiffies + msecs_to_jiffies(3 * 1000);
 	ath12k_fw_stats_reset(ar);
 
 	reinit_completion(&ar->fw_stats_complete);
+	reinit_completion(&ar->fw_stats_done);
 
 	ret = ath12k_wmi_send_stats_request_cmd(ar, param->stats_id,
 						param->vdev_id, param->pdev_id);
-
 	if (ret) {
 		ath12k_warn(ab, "failed to request fw stats: %d\n", ret);
 		return ret;
@@ -4391,7 +4385,6 @@ int ath12k_mac_get_fw_stats(struct ath12k *ar,
 		   param->pdev_id, param->vdev_id, param->stats_id);
 
 	time_left = wait_for_completion_timeout(&ar->fw_stats_complete, 1 * HZ);
-
 	if (!time_left) {
 		ath12k_warn(ab, "time out while waiting for get fw stats\n");
 		return -ETIMEDOUT;
@@ -4400,19 +4393,15 @@ int ath12k_mac_get_fw_stats(struct ath12k *ar,
 	/* Firmware sends WMI_UPDATE_STATS_EVENTID back-to-back
 	 * when stats data buffer limit is reached. fw_stats_complete
 	 * is completed once host receives first event from firmware, but
-	 * still there could be more events following. Below loop is to wait
+	 * still there could be more events following. Below is to wait
 	 * until firmware completes sending all the events.
 	 */
-	for (;;) {
-		if (time_after(jiffies, timeout))
-			break;
-		spin_lock_bh(&ar->data_lock);
-		if (ar->fw_stats.fw_stats_done) {
-			spin_unlock_bh(&ar->data_lock);
-			break;
-		}
-		spin_unlock_bh(&ar->data_lock);
+	time_left = wait_for_completion_timeout(&ar->fw_stats_done, 3 * HZ);
+	if (!time_left) {
+		ath12k_warn(ab, "time out while waiting for fw stats done\n");
+		return -ETIMEDOUT;
 	}
+
 	return 0;
 }
 
diff --git a/drivers/net/wireless/ath/ath12k/wmi.c b/drivers/net/wireless/ath/ath12k/wmi.c
index 6dbd272db1d5..e8323581a5af 100644
--- a/drivers/net/wireless/ath/ath12k/wmi.c
+++ b/drivers/net/wireless/ath/ath12k/wmi.c
@@ -8192,11 +8192,12 @@ static void ath12k_wmi_fw_stats_process(struct ath12k *ar,
 				      &ar->fw_stats.vdevs);
 
 		if (is_end) {
-			ar->fw_stats.fw_stats_done = true;
+			complete(&ar->fw_stats_done);
 			num_vdev = 0;
 		}
 		return;
 	}
+
 	if (stats->stats_id == WMI_REQUEST_BCN_STAT) {
 		if (list_empty(&stats->bcn)) {
 			ath12k_warn(ab, "empty beacon stats");
@@ -8211,7 +8212,7 @@ static void ath12k_wmi_fw_stats_process(struct ath12k *ar,
 				      &ar->fw_stats.bcn);
 
 		if (is_end) {
-			ar->fw_stats.fw_stats_done = true;
+			complete(&ar->fw_stats_done);
 			num_bcn = 0;
 		}
 	}
@@ -8249,7 +8250,7 @@ static void ath12k_update_stats_event(struct ath12k_base *ab, struct sk_buff *sk
 	/* Handle WMI_REQUEST_PDEV_STAT status update */
 	if (stats.stats_id == WMI_REQUEST_PDEV_STAT) {
 		list_splice_tail_init(&stats.pdevs, &ar->fw_stats.pdevs);
-		ar->fw_stats.fw_stats_done = true;
+		complete(&ar->fw_stats_done);
 		goto complete;
 	}
 

From ac7b8ff7839ded757806317ab8979be844766770 Mon Sep 17 00:00:00 2001
From: Baochen Qiang <quic_bqiang@quicinc.com>
Date: Thu, 12 Jun 2025 09:31:51 +0800
Subject: [PATCH 0514/1334] wifi: ath12k: don't use static variables in
 ath12k_wmi_fw_stats_process()

Currently ath12k_wmi_fw_stats_process() is using static variables to count
firmware stat events. Taking num_vdev as an example, if for whatever
reason (say ar->num_started_vdevs is 0 or firmware bug etc.) the following
condition

	(++num_vdev) == total_vdevs_started

is not met, is_end is not set thus num_vdev won't be cleared. Next time
when firmware stats is requested again, even if everything is working
fine, failure is expected due to the condition above will never be
satisfied.

The same applies to num_bcn as well.

Change to use non-static counters and reset them each time before firmware
stats is requested.

Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.1.c5-00284.1-QCAHMTSWPL_V1.0_V2.0_SILICONZ-3
Tested-on: QCN9274 hw2.0 WLAN.WBE.1.5-01651-QCAHKSWPL_SILICONZ-1

Fixes: e367c924768b ("wifi: ath12k: Request vdev stats from firmware")
Signed-off-by: Baochen Qiang <quic_bqiang@quicinc.com>
Link: https://patch.msgid.link/20250612-ath12k-fw-fixes-v1-3-12f594f3b857@quicinc.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/core.c |  2 ++
 drivers/net/wireless/ath/ath12k/core.h |  2 ++
 drivers/net/wireless/ath/ath12k/wmi.c  | 14 +++++---------
 3 files changed, 9 insertions(+), 9 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/core.c b/drivers/net/wireless/ath/ath12k/core.c
index fbc62209086f..89ae80934b30 100644
--- a/drivers/net/wireless/ath/ath12k/core.c
+++ b/drivers/net/wireless/ath/ath12k/core.c
@@ -1230,6 +1230,8 @@ void ath12k_fw_stats_reset(struct ath12k *ar)
 {
 	spin_lock_bh(&ar->data_lock);
 	ath12k_fw_stats_free(&ar->fw_stats);
+	ar->fw_stats.num_vdev_recvd = 0;
+	ar->fw_stats.num_bcn_recvd = 0;
 	spin_unlock_bh(&ar->data_lock);
 }
 
diff --git a/drivers/net/wireless/ath/ath12k/core.h b/drivers/net/wireless/ath/ath12k/core.h
index 2b2e0c16b64e..7bcd9c70309f 100644
--- a/drivers/net/wireless/ath/ath12k/core.h
+++ b/drivers/net/wireless/ath/ath12k/core.h
@@ -632,6 +632,8 @@ struct ath12k_fw_stats {
 	struct list_head pdevs;
 	struct list_head vdevs;
 	struct list_head bcn;
+	u32 num_vdev_recvd;
+	u32 num_bcn_recvd;
 };
 
 struct ath12k_dbg_htt_stats {
diff --git a/drivers/net/wireless/ath/ath12k/wmi.c b/drivers/net/wireless/ath/ath12k/wmi.c
index e8323581a5af..533e4ddb9a50 100644
--- a/drivers/net/wireless/ath/ath12k/wmi.c
+++ b/drivers/net/wireless/ath/ath12k/wmi.c
@@ -8166,7 +8166,6 @@ static void ath12k_wmi_fw_stats_process(struct ath12k *ar,
 	struct ath12k_base *ab = ar->ab;
 	struct ath12k_pdev *pdev;
 	bool is_end;
-	static unsigned int num_vdev, num_bcn;
 	size_t total_vdevs_started = 0;
 	int i;
 
@@ -8186,15 +8185,14 @@ static void ath12k_wmi_fw_stats_process(struct ath12k *ar,
 		}
 		rcu_read_unlock();
 
-		is_end = ((++num_vdev) == total_vdevs_started);
+		is_end = ((++ar->fw_stats.num_vdev_recvd) == total_vdevs_started);
 
 		list_splice_tail_init(&stats->vdevs,
 				      &ar->fw_stats.vdevs);
 
-		if (is_end) {
+		if (is_end)
 			complete(&ar->fw_stats_done);
-			num_vdev = 0;
-		}
+
 		return;
 	}
 
@@ -8206,15 +8204,13 @@ static void ath12k_wmi_fw_stats_process(struct ath12k *ar,
 		/* Mark end until we reached the count of all started VDEVs
 		 * within the PDEV
 		 */
-		is_end = ((++num_bcn) == ar->num_started_vdevs);
+		is_end = ((++ar->fw_stats.num_bcn_recvd) == ar->num_started_vdevs);
 
 		list_splice_tail_init(&stats->bcn,
 				      &ar->fw_stats.bcn);
 
-		if (is_end) {
+		if (is_end)
 			complete(&ar->fw_stats_done);
-			num_bcn = 0;
-		}
 	}
 }
 

From ad5e9178cec589bf3af589dc43e638e5a5bf56fa Mon Sep 17 00:00:00 2001
From: Baochen Qiang <quic_bqiang@quicinc.com>
Date: Thu, 12 Jun 2025 09:31:52 +0800
Subject: [PATCH 0515/1334] wifi: ath12k: don't wait when there is no vdev
 started

For WMI_REQUEST_VDEV_STAT request, firmware might split response into
multiple events dut to buffer limit, hence currently in
ath12k_wmi_fw_stats_process() host waits until all events received. In
case there is no vdev started, this results in that below condition
would never get satisfied

	((++ar->fw_stats.num_vdev_recvd) == total_vdevs_started)

consequently the requestor would be blocked until time out.

The same applies to WMI_REQUEST_BCN_STAT request as well due to:

	((++ar->fw_stats.num_bcn_recvd) == ar->num_started_vdevs)

Change to check the number of started vdev first: if it is zero, finish
directly; if not, follow the old way.

Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.1.c5-00284.1-QCAHMTSWPL_V1.0_V2.0_SILICONZ-3
Tested-on: QCN9274 hw2.0 WLAN.WBE.1.5-01651-QCAHKSWPL_SILICONZ-1

Fixes: e367c924768b ("wifi: ath12k: Request vdev stats from firmware")
Signed-off-by: Baochen Qiang <quic_bqiang@quicinc.com>
Link: https://patch.msgid.link/20250612-ath12k-fw-fixes-v1-4-12f594f3b857@quicinc.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/wmi.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/wmi.c b/drivers/net/wireless/ath/ath12k/wmi.c
index 533e4ddb9a50..465f877fc0fb 100644
--- a/drivers/net/wireless/ath/ath12k/wmi.c
+++ b/drivers/net/wireless/ath/ath12k/wmi.c
@@ -8165,7 +8165,7 @@ static void ath12k_wmi_fw_stats_process(struct ath12k *ar,
 {
 	struct ath12k_base *ab = ar->ab;
 	struct ath12k_pdev *pdev;
-	bool is_end;
+	bool is_end = true;
 	size_t total_vdevs_started = 0;
 	int i;
 
@@ -8185,7 +8185,9 @@ static void ath12k_wmi_fw_stats_process(struct ath12k *ar,
 		}
 		rcu_read_unlock();
 
-		is_end = ((++ar->fw_stats.num_vdev_recvd) == total_vdevs_started);
+		if (total_vdevs_started)
+			is_end = ((++ar->fw_stats.num_vdev_recvd) ==
+				  total_vdevs_started);
 
 		list_splice_tail_init(&stats->vdevs,
 				      &ar->fw_stats.vdevs);
@@ -8204,7 +8206,9 @@ static void ath12k_wmi_fw_stats_process(struct ath12k *ar,
 		/* Mark end until we reached the count of all started VDEVs
 		 * within the PDEV
 		 */
-		is_end = ((++ar->fw_stats.num_bcn_recvd) == ar->num_started_vdevs);
+		if (ar->num_started_vdevs)
+			is_end = ((++ar->fw_stats.num_bcn_recvd) ==
+				  ar->num_started_vdevs);
 
 		list_splice_tail_init(&stats->bcn,
 				      &ar->fw_stats.bcn);

From 15d25307692312cec4b57052da73387f91a2e870 Mon Sep 17 00:00:00 2001
From: Dmitry Antipov <dmantipov@yandex.ru>
Date: Mon, 16 Jun 2025 21:12:05 +0300
Subject: [PATCH 0516/1334] wifi: carl9170: do not ping device which has failed
 to load firmware

Syzkaller reports [1, 2] crashes caused by an attempts to ping
the device which has failed to load firmware. Since such a device
doesn't pass 'ieee80211_register_hw()', an internal workqueue
managed by 'ieee80211_queue_work()' is not yet created and an
attempt to queue work on it causes null-ptr-deref.

[1] https://syzkaller.appspot.com/bug?extid=9a4aec827829942045ff
[2] https://syzkaller.appspot.com/bug?extid=0d8afba53e8fb2633217

Fixes: e4a668c59080 ("carl9170: fix spurious restart due to high latency")
Signed-off-by: Dmitry Antipov <dmantipov@yandex.ru>
Acked-by: Christian Lamparter <chunkeey@gmail.com>
Link: https://patch.msgid.link/20250616181205.38883-1-dmantipov@yandex.ru
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/carl9170/usb.c | 19 +++++++++++++------
 1 file changed, 13 insertions(+), 6 deletions(-)

diff --git a/drivers/net/wireless/ath/carl9170/usb.c b/drivers/net/wireless/ath/carl9170/usb.c
index a3e03580cd9f..564ca6a61985 100644
--- a/drivers/net/wireless/ath/carl9170/usb.c
+++ b/drivers/net/wireless/ath/carl9170/usb.c
@@ -438,14 +438,21 @@ static void carl9170_usb_rx_complete(struct urb *urb)
 
 		if (atomic_read(&ar->rx_anch_urbs) == 0) {
 			/*
-			 * The system is too slow to cope with
-			 * the enormous workload. We have simply
-			 * run out of active rx urbs and this
-			 * unfortunately leads to an unpredictable
-			 * device.
+			 * At this point, either the system is too slow to
+			 * cope with the enormous workload (so we have simply
+			 * run out of active rx urbs and this unfortunately
+			 * leads to an unpredictable device), or the device
+			 * is not fully functional after an unsuccessful
+			 * firmware loading attempts (so it doesn't pass
+			 * ieee80211_register_hw() and there is no internal
+			 * workqueue at all).
 			 */
 
-			ieee80211_queue_work(ar->hw, &ar->ping_work);
+			if (ar->registered)
+				ieee80211_queue_work(ar->hw, &ar->ping_work);
+			else
+				pr_warn_once("device %s is not registered\n",
+					     dev_name(&ar->udev->dev));
 		}
 	} else {
 		/*

From cb6075bc62dc6a9cd7ab3572758685fdf78e3e20 Mon Sep 17 00:00:00 2001
From: Rik van Riel <riel@surriel.com>
Date: Fri, 6 Jun 2025 13:10:34 -0400
Subject: [PATCH 0517/1334] x86/mm: Fix early boot use of INVPLGB

The INVLPGB instruction has limits on how many pages it can invalidate
at once. That limit is enumerated in CPUID, read by the kernel, and
stored in 'invpgb_count_max'. Ranged invalidation, like
invlpgb_kernel_range_flush() break up their invalidations so
that they do not exceed the limit.

However, early boot code currently attempts to do ranged
invalidation before populating 'invlpgb_count_max'. There is a
for loop which is basically:

	for (...; addr < end; addr += invlpgb_count_max*PAGE_SIZE)

If invlpgb_kernel_range_flush is called before the kernel has read
the value of invlpgb_count_max from the hardware, the normally
bounded loop can become an infinite loop if invlpgb_count_max is
initialized to zero.

Fix that issue by initializing invlpgb_count_max to 1.

This way INVPLGB at early boot time will be a little bit slower
than normal (with initialized invplgb_count_max), and not an
instant hang at bootup time.

Fixes: b7aa05cbdc52 ("x86/mm: Add INVLPGB support code")
Signed-off-by: Rik van Riel <riel@surriel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Link: https://lore.kernel.org/all/20250606171112.4013261-3-riel%40surriel.com
---
 arch/x86/kernel/cpu/amd.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 93da466dfe2c..b2ad8d13211a 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -31,7 +31,7 @@
 
 #include "cpu.h"
 
-u16 invlpgb_count_max __ro_after_init;
+u16 invlpgb_count_max __ro_after_init = 1;
 
 static inline int rdmsrq_amd_safe(unsigned msr, u64 *p)
 {

From 3f890768dab1f97ff9bd7ebb76f4c52309401501 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Tue, 17 Jun 2025 16:41:43 -0400
Subject: [PATCH 0518/1334] bcachefs: fsck: fix unhandled restart in topology
 repair

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/btree_gc.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/fs/bcachefs/btree_gc.c b/fs/bcachefs/btree_gc.c
index e92cf3928c63..697c6ecc3a65 100644
--- a/fs/bcachefs/btree_gc.c
+++ b/fs/bcachefs/btree_gc.c
@@ -503,8 +503,14 @@ again:
 	prt_newline(&buf);
 	bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(&b->key));
 
+	/*
+	 * XXX: we're not passing the trans object here because we're not set up
+	 * to handle a transaction restart - this code needs to be rewritten
+	 * when we start doing online topology repair
+	 */
+	bch2_trans_unlock_long(trans);
 	if (mustfix_fsck_err_on(!have_child,
-			trans, btree_node_topology_interior_node_empty,
+			c, btree_node_topology_interior_node_empty,
 			"empty interior btree node at %s", buf.buf))
 		ret = DROP_THIS_NODE;
 err:

From 1df310860aa5b4d97b3cc83a1a8dee599071b72d Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Tue, 17 Jun 2025 16:49:40 -0400
Subject: [PATCH 0519/1334] bcachefs: fsck: Fix oops in
 key_visible_in_snapshot()

The normal fsck code doesn't call key_visible_in_snapshot() with an
empty list of snapshot IDs seen (the current snapshot ID will always be
on the list), but str_hash_repair_key() ->
bch2_get_snapshot_overwrites() can, and that's totally fine as long as
we check for it.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/fsck.c | 13 ++-----------
 1 file changed, 2 insertions(+), 11 deletions(-)

diff --git a/fs/bcachefs/fsck.c b/fs/bcachefs/fsck.c
index 57ddc20a5cce..9920f1affc5b 100644
--- a/fs/bcachefs/fsck.c
+++ b/fs/bcachefs/fsck.c
@@ -728,14 +728,8 @@ static int snapshots_seen_update(struct bch_fs *c, struct snapshots_seen *s,
 static bool key_visible_in_snapshot(struct bch_fs *c, struct snapshots_seen *seen,
 				    u32 id, u32 ancestor)
 {
-	ssize_t i;
-
 	EBUG_ON(id > ancestor);
 
-	/* @ancestor should be the snapshot most recently added to @seen */
-	EBUG_ON(ancestor != seen->pos.snapshot);
-	EBUG_ON(ancestor != darray_last(seen->ids));
-
 	if (id == ancestor)
 		return true;
 
@@ -751,11 +745,8 @@ static bool key_visible_in_snapshot(struct bch_fs *c, struct snapshots_seen *see
 	 * numerically, since snapshot ID lists are kept sorted, so if we find
 	 * an id that's an ancestor of @id we're done:
 	 */
-
-	for (i = seen->ids.nr - 2;
-	     i >= 0 && seen->ids.data[i] >= id;
-	     --i)
-		if (bch2_snapshot_is_ancestor(c, id, seen->ids.data[i]))
+	darray_for_each_reverse(seen->ids, i)
+		if (*i != ancestor && bch2_snapshot_is_ancestor(c, id, *i))
 			return false;
 
 	return true;

From 88bd771191f7f20d6295700d1746f576419e3d1f Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Tue, 17 Jun 2025 20:24:12 -0400
Subject: [PATCH 0520/1334] bcachefs: fix spurious error in read_btree_roots()

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/recovery.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/fs/bcachefs/recovery.c b/fs/bcachefs/recovery.c
index fa5d1ef5bea6..e0d824471bff 100644
--- a/fs/bcachefs/recovery.c
+++ b/fs/bcachefs/recovery.c
@@ -607,6 +607,7 @@ static int read_btree_roots(struct bch_fs *c)
 					buf.buf, bch2_err_str(ret))) {
 			if (btree_id_is_alloc(i))
 				r->error = 0;
+			ret = 0;
 		}
 	}
 

From 434635987fb7d544dd134f25c922413e19b02112 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Tue, 17 Jun 2025 20:22:32 -0400
Subject: [PATCH 0521/1334] bcachefs: Fix missing newlines before ero

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/data_update.c | 1 +
 fs/bcachefs/journal_io.c  | 5 +++--
 fs/bcachefs/recovery.c    | 2 +-
 3 files changed, 5 insertions(+), 3 deletions(-)

diff --git a/fs/bcachefs/data_update.c b/fs/bcachefs/data_update.c
index 5f1174348974..e848e210a9bf 100644
--- a/fs/bcachefs/data_update.c
+++ b/fs/bcachefs/data_update.c
@@ -249,6 +249,7 @@ static int data_update_invalid_bkey(struct data_update *m,
 	bch2_bkey_val_to_text(&buf, c, k);
 	prt_str(&buf, "\nnew: ");
 	bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(insert));
+	prt_newline(&buf);
 
 	bch2_fs_emergency_read_only2(c, &buf);
 
diff --git a/fs/bcachefs/journal_io.c b/fs/bcachefs/journal_io.c
index afbf12e8f0c5..dd3f3434c1b0 100644
--- a/fs/bcachefs/journal_io.c
+++ b/fs/bcachefs/journal_io.c
@@ -1716,9 +1716,10 @@ static CLOSURE_CALLBACK(journal_write_done)
 		bch2_log_msg_start(c, &buf);
 
 		if (err == -BCH_ERR_journal_write_err)
-			prt_printf(&buf, "unable to write journal to sufficient devices");
+			prt_printf(&buf, "unable to write journal to sufficient devices\n");
 		else
-			prt_printf(&buf, "journal write error marking replicas: %s", bch2_err_str(err));
+			prt_printf(&buf, "journal write error marking replicas: %s\n",
+				   bch2_err_str(err));
 
 		bch2_fs_emergency_read_only2(c, &buf);
 
diff --git a/fs/bcachefs/recovery.c b/fs/bcachefs/recovery.c
index e0d824471bff..d0b7e3a36a54 100644
--- a/fs/bcachefs/recovery.c
+++ b/fs/bcachefs/recovery.c
@@ -1142,7 +1142,7 @@ fsck_err:
 		struct printbuf buf = PRINTBUF;
 		bch2_log_msg_start(c, &buf);
 
-		prt_printf(&buf, "error in recovery: %s", bch2_err_str(ret));
+		prt_printf(&buf, "error in recovery: %s\n", bch2_err_str(ret));
 		bch2_fs_emergency_read_only2(c, &buf);
 
 		bch2_print_str(c, KERN_ERR, buf.buf);

From 6dbb0d97c5096072c78a6abffe393584e57ae945 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@google.com>
Date: Mon, 16 Jun 2025 13:15:12 -0700
Subject: [PATCH 0522/1334] mpls: Use rcu_dereference_rtnl() in
 mpls_route_input_rcu().

As syzbot reported [0], mpls_route_input_rcu() can be called
from mpls_getroute(), where is under RTNL.

net->mpls.platform_label is only updated under RTNL.

Let's use rcu_dereference_rtnl() in mpls_route_input_rcu() to
silence the splat.

[0]:
WARNING: suspicious RCU usage
6.15.0-rc7-syzkaller-00082-g5cdb2c77c4c3 #0 Not tainted
 ----------------------------
net/mpls/af_mpls.c:84 suspicious rcu_dereference_check() usage!

other info that might help us debug this:

rcu_scheduler_active = 2, debug_locks = 1
1 lock held by syz.2.4451/17730:
 #0: ffffffff9012a3e8 (rtnl_mutex){+.+.}-{4:4}, at: rtnl_lock net/core/rtnetlink.c:80 [inline]
 #0: ffffffff9012a3e8 (rtnl_mutex){+.+.}-{4:4}, at: rtnetlink_rcv_msg+0x371/0xe90 net/core/rtnetlink.c:6961

stack backtrace:
CPU: 1 UID: 0 PID: 17730 Comm: syz.2.4451 Not tainted 6.15.0-rc7-syzkaller-00082-g5cdb2c77c4c3 #0 PREEMPT(full)
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 05/07/2025
Call Trace:
 <TASK>
 __dump_stack lib/dump_stack.c:94 [inline]
 dump_stack_lvl+0x16c/0x1f0 lib/dump_stack.c:120
 lockdep_rcu_suspicious+0x166/0x260 kernel/locking/lockdep.c:6865
 mpls_route_input_rcu+0x1d4/0x200 net/mpls/af_mpls.c:84
 mpls_getroute+0x621/0x1ea0 net/mpls/af_mpls.c:2381
 rtnetlink_rcv_msg+0x3c9/0xe90 net/core/rtnetlink.c:6964
 netlink_rcv_skb+0x16d/0x440 net/netlink/af_netlink.c:2534
 netlink_unicast_kernel net/netlink/af_netlink.c:1313 [inline]
 netlink_unicast+0x53a/0x7f0 net/netlink/af_netlink.c:1339
 netlink_sendmsg+0x8d1/0xdd0 net/netlink/af_netlink.c:1883
 sock_sendmsg_nosec net/socket.c:712 [inline]
 __sock_sendmsg net/socket.c:727 [inline]
 ____sys_sendmsg+0xa98/0xc70 net/socket.c:2566
 ___sys_sendmsg+0x134/0x1d0 net/socket.c:2620
 __sys_sendmmsg+0x200/0x420 net/socket.c:2709
 __do_sys_sendmmsg net/socket.c:2736 [inline]
 __se_sys_sendmmsg net/socket.c:2733 [inline]
 __x64_sys_sendmmsg+0x9c/0x100 net/socket.c:2733
 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline]
 do_syscall_64+0xcd/0x230 arch/x86/entry/syscall_64.c:94
 entry_SYSCALL_64_after_hwframe+0x77/0x7f
RIP: 0033:0x7f0a2818e969
Code: ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 40 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 a8 ff ff ff f7 d8 64 89 01 48
RSP: 002b:00007f0a28f52038 EFLAGS: 00000246 ORIG_RAX: 0000000000000133
RAX: ffffffffffffffda RBX: 00007f0a283b5fa0 RCX: 00007f0a2818e969
RDX: 0000000000000003 RSI: 0000200000000080 RDI: 0000000000000003
RBP: 00007f0a28210ab1 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000
R13: 0000000000000000 R14: 00007f0a283b5fa0 R15: 00007ffce5e9f268
 </TASK>

Fixes: 0189197f4416 ("mpls: Basic routing support")
Reported-by: syzbot+8a583bdd1a5cc0b0e068@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/netdev/68507981.a70a0220.395abc.01ef.GAE@google.com/
Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Link: https://patch.msgid.link/20250616201532.1036568-1-kuni1840@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/mpls/af_mpls.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c
index d536c97144e9..47d7dfd9ad09 100644
--- a/net/mpls/af_mpls.c
+++ b/net/mpls/af_mpls.c
@@ -81,8 +81,8 @@ static struct mpls_route *mpls_route_input_rcu(struct net *net, unsigned index)
 
 	if (index < net->mpls.platform_labels) {
 		struct mpls_route __rcu **platform_label =
-			rcu_dereference(net->mpls.platform_label);
-		rt = rcu_dereference(platform_label[index]);
+			rcu_dereference_rtnl(net->mpls.platform_label);
+		rt = rcu_dereference_rtnl(platform_label[index]);
 	}
 	return rt;
 }

From 2f370ae1fb6317985f3497b1bb80d457508ca2f7 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@google.com>
Date: Mon, 16 Jun 2025 11:21:14 -0700
Subject: [PATCH 0523/1334] atm: atmtcp: Free invalid length skb in
 atmtcp_c_send().

syzbot reported the splat below. [0]

vcc_sendmsg() copies data passed from userspace to skb and passes
it to vcc->dev->ops->send().

atmtcp_c_send() accesses skb->data as struct atmtcp_hdr after
checking if skb->len is 0, but it's not enough.

Also, when skb->len == 0, skb and sk (vcc) were leaked because
dev_kfree_skb() is not called and sk_wmem_alloc adjustment is missing
to revert atm_account_tx() in vcc_sendmsg(), which is expected
to be done in atm_pop_raw().

Let's properly free skb with an invalid length in atmtcp_c_send().

[0]:
BUG: KMSAN: uninit-value in atmtcp_c_send+0x255/0xed0 drivers/atm/atmtcp.c:294
 atmtcp_c_send+0x255/0xed0 drivers/atm/atmtcp.c:294
 vcc_sendmsg+0xd7c/0xff0 net/atm/common.c:644
 sock_sendmsg_nosec net/socket.c:712 [inline]
 __sock_sendmsg+0x330/0x3d0 net/socket.c:727
 ____sys_sendmsg+0x7e0/0xd80 net/socket.c:2566
 ___sys_sendmsg+0x271/0x3b0 net/socket.c:2620
 __sys_sendmsg net/socket.c:2652 [inline]
 __do_sys_sendmsg net/socket.c:2657 [inline]
 __se_sys_sendmsg net/socket.c:2655 [inline]
 __x64_sys_sendmsg+0x211/0x3e0 net/socket.c:2655
 x64_sys_call+0x32fb/0x3db0 arch/x86/include/generated/asm/syscalls_64.h:47
 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline]
 do_syscall_64+0xd9/0x210 arch/x86/entry/syscall_64.c:94
 entry_SYSCALL_64_after_hwframe+0x77/0x7f

Uninit was created at:
 slab_post_alloc_hook mm/slub.c:4154 [inline]
 slab_alloc_node mm/slub.c:4197 [inline]
 kmem_cache_alloc_node_noprof+0x818/0xf00 mm/slub.c:4249
 kmalloc_reserve+0x13c/0x4b0 net/core/skbuff.c:579
 __alloc_skb+0x347/0x7d0 net/core/skbuff.c:670
 alloc_skb include/linux/skbuff.h:1336 [inline]
 vcc_sendmsg+0xb40/0xff0 net/atm/common.c:628
 sock_sendmsg_nosec net/socket.c:712 [inline]
 __sock_sendmsg+0x330/0x3d0 net/socket.c:727
 ____sys_sendmsg+0x7e0/0xd80 net/socket.c:2566
 ___sys_sendmsg+0x271/0x3b0 net/socket.c:2620
 __sys_sendmsg net/socket.c:2652 [inline]
 __do_sys_sendmsg net/socket.c:2657 [inline]
 __se_sys_sendmsg net/socket.c:2655 [inline]
 __x64_sys_sendmsg+0x211/0x3e0 net/socket.c:2655
 x64_sys_call+0x32fb/0x3db0 arch/x86/include/generated/asm/syscalls_64.h:47
 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline]
 do_syscall_64+0xd9/0x210 arch/x86/entry/syscall_64.c:94
 entry_SYSCALL_64_after_hwframe+0x77/0x7f

CPU: 1 UID: 0 PID: 5798 Comm: syz-executor192 Not tainted 6.16.0-rc1-syzkaller-00010-g2c4a1f3fe03e #0 PREEMPT(undef)
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 05/07/2025

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Reported-by: syzbot+1d3c235276f62963e93a@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=1d3c235276f62963e93a
Tested-by: syzbot+1d3c235276f62963e93a@syzkaller.appspotmail.com
Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Link: https://patch.msgid.link/20250616182147.963333-2-kuni1840@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/atm/atmtcp.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/atm/atmtcp.c b/drivers/atm/atmtcp.c
index d4aa0f353b6c..eeae160c898d 100644
--- a/drivers/atm/atmtcp.c
+++ b/drivers/atm/atmtcp.c
@@ -288,7 +288,9 @@ static int atmtcp_c_send(struct atm_vcc *vcc,struct sk_buff *skb)
 	struct sk_buff *new_skb;
 	int result = 0;
 
-	if (!skb->len) return 0;
+	if (skb->len < sizeof(struct atmtcp_hdr))
+		goto done;
+
 	dev = vcc->dev_data;
 	hdr = (struct atmtcp_hdr *) skb->data;
 	if (hdr->length == ATMTCP_HDR_MAGIC) {

From 7851263998d4269125fd6cb3fdbfc7c6db853859 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@google.com>
Date: Mon, 16 Jun 2025 11:21:15 -0700
Subject: [PATCH 0524/1334] atm: Revert atm_account_tx() if
 copy_from_iter_full() fails.

In vcc_sendmsg(), we account skb->truesize to sk->sk_wmem_alloc by
atm_account_tx().

It is expected to be reverted by atm_pop_raw() later called by
vcc->dev->ops->send(vcc, skb).

However, vcc_sendmsg() misses the same revert when copy_from_iter_full()
fails, and then we will leak a socket.

Let's factorise the revert part as atm_return_tx() and call it in
the failure path.

Note that the corresponding sk_wmem_alloc operation can be found in
alloc_tx() as of the blamed commit.

  $ git blame -L:alloc_tx net/atm/common.c c55fa3cccbc2c~

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Reported-by: Simon Horman <horms@kernel.org>
Closes: https://lore.kernel.org/netdev/20250614161959.GR414686@horms.kernel.org/
Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Link: https://patch.msgid.link/20250616182147.963333-3-kuni1840@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/atmdev.h | 6 ++++++
 net/atm/common.c       | 1 +
 net/atm/raw.c          | 2 +-
 3 files changed, 8 insertions(+), 1 deletion(-)

diff --git a/include/linux/atmdev.h b/include/linux/atmdev.h
index 9b02961d65ee..45f2f278b50a 100644
--- a/include/linux/atmdev.h
+++ b/include/linux/atmdev.h
@@ -249,6 +249,12 @@ static inline void atm_account_tx(struct atm_vcc *vcc, struct sk_buff *skb)
 	ATM_SKB(skb)->atm_options = vcc->atm_options;
 }
 
+static inline void atm_return_tx(struct atm_vcc *vcc, struct sk_buff *skb)
+{
+	WARN_ON_ONCE(refcount_sub_and_test(ATM_SKB(skb)->acct_truesize,
+					   &sk_atm(vcc)->sk_wmem_alloc));
+}
+
 static inline void atm_force_charge(struct atm_vcc *vcc,int truesize)
 {
 	atomic_add(truesize, &sk_atm(vcc)->sk_rmem_alloc);
diff --git a/net/atm/common.c b/net/atm/common.c
index 9b75699992ff..d7f7976ea13a 100644
--- a/net/atm/common.c
+++ b/net/atm/common.c
@@ -635,6 +635,7 @@ int vcc_sendmsg(struct socket *sock, struct msghdr *m, size_t size)
 
 	skb->dev = NULL; /* for paths shared with net_device interfaces */
 	if (!copy_from_iter_full(skb_put(skb, size), size, &m->msg_iter)) {
+		atm_return_tx(vcc, skb);
 		kfree_skb(skb);
 		error = -EFAULT;
 		goto out;
diff --git a/net/atm/raw.c b/net/atm/raw.c
index 2b5f78a7ec3e..1e6511ec842c 100644
--- a/net/atm/raw.c
+++ b/net/atm/raw.c
@@ -36,7 +36,7 @@ static void atm_pop_raw(struct atm_vcc *vcc, struct sk_buff *skb)
 
 	pr_debug("(%d) %d -= %d\n",
 		 vcc->vci, sk_wmem_alloc_get(sk), ATM_SKB(skb)->acct_truesize);
-	WARN_ON(refcount_sub_and_test(ATM_SKB(skb)->acct_truesize, &sk->sk_wmem_alloc));
+	atm_return_tx(vcc, skb);
 	dev_kfree_skb_any(skb);
 	sk->sk_write_space(sk);
 }

From 905eeb2b7c33adda23a966aeb811ab4cb9e62031 Mon Sep 17 00:00:00 2001
From: Tatsuyuki Ishi <ishitatsuyuki@google.com>
Date: Thu, 12 Jun 2025 19:18:25 +0900
Subject: [PATCH 0525/1334] erofs: impersonate the opener's credentials when
 accessing backing file

Previously, file operations on a file-backed mount used the current
process' credentials to access the backing FD. Attempting to do so on
Android lead to SELinux denials, as ACL rules on the backing file (e.g.
/system/apex/foo.apex) is restricted to a small set of process.
Arguably, this error is redundant and leaking implementation details, as
access to files on a mount is already ACL'ed by path.

Instead, override to use the opener's cred when accessing the backing
file. This makes the behavior similar to a loop-backed mount, which
uses kworker cred when accessing the backing file and does not cause
SELinux denials.

Signed-off-by: Tatsuyuki Ishi <ishitatsuyuki@google.com>
Reviewed-by: Gao Xiang <hsiangkao@linux.alibaba.com>
Reviewed-by: Hongbo Li <lihongbo22@huawei.com>
Link: https://lore.kernel.org/r/20250612-b4-erofs-impersonate-v1-1-8ea7d6f65171@google.com
Signed-off-by: Gao Xiang <hsiangkao@linux.alibaba.com>
---
 fs/erofs/fileio.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/fs/erofs/fileio.c b/fs/erofs/fileio.c
index 7d81f504bff0..df5cc63f2c01 100644
--- a/fs/erofs/fileio.c
+++ b/fs/erofs/fileio.c
@@ -47,6 +47,7 @@ static void erofs_fileio_ki_complete(struct kiocb *iocb, long ret)
 
 static void erofs_fileio_rq_submit(struct erofs_fileio_rq *rq)
 {
+	const struct cred *old_cred;
 	struct iov_iter iter;
 	int ret;
 
@@ -60,7 +61,9 @@ static void erofs_fileio_rq_submit(struct erofs_fileio_rq *rq)
 		rq->iocb.ki_flags = IOCB_DIRECT;
 	iov_iter_bvec(&iter, ITER_DEST, rq->bvecs, rq->bio.bi_vcnt,
 		      rq->bio.bi_iter.bi_size);
+	old_cred = override_creds(rq->iocb.ki_filp->f_cred);
 	ret = vfs_iocb_iter_read(rq->iocb.ki_filp, &rq->iocb, &iter);
+	revert_creds(old_cred);
 	if (ret != -EIOCBQUEUED)
 		erofs_fileio_ki_complete(&rq->iocb, ret);
 }

From 30b58444807c93bffeaba7d776110f2a909d2f9a Mon Sep 17 00:00:00 2001
From: Gao Xiang <hsiangkao@linux.alibaba.com>
Date: Tue, 17 Jun 2025 13:40:56 +0800
Subject: [PATCH 0526/1334] erofs: remove unused trace event
 erofs_destroy_inode

The trace event `erofs_destroy_inode` was added but remains unused. This
unused event contributes approximately 5KB to the kernel module size.

Reported-by: Steven Rostedt <rostedt@goodmis.org>
Closes: https://lore.kernel.org/r/20250612224906.15000244@batman.local.home
Fixes: 13f06f48f7bf ("staging: erofs: support tracepoint")
Cc: stable@vger.kernel.org
Reviewed-by: Hongbo Li <lihongbo22@huawei.com>
Signed-off-by: Gao Xiang <hsiangkao@linux.alibaba.com>
Link: https://lore.kernel.org/r/20250617054056.3232365-1-hsiangkao@linux.alibaba.com
---
 include/trace/events/erofs.h | 18 ------------------
 1 file changed, 18 deletions(-)

diff --git a/include/trace/events/erofs.h b/include/trace/events/erofs.h
index a5f4b9234f46..dad7360f42f9 100644
--- a/include/trace/events/erofs.h
+++ b/include/trace/events/erofs.h
@@ -211,24 +211,6 @@ TRACE_EVENT(erofs_map_blocks_exit,
 		  show_mflags(__entry->mflags), __entry->ret)
 );
 
-TRACE_EVENT(erofs_destroy_inode,
-	TP_PROTO(struct inode *inode),
-
-	TP_ARGS(inode),
-
-	TP_STRUCT__entry(
-		__field(	dev_t,		dev		)
-		__field(	erofs_nid_t,	nid		)
-	),
-
-	TP_fast_assign(
-		__entry->dev	= inode->i_sb->s_dev;
-		__entry->nid	= EROFS_I(inode)->nid;
-	),
-
-	TP_printk("dev = (%d,%d), nid = %llu", show_dev_nid(__entry))
-);
-
 #endif /* _TRACE_EROFS_H */
 
  /* This part must be outside protection */

From e7417421d89358da071fd2930f91e67c7128fbff Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Tue, 17 Jun 2025 11:45:29 +0200
Subject: [PATCH 0527/1334] wifi: ath6kl: remove WARN on bad firmware input

If the firmware gives bad input, that's nothing to do with
the driver's stack at this point etc., so the WARN_ON()
doesn't add any value. Additionally, this is one of the
top syzbot reports now. Just print a message, and as an
added bonus, print the sizes too.

Reported-by: syzbot+92c6dd14aaa230be6855@syzkaller.appspotmail.com
Tested-by: syzbot+92c6dd14aaa230be6855@syzkaller.appspotmail.com
Acked-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
Link: https://patch.msgid.link/20250617114529.031a677a348e.I58bf1eb4ac16a82c546725ff010f3f0d2b0cca49@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/ath/ath6kl/bmi.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/ath6kl/bmi.c b/drivers/net/wireless/ath/ath6kl/bmi.c
index af98e871199d..5a9e93fd1ef4 100644
--- a/drivers/net/wireless/ath/ath6kl/bmi.c
+++ b/drivers/net/wireless/ath/ath6kl/bmi.c
@@ -87,7 +87,9 @@ int ath6kl_bmi_get_target_info(struct ath6kl *ar,
 		 * We need to do some backwards compatibility to make this work.
 		 */
 		if (le32_to_cpu(targ_info->byte_count) != sizeof(*targ_info)) {
-			WARN_ON(1);
+			ath6kl_err("mismatched byte count %d vs. expected %zd\n",
+				   le32_to_cpu(targ_info->byte_count),
+				   sizeof(*targ_info));
 			return -EINVAL;
 		}
 

From db5957ab85204a02093ac5ab2d0bbfe253955b71 Mon Sep 17 00:00:00 2001
From: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Date: Tue, 17 Jun 2025 15:00:06 +0300
Subject: [PATCH 0528/1334] wifi: iwlwifi: restore missing initialization of
 async_handlers_list (again)

The initialization of async_handlers_list
was accidentally removed in a previous change.

Then it was restoted by commit 175e69e33c66 ("wifi: iwlwifi: restore
missing initialization of async_handlers_list").

Somehow, the initialization disappeared again.
Restote it.

Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mld/mld.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/wireless/intel/iwlwifi/mld/mld.c b/drivers/net/wireless/intel/iwlwifi/mld/mld.c
index e8820e7cf8fa..1774bb84dd3f 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/mld.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/mld.c
@@ -77,6 +77,7 @@ void iwl_construct_mld(struct iwl_mld *mld, struct iwl_trans *trans,
 
 	/* Setup async RX handling */
 	spin_lock_init(&mld->async_handlers_lock);
+	INIT_LIST_HEAD(&mld->async_handlers_list);
 	wiphy_work_init(&mld->async_handlers_wk,
 			iwl_mld_async_handlers_wk);
 

From d5352b491a3a2628f1a798952a4ae76bde5d42e4 Mon Sep 17 00:00:00 2001
From: Pei Xiao <xiaopei01@kylinos.cn>
Date: Tue, 27 May 2025 16:03:55 +0800
Subject: [PATCH 0529/1334] wifi: iwlwifi: cfg: Limit cb_size to valid range

on arm64 defconfig build failed with gcc-8:

drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info.c:208:3:
include/linux/bitfield.h:195:3: error: call to '__field_overflow'
declared with attribute error: value doesn't fit into mask
   __field_overflow();     \
   ^~~~~~~~~~~~~~~~~~
include/linux/bitfield.h:215:2: note: in expansion of macro '____MAKE_OP'
  ____MAKE_OP(u##size,u##size,,)
  ^~~~~~~~~~~
include/linux/bitfield.h:218:1: note: in expansion of macro '__MAKE_OP'
 __MAKE_OP(32)

Limit cb_size to valid range to fix it.

Signed-off-by: Pei Xiao <xiaopei01@kylinos.cn>
Link: https://patch.msgid.link/7b373a4426070d50b5afb3269fd116c18ce3aea8.1748332709.git.xiaopei01@kylinos.cn
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info.c | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info.c b/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info.c
index cb36baac14da..4f2be0c1bd97 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info.c
@@ -166,7 +166,7 @@ int iwl_pcie_ctxt_info_init(struct iwl_trans *trans,
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
 	struct iwl_context_info *ctxt_info;
 	struct iwl_context_info_rbd_cfg *rx_cfg;
-	u32 control_flags = 0, rb_size;
+	u32 control_flags = 0, rb_size, cb_size;
 	dma_addr_t phys;
 	int ret;
 
@@ -202,11 +202,12 @@ int iwl_pcie_ctxt_info_init(struct iwl_trans *trans,
 		rb_size = IWL_CTXT_INFO_RB_SIZE_4K;
 	}
 
-	WARN_ON(RX_QUEUE_CB_SIZE(iwl_trans_get_num_rbds(trans)) > 12);
+	cb_size = RX_QUEUE_CB_SIZE(iwl_trans_get_num_rbds(trans));
+	if (WARN_ON(cb_size > 12))
+		cb_size = 12;
+
 	control_flags = IWL_CTXT_INFO_TFD_FORMAT_LONG;
-	control_flags |=
-		u32_encode_bits(RX_QUEUE_CB_SIZE(iwl_trans_get_num_rbds(trans)),
-				IWL_CTXT_INFO_RB_CB_SIZE);
+	control_flags |= u32_encode_bits(cb_size, IWL_CTXT_INFO_RB_CB_SIZE);
 	control_flags |= u32_encode_bits(rb_size, IWL_CTXT_INFO_RB_SIZE);
 	ctxt_info->control.control_flags = cpu_to_le32(control_flags);
 

From 432a41232ca932ecb2330f46105e68e296ba8c7f Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Mon, 16 Jun 2025 13:48:36 +0200
Subject: [PATCH 0530/1334] wifi: iwlwifi: dvm: restore n_no_reclaim_cmds
 setting

Apparently I accidentally removed this setting in my transport
configuration rework, leading to an endless stream of warnings
from the PCIe code when relevant notifications are received by
the driver from firmware. Restore it.

Reported-by: Woody Suwalski <terraluna977@gmail.com>
Closes: https://lore.kernel.org/r/e8c45d32-6129-8a5e-af80-ccc42aaf200b@gmail.com/
Fixes: 08e77d5edf70 ("wifi: iwlwifi: rework transport configuration")
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Link: https://patch.msgid.link/20250616134902.222342908ca4.I47a551c86cbc0e9de4f980ca2fd0d67bf4052e50@changeid
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/dvm/main.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/wireless/intel/iwlwifi/dvm/main.c b/drivers/net/wireless/intel/iwlwifi/dvm/main.c
index dbfd45948e8b..66211426aa3a 100644
--- a/drivers/net/wireless/intel/iwlwifi/dvm/main.c
+++ b/drivers/net/wireless/intel/iwlwifi/dvm/main.c
@@ -1316,6 +1316,7 @@ static struct iwl_op_mode *iwl_op_mode_dvm_start(struct iwl_trans *trans,
 		     sizeof(trans->conf.no_reclaim_cmds));
 	memcpy(trans->conf.no_reclaim_cmds, no_reclaim_cmds,
 	       sizeof(no_reclaim_cmds));
+	trans->conf.n_no_reclaim_cmds = ARRAY_SIZE(no_reclaim_cmds);
 
 	switch (iwlwifi_mod_params.amsdu_size) {
 	case IWL_AMSDU_DEF:

From 83f3ac2848b46e3e5af5d06b5f176c17e35733a3 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.i.king@gmail.com>
Date: Thu, 22 May 2025 13:17:03 +0100
Subject: [PATCH 0531/1334] wifi: iwlwifi: Fix incorrect logic on cmd_ver range
 checking

The current cmd_ver range checking on cmd_ver < 1 && cmd_ver > 3 can
never be true because the logical operator && is being used, cmd_ver
can never be less than 1 and also greater than 3. Fix this by using
the logical || operator.

Fixes: df6146a0296e ("wifi: iwlwifi: Add a new version for mac config command")

Signed-off-by: Colin Ian King <colin.i.king@gmail.com>
Link: https://patch.msgid.link/20250522121703.2766764-1-colin.i.king@gmail.com
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/mld-mac.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac.c b/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac.c
index 81ca9ff67be9..3c255ae916c8 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac.c
@@ -34,7 +34,7 @@ static void iwl_mvm_mld_mac_ctxt_cmd_common(struct iwl_mvm *mvm,
 					    WIDE_ID(MAC_CONF_GROUP,
 						    MAC_CONFIG_CMD), 0);
 
-	if (WARN_ON(cmd_ver < 1 && cmd_ver > 3))
+	if (WARN_ON(cmd_ver < 1 || cmd_ver > 3))
 		return;
 
 	cmd->id_and_color = cpu_to_le32(mvmvif->id);

From d0fa59897e049e84432600e86df82aab3dce7aa5 Mon Sep 17 00:00:00 2001
From: Neal Cardwell <ncardwell@google.com>
Date: Fri, 13 Jun 2025 15:30:56 -0400
Subject: [PATCH 0532/1334] tcp: fix tcp_packet_delayed() for
 tcp_is_non_sack_preventing_reopen() behavior

After the following commit from 2024:

commit e37ab7373696 ("tcp: fix to allow timestamp undo if no retransmits were sent")

...there was buggy behavior where TCP connections without SACK support
could easily see erroneous undo events at the end of fast recovery or
RTO recovery episodes. The erroneous undo events could cause those
connections to suffer repeated loss recovery episodes and high
retransmit rates.

The problem was an interaction between the non-SACK behavior on these
connections and the undo logic. The problem is that, for non-SACK
connections at the end of a loss recovery episode, if snd_una ==
high_seq, then tcp_is_non_sack_preventing_reopen() holds steady in
CA_Recovery or CA_Loss, but clears tp->retrans_stamp to 0. Then upon
the next ACK the "tcp: fix to allow timestamp undo if no retransmits
were sent" logic saw the tp->retrans_stamp at 0 and erroneously
concluded that no data was retransmitted, and erroneously performed an
undo of the cwnd reduction, restoring cwnd immediately to the value it
had before loss recovery.  This caused an immediate burst of traffic
and build-up of queues and likely another immediate loss recovery
episode.

This commit fixes tcp_packet_delayed() to ignore zero retrans_stamp
values for non-SACK connections when snd_una is at or above high_seq,
because tcp_is_non_sack_preventing_reopen() clears retrans_stamp in
this case, so it's not a valid signal that we can undo.

Note that the commit named in the Fixes footer restored long-present
behavior from roughly 2005-2019, so apparently this bug was present
for a while during that era, and this was simply not caught.

Fixes: e37ab7373696 ("tcp: fix to allow timestamp undo if no retransmits were sent")
Reported-by: Eric Wheeler <netdev@lists.ewheeler.net>
Closes: https://lore.kernel.org/netdev/64ea9333-e7f9-0df-b0f2-8d566143acab@ewheeler.net/
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Co-developed-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_input.c | 35 ++++++++++++++++++++++++-----------
 1 file changed, 24 insertions(+), 11 deletions(-)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 8ec92dec321a..12c2e6fc85c6 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -2479,20 +2479,33 @@ static inline bool tcp_packet_delayed(const struct tcp_sock *tp)
 {
 	const struct sock *sk = (const struct sock *)tp;
 
-	if (tp->retrans_stamp &&
-	    tcp_tsopt_ecr_before(tp, tp->retrans_stamp))
-		return true;  /* got echoed TS before first retransmission */
+	/* Received an echoed timestamp before the first retransmission? */
+	if (tp->retrans_stamp)
+		return tcp_tsopt_ecr_before(tp, tp->retrans_stamp);
 
-	/* Check if nothing was retransmitted (retrans_stamp==0), which may
-	 * happen in fast recovery due to TSQ. But we ignore zero retrans_stamp
-	 * in TCP_SYN_SENT, since when we set FLAG_SYN_ACKED we also clear
-	 * retrans_stamp even if we had retransmitted the SYN.
+	/* We set tp->retrans_stamp upon the first retransmission of a loss
+	 * recovery episode, so normally if tp->retrans_stamp is 0 then no
+	 * retransmission has happened yet (likely due to TSQ, which can cause
+	 * fast retransmits to be delayed). So if snd_una advanced while
+	 * (tp->retrans_stamp is 0 then apparently a packet was merely delayed,
+	 * not lost. But there are exceptions where we retransmit but then
+	 * clear tp->retrans_stamp, so we check for those exceptions.
 	 */
-	if (!tp->retrans_stamp &&	   /* no record of a retransmit/SYN? */
-	    sk->sk_state != TCP_SYN_SENT)  /* not the FLAG_SYN_ACKED case? */
-		return true;  /* nothing was retransmitted */
 
-	return false;
+	/* (1) For non-SACK connections, tcp_is_non_sack_preventing_reopen()
+	 * clears tp->retrans_stamp when snd_una == high_seq.
+	 */
+	if (!tcp_is_sack(tp) && !before(tp->snd_una, tp->high_seq))
+		return false;
+
+	/* (2) In TCP_SYN_SENT tcp_clean_rtx_queue() clears tp->retrans_stamp
+	 * when setting FLAG_SYN_ACKED is set, even if the SYN was
+	 * retransmitted.
+	 */
+	if (sk->sk_state == TCP_SYN_SENT)
+		return false;
+
+	return true;	/* tp->retrans_stamp is zero; no retransmit yet */
 }
 
 /* Undo procedures. */

From df29f60369ccec0aa17d7eed7e2ae1fcdc9be6d4 Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Mon, 16 Jun 2025 12:09:17 +0800
Subject: [PATCH 0533/1334] crypto: ahash - Fix infinite recursion in
 ahash_def_finup

Invoke the final function directly in the default finup implementation
since crypto_ahash_final is now just a wrapper around finup.

Reported-by: Eric Biggers <ebiggers@kernel.org>
Fixes: 9d7a0ab1c753 ("crypto: ahash - Handle partial blocks in API")
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 crypto/ahash.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/crypto/ahash.c b/crypto/ahash.c
index e10bc2659ae4..bc84a07c924c 100644
--- a/crypto/ahash.c
+++ b/crypto/ahash.c
@@ -600,12 +600,14 @@ static void ahash_def_finup_done2(void *data, int err)
 
 static int ahash_def_finup_finish1(struct ahash_request *req, int err)
 {
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+
 	if (err)
 		goto out;
 
 	req->base.complete = ahash_def_finup_done2;
 
-	err = crypto_ahash_final(req);
+	err = crypto_ahash_alg(tfm)->final(req);
 	if (err == -EINPROGRESS || err == -EBUSY)
 		return err;
 

From 635e118317ffa773f6d25ec6a71b7927d7e8886a Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Wed, 18 Jun 2025 10:54:44 +0200
Subject: [PATCH 0534/1334] Revert "mtd: core: always create master device"

The idea behind this patch was to always let a "master" mtd device
available to anchor runtime PM. Historically, there was no mtd device
representing the whole storage as soon as partitions were coming into
play. The introduction of CONFIG_MTD_PARTITIONED_MASTER allowed to keep
this "master" device, but was not enabled by default to avoid breaking
existing users (otherwise the mtd device numbering would be totally
messed up with an off by 1, at least).

The approach of adding an mtd_master class on top of partitioned mtd
devices is breaking the mtd core in many creative ways, so better think
again this approach and revert the faulty changes for now.

This reverts commit 0aa7b390fc40a871267a2328bbbefca8b37ad307.

Fixes: 0aa7b390fc40 ("mtd: core: always create master device")
Tested-by: Guenter Roeck <linux@roeck-us.net>
Acked-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/mtdchar.c          |   2 +-
 drivers/mtd/mtdcore.c          | 152 +++++++++------------------------
 drivers/mtd/mtdcore.h          |   2 +-
 drivers/mtd/mtdpart.c          |  16 ++--
 include/linux/mtd/partitions.h |   2 +-
 5 files changed, 51 insertions(+), 123 deletions(-)

diff --git a/drivers/mtd/mtdchar.c b/drivers/mtd/mtdchar.c
index 391d81ad960c..8dc4f5c493fc 100644
--- a/drivers/mtd/mtdchar.c
+++ b/drivers/mtd/mtdchar.c
@@ -559,7 +559,7 @@ static int mtdchar_blkpg_ioctl(struct mtd_info *mtd,
 		/* Sanitize user input */
 		p.devname[BLKPG_DEVNAMELTH - 1] = '\0';
 
-		return mtd_add_partition(mtd, p.devname, p.start, p.length, NULL);
+		return mtd_add_partition(mtd, p.devname, p.start, p.length);
 
 	case BLKPG_DEL_PARTITION:
 
diff --git a/drivers/mtd/mtdcore.c b/drivers/mtd/mtdcore.c
index 429d8c16baf0..5ba9a741f5ac 100644
--- a/drivers/mtd/mtdcore.c
+++ b/drivers/mtd/mtdcore.c
@@ -68,13 +68,7 @@ static struct class mtd_class = {
 	.pm = MTD_CLS_PM_OPS,
 };
 
-static struct class mtd_master_class = {
-	.name = "mtd_master",
-	.pm = MTD_CLS_PM_OPS,
-};
-
 static DEFINE_IDR(mtd_idr);
-static DEFINE_IDR(mtd_master_idr);
 
 /* These are exported solely for the purpose of mtd_blkdevs.c. You
    should not use them for _anything_ else */
@@ -89,9 +83,8 @@ EXPORT_SYMBOL_GPL(__mtd_next_device);
 
 static LIST_HEAD(mtd_notifiers);
 
-#define MTD_MASTER_DEVS 255
+
 #define MTD_DEVT(index) MKDEV(MTD_CHAR_MAJOR, (index)*2)
-static dev_t mtd_master_devt;
 
 /* REVISIT once MTD uses the driver model better, whoever allocates
  * the mtd_info will probably want to use the release() hook...
@@ -111,17 +104,6 @@ static void mtd_release(struct device *dev)
 	device_destroy(&mtd_class, index + 1);
 }
 
-static void mtd_master_release(struct device *dev)
-{
-	struct mtd_info *mtd = dev_get_drvdata(dev);
-
-	idr_remove(&mtd_master_idr, mtd->index);
-	of_node_put(mtd_get_of_node(mtd));
-
-	if (mtd_is_partition(mtd))
-		release_mtd_partition(mtd);
-}
-
 static void mtd_device_release(struct kref *kref)
 {
 	struct mtd_info *mtd = container_of(kref, struct mtd_info, refcnt);
@@ -385,11 +367,6 @@ static const struct device_type mtd_devtype = {
 	.release	= mtd_release,
 };
 
-static const struct device_type mtd_master_devtype = {
-	.name		= "mtd_master",
-	.release	= mtd_master_release,
-};
-
 static bool mtd_expert_analysis_mode;
 
 #ifdef CONFIG_DEBUG_FS
@@ -657,13 +634,13 @@ exit_parent:
 /**
  *	add_mtd_device - register an MTD device
  *	@mtd: pointer to new MTD device info structure
- *	@partitioned: create partitioned device
  *
  *	Add a device to the list of MTD devices present in the system, and
  *	notify each currently active MTD 'user' of its arrival. Returns
  *	zero on success or non-zero on failure.
  */
-int add_mtd_device(struct mtd_info *mtd, bool partitioned)
+
+int add_mtd_device(struct mtd_info *mtd)
 {
 	struct device_node *np = mtd_get_of_node(mtd);
 	struct mtd_info *master = mtd_get_master(mtd);
@@ -710,17 +687,10 @@ int add_mtd_device(struct mtd_info *mtd, bool partitioned)
 	ofidx = -1;
 	if (np)
 		ofidx = of_alias_get_id(np, "mtd");
-	if (partitioned) {
-		if (ofidx >= 0)
-			i = idr_alloc(&mtd_idr, mtd, ofidx, ofidx + 1, GFP_KERNEL);
-		else
-			i = idr_alloc(&mtd_idr, mtd, 0, 0, GFP_KERNEL);
-	} else {
-		if (ofidx >= 0)
-			i = idr_alloc(&mtd_master_idr, mtd, ofidx, ofidx + 1, GFP_KERNEL);
-		else
-			i = idr_alloc(&mtd_master_idr, mtd, 0, 0, GFP_KERNEL);
-	}
+	if (ofidx >= 0)
+		i = idr_alloc(&mtd_idr, mtd, ofidx, ofidx + 1, GFP_KERNEL);
+	else
+		i = idr_alloc(&mtd_idr, mtd, 0, 0, GFP_KERNEL);
 	if (i < 0) {
 		error = i;
 		goto fail_locked;
@@ -768,18 +738,10 @@ int add_mtd_device(struct mtd_info *mtd, bool partitioned)
 	/* Caller should have set dev.parent to match the
 	 * physical device, if appropriate.
 	 */
-	if (partitioned) {
-		mtd->dev.type = &mtd_devtype;
-		mtd->dev.class = &mtd_class;
-		mtd->dev.devt = MTD_DEVT(i);
-		dev_set_name(&mtd->dev, "mtd%d", i);
-		error = dev_set_name(&mtd->dev, "mtd%d", i);
-	} else {
-		mtd->dev.type = &mtd_master_devtype;
-		mtd->dev.class = &mtd_master_class;
-		mtd->dev.devt = MKDEV(MAJOR(mtd_master_devt), i);
-		error = dev_set_name(&mtd->dev, "mtd_master%d", i);
-	}
+	mtd->dev.type = &mtd_devtype;
+	mtd->dev.class = &mtd_class;
+	mtd->dev.devt = MTD_DEVT(i);
+	error = dev_set_name(&mtd->dev, "mtd%d", i);
 	if (error)
 		goto fail_devname;
 	dev_set_drvdata(&mtd->dev, mtd);
@@ -787,7 +749,6 @@ int add_mtd_device(struct mtd_info *mtd, bool partitioned)
 	of_node_get(mtd_get_of_node(mtd));
 	error = device_register(&mtd->dev);
 	if (error) {
-		pr_err("mtd: %s device_register fail %d\n", mtd->name, error);
 		put_device(&mtd->dev);
 		goto fail_added;
 	}
@@ -799,13 +760,10 @@ int add_mtd_device(struct mtd_info *mtd, bool partitioned)
 
 	mtd_debugfs_populate(mtd);
 
-	if (partitioned) {
-		device_create(&mtd_class, mtd->dev.parent, MTD_DEVT(i) + 1, NULL,
-			      "mtd%dro", i);
-	}
+	device_create(&mtd_class, mtd->dev.parent, MTD_DEVT(i) + 1, NULL,
+		      "mtd%dro", i);
 
-	pr_debug("mtd: Giving out %spartitioned device %d to %s\n",
-		 partitioned ? "" : "un-", i, mtd->name);
+	pr_debug("mtd: Giving out device %d to %s\n", i, mtd->name);
 	/* No need to get a refcount on the module containing
 	   the notifier, since we hold the mtd_table_mutex */
 	list_for_each_entry(not, &mtd_notifiers, list)
@@ -813,16 +771,13 @@ int add_mtd_device(struct mtd_info *mtd, bool partitioned)
 
 	mutex_unlock(&mtd_table_mutex);
 
-	if (partitioned) {
-		if (of_property_read_bool(mtd_get_of_node(mtd), "linux,rootfs")) {
-			if (IS_BUILTIN(CONFIG_MTD)) {
-				pr_info("mtd: setting mtd%d (%s) as root device\n",
-					mtd->index, mtd->name);
-				ROOT_DEV = MKDEV(MTD_BLOCK_MAJOR, mtd->index);
-			} else {
-				pr_warn("mtd: can't set mtd%d (%s) as root device - mtd must be builtin\n",
-					mtd->index, mtd->name);
-			}
+	if (of_property_read_bool(mtd_get_of_node(mtd), "linux,rootfs")) {
+		if (IS_BUILTIN(CONFIG_MTD)) {
+			pr_info("mtd: setting mtd%d (%s) as root device\n", mtd->index, mtd->name);
+			ROOT_DEV = MKDEV(MTD_BLOCK_MAJOR, mtd->index);
+		} else {
+			pr_warn("mtd: can't set mtd%d (%s) as root device - mtd must be builtin\n",
+				mtd->index, mtd->name);
 		}
 	}
 
@@ -838,10 +793,7 @@ fail_nvmem_add:
 fail_added:
 	of_node_put(mtd_get_of_node(mtd));
 fail_devname:
-	if (partitioned)
-		idr_remove(&mtd_idr, i);
-	else
-		idr_remove(&mtd_master_idr, i);
+	idr_remove(&mtd_idr, i);
 fail_locked:
 	mutex_unlock(&mtd_table_mutex);
 	return error;
@@ -859,14 +811,12 @@ fail_locked:
 
 int del_mtd_device(struct mtd_info *mtd)
 {
-	struct mtd_notifier *not;
-	struct idr *idr;
 	int ret;
+	struct mtd_notifier *not;
 
 	mutex_lock(&mtd_table_mutex);
 
-	idr = mtd->dev.class == &mtd_class ? &mtd_idr : &mtd_master_idr;
-	if (idr_find(idr, mtd->index) != mtd) {
+	if (idr_find(&mtd_idr, mtd->index) != mtd) {
 		ret = -ENODEV;
 		goto out_error;
 	}
@@ -1106,7 +1056,6 @@ int mtd_device_parse_register(struct mtd_info *mtd, const char * const *types,
 			      const struct mtd_partition *parts,
 			      int nr_parts)
 {
-	struct mtd_info *parent;
 	int ret, err;
 
 	mtd_set_dev_defaults(mtd);
@@ -1115,30 +1064,25 @@ int mtd_device_parse_register(struct mtd_info *mtd, const char * const *types,
 	if (ret)
 		goto out;
 
-	ret = add_mtd_device(mtd, false);
-	if (ret)
-		goto out;
-
 	if (IS_ENABLED(CONFIG_MTD_PARTITIONED_MASTER)) {
-		ret = mtd_add_partition(mtd, mtd->name, 0, MTDPART_SIZ_FULL, &parent);
+		ret = add_mtd_device(mtd);
 		if (ret)
 			goto out;
-
-	} else {
-		parent = mtd;
 	}
 
 	/* Prefer parsed partitions over driver-provided fallback */
-	ret = parse_mtd_partitions(parent, types, parser_data);
+	ret = parse_mtd_partitions(mtd, types, parser_data);
 	if (ret == -EPROBE_DEFER)
 		goto out;
 
 	if (ret > 0)
 		ret = 0;
 	else if (nr_parts)
-		ret = add_mtd_partitions(parent, parts, nr_parts);
-	else if (!IS_ENABLED(CONFIG_MTD_PARTITIONED_MASTER))
-		ret = mtd_add_partition(parent, mtd->name, 0, MTDPART_SIZ_FULL, NULL);
+		ret = add_mtd_partitions(mtd, parts, nr_parts);
+	else if (!device_is_registered(&mtd->dev))
+		ret = add_mtd_device(mtd);
+	else
+		ret = 0;
 
 	if (ret)
 		goto out;
@@ -1158,14 +1102,13 @@ int mtd_device_parse_register(struct mtd_info *mtd, const char * const *types,
 		register_reboot_notifier(&mtd->reboot_notifier);
 	}
 
-	return 0;
 out:
-	nvmem_unregister(mtd->otp_user_nvmem);
-	nvmem_unregister(mtd->otp_factory_nvmem);
+	if (ret) {
+		nvmem_unregister(mtd->otp_user_nvmem);
+		nvmem_unregister(mtd->otp_factory_nvmem);
+	}
 
-	del_mtd_partitions(mtd);
-
-	if (device_is_registered(&mtd->dev)) {
+	if (ret && device_is_registered(&mtd->dev)) {
 		err = del_mtd_device(mtd);
 		if (err)
 			pr_err("Error when deleting MTD device (%d)\n", err);
@@ -1324,7 +1267,8 @@ int __get_mtd_device(struct mtd_info *mtd)
 		mtd = mtd->parent;
 	}
 
-	kref_get(&master->refcnt);
+	if (IS_ENABLED(CONFIG_MTD_PARTITIONED_MASTER))
+		kref_get(&master->refcnt);
 
 	return 0;
 }
@@ -1418,7 +1362,8 @@ void __put_mtd_device(struct mtd_info *mtd)
 		mtd = parent;
 	}
 
-	kref_put(&master->refcnt, mtd_device_release);
+	if (IS_ENABLED(CONFIG_MTD_PARTITIONED_MASTER))
+		kref_put(&master->refcnt, mtd_device_release);
 
 	module_put(master->owner);
 
@@ -2585,16 +2530,6 @@ static int __init init_mtd(void)
 	if (ret)
 		goto err_reg;
 
-	ret = class_register(&mtd_master_class);
-	if (ret)
-		goto err_reg2;
-
-	ret = alloc_chrdev_region(&mtd_master_devt, 0, MTD_MASTER_DEVS, "mtd_master");
-	if (ret < 0) {
-		pr_err("unable to allocate char dev region\n");
-		goto err_chrdev;
-	}
-
 	mtd_bdi = mtd_bdi_init("mtd");
 	if (IS_ERR(mtd_bdi)) {
 		ret = PTR_ERR(mtd_bdi);
@@ -2619,10 +2554,6 @@ out_procfs:
 	bdi_unregister(mtd_bdi);
 	bdi_put(mtd_bdi);
 err_bdi:
-	unregister_chrdev_region(mtd_master_devt, MTD_MASTER_DEVS);
-err_chrdev:
-	class_unregister(&mtd_master_class);
-err_reg2:
 	class_unregister(&mtd_class);
 err_reg:
 	pr_err("Error registering mtd class or bdi: %d\n", ret);
@@ -2636,12 +2567,9 @@ static void __exit cleanup_mtd(void)
 	if (proc_mtd)
 		remove_proc_entry("mtd", NULL);
 	class_unregister(&mtd_class);
-	class_unregister(&mtd_master_class);
-	unregister_chrdev_region(mtd_master_devt, MTD_MASTER_DEVS);
 	bdi_unregister(mtd_bdi);
 	bdi_put(mtd_bdi);
 	idr_destroy(&mtd_idr);
-	idr_destroy(&mtd_master_idr);
 }
 
 module_init(init_mtd);
diff --git a/drivers/mtd/mtdcore.h b/drivers/mtd/mtdcore.h
index 2258d31c5aa6..b014861a06a6 100644
--- a/drivers/mtd/mtdcore.h
+++ b/drivers/mtd/mtdcore.h
@@ -8,7 +8,7 @@ extern struct mutex mtd_table_mutex;
 extern struct backing_dev_info *mtd_bdi;
 
 struct mtd_info *__mtd_next_device(int i);
-int __must_check add_mtd_device(struct mtd_info *mtd, bool partitioned);
+int __must_check add_mtd_device(struct mtd_info *mtd);
 int del_mtd_device(struct mtd_info *mtd);
 int add_mtd_partitions(struct mtd_info *, const struct mtd_partition *, int);
 int del_mtd_partitions(struct mtd_info *);
diff --git a/drivers/mtd/mtdpart.c b/drivers/mtd/mtdpart.c
index 5a3db36d734e..994e8c51e674 100644
--- a/drivers/mtd/mtdpart.c
+++ b/drivers/mtd/mtdpart.c
@@ -86,7 +86,8 @@ static struct mtd_info *allocate_partition(struct mtd_info *parent,
 	 * parent conditional on that option. Note, this is a way to
 	 * distinguish between the parent and its partitions in sysfs.
 	 */
-	child->dev.parent = &parent->dev;
+	child->dev.parent = IS_ENABLED(CONFIG_MTD_PARTITIONED_MASTER) || mtd_is_partition(parent) ?
+			    &parent->dev : parent->dev.parent;
 	child->dev.of_node = part->of_node;
 	child->parent = parent;
 	child->part.offset = part->offset;
@@ -242,7 +243,7 @@ static int mtd_add_partition_attrs(struct mtd_info *new)
 }
 
 int mtd_add_partition(struct mtd_info *parent, const char *name,
-		      long long offset, long long length, struct mtd_info **out)
+		      long long offset, long long length)
 {
 	struct mtd_info *master = mtd_get_master(parent);
 	u64 parent_size = mtd_is_partition(parent) ?
@@ -275,15 +276,12 @@ int mtd_add_partition(struct mtd_info *parent, const char *name,
 	list_add_tail(&child->part.node, &parent->partitions);
 	mutex_unlock(&master->master.partitions_lock);
 
-	ret = add_mtd_device(child, true);
+	ret = add_mtd_device(child);
 	if (ret)
 		goto err_remove_part;
 
 	mtd_add_partition_attrs(child);
 
-	if (out)
-		*out = child;
-
 	return 0;
 
 err_remove_part:
@@ -415,7 +413,7 @@ int add_mtd_partitions(struct mtd_info *parent,
 		list_add_tail(&child->part.node, &parent->partitions);
 		mutex_unlock(&master->master.partitions_lock);
 
-		ret = add_mtd_device(child, true);
+		ret = add_mtd_device(child);
 		if (ret) {
 			mutex_lock(&master->master.partitions_lock);
 			list_del(&child->part.node);
@@ -592,6 +590,9 @@ static int mtd_part_of_parse(struct mtd_info *master,
 	int ret, err = 0;
 
 	dev = &master->dev;
+	/* Use parent device (controller) if the top level MTD is not registered */
+	if (!IS_ENABLED(CONFIG_MTD_PARTITIONED_MASTER) && !mtd_is_partition(master))
+		dev = master->dev.parent;
 
 	np = mtd_get_of_node(master);
 	if (mtd_is_partition(master))
@@ -710,7 +711,6 @@ int parse_mtd_partitions(struct mtd_info *master, const char *const *types,
 		if (ret < 0 && !err)
 			err = ret;
 	}
-
 	return err;
 }
 
diff --git a/include/linux/mtd/partitions.h b/include/linux/mtd/partitions.h
index 5daf80df9e89..b74a539ec581 100644
--- a/include/linux/mtd/partitions.h
+++ b/include/linux/mtd/partitions.h
@@ -108,7 +108,7 @@ extern void deregister_mtd_parser(struct mtd_part_parser *parser);
 		      deregister_mtd_parser)
 
 int mtd_add_partition(struct mtd_info *master, const char *name,
-		      long long offset, long long length, struct mtd_info **part);
+		      long long offset, long long length);
 int mtd_del_partition(struct mtd_info *master, int partno);
 uint64_t mtd_get_device_size(const struct mtd_info *mtd);
 

From 60dffe96fab00cee7ef7f1b151da485d42ccb33a Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Wed, 18 Jun 2025 10:47:58 +0200
Subject: [PATCH 0535/1334] mtd: spinand: winbond: Fix W35N number of
 planes/LUN

There's been a mistake when extracting the geometry of the W35N02 and
W35N04 chips from the datasheet. There is a single plane, however there
are respectively 2 and 4 LUNs. They are actually referred in the
datasheet as dies (equivalent of target), but as there is no die select
operation and the chips only feature a single configuration register for
the entire chip (instead of one per die), we can reasonably assume we
are talking about LUNs and not dies.

Reported-by: Andreas Dannenberg <dannenberg@ti.com>
Suggested-by: Vignesh Raghavendra <vigneshr@ti.com>
Fixes: 25e08bf66660 ("mtd: spinand: winbond: Add support for W35N02JW and W35N04JW chips")
Cc: stable@vger.kernel.org
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/spi/winbond.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/mtd/nand/spi/winbond.c b/drivers/mtd/nand/spi/winbond.c
index 19f8dd4a6370..2808bbd7a16e 100644
--- a/drivers/mtd/nand/spi/winbond.c
+++ b/drivers/mtd/nand/spi/winbond.c
@@ -289,7 +289,7 @@ static const struct spinand_info winbond_spinand_table[] = {
 		     SPINAND_ECCINFO(&w35n01jw_ooblayout, NULL)),
 	SPINAND_INFO("W35N02JW", /* 1.8V */
 		     SPINAND_ID(SPINAND_READID_METHOD_OPCODE_DUMMY, 0xdf, 0x22),
-		     NAND_MEMORG(1, 4096, 128, 64, 512, 10, 2, 1, 1),
+		     NAND_MEMORG(1, 4096, 128, 64, 512, 10, 1, 2, 1),
 		     NAND_ECCREQ(1, 512),
 		     SPINAND_INFO_OP_VARIANTS(&read_cache_octal_variants,
 					      &write_cache_octal_variants,
@@ -298,7 +298,7 @@ static const struct spinand_info winbond_spinand_table[] = {
 		     SPINAND_ECCINFO(&w35n01jw_ooblayout, NULL)),
 	SPINAND_INFO("W35N04JW", /* 1.8V */
 		     SPINAND_ID(SPINAND_READID_METHOD_OPCODE_DUMMY, 0xdf, 0x23),
-		     NAND_MEMORG(1, 4096, 128, 64, 512, 10, 4, 1, 1),
+		     NAND_MEMORG(1, 4096, 128, 64, 512, 10, 1, 4, 1),
 		     NAND_ECCREQ(1, 512),
 		     SPINAND_INFO_OP_VARIANTS(&read_cache_octal_variants,
 					      &write_cache_octal_variants,

From 29384bbb1a2a5926f97b8cbe469081e7a1770dea Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Wed, 18 Jun 2025 10:47:59 +0200
Subject: [PATCH 0536/1334] mtd: spinand: winbond: Increase maximum frequency
 on an octal operation

The default number of dummy cycles is 16 in octal I/O mode (1S-8S-8S),
and with this default configuration the maximum frequency is higher than
what is being advertised. There are higher and lower frequency
possibilities, which involve making changes in the number of dummy
cycles through the VCR register. At this stage, let's just describe the
default configuration correctly. There should be no functional change.

Fixes: 1ac5ff2f2ad6 ("mtd: spinand: winbond: Add octal support")
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/spi/winbond.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/mtd/nand/spi/winbond.c b/drivers/mtd/nand/spi/winbond.c
index 2808bbd7a16e..0756966b4e3c 100644
--- a/drivers/mtd/nand/spi/winbond.c
+++ b/drivers/mtd/nand/spi/winbond.c
@@ -25,7 +25,7 @@
 
 static SPINAND_OP_VARIANTS(read_cache_octal_variants,
 		SPINAND_PAGE_READ_FROM_CACHE_1S_1D_8D_OP(0, 2, NULL, 0, 105 * HZ_PER_MHZ),
-		SPINAND_PAGE_READ_FROM_CACHE_1S_8S_8S_OP(0, 16, NULL, 0, 86 * HZ_PER_MHZ),
+		SPINAND_PAGE_READ_FROM_CACHE_1S_8S_8S_OP(0, 16, NULL, 0, 162 * HZ_PER_MHZ),
 		SPINAND_PAGE_READ_FROM_CACHE_1S_1S_8S_OP(0, 1, NULL, 0, 133 * HZ_PER_MHZ),
 		SPINAND_PAGE_READ_FROM_CACHE_FAST_1S_1S_1S_OP(0, 1, NULL, 0),
 		SPINAND_PAGE_READ_FROM_CACHE_1S_1S_1S_OP(0, 1, NULL, 0));

From dba90f5a79c13936de4273a19e67908a0c296afe Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Wed, 18 Jun 2025 10:48:00 +0200
Subject: [PATCH 0537/1334] mtd: spinand: winbond: Prevent unsupported
 frequencies on dual/quad I/O variants

Dual and quad capable chips natively support dual and quad I/O variants
at up to 104MHz (1-2-2 and 1-4-4 operations). Reaching the maximum speed
of 166MHz is theoretically possible (while still unsupported in the
field) by adding a few more dummy cycles. Let's be accurate and clearly
state this limit.

Setting a maximum frequency implies adding the frequency parameter to
the macro, which is done using a variadic argument to avoid impacting
all the other drivers which already make use of this macro.

Fixes: 1ea808b4d15b ("mtd: spinand: winbond: Update the *JW chip definitions")
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/spi/winbond.c |  4 ++--
 include/linux/mtd/spinand.h    | 10 ++++++----
 2 files changed, 8 insertions(+), 6 deletions(-)

diff --git a/drivers/mtd/nand/spi/winbond.c b/drivers/mtd/nand/spi/winbond.c
index 0756966b4e3c..b7a28f001a38 100644
--- a/drivers/mtd/nand/spi/winbond.c
+++ b/drivers/mtd/nand/spi/winbond.c
@@ -42,11 +42,11 @@ static SPINAND_OP_VARIANTS(update_cache_octal_variants,
 static SPINAND_OP_VARIANTS(read_cache_dual_quad_dtr_variants,
 		SPINAND_PAGE_READ_FROM_CACHE_1S_4D_4D_OP(0, 8, NULL, 0, 80 * HZ_PER_MHZ),
 		SPINAND_PAGE_READ_FROM_CACHE_1S_1D_4D_OP(0, 2, NULL, 0, 80 * HZ_PER_MHZ),
-		SPINAND_PAGE_READ_FROM_CACHE_1S_4S_4S_OP(0, 2, NULL, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_1S_4S_4S_OP(0, 2, NULL, 0, 104 * HZ_PER_MHZ),
 		SPINAND_PAGE_READ_FROM_CACHE_1S_1S_4S_OP(0, 1, NULL, 0),
 		SPINAND_PAGE_READ_FROM_CACHE_1S_2D_2D_OP(0, 4, NULL, 0, 80 * HZ_PER_MHZ),
 		SPINAND_PAGE_READ_FROM_CACHE_1S_1D_2D_OP(0, 2, NULL, 0, 80 * HZ_PER_MHZ),
-		SPINAND_PAGE_READ_FROM_CACHE_1S_2S_2S_OP(0, 1, NULL, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_1S_2S_2S_OP(0, 1, NULL, 0, 104 * HZ_PER_MHZ),
 		SPINAND_PAGE_READ_FROM_CACHE_1S_1S_2S_OP(0, 1, NULL, 0),
 		SPINAND_PAGE_READ_FROM_CACHE_1S_1D_1D_OP(0, 2, NULL, 0, 80 * HZ_PER_MHZ),
 		SPINAND_PAGE_READ_FROM_CACHE_FAST_1S_1S_1S_OP(0, 1, NULL, 0),
diff --git a/include/linux/mtd/spinand.h b/include/linux/mtd/spinand.h
index 811a0f356315..15eaa09da998 100644
--- a/include/linux/mtd/spinand.h
+++ b/include/linux/mtd/spinand.h
@@ -113,11 +113,12 @@
 		   SPI_MEM_DTR_OP_DATA_IN(len, buf, 2),			\
 		   SPI_MEM_OP_MAX_FREQ(freq))
 
-#define SPINAND_PAGE_READ_FROM_CACHE_1S_2S_2S_OP(addr, ndummy, buf, len) \
+#define SPINAND_PAGE_READ_FROM_CACHE_1S_2S_2S_OP(addr, ndummy, buf, len, ...) \
 	SPI_MEM_OP(SPI_MEM_OP_CMD(0xbb, 1),				\
 		   SPI_MEM_OP_ADDR(2, addr, 2),				\
 		   SPI_MEM_OP_DUMMY(ndummy, 2),				\
-		   SPI_MEM_OP_DATA_IN(len, buf, 2))
+		   SPI_MEM_OP_DATA_IN(len, buf, 2),			\
+		   SPI_MEM_OP_MAX_FREQ(__VA_ARGS__ + 0))
 
 #define SPINAND_PAGE_READ_FROM_CACHE_3A_1S_2S_2S_OP(addr, ndummy, buf, len) \
 	SPI_MEM_OP(SPI_MEM_OP_CMD(0xbb, 1),				\
@@ -151,11 +152,12 @@
 		   SPI_MEM_DTR_OP_DATA_IN(len, buf, 4),			\
 		   SPI_MEM_OP_MAX_FREQ(freq))
 
-#define SPINAND_PAGE_READ_FROM_CACHE_1S_4S_4S_OP(addr, ndummy, buf, len) \
+#define SPINAND_PAGE_READ_FROM_CACHE_1S_4S_4S_OP(addr, ndummy, buf, len, ...) \
 	SPI_MEM_OP(SPI_MEM_OP_CMD(0xeb, 1),				\
 		   SPI_MEM_OP_ADDR(2, addr, 4),				\
 		   SPI_MEM_OP_DUMMY(ndummy, 4),				\
-		   SPI_MEM_OP_DATA_IN(len, buf, 4))
+		   SPI_MEM_OP_DATA_IN(len, buf, 4),			\
+		   SPI_MEM_OP_MAX_FREQ(__VA_ARGS__ + 0))
 
 #define SPINAND_PAGE_READ_FROM_CACHE_3A_1S_4S_4S_OP(addr, ndummy, buf, len) \
 	SPI_MEM_OP(SPI_MEM_OP_CMD(0xeb, 1),				\

From 10af0273a35ab4513ca1546644b8c853044da134 Mon Sep 17 00:00:00 2001
From: David Thompson <davthompson@nvidia.com>
Date: Fri, 13 Jun 2025 16:34:43 +0000
Subject: [PATCH 0538/1334] gpio: mlxbf3: only get IRQ for device instance 0

The gpio-mlxbf3 driver interfaces with two GPIO controllers,
device instance 0 and 1. There is a single IRQ resource shared
between the two controllers, and it is found in the ACPI table for
device instance 0.  The driver should not attempt to get an IRQ
resource when probing device instance 1, otherwise the following
error is logged:
  mlxbf3_gpio MLNXBF33:01: error -ENXIO: IRQ index 0 not found

Signed-off-by: David Thompson <davthompson@nvidia.com>
Reviewed-by: Shravan Kumar Ramani <shravankr@nvidia.com>
Fixes: cd33f216d241 ("gpio: mlxbf3: Add gpio driver support")
Link: https://lore.kernel.org/r/20250613163443.1065217-1-davthompson@nvidia.com
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
---
 drivers/gpio/gpio-mlxbf3.c | 52 +++++++++++++++++++++++++-------------
 1 file changed, 34 insertions(+), 18 deletions(-)

diff --git a/drivers/gpio/gpio-mlxbf3.c b/drivers/gpio/gpio-mlxbf3.c
index 10ea71273c89..9875e34bde72 100644
--- a/drivers/gpio/gpio-mlxbf3.c
+++ b/drivers/gpio/gpio-mlxbf3.c
@@ -190,7 +190,9 @@ static int mlxbf3_gpio_probe(struct platform_device *pdev)
 	struct mlxbf3_gpio_context *gs;
 	struct gpio_irq_chip *girq;
 	struct gpio_chip *gc;
+	char *colon_ptr;
 	int ret, irq;
+	long num;
 
 	gs = devm_kzalloc(dev, sizeof(*gs), GFP_KERNEL);
 	if (!gs)
@@ -227,25 +229,39 @@ static int mlxbf3_gpio_probe(struct platform_device *pdev)
 	gc->owner = THIS_MODULE;
 	gc->add_pin_ranges = mlxbf3_gpio_add_pin_ranges;
 
-	irq = platform_get_irq(pdev, 0);
-	if (irq >= 0) {
-		girq = &gs->gc.irq;
-		gpio_irq_chip_set_chip(girq, &gpio_mlxbf3_irqchip);
-		girq->default_type = IRQ_TYPE_NONE;
-		/* This will let us handle the parent IRQ in the driver */
-		girq->num_parents = 0;
-		girq->parents = NULL;
-		girq->parent_handler = NULL;
-		girq->handler = handle_bad_irq;
+	colon_ptr = strchr(dev_name(dev), ':');
+	if (!colon_ptr) {
+		dev_err(dev, "invalid device name format\n");
+		return -EINVAL;
+	}
 
-		/*
-		 * Directly request the irq here instead of passing
-		 * a flow-handler because the irq is shared.
-		 */
-		ret = devm_request_irq(dev, irq, mlxbf3_gpio_irq_handler,
-				       IRQF_SHARED, dev_name(dev), gs);
-		if (ret)
-			return dev_err_probe(dev, ret, "failed to request IRQ");
+	ret = kstrtol(++colon_ptr, 16, &num);
+	if (ret) {
+		dev_err(dev, "invalid device instance\n");
+		return ret;
+	}
+
+	if (!num) {
+		irq = platform_get_irq(pdev, 0);
+		if (irq >= 0) {
+			girq = &gs->gc.irq;
+			gpio_irq_chip_set_chip(girq, &gpio_mlxbf3_irqchip);
+			girq->default_type = IRQ_TYPE_NONE;
+			/* This will let us handle the parent IRQ in the driver */
+			girq->num_parents = 0;
+			girq->parents = NULL;
+			girq->parent_handler = NULL;
+			girq->handler = handle_bad_irq;
+
+			/*
+			 * Directly request the irq here instead of passing
+			 * a flow-handler because the irq is shared.
+			 */
+			ret = devm_request_irq(dev, irq, mlxbf3_gpio_irq_handler,
+					       IRQF_SHARED, dev_name(dev), gs);
+			if (ret)
+				return dev_err_probe(dev, ret, "failed to request IRQ");
+		}
 	}
 
 	platform_set_drvdata(pdev, gs);

From e1c75831f682eef0f68b35723437146ed86070b1 Mon Sep 17 00:00:00 2001
From: Penglei Jiang <superman.xpt@gmail.com>
Date: Tue, 17 Jun 2025 09:56:44 -0700
Subject: [PATCH 0539/1334] io_uring: fix potential page leak in
 io_sqe_buffer_register()

If allocation of the 'imu' fails, then the existing pages aren't
unpinned in the error path. This is mostly a theoretical issue,
requiring fault injection to hit.

Move unpin_user_pages() to unified error handling to fix the page leak
issue.

Fixes: d8c2237d0aa9 ("io_uring: add io_pin_pages() helper")
Signed-off-by: Penglei Jiang <superman.xpt@gmail.com>
Link: https://lore.kernel.org/r/20250617165644.79165-1-superman.xpt@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/rsrc.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/io_uring/rsrc.c b/io_uring/rsrc.c
index 94a9db030e0e..d724602697e7 100644
--- a/io_uring/rsrc.c
+++ b/io_uring/rsrc.c
@@ -809,10 +809,8 @@ static struct io_rsrc_node *io_sqe_buffer_register(struct io_ring_ctx *ctx,
 
 	imu->nr_bvecs = nr_pages;
 	ret = io_buffer_account_pin(ctx, pages, nr_pages, imu, last_hpage);
-	if (ret) {
-		unpin_user_pages(pages, nr_pages);
+	if (ret)
 		goto done;
-	}
 
 	size = iov->iov_len;
 	/* store original address for later verification */
@@ -842,6 +840,8 @@ done:
 	if (ret) {
 		if (imu)
 			io_free_imu(ctx, imu);
+		if (pages)
+			unpin_user_pages(pages, nr_pages);
 		io_cache_free(&ctx->node_cache, node);
 		node = ERR_PTR(ret);
 	}

From 327e28664307d49ce3fa71ba30dcc0007c270974 Mon Sep 17 00:00:00 2001
From: Steven Rostedt <rostedt@goodmis.org>
Date: Wed, 18 Jun 2025 07:38:01 -0400
Subject: [PATCH 0540/1334] fgraph: Do not enable function_graph tracer when
 setting funcgraph-args

When setting the funcgraph-args option when function graph tracer is net
enabled, it incorrectly enables it. Worse, it unregisters itself when it
was never registered. Then when it gets enabled again, it will register
itself a second time causing a WARNing.

 ~# echo 1 > /sys/kernel/tracing/options/funcgraph-args
 ~# head -20 /sys/kernel/tracing/trace
 # tracer: nop
 #
 # entries-in-buffer/entries-written: 813/26317372   #P:8
 #
 #                                _-----=> irqs-off/BH-disabled
 #                               / _----=> need-resched
 #                              | / _---=> hardirq/softirq
 #                              || / _--=> preempt-depth
 #                              ||| / _-=> migrate-disable
 #                              |||| /     delay
 #           TASK-PID     CPU#  |||||  TIMESTAMP  FUNCTION
 #              | |         |   |||||     |         |
           <idle>-0       [007] d..4.   358.966010:  7)   1.692 us    |          fetch_next_timer_interrupt(basej=4294981640, basem=357956000000, base_local=0xffff88823c3ae040, base_global=0xffff88823c3af300, tevt=0xffff888100e47cb8);
           <idle>-0       [007] d..4.   358.966012:  7)               |          tmigr_cpu_deactivate(nextexp=357988000000) {
           <idle>-0       [007] d..4.   358.966013:  7)               |            _raw_spin_lock(lock=0xffff88823c3b2320) {
           <idle>-0       [007] d..4.   358.966014:  7)   0.981 us    |              preempt_count_add(val=1);
           <idle>-0       [007] d..5.   358.966017:  7)   1.058 us    |              do_raw_spin_lock(lock=0xffff88823c3b2320);
           <idle>-0       [007] d..4.   358.966019:  7)   5.824 us    |            }
           <idle>-0       [007] d..5.   358.966021:  7)               |            tmigr_inactive_up(group=0xffff888100cb9000, child=0x0, data=0xffff888100e47bc0) {
           <idle>-0       [007] d..5.   358.966022:  7)               |              tmigr_update_events(group=0xffff888100cb9000, child=0x0, data=0xffff888100e47bc0) {

Notice the "tracer: nop" at the top there. The current tracer is the "nop"
tracer, but the content is obviously the function graph tracer.

Enabling function graph tracing will cause it to register again and
trigger a warning in the accounting:

 ~# echo function_graph > /sys/kernel/tracing/current_tracer
 -bash: echo: write error: Device or resource busy

With the dmesg of:

 ------------[ cut here ]------------
 WARNING: CPU: 7 PID: 1095 at kernel/trace/ftrace.c:3509 ftrace_startup_subops+0xc1e/0x1000
 Modules linked in: kvm_intel kvm irqbypass
 CPU: 7 UID: 0 PID: 1095 Comm: bash Not tainted 6.16.0-rc2-test-00006-gea03de4105d3 #24 PREEMPT
 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.3-debian-1.16.3-2 04/01/2014
 RIP: 0010:ftrace_startup_subops+0xc1e/0x1000
 Code: 48 b8 22 01 00 00 00 00 ad de 49 89 84 24 88 01 00 00 8b 44 24 08 89 04 24 e9 c3 f7 ff ff c7 04 24 ed ff ff ff e9 b7 f7 ff ff <0f> 0b c7 04 24 f0 ff ff ff e9 a9 f7 ff ff c7 04 24 f4 ff ff ff e9
 RSP: 0018:ffff888133cff948 EFLAGS: 00010202
 RAX: 0000000000000001 RBX: 1ffff1102679ff31 RCX: 0000000000000000
 RDX: 1ffffffff0b27a60 RSI: ffffffff8593d2f0 RDI: ffffffff85941140
 RBP: 00000000000c2041 R08: ffffffffffffffff R09: ffffed1020240221
 R10: ffff88810120110f R11: ffffed1020240214 R12: ffffffff8593d2f0
 R13: ffffffff8593d300 R14: ffffffff85941140 R15: ffffffff85631100
 FS:  00007f7ec6f28740(0000) GS:ffff8882b5251000(0000) knlGS:0000000000000000
 CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
 CR2: 00007f7ec6f181c0 CR3: 000000012f1d0005 CR4: 0000000000172ef0
 Call Trace:
  <TASK>
  ? __pfx_ftrace_startup_subops+0x10/0x10
  ? find_held_lock+0x2b/0x80
  ? ftrace_stub_direct_tramp+0x10/0x10
  ? ftrace_stub_direct_tramp+0x10/0x10
  ? trace_preempt_on+0xd0/0x110
  ? __pfx_trace_graph_entry_args+0x10/0x10
  register_ftrace_graph+0x4d2/0x1020
  ? tracing_reset_online_cpus+0x14b/0x1e0
  ? __pfx_register_ftrace_graph+0x10/0x10
  ? ring_buffer_record_enable+0x16/0x20
  ? tracing_reset_online_cpus+0x153/0x1e0
  ? __pfx_tracing_reset_online_cpus+0x10/0x10
  ? __pfx_trace_graph_return+0x10/0x10
  graph_trace_init+0xfd/0x160
  tracing_set_tracer+0x500/0xa80
  ? __pfx_tracing_set_tracer+0x10/0x10
  ? lock_release+0x181/0x2d0
  ? _copy_from_user+0x26/0xa0
  tracing_set_trace_write+0x132/0x1e0
  ? __pfx_tracing_set_trace_write+0x10/0x10
  ? ftrace_graph_func+0xcc/0x140
  ? ftrace_stub_direct_tramp+0x10/0x10
  ? ftrace_stub_direct_tramp+0x10/0x10
  ? ftrace_stub_direct_tramp+0x10/0x10
  vfs_write+0x1d0/0xe90
  ? __pfx_vfs_write+0x10/0x10

Have the setting of the funcgraph-args check if function_graph tracer is
the current tracer of the instance, and if not, do nothing, as there's
nothing to do (the option is checked when function_graph tracing starts).

Cc: stable@vger.kernel.org
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Link: https://lore.kernel.org/20250618073801.057ea636@gandalf.local.home
Fixes: c7a60a733c373 ("ftrace: Have funcgraph-args take affect during tracing")
Closes: https://lore.kernel.org/all/4ab1a7bdd0174ab09c7b0d68cdbff9a4@huawei.com/
Reported-by: Changbin Du <changbin.du@huawei.com>
Tested-by: Changbin Du <changbin.du@huawei.com>
Reviewed-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/trace_functions_graph.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index 9234e2c39abf..14d74a7491b8 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -455,10 +455,16 @@ static int graph_trace_init(struct trace_array *tr)
 	return 0;
 }
 
+static struct tracer graph_trace;
+
 static int ftrace_graph_trace_args(struct trace_array *tr, int set)
 {
 	trace_func_graph_ent_t entry;
 
+	/* Do nothing if the current tracer is not this tracer */
+	if (tr->current_trace != &graph_trace)
+		return 0;
+
 	if (set)
 		entry = trace_graph_entry_args;
 	else

From 93712205ce2f1fb047739494c0399a26ea4f0890 Mon Sep 17 00:00:00 2001
From: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Date: Thu, 12 Jun 2025 11:14:48 +0200
Subject: [PATCH 0541/1334] pinctrl: qcom: msm: mark certain pins as invalid
 for interrupts

On some platforms, the UFS-reset pin has no interrupt logic in TLMM but
is nevertheless registered as a GPIO in the kernel. This enables the
user-space to trigger a BUG() in the pinctrl-msm driver by running, for
example: `gpiomon -c 0 113` on RB2.

The exact culprit is requesting pins whose intr_detection_width setting
is not 1 or 2 for interrupts. This hits a BUG() in
msm_gpio_irq_set_type(). Potentially crashing the kernel due to an
invalid request from user-space is not optimal, so let's go through the
pins and mark those that would fail the check as invalid for the irq chip
as we should not even register them as available irqs.

This function can be extended if we determine that there are more
corner-cases like this.

Fixes: f365be092572 ("pinctrl: Add Qualcomm TLMM driver")
Cc: stable@vger.kernel.org
Reviewed-by: Bjorn Andersson <andersson@kernel.org>
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Link: https://lore.kernel.org/20250612091448.41546-1-brgl@bgdev.pl
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/qcom/pinctrl-msm.c | 20 ++++++++++++++++++++
 1 file changed, 20 insertions(+)

diff --git a/drivers/pinctrl/qcom/pinctrl-msm.c b/drivers/pinctrl/qcom/pinctrl-msm.c
index 5c4687de1464..f713c80d7f3e 100644
--- a/drivers/pinctrl/qcom/pinctrl-msm.c
+++ b/drivers/pinctrl/qcom/pinctrl-msm.c
@@ -1038,6 +1038,25 @@ static bool msm_gpio_needs_dual_edge_parent_workaround(struct irq_data *d,
 	       test_bit(d->hwirq, pctrl->skip_wake_irqs);
 }
 
+static void msm_gpio_irq_init_valid_mask(struct gpio_chip *gc,
+					 unsigned long *valid_mask,
+					 unsigned int ngpios)
+{
+	struct msm_pinctrl *pctrl = gpiochip_get_data(gc);
+	const struct msm_pingroup *g;
+	int i;
+
+	bitmap_fill(valid_mask, ngpios);
+
+	for (i = 0; i < ngpios; i++) {
+		g = &pctrl->soc->groups[i];
+
+		if (g->intr_detection_width != 1 &&
+		    g->intr_detection_width != 2)
+			clear_bit(i, valid_mask);
+	}
+}
+
 static int msm_gpio_irq_set_type(struct irq_data *d, unsigned int type)
 {
 	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
@@ -1441,6 +1460,7 @@ static int msm_gpio_init(struct msm_pinctrl *pctrl)
 	girq->default_type = IRQ_TYPE_NONE;
 	girq->handler = handle_bad_irq;
 	girq->parents[0] = pctrl->irq;
+	girq->init_valid_mask = msm_gpio_irq_init_valid_mask;
 
 	ret = devm_gpiochip_add_data(pctrl->dev, &pctrl->chip, pctrl);
 	if (ret) {

From 2aebf5ee43bf0ed225a09a30cf515d9f2813b759 Mon Sep 17 00:00:00 2001
From: "Masami Hiramatsu (Google)" <mhiramat@kernel.org>
Date: Wed, 18 Jun 2025 09:05:23 +0900
Subject: [PATCH 0542/1334] x86/alternatives: Fix int3 handling failure from
 broken text_poke array

Since smp_text_poke_single() does not expect there is another
text_poke request is queued, it can make text_poke_array not
sorted or cause a buffer overflow on the text_poke_array.vec[].
This will cause an Oops in int3 because of bsearch failing;

   CPU 0                        CPU 1                      CPU 2
   -----                        -----                      -----

 smp_text_poke_batch_add()

			    smp_text_poke_single() <<-- Adds out of order

							<int3>
                                                	[Fails o find address
                                                        in text_poke_array ]
                                                        OOPS!

Or unhandled page fault because of a buffer overflow;

   CPU 0                        CPU 1
   -----                        -----

 smp_text_poke_batch_add() <<+
 ...                         |
 smp_text_poke_batch_add() <<-- Adds TEXT_POKE_ARRAY_MAX times.

			     smp_text_poke_single() {
			     	__smp_text_poke_batch_add() <<-- Adds entry at
								TEXT_POKE_ARRAY_MAX + 1

                		smp_text_poke_batch_finish()
                        	  [Unhandled page fault because
				   text_poke_array.nr_entries is
				   overwritten]
				   BUG!
			     }

Use smp_text_poke_batch_add() instead of __smp_text_poke_batch_add()
so that it correctly flush the queue if needed.

Closes: https://lore.kernel.org/all/CA+G9fYsLu0roY3DV=tKyqP7FEKbOEETRvTDhnpPxJGbA=Cg+4w@mail.gmail.com/
Fixes: c8976ade0c1b ("x86/alternatives: Simplify smp_text_poke_single() by using tp_vec and existing APIs")
Reported-by: Linux Kernel Functional Testing <lkft@linaro.org>
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Tested-by: Linux Kernel Functional Testing <lkft@linaro.org>
Link: https://lkml.kernel.org/r/\ 175020512308.3582717.13631440385506146631.stgit@mhiramat.tok.corp.google.com
---
 arch/x86/kernel/alternative.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 9ae80fa904a2..ea1d984166cd 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -3138,6 +3138,6 @@ void __ref smp_text_poke_batch_add(void *addr, const void *opcode, size_t len, c
  */
 void __ref smp_text_poke_single(void *addr, const void *opcode, size_t len, const void *emulate)
 {
-	__smp_text_poke_batch_add(addr, opcode, len, emulate);
+	smp_text_poke_batch_add(addr, opcode, len, emulate);
 	smp_text_poke_batch_finish();
 }

From 7d502192431e2d863f4b2595182d61c7fa8e656f Mon Sep 17 00:00:00 2001
From: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Date: Thu, 12 Jun 2025 15:19:27 +0200
Subject: [PATCH 0543/1334] MAINTAINERS: drop bouncing Lakshmi Sowjanya D

The address for Lakshmi Sowjanya D: lakshmi.sowjanya.d@intel.com is
bouncing. Drop it and mark the driver as orphaned.

Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Link: https://lore.kernel.org/20250612131927.127733-1-brgl@bgdev.pl
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 MAINTAINERS | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 0c1d245bf7b8..949317e39ed5 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -19566,8 +19566,7 @@ T:	git git://git.kernel.org/pub/scm/linux/kernel/git/pinctrl/intel.git
 F:	drivers/pinctrl/intel/
 
 PIN CONTROLLER - KEEMBAY
-M:	Lakshmi Sowjanya D <lakshmi.sowjanya.d@intel.com>
-S:	Supported
+S:	Orphan
 F:	drivers/pinctrl/pinctrl-keembay*
 
 PIN CONTROLLER - MEDIATEK

From 46147490b4098e200b7d7d3ac4637a3e4f7b806a Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Fri, 13 Jun 2025 20:13:12 +0200
Subject: [PATCH 0544/1334] pinctrl: nuvoton: Fix boot on ma35dx platforms

As part of a wider cleanup trying to get rid of OF specific APIs, an
incorrect (and partially unrelated) cleanup was introduced.

The goal was to replace a device_for_each_chil_node() loop including an
additional condition inside by a macro doing both the loop and the
check on a single line.

The snippet:

	device_for_each_child_node(dev, child)
		if (fwnode_property_present(child, "gpio-controller"))
			continue;

was replaced by:

	for_each_gpiochip_node(dev, child)

which expands into:

	device_for_each_child_node(dev, child)
		for_each_if(fwnode_property_present(child, "gpio-controller"))

This change is actually doing the opposite of what was initially
expected, breaking the probe of this driver, breaking at the same time
the whole boot of Nuvoton platforms (no more console, the kernel WARN()).

Revert these two changes to roll back to the correct behavior.

Fixes: 693c9ecd8326 ("pinctrl: nuvoton: Reduce use of OF-specific APIs")
Cc: stable@vger.kernel.org
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Link: https://lore.kernel.org/20250613181312.1269794-1-miquel.raynal@bootlin.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/nuvoton/pinctrl-ma35.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/drivers/pinctrl/nuvoton/pinctrl-ma35.c b/drivers/pinctrl/nuvoton/pinctrl-ma35.c
index 06ae1fe8b8c5..b51704bafd81 100644
--- a/drivers/pinctrl/nuvoton/pinctrl-ma35.c
+++ b/drivers/pinctrl/nuvoton/pinctrl-ma35.c
@@ -1074,7 +1074,10 @@ static int ma35_pinctrl_probe_dt(struct platform_device *pdev, struct ma35_pinct
 	u32 idx = 0;
 	int ret;
 
-	for_each_gpiochip_node(dev, child) {
+	device_for_each_child_node(dev, child) {
+		if (fwnode_property_present(child, "gpio-controller"))
+			continue;
+
 		npctl->nfunctions++;
 		npctl->ngroups += of_get_child_count(to_of_node(child));
 	}
@@ -1092,7 +1095,10 @@ static int ma35_pinctrl_probe_dt(struct platform_device *pdev, struct ma35_pinct
 	if (!npctl->groups)
 		return -ENOMEM;
 
-	for_each_gpiochip_node(dev, child) {
+	device_for_each_child_node(dev, child) {
+		if (fwnode_property_present(child, "gpio-controller"))
+			continue;
+
 		ret = ma35_pinctrl_parse_functions(child, npctl, idx++);
 		if (ret) {
 			fwnode_handle_put(child);

From eab9dcb76b9fca47402c9e93afca243e745a0f02 Mon Sep 17 00:00:00 2001
From: Madhavan Srinivasan <maddy@linux.ibm.com>
Date: Sat, 14 Jun 2025 20:59:24 +0530
Subject: [PATCH 0545/1334] Documentation: embargoed-hardware-issues.rst: Add
 myself for Power

Adding myself as the contact for Power

Signed-off-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Link: https://lore.kernel.org/r/20250614152925.82831-1-maddy@linux.ibm.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 Documentation/process/embargoed-hardware-issues.rst | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/process/embargoed-hardware-issues.rst b/Documentation/process/embargoed-hardware-issues.rst
index da6bf0f6d01e..34e00848e0da 100644
--- a/Documentation/process/embargoed-hardware-issues.rst
+++ b/Documentation/process/embargoed-hardware-issues.rst
@@ -290,6 +290,7 @@ an involved disclosed party. The current ambassadors list:
   AMD		Tom Lendacky <thomas.lendacky@amd.com>
   Ampere	Darren Hart <darren@os.amperecomputing.com>
   ARM		Catalin Marinas <catalin.marinas@arm.com>
+  IBM Power	Madhavan Srinivasan <maddy@linux.ibm.com>
   IBM Z		Christian Borntraeger <borntraeger@de.ibm.com>
   Intel		Tony Luck <tony.luck@intel.com>
   Qualcomm	Trilok Soni <quic_tsoni@quicinc.com>

From bbf10cd686835d5a4b8566dc73a3b00b4cd7932a Mon Sep 17 00:00:00 2001
From: Lukas Wunner <lukas@wunner.de>
Date: Wed, 18 Jun 2025 16:38:25 +0200
Subject: [PATCH 0546/1334] PCI: pciehp: Ignore belated Presence Detect Changed
 caused by DPC
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Commit c3be50f7547c ("PCI: pciehp: Ignore Presence Detect Changed caused by
DPC") sought to ignore Presence Detect Changed events occurring as a side
effect of Downstream Port Containment.

The commit awaits recovery from DPC and then clears events which occurred
in the meantime.  However if the first event seen after DPC is Data Link
Layer State Changed, only that event is cleared and not Presence Detect
Changed.  The object of the commit is thus defeated.

That's because pciehp_ist() computes the events to clear based on the local
"events" variable instead of "ctrl->pending_events".  The former contains
the events that had occurred when pciehp_ist() was entered, whereas the
latter also contains events that have accumulated while awaiting DPC
recovery.

In practice, the order of PDC and DLLSC events is arbitrary and the delay
in-between can be several milliseconds.

So change the logic to always clear PDC events, even if they come after an
initial DLLSC event.

Fixes: c3be50f7547c ("PCI: pciehp: Ignore Presence Detect Changed caused by DPC")
Reported-by: Lương Việt Hoàng <tcm4095@gmail.com>
Reported-by: Joel Mathew Thomas <proxy0@tutamail.com>
Closes: https://bugzilla.kernel.org/show_bug.cgi?id=219765#c165
Signed-off-by: Lukas Wunner <lukas@wunner.de>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Tested-by: Lương Việt Hoàng <tcm4095@gmail.com>
Tested-by: Joel Mathew Thomas <proxy0@tutamail.com>
Link: https://patch.msgid.link/d9c4286a16253af7e93eaf12e076e3ef3546367a.1750257164.git.lukas@wunner.de
---
 drivers/pci/hotplug/pciehp_hpc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/pci/hotplug/pciehp_hpc.c b/drivers/pci/hotplug/pciehp_hpc.c
index ebd342bda235..91d2d92717d9 100644
--- a/drivers/pci/hotplug/pciehp_hpc.c
+++ b/drivers/pci/hotplug/pciehp_hpc.c
@@ -771,7 +771,7 @@ static irqreturn_t pciehp_ist(int irq, void *dev_id)
 		u16 ignored_events = PCI_EXP_SLTSTA_DLLSC;
 
 		if (!ctrl->inband_presence_disabled)
-			ignored_events |= events & PCI_EXP_SLTSTA_PDC;
+			ignored_events |= PCI_EXP_SLTSTA_PDC;
 
 		events &= ~ignored_events;
 		pciehp_ignore_link_change(ctrl, pdev, irq, ignored_events);

From 6c5b8895c8cab4fdb496b38513ec417588b58596 Mon Sep 17 00:00:00 2001
From: Richard Fitzgerald <rf@opensource.cirrus.com>
Date: Wed, 18 Jun 2025 15:55:47 +0100
Subject: [PATCH 0547/1334] ASoC: doc: cs35l56: Add CS35L63 to the list of
 supported devices

Add CS35L63 to the list of parts supported by the cs35l56 driver and
mention the CS35L63 where the text refers to the supported part numbers.

Signed-off-by: Richard Fitzgerald <rf@opensource.cirrus.com>
Link: https://patch.msgid.link/20250618145547.152814-1-rf@opensource.cirrus.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 Documentation/sound/codecs/cs35l56.rst | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/Documentation/sound/codecs/cs35l56.rst b/Documentation/sound/codecs/cs35l56.rst
index 7db9f93d9be5..57d1964453e1 100644
--- a/Documentation/sound/codecs/cs35l56.rst
+++ b/Documentation/sound/codecs/cs35l56.rst
@@ -1,8 +1,8 @@
 .. SPDX-License-Identifier: GPL-2.0-only
 
-=====================================================================
-Audio drivers for Cirrus Logic CS35L54/56/57 Boosted Smart Amplifiers
-=====================================================================
+========================================================================
+Audio drivers for Cirrus Logic CS35L54/56/57/63 Boosted Smart Amplifiers
+========================================================================
 :Copyright: 2025 Cirrus Logic, Inc. and
                  Cirrus Logic International Semiconductor Ltd.
 
@@ -13,11 +13,11 @@ Summary
 
 The high-level summary of this document is:
 
-**If you have a laptop that uses CS35L54/56/57 amplifiers but audio is not
+**If you have a laptop that uses CS35L54/56/57/63 amplifiers but audio is not
 working, DO NOT ATTEMPT TO USE FIRMWARE AND SETTINGS FROM ANOTHER LAPTOP,
 EVEN IF THAT LAPTOP SEEMS SIMILAR.**
 
-The CS35L54/56/57 amplifiers must be correctly configured for the power
+The CS35L54/56/57/63 amplifiers must be correctly configured for the power
 supply voltage, speaker impedance, maximum speaker voltage/current, and
 other external hardware connections.
 
@@ -34,6 +34,7 @@ The cs35l56 drivers support:
 * CS35L54
 * CS35L56
 * CS35L57
+* CS35L63
 
 There are two drivers in the kernel
 

From a55737dab6ba63eb4241e9c6547629058af31e12 Mon Sep 17 00:00:00 2001
From: "Jesse.Zhang" <Jesse.Zhang@amd.com>
Date: Thu, 29 May 2025 11:27:37 +0800
Subject: [PATCH 0548/1334] drm/amdkfd: move SDMA queue reset capability check
 to node_show

Relocate the per-SDMA queue reset capability check from
kfd_topology_set_capabilities() to node_show() to ensure we read the
latest value of sdma.supported_reset after all IP blocks are initialized.

Fixes: ceb7114c961b ("drm/amdkfd: flag per-sdma queue reset supported to user space")
Reviewed-by: Jonathan Kim <jonathan.kim@amd.com>
Signed-off-by: Jesse Zhang <Jesse.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit e17df7b086cf908cedd919f448da9e00028419bb)
---
 drivers/gpu/drm/amd/amdkfd/kfd_topology.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
index baa2374acdeb..4ec73f33535e 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
@@ -510,6 +510,10 @@ static ssize_t node_show(struct kobject *kobj, struct attribute *attr,
 			dev->node_props.capability |=
 					HSA_CAP_AQL_QUEUE_DOUBLE_MAP;
 
+		if (KFD_GC_VERSION(dev->gpu) < IP_VERSION(10, 0, 0) &&
+			(dev->gpu->adev->sdma.supported_reset & AMDGPU_RESET_TYPE_PER_QUEUE))
+				dev->node_props.capability2 |= HSA_CAP2_PER_SDMA_QUEUE_RESET_SUPPORTED;
+
 		sysfs_show_32bit_prop(buffer, offs, "max_engine_clk_fcompute",
 			dev->node_props.max_engine_clk_fcompute);
 
@@ -2008,8 +2012,6 @@ static void kfd_topology_set_capabilities(struct kfd_topology_device *dev)
 		if (!amdgpu_sriov_vf(dev->gpu->adev))
 			dev->node_props.capability |= HSA_CAP_PER_QUEUE_RESET_SUPPORTED;
 
-		if (dev->gpu->adev->sdma.supported_reset & AMDGPU_RESET_TYPE_PER_QUEUE)
-			dev->node_props.capability2 |= HSA_CAP2_PER_SDMA_QUEUE_RESET_SUPPORTED;
 	} else {
 		dev->node_props.debug_prop |= HSA_DBG_WATCH_ADDR_MASK_LO_BIT_GFX10 |
 					HSA_DBG_WATCH_ADDR_MASK_HI_BIT;

From 3251b69b7efb82eba24c9e168a6142a3078de72f Mon Sep 17 00:00:00 2001
From: Peichen Huang <PeiChen.Huang@amd.com>
Date: Mon, 26 May 2025 16:04:10 +0800
Subject: [PATCH 0549/1334] drm/amd/display: Add dc cap for dp tunneling

[WHAT]
1. add dc cap for dp tunneling
2. add function to get index of host router

Cc: Mario Limonciello <mario.limonciello@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Cruise Hung <cruise.hung@amd.com>
Signed-off-by: Peichen Huang <PeiChen.Huang@amd.com>
Signed-off-by: Alex Hung <alex.hung@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 29e178d13979cf6fdb42c5fe2dfec2da2306c4ad)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/display/dc/core/dc.c      | 33 +++++++++++++++++++
 drivers/gpu/drm/amd/display/dc/dc.h           |  8 ++++-
 .../dc/resource/dcn31/dcn31_resource.c        |  3 ++
 .../dc/resource/dcn314/dcn314_resource.c      |  3 ++
 .../dc/resource/dcn35/dcn35_resource.c        |  3 ++
 .../dc/resource/dcn351/dcn351_resource.c      |  3 ++
 .../dc/resource/dcn36/dcn36_resource.c        |  3 ++
 7 files changed, 55 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c
index 56d011a1323c..b34b5b52236d 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc.c
@@ -241,6 +241,7 @@ static bool create_links(
 	DC_LOG_DC("BIOS object table - end");
 
 	/* Create a link for each usb4 dpia port */
+	dc->lowest_dpia_link_index = MAX_LINKS;
 	for (i = 0; i < dc->res_pool->usb4_dpia_count; i++) {
 		struct link_init_data link_init_params = {0};
 		struct dc_link *link;
@@ -253,6 +254,9 @@ static bool create_links(
 
 		link = dc->link_srv->create_link(&link_init_params);
 		if (link) {
+			if (dc->lowest_dpia_link_index > dc->link_count)
+				dc->lowest_dpia_link_index = dc->link_count;
+
 			dc->links[dc->link_count] = link;
 			link->dc = dc;
 			++dc->link_count;
@@ -6376,6 +6380,35 @@ unsigned int dc_get_det_buffer_size_from_state(const struct dc_state *context)
 	else
 		return 0;
 }
+/**
+ ***********************************************************************************************
+ * dc_get_host_router_index: Get index of host router from a dpia link
+ *
+ * This function return a host router index of the target link. If the target link is dpia link.
+ *
+ * @param [in] link: target link
+ * @param [out] host_router_index: host router index of the target link
+ *
+ * @return: true if the host router index is found and valid.
+ *
+ ***********************************************************************************************
+ */
+bool dc_get_host_router_index(const struct dc_link *link, unsigned int *host_router_index)
+{
+	struct dc *dc = link->ctx->dc;
+
+	if (link->ep_type != DISPLAY_ENDPOINT_USB4_DPIA)
+		return false;
+
+	if (link->link_index < dc->lowest_dpia_link_index)
+		return false;
+
+	*host_router_index = (link->link_index - dc->lowest_dpia_link_index) / dc->caps.num_of_dpias_per_host_router;
+	if (*host_router_index < dc->caps.num_of_host_routers)
+		return true;
+	else
+		return false;
+}
 
 bool dc_is_cursor_limit_pending(struct dc *dc)
 {
diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index 1d917be36fc4..f41073c0147e 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -66,7 +66,8 @@ struct dmub_notification;
 #define MAX_STREAMS 6
 #define MIN_VIEWPORT_SIZE 12
 #define MAX_NUM_EDP 2
-#define MAX_HOST_ROUTERS_NUM 2
+#define MAX_HOST_ROUTERS_NUM 3
+#define MAX_DPIA_PER_HOST_ROUTER 2
 
 /* Display Core Interfaces */
 struct dc_versions {
@@ -305,6 +306,8 @@ struct dc_caps {
 	/* Conservative limit for DCC cases which require ODM4:1 to support*/
 	uint32_t dcc_plane_width_limit;
 	struct dc_scl_caps scl_caps;
+	uint8_t num_of_host_routers;
+	uint8_t num_of_dpias_per_host_router;
 };
 
 struct dc_bug_wa {
@@ -1603,6 +1606,7 @@ struct dc {
 
 	uint8_t link_count;
 	struct dc_link *links[MAX_LINKS];
+	uint8_t lowest_dpia_link_index;
 	struct link_service *link_srv;
 
 	struct dc_state *current_state;
@@ -2595,6 +2599,8 @@ struct dc_power_profile dc_get_power_profile_for_dc_state(const struct dc_state
 
 unsigned int dc_get_det_buffer_size_from_state(const struct dc_state *context);
 
+bool dc_get_host_router_index(const struct dc_link *link, unsigned int *host_router_index);
+
 /* DSC Interfaces */
 #include "dc_dsc.h"
 
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn31/dcn31_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn31/dcn31_resource.c
index 7e0af5297dc4..51ca0b2959fc 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dcn31/dcn31_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dcn31/dcn31_resource.c
@@ -1954,6 +1954,9 @@ static bool dcn31_resource_construct(
 	dc->caps.color.mpc.ogam_rom_caps.hlg = 0;
 	dc->caps.color.mpc.ocsc = 1;
 
+	dc->caps.num_of_host_routers = 2;
+	dc->caps.num_of_dpias_per_host_router = 2;
+
 	/* Use pipe context based otg sync logic */
 	dc->config.use_pipe_ctx_sync_logic = true;
 	dc->config.disable_hbr_audio_dp2 = true;
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn314/dcn314_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn314/dcn314_resource.c
index d96bc6cb73ad..8383e2e59be5 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dcn314/dcn314_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dcn314/dcn314_resource.c
@@ -1885,6 +1885,9 @@ static bool dcn314_resource_construct(
 
 	dc->caps.max_disp_clock_khz_at_vmin = 650000;
 
+	dc->caps.num_of_host_routers = 2;
+	dc->caps.num_of_dpias_per_host_router = 2;
+
 	/* Use pipe context based otg sync logic */
 	dc->config.use_pipe_ctx_sync_logic = true;
 
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c
index 72c6cf047db0..e01aa2f2e13e 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c
@@ -1894,6 +1894,9 @@ static bool dcn35_resource_construct(
 	dc->caps.color.mpc.ogam_rom_caps.hlg = 0;
 	dc->caps.color.mpc.ocsc = 1;
 
+	dc->caps.num_of_host_routers = 2;
+	dc->caps.num_of_dpias_per_host_router = 2;
+
 	/* max_disp_clock_khz_at_vmin is slightly lower than the STA value in order
 	 * to provide some margin.
 	 * It's expected for furture ASIC to have equal or higher value, in order to
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn351/dcn351_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn351/dcn351_resource.c
index 989a270f7dea..4ebe4e00a4f8 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dcn351/dcn351_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dcn351/dcn351_resource.c
@@ -1866,6 +1866,9 @@ static bool dcn351_resource_construct(
 	dc->caps.color.mpc.ogam_rom_caps.hlg = 0;
 	dc->caps.color.mpc.ocsc = 1;
 
+	dc->caps.num_of_host_routers = 2;
+	dc->caps.num_of_dpias_per_host_router = 2;
+
 	/* max_disp_clock_khz_at_vmin is slightly lower than the STA value in order
 	 * to provide some margin.
 	 * It's expected for furture ASIC to have equal or higher value, in order to
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn36/dcn36_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn36/dcn36_resource.c
index 48e1f234185f..db36b8f9ce65 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dcn36/dcn36_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dcn36/dcn36_resource.c
@@ -1867,6 +1867,9 @@ static bool dcn36_resource_construct(
 	dc->caps.color.mpc.ogam_rom_caps.hlg = 0;
 	dc->caps.color.mpc.ocsc = 1;
 
+	dc->caps.num_of_host_routers = 2;
+	dc->caps.num_of_dpias_per_host_router = 2;
+
 	/* max_disp_clock_khz_at_vmin is slightly lower than the STA value in order
 	 * to provide some margin.
 	 * It's expected for furture ASIC to have equal or higher value, in order to

From d358a51444c88bcc995e471dc8cc840f19e4b374 Mon Sep 17 00:00:00 2001
From: Michael Strauss <michael.strauss@amd.com>
Date: Wed, 26 Feb 2025 10:03:48 -0500
Subject: [PATCH 0550/1334] drm/amd/display: Get LTTPR IEEE OUI/Device ID From
 Closest LTTPR To Host

[WHY]
These fields are read for the explicit purpose of detecting embedded LTTPRs
(i.e. between host ASIC and the user-facing port), and thus need to
calculate the correct DPCD address offset based on LTTPR count to target
the appropriate LTTPR's DPCD register space with these queries.

[HOW]
Cascaded LTTPRs in a link each snoop and increment LTTPR count when queried
via DPCD read, so an LTTPR embedded in a source device (e.g. USB4 port on a
laptop) will always be addressible using the max LTTPR count seen by the
host. Therefore we simply need to use a recently added helper function to
calculate the correct DPCD address to target potentially embedded LTTPRs
based on the received LTTPR count.

Cc: Mario Limonciello <mario.limonciello@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Wenjing Liu <wenjing.liu@amd.com>
Signed-off-by: Michael Strauss <michael.strauss@amd.com>
Signed-off-by: Alex Hung <alex.hung@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 791897f5c77a2a65d0e500be4743af2ddf6eb061)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/display/dc/dc_dp_types.h  |  4 +-
 .../dc/link/protocols/link_dp_capability.c    | 38 +++++++++++++++----
 2 files changed, 33 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dc_dp_types.h b/drivers/gpu/drm/amd/display/dc/dc_dp_types.h
index 0bad8304ccf6..d346f8ae1634 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_dp_types.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_dp_types.h
@@ -1172,8 +1172,8 @@ struct dc_lttpr_caps {
 	union dp_128b_132b_supported_lttpr_link_rates supported_128b_132b_rates;
 	union dp_alpm_lttpr_cap alpm;
 	uint8_t aux_rd_interval[MAX_REPEATER_CNT - 1];
-	uint8_t lttpr_ieee_oui[3];
-	uint8_t lttpr_device_id[6];
+	uint8_t lttpr_ieee_oui[3]; // Always read from closest LTTPR to host
+	uint8_t lttpr_device_id[6]; // Always read from closest LTTPR to host
 };
 
 struct dc_dongle_dfp_cap_ext {
diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.c
index a5127c2d47ef..0f965380a9b4 100644
--- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.c
+++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.c
@@ -385,9 +385,15 @@ bool dp_is_128b_132b_signal(struct pipe_ctx *pipe_ctx)
 bool dp_is_lttpr_present(struct dc_link *link)
 {
 	/* Some sink devices report invalid LTTPR revision, so don't validate against that cap */
-	return (dp_parse_lttpr_repeater_count(link->dpcd_caps.lttpr_caps.phy_repeater_cnt) != 0 &&
+	uint32_t lttpr_count = dp_parse_lttpr_repeater_count(link->dpcd_caps.lttpr_caps.phy_repeater_cnt);
+	bool is_lttpr_present = (lttpr_count > 0 &&
 			link->dpcd_caps.lttpr_caps.max_lane_count > 0 &&
 			link->dpcd_caps.lttpr_caps.max_lane_count <= 4);
+
+	if (lttpr_count > 0 && !is_lttpr_present)
+		DC_LOG_ERROR("LTTPR count is nonzero but invalid lane count reported. Assuming no LTTPR present.\n");
+
+	return is_lttpr_present;
 }
 
 /* in DP compliance test, DPR-120 may have
@@ -1551,6 +1557,8 @@ enum dc_status dp_retrieve_lttpr_cap(struct dc_link *link)
 	uint8_t lttpr_dpcd_data[10] = {0};
 	enum dc_status status;
 	bool is_lttpr_present;
+	uint32_t lttpr_count;
+	uint32_t closest_lttpr_offset;
 
 	/* Logic to determine LTTPR support*/
 	bool vbios_lttpr_interop = link->dc->caps.vbios_lttpr_aware;
@@ -1602,20 +1610,22 @@ enum dc_status dp_retrieve_lttpr_cap(struct dc_link *link)
 			lttpr_dpcd_data[DP_LTTPR_ALPM_CAPABILITIES -
 							DP_LT_TUNABLE_PHY_REPEATER_FIELD_DATA_STRUCTURE_REV];
 
+	lttpr_count = dp_parse_lttpr_repeater_count(link->dpcd_caps.lttpr_caps.phy_repeater_cnt);
+
 	/* If this chip cap is set, at least one retimer must exist in the chain
 	 * Override count to 1 if we receive a known bad count (0 or an invalid value) */
 	if (((link->chip_caps & AMD_EXT_DISPLAY_PATH_CAPS__EXT_CHIP_MASK) == AMD_EXT_DISPLAY_PATH_CAPS__DP_FIXED_VS_EN) &&
-			(dp_parse_lttpr_repeater_count(link->dpcd_caps.lttpr_caps.phy_repeater_cnt) == 0)) {
+			lttpr_count == 0) {
 		/* If you see this message consistently, either the host platform has FIXED_VS flag
 		 * incorrectly configured or the sink device is returning an invalid count.
 		 */
 		DC_LOG_ERROR("lttpr_caps phy_repeater_cnt is 0x%x, forcing it to 0x80.",
 			     link->dpcd_caps.lttpr_caps.phy_repeater_cnt);
 		link->dpcd_caps.lttpr_caps.phy_repeater_cnt = 0x80;
+		lttpr_count = 1;
 		DC_LOG_DC("lttpr_caps forced phy_repeater_cnt = %d\n", link->dpcd_caps.lttpr_caps.phy_repeater_cnt);
 	}
 
-	/* Attempt to train in LTTPR transparent mode if repeater count exceeds 8. */
 	is_lttpr_present = dp_is_lttpr_present(link);
 
 	DC_LOG_DC("is_lttpr_present = %d\n", is_lttpr_present);
@@ -1623,11 +1633,25 @@ enum dc_status dp_retrieve_lttpr_cap(struct dc_link *link)
 	if (is_lttpr_present) {
 		CONN_DATA_DETECT(link, lttpr_dpcd_data, sizeof(lttpr_dpcd_data), "LTTPR Caps: ");
 
-		core_link_read_dpcd(link, DP_LTTPR_IEEE_OUI, link->dpcd_caps.lttpr_caps.lttpr_ieee_oui, sizeof(link->dpcd_caps.lttpr_caps.lttpr_ieee_oui));
-		CONN_DATA_DETECT(link, link->dpcd_caps.lttpr_caps.lttpr_ieee_oui, sizeof(link->dpcd_caps.lttpr_caps.lttpr_ieee_oui), "LTTPR IEEE OUI: ");
+		// Identify closest LTTPR to determine if workarounds required for known embedded LTTPR
+		closest_lttpr_offset = dp_get_closest_lttpr_offset(lttpr_count);
 
-		core_link_read_dpcd(link, DP_LTTPR_DEVICE_ID, link->dpcd_caps.lttpr_caps.lttpr_device_id, sizeof(link->dpcd_caps.lttpr_caps.lttpr_device_id));
-		CONN_DATA_DETECT(link, link->dpcd_caps.lttpr_caps.lttpr_device_id, sizeof(link->dpcd_caps.lttpr_caps.lttpr_device_id), "LTTPR Device ID: ");
+		core_link_read_dpcd(link, (DP_LTTPR_IEEE_OUI + closest_lttpr_offset),
+				link->dpcd_caps.lttpr_caps.lttpr_ieee_oui, sizeof(link->dpcd_caps.lttpr_caps.lttpr_ieee_oui));
+		core_link_read_dpcd(link, (DP_LTTPR_DEVICE_ID + closest_lttpr_offset),
+				link->dpcd_caps.lttpr_caps.lttpr_device_id, sizeof(link->dpcd_caps.lttpr_caps.lttpr_device_id));
+
+		if (lttpr_count > 1) {
+			CONN_DATA_DETECT(link, link->dpcd_caps.lttpr_caps.lttpr_ieee_oui, sizeof(link->dpcd_caps.lttpr_caps.lttpr_ieee_oui),
+					"Closest LTTPR To Host's IEEE OUI: ");
+			CONN_DATA_DETECT(link, link->dpcd_caps.lttpr_caps.lttpr_device_id, sizeof(link->dpcd_caps.lttpr_caps.lttpr_device_id),
+					"Closest LTTPR To Host's LTTPR Device ID: ");
+		} else {
+			CONN_DATA_DETECT(link, link->dpcd_caps.lttpr_caps.lttpr_ieee_oui, sizeof(link->dpcd_caps.lttpr_caps.lttpr_ieee_oui),
+					"LTTPR IEEE OUI: ");
+			CONN_DATA_DETECT(link, link->dpcd_caps.lttpr_caps.lttpr_device_id, sizeof(link->dpcd_caps.lttpr_caps.lttpr_device_id),
+					"LTTPR Device ID: ");
+		}
 	}
 
 	return status;

From 0d57dd1765d311111d9885346108c4deeae1deb4 Mon Sep 17 00:00:00 2001
From: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Date: Wed, 21 May 2025 16:40:25 -0400
Subject: [PATCH 0551/1334] drm/amd/display: Add more checks for DSC / HUBP ONO
 guarantees

[WHY]
For non-zero DSC instances it's possible that the HUBP domain required
to drive it for sequential ONO ASICs isn't met, potentially causing
the logic to the tile to enter an undefined state leading to a system
hang.

[HOW]
Add more checks to ensure that the HUBP domain matching the DSC instance
is appropriately powered.

Cc: Mario Limonciello <mario.limonciello@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Duncan Ma <duncan.ma@amd.com>
Signed-off-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Signed-off-by: Alex Hung <alex.hung@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit da63df07112e5a9857a8d2aaa04255c4206754ec)
Cc: stable@vger.kernel.org
---
 .../amd/display/dc/hwss/dcn35/dcn35_hwseq.c   | 28 +++++++++++++++++++
 1 file changed, 28 insertions(+)

diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c
index c814d957305a..a267f574b619 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c
@@ -1047,6 +1047,15 @@ void dcn35_calc_blocks_to_gate(struct dc *dc, struct dc_state *context,
 			if (dc->caps.sequential_ono) {
 				update_state->pg_pipe_res_update[PG_HUBP][pipe_ctx->stream_res.dsc->inst] = false;
 				update_state->pg_pipe_res_update[PG_DPP][pipe_ctx->stream_res.dsc->inst] = false;
+
+				/* All HUBP/DPP instances must be powered if the DSC inst != HUBP inst */
+				if (!pipe_ctx->top_pipe && pipe_ctx->plane_res.hubp &&
+				    pipe_ctx->plane_res.hubp->inst != pipe_ctx->stream_res.dsc->inst) {
+					for (j = 0; j < dc->res_pool->pipe_count; ++j) {
+						update_state->pg_pipe_res_update[PG_HUBP][j] = false;
+						update_state->pg_pipe_res_update[PG_DPP][j] = false;
+					}
+				}
 			}
 		}
 
@@ -1193,6 +1202,25 @@ void dcn35_calc_blocks_to_ungate(struct dc *dc, struct dc_state *context,
 		update_state->pg_pipe_res_update[PG_HDMISTREAM][0] = true;
 
 	if (dc->caps.sequential_ono) {
+		for (i = 0; i < dc->res_pool->pipe_count; i++) {
+			struct pipe_ctx *new_pipe = &context->res_ctx.pipe_ctx[i];
+
+			if (new_pipe->stream_res.dsc && !new_pipe->top_pipe &&
+			    update_state->pg_pipe_res_update[PG_DSC][new_pipe->stream_res.dsc->inst]) {
+				update_state->pg_pipe_res_update[PG_HUBP][new_pipe->stream_res.dsc->inst] = true;
+				update_state->pg_pipe_res_update[PG_DPP][new_pipe->stream_res.dsc->inst] = true;
+
+				/* All HUBP/DPP instances must be powered if the DSC inst != HUBP inst */
+				if (new_pipe->plane_res.hubp &&
+				    new_pipe->plane_res.hubp->inst != new_pipe->stream_res.dsc->inst) {
+					for (j = 0; j < dc->res_pool->pipe_count; ++j) {
+						update_state->pg_pipe_res_update[PG_HUBP][j] = true;
+						update_state->pg_pipe_res_update[PG_DPP][j] = true;
+					}
+				}
+			}
+		}
+
 		for (i = dc->res_pool->pipe_count - 1; i >= 0; i--) {
 			if (update_state->pg_pipe_res_update[PG_HUBP][i] &&
 			    update_state->pg_pipe_res_update[PG_DPP][i]) {

From 8724a5380c4390eed81e271d22f34ff06453ded9 Mon Sep 17 00:00:00 2001
From: Alex Hung <alex.hung@amd.com>
Date: Thu, 29 May 2025 10:59:19 -0600
Subject: [PATCH 0552/1334] drm/amd/display: Fix mpv playback corruption on
 weston

[WHAT]
Severe video playback corruption is observed in the following setup:

weston 14.0.90 (built from source) + mpv v0.40.0 with command:
mpv bbb_sunflower_1080p_60fps_normal.mp4 --vo=gpu

[HOW]
ABGR16161616 needs to be included in dml2/2.1 translation.

Cc: Mario Limonciello <mario.limonciello@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Acked-by: Aurabindo Pillai <aurabindo.pillai@amd.com>
Reviewed-by: Harry Wentland <harry.wentland@amd.com>
Reviewed-by: Austin Zheng <austin.zheng@amd.com>
Signed-off-by: Alex Hung <alex.hung@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit d023de809f85307ca819a9dbbceee6ae1f50e2ad)
Cc: stable@vger.kernel.org
---
 .../gpu/drm/amd/display/dc/dml2/dml21/dml21_translation_helper.c | 1 +
 drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c    | 1 +
 2 files changed, 2 insertions(+)

diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_translation_helper.c b/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_translation_helper.c
index d47cacfdb695..2aa6d44bb359 100644
--- a/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_translation_helper.c
+++ b/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_translation_helper.c
@@ -788,6 +788,7 @@ static void populate_dml21_plane_config_from_plane_state(struct dml2_context *dm
 		plane->pixel_format = dml2_420_10;
 		break;
 	case SURFACE_PIXEL_FORMAT_GRPH_ARGB16161616:
+	case SURFACE_PIXEL_FORMAT_GRPH_ABGR16161616:
 	case SURFACE_PIXEL_FORMAT_GRPH_ARGB16161616F:
 	case SURFACE_PIXEL_FORMAT_GRPH_ABGR16161616F:
 		plane->pixel_format = dml2_444_64;
diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c b/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c
index 5de775fd8fce..208630754c8a 100644
--- a/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c
+++ b/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c
@@ -953,6 +953,7 @@ static void populate_dml_surface_cfg_from_plane_state(enum dml_project_id dml2_p
 		out->SourcePixelFormat[location] = dml_420_10;
 		break;
 	case SURFACE_PIXEL_FORMAT_GRPH_ARGB16161616:
+	case SURFACE_PIXEL_FORMAT_GRPH_ABGR16161616:
 	case SURFACE_PIXEL_FORMAT_GRPH_ARGB16161616F:
 	case SURFACE_PIXEL_FORMAT_GRPH_ABGR16161616F:
 		out->SourcePixelFormat[location] = dml_444_64;

From 158f9944ac05dafd2d3a23d0688e6cf40ef68b90 Mon Sep 17 00:00:00 2001
From: Yihan Zhu <Yihan.Zhu@amd.com>
Date: Tue, 27 May 2025 16:47:40 -0400
Subject: [PATCH 0553/1334] drm/amd/display: Fix RMCM programming seq errors

[WHY & HOW]
Fix RMCM programming sequence errors and mapping issues to pass the RMCM
test.

Cc: Mario Limonciello <mario.limonciello@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Dmytro Laktyushkin <dmytro.laktyushkin@amd.com>
Signed-off-by: Yihan Zhu <Yihan.Zhu@amd.com>
Signed-off-by: Alex Hung <alex.hung@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 11baa4975025033547f45f5894087a0dda6efbb8)
Cc: stable@vger.kernel.org
---
 .../dc/dml2/dml21/src/dml2_core/dml2_core_dcn4_calcs.c       | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_core/dml2_core_dcn4_calcs.c b/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_core/dml2_core_dcn4_calcs.c
index c4dad7164d31..5b62cd19d979 100644
--- a/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_core/dml2_core_dcn4_calcs.c
+++ b/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_core/dml2_core_dcn4_calcs.c
@@ -4685,7 +4685,10 @@ static void calculate_tdlut_setting(
 	//the tdlut is fetched during the 2 row times of prefetch.
 	if (p->setup_for_tdlut) {
 		*p->tdlut_groups_per_2row_ub = (unsigned int)math_ceil2((double) *p->tdlut_bytes_per_frame / *p->tdlut_bytes_per_group, 1);
-		*p->tdlut_opt_time = (*p->tdlut_bytes_per_frame - p->cursor_buffer_size * 1024) / tdlut_drain_rate;
+		if (*p->tdlut_bytes_per_frame > p->cursor_buffer_size * 1024)
+			*p->tdlut_opt_time = (*p->tdlut_bytes_per_frame - p->cursor_buffer_size * 1024) / tdlut_drain_rate;
+		else
+			*p->tdlut_opt_time = 0;
 		*p->tdlut_drain_time = p->cursor_buffer_size * 1024 / tdlut_drain_rate;
 		*p->tdlut_bytes_to_deliver = (unsigned int) (p->cursor_buffer_size * 1024.0);
 	}

From ffcaed1d7ecef31198000dfbbea791f30f7ca437 Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Thu, 29 May 2025 11:33:44 -0500
Subject: [PATCH 0554/1334] drm/amd/display: Only read ACPI backlight caps once

[WHY]
Backlight caps are read already in amdgpu_dm_update_backlight_caps().
They may be updated by update_connector_ext_caps(). Reading again when
registering backlight device may cause wrong values to be used.

[HOW]
Use backlight caps already registered to the dm.

Cc: Mario Limonciello <mario.limonciello@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Roman Li <roman.li@amd.com>
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Alex Hung <alex.hung@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 148144f6d2f14b02eaaa39b86bbe023cbff350bd)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index d3100f641ac6..0b5d5ab14a69 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -4908,7 +4908,7 @@ amdgpu_dm_register_backlight_device(struct amdgpu_dm_connector *aconnector)
 	struct drm_device *drm = aconnector->base.dev;
 	struct amdgpu_display_manager *dm = &drm_to_adev(drm)->dm;
 	struct backlight_properties props = { 0 };
-	struct amdgpu_dm_backlight_caps caps = { 0 };
+	struct amdgpu_dm_backlight_caps *caps;
 	char bl_name[16];
 	int min, max;
 
@@ -4922,20 +4922,20 @@ amdgpu_dm_register_backlight_device(struct amdgpu_dm_connector *aconnector)
 		return;
 	}
 
-	amdgpu_acpi_get_backlight_caps(&caps);
-	if (caps.caps_valid && get_brightness_range(&caps, &min, &max)) {
+	caps = &dm->backlight_caps[aconnector->bl_idx];
+	if (get_brightness_range(caps, &min, &max)) {
 		if (power_supply_is_system_supplied() > 0)
-			props.brightness = (max - min) * DIV_ROUND_CLOSEST(caps.ac_level, 100);
+			props.brightness = (max - min) * DIV_ROUND_CLOSEST(caps->ac_level, 100);
 		else
-			props.brightness = (max - min) * DIV_ROUND_CLOSEST(caps.dc_level, 100);
+			props.brightness = (max - min) * DIV_ROUND_CLOSEST(caps->dc_level, 100);
 		/* min is zero, so max needs to be adjusted */
 		props.max_brightness = max - min;
 		drm_dbg(drm, "Backlight caps: min: %d, max: %d, ac %d, dc %d\n", min, max,
-			caps.ac_level, caps.dc_level);
+			caps->ac_level, caps->dc_level);
 	} else
 		props.brightness = AMDGPU_MAX_BL_LEVEL;
 
-	if (caps.data_points && !(amdgpu_dc_debug_mask & DC_DISABLE_CUSTOM_BRIGHTNESS_CURVE))
+	if (caps->data_points && !(amdgpu_dc_debug_mask & DC_DISABLE_CUSTOM_BRIGHTNESS_CURVE))
 		drm_info(drm, "Using custom brightness curve\n");
 	props.max_brightness = AMDGPU_MAX_BL_LEVEL;
 	props.type = BACKLIGHT_RAW;

From 16dc8bc27c2aa3c93905d3e885e27f1e3535f09a Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Thu, 29 May 2025 09:46:32 -0500
Subject: [PATCH 0555/1334] drm/amd/display: Export full brightness range to
 userspace

[WHY]
Userspace currently is offered a range from 0-0xFF but the PWM is
programmed from 0-0xFFFF.  This can be limiting to some software
that wants to apply greater granularity.

[HOW]
Convert internally to firmware values only when mapping custom
brightness curves because these are in 0-0xFF range. Advertise full
PWM range to userspace.

Cc: Mario Limonciello <mario.limonciello@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Roman Li <roman.li@amd.com>
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Alex Hung <alex.hung@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 8dbd72cb790058ce52279af38a43c2b302fdd3e5)
Cc: stable@vger.kernel.org
---
 .../gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 43 ++++++++++++-------
 1 file changed, 28 insertions(+), 15 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 0b5d5ab14a69..bc4cd11bfc79 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -4718,9 +4718,23 @@ static int get_brightness_range(const struct amdgpu_dm_backlight_caps *caps,
 	return 1;
 }
 
-static void convert_custom_brightness(const struct amdgpu_dm_backlight_caps *caps,
-				      uint32_t *brightness)
+/* Rescale from [min..max] to [0..AMDGPU_MAX_BL_LEVEL] */
+static inline u32 scale_input_to_fw(int min, int max, u64 input)
 {
+	return DIV_ROUND_CLOSEST_ULL(input * AMDGPU_MAX_BL_LEVEL, max - min);
+}
+
+/* Rescale from [0..AMDGPU_MAX_BL_LEVEL] to [min..max] */
+static inline u32 scale_fw_to_input(int min, int max, u64 input)
+{
+	return min + DIV_ROUND_CLOSEST_ULL(input * (max - min), AMDGPU_MAX_BL_LEVEL);
+}
+
+static void convert_custom_brightness(const struct amdgpu_dm_backlight_caps *caps,
+				      unsigned int min, unsigned int max,
+				      uint32_t *user_brightness)
+{
+	u32 brightness = scale_input_to_fw(min, max, *user_brightness);
 	u8 prev_signal = 0, prev_lum = 0;
 	int i = 0;
 
@@ -4731,7 +4745,7 @@ static void convert_custom_brightness(const struct amdgpu_dm_backlight_caps *cap
 		return;
 
 	/* choose start to run less interpolation steps */
-	if (caps->luminance_data[caps->data_points/2].input_signal > *brightness)
+	if (caps->luminance_data[caps->data_points/2].input_signal > brightness)
 		i = caps->data_points/2;
 	do {
 		u8 signal = caps->luminance_data[i].input_signal;
@@ -4742,17 +4756,18 @@ static void convert_custom_brightness(const struct amdgpu_dm_backlight_caps *cap
 		 * brightness < signal: interpolate between previous and current luminance numerator
 		 * brightness > signal: find next data point
 		 */
-		if (*brightness > signal) {
+		if (brightness > signal) {
 			prev_signal = signal;
 			prev_lum = lum;
 			i++;
 			continue;
 		}
-		if (*brightness < signal)
+		if (brightness < signal)
 			lum = prev_lum + DIV_ROUND_CLOSEST((lum - prev_lum) *
-							   (*brightness - prev_signal),
+							   (brightness - prev_signal),
 							   signal - prev_signal);
-		*brightness = DIV_ROUND_CLOSEST(lum * *brightness, 101);
+		*user_brightness = scale_fw_to_input(min, max,
+						     DIV_ROUND_CLOSEST(lum * brightness, 101));
 		return;
 	} while (i < caps->data_points);
 }
@@ -4765,11 +4780,10 @@ static u32 convert_brightness_from_user(const struct amdgpu_dm_backlight_caps *c
 	if (!get_brightness_range(caps, &min, &max))
 		return brightness;
 
-	convert_custom_brightness(caps, &brightness);
+	convert_custom_brightness(caps, min, max, &brightness);
 
-	// Rescale 0..255 to min..max
-	return min + DIV_ROUND_CLOSEST((max - min) * brightness,
-				       AMDGPU_MAX_BL_LEVEL);
+	// Rescale 0..max to min..max
+	return min + DIV_ROUND_CLOSEST_ULL((u64)(max - min) * brightness, max);
 }
 
 static u32 convert_brightness_to_user(const struct amdgpu_dm_backlight_caps *caps,
@@ -4782,8 +4796,8 @@ static u32 convert_brightness_to_user(const struct amdgpu_dm_backlight_caps *cap
 
 	if (brightness < min)
 		return 0;
-	// Rescale min..max to 0..255
-	return DIV_ROUND_CLOSEST(AMDGPU_MAX_BL_LEVEL * (brightness - min),
+	// Rescale min..max to 0..max
+	return DIV_ROUND_CLOSEST_ULL((u64)max * (brightness - min),
 				 max - min);
 }
 
@@ -4933,11 +4947,10 @@ amdgpu_dm_register_backlight_device(struct amdgpu_dm_connector *aconnector)
 		drm_dbg(drm, "Backlight caps: min: %d, max: %d, ac %d, dc %d\n", min, max,
 			caps->ac_level, caps->dc_level);
 	} else
-		props.brightness = AMDGPU_MAX_BL_LEVEL;
+		props.brightness = props.max_brightness = AMDGPU_MAX_BL_LEVEL;
 
 	if (caps->data_points && !(amdgpu_dc_debug_mask & DC_DISABLE_CUSTOM_BRIGHTNESS_CURVE))
 		drm_info(drm, "Using custom brightness curve\n");
-	props.max_brightness = AMDGPU_MAX_BL_LEVEL;
 	props.type = BACKLIGHT_RAW;
 
 	snprintf(bl_name, sizeof(bl_name), "amdgpu_bl%d",

From 0bbf5fd86c585d437b75003f11365b324360a5d6 Mon Sep 17 00:00:00 2001
From: Frank Min <Frank.Min@amd.com>
Date: Wed, 4 Jun 2025 21:00:44 +0800
Subject: [PATCH 0556/1334] drm/amdgpu: Add kicker device detection

1. add kicker device list
2. add kicker device checking helper function

Signed-off-by: Frank Min <Frank.Min@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 09aa2b408f4ab689c3541d22b0968de0392ee406)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c | 17 +++++++++++++++++
 drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h |  6 ++++++
 2 files changed, 23 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c
index 2505c46a9c3d..eaddc441c51a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c
@@ -30,6 +30,10 @@
 
 #define AMDGPU_UCODE_NAME_MAX		(128)
 
+static const struct kicker_device kicker_device_list[] = {
+	{0x744B, 0x00},
+};
+
 static void amdgpu_ucode_print_common_hdr(const struct common_firmware_header *hdr)
 {
 	DRM_DEBUG("size_bytes: %u\n", le32_to_cpu(hdr->size_bytes));
@@ -1387,6 +1391,19 @@ static const char *amdgpu_ucode_legacy_naming(struct amdgpu_device *adev, int bl
 	return NULL;
 }
 
+bool amdgpu_is_kicker_fw(struct amdgpu_device *adev)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(kicker_device_list); i++) {
+		if (adev->pdev->device == kicker_device_list[i].device &&
+			adev->pdev->revision == kicker_device_list[i].revision)
+		return true;
+	}
+
+	return false;
+}
+
 void amdgpu_ucode_ip_version_decode(struct amdgpu_device *adev, int block_type, char *ucode_prefix, int len)
 {
 	int maj, min, rev;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h
index 9e89c3487be5..6349aad6da35 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h
@@ -605,6 +605,11 @@ struct amdgpu_firmware {
 	uint32_t pldm_version;
 };
 
+struct kicker_device{
+	unsigned short device;
+	u8 revision;
+};
+
 void amdgpu_ucode_print_mc_hdr(const struct common_firmware_header *hdr);
 void amdgpu_ucode_print_smc_hdr(const struct common_firmware_header *hdr);
 void amdgpu_ucode_print_imu_hdr(const struct common_firmware_header *hdr);
@@ -632,5 +637,6 @@ amdgpu_ucode_get_load_type(struct amdgpu_device *adev, int load_type);
 const char *amdgpu_ucode_name(enum AMDGPU_UCODE_ID ucode_id);
 
 void amdgpu_ucode_ip_version_decode(struct amdgpu_device *adev, int block_type, char *ucode_prefix, int len);
+bool amdgpu_is_kicker_fw(struct amdgpu_device *adev);
 
 #endif

From 854171405e7f093532b33d8ed0875b9e34fc55b4 Mon Sep 17 00:00:00 2001
From: Frank Min <Frank.Min@amd.com>
Date: Wed, 4 Jun 2025 21:17:05 +0800
Subject: [PATCH 0557/1334] drm/amdgpu: add kicker fws loading for
 gfx11/smu13/psp13

1. Add kicker firmwares loading for gfx11/smu13/psp13
2. Register additional MODULE_FIRMWARE entries for kicker fws
   - gc_11_0_0_rlc_kicker.bin
   - gc_11_0_0_imu_kicker.bin
   - psp_13_0_0_sos_kicker.bin
   - psp_13_0_0_ta_kicker.bin
   - smu_13_0_0_kicker.bin

Signed-off-by: Frank Min <Frank.Min@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit fb5ec2174d70a8989bc207d257db90ffeca3b163)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c        | 16 ++++++++++++----
 drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c         |  5 +++++
 drivers/gpu/drm/amd/amdgpu/imu_v11_0.c         |  9 +++++++--
 drivers/gpu/drm/amd/amdgpu/psp_v13_0.c         |  2 ++
 drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c | 12 +++++++++---
 5 files changed, 35 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
index e6f0b035e20b..c14f63cefe67 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
@@ -3522,8 +3522,12 @@ int psp_init_sos_microcode(struct psp_context *psp, const char *chip_name)
 	uint8_t *ucode_array_start_addr;
 	int err = 0;
 
-	err = amdgpu_ucode_request(adev, &adev->psp.sos_fw, AMDGPU_UCODE_REQUIRED,
-				   "amdgpu/%s_sos.bin", chip_name);
+	if (amdgpu_is_kicker_fw(adev))
+		err = amdgpu_ucode_request(adev, &adev->psp.sos_fw, AMDGPU_UCODE_REQUIRED,
+					   "amdgpu/%s_sos_kicker.bin", chip_name);
+	else
+		err = amdgpu_ucode_request(adev, &adev->psp.sos_fw, AMDGPU_UCODE_REQUIRED,
+					   "amdgpu/%s_sos.bin", chip_name);
 	if (err)
 		goto out;
 
@@ -3799,8 +3803,12 @@ int psp_init_ta_microcode(struct psp_context *psp, const char *chip_name)
 	struct amdgpu_device *adev = psp->adev;
 	int err;
 
-	err = amdgpu_ucode_request(adev, &adev->psp.ta_fw, AMDGPU_UCODE_REQUIRED,
-				   "amdgpu/%s_ta.bin", chip_name);
+	if (amdgpu_is_kicker_fw(adev))
+		err = amdgpu_ucode_request(adev, &adev->psp.ta_fw, AMDGPU_UCODE_REQUIRED,
+					   "amdgpu/%s_ta_kicker.bin", chip_name);
+	else
+		err = amdgpu_ucode_request(adev, &adev->psp.ta_fw, AMDGPU_UCODE_REQUIRED,
+					   "amdgpu/%s_ta.bin", chip_name);
 	if (err)
 		return err;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
index afd6d59164bf..ec9b84f92d46 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
@@ -85,6 +85,7 @@ MODULE_FIRMWARE("amdgpu/gc_11_0_0_pfp.bin");
 MODULE_FIRMWARE("amdgpu/gc_11_0_0_me.bin");
 MODULE_FIRMWARE("amdgpu/gc_11_0_0_mec.bin");
 MODULE_FIRMWARE("amdgpu/gc_11_0_0_rlc.bin");
+MODULE_FIRMWARE("amdgpu/gc_11_0_0_rlc_kicker.bin");
 MODULE_FIRMWARE("amdgpu/gc_11_0_0_rlc_1.bin");
 MODULE_FIRMWARE("amdgpu/gc_11_0_0_toc.bin");
 MODULE_FIRMWARE("amdgpu/gc_11_0_1_pfp.bin");
@@ -759,6 +760,10 @@ static int gfx_v11_0_init_microcode(struct amdgpu_device *adev)
 			err = amdgpu_ucode_request(adev, &adev->gfx.rlc_fw,
 						   AMDGPU_UCODE_REQUIRED,
 						   "amdgpu/gc_11_0_0_rlc_1.bin");
+		else if (amdgpu_is_kicker_fw(adev))
+			err = amdgpu_ucode_request(adev, &adev->gfx.rlc_fw,
+						   AMDGPU_UCODE_REQUIRED,
+						   "amdgpu/%s_rlc_kicker.bin", ucode_prefix);
 		else
 			err = amdgpu_ucode_request(adev, &adev->gfx.rlc_fw,
 						   AMDGPU_UCODE_REQUIRED,
diff --git a/drivers/gpu/drm/amd/amdgpu/imu_v11_0.c b/drivers/gpu/drm/amd/amdgpu/imu_v11_0.c
index cfa91d709d49..cc626036ed9c 100644
--- a/drivers/gpu/drm/amd/amdgpu/imu_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/imu_v11_0.c
@@ -32,6 +32,7 @@
 #include "gc/gc_11_0_0_sh_mask.h"
 
 MODULE_FIRMWARE("amdgpu/gc_11_0_0_imu.bin");
+MODULE_FIRMWARE("amdgpu/gc_11_0_0_imu_kicker.bin");
 MODULE_FIRMWARE("amdgpu/gc_11_0_1_imu.bin");
 MODULE_FIRMWARE("amdgpu/gc_11_0_2_imu.bin");
 MODULE_FIRMWARE("amdgpu/gc_11_0_3_imu.bin");
@@ -51,8 +52,12 @@ static int imu_v11_0_init_microcode(struct amdgpu_device *adev)
 	DRM_DEBUG("\n");
 
 	amdgpu_ucode_ip_version_decode(adev, GC_HWIP, ucode_prefix, sizeof(ucode_prefix));
-	err = amdgpu_ucode_request(adev, &adev->gfx.imu_fw, AMDGPU_UCODE_REQUIRED,
-				   "amdgpu/%s_imu.bin", ucode_prefix);
+	if (amdgpu_is_kicker_fw(adev))
+		err = amdgpu_ucode_request(adev, &adev->gfx.imu_fw, AMDGPU_UCODE_REQUIRED,
+					   "amdgpu/%s_imu_kicker.bin", ucode_prefix);
+	else
+		err = amdgpu_ucode_request(adev, &adev->gfx.imu_fw, AMDGPU_UCODE_REQUIRED,
+					   "amdgpu/%s_imu.bin", ucode_prefix);
 	if (err)
 		goto out;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c
index df612fd9cc50..ead616c11705 100644
--- a/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c
@@ -42,7 +42,9 @@ MODULE_FIRMWARE("amdgpu/psp_13_0_5_ta.bin");
 MODULE_FIRMWARE("amdgpu/psp_13_0_8_toc.bin");
 MODULE_FIRMWARE("amdgpu/psp_13_0_8_ta.bin");
 MODULE_FIRMWARE("amdgpu/psp_13_0_0_sos.bin");
+MODULE_FIRMWARE("amdgpu/psp_13_0_0_sos_kicker.bin");
 MODULE_FIRMWARE("amdgpu/psp_13_0_0_ta.bin");
+MODULE_FIRMWARE("amdgpu/psp_13_0_0_ta_kicker.bin");
 MODULE_FIRMWARE("amdgpu/psp_13_0_7_sos.bin");
 MODULE_FIRMWARE("amdgpu/psp_13_0_7_ta.bin");
 MODULE_FIRMWARE("amdgpu/psp_13_0_10_sos.bin");
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c
index a7167668d189..1c7235935d14 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c
@@ -58,6 +58,7 @@
 
 MODULE_FIRMWARE("amdgpu/aldebaran_smc.bin");
 MODULE_FIRMWARE("amdgpu/smu_13_0_0.bin");
+MODULE_FIRMWARE("amdgpu/smu_13_0_0_kicker.bin");
 MODULE_FIRMWARE("amdgpu/smu_13_0_7.bin");
 MODULE_FIRMWARE("amdgpu/smu_13_0_10.bin");
 
@@ -92,7 +93,7 @@ const int pmfw_decoded_link_width[7] = {0, 1, 2, 4, 8, 12, 16};
 int smu_v13_0_init_microcode(struct smu_context *smu)
 {
 	struct amdgpu_device *adev = smu->adev;
-	char ucode_prefix[15];
+	char ucode_prefix[30];
 	int err = 0;
 	const struct smc_firmware_header_v1_0 *hdr;
 	const struct common_firmware_header *header;
@@ -103,8 +104,13 @@ int smu_v13_0_init_microcode(struct smu_context *smu)
 		return 0;
 
 	amdgpu_ucode_ip_version_decode(adev, MP1_HWIP, ucode_prefix, sizeof(ucode_prefix));
-	err = amdgpu_ucode_request(adev, &adev->pm.fw, AMDGPU_UCODE_REQUIRED,
-				   "amdgpu/%s.bin", ucode_prefix);
+
+	if (amdgpu_is_kicker_fw(adev))
+		err = amdgpu_ucode_request(adev, &adev->pm.fw, AMDGPU_UCODE_REQUIRED,
+					   "amdgpu/%s_kicker.bin", ucode_prefix);
+	else
+		err = amdgpu_ucode_request(adev, &adev->pm.fw, AMDGPU_UCODE_REQUIRED,
+					   "amdgpu/%s.bin", ucode_prefix);
 	if (err)
 		goto out;
 

From 09b585592fa481384597c81388733aed4a04dd05 Mon Sep 17 00:00:00 2001
From: Jesse Zhang <jesse.zhang@amd.com>
Date: Wed, 11 Jun 2025 15:02:09 +0800
Subject: [PATCH 0558/1334] drm/amdgpu: Fix SDMA engine reset with logical
 instance ID

This commit makes the following improvements to SDMA engine reset handling:

1. Clarifies in the function documentation that instance_id refers to a logical ID
2. Adds conversion from logical to physical instance ID before performing reset
   using GET_INST(SDMA0, instance_id) macro
3. Improves error messaging to indicate when a logical instance reset fails
4. Adds better code organization with blank lines for readability

The change ensures proper SDMA engine reset by using the correct physical
instance ID while maintaining the logical ID interface for callers.

V2: Remove harvest_config check and convert directly to physical instance (Lijo)

Suggested-by: Jonathan Kim <jonathan.kim@amd.com>
Signed-off-by: Jesse Zhang <Jesse.Zhang@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 5efa6217c239ed1ceec0f0414f9b6f6927387dfc)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c
index 6716ac281c49..9b54a1ece447 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c
@@ -540,8 +540,10 @@ static int amdgpu_sdma_soft_reset(struct amdgpu_device *adev, u32 instance_id)
 	case IP_VERSION(4, 4, 2):
 	case IP_VERSION(4, 4, 4):
 	case IP_VERSION(4, 4, 5):
-		/* For SDMA 4.x, use the existing DPM interface for backward compatibility */
-		r = amdgpu_dpm_reset_sdma(adev, 1 << instance_id);
+		/* For SDMA 4.x, use the existing DPM interface for backward compatibility,
+		 * we need to convert the logical instance ID to physical instance ID before reset.
+		 */
+		r = amdgpu_dpm_reset_sdma(adev, 1 << GET_INST(SDMA0, instance_id));
 		break;
 	case IP_VERSION(5, 0, 0):
 	case IP_VERSION(5, 0, 1):
@@ -568,7 +570,7 @@ static int amdgpu_sdma_soft_reset(struct amdgpu_device *adev, u32 instance_id)
 /**
  * amdgpu_sdma_reset_engine - Reset a specific SDMA engine
  * @adev: Pointer to the AMDGPU device
- * @instance_id: ID of the SDMA engine instance to reset
+ * @instance_id: Logical ID of the SDMA engine instance to reset
  *
  * Returns: 0 on success, or a negative error code on failure.
  */
@@ -601,7 +603,7 @@ int amdgpu_sdma_reset_engine(struct amdgpu_device *adev, uint32_t instance_id)
 	/* Perform the SDMA reset for the specified instance */
 	ret = amdgpu_sdma_soft_reset(adev, instance_id);
 	if (ret) {
-		dev_err(adev->dev, "Failed to reset SDMA instance %u\n", instance_id);
+		dev_err(adev->dev, "Failed to reset SDMA logical instance %u\n", instance_id);
 		goto exit;
 	}
 

From caade9d69f2e2b76d2e2d47089736a99135b8772 Mon Sep 17 00:00:00 2001
From: Jesse Zhang <jesse.zhang@amd.com>
Date: Wed, 11 Jun 2025 15:07:11 +0800
Subject: [PATCH 0559/1334] drm/amdgpu: Use logical instance ID for SDMA v4_4_2
 queue operations

Simplify SDMA v4_4_2 queue reset and stop operations by:
1. Removing GET_INST(SDMA0) conversion for ring->me
2. Using the logical instance ID (ring->me) directly
3. Maintaining consistent behavior with other SDMA queue operations

This change aligns with the existing queue handling logic where
ring->me already represents the correct instance identifier.

Signed-off-by:  Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Jesse Zhang <Jesse.Zhang@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 3bab282dfe25dff7a55add432f56898505a6cc6c)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c
index 9c169112a5e7..3de125062ee3 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c
@@ -1670,7 +1670,7 @@ static bool sdma_v4_4_2_page_ring_is_guilty(struct amdgpu_ring *ring)
 static int sdma_v4_4_2_reset_queue(struct amdgpu_ring *ring, unsigned int vmid)
 {
 	struct amdgpu_device *adev = ring->adev;
-	u32 id = GET_INST(SDMA0, ring->me);
+	u32 id = ring->me;
 	int r;
 
 	if (!(adev->sdma.supported_reset & AMDGPU_RESET_TYPE_PER_QUEUE))
@@ -1686,7 +1686,7 @@ static int sdma_v4_4_2_reset_queue(struct amdgpu_ring *ring, unsigned int vmid)
 static int sdma_v4_4_2_stop_queue(struct amdgpu_ring *ring)
 {
 	struct amdgpu_device *adev = ring->adev;
-	u32 instance_id = GET_INST(SDMA0, ring->me);
+	u32 instance_id = ring->me;
 	u32 inst_mask;
 	uint64_t rptr;
 

From 46e15197b513e60786a44107759d6ca293d6288c Mon Sep 17 00:00:00 2001
From: Sonny Jiang <sonny.jiang@amd.com>
Date: Thu, 12 Jun 2025 11:01:08 -0400
Subject: [PATCH 0560/1334] drm/amdgpu: VCN v5_0_1 to prevent FW checking RB
 during DPG pause

Add a protection to ensure programming are all complete prior VCPU
starting. This is a WA for an unintended VCPU running.

Signed-off-by: Sonny Jiang <sonny.jiang@amd.com>
Acked-by: Leo Liu <leo.liu@amd.com>
Reviewed-by: Ruijing Dong <ruijing.dong@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit c29521b529fa5e225feaf709d863a636ca0cbbfa)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c
index 338cf43c45fe..cdefd7fcb0da 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c
@@ -669,6 +669,9 @@ static int vcn_v5_0_1_start_dpg_mode(struct amdgpu_vcn_inst *vinst,
 	if (indirect)
 		amdgpu_vcn_psp_update_sram(adev, inst_idx, AMDGPU_UCODE_ID_VCN0_RAM);
 
+	/* resetting ring, fw should not check RB ring */
+	fw_shared->sq.queue_mode |= FW_QUEUE_RING_RESET;
+
 	/* Pause dpg */
 	vcn_v5_0_1_pause_dpg_mode(vinst, &state);
 
@@ -681,7 +684,7 @@ static int vcn_v5_0_1_start_dpg_mode(struct amdgpu_vcn_inst *vinst,
 	tmp = RREG32_SOC15(VCN, vcn_inst, regVCN_RB_ENABLE);
 	tmp &= ~(VCN_RB_ENABLE__RB1_EN_MASK);
 	WREG32_SOC15(VCN, vcn_inst, regVCN_RB_ENABLE, tmp);
-	fw_shared->sq.queue_mode |= FW_QUEUE_RING_RESET;
+
 	WREG32_SOC15(VCN, vcn_inst, regUVD_RB_RPTR, 0);
 	WREG32_SOC15(VCN, vcn_inst, regUVD_RB_WPTR, 0);
 
@@ -692,6 +695,7 @@ static int vcn_v5_0_1_start_dpg_mode(struct amdgpu_vcn_inst *vinst,
 	tmp = RREG32_SOC15(VCN, vcn_inst, regVCN_RB_ENABLE);
 	tmp |= VCN_RB_ENABLE__RB1_EN_MASK;
 	WREG32_SOC15(VCN, vcn_inst, regVCN_RB_ENABLE, tmp);
+	/* resetting done, fw can check RB ring */
 	fw_shared->sq.queue_mode &= ~(FW_QUEUE_RING_RESET | FW_QUEUE_DPG_HOLD_OFF);
 
 	WREG32_SOC15(VCN, vcn_inst, regVCN_RB1_DB_CTRL,

From b669507b637eb6b1aaecf347f193efccc65d756e Mon Sep 17 00:00:00 2001
From: Alex Hung <alex.hung@amd.com>
Date: Tue, 3 Jun 2025 18:30:55 -0600
Subject: [PATCH 0561/1334] drm/amd/display: Check dce_hwseq before
 dereferencing it

[WHAT]

hws was checked for null earlier in dce110_blank_stream, indicating hws
can be null, and should be checked whenever it is used.

Cc: Mario Limonciello <mario.limonciello@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Aurabindo Pillai <aurabindo.pillai@amd.com>
Signed-off-by: Alex Hung <alex.hung@amd.com>
Signed-off-by: Aurabindo Pillai <aurabindo.pillai@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 79db43611ff61280b6de58ce1305e0b2ecf675ad)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c
index e8730cc40edb..38e17b1796e1 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c
@@ -1225,7 +1225,7 @@ void dce110_blank_stream(struct pipe_ctx *pipe_ctx)
 		return;
 
 	if (link->local_sink && link->local_sink->sink_signal == SIGNAL_TYPE_EDP) {
-		if (!link->skip_implict_edp_power_control)
+		if (!link->skip_implict_edp_power_control && hws)
 			hws->funcs.edp_backlight_control(link, false);
 		link->dc->hwss.set_abm_immediate_disable(pipe_ctx);
 	}

From 785c536c31c0bb057252fddedb30d79ae4979f4b Mon Sep 17 00:00:00 2001
From: Lijo Lazar <lijo.lazar@amd.com>
Date: Fri, 6 Jun 2025 10:29:28 +0530
Subject: [PATCH 0562/1334] drm/amdgpu: Release reset locks during failures

Make sure to release reset domain lock in case of failures.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Ce Sun <cesun102@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Fixes: 11bb33766f66 ("drm/amdgpu: refactor amdgpu_device_gpu_recover")
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 1ab11a82681eb33a66f423216cb063e7f40c6f85)
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 80 +++++++++++++++-------
 1 file changed, 55 insertions(+), 25 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index e1bab6a96cb6..500bf85b3ee8 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -6019,16 +6019,12 @@ static int amdgpu_device_health_check(struct list_head *device_list_handle)
 	return ret;
 }
 
-static int amdgpu_device_halt_activities(struct amdgpu_device *adev,
-			      struct amdgpu_job *job,
-			      struct amdgpu_reset_context *reset_context,
-			      struct list_head *device_list,
-			      struct amdgpu_hive_info *hive,
-			      bool need_emergency_restart)
+static int amdgpu_device_recovery_prepare(struct amdgpu_device *adev,
+					  struct list_head *device_list,
+					  struct amdgpu_hive_info *hive)
 {
-	struct list_head *device_list_handle =  NULL;
 	struct amdgpu_device *tmp_adev = NULL;
-	int i, r = 0;
+	int r;
 
 	/*
 	 * Build list of devices to reset.
@@ -6045,26 +6041,54 @@ static int amdgpu_device_halt_activities(struct amdgpu_device *adev,
 		}
 		if (!list_is_first(&adev->reset_list, device_list))
 			list_rotate_to_front(&adev->reset_list, device_list);
-		device_list_handle = device_list;
 	} else {
 		list_add_tail(&adev->reset_list, device_list);
-		device_list_handle = device_list;
 	}
 
 	if (!amdgpu_sriov_vf(adev) && (!adev->pcie_reset_ctx.occurs_dpc)) {
-		r = amdgpu_device_health_check(device_list_handle);
+		r = amdgpu_device_health_check(device_list);
 		if (r)
 			return r;
 	}
 
-	/* We need to lock reset domain only once both for XGMI and single device */
-	tmp_adev = list_first_entry(device_list_handle, struct amdgpu_device,
-				    reset_list);
+	return 0;
+}
+
+static void amdgpu_device_recovery_get_reset_lock(struct amdgpu_device *adev,
+						  struct list_head *device_list)
+{
+	struct amdgpu_device *tmp_adev = NULL;
+
+	if (list_empty(device_list))
+		return;
+	tmp_adev =
+		list_first_entry(device_list, struct amdgpu_device, reset_list);
 	amdgpu_device_lock_reset_domain(tmp_adev->reset_domain);
+}
+
+static void amdgpu_device_recovery_put_reset_lock(struct amdgpu_device *adev,
+						  struct list_head *device_list)
+{
+	struct amdgpu_device *tmp_adev = NULL;
+
+	if (list_empty(device_list))
+		return;
+	tmp_adev =
+		list_first_entry(device_list, struct amdgpu_device, reset_list);
+	amdgpu_device_unlock_reset_domain(tmp_adev->reset_domain);
+}
+
+static int amdgpu_device_halt_activities(
+	struct amdgpu_device *adev, struct amdgpu_job *job,
+	struct amdgpu_reset_context *reset_context,
+	struct list_head *device_list, struct amdgpu_hive_info *hive,
+	bool need_emergency_restart)
+{
+	struct amdgpu_device *tmp_adev = NULL;
+	int i, r = 0;
 
 	/* block all schedulers and reset given job's ring */
-	list_for_each_entry(tmp_adev, device_list_handle, reset_list) {
-
+	list_for_each_entry(tmp_adev, device_list, reset_list) {
 		amdgpu_device_set_mp1_state(tmp_adev);
 
 		/*
@@ -6252,11 +6276,6 @@ static void amdgpu_device_gpu_resume(struct amdgpu_device *adev,
 		amdgpu_ras_set_error_query_ready(tmp_adev, true);
 
 	}
-
-	tmp_adev = list_first_entry(device_list, struct amdgpu_device,
-					    reset_list);
-	amdgpu_device_unlock_reset_domain(tmp_adev->reset_domain);
-
 }
 
 
@@ -6324,10 +6343,16 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 	reset_context->hive = hive;
 	INIT_LIST_HEAD(&device_list);
 
+	if (amdgpu_device_recovery_prepare(adev, &device_list, hive))
+		goto end_reset;
+
+	/* We need to lock reset domain only once both for XGMI and single device */
+	amdgpu_device_recovery_get_reset_lock(adev, &device_list);
+
 	r = amdgpu_device_halt_activities(adev, job, reset_context, &device_list,
 					 hive, need_emergency_restart);
 	if (r)
-		goto end_reset;
+		goto reset_unlock;
 
 	if (need_emergency_restart)
 		goto skip_sched_resume;
@@ -6345,13 +6370,15 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 
 	r = amdgpu_device_asic_reset(adev, &device_list, reset_context);
 	if (r)
-		goto end_reset;
+		goto reset_unlock;
 skip_hw_reset:
 	r = amdgpu_device_sched_resume(&device_list, reset_context, job_signaled);
 	if (r)
-		goto end_reset;
+		goto reset_unlock;
 skip_sched_resume:
 	amdgpu_device_gpu_resume(adev, &device_list, need_emergency_restart);
+reset_unlock:
+	amdgpu_device_recovery_put_reset_lock(adev, &device_list);
 end_reset:
 	if (hive) {
 		mutex_unlock(&hive->hive_lock);
@@ -6763,6 +6790,8 @@ pci_ers_result_t amdgpu_pci_error_detected(struct pci_dev *pdev, pci_channel_sta
 		memset(&reset_context, 0, sizeof(reset_context));
 		INIT_LIST_HEAD(&device_list);
 
+		amdgpu_device_recovery_prepare(adev, &device_list, hive);
+		amdgpu_device_recovery_get_reset_lock(adev, &device_list);
 		r = amdgpu_device_halt_activities(adev, NULL, &reset_context, &device_list,
 					 hive, false);
 		if (hive) {
@@ -6880,8 +6909,8 @@ out:
 		if (hive) {
 			list_for_each_entry(tmp_adev, &device_list, reset_list)
 				amdgpu_device_unset_mp1_state(tmp_adev);
-			amdgpu_device_unlock_reset_domain(adev->reset_domain);
 		}
+		amdgpu_device_recovery_put_reset_lock(adev, &device_list);
 	}
 
 	if (hive) {
@@ -6927,6 +6956,7 @@ void amdgpu_pci_resume(struct pci_dev *pdev)
 
 	amdgpu_device_sched_resume(&device_list, NULL, NULL);
 	amdgpu_device_gpu_resume(adev, &device_list, false);
+	amdgpu_device_recovery_put_reset_lock(adev, &device_list);
 	adev->pcie_reset_ctx.occurs_dpc = false;
 
 	if (hive) {

From 7f3b16f3f229e37cc3e02e9e4e7106c523b119e9 Mon Sep 17 00:00:00 2001
From: Jesse Zhang <jesse.zhang@amd.com>
Date: Mon, 16 Jun 2025 19:21:41 +0800
Subject: [PATCH 0563/1334] drm/amdgpu: Fix SDMA UTC_L1 handling during
 start/stop sequences

This commit makes two key fixes to SDMA v4.4.2 handling:

1. disable UTC_L1 in sdma_cntl register when stopping SDMA engines
   by reading the current value before modifying UTC_L1_ENABLE bit.

2. Ensure UTC_L1_ENABLE is consistently managed by:
   - Adding the missing register write when enabling UTC_L1 during start
   - Keeping UTC_L1 enabled by default as per hardware requirements

v2: Correct SDMA_CNTL setting (Philip)

Suggested-by: Jonathan Kim <jonathan.kim@amd.com>
Signed-off-by: Jesse Zhang <Jesse.Zhang@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 375bf564654e85a7b1b0657b191645b3edca1bda)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c
index 3de125062ee3..cef68df4c663 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c
@@ -490,7 +490,7 @@ static void sdma_v4_4_2_inst_gfx_stop(struct amdgpu_device *adev,
 {
 	struct amdgpu_ring *sdma[AMDGPU_MAX_SDMA_INSTANCES];
 	u32 doorbell_offset, doorbell;
-	u32 rb_cntl, ib_cntl;
+	u32 rb_cntl, ib_cntl, sdma_cntl;
 	int i;
 
 	for_each_inst(i, inst_mask) {
@@ -502,6 +502,9 @@ static void sdma_v4_4_2_inst_gfx_stop(struct amdgpu_device *adev,
 		ib_cntl = RREG32_SDMA(i, regSDMA_GFX_IB_CNTL);
 		ib_cntl = REG_SET_FIELD(ib_cntl, SDMA_GFX_IB_CNTL, IB_ENABLE, 0);
 		WREG32_SDMA(i, regSDMA_GFX_IB_CNTL, ib_cntl);
+		sdma_cntl = RREG32_SDMA(i, regSDMA_CNTL);
+		sdma_cntl = REG_SET_FIELD(sdma_cntl, SDMA_CNTL, UTC_L1_ENABLE, 0);
+		WREG32_SDMA(i, regSDMA_CNTL, sdma_cntl);
 
 		if (sdma[i]->use_doorbell) {
 			doorbell = RREG32_SDMA(i, regSDMA_GFX_DOORBELL);
@@ -995,6 +998,7 @@ static int sdma_v4_4_2_inst_start(struct amdgpu_device *adev,
 		/* set utc l1 enable flag always to 1 */
 		temp = RREG32_SDMA(i, regSDMA_CNTL);
 		temp = REG_SET_FIELD(temp, SDMA_CNTL, UTC_L1_ENABLE, 1);
+		WREG32_SDMA(i, regSDMA_CNTL, temp);
 
 		if (amdgpu_ip_version(adev, SDMA0_HWIP, 0) < IP_VERSION(4, 4, 5)) {
 			/* enable context empty interrupt during initialization */

From ebe43542702c3d15d1a1d95e8e13b1b54076f05a Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Mon, 2 Jun 2025 11:31:52 -0400
Subject: [PATCH 0564/1334] drm/amdgpu: switch job hw_fence to amdgpu_fence
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Use the amdgpu fence container so we can store additional
data in the fence.  This also fixes the start_time handling
for MCBP since we were casting the fence to an amdgpu_fence
and it wasn't.

Fixes: 3f4c175d62d8 ("drm/amdgpu: MCBP based on DRM scheduler (v9)")
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit bf1cd14f9e2e1fdf981eed273ddd595863f5288c)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c |  2 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c  |  2 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c   | 30 +++++----------------
 drivers/gpu/drm/amd/amdgpu/amdgpu_job.c     | 12 ++++-----
 drivers/gpu/drm/amd/amdgpu/amdgpu_job.h     |  2 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h    | 16 +++++++++++
 6 files changed, 32 insertions(+), 32 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
index 8e626f50b362..f81608330a3d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
@@ -1902,7 +1902,7 @@ no_preempt:
 			continue;
 		}
 		job = to_amdgpu_job(s_job);
-		if (preempted && (&job->hw_fence) == fence)
+		if (preempted && (&job->hw_fence.base) == fence)
 			/* mark the job as preempted */
 			job->preemption_status |= AMDGPU_IB_PREEMPTED;
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 500bf85b3ee8..78f8755996f0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -6362,7 +6362,7 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 	 *
 	 * job->base holds a reference to parent fence
 	 */
-	if (job && dma_fence_is_signaled(&job->hw_fence)) {
+	if (job && dma_fence_is_signaled(&job->hw_fence.base)) {
 		job_signaled = true;
 		dev_info(adev->dev, "Guilty job already signaled, skipping HW reset");
 		goto skip_hw_reset;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
index 8cecf25996ed..5fec808d7f54 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
@@ -41,22 +41,6 @@
 #include "amdgpu_trace.h"
 #include "amdgpu_reset.h"
 
-/*
- * Fences mark an event in the GPUs pipeline and are used
- * for GPU/CPU synchronization.  When the fence is written,
- * it is expected that all buffers associated with that fence
- * are no longer in use by the associated ring on the GPU and
- * that the relevant GPU caches have been flushed.
- */
-
-struct amdgpu_fence {
-	struct dma_fence base;
-
-	/* RB, DMA, etc. */
-	struct amdgpu_ring		*ring;
-	ktime_t				start_timestamp;
-};
-
 static struct kmem_cache *amdgpu_fence_slab;
 
 int amdgpu_fence_slab_init(void)
@@ -151,12 +135,12 @@ int amdgpu_fence_emit(struct amdgpu_ring *ring, struct dma_fence **f, struct amd
 		am_fence = kmem_cache_alloc(amdgpu_fence_slab, GFP_ATOMIC);
 		if (am_fence == NULL)
 			return -ENOMEM;
-		fence = &am_fence->base;
-		am_fence->ring = ring;
 	} else {
 		/* take use of job-embedded fence */
-		fence = &job->hw_fence;
+		am_fence = &job->hw_fence;
 	}
+	fence = &am_fence->base;
+	am_fence->ring = ring;
 
 	seq = ++ring->fence_drv.sync_seq;
 	if (job && job->job_run_counter) {
@@ -718,7 +702,7 @@ void amdgpu_fence_driver_clear_job_fences(struct amdgpu_ring *ring)
 			 * it right here or we won't be able to track them in fence_drv
 			 * and they will remain unsignaled during sa_bo free.
 			 */
-			job = container_of(old, struct amdgpu_job, hw_fence);
+			job = container_of(old, struct amdgpu_job, hw_fence.base);
 			if (!job->base.s_fence && !dma_fence_is_signaled(old))
 				dma_fence_signal(old);
 			RCU_INIT_POINTER(*ptr, NULL);
@@ -780,7 +764,7 @@ static const char *amdgpu_fence_get_timeline_name(struct dma_fence *f)
 
 static const char *amdgpu_job_fence_get_timeline_name(struct dma_fence *f)
 {
-	struct amdgpu_job *job = container_of(f, struct amdgpu_job, hw_fence);
+	struct amdgpu_job *job = container_of(f, struct amdgpu_job, hw_fence.base);
 
 	return (const char *)to_amdgpu_ring(job->base.sched)->name;
 }
@@ -810,7 +794,7 @@ static bool amdgpu_fence_enable_signaling(struct dma_fence *f)
  */
 static bool amdgpu_job_fence_enable_signaling(struct dma_fence *f)
 {
-	struct amdgpu_job *job = container_of(f, struct amdgpu_job, hw_fence);
+	struct amdgpu_job *job = container_of(f, struct amdgpu_job, hw_fence.base);
 
 	if (!timer_pending(&to_amdgpu_ring(job->base.sched)->fence_drv.fallback_timer))
 		amdgpu_fence_schedule_fallback(to_amdgpu_ring(job->base.sched));
@@ -845,7 +829,7 @@ static void amdgpu_job_fence_free(struct rcu_head *rcu)
 	struct dma_fence *f = container_of(rcu, struct dma_fence, rcu);
 
 	/* free job if fence has a parent job */
-	kfree(container_of(f, struct amdgpu_job, hw_fence));
+	kfree(container_of(f, struct amdgpu_job, hw_fence.base));
 }
 
 /**
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
index acb21fc8b3ce..ddb9d3269357 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
@@ -272,8 +272,8 @@ void amdgpu_job_free_resources(struct amdgpu_job *job)
 	/* Check if any fences where initialized */
 	if (job->base.s_fence && job->base.s_fence->finished.ops)
 		f = &job->base.s_fence->finished;
-	else if (job->hw_fence.ops)
-		f = &job->hw_fence;
+	else if (job->hw_fence.base.ops)
+		f = &job->hw_fence.base;
 	else
 		f = NULL;
 
@@ -290,10 +290,10 @@ static void amdgpu_job_free_cb(struct drm_sched_job *s_job)
 	amdgpu_sync_free(&job->explicit_sync);
 
 	/* only put the hw fence if has embedded fence */
-	if (!job->hw_fence.ops)
+	if (!job->hw_fence.base.ops)
 		kfree(job);
 	else
-		dma_fence_put(&job->hw_fence);
+		dma_fence_put(&job->hw_fence.base);
 }
 
 void amdgpu_job_set_gang_leader(struct amdgpu_job *job,
@@ -322,10 +322,10 @@ void amdgpu_job_free(struct amdgpu_job *job)
 	if (job->gang_submit != &job->base.s_fence->scheduled)
 		dma_fence_put(job->gang_submit);
 
-	if (!job->hw_fence.ops)
+	if (!job->hw_fence.base.ops)
 		kfree(job);
 	else
-		dma_fence_put(&job->hw_fence);
+		dma_fence_put(&job->hw_fence.base);
 }
 
 struct dma_fence *amdgpu_job_submit(struct amdgpu_job *job)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h
index f2c049129661..931fed8892cc 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h
@@ -48,7 +48,7 @@ struct amdgpu_job {
 	struct drm_sched_job    base;
 	struct amdgpu_vm	*vm;
 	struct amdgpu_sync	explicit_sync;
-	struct dma_fence	hw_fence;
+	struct amdgpu_fence	hw_fence;
 	struct dma_fence	*gang_submit;
 	uint32_t		preamble_status;
 	uint32_t                preemption_status;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
index b95b47110769..e1f25218943a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
@@ -127,6 +127,22 @@ struct amdgpu_fence_driver {
 	struct dma_fence		**fences;
 };
 
+/*
+ * Fences mark an event in the GPUs pipeline and are used
+ * for GPU/CPU synchronization.  When the fence is written,
+ * it is expected that all buffers associated with that fence
+ * are no longer in use by the associated ring on the GPU and
+ * that the relevant GPU caches have been flushed.
+ */
+
+struct amdgpu_fence {
+	struct dma_fence base;
+
+	/* RB, DMA, etc. */
+	struct amdgpu_ring		*ring;
+	ktime_t				start_timestamp;
+};
+
 extern const struct drm_sched_backend_ops amdgpu_sched_ops;
 
 void amdgpu_fence_driver_clear_job_fences(struct amdgpu_ring *ring);

From 49cc5beeabd5b9b6a6660be8ea2e95de30ec0a07 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Mon, 16 Jun 2025 15:43:55 -0400
Subject: [PATCH 0565/1334] drm/amdgpu/sdma5: init engine reset mutex
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Missing the mutex init.

Fixes: e56d4bf57fab ("drm/amdgpu/: drm/amdgpu: Register the new sdma function pointers for sdma_v5_0")
Reviewed-by: Jesse Zhang <Jesse.Zhang@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 3f4caf092f02f0de169c6122639af481c7edc8f9)
---
 drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
index 9505ae96fbec..1813c3ed0aa6 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
@@ -1399,6 +1399,7 @@ static int sdma_v5_0_sw_init(struct amdgpu_ip_block *ip_block)
 		return r;
 
 	for (i = 0; i < adev->sdma.num_instances; i++) {
+		mutex_init(&adev->sdma.instance[i].engine_reset_mutex);
 		adev->sdma.instance[i].funcs = &sdma_v5_0_sdma_funcs;
 		ring = &adev->sdma.instance[i].ring;
 		ring->ring_obj = NULL;

From cfb05257ae168a0496c7637e1d9e3ab8a25cbffe Mon Sep 17 00:00:00 2001
From: Jay Cornwall <jay.cornwall@amd.com>
Date: Wed, 11 Jun 2025 09:52:14 -0500
Subject: [PATCH 0566/1334] drm/amdkfd: Fix race in GWS queue scheduling

q->gws is not updated atomically with qpd->mapped_gws_queue. If a
runlist is created between pqm_set_gws and update_queue it will
contain a queue which uses GWS in a process with no GWS allocated.
This will result in a scheduler hang.

Use q->properties.is_gws which is changed while holding the DQM lock.

Signed-off-by: Jay Cornwall <jay.cornwall@amd.com>
Reviewed-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit b98370220eb3110e82248e3354e16a489a492cfb)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/amdkfd/kfd_packet_manager_v9.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager_v9.c b/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager_v9.c
index 8fa6489b6f5d..505036968a77 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager_v9.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager_v9.c
@@ -240,7 +240,7 @@ static int pm_map_queues_v9(struct packet_manager *pm, uint32_t *buffer,
 
 	packet->bitfields2.engine_sel =
 		engine_sel__mes_map_queues__compute_vi;
-	packet->bitfields2.gws_control_queue = q->gws ? 1 : 0;
+	packet->bitfields2.gws_control_queue = q->properties.is_gws ? 1 : 0;
 	packet->bitfields2.extended_engine_sel =
 		extended_engine_sel__mes_map_queues__legacy_engine_sel;
 	packet->bitfields2.queue_type =

From fe79ef3530d3c681ef2d5644a9d1d1a67b21426a Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Mon, 16 Jun 2025 15:47:13 -0400
Subject: [PATCH 0567/1334] drm/amdgpu/sdma5.2: init engine reset mutex

Missing the mutex init.

Fixes: 47454f2dc0bf ("drm/amdgpu: Register the new sdma function pointers for sdma_v5_2")
Reviewed-by: Jesse Zhang <Jesse.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit ea685ff30a51a25dd9be90786933ada49a088f65)
---
 drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
index a6e612b4a892..23f97da62808 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
@@ -1318,6 +1318,7 @@ static int sdma_v5_2_sw_init(struct amdgpu_ip_block *ip_block)
 	}
 
 	for (i = 0; i < adev->sdma.num_instances; i++) {
+		mutex_init(&adev->sdma.instance[i].engine_reset_mutex);
 		adev->sdma.instance[i].funcs = &sdma_v5_2_sdma_funcs;
 		ring = &adev->sdma.instance[i].ring;
 		ring->ring_obj = NULL;

From 88efa0de3285be66969b71ec137d9dab1ee19e52 Mon Sep 17 00:00:00 2001
From: Qiuxu Zhuo <qiuxu.zhuo@intel.com>
Date: Thu, 19 Jun 2025 00:23:06 +0800
Subject: [PATCH 0568/1334] EDAC/igen6: Fix NULL pointer dereference
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

A kernel panic was reported with the following kernel log:

  EDAC igen6: Expected 2 mcs, but only 1 detected.
  BUG: unable to handle page fault for address: 000000000000d570
  ...
  Hardware name: Notebook V54x_6x_TU/V54x_6x_TU, BIOS Dasharo (coreboot+UEFI) v0.9.0 07/17/2024
  RIP: e030:ecclog_handler+0x7e/0xf0 [igen6_edac]
  ...
  igen6_probe+0x2a0/0x343 [igen6_edac]
  ...
  igen6_init+0xc5/0xff0 [igen6_edac]
  ...

This issue occurred because one memory controller was disabled by
the BIOS but the igen6_edac driver still checked all the memory
controllers, including this absent one, to identify the source of
the error. Accessing the null MMIO for the absent memory controller
resulted in the oops above.

Fix this issue by reverting the configuration structure to non-const
and updating the field 'res_cfg->num_imc' to reflect the number of
detected memory controllers.

Fixes: 20e190b1c1fd ("EDAC/igen6: Skip absent memory controllers")
Reported-by: Marek Marczykowski-Górecki <marmarek@invisiblethingslab.com>
Closes: https://lore.kernel.org/all/aFFN7RlXkaK_loQb@mail-itl/
Suggested-by: Borislav Petkov <bp@alien8.de>
Signed-off-by: Qiuxu Zhuo <qiuxu.zhuo@intel.com>
Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Tested-by: Marek Marczykowski-Górecki <marmarek@invisiblethingslab.com>
Link: https://lore.kernel.org/r/20250618162307.1523736-1-qiuxu.zhuo@intel.com
---
 drivers/edac/igen6_edac.c | 24 +++++++++++++-----------
 1 file changed, 13 insertions(+), 11 deletions(-)

diff --git a/drivers/edac/igen6_edac.c b/drivers/edac/igen6_edac.c
index 1930dc00c791..1cb5c67e78ae 100644
--- a/drivers/edac/igen6_edac.c
+++ b/drivers/edac/igen6_edac.c
@@ -125,7 +125,7 @@
 #define MEM_SLICE_HASH_MASK(v)		(GET_BITFIELD(v, 6, 19) << 6)
 #define MEM_SLICE_HASH_LSB_MASK_BIT(v)	GET_BITFIELD(v, 24, 26)
 
-static const struct res_config {
+static struct res_config {
 	bool machine_check;
 	/* The number of present memory controllers. */
 	int num_imc;
@@ -479,7 +479,7 @@ static u64 rpl_p_err_addr(u64 ecclog)
 	return ECC_ERROR_LOG_ADDR45(ecclog);
 }
 
-static const struct res_config ehl_cfg = {
+static struct res_config ehl_cfg = {
 	.num_imc		= 1,
 	.imc_base		= 0x5000,
 	.ibecc_base		= 0xdc00,
@@ -489,7 +489,7 @@ static const struct res_config ehl_cfg = {
 	.err_addr_to_imc_addr	= ehl_err_addr_to_imc_addr,
 };
 
-static const struct res_config icl_cfg = {
+static struct res_config icl_cfg = {
 	.num_imc		= 1,
 	.imc_base		= 0x5000,
 	.ibecc_base		= 0xd800,
@@ -499,7 +499,7 @@ static const struct res_config icl_cfg = {
 	.err_addr_to_imc_addr	= ehl_err_addr_to_imc_addr,
 };
 
-static const struct res_config tgl_cfg = {
+static struct res_config tgl_cfg = {
 	.machine_check		= true,
 	.num_imc		= 2,
 	.imc_base		= 0x5000,
@@ -513,7 +513,7 @@ static const struct res_config tgl_cfg = {
 	.err_addr_to_imc_addr	= tgl_err_addr_to_imc_addr,
 };
 
-static const struct res_config adl_cfg = {
+static struct res_config adl_cfg = {
 	.machine_check		= true,
 	.num_imc		= 2,
 	.imc_base		= 0xd800,
@@ -524,7 +524,7 @@ static const struct res_config adl_cfg = {
 	.err_addr_to_imc_addr	= adl_err_addr_to_imc_addr,
 };
 
-static const struct res_config adl_n_cfg = {
+static struct res_config adl_n_cfg = {
 	.machine_check		= true,
 	.num_imc		= 1,
 	.imc_base		= 0xd800,
@@ -535,7 +535,7 @@ static const struct res_config adl_n_cfg = {
 	.err_addr_to_imc_addr	= adl_err_addr_to_imc_addr,
 };
 
-static const struct res_config rpl_p_cfg = {
+static struct res_config rpl_p_cfg = {
 	.machine_check		= true,
 	.num_imc		= 2,
 	.imc_base		= 0xd800,
@@ -547,7 +547,7 @@ static const struct res_config rpl_p_cfg = {
 	.err_addr_to_imc_addr	= adl_err_addr_to_imc_addr,
 };
 
-static const struct res_config mtl_ps_cfg = {
+static struct res_config mtl_ps_cfg = {
 	.machine_check		= true,
 	.num_imc		= 2,
 	.imc_base		= 0xd800,
@@ -558,7 +558,7 @@ static const struct res_config mtl_ps_cfg = {
 	.err_addr_to_imc_addr	= adl_err_addr_to_imc_addr,
 };
 
-static const struct res_config mtl_p_cfg = {
+static struct res_config mtl_p_cfg = {
 	.machine_check		= true,
 	.num_imc		= 2,
 	.imc_base		= 0xd800,
@@ -569,7 +569,7 @@ static const struct res_config mtl_p_cfg = {
 	.err_addr_to_imc_addr	= adl_err_addr_to_imc_addr,
 };
 
-static const struct pci_device_id igen6_pci_tbl[] = {
+static struct pci_device_id igen6_pci_tbl[] = {
 	{ PCI_VDEVICE(INTEL, DID_EHL_SKU5), (kernel_ulong_t)&ehl_cfg },
 	{ PCI_VDEVICE(INTEL, DID_EHL_SKU6), (kernel_ulong_t)&ehl_cfg },
 	{ PCI_VDEVICE(INTEL, DID_EHL_SKU7), (kernel_ulong_t)&ehl_cfg },
@@ -1350,9 +1350,11 @@ static int igen6_register_mcis(struct pci_dev *pdev, u64 mchbar)
 		return -ENODEV;
 	}
 
-	if (lmc < res_cfg->num_imc)
+	if (lmc < res_cfg->num_imc) {
 		igen6_printk(KERN_WARNING, "Expected %d mcs, but only %d detected.",
 			     res_cfg->num_imc, lmc);
+		res_cfg->num_imc = lmc;
+	}
 
 	return 0;
 

From 306cb65bb0cb243389fcbd0a66907d5bdea07d1e Mon Sep 17 00:00:00 2001
From: Bharath SM <bharathsm@microsoft.com>
Date: Mon, 17 Mar 2025 15:57:27 +0530
Subject: [PATCH 0569/1334] smb: fix secondary channel creation issue with
 kerberos by populating hostname when adding channels

When mounting a share with kerberos authentication with multichannel
support, share mounts correctly, but fails to create secondary
channels. This occurs because the hostname is not populated when
adding the channels. The hostname is necessary for the userspace
cifs.upcall program to retrieve the required credentials and pass
it back to kernel, without hostname secondary channels fails
establish.

Cc: stable@vger.kernel.org
Reviewed-by: Shyam Prasad N <sprasad@microsoft.com>
Signed-off-by: Bharath SM <bharathsm@microsoft.com>
Reported-by: xfuren <xfuren@gmail.com>
Link: https://bugzilla.samba.org/show_bug.cgi?id=15824
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/sess.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/fs/smb/client/sess.c b/fs/smb/client/sess.c
index ec0db32c7d98..330bc3d25bad 100644
--- a/fs/smb/client/sess.c
+++ b/fs/smb/client/sess.c
@@ -498,8 +498,7 @@ cifs_ses_add_channel(struct cifs_ses *ses,
 	ctx->domainauto = ses->domainAuto;
 	ctx->domainname = ses->domainName;
 
-	/* no hostname for extra channels */
-	ctx->server_hostname = "";
+	ctx->server_hostname = ses->server->hostname;
 
 	ctx->username = ses->user_name;
 	ctx->password = ses->password;

From 840738eae94864993a735ab677b9795bb8f3b961 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Pali=20Roh=C3=A1r?= <pali@kernel.org>
Date: Sun, 8 Jun 2025 16:10:33 +0200
Subject: [PATCH 0570/1334] cifs: Remove duplicate fattr->cf_dtype assignment
 from wsl_to_fattr() function
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Commit 8bd25b61c5a5 ("smb: client: set correct d_type for reparse DFS/DFSR
and mount point") deduplicated assignment of fattr->cf_dtype member from
all places to end of the function cifs_reparse_point_to_fattr(). The only
one missing place which was not deduplicated is wsl_to_fattr(). Fix it.

Fixes: 8bd25b61c5a5 ("smb: client: set correct d_type for reparse DFS/DFSR and mount point")
Signed-off-by: Pali Rohár <pali@kernel.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/reparse.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/fs/smb/client/reparse.c b/fs/smb/client/reparse.c
index bb25e77c5540..511611206dab 100644
--- a/fs/smb/client/reparse.c
+++ b/fs/smb/client/reparse.c
@@ -1172,7 +1172,6 @@ out:
 	if (!have_xattr_dev && (tag == IO_REPARSE_TAG_LX_CHR || tag == IO_REPARSE_TAG_LX_BLK))
 		return false;
 
-	fattr->cf_dtype = S_DT(fattr->cf_mode);
 	return true;
 }
 

From 6fcab2791543924d438e7fa49276d0998b0a069f Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Wed, 18 Jun 2025 14:17:45 +0200
Subject: [PATCH 0571/1334] ACPICA: Refuse to evaluate a method if arguments
 are missing

As reported in [1], a platform firmware update that increased the number
of method parameters and forgot to update a least one of its callers,
caused ACPICA to crash due to use-after-free.

Since this a result of a clear AML issue that arguably cannot be fixed
up by the interpreter (it cannot produce missing data out of thin air),
address it by making ACPICA refuse to evaluate a method if the caller
attempts to pass fewer arguments than expected to it.

Closes: https://github.com/acpica/acpica/issues/1027 [1]
Reported-by: Peter Williams <peter@newton.cx>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Reviewed-by: Hans de Goede <hansg@kernel.org>
Tested-by: Hans de Goede <hansg@kernel.org> # Dell XPS 9640 with BIOS 1.12.0
Link: https://patch.msgid.link/5909446.DvuYhMxLoT@rjwysocki.net
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/acpica/dsmethod.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/acpi/acpica/dsmethod.c b/drivers/acpi/acpica/dsmethod.c
index c8f37f4e6626..fef6fb29ece4 100644
--- a/drivers/acpi/acpica/dsmethod.c
+++ b/drivers/acpi/acpica/dsmethod.c
@@ -483,6 +483,13 @@ acpi_ds_call_control_method(struct acpi_thread_state *thread,
 		return_ACPI_STATUS(AE_NULL_OBJECT);
 	}
 
+	if (this_walk_state->num_operands < obj_desc->method.param_count) {
+		ACPI_ERROR((AE_INFO, "Missing argument for method [%4.4s]",
+			    acpi_ut_get_node_name(method_node)));
+
+		return_ACPI_STATUS(AE_AML_UNINITIALIZED_ARG);
+	}
+
 	/* Init for new method, possibly wait on method mutex */
 
 	status =

From 37fb58a7273726e59f9429c89ade5116083a213d Mon Sep 17 00:00:00 2001
From: Chen Ridong <chenridong@huawei.com>
Date: Wed, 18 Jun 2025 07:32:17 +0000
Subject: [PATCH 0572/1334] cgroup,freezer: fix incomplete freezing when
 attaching tasks
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

An issue was found:

	# cd /sys/fs/cgroup/freezer/
	# mkdir test
	# echo FROZEN > test/freezer.state
	# cat test/freezer.state
	FROZEN
	# sleep 1000 &
	[1] 863
	# echo 863 > test/cgroup.procs
	# cat test/freezer.state
	FREEZING

When tasks are migrated to a frozen cgroup, the freezer fails to
immediately freeze the tasks, causing the cgroup to remain in the
"FREEZING".

The freeze_task() function is called before clearing the CGROUP_FROZEN
flag. This causes the freezing() check to incorrectly return false,
preventing __freeze_task() from being invoked for the migrated task.

To fix this issue, clear the CGROUP_FROZEN state before calling
freeze_task().

Fixes: f5d39b020809 ("freezer,sched: Rewrite core freezer logic")
Cc: stable@vger.kernel.org # v6.1+
Reported-by: Zhong Jiawei <zhongjiawei1@huawei.com>
Signed-off-by: Chen Ridong <chenridong@huawei.com>
Acked-by: Michal Koutný <mkoutny@suse.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 kernel/cgroup/legacy_freezer.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/kernel/cgroup/legacy_freezer.c b/kernel/cgroup/legacy_freezer.c
index 039d1eb2f215..507b8f19a262 100644
--- a/kernel/cgroup/legacy_freezer.c
+++ b/kernel/cgroup/legacy_freezer.c
@@ -188,13 +188,12 @@ static void freezer_attach(struct cgroup_taskset *tset)
 		if (!(freezer->state & CGROUP_FREEZING)) {
 			__thaw_task(task);
 		} else {
-			freeze_task(task);
-
 			/* clear FROZEN and propagate upwards */
 			while (freezer && (freezer->state & CGROUP_FROZEN)) {
 				freezer->state &= ~CGROUP_FROZEN;
 				freezer = parent_freezer(freezer);
 			}
+			freeze_task(task);
 		}
 	}
 

From c6d732c38f93c4aebd204a5656583142289c3a2e Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 17 Jun 2025 13:22:40 -0700
Subject: [PATCH 0573/1334] net: ethtool: remove duplicate defines for family
 info

Commit under fixes switched to uAPI generation from the YAML
spec. A number of custom defines were left behind, mostly
for commands very hard to express in YAML spec.

Among what was left behind was the name and version of
the generic netlink family. Problem is that the codegen
always outputs those values so we ended up with a duplicated,
differently named set of defines.

Provide naming info in YAML and remove the incorrect defines.

Fixes: 8d0580c6ebdd ("ethtool: regenerate uapi header from the spec")
Acked-by: Stanislav Fomichev <sdf@fomichev.me>
Link: https://patch.msgid.link/20250617202240.811179-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/netlink/specs/ethtool.yaml       | 3 +++
 include/uapi/linux/ethtool_netlink.h           | 4 ----
 include/uapi/linux/ethtool_netlink_generated.h | 4 ++--
 3 files changed, 5 insertions(+), 6 deletions(-)

diff --git a/Documentation/netlink/specs/ethtool.yaml b/Documentation/netlink/specs/ethtool.yaml
index 9f98715a6512..72a076b0e1b5 100644
--- a/Documentation/netlink/specs/ethtool.yaml
+++ b/Documentation/netlink/specs/ethtool.yaml
@@ -7,6 +7,9 @@ protocol: genetlink-legacy
 doc: Partial family for Ethtool Netlink.
 uapi-header: linux/ethtool_netlink_generated.h
 
+c-family-name: ethtool-genl-name
+c-version-name: ethtool-genl-version
+
 definitions:
   -
     name: udp-tunnel-type
diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h
index 9ff72cfb2e98..09a75bdb6560 100644
--- a/include/uapi/linux/ethtool_netlink.h
+++ b/include/uapi/linux/ethtool_netlink.h
@@ -208,10 +208,6 @@ enum {
 	ETHTOOL_A_STATS_PHY_MAX = (__ETHTOOL_A_STATS_PHY_CNT - 1)
 };
 
-/* generic netlink info */
-#define ETHTOOL_GENL_NAME "ethtool"
-#define ETHTOOL_GENL_VERSION 1
-
 #define ETHTOOL_MCGRP_MONITOR_NAME "monitor"
 
 #endif /* _UAPI_LINUX_ETHTOOL_NETLINK_H_ */
diff --git a/include/uapi/linux/ethtool_netlink_generated.h b/include/uapi/linux/ethtool_netlink_generated.h
index 9a02f579de22..aa8ab5227c1e 100644
--- a/include/uapi/linux/ethtool_netlink_generated.h
+++ b/include/uapi/linux/ethtool_netlink_generated.h
@@ -6,8 +6,8 @@
 #ifndef _UAPI_LINUX_ETHTOOL_NETLINK_GENERATED_H
 #define _UAPI_LINUX_ETHTOOL_NETLINK_GENERATED_H
 
-#define ETHTOOL_FAMILY_NAME	"ethtool"
-#define ETHTOOL_FAMILY_VERSION	1
+#define ETHTOOL_GENL_NAME	"ethtool"
+#define ETHTOOL_GENL_VERSION	1
 
 enum {
 	ETHTOOL_UDP_TUNNEL_TYPE_VXLAN,

From ae409629e022fbebbc6d31a1bfeccdbbeee20fd6 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Tue, 17 Jun 2025 20:20:17 +0200
Subject: [PATCH 0574/1334] net: ftgmac100: select FIXED_PHY

Depending on e.g. DT configuration this driver uses a fixed link.
So we shouldn't rely on the user to enable FIXED_PHY, select it in
Kconfig instead. We may end up with a non-functional driver otherwise.

Fixes: 38561ded50d0 ("net: ftgmac100: support fixed link")
Cc: stable@vger.kernel.org
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Link: https://patch.msgid.link/476bb33b-5584-40f0-826a-7294980f2895@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/faraday/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/faraday/Kconfig b/drivers/net/ethernet/faraday/Kconfig
index c699bd6bcbb9..474073c7f94d 100644
--- a/drivers/net/ethernet/faraday/Kconfig
+++ b/drivers/net/ethernet/faraday/Kconfig
@@ -31,6 +31,7 @@ config FTGMAC100
 	depends on ARM || COMPILE_TEST
 	depends on !64BIT || BROKEN
 	select PHYLIB
+	select FIXED_PHY
 	select MDIO_ASPEED if MACH_ASPEED_G6
 	select CRC32
 	help

From 9ac8d0c640a161486eaf71d1999ee990fad62947 Mon Sep 17 00:00:00 2001
From: Hariprasad Kelam <hkelam@marvell.com>
Date: Tue, 17 Jun 2025 12:04:02 +0530
Subject: [PATCH 0575/1334] Octeontx2-pf: Fix Backpresure configuration

NIX block can receive packets from multiple links such as
MAC (RPM), LBK and CPT.

       -----------------
 RPM --|     NIX       |
       -----------------
             |
             |
            LBK

Each link supports multiple channels for example RPM link supports
16 channels. In case of link oversubsribe, NIX will assert backpressure
on receive channels.

The previous patch considered a single channel per link, resulting in
backpressure not being enabled on the remaining channels

Fixes: a7ef63dbd588 ("octeontx2-af: Disable backpressure between CPT and NIX")
Signed-off-by: Hariprasad Kelam <hkelam@marvell.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250617063403.3582210-1-hkelam@marvell.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
index 6f572589f1e5..6b5c9536d26d 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
@@ -1822,7 +1822,7 @@ int otx2_nix_config_bp(struct otx2_nic *pfvf, bool enable)
 		req->chan_cnt = IEEE_8021QAZ_MAX_TCS;
 		req->bpid_per_chan = 1;
 	} else {
-		req->chan_cnt = 1;
+		req->chan_cnt = pfvf->hw.rx_chan_cnt;
 		req->bpid_per_chan = 0;
 	}
 
@@ -1847,7 +1847,7 @@ int otx2_nix_cpt_config_bp(struct otx2_nic *pfvf, bool enable)
 		req->chan_cnt = IEEE_8021QAZ_MAX_TCS;
 		req->bpid_per_chan = 1;
 	} else {
-		req->chan_cnt = 1;
+		req->chan_cnt = pfvf->hw.rx_chan_cnt;
 		req->bpid_per_chan = 0;
 	}
 

From f82727adcf2992822e12198792af450a76ebd5ef Mon Sep 17 00:00:00 2001
From: Haixia Qu <hxqu@hillstonenet.com>
Date: Tue, 17 Jun 2025 05:56:24 +0000
Subject: [PATCH 0576/1334] tipc: fix null-ptr-deref when acquiring remote ip
 of ethernet bearer

The reproduction steps:
1. create a tun interface
2. enable l2 bearer
3. TIPC_NL_UDP_GET_REMOTEIP with media name set to tun

tipc: Started in network mode
tipc: Node identity 8af312d38a21, cluster identity 4711
tipc: Enabled bearer <eth:syz_tun>, priority 1
Oops: general protection fault
KASAN: null-ptr-deref in range
CPU: 1 UID: 1000 PID: 559 Comm: poc Not tainted 6.16.0-rc1+ #117 PREEMPT
Hardware name: QEMU Ubuntu 24.04 PC
RIP: 0010:tipc_udp_nl_dump_remoteip+0x4a4/0x8f0

the ub was in fact a struct dev.

when bid != 0 && skip_cnt != 0, bearer_list[bid] may be NULL or
other media when other thread changes it.

fix this by checking media_id.

Fixes: 832629ca5c313 ("tipc: add UDP remoteip dump to netlink API")
Signed-off-by: Haixia Qu <hxqu@hillstonenet.com>
Reviewed-by: Tung Nguyen <tung.quang.nguyen@est.tech>
Link: https://patch.msgid.link/20250617055624.2680-1-hxqu@hillstonenet.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/tipc/udp_media.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c
index 108a4cc2e001..258d6aa4f21a 100644
--- a/net/tipc/udp_media.c
+++ b/net/tipc/udp_media.c
@@ -489,7 +489,7 @@ int tipc_udp_nl_dump_remoteip(struct sk_buff *skb, struct netlink_callback *cb)
 
 		rtnl_lock();
 		b = tipc_bearer_find(net, bname);
-		if (!b) {
+		if (!b || b->bcast_addr.media_id != TIPC_MEDIA_TYPE_UDP) {
 			rtnl_unlock();
 			return -EINVAL;
 		}
@@ -500,7 +500,7 @@ int tipc_udp_nl_dump_remoteip(struct sk_buff *skb, struct netlink_callback *cb)
 
 		rtnl_lock();
 		b = rtnl_dereference(tn->bearer_list[bid]);
-		if (!b) {
+		if (!b || b->bcast_addr.media_id != TIPC_MEDIA_TYPE_UDP) {
 			rtnl_unlock();
 			return -EINVAL;
 		}

From ba8dac350faf16afc129ce6303ca4feaf083ccb1 Mon Sep 17 00:00:00 2001
From: Chao Yu <chao@kernel.org>
Date: Thu, 5 Jun 2025 11:26:33 +0800
Subject: [PATCH 0577/1334] f2fs: fix to zero post-eof page
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

fstest reports a f2fs bug:

generic/363 42s ... [failed, exit status 1]- output mismatch (see /share/git/fstests/results//generic/363.out.bad)
    --- tests/generic/363.out   2025-01-12 21:57:40.271440542 +0800
    +++ /share/git/fstests/results//generic/363.out.bad 2025-05-19 19:55:58.000000000 +0800
    @@ -1,2 +1,78 @@
     QA output created by 363
     fsx -q -S 0 -e 1 -N 100000
    +READ BAD DATA: offset = 0xd6fb, size = 0xf044, fname = /mnt/f2fs/junk
    +OFFSET      GOOD    BAD     RANGE
    +0x1540d     0x0000  0x2a25  0x0
    +operation# (mod 256) for the bad data may be 37
    +0x1540e     0x0000  0x2527  0x1
    ...
    (Run 'diff -u /share/git/fstests/tests/generic/363.out /share/git/fstests/results//generic/363.out.bad'  to see the entire diff)
Ran: generic/363
Failures: generic/363
Failed 1 of 1 tests

The root cause is user can update post-eof page via mmap [1], however, f2fs
missed to zero post-eof page in below operations, so, once it expands i_size,
then it will include dummy data locates previous post-eof page, so during
below operations, we need to zero post-eof page.

Operations which can include dummy data after previous i_size after expanding
i_size:
- write
- mapwrite [1]
- truncate
- fallocate
 * preallocate
 * zero_range
 * insert_range
 * collapse_range
- clone_range (doesn’t support in f2fs)
- copy_range (doesn’t support in f2fs)

[1] https://man7.org/linux/man-pages/man2/mmap.2.html 'BUG section'

Cc: stable@kernel.org
Signed-off-by: Chao Yu <chao@kernel.org>
Reviewed-by: Zhiguo Niu <zhiguo.niu@unisoc.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/file.c | 38 ++++++++++++++++++++++++++++++++++++++
 1 file changed, 38 insertions(+)

diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index 6bd3de64f2a8..696131e655ed 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -35,6 +35,17 @@
 #include <trace/events/f2fs.h>
 #include <uapi/linux/f2fs.h>
 
+static void f2fs_zero_post_eof_page(struct inode *inode, loff_t new_size)
+{
+	loff_t old_size = i_size_read(inode);
+
+	if (old_size >= new_size)
+		return;
+
+	/* zero or drop pages only in range of [old_size, new_size] */
+	truncate_pagecache(inode, old_size);
+}
+
 static vm_fault_t f2fs_filemap_fault(struct vm_fault *vmf)
 {
 	struct inode *inode = file_inode(vmf->vma->vm_file);
@@ -103,8 +114,13 @@ static vm_fault_t f2fs_vm_page_mkwrite(struct vm_fault *vmf)
 
 	f2fs_bug_on(sbi, f2fs_has_inline_data(inode));
 
+	filemap_invalidate_lock(inode->i_mapping);
+	f2fs_zero_post_eof_page(inode, (folio->index + 1) << PAGE_SHIFT);
+	filemap_invalidate_unlock(inode->i_mapping);
+
 	file_update_time(vmf->vma->vm_file);
 	filemap_invalidate_lock_shared(inode->i_mapping);
+
 	folio_lock(folio);
 	if (unlikely(folio->mapping != inode->i_mapping ||
 			folio_pos(folio) > i_size_read(inode) ||
@@ -1109,6 +1125,8 @@ int f2fs_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
 		f2fs_down_write(&fi->i_gc_rwsem[WRITE]);
 		filemap_invalidate_lock(inode->i_mapping);
 
+		if (attr->ia_size > old_size)
+			f2fs_zero_post_eof_page(inode, attr->ia_size);
 		truncate_setsize(inode, attr->ia_size);
 
 		if (attr->ia_size <= old_size)
@@ -1227,6 +1245,10 @@ static int f2fs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
 	if (ret)
 		return ret;
 
+	filemap_invalidate_lock(inode->i_mapping);
+	f2fs_zero_post_eof_page(inode, offset + len);
+	filemap_invalidate_unlock(inode->i_mapping);
+
 	pg_start = ((unsigned long long) offset) >> PAGE_SHIFT;
 	pg_end = ((unsigned long long) offset + len) >> PAGE_SHIFT;
 
@@ -1510,6 +1532,8 @@ static int f2fs_do_collapse(struct inode *inode, loff_t offset, loff_t len)
 	f2fs_down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
 	filemap_invalidate_lock(inode->i_mapping);
 
+	f2fs_zero_post_eof_page(inode, offset + len);
+
 	f2fs_lock_op(sbi);
 	f2fs_drop_extent_tree(inode);
 	truncate_pagecache(inode, offset);
@@ -1631,6 +1655,10 @@ static int f2fs_zero_range(struct inode *inode, loff_t offset, loff_t len,
 	if (ret)
 		return ret;
 
+	filemap_invalidate_lock(mapping);
+	f2fs_zero_post_eof_page(inode, offset + len);
+	filemap_invalidate_unlock(mapping);
+
 	pg_start = ((unsigned long long) offset) >> PAGE_SHIFT;
 	pg_end = ((unsigned long long) offset + len) >> PAGE_SHIFT;
 
@@ -1762,6 +1790,8 @@ static int f2fs_insert_range(struct inode *inode, loff_t offset, loff_t len)
 	/* avoid gc operation during block exchange */
 	f2fs_down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
 	filemap_invalidate_lock(mapping);
+
+	f2fs_zero_post_eof_page(inode, offset + len);
 	truncate_pagecache(inode, offset);
 
 	while (!ret && idx > pg_start) {
@@ -1819,6 +1849,10 @@ static int f2fs_expand_inode_data(struct inode *inode, loff_t offset,
 	if (err)
 		return err;
 
+	filemap_invalidate_lock(inode->i_mapping);
+	f2fs_zero_post_eof_page(inode, offset + len);
+	filemap_invalidate_unlock(inode->i_mapping);
+
 	f2fs_balance_fs(sbi, true);
 
 	pg_start = ((unsigned long long)offset) >> PAGE_SHIFT;
@@ -4860,6 +4894,10 @@ static ssize_t f2fs_write_checks(struct kiocb *iocb, struct iov_iter *from)
 	err = file_modified(file);
 	if (err)
 		return err;
+
+	filemap_invalidate_lock(inode->i_mapping);
+	f2fs_zero_post_eof_page(inode, iocb->ki_pos + iov_iter_count(from));
+	filemap_invalidate_unlock(inode->i_mapping);
 	return count;
 }
 

From 3168276591210d147ed9e6dc267f8a04007593c7 Mon Sep 17 00:00:00 2001
From: David Wei <dw@davidwei.uk>
Date: Tue, 17 Jun 2025 14:20:59 -0700
Subject: [PATCH 0578/1334] selftests: netdevsim: improve lib.sh include in
 peer.sh

Fix the peer.sh test to run from INSTALL_PATH.

Signed-off-by: David Wei <dw@davidwei.uk>
Link: https://patch.msgid.link/20250617212102.175711-2-dw@davidwei.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/drivers/net/netdevsim/peer.sh | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/drivers/net/netdevsim/peer.sh b/tools/testing/selftests/drivers/net/netdevsim/peer.sh
index 1bb46ec435d4..7f32b5600925 100755
--- a/tools/testing/selftests/drivers/net/netdevsim/peer.sh
+++ b/tools/testing/selftests/drivers/net/netdevsim/peer.sh
@@ -1,7 +1,8 @@
 #!/bin/bash
 # SPDX-License-Identifier: GPL-2.0-only
 
-source ../../../net/lib.sh
+lib_dir=$(dirname $0)/../../../net
+source $lib_dir/lib.sh
 
 NSIM_DEV_1_ID=$((256 + RANDOM % 256))
 NSIM_DEV_1_SYS=/sys/bus/netdevsim/devices/netdevsim$NSIM_DEV_1_ID

From c65b5bb2329e36340eba76f05752f8f1eb15bee0 Mon Sep 17 00:00:00 2001
From: David Wei <dw@davidwei.uk>
Date: Tue, 17 Jun 2025 14:21:00 -0700
Subject: [PATCH 0579/1334] selftests: net: add passive TFO test binary

Add a simple passive TFO server and client test binary. This will be
used to test the SO_INCOMING_NAPI_ID of passive TFO accepted sockets.

Signed-off-by: David Wei <dw@davidwei.uk>
Link: https://patch.msgid.link/20250617212102.175711-3-dw@davidwei.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/.gitignore |   1 +
 tools/testing/selftests/net/Makefile   |   1 +
 tools/testing/selftests/net/tfo.c      | 171 +++++++++++++++++++++++++
 3 files changed, 173 insertions(+)
 create mode 100644 tools/testing/selftests/net/tfo.c

diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore
index 532bb732bc6d..c6dd2a335cf4 100644
--- a/tools/testing/selftests/net/.gitignore
+++ b/tools/testing/selftests/net/.gitignore
@@ -50,6 +50,7 @@ tap
 tcp_fastopen_backup_key
 tcp_inq
 tcp_mmap
+tfo
 timestamping
 tls
 toeplitz
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index ab996bd22a5f..ab8da438fd78 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -110,6 +110,7 @@ TEST_GEN_PROGS += proc_net_pktgen
 TEST_PROGS += lwt_dst_cache_ref_loop.sh
 TEST_PROGS += skf_net_off.sh
 TEST_GEN_FILES += skf_net_off
+TEST_GEN_FILES += tfo
 
 # YNL files, must be before "include ..lib.mk"
 YNL_GEN_FILES := busy_poller netlink-dumps
diff --git a/tools/testing/selftests/net/tfo.c b/tools/testing/selftests/net/tfo.c
new file mode 100644
index 000000000000..eb3cac5e583c
--- /dev/null
+++ b/tools/testing/selftests/net/tfo.c
@@ -0,0 +1,171 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <error.h>
+#include <fcntl.h>
+#include <limits.h>
+#include <stdbool.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <arpa/inet.h>
+#include <sys/socket.h>
+#include <netinet/tcp.h>
+#include <errno.h>
+
+static int cfg_server;
+static int cfg_client;
+static int cfg_port = 8000;
+static struct sockaddr_in6 cfg_addr;
+static char *cfg_outfile;
+
+static int parse_address(const char *str, int port, struct sockaddr_in6 *sin6)
+{
+	int ret;
+
+	sin6->sin6_family = AF_INET6;
+	sin6->sin6_port = htons(port);
+
+	ret = inet_pton(sin6->sin6_family, str, &sin6->sin6_addr);
+	if (ret != 1) {
+		/* fallback to plain IPv4 */
+		ret = inet_pton(AF_INET, str, &sin6->sin6_addr.s6_addr32[3]);
+		if (ret != 1)
+			return -1;
+
+		/* add ::ffff prefix */
+		sin6->sin6_addr.s6_addr32[0] = 0;
+		sin6->sin6_addr.s6_addr32[1] = 0;
+		sin6->sin6_addr.s6_addr16[4] = 0;
+		sin6->sin6_addr.s6_addr16[5] = 0xffff;
+	}
+
+	return 0;
+}
+
+static void run_server(void)
+{
+	unsigned long qlen = 32;
+	int fd, opt, connfd;
+	socklen_t len;
+	char buf[64];
+	FILE *outfile;
+
+	outfile = fopen(cfg_outfile, "w");
+	if (!outfile)
+		error(1, errno, "fopen() outfile");
+
+	fd = socket(AF_INET6, SOCK_STREAM, 0);
+	if (fd == -1)
+		error(1, errno, "socket()");
+
+	opt = 1;
+	if (setsockopt(fd, SOL_SOCKET, SO_REUSEADDR, &opt, sizeof(opt)) < 0)
+		error(1, errno, "setsockopt(SO_REUSEADDR)");
+
+	if (setsockopt(fd, SOL_TCP, TCP_FASTOPEN, &qlen, sizeof(qlen)) < 0)
+		error(1, errno, "setsockopt(TCP_FASTOPEN)");
+
+	if (bind(fd, (struct sockaddr *)&cfg_addr, sizeof(cfg_addr)) < 0)
+		error(1, errno, "bind()");
+
+	if (listen(fd, 5) < 0)
+		error(1, errno, "listen()");
+
+	len = sizeof(cfg_addr);
+	connfd = accept(fd, (struct sockaddr *)&cfg_addr, &len);
+	if (connfd < 0)
+		error(1, errno, "accept()");
+
+	len = sizeof(opt);
+	if (getsockopt(connfd, SOL_SOCKET, SO_INCOMING_NAPI_ID, &opt, &len) < 0)
+		error(1, errno, "getsockopt(SO_INCOMING_NAPI_ID)");
+
+	read(connfd, buf, 64);
+	fprintf(outfile, "%d\n", opt);
+
+	fclose(outfile);
+	close(connfd);
+	close(fd);
+}
+
+static void run_client(void)
+{
+	int fd;
+	char *msg = "Hello, world!";
+
+	fd = socket(AF_INET6, SOCK_STREAM, 0);
+	if (fd == -1)
+		error(1, errno, "socket()");
+
+	sendto(fd, msg, strlen(msg), MSG_FASTOPEN, (struct sockaddr *)&cfg_addr, sizeof(cfg_addr));
+
+	close(fd);
+}
+
+static void usage(const char *filepath)
+{
+	error(1, 0, "Usage: %s (-s|-c) -h<server_ip> -p<port> -o<outfile> ", filepath);
+}
+
+static void parse_opts(int argc, char **argv)
+{
+	struct sockaddr_in6 *addr6 = (void *) &cfg_addr;
+	char *addr = NULL;
+	int ret;
+	int c;
+
+	if (argc <= 1)
+		usage(argv[0]);
+
+	while ((c = getopt(argc, argv, "sch:p:o:")) != -1) {
+		switch (c) {
+		case 's':
+			if (cfg_client)
+				error(1, 0, "Pass one of -s or -c");
+			cfg_server = 1;
+			break;
+		case 'c':
+			if (cfg_server)
+				error(1, 0, "Pass one of -s or -c");
+			cfg_client = 1;
+			break;
+		case 'h':
+			addr = optarg;
+			break;
+		case 'p':
+			cfg_port = strtoul(optarg, NULL, 0);
+			break;
+		case 'o':
+			cfg_outfile = strdup(optarg);
+			if (!cfg_outfile)
+				error(1, 0, "outfile invalid");
+			break;
+		}
+	}
+
+	if (cfg_server && addr)
+		error(1, 0, "Server cannot have -h specified");
+
+	memset(addr6, 0, sizeof(*addr6));
+	addr6->sin6_family = AF_INET6;
+	addr6->sin6_port = htons(cfg_port);
+	addr6->sin6_addr = in6addr_any;
+	if (addr) {
+		ret = parse_address(addr, cfg_port, addr6);
+		if (ret)
+			error(1, 0, "Client address parse error: %s", addr);
+	}
+}
+
+int main(int argc, char **argv)
+{
+	parse_opts(argc, argv);
+
+	if (cfg_server)
+		run_server();
+	else if (cfg_client)
+		run_client();
+
+	return 0;
+}

From 137e7b5cceda2fd634ff47fde6c4226092d09442 Mon Sep 17 00:00:00 2001
From: David Wei <dw@davidwei.uk>
Date: Tue, 17 Jun 2025 14:21:01 -0700
Subject: [PATCH 0580/1334] selftests: net: add test for passive TFO socket
 NAPI ID

Add a test that checks that the NAPI ID of a passive TFO socket is valid
i.e. not zero.

Signed-off-by: David Wei <dw@davidwei.uk>
Link: https://patch.msgid.link/20250617212102.175711-4-dw@davidwei.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/Makefile       |   1 +
 tools/testing/selftests/net/tfo_passive.sh | 112 +++++++++++++++++++++
 2 files changed, 113 insertions(+)
 create mode 100755 tools/testing/selftests/net/tfo_passive.sh

diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index ab8da438fd78..332f387615d7 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -111,6 +111,7 @@ TEST_PROGS += lwt_dst_cache_ref_loop.sh
 TEST_PROGS += skf_net_off.sh
 TEST_GEN_FILES += skf_net_off
 TEST_GEN_FILES += tfo
+TEST_PROGS += tfo_passive.sh
 
 # YNL files, must be before "include ..lib.mk"
 YNL_GEN_FILES := busy_poller netlink-dumps
diff --git a/tools/testing/selftests/net/tfo_passive.sh b/tools/testing/selftests/net/tfo_passive.sh
new file mode 100755
index 000000000000..80bf11fdc046
--- /dev/null
+++ b/tools/testing/selftests/net/tfo_passive.sh
@@ -0,0 +1,112 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+source lib.sh
+
+NSIM_SV_ID=$((256 + RANDOM % 256))
+NSIM_SV_SYS=/sys/bus/netdevsim/devices/netdevsim$NSIM_SV_ID
+NSIM_CL_ID=$((512 + RANDOM % 256))
+NSIM_CL_SYS=/sys/bus/netdevsim/devices/netdevsim$NSIM_CL_ID
+
+NSIM_DEV_SYS_NEW=/sys/bus/netdevsim/new_device
+NSIM_DEV_SYS_DEL=/sys/bus/netdevsim/del_device
+NSIM_DEV_SYS_LINK=/sys/bus/netdevsim/link_device
+NSIM_DEV_SYS_UNLINK=/sys/bus/netdevsim/unlink_device
+
+SERVER_IP=192.168.1.1
+CLIENT_IP=192.168.1.2
+SERVER_PORT=48675
+
+setup_ns()
+{
+	set -e
+	ip netns add nssv
+	ip netns add nscl
+
+	NSIM_SV_NAME=$(find $NSIM_SV_SYS/net -maxdepth 1 -type d ! \
+		-path $NSIM_SV_SYS/net -exec basename {} \;)
+	NSIM_CL_NAME=$(find $NSIM_CL_SYS/net -maxdepth 1 -type d ! \
+		-path $NSIM_CL_SYS/net -exec basename {} \;)
+
+	ip link set $NSIM_SV_NAME netns nssv
+	ip link set $NSIM_CL_NAME netns nscl
+
+	ip netns exec nssv ip addr add "${SERVER_IP}/24" dev $NSIM_SV_NAME
+	ip netns exec nscl ip addr add "${CLIENT_IP}/24" dev $NSIM_CL_NAME
+
+	ip netns exec nssv ip link set dev $NSIM_SV_NAME up
+	ip netns exec nscl ip link set dev $NSIM_CL_NAME up
+
+	# Enable passive TFO
+	ip netns exec nssv sysctl -w net.ipv4.tcp_fastopen=519 > /dev/null
+
+	set +e
+}
+
+cleanup_ns()
+{
+	ip netns del nscl
+	ip netns del nssv
+}
+
+###
+### Code start
+###
+
+modprobe netdevsim
+
+# linking
+
+echo $NSIM_SV_ID > $NSIM_DEV_SYS_NEW
+echo $NSIM_CL_ID > $NSIM_DEV_SYS_NEW
+udevadm settle
+
+setup_ns
+
+NSIM_SV_FD=$((256 + RANDOM % 256))
+exec {NSIM_SV_FD}</var/run/netns/nssv
+NSIM_SV_IFIDX=$(ip netns exec nssv cat /sys/class/net/$NSIM_SV_NAME/ifindex)
+
+NSIM_CL_FD=$((256 + RANDOM % 256))
+exec {NSIM_CL_FD}</var/run/netns/nscl
+NSIM_CL_IFIDX=$(ip netns exec nscl cat /sys/class/net/$NSIM_CL_NAME/ifindex)
+
+echo "$NSIM_SV_FD:$NSIM_SV_IFIDX $NSIM_CL_FD:$NSIM_CL_IFIDX" > \
+     $NSIM_DEV_SYS_LINK
+
+if [ $? -ne 0 ]; then
+	echo "linking netdevsim1 with netdevsim2 should succeed"
+	cleanup_ns
+	exit 1
+fi
+
+out_file=$(mktemp)
+
+timeout -k 1s 30s ip netns exec nssv ./tfo        \
+				-s                \
+				-p ${SERVER_PORT} \
+				-o ${out_file}&
+
+wait_local_port_listen nssv ${SERVER_PORT} tcp
+
+ip netns exec nscl ./tfo -c -h ${SERVER_IP} -p ${SERVER_PORT}
+
+wait
+
+res=$(cat $out_file)
+rm $out_file
+
+if [ $res -eq 0 ]; then
+	echo "got invalid NAPI ID from passive TFO socket"
+	cleanup_ns
+	exit 1
+fi
+
+echo "$NSIM_SV_FD:$NSIM_SV_IFIDX" > $NSIM_DEV_SYS_UNLINK
+
+echo $NSIM_CL_ID > $NSIM_DEV_SYS_DEL
+
+cleanup_ns
+
+modprobe -r netdevsim
+
+exit 0

From dbe0ca8da1f62b6252e7be6337209f4d86d4a914 Mon Sep 17 00:00:00 2001
From: David Wei <dw@davidwei.uk>
Date: Tue, 17 Jun 2025 14:21:02 -0700
Subject: [PATCH 0581/1334] tcp: fix passive TFO socket having invalid NAPI ID

There is a bug with passive TFO sockets returning an invalid NAPI ID 0
from SO_INCOMING_NAPI_ID. Normally this is not an issue, but zero copy
receive relies on a correct NAPI ID to process sockets on the right
queue.

Fix by adding a sk_mark_napi_id_set().

Fixes: e5907459ce7e ("tcp: Record Rx hash and NAPI ID in tcp_child_process")
Signed-off-by: David Wei <dw@davidwei.uk>
Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20250617212102.175711-5-dw@davidwei.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/tcp_fastopen.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
index 9b83d639b5ac..5107121c5e37 100644
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -3,6 +3,7 @@
 #include <linux/tcp.h>
 #include <linux/rcupdate.h>
 #include <net/tcp.h>
+#include <net/busy_poll.h>
 
 void tcp_fastopen_init_key_once(struct net *net)
 {
@@ -279,6 +280,8 @@ static struct sock *tcp_fastopen_create_child(struct sock *sk,
 
 	refcount_set(&req->rsk_refcnt, 2);
 
+	sk_mark_napi_id_set(child, skb);
+
 	/* Now finish processing the fastopen child socket. */
 	tcp_init_transfer(child, BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB, skb);
 

From d4adf1c9ee7722545450608bcb095fb31512f0c6 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Wed, 18 Jun 2025 17:57:40 -0400
Subject: [PATCH 0582/1334] bpf: Adjust free target to avoid global starvation
 of LRU map

BPF_MAP_TYPE_LRU_HASH can recycle most recent elements well before the
map is full, due to percpu reservations and force shrink before
neighbor stealing. Once a CPU is unable to borrow from the global map,
it will once steal one elem from a neighbor and after that each time
flush this one element to the global list and immediately recycle it.

Batch value LOCAL_FREE_TARGET (128) will exhaust a 10K element map
with 79 CPUs. CPU 79 will observe this behavior even while its
neighbors hold 78 * 127 + 1 * 15 == 9921 free elements (99%).

CPUs need not be active concurrently. The issue can appear with
affinity migration, e.g., irqbalance. Each CPU can reserve and then
hold onto its 128 elements indefinitely.

Avoid global list exhaustion by limiting aggregate percpu caches to
half of map size, by adjusting LOCAL_FREE_TARGET based on cpu count.
This change has no effect on sufficiently large tables.

Similar to LOCAL_NR_SCANS and lru->nr_scans, introduce a map variable
lru->free_target. The extra field fits in a hole in struct bpf_lru.
The cacheline is already warm where read in the hot path. The field is
only accessed with the lru lock held.

Tested-by: Anton Protopopov <a.s.protopopov@gmail.com>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Acked-by: Stanislav Fomichev <sdf@fomichev.me>
Link: https://lore.kernel.org/r/20250618215803.3587312-1-willemdebruijn.kernel@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 Documentation/bpf/map_hash.rst             |  8 ++-
 Documentation/bpf/map_lru_hash_update.dot  |  6 +-
 kernel/bpf/bpf_lru_list.c                  |  9 ++-
 kernel/bpf/bpf_lru_list.h                  |  1 +
 tools/testing/selftests/bpf/test_lru_map.c | 72 +++++++++++-----------
 5 files changed, 52 insertions(+), 44 deletions(-)

diff --git a/Documentation/bpf/map_hash.rst b/Documentation/bpf/map_hash.rst
index d2343952f2cb..8606bf958a8c 100644
--- a/Documentation/bpf/map_hash.rst
+++ b/Documentation/bpf/map_hash.rst
@@ -233,10 +233,16 @@ attempts in order to enforce the LRU property which have increasing impacts on
 other CPUs involved in the following operation attempts:
 
 - Attempt to use CPU-local state to batch operations
-- Attempt to fetch free nodes from global lists
+- Attempt to fetch ``target_free`` free nodes from global lists
 - Attempt to pull any node from a global list and remove it from the hashmap
 - Attempt to pull any node from any CPU's list and remove it from the hashmap
 
+The number of nodes to borrow from the global list in a batch, ``target_free``,
+depends on the size of the map. Larger batch size reduces lock contention, but
+may also exhaust the global structure. The value is computed at map init to
+avoid exhaustion, by limiting aggregate reservation by all CPUs to half the map
+size. With a minimum of a single element and maximum budget of 128 at a time.
+
 This algorithm is described visually in the following diagram. See the
 description in commit 3a08c2fd7634 ("bpf: LRU List") for a full explanation of
 the corresponding operations:
diff --git a/Documentation/bpf/map_lru_hash_update.dot b/Documentation/bpf/map_lru_hash_update.dot
index a0fee349d29c..ab10058f5b79 100644
--- a/Documentation/bpf/map_lru_hash_update.dot
+++ b/Documentation/bpf/map_lru_hash_update.dot
@@ -35,18 +35,18 @@ digraph {
   fn_bpf_lru_list_pop_free_to_local [shape=rectangle,fillcolor=2,
     label="Flush local pending,
     Rotate Global list, move
-    LOCAL_FREE_TARGET
+    target_free
     from global -> local"]
   // Also corresponds to:
   // fn__local_list_flush()
   // fn_bpf_lru_list_rotate()
   fn___bpf_lru_node_move_to_free[shape=diamond,fillcolor=2,
-    label="Able to free\nLOCAL_FREE_TARGET\nnodes?"]
+    label="Able to free\ntarget_free\nnodes?"]
 
   fn___bpf_lru_list_shrink_inactive [shape=rectangle,fillcolor=3,
     label="Shrink inactive list
       up to remaining
-      LOCAL_FREE_TARGET
+      target_free
       (global LRU -> local)"]
   fn___bpf_lru_list_shrink [shape=diamond,fillcolor=2,
     label="> 0 entries in\nlocal free list?"]
diff --git a/kernel/bpf/bpf_lru_list.c b/kernel/bpf/bpf_lru_list.c
index 3dabdd137d10..2d6e1c98d8ad 100644
--- a/kernel/bpf/bpf_lru_list.c
+++ b/kernel/bpf/bpf_lru_list.c
@@ -337,12 +337,12 @@ static void bpf_lru_list_pop_free_to_local(struct bpf_lru *lru,
 				 list) {
 		__bpf_lru_node_move_to_free(l, node, local_free_list(loc_l),
 					    BPF_LRU_LOCAL_LIST_T_FREE);
-		if (++nfree == LOCAL_FREE_TARGET)
+		if (++nfree == lru->target_free)
 			break;
 	}
 
-	if (nfree < LOCAL_FREE_TARGET)
-		__bpf_lru_list_shrink(lru, l, LOCAL_FREE_TARGET - nfree,
+	if (nfree < lru->target_free)
+		__bpf_lru_list_shrink(lru, l, lru->target_free - nfree,
 				      local_free_list(loc_l),
 				      BPF_LRU_LOCAL_LIST_T_FREE);
 
@@ -577,6 +577,9 @@ static void bpf_common_lru_populate(struct bpf_lru *lru, void *buf,
 		list_add(&node->list, &l->lists[BPF_LRU_LIST_T_FREE]);
 		buf += elem_size;
 	}
+
+	lru->target_free = clamp((nr_elems / num_possible_cpus()) / 2,
+				 1, LOCAL_FREE_TARGET);
 }
 
 static void bpf_percpu_lru_populate(struct bpf_lru *lru, void *buf,
diff --git a/kernel/bpf/bpf_lru_list.h b/kernel/bpf/bpf_lru_list.h
index cbd8d3720c2b..fe2661a58ea9 100644
--- a/kernel/bpf/bpf_lru_list.h
+++ b/kernel/bpf/bpf_lru_list.h
@@ -58,6 +58,7 @@ struct bpf_lru {
 	del_from_htab_func del_from_htab;
 	void *del_arg;
 	unsigned int hash_offset;
+	unsigned int target_free;
 	unsigned int nr_scans;
 	bool percpu;
 };
diff --git a/tools/testing/selftests/bpf/test_lru_map.c b/tools/testing/selftests/bpf/test_lru_map.c
index fda7589c5023..4ae83f4b7fc7 100644
--- a/tools/testing/selftests/bpf/test_lru_map.c
+++ b/tools/testing/selftests/bpf/test_lru_map.c
@@ -138,6 +138,12 @@ static int sched_next_online(int pid, int *next_to_try)
 	return ret;
 }
 
+/* Inverse of how bpf_common_lru_populate derives target_free from map_size. */
+static unsigned int __map_size(unsigned int tgt_free)
+{
+	return tgt_free * nr_cpus * 2;
+}
+
 /* Size of the LRU map is 2
  * Add key=1 (+1 key)
  * Add key=2 (+1 key)
@@ -231,11 +237,11 @@ static void test_lru_sanity0(int map_type, int map_flags)
 	printf("Pass\n");
 }
 
-/* Size of the LRU map is 1.5*tgt_free
- * Insert 1 to tgt_free (+tgt_free keys)
- * Lookup 1 to tgt_free/2
- * Insert 1+tgt_free to 2*tgt_free (+tgt_free keys)
- * => 1+tgt_free/2 to LOCALFREE_TARGET will be removed by LRU
+/* Verify that unreferenced elements are recycled before referenced ones.
+ * Insert elements.
+ * Reference a subset of these.
+ * Insert more, enough to trigger recycling.
+ * Verify that unreferenced are recycled.
  */
 static void test_lru_sanity1(int map_type, int map_flags, unsigned int tgt_free)
 {
@@ -257,7 +263,7 @@ static void test_lru_sanity1(int map_type, int map_flags, unsigned int tgt_free)
 	batch_size = tgt_free / 2;
 	assert(batch_size * 2 == tgt_free);
 
-	map_size = tgt_free + batch_size;
+	map_size = __map_size(tgt_free) + batch_size;
 	lru_map_fd = create_map(map_type, map_flags, map_size);
 	assert(lru_map_fd != -1);
 
@@ -266,13 +272,13 @@ static void test_lru_sanity1(int map_type, int map_flags, unsigned int tgt_free)
 
 	value[0] = 1234;
 
-	/* Insert 1 to tgt_free (+tgt_free keys) */
-	end_key = 1 + tgt_free;
+	/* Insert map_size - batch_size keys */
+	end_key = 1 + __map_size(tgt_free);
 	for (key = 1; key < end_key; key++)
 		assert(!bpf_map_update_elem(lru_map_fd, &key, value,
 					    BPF_NOEXIST));
 
-	/* Lookup 1 to tgt_free/2 */
+	/* Lookup 1 to batch_size */
 	end_key = 1 + batch_size;
 	for (key = 1; key < end_key; key++) {
 		assert(!bpf_map_lookup_elem_with_ref_bit(lru_map_fd, key, value));
@@ -280,12 +286,13 @@ static void test_lru_sanity1(int map_type, int map_flags, unsigned int tgt_free)
 					    BPF_NOEXIST));
 	}
 
-	/* Insert 1+tgt_free to 2*tgt_free
-	 * => 1+tgt_free/2 to LOCALFREE_TARGET will be
+	/* Insert another map_size - batch_size keys
+	 * Map will contain 1 to batch_size plus these latest, i.e.,
+	 * => previous 1+batch_size to map_size - batch_size will have been
 	 * removed by LRU
 	 */
-	key = 1 + tgt_free;
-	end_key = key + tgt_free;
+	key = 1 + __map_size(tgt_free);
+	end_key = key + __map_size(tgt_free);
 	for (; key < end_key; key++) {
 		assert(!bpf_map_update_elem(lru_map_fd, &key, value,
 					    BPF_NOEXIST));
@@ -301,17 +308,8 @@ static void test_lru_sanity1(int map_type, int map_flags, unsigned int tgt_free)
 	printf("Pass\n");
 }
 
-/* Size of the LRU map 1.5 * tgt_free
- * Insert 1 to tgt_free (+tgt_free keys)
- * Update 1 to tgt_free/2
- *   => The original 1 to tgt_free/2 will be removed due to
- *      the LRU shrink process
- * Re-insert 1 to tgt_free/2 again and do a lookup immeidately
- * Insert 1+tgt_free to tgt_free*3/2
- * Insert 1+tgt_free*3/2 to tgt_free*5/2
- *   => Key 1+tgt_free to tgt_free*3/2
- *      will be removed from LRU because it has never
- *      been lookup and ref bit is not set
+/* Verify that insertions exceeding map size will recycle the oldest.
+ * Verify that unreferenced elements are recycled before referenced.
  */
 static void test_lru_sanity2(int map_type, int map_flags, unsigned int tgt_free)
 {
@@ -334,7 +332,7 @@ static void test_lru_sanity2(int map_type, int map_flags, unsigned int tgt_free)
 	batch_size = tgt_free / 2;
 	assert(batch_size * 2 == tgt_free);
 
-	map_size = tgt_free + batch_size;
+	map_size = __map_size(tgt_free) + batch_size;
 	lru_map_fd = create_map(map_type, map_flags, map_size);
 	assert(lru_map_fd != -1);
 
@@ -343,8 +341,8 @@ static void test_lru_sanity2(int map_type, int map_flags, unsigned int tgt_free)
 
 	value[0] = 1234;
 
-	/* Insert 1 to tgt_free (+tgt_free keys) */
-	end_key = 1 + tgt_free;
+	/* Insert map_size - batch_size keys */
+	end_key = 1 + __map_size(tgt_free);
 	for (key = 1; key < end_key; key++)
 		assert(!bpf_map_update_elem(lru_map_fd, &key, value,
 					    BPF_NOEXIST));
@@ -357,8 +355,7 @@ static void test_lru_sanity2(int map_type, int map_flags, unsigned int tgt_free)
 	 * shrink the inactive list to get tgt_free
 	 * number of free nodes.
 	 *
-	 * Hence, the oldest key 1 to tgt_free/2
-	 * are removed from the LRU list.
+	 * Hence, the oldest key is removed from the LRU list.
 	 */
 	key = 1;
 	if (map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) {
@@ -370,8 +367,7 @@ static void test_lru_sanity2(int map_type, int map_flags, unsigned int tgt_free)
 					   BPF_EXIST));
 	}
 
-	/* Re-insert 1 to tgt_free/2 again and do a lookup
-	 * immeidately.
+	/* Re-insert 1 to batch_size again and do a lookup immediately.
 	 */
 	end_key = 1 + batch_size;
 	value[0] = 4321;
@@ -387,17 +383,18 @@ static void test_lru_sanity2(int map_type, int map_flags, unsigned int tgt_free)
 
 	value[0] = 1234;
 
-	/* Insert 1+tgt_free to tgt_free*3/2 */
-	end_key = 1 + tgt_free + batch_size;
-	for (key = 1 + tgt_free; key < end_key; key++)
+	/* Insert batch_size new elements */
+	key = 1 + __map_size(tgt_free);
+	end_key = key + batch_size;
+	for (; key < end_key; key++)
 		/* These newly added but not referenced keys will be
 		 * gone during the next LRU shrink.
 		 */
 		assert(!bpf_map_update_elem(lru_map_fd, &key, value,
 					    BPF_NOEXIST));
 
-	/* Insert 1+tgt_free*3/2 to  tgt_free*5/2 */
-	end_key = key + tgt_free;
+	/* Insert map_size - batch_size elements */
+	end_key += __map_size(tgt_free);
 	for (; key < end_key; key++) {
 		assert(!bpf_map_update_elem(lru_map_fd, &key, value,
 					    BPF_NOEXIST));
@@ -500,7 +497,8 @@ static void test_lru_sanity4(int map_type, int map_flags, unsigned int tgt_free)
 		lru_map_fd = create_map(map_type, map_flags,
 					3 * tgt_free * nr_cpus);
 	else
-		lru_map_fd = create_map(map_type, map_flags, 3 * tgt_free);
+		lru_map_fd = create_map(map_type, map_flags,
+					3 * __map_size(tgt_free));
 	assert(lru_map_fd != -1);
 
 	expected_map_fd = create_map(BPF_MAP_TYPE_HASH, 0,

From 7869738b6908eec7755818aaf6f3aa068b2f0e1b Mon Sep 17 00:00:00 2001
From: Gao Xiang <hsiangkao@linux.alibaba.com>
Date: Thu, 19 Jun 2025 11:28:39 +0800
Subject: [PATCH 0583/1334] erofs: refuse crafted out-of-file-range encoded
 extents

Crafted encoded extents could record out-of-range `lstart`, which should
not happen in normal cases.

It caused an iomap_iter_done() complaint [1] reported by syzbot.

[1] https://lore.kernel.org/r/684cb499.a00a0220.c6bd7.0010.GAE@google.com

Fixes: 1d191b4ca51d ("erofs: implement encoded extent metadata")
Reported-and-tested-by: syzbot+d8f000c609f05f52d9b5@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=d8f000c609f05f52d9b5
Signed-off-by: Gao Xiang <hsiangkao@linux.alibaba.com>
Link: https://lore.kernel.org/r/20250619032839.2642193-1-hsiangkao@linux.alibaba.com
---
 fs/erofs/zmap.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/fs/erofs/zmap.c b/fs/erofs/zmap.c
index 14ea47f954f5..6afcb054780d 100644
--- a/fs/erofs/zmap.c
+++ b/fs/erofs/zmap.c
@@ -597,6 +597,10 @@ static int z_erofs_map_blocks_ext(struct inode *inode,
 
 			if (la > map->m_la) {
 				r = mid;
+				if (la > lend) {
+					DBG_BUGON(1);
+					return -EFSCORRUPTED;
+				}
 				lend = la;
 			} else {
 				l = mid + 1;

From 8a8ff069c7ad9a359c54683329883e2432cff191 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Sun, 15 Jun 2025 16:11:38 +0100
Subject: [PATCH 0584/1334] KVM: arm64: nv: Fix tracking of shadow list
 registers

Wei-Lin reports that the tracking of shadow list registers is
majorly broken when resync'ing the L2 state after a run, as
we confuse the guest's LR index with the host's, potentially
losing the interrupt state.

While this could be fixed by adding yet another side index to
track it (Wei-Lin's fix), it may be better to refactor this
code to avoid having a side index altogether, limiting the
risk to introduce this class of bugs.

A key observation is that the shadow index is always the number
of bits in the lr_map bitmap. With that, the parallel indexing
scheme can be completely dropped.

While doing this, introduce a couple of helpers that abstract
the index conversion and some of the LR repainting, making the
whole exercise much simpler.

Reported-by: Wei-Lin Chang <r09922117@csie.ntu.edu.tw>
Reviewed-by: Wei-Lin Chang <r09922117@csie.ntu.edu.tw>
Reviewed-by: Oliver Upton <oliver.upton@linux.dev>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20250614145721.2504524-1-r09922117@csie.ntu.edu.tw
Link: https://lore.kernel.org/r/86qzzkc5xa.wl-maz@kernel.org
---
 arch/arm64/kvm/vgic/vgic-v3-nested.c | 81 ++++++++++++++--------------
 1 file changed, 42 insertions(+), 39 deletions(-)

diff --git a/arch/arm64/kvm/vgic/vgic-v3-nested.c b/arch/arm64/kvm/vgic/vgic-v3-nested.c
index d22a8ad7bcc5..a50fb7e6841f 100644
--- a/arch/arm64/kvm/vgic/vgic-v3-nested.c
+++ b/arch/arm64/kvm/vgic/vgic-v3-nested.c
@@ -36,6 +36,11 @@ struct shadow_if {
 
 static DEFINE_PER_CPU(struct shadow_if, shadow_if);
 
+static int lr_map_idx_to_shadow_idx(struct shadow_if *shadow_if, int idx)
+{
+	return hweight16(shadow_if->lr_map & (BIT(idx) - 1));
+}
+
 /*
  * Nesting GICv3 support
  *
@@ -209,6 +214,29 @@ u64 vgic_v3_get_misr(struct kvm_vcpu *vcpu)
 	return reg;
 }
 
+static u64 translate_lr_pintid(struct kvm_vcpu *vcpu, u64 lr)
+{
+	struct vgic_irq *irq;
+
+	if (!(lr & ICH_LR_HW))
+		return lr;
+
+	/* We have the HW bit set, check for validity of pINTID */
+	irq = vgic_get_vcpu_irq(vcpu, FIELD_GET(ICH_LR_PHYS_ID_MASK, lr));
+	/* If there was no real mapping, nuke the HW bit */
+	if (!irq || !irq->hw || irq->intid > VGIC_MAX_SPI)
+		lr &= ~ICH_LR_HW;
+
+	/* Translate the virtual mapping to the real one, even if invalid */
+	if (irq) {
+		lr &= ~ICH_LR_PHYS_ID_MASK;
+		lr |= FIELD_PREP(ICH_LR_PHYS_ID_MASK, (u64)irq->hwintid);
+		vgic_put_irq(vcpu->kvm, irq);
+	}
+
+	return lr;
+}
+
 /*
  * For LRs which have HW bit set such as timer interrupts, we modify them to
  * have the host hardware interrupt number instead of the virtual one programmed
@@ -217,58 +245,37 @@ u64 vgic_v3_get_misr(struct kvm_vcpu *vcpu)
 static void vgic_v3_create_shadow_lr(struct kvm_vcpu *vcpu,
 				     struct vgic_v3_cpu_if *s_cpu_if)
 {
-	unsigned long lr_map = 0;
-	int index = 0;
+	struct shadow_if *shadow_if;
+
+	shadow_if = container_of(s_cpu_if, struct shadow_if, cpuif);
+	shadow_if->lr_map = 0;
 
 	for (int i = 0; i < kvm_vgic_global_state.nr_lr; i++) {
 		u64 lr = __vcpu_sys_reg(vcpu, ICH_LRN(i));
-		struct vgic_irq *irq;
 
 		if (!(lr & ICH_LR_STATE))
-			lr = 0;
+			continue;
 
-		if (!(lr & ICH_LR_HW))
-			goto next;
+		lr = translate_lr_pintid(vcpu, lr);
 
-		/* We have the HW bit set, check for validity of pINTID */
-		irq = vgic_get_vcpu_irq(vcpu, FIELD_GET(ICH_LR_PHYS_ID_MASK, lr));
-		if (!irq || !irq->hw || irq->intid > VGIC_MAX_SPI ) {
-			/* There was no real mapping, so nuke the HW bit */
-			lr &= ~ICH_LR_HW;
-			if (irq)
-				vgic_put_irq(vcpu->kvm, irq);
-			goto next;
-		}
-
-		/* Translate the virtual mapping to the real one */
-		lr &= ~ICH_LR_PHYS_ID_MASK;
-		lr |= FIELD_PREP(ICH_LR_PHYS_ID_MASK, (u64)irq->hwintid);
-
-		vgic_put_irq(vcpu->kvm, irq);
-
-next:
-		s_cpu_if->vgic_lr[index] = lr;
-		if (lr) {
-			lr_map |= BIT(i);
-			index++;
-		}
+		s_cpu_if->vgic_lr[hweight16(shadow_if->lr_map)] = lr;
+		shadow_if->lr_map |= BIT(i);
 	}
 
-	container_of(s_cpu_if, struct shadow_if, cpuif)->lr_map = lr_map;
-	s_cpu_if->used_lrs = index;
+	s_cpu_if->used_lrs = hweight16(shadow_if->lr_map);
 }
 
 void vgic_v3_sync_nested(struct kvm_vcpu *vcpu)
 {
 	struct shadow_if *shadow_if = get_shadow_if();
-	int i, index = 0;
+	int i;
 
 	for_each_set_bit(i, &shadow_if->lr_map, kvm_vgic_global_state.nr_lr) {
 		u64 lr = __vcpu_sys_reg(vcpu, ICH_LRN(i));
 		struct vgic_irq *irq;
 
 		if (!(lr & ICH_LR_HW) || !(lr & ICH_LR_STATE))
-			goto next;
+			continue;
 
 		/*
 		 * If we had a HW lr programmed by the guest hypervisor, we
@@ -277,15 +284,13 @@ void vgic_v3_sync_nested(struct kvm_vcpu *vcpu)
 		 */
 		irq = vgic_get_vcpu_irq(vcpu, FIELD_GET(ICH_LR_PHYS_ID_MASK, lr));
 		if (WARN_ON(!irq)) /* Shouldn't happen as we check on load */
-			goto next;
+			continue;
 
-		lr = __gic_v3_get_lr(index);
+		lr = __gic_v3_get_lr(lr_map_idx_to_shadow_idx(shadow_if, i));
 		if (!(lr & ICH_LR_STATE))
 			irq->active = false;
 
 		vgic_put_irq(vcpu->kvm, irq);
-	next:
-		index++;
 	}
 }
 
@@ -368,13 +373,11 @@ void vgic_v3_put_nested(struct kvm_vcpu *vcpu)
 		val = __vcpu_sys_reg(vcpu, ICH_LRN(i));
 
 		val &= ~ICH_LR_STATE;
-		val |= s_cpu_if->vgic_lr[i] & ICH_LR_STATE;
+		val |= s_cpu_if->vgic_lr[lr_map_idx_to_shadow_idx(shadow_if, i)] & ICH_LR_STATE;
 
 		__vcpu_assign_sys_reg(vcpu, ICH_LRN(i), val);
-		s_cpu_if->vgic_lr[i] = 0;
 	}
 
-	shadow_if->lr_map = 0;
 	vcpu->arch.vgic_cpu.vgic_v3.used_lrs = 0;
 }
 

From 1fbe6861a6d9a942fb8ab8677ddf1ecb86b1af60 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Wed, 11 Jun 2025 15:45:04 -0700
Subject: [PATCH 0585/1334] KVM: arm64: Explicitly treat routing entry type
 changes as changes

Explicitly treat type differences as GSI routing changes, as comparing MSI
data between two entries could get a false negative, e.g. if userspace
changed the type but left the type-specific data as-

Note, the same bug was fixed in x86 by commit bcda70c56f3e ("KVM: x86:
Explicitly treat routing entry type changes as changes").

Fixes: 4bf3693d36af ("KVM: arm64: Unmap vLPIs affected by changes to GSI routing information")
Signed-off-by: Sean Christopherson <seanjc@google.com>
Reviewed-by: Oliver Upton <oliver.upton@linux.dev>
Link: https://lore.kernel.org/r/20250611224604.313496-3-seanjc@google.com
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/kvm/arm.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index de2b4e9c9f9f..38a91bb5d4c7 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -2764,7 +2764,8 @@ void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *cons,
 bool kvm_arch_irqfd_route_changed(struct kvm_kernel_irq_routing_entry *old,
 				  struct kvm_kernel_irq_routing_entry *new)
 {
-	if (new->type != KVM_IRQ_ROUTING_MSI)
+	if (old->type != KVM_IRQ_ROUTING_MSI ||
+	    new->type != KVM_IRQ_ROUTING_MSI)
 		return true;
 
 	return memcmp(&old->msi, &new->msi, sizeof(new->msi));

From 56a14984505b11674df5e01407748236bc4bc8f8 Mon Sep 17 00:00:00 2001
From: Zenghui Yu <yuzenghui@huawei.com>
Date: Sun, 8 Jun 2025 17:54:02 +0800
Subject: [PATCH 0586/1334] KVM: arm64: selftests: Close the GIC FD in
 arch_timer_edge_cases

Close the GIC FD to free the reference it holds to the VM so that we can
correctly clean up the VM. This also gets rid of the

	"KVM: debugfs: duplicate directory 395722-4"

warning when running arch_timer_edge_cases.

Signed-off-by: Zenghui Yu <yuzenghui@huawei.com>
Reviewed-by: Miguel Luis <miguel.luis@oracle.com>
Reviewed-by: Sebastian Ott <sebott@redhat.com>
Link: https://lore.kernel.org/r/20250608095402.1131-1-yuzenghui@huawei.com
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 .../selftests/kvm/arm64/arch_timer_edge_cases.c  | 16 +++++++++++++---
 1 file changed, 13 insertions(+), 3 deletions(-)

diff --git a/tools/testing/selftests/kvm/arm64/arch_timer_edge_cases.c b/tools/testing/selftests/kvm/arm64/arch_timer_edge_cases.c
index b4d22b3ab7cc..4e71740a098b 100644
--- a/tools/testing/selftests/kvm/arm64/arch_timer_edge_cases.c
+++ b/tools/testing/selftests/kvm/arm64/arch_timer_edge_cases.c
@@ -954,6 +954,8 @@ static void test_init_timer_irq(struct kvm_vm *vm, struct kvm_vcpu *vcpu)
 	pr_debug("ptimer_irq: %d; vtimer_irq: %d\n", ptimer_irq, vtimer_irq);
 }
 
+static int gic_fd;
+
 static void test_vm_create(struct kvm_vm **vm, struct kvm_vcpu **vcpu,
 			   enum arch_timer timer)
 {
@@ -968,12 +970,20 @@ static void test_vm_create(struct kvm_vm **vm, struct kvm_vcpu **vcpu,
 	vcpu_args_set(*vcpu, 1, timer);
 
 	test_init_timer_irq(*vm, *vcpu);
-	vgic_v3_setup(*vm, 1, 64);
+	gic_fd = vgic_v3_setup(*vm, 1, 64);
+	__TEST_REQUIRE(gic_fd >= 0, "Failed to create vgic-v3");
+
 	sync_global_to_guest(*vm, test_args);
 	sync_global_to_guest(*vm, CVAL_MAX);
 	sync_global_to_guest(*vm, DEF_CNT);
 }
 
+static void test_vm_cleanup(struct kvm_vm *vm)
+{
+	close(gic_fd);
+	kvm_vm_free(vm);
+}
+
 static void test_print_help(char *name)
 {
 	pr_info("Usage: %s [-h] [-b] [-i iterations] [-l long_wait_ms] [-p] [-v]\n"
@@ -1060,13 +1070,13 @@ int main(int argc, char *argv[])
 	if (test_args.test_virtual) {
 		test_vm_create(&vm, &vcpu, VIRTUAL);
 		test_run(vm, vcpu);
-		kvm_vm_free(vm);
+		test_vm_cleanup(vm);
 	}
 
 	if (test_args.test_physical) {
 		test_vm_create(&vm, &vcpu, PHYSICAL);
 		test_run(vm, vcpu);
-		kvm_vm_free(vm);
+		test_vm_cleanup(vm);
 	}
 
 	return 0;

From d9d79e4f7dc935fea96dbf3de524404c08d08b03 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 20 May 2025 17:40:43 +0200
Subject: [PATCH 0587/1334] mfd: Fix building without CONFIG_OF

Using the of_fwnode_handle() means that local 'node' variables are unused
whenever CONFIG_OF is disabled for compile testing:

drivers/mfd/88pm860x-core.c: In function 'device_irq_init':
drivers/mfd/88pm860x-core.c:576:29: error: unused variable 'node' [-Werror=unused-variable]
  576 |         struct device_node *node = i2c->dev.of_node;
      |                             ^~~~
drivers/mfd/max8925-core.c: In function 'max8925_irq_init':
drivers/mfd/max8925-core.c:659:29: error: unused variable 'node' [-Werror=unused-variable]
  659 |         struct device_node *node = chip->dev->of_node;
      |                             ^~~~
drivers/mfd/twl4030-irq.c: In function 'twl4030_init_irq':
drivers/mfd/twl4030-irq.c:679:46: error: unused variable 'node' [-Werror=unused-variable]
  679 |         struct                  device_node *node = dev->of_node;
      |                                              ^~~~

Replace these with the corresponding dev_fwnode() lookups that
keep the code simpler in addition to avoiding the warnings.

Fixes: e3d44f11da04 ("mfd: Switch to irq_domain_create_*()")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Jiri Slaby <jirislaby@kernel.org>
Link: https://lore.kernel.org/r/20250520154106.2019525-1-arnd@kernel.org
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/mfd/88pm860x-core.c | 3 +--
 drivers/mfd/max8925-core.c  | 6 +++---
 drivers/mfd/twl4030-irq.c   | 3 +--
 3 files changed, 5 insertions(+), 7 deletions(-)

diff --git a/drivers/mfd/88pm860x-core.c b/drivers/mfd/88pm860x-core.c
index 488e346047c1..77230fbe07be 100644
--- a/drivers/mfd/88pm860x-core.c
+++ b/drivers/mfd/88pm860x-core.c
@@ -573,7 +573,6 @@ static int device_irq_init(struct pm860x_chip *chip,
 	unsigned long flags = IRQF_TRIGGER_FALLING | IRQF_ONESHOT;
 	int data, mask, ret = -EINVAL;
 	int nr_irqs, irq_base = -1;
-	struct device_node *node = i2c->dev.of_node;
 
 	mask = PM8607_B0_MISC1_INV_INT | PM8607_B0_MISC1_INT_CLEAR
 		| PM8607_B0_MISC1_INT_MASK;
@@ -624,7 +623,7 @@ static int device_irq_init(struct pm860x_chip *chip,
 		ret = -EBUSY;
 		goto out;
 	}
-	irq_domain_create_legacy(of_fwnode_handle(node), nr_irqs, chip->irq_base, 0,
+	irq_domain_create_legacy(dev_fwnode(&i2c->dev), nr_irqs, chip->irq_base, 0,
 				 &pm860x_irq_domain_ops, chip);
 	chip->core_irq = i2c->irq;
 	if (!chip->core_irq)
diff --git a/drivers/mfd/max8925-core.c b/drivers/mfd/max8925-core.c
index 78b16c67a5fc..25377dcce60e 100644
--- a/drivers/mfd/max8925-core.c
+++ b/drivers/mfd/max8925-core.c
@@ -656,7 +656,6 @@ static int max8925_irq_init(struct max8925_chip *chip, int irq,
 {
 	unsigned long flags = IRQF_TRIGGER_FALLING | IRQF_ONESHOT;
 	int ret;
-	struct device_node *node = chip->dev->of_node;
 
 	/* clear all interrupts */
 	max8925_reg_read(chip->i2c, MAX8925_CHG_IRQ1);
@@ -682,8 +681,9 @@ static int max8925_irq_init(struct max8925_chip *chip, int irq,
 		return -EBUSY;
 	}
 
-	irq_domain_create_legacy(of_fwnode_handle(node), MAX8925_NR_IRQS, chip->irq_base, 0,
-				 &max8925_irq_domain_ops, chip);
+	irq_domain_create_legacy(dev_fwnode(chip->dev), MAX8925_NR_IRQS,
+				 chip->irq_base, 0, &max8925_irq_domain_ops,
+				 chip);
 
 	/* request irq handler for pmic main irq*/
 	chip->core_irq = irq;
diff --git a/drivers/mfd/twl4030-irq.c b/drivers/mfd/twl4030-irq.c
index 232c2bfe8c18..d3ab40651307 100644
--- a/drivers/mfd/twl4030-irq.c
+++ b/drivers/mfd/twl4030-irq.c
@@ -676,7 +676,6 @@ int twl4030_init_irq(struct device *dev, int irq_num)
 	static struct irq_chip	twl4030_irq_chip;
 	int			status, i;
 	int			irq_base, irq_end, nr_irqs;
-	struct			device_node *node = dev->of_node;
 
 	/*
 	 * TWL core and pwr interrupts must be contiguous because
@@ -691,7 +690,7 @@ int twl4030_init_irq(struct device *dev, int irq_num)
 		return irq_base;
 	}
 
-	irq_domain_create_legacy(of_fwnode_handle(node), nr_irqs, irq_base, 0,
+	irq_domain_create_legacy(dev_fwnode(dev), nr_irqs, irq_base, 0,
 				 &irq_domain_simple_ops, NULL);
 
 	irq_end = irq_base + TWL4030_CORE_NR_IRQS;

From 5bd1bafd4474ee26f504b41aba11f3e2a1175b88 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Mon, 16 Jun 2025 12:55:10 -0700
Subject: [PATCH 0588/1334] eth: fbnic: avoid double free when failing to
 DMA-map FW msg

The semantics are that caller of fbnic_mbx_map_msg() retains
the ownership of the message on error. All existing callers
dutifully free the page.

Fixes: da3cde08209e ("eth: fbnic: Add FW communication mechanism")
Reviewed-by: Alexander Duyck <alexanderduyck@fb.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://patch.msgid.link/20250616195510.225819-1-kuba@kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/meta/fbnic/fbnic_fw.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_fw.c b/drivers/net/ethernet/meta/fbnic/fbnic_fw.c
index e2368075ab8c..4521d0483d18 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_fw.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_fw.c
@@ -127,11 +127,8 @@ static int fbnic_mbx_map_msg(struct fbnic_dev *fbd, int mbx_idx,
 		return -EBUSY;
 
 	addr = dma_map_single(fbd->dev, msg, PAGE_SIZE, direction);
-	if (dma_mapping_error(fbd->dev, addr)) {
-		free_page((unsigned long)msg);
-
+	if (dma_mapping_error(fbd->dev, addr))
 		return -ENOSPC;
-	}
 
 	mbx->buf_info[tail].msg = msg;
 	mbx->buf_info[tail].addr = addr;

From 7e2c421ef88e9da9c39e01496b7f5b0b354b42bc Mon Sep 17 00:00:00 2001
From: Peter Chen <peter.chen@cixtech.com>
Date: Thu, 19 Jun 2025 09:34:13 +0800
Subject: [PATCH 0589/1334] usb: cdnsp: do not disable slot for disabled slot

It doesn't need to do it, and the related command event returns
'Slot Not Enabled Error' status.

Fixes: 3d82904559f4 ("usb: cdnsp: cdns3 Add main part of Cadence USBSSP DRD Driver")
Cc: stable <stable@kernel.org>
Suggested-by: Hongliang Yang <hongliang.yang@cixtech.com>
Reviewed-by: Fugang Duan <fugang.duan@cixtech.com>
Signed-off-by: Peter Chen <peter.chen@cixtech.com>
Link: https://lore.kernel.org/r/20250619013413.35817-1-peter.chen@cixtech.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/cdns3/cdnsp-ring.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/usb/cdns3/cdnsp-ring.c b/drivers/usb/cdns3/cdnsp-ring.c
index fd06cb85c4ea..757fdd918286 100644
--- a/drivers/usb/cdns3/cdnsp-ring.c
+++ b/drivers/usb/cdns3/cdnsp-ring.c
@@ -772,7 +772,9 @@ static int cdnsp_update_port_id(struct cdnsp_device *pdev, u32 port_id)
 	}
 
 	if (port_id != old_port) {
-		cdnsp_disable_slot(pdev);
+		if (pdev->slot_id)
+			cdnsp_disable_slot(pdev);
+
 		pdev->active_port = port;
 		cdnsp_enable_slot(pdev);
 	}

From 630a1dec3b0eba2a695b9063f1c205d585cbfec9 Mon Sep 17 00:00:00 2001
From: Kuen-Han Tsai <khtsai@google.com>
Date: Wed, 28 May 2025 18:03:11 +0800
Subject: [PATCH 0590/1334] usb: dwc3: Abort suspend on soft disconnect failure

When dwc3_gadget_soft_disconnect() fails, dwc3_suspend_common() keeps
going with the suspend, resulting in a period where the power domain is
off, but the gadget driver remains connected.  Within this time frame,
invoking vbus_event_work() will cause an error as it attempts to access
DWC3 registers for endpoint disabling after the power domain has been
completely shut down.

Abort the suspend sequence when dwc3_gadget_suspend() cannot halt the
controller and proceeds with a soft connect.

Fixes: 9f8a67b65a49 ("usb: dwc3: gadget: fix gadget suspend/resume")
Cc: stable <stable@kernel.org>
Acked-by: Thinh Nguyen <Thinh.Nguyen@synopsys.com>
Signed-off-by: Kuen-Han Tsai <khtsai@google.com>
Link: https://lore.kernel.org/r/20250528100315.2162699-1-khtsai@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/dwc3/core.c   |  9 +++++++--
 drivers/usb/dwc3/gadget.c | 22 +++++++++-------------
 2 files changed, 16 insertions(+), 15 deletions(-)

diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c
index 2bc775a747f2..8002c23a5a02 100644
--- a/drivers/usb/dwc3/core.c
+++ b/drivers/usb/dwc3/core.c
@@ -2422,6 +2422,7 @@ static int dwc3_suspend_common(struct dwc3 *dwc, pm_message_t msg)
 {
 	u32 reg;
 	int i;
+	int ret;
 
 	if (!pm_runtime_suspended(dwc->dev) && !PMSG_IS_AUTO(msg)) {
 		dwc->susphy_state = (dwc3_readl(dwc->regs, DWC3_GUSB2PHYCFG(0)) &
@@ -2440,7 +2441,9 @@ static int dwc3_suspend_common(struct dwc3 *dwc, pm_message_t msg)
 	case DWC3_GCTL_PRTCAP_DEVICE:
 		if (pm_runtime_suspended(dwc->dev))
 			break;
-		dwc3_gadget_suspend(dwc);
+		ret = dwc3_gadget_suspend(dwc);
+		if (ret)
+			return ret;
 		synchronize_irq(dwc->irq_gadget);
 		dwc3_core_exit(dwc);
 		break;
@@ -2475,7 +2478,9 @@ static int dwc3_suspend_common(struct dwc3 *dwc, pm_message_t msg)
 			break;
 
 		if (dwc->current_otg_role == DWC3_OTG_ROLE_DEVICE) {
-			dwc3_gadget_suspend(dwc);
+			ret = dwc3_gadget_suspend(dwc);
+			if (ret)
+				return ret;
 			synchronize_irq(dwc->irq_gadget);
 		}
 
diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c
index 321361288935..b6b63b530148 100644
--- a/drivers/usb/dwc3/gadget.c
+++ b/drivers/usb/dwc3/gadget.c
@@ -4821,8 +4821,15 @@ int dwc3_gadget_suspend(struct dwc3 *dwc)
 	int ret;
 
 	ret = dwc3_gadget_soft_disconnect(dwc);
-	if (ret)
-		goto err;
+	/*
+	 * Attempt to reset the controller's state. Likely no
+	 * communication can be established until the host
+	 * performs a port reset.
+	 */
+	if (ret && dwc->softconnect) {
+		dwc3_gadget_soft_connect(dwc);
+		return -EAGAIN;
+	}
 
 	spin_lock_irqsave(&dwc->lock, flags);
 	if (dwc->gadget_driver)
@@ -4830,17 +4837,6 @@ int dwc3_gadget_suspend(struct dwc3 *dwc)
 	spin_unlock_irqrestore(&dwc->lock, flags);
 
 	return 0;
-
-err:
-	/*
-	 * Attempt to reset the controller's state. Likely no
-	 * communication can be established until the host
-	 * performs a port reset.
-	 */
-	if (dwc->softconnect)
-		dwc3_gadget_soft_connect(dwc);
-
-	return ret;
 }
 
 int dwc3_gadget_resume(struct dwc3 *dwc)

From cee4392a57e14a799fbdee193bc4c0de65b29521 Mon Sep 17 00:00:00 2001
From: Oliver Neukum <oneukum@suse.com>
Date: Thu, 5 Jun 2025 14:28:45 +0200
Subject: [PATCH 0591/1334] Logitech C-270 even more broken

Some varieties of this device don't work with
RESET_RESUME alone.

Signed-off-by: Oliver Neukum <oneukum@suse.com>
Cc: stable <stable@kernel.org>
Link: https://lore.kernel.org/r/20250605122852.1440382-1-oneukum@suse.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/core/quirks.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c
index 53d68d20fb62..0cf94c7a2c9c 100644
--- a/drivers/usb/core/quirks.c
+++ b/drivers/usb/core/quirks.c
@@ -227,7 +227,8 @@ static const struct usb_device_id usb_quirk_list[] = {
 	{ USB_DEVICE(0x046a, 0x0023), .driver_info = USB_QUIRK_RESET_RESUME },
 
 	/* Logitech HD Webcam C270 */
-	{ USB_DEVICE(0x046d, 0x0825), .driver_info = USB_QUIRK_RESET_RESUME },
+	{ USB_DEVICE(0x046d, 0x0825), .driver_info = USB_QUIRK_RESET_RESUME |
+		USB_QUIRK_NO_LPM},
 
 	/* Logitech HD Pro Webcams C920, C920-C, C922, C925e and C930e */
 	{ USB_DEVICE(0x046d, 0x082d), .driver_info = USB_QUIRK_DELAY_INIT },

From 8f5b7e2bec1c36578fdaa74a6951833541103e27 Mon Sep 17 00:00:00 2001
From: Mathias Nyman <mathias.nyman@linux.intel.com>
Date: Wed, 11 Jun 2025 14:24:41 +0300
Subject: [PATCH 0592/1334] usb: hub: fix detection of high tier USB3 devices
 behind suspended hubs

USB3 devices connected behind several external suspended hubs may not
be detected when plugged in due to aggressive hub runtime pm suspend.

The hub driver immediately runtime-suspends hubs if there are no
active children or port activity.

There is a delay between the wake signal causing hub resume, and driver
visible port activity on the hub downstream facing ports.
Most of the LFPS handshake, resume signaling and link training done
on the downstream ports is not visible to the hub driver until completed,
when device then will appear fully enabled and running on the port.

This delay between wake signal and detectable port change is even more
significant with chained suspended hubs where the wake signal will
propagate upstream first. Suspended hubs will only start resuming
downstream ports after upstream facing port resumes.

The hub driver may resume a USB3 hub, read status of all ports, not
yet see any activity, and runtime suspend back the hub before any
port activity is visible.

This exact case was seen when conncting USB3 devices to a suspended
Thunderbolt dock.

USB3 specification defines a 100ms tU3WakeupRetryDelay, indicating
USB3 devices expect to be resumed within 100ms after signaling wake.
if not then device will resend the wake signal.

Give the USB3 hubs twice this time (200ms) to detect any port
changes after resume, before allowing hub to runtime suspend again.

Cc: stable <stable@kernel.org>
Fixes: 2839f5bcfcfc ("USB: Turn on auto-suspend for USB 3.0 hubs.")
Acked-by: Alan Stern <stern@rowland.harvard.edu>
Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Link: https://lore.kernel.org/r/20250611112441.2267883-1-mathias.nyman@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/core/hub.c | 33 ++++++++++++++++++++++++++++++++-
 1 file changed, 32 insertions(+), 1 deletion(-)

diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c
index 770d1e91183c..5c12dfdef569 100644
--- a/drivers/usb/core/hub.c
+++ b/drivers/usb/core/hub.c
@@ -68,6 +68,12 @@
  */
 #define USB_SHORT_SET_ADDRESS_REQ_TIMEOUT	500  /* ms */
 
+/*
+ * Give SS hubs 200ms time after wake to train downstream links before
+ * assuming no port activity and allowing hub to runtime suspend back.
+ */
+#define USB_SS_PORT_U0_WAKE_TIME	200  /* ms */
+
 /* Protect struct usb_device->state and ->children members
  * Note: Both are also protected by ->dev.sem, except that ->state can
  * change to USB_STATE_NOTATTACHED even when the semaphore isn't held. */
@@ -1068,11 +1074,12 @@ int usb_remove_device(struct usb_device *udev)
 
 enum hub_activation_type {
 	HUB_INIT, HUB_INIT2, HUB_INIT3,		/* INITs must come first */
-	HUB_POST_RESET, HUB_RESUME, HUB_RESET_RESUME,
+	HUB_POST_RESET, HUB_RESUME, HUB_RESET_RESUME, HUB_POST_RESUME,
 };
 
 static void hub_init_func2(struct work_struct *ws);
 static void hub_init_func3(struct work_struct *ws);
+static void hub_post_resume(struct work_struct *ws);
 
 static void hub_activate(struct usb_hub *hub, enum hub_activation_type type)
 {
@@ -1095,6 +1102,13 @@ static void hub_activate(struct usb_hub *hub, enum hub_activation_type type)
 			goto init2;
 		goto init3;
 	}
+
+	if (type == HUB_POST_RESUME) {
+		usb_autopm_put_interface_async(to_usb_interface(hub->intfdev));
+		hub_put(hub);
+		return;
+	}
+
 	hub_get(hub);
 
 	/* The superspeed hub except for root hub has to use Hub Depth
@@ -1343,6 +1357,16 @@ static void hub_activate(struct usb_hub *hub, enum hub_activation_type type)
 		device_unlock(&hdev->dev);
 	}
 
+	if (type == HUB_RESUME && hub_is_superspeed(hub->hdev)) {
+		/* give usb3 downstream links training time after hub resume */
+		INIT_DELAYED_WORK(&hub->init_work, hub_post_resume);
+		queue_delayed_work(system_power_efficient_wq, &hub->init_work,
+				   msecs_to_jiffies(USB_SS_PORT_U0_WAKE_TIME));
+		usb_autopm_get_interface_no_resume(
+			to_usb_interface(hub->intfdev));
+		return;
+	}
+
 	hub_put(hub);
 }
 
@@ -1361,6 +1385,13 @@ static void hub_init_func3(struct work_struct *ws)
 	hub_activate(hub, HUB_INIT3);
 }
 
+static void hub_post_resume(struct work_struct *ws)
+{
+	struct usb_hub *hub = container_of(ws, struct usb_hub, init_work.work);
+
+	hub_activate(hub, HUB_POST_RESUME);
+}
+
 enum hub_quiescing_type {
 	HUB_DISCONNECT, HUB_PRE_RESET, HUB_SUSPEND
 };

From 3b18405763c1ebb1efc15feef5563c9cdb2cc3a7 Mon Sep 17 00:00:00 2001
From: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Date: Wed, 11 Jun 2025 14:14:15 +0300
Subject: [PATCH 0593/1334] usb: acpi: fix device link removal

The device link to the USB4 host interface has to be removed
manually since it's no longer auto removed.

Fixes: 623dae3e7084 ("usb: acpi: fix boot hang due to early incorrect 'tunneled' USB3 device links")
Cc: stable <stable@kernel.org>
Signed-off-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Reviewed-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Link: https://lore.kernel.org/r/20250611111415.2707865-1-heikki.krogerus@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/core/hub.c      | 3 +++
 drivers/usb/core/usb-acpi.c | 4 +++-
 include/linux/usb.h         | 2 ++
 3 files changed, 8 insertions(+), 1 deletion(-)

diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c
index 5c12dfdef569..6bb6e92cb0a4 100644
--- a/drivers/usb/core/hub.c
+++ b/drivers/usb/core/hub.c
@@ -2368,6 +2368,9 @@ void usb_disconnect(struct usb_device **pdev)
 	usb_remove_ep_devs(&udev->ep0);
 	usb_unlock_device(udev);
 
+	if (udev->usb4_link)
+		device_link_del(udev->usb4_link);
+
 	/* Unregister the device.  The device driver is responsible
 	 * for de-configuring the device and invoking the remove-device
 	 * notifier chain (used by usbfs and possibly others).
diff --git a/drivers/usb/core/usb-acpi.c b/drivers/usb/core/usb-acpi.c
index ea1ce8beb0cb..489dbdc96f94 100644
--- a/drivers/usb/core/usb-acpi.c
+++ b/drivers/usb/core/usb-acpi.c
@@ -157,7 +157,7 @@ EXPORT_SYMBOL_GPL(usb_acpi_set_power_state);
  */
 static int usb_acpi_add_usb4_devlink(struct usb_device *udev)
 {
-	const struct device_link *link;
+	struct device_link *link;
 	struct usb_port *port_dev;
 	struct usb_hub *hub;
 
@@ -188,6 +188,8 @@ static int usb_acpi_add_usb4_devlink(struct usb_device *udev)
 	dev_dbg(&port_dev->dev, "Created device link from %s to %s\n",
 		dev_name(&port_dev->child->dev), dev_name(nhi_fwnode->dev));
 
+	udev->usb4_link = link;
+
 	return 0;
 }
 
diff --git a/include/linux/usb.h b/include/linux/usb.h
index 1b2545b4363b..92c752f5446f 100644
--- a/include/linux/usb.h
+++ b/include/linux/usb.h
@@ -614,6 +614,7 @@ struct usb3_lpm_parameters {
  *	FIXME -- complete doc
  * @authenticated: Crypto authentication passed
  * @tunnel_mode: Connection native or tunneled over USB4
+ * @usb4_link: device link to the USB4 host interface
  * @lpm_capable: device supports LPM
  * @lpm_devinit_allow: Allow USB3 device initiated LPM, exit latency is in range
  * @usb2_hw_lpm_capable: device can perform USB2 hardware LPM
@@ -724,6 +725,7 @@ struct usb_device {
 	unsigned reset_resume:1;
 	unsigned port_is_suspended:1;
 	enum usb_link_tunnel_mode tunnel_mode;
+	struct device_link *usb4_link;
 
 	int slot_id;
 	struct usb2_lpm_parameters l1_params;

From 31a6afbe86e8e9deba9ab53876ec49eafc7fd901 Mon Sep 17 00:00:00 2001
From: Xu Yang <xu.yang_2@nxp.com>
Date: Sat, 14 Jun 2025 20:49:14 +0800
Subject: [PATCH 0594/1334] usb: chipidea: udc: disconnect/reconnect from host
 when do suspend/resume

Shawn and John reported a hang issue during system suspend as below:

 - USB gadget is enabled as Ethernet
 - There is data transfer over USB Ethernet (scp a big file between host
                                             and device)
 - Device is going in/out suspend (echo mem > /sys/power/state)

The root cause is the USB device controller is suspended but the USB bus
is still active which caused the USB host continues to transfer data with
device and the device continues to queue USB requests (in this case, a
delayed TCP ACK packet trigger the issue) after controller is suspended,
however the USB controller clock is already gated off. Then if udc driver
access registers after that point, the system will hang.

The correct way to avoid such issue is to disconnect device from host when
the USB bus is not at suspend state. Then the host will receive disconnect
event and stop data transfer in time. To continue make USB gadget device
work after system resume, this will reconnect device automatically.

To make usb wakeup work if USB bus is already at suspend state, this will
keep connection for it only when USB device controller has enabled wakeup
capability.

Reported-by: Shawn Guo <shawnguo@kernel.org>
Reported-by: John Ernberg <john.ernberg@actia.se>
Closes: https://lore.kernel.org/linux-usb/aEZxmlHmjeWcXiF3@dragon/
Tested-by: John Ernberg <john.ernberg@actia.se> # iMX8QXP
Fixes: 235ffc17d014 ("usb: chipidea: udc: add suspend/resume support for device controller")
Cc: stable <stable@kernel.org>
Reviewed-by: Jun Li <jun.li@nxp.com>
Signed-off-by: Xu Yang <xu.yang_2@nxp.com>
Acked-by: Peter Chen <peter.chen@kernel.org>
Link: https://lore.kernel.org/r/20250614124914.207540-1-xu.yang_2@nxp.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/chipidea/udc.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/usb/chipidea/udc.c b/drivers/usb/chipidea/udc.c
index 8a9b31fd5c89..1a48e6440e6c 100644
--- a/drivers/usb/chipidea/udc.c
+++ b/drivers/usb/chipidea/udc.c
@@ -2374,6 +2374,10 @@ static void udc_suspend(struct ci_hdrc *ci)
 	 */
 	if (hw_read(ci, OP_ENDPTLISTADDR, ~0) == 0)
 		hw_write(ci, OP_ENDPTLISTADDR, ~0, ~0);
+
+	if (ci->gadget.connected &&
+	    (!ci->suspended || !device_may_wakeup(ci->dev)))
+		usb_gadget_disconnect(&ci->gadget);
 }
 
 static void udc_resume(struct ci_hdrc *ci, bool power_lost)
@@ -2384,6 +2388,9 @@ static void udc_resume(struct ci_hdrc *ci, bool power_lost)
 					OTGSC_BSVIS | OTGSC_BSVIE);
 		if (ci->vbus_active)
 			usb_gadget_vbus_disconnect(&ci->gadget);
+	} else if (ci->vbus_active && ci->driver &&
+		   !ci->gadget.connected) {
+		usb_gadget_connect(&ci->gadget);
 	}
 
 	/* Restore value 0 if it was set for power lost check */

From f6c7bc4a6823a0a959f40866a1efe99bd03c2c5b Mon Sep 17 00:00:00 2001
From: Kuen-Han Tsai <khtsai@google.com>
Date: Tue, 17 Jun 2025 13:07:11 +0800
Subject: [PATCH 0595/1334] Revert "usb: gadget: u_serial: Add null pointer
 check in gs_start_io"

This reverts commit ffd603f214237e250271162a5b325c6199a65382.

Commit ffd603f21423 ("usb: gadget: u_serial: Add null pointer check in
gs_start_io") adds null pointer checks at the beginning of the
gs_start_io() function to prevent a null pointer dereference. However,
these checks are redundant because the function's comment already
requires callers to hold the port_lock and ensure port.tty and port_usb
are not null. All existing callers already follow these rules.

The true cause of the null pointer dereference is a race condition. When
gs_start_io() calls either gs_start_rx() or gs_start_tx(), the port_lock
is temporarily released for usb_ep_queue(). This allows port.tty and
port_usb to be cleared.

Fixes: ffd603f21423 ("usb: gadget: u_serial: Add null pointer check in gs_start_io")
Cc: stable <stable@kernel.org>
Signed-off-by: Kuen-Han Tsai <khtsai@google.com>
Reviewed-by: Prashanth K <prashanth.k@oss.qualcomm.com>
Link: https://lore.kernel.org/r/20250617050844.1848232-1-khtsai@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/function/u_serial.c | 6 +-----
 1 file changed, 1 insertion(+), 5 deletions(-)

diff --git a/drivers/usb/gadget/function/u_serial.c b/drivers/usb/gadget/function/u_serial.c
index ab544f6824be..c043bdc30d8a 100644
--- a/drivers/usb/gadget/function/u_serial.c
+++ b/drivers/usb/gadget/function/u_serial.c
@@ -544,20 +544,16 @@ static int gs_alloc_requests(struct usb_ep *ep, struct list_head *head,
 static int gs_start_io(struct gs_port *port)
 {
 	struct list_head	*head = &port->read_pool;
-	struct usb_ep		*ep;
+	struct usb_ep		*ep = port->port_usb->out;
 	int			status;
 	unsigned		started;
 
-	if (!port->port_usb || !port->port.tty)
-		return -EIO;
-
 	/* Allocate RX and TX I/O buffers.  We can't easily do this much
 	 * earlier (with GFP_KERNEL) because the requests are coupled to
 	 * endpoints, as are the packet sizes we'll be using.  Different
 	 * configurations may use different endpoints with a given port;
 	 * and high speed vs full speed changes packet sizes too.
 	 */
-	ep = port->port_usb->out;
 	status = gs_alloc_requests(ep, head, gs_read_complete,
 		&port->read_allocated);
 	if (status)

From c529c3730bd09115684644e26bf01ecbd7e2c2c9 Mon Sep 17 00:00:00 2001
From: Kuen-Han Tsai <khtsai@google.com>
Date: Tue, 17 Jun 2025 13:07:12 +0800
Subject: [PATCH 0596/1334] usb: gadget: u_serial: Fix race condition in TTY
 wakeup

A race condition occurs when gs_start_io() calls either gs_start_rx() or
gs_start_tx(), as those functions briefly drop the port_lock for
usb_ep_queue(). This allows gs_close() and gserial_disconnect() to clear
port.tty and port_usb, respectively.

Use the null-safe TTY Port helper function to wake up TTY.

Example
  CPU1:			      CPU2:
  gserial_connect() // lock
  			      gs_close() // await lock
  gs_start_rx()     // unlock
  usb_ep_queue()
  			      gs_close() // lock, reset port.tty and unlock
  gs_start_rx()     // lock
  tty_wakeup()      // NPE

Fixes: 35f95fd7f234 ("TTY: usb/u_serial, use tty from tty_port")
Cc: stable <stable@kernel.org>
Signed-off-by: Kuen-Han Tsai <khtsai@google.com>
Reviewed-by: Prashanth K <prashanth.k@oss.qualcomm.com>
Link: https://lore.kernel.org/linux-usb/20240116141801.396398-1-khtsai@google.com/
Link: https://lore.kernel.org/r/20250617050844.1848232-2-khtsai@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/function/u_serial.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/usb/gadget/function/u_serial.c b/drivers/usb/gadget/function/u_serial.c
index c043bdc30d8a..540dc5ab96fc 100644
--- a/drivers/usb/gadget/function/u_serial.c
+++ b/drivers/usb/gadget/function/u_serial.c
@@ -295,8 +295,8 @@ __acquires(&port->port_lock)
 			break;
 	}
 
-	if (do_tty_wake && port->port.tty)
-		tty_wakeup(port->port.tty);
+	if (do_tty_wake)
+		tty_port_tty_wakeup(&port->port);
 	return status;
 }
 
@@ -574,7 +574,7 @@ static int gs_start_io(struct gs_port *port)
 		gs_start_tx(port);
 		/* Unblock any pending writes into our circular buffer, in case
 		 * we didn't in gs_start_tx() */
-		tty_wakeup(port->port.tty);
+		tty_port_tty_wakeup(&port->port);
 	} else {
 		/* Free reqs only if we are still connected */
 		if (port->port_usb) {

From 3eff494f6e17abf932699483f133a708ac0355dc Mon Sep 17 00:00:00 2001
From: Roy Luo <royluo@google.com>
Date: Thu, 22 May 2025 19:09:11 +0000
Subject: [PATCH 0597/1334] usb: xhci: Skip xhci_reset in xhci_resume if xhci
 is being removed

xhci_reset() currently returns -ENODEV if XHCI_STATE_REMOVING is
set, without completing the xhci handshake, unless the reset completes
exceptionally quickly. This behavior causes a regression on Synopsys
DWC3 USB controllers with dual-role capabilities.

Specifically, when a DWC3 controller exits host mode and removes xhci
while a reset is still in progress, and then attempts to configure its
hardware for device mode, the ongoing, incomplete reset leads to
critical register access issues. All register reads return zero, not
just within the xHCI register space (which might be expected during a
reset), but across the entire DWC3 IP block.

This patch addresses the issue by preventing xhci_reset() from being
called in xhci_resume() and bailing out early in the reinit flow when
XHCI_STATE_REMOVING is set.

Cc: stable <stable@kernel.org>
Fixes: 6ccb83d6c497 ("usb: xhci: Implement xhci_handshake_check_state() helper")
Suggested-by: Mathias Nyman <mathias.nyman@intel.com>
Signed-off-by: Roy Luo <royluo@google.com>
Link: https://lore.kernel.org/r/20250522190912.457583-2-royluo@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/host/xhci.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c
index 4e6dbd2375c3..4637d026716a 100644
--- a/drivers/usb/host/xhci.c
+++ b/drivers/usb/host/xhci.c
@@ -1182,7 +1182,10 @@ int xhci_resume(struct xhci_hcd *xhci, bool power_lost, bool is_auto_resume)
 		xhci_dbg(xhci, "Stop HCD\n");
 		xhci_halt(xhci);
 		xhci_zero_64b_regs(xhci);
-		retval = xhci_reset(xhci, XHCI_RESET_LONG_USEC);
+		if (xhci->xhc_state & XHCI_STATE_REMOVING)
+			retval = -ENODEV;
+		else
+			retval = xhci_reset(xhci, XHCI_RESET_LONG_USEC);
 		spin_unlock_irq(&xhci->lock);
 		if (retval)
 			return retval;

From 7aed15379db9c6ec67999cdaf5c443b7be06ea73 Mon Sep 17 00:00:00 2001
From: Roy Luo <royluo@google.com>
Date: Thu, 22 May 2025 19:09:12 +0000
Subject: [PATCH 0598/1334] Revert "usb: xhci: Implement
 xhci_handshake_check_state() helper"

This reverts commit 6ccb83d6c4972ebe6ae49de5eba051de3638362c.

Commit 6ccb83d6c497 ("usb: xhci: Implement xhci_handshake_check_state()
helper") was introduced to workaround watchdog timeout issues on some
platforms, allowing xhci_reset() to bail out early without waiting
for the reset to complete.

Skipping the xhci handshake during a reset is a dangerous move. The
xhci specification explicitly states that certain registers cannot
be accessed during reset in section 5.4.1 USB Command Register (USBCMD),
Host Controller Reset (HCRST) field:
"This bit is cleared to '0' by the Host Controller when the reset
process is complete. Software cannot terminate the reset process
early by writinga '0' to this bit and shall not write any xHC
Operational or Runtime registers until while HCRST is '1'."

This behavior causes a regression on SNPS DWC3 USB controller with
dual-role capability. When the DWC3 controller exits host mode and
removes xhci while a reset is still in progress, and then tries to
configure its hardware for device mode, the ongoing reset leads to
register access issues; specifically, all register reads returns 0.
These issues extend beyond the xhci register space (which is expected
during a reset) and affect the entire DWC3 IP block, causing the DWC3
device mode to malfunction.

Cc: stable <stable@kernel.org>
Fixes: 6ccb83d6c497 ("usb: xhci: Implement xhci_handshake_check_state() helper")
Signed-off-by: Roy Luo <royluo@google.com>
Link: https://lore.kernel.org/r/20250522190912.457583-3-royluo@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/host/xhci-ring.c |  5 ++---
 drivers/usb/host/xhci.c      | 26 +-------------------------
 drivers/usb/host/xhci.h      |  2 --
 3 files changed, 3 insertions(+), 30 deletions(-)

diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c
index e038ad3375dc..94c9c9271658 100644
--- a/drivers/usb/host/xhci-ring.c
+++ b/drivers/usb/host/xhci-ring.c
@@ -518,9 +518,8 @@ static int xhci_abort_cmd_ring(struct xhci_hcd *xhci, unsigned long flags)
 	 * In the future we should distinguish between -ENODEV and -ETIMEDOUT
 	 * and try to recover a -ETIMEDOUT with a host controller reset.
 	 */
-	ret = xhci_handshake_check_state(xhci, &xhci->op_regs->cmd_ring,
-			CMD_RING_RUNNING, 0, 5 * 1000 * 1000,
-			XHCI_STATE_REMOVING);
+	ret = xhci_handshake(&xhci->op_regs->cmd_ring,
+			CMD_RING_RUNNING, 0, 5 * 1000 * 1000);
 	if (ret < 0) {
 		xhci_err(xhci, "Abort failed to stop command ring: %d\n", ret);
 		xhci_halt(xhci);
diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c
index 4637d026716a..8a819e853288 100644
--- a/drivers/usb/host/xhci.c
+++ b/drivers/usb/host/xhci.c
@@ -84,29 +84,6 @@ int xhci_handshake(void __iomem *ptr, u32 mask, u32 done, u64 timeout_us)
 	return ret;
 }
 
-/*
- * xhci_handshake_check_state - same as xhci_handshake but takes an additional
- * exit_state parameter, and bails out with an error immediately when xhc_state
- * has exit_state flag set.
- */
-int xhci_handshake_check_state(struct xhci_hcd *xhci, void __iomem *ptr,
-		u32 mask, u32 done, int usec, unsigned int exit_state)
-{
-	u32	result;
-	int	ret;
-
-	ret = readl_poll_timeout_atomic(ptr, result,
-				(result & mask) == done ||
-				result == U32_MAX ||
-				xhci->xhc_state & exit_state,
-				1, usec);
-
-	if (result == U32_MAX || xhci->xhc_state & exit_state)
-		return -ENODEV;
-
-	return ret;
-}
-
 /*
  * Disable interrupts and begin the xHCI halting process.
  */
@@ -227,8 +204,7 @@ int xhci_reset(struct xhci_hcd *xhci, u64 timeout_us)
 	if (xhci->quirks & XHCI_INTEL_HOST)
 		udelay(1000);
 
-	ret = xhci_handshake_check_state(xhci, &xhci->op_regs->command,
-				CMD_RESET, 0, timeout_us, XHCI_STATE_REMOVING);
+	ret = xhci_handshake(&xhci->op_regs->command, CMD_RESET, 0, timeout_us);
 	if (ret)
 		return ret;
 
diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h
index 49887a303e43..fa1ea0e0c7fb 100644
--- a/drivers/usb/host/xhci.h
+++ b/drivers/usb/host/xhci.h
@@ -1868,8 +1868,6 @@ void xhci_skip_sec_intr_events(struct xhci_hcd *xhci,
 /* xHCI host controller glue */
 typedef void (*xhci_get_quirks_t)(struct device *, struct xhci_hcd *);
 int xhci_handshake(void __iomem *ptr, u32 mask, u32 done, u64 timeout_us);
-int xhci_handshake_check_state(struct xhci_hcd *xhci, void __iomem *ptr,
-		u32 mask, u32 done, int usec, unsigned int exit_state);
 void xhci_quiesce(struct xhci_hcd *xhci);
 int xhci_halt(struct xhci_hcd *xhci);
 int xhci_start(struct xhci_hcd *xhci);

From f5de469990f19569627ea0dd56536ff5a13beaa3 Mon Sep 17 00:00:00 2001
From: "Masami Hiramatsu (Google)" <mhiramat@kernel.org>
Date: Thu, 12 Jun 2025 20:26:10 +0900
Subject: [PATCH 0599/1334] mtk-sd: Prevent memory corruption from DMA map
 failure

If msdc_prepare_data() fails to map the DMA region, the request is
not prepared for data receiving, but msdc_start_data() proceeds
the DMA with previous setting.
Since this will lead a memory corruption, we have to stop the
request operation soon after the msdc_prepare_data() fails to
prepare it.

Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Fixes: 208489032bdd ("mmc: mediatek: Add Mediatek MMC driver")
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/174972756982.3337526.6755001617701603082.stgit@mhiramat.tok.corp.google.com
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/host/mtk-sd.c | 17 ++++++++++++++++-
 1 file changed, 16 insertions(+), 1 deletion(-)

diff --git a/drivers/mmc/host/mtk-sd.c b/drivers/mmc/host/mtk-sd.c
index b1d1586cf1fc..b12cfb9a5e5f 100644
--- a/drivers/mmc/host/mtk-sd.c
+++ b/drivers/mmc/host/mtk-sd.c
@@ -853,6 +853,11 @@ static void msdc_prepare_data(struct msdc_host *host, struct mmc_data *data)
 	}
 }
 
+static bool msdc_data_prepared(struct mmc_data *data)
+{
+	return data->host_cookie & MSDC_PREPARE_FLAG;
+}
+
 static void msdc_unprepare_data(struct msdc_host *host, struct mmc_data *data)
 {
 	if (data->host_cookie & MSDC_ASYNC_FLAG)
@@ -1484,8 +1489,18 @@ static void msdc_ops_request(struct mmc_host *mmc, struct mmc_request *mrq)
 	WARN_ON(!host->hsq_en && host->mrq);
 	host->mrq = mrq;
 
-	if (mrq->data)
+	if (mrq->data) {
 		msdc_prepare_data(host, mrq->data);
+		if (!msdc_data_prepared(mrq->data)) {
+			/*
+			 * Failed to prepare DMA area, fail fast before
+			 * starting any commands.
+			 */
+			mrq->cmd->error = -ENOSPC;
+			mmc_request_done(mmc_from_priv(host), mrq);
+			return;
+		}
+	}
 
 	/* if SBC is required, we have HW option and SW option.
 	 * if HW option is enabled, and SBC does not have "special" flags,

From ff78538e07fa284ce08cbbcb0730daa91ed16722 Mon Sep 17 00:00:00 2001
From: Nicolas Pitre <npitre@baylibre.com>
Date: Tue, 10 Jun 2025 21:41:44 -0400
Subject: [PATCH 0600/1334] vt: add missing notification when switching back to
 text mode

Programs using poll() on /dev/vcsa to be notified when VT changes occur
were missing one case: the switch from gfx to text mode.

Signed-off-by: Nicolas Pitre <npitre@baylibre.com>
Link: https://lore.kernel.org/r/9o5ro928-0pp4-05rq-70p4-ro385n21n723@onlyvoer.pbz
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/vt/vt.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c
index ed39d9cb4432..62049ceb34de 100644
--- a/drivers/tty/vt/vt.c
+++ b/drivers/tty/vt/vt.c
@@ -4650,6 +4650,7 @@ void do_unblank_screen(int leaving_gfx)
 	set_palette(vc);
 	set_cursor(vc);
 	vt_event_post(VT_EVENT_UNBLANK, vc->vc_num, vc->vc_num);
+	notify_update(vc);
 }
 EXPORT_SYMBOL(do_unblank_screen);
 

From 747b52413effe958ed57cf6d7bef80c34e1185f3 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Tue, 10 Jun 2025 19:02:29 -0700
Subject: [PATCH 0601/1334] vt: fix kernel-doc warnings in ucs_get_fallback()

Use the correct function parameter name in ucs_get_fallback() to prevent
kernel-doc warnings:

Warning: drivers/tty/vt/ucs.c:218 function parameter 'cp' not described in 'ucs_get_fallback'
Warning: drivers/tty/vt/ucs.c:218 Excess function parameter 'base' description in 'ucs_get_fallback'

Fixes: fe26933cf1e1 ("vt: add ucs_get_fallback()")
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Nicolas Pitre <npitre@baylibre.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Jiri Slaby <jirislaby@kernel.org>
Cc: linux-serial@vger.kernel.org
Reviewed-by: Nicolas Pitre <npitre@baylibre.com>.
Link: https://lore.kernel.org/r/20250611020229.2650595-1-rdunlap@infradead.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/vt/ucs.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/tty/vt/ucs.c b/drivers/tty/vt/ucs.c
index 6ead622b7713..03877485dfb7 100644
--- a/drivers/tty/vt/ucs.c
+++ b/drivers/tty/vt/ucs.c
@@ -206,7 +206,7 @@ static int ucs_page_entry_cmp(const void *key, const void *element)
 
 /**
  * ucs_get_fallback() - Get a substitution for the provided Unicode character
- * @base: Base Unicode code point (UCS-4)
+ * @cp: Unicode code point (UCS-4)
  *
  * Get a simpler fallback character for the provided Unicode character.
  * This is used for terminal display when corresponding glyph is unavailable.

From d36f0e9a0002f04f4d6dd9be908d58fe5bd3a279 Mon Sep 17 00:00:00 2001
From: Aidan Stewart <astewart@tektelic.com>
Date: Tue, 17 Jun 2025 10:48:19 -0600
Subject: [PATCH 0602/1334] serial: core: restore of_node information in sysfs

Since in v6.8-rc1, the of_node symlink under tty devices is
missing. This breaks any udev rules relying on this information.

Link the of_node information in the serial controller device with the
parent defined in the device tree. This will also apply to the serial
device which takes the serial controller as a parent device.

Fixes: b286f4e87e32 ("serial: core: Move tty and serdev to be children of serial core port device")
Cc: stable@vger.kernel.org
Signed-off-by: Aidan Stewart <astewart@tektelic.com>
Link: https://lore.kernel.org/r/20250617164819.13912-1-astewart@tektelic.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/serial_base_bus.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/tty/serial/serial_base_bus.c b/drivers/tty/serial/serial_base_bus.c
index 5d1677f1b651..cb3b127b06b6 100644
--- a/drivers/tty/serial/serial_base_bus.c
+++ b/drivers/tty/serial/serial_base_bus.c
@@ -72,6 +72,7 @@ static int serial_base_device_init(struct uart_port *port,
 	dev->parent = parent_dev;
 	dev->bus = &serial_base_bus_type;
 	dev->release = release;
+	device_set_of_node_from_dev(dev, parent_dev);
 
 	if (!serial_base_initialized) {
 		dev_dbg(port->dev, "uart_add_one_port() called before arch_initcall()?\n");

From cade3d57e456e69f67aa9894bf89dc8678796bb7 Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Tue, 17 Jun 2025 14:37:12 +0100
Subject: [PATCH 0603/1334] KVM: arm64: VHE: Synchronize restore of host debug
 registers

When KVM runs in non-protected VHE mode, there's no context
synchronization event between __debug_switch_to_host() restoring the
host debug registers and __kvm_vcpu_run() unmasking debug exceptions.
Due to this, it's theoretically possible for the host to take an
unexpected debug exception due to the stale guest configuration.

This cannot happen in NVHE/HVHE mode as debug exceptions are masked in
the hyp code, and the exception return to the host will provide the
necessary context synchronization before debug exceptions can be taken.

For now, avoid the problem by adding an ISB after VHE hyp code restores
the host debug registers.

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Fuad Tabba <tabba@google.com>
Cc: Marc Zyngier <maz@kernel.org>
Cc: Mark Brown <broonie@kernel.org>
Cc: Oliver Upton <oliver.upton@linux.dev>
Cc: Will Deacon <will@kernel.org>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20250617133718.4014181-2-mark.rutland@arm.com
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/kvm/hyp/include/hyp/debug-sr.h | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/arch/arm64/kvm/hyp/include/hyp/debug-sr.h b/arch/arm64/kvm/hyp/include/hyp/debug-sr.h
index 502a5b73ee70..73881e1dc267 100644
--- a/arch/arm64/kvm/hyp/include/hyp/debug-sr.h
+++ b/arch/arm64/kvm/hyp/include/hyp/debug-sr.h
@@ -167,6 +167,9 @@ static inline void __debug_switch_to_host_common(struct kvm_vcpu *vcpu)
 
 	__debug_save_state(guest_dbg, guest_ctxt);
 	__debug_restore_state(host_dbg, host_ctxt);
+
+	if (has_vhe())
+		isb();
 }
 
 #endif /* __ARM64_KVM_HYP_DEBUG_SR_H__ */

From 257d0aa8e2502754bc758faceceb6ff59318af60 Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Tue, 17 Jun 2025 14:37:13 +0100
Subject: [PATCH 0604/1334] KVM: arm64: VHE: Synchronize CPTR trap deactivation

Currently there is no ISB between __deactivate_cptr_traps() disabling
traps that affect EL2 and fpsimd_lazy_switch_to_host() manipulating
registers potentially affected by CPTR traps.

When NV is not in use, this is safe because the relevant registers are
only accessed when guest_owns_fp_regs() && vcpu_has_sve(vcpu), and this
also implies that SVE traps affecting EL2 have been deactivated prior to
__guest_entry().

When NV is in use, a guest hypervisor may have configured SVE traps for
a nested context, and so it is necessary to have an ISB between
__deactivate_cptr_traps() and fpsimd_lazy_switch_to_host().

Due to the current lack of an ISB, when a guest hypervisor enables SVE
traps in CPTR, the host can take an unexpected SVE trap from within
fpsimd_lazy_switch_to_host(), e.g.

| Unhandled 64-bit el1h sync exception on CPU1, ESR 0x0000000066000000 -- SVE
| CPU: 1 UID: 0 PID: 164 Comm: kvm-vcpu-0 Not tainted 6.15.0-rc4-00138-ga05e0f012c05 #3 PREEMPT
| Hardware name: FVP Base RevC (DT)
| pstate: 604023c9 (nZCv DAIF +PAN -UAO -TCO -DIT -SSBS BTYPE=--)
| pc : __kvm_vcpu_run+0x6f4/0x844
| lr : __kvm_vcpu_run+0x150/0x844
| sp : ffff800083903a60
| x29: ffff800083903a90 x28: ffff000801f4a300 x27: 0000000000000000
| x26: 0000000000000000 x25: ffff000801f90000 x24: ffff000801f900f0
| x23: ffff800081ff7720 x22: 0002433c807d623f x21: ffff000801f90000
| x20: ffff00087f730730 x19: 0000000000000000 x18: 0000000000000000
| x17: 0000000000000000 x16: 0000000000000000 x15: 0000000000000000
| x14: 0000000000000000 x13: 0000000000000000 x12: 0000000000000000
| x11: 0000000000000000 x10: 0000000000000000 x9 : 0000000000000000
| x8 : 0000000000000000 x7 : 0000000000000000 x6 : ffff000801f90d70
| x5 : 0000000000001000 x4 : ffff8007fd739000 x3 : ffff000801f90000
| x2 : 0000000000000000 x1 : 00000000000003cc x0 : ffff800082f9d000
| Kernel panic - not syncing: Unhandled exception
| CPU: 1 UID: 0 PID: 164 Comm: kvm-vcpu-0 Not tainted 6.15.0-rc4-00138-ga05e0f012c05 #3 PREEMPT
| Hardware name: FVP Base RevC (DT)
| Call trace:
|  show_stack+0x18/0x24 (C)
|  dump_stack_lvl+0x60/0x80
|  dump_stack+0x18/0x24
|  panic+0x168/0x360
|  __panic_unhandled+0x68/0x74
|  el1h_64_irq_handler+0x0/0x24
|  el1h_64_sync+0x6c/0x70
|  __kvm_vcpu_run+0x6f4/0x844 (P)
|  kvm_arm_vcpu_enter_exit+0x64/0xa0
|  kvm_arch_vcpu_ioctl_run+0x21c/0x870
|  kvm_vcpu_ioctl+0x1a8/0x9d0
|  __arm64_sys_ioctl+0xb4/0xf4
|  invoke_syscall+0x48/0x104
|  el0_svc_common.constprop.0+0x40/0xe0
|  do_el0_svc+0x1c/0x28
|  el0_svc+0x30/0xcc
|  el0t_64_sync_handler+0x10c/0x138
|  el0t_64_sync+0x198/0x19c
| SMP: stopping secondary CPUs
| Kernel Offset: disabled
| CPU features: 0x0000,000002c0,02df4fb9,97ee773f
| Memory Limit: none
| ---[ end Kernel panic - not syncing: Unhandled exception ]---

Fix this by adding an ISB between __deactivate_traps() and
fpsimd_lazy_switch_to_host().

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Fuad Tabba <tabba@google.com>
Cc: Marc Zyngier <maz@kernel.org>
Cc: Mark Brown <broonie@kernel.org>
Cc: Oliver Upton <oliver.upton@linux.dev>
Cc: Will Deacon <will@kernel.org>
Link: https://lore.kernel.org/r/20250617133718.4014181-3-mark.rutland@arm.com
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/kvm/hyp/vhe/switch.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c
index 09df2b42bc1b..20df44b49ceb 100644
--- a/arch/arm64/kvm/hyp/vhe/switch.c
+++ b/arch/arm64/kvm/hyp/vhe/switch.c
@@ -667,6 +667,9 @@ static int __kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu)
 
 	__deactivate_traps(vcpu);
 
+	/* Ensure CPTR trap deactivation has taken effect */
+	isb();
+
 	fpsimd_lazy_switch_to_host(vcpu);
 
 	sysreg_restore_host_state_vhe(host_ctxt);

From e62dd507844fa47f0fdc29f3be5a90a83f297820 Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Tue, 17 Jun 2025 14:37:14 +0100
Subject: [PATCH 0605/1334] KVM: arm64: Reorganise CPTR trap manipulation

The NVHE/HVHE and VHE modes have separate implementations of
__activate_cptr_traps() and __deactivate_cptr_traps() in their
respective switch.c files. There's some duplication of logic, and it's
not currently possible to reuse this logic elsewhere.

Move the logic into the common switch.h header so that it can be reused,
and de-duplicate the common logic.

This rework changes the way SVE traps are deactivated in VHE mode,
aligning it with NVHE/HVHE modes:

* Before this patch, VHE's __deactivate_cptr_traps() would
  unconditionally enable SVE for host EL2 (but not EL0), regardless of
  whether the ARM64_SVE cpucap was set.

* After this patch, VHE's __deactivate_cptr_traps() will take the
  ARM64_SVE cpucap into account. When ARM64_SVE is not set, SVE will be
  trapped from EL2 and below.

The old and new behaviour are both benign:

* When ARM64_SVE is not set, the host will not touch SVE state, and will
  not reconfigure SVE traps. Host EL0 access to SVE will be trapped as
  expected.

* When ARM64_SVE is set, the host will configure EL0 SVE traps before
  returning to EL0 as part of reloading the EL0 FPSIMD/SVE/SME state.

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Fuad Tabba <tabba@google.com>
Cc: Marc Zyngier <maz@kernel.org>
Cc: Mark Brown <broonie@kernel.org>
Cc: Oliver Upton <oliver.upton@linux.dev>
Cc: Will Deacon <will@kernel.org>
Link: https://lore.kernel.org/r/20250617133718.4014181-4-mark.rutland@arm.com
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/kvm/hyp/include/hyp/switch.h | 130 ++++++++++++++++++++++++
 arch/arm64/kvm/hyp/nvhe/switch.c        |  59 -----------
 arch/arm64/kvm/hyp/vhe/switch.c         |  81 ---------------
 3 files changed, 130 insertions(+), 140 deletions(-)

diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h
index 76dfda116e56..8a77fcccbcf6 100644
--- a/arch/arm64/kvm/hyp/include/hyp/switch.h
+++ b/arch/arm64/kvm/hyp/include/hyp/switch.h
@@ -65,6 +65,136 @@ static inline void __activate_traps_fpsimd32(struct kvm_vcpu *vcpu)
 	}
 }
 
+static inline void __activate_cptr_traps_nvhe(struct kvm_vcpu *vcpu)
+{
+	u64 val = CPTR_NVHE_EL2_RES1 | CPTR_EL2_TAM | CPTR_EL2_TTA;
+
+	/*
+	 * Always trap SME since it's not supported in KVM.
+	 * TSM is RES1 if SME isn't implemented.
+	 */
+	val |= CPTR_EL2_TSM;
+
+	if (!vcpu_has_sve(vcpu) || !guest_owns_fp_regs())
+		val |= CPTR_EL2_TZ;
+
+	if (!guest_owns_fp_regs())
+		val |= CPTR_EL2_TFP;
+
+	write_sysreg(val, cptr_el2);
+}
+
+static inline void __activate_cptr_traps_vhe(struct kvm_vcpu *vcpu)
+{
+	/*
+	 * With VHE (HCR.E2H == 1), accesses to CPACR_EL1 are routed to
+	 * CPTR_EL2. In general, CPACR_EL1 has the same layout as CPTR_EL2,
+	 * except for some missing controls, such as TAM.
+	 * In this case, CPTR_EL2.TAM has the same position with or without
+	 * VHE (HCR.E2H == 1) which allows us to use here the CPTR_EL2.TAM
+	 * shift value for trapping the AMU accesses.
+	 */
+	u64 val = CPTR_EL2_TAM | CPACR_EL1_TTA;
+	u64 cptr;
+
+	if (guest_owns_fp_regs()) {
+		val |= CPACR_EL1_FPEN;
+		if (vcpu_has_sve(vcpu))
+			val |= CPACR_EL1_ZEN;
+	}
+
+	if (!vcpu_has_nv(vcpu))
+		goto write;
+
+	/*
+	 * The architecture is a bit crap (what a surprise): an EL2 guest
+	 * writing to CPTR_EL2 via CPACR_EL1 can't set any of TCPAC or TTA,
+	 * as they are RES0 in the guest's view. To work around it, trap the
+	 * sucker using the very same bit it can't set...
+	 */
+	if (vcpu_el2_e2h_is_set(vcpu) && is_hyp_ctxt(vcpu))
+		val |= CPTR_EL2_TCPAC;
+
+	/*
+	 * Layer the guest hypervisor's trap configuration on top of our own if
+	 * we're in a nested context.
+	 */
+	if (is_hyp_ctxt(vcpu))
+		goto write;
+
+	cptr = vcpu_sanitised_cptr_el2(vcpu);
+
+	/*
+	 * Pay attention, there's some interesting detail here.
+	 *
+	 * The CPTR_EL2.xEN fields are 2 bits wide, although there are only two
+	 * meaningful trap states when HCR_EL2.TGE = 0 (running a nested guest):
+	 *
+	 *  - CPTR_EL2.xEN = x0, traps are enabled
+	 *  - CPTR_EL2.xEN = x1, traps are disabled
+	 *
+	 * In other words, bit[0] determines if guest accesses trap or not. In
+	 * the interest of simplicity, clear the entire field if the guest
+	 * hypervisor has traps enabled to dispel any illusion of something more
+	 * complicated taking place.
+	 */
+	if (!(SYS_FIELD_GET(CPACR_EL1, FPEN, cptr) & BIT(0)))
+		val &= ~CPACR_EL1_FPEN;
+	if (!(SYS_FIELD_GET(CPACR_EL1, ZEN, cptr) & BIT(0)))
+		val &= ~CPACR_EL1_ZEN;
+
+	if (kvm_has_feat(vcpu->kvm, ID_AA64MMFR3_EL1, S2POE, IMP))
+		val |= cptr & CPACR_EL1_E0POE;
+
+	val |= cptr & CPTR_EL2_TCPAC;
+
+write:
+	write_sysreg(val, cpacr_el1);
+}
+
+static inline void __activate_cptr_traps(struct kvm_vcpu *vcpu)
+{
+	if (!guest_owns_fp_regs())
+		__activate_traps_fpsimd32(vcpu);
+
+	if (has_vhe() || has_hvhe())
+		__activate_cptr_traps_vhe(vcpu);
+	else
+		__activate_cptr_traps_nvhe(vcpu);
+}
+
+static inline void __deactivate_cptr_traps_nvhe(struct kvm_vcpu *vcpu)
+{
+	u64 val = CPTR_NVHE_EL2_RES1;
+
+	if (!cpus_have_final_cap(ARM64_SVE))
+		val |= CPTR_EL2_TZ;
+	if (!cpus_have_final_cap(ARM64_SME))
+		val |= CPTR_EL2_TSM;
+
+	write_sysreg(val, cptr_el2);
+}
+
+static inline void __deactivate_cptr_traps_vhe(struct kvm_vcpu *vcpu)
+{
+	u64 val = CPACR_EL1_FPEN;
+
+	if (cpus_have_final_cap(ARM64_SVE))
+		val |= CPACR_EL1_ZEN;
+	if (cpus_have_final_cap(ARM64_SME))
+		val |= CPACR_EL1_SMEN;
+
+	write_sysreg(val, cpacr_el1);
+}
+
+static inline void __deactivate_cptr_traps(struct kvm_vcpu *vcpu)
+{
+	if (has_vhe() || has_hvhe())
+		__deactivate_cptr_traps_vhe(vcpu);
+	else
+		__deactivate_cptr_traps_nvhe(vcpu);
+}
+
 #define reg_to_fgt_masks(reg)						\
 	({								\
 		struct fgt_masks *m;					\
diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c
index 73affe1333a4..0e752b515d0f 100644
--- a/arch/arm64/kvm/hyp/nvhe/switch.c
+++ b/arch/arm64/kvm/hyp/nvhe/switch.c
@@ -47,65 +47,6 @@ struct fgt_masks hdfgwtr2_masks;
 
 extern void kvm_nvhe_prepare_backtrace(unsigned long fp, unsigned long pc);
 
-static void __activate_cptr_traps(struct kvm_vcpu *vcpu)
-{
-	u64 val = CPTR_EL2_TAM;	/* Same bit irrespective of E2H */
-
-	if (!guest_owns_fp_regs())
-		__activate_traps_fpsimd32(vcpu);
-
-	if (has_hvhe()) {
-		val |= CPACR_EL1_TTA;
-
-		if (guest_owns_fp_regs()) {
-			val |= CPACR_EL1_FPEN;
-			if (vcpu_has_sve(vcpu))
-				val |= CPACR_EL1_ZEN;
-		}
-
-		write_sysreg(val, cpacr_el1);
-	} else {
-		val |= CPTR_EL2_TTA | CPTR_NVHE_EL2_RES1;
-
-		/*
-		 * Always trap SME since it's not supported in KVM.
-		 * TSM is RES1 if SME isn't implemented.
-		 */
-		val |= CPTR_EL2_TSM;
-
-		if (!vcpu_has_sve(vcpu) || !guest_owns_fp_regs())
-			val |= CPTR_EL2_TZ;
-
-		if (!guest_owns_fp_regs())
-			val |= CPTR_EL2_TFP;
-
-		write_sysreg(val, cptr_el2);
-	}
-}
-
-static void __deactivate_cptr_traps(struct kvm_vcpu *vcpu)
-{
-	if (has_hvhe()) {
-		u64 val = CPACR_EL1_FPEN;
-
-		if (cpus_have_final_cap(ARM64_SVE))
-			val |= CPACR_EL1_ZEN;
-		if (cpus_have_final_cap(ARM64_SME))
-			val |= CPACR_EL1_SMEN;
-
-		write_sysreg(val, cpacr_el1);
-	} else {
-		u64 val = CPTR_NVHE_EL2_RES1;
-
-		if (!cpus_have_final_cap(ARM64_SVE))
-			val |= CPTR_EL2_TZ;
-		if (!cpus_have_final_cap(ARM64_SME))
-			val |= CPTR_EL2_TSM;
-
-		write_sysreg(val, cptr_el2);
-	}
-}
-
 static void __activate_traps(struct kvm_vcpu *vcpu)
 {
 	___activate_traps(vcpu, vcpu->arch.hcr_el2);
diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c
index 20df44b49ceb..32b4814eb2b7 100644
--- a/arch/arm64/kvm/hyp/vhe/switch.c
+++ b/arch/arm64/kvm/hyp/vhe/switch.c
@@ -90,87 +90,6 @@ static u64 __compute_hcr(struct kvm_vcpu *vcpu)
 	return hcr | (guest_hcr & ~NV_HCR_GUEST_EXCLUDE);
 }
 
-static void __activate_cptr_traps(struct kvm_vcpu *vcpu)
-{
-	u64 cptr;
-
-	/*
-	 * With VHE (HCR.E2H == 1), accesses to CPACR_EL1 are routed to
-	 * CPTR_EL2. In general, CPACR_EL1 has the same layout as CPTR_EL2,
-	 * except for some missing controls, such as TAM.
-	 * In this case, CPTR_EL2.TAM has the same position with or without
-	 * VHE (HCR.E2H == 1) which allows us to use here the CPTR_EL2.TAM
-	 * shift value for trapping the AMU accesses.
-	 */
-	u64 val = CPACR_EL1_TTA | CPTR_EL2_TAM;
-
-	if (guest_owns_fp_regs()) {
-		val |= CPACR_EL1_FPEN;
-		if (vcpu_has_sve(vcpu))
-			val |= CPACR_EL1_ZEN;
-	} else {
-		__activate_traps_fpsimd32(vcpu);
-	}
-
-	if (!vcpu_has_nv(vcpu))
-		goto write;
-
-	/*
-	 * The architecture is a bit crap (what a surprise): an EL2 guest
-	 * writing to CPTR_EL2 via CPACR_EL1 can't set any of TCPAC or TTA,
-	 * as they are RES0 in the guest's view. To work around it, trap the
-	 * sucker using the very same bit it can't set...
-	 */
-	if (vcpu_el2_e2h_is_set(vcpu) && is_hyp_ctxt(vcpu))
-		val |= CPTR_EL2_TCPAC;
-
-	/*
-	 * Layer the guest hypervisor's trap configuration on top of our own if
-	 * we're in a nested context.
-	 */
-	if (is_hyp_ctxt(vcpu))
-		goto write;
-
-	cptr = vcpu_sanitised_cptr_el2(vcpu);
-
-	/*
-	 * Pay attention, there's some interesting detail here.
-	 *
-	 * The CPTR_EL2.xEN fields are 2 bits wide, although there are only two
-	 * meaningful trap states when HCR_EL2.TGE = 0 (running a nested guest):
-	 *
-	 *  - CPTR_EL2.xEN = x0, traps are enabled
-	 *  - CPTR_EL2.xEN = x1, traps are disabled
-	 *
-	 * In other words, bit[0] determines if guest accesses trap or not. In
-	 * the interest of simplicity, clear the entire field if the guest
-	 * hypervisor has traps enabled to dispel any illusion of something more
-	 * complicated taking place.
-	 */
-	if (!(SYS_FIELD_GET(CPACR_EL1, FPEN, cptr) & BIT(0)))
-		val &= ~CPACR_EL1_FPEN;
-	if (!(SYS_FIELD_GET(CPACR_EL1, ZEN, cptr) & BIT(0)))
-		val &= ~CPACR_EL1_ZEN;
-
-	if (kvm_has_feat(vcpu->kvm, ID_AA64MMFR3_EL1, S2POE, IMP))
-		val |= cptr & CPACR_EL1_E0POE;
-
-	val |= cptr & CPTR_EL2_TCPAC;
-
-write:
-	write_sysreg(val, cpacr_el1);
-}
-
-static void __deactivate_cptr_traps(struct kvm_vcpu *vcpu)
-{
-	u64 val = CPACR_EL1_FPEN | CPACR_EL1_ZEN_EL1EN;
-
-	if (cpus_have_final_cap(ARM64_SME))
-		val |= CPACR_EL1_SMEN_EL1EN;
-
-	write_sysreg(val, cpacr_el1);
-}
-
 static void __activate_traps(struct kvm_vcpu *vcpu)
 {
 	u64 val;

From 59e6e101a6fa542a365dd5858affd18ba3e84cb8 Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Tue, 17 Jun 2025 14:37:15 +0100
Subject: [PATCH 0606/1334] KVM: arm64: Remove ad-hoc CPTR manipulation from
 fpsimd_sve_sync()

There's no need for fpsimd_sve_sync() to write to CPTR/CPACR. All
relevant traps are always disabled earlier within __kvm_vcpu_run(), when
__deactivate_cptr_traps() configures CPTR/CPACR.

With irrelevant details elided, the flow is:

handle___kvm_vcpu_run(...)
{
	flush_hyp_vcpu(...) {
		fpsimd_sve_flush(...);
	}

	__kvm_vcpu_run(...) {
		__activate_traps(...) {
			__activate_cptr_traps(...);
		}

		do {
			__guest_enter(...);
		} while (...);

		__deactivate_traps(....) {
			__deactivate_cptr_traps(...);
		}
	}

	sync_hyp_vcpu(...) {
		fpsimd_sve_sync(...);
	}
}

Remove the unnecessary write to CPTR/CPACR. An ISB is still necessary,
so a comment is added to describe this requirement.

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Fuad Tabba <tabba@google.com>
Cc: Marc Zyngier <maz@kernel.org>
Cc: Mark Brown <broonie@kernel.org>
Cc: Oliver Upton <oliver.upton@linux.dev>
Cc: Will Deacon <will@kernel.org>
Link: https://lore.kernel.org/r/20250617133718.4014181-5-mark.rutland@arm.com
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/kvm/hyp/nvhe/hyp-main.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
index e9198e56e784..3206b2c07f82 100644
--- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c
+++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
@@ -69,7 +69,10 @@ static void fpsimd_sve_sync(struct kvm_vcpu *vcpu)
 	if (!guest_owns_fp_regs())
 		return;
 
-	cpacr_clear_set(0, CPACR_EL1_FPEN | CPACR_EL1_ZEN);
+	/*
+	 * Traps have been disabled by __deactivate_cptr_traps(), but there
+	 * hasn't necessarily been a context synchronization event yet.
+	 */
 	isb();
 
 	if (vcpu_has_sve(vcpu))

From 186b58bacd74d9b7892869f7c7d20cf865a3c237 Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Tue, 17 Jun 2025 14:37:16 +0100
Subject: [PATCH 0607/1334] KVM: arm64: Remove ad-hoc CPTR manipulation from
 kvm_hyp_handle_fpsimd()

The hyp code FPSIMD/SVE/SME trap handling logic has some rather messy
open-coded manipulation of CPTR/CPACR. This is benign for non-nested
guests, but broken for nested guests, as the guest hypervisor's CPTR
configuration is not taken into account.

Consider the case where L0 provides FPSIMD+SVE to an L1 guest
hypervisor, and the L1 guest hypervisor only provides FPSIMD to an L2
guest (with L1 configuring CPTR/CPACR to trap SVE usage from L2). If the
L2 guest triggers an FPSIMD trap to the L0 hypervisor,
kvm_hyp_handle_fpsimd() will see that the vCPU supports FPSIMD+SVE, and
will configure CPTR/CPACR to NOT trap FPSIMD+SVE before returning to the
L2 guest. Consequently the L2 guest would be able to manipulate SVE
state even though the L1 hypervisor had configured CPTR/CPACR to forbid
this.

Clean this up, and fix the nested virt issue by always using
__deactivate_cptr_traps() and __activate_cptr_traps() to manage the CPTR
traps. This removes the need for the ad-hoc fixup in
kvm_hyp_save_fpsimd_host(), and ensures that any guest hypervisor
configuration of CPTR/CPACR is taken into account.

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Fuad Tabba <tabba@google.com>
Cc: Marc Zyngier <maz@kernel.org>
Cc: Mark Brown <broonie@kernel.org>
Cc: Oliver Upton <oliver.upton@linux.dev>
Cc: Will Deacon <will@kernel.org>
Link: https://lore.kernel.org/r/20250617133718.4014181-6-mark.rutland@arm.com
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/kvm/hyp/include/hyp/switch.h | 17 ++++++++---------
 1 file changed, 8 insertions(+), 9 deletions(-)

diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h
index 8a77fcccbcf6..2ad57b117385 100644
--- a/arch/arm64/kvm/hyp/include/hyp/switch.h
+++ b/arch/arm64/kvm/hyp/include/hyp/switch.h
@@ -616,11 +616,6 @@ static void kvm_hyp_save_fpsimd_host(struct kvm_vcpu *vcpu)
 	 */
 	if (system_supports_sve()) {
 		__hyp_sve_save_host();
-
-		/* Re-enable SVE traps if not supported for the guest vcpu. */
-		if (!vcpu_has_sve(vcpu))
-			cpacr_clear_set(CPACR_EL1_ZEN, 0);
-
 	} else {
 		__fpsimd_save_state(host_data_ptr(host_ctxt.fp_regs));
 	}
@@ -671,10 +666,7 @@ static inline bool kvm_hyp_handle_fpsimd(struct kvm_vcpu *vcpu, u64 *exit_code)
 	/* Valid trap.  Switch the context: */
 
 	/* First disable enough traps to allow us to update the registers */
-	if (sve_guest || (is_protected_kvm_enabled() && system_supports_sve()))
-		cpacr_clear_set(0, CPACR_EL1_FPEN | CPACR_EL1_ZEN);
-	else
-		cpacr_clear_set(0, CPACR_EL1_FPEN);
+	__deactivate_cptr_traps(vcpu);
 	isb();
 
 	/* Write out the host state if it's in the registers */
@@ -696,6 +688,13 @@ static inline bool kvm_hyp_handle_fpsimd(struct kvm_vcpu *vcpu, u64 *exit_code)
 
 	*host_data_ptr(fp_owner) = FP_STATE_GUEST_OWNED;
 
+	/*
+	 * Re-enable traps necessary for the current state of the guest, e.g.
+	 * those enabled by a guest hypervisor. The ERET to the guest will
+	 * provide the necessary context synchronization.
+	 */
+	__activate_cptr_traps(vcpu);
+
 	return true;
 }
 

From 3a300a33e4063fb44c7887bec3aecd2fd6966df8 Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Tue, 17 Jun 2025 14:37:17 +0100
Subject: [PATCH 0608/1334] KVM: arm64: Remove cpacr_clear_set()

We no longer use cpacr_clear_set().

Remove cpacr_clear_set() and its helper functions.

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Fuad Tabba <tabba@google.com>
Cc: Marc Zyngier <maz@kernel.org>
Cc: Mark Brown <broonie@kernel.org>
Cc: Oliver Upton <oliver.upton@linux.dev>
Cc: Will Deacon <will@kernel.org>
Link: https://lore.kernel.org/r/20250617133718.4014181-7-mark.rutland@arm.com
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/kvm_emulate.h | 62 ----------------------------
 1 file changed, 62 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index bd020fc28aa9..0720898f563e 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -561,68 +561,6 @@ static __always_inline void kvm_incr_pc(struct kvm_vcpu *vcpu)
 		vcpu_set_flag((v), e);					\
 	} while (0)
 
-#define __build_check_all_or_none(r, bits)				\
-	BUILD_BUG_ON(((r) & (bits)) && ((r) & (bits)) != (bits))
-
-#define __cpacr_to_cptr_clr(clr, set)					\
-	({								\
-		u64 cptr = 0;						\
-									\
-		if ((set) & CPACR_EL1_FPEN)				\
-			cptr |= CPTR_EL2_TFP;				\
-		if ((set) & CPACR_EL1_ZEN)				\
-			cptr |= CPTR_EL2_TZ;				\
-		if ((set) & CPACR_EL1_SMEN)				\
-			cptr |= CPTR_EL2_TSM;				\
-		if ((clr) & CPACR_EL1_TTA)				\
-			cptr |= CPTR_EL2_TTA;				\
-		if ((clr) & CPTR_EL2_TAM)				\
-			cptr |= CPTR_EL2_TAM;				\
-		if ((clr) & CPTR_EL2_TCPAC)				\
-			cptr |= CPTR_EL2_TCPAC;				\
-									\
-		cptr;							\
-	})
-
-#define __cpacr_to_cptr_set(clr, set)					\
-	({								\
-		u64 cptr = 0;						\
-									\
-		if ((clr) & CPACR_EL1_FPEN)				\
-			cptr |= CPTR_EL2_TFP;				\
-		if ((clr) & CPACR_EL1_ZEN)				\
-			cptr |= CPTR_EL2_TZ;				\
-		if ((clr) & CPACR_EL1_SMEN)				\
-			cptr |= CPTR_EL2_TSM;				\
-		if ((set) & CPACR_EL1_TTA)				\
-			cptr |= CPTR_EL2_TTA;				\
-		if ((set) & CPTR_EL2_TAM)				\
-			cptr |= CPTR_EL2_TAM;				\
-		if ((set) & CPTR_EL2_TCPAC)				\
-			cptr |= CPTR_EL2_TCPAC;				\
-									\
-		cptr;							\
-	})
-
-#define cpacr_clear_set(clr, set)					\
-	do {								\
-		BUILD_BUG_ON((set) & CPTR_VHE_EL2_RES0);		\
-		BUILD_BUG_ON((clr) & CPACR_EL1_E0POE);			\
-		__build_check_all_or_none((clr), CPACR_EL1_FPEN);	\
-		__build_check_all_or_none((set), CPACR_EL1_FPEN);	\
-		__build_check_all_or_none((clr), CPACR_EL1_ZEN);	\
-		__build_check_all_or_none((set), CPACR_EL1_ZEN);	\
-		__build_check_all_or_none((clr), CPACR_EL1_SMEN);	\
-		__build_check_all_or_none((set), CPACR_EL1_SMEN);	\
-									\
-		if (has_vhe() || has_hvhe())				\
-			sysreg_clear_set(cpacr_el1, clr, set);		\
-		else							\
-			sysreg_clear_set(cptr_el2,			\
-					 __cpacr_to_cptr_clr(clr, set),	\
-					 __cpacr_to_cptr_set(clr, set));\
-	} while (0)
-
 /*
  * Returns a 'sanitised' view of CPTR_EL2, translating from nVHE to the VHE
  * format if E2H isn't set.

From 04c5355b2a94ff3191ce63ab035fb7f04d036869 Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Tue, 17 Jun 2025 14:37:18 +0100
Subject: [PATCH 0609/1334] KVM: arm64: VHE: Centralize ISBs when returning to
 host

The VHE hyp code has recently gained a few ISBs. Simplify this to one
unconditional ISB in __kvm_vcpu_run_vhe(), and remove the unnecessary
ISB from the kvm_call_hyp_ret() macro.

While kvm_call_hyp_ret() is also used to invoke
__vgic_v3_get_gic_config(), but no ISB is necessary in that case either.

For the moment, an ISB is left in kvm_call_hyp(), as there are many more
users, and removing the ISB would require a more thorough audit.

Suggested-by: Marc Zyngier <maz@kernel.org>
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Fuad Tabba <tabba@google.com>
Cc: Marc Zyngier <maz@kernel.org>
Cc: Mark Brown <broonie@kernel.org>
Cc: Oliver Upton <oliver.upton@linux.dev>
Cc: Will Deacon <will@kernel.org>
Link: https://lore.kernel.org/r/20250617133718.4014181-8-mark.rutland@arm.com
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/kvm_host.h         |  6 ++----
 arch/arm64/kvm/hyp/include/hyp/debug-sr.h |  3 ---
 arch/arm64/kvm/hyp/vhe/switch.c           | 25 +++++++++++------------
 3 files changed, 14 insertions(+), 20 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 5ccca509dff1..d27079968341 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -1289,9 +1289,8 @@ void kvm_arm_resume_guest(struct kvm *kvm);
 	})
 
 /*
- * The couple of isb() below are there to guarantee the same behaviour
- * on VHE as on !VHE, where the eret to EL1 acts as a context
- * synchronization event.
+ * The isb() below is there to guarantee the same behaviour on VHE as on !VHE,
+ * where the eret to EL1 acts as a context synchronization event.
  */
 #define kvm_call_hyp(f, ...)						\
 	do {								\
@@ -1309,7 +1308,6 @@ void kvm_arm_resume_guest(struct kvm *kvm);
 									\
 		if (has_vhe()) {					\
 			ret = f(__VA_ARGS__);				\
-			isb();						\
 		} else {						\
 			ret = kvm_call_hyp_nvhe(f, ##__VA_ARGS__);	\
 		}							\
diff --git a/arch/arm64/kvm/hyp/include/hyp/debug-sr.h b/arch/arm64/kvm/hyp/include/hyp/debug-sr.h
index 73881e1dc267..502a5b73ee70 100644
--- a/arch/arm64/kvm/hyp/include/hyp/debug-sr.h
+++ b/arch/arm64/kvm/hyp/include/hyp/debug-sr.h
@@ -167,9 +167,6 @@ static inline void __debug_switch_to_host_common(struct kvm_vcpu *vcpu)
 
 	__debug_save_state(guest_dbg, guest_ctxt);
 	__debug_restore_state(host_dbg, host_ctxt);
-
-	if (has_vhe())
-		isb();
 }
 
 #endif /* __ARM64_KVM_HYP_DEBUG_SR_H__ */
diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c
index 32b4814eb2b7..477f1580ffea 100644
--- a/arch/arm64/kvm/hyp/vhe/switch.c
+++ b/arch/arm64/kvm/hyp/vhe/switch.c
@@ -558,10 +558,10 @@ static int __kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu)
 	host_ctxt = host_data_ptr(host_ctxt);
 	guest_ctxt = &vcpu->arch.ctxt;
 
-	sysreg_save_host_state_vhe(host_ctxt);
-
 	fpsimd_lazy_switch_to_guest(vcpu);
 
+	sysreg_save_host_state_vhe(host_ctxt);
+
 	/*
 	 * Note that ARM erratum 1165522 requires us to configure both stage 1
 	 * and stage 2 translation for the guest context before we clear
@@ -586,18 +586,23 @@ static int __kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu)
 
 	__deactivate_traps(vcpu);
 
-	/* Ensure CPTR trap deactivation has taken effect */
+	sysreg_restore_host_state_vhe(host_ctxt);
+
+	__debug_switch_to_host(vcpu);
+
+	/*
+	 * Ensure that all system register writes above have taken effect
+	 * before returning to the host. In VHE mode, CPTR traps for
+	 * FPSIMD/SVE/SME also apply to EL2, so FPSIMD/SVE/SME state must be
+	 * manipulated after the ISB.
+	 */
 	isb();
 
 	fpsimd_lazy_switch_to_host(vcpu);
 
-	sysreg_restore_host_state_vhe(host_ctxt);
-
 	if (guest_owns_fp_regs())
 		__fpsimd_save_fpexc32(vcpu);
 
-	__debug_switch_to_host(vcpu);
-
 	return exit_code;
 }
 NOKPROBE_SYMBOL(__kvm_vcpu_run_vhe);
@@ -627,12 +632,6 @@ int __kvm_vcpu_run(struct kvm_vcpu *vcpu)
 	 */
 	local_daif_restore(DAIF_PROCCTX_NOIRQ);
 
-	/*
-	 * When we exit from the guest we change a number of CPU configuration
-	 * parameters, such as traps.  We rely on the isb() in kvm_call_hyp*()
-	 * to make sure these changes take effect before running the host or
-	 * additional guests.
-	 */
 	return ret;
 }
 

From c769be2d3dbb165a3d432f4fcca2c80fabb35877 Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Thu, 22 May 2025 16:10:00 +0100
Subject: [PATCH 0610/1334] btrfs: include root in error message when unlinking
 inode

To help debugging include the root number in the error message, and since
this is a critical error that implies a metadata inconsistency and results
in a transaction abort change the log message level from "info" to
"critical", which is a much better fit.

Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/inode.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index c0c778243bf1..a62f92ab5977 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -4250,9 +4250,9 @@ static int __btrfs_unlink_inode(struct btrfs_trans_handle *trans,
 
 	ret = btrfs_del_inode_ref(trans, root, name, ino, dir_ino, &index);
 	if (ret) {
-		btrfs_info(fs_info,
-			"failed to delete reference to %.*s, inode %llu parent %llu",
-			name->len, name->name, ino, dir_ino);
+		btrfs_crit(fs_info,
+	   "failed to delete reference to %.*s, root %llu inode %llu parent %llu",
+			   name->len, name->name, btrfs_root_id(root), ino, dir_ino);
 		btrfs_abort_transaction(trans, ret);
 		goto err;
 	}

From dd276214e439db08f444fd3e07e9fe4c9e0ca210 Mon Sep 17 00:00:00 2001
From: Leo Martins <loemra.dev@gmail.com>
Date: Tue, 27 May 2025 17:04:21 -0700
Subject: [PATCH 0611/1334] btrfs: fix delayed ref refcount leak in debug
 assertion

If the delayed_root is not empty we are increasing the number of
references to a delayed_node without decreasing it, causing a leak.  Fix
by decrementing the delayed_node reference count.

Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Leo Martins <loemra.dev@gmail.com>
Reviewed-by: Qu Wenruo <wqu@suse.com>
[ Remove the changelog from the commit message. ]
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/delayed-inode.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
index c7cc24a5dd5e..8c597fa60523 100644
--- a/fs/btrfs/delayed-inode.c
+++ b/fs/btrfs/delayed-inode.c
@@ -1377,7 +1377,10 @@ static int btrfs_wq_run_delayed_node(struct btrfs_delayed_root *delayed_root,
 
 void btrfs_assert_delayed_root_empty(struct btrfs_fs_info *fs_info)
 {
-	WARN_ON(btrfs_first_delayed_node(fs_info->delayed_root));
+	struct btrfs_delayed_node *node = btrfs_first_delayed_node(fs_info->delayed_root);
+
+	if (WARN_ON(node))
+		refcount_dec(&node->refs);
 }
 
 static bool could_end_wait(struct btrfs_delayed_root *delayed_root, int seq)

From 186b9dc3c302ad706b3f23c857eb128165f6b484 Mon Sep 17 00:00:00 2001
From: Leo Martins <loemra.dev@gmail.com>
Date: Tue, 27 May 2025 17:04:22 -0700
Subject: [PATCH 0612/1334] btrfs: warn if leaking delayed_nodes in
 btrfs_put_root()

Add a warning for leaked delayed_nodes when putting a root. We currently
do this for inodes, but not delayed_nodes.

Signed-off-by: Leo Martins <loemra.dev@gmail.com>
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: Qu Wenruo <wqu@suse.com>
[ Remove the changelog from the commit message. ]
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/disk-io.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 1beb9458f622..3def93016963 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1835,6 +1835,8 @@ void btrfs_put_root(struct btrfs_root *root)
 	if (refcount_dec_and_test(&root->refs)) {
 		if (WARN_ON(!xa_empty(&root->inodes)))
 			xa_destroy(&root->inodes);
+		if (WARN_ON(!xa_empty(&root->delayed_nodes)))
+			xa_destroy(&root->delayed_nodes);
 		WARN_ON(test_bit(BTRFS_ROOT_DEAD_RELOC_TREE, &root->state));
 		if (root->anon_dev)
 			free_anon_bdev(root->anon_dev);

From 65d5112b4d7cf019ccb62cf40077038aae66239b Mon Sep 17 00:00:00 2001
From: Anand Jain <anand.jain@oracle.com>
Date: Tue, 20 May 2025 19:42:23 +0800
Subject: [PATCH 0613/1334] btrfs: scrub: add prefix for the error messages

Add a "scrub: " prefix to all messages logged by scrub so that it's
easy to filter them from dmesg for analysis.

Reviewed-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: Anand Jain <anand.jain@oracle.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/ioctl.c |  2 +-
 fs/btrfs/scrub.c | 53 ++++++++++++++++++++++++------------------------
 2 files changed, 27 insertions(+), 28 deletions(-)

diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index a498fe524c90..1e8f7082239c 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -3142,7 +3142,7 @@ static long btrfs_ioctl_scrub(struct file *file, void __user *arg)
 		return -EPERM;
 
 	if (btrfs_fs_incompat(fs_info, EXTENT_TREE_V2)) {
-		btrfs_err(fs_info, "scrub is not supported on extent tree v2 yet");
+		btrfs_err(fs_info, "scrub: extent tree v2 not yet supported");
 		return -EINVAL;
 	}
 
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index ed120621021b..94618add3b44 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -557,7 +557,7 @@ static int scrub_print_warning_inode(u64 inum, u64 offset, u64 num_bytes,
 	 */
 	for (i = 0; i < ipath->fspath->elem_cnt; ++i)
 		btrfs_warn_in_rcu(fs_info,
-"%s at logical %llu on dev %s, physical %llu, root %llu, inode %llu, offset %llu, length %u, links %u (path: %s)",
+"scrub: %s at logical %llu on dev %s, physical %llu root %llu inode %llu offset %llu length %u links %u (path: %s)",
 				  swarn->errstr, swarn->logical,
 				  btrfs_dev_name(swarn->dev),
 				  swarn->physical,
@@ -571,7 +571,7 @@ static int scrub_print_warning_inode(u64 inum, u64 offset, u64 num_bytes,
 
 err:
 	btrfs_warn_in_rcu(fs_info,
-			  "%s at logical %llu on dev %s, physical %llu, root %llu, inode %llu, offset %llu: path resolving failed with ret=%d",
+			  "scrub: %s at logical %llu on dev %s, physical %llu root %llu inode %llu offset %llu: path resolving failed with ret=%d",
 			  swarn->errstr, swarn->logical,
 			  btrfs_dev_name(swarn->dev),
 			  swarn->physical,
@@ -596,7 +596,7 @@ static void scrub_print_common_warning(const char *errstr, struct btrfs_device *
 
 	/* Super block error, no need to search extent tree. */
 	if (is_super) {
-		btrfs_warn_in_rcu(fs_info, "%s on device %s, physical %llu",
+		btrfs_warn_in_rcu(fs_info, "scrub: %s on device %s, physical %llu",
 				  errstr, btrfs_dev_name(dev), physical);
 		return;
 	}
@@ -631,14 +631,14 @@ static void scrub_print_common_warning(const char *errstr, struct btrfs_device *
 						      &ref_level);
 			if (ret < 0) {
 				btrfs_warn(fs_info,
-				"failed to resolve tree backref for logical %llu: %d",
-						  swarn.logical, ret);
+		   "scrub: failed to resolve tree backref for logical %llu: %d",
+					   swarn.logical, ret);
 				break;
 			}
 			if (ret > 0)
 				break;
 			btrfs_warn_in_rcu(fs_info,
-"%s at logical %llu on dev %s, physical %llu: metadata %s (level %d) in tree %llu",
+"scrub: %s at logical %llu on dev %s, physical %llu: metadata %s (level %d) in tree %llu",
 				errstr, swarn.logical, btrfs_dev_name(dev),
 				swarn.physical, (ref_level ? "node" : "leaf"),
 				ref_level, ref_root);
@@ -718,7 +718,7 @@ static void scrub_verify_one_metadata(struct scrub_stripe *stripe, int sector_nr
 		scrub_bitmap_set_meta_error(stripe, sector_nr, sectors_per_tree);
 		scrub_bitmap_set_error(stripe, sector_nr, sectors_per_tree);
 		btrfs_warn_rl(fs_info,
-		"tree block %llu mirror %u has bad bytenr, has %llu want %llu",
+	  "scrub: tree block %llu mirror %u has bad bytenr, has %llu want %llu",
 			      logical, stripe->mirror_num,
 			      btrfs_stack_header_bytenr(header), logical);
 		return;
@@ -728,7 +728,7 @@ static void scrub_verify_one_metadata(struct scrub_stripe *stripe, int sector_nr
 		scrub_bitmap_set_meta_error(stripe, sector_nr, sectors_per_tree);
 		scrub_bitmap_set_error(stripe, sector_nr, sectors_per_tree);
 		btrfs_warn_rl(fs_info,
-		"tree block %llu mirror %u has bad fsid, has %pU want %pU",
+	      "scrub: tree block %llu mirror %u has bad fsid, has %pU want %pU",
 			      logical, stripe->mirror_num,
 			      header->fsid, fs_info->fs_devices->fsid);
 		return;
@@ -738,7 +738,7 @@ static void scrub_verify_one_metadata(struct scrub_stripe *stripe, int sector_nr
 		scrub_bitmap_set_meta_error(stripe, sector_nr, sectors_per_tree);
 		scrub_bitmap_set_error(stripe, sector_nr, sectors_per_tree);
 		btrfs_warn_rl(fs_info,
-		"tree block %llu mirror %u has bad chunk tree uuid, has %pU want %pU",
+   "scrub: tree block %llu mirror %u has bad chunk tree uuid, has %pU want %pU",
 			      logical, stripe->mirror_num,
 			      header->chunk_tree_uuid, fs_info->chunk_tree_uuid);
 		return;
@@ -760,7 +760,7 @@ static void scrub_verify_one_metadata(struct scrub_stripe *stripe, int sector_nr
 		scrub_bitmap_set_meta_error(stripe, sector_nr, sectors_per_tree);
 		scrub_bitmap_set_error(stripe, sector_nr, sectors_per_tree);
 		btrfs_warn_rl(fs_info,
-		"tree block %llu mirror %u has bad csum, has " CSUM_FMT " want " CSUM_FMT,
+"scrub: tree block %llu mirror %u has bad csum, has " CSUM_FMT " want " CSUM_FMT,
 			      logical, stripe->mirror_num,
 			      CSUM_FMT_VALUE(fs_info->csum_size, on_disk_csum),
 			      CSUM_FMT_VALUE(fs_info->csum_size, calculated_csum));
@@ -771,7 +771,7 @@ static void scrub_verify_one_metadata(struct scrub_stripe *stripe, int sector_nr
 		scrub_bitmap_set_meta_gen_error(stripe, sector_nr, sectors_per_tree);
 		scrub_bitmap_set_error(stripe, sector_nr, sectors_per_tree);
 		btrfs_warn_rl(fs_info,
-		"tree block %llu mirror %u has bad generation, has %llu want %llu",
+      "scrub: tree block %llu mirror %u has bad generation, has %llu want %llu",
 			      logical, stripe->mirror_num,
 			      btrfs_stack_header_generation(header),
 			      stripe->sectors[sector_nr].generation);
@@ -814,7 +814,7 @@ static void scrub_verify_one_sector(struct scrub_stripe *stripe, int sector_nr)
 		 */
 		if (unlikely(sector_nr + sectors_per_tree > stripe->nr_sectors)) {
 			btrfs_warn_rl(fs_info,
-			"tree block at %llu crosses stripe boundary %llu",
+			"scrub: tree block at %llu crosses stripe boundary %llu",
 				      stripe->logical +
 				      (sector_nr << fs_info->sectorsize_bits),
 				      stripe->logical);
@@ -1046,12 +1046,12 @@ skip:
 		if (repaired) {
 			if (dev) {
 				btrfs_err_rl_in_rcu(fs_info,
-			"fixed up error at logical %llu on dev %s physical %llu",
+		"scrub: fixed up error at logical %llu on dev %s physical %llu",
 					    stripe->logical, btrfs_dev_name(dev),
 					    physical);
 			} else {
 				btrfs_err_rl_in_rcu(fs_info,
-			"fixed up error at logical %llu on mirror %u",
+			   "scrub: fixed up error at logical %llu on mirror %u",
 					    stripe->logical, stripe->mirror_num);
 			}
 			continue;
@@ -1060,12 +1060,12 @@ skip:
 		/* The remaining are all for unrepaired. */
 		if (dev) {
 			btrfs_err_rl_in_rcu(fs_info,
-	"unable to fixup (regular) error at logical %llu on dev %s physical %llu",
+"scrub: unable to fixup (regular) error at logical %llu on dev %s physical %llu",
 					    stripe->logical, btrfs_dev_name(dev),
 					    physical);
 		} else {
 			btrfs_err_rl_in_rcu(fs_info,
-	"unable to fixup (regular) error at logical %llu on mirror %u",
+	  "scrub: unable to fixup (regular) error at logical %llu on mirror %u",
 					    stripe->logical, stripe->mirror_num);
 		}
 
@@ -1593,8 +1593,7 @@ static int sync_write_pointer_for_zoned(struct scrub_ctx *sctx, u64 logical,
 						    physical,
 						    sctx->write_pointer);
 		if (ret)
-			btrfs_err(fs_info,
-				  "zoned: failed to recover write pointer");
+			btrfs_err(fs_info, "scrub: zoned: failed to recover write pointer");
 	}
 	mutex_unlock(&sctx->wr_lock);
 	btrfs_dev_clear_zone_empty(sctx->wr_tgtdev, physical);
@@ -1658,7 +1657,7 @@ static int scrub_find_fill_first_stripe(struct btrfs_block_group *bg,
 	int ret;
 
 	if (unlikely(!extent_root || !csum_root)) {
-		btrfs_err(fs_info, "no valid extent or csum root for scrub");
+		btrfs_err(fs_info, "scrub: no valid extent or csum root found");
 		return -EUCLEAN;
 	}
 	memset(stripe->sectors, 0, sizeof(struct scrub_sector_verification) *
@@ -1907,7 +1906,7 @@ static bool stripe_has_metadata_error(struct scrub_stripe *stripe)
 			struct btrfs_fs_info *fs_info = stripe->bg->fs_info;
 
 			btrfs_err(fs_info,
-			"stripe %llu has unrepaired metadata sector at %llu",
+		    "scrub: stripe %llu has unrepaired metadata sector at logical %llu",
 				  stripe->logical,
 				  stripe->logical + (i << fs_info->sectorsize_bits));
 			return true;
@@ -2167,7 +2166,7 @@ static int scrub_raid56_parity_stripe(struct scrub_ctx *sctx,
 		bitmap_and(&error, &error, &has_extent, stripe->nr_sectors);
 		if (!bitmap_empty(&error, stripe->nr_sectors)) {
 			btrfs_err(fs_info,
-"unrepaired sectors detected, full stripe %llu data stripe %u errors %*pbl",
+"scrub: unrepaired sectors detected, full stripe %llu data stripe %u errors %*pbl",
 				  full_stripe_start, i, stripe->nr_sectors,
 				  &error);
 			ret = -EIO;
@@ -2789,14 +2788,14 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx,
 			ro_set = 0;
 		} else if (ret == -ETXTBSY) {
 			btrfs_warn(fs_info,
-		   "skipping scrub of block group %llu due to active swapfile",
+	     "scrub: skipping scrub of block group %llu due to active swapfile",
 				   cache->start);
 			scrub_pause_off(fs_info);
 			ret = 0;
 			goto skip_unfreeze;
 		} else {
-			btrfs_warn(fs_info,
-				   "failed setting block group ro: %d", ret);
+			btrfs_warn(fs_info, "scrub: failed setting block group ro: %d",
+				   ret);
 			btrfs_unfreeze_block_group(cache);
 			btrfs_put_block_group(cache);
 			scrub_pause_off(fs_info);
@@ -2898,13 +2897,13 @@ static int scrub_one_super(struct scrub_ctx *sctx, struct btrfs_device *dev,
 	ret = btrfs_check_super_csum(fs_info, sb);
 	if (ret != 0) {
 		btrfs_err_rl(fs_info,
-			"super block at physical %llu devid %llu has bad csum",
+		  "scrub: super block at physical %llu devid %llu has bad csum",
 			physical, dev->devid);
 		return -EIO;
 	}
 	if (btrfs_super_generation(sb) != generation) {
 		btrfs_err_rl(fs_info,
-"super block at physical %llu devid %llu has bad generation %llu expect %llu",
+"scrub: super block at physical %llu devid %llu has bad generation %llu expect %llu",
 			     physical, dev->devid,
 			     btrfs_super_generation(sb), generation);
 		return -EUCLEAN;
@@ -3065,7 +3064,7 @@ int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start,
 	    !test_bit(BTRFS_DEV_STATE_WRITEABLE, &dev->dev_state)) {
 		mutex_unlock(&fs_info->fs_devices->device_list_mutex);
 		btrfs_err_in_rcu(fs_info,
-			"scrub on devid %llu: filesystem on %s is not writable",
+			"scrub: devid %llu: filesystem on %s is not writable",
 				 devid, btrfs_dev_name(dev));
 		ret = -EROFS;
 		goto out;

From 3ca864de852bc91007b32d2a0d48993724f4abad Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Wed, 28 May 2025 12:28:27 +0100
Subject: [PATCH 0614/1334] btrfs: fix a race between renames and directory
 logging

We have a race between a rename and directory inode logging that if it
happens and we crash/power fail before the rename completes, the next time
the filesystem is mounted, the log replay code will end up deleting the
file that was being renamed.

This is best explained following a step by step analysis of an interleaving
of steps that lead into this situation.

Consider the initial conditions:

1) We are at transaction N;

2) We have directories A and B created in a past transaction (< N);

3) We have inode X corresponding to a file that has 2 hardlinks, one in
   directory A and the other in directory B, so we'll name them as
   "A/foo_link1" and "B/foo_link2". Both hard links were persisted in a
   past transaction (< N);

4) We have inode Y corresponding to a file that as a single hard link and
   is located in directory A, we'll name it as "A/bar". This file was also
   persisted in a past transaction (< N).

The steps leading to a file loss are the following and for all of them we
are under transaction N:

 1) Link "A/foo_link1" is removed, so inode's X last_unlink_trans field
    is updated to N, through btrfs_unlink() -> btrfs_record_unlink_dir();

 2) Task A starts a rename for inode Y, with the goal of renaming from
    "A/bar" to "A/baz", so we enter btrfs_rename();

 3) Task A inserts the new BTRFS_INODE_REF_KEY for inode Y by calling
    btrfs_insert_inode_ref();

 4) Because the rename happens in the same directory, we don't set the
    last_unlink_trans field of directoty A's inode to the current
    transaction id, that is, we don't cal btrfs_record_unlink_dir();

 5) Task A then removes the entries from directory A (BTRFS_DIR_ITEM_KEY
    and BTRFS_DIR_INDEX_KEY items) when calling __btrfs_unlink_inode()
    (actually the dir index item is added as a delayed item, but the
    effect is the same);

 6) Now before task A adds the new entry "A/baz" to directory A by
    calling btrfs_add_link(), another task, task B is logging inode X;

 7) Task B starts a fsync of inode X and after logging inode X, at
    btrfs_log_inode_parent() it calls btrfs_log_all_parents(), since
    inode X has a last_unlink_trans value of N, set at in step 1;

 8) At btrfs_log_all_parents() we search for all parent directories of
    inode X using the commit root, so we find directories A and B and log
    them. Bu when logging direct A, we don't have a dir index item for
    inode Y anymore, neither the old name "A/bar" nor for the new name
    "A/baz" since the rename has deleted the old name but has not yet
    inserted the new name - task A hasn't called yet btrfs_add_link() to
    do that.

    Note that logging directory A doesn't fallback to a transaction
    commit because its last_unlink_trans has a lower value than the
    current transaction's id (see step 4);

 9) Task B finishes logging directories A and B and gets back to
    btrfs_sync_file() where it calls btrfs_sync_log() to persist the log
    tree;

10) Task B successfully persisted the log tree, btrfs_sync_log() completed
    with success, and a power failure happened.

    We have a log tree without any directory entry for inode Y, so the
    log replay code deletes the entry for inode Y, name "A/bar", from the
    subvolume tree since it doesn't exist in the log tree and the log
    tree is authorative for its index (we logged a BTRFS_DIR_LOG_INDEX_KEY
    item that covers the index range for the dentry that corresponds to
    "A/bar").

    Since there's no other hard link for inode Y and the log replay code
    deletes the name "A/bar", the file is lost.

The issue wouldn't happen if task B synced the log only after task A
called btrfs_log_new_name(), which would update the log with the new name
for inode Y ("A/bar").

Fix this by pinning the log root during renames before removing the old
directory entry, and unpinning after btrfs_log_new_name() is called.

Fixes: 259c4b96d78d ("btrfs: stop doing unnecessary log updates during a rename")
CC: stable@vger.kernel.org # 5.18+
Reviewed-by: Boris Burkov <boris@bur.io>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/inode.c | 83 +++++++++++++++++++++++++++++++++++++-----------
 1 file changed, 65 insertions(+), 18 deletions(-)

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index a62f92ab5977..26d6ed170a19 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -8059,6 +8059,7 @@ static int btrfs_rename_exchange(struct inode *old_dir,
 	int ret;
 	int ret2;
 	bool need_abort = false;
+	bool logs_pinned = false;
 	struct fscrypt_name old_fname, new_fname;
 	struct fscrypt_str *old_name, *new_name;
 
@@ -8182,6 +8183,31 @@ static int btrfs_rename_exchange(struct inode *old_dir,
 	inode_inc_iversion(new_inode);
 	simple_rename_timestamp(old_dir, old_dentry, new_dir, new_dentry);
 
+	if (old_ino != BTRFS_FIRST_FREE_OBJECTID &&
+	    new_ino != BTRFS_FIRST_FREE_OBJECTID) {
+		/*
+		 * If we are renaming in the same directory (and it's not for
+		 * root entries) pin the log early to prevent any concurrent
+		 * task from logging the directory after we removed the old
+		 * entries and before we add the new entries, otherwise that
+		 * task can sync a log without any entry for the inodes we are
+		 * renaming and therefore replaying that log, if a power failure
+		 * happens after syncing the log, would result in deleting the
+		 * inodes.
+		 *
+		 * If the rename affects two different directories, we want to
+		 * make sure the that there's no log commit that contains
+		 * updates for only one of the directories but not for the
+		 * other.
+		 *
+		 * If we are renaming an entry for a root, we don't care about
+		 * log updates since we called btrfs_set_log_full_commit().
+		 */
+		btrfs_pin_log_trans(root);
+		btrfs_pin_log_trans(dest);
+		logs_pinned = true;
+	}
+
 	if (old_dentry->d_parent != new_dentry->d_parent) {
 		btrfs_record_unlink_dir(trans, BTRFS_I(old_dir),
 					BTRFS_I(old_inode), true);
@@ -8253,30 +8279,23 @@ static int btrfs_rename_exchange(struct inode *old_dir,
 		BTRFS_I(new_inode)->dir_index = new_idx;
 
 	/*
-	 * Now pin the logs of the roots. We do it to ensure that no other task
-	 * can sync the logs while we are in progress with the rename, because
-	 * that could result in an inconsistency in case any of the inodes that
-	 * are part of this rename operation were logged before.
+	 * Do the log updates for all inodes.
+	 *
+	 * If either entry is for a root we don't need to update the logs since
+	 * we've called btrfs_set_log_full_commit() before.
 	 */
-	if (old_ino != BTRFS_FIRST_FREE_OBJECTID)
-		btrfs_pin_log_trans(root);
-	if (new_ino != BTRFS_FIRST_FREE_OBJECTID)
-		btrfs_pin_log_trans(dest);
-
-	/* Do the log updates for all inodes. */
-	if (old_ino != BTRFS_FIRST_FREE_OBJECTID)
+	if (logs_pinned) {
 		btrfs_log_new_name(trans, old_dentry, BTRFS_I(old_dir),
 				   old_rename_ctx.index, new_dentry->d_parent);
-	if (new_ino != BTRFS_FIRST_FREE_OBJECTID)
 		btrfs_log_new_name(trans, new_dentry, BTRFS_I(new_dir),
 				   new_rename_ctx.index, old_dentry->d_parent);
+	}
 
-	/* Now unpin the logs. */
-	if (old_ino != BTRFS_FIRST_FREE_OBJECTID)
-		btrfs_end_log_trans(root);
-	if (new_ino != BTRFS_FIRST_FREE_OBJECTID)
-		btrfs_end_log_trans(dest);
 out_fail:
+	if (logs_pinned) {
+		btrfs_end_log_trans(root);
+		btrfs_end_log_trans(dest);
+	}
 	ret2 = btrfs_end_transaction(trans);
 	ret = ret ? ret : ret2;
 out_notrans:
@@ -8326,6 +8345,7 @@ static int btrfs_rename(struct mnt_idmap *idmap,
 	int ret2;
 	u64 old_ino = btrfs_ino(BTRFS_I(old_inode));
 	struct fscrypt_name old_fname, new_fname;
+	bool logs_pinned = false;
 
 	if (btrfs_ino(BTRFS_I(new_dir)) == BTRFS_EMPTY_SUBVOL_DIR_OBJECTID)
 		return -EPERM;
@@ -8460,6 +8480,29 @@ static int btrfs_rename(struct mnt_idmap *idmap,
 	inode_inc_iversion(old_inode);
 	simple_rename_timestamp(old_dir, old_dentry, new_dir, new_dentry);
 
+	if (old_ino != BTRFS_FIRST_FREE_OBJECTID) {
+		/*
+		 * If we are renaming in the same directory (and it's not a
+		 * root entry) pin the log to prevent any concurrent task from
+		 * logging the directory after we removed the old entry and
+		 * before we add the new entry, otherwise that task can sync
+		 * a log without any entry for the inode we are renaming and
+		 * therefore replaying that log, if a power failure happens
+		 * after syncing the log, would result in deleting the inode.
+		 *
+		 * If the rename affects two different directories, we want to
+		 * make sure the that there's no log commit that contains
+		 * updates for only one of the directories but not for the
+		 * other.
+		 *
+		 * If we are renaming an entry for a root, we don't care about
+		 * log updates since we called btrfs_set_log_full_commit().
+		 */
+		btrfs_pin_log_trans(root);
+		btrfs_pin_log_trans(dest);
+		logs_pinned = true;
+	}
+
 	if (old_dentry->d_parent != new_dentry->d_parent)
 		btrfs_record_unlink_dir(trans, BTRFS_I(old_dir),
 					BTRFS_I(old_inode), true);
@@ -8524,7 +8567,7 @@ static int btrfs_rename(struct mnt_idmap *idmap,
 	if (old_inode->i_nlink == 1)
 		BTRFS_I(old_inode)->dir_index = index;
 
-	if (old_ino != BTRFS_FIRST_FREE_OBJECTID)
+	if (logs_pinned)
 		btrfs_log_new_name(trans, old_dentry, BTRFS_I(old_dir),
 				   rename_ctx.index, new_dentry->d_parent);
 
@@ -8540,6 +8583,10 @@ static int btrfs_rename(struct mnt_idmap *idmap,
 		}
 	}
 out_fail:
+	if (logs_pinned) {
+		btrfs_end_log_trans(root);
+		btrfs_end_log_trans(dest);
+	}
 	ret2 = btrfs_end_transaction(trans);
 	ret = ret ? ret : ret2;
 out_notrans:

From ae4477f937569d097ca5dbce92a89ba384b49bc6 Mon Sep 17 00:00:00 2001
From: Mark Harmstone <maharmstone@fb.com>
Date: Thu, 29 May 2025 10:37:44 +0100
Subject: [PATCH 0615/1334] btrfs: update superblock's device bytes_used when
 dropping chunk

Each superblock contains a copy of the device item for that device. In a
transaction which drops a chunk but doesn't create any new ones, we were
correctly updating the device item in the chunk tree but not copying
over the new bytes_used value to the superblock.

This can be seen by doing the following:

  # dd if=/dev/zero of=test bs=4096 count=2621440
  # mkfs.btrfs test
  # mount test /root/temp

  # cd /root/temp
  # for i in {00..10}; do dd if=/dev/zero of=$i bs=4096 count=32768; done
  # sync
  # rm *
  # sync
  # btrfs balance start -dusage=0 .
  # sync

  # cd
  # umount /root/temp
  # btrfs check test

For btrfs-check to detect this, you will also need my patch at
https://github.com/kdave/btrfs-progs/pull/991.

Change btrfs_remove_dev_extents() so that it adds the devices to the
fs_info->post_commit_list if they're not there already. This causes
btrfs_commit_device_sizes() to be called, which updates the bytes_used
value in the superblock.

Fixes: bbbf7243d62d ("btrfs: combine device update operations during transaction commit")
CC: stable@vger.kernel.org # 5.10+
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: Mark Harmstone <maharmstone@fb.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/volumes.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 89835071cfea..f475b4b7c457 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -3282,6 +3282,12 @@ int btrfs_remove_chunk(struct btrfs_trans_handle *trans, u64 chunk_offset)
 					device->bytes_used - dev_extent_len);
 			atomic64_add(dev_extent_len, &fs_info->free_chunk_space);
 			btrfs_clear_space_info_full(fs_info);
+
+			if (list_empty(&device->post_commit_list)) {
+				list_add_tail(&device->post_commit_list,
+					      &trans->transaction->dev_update_list);
+			}
+
 			mutex_unlock(&fs_info->chunk_mutex);
 		}
 	}

From e5b5596011773a38e035e9633ed928ef13c720b1 Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Tue, 3 Jun 2025 19:45:35 +0100
Subject: [PATCH 0616/1334] btrfs: fix double unlock of buffer_tree xarray when
 releasing subpage eb

If we break out of the loop because an extent buffer doesn't have the bit
EXTENT_BUFFER_TREE_REF set, we end up unlocking the xarray twice, once
before we tested for the bit and break out of the loop, and once again
after the loop.

Fix this by testing the bit and exiting before unlocking the xarray.
The time spent testing the bit is negligible and it's not worth trying
to do that outside the critical section delimited by the xarray lock due
to the code complexity required to avoid it (like using a local boolean
variable to track whether the xarray is locked or not). The xarray unlock
only needs to be done before calling release_extent_buffer(), as that
needs to lock the xarray (through xa_cmpxchg_irq()) and does a more
significant amount of work.

Fixes: 19d7f65f032f ("btrfs: convert the buffer_radix to an xarray")
Reported-by: Dan Carpenter <dan.carpenter@linaro.org>
Link: https://lore.kernel.org/linux-btrfs/aDRNDU0GM1_D4Xnw@stanley.mountain/
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/extent_io.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 849199768664..1dc931c4937f 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -4312,7 +4312,6 @@ static int try_release_subpage_extent_buffer(struct folio *folio)
 			spin_unlock(&eb->refs_lock);
 			continue;
 		}
-		xa_unlock_irq(&fs_info->buffer_tree);
 
 		/*
 		 * If tree ref isn't set then we know the ref on this eb is a
@@ -4329,6 +4328,7 @@ static int try_release_subpage_extent_buffer(struct folio *folio)
 		 * check the folio private at the end.  And
 		 * release_extent_buffer() will release the refs_lock.
 		 */
+		xa_unlock_irq(&fs_info->buffer_tree);
 		release_extent_buffer(eb);
 		xa_lock_irq(&fs_info->buffer_tree);
 	}

From 2dcf838cf5c2f0f4501edaa1680fcad03618d760 Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Tue, 3 Jun 2025 19:29:01 +0100
Subject: [PATCH 0617/1334] btrfs: fix invalid inode pointer dereferences
 during log replay

In a few places where we call read_one_inode(), if we get a NULL pointer
we end up jumping into an error path, or fallthrough in case of
__add_inode_ref(), where we then do something like this:

   iput(&inode->vfs_inode);

which results in an invalid inode pointer that triggers an invalid memory
access, resulting in a crash.

Fix this by making sure we don't do such dereferences.

Fixes: b4c50cbb01a1 ("btrfs: return a btrfs_inode from read_one_inode()")
CC: stable@vger.kernel.org # 6.15+
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/tree-log.c | 14 ++++++--------
 1 file changed, 6 insertions(+), 8 deletions(-)

diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 97e933113b82..21d2f3dded51 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -668,15 +668,12 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans,
 		extent_end = ALIGN(start + size,
 				   fs_info->sectorsize);
 	} else {
-		ret = 0;
-		goto out;
+		return 0;
 	}
 
 	inode = read_one_inode(root, key->objectid);
-	if (!inode) {
-		ret = -EIO;
-		goto out;
-	}
+	if (!inode)
+		return -EIO;
 
 	/*
 	 * first check to see if we already have this extent in the
@@ -961,7 +958,8 @@ static noinline int drop_one_dir_item(struct btrfs_trans_handle *trans,
 	ret = unlink_inode_for_log_replay(trans, dir, inode, &name);
 out:
 	kfree(name.name);
-	iput(&inode->vfs_inode);
+	if (inode)
+		iput(&inode->vfs_inode);
 	return ret;
 }
 
@@ -1176,8 +1174,8 @@ again:
 					ret = unlink_inode_for_log_replay(trans,
 							victim_parent,
 							inode, &victim_name);
+					iput(&victim_parent->vfs_inode);
 				}
-				iput(&victim_parent->vfs_inode);
 				kfree(victim_name.name);
 				if (ret)
 					return ret;

From 16edae52f60658caeaa0702e7cb6b738a09d4ad4 Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Tue, 3 Jun 2025 22:06:17 +0100
Subject: [PATCH 0618/1334] btrfs: don't silently ignore unexpected extent type
 when replaying log

If there's an unexpected (invalid) extent type, we just silently ignore
it. This means a corruption or some bug somewhere, so instead return
-EUCLEAN to the caller, making log replay fail, and print an error message
with relevant information.

Reviewed-by: Boris Burkov <boris@bur.io>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/tree-log.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 21d2f3dded51..858b609e292c 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -668,7 +668,10 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans,
 		extent_end = ALIGN(start + size,
 				   fs_info->sectorsize);
 	} else {
-		return 0;
+		btrfs_err(fs_info,
+		  "unexpected extent type=%d root=%llu inode=%llu offset=%llu",
+			  found_type, btrfs_root_id(root), key->objectid, key->offset);
+		return -EUCLEAN;
 	}
 
 	inode = read_one_inode(root, key->objectid);

From 1961d20f6fa8903266ed9bd77c691924c22c8f02 Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Thu, 5 Jun 2025 20:51:03 +0100
Subject: [PATCH 0619/1334] btrfs: fix assertion when building free space tree

When building the free space tree with the block group tree feature
enabled, we can hit an assertion failure like this:

  BTRFS info (device loop0 state M): rebuilding free space tree
  assertion failed: ret == 0, in fs/btrfs/free-space-tree.c:1102
  ------------[ cut here ]------------
  kernel BUG at fs/btrfs/free-space-tree.c:1102!
  Internal error: Oops - BUG: 00000000f2000800 [#1]  SMP
  Modules linked in:
  CPU: 1 UID: 0 PID: 6592 Comm: syz-executor322 Not tainted 6.15.0-rc7-syzkaller-gd7fa1af5b33e #0 PREEMPT
  Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 05/07/2025
  pstate: 60400005 (nZCv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--)
  pc : populate_free_space_tree+0x514/0x518 fs/btrfs/free-space-tree.c:1102
  lr : populate_free_space_tree+0x514/0x518 fs/btrfs/free-space-tree.c:1102
  sp : ffff8000a4ce7600
  x29: ffff8000a4ce76e0 x28: ffff0000c9bc6000 x27: ffff0000ddfff3d8
  x26: ffff0000ddfff378 x25: dfff800000000000 x24: 0000000000000001
  x23: ffff8000a4ce7660 x22: ffff70001499cecc x21: ffff0000e1d8c160
  x20: ffff0000e1cb7800 x19: ffff0000e1d8c0b0 x18: 00000000ffffffff
  x17: ffff800092f39000 x16: ffff80008ad27e48 x15: ffff700011e740c0
  x14: 1ffff00011e740c0 x13: 0000000000000004 x12: ffffffffffffffff
  x11: ffff700011e740c0 x10: 0000000000ff0100 x9 : 94ef24f55d2dbc00
  x8 : 94ef24f55d2dbc00 x7 : 0000000000000001 x6 : 0000000000000001
  x5 : ffff8000a4ce6f98 x4 : ffff80008f415ba0 x3 : ffff800080548ef0
  x2 : 0000000000000000 x1 : 0000000100000000 x0 : 000000000000003e
  Call trace:
   populate_free_space_tree+0x514/0x518 fs/btrfs/free-space-tree.c:1102 (P)
   btrfs_rebuild_free_space_tree+0x14c/0x54c fs/btrfs/free-space-tree.c:1337
   btrfs_start_pre_rw_mount+0xa78/0xe10 fs/btrfs/disk-io.c:3074
   btrfs_remount_rw fs/btrfs/super.c:1319 [inline]
   btrfs_reconfigure+0x828/0x2418 fs/btrfs/super.c:1543
   reconfigure_super+0x1d4/0x6f0 fs/super.c:1083
   do_remount fs/namespace.c:3365 [inline]
   path_mount+0xb34/0xde0 fs/namespace.c:4200
   do_mount fs/namespace.c:4221 [inline]
   __do_sys_mount fs/namespace.c:4432 [inline]
   __se_sys_mount fs/namespace.c:4409 [inline]
   __arm64_sys_mount+0x3e8/0x468 fs/namespace.c:4409
   __invoke_syscall arch/arm64/kernel/syscall.c:35 [inline]
   invoke_syscall+0x98/0x2b8 arch/arm64/kernel/syscall.c:49
   el0_svc_common+0x130/0x23c arch/arm64/kernel/syscall.c:132
   do_el0_svc+0x48/0x58 arch/arm64/kernel/syscall.c:151
   el0_svc+0x58/0x17c arch/arm64/kernel/entry-common.c:767
   el0t_64_sync_handler+0x78/0x108 arch/arm64/kernel/entry-common.c:786
   el0t_64_sync+0x198/0x19c arch/arm64/kernel/entry.S:600
  Code: f0047182 91178042 528089c3 9771d47b (d4210000)
  ---[ end trace 0000000000000000 ]---

This happens because we are processing an empty block group, which has
no extents allocated from it, there are no items for this block group,
including the block group item since block group items are stored in a
dedicated tree when using the block group tree feature. It also means
this is the block group with the highest start offset, so there are no
higher keys in the extent root, hence btrfs_search_slot_for_read()
returns 1 (no higher key found).

Fix this by asserting 'ret' is 0 only if the block group tree feature
is not enabled, in which case we should find a block group item for
the block group since it's stored in the extent root and block group
item keys are greater than extent item keys (the value for
BTRFS_BLOCK_GROUP_ITEM_KEY is 192 and for BTRFS_EXTENT_ITEM_KEY and
BTRFS_METADATA_ITEM_KEY the values are 168 and 169 respectively).
In case 'ret' is 1, we just need to add a record to the free space
tree which spans the whole block group, and we can achieve this by
making 'ret == 0' as the while loop's condition.

Reported-by: syzbot+36fae25c35159a763a2a@syzkaller.appspotmail.com
Link: https://lore.kernel.org/linux-btrfs/6841dca8.a00a0220.d4325.0020.GAE@google.com/
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/free-space-tree.c | 16 ++++++++++++----
 1 file changed, 12 insertions(+), 4 deletions(-)

diff --git a/fs/btrfs/free-space-tree.c b/fs/btrfs/free-space-tree.c
index 0c573d46639a..a3e2a2a81461 100644
--- a/fs/btrfs/free-space-tree.c
+++ b/fs/btrfs/free-space-tree.c
@@ -1115,11 +1115,21 @@ static int populate_free_space_tree(struct btrfs_trans_handle *trans,
 	ret = btrfs_search_slot_for_read(extent_root, &key, path, 1, 0);
 	if (ret < 0)
 		goto out_locked;
-	ASSERT(ret == 0);
+	/*
+	 * If ret is 1 (no key found), it means this is an empty block group,
+	 * without any extents allocated from it and there's no block group
+	 * item (key BTRFS_BLOCK_GROUP_ITEM_KEY) located in the extent tree
+	 * because we are using the block group tree feature, so block group
+	 * items are stored in the block group tree. It also means there are no
+	 * extents allocated for block groups with a start offset beyond this
+	 * block group's end offset (this is the last, highest, block group).
+	 */
+	if (!btrfs_fs_compat_ro(trans->fs_info, BLOCK_GROUP_TREE))
+		ASSERT(ret == 0);
 
 	start = block_group->start;
 	end = block_group->start + block_group->length;
-	while (1) {
+	while (ret == 0) {
 		btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]);
 
 		if (key.type == BTRFS_EXTENT_ITEM_KEY ||
@@ -1149,8 +1159,6 @@ static int populate_free_space_tree(struct btrfs_trans_handle *trans,
 		ret = btrfs_next_item(extent_root, path);
 		if (ret < 0)
 			goto out_locked;
-		if (ret)
-			break;
 	}
 	if (start < end) {
 		ret = __add_to_free_space_tree(trans, block_group, path2,

From a26bf338cdad3643a6e7c3d78a172baadba15c1a Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Wed, 4 Jun 2025 16:54:44 +0100
Subject: [PATCH 0620/1334] btrfs: fix race between async reclaim worker and
 close_ctree()

Syzbot reported an assertion failure due to an attempt to add a delayed
iput after we have set BTRFS_FS_STATE_NO_DELAYED_IPUT in the fs_info
state:

  WARNING: CPU: 0 PID: 65 at fs/btrfs/inode.c:3420 btrfs_add_delayed_iput+0x2f8/0x370 fs/btrfs/inode.c:3420
  Modules linked in:
  CPU: 0 UID: 0 PID: 65 Comm: kworker/u8:4 Not tainted 6.15.0-next-20250530-syzkaller #0 PREEMPT(full)
  Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 05/07/2025
  Workqueue: btrfs-endio-write btrfs_work_helper
  RIP: 0010:btrfs_add_delayed_iput+0x2f8/0x370 fs/btrfs/inode.c:3420
  Code: 4e ad 5d (...)
  RSP: 0018:ffffc9000213f780 EFLAGS: 00010293
  RAX: ffffffff83c635b7 RBX: ffff888058920000 RCX: ffff88801c769e00
  RDX: 0000000000000000 RSI: 0000000000000100 RDI: 0000000000000000
  RBP: 0000000000000001 R08: ffff888058921b67 R09: 1ffff1100b12436c
  R10: dffffc0000000000 R11: ffffed100b12436d R12: 0000000000000001
  R13: dffffc0000000000 R14: ffff88807d748000 R15: 0000000000000100
  FS:  0000000000000000(0000) GS:ffff888125c53000(0000) knlGS:0000000000000000
  CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
  CR2: 00002000000bd038 CR3: 000000006a142000 CR4: 00000000003526f0
  DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
  DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
  Call Trace:
   <TASK>
   btrfs_put_ordered_extent+0x19f/0x470 fs/btrfs/ordered-data.c:635
   btrfs_finish_one_ordered+0x11d8/0x1b10 fs/btrfs/inode.c:3312
   btrfs_work_helper+0x399/0xc20 fs/btrfs/async-thread.c:312
   process_one_work kernel/workqueue.c:3238 [inline]
   process_scheduled_works+0xae1/0x17b0 kernel/workqueue.c:3321
   worker_thread+0x8a0/0xda0 kernel/workqueue.c:3402
   kthread+0x70e/0x8a0 kernel/kthread.c:464
   ret_from_fork+0x3fc/0x770 arch/x86/kernel/process.c:148
   ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:245
   </TASK>

This can happen due to a race with the async reclaim worker like this:

1) The async metadata reclaim worker enters shrink_delalloc(), which calls
   btrfs_start_delalloc_roots() with an nr_pages argument that has a value
   less than LONG_MAX, and that in turn enters start_delalloc_inodes(),
   which sets the local variable 'full_flush' to false because
   wbc->nr_to_write is less than LONG_MAX;

2) There it finds inode X in a root's delalloc list, grabs a reference for
   inode X (with igrab()), and triggers writeback for it with
   filemap_fdatawrite_wbc(), which creates an ordered extent for inode X;

3) The unmount sequence starts from another task, we enter close_ctree()
   and we flush the workqueue fs_info->endio_write_workers, which waits
   for the ordered extent for inode X to complete and when dropping the
   last reference of the ordered extent, with btrfs_put_ordered_extent(),
   when we call btrfs_add_delayed_iput() we don't add the inode to the
   list of delayed iputs because it has a refcount of 2, so we decrement
   it to 1 and return;

4) Shortly after at close_ctree() we call btrfs_run_delayed_iputs() which
   runs all delayed iputs, and then we set BTRFS_FS_STATE_NO_DELAYED_IPUT
   in the fs_info state;

5) The async reclaim worker, after calling filemap_fdatawrite_wbc(), now
   calls btrfs_add_delayed_iput() for inode X and there we trigger an
   assertion failure since the fs_info state has the flag
   BTRFS_FS_STATE_NO_DELAYED_IPUT set.

Fix this by setting BTRFS_FS_STATE_NO_DELAYED_IPUT only after we wait for
the async reclaim workers to finish, after we call cancel_work_sync() for
them at close_ctree(), and by running delayed iputs after wait for the
reclaim workers to finish and before setting the bit.

This race was recently introduced by commit 19e60b2a95f5 ("btrfs: add
extra warning if delayed iput is added when it's not allowed"). Without
the new validation at btrfs_add_delayed_iput(), this described scenario
was safe because close_ctree() later calls btrfs_commit_super(). That
will run any final delayed iputs added by reclaim workers in the window
between the btrfs_run_delayed_iputs() and the the reclaim workers being
shut down.

Reported-by: syzbot+0ed30ad435bf6f5b7a42@syzkaller.appspotmail.com
Link: https://lore.kernel.org/linux-btrfs/6840481c.a00a0220.d4325.000c.GAE@google.com/T/#u
Fixes: 19e60b2a95f5 ("btrfs: add extra warning if delayed iput is added when it's not allowed")
Reviewed-by: Boris Burkov <boris@bur.io>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/disk-io.c | 22 ++++++++++++++++++----
 1 file changed, 18 insertions(+), 4 deletions(-)

diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 3def93016963..f48f9d924a62 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -4312,8 +4312,8 @@ void __cold close_ctree(struct btrfs_fs_info *fs_info)
 	 *
 	 * So wait for all ongoing ordered extents to complete and then run
 	 * delayed iputs. This works because once we reach this point no one
-	 * can either create new ordered extents nor create delayed iputs
-	 * through some other means.
+	 * can create new ordered extents, but delayed iputs can still be added
+	 * by a reclaim worker (see comments further below).
 	 *
 	 * Also note that btrfs_wait_ordered_roots() is not safe here, because
 	 * it waits for BTRFS_ORDERED_COMPLETE to be set on an ordered extent,
@@ -4324,15 +4324,29 @@ void __cold close_ctree(struct btrfs_fs_info *fs_info)
 	btrfs_flush_workqueue(fs_info->endio_write_workers);
 	/* Ordered extents for free space inodes. */
 	btrfs_flush_workqueue(fs_info->endio_freespace_worker);
+	/*
+	 * Run delayed iputs in case an async reclaim worker is waiting for them
+	 * to be run as mentioned above.
+	 */
 	btrfs_run_delayed_iputs(fs_info);
-	/* There should be no more workload to generate new delayed iputs. */
-	set_bit(BTRFS_FS_STATE_NO_DELAYED_IPUT, &fs_info->fs_state);
 
 	cancel_work_sync(&fs_info->async_reclaim_work);
 	cancel_work_sync(&fs_info->async_data_reclaim_work);
 	cancel_work_sync(&fs_info->preempt_reclaim_work);
 	cancel_work_sync(&fs_info->em_shrinker_work);
 
+	/*
+	 * Run delayed iputs again because an async reclaim worker may have
+	 * added new ones if it was flushing delalloc:
+	 *
+	 * shrink_delalloc() -> btrfs_start_delalloc_roots() ->
+	 *    start_delalloc_inodes() -> btrfs_add_delayed_iput()
+	 */
+	btrfs_run_delayed_iputs(fs_info);
+
+	/* There should be no more workload to generate new delayed iputs. */
+	set_bit(BTRFS_FS_STATE_NO_DELAYED_IPUT, &fs_info->fs_state);
+
 	/* Cancel or finish ongoing discard work */
 	btrfs_discard_cleanup(fs_info);
 

From 547e836661554dcfa15c212a3821664e85b4191a Mon Sep 17 00:00:00 2001
From: Qu Wenruo <wqu@suse.com>
Date: Sat, 7 Jun 2025 09:18:43 +0930
Subject: [PATCH 0621/1334] btrfs: handle csum tree error with rescue=ibadroots
 correctly

[BUG]
There is syzbot based reproducer that can crash the kernel, with the
following call trace: (With some debug output added)

 DEBUG: rescue=ibadroots parsed
 BTRFS: device fsid 14d642db-7b15-43e4-81e6-4b8fac6a25f8 devid 1 transid 8 /dev/loop0 (7:0) scanned by repro (1010)
 BTRFS info (device loop0): first mount of filesystem 14d642db-7b15-43e4-81e6-4b8fac6a25f8
 BTRFS info (device loop0): using blake2b (blake2b-256-generic) checksum algorithm
 BTRFS info (device loop0): using free-space-tree
 BTRFS warning (device loop0): checksum verify failed on logical 5312512 mirror 1 wanted 0xb043382657aede36608fd3386d6b001692ff406164733d94e2d9a180412c6003 found 0x810ceb2bacb7f0f9eb2bf3b2b15c02af867cb35ad450898169f3b1f0bd818651 level 0
 DEBUG: read tree root path failed for tree csum, ret=-5
 BTRFS warning (device loop0): checksum verify failed on logical 5328896 mirror 1 wanted 0x51be4e8b303da58e6340226815b70e3a93592dac3f30dd510c7517454de8567a found 0x51be4e8b303da58e634022a315b70e3a93592dac3f30dd510c7517454de8567a level 0
 BTRFS warning (device loop0): checksum verify failed on logical 5292032 mirror 1 wanted 0x1924ccd683be9efc2fa98582ef58760e3848e9043db8649ee382681e220cdee4 found 0x0cb6184f6e8799d9f8cb335dccd1d1832da1071d12290dab3b85b587ecacca6e level 0
 process 'repro' launched './file2' with NULL argv: empty string added
 DEBUG: no csum root, idatacsums=0 ibadroots=134217728
 Oops: general protection fault, probably for non-canonical address 0xdffffc0000000041: 0000 [#1] SMP KASAN NOPTI
 KASAN: null-ptr-deref in range [0x0000000000000208-0x000000000000020f]
 CPU: 5 UID: 0 PID: 1010 Comm: repro Tainted: G           OE       6.15.0-custom+ #249 PREEMPT(full)
 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS unknown 02/02/2022
 RIP: 0010:btrfs_lookup_csum+0x93/0x3d0 [btrfs]
 Call Trace:
  <TASK>
  btrfs_lookup_bio_sums+0x47a/0xdf0 [btrfs]
  btrfs_submit_bbio+0x43e/0x1a80 [btrfs]
  submit_one_bio+0xde/0x160 [btrfs]
  btrfs_readahead+0x498/0x6a0 [btrfs]
  read_pages+0x1c3/0xb20
  page_cache_ra_order+0x4b5/0xc20
  filemap_get_pages+0x2d3/0x19e0
  filemap_read+0x314/0xde0
  __kernel_read+0x35b/0x900
  bprm_execve+0x62e/0x1140
  do_execveat_common.isra.0+0x3fc/0x520
  __x64_sys_execveat+0xdc/0x130
  do_syscall_64+0x54/0x1d0
  entry_SYSCALL_64_after_hwframe+0x76/0x7e
 ---[ end trace 0000000000000000 ]---

[CAUSE]
Firstly the fs has a corrupted csum tree root, thus to mount the fs we
have to go "ro,rescue=ibadroots" mount option.

Normally with that mount option, a bad csum tree root should set
BTRFS_FS_STATE_NO_DATA_CSUMS flag, so that any future data read will
ignore csum search.

But in this particular case, we have the following call trace that
caused NULL csum root, but not setting BTRFS_FS_STATE_NO_DATA_CSUMS:

load_global_roots_objectid():

		ret = btrfs_search_slot();
		/* Succeeded */
		btrfs_item_key_to_cpu()
		found = true;
		/* We found the root item for csum tree. */
		root = read_tree_root_path();
		if (IS_ERR(root)) {
			if (!btrfs_test_opt(fs_info, IGNOREBADROOTS))
			/*
			 * Since we have rescue=ibadroots mount option,
			 * @ret is still 0.
			 */
			break;
	if (!found || ret) {
		/* @found is true, @ret is 0, error handling for csum
		 * tree is skipped.
		 */
	}

This means we completely skipped to set BTRFS_FS_STATE_NO_DATA_CSUMS if
the csum tree is corrupted, which results unexpected later csum lookup.

[FIX]
If read_tree_root_path() failed, always populate @ret to the error
number.

As at the end of the function, we need @ret to determine if we need to
do the extra error handling for csum tree.

Fixes: abed4aaae4f7 ("btrfs: track the csum, extent, and free space trees in a rb tree")
Reported-by: Zhiyu Zhang <zhiyuzhang999@gmail.com>
Reported-by: Longxing Li <coregee2000@gmail.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/disk-io.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index f48f9d924a62..0d6ad7512f21 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -2158,8 +2158,7 @@ static int load_global_roots_objectid(struct btrfs_root *tree_root,
 		found = true;
 		root = read_tree_root_path(tree_root, path, &key);
 		if (IS_ERR(root)) {
-			if (!btrfs_test_opt(fs_info, IGNOREBADROOTS))
-				ret = PTR_ERR(root);
+			ret = PTR_ERR(root);
 			break;
 		}
 		set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state);

From c0d90a79e8e65b89037508276b2b31f41a1b3783 Mon Sep 17 00:00:00 2001
From: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Date: Fri, 6 Jun 2025 09:17:41 +0200
Subject: [PATCH 0622/1334] btrfs: zoned: fix alloc_offset calculation for
 partly conventional block groups

When one of two zones composing a DUP block group is a conventional zone,
we have the zone_info[i]->alloc_offset = WP_CONVENTIONAL. That will, of
course, not match the write pointer of the other zone, and fails that
block group.

This commit solves that issue by properly recovering the emulated write
pointer from the last allocated extent. The offset for the SINGLE, DUP,
and RAID1 are straight-forward: it is same as the end of last allocated
extent. The RAID0 and RAID10 are a bit tricky that we need to do the math
of striping.

This is the kernel equivalent of Naohiro's user-space commit:
"btrfs-progs: zoned: fix alloc_offset calculation for partly
conventional block groups".

Reviewed-by: Naohiro Aota <naohiro.aota@wdc.com>
Signed-off-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/zoned.c | 86 ++++++++++++++++++++++++++++++++++++++++--------
 1 file changed, 72 insertions(+), 14 deletions(-)

diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c
index b5b0156d5b95..9430b34d3cbb 100644
--- a/fs/btrfs/zoned.c
+++ b/fs/btrfs/zoned.c
@@ -1403,7 +1403,8 @@ static int btrfs_load_block_group_single(struct btrfs_block_group *bg,
 static int btrfs_load_block_group_dup(struct btrfs_block_group *bg,
 				      struct btrfs_chunk_map *map,
 				      struct zone_info *zone_info,
-				      unsigned long *active)
+				      unsigned long *active,
+				      u64 last_alloc)
 {
 	struct btrfs_fs_info *fs_info = bg->fs_info;
 
@@ -1426,6 +1427,13 @@ static int btrfs_load_block_group_dup(struct btrfs_block_group *bg,
 			  zone_info[1].physical);
 		return -EIO;
 	}
+
+	if (zone_info[0].alloc_offset == WP_CONVENTIONAL)
+		zone_info[0].alloc_offset = last_alloc;
+
+	if (zone_info[1].alloc_offset == WP_CONVENTIONAL)
+		zone_info[1].alloc_offset = last_alloc;
+
 	if (zone_info[0].alloc_offset != zone_info[1].alloc_offset) {
 		btrfs_err(bg->fs_info,
 			  "zoned: write pointer offset mismatch of zones in DUP profile");
@@ -1446,7 +1454,8 @@ static int btrfs_load_block_group_dup(struct btrfs_block_group *bg,
 static int btrfs_load_block_group_raid1(struct btrfs_block_group *bg,
 					struct btrfs_chunk_map *map,
 					struct zone_info *zone_info,
-					unsigned long *active)
+					unsigned long *active,
+					u64 last_alloc)
 {
 	struct btrfs_fs_info *fs_info = bg->fs_info;
 	int i;
@@ -1461,10 +1470,12 @@ static int btrfs_load_block_group_raid1(struct btrfs_block_group *bg,
 	bg->zone_capacity = min_not_zero(zone_info[0].capacity, zone_info[1].capacity);
 
 	for (i = 0; i < map->num_stripes; i++) {
-		if (zone_info[i].alloc_offset == WP_MISSING_DEV ||
-		    zone_info[i].alloc_offset == WP_CONVENTIONAL)
+		if (zone_info[i].alloc_offset == WP_MISSING_DEV)
 			continue;
 
+		if (zone_info[i].alloc_offset == WP_CONVENTIONAL)
+			zone_info[i].alloc_offset = last_alloc;
+
 		if ((zone_info[0].alloc_offset != zone_info[i].alloc_offset) &&
 		    !btrfs_test_opt(fs_info, DEGRADED)) {
 			btrfs_err(fs_info,
@@ -1494,7 +1505,8 @@ static int btrfs_load_block_group_raid1(struct btrfs_block_group *bg,
 static int btrfs_load_block_group_raid0(struct btrfs_block_group *bg,
 					struct btrfs_chunk_map *map,
 					struct zone_info *zone_info,
-					unsigned long *active)
+					unsigned long *active,
+					u64 last_alloc)
 {
 	struct btrfs_fs_info *fs_info = bg->fs_info;
 
@@ -1505,10 +1517,29 @@ static int btrfs_load_block_group_raid0(struct btrfs_block_group *bg,
 	}
 
 	for (int i = 0; i < map->num_stripes; i++) {
-		if (zone_info[i].alloc_offset == WP_MISSING_DEV ||
-		    zone_info[i].alloc_offset == WP_CONVENTIONAL)
+		if (zone_info[i].alloc_offset == WP_MISSING_DEV)
 			continue;
 
+		if (zone_info[i].alloc_offset == WP_CONVENTIONAL) {
+			u64 stripe_nr, full_stripe_nr;
+			u64 stripe_offset;
+			int stripe_index;
+
+			stripe_nr = div64_u64(last_alloc, map->stripe_size);
+			stripe_offset = stripe_nr * map->stripe_size;
+			full_stripe_nr = div_u64(stripe_nr, map->num_stripes);
+			div_u64_rem(stripe_nr, map->num_stripes, &stripe_index);
+
+			zone_info[i].alloc_offset =
+				full_stripe_nr * map->stripe_size;
+
+			if (stripe_index > i)
+				zone_info[i].alloc_offset += map->stripe_size;
+			else if (stripe_index == i)
+				zone_info[i].alloc_offset +=
+					(last_alloc - stripe_offset);
+		}
+
 		if (test_bit(0, active) != test_bit(i, active)) {
 			if (!btrfs_zone_activate(bg))
 				return -EIO;
@@ -1526,7 +1557,8 @@ static int btrfs_load_block_group_raid0(struct btrfs_block_group *bg,
 static int btrfs_load_block_group_raid10(struct btrfs_block_group *bg,
 					 struct btrfs_chunk_map *map,
 					 struct zone_info *zone_info,
-					 unsigned long *active)
+					 unsigned long *active,
+					 u64 last_alloc)
 {
 	struct btrfs_fs_info *fs_info = bg->fs_info;
 
@@ -1537,8 +1569,7 @@ static int btrfs_load_block_group_raid10(struct btrfs_block_group *bg,
 	}
 
 	for (int i = 0; i < map->num_stripes; i++) {
-		if (zone_info[i].alloc_offset == WP_MISSING_DEV ||
-		    zone_info[i].alloc_offset == WP_CONVENTIONAL)
+		if (zone_info[i].alloc_offset == WP_MISSING_DEV)
 			continue;
 
 		if (test_bit(0, active) != test_bit(i, active)) {
@@ -1549,6 +1580,29 @@ static int btrfs_load_block_group_raid10(struct btrfs_block_group *bg,
 				set_bit(BLOCK_GROUP_FLAG_ZONE_IS_ACTIVE, &bg->runtime_flags);
 		}
 
+		if (zone_info[i].alloc_offset == WP_CONVENTIONAL) {
+			u64 stripe_nr, full_stripe_nr;
+			u64 stripe_offset;
+			int stripe_index;
+
+			stripe_nr = div64_u64(last_alloc, map->stripe_size);
+			stripe_offset = stripe_nr * map->stripe_size;
+			full_stripe_nr = div_u64(stripe_nr,
+					 map->num_stripes / map->sub_stripes);
+			div_u64_rem(stripe_nr,
+				    (map->num_stripes / map->sub_stripes),
+				    &stripe_index);
+
+			zone_info[i].alloc_offset =
+				full_stripe_nr * map->stripe_size;
+
+			if (stripe_index > (i / map->sub_stripes))
+				zone_info[i].alloc_offset += map->stripe_size;
+			else if (stripe_index == (i / map->sub_stripes))
+				zone_info[i].alloc_offset +=
+					(last_alloc - stripe_offset);
+		}
+
 		if ((i % map->sub_stripes) == 0) {
 			bg->zone_capacity += zone_info[i].capacity;
 			bg->alloc_offset += zone_info[i].alloc_offset;
@@ -1637,18 +1691,22 @@ int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new)
 		ret = btrfs_load_block_group_single(cache, &zone_info[0], active);
 		break;
 	case BTRFS_BLOCK_GROUP_DUP:
-		ret = btrfs_load_block_group_dup(cache, map, zone_info, active);
+		ret = btrfs_load_block_group_dup(cache, map, zone_info, active,
+						 last_alloc);
 		break;
 	case BTRFS_BLOCK_GROUP_RAID1:
 	case BTRFS_BLOCK_GROUP_RAID1C3:
 	case BTRFS_BLOCK_GROUP_RAID1C4:
-		ret = btrfs_load_block_group_raid1(cache, map, zone_info, active);
+		ret = btrfs_load_block_group_raid1(cache, map, zone_info,
+						   active, last_alloc);
 		break;
 	case BTRFS_BLOCK_GROUP_RAID0:
-		ret = btrfs_load_block_group_raid0(cache, map, zone_info, active);
+		ret = btrfs_load_block_group_raid0(cache, map, zone_info,
+						   active, last_alloc);
 		break;
 	case BTRFS_BLOCK_GROUP_RAID10:
-		ret = btrfs_load_block_group_raid10(cache, map, zone_info, active);
+		ret = btrfs_load_block_group_raid10(cache, map, zone_info,
+						    active, last_alloc);
 		break;
 	case BTRFS_BLOCK_GROUP_RAID5:
 	case BTRFS_BLOCK_GROUP_RAID6:

From e353b0854d3a1a31cb061df8d022fbfea53a0f24 Mon Sep 17 00:00:00 2001
From: Alexey Kodanev <aleksei.kodanev@bell-sw.com>
Date: Mon, 16 Jun 2025 11:37:43 +0000
Subject: [PATCH 0623/1334] net: lan743x: fix potential out-of-bounds write in
 lan743x_ptp_io_event_clock_get()

Before calling lan743x_ptp_io_event_clock_get(), the 'channel' value
is checked against the maximum value of PCI11X1X_PTP_IO_MAX_CHANNELS(8).
This seems correct and aligns with the PTP interrupt status register
(PTP_INT_STS) specifications.

However, lan743x_ptp_io_event_clock_get() writes to ptp->extts[] with
only LAN743X_PTP_N_EXTTS(4) elements, using channel as an index:

    lan743x_ptp_io_event_clock_get(..., u8 channel,...)
    {
        ...
        /* Update Local timestamp */
        extts = &ptp->extts[channel];
        extts->ts.tv_sec = sec;
        ...
    }

To avoid an out-of-bounds write and utilize all the supported GPIO
inputs, set LAN743X_PTP_N_EXTTS to 8.

Detected using the static analysis tool - Svace.
Fixes: 60942c397af6 ("net: lan743x: Add support for PTP-IO Event Input External Timestamp (extts)")
Signed-off-by: Alexey Kodanev <aleksei.kodanev@bell-sw.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Acked-by: Rengarajan S <rengarajan.s@microchip.com>
Link: https://patch.msgid.link/20250616113743.36284-1-aleksei.kodanev@bell-sw.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/microchip/lan743x_ptp.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/microchip/lan743x_ptp.h b/drivers/net/ethernet/microchip/lan743x_ptp.h
index e8d073bfa2ca..f33dc83c5700 100644
--- a/drivers/net/ethernet/microchip/lan743x_ptp.h
+++ b/drivers/net/ethernet/microchip/lan743x_ptp.h
@@ -18,9 +18,9 @@
  */
 #define LAN743X_PTP_N_EVENT_CHAN	2
 #define LAN743X_PTP_N_PEROUT		LAN743X_PTP_N_EVENT_CHAN
-#define LAN743X_PTP_N_EXTTS		4
-#define LAN743X_PTP_N_PPS		0
 #define PCI11X1X_PTP_IO_MAX_CHANNELS	8
+#define LAN743X_PTP_N_EXTTS		PCI11X1X_PTP_IO_MAX_CHANNELS
+#define LAN743X_PTP_N_PPS		0
 #define PTP_CMD_CTL_TIMEOUT_CNT		50
 
 struct lan743x_adapter;

From 8ea688a3372e8369dc04395b39b4e71a6d91d4d5 Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@kernel.org>
Date: Tue, 27 May 2025 20:12:47 -0400
Subject: [PATCH 0624/1334] nfsd: use threads array as-is in netlink interface

The old nfsdfs interface for starting a server with multiple pools
handles the special case of a single entry array passed down from
userland by distributing the threads over every NUMA node.

The netlink control interface however constructs an array of length
nfsd_nrpools() and fills any unprovided slots with 0's. This behavior
defeats the special casing that the old interface relies on.

Change nfsd_nl_threads_set_doit() to pass down the array from userland
as-is.

Fixes: 7f5c330b2620 ("nfsd: allow passing in array of thread counts via netlink")
Cc: stable@vger.kernel.org
Reported-by: Mike Snitzer <snitzer@kernel.org>
Closes: https://lore.kernel.org/linux-nfs/aDC-ftnzhJAlwqwh@kernel.org/
Signed-off-by: Jeff Layton <jlayton@kernel.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Tested-by: Mike Snitzer <snitzer@kernel.org>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 fs/nfsd/nfsctl.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
index 3f3e9f6c4250..6a42cc7a845a 100644
--- a/fs/nfsd/nfsctl.c
+++ b/fs/nfsd/nfsctl.c
@@ -1611,7 +1611,7 @@ out_unlock:
  */
 int nfsd_nl_threads_set_doit(struct sk_buff *skb, struct genl_info *info)
 {
-	int *nthreads, count = 0, nrpools, i, ret = -EOPNOTSUPP, rem;
+	int *nthreads, nrpools = 0, i, ret = -EOPNOTSUPP, rem;
 	struct net *net = genl_info_net(info);
 	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
 	const struct nlattr *attr;
@@ -1623,12 +1623,11 @@ int nfsd_nl_threads_set_doit(struct sk_buff *skb, struct genl_info *info)
 	/* count number of SERVER_THREADS values */
 	nlmsg_for_each_attr(attr, info->nlhdr, GENL_HDRLEN, rem) {
 		if (nla_type(attr) == NFSD_A_SERVER_THREADS)
-			count++;
+			nrpools++;
 	}
 
 	mutex_lock(&nfsd_mutex);
 
-	nrpools = max(count, nfsd_nrpools(net));
 	nthreads = kcalloc(nrpools, sizeof(int), GFP_KERNEL);
 	if (!nthreads) {
 		ret = -ENOMEM;

From 94d10a4dba0bc482f2b01e39f06d5513d0f75742 Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@kernel.org>
Date: Thu, 19 Jun 2025 06:01:55 -0400
Subject: [PATCH 0625/1334] sunrpc: handle SVC_GARBAGE during svc auth
 processing as auth error

tianshuo han reported a remotely-triggerable crash if the client sends a
kernel RPC server a specially crafted packet. If decoding the RPC reply
fails in such a way that SVC_GARBAGE is returned without setting the
rq_accept_statp pointer, then that pointer can be dereferenced and a
value stored there.

If it's the first time the thread has processed an RPC, then that
pointer will be set to NULL and the kernel will crash. In other cases,
it could create a memory scribble.

The server sunrpc code treats a SVC_GARBAGE return from svc_authenticate
or pg_authenticate as if it should send a GARBAGE_ARGS reply. RFC 5531
says that if authentication fails that the RPC should be rejected
instead with a status of AUTH_ERR.

Handle a SVC_GARBAGE return as an AUTH_ERROR, with a reason of
AUTH_BADCRED instead of returning GARBAGE_ARGS in that case. This
sidesteps the whole problem of touching the rpc_accept_statp pointer in
this situation and avoids the crash.

Cc: stable@kernel.org
Fixes: 29cd2927fb91 ("SUNRPC: Fix encoding of accepted but unsuccessful RPC replies")
Reported-by: tianshuo han <hantianshuo233@gmail.com>
Reviewed-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 net/sunrpc/svc.c | 11 ++---------
 1 file changed, 2 insertions(+), 9 deletions(-)

diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index ef8a05aac87f..9c93b854e809 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -1371,7 +1371,8 @@ svc_process_common(struct svc_rqst *rqstp)
 	case SVC_OK:
 		break;
 	case SVC_GARBAGE:
-		goto err_garbage_args;
+		rqstp->rq_auth_stat = rpc_autherr_badcred;
+		goto err_bad_auth;
 	case SVC_SYSERR:
 		goto err_system_err;
 	case SVC_DENIED:
@@ -1512,14 +1513,6 @@ err_bad_proc:
 	*rqstp->rq_accept_statp = rpc_proc_unavail;
 	goto sendit;
 
-err_garbage_args:
-	svc_printk(rqstp, "failed to decode RPC header\n");
-
-	if (serv->sv_stats)
-		serv->sv_stats->rpcbadfmt++;
-	*rqstp->rq_accept_statp = rpc_garbage_args;
-	goto sendit;
-
 err_system_err:
 	if (serv->sv_stats)
 		serv->sv_stats->rpcbadfmt++;

From 8c8472855884355caf3d8e0c50adf825f83454b2 Mon Sep 17 00:00:00 2001
From: Ronnie Sahlberg <rsahlberg@whamcloud.com>
Date: Thu, 19 Jun 2025 12:10:31 +1000
Subject: [PATCH 0626/1334] ublk: santizize the arguments from userspace when
 adding a device

Sanity check the values for queue depth and number of queues
we get from userspace when adding a device.

Signed-off-by: Ronnie Sahlberg <rsahlberg@whamcloud.com>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Fixes: 71f28f3136af ("ublk_drv: add io_uring based userspace block driver")
Fixes: 62fe99cef94a ("ublk: add read()/write() support for ublk char device")
Link: https://lore.kernel.org/r/20250619021031.181340-1-ronniesahlberg@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/ublk_drv.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c
index c637ea010d34..d36f44f5ee80 100644
--- a/drivers/block/ublk_drv.c
+++ b/drivers/block/ublk_drv.c
@@ -2825,6 +2825,9 @@ static int ublk_ctrl_add_dev(const struct ublksrv_ctrl_cmd *header)
 	if (copy_from_user(&info, argp, sizeof(info)))
 		return -EFAULT;
 
+	if (info.queue_depth > UBLK_MAX_QUEUE_DEPTH || info.nr_hw_queues > UBLK_MAX_NR_QUEUES)
+		return -EINVAL;
+
 	if (capable(CAP_SYS_ADMIN))
 		info.flags &= ~UBLK_F_UNPRIVILEGED_DEV;
 	else if (!(info.flags & UBLK_F_UNPRIVILEGED_DEV))

From 16c1241b08751a67cd7a0221ea9f82b0b02806f4 Mon Sep 17 00:00:00 2001
From: Vinay Belgaumkar <vinay.belgaumkar@intel.com>
Date: Thu, 12 Jun 2025 00:09:01 -0700
Subject: [PATCH 0627/1334] drm/xe/bmg: Update Wa_16023588340
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This allows for additional L2 caching modes.

Fixes: 01570b446939 ("drm/xe/bmg: implement Wa_16023588340")
Cc: Matthew Auld <matthew.auld@intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Signed-off-by: Vinay Belgaumkar <vinay.belgaumkar@intel.com>
Link: https://lore.kernel.org/r/20250612-wa-14022085890-v4-2-94ba5dcc1e30@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
(cherry picked from commit 6ab42fa03d4c88a0ddf5e56e62794853b198e7bf)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
---
 drivers/gpu/drm/xe/xe_gt.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/xe/xe_gt.c b/drivers/gpu/drm/xe/xe_gt.c
index 0e5d243c9451..6c4cb9576fb6 100644
--- a/drivers/gpu/drm/xe/xe_gt.c
+++ b/drivers/gpu/drm/xe/xe_gt.c
@@ -118,7 +118,7 @@ static void xe_gt_enable_host_l2_vram(struct xe_gt *gt)
 		xe_gt_mcr_multicast_write(gt, XE2_GAMREQSTRM_CTRL, reg);
 	}
 
-	xe_gt_mcr_multicast_write(gt, XEHPC_L3CLOS_MASK(3), 0x3);
+	xe_gt_mcr_multicast_write(gt, XEHPC_L3CLOS_MASK(3), 0xF);
 	xe_force_wake_put(gt_to_fw(gt), fw_ref);
 }
 

From 87a15c89d8c7b00b0fc94e0d4f554f7ee2fe6961 Mon Sep 17 00:00:00 2001
From: Lucas De Marchi <lucas.demarchi@intel.com>
Date: Thu, 12 Jun 2025 15:14:12 -0700
Subject: [PATCH 0628/1334] drm/xe: Fix memset on iomem
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

It should rather use xe_map_memset() as the BO is created with
XE_BO_FLAG_VRAM_IF_DGFX in xe_guc_pc_init().

Fixes: dd08ebf6c352 ("drm/xe: Introduce a new DRM driver for Intel GPUs")
Cc: stable@vger.kernel.org
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Link: https://lore.kernel.org/r/20250612-vmap-vaddr-v1-1-26238ed443eb@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
(cherry picked from commit 21cf47d89fba353b2d5915ba4718040c4cb955d3)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
---
 drivers/gpu/drm/xe/xe_guc_pc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/xe/xe_guc_pc.c b/drivers/gpu/drm/xe/xe_guc_pc.c
index 18c623992035..3beaaa7b25c1 100644
--- a/drivers/gpu/drm/xe/xe_guc_pc.c
+++ b/drivers/gpu/drm/xe/xe_guc_pc.c
@@ -1068,7 +1068,7 @@ int xe_guc_pc_start(struct xe_guc_pc *pc)
 		goto out;
 	}
 
-	memset(pc->bo->vmap.vaddr, 0, size);
+	xe_map_memset(xe, &pc->bo->vmap, 0, 0, size);
 	slpc_shared_data_write(pc, header.size, size);
 
 	earlier = ktime_get();

From 16ea4666bbb7f5bd1130fa2d75631ccf8b62362e Mon Sep 17 00:00:00 2001
From: Peter Ujfalusi <peter.ujfalusi@linux.intel.com>
Date: Thu, 19 Jun 2025 13:47:05 +0300
Subject: [PATCH 0629/1334] ASoC: Intel: sof-function-topology-lib: Print out
 the unsupported dmic count

It is better to print out the non supported num_dmics than printing that
it is not matching with 2 or 4.

Fixes: 2fbeff33381c ("ASoC: Intel: add sof_sdw_get_tplg_files ops")
Cc: stable@vger.kernel.org
Signed-off-by: Peter Ujfalusi <peter.ujfalusi@linux.intel.com>
Reviewed-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Reviewed-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.dev>
Link: https://patch.msgid.link/20250619104705.26057-1-peter.ujfalusi@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/intel/common/sof-function-topology-lib.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/sound/soc/intel/common/sof-function-topology-lib.c b/sound/soc/intel/common/sof-function-topology-lib.c
index 90fe7aa3df1c..3cc81dcf047e 100644
--- a/sound/soc/intel/common/sof-function-topology-lib.c
+++ b/sound/soc/intel/common/sof-function-topology-lib.c
@@ -73,7 +73,8 @@ int sof_sdw_get_tplg_files(struct snd_soc_card *card, const struct snd_soc_acpi_
 				break;
 			default:
 				dev_warn(card->dev,
-					 "only -2ch and -4ch are supported for dmic\n");
+					 "unsupported number of dmics: %d\n",
+					 mach_params.dmic_num);
 				continue;
 			}
 			tplg_dev = TPLG_DEVICE_INTEL_PCH_DMIC;

From a39d082c3553d35b4fe5585e1e2fb221c130cae8 Mon Sep 17 00:00:00 2001
From: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Date: Wed, 11 Jun 2025 14:44:54 -0700
Subject: [PATCH 0630/1334] drm/xe: Fix early wedge on GuC load failure
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When the GuC fails to load we declare the device wedged. However, the
very first GuC load attempt on GT0 (from xe_gt_init_hwconfig) is done
before the GT1 GuC objects are initialized, so things go bad when the
wedge code attempts to cleanup GT1. To fix this, check the initialization
status in the functions called during wedge.

Fixes: 7dbe8af13c18 ("drm/xe: Wedge the entire device")
Signed-off-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Cc: Jonathan Cavitt <jonathan.cavitt@intel.com>
Cc: Lucas De Marchi <lucas.demarchi@intel.com>
Cc: Zhanjun Dong <zhanjun.dong@intel.com>
Cc: stable@vger.kernel.org # v6.12+: 1e1981b16bb1: drm/xe: Fix taking invalid lock on wedge
Cc: stable@vger.kernel.org # v6.12+
Reviewed-by: Jonathan Cavitt <jonathan.cavitt@intel.com>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://lore.kernel.org/r/20250611214453.1159846-2-daniele.ceraolospurio@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
(cherry picked from commit 0b93b7dcd9eb888a6ac7546560877705d4ad61bf)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
---
 drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c | 8 ++++++++
 drivers/gpu/drm/xe/xe_guc_ct.c              | 7 +++++--
 drivers/gpu/drm/xe/xe_guc_ct.h              | 5 +++++
 drivers/gpu/drm/xe/xe_guc_submit.c          | 3 +++
 4 files changed, 21 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c
index 084cbdeba8ea..e1362e608146 100644
--- a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c
+++ b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c
@@ -137,6 +137,14 @@ void xe_gt_tlb_invalidation_reset(struct xe_gt *gt)
 	struct xe_gt_tlb_invalidation_fence *fence, *next;
 	int pending_seqno;
 
+	/*
+	 * we can get here before the CTs are even initialized if we're wedging
+	 * very early, in which case there are not going to be any pending
+	 * fences so we can bail immediately.
+	 */
+	if (!xe_guc_ct_initialized(&gt->uc.guc.ct))
+		return;
+
 	/*
 	 * CT channel is already disabled at this point. No new TLB requests can
 	 * appear.
diff --git a/drivers/gpu/drm/xe/xe_guc_ct.c b/drivers/gpu/drm/xe/xe_guc_ct.c
index 2447de0ebedf..d0ac48d8f4f7 100644
--- a/drivers/gpu/drm/xe/xe_guc_ct.c
+++ b/drivers/gpu/drm/xe/xe_guc_ct.c
@@ -514,6 +514,9 @@ void xe_guc_ct_disable(struct xe_guc_ct *ct)
  */
 void xe_guc_ct_stop(struct xe_guc_ct *ct)
 {
+	if (!xe_guc_ct_initialized(ct))
+		return;
+
 	xe_guc_ct_set_state(ct, XE_GUC_CT_STATE_STOPPED);
 	stop_g2h_handler(ct);
 }
@@ -760,7 +763,7 @@ static int __guc_ct_send_locked(struct xe_guc_ct *ct, const u32 *action,
 	u16 seqno;
 	int ret;
 
-	xe_gt_assert(gt, ct->state != XE_GUC_CT_STATE_NOT_INITIALIZED);
+	xe_gt_assert(gt, xe_guc_ct_initialized(ct));
 	xe_gt_assert(gt, !g2h_len || !g2h_fence);
 	xe_gt_assert(gt, !num_g2h || !g2h_fence);
 	xe_gt_assert(gt, !g2h_len || num_g2h);
@@ -1344,7 +1347,7 @@ static int g2h_read(struct xe_guc_ct *ct, u32 *msg, bool fast_path)
 	u32 action;
 	u32 *hxg;
 
-	xe_gt_assert(gt, ct->state != XE_GUC_CT_STATE_NOT_INITIALIZED);
+	xe_gt_assert(gt, xe_guc_ct_initialized(ct));
 	lockdep_assert_held(&ct->fast_lock);
 
 	if (ct->state == XE_GUC_CT_STATE_DISABLED)
diff --git a/drivers/gpu/drm/xe/xe_guc_ct.h b/drivers/gpu/drm/xe/xe_guc_ct.h
index 82c4ae458dda..582aac106469 100644
--- a/drivers/gpu/drm/xe/xe_guc_ct.h
+++ b/drivers/gpu/drm/xe/xe_guc_ct.h
@@ -22,6 +22,11 @@ void xe_guc_ct_snapshot_print(struct xe_guc_ct_snapshot *snapshot, struct drm_pr
 void xe_guc_ct_snapshot_free(struct xe_guc_ct_snapshot *snapshot);
 void xe_guc_ct_print(struct xe_guc_ct *ct, struct drm_printer *p, bool want_ctb);
 
+static inline bool xe_guc_ct_initialized(struct xe_guc_ct *ct)
+{
+	return ct->state != XE_GUC_CT_STATE_NOT_INITIALIZED;
+}
+
 static inline bool xe_guc_ct_enabled(struct xe_guc_ct *ct)
 {
 	return ct->state == XE_GUC_CT_STATE_ENABLED;
diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c
index 6d84a52b660a..9567f6700cf2 100644
--- a/drivers/gpu/drm/xe/xe_guc_submit.c
+++ b/drivers/gpu/drm/xe/xe_guc_submit.c
@@ -1762,6 +1762,9 @@ int xe_guc_submit_reset_prepare(struct xe_guc *guc)
 {
 	int ret;
 
+	if (!guc->submission_state.initialized)
+		return 0;
+
 	/*
 	 * Using an atomic here rather than submission_state.lock as this
 	 * function can be called while holding the CT lock (engine reset

From a1113cefd7d62e20735edda79507dc9f6ce103ff Mon Sep 17 00:00:00 2001
From: Shannon Nelson <shannon.nelson@amd.com>
Date: Mon, 16 Jun 2025 15:44:37 -0700
Subject: [PATCH 0631/1334] MAINTAINERS: Remove Shannon Nelson from MAINTAINERS
 file

Brett Creeley is taking ownership of AMD/Pensando drivers while I wander
off into the sunset with my retirement this month.  I'll still keep an
eye out on a few topics for awhile, and maybe do some free-lance work in
the future.

Meanwhile, thank you all for the fun and support and the many learning
opportunities :-).

Special thanks go to DaveM for merging my first patch long ago, the big
ionic patchset a few years ago, and my last patchset last week.

Redirect things to a non-corporate account.

Signed-off-by: Shannon Nelson <shannon.nelson@amd.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Brett Creeley <brett.creeley@amd.com>
Link: https://patch.msgid.link/20250616224437.56581-1-shannon.nelson@amd.com
[Jakub: squash in the .mailmap update]
Signed-off-by: Shannon Nelson <sln@onemain.com>
Link: https://patch.msgid.link/20250619010603.1173141-1-sln@onemain.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .mailmap    | 7 ++++---
 MAINTAINERS | 5 +----
 2 files changed, 5 insertions(+), 7 deletions(-)

diff --git a/.mailmap b/.mailmap
index b77cd34cf852..7a3ffabb3434 100644
--- a/.mailmap
+++ b/.mailmap
@@ -691,9 +691,10 @@ Serge Hallyn <sergeh@kernel.org> <serge.hallyn@canonical.com>
 Serge Hallyn <sergeh@kernel.org> <serue@us.ibm.com>
 Seth Forshee <sforshee@kernel.org> <seth.forshee@canonical.com>
 Shakeel Butt <shakeel.butt@linux.dev> <shakeelb@google.com>
-Shannon Nelson <shannon.nelson@amd.com> <snelson@pensando.io>
-Shannon Nelson <shannon.nelson@amd.com> <shannon.nelson@intel.com>
-Shannon Nelson <shannon.nelson@amd.com> <shannon.nelson@oracle.com>
+Shannon Nelson <sln@onemain.com> <shannon.nelson@amd.com>
+Shannon Nelson <sln@onemain.com> <snelson@pensando.io>
+Shannon Nelson <sln@onemain.com> <shannon.nelson@intel.com>
+Shannon Nelson <sln@onemain.com> <shannon.nelson@oracle.com>
 Sharath Chandra Vurukala <quic_sharathv@quicinc.com> <sharathv@codeaurora.org>
 Shiraz Hashim <shiraz.linux.kernel@gmail.com> <shiraz.hashim@st.com>
 Shuah Khan <shuah@kernel.org> <shuahkhan@gmail.com>
diff --git a/MAINTAINERS b/MAINTAINERS
index 99fbde007792..437381aeaa71 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -1157,7 +1157,6 @@ F:	arch/x86/include/asm/amd/node.h
 F:	arch/x86/kernel/amd_node.c
 
 AMD PDS CORE DRIVER
-M:	Shannon Nelson <shannon.nelson@amd.com>
 M:	Brett Creeley <brett.creeley@amd.com>
 L:	netdev@vger.kernel.org
 S:	Maintained
@@ -9941,7 +9940,6 @@ F:	drivers/fwctl/mlx5/
 
 FWCTL PDS DRIVER
 M:	Brett Creeley <brett.creeley@amd.com>
-R:	Shannon Nelson <shannon.nelson@amd.com>
 L:	linux-kernel@vger.kernel.org
 S:	Maintained
 F:	drivers/fwctl/pds/
@@ -19377,7 +19375,7 @@ F:	crypto/pcrypt.c
 F:	include/crypto/pcrypt.h
 
 PDS DSC VIRTIO DATA PATH ACCELERATOR
-R:	Shannon Nelson <shannon.nelson@amd.com>
+R:	Brett Creeley <brett.creeley@amd.com>
 F:	drivers/vdpa/pds/
 
 PECI HARDWARE MONITORING DRIVERS
@@ -19399,7 +19397,6 @@ F:	include/linux/peci-cpu.h
 F:	include/linux/peci.h
 
 PENSANDO ETHERNET DRIVERS
-M:	Shannon Nelson <shannon.nelson@amd.com>
 M:	Brett Creeley <brett.creeley@amd.com>
 L:	netdev@vger.kernel.org
 S:	Maintained

From 10876da918fa1aec0227fb4c67647513447f53a9 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@google.com>
Date: Tue, 17 Jun 2025 15:40:42 -0700
Subject: [PATCH 0632/1334] calipso: Fix null-ptr-deref in
 calipso_req_{set,del}attr().

syzkaller reported a null-ptr-deref in sock_omalloc() while allocating
a CALIPSO option.  [0]

The NULL is of struct sock, which was fetched by sk_to_full_sk() in
calipso_req_setattr().

Since commit a1a5344ddbe8 ("tcp: avoid two atomic ops for syncookies"),
reqsk->rsk_listener could be NULL when SYN Cookie is returned to its
client, as hinted by the leading SYN Cookie log.

Here are 3 options to fix the bug:

  1) Return 0 in calipso_req_setattr()
  2) Return an error in calipso_req_setattr()
  3) Alaways set rsk_listener

1) is no go as it bypasses LSM, but 2) effectively disables SYN Cookie
for CALIPSO.  3) is also no go as there have been many efforts to reduce
atomic ops and make TCP robust against DDoS.  See also commit 3b24d854cb35
("tcp/dccp: do not touch listener sk_refcnt under synflood").

As of the blamed commit, SYN Cookie already did not need refcounting,
and no one has stumbled on the bug for 9 years, so no CALIPSO user will
care about SYN Cookie.

Let's return an error in calipso_req_setattr() and calipso_req_delattr()
in the SYN Cookie case.

This can be reproduced by [1] on Fedora and now connect() of nc times out.

[0]:
TCP: request_sock_TCPv6: Possible SYN flooding on port [::]:20002. Sending cookies.
Oops: general protection fault, probably for non-canonical address 0xdffffc0000000006: 0000 [#1] PREEMPT SMP KASAN NOPTI
KASAN: null-ptr-deref in range [0x0000000000000030-0x0000000000000037]
CPU: 3 UID: 0 PID: 12262 Comm: syz.1.2611 Not tainted 6.14.0 #2
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.3-0-ga6ed6b701f0a-prebuilt.qemu.org 04/01/2014
RIP: 0010:read_pnet include/net/net_namespace.h:406 [inline]
RIP: 0010:sock_net include/net/sock.h:655 [inline]
RIP: 0010:sock_kmalloc+0x35/0x170 net/core/sock.c:2806
Code: 89 d5 41 54 55 89 f5 53 48 89 fb e8 25 e3 c6 fd e8 f0 91 e3 00 48 8d 7b 30 48 b8 00 00 00 00 00 fc ff df 48 89 fa 48 c1 ea 03 <80> 3c 02 00 0f 85 26 01 00 00 48 b8 00 00 00 00 00 fc ff df 4c 8b
RSP: 0018:ffff88811af89038 EFLAGS: 00010216
RAX: dffffc0000000000 RBX: 0000000000000000 RCX: ffff888105266400
RDX: 0000000000000006 RSI: ffff88800c890000 RDI: 0000000000000030
RBP: 0000000000000050 R08: 0000000000000000 R09: ffff88810526640e
R10: ffffed1020a4cc81 R11: ffff88810526640f R12: 0000000000000000
R13: 0000000000000820 R14: ffff888105266400 R15: 0000000000000050
FS:  00007f0653a07640(0000) GS:ffff88811af80000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007f863ba096f4 CR3: 00000000163c0005 CR4: 0000000000770ef0
PKRU: 80000000
Call Trace:
 <IRQ>
 ipv6_renew_options+0x279/0x950 net/ipv6/exthdrs.c:1288
 calipso_req_setattr+0x181/0x340 net/ipv6/calipso.c:1204
 calipso_req_setattr+0x56/0x80 net/netlabel/netlabel_calipso.c:597
 netlbl_req_setattr+0x18a/0x440 net/netlabel/netlabel_kapi.c:1249
 selinux_netlbl_inet_conn_request+0x1fb/0x320 security/selinux/netlabel.c:342
 selinux_inet_conn_request+0x1eb/0x2c0 security/selinux/hooks.c:5551
 security_inet_conn_request+0x50/0xa0 security/security.c:4945
 tcp_v6_route_req+0x22c/0x550 net/ipv6/tcp_ipv6.c:825
 tcp_conn_request+0xec8/0x2b70 net/ipv4/tcp_input.c:7275
 tcp_v6_conn_request+0x1e3/0x440 net/ipv6/tcp_ipv6.c:1328
 tcp_rcv_state_process+0xafa/0x52b0 net/ipv4/tcp_input.c:6781
 tcp_v6_do_rcv+0x8a6/0x1a40 net/ipv6/tcp_ipv6.c:1667
 tcp_v6_rcv+0x505e/0x5b50 net/ipv6/tcp_ipv6.c:1904
 ip6_protocol_deliver_rcu+0x17c/0x1da0 net/ipv6/ip6_input.c:436
 ip6_input_finish+0x103/0x180 net/ipv6/ip6_input.c:480
 NF_HOOK include/linux/netfilter.h:314 [inline]
 NF_HOOK include/linux/netfilter.h:308 [inline]
 ip6_input+0x13c/0x6b0 net/ipv6/ip6_input.c:491
 dst_input include/net/dst.h:469 [inline]
 ip6_rcv_finish net/ipv6/ip6_input.c:79 [inline]
 ip6_rcv_finish+0xb6/0x490 net/ipv6/ip6_input.c:69
 NF_HOOK include/linux/netfilter.h:314 [inline]
 NF_HOOK include/linux/netfilter.h:308 [inline]
 ipv6_rcv+0xf9/0x490 net/ipv6/ip6_input.c:309
 __netif_receive_skb_one_core+0x12e/0x1f0 net/core/dev.c:5896
 __netif_receive_skb+0x1d/0x170 net/core/dev.c:6009
 process_backlog+0x41e/0x13b0 net/core/dev.c:6357
 __napi_poll+0xbd/0x710 net/core/dev.c:7191
 napi_poll net/core/dev.c:7260 [inline]
 net_rx_action+0x9de/0xde0 net/core/dev.c:7382
 handle_softirqs+0x19a/0x770 kernel/softirq.c:561
 do_softirq.part.0+0x36/0x70 kernel/softirq.c:462
 </IRQ>
 <TASK>
 do_softirq arch/x86/include/asm/preempt.h:26 [inline]
 __local_bh_enable_ip+0xf1/0x110 kernel/softirq.c:389
 local_bh_enable include/linux/bottom_half.h:33 [inline]
 rcu_read_unlock_bh include/linux/rcupdate.h:919 [inline]
 __dev_queue_xmit+0xc2a/0x3c40 net/core/dev.c:4679
 dev_queue_xmit include/linux/netdevice.h:3313 [inline]
 neigh_hh_output include/net/neighbour.h:523 [inline]
 neigh_output include/net/neighbour.h:537 [inline]
 ip6_finish_output2+0xd69/0x1f80 net/ipv6/ip6_output.c:141
 __ip6_finish_output net/ipv6/ip6_output.c:215 [inline]
 ip6_finish_output+0x5dc/0xd60 net/ipv6/ip6_output.c:226
 NF_HOOK_COND include/linux/netfilter.h:303 [inline]
 ip6_output+0x24b/0x8d0 net/ipv6/ip6_output.c:247
 dst_output include/net/dst.h:459 [inline]
 NF_HOOK include/linux/netfilter.h:314 [inline]
 NF_HOOK include/linux/netfilter.h:308 [inline]
 ip6_xmit+0xbbc/0x20d0 net/ipv6/ip6_output.c:366
 inet6_csk_xmit+0x39a/0x720 net/ipv6/inet6_connection_sock.c:135
 __tcp_transmit_skb+0x1a7b/0x3b40 net/ipv4/tcp_output.c:1471
 tcp_transmit_skb net/ipv4/tcp_output.c:1489 [inline]
 tcp_send_syn_data net/ipv4/tcp_output.c:4059 [inline]
 tcp_connect+0x1c0c/0x4510 net/ipv4/tcp_output.c:4148
 tcp_v6_connect+0x156c/0x2080 net/ipv6/tcp_ipv6.c:333
 __inet_stream_connect+0x3a7/0xed0 net/ipv4/af_inet.c:677
 tcp_sendmsg_fastopen+0x3e2/0x710 net/ipv4/tcp.c:1039
 tcp_sendmsg_locked+0x1e82/0x3570 net/ipv4/tcp.c:1091
 tcp_sendmsg+0x2f/0x50 net/ipv4/tcp.c:1358
 inet6_sendmsg+0xb9/0x150 net/ipv6/af_inet6.c:659
 sock_sendmsg_nosec net/socket.c:718 [inline]
 __sock_sendmsg+0xf4/0x2a0 net/socket.c:733
 __sys_sendto+0x29a/0x390 net/socket.c:2187
 __do_sys_sendto net/socket.c:2194 [inline]
 __se_sys_sendto net/socket.c:2190 [inline]
 __x64_sys_sendto+0xe1/0x1c0 net/socket.c:2190
 do_syscall_x64 arch/x86/entry/common.c:52 [inline]
 do_syscall_64+0xc3/0x1d0 arch/x86/entry/common.c:83
 entry_SYSCALL_64_after_hwframe+0x77/0x7f
RIP: 0033:0x7f06553c47ed
Code: 02 b8 ff ff ff ff c3 66 0f 1f 44 00 00 f3 0f 1e fa 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 a8 ff ff ff f7 d8 64 89 01 48
RSP: 002b:00007f0653a06fc8 EFLAGS: 00000246 ORIG_RAX: 000000000000002c
RAX: ffffffffffffffda RBX: 00007f0655605fa0 RCX: 00007f06553c47ed
RDX: 0000000000000000 RSI: 0000000000000000 RDI: 000000000000000b
RBP: 00007f065545db38 R08: 0000200000000140 R09: 000000000000001c
R10: f7384d4ea84b01bd R11: 0000000000000246 R12: 0000000000000000
R13: 00007f0655605fac R14: 00007f0655606038 R15: 00007f06539e7000
 </TASK>
Modules linked in:

[1]:
dnf install -y selinux-policy-targeted policycoreutils netlabel_tools procps-ng nmap-ncat
mount -t selinuxfs none /sys/fs/selinux
load_policy
netlabelctl calipso add pass doi:1
netlabelctl map del default
netlabelctl map add default address:::1 protocol:calipso,1
sysctl net.ipv4.tcp_syncookies=2
nc -l ::1 80 &
nc ::1 80

Fixes: e1adea927080 ("calipso: Allow request sockets to be relabelled by the lsm.")
Reported-by: syzkaller <syzkaller@googlegroups.com>
Reported-by: John Cheung <john.cs.hey@gmail.com>
Closes: https://lore.kernel.org/netdev/CAP=Rh=MvfhrGADy+-WJiftV2_WzMH4VEhEFmeT28qY+4yxNu4w@mail.gmail.com/
Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Acked-by: Paul Moore <paul@paul-moore.com>
Link: https://patch.msgid.link/20250617224125.17299-1-kuni1840@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv6/calipso.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/net/ipv6/calipso.c b/net/ipv6/calipso.c
index 62618a058b8f..a247bb93908b 100644
--- a/net/ipv6/calipso.c
+++ b/net/ipv6/calipso.c
@@ -1207,6 +1207,10 @@ static int calipso_req_setattr(struct request_sock *req,
 	struct ipv6_opt_hdr *old, *new;
 	struct sock *sk = sk_to_full_sk(req_to_sk(req));
 
+	/* sk is NULL for SYN+ACK w/ SYN Cookie */
+	if (!sk)
+		return -ENOMEM;
+
 	if (req_inet->ipv6_opt && req_inet->ipv6_opt->hopopt)
 		old = req_inet->ipv6_opt->hopopt;
 	else
@@ -1247,6 +1251,10 @@ static void calipso_req_delattr(struct request_sock *req)
 	struct ipv6_txoptions *txopts;
 	struct sock *sk = sk_to_full_sk(req_to_sk(req));
 
+	/* sk is NULL for SYN+ACK w/ SYN Cookie */
+	if (!sk)
+		return;
+
 	if (!req_inet->ipv6_opt || !req_inet->ipv6_opt->hopopt)
 		return;
 

From a55bc4ffc06d8c965a7d6f0a01ed0ed41380df28 Mon Sep 17 00:00:00 2001
From: Nathan Chancellor <nathan@kernel.org>
Date: Mon, 9 Jun 2025 14:13:14 -0700
Subject: [PATCH 0633/1334] staging: rtl8723bs: Avoid memset() in aes_cipher()
 and aes_decipher()

After commit 6f110a5e4f99 ("Disable SLUB_TINY for build testing"), which
causes CONFIG_KASAN to be enabled in allmodconfig again, arm64
allmodconfig builds with older versions of clang (15 through 17) show an
instance of -Wframe-larger-than (which breaks the build with
CONFIG_WERROR=y):

  drivers/staging/rtl8723bs/core/rtw_security.c:1287:5: error: stack frame size (2208) exceeds limit (2048) in 'rtw_aes_decrypt' [-Werror,-Wframe-larger-than]
   1287 | u32 rtw_aes_decrypt(struct adapter *padapter, u8 *precvframe)
        |     ^

This comes from aes_decipher() being inlined in rtw_aes_decrypt().
Running the same build with CONFIG_FRAME_WARN=128 shows aes_cipher()
also uses a decent amount of stack, just under the limit of 2048:

  drivers/staging/rtl8723bs/core/rtw_security.c:864:19: warning: stack frame size (1952) exceeds limit (128) in 'aes_cipher' [-Wframe-larger-than]
    864 | static signed int aes_cipher(u8 *key, uint      hdrlen,
        |                   ^

-Rpass-analysis=stack-frame-layout only shows one large structure on the
stack, which is the ctx variable inlined from aes128k128d(). A good
number of the other variables come from the additional checks of
fortified string routines, which are present in memset(), which both
aes_cipher() and aes_decipher() use to initialize some temporary
buffers. In this case, since the size is known at compile time, these
additional checks should not result in any code generation changes but
allmodconfig has several sanitizers enabled, which may make it harder
for the compiler to eliminate the compile time checks and the variables
that come about from them.

The memset() calls are just initializing these buffers to zero, so use
'= {}' instead, which is used all over the kernel and does the exact
same thing as memset() without the fortify checks, which drops the stack
usage of these functions by a few hundred kilobytes.

  drivers/staging/rtl8723bs/core/rtw_security.c:864:19: warning: stack frame size (1584) exceeds limit (128) in 'aes_cipher' [-Wframe-larger-than]
    864 | static signed int aes_cipher(u8 *key, uint      hdrlen,
        |                   ^
  drivers/staging/rtl8723bs/core/rtw_security.c:1271:5: warning: stack frame size (1456) exceeds limit (128) in 'rtw_aes_decrypt' [-Wframe-larger-than]
   1271 | u32 rtw_aes_decrypt(struct adapter *padapter, u8 *precvframe)
        |     ^

Cc: stable@vger.kernel.org
Fixes: 554c0a3abf21 ("staging: Add rtl8723bs sdio wifi driver")
Signed-off-by: Nathan Chancellor <nathan@kernel.org>
Reviewed-by: Dan Carpenter <dan.carpenter@linaro.org>
Link: https://lore.kernel.org/r/20250609-rtl8723bs-fix-clang-arm64-wflt-v1-1-e2accba43def@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8723bs/core/rtw_security.c | 44 ++++++-------------
 1 file changed, 14 insertions(+), 30 deletions(-)

diff --git a/drivers/staging/rtl8723bs/core/rtw_security.c b/drivers/staging/rtl8723bs/core/rtw_security.c
index 1e9eff01b1aa..e9f382c280d9 100644
--- a/drivers/staging/rtl8723bs/core/rtw_security.c
+++ b/drivers/staging/rtl8723bs/core/rtw_security.c
@@ -868,29 +868,21 @@ static signed int aes_cipher(u8 *key, uint	hdrlen,
 		num_blocks, payload_index;
 
 	u8 pn_vector[6];
-	u8 mic_iv[16];
-	u8 mic_header1[16];
-	u8 mic_header2[16];
-	u8 ctr_preload[16];
+	u8 mic_iv[16] = {};
+	u8 mic_header1[16] = {};
+	u8 mic_header2[16] = {};
+	u8 ctr_preload[16] = {};
 
 	/* Intermediate Buffers */
-	u8 chain_buffer[16];
-	u8 aes_out[16];
-	u8 padded_buffer[16];
+	u8 chain_buffer[16] = {};
+	u8 aes_out[16] = {};
+	u8 padded_buffer[16] = {};
 	u8 mic[8];
 	uint	frtype  = GetFrameType(pframe);
 	uint	frsubtype  = GetFrameSubType(pframe);
 
 	frsubtype = frsubtype>>4;
 
-	memset((void *)mic_iv, 0, 16);
-	memset((void *)mic_header1, 0, 16);
-	memset((void *)mic_header2, 0, 16);
-	memset((void *)ctr_preload, 0, 16);
-	memset((void *)chain_buffer, 0, 16);
-	memset((void *)aes_out, 0, 16);
-	memset((void *)padded_buffer, 0, 16);
-
 	if ((hdrlen == WLAN_HDR_A3_LEN) || (hdrlen ==  WLAN_HDR_A3_QOS_LEN))
 		a4_exists = 0;
 	else
@@ -1080,15 +1072,15 @@ static signed int aes_decipher(u8 *key, uint	hdrlen,
 			num_blocks, payload_index;
 	signed int res = _SUCCESS;
 	u8 pn_vector[6];
-	u8 mic_iv[16];
-	u8 mic_header1[16];
-	u8 mic_header2[16];
-	u8 ctr_preload[16];
+	u8 mic_iv[16] = {};
+	u8 mic_header1[16] = {};
+	u8 mic_header2[16] = {};
+	u8 ctr_preload[16] = {};
 
 		/* Intermediate Buffers */
-	u8 chain_buffer[16];
-	u8 aes_out[16];
-	u8 padded_buffer[16];
+	u8 chain_buffer[16] = {};
+	u8 aes_out[16] = {};
+	u8 padded_buffer[16] = {};
 	u8 mic[8];
 
 	uint frtype  = GetFrameType(pframe);
@@ -1096,14 +1088,6 @@ static signed int aes_decipher(u8 *key, uint	hdrlen,
 
 	frsubtype = frsubtype>>4;
 
-	memset((void *)mic_iv, 0, 16);
-	memset((void *)mic_header1, 0, 16);
-	memset((void *)mic_header2, 0, 16);
-	memset((void *)ctr_preload, 0, 16);
-	memset((void *)chain_buffer, 0, 16);
-	memset((void *)aes_out, 0, 16);
-	memset((void *)padded_buffer, 0, 16);
-
 	/* start to decrypt the payload */
 
 	num_blocks = (plen-8) / 16; /* plen including LLC, payload_length and mic) */

From fc27ab48904ceb7e4792f0c400f1ef175edf16fe Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Wed, 18 Jun 2025 09:36:50 +0200
Subject: [PATCH 0634/1334] NFC: nci: uart: Set tty->disc_data only in success
 path

Setting tty->disc_data before opening the NCI device means we need to
clean it up on error paths.  This also opens some short window if device
starts sending data, even before NCIUARTSETDRIVER IOCTL succeeded
(broken hardware?).  Close the window by exposing tty->disc_data only on
the success path, when opening of the NCI device and try_module_get()
succeeds.

The code differs in error path in one aspect: tty->disc_data won't be
ever assigned thus NULL-ified.  This however should not be relevant
difference, because of "tty->disc_data=NULL" in nci_uart_tty_open().

Cc: Linus Torvalds <torvalds@linuxfoundation.org>
Fixes: 9961127d4bce ("NFC: nci: add generic uart support")
Cc: <stable@vger.kernel.org>
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Link: https://patch.msgid.link/20250618073649.25049-2-krzysztof.kozlowski@linaro.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/nfc/nci/uart.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/nfc/nci/uart.c b/net/nfc/nci/uart.c
index ed1508a9e093..aab107727f18 100644
--- a/net/nfc/nci/uart.c
+++ b/net/nfc/nci/uart.c
@@ -119,22 +119,22 @@ static int nci_uart_set_driver(struct tty_struct *tty, unsigned int driver)
 
 	memcpy(nu, nci_uart_drivers[driver], sizeof(struct nci_uart));
 	nu->tty = tty;
-	tty->disc_data = nu;
 	skb_queue_head_init(&nu->tx_q);
 	INIT_WORK(&nu->write_work, nci_uart_write_work);
 	spin_lock_init(&nu->rx_lock);
 
 	ret = nu->ops.open(nu);
 	if (ret) {
-		tty->disc_data = NULL;
 		kfree(nu);
+		return ret;
 	} else if (!try_module_get(nu->owner)) {
 		nu->ops.close(nu);
-		tty->disc_data = NULL;
 		kfree(nu);
 		return -ENOENT;
 	}
-	return ret;
+	tty->disc_data = nu;
+
+	return 0;
 }
 
 /* ------ LDISC part ------ */

From 78bd03ee1f20a267d2c218884b66041b3508ac9c Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Wed, 18 Jun 2025 09:37:40 +0200
Subject: [PATCH 0635/1334] net: airoha: Always check return value from
 airoha_ppe_foe_get_entry()

airoha_ppe_foe_get_entry routine can return NULL, so check the returned
pointer is not NULL in airoha_ppe_foe_flow_l2_entry_update()

Fixes: b81e0f2b58be3 ("net: airoha: Add FLOW_CLS_STATS callback support")
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Link: https://patch.msgid.link/20250618-check-ret-from-airoha_ppe_foe_get_entry-v2-1-068dcea3cc66@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/airoha/airoha_ppe.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/airoha/airoha_ppe.c b/drivers/net/ethernet/airoha/airoha_ppe.c
index 9067d2fc7706..0e217acfc5ef 100644
--- a/drivers/net/ethernet/airoha/airoha_ppe.c
+++ b/drivers/net/ethernet/airoha/airoha_ppe.c
@@ -809,8 +809,10 @@ airoha_ppe_foe_flow_l2_entry_update(struct airoha_ppe *ppe,
 		int idle;
 
 		hwe = airoha_ppe_foe_get_entry(ppe, iter->hash);
-		ib1 = READ_ONCE(hwe->ib1);
+		if (!hwe)
+			continue;
 
+		ib1 = READ_ONCE(hwe->ib1);
 		state = FIELD_GET(AIROHA_FOE_IB1_BIND_STATE, ib1);
 		if (state != AIROHA_FOE_STATE_BIND) {
 			iter->hash = 0xffff;

From e7ea5f5b1858ddb96b152584d5fe06e6fc623e89 Mon Sep 17 00:00:00 2001
From: David Thompson <davthompson@nvidia.com>
Date: Wed, 18 Jun 2025 13:59:02 +0000
Subject: [PATCH 0636/1334] mlxbf_gige: return EPROBE_DEFER if PHY IRQ is not
 available

The message "Error getting PHY irq. Use polling instead"
is emitted when the mlxbf_gige driver is loaded by the
kernel before the associated gpio-mlxbf driver, and thus
the call to get the PHY IRQ fails since it is not yet
available. The driver probe() must return -EPROBE_DEFER
if acpi_dev_gpio_irq_get_by() returns the same.

Fixes: 6c2a6ddca763 ("net: mellanox: mlxbf_gige: Replace non-standard interrupt handling")
Signed-off-by: David Thompson <davthompson@nvidia.com>
Reviewed-by: Asmaa Mnebhi <asmaa@nvidia.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250618135902.346-1-davthompson@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c
index fb2e5b844c15..d76d7a945899 100644
--- a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c
+++ b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c
@@ -447,8 +447,10 @@ static int mlxbf_gige_probe(struct platform_device *pdev)
 	priv->llu_plu_irq = platform_get_irq(pdev, MLXBF_GIGE_LLU_PLU_INTR_IDX);
 
 	phy_irq = acpi_dev_gpio_irq_get_by(ACPI_COMPANION(&pdev->dev), "phy", 0);
-	if (phy_irq < 0) {
-		dev_err(&pdev->dev, "Error getting PHY irq. Use polling instead");
+	if (phy_irq == -EPROBE_DEFER) {
+		err = -EPROBE_DEFER;
+		goto out;
+	} else if (phy_irq < 0) {
 		phy_irq = PHY_POLL;
 	}
 

From d13a3824bfd2b4774b671a75cf766a16637a0e67 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 18 Jun 2025 14:08:43 +0000
Subject: [PATCH 0637/1334] net: atm: add lec_mutex

syzbot found its way in net/atm/lec.c, and found an error path
in lecd_attach() could leave a dangling pointer in dev_lec[].

Add a mutex to protect dev_lecp[] uses from lecd_attach(),
lec_vcc_attach() and lec_mcast_attach().

Following patch will use this mutex for /proc/net/atm/lec.

BUG: KASAN: slab-use-after-free in lecd_attach net/atm/lec.c:751 [inline]
BUG: KASAN: slab-use-after-free in lane_ioctl+0x2224/0x23e0 net/atm/lec.c:1008
Read of size 8 at addr ffff88807c7b8e68 by task syz.1.17/6142

CPU: 1 UID: 0 PID: 6142 Comm: syz.1.17 Not tainted 6.16.0-rc1-syzkaller-00239-g08215f5486ec #0 PREEMPT(full)
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 05/07/2025
Call Trace:
 <TASK>
  __dump_stack lib/dump_stack.c:94 [inline]
  dump_stack_lvl+0x116/0x1f0 lib/dump_stack.c:120
  print_address_description mm/kasan/report.c:408 [inline]
  print_report+0xcd/0x680 mm/kasan/report.c:521
  kasan_report+0xe0/0x110 mm/kasan/report.c:634
  lecd_attach net/atm/lec.c:751 [inline]
  lane_ioctl+0x2224/0x23e0 net/atm/lec.c:1008
  do_vcc_ioctl+0x12c/0x930 net/atm/ioctl.c:159
  sock_do_ioctl+0x118/0x280 net/socket.c:1190
  sock_ioctl+0x227/0x6b0 net/socket.c:1311
  vfs_ioctl fs/ioctl.c:51 [inline]
  __do_sys_ioctl fs/ioctl.c:907 [inline]
  __se_sys_ioctl fs/ioctl.c:893 [inline]
  __x64_sys_ioctl+0x18e/0x210 fs/ioctl.c:893
  do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline]
  do_syscall_64+0xcd/0x4c0 arch/x86/entry/syscall_64.c:94
 entry_SYSCALL_64_after_hwframe+0x77/0x7f
 </TASK>

Allocated by task 6132:
  kasan_save_stack+0x33/0x60 mm/kasan/common.c:47
  kasan_save_track+0x14/0x30 mm/kasan/common.c:68
  poison_kmalloc_redzone mm/kasan/common.c:377 [inline]
  __kasan_kmalloc+0xaa/0xb0 mm/kasan/common.c:394
  kasan_kmalloc include/linux/kasan.h:260 [inline]
  __do_kmalloc_node mm/slub.c:4328 [inline]
  __kvmalloc_node_noprof+0x27b/0x620 mm/slub.c:5015
  alloc_netdev_mqs+0xd2/0x1570 net/core/dev.c:11711
  lecd_attach net/atm/lec.c:737 [inline]
  lane_ioctl+0x17db/0x23e0 net/atm/lec.c:1008
  do_vcc_ioctl+0x12c/0x930 net/atm/ioctl.c:159
  sock_do_ioctl+0x118/0x280 net/socket.c:1190
  sock_ioctl+0x227/0x6b0 net/socket.c:1311
  vfs_ioctl fs/ioctl.c:51 [inline]
  __do_sys_ioctl fs/ioctl.c:907 [inline]
  __se_sys_ioctl fs/ioctl.c:893 [inline]
  __x64_sys_ioctl+0x18e/0x210 fs/ioctl.c:893
  do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline]
  do_syscall_64+0xcd/0x4c0 arch/x86/entry/syscall_64.c:94
 entry_SYSCALL_64_after_hwframe+0x77/0x7f

Freed by task 6132:
  kasan_save_stack+0x33/0x60 mm/kasan/common.c:47
  kasan_save_track+0x14/0x30 mm/kasan/common.c:68
  kasan_save_free_info+0x3b/0x60 mm/kasan/generic.c:576
  poison_slab_object mm/kasan/common.c:247 [inline]
  __kasan_slab_free+0x51/0x70 mm/kasan/common.c:264
  kasan_slab_free include/linux/kasan.h:233 [inline]
  slab_free_hook mm/slub.c:2381 [inline]
  slab_free mm/slub.c:4643 [inline]
  kfree+0x2b4/0x4d0 mm/slub.c:4842
  free_netdev+0x6c5/0x910 net/core/dev.c:11892
  lecd_attach net/atm/lec.c:744 [inline]
  lane_ioctl+0x1ce8/0x23e0 net/atm/lec.c:1008
  do_vcc_ioctl+0x12c/0x930 net/atm/ioctl.c:159
  sock_do_ioctl+0x118/0x280 net/socket.c:1190
  sock_ioctl+0x227/0x6b0 net/socket.c:1311
  vfs_ioctl fs/ioctl.c:51 [inline]
  __do_sys_ioctl fs/ioctl.c:907 [inline]
  __se_sys_ioctl fs/ioctl.c:893 [inline]
  __x64_sys_ioctl+0x18e/0x210 fs/ioctl.c:893

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Reported-by: syzbot+8b64dec3affaed7b3af5@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/netdev/6852c6f6.050a0220.216029.0018.GAE@google.com/T/#u
Signed-off-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20250618140844.1686882-2-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/atm/lec.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/net/atm/lec.c b/net/atm/lec.c
index acef984f3367..1e1f3eb0e2ba 100644
--- a/net/atm/lec.c
+++ b/net/atm/lec.c
@@ -124,6 +124,7 @@ static unsigned char bus_mac[ETH_ALEN] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
 
 /* Device structures */
 static struct net_device *dev_lec[MAX_LEC_ITF];
+static DEFINE_MUTEX(lec_mutex);
 
 #if IS_ENABLED(CONFIG_BRIDGE)
 static void lec_handle_bridge(struct sk_buff *skb, struct net_device *dev)
@@ -685,6 +686,7 @@ static int lec_vcc_attach(struct atm_vcc *vcc, void __user *arg)
 	int bytes_left;
 	struct atmlec_ioc ioc_data;
 
+	lockdep_assert_held(&lec_mutex);
 	/* Lecd must be up in this case */
 	bytes_left = copy_from_user(&ioc_data, arg, sizeof(struct atmlec_ioc));
 	if (bytes_left != 0)
@@ -710,6 +712,7 @@ static int lec_vcc_attach(struct atm_vcc *vcc, void __user *arg)
 
 static int lec_mcast_attach(struct atm_vcc *vcc, int arg)
 {
+	lockdep_assert_held(&lec_mutex);
 	if (arg < 0 || arg >= MAX_LEC_ITF)
 		return -EINVAL;
 	arg = array_index_nospec(arg, MAX_LEC_ITF);
@@ -725,6 +728,7 @@ static int lecd_attach(struct atm_vcc *vcc, int arg)
 	int i;
 	struct lec_priv *priv;
 
+	lockdep_assert_held(&lec_mutex);
 	if (arg < 0)
 		arg = 0;
 	if (arg >= MAX_LEC_ITF)
@@ -742,6 +746,7 @@ static int lecd_attach(struct atm_vcc *vcc, int arg)
 		snprintf(dev_lec[i]->name, IFNAMSIZ, "lec%d", i);
 		if (register_netdev(dev_lec[i])) {
 			free_netdev(dev_lec[i]);
+			dev_lec[i] = NULL;
 			return -EINVAL;
 		}
 
@@ -1003,6 +1008,7 @@ static int lane_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
 		return -ENOIOCTLCMD;
 	}
 
+	mutex_lock(&lec_mutex);
 	switch (cmd) {
 	case ATMLEC_CTRL:
 		err = lecd_attach(vcc, (int)arg);
@@ -1017,6 +1023,7 @@ static int lane_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
 		break;
 	}
 
+	mutex_unlock(&lec_mutex);
 	return err;
 }
 

From d03b79f459c7935cff830d98373474f440bd03ae Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 18 Jun 2025 14:08:44 +0000
Subject: [PATCH 0638/1334] net: atm: fix /proc/net/atm/lec handling

/proc/net/atm/lec must ensure safety against dev_lec[] changes.

It appears it had dev_put() calls without prior dev_hold(),
leading to imbalance and UAF.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Francois Romieu <romieu@fr.zoreil.com> # Minor atm contributor
Link: https://patch.msgid.link/20250618140844.1686882-3-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/atm/lec.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/net/atm/lec.c b/net/atm/lec.c
index 1e1f3eb0e2ba..afb8d3eb2185 100644
--- a/net/atm/lec.c
+++ b/net/atm/lec.c
@@ -909,7 +909,6 @@ static void *lec_itf_walk(struct lec_state *state, loff_t *l)
 	v = (dev && netdev_priv(dev)) ?
 		lec_priv_walk(state, l, netdev_priv(dev)) : NULL;
 	if (!v && dev) {
-		dev_put(dev);
 		/* Partial state reset for the next time we get called */
 		dev = NULL;
 	}
@@ -933,6 +932,7 @@ static void *lec_seq_start(struct seq_file *seq, loff_t *pos)
 {
 	struct lec_state *state = seq->private;
 
+	mutex_lock(&lec_mutex);
 	state->itf = 0;
 	state->dev = NULL;
 	state->locked = NULL;
@@ -950,8 +950,9 @@ static void lec_seq_stop(struct seq_file *seq, void *v)
 	if (state->dev) {
 		spin_unlock_irqrestore(&state->locked->lec_arp_lock,
 				       state->flags);
-		dev_put(state->dev);
+		state->dev = NULL;
 	}
+	mutex_unlock(&lec_mutex);
 }
 
 static void *lec_seq_next(struct seq_file *seq, void *v, loff_t *pos)

From 9738280aae592b579a25b5b1b6584c894827d3c7 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Wed, 18 Jun 2025 10:17:46 -0700
Subject: [PATCH 0639/1334] tools: ynl: fix mixing ops and notifications on one
 socket

The multi message support loosened the connection between the request
and response handling, as we can now submit multiple requests before
we start processing responses. Passing the attr set to NlMsgs decoding
no longer makes sense (if it ever did), attr set may differ message
by messsage. Isolate the part of decoding responsible for attr-set
specific interpretation and call it once we identified the correct op.

Without this fix performing SET operation on an ethtool socket, while
being subscribed to notifications causes:

 # File "tools/net/ynl/pyynl/lib/ynl.py", line 1096, in _op
 # Exception|     return self._ops(ops)[0]
 # Exception|            ~~~~~~~~~^^^^^
 # File "tools/net/ynl/pyynl/lib/ynl.py", line 1040, in _ops
 # Exception|     nms = NlMsgs(reply, attr_space=op.attr_set)
 # Exception|                                    ^^^^^^^^^^^

The value of op we use on line 1040 is stale, it comes form the previous
loop. If a notification comes before a response we will update op to None
and the next iteration thru the loop will break with the trace above.

Fixes: 6fda63c45fe8 ("tools/net/ynl: fix cli.py --subscribe feature")
Fixes: ba8be00f68f5 ("tools/net/ynl: Add multi message support to ynl")
Reviewed-by: Donald Hunter <donald.hunter@gmail.com>
Link: https://patch.msgid.link/20250618171746.1201403-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/net/ynl/pyynl/lib/ynl.py | 28 +++++++++++++++++-----------
 1 file changed, 17 insertions(+), 11 deletions(-)

diff --git a/tools/net/ynl/pyynl/lib/ynl.py b/tools/net/ynl/pyynl/lib/ynl.py
index 55b59f6c79b8..61deb5923067 100644
--- a/tools/net/ynl/pyynl/lib/ynl.py
+++ b/tools/net/ynl/pyynl/lib/ynl.py
@@ -231,14 +231,7 @@ class NlMsg:
                     self.extack['unknown'].append(extack)
 
             if attr_space:
-                # We don't have the ability to parse nests yet, so only do global
-                if 'miss-type' in self.extack and 'miss-nest' not in self.extack:
-                    miss_type = self.extack['miss-type']
-                    if miss_type in attr_space.attrs_by_val:
-                        spec = attr_space.attrs_by_val[miss_type]
-                        self.extack['miss-type'] = spec['name']
-                        if 'doc' in spec:
-                            self.extack['miss-type-doc'] = spec['doc']
+                self.annotate_extack(attr_space)
 
     def _decode_policy(self, raw):
         policy = {}
@@ -264,6 +257,18 @@ class NlMsg:
                 policy['mask'] = attr.as_scalar('u64')
         return policy
 
+    def annotate_extack(self, attr_space):
+        """ Make extack more human friendly with attribute information """
+
+        # We don't have the ability to parse nests yet, so only do global
+        if 'miss-type' in self.extack and 'miss-nest' not in self.extack:
+            miss_type = self.extack['miss-type']
+            if miss_type in attr_space.attrs_by_val:
+                spec = attr_space.attrs_by_val[miss_type]
+                self.extack['miss-type'] = spec['name']
+                if 'doc' in spec:
+                    self.extack['miss-type-doc'] = spec['doc']
+
     def cmd(self):
         return self.nl_type
 
@@ -277,12 +282,12 @@ class NlMsg:
 
 
 class NlMsgs:
-    def __init__(self, data, attr_space=None):
+    def __init__(self, data):
         self.msgs = []
 
         offset = 0
         while offset < len(data):
-            msg = NlMsg(data, offset, attr_space=attr_space)
+            msg = NlMsg(data, offset)
             offset += msg.nl_len
             self.msgs.append(msg)
 
@@ -1034,12 +1039,13 @@ class YnlFamily(SpecFamily):
         op_rsp = []
         while not done:
             reply = self.sock.recv(self._recv_size)
-            nms = NlMsgs(reply, attr_space=op.attr_set)
+            nms = NlMsgs(reply)
             self._recv_dbg_print(reply, nms)
             for nl_msg in nms:
                 if nl_msg.nl_seq in reqs_by_seq:
                     (op, vals, req_msg, req_flags) = reqs_by_seq[nl_msg.nl_seq]
                     if nl_msg.extack:
+                        nl_msg.annotate_extack(op.attr_set)
                         self._decode_extack(req_msg, op, nl_msg.extack, vals)
                 else:
                     op = None

From edf8afeecfbb0b8c1a2edb8c8892d2f759d35321 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Thu, 19 Jun 2025 09:07:24 +0200
Subject: [PATCH 0640/1334] net: airoha: Compute number of descriptors
 according to reserved memory size

In order to not exceed the reserved memory size for hwfd buffers,
compute the number of hwfd buffers/descriptors according to the
reserved memory size and the size of each hwfd buffer (2KB).

Fixes: 3a1ce9e3d01b ("net: airoha: Add the capability to allocate hwfd buffers via reserved-memory")
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Link: https://patch.msgid.link/20250619-airoha-hw-num-desc-v4-1-49600a9b319a@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/airoha/airoha_eth.c | 21 ++++++++++++---------
 1 file changed, 12 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/airoha/airoha_eth.c b/drivers/net/ethernet/airoha/airoha_eth.c
index a7ec609d64de..1b7fd7ee0cbf 100644
--- a/drivers/net/ethernet/airoha/airoha_eth.c
+++ b/drivers/net/ethernet/airoha/airoha_eth.c
@@ -1065,19 +1065,13 @@ static void airoha_qdma_cleanup_tx_queue(struct airoha_queue *q)
 
 static int airoha_qdma_init_hfwd_queues(struct airoha_qdma *qdma)
 {
+	int size, index, num_desc = HW_DSCP_NUM;
 	struct airoha_eth *eth = qdma->eth;
 	int id = qdma - &eth->qdma[0];
 	dma_addr_t dma_addr;
 	const char *name;
-	int size, index;
 	u32 status;
 
-	size = HW_DSCP_NUM * sizeof(struct airoha_qdma_fwd_desc);
-	if (!dmam_alloc_coherent(eth->dev, size, &dma_addr, GFP_KERNEL))
-		return -ENOMEM;
-
-	airoha_qdma_wr(qdma, REG_FWD_DSCP_BASE, dma_addr);
-
 	name = devm_kasprintf(eth->dev, GFP_KERNEL, "qdma%d-buf", id);
 	if (!name)
 		return -ENOMEM;
@@ -1099,8 +1093,12 @@ static int airoha_qdma_init_hfwd_queues(struct airoha_qdma *qdma)
 		rmem = of_reserved_mem_lookup(np);
 		of_node_put(np);
 		dma_addr = rmem->base;
+		/* Compute the number of hw descriptors according to the
+		 * reserved memory size and the payload buffer size
+		 */
+		num_desc = rmem->size / AIROHA_MAX_PACKET_SIZE;
 	} else {
-		size = AIROHA_MAX_PACKET_SIZE * HW_DSCP_NUM;
+		size = AIROHA_MAX_PACKET_SIZE * num_desc;
 		if (!dmam_alloc_coherent(eth->dev, size, &dma_addr,
 					 GFP_KERNEL))
 			return -ENOMEM;
@@ -1108,6 +1106,11 @@ static int airoha_qdma_init_hfwd_queues(struct airoha_qdma *qdma)
 
 	airoha_qdma_wr(qdma, REG_FWD_BUF_BASE, dma_addr);
 
+	size = num_desc * sizeof(struct airoha_qdma_fwd_desc);
+	if (!dmam_alloc_coherent(eth->dev, size, &dma_addr, GFP_KERNEL))
+		return -ENOMEM;
+
+	airoha_qdma_wr(qdma, REG_FWD_DSCP_BASE, dma_addr);
 	airoha_qdma_rmw(qdma, REG_HW_FWD_DSCP_CFG,
 			HW_FWD_DSCP_PAYLOAD_SIZE_MASK,
 			FIELD_PREP(HW_FWD_DSCP_PAYLOAD_SIZE_MASK, 0));
@@ -1116,7 +1119,7 @@ static int airoha_qdma_init_hfwd_queues(struct airoha_qdma *qdma)
 	airoha_qdma_rmw(qdma, REG_LMGR_INIT_CFG,
 			LMGR_INIT_START | LMGR_SRAM_MODE_MASK |
 			HW_FWD_DESC_NUM_MASK,
-			FIELD_PREP(HW_FWD_DESC_NUM_MASK, HW_DSCP_NUM) |
+			FIELD_PREP(HW_FWD_DESC_NUM_MASK, num_desc) |
 			LMGR_INIT_START | LMGR_SRAM_MODE_MASK);
 
 	return read_poll_timeout(airoha_qdma_rr, status,

From 7b46bdaec00a675f6fac9d0b01a2105b5746ebe9 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Thu, 19 Jun 2025 09:07:25 +0200
Subject: [PATCH 0641/1334] net: airoha: Differentiate hwfd buffer size for
 QDMA0 and QDMA1

EN7581 SoC allows configuring the size and the number of buffers in
hwfd payload queue for both QDMA0 and QDMA1.
In order to reduce the required DRAM used for hwfd buffers queues and
decrease the memory footprint, differentiate hwfd buffer size for QDMA0
and QDMA1 and reduce hwfd buffer size to 1KB for QDMA1 (WAN) while
maintaining 2KB for QDMA0 (LAN).

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250619-airoha-hw-num-desc-v4-2-49600a9b319a@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/airoha/airoha_eth.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/airoha/airoha_eth.c b/drivers/net/ethernet/airoha/airoha_eth.c
index 1b7fd7ee0cbf..06dea3a13e77 100644
--- a/drivers/net/ethernet/airoha/airoha_eth.c
+++ b/drivers/net/ethernet/airoha/airoha_eth.c
@@ -1068,14 +1068,15 @@ static int airoha_qdma_init_hfwd_queues(struct airoha_qdma *qdma)
 	int size, index, num_desc = HW_DSCP_NUM;
 	struct airoha_eth *eth = qdma->eth;
 	int id = qdma - &eth->qdma[0];
+	u32 status, buf_size;
 	dma_addr_t dma_addr;
 	const char *name;
-	u32 status;
 
 	name = devm_kasprintf(eth->dev, GFP_KERNEL, "qdma%d-buf", id);
 	if (!name)
 		return -ENOMEM;
 
+	buf_size = id ? AIROHA_MAX_PACKET_SIZE / 2 : AIROHA_MAX_PACKET_SIZE;
 	index = of_property_match_string(eth->dev->of_node,
 					 "memory-region-names", name);
 	if (index >= 0) {
@@ -1096,9 +1097,9 @@ static int airoha_qdma_init_hfwd_queues(struct airoha_qdma *qdma)
 		/* Compute the number of hw descriptors according to the
 		 * reserved memory size and the payload buffer size
 		 */
-		num_desc = rmem->size / AIROHA_MAX_PACKET_SIZE;
+		num_desc = div_u64(rmem->size, buf_size);
 	} else {
-		size = AIROHA_MAX_PACKET_SIZE * num_desc;
+		size = buf_size * num_desc;
 		if (!dmam_alloc_coherent(eth->dev, size, &dma_addr,
 					 GFP_KERNEL))
 			return -ENOMEM;
@@ -1111,9 +1112,10 @@ static int airoha_qdma_init_hfwd_queues(struct airoha_qdma *qdma)
 		return -ENOMEM;
 
 	airoha_qdma_wr(qdma, REG_FWD_DSCP_BASE, dma_addr);
+	/* QDMA0: 2KB. QDMA1: 1KB */
 	airoha_qdma_rmw(qdma, REG_HW_FWD_DSCP_CFG,
 			HW_FWD_DSCP_PAYLOAD_SIZE_MASK,
-			FIELD_PREP(HW_FWD_DSCP_PAYLOAD_SIZE_MASK, 0));
+			FIELD_PREP(HW_FWD_DSCP_PAYLOAD_SIZE_MASK, !!id));
 	airoha_qdma_rmw(qdma, REG_FWD_DSCP_LOW_THR, FWD_DSCP_LOW_THR_MASK,
 			FIELD_PREP(FWD_DSCP_LOW_THR_MASK, 128));
 	airoha_qdma_rmw(qdma, REG_LMGR_INIT_CFG,

From b2348fe6c81cc92c7d0bd8a7d9241f8de0fa72b7 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Thu, 19 Jun 2025 12:25:41 -0400
Subject: [PATCH 0642/1334] bcachefs: Fix *__bch2_trans_subbuf_alloc() error
 path

Don't change buf->size on error - this would usually be a transaction
restart, but it could also be -ENOMEM - when we've exceeded the bump
allocator max).

Fixes: 247abee6ae6d ("bcachefs: btree_trans_subbuf")
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/btree_update.c | 16 +++++++++++-----
 1 file changed, 11 insertions(+), 5 deletions(-)

diff --git a/fs/bcachefs/btree_update.c b/fs/bcachefs/btree_update.c
index e97e78c10f49..ee657b9f4b96 100644
--- a/fs/bcachefs/btree_update.c
+++ b/fs/bcachefs/btree_update.c
@@ -549,20 +549,26 @@ void *__bch2_trans_subbuf_alloc(struct btree_trans *trans,
 				unsigned u64s)
 {
 	unsigned new_top = buf->u64s + u64s;
-	unsigned old_size = buf->size;
+	unsigned new_size = buf->size;
 
-	if (new_top > buf->size)
-		buf->size = roundup_pow_of_two(new_top);
+	BUG_ON(roundup_pow_of_two(new_top) > U16_MAX);
 
-	void *n = bch2_trans_kmalloc_nomemzero(trans, buf->size * sizeof(u64));
+	if (new_top > new_size)
+		new_size = roundup_pow_of_two(new_top);
+
+	void *n = bch2_trans_kmalloc_nomemzero(trans, new_size * sizeof(u64));
 	if (IS_ERR(n))
 		return n;
 
+	unsigned offset = (u64 *) n - (u64 *) trans->mem;
+	BUG_ON(offset > U16_MAX);
+
 	if (buf->u64s)
 		memcpy(n,
 		       btree_trans_subbuf_base(trans, buf),
-		       old_size * sizeof(u64));
+		       buf->size * sizeof(u64));
 	buf->base = (u64 *) n - (u64 *) trans->mem;
+	buf->size = new_size;
 
 	void *p = btree_trans_subbuf_top(trans, buf);
 	buf->u64s = new_top;

From 32a01cd4334175a0ae42b3c3d7f37fd26468ecc3 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Thu, 19 Jun 2025 12:50:06 -0400
Subject: [PATCH 0643/1334] bcachefs: Don't log fsck err in the journal if
 doing repair elsewhere

This fixes exceeding the bump allocator limit when the allocator finds
many buckets that need repair - they're repaired asynchronously, which
means that every error logged a message in the bump allocator, without
committing.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/alloc_background.c | 13 +++++++++----
 fs/bcachefs/btree_iter.c       |  4 ++++
 fs/bcachefs/error.c            |  4 +++-
 fs/bcachefs/sb-errors_format.h |  7 ++++---
 4 files changed, 20 insertions(+), 8 deletions(-)

diff --git a/fs/bcachefs/alloc_background.c b/fs/bcachefs/alloc_background.c
index b228a5a64479..66de46318620 100644
--- a/fs/bcachefs/alloc_background.c
+++ b/fs/bcachefs/alloc_background.c
@@ -1406,6 +1406,9 @@ int bch2_check_discard_freespace_key(struct btree_trans *trans, struct btree_ite
 		: BCH_DATA_free;
 	struct printbuf buf = PRINTBUF;
 
+	unsigned fsck_flags = (async_repair ? FSCK_ERR_NO_LOG : 0)|
+		FSCK_CAN_FIX|FSCK_CAN_IGNORE;
+
 	struct bpos bucket = iter->pos;
 	bucket.offset &= ~(~0ULL << 56);
 	u64 genbits = iter->pos.offset & (~0ULL << 56);
@@ -1419,9 +1422,10 @@ int bch2_check_discard_freespace_key(struct btree_trans *trans, struct btree_ite
 		return ret;
 
 	if (!bch2_dev_bucket_exists(c, bucket)) {
-		if (fsck_err(trans, need_discard_freespace_key_to_invalid_dev_bucket,
-			     "entry in %s btree for nonexistant dev:bucket %llu:%llu",
-			     bch2_btree_id_str(iter->btree_id), bucket.inode, bucket.offset))
+		if (__fsck_err(trans, fsck_flags,
+			       need_discard_freespace_key_to_invalid_dev_bucket,
+			       "entry in %s btree for nonexistant dev:bucket %llu:%llu",
+			       bch2_btree_id_str(iter->btree_id), bucket.inode, bucket.offset))
 			goto delete;
 		ret = 1;
 		goto out;
@@ -1433,7 +1437,8 @@ int bch2_check_discard_freespace_key(struct btree_trans *trans, struct btree_ite
 	if (a->data_type != state ||
 	    (state == BCH_DATA_free &&
 	     genbits != alloc_freespace_genbits(*a))) {
-		if (fsck_err(trans, need_discard_freespace_key_bad,
+		if (__fsck_err(trans, fsck_flags,
+			       need_discard_freespace_key_bad,
 			     "%s\nincorrectly set at %s:%llu:%llu:0 (free %u, genbits %llu should be %llu)",
 			     (bch2_bkey_val_to_text(&buf, c, alloc_k), buf.buf),
 			     bch2_btree_id_str(iter->btree_id),
diff --git a/fs/bcachefs/btree_iter.c b/fs/bcachefs/btree_iter.c
index 061603999ae5..352f9cd2634f 100644
--- a/fs/bcachefs/btree_iter.c
+++ b/fs/bcachefs/btree_iter.c
@@ -3194,6 +3194,10 @@ void *__bch2_trans_kmalloc(struct btree_trans *trans, size_t size, unsigned long
 	if (WARN_ON_ONCE(new_bytes > BTREE_TRANS_MEM_MAX)) {
 #ifdef CONFIG_BCACHEFS_TRANS_KMALLOC_TRACE
 		struct printbuf buf = PRINTBUF;
+		bch2_log_msg_start(c, &buf);
+		prt_printf(&buf, "bump allocator exceeded BTREE_TRANS_MEM_MAX (%u)\n",
+			   BTREE_TRANS_MEM_MAX);
+
 		bch2_trans_kmalloc_trace_to_text(&buf, &trans->trans_kmalloc_trace);
 		bch2_print_str(c, KERN_ERR, buf.buf);
 		printbuf_exit(&buf);
diff --git a/fs/bcachefs/error.c b/fs/bcachefs/error.c
index a8ec6aae5738..b2a6c041e165 100644
--- a/fs/bcachefs/error.c
+++ b/fs/bcachefs/error.c
@@ -621,7 +621,9 @@ print:
 	if (s)
 		s->ret = ret;
 
-	if (trans)
+	if (trans &&
+	    !(flags & FSCK_ERR_NO_LOG) &&
+	    ret == -BCH_ERR_fsck_fix)
 		ret = bch2_trans_log_str(trans, bch2_sb_error_strs[err]) ?: ret;
 err_unlock:
 	mutex_unlock(&c->fsck_error_msgs_lock);
diff --git a/fs/bcachefs/sb-errors_format.h b/fs/bcachefs/sb-errors_format.h
index f1aa40542a0e..041887aad63a 100644
--- a/fs/bcachefs/sb-errors_format.h
+++ b/fs/bcachefs/sb-errors_format.h
@@ -3,9 +3,10 @@
 #define _BCACHEFS_SB_ERRORS_FORMAT_H
 
 enum bch_fsck_flags {
-	FSCK_CAN_FIX		= 1 << 0,
-	FSCK_CAN_IGNORE		= 1 << 1,
-	FSCK_AUTOFIX		= 1 << 2,
+	FSCK_CAN_FIX		= BIT(0),
+	FSCK_CAN_IGNORE		= BIT(1),
+	FSCK_AUTOFIX		= BIT(2),
+	FSCK_ERR_NO_LOG		= BIT(3),
 };
 
 #define BCH_SB_ERRS()									\

From 6463cbe08b0cbf9bba8763306764f5fd643023e1 Mon Sep 17 00:00:00 2001
From: Pablo Martin-Gomez <pmartin-gomez@freebox.fr>
Date: Wed, 18 Jun 2025 13:35:16 +0200
Subject: [PATCH 0644/1334] mtd: spinand: fix memory leak of ECC engine conf

Memory allocated for the ECC engine conf is not released during spinand
cleanup. Below kmemleak trace is seen for this memory leak:

unreferenced object 0xffffff80064f00e0 (size 8):
  comm "swapper/0", pid 1, jiffies 4294937458
  hex dump (first 8 bytes):
    00 00 00 00 00 00 00 00                          ........
  backtrace (crc 0):
    kmemleak_alloc+0x30/0x40
    __kmalloc_cache_noprof+0x208/0x3c0
    spinand_ondie_ecc_init_ctx+0x114/0x200
    nand_ecc_init_ctx+0x70/0xa8
    nanddev_ecc_engine_init+0xec/0x27c
    spinand_probe+0xa2c/0x1620
    spi_mem_probe+0x130/0x21c
    spi_probe+0xf0/0x170
    really_probe+0x17c/0x6e8
    __driver_probe_device+0x17c/0x21c
    driver_probe_device+0x58/0x180
    __device_attach_driver+0x15c/0x1f8
    bus_for_each_drv+0xec/0x150
    __device_attach+0x188/0x24c
    device_initial_probe+0x10/0x20
    bus_probe_device+0x11c/0x160

Fix the leak by calling nanddev_ecc_engine_cleanup() inside
spinand_cleanup().

Signed-off-by: Pablo Martin-Gomez <pmartin-gomez@freebox.fr>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/spi/core.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/mtd/nand/spi/core.c b/drivers/mtd/nand/spi/core.c
index 7099db7a62be..c411fe9be3ef 100644
--- a/drivers/mtd/nand/spi/core.c
+++ b/drivers/mtd/nand/spi/core.c
@@ -1585,6 +1585,7 @@ static void spinand_cleanup(struct spinand_device *spinand)
 {
 	struct nand_device *nand = spinand_to_nand(spinand);
 
+	nanddev_ecc_engine_cleanup(nand);
 	nanddev_cleanup(nand);
 	spinand_manufacturer_cleanup(spinand);
 	kfree(spinand->databuf);

From b2e2bed119809a5ca384241e0631f04c6142ae08 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Thu, 19 Jun 2025 14:32:57 -0400
Subject: [PATCH 0645/1334] bcachefs: Add missing key type checks to
 check_snapshot_exists()

For now we only have one key type in these btrees, but forward
compatibility means we do have to check.

Reported-by: syzbot+b4cb4a6988aced0cec4b@syzkaller.appspotmail.com
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/snapshot.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/fs/bcachefs/snapshot.c b/fs/bcachefs/snapshot.c
index 38aeaa128d27..4c43d2a2c1f5 100644
--- a/fs/bcachefs/snapshot.c
+++ b/fs/bcachefs/snapshot.c
@@ -871,7 +871,8 @@ static int check_snapshot_exists(struct btree_trans *trans, u32 id)
 
 	for_each_btree_key_norestart(trans, iter, BTREE_ID_snapshot_trees, POS_MIN,
 				     0, k, ret) {
-		if (le32_to_cpu(bkey_s_c_to_snapshot_tree(k).v->root_snapshot) == id) {
+		if (k.k->type == KEY_TYPE_snapshot_tree &&
+		    le32_to_cpu(bkey_s_c_to_snapshot_tree(k).v->root_snapshot) == id) {
 			tree_id = k.k->p.offset;
 			break;
 		}
@@ -899,7 +900,8 @@ static int check_snapshot_exists(struct btree_trans *trans, u32 id)
 
 	for_each_btree_key_norestart(trans, iter, BTREE_ID_subvolumes, POS_MIN,
 				     0, k, ret) {
-		if (le32_to_cpu(bkey_s_c_to_subvolume(k).v->snapshot) == id) {
+		if (k.k->type == KEY_TYPE_subvolume &&
+		    le32_to_cpu(bkey_s_c_to_subvolume(k).v->snapshot) == id) {
 			snapshot->v.subvol = cpu_to_le32(k.k->p.offset);
 			SET_BCH_SNAPSHOT_SUBVOL(&snapshot->v, true);
 			break;

From fde46f60f6c5138ee422087addbc5bf5b4968bf1 Mon Sep 17 00:00:00 2001
From: Stephen Smalley <stephen.smalley.work@gmail.com>
Date: Tue, 10 Jun 2025 15:48:27 -0400
Subject: [PATCH 0646/1334] selinux: change security_compute_sid to return the
 ssid or tsid on match

If the end result of a security_compute_sid() computation matches the
ssid or tsid, return that SID rather than looking it up again. This
avoids the problem of multiple initial SIDs that map to the same
context.

Cc: stable@vger.kernel.org
Reported-by: Guido Trentalancia <guido@trentalancia.com>
Fixes: ae254858ce07 ("selinux: introduce an initial SID for early boot processes")
Signed-off-by: Stephen Smalley <stephen.smalley.work@gmail.com>
Tested-by: Guido Trentalancia <guido@trentalancia.com>
Signed-off-by: Paul Moore <paul@paul-moore.com>
---
 security/selinux/ss/services.c | 16 +++++++++++-----
 1 file changed, 11 insertions(+), 5 deletions(-)

diff --git a/security/selinux/ss/services.c b/security/selinux/ss/services.c
index 7becf3808818..d185754c2786 100644
--- a/security/selinux/ss/services.c
+++ b/security/selinux/ss/services.c
@@ -1909,11 +1909,17 @@ retry:
 			goto out_unlock;
 	}
 	/* Obtain the sid for the context. */
-	rc = sidtab_context_to_sid(sidtab, &newcontext, out_sid);
-	if (rc == -ESTALE) {
-		rcu_read_unlock();
-		context_destroy(&newcontext);
-		goto retry;
+	if (context_equal(scontext, &newcontext))
+		*out_sid = ssid;
+	else if (context_equal(tcontext, &newcontext))
+		*out_sid = tsid;
+	else {
+		rc = sidtab_context_to_sid(sidtab, &newcontext, out_sid);
+		if (rc == -ESTALE) {
+			rcu_read_unlock();
+			context_destroy(&newcontext);
+			goto retry;
+		}
 	}
 out_unlock:
 	rcu_read_unlock();

From e0fca6f2cebff539e9317a15a37dcf432e3b851a Mon Sep 17 00:00:00 2001
From: Long Li <longli@microsoft.com>
Date: Tue, 17 Jun 2025 18:36:46 -0700
Subject: [PATCH 0647/1334] net: mana: Record doorbell physical address in PF
 mode

MANA supports RDMA in PF mode. The driver should record the doorbell
physical address when in PF mode.

The doorbell physical address is used by the RDMA driver to map
doorbell pages of the device to user-mode applications through RDMA
verbs interface. In the past, they have been mapped to user-mode while
the device is in VF mode. With the support for PF mode implemented,
also expose those pages in PF mode.

Support for PF mode is implemented in
290e5d3c49f6 ("net: mana: Add support for Multi Vports on Bare metal")

Signed-off-by: Long Li <longli@microsoft.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/1750210606-12167-1-git-send-email-longli@linuxonhyperv.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/microsoft/mana/gdma_main.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c
index 3504507477c6..52cf7112762c 100644
--- a/drivers/net/ethernet/microsoft/mana/gdma_main.c
+++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c
@@ -31,6 +31,9 @@ static void mana_gd_init_pf_regs(struct pci_dev *pdev)
 	gc->db_page_base = gc->bar0_va +
 				mana_gd_r64(gc, GDMA_PF_REG_DB_PAGE_OFF);
 
+	gc->phys_db_page_base = gc->bar0_pa +
+				mana_gd_r64(gc, GDMA_PF_REG_DB_PAGE_OFF);
+
 	sriov_base_off = mana_gd_r64(gc, GDMA_SRIOV_REG_CFG_BASE_OFF);
 
 	sriov_base_va = gc->bar0_va + sriov_base_off;

From 6306e0c5a0d28e9df2b5902f4a021204bee75173 Mon Sep 17 00:00:00 2001
From: Sascha Hauer <s.hauer@pengutronix.de>
Date: Thu, 12 Jun 2025 14:56:57 +0200
Subject: [PATCH 0648/1334] clk: scmi: Handle case where child clocks are
 initialized before their parents

The SCMI clock driver currently assumes that parent clocks are always
initialized before their children. However, this assumption can fail if
a child clock is encountered before its parent during probe.

This leads to an issue during initialization of the parent_data array:

    sclk->parent_data[i].hw = hws[sclk->info->parents[i]];

If the parent clock's hardware structure has not been initialized yet,
this assignment results in invalid data.

To resolve this, allocate all struct scmi_clk instances as a contiguous
array at the beginning of the probe and populate the hws[] array
upfront. This ensures that any parent referenced later is already
initialized, regardless of the order in which clocks are processed.

Note that we can no longer free individual scmi_clk instances if
scmi_clk_ops_init() fails which shouldn't be a problem if the SCMI
platform has proper per-agent clock discovery.

Fixes: 65a8a3dd3b95f ("clk: scmi: Add support for clock {set,get}_parent")
Reviewed-by: peng.fan@nxp.com
Reviewed-by: Cristian Marussi <cristian.marussi@arm.com>
Reviewed-by: Sudeep Holla <sudeep.holla@arm.com>
Signed-off-by: Sascha Hauer <s.hauer@pengutronix.de>
Link: https://lore.kernel.org/r/20250612-clk-scmi-children-parent-fix-v3-1-7de52a27593d@pengutronix.de
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/clk-scmi.c | 20 +++++++++++---------
 1 file changed, 11 insertions(+), 9 deletions(-)

diff --git a/drivers/clk/clk-scmi.c b/drivers/clk/clk-scmi.c
index 15510c2ff21c..1b1561c84127 100644
--- a/drivers/clk/clk-scmi.c
+++ b/drivers/clk/clk-scmi.c
@@ -404,6 +404,7 @@ static int scmi_clocks_probe(struct scmi_device *sdev)
 	const struct scmi_handle *handle = sdev->handle;
 	struct scmi_protocol_handle *ph;
 	const struct clk_ops *scmi_clk_ops_db[SCMI_MAX_CLK_OPS] = {};
+	struct scmi_clk *sclks;
 
 	if (!handle)
 		return -ENODEV;
@@ -430,18 +431,21 @@ static int scmi_clocks_probe(struct scmi_device *sdev)
 	transport_is_atomic = handle->is_transport_atomic(handle,
 							  &atomic_threshold_us);
 
-	for (idx = 0; idx < count; idx++) {
-		struct scmi_clk *sclk;
-		const struct clk_ops *scmi_ops;
+	sclks = devm_kcalloc(dev, count, sizeof(*sclks), GFP_KERNEL);
+	if (!sclks)
+		return -ENOMEM;
 
-		sclk = devm_kzalloc(dev, sizeof(*sclk), GFP_KERNEL);
-		if (!sclk)
-			return -ENOMEM;
+	for (idx = 0; idx < count; idx++)
+		hws[idx] = &sclks[idx].hw;
+
+	for (idx = 0; idx < count; idx++) {
+		struct scmi_clk *sclk = &sclks[idx];
+		const struct clk_ops *scmi_ops;
 
 		sclk->info = scmi_proto_clk_ops->info_get(ph, idx);
 		if (!sclk->info) {
 			dev_dbg(dev, "invalid clock info for idx %d\n", idx);
-			devm_kfree(dev, sclk);
+			hws[idx] = NULL;
 			continue;
 		}
 
@@ -479,13 +483,11 @@ static int scmi_clocks_probe(struct scmi_device *sdev)
 		if (err) {
 			dev_err(dev, "failed to register clock %d\n", idx);
 			devm_kfree(dev, sclk->parent_data);
-			devm_kfree(dev, sclk);
 			hws[idx] = NULL;
 		} else {
 			dev_dbg(dev, "Registered clock:%s%s\n",
 				sclk->info->name,
 				scmi_ops->enable ? " (atomic ops)" : "");
-			hws[idx] = &sclk->hw;
 		}
 	}
 

From aacc875a448d363332b9df0621dde6d3a225ea9f Mon Sep 17 00:00:00 2001
From: Xiaolei Wang <xiaolei.wang@windriver.com>
Date: Thu, 19 Jun 2025 14:21:08 +0800
Subject: [PATCH 0649/1334] clk: imx: Fix an out-of-bounds access in
 dispmix_csr_clk_dev_data

When num_parents is 4, __clk_register() occurs an out-of-bounds
when accessing parent_names member. Use ARRAY_SIZE() instead of
hardcode number here.

 BUG: KASAN: global-out-of-bounds in __clk_register+0x1844/0x20d8
 Read of size 8 at addr ffff800086988e78 by task kworker/u24:3/59
  Hardware name: NXP i.MX95 19X19 board (DT)
  Workqueue: events_unbound deferred_probe_work_func
  Call trace:
    dump_backtrace+0x94/0xec
    show_stack+0x18/0x24
    dump_stack_lvl+0x8c/0xcc
    print_report+0x398/0x5fc
    kasan_report+0xd4/0x114
    __asan_report_load8_noabort+0x20/0x2c
    __clk_register+0x1844/0x20d8
    clk_hw_register+0x44/0x110
    __clk_hw_register_mux+0x284/0x3a8
    imx95_bc_probe+0x4f4/0xa70

Fixes: 5224b189462f ("clk: imx: add i.MX95 BLK CTL clk driver")
Cc: stable@vger.kernel.org
Reviewed-by: Frank Li <Frank.Li@nxp.com>
Signed-off-by: Xiaolei Wang <xiaolei.wang@windriver.com>
Link: https://lore.kernel.org/r/20250619062108.2016511-1-xiaolei.wang@windriver.com
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/imx/clk-imx95-blk-ctl.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/drivers/clk/imx/clk-imx95-blk-ctl.c b/drivers/clk/imx/clk-imx95-blk-ctl.c
index 25974947ad0c..cc2ee2be1819 100644
--- a/drivers/clk/imx/clk-imx95-blk-ctl.c
+++ b/drivers/clk/imx/clk-imx95-blk-ctl.c
@@ -219,11 +219,15 @@ static const struct imx95_blk_ctl_dev_data lvds_csr_dev_data = {
 	.clk_reg_offset = 0,
 };
 
+static const char * const disp_engine_parents[] = {
+	"videopll1", "dsi_pll", "ldb_pll_div7"
+};
+
 static const struct imx95_blk_ctl_clk_dev_data dispmix_csr_clk_dev_data[] = {
 	[IMX95_CLK_DISPMIX_ENG0_SEL] = {
 		.name = "disp_engine0_sel",
-		.parent_names = (const char *[]){"videopll1", "dsi_pll", "ldb_pll_div7", },
-		.num_parents = 4,
+		.parent_names = disp_engine_parents,
+		.num_parents = ARRAY_SIZE(disp_engine_parents),
 		.reg = 0,
 		.bit_idx = 0,
 		.bit_width = 2,
@@ -232,8 +236,8 @@ static const struct imx95_blk_ctl_clk_dev_data dispmix_csr_clk_dev_data[] = {
 	},
 	[IMX95_CLK_DISPMIX_ENG1_SEL] = {
 		.name = "disp_engine1_sel",
-		.parent_names = (const char *[]){"videopll1", "dsi_pll", "ldb_pll_div7", },
-		.num_parents = 4,
+		.parent_names = disp_engine_parents,
+		.num_parents = ARRAY_SIZE(disp_engine_parents),
 		.reg = 0,
 		.bit_idx = 2,
 		.bit_width = 2,

From 752eb816b55adb0673727ba0ed96609a17895654 Mon Sep 17 00:00:00 2001
From: Chen Yu <yu.c.chen@intel.com>
Date: Wed, 4 Jun 2025 12:25:56 +0800
Subject: [PATCH 0650/1334] scsi: megaraid_sas: Fix invalid node index

On a system with DRAM interleave enabled, out-of-bound access is
detected:

megaraid_sas 0000:3f:00.0: requested/available msix 128/128 poll_queue 0
------------[ cut here ]------------
UBSAN: array-index-out-of-bounds in ./arch/x86/include/asm/topology.h:72:28
index -1 is out of range for type 'cpumask *[1024]'
dump_stack_lvl+0x5d/0x80
ubsan_epilogue+0x5/0x2b
__ubsan_handle_out_of_bounds.cold+0x46/0x4b
megasas_alloc_irq_vectors+0x149/0x190 [megaraid_sas]
megasas_probe_one.cold+0xa4d/0x189c [megaraid_sas]
local_pci_probe+0x42/0x90
pci_device_probe+0xdc/0x290
really_probe+0xdb/0x340
__driver_probe_device+0x78/0x110
driver_probe_device+0x1f/0xa0
__driver_attach+0xba/0x1c0
bus_for_each_dev+0x8b/0xe0
bus_add_driver+0x142/0x220
driver_register+0x72/0xd0
megasas_init+0xdf/0xff0 [megaraid_sas]
do_one_initcall+0x57/0x310
do_init_module+0x90/0x250
init_module_from_file+0x85/0xc0
idempotent_init_module+0x114/0x310
__x64_sys_finit_module+0x65/0xc0
do_syscall_64+0x82/0x170
entry_SYSCALL_64_after_hwframe+0x76/0x7e

Fix it accordingly.

Signed-off-by: Chen Yu <yu.c.chen@intel.com>
Link: https://lore.kernel.org/r/20250604042556.3731059-1-yu.c.chen@intel.com
Fixes: 8049da6f3943 ("scsi: megaraid_sas: Use irq_set_affinity_and_hint()")
Cc: stable@vger.kernel.org
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/megaraid/megaraid_sas_base.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c
index 3aac0e17cb00..9179f8aee964 100644
--- a/drivers/scsi/megaraid/megaraid_sas_base.c
+++ b/drivers/scsi/megaraid/megaraid_sas_base.c
@@ -5910,7 +5910,11 @@ megasas_set_high_iops_queue_affinity_and_hint(struct megasas_instance *instance)
 	const struct cpumask *mask;
 
 	if (instance->perf_mode == MR_BALANCED_PERF_MODE) {
-		mask = cpumask_of_node(dev_to_node(&instance->pdev->dev));
+		int nid = dev_to_node(&instance->pdev->dev);
+
+		if (nid == NUMA_NO_NODE)
+			nid = 0;
+		mask = cpumask_of_node(nid);
 
 		for (i = 0; i < instance->low_latency_index_start; i++) {
 			irq = pci_irq_vector(instance->pdev, i);

From 2e083cd802294693a5414e4557a183dd7e442e71 Mon Sep 17 00:00:00 2001
From: anvithdosapati <anvithdosapati@google.com>
Date: Mon, 16 Jun 2025 08:57:34 +0000
Subject: [PATCH 0651/1334] scsi: ufs: core: Fix clk scaling to be conditional
 in reset and restore

In ufshcd_host_reset_and_restore(), scale up clocks only when clock
scaling is supported. Without this change CPU latency is voted for 0
(ufshcd_pm_qos_update) during resume unconditionally.

Signed-off-by: anvithdosapati <anvithdosapati@google.com>
Link: https://lore.kernel.org/r/20250616085734.2133581-1-anvithdosapati@google.com
Fixes: a3cd5ec55f6c ("scsi: ufs: add load based scaling of UFS gear")
Cc: stable@vger.kernel.org
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/ufs/core/ufshcd.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index f62d89c8e580..50adfb8b335b 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -7807,7 +7807,8 @@ static int ufshcd_host_reset_and_restore(struct ufs_hba *hba)
 	hba->silence_err_logs = false;
 
 	/* scale up clocks to max frequency before full reinitialization */
-	ufshcd_scale_clks(hba, ULONG_MAX, true);
+	if (ufshcd_is_clkscaling_supported(hba))
+		ufshcd_scale_clks(hba, ULONG_MAX, true);
 
 	err = ufshcd_hba_enable(hba);
 

From a35b29bdedb4d2ae3160d4d6684a6f1ecd9ca7c2 Mon Sep 17 00:00:00 2001
From: Karan Tilak Kumar <kartilak@cisco.com>
Date: Tue, 17 Jun 2025 17:34:28 -0700
Subject: [PATCH 0652/1334] scsi: fnic: Fix crash in fnic_wq_cmpl_handler when
 FDMI times out

When both the RHBA and RPA FDMI requests time out, fnic reuses a frame to
send ABTS for each of them. On send completion, this causes an attempt to
free the same frame twice that leads to a crash.

Fix crash by allocating separate frames for RHBA and RPA, and modify ABTS
logic accordingly.

Tested by checking MDS for FDMI information.

Tested by using instrumented driver to:

 - Drop PLOGI response
 - Drop RHBA response
 - Drop RPA response
 - Drop RHBA and RPA response
 - Drop PLOGI response + ABTS response
 - Drop RHBA response + ABTS response
 - Drop RPA response + ABTS response
 - Drop RHBA and RPA response + ABTS response for both of them

Fixes: 09c1e6ab4ab2 ("scsi: fnic: Add and integrate support for FDMI")
Reviewed-by: Sesidhar Baddela <sebaddel@cisco.com>
Reviewed-by: Arulprabhu Ponnusamy <arulponn@cisco.com>
Reviewed-by: Gian Carlo Boffa <gcboffa@cisco.com>
Tested-by: Arun Easi <aeasi@cisco.com>
Co-developed-by: Arun Easi <aeasi@cisco.com>
Signed-off-by: Arun Easi <aeasi@cisco.com>
Tested-by: Karan Tilak Kumar <kartilak@cisco.com>
Cc: stable@vger.kernel.org
Signed-off-by: Karan Tilak Kumar <kartilak@cisco.com>
Link: https://lore.kernel.org/r/20250618003431.6314-1-kartilak@cisco.com
Reviewed-by: John Meneghini <jmeneghi@redhat.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/fnic/fdls_disc.c | 113 +++++++++++++++++++++++++---------
 drivers/scsi/fnic/fnic.h      |   2 +-
 drivers/scsi/fnic/fnic_fdls.h |   1 +
 3 files changed, 87 insertions(+), 29 deletions(-)

diff --git a/drivers/scsi/fnic/fdls_disc.c b/drivers/scsi/fnic/fdls_disc.c
index f8ab69c51dab..36b498ad55b4 100644
--- a/drivers/scsi/fnic/fdls_disc.c
+++ b/drivers/scsi/fnic/fdls_disc.c
@@ -763,47 +763,69 @@ static void fdls_send_fabric_abts(struct fnic_iport_s *iport)
 	iport->fabric.timer_pending = 1;
 }
 
-static void fdls_send_fdmi_abts(struct fnic_iport_s *iport)
+static uint8_t *fdls_alloc_init_fdmi_abts_frame(struct fnic_iport_s *iport,
+		uint16_t oxid)
 {
-	uint8_t *frame;
+	struct fc_frame_header *pfdmi_abts;
 	uint8_t d_id[3];
+	uint8_t *frame;
 	struct fnic *fnic = iport->fnic;
-	struct fc_frame_header *pfabric_abts;
-	unsigned long fdmi_tov;
-	uint16_t oxid;
-	uint16_t frame_size = FNIC_ETH_FCOE_HDRS_OFFSET +
-			sizeof(struct fc_frame_header);
 
 	frame = fdls_alloc_frame(iport);
 	if (frame == NULL) {
 		FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num,
 				"Failed to allocate frame to send FDMI ABTS");
-		return;
+		return NULL;
 	}
 
-	pfabric_abts = (struct fc_frame_header *) (frame + FNIC_ETH_FCOE_HDRS_OFFSET);
+	pfdmi_abts = (struct fc_frame_header *) (frame + FNIC_ETH_FCOE_HDRS_OFFSET);
 	fdls_init_fabric_abts_frame(frame, iport);
 
 	hton24(d_id, FC_FID_MGMT_SERV);
-	FNIC_STD_SET_D_ID(*pfabric_abts, d_id);
+	FNIC_STD_SET_D_ID(*pfdmi_abts, d_id);
+	FNIC_STD_SET_OX_ID(*pfdmi_abts, oxid);
+
+	return frame;
+}
+
+static void fdls_send_fdmi_abts(struct fnic_iport_s *iport)
+{
+	uint8_t *frame;
+	unsigned long fdmi_tov;
+	uint16_t frame_size = FNIC_ETH_FCOE_HDRS_OFFSET +
+			sizeof(struct fc_frame_header);
 
 	if (iport->fabric.fdmi_pending & FDLS_FDMI_PLOGI_PENDING) {
-		oxid = iport->active_oxid_fdmi_plogi;
-		FNIC_STD_SET_OX_ID(*pfabric_abts, oxid);
+		frame = fdls_alloc_init_fdmi_abts_frame(iport,
+						iport->active_oxid_fdmi_plogi);
+		if (frame == NULL)
+			return;
+
 		fnic_send_fcoe_frame(iport, frame, frame_size);
 	} else {
 		if (iport->fabric.fdmi_pending & FDLS_FDMI_REG_HBA_PENDING) {
-			oxid = iport->active_oxid_fdmi_rhba;
-			FNIC_STD_SET_OX_ID(*pfabric_abts, oxid);
+			frame = fdls_alloc_init_fdmi_abts_frame(iport,
+						iport->active_oxid_fdmi_rhba);
+			if (frame == NULL)
+				return;
+
 			fnic_send_fcoe_frame(iport, frame, frame_size);
 		}
 		if (iport->fabric.fdmi_pending & FDLS_FDMI_RPA_PENDING) {
-			oxid = iport->active_oxid_fdmi_rpa;
-			FNIC_STD_SET_OX_ID(*pfabric_abts, oxid);
+			frame = fdls_alloc_init_fdmi_abts_frame(iport,
+						iport->active_oxid_fdmi_rpa);
+			if (frame == NULL) {
+				if (iport->fabric.fdmi_pending & FDLS_FDMI_REG_HBA_PENDING)
+					goto arm_timer;
+				else
+					return;
+			}
+
 			fnic_send_fcoe_frame(iport, frame, frame_size);
 		}
 	}
 
+arm_timer:
 	fdmi_tov = jiffies + msecs_to_jiffies(2 * iport->e_d_tov);
 	mod_timer(&iport->fabric.fdmi_timer, round_jiffies(fdmi_tov));
 	iport->fabric.fdmi_pending |= FDLS_FDMI_ABORT_PENDING;
@@ -2245,6 +2267,21 @@ void fdls_fabric_timer_callback(struct timer_list *t)
 	spin_unlock_irqrestore(&fnic->fnic_lock, flags);
 }
 
+void fdls_fdmi_retry_plogi(struct fnic_iport_s *iport)
+{
+	struct fnic *fnic = iport->fnic;
+
+	iport->fabric.fdmi_pending = 0;
+	/* If max retries not exhausted, start over from fdmi plogi */
+	if (iport->fabric.fdmi_retry < FDLS_FDMI_MAX_RETRY) {
+		iport->fabric.fdmi_retry++;
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+					 "Retry FDMI PLOGI. FDMI retry: %d",
+					 iport->fabric.fdmi_retry);
+		fdls_send_fdmi_plogi(iport);
+	}
+}
+
 void fdls_fdmi_timer_callback(struct timer_list *t)
 {
 	struct fnic_fdls_fabric_s *fabric = timer_container_of(fabric, t,
@@ -2291,14 +2328,7 @@ void fdls_fdmi_timer_callback(struct timer_list *t)
 	FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
 		"fdmi timer callback : 0x%x\n", iport->fabric.fdmi_pending);
 
-	iport->fabric.fdmi_pending = 0;
-	/* If max retries not exhaused, start over from fdmi plogi */
-	if (iport->fabric.fdmi_retry < FDLS_FDMI_MAX_RETRY) {
-		iport->fabric.fdmi_retry++;
-		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
-					 "retry fdmi timer %d", iport->fabric.fdmi_retry);
-		fdls_send_fdmi_plogi(iport);
-	}
+	fdls_fdmi_retry_plogi(iport);
 	FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
 		"fdmi timer callback : 0x%x\n", iport->fabric.fdmi_pending);
 	spin_unlock_irqrestore(&fnic->fnic_lock, flags);
@@ -3716,11 +3746,32 @@ static void fdls_process_fdmi_abts_rsp(struct fnic_iport_s *iport,
 	switch (FNIC_FRAME_TYPE(oxid)) {
 	case FNIC_FRAME_TYPE_FDMI_PLOGI:
 		fdls_free_oxid(iport, oxid, &iport->active_oxid_fdmi_plogi);
+
+		iport->fabric.fdmi_pending &= ~FDLS_FDMI_PLOGI_PENDING;
+		iport->fabric.fdmi_pending &= ~FDLS_FDMI_ABORT_PENDING;
 		break;
 	case FNIC_FRAME_TYPE_FDMI_RHBA:
+		iport->fabric.fdmi_pending &= ~FDLS_FDMI_REG_HBA_PENDING;
+
+		/* If RPA is still pending, don't turn off ABORT PENDING.
+		 * We count on the timer to detect the ABTS timeout and take
+		 * corrective action.
+		 */
+		if (!(iport->fabric.fdmi_pending & FDLS_FDMI_RPA_PENDING))
+			iport->fabric.fdmi_pending &= ~FDLS_FDMI_ABORT_PENDING;
+
 		fdls_free_oxid(iport, oxid, &iport->active_oxid_fdmi_rhba);
 		break;
 	case FNIC_FRAME_TYPE_FDMI_RPA:
+		iport->fabric.fdmi_pending &= ~FDLS_FDMI_RPA_PENDING;
+
+		/* If RHBA is still pending, don't turn off ABORT PENDING.
+		 * We count on the timer to detect the ABTS timeout and take
+		 * corrective action.
+		 */
+		if (!(iport->fabric.fdmi_pending & FDLS_FDMI_REG_HBA_PENDING))
+			iport->fabric.fdmi_pending &= ~FDLS_FDMI_ABORT_PENDING;
+
 		fdls_free_oxid(iport, oxid, &iport->active_oxid_fdmi_rpa);
 		break;
 	default:
@@ -3730,10 +3781,16 @@ static void fdls_process_fdmi_abts_rsp(struct fnic_iport_s *iport,
 		break;
 	}
 
-	timer_delete_sync(&iport->fabric.fdmi_timer);
-	iport->fabric.fdmi_pending &= ~FDLS_FDMI_ABORT_PENDING;
-
-	fdls_send_fdmi_plogi(iport);
+	/*
+	 * Only if ABORT PENDING is off, delete the timer, and if no other
+	 * operations are pending, retry FDMI.
+	 * Otherwise, let the timer pop and take the appropriate action.
+	 */
+	if (!(iport->fabric.fdmi_pending & FDLS_FDMI_ABORT_PENDING)) {
+		timer_delete_sync(&iport->fabric.fdmi_timer);
+		if (!iport->fabric.fdmi_pending)
+			fdls_fdmi_retry_plogi(iport);
+	}
 }
 
 static void
diff --git a/drivers/scsi/fnic/fnic.h b/drivers/scsi/fnic/fnic.h
index 6c5f6046b1f5..86e293ce530d 100644
--- a/drivers/scsi/fnic/fnic.h
+++ b/drivers/scsi/fnic/fnic.h
@@ -30,7 +30,7 @@
 
 #define DRV_NAME		"fnic"
 #define DRV_DESCRIPTION		"Cisco FCoE HBA Driver"
-#define DRV_VERSION		"1.8.0.0"
+#define DRV_VERSION		"1.8.0.1"
 #define PFX			DRV_NAME ": "
 #define DFX                     DRV_NAME "%d: "
 
diff --git a/drivers/scsi/fnic/fnic_fdls.h b/drivers/scsi/fnic/fnic_fdls.h
index 8e610b65ad57..531d0b37e450 100644
--- a/drivers/scsi/fnic/fnic_fdls.h
+++ b/drivers/scsi/fnic/fnic_fdls.h
@@ -394,6 +394,7 @@ void fdls_send_tport_abts(struct fnic_iport_s *iport,
 bool fdls_delete_tport(struct fnic_iport_s *iport,
 		       struct fnic_tport_s *tport);
 void fdls_fdmi_timer_callback(struct timer_list *t);
+void fdls_fdmi_retry_plogi(struct fnic_iport_s *iport);
 
 /* fnic_fcs.c */
 void fnic_fdls_init(struct fnic *fnic, int usefip);

From 74f46a0524f8d2f01dc7ca95bb5fc463a8603e72 Mon Sep 17 00:00:00 2001
From: Karan Tilak Kumar <kartilak@cisco.com>
Date: Tue, 17 Jun 2025 17:34:29 -0700
Subject: [PATCH 0653/1334] scsi: fnic: Turn off FDMI ACTIVE flags on link down

When the link goes down and comes up, FDMI requests are not sent out
anymore.

Fix bug by turning off FNIC_FDMI_ACTIVE when the link goes down.

Fixes: 09c1e6ab4ab2 ("scsi: fnic: Add and integrate support for FDMI")
Reviewed-by: Sesidhar Baddela <sebaddel@cisco.com>
Reviewed-by: Arulprabhu Ponnusamy <arulponn@cisco.com>
Reviewed-by: Gian Carlo Boffa <gcboffa@cisco.com>
Reviewed-by: Arun Easi <aeasi@cisco.com>
Tested-by: Karan Tilak Kumar <kartilak@cisco.com>
Cc: stable@vger.kernel.org
Signed-off-by: Karan Tilak Kumar <kartilak@cisco.com>
Link: https://lore.kernel.org/r/20250618003431.6314-2-kartilak@cisco.com
Reviewed-by: John Meneghini <jmeneghi@redhat.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/fnic/fdls_disc.c | 9 ++++++---
 drivers/scsi/fnic/fnic.h      | 2 +-
 2 files changed, 7 insertions(+), 4 deletions(-)

diff --git a/drivers/scsi/fnic/fdls_disc.c b/drivers/scsi/fnic/fdls_disc.c
index 36b498ad55b4..fa9cf0b37d72 100644
--- a/drivers/scsi/fnic/fdls_disc.c
+++ b/drivers/scsi/fnic/fdls_disc.c
@@ -5029,9 +5029,12 @@ void fnic_fdls_link_down(struct fnic_iport_s *iport)
 		fdls_delete_tport(iport, tport);
 	}
 
-	if ((fnic_fdmi_support == 1) && (iport->fabric.fdmi_pending > 0)) {
-		timer_delete_sync(&iport->fabric.fdmi_timer);
-		iport->fabric.fdmi_pending = 0;
+	if (fnic_fdmi_support == 1) {
+		if (iport->fabric.fdmi_pending > 0) {
+			timer_delete_sync(&iport->fabric.fdmi_timer);
+			iport->fabric.fdmi_pending = 0;
+		}
+		iport->flags &= ~FNIC_FDMI_ACTIVE;
 	}
 
 	FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
diff --git a/drivers/scsi/fnic/fnic.h b/drivers/scsi/fnic/fnic.h
index 86e293ce530d..c2fdc6553e62 100644
--- a/drivers/scsi/fnic/fnic.h
+++ b/drivers/scsi/fnic/fnic.h
@@ -30,7 +30,7 @@
 
 #define DRV_NAME		"fnic"
 #define DRV_DESCRIPTION		"Cisco FCoE HBA Driver"
-#define DRV_VERSION		"1.8.0.1"
+#define DRV_VERSION		"1.8.0.2"
 #define PFX			DRV_NAME ": "
 #define DFX                     DRV_NAME "%d: "
 

From 9b9b8594654a79e3d4166356fd86cd5397477b24 Mon Sep 17 00:00:00 2001
From: Karan Tilak Kumar <kartilak@cisco.com>
Date: Tue, 17 Jun 2025 17:34:30 -0700
Subject: [PATCH 0654/1334] scsi: fnic: Add and improve logs in FDMI and FDMI
 ABTS paths

Add logs in FDMI and FDMI ABTS paths.

Modify log text in these paths.

Reviewed-by: Sesidhar Baddela <sebaddel@cisco.com>
Reviewed-by: Arulprabhu Ponnusamy <arulponn@cisco.com>
Reviewed-by: Gian Carlo Boffa <gcboffa@cisco.com>
Reviewed-by: Arun Easi <aeasi@cisco.com>
Reviewed-by: John Meneghini <jmeneghi@redhat.com>
Signed-off-by: Karan Tilak Kumar <kartilak@cisco.com>
Link: https://lore.kernel.org/r/20250618003431.6314-3-kartilak@cisco.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/fnic/fdls_disc.c | 65 +++++++++++++++++++++++++++++++----
 1 file changed, 58 insertions(+), 7 deletions(-)

diff --git a/drivers/scsi/fnic/fdls_disc.c b/drivers/scsi/fnic/fdls_disc.c
index fa9cf0b37d72..ae37f85f618b 100644
--- a/drivers/scsi/fnic/fdls_disc.c
+++ b/drivers/scsi/fnic/fdls_disc.c
@@ -791,6 +791,7 @@ static uint8_t *fdls_alloc_init_fdmi_abts_frame(struct fnic_iport_s *iport,
 static void fdls_send_fdmi_abts(struct fnic_iport_s *iport)
 {
 	uint8_t *frame;
+	struct fnic *fnic = iport->fnic;
 	unsigned long fdmi_tov;
 	uint16_t frame_size = FNIC_ETH_FCOE_HDRS_OFFSET +
 			sizeof(struct fc_frame_header);
@@ -801,6 +802,9 @@ static void fdls_send_fdmi_abts(struct fnic_iport_s *iport)
 		if (frame == NULL)
 			return;
 
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			 "0x%x: FDLS send FDMI PLOGI abts. iport->fabric.state: %d oxid: 0x%x",
+			 iport->fcid, iport->fabric.state, iport->active_oxid_fdmi_plogi);
 		fnic_send_fcoe_frame(iport, frame, frame_size);
 	} else {
 		if (iport->fabric.fdmi_pending & FDLS_FDMI_REG_HBA_PENDING) {
@@ -809,6 +813,9 @@ static void fdls_send_fdmi_abts(struct fnic_iport_s *iport)
 			if (frame == NULL)
 				return;
 
+			FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				 "0x%x: FDLS send FDMI RHBA abts. iport->fabric.state: %d oxid: 0x%x",
+				 iport->fcid, iport->fabric.state, iport->active_oxid_fdmi_rhba);
 			fnic_send_fcoe_frame(iport, frame, frame_size);
 		}
 		if (iport->fabric.fdmi_pending & FDLS_FDMI_RPA_PENDING) {
@@ -821,6 +828,9 @@ static void fdls_send_fdmi_abts(struct fnic_iport_s *iport)
 					return;
 			}
 
+			FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+				 "0x%x: FDLS send FDMI RPA abts. iport->fabric.state: %d oxid: 0x%x",
+				 iport->fcid, iport->fabric.state, iport->active_oxid_fdmi_rpa);
 			fnic_send_fcoe_frame(iport, frame, frame_size);
 		}
 	}
@@ -829,6 +839,10 @@ arm_timer:
 	fdmi_tov = jiffies + msecs_to_jiffies(2 * iport->e_d_tov);
 	mod_timer(&iport->fabric.fdmi_timer, round_jiffies(fdmi_tov));
 	iport->fabric.fdmi_pending |= FDLS_FDMI_ABORT_PENDING;
+
+	FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+		 "0x%x: iport->fabric.fdmi_pending: 0x%x",
+		 iport->fcid, iport->fabric.fdmi_pending);
 }
 
 static void fdls_send_fabric_flogi(struct fnic_iport_s *iport)
@@ -2294,7 +2308,7 @@ void fdls_fdmi_timer_callback(struct timer_list *t)
 	spin_lock_irqsave(&fnic->fnic_lock, flags);
 
 	FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
-		"fdmi timer callback : 0x%x\n", iport->fabric.fdmi_pending);
+		"iport->fabric.fdmi_pending: 0x%x\n", iport->fabric.fdmi_pending);
 
 	if (!iport->fabric.fdmi_pending) {
 		/* timer expired after fdmi responses received. */
@@ -2302,7 +2316,7 @@ void fdls_fdmi_timer_callback(struct timer_list *t)
 		return;
 	}
 	FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
-		"fdmi timer callback : 0x%x\n", iport->fabric.fdmi_pending);
+		"iport->fabric.fdmi_pending: 0x%x\n", iport->fabric.fdmi_pending);
 
 	/* if not abort pending, send an abort */
 	if (!(iport->fabric.fdmi_pending & FDLS_FDMI_ABORT_PENDING)) {
@@ -2311,26 +2325,37 @@ void fdls_fdmi_timer_callback(struct timer_list *t)
 		return;
 	}
 	FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
-		"fdmi timer callback : 0x%x\n", iport->fabric.fdmi_pending);
+		"iport->fabric.fdmi_pending: 0x%x\n", iport->fabric.fdmi_pending);
 
 	/* ABTS pending for an active fdmi request that is pending.
 	 * That means FDMI ABTS timed out
 	 * Schedule to free the OXID after 2*r_a_tov and proceed
 	 */
 	if (iport->fabric.fdmi_pending & FDLS_FDMI_PLOGI_PENDING) {
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			"FDMI PLOGI ABTS timed out. Schedule oxid free: 0x%x\n",
+			iport->active_oxid_fdmi_plogi);
 		fdls_schedule_oxid_free(iport, &iport->active_oxid_fdmi_plogi);
 	} else {
-		if (iport->fabric.fdmi_pending & FDLS_FDMI_REG_HBA_PENDING)
+		if (iport->fabric.fdmi_pending & FDLS_FDMI_REG_HBA_PENDING) {
+			FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+						"FDMI RHBA ABTS timed out. Schedule oxid free: 0x%x\n",
+						iport->active_oxid_fdmi_rhba);
 			fdls_schedule_oxid_free(iport, &iport->active_oxid_fdmi_rhba);
-		if (iport->fabric.fdmi_pending & FDLS_FDMI_RPA_PENDING)
+		}
+		if (iport->fabric.fdmi_pending & FDLS_FDMI_RPA_PENDING) {
+			FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+						"FDMI RPA ABTS timed out. Schedule oxid free: 0x%x\n",
+						iport->active_oxid_fdmi_rpa);
 			fdls_schedule_oxid_free(iport, &iport->active_oxid_fdmi_rpa);
+		}
 	}
 	FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
-		"fdmi timer callback : 0x%x\n", iport->fabric.fdmi_pending);
+		"iport->fabric.fdmi_pending: 0x%x\n", iport->fabric.fdmi_pending);
 
 	fdls_fdmi_retry_plogi(iport);
 	FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
-		"fdmi timer callback : 0x%x\n", iport->fabric.fdmi_pending);
+		"iport->fabric.fdmi_pending: 0x%x\n", iport->fabric.fdmi_pending);
 	spin_unlock_irqrestore(&fnic->fnic_lock, flags);
 }
 
@@ -3745,12 +3770,26 @@ static void fdls_process_fdmi_abts_rsp(struct fnic_iport_s *iport,
 
 	switch (FNIC_FRAME_TYPE(oxid)) {
 	case FNIC_FRAME_TYPE_FDMI_PLOGI:
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			"Received FDMI PLOGI ABTS rsp with oxid: 0x%x", oxid);
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			 "0x%x: iport->fabric.fdmi_pending: 0x%x",
+			 iport->fcid, iport->fabric.fdmi_pending);
 		fdls_free_oxid(iport, oxid, &iport->active_oxid_fdmi_plogi);
 
 		iport->fabric.fdmi_pending &= ~FDLS_FDMI_PLOGI_PENDING;
 		iport->fabric.fdmi_pending &= ~FDLS_FDMI_ABORT_PENDING;
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			 "0x%x: iport->fabric.fdmi_pending: 0x%x",
+			 iport->fcid, iport->fabric.fdmi_pending);
 		break;
 	case FNIC_FRAME_TYPE_FDMI_RHBA:
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			"Received FDMI RHBA ABTS rsp with oxid: 0x%x", oxid);
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			 "0x%x: iport->fabric.fdmi_pending: 0x%x",
+			 iport->fcid, iport->fabric.fdmi_pending);
+
 		iport->fabric.fdmi_pending &= ~FDLS_FDMI_REG_HBA_PENDING;
 
 		/* If RPA is still pending, don't turn off ABORT PENDING.
@@ -3761,8 +3800,17 @@ static void fdls_process_fdmi_abts_rsp(struct fnic_iport_s *iport,
 			iport->fabric.fdmi_pending &= ~FDLS_FDMI_ABORT_PENDING;
 
 		fdls_free_oxid(iport, oxid, &iport->active_oxid_fdmi_rhba);
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			 "0x%x: iport->fabric.fdmi_pending: 0x%x",
+			 iport->fcid, iport->fabric.fdmi_pending);
 		break;
 	case FNIC_FRAME_TYPE_FDMI_RPA:
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			"Received FDMI RPA ABTS rsp with oxid: 0x%x", oxid);
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			 "0x%x: iport->fabric.fdmi_pending: 0x%x",
+			 iport->fcid, iport->fabric.fdmi_pending);
+
 		iport->fabric.fdmi_pending &= ~FDLS_FDMI_RPA_PENDING;
 
 		/* If RHBA is still pending, don't turn off ABORT PENDING.
@@ -3773,6 +3821,9 @@ static void fdls_process_fdmi_abts_rsp(struct fnic_iport_s *iport,
 			iport->fabric.fdmi_pending &= ~FDLS_FDMI_ABORT_PENDING;
 
 		fdls_free_oxid(iport, oxid, &iport->active_oxid_fdmi_rpa);
+		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+			 "0x%x: iport->fabric.fdmi_pending: 0x%x",
+			 iport->fcid, iport->fabric.fdmi_pending);
 		break;
 	default:
 		FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,

From 18b5cb6f1fdda4454f55a31f7c78d94da62be495 Mon Sep 17 00:00:00 2001
From: Karan Tilak Kumar <kartilak@cisco.com>
Date: Tue, 17 Jun 2025 17:34:31 -0700
Subject: [PATCH 0655/1334] scsi: fnic: Set appropriate logging level for log
 message

Replace KERN_INFO with KERN_DEBUG for a log message.

Reviewed-by: Sesidhar Baddela <sebaddel@cisco.com>
Reviewed-by: Arulprabhu Ponnusamy <arulponn@cisco.com>
Reviewed-by: Gian Carlo Boffa <gcboffa@cisco.com>
Reviewed-by: Arun Easi <aeasi@cisco.com>
Signed-off-by: Karan Tilak Kumar <kartilak@cisco.com>
Link: https://lore.kernel.org/stable/20250612002212.4144-1-kartilak%40cisco.com
Link: https://lore.kernel.org/r/20250618003431.6314-4-kartilak@cisco.com
Reviewed-by: John Meneghini <jmeneghi@redhat.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/fnic/fnic_scsi.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/scsi/fnic/fnic_scsi.c b/drivers/scsi/fnic/fnic_scsi.c
index 7133b254cbe4..75b29a018d1f 100644
--- a/drivers/scsi/fnic/fnic_scsi.c
+++ b/drivers/scsi/fnic/fnic_scsi.c
@@ -1046,7 +1046,7 @@ static void fnic_fcpio_icmnd_cmpl_handler(struct fnic *fnic, unsigned int cq_ind
 		if (icmnd_cmpl->scsi_status == SAM_STAT_TASK_SET_FULL)
 			atomic64_inc(&fnic_stats->misc_stats.queue_fulls);
 
-		FNIC_SCSI_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+		FNIC_SCSI_DBG(KERN_DEBUG, fnic->host, fnic->fnic_num,
 				"xfer_len: %llu", xfer_len);
 		break;
 

From 85d6fbc47c3087c5d048e6734926b0c36af34fe9 Mon Sep 17 00:00:00 2001
From: Thomas Fourier <fourier.thomas@gmail.com>
Date: Wed, 18 Jun 2025 08:57:04 +0200
Subject: [PATCH 0656/1334] scsi: fnic: Fix missing DMA mapping error in
 fnic_send_frame()

dma_map_XXX() can fail and should be tested for errors with
dma_mapping_error().

Fixes: a63e78eb2b0f ("scsi: fnic: Add support for fabric based solicited requests and responses")
Signed-off-by: Thomas Fourier <fourier.thomas@gmail.com>
Link: https://lore.kernel.org/r/20250618065715.14740-2-fourier.thomas@gmail.com
Reviewed-by: Karan Tilak Kumar <kartilak@cisco.com>
Reviewed-by: John Menghini <jmeneghi@redhat.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/fnic/fnic_fcs.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/scsi/fnic/fnic_fcs.c b/drivers/scsi/fnic/fnic_fcs.c
index 1e8cd64f9a5c..103ab6f1f7cd 100644
--- a/drivers/scsi/fnic/fnic_fcs.c
+++ b/drivers/scsi/fnic/fnic_fcs.c
@@ -636,6 +636,8 @@ static int fnic_send_frame(struct fnic *fnic, void *frame, int frame_len)
 	unsigned long flags;
 
 	pa = dma_map_single(&fnic->pdev->dev, frame, frame_len, DMA_TO_DEVICE);
+	if (dma_mapping_error(&fnic->pdev->dev, pa))
+		return -ENOMEM;
 
 	if ((fnic_fc_trace_set_data(fnic->fnic_num,
 				FNIC_FC_SEND | 0x80, (char *) frame,

From a05dd8ae5cbb1cb45f349922cfea4f548a5e5d6f Mon Sep 17 00:00:00 2001
From: Kairui Song <kasong@tencent.com>
Date: Tue, 10 Jun 2025 01:17:51 +0800
Subject: [PATCH 0657/1334] mm/shmem, swap: fix softlockup with mTHP swapin
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Following softlockup can be easily reproduced on my test machine with:

echo always > /sys/kernel/mm/transparent_hugepage/hugepages-64kB/enabled
swapon /dev/zram0 # zram0 is a 48G swap device
mkdir -p /sys/fs/cgroup/memory/test
echo 1G > /sys/fs/cgroup/test/memory.max
echo $BASHPID > /sys/fs/cgroup/test/cgroup.procs
while true; do
    dd if=/dev/zero of=/tmp/test.img bs=1M count=5120
    cat /tmp/test.img > /dev/null
    rm /tmp/test.img
done

Then after a while:
watchdog: BUG: soft lockup - CPU#0 stuck for 763s! [cat:5787]
Modules linked in: zram virtiofs
CPU: 0 UID: 0 PID: 5787 Comm: cat Kdump: loaded Tainted: G             L      6.15.0.orig-gf3021d9246bc-dirty #118 PREEMPT(voluntary)·
Tainted: [L]=SOFTLOCKUP
Hardware name: Red Hat KVM/RHEL-AV, BIOS 0.0.0 02/06/2015
RIP: 0010:mpol_shared_policy_lookup+0xd/0x70
Code: e9 b8 b4 ff ff 31 c0 c3 cc cc cc cc 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 66 0f 1f 00 0f 1f 44 00 00 41 54 55 53 <48> 8b 1f 48 85 db 74 41 4c 8d 67 08 48 89 fb 48 89 f5 4c 89 e7 e8
RSP: 0018:ffffc90002b1fc28 EFLAGS: 00000202
RAX: 00000000001c20ca RBX: 0000000000724e1e RCX: 0000000000000001
RDX: ffff888118e214c8 RSI: 0000000000057d42 RDI: ffff888118e21518
RBP: 000000000002bec8 R08: 0000000000000001 R09: 0000000000000000
R10: 0000000000000bf4 R11: 0000000000000000 R12: 0000000000000001
R13: 00000000001c20ca R14: 00000000001c20ca R15: 0000000000000000
FS:  00007f03f995c740(0000) GS:ffff88a07ad9a000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007f03f98f1000 CR3: 0000000144626004 CR4: 0000000000770eb0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
PKRU: 55555554
Call Trace:
 <TASK>
 shmem_alloc_folio+0x31/0xc0
 shmem_swapin_folio+0x309/0xcf0
 ? filemap_get_entry+0x117/0x1e0
 ? xas_load+0xd/0xb0
 ? filemap_get_entry+0x101/0x1e0
 shmem_get_folio_gfp+0x2ed/0x5b0
 shmem_file_read_iter+0x7f/0x2e0
 vfs_read+0x252/0x330
 ksys_read+0x68/0xf0
 do_syscall_64+0x4c/0x1c0
 entry_SYSCALL_64_after_hwframe+0x76/0x7e
RIP: 0033:0x7f03f9a46991
Code: 00 48 8b 15 81 14 10 00 f7 d8 64 89 02 b8 ff ff ff ff eb bd e8 20 ad 01 00 f3 0f 1e fa 80 3d 35 97 10 00 00 74 13 31 c0 0f 05 <48> 3d 00 f0 ff ff 77 4f c3 66 0f 1f 44 00 00 55 48 89 e5 48 83 ec
RSP: 002b:00007fff3c52bd28 EFLAGS: 00000246 ORIG_RAX: 0000000000000000
RAX: ffffffffffffffda RBX: 0000000000040000 RCX: 00007f03f9a46991
RDX: 0000000000040000 RSI: 00007f03f98ba000 RDI: 0000000000000003
RBP: 00007fff3c52bd50 R08: 0000000000000000 R09: 00007f03f9b9a380
R10: 0000000000000022 R11: 0000000000000246 R12: 0000000000040000
R13: 00007f03f98ba000 R14: 0000000000000003 R15: 0000000000000000
 </TASK>

The reason is simple, readahead brought some order 0 folio in swap cache,
and the swapin mTHP folio being allocated is in conflict with it, so
swapcache_prepare fails and causes shmem_swap_alloc_folio to return
-EEXIST, and shmem simply retries again and again causing this loop.

Fix it by applying a similar fix for anon mTHP swapin.

The performance change is very slight, time of swapin 10g zero folios
with shmem (test for 12 times):
Before:  2.47s
After:   2.48s

[kasong@tencent.com: add comment]
  Link: https://lkml.kernel.org/r/20250610181645.45922-1-ryncsn@gmail.com
Link: https://lkml.kernel.org/r/20250610181645.45922-1-ryncsn@gmail.com
Link: https://lkml.kernel.org/r/20250609171751.36305-1-ryncsn@gmail.com
Fixes: 1dd44c0af4fa ("mm: shmem: skip swapcache for swapin of synchronous swap device")
Signed-off-by: Kairui Song <kasong@tencent.com>
Reviewed-by: Barry Song <baohua@kernel.org>
Acked-by: Nhat Pham <nphamcs@gmail.com>
Reviewed-by: Baolin Wang <baolin.wang@linux.alibaba.com>
Cc: Baoquan He <bhe@redhat.com>
Cc: Chris Li <chrisl@kernel.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: Kemeng Shi <shikemeng@huaweicloud.com>
Cc: Usama Arif <usamaarif642@gmail.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/memory.c | 20 --------------------
 mm/shmem.c  |  6 +++++-
 mm/swap.h   | 23 +++++++++++++++++++++++
 3 files changed, 28 insertions(+), 21 deletions(-)

diff --git a/mm/memory.c b/mm/memory.c
index 8eba595056fe..b0cda5aab398 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -4315,26 +4315,6 @@ static struct folio *__alloc_swap_folio(struct vm_fault *vmf)
 }
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
-static inline int non_swapcache_batch(swp_entry_t entry, int max_nr)
-{
-	struct swap_info_struct *si = swp_swap_info(entry);
-	pgoff_t offset = swp_offset(entry);
-	int i;
-
-	/*
-	 * While allocating a large folio and doing swap_read_folio, which is
-	 * the case the being faulted pte doesn't have swapcache. We need to
-	 * ensure all PTEs have no cache as well, otherwise, we might go to
-	 * swap devices while the content is in swapcache.
-	 */
-	for (i = 0; i < max_nr; i++) {
-		if ((si->swap_map[offset + i] & SWAP_HAS_CACHE))
-			return i;
-	}
-
-	return i;
-}
-
 /*
  * Check if the PTEs within a range are contiguous swap entries
  * and have consistent swapcache, zeromap.
diff --git a/mm/shmem.c b/mm/shmem.c
index 0c5fb4ffa03a..3a5a65b1f41a 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -2259,6 +2259,7 @@ static int shmem_swapin_folio(struct inode *inode, pgoff_t index,
 	folio = swap_cache_get_folio(swap, NULL, 0);
 	order = xa_get_order(&mapping->i_pages, index);
 	if (!folio) {
+		int nr_pages = 1 << order;
 		bool fallback_order0 = false;
 
 		/* Or update major stats only when swapin succeeds?? */
@@ -2272,9 +2273,12 @@ static int shmem_swapin_folio(struct inode *inode, pgoff_t index,
 		 * If uffd is active for the vma, we need per-page fault
 		 * fidelity to maintain the uffd semantics, then fallback
 		 * to swapin order-0 folio, as well as for zswap case.
+		 * Any existing sub folio in the swap cache also blocks
+		 * mTHP swapin.
 		 */
 		if (order > 0 && ((vma && unlikely(userfaultfd_armed(vma))) ||
-				  !zswap_never_enabled()))
+				  !zswap_never_enabled() ||
+				  non_swapcache_batch(swap, nr_pages) != nr_pages))
 			fallback_order0 = true;
 
 		/* Skip swapcache for synchronous device. */
diff --git a/mm/swap.h b/mm/swap.h
index 2269eb9df0af..9096082a915e 100644
--- a/mm/swap.h
+++ b/mm/swap.h
@@ -106,6 +106,25 @@ static inline int swap_zeromap_batch(swp_entry_t entry, int max_nr,
 		return find_next_bit(sis->zeromap, end, start) - start;
 }
 
+static inline int non_swapcache_batch(swp_entry_t entry, int max_nr)
+{
+	struct swap_info_struct *si = swp_swap_info(entry);
+	pgoff_t offset = swp_offset(entry);
+	int i;
+
+	/*
+	 * While allocating a large folio and doing mTHP swapin, we need to
+	 * ensure all entries are not cached, otherwise, the mTHP folio will
+	 * be in conflict with the folio in swap cache.
+	 */
+	for (i = 0; i < max_nr; i++) {
+		if ((si->swap_map[offset + i] & SWAP_HAS_CACHE))
+			return i;
+	}
+
+	return i;
+}
+
 #else /* CONFIG_SWAP */
 struct swap_iocb;
 static inline void swap_read_folio(struct folio *folio, struct swap_iocb **plug)
@@ -199,6 +218,10 @@ static inline int swap_zeromap_batch(swp_entry_t entry, int max_nr,
 	return 0;
 }
 
+static inline int non_swapcache_batch(swp_entry_t entry, int max_nr)
+{
+	return 0;
+}
 #endif /* CONFIG_SWAP */
 
 /**

From 965f87700adbcc6d72430f524d88135027f5bba3 Mon Sep 17 00:00:00 2001
From: Shivank Garg <shivankg@amd.com>
Date: Mon, 9 Jun 2025 12:06:07 +0000
Subject: [PATCH 0658/1334] selftests/mm: increase timeout from 180 to 900
 seconds

The mm selftests are timing out with the current 180-second limit.
Testing shows that run_vmtests.sh takes approximately 11 minutes
(664 seconds) to complete.

Increase the timeout to 900 seconds (15 minutes) to provide sufficient
buffer for the tests to complete successfully.

Link: https://lkml.kernel.org/r/20250609120606.73145-2-shivankg@amd.com
Signed-off-by: Shivank Garg <shivankg@amd.com>
Cc: Shuah Khan <shuah@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 tools/testing/selftests/mm/settings | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/mm/settings b/tools/testing/selftests/mm/settings
index a953c96aa16e..e2206265f67c 100644
--- a/tools/testing/selftests/mm/settings
+++ b/tools/testing/selftests/mm/settings
@@ -1 +1 @@
-timeout=180
+timeout=900

From 517f496e1e61bd169d585dab4dd77e7147506322 Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Wed, 11 Jun 2025 15:13:14 +0200
Subject: [PATCH 0659/1334] mm/gup: revert "mm: gup: fix infinite loop within
 __get_longterm_locked"

After commit 1aaf8c122918 ("mm: gup: fix infinite loop within
__get_longterm_locked") we are able to longterm pin folios that are not
supposed to get longterm pinned, simply because they temporarily have the
LRU flag cleared (esp.  temporarily isolated).

For example, two __get_longterm_locked() callers can race, or
__get_longterm_locked() can race with anything else that temporarily
isolates folios.

The introducing commit mentions the use case of a driver that uses
vm_ops->fault to insert pages allocated through cma_alloc() into the page
tables, assuming they can later get longterm pinned.  These pages/ folios
would never have the LRU flag set and consequently cannot get isolated.
There is no known in-tree user making use of that so far, fortunately.

To handle that in the future -- and avoid retrying forever to
isolate/migrate them -- we will need a different mechanism for the CMA
area *owner* to indicate that it actually already allocated the page and
is fine with longterm pinning it.  The LRU flag is not suitable for that.

Probably we can lookup the relevant CMA area and query the bitmap; we only
have have to care about some races, probably.  If already allocated, we
could just allow longterm pinning)

Anyhow, let's fix the "must not be longterm pinned" problem first by
reverting the original commit.

Link: https://lkml.kernel.org/r/20250611131314.594529-1-david@redhat.com
Fixes: 1aaf8c122918 ("mm: gup: fix infinite loop within __get_longterm_locked")
Signed-off-by: David Hildenbrand <david@redhat.com>
Closes: https://lore.kernel.org/all/20250522092755.GA3277597@tiffany/
Reported-by: Hyesoo Yu <hyesoo.yu@samsung.com>
Reviewed-by: John Hubbard <jhubbard@nvidia.com>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: Peter Xu <peterx@redhat.com>
Cc: Zhaoyang Huang <zhaoyang.huang@unisoc.com>
Cc: Aijun Sun <aijun.sun@unisoc.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/gup.c | 14 ++++++++++----
 1 file changed, 10 insertions(+), 4 deletions(-)

diff --git a/mm/gup.c b/mm/gup.c
index e065a49842a8..3c39cbbeebef 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -2303,13 +2303,13 @@ static void pofs_unpin(struct pages_or_folios *pofs)
 /*
  * Returns the number of collected folios. Return value is always >= 0.
  */
-static void collect_longterm_unpinnable_folios(
+static unsigned long collect_longterm_unpinnable_folios(
 		struct list_head *movable_folio_list,
 		struct pages_or_folios *pofs)
 {
+	unsigned long i, collected = 0;
 	struct folio *prev_folio = NULL;
 	bool drain_allow = true;
-	unsigned long i;
 
 	for (i = 0; i < pofs->nr_entries; i++) {
 		struct folio *folio = pofs_get_folio(pofs, i);
@@ -2321,6 +2321,8 @@ static void collect_longterm_unpinnable_folios(
 		if (folio_is_longterm_pinnable(folio))
 			continue;
 
+		collected++;
+
 		if (folio_is_device_coherent(folio))
 			continue;
 
@@ -2342,6 +2344,8 @@ static void collect_longterm_unpinnable_folios(
 				    NR_ISOLATED_ANON + folio_is_file_lru(folio),
 				    folio_nr_pages(folio));
 	}
+
+	return collected;
 }
 
 /*
@@ -2418,9 +2422,11 @@ static long
 check_and_migrate_movable_pages_or_folios(struct pages_or_folios *pofs)
 {
 	LIST_HEAD(movable_folio_list);
+	unsigned long collected;
 
-	collect_longterm_unpinnable_folios(&movable_folio_list, pofs);
-	if (list_empty(&movable_folio_list))
+	collected = collect_longterm_unpinnable_folios(&movable_folio_list,
+						       pofs);
+	if (!collected)
 		return 0;
 
 	return migrate_longterm_unpinnable_folios(&movable_folio_list, pofs);

From 0ea148a799198518d8ebab63ddd0bb6114a103bc Mon Sep 17 00:00:00 2001
From: Kairui Song <kasong@tencent.com>
Date: Wed, 4 Jun 2025 23:10:38 +0800
Subject: [PATCH 0660/1334] mm: userfaultfd: fix race of userfaultfd_move and
 swap cache

This commit fixes two kinds of races, they may have different results:

Barry reported a BUG_ON in commit c50f8e6053b0, we may see the same
BUG_ON if the filemap lookup returned NULL and folio is added to swap
cache after that.

If another kind of race is triggered (folio changed after lookup) we
may see RSS counter is corrupted:

[  406.893936] BUG: Bad rss-counter state mm:ffff0000c5a9ddc0
type:MM_ANONPAGES val:-1
[  406.894071] BUG: Bad rss-counter state mm:ffff0000c5a9ddc0
type:MM_SHMEMPAGES val:1

Because the folio is being accounted to the wrong VMA.

I'm not sure if there will be any data corruption though, seems no.
The issues above are critical already.


On seeing a swap entry PTE, userfaultfd_move does a lockless swap cache
lookup, and tries to move the found folio to the faulting vma.  Currently,
it relies on checking the PTE value to ensure that the moved folio still
belongs to the src swap entry and that no new folio has been added to the
swap cache, which turns out to be unreliable.

While working and reviewing the swap table series with Barry, following
existing races are observed and reproduced [1]:

In the example below, move_pages_pte is moving src_pte to dst_pte, where
src_pte is a swap entry PTE holding swap entry S1, and S1 is not in the
swap cache:

CPU1                               CPU2
userfaultfd_move
  move_pages_pte()
    entry = pte_to_swp_entry(orig_src_pte);
    // Here it got entry = S1
    ... < interrupted> ...
                                   <swapin src_pte, alloc and use folio A>
                                   // folio A is a new allocated folio
                                   // and get installed into src_pte
                                   <frees swap entry S1>
                                   // src_pte now points to folio A, S1
                                   // has swap count == 0, it can be freed
                                   // by folio_swap_swap or swap
                                   // allocator's reclaim.
                                   <try to swap out another folio B>
                                   // folio B is a folio in another VMA.
                                   <put folio B to swap cache using S1 >
                                   // S1 is freed, folio B can use it
                                   // for swap out with no problem.
                                   ...
    folio = filemap_get_folio(S1)
    // Got folio B here !!!
    ... < interrupted again> ...
                                   <swapin folio B and free S1>
                                   // Now S1 is free to be used again.
                                   <swapout src_pte & folio A using S1>
                                   // Now src_pte is a swap entry PTE
                                   // holding S1 again.
    folio_trylock(folio)
    move_swap_pte
      double_pt_lock
      is_pte_pages_stable
      // Check passed because src_pte == S1
      folio_move_anon_rmap(...)
      // Moved invalid folio B here !!!

The race window is very short and requires multiple collisions of multiple
rare events, so it's very unlikely to happen, but with a deliberately
constructed reproducer and increased time window, it can be reproduced
easily.

This can be fixed by checking if the folio returned by filemap is the
valid swap cache folio after acquiring the folio lock.

Another similar race is possible: filemap_get_folio may return NULL, but
folio (A) could be swapped in and then swapped out again using the same
swap entry after the lookup.  In such a case, folio (A) may remain in the
swap cache, so it must be moved too:

CPU1                               CPU2
userfaultfd_move
  move_pages_pte()
    entry = pte_to_swp_entry(orig_src_pte);
    // Here it got entry = S1, and S1 is not in swap cache
    folio = filemap_get_folio(S1)
    // Got NULL
    ... < interrupted again> ...
                                   <swapin folio A and free S1>
                                   <swapout folio A re-using S1>
    move_swap_pte
      double_pt_lock
      is_pte_pages_stable
      // Check passed because src_pte == S1
      folio_move_anon_rmap(...)
      // folio A is ignored !!!

Fix this by checking the swap cache again after acquiring the src_pte
lock.  And to avoid the filemap overhead, we check swap_map directly [2].

The SWP_SYNCHRONOUS_IO path does make the problem more complex, but so far
we don't need to worry about that, since folios can only be exposed to the
swap cache in the swap out path, and this is covered in this patch by
checking the swap cache again after acquiring the src_pte lock.

Testing with a simple C program that allocates and moves several GB of
memory did not show any observable performance change.

Link: https://lkml.kernel.org/r/20250604151038.21968-1-ryncsn@gmail.com
Fixes: adef440691ba ("userfaultfd: UFFDIO_MOVE uABI")
Signed-off-by: Kairui Song <kasong@tencent.com>
Closes: https://lore.kernel.org/linux-mm/CAMgjq7B1K=6OOrK2OUZ0-tqCzi+EJt+2_K97TPGoSt=9+JwP7Q@mail.gmail.com/ [1]
Link: https://lore.kernel.org/all/CAGsJ_4yJhJBo16XhiC-nUzSheyX-V3-nFE+tAi=8Y560K8eT=A@mail.gmail.com/ [2]
Reviewed-by: Lokesh Gidra <lokeshgidra@google.com>
Acked-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Suren Baghdasaryan <surenb@google.com>
Reviewed-by: Barry Song <baohua@kernel.org>
Reviewed-by: Chris Li <chrisl@kernel.org>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Kairui Song <kasong@tencent.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/userfaultfd.c | 33 +++++++++++++++++++++++++++++++--
 1 file changed, 31 insertions(+), 2 deletions(-)

diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index bc473ad21202..8253978ee0fb 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -1084,8 +1084,18 @@ static int move_swap_pte(struct mm_struct *mm, struct vm_area_struct *dst_vma,
 			 pte_t orig_dst_pte, pte_t orig_src_pte,
 			 pmd_t *dst_pmd, pmd_t dst_pmdval,
 			 spinlock_t *dst_ptl, spinlock_t *src_ptl,
-			 struct folio *src_folio)
+			 struct folio *src_folio,
+			 struct swap_info_struct *si, swp_entry_t entry)
 {
+	/*
+	 * Check if the folio still belongs to the target swap entry after
+	 * acquiring the lock. Folio can be freed in the swap cache while
+	 * not locked.
+	 */
+	if (src_folio && unlikely(!folio_test_swapcache(src_folio) ||
+				  entry.val != src_folio->swap.val))
+		return -EAGAIN;
+
 	double_pt_lock(dst_ptl, src_ptl);
 
 	if (!is_pte_pages_stable(dst_pte, src_pte, orig_dst_pte, orig_src_pte,
@@ -1102,6 +1112,25 @@ static int move_swap_pte(struct mm_struct *mm, struct vm_area_struct *dst_vma,
 	if (src_folio) {
 		folio_move_anon_rmap(src_folio, dst_vma);
 		src_folio->index = linear_page_index(dst_vma, dst_addr);
+	} else {
+		/*
+		 * Check if the swap entry is cached after acquiring the src_pte
+		 * lock. Otherwise, we might miss a newly loaded swap cache folio.
+		 *
+		 * Check swap_map directly to minimize overhead, READ_ONCE is sufficient.
+		 * We are trying to catch newly added swap cache, the only possible case is
+		 * when a folio is swapped in and out again staying in swap cache, using the
+		 * same entry before the PTE check above. The PTL is acquired and released
+		 * twice, each time after updating the swap_map's flag. So holding
+		 * the PTL here ensures we see the updated value. False positive is possible,
+		 * e.g. SWP_SYNCHRONOUS_IO swapin may set the flag without touching the
+		 * cache, or during the tiny synchronization window between swap cache and
+		 * swap_map, but it will be gone very quickly, worst result is retry jitters.
+		 */
+		if (READ_ONCE(si->swap_map[swp_offset(entry)]) & SWAP_HAS_CACHE) {
+			double_pt_unlock(dst_ptl, src_ptl);
+			return -EAGAIN;
+		}
 	}
 
 	orig_src_pte = ptep_get_and_clear(mm, src_addr, src_pte);
@@ -1412,7 +1441,7 @@ retry:
 		}
 		err = move_swap_pte(mm, dst_vma, dst_addr, src_addr, dst_pte, src_pte,
 				orig_dst_pte, orig_src_pte, dst_pmd, dst_pmdval,
-				dst_ptl, src_ptl, src_folio);
+				dst_ptl, src_ptl, src_folio, si, entry);
 	}
 
 out:

From 417d145c2e71ad7362200ede6e8afdfc6e56c4fb Mon Sep 17 00:00:00 2001
From: Pratyush Yadav <ptyadav@amazon.de>
Date: Fri, 13 Jun 2025 15:19:14 +0200
Subject: [PATCH 0661/1334] MAINTAINERS: add linux-mm@ list to Kexec Handover

Along with kexec, KHO also has parts dealing with memory management, like
page/folio initialization, memblock, and preserving/unpreserving memory
for next kernel.  Copy linux-mm@ to KHO patches so the right set of eyes
can look at changes to those parts.

Link: https://lkml.kernel.org/r/20250613131917.4488-1-pratyush@kernel.org
Signed-off-by: Pratyush Yadav <ptyadav@amazon.de>
Reviewed-by: Pasha Tatashin <pasha.tatashin@soleen.com>
Reviewed-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
Acked-by: SeongJae Park <sj@kernel.org>
Cc: Alexander Graf <graf@amazon.com>
Cc: Baoquan He <bhe@redhat.com>
Cc: Changyuan Lyu <changyuanl@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 MAINTAINERS | 1 +
 1 file changed, 1 insertion(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index 0c1d245bf7b8..9a7fdc52cf9d 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -13347,6 +13347,7 @@ M:	Alexander Graf <graf@amazon.com>
 M:	Mike Rapoport <rppt@kernel.org>
 M:	Changyuan Lyu <changyuanl@google.com>
 L:	kexec@lists.infradead.org
+L:	linux-mm@kvack.org
 S:	Maintained
 F:	Documentation/admin-guide/mm/kho.rst
 F:	Documentation/core-api/kho/*

From 12b9a2c05d1b474518b0f5fac4a50b7f93b16930 Mon Sep 17 00:00:00 2001
From: Pratyush Yadav <ptyadav@amazon.de>
Date: Thu, 5 Jun 2025 19:11:41 +0200
Subject: [PATCH 0662/1334] kho: initialize tail pages for higher order folios
 properly

Currently, when restoring higher order folios, kho_restore_folio() only
calls prep_compound_page() on all the pages.  That is not enough to
properly initialize the folios.  The managed page count does not get
updated, the reserved flag does not get dropped, and page count does not
get initialized properly.

Restoring a higher order folio with it results in the following BUG with
CONFIG_DEBUG_VM when attempting to free the folio:

    BUG: Bad page state in process test  pfn:104e2b
    page: refcount:1 mapcount:0 mapping:0000000000000000 index:0xffffffffffffffff pfn:0x104e2b
    flags: 0x2fffff80000000(node=0|zone=2|lastcpupid=0x1fffff)
    raw: 002fffff80000000 0000000000000000 00000000ffffffff 0000000000000000
    raw: ffffffffffffffff 0000000000000000 00000001ffffffff 0000000000000000
    page dumped because: nonzero _refcount
    [...]
    Call Trace:
    <TASK>
    dump_stack_lvl+0x4b/0x70
    bad_page.cold+0x97/0xb2
    __free_frozen_pages+0x616/0x850
    [...]

Combine the path for 0-order and higher order folios, initialize the tail
pages with a count of zero, and call adjust_managed_page_count() to
account for all the pages instead of just missing them.

In addition, since all the KHO-preserved pages get marked with
MEMBLOCK_RSRV_NOINIT by deserialize_bitmap(), the reserved flag is not
actually set (as can also be seen from the flags of the dumped page in the
logs above).  So drop the ClearPageReserved() calls.

[ptyadav@amazon.de: declare i in the loop instead of at the top]
  Link: https://lkml.kernel.org/r/20250613125916.39272-1-pratyush@kernel.org
Link: https://lkml.kernel.org/r/20250605171143.76963-1-pratyush@kernel.org
Fixes: fc33e4b44b27 ("kexec: enable KHO support for memory preservation")
Signed-off-by: Pratyush Yadav <ptyadav@amazon.de>
Reviewed-by: Pasha Tatashin <pasha.tatashin@soleen.com>
Reviewed-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
Cc: Alexander Graf <graf@amazon.com>
Cc: Baoquan He <bhe@redhat.com>
Cc: Changyuan Lyu <changyuanl@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 kernel/kexec_handover.c | 29 +++++++++++++++++------------
 1 file changed, 17 insertions(+), 12 deletions(-)

diff --git a/kernel/kexec_handover.c b/kernel/kexec_handover.c
index 69b953551677..5a21dbe17950 100644
--- a/kernel/kexec_handover.c
+++ b/kernel/kexec_handover.c
@@ -164,11 +164,21 @@ static int __kho_preserve_order(struct kho_mem_track *track, unsigned long pfn,
 }
 
 /* almost as free_reserved_page(), just don't free the page */
-static void kho_restore_page(struct page *page)
+static void kho_restore_page(struct page *page, unsigned int order)
 {
-	ClearPageReserved(page);
-	init_page_count(page);
-	adjust_managed_page_count(page, 1);
+	unsigned int nr_pages = (1 << order);
+
+	/* Head page gets refcount of 1. */
+	set_page_count(page, 1);
+
+	/* For higher order folios, tail pages get a page count of zero. */
+	for (unsigned int i = 1; i < nr_pages; i++)
+		set_page_count(page + i, 0);
+
+	if (order > 0)
+		prep_compound_page(page, order);
+
+	adjust_managed_page_count(page, nr_pages);
 }
 
 /**
@@ -186,15 +196,10 @@ struct folio *kho_restore_folio(phys_addr_t phys)
 		return NULL;
 
 	order = page->private;
-	if (order) {
-		if (order > MAX_PAGE_ORDER)
-			return NULL;
-
-		prep_compound_page(page, order);
-	} else {
-		kho_restore_page(page);
-	}
+	if (order > MAX_PAGE_ORDER)
+		return NULL;
 
+	kho_restore_page(page, order);
 	return page_folio(page);
 }
 EXPORT_SYMBOL_GPL(kho_restore_folio);

From 223731cd63004cb07edfc6257d53565995c00cbb Mon Sep 17 00:00:00 2001
From: Dev Jain <dev.jain@arm.com>
Date: Fri, 13 Jun 2025 09:19:12 +0530
Subject: [PATCH 0663/1334] selftests/mm: add configs to fix testcase failure

If CONFIG_UPROBES is not set, a merge subtest fails:

Failure log:

  7151 12:46:54.627936  # # #  RUN           merge.handle_uprobe_upon_merged_vma ...
  7152 12:46:54.639014  # # f /sys/bus/event_source/devices/uprobe/type
  7153 12:46:54.639306  # # fopen: No such file or directory
  7154 12:46:54.650451  # # # merge.c:473:handle_uprobe_upon_merged_vma:Expected read_sysfs("/sys/bus/event_source/devices/uprobe/type", &type) (1) == 0 (0)
  7155 12:46:54.650730  # # # handle_uprobe_upon_merged_vma: Test terminated by assertion
  7156 12:46:54.661750  # # #          FAIL  merge.handle_uprobe_upon_merged_vma
  7157 12:46:54.662030  # # not ok 8 merge.handle_uprobe_upon_merged_vma

CONFIG_UPROBES is enabled by CONFIG_UPROBE_EVENTS, which gets enabled by
CONFIG_FTRACE. Therefore add these configs to selftests/mm/config so that
CI systems can include this config in the kernel build. To be completely
safe, add CONFIG_PROFILING too, to enable the dependency chain
PROFILING -> PERF_EVENTS -> UPROBE_EVENTS -> UPROBES.

Link: https://lkml.kernel.org/r/20250613034912.53791-1-dev.jain@arm.com
Fixes: efe99fabeb11 ("selftests/mm: add test about uprobe pte be orphan during vma merge")
Signed-off-by: Dev Jain <dev.jain@arm.com>
Reported-by: Aishwarya <aishwarya.tcv@arm.com>
Closes: https://lore.kernel.org/all/20250610103729.72440-1-aishwarya.tcv@arm.com/
Tested-by: Aishwarya TCV <aishwarya.tcv@arm.com>
Tested-by : Donet Tom <donettom@linux.ibm.com>
Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Reviewed-by: Anshuman Khandual <anshuman.khandual@arm.com>
Reviewed-by: Mark Brown <broonie@kernel.org>
Reviewed-by: Donet Tom <donettom@linux.ibm.com>
Reviewed-by: Pedro Falcato <pfalcato@suse.de>
Cc: Jann Horn <jannh@google.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Pu Lehui <pulehui@huawei.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 tools/testing/selftests/mm/config | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/tools/testing/selftests/mm/config b/tools/testing/selftests/mm/config
index a28baa536332..deba93379c80 100644
--- a/tools/testing/selftests/mm/config
+++ b/tools/testing/selftests/mm/config
@@ -8,3 +8,6 @@ CONFIG_GUP_TEST=y
 CONFIG_TRANSPARENT_HUGEPAGE=y
 CONFIG_MEM_SOFT_DIRTY=y
 CONFIG_ANON_VMA_NAME=y
+CONFIG_FTRACE=y
+CONFIG_PROFILING=y
+CONFIG_UPROBES=y

From 845f1f2d69f3f49b3d8c142265952c8257e3368c Mon Sep 17 00:00:00 2001
From: Kuan-Wei Chiu <visitorckw@gmail.com>
Date: Sun, 15 Jun 2025 04:23:51 +0800
Subject: [PATCH 0664/1334] Revert "bcache: update min_heap_callbacks to use
 default builtin swap"

Patch series "bcache: Revert min_heap migration due to performance
regression".

This patch series reverts the migration of bcache from its original heap
implementation to the generic min_heap library.  While the original change
aimed to simplify the code and improve maintainability, it introduced a
severe performance regression in real-world scenarios.

As reported by Robert, systems using bcache now suffer from periodic
latency spikes, with P100 (max) latency increasing from 600 ms to 2.4
seconds every 5 minutes.  This degrades bcache's value as a low-latency
caching layer, and leads to frequent timeouts and application stalls in
production environments.

The primary cause of this regression is the behavior of the generic
min_heap implementation's bottom-up sift_down, which performs up to 2 *
log2(n) comparisons when many elements are equal.  The original top-down
variant used by bcache only required O(1) comparisons in such cases.  The
issue was further exacerbated by commit 92a8b224b833 ("lib/min_heap:
introduce non-inline versions of min heap API functions"), which
introduced non-inlined versions of the min_heap API, adding function call
overhead to a performance-critical hot path.


This patch (of 3):

This reverts commit 3d8a9a1c35227c3f1b0bd132c9f0a80dbda07b65.

Although removing the custom swap function simplified the code, this
change is part of a broader migration to the generic min_heap API that
introduced significant performance regressions in bcache.

As reported by Robert, bcache now suffers from latency spikes, with P100
(max) latency increasing from 600 ms to 2.4 seconds every 5 minutes.
These regressions degrade bcache's effectiveness as a low-latency cache
layer and lead to frequent timeouts and application stalls in production
environments.

This revert is part of a series of changes to restore previous performance
by undoing the min_heap transition.

Link: https://lkml.kernel.org/r/20250614202353.1632957-1-visitorckw@gmail.com
Link: https://lore.kernel.org/lkml/CAJhEC05+0S69z+3+FB2Cd0hD+pCRyWTKLEOsc8BOmH73p1m+KQ@mail.gmail.com
Link: https://lkml.kernel.org/r/20250614202353.1632957-2-visitorckw@gmail.com
Fixes: 866898efbb25 ("bcache: remove heap-related macros and switch to generic min_heap")
Fixes: 92a8b224b833 ("lib/min_heap: introduce non-inline versions of min heap API functions")
Signed-off-by: Kuan-Wei Chiu <visitorckw@gmail.com>
Reported-by: Robert Pang <robertpang@google.com>
Closes: https://lore.kernel.org/linux-bcache/CAJhEC06F_AtrPgw2-7CvCqZgeStgCtitbD-ryuPpXQA-JG5XXw@mail.gmail.com
Acked-by: Coly Li <colyli@kernel.org>
Cc: Ching-Chun (Jim) Huang <jserv@ccns.ncku.edu.tw>
Cc: Kent Overstreet <kent.overstreet@linux.dev>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 drivers/md/bcache/alloc.c    | 11 +++++++++--
 drivers/md/bcache/bset.c     | 14 +++++++++++---
 drivers/md/bcache/extents.c  | 10 +++++++++-
 drivers/md/bcache/movinggc.c | 10 +++++++++-
 4 files changed, 38 insertions(+), 7 deletions(-)

diff --git a/drivers/md/bcache/alloc.c b/drivers/md/bcache/alloc.c
index 8998e61efa40..da50f6661bae 100644
--- a/drivers/md/bcache/alloc.c
+++ b/drivers/md/bcache/alloc.c
@@ -189,16 +189,23 @@ static inline bool new_bucket_min_cmp(const void *l, const void *r, void *args)
 	return new_bucket_prio(ca, *lhs) < new_bucket_prio(ca, *rhs);
 }
 
+static inline void new_bucket_swap(void *l, void *r, void __always_unused *args)
+{
+	struct bucket **lhs = l, **rhs = r;
+
+	swap(*lhs, *rhs);
+}
+
 static void invalidate_buckets_lru(struct cache *ca)
 {
 	struct bucket *b;
 	const struct min_heap_callbacks bucket_max_cmp_callback = {
 		.less = new_bucket_max_cmp,
-		.swp = NULL,
+		.swp = new_bucket_swap,
 	};
 	const struct min_heap_callbacks bucket_min_cmp_callback = {
 		.less = new_bucket_min_cmp,
-		.swp = NULL,
+		.swp = new_bucket_swap,
 	};
 
 	ca->heap.nr = 0;
diff --git a/drivers/md/bcache/bset.c b/drivers/md/bcache/bset.c
index 68258a16e125..bd97d8626887 100644
--- a/drivers/md/bcache/bset.c
+++ b/drivers/md/bcache/bset.c
@@ -1093,6 +1093,14 @@ static inline bool new_btree_iter_cmp(const void *l, const void *r, void __alway
 	return bkey_cmp(_l->k, _r->k) <= 0;
 }
 
+static inline void new_btree_iter_swap(void *iter1, void *iter2, void __always_unused *args)
+{
+	struct btree_iter_set *_iter1 = iter1;
+	struct btree_iter_set *_iter2 = iter2;
+
+	swap(*_iter1, *_iter2);
+}
+
 static inline bool btree_iter_end(struct btree_iter *iter)
 {
 	return !iter->heap.nr;
@@ -1103,7 +1111,7 @@ void bch_btree_iter_push(struct btree_iter *iter, struct bkey *k,
 {
 	const struct min_heap_callbacks callbacks = {
 		.less = new_btree_iter_cmp,
-		.swp = NULL,
+		.swp = new_btree_iter_swap,
 	};
 
 	if (k != end)
@@ -1149,7 +1157,7 @@ static inline struct bkey *__bch_btree_iter_next(struct btree_iter *iter,
 	struct bkey *ret = NULL;
 	const struct min_heap_callbacks callbacks = {
 		.less = cmp,
-		.swp = NULL,
+		.swp = new_btree_iter_swap,
 	};
 
 	if (!btree_iter_end(iter)) {
@@ -1223,7 +1231,7 @@ static void btree_mergesort(struct btree_keys *b, struct bset *out,
 		: bch_ptr_invalid;
 	const struct min_heap_callbacks callbacks = {
 		.less = b->ops->sort_cmp,
-		.swp = NULL,
+		.swp = new_btree_iter_swap,
 	};
 
 	/* Heapify the iterator, using our comparison function */
diff --git a/drivers/md/bcache/extents.c b/drivers/md/bcache/extents.c
index 4b84fda1530a..a7221e5dbe81 100644
--- a/drivers/md/bcache/extents.c
+++ b/drivers/md/bcache/extents.c
@@ -266,12 +266,20 @@ static bool new_bch_extent_sort_cmp(const void *l, const void *r, void __always_
 	return !(c ? c > 0 : _l->k < _r->k);
 }
 
+static inline void new_btree_iter_swap(void *iter1, void *iter2, void __always_unused *args)
+{
+	struct btree_iter_set *_iter1 = iter1;
+	struct btree_iter_set *_iter2 = iter2;
+
+	swap(*_iter1, *_iter2);
+}
+
 static struct bkey *bch_extent_sort_fixup(struct btree_iter *iter,
 					  struct bkey *tmp)
 {
 	const struct min_heap_callbacks callbacks = {
 		.less = new_bch_extent_sort_cmp,
-		.swp = NULL,
+		.swp = new_btree_iter_swap,
 	};
 	while (iter->heap.nr > 1) {
 		struct btree_iter_set *top = iter->heap.data, *i = top + 1;
diff --git a/drivers/md/bcache/movinggc.c b/drivers/md/bcache/movinggc.c
index 45ca134cbf02..d6c73dd8eb2b 100644
--- a/drivers/md/bcache/movinggc.c
+++ b/drivers/md/bcache/movinggc.c
@@ -190,6 +190,14 @@ static bool new_bucket_cmp(const void *l, const void *r, void __always_unused *a
 	return GC_SECTORS_USED(*_l) >= GC_SECTORS_USED(*_r);
 }
 
+static void new_bucket_swap(void *l, void *r, void __always_unused *args)
+{
+	struct bucket **_l = l;
+	struct bucket **_r = r;
+
+	swap(*_l, *_r);
+}
+
 static unsigned int bucket_heap_top(struct cache *ca)
 {
 	struct bucket *b;
@@ -204,7 +212,7 @@ void bch_moving_gc(struct cache_set *c)
 	unsigned long sectors_to_move, reserve_sectors;
 	const struct min_heap_callbacks callbacks = {
 		.less = new_bucket_cmp,
-		.swp = NULL,
+		.swp = new_bucket_swap,
 	};
 
 	if (!c->copy_gc_enabled)

From 48fd7ebe00c1cdc782b42576548b25185902f64c Mon Sep 17 00:00:00 2001
From: Kuan-Wei Chiu <visitorckw@gmail.com>
Date: Sun, 15 Jun 2025 04:23:52 +0800
Subject: [PATCH 0665/1334] Revert "bcache: remove heap-related macros and
 switch to generic min_heap"

This reverts commit 866898efbb25bb44fd42848318e46db9e785973a.

The generic bottom-up min_heap implementation causes performance
regression in invalidate_buckets_lru(), a hot path in bcache.  Before the
cache is fully populated, new_bucket_prio() often returns zero, leading to
many equal comparisons.  In such cases, bottom-up sift_down performs up to
2 * log2(n) comparisons, while the original top-down approach completes
with just O() comparisons, resulting in a measurable performance gap.

The performance degradation is further worsened by the non-inlined
min_heap API functions introduced in commit 92a8b224b833 ("lib/min_heap:
introduce non-inline versions of min heap API functions"), adding function
call overhead to this critical path.

As reported by Robert, bcache now suffers from latency spikes, with P100
(max) latency increasing from 600 ms to 2.4 seconds every 5 minutes.
These regressions degrade bcache's effectiveness as a low-latency cache
layer and lead to frequent timeouts and application stalls in production
environments.

This revert aims to restore bcache's original low-latency behavior.

Link: https://lore.kernel.org/lkml/CAJhEC05+0S69z+3+FB2Cd0hD+pCRyWTKLEOsc8BOmH73p1m+KQ@mail.gmail.com
Link: https://lkml.kernel.org/r/20250614202353.1632957-3-visitorckw@gmail.com
Fixes: 866898efbb25 ("bcache: remove heap-related macros and switch to generic min_heap")
Fixes: 92a8b224b833 ("lib/min_heap: introduce non-inline versions of min heap API functions")
Signed-off-by: Kuan-Wei Chiu <visitorckw@gmail.com>
Reported-by: Robert Pang <robertpang@google.com>
Closes: https://lore.kernel.org/linux-bcache/CAJhEC06F_AtrPgw2-7CvCqZgeStgCtitbD-ryuPpXQA-JG5XXw@mail.gmail.com
Acked-by: Coly Li <colyli@kernel.org>
Cc: Ching-Chun (Jim) Huang <jserv@ccns.ncku.edu.tw>
Cc: Kent Overstreet <kent.overstreet@linux.dev>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 drivers/md/bcache/alloc.c     |  64 +++++-------------
 drivers/md/bcache/bcache.h    |   2 +-
 drivers/md/bcache/bset.c      | 124 ++++++++++++----------------------
 drivers/md/bcache/bset.h      |  40 ++++++-----
 drivers/md/bcache/btree.c     |  69 ++++++++-----------
 drivers/md/bcache/extents.c   |  51 +++++---------
 drivers/md/bcache/movinggc.c  |  41 +++--------
 drivers/md/bcache/super.c     |   3 +-
 drivers/md/bcache/sysfs.c     |   4 +-
 drivers/md/bcache/util.h      |  67 +++++++++++++++++-
 drivers/md/bcache/writeback.c |  13 ++--
 11 files changed, 216 insertions(+), 262 deletions(-)

diff --git a/drivers/md/bcache/alloc.c b/drivers/md/bcache/alloc.c
index da50f6661bae..48ce750bf70a 100644
--- a/drivers/md/bcache/alloc.c
+++ b/drivers/md/bcache/alloc.c
@@ -164,68 +164,40 @@ static void bch_invalidate_one_bucket(struct cache *ca, struct bucket *b)
  * prio is worth 1/8th of what INITIAL_PRIO is worth.
  */
 
-static inline unsigned int new_bucket_prio(struct cache *ca, struct bucket *b)
-{
-	unsigned int min_prio = (INITIAL_PRIO - ca->set->min_prio) / 8;
+#define bucket_prio(b)							\
+({									\
+	unsigned int min_prio = (INITIAL_PRIO - ca->set->min_prio) / 8;	\
+									\
+	(b->prio - ca->set->min_prio + min_prio) * GC_SECTORS_USED(b);	\
+})
 
-	return (b->prio - ca->set->min_prio + min_prio) * GC_SECTORS_USED(b);
-}
-
-static inline bool new_bucket_max_cmp(const void *l, const void *r, void *args)
-{
-	struct bucket **lhs = (struct bucket **)l;
-	struct bucket **rhs = (struct bucket **)r;
-	struct cache *ca = args;
-
-	return new_bucket_prio(ca, *lhs) > new_bucket_prio(ca, *rhs);
-}
-
-static inline bool new_bucket_min_cmp(const void *l, const void *r, void *args)
-{
-	struct bucket **lhs = (struct bucket **)l;
-	struct bucket **rhs = (struct bucket **)r;
-	struct cache *ca = args;
-
-	return new_bucket_prio(ca, *lhs) < new_bucket_prio(ca, *rhs);
-}
-
-static inline void new_bucket_swap(void *l, void *r, void __always_unused *args)
-{
-	struct bucket **lhs = l, **rhs = r;
-
-	swap(*lhs, *rhs);
-}
+#define bucket_max_cmp(l, r)	(bucket_prio(l) < bucket_prio(r))
+#define bucket_min_cmp(l, r)	(bucket_prio(l) > bucket_prio(r))
 
 static void invalidate_buckets_lru(struct cache *ca)
 {
 	struct bucket *b;
-	const struct min_heap_callbacks bucket_max_cmp_callback = {
-		.less = new_bucket_max_cmp,
-		.swp = new_bucket_swap,
-	};
-	const struct min_heap_callbacks bucket_min_cmp_callback = {
-		.less = new_bucket_min_cmp,
-		.swp = new_bucket_swap,
-	};
+	ssize_t i;
 
-	ca->heap.nr = 0;
+	ca->heap.used = 0;
 
 	for_each_bucket(b, ca) {
 		if (!bch_can_invalidate_bucket(ca, b))
 			continue;
 
-		if (!min_heap_full(&ca->heap))
-			min_heap_push(&ca->heap, &b, &bucket_max_cmp_callback, ca);
-		else if (!new_bucket_max_cmp(&b, min_heap_peek(&ca->heap), ca)) {
+		if (!heap_full(&ca->heap))
+			heap_add(&ca->heap, b, bucket_max_cmp);
+		else if (bucket_max_cmp(b, heap_peek(&ca->heap))) {
 			ca->heap.data[0] = b;
-			min_heap_sift_down(&ca->heap, 0, &bucket_max_cmp_callback, ca);
+			heap_sift(&ca->heap, 0, bucket_max_cmp);
 		}
 	}
 
-	min_heapify_all(&ca->heap, &bucket_min_cmp_callback, ca);
+	for (i = ca->heap.used / 2 - 1; i >= 0; --i)
+		heap_sift(&ca->heap, i, bucket_min_cmp);
 
 	while (!fifo_full(&ca->free_inc)) {
-		if (!ca->heap.nr) {
+		if (!heap_pop(&ca->heap, b, bucket_min_cmp)) {
 			/*
 			 * We don't want to be calling invalidate_buckets()
 			 * multiple times when it can't do anything
@@ -234,8 +206,6 @@ static void invalidate_buckets_lru(struct cache *ca)
 			wake_up_gc(ca->set);
 			return;
 		}
-		b = min_heap_peek(&ca->heap)[0];
-		min_heap_pop(&ca->heap, &bucket_min_cmp_callback, ca);
 
 		bch_invalidate_one_bucket(ca, b);
 	}
diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h
index 785b0d9008fa..1d33e40d26ea 100644
--- a/drivers/md/bcache/bcache.h
+++ b/drivers/md/bcache/bcache.h
@@ -458,7 +458,7 @@ struct cache {
 	/* Allocation stuff: */
 	struct bucket		*buckets;
 
-	DEFINE_MIN_HEAP(struct bucket *, cache_heap) heap;
+	DECLARE_HEAP(struct bucket *, heap);
 
 	/*
 	 * If nonzero, we know we aren't going to find any buckets to invalidate
diff --git a/drivers/md/bcache/bset.c b/drivers/md/bcache/bset.c
index bd97d8626887..463eb13bd0b2 100644
--- a/drivers/md/bcache/bset.c
+++ b/drivers/md/bcache/bset.c
@@ -54,11 +54,9 @@ void bch_dump_bucket(struct btree_keys *b)
 int __bch_count_data(struct btree_keys *b)
 {
 	unsigned int ret = 0;
-	struct btree_iter iter;
+	struct btree_iter_stack iter;
 	struct bkey *k;
 
-	min_heap_init(&iter.heap, NULL, MAX_BSETS);
-
 	if (b->ops->is_extents)
 		for_each_key(b, k, &iter)
 			ret += KEY_SIZE(k);
@@ -69,11 +67,9 @@ void __bch_check_keys(struct btree_keys *b, const char *fmt, ...)
 {
 	va_list args;
 	struct bkey *k, *p = NULL;
-	struct btree_iter iter;
+	struct btree_iter_stack iter;
 	const char *err;
 
-	min_heap_init(&iter.heap, NULL, MAX_BSETS);
-
 	for_each_key(b, k, &iter) {
 		if (b->ops->is_extents) {
 			err = "Keys out of order";
@@ -114,9 +110,9 @@ bug:
 
 static void bch_btree_iter_next_check(struct btree_iter *iter)
 {
-	struct bkey *k = iter->heap.data->k, *next = bkey_next(k);
+	struct bkey *k = iter->data->k, *next = bkey_next(k);
 
-	if (next < iter->heap.data->end &&
+	if (next < iter->data->end &&
 	    bkey_cmp(k, iter->b->ops->is_extents ?
 		     &START_KEY(next) : next) > 0) {
 		bch_dump_bucket(iter->b);
@@ -883,14 +879,12 @@ unsigned int bch_btree_insert_key(struct btree_keys *b, struct bkey *k,
 	unsigned int status = BTREE_INSERT_STATUS_NO_INSERT;
 	struct bset *i = bset_tree_last(b)->data;
 	struct bkey *m, *prev = NULL;
-	struct btree_iter iter;
+	struct btree_iter_stack iter;
 	struct bkey preceding_key_on_stack = ZERO_KEY;
 	struct bkey *preceding_key_p = &preceding_key_on_stack;
 
 	BUG_ON(b->ops->is_extents && !KEY_SIZE(k));
 
-	min_heap_init(&iter.heap, NULL, MAX_BSETS);
-
 	/*
 	 * If k has preceding key, preceding_key_p will be set to address
 	 *  of k's preceding key; otherwise preceding_key_p will be set
@@ -901,9 +895,9 @@ unsigned int bch_btree_insert_key(struct btree_keys *b, struct bkey *k,
 	else
 		preceding_key(k, &preceding_key_p);
 
-	m = bch_btree_iter_init(b, &iter, preceding_key_p);
+	m = bch_btree_iter_stack_init(b, &iter, preceding_key_p);
 
-	if (b->ops->insert_fixup(b, k, &iter, replace_key))
+	if (b->ops->insert_fixup(b, k, &iter.iter, replace_key))
 		return status;
 
 	status = BTREE_INSERT_STATUS_INSERT;
@@ -1083,102 +1077,79 @@ struct bkey *__bch_bset_search(struct btree_keys *b, struct bset_tree *t,
 
 /* Btree iterator */
 
-typedef bool (new_btree_iter_cmp_fn)(const void *, const void *, void *);
+typedef bool (btree_iter_cmp_fn)(struct btree_iter_set,
+				 struct btree_iter_set);
 
-static inline bool new_btree_iter_cmp(const void *l, const void *r, void __always_unused *args)
+static inline bool btree_iter_cmp(struct btree_iter_set l,
+				  struct btree_iter_set r)
 {
-	const struct btree_iter_set *_l = l;
-	const struct btree_iter_set *_r = r;
-
-	return bkey_cmp(_l->k, _r->k) <= 0;
-}
-
-static inline void new_btree_iter_swap(void *iter1, void *iter2, void __always_unused *args)
-{
-	struct btree_iter_set *_iter1 = iter1;
-	struct btree_iter_set *_iter2 = iter2;
-
-	swap(*_iter1, *_iter2);
+	return bkey_cmp(l.k, r.k) > 0;
 }
 
 static inline bool btree_iter_end(struct btree_iter *iter)
 {
-	return !iter->heap.nr;
+	return !iter->used;
 }
 
 void bch_btree_iter_push(struct btree_iter *iter, struct bkey *k,
 			 struct bkey *end)
 {
-	const struct min_heap_callbacks callbacks = {
-		.less = new_btree_iter_cmp,
-		.swp = new_btree_iter_swap,
-	};
-
 	if (k != end)
-		BUG_ON(!min_heap_push(&iter->heap,
-				 &((struct btree_iter_set) { k, end }),
-				 &callbacks,
-				 NULL));
+		BUG_ON(!heap_add(iter,
+				 ((struct btree_iter_set) { k, end }),
+				 btree_iter_cmp));
 }
 
-static struct bkey *__bch_btree_iter_init(struct btree_keys *b,
-					  struct btree_iter *iter,
-					  struct bkey *search,
-					  struct bset_tree *start)
+static struct bkey *__bch_btree_iter_stack_init(struct btree_keys *b,
+						struct btree_iter_stack *iter,
+						struct bkey *search,
+						struct bset_tree *start)
 {
 	struct bkey *ret = NULL;
 
-	iter->heap.size = ARRAY_SIZE(iter->heap.preallocated);
-	iter->heap.nr = 0;
+	iter->iter.size = ARRAY_SIZE(iter->stack_data);
+	iter->iter.used = 0;
 
 #ifdef CONFIG_BCACHE_DEBUG
-	iter->b = b;
+	iter->iter.b = b;
 #endif
 
 	for (; start <= bset_tree_last(b); start++) {
 		ret = bch_bset_search(b, start, search);
-		bch_btree_iter_push(iter, ret, bset_bkey_last(start->data));
+		bch_btree_iter_push(&iter->iter, ret, bset_bkey_last(start->data));
 	}
 
 	return ret;
 }
 
-struct bkey *bch_btree_iter_init(struct btree_keys *b,
-				 struct btree_iter *iter,
+struct bkey *bch_btree_iter_stack_init(struct btree_keys *b,
+				 struct btree_iter_stack *iter,
 				 struct bkey *search)
 {
-	return __bch_btree_iter_init(b, iter, search, b->set);
+	return __bch_btree_iter_stack_init(b, iter, search, b->set);
 }
 
 static inline struct bkey *__bch_btree_iter_next(struct btree_iter *iter,
-						 new_btree_iter_cmp_fn *cmp)
+						 btree_iter_cmp_fn *cmp)
 {
 	struct btree_iter_set b __maybe_unused;
 	struct bkey *ret = NULL;
-	const struct min_heap_callbacks callbacks = {
-		.less = cmp,
-		.swp = new_btree_iter_swap,
-	};
 
 	if (!btree_iter_end(iter)) {
 		bch_btree_iter_next_check(iter);
 
-		ret = iter->heap.data->k;
-		iter->heap.data->k = bkey_next(iter->heap.data->k);
+		ret = iter->data->k;
+		iter->data->k = bkey_next(iter->data->k);
 
-		if (iter->heap.data->k > iter->heap.data->end) {
+		if (iter->data->k > iter->data->end) {
 			WARN_ONCE(1, "bset was corrupt!\n");
-			iter->heap.data->k = iter->heap.data->end;
+			iter->data->k = iter->data->end;
 		}
 
-		if (iter->heap.data->k == iter->heap.data->end) {
-			if (iter->heap.nr) {
-				b = min_heap_peek(&iter->heap)[0];
-				min_heap_pop(&iter->heap, &callbacks, NULL);
-			}
-		}
+		if (iter->data->k == iter->data->end)
+			heap_pop(iter, b, cmp);
 		else
-			min_heap_sift_down(&iter->heap, 0, &callbacks, NULL);
+			heap_sift(iter, 0, cmp);
 	}
 
 	return ret;
@@ -1186,7 +1157,7 @@ static inline struct bkey *__bch_btree_iter_next(struct btree_iter *iter,
 
 struct bkey *bch_btree_iter_next(struct btree_iter *iter)
 {
-	return __bch_btree_iter_next(iter, new_btree_iter_cmp);
+	return __bch_btree_iter_next(iter, btree_iter_cmp);
 
 }
 
@@ -1224,18 +1195,16 @@ static void btree_mergesort(struct btree_keys *b, struct bset *out,
 			    struct btree_iter *iter,
 			    bool fixup, bool remove_stale)
 {
+	int i;
 	struct bkey *k, *last = NULL;
 	BKEY_PADDED(k) tmp;
 	bool (*bad)(struct btree_keys *, const struct bkey *) = remove_stale
 		? bch_ptr_bad
 		: bch_ptr_invalid;
-	const struct min_heap_callbacks callbacks = {
-		.less = b->ops->sort_cmp,
-		.swp = new_btree_iter_swap,
-	};
 
 	/* Heapify the iterator, using our comparison function */
-	min_heapify_all(&iter->heap, &callbacks, NULL);
+	for (i = iter->used / 2 - 1; i >= 0; --i)
+		heap_sift(iter, i, b->ops->sort_cmp);
 
 	while (!btree_iter_end(iter)) {
 		if (b->ops->sort_fixup && fixup)
@@ -1324,11 +1293,10 @@ void bch_btree_sort_partial(struct btree_keys *b, unsigned int start,
 			    struct bset_sort_state *state)
 {
 	size_t order = b->page_order, keys = 0;
-	struct btree_iter iter;
+	struct btree_iter_stack iter;
 	int oldsize = bch_count_data(b);
 
-	min_heap_init(&iter.heap, NULL, MAX_BSETS);
-	__bch_btree_iter_init(b, &iter, NULL, &b->set[start]);
+	__bch_btree_iter_stack_init(b, &iter, NULL, &b->set[start]);
 
 	if (start) {
 		unsigned int i;
@@ -1339,7 +1307,7 @@ void bch_btree_sort_partial(struct btree_keys *b, unsigned int start,
 		order = get_order(__set_bytes(b->set->data, keys));
 	}
 
-	__btree_sort(b, &iter, start, order, false, state);
+	__btree_sort(b, &iter.iter, start, order, false, state);
 
 	EBUG_ON(oldsize >= 0 && bch_count_data(b) != oldsize);
 }
@@ -1355,13 +1323,11 @@ void bch_btree_sort_into(struct btree_keys *b, struct btree_keys *new,
 			 struct bset_sort_state *state)
 {
 	uint64_t start_time = local_clock();
-	struct btree_iter iter;
+	struct btree_iter_stack iter;
 
-	min_heap_init(&iter.heap, NULL, MAX_BSETS);
+	bch_btree_iter_stack_init(b, &iter, NULL);
 
-	bch_btree_iter_init(b, &iter, NULL);
-
-	btree_mergesort(b, new->set->data, &iter, false, true);
+	btree_mergesort(b, new->set->data, &iter.iter, false, true);
 
 	bch_time_stats_update(&state->time, start_time);
 
diff --git a/drivers/md/bcache/bset.h b/drivers/md/bcache/bset.h
index f79441acd4c1..011f6062c4c0 100644
--- a/drivers/md/bcache/bset.h
+++ b/drivers/md/bcache/bset.h
@@ -187,9 +187,8 @@ struct bset_tree {
 };
 
 struct btree_keys_ops {
-	bool		(*sort_cmp)(const void *l,
-				    const void *r,
-					void *args);
+	bool		(*sort_cmp)(struct btree_iter_set l,
+				    struct btree_iter_set r);
 	struct bkey	*(*sort_fixup)(struct btree_iter *iter,
 				       struct bkey *tmp);
 	bool		(*insert_fixup)(struct btree_keys *b,
@@ -313,17 +312,23 @@ enum {
 	BTREE_INSERT_STATUS_FRONT_MERGE,
 };
 
-struct btree_iter_set {
-	struct bkey *k, *end;
-};
-
 /* Btree key iteration */
 
 struct btree_iter {
+	size_t size, used;
 #ifdef CONFIG_BCACHE_DEBUG
 	struct btree_keys *b;
 #endif
-	MIN_HEAP_PREALLOCATED(struct btree_iter_set, btree_iter_heap, MAX_BSETS) heap;
+	struct btree_iter_set {
+		struct bkey *k, *end;
+	} data[];
+};
+
+/* Fixed-size btree_iter that can be allocated on the stack */
+
+struct btree_iter_stack {
+	struct btree_iter iter;
+	struct btree_iter_set stack_data[MAX_BSETS];
 };
 
 typedef bool (*ptr_filter_fn)(struct btree_keys *b, const struct bkey *k);
@@ -335,9 +340,9 @@ struct bkey *bch_btree_iter_next_filter(struct btree_iter *iter,
 
 void bch_btree_iter_push(struct btree_iter *iter, struct bkey *k,
 			 struct bkey *end);
-struct bkey *bch_btree_iter_init(struct btree_keys *b,
-				 struct btree_iter *iter,
-				 struct bkey *search);
+struct bkey *bch_btree_iter_stack_init(struct btree_keys *b,
+				       struct btree_iter_stack *iter,
+				       struct bkey *search);
 
 struct bkey *__bch_bset_search(struct btree_keys *b, struct bset_tree *t,
 			       const struct bkey *search);
@@ -352,13 +357,14 @@ static inline struct bkey *bch_bset_search(struct btree_keys *b,
 	return search ? __bch_bset_search(b, t, search) : t->data->start;
 }
 
-#define for_each_key_filter(b, k, iter, filter)				\
-	for (bch_btree_iter_init((b), (iter), NULL);			\
-	     ((k) = bch_btree_iter_next_filter((iter), (b), filter));)
+#define for_each_key_filter(b, k, stack_iter, filter)                      \
+	for (bch_btree_iter_stack_init((b), (stack_iter), NULL);           \
+	     ((k) = bch_btree_iter_next_filter(&((stack_iter)->iter), (b), \
+					       filter));)
 
-#define for_each_key(b, k, iter)					\
-	for (bch_btree_iter_init((b), (iter), NULL);			\
-	     ((k) = bch_btree_iter_next(iter));)
+#define for_each_key(b, k, stack_iter)                           \
+	for (bch_btree_iter_stack_init((b), (stack_iter), NULL); \
+	     ((k) = bch_btree_iter_next(&((stack_iter)->iter)));)
 
 /* Sorting */
 
diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c
index 1d0100677357..210b59007d98 100644
--- a/drivers/md/bcache/btree.c
+++ b/drivers/md/bcache/btree.c
@@ -148,19 +148,19 @@ void bch_btree_node_read_done(struct btree *b)
 {
 	const char *err = "bad btree header";
 	struct bset *i = btree_bset_first(b);
-	struct btree_iter iter;
+	struct btree_iter *iter;
 
 	/*
 	 * c->fill_iter can allocate an iterator with more memory space
 	 * than static MAX_BSETS.
 	 * See the comment arount cache_set->fill_iter.
 	 */
-	iter.heap.data = mempool_alloc(&b->c->fill_iter, GFP_NOIO);
-	iter.heap.size = b->c->cache->sb.bucket_size / b->c->cache->sb.block_size;
-	iter.heap.nr = 0;
+	iter = mempool_alloc(&b->c->fill_iter, GFP_NOIO);
+	iter->size = b->c->cache->sb.bucket_size / b->c->cache->sb.block_size;
+	iter->used = 0;
 
 #ifdef CONFIG_BCACHE_DEBUG
-	iter.b = &b->keys;
+	iter->b = &b->keys;
 #endif
 
 	if (!i->seq)
@@ -198,7 +198,7 @@ void bch_btree_node_read_done(struct btree *b)
 		if (i != b->keys.set[0].data && !i->keys)
 			goto err;
 
-		bch_btree_iter_push(&iter, i->start, bset_bkey_last(i));
+		bch_btree_iter_push(iter, i->start, bset_bkey_last(i));
 
 		b->written += set_blocks(i, block_bytes(b->c->cache));
 	}
@@ -210,7 +210,7 @@ void bch_btree_node_read_done(struct btree *b)
 		if (i->seq == b->keys.set[0].data->seq)
 			goto err;
 
-	bch_btree_sort_and_fix_extents(&b->keys, &iter, &b->c->sort);
+	bch_btree_sort_and_fix_extents(&b->keys, iter, &b->c->sort);
 
 	i = b->keys.set[0].data;
 	err = "short btree key";
@@ -222,7 +222,7 @@ void bch_btree_node_read_done(struct btree *b)
 		bch_bset_init_next(&b->keys, write_block(b),
 				   bset_magic(&b->c->cache->sb));
 out:
-	mempool_free(iter.heap.data, &b->c->fill_iter);
+	mempool_free(iter, &b->c->fill_iter);
 	return;
 err:
 	set_btree_node_io_error(b);
@@ -1306,11 +1306,9 @@ static bool btree_gc_mark_node(struct btree *b, struct gc_stat *gc)
 	uint8_t stale = 0;
 	unsigned int keys = 0, good_keys = 0;
 	struct bkey *k;
-	struct btree_iter iter;
+	struct btree_iter_stack iter;
 	struct bset_tree *t;
 
-	min_heap_init(&iter.heap, NULL, MAX_BSETS);
-
 	gc->nodes++;
 
 	for_each_key_filter(&b->keys, k, &iter, bch_ptr_invalid) {
@@ -1569,11 +1567,9 @@ static int btree_gc_rewrite_node(struct btree *b, struct btree_op *op,
 static unsigned int btree_gc_count_keys(struct btree *b)
 {
 	struct bkey *k;
-	struct btree_iter iter;
+	struct btree_iter_stack iter;
 	unsigned int ret = 0;
 
-	min_heap_init(&iter.heap, NULL, MAX_BSETS);
-
 	for_each_key_filter(&b->keys, k, &iter, bch_ptr_bad)
 		ret += bkey_u64s(k);
 
@@ -1612,18 +1608,18 @@ static int btree_gc_recurse(struct btree *b, struct btree_op *op,
 	int ret = 0;
 	bool should_rewrite;
 	struct bkey *k;
-	struct btree_iter iter;
+	struct btree_iter_stack iter;
 	struct gc_merge_info r[GC_MERGE_NODES];
 	struct gc_merge_info *i, *last = r + ARRAY_SIZE(r) - 1;
 
-	min_heap_init(&iter.heap, NULL, MAX_BSETS);
-	bch_btree_iter_init(&b->keys, &iter, &b->c->gc_done);
+	bch_btree_iter_stack_init(&b->keys, &iter, &b->c->gc_done);
 
 	for (i = r; i < r + ARRAY_SIZE(r); i++)
 		i->b = ERR_PTR(-EINTR);
 
 	while (1) {
-		k = bch_btree_iter_next_filter(&iter, &b->keys, bch_ptr_bad);
+		k = bch_btree_iter_next_filter(&iter.iter, &b->keys,
+					       bch_ptr_bad);
 		if (k) {
 			r->b = bch_btree_node_get(b->c, op, k, b->level - 1,
 						  true, b);
@@ -1918,9 +1914,7 @@ static int bch_btree_check_recurse(struct btree *b, struct btree_op *op)
 {
 	int ret = 0;
 	struct bkey *k, *p = NULL;
-	struct btree_iter iter;
-
-	min_heap_init(&iter.heap, NULL, MAX_BSETS);
+	struct btree_iter_stack iter;
 
 	for_each_key_filter(&b->keys, k, &iter, bch_ptr_invalid)
 		bch_initial_mark_key(b->c, b->level, k);
@@ -1928,10 +1922,10 @@ static int bch_btree_check_recurse(struct btree *b, struct btree_op *op)
 	bch_initial_mark_key(b->c, b->level + 1, &b->key);
 
 	if (b->level) {
-		bch_btree_iter_init(&b->keys, &iter, NULL);
+		bch_btree_iter_stack_init(&b->keys, &iter, NULL);
 
 		do {
-			k = bch_btree_iter_next_filter(&iter, &b->keys,
+			k = bch_btree_iter_next_filter(&iter.iter, &b->keys,
 						       bch_ptr_bad);
 			if (k) {
 				btree_node_prefetch(b, k);
@@ -1959,7 +1953,7 @@ static int bch_btree_check_thread(void *arg)
 	struct btree_check_info *info = arg;
 	struct btree_check_state *check_state = info->state;
 	struct cache_set *c = check_state->c;
-	struct btree_iter iter;
+	struct btree_iter_stack iter;
 	struct bkey *k, *p;
 	int cur_idx, prev_idx, skip_nr;
 
@@ -1967,11 +1961,9 @@ static int bch_btree_check_thread(void *arg)
 	cur_idx = prev_idx = 0;
 	ret = 0;
 
-	min_heap_init(&iter.heap, NULL, MAX_BSETS);
-
 	/* root node keys are checked before thread created */
-	bch_btree_iter_init(&c->root->keys, &iter, NULL);
-	k = bch_btree_iter_next_filter(&iter, &c->root->keys, bch_ptr_bad);
+	bch_btree_iter_stack_init(&c->root->keys, &iter, NULL);
+	k = bch_btree_iter_next_filter(&iter.iter, &c->root->keys, bch_ptr_bad);
 	BUG_ON(!k);
 
 	p = k;
@@ -1989,7 +1981,7 @@ static int bch_btree_check_thread(void *arg)
 		skip_nr = cur_idx - prev_idx;
 
 		while (skip_nr) {
-			k = bch_btree_iter_next_filter(&iter,
+			k = bch_btree_iter_next_filter(&iter.iter,
 						       &c->root->keys,
 						       bch_ptr_bad);
 			if (k)
@@ -2062,11 +2054,9 @@ int bch_btree_check(struct cache_set *c)
 	int ret = 0;
 	int i;
 	struct bkey *k = NULL;
-	struct btree_iter iter;
+	struct btree_iter_stack iter;
 	struct btree_check_state check_state;
 
-	min_heap_init(&iter.heap, NULL, MAX_BSETS);
-
 	/* check and mark root node keys */
 	for_each_key_filter(&c->root->keys, k, &iter, bch_ptr_invalid)
 		bch_initial_mark_key(c, c->root->level, k);
@@ -2560,12 +2550,11 @@ static int bch_btree_map_nodes_recurse(struct btree *b, struct btree_op *op,
 
 	if (b->level) {
 		struct bkey *k;
-		struct btree_iter iter;
+		struct btree_iter_stack iter;
 
-		min_heap_init(&iter.heap, NULL, MAX_BSETS);
-		bch_btree_iter_init(&b->keys, &iter, from);
+		bch_btree_iter_stack_init(&b->keys, &iter, from);
 
-		while ((k = bch_btree_iter_next_filter(&iter, &b->keys,
+		while ((k = bch_btree_iter_next_filter(&iter.iter, &b->keys,
 						       bch_ptr_bad))) {
 			ret = bcache_btree(map_nodes_recurse, k, b,
 				    op, from, fn, flags);
@@ -2594,12 +2583,12 @@ int bch_btree_map_keys_recurse(struct btree *b, struct btree_op *op,
 {
 	int ret = MAP_CONTINUE;
 	struct bkey *k;
-	struct btree_iter iter;
+	struct btree_iter_stack iter;
 
-	min_heap_init(&iter.heap, NULL, MAX_BSETS);
-	bch_btree_iter_init(&b->keys, &iter, from);
+	bch_btree_iter_stack_init(&b->keys, &iter, from);
 
-	while ((k = bch_btree_iter_next_filter(&iter, &b->keys, bch_ptr_bad))) {
+	while ((k = bch_btree_iter_next_filter(&iter.iter, &b->keys,
+					       bch_ptr_bad))) {
 		ret = !b->level
 			? fn(op, b, k)
 			: bcache_btree(map_keys_recurse, k,
diff --git a/drivers/md/bcache/extents.c b/drivers/md/bcache/extents.c
index a7221e5dbe81..d626ffcbecb9 100644
--- a/drivers/md/bcache/extents.c
+++ b/drivers/md/bcache/extents.c
@@ -33,16 +33,15 @@ static void sort_key_next(struct btree_iter *iter,
 	i->k = bkey_next(i->k);
 
 	if (i->k == i->end)
-		*i = iter->heap.data[--iter->heap.nr];
+		*i = iter->data[--iter->used];
 }
 
-static bool new_bch_key_sort_cmp(const void *l, const void *r, void *args)
+static bool bch_key_sort_cmp(struct btree_iter_set l,
+			     struct btree_iter_set r)
 {
-	struct btree_iter_set *_l = (struct btree_iter_set *)l;
-	struct btree_iter_set *_r = (struct btree_iter_set *)r;
-	int64_t c = bkey_cmp(_l->k, _r->k);
+	int64_t c = bkey_cmp(l.k, r.k);
 
-	return !(c ? c > 0 : _l->k < _r->k);
+	return c ? c > 0 : l.k < r.k;
 }
 
 static bool __ptr_invalid(struct cache_set *c, const struct bkey *k)
@@ -239,7 +238,7 @@ static bool bch_btree_ptr_insert_fixup(struct btree_keys *bk,
 }
 
 const struct btree_keys_ops bch_btree_keys_ops = {
-	.sort_cmp	= new_bch_key_sort_cmp,
+	.sort_cmp	= bch_key_sort_cmp,
 	.insert_fixup	= bch_btree_ptr_insert_fixup,
 	.key_invalid	= bch_btree_ptr_invalid,
 	.key_bad	= bch_btree_ptr_bad,
@@ -256,36 +255,22 @@ const struct btree_keys_ops bch_btree_keys_ops = {
  * Necessary for btree_sort_fixup() - if there are multiple keys that compare
  * equal in different sets, we have to process them newest to oldest.
  */
-
-static bool new_bch_extent_sort_cmp(const void *l, const void *r, void __always_unused *args)
+static bool bch_extent_sort_cmp(struct btree_iter_set l,
+				struct btree_iter_set r)
 {
-	struct btree_iter_set *_l = (struct btree_iter_set *)l;
-	struct btree_iter_set *_r = (struct btree_iter_set *)r;
-	int64_t c = bkey_cmp(&START_KEY(_l->k), &START_KEY(_r->k));
+	int64_t c = bkey_cmp(&START_KEY(l.k), &START_KEY(r.k));
 
-	return !(c ? c > 0 : _l->k < _r->k);
-}
-
-static inline void new_btree_iter_swap(void *iter1, void *iter2, void __always_unused *args)
-{
-	struct btree_iter_set *_iter1 = iter1;
-	struct btree_iter_set *_iter2 = iter2;
-
-	swap(*_iter1, *_iter2);
+	return c ? c > 0 : l.k < r.k;
 }
 
 static struct bkey *bch_extent_sort_fixup(struct btree_iter *iter,
 					  struct bkey *tmp)
 {
-	const struct min_heap_callbacks callbacks = {
-		.less = new_bch_extent_sort_cmp,
-		.swp = new_btree_iter_swap,
-	};
-	while (iter->heap.nr > 1) {
-		struct btree_iter_set *top = iter->heap.data, *i = top + 1;
+	while (iter->used > 1) {
+		struct btree_iter_set *top = iter->data, *i = top + 1;
 
-		if (iter->heap.nr > 2 &&
-		    !new_bch_extent_sort_cmp(&i[0], &i[1], NULL))
+		if (iter->used > 2 &&
+		    bch_extent_sort_cmp(i[0], i[1]))
 			i++;
 
 		if (bkey_cmp(top->k, &START_KEY(i->k)) <= 0)
@@ -293,7 +278,7 @@ static struct bkey *bch_extent_sort_fixup(struct btree_iter *iter,
 
 		if (!KEY_SIZE(i->k)) {
 			sort_key_next(iter, i);
-			min_heap_sift_down(&iter->heap, i - top, &callbacks, NULL);
+			heap_sift(iter, i - top, bch_extent_sort_cmp);
 			continue;
 		}
 
@@ -303,7 +288,7 @@ static struct bkey *bch_extent_sort_fixup(struct btree_iter *iter,
 			else
 				bch_cut_front(top->k, i->k);
 
-			min_heap_sift_down(&iter->heap, i - top, &callbacks, NULL);
+			heap_sift(iter, i - top, bch_extent_sort_cmp);
 		} else {
 			/* can't happen because of comparison func */
 			BUG_ON(!bkey_cmp(&START_KEY(top->k), &START_KEY(i->k)));
@@ -313,7 +298,7 @@ static struct bkey *bch_extent_sort_fixup(struct btree_iter *iter,
 
 				bch_cut_back(&START_KEY(i->k), tmp);
 				bch_cut_front(i->k, top->k);
-				min_heap_sift_down(&iter->heap, 0, &callbacks, NULL);
+				heap_sift(iter, 0, bch_extent_sort_cmp);
 
 				return tmp;
 			} else {
@@ -633,7 +618,7 @@ static bool bch_extent_merge(struct btree_keys *bk,
 }
 
 const struct btree_keys_ops bch_extent_keys_ops = {
-	.sort_cmp	= new_bch_extent_sort_cmp,
+	.sort_cmp	= bch_extent_sort_cmp,
 	.sort_fixup	= bch_extent_sort_fixup,
 	.insert_fixup	= bch_extent_insert_fixup,
 	.key_invalid	= bch_extent_invalid,
diff --git a/drivers/md/bcache/movinggc.c b/drivers/md/bcache/movinggc.c
index d6c73dd8eb2b..26a6a535ec32 100644
--- a/drivers/md/bcache/movinggc.c
+++ b/drivers/md/bcache/movinggc.c
@@ -182,27 +182,16 @@ err:		if (!IS_ERR_OR_NULL(w->private))
 	closure_sync(&cl);
 }
 
-static bool new_bucket_cmp(const void *l, const void *r, void __always_unused *args)
+static bool bucket_cmp(struct bucket *l, struct bucket *r)
 {
-	struct bucket **_l = (struct bucket **)l;
-	struct bucket **_r = (struct bucket **)r;
-
-	return GC_SECTORS_USED(*_l) >= GC_SECTORS_USED(*_r);
-}
-
-static void new_bucket_swap(void *l, void *r, void __always_unused *args)
-{
-	struct bucket **_l = l;
-	struct bucket **_r = r;
-
-	swap(*_l, *_r);
+	return GC_SECTORS_USED(l) < GC_SECTORS_USED(r);
 }
 
 static unsigned int bucket_heap_top(struct cache *ca)
 {
 	struct bucket *b;
 
-	return (b = min_heap_peek(&ca->heap)[0]) ? GC_SECTORS_USED(b) : 0;
+	return (b = heap_peek(&ca->heap)) ? GC_SECTORS_USED(b) : 0;
 }
 
 void bch_moving_gc(struct cache_set *c)
@@ -210,10 +199,6 @@ void bch_moving_gc(struct cache_set *c)
 	struct cache *ca = c->cache;
 	struct bucket *b;
 	unsigned long sectors_to_move, reserve_sectors;
-	const struct min_heap_callbacks callbacks = {
-		.less = new_bucket_cmp,
-		.swp = new_bucket_swap,
-	};
 
 	if (!c->copy_gc_enabled)
 		return;
@@ -224,7 +209,7 @@ void bch_moving_gc(struct cache_set *c)
 	reserve_sectors = ca->sb.bucket_size *
 			     fifo_used(&ca->free[RESERVE_MOVINGGC]);
 
-	ca->heap.nr = 0;
+	ca->heap.used = 0;
 
 	for_each_bucket(b, ca) {
 		if (GC_MARK(b) == GC_MARK_METADATA ||
@@ -233,31 +218,25 @@ void bch_moving_gc(struct cache_set *c)
 		    atomic_read(&b->pin))
 			continue;
 
-		if (!min_heap_full(&ca->heap)) {
+		if (!heap_full(&ca->heap)) {
 			sectors_to_move += GC_SECTORS_USED(b);
-			min_heap_push(&ca->heap, &b, &callbacks, NULL);
-		} else if (!new_bucket_cmp(&b, min_heap_peek(&ca->heap), ca)) {
+			heap_add(&ca->heap, b, bucket_cmp);
+		} else if (bucket_cmp(b, heap_peek(&ca->heap))) {
 			sectors_to_move -= bucket_heap_top(ca);
 			sectors_to_move += GC_SECTORS_USED(b);
 
 			ca->heap.data[0] = b;
-			min_heap_sift_down(&ca->heap, 0, &callbacks, NULL);
+			heap_sift(&ca->heap, 0, bucket_cmp);
 		}
 	}
 
 	while (sectors_to_move > reserve_sectors) {
-		if (ca->heap.nr) {
-			b = min_heap_peek(&ca->heap)[0];
-			min_heap_pop(&ca->heap, &callbacks, NULL);
-		}
+		heap_pop(&ca->heap, b, bucket_cmp);
 		sectors_to_move -= GC_SECTORS_USED(b);
 	}
 
-	while (ca->heap.nr) {
-		b = min_heap_peek(&ca->heap)[0];
-		min_heap_pop(&ca->heap, &callbacks, NULL);
+	while (heap_pop(&ca->heap, b, bucket_cmp))
 		SET_GC_MOVE(b, 1);
-	}
 
 	mutex_unlock(&c->bucket_lock);
 
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index 1efb768b2890..2ea490b9d370 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -1912,7 +1912,8 @@ struct cache_set *bch_cache_set_alloc(struct cache_sb *sb)
 	INIT_LIST_HEAD(&c->btree_cache_freed);
 	INIT_LIST_HEAD(&c->data_buckets);
 
-	iter_size = ((meta_bucket_pages(sb) * PAGE_SECTORS) / sb->block_size) *
+	iter_size = sizeof(struct btree_iter) +
+		    ((meta_bucket_pages(sb) * PAGE_SECTORS) / sb->block_size) *
 			    sizeof(struct btree_iter_set);
 
 	c->devices = kcalloc(c->nr_uuids, sizeof(void *), GFP_KERNEL);
diff --git a/drivers/md/bcache/sysfs.c b/drivers/md/bcache/sysfs.c
index e8f696cb58c0..826b14cae4e5 100644
--- a/drivers/md/bcache/sysfs.c
+++ b/drivers/md/bcache/sysfs.c
@@ -660,9 +660,7 @@ static unsigned int bch_root_usage(struct cache_set *c)
 	unsigned int bytes = 0;
 	struct bkey *k;
 	struct btree *b;
-	struct btree_iter iter;
-
-	min_heap_init(&iter.heap, NULL, MAX_BSETS);
+	struct btree_iter_stack iter;
 
 	goto lock_root;
 
diff --git a/drivers/md/bcache/util.h b/drivers/md/bcache/util.h
index 539454d8e2d0..f61ab1bada6c 100644
--- a/drivers/md/bcache/util.h
+++ b/drivers/md/bcache/util.h
@@ -9,7 +9,6 @@
 #include <linux/kernel.h>
 #include <linux/sched/clock.h>
 #include <linux/llist.h>
-#include <linux/min_heap.h>
 #include <linux/ratelimit.h>
 #include <linux/vmalloc.h>
 #include <linux/workqueue.h>
@@ -31,10 +30,16 @@ struct closure;
 
 #endif
 
+#define DECLARE_HEAP(type, name)					\
+	struct {							\
+		size_t size, used;					\
+		type *data;						\
+	} name
+
 #define init_heap(heap, _size, gfp)					\
 ({									\
 	size_t _bytes;							\
-	(heap)->nr = 0;						\
+	(heap)->used = 0;						\
 	(heap)->size = (_size);						\
 	_bytes = (heap)->size * sizeof(*(heap)->data);			\
 	(heap)->data = kvmalloc(_bytes, (gfp) & GFP_KERNEL);		\
@@ -47,6 +52,64 @@ do {									\
 	(heap)->data = NULL;						\
 } while (0)
 
+#define heap_swap(h, i, j)	swap((h)->data[i], (h)->data[j])
+
+#define heap_sift(h, i, cmp)						\
+do {									\
+	size_t _r, _j = i;						\
+									\
+	for (; _j * 2 + 1 < (h)->used; _j = _r) {			\
+		_r = _j * 2 + 1;					\
+		if (_r + 1 < (h)->used &&				\
+		    cmp((h)->data[_r], (h)->data[_r + 1]))		\
+			_r++;						\
+									\
+		if (cmp((h)->data[_r], (h)->data[_j]))			\
+			break;						\
+		heap_swap(h, _r, _j);					\
+	}								\
+} while (0)
+
+#define heap_sift_down(h, i, cmp)					\
+do {									\
+	while (i) {							\
+		size_t p = (i - 1) / 2;					\
+		if (cmp((h)->data[i], (h)->data[p]))			\
+			break;						\
+		heap_swap(h, i, p);					\
+		i = p;							\
+	}								\
+} while (0)
+
+#define heap_add(h, d, cmp)						\
+({									\
+	bool _r = !heap_full(h);					\
+	if (_r) {							\
+		size_t _i = (h)->used++;				\
+		(h)->data[_i] = d;					\
+									\
+		heap_sift_down(h, _i, cmp);				\
+		heap_sift(h, _i, cmp);					\
+	}								\
+	_r;								\
+})
+
+#define heap_pop(h, d, cmp)						\
+({									\
+	bool _r = (h)->used;						\
+	if (_r) {							\
+		(d) = (h)->data[0];					\
+		(h)->used--;						\
+		heap_swap(h, 0, (h)->used);				\
+		heap_sift(h, 0, cmp);					\
+	}								\
+	_r;								\
+})
+
+#define heap_peek(h)	((h)->used ? (h)->data[0] : NULL)
+
+#define heap_full(h)	((h)->used == (h)->size)
+
 #define DECLARE_FIFO(type, name)					\
 	struct {							\
 		size_t front, back, size, mask;				\
diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c
index 453efbbdc8ee..302e75f1fc4b 100644
--- a/drivers/md/bcache/writeback.c
+++ b/drivers/md/bcache/writeback.c
@@ -908,16 +908,15 @@ static int bch_dirty_init_thread(void *arg)
 	struct dirty_init_thrd_info *info = arg;
 	struct bch_dirty_init_state *state = info->state;
 	struct cache_set *c = state->c;
-	struct btree_iter iter;
+	struct btree_iter_stack iter;
 	struct bkey *k, *p;
 	int cur_idx, prev_idx, skip_nr;
 
 	k = p = NULL;
 	prev_idx = 0;
 
-	min_heap_init(&iter.heap, NULL, MAX_BSETS);
-	bch_btree_iter_init(&c->root->keys, &iter, NULL);
-	k = bch_btree_iter_next_filter(&iter, &c->root->keys, bch_ptr_bad);
+	bch_btree_iter_stack_init(&c->root->keys, &iter, NULL);
+	k = bch_btree_iter_next_filter(&iter.iter, &c->root->keys, bch_ptr_bad);
 	BUG_ON(!k);
 
 	p = k;
@@ -931,7 +930,7 @@ static int bch_dirty_init_thread(void *arg)
 		skip_nr = cur_idx - prev_idx;
 
 		while (skip_nr) {
-			k = bch_btree_iter_next_filter(&iter,
+			k = bch_btree_iter_next_filter(&iter.iter,
 						       &c->root->keys,
 						       bch_ptr_bad);
 			if (k)
@@ -980,13 +979,11 @@ void bch_sectors_dirty_init(struct bcache_device *d)
 	int i;
 	struct btree *b = NULL;
 	struct bkey *k = NULL;
-	struct btree_iter iter;
+	struct btree_iter_stack iter;
 	struct sectors_dirty_init op;
 	struct cache_set *c = d->c;
 	struct bch_dirty_init_state state;
 
-	min_heap_init(&iter.heap, NULL, MAX_BSETS);
-
 retry_lock:
 	b = c->root;
 	rw_lock(0, b, b->level);

From 95b2e31e1752494d477c5da89d6789f769b0d67b Mon Sep 17 00:00:00 2001
From: Kuan-Wei Chiu <visitorckw@gmail.com>
Date: Sun, 15 Jun 2025 04:23:53 +0800
Subject: [PATCH 0666/1334] bcache: remove unnecessary select MIN_HEAP

After reverting the transition to the generic min heap library, bcache no
longer depends on MIN_HEAP.  The select entry can be removed to reduce
code size and shrink the kernel's attack surface.

This change effectively reverts the bcache-related part of commit
92a8b224b833 ("lib/min_heap: introduce non-inline versions of min heap API
functions").

This is part of a series of changes to address a performance regression
caused by the use of the generic min_heap implementation.

As reported by Robert, bcache now suffers from latency spikes, with P100
(max) latency increasing from 600 ms to 2.4 seconds every 5 minutes.
These regressions degrade bcache's effectiveness as a low-latency cache
layer and lead to frequent timeouts and application stalls in production
environments.

Link: https://lore.kernel.org/lkml/CAJhEC05+0S69z+3+FB2Cd0hD+pCRyWTKLEOsc8BOmH73p1m+KQ@mail.gmail.com
Link: https://lkml.kernel.org/r/20250614202353.1632957-4-visitorckw@gmail.com
Fixes: 866898efbb25 ("bcache: remove heap-related macros and switch to generic min_heap")
Fixes: 92a8b224b833 ("lib/min_heap: introduce non-inline versions of min heap API functions")
Signed-off-by: Kuan-Wei Chiu <visitorckw@gmail.com>
Reported-by: Robert Pang <robertpang@google.com>
Closes: https://lore.kernel.org/linux-bcache/CAJhEC06F_AtrPgw2-7CvCqZgeStgCtitbD-ryuPpXQA-JG5XXw@mail.gmail.com
Acked-by: Coly Li <colyli@kernel.org>
Cc: Ching-Chun (Jim) Huang <jserv@ccns.ncku.edu.tw>
Cc: Kent Overstreet <kent.overstreet@linux.dev>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 drivers/md/bcache/Kconfig | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/md/bcache/Kconfig b/drivers/md/bcache/Kconfig
index d4697e79d5a3..b2d10063d35f 100644
--- a/drivers/md/bcache/Kconfig
+++ b/drivers/md/bcache/Kconfig
@@ -5,7 +5,6 @@ config BCACHE
 	select BLOCK_HOLDER_DEPRECATED if SYSFS
 	select CRC64
 	select CLOSURES
-	select MIN_HEAP
 	help
 	Allows a block device to be used as cache for other devices; uses
 	a btree for indexing and the layout is optimized for SSDs.

From 3333871296efd52ef6f6d5cce5a92dc7b06ba879 Mon Sep 17 00:00:00 2001
From: Pedro Falcato <pfalcato@suse.de>
Date: Tue, 10 Jun 2025 13:22:09 +0100
Subject: [PATCH 0667/1334] selftests/mm: skip uprobe vma merge test if uprobes
 are not enabled

If uprobes are not enabled, the test currently fails with:

7151 12:46:54.627936  # # #  RUN           merge.handle_uprobe_upon_merged_vma ...
7152 12:46:54.639014  # # f /sys/bus/event_source/devices/uprobe/type
7153 12:46:54.639306  # # fopen: No such file or directory
7154 12:46:54.650451  # # # merge.c:473:handle_uprobe_upon_merged_vma:Expected
read_sysfs("/sys/bus/event_source/devices/uprobe/type", &type) (1) == 0 (0)
7155 12:46:54.650730  # # # handle_uprobe_upon_merged_vma: Test terminated by assertion
7156 12:46:54.661750  # # #          FAIL  merge.handle_uprobe_upon_merged_vma
7157 12:46:54.662030  # # not ok 8 merge.handle_uprobe_upon_merged_vma

Skipping is a more sane and friendly behavior here.

Link: https://lkml.kernel.org/r/20250610122209.3177587-1-pfalcato@suse.de
Fixes: efe99fabeb11 ("selftests/mm: add test about uprobe pte be orphan during vma merge")
Signed-off-by: Pedro Falcato <pfalcato@suse.de>
Reported-by: Aishwarya <aishwarya.tcv@arm.com>
Closes: https://lore.kernel.org/linux-mm/20250610103729.72440-1-aishwarya.tcv@arm.com/
Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Tested-by : Donet Tom <donettom@linux.ibm.com>
Reviewed-by : Donet Tom <donettom@linux.ibm.com>
Reviewed-by: Dev Jain <dev.jain@arm.com>
Reviewed-by: Pu Lehui <pulehui@huawei.com>
Cc: Jann Horn <jannh@google.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Mark Brown <broonie@kernel.org>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 tools/testing/selftests/mm/merge.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/mm/merge.c b/tools/testing/selftests/mm/merge.c
index bbae66fc5038..cc26480098ae 100644
--- a/tools/testing/selftests/mm/merge.c
+++ b/tools/testing/selftests/mm/merge.c
@@ -470,7 +470,9 @@ TEST_F(merge, handle_uprobe_upon_merged_vma)
 	ASSERT_GE(fd, 0);
 
 	ASSERT_EQ(ftruncate(fd, page_size), 0);
-	ASSERT_EQ(read_sysfs("/sys/bus/event_source/devices/uprobe/type", &type), 0);
+	if (read_sysfs("/sys/bus/event_source/devices/uprobe/type", &type) != 0) {
+		SKIP(goto out, "Failed to read uprobe sysfs file, skipping");
+	}
 
 	memset(&attr, 0, attr_sz);
 	attr.size = attr_sz;
@@ -491,6 +493,7 @@ TEST_F(merge, handle_uprobe_upon_merged_vma)
 	ASSERT_NE(mremap(ptr2, page_size, page_size,
 			 MREMAP_MAYMOVE | MREMAP_FIXED, ptr1), MAP_FAILED);
 
+out:
 	close(fd);
 	remove(probe_file);
 }

From 38103247777695ca2b09691b2247e66f157908c6 Mon Sep 17 00:00:00 2001
From: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Date: Mon, 16 Jun 2025 21:16:43 +0100
Subject: [PATCH 0668/1334] MAINTAINERS: add missing mm/workingset.c file to mm
 reclaim section

The working set logic belongs very much to the reclaim section and is
otherwise not assigned to any other MAINTAINERS section so add it here.

Link: https://lkml.kernel.org/r/20250616201643.561626-1-lorenzo.stoakes@oracle.com
Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Acked-by: David Hildenbrand <david@redhat.com>
Acked-by: Shakeel Butt <shakeel.butt@linux.dev>
Acked-by: Qi Zheng <zhengqi.arch@bytedance.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 MAINTAINERS | 1 +
 1 file changed, 1 insertion(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index 9a7fdc52cf9d..0497cbcc5d3e 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -15871,6 +15871,7 @@ L:	linux-mm@kvack.org
 S:	Maintained
 F:	mm/pt_reclaim.c
 F:	mm/vmscan.c
+F:	mm/workingset.c
 
 MEMORY MANAGEMENT - RMAP (REVERSE MAPPING)
 M:	Andrew Morton <akpm@linux-foundation.org>

From 40ffd2887635c492b758d8b02172c97f5d42f593 Mon Sep 17 00:00:00 2001
From: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Date: Mon, 16 Jun 2025 21:08:44 +0100
Subject: [PATCH 0669/1334] MAINTAINERS: add missing test files to mm gup
 section

We previously overlooked GUP test files that sensibly should belong to the
GUP section, include them now.

Link: https://lkml.kernel.org/r/20250616200844.560225-1-lorenzo.stoakes@oracle.com
Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Acked-by: David Hildenbrand <david@redhat.com>
Reviewed-by: John Hubbard <jhubbard@nvidia.com>
Cc: Jason Gunthorpe <jgg@nvidia.com>
Cc: Peter Xu <peterx@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 MAINTAINERS | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index 0497cbcc5d3e..a70454f527c3 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -15795,6 +15795,10 @@ S:	Maintained
 W:	http://www.linux-mm.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
 F:	mm/gup.c
+F:	mm/gup_test.c
+F:	mm/gup_test.h
+F:	tools/testing/selftests/mm/gup_longterm.c
+F:	tools/testing/selftests/mm/gup_test.c
 
 MEMORY MANAGEMENT - KSM (Kernel Samepage Merging)
 M:	Andrew Morton <akpm@linux-foundation.org>

From fba46a5d83ca8decb338722fb4899026d8d9ead2 Mon Sep 17 00:00:00 2001
From: "Liam R. Howlett" <Liam.Howlett@oracle.com>
Date: Mon, 16 Jun 2025 14:45:20 -0400
Subject: [PATCH 0670/1334] maple_tree: fix MA_STATE_PREALLOC flag in
 mas_preallocate()

Temporarily clear the preallocation flag when explicitly requesting
allocations.  Pre-existing allocations are already counted against the
request through mas_node_count_gfp(), but the allocations will not happen
if the MA_STATE_PREALLOC flag is set.  This flag is meant to avoid
re-allocating in bulk allocation mode, and to detect issues with
preallocation calculations.

The MA_STATE_PREALLOC flag should also always be set on zero allocations
so that detection of underflow allocations will print a WARN_ON() during
consumption.

User visible effect of this flaw is a WARN_ON() followed by a null pointer
dereference when subsequent requests for larger number of nodes is
ignored, such as the vma merge retry in mmap_region() caused by drivers
altering the vma flags (which happens in v6.6, at least)

Link: https://lkml.kernel.org/r/20250616184521.3382795-3-Liam.Howlett@oracle.com
Fixes: 54a611b60590 ("Maple Tree: add new data structure")
Signed-off-by: Liam R. Howlett <Liam.Howlett@oracle.com>
Reported-by: Zhaoyang Huang <zhaoyang.huang@unisoc.com>
Reported-by: Hailong Liu <hailong.liu@oppo.com>
Link: https://lore.kernel.org/all/1652f7eb-a51b-4fee-8058-c73af63bacd1@oppo.com/
Link: https://lore.kernel.org/all/20250428184058.1416274-1-Liam.Howlett@oracle.com/
Link: https://lore.kernel.org/all/20250429014754.1479118-1-Liam.Howlett@oracle.com/
Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Hailong Liu <hailong.liu@oppo.com>
Cc: zhangpeng.00@bytedance.com <zhangpeng.00@bytedance.com>
Cc: Steve Kang <Steve.Kang@unisoc.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Sidhartha Kumar <sidhartha.kumar@oracle.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 lib/maple_tree.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/lib/maple_tree.c b/lib/maple_tree.c
index affe979bd14d..00524e55a21e 100644
--- a/lib/maple_tree.c
+++ b/lib/maple_tree.c
@@ -5527,8 +5527,9 @@ int mas_preallocate(struct ma_state *mas, void *entry, gfp_t gfp)
 	mas->store_type = mas_wr_store_type(&wr_mas);
 	request = mas_prealloc_calc(&wr_mas, entry);
 	if (!request)
-		return ret;
+		goto set_flag;
 
+	mas->mas_flags &= ~MA_STATE_PREALLOC;
 	mas_node_count_gfp(mas, request, gfp);
 	if (mas_is_err(mas)) {
 		mas_set_alloc_req(mas, 0);
@@ -5538,6 +5539,7 @@ int mas_preallocate(struct ma_state *mas, void *entry, gfp_t gfp)
 		return ret;
 	}
 
+set_flag:
 	mas->mas_flags |= MA_STATE_PREALLOC;
 	return ret;
 }

From 883cf5b0b8389610f17106c454180c7f54b8d486 Mon Sep 17 00:00:00 2001
From: Oscar Salvador <osalvador@suse.de>
Date: Tue, 17 Jun 2025 20:59:10 +0200
Subject: [PATCH 0671/1334] MAINTAINERS: update maintainers for HugeTLB

Change my role to Maintainer as I am quite involved in HugeTLB
development, and will be more so with the upcoming HugetLB-pagewalk
unification, so I would like to help Munchun take care of the code.
Besides, having two people will help in offloading some pressure.

Also add David as a Reviewer since he has quite some knowledge in the
field and has already provided valuable feedback.

Link: https://lkml.kernel.org/r/20250617185910.471406-1-osalvador@suse.de
Signed-off-by: Oscar Salvador <osalvador@suse.de>
Acked-by: David Hildenbrand <david@redhat.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Muchun Song <muchun.song@linux.dev>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Peter Xu <peterx@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 MAINTAINERS | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index a70454f527c3..a2c8e4546cf8 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -11157,7 +11157,8 @@ F:	include/linux/platform_data/huawei-gaokun-ec.h
 
 HUGETLB SUBSYSTEM
 M:	Muchun Song <muchun.song@linux.dev>
-R:	Oscar Salvador <osalvador@suse.de>
+M:	Oscar Salvador <osalvador@suse.de>
+R:	David Hildenbrand <david@redhat.com>
 L:	linux-mm@kvack.org
 S:	Maintained
 F:	Documentation/ABI/testing/sysfs-kernel-mm-hugepages

From b6d19f3742ff3429d8eb2cdf51a8ab598c197ee5 Mon Sep 17 00:00:00 2001
From: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Date: Tue, 17 Jun 2025 18:45:38 +0100
Subject: [PATCH 0672/1334] MAINTAINERS: add further init files to mm init
 block

These files comprise the bootmem info logic which is initialised on
startup and also memory tests that are run on startup and as such this
seems the most appropriate section for them.

Link: https://lkml.kernel.org/r/20250617174538.188977-1-lorenzo.stoakes@oracle.com
Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Reviewed-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 MAINTAINERS | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index a2c8e4546cf8..1f87cb444c83 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -15680,8 +15680,11 @@ S:	Maintained
 F:	Documentation/core-api/boot-time-mm.rst
 F:	Documentation/core-api/kho/bindings/memblock/*
 F:	include/linux/memblock.h
+F:	mm/bootmem_info.c
 F:	mm/memblock.c
+F:	mm/memtest.c
 F:	mm/mm_init.c
+F:	mm/rodata_test.c
 F:	tools/testing/memblock/
 
 MEMORY ALLOCATION PROFILING

From d91b00b687abf6fef13be030abd848416f320149 Mon Sep 17 00:00:00 2001
From: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Date: Tue, 17 Jun 2025 18:15:38 +0100
Subject: [PATCH 0673/1334] MAINTAINERS: add hugetlb_cgroup.c to hugetlb
 section

This file is clearly specific to hugetlb so this seems the most
appropriate place for it.

Link: https://lkml.kernel.org/r/20250617171538.178042-1-lorenzo.stoakes@oracle.com
Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Oscar Salvador <osalvador@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 MAINTAINERS | 1 +
 1 file changed, 1 insertion(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index 1f87cb444c83..cf9ea0425011 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -11169,6 +11169,7 @@ F:	fs/hugetlbfs/
 F:	include/linux/hugetlb.h
 F:	include/trace/events/hugetlbfs.h
 F:	mm/hugetlb.c
+F:	mm/hugetlb_cgroup.c
 F:	mm/hugetlb_cma.c
 F:	mm/hugetlb_cma.h
 F:	mm/hugetlb_vmemmap.c

From a1540dcbe0246c42ee271a3b7bba5ec7c933321a Mon Sep 17 00:00:00 2001
From: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Date: Tue, 17 Jun 2025 17:51:42 +0100
Subject: [PATCH 0674/1334] MAINTAINERS: add stray rmap file to mm rmap section

page_vma_mapped_walk() is used to traverse page tables from a VMA, used by
rmap logic once the reverse mapping has been traversed to the VMA level.

It is also used by other users (migration, damon, etc.) but is primarily
used by the reverse mapping and is a key part of its logic, so it seems
appropriate to place it here.

Link: https://lkml.kernel.org/r/20250617165142.173716-1-lorenzo.stoakes@oracle.com
Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Acked-by: Liam R. Howlett <Liam.Howlett@oracle.com>
Acked-by: David Hildenbrand <david@redhat.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Rik van Riel <riel@surriel.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 MAINTAINERS | 1 +
 1 file changed, 1 insertion(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index cf9ea0425011..49fcc5d02df7 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -15893,6 +15893,7 @@ R:	Harry Yoo <harry.yoo@oracle.com>
 L:	linux-mm@kvack.org
 S:	Maintained
 F:	include/linux/rmap.h
+F:	mm/page_vma_mapped.c
 F:	mm/rmap.c
 
 MEMORY MANAGEMENT - SECRETMEM

From db5921ab8aa23142b277325192a7443601dc4534 Mon Sep 17 00:00:00 2001
From: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Date: Tue, 17 Jun 2025 17:13:59 +0100
Subject: [PATCH 0675/1334] MAINTAINERS: add memfd, shmem quota files to shmem
 section

These files seem best suited to shmem.

Link: https://lkml.kernel.org/r/20250617161359.166955-1-lorenzo.stoakes@oracle.com
Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Baolin Wang <baolin.wang@linux.alibaba.com>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 MAINTAINERS | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 49fcc5d02df7..0eec6e1d4694 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -15740,7 +15740,6 @@ F:	Documentation/admin-guide/mm/
 F:	Documentation/mm/
 F:	include/linux/gfp.h
 F:	include/linux/gfp_types.h
-F:	include/linux/memfd.h
 F:	include/linux/memory_hotplug.h
 F:	include/linux/memory-tiers.h
 F:	include/linux/mempolicy.h
@@ -25042,8 +25041,11 @@ M:	Hugh Dickins <hughd@google.com>
 R:	Baolin Wang <baolin.wang@linux.alibaba.com>
 L:	linux-mm@kvack.org
 S:	Maintained
+F:	include/linux/memfd.h
 F:	include/linux/shmem_fs.h
+F:	mm/memfd.c
 F:	mm/shmem.c
+F:	mm/shmem_quota.c
 
 TOMOYO SECURITY MODULE
 M:	Kentaro Takeda <takedakn@nttdata.co.jp>

From c742d127d2d831aa83ae2987a508bca2bf0c7736 Mon Sep 17 00:00:00 2001
From: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Date: Tue, 17 Jun 2025 15:41:30 +0100
Subject: [PATCH 0676/1334] MAINTAINERS: add additional mmap-related files to
 mmap section

msync and nommu are directly related to memory mapping, mincore is less so
but all are roughly speaking operating on virtual memory mappings from the
point of view of the user so this seems the most appropriate place for
them.

Link: https://lkml.kernel.org/r/20250617144130.147847-1-lorenzo.stoakes@oracle.com
Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Reviewed-by: Pedro Falcato <pfalcato@suse.de>
Acked-by: Liam R. Howlett <Liam.Howlett@oracle.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: David Hildenbrand <david@redhat.com>
Cc: Jann Horn <jannh@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 MAINTAINERS | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index 0eec6e1d4694..ca8a70f7b047 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -15985,11 +15985,14 @@ S:	Maintained
 W:	http://www.linux-mm.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
 F:	include/trace/events/mmap.h
+F:	mm/mincore.c
 F:	mm/mlock.c
 F:	mm/mmap.c
 F:	mm/mprotect.c
 F:	mm/mremap.c
 F:	mm/mseal.c
+F:	mm/msync.c
+F:	mm/nommu.c
 F:	mm/vma.c
 F:	mm/vma.h
 F:	mm/vma_exec.c

From 4540e41e753a7d69ecd3f5bad51fe620205c3a18 Mon Sep 17 00:00:00 2001
From: Qasim Ijaz <qasdev00@gmail.com>
Date: Sun, 15 Jun 2025 23:59:41 +0100
Subject: [PATCH 0677/1334] HID: appletb-kbd: fix "appletb_backlight" backlight
 device reference counting

During appletb_kbd_probe, probe attempts to get the backlight device
by name. When this happens backlight_device_get_by_name looks for a
device in the backlight class which has name "appletb_backlight" and
upon finding a match it increments the reference count for the device
and returns it to the caller. However this reference is never released
leading to a reference leak.

Fix this by decrementing the backlight device reference count on removal
via put_device and on probe failure.

Fixes: 93a0fc489481 ("HID: hid-appletb-kbd: add support for automatic brightness control while using the touchbar")
Cc: stable@vger.kernel.org
Signed-off-by: Qasim Ijaz <qasdev00@gmail.com>
Reviewed-by: Aditya Garg <gargaditya08@live.com>
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
 drivers/hid/hid-appletb-kbd.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/hid/hid-appletb-kbd.c b/drivers/hid/hid-appletb-kbd.c
index ef51b2c06872..e06567886e50 100644
--- a/drivers/hid/hid-appletb-kbd.c
+++ b/drivers/hid/hid-appletb-kbd.c
@@ -438,6 +438,8 @@ static int appletb_kbd_probe(struct hid_device *hdev, const struct hid_device_id
 	return 0;
 
 close_hw:
+	if (kbd->backlight_dev)
+		put_device(&kbd->backlight_dev->dev);
 	hid_hw_close(hdev);
 stop_hw:
 	hid_hw_stop(hdev);
@@ -453,6 +455,9 @@ static void appletb_kbd_remove(struct hid_device *hdev)
 	input_unregister_handler(&kbd->inp_handler);
 	timer_delete_sync(&kbd->inactivity_timer);
 
+	if (kbd->backlight_dev)
+		put_device(&kbd->backlight_dev->dev);
+
 	hid_hw_close(hdev);
 	hid_hw_stop(hdev);
 }

From a8905238c3bbe13db90065ed74682418f23830c3 Mon Sep 17 00:00:00 2001
From: Akira Inoue <niyarium@gmail.com>
Date: Thu, 12 Jun 2025 13:34:38 +0900
Subject: [PATCH 0678/1334] HID: lenovo: Add support for ThinkPad X1 Tablet
 Thin Keyboard Gen2

Add "Thinkpad X1 Tablet Gen 2 Keyboard" PID to hid-lenovo driver to fix trackpoint not working issue.

Signed-off-by: Akira Inoue <niyarium@gmail.com>
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
 drivers/hid/hid-ids.h        | 1 +
 drivers/hid/hid-lenovo.c     | 8 ++++++++
 drivers/hid/hid-multitouch.c | 8 +++++++-
 3 files changed, 16 insertions(+), 1 deletion(-)

diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h
index 2d3769405ec3..c6468568aea1 100644
--- a/drivers/hid/hid-ids.h
+++ b/drivers/hid/hid-ids.h
@@ -821,6 +821,7 @@
 #define USB_DEVICE_ID_LENOVO_TPPRODOCK	0x6067
 #define USB_DEVICE_ID_LENOVO_X1_COVER	0x6085
 #define USB_DEVICE_ID_LENOVO_X1_TAB	0x60a3
+#define USB_DEVICE_ID_LENOVO_X1_TAB2	0x60a4
 #define USB_DEVICE_ID_LENOVO_X1_TAB3	0x60b5
 #define USB_DEVICE_ID_LENOVO_X12_TAB	0x60fe
 #define USB_DEVICE_ID_LENOVO_X12_TAB2	0x61ae
diff --git a/drivers/hid/hid-lenovo.c b/drivers/hid/hid-lenovo.c
index a3c23a72316a..b3121fa7a72d 100644
--- a/drivers/hid/hid-lenovo.c
+++ b/drivers/hid/hid-lenovo.c
@@ -492,6 +492,7 @@ static int lenovo_input_mapping(struct hid_device *hdev,
 	case USB_DEVICE_ID_LENOVO_X12_TAB:
 	case USB_DEVICE_ID_LENOVO_X12_TAB2:
 	case USB_DEVICE_ID_LENOVO_X1_TAB:
+	case USB_DEVICE_ID_LENOVO_X1_TAB2:
 	case USB_DEVICE_ID_LENOVO_X1_TAB3:
 		return lenovo_input_mapping_x1_tab_kbd(hdev, hi, field, usage, bit, max);
 	default:
@@ -608,6 +609,7 @@ static ssize_t attr_fn_lock_store(struct device *dev,
 	case USB_DEVICE_ID_LENOVO_X12_TAB2:
 	case USB_DEVICE_ID_LENOVO_TP10UBKBD:
 	case USB_DEVICE_ID_LENOVO_X1_TAB:
+	case USB_DEVICE_ID_LENOVO_X1_TAB2:
 	case USB_DEVICE_ID_LENOVO_X1_TAB3:
 		ret = lenovo_led_set_tp10ubkbd(hdev, TP10UBKBD_FN_LOCK_LED, value);
 		if (ret)
@@ -864,6 +866,7 @@ static int lenovo_event(struct hid_device *hdev, struct hid_field *field,
 	case USB_DEVICE_ID_LENOVO_X12_TAB2:
 	case USB_DEVICE_ID_LENOVO_TP10UBKBD:
 	case USB_DEVICE_ID_LENOVO_X1_TAB:
+	case USB_DEVICE_ID_LENOVO_X1_TAB2:
 	case USB_DEVICE_ID_LENOVO_X1_TAB3:
 		return lenovo_event_tp10ubkbd(hdev, field, usage, value);
 	default:
@@ -1147,6 +1150,7 @@ static int lenovo_led_brightness_set(struct led_classdev *led_cdev,
 	case USB_DEVICE_ID_LENOVO_X12_TAB2:
 	case USB_DEVICE_ID_LENOVO_TP10UBKBD:
 	case USB_DEVICE_ID_LENOVO_X1_TAB:
+	case USB_DEVICE_ID_LENOVO_X1_TAB2:
 	case USB_DEVICE_ID_LENOVO_X1_TAB3:
 		ret = lenovo_led_set_tp10ubkbd(hdev, tp10ubkbd_led[led_nr], value);
 		break;
@@ -1387,6 +1391,7 @@ static int lenovo_probe(struct hid_device *hdev,
 	case USB_DEVICE_ID_LENOVO_X12_TAB2:
 	case USB_DEVICE_ID_LENOVO_TP10UBKBD:
 	case USB_DEVICE_ID_LENOVO_X1_TAB:
+	case USB_DEVICE_ID_LENOVO_X1_TAB2:
 	case USB_DEVICE_ID_LENOVO_X1_TAB3:
 		ret = lenovo_probe_tp10ubkbd(hdev);
 		break;
@@ -1476,6 +1481,7 @@ static void lenovo_remove(struct hid_device *hdev)
 	case USB_DEVICE_ID_LENOVO_X12_TAB2:
 	case USB_DEVICE_ID_LENOVO_TP10UBKBD:
 	case USB_DEVICE_ID_LENOVO_X1_TAB:
+	case USB_DEVICE_ID_LENOVO_X1_TAB2:
 	case USB_DEVICE_ID_LENOVO_X1_TAB3:
 		lenovo_remove_tp10ubkbd(hdev);
 		break;
@@ -1526,6 +1532,8 @@ static const struct hid_device_id lenovo_devices[] = {
 	 */
 	{ HID_DEVICE(BUS_USB, HID_GROUP_GENERIC,
 		     USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_X1_TAB) },
+	{ HID_DEVICE(BUS_USB, HID_GROUP_GENERIC,
+		     USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_X1_TAB2) },
 	{ HID_DEVICE(BUS_USB, HID_GROUP_GENERIC,
 		     USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_X1_TAB3) },
 	{ HID_DEVICE(BUS_USB, HID_GROUP_GENERIC,
diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c
index ded0fef7d8c7..24aa6e7e6fdd 100644
--- a/drivers/hid/hid-multitouch.c
+++ b/drivers/hid/hid-multitouch.c
@@ -2132,12 +2132,18 @@ static const struct hid_device_id mt_devices[] = {
 		HID_DEVICE(BUS_I2C, HID_GROUP_GENERIC,
 			USB_VENDOR_ID_LG, I2C_DEVICE_ID_LG_7010) },
 
-	/* Lenovo X1 TAB Gen 2 */
+	/* Lenovo X1 TAB Gen 1 */
 	{ .driver_data = MT_CLS_WIN_8_FORCE_MULTI_INPUT,
 		HID_DEVICE(BUS_USB, HID_GROUP_MULTITOUCH_WIN_8,
 			   USB_VENDOR_ID_LENOVO,
 			   USB_DEVICE_ID_LENOVO_X1_TAB) },
 
+	/* Lenovo X1 TAB Gen 2 */
+	{ .driver_data = MT_CLS_WIN_8_FORCE_MULTI_INPUT,
+		HID_DEVICE(BUS_USB, HID_GROUP_MULTITOUCH_WIN_8,
+			   USB_VENDOR_ID_LENOVO,
+			   USB_DEVICE_ID_LENOVO_X1_TAB2) },
+
 	/* Lenovo X1 TAB Gen 3 */
 	{ .driver_data = MT_CLS_WIN_8_FORCE_MULTI_INPUT,
 		HID_DEVICE(BUS_USB, HID_GROUP_MULTITOUCH_WIN_8,

From 33bdee12822d240caaa01aeac231eac42182fd64 Mon Sep 17 00:00:00 2001
From: Edson Juliano Drosdeck <edson.drosdeck@gmail.com>
Date: Thu, 19 Jun 2025 16:12:15 -0300
Subject: [PATCH 0679/1334] ALSA: hda/realtek: Enable headset Mic on Positivo
 P15X

Positivo P15X is equipped with ALC269VC, and needs a fix to make
the headset mic to work.
Also must to limits the internal microphone boost.

Signed-off-by: Edson Juliano Drosdeck <edson.drosdeck@gmail.com>
Link: https://patch.msgid.link/20250619191215.17203-1-edson.drosdeck@gmail.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/patch_realtek.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 76cc908d4957..2e1618494c20 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -8032,6 +8032,7 @@ enum {
 	ALC287_FIXUP_PREDATOR_SPK_CS35L41_I2C_2,
 	ALC285_FIXUP_ASUS_GA605K_HEADSET_MIC,
 	ALC285_FIXUP_ASUS_GA605K_I2C_SPEAKER2_TO_DAC1,
+	ALC269_FIXUP_POSITIVO_P15X_HEADSET_MIC,
 };
 
 /* A special fixup for Lenovo C940 and Yoga Duet 7;
@@ -10430,6 +10431,12 @@ static const struct hda_fixup alc269_fixups[] = {
 		.type = HDA_FIXUP_FUNC,
 		.v.func = alc285_fixup_speaker2_to_dac1,
 	},
+	[ALC269_FIXUP_POSITIVO_P15X_HEADSET_MIC] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc269_fixup_limit_int_mic_boost,
+		.chained = true,
+		.chain_id = ALC269VC_FIXUP_ACER_MIC_NO_PRESENCE,
+	},
 };
 
 static const struct hda_quirk alc269_fixup_tbl[] = {
@@ -11406,6 +11413,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x2782, 0x0214, "VAIO VJFE-CL", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
 	SND_PCI_QUIRK(0x2782, 0x0228, "Infinix ZERO BOOK 13", ALC269VB_FIXUP_INFINIX_ZERO_BOOK_13),
 	SND_PCI_QUIRK(0x2782, 0x0232, "CHUWI CoreBook XPro", ALC269VB_FIXUP_CHUWI_COREBOOK_XPRO),
+	SND_PCI_QUIRK(0x2782, 0x1407, "Positivo P15X", ALC269_FIXUP_POSITIVO_P15X_HEADSET_MIC),
 	SND_PCI_QUIRK(0x2782, 0x1701, "Infinix Y4 Max", ALC269VC_FIXUP_INFINIX_Y4_MAX),
 	SND_PCI_QUIRK(0x2782, 0x1705, "MEDION E15433", ALC269VC_FIXUP_INFINIX_Y4_MAX),
 	SND_PCI_QUIRK(0x2782, 0x1707, "Vaio VJFE-ADL", ALC298_FIXUP_SPK_VOLUME),

From f8b53cc9174c5980549f60c972faad82b660b62d Mon Sep 17 00:00:00 2001
From: Vitaly Kuznetsov <vkuznets@redhat.com>
Date: Fri, 20 Jun 2025 13:16:07 +0200
Subject: [PATCH 0680/1334] efi: Fix .data section size calculations when .sbat
 is present

Commit 0f9a1739dd0e ("efi: zboot specific mechanism for embedding SBAT
section") neglected to adjust the sizes of the .data section when
CONFIG_EFI_SBAT_FILE is set. As the result, the produced PE binary is
incorrect and some tools complain about it. E.g. 'sbsign' reports:

 # sbsign --key my.key --cert my.crt arch/arm64/boot/vmlinuz.efi
 warning: file-aligned section .data extends beyond end of file
 warning: checksum areas are greater than image size. Invalid section table?

Note, '__data_size' is also used in the PE optional header and it is not
entirely clear whether .sbat needs to be accounted as part of
SizeOfInitializedData or not. As the header seems to be unused by the real
world firmware, keeping the field equal to __data_size.

Fixes: 0f9a1739dd0e ("efi: zboot specific mechanism for embedding SBAT section")
Reported-by: Heinrich Schuchardt <heinrich.schuchardt@gmx.de>
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
 drivers/firmware/efi/libstub/zboot.lds | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/firmware/efi/libstub/zboot.lds b/drivers/firmware/efi/libstub/zboot.lds
index 4b8d5cd3dfa2..367907eb7d86 100644
--- a/drivers/firmware/efi/libstub/zboot.lds
+++ b/drivers/firmware/efi/libstub/zboot.lds
@@ -58,6 +58,6 @@ SECTIONS
 PROVIDE(__efistub__gzdata_size =
 		ABSOLUTE(__efistub__gzdata_end - __efistub__gzdata_start));
 
-PROVIDE(__data_rawsize = ABSOLUTE(_edata - _etext));
-PROVIDE(__data_size = ABSOLUTE(_end - _etext));
+PROVIDE(__data_rawsize = ABSOLUTE(_edata - _data));
+PROVIDE(__data_size = ABSOLUTE(_end - _data));
 PROVIDE(__sbat_size = ABSOLUTE(_esbat - _sbat));

From 51a4598ad5d9eb6be4ec9ba65bbfdf0ac302eb2e Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Fri, 20 Jun 2025 07:41:21 -0600
Subject: [PATCH 0681/1334] io_uring/net: always use current transfer count for
 buffer put

A previous fix corrected the retry condition for when to continue a
current bundle, but it missed that the current (not the total) transfer
count also applies to the buffer put. If not, then for incrementally
consumed buffer rings repeated completions on the same request may end
up over consuming.

Reported-by: Roy Tang (ErgoniaTrading) <royonia@ergonia.io>
Cc: stable@vger.kernel.org
Fixes: 3a08988123c8 ("io_uring/net: only retry recv bundle for a full transfer")
Link: https://github.com/axboe/liburing/issues/1423
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/net.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/io_uring/net.c b/io_uring/net.c
index e16633fd6630..9550d4c8f866 100644
--- a/io_uring/net.c
+++ b/io_uring/net.c
@@ -821,7 +821,7 @@ static inline bool io_recv_finish(struct io_kiocb *req, int *ret,
 	if (sr->flags & IORING_RECVSEND_BUNDLE) {
 		size_t this_ret = *ret - sr->done_io;
 
-		cflags |= io_put_kbufs(req, *ret, io_bundle_nbufs(kmsg, this_ret),
+		cflags |= io_put_kbufs(req, this_ret, io_bundle_nbufs(kmsg, this_ret),
 				      issue_flags);
 		if (sr->retry)
 			cflags = req->cqe.flags | (cflags & CQE_F_MASK);

From 417b8af2e30d7f131682a893ad79c506fd39c624 Mon Sep 17 00:00:00 2001
From: Gao Xiang <hsiangkao@linux.alibaba.com>
Date: Fri, 20 Jun 2025 23:31:08 +0800
Subject: [PATCH 0682/1334] erofs: remove a superfluous check for encoded
 extents

It is possible when an inode is split into segments for multi-threaded
compression, and the tail extent of a segment could also be small.

Fixes: 1d191b4ca51d ("erofs: implement encoded extent metadata")
Signed-off-by: Gao Xiang <hsiangkao@linux.alibaba.com>
Link: https://lore.kernel.org/r/20250620153108.1368029-1-hsiangkao@linux.alibaba.com
---
 fs/erofs/zmap.c | 6 ------
 1 file changed, 6 deletions(-)

diff --git a/fs/erofs/zmap.c b/fs/erofs/zmap.c
index 6afcb054780d..0bebc6e3a4d7 100644
--- a/fs/erofs/zmap.c
+++ b/fs/erofs/zmap.c
@@ -639,12 +639,6 @@ static int z_erofs_map_blocks_ext(struct inode *inode,
 		}
 	}
 	map->m_llen = lend - map->m_la;
-	if (!last && map->m_llen < sb->s_blocksize) {
-		erofs_err(sb, "extent too small %llu @ offset %llu of nid %llu",
-			  map->m_llen, map->m_la, vi->nid);
-		DBG_BUGON(1);
-		return -EFSCORRUPTED;
-	}
 	return 0;
 }
 

From 89a33de314945c866b155d369f224fa552af1722 Mon Sep 17 00:00:00 2001
From: Kiran K <kiran.k@intel.com>
Date: Tue, 10 Jun 2025 19:30:37 +0530
Subject: [PATCH 0683/1334] Bluetooth: btintel_pcie: Fix potential race
 condition in firmware download

During firmware download, if an error occurs, interrupts must be
disabled, synchronized, and re-enabled before retrying the download.
This change ensures proper interrupt handling to prevent race
conditions.

Signed-off-by: Chandrashekar Devegowda <chandrashekar.devegowda@intel.com>
Signed-off-by: Kiran K <kiran.k@intel.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/btintel_pcie.c | 33 ++++++++++++++++++++++++++++++--
 1 file changed, 31 insertions(+), 2 deletions(-)

diff --git a/drivers/bluetooth/btintel_pcie.c b/drivers/bluetooth/btintel_pcie.c
index 563165c5efae..e1c688dd2d45 100644
--- a/drivers/bluetooth/btintel_pcie.c
+++ b/drivers/bluetooth/btintel_pcie.c
@@ -2033,6 +2033,28 @@ static void btintel_pcie_release_hdev(struct btintel_pcie_data *data)
 	data->hdev = NULL;
 }
 
+static void btintel_pcie_disable_interrupts(struct btintel_pcie_data *data)
+{
+	spin_lock(&data->irq_lock);
+	btintel_pcie_wr_reg32(data, BTINTEL_PCIE_CSR_MSIX_FH_INT_MASK, data->fh_init_mask);
+	btintel_pcie_wr_reg32(data, BTINTEL_PCIE_CSR_MSIX_HW_INT_MASK, data->hw_init_mask);
+	spin_unlock(&data->irq_lock);
+}
+
+static void btintel_pcie_enable_interrupts(struct btintel_pcie_data *data)
+{
+	spin_lock(&data->irq_lock);
+	btintel_pcie_wr_reg32(data, BTINTEL_PCIE_CSR_MSIX_FH_INT_MASK, ~data->fh_init_mask);
+	btintel_pcie_wr_reg32(data, BTINTEL_PCIE_CSR_MSIX_HW_INT_MASK, ~data->hw_init_mask);
+	spin_unlock(&data->irq_lock);
+}
+
+static void btintel_pcie_synchronize_irqs(struct btintel_pcie_data *data)
+{
+	for (int i = 0; i < data->alloc_vecs; i++)
+		synchronize_irq(data->msix_entries[i].vector);
+}
+
 static int btintel_pcie_setup_internal(struct hci_dev *hdev)
 {
 	struct btintel_pcie_data *data = hci_get_drvdata(hdev);
@@ -2152,6 +2174,8 @@ static int btintel_pcie_setup(struct hci_dev *hdev)
 		bt_dev_err(hdev, "Firmware download retry count: %d",
 			   fw_dl_retry);
 		btintel_pcie_dump_debug_registers(hdev);
+		btintel_pcie_disable_interrupts(data);
+		btintel_pcie_synchronize_irqs(data);
 		err = btintel_pcie_reset_bt(data);
 		if (err) {
 			bt_dev_err(hdev, "Failed to do shr reset: %d", err);
@@ -2159,6 +2183,7 @@ static int btintel_pcie_setup(struct hci_dev *hdev)
 		}
 		usleep_range(10000, 12000);
 		btintel_pcie_reset_ia(data);
+		btintel_pcie_enable_interrupts(data);
 		btintel_pcie_config_msix(data);
 		err = btintel_pcie_enable_bt(data);
 		if (err) {
@@ -2291,6 +2316,12 @@ static void btintel_pcie_remove(struct pci_dev *pdev)
 
 	data = pci_get_drvdata(pdev);
 
+	btintel_pcie_disable_interrupts(data);
+
+	btintel_pcie_synchronize_irqs(data);
+
+	flush_work(&data->rx_work);
+
 	btintel_pcie_reset_bt(data);
 	for (int i = 0; i < data->alloc_vecs; i++) {
 		struct msix_entry *msix_entry;
@@ -2303,8 +2334,6 @@ static void btintel_pcie_remove(struct pci_dev *pdev)
 
 	btintel_pcie_release_hdev(data);
 
-	flush_work(&data->rx_work);
-
 	destroy_workqueue(data->workqueue);
 
 	btintel_pcie_free(data);

From 042bb9603c44620dce98717a2d23235ca57a00d7 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Fr=C3=A9d=C3=A9ric=20Danis?= <frederic.danis@collabora.com>
Date: Thu, 12 Jun 2025 09:50:34 +0200
Subject: [PATCH 0684/1334] Bluetooth: L2CAP: Fix L2CAP MTU negotiation
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

OBEX download from iPhone is currently slow due to small packet size
used to transfer data which doesn't follow the MTU negotiated during
L2CAP connection, i.e. 672 bytes instead of 32767:

  < ACL Data TX: Handle 11 flags 0x00 dlen 12
      L2CAP: Connection Request (0x02) ident 18 len 4
        PSM: 4103 (0x1007)
        Source CID: 72
  > ACL Data RX: Handle 11 flags 0x02 dlen 16
      L2CAP: Connection Response (0x03) ident 18 len 8
        Destination CID: 14608
        Source CID: 72
        Result: Connection successful (0x0000)
        Status: No further information available (0x0000)
  < ACL Data TX: Handle 11 flags 0x00 dlen 27
      L2CAP: Configure Request (0x04) ident 20 len 19
        Destination CID: 14608
        Flags: 0x0000
        Option: Maximum Transmission Unit (0x01) [mandatory]
          MTU: 32767
        Option: Retransmission and Flow Control (0x04) [mandatory]
          Mode: Enhanced Retransmission (0x03)
          TX window size: 63
          Max transmit: 3
          Retransmission timeout: 2000
          Monitor timeout: 12000
          Maximum PDU size: 1009
  > ACL Data RX: Handle 11 flags 0x02 dlen 26
      L2CAP: Configure Request (0x04) ident 72 len 18
        Destination CID: 72
        Flags: 0x0000
        Option: Retransmission and Flow Control (0x04) [mandatory]
          Mode: Enhanced Retransmission (0x03)
          TX window size: 32
          Max transmit: 255
          Retransmission timeout: 0
          Monitor timeout: 0
          Maximum PDU size: 65527
        Option: Frame Check Sequence (0x05) [mandatory]
          FCS: 16-bit FCS (0x01)
  < ACL Data TX: Handle 11 flags 0x00 dlen 29
      L2CAP: Configure Response (0x05) ident 72 len 21
        Source CID: 14608
        Flags: 0x0000
        Result: Success (0x0000)
        Option: Maximum Transmission Unit (0x01) [mandatory]
          MTU: 672
        Option: Retransmission and Flow Control (0x04) [mandatory]
          Mode: Enhanced Retransmission (0x03)
          TX window size: 32
          Max transmit: 255
          Retransmission timeout: 2000
          Monitor timeout: 12000
          Maximum PDU size: 1009
  > ACL Data RX: Handle 11 flags 0x02 dlen 32
      L2CAP: Configure Response (0x05) ident 20 len 24
        Source CID: 72
        Flags: 0x0000
        Result: Success (0x0000)
        Option: Maximum Transmission Unit (0x01) [mandatory]
          MTU: 32767
        Option: Retransmission and Flow Control (0x04) [mandatory]
          Mode: Enhanced Retransmission (0x03)
          TX window size: 63
          Max transmit: 3
          Retransmission timeout: 2000
          Monitor timeout: 12000
          Maximum PDU size: 1009
        Option: Frame Check Sequence (0x05) [mandatory]
          FCS: 16-bit FCS (0x01)
  ...
  > ACL Data RX: Handle 11 flags 0x02 dlen 680
      Channel: 72 len 676 ctrl 0x0202 [PSM 4103 mode Enhanced Retransmission (0x03)] {chan 8}
      I-frame: Unsegmented TxSeq 1 ReqSeq 2
  < ACL Data TX: Handle 11 flags 0x00 dlen 13
      Channel: 14608 len 9 ctrl 0x0204 [PSM 4103 mode Enhanced Retransmission (0x03)] {chan 8}
      I-frame: Unsegmented TxSeq 2 ReqSeq 2
  > ACL Data RX: Handle 11 flags 0x02 dlen 680
      Channel: 72 len 676 ctrl 0x0304 [PSM 4103 mode Enhanced Retransmission (0x03)] {chan 8}
      I-frame: Unsegmented TxSeq 2 ReqSeq 3

The MTUs are negotiated for each direction. In this traces 32767 for
iPhone->localhost and no MTU for localhost->iPhone, which based on
'4.4 L2CAP_CONFIGURATION_REQ' (Core specification v5.4, Vol. 3, Part
A):

  The only parameters that should be included in the
  L2CAP_CONFIGURATION_REQ packet are those that require different
  values than the default or previously agreed values.
  ...
  Any missing configuration parameters are assumed to have their
  most recently explicitly or implicitly accepted values.

and '5.1 Maximum transmission unit (MTU)':

  If the remote device sends a positive L2CAP_CONFIGURATION_RSP
  packet it should include the actual MTU to be used on this channel
  for traffic flowing into the local device.
  ...
  The default value is 672 octets.

is set by BlueZ to 672 bytes.

It seems that the iPhone used the lowest negotiated value to transfer
data to the localhost instead of the negotiated one for the incoming
direction.

This could be fixed by using the MTU negotiated for the other
direction, if exists, in the L2CAP_CONFIGURATION_RSP.
This allows to use segmented packets as in the following traces:

  < ACL Data TX: Handle 11 flags 0x00 dlen 12
        L2CAP: Connection Request (0x02) ident 22 len 4
          PSM: 4103 (0x1007)
          Source CID: 72
  < ACL Data TX: Handle 11 flags 0x00 dlen 27
        L2CAP: Configure Request (0x04) ident 24 len 19
          Destination CID: 2832
          Flags: 0x0000
          Option: Maximum Transmission Unit (0x01) [mandatory]
            MTU: 32767
          Option: Retransmission and Flow Control (0x04) [mandatory]
            Mode: Enhanced Retransmission (0x03)
            TX window size: 63
            Max transmit: 3
            Retransmission timeout: 2000
            Monitor timeout: 12000
            Maximum PDU size: 1009
  > ACL Data RX: Handle 11 flags 0x02 dlen 26
        L2CAP: Configure Request (0x04) ident 15 len 18
          Destination CID: 72
          Flags: 0x0000
          Option: Retransmission and Flow Control (0x04) [mandatory]
            Mode: Enhanced Retransmission (0x03)
            TX window size: 32
            Max transmit: 255
            Retransmission timeout: 0
            Monitor timeout: 0
            Maximum PDU size: 65527
          Option: Frame Check Sequence (0x05) [mandatory]
            FCS: 16-bit FCS (0x01)
  < ACL Data TX: Handle 11 flags 0x00 dlen 29
        L2CAP: Configure Response (0x05) ident 15 len 21
          Source CID: 2832
          Flags: 0x0000
          Result: Success (0x0000)
          Option: Maximum Transmission Unit (0x01) [mandatory]
            MTU: 32767
          Option: Retransmission and Flow Control (0x04) [mandatory]
            Mode: Enhanced Retransmission (0x03)
            TX window size: 32
            Max transmit: 255
            Retransmission timeout: 2000
            Monitor timeout: 12000
            Maximum PDU size: 1009
  > ACL Data RX: Handle 11 flags 0x02 dlen 32
        L2CAP: Configure Response (0x05) ident 24 len 24
          Source CID: 72
          Flags: 0x0000
          Result: Success (0x0000)
          Option: Maximum Transmission Unit (0x01) [mandatory]
            MTU: 32767
          Option: Retransmission and Flow Control (0x04) [mandatory]
            Mode: Enhanced Retransmission (0x03)
            TX window size: 63
            Max transmit: 3
            Retransmission timeout: 2000
            Monitor timeout: 12000
            Maximum PDU size: 1009
          Option: Frame Check Sequence (0x05) [mandatory]
            FCS: 16-bit FCS (0x01)
  ...
  > ACL Data RX: Handle 11 flags 0x02 dlen 1009
        Channel: 72 len 1005 ctrl 0x4202 [PSM 4103 mode Enhanced Retransmission (0x03)] {chan 8}
        I-frame: Start (len 21884) TxSeq 1 ReqSeq 2
  > ACL Data RX: Handle 11 flags 0x02 dlen 1009
        Channel: 72 len 1005 ctrl 0xc204 [PSM 4103 mode Enhanced Retransmission (0x03)] {chan 8}
        I-frame: Continuation TxSeq 2 ReqSeq 2

This has been tested with kernel 5.4 and BlueZ 5.77.

Cc: stable@vger.kernel.org
Signed-off-by: Frédéric Danis <frederic.danis@collabora.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/l2cap_core.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index a5bde5db58ef..40daa38276f3 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -3415,7 +3415,7 @@ static int l2cap_parse_conf_req(struct l2cap_chan *chan, void *data, size_t data
 	struct l2cap_conf_rfc rfc = { .mode = L2CAP_MODE_BASIC };
 	struct l2cap_conf_efs efs;
 	u8 remote_efs = 0;
-	u16 mtu = L2CAP_DEFAULT_MTU;
+	u16 mtu = 0;
 	u16 result = L2CAP_CONF_SUCCESS;
 	u16 size;
 
@@ -3520,6 +3520,13 @@ done:
 		/* Configure output options and let the other side know
 		 * which ones we don't like. */
 
+		/* If MTU is not provided in configure request, use the most recently
+		 * explicitly or implicitly accepted value for the other direction,
+		 * or the default value.
+		 */
+		if (mtu == 0)
+			mtu = chan->imtu ? chan->imtu : L2CAP_DEFAULT_MTU;
+
 		if (mtu < L2CAP_DEFAULT_MIN_MTU)
 			result = L2CAP_CONF_UNACCEPT;
 		else {

From db0ff7e15923ffa7067874604ca275e92343f1b1 Mon Sep 17 00:00:00 2001
From: Shuai Zhang <quic_shuaz@quicinc.com>
Date: Mon, 9 Jun 2025 18:55:00 +0800
Subject: [PATCH 0685/1334] driver: bluetooth: hci_qca:fix unable to load the
 BT driver

Some modules have BT_EN enabled via a hardware pull-up,
meaning it is not defined in the DTS and is not controlled
through the power sequence. In such cases, fall through
to follow the legacy flow.

Signed-off-by: Shuai Zhang <quic_shuaz@quicinc.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/hci_qca.c | 13 ++++++++++---
 1 file changed, 10 insertions(+), 3 deletions(-)

diff --git a/drivers/bluetooth/hci_qca.c b/drivers/bluetooth/hci_qca.c
index 5fe5879881f5..3ec0be496820 100644
--- a/drivers/bluetooth/hci_qca.c
+++ b/drivers/bluetooth/hci_qca.c
@@ -2392,10 +2392,17 @@ static int qca_serdev_probe(struct serdev_device *serdev)
 			 */
 			qcadev->bt_power->pwrseq = devm_pwrseq_get(&serdev->dev,
 								   "bluetooth");
-			if (IS_ERR(qcadev->bt_power->pwrseq))
-				return PTR_ERR(qcadev->bt_power->pwrseq);
 
-			break;
+			/*
+			 * Some modules have BT_EN enabled via a hardware pull-up,
+			 * meaning it is not defined in the DTS and is not controlled
+			 * through the power sequence. In such cases, fall through
+			 * to follow the legacy flow.
+			 */
+			if (IS_ERR(qcadev->bt_power->pwrseq))
+				qcadev->bt_power->pwrseq = NULL;
+			else
+				break;
 		}
 		fallthrough;
 	case QCA_WCN3950:

From 850f0e2433cdd38f36d80a4c1ab59f82029bef74 Mon Sep 17 00:00:00 2001
From: Drew Fustini <fustini@kernel.org>
Date: Wed, 18 Jun 2025 20:54:57 -0700
Subject: [PATCH 0686/1334] MAINTAINERS: Update Drew Fustini's email address

Switch from personal domain to kernel.org address.

Signed-off-by: Drew Fustini <fustini@kernel.org>
Link: https://lore.kernel.org/r/20250619035457.331065-1-fustini@kernel.org
Signed-off-by: Palmer Dabbelt <palmer@dabbelt.com>
---
 .mailmap    | 1 +
 MAINTAINERS | 2 +-
 2 files changed, 2 insertions(+), 1 deletion(-)

diff --git a/.mailmap b/.mailmap
index c8a21d72241f..1ce0dd52dfaf 100644
--- a/.mailmap
+++ b/.mailmap
@@ -222,6 +222,7 @@ Dmitry Safonov <0x7f454c46@gmail.com> <d.safonov@partner.samsung.com>
 Dmitry Safonov <0x7f454c46@gmail.com> <dsafonov@virtuozzo.com>
 Domen Puncer <domen@coderock.org>
 Douglas Gilbert <dougg@torque.net>
+Drew Fustini <fustini@kernel.org> <drew@pdp7.com>
 Ed L. Cashin <ecashin@coraid.com>
 Elliot Berman <quic_eberman@quicinc.com> <eberman@codeaurora.org>
 Enric Balletbo i Serra <eballetbo@kernel.org> <enric.balletbo@collabora.com>
diff --git a/MAINTAINERS b/MAINTAINERS
index a92290fffa16..dcb1142d10b6 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -21374,7 +21374,7 @@ N:	spacemit
 K:	spacemit
 
 RISC-V THEAD SoC SUPPORT
-M:	Drew Fustini <drew@pdp7.com>
+M:	Drew Fustini <fustini@kernel.org>
 M:	Guo Ren <guoren@kernel.org>
 M:	Fu Wei <wefu@redhat.com>
 L:	linux-riscv@lists.infradead.org

From b5aafcb4efd2bdacbc37753cf807d69faa6a7304 Mon Sep 17 00:00:00 2001
From: Binbin Wu <binbin.wu@linux.intel.com>
Date: Tue, 10 Jun 2025 10:14:19 +0800
Subject: [PATCH 0687/1334] KVM: TDX: Add new TDVMCALL status code for
 unsupported subfuncs

Add the new TDVMCALL status code TDVMCALL_STATUS_SUBFUNC_UNSUPPORTED and
return it for unimplemented TDVMCALL subfunctions.

Returning TDVMCALL_STATUS_INVALID_OPERAND when a subfunction is not
implemented is vague because TDX guests can't tell the error is due to
the subfunction is not supported or an invalid input of the subfunction.
New GHCI spec adds TDVMCALL_STATUS_SUBFUNC_UNSUPPORTED to avoid the
ambiguity. Use it instead of TDVMCALL_STATUS_INVALID_OPERAND.

Before the change, for common guest implementations, when a TDX guest
receives TDVMCALL_STATUS_INVALID_OPERAND, it has two cases:
1. Some operand is invalid. It could change the operand to another value
   retry.
2. The subfunction is not supported.

For case 1, an invalid operand usually means the guest implementation bug.
Since the TDX guest can't tell which case is, the best practice for
handling TDVMCALL_STATUS_INVALID_OPERAND is stopping calling such leaf,
treating the failure as fatal if the TDVMCALL is essential or ignoring
it if the TDVMCALL is optional.

With this change, TDVMCALL_STATUS_SUBFUNC_UNSUPPORTED could be sent to
old TDX guest that do not know about it, but it is expected that the
guest will make the same action as TDVMCALL_STATUS_INVALID_OPERAND.
Currently, no known TDX guest checks TDVMCALL_STATUS_INVALID_OPERAND
specifically; for example Linux just checks for success.

Signed-off-by: Binbin Wu <binbin.wu@linux.intel.com>
[Return it for untrapped KVM_HC_MAP_GPA_RANGE. - Paolo]
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/include/asm/shared/tdx.h |  1 +
 arch/x86/kvm/vmx/tdx.c            | 10 ++++++----
 2 files changed, 7 insertions(+), 4 deletions(-)

diff --git a/arch/x86/include/asm/shared/tdx.h b/arch/x86/include/asm/shared/tdx.h
index 2f3820342598..d8525e6ef50a 100644
--- a/arch/x86/include/asm/shared/tdx.h
+++ b/arch/x86/include/asm/shared/tdx.h
@@ -80,6 +80,7 @@
 #define TDVMCALL_STATUS_RETRY		0x0000000000000001ULL
 #define TDVMCALL_STATUS_INVALID_OPERAND	0x8000000000000000ULL
 #define TDVMCALL_STATUS_ALIGN_ERROR	0x8000000000000002ULL
+#define TDVMCALL_STATUS_SUBFUNC_UNSUPPORTED	0x8000000000000003ULL
 
 /*
  * Bitmasks of exposed registers (with VMM).
diff --git a/arch/x86/kvm/vmx/tdx.c b/arch/x86/kvm/vmx/tdx.c
index b952bc673271..5d100c240ab3 100644
--- a/arch/x86/kvm/vmx/tdx.c
+++ b/arch/x86/kvm/vmx/tdx.c
@@ -1212,11 +1212,13 @@ static int tdx_map_gpa(struct kvm_vcpu *vcpu)
 	/*
 	 * Converting TDVMCALL_MAP_GPA to KVM_HC_MAP_GPA_RANGE requires
 	 * userspace to enable KVM_CAP_EXIT_HYPERCALL with KVM_HC_MAP_GPA_RANGE
-	 * bit set.  If not, the error code is not defined in GHCI for TDX, use
-	 * TDVMCALL_STATUS_INVALID_OPERAND for this case.
+	 * bit set.  This is a base call so it should always be supported, but
+	 * KVM has no way to ensure that userspace implements the GHCI correctly.
+	 * So if KVM_HC_MAP_GPA_RANGE does not cause a VMEXIT, return an error
+	 * to the guest.
 	 */
 	if (!user_exit_on_hypercall(vcpu->kvm, KVM_HC_MAP_GPA_RANGE)) {
-		ret = TDVMCALL_STATUS_INVALID_OPERAND;
+		ret = TDVMCALL_STATUS_SUBFUNC_UNSUPPORTED;
 		goto error;
 	}
 
@@ -1476,7 +1478,7 @@ static int handle_tdvmcall(struct kvm_vcpu *vcpu)
 		break;
 	}
 
-	tdvmcall_set_return_code(vcpu, TDVMCALL_STATUS_INVALID_OPERAND);
+	tdvmcall_set_return_code(vcpu, TDVMCALL_STATUS_SUBFUNC_UNSUPPORTED);
 	return 1;
 }
 

From cf207eac06f661fb692f405d5ab8230df884ee52 Mon Sep 17 00:00:00 2001
From: Binbin Wu <binbin.wu@linux.intel.com>
Date: Tue, 10 Jun 2025 10:14:20 +0800
Subject: [PATCH 0688/1334] KVM: TDX: Handle TDG.VP.VMCALL<GetQuote>

Handle TDVMCALL for GetQuote to generate a TD-Quote.

GetQuote is a doorbell-like interface used by TDX guests to request VMM
to generate a TD-Quote signed by a service hosting TD-Quoting Enclave
operating on the host.  A TDX guest passes a TD Report (TDREPORT_STRUCT) in
a shared-memory area as parameter.  Host VMM can access it and queue the
operation for a service hosting TD-Quoting enclave.  When completed, the
Quote is returned via the same shared-memory area.

KVM only checks the GPA from the TDX guest has the shared-bit set and drops
the shared-bit before exiting to userspace to avoid bleeding the shared-bit
into KVM's exit ABI.  KVM forwards the request to userspace VMM (e.g. QEMU)
and userspace VMM queues the operation asynchronously.  KVM sets the return
code according to the 'ret' field set by userspace to notify the TDX guest
whether the request has been queued successfully or not.  When the request
has been queued successfully, the TDX guest can poll the status field in
the shared-memory area to check whether the Quote generation is completed
or not.  When completed, the generated Quote is returned via the same
buffer.

Add KVM_EXIT_TDX as a new exit reason to userspace. Userspace is
required to handle the KVM exit reason as the initial support for TDX,
by reentering KVM to ensure that the TDVMCALL is complete.  While at it,
add a note that KVM_EXIT_HYPERCALL also requires reentry with KVM_RUN.

Signed-off-by: Binbin Wu <binbin.wu@linux.intel.com>
Tested-by: Mikko Ylinen <mikko.ylinen@linux.intel.com>
Acked-by: Kai Huang <kai.huang@intel.com>
[Adjust userspace API. - Paolo]
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 Documentation/virt/kvm/api.rst | 49 +++++++++++++++++++++++++++++++++-
 arch/x86/kvm/vmx/tdx.c         | 32 ++++++++++++++++++++++
 include/uapi/linux/kvm.h       | 17 ++++++++++++
 3 files changed, 97 insertions(+), 1 deletion(-)

diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index 1bd2d42e6424..115ec3c2b641 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -6645,7 +6645,8 @@ to the byte array.
 .. note::
 
       For KVM_EXIT_IO, KVM_EXIT_MMIO, KVM_EXIT_OSI, KVM_EXIT_PAPR, KVM_EXIT_XEN,
-      KVM_EXIT_EPR, KVM_EXIT_X86_RDMSR and KVM_EXIT_X86_WRMSR the corresponding
+      KVM_EXIT_EPR, KVM_EXIT_HYPERCALL, KVM_EXIT_TDX,
+      KVM_EXIT_X86_RDMSR and KVM_EXIT_X86_WRMSR the corresponding
       operations are complete (and guest state is consistent) only after userspace
       has re-entered the kernel with KVM_RUN.  The kernel side will first finish
       incomplete operations and then check for pending signals.
@@ -7174,6 +7175,52 @@ The valid value for 'flags' is:
   - KVM_NOTIFY_CONTEXT_INVALID -- the VM context is corrupted and not valid
     in VMCS. It would run into unknown result if resume the target VM.
 
+::
+
+		/* KVM_EXIT_TDX */
+		struct {
+			__u64 flags;
+			__u64 nr;
+			union {
+				struct {
+					u64 ret;
+					u64 data[5];
+				} unknown;
+				struct {
+					u64 ret;
+					u64 gpa;
+					u64 size;
+				} get_quote;
+			};
+		} tdx;
+
+Process a TDVMCALL from the guest.  KVM forwards select TDVMCALL based
+on the Guest-Hypervisor Communication Interface (GHCI) specification;
+KVM bridges these requests to the userspace VMM with minimal changes,
+placing the inputs in the union and copying them back to the guest
+on re-entry.
+
+Flags are currently always zero, whereas ``nr`` contains the TDVMCALL
+number from register R11.  The remaining field of the union provide the
+inputs and outputs of the TDVMCALL.  Currently the following values of
+``nr`` are defined:
+
+* ``TDVMCALL_GET_QUOTE``: the guest has requested to generate a TD-Quote
+signed by a service hosting TD-Quoting Enclave operating on the host.
+Parameters and return value are in the ``get_quote`` field of the union.
+The ``gpa`` field and ``size`` specify the guest physical address
+(without the shared bit set) and the size of a shared-memory buffer, in
+which the TDX guest passes a TD Report.  The ``ret`` field represents
+the return value of the GetQuote request.  When the request has been
+queued successfully, the TDX guest can poll the status field in the
+shared-memory area to check whether the Quote generation is completed or
+not. When completed, the generated Quote is returned via the same buffer.
+
+KVM may add support for more values in the future that may cause a userspace
+exit, even without calls to ``KVM_ENABLE_CAP`` or similar.  In this case,
+it will enter with output fields already valid; in the common case, the
+``unknown.ret`` field of the union will be ``TDVMCALL_STATUS_SUBFUNC_UNSUPPORTED``.
+Userspace need not do anything if it does not wish to support a TDVMCALL.
 ::
 
 		/* Fix the size of the union. */
diff --git a/arch/x86/kvm/vmx/tdx.c b/arch/x86/kvm/vmx/tdx.c
index 5d100c240ab3..b619a3478983 100644
--- a/arch/x86/kvm/vmx/tdx.c
+++ b/arch/x86/kvm/vmx/tdx.c
@@ -1465,6 +1465,36 @@ static int tdx_get_td_vm_call_info(struct kvm_vcpu *vcpu)
 	return 1;
 }
 
+static int tdx_complete_simple(struct kvm_vcpu *vcpu)
+{
+	tdvmcall_set_return_code(vcpu, vcpu->run->tdx.unknown.ret);
+	return 1;
+}
+
+static int tdx_get_quote(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_tdx *tdx = to_tdx(vcpu);
+	u64 gpa = tdx->vp_enter_args.r12;
+	u64 size = tdx->vp_enter_args.r13;
+
+	/* The gpa of buffer must have shared bit set. */
+	if (vt_is_tdx_private_gpa(vcpu->kvm, gpa)) {
+		tdvmcall_set_return_code(vcpu, TDVMCALL_STATUS_INVALID_OPERAND);
+		return 1;
+	}
+
+	vcpu->run->exit_reason = KVM_EXIT_TDX;
+	vcpu->run->tdx.flags = 0;
+	vcpu->run->tdx.nr = TDVMCALL_GET_QUOTE;
+	vcpu->run->tdx.get_quote.ret = TDVMCALL_STATUS_SUBFUNC_UNSUPPORTED;
+	vcpu->run->tdx.get_quote.gpa = gpa & ~gfn_to_gpa(kvm_gfn_direct_bits(tdx->vcpu.kvm));
+	vcpu->run->tdx.get_quote.size = size;
+
+	vcpu->arch.complete_userspace_io = tdx_complete_simple;
+
+	return 0;
+}
+
 static int handle_tdvmcall(struct kvm_vcpu *vcpu)
 {
 	switch (tdvmcall_leaf(vcpu)) {
@@ -1474,6 +1504,8 @@ static int handle_tdvmcall(struct kvm_vcpu *vcpu)
 		return tdx_report_fatal_error(vcpu);
 	case TDVMCALL_GET_TD_VM_CALL_INFO:
 		return tdx_get_td_vm_call_info(vcpu);
+	case TDVMCALL_GET_QUOTE:
+		return tdx_get_quote(vcpu);
 	default:
 		break;
 	}
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index d00b85cb168c..e23e7286ad1a 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -178,6 +178,7 @@ struct kvm_xen_exit {
 #define KVM_EXIT_NOTIFY           37
 #define KVM_EXIT_LOONGARCH_IOCSR  38
 #define KVM_EXIT_MEMORY_FAULT     39
+#define KVM_EXIT_TDX              40
 
 /* For KVM_EXIT_INTERNAL_ERROR */
 /* Emulate instruction failed. */
@@ -447,6 +448,22 @@ struct kvm_run {
 			__u64 gpa;
 			__u64 size;
 		} memory_fault;
+		/* KVM_EXIT_TDX */
+		struct {
+			__u64 flags;
+			__u64 nr;
+			union {
+				struct {
+					__u64 ret;
+					__u64 data[5];
+				} unknown;
+				struct {
+					__u64 ret;
+					__u64 gpa;
+					__u64 size;
+				} get_quote;
+			};
+		} tdx;
 		/* Fix the size of the union. */
 		char padding[256];
 	};

From 25e8b1dd4883e6c251c3db5b347f3c8ae4ade921 Mon Sep 17 00:00:00 2001
From: Binbin Wu <binbin.wu@linux.intel.com>
Date: Tue, 10 Jun 2025 10:14:21 +0800
Subject: [PATCH 0689/1334] KVM: TDX: Exit to userspace for GetTdVmCallInfo

Exit to userspace for TDG.VP.VMCALL<GetTdVmCallInfo> via KVM_EXIT_TDX,
to allow userspace to provide information about the support of
TDVMCALLs when r12 is 1 for the TDVMCALLs beyond the GHCI base API.

GHCI spec defines the GHCI base TDVMCALLs: <GetTdVmCallInfo>, <MapGPA>,
<ReportFatalError>, <Instruction.CPUID>, <#VE.RequestMMIO>,
<Instruction.HLT>, <Instruction.IO>, <Instruction.RDMSR> and
<Instruction.WRMSR>. They must be supported by VMM to support TDX guests.

For GetTdVmCallInfo
- When leaf (r12) to enumerate TDVMCALL functionality is set to 0,
  successful execution indicates all GHCI base TDVMCALLs listed above are
  supported.

  Update the KVM TDX document with the set of the GHCI base APIs.

- When leaf (r12) to enumerate TDVMCALL functionality is set to 1, it
  indicates the TDX guest is querying the supported TDVMCALLs beyond
  the GHCI base TDVMCALLs.
  Exit to userspace to let userspace set the TDVMCALL sub-function bit(s)
  accordingly to the leaf outputs.  KVM could set the TDVMCALL bit(s)
  supported by itself when the TDVMCALLs don't need support from userspace
  after returning from userspace and before entering guest. Currently, no
  such TDVMCALLs implemented, KVM just sets the values returned from
  userspace.

Suggested-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Binbin Wu <binbin.wu@linux.intel.com>
[Adjust userspace API. - Paolo]
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 Documentation/virt/kvm/api.rst | 10 ++++++++
 arch/x86/kvm/vmx/tdx.c         | 43 ++++++++++++++++++++++++++++++----
 include/uapi/linux/kvm.h       |  5 ++++
 3 files changed, 54 insertions(+), 4 deletions(-)

diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index 115ec3c2b641..9abf93ee5f65 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -7191,6 +7191,11 @@ The valid value for 'flags' is:
 					u64 gpa;
 					u64 size;
 				} get_quote;
+				struct {
+					u64 ret;
+					u64 leaf;
+					u64 r11, r12, r13, r14;
+				} get_tdvmcall_info;
 			};
 		} tdx;
 
@@ -7216,6 +7221,11 @@ queued successfully, the TDX guest can poll the status field in the
 shared-memory area to check whether the Quote generation is completed or
 not. When completed, the generated Quote is returned via the same buffer.
 
+* ``TDVMCALL_GET_TD_VM_CALL_INFO``: the guest has requested the support
+status of TDVMCALLs.  The output values for the given leaf should be
+placed in fields from ``r11`` to ``r14`` of the ``get_tdvmcall_info``
+field of the union.
+
 KVM may add support for more values in the future that may cause a userspace
 exit, even without calls to ``KVM_ENABLE_CAP`` or similar.  In this case,
 it will enter with output fields already valid; in the common case, the
diff --git a/arch/x86/kvm/vmx/tdx.c b/arch/x86/kvm/vmx/tdx.c
index b619a3478983..1ad20c273f3b 100644
--- a/arch/x86/kvm/vmx/tdx.c
+++ b/arch/x86/kvm/vmx/tdx.c
@@ -1451,18 +1451,53 @@ error:
 	return 1;
 }
 
+static int tdx_complete_get_td_vm_call_info(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_tdx *tdx = to_tdx(vcpu);
+
+	tdvmcall_set_return_code(vcpu, vcpu->run->tdx.get_tdvmcall_info.ret);
+
+	/*
+	 * For now, there is no TDVMCALL beyond GHCI base API supported by KVM
+	 * directly without the support from userspace, just set the value
+	 * returned from userspace.
+	 */
+	tdx->vp_enter_args.r11 = vcpu->run->tdx.get_tdvmcall_info.r11;
+	tdx->vp_enter_args.r12 = vcpu->run->tdx.get_tdvmcall_info.r12;
+	tdx->vp_enter_args.r13 = vcpu->run->tdx.get_tdvmcall_info.r13;
+	tdx->vp_enter_args.r14 = vcpu->run->tdx.get_tdvmcall_info.r14;
+
+	return 1;
+}
+
 static int tdx_get_td_vm_call_info(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_tdx *tdx = to_tdx(vcpu);
 
-	if (tdx->vp_enter_args.r12)
-		tdvmcall_set_return_code(vcpu, TDVMCALL_STATUS_INVALID_OPERAND);
-	else {
+	switch (tdx->vp_enter_args.r12) {
+	case 0:
 		tdx->vp_enter_args.r11 = 0;
+		tdx->vp_enter_args.r12 = 0;
 		tdx->vp_enter_args.r13 = 0;
 		tdx->vp_enter_args.r14 = 0;
+		tdvmcall_set_return_code(vcpu, TDVMCALL_STATUS_SUCCESS);
+		return 1;
+	case 1:
+		vcpu->run->tdx.get_tdvmcall_info.leaf = tdx->vp_enter_args.r12;
+		vcpu->run->exit_reason = KVM_EXIT_TDX;
+		vcpu->run->tdx.flags = 0;
+		vcpu->run->tdx.nr = TDVMCALL_GET_TD_VM_CALL_INFO;
+		vcpu->run->tdx.get_tdvmcall_info.ret = TDVMCALL_STATUS_SUCCESS;
+		vcpu->run->tdx.get_tdvmcall_info.r11 = 0;
+		vcpu->run->tdx.get_tdvmcall_info.r12 = 0;
+		vcpu->run->tdx.get_tdvmcall_info.r13 = 0;
+		vcpu->run->tdx.get_tdvmcall_info.r14 = 0;
+		vcpu->arch.complete_userspace_io = tdx_complete_get_td_vm_call_info;
+		return 0;
+	default:
+		tdvmcall_set_return_code(vcpu, TDVMCALL_STATUS_INVALID_OPERAND);
+		return 1;
 	}
-	return 1;
 }
 
 static int tdx_complete_simple(struct kvm_vcpu *vcpu)
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index e23e7286ad1a..37891580d05d 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -462,6 +462,11 @@ struct kvm_run {
 					__u64 gpa;
 					__u64 size;
 				} get_quote;
+				struct {
+					__u64 ret;
+					__u64 leaf;
+					__u64 r11, r12, r13, r14;
+				} get_tdvmcall_info;
 			};
 		} tdx;
 		/* Fix the size of the union. */

From 4580dbef5ce0f95a4bd8ac2d007bc4fbf1539332 Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Fri, 20 Jun 2025 13:28:08 -0400
Subject: [PATCH 0690/1334] KVM: TDX: Exit to userspace for
 SetupEventNotifyInterrupt

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 Documentation/virt/kvm/api.rst    |  7 +++++++
 arch/x86/include/asm/shared/tdx.h |  1 +
 arch/x86/kvm/vmx/tdx.c            | 23 +++++++++++++++++++++++
 include/uapi/linux/kvm.h          |  4 ++++
 4 files changed, 35 insertions(+)

diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index 9abf93ee5f65..f0d961436d0f 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -7196,6 +7196,10 @@ The valid value for 'flags' is:
 					u64 leaf;
 					u64 r11, r12, r13, r14;
 				} get_tdvmcall_info;
+				struct {
+					u64 ret;
+					u64 vector;
+				} setup_event_notify;
 			};
 		} tdx;
 
@@ -7226,6 +7230,9 @@ status of TDVMCALLs.  The output values for the given leaf should be
 placed in fields from ``r11`` to ``r14`` of the ``get_tdvmcall_info``
 field of the union.
 
+* ``TDVMCALL_SETUP_EVENT_NOTIFY_INTERRUPT``: the guest has requested to
+set up a notification interrupt for vector ``vector``.
+
 KVM may add support for more values in the future that may cause a userspace
 exit, even without calls to ``KVM_ENABLE_CAP`` or similar.  In this case,
 it will enter with output fields already valid; in the common case, the
diff --git a/arch/x86/include/asm/shared/tdx.h b/arch/x86/include/asm/shared/tdx.h
index d8525e6ef50a..8bc074c8d7c6 100644
--- a/arch/x86/include/asm/shared/tdx.h
+++ b/arch/x86/include/asm/shared/tdx.h
@@ -72,6 +72,7 @@
 #define TDVMCALL_MAP_GPA		0x10001
 #define TDVMCALL_GET_QUOTE		0x10002
 #define TDVMCALL_REPORT_FATAL_ERROR	0x10003
+#define TDVMCALL_SETUP_EVENT_NOTIFY_INTERRUPT 0x10004ULL
 
 /*
  * TDG.VP.VMCALL Status Codes (returned in R10)
diff --git a/arch/x86/kvm/vmx/tdx.c b/arch/x86/kvm/vmx/tdx.c
index 1ad20c273f3b..b4055a746ecd 100644
--- a/arch/x86/kvm/vmx/tdx.c
+++ b/arch/x86/kvm/vmx/tdx.c
@@ -1530,6 +1530,27 @@ static int tdx_get_quote(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
+static int tdx_setup_event_notify_interrupt(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_tdx *tdx = to_tdx(vcpu);
+	u64 vector = tdx->vp_enter_args.r12;
+
+	if (vector < 32 || vector > 255) {
+		tdvmcall_set_return_code(vcpu, TDVMCALL_STATUS_INVALID_OPERAND);
+		return 1;
+	}
+
+	vcpu->run->exit_reason = KVM_EXIT_TDX;
+	vcpu->run->tdx.flags = 0;
+	vcpu->run->tdx.nr = TDVMCALL_SETUP_EVENT_NOTIFY_INTERRUPT;
+	vcpu->run->tdx.setup_event_notify.ret = TDVMCALL_STATUS_SUBFUNC_UNSUPPORTED;
+	vcpu->run->tdx.setup_event_notify.vector = vector;
+
+	vcpu->arch.complete_userspace_io = tdx_complete_simple;
+
+	return 0;
+}
+
 static int handle_tdvmcall(struct kvm_vcpu *vcpu)
 {
 	switch (tdvmcall_leaf(vcpu)) {
@@ -1541,6 +1562,8 @@ static int handle_tdvmcall(struct kvm_vcpu *vcpu)
 		return tdx_get_td_vm_call_info(vcpu);
 	case TDVMCALL_GET_QUOTE:
 		return tdx_get_quote(vcpu);
+	case TDVMCALL_SETUP_EVENT_NOTIFY_INTERRUPT:
+		return tdx_setup_event_notify_interrupt(vcpu);
 	default:
 		break;
 	}
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 37891580d05d..7a4c35ff03fe 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -467,6 +467,10 @@ struct kvm_run {
 					__u64 leaf;
 					__u64 r11, r12, r13, r14;
 				} get_tdvmcall_info;
+				struct {
+					__u64 ret;
+					__u64 vector;
+				} setup_event_notify;
 			};
 		} tdx;
 		/* Fix the size of the union. */

From 28224ef02b56fceee2c161fe2a49a0bb197e44f5 Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Fri, 20 Jun 2025 14:20:20 -0400
Subject: [PATCH 0691/1334] KVM: TDX: Report supported optional TDVMCALLs in
 TDX capabilities

Allow userspace to advertise TDG.VP.VMCALL subfunctions that the
kernel also supports.  For each output register of GetTdVmCallInfo's
leaf 1, add two fields to KVM_TDX_CAPABILITIES: one for kernel-supported
TDVMCALLs (userspace can set those blindly) and one for user-supported
TDVMCALLs (userspace can set those if it knows how to handle them).

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 Documentation/virt/kvm/x86/intel-tdx.rst | 15 ++++++++++++++-
 arch/x86/include/uapi/asm/kvm.h          |  8 +++++++-
 arch/x86/kvm/vmx/tdx.c                   |  7 +++++++
 3 files changed, 28 insertions(+), 2 deletions(-)

diff --git a/Documentation/virt/kvm/x86/intel-tdx.rst b/Documentation/virt/kvm/x86/intel-tdx.rst
index 76bdd95334d6..5efac62c92c7 100644
--- a/Documentation/virt/kvm/x86/intel-tdx.rst
+++ b/Documentation/virt/kvm/x86/intel-tdx.rst
@@ -79,7 +79,20 @@ to be configured to the TDX guest.
   struct kvm_tdx_capabilities {
         __u64 supported_attrs;
         __u64 supported_xfam;
-        __u64 reserved[254];
+
+        /* TDG.VP.VMCALL hypercalls executed in kernel and forwarded to
+         * userspace, respectively
+         */
+        __u64 kernel_tdvmcallinfo_1_r11;
+        __u64 user_tdvmcallinfo_1_r11;
+
+        /* TDG.VP.VMCALL instruction executions subfunctions executed in kernel
+         * and forwarded to userspace, respectively
+         */
+        __u64 kernel_tdvmcallinfo_1_r12;
+        __u64 user_tdvmcallinfo_1_r12;
+
+        __u64 reserved[250];
 
         /* Configurable CPUID bits for userspace */
         struct kvm_cpuid2 cpuid;
diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h
index 6f3499507c5e..0f15d683817d 100644
--- a/arch/x86/include/uapi/asm/kvm.h
+++ b/arch/x86/include/uapi/asm/kvm.h
@@ -965,7 +965,13 @@ struct kvm_tdx_cmd {
 struct kvm_tdx_capabilities {
 	__u64 supported_attrs;
 	__u64 supported_xfam;
-	__u64 reserved[254];
+
+	__u64 kernel_tdvmcallinfo_1_r11;
+	__u64 user_tdvmcallinfo_1_r11;
+	__u64 kernel_tdvmcallinfo_1_r12;
+	__u64 user_tdvmcallinfo_1_r12;
+
+	__u64 reserved[250];
 
 	/* Configurable CPUID bits for userspace */
 	struct kvm_cpuid2 cpuid;
diff --git a/arch/x86/kvm/vmx/tdx.c b/arch/x86/kvm/vmx/tdx.c
index b4055a746ecd..f31ccdeb905b 100644
--- a/arch/x86/kvm/vmx/tdx.c
+++ b/arch/x86/kvm/vmx/tdx.c
@@ -173,6 +173,9 @@ static void td_init_cpuid_entry2(struct kvm_cpuid_entry2 *entry, unsigned char i
 	tdx_clear_unsupported_cpuid(entry);
 }
 
+#define TDVMCALLINFO_GET_QUOTE				BIT(0)
+#define TDVMCALLINFO_SETUP_EVENT_NOTIFY_INTERRUPT	BIT(1)
+
 static int init_kvm_tdx_caps(const struct tdx_sys_info_td_conf *td_conf,
 			     struct kvm_tdx_capabilities *caps)
 {
@@ -188,6 +191,10 @@ static int init_kvm_tdx_caps(const struct tdx_sys_info_td_conf *td_conf,
 
 	caps->cpuid.nent = td_conf->num_cpuid_config;
 
+	caps->user_tdvmcallinfo_1_r11 =
+		TDVMCALLINFO_GET_QUOTE |
+		TDVMCALLINFO_SETUP_EVENT_NOTIFY_INTERRUPT;
+
 	for (i = 0; i < td_conf->num_cpuid_config; i++)
 		td_init_cpuid_entry2(&caps->cpuid.entries[i], i);
 

From 33b6a1f155d627f5bd80c7485c598ce45428f74f Mon Sep 17 00:00:00 2001
From: "Uladzislau Rezki (Sony)" <urezki@gmail.com>
Date: Tue, 10 Jun 2025 19:34:48 +0200
Subject: [PATCH 0692/1334] rcu: Return early if callback is not specified

Currently the call_rcu() API does not check whether a callback
pointer is NULL. If NULL is passed, rcu_core() will try to invoke
it, resulting in NULL pointer dereference and a kernel crash.

To prevent this and improve debuggability, this patch adds a check
for NULL and emits a kernel stack trace to help identify a faulty
caller.

Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com>
Reviewed-by: Joel Fernandes <joelagnelf@nvidia.com>
Signed-off-by: Joel Fernandes <joelagnelf@nvidia.com>
---
 kernel/rcu/tree.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index e8a4b720d7d2..14d4499c6fc3 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -3072,6 +3072,10 @@ __call_rcu_common(struct rcu_head *head, rcu_callback_t func, bool lazy_in)
 	/* Misaligned rcu_head! */
 	WARN_ON_ONCE((unsigned long)head & (sizeof(void *) - 1));
 
+	/* Avoid NULL dereference if callback is NULL. */
+	if (WARN_ON_ONCE(!func))
+		return;
+
 	if (debug_rcu_head_queue(head)) {
 		/*
 		 * Probable double call_rcu(), so leak the callback.

From 3085ef9d9e7ab5ae4cddbe809e2e3b8dc11cdc75 Mon Sep 17 00:00:00 2001
From: Shiji Yang <yangshiji66@outlook.com>
Date: Wed, 18 Jun 2025 23:07:43 +0800
Subject: [PATCH 0693/1334] irqchip/ath79-misc: Fix missing prototypes warnings

ath79_misc_irq_init() was defined but unused since commit 51fa4f8912c0
("MIPS: ath79: drop legacy IRQ code"), so it's time to drop it.

The build also warns about a missing prototype of get_c0_perfcount_int().

Remove the stale leftover function and add the missing include.

Signed-off-by: Shiji Yang <yangshiji66@outlook.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/OSBPR01MB167032D2017645200787AAEBBC72A@OSBPR01MB1670.jpnprd01.prod.outlook.com
---
 drivers/irqchip/irq-ath79-misc.c | 20 ++------------------
 1 file changed, 2 insertions(+), 18 deletions(-)

diff --git a/drivers/irqchip/irq-ath79-misc.c b/drivers/irqchip/irq-ath79-misc.c
index 268cc18b781f..258b8e9a2d57 100644
--- a/drivers/irqchip/irq-ath79-misc.c
+++ b/drivers/irqchip/irq-ath79-misc.c
@@ -15,6 +15,8 @@
 #include <linux/of_address.h>
 #include <linux/of_irq.h>
 
+#include <asm/time.h>
+
 #define AR71XX_RESET_REG_MISC_INT_STATUS	0
 #define AR71XX_RESET_REG_MISC_INT_ENABLE	4
 
@@ -177,21 +179,3 @@ static int __init ar7240_misc_intc_of_init(
 
 IRQCHIP_DECLARE(ar7240_misc_intc, "qca,ar7240-misc-intc",
 		ar7240_misc_intc_of_init);
-
-void __init ath79_misc_irq_init(void __iomem *regs, int irq,
-				int irq_base, bool is_ar71xx)
-{
-	struct irq_domain *domain;
-
-	if (is_ar71xx)
-		ath79_misc_irq_chip.irq_mask_ack = ar71xx_misc_irq_mask;
-	else
-		ath79_misc_irq_chip.irq_ack = ar724x_misc_irq_ack;
-
-	domain = irq_domain_create_legacy(NULL, ATH79_MISC_IRQ_COUNT,
-			irq_base, 0, &misc_irq_domain_ops, regs);
-	if (!domain)
-		panic("Failed to create MISC irqdomain");
-
-	ath79_misc_intc_domain_init(domain, irq);
-}

From 64f7548aad63d2fbca2eeb6eb33361c218ebd5a5 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Fri, 20 Jun 2025 21:19:40 +0200
Subject: [PATCH 0694/1334] lib/crypto: sha256: Mark sha256_choose_blocks as
 __always_inline

When the compiler chooses to not inline sha256_choose_blocks() in
the purgatory code, it fails to link against the missing CPU
specific version:

x86_64-linux-ld: arch/x86/purgatory/purgatory.ro: in function `sha256_choose_blocks.part.0':
sha256.c:(.text+0x6a6): undefined reference to `irq_fpu_usable'
sha256.c:(.text+0x6c7): undefined reference to `sha256_blocks_arch'
sha256.c:(.text+0x6cc): undefined reference to `sha256_blocks_simd'

Mark this function as __always_inline to prevent this, same as sha256_finup().

Fixes: 5b90a779bc54 ("crypto: lib/sha256 - Add helpers for block-based shash")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Link: https://lore.kernel.org/r/20250620191952.1867578-1-arnd@kernel.org
Signed-off-by: Eric Biggers <ebiggers@kernel.org>
---
 include/crypto/internal/sha2.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/crypto/internal/sha2.h b/include/crypto/internal/sha2.h
index b9bccd3ff57f..21a27fd5e198 100644
--- a/include/crypto/internal/sha2.h
+++ b/include/crypto/internal/sha2.h
@@ -25,7 +25,7 @@ void sha256_blocks_arch(u32 state[SHA256_STATE_WORDS],
 void sha256_blocks_simd(u32 state[SHA256_STATE_WORDS],
 			const u8 *data, size_t nblocks);
 
-static inline void sha256_choose_blocks(
+static __always_inline void sha256_choose_blocks(
 	u32 state[SHA256_STATE_WORDS], const u8 *data, size_t nblocks,
 	bool force_generic, bool force_simd)
 {

From a42b4dcc4f9f309a23e6de5ae57a680b9fd2ea10 Mon Sep 17 00:00:00 2001
From: Julien Massot <julien.massot@collabora.com>
Date: Fri, 16 May 2025 16:12:13 +0200
Subject: [PATCH 0695/1334] dt-bindings: clock: mediatek: Add #reset-cells
 property for MT8188

The '#reset-cells' property is permitted for some of the MT8188
clock controllers, but not listed as a valid property.

Fixes: 9a5cd59640ac ("dt-bindings: clock: mediatek: Add SMI LARBs reset for MT8188")
Reviewed-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
Signed-off-by: Julien Massot <julien.massot@collabora.com>
Link: https://lore.kernel.org/r/20250516-dtb-check-mt8188-v2-1-fb60bef1b8e1@collabora.com
Acked-by: Conor Dooley <conor.dooley@microchip.com>
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 .../devicetree/bindings/clock/mediatek,mt8188-clock.yaml       | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/Documentation/devicetree/bindings/clock/mediatek,mt8188-clock.yaml b/Documentation/devicetree/bindings/clock/mediatek,mt8188-clock.yaml
index 2985c8c717d7..5403242545ab 100644
--- a/Documentation/devicetree/bindings/clock/mediatek,mt8188-clock.yaml
+++ b/Documentation/devicetree/bindings/clock/mediatek,mt8188-clock.yaml
@@ -52,6 +52,9 @@ properties:
   '#clock-cells':
     const: 1
 
+  '#reset-cells':
+    const: 1
+
 required:
   - compatible
   - reg

From 0b39b055b5b48cbbdf5746a1ca6e3f6b0221e537 Mon Sep 17 00:00:00 2001
From: Xiaowei Li <xiaowei.li@simcom.com>
Date: Fri, 20 Jun 2025 10:27:02 +0800
Subject: [PATCH 0696/1334] net: usb: qmi_wwan: add SIMCom 8230C composition
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add support for SIMCom 8230C which is based on Qualcomm SDX35 chip.
0x9071: tty (DM) + tty (NMEA) + tty (AT) + rmnet
T:  Bus=01 Lev=01 Prnt=01 Port=05 Cnt=02 Dev#=  8 Spd=480  MxCh= 0
D:  Ver= 2.00 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs=  1
P:  Vendor=1e0e ProdID=9071 Rev= 5.15
S:  Manufacturer=SIMCOM
S:  Product=SDXBAAGHA-IDP _SN:D744C4C5
S:  SerialNumber=0123456789ABCDEF
C:* #Ifs= 5 Cfg#= 1 Atr=a0 MxPwr=500mA
I:* If#= 0 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=30 Driver=option
E:  Ad=01(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=81(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 1 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
E:  Ad=82(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=40 Driver=option
E:  Ad=84(I) Atr=03(Int.) MxPS=  10 Ivl=32ms
E:  Ad=83(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=03(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 3 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=50 Driver=qmi_wwan
E:  Ad=86(I) Atr=03(Int.) MxPS=   8 Ivl=32ms
E:  Ad=85(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=04(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 4 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=42 Prot=01 Driver=none
E:  Ad=05(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=87(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms

Signed-off-by: Xiaowei Li <xiaowei.li@simcom.com>
Acked-by: Bjørn Mork <bjorn@mork.no>
Link: https://patch.msgid.link/tencent_21D781FAA4969FEACA6ABB460362B52C9409@qq.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/usb/qmi_wwan.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index b586b1c13a47..f5647ee0adde 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -1426,6 +1426,7 @@ static const struct usb_device_id products[] = {
 	{QMI_QUIRK_SET_DTR(0x22de, 0x9051, 2)}, /* Hucom Wireless HM-211S/K */
 	{QMI_FIXED_INTF(0x22de, 0x9061, 3)},	/* WeTelecom WPD-600N */
 	{QMI_QUIRK_SET_DTR(0x1e0e, 0x9001, 5)},	/* SIMCom 7100E, 7230E, 7600E ++ */
+	{QMI_QUIRK_SET_DTR(0x1e0e, 0x9071, 3)},	/* SIMCom 8230C ++ */
 	{QMI_QUIRK_SET_DTR(0x2c7c, 0x0121, 4)},	/* Quectel EC21 Mini PCIe */
 	{QMI_QUIRK_SET_DTR(0x2c7c, 0x0191, 4)},	/* Quectel EG91 */
 	{QMI_QUIRK_SET_DTR(0x2c7c, 0x0195, 4)},	/* Quectel EG95 */

From 714db279942b1fb9b97c4243e186825a96750239 Mon Sep 17 00:00:00 2001
From: Shannon Nelson <sln@onemain.com>
Date: Thu, 19 Jun 2025 14:16:07 -0700
Subject: [PATCH 0697/1334] CREDITS: Add entry for Shannon Nelson

I'm retiring and have already had my name removed from MAINTAINERS.
A couple of folks kindly suggested I should have an entry here.

Signed-off-by: Shannon Nelson <sln@onemain.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/20250619211607.1244217-1-sln@onemain.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 CREDITS | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/CREDITS b/CREDITS
index 45446ae322ec..c30b75f9a732 100644
--- a/CREDITS
+++ b/CREDITS
@@ -2981,6 +2981,11 @@ S: 521 Pleasant Valley Road
 S: Potsdam, New York 13676
 S: USA
 
+N: Shannon Nelson
+E: sln@onemain.com
+D: Worked on several network drivers including
+D: ixgbe, i40e, ionic, pds_core, pds_vdpa, pds_fwctl
+
 N: Dave Neuer
 E: dave.neuer@pobox.com
 D: Helped implement support for Compaq's H31xx series iPAQs

From 34331d7beed7576acfc98e991c39738b96162499 Mon Sep 17 00:00:00 2001
From: zhangjian <zhangjian496@huawei.com>
Date: Thu, 19 Jun 2025 09:18:29 +0800
Subject: [PATCH 0698/1334] smb: client: fix first command failure during
 re-negotiation

after fabc4ed200f9, server_unresponsive add a condition to check whether client
need to reconnect depending on server->lstrp. When client failed to reconnect
for some time and abort connection, server->lstrp is updated for the last time.
In the following scene, server->lstrp is too old. This cause next command
failure in re-negotiation rather than waiting for re-negotiation done.

1. mount -t cifs -o username=Everyone,echo_internal=10 //$server_ip/export /mnt
2. ssh $server_ip "echo b > /proc/sysrq-trigger &"
3. ls /mnt
4. sleep 21s
5. ssh $server_ip "service firewalld stop"
6. ls # return EHOSTDOWN

If the interval between 5 and 6 is too small, 6 may trigger sending negotiation
request. Before backgrounding cifsd thread try to receive negotiation response
from server in cifs_readv_from_socket, server_unresponsive may trigger
cifs_reconnect which cause 6 to be failed:

ls thread
----------------
  smb2_negotiate
    server->tcpStatus = CifsInNegotiate
    compound_send_recv
      wait_for_compound_request

cifsd thread
----------------
  cifs_readv_from_socket
    server_unresponsive
      server->tcpStatus == CifsInNegotiate && jiffies > server->lstrp + 20s
        cifs_reconnect
          cifs_abort_connection: mid_state = MID_RETRY_NEEDED

ls thread
----------------
      cifs_sync_mid_result return EAGAIN
  smb2_negotiate return EHOSTDOWN

Though server->lstrp means last server response time, it is updated in
cifs_abort_connection and cifs_get_tcp_session. We can also update server->lstrp
before switching into CifsInNegotiate state to avoid failure in 6.

Fixes: 7ccc1465465d ("smb: client: fix hang in wait_for_response() for negproto")
Acked-by: Paulo Alcantara (Red Hat) <pc@manguebit.org>
Acked-by: Meetakshi Setiya <msetiya@microsoft.com>
Signed-off-by: zhangjian <zhangjian496@huawei.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/connect.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/fs/smb/client/connect.c b/fs/smb/client/connect.c
index c4fb80b37738..c48869c29e15 100644
--- a/fs/smb/client/connect.c
+++ b/fs/smb/client/connect.c
@@ -4199,6 +4199,7 @@ retry:
 		return 0;
 	}
 
+	server->lstrp = jiffies;
 	server->tcpStatus = CifsInNegotiate;
 	spin_unlock(&server->srv_lock);
 

From a379a8a2a0032e12e7ef397197c9c2ad011588d6 Mon Sep 17 00:00:00 2001
From: Stefan Metzmacher <metze@samba.org>
Date: Wed, 18 Jun 2025 18:51:40 +0200
Subject: [PATCH 0699/1334] smb: client: fix max_sge overflow in
 smb_extract_folioq_to_rdma()

This fixes the following problem:

[  749.901015] [   T8673] run fstests cifs/001 at 2025-06-17 09:40:30
[  750.346409] [   T9870] ==================================================================
[  750.346814] [   T9870] BUG: KASAN: slab-out-of-bounds in smb_set_sge+0x2cc/0x3b0 [cifs]
[  750.347330] [   T9870] Write of size 8 at addr ffff888011082890 by task xfs_io/9870
[  750.347705] [   T9870]
[  750.348077] [   T9870] CPU: 0 UID: 0 PID: 9870 Comm: xfs_io Kdump: loaded Not tainted 6.16.0-rc2-metze.02+ #1 PREEMPT(voluntary)
[  750.348082] [   T9870] Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006
[  750.348085] [   T9870] Call Trace:
[  750.348086] [   T9870]  <TASK>
[  750.348088] [   T9870]  dump_stack_lvl+0x76/0xa0
[  750.348106] [   T9870]  print_report+0xd1/0x640
[  750.348116] [   T9870]  ? __pfx__raw_spin_lock_irqsave+0x10/0x10
[  750.348120] [   T9870]  ? kasan_complete_mode_report_info+0x26/0x210
[  750.348124] [   T9870]  kasan_report+0xe7/0x130
[  750.348128] [   T9870]  ? smb_set_sge+0x2cc/0x3b0 [cifs]
[  750.348262] [   T9870]  ? smb_set_sge+0x2cc/0x3b0 [cifs]
[  750.348377] [   T9870]  __asan_report_store8_noabort+0x17/0x30
[  750.348381] [   T9870]  smb_set_sge+0x2cc/0x3b0 [cifs]
[  750.348496] [   T9870]  smbd_post_send_iter+0x1990/0x3070 [cifs]
[  750.348625] [   T9870]  ? __pfx_smbd_post_send_iter+0x10/0x10 [cifs]
[  750.348741] [   T9870]  ? update_stack_state+0x2a0/0x670
[  750.348749] [   T9870]  ? cifs_flush+0x153/0x320 [cifs]
[  750.348870] [   T9870]  ? cifs_flush+0x153/0x320 [cifs]
[  750.348990] [   T9870]  ? update_stack_state+0x2a0/0x670
[  750.348995] [   T9870]  smbd_send+0x58c/0x9c0 [cifs]
[  750.349117] [   T9870]  ? __pfx_smbd_send+0x10/0x10 [cifs]
[  750.349231] [   T9870]  ? unwind_get_return_address+0x65/0xb0
[  750.349235] [   T9870]  ? __pfx_stack_trace_consume_entry+0x10/0x10
[  750.349242] [   T9870]  ? arch_stack_walk+0xa7/0x100
[  750.349250] [   T9870]  ? stack_trace_save+0x92/0xd0
[  750.349254] [   T9870]  __smb_send_rqst+0x931/0xec0 [cifs]
[  750.349374] [   T9870]  ? kernel_text_address+0x173/0x190
[  750.349379] [   T9870]  ? kasan_save_stack+0x39/0x70
[  750.349382] [   T9870]  ? kasan_save_track+0x18/0x70
[  750.349385] [   T9870]  ? __kasan_slab_alloc+0x9d/0xa0
[  750.349389] [   T9870]  ? __pfx___smb_send_rqst+0x10/0x10 [cifs]
[  750.349508] [   T9870]  ? smb2_mid_entry_alloc+0xb4/0x7e0 [cifs]
[  750.349626] [   T9870]  ? cifs_call_async+0x277/0xb00 [cifs]
[  750.349746] [   T9870]  ? cifs_issue_write+0x256/0x610 [cifs]
[  750.349867] [   T9870]  ? netfs_do_issue_write+0xc2/0x340 [netfs]
[  750.349900] [   T9870]  ? netfs_advance_write+0x45b/0x1270 [netfs]
[  750.349929] [   T9870]  ? netfs_write_folio+0xd6c/0x1be0 [netfs]
[  750.349958] [   T9870]  ? netfs_writepages+0x2e9/0xa80 [netfs]
[  750.349987] [   T9870]  ? do_writepages+0x21f/0x590
[  750.349993] [   T9870]  ? filemap_fdatawrite_wbc+0xe1/0x140
[  750.349997] [   T9870]  ? entry_SYSCALL_64_after_hwframe+0x76/0x7e
[  750.350002] [   T9870]  smb_send_rqst+0x22e/0x2f0 [cifs]
[  750.350131] [   T9870]  ? __pfx_smb_send_rqst+0x10/0x10 [cifs]
[  750.350255] [   T9870]  ? local_clock_noinstr+0xe/0xd0
[  750.350261] [   T9870]  ? kasan_save_alloc_info+0x37/0x60
[  750.350268] [   T9870]  ? __kasan_check_write+0x14/0x30
[  750.350271] [   T9870]  ? _raw_spin_lock+0x81/0xf0
[  750.350275] [   T9870]  ? __pfx__raw_spin_lock+0x10/0x10
[  750.350278] [   T9870]  ? smb2_setup_async_request+0x293/0x580 [cifs]
[  750.350398] [   T9870]  cifs_call_async+0x477/0xb00 [cifs]
[  750.350518] [   T9870]  ? __pfx_smb2_writev_callback+0x10/0x10 [cifs]
[  750.350636] [   T9870]  ? __pfx_cifs_call_async+0x10/0x10 [cifs]
[  750.350756] [   T9870]  ? __pfx__raw_spin_lock+0x10/0x10
[  750.350760] [   T9870]  ? __kasan_check_write+0x14/0x30
[  750.350763] [   T9870]  ? __smb2_plain_req_init+0x933/0x1090 [cifs]
[  750.350891] [   T9870]  smb2_async_writev+0x15ff/0x2460 [cifs]
[  750.351008] [   T9870]  ? sched_clock_noinstr+0x9/0x10
[  750.351012] [   T9870]  ? local_clock_noinstr+0xe/0xd0
[  750.351018] [   T9870]  ? __pfx_smb2_async_writev+0x10/0x10 [cifs]
[  750.351144] [   T9870]  ? __pfx__raw_spin_lock_irqsave+0x10/0x10
[  750.351150] [   T9870]  ? _raw_spin_unlock+0xe/0x40
[  750.351154] [   T9870]  ? cifs_pick_channel+0x242/0x370 [cifs]
[  750.351275] [   T9870]  cifs_issue_write+0x256/0x610 [cifs]
[  750.351554] [   T9870]  ? cifs_issue_write+0x256/0x610 [cifs]
[  750.351677] [   T9870]  netfs_do_issue_write+0xc2/0x340 [netfs]
[  750.351710] [   T9870]  netfs_advance_write+0x45b/0x1270 [netfs]
[  750.351740] [   T9870]  ? rolling_buffer_append+0x12d/0x440 [netfs]
[  750.351769] [   T9870]  netfs_write_folio+0xd6c/0x1be0 [netfs]
[  750.351798] [   T9870]  ? __kasan_check_write+0x14/0x30
[  750.351804] [   T9870]  netfs_writepages+0x2e9/0xa80 [netfs]
[  750.351835] [   T9870]  ? __pfx_netfs_writepages+0x10/0x10 [netfs]
[  750.351864] [   T9870]  ? exit_files+0xab/0xe0
[  750.351867] [   T9870]  ? do_exit+0x148f/0x2980
[  750.351871] [   T9870]  ? do_group_exit+0xb5/0x250
[  750.351874] [   T9870]  ? arch_do_signal_or_restart+0x92/0x630
[  750.351879] [   T9870]  ? exit_to_user_mode_loop+0x98/0x170
[  750.351882] [   T9870]  ? do_syscall_64+0x2cf/0xd80
[  750.351886] [   T9870]  ? entry_SYSCALL_64_after_hwframe+0x76/0x7e
[  750.351890] [   T9870]  do_writepages+0x21f/0x590
[  750.351894] [   T9870]  ? __pfx_do_writepages+0x10/0x10
[  750.351897] [   T9870]  filemap_fdatawrite_wbc+0xe1/0x140
[  750.351901] [   T9870]  __filemap_fdatawrite_range+0xba/0x100
[  750.351904] [   T9870]  ? __pfx___filemap_fdatawrite_range+0x10/0x10
[  750.351912] [   T9870]  ? __kasan_check_write+0x14/0x30
[  750.351916] [   T9870]  filemap_write_and_wait_range+0x7d/0xf0
[  750.351920] [   T9870]  cifs_flush+0x153/0x320 [cifs]
[  750.352042] [   T9870]  filp_flush+0x107/0x1a0
[  750.352046] [   T9870]  filp_close+0x14/0x30
[  750.352049] [   T9870]  put_files_struct.part.0+0x126/0x2a0
[  750.352053] [   T9870]  ? __pfx__raw_spin_lock+0x10/0x10
[  750.352058] [   T9870]  exit_files+0xab/0xe0
[  750.352061] [   T9870]  do_exit+0x148f/0x2980
[  750.352065] [   T9870]  ? __pfx_do_exit+0x10/0x10
[  750.352069] [   T9870]  ? __kasan_check_write+0x14/0x30
[  750.352072] [   T9870]  ? _raw_spin_lock_irq+0x8a/0xf0
[  750.352076] [   T9870]  do_group_exit+0xb5/0x250
[  750.352080] [   T9870]  get_signal+0x22d3/0x22e0
[  750.352086] [   T9870]  ? __pfx_get_signal+0x10/0x10
[  750.352089] [   T9870]  ? fpregs_assert_state_consistent+0x68/0x100
[  750.352101] [   T9870]  ? folio_add_lru+0xda/0x120
[  750.352105] [   T9870]  arch_do_signal_or_restart+0x92/0x630
[  750.352109] [   T9870]  ? __pfx_arch_do_signal_or_restart+0x10/0x10
[  750.352115] [   T9870]  exit_to_user_mode_loop+0x98/0x170
[  750.352118] [   T9870]  do_syscall_64+0x2cf/0xd80
[  750.352123] [   T9870]  ? __kasan_check_read+0x11/0x20
[  750.352126] [   T9870]  ? count_memcg_events+0x1b4/0x420
[  750.352132] [   T9870]  ? handle_mm_fault+0x148/0x690
[  750.352136] [   T9870]  ? _raw_spin_lock_irq+0x8a/0xf0
[  750.352140] [   T9870]  ? __kasan_check_read+0x11/0x20
[  750.352143] [   T9870]  ? fpregs_assert_state_consistent+0x68/0x100
[  750.352146] [   T9870]  ? irqentry_exit_to_user_mode+0x2e/0x250
[  750.352151] [   T9870]  ? irqentry_exit+0x43/0x50
[  750.352154] [   T9870]  ? exc_page_fault+0x75/0xe0
[  750.352160] [   T9870]  entry_SYSCALL_64_after_hwframe+0x76/0x7e
[  750.352163] [   T9870] RIP: 0033:0x7858c94ab6e2
[  750.352167] [   T9870] Code: Unable to access opcode bytes at 0x7858c94ab6b8.
[  750.352175] [   T9870] RSP: 002b:00007858c9248ce8 EFLAGS: 00000246 ORIG_RAX: 0000000000000022
[  750.352179] [   T9870] RAX: fffffffffffffdfe RBX: 00007858c92496c0 RCX: 00007858c94ab6e2
[  750.352182] [   T9870] RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000
[  750.352184] [   T9870] RBP: 00007858c9248d10 R08: 0000000000000000 R09: 0000000000000000
[  750.352185] [   T9870] R10: 0000000000000000 R11: 0000000000000246 R12: fffffffffffffde0
[  750.352187] [   T9870] R13: 0000000000000020 R14: 0000000000000002 R15: 00007ffc072d2230
[  750.352191] [   T9870]  </TASK>
[  750.352195] [   T9870]
[  750.395206] [   T9870] Allocated by task 9870 on cpu 0 at 750.346406s:
[  750.395523] [   T9870]  kasan_save_stack+0x39/0x70
[  750.395532] [   T9870]  kasan_save_track+0x18/0x70
[  750.395536] [   T9870]  kasan_save_alloc_info+0x37/0x60
[  750.395539] [   T9870]  __kasan_slab_alloc+0x9d/0xa0
[  750.395543] [   T9870]  kmem_cache_alloc_noprof+0x13c/0x3f0
[  750.395548] [   T9870]  mempool_alloc_slab+0x15/0x20
[  750.395553] [   T9870]  mempool_alloc_noprof+0x135/0x340
[  750.395557] [   T9870]  smbd_post_send_iter+0x63e/0x3070 [cifs]
[  750.395694] [   T9870]  smbd_send+0x58c/0x9c0 [cifs]
[  750.395819] [   T9870]  __smb_send_rqst+0x931/0xec0 [cifs]
[  750.395950] [   T9870]  smb_send_rqst+0x22e/0x2f0 [cifs]
[  750.396081] [   T9870]  cifs_call_async+0x477/0xb00 [cifs]
[  750.396232] [   T9870]  smb2_async_writev+0x15ff/0x2460 [cifs]
[  750.396359] [   T9870]  cifs_issue_write+0x256/0x610 [cifs]
[  750.396492] [   T9870]  netfs_do_issue_write+0xc2/0x340 [netfs]
[  750.396544] [   T9870]  netfs_advance_write+0x45b/0x1270 [netfs]
[  750.396576] [   T9870]  netfs_write_folio+0xd6c/0x1be0 [netfs]
[  750.396608] [   T9870]  netfs_writepages+0x2e9/0xa80 [netfs]
[  750.396639] [   T9870]  do_writepages+0x21f/0x590
[  750.396643] [   T9870]  filemap_fdatawrite_wbc+0xe1/0x140
[  750.396647] [   T9870]  __filemap_fdatawrite_range+0xba/0x100
[  750.396651] [   T9870]  filemap_write_and_wait_range+0x7d/0xf0
[  750.396656] [   T9870]  cifs_flush+0x153/0x320 [cifs]
[  750.396787] [   T9870]  filp_flush+0x107/0x1a0
[  750.396791] [   T9870]  filp_close+0x14/0x30
[  750.396795] [   T9870]  put_files_struct.part.0+0x126/0x2a0
[  750.396800] [   T9870]  exit_files+0xab/0xe0
[  750.396803] [   T9870]  do_exit+0x148f/0x2980
[  750.396808] [   T9870]  do_group_exit+0xb5/0x250
[  750.396813] [   T9870]  get_signal+0x22d3/0x22e0
[  750.396817] [   T9870]  arch_do_signal_or_restart+0x92/0x630
[  750.396822] [   T9870]  exit_to_user_mode_loop+0x98/0x170
[  750.396827] [   T9870]  do_syscall_64+0x2cf/0xd80
[  750.396832] [   T9870]  entry_SYSCALL_64_after_hwframe+0x76/0x7e
[  750.396836] [   T9870]
[  750.397150] [   T9870] The buggy address belongs to the object at ffff888011082800
                           which belongs to the cache smbd_request_0000000008f3bd7b of size 144
[  750.397798] [   T9870] The buggy address is located 0 bytes to the right of
                           allocated 144-byte region [ffff888011082800, ffff888011082890)
[  750.398469] [   T9870]
[  750.398800] [   T9870] The buggy address belongs to the physical page:
[  750.399141] [   T9870] page: refcount:0 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x11082
[  750.399148] [   T9870] flags: 0xfffffc0000000(node=0|zone=1|lastcpupid=0x1fffff)
[  750.399155] [   T9870] page_type: f5(slab)
[  750.399161] [   T9870] raw: 000fffffc0000000 ffff888022d65640 dead000000000122 0000000000000000
[  750.399165] [   T9870] raw: 0000000000000000 0000000080100010 00000000f5000000 0000000000000000
[  750.399169] [   T9870] page dumped because: kasan: bad access detected
[  750.399172] [   T9870]
[  750.399505] [   T9870] Memory state around the buggy address:
[  750.399863] [   T9870]  ffff888011082780: fb fb fc fc fc fc fc fc fc fc fc fc fc fc fc fc
[  750.400247] [   T9870]  ffff888011082800: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
[  750.400618] [   T9870] >ffff888011082880: 00 00 fc fc fc fc fc fc fc fc fc fc fc fc fc fc
[  750.400982] [   T9870]                          ^
[  750.401370] [   T9870]  ffff888011082900: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
[  750.401774] [   T9870]  ffff888011082980: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
[  750.402171] [   T9870] ==================================================================
[  750.402696] [   T9870] Disabling lock debugging due to kernel taint
[  750.403202] [   T9870] BUG: unable to handle page fault for address: ffff8880110a2000
[  750.403797] [   T9870] #PF: supervisor write access in kernel mode
[  750.404204] [   T9870] #PF: error_code(0x0003) - permissions violation
[  750.404581] [   T9870] PGD 5ce01067 P4D 5ce01067 PUD 5ce02067 PMD 78aa063 PTE 80000000110a2021
[  750.404969] [   T9870] Oops: Oops: 0003 [#1] SMP KASAN PTI
[  750.405394] [   T9870] CPU: 0 UID: 0 PID: 9870 Comm: xfs_io Kdump: loaded Tainted: G    B               6.16.0-rc2-metze.02+ #1 PREEMPT(voluntary)
[  750.406510] [   T9870] Tainted: [B]=BAD_PAGE
[  750.406967] [   T9870] Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006
[  750.407440] [   T9870] RIP: 0010:smb_set_sge+0x15c/0x3b0 [cifs]
[  750.408065] [   T9870] Code: 48 83 f8 ff 0f 84 b0 00 00 00 48 ba 00 00 00 00 00 fc ff df 4c 89 e1 48 c1 e9 03 80 3c 11 00 0f 85 69 01 00 00 49 8d 7c 24 08 <49> 89 04 24 48 b8 00 00 00 00 00 fc ff df 48 89 fa 48 c1 ea 03 0f
[  750.409283] [   T9870] RSP: 0018:ffffc90005e2e758 EFLAGS: 00010246
[  750.409803] [   T9870] RAX: ffff888036c53400 RBX: ffffc90005e2e878 RCX: 1ffff11002214400
[  750.410323] [   T9870] RDX: dffffc0000000000 RSI: dffffc0000000000 RDI: ffff8880110a2008
[  750.411217] [   T9870] RBP: ffffc90005e2e798 R08: 0000000000000001 R09: 0000000000000400
[  750.411770] [   T9870] R10: ffff888011082800 R11: 0000000000000000 R12: ffff8880110a2000
[  750.412325] [   T9870] R13: 0000000000000000 R14: ffffc90005e2e888 R15: ffff88801a4b6000
[  750.412901] [   T9870] FS:  0000000000000000(0000) GS:ffff88812bc68000(0000) knlGS:0000000000000000
[  750.413477] [   T9870] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  750.414077] [   T9870] CR2: ffff8880110a2000 CR3: 000000005b0a6005 CR4: 00000000000726f0
[  750.414654] [   T9870] Call Trace:
[  750.415211] [   T9870]  <TASK>
[  750.415748] [   T9870]  smbd_post_send_iter+0x1990/0x3070 [cifs]
[  750.416449] [   T9870]  ? __pfx_smbd_post_send_iter+0x10/0x10 [cifs]
[  750.417128] [   T9870]  ? update_stack_state+0x2a0/0x670
[  750.417685] [   T9870]  ? cifs_flush+0x153/0x320 [cifs]
[  750.418380] [   T9870]  ? cifs_flush+0x153/0x320 [cifs]
[  750.419055] [   T9870]  ? update_stack_state+0x2a0/0x670
[  750.419624] [   T9870]  smbd_send+0x58c/0x9c0 [cifs]
[  750.420297] [   T9870]  ? __pfx_smbd_send+0x10/0x10 [cifs]
[  750.420936] [   T9870]  ? unwind_get_return_address+0x65/0xb0
[  750.421456] [   T9870]  ? __pfx_stack_trace_consume_entry+0x10/0x10
[  750.421954] [   T9870]  ? arch_stack_walk+0xa7/0x100
[  750.422460] [   T9870]  ? stack_trace_save+0x92/0xd0
[  750.422948] [   T9870]  __smb_send_rqst+0x931/0xec0 [cifs]
[  750.423579] [   T9870]  ? kernel_text_address+0x173/0x190
[  750.424056] [   T9870]  ? kasan_save_stack+0x39/0x70
[  750.424813] [   T9870]  ? kasan_save_track+0x18/0x70
[  750.425323] [   T9870]  ? __kasan_slab_alloc+0x9d/0xa0
[  750.425831] [   T9870]  ? __pfx___smb_send_rqst+0x10/0x10 [cifs]
[  750.426548] [   T9870]  ? smb2_mid_entry_alloc+0xb4/0x7e0 [cifs]
[  750.427231] [   T9870]  ? cifs_call_async+0x277/0xb00 [cifs]
[  750.427882] [   T9870]  ? cifs_issue_write+0x256/0x610 [cifs]
[  750.428909] [   T9870]  ? netfs_do_issue_write+0xc2/0x340 [netfs]
[  750.429425] [   T9870]  ? netfs_advance_write+0x45b/0x1270 [netfs]
[  750.429882] [   T9870]  ? netfs_write_folio+0xd6c/0x1be0 [netfs]
[  750.430345] [   T9870]  ? netfs_writepages+0x2e9/0xa80 [netfs]
[  750.430809] [   T9870]  ? do_writepages+0x21f/0x590
[  750.431239] [   T9870]  ? filemap_fdatawrite_wbc+0xe1/0x140
[  750.431652] [   T9870]  ? entry_SYSCALL_64_after_hwframe+0x76/0x7e
[  750.432041] [   T9870]  smb_send_rqst+0x22e/0x2f0 [cifs]
[  750.432586] [   T9870]  ? __pfx_smb_send_rqst+0x10/0x10 [cifs]
[  750.433108] [   T9870]  ? local_clock_noinstr+0xe/0xd0
[  750.433482] [   T9870]  ? kasan_save_alloc_info+0x37/0x60
[  750.433855] [   T9870]  ? __kasan_check_write+0x14/0x30
[  750.434214] [   T9870]  ? _raw_spin_lock+0x81/0xf0
[  750.434561] [   T9870]  ? __pfx__raw_spin_lock+0x10/0x10
[  750.434903] [   T9870]  ? smb2_setup_async_request+0x293/0x580 [cifs]
[  750.435394] [   T9870]  cifs_call_async+0x477/0xb00 [cifs]
[  750.435892] [   T9870]  ? __pfx_smb2_writev_callback+0x10/0x10 [cifs]
[  750.436388] [   T9870]  ? __pfx_cifs_call_async+0x10/0x10 [cifs]
[  750.436881] [   T9870]  ? __pfx__raw_spin_lock+0x10/0x10
[  750.437237] [   T9870]  ? __kasan_check_write+0x14/0x30
[  750.437579] [   T9870]  ? __smb2_plain_req_init+0x933/0x1090 [cifs]
[  750.438062] [   T9870]  smb2_async_writev+0x15ff/0x2460 [cifs]
[  750.438557] [   T9870]  ? sched_clock_noinstr+0x9/0x10
[  750.438906] [   T9870]  ? local_clock_noinstr+0xe/0xd0
[  750.439293] [   T9870]  ? __pfx_smb2_async_writev+0x10/0x10 [cifs]
[  750.439786] [   T9870]  ? __pfx__raw_spin_lock_irqsave+0x10/0x10
[  750.440143] [   T9870]  ? _raw_spin_unlock+0xe/0x40
[  750.440495] [   T9870]  ? cifs_pick_channel+0x242/0x370 [cifs]
[  750.440989] [   T9870]  cifs_issue_write+0x256/0x610 [cifs]
[  750.441492] [   T9870]  ? cifs_issue_write+0x256/0x610 [cifs]
[  750.441987] [   T9870]  netfs_do_issue_write+0xc2/0x340 [netfs]
[  750.442387] [   T9870]  netfs_advance_write+0x45b/0x1270 [netfs]
[  750.442969] [   T9870]  ? rolling_buffer_append+0x12d/0x440 [netfs]
[  750.443376] [   T9870]  netfs_write_folio+0xd6c/0x1be0 [netfs]
[  750.443768] [   T9870]  ? __kasan_check_write+0x14/0x30
[  750.444145] [   T9870]  netfs_writepages+0x2e9/0xa80 [netfs]
[  750.444541] [   T9870]  ? __pfx_netfs_writepages+0x10/0x10 [netfs]
[  750.444936] [   T9870]  ? exit_files+0xab/0xe0
[  750.445312] [   T9870]  ? do_exit+0x148f/0x2980
[  750.445672] [   T9870]  ? do_group_exit+0xb5/0x250
[  750.446028] [   T9870]  ? arch_do_signal_or_restart+0x92/0x630
[  750.446402] [   T9870]  ? exit_to_user_mode_loop+0x98/0x170
[  750.446762] [   T9870]  ? do_syscall_64+0x2cf/0xd80
[  750.447132] [   T9870]  ? entry_SYSCALL_64_after_hwframe+0x76/0x7e
[  750.447499] [   T9870]  do_writepages+0x21f/0x590
[  750.447859] [   T9870]  ? __pfx_do_writepages+0x10/0x10
[  750.448236] [   T9870]  filemap_fdatawrite_wbc+0xe1/0x140
[  750.448595] [   T9870]  __filemap_fdatawrite_range+0xba/0x100
[  750.448953] [   T9870]  ? __pfx___filemap_fdatawrite_range+0x10/0x10
[  750.449336] [   T9870]  ? __kasan_check_write+0x14/0x30
[  750.449697] [   T9870]  filemap_write_and_wait_range+0x7d/0xf0
[  750.450062] [   T9870]  cifs_flush+0x153/0x320 [cifs]
[  750.450592] [   T9870]  filp_flush+0x107/0x1a0
[  750.450952] [   T9870]  filp_close+0x14/0x30
[  750.451322] [   T9870]  put_files_struct.part.0+0x126/0x2a0
[  750.451678] [   T9870]  ? __pfx__raw_spin_lock+0x10/0x10
[  750.452033] [   T9870]  exit_files+0xab/0xe0
[  750.452401] [   T9870]  do_exit+0x148f/0x2980
[  750.452751] [   T9870]  ? __pfx_do_exit+0x10/0x10
[  750.453109] [   T9870]  ? __kasan_check_write+0x14/0x30
[  750.453459] [   T9870]  ? _raw_spin_lock_irq+0x8a/0xf0
[  750.453787] [   T9870]  do_group_exit+0xb5/0x250
[  750.454082] [   T9870]  get_signal+0x22d3/0x22e0
[  750.454406] [   T9870]  ? __pfx_get_signal+0x10/0x10
[  750.454709] [   T9870]  ? fpregs_assert_state_consistent+0x68/0x100
[  750.455031] [   T9870]  ? folio_add_lru+0xda/0x120
[  750.455347] [   T9870]  arch_do_signal_or_restart+0x92/0x630
[  750.455656] [   T9870]  ? __pfx_arch_do_signal_or_restart+0x10/0x10
[  750.455967] [   T9870]  exit_to_user_mode_loop+0x98/0x170
[  750.456282] [   T9870]  do_syscall_64+0x2cf/0xd80
[  750.456591] [   T9870]  ? __kasan_check_read+0x11/0x20
[  750.456897] [   T9870]  ? count_memcg_events+0x1b4/0x420
[  750.457280] [   T9870]  ? handle_mm_fault+0x148/0x690
[  750.457616] [   T9870]  ? _raw_spin_lock_irq+0x8a/0xf0
[  750.457925] [   T9870]  ? __kasan_check_read+0x11/0x20
[  750.458297] [   T9870]  ? fpregs_assert_state_consistent+0x68/0x100
[  750.458672] [   T9870]  ? irqentry_exit_to_user_mode+0x2e/0x250
[  750.459191] [   T9870]  ? irqentry_exit+0x43/0x50
[  750.459600] [   T9870]  ? exc_page_fault+0x75/0xe0
[  750.460130] [   T9870]  entry_SYSCALL_64_after_hwframe+0x76/0x7e
[  750.460570] [   T9870] RIP: 0033:0x7858c94ab6e2
[  750.461206] [   T9870] Code: Unable to access opcode bytes at 0x7858c94ab6b8.
[  750.461780] [   T9870] RSP: 002b:00007858c9248ce8 EFLAGS: 00000246 ORIG_RAX: 0000000000000022
[  750.462327] [   T9870] RAX: fffffffffffffdfe RBX: 00007858c92496c0 RCX: 00007858c94ab6e2
[  750.462653] [   T9870] RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000
[  750.462969] [   T9870] RBP: 00007858c9248d10 R08: 0000000000000000 R09: 0000000000000000
[  750.463290] [   T9870] R10: 0000000000000000 R11: 0000000000000246 R12: fffffffffffffde0
[  750.463640] [   T9870] R13: 0000000000000020 R14: 0000000000000002 R15: 00007ffc072d2230
[  750.463965] [   T9870]  </TASK>
[  750.464285] [   T9870] Modules linked in: siw ib_uverbs ccm cmac nls_utf8 cifs cifs_arc4 nls_ucs2_utils rdma_cm iw_cm ib_cm ib_core cifs_md4 netfs softdog vboxsf vboxguest cpuid intel_rapl_msr intel_rapl_common intel_uncore_frequency_common intel_pmc_core pmt_telemetry pmt_class intel_pmc_ssram_telemetry intel_vsec polyval_clmulni ghash_clmulni_intel sha1_ssse3 aesni_intel rapl i2c_piix4 i2c_smbus joydev input_leds mac_hid sunrpc binfmt_misc kvm_intel kvm irqbypass sch_fq_codel efi_pstore nfnetlink vsock_loopback vmw_vsock_virtio_transport_common vmw_vsock_vmci_transport vsock vmw_vmci dmi_sysfs ip_tables x_tables autofs4 hid_generic vboxvideo usbhid drm_vram_helper psmouse vga16fb vgastate drm_ttm_helper serio_raw hid ahci libahci ttm pata_acpi video wmi [last unloaded: vboxguest]
[  750.467127] [   T9870] CR2: ffff8880110a2000

cc: Tom Talpey <tom@talpey.com>
cc: linux-cifs@vger.kernel.org
Reviewed-by: David Howells <dhowells@redhat.com>
Reviewed-by: Tom Talpey <tom@talpey.com>
Fixes: c45ebd636c32 ("cifs: Provide the capability to extract from ITER_FOLIOQ to RDMA SGEs")
Signed-off-by: Stefan Metzmacher <metze@samba.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/smbdirect.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/fs/smb/client/smbdirect.c b/fs/smb/client/smbdirect.c
index 5ae847919da5..cbc85bca006f 100644
--- a/fs/smb/client/smbdirect.c
+++ b/fs/smb/client/smbdirect.c
@@ -2589,13 +2589,14 @@ static ssize_t smb_extract_folioq_to_rdma(struct iov_iter *iter,
 		size_t fsize = folioq_folio_size(folioq, slot);
 
 		if (offset < fsize) {
-			size_t part = umin(maxsize - ret, fsize - offset);
+			size_t part = umin(maxsize, fsize - offset);
 
 			if (!smb_set_sge(rdma, folio_page(folio, 0), offset, part))
 				return -EIO;
 
 			offset += part;
 			ret += part;
+			maxsize -= part;
 		}
 
 		if (offset >= fsize) {
@@ -2610,7 +2611,7 @@ static ssize_t smb_extract_folioq_to_rdma(struct iov_iter *iter,
 				slot = 0;
 			}
 		}
-	} while (rdma->nr_sge < rdma->max_sge || maxsize > 0);
+	} while (rdma->nr_sge < rdma->max_sge && maxsize > 0);
 
 	iter->folioq = folioq;
 	iter->folioq_slot = slot;

From 2c4fd3d141465ef1afc8318c95e7b916d9a8c49c Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Wed, 18 Jun 2025 16:39:47 +0100
Subject: [PATCH 0700/1334] cifs: Fix prepare_write to negotiate wsize if
 needed

Fix cifs_prepare_write() to negotiate the wsize if it is unset.

Reviewed-by: Shyam Prasad N <nspmangalore@gmail.com>
Reviewed-by: Bharath SM <bharathsm@microsoft.com>
Signed-off-by: David Howells <dhowells@redhat.com>
cc: Paulo Alcantara <pc@manguebit.org>
cc: netfs@lists.linux.dev
cc: linux-fsdevel@vger.kernel.org
cc: linux-cifs@vger.kernel.org
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/file.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c
index 9835672267d2..e9212da32f01 100644
--- a/fs/smb/client/file.c
+++ b/fs/smb/client/file.c
@@ -52,6 +52,7 @@ static void cifs_prepare_write(struct netfs_io_subrequest *subreq)
 	struct netfs_io_stream *stream = &req->rreq.io_streams[subreq->stream_nr];
 	struct TCP_Server_Info *server;
 	struct cifsFileInfo *open_file = req->cfile;
+	struct cifs_sb_info *cifs_sb = CIFS_SB(wdata->rreq->inode->i_sb);
 	size_t wsize = req->rreq.wsize;
 	int rc;
 
@@ -63,6 +64,10 @@ static void cifs_prepare_write(struct netfs_io_subrequest *subreq)
 	server = cifs_pick_channel(tlink_tcon(open_file->tlink)->ses);
 	wdata->server = server;
 
+	if (cifs_sb->ctx->wsize == 0)
+		cifs_negotiate_wsize(server, cifs_sb->ctx,
+				     tlink_tcon(req->cfile->tlink));
+
 retry:
 	if (open_file->invalidHandle) {
 		rc = cifs_reopen_file(open_file, false);
@@ -160,10 +165,9 @@ static int cifs_prepare_read(struct netfs_io_subrequest *subreq)
 	server = cifs_pick_channel(tlink_tcon(req->cfile->tlink)->ses);
 	rdata->server = server;
 
-	if (cifs_sb->ctx->rsize == 0) {
+	if (cifs_sb->ctx->rsize == 0)
 		cifs_negotiate_rsize(server, cifs_sb->ctx,
 				     tlink_tcon(req->cfile->tlink));
-	}
 
 	rc = server->ops->wait_mtu_credits(server, cifs_sb->ctx->rsize,
 					   &size, &rdata->credits);

From a2182743a8b4969481f64aec4908ff162e8a206c Mon Sep 17 00:00:00 2001
From: Paul Aurich <paul@darkrain42.org>
Date: Wed, 20 Nov 2024 08:01:54 -0800
Subject: [PATCH 0701/1334] smb: Log an error when close_all_cached_dirs fails

Under low-memory conditions, close_all_cached_dirs() can't move the
dentries to a separate list to dput() them once the locks are dropped.
This will result in a "Dentry still in use" error, so add an error
message that makes it clear this is what happened:

[  495.281119] CIFS: VFS: \\otters.example.com\share Out of memory while dropping dentries
[  495.281595] ------------[ cut here ]------------
[  495.281887] BUG: Dentry ffff888115531138{i=78,n=/}  still in use (2) [unmount of cifs cifs]
[  495.282391] WARNING: CPU: 1 PID: 2329 at fs/dcache.c:1536 umount_check+0xc8/0xf0

Also, bail out of looping through all tcons as soon as a single
allocation fails, since we're already in trouble, and kmalloc() attempts
for subseqeuent tcons are likely to fail just like the first one did.

Signed-off-by: Paul Aurich <paul@darkrain42.org>
Acked-by: Bharath SM <bharathsm@microsoft.com>
Suggested-by: Ruben Devos <rdevos@oxya.com>
Cc: stable@vger.kernel.org
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/cached_dir.c | 14 ++++++++++++--
 1 file changed, 12 insertions(+), 2 deletions(-)

diff --git a/fs/smb/client/cached_dir.c b/fs/smb/client/cached_dir.c
index 5200a0f3cafc..368e870624da 100644
--- a/fs/smb/client/cached_dir.c
+++ b/fs/smb/client/cached_dir.c
@@ -509,8 +509,17 @@ void close_all_cached_dirs(struct cifs_sb_info *cifs_sb)
 		spin_lock(&cfids->cfid_list_lock);
 		list_for_each_entry(cfid, &cfids->entries, entry) {
 			tmp_list = kmalloc(sizeof(*tmp_list), GFP_ATOMIC);
-			if (tmp_list == NULL)
-				break;
+			if (tmp_list == NULL) {
+				/*
+				 * If the malloc() fails, we won't drop all
+				 * dentries, and unmounting is likely to trigger
+				 * a 'Dentry still in use' error.
+				 */
+				cifs_tcon_dbg(VFS, "Out of memory while dropping dentries\n");
+				spin_unlock(&cfids->cfid_list_lock);
+				spin_unlock(&cifs_sb->tlink_tree_lock);
+				goto done;
+			}
 			spin_lock(&cfid->fid_lock);
 			tmp_list->dentry = cfid->dentry;
 			cfid->dentry = NULL;
@@ -522,6 +531,7 @@ void close_all_cached_dirs(struct cifs_sb_info *cifs_sb)
 	}
 	spin_unlock(&cifs_sb->tlink_tree_lock);
 
+done:
 	list_for_each_entry_safe(tmp_list, q, &entry, entry) {
 		list_del(&tmp_list->entry);
 		dput(tmp_list->dentry);

From 4eb11a34b72c86d559f437fdadc47e512bba41d2 Mon Sep 17 00:00:00 2001
From: Bharath SM <bharathsm@microsoft.com>
Date: Thu, 19 Jun 2025 21:05:32 +0530
Subject: [PATCH 0702/1334] smb: Use loff_t for directory position in
 cached_dirents

Change the pos field in struct cached_dirents from int to loff_t
to support large directory offsets. This avoids overflow and
matches kernel conventions for directory positions.

Reviewed-by: Paulo Alcantara (Red Hat) <pc@manguebit.org>
Signed-off-by: Bharath SM <bharathsm@microsoft.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/cached_dir.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/smb/client/cached_dir.h b/fs/smb/client/cached_dir.h
index bc8a812ff95f..a28f7cae3caa 100644
--- a/fs/smb/client/cached_dir.h
+++ b/fs/smb/client/cached_dir.h
@@ -26,7 +26,7 @@ struct cached_dirents {
 			    * open file instance.
 			    */
 	struct mutex de_mutex;
-	int pos;		 /* Expected ctx->pos */
+	loff_t pos;		 /* Expected ctx->pos */
 	struct list_head entries;
 };
 

From 4d360cfe8cbac3b62bd9e1df9889bde8a9d5b1d7 Mon Sep 17 00:00:00 2001
From: Bharath SM <bharathsm@microsoft.com>
Date: Thu, 19 Jun 2025 21:05:33 +0530
Subject: [PATCH 0703/1334] smb: minor fix to use sizeof to initialize
 flags_string buffer

Replaced hardcoded length with sizeof(flags_string).

Reviewed-by: Paulo Alcantara (Red Hat) <pc@manguebit.org>
Signed-off-by: Bharath SM <bharathsm@microsoft.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/cifs_debug.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/smb/client/cifs_debug.c b/fs/smb/client/cifs_debug.c
index c0196be0e65f..3fdf75737d43 100644
--- a/fs/smb/client/cifs_debug.c
+++ b/fs/smb/client/cifs_debug.c
@@ -1105,7 +1105,7 @@ static ssize_t cifs_security_flags_proc_write(struct file *file,
 	if ((count < 1) || (count > 11))
 		return -EINVAL;
 
-	memset(flags_string, 0, 12);
+	memset(flags_string, 0, sizeof(flags_string));
 
 	if (copy_from_user(flags_string, buffer, count))
 		return -EFAULT;

From 27e9d5d021dbaa1211836d07a240078bf84b284e Mon Sep 17 00:00:00 2001
From: Bharath SM <bharathsm@microsoft.com>
Date: Thu, 19 Jun 2025 21:05:34 +0530
Subject: [PATCH 0704/1334] smb: minor fix to use SMB2_NTLMV2_SESSKEY_SIZE for
 auth_key size

Replaced hardcoded value 16 with SMB2_NTLMV2_SESSKEY_SIZE
in the auth_key definition and memcpy call.

Reviewed-by: Paulo Alcantara (Red Hat) <pc@manguebit.org>
Signed-off-by: Bharath SM <bharathsm@microsoft.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/cifs_ioctl.h | 2 +-
 fs/smb/client/ioctl.c      | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/fs/smb/client/cifs_ioctl.h b/fs/smb/client/cifs_ioctl.h
index 26327442e383..b51ce64fcccf 100644
--- a/fs/smb/client/cifs_ioctl.h
+++ b/fs/smb/client/cifs_ioctl.h
@@ -61,7 +61,7 @@ struct smb_query_info {
 struct smb3_key_debug_info {
 	__u64	Suid;
 	__u16	cipher_type;
-	__u8	auth_key[16]; /* SMB2_NTLMV2_SESSKEY_SIZE */
+	__u8	auth_key[SMB2_NTLMV2_SESSKEY_SIZE];
 	__u8	smb3encryptionkey[SMB3_SIGN_KEY_SIZE];
 	__u8	smb3decryptionkey[SMB3_SIGN_KEY_SIZE];
 } __packed;
diff --git a/fs/smb/client/ioctl.c b/fs/smb/client/ioctl.c
index 56439da4f119..0a9935ce05a5 100644
--- a/fs/smb/client/ioctl.c
+++ b/fs/smb/client/ioctl.c
@@ -506,7 +506,7 @@ long cifs_ioctl(struct file *filep, unsigned int command, unsigned long arg)
 				le16_to_cpu(tcon->ses->server->cipher_type);
 			pkey_inf.Suid = tcon->ses->Suid;
 			memcpy(pkey_inf.auth_key, tcon->ses->auth_key.response,
-					16 /* SMB2_NTLMV2_SESSKEY_SIZE */);
+				  SMB2_NTLMV2_SESSKEY_SIZE);
 			memcpy(pkey_inf.smb3decryptionkey,
 			      tcon->ses->smb3decryptionkey, SMB3_SIGN_KEY_SIZE);
 			memcpy(pkey_inf.smb3encryptionkey,

From a6c23dac756b9541b33aa3bcd30f464df2879209 Mon Sep 17 00:00:00 2001
From: Alex Elder <elder@riscstar.com>
Date: Mon, 16 Jun 2025 07:51:36 -0500
Subject: [PATCH 0705/1334] i2c: k1: check for transfer error

If spacemit_i2c_xfer_msg() times out waiting for a message transfer to
complete, or if the hardware reports an error, it returns a negative
error code (-ETIMEDOUT, -EAGAIN, -ENXIO. or -EIO).

The sole caller of spacemit_i2c_xfer_msg() is spacemit_i2c_xfer(),
which is the i2c_algorithm->xfer callback function.  It currently
does not save the value returned by spacemit_i2c_xfer_msg().

The result is that transfer errors go unreported, and a caller
has no indication anything is wrong.

When this code was out for review, the return value *was* checked
in early versions.  But for some reason, that assignment got dropped
between versions 5 and 6 of the series, perhaps related to reworking
the code to merge spacemit_i2c_xfer_core() into spacemit_i2c_xfer().

Simply assigning the value returned to "ret" fixes the problem.

Fixes: 5ea558473fa31 ("i2c: spacemit: add support for SpacemiT K1 SoC")
Signed-off-by: Alex Elder <elder@riscstar.com>
Cc: <stable@vger.kernel.org> # v6.15+
Reviewed-by: Troy Mitchell <troymitchell988@gmail.com>
Link: https://lore.kernel.org/r/20250616125137.1555453-1-elder@riscstar.com
Signed-off-by: Andi Shyti <andi@smida.it>
Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
---
 drivers/i2c/busses/i2c-k1.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/i2c/busses/i2c-k1.c b/drivers/i2c/busses/i2c-k1.c
index 5965b4cf6220..b68a21fff0b5 100644
--- a/drivers/i2c/busses/i2c-k1.c
+++ b/drivers/i2c/busses/i2c-k1.c
@@ -477,7 +477,7 @@ static int spacemit_i2c_xfer(struct i2c_adapter *adapt, struct i2c_msg *msgs, in
 
 	ret = spacemit_i2c_wait_bus_idle(i2c);
 	if (!ret)
-		spacemit_i2c_xfer_msg(i2c);
+		ret = spacemit_i2c_xfer_msg(i2c);
 	else if (ret < 0)
 		dev_dbg(i2c->dev, "i2c transfer error: %d\n", ret);
 	else

From bb378314ceee4d181e26bfe180deca852ae80c5c Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Thu, 19 Jun 2025 16:51:32 -0400
Subject: [PATCH 0706/1334] bcachefs: Add missing bch2_err_class() to
 fileattr_set()

Make sure we return a standard error code.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/fs.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/fs/bcachefs/fs.c b/fs/bcachefs/fs.c
index 3063a8ddc2df..db24a76563f8 100644
--- a/fs/bcachefs/fs.c
+++ b/fs/bcachefs/fs.c
@@ -1732,7 +1732,8 @@ static int bch2_fileattr_set(struct mnt_idmap *idmap,
 		bch2_write_inode(c, inode, fssetxattr_inode_update_fn, &s,
 			       ATTR_CTIME);
 	mutex_unlock(&inode->ei_update_lock);
-	return ret;
+
+	return bch2_err_class(ret);
 }
 
 static const struct file_operations bch_file_operations = {

From abcb6bd4be19d935795611c022d7d19ab69363b0 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Thu, 19 Jun 2025 17:06:43 -0400
Subject: [PATCH 0707/1334] bcachefs: fix spurious error_throw

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/backpointers.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/bcachefs/backpointers.c b/fs/bcachefs/backpointers.c
index e76809e71858..77d93beb3c8f 100644
--- a/fs/bcachefs/backpointers.c
+++ b/fs/bcachefs/backpointers.c
@@ -353,7 +353,7 @@ static struct bkey_s_c __bch2_backpointer_get_key(struct btree_trans *trans,
 		return ret ? bkey_s_c_err(ret) : bkey_s_c_null;
 	} else {
 		struct btree *b = __bch2_backpointer_get_node(trans, bp, iter, last_flushed, commit);
-		if (b == ERR_PTR(bch_err_throw(c, backpointer_to_overwritten_btree_node)))
+		if (b == ERR_PTR(-BCH_ERR_backpointer_to_overwritten_btree_node))
 			return bkey_s_c_null;
 		if (IS_ERR_OR_NULL(b))
 			return ((struct bkey_s_c) { .k = ERR_CAST(b) });

From 72c0d9cb0fc48b6d382c3b5b6f702108a612cfdb Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Thu, 19 Jun 2025 23:06:01 -0400
Subject: [PATCH 0708/1334] bcachefs: Fix range in
 bch2_lookup_indirect_extent() error path

Before calling bch2_indirect_extent_missing_error(), we have to
calculate the missing range, which is the intersection of the reflink
pointer and the non-indirect-extent we found.

The calculation didn't take into account that the returned extent may
span the iter position, leading to an infinite loop when we
(unnecessarily) resized the extent we were returning to one that didn't
extend past the offset we were looking up.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/reflink.c | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/fs/bcachefs/reflink.c b/fs/bcachefs/reflink.c
index a535abd44df3..92b90cfe622b 100644
--- a/fs/bcachefs/reflink.c
+++ b/fs/bcachefs/reflink.c
@@ -64,6 +64,9 @@ void bch2_reflink_p_to_text(struct printbuf *out, struct bch_fs *c,
 	       REFLINK_P_IDX(p.v),
 	       le32_to_cpu(p.v->front_pad),
 	       le32_to_cpu(p.v->back_pad));
+
+	if (REFLINK_P_ERROR(p.v))
+		prt_str(out, " error");
 }
 
 bool bch2_reflink_p_merge(struct bch_fs *c, struct bkey_s _l, struct bkey_s_c _r)
@@ -269,13 +272,12 @@ struct bkey_s_c bch2_lookup_indirect_extent(struct btree_trans *trans,
 		return k;
 
 	if (unlikely(!bkey_extent_is_reflink_data(k.k))) {
-		unsigned size = min((u64) k.k->size,
-				    REFLINK_P_IDX(p.v) + p.k->size + le32_to_cpu(p.v->back_pad) -
-				    reflink_offset);
-		bch2_key_resize(&iter->k, size);
+		u64 missing_end = min(k.k->p.offset,
+				      REFLINK_P_IDX(p.v) + p.k->size + le32_to_cpu(p.v->back_pad));
+		BUG_ON(reflink_offset == missing_end);
 
 		int ret = bch2_indirect_extent_missing_error(trans, p, reflink_offset,
-							     k.k->p.offset, should_commit);
+							     missing_end, should_commit);
 		if (ret) {
 			bch2_trans_iter_exit(trans, iter);
 			return bkey_s_c_err(ret);

From e41687b511d5e5437db5d2151e23c115dba30411 Mon Sep 17 00:00:00 2001
From: Tim Crawford <tcrawford@system76.com>
Date: Fri, 20 Jun 2025 14:43:29 -0600
Subject: [PATCH 0709/1334] ALSA: hda/realtek: Add quirks for some Clevo
 laptops

Add audio quirks to fix speaker output and headset detection on the
following Clevo models:

- V350ENC
- V350WNPQ
- V540TU
- X560WNR
- X580WNS

Signed-off-by: Tim Crawford <tcrawford@system76.com>
Link: https://patch.msgid.link/20250620204329.35878-1-tcrawford@system76.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/patch_realtek.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 2e1618494c20..2149dcd34bc6 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -2656,6 +2656,7 @@ static const struct hda_quirk alc882_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x147b, 0x107a, "Abit AW9D-MAX", ALC882_FIXUP_ABIT_AW9D_MAX),
 	SND_PCI_QUIRK(0x1558, 0x3702, "Clevo X370SN[VW]", ALC1220_FIXUP_CLEVO_PB51ED_PINS),
 	SND_PCI_QUIRK(0x1558, 0x50d3, "Clevo PC50[ER][CDF]", ALC1220_FIXUP_CLEVO_PB51ED_PINS),
+	SND_PCI_QUIRK(0x1558, 0x5802, "Clevo X58[05]WN[RST]", ALC1220_FIXUP_CLEVO_PB51ED_PINS),
 	SND_PCI_QUIRK(0x1558, 0x65d1, "Clevo PB51[ER][CDF]", ALC1220_FIXUP_CLEVO_PB51ED_PINS),
 	SND_PCI_QUIRK(0x1558, 0x65d2, "Clevo PB51R[CDF]", ALC1220_FIXUP_CLEVO_PB51ED_PINS),
 	SND_PCI_QUIRK(0x1558, 0x65e1, "Clevo PB51[ED][DF]", ALC1220_FIXUP_CLEVO_PB51ED_PINS),
@@ -11135,6 +11136,8 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1558, 0x14a1, "Clevo L141MU", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1558, 0x2624, "Clevo L240TU", ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1558, 0x28c1, "Clevo V370VND", ALC2XX_FIXUP_HEADSET_MIC),
+	SND_PCI_QUIRK(0x1558, 0x35a1, "Clevo V3[56]0EN[CDE]", ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
+	SND_PCI_QUIRK(0x1558, 0x35b1, "Clevo V3[57]0WN[MNP]Q", ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1558, 0x4018, "Clevo NV40M[BE]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1558, 0x4019, "Clevo NV40MZ", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1558, 0x4020, "Clevo NV40MB", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
@@ -11162,6 +11165,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1558, 0x51b1, "Clevo NS50AU", ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1558, 0x51b3, "Clevo NS70AU", ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1558, 0x5630, "Clevo NP50RNJS", ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
+	SND_PCI_QUIRK(0x1558, 0x5700, "Clevo X560WN[RST]", ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1558, 0x70a1, "Clevo NB70T[HJK]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1558, 0x70b3, "Clevo NK70SB", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1558, 0x70f2, "Clevo NH79EPY", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
@@ -11201,6 +11205,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1558, 0xa650, "Clevo NP[567]0SN[CD]", ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1558, 0xa671, "Clevo NP70SN[CDE]", ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1558, 0xa741, "Clevo V54x_6x_TNE", ALC245_FIXUP_CLEVO_NOISY_MIC),
+	SND_PCI_QUIRK(0x1558, 0xa743, "Clevo V54x_6x_TU", ALC245_FIXUP_CLEVO_NOISY_MIC),
 	SND_PCI_QUIRK(0x1558, 0xa763, "Clevo V54x_6x_TU", ALC245_FIXUP_CLEVO_NOISY_MIC),
 	SND_PCI_QUIRK(0x1558, 0xb018, "Clevo NP50D[BE]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1558, 0xb019, "Clevo NH77D[BE]Q", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),

From 68cc9d3c8e44afe90e43cbbd2960da15c2f31e23 Mon Sep 17 00:00:00 2001
From: Yasmin Fitzgerald <sunoflife1.git@gmail.com>
Date: Sat, 21 Jun 2025 01:36:14 -0400
Subject: [PATCH 0710/1334] ALSA: hda/realtek - Enable mute LED on HP Pavilion
 Laptop 15-eg100

The HP Pavilion Laptop 15-eg100 has Realtek HDA codec ALC287.
It needs the ALC287_FIXUP_HP_GPIO_LED quirk to enable the mute LED.

Signed-off-by: Yasmin Fitzgerald <sunoflife1.git@gmail.com>
Link: https://patch.msgid.link/20250621053832.52950-1-sunoflife1.git@gmail.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/patch_realtek.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 2149dcd34bc6..e144ebb08841 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -10738,6 +10738,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x103c, 0x8975, "HP EliteBook x360 840 Aero G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x897d, "HP mt440 Mobile Thin Client U74", ALC236_FIXUP_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8981, "HP Elite Dragonfly G3", ALC245_FIXUP_CS35L41_SPI_4),
+	SND_PCI_QUIRK(0x103c, 0x898a, "HP Pavilion 15-eg100", ALC287_FIXUP_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x898e, "HP EliteBook 835 G9", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x103c, 0x898f, "HP EliteBook 835 G9", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x103c, 0x8991, "HP EliteBook 845 G9", ALC287_FIXUP_CS35L41_I2C_2_HP_GPIO_LED),

From 302251f1fdfd302ce99a619aac1a5164d0bb7c4b Mon Sep 17 00:00:00 2001
From: Faisal Bukhari <faisalbukhari523@gmail.com>
Date: Sat, 21 Jun 2025 16:02:04 +0530
Subject: [PATCH 0711/1334] Fix typo in marvell octeontx2 documentation
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Documentation/networking/device_drivers/ethernet/marvell/octeontx2.rst
Fixes a spelling mistake: "funcionality" → "functionality".

Signed-off-by: Faisal Bukhari <faisalbukhari523@gmail.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../networking/device_drivers/ethernet/marvell/octeontx2.rst    | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/networking/device_drivers/ethernet/marvell/octeontx2.rst b/Documentation/networking/device_drivers/ethernet/marvell/octeontx2.rst
index af7db0e91f6b..a52850602cd8 100644
--- a/Documentation/networking/device_drivers/ethernet/marvell/octeontx2.rst
+++ b/Documentation/networking/device_drivers/ethernet/marvell/octeontx2.rst
@@ -66,7 +66,7 @@ Admin Function driver
 As mentioned above RVU PF0 is called the admin function (AF), this driver
 supports resource provisioning and configuration of functional blocks.
 Doesn't handle any I/O. It sets up few basic stuff but most of the
-funcionality is achieved via configuration requests from PFs and VFs.
+functionality is achieved via configuration requests from PFs and VFs.
 
 PF/VFs communicates with AF via a shared memory region (mailbox). Upon
 receiving requests AF does resource provisioning and other HW configuration.

From b993ea46b3b601915ceaaf3c802adf11e7d6bac6 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 20 Jun 2025 14:28:44 +0000
Subject: [PATCH 0712/1334] atm: clip: prevent NULL deref in clip_push()

Blamed commit missed that vcc_destroy_socket() calls
clip_push() with a NULL skb.

If clip_devs is NULL, clip_push() then crashes when reading
skb->truesize.

Fixes: 93a2014afbac ("atm: fix a UAF in lec_arp_clear_vccs()")
Reported-by: syzbot+1316233c4c6803382a8b@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/netdev/68556f59.a00a0220.137b3.004e.GAE@google.com/T/#u
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Cong Wang <xiyou.wangcong@gmail.com>
Cc: Gengming Liu <l.dmxcsnsbh@gmail.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/atm/clip.c | 11 +++++------
 1 file changed, 5 insertions(+), 6 deletions(-)

diff --git a/net/atm/clip.c b/net/atm/clip.c
index 61b5b700817d..b234dc3bcb0d 100644
--- a/net/atm/clip.c
+++ b/net/atm/clip.c
@@ -193,12 +193,6 @@ static void clip_push(struct atm_vcc *vcc, struct sk_buff *skb)
 
 	pr_debug("\n");
 
-	if (!clip_devs) {
-		atm_return(vcc, skb->truesize);
-		kfree_skb(skb);
-		return;
-	}
-
 	if (!skb) {
 		pr_debug("removing VCC %p\n", clip_vcc);
 		if (clip_vcc->entry)
@@ -208,6 +202,11 @@ static void clip_push(struct atm_vcc *vcc, struct sk_buff *skb)
 		return;
 	}
 	atm_return(vcc, skb->truesize);
+	if (!clip_devs) {
+		kfree_skb(skb);
+		return;
+	}
+
 	skb->dev = clip_vcc->entry ? clip_vcc->entry->neigh->dev : clip_devs;
 	/* clip_vcc->entry == NULL if we don't have an IP address yet */
 	if (!skb->dev) {

From 86731a2a651e58953fc949573895f2fa6d456841 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Sun, 22 Jun 2025 13:30:08 -0700
Subject: [PATCH 0713/1334] Linux 6.16-rc3

---
 Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Makefile b/Makefile
index ba0827a1fccd..f884dfe10246 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
 VERSION = 6
 PATCHLEVEL = 16
 SUBLEVEL = 0
-EXTRAVERSION = -rc2
+EXTRAVERSION = -rc3
 NAME = Baby Opossum Posse
 
 # *DOCUMENTATION*

From 999fb9d51f939ee23cbb9313ae558d29d6987804 Mon Sep 17 00:00:00 2001
From: Luca Weiss <luca.weiss@fairphone.com>
Date: Tue, 17 Jun 2025 14:20:12 +0200
Subject: [PATCH 0714/1334] ASoC: qcom: sm8250: Fix possibly undefined
 reference

With CONFIG_SND_SOC_SM8250=y and CONFIG_SND_SOC_QCOM_OFFLOAD_UTILS=m
selected in kconfig, the build will fail due to trying to link against a
symbol only found in the module.

  aarch64-linux-gnu-ld: sound/soc/qcom/sm8250.o: in function `sm8250_snd_exit':
  sound/soc/qcom/sm8250.c:52:(.text+0x210): undefined reference to `qcom_snd_usb_offload_jack_remove'

Fix this by declaring the dependency that forces CONFIG_SND_SOC_SM8250=m
when CONFIG_SND_SOC_QCOM_OFFLOAD_UTILS is =m.

Reported-by: Matthew Croughan <matthew.croughan@nix.how>
Fixes: 1b8d0d87b934 ("ASoC: qcom: qdsp6: Add headphone jack for offload connection status")
Signed-off-by: Luca Weiss <luca.weiss@fairphone.com>
Link: https://patch.msgid.link/20250617-snd-sm8250-dep-fix-v1-1-879af8906ec4@fairphone.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/qcom/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/soc/qcom/Kconfig b/sound/soc/qcom/Kconfig
index e86b4a03dd61..3d9ba13ee1e5 100644
--- a/sound/soc/qcom/Kconfig
+++ b/sound/soc/qcom/Kconfig
@@ -186,6 +186,7 @@ config SND_SOC_SM8250
 	tristate "SoC Machine driver for SM8250 boards"
 	depends on QCOM_APR && SOUNDWIRE
 	depends on COMMON_CLK
+	depends on SND_SOC_QCOM_OFFLOAD_UTILS || !SND_SOC_QCOM_OFFLOAD_UTILS
 	select SND_SOC_QDSP6
 	select SND_SOC_QCOM_COMMON
 	select SND_SOC_QCOM_SDW

From 7186b81807b4a08f8bf834b6bdc72d6ed8ba1587 Mon Sep 17 00:00:00 2001
From: Yuzuru10 <yuzuru_10@proton.me>
Date: Sun, 22 Jun 2025 22:58:00 +0000
Subject: [PATCH 0715/1334] ASoC: amd: yc: add quirk for Acer Nitro ANV15-41
 internal mic

This patch adds DMI-based quirk for the Acer Nitro ANV15-41,
allowing the internal microphone to be detected correctly on
machines with "RB" as board vendor.

Signed-off-by: Yuzuru <yuzuru_10@proton.me>
Link: https://patch.msgid.link/20250622225754.20856-1-yuzuru_10@proton.me
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/amd/yc/acp6x-mach.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/sound/soc/amd/yc/acp6x-mach.c b/sound/soc/amd/yc/acp6x-mach.c
index 98022e5fd428..499f9f7c76ee 100644
--- a/sound/soc/amd/yc/acp6x-mach.c
+++ b/sound/soc/amd/yc/acp6x-mach.c
@@ -353,6 +353,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "83Q3"),
 		}
 	},
+	{
+		.driver_data = &acp6x_card,
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "RB"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Nitro ANV15-41"),
+		}
+	},
 	{
 		.driver_data = &acp6x_card,
 		.matches = {

From bf39286adc5e10ce3e32eb86ad316ae56f3b52a0 Mon Sep 17 00:00:00 2001
From: Oliver Schramm <oliver.schramm97@gmail.com>
Date: Sun, 22 Jun 2025 00:30:01 +0200
Subject: [PATCH 0716/1334] ASoC: amd: yc: Add DMI quirk for Lenovo IdeaPad
 Slim 5 15

It's smaller brother has already received the patch to enable the microphone,
now add it too to the DMI quirk table.

Cc: stable@vger.kernel.org
Signed-off-by: Oliver Schramm <oliver.schramm97@gmail.com>
Link: https://patch.msgid.link/20250621223000.11817-2-oliver.schramm97@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/amd/yc/acp6x-mach.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/sound/soc/amd/yc/acp6x-mach.c b/sound/soc/amd/yc/acp6x-mach.c
index 499f9f7c76ee..97e340140d0c 100644
--- a/sound/soc/amd/yc/acp6x-mach.c
+++ b/sound/soc/amd/yc/acp6x-mach.c
@@ -367,6 +367,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "83J2"),
 		}
 	},
+	{
+		.driver_data = &acp6x_card,
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "83J3"),
+		}
+	},
 	{
 		.driver_data = &acp6x_card,
 		.matches = {

From fb721b2c35b1829b8ecf62e3adb41cf30260316a Mon Sep 17 00:00:00 2001
From: Louis Chauvet <louis.chauvet@bootlin.com>
Date: Tue, 29 Apr 2025 10:36:23 +0200
Subject: [PATCH 0717/1334] drm: writeback: Fix drm_writeback_connector_cleanup
 signature
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The drm_writeback_connector_cleanup have the signature:

     static void drm_writeback_connector_cleanup(
		struct drm_device *dev,
		struct drm_writeback_connector *wb_connector)

But it is stored and used as a drmres_release_t

    typedef void (*drmres_release_t)(struct drm_device *dev, void *res);

While the current code is valid and does not produce any warning, the
CFI runtime check (CONFIG_CFI_CLANG) can fail because the function
signature is not the same as drmres_release_t.

In order to fix this, change the function signature to match what is
expected by drmres_release_t.

Fixes: 1914ba2b91ea ("drm: writeback: Create drmm variants for drm_writeback_connector initialization")

Suggested-by: Mark Yacoub <markyacoub@google.com>
Reviewed-by: Maíra Canal <mcanal@igalia.com>
Link: https://lore.kernel.org/r/20250429-drm-fix-writeback-cleanup-v2-1-548ff3a4e284@bootlin.com
Signed-off-by: Louis Chauvet <louis.chauvet@bootlin.com>
---
 drivers/gpu/drm/drm_writeback.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/drm_writeback.c b/drivers/gpu/drm/drm_writeback.c
index edbeab88ff2b..d983ee85cf13 100644
--- a/drivers/gpu/drm/drm_writeback.c
+++ b/drivers/gpu/drm/drm_writeback.c
@@ -343,17 +343,18 @@ EXPORT_SYMBOL(drm_writeback_connector_init_with_encoder);
 /**
  * drm_writeback_connector_cleanup - Cleanup the writeback connector
  * @dev: DRM device
- * @wb_connector: Pointer to the writeback connector to clean up
+ * @data: Pointer to the writeback connector to clean up
  *
  * This will decrement the reference counter of blobs and destroy properties. It
  * will also clean the remaining jobs in this writeback connector. Caution: This helper will not
  * clean up the attached encoder and the drm_connector.
  */
 static void drm_writeback_connector_cleanup(struct drm_device *dev,
-					    struct drm_writeback_connector *wb_connector)
+					    void *data)
 {
 	unsigned long flags;
 	struct drm_writeback_job *pos, *n;
+	struct drm_writeback_connector *wb_connector = data;
 
 	delete_writeback_properties(dev);
 	drm_property_blob_put(wb_connector->pixel_formats_blob_ptr);
@@ -405,7 +406,7 @@ int drmm_writeback_connector_init(struct drm_device *dev,
 	if (ret)
 		return ret;
 
-	ret = drmm_add_action_or_reset(dev, (void *)drm_writeback_connector_cleanup,
+	ret = drmm_add_action_or_reset(dev, drm_writeback_connector_cleanup,
 				       wb_connector);
 	if (ret)
 		return ret;

From 20d71750cc72e80859d52548cf5c2a7513983b0d Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Fri, 20 Jun 2025 20:15:03 +0800
Subject: [PATCH 0718/1334] crypto: wp512 - Use API partial block handling

Use the Crypto API partial block handling.

Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Tested-by: Milan Broz <gmazyland@gmail.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 crypto/wp512.c | 125 +++++++++++++++++++------------------------------
 1 file changed, 47 insertions(+), 78 deletions(-)

diff --git a/crypto/wp512.c b/crypto/wp512.c
index 41f13d490333..229b189a7988 100644
--- a/crypto/wp512.c
+++ b/crypto/wp512.c
@@ -21,10 +21,10 @@
  */
 #include <crypto/internal/hash.h>
 #include <linux/init.h>
+#include <linux/kernel.h>
 #include <linux/module.h>
-#include <linux/mm.h>
-#include <asm/byteorder.h>
-#include <linux/types.h>
+#include <linux/string.h>
+#include <linux/unaligned.h>
 
 #define WP512_DIGEST_SIZE 64
 #define WP384_DIGEST_SIZE 48
@@ -37,9 +37,6 @@
 
 struct wp512_ctx {
 	u8  bitLength[WP512_LENGTHBYTES];
-	u8  buffer[WP512_BLOCK_SIZE];
-	int bufferBits;
-	int bufferPos;
 	u64 hash[WP512_DIGEST_SIZE/8];
 };
 
@@ -779,16 +776,16 @@ static const u64 rc[WHIRLPOOL_ROUNDS] = {
  * The core Whirlpool transform.
  */
 
-static __no_kmsan_checks void wp512_process_buffer(struct wp512_ctx *wctx) {
+static __no_kmsan_checks void wp512_process_buffer(struct wp512_ctx *wctx,
+						   const u8 *buffer) {
 	int i, r;
 	u64 K[8];        /* the round key */
 	u64 block[8];    /* mu(buffer) */
 	u64 state[8];    /* the cipher state */
 	u64 L[8];
-	const __be64 *buffer = (const __be64 *)wctx->buffer;
 
 	for (i = 0; i < 8; i++)
-		block[i] = be64_to_cpu(buffer[i]);
+		block[i] = get_unaligned_be64(buffer + i * 8);
 
 	state[0] = block[0] ^ (K[0] = wctx->hash[0]);
 	state[1] = block[1] ^ (K[1] = wctx->hash[1]);
@@ -991,8 +988,6 @@ static int wp512_init(struct shash_desc *desc) {
 	int i;
 
 	memset(wctx->bitLength, 0, 32);
-	wctx->bufferBits = wctx->bufferPos = 0;
-	wctx->buffer[0] = 0;
 	for (i = 0; i < 8; i++) {
 		wctx->hash[i] = 0L;
 	}
@@ -1000,84 +995,54 @@ static int wp512_init(struct shash_desc *desc) {
 	return 0;
 }
 
-static int wp512_update(struct shash_desc *desc, const u8 *source,
-			 unsigned int len)
+static void wp512_add_length(u8 *bitLength, u64 value)
 {
-	struct wp512_ctx *wctx = shash_desc_ctx(desc);
-	int sourcePos    = 0;
-	unsigned int bits_len = len * 8; // convert to number of bits
-	int sourceGap    = (8 - ((int)bits_len & 7)) & 7;
-	int bufferRem    = wctx->bufferBits & 7;
+	u32 carry;
 	int i;
-	u32 b, carry;
-	u8 *buffer       = wctx->buffer;
-	u8 *bitLength    = wctx->bitLength;
-	int bufferBits   = wctx->bufferBits;
-	int bufferPos    = wctx->bufferPos;
 
-	u64 value = bits_len;
 	for (i = 31, carry = 0; i >= 0 && (carry != 0 || value != 0ULL); i--) {
 		carry += bitLength[i] + ((u32)value & 0xff);
 		bitLength[i] = (u8)carry;
 		carry >>= 8;
 		value >>= 8;
 	}
-	while (bits_len > 8) {
-		b = ((source[sourcePos] << sourceGap) & 0xff) |
-		((source[sourcePos + 1] & 0xff) >> (8 - sourceGap));
-		buffer[bufferPos++] |= (u8)(b >> bufferRem);
-		bufferBits += 8 - bufferRem;
-		if (bufferBits == WP512_BLOCK_SIZE * 8) {
-			wp512_process_buffer(wctx);
-			bufferBits = bufferPos = 0;
-		}
-		buffer[bufferPos] = b << (8 - bufferRem);
-		bufferBits += bufferRem;
-		bits_len -= 8;
-		sourcePos++;
-	}
-	if (bits_len > 0) {
-		b = (source[sourcePos] << sourceGap) & 0xff;
-		buffer[bufferPos] |= b >> bufferRem;
-	} else {
-		b = 0;
-	}
-	if (bufferRem + bits_len < 8) {
-		bufferBits += bits_len;
-	} else {
-		bufferPos++;
-		bufferBits += 8 - bufferRem;
-		bits_len -= 8 - bufferRem;
-		if (bufferBits == WP512_BLOCK_SIZE * 8) {
-			wp512_process_buffer(wctx);
-			bufferBits = bufferPos = 0;
-		}
-		buffer[bufferPos] = b << (8 - bufferRem);
-		bufferBits += (int)bits_len;
-	}
-
-	wctx->bufferBits   = bufferBits;
-	wctx->bufferPos    = bufferPos;
-
-	return 0;
 }
 
-static int wp512_final(struct shash_desc *desc, u8 *out)
+static int wp512_update(struct shash_desc *desc, const u8 *source,
+			 unsigned int len)
+{
+	struct wp512_ctx *wctx = shash_desc_ctx(desc);
+	unsigned int remain = len % WP512_BLOCK_SIZE;
+	u64 bits_len = (len - remain) * 8ull;
+	u8 *bitLength    = wctx->bitLength;
+
+	wp512_add_length(bitLength, bits_len);
+	do {
+		wp512_process_buffer(wctx, source);
+		source += WP512_BLOCK_SIZE;
+		bits_len -= WP512_BLOCK_SIZE * 8;
+	} while (bits_len);
+
+	return remain;
+}
+
+static int wp512_finup(struct shash_desc *desc, const u8 *src,
+		       unsigned int bufferPos, u8 *out)
 {
 	struct wp512_ctx *wctx = shash_desc_ctx(desc);
 	int i;
-	u8 *buffer      = wctx->buffer;
 	u8 *bitLength   = wctx->bitLength;
-	int bufferBits  = wctx->bufferBits;
-	int bufferPos   = wctx->bufferPos;
 	__be64 *digest  = (__be64 *)out;
+	u8 buffer[WP512_BLOCK_SIZE];
 
-	buffer[bufferPos] |= 0x80U >> (bufferBits & 7);
+	wp512_add_length(bitLength, bufferPos * 8);
+	memcpy(buffer, src, bufferPos);
+	buffer[bufferPos] = 0x80U;
 	bufferPos++;
 	if (bufferPos > WP512_BLOCK_SIZE - WP512_LENGTHBYTES) {
 		if (bufferPos < WP512_BLOCK_SIZE)
 			memset(&buffer[bufferPos], 0, WP512_BLOCK_SIZE - bufferPos);
-		wp512_process_buffer(wctx);
+		wp512_process_buffer(wctx, buffer);
 		bufferPos = 0;
 	}
 	if (bufferPos < WP512_BLOCK_SIZE - WP512_LENGTHBYTES)
@@ -1086,31 +1051,32 @@ static int wp512_final(struct shash_desc *desc, u8 *out)
 	bufferPos = WP512_BLOCK_SIZE - WP512_LENGTHBYTES;
 	memcpy(&buffer[WP512_BLOCK_SIZE - WP512_LENGTHBYTES],
 		   bitLength, WP512_LENGTHBYTES);
-	wp512_process_buffer(wctx);
+	wp512_process_buffer(wctx, buffer);
+	memzero_explicit(buffer, sizeof(buffer));
 	for (i = 0; i < WP512_DIGEST_SIZE/8; i++)
 		digest[i] = cpu_to_be64(wctx->hash[i]);
-	wctx->bufferBits   = bufferBits;
-	wctx->bufferPos    = bufferPos;
 
 	return 0;
 }
 
-static int wp384_final(struct shash_desc *desc, u8 *out)
+static int wp384_finup(struct shash_desc *desc, const u8 *src,
+		       unsigned int len, u8 *out)
 {
 	u8 D[64];
 
-	wp512_final(desc, D);
+	wp512_finup(desc, src, len, D);
 	memcpy(out, D, WP384_DIGEST_SIZE);
 	memzero_explicit(D, WP512_DIGEST_SIZE);
 
 	return 0;
 }
 
-static int wp256_final(struct shash_desc *desc, u8 *out)
+static int wp256_finup(struct shash_desc *desc, const u8 *src,
+		       unsigned int len, u8 *out)
 {
 	u8 D[64];
 
-	wp512_final(desc, D);
+	wp512_finup(desc, src, len, D);
 	memcpy(out, D, WP256_DIGEST_SIZE);
 	memzero_explicit(D, WP512_DIGEST_SIZE);
 
@@ -1121,11 +1087,12 @@ static struct shash_alg wp_algs[3] = { {
 	.digestsize	=	WP512_DIGEST_SIZE,
 	.init		=	wp512_init,
 	.update		=	wp512_update,
-	.final		=	wp512_final,
+	.finup		=	wp512_finup,
 	.descsize	=	sizeof(struct wp512_ctx),
 	.base		=	{
 		.cra_name	 =	"wp512",
 		.cra_driver_name =	"wp512-generic",
+		.cra_flags	 =	CRYPTO_AHASH_ALG_BLOCK_ONLY,
 		.cra_blocksize	 =	WP512_BLOCK_SIZE,
 		.cra_module	 =	THIS_MODULE,
 	}
@@ -1133,11 +1100,12 @@ static struct shash_alg wp_algs[3] = { {
 	.digestsize	=	WP384_DIGEST_SIZE,
 	.init		=	wp512_init,
 	.update		=	wp512_update,
-	.final		=	wp384_final,
+	.finup		=	wp384_finup,
 	.descsize	=	sizeof(struct wp512_ctx),
 	.base		=	{
 		.cra_name	 =	"wp384",
 		.cra_driver_name =	"wp384-generic",
+		.cra_flags	 =	CRYPTO_AHASH_ALG_BLOCK_ONLY,
 		.cra_blocksize	 =	WP512_BLOCK_SIZE,
 		.cra_module	 =	THIS_MODULE,
 	}
@@ -1145,11 +1113,12 @@ static struct shash_alg wp_algs[3] = { {
 	.digestsize	=	WP256_DIGEST_SIZE,
 	.init		=	wp512_init,
 	.update		=	wp512_update,
-	.final		=	wp256_final,
+	.finup		=	wp256_finup,
 	.descsize	=	sizeof(struct wp512_ctx),
 	.base		=	{
 		.cra_name	 =	"wp256",
 		.cra_driver_name =	"wp256-generic",
+		.cra_flags	 =	CRYPTO_AHASH_ALG_BLOCK_ONLY,
 		.cra_blocksize	 =	WP512_BLOCK_SIZE,
 		.cra_module	 =	THIS_MODULE,
 	}

From 6a68d28066b6257b8d09b1daa91db43d56dbb6ad Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Fri, 20 Jun 2025 13:02:52 +0200
Subject: [PATCH 0719/1334] selftests/coredump: Fix
 "socket_detect_userspace_client" test failure

The coredump.socket_detect_userspace_client test occasionally fails:
    #  RUN           coredump.socket_detect_userspace_client ...
    # stackdump_test.c:500:socket_detect_userspace_client:Expected 0 (0) != WIFEXITED(status) (0)
    # socket_detect_userspace_client: Test terminated by assertion
    #          FAIL  coredump.socket_detect_userspace_client
    not ok 3 coredump.socket_detect_userspace_client

because there is no guarantee that client's write() happens before server's
close(). The client gets terminated SIGPIPE, and thus the test fails.

Add a read() to server to make sure server's close() doesn't happen before
client's write().

Fixes: 7b6724fe9a6b ("selftests/coredump: add tests for AF_UNIX coredumps")
Signed-off-by: Nam Cao <namcao@linutronix.de>
Link: https://lore.kernel.org/20250620110252.1640391-1-namcao@linutronix.de
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 tools/testing/selftests/coredump/stackdump_test.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/tools/testing/selftests/coredump/stackdump_test.c b/tools/testing/selftests/coredump/stackdump_test.c
index 9984413be9f0..68f8e479ac36 100644
--- a/tools/testing/selftests/coredump/stackdump_test.c
+++ b/tools/testing/selftests/coredump/stackdump_test.c
@@ -461,10 +461,15 @@ TEST_F(coredump, socket_detect_userspace_client)
 			_exit(EXIT_FAILURE);
 		}
 
+		ret = read(fd_coredump, &c, 1);
+
 		close(fd_coredump);
 		close(fd_server);
 		close(fd_peer_pidfd);
 		close(fd_core_file);
+
+		if (ret < 1)
+			_exit(EXIT_FAILURE);
 		_exit(EXIT_SUCCESS);
 	}
 	self->pid_coredump_server = pid_coredump_server;

From cbe4134ea4bc493239786220bd69cb8a13493190 Mon Sep 17 00:00:00 2001
From: Shivank Garg <shivankg@amd.com>
Date: Fri, 20 Jun 2025 07:03:30 +0000
Subject: [PATCH 0720/1334] fs: export anon_inode_make_secure_inode() and fix
 secretmem LSM bypass

Export anon_inode_make_secure_inode() to allow KVM guest_memfd to create
anonymous inodes with proper security context. This replaces the current
pattern of calling alloc_anon_inode() followed by
inode_init_security_anon() for creating security context manually.

This change also fixes a security regression in secretmem where the
S_PRIVATE flag was not cleared after alloc_anon_inode(), causing
LSM/SELinux checks to be bypassed for secretmem file descriptors.

As guest_memfd currently resides in the KVM module, we need to export this
symbol for use outside the core kernel. In the future, guest_memfd might be
moved to core-mm, at which point the symbols no longer would have to be
exported. When/if that happens is still unclear.

Fixes: 2bfe15c52612 ("mm: create security context for memfd_secret inodes")
Suggested-by: David Hildenbrand <david@redhat.com>
Suggested-by: Mike Rapoport <rppt@kernel.org>
Signed-off-by: Shivank Garg <shivankg@amd.com>
Link: https://lore.kernel.org/20250620070328.803704-3-shivankg@amd.com
Acked-by: "Mike Rapoport (Microsoft)" <rppt@kernel.org>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/anon_inodes.c   | 23 ++++++++++++++++++-----
 include/linux/fs.h |  2 ++
 mm/secretmem.c     |  9 +--------
 3 files changed, 21 insertions(+), 13 deletions(-)

diff --git a/fs/anon_inodes.c b/fs/anon_inodes.c
index e51e7d88980a..1d847a939f29 100644
--- a/fs/anon_inodes.c
+++ b/fs/anon_inodes.c
@@ -98,14 +98,25 @@ static struct file_system_type anon_inode_fs_type = {
 	.kill_sb	= kill_anon_super,
 };
 
-static struct inode *anon_inode_make_secure_inode(
-	const char *name,
-	const struct inode *context_inode)
+/**
+ * anon_inode_make_secure_inode - allocate an anonymous inode with security context
+ * @sb:		[in]	Superblock to allocate from
+ * @name:	[in]	Name of the class of the newfile (e.g., "secretmem")
+ * @context_inode:
+ *		[in]	Optional parent inode for security inheritance
+ *
+ * The function ensures proper security initialization through the LSM hook
+ * security_inode_init_security_anon().
+ *
+ * Return:	Pointer to new inode on success, ERR_PTR on failure.
+ */
+struct inode *anon_inode_make_secure_inode(struct super_block *sb, const char *name,
+					   const struct inode *context_inode)
 {
 	struct inode *inode;
 	int error;
 
-	inode = alloc_anon_inode(anon_inode_mnt->mnt_sb);
+	inode = alloc_anon_inode(sb);
 	if (IS_ERR(inode))
 		return inode;
 	inode->i_flags &= ~S_PRIVATE;
@@ -118,6 +129,7 @@ static struct inode *anon_inode_make_secure_inode(
 	}
 	return inode;
 }
+EXPORT_SYMBOL_GPL_FOR_MODULES(anon_inode_make_secure_inode, "kvm");
 
 static struct file *__anon_inode_getfile(const char *name,
 					 const struct file_operations *fops,
@@ -132,7 +144,8 @@ static struct file *__anon_inode_getfile(const char *name,
 		return ERR_PTR(-ENOENT);
 
 	if (make_inode) {
-		inode =	anon_inode_make_secure_inode(name, context_inode);
+		inode =	anon_inode_make_secure_inode(anon_inode_mnt->mnt_sb,
+						     name, context_inode);
 		if (IS_ERR(inode)) {
 			file = ERR_CAST(inode);
 			goto err;
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 4ec77da65f14..3a8e643c4279 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -3606,6 +3606,8 @@ extern int simple_write_begin(struct file *file, struct address_space *mapping,
 extern const struct address_space_operations ram_aops;
 extern int always_delete_dentry(const struct dentry *);
 extern struct inode *alloc_anon_inode(struct super_block *);
+struct inode *anon_inode_make_secure_inode(struct super_block *sb, const char *name,
+					   const struct inode *context_inode);
 extern int simple_nosetlease(struct file *, int, struct file_lease **, void **);
 extern const struct dentry_operations simple_dentry_operations;
 
diff --git a/mm/secretmem.c b/mm/secretmem.c
index 589b26c2d553..9a11a38a6770 100644
--- a/mm/secretmem.c
+++ b/mm/secretmem.c
@@ -195,18 +195,11 @@ static struct file *secretmem_file_create(unsigned long flags)
 	struct file *file;
 	struct inode *inode;
 	const char *anon_name = "[secretmem]";
-	int err;
 
-	inode = alloc_anon_inode(secretmem_mnt->mnt_sb);
+	inode = anon_inode_make_secure_inode(secretmem_mnt->mnt_sb, anon_name, NULL);
 	if (IS_ERR(inode))
 		return ERR_CAST(inode);
 
-	err = security_inode_init_security_anon(inode, &QSTR(anon_name), NULL);
-	if (err) {
-		file = ERR_PTR(err);
-		goto err_free_inode;
-	}
-
 	file = alloc_file_pseudo(inode, secretmem_mnt, "secretmem",
 				 O_RDWR, &secretmem_fops);
 	if (IS_ERR(file))

From b872f562c8cef59743993b48eb458c2d87c1651e Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Mon, 23 Jun 2025 19:11:50 +0800
Subject: [PATCH 0721/1334] dm-crypt: Extend state buffer size in
 crypt_iv_lmk_one

Add a macro CRYPTO_MD5_STATESIZE for the Crypto API export state
size of md5 and use that in dm-crypt instead of relying on the
size of struct md5_state (the latter is currently undergoing a
transition and may shrink).

This commit fixes a crash on 32-bit machines:
Oops: Oops: 0000 [#1] SMP
CPU: 1 UID: 0 PID: 12 Comm: kworker/u16:0 Not tainted 6.16.0-rc2+ #993 PREEMPT(full)
Hardware name: VMware, Inc. VMware Virtual Platform/440BX Desktop Reference Platform, BIOS 6.00 11/12/2020
Workqueue: kcryptd-254:0-1 kcryptd_crypt [dm_crypt]
EIP: __crypto_shash_export+0xf/0x90
Code: 4a c1 c7 40 20 a0 b4 4a c1 81 cf 0e 00 04 08 89 78 50 e9 2b ff ff ff 8d 74 26 00 55 89 e5 57 56 53 89 c3 89 d6 8b 00 8b 40 14 <8b> 50 fc f6 40 13 01 74 04 4a 2b 50 14 85 c9 74 10 89 f2 89 d8 ff
EAX: 303a3435 EBX: c3007c90 ECX: 00000000 EDX: c3007c38
ESI: c3007c38 EDI: c3007c90 EBP: c3007bfc ESP: c3007bf0
DS: 007b ES: 007b FS: 00d8 GS: 0000 SS: 0068 EFLAGS: 00010216
CR0: 80050033 CR2: 303a3431 CR3: 04fbe000 CR4: 00350e90
Call Trace:
 crypto_shash_export+0x65/0xc0
 crypt_iv_lmk_one+0x106/0x1a0 [dm_crypt]

Fixes: efd62c85525e ("crypto: md5-generic - Use API partial block handling")
Reported-by: Milan Broz <gmazyland@gmail.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Tested-by: Milan Broz <gmazyland@gmail.com>
Closes: https://lore.kernel.org/linux-crypto/f1625ddc-e82e-4b77-80c2-dc8e45b54848@gmail.com/T/
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
---
 drivers/md/dm-crypt.c | 11 +++++++----
 include/crypto/hash.h |  2 ++
 include/crypto/md5.h  |  4 ++++
 3 files changed, 13 insertions(+), 4 deletions(-)

diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index 9dfdb63220d7..17157c4216a5 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -517,7 +517,10 @@ static int crypt_iv_lmk_one(struct crypt_config *cc, u8 *iv,
 {
 	struct iv_lmk_private *lmk = &cc->iv_gen_private.lmk;
 	SHASH_DESC_ON_STACK(desc, lmk->hash_tfm);
-	struct md5_state md5state;
+	union {
+		struct md5_state md5state;
+		u8 state[CRYPTO_MD5_STATESIZE];
+	} u;
 	__le32 buf[4];
 	int i, r;
 
@@ -548,13 +551,13 @@ static int crypt_iv_lmk_one(struct crypt_config *cc, u8 *iv,
 		return r;
 
 	/* No MD5 padding here */
-	r = crypto_shash_export(desc, &md5state);
+	r = crypto_shash_export(desc, &u.md5state);
 	if (r)
 		return r;
 
 	for (i = 0; i < MD5_HASH_WORDS; i++)
-		__cpu_to_le32s(&md5state.hash[i]);
-	memcpy(iv, &md5state.hash, cc->iv_size);
+		__cpu_to_le32s(&u.md5state.hash[i]);
+	memcpy(iv, &u.md5state.hash, cc->iv_size);
 
 	return 0;
 }
diff --git a/include/crypto/hash.h b/include/crypto/hash.h
index 6f6b9de12cd3..db294d452e8c 100644
--- a/include/crypto/hash.h
+++ b/include/crypto/hash.h
@@ -202,6 +202,8 @@ struct shash_desc {
 #define HASH_REQUEST_CLONE(name, gfp) \
 	hash_request_clone(name, sizeof(__##name##_req), gfp)
 
+#define CRYPTO_HASH_STATESIZE(coresize, blocksize) (coresize + blocksize + 1)
+
 /**
  * struct shash_alg - synchronous message digest definition
  * @init: see struct ahash_alg
diff --git a/include/crypto/md5.h b/include/crypto/md5.h
index 198b5d69b92f..28ee533a0507 100644
--- a/include/crypto/md5.h
+++ b/include/crypto/md5.h
@@ -2,6 +2,7 @@
 #ifndef _CRYPTO_MD5_H
 #define _CRYPTO_MD5_H
 
+#include <crypto/hash.h>
 #include <linux/types.h>
 
 #define MD5_DIGEST_SIZE		16
@@ -15,6 +16,9 @@
 #define MD5_H2	0x98badcfeUL
 #define MD5_H3	0x10325476UL
 
+#define CRYPTO_MD5_STATESIZE \
+	CRYPTO_HASH_STATESIZE(MD5_STATE_SIZE, MD5_HMAC_BLOCK_SIZE)
+
 extern const u8 md5_zero_message_hash[MD5_DIGEST_SIZE];
 
 struct md5_state {

From 9205999e9f13a07cb29d5a8836c25afdca186007 Mon Sep 17 00:00:00 2001
From: Ankit Nautiyal <ankit.k.nautiyal@intel.com>
Date: Wed, 18 Jun 2025 18:39:50 +0530
Subject: [PATCH 0722/1334] drm/i915/snps_hdmi_pll: Fix 64-bit divisor
 truncation by using div64_u64

DIV_ROUND_CLOSEST_ULL uses do_div(), which expects a 32-bit divisor.
When passing a 64-bit constant like CURVE2_MULTIPLIER, the value is
silently truncated to u32, potentially leading to incorrect results
on large divisors.

Replace DIV_ROUND_CLOSEST_ULL with DIV64_U64_ROUND_CLOSEST which correctly
handles full 64-bit division.

v2: Use DIV64_U64_ROUND_CLOSEST instead of div64_u64 macro. (Jani)

Fixes: 5947642004bf ("drm/i915/display: Add support for SNPS PHY HDMI PLL algorithm for DG2")
Reported-by: Vas Novikov <vasya.novikov@gmail.com>
Closes: https://lore.kernel.org/all/8d7c7958-9558-4c8a-a81a-e9310f2d8852@gmail.com/
Cc: Ankit Nautiyal <ankit.k.nautiyal@intel.com>
Cc: Suraj Kandpal <suraj.kandpal@intel.com>
Cc: Jani Nikula <jani.nikula@intel.com>
Cc: Vas Novikov <vasya.novikov@gmail.com>
Cc: stable@vger.kernel.org # v6.15+
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Ankit Nautiyal <ankit.k.nautiyal@intel.com>
Link: https://lore.kernel.org/r/20250618130951.1596587-2-ankit.k.nautiyal@intel.com
(cherry picked from commit b300a175a11e6a934d728317dc39787723cc7917)
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
---
 drivers/gpu/drm/i915/display/intel_snps_hdmi_pll.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_snps_hdmi_pll.c b/drivers/gpu/drm/i915/display/intel_snps_hdmi_pll.c
index 74bb3bedf30f..5111bdc3075b 100644
--- a/drivers/gpu/drm/i915/display/intel_snps_hdmi_pll.c
+++ b/drivers/gpu/drm/i915/display/intel_snps_hdmi_pll.c
@@ -103,8 +103,8 @@ static void get_ana_cp_int_prop(u64 vco_clk,
 			    DIV_ROUND_DOWN_ULL(curve_1_interpolated, CURVE0_MULTIPLIER)));
 
 	ana_cp_int_temp =
-		DIV_ROUND_CLOSEST_ULL(DIV_ROUND_DOWN_ULL(adjusted_vco_clk1, curve_2_scaled1),
-				      CURVE2_MULTIPLIER);
+		DIV64_U64_ROUND_CLOSEST(DIV_ROUND_DOWN_ULL(adjusted_vco_clk1, curve_2_scaled1),
+					CURVE2_MULTIPLIER);
 
 	*ana_cp_int = max(1, min(ana_cp_int_temp, 127));
 

From a24cc6ce1933eade12aa2b9859de0fcd2dac2c06 Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Mon, 23 Jun 2025 10:34:08 +0200
Subject: [PATCH 0723/1334] futex: Initialize futex_phash_new during fork().

During a hash resize operation the new private hash is stored in
mm_struct::futex_phash_new if the current hash can not be immediately
replaced.

The new hash must not be copied during fork() into the new task. Doing
so will lead to a double-free of the memory by the two tasks.

Initialize the mm_struct::futex_phash_new during fork().

Closes: https://lore.kernel.org/all/aFBQ8CBKmRzEqIfS@mozart.vkv.me/
Fixes: bd54df5ea7cad ("futex: Allow to resize the private local hash")
Reported-by: Calvin Owens <calvin@wbinvd.org>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Calvin Owens <calvin@wbinvd.org>
Link: https://lkml.kernel.org/r/20250623083408.jTiJiC6_@linutronix.de
---
 include/linux/futex.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/include/linux/futex.h b/include/linux/futex.h
index 005b040c4791..b37193653e6b 100644
--- a/include/linux/futex.h
+++ b/include/linux/futex.h
@@ -89,6 +89,7 @@ void futex_hash_free(struct mm_struct *mm);
 static inline void futex_mm_init(struct mm_struct *mm)
 {
 	RCU_INIT_POINTER(mm->futex_phash, NULL);
+	mm->futex_phash_new = NULL;
 	mutex_init(&mm->futex_hash_lock);
 }
 

From a3ef3c2da675a8a564c8bea1a511cdd0a2a9aa49 Mon Sep 17 00:00:00 2001
From: Imre Deak <imre.deak@intel.com>
Date: Thu, 5 Jun 2025 11:28:46 +0300
Subject: [PATCH 0724/1334] drm/dp: Change AUX DPCD probe address from DPCD_REV
 to LANE0_1_STATUS
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Reading DPCD registers has side-effects in general. In particular
accessing registers outside of the link training register range
(0x102-0x106, 0x202-0x207, 0x200c-0x200f, 0x2216) is explicitly
forbidden by the DP v2.1 Standard, see

3.6.5.1 DPTX AUX Transaction Handling Mandates
3.6.7.4 128b/132b DP Link Layer LTTPR Link Training Mandates

Based on my tests, accessing the DPCD_REV register during the link
training of an UHBR TBT DP tunnel sink leads to link training failures.

Solve the above by using the DP_LANE0_1_STATUS (0x202) register for the
DPCD register access quirk.

Cc: <stable@vger.kernel.org>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Cc: Jani Nikula <jani.nikula@linux.intel.com>
Acked-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Imre Deak <imre.deak@intel.com>
Link: https://lore.kernel.org/r/20250605082850.65136-2-imre.deak@intel.com
(cherry picked from commit a40c5d727b8111b5db424a1e43e14a1dcce1e77f)
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
---
 drivers/gpu/drm/display/drm_dp_helper.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/display/drm_dp_helper.c b/drivers/gpu/drm/display/drm_dp_helper.c
index f2a6559a2710..dc622c78db9d 100644
--- a/drivers/gpu/drm/display/drm_dp_helper.c
+++ b/drivers/gpu/drm/display/drm_dp_helper.c
@@ -725,7 +725,7 @@ ssize_t drm_dp_dpcd_read(struct drm_dp_aux *aux, unsigned int offset,
 	 * monitor doesn't power down exactly after the throw away read.
 	 */
 	if (!aux->is_remote) {
-		ret = drm_dp_dpcd_probe(aux, DP_DPCD_REV);
+		ret = drm_dp_dpcd_probe(aux, DP_LANE0_1_STATUS);
 		if (ret < 0)
 			return ret;
 	}

From dc6458ed95e40146699f9c523e34cb13ff127170 Mon Sep 17 00:00:00 2001
From: Vijendar Mukunda <Vijendar.Mukunda@amd.com>
Date: Mon, 23 Jun 2025 14:14:55 +0530
Subject: [PATCH 0725/1334] ASoC: amd: ps: fix for soundwire failures during
 hibernation exit sequence

During the hibernate entry sequence, ACP registers will be reset to
default values and acp ip will be completely powered off including acp
SoundWire pads. During resume sequence, if acp SoundWire pad keeper enable
register is not restored along with pad pulldown control register value,
then SoundWire manager links won't be powered on correctly results in
peripheral register access failures and completely audio function is
broken.

Add code to store the acp SoundWire pad keeper enable register and acp pad
pulldown ctrl register values before entering into suspend state and
restore the register values during resume sequence based on condition check
for acp SoundWire pad keeper enable register for ACP6.3, ACP7.0 & ACP7.1
platforms.

Fixes: 491628388005 ("ASoC: amd: ps: add callback functions for acp pci driver pm ops")
Signed-off-by: Vijendar Mukunda <Vijendar.Mukunda@amd.com>
Link: https://patch.msgid.link/20250623084630.3100279-1-Vijendar.Mukunda@amd.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/amd/ps/acp63.h     |  4 ++++
 sound/soc/amd/ps/ps-common.c | 18 ++++++++++++++++++
 2 files changed, 22 insertions(+)

diff --git a/sound/soc/amd/ps/acp63.h b/sound/soc/amd/ps/acp63.h
index 85feae45c44c..d7c994e26e4d 100644
--- a/sound/soc/amd/ps/acp63.h
+++ b/sound/soc/amd/ps/acp63.h
@@ -334,6 +334,8 @@ struct acp_hw_ops {
  * @addr: pci ioremap address
  * @reg_range: ACP reigister range
  * @acp_rev: ACP PCI revision id
+ * @acp_sw_pad_keeper_en: store acp SoundWire pad keeper enable register value
+ * @acp_pad_pulldown_ctrl: store acp pad pulldown control register value
  * @acp63_sdw0-dma_intr_stat: DMA interrupt status array for ACP6.3 platform SoundWire
  * manager-SW0 instance
  * @acp63_sdw_dma_intr_stat: DMA interrupt status array for ACP6.3 platform SoundWire
@@ -367,6 +369,8 @@ struct acp63_dev_data {
 	u32 addr;
 	u32 reg_range;
 	u32 acp_rev;
+	u32 acp_sw_pad_keeper_en;
+	u32 acp_pad_pulldown_ctrl;
 	u16 acp63_sdw0_dma_intr_stat[ACP63_SDW0_DMA_MAX_STREAMS];
 	u16 acp63_sdw1_dma_intr_stat[ACP63_SDW1_DMA_MAX_STREAMS];
 	u16 acp70_sdw0_dma_intr_stat[ACP70_SDW0_DMA_MAX_STREAMS];
diff --git a/sound/soc/amd/ps/ps-common.c b/sound/soc/amd/ps/ps-common.c
index 1c89fb5fe1da..7b4966b75dc6 100644
--- a/sound/soc/amd/ps/ps-common.c
+++ b/sound/soc/amd/ps/ps-common.c
@@ -160,6 +160,8 @@ static int __maybe_unused snd_acp63_suspend(struct device *dev)
 
 	adata = dev_get_drvdata(dev);
 	if (adata->is_sdw_dev) {
+		adata->acp_sw_pad_keeper_en = readl(adata->acp63_base + ACP_SW0_PAD_KEEPER_EN);
+		adata->acp_pad_pulldown_ctrl = readl(adata->acp63_base + ACP_PAD_PULLDOWN_CTRL);
 		adata->sdw_en_stat = check_acp_sdw_enable_status(adata);
 		if (adata->sdw_en_stat) {
 			writel(1, adata->acp63_base + ACP_ZSC_DSP_CTRL);
@@ -197,6 +199,7 @@ static int __maybe_unused snd_acp63_runtime_resume(struct device *dev)
 static int __maybe_unused snd_acp63_resume(struct device *dev)
 {
 	struct acp63_dev_data *adata;
+	u32 acp_sw_pad_keeper_en;
 	int ret;
 
 	adata = dev_get_drvdata(dev);
@@ -209,6 +212,12 @@ static int __maybe_unused snd_acp63_resume(struct device *dev)
 	if (ret)
 		dev_err(dev, "ACP init failed\n");
 
+	acp_sw_pad_keeper_en = readl(adata->acp63_base + ACP_SW0_PAD_KEEPER_EN);
+	dev_dbg(dev, "ACP_SW0_PAD_KEEPER_EN:0x%x\n", acp_sw_pad_keeper_en);
+	if (!acp_sw_pad_keeper_en) {
+		writel(adata->acp_sw_pad_keeper_en, adata->acp63_base + ACP_SW0_PAD_KEEPER_EN);
+		writel(adata->acp_pad_pulldown_ctrl, adata->acp63_base + ACP_PAD_PULLDOWN_CTRL);
+	}
 	return ret;
 }
 
@@ -408,6 +417,8 @@ static int __maybe_unused snd_acp70_suspend(struct device *dev)
 
 	adata = dev_get_drvdata(dev);
 	if (adata->is_sdw_dev) {
+		adata->acp_sw_pad_keeper_en = readl(adata->acp63_base + ACP_SW0_PAD_KEEPER_EN);
+		adata->acp_pad_pulldown_ctrl = readl(adata->acp63_base + ACP_PAD_PULLDOWN_CTRL);
 		adata->sdw_en_stat = check_acp_sdw_enable_status(adata);
 		if (adata->sdw_en_stat) {
 			writel(1, adata->acp63_base + ACP_ZSC_DSP_CTRL);
@@ -445,6 +456,7 @@ static int __maybe_unused snd_acp70_runtime_resume(struct device *dev)
 static int __maybe_unused snd_acp70_resume(struct device *dev)
 {
 	struct acp63_dev_data *adata;
+	u32 acp_sw_pad_keeper_en;
 	int ret;
 
 	adata = dev_get_drvdata(dev);
@@ -459,6 +471,12 @@ static int __maybe_unused snd_acp70_resume(struct device *dev)
 	if (ret)
 		dev_err(dev, "ACP init failed\n");
 
+	acp_sw_pad_keeper_en = readl(adata->acp63_base + ACP_SW0_PAD_KEEPER_EN);
+	dev_dbg(dev, "ACP_SW0_PAD_KEEPER_EN:0x%x\n", acp_sw_pad_keeper_en);
+	if (!acp_sw_pad_keeper_en) {
+		writel(adata->acp_sw_pad_keeper_en, adata->acp63_base + ACP_SW0_PAD_KEEPER_EN);
+		writel(adata->acp_pad_pulldown_ctrl, adata->acp63_base + ACP_PAD_PULLDOWN_CTRL);
+	}
 	return ret;
 }
 

From 95b6759a81833d0e8c7456430186c2f6d174764e Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Fri, 20 Jun 2025 15:09:53 +0200
Subject: [PATCH 0726/1334] net: qed: reduce stack usage for TLV processing

clang gets a bit confused by the code in the qed_mfw_process_tlv_req and
ends up spilling registers to the stack hundreds of times. When sanitizers
are enabled, this can end up blowing the stack warning limit:

drivers/net/ethernet/qlogic/qed/qed_mng_tlv.c:1244:5: error: stack frame size (1824) exceeds limit (1280) in 'qed_mfw_process_tlv_req' [-Werror,-Wframe-larger-than]

Apparently the problem is the complexity of qed_mfw_update_tlvs()
after inlining, and marking the four main branches of that function
as noinline_for_stack makes this problem completely go away, the stack
usage goes down to 100 bytes.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qed/qed_mng_tlv.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/qlogic/qed/qed_mng_tlv.c b/drivers/net/ethernet/qlogic/qed/qed_mng_tlv.c
index f55eed092f25..7d78f072b0a1 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_mng_tlv.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_mng_tlv.c
@@ -242,7 +242,7 @@ static int qed_mfw_get_tlv_group(u8 tlv_type, u8 *tlv_group)
 }
 
 /* Returns size of the data buffer or, -1 in case TLV data is not available. */
-static int
+static noinline_for_stack int
 qed_mfw_get_gen_tlv_value(struct qed_drv_tlv_hdr *p_tlv,
 			  struct qed_mfw_tlv_generic *p_drv_buf,
 			  struct qed_tlv_parsed_buf *p_buf)
@@ -304,7 +304,7 @@ qed_mfw_get_gen_tlv_value(struct qed_drv_tlv_hdr *p_tlv,
 	return -1;
 }
 
-static int
+static noinline_for_stack int
 qed_mfw_get_eth_tlv_value(struct qed_drv_tlv_hdr *p_tlv,
 			  struct qed_mfw_tlv_eth *p_drv_buf,
 			  struct qed_tlv_parsed_buf *p_buf)
@@ -438,7 +438,7 @@ qed_mfw_get_tlv_time_value(struct qed_mfw_tlv_time *p_time,
 	return QED_MFW_TLV_TIME_SIZE;
 }
 
-static int
+static noinline_for_stack int
 qed_mfw_get_fcoe_tlv_value(struct qed_drv_tlv_hdr *p_tlv,
 			   struct qed_mfw_tlv_fcoe *p_drv_buf,
 			   struct qed_tlv_parsed_buf *p_buf)
@@ -1073,7 +1073,7 @@ qed_mfw_get_fcoe_tlv_value(struct qed_drv_tlv_hdr *p_tlv,
 	return -1;
 }
 
-static int
+static noinline_for_stack int
 qed_mfw_get_iscsi_tlv_value(struct qed_drv_tlv_hdr *p_tlv,
 			    struct qed_mfw_tlv_iscsi *p_drv_buf,
 			    struct qed_tlv_parsed_buf *p_buf)

From ff8abbd248c1f52df0c321690b88454b13ff54b2 Mon Sep 17 00:00:00 2001
From: Paulo Alcantara <pc@manguebit.org>
Date: Sun, 22 Jun 2025 14:13:40 -0300
Subject: [PATCH 0727/1334] smb: client: fix regression with native SMB
 symlinks

Some users and customers reported that their backup/copy tools started
to fail when the directory being copied contained symlink targets that
the client couldn't parse - even when those symlinks weren't followed.

Fix this by allowing lstat(2) and readlink(2) to succeed even when the
client can't resolve the symlink target, restoring old behavior.

Cc: linux-cifs@vger.kernel.org
Cc: stable@vger.kernel.org
Reported-by: Remy Monsen <monsen@monsen.cc>
Closes: https://lore.kernel.org/r/CAN+tdP7y=jqw3pBndZAGjQv0ObFq8Q=+PUDHgB36HdEz9QA6FQ@mail.gmail.com
Reported-by: Pierguido Lambri <plambri@redhat.com>
Fixes: 12b466eb52d9 ("cifs: Fix creating and resolving absolute NT-style symlinks")
Signed-off-by: Paulo Alcantara (Red Hat) <pc@manguebit.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/reparse.c | 20 ++++----------------
 1 file changed, 4 insertions(+), 16 deletions(-)

diff --git a/fs/smb/client/reparse.c b/fs/smb/client/reparse.c
index 511611206dab..1c40e42e4d89 100644
--- a/fs/smb/client/reparse.c
+++ b/fs/smb/client/reparse.c
@@ -875,15 +875,8 @@ globalroot:
 			abs_path += sizeof("\\DosDevices\\")-1;
 		else if (strstarts(abs_path, "\\GLOBAL??\\"))
 			abs_path += sizeof("\\GLOBAL??\\")-1;
-		else {
-			/* Unhandled absolute symlink, points outside of DOS/Win32 */
-			cifs_dbg(VFS,
-				 "absolute symlink '%s' cannot be converted from NT format "
-				 "because points to unknown target\n",
-				 smb_target);
-			rc = -EIO;
-			goto out;
-		}
+		else
+			goto out_unhandled_target;
 
 		/* Sometimes path separator after \?? is double backslash */
 		if (abs_path[0] == '\\')
@@ -910,13 +903,7 @@ globalroot:
 			abs_path++;
 			abs_path[0] = drive_letter;
 		} else {
-			/* Unhandled absolute symlink. Report an error. */
-			cifs_dbg(VFS,
-				 "absolute symlink '%s' cannot be converted from NT format "
-				 "because points to unknown target\n",
-				 smb_target);
-			rc = -EIO;
-			goto out;
+			goto out_unhandled_target;
 		}
 
 		abs_path_len = strlen(abs_path)+1;
@@ -966,6 +953,7 @@ globalroot:
 		 * These paths have same format as Linux symlinks, so no
 		 * conversion is needed.
 		 */
+out_unhandled_target:
 		linux_target = smb_target;
 		smb_target = NULL;
 	}

From db53805156f1e0aa6d059c0d3f9ac660d4ef3eb4 Mon Sep 17 00:00:00 2001
From: Heinz Mauelshagen <heinzm@redhat.com>
Date: Tue, 10 Jun 2025 20:53:30 +0200
Subject: [PATCH 0728/1334] dm-raid: fix variable in journal device check

Replace "rdev" with correct loop variable name "r".

Signed-off-by: Heinz Mauelshagen <heinzm@redhat.com>
Cc: stable@vger.kernel.org
Fixes: 63c32ed4afc2 ("dm raid: add raid4/5/6 journaling support")
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
---
 drivers/md/dm-raid.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c
index d296770478b2..e8c0a8c6fb51 100644
--- a/drivers/md/dm-raid.c
+++ b/drivers/md/dm-raid.c
@@ -2407,7 +2407,7 @@ static int super_init_validation(struct raid_set *rs, struct md_rdev *rdev)
 	 */
 	sb_retrieve_failed_devices(sb, failed_devices);
 	rdev_for_each(r, mddev) {
-		if (test_bit(Journal, &rdev->flags) ||
+		if (test_bit(Journal, &r->flags) ||
 		    !r->sb_page)
 			continue;
 		sb2 = page_address(r->sb_page);

From 88a80066af1617fab444776135d840467414beb6 Mon Sep 17 00:00:00 2001
From: Fengnan Chang <changfengnan@bytedance.com>
Date: Mon, 23 Jun 2025 19:02:18 +0800
Subject: [PATCH 0729/1334] io_uring: make fallocate be hashed work

Like ftruncate and write, fallocate operations on the same file cannot
be executed in parallel, so it is better to make fallocate be hashed
work.

Signed-off-by: Fengnan Chang <changfengnan@bytedance.com>
Link: https://lore.kernel.org/r/20250623110218.61490-1-changfengnan@bytedance.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/opdef.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/io_uring/opdef.c b/io_uring/opdef.c
index 6e0882b051f9..6de6229207a8 100644
--- a/io_uring/opdef.c
+++ b/io_uring/opdef.c
@@ -216,6 +216,7 @@ const struct io_issue_def io_issue_defs[] = {
 	},
 	[IORING_OP_FALLOCATE] = {
 		.needs_file		= 1,
+		.hash_reg_file          = 1,
 		.prep			= io_fallocate_prep,
 		.issue			= io_fallocate,
 	},

From 1d6123102e9fbedc8d25bf4731da6d513173e49e Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@google.com>
Date: Tue, 17 Jun 2025 09:58:13 -0700
Subject: [PATCH 0730/1334] Bluetooth: hci_core: Fix use-after-free in
 vhci_flush()

syzbot reported use-after-free in vhci_flush() without repro. [0]

From the splat, a thread close()d a vhci file descriptor while
its device was being used by iotcl() on another thread.

Once the last fd refcnt is released, vhci_release() calls
hci_unregister_dev(), hci_free_dev(), and kfree() for struct
vhci_data, which is set to hci_dev->dev->driver_data.

The problem is that there is no synchronisation after unlinking
hdev from hci_dev_list in hci_unregister_dev().  There might be
another thread still accessing the hdev which was fetched before
the unlink operation.

We can use SRCU for such synchronisation.

Let's run hci_dev_reset() under SRCU and wait for its completion
in hci_unregister_dev().

Another option would be to restore hci_dev->destruct(), which was
removed in commit 587ae086f6e4 ("Bluetooth: Remove unused
hci-destruct cb").  However, this would not be a good solution, as
we should not run hci_unregister_dev() while there are in-flight
ioctl() requests, which could lead to another data-race KCSAN splat.

Note that other drivers seem to have the same problem, for exmaple,
virtbt_remove().

[0]:
BUG: KASAN: slab-use-after-free in skb_queue_empty_lockless include/linux/skbuff.h:1891 [inline]
BUG: KASAN: slab-use-after-free in skb_queue_purge_reason+0x99/0x360 net/core/skbuff.c:3937
Read of size 8 at addr ffff88807cb8d858 by task syz.1.219/6718

CPU: 1 UID: 0 PID: 6718 Comm: syz.1.219 Not tainted 6.16.0-rc1-syzkaller-00196-g08207f42d3ff #0 PREEMPT(full)
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 05/07/2025
Call Trace:
 <TASK>
 dump_stack_lvl+0x189/0x250 lib/dump_stack.c:120
 print_address_description mm/kasan/report.c:408 [inline]
 print_report+0xd2/0x2b0 mm/kasan/report.c:521
 kasan_report+0x118/0x150 mm/kasan/report.c:634
 skb_queue_empty_lockless include/linux/skbuff.h:1891 [inline]
 skb_queue_purge_reason+0x99/0x360 net/core/skbuff.c:3937
 skb_queue_purge include/linux/skbuff.h:3368 [inline]
 vhci_flush+0x44/0x50 drivers/bluetooth/hci_vhci.c:69
 hci_dev_do_reset net/bluetooth/hci_core.c:552 [inline]
 hci_dev_reset+0x420/0x5c0 net/bluetooth/hci_core.c:592
 sock_do_ioctl+0xd9/0x300 net/socket.c:1190
 sock_ioctl+0x576/0x790 net/socket.c:1311
 vfs_ioctl fs/ioctl.c:51 [inline]
 __do_sys_ioctl fs/ioctl.c:907 [inline]
 __se_sys_ioctl+0xf9/0x170 fs/ioctl.c:893
 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline]
 do_syscall_64+0xfa/0x3b0 arch/x86/entry/syscall_64.c:94
 entry_SYSCALL_64_after_hwframe+0x77/0x7f
RIP: 0033:0x7fcf5b98e929
Code: ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 40 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 a8 ff ff ff f7 d8 64 89 01 48
RSP: 002b:00007fcf5c7b9038 EFLAGS: 00000246 ORIG_RAX: 0000000000000010
RAX: ffffffffffffffda RBX: 00007fcf5bbb6160 RCX: 00007fcf5b98e929
RDX: 0000000000000000 RSI: 00000000400448cb RDI: 0000000000000009
RBP: 00007fcf5ba10b39 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000
R13: 0000000000000000 R14: 00007fcf5bbb6160 R15: 00007ffd6353d528
 </TASK>

Allocated by task 6535:
 kasan_save_stack mm/kasan/common.c:47 [inline]
 kasan_save_track+0x3e/0x80 mm/kasan/common.c:68
 poison_kmalloc_redzone mm/kasan/common.c:377 [inline]
 __kasan_kmalloc+0x93/0xb0 mm/kasan/common.c:394
 kasan_kmalloc include/linux/kasan.h:260 [inline]
 __kmalloc_cache_noprof+0x230/0x3d0 mm/slub.c:4359
 kmalloc_noprof include/linux/slab.h:905 [inline]
 kzalloc_noprof include/linux/slab.h:1039 [inline]
 vhci_open+0x57/0x360 drivers/bluetooth/hci_vhci.c:635
 misc_open+0x2bc/0x330 drivers/char/misc.c:161
 chrdev_open+0x4c9/0x5e0 fs/char_dev.c:414
 do_dentry_open+0xdf0/0x1970 fs/open.c:964
 vfs_open+0x3b/0x340 fs/open.c:1094
 do_open fs/namei.c:3887 [inline]
 path_openat+0x2ee5/0x3830 fs/namei.c:4046
 do_filp_open+0x1fa/0x410 fs/namei.c:4073
 do_sys_openat2+0x121/0x1c0 fs/open.c:1437
 do_sys_open fs/open.c:1452 [inline]
 __do_sys_openat fs/open.c:1468 [inline]
 __se_sys_openat fs/open.c:1463 [inline]
 __x64_sys_openat+0x138/0x170 fs/open.c:1463
 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline]
 do_syscall_64+0xfa/0x3b0 arch/x86/entry/syscall_64.c:94
 entry_SYSCALL_64_after_hwframe+0x77/0x7f

Freed by task 6535:
 kasan_save_stack mm/kasan/common.c:47 [inline]
 kasan_save_track+0x3e/0x80 mm/kasan/common.c:68
 kasan_save_free_info+0x46/0x50 mm/kasan/generic.c:576
 poison_slab_object mm/kasan/common.c:247 [inline]
 __kasan_slab_free+0x62/0x70 mm/kasan/common.c:264
 kasan_slab_free include/linux/kasan.h:233 [inline]
 slab_free_hook mm/slub.c:2381 [inline]
 slab_free mm/slub.c:4643 [inline]
 kfree+0x18e/0x440 mm/slub.c:4842
 vhci_release+0xbc/0xd0 drivers/bluetooth/hci_vhci.c:671
 __fput+0x44c/0xa70 fs/file_table.c:465
 task_work_run+0x1d1/0x260 kernel/task_work.c:227
 exit_task_work include/linux/task_work.h:40 [inline]
 do_exit+0x6ad/0x22e0 kernel/exit.c:955
 do_group_exit+0x21c/0x2d0 kernel/exit.c:1104
 __do_sys_exit_group kernel/exit.c:1115 [inline]
 __se_sys_exit_group kernel/exit.c:1113 [inline]
 __x64_sys_exit_group+0x3f/0x40 kernel/exit.c:1113
 x64_sys_call+0x21ba/0x21c0 arch/x86/include/generated/asm/syscalls_64.h:232
 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline]
 do_syscall_64+0xfa/0x3b0 arch/x86/entry/syscall_64.c:94
 entry_SYSCALL_64_after_hwframe+0x77/0x7f

The buggy address belongs to the object at ffff88807cb8d800
 which belongs to the cache kmalloc-1k of size 1024
The buggy address is located 88 bytes inside of
 freed 1024-byte region [ffff88807cb8d800, ffff88807cb8dc00)

Fixes: bf18c7118cf8 ("Bluetooth: vhci: Free driver_data on file release")
Reported-by: syzbot+2faa4825e556199361f9@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=f62d64848fc4c7c30cd6
Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Acked-by: Paul Menzel <pmenzel@molgen.mpg.de>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 include/net/bluetooth/hci_core.h |  2 ++
 net/bluetooth/hci_core.c         | 34 ++++++++++++++++++++++++++++----
 2 files changed, 32 insertions(+), 4 deletions(-)

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index a760f05fa3fb..9fc8f544e20e 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -29,6 +29,7 @@
 #include <linux/idr.h>
 #include <linux/leds.h>
 #include <linux/rculist.h>
+#include <linux/srcu.h>
 
 #include <net/bluetooth/hci.h>
 #include <net/bluetooth/hci_drv.h>
@@ -347,6 +348,7 @@ struct adv_monitor {
 
 struct hci_dev {
 	struct list_head list;
+	struct srcu_struct srcu;
 	struct mutex	lock;
 
 	struct ida	unset_handle_ida;
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index 07a8b4281a39..14d7221b8ac0 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -64,7 +64,7 @@ static DEFINE_IDA(hci_index_ida);
 
 /* Get HCI device by index.
  * Device is held on return. */
-struct hci_dev *hci_dev_get(int index)
+static struct hci_dev *__hci_dev_get(int index, int *srcu_index)
 {
 	struct hci_dev *hdev = NULL, *d;
 
@@ -77,6 +77,8 @@ struct hci_dev *hci_dev_get(int index)
 	list_for_each_entry(d, &hci_dev_list, list) {
 		if (d->id == index) {
 			hdev = hci_dev_hold(d);
+			if (srcu_index)
+				*srcu_index = srcu_read_lock(&d->srcu);
 			break;
 		}
 	}
@@ -84,6 +86,22 @@ struct hci_dev *hci_dev_get(int index)
 	return hdev;
 }
 
+struct hci_dev *hci_dev_get(int index)
+{
+	return __hci_dev_get(index, NULL);
+}
+
+static struct hci_dev *hci_dev_get_srcu(int index, int *srcu_index)
+{
+	return __hci_dev_get(index, srcu_index);
+}
+
+static void hci_dev_put_srcu(struct hci_dev *hdev, int srcu_index)
+{
+	srcu_read_unlock(&hdev->srcu, srcu_index);
+	hci_dev_put(hdev);
+}
+
 /* ---- Inquiry support ---- */
 
 bool hci_discovery_active(struct hci_dev *hdev)
@@ -568,9 +586,9 @@ static int hci_dev_do_reset(struct hci_dev *hdev)
 int hci_dev_reset(__u16 dev)
 {
 	struct hci_dev *hdev;
-	int err;
+	int err, srcu_index;
 
-	hdev = hci_dev_get(dev);
+	hdev = hci_dev_get_srcu(dev, &srcu_index);
 	if (!hdev)
 		return -ENODEV;
 
@@ -592,7 +610,7 @@ int hci_dev_reset(__u16 dev)
 	err = hci_dev_do_reset(hdev);
 
 done:
-	hci_dev_put(hdev);
+	hci_dev_put_srcu(hdev, srcu_index);
 	return err;
 }
 
@@ -2433,6 +2451,11 @@ struct hci_dev *hci_alloc_dev_priv(int sizeof_priv)
 	if (!hdev)
 		return NULL;
 
+	if (init_srcu_struct(&hdev->srcu)) {
+		kfree(hdev);
+		return NULL;
+	}
+
 	hdev->pkt_type  = (HCI_DM1 | HCI_DH1 | HCI_HV1);
 	hdev->esco_type = (ESCO_HV1);
 	hdev->link_mode = (HCI_LM_ACCEPT);
@@ -2678,6 +2701,9 @@ void hci_unregister_dev(struct hci_dev *hdev)
 	list_del(&hdev->list);
 	write_unlock(&hci_dev_list_lock);
 
+	synchronize_srcu(&hdev->srcu);
+	cleanup_srcu_struct(&hdev->srcu);
+
 	disable_work_sync(&hdev->rx_work);
 	disable_work_sync(&hdev->cmd_work);
 	disable_work_sync(&hdev->tx_work);

From 9c19b3315cef8b62d2c037616a66b4446b966f6d Mon Sep 17 00:00:00 2001
From: Nikhil Jha <njha@janestreet.com>
Date: Wed, 11 Jun 2025 15:46:39 -0400
Subject: [PATCH 0731/1334] sunrpc: fix loop in gss seqno cache

There was a silly bug in the initial implementation where a loop
variable was not incremented. This commit increments the loop variable.

This bug is somewhat tricky to catch because it can only happen on loops
of two or more. If it is hit, it locks up a kernel thread in an infinite
loop.

Signed-off-by: Nikhil Jha <njha@janestreet.com>
Tested-by: Nikhil Jha <njha@janestreet.com>
Fixes: 08d6ee6d8a10 ("sunrpc: implement rfc2203 rpcsec_gss seqnum cache")
Reviewed-by: Benjamin Coddington <bcodding@redhat.com>
Signed-off-by: Anna Schumaker <anna.schumaker@oracle.com>
---
 net/sunrpc/auth_gss/auth_gss.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c
index 0fa244f16876..7b943fbafcc3 100644
--- a/net/sunrpc/auth_gss/auth_gss.c
+++ b/net/sunrpc/auth_gss/auth_gss.c
@@ -1724,7 +1724,7 @@ gss_validate(struct rpc_task *task, struct xdr_stream *xdr)
 	maj_stat = gss_validate_seqno_mic(ctx, task->tk_rqstp->rq_seqnos[0], seq, p, len);
 	/* RFC 2203 5.3.3.1 - compute the checksum of each sequence number in the cache */
 	while (unlikely(maj_stat == GSS_S_BAD_SIG && i < task->tk_rqstp->rq_seqno_count))
-		maj_stat = gss_validate_seqno_mic(ctx, task->tk_rqstp->rq_seqnos[i], seq, p, len);
+		maj_stat = gss_validate_seqno_mic(ctx, task->tk_rqstp->rq_seqnos[i++], seq, p, len);
 	if (maj_stat == GSS_S_CONTEXT_EXPIRED)
 		clear_bit(RPCAUTH_CRED_UPTODATE, &cred->cr_flags);
 	if (maj_stat)

From e8d6f3ab59468e230f3253efe5cb63efa35289f7 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@google.com>
Date: Thu, 12 Jun 2025 14:52:50 -0700
Subject: [PATCH 0732/1334] nfs: Clean up /proc/net/rpc/nfs when
 nfs_fs_proc_net_init() fails.

syzbot reported a warning below [1] following a fault injection in
nfs_fs_proc_net_init(). [0]

When nfs_fs_proc_net_init() fails, /proc/net/rpc/nfs is not removed.

Later, rpc_proc_exit() tries to remove /proc/net/rpc, and the warning
is logged as the directory is not empty.

Let's handle the error of nfs_fs_proc_net_init() properly.

[0]:
FAULT_INJECTION: forcing a failure.
name failslab, interval 1, probability 0, space 0, times 0
CPU: 1 UID: 0 PID: 6120 Comm: syz.2.27 Not tainted 6.16.0-rc1-syzkaller-00010-g2c4a1f3fe03e #0 PREEMPT(full)
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 05/07/2025
Call Trace:
 <TASK>
  dump_stack_lvl (lib/dump_stack.c:123)
 should_fail_ex (lib/fault-inject.c:73 lib/fault-inject.c:174)
 should_failslab (mm/failslab.c:46)
 kmem_cache_alloc_noprof (mm/slub.c:4178 mm/slub.c:4204)
 __proc_create (fs/proc/generic.c:427)
 proc_create_reg (fs/proc/generic.c:554)
 proc_create_net_data (fs/proc/proc_net.c:120)
 nfs_fs_proc_net_init (fs/nfs/client.c:1409)
 nfs_net_init (fs/nfs/inode.c:2600)
 ops_init (net/core/net_namespace.c:138)
 setup_net (net/core/net_namespace.c:443)
 copy_net_ns (net/core/net_namespace.c:576)
 create_new_namespaces (kernel/nsproxy.c:110)
 unshare_nsproxy_namespaces (kernel/nsproxy.c:218 (discriminator 4))
 ksys_unshare (kernel/fork.c:3123)
 __x64_sys_unshare (kernel/fork.c:3190)
 do_syscall_64 (arch/x86/entry/syscall_64.c:63 arch/x86/entry/syscall_64.c:94)
 entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:130)
 </TASK>

[1]:
remove_proc_entry: removing non-empty directory 'net/rpc', leaking at least 'nfs'
 WARNING: CPU: 1 PID: 6120 at fs/proc/generic.c:727 remove_proc_entry+0x45e/0x530 fs/proc/generic.c:727
Modules linked in:
CPU: 1 UID: 0 PID: 6120 Comm: syz.2.27 Not tainted 6.16.0-rc1-syzkaller-00010-g2c4a1f3fe03e #0 PREEMPT(full)
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 05/07/2025
 RIP: 0010:remove_proc_entry+0x45e/0x530 fs/proc/generic.c:727
Code: 3c 02 00 0f 85 85 00 00 00 48 8b 93 d8 00 00 00 4d 89 f0 4c 89 e9 48 c7 c6 40 ba a2 8b 48 c7 c7 60 b9 a2 8b e8 33 81 1d ff 90 <0f> 0b 90 90 e9 5f fe ff ff e8 04 69 5e ff 90 48 b8 00 00 00 00 00
RSP: 0018:ffffc90003637b08 EFLAGS: 00010282
RAX: 0000000000000000 RBX: ffff88805f534140 RCX: ffffffff817a92c8
RDX: ffff88807da99e00 RSI: ffffffff817a92d5 RDI: 0000000000000001
RBP: ffff888033431ac0 R08: 0000000000000001 R09: 0000000000000000
R10: 0000000000000001 R11: 0000000000000001 R12: ffff888033431a00
R13: ffff888033431ae4 R14: ffff888033184724 R15: dffffc0000000000
FS:  0000555580328500(0000) GS:ffff888124a62000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007f71733743e0 CR3: 000000007f618000 CR4: 00000000003526f0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
 <TASK>
  sunrpc_exit_net+0x46/0x90 net/sunrpc/sunrpc_syms.c:76
  ops_exit_list net/core/net_namespace.c:200 [inline]
  ops_undo_list+0x2eb/0xab0 net/core/net_namespace.c:253
  setup_net+0x2e1/0x510 net/core/net_namespace.c:457
  copy_net_ns+0x2a6/0x5f0 net/core/net_namespace.c:574
  create_new_namespaces+0x3ea/0xa90 kernel/nsproxy.c:110
  unshare_nsproxy_namespaces+0xc0/0x1f0 kernel/nsproxy.c:218
  ksys_unshare+0x45b/0xa40 kernel/fork.c:3121
  __do_sys_unshare kernel/fork.c:3192 [inline]
  __se_sys_unshare kernel/fork.c:3190 [inline]
  __x64_sys_unshare+0x31/0x40 kernel/fork.c:3190
  do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline]
  do_syscall_64+0xcd/0x490 arch/x86/entry/syscall_64.c:94
 entry_SYSCALL_64_after_hwframe+0x77/0x7f
RIP: 0033:0x7fa1a6b8e929
Code: ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 40 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 a8 ff ff ff f7 d8 64 89 01 48
RSP: 002b:00007fff3a090368 EFLAGS: 00000246 ORIG_RAX: 0000000000000110
RAX: ffffffffffffffda RBX: 00007fa1a6db5fa0 RCX: 00007fa1a6b8e929
RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000040000080
RBP: 00007fa1a6c10b39 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000
R13: 00007fa1a6db5fa0 R14: 00007fa1a6db5fa0 R15: 0000000000000001
 </TASK>

Fixes: d47151b79e32 ("nfs: expose /proc/net/sunrpc/nfs in net namespaces")
Reported-by: syzbot+a4cc4ac22daa4a71b87c@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=a4cc4ac22daa4a71b87c
Tested-by: syzbot+a4cc4ac22daa4a71b87c@syzkaller.appspotmail.com
Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Signed-off-by: Anna Schumaker <anna.schumaker@oracle.com>
---
 fs/nfs/inode.c | 17 ++++++++++++++---
 1 file changed, 14 insertions(+), 3 deletions(-)

diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 8ab7868807a7..a2fa6bc4d74e 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -2589,15 +2589,26 @@ EXPORT_SYMBOL_GPL(nfs_net_id);
 static int nfs_net_init(struct net *net)
 {
 	struct nfs_net *nn = net_generic(net, nfs_net_id);
+	int err;
 
 	nfs_clients_init(net);
 
 	if (!rpc_proc_register(net, &nn->rpcstats)) {
-		nfs_clients_exit(net);
-		return -ENOMEM;
+		err = -ENOMEM;
+		goto err_proc_rpc;
 	}
 
-	return nfs_fs_proc_net_init(net);
+	err = nfs_fs_proc_net_init(net);
+	if (err)
+		goto err_proc_nfs;
+
+	return 0;
+
+err_proc_nfs:
+	rpc_proc_unregister(net, "nfs");
+err_proc_rpc:
+	nfs_clients_exit(net);
+	return err;
 }
 
 static void nfs_net_exit(struct net *net)

From c01776287414ca43412d1319d2877cbad65444ac Mon Sep 17 00:00:00 2001
From: Benjamin Coddington <bcodding@redhat.com>
Date: Thu, 19 Jun 2025 11:02:21 -0400
Subject: [PATCH 0733/1334] NFSv4/pNFS: Fix a race to wake on NFS_LAYOUT_DRAIN

We found a few different systems hung up in writeback waiting on the same
page lock, and one task waiting on the NFS_LAYOUT_DRAIN bit in
pnfs_update_layout(), however the pnfs_layout_hdr's plh_outstanding count
was zero.

It seems most likely that this is another race between the waiter and waker
similar to commit ed0172af5d6f ("SUNRPC: Fix a race to wake a sync task").
Fix it up by applying the advised barrier.

Fixes: 880265c77ac4 ("pNFS: Avoid a live lock condition in pnfs_update_layout()")
Signed-off-by: Benjamin Coddington <bcodding@redhat.com>
Signed-off-by: Anna Schumaker <anna.schumaker@oracle.com>
---
 fs/nfs/pnfs.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index 3adb7d0dbec7..1a7ec68bde15 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -2059,8 +2059,10 @@ static void nfs_layoutget_begin(struct pnfs_layout_hdr *lo)
 static void nfs_layoutget_end(struct pnfs_layout_hdr *lo)
 {
 	if (atomic_dec_and_test(&lo->plh_outstanding) &&
-	    test_and_clear_bit(NFS_LAYOUT_DRAIN, &lo->plh_flags))
+	    test_and_clear_bit(NFS_LAYOUT_DRAIN, &lo->plh_flags)) {
+		smp_mb__after_atomic();
 		wake_up_bit(&lo->plh_flags, NFS_LAYOUT_DRAIN);
+	}
 }
 
 static bool pnfs_is_first_layoutget(struct pnfs_layout_hdr *lo)

From 9a07ca9a4015f8f71e2b594ee76ac55483babd89 Mon Sep 17 00:00:00 2001
From: Chris Chiu <chris.chiu@canonical.com>
Date: Mon, 23 Jun 2025 14:30:23 +0800
Subject: [PATCH 0734/1334] ALSA: hda/realtek: fix mute/micmute LEDs for HP
 EliteBook 6 G1a

HP EliteBook 6 G1a laptops use ALC236 codec and need the fixup
ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF to make the mic/micmute LEDs
work.

Signed-off-by: Chris Chiu <chris.chiu@canonical.com>
Link: https://patch.msgid.link/20250623063023.374920-1-chris.chiu@canonical.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/patch_realtek.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index e144ebb08841..166730f00e5e 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -10909,7 +10909,9 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x103c, 0x8def, "HP EliteBook 660 G12", ALC236_FIXUP_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8df0, "HP EliteBook 630 G12", ALC236_FIXUP_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8df1, "HP EliteBook 630 G12", ALC236_FIXUP_HP_GPIO_LED),
+	SND_PCI_QUIRK(0x103c, 0x8dfb, "HP EliteBook 6 G1a 14", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF),
 	SND_PCI_QUIRK(0x103c, 0x8dfc, "HP EliteBook 645 G12", ALC236_FIXUP_HP_GPIO_LED),
+	SND_PCI_QUIRK(0x103c, 0x8dfd, "HP EliteBook 6 G1a 16", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF),
 	SND_PCI_QUIRK(0x103c, 0x8dfe, "HP EliteBook 665 G12", ALC236_FIXUP_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8e11, "HP Trekker", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x103c, 0x8e12, "HP Trekker", ALC287_FIXUP_CS35L41_I2C_2),

From fb4e2a6e8f28a3c0ad382e363aeb9cd822007b8a Mon Sep 17 00:00:00 2001
From: Youngjun Lee <yjjuny.lee@samsung.com>
Date: Mon, 23 Jun 2025 20:05:25 +0900
Subject: [PATCH 0735/1334] ALSA: usb-audio: Fix out-of-bounds read in
 snd_usb_get_audioformat_uac3()

In snd_usb_get_audioformat_uac3(), the length value returned from
snd_usb_ctl_msg() is used directly for memory allocation without
validation. This length is controlled by the USB device.

The allocated buffer is cast to a uac3_cluster_header_descriptor
and its fields are accessed without verifying that the buffer
is large enough. If the device returns a smaller than expected
length, this leads to an out-of-bounds read.

Add a length check to ensure the buffer is large enough for
uac3_cluster_header_descriptor.

Signed-off-by: Youngjun Lee <yjjuny.lee@samsung.com>
Fixes: 9a2fe9b801f5 ("ALSA: usb: initial USB Audio Device Class 3.0 support")
Link: https://patch.msgid.link/20250623-uac3-oob-fix-v1-1-527303eaf40a@samsung.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/usb/stream.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/sound/usb/stream.c b/sound/usb/stream.c
index c1ea8844a46f..aa91d63749f2 100644
--- a/sound/usb/stream.c
+++ b/sound/usb/stream.c
@@ -987,6 +987,8 @@ snd_usb_get_audioformat_uac3(struct snd_usb_audio *chip,
 	 * and request Cluster Descriptor
 	 */
 	wLength = le16_to_cpu(hc_header.wLength);
+	if (wLength < sizeof(cluster))
+		return NULL;
 	cluster = kzalloc(wLength, GFP_KERNEL);
 	if (!cluster)
 		return ERR_PTR(-ENOMEM);

From 41c66461cb2e8d3934a5395f27e572ebe63696b4 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Mon, 23 Jun 2025 17:18:39 +0200
Subject: [PATCH 0736/1334] ALSA: hda/realtek: Add mic-mute LED setup for ASUS
 UM5606

ASUS UM5606* models use the quirk to set up the bass speakers, but it
missed the mic-mute LED configuration.  Other similar models have the
AMD ACP dmic, and the mic-mute is set up for that, but those models
don't have AMD ACP but rather built-in mics of Realtek codec, hence
the Realtek driver should set it up, instead.

Link: https://bugzilla.kernel.org/show_bug.cgi?id=220125
Link: https://patch.msgid.link/20250623151841.28810-1-tiwai@suse.de
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/patch_realtek.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 166730f00e5e..784644a2b51d 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -6610,6 +6610,7 @@ static void alc294_fixup_bass_speaker_15(struct hda_codec *codec,
 	if (action == HDA_FIXUP_ACT_PRE_PROBE) {
 		static const hda_nid_t conn[] = { 0x02, 0x03 };
 		snd_hda_override_conn_list(codec, 0x15, ARRAY_SIZE(conn), conn);
+		snd_hda_gen_add_micmute_led_cdev(codec, NULL);
 	}
 }
 

From c3b214719a87735d4f67333a8ef3c0e31a34837c Mon Sep 17 00:00:00 2001
From: Thomas Fourier <fourier.thomas@gmail.com>
Date: Tue, 17 Jun 2025 18:11:11 +0200
Subject: [PATCH 0737/1334] scsi: qla2xxx: Fix DMA mapping test in
 qla24xx_get_port_database()

dma_map_XXX() functions return as error values DMA_MAPPING_ERROR which is
often ~0.  The error value should be tested with dma_mapping_error() like
it was done in qla26xx_dport_diagnostics().

Fixes: 818c7f87a177 ("scsi: qla2xxx: Add changes in preparation for vendor extended FDMI/RDP")
Signed-off-by: Thomas Fourier <fourier.thomas@gmail.com>
Link: https://lore.kernel.org/r/20250617161115.39888-2-fourier.thomas@gmail.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/qla2xxx/qla_mbx.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/scsi/qla2xxx/qla_mbx.c b/drivers/scsi/qla2xxx/qla_mbx.c
index 0cd6f3e14882..13b6cb1b93ac 100644
--- a/drivers/scsi/qla2xxx/qla_mbx.c
+++ b/drivers/scsi/qla2xxx/qla_mbx.c
@@ -2147,7 +2147,7 @@ qla24xx_get_port_database(scsi_qla_host_t *vha, u16 nport_handle,
 
 	pdb_dma = dma_map_single(&vha->hw->pdev->dev, pdb,
 	    sizeof(*pdb), DMA_FROM_DEVICE);
-	if (!pdb_dma) {
+	if (dma_mapping_error(&vha->hw->pdev->dev, pdb_dma)) {
 		ql_log(ql_log_warn, vha, 0x1116, "Failed to map dma buffer.\n");
 		return QLA_MEMORY_ALLOC_FAILED;
 	}

From 00f452a1b084efbe8dcb60a29860527944a002a1 Mon Sep 17 00:00:00 2001
From: Thomas Fourier <fourier.thomas@gmail.com>
Date: Wed, 18 Jun 2025 09:17:37 +0200
Subject: [PATCH 0738/1334] scsi: qla4xxx: Fix missing DMA mapping error in
 qla4xxx_alloc_pdu()

dma_map_XXX() can fail and should be tested for errors with
dma_mapping_error().

Fixes: b3a271a94d00 ("[SCSI] qla4xxx: support iscsiadm session mgmt")
Signed-off-by: Thomas Fourier <fourier.thomas@gmail.com>
Link: https://lore.kernel.org/r/20250618071742.21822-2-fourier.thomas@gmail.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/qla4xxx/ql4_os.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/scsi/qla4xxx/ql4_os.c b/drivers/scsi/qla4xxx/ql4_os.c
index d4141656b204..a39f1da4ce47 100644
--- a/drivers/scsi/qla4xxx/ql4_os.c
+++ b/drivers/scsi/qla4xxx/ql4_os.c
@@ -3420,6 +3420,8 @@ static int qla4xxx_alloc_pdu(struct iscsi_task *task, uint8_t opcode)
 		task_data->data_dma = dma_map_single(&ha->pdev->dev, task->data,
 						     task->data_count,
 						     DMA_TO_DEVICE);
+		if (dma_mapping_error(&ha->pdev->dev, task_data->data_dma))
+			return -ENOMEM;
 	}
 
 	DEBUG2(ql4_printk(KERN_INFO, ha, "%s: MaxRecvLen %u, iscsi hrd %d\n",

From 5aa326a6a2ff0a7e7c6e11777045e66704c2d5e4 Mon Sep 17 00:00:00 2001
From: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Date: Sun, 8 Jun 2025 09:03:05 +0530
Subject: [PATCH 0739/1334] PCI/PTM: Build debugfs code only if CONFIG_DEBUG_FS
 is enabled

Otherwise, the following build error will happen for CONFIG_DEBUG_FS=n &&
CONFIG_PCIE_PTM=y:

  drivers/pci/pcie/ptm.c:498:25: error: redefinition of 'pcie_ptm_create_debugfs'
    498 | struct pci_ptm_debugfs *pcie_ptm_create_debugfs(struct device *dev, void *pdata,
	|                         ^
  ./include/linux/pci.h:1915:2: note: previous definition is here
   1915 | *pcie_ptm_create_debugfs(struct device *dev, void *pdata,
	|  ^
  drivers/pci/pcie/ptm.c:546:6: error: redefinition of 'pcie_ptm_destroy_debugfs'
    546 | void pcie_ptm_destroy_debugfs(struct pci_ptm_debugfs *ptm_debugfs)
	|      ^
  ./include/linux/pci.h:1918:1: note: previous definition is here
   1918 | pcie_ptm_destroy_debugfs(struct pci_ptm_debugfs *ptm_debugfs) { }
	|

Fixes: 132833405e61 ("PCI: Add debugfs support for exposing PTM context")
Reported-by: Eric Biggers <ebiggers@kernel.org>
Closes: https://lore.kernel.org/linux-pci/20250607025506.GA16607@sol
Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Tested-by: Eric Biggers <ebiggers@kernel.org>
Reviewed-by: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@linux.intel.com>
Link: https://patch.msgid.link/20250608033305.15214-1-manivannan.sadhasivam@linaro.org
---
 drivers/pci/pcie/ptm.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/pci/pcie/ptm.c b/drivers/pci/pcie/ptm.c
index ee5f615a9023..4bd73f038ffb 100644
--- a/drivers/pci/pcie/ptm.c
+++ b/drivers/pci/pcie/ptm.c
@@ -254,6 +254,7 @@ bool pcie_ptm_enabled(struct pci_dev *dev)
 }
 EXPORT_SYMBOL(pcie_ptm_enabled);
 
+#if IS_ENABLED(CONFIG_DEBUG_FS)
 static ssize_t context_update_write(struct file *file, const char __user *ubuf,
 			     size_t count, loff_t *ppos)
 {
@@ -552,3 +553,4 @@ void pcie_ptm_destroy_debugfs(struct pci_ptm_debugfs *ptm_debugfs)
 	debugfs_remove_recursive(ptm_debugfs->debugfs);
 }
 EXPORT_SYMBOL_GPL(pcie_ptm_destroy_debugfs);
+#endif

From 7484e15dbb016d9d40f8c6e0475810212ae181db Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Tue, 17 Jun 2025 00:09:51 -0400
Subject: [PATCH 0740/1334] replace collect_mounts()/drop_collected_mounts()
 with a safer variant

collect_mounts() has several problems - one can't iterate over the results
directly, so it has to be done with callback passed to iterate_mounts();
it has an oopsable race with d_invalidate(); it creates temporary clones
of mounts invisibly for sync umount (IOW, you can have non-lazy umount
succeed leaving filesystem not mounted anywhere and yet still busy).

A saner approach is to give caller an array of struct path that would pin
every mount in a subtree, without cloning any mounts.

        * collect_mounts()/drop_collected_mounts()/iterate_mounts() is gone
        * collect_paths(where, preallocated, size) gives either ERR_PTR(-E...) or
a pointer to array of struct path, one for each chunk of tree visible under
'where' (i.e. the first element is a copy of where, followed by (mount,root)
for everything mounted under it - the same set collect_mounts() would give).
Unlike collect_mounts(), the mounts are *not* cloned - we just get pinning
references to the roots of subtrees in the caller's namespace.
        Array is terminated by {NULL, NULL} struct path.  If it fits into
preallocated array (on-stack, normally), that's where it goes; otherwise
it's allocated by kmalloc_array().  Passing 0 as size means that 'preallocated'
is ignored (and expected to be NULL).
        * drop_collected_paths(paths, preallocated) is given the array returned
by an earlier call of collect_paths() and the preallocated array passed to that
call.  All mount/dentry references are dropped and array is kfree'd if it's not
equal to 'preallocated'.
        * instead of iterate_mounts(), users should just iterate over array
of struct path - nothing exotic is needed for that.  Existing users (all in
audit_tree.c) are converted.

[folded a fix for braino reported by Venkat Rao Bagalkote <venkat88@linux.ibm.com>]

Fixes: 80b5dce8c59b0 ("vfs: Add a function to lazily unmount all mounts from any dentry")
Tested-by: Venkat Rao Bagalkote <venkat88@linux.ibm.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 Documentation/filesystems/porting.rst |  9 +++
 fs/namespace.c                        | 99 ++++++++++++++++-----------
 fs/pnode.h                            |  2 -
 include/linux/mount.h                 |  6 +-
 kernel/audit_tree.c                   | 63 +++++++++--------
 5 files changed, 105 insertions(+), 74 deletions(-)

diff --git a/Documentation/filesystems/porting.rst b/Documentation/filesystems/porting.rst
index 3616d7161dab..a5734bdd1cc7 100644
--- a/Documentation/filesystems/porting.rst
+++ b/Documentation/filesystems/porting.rst
@@ -1249,3 +1249,12 @@ Using try_lookup_noperm() will require linux/namei.h to be included.
 
 Calling conventions for ->d_automount() have changed; we should *not* grab
 an extra reference to new mount - it should be returned with refcount 1.
+
+---
+
+collect_mounts()/drop_collected_mounts()/iterate_mounts() are gone now.
+Replacement is collect_paths()/drop_collected_path(), with no special
+iterator needed.  Instead of a cloned mount tree, the new interface returns
+an array of struct path, one for each mount collect_mounts() would've
+created.  These struct path point to locations in the caller's namespace
+that would be roots of the cloned mounts.
diff --git a/fs/namespace.c b/fs/namespace.c
index e13d9ab4f564..14601ec4c2c5 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -2310,21 +2310,62 @@ out:
 	return dst_mnt;
 }
 
-/* Caller should check returned pointer for errors */
-
-struct vfsmount *collect_mounts(const struct path *path)
+static inline bool extend_array(struct path **res, struct path **to_free,
+				unsigned n, unsigned *count, unsigned new_count)
 {
-	struct mount *tree;
-	namespace_lock();
-	if (!check_mnt(real_mount(path->mnt)))
-		tree = ERR_PTR(-EINVAL);
-	else
-		tree = copy_tree(real_mount(path->mnt), path->dentry,
-				 CL_COPY_ALL | CL_PRIVATE);
-	namespace_unlock();
-	if (IS_ERR(tree))
-		return ERR_CAST(tree);
-	return &tree->mnt;
+	struct path *p;
+
+	if (likely(n < *count))
+		return true;
+	p = kmalloc_array(new_count, sizeof(struct path), GFP_KERNEL);
+	if (p && *count)
+		memcpy(p, *res, *count * sizeof(struct path));
+	*count = new_count;
+	kfree(*to_free);
+	*to_free = *res = p;
+	return p;
+}
+
+struct path *collect_paths(const struct path *path,
+			      struct path *prealloc, unsigned count)
+{
+	struct mount *root = real_mount(path->mnt);
+	struct mount *child;
+	struct path *res = prealloc, *to_free = NULL;
+	unsigned n = 0;
+
+	guard(rwsem_read)(&namespace_sem);
+
+	if (!check_mnt(root))
+		return ERR_PTR(-EINVAL);
+	if (!extend_array(&res, &to_free, 0, &count, 32))
+		return ERR_PTR(-ENOMEM);
+	res[n++] = *path;
+	list_for_each_entry(child, &root->mnt_mounts, mnt_child) {
+		if (!is_subdir(child->mnt_mountpoint, path->dentry))
+			continue;
+		for (struct mount *m = child; m; m = next_mnt(m, child)) {
+			if (!extend_array(&res, &to_free, n, &count, 2 * count))
+				return ERR_PTR(-ENOMEM);
+			res[n].mnt = &m->mnt;
+			res[n].dentry = m->mnt.mnt_root;
+			n++;
+		}
+	}
+	if (!extend_array(&res, &to_free, n, &count, count + 1))
+		return ERR_PTR(-ENOMEM);
+	memset(res + n, 0, (count - n) * sizeof(struct path));
+	for (struct path *p = res; p->mnt; p++)
+		path_get(p);
+	return res;
+}
+
+void drop_collected_paths(struct path *paths, struct path *prealloc)
+{
+	for (struct path *p = paths; p->mnt; p++)
+		path_put(p);
+	if (paths != prealloc)
+		kfree(paths);
 }
 
 static void free_mnt_ns(struct mnt_namespace *);
@@ -2401,15 +2442,6 @@ void dissolve_on_fput(struct vfsmount *mnt)
 	free_mnt_ns(ns);
 }
 
-void drop_collected_mounts(struct vfsmount *mnt)
-{
-	namespace_lock();
-	lock_mount_hash();
-	umount_tree(real_mount(mnt), 0);
-	unlock_mount_hash();
-	namespace_unlock();
-}
-
 static bool __has_locked_children(struct mount *mnt, struct dentry *dentry)
 {
 	struct mount *child;
@@ -2511,21 +2543,6 @@ struct vfsmount *clone_private_mount(const struct path *path)
 }
 EXPORT_SYMBOL_GPL(clone_private_mount);
 
-int iterate_mounts(int (*f)(struct vfsmount *, void *), void *arg,
-		   struct vfsmount *root)
-{
-	struct mount *mnt;
-	int res = f(root, arg);
-	if (res)
-		return res;
-	list_for_each_entry(mnt, &real_mount(root)->mnt_list, mnt_list) {
-		res = f(&mnt->mnt, arg);
-		if (res)
-			return res;
-	}
-	return 0;
-}
-
 static void lock_mnt_tree(struct mount *mnt)
 {
 	struct mount *p;
@@ -6262,7 +6279,11 @@ void put_mnt_ns(struct mnt_namespace *ns)
 {
 	if (!refcount_dec_and_test(&ns->ns.count))
 		return;
-	drop_collected_mounts(&ns->root->mnt);
+	namespace_lock();
+	lock_mount_hash();
+	umount_tree(ns->root, 0);
+	unlock_mount_hash();
+	namespace_unlock();
 	free_mnt_ns(ns);
 }
 
diff --git a/fs/pnode.h b/fs/pnode.h
index 34b6247af01d..2d026fb98b18 100644
--- a/fs/pnode.h
+++ b/fs/pnode.h
@@ -28,8 +28,6 @@
 #define CL_SHARED_TO_SLAVE	0x20
 #define CL_COPY_MNT_NS_FILE	0x40
 
-#define CL_COPY_ALL		(CL_COPY_UNBINDABLE | CL_COPY_MNT_NS_FILE)
-
 static inline void set_mnt_shared(struct mount *mnt)
 {
 	mnt->mnt.mnt_flags &= ~MNT_SHARED_MASK;
diff --git a/include/linux/mount.h b/include/linux/mount.h
index 4880f434c021..1a508beba446 100644
--- a/include/linux/mount.h
+++ b/include/linux/mount.h
@@ -116,10 +116,8 @@ extern int may_umount_tree(struct vfsmount *);
 extern int may_umount(struct vfsmount *);
 int do_mount(const char *, const char __user *,
 		     const char *, unsigned long, void *);
-extern struct vfsmount *collect_mounts(const struct path *);
-extern void drop_collected_mounts(struct vfsmount *);
-extern int iterate_mounts(int (*)(struct vfsmount *, void *), void *,
-			  struct vfsmount *);
+extern struct path *collect_paths(const struct path *, struct path *, unsigned);
+extern void drop_collected_paths(struct path *, struct path *);
 extern void kern_unmount_array(struct vfsmount *mnt[], unsigned int num);
 
 extern int cifs_root_data(char **dev, char **opts);
diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c
index f2f38903b2fe..b0eae2a3c895 100644
--- a/kernel/audit_tree.c
+++ b/kernel/audit_tree.c
@@ -668,12 +668,6 @@ int audit_remove_tree_rule(struct audit_krule *rule)
 	return 0;
 }
 
-static int compare_root(struct vfsmount *mnt, void *arg)
-{
-	return inode_to_key(d_backing_inode(mnt->mnt_root)) ==
-	       (unsigned long)arg;
-}
-
 void audit_trim_trees(void)
 {
 	struct list_head cursor;
@@ -683,8 +677,9 @@ void audit_trim_trees(void)
 	while (cursor.next != &tree_list) {
 		struct audit_tree *tree;
 		struct path path;
-		struct vfsmount *root_mnt;
 		struct audit_node *node;
+		struct path *paths;
+		struct path array[16];
 		int err;
 
 		tree = container_of(cursor.next, struct audit_tree, list);
@@ -696,9 +691,9 @@ void audit_trim_trees(void)
 		if (err)
 			goto skip_it;
 
-		root_mnt = collect_mounts(&path);
+		paths = collect_paths(&path, array, 16);
 		path_put(&path);
-		if (IS_ERR(root_mnt))
+		if (IS_ERR(paths))
 			goto skip_it;
 
 		spin_lock(&hash_lock);
@@ -706,14 +701,17 @@ void audit_trim_trees(void)
 			struct audit_chunk *chunk = find_chunk(node);
 			/* this could be NULL if the watch is dying else where... */
 			node->index |= 1U<<31;
-			if (iterate_mounts(compare_root,
-					   (void *)(chunk->key),
-					   root_mnt))
-				node->index &= ~(1U<<31);
+			for (struct path *p = paths; p->dentry; p++) {
+				struct inode *inode = p->dentry->d_inode;
+				if (inode_to_key(inode) == chunk->key) {
+					node->index &= ~(1U<<31);
+					break;
+				}
+			}
 		}
 		spin_unlock(&hash_lock);
 		trim_marked(tree);
-		drop_collected_mounts(root_mnt);
+		drop_collected_paths(paths, array);
 skip_it:
 		put_tree(tree);
 		mutex_lock(&audit_filter_mutex);
@@ -742,9 +740,14 @@ void audit_put_tree(struct audit_tree *tree)
 	put_tree(tree);
 }
 
-static int tag_mount(struct vfsmount *mnt, void *arg)
+static int tag_mounts(struct path *paths, struct audit_tree *tree)
 {
-	return tag_chunk(d_backing_inode(mnt->mnt_root), arg);
+	for (struct path *p = paths; p->dentry; p++) {
+		int err = tag_chunk(p->dentry->d_inode, tree);
+		if (err)
+			return err;
+	}
+	return 0;
 }
 
 /*
@@ -801,7 +804,8 @@ int audit_add_tree_rule(struct audit_krule *rule)
 {
 	struct audit_tree *seed = rule->tree, *tree;
 	struct path path;
-	struct vfsmount *mnt;
+	struct path array[16];
+	struct path *paths;
 	int err;
 
 	rule->tree = NULL;
@@ -828,16 +832,16 @@ int audit_add_tree_rule(struct audit_krule *rule)
 	err = kern_path(tree->pathname, 0, &path);
 	if (err)
 		goto Err;
-	mnt = collect_mounts(&path);
+	paths = collect_paths(&path, array, 16);
 	path_put(&path);
-	if (IS_ERR(mnt)) {
-		err = PTR_ERR(mnt);
+	if (IS_ERR(paths)) {
+		err = PTR_ERR(paths);
 		goto Err;
 	}
 
 	get_tree(tree);
-	err = iterate_mounts(tag_mount, tree, mnt);
-	drop_collected_mounts(mnt);
+	err = tag_mounts(paths, tree);
+	drop_collected_paths(paths, array);
 
 	if (!err) {
 		struct audit_node *node;
@@ -872,20 +876,21 @@ int audit_tag_tree(char *old, char *new)
 	struct list_head cursor, barrier;
 	int failed = 0;
 	struct path path1, path2;
-	struct vfsmount *tagged;
+	struct path array[16];
+	struct path *paths;
 	int err;
 
 	err = kern_path(new, 0, &path2);
 	if (err)
 		return err;
-	tagged = collect_mounts(&path2);
+	paths = collect_paths(&path2, array, 16);
 	path_put(&path2);
-	if (IS_ERR(tagged))
-		return PTR_ERR(tagged);
+	if (IS_ERR(paths))
+		return PTR_ERR(paths);
 
 	err = kern_path(old, 0, &path1);
 	if (err) {
-		drop_collected_mounts(tagged);
+		drop_collected_paths(paths, array);
 		return err;
 	}
 
@@ -914,7 +919,7 @@ int audit_tag_tree(char *old, char *new)
 			continue;
 		}
 
-		failed = iterate_mounts(tag_mount, tree, tagged);
+		failed = tag_mounts(paths, tree);
 		if (failed) {
 			put_tree(tree);
 			mutex_lock(&audit_filter_mutex);
@@ -955,7 +960,7 @@ int audit_tag_tree(char *old, char *new)
 	list_del(&cursor);
 	mutex_unlock(&audit_filter_mutex);
 	path_put(&path1);
-	drop_collected_mounts(tagged);
+	drop_collected_paths(paths, array);
 	return failed;
 }
 

From ce7df19686530920f2f6b636e71ce5eb1d9303ef Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sun, 22 Jun 2025 18:03:29 -0400
Subject: [PATCH 0741/1334] attach_recursive_mnt(): do not lock the covering
 tree when sliding something under it

If we are propagating across the userns boundary, we need to lock the
mounts added there.  However, in case when something has already
been mounted there and we end up sliding a new tree under that,
the stuff that had been there before should not get locked.

IOW, lock_mnt_tree() should be called before we reparent the
preexisting tree on top of what we are adding.

Fixes: 3bd045cc9c4b ("separate copying and locking mount tree on cross-userns copies")
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/namespace.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/fs/namespace.c b/fs/namespace.c
index 14601ec4c2c5..eed83254492f 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -2768,14 +2768,14 @@ static int attach_recursive_mnt(struct mount *source_mnt,
 	hlist_for_each_entry_safe(child, n, &tree_list, mnt_hash) {
 		struct mount *q;
 		hlist_del_init(&child->mnt_hash);
-		q = __lookup_mnt(&child->mnt_parent->mnt,
-				 child->mnt_mountpoint);
-		if (q)
-			mnt_change_mountpoint(child, smp, q);
 		/* Notice when we are propagating across user namespaces */
 		if (child->mnt_parent->mnt_ns->user_ns != user_ns)
 			lock_mnt_tree(child);
 		child->mnt.mnt_flags &= ~MNT_LOCKED;
+		q = __lookup_mnt(&child->mnt_parent->mnt,
+				 child->mnt_mountpoint);
+		if (q)
+			mnt_change_mountpoint(child, smp, q);
 		commit_tree(child);
 	}
 	put_mountpoint(smp);

From aa485e8789d56a4573f7c8d000a182b749eaa64d Mon Sep 17 00:00:00 2001
From: Yuan Chen <chenyuan@kylinos.cn>
Date: Wed, 18 Jun 2025 09:19:33 +0800
Subject: [PATCH 0742/1334] libbpf: Fix null pointer dereference in
 btf_dump__free on allocation failure

When btf_dump__new() fails to allocate memory for the internal hashmap
(btf_dump->type_names), it returns an error code. However, the cleanup
function btf_dump__free() does not check if btf_dump->type_names is NULL
before attempting to free it. This leads to a null pointer dereference
when btf_dump__free() is called on a btf_dump object.

Fixes: 351131b51c7a ("libbpf: add btf_dump API for BTF-to-C conversion")
Signed-off-by: Yuan Chen <chenyuan@kylinos.cn>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20250618011933.11423-1-chenyuan_fl@163.com
---
 tools/lib/bpf/btf_dump.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/tools/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c
index 460c3e57fadb..0381f209920a 100644
--- a/tools/lib/bpf/btf_dump.c
+++ b/tools/lib/bpf/btf_dump.c
@@ -226,6 +226,9 @@ static void btf_dump_free_names(struct hashmap *map)
 	size_t bkt;
 	struct hashmap_entry *cur;
 
+	if (!map)
+		return;
+
 	hashmap__for_each_entry(map, cur, bkt)
 		free((void *)cur->pkey);
 

From f5990207026987a353d5a95204c4d9cb725637fd Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Fri, 20 Jun 2025 11:48:55 -0700
Subject: [PATCH 0743/1334] net: netpoll: Initialize UDP checksum field before
 checksumming

commit f1fce08e63fe ("netpoll: Eliminate redundant assignment") removed
the initialization of the UDP checksum, which was wrong and broke
netpoll IPv6 transmission due to bad checksumming.

udph->check needs to be set before calling csum_ipv6_magic().

Fixes: f1fce08e63fe ("netpoll: Eliminate redundant assignment")
Signed-off-by: Breno Leitao <leitao@debian.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250620-netpoll_fix-v1-1-f9f0b82bc059@debian.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/netpoll.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index 4ddb7490df4b..6ad84d4a2b46 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -432,6 +432,7 @@ int netpoll_send_udp(struct netpoll *np, const char *msg, int len)
 	udph->dest = htons(np->remote_port);
 	udph->len = htons(udp_len);
 
+	udph->check = 0;
 	if (np->ipv6) {
 		udph->check = csum_ipv6_magic(&np->local_ip.in6,
 					      &np->remote_ip.in6,
@@ -460,7 +461,6 @@ int netpoll_send_udp(struct netpoll *np, const char *msg, int len)
 		skb_reset_mac_header(skb);
 		skb->protocol = eth->h_proto = htons(ETH_P_IPV6);
 	} else {
-		udph->check = 0;
 		udph->check = csum_tcpudp_magic(np->local_ip.ip,
 						np->remote_ip.ip,
 						udp_len, IPPROTO_UDP,

From 2b8be57fa0c88ac824a906f29c04d728f9f6047a Mon Sep 17 00:00:00 2001
From: Zhe Qiao <qiaozhe@iscas.ac.cn>
Date: Thu, 19 Jun 2025 15:26:08 +0800
Subject: [PATCH 0744/1334] Revert "PCI/ACPI: Fix allocated memory release on
 error in pci_acpi_scan_root()"

This reverts commit 631b2af2f357 ("PCI/ACPI: Fix allocated memory release
on error in pci_acpi_scan_root()").

The reverted patch causes the 'ri->cfg' and 'root_ops' resources to be
released multiple times.

When acpi_pci_root_create() fails, these resources have already been
released internally by the __acpi_pci_root_release_info() function.

Releasing them again in pci_acpi_scan_root() leads to incorrect behavior
and potential memory issues.

We plan to resolve the issue using a more appropriate fix.

Reported-by: Dan Carpenter <dan.carpenter@linaro.org>
Closes: https://lore.kernel.org/all/aEmdnuw715btq7Q5@stanley.mountain/
Signed-off-by: Zhe Qiao <qiaozhe@iscas.ac.cn>
Acked-by: Dan Carpenter <dan.carpenter@linaro.org>
Link: https://patch.msgid.link/20250619072608.2075475-1-qiaozhe@iscas.ac.cn
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/pci/pci-acpi.c | 23 ++++++++++-------------
 1 file changed, 10 insertions(+), 13 deletions(-)

diff --git a/drivers/pci/pci-acpi.c b/drivers/pci/pci-acpi.c
index b78e0e417324..af370628e583 100644
--- a/drivers/pci/pci-acpi.c
+++ b/drivers/pci/pci-acpi.c
@@ -1676,19 +1676,24 @@ struct pci_bus *pci_acpi_scan_root(struct acpi_pci_root *root)
 		return NULL;
 
 	root_ops = kzalloc(sizeof(*root_ops), GFP_KERNEL);
-	if (!root_ops)
-		goto free_ri;
+	if (!root_ops) {
+		kfree(ri);
+		return NULL;
+	}
 
 	ri->cfg = pci_acpi_setup_ecam_mapping(root);
-	if (!ri->cfg)
-		goto free_root_ops;
+	if (!ri->cfg) {
+		kfree(ri);
+		kfree(root_ops);
+		return NULL;
+	}
 
 	root_ops->release_info = pci_acpi_generic_release_info;
 	root_ops->prepare_resources = pci_acpi_root_prepare_resources;
 	root_ops->pci_ops = (struct pci_ops *)&ri->cfg->ops->pci_ops;
 	bus = acpi_pci_root_create(root, root_ops, &ri->common, ri->cfg);
 	if (!bus)
-		goto free_cfg;
+		return NULL;
 
 	/* If we must preserve the resource configuration, claim now */
 	host = pci_find_host_bridge(bus);
@@ -1705,14 +1710,6 @@ struct pci_bus *pci_acpi_scan_root(struct acpi_pci_root *root)
 		pcie_bus_configure_settings(child);
 
 	return bus;
-
-free_cfg:
-	pci_ecam_free(ri->cfg);
-free_root_ops:
-	kfree(root_ops);
-free_ri:
-	kfree(ri);
-	return NULL;
 }
 
 void pcibios_add_bus(struct pci_bus *bus)

From 002cc0ee90e6172ef40ae95c248bf6ce67fb3f3f Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Andr=C3=A9=20Draszik?= <andre.draszik@linaro.org>
Date: Wed, 9 Apr 2025 21:37:46 +0100
Subject: [PATCH 0745/1334] rtc: s5m: cache device type during probe
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

platform_get_device_id() is called mulitple times during probe to
retrieve the device type. This makes the code harder to read than
necessary.

Just get the type once, which also trims the lengths of the lines
involved.

Signed-off-by: André Draszik <andre.draszik@linaro.org>
Link: https://lore.kernel.org/r/20250409-s2mpg10-v4-25-d66d5f39b6bf@linaro.org
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-s5m.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/drivers/rtc/rtc-s5m.c b/drivers/rtc/rtc-s5m.c
index db5c9b641277..c7636738b797 100644
--- a/drivers/rtc/rtc-s5m.c
+++ b/drivers/rtc/rtc-s5m.c
@@ -637,6 +637,8 @@ static int s5m8767_rtc_init_reg(struct s5m_rtc_info *info)
 static int s5m_rtc_probe(struct platform_device *pdev)
 {
 	struct sec_pmic_dev *s5m87xx = dev_get_drvdata(pdev->dev.parent);
+	enum sec_device_type device_type =
+		platform_get_device_id(pdev)->driver_data;
 	struct s5m_rtc_info *info;
 	struct i2c_client *i2c;
 	const struct regmap_config *regmap_cfg;
@@ -646,7 +648,7 @@ static int s5m_rtc_probe(struct platform_device *pdev)
 	if (!info)
 		return -ENOMEM;
 
-	switch (platform_get_device_id(pdev)->driver_data) {
+	switch (device_type) {
 	case S2MPS15X:
 		regmap_cfg = &s2mps14_rtc_regmap_config;
 		info->regs = &s2mps15_rtc_regs;
@@ -669,8 +671,8 @@ static int s5m_rtc_probe(struct platform_device *pdev)
 		break;
 	default:
 		return dev_err_probe(&pdev->dev, -ENODEV,
-				     "Device type %lu is not supported by RTC driver\n",
-				     platform_get_device_id(pdev)->driver_data);
+				     "Device type %d is not supported by RTC driver\n",
+				     device_type);
 	}
 
 	i2c = devm_i2c_new_dummy_device(&pdev->dev, s5m87xx->i2c->adapter,
@@ -686,7 +688,7 @@ static int s5m_rtc_probe(struct platform_device *pdev)
 
 	info->dev = &pdev->dev;
 	info->s5m87xx = s5m87xx;
-	info->device_type = platform_get_device_id(pdev)->driver_data;
+	info->device_type = device_type;
 
 	if (s5m87xx->irq_data) {
 		info->irq = regmap_irq_get_virq(s5m87xx->irq_data, alarm_irq);

From a57743bf009e788ada3607ac6b74ae9ebbd4ed74 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Andr=C3=A9=20Draszik?= <andre.draszik@linaro.org>
Date: Wed, 9 Apr 2025 21:37:47 +0100
Subject: [PATCH 0746/1334] rtc: s5m: prepare for external regmap
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The Samsung S2MPG10 PMIC is not connected via I2C as this driver
assumes, hence this driver's current approach of creating an I2C-based
regmap doesn't work for it, and this driver should use the regmap
provided by the parent (core) driver instead for that PMIC.

To prepare this driver for s2mpg support, restructure the code to only
create a regmap if one isn't provided by the parent.

No functional changes, since the parent doesn't provide a regmap for
any of the PMICs currently supported by this driver. Having this change
separate will simply make the addition of S2MPG10 support more
self-contained, without additional restructuring.

Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: André Draszik <andre.draszik@linaro.org>
Link: https://lore.kernel.org/r/20250409-s2mpg10-v4-26-d66d5f39b6bf@linaro.org
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-s5m.c | 81 ++++++++++++++++++++++++-------------------
 1 file changed, 45 insertions(+), 36 deletions(-)

diff --git a/drivers/rtc/rtc-s5m.c b/drivers/rtc/rtc-s5m.c
index c7636738b797..f8abcdee8611 100644
--- a/drivers/rtc/rtc-s5m.c
+++ b/drivers/rtc/rtc-s5m.c
@@ -640,52 +640,61 @@ static int s5m_rtc_probe(struct platform_device *pdev)
 	enum sec_device_type device_type =
 		platform_get_device_id(pdev)->driver_data;
 	struct s5m_rtc_info *info;
-	struct i2c_client *i2c;
-	const struct regmap_config *regmap_cfg;
 	int ret, alarm_irq;
 
 	info = devm_kzalloc(&pdev->dev, sizeof(*info), GFP_KERNEL);
 	if (!info)
 		return -ENOMEM;
 
-	switch (device_type) {
-	case S2MPS15X:
-		regmap_cfg = &s2mps14_rtc_regmap_config;
-		info->regs = &s2mps15_rtc_regs;
-		alarm_irq = S2MPS14_IRQ_RTCA0;
-		break;
-	case S2MPS14X:
-		regmap_cfg = &s2mps14_rtc_regmap_config;
-		info->regs = &s2mps14_rtc_regs;
-		alarm_irq = S2MPS14_IRQ_RTCA0;
-		break;
-	case S2MPS13X:
-		regmap_cfg = &s2mps14_rtc_regmap_config;
-		info->regs = &s2mps13_rtc_regs;
-		alarm_irq = S2MPS14_IRQ_RTCA0;
-		break;
-	case S5M8767X:
-		regmap_cfg = &s5m_rtc_regmap_config;
-		info->regs = &s5m_rtc_regs;
-		alarm_irq = S5M8767_IRQ_RTCA1;
-		break;
-	default:
+	info->regmap = dev_get_regmap(pdev->dev.parent, "rtc");
+	if (!info->regmap) {
+		const struct regmap_config *regmap_cfg;
+		struct i2c_client *i2c;
+
+		switch (device_type) {
+		case S2MPS15X:
+			regmap_cfg = &s2mps14_rtc_regmap_config;
+			info->regs = &s2mps15_rtc_regs;
+			alarm_irq = S2MPS14_IRQ_RTCA0;
+			break;
+		case S2MPS14X:
+			regmap_cfg = &s2mps14_rtc_regmap_config;
+			info->regs = &s2mps14_rtc_regs;
+			alarm_irq = S2MPS14_IRQ_RTCA0;
+			break;
+		case S2MPS13X:
+			regmap_cfg = &s2mps14_rtc_regmap_config;
+			info->regs = &s2mps13_rtc_regs;
+			alarm_irq = S2MPS14_IRQ_RTCA0;
+			break;
+		case S5M8767X:
+			regmap_cfg = &s5m_rtc_regmap_config;
+			info->regs = &s5m_rtc_regs;
+			alarm_irq = S5M8767_IRQ_RTCA1;
+			break;
+		default:
+			return dev_err_probe(&pdev->dev, -ENODEV,
+					     "Unsupported device type %d\n",
+					     device_type);
+		}
+
+		i2c = devm_i2c_new_dummy_device(&pdev->dev,
+						s5m87xx->i2c->adapter,
+						RTC_I2C_ADDR);
+		if (IS_ERR(i2c))
+			return dev_err_probe(&pdev->dev, PTR_ERR(i2c),
+					     "Failed to allocate I2C\n");
+
+		info->regmap = devm_regmap_init_i2c(i2c, regmap_cfg);
+		if (IS_ERR(info->regmap))
+			return dev_err_probe(&pdev->dev, PTR_ERR(info->regmap),
+					     "Failed to allocate regmap\n");
+	} else {
 		return dev_err_probe(&pdev->dev, -ENODEV,
-				     "Device type %d is not supported by RTC driver\n",
+				     "Unsupported device type %d\n",
 				     device_type);
 	}
 
-	i2c = devm_i2c_new_dummy_device(&pdev->dev, s5m87xx->i2c->adapter,
-					RTC_I2C_ADDR);
-	if (IS_ERR(i2c))
-		return dev_err_probe(&pdev->dev, PTR_ERR(i2c),
-				     "Failed to allocate I2C for RTC\n");
-
-	info->regmap = devm_regmap_init_i2c(i2c, regmap_cfg);
-	if (IS_ERR(info->regmap))
-		return dev_err_probe(&pdev->dev, PTR_ERR(info->regmap),
-				     "Failed to allocate RTC register map\n");
-
 	info->dev = &pdev->dev;
 	info->s5m87xx = s5m87xx;
 	info->device_type = device_type;

From e64180846e7e4397938bbd0acf0640836f0f8051 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Andr=C3=A9=20Draszik?= <andre.draszik@linaro.org>
Date: Wed, 9 Apr 2025 21:37:48 +0100
Subject: [PATCH 0747/1334] rtc: s5m: add support for S2MPG10 RTC
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add support for Samsung's S2MPG10 PMIC RTC, which is similar to the
existing PMIC RTCs supported by this driver.

S2MPG10 doesn't use I2C, so we expect the core driver to have created a
regmap for us.

Additionally, it can be used for doing a cold-reset. If requested to do
so (via DT), S2MPG10 is programmed with a watchdog configuration that
will perform a full power cycle upon watchdog expiry.

Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: André Draszik <andre.draszik@linaro.org>
Link: https://lore.kernel.org/r/20250409-s2mpg10-v4-27-d66d5f39b6bf@linaro.org
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-s5m.c | 60 +++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 60 insertions(+)

diff --git a/drivers/rtc/rtc-s5m.c b/drivers/rtc/rtc-s5m.c
index f8abcdee8611..c6394faaee86 100644
--- a/drivers/rtc/rtc-s5m.c
+++ b/drivers/rtc/rtc-s5m.c
@@ -10,6 +10,7 @@
 #include <linux/module.h>
 #include <linux/i2c.h>
 #include <linux/bcd.h>
+#include <linux/reboot.h>
 #include <linux/regmap.h>
 #include <linux/rtc.h>
 #include <linux/platform_device.h>
@@ -53,6 +54,7 @@ enum {
  * Device     | Write time | Read time | Write alarm
  * =================================================
  * S5M8767    | UDR + TIME |           | UDR
+ * S2MPG10    | WUDR       | RUDR      | AUDR
  * S2MPS11/14 | WUDR       | RUDR      | WUDR + RUDR
  * S2MPS13    | WUDR       | RUDR      | WUDR + AUDR
  * S2MPS15    | WUDR       | RUDR      | AUDR
@@ -99,6 +101,20 @@ static const struct s5m_rtc_reg_config s5m_rtc_regs = {
 	.write_alarm_udr_mask	= S5M_RTC_UDR_MASK,
 };
 
+/* Register map for S2MPG10 */
+static const struct s5m_rtc_reg_config s2mpg10_rtc_regs = {
+	.regs_count		= 7,
+	.time			= S2MPG10_RTC_SEC,
+	.ctrl			= S2MPG10_RTC_CTRL,
+	.alarm0			= S2MPG10_RTC_A0SEC,
+	.alarm1			= S2MPG10_RTC_A1SEC,
+	.udr_update		= S2MPG10_RTC_UPDATE,
+	.autoclear_udr_mask	= S2MPS15_RTC_WUDR_MASK | S2MPS15_RTC_AUDR_MASK,
+	.read_time_udr_mask	= S2MPS_RTC_RUDR_MASK,
+	.write_time_udr_mask	= S2MPS15_RTC_WUDR_MASK,
+	.write_alarm_udr_mask	= S2MPS15_RTC_AUDR_MASK,
+};
+
 /* Register map for S2MPS13 */
 static const struct s5m_rtc_reg_config s2mps13_rtc_regs = {
 	.regs_count		= 7,
@@ -238,6 +254,7 @@ static int s5m_check_peding_alarm_interrupt(struct s5m_rtc_info *info,
 		ret = regmap_read(info->regmap, S5M_RTC_STATUS, &val);
 		val &= S5M_ALARM0_STATUS;
 		break;
+	case S2MPG10:
 	case S2MPS15X:
 	case S2MPS14X:
 	case S2MPS13X:
@@ -300,6 +317,7 @@ static int s5m8767_rtc_set_alarm_reg(struct s5m_rtc_info *info)
 	case S5M8767X:
 		data &= ~S5M_RTC_TIME_EN_MASK;
 		break;
+	case S2MPG10:
 	case S2MPS15X:
 	case S2MPS14X:
 	case S2MPS13X:
@@ -351,6 +369,7 @@ static int s5m_rtc_read_time(struct device *dev, struct rtc_time *tm)
 
 	switch (info->device_type) {
 	case S5M8767X:
+	case S2MPG10:
 	case S2MPS15X:
 	case S2MPS14X:
 	case S2MPS13X:
@@ -374,6 +393,7 @@ static int s5m_rtc_set_time(struct device *dev, struct rtc_time *tm)
 
 	switch (info->device_type) {
 	case S5M8767X:
+	case S2MPG10:
 	case S2MPS15X:
 	case S2MPS14X:
 	case S2MPS13X:
@@ -411,6 +431,7 @@ static int s5m_rtc_read_alarm(struct device *dev, struct rtc_wkalrm *alrm)
 
 	switch (info->device_type) {
 	case S5M8767X:
+	case S2MPG10:
 	case S2MPS15X:
 	case S2MPS14X:
 	case S2MPS13X:
@@ -449,6 +470,7 @@ static int s5m_rtc_stop_alarm(struct s5m_rtc_info *info)
 
 	switch (info->device_type) {
 	case S5M8767X:
+	case S2MPG10:
 	case S2MPS15X:
 	case S2MPS14X:
 	case S2MPS13X:
@@ -487,6 +509,7 @@ static int s5m_rtc_start_alarm(struct s5m_rtc_info *info)
 
 	switch (info->device_type) {
 	case S5M8767X:
+	case S2MPG10:
 	case S2MPS15X:
 	case S2MPS14X:
 	case S2MPS13X:
@@ -524,6 +547,7 @@ static int s5m_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alrm)
 
 	switch (info->device_type) {
 	case S5M8767X:
+	case S2MPG10:
 	case S2MPS15X:
 	case S2MPS14X:
 	case S2MPS13X:
@@ -604,6 +628,7 @@ static int s5m8767_rtc_init_reg(struct s5m_rtc_info *info)
 		ret = regmap_raw_write(info->regmap, S5M_ALARM0_CONF, data, 2);
 		break;
 
+	case S2MPG10:
 	case S2MPS15X:
 	case S2MPS14X:
 	case S2MPS13X:
@@ -634,6 +659,25 @@ static int s5m8767_rtc_init_reg(struct s5m_rtc_info *info)
 	return ret;
 }
 
+static int s5m_rtc_restart_s2mpg10(struct sys_off_data *data)
+{
+	struct s5m_rtc_info *info = data->cb_data;
+	int ret;
+
+	if (data->mode != REBOOT_COLD && data->mode != REBOOT_HARD)
+		return NOTIFY_DONE;
+
+	/*
+	 * Arm watchdog with maximum timeout (2 seconds), and perform full reset
+	 * on expiry.
+	 */
+	ret = regmap_set_bits(info->regmap, S2MPG10_RTC_WTSR,
+			      (S2MPG10_WTSR_COLDTIMER | S2MPG10_WTSR_COLDRST
+			       | S2MPG10_WTSR_WTSRT | S2MPG10_WTSR_WTSR_EN));
+
+	return ret ? NOTIFY_BAD : NOTIFY_DONE;
+}
+
 static int s5m_rtc_probe(struct platform_device *pdev)
 {
 	struct sec_pmic_dev *s5m87xx = dev_get_drvdata(pdev->dev.parent);
@@ -689,6 +733,9 @@ static int s5m_rtc_probe(struct platform_device *pdev)
 		if (IS_ERR(info->regmap))
 			return dev_err_probe(&pdev->dev, PTR_ERR(info->regmap),
 					     "Failed to allocate regmap\n");
+	} else if (device_type == S2MPG10) {
+		info->regs = &s2mpg10_rtc_regs;
+		alarm_irq = S2MPG10_IRQ_RTCA0;
 	} else {
 		return dev_err_probe(&pdev->dev, -ENODEV,
 				     "Unsupported device type %d\n",
@@ -735,6 +782,18 @@ static int s5m_rtc_probe(struct platform_device *pdev)
 		device_init_wakeup(&pdev->dev, true);
 	}
 
+	if (of_device_is_system_power_controller(pdev->dev.parent->of_node) &&
+	    info->device_type == S2MPG10) {
+		ret = devm_register_sys_off_handler(&pdev->dev,
+						    SYS_OFF_MODE_RESTART,
+						    SYS_OFF_PRIO_HIGH + 1,
+						    s5m_rtc_restart_s2mpg10,
+						    info);
+		if (ret)
+			return dev_err_probe(&pdev->dev, ret,
+				       "Failed to register restart handler\n");
+	}
+
 	return devm_rtc_register_device(info->rtc_dev);
 }
 
@@ -766,6 +825,7 @@ static SIMPLE_DEV_PM_OPS(s5m_rtc_pm_ops, s5m_rtc_suspend, s5m_rtc_resume);
 
 static const struct platform_device_id s5m_rtc_id[] = {
 	{ "s5m-rtc",		S5M8767X },
+	{ "s2mpg10-rtc",	S2MPG10 },
 	{ "s2mps13-rtc",	S2MPS13X },
 	{ "s2mps14-rtc",	S2MPS14X },
 	{ "s2mps15-rtc",	S2MPS15X },

From 972a3b47f6e191a0c5afcc45f4de74bf3d043a75 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Andr=C3=A9=20Draszik?= <andre.draszik@linaro.org>
Date: Wed, 9 Apr 2025 21:37:49 +0100
Subject: [PATCH 0748/1334] rtc: s5m: fix a typo: peding -> pending
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Fix this minor typo, and adjust the a related incorrect alignment to
avoid a checkpatch error.

Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: André Draszik <andre.draszik@linaro.org>
Link: https://lore.kernel.org/r/20250409-s2mpg10-v4-28-d66d5f39b6bf@linaro.org
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-s5m.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/rtc/rtc-s5m.c b/drivers/rtc/rtc-s5m.c
index c6394faaee86..095b090ec394 100644
--- a/drivers/rtc/rtc-s5m.c
+++ b/drivers/rtc/rtc-s5m.c
@@ -243,8 +243,8 @@ static int s5m8767_wait_for_udr_update(struct s5m_rtc_info *info)
 	return ret;
 }
 
-static int s5m_check_peding_alarm_interrupt(struct s5m_rtc_info *info,
-		struct rtc_wkalrm *alarm)
+static int s5m_check_pending_alarm_interrupt(struct s5m_rtc_info *info,
+					     struct rtc_wkalrm *alarm)
 {
 	int ret;
 	unsigned int val;
@@ -451,7 +451,7 @@ static int s5m_rtc_read_alarm(struct device *dev, struct rtc_wkalrm *alrm)
 
 	dev_dbg(dev, "%s: %ptR(%d)\n", __func__, &alrm->time, alrm->time.tm_wday);
 
-	return s5m_check_peding_alarm_interrupt(info, alrm);
+	return s5m_check_pending_alarm_interrupt(info, alrm);
 }
 
 static int s5m_rtc_stop_alarm(struct s5m_rtc_info *info)

From 1dd609587414f8b2844e551d1fe0505f12871992 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Andr=C3=A9=20Draszik?= <andre.draszik@linaro.org>
Date: Wed, 9 Apr 2025 21:37:50 +0100
Subject: [PATCH 0749/1334] rtc: s5m: switch to devm_device_init_wakeup
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

To release memory allocated by device_init_wakeup(true), drivers have
to call device_init_wakeup(false) in error paths and unbind.

Switch to the new devres managed version devm_device_init_wakeup() to
plug this memleak.

Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: André Draszik <andre.draszik@linaro.org>
Link: https://lore.kernel.org/r/20250409-s2mpg10-v4-29-d66d5f39b6bf@linaro.org
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-s5m.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/rtc/rtc-s5m.c b/drivers/rtc/rtc-s5m.c
index 095b090ec394..f4caed953efd 100644
--- a/drivers/rtc/rtc-s5m.c
+++ b/drivers/rtc/rtc-s5m.c
@@ -779,7 +779,11 @@ static int s5m_rtc_probe(struct platform_device *pdev)
 			return dev_err_probe(&pdev->dev, ret,
 					     "Failed to request alarm IRQ %d\n",
 					     info->irq);
-		device_init_wakeup(&pdev->dev, true);
+
+		ret = devm_device_init_wakeup(&pdev->dev);
+		if (ret < 0)
+			return dev_err_probe(&pdev->dev, ret,
+					     "Failed to init wakeup\n");
 	}
 
 	if (of_device_is_system_power_controller(pdev->dev.parent->of_node) &&

From f5adb1fa04d08731a13db48afafd1a5f4384d3c9 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Andr=C3=A9=20Draszik?= <andre.draszik@linaro.org>
Date: Wed, 9 Apr 2025 21:37:51 +0100
Subject: [PATCH 0750/1334] rtc: s5m: replace regmap_update_bits with
 regmap_clear/set_bits
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The regmap_clear_bits() and regmap_set_bits() helper macros state the
intention a bit more obviously.

Use those.

Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: André Draszik <andre.draszik@linaro.org>
Link: https://lore.kernel.org/r/20250409-s2mpg10-v4-30-d66d5f39b6bf@linaro.org
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-s5m.c | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

diff --git a/drivers/rtc/rtc-s5m.c b/drivers/rtc/rtc-s5m.c
index f4caed953efd..27115523b8c2 100644
--- a/drivers/rtc/rtc-s5m.c
+++ b/drivers/rtc/rtc-s5m.c
@@ -338,8 +338,8 @@ static int s5m8767_rtc_set_alarm_reg(struct s5m_rtc_info *info)
 
 	/* On S2MPS13 the AUDR is not auto-cleared */
 	if (info->device_type == S2MPS13X)
-		regmap_update_bits(info->regmap, info->regs->udr_update,
-				   S2MPS13_RTC_AUDR_MASK, 0);
+		regmap_clear_bits(info->regmap, info->regs->udr_update,
+				  S2MPS13_RTC_AUDR_MASK);
 
 	return ret;
 }
@@ -351,10 +351,8 @@ static int s5m_rtc_read_time(struct device *dev, struct rtc_time *tm)
 	int ret;
 
 	if (info->regs->read_time_udr_mask) {
-		ret = regmap_update_bits(info->regmap,
-				info->regs->udr_update,
-				info->regs->read_time_udr_mask,
-				info->regs->read_time_udr_mask);
+		ret = regmap_set_bits(info->regmap, info->regs->udr_update,
+				      info->regs->read_time_udr_mask);
 		if (ret) {
 			dev_err(dev,
 				"Failed to prepare registers for time reading: %d\n",

From b1248da008362323f75e8b84874586e9ea4c0b31 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Andr=C3=A9=20Draszik?= <andre.draszik@linaro.org>
Date: Wed, 9 Apr 2025 21:37:52 +0100
Subject: [PATCH 0751/1334] rtc: s5m: replace open-coded read/modify/write
 registers with regmap helpers
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Instead of the open-coded read/modify/write sequence, we can simply use
the regmap helpers regmap_set_bits() and regmap_update_bits()
respectively.

This makes the code easier to read, and avoids extra work in case the
underlying bus supports updating bits via
struct regmap_bus::reg_update_bits() directly (which is the case for
S2MPG10 on gs101 where this driver communicates via ACPM).

Signed-off-by: André Draszik <andre.draszik@linaro.org>
Link: https://lore.kernel.org/r/20250409-s2mpg10-v4-31-d66d5f39b6bf@linaro.org
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-s5m.c | 28 +++++++---------------------
 1 file changed, 7 insertions(+), 21 deletions(-)

diff --git a/drivers/rtc/rtc-s5m.c b/drivers/rtc/rtc-s5m.c
index 27115523b8c2..a7220b4d0e8d 100644
--- a/drivers/rtc/rtc-s5m.c
+++ b/drivers/rtc/rtc-s5m.c
@@ -279,17 +279,9 @@ static int s5m_check_pending_alarm_interrupt(struct s5m_rtc_info *info,
 static int s5m8767_rtc_set_time_reg(struct s5m_rtc_info *info)
 {
 	int ret;
-	unsigned int data;
 
-	ret = regmap_read(info->regmap, info->regs->udr_update, &data);
-	if (ret < 0) {
-		dev_err(info->dev, "failed to read update reg(%d)\n", ret);
-		return ret;
-	}
-
-	data |= info->regs->write_time_udr_mask;
-
-	ret = regmap_write(info->regmap, info->regs->udr_update, data);
+	ret = regmap_set_bits(info->regmap, info->regs->udr_update,
+			      info->regs->write_time_udr_mask);
 	if (ret < 0) {
 		dev_err(info->dev, "failed to write update reg(%d)\n", ret);
 		return ret;
@@ -303,19 +295,12 @@ static int s5m8767_rtc_set_time_reg(struct s5m_rtc_info *info)
 static int s5m8767_rtc_set_alarm_reg(struct s5m_rtc_info *info)
 {
 	int ret;
-	unsigned int data;
+	unsigned int udr_mask;
 
-	ret = regmap_read(info->regmap, info->regs->udr_update, &data);
-	if (ret < 0) {
-		dev_err(info->dev, "%s: fail to read update reg(%d)\n",
-			__func__, ret);
-		return ret;
-	}
-
-	data |= info->regs->write_alarm_udr_mask;
+	udr_mask = info->regs->write_alarm_udr_mask;
 	switch (info->device_type) {
 	case S5M8767X:
-		data &= ~S5M_RTC_TIME_EN_MASK;
+		udr_mask |= S5M_RTC_TIME_EN_MASK;
 		break;
 	case S2MPG10:
 	case S2MPS15X:
@@ -327,7 +312,8 @@ static int s5m8767_rtc_set_alarm_reg(struct s5m_rtc_info *info)
 		return -EINVAL;
 	}
 
-	ret = regmap_write(info->regmap, info->regs->udr_update, data);
+	ret = regmap_update_bits(info->regmap, info->regs->udr_update,
+				 udr_mask, info->regs->write_alarm_udr_mask);
 	if (ret < 0) {
 		dev_err(info->dev, "%s: fail to write update reg(%d)\n",
 			__func__, ret);

From 10357824151262636fda879845f8b64553541106 Mon Sep 17 00:00:00 2001
From: Chaoyi Chen <chaoyi.chen@rock-chips.com>
Date: Fri, 20 Jun 2025 09:16:16 +0800
Subject: [PATCH 0752/1334] drm/bridge-connector: Fix bridge in
 drm_connector_hdmi_audio_init()

The bridge used in drm_connector_hdmi_audio_init() does not correctly
point to the required audio bridge, which lead to incorrect audio
configuration input.

Fixes: 231adeda9f67 ("drm/bridge-connector: hook DisplayPort audio support")
Signed-off-by: Chaoyi Chen <chaoyi.chen@rock-chips.com>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
Tested-by: Stephan Gerhold <stephan.gerhold@linaro.org>
Link: https://lore.kernel.org/r/20250620011616.118-1-kernel@airkyi.com
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
---
 drivers/gpu/drm/display/drm_bridge_connector.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/display/drm_bridge_connector.c b/drivers/gpu/drm/display/drm_bridge_connector.c
index 7d2e499ea5de..262e93e07a28 100644
--- a/drivers/gpu/drm/display/drm_bridge_connector.c
+++ b/drivers/gpu/drm/display/drm_bridge_connector.c
@@ -708,11 +708,14 @@ struct drm_connector *drm_bridge_connector_init(struct drm_device *drm,
 	if (bridge_connector->bridge_hdmi_audio ||
 	    bridge_connector->bridge_dp_audio) {
 		struct device *dev;
+		struct drm_bridge *bridge;
 
 		if (bridge_connector->bridge_hdmi_audio)
-			dev = bridge_connector->bridge_hdmi_audio->hdmi_audio_dev;
+			bridge = bridge_connector->bridge_hdmi_audio;
 		else
-			dev = bridge_connector->bridge_dp_audio->hdmi_audio_dev;
+			bridge = bridge_connector->bridge_dp_audio;
+
+		dev = bridge->hdmi_audio_dev;
 
 		ret = drm_connector_hdmi_audio_init(connector, dev,
 						    &drm_bridge_connector_hdmi_audio_funcs,

From 00a39d8652ff9088de07a6fe6e9e1893452fe0dd Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Mateusz=20Jo=C5=84czyk?= <mat.jonczyk@o2.pl>
Date: Sat, 7 Jun 2025 23:06:08 +0200
Subject: [PATCH 0753/1334] rtc: cmos: use spin_lock_irqsave in cmos_interrupt
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

cmos_interrupt() can be called in a non-interrupt context, such as in
an ACPI event handler (which runs in an interrupt thread). Therefore,
usage of spin_lock(&rtc_lock) is insecure. Use spin_lock_irqsave() /
spin_unlock_irqrestore() instead.

Before a misguided
commit 6950d046eb6e ("rtc: cmos: Replace spin_lock_irqsave with spin_lock in hard IRQ")
the cmos_interrupt() function used spin_lock_irqsave(). That commit
changed it to spin_lock() and broke locking, which was partially fixed in
commit 13be2efc390a ("rtc: cmos: Disable irq around direct invocation of cmos_interrupt()")

That second commit did not take account of the ACPI fixed event handler
pathway, however. It introduced local_irq_disable() workarounds in
cmos_check_wkalrm(), which can cause problems on PREEMPT_RT kernels
and are now unnecessary.

Add an explicit comment so that this change will not be reverted by
mistake.

Cc: stable@vger.kernel.org
Fixes: 6950d046eb6e ("rtc: cmos: Replace spin_lock_irqsave with spin_lock in hard IRQ")
Signed-off-by: Mateusz Jończyk <mat.jonczyk@o2.pl>
Reviewed-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Tested-by: Chris Bainbridge <chris.bainbridge@gmail.com>
Reported-by: Chris Bainbridge <chris.bainbridge@gmail.com>
Closes: https://lore.kernel.org/all/aDtJ92foPUYmGheF@debian.local/
Link: https://lore.kernel.org/r/20250607210608.14835-1-mat.jonczyk@o2.pl
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-cmos.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/drivers/rtc/rtc-cmos.c b/drivers/rtc/rtc-cmos.c
index 8172869bd3d7..0743c6acd6e2 100644
--- a/drivers/rtc/rtc-cmos.c
+++ b/drivers/rtc/rtc-cmos.c
@@ -692,8 +692,12 @@ static irqreturn_t cmos_interrupt(int irq, void *p)
 {
 	u8		irqstat;
 	u8		rtc_control;
+	unsigned long	flags;
 
-	spin_lock(&rtc_lock);
+	/* We cannot use spin_lock() here, as cmos_interrupt() is also called
+	 * in a non-irq context.
+	 */
+	spin_lock_irqsave(&rtc_lock, flags);
 
 	/* When the HPET interrupt handler calls us, the interrupt
 	 * status is passed as arg1 instead of the irq number.  But
@@ -727,7 +731,7 @@ static irqreturn_t cmos_interrupt(int irq, void *p)
 			hpet_mask_rtc_irq_bit(RTC_AIE);
 		CMOS_READ(RTC_INTR_FLAGS);
 	}
-	spin_unlock(&rtc_lock);
+	spin_unlock_irqrestore(&rtc_lock, flags);
 
 	if (is_intr(irqstat)) {
 		rtc_update_irq(p, 1, irqstat);
@@ -1295,9 +1299,7 @@ static void cmos_check_wkalrm(struct device *dev)
 	 * ACK the rtc irq here
 	 */
 	if (t_now >= cmos->alarm_expires && cmos_use_acpi_alarm()) {
-		local_irq_disable();
 		cmos_interrupt(0, (void *)cmos->rtc);
-		local_irq_enable();
 		return;
 	}
 

From 2f73c62d4e13df67380ff6faca39eec2bf08dd93 Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Fri, 20 Jun 2025 13:09:39 +0200
Subject: [PATCH 0754/1334] Revert "riscv: misaligned: fix sleeping function
 called during misaligned access handling"
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This reverts commit 61a74ad25462 ("riscv: misaligned: fix sleeping function
called during misaligned access handling"). The commit addresses a sleeping
in atomic context problem, but it is not the correct fix as explained by
Clément:

"Using nofault would lead to failure to read from user memory that is paged
out for instance. This is not really acceptable, we should handle user
misaligned access even at an address that would generate a page fault."

This bug has been properly fixed by commit 453805f0a28f ("riscv:
misaligned: enable IRQs while handling misaligned accesses").

Revert this improper fix.

Link: https://lore.kernel.org/linux-riscv/b779beed-e44e-4a5e-9551-4647682b0d21@rivosinc.com/
Signed-off-by: Nam Cao <namcao@linutronix.de>
Cc: stable@vger.kernel.org
Reviewed-by: Clément Léger <cleger@rivosinc.com>
Reviewed-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Fixes: 61a74ad25462 ("riscv: misaligned: fix sleeping function called during misaligned access handling")
Link: https://lore.kernel.org/r/20250620110939.1642735-1-namcao@linutronix.de
Signed-off-by: Palmer Dabbelt <palmer@dabbelt.com>
---
 arch/riscv/kernel/traps_misaligned.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/riscv/kernel/traps_misaligned.c b/arch/riscv/kernel/traps_misaligned.c
index dd8e4af6583f..93043924fe6c 100644
--- a/arch/riscv/kernel/traps_misaligned.c
+++ b/arch/riscv/kernel/traps_misaligned.c
@@ -454,7 +454,7 @@ static int handle_scalar_misaligned_load(struct pt_regs *regs)
 
 	val.data_u64 = 0;
 	if (user_mode(regs)) {
-		if (copy_from_user_nofault(&val, (u8 __user *)addr, len))
+		if (copy_from_user(&val, (u8 __user *)addr, len))
 			return -1;
 	} else {
 		memcpy(&val, (u8 *)addr, len);
@@ -555,7 +555,7 @@ static int handle_scalar_misaligned_store(struct pt_regs *regs)
 		return -EOPNOTSUPP;
 
 	if (user_mode(regs)) {
-		if (copy_to_user_nofault((u8 __user *)addr, &val, len))
+		if (copy_to_user((u8 __user *)addr, &val, len))
 			return -1;
 	} else {
 		memcpy((u8 *)addr, &val, len);

From b0843f836126c980fb31923563c86ec52e8b9514 Mon Sep 17 00:00:00 2001
From: Alexandre Ghiti <alexghiti@rivosinc.com>
Date: Fri, 20 Jun 2025 12:08:11 +0000
Subject: [PATCH 0755/1334] riscv: Fix sparse warning in
 vendor_extensions/sifive.c

sparse reports the following warning:

arch/riscv/kernel/vendor_extensions/sifive.c:11:33: sparse: sparse: symbol 'riscv_isa_vendor_ext_sifive' was not declared. Should it be static?

So as this struct is only used in this file, make it static.

Fixes: 2d147d77ae6e ("riscv: Add SiFive xsfvqmaccdod and xsfvqmaccqoq vendor extensions")
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202505072100.TZlEp8h1-lkp@intel.com/
Signed-off-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Link: https://lore.kernel.org/r/20250620-dev-alex-fix_sparse_sifive_v1-v1-1-efa3a6f93846@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@dabbelt.com>
---
 arch/riscv/kernel/vendor_extensions/sifive.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/riscv/kernel/vendor_extensions/sifive.c b/arch/riscv/kernel/vendor_extensions/sifive.c
index 1411337dc1e6..8fcf67e8c07f 100644
--- a/arch/riscv/kernel/vendor_extensions/sifive.c
+++ b/arch/riscv/kernel/vendor_extensions/sifive.c
@@ -8,7 +8,7 @@
 #include <linux/types.h>
 
 /* All SiFive vendor extensions supported in Linux */
-const struct riscv_isa_ext_data riscv_isa_vendor_ext_sifive[] = {
+static const struct riscv_isa_ext_data riscv_isa_vendor_ext_sifive[] = {
 	__RISCV_ISA_EXT_DATA(xsfvfnrclipxfqf, RISCV_ISA_VENDOR_EXT_XSFVFNRCLIPXFQF),
 	__RISCV_ISA_EXT_DATA(xsfvfwmaccqqq, RISCV_ISA_VENDOR_EXT_XSFVFWMACCQQQ),
 	__RISCV_ISA_EXT_DATA(xsfvqmaccdod, RISCV_ISA_VENDOR_EXT_XSFVQMACCDOD),

From 890ba5be6335dbbbc99af14ea007befb5f83f174 Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Thu, 19 Jun 2025 17:58:58 +0200
Subject: [PATCH 0756/1334] Revert "riscv: Define TASK_SIZE_MAX for
 __access_ok()"

This reverts commit ad5643cf2f69 ("riscv: Define TASK_SIZE_MAX for
__access_ok()").

This commit changes TASK_SIZE_MAX to be LONG_MAX to optimize access_ok(),
because the previous TASK_SIZE_MAX (default to TASK_SIZE) requires some
computation.

The reasoning was that all user addresses are less than LONG_MAX, and all
kernel addresses are greater than LONG_MAX. Therefore access_ok() can
filter kernel addresses.

Addresses between TASK_SIZE and LONG_MAX are not valid user addresses, but
access_ok() let them pass. That was thought to be okay, because they are
not valid addresses at hardware level.

Unfortunately, one case is missed: get_user_pages_fast() happily accepts
addresses between TASK_SIZE and LONG_MAX. futex(), for instance, uses
get_user_pages_fast(). This causes the problem reported by Robert [1].

Therefore, revert this commit. TASK_SIZE_MAX is changed to the default:
TASK_SIZE.

This unfortunately reduces performance, because TASK_SIZE is more expensive
to compute compared to LONG_MAX. But correctness first, we can think about
optimization later, if required.

Reported-by: <rtm@csail.mit.edu>
Closes: https://lore.kernel.org/linux-riscv/77605.1750245028@localhost/
Signed-off-by: Nam Cao <namcao@linutronix.de>
Cc: stable@vger.kernel.org
Reviewed-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Fixes: ad5643cf2f69 ("riscv: Define TASK_SIZE_MAX for __access_ok()")
Link: https://lore.kernel.org/r/20250619155858.1249789-1-namcao@linutronix.de
Signed-off-by: Palmer Dabbelt <palmer@dabbelt.com>
---
 arch/riscv/include/asm/pgtable.h | 1 -
 1 file changed, 1 deletion(-)

diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h
index a11816bbf9e7..521a995741cd 100644
--- a/arch/riscv/include/asm/pgtable.h
+++ b/arch/riscv/include/asm/pgtable.h
@@ -1075,7 +1075,6 @@ static inline pte_t pte_swp_clear_exclusive(pte_t pte)
  */
 #ifdef CONFIG_64BIT
 #define TASK_SIZE_64	(PGDIR_SIZE * PTRS_PER_PGD / 2)
-#define TASK_SIZE_MAX	LONG_MAX
 
 #ifdef CONFIG_COMPAT
 #define TASK_SIZE_32	(_AC(0x80000000, UL) - PAGE_SIZE)

From c5136add3f9b4c23b8bbe5f4d722c95d4cfb936e Mon Sep 17 00:00:00 2001
From: Klara Modin <klarasmodin@gmail.com>
Date: Tue, 17 Jun 2025 14:58:47 +0200
Subject: [PATCH 0757/1334] riscv: export boot_cpu_hartid

The mailbox controller driver for the Microchip Inter-processor
Communication can be built as a module. It uses cpuid_to_hartid_map and
commit 4783ce32b080 ("riscv: export __cpuid_to_hartid_map") enables that
to work for SMP. However, cpuid_to_hartid_map uses boot_cpu_hartid on
non-SMP kernels and this driver can be useful in such configurations[1].

Export boot_cpu_hartid so the driver can be built as a module on non-SMP
kernels as well.

Link: https://lore.kernel.org/lkml/20250617-confess-reimburse-876101e099cb@spud/ [1]
Cc: stable@vger.kernel.org
Fixes: e4b1d67e7141 ("mailbox: add Microchip IPC support")
Signed-off-by: Klara Modin <klarasmodin@gmail.com>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
Link: https://lore.kernel.org/r/20250617125847.23829-1-klarasmodin@gmail.com
Signed-off-by: Palmer Dabbelt <palmer@dabbelt.com>
---
 arch/riscv/kernel/setup.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c
index f7c9a1caa83e..14888e5ea19a 100644
--- a/arch/riscv/kernel/setup.c
+++ b/arch/riscv/kernel/setup.c
@@ -50,6 +50,7 @@ atomic_t hart_lottery __section(".sdata")
 #endif
 ;
 unsigned long boot_cpu_hartid;
+EXPORT_SYMBOL_GPL(boot_cpu_hartid);
 
 /*
  * Place kernel memory regions on the resource tree so that

From d5e3241c5a386a2425823c8c7afb77a465bd040f Mon Sep 17 00:00:00 2001
From: Thomas Fourier <fourier.thomas@gmail.com>
Date: Thu, 19 Jun 2025 11:45:30 +0200
Subject: [PATCH 0758/1334] ethernet: ionic: Fix DMA mapping tests

Change error values of `ionic_tx_map_single()` and `ionic_tx_map_frag()`
from 0 to `DMA_MAPPING_ERROR` to prevent collision with 0 as a valid
address.

This also fixes the use of `dma_mapping_error()` to test against 0 in
`ionic_xdp_post_frame()`

Fixes: 0f3154e6bcb3 ("ionic: Add Tx and Rx handling")
Fixes: 56e41ee12d2d ("ionic: better dma-map error handling")
Fixes: ac8813c0ab7d ("ionic: convert Rx queue buffers to use page_pool")
Signed-off-by: Thomas Fourier <fourier.thomas@gmail.com>
Reviewed-by: Brett Creeley <brett.creeley@amd.com>
Link: https://patch.msgid.link/20250619094538.283723-2-fourier.thomas@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/pensando/ionic/ionic_txrx.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c
index 2ac59564ded1..d10b58ebf603 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c
@@ -321,7 +321,7 @@ static int ionic_xdp_post_frame(struct ionic_queue *q, struct xdp_frame *frame,
 					   len, DMA_TO_DEVICE);
 	} else /* XDP_REDIRECT */ {
 		dma_addr = ionic_tx_map_single(q, frame->data, len);
-		if (!dma_addr)
+		if (dma_addr == DMA_MAPPING_ERROR)
 			return -EIO;
 	}
 
@@ -357,7 +357,7 @@ static int ionic_xdp_post_frame(struct ionic_queue *q, struct xdp_frame *frame,
 			} else {
 				dma_addr = ionic_tx_map_frag(q, frag, 0,
 							     skb_frag_size(frag));
-				if (dma_mapping_error(q->dev, dma_addr)) {
+				if (dma_addr == DMA_MAPPING_ERROR) {
 					ionic_tx_desc_unmap_bufs(q, desc_info);
 					return -EIO;
 				}
@@ -1083,7 +1083,7 @@ static dma_addr_t ionic_tx_map_single(struct ionic_queue *q,
 		net_warn_ratelimited("%s: DMA single map failed on %s!\n",
 				     dev_name(dev), q->name);
 		q_to_tx_stats(q)->dma_map_err++;
-		return 0;
+		return DMA_MAPPING_ERROR;
 	}
 	return dma_addr;
 }
@@ -1100,7 +1100,7 @@ static dma_addr_t ionic_tx_map_frag(struct ionic_queue *q,
 		net_warn_ratelimited("%s: DMA frag map failed on %s!\n",
 				     dev_name(dev), q->name);
 		q_to_tx_stats(q)->dma_map_err++;
-		return 0;
+		return DMA_MAPPING_ERROR;
 	}
 	return dma_addr;
 }
@@ -1116,7 +1116,7 @@ static int ionic_tx_map_skb(struct ionic_queue *q, struct sk_buff *skb,
 	int frag_idx;
 
 	dma_addr = ionic_tx_map_single(q, skb->data, skb_headlen(skb));
-	if (!dma_addr)
+	if (dma_addr == DMA_MAPPING_ERROR)
 		return -EIO;
 	buf_info->dma_addr = dma_addr;
 	buf_info->len = skb_headlen(skb);
@@ -1126,7 +1126,7 @@ static int ionic_tx_map_skb(struct ionic_queue *q, struct sk_buff *skb,
 	nfrags = skb_shinfo(skb)->nr_frags;
 	for (frag_idx = 0; frag_idx < nfrags; frag_idx++, frag++) {
 		dma_addr = ionic_tx_map_frag(q, frag, 0, skb_frag_size(frag));
-		if (!dma_addr)
+		if (dma_addr == DMA_MAPPING_ERROR)
 			goto dma_fail;
 		buf_info->dma_addr = dma_addr;
 		buf_info->len = skb_frag_size(frag);

From 7544f3f5b0b58c396f374d060898b5939da31709 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Thu, 19 Jun 2025 21:22:28 +0300
Subject: [PATCH 0759/1334] bridge: mcast: Fix use-after-free during router
 port configuration

The bridge maintains a global list of ports behind which a multicast
router resides. The list is consulted during forwarding to ensure
multicast packets are forwarded to these ports even if the ports are not
member in the matching MDB entry.

When per-VLAN multicast snooping is enabled, the per-port multicast
context is disabled on each port and the port is removed from the global
router port list:

 # ip link add name br1 up type bridge vlan_filtering 1 mcast_snooping 1
 # ip link add name dummy1 up master br1 type dummy
 # ip link set dev dummy1 type bridge_slave mcast_router 2
 $ bridge -d mdb show | grep router
 router ports on br1: dummy1
 # ip link set dev br1 type bridge mcast_vlan_snooping 1
 $ bridge -d mdb show | grep router

However, the port can be re-added to the global list even when per-VLAN
multicast snooping is enabled:

 # ip link set dev dummy1 type bridge_slave mcast_router 0
 # ip link set dev dummy1 type bridge_slave mcast_router 2
 $ bridge -d mdb show | grep router
 router ports on br1: dummy1

Since commit 4b30ae9adb04 ("net: bridge: mcast: re-implement
br_multicast_{enable, disable}_port functions"), when per-VLAN multicast
snooping is enabled, multicast disablement on a port will disable the
per-{port, VLAN} multicast contexts and not the per-port one. As a
result, a port will remain in the global router port list even after it
is deleted. This will lead to a use-after-free [1] when the list is
traversed (when adding a new port to the list, for example):

 # ip link del dev dummy1
 # ip link add name dummy2 up master br1 type dummy
 # ip link set dev dummy2 type bridge_slave mcast_router 2

Similarly, stale entries can also be found in the per-VLAN router port
list. When per-VLAN multicast snooping is disabled, the per-{port, VLAN}
contexts are disabled on each port and the port is removed from the
per-VLAN router port list:

 # ip link add name br1 up type bridge vlan_filtering 1 mcast_snooping 1 mcast_vlan_snooping 1
 # ip link add name dummy1 up master br1 type dummy
 # bridge vlan add vid 2 dev dummy1
 # bridge vlan global set vid 2 dev br1 mcast_snooping 1
 # bridge vlan set vid 2 dev dummy1 mcast_router 2
 $ bridge vlan global show dev br1 vid 2 | grep router
       router ports: dummy1
 # ip link set dev br1 type bridge mcast_vlan_snooping 0
 $ bridge vlan global show dev br1 vid 2 | grep router

However, the port can be re-added to the per-VLAN list even when
per-VLAN multicast snooping is disabled:

 # bridge vlan set vid 2 dev dummy1 mcast_router 0
 # bridge vlan set vid 2 dev dummy1 mcast_router 2
 $ bridge vlan global show dev br1 vid 2 | grep router
       router ports: dummy1

When the VLAN is deleted from the port, the per-{port, VLAN} multicast
context will not be disabled since multicast snooping is not enabled
on the VLAN. As a result, the port will remain in the per-VLAN router
port list even after it is no longer member in the VLAN. This will lead
to a use-after-free [2] when the list is traversed (when adding a new
port to the list, for example):

 # ip link add name dummy2 up master br1 type dummy
 # bridge vlan add vid 2 dev dummy2
 # bridge vlan del vid 2 dev dummy1
 # bridge vlan set vid 2 dev dummy2 mcast_router 2

Fix these issues by removing the port from the relevant (global or
per-VLAN) router port list in br_multicast_port_ctx_deinit(). The
function is invoked during port deletion with the per-port multicast
context and during VLAN deletion with the per-{port, VLAN} multicast
context.

Note that deleting the multicast router timer is not enough as it only
takes care of the temporary multicast router states (1 or 3) and not the
permanent one (2).

[1]
BUG: KASAN: slab-out-of-bounds in br_multicast_add_router.part.0+0x3f1/0x560
Write of size 8 at addr ffff888004a67328 by task ip/384
[...]
Call Trace:
 <TASK>
 dump_stack_lvl+0x6f/0xa0
 print_address_description.constprop.0+0x6f/0x350
 print_report+0x108/0x205
 kasan_report+0xdf/0x110
 br_multicast_add_router.part.0+0x3f1/0x560
 br_multicast_set_port_router+0x74e/0xac0
 br_setport+0xa55/0x1870
 br_port_slave_changelink+0x95/0x120
 __rtnl_newlink+0x5e8/0xa40
 rtnl_newlink+0x627/0xb00
 rtnetlink_rcv_msg+0x6fb/0xb70
 netlink_rcv_skb+0x11f/0x350
 netlink_unicast+0x426/0x710
 netlink_sendmsg+0x75a/0xc20
 __sock_sendmsg+0xc1/0x150
 ____sys_sendmsg+0x5aa/0x7b0
 ___sys_sendmsg+0xfc/0x180
 __sys_sendmsg+0x124/0x1c0
 do_syscall_64+0xbb/0x360
 entry_SYSCALL_64_after_hwframe+0x4b/0x53

[2]
BUG: KASAN: slab-use-after-free in br_multicast_add_router.part.0+0x378/0x560
Read of size 8 at addr ffff888009f00840 by task bridge/391
[...]
Call Trace:
 <TASK>
 dump_stack_lvl+0x6f/0xa0
 print_address_description.constprop.0+0x6f/0x350
 print_report+0x108/0x205
 kasan_report+0xdf/0x110
 br_multicast_add_router.part.0+0x378/0x560
 br_multicast_set_port_router+0x6f9/0xac0
 br_vlan_process_options+0x8b6/0x1430
 br_vlan_rtm_process_one+0x605/0xa30
 br_vlan_rtm_process+0x396/0x4c0
 rtnetlink_rcv_msg+0x2f7/0xb70
 netlink_rcv_skb+0x11f/0x350
 netlink_unicast+0x426/0x710
 netlink_sendmsg+0x75a/0xc20
 __sock_sendmsg+0xc1/0x150
 ____sys_sendmsg+0x5aa/0x7b0
 ___sys_sendmsg+0xfc/0x180
 __sys_sendmsg+0x124/0x1c0
 do_syscall_64+0xbb/0x360
 entry_SYSCALL_64_after_hwframe+0x4b/0x53

Fixes: 2796d846d74a ("net: bridge: vlan: convert mcast router global option to per-vlan entry")
Fixes: 4b30ae9adb04 ("net: bridge: mcast: re-implement br_multicast_{enable, disable}_port functions")
Reported-by: syzbot+7bfa4b72c6a5da128d32@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/all/684c18bd.a00a0220.279073.000b.GAE@google.com/T/
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Link: https://patch.msgid.link/20250619182228.1656906-1-idosch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/bridge/br_multicast.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index 0224ef3dfec0..1377f31b719c 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -2015,10 +2015,19 @@ void br_multicast_port_ctx_init(struct net_bridge_port *port,
 
 void br_multicast_port_ctx_deinit(struct net_bridge_mcast_port *pmctx)
 {
+	struct net_bridge *br = pmctx->port->br;
+	bool del = false;
+
 #if IS_ENABLED(CONFIG_IPV6)
 	timer_delete_sync(&pmctx->ip6_mc_router_timer);
 #endif
 	timer_delete_sync(&pmctx->ip4_mc_router_timer);
+
+	spin_lock_bh(&br->multicast_lock);
+	del |= br_ip6_multicast_rport_del(pmctx);
+	del |= br_ip4_multicast_rport_del(pmctx);
+	br_multicast_rport_del_notify(pmctx, del);
+	spin_unlock_bh(&br->multicast_lock);
 }
 
 int br_multicast_add_port(struct net_bridge_port *port)

From 2eb7648558a7911f2208e8940cd22ca40e93cc76 Mon Sep 17 00:00:00 2001
From: Jerome Marchand <jmarchan@redhat.com>
Date: Thu, 19 Jun 2025 16:06:02 +0200
Subject: [PATCH 0760/1334] bpf: Specify access type of bpf_sysctl_get_name
 args

The second argument of bpf_sysctl_get_name() helper is a pointer to a
buffer that is being written to. However that isn't specify in the
prototype.

Until commit 37cce22dbd51a ("bpf: verifier: Refactor helper access
type tracking"), all helper accesses were considered as a possible
write access by the verifier, so no big harm was done. However, since
then, the verifier might make wrong asssumption about the content of
that address which might lead it to make faulty optimizations (such as
removing code that was wrongly labeled dead). This is what happens in
test_sysctl selftest to the tests related to sysctl_get_name.

Add MEM_WRITE flag the second argument of bpf_sysctl_get_name().

Signed-off-by: Jerome Marchand <jmarchan@redhat.com>
Acked-by: Yonghong Song <yonghong.song@linux.dev>
Link: https://lore.kernel.org/r/20250619140603.148942-2-jmarchan@redhat.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/cgroup.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index 9122c39870bf..f4885514f007 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -2134,7 +2134,7 @@ static const struct bpf_func_proto bpf_sysctl_get_name_proto = {
 	.gpl_only	= false,
 	.ret_type	= RET_INTEGER,
 	.arg1_type	= ARG_PTR_TO_CTX,
-	.arg2_type	= ARG_PTR_TO_MEM,
+	.arg2_type	= ARG_PTR_TO_MEM | MEM_WRITE,
 	.arg3_type	= ARG_CONST_SIZE,
 	.arg4_type	= ARG_ANYTHING,
 };

From b8a205486ed5c0c5c0386e472157a81ce686af25 Mon Sep 17 00:00:00 2001
From: Jerome Marchand <jmarchan@redhat.com>
Date: Thu, 19 Jun 2025 16:06:03 +0200
Subject: [PATCH 0761/1334] selftests/bpf: Convert test_sysctl to prog_tests

Convert test_sysctl test to prog_tests with minimal change to the
tests themselves.

Signed-off-by: Jerome Marchand <jmarchan@redhat.com>
Acked-by: Yonghong Song <yonghong.song@linux.dev>
Link: https://lore.kernel.org/r/20250619140603.148942-3-jmarchan@redhat.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/.gitignore        |  1 -
 tools/testing/selftests/bpf/Makefile          |  5 +--
 .../bpf/{ => prog_tests}/test_sysctl.c        | 37 ++++---------------
 3 files changed, 10 insertions(+), 33 deletions(-)
 rename tools/testing/selftests/bpf/{ => prog_tests}/test_sysctl.c (98%)

diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore
index e2a2c46c008b..3d8378972d26 100644
--- a/tools/testing/selftests/bpf/.gitignore
+++ b/tools/testing/selftests/bpf/.gitignore
@@ -21,7 +21,6 @@ test_lirc_mode2_user
 flow_dissector_load
 test_tcpnotify_user
 test_libbpf
-test_sysctl
 xdping
 test_cpp
 *.d
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index cf5ed3bee573..910d8d6402ef 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -73,7 +73,7 @@ endif
 # Order correspond to 'make run_tests' order
 TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_progs \
 	test_sockmap \
-	test_tcpnotify_user test_sysctl \
+	test_tcpnotify_user \
 	test_progs-no_alu32
 TEST_INST_SUBDIRS := no_alu32
 
@@ -220,7 +220,7 @@ ifeq ($(VMLINUX_BTF),)
 $(error Cannot find a vmlinux for VMLINUX_BTF at any of "$(VMLINUX_BTF_PATHS)")
 endif
 
-# Define simple and short `make test_progs`, `make test_sysctl`, etc targets
+# Define simple and short `make test_progs`, `make test_maps`, etc targets
 # to build individual tests.
 # NOTE: Semicolon at the end is critical to override lib.mk's default static
 # rule for binaries.
@@ -329,7 +329,6 @@ NETWORK_HELPERS := $(OUTPUT)/network_helpers.o
 $(OUTPUT)/test_sockmap: $(CGROUP_HELPERS) $(TESTING_HELPERS)
 $(OUTPUT)/test_tcpnotify_user: $(CGROUP_HELPERS) $(TESTING_HELPERS) $(TRACE_HELPERS)
 $(OUTPUT)/test_sock_fields: $(CGROUP_HELPERS) $(TESTING_HELPERS)
-$(OUTPUT)/test_sysctl: $(CGROUP_HELPERS) $(TESTING_HELPERS)
 $(OUTPUT)/test_tag: $(TESTING_HELPERS)
 $(OUTPUT)/test_lirc_mode2_user: $(TESTING_HELPERS)
 $(OUTPUT)/xdping: $(TESTING_HELPERS)
diff --git a/tools/testing/selftests/bpf/test_sysctl.c b/tools/testing/selftests/bpf/prog_tests/test_sysctl.c
similarity index 98%
rename from tools/testing/selftests/bpf/test_sysctl.c
rename to tools/testing/selftests/bpf/prog_tests/test_sysctl.c
index bcdbd27f22f0..273dd41ca09e 100644
--- a/tools/testing/selftests/bpf/test_sysctl.c
+++ b/tools/testing/selftests/bpf/prog_tests/test_sysctl.c
@@ -1,22 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0
 // Copyright (c) 2019 Facebook
 
-#include <fcntl.h>
-#include <stdint.h>
-#include <stdio.h>
-#include <stdlib.h>
-#include <string.h>
-#include <unistd.h>
-
-#include <linux/filter.h>
-
-#include <bpf/bpf.h>
-#include <bpf/libbpf.h>
-
-#include <bpf/bpf_endian.h>
-#include "bpf_util.h"
+#include "test_progs.h"
 #include "cgroup_helpers.h"
-#include "testing_helpers.h"
 
 #define CG_PATH			"/foo"
 #define MAX_INSNS		512
@@ -1608,26 +1594,19 @@ static int run_tests(int cgfd)
 	return fails ? -1 : 0;
 }
 
-int main(int argc, char **argv)
+void test_sysctl(void)
 {
-	int cgfd = -1;
-	int err = 0;
+	int cgfd;
 
 	cgfd = cgroup_setup_and_join(CG_PATH);
-	if (cgfd < 0)
-		goto err;
+	if (!ASSERT_OK_FD(cgfd < 0, "create_cgroup"))
+		goto out;
 
-	/* Use libbpf 1.0 API mode */
-	libbpf_set_strict_mode(LIBBPF_STRICT_ALL);
+	if (!ASSERT_OK(run_tests(cgfd), "run_tests"))
+		goto out;
 
-	if (run_tests(cgfd))
-		goto err;
-
-	goto out;
-err:
-	err = -1;
 out:
 	close(cgfd);
 	cleanup_cgroup_environment();
-	return err;
+	return;
 }

From 0e7facea6da2bd360361440786785752aa5b0e30 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Fri, 20 Jun 2025 13:39:42 +0200
Subject: [PATCH 0762/1334] wifi: iwlegacy: work around excessive stack usage
 on clang/kasan

In some rare randconfig builds, I seem to trigger a bug in clang where
it unrolls a loop but then runs out of registers, which then get
spilled to the stack:

net/wireless/intel/iwlegacy/4965-rs.c:2262:1: error: stack frame size (1696) exceeds limit (1280) in 'il4965_rs_rate_init' [-Werror,-Wframe-larger-than]

This seems to be the same one I saw in the omapdrm driver, and there is
an easy workaround by not inlining the il4965_rs_rate_scale_clear_win
function.

Link: https://github.com/llvm/llvm-project/issues/143908
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Stanislaw Gruszka <stf_xl@wp.pl>
Link: https://patch.msgid.link/20250620113946.3987160-1-arnd@kernel.org
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlegacy/4965-rs.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/intel/iwlegacy/4965-rs.c b/drivers/net/wireless/intel/iwlegacy/4965-rs.c
index 0e5130d1fccd..031d88bf6393 100644
--- a/drivers/net/wireless/intel/iwlegacy/4965-rs.c
+++ b/drivers/net/wireless/intel/iwlegacy/4965-rs.c
@@ -203,7 +203,8 @@ il4965_rs_extract_rate(u32 rate_n_flags)
 	return (u8) (rate_n_flags & 0xFF);
 }
 
-static void
+/* noinline works around https://github.com/llvm/llvm-project/issues/143908 */
+static noinline_for_stack void
 il4965_rs_rate_scale_clear_win(struct il_rate_scale_data *win)
 {
 	win->data = 0;

From 7a3750ff0f2e8fee338a9c168f429f6c37f0e820 Mon Sep 17 00:00:00 2001
From: Lachlan Hodges <lachlan.hodges@morsemicro.com>
Date: Sat, 21 Jun 2025 22:32:09 +1000
Subject: [PATCH 0763/1334] wifi: mac80211: fix beacon interval calculation
 overflow

As we are converting from TU to usecs, a beacon interval of
100*1024 usecs will lead to integer wrapping. To fix change
to use a u32.

Fixes: 057d5f4ba1e4 ("mac80211: sync dtim_count to TSF")
Signed-off-by: Lachlan Hodges <lachlan.hodges@morsemicro.com>
Link: https://patch.msgid.link/20250621123209.511796-1-lachlan.hodges@morsemicro.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/util.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index 27d414efa3fd..a125995ed252 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -3884,7 +3884,7 @@ void ieee80211_recalc_dtim(struct ieee80211_local *local,
 {
 	u64 tsf = drv_get_tsf(local, sdata);
 	u64 dtim_count = 0;
-	u16 beacon_int = sdata->vif.bss_conf.beacon_int * 1024;
+	u32 beacon_int = sdata->vif.bss_conf.beacon_int * 1024;
 	u8 dtim_period = sdata->vif.bss_conf.dtim_period;
 	struct ps_data *ps;
 	u8 bcns_from_dtim;

From 32ca245464e1479bfea8592b9db227fdc1641705 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@google.com>
Date: Wed, 18 Jun 2025 21:13:55 -0700
Subject: [PATCH 0764/1334] af_unix: Don't leave consecutive consumed OOB skbs.

Jann Horn reported a use-after-free in unix_stream_read_generic().

The following sequences reproduce the issue:

  $ python3
  from socket import *
  s1, s2 = socketpair(AF_UNIX, SOCK_STREAM)
  s1.send(b'x', MSG_OOB)
  s2.recv(1, MSG_OOB)     # leave a consumed OOB skb
  s1.send(b'y', MSG_OOB)
  s2.recv(1, MSG_OOB)     # leave a consumed OOB skb
  s1.send(b'z', MSG_OOB)
  s2.recv(1)              # recv 'z' illegally
  s2.recv(1, MSG_OOB)     # access 'z' skb (use-after-free)

Even though a user reads OOB data, the skb holding the data stays on
the recv queue to mark the OOB boundary and break the next recv().

After the last send() in the scenario above, the sk2's recv queue has
2 leading consumed OOB skbs and 1 real OOB skb.

Then, the following happens during the next recv() without MSG_OOB

  1. unix_stream_read_generic() peeks the first consumed OOB skb
  2. manage_oob() returns the next consumed OOB skb
  3. unix_stream_read_generic() fetches the next not-yet-consumed OOB skb
  4. unix_stream_read_generic() reads and frees the OOB skb

, and the last recv(MSG_OOB) triggers KASAN splat.

The 3. above occurs because of the SO_PEEK_OFF code, which does not
expect unix_skb_len(skb) to be 0, but this is true for such consumed
OOB skbs.

  while (skip >= unix_skb_len(skb)) {
    skip -= unix_skb_len(skb);
    skb = skb_peek_next(skb, &sk->sk_receive_queue);
    ...
  }

In addition to this use-after-free, there is another issue that
ioctl(SIOCATMARK) does not function properly with consecutive consumed
OOB skbs.

So, nothing good comes out of such a situation.

Instead of complicating manage_oob(), ioctl() handling, and the next
ECONNRESET fix by introducing a loop for consecutive consumed OOB skbs,
let's not leave such consecutive OOB unnecessarily.

Now, while receiving an OOB skb in unix_stream_recv_urg(), if its
previous skb is a consumed OOB skb, it is freed.

[0]:
BUG: KASAN: slab-use-after-free in unix_stream_read_actor (net/unix/af_unix.c:3027)
Read of size 4 at addr ffff888106ef2904 by task python3/315

CPU: 2 UID: 0 PID: 315 Comm: python3 Not tainted 6.16.0-rc1-00407-gec315832f6f9 #8 PREEMPT(voluntary)
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.16.3-4.fc42 04/01/2014
Call Trace:
 <TASK>
 dump_stack_lvl (lib/dump_stack.c:122)
 print_report (mm/kasan/report.c:409 mm/kasan/report.c:521)
 kasan_report (mm/kasan/report.c:636)
 unix_stream_read_actor (net/unix/af_unix.c:3027)
 unix_stream_read_generic (net/unix/af_unix.c:2708 net/unix/af_unix.c:2847)
 unix_stream_recvmsg (net/unix/af_unix.c:3048)
 sock_recvmsg (net/socket.c:1063 (discriminator 20) net/socket.c:1085 (discriminator 20))
 __sys_recvfrom (net/socket.c:2278)
 __x64_sys_recvfrom (net/socket.c:2291 (discriminator 1) net/socket.c:2287 (discriminator 1) net/socket.c:2287 (discriminator 1))
 do_syscall_64 (arch/x86/entry/syscall_64.c:63 (discriminator 1) arch/x86/entry/syscall_64.c:94 (discriminator 1))
 entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:130)
RIP: 0033:0x7f8911fcea06
Code: 5d e8 41 8b 93 08 03 00 00 59 5e 48 83 f8 fc 75 19 83 e2 39 83 fa 08 75 11 e8 26 ff ff ff 66 0f 1f 44 00 00 48 8b 45 10 0f 05 <48> 8b 5d f8 c9 c3 0f 1f 40 00 f3 0f 1e fa 55 48 89 e5 48 83 ec 08
RSP: 002b:00007fffdb0dccb0 EFLAGS: 00000202 ORIG_RAX: 000000000000002d
RAX: ffffffffffffffda RBX: 00007fffdb0dcdc8 RCX: 00007f8911fcea06
RDX: 0000000000000001 RSI: 00007f8911a5e060 RDI: 0000000000000006
RBP: 00007fffdb0dccd0 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000001 R11: 0000000000000202 R12: 00007f89119a7d20
R13: ffffffffc4653600 R14: 0000000000000000 R15: 0000000000000000
 </TASK>

Allocated by task 315:
 kasan_save_stack (mm/kasan/common.c:48)
 kasan_save_track (mm/kasan/common.c:60 (discriminator 1) mm/kasan/common.c:69 (discriminator 1))
 __kasan_slab_alloc (mm/kasan/common.c:348)
 kmem_cache_alloc_node_noprof (./include/linux/kasan.h:250 mm/slub.c:4148 mm/slub.c:4197 mm/slub.c:4249)
 __alloc_skb (net/core/skbuff.c:660 (discriminator 4))
 alloc_skb_with_frags (./include/linux/skbuff.h:1336 net/core/skbuff.c:6668)
 sock_alloc_send_pskb (net/core/sock.c:2993)
 unix_stream_sendmsg (./include/net/sock.h:1847 net/unix/af_unix.c:2256 net/unix/af_unix.c:2418)
 __sys_sendto (net/socket.c:712 (discriminator 20) net/socket.c:727 (discriminator 20) net/socket.c:2226 (discriminator 20))
 __x64_sys_sendto (net/socket.c:2233 (discriminator 1) net/socket.c:2229 (discriminator 1) net/socket.c:2229 (discriminator 1))
 do_syscall_64 (arch/x86/entry/syscall_64.c:63 (discriminator 1) arch/x86/entry/syscall_64.c:94 (discriminator 1))
 entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:130)

Freed by task 315:
 kasan_save_stack (mm/kasan/common.c:48)
 kasan_save_track (mm/kasan/common.c:60 (discriminator 1) mm/kasan/common.c:69 (discriminator 1))
 kasan_save_free_info (mm/kasan/generic.c:579 (discriminator 1))
 __kasan_slab_free (mm/kasan/common.c:271)
 kmem_cache_free (mm/slub.c:4643 (discriminator 3) mm/slub.c:4745 (discriminator 3))
 unix_stream_read_generic (net/unix/af_unix.c:3010)
 unix_stream_recvmsg (net/unix/af_unix.c:3048)
 sock_recvmsg (net/socket.c:1063 (discriminator 20) net/socket.c:1085 (discriminator 20))
 __sys_recvfrom (net/socket.c:2278)
 __x64_sys_recvfrom (net/socket.c:2291 (discriminator 1) net/socket.c:2287 (discriminator 1) net/socket.c:2287 (discriminator 1))
 do_syscall_64 (arch/x86/entry/syscall_64.c:63 (discriminator 1) arch/x86/entry/syscall_64.c:94 (discriminator 1))
 entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:130)

The buggy address belongs to the object at ffff888106ef28c0
 which belongs to the cache skbuff_head_cache of size 224
The buggy address is located 68 bytes inside of
 freed 224-byte region [ffff888106ef28c0, ffff888106ef29a0)

The buggy address belongs to the physical page:
page: refcount:0 mapcount:0 mapping:0000000000000000 index:0xffff888106ef3cc0 pfn:0x106ef2
head: order:1 mapcount:0 entire_mapcount:0 nr_pages_mapped:0 pincount:0
flags: 0x200000000000040(head|node=0|zone=2)
page_type: f5(slab)
raw: 0200000000000040 ffff8881001d28c0 ffffea000422fe00 0000000000000004
raw: ffff888106ef3cc0 0000000080190010 00000000f5000000 0000000000000000
head: 0200000000000040 ffff8881001d28c0 ffffea000422fe00 0000000000000004
head: ffff888106ef3cc0 0000000080190010 00000000f5000000 0000000000000000
head: 0200000000000001 ffffea00041bbc81 00000000ffffffff 00000000ffffffff
head: 0000000000000000 0000000000000000 00000000ffffffff 0000000000000000
page dumped because: kasan: bad access detected

Memory state around the buggy address:
 ffff888106ef2800: 00 00 00 00 00 00 00 00 00 00 00 00 fc fc fc fc
 ffff888106ef2880: fc fc fc fc fc fc fc fc fa fb fb fb fb fb fb fb
>ffff888106ef2900: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
                   ^
 ffff888106ef2980: fb fb fb fb fc fc fc fc fc fc fc fc fc fc fc fc
 ffff888106ef2a00: fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb

Fixes: 314001f0bf92 ("af_unix: Add OOB support")
Reported-by: Jann Horn <jannh@google.com>
Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Reviewed-by: Jann Horn <jannh@google.com>
Link: https://patch.msgid.link/20250619041457.1132791-2-kuni1840@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/unix/af_unix.c | 13 +++++++++++--
 1 file changed, 11 insertions(+), 2 deletions(-)

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 22e170fb5dda..5392aa53cbc8 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -2680,11 +2680,11 @@ struct unix_stream_read_state {
 #if IS_ENABLED(CONFIG_AF_UNIX_OOB)
 static int unix_stream_recv_urg(struct unix_stream_read_state *state)
 {
+	struct sk_buff *oob_skb, *read_skb = NULL;
 	struct socket *sock = state->socket;
 	struct sock *sk = sock->sk;
 	struct unix_sock *u = unix_sk(sk);
 	int chunk = 1;
-	struct sk_buff *oob_skb;
 
 	mutex_lock(&u->iolock);
 	unix_state_lock(sk);
@@ -2699,9 +2699,16 @@ static int unix_stream_recv_urg(struct unix_stream_read_state *state)
 
 	oob_skb = u->oob_skb;
 
-	if (!(state->flags & MSG_PEEK))
+	if (!(state->flags & MSG_PEEK)) {
 		WRITE_ONCE(u->oob_skb, NULL);
 
+		if (oob_skb->prev != (struct sk_buff *)&sk->sk_receive_queue &&
+		    !unix_skb_len(oob_skb->prev)) {
+			read_skb = oob_skb->prev;
+			__skb_unlink(read_skb, &sk->sk_receive_queue);
+		}
+	}
+
 	spin_unlock(&sk->sk_receive_queue.lock);
 	unix_state_unlock(sk);
 
@@ -2712,6 +2719,8 @@ static int unix_stream_recv_urg(struct unix_stream_read_state *state)
 
 	mutex_unlock(&u->iolock);
 
+	consume_skb(read_skb);
+
 	if (chunk < 0)
 		return -EFAULT;
 

From e1ca44e85f652a6ebd657c67c394894c1fdfb403 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@google.com>
Date: Wed, 18 Jun 2025 21:13:56 -0700
Subject: [PATCH 0765/1334] af_unix: Add test for consecutive consumed OOB.

Let's add a test case where consecutive concumed OOB skbs stay
at the head of the queue.

Without the previous patch, ioctl(SIOCATMARK) assertion fails.

Before:

  #  RUN           msg_oob.no_peek.ex_oob_ex_oob_oob ...
  # msg_oob.c:305:ex_oob_ex_oob_oob:Expected answ[0] (0) == oob_head (1)
  # ex_oob_ex_oob_oob: Test terminated by assertion
  #          FAIL  msg_oob.no_peek.ex_oob_ex_oob_oob
  not ok 12 msg_oob.no_peek.ex_oob_ex_oob_oob

After:

  #  RUN           msg_oob.no_peek.ex_oob_ex_oob_oob ...
  #            OK  msg_oob.no_peek.ex_oob_ex_oob_oob
  ok 12 msg_oob.no_peek.ex_oob_ex_oob_oob

Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Link: https://patch.msgid.link/20250619041457.1132791-3-kuni1840@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 tools/testing/selftests/net/af_unix/msg_oob.c | 23 +++++++++++++++++++
 1 file changed, 23 insertions(+)

diff --git a/tools/testing/selftests/net/af_unix/msg_oob.c b/tools/testing/selftests/net/af_unix/msg_oob.c
index 3ed3882a93b8..918509a3f040 100644
--- a/tools/testing/selftests/net/af_unix/msg_oob.c
+++ b/tools/testing/selftests/net/af_unix/msg_oob.c
@@ -548,6 +548,29 @@ TEST_F(msg_oob, ex_oob_oob)
 	siocatmarkpair(false);
 }
 
+TEST_F(msg_oob, ex_oob_ex_oob_oob)
+{
+	sendpair("x", 1, MSG_OOB);
+	epollpair(true);
+	siocatmarkpair(true);
+
+	recvpair("x", 1, 1, MSG_OOB);
+	epollpair(false);
+	siocatmarkpair(true);
+
+	sendpair("y", 1, MSG_OOB);
+	epollpair(true);
+	siocatmarkpair(true);
+
+	recvpair("y", 1, 1, MSG_OOB);
+	epollpair(false);
+	siocatmarkpair(true);
+
+	sendpair("z", 1, MSG_OOB);
+	epollpair(true);
+	siocatmarkpair(true);
+}
+
 TEST_F(msg_oob, ex_oob_ahead_break)
 {
 	sendpair("hello", 5, MSG_OOB);

From 2a5a4841846b079b5fca5752fe94e59346fbda40 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@google.com>
Date: Wed, 18 Jun 2025 21:13:57 -0700
Subject: [PATCH 0766/1334] af_unix: Don't set -ECONNRESET for consumed OOB
 skb.

Christian Brauner reported that even after MSG_OOB data is consumed,
calling close() on the receiver socket causes the peer's recv() to
return -ECONNRESET:

  1. send() and recv() an OOB data.

    >>> from socket import *
    >>> s1, s2 = socketpair(AF_UNIX, SOCK_STREAM)
    >>> s1.send(b'x', MSG_OOB)
    1
    >>> s2.recv(1, MSG_OOB)
    b'x'

  2. close() for s2 sets ECONNRESET to s1->sk_err even though
     s2 consumed the OOB data

    >>> s2.close()
    >>> s1.recv(10, MSG_DONTWAIT)
    ...
    ConnectionResetError: [Errno 104] Connection reset by peer

Even after being consumed, the skb holding the OOB 1-byte data stays in
the recv queue to mark the OOB boundary and break recv() at that point.

This must be considered while close()ing a socket.

Let's skip the leading consumed OOB skb while checking the -ECONNRESET
condition in unix_release_sock().

Fixes: 314001f0bf92 ("af_unix: Add OOB support")
Reported-by: Christian Brauner <brauner@kernel.org>
Closes: https://lore.kernel.org/netdev/20250529-sinkt-abfeuern-e7b08200c6b0@brauner/
Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Acked-by: Christian Brauner <brauner@kernel.org>
Link: https://patch.msgid.link/20250619041457.1132791-4-kuni1840@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/unix/af_unix.c | 18 ++++++++++++------
 1 file changed, 12 insertions(+), 6 deletions(-)

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 5392aa53cbc8..52b155123985 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -660,6 +660,11 @@ static void unix_sock_destructor(struct sock *sk)
 #endif
 }
 
+static unsigned int unix_skb_len(const struct sk_buff *skb)
+{
+	return skb->len - UNIXCB(skb).consumed;
+}
+
 static void unix_release_sock(struct sock *sk, int embrion)
 {
 	struct unix_sock *u = unix_sk(sk);
@@ -694,10 +699,16 @@ static void unix_release_sock(struct sock *sk, int embrion)
 
 	if (skpair != NULL) {
 		if (sk->sk_type == SOCK_STREAM || sk->sk_type == SOCK_SEQPACKET) {
+			struct sk_buff *skb = skb_peek(&sk->sk_receive_queue);
+
+#if IS_ENABLED(CONFIG_AF_UNIX_OOB)
+			if (skb && !unix_skb_len(skb))
+				skb = skb_peek_next(skb, &sk->sk_receive_queue);
+#endif
 			unix_state_lock(skpair);
 			/* No more writes */
 			WRITE_ONCE(skpair->sk_shutdown, SHUTDOWN_MASK);
-			if (!skb_queue_empty_lockless(&sk->sk_receive_queue) || embrion)
+			if (skb || embrion)
 				WRITE_ONCE(skpair->sk_err, ECONNRESET);
 			unix_state_unlock(skpair);
 			skpair->sk_state_change(skpair);
@@ -2661,11 +2672,6 @@ static long unix_stream_data_wait(struct sock *sk, long timeo,
 	return timeo;
 }
 
-static unsigned int unix_skb_len(const struct sk_buff *skb)
-{
-	return skb->len - UNIXCB(skb).consumed;
-}
-
 struct unix_stream_read_state {
 	int (*recv_actor)(struct sk_buff *, int, int,
 			  struct unix_stream_read_state *);

From 632f55fa60c481035297739ecd374d945c9b32c7 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@google.com>
Date: Wed, 18 Jun 2025 21:13:58 -0700
Subject: [PATCH 0767/1334] selftest: af_unix: Add tests for -ECONNRESET.

A new function resetpair() calls close() for the receiver and checks
the return value from recv() on the initial sender side.

Now resetpair() is added to each test case and some additional test
cases.

Note that TCP sets -ECONNRESET to the consumed OOB, but we have decided
not to touch TCP MSG_OOB code in the past.

Before:

  #  RUN           msg_oob.no_peek.ex_oob_ex_oob ...
  # msg_oob.c:236:ex_oob_ex_oob:AF_UNIX :Connection reset by peer
  # msg_oob.c:237:ex_oob_ex_oob:Expected:
  # msg_oob.c:239:ex_oob_ex_oob:Expected ret[0] (-1) == expected_len (0)
  # ex_oob_ex_oob: Test terminated by assertion
  #          FAIL  msg_oob.no_peek.ex_oob_ex_oob
  not ok 14 msg_oob.no_peek.ex_oob_ex_oob
  ...
  # FAILED: 36 / 48 tests passed.
  # Totals: pass:36 fail:12 xfail:0 xpass:0 skip:0 error:0

After:

  #  RUN           msg_oob.no_peek.ex_oob_ex_oob ...
  # msg_oob.c:244:ex_oob_ex_oob:AF_UNIX :
  # msg_oob.c:245:ex_oob_ex_oob:TCP     :Connection reset by peer
  #            OK  msg_oob.no_peek.ex_oob_ex_oob
  ok 14 msg_oob.no_peek.ex_oob_ex_oob
  ...
  # PASSED: 48 / 48 tests passed.
  # Totals: pass:48 fail:0 xfail:0 xpass:0 skip:0 error:0

Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Link: https://patch.msgid.link/20250619041457.1132791-5-kuni1840@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 tools/testing/selftests/net/af_unix/msg_oob.c | 119 +++++++++++++++++-
 1 file changed, 115 insertions(+), 4 deletions(-)

diff --git a/tools/testing/selftests/net/af_unix/msg_oob.c b/tools/testing/selftests/net/af_unix/msg_oob.c
index 918509a3f040..b5f474969917 100644
--- a/tools/testing/selftests/net/af_unix/msg_oob.c
+++ b/tools/testing/selftests/net/af_unix/msg_oob.c
@@ -210,7 +210,7 @@ static void __sendpair(struct __test_metadata *_metadata,
 static void __recvpair(struct __test_metadata *_metadata,
 		       FIXTURE_DATA(msg_oob) *self,
 		       const char *expected_buf, int expected_len,
-		       int buf_len, int flags)
+		       int buf_len, int flags, bool is_sender)
 {
 	int i, ret[2], recv_errno[2], expected_errno = 0;
 	char recv_buf[2][BUF_SZ] = {};
@@ -221,7 +221,9 @@ static void __recvpair(struct __test_metadata *_metadata,
 	errno = 0;
 
 	for (i = 0; i < 2; i++) {
-		ret[i] = recv(self->fd[i * 2 + 1], recv_buf[i], buf_len, flags);
+		int index = is_sender ? i * 2 : i * 2 + 1;
+
+		ret[i] = recv(self->fd[index], recv_buf[i], buf_len, flags);
 		recv_errno[i] = errno;
 	}
 
@@ -308,6 +310,20 @@ static void __siocatmarkpair(struct __test_metadata *_metadata,
 		ASSERT_EQ(answ[0], answ[1]);
 }
 
+static void __resetpair(struct __test_metadata *_metadata,
+			FIXTURE_DATA(msg_oob) *self,
+			const FIXTURE_VARIANT(msg_oob) *variant,
+			bool reset)
+{
+	int i;
+
+	for (i = 0; i < 2; i++)
+		close(self->fd[i * 2 + 1]);
+
+	__recvpair(_metadata, self, "", reset ? -ECONNRESET : 0, 1,
+		   variant->peek ? MSG_PEEK : 0, true);
+}
+
 #define sendpair(buf, len, flags)					\
 	__sendpair(_metadata, self, buf, len, flags)
 
@@ -316,9 +332,10 @@ static void __siocatmarkpair(struct __test_metadata *_metadata,
 		if (variant->peek)					\
 			__recvpair(_metadata, self,			\
 				   expected_buf, expected_len,		\
-				   buf_len, (flags) | MSG_PEEK);	\
+				   buf_len, (flags) | MSG_PEEK, false);	\
 		__recvpair(_metadata, self,				\
-			   expected_buf, expected_len, buf_len, flags);	\
+			   expected_buf, expected_len,			\
+			   buf_len, flags, false);			\
 	} while (0)
 
 #define epollpair(oob_remaining)					\
@@ -330,6 +347,9 @@ static void __siocatmarkpair(struct __test_metadata *_metadata,
 #define setinlinepair()							\
 	__setinlinepair(_metadata, self)
 
+#define resetpair(reset)						\
+	__resetpair(_metadata, self, variant, reset)
+
 #define tcp_incompliant							\
 	for (self->tcp_compliant = false;				\
 	     self->tcp_compliant == false;				\
@@ -344,6 +364,21 @@ TEST_F(msg_oob, non_oob)
 	recvpair("", -EINVAL, 1, MSG_OOB);
 	epollpair(false);
 	siocatmarkpair(false);
+
+	resetpair(true);
+}
+
+TEST_F(msg_oob, non_oob_no_reset)
+{
+	sendpair("x", 1, 0);
+	epollpair(false);
+	siocatmarkpair(false);
+
+	recvpair("x", 1, 1, 0);
+	epollpair(false);
+	siocatmarkpair(false);
+
+	resetpair(false);
 }
 
 TEST_F(msg_oob, oob)
@@ -355,6 +390,19 @@ TEST_F(msg_oob, oob)
 	recvpair("x", 1, 1, MSG_OOB);
 	epollpair(false);
 	siocatmarkpair(true);
+
+	tcp_incompliant {
+		resetpair(false);		/* TCP sets -ECONNRESET for ex-OOB. */
+	}
+}
+
+TEST_F(msg_oob, oob_reset)
+{
+	sendpair("x", 1, MSG_OOB);
+	epollpair(true);
+	siocatmarkpair(true);
+
+	resetpair(true);
 }
 
 TEST_F(msg_oob, oob_drop)
@@ -370,6 +418,8 @@ TEST_F(msg_oob, oob_drop)
 	recvpair("", -EINVAL, 1, MSG_OOB);
 	epollpair(false);
 	siocatmarkpair(false);
+
+	resetpair(false);
 }
 
 TEST_F(msg_oob, oob_ahead)
@@ -385,6 +435,10 @@ TEST_F(msg_oob, oob_ahead)
 	recvpair("hell", 4, 4, 0);
 	epollpair(false);
 	siocatmarkpair(true);
+
+	tcp_incompliant {
+		resetpair(false);		/* TCP sets -ECONNRESET for ex-OOB. */
+	}
 }
 
 TEST_F(msg_oob, oob_break)
@@ -403,6 +457,8 @@ TEST_F(msg_oob, oob_break)
 
 	recvpair("", -EAGAIN, 1, 0);
 	siocatmarkpair(false);
+
+	resetpair(false);
 }
 
 TEST_F(msg_oob, oob_ahead_break)
@@ -426,6 +482,8 @@ TEST_F(msg_oob, oob_ahead_break)
 	recvpair("world", 5, 5, 0);
 	epollpair(false);
 	siocatmarkpair(false);
+
+	resetpair(false);
 }
 
 TEST_F(msg_oob, oob_break_drop)
@@ -449,6 +507,8 @@ TEST_F(msg_oob, oob_break_drop)
 	recvpair("", -EINVAL, 1, MSG_OOB);
 	epollpair(false);
 	siocatmarkpair(false);
+
+	resetpair(false);
 }
 
 TEST_F(msg_oob, ex_oob_break)
@@ -476,6 +536,8 @@ TEST_F(msg_oob, ex_oob_break)
 	recvpair("ld", 2, 2, 0);
 	epollpair(false);
 	siocatmarkpair(false);
+
+	resetpair(false);
 }
 
 TEST_F(msg_oob, ex_oob_drop)
@@ -498,6 +560,8 @@ TEST_F(msg_oob, ex_oob_drop)
 		epollpair(false);
 		siocatmarkpair(true);
 	}
+
+	resetpair(false);
 }
 
 TEST_F(msg_oob, ex_oob_drop_2)
@@ -523,6 +587,8 @@ TEST_F(msg_oob, ex_oob_drop_2)
 		epollpair(false);
 		siocatmarkpair(true);
 	}
+
+	resetpair(false);
 }
 
 TEST_F(msg_oob, ex_oob_oob)
@@ -546,6 +612,31 @@ TEST_F(msg_oob, ex_oob_oob)
 	recvpair("", -EINVAL, 1, MSG_OOB);
 	epollpair(false);
 	siocatmarkpair(false);
+
+	resetpair(false);
+}
+
+TEST_F(msg_oob, ex_oob_ex_oob)
+{
+	sendpair("x", 1, MSG_OOB);
+	epollpair(true);
+	siocatmarkpair(true);
+
+	recvpair("x", 1, 1, MSG_OOB);
+	epollpair(false);
+	siocatmarkpair(true);
+
+	sendpair("y", 1, MSG_OOB);
+	epollpair(true);
+	siocatmarkpair(true);
+
+	recvpair("y", 1, 1, MSG_OOB);
+	epollpair(false);
+	siocatmarkpair(true);
+
+	tcp_incompliant {
+		resetpair(false);		/* TCP sets -ECONNRESET for ex-OOB. */
+	}
 }
 
 TEST_F(msg_oob, ex_oob_ex_oob_oob)
@@ -599,6 +690,10 @@ TEST_F(msg_oob, ex_oob_ahead_break)
 	recvpair("d", 1, 1, MSG_OOB);
 	epollpair(false);
 	siocatmarkpair(true);
+
+	tcp_incompliant {
+		resetpair(false);		/* TCP sets -ECONNRESET for ex-OOB. */
+	}
 }
 
 TEST_F(msg_oob, ex_oob_siocatmark)
@@ -618,6 +713,8 @@ TEST_F(msg_oob, ex_oob_siocatmark)
 	recvpair("hell", 4, 4, 0);		/* Intentionally stop at ex-OOB. */
 	epollpair(true);
 	siocatmarkpair(false);
+
+	resetpair(true);
 }
 
 TEST_F(msg_oob, inline_oob)
@@ -635,6 +732,8 @@ TEST_F(msg_oob, inline_oob)
 	recvpair("x", 1, 1, 0);
 	epollpair(false);
 	siocatmarkpair(false);
+
+	resetpair(false);
 }
 
 TEST_F(msg_oob, inline_oob_break)
@@ -656,6 +755,8 @@ TEST_F(msg_oob, inline_oob_break)
 	recvpair("o", 1, 1, 0);
 	epollpair(false);
 	siocatmarkpair(false);
+
+	resetpair(false);
 }
 
 TEST_F(msg_oob, inline_oob_ahead_break)
@@ -684,6 +785,8 @@ TEST_F(msg_oob, inline_oob_ahead_break)
 
 	epollpair(false);
 	siocatmarkpair(false);
+
+	resetpair(false);
 }
 
 TEST_F(msg_oob, inline_ex_oob_break)
@@ -709,6 +812,8 @@ TEST_F(msg_oob, inline_ex_oob_break)
 	recvpair("rld", 3, 3, 0);
 	epollpair(false);
 	siocatmarkpair(false);
+
+	resetpair(false);
 }
 
 TEST_F(msg_oob, inline_ex_oob_no_drop)
@@ -730,6 +835,8 @@ TEST_F(msg_oob, inline_ex_oob_no_drop)
 	recvpair("y", 1, 1, 0);
 	epollpair(false);
 	siocatmarkpair(false);
+
+	resetpair(false);
 }
 
 TEST_F(msg_oob, inline_ex_oob_drop)
@@ -754,6 +861,8 @@ TEST_F(msg_oob, inline_ex_oob_drop)
 		epollpair(false);
 		siocatmarkpair(false);
 	}
+
+	resetpair(false);
 }
 
 TEST_F(msg_oob, inline_ex_oob_siocatmark)
@@ -775,6 +884,8 @@ TEST_F(msg_oob, inline_ex_oob_siocatmark)
 	recvpair("hell", 4, 4, 0);		/* Intentionally stop at ex-OOB. */
 	epollpair(true);
 	siocatmarkpair(false);
+
+	resetpair(true);
 }
 
 TEST_HARNESS_MAIN

From b272f42547d85356b035e46273ddaf2aa4e161b8 Mon Sep 17 00:00:00 2001
From: Harshit Mogalapalli <harshit.m.mogalapalli@oracle.com>
Date: Mon, 23 Jun 2025 07:26:27 -0700
Subject: [PATCH 0768/1334] ALSA: qc_audio_offload: Fix missing error code in
 prepare_qmi_response()

When snd_soc_usb_find_priv_data() fails, return failure instead of
success. While we are at it also use direct returns at first few error
paths where there is no additional cleanup needed.

Reported-by: Dan Carpenter <dan.carpenter@linaro.org>
Closes: https://lore.kernel.org/all/Z_40qL4JnyjR4j0O@stanley.mountain/
Fixes: 326bbc348298 ("ALSA: usb-audio: qcom: Introduce QC USB SND offloading support")
Signed-off-by: Harshit Mogalapalli <harshit.m.mogalapalli@oracle.com>
Link: https://patch.msgid.link/20250623142639.2938056-1-harshit.m.mogalapalli@oracle.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/usb/qcom/qc_audio_offload.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/sound/usb/qcom/qc_audio_offload.c b/sound/usb/qcom/qc_audio_offload.c
index 5bc27c82e0af..797afd4561bd 100644
--- a/sound/usb/qcom/qc_audio_offload.c
+++ b/sound/usb/qcom/qc_audio_offload.c
@@ -1360,20 +1360,21 @@ static int prepare_qmi_response(struct snd_usb_substream *subs,
 
 	if (!uadev[card_num].ctrl_intf) {
 		dev_err(&subs->dev->dev, "audio ctrl intf info not cached\n");
-		ret = -ENODEV;
-		goto err;
+		return -ENODEV;
 	}
 
 	ret = uaudio_populate_uac_desc(subs, resp);
 	if (ret < 0)
-		goto err;
+		return ret;
 
 	resp->slot_id = subs->dev->slot_id;
 	resp->slot_id_valid = 1;
 
 	data = snd_soc_usb_find_priv_data(uaudio_qdev->auxdev->dev.parent);
-	if (!data)
-		goto err;
+	if (!data) {
+		dev_err(&subs->dev->dev, "No private data found\n");
+		return -ENODEV;
+	}
 
 	uaudio_qdev->data = data;
 
@@ -1382,7 +1383,7 @@ static int prepare_qmi_response(struct snd_usb_substream *subs,
 				    &resp->xhci_mem_info.tr_data,
 				    &resp->std_as_data_ep_desc);
 	if (ret < 0)
-		goto err;
+		return ret;
 
 	resp->std_as_data_ep_desc_valid = 1;
 
@@ -1500,7 +1501,6 @@ drop_data_ep:
 	xhci_sideband_remove_endpoint(uadev[card_num].sb,
 			usb_pipe_endpoint(subs->dev, subs->data_endpoint->pipe));
 
-err:
 	return ret;
 }
 

From 93598167dcb6351ba40449d994244696168f1094 Mon Sep 17 00:00:00 2001
From: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Date: Tue, 24 Jun 2025 10:14:27 +0300
Subject: [PATCH 0769/1334] wifi: iwlwifi: mvm: assume '1' as the default
 mac_config_cmd version

Unfortunately, FWs of some devices don't have the version of the
iwl_mac_config_cmd defined in the TLVs. We send 0 as the 'def argument
to  iwl_fw_lookup_cmd_ver, so for such FWs, the return value will be 0,
leading to a warning, and to not sending the command.

Fix this by assuming that the default version is 1.

Fixes: 83f3ac2848b4 ("wifi: iwlwifi: Fix incorrect logic on cmd_ver range checking")
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250624071427.2662621-1-miriam.rachel.korenblit@intel.com
---
 drivers/net/wireless/intel/iwlwifi/mvm/mld-mac.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac.c b/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac.c
index 3c255ae916c8..3f8b840871d3 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac.c
@@ -32,9 +32,9 @@ static void iwl_mvm_mld_mac_ctxt_cmd_common(struct iwl_mvm *mvm,
 	unsigned int link_id;
 	int cmd_ver = iwl_fw_lookup_cmd_ver(mvm->fw,
 					    WIDE_ID(MAC_CONF_GROUP,
-						    MAC_CONFIG_CMD), 0);
+						    MAC_CONFIG_CMD), 1);
 
-	if (WARN_ON(cmd_ver < 1 || cmd_ver > 3))
+	if (WARN_ON(cmd_ver > 3))
 		return;
 
 	cmd->id_and_color = cpu_to_le32(mvmvif->id);

From dbee298cb7bba3aa112a0265b208f2f3861c5744 Mon Sep 17 00:00:00 2001
From: Joanne Koong <joannelkoong@gmail.com>
Date: Fri, 13 Jun 2025 17:01:14 -0700
Subject: [PATCH 0770/1334] fuse: fix fuse_fill_write_pages() upper bound
 calculation

This fixes a bug in commit 63c69ad3d18a ("fuse: refactor
fuse_fill_write_pages()") where max_pages << PAGE_SHIFT is mistakenly
used as the calculation for the max_pages upper limit but there's the
possibility that copy_folio_from_iter_atomic() may copy over bytes
from the iov_iter that are less than the full length of the folio,
which would lead to exceeding max_pages.

This commit fixes it by adding a 'ap->num_folios < max_folios' check.

Signed-off-by: Joanne Koong <joannelkoong@gmail.com>
Link: https://lore.kernel.org/20250614000114.910380-1-joannelkoong@gmail.com
Fixes: 63c69ad3d18a ("fuse: refactor fuse_fill_write_pages()")
Tested-by: Brian Foster <bfoster@redhat.com>
Reported-by: Brian Foster <bfoster@redhat.com>
Closes: https://lore.kernel.org/linux-fsdevel/aEq4haEQScwHIWK6@bfoster/
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/fuse/file.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index f102afc03359..47006d0753f1 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -1147,7 +1147,7 @@ static ssize_t fuse_send_write_pages(struct fuse_io_args *ia,
 static ssize_t fuse_fill_write_pages(struct fuse_io_args *ia,
 				     struct address_space *mapping,
 				     struct iov_iter *ii, loff_t pos,
-				     unsigned int max_pages)
+				     unsigned int max_folios)
 {
 	struct fuse_args_pages *ap = &ia->ap;
 	struct fuse_conn *fc = get_fuse_conn(mapping->host);
@@ -1157,12 +1157,11 @@ static ssize_t fuse_fill_write_pages(struct fuse_io_args *ia,
 	int err = 0;
 
 	num = min(iov_iter_count(ii), fc->max_write);
-	num = min(num, max_pages << PAGE_SHIFT);
 
 	ap->args.in_pages = true;
 	ap->descs[0].offset = offset;
 
-	while (num) {
+	while (num && ap->num_folios < max_folios) {
 		size_t tmp;
 		struct folio *folio;
 		pgoff_t index = pos >> PAGE_SHIFT;

From 14633da0f416fdbb6844d1b295cdc828b666e273 Mon Sep 17 00:00:00 2001
From: Victor Shih <victor.shih@genesyslogic.com.tw>
Date: Fri, 6 Jun 2025 19:01:19 +0800
Subject: [PATCH 0771/1334] mmc: core: Adjust some error messages for SD UHS-II
 cards

Adjust some error messages to debug mode to avoid causing
misunderstanding it is an error.

Signed-off-by: Victor Shih <victor.shih@genesyslogic.com.tw>
Acked-by: Adrian Hunter <adrian.hunter@intel.com>
Fixes: 9a9f7e13952b ("mmc: core: Support UHS-II card control and access")
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20250606110121.96314-2-victorshihgli@gmail.com
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/core/sd_uhs2.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/mmc/core/sd_uhs2.c b/drivers/mmc/core/sd_uhs2.c
index 1c31d0dfa961..de17d1611290 100644
--- a/drivers/mmc/core/sd_uhs2.c
+++ b/drivers/mmc/core/sd_uhs2.c
@@ -91,8 +91,8 @@ static int sd_uhs2_phy_init(struct mmc_host *host)
 
 	err = host->ops->uhs2_control(host, UHS2_PHY_INIT);
 	if (err) {
-		pr_err("%s: failed to initial phy for UHS-II!\n",
-		       mmc_hostname(host));
+		pr_debug("%s: failed to initial phy for UHS-II!\n",
+			 mmc_hostname(host));
 	}
 
 	return err;

From 2881ba9af073faa8ee7408a8d1e0575e50eb3f6c Mon Sep 17 00:00:00 2001
From: Victor Shih <victor.shih@genesyslogic.com.tw>
Date: Fri, 6 Jun 2025 19:01:20 +0800
Subject: [PATCH 0772/1334] mmc: sdhci: Add a helper function for dump register
 in dynamic debug mode

Add a helper function for dump register in dynamic debug mode.

Signed-off-by: Victor Shih <victor.shih@genesyslogic.com.tw>
Acked-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20250606110121.96314-3-victorshihgli@gmail.com
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/host/sdhci.h | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/drivers/mmc/host/sdhci.h b/drivers/mmc/host/sdhci.h
index f9d65dd0f2b2..70ada1857a4c 100644
--- a/drivers/mmc/host/sdhci.h
+++ b/drivers/mmc/host/sdhci.h
@@ -900,4 +900,20 @@ void sdhci_switch_external_dma(struct sdhci_host *host, bool en);
 void sdhci_set_data_timeout_irq(struct sdhci_host *host, bool enable);
 void __sdhci_set_timeout(struct sdhci_host *host, struct mmc_command *cmd);
 
+#if defined(CONFIG_DYNAMIC_DEBUG) || \
+	(defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE))
+#define SDHCI_DBG_ANYWAY 0
+#elif defined(DEBUG)
+#define SDHCI_DBG_ANYWAY 1
+#else
+#define SDHCI_DBG_ANYWAY 0
+#endif
+
+#define sdhci_dbg_dumpregs(host, fmt)					\
+do {									\
+	DEFINE_DYNAMIC_DEBUG_METADATA(descriptor, fmt);			\
+	if (DYNAMIC_DEBUG_BRANCH(descriptor) ||	SDHCI_DBG_ANYWAY)	\
+		sdhci_dumpregs(host);					\
+} while (0)
+
 #endif /* __SDHCI_HW_H */

From 49b14db035135341f6cf4de7af6ac2cbc8ad29b6 Mon Sep 17 00:00:00 2001
From: Victor Shih <victor.shih@genesyslogic.com.tw>
Date: Fri, 6 Jun 2025 19:01:21 +0800
Subject: [PATCH 0773/1334] mmc: sdhci-uhs2: Adjust some error messages and
 register dump for SD UHS-II card

Adjust some error messages to debug mode and register dump to dynamic
debug mode to avoid causing misunderstanding it is an error.

Signed-off-by: Victor Shih <victor.shih@genesyslogic.com.tw>
Acked-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20250606110121.96314-4-victorshihgli@gmail.com
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/host/sdhci-uhs2.c | 20 ++++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

diff --git a/drivers/mmc/host/sdhci-uhs2.c b/drivers/mmc/host/sdhci-uhs2.c
index c53b64d50c0d..0efeb9d0c376 100644
--- a/drivers/mmc/host/sdhci-uhs2.c
+++ b/drivers/mmc/host/sdhci-uhs2.c
@@ -99,8 +99,8 @@ void sdhci_uhs2_reset(struct sdhci_host *host, u16 mask)
 	/* hw clears the bit when it's done */
 	if (read_poll_timeout_atomic(sdhci_readw, val, !(val & mask), 10,
 				     UHS2_RESET_TIMEOUT_100MS, true, host, SDHCI_UHS2_SW_RESET)) {
-		pr_warn("%s: %s: Reset 0x%x never completed. %s: clean reset bit.\n", __func__,
-			mmc_hostname(host->mmc), (int)mask, mmc_hostname(host->mmc));
+		pr_debug("%s: %s: Reset 0x%x never completed. %s: clean reset bit.\n", __func__,
+			 mmc_hostname(host->mmc), (int)mask, mmc_hostname(host->mmc));
 		sdhci_writeb(host, 0, SDHCI_UHS2_SW_RESET);
 		return;
 	}
@@ -335,8 +335,8 @@ static int sdhci_uhs2_interface_detect(struct sdhci_host *host)
 	if (read_poll_timeout(sdhci_readl, val, (val & SDHCI_UHS2_IF_DETECT),
 			      100, UHS2_INTERFACE_DETECT_TIMEOUT_100MS, true,
 			      host, SDHCI_PRESENT_STATE)) {
-		pr_warn("%s: not detect UHS2 interface in 100ms.\n", mmc_hostname(host->mmc));
-		sdhci_dumpregs(host);
+		pr_debug("%s: not detect UHS2 interface in 100ms.\n", mmc_hostname(host->mmc));
+		sdhci_dbg_dumpregs(host, "UHS2 interface detect timeout in 100ms");
 		return -EIO;
 	}
 
@@ -345,8 +345,8 @@ static int sdhci_uhs2_interface_detect(struct sdhci_host *host)
 
 	if (read_poll_timeout(sdhci_readl, val, (val & SDHCI_UHS2_LANE_SYNC),
 			      100, UHS2_LANE_SYNC_TIMEOUT_150MS, true, host, SDHCI_PRESENT_STATE)) {
-		pr_warn("%s: UHS2 Lane sync fail in 150ms.\n", mmc_hostname(host->mmc));
-		sdhci_dumpregs(host);
+		pr_debug("%s: UHS2 Lane sync fail in 150ms.\n", mmc_hostname(host->mmc));
+		sdhci_dbg_dumpregs(host, "UHS2 Lane sync fail in 150ms");
 		return -EIO;
 	}
 
@@ -417,12 +417,12 @@ static int sdhci_uhs2_do_detect_init(struct mmc_host *mmc)
 		host->ops->uhs2_pre_detect_init(host);
 
 	if (sdhci_uhs2_interface_detect(host)) {
-		pr_warn("%s: cannot detect UHS2 interface.\n", mmc_hostname(host->mmc));
+		pr_debug("%s: cannot detect UHS2 interface.\n", mmc_hostname(host->mmc));
 		return -EIO;
 	}
 
 	if (sdhci_uhs2_init(host)) {
-		pr_warn("%s: UHS2 init fail.\n", mmc_hostname(host->mmc));
+		pr_debug("%s: UHS2 init fail.\n", mmc_hostname(host->mmc));
 		return -EIO;
 	}
 
@@ -504,8 +504,8 @@ static int sdhci_uhs2_check_dormant(struct sdhci_host *host)
 	if (read_poll_timeout(sdhci_readl, val, (val & SDHCI_UHS2_IN_DORMANT_STATE),
 			      100, UHS2_CHECK_DORMANT_TIMEOUT_100MS, true, host,
 			      SDHCI_PRESENT_STATE)) {
-		pr_warn("%s: UHS2 IN_DORMANT fail in 100ms.\n", mmc_hostname(host->mmc));
-		sdhci_dumpregs(host);
+		pr_debug("%s: UHS2 IN_DORMANT fail in 100ms.\n", mmc_hostname(host->mmc));
+		sdhci_dbg_dumpregs(host, "UHS2 IN_DORMANT fail in 100ms");
 		return -EIO;
 	}
 	return 0;

From dcc3bcfc5b50c625b475dcc25d167b6b947a6637 Mon Sep 17 00:00:00 2001
From: Ulf Hansson <ulf.hansson@linaro.org>
Date: Tue, 24 Jun 2025 13:09:32 +0200
Subject: [PATCH 0774/1334] Revert "mmc: sdhci: Disable SD card clock before
 changing parameters"

It has turned out the trying to strictly conform to the SDHCI specification
is causing problems. Let's revert and start over.

This reverts commit fb3bbc46c94f261b6156ee863c1b06c84cf157dc.

Cc: Erick Shepherd <erick.shepherd@ni.com>
Cc: stable@vger.kernel.org
Fixes: fb3bbc46c94f ("mmc: sdhci: Disable SD card clock before changing parameters")
Suggested-by: Adrian Hunter <adrian.hunter@intel.com>
Reported-by: Jonathan Liu <net147@gmail.com>
Reported-by: Salvatore Bonaccorso <carnil@debian.org>
Closes: https://bugs.debian.org/1108065
Acked-by: Adrian Hunter <adrian.hunter@intel.com>
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Link: https://lore.kernel.org/r/20250624110932.176925-1-ulf.hansson@linaro.org
---
 drivers/mmc/host/sdhci.c | 9 ++-------
 1 file changed, 2 insertions(+), 7 deletions(-)

diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c
index f008167d1863..e116f2db34d5 100644
--- a/drivers/mmc/host/sdhci.c
+++ b/drivers/mmc/host/sdhci.c
@@ -2065,15 +2065,10 @@ void sdhci_set_clock(struct sdhci_host *host, unsigned int clock)
 
 	host->mmc->actual_clock = 0;
 
-	clk = sdhci_readw(host, SDHCI_CLOCK_CONTROL);
-	if (clk & SDHCI_CLOCK_CARD_EN)
-		sdhci_writew(host, clk & ~SDHCI_CLOCK_CARD_EN,
-			SDHCI_CLOCK_CONTROL);
+	sdhci_writew(host, 0, SDHCI_CLOCK_CONTROL);
 
-	if (clock == 0) {
-		sdhci_writew(host, 0, SDHCI_CLOCK_CONTROL);
+	if (clock == 0)
 		return;
-	}
 
 	clk = sdhci_calc_clk(host, clock, &host->mmc->actual_clock);
 	sdhci_enable_clk(host, clk);

From ff21a6ec0f27c126db0a86d96751bd6e5d1d9874 Mon Sep 17 00:00:00 2001
From: Jack Yu <jack.yu@realtek.com>
Date: Tue, 24 Jun 2025 02:59:28 +0000
Subject: [PATCH 0775/1334] ASoC: rt721-sdca: fix boost gain calculation error

Fix the boost gain calculation error in rt721_sdca_set_gain_get.
This patch is specific for "FU33 Boost Volume".

Signed-off-by: Jack Yu <jack.yu@realtek.com>
Link: https://patch.msgid.link/1b18fcde41c64d6fa85451d523c0434a@realtek.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/rt721-sdca.c | 23 +++++++++++++++++++----
 1 file changed, 19 insertions(+), 4 deletions(-)

diff --git a/sound/soc/codecs/rt721-sdca.c b/sound/soc/codecs/rt721-sdca.c
index 1c9f32e405cf..ba080957e933 100644
--- a/sound/soc/codecs/rt721-sdca.c
+++ b/sound/soc/codecs/rt721-sdca.c
@@ -430,6 +430,7 @@ static int rt721_sdca_set_gain_get(struct snd_kcontrol *kcontrol,
 	unsigned int read_l, read_r, ctl_l = 0, ctl_r = 0;
 	unsigned int adc_vol_flag = 0;
 	const unsigned int interval_offset = 0xc0;
+	const unsigned int tendA = 0x200;
 	const unsigned int tendB = 0xa00;
 
 	if (strstr(ucontrol->id.name, "FU1E Capture Volume") ||
@@ -439,9 +440,16 @@ static int rt721_sdca_set_gain_get(struct snd_kcontrol *kcontrol,
 	regmap_read(rt721->mbq_regmap, mc->reg, &read_l);
 	regmap_read(rt721->mbq_regmap, mc->rreg, &read_r);
 
-	if (mc->shift == 8) /* boost gain */
+	if (mc->shift == 8) {
+		/* boost gain */
 		ctl_l = read_l / tendB;
-	else {
+	} else if (mc->shift == 1) {
+		/* FU33 boost gain */
+		if (read_l == 0x8000 || read_l == 0xfe00)
+			ctl_l = 0;
+		else
+			ctl_l = read_l / tendA + 1;
+	} else {
 		if (adc_vol_flag)
 			ctl_l = mc->max - (((0x1e00 - read_l) & 0xffff) / interval_offset);
 		else
@@ -449,9 +457,16 @@ static int rt721_sdca_set_gain_get(struct snd_kcontrol *kcontrol,
 	}
 
 	if (read_l != read_r) {
-		if (mc->shift == 8) /* boost gain */
+		if (mc->shift == 8) {
+			/* boost gain */
 			ctl_r = read_r / tendB;
-		else { /* ADC/DAC gain */
+		} else if (mc->shift == 1) {
+			/* FU33 boost gain */
+			if (read_r == 0x8000 || read_r == 0xfe00)
+				ctl_r = 0;
+			else
+				ctl_r = read_r / tendA + 1;
+		} else { /* ADC/DAC gain */
 			if (adc_vol_flag)
 				ctl_r = mc->max - (((0x1e00 - read_r) & 0xffff) / interval_offset);
 			else

From d87c3ca0f8f1ca4c25f2ed819e954952f4d8d709 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Tue, 24 Jun 2025 13:07:49 +0200
Subject: [PATCH 0776/1334] wifi: mac80211: finish link init before RCU publish

Since the link/conf pointers can be accessed without any
protection other than RCU, make sure the data is actually
set up before publishing the structures.

Fixes: b2e8434f1829 ("wifi: mac80211: set up/tear down client vif links properly")
Link: https://patch.msgid.link/20250624130749.9a308b713c74.I4a80f5eead112a38730939ea591d2e275c721256@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/link.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/mac80211/link.c b/net/mac80211/link.c
index d40c2bd3b50b..4f7b7d0f64f2 100644
--- a/net/mac80211/link.c
+++ b/net/mac80211/link.c
@@ -93,9 +93,6 @@ void ieee80211_link_init(struct ieee80211_sub_if_data *sdata,
 	if (link_id < 0)
 		link_id = 0;
 
-	rcu_assign_pointer(sdata->vif.link_conf[link_id], link_conf);
-	rcu_assign_pointer(sdata->link[link_id], link);
-
 	if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN) {
 		struct ieee80211_sub_if_data *ap_bss;
 		struct ieee80211_bss_conf *ap_bss_conf;
@@ -145,6 +142,9 @@ void ieee80211_link_init(struct ieee80211_sub_if_data *sdata,
 
 		ieee80211_link_debugfs_add(link);
 	}
+
+	rcu_assign_pointer(sdata->vif.link_conf[link_id], link_conf);
+	rcu_assign_pointer(sdata->link[link_id], link);
 }
 
 void ieee80211_link_stop(struct ieee80211_link_data *link)

From fa78e9b606a472495ef5b6b3d8b45c37f7727f9d Mon Sep 17 00:00:00 2001
From: Elena Popa <elena.popa@nxp.com>
Date: Fri, 30 May 2025 13:40:00 +0300
Subject: [PATCH 0777/1334] rtc: pcf2127: fix SPI command byte for PCF2131

PCF2131 was not responding to read/write operations using SPI. PCF2131
has a different command byte definition, compared to PCF2127/29. Added
the new command byte definition when PCF2131 is detected.

Fixes: afc505bf9039 ("rtc: pcf2127: add support for PCF2131 RTC")
Cc: stable@vger.kernel.org
Signed-off-by: Elena Popa <elena.popa@nxp.com>
Acked-by: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Link: https://lore.kernel.org/r/20250530104001.957977-1-elena.popa@nxp.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-pcf2127.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/rtc/rtc-pcf2127.c b/drivers/rtc/rtc-pcf2127.c
index 31c7dca8f469..2c7917bc2a31 100644
--- a/drivers/rtc/rtc-pcf2127.c
+++ b/drivers/rtc/rtc-pcf2127.c
@@ -1538,6 +1538,11 @@ static int pcf2127_spi_probe(struct spi_device *spi)
 		variant = &pcf21xx_cfg[type];
 	}
 
+	if (variant->type == PCF2131) {
+		config.read_flag_mask = 0x0;
+		config.write_flag_mask = 0x0;
+	}
+
 	config.max_register = variant->max_register,
 
 	regmap = devm_regmap_init_spi(spi, &config);

From 08d82d0cad51c2b1d454fe41ea1ff96ade676961 Mon Sep 17 00:00:00 2001
From: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Date: Thu, 29 May 2025 16:29:22 -0400
Subject: [PATCH 0778/1334] rtc: pcf2127: add missing semicolon after statement

Replace comma with semicolon at the end of the statement when setting
config.max_register.

Fixes: fd28ceb4603f ("rtc: pcf2127: add variant-specific configuration structure")
Cc: stable@vger.kernel.org
Cc: Elena Popa <elena.popa@nxp.com>
Signed-off-by: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Link: https://lore.kernel.org/r/20250529202923.1552560-1-hugo@hugovil.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/rtc/rtc-pcf2127.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/rtc/rtc-pcf2127.c b/drivers/rtc/rtc-pcf2127.c
index 2c7917bc2a31..2e1ac0c42e93 100644
--- a/drivers/rtc/rtc-pcf2127.c
+++ b/drivers/rtc/rtc-pcf2127.c
@@ -1543,7 +1543,7 @@ static int pcf2127_spi_probe(struct spi_device *spi)
 		config.write_flag_mask = 0x0;
 	}
 
-	config.max_register = variant->max_register,
+	config.max_register = variant->max_register;
 
 	regmap = devm_regmap_init_spi(spi, &config);
 	if (IS_ERR(regmap)) {

From 0748e553df0225754c316a92af3a77fdc057b358 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Tue, 24 Jun 2025 10:25:04 -0400
Subject: [PATCH 0779/1334] userns and mnt_idmap leak in open_tree_attr(2)

Once want_mount_setattr() has returned a positive, it does require
finish_mount_kattr() to release ->mnt_userns.  Failing do_mount_setattr()
does not change that.

As the result, we can end up leaking userns and possibly mnt_idmap as
well.

Fixes: c4a16820d901 ("fs: add open_tree_attr()")
Reviewed-by: Christian Brauner <brauner@kernel.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/namespace.c | 10 +++-------
 1 file changed, 3 insertions(+), 7 deletions(-)

diff --git a/fs/namespace.c b/fs/namespace.c
index eed83254492f..54c59e091919 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -5307,16 +5307,12 @@ SYSCALL_DEFINE5(open_tree_attr, int, dfd, const char __user *, filename,
 			kattr.kflags |= MOUNT_KATTR_RECURSE;
 
 		ret = wants_mount_setattr(uattr, usize, &kattr);
-		if (ret < 0)
-			return ret;
-
-		if (ret) {
+		if (ret > 0) {
 			ret = do_mount_setattr(&file->f_path, &kattr);
-			if (ret)
-				return ret;
-
 			finish_mount_kattr(&kattr);
 		}
+		if (ret)
+			return ret;
 	}
 
 	fd = get_unused_fd_flags(flags & O_CLOEXEC);

From f23c52aafb1675ab1d1f46914556d8e29cbbf7b3 Mon Sep 17 00:00:00 2001
From: Fabio Estevam <festevam@gmail.com>
Date: Thu, 19 Jun 2025 08:46:17 -0300
Subject: [PATCH 0780/1334] serial: imx: Restore original RXTL for console to
 fix data loss

Commit 7a637784d517 ("serial: imx: reduce RX interrupt frequency")
introduced a regression on the i.MX6UL EVK board. The issue can be
reproduced with the following steps:

- Open vi on the board.
- Paste a text file (~150 characters).
- Save the file, then repeat the process.
- Compare the sha256sum of the saved files.

The checksums do not match due to missing characters or entire lines.

Fix this by restoring the RXTL value to 1 when the UART is used as a
console.

This ensures timely RX interrupts and reliable data reception in console
mode.

With this change, pasted content is saved correctly, and checksums are
always consistent.

Cc: stable <stable@kernel.org>
Fixes: 7a637784d517 ("serial: imx: reduce RX interrupt frequency")
Signed-off-by: Fabio Estevam <festevam@gmail.com>
Reviewed-by: Stefan Wahren <wahrenst@gmx.net>
Link: https://lore.kernel.org/r/20250619114617.2791939-1-festevam@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/imx.c | 17 ++++++++++++-----
 1 file changed, 12 insertions(+), 5 deletions(-)

diff --git a/drivers/tty/serial/imx.c b/drivers/tty/serial/imx.c
index bd02ee898f5d..500dfc009d03 100644
--- a/drivers/tty/serial/imx.c
+++ b/drivers/tty/serial/imx.c
@@ -235,6 +235,7 @@ struct imx_port {
 	enum imx_tx_state	tx_state;
 	struct hrtimer		trigger_start_tx;
 	struct hrtimer		trigger_stop_tx;
+	unsigned int		rxtl;
 };
 
 struct imx_port_ucrs {
@@ -1339,6 +1340,7 @@ static void imx_uart_clear_rx_errors(struct imx_port *sport)
 
 #define TXTL_DEFAULT 8
 #define RXTL_DEFAULT 8 /* 8 characters or aging timer */
+#define RXTL_CONSOLE_DEFAULT 1
 #define TXTL_DMA 8 /* DMA burst setting */
 #define RXTL_DMA 9 /* DMA burst setting */
 
@@ -1457,7 +1459,7 @@ static void imx_uart_disable_dma(struct imx_port *sport)
 	ucr1 &= ~(UCR1_RXDMAEN | UCR1_TXDMAEN | UCR1_ATDMAEN);
 	imx_uart_writel(sport, ucr1, UCR1);
 
-	imx_uart_setup_ufcr(sport, TXTL_DEFAULT, RXTL_DEFAULT);
+	imx_uart_setup_ufcr(sport, TXTL_DEFAULT, sport->rxtl);
 
 	sport->dma_is_enabled = 0;
 }
@@ -1482,7 +1484,12 @@ static int imx_uart_startup(struct uart_port *port)
 		return retval;
 	}
 
-	imx_uart_setup_ufcr(sport, TXTL_DEFAULT, RXTL_DEFAULT);
+	if (uart_console(&sport->port))
+		sport->rxtl = RXTL_CONSOLE_DEFAULT;
+	else
+		sport->rxtl = RXTL_DEFAULT;
+
+	imx_uart_setup_ufcr(sport, TXTL_DEFAULT, sport->rxtl);
 
 	/* disable the DREN bit (Data Ready interrupt enable) before
 	 * requesting IRQs
@@ -1948,7 +1955,7 @@ static int imx_uart_poll_init(struct uart_port *port)
 	if (retval)
 		clk_disable_unprepare(sport->clk_ipg);
 
-	imx_uart_setup_ufcr(sport, TXTL_DEFAULT, RXTL_DEFAULT);
+	imx_uart_setup_ufcr(sport, TXTL_DEFAULT, sport->rxtl);
 
 	uart_port_lock_irqsave(&sport->port, &flags);
 
@@ -2040,7 +2047,7 @@ static int imx_uart_rs485_config(struct uart_port *port, struct ktermios *termio
 		/* If the receiver trigger is 0, set it to a default value */
 		ufcr = imx_uart_readl(sport, UFCR);
 		if ((ufcr & UFCR_RXTL_MASK) == 0)
-			imx_uart_setup_ufcr(sport, TXTL_DEFAULT, RXTL_DEFAULT);
+			imx_uart_setup_ufcr(sport, TXTL_DEFAULT, sport->rxtl);
 		imx_uart_start_rx(port);
 	}
 
@@ -2302,7 +2309,7 @@ imx_uart_console_setup(struct console *co, char *options)
 	else
 		imx_uart_console_get_options(sport, &baud, &parity, &bits);
 
-	imx_uart_setup_ufcr(sport, TXTL_DEFAULT, RXTL_DEFAULT);
+	imx_uart_setup_ufcr(sport, TXTL_DEFAULT, sport->rxtl);
 
 	retval = uart_set_options(&sport->port, co, baud, parity, bits, flow);
 

From 09812134071b3941fb81def30b61ed36d3a5dfb5 Mon Sep 17 00:00:00 2001
From: Yao Zi <ziyao@disroot.org>
Date: Mon, 23 Jun 2025 09:34:45 +0000
Subject: [PATCH 0781/1334] dt-bindings: serial: 8250: Make clocks and
 clock-frequency exclusive

The 8250 binding before converting to json-schema states,

  - clock-frequency : the input clock frequency for the UART
  	or
  - clocks phandle to refer to the clk used as per Documentation/devicetree

for clock-related properties, where "or" indicates these properties
shouldn't exist at the same time.

Additionally, the behavior of Linux's driver is strange when both clocks
and clock-frequency are specified: it ignores clocks and obtains the
frequency from clock-frequency, left the specified clocks unclaimed. It
may even be disabled, which is undesired most of the time.

But "anyOf" doesn't prevent these two properties from coexisting, as it
considers the object valid as long as there's at LEAST one match.

Let's switch to "oneOf" and disallows the other property if one exists,
precisely matching the original binding and avoiding future confusion on
the driver's behavior.

Fixes: e69f5dc623f9 ("dt-bindings: serial: Convert 8250 to json-schema")
Cc: stable <stable@kernel.org>
Signed-off-by: Yao Zi <ziyao@disroot.org>
Reviewed-by: Conor Dooley <conor.dooley@microchip.com>
Link: https://lore.kernel.org/r/20250623093445.62327-1-ziyao@disroot.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 Documentation/devicetree/bindings/serial/8250.yaml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/serial/8250.yaml b/Documentation/devicetree/bindings/serial/8250.yaml
index 33d2016b6509..c6bc27709bf7 100644
--- a/Documentation/devicetree/bindings/serial/8250.yaml
+++ b/Documentation/devicetree/bindings/serial/8250.yaml
@@ -45,7 +45,7 @@ allOf:
                   - ns16550
                   - ns16550a
     then:
-      anyOf:
+      oneOf:
         - required: [ clock-frequency ]
         - required: [ clocks ]
 

From 0043ec26d827ddb1e85bd9786693152aa6f55d16 Mon Sep 17 00:00:00 2001
From: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Date: Thu, 12 Jun 2025 20:11:14 +0530
Subject: [PATCH 0782/1334] drm/amdgpu/gfx9: Add Cleaner Shader Support for
 GFX9.x GPUs
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Enable the cleaner shader for other GFX9.x series of GPUs to provide
data isolation between GPU workloads. The cleaner shader is responsible
for clearing the Local Data Store (LDS), Vector General Purpose
Registers (VGPRs), and Scalar General Purpose Registers (SGPRs), which
helps prevent data leakage and ensures accurate computation results.

This update extends cleaner shader support to GFX9.x GPUs, previously
available for GFX9.4.2. It enhances security by clearing GPU memory
between processes and maintains a consistent GPU state across KGD and
KFD workloads.

Cc: Manu Rastogi <manu.rastogi@amd.com>
Cc: Christian König <christian.koenig@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 99808926d0ea6234a89e35240a7cb088368de9e1)
---
 drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c | 19 +++++++++++++++++++
 1 file changed, 19 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index d377a7c57d5e..ad9be3656653 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -2235,6 +2235,25 @@ static int gfx_v9_0_sw_init(struct amdgpu_ip_block *ip_block)
 	}
 
 	switch (amdgpu_ip_version(adev, GC_HWIP, 0)) {
+	case IP_VERSION(9, 0, 1):
+	case IP_VERSION(9, 2, 1):
+	case IP_VERSION(9, 4, 0):
+	case IP_VERSION(9, 2, 2):
+	case IP_VERSION(9, 1, 0):
+	case IP_VERSION(9, 3, 0):
+		adev->gfx.cleaner_shader_ptr = gfx_9_4_2_cleaner_shader_hex;
+		adev->gfx.cleaner_shader_size = sizeof(gfx_9_4_2_cleaner_shader_hex);
+		if (adev->gfx.me_fw_version  >= 167 &&
+		    adev->gfx.pfp_fw_version >= 196 &&
+		    adev->gfx.mec_fw_version >= 474) {
+			adev->gfx.enable_cleaner_shader = true;
+			r = amdgpu_gfx_cleaner_shader_sw_init(adev, adev->gfx.cleaner_shader_size);
+			if (r) {
+				adev->gfx.enable_cleaner_shader = false;
+				dev_err(adev->dev, "Failed to initialize cleaner shader\n");
+			}
+		}
+		break;
 	case IP_VERSION(9, 4, 2):
 		adev->gfx.cleaner_shader_ptr = gfx_9_4_2_cleaner_shader_hex;
 		adev->gfx.cleaner_shader_size = sizeof(gfx_9_4_2_cleaner_shader_hex);

From 99579c55c3d6132a5236926652c0a72a526b809d Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Tue, 20 May 2025 10:02:14 -0400
Subject: [PATCH 0783/1334] drm/amdgpu/mes: add compatibility checks for
 set_hw_resource_1

Seems some older MES firmware versions do not properly support
this packet.  Add back some the compatibility checks.

v2: switch to fw version check (Shaoyun)

Fixes: f81cd793119e ("drm/amd/amdgpu: Fix MES init sequence")
Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/4295
Cc: Shaoyun Liu <shaoyun.liu@amd.com>
Reviewed-by: shaoyun.liu <shaoyun.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 0180e0a5dd5c6ff118043ee42dbbbddaf881f283)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/amdgpu/mes_v11_0.c | 10 ++++++----
 drivers/gpu/drm/amd/amdgpu/mes_v12_0.c |  3 ++-
 2 files changed, 8 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
index c9eba537de09..28eb846280dd 100644
--- a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
@@ -1630,10 +1630,12 @@ static int mes_v11_0_hw_init(struct amdgpu_ip_block *ip_block)
 	if (r)
 		goto failure;
 
-	r = mes_v11_0_set_hw_resources_1(&adev->mes);
-	if (r) {
-		DRM_ERROR("failed mes_v11_0_set_hw_resources_1, r=%d\n", r);
-		goto failure;
+	if ((adev->mes.sched_version & AMDGPU_MES_VERSION_MASK) >= 0x50) {
+		r = mes_v11_0_set_hw_resources_1(&adev->mes);
+		if (r) {
+			DRM_ERROR("failed mes_v11_0_set_hw_resources_1, r=%d\n", r);
+			goto failure;
+		}
 	}
 
 	r = mes_v11_0_query_sched_status(&adev->mes);
diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c
index b4f17332d466..6b222630f3fa 100644
--- a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c
@@ -1742,7 +1742,8 @@ static int mes_v12_0_hw_init(struct amdgpu_ip_block *ip_block)
 	if (r)
 		goto failure;
 
-	mes_v12_0_set_hw_resources_1(&adev->mes, AMDGPU_MES_SCHED_PIPE);
+	if ((adev->mes.sched_version & AMDGPU_MES_VERSION_MASK) >= 0x4b)
+		mes_v12_0_set_hw_resources_1(&adev->mes, AMDGPU_MES_SCHED_PIPE);
 
 	mes_v12_0_init_aggregated_doorbell(&adev->mes);
 

From 73eab78721f7b85216f1ca8c7b732f13213b5b32 Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Tue, 17 Jun 2025 13:30:52 -0500
Subject: [PATCH 0784/1334] drm/amd: Adjust output for discovery error handling

commit 017fbb6690c2 ("drm/amdgpu/discovery: check ip_discovery fw file
available") added support for reading an amdgpu IP discovery bin file
for some specific products. If it's not found then it will fallback to
hardcoded values. However if it's not found there is also a lot of noise
about missing files and errors.

Adjust the error handling to decrease most messages to DEBUG and to show
users less about missing files.

Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Reported-by: Marcus Seyfarth <m.seyfarth@gmail.com>
Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/4312
Tested-by: Marcus Seyfarth <m.seyfarth@gmail.com>
Fixes: 017fbb6690c2 ("drm/amdgpu/discovery: check ip_discovery fw file available")
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Link: https://lore.kernel.org/r/20250617183052.1692059-1-superm1@kernel.org
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 49f1f9f6c3c9febf8ba93f94a8d9c8d03e1ea0a1)
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c | 28 +++++++++----------
 1 file changed, 13 insertions(+), 15 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
index a0e9bf9b2710..81b3443c8d7f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
@@ -321,10 +321,12 @@ static int amdgpu_discovery_read_binary_from_file(struct amdgpu_device *adev,
 	const struct firmware *fw;
 	int r;
 
-	r = request_firmware(&fw, fw_name, adev->dev);
+	r = firmware_request_nowarn(&fw, fw_name, adev->dev);
 	if (r) {
-		dev_err(adev->dev, "can't load firmware \"%s\"\n",
-			fw_name);
+		if (amdgpu_discovery == 2)
+			dev_err(adev->dev, "can't load firmware \"%s\"\n", fw_name);
+		else
+			drm_info(&adev->ddev, "Optional firmware \"%s\" was not found\n", fw_name);
 		return r;
 	}
 
@@ -459,16 +461,12 @@ static int amdgpu_discovery_init(struct amdgpu_device *adev)
 	/* Read from file if it is the preferred option */
 	fw_name = amdgpu_discovery_get_fw_name(adev);
 	if (fw_name != NULL) {
-		dev_info(adev->dev, "use ip discovery information from file");
+		drm_dbg(&adev->ddev, "use ip discovery information from file");
 		r = amdgpu_discovery_read_binary_from_file(adev, adev->mman.discovery_bin, fw_name);
-
-		if (r) {
-			dev_err(adev->dev, "failed to read ip discovery binary from file\n");
-			r = -EINVAL;
+		if (r)
 			goto out;
-		}
-
 	} else {
+		drm_dbg(&adev->ddev, "use ip discovery information from memory");
 		r = amdgpu_discovery_read_binary_from_mem(
 			adev, adev->mman.discovery_bin);
 		if (r)
@@ -1338,10 +1336,8 @@ static int amdgpu_discovery_reg_base_init(struct amdgpu_device *adev)
 	int r;
 
 	r = amdgpu_discovery_init(adev);
-	if (r) {
-		DRM_ERROR("amdgpu_discovery_init failed\n");
+	if (r)
 		return r;
-	}
 
 	wafl_ver = 0;
 	adev->gfx.xcc_mask = 0;
@@ -2579,8 +2575,10 @@ int amdgpu_discovery_set_ip_blocks(struct amdgpu_device *adev)
 		break;
 	default:
 		r = amdgpu_discovery_reg_base_init(adev);
-		if (r)
-			return -EINVAL;
+		if (r) {
+			drm_err(&adev->ddev, "discovery failed: %d\n", r);
+			return r;
+		}
 
 		amdgpu_discovery_harvest_ip(adev);
 		amdgpu_discovery_get_gfx_info(adev);

From 899dec4e885f839da2065803e21b7ab003a5c609 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Thu, 19 Jun 2025 17:56:29 -0400
Subject: [PATCH 0785/1334] drm/amdgpu/sdma6: add ucode version checks for
 userq support

SDMA 6.0.0 version 24
SDMA 6.0.2 version 21
SDMA 6.0.3 version 25

Reviewed-by: Jesse Zhang <Jesse.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit e8cca30d8b34f1c4101c237914c53068d4a55e73)
---
 drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c | 19 ++++++++++++++++---
 1 file changed, 16 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c
index 5a70ae17be04..a9bdf8d61d6c 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c
@@ -1374,9 +1374,22 @@ static int sdma_v6_0_sw_init(struct amdgpu_ip_block *ip_block)
 	else
 		DRM_ERROR("Failed to allocated memory for SDMA IP Dump\n");
 
-	/* add firmware version checks here */
-	if (0 && !adev->sdma.disable_uq)
-		adev->userq_funcs[AMDGPU_HW_IP_DMA] = &userq_mes_funcs;
+	switch (amdgpu_ip_version(adev, SDMA0_HWIP, 0)) {
+	case IP_VERSION(6, 0, 0):
+		if ((adev->sdma.instance[0].fw_version >= 24) && !adev->sdma.disable_uq)
+			adev->userq_funcs[AMDGPU_HW_IP_DMA] = &userq_mes_funcs;
+		break;
+	case IP_VERSION(6, 0, 2):
+		if ((adev->sdma.instance[0].fw_version >= 21) && !adev->sdma.disable_uq)
+			adev->userq_funcs[AMDGPU_HW_IP_DMA] = &userq_mes_funcs;
+		break;
+	case IP_VERSION(6, 0, 3):
+		if ((adev->sdma.instance[0].fw_version >= 25) && !adev->sdma.disable_uq)
+			adev->userq_funcs[AMDGPU_HW_IP_DMA] = &userq_mes_funcs;
+		break;
+	default:
+		break;
+	}
 
 	r = amdgpu_sdma_sysfs_reset_mask_init(adev);
 	if (r)

From 31135cc99c40247bec924dcdcd74a58e866c52d8 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Fri, 20 Jun 2025 11:39:22 -0400
Subject: [PATCH 0786/1334] drm/amdgpu/sdma7: add ucode version checks for
 userq support

SDMA 7.0.0/1: 7836028

Reviewed-by: Jesse Zhang <Jesse.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 8c011408ed842dfccdd50a90a9cf6bccdb85cc0e)
---
 drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c | 12 +++++++++---
 1 file changed, 9 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c
index ad47d0bdf777..86903eccbd4e 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c
@@ -1349,9 +1349,15 @@ static int sdma_v7_0_sw_init(struct amdgpu_ip_block *ip_block)
 	else
 		DRM_ERROR("Failed to allocated memory for SDMA IP Dump\n");
 
-	/* add firmware version checks here */
-	if (0 && !adev->sdma.disable_uq)
-		adev->userq_funcs[AMDGPU_HW_IP_DMA] = &userq_mes_funcs;
+	switch (amdgpu_ip_version(adev, SDMA0_HWIP, 0)) {
+	case IP_VERSION(7, 0, 0):
+	case IP_VERSION(7, 0, 1):
+		if ((adev->sdma.instance[0].fw_version >= 7836028) && !adev->sdma.disable_uq)
+			adev->userq_funcs[AMDGPU_HW_IP_DMA] = &userq_mes_funcs;
+		break;
+	default:
+		break;
+	}
 
 	return r;
 }

From 66abb996999de0d440a02583a6e70c2c24deab45 Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Mon, 23 Jun 2025 12:11:13 -0500
Subject: [PATCH 0787/1334] drm/amd/display: Fix AMDGPU_MAX_BL_LEVEL value

[Why]
commit 16dc8bc27c2a ("drm/amd/display: Export full brightness range to
userspace") adjusted the brightness range to scale to larger values, but
missed updating AMDGPU_MAX_BL_LEVEL which is needed to make sure that
scaling works properly with custom brightness curves.

[How]
As the change for max brightness of 0xFFFF only applies to devices
supporting DC, use existing DC define MAX_BACKLIGHT_LEVEL.

Fixes: 16dc8bc27c2a ("drm/amd/display: Export full brightness range to userspace")
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Link: https://lore.kernel.org/r/20250623171114.1156451-1-mario.limonciello@amd.com
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 5b852044eb0d3e1f1c946d32e05fcb068e0a20a0)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index bc4cd11bfc79..0b8ac9edc070 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -4718,16 +4718,16 @@ static int get_brightness_range(const struct amdgpu_dm_backlight_caps *caps,
 	return 1;
 }
 
-/* Rescale from [min..max] to [0..AMDGPU_MAX_BL_LEVEL] */
+/* Rescale from [min..max] to [0..MAX_BACKLIGHT_LEVEL] */
 static inline u32 scale_input_to_fw(int min, int max, u64 input)
 {
-	return DIV_ROUND_CLOSEST_ULL(input * AMDGPU_MAX_BL_LEVEL, max - min);
+	return DIV_ROUND_CLOSEST_ULL(input * MAX_BACKLIGHT_LEVEL, max - min);
 }
 
-/* Rescale from [0..AMDGPU_MAX_BL_LEVEL] to [min..max] */
+/* Rescale from [0..MAX_BACKLIGHT_LEVEL] to [min..max] */
 static inline u32 scale_fw_to_input(int min, int max, u64 input)
 {
-	return min + DIV_ROUND_CLOSEST_ULL(input * (max - min), AMDGPU_MAX_BL_LEVEL);
+	return min + DIV_ROUND_CLOSEST_ULL(input * (max - min), MAX_BACKLIGHT_LEVEL);
 }
 
 static void convert_custom_brightness(const struct amdgpu_dm_backlight_caps *caps,
@@ -4947,7 +4947,7 @@ amdgpu_dm_register_backlight_device(struct amdgpu_dm_connector *aconnector)
 		drm_dbg(drm, "Backlight caps: min: %d, max: %d, ac %d, dc %d\n", min, max,
 			caps->ac_level, caps->dc_level);
 	} else
-		props.brightness = props.max_brightness = AMDGPU_MAX_BL_LEVEL;
+		props.brightness = props.max_brightness = MAX_BACKLIGHT_LEVEL;
 
 	if (caps->data_points && !(amdgpu_dc_debug_mask & DC_DISABLE_CUSTOM_BRIGHTNESS_CURVE))
 		drm_info(drm, "Using custom brightness curve\n");

From 6847b3b6e84ef37451c074e6a8db3fbd250c8dbf Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Mon, 16 Jun 2025 18:08:41 +0200
Subject: [PATCH 0788/1334] drm/amd/display: Add sanity checks for
 drm_edid_raw()

When EDID is retrieved via drm_edid_raw(), it doesn't guarantee to
return proper EDID bytes the caller wants: it may be either NULL (that
leads to an Oops) or with too long bytes over the fixed size raw_edid
array (that may lead to memory corruption).  The latter was reported
actually when connected with a bad adapter.

Add sanity checks for drm_edid_raw() to address the above corner
cases, and return EDID_BAD_INPUT accordingly.

Fixes: 48edb2a4256e ("drm/amd/display: switch amdgpu_dm_connector to use struct drm_edid")
Link: https://bugzilla.suse.com/show_bug.cgi?id=1236415
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 648d3f4d209725d51900d6a3ed46b7b600140cdf)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c
index d4395b92fb85..9e3e51a2dc49 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c
@@ -1029,6 +1029,10 @@ enum dc_edid_status dm_helpers_read_local_edid(
 			return EDID_NO_RESPONSE;
 
 		edid = drm_edid_raw(drm_edid); // FIXME: Get rid of drm_edid_raw()
+		if (!edid ||
+		    edid->extensions >= sizeof(sink->dc_edid.raw_edid) / EDID_LENGTH)
+			return EDID_BAD_INPUT;
+
 		sink->dc_edid.length = EDID_LENGTH * (edid->extensions + 1);
 		memmove(sink->dc_edid.raw_edid, (uint8_t *)edid, sink->dc_edid.length);
 

From bec15191d52300defa282e3fd83820f69e447116 Mon Sep 17 00:00:00 2001
From: RD Babiera <rdbabiera@google.com>
Date: Wed, 18 Jun 2025 23:06:04 +0000
Subject: [PATCH 0789/1334] usb: typec: tcpm: apply vbus before data bringup in
 tcpm_src_attach

This patch fixes Type-C compliance test TD 4.7.6 - Try.SNK DRP Connect
SNKAS.

tVbusON has a limit of 275ms when entering SRC_ATTACHED. Compliance
testers can interpret the TryWait.Src to Attached.Src transition after
Try.Snk as being in Attached.Src the entire time, so ~170ms is lost
to the debounce timer.

Setting the data role can be a costly operation in host mode, and when
completed after 100ms can cause Type-C compliance test check TD 4.7.5.V.4
to fail.

Turn VBUS on before tcpm_set_roles to meet timing requirement.

Fixes: f0690a25a140 ("staging: typec: USB Type-C Port Manager (tcpm)")
Cc: stable <stable@kernel.org>
Signed-off-by: RD Babiera <rdbabiera@google.com>
Reviewed-by: Badhri Jagan Sridharan <badhri@google.com>
Reviewed-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Link: https://lore.kernel.org/r/20250618230606.3272497-2-rdbabiera@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/typec/tcpm/tcpm.c | 34 +++++++++++++++++-----------------
 1 file changed, 17 insertions(+), 17 deletions(-)

diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c
index 1a1f9e1f8e4e..1f6fdfaa34bf 100644
--- a/drivers/usb/typec/tcpm/tcpm.c
+++ b/drivers/usb/typec/tcpm/tcpm.c
@@ -4410,17 +4410,6 @@ static int tcpm_src_attach(struct tcpm_port *port)
 
 	tcpm_enable_auto_vbus_discharge(port, true);
 
-	ret = tcpm_set_roles(port, true, TYPEC_STATE_USB,
-			     TYPEC_SOURCE, tcpm_data_role_for_source(port));
-	if (ret < 0)
-		return ret;
-
-	if (port->pd_supported) {
-		ret = port->tcpc->set_pd_rx(port->tcpc, true);
-		if (ret < 0)
-			goto out_disable_mux;
-	}
-
 	/*
 	 * USB Type-C specification, version 1.2,
 	 * chapter 4.5.2.2.8.1 (Attached.SRC Requirements)
@@ -4430,13 +4419,24 @@ static int tcpm_src_attach(struct tcpm_port *port)
 	    (polarity == TYPEC_POLARITY_CC2 && port->cc1 == TYPEC_CC_RA)) {
 		ret = tcpm_set_vconn(port, true);
 		if (ret < 0)
-			goto out_disable_pd;
+			return ret;
 	}
 
 	ret = tcpm_set_vbus(port, true);
 	if (ret < 0)
 		goto out_disable_vconn;
 
+	ret = tcpm_set_roles(port, true, TYPEC_STATE_USB, TYPEC_SOURCE,
+			     tcpm_data_role_for_source(port));
+	if (ret < 0)
+		goto out_disable_vbus;
+
+	if (port->pd_supported) {
+		ret = port->tcpc->set_pd_rx(port->tcpc, true);
+		if (ret < 0)
+			goto out_disable_mux;
+	}
+
 	port->pd_capable = false;
 
 	port->partner = NULL;
@@ -4447,14 +4447,14 @@ static int tcpm_src_attach(struct tcpm_port *port)
 
 	return 0;
 
-out_disable_vconn:
-	tcpm_set_vconn(port, false);
-out_disable_pd:
-	if (port->pd_supported)
-		port->tcpc->set_pd_rx(port->tcpc, false);
 out_disable_mux:
 	tcpm_mux_set(port, TYPEC_STATE_SAFE, USB_ROLE_NONE,
 		     TYPEC_ORIENTATION_NONE);
+out_disable_vbus:
+	tcpm_set_vbus(port, false);
+out_disable_vconn:
+	tcpm_set_vconn(port, false);
+
 	return ret;
 }
 

From 2831a81077f5162f104ba5a97a7d886eb371c21c Mon Sep 17 00:00:00 2001
From: Pawel Laszczak <pawell@cadence.com>
Date: Fri, 20 Jun 2025 08:23:12 +0000
Subject: [PATCH 0790/1334] usb: cdnsp: Fix issue with CV Bad Descriptor test

The SSP2 controller has extra endpoint state preserve bit (ESP) which
setting causes that endpoint state will be preserved during
Halt Endpoint command. It is used only for EP0.
Without this bit the Command Verifier "TD 9.10 Bad Descriptor Test"
failed.
Setting this bit doesn't have any impact for SSP controller.

Fixes: 3d82904559f4 ("usb: cdnsp: cdns3 Add main part of Cadence USBSSP DRD Driver")
Cc: stable <stable@kernel.org>
Signed-off-by: Pawel Laszczak <pawell@cadence.com>
Acked-by: Peter Chen <peter.chen@kernel.org>
Link: https://lore.kernel.org/r/PH7PR07MB95382CCD50549DABAEFD6156DD7CA@PH7PR07MB9538.namprd07.prod.outlook.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/cdns3/cdnsp-debug.h  |  5 +++--
 drivers/usb/cdns3/cdnsp-ep0.c    | 18 +++++++++++++++---
 drivers/usb/cdns3/cdnsp-gadget.h |  6 ++++++
 drivers/usb/cdns3/cdnsp-ring.c   |  3 ++-
 4 files changed, 26 insertions(+), 6 deletions(-)

diff --git a/drivers/usb/cdns3/cdnsp-debug.h b/drivers/usb/cdns3/cdnsp-debug.h
index cd138acdcce1..86860686d836 100644
--- a/drivers/usb/cdns3/cdnsp-debug.h
+++ b/drivers/usb/cdns3/cdnsp-debug.h
@@ -327,12 +327,13 @@ static inline const char *cdnsp_decode_trb(char *str, size_t size, u32 field0,
 	case TRB_RESET_EP:
 	case TRB_HALT_ENDPOINT:
 		ret = scnprintf(str, size,
-				"%s: ep%d%s(%d) ctx %08x%08x slot %ld flags %c",
+				"%s: ep%d%s(%d) ctx %08x%08x slot %ld flags %c %c",
 				cdnsp_trb_type_string(type),
 				ep_num, ep_id % 2 ? "out" : "in",
 				TRB_TO_EP_INDEX(field3), field1, field0,
 				TRB_TO_SLOT_ID(field3),
-				field3 & TRB_CYCLE ? 'C' : 'c');
+				field3 & TRB_CYCLE ? 'C' : 'c',
+				field3 & TRB_ESP ? 'P' : 'p');
 		break;
 	case TRB_STOP_RING:
 		ret = scnprintf(str, size,
diff --git a/drivers/usb/cdns3/cdnsp-ep0.c b/drivers/usb/cdns3/cdnsp-ep0.c
index f317d3c84781..5cd9b898ce97 100644
--- a/drivers/usb/cdns3/cdnsp-ep0.c
+++ b/drivers/usb/cdns3/cdnsp-ep0.c
@@ -414,6 +414,7 @@ static int cdnsp_ep0_std_request(struct cdnsp_device *pdev,
 void cdnsp_setup_analyze(struct cdnsp_device *pdev)
 {
 	struct usb_ctrlrequest *ctrl = &pdev->setup;
+	struct cdnsp_ep *pep;
 	int ret = -EINVAL;
 	u16 len;
 
@@ -427,10 +428,21 @@ void cdnsp_setup_analyze(struct cdnsp_device *pdev)
 		goto out;
 	}
 
+	pep = &pdev->eps[0];
+
 	/* Restore the ep0 to Stopped/Running state. */
-	if (pdev->eps[0].ep_state & EP_HALTED) {
-		trace_cdnsp_ep0_halted("Restore to normal state");
-		cdnsp_halt_endpoint(pdev, &pdev->eps[0], 0);
+	if (pep->ep_state & EP_HALTED) {
+		if (GET_EP_CTX_STATE(pep->out_ctx) == EP_STATE_HALTED)
+			cdnsp_halt_endpoint(pdev, pep, 0);
+
+		/*
+		 * Halt Endpoint Command for SSP2 for ep0 preserve current
+		 * endpoint state and driver has to synchronize the
+		 * software endpoint state with endpoint output context
+		 * state.
+		 */
+		pep->ep_state &= ~EP_HALTED;
+		pep->ep_state |= EP_STOPPED;
 	}
 
 	/*
diff --git a/drivers/usb/cdns3/cdnsp-gadget.h b/drivers/usb/cdns3/cdnsp-gadget.h
index 2afa3e558f85..a91cca509db0 100644
--- a/drivers/usb/cdns3/cdnsp-gadget.h
+++ b/drivers/usb/cdns3/cdnsp-gadget.h
@@ -987,6 +987,12 @@ enum cdnsp_setup_dev {
 #define STREAM_ID_FOR_TRB(p)		((((p)) << 16) & GENMASK(31, 16))
 #define SCT_FOR_TRB(p)			(((p) << 1) & 0x7)
 
+/*
+ * Halt Endpoint Command TRB field.
+ * The ESP bit only exists in the SSP2 controller.
+ */
+#define TRB_ESP				BIT(9)
+
 /* Link TRB specific fields. */
 #define TRB_TC				BIT(1)
 
diff --git a/drivers/usb/cdns3/cdnsp-ring.c b/drivers/usb/cdns3/cdnsp-ring.c
index 757fdd918286..0758f171f73e 100644
--- a/drivers/usb/cdns3/cdnsp-ring.c
+++ b/drivers/usb/cdns3/cdnsp-ring.c
@@ -2485,7 +2485,8 @@ void cdnsp_queue_halt_endpoint(struct cdnsp_device *pdev, unsigned int ep_index)
 {
 	cdnsp_queue_command(pdev, 0, 0, 0, TRB_TYPE(TRB_HALT_ENDPOINT) |
 			    SLOT_ID_FOR_TRB(pdev->slot_id) |
-			    EP_ID_FOR_TRB(ep_index));
+			    EP_ID_FOR_TRB(ep_index) |
+			    (!ep_index ? TRB_ESP : 0));
 }
 
 void cdnsp_force_header_wakeup(struct cdnsp_device *pdev, int intf_num)

From af4db5a35a4ef7a68046883bfd12468007db38f1 Mon Sep 17 00:00:00 2001
From: RD Babiera <rdbabiera@google.com>
Date: Wed, 18 Jun 2025 22:49:42 +0000
Subject: [PATCH 0791/1334] usb: typec: altmodes/displayport: do not index
 invalid pin_assignments

A poorly implemented DisplayPort Alt Mode port partner can indicate
that its pin assignment capabilities are greater than the maximum
value, DP_PIN_ASSIGN_F. In this case, calls to pin_assignment_show
will cause a BRK exception due to an out of bounds array access.

Prevent for loop in pin_assignment_show from accessing
invalid values in pin_assignments by adding DP_PIN_ASSIGN_MAX
value in typec_dp.h and using i < DP_PIN_ASSIGN_MAX as a loop
condition.

Fixes: 0e3bb7d6894d ("usb: typec: Add driver for DisplayPort alternate mode")
Cc: stable <stable@kernel.org>
Signed-off-by: RD Babiera <rdbabiera@google.com>
Reviewed-by: Badhri Jagan Sridharan <badhri@google.com>
Reviewed-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Link: https://lore.kernel.org/r/20250618224943.3263103-2-rdbabiera@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/typec/altmodes/displayport.c | 2 +-
 include/linux/usb/typec_dp.h             | 1 +
 2 files changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/usb/typec/altmodes/displayport.c b/drivers/usb/typec/altmodes/displayport.c
index b09b58d7311d..773786129dfb 100644
--- a/drivers/usb/typec/altmodes/displayport.c
+++ b/drivers/usb/typec/altmodes/displayport.c
@@ -677,7 +677,7 @@ static ssize_t pin_assignment_show(struct device *dev,
 
 	assignments = get_current_pin_assignments(dp);
 
-	for (i = 0; assignments; assignments >>= 1, i++) {
+	for (i = 0; assignments && i < DP_PIN_ASSIGN_MAX; assignments >>= 1, i++) {
 		if (assignments & 1) {
 			if (i == cur)
 				len += sprintf(buf + len, "[%s] ",
diff --git a/include/linux/usb/typec_dp.h b/include/linux/usb/typec_dp.h
index f2da264d9c14..acb0ad03bdac 100644
--- a/include/linux/usb/typec_dp.h
+++ b/include/linux/usb/typec_dp.h
@@ -57,6 +57,7 @@ enum {
 	DP_PIN_ASSIGN_D,
 	DP_PIN_ASSIGN_E,
 	DP_PIN_ASSIGN_F, /* Not supported after v1.0b */
+	DP_PIN_ASSIGN_MAX,
 };
 
 /* DisplayPort alt mode specific commands */

From 099cf1fbb8afc3771f408109f62bdec66f85160e Mon Sep 17 00:00:00 2001
From: Andrei Kuchynski <akuchynski@chromium.org>
Date: Tue, 24 Jun 2025 13:32:46 +0000
Subject: [PATCH 0792/1334] usb: typec: displayport: Fix potential deadlock

The deadlock can occur due to a recursive lock acquisition of
`cros_typec_altmode_data::mutex`.
The call chain is as follows:
1. cros_typec_altmode_work() acquires the mutex
2. typec_altmode_vdm() -> dp_altmode_vdm() ->
3. typec_altmode_exit() -> cros_typec_altmode_exit()
4. cros_typec_altmode_exit() attempts to acquire the mutex again

To prevent this, defer the `typec_altmode_exit()` call by scheduling
it rather than calling it directly from within the mutex-protected
context.

Cc: stable <stable@kernel.org>
Fixes: b4b38ffb38c9 ("usb: typec: displayport: Receive DP Status Update NAK request exit dp altmode")
Signed-off-by: Andrei Kuchynski <akuchynski@chromium.org>
Reviewed-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Link: https://lore.kernel.org/r/20250624133246.3936737-1-akuchynski@chromium.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/typec/altmodes/displayport.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/usb/typec/altmodes/displayport.c b/drivers/usb/typec/altmodes/displayport.c
index 773786129dfb..d8b906ec4d1c 100644
--- a/drivers/usb/typec/altmodes/displayport.c
+++ b/drivers/usb/typec/altmodes/displayport.c
@@ -394,8 +394,7 @@ static int dp_altmode_vdm(struct typec_altmode *alt,
 	case CMDT_RSP_NAK:
 		switch (cmd) {
 		case DP_CMD_STATUS_UPDATE:
-			if (typec_altmode_exit(alt))
-				dev_err(&dp->alt->dev, "Exit Mode Failed!\n");
+			dp->state = DP_STATE_EXIT;
 			break;
 		case DP_CMD_CONFIGURE:
 			dp->data.conf = 0;

From 6c038b58a2dc5a008c7e7a1297f5aaa4deaaaa7e Mon Sep 17 00:00:00 2001
From: Tamura Dai <kirinode0@gmail.com>
Date: Mon, 16 Jun 2025 08:55:48 +0900
Subject: [PATCH 0793/1334] ASoC: SOF: Intel: hda: Use devm_kstrdup() to avoid
 memleak.

sof_pdata->tplg_filename can have address allocated by kstrdup()
and can be overwritten. Memory leak was detected with kmemleak:

unreferenced object 0xffff88812391ff60 (size 16):
  comm "kworker/4:1", pid 161, jiffies 4294802931
  hex dump (first 16 bytes):
    73 6f 66 2d 68 64 61 2d 67 65 6e 65 72 69 63 00  sof-hda-generic.
  backtrace (crc 4bf1675c):
    __kmalloc_node_track_caller_noprof+0x49c/0x6b0
    kstrdup+0x46/0xc0
    hda_machine_select.cold+0x1de/0x12cf [snd_sof_intel_hda_generic]
    sof_init_environment+0x16f/0xb50 [snd_sof]
    sof_probe_continue+0x45/0x7c0 [snd_sof]
    sof_probe_work+0x1e/0x40 [snd_sof]
    process_one_work+0x894/0x14b0
    worker_thread+0x5e5/0xfb0
    kthread+0x39d/0x760
    ret_from_fork+0x31/0x70
    ret_from_fork_asm+0x1a/0x30

Signed-off-by: Tamura Dai <kirinode0@gmail.com>
Link: https://patch.msgid.link/20250615235548.8591-1-kirinode0@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/sof/intel/hda.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/sound/soc/sof/intel/hda.c b/sound/soc/sof/intel/hda.c
index bdfe388da198..3b47191ea7a5 100644
--- a/sound/soc/sof/intel/hda.c
+++ b/sound/soc/sof/intel/hda.c
@@ -1257,11 +1257,11 @@ static int check_tplg_quirk_mask(struct snd_soc_acpi_mach *mach)
 	return 0;
 }
 
-static char *remove_file_ext(const char *tplg_filename)
+static char *remove_file_ext(struct device *dev, const char *tplg_filename)
 {
 	char *filename, *tmp;
 
-	filename = kstrdup(tplg_filename, GFP_KERNEL);
+	filename = devm_kstrdup(dev, tplg_filename, GFP_KERNEL);
 	if (!filename)
 		return NULL;
 
@@ -1345,7 +1345,7 @@ struct snd_soc_acpi_mach *hda_machine_select(struct snd_sof_dev *sdev)
 		 */
 		if (!sof_pdata->tplg_filename) {
 			/* remove file extension if it exists */
-			tplg_filename = remove_file_ext(mach->sof_tplg_filename);
+			tplg_filename = remove_file_ext(sdev->dev, mach->sof_tplg_filename);
 			if (!tplg_filename)
 				return NULL;
 

From b07f349d1864abe29436f45e3047da2bdd476462 Mon Sep 17 00:00:00 2001
From: Khairul Anuar Romli <khairul.anuar.romli@altera.com>
Date: Mon, 16 Jun 2025 09:13:53 +0800
Subject: [PATCH 0794/1334] spi: spi-cadence-quadspi: Fix pm runtime unbalance

Having PM put sync in remove function is causing PM underflow during
remove operation. This is caused by the function, runtime_pm_get_sync,
not being called anywhere during the op. Ensure that calls to
pm_runtime_enable()/pm_runtime_disable() and
pm_runtime_get_sync()/pm_runtime_put_sync() match.

echo 108d2000.spi > /sys/bus/platform/drivers/cadence-qspi/unbind
[   49.644256] Deleting MTD partitions on "108d2000.spi.0":
[   49.649575] Deleting u-boot MTD partition
[   49.684087] Deleting root MTD partition
[   49.724188] cadence-qspi 108d2000.spi: Runtime PM usage count underflow!

Continuous bind/unbind will result in an "Unbalanced pm_runtime_enable" error.
Subsequent unbind attempts will return a "No such device" error, while bind
attempts will return a "Resource temporarily unavailable" error.

[   47.592434] cadence-qspi 108d2000.spi: Runtime PM usage count underflow!
[   49.592233] cadence-qspi 108d2000.spi: detected FIFO depth (1024) different from config (128)
[   53.232309] cadence-qspi 108d2000.spi: Runtime PM usage count underflow!
[   55.828550] cadence-qspi 108d2000.spi: detected FIFO depth (1024) different from config (128)
[   57.940627] cadence-qspi 108d2000.spi: Runtime PM usage count underflow!
[   59.912490] cadence-qspi 108d2000.spi: detected FIFO depth (1024) different from config (128)
[   61.876243] cadence-qspi 108d2000.spi: Runtime PM usage count underflow!
[   61.883000] platform 108d2000.spi: Unbalanced pm_runtime_enable!
[  532.012270] cadence-qspi 108d2000.spi: probe with driver cadence-qspi failed1

Also, change clk_disable_unprepare() to clk_disable() since continuous
bind and unbind operations will trigger a warning indicating that the clock is
already unprepared.

Fixes: 4892b374c9b7 ("mtd: spi-nor: cadence-quadspi: Add runtime PM support")
cc: stable@vger.kernel.org # 6.6+
Signed-off-by: Khairul Anuar Romli <khairul.anuar.romli@altera.com>
Reviewed-by: Matthew Gerlach <matthew.gerlach@altera.com>
Link: https://patch.msgid.link/4e7a4b8aba300e629b45a04f90bddf665fbdb335.1749601877.git.khairul.anuar.romli@altera.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-cadence-quadspi.c | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/drivers/spi/spi-cadence-quadspi.c b/drivers/spi/spi-cadence-quadspi.c
index fe0f122f07b0..aa1932ba17cb 100644
--- a/drivers/spi/spi-cadence-quadspi.c
+++ b/drivers/spi/spi-cadence-quadspi.c
@@ -1958,10 +1958,10 @@ static int cqspi_probe(struct platform_device *pdev)
 			goto probe_setup_failed;
 	}
 
-	ret = devm_pm_runtime_enable(dev);
-	if (ret) {
-		if (cqspi->rx_chan)
-			dma_release_channel(cqspi->rx_chan);
+	pm_runtime_enable(dev);
+
+	if (cqspi->rx_chan) {
+		dma_release_channel(cqspi->rx_chan);
 		goto probe_setup_failed;
 	}
 
@@ -1981,6 +1981,7 @@ static int cqspi_probe(struct platform_device *pdev)
 	return 0;
 probe_setup_failed:
 	cqspi_controller_enable(cqspi, 0);
+	pm_runtime_disable(dev);
 probe_reset_failed:
 	if (cqspi->is_jh7110)
 		cqspi_jh7110_disable_clk(pdev, cqspi);
@@ -1999,7 +2000,8 @@ static void cqspi_remove(struct platform_device *pdev)
 	if (cqspi->rx_chan)
 		dma_release_channel(cqspi->rx_chan);
 
-	clk_disable_unprepare(cqspi->clk);
+	if (pm_runtime_get_sync(&pdev->dev) >= 0)
+		clk_disable(cqspi->clk);
 
 	if (cqspi->is_jh7110)
 		cqspi_jh7110_disable_clk(pdev, cqspi);

From 62207293479e6c03ef498a70f2914c51f4d31d2c Mon Sep 17 00:00:00 2001
From: Haoxiang Li <haoxiang_li2024@163.com>
Date: Fri, 16 May 2025 15:16:55 +0300
Subject: [PATCH 0795/1334] drm/xe/display: Add check for
 alloc_ordered_workqueue()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add check for the return value of alloc_ordered_workqueue()
in xe_display_create() to catch potential exception.

Fixes: 44e694958b95 ("drm/xe/display: Implement display support")
Cc: stable@vger.kernel.org
Signed-off-by: Haoxiang Li <haoxiang_li2024@163.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://lore.kernel.org/r/4ee1b0e5d1626ce1dde2e82af05c2edaed50c3aa.1747397638.git.jani.nikula@intel.com
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
(cherry picked from commit 5b62d63395d5b7d4094e7cd380bccae4b25415cb)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
---
 drivers/gpu/drm/xe/display/xe_display.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/gpu/drm/xe/display/xe_display.c b/drivers/gpu/drm/xe/display/xe_display.c
index 68f064f33d4b..9f4ade25787a 100644
--- a/drivers/gpu/drm/xe/display/xe_display.c
+++ b/drivers/gpu/drm/xe/display/xe_display.c
@@ -104,6 +104,8 @@ int xe_display_create(struct xe_device *xe)
 	spin_lock_init(&xe->display.fb_tracking.lock);
 
 	xe->display.hotplug.dp_wq = alloc_ordered_workqueue("xe-dp", 0);
+	if (!xe->display.hotplug.dp_wq)
+		return -ENOMEM;
 
 	return drmm_add_action_or_reset(&xe->drm, display_destroy, NULL);
 }

From 9127a69c7193ad47047ff968a2de9161d5c93d37 Mon Sep 17 00:00:00 2001
From: Karthik Poosa <karthik.poosa@intel.com>
Date: Tue, 17 Jun 2025 17:30:30 +0530
Subject: [PATCH 0796/1334] drm/xe/hwmon: Fix xe_hwmon_power_max_write
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Prevent other bits of mailbox power limit from being overwritten with 0.
This issue was due to a missing read and modify of current power limit,
before setting a requested mailbox power limit, which is added in this
patch.

v2:
 - Improve commit message. (Anshuman)

v3:
 - Rebase.
 - Rephrase commit message. (Riana)
 - Add read-modify-write variant of xe_hwmon_pcode_write_power_limit()
   i.e. xe_hwmon_pcode_rmw_power_limit(). (Badal)
 - Use xe_hwmon_pcode_rmw_power_limit() to set mailbox power limits.
 - Remove xe_hwmon_pcode_write_power_limit() as all mailbox power limits
   writes use xe_hwmon_pcode_rmw_power_limit() only.

v4:
 - Use PWR_LIM in place of (PWR_LIM_EN | PWR_LIM_VAL) wherever
   applicable. (Riana)

Fixes: 25a2aa779fc3 ("drm/xe/hwmon: Add support to manage power limits though mailbox")
Reviewed-by: Riana Tauro <riana.tauro@intel.com>
Signed-off-by: Karthik Poosa <karthik.poosa@intel.com>
Reviewed-by: Badal Nilawar <badal.nilawar@intel.com>
Link: https://lore.kernel.org/r/20250617120030.612819-1-karthik.poosa@intel.com
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
(cherry picked from commit 8aa7306631f088881759398972d503757cf0c901)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
---
 drivers/gpu/drm/xe/regs/xe_mchbar_regs.h |  1 +
 drivers/gpu/drm/xe/xe_hwmon.c            | 34 +++++++++++-------------
 2 files changed, 16 insertions(+), 19 deletions(-)

diff --git a/drivers/gpu/drm/xe/regs/xe_mchbar_regs.h b/drivers/gpu/drm/xe/regs/xe_mchbar_regs.h
index 5394a1373a6b..ef2bf984723f 100644
--- a/drivers/gpu/drm/xe/regs/xe_mchbar_regs.h
+++ b/drivers/gpu/drm/xe/regs/xe_mchbar_regs.h
@@ -40,6 +40,7 @@
 #define PCU_CR_PACKAGE_RAPL_LIMIT		XE_REG(MCHBAR_MIRROR_BASE_SNB + 0x59a0)
 #define   PWR_LIM_VAL				REG_GENMASK(14, 0)
 #define   PWR_LIM_EN				REG_BIT(15)
+#define   PWR_LIM				REG_GENMASK(15, 0)
 #define   PWR_LIM_TIME				REG_GENMASK(23, 17)
 #define   PWR_LIM_TIME_X			REG_GENMASK(23, 22)
 #define   PWR_LIM_TIME_Y			REG_GENMASK(21, 17)
diff --git a/drivers/gpu/drm/xe/xe_hwmon.c b/drivers/gpu/drm/xe/xe_hwmon.c
index 74f31639b37f..f008e8049700 100644
--- a/drivers/gpu/drm/xe/xe_hwmon.c
+++ b/drivers/gpu/drm/xe/xe_hwmon.c
@@ -159,8 +159,8 @@ static int xe_hwmon_pcode_read_power_limit(const struct xe_hwmon *hwmon, u32 att
 	return ret;
 }
 
-static int xe_hwmon_pcode_write_power_limit(const struct xe_hwmon *hwmon, u32 attr, u8 channel,
-					    u32 uval)
+static int xe_hwmon_pcode_rmw_power_limit(const struct xe_hwmon *hwmon, u32 attr, u8 channel,
+					  u32 clr, u32 set)
 {
 	struct xe_tile *root_tile = xe_device_get_root_tile(hwmon->xe);
 	u32 val0, val1;
@@ -179,7 +179,7 @@ static int xe_hwmon_pcode_write_power_limit(const struct xe_hwmon *hwmon, u32 at
 			channel, val0, val1, ret);
 
 	if (attr == PL1_HWMON_ATTR)
-		val0 = uval;
+		val0 = (val0 & ~clr) | set;
 	else
 		return -EIO;
 
@@ -339,7 +339,7 @@ static int xe_hwmon_power_max_write(struct xe_hwmon *hwmon, u32 attr, int channe
 		if (hwmon->xe->info.has_mbx_power_limits) {
 			drm_dbg(&hwmon->xe->drm, "disabling %s on channel %d\n",
 				PWR_ATTR_TO_STR(attr), channel);
-			xe_hwmon_pcode_write_power_limit(hwmon, attr, channel, 0);
+			xe_hwmon_pcode_rmw_power_limit(hwmon, attr, channel, PWR_LIM_EN, 0);
 			xe_hwmon_pcode_read_power_limit(hwmon, attr, channel, &reg_val);
 		} else {
 			reg_val = xe_mmio_rmw32(mmio, rapl_limit, PWR_LIM_EN, 0);
@@ -370,10 +370,9 @@ static int xe_hwmon_power_max_write(struct xe_hwmon *hwmon, u32 attr, int channe
 	}
 
 	if (hwmon->xe->info.has_mbx_power_limits)
-		ret = xe_hwmon_pcode_write_power_limit(hwmon, attr, channel, reg_val);
+		ret = xe_hwmon_pcode_rmw_power_limit(hwmon, attr, channel, PWR_LIM, reg_val);
 	else
-		reg_val = xe_mmio_rmw32(mmio, rapl_limit, PWR_LIM_EN | PWR_LIM_VAL,
-					reg_val);
+		reg_val = xe_mmio_rmw32(mmio, rapl_limit, PWR_LIM, reg_val);
 unlock:
 	mutex_unlock(&hwmon->hwmon_lock);
 	return ret;
@@ -563,14 +562,11 @@ xe_hwmon_power_max_interval_store(struct device *dev, struct device_attribute *a
 
 	mutex_lock(&hwmon->hwmon_lock);
 
-	if (hwmon->xe->info.has_mbx_power_limits) {
-		ret = xe_hwmon_pcode_read_power_limit(hwmon, power_attr, channel, (u32 *)&r);
-		r = (r & ~PWR_LIM_TIME) | rxy;
-		xe_hwmon_pcode_write_power_limit(hwmon, power_attr, channel, r);
-	} else {
+	if (hwmon->xe->info.has_mbx_power_limits)
+		xe_hwmon_pcode_rmw_power_limit(hwmon, power_attr, channel, PWR_LIM_TIME, rxy);
+	else
 		r = xe_mmio_rmw32(mmio, xe_hwmon_get_reg(hwmon, REG_PKG_RAPL_LIMIT, channel),
 				  PWR_LIM_TIME, rxy);
-	}
 
 	mutex_unlock(&hwmon->hwmon_lock);
 
@@ -1138,12 +1134,12 @@ xe_hwmon_get_preregistration_info(struct xe_hwmon *hwmon)
 		} else {
 			drm_info(&hwmon->xe->drm, "Using mailbox commands for power limits\n");
 			/* Write default limits to read from pcode from now on. */
-			xe_hwmon_pcode_write_power_limit(hwmon, PL1_HWMON_ATTR,
-							 CHANNEL_CARD,
-							 hwmon->pl1_on_boot[CHANNEL_CARD]);
-			xe_hwmon_pcode_write_power_limit(hwmon, PL1_HWMON_ATTR,
-							 CHANNEL_PKG,
-							 hwmon->pl1_on_boot[CHANNEL_PKG]);
+			xe_hwmon_pcode_rmw_power_limit(hwmon, PL1_HWMON_ATTR,
+						       CHANNEL_CARD, PWR_LIM | PWR_LIM_TIME,
+						       hwmon->pl1_on_boot[CHANNEL_CARD]);
+			xe_hwmon_pcode_rmw_power_limit(hwmon, PL1_HWMON_ATTR,
+						       CHANNEL_PKG, PWR_LIM | PWR_LIM_TIME,
+						       hwmon->pl1_on_boot[CHANNEL_PKG]);
 			hwmon->scl_shift_power = PWR_UNIT;
 			hwmon->scl_shift_energy = ENERGY_UNIT;
 			hwmon->scl_shift_time = TIME_UNIT;

From 818625570558cd91082c9bafd6f2b59b73241a69 Mon Sep 17 00:00:00 2001
From: Nicolin Chen <nicolinc@nvidia.com>
Date: Tue, 24 Jun 2025 11:00:45 -0700
Subject: [PATCH 0797/1334] iommufd/selftest: Fix iommufd_dirty_tracking with
 large hugepage sizes

The hugepage test cases of iommufd_dirty_tracking have the 64MB and 128MB
coverages. Both of them are smaller than the default hugepage size 512MB,
when CONFIG_PAGE_SIZE_64KB=y. However, these test cases have a variant of
using huge pages, which would mmap(MAP_HUGETLB) using these smaller sizes
than the system hugepag size. This results in the kernel aligning up the
smaller size to 512MB. If a memory was located between the upper 64/128MB
size boundary and the hugepage 512MB boundary, it would get wiped out:
https://lore.kernel.org/all/aEoUhPYIAizTLADq@nvidia.com/

Given that this aligning up behavior is well documented, we have no choice
but to allocate a hugepage aligned size to avoid this unintended wipe out.
Instead of relying on the kernel's internal force alignment, pass the same
size to posix_memalign() and map().

Also, fix the FIXTURE_TEARDOWN() misusing munmap() to free the memory from
posix_memalign(), as munmap() doesn't destroy the allocator meta data. So,
call free() instead.

Fixes: a9af47e382a4 ("iommufd/selftest: Test IOMMU_HWPT_GET_DIRTY_BITMAP")
Link: https://patch.msgid.link/r/1ea8609ae6d523fdd4d8efb179ddee79c8582cb6.1750787928.git.nicolinc@nvidia.com
Cc: stable@vger.kernel.org
Suggested-by: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Nicolin Chen <nicolinc@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 tools/testing/selftests/iommu/iommufd.c | 30 +++++++++++++++++--------
 1 file changed, 21 insertions(+), 9 deletions(-)

diff --git a/tools/testing/selftests/iommu/iommufd.c b/tools/testing/selftests/iommu/iommufd.c
index 1a8e85afe9aa..e7eb11a94034 100644
--- a/tools/testing/selftests/iommu/iommufd.c
+++ b/tools/testing/selftests/iommu/iommufd.c
@@ -2008,6 +2008,7 @@ FIXTURE_VARIANT(iommufd_dirty_tracking)
 
 FIXTURE_SETUP(iommufd_dirty_tracking)
 {
+	size_t mmap_buffer_size;
 	unsigned long size;
 	int mmap_flags;
 	void *vrc;
@@ -2022,22 +2023,33 @@ FIXTURE_SETUP(iommufd_dirty_tracking)
 	self->fd = open("/dev/iommu", O_RDWR);
 	ASSERT_NE(-1, self->fd);
 
-	rc = posix_memalign(&self->buffer, HUGEPAGE_SIZE, variant->buffer_size);
-	if (rc || !self->buffer) {
-		SKIP(return, "Skipping buffer_size=%lu due to errno=%d",
-			   variant->buffer_size, rc);
-	}
-
 	mmap_flags = MAP_SHARED | MAP_ANONYMOUS | MAP_FIXED;
+	mmap_buffer_size = variant->buffer_size;
 	if (variant->hugepages) {
 		/*
 		 * MAP_POPULATE will cause the kernel to fail mmap if THPs are
 		 * not available.
 		 */
 		mmap_flags |= MAP_HUGETLB | MAP_POPULATE;
+
+		/*
+		 * Allocation must be aligned to the HUGEPAGE_SIZE, because the
+		 * following mmap() will automatically align the length to be a
+		 * multiple of the underlying huge page size. Failing to do the
+		 * same at this allocation will result in a memory overwrite by
+		 * the mmap().
+		 */
+		if (mmap_buffer_size < HUGEPAGE_SIZE)
+			mmap_buffer_size = HUGEPAGE_SIZE;
+	}
+
+	rc = posix_memalign(&self->buffer, HUGEPAGE_SIZE, mmap_buffer_size);
+	if (rc || !self->buffer) {
+		SKIP(return, "Skipping buffer_size=%lu due to errno=%d",
+			   mmap_buffer_size, rc);
 	}
 	assert((uintptr_t)self->buffer % HUGEPAGE_SIZE == 0);
-	vrc = mmap(self->buffer, variant->buffer_size, PROT_READ | PROT_WRITE,
+	vrc = mmap(self->buffer, mmap_buffer_size, PROT_READ | PROT_WRITE,
 		   mmap_flags, -1, 0);
 	assert(vrc == self->buffer);
 
@@ -2066,8 +2078,8 @@ FIXTURE_SETUP(iommufd_dirty_tracking)
 
 FIXTURE_TEARDOWN(iommufd_dirty_tracking)
 {
-	munmap(self->buffer, variant->buffer_size);
-	munmap(self->bitmap, DIV_ROUND_UP(self->bitmap_size, BITS_PER_BYTE));
+	free(self->buffer);
+	free(self->bitmap);
 	teardown_iommufd(self->fd, _metadata);
 }
 

From 4b75e3babb85238912f50bbe0647bae08242a9b6 Mon Sep 17 00:00:00 2001
From: Nicolin Chen <nicolinc@nvidia.com>
Date: Tue, 24 Jun 2025 11:00:46 -0700
Subject: [PATCH 0798/1334] iommufd/selftest: Add missing close(mfd) in
 memfd_mmap()

Do not forget to close mfd in the error paths, since none of the callers
would close it when ASSERT_NE(MAP_FAILED, buf) fails.

Fixes: 0bcceb1f51c7 ("iommufd: Selftest coverage for IOMMU_IOAS_MAP_FILE")
Link: https://patch.msgid.link/r/a363a69dbf453d4bc1bde276f3b16778620488e1.1750787928.git.nicolinc@nvidia.com
Cc: stable@vger.kernel.org
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Nicolin Chen <nicolinc@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 tools/testing/selftests/iommu/iommufd_utils.h | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/iommu/iommufd_utils.h b/tools/testing/selftests/iommu/iommufd_utils.h
index 72f6636e5d90..6e967b58acfd 100644
--- a/tools/testing/selftests/iommu/iommufd_utils.h
+++ b/tools/testing/selftests/iommu/iommufd_utils.h
@@ -60,13 +60,18 @@ static inline void *memfd_mmap(size_t length, int prot, int flags, int *mfd_p)
 {
 	int mfd_flags = (flags & MAP_HUGETLB) ? MFD_HUGETLB : 0;
 	int mfd = memfd_create("buffer", mfd_flags);
+	void *buf = MAP_FAILED;
 
 	if (mfd <= 0)
 		return MAP_FAILED;
 	if (ftruncate(mfd, length))
-		return MAP_FAILED;
+		goto out;
 	*mfd_p = mfd;
-	return mmap(0, length, prot, flags, mfd, 0);
+	buf = mmap(0, length, prot, flags, mfd, 0);
+out:
+	if (buf == MAP_FAILED)
+		close(mfd);
+	return buf;
 }
 
 /*

From a9bf67ee170514b17541038c60bb94cb2cf5732f Mon Sep 17 00:00:00 2001
From: Nicolin Chen <nicolinc@nvidia.com>
Date: Tue, 24 Jun 2025 11:00:47 -0700
Subject: [PATCH 0799/1334] iommufd/selftest: Add asserts testing global mfd

The mfd and mfd_buffer will be used in the tests directly without an extra
check. Test them in setup_sizes() to ensure they are safe to use.

Fixes: 0bcceb1f51c7 ("iommufd: Selftest coverage for IOMMU_IOAS_MAP_FILE")
Link: https://patch.msgid.link/r/94bdc11d2b6d5db337b1361c5e5fce0ed494bb40.1750787928.git.nicolinc@nvidia.com
Cc: stable@vger.kernel.org
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Nicolin Chen <nicolinc@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 tools/testing/selftests/iommu/iommufd.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/tools/testing/selftests/iommu/iommufd.c b/tools/testing/selftests/iommu/iommufd.c
index e7eb11a94034..e61218c0537f 100644
--- a/tools/testing/selftests/iommu/iommufd.c
+++ b/tools/testing/selftests/iommu/iommufd.c
@@ -54,6 +54,8 @@ static __attribute__((constructor)) void setup_sizes(void)
 
 	mfd_buffer = memfd_mmap(BUFFER_SIZE, PROT_READ | PROT_WRITE, MAP_SHARED,
 				&mfd);
+	assert(mfd_buffer != MAP_FAILED);
+	assert(mfd > 0);
 }
 
 FIXTURE(iommufd)

From 9a96876e3c6578031fa5dc5dde7759d383b2fb75 Mon Sep 17 00:00:00 2001
From: Nicolin Chen <nicolinc@nvidia.com>
Date: Tue, 24 Jun 2025 11:00:48 -0700
Subject: [PATCH 0800/1334] iommufd/selftest: Fix build warnings due to
 uninitialized mfd
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Commit 869c788909b9 ("selftests: harness: Stop using setjmp()/longjmp()")
changed the harness structure. For some unknown reason, two build warnings
occur to the iommufd selftest:

iommufd.c: In function ‘wrapper_iommufd_mock_domain_all_aligns’:
iommufd.c:1807:17: warning: ‘mfd’ may be used uninitialized in this function
 1807 |                 close(mfd);
      |                 ^~~~~~~~~~
iommufd.c:1767:13: note: ‘mfd’ was declared here
 1767 |         int mfd;
      |             ^~~
iommufd.c: In function ‘wrapper_iommufd_mock_domain_all_aligns_copy’:
iommufd.c:1870:17: warning: ‘mfd’ may be used uninitialized in this function
 1870 |                 close(mfd);
      |                 ^~~~~~~~~~
iommufd.c:1819:13: note: ‘mfd’ was declared here
 1819 |         int mfd;
      |             ^~~

All the mfd have been used in the variant->file path only, so it's likely
a false alarm.

FWIW, the commit mentioned above does not cause this, yet it might affect
gcc in a certain way that resulted in the warnings. It is also found that
ading a dummy setjmp (which doesn't make sense) could mute the warnings:
https://lore.kernel.org/all/aEi8DV+ReF3v3Rlf@nvidia.com/

The job of this selftest is to catch kernel bug, while such warnings will
unlikely disrupt its role. Mute the warning by force initializing the mfd
and add an ASSERT_GT().

Link: https://patch.msgid.link/r/6951d85d5cd34cbf22abab7714542654e63ecc44.1750787928.git.nicolinc@nvidia.com
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Nicolin Chen <nicolinc@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 tools/testing/selftests/iommu/iommufd.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/iommu/iommufd.c b/tools/testing/selftests/iommu/iommufd.c
index e61218c0537f..1926ef6b40ab 100644
--- a/tools/testing/selftests/iommu/iommufd.c
+++ b/tools/testing/selftests/iommu/iommufd.c
@@ -1748,13 +1748,15 @@ TEST_F(iommufd_mock_domain, all_aligns)
 	unsigned int end;
 	uint8_t *buf;
 	int prot = PROT_READ | PROT_WRITE;
-	int mfd;
+	int mfd = -1;
 
 	if (variant->file)
 		buf = memfd_mmap(buf_size, prot, MAP_SHARED, &mfd);
 	else
 		buf = mmap(0, buf_size, prot, self->mmap_flags, -1, 0);
 	ASSERT_NE(MAP_FAILED, buf);
+	if (variant->file)
+		ASSERT_GT(mfd, 0);
 	check_refs(buf, buf_size, 0);
 
 	/*
@@ -1800,13 +1802,15 @@ TEST_F(iommufd_mock_domain, all_aligns_copy)
 	unsigned int end;
 	uint8_t *buf;
 	int prot = PROT_READ | PROT_WRITE;
-	int mfd;
+	int mfd = -1;
 
 	if (variant->file)
 		buf = memfd_mmap(buf_size, prot, MAP_SHARED, &mfd);
 	else
 		buf = mmap(0, buf_size, prot, self->mmap_flags, -1, 0);
 	ASSERT_NE(MAP_FAILED, buf);
+	if (variant->file)
+		ASSERT_GT(mfd, 0);
 	check_refs(buf, buf_size, 0);
 
 	/*

From ecf371f8b02d5e31b9aa1da7f159f1b2107bdb01 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Mon, 2 Jun 2025 15:44:58 -0700
Subject: [PATCH 0801/1334] KVM: SVM: Reject SEV{-ES} intra host migration if
 vCPU creation is in-flight

Reject migration of SEV{-ES} state if either the source or destination VM
is actively creating a vCPU, i.e. if kvm_vm_ioctl_create_vcpu() is in the
section between incrementing created_vcpus and online_vcpus.  The bulk of
vCPU creation runs _outside_ of kvm->lock to allow creating multiple vCPUs
in parallel, and so sev_info.es_active can get toggled from false=>true in
the destination VM after (or during) svm_vcpu_create(), resulting in an
SEV{-ES} VM effectively having a non-SEV{-ES} vCPU.

The issue manifests most visibly as a crash when trying to free a vCPU's
NULL VMSA page in an SEV-ES VM, but any number of things can go wrong.

  BUG: unable to handle page fault for address: ffffebde00000000
  #PF: supervisor read access in kernel mode
  #PF: error_code(0x0000) - not-present page
  PGD 0 P4D 0
  Oops: Oops: 0000 [#1] SMP KASAN NOPTI
  CPU: 227 UID: 0 PID: 64063 Comm: syz.5.60023 Tainted: G     U     O        6.15.0-smp-DEV #2 NONE
  Tainted: [U]=USER, [O]=OOT_MODULE
  Hardware name: Google, Inc. Arcadia_IT_80/Arcadia_IT_80, BIOS 12.52.0-0 10/28/2024
  RIP: 0010:constant_test_bit arch/x86/include/asm/bitops.h:206 [inline]
  RIP: 0010:arch_test_bit arch/x86/include/asm/bitops.h:238 [inline]
  RIP: 0010:_test_bit include/asm-generic/bitops/instrumented-non-atomic.h:142 [inline]
  RIP: 0010:PageHead include/linux/page-flags.h:866 [inline]
  RIP: 0010:___free_pages+0x3e/0x120 mm/page_alloc.c:5067
  Code: <49> f7 06 40 00 00 00 75 05 45 31 ff eb 0c 66 90 4c 89 f0 4c 39 f0
  RSP: 0018:ffff8984551978d0 EFLAGS: 00010246
  RAX: 0000777f80000001 RBX: 0000000000000000 RCX: ffffffff918aeb98
  RDX: 0000000000000000 RSI: 0000000000000008 RDI: ffffebde00000000
  RBP: 0000000000000000 R08: ffffebde00000007 R09: 1ffffd7bc0000000
  R10: dffffc0000000000 R11: fffff97bc0000001 R12: dffffc0000000000
  R13: ffff8983e19751a8 R14: ffffebde00000000 R15: 1ffffd7bc0000000
  FS:  0000000000000000(0000) GS:ffff89ee661d3000(0000) knlGS:0000000000000000
  CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
  CR2: ffffebde00000000 CR3: 000000793ceaa000 CR4: 0000000000350ef0
  DR0: 0000000000000000 DR1: 0000000000000b5f DR2: 0000000000000000
  DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400
  Call Trace:
   <TASK>
   sev_free_vcpu+0x413/0x630 arch/x86/kvm/svm/sev.c:3169
   svm_vcpu_free+0x13a/0x2a0 arch/x86/kvm/svm/svm.c:1515
   kvm_arch_vcpu_destroy+0x6a/0x1d0 arch/x86/kvm/x86.c:12396
   kvm_vcpu_destroy virt/kvm/kvm_main.c:470 [inline]
   kvm_destroy_vcpus+0xd1/0x300 virt/kvm/kvm_main.c:490
   kvm_arch_destroy_vm+0x636/0x820 arch/x86/kvm/x86.c:12895
   kvm_put_kvm+0xb8e/0xfb0 virt/kvm/kvm_main.c:1310
   kvm_vm_release+0x48/0x60 virt/kvm/kvm_main.c:1369
   __fput+0x3e4/0x9e0 fs/file_table.c:465
   task_work_run+0x1a9/0x220 kernel/task_work.c:227
   exit_task_work include/linux/task_work.h:40 [inline]
   do_exit+0x7f0/0x25b0 kernel/exit.c:953
   do_group_exit+0x203/0x2d0 kernel/exit.c:1102
   get_signal+0x1357/0x1480 kernel/signal.c:3034
   arch_do_signal_or_restart+0x40/0x690 arch/x86/kernel/signal.c:337
   exit_to_user_mode_loop kernel/entry/common.c:111 [inline]
   exit_to_user_mode_prepare include/linux/entry-common.h:329 [inline]
   __syscall_exit_to_user_mode_work kernel/entry/common.c:207 [inline]
   syscall_exit_to_user_mode+0x67/0xb0 kernel/entry/common.c:218
   do_syscall_64+0x7c/0x150 arch/x86/entry/syscall_64.c:100
   entry_SYSCALL_64_after_hwframe+0x76/0x7e
  RIP: 0033:0x7f87a898e969
   </TASK>
  Modules linked in: gq(O)
  gsmi: Log Shutdown Reason 0x03
  CR2: ffffebde00000000
  ---[ end trace 0000000000000000 ]---

Deliberately don't check for a NULL VMSA when freeing the vCPU, as crashing
the host is likely desirable due to the VMSA being consumed by hardware.
E.g. if KVM manages to allow VMRUN on the vCPU, hardware may read/write a
bogus VMSA page.  Accessing PFN 0 is "fine"-ish now that it's sequestered
away thanks to L1TF, but panicking in this scenario is preferable to
potentially running with corrupted state.

Reported-by: Alexander Potapenko <glider@google.com>
Tested-by: Alexander Potapenko <glider@google.com>
Fixes: 0b020f5af092 ("KVM: SEV: Add support for SEV-ES intra host migration")
Fixes: b56639318bb2 ("KVM: SEV: Add support for SEV intra host migration")
Cc: stable@vger.kernel.org
Cc: James Houghton <jthoughton@google.com>
Cc: Peter Gonda <pgonda@google.com>
Reviewed-by: Liam Merwick <liam.merwick@oracle.com>
Tested-by: Liam Merwick <liam.merwick@oracle.com>
Reviewed-by: James Houghton <jthoughton@google.com>
Link: https://lore.kernel.org/r/20250602224459.41505-2-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/svm/sev.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 459c3b791fd4..65d1597c3fed 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -1971,6 +1971,10 @@ static int sev_check_source_vcpus(struct kvm *dst, struct kvm *src)
 	struct kvm_vcpu *src_vcpu;
 	unsigned long i;
 
+	if (src->created_vcpus != atomic_read(&src->online_vcpus) ||
+	    dst->created_vcpus != atomic_read(&dst->online_vcpus))
+		return -EBUSY;
+
 	if (!sev_es_guest(src))
 		return 0;
 

From 48f15f624189762e7ff2d95bcbb68e21c2d56077 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Mon, 2 Jun 2025 15:44:59 -0700
Subject: [PATCH 0802/1334] KVM: SVM: Initialize vmsa_pa in VMCB to
 INVALID_PAGE if VMSA page is NULL

When creating an SEV-ES vCPU for intra-host migration, set its vmsa_pa to
INVALID_PAGE to harden against doing VMRUN with a bogus VMSA (KVM checks
for a valid VMSA page in pre_sev_run()).

Cc: Tom Lendacky <thomas.lendacky@amd.com>
Reviewed-by: Liam Merwick <liam.merwick@oracle.com>
Tested-by: Liam Merwick <liam.merwick@oracle.com>
Link: https://lore.kernel.org/r/20250602224459.41505-3-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/svm/sev.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 65d1597c3fed..b201f77fcd49 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -4449,8 +4449,12 @@ static void sev_es_init_vmcb(struct vcpu_svm *svm)
 	 * the VMSA will be NULL if this vCPU is the destination for intrahost
 	 * migration, and will be copied later.
 	 */
-	if (svm->sev_es.vmsa && !svm->sev_es.snp_has_guest_vmsa)
-		svm->vmcb->control.vmsa_pa = __pa(svm->sev_es.vmsa);
+	if (!svm->sev_es.snp_has_guest_vmsa) {
+		if (svm->sev_es.vmsa)
+			svm->vmcb->control.vmsa_pa = __pa(svm->sev_es.vmsa);
+		else
+			svm->vmcb->control.vmsa_pa = INVALID_PAGE;
+	}
 
 	if (cpu_feature_enabled(X86_FEATURE_ALLOWED_SEV_FEATURES))
 		svm->vmcb->control.allowed_sev_features = sev->vmsa_features |

From 0b6f4a5f0878c410677a8201c48127fda0bfd843 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 13 Jun 2025 12:39:22 -0700
Subject: [PATCH 0803/1334] KVM: x86/hyper-v: Use preallocated per-vCPU buffer
 for de-sparsified vCPU masks

Use a preallocated per-vCPU bitmap for tracking the unpacked set of vCPUs
being targeted for Hyper-V's paravirt TLB flushing.  If KVM_MAX_NR_VCPUS
is set to 4096 (which is allowed even for MAXSMP=n builds), putting the
vCPU mask on-stack pushes kvm_hv_flush_tlb() past the default FRAME_WARN
limit.

  arch/x86/kvm/hyperv.c:2001:12: error: stack frame size (1288) exceeds limit (1024)
                                 in 'kvm_hv_flush_tlb' [-Werror,-Wframe-larger-than]
  2001 | static u64 kvm_hv_flush_tlb(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc)
       |            ^
  1 error generated.

Note, sparse_banks was given the same treatment by commit 7d5e88d301f8
("KVM: x86: hyper-v: Use preallocated buffer in 'struct kvm_vcpu_hv'
instead of on-stack 'sparse_banks'"), for the exact same reason.

Reported-by: Abinash Lalotra <abinashsinghlalotra@gmail.com>
Closes: https://lore.kernel.org/all/20250613111023.786265-1-abinashsinghlalotra@gmail.com
Link: https://lore.kernel.org/all/aEylI-O8kFnFHrOH@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/include/asm/kvm_host.h | 7 ++++++-
 arch/x86/kvm/hyperv.c           | 2 +-
 2 files changed, 7 insertions(+), 2 deletions(-)

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index b4a391929cdb..ee43615d96d8 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -700,8 +700,13 @@ struct kvm_vcpu_hv {
 
 	struct kvm_vcpu_hv_tlb_flush_fifo tlb_flush_fifo[HV_NR_TLB_FLUSH_FIFOS];
 
-	/* Preallocated buffer for handling hypercalls passing sparse vCPU set */
+	/*
+	 * Preallocated buffers for handling hypercalls that pass sparse vCPU
+	 * sets (for high vCPU counts, they're too large to comfortably fit on
+	 * the stack).
+	 */
 	u64 sparse_banks[HV_MAX_SPARSE_VCPU_BANKS];
+	DECLARE_BITMAP(vcpu_mask, KVM_MAX_VCPUS);
 
 	struct hv_vp_assist_page vp_assist_page;
 
diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index 24f0318c50d7..75221a11e15e 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -2001,11 +2001,11 @@ out_flush_all:
 static u64 kvm_hv_flush_tlb(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc)
 {
 	struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu);
+	unsigned long *vcpu_mask = hv_vcpu->vcpu_mask;
 	u64 *sparse_banks = hv_vcpu->sparse_banks;
 	struct kvm *kvm = vcpu->kvm;
 	struct hv_tlb_flush_ex flush_ex;
 	struct hv_tlb_flush flush;
-	DECLARE_BITMAP(vcpu_mask, KVM_MAX_VCPUS);
 	struct kvm_vcpu_hv_tlb_flush_fifo *tlb_flush_fifo;
 	/*
 	 * Normally, there can be no more than 'KVM_HV_TLB_FLUSH_FIFO_SIZE'

From a7f4dff21fd744d08fa956c243d2b1795f23cbf7 Mon Sep 17 00:00:00 2001
From: David Woodhouse <dwmw@amazon.co.uk>
Date: Thu, 8 May 2025 13:30:12 -0700
Subject: [PATCH 0804/1334] KVM: x86/xen: Allow 'out of range' event channel
 ports in IRQ routing table.

To avoid imposing an ordering constraint on userspace, allow 'invalid'
event channel targets to be configured in the IRQ routing table.

This is the same as accepting interrupts targeted at vCPUs which don't
exist yet, which is already the case for both Xen event channels *and*
for MSIs (which don't do any filtering of permitted APIC ID targets at
all).

If userspace actually *triggers* an IRQ with an invalid target, that
will fail cleanly, as kvm_xen_set_evtchn_fast() also does the same range
check.

If KVM enforced that the IRQ target must be valid at the time it is
*configured*, that would force userspace to create all vCPUs and do
various other parts of setup (in this case, setting the Xen long_mode)
before restoring the IRQ table.

Cc: stable@vger.kernel.org
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Reviewed-by: Paul Durrant <paul@xen.org>
Link: https://lore.kernel.org/r/e489252745ac4b53f1f7f50570b03fb416aa2065.camel@infradead.org
[sean: massage comment]
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/xen.c | 15 +++++++++++++--
 1 file changed, 13 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c
index 9b029bb29a16..5fa2cca43653 100644
--- a/arch/x86/kvm/xen.c
+++ b/arch/x86/kvm/xen.c
@@ -1971,8 +1971,19 @@ int kvm_xen_setup_evtchn(struct kvm *kvm,
 {
 	struct kvm_vcpu *vcpu;
 
-	if (ue->u.xen_evtchn.port >= max_evtchn_port(kvm))
-		return -EINVAL;
+	/*
+	 * Don't check for the port being within range of max_evtchn_port().
+	 * Userspace can configure what ever targets it likes; events just won't
+	 * be delivered if/while the target is invalid, just like userspace can
+	 * configure MSIs which target non-existent APICs.
+	 *
+	 * This allow on Live Migration and Live Update, the IRQ routing table
+	 * can be restored *independently* of other things like creating vCPUs,
+	 * without imposing an ordering dependency on userspace.  In this
+	 * particular case, the problematic ordering would be with setting the
+	 * Xen 'long mode' flag, which changes max_evtchn_port() to allow 4096
+	 * instead of 1024 event channels.
+	 */
 
 	/* We only support 2 level event channels for now */
 	if (ue->u.xen_evtchn.priority != KVM_IRQ_ROUTING_XEN_EVTCHN_PRIO_2LEVEL)

From 47bb584237cc285e3a860b70c01f7bda9dcfb05b Mon Sep 17 00:00:00 2001
From: Liam Merwick <liam.merwick@oracle.com>
Date: Mon, 9 Jun 2025 09:11:19 +0000
Subject: [PATCH 0805/1334] KVM: Allow CPU to reschedule while setting per-page
 memory attributes

When running an SEV-SNP guest with a sufficiently large amount of memory (1TB+),
the host can experience CPU soft lockups when running an operation in
kvm_vm_set_mem_attributes() to set memory attributes on the whole
range of guest memory.

watchdog: BUG: soft lockup - CPU#8 stuck for 26s! [qemu-kvm:6372]
CPU: 8 UID: 0 PID: 6372 Comm: qemu-kvm Kdump: loaded Not tainted 6.15.0-rc7.20250520.el9uek.rc1.x86_64 #1 PREEMPT(voluntary)
Hardware name: Oracle Corporation ORACLE SERVER E4-2c/Asm,MB Tray,2U,E4-2c, BIOS 78016600 11/13/2024
RIP: 0010:xas_create+0x78/0x1f0
Code: 00 00 00 41 80 fc 01 0f 84 82 00 00 00 ba 06 00 00 00 bd 06 00 00 00 49 8b 45 08 4d 8d 65 08 41 39 d6 73 20 83 ed 06 48 85 c0 <74> 67 48 89 c2 83 e2 03 48 83 fa 02 75 0c 48 3d 00 10 00 00 0f 87
RSP: 0018:ffffad890a34b940 EFLAGS: 00000286
RAX: ffff96f30b261daa RBX: ffffad890a34b9c8 RCX: 0000000000000000
RDX: 000000000000001e RSI: 0000000000000000 RDI: 0000000000000000
RBP: 0000000000000018 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000000 R12: ffffad890a356868
R13: ffffad890a356860 R14: 0000000000000000 R15: ffffad890a356868
FS:  00007f5578a2a400(0000) GS:ffff97ed317e1000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007f015c70fb18 CR3: 00000001109fd006 CR4: 0000000000f70ef0
PKRU: 55555554
Call Trace:
 <TASK>
 xas_store+0x58/0x630
 __xa_store+0xa5/0x130
 xa_store+0x2c/0x50
 kvm_vm_set_mem_attributes+0x343/0x710 [kvm]
 kvm_vm_ioctl+0x796/0xab0 [kvm]
 __x64_sys_ioctl+0xa3/0xd0
 do_syscall_64+0x8c/0x7a0
 entry_SYSCALL_64_after_hwframe+0x76/0x7e
RIP: 0033:0x7f5578d031bb
Code: ff ff ff 85 c0 79 9b 49 c7 c4 ff ff ff ff 5b 5d 4c 89 e0 41 5c c3 66 0f 1f 84 00 00 00 00 00 f3 0f 1e fa b8 10 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d 2d 4c 0f 00 f7 d8 64 89 01 48
RSP: 002b:00007ffe0a742b88 EFLAGS: 00000246 ORIG_RAX: 0000000000000010
RAX: ffffffffffffffda RBX: 000000004020aed2 RCX: 00007f5578d031bb
RDX: 00007ffe0a742c80 RSI: 000000004020aed2 RDI: 000000000000000b
RBP: 0000010000000000 R08: 0000010000000000 R09: 0000017680000000
R10: 0000000000000080 R11: 0000000000000246 R12: 00005575e5f95120
R13: 00007ffe0a742c80 R14: 0000000000000008 R15: 00005575e5f961e0

While looping through the range of memory setting the attributes,
call cond_resched() to give the scheduler a chance to run a higher
priority task on the runqueue if necessary and avoid staying in
kernel mode long enough to trigger the lockup.

Fixes: 5a475554db1e ("KVM: Introduce per-page memory attributes")
Cc: stable@vger.kernel.org # 6.12.x
Suggested-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Liam Merwick <liam.merwick@oracle.com>
Reviewed-by: Pankaj Gupta <pankaj.gupta@amd.com>
Link: https://lore.kernel.org/r/20250609091121.2497429-2-liam.merwick@oracle.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 virt/kvm/kvm_main.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index eec82775c5bf..222f0e894a0c 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -2572,6 +2572,8 @@ static int kvm_vm_set_mem_attributes(struct kvm *kvm, gfn_t start, gfn_t end,
 		r = xa_reserve(&kvm->mem_attr_array, i, GFP_KERNEL_ACCOUNT);
 		if (r)
 			goto out_unlock;
+
+		cond_resched();
 	}
 
 	kvm_handle_gfn_range(kvm, &pre_set_range);
@@ -2580,6 +2582,7 @@ static int kvm_vm_set_mem_attributes(struct kvm *kvm, gfn_t start, gfn_t end,
 		r = xa_err(xa_store(&kvm->mem_attr_array, i, entry,
 				    GFP_KERNEL_ACCOUNT));
 		KVM_BUG_ON(r, kvm);
+		cond_resched();
 	}
 
 	kvm_handle_gfn_range(kvm, &post_set_range);

From 5c4acbc8ce9025fe6e318966af8d3c42ffc6e9ca Mon Sep 17 00:00:00 2001
From: Alan Huang <mmpgouride@gmail.com>
Date: Wed, 25 Jun 2025 03:10:27 +0800
Subject: [PATCH 0806/1334] bcachefs: Don't unlock the trans if ret doesn't
 match BCH_ERR_operation_blocked

Reported-by: syzbot+d540192e763531d307ff@syzkaller.appspotmail.com
Signed-off-by: Alan Huang <mmpgouride@gmail.com>
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/btree_update_interior.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/fs/bcachefs/btree_update_interior.c b/fs/bcachefs/btree_update_interior.c
index 7bf1bd6a6e92..553059b33bfd 100644
--- a/fs/bcachefs/btree_update_interior.c
+++ b/fs/bcachefs/btree_update_interior.c
@@ -1287,10 +1287,11 @@ bch2_btree_update_start(struct btree_trans *trans, struct btree_path *path,
 
 		do {
 			ret = bch2_btree_reserve_get(trans, as, nr_nodes, target, flags, &cl);
-
+			if (!bch2_err_matches(ret, BCH_ERR_operation_blocked))
+				break;
 			bch2_trans_unlock(trans);
 			bch2_wait_on_allocator(c, &cl);
-		} while (bch2_err_matches(ret, BCH_ERR_operation_blocked));
+		} while (1);
 	}
 
 	if (ret) {

From 865ad1dbf13244b349e3da2731c1188476ad17b8 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Mon, 23 Jun 2025 18:42:42 -0400
Subject: [PATCH 0807/1334] bcachefs: Check for bad write buffer key when
 moving from journal

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/btree_update.h       | 5 ++---
 fs/bcachefs/btree_write_buffer.c | 5 ++---
 fs/bcachefs/btree_write_buffer.h | 6 ++++++
 3 files changed, 10 insertions(+), 6 deletions(-)

diff --git a/fs/bcachefs/btree_update.h b/fs/bcachefs/btree_update.h
index 9feef1dc4de5..0b98ab959719 100644
--- a/fs/bcachefs/btree_update.h
+++ b/fs/bcachefs/btree_update.h
@@ -170,8 +170,7 @@ bch2_trans_jset_entry_alloc(struct btree_trans *trans, unsigned u64s)
 
 int bch2_btree_insert_clone_trans(struct btree_trans *, enum btree_id, struct bkey_i *);
 
-int bch2_btree_write_buffer_insert_err(struct btree_trans *,
-				       enum btree_id, struct bkey_i *);
+int bch2_btree_write_buffer_insert_err(struct bch_fs *, enum btree_id, struct bkey_i *);
 
 static inline int __must_check bch2_trans_update_buffered(struct btree_trans *trans,
 					    enum btree_id btree,
@@ -182,7 +181,7 @@ static inline int __must_check bch2_trans_update_buffered(struct btree_trans *tr
 	EBUG_ON(k->k.u64s > BTREE_WRITE_BUFERED_U64s_MAX);
 
 	if (unlikely(!btree_type_uses_write_buffer(btree))) {
-		int ret = bch2_btree_write_buffer_insert_err(trans, btree, k);
+		int ret = bch2_btree_write_buffer_insert_err(trans->c, btree, k);
 		dump_stack();
 		return ret;
 	}
diff --git a/fs/bcachefs/btree_write_buffer.c b/fs/bcachefs/btree_write_buffer.c
index 21b5c03d1822..4b095235a0d2 100644
--- a/fs/bcachefs/btree_write_buffer.c
+++ b/fs/bcachefs/btree_write_buffer.c
@@ -267,10 +267,9 @@ out:
 	BUG_ON(wb->sorted.size < wb->flushing.keys.nr);
 }
 
-int bch2_btree_write_buffer_insert_err(struct btree_trans *trans,
+int bch2_btree_write_buffer_insert_err(struct bch_fs *c,
 				       enum btree_id btree, struct bkey_i *k)
 {
-	struct bch_fs *c = trans->c;
 	struct printbuf buf = PRINTBUF;
 
 	prt_printf(&buf, "attempting to do write buffer update on non wb btree=");
@@ -332,7 +331,7 @@ static int bch2_btree_write_buffer_flush_locked(struct btree_trans *trans)
 		struct btree_write_buffered_key *k = &wb->flushing.keys.data[i->idx];
 
 		if (unlikely(!btree_type_uses_write_buffer(k->btree))) {
-			ret = bch2_btree_write_buffer_insert_err(trans, k->btree, &k->k);
+			ret = bch2_btree_write_buffer_insert_err(trans->c, k->btree, &k->k);
 			goto err;
 		}
 
diff --git a/fs/bcachefs/btree_write_buffer.h b/fs/bcachefs/btree_write_buffer.h
index 05f56fd1eed0..c351d21aca0b 100644
--- a/fs/bcachefs/btree_write_buffer.h
+++ b/fs/bcachefs/btree_write_buffer.h
@@ -89,6 +89,12 @@ static inline int bch2_journal_key_to_wb(struct bch_fs *c,
 			     struct journal_keys_to_wb *dst,
 			     enum btree_id btree, struct bkey_i *k)
 {
+	if (unlikely(!btree_type_uses_write_buffer(btree))) {
+		int ret = bch2_btree_write_buffer_insert_err(c, btree, k);
+		dump_stack();
+		return ret;
+	}
+
 	EBUG_ON(!dst->seq);
 
 	return k->k.type == KEY_TYPE_accounting

From 0048ca5e9945f487fc055dad987ee4c7fdc1ed18 Mon Sep 17 00:00:00 2001
From: Chenyi Qiang <chenyi.qiang@intel.com>
Date: Fri, 20 Jun 2025 14:22:18 +0800
Subject: [PATCH 0808/1334] KVM: selftests: Add back the missing check of
 MONITOR/MWAIT availability

The revamp of monitor/mwait test missed the original check of feature
availability [*]. If MONITOR/MWAIT is not supported or is disabled by
IA32_MISC_ENABLE on the host, executing MONITOR or MWAIT instruction
from guest doesn't cause monitor/mwait VM exits, but a #UD.

[*] https://lore.kernel.org/all/20240411210237.34646-1-zide.chen@intel.com/

Reported-by: Xuelian Guo <xuelian.guo@intel.com>
Fixes: 80fd663590cf ("selftests: kvm: revamp MONITOR/MWAIT tests")
Signed-off-by: Chenyi Qiang <chenyi.qiang@intel.com>
Link: https://lore.kernel.org/r/20250620062219.342930-1-chenyi.qiang@intel.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 tools/testing/selftests/kvm/x86/monitor_mwait_test.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/testing/selftests/kvm/x86/monitor_mwait_test.c b/tools/testing/selftests/kvm/x86/monitor_mwait_test.c
index 390ae2d87493..0eb371c62ab8 100644
--- a/tools/testing/selftests/kvm/x86/monitor_mwait_test.c
+++ b/tools/testing/selftests/kvm/x86/monitor_mwait_test.c
@@ -74,6 +74,7 @@ int main(int argc, char *argv[])
 	int testcase;
 	char test[80];
 
+	TEST_REQUIRE(this_cpu_has(X86_FEATURE_MWAIT));
 	TEST_REQUIRE(kvm_has_cap(KVM_CAP_DISABLE_QUIRKS2));
 
 	ksft_print_header();

From 5f465c148c61e876b6d6eacd8e8e365f2d47758f Mon Sep 17 00:00:00 2001
From: "Xin Li (Intel)" <xin@zytor.com>
Date: Fri, 20 Jun 2025 16:15:03 -0700
Subject: [PATCH 0809/1334] x86/traps: Initialize DR6 by writing its
 architectural reset value

Initialize DR6 by writing its architectural reset value to avoid
incorrectly zeroing DR6 to clear DR6.BLD at boot time, which leads
to a false bus lock detected warning.

The Intel SDM says:

  1) Certain debug exceptions may clear bits 0-3 of DR6.

  2) BLD induced #DB clears DR6.BLD and any other debug exception
     doesn't modify DR6.BLD.

  3) RTM induced #DB clears DR6.RTM and any other debug exception
     sets DR6.RTM.

  To avoid confusion in identifying debug exceptions, debug handlers
  should set DR6.BLD and DR6.RTM, and clear other DR6 bits before
  returning.

The DR6 architectural reset value 0xFFFF0FF0, already defined as
macro DR6_RESERVED, satisfies these requirements, so just use it to
reinitialize DR6 whenever needed.

Since clear_all_debug_regs() no longer zeros all debug registers,
rename it to initialize_debug_regs() to better reflect its current
behavior.

Since debug_read_clear_dr6() no longer clears DR6, rename it to
debug_read_reset_dr6() to better reflect its current behavior.

Fixes: ebb1064e7c2e9 ("x86/traps: Handle #DB for bus lock")
Reported-by: Sohil Mehta <sohil.mehta@intel.com>
Suggested-by: H. Peter Anvin (Intel) <hpa@zytor.com>
Signed-off-by: Xin Li (Intel) <xin@zytor.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: H. Peter Anvin (Intel) <hpa@zytor.com>
Reviewed-by: Sohil Mehta <sohil.mehta@intel.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Sohil Mehta <sohil.mehta@intel.com>
Link: https://lore.kernel.org/lkml/06e68373-a92b-472e-8fd9-ba548119770c@intel.com/
Cc:stable@vger.kernel.org
Link: https://lore.kernel.org/all/20250620231504.2676902-2-xin%40zytor.com
---
 arch/x86/include/uapi/asm/debugreg.h | 21 ++++++++++++++++-
 arch/x86/kernel/cpu/common.c         | 24 ++++++++------------
 arch/x86/kernel/traps.c              | 34 +++++++++++++++++-----------
 3 files changed, 51 insertions(+), 28 deletions(-)

diff --git a/arch/x86/include/uapi/asm/debugreg.h b/arch/x86/include/uapi/asm/debugreg.h
index 0007ba077c0c..41da492dfb01 100644
--- a/arch/x86/include/uapi/asm/debugreg.h
+++ b/arch/x86/include/uapi/asm/debugreg.h
@@ -15,7 +15,26 @@
    which debugging register was responsible for the trap.  The other bits
    are either reserved or not of interest to us. */
 
-/* Define reserved bits in DR6 which are always set to 1 */
+/*
+ * Define bits in DR6 which are set to 1 by default.
+ *
+ * This is also the DR6 architectural value following Power-up, Reset or INIT.
+ *
+ * Note, with the introduction of Bus Lock Detection (BLD) and Restricted
+ * Transactional Memory (RTM), the DR6 register has been modified:
+ *
+ * 1) BLD flag (bit 11) is no longer reserved to 1 if the CPU supports
+ *    Bus Lock Detection.  The assertion of a bus lock could clear it.
+ *
+ * 2) RTM flag (bit 16) is no longer reserved to 1 if the CPU supports
+ *    restricted transactional memory.  #DB occurred inside an RTM region
+ *    could clear it.
+ *
+ * Apparently, DR6.BLD and DR6.RTM are active low bits.
+ *
+ * As a result, DR6_RESERVED is an incorrect name now, but it is kept for
+ * compatibility.
+ */
 #define DR6_RESERVED	(0xFFFF0FF0)
 
 #define DR_TRAP0	(0x1)		/* db0 */
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 8feb8fd2957a..0f6c280a94f0 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -2243,20 +2243,16 @@ EXPORT_PER_CPU_SYMBOL(__stack_chk_guard);
 #endif
 #endif
 
-/*
- * Clear all 6 debug registers:
- */
-static void clear_all_debug_regs(void)
+static void initialize_debug_regs(void)
 {
-	int i;
-
-	for (i = 0; i < 8; i++) {
-		/* Ignore db4, db5 */
-		if ((i == 4) || (i == 5))
-			continue;
-
-		set_debugreg(0, i);
-	}
+	/* Control register first -- to make sure everything is disabled. */
+	set_debugreg(0, 7);
+	set_debugreg(DR6_RESERVED, 6);
+	/* dr5 and dr4 don't exist */
+	set_debugreg(0, 3);
+	set_debugreg(0, 2);
+	set_debugreg(0, 1);
+	set_debugreg(0, 0);
 }
 
 #ifdef CONFIG_KGDB
@@ -2417,7 +2413,7 @@ void cpu_init(void)
 
 	load_mm_ldt(&init_mm);
 
-	clear_all_debug_regs();
+	initialize_debug_regs();
 	dbg_restore_debug_regs();
 
 	doublefault_init_cpu_tss();
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index c5c897a86418..36354b470590 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -1022,24 +1022,32 @@ static bool is_sysenter_singlestep(struct pt_regs *regs)
 #endif
 }
 
-static __always_inline unsigned long debug_read_clear_dr6(void)
+static __always_inline unsigned long debug_read_reset_dr6(void)
 {
 	unsigned long dr6;
 
+	get_debugreg(dr6, 6);
+	dr6 ^= DR6_RESERVED; /* Flip to positive polarity */
+
 	/*
 	 * The Intel SDM says:
 	 *
-	 *   Certain debug exceptions may clear bits 0-3. The remaining
-	 *   contents of the DR6 register are never cleared by the
-	 *   processor. To avoid confusion in identifying debug
-	 *   exceptions, debug handlers should clear the register before
-	 *   returning to the interrupted task.
+	 *   Certain debug exceptions may clear bits 0-3 of DR6.
 	 *
-	 * Keep it simple: clear DR6 immediately.
+	 *   BLD induced #DB clears DR6.BLD and any other debug
+	 *   exception doesn't modify DR6.BLD.
+	 *
+	 *   RTM induced #DB clears DR6.RTM and any other debug
+	 *   exception sets DR6.RTM.
+	 *
+	 *   To avoid confusion in identifying debug exceptions,
+	 *   debug handlers should set DR6.BLD and DR6.RTM, and
+	 *   clear other DR6 bits before returning.
+	 *
+	 * Keep it simple: write DR6 with its architectural reset
+	 * value 0xFFFF0FF0, defined as DR6_RESERVED, immediately.
 	 */
-	get_debugreg(dr6, 6);
 	set_debugreg(DR6_RESERVED, 6);
-	dr6 ^= DR6_RESERVED; /* Flip to positive polarity */
 
 	return dr6;
 }
@@ -1239,13 +1247,13 @@ out:
 /* IST stack entry */
 DEFINE_IDTENTRY_DEBUG(exc_debug)
 {
-	exc_debug_kernel(regs, debug_read_clear_dr6());
+	exc_debug_kernel(regs, debug_read_reset_dr6());
 }
 
 /* User entry, runs on regular task stack */
 DEFINE_IDTENTRY_DEBUG_USER(exc_debug)
 {
-	exc_debug_user(regs, debug_read_clear_dr6());
+	exc_debug_user(regs, debug_read_reset_dr6());
 }
 
 #ifdef CONFIG_X86_FRED
@@ -1264,7 +1272,7 @@ DEFINE_FREDENTRY_DEBUG(exc_debug)
 {
 	/*
 	 * FRED #DB stores DR6 on the stack in the format which
-	 * debug_read_clear_dr6() returns for the IDT entry points.
+	 * debug_read_reset_dr6() returns for the IDT entry points.
 	 */
 	unsigned long dr6 = fred_event_data(regs);
 
@@ -1279,7 +1287,7 @@ DEFINE_FREDENTRY_DEBUG(exc_debug)
 /* 32 bit does not have separate entry points. */
 DEFINE_IDTENTRY_RAW(exc_debug)
 {
-	unsigned long dr6 = debug_read_clear_dr6();
+	unsigned long dr6 = debug_read_reset_dr6();
 
 	if (user_mode(regs))
 		exc_debug_user(regs, dr6);

From fa7d0f83c5c4223a01598876352473cb3d3bd4d7 Mon Sep 17 00:00:00 2001
From: "Xin Li (Intel)" <xin@zytor.com>
Date: Fri, 20 Jun 2025 16:15:04 -0700
Subject: [PATCH 0810/1334] x86/traps: Initialize DR7 by writing its
 architectural reset value

Initialize DR7 by writing its architectural reset value to always set
bit 10, which is reserved to '1', when "clearing" DR7 so as not to
trigger unanticipated behavior if said bit is ever unreserved, e.g. as
a feature enabling flag with inverted polarity.

Signed-off-by: Xin Li (Intel) <xin@zytor.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: H. Peter Anvin (Intel) <hpa@zytor.com>
Reviewed-by: Sohil Mehta <sohil.mehta@intel.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Sean Christopherson <seanjc@google.com>
Tested-by: Sohil Mehta <sohil.mehta@intel.com>
Cc:stable@vger.kernel.org
Link: https://lore.kernel.org/all/20250620231504.2676902-3-xin%40zytor.com
---
 arch/x86/include/asm/debugreg.h | 19 +++++++++++++++----
 arch/x86/include/asm/kvm_host.h |  2 +-
 arch/x86/kernel/cpu/common.c    |  2 +-
 arch/x86/kernel/kgdb.c          |  2 +-
 arch/x86/kernel/process_32.c    |  2 +-
 arch/x86/kernel/process_64.c    |  2 +-
 arch/x86/kvm/x86.c              |  4 ++--
 7 files changed, 22 insertions(+), 11 deletions(-)

diff --git a/arch/x86/include/asm/debugreg.h b/arch/x86/include/asm/debugreg.h
index 363110e6b2e3..a2c1f2d24b64 100644
--- a/arch/x86/include/asm/debugreg.h
+++ b/arch/x86/include/asm/debugreg.h
@@ -9,6 +9,14 @@
 #include <asm/cpufeature.h>
 #include <asm/msr.h>
 
+/*
+ * Define bits that are always set to 1 in DR7, only bit 10 is
+ * architecturally reserved to '1'.
+ *
+ * This is also the init/reset value for DR7.
+ */
+#define DR7_FIXED_1	0x00000400
+
 DECLARE_PER_CPU(unsigned long, cpu_dr7);
 
 #ifndef CONFIG_PARAVIRT_XXL
@@ -100,8 +108,8 @@ static __always_inline void native_set_debugreg(int regno, unsigned long value)
 
 static inline void hw_breakpoint_disable(void)
 {
-	/* Zero the control register for HW Breakpoint */
-	set_debugreg(0UL, 7);
+	/* Reset the control register for HW Breakpoint */
+	set_debugreg(DR7_FIXED_1, 7);
 
 	/* Zero-out the individual HW breakpoint address registers */
 	set_debugreg(0UL, 0);
@@ -125,9 +133,12 @@ static __always_inline unsigned long local_db_save(void)
 		return 0;
 
 	get_debugreg(dr7, 7);
-	dr7 &= ~0x400; /* architecturally set bit */
+
+	/* Architecturally set bit */
+	dr7 &= ~DR7_FIXED_1;
 	if (dr7)
-		set_debugreg(0, 7);
+		set_debugreg(DR7_FIXED_1, 7);
+
 	/*
 	 * Ensure the compiler doesn't lower the above statements into
 	 * the critical section; disabling breakpoints late would not
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index b4a391929cdb..639d9bcee842 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -31,6 +31,7 @@
 
 #include <asm/apic.h>
 #include <asm/pvclock-abi.h>
+#include <asm/debugreg.h>
 #include <asm/desc.h>
 #include <asm/mtrr.h>
 #include <asm/msr-index.h>
@@ -249,7 +250,6 @@ enum x86_intercept_stage;
 #define DR7_BP_EN_MASK	0x000000ff
 #define DR7_GE		(1 << 9)
 #define DR7_GD		(1 << 13)
-#define DR7_FIXED_1	0x00000400
 #define DR7_VOLATILE	0xffff2bff
 
 #define KVM_GUESTDBG_VALID_MASK \
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 0f6c280a94f0..27125e009847 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -2246,7 +2246,7 @@ EXPORT_PER_CPU_SYMBOL(__stack_chk_guard);
 static void initialize_debug_regs(void)
 {
 	/* Control register first -- to make sure everything is disabled. */
-	set_debugreg(0, 7);
+	set_debugreg(DR7_FIXED_1, 7);
 	set_debugreg(DR6_RESERVED, 6);
 	/* dr5 and dr4 don't exist */
 	set_debugreg(0, 3);
diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c
index 102641fd2172..8b1a9733d13e 100644
--- a/arch/x86/kernel/kgdb.c
+++ b/arch/x86/kernel/kgdb.c
@@ -385,7 +385,7 @@ static void kgdb_disable_hw_debug(struct pt_regs *regs)
 	struct perf_event *bp;
 
 	/* Disable hardware debugging while we are in kgdb: */
-	set_debugreg(0UL, 7);
+	set_debugreg(DR7_FIXED_1, 7);
 	for (i = 0; i < HBP_NUM; i++) {
 		if (!breakinfo[i].enabled)
 			continue;
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index a10e180cbf23..3ef15c2f152f 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -93,7 +93,7 @@ void __show_regs(struct pt_regs *regs, enum show_regs_mode mode,
 
 	/* Only print out debug registers if they are in their non-default state. */
 	if ((d0 == 0) && (d1 == 0) && (d2 == 0) && (d3 == 0) &&
-	    (d6 == DR6_RESERVED) && (d7 == 0x400))
+	    (d6 == DR6_RESERVED) && (d7 == DR7_FIXED_1))
 		return;
 
 	printk("%sDR0: %08lx DR1: %08lx DR2: %08lx DR3: %08lx\n",
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 8d6cf25127aa..b972bf72fb8b 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -133,7 +133,7 @@ void __show_regs(struct pt_regs *regs, enum show_regs_mode mode,
 
 	/* Only print out debug registers if they are in their non-default state. */
 	if (!((d0 == 0) && (d1 == 0) && (d2 == 0) && (d3 == 0) &&
-	    (d6 == DR6_RESERVED) && (d7 == 0x400))) {
+	    (d6 == DR6_RESERVED) && (d7 == DR7_FIXED_1))) {
 		printk("%sDR0: %016lx DR1: %016lx DR2: %016lx\n",
 		       log_lvl, d0, d1, d2);
 		printk("%sDR3: %016lx DR6: %016lx DR7: %016lx\n",
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index b58a74c1722d..a9d992d5652f 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -11035,7 +11035,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 
 	if (unlikely(vcpu->arch.switch_db_regs &&
 		     !(vcpu->arch.switch_db_regs & KVM_DEBUGREG_AUTO_SWITCH))) {
-		set_debugreg(0, 7);
+		set_debugreg(DR7_FIXED_1, 7);
 		set_debugreg(vcpu->arch.eff_db[0], 0);
 		set_debugreg(vcpu->arch.eff_db[1], 1);
 		set_debugreg(vcpu->arch.eff_db[2], 2);
@@ -11044,7 +11044,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 		if (unlikely(vcpu->arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT))
 			kvm_x86_call(set_dr6)(vcpu, vcpu->arch.dr6);
 	} else if (unlikely(hw_breakpoint_active())) {
-		set_debugreg(0, 7);
+		set_debugreg(DR7_FIXED_1, 7);
 	}
 
 	vcpu->arch.host_debugctl = get_debugctlmsr();

From f5109c201cf2bc304a05ecc40c2aabb119b27833 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Tue, 24 Jun 2025 17:53:00 -0400
Subject: [PATCH 0811/1334] bcachefs: Use wait_on_allocator() when allocating
 journal

wait_on_allocator() emits debug info when we hang trying to allocate.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/journal.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/bcachefs/journal.c b/fs/bcachefs/journal.c
index df71af0013ba..f22b05e02c1e 100644
--- a/fs/bcachefs/journal.c
+++ b/fs/bcachefs/journal.c
@@ -1283,7 +1283,7 @@ static int bch2_set_nr_journal_buckets_loop(struct bch_fs *c, struct bch_dev *ca
 			ret = 0; /* wait and retry */
 
 		bch2_disk_reservation_put(c, &disk_res);
-		closure_sync(&cl);
+		bch2_wait_on_allocator(c, &cl);
 	}
 
 	return ret;

From 1f8aede70d491a1d5867f575ca44c86fe2e335ae Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Tue, 24 Jun 2025 16:04:32 -0400
Subject: [PATCH 0812/1334] bcachefs: fix bch2_journal_keys_peek_prev_min()
 underflow

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/btree_journal_iter.c | 20 +++++++++++++++-----
 1 file changed, 15 insertions(+), 5 deletions(-)

diff --git a/fs/bcachefs/btree_journal_iter.c b/fs/bcachefs/btree_journal_iter.c
index a41fabd06332..ea839560a136 100644
--- a/fs/bcachefs/btree_journal_iter.c
+++ b/fs/bcachefs/btree_journal_iter.c
@@ -137,12 +137,15 @@ struct bkey_i *bch2_journal_keys_peek_prev_min(struct bch_fs *c, enum btree_id b
 	struct journal_key *k;
 
 	BUG_ON(*idx > keys->nr);
+
+	if (!keys->nr)
+		return NULL;
 search:
 	if (!*idx)
 		*idx = __bch2_journal_key_search(keys, btree_id, level, pos);
 
 	while (*idx < keys->nr &&
-	       __journal_key_cmp(btree_id, level, end_pos, idx_to_key(keys, *idx - 1)) >= 0) {
+	       __journal_key_cmp(btree_id, level, end_pos, idx_to_key(keys, *idx)) >= 0) {
 		(*idx)++;
 		iters++;
 		if (iters == 10) {
@@ -151,18 +154,23 @@ search:
 		}
 	}
 
+	if (*idx == keys->nr)
+		--(*idx);
+
 	struct bkey_i *ret = NULL;
 	rcu_read_lock(); /* for overwritten_ranges */
 
-	while ((k = *idx < keys->nr ? idx_to_key(keys, *idx) : NULL)) {
+	while (true) {
+		k = idx_to_key(keys, *idx);
 		if (__journal_key_cmp(btree_id, level, end_pos, k) > 0)
 			break;
 
 		if (k->overwritten) {
 			if (k->overwritten_range)
-				*idx = rcu_dereference(k->overwritten_range)->start - 1;
-			else
-				*idx -= 1;
+				*idx = rcu_dereference(k->overwritten_range)->start;
+			if (!*idx)
+				break;
+			--(*idx);
 			continue;
 		}
 
@@ -171,6 +179,8 @@ search:
 			break;
 		}
 
+		if (!*idx)
+			break;
 		--(*idx);
 		iters++;
 		if (iters == 10) {

From 22bbc1dcd0d6785fb390c41f0dd5b5e218d23bdd Mon Sep 17 00:00:00 2001
From: Stefano Garzarella <sgarzare@redhat.com>
Date: Mon, 23 Jun 2025 12:00:53 +0200
Subject: [PATCH 0813/1334] vsock/uapi: fix linux/vm_sockets.h userspace
 compilation errors
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

If a userspace application just include <linux/vm_sockets.h> will fail
to build with the following errors:

    /usr/include/linux/vm_sockets.h:182:39: error: invalid application of ‘sizeof’ to incomplete type ‘struct sockaddr’
      182 |         unsigned char svm_zero[sizeof(struct sockaddr) -
          |                                       ^~~~~~
    /usr/include/linux/vm_sockets.h:183:39: error: ‘sa_family_t’ undeclared here (not in a function)
      183 |                                sizeof(sa_family_t) -
          |

Include <sys/socket.h> for userspace (guarded by ifndef __KERNEL__)
where `struct sockaddr` and `sa_family_t` are defined.
We already do something similar in <linux/mptcp.h> and <linux/if.h>.

Fixes: d021c344051a ("VSOCK: Introduce VM Sockets")
Reported-by: Daan De Meyer <daan.j.demeyer@gmail.com>
Signed-off-by: Stefano Garzarella <sgarzare@redhat.com>
Link: https://patch.msgid.link/20250623100053.40979-1-sgarzare@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/uapi/linux/vm_sockets.h | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/include/uapi/linux/vm_sockets.h b/include/uapi/linux/vm_sockets.h
index ed07181d4eff..e05280e41522 100644
--- a/include/uapi/linux/vm_sockets.h
+++ b/include/uapi/linux/vm_sockets.h
@@ -17,6 +17,10 @@
 #ifndef _UAPI_VM_SOCKETS_H
 #define _UAPI_VM_SOCKETS_H
 
+#ifndef __KERNEL__
+#include <sys/socket.h>        /* for struct sockaddr and sa_family_t */
+#endif
+
 #include <linux/socket.h>
 #include <linux/types.h>
 

From 9caca6ac0e26cd20efd490d8b3b2ffb1c7c00f6f Mon Sep 17 00:00:00 2001
From: Yan Zhai <yan@cloudflare.com>
Date: Mon, 23 Jun 2025 09:06:38 -0700
Subject: [PATCH 0814/1334] bnxt: properly flush XDP redirect lists

We encountered following crash when testing a XDP_REDIRECT feature
in production:

[56251.579676] list_add corruption. next->prev should be prev (ffff93120dd40f30), but was ffffb301ef3a6740. (next=ffff93120dd
40f30).
[56251.601413] ------------[ cut here ]------------
[56251.611357] kernel BUG at lib/list_debug.c:29!
[56251.621082] Oops: invalid opcode: 0000 [#1] PREEMPT SMP NOPTI
[56251.632073] CPU: 111 UID: 0 PID: 0 Comm: swapper/111 Kdump: loaded Tainted: P           O       6.12.33-cloudflare-2025.6.
3 #1
[56251.653155] Tainted: [P]=PROPRIETARY_MODULE, [O]=OOT_MODULE
[56251.663877] Hardware name: MiTAC GC68B-B8032-G11P6-GPU/S8032GM-HE-CFR, BIOS V7.020.B10-sig 01/22/2025
[56251.682626] RIP: 0010:__list_add_valid_or_report+0x4b/0xa0
[56251.693203] Code: 0e 48 c7 c7 68 e7 d9 97 e8 42 16 fe ff 0f 0b 48 8b 52 08 48 39 c2 74 14 48 89 f1 48 c7 c7 90 e7 d9 97 48
 89 c6 e8 25 16 fe ff <0f> 0b 4c 8b 02 49 39 f0 74 14 48 89 d1 48 c7 c7 e8 e7 d9 97 4c 89
[56251.725811] RSP: 0018:ffff93120dd40b80 EFLAGS: 00010246
[56251.736094] RAX: 0000000000000075 RBX: ffffb301e6bba9d8 RCX: 0000000000000000
[56251.748260] RDX: 0000000000000000 RSI: ffff9149afda0b80 RDI: ffff9149afda0b80
[56251.760349] RBP: ffff9131e49c8000 R08: 0000000000000000 R09: ffff93120dd40a18
[56251.772382] R10: ffff9159cf2ce1a8 R11: 0000000000000003 R12: ffff911a80850000
[56251.784364] R13: ffff93120fbc7000 R14: 0000000000000010 R15: ffff9139e7510e40
[56251.796278] FS:  0000000000000000(0000) GS:ffff9149afd80000(0000) knlGS:0000000000000000
[56251.809133] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[56251.819561] CR2: 00007f5e85e6f300 CR3: 00000038b85e2006 CR4: 0000000000770ef0
[56251.831365] PKRU: 55555554
[56251.838653] Call Trace:
[56251.845560]  <IRQ>
[56251.851943]  cpu_map_enqueue.cold+0x5/0xa
[56251.860243]  xdp_do_redirect+0x2d9/0x480
[56251.868388]  bnxt_rx_xdp+0x1d8/0x4c0 [bnxt_en]
[56251.877028]  bnxt_rx_pkt+0x5f7/0x19b0 [bnxt_en]
[56251.885665]  ? cpu_max_write+0x1e/0x100
[56251.893510]  ? srso_alias_return_thunk+0x5/0xfbef5
[56251.902276]  __bnxt_poll_work+0x190/0x340 [bnxt_en]
[56251.911058]  bnxt_poll+0xab/0x1b0 [bnxt_en]
[56251.919041]  ? srso_alias_return_thunk+0x5/0xfbef5
[56251.927568]  ? srso_alias_return_thunk+0x5/0xfbef5
[56251.935958]  ? srso_alias_return_thunk+0x5/0xfbef5
[56251.944250]  __napi_poll+0x2b/0x160
[56251.951155]  bpf_trampoline_6442548651+0x79/0x123
[56251.959262]  __napi_poll+0x5/0x160
[56251.966037]  net_rx_action+0x3d2/0x880
[56251.973133]  ? srso_alias_return_thunk+0x5/0xfbef5
[56251.981265]  ? srso_alias_return_thunk+0x5/0xfbef5
[56251.989262]  ? __hrtimer_run_queues+0x162/0x2a0
[56251.996967]  ? srso_alias_return_thunk+0x5/0xfbef5
[56252.004875]  ? srso_alias_return_thunk+0x5/0xfbef5
[56252.012673]  ? bnxt_msix+0x62/0x70 [bnxt_en]
[56252.019903]  handle_softirqs+0xcf/0x270
[56252.026650]  irq_exit_rcu+0x67/0x90
[56252.032933]  common_interrupt+0x85/0xa0
[56252.039498]  </IRQ>
[56252.044246]  <TASK>
[56252.048935]  asm_common_interrupt+0x26/0x40
[56252.055727] RIP: 0010:cpuidle_enter_state+0xb8/0x420
[56252.063305] Code: dc 01 00 00 e8 f9 79 3b ff e8 64 f7 ff ff 49 89 c5 0f 1f 44 00 00 31 ff e8 a5 32 3a ff 45 84 ff 0f 85 ae
 01 00 00 fb 45 85 f6 <0f> 88 88 01 00 00 48 8b 04 24 49 63 ce 4c 89 ea 48 6b f1 68 48 29
[56252.088911] RSP: 0018:ffff93120c97fe98 EFLAGS: 00000202
[56252.096912] RAX: ffff9149afd80000 RBX: ffff9141d3a72800 RCX: 0000000000000000
[56252.106844] RDX: 00003329176c6b98 RSI: ffffffe36db3fdc7 RDI: 0000000000000000
[56252.116733] RBP: 0000000000000002 R08: 0000000000000002 R09: 000000000000004e
[56252.126652] R10: ffff9149afdb30c4 R11: 071c71c71c71c71c R12: ffffffff985ff860
[56252.136637] R13: 00003329176c6b98 R14: 0000000000000002 R15: 0000000000000000
[56252.146667]  ? cpuidle_enter_state+0xab/0x420
[56252.153909]  cpuidle_enter+0x2d/0x40
[56252.160360]  do_idle+0x176/0x1c0
[56252.166456]  cpu_startup_entry+0x29/0x30
[56252.173248]  start_secondary+0xf7/0x100
[56252.179941]  common_startup_64+0x13e/0x141
[56252.186886]  </TASK>

From the crash dump, we found that the cpu_map_flush_list inside
redirect info is partially corrupted: its list_head->next points to
itself, but list_head->prev points to a valid list of unflushed bq
entries.

This turned out to be a result of missed XDP flush on redirect lists. By
digging in the actual source code, we found that
commit 7f0a168b0441 ("bnxt_en: Add completion ring pointer in TX and RX
ring structures") incorrectly overwrites the event mask for XDP_REDIRECT
in bnxt_rx_xdp. We can stably reproduce this crash by returning XDP_TX
and XDP_REDIRECT randomly for incoming packets in a naive XDP program.
Properly propagate the XDP_REDIRECT events back fixes the crash.

Fixes: a7559bc8c17c ("bnxt: support transmit and free of aggregation buffers")
Tested-by: Andrew Rzeznik <arzeznik@cloudflare.com>
Signed-off-by: Yan Zhai <yan@cloudflare.com>
Acked-by: Jesper Dangaard Brouer <hawk@kernel.org>
Reviewed-by: Michael Chan <michael.chan@broadcom.com>
Reviewed-by: Andy Gospodarek <gospo@broadcom.com>
Link: https://patch.msgid.link/aFl7jpCNzscumuN2@debian.debian
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 2cb3185c442c..ae89a981e052 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -2989,6 +2989,7 @@ static int __bnxt_poll_work(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 {
 	struct bnxt_napi *bnapi = cpr->bnapi;
 	u32 raw_cons = cpr->cp_raw_cons;
+	bool flush_xdp = false;
 	u32 cons;
 	int rx_pkts = 0;
 	u8 event = 0;
@@ -3042,6 +3043,8 @@ static int __bnxt_poll_work(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 			else
 				rc = bnxt_force_rx_discard(bp, cpr, &raw_cons,
 							   &event);
+			if (event & BNXT_REDIRECT_EVENT)
+				flush_xdp = true;
 			if (likely(rc >= 0))
 				rx_pkts += rc;
 			/* Increment rx_pkts when rc is -ENOMEM to count towards
@@ -3066,7 +3069,7 @@ static int __bnxt_poll_work(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 		}
 	}
 
-	if (event & BNXT_REDIRECT_EVENT) {
+	if (flush_xdp) {
 		xdp_do_flush();
 		event &= ~BNXT_REDIRECT_EVENT;
 	}

From 8889676cd62161896f1d861ce294adc29c4f2cb5 Mon Sep 17 00:00:00 2001
From: jackysliu <1972843537@qq.com>
Date: Thu, 19 Jun 2025 12:03:02 +0800
Subject: [PATCH 0815/1334] scsi: sd: Fix VPD page 0xb7 length check

sd_read_block_limits_ext() currently assumes that vpd->len excludes the
size of the page header. However, vpd->len describes the size of the entire
VPD page, therefore the sanity check is incorrect.

In practice this is not really a problem since we don't attach VPD
pages unless they actually report data trailing the header. But fix
the length check regardless.

This issue was identified by Wukong-Agent (formerly Tencent Woodpecker), a
code security AI agent, through static code analysis.

[mkp: rewrote patch description]

Signed-off-by: jackysliu <1972843537@qq.com>
Link: https://lore.kernel.org/r/tencent_ADA5210D1317EEB6CD7F3DE9FE9DA4591D05@qq.com
Fixes: 96b171d6dba6 ("scsi: core: Query the Block Limits Extension VPD page")
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/sd.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index 3f6e87705b62..eeaa6af294b8 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -3384,7 +3384,7 @@ static void sd_read_block_limits_ext(struct scsi_disk *sdkp)
 
 	rcu_read_lock();
 	vpd = rcu_dereference(sdkp->device->vpd_pgb7);
-	if (vpd && vpd->len >= 2)
+	if (vpd && vpd->len >= 6)
 		sdkp->rscs = vpd->data[5] & 1;
 	rcu_read_unlock();
 }

From 844c6a160e69cc6d1da4b666f8672f6fc5f4f862 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 24 Jun 2025 14:52:27 +0200
Subject: [PATCH 0816/1334] scsi: RDMA/srp: Don't set a max_segment_size when
 virt_boundary_mask is set

virt_boundary_mask implies an unlimited max_segment_size.  Setting both
can lead to data corruption because __blk_rq_map_sg() can split requests
so that the virt_boundary_mask is not respected if max_segment_size is
not UINT_MAX.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20250624125233.219635-2-hch@lst.de
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: John Garry <john.g.garry@oracle.com>
Acked-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/infiniband/ulp/srp/ib_srp.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/infiniband/ulp/srp/ib_srp.c b/drivers/infiniband/ulp/srp/ib_srp.c
index 1378651735f6..23ed2fc688f0 100644
--- a/drivers/infiniband/ulp/srp/ib_srp.c
+++ b/drivers/infiniband/ulp/srp/ib_srp.c
@@ -3705,9 +3705,10 @@ static ssize_t add_target_store(struct device *dev,
 	target_host->max_id      = 1;
 	target_host->max_lun     = -1LL;
 	target_host->max_cmd_len = sizeof ((struct srp_cmd *) (void *) 0L)->cdb;
-	target_host->max_segment_size = ib_dma_max_seg_size(ibdev);
 
-	if (!(ibdev->attrs.kernel_cap_flags & IBK_SG_GAPS_REG))
+	if (ibdev->attrs.kernel_cap_flags & IBK_SG_GAPS_REG)
+		target_host->max_segment_size = ib_dma_max_seg_size(ibdev);
+	else
 		target_host->virt_boundary_mask = ~srp_dev->mr_page_mask;
 
 	target = host_to_target(target_host);

From 4937e604ca24c41cae3296d069c871c2f3f519c8 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 24 Jun 2025 14:52:28 +0200
Subject: [PATCH 0817/1334] scsi: core: Enforce unlimited max_segment_size when
 virt_boundary_mask is set

The virt_boundary_mask limit requires an unlimited max_segment_size for
bio splitting to not corrupt data.  Historically, the block layer tried
to validate this, although the check was half-hearted until the addition
of the atomic queue limits API.  The full blown check then triggered
issues with stacked devices incorrectly inheriting limits such as the
virt boundary and got disabled in commit b561ea56a264 ("block: allow
device to have both virt_boundary_mask and max segment size") instead of
fixing the issue properly.

Ensure that the SCSI mid layer doesn't set the default low
max_segment_size limit for this case, and check for invalid
max_segment_size values in the host template, similar to the original
block layer check given that SCSI devices can't be stacked.

This fixes reported data corruption on storvsc, although as far as I can
tell storvsc always failed to properly set the max_segment_size limit as
the SCSI APIs historically applied that when setting up the host, while
storvsc only set the virt_boundary_mask when configuring the scsi_device.

Fixes: 81988a0e6b03 ("storvsc: get rid of bounce buffer")
Fixes: b561ea56a264 ("block: allow device to have both virt_boundary_mask and max segment size")
Reported-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20250624125233.219635-3-hch@lst.de
Reviewed-by: John Garry <john.g.garry@oracle.com>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/hosts.c | 18 +++++++++++-------
 1 file changed, 11 insertions(+), 7 deletions(-)

diff --git a/drivers/scsi/hosts.c b/drivers/scsi/hosts.c
index e021f1106bea..cc5d05dc395c 100644
--- a/drivers/scsi/hosts.c
+++ b/drivers/scsi/hosts.c
@@ -473,10 +473,17 @@ struct Scsi_Host *scsi_host_alloc(const struct scsi_host_template *sht, int priv
 	else
 		shost->max_sectors = SCSI_DEFAULT_MAX_SECTORS;
 
-	if (sht->max_segment_size)
-		shost->max_segment_size = sht->max_segment_size;
-	else
-		shost->max_segment_size = BLK_MAX_SEGMENT_SIZE;
+	shost->virt_boundary_mask = sht->virt_boundary_mask;
+	if (shost->virt_boundary_mask) {
+		WARN_ON_ONCE(sht->max_segment_size &&
+			     sht->max_segment_size != UINT_MAX);
+		shost->max_segment_size = UINT_MAX;
+	} else {
+		if (sht->max_segment_size)
+			shost->max_segment_size = sht->max_segment_size;
+		else
+			shost->max_segment_size = BLK_MAX_SEGMENT_SIZE;
+	}
 
 	/* 32-byte (dword) is a common minimum for HBAs. */
 	if (sht->dma_alignment)
@@ -492,9 +499,6 @@ struct Scsi_Host *scsi_host_alloc(const struct scsi_host_template *sht, int priv
 	else
 		shost->dma_boundary = 0xffffffff;
 
-	if (sht->virt_boundary_mask)
-		shost->virt_boundary_mask = sht->virt_boundary_mask;
-
 	device_initialize(&shost->shost_gendev);
 	dev_set_name(&shost->shost_gendev, "host%d", shost->host_no);
 	shost->shost_gendev.bus = &scsi_bus_type;

From 021f243627ead17eb6500170256d3d9be787dad8 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bvanassche@acm.org>
Date: Tue, 24 Jun 2025 11:16:44 -0700
Subject: [PATCH 0818/1334] scsi: ufs: core: Fix spelling of a sysfs attribute
 name

Change "resourse" into "resource" in the name of a sysfs attribute.

Fixes: d829fc8a1058 ("scsi: ufs: sysfs: unit descriptor")
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Link: https://lore.kernel.org/r/20250624181658.336035-1-bvanassche@acm.org
Reviewed-by: Avri Altman <avri.altman@sandisk.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 Documentation/ABI/testing/sysfs-driver-ufs | 2 +-
 drivers/ufs/core/ufs-sysfs.c               | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/Documentation/ABI/testing/sysfs-driver-ufs b/Documentation/ABI/testing/sysfs-driver-ufs
index d4140dc6c5ba..615453fcc9ff 100644
--- a/Documentation/ABI/testing/sysfs-driver-ufs
+++ b/Documentation/ABI/testing/sysfs-driver-ufs
@@ -711,7 +711,7 @@ Description:	This file shows the thin provisioning type. This is one of
 
 		The file is read only.
 
-What:		/sys/class/scsi_device/*/device/unit_descriptor/physical_memory_resourse_count
+What:		/sys/class/scsi_device/*/device/unit_descriptor/physical_memory_resource_count
 Date:		February 2018
 Contact:	Stanislav Nijnikov <stanislav.nijnikov@wdc.com>
 Description:	This file shows the total physical memory resources. This is
diff --git a/drivers/ufs/core/ufs-sysfs.c b/drivers/ufs/core/ufs-sysfs.c
index de8b6acd4058..fcb4b14a710f 100644
--- a/drivers/ufs/core/ufs-sysfs.c
+++ b/drivers/ufs/core/ufs-sysfs.c
@@ -1808,7 +1808,7 @@ UFS_UNIT_DESC_PARAM(logical_block_size, _LOGICAL_BLK_SIZE, 1);
 UFS_UNIT_DESC_PARAM(logical_block_count, _LOGICAL_BLK_COUNT, 8);
 UFS_UNIT_DESC_PARAM(erase_block_size, _ERASE_BLK_SIZE, 4);
 UFS_UNIT_DESC_PARAM(provisioning_type, _PROVISIONING_TYPE, 1);
-UFS_UNIT_DESC_PARAM(physical_memory_resourse_count, _PHY_MEM_RSRC_CNT, 8);
+UFS_UNIT_DESC_PARAM(physical_memory_resource_count, _PHY_MEM_RSRC_CNT, 8);
 UFS_UNIT_DESC_PARAM(context_capabilities, _CTX_CAPABILITIES, 2);
 UFS_UNIT_DESC_PARAM(large_unit_granularity, _LARGE_UNIT_SIZE_M1, 1);
 UFS_UNIT_DESC_PARAM(wb_buf_alloc_units, _WB_BUF_ALLOC_UNITS, 4);
@@ -1825,7 +1825,7 @@ static struct attribute *ufs_sysfs_unit_descriptor[] = {
 	&dev_attr_logical_block_count.attr,
 	&dev_attr_erase_block_size.attr,
 	&dev_attr_provisioning_type.attr,
-	&dev_attr_physical_memory_resourse_count.attr,
+	&dev_attr_physical_memory_resource_count.attr,
 	&dev_attr_context_capabilities.attr,
 	&dev_attr_large_unit_granularity.attr,
 	&dev_attr_wb_buf_alloc_units.attr,

From 524346e9d79f63a6e5aaa645140da3d1ec7a8a0f Mon Sep 17 00:00:00 2001
From: Ming Lei <ming.lei@redhat.com>
Date: Wed, 25 Jun 2025 10:25:54 +0800
Subject: [PATCH 0819/1334] ublk: build batch from IOs in same io_ring_ctx and
 io task

ublk_queue_cmd_list() dispatches the whole batch list by scheduling task
work via the tail request's io_uring_cmd, this way is fine even though
more than one io_ring_ctx are involved for this batch since it is just
one running context.

However, the task work handler ublk_cmd_list_tw_cb() takes `issue_flags`
of tail uring_cmd's io_ring_ctx for completing all commands. This way is
wrong if any uring_cmd is issued from different io_ring_ctx.

Fixes it by always building batch IOs from same io_ring_ctx and io task
because ublk_dispatch_req() does validate task context, and IO needs to
be aborted in case of running from fallback task work context.

For typical per-queue or per-io daemon implementation, this way shouldn't
make difference from performance viewpoint, because single io_ring_ctx is
taken in each daemon for normal use case.

Fixes: d796cea7b9f3 ("ublk: implement ->queue_rqs()")
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/20250625022554.883571-1-ming.lei@redhat.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/ublk_drv.c | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c
index d36f44f5ee80..90c02ced392a 100644
--- a/drivers/block/ublk_drv.c
+++ b/drivers/block/ublk_drv.c
@@ -1416,6 +1416,14 @@ static blk_status_t ublk_queue_rq(struct blk_mq_hw_ctx *hctx,
 	return BLK_STS_OK;
 }
 
+static inline bool ublk_belong_to_same_batch(const struct ublk_io *io,
+					     const struct ublk_io *io2)
+{
+	return (io_uring_cmd_ctx_handle(io->cmd) ==
+		io_uring_cmd_ctx_handle(io2->cmd)) &&
+		(io->task == io2->task);
+}
+
 static void ublk_queue_rqs(struct rq_list *rqlist)
 {
 	struct rq_list requeue_list = { };
@@ -1427,7 +1435,8 @@ static void ublk_queue_rqs(struct rq_list *rqlist)
 		struct ublk_queue *this_q = req->mq_hctx->driver_data;
 		struct ublk_io *this_io = &this_q->ios[req->tag];
 
-		if (io && io->task != this_io->task && !rq_list_empty(&submit_list))
+		if (io && !ublk_belong_to_same_batch(io, this_io) &&
+				!rq_list_empty(&submit_list))
 			ublk_queue_cmd_list(io, &submit_list);
 		io = this_io;
 

From 5223372e672eaa576c892984b438875426d8ff2b Mon Sep 17 00:00:00 2001
From: Ming Lei <ming.lei@redhat.com>
Date: Mon, 23 Jun 2025 09:19:27 +0800
Subject: [PATCH 0820/1334] selftests: ublk: don't take same backing file for
 more than one ublk devices

Don't use same backing file for more than one ublk devices, and avoid
concurrent write on same file from more ublk disks.

Fixes: 8ccebc19ee3d ("selftests: ublk: support UBLK_F_AUTO_BUF_REG")
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/20250623011934.741788-3-ming.lei@redhat.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 tools/testing/selftests/ublk/test_stress_03.sh | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/ublk/test_stress_03.sh b/tools/testing/selftests/ublk/test_stress_03.sh
index 6eef282d569f..3ed4c9b2d8c0 100755
--- a/tools/testing/selftests/ublk/test_stress_03.sh
+++ b/tools/testing/selftests/ublk/test_stress_03.sh
@@ -32,22 +32,23 @@ _create_backfile 2 128M
 ublk_io_and_remove 8G -t null -q 4 -z &
 ublk_io_and_remove 256M -t loop -q 4 -z "${UBLK_BACKFILES[0]}" &
 ublk_io_and_remove 256M -t stripe -q 4 -z "${UBLK_BACKFILES[1]}" "${UBLK_BACKFILES[2]}" &
+wait
 
 if _have_feature "AUTO_BUF_REG"; then
 	ublk_io_and_remove 8G -t null -q 4 --auto_zc &
 	ublk_io_and_remove 256M -t loop -q 4 --auto_zc "${UBLK_BACKFILES[0]}" &
 	ublk_io_and_remove 256M -t stripe -q 4 --auto_zc "${UBLK_BACKFILES[1]}" "${UBLK_BACKFILES[2]}" &
 	ublk_io_and_remove 8G -t null -q 4 -z --auto_zc --auto_zc_fallback &
+	wait
 fi
-wait
 
 if _have_feature "PER_IO_DAEMON"; then
 	ublk_io_and_remove 8G -t null -q 4 --auto_zc --nthreads 8 --per_io_tasks &
 	ublk_io_and_remove 256M -t loop -q 4 --auto_zc --nthreads 8 --per_io_tasks "${UBLK_BACKFILES[0]}" &
 	ublk_io_and_remove 256M -t stripe -q 4 --auto_zc --nthreads 8 --per_io_tasks "${UBLK_BACKFILES[1]}" "${UBLK_BACKFILES[2]}" &
 	ublk_io_and_remove 8G -t null -q 4 -z --auto_zc --auto_zc_fallback --nthreads 8 --per_io_tasks &
+	wait
 fi
-wait
 
 _cleanup_test "stress"
 _show_result $TID $ERR_CODE

From 67caa528ae08cd05e485c0ea6aea0baaf6579b06 Mon Sep 17 00:00:00 2001
From: Caleb Sander Mateos <csander@purestorage.com>
Date: Sat, 21 Jun 2025 10:28:41 -0600
Subject: [PATCH 0821/1334] ublk: fix narrowing warnings in UAPI header

When a C++ file compiled with -Wc++11-narrowing includes the UAPI header
linux/ublk_cmd.h, ublk_sqe_addr_to_auto_buf_reg()'s assignments of u64
values to u8, u16, and u32 fields result in compiler warnings. Add
explicit casts to the intended types to avoid these warnings. Drop the
unnecessary bitmasks.

Reported-by: Uday Shankar <ushankar@purestorage.com>
Signed-off-by: Caleb Sander Mateos <csander@purestorage.com>
Fixes: 99c1e4eb6a3f ("ublk: register buffer to local io_uring with provided buf index via UBLK_F_AUTO_BUF_REG")
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/20250621162842.337452-1-csander@purestorage.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/uapi/linux/ublk_cmd.h | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/include/uapi/linux/ublk_cmd.h b/include/uapi/linux/ublk_cmd.h
index 77d9d6af46da..c062109cb686 100644
--- a/include/uapi/linux/ublk_cmd.h
+++ b/include/uapi/linux/ublk_cmd.h
@@ -450,10 +450,10 @@ static inline struct ublk_auto_buf_reg ublk_sqe_addr_to_auto_buf_reg(
 		__u64 sqe_addr)
 {
 	struct ublk_auto_buf_reg reg = {
-		.index = sqe_addr & 0xffff,
-		.flags = (sqe_addr >> 16) & 0xff,
-		.reserved0 = (sqe_addr >> 24) & 0xff,
-		.reserved1 = sqe_addr >> 32,
+		.index = (__u16)sqe_addr,
+		.flags = (__u8)(sqe_addr >> 16),
+		.reserved0 = (__u8)(sqe_addr >> 24),
+		.reserved1 = (__u32)(sqe_addr >> 32),
 	};
 
 	return reg;

From 81b4d1a1d03301dcca8af5c58eded9e535f1f6ed Mon Sep 17 00:00:00 2001
From: Caleb Sander Mateos <csander@purestorage.com>
Date: Sat, 21 Jun 2025 11:10:14 -0600
Subject: [PATCH 0822/1334] ublk: update UBLK_F_SUPPORT_ZERO_COPY comment in
 UAPI header

UBLK_F_SUPPORT_ZERO_COPY has a very old comment describing the initial
idea for how zero-copy would be implemented. The actual implementation
added in commit 1f6540e2aabb ("ublk: zc register/unregister bvec") uses
io_uring registered buffers rather than shared memory mapping.
Remove the inaccurate remarks about mapping ublk request memory into the
ublk server's address space and requiring 4K block size. Replace them
with a description of the current zero-copy mechanism.

Signed-off-by: Caleb Sander Mateos <csander@purestorage.com>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/20250621171015.354932-1-csander@purestorage.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/uapi/linux/ublk_cmd.h | 24 ++++++++++++++++++++++--
 1 file changed, 22 insertions(+), 2 deletions(-)

diff --git a/include/uapi/linux/ublk_cmd.h b/include/uapi/linux/ublk_cmd.h
index c062109cb686..c9751bdfd937 100644
--- a/include/uapi/linux/ublk_cmd.h
+++ b/include/uapi/linux/ublk_cmd.h
@@ -135,8 +135,28 @@
 #define UBLKSRV_IO_BUF_TOTAL_SIZE	(1ULL << UBLKSRV_IO_BUF_TOTAL_BITS)
 
 /*
- * zero copy requires 4k block size, and can remap ublk driver's io
- * request into ublksrv's vm space
+ * ublk server can register data buffers for incoming I/O requests with a sparse
+ * io_uring buffer table. The request buffer can then be used as the data buffer
+ * for io_uring operations via the fixed buffer index.
+ * Note that the ublk server can never directly access the request data memory.
+ *
+ * To use this feature, the ublk server must first register a sparse buffer
+ * table on an io_uring instance.
+ * When an incoming ublk request is received, the ublk server submits a
+ * UBLK_U_IO_REGISTER_IO_BUF command to that io_uring instance. The
+ * ublksrv_io_cmd's q_id and tag specify the request whose buffer to register
+ * and addr is the index in the io_uring's buffer table to install the buffer.
+ * SQEs can now be submitted to the io_uring to read/write the request's buffer
+ * by enabling fixed buffers (e.g. using IORING_OP_{READ,WRITE}_FIXED or
+ * IORING_URING_CMD_FIXED) and passing the registered buffer index in buf_index.
+ * Once the last io_uring operation using the request's buffer has completed,
+ * the ublk server submits a UBLK_U_IO_UNREGISTER_IO_BUF command with q_id, tag,
+ * and addr again specifying the request buffer to unregister.
+ * The ublk request is completed when its buffer is unregistered from all
+ * io_uring instances and the ublk server issues UBLK_U_IO_COMMIT_AND_FETCH_REQ.
+ *
+ * Not available for UBLK_F_UNPRIVILEGED_DEV, as a ublk server can leak
+ * uninitialized kernel memory by not reading into the full request buffer.
  */
 #define UBLK_F_SUPPORT_ZERO_COPY	(1ULL << 0)
 

From 4c8a951787ffc4b61a547db9866196104971b5fd Mon Sep 17 00:00:00 2001
From: Ming Lei <ming.lei@redhat.com>
Date: Tue, 24 Jun 2025 18:41:21 +0800
Subject: [PATCH 0823/1334] ublk: setup ublk_io correctly in case of
 ublk_get_data() failure

If ublk_get_data() fails, -EIOCBQUEUED is returned and the current command
becomes ASYNC. And the only reason is that mapping data can't move on,
because of no enough pages or pending signal, then the current ublk request
has to be requeued.

Once the request need to be requeued, we have to setup `ublk_io` correctly,
including io->cmd and flags, otherwise the request may not be forwarded to
ublk server successfully.

Fixes: 9810362a57cb ("ublk: don't call ublk_dispatch_req() for NEED_GET_DATA")
Reported-by: Changhui Zhong <czhong@redhat.com>
Closes: https://lore.kernel.org/linux-block/CAGVVp+VN9QcpHUz_0nasFf5q9i1gi8H8j-G-6mkBoqa3TyjRHA@mail.gmail.com/
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Tested-by: Changhui Zhong <czhong@redhat.com>
Link: https://lore.kernel.org/r/20250624104121.859519-1-ming.lei@redhat.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/ublk_drv.c | 35 +++++++++++++++++++++++++----------
 1 file changed, 25 insertions(+), 10 deletions(-)

diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c
index 90c02ced392a..d441d3259edb 100644
--- a/drivers/block/ublk_drv.c
+++ b/drivers/block/ublk_drv.c
@@ -1148,8 +1148,8 @@ exit:
 	blk_mq_end_request(req, res);
 }
 
-static void ublk_complete_io_cmd(struct ublk_io *io, struct request *req,
-				 int res, unsigned issue_flags)
+static struct io_uring_cmd *__ublk_prep_compl_io_cmd(struct ublk_io *io,
+						     struct request *req)
 {
 	/* read cmd first because req will overwrite it */
 	struct io_uring_cmd *cmd = io->cmd;
@@ -1164,6 +1164,13 @@ static void ublk_complete_io_cmd(struct ublk_io *io, struct request *req,
 	io->flags &= ~UBLK_IO_FLAG_ACTIVE;
 
 	io->req = req;
+	return cmd;
+}
+
+static void ublk_complete_io_cmd(struct ublk_io *io, struct request *req,
+				 int res, unsigned issue_flags)
+{
+	struct io_uring_cmd *cmd = __ublk_prep_compl_io_cmd(io, req);
 
 	/* tell ublksrv one io request is coming */
 	io_uring_cmd_done(cmd, res, 0, issue_flags);
@@ -2157,10 +2164,9 @@ static int ublk_commit_and_fetch(const struct ublk_queue *ubq,
 	return 0;
 }
 
-static bool ublk_get_data(const struct ublk_queue *ubq, struct ublk_io *io)
+static bool ublk_get_data(const struct ublk_queue *ubq, struct ublk_io *io,
+			  struct request *req)
 {
-	struct request *req = io->req;
-
 	/*
 	 * We have handled UBLK_IO_NEED_GET_DATA command,
 	 * so clear UBLK_IO_FLAG_NEED_GET_DATA now and just
@@ -2187,6 +2193,7 @@ static int __ublk_ch_uring_cmd(struct io_uring_cmd *cmd,
 	u32 cmd_op = cmd->cmd_op;
 	unsigned tag = ub_cmd->tag;
 	int ret = -EINVAL;
+	struct request *req;
 
 	pr_devel("%s: received: cmd op %d queue %d tag %d result %d\n",
 			__func__, cmd->cmd_op, ub_cmd->q_id, tag,
@@ -2245,11 +2252,19 @@ static int __ublk_ch_uring_cmd(struct io_uring_cmd *cmd,
 			goto out;
 		break;
 	case UBLK_IO_NEED_GET_DATA:
-		io->addr = ub_cmd->addr;
-		if (!ublk_get_data(ubq, io))
-			return -EIOCBQUEUED;
-
-		return UBLK_IO_RES_OK;
+		/*
+		 * ublk_get_data() may fail and fallback to requeue, so keep
+		 * uring_cmd active first and prepare for handling new requeued
+		 * request
+		 */
+		req = io->req;
+		ublk_fill_io_cmd(io, cmd, ub_cmd->addr);
+		io->flags &= ~UBLK_IO_FLAG_OWNED_BY_SRV;
+		if (likely(ublk_get_data(ubq, io, req))) {
+			__ublk_prep_compl_io_cmd(io, req);
+			return UBLK_IO_RES_OK;
+		}
+		break;
 	default:
 		goto out;
 	}

From 5afb4bf9fc62d828647647ec31745083637132e4 Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Tue, 24 Jun 2025 14:40:33 +0100
Subject: [PATCH 0824/1334] io_uring/rsrc: fix folio unpinning

syzbot complains about an unmapping failure:

[  108.070381][   T14] kernel BUG at mm/gup.c:71!
[  108.070502][   T14] Internal error: Oops - BUG: 00000000f2000800 [#1]  SMP
[  108.123672][   T14] Hardware name: QEMU KVM Virtual Machine, BIOS edk2-20250221-8.fc42 02/21/2025
[  108.127458][   T14] Workqueue: iou_exit io_ring_exit_work
[  108.174205][   T14] Call trace:
[  108.175649][   T14]  sanity_check_pinned_pages+0x7cc/0x7d0 (P)
[  108.178138][   T14]  unpin_user_page+0x80/0x10c
[  108.180189][   T14]  io_release_ubuf+0x84/0xf8
[  108.182196][   T14]  io_free_rsrc_node+0x250/0x57c
[  108.184345][   T14]  io_rsrc_data_free+0x148/0x298
[  108.186493][   T14]  io_sqe_buffers_unregister+0x84/0xa0
[  108.188991][   T14]  io_ring_ctx_free+0x48/0x480
[  108.191057][   T14]  io_ring_exit_work+0x764/0x7d8
[  108.193207][   T14]  process_one_work+0x7e8/0x155c
[  108.195431][   T14]  worker_thread+0x958/0xed8
[  108.197561][   T14]  kthread+0x5fc/0x75c
[  108.199362][   T14]  ret_from_fork+0x10/0x20

We can pin a tail page of a folio, but then io_uring will try to unpin
the head page of the folio. While it should be fine in terms of keeping
the page actually alive, mm folks say it's wrong and triggers a debug
warning. Use unpin_user_folio() instead of unpin_user_page*.

Cc: stable@vger.kernel.org
Debugged-by: David Hildenbrand <david@redhat.com>
Reported-by: syzbot+1d335893772467199ab6@syzkaller.appspotmail.com
Closes: https://lkml.kernel.org/r/683f1551.050a0220.55ceb.0017.GAE@google.com
Fixes: a8edbb424b139 ("io_uring/rsrc: enable multi-hugepage buffer coalescing")
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/io-uring/a28b0f87339ac2acf14a645dad1e95bbcbf18acd.1750771718.git.asml.silence@gmail.com/
[axboe: adapt to current tree, massage commit message]
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/rsrc.c | 13 +++++++++----
 1 file changed, 9 insertions(+), 4 deletions(-)

diff --git a/io_uring/rsrc.c b/io_uring/rsrc.c
index d724602697e7..0c09e38784c9 100644
--- a/io_uring/rsrc.c
+++ b/io_uring/rsrc.c
@@ -112,8 +112,11 @@ static void io_release_ubuf(void *priv)
 	struct io_mapped_ubuf *imu = priv;
 	unsigned int i;
 
-	for (i = 0; i < imu->nr_bvecs; i++)
-		unpin_user_page(imu->bvec[i].bv_page);
+	for (i = 0; i < imu->nr_bvecs; i++) {
+		struct folio *folio = page_folio(imu->bvec[i].bv_page);
+
+		unpin_user_folio(folio, 1);
+	}
 }
 
 static struct io_mapped_ubuf *io_alloc_imu(struct io_ring_ctx *ctx,
@@ -840,8 +843,10 @@ done:
 	if (ret) {
 		if (imu)
 			io_free_imu(ctx, imu);
-		if (pages)
-			unpin_user_pages(pages, nr_pages);
+		if (pages) {
+			for (i = 0; i < nr_pages; i++)
+				unpin_user_folio(page_folio(pages[i]), 1);
+		}
 		io_cache_free(&ctx->node_cache, node);
 		node = ERR_PTR(ret);
 	}

From 3a3c6d61577dbb23c09df3e21f6f9eda1ecd634b Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Tue, 24 Jun 2025 14:40:34 +0100
Subject: [PATCH 0825/1334] io_uring/rsrc: don't rely on user vaddr alignment

There is no guaranteed alignment for user pointers, however the
calculation of an offset of the first page into a folio after coalescing
uses some weird bit mask logic, get rid of it.

Cc: stable@vger.kernel.org
Reported-by: David Hildenbrand <david@redhat.com>
Fixes: a8edbb424b139 ("io_uring/rsrc: enable multi-hugepage buffer coalescing")
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/io-uring/e387b4c78b33f231105a601d84eefd8301f57954.1750771718.git.asml.silence@gmail.com/
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/rsrc.c | 7 ++++++-
 io_uring/rsrc.h | 1 +
 2 files changed, 7 insertions(+), 1 deletion(-)

diff --git a/io_uring/rsrc.c b/io_uring/rsrc.c
index 0c09e38784c9..afc67530f912 100644
--- a/io_uring/rsrc.c
+++ b/io_uring/rsrc.c
@@ -734,6 +734,7 @@ bool io_check_coalesce_buffer(struct page **page_array, int nr_pages,
 
 	data->nr_pages_mid = folio_nr_pages(folio);
 	data->folio_shift = folio_shift(folio);
+	data->first_folio_page_idx = folio_page_idx(folio, page_array[0]);
 
 	/*
 	 * Check if pages are contiguous inside a folio, and all folios have
@@ -827,7 +828,11 @@ static struct io_rsrc_node *io_sqe_buffer_register(struct io_ring_ctx *ctx,
 	if (coalesced)
 		imu->folio_shift = data.folio_shift;
 	refcount_set(&imu->refs, 1);
-	off = (unsigned long) iov->iov_base & ((1UL << imu->folio_shift) - 1);
+
+	off = (unsigned long)iov->iov_base & ~PAGE_MASK;
+	if (coalesced)
+		off += data.first_folio_page_idx << PAGE_SHIFT;
+
 	node->buf = imu;
 	ret = 0;
 
diff --git a/io_uring/rsrc.h b/io_uring/rsrc.h
index 0d2138f16322..25e7e998dcfd 100644
--- a/io_uring/rsrc.h
+++ b/io_uring/rsrc.h
@@ -49,6 +49,7 @@ struct io_imu_folio_data {
 	unsigned int	nr_pages_mid;
 	unsigned int	folio_shift;
 	unsigned int	nr_folios;
+	unsigned long	first_folio_page_idx;
 };
 
 bool io_rsrc_cache_init(struct io_ring_ctx *ctx);

From e1d7727b73a1f78035316ac35ee184d477059f0b Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Tue, 24 Jun 2025 14:40:35 +0100
Subject: [PATCH 0826/1334] io_uring: don't assume uaddr alignment in
 io_vec_fill_bvec

There is no guaranteed alignment for user pointers. Don't use mask
trickery and adjust the offset by bv_offset.

Cc: stable@vger.kernel.org
Reported-by: David Hildenbrand <david@redhat.com>
Fixes: 9ef4cbbcb4ac3 ("io_uring: add infra for importing vectored reg buffers")
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/io-uring/19530391f5c361a026ac9b401ff8e123bde55d98.1750771718.git.asml.silence@gmail.com/
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/rsrc.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/io_uring/rsrc.c b/io_uring/rsrc.c
index afc67530f912..f2b31fb68992 100644
--- a/io_uring/rsrc.c
+++ b/io_uring/rsrc.c
@@ -1339,7 +1339,6 @@ static int io_vec_fill_bvec(int ddir, struct iov_iter *iter,
 {
 	unsigned long folio_size = 1 << imu->folio_shift;
 	unsigned long folio_mask = folio_size - 1;
-	u64 folio_addr = imu->ubuf & ~folio_mask;
 	struct bio_vec *res_bvec = vec->bvec;
 	size_t total_len = 0;
 	unsigned bvec_idx = 0;
@@ -1361,8 +1360,13 @@ static int io_vec_fill_bvec(int ddir, struct iov_iter *iter,
 		if (unlikely(check_add_overflow(total_len, iov_len, &total_len)))
 			return -EOVERFLOW;
 
-		/* by using folio address it also accounts for bvec offset */
-		offset = buf_addr - folio_addr;
+		offset = buf_addr - imu->ubuf;
+		/*
+		 * Only the first bvec can have non zero bv_offset, account it
+		 * here and work with full folios below.
+		 */
+		offset += imu->bvec[0].bv_offset;
+
 		src_bvec = imu->bvec + (offset >> imu->folio_shift);
 		offset &= folio_mask;
 

From 5e9571750c4e53d16727a04159455c693d7b31cb Mon Sep 17 00:00:00 2001
From: Pei Xiao <xiaopei01@kylinos.cn>
Date: Tue, 24 Jun 2025 17:00:47 +0800
Subject: [PATCH 0827/1334] ALSA: usb: qcom: fix NULL pointer dereference in
 qmi_stop_session

The find_substream() call may return NULL, but the error path
dereferenced 'subs' unconditionally via dev_err(&subs->dev->dev, ...),
causing a NULL pointer dereference when subs is NULL.

Fix by switching to &uadev[idx].udev->dev which is always valid
in this context.

Signed-off-by: Pei Xiao <xiaopei01@kylinos.cn>
Link: https://patch.msgid.link/86ac2939273ac853535049e60391c09d7688714e.1750755508.git.xiaopei01@kylinos.cn
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/usb/qcom/qc_audio_offload.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/usb/qcom/qc_audio_offload.c b/sound/usb/qcom/qc_audio_offload.c
index 797afd4561bd..3543b5a53592 100644
--- a/sound/usb/qcom/qc_audio_offload.c
+++ b/sound/usb/qcom/qc_audio_offload.c
@@ -759,7 +759,7 @@ static void qmi_stop_session(void)
 			subs = find_substream(pcm_card_num, info->pcm_dev_num,
 					      info->direction);
 			if (!subs || !chip || atomic_read(&chip->shutdown)) {
-				dev_err(&subs->dev->dev,
+				dev_err(&uadev[idx].udev->dev,
 					"no sub for c#%u dev#%u dir%u\n",
 					info->pcm_card_num,
 					info->pcm_dev_num,

From d02b2103a08b6d6908f1d3d8e8783d3f342555ac Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Fri, 20 Jun 2025 13:18:18 +0200
Subject: [PATCH 0828/1334] drm/i915: fix build error some more

An earlier patch fixed a build failure with clang, but I still see the
same problem with some configurations using gcc:

drivers/gpu/drm/i915/i915_pmu.c: In function 'config_mask':
include/linux/compiler_types.h:568:38: error: call to '__compiletime_assert_462' declared with attribute error: BUILD_BUG_ON failed: bit > BITS_PER_TYPE(typeof_member(struct i915_pmu, enable)) - 1
drivers/gpu/drm/i915/i915_pmu.c:116:3: note: in expansion of macro 'BUILD_BUG_ON'
  116 |   BUILD_BUG_ON(bit >

As I understand it, the problem is that the function is not always fully
inlined, but the __builtin_constant_p() can still evaluate the argument
as being constant.

Marking it as __always_inline so far works for me in all configurations.

Fixes: a7137b1825b5 ("drm/i915/pmu: Fix build error with GCOV and AutoFDO enabled")
Fixes: a644fde77ff7 ("drm/i915/pmu: Change bitmask of enabled events to u32")
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Link: https://lore.kernel.org/r/20250620111824.3395007-1-arnd@kernel.org
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
(cherry picked from commit ef69f9dd1cd7301cdf04ba326ed28152a3affcf6)
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
---
 drivers/gpu/drm/i915/i915_pmu.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/i915_pmu.c b/drivers/gpu/drm/i915/i915_pmu.c
index 990bfaba3ce4..5bc696bfbb0f 100644
--- a/drivers/gpu/drm/i915/i915_pmu.c
+++ b/drivers/gpu/drm/i915/i915_pmu.c
@@ -108,7 +108,7 @@ static unsigned int config_bit(const u64 config)
 		return other_bit(config);
 }
 
-static u32 config_mask(const u64 config)
+static __always_inline u32 config_mask(const u64 config)
 {
 	unsigned int bit = config_bit(config);
 

From c55c7a85e02a7bfee20a3ffebdff7cbeb41613ef Mon Sep 17 00:00:00 2001
From: Tiwei Bie <tiwei.btw@antgroup.com>
Date: Fri, 6 Jun 2025 20:44:25 +0800
Subject: [PATCH 0829/1334] um: ubd: Add missing error check in
 start_io_thread()

The subsequent call to os_set_fd_block() overwrites the previous
return value. OR the two return values together to fix it.

Fixes: f88f0bdfc32f ("um: UBD Improvements")
Signed-off-by: Tiwei Bie <tiwei.btw@antgroup.com>
Link: https://patch.msgid.link/20250606124428.148164-2-tiwei.btw@antgroup.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 arch/um/drivers/ubd_user.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/um/drivers/ubd_user.c b/arch/um/drivers/ubd_user.c
index c5e6545f6fcf..8e8a8bf518b6 100644
--- a/arch/um/drivers/ubd_user.c
+++ b/arch/um/drivers/ubd_user.c
@@ -41,7 +41,7 @@ int start_io_thread(struct os_helper_thread **td_out, int *fd_out)
 	*fd_out = fds[1];
 
 	err = os_set_fd_block(*fd_out, 0);
-	err = os_set_fd_block(kernel_fd, 0);
+	err |= os_set_fd_block(kernel_fd, 0);
 	if (err) {
 		printk("start_io_thread - failed to set nonblocking I/O.\n");
 		goto out_close;

From bc4e2ae08183d9017f43bf88aa7cfdf84e76f573 Mon Sep 17 00:00:00 2001
From: Tiwei Bie <tiwei.btw@antgroup.com>
Date: Fri, 6 Jun 2025 20:44:27 +0800
Subject: [PATCH 0830/1334] um: vfio: Prevent duplicate device assignments

Ensure devices are assigned only once. Reject subsequent requests
for duplicate assignments.

Fixes: a0e2cb6a9063 ("um: Add VFIO-based virtual PCI driver")
Signed-off-by: Tiwei Bie <tiwei.btw@antgroup.com>
Link: https://patch.msgid.link/20250606124428.148164-4-tiwei.btw@antgroup.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 arch/um/drivers/vfio_kern.c | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/arch/um/drivers/vfio_kern.c b/arch/um/drivers/vfio_kern.c
index b51fc9888ae1..13b971a2bd43 100644
--- a/arch/um/drivers/vfio_kern.c
+++ b/arch/um/drivers/vfio_kern.c
@@ -570,6 +570,17 @@ static void uml_vfio_release_device(struct uml_vfio_device *dev)
 	kfree(dev);
 }
 
+static struct uml_vfio_device *uml_vfio_find_device(const char *device)
+{
+	struct uml_vfio_device *dev;
+
+	list_for_each_entry(dev, &uml_vfio_devices, list) {
+		if (!strcmp(dev->name, device))
+			return dev;
+	}
+	return NULL;
+}
+
 static int uml_vfio_cmdline_set(const char *device, const struct kernel_param *kp)
 {
 	struct uml_vfio_device *dev;
@@ -582,6 +593,9 @@ static int uml_vfio_cmdline_set(const char *device, const struct kernel_param *k
 		uml_vfio_container.fd = fd;
 	}
 
+	if (uml_vfio_find_device(device))
+		return -EEXIST;
+
 	dev = kzalloc(sizeof(*dev), GFP_KERNEL);
 	if (!dev)
 		return -ENOMEM;

From 8948941276024fcfb08fdb3d678867dc1f7b1c16 Mon Sep 17 00:00:00 2001
From: Tiwei Bie <tiwei.btw@antgroup.com>
Date: Fri, 6 Jun 2025 20:44:28 +0800
Subject: [PATCH 0831/1334] um: Use correct data source in fpregs_legacy_set()

Read from the buffer pointed to by 'from' instead of '&buf', as
'buf' contains no valid data when 'ubuf' is NULL.

Fixes: b1e1bd2e6943 ("um: Add helper functions to get/set state for SECCOMP")
Signed-off-by: Tiwei Bie <tiwei.btw@antgroup.com>
Link: https://patch.msgid.link/20250606124428.148164-5-tiwei.btw@antgroup.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 arch/x86/um/ptrace.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/um/ptrace.c b/arch/x86/um/ptrace.c
index 3275870330fe..fae8aabad10f 100644
--- a/arch/x86/um/ptrace.c
+++ b/arch/x86/um/ptrace.c
@@ -161,7 +161,7 @@ static int fpregs_legacy_set(struct task_struct *target,
 		from = kbuf;
 	}
 
-	return um_fxsr_from_i387(fxsave, &buf);
+	return um_fxsr_from_i387(fxsave, from);
 }
 #endif
 

From 2d65fc13be85c336c56af7077f08ccd3a3a15a4a Mon Sep 17 00:00:00 2001
From: Tiwei Bie <tiwei.btw@antgroup.com>
Date: Mon, 23 Jun 2025 19:08:29 +0800
Subject: [PATCH 0832/1334] um: vector: Reduce stack usage in
 vector_eth_configure()

When compiling with clang (19.1.7), initializing *vp using a compound
literal may result in excessive stack usage. Fix it by initializing the
required fields of *vp individually.

Without this patch:

$ objdump -d arch/um/drivers/vector_kern.o | ./scripts/checkstack.pl x86_64 0
...
0x0000000000000540 vector_eth_configure [vector_kern.o]:1472
...

With this patch:

$ objdump -d arch/um/drivers/vector_kern.o | ./scripts/checkstack.pl x86_64 0
...
0x0000000000000540 vector_eth_configure [vector_kern.o]:208
...

Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202506221017.WtB7Usua-lkp@intel.com/
Signed-off-by: Tiwei Bie <tiwei.btw@antgroup.com>
Link: https://patch.msgid.link/20250623110829.314864-1-tiwei.btw@antgroup.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 arch/um/drivers/vector_kern.c | 42 +++++++++++------------------------
 1 file changed, 13 insertions(+), 29 deletions(-)

diff --git a/arch/um/drivers/vector_kern.c b/arch/um/drivers/vector_kern.c
index f292e0b4ff8b..9bbbddfe866b 100644
--- a/arch/um/drivers/vector_kern.c
+++ b/arch/um/drivers/vector_kern.c
@@ -1625,35 +1625,19 @@ static void vector_eth_configure(
 
 	device->dev = dev;
 
-	*vp = ((struct vector_private)
-		{
-		.list			= LIST_HEAD_INIT(vp->list),
-		.dev			= dev,
-		.unit			= n,
-		.options		= get_transport_options(def),
-		.rx_irq			= 0,
-		.tx_irq			= 0,
-		.parsed			= def,
-		.max_packet		= get_mtu(def) + ETH_HEADER_OTHER,
-		/* TODO - we need to calculate headroom so that ip header
-		 * is 16 byte aligned all the time
-		 */
-		.headroom		= get_headroom(def),
-		.form_header		= NULL,
-		.verify_header		= NULL,
-		.header_rxbuffer	= NULL,
-		.header_txbuffer	= NULL,
-		.header_size		= 0,
-		.rx_header_size		= 0,
-		.rexmit_scheduled	= false,
-		.opened			= false,
-		.transport_data		= NULL,
-		.in_write_poll		= false,
-		.coalesce		= 2,
-		.req_size		= get_req_size(def),
-		.in_error		= false,
-		.bpf			= NULL
-	});
+	INIT_LIST_HEAD(&vp->list);
+	vp->dev		= dev;
+	vp->unit	= n;
+	vp->options	= get_transport_options(def);
+	vp->parsed	= def;
+	vp->max_packet	= get_mtu(def) + ETH_HEADER_OTHER;
+	/*
+	 * TODO - we need to calculate headroom so that ip header
+	 * is 16 byte aligned all the time
+	 */
+	vp->headroom	= get_headroom(def);
+	vp->coalesce	= 2;
+	vp->req_size	= get_req_size(def);
 
 	dev->features = dev->hw_features = (NETIF_F_SG | NETIF_F_FRAGLIST);
 	INIT_WORK(&vp->reset_tx, vector_reset_tx);

From 2ed25aa7f7711f508b6120e336f05cd9d49943c0 Mon Sep 17 00:00:00 2001
From: Or Har-Toov <ohartoov@nvidia.com>
Date: Mon, 16 Jun 2025 11:14:09 +0300
Subject: [PATCH 0833/1334] IB/mlx5: Fix potential deadlock in MR
 deregistration
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The issue arises when kzalloc() is invoked while holding umem_mutex or
any other lock acquired under umem_mutex. This is problematic because
kzalloc() can trigger fs_reclaim_aqcuire(), which may, in turn, invoke
mmu_notifier_invalidate_range_start(). This function can lead to
mlx5_ib_invalidate_range(), which attempts to acquire umem_mutex again,
resulting in a deadlock.

The problematic flow:
             CPU0                      |              CPU1
---------------------------------------|------------------------------------------------
mlx5_ib_dereg_mr()                     |
 → revoke_mr()                         |
   → mutex_lock(&umem_odp->umem_mutex) |
                                       | mlx5_mkey_cache_init()
                                       |  → mutex_lock(&dev->cache.rb_lock)
                                       |  → mlx5r_cache_create_ent_locked()
                                       |    → kzalloc(GFP_KERNEL)
                                       |      → fs_reclaim()
                                       |        → mmu_notifier_invalidate_range_start()
                                       |          → mlx5_ib_invalidate_range()
                                       |            → mutex_lock(&umem_odp->umem_mutex)
   → cache_ent_find_and_store()        |
     → mutex_lock(&dev->cache.rb_lock) |

Additionally, when kzalloc() is called from within
cache_ent_find_and_store(), we encounter the same deadlock due to
re-acquisition of umem_mutex.

Solve by releasing umem_mutex in dereg_mr() after umr_revoke_mr()
and before acquiring rb_lock. This ensures that we don't hold
umem_mutex while performing memory allocations that could trigger
the reclaim path.

This change prevents the deadlock by ensuring proper lock ordering and
avoiding holding locks during memory allocation operations that could
trigger the reclaim path.

The following lockdep warning demonstrates the deadlock:

 python3/20557 is trying to acquire lock:
 ffff888387542128 (&umem_odp->umem_mutex){+.+.}-{4:4}, at:
 mlx5_ib_invalidate_range+0x5b/0x550 [mlx5_ib]

 but task is already holding lock:
 ffffffff82f6b840 (mmu_notifier_invalidate_range_start){+.+.}-{0:0}, at:
 unmap_vmas+0x7b/0x1a0

 which lock already depends on the new lock.

 the existing dependency chain (in reverse order) is:

 -> #3 (mmu_notifier_invalidate_range_start){+.+.}-{0:0}:
       fs_reclaim_acquire+0x60/0xd0
       mem_cgroup_css_alloc+0x6f/0x9b0
       cgroup_init_subsys+0xa4/0x240
       cgroup_init+0x1c8/0x510
       start_kernel+0x747/0x760
       x86_64_start_reservations+0x25/0x30
       x86_64_start_kernel+0x73/0x80
       common_startup_64+0x129/0x138

 -> #2 (fs_reclaim){+.+.}-{0:0}:
       fs_reclaim_acquire+0x91/0xd0
       __kmalloc_cache_noprof+0x4d/0x4c0
       mlx5r_cache_create_ent_locked+0x75/0x620 [mlx5_ib]
       mlx5_mkey_cache_init+0x186/0x360 [mlx5_ib]
       mlx5_ib_stage_post_ib_reg_umr_init+0x3c/0x60 [mlx5_ib]
       __mlx5_ib_add+0x4b/0x190 [mlx5_ib]
       mlx5r_probe+0xd9/0x320 [mlx5_ib]
       auxiliary_bus_probe+0x42/0x70
       really_probe+0xdb/0x360
       __driver_probe_device+0x8f/0x130
       driver_probe_device+0x1f/0xb0
       __driver_attach+0xd4/0x1f0
       bus_for_each_dev+0x79/0xd0
       bus_add_driver+0xf0/0x200
       driver_register+0x6e/0xc0
       __auxiliary_driver_register+0x6a/0xc0
       do_one_initcall+0x5e/0x390
       do_init_module+0x88/0x240
       init_module_from_file+0x85/0xc0
       idempotent_init_module+0x104/0x300
       __x64_sys_finit_module+0x68/0xc0
       do_syscall_64+0x6d/0x140
       entry_SYSCALL_64_after_hwframe+0x4b/0x53

 -> #1 (&dev->cache.rb_lock){+.+.}-{4:4}:
       __mutex_lock+0x98/0xf10
       __mlx5_ib_dereg_mr+0x6f2/0x890 [mlx5_ib]
       mlx5_ib_dereg_mr+0x21/0x110 [mlx5_ib]
       ib_dereg_mr_user+0x85/0x1f0 [ib_core]
       uverbs_free_mr+0x19/0x30 [ib_uverbs]
       destroy_hw_idr_uobject+0x21/0x80 [ib_uverbs]
       uverbs_destroy_uobject+0x60/0x3d0 [ib_uverbs]
       uobj_destroy+0x57/0xa0 [ib_uverbs]
       ib_uverbs_cmd_verbs+0x4d5/0x1210 [ib_uverbs]
       ib_uverbs_ioctl+0x129/0x230 [ib_uverbs]
       __x64_sys_ioctl+0x596/0xaa0
       do_syscall_64+0x6d/0x140
       entry_SYSCALL_64_after_hwframe+0x4b/0x53

 -> #0 (&umem_odp->umem_mutex){+.+.}-{4:4}:
       __lock_acquire+0x1826/0x2f00
       lock_acquire+0xd3/0x2e0
       __mutex_lock+0x98/0xf10
       mlx5_ib_invalidate_range+0x5b/0x550 [mlx5_ib]
       __mmu_notifier_invalidate_range_start+0x18e/0x1f0
       unmap_vmas+0x182/0x1a0
       exit_mmap+0xf3/0x4a0
       mmput+0x3a/0x100
       do_exit+0x2b9/0xa90
       do_group_exit+0x32/0xa0
       get_signal+0xc32/0xcb0
       arch_do_signal_or_restart+0x29/0x1d0
       syscall_exit_to_user_mode+0x105/0x1d0
       do_syscall_64+0x79/0x140
       entry_SYSCALL_64_after_hwframe+0x4b/0x53

 Chain exists of:
 &dev->cache.rb_lock --> mmu_notifier_invalidate_range_start -->
 &umem_odp->umem_mutex

 Possible unsafe locking scenario:

       CPU0                        CPU1
       ----                        ----
   lock(&umem_odp->umem_mutex);
                                lock(mmu_notifier_invalidate_range_start);
                                lock(&umem_odp->umem_mutex);
   lock(&dev->cache.rb_lock);

 *** DEADLOCK ***

Fixes: abb604a1a9c8 ("RDMA/mlx5: Fix a race for an ODP MR which leads to CQE with error")
Signed-off-by: Or Har-Toov <ohartoov@nvidia.com>
Reviewed-by: Michael Guralnik <michaelgur@nvidia.com>
Link: https://patch.msgid.link/3c8f225a8a9fade647d19b014df1172544643e4a.1750061612.git.leon@kernel.org
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/hw/mlx5/mr.c | 61 +++++++++++++++++++++++++--------
 1 file changed, 47 insertions(+), 14 deletions(-)

diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c
index 57f9bc2a4a3a..bd35e75d9ce5 100644
--- a/drivers/infiniband/hw/mlx5/mr.c
+++ b/drivers/infiniband/hw/mlx5/mr.c
@@ -2027,23 +2027,50 @@ void mlx5_ib_revoke_data_direct_mrs(struct mlx5_ib_dev *dev)
 	}
 }
 
-static int mlx5_revoke_mr(struct mlx5_ib_mr *mr)
+static int mlx5_umr_revoke_mr_with_lock(struct mlx5_ib_mr *mr)
 {
-	struct mlx5_ib_dev *dev = to_mdev(mr->ibmr.device);
-	struct mlx5_cache_ent *ent = mr->mmkey.cache_ent;
-	bool is_odp = is_odp_mr(mr);
 	bool is_odp_dma_buf = is_dmabuf_mr(mr) &&
-			!to_ib_umem_dmabuf(mr->umem)->pinned;
-	bool from_cache = !!ent;
-	int ret = 0;
+			      !to_ib_umem_dmabuf(mr->umem)->pinned;
+	bool is_odp = is_odp_mr(mr);
+	int ret;
 
 	if (is_odp)
 		mutex_lock(&to_ib_umem_odp(mr->umem)->umem_mutex);
 
 	if (is_odp_dma_buf)
-		dma_resv_lock(to_ib_umem_dmabuf(mr->umem)->attach->dmabuf->resv, NULL);
+		dma_resv_lock(to_ib_umem_dmabuf(mr->umem)->attach->dmabuf->resv,
+			      NULL);
 
-	if (mr->mmkey.cacheable && !mlx5r_umr_revoke_mr(mr) && !cache_ent_find_and_store(dev, mr)) {
+	ret = mlx5r_umr_revoke_mr(mr);
+
+	if (is_odp) {
+		if (!ret)
+			to_ib_umem_odp(mr->umem)->private = NULL;
+		mutex_unlock(&to_ib_umem_odp(mr->umem)->umem_mutex);
+	}
+
+	if (is_odp_dma_buf) {
+		if (!ret)
+			to_ib_umem_dmabuf(mr->umem)->private = NULL;
+		dma_resv_unlock(
+			to_ib_umem_dmabuf(mr->umem)->attach->dmabuf->resv);
+	}
+
+	return ret;
+}
+
+static int mlx5r_handle_mkey_cleanup(struct mlx5_ib_mr *mr)
+{
+	bool is_odp_dma_buf = is_dmabuf_mr(mr) &&
+			      !to_ib_umem_dmabuf(mr->umem)->pinned;
+	struct mlx5_ib_dev *dev = to_mdev(mr->ibmr.device);
+	struct mlx5_cache_ent *ent = mr->mmkey.cache_ent;
+	bool is_odp = is_odp_mr(mr);
+	bool from_cache = !!ent;
+	int ret;
+
+	if (mr->mmkey.cacheable && !mlx5_umr_revoke_mr_with_lock(mr) &&
+	    !cache_ent_find_and_store(dev, mr)) {
 		ent = mr->mmkey.cache_ent;
 		/* upon storing to a clean temp entry - schedule its cleanup */
 		spin_lock_irq(&ent->mkeys_queue.lock);
@@ -2055,7 +2082,7 @@ static int mlx5_revoke_mr(struct mlx5_ib_mr *mr)
 			ent->tmp_cleanup_scheduled = true;
 		}
 		spin_unlock_irq(&ent->mkeys_queue.lock);
-		goto out;
+		return 0;
 	}
 
 	if (ent) {
@@ -2064,8 +2091,14 @@ static int mlx5_revoke_mr(struct mlx5_ib_mr *mr)
 		mr->mmkey.cache_ent = NULL;
 		spin_unlock_irq(&ent->mkeys_queue.lock);
 	}
+
+	if (is_odp)
+		mutex_lock(&to_ib_umem_odp(mr->umem)->umem_mutex);
+
+	if (is_odp_dma_buf)
+		dma_resv_lock(to_ib_umem_dmabuf(mr->umem)->attach->dmabuf->resv,
+			      NULL);
 	ret = destroy_mkey(dev, mr);
-out:
 	if (is_odp) {
 		if (!ret)
 			to_ib_umem_odp(mr->umem)->private = NULL;
@@ -2075,9 +2108,9 @@ out:
 	if (is_odp_dma_buf) {
 		if (!ret)
 			to_ib_umem_dmabuf(mr->umem)->private = NULL;
-		dma_resv_unlock(to_ib_umem_dmabuf(mr->umem)->attach->dmabuf->resv);
+		dma_resv_unlock(
+			to_ib_umem_dmabuf(mr->umem)->attach->dmabuf->resv);
 	}
-
 	return ret;
 }
 
@@ -2126,7 +2159,7 @@ static int __mlx5_ib_dereg_mr(struct ib_mr *ibmr)
 	}
 
 	/* Stop DMA */
-	rc = mlx5_revoke_mr(mr);
+	rc = mlx5r_handle_mkey_cleanup(mr);
 	if (rc)
 		return rc;
 

From 3f5f6321f129ad5a30aa03c99c196b4612be68a8 Mon Sep 17 00:00:00 2001
From: Or Har-Toov <ohartoov@nvidia.com>
Date: Mon, 16 Jun 2025 11:16:03 +0300
Subject: [PATCH 0834/1334] IB/core: Annotate umem_mutex acquisition under
 fs_reclaim for lockdep
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Following the fix in the previous commit ("IB/mlx5: Fix potential
deadlock in MR deregistration"), teach lockdep explicitly about the
locking order between fs_reclaim and umem_mutex.

The previous commit resolved a potential deadlock scenario where
kzalloc(GFP_KERNEL) was called while holding umem_mutex, which could
lead to reclaim and eventually invoke the MMU notifier
(mlx5_ib_invalidate_range()), causing a recursive acquisition of
umem_mutex.

To prevent such issues from reoccurring unnoticed in future code
changes, add a lockdep annotation in ib_init_umem_odp() that simulates
taking umem_mutex inside a reclaim context. This makes lockdep aware
of this locking dependency and ensures that future violations—such as
calling kzalloc() or any memory allocator that may enter reclaim while
holding umem_mutex—will immediately raise a lockdep warning.

Signed-off-by: Or Har-Toov <ohartoov@nvidia.com>
Reviewed-by: Michael Guralnik <michaelgur@nvidia.com>
Link: https://patch.msgid.link/9d31b9d8fe1db648a9f47cec3df6b8463319dee5.1750061698.git.leon@kernel.org
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/core/umem_odp.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/drivers/infiniband/core/umem_odp.c b/drivers/infiniband/core/umem_odp.c
index c752ae9fad6c..b1c44ec1a3f3 100644
--- a/drivers/infiniband/core/umem_odp.c
+++ b/drivers/infiniband/core/umem_odp.c
@@ -76,6 +76,17 @@ static int ib_init_umem_odp(struct ib_umem_odp *umem_odp,
 	end = ALIGN(end, page_size);
 	if (unlikely(end < page_size))
 		return -EOVERFLOW;
+	/*
+	 * The mmu notifier can be called within reclaim contexts and takes the
+	 * umem_mutex. This is rare to trigger in testing, teach lockdep about
+	 * it.
+	 */
+	if (IS_ENABLED(CONFIG_LOCKDEP)) {
+		fs_reclaim_acquire(GFP_KERNEL);
+		mutex_lock(&umem_odp->umem_mutex);
+		mutex_unlock(&umem_odp->umem_mutex);
+		fs_reclaim_release(GFP_KERNEL);
+	}
 
 	nr_entries = (end - start) >> PAGE_SHIFT;
 	if (!(nr_entries * PAGE_SIZE / page_size))

From 3cc1dbfddf88dc5ecce0a75185061403b1f7352d Mon Sep 17 00:00:00 2001
From: Patrisious Haddad <phaddad@nvidia.com>
Date: Mon, 16 Jun 2025 12:14:52 +0300
Subject: [PATCH 0835/1334] RDMA/mlx5: Fix HW counters query for
 non-representor devices

To get the device HW counters, a non-representor switchdev device
should use the mlx5_ib_query_q_counters() function and query all of
the available counters. While a representor device in switchdev mode
should use the mlx5_ib_query_q_counters_vport() function and query only
the Q_Counters without the PPCNT counters and congestion control counters,
since they aren't relevant for a representor device.

Currently a non-representor switchdev device skips querying the PPCNT
counters and congestion control counters, leaving them unupdated.
Fix that by properly querying those counters for non-representor devices.

Fixes: d22467a71ebe ("RDMA/mlx5: Expand switchdev Q-counters to expose representor statistics")
Signed-off-by: Patrisious Haddad <phaddad@nvidia.com>
Reviewed-by: Maher Sanalla <msanalla@nvidia.com>
Link: https://patch.msgid.link/56bf8af4ca8c58e3fb9f7e47b1dca2009eeeed81.1750064969.git.leon@kernel.org
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/hw/mlx5/counters.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/infiniband/hw/mlx5/counters.c b/drivers/infiniband/hw/mlx5/counters.c
index b847084dcd99..943e9eb2ad20 100644
--- a/drivers/infiniband/hw/mlx5/counters.c
+++ b/drivers/infiniband/hw/mlx5/counters.c
@@ -398,7 +398,7 @@ static int do_get_hw_stats(struct ib_device *ibdev,
 		return ret;
 
 	/* We don't expose device counters over Vports */
-	if (is_mdev_switchdev_mode(dev->mdev) && port_num != 0)
+	if (is_mdev_switchdev_mode(dev->mdev) && dev->is_rep && port_num != 0)
 		goto done;
 
 	if (MLX5_CAP_PCAM_FEATURE(dev->mdev, rx_icrc_encapsulated_counter)) {

From acd245b1e33fc4b9d0f2e3372021d632f7ee0652 Mon Sep 17 00:00:00 2001
From: Patrisious Haddad <phaddad@nvidia.com>
Date: Mon, 16 Jun 2025 12:14:53 +0300
Subject: [PATCH 0836/1334] RDMA/mlx5: Fix CC counters query for MPV

In case, CC counters are querying for the second port use the correct
core device for the query instead of always using the master core device.

Fixes: aac4492ef23a ("IB/mlx5: Update counter implementation for dual port RoCE")
Signed-off-by: Patrisious Haddad <phaddad@nvidia.com>
Reviewed-by: Michael Guralnik <michaelgur@nvidia.com>
Link: https://patch.msgid.link/9cace74dcf106116118bebfa9146d40d4166c6b0.1750064969.git.leon@kernel.org
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/hw/mlx5/counters.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/infiniband/hw/mlx5/counters.c b/drivers/infiniband/hw/mlx5/counters.c
index 943e9eb2ad20..a506fafd2b15 100644
--- a/drivers/infiniband/hw/mlx5/counters.c
+++ b/drivers/infiniband/hw/mlx5/counters.c
@@ -418,7 +418,7 @@ static int do_get_hw_stats(struct ib_device *ibdev,
 			 */
 			goto done;
 		}
-		ret = mlx5_lag_query_cong_counters(dev->mdev,
+		ret = mlx5_lag_query_cong_counters(mdev,
 						   stats->value +
 						   cnts->num_q_counters,
 						   cnts->num_cong_counters,

From a9a9e68954f29b1e197663f76289db4879fd51bb Mon Sep 17 00:00:00 2001
From: Patrisious Haddad <phaddad@nvidia.com>
Date: Mon, 16 Jun 2025 12:14:54 +0300
Subject: [PATCH 0837/1334] RDMA/mlx5: Fix vport loopback for MPV device

Always enable vport loopback for both MPV devices on driver start.

Previously in some cases related to MPV RoCE, packets weren't correctly
executing loopback check at vport in FW, since it was disabled.
Due to complexity of identifying such cases for MPV always enable vport
loopback for both GVMIs when binding the slave to the master port.

Fixes: 0042f9e458a5 ("RDMA/mlx5: Enable vport loopback when user context or QP mandate")
Signed-off-by: Patrisious Haddad <phaddad@nvidia.com>
Reviewed-by: Mark Bloch <mbloch@nvidia.com>
Link: https://patch.msgid.link/d4298f5ebb2197459e9e7221c51ecd6a34699847.1750064969.git.leon@kernel.org
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/hw/mlx5/main.c | 33 +++++++++++++++++++++++++++++++
 1 file changed, 33 insertions(+)

diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index ce7610740412..df6557ddbdfc 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -1791,6 +1791,33 @@ static void deallocate_uars(struct mlx5_ib_dev *dev,
 					     context->devx_uid);
 }
 
+static int mlx5_ib_enable_lb_mp(struct mlx5_core_dev *master,
+				struct mlx5_core_dev *slave)
+{
+	int err;
+
+	err = mlx5_nic_vport_update_local_lb(master, true);
+	if (err)
+		return err;
+
+	err = mlx5_nic_vport_update_local_lb(slave, true);
+	if (err)
+		goto out;
+
+	return 0;
+
+out:
+	mlx5_nic_vport_update_local_lb(master, false);
+	return err;
+}
+
+static void mlx5_ib_disable_lb_mp(struct mlx5_core_dev *master,
+				  struct mlx5_core_dev *slave)
+{
+	mlx5_nic_vport_update_local_lb(slave, false);
+	mlx5_nic_vport_update_local_lb(master, false);
+}
+
 int mlx5_ib_enable_lb(struct mlx5_ib_dev *dev, bool td, bool qp)
 {
 	int err = 0;
@@ -3495,6 +3522,8 @@ static void mlx5_ib_unbind_slave_port(struct mlx5_ib_dev *ibdev,
 
 	lockdep_assert_held(&mlx5_ib_multiport_mutex);
 
+	mlx5_ib_disable_lb_mp(ibdev->mdev, mpi->mdev);
+
 	mlx5_core_mp_event_replay(ibdev->mdev,
 				  MLX5_DRIVER_EVENT_AFFILIATION_REMOVED,
 				  NULL);
@@ -3590,6 +3619,10 @@ static bool mlx5_ib_bind_slave_port(struct mlx5_ib_dev *ibdev,
 				  MLX5_DRIVER_EVENT_AFFILIATION_DONE,
 				  &key);
 
+	err = mlx5_ib_enable_lb_mp(ibdev->mdev, mpi->mdev);
+	if (err)
+		goto unbind;
+
 	return true;
 
 unbind:

From d0f8ee81a8fe63cd29d01b905eead72b88326ef2 Mon Sep 17 00:00:00 2001
From: Paul Menzel <pmenzel@molgen.mpg.de>
Date: Sun, 22 Jun 2025 10:07:20 +0200
Subject: [PATCH 0838/1334] platform/x86: dell-lis3lv02d: Add Latitude 5500
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add 0x29 as the accelerometer address for the Dell Latitude 5500 to
lis3lv02d_devices[].

The address was verified as below:

    $ cd /sys/bus/pci/drivers/i801_smbus/0000:00:1f.4
    $ ls -d i2c-?
    i2c-2
    $ sudo modprobe i2c-dev
    $ sudo i2cdetect 2
    WARNING! This program can confuse your I2C bus, cause data loss and worse!
    I will probe file /dev/i2c-2.
    I will probe address range 0x08-0x77.
    Continue? [Y/n] Y
         0  1  2  3  4  5  6  7  8  9  a  b  c  d  e  f
    00:                         08 -- -- -- -- -- -- --
    10: -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- --
    20: -- -- -- -- -- -- -- -- -- 29 -- -- -- -- -- --
    30: 30 -- -- -- -- 35 UU UU -- -- -- -- -- -- -- --
    40: -- -- -- -- 44 -- -- -- -- -- -- -- -- -- -- --
    50: UU -- 52 -- -- -- -- -- -- -- -- -- -- -- -- --
    60: -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- --
    70: -- -- -- -- -- -- -- --
    $ echo lis3lv02d 0x29 | sudo tee /sys/bus/i2c/devices/i2c-2/new_device
    lis3lv02d 0x29
    $ sudo dmesg
    [    0.000000] Linux version 6.12.32-amd64 (debian-kernel@lists.debian.org) (x86_64-linux-gnu-gcc-14 (Debian 14.2.0-19) 14.2.0, GNU ld (GNU Binutils for Debian) 2.44) #1 SMP PREEMPT_DYNAMIC Debian 6.12.32-1 (2025-06-07)
    […]
    [    0.000000] DMI: Dell Inc. Latitude 5500/0M14W7, BIOS 1.38.0 03/06/2025
    […]
    [  609.063488] i2c_dev: i2c /dev entries driver
    [  639.135020] i2c i2c-2: new_device: Instantiated device lis3lv02d at 0x29

Signed-off-by: Paul Menzel <pmenzel@molgen.mpg.de>
Reviewed-by: Hans de Goede <hansg@kernel.org>
Link: https://lore.kernel.org/r/20250622080721.4661-1-pmenzel@molgen.mpg.de
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/dell/dell-lis3lv02d.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/platform/x86/dell/dell-lis3lv02d.c b/drivers/platform/x86/dell/dell-lis3lv02d.c
index efe26d667973..0791118dd6b7 100644
--- a/drivers/platform/x86/dell/dell-lis3lv02d.c
+++ b/drivers/platform/x86/dell/dell-lis3lv02d.c
@@ -45,6 +45,7 @@ static const struct dmi_system_id lis3lv02d_devices[] __initconst = {
 	 * Additional individual entries were added after verification.
 	 */
 	DELL_LIS3LV02D_DMI_ENTRY("Latitude 5480",      0x29),
+	DELL_LIS3LV02D_DMI_ENTRY("Latitude 5500",      0x29),
 	DELL_LIS3LV02D_DMI_ENTRY("Latitude E6330",     0x29),
 	DELL_LIS3LV02D_DMI_ENTRY("Latitude E6430",     0x29),
 	DELL_LIS3LV02D_DMI_ENTRY("Precision 3540",     0x29),

From 7dc6b2d3b5503bcafebbeaf9818112bf367107b4 Mon Sep 17 00:00:00 2001
From: Rahul Chandra <rahul@chandra.net>
Date: Tue, 24 Jun 2025 03:33:01 -0400
Subject: [PATCH 0839/1334] platform/x86: asus-nb-wmi: add DMI quirk for ASUS
 Zenbook Duo UX8406CA
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add a DMI quirk entry for the ASUS Zenbook Duo UX8406CA 2025 model to use
the existing zenbook duo keyboard quirk.

Signed-off-by: Rahul Chandra <rahul@chandra.net>
Link: https://lore.kernel.org/r/20250624073301.602070-1-rahul@chandra.net
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/asus-nb-wmi.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/drivers/platform/x86/asus-nb-wmi.c b/drivers/platform/x86/asus-nb-wmi.c
index 3f8b2a324efd..f84c3d03c1de 100644
--- a/drivers/platform/x86/asus-nb-wmi.c
+++ b/drivers/platform/x86/asus-nb-wmi.c
@@ -530,6 +530,15 @@ static const struct dmi_system_id asus_quirks[] = {
 		},
 		.driver_data = &quirk_asus_zenbook_duo_kbd,
 	},
+	{
+		.callback = dmi_matched,
+		.ident = "ASUS Zenbook Duo UX8406CA",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "UX8406CA"),
+		},
+		.driver_data = &quirk_asus_zenbook_duo_kbd,
+	},
 	{},
 };
 

From b511bbfe4242e14c27a4f80da95dabc4a99d73b2 Mon Sep 17 00:00:00 2001
From: Mark Pearson <mpearson-lenovo@squebb.ca>
Date: Fri, 20 Jun 2025 14:11:10 -0400
Subject: [PATCH 0840/1334] platform/x86: thinkpad_acpi: handle HKEY 0x1402
 event
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

2025 Thinkpads F11 key launch the Intel Unison app on Windows,
which does some sort of smart sharing between laptop and phone.

Map this key event to KEY_LINK_PHONE as the closest thing we have.
This prevents an error message being displayed on key press.

Reported-by: Damjan Georgievski <gdamjan@gmail.com>
Closes: https://sourceforge.net/p/ibm-acpi/mailman/message/59189556/
Signed-off-by: Mark Pearson <mpearson-lenovo@squebb.ca>
Link: https://lore.kernel.org/r/20250620181119.2519546-1-mpearson-lenovo@squebb.ca
[ij: converted directory to pre-lenovo move as this is fixes material.]
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/thinkpad_acpi.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c
index e7350c9fa3aa..b59b4d90b0c7 100644
--- a/drivers/platform/x86/thinkpad_acpi.c
+++ b/drivers/platform/x86/thinkpad_acpi.c
@@ -3295,6 +3295,7 @@ static const struct key_entry keymap_lenovo[] __initconst = {
 	 */
 	{ KE_KEY, 0x131d, { KEY_VENDOR } }, /* System debug info, similar to old ThinkPad key */
 	{ KE_KEY, 0x1320, { KEY_LINK_PHONE } },
+	{ KE_KEY, 0x1402, { KEY_LINK_PHONE } },
 	{ KE_KEY, TP_HKEY_EV_TRACK_DOUBLETAP /* 0x8036 */, { KEY_PROG4 } },
 	{ KE_END }
 };

From 173bbec6693f3f3f00dac144f3aa0cd62fb60d33 Mon Sep 17 00:00:00 2001
From: Alok Tiwari <alok.a.tiwari@oracle.com>
Date: Wed, 18 Jun 2025 23:05:00 -0700
Subject: [PATCH 0841/1334] platform/mellanox: mlxbf-pmc: Fix duplicate event
 ID for CACHE_DATA1
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

same ID (103) was assigned to both GDC_BANK0_G_RSE_PIPE_CACHE_DATA0
and GDC_BANK0_G_RSE_PIPE_CACHE_DATA1. This could lead to incorrect
event mapping.
Updated the ID to 104 to ensure uniqueness.

Fixes: 423c3361855c ("platform/mellanox: mlxbf-pmc: Add support for BlueField-3")
Signed-off-by: Alok Tiwari <alok.a.tiwari@oracle.com>
Reviewed-by: David Thompson <davthompson@nvidia.com>
Link: https://lore.kernel.org/r/20250619060502.3594350-1-alok.a.tiwari@oracle.com
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/mellanox/mlxbf-pmc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/platform/mellanox/mlxbf-pmc.c b/drivers/platform/mellanox/mlxbf-pmc.c
index 900069eb186e..a1c529f1ff1a 100644
--- a/drivers/platform/mellanox/mlxbf-pmc.c
+++ b/drivers/platform/mellanox/mlxbf-pmc.c
@@ -715,7 +715,7 @@ static const struct mlxbf_pmc_events mlxbf_pmc_llt_events[] = {
 	{101, "GDC_BANK0_HIT_DCL_PARTIAL"},
 	{102, "GDC_BANK0_EVICT_DCL"},
 	{103, "GDC_BANK0_G_RSE_PIPE_CACHE_DATA0"},
-	{103, "GDC_BANK0_G_RSE_PIPE_CACHE_DATA1"},
+	{104, "GDC_BANK0_G_RSE_PIPE_CACHE_DATA1"},
 	{105, "GDC_BANK0_ARB_STRB"},
 	{106, "GDC_BANK0_ARB_WAIT"},
 	{107, "GDC_BANK0_GGA_STRB"},

From ec54c0a20709ed6e56f40a8d59eee725c31a916b Mon Sep 17 00:00:00 2001
From: Sergey Senozhatsky <senozhatsky@chromium.org>
Date: Wed, 25 Jun 2025 14:20:37 +0900
Subject: [PATCH 0842/1334] mtk-sd: reset host->mrq on prepare_data() error

Do not leave host with dangling ->mrq pointer if we hit
the msdc_prepare_data() error out path.

Signed-off-by: Sergey Senozhatsky <senozhatsky@chromium.org>
Reviewed-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Fixes: f5de469990f1 ("mtk-sd: Prevent memory corruption from DMA map failure")
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20250625052106.584905-1-senozhatsky@chromium.org
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/host/mtk-sd.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/mmc/host/mtk-sd.c b/drivers/mmc/host/mtk-sd.c
index b12cfb9a5e5f..d7020e06dd55 100644
--- a/drivers/mmc/host/mtk-sd.c
+++ b/drivers/mmc/host/mtk-sd.c
@@ -1492,6 +1492,7 @@ static void msdc_ops_request(struct mmc_host *mmc, struct mmc_request *mrq)
 	if (mrq->data) {
 		msdc_prepare_data(host, mrq->data);
 		if (!msdc_data_prepared(mrq->data)) {
+			host->mrq = NULL;
 			/*
 			 * Failed to prepare DMA area, fail fast before
 			 * starting any commands.

From 3e0809b1664b9dc650d9dbca9a2d3ac690d4f661 Mon Sep 17 00:00:00 2001
From: Niklas Cassel <cassel@kernel.org>
Date: Tue, 24 Jun 2025 09:40:30 +0200
Subject: [PATCH 0843/1334] ata: ahci: Use correct DMI identifier for
 ASUSPRO-D840SA LPM quirk

ASUS store the board name in DMI_PRODUCT_NAME rather than
DMI_PRODUCT_VERSION. (Apparently it is only Lenovo that stores the
model-name in DMI_PRODUCT_VERSION.)

Use the correct DMI identifier, DMI_PRODUCT_NAME, to match the
ASUSPRO-D840SA board, such that the quirk actually gets applied.

Cc: stable@vger.kernel.org
Reported-by: Andy Yang <andyybtc79@gmail.com>
Tested-by: Andy Yang <andyybtc79@gmail.com>
Closes: https://lore.kernel.org/linux-ide/aFb3wXAwJSSJUB7o@ryzen/
Fixes: b5acc3628898 ("ata: ahci: Disallow LPM for ASUSPRO-D840SA motherboard")
Reviewed-by: Hans de Goede <hansg@kernel.org>
Reviewed-by: Damien Le Moal <dlemoal@kernel.org>
Link: https://lore.kernel.org/r/20250624074029.963028-2-cassel@kernel.org
Signed-off-by: Niklas Cassel <cassel@kernel.org>
---
 drivers/ata/ahci.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c
index e5e5c2e81d09..aa93b0ecbbc6 100644
--- a/drivers/ata/ahci.c
+++ b/drivers/ata/ahci.c
@@ -1450,7 +1450,7 @@ static bool ahci_broken_lpm(struct pci_dev *pdev)
 		{
 			.matches = {
 				DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
-				DMI_MATCH(DMI_PRODUCT_VERSION, "ASUSPRO D840MB_M840SA"),
+				DMI_MATCH(DMI_PRODUCT_NAME, "ASUSPRO D840MB_M840SA"),
 			},
 			/* 320 is broken, there is no known good version. */
 		},

From 0c84b534047dcf843f4344108bc3f2c2344b7e31 Mon Sep 17 00:00:00 2001
From: Binbin Wu <binbin.wu@linux.intel.com>
Date: Wed, 25 Jun 2025 09:48:29 +0800
Subject: [PATCH 0844/1334] Documentation: KVM: Fix unexpected unindent
 warnings

Add proper indentations to bullet list items to resolve the warning:
"Bullet list ends without a blank line; unexpected unindent."

Closes:https://lore.kernel.org/kvm/20250623162110.6e2f4241@canb.auug.org.au/

Fixes: cf207eac06f6 ("KVM: TDX: Handle TDG.VP.VMCALL<GetQuote>")
Fixes: 25e8b1dd4883 ("KVM: TDX: Exit to userspace for GetTdVmCallInfo")
Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Binbin Wu <binbin.wu@linux.intel.com>
Reviewed-by: Bagas Sanjaya <bagasdotme@gmail.com>
Link: https://lore.kernel.org/r/20250625014829.82289-1-binbin.wu@linux.intel.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 Documentation/virt/kvm/api.rst | 28 ++++++++++++++--------------
 1 file changed, 14 insertions(+), 14 deletions(-)

diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index f0d961436d0f..43ed57e048a8 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -7214,21 +7214,21 @@ number from register R11.  The remaining field of the union provide the
 inputs and outputs of the TDVMCALL.  Currently the following values of
 ``nr`` are defined:
 
-* ``TDVMCALL_GET_QUOTE``: the guest has requested to generate a TD-Quote
-signed by a service hosting TD-Quoting Enclave operating on the host.
-Parameters and return value are in the ``get_quote`` field of the union.
-The ``gpa`` field and ``size`` specify the guest physical address
-(without the shared bit set) and the size of a shared-memory buffer, in
-which the TDX guest passes a TD Report.  The ``ret`` field represents
-the return value of the GetQuote request.  When the request has been
-queued successfully, the TDX guest can poll the status field in the
-shared-memory area to check whether the Quote generation is completed or
-not. When completed, the generated Quote is returned via the same buffer.
+ * ``TDVMCALL_GET_QUOTE``: the guest has requested to generate a TD-Quote
+   signed by a service hosting TD-Quoting Enclave operating on the host.
+   Parameters and return value are in the ``get_quote`` field of the union.
+   The ``gpa`` field and ``size`` specify the guest physical address
+   (without the shared bit set) and the size of a shared-memory buffer, in
+   which the TDX guest passes a TD Report.  The ``ret`` field represents
+   the return value of the GetQuote request.  When the request has been
+   queued successfully, the TDX guest can poll the status field in the
+   shared-memory area to check whether the Quote generation is completed or
+   not. When completed, the generated Quote is returned via the same buffer.
 
-* ``TDVMCALL_GET_TD_VM_CALL_INFO``: the guest has requested the support
-status of TDVMCALLs.  The output values for the given leaf should be
-placed in fields from ``r11`` to ``r14`` of the ``get_tdvmcall_info``
-field of the union.
+ * ``TDVMCALL_GET_TD_VM_CALL_INFO``: the guest has requested the support
+   status of TDVMCALLs.  The output values for the given leaf should be
+   placed in fields from ``r11`` to ``r14`` of the ``get_tdvmcall_info``
+   field of the union.
 
 * ``TDVMCALL_SETUP_EVENT_NOTIFY_INTERRUPT``: the guest has requested to
 set up a notification interrupt for vector ``vector``.

From 7cac633a42a7b3c8146eb1db76fb80dc652998de Mon Sep 17 00:00:00 2001
From: Penglei Jiang <superman.xpt@gmail.com>
Date: Wed, 25 Jun 2025 03:27:03 -0700
Subject: [PATCH 0845/1334] io_uring: fix resource leak in io_import_dmabuf()

Replace the return statement with setting ret = -EINVAL and jumping to
the err label to ensure resources are released via io_release_dmabuf.

Fixes: a5c98e942457 ("io_uring/zcrx: dmabuf backed zerocopy receive")
Signed-off-by: Penglei Jiang <superman.xpt@gmail.com>
Link: https://lore.kernel.org/r/20250625102703.68336-1-superman.xpt@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/zcrx.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/io_uring/zcrx.c b/io_uring/zcrx.c
index 21c816c3bfe0..ade4da9c4e31 100644
--- a/io_uring/zcrx.c
+++ b/io_uring/zcrx.c
@@ -106,8 +106,10 @@ static int io_import_dmabuf(struct io_zcrx_ifq *ifq,
 	for_each_sgtable_dma_sg(mem->sgt, sg, i)
 		total_size += sg_dma_len(sg);
 
-	if (total_size < off + len)
-		return -EINVAL;
+	if (total_size < off + len) {
+		ret = -EINVAL;
+		goto err;
+	}
 
 	mem->dmabuf_offset = off;
 	mem->size = len;

From 51a4273dcab39dd1e850870945ccec664352d383 Mon Sep 17 00:00:00 2001
From: Nikunj A Dadhania <nikunj@amd.com>
Date: Tue, 8 Apr 2025 15:02:11 +0530
Subject: [PATCH 0846/1334] KVM: SVM: Add missing member in SNP_LAUNCH_START
 command structure

The sev_data_snp_launch_start structure should include a 4-byte
desired_tsc_khz field before the gosvw field, which was missed in the
initial implementation. As a result, the structure is 4 bytes shorter than
expected by the firmware, causing the gosvw field to start 4 bytes early.
Fix this by adding the missing 4-byte member for the desired TSC frequency.

Fixes: 3a45dc2b419e ("crypto: ccp: Define the SEV-SNP commands")
Cc: stable@vger.kernel.org
Suggested-by: Tom Lendacky <thomas.lendacky@amd.com>
Reviewed-by: Tom Lendacky <thomas.lendacky@amd.com>
Tested-by: Vaishali Thakkar <vaishali.thakkar@suse.com>
Signed-off-by: Nikunj A Dadhania <nikunj@amd.com>
Link: https://lore.kernel.org/r/20250408093213.57962-3-nikunj@amd.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 include/linux/psp-sev.h | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/include/linux/psp-sev.h b/include/linux/psp-sev.h
index 0b3a36bdaa90..0f5f94137f6d 100644
--- a/include/linux/psp-sev.h
+++ b/include/linux/psp-sev.h
@@ -594,6 +594,7 @@ struct sev_data_snp_addr {
  * @imi_en: launch flow is launching an IMI (Incoming Migration Image) for the
  *          purpose of guest-assisted migration.
  * @rsvd: reserved
+ * @desired_tsc_khz: hypervisor desired mean TSC freq in kHz of the guest
  * @gosvw: guest OS-visible workarounds, as defined by hypervisor
  */
 struct sev_data_snp_launch_start {
@@ -603,6 +604,7 @@ struct sev_data_snp_launch_start {
 	u32 ma_en:1;				/* In */
 	u32 imi_en:1;				/* In */
 	u32 rsvd:30;
+	u32 desired_tsc_khz;			/* In */
 	u8 gosvw[16];				/* In */
 } __packed;
 

From a3f3040657417aeadb9622c629d4a0c2693a0f93 Mon Sep 17 00:00:00 2001
From: Avadhut Naik <avadhut.naik@amd.com>
Date: Thu, 29 May 2025 20:50:04 +0000
Subject: [PATCH 0847/1334] EDAC/amd64: Fix size calculation for
 Non-Power-of-Two DIMMs
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Each Chip-Select (CS) of a Unified Memory Controller (UMC) on AMD Zen-based
SOCs has an Address Mask and a Secondary Address Mask register associated with
it. The amd64_edac module logs DIMM sizes on a per-UMC per-CS granularity
during init using these two registers.

Currently, the module primarily considers only the Address Mask register for
computing DIMM sizes. The Secondary Address Mask register is only considered
for odd CS. Additionally, if it has been considered, the Address Mask register
is ignored altogether for that CS. For power-of-two DIMMs i.e. DIMMs whose
total capacity is a power of two (32GB, 64GB, etc), this is not an issue
since only the Address Mask register is used.

For non-power-of-two DIMMs i.e., DIMMs whose total capacity is not a power of
two (48GB, 96GB, etc), however, the Secondary Address Mask register is used
in conjunction with the Address Mask register. However, since the module only
considers either of the two registers for a CS, the size computed by the
module is incorrect. The Secondary Address Mask register is not considered for
even CS, and the Address Mask register is not considered for odd CS.

Introduce a new helper function so that both Address Mask and Secondary
Address Mask registers are considered, when valid, for computing DIMM sizes.
Furthermore, also rename some variables for greater clarity.

Fixes: 81f5090db843 ("EDAC/amd64: Support asymmetric dual-rank DIMMs")
Closes: https://lore.kernel.org/dbec22b6-00f2-498b-b70d-ab6f8a5ec87e@natrix.lt
Reported-by: Žilvinas Žaltiena <zilvinas@natrix.lt>
Signed-off-by: Avadhut Naik <avadhut.naik@amd.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Yazen Ghannam <yazen.ghannam@amd.com>
Tested-by: Žilvinas Žaltiena <zilvinas@natrix.lt>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/20250529205013.403450-1-avadhut.naik@amd.com
---
 drivers/edac/amd64_edac.c | 57 ++++++++++++++++++++++++---------------
 1 file changed, 36 insertions(+), 21 deletions(-)

diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c
index b681c0663203..07f1e9dc1ca7 100644
--- a/drivers/edac/amd64_edac.c
+++ b/drivers/edac/amd64_edac.c
@@ -1209,7 +1209,9 @@ static int umc_get_cs_mode(int dimm, u8 ctrl, struct amd64_pvt *pvt)
 	if (csrow_enabled(2 * dimm + 1, ctrl, pvt))
 		cs_mode |= CS_ODD_PRIMARY;
 
-	/* Asymmetric dual-rank DIMM support. */
+	if (csrow_sec_enabled(2 * dimm, ctrl, pvt))
+		cs_mode |= CS_EVEN_SECONDARY;
+
 	if (csrow_sec_enabled(2 * dimm + 1, ctrl, pvt))
 		cs_mode |= CS_ODD_SECONDARY;
 
@@ -1230,12 +1232,13 @@ static int umc_get_cs_mode(int dimm, u8 ctrl, struct amd64_pvt *pvt)
 	return cs_mode;
 }
 
-static int __addr_mask_to_cs_size(u32 addr_mask_orig, unsigned int cs_mode,
-				  int csrow_nr, int dimm)
+static int calculate_cs_size(u32 mask, unsigned int cs_mode)
 {
-	u32 msb, weight, num_zero_bits;
-	u32 addr_mask_deinterleaved;
-	int size = 0;
+	int msb, weight, num_zero_bits;
+	u32 deinterleaved_mask;
+
+	if (!mask)
+		return 0;
 
 	/*
 	 * The number of zero bits in the mask is equal to the number of bits
@@ -1248,19 +1251,30 @@ static int __addr_mask_to_cs_size(u32 addr_mask_orig, unsigned int cs_mode,
 	 * without swapping with the most significant bit. This can be handled
 	 * by keeping the MSB where it is and ignoring the single zero bit.
 	 */
-	msb = fls(addr_mask_orig) - 1;
-	weight = hweight_long(addr_mask_orig);
+	msb = fls(mask) - 1;
+	weight = hweight_long(mask);
 	num_zero_bits = msb - weight - !!(cs_mode & CS_3R_INTERLEAVE);
 
 	/* Take the number of zero bits off from the top of the mask. */
-	addr_mask_deinterleaved = GENMASK_ULL(msb - num_zero_bits, 1);
+	deinterleaved_mask = GENMASK(msb - num_zero_bits, 1);
+	edac_dbg(1, "  Deinterleaved AddrMask: 0x%x\n", deinterleaved_mask);
+
+	return (deinterleaved_mask >> 2) + 1;
+}
+
+static int __addr_mask_to_cs_size(u32 addr_mask, u32 addr_mask_sec,
+				  unsigned int cs_mode, int csrow_nr, int dimm)
+{
+	int size;
 
 	edac_dbg(1, "CS%d DIMM%d AddrMasks:\n", csrow_nr, dimm);
-	edac_dbg(1, "  Original AddrMask: 0x%x\n", addr_mask_orig);
-	edac_dbg(1, "  Deinterleaved AddrMask: 0x%x\n", addr_mask_deinterleaved);
+	edac_dbg(1, "  Primary AddrMask: 0x%x\n", addr_mask);
 
 	/* Register [31:1] = Address [39:9]. Size is in kBs here. */
-	size = (addr_mask_deinterleaved >> 2) + 1;
+	size = calculate_cs_size(addr_mask, cs_mode);
+
+	edac_dbg(1, "  Secondary AddrMask: 0x%x\n", addr_mask_sec);
+	size += calculate_cs_size(addr_mask_sec, cs_mode);
 
 	/* Return size in MBs. */
 	return size >> 10;
@@ -1269,8 +1283,8 @@ static int __addr_mask_to_cs_size(u32 addr_mask_orig, unsigned int cs_mode,
 static int umc_addr_mask_to_cs_size(struct amd64_pvt *pvt, u8 umc,
 				    unsigned int cs_mode, int csrow_nr)
 {
+	u32 addr_mask = 0, addr_mask_sec = 0;
 	int cs_mask_nr = csrow_nr;
-	u32 addr_mask_orig;
 	int dimm, size = 0;
 
 	/* No Chip Selects are enabled. */
@@ -1308,13 +1322,13 @@ static int umc_addr_mask_to_cs_size(struct amd64_pvt *pvt, u8 umc,
 	if (!pvt->flags.zn_regs_v2)
 		cs_mask_nr >>= 1;
 
-	/* Asymmetric dual-rank DIMM support. */
-	if ((csrow_nr & 1) && (cs_mode & CS_ODD_SECONDARY))
-		addr_mask_orig = pvt->csels[umc].csmasks_sec[cs_mask_nr];
-	else
-		addr_mask_orig = pvt->csels[umc].csmasks[cs_mask_nr];
+	if (cs_mode & (CS_EVEN_PRIMARY | CS_ODD_PRIMARY))
+		addr_mask = pvt->csels[umc].csmasks[cs_mask_nr];
 
-	return __addr_mask_to_cs_size(addr_mask_orig, cs_mode, csrow_nr, dimm);
+	if (cs_mode & (CS_EVEN_SECONDARY | CS_ODD_SECONDARY))
+		addr_mask_sec = pvt->csels[umc].csmasks_sec[cs_mask_nr];
+
+	return __addr_mask_to_cs_size(addr_mask, addr_mask_sec, cs_mode, csrow_nr, dimm);
 }
 
 static void umc_debug_display_dimm_sizes(struct amd64_pvt *pvt, u8 ctrl)
@@ -3512,9 +3526,10 @@ static void gpu_get_err_info(struct mce *m, struct err_info *err)
 static int gpu_addr_mask_to_cs_size(struct amd64_pvt *pvt, u8 umc,
 				    unsigned int cs_mode, int csrow_nr)
 {
-	u32 addr_mask_orig = pvt->csels[umc].csmasks[csrow_nr];
+	u32 addr_mask		= pvt->csels[umc].csmasks[csrow_nr];
+	u32 addr_mask_sec	= pvt->csels[umc].csmasks_sec[csrow_nr];
 
-	return __addr_mask_to_cs_size(addr_mask_orig, cs_mode, csrow_nr, csrow_nr >> 1);
+	return __addr_mask_to_cs_size(addr_mask, addr_mask_sec, cs_mode, csrow_nr, csrow_nr >> 1);
 }
 
 static void gpu_debug_display_dimm_sizes(struct amd64_pvt *pvt, u8 ctrl)

From 55e8ff842051b1150461d7595d8f1d033c69d66b Mon Sep 17 00:00:00 2001
From: Jayesh Choudhary <j-choudhary@ti.com>
Date: Tue, 24 Jun 2025 10:18:35 +0530
Subject: [PATCH 0848/1334] drm/bridge: ti-sn65dsi86: Add HPD for DisplayPort
 connector type

By default, HPD was disabled on SN65DSI86 bridge. When the driver was
added (commit "a095f15c00e27"), the HPD_DISABLE bit was set in pre-enable
call which was moved to other function calls subsequently.
Later on, commit "c312b0df3b13" added detect utility for DP mode. But with
HPD_DISABLE bit set, all the HPD events are disabled[0] and the debounced
state always return 1 (always connected state).

Set HPD_DISABLE bit conditionally based on display sink's connector type.
Since the HPD_STATE is reflected correctly only after waiting for debounce
time (~100-400ms) and adding this delay in detect() is not feasible
owing to the performace impact (glitches and frame drop), remove runtime
calls in detect() and add hpd_enable()/disable() bridge hooks with runtime
calls, to detect hpd properly without any delay.

[0]: <https://www.ti.com/lit/gpn/SN65DSI86> (Pg. 32)

Fixes: c312b0df3b13 ("drm/bridge: ti-sn65dsi86: Implement bridge connector operations for DP")
Cc: Max Krummenacher <max.krummenacher@toradex.com>
Reviewed-by: Douglas Anderson <dianders@chromium.org>
Tested-by: Ernest Van Hoecke <ernest.vanhoecke@toradex.com>
Signed-off-by: Jayesh Choudhary <j-choudhary@ti.com>
Signed-off-by: Douglas Anderson <dianders@chromium.org>
Link: https://lore.kernel.org/r/20250624044835.165708-1-j-choudhary@ti.com
---
 drivers/gpu/drm/bridge/ti-sn65dsi86.c | 69 +++++++++++++++++++++++----
 1 file changed, 60 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/bridge/ti-sn65dsi86.c b/drivers/gpu/drm/bridge/ti-sn65dsi86.c
index 60224f476e1d..de9c23537465 100644
--- a/drivers/gpu/drm/bridge/ti-sn65dsi86.c
+++ b/drivers/gpu/drm/bridge/ti-sn65dsi86.c
@@ -348,12 +348,18 @@ static void ti_sn65dsi86_enable_comms(struct ti_sn65dsi86 *pdata,
 	 * 200 ms.  We'll assume that the panel driver will have the hardcoded
 	 * delay in its prepare and always disable HPD.
 	 *
-	 * If HPD somehow makes sense on some future panel we'll have to
-	 * change this to be conditional on someone specifying that HPD should
-	 * be used.
+	 * For DisplayPort bridge type, we need HPD. So we use the bridge type
+	 * to conditionally disable HPD.
+	 * NOTE: The bridge type is set in ti_sn_bridge_probe() but enable_comms()
+	 * can be called before. So for DisplayPort, HPD will be enabled once
+	 * bridge type is set. We are using bridge type instead of "no-hpd"
+	 * property because it is not used properly in devicetree description
+	 * and hence is unreliable.
 	 */
-	regmap_update_bits(pdata->regmap, SN_HPD_DISABLE_REG, HPD_DISABLE,
-			   HPD_DISABLE);
+
+	if (pdata->bridge.type != DRM_MODE_CONNECTOR_DisplayPort)
+		regmap_update_bits(pdata->regmap, SN_HPD_DISABLE_REG, HPD_DISABLE,
+				   HPD_DISABLE);
 
 	pdata->comms_enabled = true;
 
@@ -1195,9 +1201,14 @@ static enum drm_connector_status ti_sn_bridge_detect(struct drm_bridge *bridge)
 	struct ti_sn65dsi86 *pdata = bridge_to_ti_sn65dsi86(bridge);
 	int val = 0;
 
-	pm_runtime_get_sync(pdata->dev);
+	/*
+	 * Runtime reference is grabbed in ti_sn_bridge_hpd_enable()
+	 * as the chip won't report HPD just after being powered on.
+	 * HPD_DEBOUNCED_STATE reflects correct state only after the
+	 * debounce time (~100-400 ms).
+	 */
+
 	regmap_read(pdata->regmap, SN_HPD_DISABLE_REG, &val);
-	pm_runtime_put_autosuspend(pdata->dev);
 
 	return val & HPD_DEBOUNCED_STATE ? connector_status_connected
 					 : connector_status_disconnected;
@@ -1220,6 +1231,26 @@ static void ti_sn65dsi86_debugfs_init(struct drm_bridge *bridge, struct dentry *
 	debugfs_create_file("status", 0600, debugfs, pdata, &status_fops);
 }
 
+static void ti_sn_bridge_hpd_enable(struct drm_bridge *bridge)
+{
+	struct ti_sn65dsi86 *pdata = bridge_to_ti_sn65dsi86(bridge);
+
+	/*
+	 * Device needs to be powered on before reading the HPD state
+	 * for reliable hpd detection in ti_sn_bridge_detect() due to
+	 * the high debounce time.
+	 */
+
+	pm_runtime_get_sync(pdata->dev);
+}
+
+static void ti_sn_bridge_hpd_disable(struct drm_bridge *bridge)
+{
+	struct ti_sn65dsi86 *pdata = bridge_to_ti_sn65dsi86(bridge);
+
+	pm_runtime_put_autosuspend(pdata->dev);
+}
+
 static const struct drm_bridge_funcs ti_sn_bridge_funcs = {
 	.attach = ti_sn_bridge_attach,
 	.detach = ti_sn_bridge_detach,
@@ -1234,6 +1265,8 @@ static const struct drm_bridge_funcs ti_sn_bridge_funcs = {
 	.atomic_duplicate_state = drm_atomic_helper_bridge_duplicate_state,
 	.atomic_destroy_state = drm_atomic_helper_bridge_destroy_state,
 	.debugfs_init = ti_sn65dsi86_debugfs_init,
+	.hpd_enable = ti_sn_bridge_hpd_enable,
+	.hpd_disable = ti_sn_bridge_hpd_disable,
 };
 
 static void ti_sn_bridge_parse_lanes(struct ti_sn65dsi86 *pdata,
@@ -1321,8 +1354,26 @@ static int ti_sn_bridge_probe(struct auxiliary_device *adev,
 	pdata->bridge.type = pdata->next_bridge->type == DRM_MODE_CONNECTOR_DisplayPort
 			   ? DRM_MODE_CONNECTOR_DisplayPort : DRM_MODE_CONNECTOR_eDP;
 
-	if (pdata->bridge.type == DRM_MODE_CONNECTOR_DisplayPort)
-		pdata->bridge.ops = DRM_BRIDGE_OP_EDID | DRM_BRIDGE_OP_DETECT;
+	if (pdata->bridge.type == DRM_MODE_CONNECTOR_DisplayPort) {
+		pdata->bridge.ops = DRM_BRIDGE_OP_EDID | DRM_BRIDGE_OP_DETECT |
+				    DRM_BRIDGE_OP_HPD;
+		/*
+		 * If comms were already enabled they would have been enabled
+		 * with the wrong value of HPD_DISABLE. Update it now. Comms
+		 * could be enabled if anyone is holding a pm_runtime reference
+		 * (like if a GPIO is in use). Note that in most cases nobody
+		 * is doing AUX channel xfers before the bridge is added so
+		 * HPD doesn't _really_ matter then. The only exception is in
+		 * the eDP case where the panel wants to read the EDID before
+		 * the bridge is added. We always consistently have HPD disabled
+		 * for eDP.
+		 */
+		mutex_lock(&pdata->comms_mutex);
+		if (pdata->comms_enabled)
+			regmap_update_bits(pdata->regmap, SN_HPD_DISABLE_REG,
+					   HPD_DISABLE, 0);
+		mutex_unlock(&pdata->comms_mutex);
+	};
 
 	drm_bridge_add(&pdata->bridge);
 

From 1944f6ab4967db7ad8d4db527dceae8c77de76e9 Mon Sep 17 00:00:00 2001
From: Stefan Metzmacher <metze@samba.org>
Date: Wed, 25 Jun 2025 10:16:38 +0200
Subject: [PATCH 0849/1334] smb: client: let smbd_post_send_iter() respect the
 peers max_send_size and transmit all data

We should not send smbdirect_data_transfer messages larger than
the negotiated max_send_size, typically 1364 bytes, which means
24 bytes of the smbdirect_data_transfer header + 1340 payload bytes.

This happened when doing an SMB2 write with more than 1340 bytes
(which is done inline as it's below rdma_readwrite_threshold).

It means the peer resets the connection.

When testing between cifs.ko and ksmbd.ko something like this
is logged:

client:

    CIFS: VFS: RDMA transport re-established
    siw: got TERMINATE. layer 1, type 2, code 2
    siw: got TERMINATE. layer 1, type 2, code 2
    siw: got TERMINATE. layer 1, type 2, code 2
    siw: got TERMINATE. layer 1, type 2, code 2
    siw: got TERMINATE. layer 1, type 2, code 2
    siw: got TERMINATE. layer 1, type 2, code 2
    siw: got TERMINATE. layer 1, type 2, code 2
    siw: got TERMINATE. layer 1, type 2, code 2
    siw: got TERMINATE. layer 1, type 2, code 2
    CIFS: VFS: \\carina Send error in SessSetup = -11
    smb2_reconnect: 12 callbacks suppressed
    CIFS: VFS: reconnect tcon failed rc = -11
    CIFS: VFS: reconnect tcon failed rc = -11
    CIFS: VFS: reconnect tcon failed rc = -11
    CIFS: VFS: SMB: Zero rsize calculated, using minimum value 65536

and:

    CIFS: VFS: RDMA transport re-established
    siw: got TERMINATE. layer 1, type 2, code 2
    CIFS: VFS: smbd_recv:1894 disconnected
    siw: got TERMINATE. layer 1, type 2, code 2

The ksmbd dmesg is showing things like:

    smb_direct: Recv error. status='local length error (1)' opcode=128
    smb_direct: disconnected
    smb_direct: Recv error. status='local length error (1)' opcode=128
    ksmbd: smb_direct: disconnected
    ksmbd: sock_read failed: -107

As smbd_post_send_iter() limits the transmitted number of bytes
we need loop over it in order to transmit the whole iter.

Reviewed-by: David Howells <dhowells@redhat.com>
Tested-by: David Howells <dhowells@redhat.com>
Tested-by: Meetakshi Setiya <msetiya@microsoft.com>
Cc: Tom Talpey <tom@talpey.com>
Cc: linux-cifs@vger.kernel.org
Cc: <stable+noautosel@kernel.org> # sp->max_send_size should be info->max_send_size in backports
Fixes: 3d78fe73fa12 ("cifs: Build the RDMA SGE list directly from an iterator")
Signed-off-by: Stefan Metzmacher <metze@samba.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/smbdirect.c | 31 +++++++++++++++++++++++++++----
 1 file changed, 27 insertions(+), 4 deletions(-)

diff --git a/fs/smb/client/smbdirect.c b/fs/smb/client/smbdirect.c
index cbc85bca006f..a976bcf61226 100644
--- a/fs/smb/client/smbdirect.c
+++ b/fs/smb/client/smbdirect.c
@@ -907,8 +907,10 @@ wait_send_queue:
 			.local_dma_lkey	= sc->ib.pd->local_dma_lkey,
 			.direction	= DMA_TO_DEVICE,
 		};
+		size_t payload_len = umin(*_remaining_data_length,
+					  sp->max_send_size - sizeof(*packet));
 
-		rc = smb_extract_iter_to_rdma(iter, *_remaining_data_length,
+		rc = smb_extract_iter_to_rdma(iter, payload_len,
 					      &extract);
 		if (rc < 0)
 			goto err_dma;
@@ -1013,6 +1015,27 @@ static int smbd_post_send_empty(struct smbd_connection *info)
 	return smbd_post_send_iter(info, NULL, &remaining_data_length);
 }
 
+static int smbd_post_send_full_iter(struct smbd_connection *info,
+				    struct iov_iter *iter,
+				    int *_remaining_data_length)
+{
+	int rc = 0;
+
+	/*
+	 * smbd_post_send_iter() respects the
+	 * negotiated max_send_size, so we need to
+	 * loop until the full iter is posted
+	 */
+
+	while (iov_iter_count(iter) > 0) {
+		rc = smbd_post_send_iter(info, iter, _remaining_data_length);
+		if (rc < 0)
+			break;
+	}
+
+	return rc;
+}
+
 /*
  * Post a receive request to the transport
  * The remote peer can only send data when a receive request is posted
@@ -2032,14 +2055,14 @@ int smbd_send(struct TCP_Server_Info *server,
 			klen += rqst->rq_iov[i].iov_len;
 		iov_iter_kvec(&iter, ITER_SOURCE, rqst->rq_iov, rqst->rq_nvec, klen);
 
-		rc = smbd_post_send_iter(info, &iter, &remaining_data_length);
+		rc = smbd_post_send_full_iter(info, &iter, &remaining_data_length);
 		if (rc < 0)
 			break;
 
 		if (iov_iter_count(&rqst->rq_iter) > 0) {
 			/* And then the data pages if there are any */
-			rc = smbd_post_send_iter(info, &rqst->rq_iter,
-						 &remaining_data_length);
+			rc = smbd_post_send_full_iter(info, &rqst->rq_iter,
+						      &remaining_data_length);
 			if (rc < 0)
 				break;
 		}

From fa787ac07b3ceb56dd88a62d1866038498e96230 Mon Sep 17 00:00:00 2001
From: Manuel Andreas <manuel.andreas@tum.de>
Date: Wed, 25 Jun 2025 15:53:19 +0200
Subject: [PATCH 0850/1334] KVM: x86/hyper-v: Skip non-canonical addresses
 during PV TLB flush

In KVM guests with Hyper-V hypercalls enabled, the hypercalls
HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST and HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST_EX
allow a guest to request invalidation of portions of a virtual TLB.
For this, the hypercall parameter includes a list of GVAs that are supposed
to be invalidated.

However, when non-canonical GVAs are passed, there is currently no
filtering in place and they are eventually passed to checked invocations of
INVVPID on Intel / INVLPGA on AMD.  While AMD's INVLPGA silently ignores
non-canonical addresses (effectively a no-op), Intel's INVVPID explicitly
signals VM-Fail and ultimately triggers the WARN_ONCE in invvpid_error():

  invvpid failed: ext=0x0 vpid=1 gva=0xaaaaaaaaaaaaa000
  WARNING: CPU: 6 PID: 326 at arch/x86/kvm/vmx/vmx.c:482
  invvpid_error+0x91/0xa0 [kvm_intel]
  Modules linked in: kvm_intel kvm 9pnet_virtio irqbypass fuse
  CPU: 6 UID: 0 PID: 326 Comm: kvm-vm Not tainted 6.15.0 #14 PREEMPT(voluntary)
  RIP: 0010:invvpid_error+0x91/0xa0 [kvm_intel]
  Call Trace:
    vmx_flush_tlb_gva+0x320/0x490 [kvm_intel]
    kvm_hv_vcpu_flush_tlb+0x24f/0x4f0 [kvm]
    kvm_arch_vcpu_ioctl_run+0x3013/0x5810 [kvm]

Hyper-V documents that invalid GVAs (those that are beyond a partition's
GVA space) are to be ignored.  While not completely clear whether this
ruling also applies to non-canonical GVAs, it is likely fine to make that
assumption, and manual testing on Azure confirms "real" Hyper-V interprets
the specification in the same way.

Skip non-canonical GVAs when processing the list of address to avoid
tripping the INVVPID failure.  Alternatively, KVM could filter out "bad"
GVAs before inserting into the FIFO, but practically speaking the only
downside of pushing validation to the final processing is that doing so
is suboptimal for the guest, and no well-behaved guest will request TLB
flushes for non-canonical addresses.

Fixes: 260970862c88 ("KVM: x86: hyper-v: Handle HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST{,EX} calls gently")
Cc: stable@vger.kernel.org
Signed-off-by: Manuel Andreas <manuel.andreas@tum.de>
Suggested-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Link: https://lore.kernel.org/r/c090efb3-ef82-499f-a5e0-360fc8420fb7@tum.de
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/hyperv.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index 75221a11e15e..ee27064dd72f 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -1979,6 +1979,9 @@ int kvm_hv_vcpu_flush_tlb(struct kvm_vcpu *vcpu)
 		if (entries[i] == KVM_HV_TLB_FLUSHALL_ENTRY)
 			goto out_flush_all;
 
+		if (is_noncanonical_invlpg_address(entries[i], vcpu))
+			continue;
+
 		/*
 		 * Lower 12 bits of 'address' encode the number of additional
 		 * pages to flush.

From 9a709b7e98e6fa51600b5f2d24c5068efa6d39de Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Wed, 25 Jun 2025 10:17:06 -0600
Subject: [PATCH 0851/1334] io_uring/net: mark iov as dynamically allocated
 even for single segments

A bigger array of vecs could've been allocated, but
io_ring_buffers_peek() still decided to cap the mapped range depending
on how much data was available. Hence don't rely on the segment count
to know if the request should be marked as needing cleanup, always
check upfront if the iov array is different than the fast_iov array.

Fixes: 26ec15e4b0c1 ("io_uring/kbuf: don't truncate end buffer for multiple buffer peeks")
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/net.c | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/io_uring/net.c b/io_uring/net.c
index 9550d4c8f866..5c1e8c4ba468 100644
--- a/io_uring/net.c
+++ b/io_uring/net.c
@@ -1077,6 +1077,12 @@ static int io_recv_buf_select(struct io_kiocb *req, struct io_async_msghdr *kmsg
 		if (unlikely(ret < 0))
 			return ret;
 
+		if (arg.iovs != &kmsg->fast_iov && arg.iovs != kmsg->vec.iovec) {
+			kmsg->vec.nr = ret;
+			kmsg->vec.iovec = arg.iovs;
+			req->flags |= REQ_F_NEED_CLEANUP;
+		}
+
 		/* special case 1 vec, can be a fast path */
 		if (ret == 1) {
 			sr->buf = arg.iovs[0].iov_base;
@@ -1085,11 +1091,6 @@ static int io_recv_buf_select(struct io_kiocb *req, struct io_async_msghdr *kmsg
 		}
 		iov_iter_init(&kmsg->msg.msg_iter, ITER_DEST, arg.iovs, ret,
 				arg.out_len);
-		if (arg.iovs != &kmsg->fast_iov && arg.iovs != kmsg->vec.iovec) {
-			kmsg->vec.nr = ret;
-			kmsg->vec.iovec = arg.iovs;
-			req->flags |= REQ_F_NEED_CLEANUP;
-		}
 	} else {
 		void __user *buf;
 

From e97f9540ce001503a4539f337da742c1dfa7d86a Mon Sep 17 00:00:00 2001
From: Stefan Metzmacher <metze@samba.org>
Date: Wed, 25 Jun 2025 10:13:04 +0200
Subject: [PATCH 0852/1334] smb: client: remove \t from TP_printk statements

The generate '[FAILED TO PARSE]' strings in trace-cmd report output like this:

  rm-5298  [001]  6084.533748493: smb3_exit_err:        [FAILED TO PARSE] xid=972 func_name=cifs_rmdir rc=-39
  rm-5298  [001]  6084.533959234: smb3_enter:           [FAILED TO PARSE] xid=973 func_name=cifs_closedir
  rm-5298  [001]  6084.533967630: smb3_close_enter:     [FAILED TO PARSE] xid=973 fid=94489281833 tid=1 sesid=96758029877361
  rm-5298  [001]  6084.534004008: smb3_cmd_enter:       [FAILED TO PARSE] tid=1 sesid=96758029877361 cmd=6 mid=566
  rm-5298  [001]  6084.552248232: smb3_cmd_done:        [FAILED TO PARSE] tid=1 sesid=96758029877361 cmd=6 mid=566
  rm-5298  [001]  6084.552280542: smb3_close_done:      [FAILED TO PARSE] xid=973 fid=94489281833 tid=1 sesid=96758029877361
  rm-5298  [001]  6084.552316034: smb3_exit_done:       [FAILED TO PARSE] xid=973 func_name=cifs_closedir

Cc: stable@vger.kernel.org
Signed-off-by: Stefan Metzmacher <metze@samba.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/trace.h | 24 ++++++++++++------------
 1 file changed, 12 insertions(+), 12 deletions(-)

diff --git a/fs/smb/client/trace.h b/fs/smb/client/trace.h
index 52bcb55d9952..93e5b2bb9f28 100644
--- a/fs/smb/client/trace.h
+++ b/fs/smb/client/trace.h
@@ -140,7 +140,7 @@ DECLARE_EVENT_CLASS(smb3_rw_err_class,
 		__entry->len = len;
 		__entry->rc = rc;
 	),
-	TP_printk("\tR=%08x[%x] xid=%u sid=0x%llx tid=0x%x fid=0x%llx offset=0x%llx len=0x%x rc=%d",
+	TP_printk("R=%08x[%x] xid=%u sid=0x%llx tid=0x%x fid=0x%llx offset=0x%llx len=0x%x rc=%d",
 		  __entry->rreq_debug_id, __entry->rreq_debug_index,
 		  __entry->xid, __entry->sesid, __entry->tid, __entry->fid,
 		  __entry->offset, __entry->len, __entry->rc)
@@ -190,7 +190,7 @@ DECLARE_EVENT_CLASS(smb3_other_err_class,
 		__entry->len = len;
 		__entry->rc = rc;
 	),
-	TP_printk("\txid=%u sid=0x%llx tid=0x%x fid=0x%llx offset=0x%llx len=0x%x rc=%d",
+	TP_printk("xid=%u sid=0x%llx tid=0x%x fid=0x%llx offset=0x%llx len=0x%x rc=%d",
 		__entry->xid, __entry->sesid, __entry->tid, __entry->fid,
 		__entry->offset, __entry->len, __entry->rc)
 )
@@ -247,7 +247,7 @@ DECLARE_EVENT_CLASS(smb3_copy_range_err_class,
 		__entry->len = len;
 		__entry->rc = rc;
 	),
-	TP_printk("\txid=%u sid=0x%llx tid=0x%x source fid=0x%llx source offset=0x%llx target fid=0x%llx target offset=0x%llx len=0x%x rc=%d",
+	TP_printk("xid=%u sid=0x%llx tid=0x%x source fid=0x%llx source offset=0x%llx target fid=0x%llx target offset=0x%llx len=0x%x rc=%d",
 		__entry->xid, __entry->sesid, __entry->tid, __entry->target_fid,
 		__entry->src_offset, __entry->target_fid, __entry->target_offset, __entry->len, __entry->rc)
 )
@@ -298,7 +298,7 @@ DECLARE_EVENT_CLASS(smb3_copy_range_done_class,
 		__entry->target_offset = target_offset;
 		__entry->len = len;
 	),
-	TP_printk("\txid=%u sid=0x%llx tid=0x%x source fid=0x%llx source offset=0x%llx target fid=0x%llx target offset=0x%llx len=0x%x",
+	TP_printk("xid=%u sid=0x%llx tid=0x%x source fid=0x%llx source offset=0x%llx target fid=0x%llx target offset=0x%llx len=0x%x",
 		__entry->xid, __entry->sesid, __entry->tid, __entry->target_fid,
 		__entry->src_offset, __entry->target_fid, __entry->target_offset, __entry->len)
 )
@@ -482,7 +482,7 @@ DECLARE_EVENT_CLASS(smb3_fd_class,
 		__entry->tid = tid;
 		__entry->sesid = sesid;
 	),
-	TP_printk("\txid=%u sid=0x%llx tid=0x%x fid=0x%llx",
+	TP_printk("xid=%u sid=0x%llx tid=0x%x fid=0x%llx",
 		__entry->xid, __entry->sesid, __entry->tid, __entry->fid)
 )
 
@@ -521,7 +521,7 @@ DECLARE_EVENT_CLASS(smb3_fd_err_class,
 		__entry->sesid = sesid;
 		__entry->rc = rc;
 	),
-	TP_printk("\txid=%u sid=0x%llx tid=0x%x fid=0x%llx rc=%d",
+	TP_printk("xid=%u sid=0x%llx tid=0x%x fid=0x%llx rc=%d",
 		__entry->xid, __entry->sesid, __entry->tid, __entry->fid,
 		__entry->rc)
 )
@@ -794,7 +794,7 @@ DECLARE_EVENT_CLASS(smb3_cmd_err_class,
 		__entry->status = status;
 		__entry->rc = rc;
 	),
-	TP_printk("\tsid=0x%llx tid=0x%x cmd=%u mid=%llu status=0x%x rc=%d",
+	TP_printk("sid=0x%llx tid=0x%x cmd=%u mid=%llu status=0x%x rc=%d",
 		__entry->sesid, __entry->tid, __entry->cmd, __entry->mid,
 		__entry->status, __entry->rc)
 )
@@ -829,7 +829,7 @@ DECLARE_EVENT_CLASS(smb3_cmd_done_class,
 		__entry->cmd = cmd;
 		__entry->mid = mid;
 	),
-	TP_printk("\tsid=0x%llx tid=0x%x cmd=%u mid=%llu",
+	TP_printk("sid=0x%llx tid=0x%x cmd=%u mid=%llu",
 		__entry->sesid, __entry->tid,
 		__entry->cmd, __entry->mid)
 )
@@ -867,7 +867,7 @@ DECLARE_EVENT_CLASS(smb3_mid_class,
 		__entry->when_sent = when_sent;
 		__entry->when_received = when_received;
 	),
-	TP_printk("\tcmd=%u mid=%llu pid=%u, when_sent=%lu when_rcv=%lu",
+	TP_printk("cmd=%u mid=%llu pid=%u, when_sent=%lu when_rcv=%lu",
 		__entry->cmd, __entry->mid, __entry->pid, __entry->when_sent,
 		__entry->when_received)
 )
@@ -898,7 +898,7 @@ DECLARE_EVENT_CLASS(smb3_exit_err_class,
 		__assign_str(func_name);
 		__entry->rc = rc;
 	),
-	TP_printk("\t%s: xid=%u rc=%d",
+	TP_printk("%s: xid=%u rc=%d",
 		__get_str(func_name), __entry->xid, __entry->rc)
 )
 
@@ -924,7 +924,7 @@ DECLARE_EVENT_CLASS(smb3_sync_err_class,
 		__entry->ino = ino;
 		__entry->rc = rc;
 	),
-	TP_printk("\tino=%lu rc=%d",
+	TP_printk("ino=%lu rc=%d",
 		__entry->ino, __entry->rc)
 )
 
@@ -950,7 +950,7 @@ DECLARE_EVENT_CLASS(smb3_enter_exit_class,
 		__entry->xid = xid;
 		__assign_str(func_name);
 	),
-	TP_printk("\t%s: xid=%u",
+	TP_printk("%s: xid=%u",
 		__get_str(func_name), __entry->xid)
 )
 

From 0a46f60a9fe16f5596b6b4b3ee1a483ea7854136 Mon Sep 17 00:00:00 2001
From: Li Ming <ming.li@zohomail.com>
Date: Fri, 20 Jun 2025 13:29:24 +0800
Subject: [PATCH 0853/1334] cxl/edac: Fix using wrong repair type to check dram
 event record

cxl_find_rec_dram() is used to find a DRAM event record based on the
inputted attributes. Different repair_type of the inputted attributes
will check the DRAM event record in different ways.
When EDAC driver is performing a memory rank sparing, it should use
CXL_RANK_SPARING rather than CXL_BANK_SPARING as repair_type for DRAM
event record checking.

Fixes: 588ca944c277 ("cxl/edac: Add CXL memory device memory sparing control feature")
Signed-off-by: Li Ming <ming.li@zohomail.com>
Reviewed-by: Shiju Jose <shiju.jose@huawei.com>
Reviewed-by: Jonathan Cameron <jonathan.cameron@huawei.com>
Reviewed-by: Ira Weiny <ira.weiny@intel.com>
Reviewed-by: Fan Ni <fan.ni@samsung.com>
Link: https://patch.msgid.link/20250620052924.138892-1-ming.li@zohomail.com
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
---
 drivers/cxl/core/edac.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/cxl/core/edac.c b/drivers/cxl/core/edac.c
index d725ee954199..623aaa4439c4 100644
--- a/drivers/cxl/core/edac.c
+++ b/drivers/cxl/core/edac.c
@@ -1323,7 +1323,7 @@ cxl_mem_get_rec_dram(struct cxl_memdev *cxlmd,
 		attrbs.bank = ctx->bank;
 	break;
 	case EDAC_REPAIR_RANK_SPARING:
-		attrbs.repair_type = CXL_BANK_SPARING;
+		attrbs.repair_type = CXL_RANK_SPARING;
 		break;
 	default:
 		return NULL;

From fa6f092cc0a02d0fcee37e9e8172eda372a03d33 Mon Sep 17 00:00:00 2001
From: Adin Scannell <amscanne@meta.com>
Date: Tue, 24 Jun 2025 22:02:15 -0700
Subject: [PATCH 0854/1334] libbpf: Fix possible use-after-free for externs

The `name` field in `obj->externs` points into the BTF data at initial
open time. However, some functions may invalidate this after opening and
before loading (e.g. `bpf_map__set_value_size`), which results in
pointers into freed memory and undefined behavior.

The simplest solution is to simply `strdup` these strings, similar to
the `essent_name`, and free them at the same time.

In order to test this path, the `global_map_resize` BPF selftest is
modified slightly to ensure the presence of an extern, which causes this
test to fail prior to the fix. Given there isn't an obvious API or error
to test against, I opted to add this to the existing test as an aspect
of the resizing feature rather than duplicate the test.

Fixes: 9d0a23313b1a ("libbpf: Add capability for resizing datasec maps")
Signed-off-by: Adin Scannell <amscanne@meta.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20250625050215.2777374-1-amscanne@meta.com
---
 tools/lib/bpf/libbpf.c                           | 10 +++++++---
 .../selftests/bpf/progs/test_global_map_resize.c | 16 ++++++++++++++++
 2 files changed, 23 insertions(+), 3 deletions(-)

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index e9c641a2fb20..52e353368f58 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -597,7 +597,7 @@ struct extern_desc {
 	int sym_idx;
 	int btf_id;
 	int sec_btf_id;
-	const char *name;
+	char *name;
 	char *essent_name;
 	bool is_set;
 	bool is_weak;
@@ -4259,7 +4259,9 @@ static int bpf_object__collect_externs(struct bpf_object *obj)
 			return ext->btf_id;
 		}
 		t = btf__type_by_id(obj->btf, ext->btf_id);
-		ext->name = btf__name_by_offset(obj->btf, t->name_off);
+		ext->name = strdup(btf__name_by_offset(obj->btf, t->name_off));
+		if (!ext->name)
+			return -ENOMEM;
 		ext->sym_idx = i;
 		ext->is_weak = ELF64_ST_BIND(sym->st_info) == STB_WEAK;
 
@@ -9138,8 +9140,10 @@ void bpf_object__close(struct bpf_object *obj)
 	zfree(&obj->btf_custom_path);
 	zfree(&obj->kconfig);
 
-	for (i = 0; i < obj->nr_extern; i++)
+	for (i = 0; i < obj->nr_extern; i++) {
+		zfree(&obj->externs[i].name);
 		zfree(&obj->externs[i].essent_name);
+	}
 
 	zfree(&obj->externs);
 	obj->nr_extern = 0;
diff --git a/tools/testing/selftests/bpf/progs/test_global_map_resize.c b/tools/testing/selftests/bpf/progs/test_global_map_resize.c
index a3f220ba7025..ee65bad0436d 100644
--- a/tools/testing/selftests/bpf/progs/test_global_map_resize.c
+++ b/tools/testing/selftests/bpf/progs/test_global_map_resize.c
@@ -32,6 +32,16 @@ int my_int_last SEC(".data.array_not_last");
 
 int percpu_arr[1] SEC(".data.percpu_arr");
 
+/* at least one extern is included, to ensure that a specific
+ * regression is tested whereby resizing resulted in a free-after-use
+ * bug after type information is invalidated by the resize operation.
+ *
+ * There isn't a particularly good API to test for this specific condition,
+ * but by having externs for the resizing tests it will cover this path.
+ */
+extern int LINUX_KERNEL_VERSION __kconfig;
+long version_sink;
+
 SEC("tp/syscalls/sys_enter_getpid")
 int bss_array_sum(void *ctx)
 {
@@ -44,6 +54,9 @@ int bss_array_sum(void *ctx)
 	for (size_t i = 0; i < bss_array_len; ++i)
 		sum += array[i];
 
+	/* see above; ensure this is not optimized out */
+	version_sink = LINUX_KERNEL_VERSION;
+
 	return 0;
 }
 
@@ -59,6 +72,9 @@ int data_array_sum(void *ctx)
 	for (size_t i = 0; i < data_array_len; ++i)
 		sum += my_array[i];
 
+	/* see above; ensure this is not optimized out */
+	version_sink = LINUX_KERNEL_VERSION;
+
 	return 0;
 }
 

From a5d0b9e32745277644cda8d7d334e7080bd339bf Mon Sep 17 00:00:00 2001
From: Lukasz Kucharczyk <lukasz.kucharczyk@leica-geosystems.com>
Date: Tue, 20 May 2025 14:22:52 +0200
Subject: [PATCH 0855/1334] i2c: imx: fix emulated smbus block read

Acknowledge the byte count submitted by the target.
When I2C_SMBUS_BLOCK_DATA read operation is executed by
i2c_smbus_xfer_emulated(), the length of the second (read) message is set
to 1. Length of the block is supposed to be obtained from the target by the
underlying bus driver.
The i2c_imx_isr_read() function should emit the acknowledge on i2c bus
after reading the first byte (i.e., byte count) while processing such
message (as defined in Section 6.5.7 of System Management Bus
Specification [1]). Without this acknowledge, the target does not submit
subsequent bytes and the controller only reads 0xff's.

In addition, store the length of block data obtained from the target in
the buffer provided by i2c_smbus_xfer_emulated() - otherwise the first
byte of actual data is erroneously interpreted as length of the data
block.

[1] https://smbus.org/specs/SMBus_3_3_20240512.pdf

Fixes: 5f5c2d4579ca ("i2c: imx: prevent rescheduling in non dma mode")
Signed-off-by: Lukasz Kucharczyk <lukasz.kucharczyk@leica-geosystems.com>
Cc: <stable@vger.kernel.org> # v6.13+
Acked-by: Oleksij Rempel <o.rempel@pengutronix.de>
Reviewed-by: Stefan Eichenberger <eichest@gmail.com>
Reviewed-by: Carlos Song <carlos.song@nxp.com>
Signed-off-by: Andi Shyti <andi.shyti@kernel.org>
Link: https://lore.kernel.org/r/20250520122252.1475403-1-lukasz.kucharczyk@leica-geosystems.com
---
 drivers/i2c/busses/i2c-imx.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/i2c/busses/i2c-imx.c b/drivers/i2c/busses/i2c-imx.c
index e5732b0557fb..205cc132fdec 100644
--- a/drivers/i2c/busses/i2c-imx.c
+++ b/drivers/i2c/busses/i2c-imx.c
@@ -1008,7 +1008,7 @@ static inline int i2c_imx_isr_read(struct imx_i2c_struct *i2c_imx)
 	/* setup bus to read data */
 	temp = imx_i2c_read_reg(i2c_imx, IMX_I2C_I2CR);
 	temp &= ~I2CR_MTX;
-	if (i2c_imx->msg->len - 1)
+	if ((i2c_imx->msg->len - 1) || (i2c_imx->msg->flags & I2C_M_RECV_LEN))
 		temp &= ~I2CR_TXAK;
 
 	imx_i2c_write_reg(temp, i2c_imx, IMX_I2C_I2CR);
@@ -1063,6 +1063,7 @@ static inline void i2c_imx_isr_read_block_data_len(struct imx_i2c_struct *i2c_im
 		wake_up(&i2c_imx->queue);
 	}
 	i2c_imx->msg->len += len;
+	i2c_imx->msg->buf[i2c_imx->msg_buf_idx++] = len;
 }
 
 static irqreturn_t i2c_imx_master_isr(struct imx_i2c_struct *i2c_imx, unsigned int status)

From 56ad91c1aa9c18064348edf69308080b03c9dc48 Mon Sep 17 00:00:00 2001
From: Wolfram Sang <wsa+renesas@sang-engineering.com>
Date: Thu, 22 May 2025 08:42:35 +0200
Subject: [PATCH 0856/1334] i2c: robotfuzz-osif: disable zero-length read
 messages

This driver passes the length of an i2c_msg directly to
usb_control_msg(). If the message is now a read and of length 0, it
violates the USB protocol and a warning will be printed. Enable the
I2C_AQ_NO_ZERO_LEN_READ quirk for this adapter thus forbidding 0-length
read messages altogether.

Fixes: 83e53a8f120f ("i2c: Add bus driver for for OSIF USB i2c device.")
Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
Cc: <stable@vger.kernel.org> # v3.14+
Signed-off-by: Andi Shyti <andi.shyti@kernel.org>
Link: https://lore.kernel.org/r/20250522064234.3721-2-wsa+renesas@sang-engineering.com
---
 drivers/i2c/busses/i2c-robotfuzz-osif.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/i2c/busses/i2c-robotfuzz-osif.c b/drivers/i2c/busses/i2c-robotfuzz-osif.c
index 80d45079b763..e0a76fb5bc31 100644
--- a/drivers/i2c/busses/i2c-robotfuzz-osif.c
+++ b/drivers/i2c/busses/i2c-robotfuzz-osif.c
@@ -111,6 +111,11 @@ static u32 osif_func(struct i2c_adapter *adapter)
 	return I2C_FUNC_I2C | I2C_FUNC_SMBUS_EMUL;
 }
 
+/* prevent invalid 0-length usb_control_msg */
+static const struct i2c_adapter_quirks osif_quirks = {
+	.flags = I2C_AQ_NO_ZERO_LEN_READ,
+};
+
 static const struct i2c_algorithm osif_algorithm = {
 	.xfer = osif_xfer,
 	.functionality = osif_func,
@@ -143,6 +148,7 @@ static int osif_probe(struct usb_interface *interface,
 
 	priv->adapter.owner = THIS_MODULE;
 	priv->adapter.class = I2C_CLASS_HWMON;
+	priv->adapter.quirks = &osif_quirks;
 	priv->adapter.algo = &osif_algorithm;
 	priv->adapter.algo_data = priv;
 	snprintf(priv->adapter.name, sizeof(priv->adapter.name),

From cbdb25ccf7566eee0c2b945e35cb98baf9ed0aa6 Mon Sep 17 00:00:00 2001
From: Wolfram Sang <wsa+renesas@sang-engineering.com>
Date: Thu, 22 May 2025 08:43:49 +0200
Subject: [PATCH 0857/1334] i2c: tiny-usb: disable zero-length read messages

This driver passes the length of an i2c_msg directly to
usb_control_msg(). If the message is now a read and of length 0, it
violates the USB protocol and a warning will be printed. Enable the
I2C_AQ_NO_ZERO_LEN_READ quirk for this adapter thus forbidding 0-length
read messages altogether.

Fixes: e8c76eed2ecd ("i2c: New i2c-tiny-usb bus driver")
Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
Cc: <stable@vger.kernel.org> # v2.6.22+
Signed-off-by: Andi Shyti <andi.shyti@kernel.org>
Link: https://lore.kernel.org/r/20250522064349.3823-2-wsa+renesas@sang-engineering.com
---
 drivers/i2c/busses/i2c-tiny-usb.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/i2c/busses/i2c-tiny-usb.c b/drivers/i2c/busses/i2c-tiny-usb.c
index a18eab0992a1..57dfe5f1a7d9 100644
--- a/drivers/i2c/busses/i2c-tiny-usb.c
+++ b/drivers/i2c/busses/i2c-tiny-usb.c
@@ -139,6 +139,11 @@ out:
 	return ret;
 }
 
+/* prevent invalid 0-length usb_control_msg */
+static const struct i2c_adapter_quirks usb_quirks = {
+	.flags = I2C_AQ_NO_ZERO_LEN_READ,
+};
+
 /* This is the actual algorithm we define */
 static const struct i2c_algorithm usb_algorithm = {
 	.xfer = usb_xfer,
@@ -247,6 +252,7 @@ static int i2c_tiny_usb_probe(struct usb_interface *interface,
 	/* setup i2c adapter description */
 	dev->adapter.owner = THIS_MODULE;
 	dev->adapter.class = I2C_CLASS_HWMON;
+	dev->adapter.quirks = &usb_quirks;
 	dev->adapter.algo = &usb_algorithm;
 	dev->adapter.algo_data = dev;
 	snprintf(dev->adapter.name, sizeof(dev->adapter.name),

From 942e1aece13e4007656e41d3182c0adf05cf08b8 Mon Sep 17 00:00:00 2001
From: Pratap Nirujogi <pratap.nirujogi@amd.com>
Date: Mon, 9 Jun 2025 11:53:55 -0400
Subject: [PATCH 0858/1334] i2c: designware: Initialize adapter name only when
 not set

Check if the adapter name is already set in the driver prior to
initializing with generic name in i2c_dw_probe_master(). This
check allows to retain the unique adapter name driver has
initialized, which platform driver can use to distinguish it
from other i2c designware adapters.

Tested-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Pratap Nirujogi <pratap.nirujogi@amd.com>
Signed-off-by: Andi Shyti <andi.shyti@kernel.org>
Link: https://lore.kernel.org/r/20250609155601.1477055-2-pratap.nirujogi@amd.com
---
 drivers/i2c/busses/i2c-designware-master.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/i2c/busses/i2c-designware-master.c b/drivers/i2c/busses/i2c-designware-master.c
index c5394229b77f..9d7d9e47564a 100644
--- a/drivers/i2c/busses/i2c-designware-master.c
+++ b/drivers/i2c/busses/i2c-designware-master.c
@@ -1042,8 +1042,9 @@ int i2c_dw_probe_master(struct dw_i2c_dev *dev)
 	if (ret)
 		return ret;
 
-	snprintf(adap->name, sizeof(adap->name),
-		 "Synopsys DesignWare I2C adapter");
+	if (!adap->name[0])
+		scnprintf(adap->name, sizeof(adap->name),
+			  "Synopsys DesignWare I2C adapter");
 	adap->retries = 3;
 	adap->algo = &i2c_dw_algo;
 	adap->quirks = &i2c_dw_quirks;

From c8dc579169738a3546f57ecb38e62d3872a3cc04 Mon Sep 17 00:00:00 2001
From: Pratap Nirujogi <pratap.nirujogi@amd.com>
Date: Mon, 9 Jun 2025 11:53:56 -0400
Subject: [PATCH 0859/1334] i2c: amd-isp: Initialize unique adapter name

Initialize unique name for amdisp i2c adapter, which is used
in the platform driver to detect the matching adapter for
i2c_client creation.

Add definition of amdisp i2c adapter name in a new header file
(include/linux/soc/amd/isp4_misc.h) as it is referred in different
driver modules.

Tested-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Pratap Nirujogi <pratap.nirujogi@amd.com>
Signed-off-by: Andi Shyti <andi.shyti@kernel.org>
Link: https://lore.kernel.org/r/20250609155601.1477055-3-pratap.nirujogi@amd.com
---
 MAINTAINERS                                |  1 +
 drivers/i2c/busses/i2c-designware-amdisp.c |  2 ++
 include/linux/soc/amd/isp4_misc.h          | 12 ++++++++++++
 3 files changed, 15 insertions(+)
 create mode 100644 include/linux/soc/amd/isp4_misc.h

diff --git a/MAINTAINERS b/MAINTAINERS
index c3f7fbd0d67a..8719f097aae3 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -24063,6 +24063,7 @@ M:	Bin Du <bin.du@amd.com>
 L:	linux-i2c@vger.kernel.org
 S:	Maintained
 F:	drivers/i2c/busses/i2c-designware-amdisp.c
+F:	include/linux/soc/amd/isp4_misc.h
 
 SYNOPSYS DESIGNWARE MMC/SD/SDIO DRIVER
 M:	Jaehoon Chung <jh80.chung@samsung.com>
diff --git a/drivers/i2c/busses/i2c-designware-amdisp.c b/drivers/i2c/busses/i2c-designware-amdisp.c
index ad6f08338124..450793d5f839 100644
--- a/drivers/i2c/busses/i2c-designware-amdisp.c
+++ b/drivers/i2c/busses/i2c-designware-amdisp.c
@@ -8,6 +8,7 @@
 #include <linux/module.h>
 #include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
+#include <linux/soc/amd/isp4_misc.h>
 
 #include "i2c-designware-core.h"
 
@@ -62,6 +63,7 @@ static int amd_isp_dw_i2c_plat_probe(struct platform_device *pdev)
 
 	adap = &isp_i2c_dev->adapter;
 	adap->owner = THIS_MODULE;
+	scnprintf(adap->name, sizeof(adap->name), AMDISP_I2C_ADAP_NAME);
 	ACPI_COMPANION_SET(&adap->dev, ACPI_COMPANION(&pdev->dev));
 	adap->dev.of_node = pdev->dev.of_node;
 	/* use dynamically allocated adapter id */
diff --git a/include/linux/soc/amd/isp4_misc.h b/include/linux/soc/amd/isp4_misc.h
new file mode 100644
index 000000000000..6738796986a7
--- /dev/null
+++ b/include/linux/soc/amd/isp4_misc.h
@@ -0,0 +1,12 @@
+// SPDX-License-Identifier: GPL-2.0+
+
+/*
+ * Copyright (C) 2025 Advanced Micro Devices, Inc.
+ */
+
+#ifndef __SOC_ISP4_MISC_H
+#define __SOC_ISP4_MISC_H
+
+#define AMDISP_I2C_ADAP_NAME "AMDISP DesignWare I2C adapter"
+
+#endif

From 577c1e0ef351e41aba764816232a9feb7a9b3969 Mon Sep 17 00:00:00 2001
From: Pratap Nirujogi <pratap.nirujogi@amd.com>
Date: Mon, 9 Jun 2025 11:53:57 -0400
Subject: [PATCH 0860/1334] platform/x86: Use i2c adapter name to fix build
 errors
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Use adapater->name inplace of adapter->owner->name to fix
build issues when CONFIG_MODULES is not defined.

Fixes: 90b85567e457 ("platform/x86: Add AMD ISP platform config for OV05C10")
Reported-by: Randy Dunlap <rdunlap@infradead.org>
Link: https://lore.kernel.org/all/04577a46-9add-420c-b181-29bad582026d@infradead.org
Tested-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Pratap Nirujogi <pratap.nirujogi@amd.com>
Requires: 942e1aece13e ("i2c: designware: Initialize adapter name only when not set"
Requires: c8dc57916973 ("i2c: amd-isp: Initialize unique adapter name")
Acked-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Andi Shyti <andi.shyti@kernel.org>
Link: https://lore.kernel.org/r/20250609155601.1477055-4-pratap.nirujogi@amd.com
---
 drivers/platform/x86/amd/amd_isp4.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/platform/x86/amd/amd_isp4.c b/drivers/platform/x86/amd/amd_isp4.c
index 0cc01441bcbb..9f291aeb35f1 100644
--- a/drivers/platform/x86/amd/amd_isp4.c
+++ b/drivers/platform/x86/amd/amd_isp4.c
@@ -11,6 +11,7 @@
 #include <linux/mutex.h>
 #include <linux/platform_device.h>
 #include <linux/property.h>
+#include <linux/soc/amd/isp4_misc.h>
 #include <linux/string.h>
 #include <linux/types.h>
 #include <linux/units.h>
@@ -151,7 +152,7 @@ MODULE_DEVICE_TABLE(acpi, amdisp_sensor_ids);
 
 static inline bool is_isp_i2c_adapter(struct i2c_adapter *adap)
 {
-	return !strcmp(adap->owner->name, "i2c_designware_amdisp");
+	return !strcmp(adap->name, AMDISP_I2C_ADAP_NAME);
 }
 
 static void instantiate_isp_i2c_client(struct amdisp_platform *isp4_platform,

From 666c23af755dccca8c25b5d5200ca28153c69a05 Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Sat, 14 Jun 2025 16:59:26 +0200
Subject: [PATCH 0861/1334] i2c: omap: Fix an error handling path in
 omap_i2c_probe()

If an error occurs after calling mux_state_select(), mux_state_deselect()
should be called as already done in the remove function.

Fixes: b6ef830c60b6 ("i2c: omap: Add support for setting mux")
Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Cc: <stable@vger.kernel.org> # v6.15+
Signed-off-by: Andi Shyti <andi.shyti@kernel.org>
Link: https://lore.kernel.org/r/998542981b6d2435c057dd8b9fe71743927babab.1749913149.git.christophe.jaillet@wanadoo.fr
---
 drivers/i2c/busses/i2c-omap.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/i2c/busses/i2c-omap.c b/drivers/i2c/busses/i2c-omap.c
index f1cc26ac5b80..8b01df3cc8e9 100644
--- a/drivers/i2c/busses/i2c-omap.c
+++ b/drivers/i2c/busses/i2c-omap.c
@@ -1461,13 +1461,13 @@ omap_i2c_probe(struct platform_device *pdev)
 		if (IS_ERR(mux_state)) {
 			r = PTR_ERR(mux_state);
 			dev_dbg(&pdev->dev, "failed to get I2C mux: %d\n", r);
-			goto err_disable_pm;
+			goto err_put_pm;
 		}
 		omap->mux_state = mux_state;
 		r = mux_state_select(omap->mux_state);
 		if (r) {
 			dev_err(&pdev->dev, "failed to select I2C mux: %d\n", r);
-			goto err_disable_pm;
+			goto err_put_pm;
 		}
 	}
 
@@ -1515,6 +1515,9 @@ omap_i2c_probe(struct platform_device *pdev)
 
 err_unuse_clocks:
 	omap_i2c_write_reg(omap, OMAP_I2C_CON_REG, 0);
+	if (omap->mux_state)
+		mux_state_deselect(omap->mux_state);
+err_put_pm:
 	pm_runtime_dont_use_autosuspend(omap->dev);
 	pm_runtime_put_sync(omap->dev);
 err_disable_pm:

From 5e9388f7984a9cc7e659a105113f6ccf0aebedd0 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Wed, 25 Jun 2025 17:03:55 -0400
Subject: [PATCH 0862/1334] selftests/bpf: adapt one more case in test_lru_map
 to the new target_free

The below commit that updated BPF_MAP_TYPE_LRU_HASH free target,
also updated tools/testing/selftests/bpf/test_lru_map to match.

But that missed one case that passes with 4 cores, but fails at
higher cpu counts.

Update test_lru_sanity3 to also adjust its expectation of target_free.

This time tested with 1, 4, 16, 64 and 384 cpu count.

Fixes: d4adf1c9ee77 ("bpf: Adjust free target to avoid global starvation of LRU map")
Signed-off-by: Willem de Bruijn <willemb@google.com>
Link: https://lore.kernel.org/r/20250625210412.2732970-1-willemdebruijn.kernel@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/test_lru_map.c | 33 ++++++++++++----------
 1 file changed, 18 insertions(+), 15 deletions(-)

diff --git a/tools/testing/selftests/bpf/test_lru_map.c b/tools/testing/selftests/bpf/test_lru_map.c
index 4ae83f4b7fc7..0921939532c6 100644
--- a/tools/testing/selftests/bpf/test_lru_map.c
+++ b/tools/testing/selftests/bpf/test_lru_map.c
@@ -138,6 +138,12 @@ static int sched_next_online(int pid, int *next_to_try)
 	return ret;
 }
 
+/* Derive target_free from map_size, same as bpf_common_lru_populate */
+static unsigned int __tgt_size(unsigned int map_size)
+{
+	return (map_size / nr_cpus) / 2;
+}
+
 /* Inverse of how bpf_common_lru_populate derives target_free from map_size. */
 static unsigned int __map_size(unsigned int tgt_free)
 {
@@ -410,12 +416,12 @@ static void test_lru_sanity2(int map_type, int map_flags, unsigned int tgt_free)
 	printf("Pass\n");
 }
 
-/* Size of the LRU map is 2*tgt_free
- * It is to test the active/inactive list rotation
- * Insert 1 to 2*tgt_free (+2*tgt_free keys)
- * Lookup key 1 to tgt_free*3/2
- * Add 1+2*tgt_free to tgt_free*5/2 (+tgt_free/2 keys)
- *  => key 1+tgt_free*3/2 to 2*tgt_free are removed from LRU
+/* Test the active/inactive list rotation
+ *
+ * Fill the whole map, deplete the free list.
+ * Reference all except the last lru->target_free elements.
+ * Insert lru->target_free new elements. This triggers one shrink.
+ * Verify that the non-referenced elements are replaced.
  */
 static void test_lru_sanity3(int map_type, int map_flags, unsigned int tgt_free)
 {
@@ -434,8 +440,7 @@ static void test_lru_sanity3(int map_type, int map_flags, unsigned int tgt_free)
 
 	assert(sched_next_online(0, &next_cpu) != -1);
 
-	batch_size = tgt_free / 2;
-	assert(batch_size * 2 == tgt_free);
+	batch_size = __tgt_size(tgt_free);
 
 	map_size = tgt_free * 2;
 	lru_map_fd = create_map(map_type, map_flags, map_size);
@@ -446,23 +451,21 @@ static void test_lru_sanity3(int map_type, int map_flags, unsigned int tgt_free)
 
 	value[0] = 1234;
 
-	/* Insert 1 to 2*tgt_free (+2*tgt_free keys) */
-	end_key = 1 + (2 * tgt_free);
+	/* Fill the map */
+	end_key = 1 + map_size;
 	for (key = 1; key < end_key; key++)
 		assert(!bpf_map_update_elem(lru_map_fd, &key, value,
 					    BPF_NOEXIST));
 
-	/* Lookup key 1 to tgt_free*3/2 */
-	end_key = tgt_free + batch_size;
+	/* Reference all but the last batch_size */
+	end_key = 1 + map_size - batch_size;
 	for (key = 1; key < end_key; key++) {
 		assert(!bpf_map_lookup_elem_with_ref_bit(lru_map_fd, key, value));
 		assert(!bpf_map_update_elem(expected_map_fd, &key, value,
 					    BPF_NOEXIST));
 	}
 
-	/* Add 1+2*tgt_free to tgt_free*5/2
-	 * (+tgt_free/2 keys)
-	 */
+	/* Insert new batch_size: replaces the non-referenced elements */
 	key = 2 * tgt_free + 1;
 	end_key = key + batch_size;
 	for (; key < end_key; key++) {

From c4890963350dcf4e9a909bae23665921fba4ad27 Mon Sep 17 00:00:00 2001
From: Thomas Fourier <fourier.thomas@gmail.com>
Date: Tue, 24 Jun 2025 08:41:47 +0200
Subject: [PATCH 0863/1334] atm: idt77252: Add missing `dma_map_error()`

The DMA map functions can fail and should be tested for errors.

Signed-off-by: Thomas Fourier <fourier.thomas@gmail.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250624064148.12815-3-fourier.thomas@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/atm/idt77252.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/atm/idt77252.c b/drivers/atm/idt77252.c
index 1206ab764ba9..f2e91b7d79f0 100644
--- a/drivers/atm/idt77252.c
+++ b/drivers/atm/idt77252.c
@@ -852,6 +852,8 @@ queue_skb(struct idt77252_dev *card, struct vc_map *vc,
 
 	IDT77252_PRV_PADDR(skb) = dma_map_single(&card->pcidev->dev, skb->data,
 						 skb->len, DMA_TO_DEVICE);
+	if (dma_mapping_error(&card->pcidev->dev, IDT77252_PRV_PADDR(skb)))
+		return -ENOMEM;
 
 	error = -EINVAL;
 
@@ -1857,6 +1859,8 @@ add_rx_skb(struct idt77252_dev *card, int queue,
 		paddr = dma_map_single(&card->pcidev->dev, skb->data,
 				       skb_end_pointer(skb) - skb->data,
 				       DMA_FROM_DEVICE);
+		if (dma_mapping_error(&card->pcidev->dev, paddr))
+			goto outpoolrm;
 		IDT77252_PRV_PADDR(skb) = paddr;
 
 		if (push_rx_skb(card, skb, queue)) {
@@ -1871,6 +1875,7 @@ outunmap:
 	dma_unmap_single(&card->pcidev->dev, IDT77252_PRV_PADDR(skb),
 			 skb_end_pointer(skb) - skb->data, DMA_FROM_DEVICE);
 
+outpoolrm:
 	handle = IDT77252_PRV_POOL(skb);
 	card->sbpool[POOL_QUEUE(handle)].skb[POOL_INDEX(handle)] = NULL;
 

From 7b515f35a911fdc31fbde6531828dcd6ae9803d3 Mon Sep 17 00:00:00 2001
From: Simon Horman <horms@kernel.org>
Date: Tue, 24 Jun 2025 17:35:12 +0100
Subject: [PATCH 0864/1334] net: enetc: Correct endianness handling in
 _enetc_rd_reg64

enetc_hw.h provides two versions of _enetc_rd_reg64.
One which simply calls ioread64() when available.
And another that composes the 64-bit result from ioread32() calls.

In the second case the code appears to assume that each ioread32() call
returns a little-endian value. However both the shift and logical or
used to compose the return value would not work correctly on big endian
systems if this were the case. Moreover, this is inconsistent with the
first case where the return value of ioread64() is assumed to be in host
byte order.

It appears that the correct approach is for both versions to treat the
return value of ioread*() functions as being in host byte order. And
this patch corrects the ioread32()-based version to do so.

This is a bug but would only manifest on big endian systems
that make use of the ioread32-based implementation of _enetc_rd_reg64.
While all in-tree users of this driver are little endian and
make use of the ioread64-based implementation of _enetc_rd_reg64.
Thus, no in-tree user of this driver is affected by this bug.

Flagged by Sparse.
Compile tested only.

Fixes: 16eb4c85c964 ("enetc: Add ethtool statistics")
Closes: https://lore.kernel.org/all/AM9PR04MB850500D3FC24FE23DEFCEA158879A@AM9PR04MB8505.eurprd04.prod.outlook.com/
Signed-off-by: Simon Horman <horms@kernel.org>
Reviewed-by: Wei Fang <wei.fang@nxp.com>
Link: https://patch.msgid.link/20250624-etnetc-le-v1-1-a73a95d96e4e@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/freescale/enetc/enetc_hw.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/freescale/enetc/enetc_hw.h b/drivers/net/ethernet/freescale/enetc/enetc_hw.h
index 4098f01479bc..53e8d18c7a34 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_hw.h
+++ b/drivers/net/ethernet/freescale/enetc/enetc_hw.h
@@ -507,7 +507,7 @@ static inline u64 _enetc_rd_reg64(void __iomem *reg)
 		tmp = ioread32(reg + 4);
 	} while (high != tmp);
 
-	return le64_to_cpu((__le64)high << 32 | low);
+	return (u64)high << 32 | low;
 }
 #endif
 

From 2434ccb94dfc8e036c81e9d7c77fca6dc1dc2590 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 24 Jun 2025 14:09:53 -0700
Subject: [PATCH 0865/1334] netlink: specs: nfsd: replace underscores with
 dashes in names

We're trying to add a strict regexp for the name format in the spec.
Underscores will not be allowed, dashes should be used instead.
This makes no difference to C (codegen, if used, replaces special
chars in names) but it gives more uniform naming in Python.

Fixes: 13727f85b49b ("NFSD: introduce netlink stubs")
Reviewed-by: Donald Hunter <donald.hunter@gmail.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Link: https://patch.msgid.link/20250624211002.3475021-2-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/netlink/specs/nfsd.yaml | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/Documentation/netlink/specs/nfsd.yaml b/Documentation/netlink/specs/nfsd.yaml
index c87658114852..8d1a3c01708f 100644
--- a/Documentation/netlink/specs/nfsd.yaml
+++ b/Documentation/netlink/specs/nfsd.yaml
@@ -27,7 +27,7 @@ attribute-sets:
         name: proc
         type: u32
       -
-        name: service_time
+        name: service-time
         type: s64
       -
         name: pad
@@ -139,7 +139,7 @@ operations:
             - prog
             - version
             - proc
-            - service_time
+            - service-time
             - saddr4
             - daddr4
             - saddr6

From 791a9ed0a40dfa70fe793dcecf950273255cbb84 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 24 Jun 2025 14:09:54 -0700
Subject: [PATCH 0866/1334] netlink: specs: fou: replace underscores with
 dashes in names

We're trying to add a strict regexp for the name format in the spec.
Underscores will not be allowed, dashes should be used instead.
This makes no difference to C (codegen, if used, replaces special
chars in names) but it gives more uniform naming in Python.

Fixes: 4eb77b4ecd3c ("netlink: add a proto specification for FOU")
Reviewed-by: Donald Hunter <donald.hunter@gmail.com>
Link: https://patch.msgid.link/20250624211002.3475021-3-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/netlink/specs/fou.yaml | 36 ++++++++++++++--------------
 1 file changed, 18 insertions(+), 18 deletions(-)

diff --git a/Documentation/netlink/specs/fou.yaml b/Documentation/netlink/specs/fou.yaml
index 0af5ab842c04..b02ab19817d3 100644
--- a/Documentation/netlink/specs/fou.yaml
+++ b/Documentation/netlink/specs/fou.yaml
@@ -15,7 +15,7 @@ kernel-policy: global
 definitions:
   -
     type: enum
-    name: encap_type
+    name: encap-type
     name-prefix: fou-encap-
     enum-name:
     entries: [ unspec, direct, gue ]
@@ -43,26 +43,26 @@ attribute-sets:
         name: type
         type: u8
       -
-        name: remcsum_nopartial
+        name: remcsum-nopartial
         type: flag
       -
-        name: local_v4
+        name: local-v4
         type: u32
       -
-        name: local_v6
+        name: local-v6
         type: binary
         checks:
           min-len: 16
       -
-        name: peer_v4
+        name: peer-v4
         type: u32
       -
-        name: peer_v6
+        name: peer-v6
         type: binary
         checks:
           min-len: 16
       -
-        name: peer_port
+        name: peer-port
         type: u16
         byte-order: big-endian
       -
@@ -90,12 +90,12 @@ operations:
             - port
             - ipproto
             - type
-            - remcsum_nopartial
-            - local_v4
-            - peer_v4
-            - local_v6
-            - peer_v6
-            - peer_port
+            - remcsum-nopartial
+            - local-v4
+            - peer-v4
+            - local-v6
+            - peer-v6
+            - peer-port
             - ifindex
 
     -
@@ -112,11 +112,11 @@ operations:
             - af
             - ifindex
             - port
-            - peer_port
-            - local_v4
-            - peer_v4
-            - local_v6
-            - peer_v6
+            - peer-port
+            - local-v4
+            - peer-v4
+            - local-v6
+            - peer-v6
 
     -
       name: get

From 07caaf875c937e5f0a262a1dbad307d08ecc8673 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 24 Jun 2025 14:09:55 -0700
Subject: [PATCH 0867/1334] netlink: specs: ethtool: replace underscores with
 dashes in names

We're trying to add a strict regexp for the name format in the spec.
Underscores will not be allowed, dashes should be used instead.
This makes no difference to C (codegen replaces special chars in names)
but gives more uniform naming in Python.

Fixes: 13e59344fb9d ("net: ethtool: add support for symmetric-xor RSS hash")
Fixes: 46fb3ba95b93 ("ethtool: Add an interface for flashing transceiver modules' firmware")
Reviewed-by: Kory Maincent <kory.maincent@bootlin.com>
Reviewed-by: Donald Hunter <donald.hunter@gmail.com>
Link: https://patch.msgid.link/20250624211002.3475021-4-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/netlink/specs/ethtool.yaml                 | 6 +++---
 tools/testing/selftests/drivers/net/hw/rss_input_xfrm.py | 2 +-
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/Documentation/netlink/specs/ethtool.yaml b/Documentation/netlink/specs/ethtool.yaml
index 72a076b0e1b5..348c6ad548f5 100644
--- a/Documentation/netlink/specs/ethtool.yaml
+++ b/Documentation/netlink/specs/ethtool.yaml
@@ -48,7 +48,7 @@ definitions:
         name: started
         doc: The firmware flashing process has started.
       -
-        name: in_progress
+        name: in-progress
         doc: The firmware flashing process is in progress.
       -
         name: completed
@@ -1422,7 +1422,7 @@ attribute-sets:
         name: hkey
         type: binary
       -
-        name: input_xfrm
+        name: input-xfrm
         type: u32
       -
         name: start-context
@@ -2238,7 +2238,7 @@ operations:
             - hfunc
             - indir
             - hkey
-            - input_xfrm
+            - input-xfrm
       dump:
         request:
           attributes:
diff --git a/tools/testing/selftests/drivers/net/hw/rss_input_xfrm.py b/tools/testing/selftests/drivers/net/hw/rss_input_xfrm.py
index f439c434ba36..648ff50bc1c3 100755
--- a/tools/testing/selftests/drivers/net/hw/rss_input_xfrm.py
+++ b/tools/testing/selftests/drivers/net/hw/rss_input_xfrm.py
@@ -38,7 +38,7 @@ def test_rss_input_xfrm(cfg, ipver):
         raise KsftSkipEx("socket.SO_INCOMING_CPU was added in Python 3.11")
 
     input_xfrm = cfg.ethnl.rss_get(
-        {'header': {'dev-name': cfg.ifname}}).get('input_xfrm')
+        {'header': {'dev-name': cfg.ifname}}).get('input-xfrm')
 
     # Check for symmetric xor/or-xor
     if not input_xfrm or (input_xfrm != 1 and input_xfrm != 2):

From 354592f19c7b0ac5983d56d8594a76aa3437f0a6 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 24 Jun 2025 14:09:56 -0700
Subject: [PATCH 0868/1334] netlink: specs: dpll: replace underscores with
 dashes in names

We're trying to add a strict regexp for the name format in the spec.
Underscores will not be allowed, dashes should be used instead.
This makes no difference to C (codegen, if used, replaces special
chars in names) but it gives more uniform naming in Python.

Fixes: 3badff3a25d8 ("dpll: spec: Add Netlink spec in YAML")
Reviewed-by: Vadim Fedorenko <vadim.fedorenko@linux.dev>
Reviewed-by: Donald Hunter <donald.hunter@gmail.com>
Link: https://patch.msgid.link/20250624211002.3475021-5-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/netlink/specs/dpll.yaml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/netlink/specs/dpll.yaml b/Documentation/netlink/specs/dpll.yaml
index 8feefeae5376..f434140b538e 100644
--- a/Documentation/netlink/specs/dpll.yaml
+++ b/Documentation/netlink/specs/dpll.yaml
@@ -188,7 +188,7 @@ definitions:
     value: 10000
   -
     type: const
-    name: pin-frequency-77_5-khz
+    name: pin-frequency-77-5-khz
     value: 77500
   -
     type: const

From 9407680945145cc34fafd0e9f802b03574620d43 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 24 Jun 2025 14:09:57 -0700
Subject: [PATCH 0869/1334] netlink: specs: devlink: replace underscores with
 dashes in names

We're trying to add a strict regexp for the name format in the spec.
Underscores will not be allowed, dashes should be used instead.
This makes no difference to C (codegen, if used, replaces special
chars in names) but it gives more uniform naming in Python.

Fixes: 429ac6211494 ("devlink: define enum for attr types of dynamic attributes")
Fixes: f2f9dd164db0 ("netlink: specs: devlink: add the remaining command to generate complete split_ops")
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Donald Hunter <donald.hunter@gmail.com>
Link: https://patch.msgid.link/20250624211002.3475021-6-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/netlink/specs/devlink.yaml | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/Documentation/netlink/specs/devlink.yaml b/Documentation/netlink/specs/devlink.yaml
index 05fee1b7fe19..38ddc04f9e6d 100644
--- a/Documentation/netlink/specs/devlink.yaml
+++ b/Documentation/netlink/specs/devlink.yaml
@@ -38,15 +38,15 @@ definitions:
       -
         name: dsa
       -
-        name: pci_pf
+        name: pci-pf
       -
-        name: pci_vf
+        name: pci-vf
       -
         name: virtual
       -
         name: unused
       -
-        name: pci_sf
+        name: pci-sf
   -
     type: enum
     name: port-fn-state
@@ -220,7 +220,7 @@ definitions:
       -
         name: flag
       -
-        name: nul_string
+        name: nul-string
         value: 10
       -
         name: binary

From e40d3d0931d2b1e86ba2ca0e9c95f90ac6dd5525 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 24 Jun 2025 14:09:58 -0700
Subject: [PATCH 0870/1334] netlink: specs: ovs_flow: replace underscores with
 dashes in names

We're trying to add a strict regexp for the name format in the spec.
Underscores will not be allowed, dashes should be used instead.
This makes no difference to C (codegen, if used, replaces special
chars in names) but it gives more uniform naming in Python.

Fixes: 93b230b549bc ("netlink: specs: add ynl spec for ovs_flow")
Reviewed-by: Donald Hunter <donald.hunter@gmail.com>
Reviewed-by: Ilya Maximets <i.maximets@ovn.org>
Reviewed-by: Eelco Chaudron <echaudro@redhat.com>
Link: https://patch.msgid.link/20250624211002.3475021-7-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/netlink/specs/ovs_flow.yaml | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/Documentation/netlink/specs/ovs_flow.yaml b/Documentation/netlink/specs/ovs_flow.yaml
index 46f5d1cd8a5f..7974aa7d8905 100644
--- a/Documentation/netlink/specs/ovs_flow.yaml
+++ b/Documentation/netlink/specs/ovs_flow.yaml
@@ -216,7 +216,7 @@ definitions:
     type: struct
     members:
       -
-        name: nd_target
+        name: nd-target
         type: binary
         len: 16
         byte-order: big-endian
@@ -258,12 +258,12 @@ definitions:
     type: struct
     members:
       -
-        name: vlan_tpid
+        name: vlan-tpid
         type: u16
         byte-order: big-endian
         doc: Tag protocol identifier (TPID) to push.
       -
-        name: vlan_tci
+        name: vlan-tci
         type: u16
         byte-order: big-endian
         doc: Tag control identifier (TCI) to push.

From 9e6dd4c256d0774701637b958ba682eff4991277 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 24 Jun 2025 14:09:59 -0700
Subject: [PATCH 0871/1334] netlink: specs: mptcp: replace underscores with
 dashes in names

We're trying to add a strict regexp for the name format in the spec.
Underscores will not be allowed, dashes should be used instead.
This makes no difference to C (codegen, if used, replaces special
chars in names) but it gives more uniform naming in Python.

Fixes: bc8aeb2045e2 ("Documentation: netlink: add a YAML spec for mptcp")
Reviewed-by: Davide Caratti <dcaratti@redhat.com>
Reviewed-by: Donald Hunter <donald.hunter@gmail.com>
Reviewed-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20250624211002.3475021-8-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/netlink/specs/mptcp_pm.yaml | 8 ++++----
 include/uapi/linux/mptcp_pm.h             | 6 +++---
 2 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/Documentation/netlink/specs/mptcp_pm.yaml b/Documentation/netlink/specs/mptcp_pm.yaml
index dfd017780d2f..fb57860fe778 100644
--- a/Documentation/netlink/specs/mptcp_pm.yaml
+++ b/Documentation/netlink/specs/mptcp_pm.yaml
@@ -57,21 +57,21 @@ definitions:
       doc: >-
         A new subflow has been established. 'error' should not be set.
         Attributes: token, family, loc_id, rem_id, saddr4 | saddr6, daddr4 |
-        daddr6, sport, dport, backup, if_idx [, error].
+        daddr6, sport, dport, backup, if-idx [, error].
      -
       name: sub-closed
       doc: >-
         A subflow has been closed. An error (copy of sk_err) could be set if an
         error has been detected for this subflow.
         Attributes: token, family, loc_id, rem_id, saddr4 | saddr6, daddr4 |
-        daddr6, sport, dport, backup, if_idx [, error].
+        daddr6, sport, dport, backup, if-idx [, error].
      -
       name: sub-priority
       value: 13
       doc: >-
         The priority of a subflow has changed. 'error' should not be set.
         Attributes: token, family, loc_id, rem_id, saddr4 | saddr6, daddr4 |
-        daddr6, sport, dport, backup, if_idx [, error].
+        daddr6, sport, dport, backup, if-idx [, error].
      -
       name: listener-created
       value: 15
@@ -255,7 +255,7 @@ attribute-sets:
         name: timeout
         type: u32
       -
-        name: if_idx
+        name: if-idx
         type: u32
       -
         name: reset-reason
diff --git a/include/uapi/linux/mptcp_pm.h b/include/uapi/linux/mptcp_pm.h
index 84fa8a21dfd0..6ac84b2f636c 100644
--- a/include/uapi/linux/mptcp_pm.h
+++ b/include/uapi/linux/mptcp_pm.h
@@ -27,14 +27,14 @@
  *   token, rem_id.
  * @MPTCP_EVENT_SUB_ESTABLISHED: A new subflow has been established. 'error'
  *   should not be set. Attributes: token, family, loc_id, rem_id, saddr4 |
- *   saddr6, daddr4 | daddr6, sport, dport, backup, if_idx [, error].
+ *   saddr6, daddr4 | daddr6, sport, dport, backup, if-idx [, error].
  * @MPTCP_EVENT_SUB_CLOSED: A subflow has been closed. An error (copy of
  *   sk_err) could be set if an error has been detected for this subflow.
  *   Attributes: token, family, loc_id, rem_id, saddr4 | saddr6, daddr4 |
- *   daddr6, sport, dport, backup, if_idx [, error].
+ *   daddr6, sport, dport, backup, if-idx [, error].
  * @MPTCP_EVENT_SUB_PRIORITY: The priority of a subflow has changed. 'error'
  *   should not be set. Attributes: token, family, loc_id, rem_id, saddr4 |
- *   saddr6, daddr4 | daddr6, sport, dport, backup, if_idx [, error].
+ *   saddr6, daddr4 | daddr6, sport, dport, backup, if-idx [, error].
  * @MPTCP_EVENT_LISTENER_CREATED: A new PM listener is created. Attributes:
  *   family, sport, saddr4 | saddr6.
  * @MPTCP_EVENT_LISTENER_CLOSED: A PM listener is closed. Attributes: family,

From 8d7e211ea925e050882c762ddf8cf2da78856dfb Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 24 Jun 2025 14:10:00 -0700
Subject: [PATCH 0872/1334] netlink: specs: rt-link: replace underscores with
 dashes in names

We're trying to add a strict regexp for the name format in the spec.
Underscores will not be allowed, dashes should be used instead.
This makes no difference to C (codegen, if used, replaces special
chars in names) but it gives more uniform naming in Python.

Fixes: b2f63d904e72 ("doc/netlink: Add spec for rt link messages")
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Donald Hunter <donald.hunter@gmail.com>
Link: https://patch.msgid.link/20250624211002.3475021-9-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/netlink/specs/rt-link.yaml | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/Documentation/netlink/specs/rt-link.yaml b/Documentation/netlink/specs/rt-link.yaml
index b41b31eebcae..28c4cf66517c 100644
--- a/Documentation/netlink/specs/rt-link.yaml
+++ b/Documentation/netlink/specs/rt-link.yaml
@@ -603,7 +603,7 @@ definitions:
         name: optmask
         type: u32
   -
-    name: if_stats_msg
+    name: if-stats-msg
     type: struct
     members:
       -
@@ -2486,7 +2486,7 @@ operations:
       name: getstats
       doc: Get / dump link stats.
       attribute-set: stats-attrs
-      fixed-header: if_stats_msg
+      fixed-header: if-stats-msg
       do:
         request:
           value: 94

From eef0eaeca7fa8e358a31e89802f564451b797718 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 24 Jun 2025 14:10:01 -0700
Subject: [PATCH 0873/1334] netlink: specs: tc: replace underscores with dashes
 in names

We're trying to add a strict regexp for the name format in the spec.
Underscores will not be allowed, dashes should be used instead.
This makes no difference to C (codegen, if used, replaces special
chars in names) but it gives more uniform naming in Python.

Fixes: a1bcfde83669 ("doc/netlink/specs: Add a spec for tc")
Reviewed-by: Donald Hunter <donald.hunter@gmail.com>
Link: https://patch.msgid.link/20250624211002.3475021-10-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/netlink/specs/tc.yaml | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/Documentation/netlink/specs/tc.yaml b/Documentation/netlink/specs/tc.yaml
index cb7ea7d62e56..42d74c9aeb54 100644
--- a/Documentation/netlink/specs/tc.yaml
+++ b/Documentation/netlink/specs/tc.yaml
@@ -232,7 +232,7 @@ definitions:
         type: u8
         doc: log(P_max / (qth-max - qth-min))
       -
-        name: Scell_log
+        name: Scell-log
         type: u8
         doc: cell size for idle damping
       -
@@ -253,7 +253,7 @@ definitions:
         name: DPs
         type: u32
       -
-        name: def_DP
+        name: def-DP
         type: u32
       -
         name: grio

From af852f1f1c951d43b36881302fd10d9f898cdb54 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 24 Jun 2025 14:10:02 -0700
Subject: [PATCH 0874/1334] netlink: specs: enforce strict naming of properties

Add a regexp to make sure all names which may end up being visible
to the user consist of lower case characters, numbers and dashes.
Underscores keep sneaking into the specs, which is not visible
in the C code but makes the Python and alike inconsistent.

Note that starting with a number is okay, as in C the full
name will include the family name.

For legacy families we can't enforce the naming in the family
name or the multicast group names, as these are part of the
binary uAPI of the kernel.

For classic netlink we need to allow capital letters in names
of struct members. TC has some structs with capitalized members.

Reviewed-by: Donald Hunter <donald.hunter@gmail.com>
Link: https://patch.msgid.link/20250624211002.3475021-11-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/netlink/genetlink-legacy.yaml | 15 +++++++++------
 Documentation/netlink/genetlink.yaml        | 17 ++++++++++-------
 Documentation/netlink/netlink-raw.yaml      | 18 ++++++++++++------
 3 files changed, 31 insertions(+), 19 deletions(-)

diff --git a/Documentation/netlink/genetlink-legacy.yaml b/Documentation/netlink/genetlink-legacy.yaml
index 4cbfe666e6f5..b29d62eefa16 100644
--- a/Documentation/netlink/genetlink-legacy.yaml
+++ b/Documentation/netlink/genetlink-legacy.yaml
@@ -6,6 +6,9 @@ $schema: https://json-schema.org/draft-07/schema
 
 # Common defines
 $defs:
+  name:
+    type: string
+    pattern: ^[0-9a-z-]+$
   uint:
     type: integer
     minimum: 0
@@ -76,7 +79,7 @@ properties:
       additionalProperties: False
       properties:
         name:
-          type: string
+          $ref: '#/$defs/name'
         header:
           description: For C-compatible languages, header which already defines this value.
           type: string
@@ -103,7 +106,7 @@ properties:
                 additionalProperties: False
                 properties:
                   name:
-                    type: string
+                    $ref: '#/$defs/name'
                   value:
                     type: integer
                   doc:
@@ -132,7 +135,7 @@ properties:
             additionalProperties: False
             properties:
               name:
-                type: string
+                $ref: '#/$defs/name'
               type:
                 description: The netlink attribute type
                 enum: [ u8, u16, u32, u64, s8, s16, s32, s64, string, binary ]
@@ -169,7 +172,7 @@ properties:
         name:
           description: |
             Name used when referring to this space in other definitions, not used outside of the spec.
-          type: string
+          $ref: '#/$defs/name'
         name-prefix:
           description: |
             Prefix for the C enum name of the attributes. Default family[name]-set[name]-a-
@@ -206,7 +209,7 @@ properties:
             additionalProperties: False
             properties:
               name:
-                type: string
+                $ref: '#/$defs/name'
               type: &attr-type
                 description: The netlink attribute type
                 enum: [ unused, pad, flag, binary, bitfield32,
@@ -348,7 +351,7 @@ properties:
           properties:
             name:
               description: Name of the operation, also defining its C enum value in uAPI.
-              type: string
+              $ref: '#/$defs/name'
             doc:
               description: Documentation for the command.
               type: string
diff --git a/Documentation/netlink/genetlink.yaml b/Documentation/netlink/genetlink.yaml
index 40efbbad76ab..7b1ec153e834 100644
--- a/Documentation/netlink/genetlink.yaml
+++ b/Documentation/netlink/genetlink.yaml
@@ -6,6 +6,9 @@ $schema: https://json-schema.org/draft-07/schema
 
 # Common defines
 $defs:
+  name:
+    type: string
+    pattern: ^[0-9a-z-]+$
   uint:
     type: integer
     minimum: 0
@@ -29,7 +32,7 @@ additionalProperties: False
 properties:
   name:
     description: Name of the genetlink family.
-    type: string
+    $ref: '#/$defs/name'
   doc:
     type: string
   protocol:
@@ -48,7 +51,7 @@ properties:
       additionalProperties: False
       properties:
         name:
-          type: string
+          $ref: '#/$defs/name'
         header:
           description: For C-compatible languages, header which already defines this value.
           type: string
@@ -75,7 +78,7 @@ properties:
                 additionalProperties: False
                 properties:
                   name:
-                    type: string
+                    $ref: '#/$defs/name'
                   value:
                     type: integer
                   doc:
@@ -96,7 +99,7 @@ properties:
         name:
           description: |
             Name used when referring to this space in other definitions, not used outside of the spec.
-          type: string
+          $ref: '#/$defs/name'
         name-prefix:
           description: |
             Prefix for the C enum name of the attributes. Default family[name]-set[name]-a-
@@ -121,7 +124,7 @@ properties:
             additionalProperties: False
             properties:
               name:
-                type: string
+                $ref: '#/$defs/name'
               type: &attr-type
                 enum: [ unused, pad, flag, binary,
                         uint, sint, u8, u16, u32, u64, s8, s16, s32, s64,
@@ -243,7 +246,7 @@ properties:
           properties:
             name:
               description: Name of the operation, also defining its C enum value in uAPI.
-              type: string
+              $ref: '#/$defs/name'
             doc:
               description: Documentation for the command.
               type: string
@@ -327,7 +330,7 @@ properties:
             name:
               description: |
                 The name for the group, used to form the define and the value of the define.
-              type: string
+              $ref: '#/$defs/name'
             flags: *cmd_flags
 
   kernel-family:
diff --git a/Documentation/netlink/netlink-raw.yaml b/Documentation/netlink/netlink-raw.yaml
index e34bf23897fa..246fa07bccf6 100644
--- a/Documentation/netlink/netlink-raw.yaml
+++ b/Documentation/netlink/netlink-raw.yaml
@@ -6,6 +6,12 @@ $schema: https://json-schema.org/draft-07/schema
 
 # Common defines
 $defs:
+  name:
+    type: string
+    pattern: ^[0-9a-z-]+$
+  name-cap:
+    type: string
+    pattern: ^[0-9a-zA-Z-]+$
   uint:
     type: integer
     minimum: 0
@@ -71,7 +77,7 @@ properties:
       additionalProperties: False
       properties:
         name:
-          type: string
+          $ref: '#/$defs/name'
         header:
           description: For C-compatible languages, header which already defines this value.
           type: string
@@ -98,7 +104,7 @@ properties:
                 additionalProperties: False
                 properties:
                   name:
-                    type: string
+                    $ref: '#/$defs/name'
                   value:
                     type: integer
                   doc:
@@ -124,7 +130,7 @@ properties:
             additionalProperties: False
             properties:
               name:
-                type: string
+                $ref: '#/$defs/name-cap'
               type:
                 description: |
                   The netlink attribute type. Members of type 'binary' or 'pad'
@@ -183,7 +189,7 @@ properties:
         name:
           description: |
             Name used when referring to this space in other definitions, not used outside of the spec.
-          type: string
+          $ref: '#/$defs/name'
         name-prefix:
           description: |
             Prefix for the C enum name of the attributes. Default family[name]-set[name]-a-
@@ -220,7 +226,7 @@ properties:
             additionalProperties: False
             properties:
               name:
-                type: string
+                $ref: '#/$defs/name'
               type: &attr-type
                 description: The netlink attribute type
                 enum: [ unused, pad, flag, binary, bitfield32,
@@ -408,7 +414,7 @@ properties:
           properties:
             name:
               description: Name of the operation, also defining its C enum value in uAPI.
-              type: string
+              $ref: '#/$defs/name'
             doc:
               description: Documentation for the command.
               type: string

From 4a5e85f4eb8fd18b1266342d100e4f0849544ca0 Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Tue, 17 Jun 2025 16:35:32 +0200
Subject: [PATCH 0875/1334] fs/proc/task_mmu: fix PAGE_IS_PFNZERO detection for
 the huge zero folio

is_zero_pfn() does not work for the huge zero folio. Fix it by using
is_huge_zero_pmd().

This can cause the PAGEMAP_SCAN ioctl against /proc/pid/pagemap to
present pages as PAGE_IS_PRESENT rather than as PAGE_IS_PFNZERO.

Found by code inspection.

Link: https://lkml.kernel.org/r/20250617143532.2375383-1-david@redhat.com
Fixes: 52526ca7fdb9 ("fs/proc/task_mmu: implement IOCTL to get and optionally clear info about PTEs")
Signed-off-by: David Hildenbrand <david@redhat.com>
Cc: Muhammad Usama Anjum <usama.anjum@collabora.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 fs/proc/task_mmu.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 27972c0749e7..4be91eb6ea5c 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -2182,7 +2182,7 @@ static unsigned long pagemap_thp_category(struct pagemap_scan_private *p,
 				categories |= PAGE_IS_FILE;
 		}
 
-		if (is_zero_pfn(pmd_pfn(pmd)))
+		if (is_huge_zero_pmd(pmd))
 			categories |= PAGE_IS_PFNZERO;
 		if (pmd_soft_dirty(pmd))
 			categories |= PAGE_IS_SOFT_DIRTY;

From 86bc5752a9173589271439911b33b4d952b0a91f Mon Sep 17 00:00:00 2001
From: Michal Hocko <mhocko@suse.com>
Date: Tue, 17 Jun 2025 10:58:19 +0200
Subject: [PATCH 0876/1334] mm: add OOM killer maintainer structure

Add MAINTAINERS info for the oom-killer.

[akpm@linux-foundation.org: fix mhocko email address (SeongJae), add files (Lorenzo)]
[akpm@linux-foundation.org: fix ordering]
Link: https://lkml.kernel.org/r/20250617085819.355838-1-mhocko@kernel.org
Signed-off-by: Michal Hocko <mhocko@suse.com>
Acked-by: David Rientjes <rientjes@google.com>
Acked-by: Shakeel Butt <shakeel.butt@linux.dev>
Acked-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Acked-by: SeongJae Park <sj@kernel.org>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Michal Hocko <mhocko@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 MAINTAINERS | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index efb51ee92683..689b9a20b6df 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -15848,6 +15848,17 @@ F:	mm/numa.c
 F:	mm/numa_emulation.c
 F:	mm/numa_memblks.c
 
+MEMORY MANAGEMENT - OOM KILLER
+M:	Michal Hocko <mhocko@suse.com>
+R:	David Rientjes <rientjes@google.com>
+R:	Shakeel Butt <shakeel.butt@linux.dev>
+L:	linux-mm@kvack.org
+S:	Maintained
+F:	include/linux/oom.h
+F:	include/trace/events/oom.h
+F:	include/uapi/linux/oom.h
+F:	mm/oom_kill.c
+
 MEMORY MANAGEMENT - PAGE ALLOCATOR
 M:	Andrew Morton <akpm@linux-foundation.org>
 M:	Vlastimil Babka <vbabka@suse.cz>

From 71aa17fd981be2ef683bf83326128c505abe070c Mon Sep 17 00:00:00 2001
From: "Mike Rapoport (Microsoft)" <rppt@kernel.org>
Date: Wed, 18 Jun 2025 19:47:52 +0300
Subject: [PATCH 0877/1334] MAINTAINERS: add tree entry to mm init block

Link: https://lkml.kernel.org/r/aFLubPfiO5hqfhCe@kernel.org
Signed-off-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 MAINTAINERS | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index 689b9a20b6df..fc6cc0b2e9a3 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -15676,6 +15676,8 @@ MEMBLOCK AND MEMORY MANAGEMENT INITIALIZATION
 M:	Mike Rapoport <rppt@kernel.org>
 L:	linux-mm@kvack.org
 S:	Maintained
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/rppt/memblock.git for-next
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/rppt/memblock.git fixes
 F:	Documentation/core-api/boot-time-mm.rst
 F:	Documentation/core-api/kho/bindings/memblock/*
 F:	include/linux/memblock.h

From 3746351e876b42f5221c2f85ba60965b38494ff2 Mon Sep 17 00:00:00 2001
From: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Date: Wed, 18 Jun 2025 11:59:53 +0100
Subject: [PATCH 0878/1334] MAINTAINERS: add missing files to mm page alloc
 section

There are a number of files within memory management which appear to be
most suitably placed within the page allocation section of MAINTAINERS and
are otherwise unassigned, so place these there.

Link: https://lkml.kernel.org/r/20250618105953.67630-1-lorenzo.stoakes@oracle.com
Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Brendan Jackman <jackmanb@google.com>
Acked-by: Zi Yan <ziy@nvidia.com>
Acked-by: David Hildenbrand <david@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Suren Baghdasaryan <surenb@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 MAINTAINERS | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index fc6cc0b2e9a3..4e131bb97894 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -15875,8 +15875,17 @@ F:	include/linux/compaction.h
 F:	include/linux/gfp.h
 F:	include/linux/page-isolation.h
 F:	mm/compaction.c
+F:	mm/debug_page_alloc.c
+F:	mm/fail_page_alloc.c
 F:	mm/page_alloc.c
+F:	mm/page_ext.c
+F:	mm/page_frag_cache.c
 F:	mm/page_isolation.c
+F:	mm/page_owner.c
+F:	mm/page_poison.c
+F:	mm/page_reporting.c
+F:	mm/show_mem.c
+F:	mm/shuffle.c
 
 MEMORY MANAGEMENT - RECLAIM
 M:	Andrew Morton <akpm@linux-foundation.org>

From 344ef45b03336e7f74658814f66483b5417c9cf1 Mon Sep 17 00:00:00 2001
From: Ge Yang <yangge1116@126.com>
Date: Tue, 27 May 2025 11:36:50 +0800
Subject: [PATCH 0879/1334] mm/hugetlb: remove unnecessary holding of
 hugetlb_lock

In isolate_or_dissolve_huge_folio(), after acquiring the hugetlb_lock, it
is only for the purpose of obtaining the correct hstate, which is then
passed to alloc_and_dissolve_hugetlb_folio().

alloc_and_dissolve_hugetlb_folio() itself also acquires the hugetlb_lock.
We can have alloc_and_dissolve_hugetlb_folio() obtain the hstate by
itself, so that isolate_or_dissolve_huge_folio() no longer needs to
acquire the hugetlb_lock.  In addition, we keep the folio_test_hugetlb()
check within isolate_or_dissolve_huge_folio().  By doing so, we can avoid
disrupting the normal path by vainly holding the hugetlb_lock.

replace_free_hugepage_folios() has the same issue, and we should address
it as well.

Addresses a possible performance problem which was added by the hotfix
113ed54ad276 ("mm/hugetlb: fix kernel NULL pointer dereference when
replacing free hugetlb folios").

Link: https://lkml.kernel.org/r/1748317010-16272-1-git-send-email-yangge1116@126.com
Fixes: 113ed54ad276 ("mm/hugetlb: fix kernel NULL pointer dereference when replacing free hugetlb folios")
Signed-off-by: Ge Yang <yangge1116@126.com>
Suggested-by: Oscar Salvador <osalvador@suse.de>
Reviewed-by: Muchun Song <muchun.song@linux.dev>
Cc: Baolin Wang <baolin.wang@linux.alibaba.com>
Cc: Barry Song <21cnbao@gmail.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/hugetlb.c | 54 +++++++++++++++++-----------------------------------
 1 file changed, 17 insertions(+), 37 deletions(-)

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 8746ed2fec13..9dc95eac558c 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -2787,20 +2787,24 @@ void restore_reserve_on_error(struct hstate *h, struct vm_area_struct *vma,
 /*
  * alloc_and_dissolve_hugetlb_folio - Allocate a new folio and dissolve
  * the old one
- * @h: struct hstate old page belongs to
  * @old_folio: Old folio to dissolve
  * @list: List to isolate the page in case we need to
  * Returns 0 on success, otherwise negated error.
  */
-static int alloc_and_dissolve_hugetlb_folio(struct hstate *h,
-			struct folio *old_folio, struct list_head *list)
+static int alloc_and_dissolve_hugetlb_folio(struct folio *old_folio,
+			struct list_head *list)
 {
-	gfp_t gfp_mask = htlb_alloc_mask(h) | __GFP_THISNODE;
+	gfp_t gfp_mask;
+	struct hstate *h;
 	int nid = folio_nid(old_folio);
 	struct folio *new_folio = NULL;
 	int ret = 0;
 
 retry:
+	/*
+	 * The old_folio might have been dissolved from under our feet, so make sure
+	 * to carefully check the state under the lock.
+	 */
 	spin_lock_irq(&hugetlb_lock);
 	if (!folio_test_hugetlb(old_folio)) {
 		/*
@@ -2829,8 +2833,10 @@ retry:
 		cond_resched();
 		goto retry;
 	} else {
+		h = folio_hstate(old_folio);
 		if (!new_folio) {
 			spin_unlock_irq(&hugetlb_lock);
+			gfp_mask = htlb_alloc_mask(h) | __GFP_THISNODE;
 			new_folio = alloc_buddy_hugetlb_folio(h, gfp_mask, nid,
 							      NULL, NULL);
 			if (!new_folio)
@@ -2874,35 +2880,24 @@ free_new:
 
 int isolate_or_dissolve_huge_folio(struct folio *folio, struct list_head *list)
 {
-	struct hstate *h;
 	int ret = -EBUSY;
 
-	/*
-	 * The page might have been dissolved from under our feet, so make sure
-	 * to carefully check the state under the lock.
-	 * Return success when racing as if we dissolved the page ourselves.
-	 */
-	spin_lock_irq(&hugetlb_lock);
-	if (folio_test_hugetlb(folio)) {
-		h = folio_hstate(folio);
-	} else {
-		spin_unlock_irq(&hugetlb_lock);
+	/* Not to disrupt normal path by vainly holding hugetlb_lock */
+	if (!folio_test_hugetlb(folio))
 		return 0;
-	}
-	spin_unlock_irq(&hugetlb_lock);
 
 	/*
 	 * Fence off gigantic pages as there is a cyclic dependency between
 	 * alloc_contig_range and them. Return -ENOMEM as this has the effect
 	 * of bailing out right away without further retrying.
 	 */
-	if (hstate_is_gigantic(h))
+	if (folio_order(folio) > MAX_PAGE_ORDER)
 		return -ENOMEM;
 
 	if (folio_ref_count(folio) && folio_isolate_hugetlb(folio, list))
 		ret = 0;
 	else if (!folio_ref_count(folio))
-		ret = alloc_and_dissolve_hugetlb_folio(h, folio, list);
+		ret = alloc_and_dissolve_hugetlb_folio(folio, list);
 
 	return ret;
 }
@@ -2916,7 +2911,6 @@ int isolate_or_dissolve_huge_folio(struct folio *folio, struct list_head *list)
  */
 int replace_free_hugepage_folios(unsigned long start_pfn, unsigned long end_pfn)
 {
-	struct hstate *h;
 	struct folio *folio;
 	int ret = 0;
 
@@ -2925,23 +2919,9 @@ int replace_free_hugepage_folios(unsigned long start_pfn, unsigned long end_pfn)
 	while (start_pfn < end_pfn) {
 		folio = pfn_folio(start_pfn);
 
-		/*
-		 * The folio might have been dissolved from under our feet, so make sure
-		 * to carefully check the state under the lock.
-		 */
-		spin_lock_irq(&hugetlb_lock);
-		if (folio_test_hugetlb(folio)) {
-			h = folio_hstate(folio);
-		} else {
-			spin_unlock_irq(&hugetlb_lock);
-			start_pfn++;
-			continue;
-		}
-		spin_unlock_irq(&hugetlb_lock);
-
-		if (!folio_ref_count(folio)) {
-			ret = alloc_and_dissolve_hugetlb_folio(h, folio,
-							       &isolate_list);
+		/* Not to disrupt normal path by vainly holding hugetlb_lock */
+		if (folio_test_hugetlb(folio) && !folio_ref_count(folio)) {
+			ret = alloc_and_dissolve_hugetlb_folio(folio, &isolate_list);
 			if (ret)
 				break;
 

From df831e97739405ecbaddb85516bc7d4d1c933d6b Mon Sep 17 00:00:00 2001
From: Yu Kuai <yukuai3@huawei.com>
Date: Thu, 19 Jun 2025 21:26:55 +0800
Subject: [PATCH 0880/1334] lib/group_cpus: fix NULL pointer dereference from
 group_cpus_evenly()

While testing null_blk with configfs, echo 0 > poll_queues will trigger
following panic:

BUG: kernel NULL pointer dereference, address: 0000000000000010
Oops: Oops: 0000 [#1] SMP NOPTI
CPU: 27 UID: 0 PID: 920 Comm: bash Not tainted 6.15.0-02023-gadbdb95c8696-dirty #1238 PREEMPT(undef)
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.16.1-2.fc37 04/01/2014
RIP: 0010:__bitmap_or+0x48/0x70
Call Trace:
 <TASK>
 __group_cpus_evenly+0x822/0x8c0
 group_cpus_evenly+0x2d9/0x490
 blk_mq_map_queues+0x1e/0x110
 null_map_queues+0xc9/0x170 [null_blk]
 blk_mq_update_queue_map+0xdb/0x160
 blk_mq_update_nr_hw_queues+0x22b/0x560
 nullb_update_nr_hw_queues+0x71/0xf0 [null_blk]
 nullb_device_poll_queues_store+0xa4/0x130 [null_blk]
 configfs_write_iter+0x109/0x1d0
 vfs_write+0x26e/0x6f0
 ksys_write+0x79/0x180
 __x64_sys_write+0x1d/0x30
 x64_sys_call+0x45c4/0x45f0
 do_syscall_64+0xa5/0x240
 entry_SYSCALL_64_after_hwframe+0x76/0x7e

Root cause is that numgrps is set to 0, and ZERO_SIZE_PTR is returned from
kcalloc(), and later ZERO_SIZE_PTR will be deferenced.

Fix the problem by checking numgrps first in group_cpus_evenly(), and
return NULL directly if numgrps is zero.

[yukuai3@huawei.com: also fix the non-SMP version]
  Link: https://lkml.kernel.org/r/20250620010958.1265984-1-yukuai1@huaweicloud.com
Link: https://lkml.kernel.org/r/20250619132655.3318883-1-yukuai1@huaweicloud.com
Fixes: 6a6dcae8f486 ("blk-mq: Build default queue map via group_cpus_evenly()")
Signed-off-by: Yu Kuai <yukuai3@huawei.com>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Reviewed-by: Jens Axboe <axboe@kernel.dk>
Cc: ErKun Yang <yangerkun@huawei.com>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Thomas Gleinxer <tglx@linutronix.de>
Cc: "zhangyi (F)" <yi.zhang@huawei.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 lib/group_cpus.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/lib/group_cpus.c b/lib/group_cpus.c
index ee272c4cefcc..18d43a406114 100644
--- a/lib/group_cpus.c
+++ b/lib/group_cpus.c
@@ -352,6 +352,9 @@ struct cpumask *group_cpus_evenly(unsigned int numgrps)
 	int ret = -ENOMEM;
 	struct cpumask *masks = NULL;
 
+	if (numgrps == 0)
+		return NULL;
+
 	if (!zalloc_cpumask_var(&nmsk, GFP_KERNEL))
 		return NULL;
 
@@ -426,8 +429,12 @@ struct cpumask *group_cpus_evenly(unsigned int numgrps)
 #else /* CONFIG_SMP */
 struct cpumask *group_cpus_evenly(unsigned int numgrps)
 {
-	struct cpumask *masks = kcalloc(numgrps, sizeof(*masks), GFP_KERNEL);
+	struct cpumask *masks;
 
+	if (numgrps == 0)
+		return NULL;
+
+	masks = kcalloc(numgrps, sizeof(*masks), GFP_KERNEL);
 	if (!masks)
 		return NULL;
 

From f5769359c5b241978e6933672bb78b3adc36aa18 Mon Sep 17 00:00:00 2001
From: Hao Ge <gehao@kylinos.cn>
Date: Fri, 20 Jun 2025 02:31:54 +0800
Subject: [PATCH 0881/1334] mm/alloc_tag: fix the kmemleak false positive issue
 in the allocation of the percpu variable tag->counters

When loading a module, as long as the module has memory allocation
operations, kmemleak produces a false positive report that resembles the
following:

unreferenced object (percpu) 0x7dfd232a1650 (size 16):
  comm "modprobe", pid 1301, jiffies 4294940249
  hex dump (first 16 bytes on cpu 2):
    00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
  backtrace (crc 0):
    kmemleak_alloc_percpu+0xb4/0xd0
    pcpu_alloc_noprof+0x700/0x1098
    load_module+0xd4/0x348
    codetag_module_init+0x20c/0x450
    codetag_load_module+0x70/0xb8
    load_module+0xef8/0x1608
    init_module_from_file+0xec/0x158
    idempotent_init_module+0x354/0x608
    __arm64_sys_finit_module+0xbc/0x150
    invoke_syscall+0xd4/0x258
    el0_svc_common.constprop.0+0xb4/0x240
    do_el0_svc+0x48/0x68
    el0_svc+0x40/0xf8
    el0t_64_sync_handler+0x10c/0x138
    el0t_64_sync+0x1ac/0x1b0

This is because the module can only indirectly reference
alloc_tag_counters through the alloc_tag section, which misleads kmemleak.

However, we don't have a kmemleak ignore interface for percpu allocations
yet.  So let's create one and invoke it for tag->counters.

[gehao@kylinos.cn: fix build error when CONFIG_DEBUG_KMEMLEAK=n, s/igonore/ignore/]
  Link: https://lkml.kernel.org/r/20250620093102.2416767-1-hao.ge@linux.dev
Link: https://lkml.kernel.org/r/20250619183154.2122608-1-hao.ge@linux.dev
Fixes: 12ca42c23775 ("alloc_tag: allocate percpu counters for module tags dynamically")
Signed-off-by: Hao Ge <gehao@kylinos.cn>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Acked-by: Suren Baghdasaryan <surenb@google.com>	[lib/alloc_tag.c]
Cc: Kent Overstreet <kent.overstreet@linux.dev>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/kmemleak.h |  4 ++++
 lib/alloc_tag.c          |  8 +++++++-
 mm/kmemleak.c            | 14 ++++++++++++++
 3 files changed, 25 insertions(+), 1 deletion(-)

diff --git a/include/linux/kmemleak.h b/include/linux/kmemleak.h
index 93a73c076d16..fbd424b2abb1 100644
--- a/include/linux/kmemleak.h
+++ b/include/linux/kmemleak.h
@@ -28,6 +28,7 @@ extern void kmemleak_update_trace(const void *ptr) __ref;
 extern void kmemleak_not_leak(const void *ptr) __ref;
 extern void kmemleak_transient_leak(const void *ptr) __ref;
 extern void kmemleak_ignore(const void *ptr) __ref;
+extern void kmemleak_ignore_percpu(const void __percpu *ptr) __ref;
 extern void kmemleak_scan_area(const void *ptr, size_t size, gfp_t gfp) __ref;
 extern void kmemleak_no_scan(const void *ptr) __ref;
 extern void kmemleak_alloc_phys(phys_addr_t phys, size_t size,
@@ -97,6 +98,9 @@ static inline void kmemleak_not_leak(const void *ptr)
 static inline void kmemleak_transient_leak(const void *ptr)
 {
 }
+static inline void kmemleak_ignore_percpu(const void __percpu *ptr)
+{
+}
 static inline void kmemleak_ignore(const void *ptr)
 {
 }
diff --git a/lib/alloc_tag.c b/lib/alloc_tag.c
index d48b80f3f007..3a74d63a959e 100644
--- a/lib/alloc_tag.c
+++ b/lib/alloc_tag.c
@@ -10,6 +10,7 @@
 #include <linux/seq_buf.h>
 #include <linux/seq_file.h>
 #include <linux/vmalloc.h>
+#include <linux/kmemleak.h>
 
 #define ALLOCINFO_FILE_NAME		"allocinfo"
 #define MODULE_ALLOC_TAG_VMAP_SIZE	(100000UL * sizeof(struct alloc_tag))
@@ -632,8 +633,13 @@ static int load_module(struct module *mod, struct codetag *start, struct codetag
 			       mod->name);
 			return -ENOMEM;
 		}
-	}
 
+		/*
+		 * Avoid a kmemleak false positive. The pointer to the counters is stored
+		 * in the alloc_tag section of the module and cannot be directly accessed.
+		 */
+		kmemleak_ignore_percpu(tag->counters);
+	}
 	return 0;
 }
 
diff --git a/mm/kmemleak.c b/mm/kmemleak.c
index da9cee34ee1b..8d588e685311 100644
--- a/mm/kmemleak.c
+++ b/mm/kmemleak.c
@@ -1246,6 +1246,20 @@ void __ref kmemleak_transient_leak(const void *ptr)
 }
 EXPORT_SYMBOL(kmemleak_transient_leak);
 
+/**
+ * kmemleak_ignore_percpu - similar to kmemleak_ignore but taking a percpu
+ *			    address argument
+ * @ptr:	percpu address of the object
+ */
+void __ref kmemleak_ignore_percpu(const void __percpu *ptr)
+{
+	pr_debug("%s(0x%px)\n", __func__, ptr);
+
+	if (kmemleak_enabled && ptr && !IS_ERR_PCPU(ptr))
+		make_black_object((unsigned long)ptr, OBJECT_PERCPU);
+}
+EXPORT_SYMBOL_GPL(kmemleak_ignore_percpu);
+
 /**
  * kmemleak_ignore - ignore an allocated object
  * @ptr:	pointer to beginning of the object

From 4f489fe6afb395dbc79840efa3c05440b760d883 Mon Sep 17 00:00:00 2001
From: SeongJae Park <sj@kernel.org>
Date: Thu, 19 Jun 2025 11:36:07 -0700
Subject: [PATCH 0882/1334] mm/damon/sysfs-schemes: free old
 damon_sysfs_scheme_filter->memcg_path on write

memcg_path_store() assigns a newly allocated memory buffer to
filter->memcg_path, without deallocating the previously allocated and
assigned memory buffer.  As a result, users can leak kernel memory by
continuously writing a data to memcg_path DAMOS sysfs file.  Fix the leak
by deallocating the previously set memory buffer.

Link: https://lkml.kernel.org/r/20250619183608.6647-2-sj@kernel.org
Fixes: 7ee161f18b5d ("mm/damon/sysfs-schemes: implement filter directory")
Signed-off-by: SeongJae Park <sj@kernel.org>
Cc: Shuah Khan <shuah@kernel.org>
Cc: <stable@vger.kernel.org>		[6.3.x]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/damon/sysfs-schemes.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/mm/damon/sysfs-schemes.c b/mm/damon/sysfs-schemes.c
index 0f6c9e1fec0b..30ae7518ffbf 100644
--- a/mm/damon/sysfs-schemes.c
+++ b/mm/damon/sysfs-schemes.c
@@ -472,6 +472,7 @@ static ssize_t memcg_path_store(struct kobject *kobj,
 		return -ENOMEM;
 
 	strscpy(path, buf, count + 1);
+	kfree(filter->memcg_path);
 	filter->memcg_path = path;
 	return count;
 }

From 79300ac805b672a84b64d80d4cbc374d83411599 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <florian.fainelli@broadcom.com>
Date: Thu, 19 Jun 2025 15:51:05 -0700
Subject: [PATCH 0883/1334] scripts/gdb: fix dentry_name() lookup

The "d_iname" member was replaced with "d_shortname.string" in the commit
referenced in the Fixes tag.  This prevented the GDB script "lx-mount"
command to properly function:

(gdb) lx-mounts
      mount          super_block     devname pathname fstype options
0xff11000002d21180 0xff11000002d24800 rootfs / rootfs rw 0 0
0xff11000002e18a80 0xff11000003713000 /dev/root / ext4 rw,relatime 0 0
Python Exception <class 'gdb.error'>: There is no member named d_iname.
Error occurred in Python: There is no member named d_iname.

Link: https://lkml.kernel.org/r/20250619225105.320729-1-florian.fainelli@broadcom.com
Fixes: 58cf9c383c5c ("dcache: back inline names with a struct-wrapped array of unsigned long")
Signed-off-by: Florian Fainelli <florian.fainelli@broadcom.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Jan Kara <jack@suse.cz>
Cc: Jan Kiszka <jan.kiszka@siemens.com>
Cc: Jeff Layton <jlayton@kernel.org>
Cc: Kieran Bingham <kbingham@kernel.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 scripts/gdb/linux/vfs.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/scripts/gdb/linux/vfs.py b/scripts/gdb/linux/vfs.py
index c77b9ce75f6d..b5fbb18ccb77 100644
--- a/scripts/gdb/linux/vfs.py
+++ b/scripts/gdb/linux/vfs.py
@@ -22,7 +22,7 @@ def dentry_name(d):
     if parent == d or parent == 0:
         return ""
     p = dentry_name(d['d_parent']) + "/"
-    return p + d['d_iname'].string()
+    return p + d['d_shortname']['string'].string()
 
 class DentryName(gdb.Function):
     """Return string of the full path of a dentry.

From befd9a71d859ea625eaa84dae1b243efb3df3eca Mon Sep 17 00:00:00 2001
From: Haiyue Wang <haiyuewa@163.com>
Date: Sun, 22 Jun 2025 01:13:51 +0800
Subject: [PATCH 0884/1334] fuse: fix runtime warning on
 truncate_folio_batch_exceptionals()

The WARN_ON_ONCE is introduced on truncate_folio_batch_exceptionals() to
capture whether the filesystem has removed all DAX entries or not.

And the fix has been applied on the filesystem xfs and ext4 by the commit
0e2f80afcfa6 ("fs/dax: ensure all pages are idle prior to filesystem
unmount").

Apply the missed fix on filesystem fuse to fix the runtime warning:

[    2.011450] ------------[ cut here ]------------
[    2.011873] WARNING: CPU: 0 PID: 145 at mm/truncate.c:89 truncate_folio_batch_exceptionals+0x272/0x2b0
[    2.012468] Modules linked in:
[    2.012718] CPU: 0 UID: 1000 PID: 145 Comm: weston Not tainted 6.16.0-rc2-WSL2-STABLE #2 PREEMPT(undef)
[    2.013292] RIP: 0010:truncate_folio_batch_exceptionals+0x272/0x2b0
[    2.013704] Code: 48 63 d0 41 29 c5 48 8d 1c d5 00 00 00 00 4e 8d 6c 2a 01 49 c1 e5 03 eb 09 48 83 c3 08 49 39 dd 74 83 41 f6 44 1c 08 01 74 ef <0f> 0b 49 8b 34 1e 48 89 ef e8 10 a2 17 00 eb df 48 8b 7d 00 e8 35
[    2.014845] RSP: 0018:ffffa47ec33f3b10 EFLAGS: 00010202
[    2.015279] RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000000000000
[    2.015884] RDX: 0000000000000000 RSI: ffffa47ec33f3ca0 RDI: ffff98aa44f3fa80
[    2.016377] RBP: ffff98aa44f3fbf0 R08: ffffa47ec33f3ba8 R09: 0000000000000000
[    2.016942] R10: 0000000000000001 R11: 0000000000000000 R12: ffffa47ec33f3ca0
[    2.017437] R13: 0000000000000008 R14: ffffa47ec33f3ba8 R15: 0000000000000000
[    2.017972] FS:  000079ce006afa40(0000) GS:ffff98aade441000(0000) knlGS:0000000000000000
[    2.018510] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[    2.018987] CR2: 000079ce03e74000 CR3: 000000010784f006 CR4: 0000000000372eb0
[    2.019518] Call Trace:
[    2.019729]  <TASK>
[    2.019901]  truncate_inode_pages_range+0xd8/0x400
[    2.020280]  ? timerqueue_add+0x66/0xb0
[    2.020574]  ? get_nohz_timer_target+0x2a/0x140
[    2.020904]  ? timerqueue_add+0x66/0xb0
[    2.021231]  ? timerqueue_del+0x2e/0x50
[    2.021646]  ? __remove_hrtimer+0x39/0x90
[    2.022017]  ? srso_alias_untrain_ret+0x1/0x10
[    2.022497]  ? psi_group_change+0x136/0x350
[    2.023046]  ? _raw_spin_unlock+0xe/0x30
[    2.023514]  ? finish_task_switch.isra.0+0x8d/0x280
[    2.024068]  ? __schedule+0x532/0xbd0
[    2.024551]  fuse_evict_inode+0x29/0x190
[    2.025131]  evict+0x100/0x270
[    2.025641]  ? _atomic_dec_and_lock+0x39/0x50
[    2.026316]  ? __pfx_generic_delete_inode+0x10/0x10
[    2.026843]  __dentry_kill+0x71/0x180
[    2.027335]  dput+0xeb/0x1b0
[    2.027725]  __fput+0x136/0x2b0
[    2.028054]  __x64_sys_close+0x3d/0x80
[    2.028469]  do_syscall_64+0x6d/0x1b0
[    2.028832]  ? clear_bhb_loop+0x30/0x80
[    2.029182]  ? clear_bhb_loop+0x30/0x80
[    2.029533]  ? clear_bhb_loop+0x30/0x80
[    2.029902]  entry_SYSCALL_64_after_hwframe+0x76/0x7e
[    2.030423] RIP: 0033:0x79ce03d0d067
[    2.030820] Code: b8 ff ff ff ff e9 3e ff ff ff 66 0f 1f 84 00 00 00 00 00 f3 0f 1e fa 64 8b 04 25 18 00 00 00 85 c0 75 10 b8 03 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 41 c3 48 83 ec 18 89 7c 24 0c e8 c3 a7 f8 ff
[    2.032354] RSP: 002b:00007ffef0498948 EFLAGS: 00000246 ORIG_RAX: 0000000000000003
[    2.032939] RAX: ffffffffffffffda RBX: 00007ffef0498960 RCX: 000079ce03d0d067
[    2.033612] RDX: 0000000000000003 RSI: 0000000000001000 RDI: 000000000000000d
[    2.034289] RBP: 00007ffef0498a30 R08: 000000000000000d R09: 0000000000000000
[    2.034944] R10: 00007ffef0498978 R11: 0000000000000246 R12: 0000000000000001
[    2.035610] R13: 00007ffef0498960 R14: 000079ce03e09ce0 R15: 0000000000000003
[    2.036301]  </TASK>
[    2.036532] ---[ end trace 0000000000000000 ]---

Link: https://lkml.kernel.org/r/20250621171507.3770-1-haiyuewa@163.com
Fixes: bde708f1a65d ("fs/dax: always remove DAX page-cache entries when breaking layouts")
Signed-off-by: Haiyue Wang <haiyuewa@163.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Miklos Szeredi <miklos@szeredi.hu>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 fs/fuse/inode.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index bfe8d8af46f3..9572bdef49ee 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -9,6 +9,7 @@
 #include "fuse_i.h"
 #include "dev_uring_i.h"
 
+#include <linux/dax.h>
 #include <linux/pagemap.h>
 #include <linux/slab.h>
 #include <linux/file.h>
@@ -162,6 +163,9 @@ static void fuse_evict_inode(struct inode *inode)
 	/* Will write inode on close/munmap and in all other dirtiers */
 	WARN_ON(inode->i_state & I_DIRTY_INODE);
 
+	if (FUSE_IS_DAX(inode))
+		dax_break_layout_final(inode);
+
 	truncate_inode_pages_final(&inode->i_data);
 	clear_inode(inode);
 	if (inode->i_sb->s_flags & SB_ACTIVE) {

From b160a5cc6ac761f341e58e48ae3f03a04d310677 Mon Sep 17 00:00:00 2001
From: Zijun Hu <zijun.hu@oss.qualcomm.com>
Date: Fri, 20 Jun 2025 19:53:53 +0800
Subject: [PATCH 0885/1334] mailmap: add entries for Zijun Hu

Map my old qualcomm email addresses:
	Zijun Hu <quic_zijuhu@quicinc.com>
	Zijun Hu <zijuhu@codeaurora.org>
To the current one:
	Zijun Hu <zijun.hu@oss.qualcomm.com>

Link: https://lkml.kernel.org/r/20250620-my_mailmap-v1-1-11ea3db8ba1e@oss.qualcomm.com
Signed-off-by: Zijun Hu <zijun.hu@oss.qualcomm.com>
Cc: Hans verkuil <hverkuil@xs4all.nl>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 .mailmap | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/.mailmap b/.mailmap
index d57531dab08b..85f13b941f08 100644
--- a/.mailmap
+++ b/.mailmap
@@ -830,3 +830,5 @@ Yosry Ahmed <yosry.ahmed@linux.dev> <yosryahmed@google.com>
 Yusuke Goda <goda.yusuke@renesas.com>
 Zack Rusin <zack.rusin@broadcom.com> <zackr@vmware.com>
 Zhu Yanjun <zyjzyj2000@gmail.com> <yanjunz@nvidia.com>
+Zijun Hu <zijun.hu@oss.qualcomm.com> <quic_zijuhu@quicinc.com>
+Zijun Hu <zijun.hu@oss.qualcomm.com> <zijuhu@codeaurora.org>

From c9e8efa0b384c43670852f955567b31a5eb4ac2b Mon Sep 17 00:00:00 2001
From: Zijun Hu <zijun.hu@oss.qualcomm.com>
Date: Fri, 20 Jun 2025 19:53:54 +0800
Subject: [PATCH 0886/1334] mailmap: correct name for a historical account of
 Zijun Hu

Correct the name for <zijun_hu@htc.com> from 'zijun_hu' to 'Zijun Hu'.

Link: https://lkml.kernel.org/r/20250620-my_mailmap-v1-2-11ea3db8ba1e@oss.qualcomm.com
Signed-off-by: Zijun Hu <zijun.hu@oss.qualcomm.com>
Cc: Hans verkuil <hverkuil@xs4all.nl>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 .mailmap | 1 +
 1 file changed, 1 insertion(+)

diff --git a/.mailmap b/.mailmap
index 85f13b941f08..a5534ff9c1d7 100644
--- a/.mailmap
+++ b/.mailmap
@@ -832,3 +832,4 @@ Zack Rusin <zack.rusin@broadcom.com> <zackr@vmware.com>
 Zhu Yanjun <zyjzyj2000@gmail.com> <yanjunz@nvidia.com>
 Zijun Hu <zijun.hu@oss.qualcomm.com> <quic_zijuhu@quicinc.com>
 Zijun Hu <zijun.hu@oss.qualcomm.com> <zijuhu@codeaurora.org>
+Zijun Hu <zijun_hu@htc.com>

From b6f5e748587063d4ad3294d07ca29886851d9cd7 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Fri, 20 Jun 2025 13:21:22 +0200
Subject: [PATCH 0887/1334] crashdump: add CONFIG_KEYS dependency

The dm_crypt code fails to build without CONFIG_KEYS:

kernel/crash_dump_dm_crypt.c: In function 'restore_dm_crypt_keys_to_thread_keyring':
kernel/crash_dump_dm_crypt.c:105:9: error: unknown type name 'key_ref_t'; did you mean 'key_ref_put'?

There is a mix of 'select KEYS' and 'depends on KEYS' in Kconfig,
so there is no single obvious solution here, but generally using 'depends on'
makes more sense and is less likely to cause dependency loops.

Link: https://lkml.kernel.org/r/20250620112140.3396316-1-arnd@kernel.org
Fixes: 62f17d9df692 ("crash_dump: retrieve dm crypt keys in kdump kernel")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Cc: Alexander Graf <graf@amazon.com>
Cc: Baoquan He <bhe@redhat.com>
Cc: Coiby Xu <coxu@redhat.com>
Cc: Dave Vasilevsky <dave@vasilevsky.ca>
Cc: Eric Biggers <ebiggers@google.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 kernel/Kconfig.kexec | 1 +
 1 file changed, 1 insertion(+)

diff --git a/kernel/Kconfig.kexec b/kernel/Kconfig.kexec
index e64ce21f9a80..2ee603a98813 100644
--- a/kernel/Kconfig.kexec
+++ b/kernel/Kconfig.kexec
@@ -134,6 +134,7 @@ config CRASH_DM_CRYPT
 	depends on KEXEC_FILE
 	depends on CRASH_DUMP
 	depends on DM_CRYPT
+	depends on KEYS
 	help
 	  With this option enabled, user space can intereact with
 	  /sys/kernel/config/crash_dm_crypt_keys to make the dm crypt keys

From 7c942f87cc0be5699b1ce434d369eccd8b5321d4 Mon Sep 17 00:00:00 2001
From: Dev Jain <dev.jain@arm.com>
Date: Fri, 20 Jun 2025 16:41:50 +0530
Subject: [PATCH 0888/1334] selftests/mm: fix validate_addr() helper

validate_addr() checks whether the address returned by mmap() lies in the
low or high VA space, according to whether a high addr hint was passed or
not.  The fix commit mentioned below changed the code in such a way that
this function will always return failure when passed high_addr == 1; addr
will be >= HIGH_ADDR_MARK always, we will fall down to "if (addr >
HIGH_ADDR_MARK)" and return failure.  Fix this.

Link: https://lkml.kernel.org/r/20250620111150.50344-1-dev.jain@arm.com
Fixes: d1d86ce28d0f ("selftests/mm: virtual_address_range: conform to TAP format output")
Signed-off-by: Dev Jain <dev.jain@arm.com>
Reviewed-by: Donet Tom <donettom@linux.ibm.com>
Acked-by: David Hildenbrand <david@redhat.com>
Cc: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Shuah Khan <shuah@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 tools/testing/selftests/mm/virtual_address_range.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/mm/virtual_address_range.c b/tools/testing/selftests/mm/virtual_address_range.c
index b380e102b22f..169dbd692bf5 100644
--- a/tools/testing/selftests/mm/virtual_address_range.c
+++ b/tools/testing/selftests/mm/virtual_address_range.c
@@ -77,8 +77,11 @@ static void validate_addr(char *ptr, int high_addr)
 {
 	unsigned long addr = (unsigned long) ptr;
 
-	if (high_addr && addr < HIGH_ADDR_MARK)
-		ksft_exit_fail_msg("Bad address %lx\n", addr);
+	if (high_addr) {
+		if (addr < HIGH_ADDR_MARK)
+			ksft_exit_fail_msg("Bad address %lx\n", addr);
+		return;
+	}
 
 	if (addr > HIGH_ADDR_MARK)
 		ksft_exit_fail_msg("Bad address %lx\n", addr);

From 02d67850aecaf2306d849a3c804a125bb4f9c5f6 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Duje=20Mihanovi=C4=87?= <duje@dujemihanovic.xyz>
Date: Fri, 20 Jun 2025 11:25:35 +0200
Subject: [PATCH 0889/1334] =?UTF-8?q?mailmap:=20update=20Duje=20Mihanovi?=
 =?UTF-8?q?=C4=87's=20email=20address?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

I'm switching to a new mail address, so map my old one to it.

Link: https://lkml.kernel.org/r/20250620-mailmap-v1-1-a6b4b72dbd07@dujemihanovic.xyz
Signed-off-by: Duje Mihanović <duje@dujemihanovic.xyz>
Cc: Karel Balej <balejk@matfyz.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 .mailmap | 1 +
 1 file changed, 1 insertion(+)

diff --git a/.mailmap b/.mailmap
index a5534ff9c1d7..bd18a7c9d2ce 100644
--- a/.mailmap
+++ b/.mailmap
@@ -223,6 +223,7 @@ Dmitry Safonov <0x7f454c46@gmail.com> <d.safonov@partner.samsung.com>
 Dmitry Safonov <0x7f454c46@gmail.com> <dsafonov@virtuozzo.com>
 Domen Puncer <domen@coderock.org>
 Douglas Gilbert <dougg@torque.net>
+<duje@dujemihanovic.xyz> <duje.mihanovic@skole.hr>
 Ed L. Cashin <ecashin@coraid.com>
 Elliot Berman <quic_eberman@quicinc.com> <eberman@codeaurora.org>
 Enric Balletbo i Serra <eballetbo@kernel.org> <enric.balletbo@collabora.com>

From c0cb210a87fcdda3c25f43b5a64420e6b07d3f53 Mon Sep 17 00:00:00 2001
From: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Date: Wed, 25 Jun 2025 10:52:31 +0100
Subject: [PATCH 0890/1334] MAINTAINERS: add Lorenzo as THP co-maintainer

I am doing a great deal of review and getting ever more involved in THP
with intent to do more so in future also, so add myself as co-maintainer
to help David with workload.

Link: https://lkml.kernel.org/r/20250625095231.42874-1-lorenzo.stoakes@oracle.com
Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Acked-by: David Hildenbrand <david@redhat.com>
Acked-by: Baolin Wang <baolin.wang@linux.alibaba.com>
Acked-by: Dev Jain <dev.jain@arm.com>
Acked-by: Zi Yan <ziy@nvidia.com>
Acked-by: Oscar Salvador <osalvador@suse.de>
Cc: Barry Song <baohua@kernel.org>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Mariano Pache <npache@redhat.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 MAINTAINERS | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 4e131bb97894..d4fa7884b4a8 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -15945,9 +15945,9 @@ F:	mm/swapfile.c
 MEMORY MANAGEMENT - THP (TRANSPARENT HUGE PAGE)
 M:	Andrew Morton <akpm@linux-foundation.org>
 M:	David Hildenbrand <david@redhat.com>
+M:	Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
 R:	Zi Yan <ziy@nvidia.com>
 R:	Baolin Wang <baolin.wang@linux.alibaba.com>
-R:	Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
 R:	Liam R. Howlett <Liam.Howlett@oracle.com>
 R:	Nico Pache <npache@redhat.com>
 R:	Ryan Roberts <ryan.roberts@arm.com>

From a433791aeaea6e84df709e0b9584b9bbe040cd1c Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@google.com>
Date: Tue, 24 Jun 2025 14:45:00 -0700
Subject: [PATCH 0891/1334] atm: Release atm_dev_mutex after removing procfs in
 atm_dev_deregister().

syzbot reported a warning below during atm_dev_register(). [0]

Before creating a new device and procfs/sysfs for it, atm_dev_register()
looks up a duplicated device by __atm_dev_lookup().  These operations are
done under atm_dev_mutex.

However, when removing a device in atm_dev_deregister(), it releases the
mutex just after removing the device from the list that __atm_dev_lookup()
iterates over.

So, there will be a small race window where the device does not exist on
the device list but procfs/sysfs are still not removed, triggering the
splat.

Let's hold the mutex until procfs/sysfs are removed in
atm_dev_deregister().

[0]:
proc_dir_entry 'atm/atmtcp:0' already registered
WARNING: CPU: 0 PID: 5919 at fs/proc/generic.c:377 proc_register+0x455/0x5f0 fs/proc/generic.c:377
Modules linked in:
CPU: 0 UID: 0 PID: 5919 Comm: syz-executor284 Not tainted 6.16.0-rc2-syzkaller-00047-g52da431bf03b #0 PREEMPT(full)
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 05/07/2025
RIP: 0010:proc_register+0x455/0x5f0 fs/proc/generic.c:377
Code: 48 89 f9 48 c1 e9 03 80 3c 01 00 0f 85 a2 01 00 00 48 8b 44 24 10 48 c7 c7 20 c0 c2 8b 48 8b b0 d8 00 00 00 e8 0c 02 1c ff 90 <0f> 0b 90 90 48 c7 c7 80 f2 82 8e e8 0b de 23 09 48 8b 4c 24 28 48
RSP: 0018:ffffc9000466fa30 EFLAGS: 00010282
RAX: 0000000000000000 RBX: 0000000000000000 RCX: ffffffff817ae248
RDX: ffff888026280000 RSI: ffffffff817ae255 RDI: 0000000000000001
RBP: ffff8880232bed48 R08: 0000000000000001 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000001 R12: ffff888076ed2140
R13: dffffc0000000000 R14: ffff888078a61340 R15: ffffed100edda444
FS:  00007f38b3b0c6c0(0000) GS:ffff888124753000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007f38b3bdf953 CR3: 0000000076d58000 CR4: 00000000003526f0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
 <TASK>
 proc_create_data+0xbe/0x110 fs/proc/generic.c:585
 atm_proc_dev_register+0x112/0x1e0 net/atm/proc.c:361
 atm_dev_register+0x46d/0x890 net/atm/resources.c:113
 atmtcp_create+0x77/0x210 drivers/atm/atmtcp.c:369
 atmtcp_attach drivers/atm/atmtcp.c:403 [inline]
 atmtcp_ioctl+0x2f9/0xd60 drivers/atm/atmtcp.c:464
 do_vcc_ioctl+0x12c/0x930 net/atm/ioctl.c:159
 sock_do_ioctl+0x115/0x280 net/socket.c:1190
 sock_ioctl+0x227/0x6b0 net/socket.c:1311
 vfs_ioctl fs/ioctl.c:51 [inline]
 __do_sys_ioctl fs/ioctl.c:907 [inline]
 __se_sys_ioctl fs/ioctl.c:893 [inline]
 __x64_sys_ioctl+0x18b/0x210 fs/ioctl.c:893
 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline]
 do_syscall_64+0xcd/0x4c0 arch/x86/entry/syscall_64.c:94
 entry_SYSCALL_64_after_hwframe+0x77/0x7f
RIP: 0033:0x7f38b3b74459
Code: 28 00 00 00 75 05 48 83 c4 28 c3 e8 51 18 00 00 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 b0 ff ff ff f7 d8 64 89 01 48
RSP: 002b:00007f38b3b0c198 EFLAGS: 00000246 ORIG_RAX: 0000000000000010
RAX: ffffffffffffffda RBX: 00007f38b3bfe318 RCX: 00007f38b3b74459
RDX: 0000000000000000 RSI: 0000000000006180 RDI: 0000000000000005
RBP: 00007f38b3bfe310 R08: 65732f636f72702f R09: 65732f636f72702f
R10: 65732f636f72702f R11: 0000000000000246 R12: 00007f38b3bcb0ac
R13: 00007f38b3b0c1a0 R14: 0000200000000200 R15: 00007f38b3bcb03b
 </TASK>

Fixes: 64bf69ddff76 ("[ATM]: deregistration removes device from atm_devs list immediately")
Reported-by: syzbot+8bd335d2ad3b93e80715@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/netdev/685316de.050a0220.216029.0087.GAE@google.com/
Tested-by: syzbot+8bd335d2ad3b93e80715@syzkaller.appspotmail.com
Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Link: https://patch.msgid.link/20250624214505.570679-1-kuni1840@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/atm/resources.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/net/atm/resources.c b/net/atm/resources.c
index 995d29e7fb13..b19d851e1f44 100644
--- a/net/atm/resources.c
+++ b/net/atm/resources.c
@@ -146,11 +146,10 @@ void atm_dev_deregister(struct atm_dev *dev)
 	 */
 	mutex_lock(&atm_dev_mutex);
 	list_del(&dev->dev_list);
-	mutex_unlock(&atm_dev_mutex);
-
 	atm_dev_release_vccs(dev);
 	atm_unregister_sysfs(dev);
 	atm_proc_dev_deregister(dev);
+	mutex_unlock(&atm_dev_mutex);
 
 	atm_dev_put(dev);
 }

From 1dcea07810c8bb4aba1bfed0bbe015b2d708a903 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Wed, 25 Jun 2025 12:17:51 -0400
Subject: [PATCH 0892/1334] bcachefs:
 btree_root_unreadable_and_scan_found_nothing should not be autofix

Autofix is specified in btree_gc.c if it's not an important btree.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/sb-errors_format.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/bcachefs/sb-errors_format.h b/fs/bcachefs/sb-errors_format.h
index 041887aad63a..0641fb634bd4 100644
--- a/fs/bcachefs/sb-errors_format.h
+++ b/fs/bcachefs/sb-errors_format.h
@@ -301,7 +301,7 @@ enum bch_fsck_flags {
 	x(btree_node_bkey_bad_u64s,				260,	0)		\
 	x(btree_node_topology_empty_interior_node,		261,	0)		\
 	x(btree_ptr_v2_min_key_bad,				262,	0)		\
-	x(btree_root_unreadable_and_scan_found_nothing,		263,	FSCK_AUTOFIX)	\
+	x(btree_root_unreadable_and_scan_found_nothing,		263,	0)		\
 	x(snapshot_node_missing,				264,	FSCK_AUTOFIX)	\
 	x(dup_backpointer_to_bad_csum_extent,			265,	0)		\
 	x(btree_bitmap_not_marked,				266,	FSCK_AUTOFIX)	\

From 3e72acb78b73ccffeaf929c039dc5a0a7a147535 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Wed, 25 Jun 2025 12:45:11 -0400
Subject: [PATCH 0893/1334] bcachefs: Ensure btree node scan runs before
 checking for scanned nodes

Previously, calling bch2_btree_has_scanned_nodes() when btree node
scan hadn't actually run would erroniously return false - causing us to
think a btree was entirely gone.

This fixes a 6.16 regression from moving the scheduling of btree node
scan out of bch2_btree_lost_data() (fixing the bug where we'd schedule
it persistently in the superblock) and only scheduling it when
check_toploogy() is asking for scanned btree nodes.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/btree_gc.c        | 29 ++++++++++++++++++-----------
 fs/bcachefs/btree_node_scan.c |  6 +++++-
 fs/bcachefs/btree_node_scan.h |  2 +-
 3 files changed, 24 insertions(+), 13 deletions(-)

diff --git a/fs/bcachefs/btree_gc.c b/fs/bcachefs/btree_gc.c
index 697c6ecc3a65..bac108e93823 100644
--- a/fs/bcachefs/btree_gc.c
+++ b/fs/bcachefs/btree_gc.c
@@ -534,32 +534,39 @@ fsck_err:
 	return ret;
 }
 
-static int bch2_check_root(struct btree_trans *trans, enum btree_id i,
+static int bch2_check_root(struct btree_trans *trans, enum btree_id btree,
 			   bool *reconstructed_root)
 {
 	struct bch_fs *c = trans->c;
-	struct btree_root *r = bch2_btree_id_root(c, i);
+	struct btree_root *r = bch2_btree_id_root(c, btree);
 	struct printbuf buf = PRINTBUF;
 	int ret = 0;
 
-	bch2_btree_id_to_text(&buf, i);
+	bch2_btree_id_to_text(&buf, btree);
 
 	if (r->error) {
 		bch_info(c, "btree root %s unreadable, must recover from scan", buf.buf);
 
-		r->alive = false;
-		r->error = 0;
+		ret = bch2_btree_has_scanned_nodes(c, btree);
+		if (ret < 0)
+			goto err;
 
-		if (!bch2_btree_has_scanned_nodes(c, i)) {
+		if (!ret) {
 			__fsck_err(trans,
-				   FSCK_CAN_FIX|(!btree_id_important(i) ? FSCK_AUTOFIX : 0),
+				   FSCK_CAN_FIX|(!btree_id_important(btree) ? FSCK_AUTOFIX : 0),
 				   btree_root_unreadable_and_scan_found_nothing,
 				   "no nodes found for btree %s, continue?", buf.buf);
-			bch2_btree_root_alloc_fake_trans(trans, i, 0);
+
+			r->alive = false;
+			r->error = 0;
+			bch2_btree_root_alloc_fake_trans(trans, btree, 0);
 		} else {
-			bch2_btree_root_alloc_fake_trans(trans, i, 1);
-			bch2_shoot_down_journal_keys(c, i, 1, BTREE_MAX_DEPTH, POS_MIN, SPOS_MAX);
-			ret = bch2_get_scanned_nodes(c, i, 0, POS_MIN, SPOS_MAX);
+			r->alive = false;
+			r->error = 0;
+			bch2_btree_root_alloc_fake_trans(trans, btree, 1);
+
+			bch2_shoot_down_journal_keys(c, btree, 1, BTREE_MAX_DEPTH, POS_MIN, SPOS_MAX);
+			ret = bch2_get_scanned_nodes(c, btree, 0, POS_MIN, SPOS_MAX);
 			if (ret)
 				goto err;
 		}
diff --git a/fs/bcachefs/btree_node_scan.c b/fs/bcachefs/btree_node_scan.c
index a35847734a60..23d8c62ea4b6 100644
--- a/fs/bcachefs/btree_node_scan.c
+++ b/fs/bcachefs/btree_node_scan.c
@@ -521,8 +521,12 @@ bool bch2_btree_node_is_stale(struct bch_fs *c, struct btree *b)
 	return false;
 }
 
-bool bch2_btree_has_scanned_nodes(struct bch_fs *c, enum btree_id btree)
+int bch2_btree_has_scanned_nodes(struct bch_fs *c, enum btree_id btree)
 {
+	int ret = bch2_run_print_explicit_recovery_pass(c, BCH_RECOVERY_PASS_scan_for_btree_nodes);
+	if (ret)
+		return ret;
+
 	struct found_btree_node search = {
 		.btree_id	= btree,
 		.level		= 0,
diff --git a/fs/bcachefs/btree_node_scan.h b/fs/bcachefs/btree_node_scan.h
index 08687b209787..66e6f9ed19d0 100644
--- a/fs/bcachefs/btree_node_scan.h
+++ b/fs/bcachefs/btree_node_scan.h
@@ -4,7 +4,7 @@
 
 int bch2_scan_for_btree_nodes(struct bch_fs *);
 bool bch2_btree_node_is_stale(struct bch_fs *, struct btree *);
-bool bch2_btree_has_scanned_nodes(struct bch_fs *, enum btree_id);
+int bch2_btree_has_scanned_nodes(struct bch_fs *, enum btree_id);
 int bch2_get_scanned_nodes(struct bch_fs *, enum btree_id, unsigned, struct bpos, struct bpos);
 void bch2_find_btree_nodes_exit(struct find_btree_nodes *);
 

From 64b6a788bd96a0cdc11073a2d1f85413b078c1f2 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Wed, 25 Jun 2025 00:48:14 -0400
Subject: [PATCH 0894/1334] bcachefs: Ensure we rewind to run recovery passes

Fix a 6.16 regression from the recovery pass rework, which introduced a
bug where calling bch2_run_explicit_recovery_pass() would only return
the error code to rewind recovery for the first call that scheduled that
recovery pass.

If the error code from the first call was swallowed (because it was
called by an asynchronous codepath), subsequent calls would go "ok, this
pass is already marked as needing to run" and return 0.

Fixing this ensures that check_topology bails out to run btree_node_scan
before doing any repair.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/recovery_passes.c | 13 ++++++++-----
 1 file changed, 8 insertions(+), 5 deletions(-)

diff --git a/fs/bcachefs/recovery_passes.c b/fs/bcachefs/recovery_passes.c
index c2c18c0a5429..c09ed2dd4639 100644
--- a/fs/bcachefs/recovery_passes.c
+++ b/fs/bcachefs/recovery_passes.c
@@ -313,6 +313,9 @@ static bool recovery_pass_needs_set(struct bch_fs *c,
 	 */
 	bool in_recovery = test_bit(BCH_FS_in_recovery, &c->flags);
 	bool persistent = !in_recovery || !(*flags & RUN_RECOVERY_PASS_nopersistent);
+	bool rewind = in_recovery &&
+		r->curr_pass > pass &&
+		!(r->passes_complete & BIT_ULL(pass));
 
 	if (persistent
 	    ? !(c->sb.recovery_passes_required & BIT_ULL(pass))
@@ -323,6 +326,9 @@ static bool recovery_pass_needs_set(struct bch_fs *c,
 	    (r->passes_ratelimiting & BIT_ULL(pass)))
 		return true;
 
+	if (rewind)
+		return true;
+
 	return false;
 }
 
@@ -337,7 +343,6 @@ int __bch2_run_explicit_recovery_pass(struct bch_fs *c,
 	struct bch_fs_recovery *r = &c->recovery;
 	int ret = 0;
 
-
 	lockdep_assert_held(&c->sb_lock);
 
 	bch2_printbuf_make_room(out, 1024);
@@ -408,10 +413,8 @@ int bch2_run_explicit_recovery_pass(struct bch_fs *c,
 {
 	int ret = 0;
 
-	scoped_guard(mutex, &c->sb_lock) {
-		if (!recovery_pass_needs_set(c, pass, &flags))
-			return 0;
-
+	if (recovery_pass_needs_set(c, pass, &flags)) {
+		guard(mutex)(&c->sb_lock);
 		ret = __bch2_run_explicit_recovery_pass(c, out, pass, flags);
 		bch2_write_super(c);
 	}

From ef6fac0f9e5d0695cee1d820c727fe753eca52d5 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Wed, 25 Jun 2025 14:55:59 -0400
Subject: [PATCH 0895/1334] bcachefs: Plumb correct ip to trans_relock_fail
 tracepoint

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/btree_locking.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/fs/bcachefs/btree_locking.c b/fs/bcachefs/btree_locking.c
index 91a51aef82f1..bed2b4b6ffb9 100644
--- a/fs/bcachefs/btree_locking.c
+++ b/fs/bcachefs/btree_locking.c
@@ -771,7 +771,7 @@ static inline void __bch2_trans_unlock(struct btree_trans *trans)
 }
 
 static noinline __cold void bch2_trans_relock_fail(struct btree_trans *trans, struct btree_path *path,
-						  struct get_locks_fail *f, bool trace)
+						   struct get_locks_fail *f, bool trace, ulong ip)
 {
 	if (!trace)
 		goto out;
@@ -796,7 +796,7 @@ static noinline __cold void bch2_trans_relock_fail(struct btree_trans *trans, st
 			prt_printf(&buf, " total locked %u.%u.%u", c.n[0], c.n[1], c.n[2]);
 		}
 
-		trace_trans_restart_relock(trans, _RET_IP_, buf.buf);
+		trace_trans_restart_relock(trans, ip, buf.buf);
 		printbuf_exit(&buf);
 	}
 
@@ -806,7 +806,7 @@ out:
 	bch2_trans_verify_locks(trans);
 }
 
-static inline int __bch2_trans_relock(struct btree_trans *trans, bool trace)
+static inline int __bch2_trans_relock(struct btree_trans *trans, bool trace, ulong ip)
 {
 	bch2_trans_verify_locks(trans);
 
@@ -825,7 +825,7 @@ static inline int __bch2_trans_relock(struct btree_trans *trans, bool trace)
 		if (path->should_be_locked &&
 		    (ret = btree_path_get_locks(trans, path, false, &f,
 					BCH_ERR_transaction_restart_relock))) {
-			bch2_trans_relock_fail(trans, path, &f, trace);
+			bch2_trans_relock_fail(trans, path, &f, trace, ip);
 			return ret;
 		}
 	}
@@ -838,12 +838,12 @@ out:
 
 int bch2_trans_relock(struct btree_trans *trans)
 {
-	return __bch2_trans_relock(trans, true);
+	return __bch2_trans_relock(trans, true, _RET_IP_);
 }
 
 int bch2_trans_relock_notrace(struct btree_trans *trans)
 {
-	return __bch2_trans_relock(trans, false);
+	return __bch2_trans_relock(trans, false, _RET_IP_);
 }
 
 void bch2_trans_unlock(struct btree_trans *trans)

From 7ab6847a03229e73bb7c58ca397630f699e79b53 Mon Sep 17 00:00:00 2001
From: Salvatore Bonaccorso <carnil@debian.org>
Date: Wed, 25 Jun 2025 20:41:28 +0200
Subject: [PATCH 0896/1334] ALSA: hda/realtek: Fix built-in mic on ASUS
 VivoBook X507UAR

The built-in mic of ASUS VivoBook X507UAR is broken recently by the fix
of the pin sort. The fixup ALC256_FIXUP_ASUS_MIC_NO_PRESENCE is working
for addressing the regression, too.

Fixes: 3b4309546b48 ("ALSA: hda: Fix headset detection failure due to unstable sort")
Reported-by: Igor Tamara <igor.tamara@gmail.com>
Closes: https://bugs.debian.org/1108069
Signed-off-by: Salvatore Bonaccorso <carnil@debian.org>
Link: https://lore.kernel.org/CADdHDco7_o=4h_epjEAb92Dj-vUz_PoTC2-W9g5ncT2E0NzfeQ@mail.gmail.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/patch_realtek.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 784644a2b51d..5d6d01ecfee2 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -11031,6 +11031,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1043, 0x1df3, "ASUS UM5606WA", ALC294_FIXUP_BASS_SPEAKER_15),
 	SND_PCI_QUIRK(0x1043, 0x1264, "ASUS UM5606KA", ALC294_FIXUP_BASS_SPEAKER_15),
 	SND_PCI_QUIRK(0x1043, 0x1e02, "ASUS UX3402ZA", ALC245_FIXUP_CS35L41_SPI_2),
+	SND_PCI_QUIRK(0x1043, 0x1e10, "ASUS VivoBook X507UAR", ALC256_FIXUP_ASUS_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1043, 0x1e11, "ASUS Zephyrus G15", ALC289_FIXUP_ASUS_GA502),
 	SND_PCI_QUIRK(0x1043, 0x1e12, "ASUS UM3402", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x1043, 0x1e1f, "ASUS Vivobook 15 X1504VAP", ALC2XX_FIXUP_HEADSET_MIC),

From af040a9a296044fd4b748786c2516f172a7617f1 Mon Sep 17 00:00:00 2001
From: Wei-Lin Chang <r09922117@csie.ntu.edu.tw>
Date: Wed, 25 Jun 2025 16:47:09 +0800
Subject: [PATCH 0897/1334] KVM: arm64: nv: Fix MI line level calculation in
 vgic_v3_nested_update_mi()

The state of the vcpu's MI line should be asserted when its
ICH_HCR_EL2.En is set and ICH_MISR_EL2 is non-zero. Using bitwise AND
(&=) directly for this calculation will not give us the correct result
when the LSB of the vcpu's ICH_MISR_EL2 isn't set. Correct this by
directly computing the line level with a logical AND operation.

Signed-off-by: Wei-Lin Chang <r09922117@csie.ntu.edu.tw>
Link: https://lore.kernel.org/r/20250625084709.3968844-1-r09922117@csie.ntu.edu.tw
[maz: drop the level check from the original code]
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/kvm/vgic/vgic-v3-nested.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/arch/arm64/kvm/vgic/vgic-v3-nested.c b/arch/arm64/kvm/vgic/vgic-v3-nested.c
index a50fb7e6841f..679aafe77de2 100644
--- a/arch/arm64/kvm/vgic/vgic-v3-nested.c
+++ b/arch/arm64/kvm/vgic/vgic-v3-nested.c
@@ -401,9 +401,7 @@ void vgic_v3_nested_update_mi(struct kvm_vcpu *vcpu)
 {
 	bool level;
 
-	level  = __vcpu_sys_reg(vcpu, ICH_HCR_EL2) & ICH_HCR_EL2_En;
-	if (level)
-		level &= vgic_v3_get_misr(vcpu);
+	level = (__vcpu_sys_reg(vcpu, ICH_HCR_EL2) & ICH_HCR_EL2_En) && vgic_v3_get_misr(vcpu);
 	kvm_vgic_inject_irq(vcpu->kvm, vcpu,
 			    vcpu->kvm->arch.vgic.mi_intid, level, vcpu);
 }

From e728e705802fec20f65d974a5d5eb91217ac618d Mon Sep 17 00:00:00 2001
From: Quentin Perret <qperret@google.com>
Date: Wed, 25 Jun 2025 10:55:48 +0000
Subject: [PATCH 0898/1334] KVM: arm64: Adjust range correctly during host
 stage-2 faults

host_stage2_adjust_range() tries to find the largest block mapping that
fits within a memory or mmio region (represented by a kvm_mem_range in
this function) during host stage-2 faults under pKVM. To do so, it walks
the host stage-2 page-table, finds the faulting PTE and its level, and
then progressively increments the level until it finds a granule of the
appropriate size. However, the condition in the loop implementing the
above is broken as it checks kvm_level_supports_block_mapping() for the
next level instead of the current, so pKVM may attempt to map a region
larger than can be covered with a single block.

This is not a security problem and is quite rare in practice (the
kvm_mem_range check usually forces host_stage2_adjust_range() to choose a
smaller granule), but this is clearly not the expected behaviour.

Refactor the loop to fix the bug and improve readability.

Fixes: c4f0935e4d95 ("KVM: arm64: Optimize host memory aborts")
Signed-off-by: Quentin Perret <qperret@google.com>
Link: https://lore.kernel.org/r/20250625105548.984572-1-qperret@google.com
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/kvm/hyp/nvhe/mem_protect.c | 20 ++++++++++++--------
 1 file changed, 12 insertions(+), 8 deletions(-)

diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
index 95d7534c9679..8957734d6183 100644
--- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c
+++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
@@ -479,6 +479,7 @@ static int host_stage2_adjust_range(u64 addr, struct kvm_mem_range *range)
 {
 	struct kvm_mem_range cur;
 	kvm_pte_t pte;
+	u64 granule;
 	s8 level;
 	int ret;
 
@@ -496,18 +497,21 @@ static int host_stage2_adjust_range(u64 addr, struct kvm_mem_range *range)
 		return -EPERM;
 	}
 
-	do {
-		u64 granule = kvm_granule_size(level);
+	for (; level <= KVM_PGTABLE_LAST_LEVEL; level++) {
+		if (!kvm_level_supports_block_mapping(level))
+			continue;
+		granule = kvm_granule_size(level);
 		cur.start = ALIGN_DOWN(addr, granule);
 		cur.end = cur.start + granule;
-		level++;
-	} while ((level <= KVM_PGTABLE_LAST_LEVEL) &&
-			!(kvm_level_supports_block_mapping(level) &&
-			  range_included(&cur, range)));
+		if (!range_included(&cur, range))
+			continue;
+		*range = cur;
+		return 0;
+	}
 
-	*range = cur;
+	WARN_ON(1);
 
-	return 0;
+	return -EINVAL;
 }
 
 int host_stage2_idmap_locked(phys_addr_t addr, u64 size,

From 9a2b9416fd1d18d97ce1b737a11fcbc521140e5d Mon Sep 17 00:00:00 2001
From: Mostafa Saleh <smostafa@google.com>
Date: Wed, 25 Jun 2025 12:30:58 +0000
Subject: [PATCH 0899/1334] KVM: arm64: Fix error path in init_hyp_mode()

In the unlikely case pKVM failed to allocate carveout, the error path
tries to access NULL ptr when it de-reference the SVE state from the
uninitialized nVHE per-cpu base.

[    1.575420] pstate: 61400005 (nZCv daif +PAN -UAO -TCO +DIT -SSBS BTYPE=--)
[    1.576010] pc : teardown_hyp_mode+0xe4/0x180
[    1.576920] lr : teardown_hyp_mode+0xd0/0x180
[    1.577308] sp : ffff8000826fb9d0
[    1.577600] x29: ffff8000826fb9d0 x28: 0000000000000000 x27: ffff80008209b000
[    1.578383] x26: ffff800081dde000 x25: ffff8000820493c0 x24: ffff80008209eb00
[    1.579180] x23: 0000000000000040 x22: 0000000000000001 x21: 0000000000000000
[    1.579881] x20: 0000000000000002 x19: ffff800081d540b8 x18: 0000000000000000
[    1.580544] x17: ffff800081205230 x16: 0000000000000152 x15: 00000000fffffff8
[    1.581183] x14: 0000000000000008 x13: fff00000ff7f6880 x12: 000000000000003e
[    1.581813] x11: 0000000000000002 x10: 00000000000000ff x9 : 0000000000000000
[    1.582503] x8 : 0000000000000000 x7 : 7f7f7f7f7f7f7f7f x6 : 43485e525851ff30
[    1.583140] x5 : fff00000ff6e9030 x4 : fff00000ff6e8f80 x3 : 0000000000000000
[    1.583780] x2 : 0000000000000000 x1 : 0000000000000002 x0 : 0000000000000000
[    1.584526] Call trace:
[    1.584945]  teardown_hyp_mode+0xe4/0x180 (P)
[    1.585578]  init_hyp_mode+0x920/0x994
[    1.586005]  kvm_arm_init+0xb4/0x25c
[    1.586387]  do_one_initcall+0xe0/0x258
[    1.586819]  do_initcall_level+0xa0/0xd4
[    1.587224]  do_initcalls+0x54/0x94
[    1.587606]  do_basic_setup+0x1c/0x28
[    1.587998]  kernel_init_freeable+0xc8/0x130
[    1.588409]  kernel_init+0x20/0x1a4
[    1.588768]  ret_from_fork+0x10/0x20
[    1.589568] Code: f875db48 8b1c0109 f100011f 9a8903e8 (f9463100)
[    1.590332] ---[ end trace 0000000000000000 ]---

As Quentin pointed, the order of free is also wrong, we need to free
SVE state first before freeing the per CPU ptrs.

I initially observed this on 6.12, but I could also repro in master.

Signed-off-by: Mostafa Saleh <smostafa@google.com>
Fixes: 66d5b53e20a6 ("KVM: arm64: Allocate memory mapped at hyp for host sve state in pKVM")
Reviewed-by: Quentin Perret <qperret@google.com>
Link: https://lore.kernel.org/r/20250625123058.875179-1-smostafa@google.com
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/kvm/arm.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 38a91bb5d4c7..6bdf79bc5d95 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -2346,7 +2346,9 @@ static void __init teardown_hyp_mode(void)
 	free_hyp_pgds();
 	for_each_possible_cpu(cpu) {
 		free_pages(per_cpu(kvm_arm_hyp_stack_base, cpu), NVHE_STACK_SHIFT - PAGE_SHIFT);
-		free_pages(kvm_nvhe_sym(kvm_arm_hyp_percpu_base)[cpu], nvhe_percpu_order());
+
+		if (!kvm_nvhe_sym(kvm_arm_hyp_percpu_base)[cpu])
+			continue;
 
 		if (free_sve) {
 			struct cpu_sve_state *sve_state;
@@ -2354,6 +2356,9 @@ static void __init teardown_hyp_mode(void)
 			sve_state = per_cpu_ptr_nvhe_sym(kvm_host_data, cpu)->sve_state;
 			free_pages((unsigned long) sve_state, pkvm_host_sve_state_order());
 		}
+
+		free_pages(kvm_nvhe_sym(kvm_arm_hyp_percpu_base)[cpu], nvhe_percpu_order());
+
 	}
 }
 

From 1476b218327b89bbb64c14619a2d34f0c320f2c3 Mon Sep 17 00:00:00 2001
From: Leo Yan <leo.yan@arm.com>
Date: Wed, 25 Jun 2025 18:07:37 +0100
Subject: [PATCH 0900/1334] perf/aux: Fix pending disable flow when the AUX
 ring buffer overruns

If an AUX event overruns, the event core layer intends to disable the
event by setting the 'pending_disable' flag. Unfortunately, the event
is not actually disabled afterwards.

In commit:

  ca6c21327c6a ("perf: Fix missing SIGTRAPs")

the 'pending_disable' flag was changed to a boolean. However, the
AUX event code was not updated accordingly. The flag ends up holding a
CPU number. If this number is zero, the flag is taken as false and the
IRQ work is never triggered.

Later, with commit:

  2b84def990d3 ("perf: Split __perf_pending_irq() out of perf_pending_irq()")

a new IRQ work 'pending_disable_irq' was introduced to handle event
disabling. The AUX event path was not updated to kick off the work queue.

To fix this bug, when an AUX ring buffer overrun is detected, call
perf_event_disable_inatomic() to initiate the pending disable flow.

Also update the outdated comment for setting the flag, to reflect the
boolean values (0 or 1).

Fixes: 2b84def990d3 ("perf: Split __perf_pending_irq() out of perf_pending_irq()")
Fixes: ca6c21327c6a ("perf: Fix missing SIGTRAPs")
Signed-off-by: Leo Yan <leo.yan@arm.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: James Clark <james.clark@linaro.org>
Reviewed-by: Yeoreum Yun <yeoreum.yun@arm.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Liang Kan <kan.liang@linux.intel.com>
Cc: Marco Elver <elver@google.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: linux-perf-users@vger.kernel.org
Link: https://lore.kernel.org/r/20250625170737.2918295-1-leo.yan@arm.com
---
 kernel/events/core.c        | 6 +++---
 kernel/events/ring_buffer.c | 4 ++--
 2 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 1f746469fda5..7281230044d0 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -7251,15 +7251,15 @@ static void __perf_pending_disable(struct perf_event *event)
 	 *  CPU-A			CPU-B
 	 *
 	 *  perf_event_disable_inatomic()
-	 *    @pending_disable = CPU-A;
+	 *    @pending_disable = 1;
 	 *    irq_work_queue();
 	 *
 	 *  sched-out
-	 *    @pending_disable = -1;
+	 *    @pending_disable = 0;
 	 *
 	 *				sched-in
 	 *				perf_event_disable_inatomic()
-	 *				  @pending_disable = CPU-B;
+	 *				  @pending_disable = 1;
 	 *				  irq_work_queue(); // FAILS
 	 *
 	 *  irq_work_run()
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index d2aef87c7e9f..aa9a759e824f 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -441,7 +441,7 @@ void *perf_aux_output_begin(struct perf_output_handle *handle,
 		 * store that will be enabled on successful return
 		 */
 		if (!handle->size) { /* A, matches D */
-			event->pending_disable = smp_processor_id();
+			perf_event_disable_inatomic(handle->event);
 			perf_output_wakeup(handle);
 			WRITE_ONCE(rb->aux_nest, 0);
 			goto err_put;
@@ -526,7 +526,7 @@ void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size)
 
 	if (wakeup) {
 		if (handle->aux_flags & PERF_AUX_FLAG_TRUNCATED)
-			handle->event->pending_disable = smp_processor_id();
+			perf_event_disable_inatomic(handle->event);
 		perf_output_wakeup(handle);
 	}
 

From 8d89661a36dd3bb8c9902cff36dc0c144dce3faf Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 24 Jun 2025 11:32:58 -0700
Subject: [PATCH 0901/1334] net: selftests: fix TCP packet checksum

The length in the pseudo header should be the length of the L3 payload
AKA the L4 header+payload. The selftest code builds the packet from
the lower layers up, so all the headers are pushed already when it
constructs L4. We need to subtract the lower layer headers from skb->len.

Fixes: 3e1e58d64c3d ("net: add generic selftest support")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Gerhard Engleder <gerhard@engleder-embedded.com>
Reported-by: Oleksij Rempel <o.rempel@pengutronix.de>
Tested-by: Oleksij Rempel <o.rempel@pengutronix.de>
Reviewed-by: Oleksij Rempel <o.rempel@pengutronix.de>
Link: https://patch.msgid.link/20250624183258.3377740-1-kuba@kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/core/selftests.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/net/core/selftests.c b/net/core/selftests.c
index 35f807ea9952..406faf8e5f3f 100644
--- a/net/core/selftests.c
+++ b/net/core/selftests.c
@@ -160,8 +160,9 @@ static struct sk_buff *net_test_get_skb(struct net_device *ndev,
 	skb->csum = 0;
 	skb->ip_summed = CHECKSUM_PARTIAL;
 	if (attr->tcp) {
-		thdr->check = ~tcp_v4_check(skb->len, ihdr->saddr,
-					    ihdr->daddr, 0);
+		int l4len = skb->len - skb_transport_offset(skb);
+
+		thdr->check = ~tcp_v4_check(l4len, ihdr->saddr, ihdr->daddr, 0);
 		skb->csum_start = skb_transport_header(skb) - skb->head;
 		skb->csum_offset = offsetof(struct tcphdr, check);
 	} else {

From 85720e04d9af0b77f8092b12a06661a8d459d4a0 Mon Sep 17 00:00:00 2001
From: Jiawen Wu <jiawenwu@trustnetic.com>
Date: Wed, 25 Jun 2025 10:39:24 +0800
Subject: [PATCH 0902/1334] net: libwx: fix the creation of page_pool

'rx_ring->size' means the count of ring descriptors multiplied by the
size of one descriptor. When increasing the count of ring descriptors,
it may exceed the limit of pool size.

[ 864.209610] page_pool_create_percpu() gave up with errno -7
[ 864.209613] txgbe 0000:11:00.0: Page pool creation failed: -7

Fix to set the pool_size to the count of ring descriptors.

Fixes: 850b971110b2 ("net: libwx: Allocate Rx and Tx resources")
Cc: stable@vger.kernel.org
Signed-off-by: Jiawen Wu <jiawenwu@trustnetic.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Mina Almasry <almasrymina@google.com>
Link: https://patch.msgid.link/434C72BFB40E350A+20250625023924.21821-1-jiawenwu@trustnetic.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/wangxun/libwx/wx_lib.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/wangxun/libwx/wx_lib.c b/drivers/net/ethernet/wangxun/libwx/wx_lib.c
index 7f2e6cddfeb1..c57cc4f27249 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_lib.c
+++ b/drivers/net/ethernet/wangxun/libwx/wx_lib.c
@@ -2623,7 +2623,7 @@ static int wx_alloc_page_pool(struct wx_ring *rx_ring)
 	struct page_pool_params pp_params = {
 		.flags = PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV,
 		.order = 0,
-		.pool_size = rx_ring->size,
+		.pool_size = rx_ring->count,
 		.nid = dev_to_node(rx_ring->dev),
 		.dev = rx_ring->dev,
 		.dma_dir = DMA_FROM_DEVICE,

From 0e02219f9cf4f0c0aa3dbf3c820e6612bf3f0c8c Mon Sep 17 00:00:00 2001
From: Quentin Perret <qperret@google.com>
Date: Thu, 26 Jun 2025 10:10:14 +0000
Subject: [PATCH 0903/1334] KVM: arm64: Don't free hyp pages with pKVM on GICv2

Marc reported that enabling protected mode on a device with GICv2
doesn't fail gracefully as one would expect, and leads to a host
kernel crash.

As it turns out, the first half of pKVM init happens before the vgic
probe, and so by the time we find out we have a GICv2 we're already
committed to keeping the pKVM vectors installed at EL2 -- pKVM rejects
stub HVCs for obvious security reasons. However, the error path on KVM
init leads to teardown_hyp_mode() which unconditionally frees hypervisor
allocations (including the EL2 stacks and per-cpu pages) under the
assumption that a previous cpu_hyp_uninit() execution has reset the
vectors back to the stubs, which is false with pKVM.

Interestingly, host stage-2 protection is not enabled yet at this point,
so this use-after-free may go unnoticed for a while. The issue becomes
more obvious after the finalize_pkvm() call.

Fix this by keeping track of the CPUs on which pKVM is initialized in
the kvm_hyp_initialized per-cpu variable, and use it from
teardown_hyp_mode() to skip freeing pages that are in fact used.

Fixes: a770ee80e662 ("KVM: arm64: pkvm: Disable GICv2 support")
Reported-by: Marc Zyngier <maz@kernel.org>
Signed-off-by: Quentin Perret <qperret@google.com>
Link: https://lore.kernel.org/r/20250626101014.1519345-1-qperret@google.com
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/kvm/arm.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 6bdf79bc5d95..b223d21c063c 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -2129,7 +2129,7 @@ static void cpu_hyp_init(void *discard)
 
 static void cpu_hyp_uninit(void *discard)
 {
-	if (__this_cpu_read(kvm_hyp_initialized)) {
+	if (!is_protected_kvm_enabled() && __this_cpu_read(kvm_hyp_initialized)) {
 		cpu_hyp_reset();
 		__this_cpu_write(kvm_hyp_initialized, 0);
 	}
@@ -2345,6 +2345,9 @@ static void __init teardown_hyp_mode(void)
 
 	free_hyp_pgds();
 	for_each_possible_cpu(cpu) {
+		if (per_cpu(kvm_hyp_initialized, cpu))
+			continue;
+
 		free_pages(per_cpu(kvm_arm_hyp_stack_base, cpu), NVHE_STACK_SHIFT - PAGE_SHIFT);
 
 		if (!kvm_nvhe_sym(kvm_arm_hyp_percpu_base)[cpu])

From dd2c18548964ae7ad48d208a765d909cd35448a1 Mon Sep 17 00:00:00 2001
From: Keith Busch <kbusch@kernel.org>
Date: Wed, 11 Jun 2025 06:50:47 +0200
Subject: [PATCH 0904/1334] nvme: reset delayed remove_work after reconnect

The remove_work will proceed with permanently disconnecting on the
initial final path failure if the head shows no paths after the delay.
If a new path connects while the remove_work is pending, and if that new
path happens to disconnect before that remove_work executes, the delayed
removal should reset based on the most recent path disconnect time, but
queue_delayed_work() won't do anything if the work is already pending.
Attempt to cancel the delayed work when a new path connects, and use
mod_delayed_work() in case the remove_work remains pending anyway.

Signed-off-by: Keith Busch <kbusch@kernel.org>
Reviewed-by: Nilay Shroff <nilay@linux.ibm.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/nvme/host/core.c      | 4 ++++
 drivers/nvme/host/multipath.c | 2 +-
 2 files changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 92697f98c601..724f5732786c 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -4036,6 +4036,10 @@ static int nvme_init_ns_head(struct nvme_ns *ns, struct nvme_ns_info *info)
 	list_add_tail_rcu(&ns->siblings, &head->list);
 	ns->head = head;
 	mutex_unlock(&ctrl->subsys->lock);
+
+#ifdef CONFIG_NVME_MULTIPATH
+	cancel_delayed_work(&head->remove_work);
+#endif
 	return 0;
 
 out_put_ns_head:
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index 140079ff86e6..1062467595f3 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -1311,7 +1311,7 @@ void nvme_mpath_remove_disk(struct nvme_ns_head *head)
 		 */
 		if (!try_module_get(THIS_MODULE))
 			goto out;
-		queue_delayed_work(nvme_wq, &head->remove_work,
+		mod_delayed_work(nvme_wq, &head->remove_work,
 				head->delayed_removal_secs * HZ);
 	} else {
 		list_del_init(&head->entry);

From b2e607fecac15e07f50269c080e2e71b5049dfa2 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 11 Jun 2025 07:09:21 +0200
Subject: [PATCH 0905/1334] nvme: refactor the atomic write unit detection

Move all the code out of nvme_update_disk_info into the helper, and
rename the helper to have a somewhat less clumsy name.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Luis Chamberlain <mcgrof@kernel.org>
Reviewed-by: John Garry <john.g.garry@oracle.com>
---
 drivers/nvme/host/core.c | 72 +++++++++++++++++++++-------------------
 1 file changed, 38 insertions(+), 34 deletions(-)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 724f5732786c..520fb5f1e214 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -2015,21 +2015,51 @@ static void nvme_configure_metadata(struct nvme_ctrl *ctrl,
 }
 
 
-static void nvme_update_atomic_write_disk_info(struct nvme_ns *ns,
-			struct nvme_id_ns *id, struct queue_limits *lim,
-			u32 bs, u32 atomic_bs)
+static u32 nvme_configure_atomic_write(struct nvme_ns *ns,
+		struct nvme_id_ns *id, struct queue_limits *lim, u32 bs)
 {
-	unsigned int boundary = 0;
+	u32 atomic_bs, boundary = 0;
 
-	if (id->nsfeat & NVME_NS_FEAT_ATOMICS && id->nawupf) {
-		if (le16_to_cpu(id->nabspf))
+	/*
+	 * We do not support an offset for the atomic boundaries.
+	 */
+	if (id->nabo)
+		return bs;
+
+	if ((id->nsfeat & NVME_NS_FEAT_ATOMICS) && id->nawupf) {
+		/*
+		 * Use the per-namespace atomic write unit when available.
+		 */
+		atomic_bs = (1 + le16_to_cpu(id->nawupf)) * bs;
+		if (id->nabspf)
 			boundary = (le16_to_cpu(id->nabspf) + 1) * bs;
+	} else {
+		/*
+		 * Use the controller wide atomic write unit.  This sucks
+		 * because the limit is defined in terms of logical blocks while
+		 * namespaces can have different formats, and because there is
+		 * no clear language in the specification prohibiting different
+		 * values for different controllers in the subsystem.
+		 */
+		atomic_bs = (1 + ns->ctrl->awupf) * bs;
 	}
+
+	if (!ns->ctrl->subsys->atomic_bs) {
+		ns->ctrl->subsys->atomic_bs = atomic_bs;
+	} else if (ns->ctrl->subsys->atomic_bs != atomic_bs) {
+		dev_err_ratelimited(ns->ctrl->device,
+			"%s: Inconsistent Atomic Write Size, Namespace will not be added: Subsystem=%d bytes, Controller/Namespace=%d bytes\n",
+			ns->disk ? ns->disk->disk_name : "?",
+			ns->ctrl->subsys->atomic_bs,
+			atomic_bs);
+	}
+
 	lim->atomic_write_hw_max = atomic_bs;
 	lim->atomic_write_hw_boundary = boundary;
 	lim->atomic_write_hw_unit_min = bs;
 	lim->atomic_write_hw_unit_max = rounddown_pow_of_two(atomic_bs);
 	lim->features |= BLK_FEAT_ATOMIC_WRITES;
+	return atomic_bs;
 }
 
 static u32 nvme_max_drv_segments(struct nvme_ctrl *ctrl)
@@ -2067,34 +2097,8 @@ static bool nvme_update_disk_info(struct nvme_ns *ns, struct nvme_id_ns *id,
 		valid = false;
 	}
 
-	atomic_bs = phys_bs = bs;
-	if (id->nabo == 0) {
-		/*
-		 * Bit 1 indicates whether NAWUPF is defined for this namespace
-		 * and whether it should be used instead of AWUPF. If NAWUPF ==
-		 * 0 then AWUPF must be used instead.
-		 */
-		if (id->nsfeat & NVME_NS_FEAT_ATOMICS && id->nawupf)
-			atomic_bs = (1 + le16_to_cpu(id->nawupf)) * bs;
-		else
-			atomic_bs = (1 + ns->ctrl->awupf) * bs;
-
-		/*
-		 * Set subsystem atomic bs.
-		 */
-		if (ns->ctrl->subsys->atomic_bs) {
-			if (atomic_bs != ns->ctrl->subsys->atomic_bs) {
-				dev_err_ratelimited(ns->ctrl->device,
-					"%s: Inconsistent Atomic Write Size, Namespace will not be added: Subsystem=%d bytes, Controller/Namespace=%d bytes\n",
-					ns->disk ? ns->disk->disk_name : "?",
-					ns->ctrl->subsys->atomic_bs,
-					atomic_bs);
-			}
-		} else
-			ns->ctrl->subsys->atomic_bs = atomic_bs;
-
-		nvme_update_atomic_write_disk_info(ns, id, lim, bs, atomic_bs);
-	}
+	phys_bs = bs;
+	atomic_bs = nvme_configure_atomic_write(ns, id, lim, bs);
 
 	if (id->nsfeat & NVME_NS_FEAT_IO_OPT) {
 		/* NPWG = Namespace Preferred Write Granularity */

From f46d273449ba65afd53f3dd8fe0182c9df877e08 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 11 Jun 2025 06:54:56 +0200
Subject: [PATCH 0906/1334] nvme: fix atomic write size validation

Don't mix the namespace and controller values, and validate the
per-controller limit when probing the controller.  This avoid spurious
failures for controllers with namespaces that have different namespaces
with different logical block sizes, or report the per-namespace values
only for some namespaces.

It also fixes a missing queue_limits_cancel_update in an error path by
removing that error path.

Fixes: 8695f060a029 ("nvme: all namespaces in a subsystem must adhere to a common atomic write size")
Reported-by: Yi Zhang <yi.zhang@redhat.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Luis Chamberlain <mcgrof@kernel.org>
Reviewed-by: John Garry <john.g.garry@oracle.com>
Tested-by: Yi Zhang <yi.zhang@redhat.com>
---
 drivers/nvme/host/core.c | 33 +++++++++++----------------------
 drivers/nvme/host/nvme.h |  3 +--
 2 files changed, 12 insertions(+), 24 deletions(-)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 520fb5f1e214..e533d791955d 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -2041,17 +2041,7 @@ static u32 nvme_configure_atomic_write(struct nvme_ns *ns,
 		 * no clear language in the specification prohibiting different
 		 * values for different controllers in the subsystem.
 		 */
-		atomic_bs = (1 + ns->ctrl->awupf) * bs;
-	}
-
-	if (!ns->ctrl->subsys->atomic_bs) {
-		ns->ctrl->subsys->atomic_bs = atomic_bs;
-	} else if (ns->ctrl->subsys->atomic_bs != atomic_bs) {
-		dev_err_ratelimited(ns->ctrl->device,
-			"%s: Inconsistent Atomic Write Size, Namespace will not be added: Subsystem=%d bytes, Controller/Namespace=%d bytes\n",
-			ns->disk ? ns->disk->disk_name : "?",
-			ns->ctrl->subsys->atomic_bs,
-			atomic_bs);
+		atomic_bs = (1 + ns->ctrl->subsys->awupf) * bs;
 	}
 
 	lim->atomic_write_hw_max = atomic_bs;
@@ -2386,16 +2376,6 @@ static int nvme_update_ns_info_block(struct nvme_ns *ns,
 	if (!nvme_update_disk_info(ns, id, &lim))
 		capacity = 0;
 
-	/*
-	 * Validate the max atomic write size fits within the subsystem's
-	 * atomic write capabilities.
-	 */
-	if (lim.atomic_write_hw_max > ns->ctrl->subsys->atomic_bs) {
-		blk_mq_unfreeze_queue(ns->disk->queue, memflags);
-		ret = -ENXIO;
-		goto out;
-	}
-
 	nvme_config_discard(ns, &lim);
 	if (IS_ENABLED(CONFIG_BLK_DEV_ZONED) &&
 	    ns->head->ids.csi == NVME_CSI_ZNS)
@@ -3219,6 +3199,7 @@ static int nvme_init_subsystem(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id)
 	memcpy(subsys->model, id->mn, sizeof(subsys->model));
 	subsys->vendor_id = le16_to_cpu(id->vid);
 	subsys->cmic = id->cmic;
+	subsys->awupf = le16_to_cpu(id->awupf);
 
 	/* Versions prior to 1.4 don't necessarily report a valid type */
 	if (id->cntrltype == NVME_CTRL_DISC ||
@@ -3556,6 +3537,15 @@ static int nvme_init_identify(struct nvme_ctrl *ctrl)
 		if (ret)
 			goto out_free;
 	}
+
+	if (le16_to_cpu(id->awupf) != ctrl->subsys->awupf) {
+		dev_err_ratelimited(ctrl->device,
+			"inconsistent AWUPF, controller not added (%u/%u).\n",
+			le16_to_cpu(id->awupf), ctrl->subsys->awupf);
+		ret = -EINVAL;
+		goto out_free;
+	}
+
 	memcpy(ctrl->subsys->firmware_rev, id->fr,
 	       sizeof(ctrl->subsys->firmware_rev));
 
@@ -3651,7 +3641,6 @@ static int nvme_init_identify(struct nvme_ctrl *ctrl)
 		dev_pm_qos_expose_latency_tolerance(ctrl->device);
 	else if (!ctrl->apst_enabled && prev_apst_enabled)
 		dev_pm_qos_hide_latency_tolerance(ctrl->device);
-	ctrl->awupf = le16_to_cpu(id->awupf);
 out_free:
 	kfree(id);
 	return ret;
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index a468cdc5b5cb..7df2ea21851f 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -410,7 +410,6 @@ struct nvme_ctrl {
 
 	enum nvme_ctrl_type cntrltype;
 	enum nvme_dctype dctype;
-	u16 awupf; /* 0's based value. */
 };
 
 static inline enum nvme_ctrl_state nvme_ctrl_state(struct nvme_ctrl *ctrl)
@@ -443,11 +442,11 @@ struct nvme_subsystem {
 	u8			cmic;
 	enum nvme_subsys_type	subtype;
 	u16			vendor_id;
+	u16			awupf; /* 0's based value. */
 	struct ida		ns_ida;
 #ifdef CONFIG_NVME_MULTIPATH
 	enum nvme_iopolicy	iopolicy;
 #endif
-	u32			atomic_bs;
 };
 
 /*

From f0ef0b02af381418973a952867052b12194f9c16 Mon Sep 17 00:00:00 2001
From: Thomas Huth <thuth@redhat.com>
Date: Thu, 26 Jun 2025 20:07:10 +0800
Subject: [PATCH 0907/1334] LoongArch: Replace __ASSEMBLY__ with __ASSEMBLER__
 in headers

While the GCC and Clang compilers already define __ASSEMBLER__
automatically when compiling assembler code, __ASSEMBLY__ is a macro
that only gets defined by the Makefiles in the kernel. This is bad
since macros starting with two underscores are names that are reserved
by the C language. It can also be very confusing for the developers
when switching between userspace and kernelspace coding, or when
dealing with uapi headers that rather should use __ASSEMBLER__ instead.
So let's now standardize on the __ASSEMBLER__ macro that is provided
by the compilers.

This is almost a completely mechanical patch (done with a simple
"sed -i" statement), with one comment tweaked manually in the
arch/loongarch/include/asm/cpu.h file (it was missing the trailing
underscores).

Signed-off-by: Thomas Huth <thuth@redhat.com>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/include/asm/addrspace.h         |  8 ++++----
 arch/loongarch/include/asm/alternative-asm.h   |  4 ++--
 arch/loongarch/include/asm/alternative.h       |  4 ++--
 arch/loongarch/include/asm/asm-extable.h       |  6 +++---
 arch/loongarch/include/asm/asm.h               |  8 ++++----
 arch/loongarch/include/asm/cpu.h               |  4 ++--
 arch/loongarch/include/asm/ftrace.h            |  4 ++--
 arch/loongarch/include/asm/gpr-num.h           |  6 +++---
 arch/loongarch/include/asm/irqflags.h          |  4 ++--
 arch/loongarch/include/asm/jump_label.h        |  4 ++--
 arch/loongarch/include/asm/kasan.h             |  2 +-
 arch/loongarch/include/asm/loongarch.h         | 16 ++++++++--------
 arch/loongarch/include/asm/orc_types.h         |  4 ++--
 arch/loongarch/include/asm/page.h              |  4 ++--
 arch/loongarch/include/asm/pgtable-bits.h      |  4 ++--
 arch/loongarch/include/asm/pgtable.h           |  4 ++--
 arch/loongarch/include/asm/prefetch.h          |  2 +-
 arch/loongarch/include/asm/thread_info.h       |  4 ++--
 arch/loongarch/include/asm/types.h             |  2 +-
 arch/loongarch/include/asm/unwind_hints.h      |  6 +++---
 arch/loongarch/include/asm/vdso/arch_data.h    |  4 ++--
 arch/loongarch/include/asm/vdso/getrandom.h    |  4 ++--
 arch/loongarch/include/asm/vdso/gettimeofday.h |  4 ++--
 arch/loongarch/include/asm/vdso/processor.h    |  4 ++--
 arch/loongarch/include/asm/vdso/vdso.h         |  4 ++--
 arch/loongarch/include/asm/vdso/vsyscall.h     |  4 ++--
 tools/arch/loongarch/include/asm/orc_types.h   |  4 ++--
 27 files changed, 64 insertions(+), 64 deletions(-)

diff --git a/arch/loongarch/include/asm/addrspace.h b/arch/loongarch/include/asm/addrspace.h
index fe198b473f84..e739dbc6329d 100644
--- a/arch/loongarch/include/asm/addrspace.h
+++ b/arch/loongarch/include/asm/addrspace.h
@@ -18,12 +18,12 @@
 /*
  * This gives the physical RAM offset.
  */
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #ifndef PHYS_OFFSET
 #define PHYS_OFFSET	_UL(0)
 #endif
 extern unsigned long vm_map_base;
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #ifndef IO_BASE
 #define IO_BASE			CSR_DMW0_BASE
@@ -66,7 +66,7 @@ extern unsigned long vm_map_base;
 #define FIXADDR_TOP		((unsigned long)(long)(int)0xfffe0000)
 #endif
 
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 #define _ATYPE_
 #define _ATYPE32_
 #define _ATYPE64_
@@ -85,7 +85,7 @@ extern unsigned long vm_map_base;
 /*
  *  32/64-bit LoongArch address spaces
  */
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 #define _ACAST32_
 #define _ACAST64_
 #else
diff --git a/arch/loongarch/include/asm/alternative-asm.h b/arch/loongarch/include/asm/alternative-asm.h
index ff3d10ac393f..7dc29bd9b2f0 100644
--- a/arch/loongarch/include/asm/alternative-asm.h
+++ b/arch/loongarch/include/asm/alternative-asm.h
@@ -2,7 +2,7 @@
 #ifndef _ASM_ALTERNATIVE_ASM_H
 #define _ASM_ALTERNATIVE_ASM_H
 
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 
 #include <asm/asm.h>
 
@@ -77,6 +77,6 @@
 	.previous
 .endm
 
-#endif  /*  __ASSEMBLY__  */
+#endif  /*  __ASSEMBLER__  */
 
 #endif /* _ASM_ALTERNATIVE_ASM_H */
diff --git a/arch/loongarch/include/asm/alternative.h b/arch/loongarch/include/asm/alternative.h
index cee7b29785ab..b5bae21fb3c8 100644
--- a/arch/loongarch/include/asm/alternative.h
+++ b/arch/loongarch/include/asm/alternative.h
@@ -2,7 +2,7 @@
 #ifndef _ASM_ALTERNATIVE_H
 #define _ASM_ALTERNATIVE_H
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/types.h>
 #include <linux/stddef.h>
@@ -106,6 +106,6 @@ extern void apply_alternatives(struct alt_instr *start, struct alt_instr *end);
 #define alternative_2(oldinstr, newinstr1, feature1, newinstr2, feature2) \
 	(asm volatile(ALTERNATIVE_2(oldinstr, newinstr1, feature1, newinstr2, feature2) ::: "memory"))
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* _ASM_ALTERNATIVE_H */
diff --git a/arch/loongarch/include/asm/asm-extable.h b/arch/loongarch/include/asm/asm-extable.h
index df05005f2b80..d60bdf2e6377 100644
--- a/arch/loongarch/include/asm/asm-extable.h
+++ b/arch/loongarch/include/asm/asm-extable.h
@@ -7,7 +7,7 @@
 #define EX_TYPE_UACCESS_ERR_ZERO	2
 #define EX_TYPE_BPF			3
 
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 
 #define __ASM_EXTABLE_RAW(insn, fixup, type, data)	\
 	.pushsection	__ex_table, "a";		\
@@ -22,7 +22,7 @@
 	__ASM_EXTABLE_RAW(\insn, \fixup, EX_TYPE_FIXUP, 0)
 	.endm
 
-#else /* __ASSEMBLY__ */
+#else /* __ASSEMBLER__ */
 
 #include <linux/bits.h>
 #include <linux/stringify.h>
@@ -60,6 +60,6 @@
 #define _ASM_EXTABLE_UACCESS_ERR(insn, fixup, err)			\
 	_ASM_EXTABLE_UACCESS_ERR_ZERO(insn, fixup, err, zero)
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* __ASM_ASM_EXTABLE_H */
diff --git a/arch/loongarch/include/asm/asm.h b/arch/loongarch/include/asm/asm.h
index f591b3245def..f018d26fc995 100644
--- a/arch/loongarch/include/asm/asm.h
+++ b/arch/loongarch/include/asm/asm.h
@@ -110,7 +110,7 @@
 #define LONG_SRA	srai.w
 #define LONG_SRAV	sra.w
 
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 #define LONG		.word
 #endif
 #define LONGSIZE	4
@@ -131,7 +131,7 @@
 #define LONG_SRA	srai.d
 #define LONG_SRAV	sra.d
 
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 #define LONG		.dword
 #endif
 #define LONGSIZE	8
@@ -158,7 +158,7 @@
 
 #define PTR_SCALESHIFT	2
 
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 #define PTR		.word
 #endif
 #define PTRSIZE		4
@@ -181,7 +181,7 @@
 
 #define PTR_SCALESHIFT	3
 
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 #define PTR		.dword
 #endif
 #define PTRSIZE		8
diff --git a/arch/loongarch/include/asm/cpu.h b/arch/loongarch/include/asm/cpu.h
index 98cf4d7b4b0a..dfb982fe8701 100644
--- a/arch/loongarch/include/asm/cpu.h
+++ b/arch/loongarch/include/asm/cpu.h
@@ -46,7 +46,7 @@
 
 #define PRID_PRODUCT_MASK	0x0fff
 
-#if !defined(__ASSEMBLY__)
+#if !defined(__ASSEMBLER__)
 
 enum cpu_type_enum {
 	CPU_UNKNOWN,
@@ -55,7 +55,7 @@ enum cpu_type_enum {
 	CPU_LAST
 };
 
-#endif /* !__ASSEMBLY */
+#endif /* !__ASSEMBLER__ */
 
 /*
  * ISA Level encodings
diff --git a/arch/loongarch/include/asm/ftrace.h b/arch/loongarch/include/asm/ftrace.h
index 6e0a99763a9a..f4caaf764f9e 100644
--- a/arch/loongarch/include/asm/ftrace.h
+++ b/arch/loongarch/include/asm/ftrace.h
@@ -14,7 +14,7 @@
 
 #define MCOUNT_INSN_SIZE 4		/* sizeof mcount call */
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #ifndef CONFIG_DYNAMIC_FTRACE
 
@@ -84,7 +84,7 @@ __arch_ftrace_set_direct_caller(struct pt_regs *regs, unsigned long addr)
 
 #endif
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* CONFIG_FUNCTION_TRACER */
 
diff --git a/arch/loongarch/include/asm/gpr-num.h b/arch/loongarch/include/asm/gpr-num.h
index 996038da806d..af95b941f48b 100644
--- a/arch/loongarch/include/asm/gpr-num.h
+++ b/arch/loongarch/include/asm/gpr-num.h
@@ -2,7 +2,7 @@
 #ifndef __ASM_GPR_NUM_H
 #define __ASM_GPR_NUM_H
 
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 
 	.equ	.L__gpr_num_zero, 0
 	.irp	num,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31
@@ -25,7 +25,7 @@
 	.equ	.L__gpr_num_$s\num, 23 + \num
 	.endr
 
-#else /* __ASSEMBLY__ */
+#else /* __ASSEMBLER__ */
 
 #define __DEFINE_ASM_GPR_NUMS					\
 "	.equ	.L__gpr_num_zero, 0\n"				\
@@ -47,6 +47,6 @@
 "	.equ	.L__gpr_num_$s\\num, 23 + \\num\n"		\
 "	.endr\n"						\
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* __ASM_GPR_NUM_H */
diff --git a/arch/loongarch/include/asm/irqflags.h b/arch/loongarch/include/asm/irqflags.h
index 003172b8406b..620163628a7f 100644
--- a/arch/loongarch/include/asm/irqflags.h
+++ b/arch/loongarch/include/asm/irqflags.h
@@ -5,7 +5,7 @@
 #ifndef _ASM_IRQFLAGS_H
 #define _ASM_IRQFLAGS_H
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/compiler.h>
 #include <linux/stringify.h>
@@ -80,6 +80,6 @@ static inline int arch_irqs_disabled(void)
 	return arch_irqs_disabled_flags(arch_local_save_flags());
 }
 
-#endif /* #ifndef __ASSEMBLY__ */
+#endif /* #ifndef __ASSEMBLER__ */
 
 #endif /* _ASM_IRQFLAGS_H */
diff --git a/arch/loongarch/include/asm/jump_label.h b/arch/loongarch/include/asm/jump_label.h
index 8a924bd69d19..4000c7603d8e 100644
--- a/arch/loongarch/include/asm/jump_label.h
+++ b/arch/loongarch/include/asm/jump_label.h
@@ -7,7 +7,7 @@
 #ifndef __ASM_JUMP_LABEL_H
 #define __ASM_JUMP_LABEL_H
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/types.h>
 
@@ -50,5 +50,5 @@ l_yes:
 	return true;
 }
 
-#endif  /* __ASSEMBLY__ */
+#endif  /* __ASSEMBLER__ */
 #endif	/* __ASM_JUMP_LABEL_H */
diff --git a/arch/loongarch/include/asm/kasan.h b/arch/loongarch/include/asm/kasan.h
index 7f52bd31b9d4..62f139a9c87d 100644
--- a/arch/loongarch/include/asm/kasan.h
+++ b/arch/loongarch/include/asm/kasan.h
@@ -2,7 +2,7 @@
 #ifndef __ASM_KASAN_H
 #define __ASM_KASAN_H
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/linkage.h>
 #include <linux/mmzone.h>
diff --git a/arch/loongarch/include/asm/loongarch.h b/arch/loongarch/include/asm/loongarch.h
index d84dac88a584..a0994d226eff 100644
--- a/arch/loongarch/include/asm/loongarch.h
+++ b/arch/loongarch/include/asm/loongarch.h
@@ -9,15 +9,15 @@
 #include <linux/linkage.h>
 #include <linux/types.h>
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #include <larchintrin.h>
 
 /* CPUCFG */
 #define read_cpucfg(reg) __cpucfg(reg)
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 
 /* LoongArch Registers */
 #define REG_ZERO	0x0
@@ -53,7 +53,7 @@
 #define REG_S7		0x1e
 #define REG_S8		0x1f
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 /* Bit fields for CPUCFG registers */
 #define LOONGARCH_CPUCFG0		0x0
@@ -171,7 +171,7 @@
  * SW emulation for KVM hypervirsor, see arch/loongarch/include/uapi/asm/kvm_para.h
  */
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 /* CSR */
 #define csr_read32(reg) __csrrd_w(reg)
@@ -187,7 +187,7 @@
 #define iocsr_write32(val, reg) __iocsrwr_w(val, reg)
 #define iocsr_write64(val, reg) __iocsrwr_d(val, reg)
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
 /* CSR register number */
 
@@ -1195,7 +1195,7 @@
 #define LOONGARCH_IOCSR_EXTIOI_ROUTE_BASE	0x1c00
 #define IOCSR_EXTIOI_VECTOR_NUM			256
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 static __always_inline u64 drdtime(void)
 {
@@ -1357,7 +1357,7 @@ __BUILD_CSR_OP(tlbidx)
 #define clear_csr_estat(val)	\
 	csr_xchg32(~(val), val, LOONGARCH_CSR_ESTAT)
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 /* Generic EntryLo bit definitions */
 #define ENTRYLO_V		(_ULCAST_(1) << 0)
diff --git a/arch/loongarch/include/asm/orc_types.h b/arch/loongarch/include/asm/orc_types.h
index caf1f71a1057..d5fa98d1d177 100644
--- a/arch/loongarch/include/asm/orc_types.h
+++ b/arch/loongarch/include/asm/orc_types.h
@@ -34,7 +34,7 @@
 #define ORC_TYPE_REGS			3
 #define ORC_TYPE_REGS_PARTIAL		4
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 /*
  * This struct is more or less a vastly simplified version of the DWARF Call
  * Frame Information standard.  It contains only the necessary parts of DWARF
@@ -53,6 +53,6 @@ struct orc_entry {
 	unsigned int	type:3;
 	unsigned int	signal:1;
 };
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* _ORC_TYPES_H */
diff --git a/arch/loongarch/include/asm/page.h b/arch/loongarch/include/asm/page.h
index 7368f12b7cb1..a3aaf34fba16 100644
--- a/arch/loongarch/include/asm/page.h
+++ b/arch/loongarch/include/asm/page.h
@@ -15,7 +15,7 @@
 #define HPAGE_MASK	(~(HPAGE_SIZE - 1))
 #define HUGETLB_PAGE_ORDER	(HPAGE_SHIFT - PAGE_SHIFT)
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/kernel.h>
 #include <linux/pfn.h>
@@ -110,6 +110,6 @@ extern int __virt_addr_valid(volatile void *kaddr);
 #include <asm-generic/memory_model.h>
 #include <asm-generic/getorder.h>
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
 #endif /* _ASM_PAGE_H */
diff --git a/arch/loongarch/include/asm/pgtable-bits.h b/arch/loongarch/include/asm/pgtable-bits.h
index 45bfc65a0c9f..7bbfb04a54cc 100644
--- a/arch/loongarch/include/asm/pgtable-bits.h
+++ b/arch/loongarch/include/asm/pgtable-bits.h
@@ -92,7 +92,7 @@
 #define PAGE_KERNEL_WUC __pgprot(_PAGE_PRESENT | __READABLE | __WRITEABLE | \
 				 _PAGE_GLOBAL | _PAGE_KERN |  _CACHE_WUC)
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #define _PAGE_IOREMAP		pgprot_val(PAGE_KERNEL_SUC)
 
@@ -127,6 +127,6 @@ static inline pgprot_t pgprot_writecombine(pgprot_t _prot)
 	return __pgprot(prot);
 }
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
 #endif /* _ASM_PGTABLE_BITS_H */
diff --git a/arch/loongarch/include/asm/pgtable.h b/arch/loongarch/include/asm/pgtable.h
index b30185302c07..f2aeff544cee 100644
--- a/arch/loongarch/include/asm/pgtable.h
+++ b/arch/loongarch/include/asm/pgtable.h
@@ -55,7 +55,7 @@
 
 #define USER_PTRS_PER_PGD       ((TASK_SIZE64 / PGDIR_SIZE)?(TASK_SIZE64 / PGDIR_SIZE):1)
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/mm_types.h>
 #include <linux/mmzone.h>
@@ -618,6 +618,6 @@ static inline long pmd_protnone(pmd_t pmd)
 #define HAVE_ARCH_UNMAPPED_AREA
 #define HAVE_ARCH_UNMAPPED_AREA_TOPDOWN
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
 #endif /* _ASM_PGTABLE_H */
diff --git a/arch/loongarch/include/asm/prefetch.h b/arch/loongarch/include/asm/prefetch.h
index 1672262a5e2e..0b168cdaae9a 100644
--- a/arch/loongarch/include/asm/prefetch.h
+++ b/arch/loongarch/include/asm/prefetch.h
@@ -8,7 +8,7 @@
 #define Pref_Load	0
 #define Pref_Store	8
 
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 
 	.macro	__pref hint addr
 #ifdef CONFIG_CPU_HAS_PREFETCH
diff --git a/arch/loongarch/include/asm/thread_info.h b/arch/loongarch/include/asm/thread_info.h
index 4f5a9441754e..9dfa2ef00816 100644
--- a/arch/loongarch/include/asm/thread_info.h
+++ b/arch/loongarch/include/asm/thread_info.h
@@ -10,7 +10,7 @@
 
 #ifdef __KERNEL__
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <asm/processor.h>
 
@@ -53,7 +53,7 @@ static inline struct thread_info *current_thread_info(void)
 
 register unsigned long current_stack_pointer __asm__("$sp");
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
 /* thread information allocation */
 #define THREAD_SIZE		SZ_16K
diff --git a/arch/loongarch/include/asm/types.h b/arch/loongarch/include/asm/types.h
index baf15a0dcf8b..0edd731f3d6a 100644
--- a/arch/loongarch/include/asm/types.h
+++ b/arch/loongarch/include/asm/types.h
@@ -8,7 +8,7 @@
 #include <asm-generic/int-ll64.h>
 #include <uapi/asm/types.h>
 
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 #define _ULCAST_
 #define _U64CAST_
 #else
diff --git a/arch/loongarch/include/asm/unwind_hints.h b/arch/loongarch/include/asm/unwind_hints.h
index 2c68bc72736c..16c7f7e465a0 100644
--- a/arch/loongarch/include/asm/unwind_hints.h
+++ b/arch/loongarch/include/asm/unwind_hints.h
@@ -5,7 +5,7 @@
 #include <linux/objtool.h>
 #include <asm/orc_types.h>
 
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 
 .macro UNWIND_HINT_UNDEFINED
 	UNWIND_HINT type=UNWIND_HINT_TYPE_UNDEFINED
@@ -23,7 +23,7 @@
 	UNWIND_HINT sp_reg=ORC_REG_SP type=UNWIND_HINT_TYPE_CALL
 .endm
 
-#else /* !__ASSEMBLY__ */
+#else /* !__ASSEMBLER__ */
 
 #define UNWIND_HINT_SAVE \
 	UNWIND_HINT(UNWIND_HINT_TYPE_SAVE, 0, 0, 0)
@@ -31,6 +31,6 @@
 #define UNWIND_HINT_RESTORE \
 	UNWIND_HINT(UNWIND_HINT_TYPE_RESTORE, 0, 0, 0)
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
 #endif /* _ASM_LOONGARCH_UNWIND_HINTS_H */
diff --git a/arch/loongarch/include/asm/vdso/arch_data.h b/arch/loongarch/include/asm/vdso/arch_data.h
index 322d0a5f1c84..395ec223bcbe 100644
--- a/arch/loongarch/include/asm/vdso/arch_data.h
+++ b/arch/loongarch/include/asm/vdso/arch_data.h
@@ -7,7 +7,7 @@
 #ifndef _VDSO_ARCH_DATA_H
 #define _VDSO_ARCH_DATA_H
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <asm/asm.h>
 #include <asm/vdso.h>
@@ -20,6 +20,6 @@ struct vdso_arch_data {
 	struct vdso_pcpu_data pdata[NR_CPUS];
 };
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif
diff --git a/arch/loongarch/include/asm/vdso/getrandom.h b/arch/loongarch/include/asm/vdso/getrandom.h
index a81724b69f29..2ff05003c6e7 100644
--- a/arch/loongarch/include/asm/vdso/getrandom.h
+++ b/arch/loongarch/include/asm/vdso/getrandom.h
@@ -5,7 +5,7 @@
 #ifndef __ASM_VDSO_GETRANDOM_H
 #define __ASM_VDSO_GETRANDOM_H
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <asm/unistd.h>
 #include <asm/vdso/vdso.h>
@@ -28,6 +28,6 @@ static __always_inline ssize_t getrandom_syscall(void *_buffer, size_t _len, uns
 	return ret;
 }
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
 #endif /* __ASM_VDSO_GETRANDOM_H */
diff --git a/arch/loongarch/include/asm/vdso/gettimeofday.h b/arch/loongarch/include/asm/vdso/gettimeofday.h
index f15503e3336c..dcafabca9bb6 100644
--- a/arch/loongarch/include/asm/vdso/gettimeofday.h
+++ b/arch/loongarch/include/asm/vdso/gettimeofday.h
@@ -7,7 +7,7 @@
 #ifndef __ASM_VDSO_GETTIMEOFDAY_H
 #define __ASM_VDSO_GETTIMEOFDAY_H
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <asm/unistd.h>
 #include <asm/vdso/vdso.h>
@@ -89,6 +89,6 @@ static inline bool loongarch_vdso_hres_capable(void)
 }
 #define __arch_vdso_hres_capable loongarch_vdso_hres_capable
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
 #endif /* __ASM_VDSO_GETTIMEOFDAY_H */
diff --git a/arch/loongarch/include/asm/vdso/processor.h b/arch/loongarch/include/asm/vdso/processor.h
index ef5770b343a0..1e255373b0b8 100644
--- a/arch/loongarch/include/asm/vdso/processor.h
+++ b/arch/loongarch/include/asm/vdso/processor.h
@@ -5,10 +5,10 @@
 #ifndef __ASM_VDSO_PROCESSOR_H
 #define __ASM_VDSO_PROCESSOR_H
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #define cpu_relax()	barrier()
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* __ASM_VDSO_PROCESSOR_H */
diff --git a/arch/loongarch/include/asm/vdso/vdso.h b/arch/loongarch/include/asm/vdso/vdso.h
index 50c65fb29daf..04bd2d452876 100644
--- a/arch/loongarch/include/asm/vdso/vdso.h
+++ b/arch/loongarch/include/asm/vdso/vdso.h
@@ -7,7 +7,7 @@
 #ifndef _ASM_VDSO_VDSO_H
 #define _ASM_VDSO_VDSO_H
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <asm/asm.h>
 #include <asm/page.h>
@@ -16,6 +16,6 @@
 
 #define VVAR_SIZE (VDSO_NR_PAGES << PAGE_SHIFT)
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif
diff --git a/arch/loongarch/include/asm/vdso/vsyscall.h b/arch/loongarch/include/asm/vdso/vsyscall.h
index 1140b54b4bc8..558eb9dfda52 100644
--- a/arch/loongarch/include/asm/vdso/vsyscall.h
+++ b/arch/loongarch/include/asm/vdso/vsyscall.h
@@ -2,13 +2,13 @@
 #ifndef __ASM_VDSO_VSYSCALL_H
 #define __ASM_VDSO_VSYSCALL_H
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <vdso/datapage.h>
 
 /* The asm-generic header needs to be included after the definitions above */
 #include <asm-generic/vdso/vsyscall.h>
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
 #endif /* __ASM_VDSO_VSYSCALL_H */
diff --git a/tools/arch/loongarch/include/asm/orc_types.h b/tools/arch/loongarch/include/asm/orc_types.h
index caf1f71a1057..d5fa98d1d177 100644
--- a/tools/arch/loongarch/include/asm/orc_types.h
+++ b/tools/arch/loongarch/include/asm/orc_types.h
@@ -34,7 +34,7 @@
 #define ORC_TYPE_REGS			3
 #define ORC_TYPE_REGS_PARTIAL		4
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 /*
  * This struct is more or less a vastly simplified version of the DWARF Call
  * Frame Information standard.  It contains only the necessary parts of DWARF
@@ -53,6 +53,6 @@ struct orc_entry {
 	unsigned int	type:3;
 	unsigned int	signal:1;
 };
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* _ORC_TYPES_H */

From 7d69294b8a8d0e19600797711ed3bc047fead1c1 Mon Sep 17 00:00:00 2001
From: Huacai Chen <chenhuacai@loongson.cn>
Date: Thu, 26 Jun 2025 20:07:18 +0800
Subject: [PATCH 0908/1334] LoongArch: Fix build warnings about export.h

After commit a934a57a42f64a4 ("scripts/misc-check: check missing #include
<linux/export.h> when W=1") and 7d95680d64ac8e836c ("scripts/misc-check:
check unnecessary #include <linux/export.h> when W=1"), we get some build
warnings with W=1:

arch/loongarch/kernel/acpi.c: warning: EXPORT_SYMBOL() is used, but #include <linux/export.h> is missing
arch/loongarch/kernel/alternative.c: warning: EXPORT_SYMBOL() is used, but #include <linux/export.h> is missing
arch/loongarch/kernel/kfpu.c: warning: EXPORT_SYMBOL() is used, but #include <linux/export.h> is missing
arch/loongarch/kernel/traps.c: warning: EXPORT_SYMBOL() is used, but #include <linux/export.h> is missing
arch/loongarch/kernel/unwind_guess.c: warning: EXPORT_SYMBOL() is used, but #include <linux/export.h> is missing
arch/loongarch/kernel/unwind_orc.c: warning: EXPORT_SYMBOL() is used, but #include <linux/export.h> is missing
arch/loongarch/kernel/unwind_prologue.c: warning: EXPORT_SYMBOL() is used, but #include <linux/export.h> is missing
arch/loongarch/lib/crc32-loongarch.c: warning: EXPORT_SYMBOL() is used, but #include <linux/export.h> is missing
arch/loongarch/lib/csum.c: warning: EXPORT_SYMBOL() is used, but #include <linux/export.h> is missing
arch/loongarch/kernel/elf.c: warning: EXPORT_SYMBOL() is not used, but #include <linux/export.h> is present
arch/loongarch/kernel/paravirt.c: warning: EXPORT_SYMBOL() is not used, but #include <linux/export.h> is present
arch/loongarch/pci/pci.c: warning: EXPORT_SYMBOL() is not used, but #include <linux/export.h> is present

So fix these build warnings for LoongArch.

Reviewed-by: Masahiro Yamada <masahiroy@kernel.org>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/kernel/acpi.c            | 1 +
 arch/loongarch/kernel/alternative.c     | 1 +
 arch/loongarch/kernel/elf.c             | 1 -
 arch/loongarch/kernel/kfpu.c            | 1 +
 arch/loongarch/kernel/paravirt.c        | 1 -
 arch/loongarch/kernel/traps.c           | 1 +
 arch/loongarch/kernel/unwind_guess.c    | 1 +
 arch/loongarch/kernel/unwind_orc.c      | 3 ++-
 arch/loongarch/kernel/unwind_prologue.c | 1 +
 arch/loongarch/lib/crc32-loongarch.c    | 1 +
 arch/loongarch/lib/csum.c               | 1 +
 arch/loongarch/pci/pci.c                | 1 -
 12 files changed, 10 insertions(+), 4 deletions(-)

diff --git a/arch/loongarch/kernel/acpi.c b/arch/loongarch/kernel/acpi.c
index a54cd6fd3796..1367ca759468 100644
--- a/arch/loongarch/kernel/acpi.c
+++ b/arch/loongarch/kernel/acpi.c
@@ -10,6 +10,7 @@
 #include <linux/init.h>
 #include <linux/acpi.h>
 #include <linux/efi-bgrt.h>
+#include <linux/export.h>
 #include <linux/irq.h>
 #include <linux/irqdomain.h>
 #include <linux/memblock.h>
diff --git a/arch/loongarch/kernel/alternative.c b/arch/loongarch/kernel/alternative.c
index 4ad13847e962..0e0c766df1e3 100644
--- a/arch/loongarch/kernel/alternative.c
+++ b/arch/loongarch/kernel/alternative.c
@@ -1,4 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0-only
+#include <linux/export.h>
 #include <linux/mm.h>
 #include <linux/module.h>
 #include <asm/alternative.h>
diff --git a/arch/loongarch/kernel/elf.c b/arch/loongarch/kernel/elf.c
index 0fa81ced28dc..3d98c6aa00db 100644
--- a/arch/loongarch/kernel/elf.c
+++ b/arch/loongarch/kernel/elf.c
@@ -6,7 +6,6 @@
 
 #include <linux/binfmts.h>
 #include <linux/elf.h>
-#include <linux/export.h>
 #include <linux/sched.h>
 
 #include <asm/cpu-features.h>
diff --git a/arch/loongarch/kernel/kfpu.c b/arch/loongarch/kernel/kfpu.c
index 4c476904227f..141b49bd989c 100644
--- a/arch/loongarch/kernel/kfpu.c
+++ b/arch/loongarch/kernel/kfpu.c
@@ -4,6 +4,7 @@
  */
 
 #include <linux/cpu.h>
+#include <linux/export.h>
 #include <linux/init.h>
 #include <asm/fpu.h>
 #include <asm/smp.h>
diff --git a/arch/loongarch/kernel/paravirt.c b/arch/loongarch/kernel/paravirt.c
index e5a39bbad078..b1b51f920b23 100644
--- a/arch/loongarch/kernel/paravirt.c
+++ b/arch/loongarch/kernel/paravirt.c
@@ -1,5 +1,4 @@
 // SPDX-License-Identifier: GPL-2.0
-#include <linux/export.h>
 #include <linux/types.h>
 #include <linux/interrupt.h>
 #include <linux/irq_work.h>
diff --git a/arch/loongarch/kernel/traps.c b/arch/loongarch/kernel/traps.c
index 47fc2de6d150..3d9be6ca7ec5 100644
--- a/arch/loongarch/kernel/traps.c
+++ b/arch/loongarch/kernel/traps.c
@@ -13,6 +13,7 @@
 #include <linux/kernel.h>
 #include <linux/kexec.h>
 #include <linux/module.h>
+#include <linux/export.h>
 #include <linux/extable.h>
 #include <linux/mm.h>
 #include <linux/sched/mm.h>
diff --git a/arch/loongarch/kernel/unwind_guess.c b/arch/loongarch/kernel/unwind_guess.c
index 98379b7d4147..08d7951b2f60 100644
--- a/arch/loongarch/kernel/unwind_guess.c
+++ b/arch/loongarch/kernel/unwind_guess.c
@@ -3,6 +3,7 @@
  * Copyright (C) 2022 Loongson Technology Corporation Limited
  */
 #include <asm/unwind.h>
+#include <linux/export.h>
 
 unsigned long unwind_get_return_address(struct unwind_state *state)
 {
diff --git a/arch/loongarch/kernel/unwind_orc.c b/arch/loongarch/kernel/unwind_orc.c
index d623935a7547..0005be49b056 100644
--- a/arch/loongarch/kernel/unwind_orc.c
+++ b/arch/loongarch/kernel/unwind_orc.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0-only
-#include <linux/objtool.h>
+#include <linux/export.h>
 #include <linux/module.h>
+#include <linux/objtool.h>
 #include <linux/sort.h>
 #include <asm/exception.h>
 #include <asm/orc_header.h>
diff --git a/arch/loongarch/kernel/unwind_prologue.c b/arch/loongarch/kernel/unwind_prologue.c
index 929ae240280a..729e775bd40d 100644
--- a/arch/loongarch/kernel/unwind_prologue.c
+++ b/arch/loongarch/kernel/unwind_prologue.c
@@ -3,6 +3,7 @@
  * Copyright (C) 2022 Loongson Technology Corporation Limited
  */
 #include <linux/cpumask.h>
+#include <linux/export.h>
 #include <linux/ftrace.h>
 #include <linux/kallsyms.h>
 
diff --git a/arch/loongarch/lib/crc32-loongarch.c b/arch/loongarch/lib/crc32-loongarch.c
index b37cd8537b45..db22c2ec55e2 100644
--- a/arch/loongarch/lib/crc32-loongarch.c
+++ b/arch/loongarch/lib/crc32-loongarch.c
@@ -11,6 +11,7 @@
 
 #include <asm/cpu-features.h>
 #include <linux/crc32.h>
+#include <linux/export.h>
 #include <linux/module.h>
 #include <linux/unaligned.h>
 
diff --git a/arch/loongarch/lib/csum.c b/arch/loongarch/lib/csum.c
index df309ae4045d..bcc9d01d8c41 100644
--- a/arch/loongarch/lib/csum.c
+++ b/arch/loongarch/lib/csum.c
@@ -2,6 +2,7 @@
 // Copyright (C) 2019-2020 Arm Ltd.
 
 #include <linux/compiler.h>
+#include <linux/export.h>
 #include <linux/kasan-checks.h>
 #include <linux/kernel.h>
 
diff --git a/arch/loongarch/pci/pci.c b/arch/loongarch/pci/pci.c
index 2726639150bc..5bc9627a6cf9 100644
--- a/arch/loongarch/pci/pci.c
+++ b/arch/loongarch/pci/pci.c
@@ -3,7 +3,6 @@
  * Copyright (C) 2020-2022 Loongson Technology Corporation Limited
  */
 #include <linux/kernel.h>
-#include <linux/export.h>
 #include <linux/init.h>
 #include <linux/acpi.h>
 #include <linux/types.h>

From 39503fc84b4ea94f2bedca481de5e225e0df729d Mon Sep 17 00:00:00 2001
From: Ming Wang <wangming01@loongson.cn>
Date: Thu, 26 Jun 2025 20:07:18 +0800
Subject: [PATCH 0909/1334] LoongArch: Reserve the EFI memory map region

The EFI memory map at 'boot_memmap' is crucial for kdump to understand
the primary kernel's memory layout. This memory region, typically part
of EFI Boot Services (BS) data, can be overwritten after ExitBootServices
if not explicitly preserved by the kernel.

This commit addresses this by:
1. Calling memblock_reserve() to reserve the entire physical region
   occupied by the EFI memory map (header + descriptors). This prevents
   the primary kernel from reallocating and corrupting this area.
2. Setting the EFI_PRESERVE_BS_REGIONS flag in efi.flags. This indicates
   that efforts have been made to preserve critical BS code/data regions
   which can be useful for other kernel subsystems or debugging.

These changes ensure the original EFI memory map data remains intact,
improving kdump reliability and potentially aiding other EFI-related
functionalities that might rely on preserved BS code/data.

Signed-off-by: Ming Wang <wangming01@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/kernel/efi.c | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/arch/loongarch/kernel/efi.c b/arch/loongarch/kernel/efi.c
index de21e72759ee..860a3bc030e0 100644
--- a/arch/loongarch/kernel/efi.c
+++ b/arch/loongarch/kernel/efi.c
@@ -144,6 +144,18 @@ void __init efi_init(void)
 		if (efi_memmap_init_early(&data) < 0)
 			panic("Unable to map EFI memory map.\n");
 
+		/*
+		 * Reserve the physical memory region occupied by the EFI
+		 * memory map table (header + descriptors). This is crucial
+		 * for kdump, as the kdump kernel relies on this original
+		 * memmap passed by the bootloader. Without reservation,
+		 * this region could be overwritten by the primary kernel.
+		 * Also, set the EFI_PRESERVE_BS_REGIONS flag to indicate that
+		 * critical boot services code/data regions like this are preserved.
+		 */
+		memblock_reserve((phys_addr_t)boot_memmap, sizeof(*tbl) + data.size);
+		set_bit(EFI_PRESERVE_BS_REGIONS, &efi.flags);
+
 		early_memunmap(tbl, sizeof(*tbl));
 	}
 

From a0137c9048252ea965a0436895c77d1c917dfe2a Mon Sep 17 00:00:00 2001
From: Kees Cook <kees@kernel.org>
Date: Thu, 26 Jun 2025 20:07:18 +0800
Subject: [PATCH 0910/1334] LoongArch: Handle KCOV __init vs inline mismatches

When the KCOV is enabled all functions get instrumented, unless
the __no_sanitize_coverage attribute is used. To prepare for
__no_sanitize_coverage being applied to __init functions, we have to
handle differences in how GCC's inline optimizations get resolved.
For LoongArch this exposed several places where __init annotations
were missing but ended up being "accidentally correct". So fix these
cases.

Signed-off-by: Kees Cook <kees@kernel.org>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/include/asm/smp.h | 2 +-
 arch/loongarch/kernel/time.c     | 2 +-
 arch/loongarch/mm/ioremap.c      | 4 ++--
 3 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/arch/loongarch/include/asm/smp.h b/arch/loongarch/include/asm/smp.h
index ad0bd234a0f1..3a47f52959a8 100644
--- a/arch/loongarch/include/asm/smp.h
+++ b/arch/loongarch/include/asm/smp.h
@@ -39,7 +39,7 @@ int loongson_cpu_disable(void);
 void loongson_cpu_die(unsigned int cpu);
 #endif
 
-static inline void plat_smp_setup(void)
+static inline void __init plat_smp_setup(void)
 {
 	loongson_smp_setup();
 }
diff --git a/arch/loongarch/kernel/time.c b/arch/loongarch/kernel/time.c
index bc75a3a69fc8..367906b10f81 100644
--- a/arch/loongarch/kernel/time.c
+++ b/arch/loongarch/kernel/time.c
@@ -102,7 +102,7 @@ static int constant_timer_next_event(unsigned long delta, struct clock_event_dev
 	return 0;
 }
 
-static unsigned long __init get_loops_per_jiffy(void)
+static unsigned long get_loops_per_jiffy(void)
 {
 	unsigned long lpj = (unsigned long)const_clock_freq;
 
diff --git a/arch/loongarch/mm/ioremap.c b/arch/loongarch/mm/ioremap.c
index 70ca73019811..df949a3d0f34 100644
--- a/arch/loongarch/mm/ioremap.c
+++ b/arch/loongarch/mm/ioremap.c
@@ -16,12 +16,12 @@ void __init early_iounmap(void __iomem *addr, unsigned long size)
 
 }
 
-void *early_memremap_ro(resource_size_t phys_addr, unsigned long size)
+void * __init early_memremap_ro(resource_size_t phys_addr, unsigned long size)
 {
 	return early_memremap(phys_addr, size);
 }
 
-void *early_memremap_prot(resource_size_t phys_addr, unsigned long size,
+void * __init early_memremap_prot(resource_size_t phys_addr, unsigned long size,
 		    unsigned long prot_val)
 {
 	return early_memremap(phys_addr, size);

From 080e8d2ecdfde588897aa8a87a8884061f4dbbbb Mon Sep 17 00:00:00 2001
From: Bibo Mao <maobibo@loongson.cn>
Date: Thu, 26 Jun 2025 20:07:27 +0800
Subject: [PATCH 0911/1334] LoongArch: KVM: Avoid overflow with array index

The variable index is modified and reused as array index when modify
register EIOINTC_ENABLE. There will be array index overflow problem.

Cc: stable@vger.kernel.org
Fixes: 3956a52bc05b ("LoongArch: KVM: Add EIOINTC read and write functions")
Signed-off-by: Bibo Mao <maobibo@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/kvm/intc/eiointc.c | 17 +++++++----------
 1 file changed, 7 insertions(+), 10 deletions(-)

diff --git a/arch/loongarch/kvm/intc/eiointc.c b/arch/loongarch/kvm/intc/eiointc.c
index f39929d7bf8a..9c47456b805c 100644
--- a/arch/loongarch/kvm/intc/eiointc.c
+++ b/arch/loongarch/kvm/intc/eiointc.c
@@ -436,17 +436,16 @@ static int loongarch_eiointc_writew(struct kvm_vcpu *vcpu,
 		break;
 	case EIOINTC_ENABLE_START ... EIOINTC_ENABLE_END:
 		index = (offset - EIOINTC_ENABLE_START) >> 1;
-		old_data = s->enable.reg_u32[index];
+		old_data = s->enable.reg_u16[index];
 		s->enable.reg_u16[index] = data;
 		/*
 		 * 1: enable irq.
 		 * update irq when isr is set.
 		 */
 		data = s->enable.reg_u16[index] & ~old_data & s->isr.reg_u16[index];
-		index = index << 1;
 		for (i = 0; i < sizeof(data); i++) {
 			u8 mask = (data >> (i * 8)) & 0xff;
-			eiointc_enable_irq(vcpu, s, index + i, mask, 1);
+			eiointc_enable_irq(vcpu, s, index * 2 + i, mask, 1);
 		}
 		/*
 		 * 0: disable irq.
@@ -455,7 +454,7 @@ static int loongarch_eiointc_writew(struct kvm_vcpu *vcpu,
 		data = ~s->enable.reg_u16[index] & old_data & s->isr.reg_u16[index];
 		for (i = 0; i < sizeof(data); i++) {
 			u8 mask = (data >> (i * 8)) & 0xff;
-			eiointc_enable_irq(vcpu, s, index, mask, 0);
+			eiointc_enable_irq(vcpu, s, index * 2 + i, mask, 0);
 		}
 		break;
 	case EIOINTC_BOUNCE_START ... EIOINTC_BOUNCE_END:
@@ -529,10 +528,9 @@ static int loongarch_eiointc_writel(struct kvm_vcpu *vcpu,
 		 * update irq when isr is set.
 		 */
 		data = s->enable.reg_u32[index] & ~old_data & s->isr.reg_u32[index];
-		index = index << 2;
 		for (i = 0; i < sizeof(data); i++) {
 			u8 mask = (data >> (i * 8)) & 0xff;
-			eiointc_enable_irq(vcpu, s, index + i, mask, 1);
+			eiointc_enable_irq(vcpu, s, index * 4 + i, mask, 1);
 		}
 		/*
 		 * 0: disable irq.
@@ -541,7 +539,7 @@ static int loongarch_eiointc_writel(struct kvm_vcpu *vcpu,
 		data = ~s->enable.reg_u32[index] & old_data & s->isr.reg_u32[index];
 		for (i = 0; i < sizeof(data); i++) {
 			u8 mask = (data >> (i * 8)) & 0xff;
-			eiointc_enable_irq(vcpu, s, index, mask, 0);
+			eiointc_enable_irq(vcpu, s, index * 4 + i, mask, 0);
 		}
 		break;
 	case EIOINTC_BOUNCE_START ... EIOINTC_BOUNCE_END:
@@ -615,10 +613,9 @@ static int loongarch_eiointc_writeq(struct kvm_vcpu *vcpu,
 		 * update irq when isr is set.
 		 */
 		data = s->enable.reg_u64[index] & ~old_data & s->isr.reg_u64[index];
-		index = index << 3;
 		for (i = 0; i < sizeof(data); i++) {
 			u8 mask = (data >> (i * 8)) & 0xff;
-			eiointc_enable_irq(vcpu, s, index + i, mask, 1);
+			eiointc_enable_irq(vcpu, s, index * 8 + i, mask, 1);
 		}
 		/*
 		 * 0: disable irq.
@@ -627,7 +624,7 @@ static int loongarch_eiointc_writeq(struct kvm_vcpu *vcpu,
 		data = ~s->enable.reg_u64[index] & old_data & s->isr.reg_u64[index];
 		for (i = 0; i < sizeof(data); i++) {
 			u8 mask = (data >> (i * 8)) & 0xff;
-			eiointc_enable_irq(vcpu, s, index, mask, 0);
+			eiointc_enable_irq(vcpu, s, index * 8 + i, mask, 0);
 		}
 		break;
 	case EIOINTC_BOUNCE_START ... EIOINTC_BOUNCE_END:

From a4b1b51ae132ac199412028a2df7b6c267888190 Mon Sep 17 00:00:00 2001
From: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Date: Fri, 6 Jun 2025 11:45:47 +0100
Subject: [PATCH 0912/1334] drm/xe: Move DSB l2 flush to a more sensible place
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Flushing l2 is only needed after all data has been written.

Fixes: 01570b446939 ("drm/xe/bmg: implement Wa_16023588340")
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Cc: Matthew Auld <matthew.auld@intel.com>
Cc: stable@vger.kernel.org # v6.12+
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Signed-off-by: Matthew Auld <matthew.auld@intel.com>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://lore.kernel.org/r/20250606104546.1996818-3-matthew.auld@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
(cherry picked from commit 0dd2dd0182bc444a62652e89d08c7f0e4fde15ba)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
---
 drivers/gpu/drm/xe/display/xe_dsb_buffer.c | 11 ++++-------
 1 file changed, 4 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/xe/display/xe_dsb_buffer.c b/drivers/gpu/drm/xe/display/xe_dsb_buffer.c
index f95375451e2f..9f941fc2e36b 100644
--- a/drivers/gpu/drm/xe/display/xe_dsb_buffer.c
+++ b/drivers/gpu/drm/xe/display/xe_dsb_buffer.c
@@ -17,10 +17,7 @@ u32 intel_dsb_buffer_ggtt_offset(struct intel_dsb_buffer *dsb_buf)
 
 void intel_dsb_buffer_write(struct intel_dsb_buffer *dsb_buf, u32 idx, u32 val)
 {
-	struct xe_device *xe = dsb_buf->vma->bo->tile->xe;
-
 	iosys_map_wr(&dsb_buf->vma->bo->vmap, idx * 4, u32, val);
-	xe_device_l2_flush(xe);
 }
 
 u32 intel_dsb_buffer_read(struct intel_dsb_buffer *dsb_buf, u32 idx)
@@ -30,12 +27,9 @@ u32 intel_dsb_buffer_read(struct intel_dsb_buffer *dsb_buf, u32 idx)
 
 void intel_dsb_buffer_memset(struct intel_dsb_buffer *dsb_buf, u32 idx, u32 val, size_t size)
 {
-	struct xe_device *xe = dsb_buf->vma->bo->tile->xe;
-
 	WARN_ON(idx > (dsb_buf->buf_size - size) / sizeof(*dsb_buf->cmd_buf));
 
 	iosys_map_memset(&dsb_buf->vma->bo->vmap, idx * 4, val, size);
-	xe_device_l2_flush(xe);
 }
 
 bool intel_dsb_buffer_create(struct intel_crtc *crtc, struct intel_dsb_buffer *dsb_buf, size_t size)
@@ -74,9 +68,12 @@ void intel_dsb_buffer_cleanup(struct intel_dsb_buffer *dsb_buf)
 
 void intel_dsb_buffer_flush_map(struct intel_dsb_buffer *dsb_buf)
 {
+	struct xe_device *xe = dsb_buf->vma->bo->tile->xe;
+
 	/*
 	 * The memory barrier here is to ensure coherency of DSB vs MMIO,
 	 * both for weak ordering archs and discrete cards.
 	 */
-	xe_device_wmb(dsb_buf->vma->bo->tile->xe);
+	xe_device_wmb(xe);
+	xe_device_l2_flush(xe);
 }

From f16873f42a06b620669d48a4b5c3f888cb3653a1 Mon Sep 17 00:00:00 2001
From: Matthew Auld <matthew.auld@intel.com>
Date: Fri, 6 Jun 2025 11:45:48 +0100
Subject: [PATCH 0913/1334] drm/xe: move DPT l2 flush to a more sensible place
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Only need the flush for DPT host updates here. Normal GGTT updates don't
need special flush.

Fixes: 01570b446939 ("drm/xe/bmg: implement Wa_16023588340")
Signed-off-by: Matthew Auld <matthew.auld@intel.com>
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Cc: stable@vger.kernel.org # v6.12+
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://lore.kernel.org/r/20250606104546.1996818-4-matthew.auld@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
(cherry picked from commit 35db1da40c8cfd7511dc42f342a133601eb45449)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
---
 drivers/gpu/drm/xe/display/xe_fb_pin.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/xe/display/xe_fb_pin.c b/drivers/gpu/drm/xe/display/xe_fb_pin.c
index d918ae1c8061..55259969480b 100644
--- a/drivers/gpu/drm/xe/display/xe_fb_pin.c
+++ b/drivers/gpu/drm/xe/display/xe_fb_pin.c
@@ -164,6 +164,9 @@ static int __xe_pin_fb_vma_dpt(const struct intel_framebuffer *fb,
 
 	vma->dpt = dpt;
 	vma->node = dpt->ggtt_node[tile0->id];
+
+	/* Ensure DPT writes are flushed */
+	xe_device_l2_flush(xe);
 	return 0;
 }
 
@@ -333,8 +336,6 @@ static struct i915_vma *__xe_pin_fb_vma(const struct intel_framebuffer *fb,
 	if (ret)
 		goto err_unpin;
 
-	/* Ensure DPT writes are flushed */
-	xe_device_l2_flush(xe);
 	return vma;
 
 err_unpin:

From ad40098da5c3b43114d860a5b5740e7204158534 Mon Sep 17 00:00:00 2001
From: Michal Wajdeczko <michal.wajdeczko@intel.com>
Date: Fri, 13 Jun 2025 00:09:37 +0200
Subject: [PATCH 0914/1334] drm/xe/guc: Explicitly exit CT safe mode on unwind
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

During driver probe we might be briefly using CT safe mode, which
is based on a delayed work, but usually we are able to stop this
once we have IRQ fully operational.  However, if we abort the probe
quite early then during unwind we might try to destroy the workqueue
while there is still a pending delayed work that attempts to restart
itself which triggers a WARN.

This was recently observed during unsuccessful VF initialization:

 [ ] xe 0000:00:02.1: probe with driver xe failed with error -62
 [ ] ------------[ cut here ]------------
 [ ] workqueue: cannot queue safe_mode_worker_func [xe] on wq xe-g2h-wq
 [ ] WARNING: CPU: 9 PID: 0 at kernel/workqueue.c:2257 __queue_work+0x287/0x710
 [ ] RIP: 0010:__queue_work+0x287/0x710
 [ ] Call Trace:
 [ ]  delayed_work_timer_fn+0x19/0x30
 [ ]  call_timer_fn+0xa1/0x2a0

Exit the CT safe mode on unwind to avoid that warning.

Fixes: 09b286950f29 ("drm/xe/guc: Allow CTB G2H processing without G2H IRQ")
Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Link: https://lore.kernel.org/r/20250612220937.857-3-michal.wajdeczko@intel.com
(cherry picked from commit 2ddbb73ec20b98e70a5200cb85deade22ccea2ec)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
---
 drivers/gpu/drm/xe/xe_guc_ct.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_guc_ct.c b/drivers/gpu/drm/xe/xe_guc_ct.c
index d0ac48d8f4f7..bbcbb348256f 100644
--- a/drivers/gpu/drm/xe/xe_guc_ct.c
+++ b/drivers/gpu/drm/xe/xe_guc_ct.c
@@ -34,6 +34,11 @@
 #include "xe_pm.h"
 #include "xe_trace_guc.h"
 
+static void receive_g2h(struct xe_guc_ct *ct);
+static void g2h_worker_func(struct work_struct *w);
+static void safe_mode_worker_func(struct work_struct *w);
+static void ct_exit_safe_mode(struct xe_guc_ct *ct);
+
 #if IS_ENABLED(CONFIG_DRM_XE_DEBUG)
 enum {
 	/* Internal states, not error conditions */
@@ -186,14 +191,11 @@ static void guc_ct_fini(struct drm_device *drm, void *arg)
 {
 	struct xe_guc_ct *ct = arg;
 
+	ct_exit_safe_mode(ct);
 	destroy_workqueue(ct->g2h_wq);
 	xa_destroy(&ct->fence_lookup);
 }
 
-static void receive_g2h(struct xe_guc_ct *ct);
-static void g2h_worker_func(struct work_struct *w);
-static void safe_mode_worker_func(struct work_struct *w);
-
 static void primelockdep(struct xe_guc_ct *ct)
 {
 	if (!IS_ENABLED(CONFIG_LOCKDEP))

From af2b588abe006bd55ddd358c4c3b87523349c475 Mon Sep 17 00:00:00 2001
From: Michal Wajdeczko <michal.wajdeczko@intel.com>
Date: Fri, 13 Jun 2025 00:09:36 +0200
Subject: [PATCH 0915/1334] drm/xe: Process deferred GGTT node removals on
 device unwind
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

While we are indirectly draining our dedicated workqueue ggtt->wq
that we use to complete asynchronous removal of some GGTT nodes,
this happends as part of the managed-drm unwinding (ggtt_fini_early),
which could be later then manage-device unwinding, where we could
already unmap our MMIO/GMS mapping (mmio_fini).

This was recently observed during unsuccessful VF initialization:

 [ ] xe 0000:00:02.1: probe with driver xe failed with error -62
 [ ] xe 0000:00:02.1: DEVRES REL ffff88811e747340 __xe_bo_unpin_map_no_vm (16 bytes)
 [ ] xe 0000:00:02.1: DEVRES REL ffff88811e747540 __xe_bo_unpin_map_no_vm (16 bytes)
 [ ] xe 0000:00:02.1: DEVRES REL ffff88811e747240 __xe_bo_unpin_map_no_vm (16 bytes)
 [ ] xe 0000:00:02.1: DEVRES REL ffff88811e747040 tiles_fini (16 bytes)
 [ ] xe 0000:00:02.1: DEVRES REL ffff88811e746840 mmio_fini (16 bytes)
 [ ] xe 0000:00:02.1: DEVRES REL ffff88811e747f40 xe_bo_pinned_fini (16 bytes)
 [ ] xe 0000:00:02.1: DEVRES REL ffff88811e746b40 devm_drm_dev_init_release (16 bytes)
 [ ] xe 0000:00:02.1: [drm:drm_managed_release] drmres release begin
 [ ] xe 0000:00:02.1: [drm:drm_managed_release] REL ffff88810ef81640 __fini_relay (8 bytes)
 [ ] xe 0000:00:02.1: [drm:drm_managed_release] REL ffff88810ef80d40 guc_ct_fini (8 bytes)
 [ ] xe 0000:00:02.1: [drm:drm_managed_release] REL ffff88810ef80040 __drmm_mutex_release (8 bytes)
 [ ] xe 0000:00:02.1: [drm:drm_managed_release] REL ffff88810ef80140 ggtt_fini_early (8 bytes)

and this was leading to:

 [ ] BUG: unable to handle page fault for address: ffffc900058162a0
 [ ] #PF: supervisor write access in kernel mode
 [ ] #PF: error_code(0x0002) - not-present page
 [ ] Oops: Oops: 0002 [#1] SMP NOPTI
 [ ] Tainted: [W]=WARN
 [ ] Workqueue: xe-ggtt-wq ggtt_node_remove_work_func [xe]
 [ ] RIP: 0010:xe_ggtt_set_pte+0x6d/0x350 [xe]
 [ ] Call Trace:
 [ ]  <TASK>
 [ ]  xe_ggtt_clear+0xb0/0x270 [xe]
 [ ]  ggtt_node_remove+0xbb/0x120 [xe]
 [ ]  ggtt_node_remove_work_func+0x30/0x50 [xe]
 [ ]  process_one_work+0x22b/0x6f0
 [ ]  worker_thread+0x1e8/0x3d

Add managed-device action that will explicitly drain the workqueue
with all pending node removals prior to releasing MMIO/GSM mapping.

Fixes: 919bb54e989c ("drm/xe: Fix missing runtime outer protection for ggtt_remove_node")
Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: Lucas De Marchi <lucas.demarchi@intel.com>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://lore.kernel.org/r/20250612220937.857-2-michal.wajdeczko@intel.com
(cherry picked from commit 89d2835c3680ab1938e22ad81b1c9f8c686bd391)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
---
 drivers/gpu/drm/xe/xe_ggtt.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/drivers/gpu/drm/xe/xe_ggtt.c b/drivers/gpu/drm/xe/xe_ggtt.c
index 7062115909f2..2c799958c1e4 100644
--- a/drivers/gpu/drm/xe/xe_ggtt.c
+++ b/drivers/gpu/drm/xe/xe_ggtt.c
@@ -201,6 +201,13 @@ static const struct xe_ggtt_pt_ops xelpg_pt_wa_ops = {
 	.ggtt_set_pte = xe_ggtt_set_pte_and_flush,
 };
 
+static void dev_fini_ggtt(void *arg)
+{
+	struct xe_ggtt *ggtt = arg;
+
+	drain_workqueue(ggtt->wq);
+}
+
 /**
  * xe_ggtt_init_early - Early GGTT initialization
  * @ggtt: the &xe_ggtt to be initialized
@@ -257,6 +264,10 @@ int xe_ggtt_init_early(struct xe_ggtt *ggtt)
 	if (err)
 		return err;
 
+	err = devm_add_action_or_reset(xe->drm.dev, dev_fini_ggtt, ggtt);
+	if (err)
+		return err;
+
 	if (IS_SRIOV_VF(xe)) {
 		err = xe_gt_sriov_vf_prepare_ggtt(xe_tile_get_gt(ggtt->tile, 0));
 		if (err)

From 969127bf0783a4ac0c8a27e633a9e8ea1738583f Mon Sep 17 00:00:00 2001
From: Ronnie Sahlberg <rsahlberg@whamcloud.com>
Date: Thu, 26 Jun 2025 12:20:45 +1000
Subject: [PATCH 0916/1334] ublk: sanity check add_dev input for underflow

Add additional checks that queue depth and number of queues are
non-zero.

Signed-off-by: Ronnie Sahlberg <rsahlberg@whamcloud.com>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/20250626022046.235018-1-ronniesahlberg@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/ublk_drv.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c
index d441d3259edb..c3e3c3b65a6d 100644
--- a/drivers/block/ublk_drv.c
+++ b/drivers/block/ublk_drv.c
@@ -2849,7 +2849,8 @@ static int ublk_ctrl_add_dev(const struct ublksrv_ctrl_cmd *header)
 	if (copy_from_user(&info, argp, sizeof(info)))
 		return -EFAULT;
 
-	if (info.queue_depth > UBLK_MAX_QUEUE_DEPTH || info.nr_hw_queues > UBLK_MAX_NR_QUEUES)
+	if (info.queue_depth > UBLK_MAX_QUEUE_DEPTH || !info.queue_depth ||
+	    info.nr_hw_queues > UBLK_MAX_NR_QUEUES || !info.nr_hw_queues)
 		return -EINVAL;
 
 	if (capable(CAP_SYS_ADMIN))

From c007062188d8e402c294117db53a24b2bed2b83f Mon Sep 17 00:00:00 2001
From: Yu Kuai <yukuai3@huawei.com>
Date: Thu, 26 Jun 2025 19:57:43 +0800
Subject: [PATCH 0917/1334] block: fix false warning in
 bdev_count_inflight_rw()

While bdev_count_inflight is interating all cpus, if some IOs are issued
from traversed cpu and then completed from the cpu that is not traversed
yet:

cpu0
		cpu1
		bdev_count_inflight
		 //for_each_possible_cpu
		 // cpu0 is 0
		 infliht += 0
// issue a io
blk_account_io_start
// cpu0 inflight ++

				cpu2
				// the io is done
				blk_account_io_done
				// cpu2 inflight --
		 // cpu 1 is 0
		 inflight += 0
		 // cpu2 is -1
		 inflight += -1
		 ...

In this case, the total inflight will be -1, causing lots of false
warning. Fix the problem by removing the warning.

Noted there is still a valid warning for nvme-mpath(From Yi) that is not
fixed yet.

Fixes: f5482ee5edb9 ("block: WARN if bdev inflight counter is negative")
Reported-by: Yi Zhang <yi.zhang@redhat.com>
Closes: https://lore.kernel.org/linux-block/aFtUXy-lct0WxY2w@mozart.vkv.me/T/#mae89155a5006463d0a21a4a2c35ae0034b26a339
Reported-and-tested-by: Calvin Owens <calvin@wbinvd.org>
Closes: https://lore.kernel.org/linux-block/aFtUXy-lct0WxY2w@mozart.vkv.me/T/#m1d935a00070bf95055d0ac84e6075158b08acaef
Reported-by: Dave Chinner <david@fromorbit.com>
Closes: https://lore.kernel.org/linux-block/aFuypjqCXo9-5_En@dread.disaster.area/
Signed-off-by: Yu Kuai <yukuai3@huawei.com>
Link: https://lore.kernel.org/r/20250626115743.1641443-1-yukuai3@huawei.com
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/genhd.c | 26 +++++++++++++++-----------
 1 file changed, 15 insertions(+), 11 deletions(-)

diff --git a/block/genhd.c b/block/genhd.c
index 8171a6bc3210..c26733f6324b 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -128,23 +128,27 @@ static void part_stat_read_all(struct block_device *part,
 static void bdev_count_inflight_rw(struct block_device *part,
 		unsigned int inflight[2], bool mq_driver)
 {
+	int write = 0;
+	int read = 0;
 	int cpu;
 
 	if (mq_driver) {
 		blk_mq_in_driver_rw(part, inflight);
-	} else {
-		for_each_possible_cpu(cpu) {
-			inflight[READ] += part_stat_local_read_cpu(
-						part, in_flight[READ], cpu);
-			inflight[WRITE] += part_stat_local_read_cpu(
-						part, in_flight[WRITE], cpu);
-		}
+		return;
 	}
 
-	if (WARN_ON_ONCE((int)inflight[READ] < 0))
-		inflight[READ] = 0;
-	if (WARN_ON_ONCE((int)inflight[WRITE] < 0))
-		inflight[WRITE] = 0;
+	for_each_possible_cpu(cpu) {
+		read += part_stat_local_read_cpu(part, in_flight[READ], cpu);
+		write += part_stat_local_read_cpu(part, in_flight[WRITE], cpu);
+	}
+
+	/*
+	 * While iterating all CPUs, some IOs may be issued from a CPU already
+	 * traversed and complete on a CPU that has not yet been traversed,
+	 * causing the inflight number to be negative.
+	 */
+	inflight[READ] = read > 0 ? read : 0;
+	inflight[WRITE] = write > 0 ? write : 0;
 }
 
 /**

From c3ac7e30309b8221a8321c3882d289ba519b4104 Mon Sep 17 00:00:00 2001
From: Alok Tiwari <alok.a.tiwari@oracle.com>
Date: Sun, 22 Jun 2025 00:29:11 -0700
Subject: [PATCH 0918/1334] platform/mellanox: Fix spelling and comment clarity
 in Mellanox drivers
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This commit corrects several minor typographical errors in comments
and error messages across multiple Mellanox platform driver.
Fixed spelling of "thresholds", "region", "platform", "default",
and removed redundant spaces in comment strings and error logs.

These changes are cosmetic and do not affect runtime behavior.

Signed-off-by: Alok Tiwari <alok.a.tiwari@oracle.com>
Reviewed-by: Vadim Pasternak <vadimp@nvidia.com>
Reviewed-by: David Thompson <davthompson@nvidia.com>
Link: https://lore.kernel.org/r/20250622072921.4111552-1-alok.a.tiwari@oracle.com
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/mellanox/mlxbf-tmfifo.c |  2 +-
 drivers/platform/mellanox/mlxreg-dpu.c   |  2 +-
 drivers/platform/mellanox/mlxreg-lc.c    | 10 +++++-----
 3 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/platform/mellanox/mlxbf-tmfifo.c b/drivers/platform/mellanox/mlxbf-tmfifo.c
index 70c58c4c6c84..14aa87b39be5 100644
--- a/drivers/platform/mellanox/mlxbf-tmfifo.c
+++ b/drivers/platform/mellanox/mlxbf-tmfifo.c
@@ -1288,7 +1288,7 @@ static void mlxbf_tmfifo_get_cfg_mac(u8 *mac)
 		ether_addr_copy(mac, mlxbf_tmfifo_net_default_mac);
 }
 
-/* Set TmFifo thresolds which is used to trigger interrupts. */
+/* Set TmFifo thresholds which is used to trigger interrupts. */
 static void mlxbf_tmfifo_set_threshold(struct mlxbf_tmfifo *fifo)
 {
 	u64 ctl;
diff --git a/drivers/platform/mellanox/mlxreg-dpu.c b/drivers/platform/mellanox/mlxreg-dpu.c
index 52260106a9f1..39f89c47144a 100644
--- a/drivers/platform/mellanox/mlxreg-dpu.c
+++ b/drivers/platform/mellanox/mlxreg-dpu.c
@@ -483,7 +483,7 @@ static int mlxreg_dpu_config_init(struct mlxreg_dpu *mlxreg_dpu, void *regmap,
 							  mlxreg_dpu->io_data,
 							  sizeof(*mlxreg_dpu->io_data));
 		if (IS_ERR(mlxreg_dpu->io_regs)) {
-			dev_err(dev, "Failed to create regio for client %s at bus %d at addr 0x%02x\n",
+			dev_err(dev, "Failed to create region for client %s at bus %d at addr 0x%02x\n",
 				data->hpdev.brdinfo->type, data->hpdev.nr,
 				data->hpdev.brdinfo->addr);
 			return PTR_ERR(mlxreg_dpu->io_regs);
diff --git a/drivers/platform/mellanox/mlxreg-lc.c b/drivers/platform/mellanox/mlxreg-lc.c
index aee395bb48ae..8eef3d990d1a 100644
--- a/drivers/platform/mellanox/mlxreg-lc.c
+++ b/drivers/platform/mellanox/mlxreg-lc.c
@@ -57,9 +57,9 @@ enum mlxreg_lc_state {
  * @dev: platform device;
  * @lock: line card lock;
  * @par_regmap: parent device regmap handle;
- * @data: pltaform core data;
+ * @data: platform core data;
  * @io_data: register access platform data;
- * @led_data: LED platform data ;
+ * @led_data: LED platform data;
  * @mux_data: MUX platform data;
  * @led: LED device;
  * @io_regs: register access device;
@@ -171,7 +171,7 @@ static int mlxreg_lc_chan[] = {
 	0x4e, 0x4f
 };
 
-/* Defaul mux configuration. */
+/* Default mux configuration. */
 static struct mlxcpld_mux_plat_data mlxreg_lc_mux_data[] = {
 	{
 		.chan_ids = mlxreg_lc_chan,
@@ -181,7 +181,7 @@ static struct mlxcpld_mux_plat_data mlxreg_lc_mux_data[] = {
 	},
 };
 
-/* Defaul mux board info. */
+/* Default mux board info. */
 static struct i2c_board_info mlxreg_lc_mux_brdinfo = {
 	I2C_BOARD_INFO("i2c-mux-mlxcpld", 0x32),
 };
@@ -758,7 +758,7 @@ mlxreg_lc_config_init(struct mlxreg_lc *mlxreg_lc, void *regmap,
 		platform_device_register_resndata(dev, "mlxreg-io", data->hpdev.nr, NULL, 0,
 						  mlxreg_lc->io_data, sizeof(*mlxreg_lc->io_data));
 		if (IS_ERR(mlxreg_lc->io_regs)) {
-			dev_err(dev, "Failed to create regio for client %s at bus %d at addr 0x%02x\n",
+			dev_err(dev, "Failed to create region for client %s at bus %d at addr 0x%02x\n",
 				data->hpdev.brdinfo->type, data->hpdev.nr,
 				data->hpdev.brdinfo->addr);
 			err = PTR_ERR(mlxreg_lc->io_regs);

From d07143b507c51c04c091081627c5a130e9d3c517 Mon Sep 17 00:00:00 2001
From: Alok Tiwari <alok.a.tiwari@oracle.com>
Date: Sun, 22 Jun 2025 00:29:12 -0700
Subject: [PATCH 0919/1334] platform/mellanox: nvsw-sn2201: Fix bus number in
 adapter error message
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

change error log to use correct bus number from main_mux_devs
instead of cpld_devs.

Fixes: 662f24826f95 ("platform/mellanox: Add support for new SN2201 system")
Signed-off-by: Alok Tiwari <alok.a.tiwari@oracle.com>
Reviewed-by: Vadim Pasternak <vadimp@nvidia.com>
Link: https://lore.kernel.org/r/20250622072921.4111552-2-alok.a.tiwari@oracle.com
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/mellanox/nvsw-sn2201.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/platform/mellanox/nvsw-sn2201.c b/drivers/platform/mellanox/nvsw-sn2201.c
index db31c8bf2255..51504113c17e 100644
--- a/drivers/platform/mellanox/nvsw-sn2201.c
+++ b/drivers/platform/mellanox/nvsw-sn2201.c
@@ -1181,7 +1181,7 @@ static int nvsw_sn2201_i2c_completion_notify(void *handle, int id)
 	if (!nvsw_sn2201->main_mux_devs->adapter) {
 		err = -ENODEV;
 		dev_err(nvsw_sn2201->dev, "Failed to get adapter for bus %d\n",
-			nvsw_sn2201->cpld_devs->nr);
+			nvsw_sn2201->main_mux_devs->nr);
 		goto i2c_get_adapter_main_fail;
 	}
 

From a49e1e2e785fb3621f2d748581881b23a364998a Mon Sep 17 00:00:00 2001
From: Mathias Nyman <mathias.nyman@linux.intel.com>
Date: Thu, 26 Jun 2025 16:01:02 +0300
Subject: [PATCH 0920/1334] usb: hub: Fix flushing and scheduling of delayed
 work that tunes runtime pm

Delayed work to prevent USB3 hubs from runtime-suspending immediately
after resume was added in commit 8f5b7e2bec1c ("usb: hub: fix detection
of high tier USB3 devices behind suspended hubs").

This delayed work needs be flushed if system suspends, or hub needs to
be quiesced for other reasons right after resume. Not flushing it
triggered issues on QC SC8280XP CRD board during suspend/resume testing.

Fix it by flushing the delayed resume work in hub_quiesce()

The delayed work item that allow hub runtime suspend is also scheduled
just before calling autopm get. Alan pointed out there is a small risk
that work is run before autopm get, which would call autopm put before
get, and mess up the runtime pm usage order.
Swap the order of work sheduling and calling autopm get to solve this.

Cc: stable <stable@kernel.org>
Fixes: 8f5b7e2bec1c ("usb: hub: fix detection of high tier USB3 devices behind suspended hubs")
Reported-by: Konrad Dybcio <konrad.dybcio@oss.qualcomm.com>
Closes: https://lore.kernel.org/linux-usb/acaaa928-832c-48ca-b0ea-d202d5cd3d6c@oss.qualcomm.com
Reported-by: Alan Stern <stern@rowland.harvard.edu>
Closes: https://lore.kernel.org/linux-usb/c73fbead-66d7-497a-8fa1-75ea4761090a@rowland.harvard.edu
Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Link: https://lore.kernel.org/r/20250626130102.3639861-2-mathias.nyman@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/core/hub.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c
index 6bb6e92cb0a4..08562711dcf2 100644
--- a/drivers/usb/core/hub.c
+++ b/drivers/usb/core/hub.c
@@ -1359,11 +1359,12 @@ static void hub_activate(struct usb_hub *hub, enum hub_activation_type type)
 
 	if (type == HUB_RESUME && hub_is_superspeed(hub->hdev)) {
 		/* give usb3 downstream links training time after hub resume */
+		usb_autopm_get_interface_no_resume(
+			to_usb_interface(hub->intfdev));
+
 		INIT_DELAYED_WORK(&hub->init_work, hub_post_resume);
 		queue_delayed_work(system_power_efficient_wq, &hub->init_work,
 				   msecs_to_jiffies(USB_SS_PORT_U0_WAKE_TIME));
-		usb_autopm_get_interface_no_resume(
-			to_usb_interface(hub->intfdev));
 		return;
 	}
 
@@ -1417,6 +1418,7 @@ static void hub_quiesce(struct usb_hub *hub, enum hub_quiescing_type type)
 
 	/* Stop hub_wq and related activity */
 	timer_delete_sync(&hub->irq_urb_retry);
+	flush_delayed_work(&hub->init_work);
 	usb_kill_urb(hub->urb);
 	if (hub->has_indicators)
 		cancel_delayed_work_sync(&hub->leds);

From cf0b812500e64a7d5e2957abed38c3a97917b34f Mon Sep 17 00:00:00 2001
From: Armin Wolf <W_Armin@gmx.de>
Date: Fri, 20 Jun 2025 00:14:39 +0200
Subject: [PATCH 0921/1334] platform/x86: wmi: Fix WMI event enablement
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

It turns out that the Windows WMI-ACPI driver always enables/disables
WMI events regardless of whether they are marked as expensive or not.
This finding is further reinforced when reading the documentation of
the WMI_FUNCTION_CONTROL_CALLBACK callback used by Windows drivers
for enabling/disabling WMI devices:

	The DpWmiFunctionControl routine enables or disables
	notification of events, and enables or disables data
	collection for data blocks that the driver registered
	as expensive to collect.

Follow this behavior to fix the WMI event used for reporting hotkey
events on the Dell Latitude 5400 and likely many more devices.

Reported-by: Dmytro Bagrii <dimich.dmb@gmail.com>
Closes: https://bugzilla.kernel.org/show_bug.cgi?id=220246
Tested-by: Dmytro Bagrii <dimich.dmb@gmail.com>
Fixes: 656f0961d126 ("platform/x86: wmi: Rework WCxx/WExx ACPI method handling")
Signed-off-by: Armin Wolf <W_Armin@gmx.de>
Link: https://lore.kernel.org/r/20250619221440.6737-1-W_Armin@gmx.de
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/wmi.c | 16 +++++++++++-----
 1 file changed, 11 insertions(+), 5 deletions(-)

diff --git a/drivers/platform/x86/wmi.c b/drivers/platform/x86/wmi.c
index e46453750d5f..03aecf8bb7f8 100644
--- a/drivers/platform/x86/wmi.c
+++ b/drivers/platform/x86/wmi.c
@@ -177,16 +177,22 @@ static int wmi_device_enable(struct wmi_device *wdev, bool enable)
 	acpi_handle handle;
 	acpi_status status;
 
-	if (!(wblock->gblock.flags & ACPI_WMI_EXPENSIVE))
-		return 0;
-
 	if (wblock->dev.dev.type == &wmi_type_method)
 		return 0;
 
-	if (wblock->dev.dev.type == &wmi_type_event)
+	if (wblock->dev.dev.type == &wmi_type_event) {
+		/*
+		 * Windows always enables/disables WMI events, even when they are
+		 * not marked as being expensive. We follow this behavior for
+		 * compatibility reasons.
+		 */
 		snprintf(method, sizeof(method), "WE%02X", wblock->gblock.notify_id);
-	else
+	} else {
+		if (!(wblock->gblock.flags & ACPI_WMI_EXPENSIVE))
+			return 0;
+
 		get_acpi_method_name(wblock, 'C', method);
+	}
 
 	/*
 	 * Not all WMI devices marked as expensive actually implement the

From 50b6914fc53c718c5426fb6e9cd9484f9ae967c2 Mon Sep 17 00:00:00 2001
From: Armin Wolf <W_Armin@gmx.de>
Date: Fri, 20 Jun 2025 00:14:40 +0200
Subject: [PATCH 0922/1334] platform/x86: wmi: Update documentation of
 WCxx/WExx ACPI methods
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Inform potential firmware developers that WExx ACPI methods are
always called by the WMI driver core even if the associated WMI event
is not marked as being expensive.

Signed-off-by: Armin Wolf <W_Armin@gmx.de>
Link: https://lore.kernel.org/r/20250619221440.6737-2-W_Armin@gmx.de
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 Documentation/wmi/acpi-interface.rst | 14 +++++++++-----
 1 file changed, 9 insertions(+), 5 deletions(-)

diff --git a/Documentation/wmi/acpi-interface.rst b/Documentation/wmi/acpi-interface.rst
index f1b28835d23c..1ef003b033bf 100644
--- a/Documentation/wmi/acpi-interface.rst
+++ b/Documentation/wmi/acpi-interface.rst
@@ -36,7 +36,7 @@ Offset  Size (in bytes) Content
 
 The WMI object flags control whether the method or notification ID is used:
 
-- 0x1: Data block usage is expensive and must be explicitly enabled/disabled.
+- 0x1: Data block is expensive to collect.
 - 0x2: Data block contains WMI methods.
 - 0x4: Data block contains ASCIZ string.
 - 0x8: Data block describes a WMI event, use notification ID instead
@@ -83,14 +83,18 @@ event as hexadecimal value. Their first parameter is an integer with a value
 of 0 if the WMI event should be disabled, other values will enable
 the WMI event.
 
+Those ACPI methods are always called even for WMI events not registered as
+being expensive to collect to match the behavior of the Windows driver.
+
 WCxx ACPI methods
 -----------------
-Similar to the ``WExx`` ACPI methods, except that it controls data collection
-instead of events and thus the last two characters of the ACPI method name are
-the method ID of the data block to enable/disable.
+Similar to the ``WExx`` ACPI methods, except that instead of WMI events it controls
+data collection of data blocks registered as being expensive to collect. Thus the
+last two characters of the ACPI method name are the method ID of the data block
+to enable/disable.
 
 Those ACPI methods are also called before setting data blocks to match the
-behaviour of the Windows driver.
+behavior of the Windows driver.
 
 _WED ACPI method
 ----------------

From 4c113a5b28bfd589e2010b5fc8867578b0135ed7 Mon Sep 17 00:00:00 2001
From: Yazen Ghannam <yazen.ghannam@amd.com>
Date: Tue, 24 Jun 2025 14:15:56 +0000
Subject: [PATCH 0923/1334] x86/mce: Don't remove sysfs if thresholding sysfs
 init fails

Currently, the MCE subsystem sysfs interface will be removed if the
thresholding sysfs interface fails to be created. A common failure is due to
new MCA bank types that are not recognized and don't have a short name set.

The MCA thresholding feature is optional and should not break the common MCE
sysfs interface. Also, new MCA bank types are occasionally introduced, and
updates will be needed to recognize them. But likewise, this should not break
the common sysfs interface.

Keep the MCE sysfs interface regardless of the status of the thresholding
sysfs interface.

Signed-off-by: Yazen Ghannam <yazen.ghannam@amd.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Qiuxu Zhuo <qiuxu.zhuo@intel.com>
Reviewed-by: Tony Luck <tony.luck@intel.com>
Tested-by: Tony Luck <tony.luck@intel.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/20250624-wip-mca-updates-v4-1-236dd74f645f@amd.com
---
 arch/x86/kernel/cpu/mce/core.c | 8 +-------
 1 file changed, 1 insertion(+), 7 deletions(-)

diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index e9b3c5d4a52e..07d61937427f 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -2801,15 +2801,9 @@ static int mce_cpu_dead(unsigned int cpu)
 static int mce_cpu_online(unsigned int cpu)
 {
 	struct timer_list *t = this_cpu_ptr(&mce_timer);
-	int ret;
 
 	mce_device_create(cpu);
-
-	ret = mce_threshold_create_device(cpu);
-	if (ret) {
-		mce_device_remove(cpu);
-		return ret;
-	}
+	mce_threshold_create_device(cpu);
 	mce_reenable_cpu();
 	mce_start_timer(t);
 	return 0;

From 711741f94ac3cf9f4e3aa73aa171e76d188c0819 Mon Sep 17 00:00:00 2001
From: Paulo Alcantara <pc@manguebit.org>
Date: Wed, 25 Jun 2025 12:22:38 -0300
Subject: [PATCH 0924/1334] smb: client: fix potential deadlock when
 reconnecting channels

Fix cifs_signal_cifsd_for_reconnect() to take the correct lock order
and prevent the following deadlock from happening

======================================================
WARNING: possible circular locking dependency detected
6.16.0-rc3-build2+ #1301 Tainted: G S      W
------------------------------------------------------
cifsd/6055 is trying to acquire lock:
ffff88810ad56038 (&tcp_ses->srv_lock){+.+.}-{3:3}, at: cifs_signal_cifsd_for_reconnect+0x134/0x200

but task is already holding lock:
ffff888119c64330 (&ret_buf->chan_lock){+.+.}-{3:3}, at: cifs_signal_cifsd_for_reconnect+0xcf/0x200

which lock already depends on the new lock.

the existing dependency chain (in reverse order) is:

-> #2 (&ret_buf->chan_lock){+.+.}-{3:3}:
       validate_chain+0x1cf/0x270
       __lock_acquire+0x60e/0x780
       lock_acquire.part.0+0xb4/0x1f0
       _raw_spin_lock+0x2f/0x40
       cifs_setup_session+0x81/0x4b0
       cifs_get_smb_ses+0x771/0x900
       cifs_mount_get_session+0x7e/0x170
       cifs_mount+0x92/0x2d0
       cifs_smb3_do_mount+0x161/0x460
       smb3_get_tree+0x55/0x90
       vfs_get_tree+0x46/0x180
       do_new_mount+0x1b0/0x2e0
       path_mount+0x6ee/0x740
       do_mount+0x98/0xe0
       __do_sys_mount+0x148/0x180
       do_syscall_64+0xa4/0x260
       entry_SYSCALL_64_after_hwframe+0x76/0x7e

-> #1 (&ret_buf->ses_lock){+.+.}-{3:3}:
       validate_chain+0x1cf/0x270
       __lock_acquire+0x60e/0x780
       lock_acquire.part.0+0xb4/0x1f0
       _raw_spin_lock+0x2f/0x40
       cifs_match_super+0x101/0x320
       sget+0xab/0x270
       cifs_smb3_do_mount+0x1e0/0x460
       smb3_get_tree+0x55/0x90
       vfs_get_tree+0x46/0x180
       do_new_mount+0x1b0/0x2e0
       path_mount+0x6ee/0x740
       do_mount+0x98/0xe0
       __do_sys_mount+0x148/0x180
       do_syscall_64+0xa4/0x260
       entry_SYSCALL_64_after_hwframe+0x76/0x7e

-> #0 (&tcp_ses->srv_lock){+.+.}-{3:3}:
       check_noncircular+0x95/0xc0
       check_prev_add+0x115/0x2f0
       validate_chain+0x1cf/0x270
       __lock_acquire+0x60e/0x780
       lock_acquire.part.0+0xb4/0x1f0
       _raw_spin_lock+0x2f/0x40
       cifs_signal_cifsd_for_reconnect+0x134/0x200
       __cifs_reconnect+0x8f/0x500
       cifs_handle_standard+0x112/0x280
       cifs_demultiplex_thread+0x64d/0xbc0
       kthread+0x2f7/0x310
       ret_from_fork+0x2a/0x230
       ret_from_fork_asm+0x1a/0x30

other info that might help us debug this:

Chain exists of:
  &tcp_ses->srv_lock --> &ret_buf->ses_lock --> &ret_buf->chan_lock

 Possible unsafe locking scenario:

       CPU0                    CPU1
       ----                    ----
  lock(&ret_buf->chan_lock);
                               lock(&ret_buf->ses_lock);
                               lock(&ret_buf->chan_lock);
  lock(&tcp_ses->srv_lock);

 *** DEADLOCK ***

3 locks held by cifsd/6055:
 #0: ffffffff857de398 (&cifs_tcp_ses_lock){+.+.}-{3:3}, at: cifs_signal_cifsd_for_reconnect+0x7b/0x200
 #1: ffff888119c64060 (&ret_buf->ses_lock){+.+.}-{3:3}, at: cifs_signal_cifsd_for_reconnect+0x9c/0x200
 #2: ffff888119c64330 (&ret_buf->chan_lock){+.+.}-{3:3}, at: cifs_signal_cifsd_for_reconnect+0xcf/0x200

Cc: linux-cifs@vger.kernel.org
Reported-by: David Howells <dhowells@redhat.com>
Fixes: d7d7a66aacd6 ("cifs: avoid use of global locks for high contention data")
Reviewed-by: David Howells <dhowells@redhat.com>
Tested-by: David Howells <dhowells@redhat.com>
Signed-off-by: Paulo Alcantara (Red Hat) <pc@manguebit.org>
Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/cifsglob.h |  1 +
 fs/smb/client/connect.c  | 58 +++++++++++++++++++++++++---------------
 2 files changed, 37 insertions(+), 22 deletions(-)

diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h
index 45e94e18f4d5..318a8405d475 100644
--- a/fs/smb/client/cifsglob.h
+++ b/fs/smb/client/cifsglob.h
@@ -709,6 +709,7 @@ inc_rfc1001_len(void *buf, int count)
 struct TCP_Server_Info {
 	struct list_head tcp_ses_list;
 	struct list_head smb_ses_list;
+	struct list_head rlist; /* reconnect list */
 	spinlock_t srv_lock;  /* protect anything here that is not protected */
 	__u64 conn_id; /* connection identifier (useful for debugging) */
 	int srv_count; /* reference counter */
diff --git a/fs/smb/client/connect.c b/fs/smb/client/connect.c
index c48869c29e15..685c65dcb8c4 100644
--- a/fs/smb/client/connect.c
+++ b/fs/smb/client/connect.c
@@ -124,6 +124,14 @@ static void smb2_query_server_interfaces(struct work_struct *work)
 			   (SMB_INTERFACE_POLL_INTERVAL * HZ));
 }
 
+#define set_need_reco(server) \
+do { \
+	spin_lock(&server->srv_lock); \
+	if (server->tcpStatus != CifsExiting) \
+		server->tcpStatus = CifsNeedReconnect; \
+	spin_unlock(&server->srv_lock); \
+} while (0)
+
 /*
  * Update the tcpStatus for the server.
  * This is used to signal the cifsd thread to call cifs_reconnect
@@ -137,39 +145,45 @@ void
 cifs_signal_cifsd_for_reconnect(struct TCP_Server_Info *server,
 				bool all_channels)
 {
-	struct TCP_Server_Info *pserver;
+	struct TCP_Server_Info *nserver;
 	struct cifs_ses *ses;
+	LIST_HEAD(reco);
 	int i;
 
-	/* If server is a channel, select the primary channel */
-	pserver = SERVER_IS_CHAN(server) ? server->primary_server : server;
-
 	/* if we need to signal just this channel */
 	if (!all_channels) {
-		spin_lock(&server->srv_lock);
-		if (server->tcpStatus != CifsExiting)
-			server->tcpStatus = CifsNeedReconnect;
-		spin_unlock(&server->srv_lock);
+		set_need_reco(server);
 		return;
 	}
 
-	spin_lock(&cifs_tcp_ses_lock);
-	list_for_each_entry(ses, &pserver->smb_ses_list, smb_ses_list) {
-		if (cifs_ses_exiting(ses))
-			continue;
-		spin_lock(&ses->chan_lock);
-		for (i = 0; i < ses->chan_count; i++) {
-			if (!ses->chans[i].server)
+	if (SERVER_IS_CHAN(server))
+		server = server->primary_server;
+	scoped_guard(spinlock, &cifs_tcp_ses_lock) {
+		set_need_reco(server);
+		list_for_each_entry(ses, &server->smb_ses_list, smb_ses_list) {
+			spin_lock(&ses->ses_lock);
+			if (ses->ses_status == SES_EXITING) {
+				spin_unlock(&ses->ses_lock);
 				continue;
-
-			spin_lock(&ses->chans[i].server->srv_lock);
-			if (ses->chans[i].server->tcpStatus != CifsExiting)
-				ses->chans[i].server->tcpStatus = CifsNeedReconnect;
-			spin_unlock(&ses->chans[i].server->srv_lock);
+			}
+			spin_lock(&ses->chan_lock);
+			for (i = 1; i < ses->chan_count; i++) {
+				nserver = ses->chans[i].server;
+				if (!nserver)
+					continue;
+				nserver->srv_count++;
+				list_add(&nserver->rlist, &reco);
+			}
+			spin_unlock(&ses->chan_lock);
+			spin_unlock(&ses->ses_lock);
 		}
-		spin_unlock(&ses->chan_lock);
 	}
-	spin_unlock(&cifs_tcp_ses_lock);
+
+	list_for_each_entry_safe(server, nserver, &reco, rlist) {
+		list_del_init(&server->rlist);
+		set_need_reco(server);
+		cifs_put_tcp_session(server, 0);
+	}
 }
 
 /*

From 43e7e284fc77b710d899569360ea46fa3374ae22 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Wed, 25 Jun 2025 14:15:04 +0100
Subject: [PATCH 0925/1334] cifs: Fix the smbd_response slab to allow usercopy

The handling of received data in the smbdirect client code involves using
copy_to_iter() to copy data from the smbd_reponse struct's packet trailer
to a folioq buffer provided by netfslib that encapsulates a chunk of
pagecache.

If, however, CONFIG_HARDENED_USERCOPY=y, this will result in the checks
then performed in copy_to_iter() oopsing with something like the following:

 CIFS: Attempting to mount //172.31.9.1/test
 CIFS: VFS: RDMA transport established
 usercopy: Kernel memory exposure attempt detected from SLUB object 'smbd_response_0000000091e24ea1' (offset 81, size 63)!
 ------------[ cut here ]------------
 kernel BUG at mm/usercopy.c:102!
 ...
 RIP: 0010:usercopy_abort+0x6c/0x80
 ...
 Call Trace:
  <TASK>
  __check_heap_object+0xe3/0x120
  __check_object_size+0x4dc/0x6d0
  smbd_recv+0x77f/0xfe0 [cifs]
  cifs_readv_from_socket+0x276/0x8f0 [cifs]
  cifs_read_from_socket+0xcd/0x120 [cifs]
  cifs_demultiplex_thread+0x7e9/0x2d50 [cifs]
  kthread+0x396/0x830
  ret_from_fork+0x2b8/0x3b0
  ret_from_fork_asm+0x1a/0x30

The problem is that the smbd_response slab's packet field isn't marked as
being permitted for usercopy.

Fix this by passing parameters to kmem_slab_create() to indicate that
copy_to_iter() is permitted from the packet region of the smbd_response
slab objects, less the header space.

Fixes: ee4cdf7ba857 ("netfs: Speed up buffered reading")
Reported-by: Stefan Metzmacher <metze@samba.org>
Link: https://lore.kernel.org/r/acb7f612-df26-4e2a-a35d-7cd040f513e1@samba.org/
Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Stefan Metzmacher <metze@samba.org>
Tested-by: Stefan Metzmacher <metze@samba.org>
cc: Paulo Alcantara <pc@manguebit.com>
cc: linux-cifs@vger.kernel.org
cc: netfs@lists.linux.dev
cc: linux-fsdevel@vger.kernel.org
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/smbdirect.c | 18 +++++++++++++-----
 1 file changed, 13 insertions(+), 5 deletions(-)

diff --git a/fs/smb/client/smbdirect.c b/fs/smb/client/smbdirect.c
index a976bcf61226..0a9fd6c399f6 100644
--- a/fs/smb/client/smbdirect.c
+++ b/fs/smb/client/smbdirect.c
@@ -1475,6 +1475,9 @@ static int allocate_caches_and_workqueue(struct smbd_connection *info)
 	char name[MAX_NAME_LEN];
 	int rc;
 
+	if (WARN_ON_ONCE(sp->max_recv_size < sizeof(struct smbdirect_data_transfer)))
+		return -ENOMEM;
+
 	scnprintf(name, MAX_NAME_LEN, "smbd_request_%p", info);
 	info->request_cache =
 		kmem_cache_create(
@@ -1492,12 +1495,17 @@ static int allocate_caches_and_workqueue(struct smbd_connection *info)
 		goto out1;
 
 	scnprintf(name, MAX_NAME_LEN, "smbd_response_%p", info);
+
+	struct kmem_cache_args response_args = {
+		.align		= __alignof__(struct smbd_response),
+		.useroffset	= (offsetof(struct smbd_response, packet) +
+				   sizeof(struct smbdirect_data_transfer)),
+		.usersize	= sp->max_recv_size - sizeof(struct smbdirect_data_transfer),
+	};
 	info->response_cache =
-		kmem_cache_create(
-			name,
-			sizeof(struct smbd_response) +
-				sp->max_recv_size,
-			0, SLAB_HWCACHE_ALIGN, NULL);
+		kmem_cache_create(name,
+				  sizeof(struct smbd_response) + sp->max_recv_size,
+				  &response_args, SLAB_HWCACHE_ALIGN);
 	if (!info->response_cache)
 		goto out2;
 

From 263debecb4aa7cec0a86487e6f409814f6194a21 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Wed, 2 Apr 2025 20:27:26 +0100
Subject: [PATCH 0926/1334] cifs: Fix reading into an ITER_FOLIOQ from the
 smbdirect code

When performing a file read from RDMA, smbd_recv() prints an "Invalid msg
type 4" error and fails the I/O.  This is due to the switch-statement there
not handling the ITER_FOLIOQ handed down from netfslib.

Fix this by collapsing smbd_recv_buf() and smbd_recv_page() into
smbd_recv() and just using copy_to_iter() instead of memcpy().  This
future-proofs the function too, in case more ITER_* types are added.

Fixes: ee4cdf7ba857 ("netfs: Speed up buffered reading")
Reported-by: Stefan Metzmacher <metze@samba.org>
Signed-off-by: David Howells <dhowells@redhat.com>
cc: Tom Talpey <tom@talpey.com>
cc: Paulo Alcantara (Red Hat) <pc@manguebit.com>
cc: Matthew Wilcox <willy@infradead.org>
cc: linux-cifs@vger.kernel.org
cc: netfs@lists.linux.dev
cc: linux-fsdevel@vger.kernel.org
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/smbdirect.c | 112 ++++++--------------------------------
 1 file changed, 17 insertions(+), 95 deletions(-)

diff --git a/fs/smb/client/smbdirect.c b/fs/smb/client/smbdirect.c
index 0a9fd6c399f6..754e94a0e07f 100644
--- a/fs/smb/client/smbdirect.c
+++ b/fs/smb/client/smbdirect.c
@@ -1778,35 +1778,39 @@ try_again:
 }
 
 /*
- * Receive data from receive reassembly queue
+ * Receive data from the transport's receive reassembly queue
  * All the incoming data packets are placed in reassembly queue
- * buf: the buffer to read data into
+ * iter: the buffer to read data into
  * size: the length of data to read
  * return value: actual data read
- * Note: this implementation copies the data from reassebmly queue to receive
+ *
+ * Note: this implementation copies the data from reassembly queue to receive
  * buffers used by upper layer. This is not the optimal code path. A better way
  * to do it is to not have upper layer allocate its receive buffers but rather
  * borrow the buffer from reassembly queue, and return it after data is
  * consumed. But this will require more changes to upper layer code, and also
  * need to consider packet boundaries while they still being reassembled.
  */
-static int smbd_recv_buf(struct smbd_connection *info, char *buf,
-		unsigned int size)
+int smbd_recv(struct smbd_connection *info, struct msghdr *msg)
 {
 	struct smbdirect_socket *sc = &info->socket;
 	struct smbd_response *response;
 	struct smbdirect_data_transfer *data_transfer;
+	size_t size = iov_iter_count(&msg->msg_iter);
 	int to_copy, to_read, data_read, offset;
 	u32 data_length, remaining_data_length, data_offset;
 	int rc;
 
+	if (WARN_ON_ONCE(iov_iter_rw(&msg->msg_iter) == WRITE))
+		return -EINVAL; /* It's a bug in upper layer to get there */
+
 again:
 	/*
 	 * No need to hold the reassembly queue lock all the time as we are
 	 * the only one reading from the front of the queue. The transport
 	 * may add more entries to the back of the queue at the same time
 	 */
-	log_read(INFO, "size=%d info->reassembly_data_length=%d\n", size,
+	log_read(INFO, "size=%zd info->reassembly_data_length=%d\n", size,
 		info->reassembly_data_length);
 	if (info->reassembly_data_length >= size) {
 		int queue_length;
@@ -1844,7 +1848,10 @@ again:
 			if (response->first_segment && size == 4) {
 				unsigned int rfc1002_len =
 					data_length + remaining_data_length;
-				*((__be32 *)buf) = cpu_to_be32(rfc1002_len);
+				__be32 rfc1002_hdr = cpu_to_be32(rfc1002_len);
+				if (copy_to_iter(&rfc1002_hdr, sizeof(rfc1002_hdr),
+						 &msg->msg_iter) != sizeof(rfc1002_hdr))
+					return -EFAULT;
 				data_read = 4;
 				response->first_segment = false;
 				log_read(INFO, "returning rfc1002 length %d\n",
@@ -1853,10 +1860,9 @@ again:
 			}
 
 			to_copy = min_t(int, data_length - offset, to_read);
-			memcpy(
-				buf + data_read,
-				(char *)data_transfer + data_offset + offset,
-				to_copy);
+			if (copy_to_iter((char *)data_transfer + data_offset + offset,
+					 to_copy, &msg->msg_iter) != to_copy)
+				return -EFAULT;
 
 			/* move on to the next buffer? */
 			if (to_copy == data_length - offset) {
@@ -1921,90 +1927,6 @@ read_rfc1002_done:
 	goto again;
 }
 
-/*
- * Receive a page from receive reassembly queue
- * page: the page to read data into
- * to_read: the length of data to read
- * return value: actual data read
- */
-static int smbd_recv_page(struct smbd_connection *info,
-		struct page *page, unsigned int page_offset,
-		unsigned int to_read)
-{
-	struct smbdirect_socket *sc = &info->socket;
-	int ret;
-	char *to_address;
-	void *page_address;
-
-	/* make sure we have the page ready for read */
-	ret = wait_event_interruptible(
-		info->wait_reassembly_queue,
-		info->reassembly_data_length >= to_read ||
-			sc->status != SMBDIRECT_SOCKET_CONNECTED);
-	if (ret)
-		return ret;
-
-	/* now we can read from reassembly queue and not sleep */
-	page_address = kmap_atomic(page);
-	to_address = (char *) page_address + page_offset;
-
-	log_read(INFO, "reading from page=%p address=%p to_read=%d\n",
-		page, to_address, to_read);
-
-	ret = smbd_recv_buf(info, to_address, to_read);
-	kunmap_atomic(page_address);
-
-	return ret;
-}
-
-/*
- * Receive data from transport
- * msg: a msghdr point to the buffer, can be ITER_KVEC or ITER_BVEC
- * return: total bytes read, or 0. SMB Direct will not do partial read.
- */
-int smbd_recv(struct smbd_connection *info, struct msghdr *msg)
-{
-	char *buf;
-	struct page *page;
-	unsigned int to_read, page_offset;
-	int rc;
-
-	if (iov_iter_rw(&msg->msg_iter) == WRITE) {
-		/* It's a bug in upper layer to get there */
-		cifs_dbg(VFS, "Invalid msg iter dir %u\n",
-			 iov_iter_rw(&msg->msg_iter));
-		rc = -EINVAL;
-		goto out;
-	}
-
-	switch (iov_iter_type(&msg->msg_iter)) {
-	case ITER_KVEC:
-		buf = msg->msg_iter.kvec->iov_base;
-		to_read = msg->msg_iter.kvec->iov_len;
-		rc = smbd_recv_buf(info, buf, to_read);
-		break;
-
-	case ITER_BVEC:
-		page = msg->msg_iter.bvec->bv_page;
-		page_offset = msg->msg_iter.bvec->bv_offset;
-		to_read = msg->msg_iter.bvec->bv_len;
-		rc = smbd_recv_page(info, page, page_offset, to_read);
-		break;
-
-	default:
-		/* It's a bug in upper layer to get there */
-		cifs_dbg(VFS, "Invalid msg type %d\n",
-			 iov_iter_type(&msg->msg_iter));
-		rc = -EINVAL;
-	}
-
-out:
-	/* SMBDirect will read it all or nothing */
-	if (rc > 0)
-		msg->msg_iter.count = 0;
-	return rc;
-}
-
 /*
  * Send data to transport
  * Each rqst is transported as a SMBDirect payload

From 38074de35b015df5623f524d6f2b49a0cd395c40 Mon Sep 17 00:00:00 2001
From: Trond Myklebust <trond.myklebust@hammerspace.com>
Date: Thu, 19 Jun 2025 15:16:11 -0400
Subject: [PATCH 0927/1334] NFSv4/flexfiles: Fix handling of NFS level errors
 in I/O

Allow the flexfiles error handling to recognise NFS level errors (as
opposed to RPC level errors) and handle them separately. The main
motivator is the NFSERR_PERM errors that get returned if the NFS client
connects to the data server through a port number that is lower than
1024. In that case, the client should disconnect and retry a READ on a
different data server, or it should retry a WRITE after reconnecting.

Reviewed-by: Tigran Mkrtchyan <tigran.mkrtchyan@desy.de>
Fixes: d67ae825a59d ("pnfs/flexfiles: Add the FlexFile Layout Driver")
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Signed-off-by: Anna Schumaker <anna.schumaker@oracle.com>
---
 fs/nfs/flexfilelayout/flexfilelayout.c | 118 ++++++++++++++++++-------
 1 file changed, 84 insertions(+), 34 deletions(-)

diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c
index df4807460596..4bea008dbebd 100644
--- a/fs/nfs/flexfilelayout/flexfilelayout.c
+++ b/fs/nfs/flexfilelayout/flexfilelayout.c
@@ -1105,6 +1105,7 @@ static void ff_layout_reset_read(struct nfs_pgio_header *hdr)
 }
 
 static int ff_layout_async_handle_error_v4(struct rpc_task *task,
+					   u32 op_status,
 					   struct nfs4_state *state,
 					   struct nfs_client *clp,
 					   struct pnfs_layout_segment *lseg,
@@ -1115,34 +1116,42 @@ static int ff_layout_async_handle_error_v4(struct rpc_task *task,
 	struct nfs4_deviceid_node *devid = FF_LAYOUT_DEVID_NODE(lseg, idx);
 	struct nfs4_slot_table *tbl = &clp->cl_session->fc_slot_table;
 
-	switch (task->tk_status) {
-	case -NFS4ERR_BADSESSION:
-	case -NFS4ERR_BADSLOT:
-	case -NFS4ERR_BAD_HIGH_SLOT:
-	case -NFS4ERR_DEADSESSION:
-	case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION:
-	case -NFS4ERR_SEQ_FALSE_RETRY:
-	case -NFS4ERR_SEQ_MISORDERED:
+	switch (op_status) {
+	case NFS4_OK:
+	case NFS4ERR_NXIO:
+		break;
+	case NFSERR_PERM:
+		if (!task->tk_xprt)
+			break;
+		xprt_force_disconnect(task->tk_xprt);
+		goto out_retry;
+	case NFS4ERR_BADSESSION:
+	case NFS4ERR_BADSLOT:
+	case NFS4ERR_BAD_HIGH_SLOT:
+	case NFS4ERR_DEADSESSION:
+	case NFS4ERR_CONN_NOT_BOUND_TO_SESSION:
+	case NFS4ERR_SEQ_FALSE_RETRY:
+	case NFS4ERR_SEQ_MISORDERED:
 		dprintk("%s ERROR %d, Reset session. Exchangeid "
 			"flags 0x%x\n", __func__, task->tk_status,
 			clp->cl_exchange_flags);
 		nfs4_schedule_session_recovery(clp->cl_session, task->tk_status);
-		break;
-	case -NFS4ERR_DELAY:
+		goto out_retry;
+	case NFS4ERR_DELAY:
 		nfs_inc_stats(lseg->pls_layout->plh_inode, NFSIOS_DELAY);
 		fallthrough;
-	case -NFS4ERR_GRACE:
+	case NFS4ERR_GRACE:
 		rpc_delay(task, FF_LAYOUT_POLL_RETRY_MAX);
-		break;
-	case -NFS4ERR_RETRY_UNCACHED_REP:
-		break;
+		goto out_retry;
+	case NFS4ERR_RETRY_UNCACHED_REP:
+		goto out_retry;
 	/* Invalidate Layout errors */
-	case -NFS4ERR_PNFS_NO_LAYOUT:
-	case -ESTALE:           /* mapped NFS4ERR_STALE */
-	case -EBADHANDLE:       /* mapped NFS4ERR_BADHANDLE */
-	case -EISDIR:           /* mapped NFS4ERR_ISDIR */
-	case -NFS4ERR_FHEXPIRED:
-	case -NFS4ERR_WRONG_TYPE:
+	case NFS4ERR_PNFS_NO_LAYOUT:
+	case NFS4ERR_STALE:
+	case NFS4ERR_BADHANDLE:
+	case NFS4ERR_ISDIR:
+	case NFS4ERR_FHEXPIRED:
+	case NFS4ERR_WRONG_TYPE:
 		dprintk("%s Invalid layout error %d\n", __func__,
 			task->tk_status);
 		/*
@@ -1155,6 +1164,11 @@ static int ff_layout_async_handle_error_v4(struct rpc_task *task,
 		pnfs_destroy_layout(NFS_I(inode));
 		rpc_wake_up(&tbl->slot_tbl_waitq);
 		goto reset;
+	default:
+		break;
+	}
+
+	switch (task->tk_status) {
 	/* RPC connection errors */
 	case -ENETDOWN:
 	case -ENETUNREACH:
@@ -1174,27 +1188,56 @@ static int ff_layout_async_handle_error_v4(struct rpc_task *task,
 		nfs4_delete_deviceid(devid->ld, devid->nfs_client,
 				&devid->deviceid);
 		rpc_wake_up(&tbl->slot_tbl_waitq);
-		fallthrough;
+		break;
 	default:
-		if (ff_layout_avoid_mds_available_ds(lseg))
-			return -NFS4ERR_RESET_TO_PNFS;
-reset:
-		dprintk("%s Retry through MDS. Error %d\n", __func__,
-			task->tk_status);
-		return -NFS4ERR_RESET_TO_MDS;
+		break;
 	}
+
+	if (ff_layout_avoid_mds_available_ds(lseg))
+		return -NFS4ERR_RESET_TO_PNFS;
+reset:
+	dprintk("%s Retry through MDS. Error %d\n", __func__,
+		task->tk_status);
+	return -NFS4ERR_RESET_TO_MDS;
+
+out_retry:
 	task->tk_status = 0;
 	return -EAGAIN;
 }
 
 /* Retry all errors through either pNFS or MDS except for -EJUKEBOX */
 static int ff_layout_async_handle_error_v3(struct rpc_task *task,
+					   u32 op_status,
 					   struct nfs_client *clp,
 					   struct pnfs_layout_segment *lseg,
 					   u32 idx)
 {
 	struct nfs4_deviceid_node *devid = FF_LAYOUT_DEVID_NODE(lseg, idx);
 
+	switch (op_status) {
+	case NFS_OK:
+	case NFSERR_NXIO:
+		break;
+	case NFSERR_PERM:
+		if (!task->tk_xprt)
+			break;
+		xprt_force_disconnect(task->tk_xprt);
+		goto out_retry;
+	case NFSERR_ACCES:
+	case NFSERR_BADHANDLE:
+	case NFSERR_FBIG:
+	case NFSERR_IO:
+	case NFSERR_NOSPC:
+	case NFSERR_ROFS:
+	case NFSERR_STALE:
+		goto out_reset_to_pnfs;
+	case NFSERR_JUKEBOX:
+		nfs_inc_stats(lseg->pls_layout->plh_inode, NFSIOS_DELAY);
+		goto out_retry;
+	default:
+		break;
+	}
+
 	switch (task->tk_status) {
 	/* File access problems. Don't mark the device as unavailable */
 	case -EACCES:
@@ -1218,6 +1261,7 @@ static int ff_layout_async_handle_error_v3(struct rpc_task *task,
 		nfs4_delete_deviceid(devid->ld, devid->nfs_client,
 				&devid->deviceid);
 	}
+out_reset_to_pnfs:
 	/* FIXME: Need to prevent infinite looping here. */
 	return -NFS4ERR_RESET_TO_PNFS;
 out_retry:
@@ -1228,6 +1272,7 @@ out_retry:
 }
 
 static int ff_layout_async_handle_error(struct rpc_task *task,
+					u32 op_status,
 					struct nfs4_state *state,
 					struct nfs_client *clp,
 					struct pnfs_layout_segment *lseg,
@@ -1246,10 +1291,11 @@ static int ff_layout_async_handle_error(struct rpc_task *task,
 
 	switch (vers) {
 	case 3:
-		return ff_layout_async_handle_error_v3(task, clp, lseg, idx);
-	case 4:
-		return ff_layout_async_handle_error_v4(task, state, clp,
+		return ff_layout_async_handle_error_v3(task, op_status, clp,
 						       lseg, idx);
+	case 4:
+		return ff_layout_async_handle_error_v4(task, op_status, state,
+						       clp, lseg, idx);
 	default:
 		/* should never happen */
 		WARN_ON_ONCE(1);
@@ -1302,6 +1348,7 @@ static void ff_layout_io_track_ds_error(struct pnfs_layout_segment *lseg,
 	switch (status) {
 	case NFS4ERR_DELAY:
 	case NFS4ERR_GRACE:
+	case NFS4ERR_PERM:
 		break;
 	case NFS4ERR_NXIO:
 		ff_layout_mark_ds_unreachable(lseg, idx);
@@ -1334,7 +1381,8 @@ static int ff_layout_read_done_cb(struct rpc_task *task,
 		trace_ff_layout_read_error(hdr, task->tk_status);
 	}
 
-	err = ff_layout_async_handle_error(task, hdr->args.context->state,
+	err = ff_layout_async_handle_error(task, hdr->res.op_status,
+					   hdr->args.context->state,
 					   hdr->ds_clp, hdr->lseg,
 					   hdr->pgio_mirror_idx);
 
@@ -1507,7 +1555,8 @@ static int ff_layout_write_done_cb(struct rpc_task *task,
 		trace_ff_layout_write_error(hdr, task->tk_status);
 	}
 
-	err = ff_layout_async_handle_error(task, hdr->args.context->state,
+	err = ff_layout_async_handle_error(task, hdr->res.op_status,
+					   hdr->args.context->state,
 					   hdr->ds_clp, hdr->lseg,
 					   hdr->pgio_mirror_idx);
 
@@ -1556,8 +1605,9 @@ static int ff_layout_commit_done_cb(struct rpc_task *task,
 		trace_ff_layout_commit_error(data, task->tk_status);
 	}
 
-	err = ff_layout_async_handle_error(task, NULL, data->ds_clp,
-					   data->lseg, data->ds_commit_index);
+	err = ff_layout_async_handle_error(task, data->res.op_status,
+					   NULL, data->ds_clp, data->lseg,
+					   data->ds_commit_index);
 
 	trace_nfs4_pnfs_commit_ds(data, err);
 	switch (err) {

From 178b8ff66ff827c41b4fa105e9aabb99a0b5c537 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Thu, 26 Jun 2025 12:17:48 -0600
Subject: [PATCH 0928/1334] io_uring/kbuf: flag partial buffer mappings

A previous commit aborted mapping more for a non-incremental ring for
bundle peeking, but depending on where in the process this peeking
happened, it would not necessarily prevent a retry by the user. That can
create gaps in the received/read data.

Add struct buf_sel_arg->partial_map, which can pass this information
back. The networking side can then map that to internal state and use it
to gate retry as well.

Since this necessitates a new flag, change io_sr_msg->retry to a
retry_flags member, and store both the retry and partial map condition
in there.

Cc: stable@vger.kernel.org
Fixes: 26ec15e4b0c1 ("io_uring/kbuf: don't truncate end buffer for multiple buffer peeks")
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/kbuf.c |  1 +
 io_uring/kbuf.h |  3 ++-
 io_uring/net.c  | 23 +++++++++++++++--------
 3 files changed, 18 insertions(+), 9 deletions(-)

diff --git a/io_uring/kbuf.c b/io_uring/kbuf.c
index ce95e3af44a9..f2d2cc319faa 100644
--- a/io_uring/kbuf.c
+++ b/io_uring/kbuf.c
@@ -271,6 +271,7 @@ static int io_ring_buffers_peek(struct io_kiocb *req, struct buf_sel_arg *arg,
 		if (len > arg->max_len) {
 			len = arg->max_len;
 			if (!(bl->flags & IOBL_INC)) {
+				arg->partial_map = 1;
 				if (iov != arg->iovs)
 					break;
 				buf->len = len;
diff --git a/io_uring/kbuf.h b/io_uring/kbuf.h
index 5d83c7adc739..723d0361898e 100644
--- a/io_uring/kbuf.h
+++ b/io_uring/kbuf.h
@@ -58,7 +58,8 @@ struct buf_sel_arg {
 	size_t max_len;
 	unsigned short nr_iovs;
 	unsigned short mode;
-	unsigned buf_group;
+	unsigned short buf_group;
+	unsigned short partial_map;
 };
 
 void __user *io_buffer_select(struct io_kiocb *req, size_t *len,
diff --git a/io_uring/net.c b/io_uring/net.c
index 5c1e8c4ba468..43a43522f406 100644
--- a/io_uring/net.c
+++ b/io_uring/net.c
@@ -75,12 +75,17 @@ struct io_sr_msg {
 	u16				flags;
 	/* initialised and used only by !msg send variants */
 	u16				buf_group;
-	bool				retry;
+	unsigned short			retry_flags;
 	void __user			*msg_control;
 	/* used only for send zerocopy */
 	struct io_kiocb 		*notif;
 };
 
+enum sr_retry_flags {
+	IO_SR_MSG_RETRY		= 1,
+	IO_SR_MSG_PARTIAL_MAP	= 2,
+};
+
 /*
  * Number of times we'll try and do receives if there's more data. If we
  * exceed this limit, then add us to the back of the queue and retry from
@@ -187,7 +192,7 @@ static inline void io_mshot_prep_retry(struct io_kiocb *req,
 
 	req->flags &= ~REQ_F_BL_EMPTY;
 	sr->done_io = 0;
-	sr->retry = false;
+	sr->retry_flags = 0;
 	sr->len = 0; /* get from the provided buffer */
 }
 
@@ -397,7 +402,7 @@ int io_sendmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 	struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg);
 
 	sr->done_io = 0;
-	sr->retry = false;
+	sr->retry_flags = 0;
 	sr->len = READ_ONCE(sqe->len);
 	sr->flags = READ_ONCE(sqe->ioprio);
 	if (sr->flags & ~SENDMSG_FLAGS)
@@ -751,7 +756,7 @@ int io_recvmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 	struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg);
 
 	sr->done_io = 0;
-	sr->retry = false;
+	sr->retry_flags = 0;
 
 	if (unlikely(sqe->file_index || sqe->addr2))
 		return -EINVAL;
@@ -823,7 +828,7 @@ static inline bool io_recv_finish(struct io_kiocb *req, int *ret,
 
 		cflags |= io_put_kbufs(req, this_ret, io_bundle_nbufs(kmsg, this_ret),
 				      issue_flags);
-		if (sr->retry)
+		if (sr->retry_flags & IO_SR_MSG_RETRY)
 			cflags = req->cqe.flags | (cflags & CQE_F_MASK);
 		/* bundle with no more immediate buffers, we're done */
 		if (req->flags & REQ_F_BL_EMPTY)
@@ -832,12 +837,12 @@ static inline bool io_recv_finish(struct io_kiocb *req, int *ret,
 		 * If more is available AND it was a full transfer, retry and
 		 * append to this one
 		 */
-		if (!sr->retry && kmsg->msg.msg_inq > 1 && this_ret > 0 &&
+		if (!sr->retry_flags && kmsg->msg.msg_inq > 1 && this_ret > 0 &&
 		    !iov_iter_count(&kmsg->msg.msg_iter)) {
 			req->cqe.flags = cflags & ~CQE_F_MASK;
 			sr->len = kmsg->msg.msg_inq;
 			sr->done_io += this_ret;
-			sr->retry = true;
+			sr->retry_flags |= IO_SR_MSG_RETRY;
 			return false;
 		}
 	} else {
@@ -1082,6 +1087,8 @@ static int io_recv_buf_select(struct io_kiocb *req, struct io_async_msghdr *kmsg
 			kmsg->vec.iovec = arg.iovs;
 			req->flags |= REQ_F_NEED_CLEANUP;
 		}
+		if (arg.partial_map)
+			sr->retry_flags |= IO_SR_MSG_PARTIAL_MAP;
 
 		/* special case 1 vec, can be a fast path */
 		if (ret == 1) {
@@ -1276,7 +1283,7 @@ int io_send_zc_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 	int ret;
 
 	zc->done_io = 0;
-	zc->retry = false;
+	zc->retry_flags = 0;
 
 	if (unlikely(READ_ONCE(sqe->__pad2[0]) || READ_ONCE(sqe->addr3)))
 		return -EINVAL;

From 12ffc3b1513ebc1f11ae77d053948504a94a68a6 Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Fri, 13 Jun 2025 16:43:44 -0500
Subject: [PATCH 0929/1334] PM: Restrict swap use to later in the suspend
 sequence

Currently swap is restricted before drivers have had a chance to do
their prepare() PM callbacks. Restricting swap this early means that if
a driver needs to evict some content from memory into sawp in it's
prepare callback, it won't be able to.

On AMD dGPUs this can lead to failed suspends under memory pressure
situations as all VRAM must be evicted to system memory or swap.

Move the swap restriction to right after all devices have had a chance
to do the prepare() callback.  If there is any problem with the sequence,
restore swap in the appropriate dpm resume callbacks or error handling
paths.

Closes: https://github.com/ROCm/ROCK-Kernel-Driver/issues/174
Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/2362
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Tested-by: Nat Wittstock <nat@fardog.io>
Tested-by: Lucian Langa <lucilanga@7pot.org>
Link: https://patch.msgid.link/20250613214413.4127087-1-superm1@kernel.org
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/base/power/main.c | 5 ++++-
 include/linux/suspend.h   | 5 +++++
 kernel/kexec_core.c       | 1 +
 kernel/power/hibernate.c  | 3 ---
 kernel/power/power.h      | 5 -----
 kernel/power/suspend.c    | 3 +--
 6 files changed, 11 insertions(+), 11 deletions(-)

diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c
index eebe699fdf4f..bf77d28e959f 100644
--- a/drivers/base/power/main.c
+++ b/drivers/base/power/main.c
@@ -1236,6 +1236,7 @@ void dpm_complete(pm_message_t state)
  */
 void dpm_resume_end(pm_message_t state)
 {
+	pm_restore_gfp_mask();
 	dpm_resume(state);
 	dpm_complete(state);
 }
@@ -2176,8 +2177,10 @@ int dpm_suspend_start(pm_message_t state)
 	error = dpm_prepare(state);
 	if (error)
 		dpm_save_failed_step(SUSPEND_PREPARE);
-	else
+	else {
+		pm_restrict_gfp_mask();
 		error = dpm_suspend(state);
+	}
 
 	dpm_show_time(starttime, state, error, "start");
 	return error;
diff --git a/include/linux/suspend.h b/include/linux/suspend.h
index b1c76c8f2c82..6a3f92098872 100644
--- a/include/linux/suspend.h
+++ b/include/linux/suspend.h
@@ -446,6 +446,8 @@ extern int unregister_pm_notifier(struct notifier_block *nb);
 extern void ksys_sync_helper(void);
 extern void pm_report_hw_sleep_time(u64 t);
 extern void pm_report_max_hw_sleep(u64 t);
+void pm_restrict_gfp_mask(void);
+void pm_restore_gfp_mask(void);
 
 #define pm_notifier(fn, pri) {				\
 	static struct notifier_block fn##_nb =			\
@@ -492,6 +494,9 @@ static inline int unregister_pm_notifier(struct notifier_block *nb)
 static inline void pm_report_hw_sleep_time(u64 t) {};
 static inline void pm_report_max_hw_sleep(u64 t) {};
 
+static inline void pm_restrict_gfp_mask(void) {}
+static inline void pm_restore_gfp_mask(void) {}
+
 static inline void ksys_sync_helper(void) {}
 
 #define pm_notifier(fn, pri)	do { (void)(fn); } while (0)
diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c
index 9c59fa480b0b..3a9a9f240dbc 100644
--- a/kernel/kexec_core.c
+++ b/kernel/kexec_core.c
@@ -1136,6 +1136,7 @@ int kernel_kexec(void)
  Resume_devices:
 		dpm_resume_end(PMSG_RESTORE);
  Resume_console:
+		pm_restore_gfp_mask();
 		console_resume_all();
 		thaw_processes();
  Restore_console:
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index 519fb09de5e0..9216e3b91d3b 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -423,7 +423,6 @@ int hibernation_snapshot(int platform_mode)
 	}
 
 	console_suspend_all();
-	pm_restrict_gfp_mask();
 
 	error = dpm_suspend(PMSG_FREEZE);
 
@@ -559,7 +558,6 @@ int hibernation_restore(int platform_mode)
 
 	pm_prepare_console();
 	console_suspend_all();
-	pm_restrict_gfp_mask();
 	error = dpm_suspend_start(PMSG_QUIESCE);
 	if (!error) {
 		error = resume_target_kernel(platform_mode);
@@ -571,7 +569,6 @@ int hibernation_restore(int platform_mode)
 		BUG_ON(!error);
 	}
 	dpm_resume_end(PMSG_RECOVER);
-	pm_restore_gfp_mask();
 	console_resume_all();
 	pm_restore_console();
 	return error;
diff --git a/kernel/power/power.h b/kernel/power/power.h
index cb1d71562002..7ccd709af93f 100644
--- a/kernel/power/power.h
+++ b/kernel/power/power.h
@@ -239,11 +239,6 @@ static inline void suspend_test_finish(const char *label) {}
 /* kernel/power/main.c */
 extern int pm_notifier_call_chain_robust(unsigned long val_up, unsigned long val_down);
 extern int pm_notifier_call_chain(unsigned long val);
-void pm_restrict_gfp_mask(void);
-void pm_restore_gfp_mask(void);
-#else
-static inline void pm_restrict_gfp_mask(void) {}
-static inline void pm_restore_gfp_mask(void) {}
 #endif
 
 #ifdef CONFIG_HIGHMEM
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index 76b141b9aac0..bb608b68fb30 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -540,6 +540,7 @@ int suspend_devices_and_enter(suspend_state_t state)
 	return error;
 
  Recover_platform:
+	pm_restore_gfp_mask();
 	platform_recover(state);
 	goto Resume_devices;
 }
@@ -606,9 +607,7 @@ static int enter_state(suspend_state_t state)
 
 	trace_suspend_resume(TPS("suspend_enter"), state, false);
 	pm_pr_dbg("Suspending system (%s)\n", mem_sleep_labels[state]);
-	pm_restrict_gfp_mask();
 	error = suspend_devices_and_enter(state);
-	pm_restore_gfp_mask();
 
  Finish:
 	events_check_enabled = false;

From 62e062a29ad5133f67c20b333ba0a952a99161ae Mon Sep 17 00:00:00 2001
From: Simon Xue <xxm@rock-chips.com>
Date: Mon, 23 Jun 2025 10:00:18 +0800
Subject: [PATCH 0930/1334] iommu/rockchip: prevent iommus dead loop when two
 masters share one IOMMU

When two masters share an IOMMU, calling ops->of_xlate during
the second master's driver init may overwrite iommu->domain set
by the first. This causes the check if (iommu->domain == domain)
in rk_iommu_attach_device() to fail, resulting in the same
iommu->node being added twice to &rk_domain->iommus, which can
lead to an infinite loop in subsequent &rk_domain->iommus operations.

Cc: <stable@vger.kernel.org>
Fixes: 25c2325575cc ("iommu/rockchip: Add missing set_platform_dma_ops callback")
Signed-off-by: Simon Xue <xxm@rock-chips.com>
Reviewed-by: Robin Murphy <robin.murphy@arm.com>
Link: https://lore.kernel.org/r/20250623020018.584802-1-xxm@rock-chips.com
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
---
 drivers/iommu/rockchip-iommu.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/iommu/rockchip-iommu.c b/drivers/iommu/rockchip-iommu.c
index 22f74ba33a0e..e6bb3c784017 100644
--- a/drivers/iommu/rockchip-iommu.c
+++ b/drivers/iommu/rockchip-iommu.c
@@ -1157,7 +1157,6 @@ static int rk_iommu_of_xlate(struct device *dev,
 		return -ENOMEM;
 
 	data->iommu = platform_get_drvdata(iommu_dev);
-	data->iommu->domain = &rk_identity_domain;
 	dev_iommu_priv_set(dev, data);
 
 	platform_device_put(iommu_dev);
@@ -1195,6 +1194,8 @@ static int rk_iommu_probe(struct platform_device *pdev)
 	if (!iommu)
 		return -ENOMEM;
 
+	iommu->domain = &rk_identity_domain;
+
 	platform_set_drvdata(pdev, iommu);
 	iommu->dev = dev;
 	iommu->num_mmu = 0;

From 2d22b63f3a5aae2088708941d08cf0f01f430a58 Mon Sep 17 00:00:00 2001
From: Maxime Ripard <mripard@kernel.org>
Date: Thu, 26 Jun 2025 12:04:59 +0200
Subject: [PATCH 0931/1334] drm/mipi-dsi: Add dev_is_mipi_dsi function

This will be especially useful for generic panels (like panel-simple)
which can take different code path depending on if they are MIPI-DSI
devices or platform devices.

Reviewed-by: Javier Martinez Canillas <javierm@redhat.com>
Tested-by: Francesco Dolcini <francesco.dolcini@toradex.com> # Toradex Colibri iMX6
Link: https://lore.kernel.org/r/20250626-drm-panel-simple-fixes-v2-1-5afcaa608bdc@kernel.org
Signed-off-by: Maxime Ripard <mripard@kernel.org>
---
 drivers/gpu/drm/drm_mipi_dsi.c | 3 ++-
 include/drm/drm_mipi_dsi.h     | 3 +++
 2 files changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/drm_mipi_dsi.c b/drivers/gpu/drm/drm_mipi_dsi.c
index e5184a0c2465..21fd647f8ce1 100644
--- a/drivers/gpu/drm/drm_mipi_dsi.c
+++ b/drivers/gpu/drm/drm_mipi_dsi.c
@@ -91,12 +91,13 @@ static const struct dev_pm_ops mipi_dsi_device_pm_ops = {
 	.restore = pm_generic_restore,
 };
 
-static const struct bus_type mipi_dsi_bus_type = {
+const struct bus_type mipi_dsi_bus_type = {
 	.name = "mipi-dsi",
 	.match = mipi_dsi_device_match,
 	.uevent = mipi_dsi_uevent,
 	.pm = &mipi_dsi_device_pm_ops,
 };
+EXPORT_SYMBOL_GPL(mipi_dsi_bus_type);
 
 /**
  * of_find_mipi_dsi_device_by_node() - find the MIPI DSI device matching a
diff --git a/include/drm/drm_mipi_dsi.h b/include/drm/drm_mipi_dsi.h
index b37860f4a895..6d2c08e81101 100644
--- a/include/drm/drm_mipi_dsi.h
+++ b/include/drm/drm_mipi_dsi.h
@@ -223,6 +223,9 @@ struct mipi_dsi_multi_context {
 
 #define to_mipi_dsi_device(__dev)	container_of_const(__dev, struct mipi_dsi_device, dev)
 
+extern const struct bus_type mipi_dsi_bus_type;
+#define dev_is_mipi_dsi(dev)	((dev)->bus == &mipi_dsi_bus_type)
+
 /**
  * mipi_dsi_pixel_format_to_bpp - obtain the number of bits per pixel for any
  *                                given pixel format defined by the MIPI DSI

From 073667fce1667eab31d6a62cdd7fb795933ec7e8 Mon Sep 17 00:00:00 2001
From: Maxime Ripard <mripard@kernel.org>
Date: Thu, 26 Jun 2025 12:05:00 +0200
Subject: [PATCH 0932/1334] drm/panel: panel-simple: make panel_dpi_probe
 return a panel_desc

If the panel-simple driver is probed from a panel-dpi compatible, the
driver will use an empty panel_desc structure as a descriminant. It
will then allocate and fill another panel_desc as part of its probe.

However, that allocation needs to happen after the panel_simple
structure has been allocated, since panel_dpi_probe(), the function
doing the panel_desc allocation and initialization, takes a panel_simple
pointer as an argument.

This pointer is used to fill the panel_simple->desc pointer that is
still initialized with the empty panel_desc when panel_dpi_probe() is
called.

Since commit de04bb0089a9 ("drm/panel/panel-simple: Use the new
allocation in place of devm_kzalloc()"), we will need the panel
connector type found in panel_desc to allocate panel_simple. This
creates a circular dependency where we need panel_desc to create
panel_simple, and need panel_simple to create panel_desc.

Let's break that dependency by making panel_dpi_probe simply return the
panel_desc it initialized and move the panel_simple->desc assignment to
the caller.

This will not fix the breaking commit entirely, but will move us towards
the right direction.

Fixes: de04bb0089a9 ("drm/panel/panel-simple: Use the new allocation in place of devm_kzalloc()")
Reviewed-by: Javier Martinez Canillas <javierm@redhat.com>
Tested-by: Francesco Dolcini <francesco.dolcini@toradex.com> # Toradex Colibri iMX6
Link: https://lore.kernel.org/r/20250626-drm-panel-simple-fixes-v2-2-5afcaa608bdc@kernel.org
Signed-off-by: Maxime Ripard <mripard@kernel.org>
---
 drivers/gpu/drm/panel/panel-simple.c | 22 +++++++++++-----------
 1 file changed, 11 insertions(+), 11 deletions(-)

diff --git a/drivers/gpu/drm/panel/panel-simple.c b/drivers/gpu/drm/panel/panel-simple.c
index 0a3b26bb4d73..89188e683822 100644
--- a/drivers/gpu/drm/panel/panel-simple.c
+++ b/drivers/gpu/drm/panel/panel-simple.c
@@ -432,8 +432,7 @@ static const struct drm_panel_funcs panel_simple_funcs = {
 
 static struct panel_desc panel_dpi;
 
-static int panel_dpi_probe(struct device *dev,
-			   struct panel_simple *panel)
+static struct panel_desc *panel_dpi_probe(struct device *dev)
 {
 	struct display_timing *timing;
 	const struct device_node *np;
@@ -445,17 +444,17 @@ static int panel_dpi_probe(struct device *dev,
 	np = dev->of_node;
 	desc = devm_kzalloc(dev, sizeof(*desc), GFP_KERNEL);
 	if (!desc)
-		return -ENOMEM;
+		return ERR_PTR(-ENOMEM);
 
 	timing = devm_kzalloc(dev, sizeof(*timing), GFP_KERNEL);
 	if (!timing)
-		return -ENOMEM;
+		return ERR_PTR(-ENOMEM);
 
 	ret = of_get_display_timing(np, "panel-timing", timing);
 	if (ret < 0) {
 		dev_err(dev, "%pOF: no panel-timing node found for \"panel-dpi\" binding\n",
 			np);
-		return ret;
+		return ERR_PTR(ret);
 	}
 
 	desc->timings = timing;
@@ -473,9 +472,7 @@ static int panel_dpi_probe(struct device *dev,
 	/* We do not know the connector for the DT node, so guess it */
 	desc->connector_type = DRM_MODE_CONNECTOR_DPI;
 
-	panel->desc = desc;
-
-	return 0;
+	return desc;
 }
 
 #define PANEL_SIMPLE_BOUNDS_CHECK(to_check, bounds, field) \
@@ -613,10 +610,13 @@ static int panel_simple_probe(struct device *dev, const struct panel_desc *desc)
 
 	if (desc == &panel_dpi) {
 		/* Handle the generic panel-dpi binding */
-		err = panel_dpi_probe(dev, panel);
-		if (err)
+		desc = panel_dpi_probe(dev);
+		if (IS_ERR(desc)) {
+			err = PTR_ERR(desc);
 			goto free_ddc;
-		desc = panel->desc;
+		}
+
+		panel->desc = desc;
 	} else {
 		if (!of_get_display_timing(dev->of_node, "panel-timing", &dt))
 			panel_simple_parse_panel_timing_node(dev, panel, &dt);

From 921c41e509746aabecbbb2595ebf41a9d8fdc4e2 Mon Sep 17 00:00:00 2001
From: Maxime Ripard <mripard@kernel.org>
Date: Thu, 26 Jun 2025 12:05:01 +0200
Subject: [PATCH 0933/1334] drm/panel: panel-simple: Make panel_simple_probe
 return its panel

In order to fix the regession introduced by commit de04bb0089a9
("drm/panel/panel-simple: Use the new allocation in place of
devm_kzalloc()"), we need to move the panel_desc lookup into the common
panel_simple_probe() function.

There's two callers for that function, the probe implementations of the
platform and MIPI-DSI drivers panel-simple implements.

The MIPI-DSI driver's probe will need to access the current panel_desc
to initialize properly, which won't be possible anymore if we make that
lookup in panel_simple_probe().

However, we can make panel_simple_probe() return the initialized
panel_simple structure it allocated, which will contain a pointer to the
associated panel_desc in its desc field.

This doesn't fix de04bb0089a9 ("drm/panel/panel-simple: Use the new
allocation in place of devm_kzalloc()") still, but makes progress
towards that goal.

Fixes: de04bb0089a9 ("drm/panel/panel-simple: Use the new allocation in place of devm_kzalloc()")
Reviewed-by: Javier Martinez Canillas <javierm@redhat.com>
Tested-by: Francesco Dolcini <francesco.dolcini@toradex.com> # Toradex Colibri iMX6
Link: https://lore.kernel.org/r/20250626-drm-panel-simple-fixes-v2-3-5afcaa608bdc@kernel.org
Signed-off-by: Maxime Ripard <mripard@kernel.org>
---
 drivers/gpu/drm/panel/panel-simple.c | 33 +++++++++++++++++-----------
 1 file changed, 20 insertions(+), 13 deletions(-)

diff --git a/drivers/gpu/drm/panel/panel-simple.c b/drivers/gpu/drm/panel/panel-simple.c
index 89188e683822..e70ee2d4a538 100644
--- a/drivers/gpu/drm/panel/panel-simple.c
+++ b/drivers/gpu/drm/panel/panel-simple.c
@@ -567,7 +567,7 @@ static int panel_simple_override_nondefault_lvds_datamapping(struct device *dev,
 	return 0;
 }
 
-static int panel_simple_probe(struct device *dev, const struct panel_desc *desc)
+static struct panel_simple *panel_simple_probe(struct device *dev, const struct panel_desc *desc)
 {
 	struct panel_simple *panel;
 	struct display_timing dt;
@@ -579,24 +579,24 @@ static int panel_simple_probe(struct device *dev, const struct panel_desc *desc)
 	panel = devm_drm_panel_alloc(dev, struct panel_simple, base,
 				     &panel_simple_funcs, desc->connector_type);
 	if (IS_ERR(panel))
-		return PTR_ERR(panel);
+		return ERR_CAST(panel);
 
 	panel->desc = desc;
 
 	panel->supply = devm_regulator_get(dev, "power");
 	if (IS_ERR(panel->supply))
-		return PTR_ERR(panel->supply);
+		return ERR_CAST(panel->supply);
 
 	panel->enable_gpio = devm_gpiod_get_optional(dev, "enable",
 						     GPIOD_OUT_LOW);
 	if (IS_ERR(panel->enable_gpio))
-		return dev_err_probe(dev, PTR_ERR(panel->enable_gpio),
-				     "failed to request GPIO\n");
+		return dev_err_cast_probe(dev, panel->enable_gpio,
+					  "failed to request GPIO\n");
 
 	err = of_drm_get_panel_orientation(dev->of_node, &panel->orientation);
 	if (err) {
 		dev_err(dev, "%pOF: failed to get orientation %d\n", dev->of_node, err);
-		return err;
+		return ERR_PTR(err);
 	}
 
 	ddc = of_parse_phandle(dev->of_node, "ddc-i2c-bus", 0);
@@ -605,7 +605,7 @@ static int panel_simple_probe(struct device *dev, const struct panel_desc *desc)
 		of_node_put(ddc);
 
 		if (!panel->ddc)
-			return -EPROBE_DEFER;
+			return ERR_PTR(-EPROBE_DEFER);
 	}
 
 	if (desc == &panel_dpi) {
@@ -703,7 +703,7 @@ static int panel_simple_probe(struct device *dev, const struct panel_desc *desc)
 
 	drm_panel_add(&panel->base);
 
-	return 0;
+	return panel;
 
 disable_pm_runtime:
 	pm_runtime_dont_use_autosuspend(dev);
@@ -712,7 +712,7 @@ free_ddc:
 	if (panel->ddc)
 		put_device(&panel->ddc->dev);
 
-	return err;
+	return ERR_PTR(err);
 }
 
 static void panel_simple_shutdown(struct device *dev)
@@ -5377,12 +5377,17 @@ MODULE_DEVICE_TABLE(of, platform_of_match);
 static int panel_simple_platform_probe(struct platform_device *pdev)
 {
 	const struct panel_desc *desc;
+	struct panel_simple *panel;
 
 	desc = of_device_get_match_data(&pdev->dev);
 	if (!desc)
 		return -ENODEV;
 
-	return panel_simple_probe(&pdev->dev, desc);
+	panel = panel_simple_probe(&pdev->dev, desc);
+	if (IS_ERR(panel))
+		return PTR_ERR(panel);
+
+	return 0;
 }
 
 static void panel_simple_platform_remove(struct platform_device *pdev)
@@ -5653,16 +5658,18 @@ MODULE_DEVICE_TABLE(of, dsi_of_match);
 static int panel_simple_dsi_probe(struct mipi_dsi_device *dsi)
 {
 	const struct panel_desc_dsi *desc;
+	struct panel_simple *panel;
 	int err;
 
 	desc = of_device_get_match_data(&dsi->dev);
 	if (!desc)
 		return -ENODEV;
 
-	err = panel_simple_probe(&dsi->dev, &desc->desc);
-	if (err < 0)
-		return err;
+	panel = panel_simple_probe(&dsi->dev, &desc->desc);
+	if (IS_ERR(panel))
+		return PTR_ERR(panel);
 
+	desc = container_of(panel->desc, struct panel_desc_dsi, desc);
 	dsi->mode_flags = desc->flags;
 	dsi->format = desc->format;
 	dsi->lanes = desc->lanes;

From 47c08262f34e1cd9c48364431e4d32529029b910 Mon Sep 17 00:00:00 2001
From: Maxime Ripard <mripard@kernel.org>
Date: Thu, 26 Jun 2025 12:05:02 +0200
Subject: [PATCH 0934/1334] drm/panel: panel-simple: Add function to look panel
 data up

Commit de04bb0089a9 ("drm/panel/panel-simple: Use the new allocation in
place of devm_kzalloc()") moved the call to drm_panel_init into the
devm_drm_panel_alloc(), which needs a connector type to initialize
properly.

In the panel-dpi compatible case, the passed panel_desc structure is an
empty one used as a discriminant, and the connector type it contains
isn't actually initialized.

It is initialized through a call to panel_dpi_probe() later in the
function, which used to be before the call to drm_panel_init() that got
merged into devm_drm_panel_alloc().

So, we do need a proper panel_desc pointer before the call to
devm_drm_panel_alloc() now. All cases associate their panel_desc with
the panel compatible and use of_device_get_match_data, except for the
panel-dpi compatible.

In that case, we're expected to call panel_dpi_probe, which will
allocate and initialize the panel_desc for us.

Let's create such a helper function that would be called first in the
driver and will lookup the desc by compatible, or allocate one if
relevant.

Reported-by: Francesco Dolcini <francesco@dolcini.it>
Closes: https://lore.kernel.org/all/20250612081834.GA248237@francesco-nb/
Fixes: de04bb0089a9 ("drm/panel/panel-simple: Use the new allocation in place of devm_kzalloc()")
Reviewed-by: Javier Martinez Canillas <javierm@redhat.com>
Tested-by: Francesco Dolcini <francesco.dolcini@toradex.com> # Toradex Colibri iMX6
Link: https://lore.kernel.org/r/20250626-drm-panel-simple-fixes-v2-4-5afcaa608bdc@kernel.org
Signed-off-by: Maxime Ripard <mripard@kernel.org>
---
 drivers/gpu/drm/panel/panel-simple.c | 82 +++++++++++++++++-----------
 1 file changed, 49 insertions(+), 33 deletions(-)

diff --git a/drivers/gpu/drm/panel/panel-simple.c b/drivers/gpu/drm/panel/panel-simple.c
index e70ee2d4a538..4c831af86414 100644
--- a/drivers/gpu/drm/panel/panel-simple.c
+++ b/drivers/gpu/drm/panel/panel-simple.c
@@ -26,6 +26,7 @@
 #include <linux/i2c.h>
 #include <linux/media-bus-format.h>
 #include <linux/module.h>
+#include <linux/of_device.h>
 #include <linux/of_platform.h>
 #include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
@@ -136,6 +137,14 @@ struct panel_desc {
 	int connector_type;
 };
 
+struct panel_desc_dsi {
+	struct panel_desc desc;
+
+	unsigned long flags;
+	enum mipi_dsi_pixel_format format;
+	unsigned int lanes;
+};
+
 struct panel_simple {
 	struct drm_panel base;
 
@@ -567,8 +576,38 @@ static int panel_simple_override_nondefault_lvds_datamapping(struct device *dev,
 	return 0;
 }
 
-static struct panel_simple *panel_simple_probe(struct device *dev, const struct panel_desc *desc)
+static const struct panel_desc *panel_simple_get_desc(struct device *dev)
 {
+	if (IS_ENABLED(CONFIG_DRM_MIPI_DSI) &&
+	    dev_is_mipi_dsi(dev)) {
+		const struct panel_desc_dsi *dsi_desc;
+
+		dsi_desc = of_device_get_match_data(dev);
+		if (!dsi_desc)
+			return ERR_PTR(-ENODEV);
+
+		return &dsi_desc->desc;
+	}
+
+	if (dev_is_platform(dev)) {
+		const struct panel_desc *desc;
+
+		desc = of_device_get_match_data(dev);
+		if (!desc)
+			return ERR_PTR(-ENODEV);
+
+		if (desc == &panel_dpi)
+			return panel_dpi_probe(dev);
+
+		return desc;
+	}
+
+	return ERR_PTR(-ENODEV);
+}
+
+static struct panel_simple *panel_simple_probe(struct device *dev)
+{
+	const struct panel_desc *desc;
 	struct panel_simple *panel;
 	struct display_timing dt;
 	struct device_node *ddc;
@@ -576,6 +615,10 @@ static struct panel_simple *panel_simple_probe(struct device *dev, const struct
 	u32 bus_flags;
 	int err;
 
+	desc = panel_simple_get_desc(dev);
+	if (IS_ERR(desc))
+		return ERR_CAST(desc);
+
 	panel = devm_drm_panel_alloc(dev, struct panel_simple, base,
 				     &panel_simple_funcs, desc->connector_type);
 	if (IS_ERR(panel))
@@ -608,19 +651,9 @@ static struct panel_simple *panel_simple_probe(struct device *dev, const struct
 			return ERR_PTR(-EPROBE_DEFER);
 	}
 
-	if (desc == &panel_dpi) {
-		/* Handle the generic panel-dpi binding */
-		desc = panel_dpi_probe(dev);
-		if (IS_ERR(desc)) {
-			err = PTR_ERR(desc);
-			goto free_ddc;
-		}
-
-		panel->desc = desc;
-	} else {
-		if (!of_get_display_timing(dev->of_node, "panel-timing", &dt))
-			panel_simple_parse_panel_timing_node(dev, panel, &dt);
-	}
+	if ((desc != &panel_dpi) &&
+	    !of_get_display_timing(dev->of_node, "panel-timing", &dt))
+		panel_simple_parse_panel_timing_node(dev, panel, &dt);
 
 	if (desc->connector_type == DRM_MODE_CONNECTOR_LVDS) {
 		/* Optional data-mapping property for overriding bus format */
@@ -5376,14 +5409,9 @@ MODULE_DEVICE_TABLE(of, platform_of_match);
 
 static int panel_simple_platform_probe(struct platform_device *pdev)
 {
-	const struct panel_desc *desc;
 	struct panel_simple *panel;
 
-	desc = of_device_get_match_data(&pdev->dev);
-	if (!desc)
-		return -ENODEV;
-
-	panel = panel_simple_probe(&pdev->dev, desc);
+	panel = panel_simple_probe(&pdev->dev);
 	if (IS_ERR(panel))
 		return PTR_ERR(panel);
 
@@ -5417,14 +5445,6 @@ static struct platform_driver panel_simple_platform_driver = {
 	.shutdown = panel_simple_platform_shutdown,
 };
 
-struct panel_desc_dsi {
-	struct panel_desc desc;
-
-	unsigned long flags;
-	enum mipi_dsi_pixel_format format;
-	unsigned int lanes;
-};
-
 static const struct drm_display_mode auo_b080uan01_mode = {
 	.clock = 154500,
 	.hdisplay = 1200,
@@ -5661,11 +5681,7 @@ static int panel_simple_dsi_probe(struct mipi_dsi_device *dsi)
 	struct panel_simple *panel;
 	int err;
 
-	desc = of_device_get_match_data(&dsi->dev);
-	if (!desc)
-		return -ENODEV;
-
-	panel = panel_simple_probe(&dsi->dev, &desc->desc);
+	panel = panel_simple_probe(&dsi->dev);
 	if (IS_ERR(panel))
 		return PTR_ERR(panel);
 

From f6faebc11a8a6d9521e5ab00481bd22ed9c7c67d Mon Sep 17 00:00:00 2001
From: Maxime Ripard <mripard@kernel.org>
Date: Thu, 26 Jun 2025 12:05:03 +0200
Subject: [PATCH 0935/1334] drm/panel: panel-simple: get rid of panel_dpi hack

The empty panel_dpi struct was only ever used as a discriminant, but
it's kind of a hack, and with the reworks done in the previous patches,
we shouldn't need it anymore.

Let's get rid of it.

Reviewed-by: Javier Martinez Canillas <javierm@redhat.com>
Tested-by: Francesco Dolcini <francesco.dolcini@toradex.com> # Toradex Colibri iMX6
Link: https://lore.kernel.org/r/20250626-drm-panel-simple-fixes-v2-5-5afcaa608bdc@kernel.org
Signed-off-by: Maxime Ripard <mripard@kernel.org>
---
 drivers/gpu/drm/panel/panel-simple.c | 27 ++++++++++++++++++---------
 1 file changed, 18 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/panel/panel-simple.c b/drivers/gpu/drm/panel/panel-simple.c
index 4c831af86414..9f81fa960b46 100644
--- a/drivers/gpu/drm/panel/panel-simple.c
+++ b/drivers/gpu/drm/panel/panel-simple.c
@@ -439,8 +439,6 @@ static const struct drm_panel_funcs panel_simple_funcs = {
 	.get_timings = panel_simple_get_timings,
 };
 
-static struct panel_desc panel_dpi;
-
 static struct panel_desc *panel_dpi_probe(struct device *dev)
 {
 	struct display_timing *timing;
@@ -593,11 +591,17 @@ static const struct panel_desc *panel_simple_get_desc(struct device *dev)
 		const struct panel_desc *desc;
 
 		desc = of_device_get_match_data(dev);
-		if (!desc)
-			return ERR_PTR(-ENODEV);
-
-		if (desc == &panel_dpi)
-			return panel_dpi_probe(dev);
+		if (!desc) {
+			/*
+			 * panel-dpi probes without a descriptor and
+			 * panel_dpi_probe() will initialize one for us
+			 * based on the device tree.
+			 */
+			if (of_device_is_compatible(dev->of_node, "panel-dpi"))
+				return panel_dpi_probe(dev);
+			else
+				return ERR_PTR(-ENODEV);
+		}
 
 		return desc;
 	}
@@ -651,7 +655,7 @@ static struct panel_simple *panel_simple_probe(struct device *dev)
 			return ERR_PTR(-EPROBE_DEFER);
 	}
 
-	if ((desc != &panel_dpi) &&
+	if (!of_device_is_compatible(dev->of_node, "panel-dpi") &&
 	    !of_get_display_timing(dev->of_node, "panel-timing", &dt))
 		panel_simple_parse_panel_timing_node(dev, panel, &dt);
 
@@ -5400,7 +5404,12 @@ static const struct of_device_id platform_of_match[] = {
 	}, {
 		/* Must be the last entry */
 		.compatible = "panel-dpi",
-		.data = &panel_dpi,
+
+		/*
+		 * Explicitly NULL, the panel_desc structure will be
+		 * allocated by panel_dpi_probe().
+		 */
+		.data = NULL,
 	}, {
 		/* sentinel */
 	}

From 9159c5e733cfa35ec863fa81960a3e7435f831fb Mon Sep 17 00:00:00 2001
From: Bibo Mao <maobibo@loongson.cn>
Date: Fri, 27 Jun 2025 18:27:44 +0800
Subject: [PATCH 0936/1334] LoongArch: KVM: Add address alignment check for
 IOCSR emulation

IOCSR instruction supports 1/2/4/8 bytes access, the address should be
naturally aligned with its access size. Here address alignment check is
added in the EIOINTC kernel emulation.

Cc: stable@vger.kernel.org
Fixes: 3956a52bc05b ("LoongArch: KVM: Add EIOINTC read and write functions")
Signed-off-by: Bibo Mao <maobibo@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/kvm/intc/eiointc.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/arch/loongarch/kvm/intc/eiointc.c b/arch/loongarch/kvm/intc/eiointc.c
index 9c47456b805c..236cbf979167 100644
--- a/arch/loongarch/kvm/intc/eiointc.c
+++ b/arch/loongarch/kvm/intc/eiointc.c
@@ -305,6 +305,11 @@ static int kvm_eiointc_read(struct kvm_vcpu *vcpu,
 		return -EINVAL;
 	}
 
+	if (addr & (len - 1)) {
+		kvm_err("%s: eiointc not aligned addr %llx len %d\n", __func__, addr, len);
+		return -EINVAL;
+	}
+
 	vcpu->kvm->stat.eiointc_read_exits++;
 	spin_lock_irqsave(&eiointc->lock, flags);
 	switch (len) {
@@ -676,6 +681,11 @@ static int kvm_eiointc_write(struct kvm_vcpu *vcpu,
 		return -EINVAL;
 	}
 
+	if (addr & (len - 1)) {
+		kvm_err("%s: eiointc not aligned addr %llx len %d\n", __func__, addr, len);
+		return -EINVAL;
+	}
+
 	vcpu->kvm->stat.eiointc_write_exits++;
 	spin_lock_irqsave(&eiointc->lock, flags);
 	switch (len) {

From c34bbc2c990700ba07b271fc7c8113b0bc3e4093 Mon Sep 17 00:00:00 2001
From: Bibo Mao <maobibo@loongson.cn>
Date: Fri, 27 Jun 2025 18:27:44 +0800
Subject: [PATCH 0937/1334] LoongArch: KVM: Fix interrupt route update with
 EIOINTC

With function eiointc_update_sw_coremap(), there is forced assignment
like val = *(u64 *)pvalue. Parameter pvalue may be pointer to char type
or others, there is problem with forced assignment with u64 type.

Here the detailed value is passed rather address pointer.

Cc: stable@vger.kernel.org
Fixes: 3956a52bc05b ("LoongArch: KVM: Add EIOINTC read and write functions")
Signed-off-by: Bibo Mao <maobibo@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/kvm/intc/eiointc.c | 13 ++++++-------
 1 file changed, 6 insertions(+), 7 deletions(-)

diff --git a/arch/loongarch/kvm/intc/eiointc.c b/arch/loongarch/kvm/intc/eiointc.c
index 236cbf979167..8d3f48e2a7f0 100644
--- a/arch/loongarch/kvm/intc/eiointc.c
+++ b/arch/loongarch/kvm/intc/eiointc.c
@@ -66,10 +66,9 @@ static void eiointc_update_irq(struct loongarch_eiointc *s, int irq, int level)
 }
 
 static inline void eiointc_update_sw_coremap(struct loongarch_eiointc *s,
-					int irq, void *pvalue, u32 len, bool notify)
+					int irq, u64 val, u32 len, bool notify)
 {
 	int i, cpu;
-	u64 val = *(u64 *)pvalue;
 
 	for (i = 0; i < len; i++) {
 		cpu = val & 0xff;
@@ -403,7 +402,7 @@ static int loongarch_eiointc_writeb(struct kvm_vcpu *vcpu,
 		irq = offset - EIOINTC_COREMAP_START;
 		index = irq;
 		s->coremap.reg_u8[index] = data;
-		eiointc_update_sw_coremap(s, irq, (void *)&data, sizeof(data), true);
+		eiointc_update_sw_coremap(s, irq, data, sizeof(data), true);
 		break;
 	default:
 		ret = -EINVAL;
@@ -488,7 +487,7 @@ static int loongarch_eiointc_writew(struct kvm_vcpu *vcpu,
 		irq = offset - EIOINTC_COREMAP_START;
 		index = irq >> 1;
 		s->coremap.reg_u16[index] = data;
-		eiointc_update_sw_coremap(s, irq, (void *)&data, sizeof(data), true);
+		eiointc_update_sw_coremap(s, irq, data, sizeof(data), true);
 		break;
 	default:
 		ret = -EINVAL;
@@ -573,7 +572,7 @@ static int loongarch_eiointc_writel(struct kvm_vcpu *vcpu,
 		irq = offset - EIOINTC_COREMAP_START;
 		index = irq >> 2;
 		s->coremap.reg_u32[index] = data;
-		eiointc_update_sw_coremap(s, irq, (void *)&data, sizeof(data), true);
+		eiointc_update_sw_coremap(s, irq, data, sizeof(data), true);
 		break;
 	default:
 		ret = -EINVAL;
@@ -658,7 +657,7 @@ static int loongarch_eiointc_writeq(struct kvm_vcpu *vcpu,
 		irq = offset - EIOINTC_COREMAP_START;
 		index = irq >> 3;
 		s->coremap.reg_u64[index] = data;
-		eiointc_update_sw_coremap(s, irq, (void *)&data, sizeof(data), true);
+		eiointc_update_sw_coremap(s, irq, data, sizeof(data), true);
 		break;
 	default:
 		ret = -EINVAL;
@@ -816,7 +815,7 @@ static int kvm_eiointc_ctrl_access(struct kvm_device *dev,
 		for (i = 0; i < (EIOINTC_IRQS / 4); i++) {
 			start_irq = i * 4;
 			eiointc_update_sw_coremap(s, start_irq,
-					(void *)&s->coremap.reg_u32[i], sizeof(u32), false);
+					s->coremap.reg_u32[i], sizeof(u32), false);
 		}
 		break;
 	default:

From 45515c643d0abb75c2cc760a6bc6b235eadafd66 Mon Sep 17 00:00:00 2001
From: Bibo Mao <maobibo@loongson.cn>
Date: Fri, 27 Jun 2025 18:27:44 +0800
Subject: [PATCH 0938/1334] LoongArch: KVM: Check interrupt route from physical
 CPU

With EIOINTC interrupt controller, physical CPU ID is set for irq route.
However the function kvm_get_vcpu() is used to get destination vCPU when
delivering irq. With API kvm_get_vcpu(), the logical CPU ID is used.

With API kvm_get_vcpu_by_cpuid(), vCPU ID can be searched from physical
CPU ID.

Cc: stable@vger.kernel.org
Fixes: 3956a52bc05b ("LoongArch: KVM: Add EIOINTC read and write functions")
Signed-off-by: Bibo Mao <maobibo@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/kvm/intc/eiointc.c | 24 ++++++++++++++++++------
 1 file changed, 18 insertions(+), 6 deletions(-)

diff --git a/arch/loongarch/kvm/intc/eiointc.c b/arch/loongarch/kvm/intc/eiointc.c
index 8d3f48e2a7f0..644fb7785c07 100644
--- a/arch/loongarch/kvm/intc/eiointc.c
+++ b/arch/loongarch/kvm/intc/eiointc.c
@@ -9,7 +9,8 @@
 
 static void eiointc_set_sw_coreisr(struct loongarch_eiointc *s)
 {
-	int ipnum, cpu, irq_index, irq_mask, irq;
+	int ipnum, cpu, cpuid, irq_index, irq_mask, irq;
+	struct kvm_vcpu *vcpu;
 
 	for (irq = 0; irq < EIOINTC_IRQS; irq++) {
 		ipnum = s->ipmap.reg_u8[irq / 32];
@@ -20,7 +21,12 @@ static void eiointc_set_sw_coreisr(struct loongarch_eiointc *s)
 		irq_index = irq / 32;
 		irq_mask = BIT(irq & 0x1f);
 
-		cpu = s->coremap.reg_u8[irq];
+		cpuid = s->coremap.reg_u8[irq];
+		vcpu = kvm_get_vcpu_by_cpuid(s->kvm, cpuid);
+		if (!vcpu)
+			continue;
+
+		cpu = vcpu->vcpu_id;
 		if (!!(s->coreisr.reg_u32[cpu][irq_index] & irq_mask))
 			set_bit(irq, s->sw_coreisr[cpu][ipnum]);
 		else
@@ -68,17 +74,23 @@ static void eiointc_update_irq(struct loongarch_eiointc *s, int irq, int level)
 static inline void eiointc_update_sw_coremap(struct loongarch_eiointc *s,
 					int irq, u64 val, u32 len, bool notify)
 {
-	int i, cpu;
+	int i, cpu, cpuid;
+	struct kvm_vcpu *vcpu;
 
 	for (i = 0; i < len; i++) {
-		cpu = val & 0xff;
+		cpuid = val & 0xff;
 		val = val >> 8;
 
 		if (!(s->status & BIT(EIOINTC_ENABLE_CPU_ENCODE))) {
-			cpu = ffs(cpu) - 1;
-			cpu = (cpu >= 4) ? 0 : cpu;
+			cpuid = ffs(cpuid) - 1;
+			cpuid = (cpuid >= 4) ? 0 : cpuid;
 		}
 
+		vcpu = kvm_get_vcpu_by_cpuid(s->kvm, cpuid);
+		if (!vcpu)
+			continue;
+
+		cpu = vcpu->vcpu_id;
 		if (s->sw_coremap[irq + i] == cpu)
 			continue;
 

From cc8d5b209e09d3b52bca1ffe00045876842d96ae Mon Sep 17 00:00:00 2001
From: Bibo Mao <maobibo@loongson.cn>
Date: Fri, 27 Jun 2025 18:27:44 +0800
Subject: [PATCH 0939/1334] LoongArch: KVM: Check validity of "num_cpu" from
 user space

The maximum supported cpu number is EIOINTC_ROUTE_MAX_VCPUS about
irqchip EIOINTC, here add validation about cpu number to avoid array
pointer overflow.

Cc: stable@vger.kernel.org
Fixes: 1ad7efa552fd ("LoongArch: KVM: Add EIOINTC user mode read and write functions")
Signed-off-by: Bibo Mao <maobibo@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/kvm/intc/eiointc.c | 19 ++++++++++++++-----
 1 file changed, 14 insertions(+), 5 deletions(-)

diff --git a/arch/loongarch/kvm/intc/eiointc.c b/arch/loongarch/kvm/intc/eiointc.c
index 644fb7785c07..056a75f7d090 100644
--- a/arch/loongarch/kvm/intc/eiointc.c
+++ b/arch/loongarch/kvm/intc/eiointc.c
@@ -805,7 +805,7 @@ static int kvm_eiointc_ctrl_access(struct kvm_device *dev,
 	int ret = 0;
 	unsigned long flags;
 	unsigned long type = (unsigned long)attr->attr;
-	u32 i, start_irq;
+	u32 i, start_irq, val;
 	void __user *data;
 	struct loongarch_eiointc *s = dev->kvm->arch.eiointc;
 
@@ -813,8 +813,14 @@ static int kvm_eiointc_ctrl_access(struct kvm_device *dev,
 	spin_lock_irqsave(&s->lock, flags);
 	switch (type) {
 	case KVM_DEV_LOONGARCH_EXTIOI_CTRL_INIT_NUM_CPU:
-		if (copy_from_user(&s->num_cpu, data, 4))
+		if (copy_from_user(&val, data, 4))
 			ret = -EFAULT;
+		else {
+			if (val >= EIOINTC_ROUTE_MAX_VCPUS)
+				ret = -EINVAL;
+			else
+				s->num_cpu = val;
+		}
 		break;
 	case KVM_DEV_LOONGARCH_EXTIOI_CTRL_INIT_FEATURE:
 		if (copy_from_user(&s->features, data, 4))
@@ -842,7 +848,7 @@ static int kvm_eiointc_regs_access(struct kvm_device *dev,
 					struct kvm_device_attr *attr,
 					bool is_write)
 {
-	int addr, cpuid, offset, ret = 0;
+	int addr, cpu, offset, ret = 0;
 	unsigned long flags;
 	void *p = NULL;
 	void __user *data;
@@ -850,7 +856,7 @@ static int kvm_eiointc_regs_access(struct kvm_device *dev,
 
 	s = dev->kvm->arch.eiointc;
 	addr = attr->attr;
-	cpuid = addr >> 16;
+	cpu = addr >> 16;
 	addr &= 0xffff;
 	data = (void __user *)attr->addr;
 	switch (addr) {
@@ -875,8 +881,11 @@ static int kvm_eiointc_regs_access(struct kvm_device *dev,
 		p = &s->isr.reg_u32[offset];
 		break;
 	case EIOINTC_COREISR_START ... EIOINTC_COREISR_END:
+		if (cpu >= s->num_cpu)
+			return -EINVAL;
+
 		offset = (addr - EIOINTC_COREISR_START) / 4;
-		p = &s->coreisr.reg_u32[cpuid][offset];
+		p = &s->coreisr.reg_u32[cpu][offset];
 		break;
 	case EIOINTC_COREMAP_START ... EIOINTC_COREMAP_END:
 		offset = (addr - EIOINTC_COREMAP_START) / 4;

From 955853cf83657faa58572ef3f08b44f0f88885c1 Mon Sep 17 00:00:00 2001
From: Bibo Mao <maobibo@loongson.cn>
Date: Fri, 27 Jun 2025 18:27:44 +0800
Subject: [PATCH 0940/1334] LoongArch: KVM: Disable updating of "num_cpu" and
 "feature"

Property "num_cpu" and "feature" are read-only once eiointc is created,
which are set with KVM_DEV_LOONGARCH_EXTIOI_GRP_CTRL attr group before
device creation.

Attr group KVM_DEV_LOONGARCH_EXTIOI_GRP_SW_STATUS is to update register
and software state for migration and reset usage, property "num_cpu" and
"feature" can not be update again if it is created already.

Here discard write operation with property "num_cpu" and "feature" in
attr group KVM_DEV_LOONGARCH_EXTIOI_GRP_CTRL.

Cc: stable@vger.kernel.org
Fixes: 1ad7efa552fd ("LoongArch: KVM: Add EIOINTC user mode read and write functions")
Signed-off-by: Bibo Mao <maobibo@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/kvm/intc/eiointc.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/arch/loongarch/kvm/intc/eiointc.c b/arch/loongarch/kvm/intc/eiointc.c
index 056a75f7d090..a75f865d6fb9 100644
--- a/arch/loongarch/kvm/intc/eiointc.c
+++ b/arch/loongarch/kvm/intc/eiointc.c
@@ -926,9 +926,15 @@ static int kvm_eiointc_sw_status_access(struct kvm_device *dev,
 	data = (void __user *)attr->addr;
 	switch (addr) {
 	case KVM_DEV_LOONGARCH_EXTIOI_SW_STATUS_NUM_CPU:
+		if (is_write)
+			return ret;
+
 		p = &s->num_cpu;
 		break;
 	case KVM_DEV_LOONGARCH_EXTIOI_SW_STATUS_FEATURE:
+		if (is_write)
+			return ret;
+
 		p = &s->features;
 		break;
 	case KVM_DEV_LOONGARCH_EXTIOI_SW_STATUS_STATE:

From f40213cd93e608ee78b5e25db042c42ec07139fe Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Fri, 6 Jun 2025 09:56:52 +0200
Subject: [PATCH 0941/1334] i2c: scx200_acb: depends on HAS_IOPORT

It already depends on X86_32, but that's also set for ARCH=um.
Recent changes made UML no longer have IO port access since
it's not needed, but this driver uses it. Build it only for
HAS_IOPORT. This is pretty much the same as depending on X86,
but on the off-chance that HAS_IOPORT will ever be optional
on x86 HAS_IOPORT is the real prerequisite.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
---
 drivers/i2c/busses/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/i2c/busses/Kconfig b/drivers/i2c/busses/Kconfig
index 48c5ab832009..0a4ecccd1851 100644
--- a/drivers/i2c/busses/Kconfig
+++ b/drivers/i2c/busses/Kconfig
@@ -1530,7 +1530,7 @@ config I2C_XGENE_SLIMPRO
 
 config SCx200_ACB
 	tristate "Geode ACCESS.bus support"
-	depends on X86_32 && PCI
+	depends on X86_32 && PCI && HAS_IOPORT
 	help
 	  Enable the use of the ACCESS.bus controllers on the Geode SCx200 and
 	  SC1100 processors and the CS5535 and CS5536 Geode companion devices.

From 00c092de6f28ebd32208aef83b02d61af2229b60 Mon Sep 17 00:00:00 2001
From: Yazen Ghannam <yazen.ghannam@amd.com>
Date: Tue, 24 Jun 2025 14:15:57 +0000
Subject: [PATCH 0942/1334] x86/mce: Ensure user polling settings are honored
 when restarting timer

Users can disable MCA polling by setting the "ignore_ce" parameter or by
setting "check_interval=0". This tells the kernel to *not* start the MCE
timer on a CPU.

If the user did not disable CMCI, then storms can occur. When these
happen, the MCE timer will be started with a fixed interval. After the
storm subsides, the timer's next interval is set to check_interval.

This disregards the user's input through "ignore_ce" and
"check_interval". Furthermore, if "check_interval=0", then the new timer
will run faster than expected.

Create a new helper to check these conditions and use it when a CMCI
storm ends.

  [ bp: Massage. ]

Fixes: 7eae17c4add5 ("x86/mce: Add per-bank CMCI storm mitigation")
Signed-off-by: Yazen Ghannam <yazen.ghannam@amd.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/20250624-wip-mca-updates-v4-2-236dd74f645f@amd.com
---
 arch/x86/kernel/cpu/mce/core.c | 16 ++++++++++------
 1 file changed, 10 insertions(+), 6 deletions(-)

diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index 07d61937427f..4da4eab56c81 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -1740,6 +1740,11 @@ static void mc_poll_banks_default(void)
 
 void (*mc_poll_banks)(void) = mc_poll_banks_default;
 
+static bool should_enable_timer(unsigned long iv)
+{
+	return !mca_cfg.ignore_ce && iv;
+}
+
 static void mce_timer_fn(struct timer_list *t)
 {
 	struct timer_list *cpu_t = this_cpu_ptr(&mce_timer);
@@ -1763,7 +1768,7 @@ static void mce_timer_fn(struct timer_list *t)
 
 	if (mce_get_storm_mode()) {
 		__start_timer(t, HZ);
-	} else {
+	} else if (should_enable_timer(iv)) {
 		__this_cpu_write(mce_next_interval, iv);
 		__start_timer(t, iv);
 	}
@@ -2156,11 +2161,10 @@ static void mce_start_timer(struct timer_list *t)
 {
 	unsigned long iv = check_interval * HZ;
 
-	if (mca_cfg.ignore_ce || !iv)
-		return;
-
-	this_cpu_write(mce_next_interval, iv);
-	__start_timer(t, iv);
+	if (should_enable_timer(iv)) {
+		this_cpu_write(mce_next_interval, iv);
+		__start_timer(t, iv);
+	}
 }
 
 static void __mcheck_cpu_setup_timer(void)

From d66e1e90b16055d2f0ee76e5384e3f119c3c2773 Mon Sep 17 00:00:00 2001
From: Yazen Ghannam <yazen.ghannam@amd.com>
Date: Tue, 24 Jun 2025 14:15:58 +0000
Subject: [PATCH 0943/1334] x86/mce/amd: Add default names for MCA banks and
 blocks

Ensure that sysfs init doesn't fail for new/unrecognized bank types or if
a bank has additional blocks available.

Most MCA banks have a single thresholding block, so the block takes the same
name as the bank.

Unified Memory Controllers (UMCs) are a special case where there are two
blocks and each has a unique name.

However, the microarchitecture allows for five blocks. Any new MCA bank types
with more than one block will be missing names for the extra blocks. The MCE
sysfs will fail to initialize in this case.

Fixes: 87a6d4091bd7 ("x86/mce/AMD: Update sysfs bank names for SMCA systems")
Signed-off-by: Yazen Ghannam <yazen.ghannam@amd.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/20250624-wip-mca-updates-v4-3-236dd74f645f@amd.com
---
 arch/x86/kernel/cpu/mce/amd.c | 13 ++++++++++---
 1 file changed, 10 insertions(+), 3 deletions(-)

diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c
index 9d852c3b2cb5..6820ebce5d46 100644
--- a/arch/x86/kernel/cpu/mce/amd.c
+++ b/arch/x86/kernel/cpu/mce/amd.c
@@ -1113,13 +1113,20 @@ static const char *get_name(unsigned int cpu, unsigned int bank, struct threshol
 	}
 
 	bank_type = smca_get_bank_type(cpu, bank);
-	if (bank_type >= N_SMCA_BANK_TYPES)
-		return NULL;
 
 	if (b && (bank_type == SMCA_UMC || bank_type == SMCA_UMC_V2)) {
 		if (b->block < ARRAY_SIZE(smca_umc_block_names))
 			return smca_umc_block_names[b->block];
-		return NULL;
+	}
+
+	if (b && b->block) {
+		snprintf(buf_mcatype, MAX_MCATYPE_NAME_LEN, "th_block_%u", b->block);
+		return buf_mcatype;
+	}
+
+	if (bank_type >= N_SMCA_BANK_TYPES) {
+		snprintf(buf_mcatype, MAX_MCATYPE_NAME_LEN, "th_bank_%u", bank);
+		return buf_mcatype;
 	}
 
 	if (per_cpu(smca_bank_counts, cpu)[bank_type] == 1)

From 5f6e3b720694ad771911f637a51930f511427ce1 Mon Sep 17 00:00:00 2001
From: Yazen Ghannam <yazen.ghannam@amd.com>
Date: Tue, 24 Jun 2025 14:15:59 +0000
Subject: [PATCH 0944/1334] x86/mce/amd: Fix threshold limit reset

The MCA threshold limit must be reset after servicing the interrupt.

Currently, the restart function doesn't have an explicit check for this.  It
makes some assumptions based on the current limit and what's in the registers.
These assumptions don't always hold, so the limit won't be reset in some
cases.

Make the reset condition explicit. Either an interrupt/overflow has occurred
or the bank is being initialized.

Signed-off-by: Yazen Ghannam <yazen.ghannam@amd.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/20250624-wip-mca-updates-v4-4-236dd74f645f@amd.com
---
 arch/x86/kernel/cpu/mce/amd.c | 15 +++++++--------
 1 file changed, 7 insertions(+), 8 deletions(-)

diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c
index 6820ebce5d46..5c4eb28c3ac9 100644
--- a/arch/x86/kernel/cpu/mce/amd.c
+++ b/arch/x86/kernel/cpu/mce/amd.c
@@ -350,7 +350,6 @@ static void smca_configure(unsigned int bank, unsigned int cpu)
 
 struct thresh_restart {
 	struct threshold_block	*b;
-	int			reset;
 	int			set_lvt_off;
 	int			lvt_off;
 	u16			old_limit;
@@ -432,13 +431,13 @@ static void threshold_restart_bank(void *_tr)
 
 	rdmsr(tr->b->address, lo, hi);
 
-	if (tr->b->threshold_limit < (hi & THRESHOLD_MAX))
-		tr->reset = 1;	/* limit cannot be lower than err count */
-
-	if (tr->reset) {		/* reset err count and overflow bit */
-		hi =
-		    (hi & ~(MASK_ERR_COUNT_HI | MASK_OVERFLOW_HI)) |
-		    (THRESHOLD_MAX - tr->b->threshold_limit);
+	/*
+	 * Reset error count and overflow bit.
+	 * This is done during init or after handling an interrupt.
+	 */
+	if (hi & MASK_OVERFLOW_HI || tr->set_lvt_off) {
+		hi &= ~(MASK_ERR_COUNT_HI | MASK_OVERFLOW_HI);
+		hi |= THRESHOLD_MAX - tr->b->threshold_limit;
 	} else if (tr->old_limit) {	/* change limit w/o reset */
 		int new_count = (hi & THRESHOLD_MAX) +
 		    (tr->old_limit - tr->b->threshold_limit);

From 09234a632be42573d9743ac5ff6773622d233ad0 Mon Sep 17 00:00:00 2001
From: Dave Chinner <dchinner@redhat.com>
Date: Thu, 26 Jun 2025 08:48:54 +1000
Subject: [PATCH 0945/1334] xfs: xfs_ifree_cluster vs xfs_iflush_shutdown_abort
 deadlock

Lock order of xfs_ifree_cluster() is cluster buffer -> try ILOCK
-> IFLUSHING, except for the last inode in the cluster that is
triggering the free. In that case, the lock order is ILOCK ->
cluster buffer -> IFLUSHING.

xfs_iflush_cluster() uses cluster buffer -> try ILOCK -> IFLUSHING,
so this can safely run concurrently with xfs_ifree_cluster().

xfs_inode_item_precommit() uses ILOCK -> cluster buffer, but this
cannot race with xfs_ifree_cluster() so being in a different order
will not trigger a deadlock.

xfs_reclaim_inode() during a filesystem shutdown uses ILOCK ->
IFLUSHING -> cluster buffer via xfs_iflush_shutdown_abort(), and
this deadlocks against xfs_ifree_cluster() like so:

 sysrq: Show Blocked State
 task:kworker/10:37   state:D stack:12560 pid:276182 tgid:276182 ppid:2      flags:0x00004000
 Workqueue: xfs-inodegc/dm-3 xfs_inodegc_worker
 Call Trace:
  <TASK>
  __schedule+0x650/0xb10
  schedule+0x6d/0xf0
  schedule_timeout+0x8b/0x180
  schedule_timeout_uninterruptible+0x1e/0x30
  xfs_ifree+0x326/0x730
  xfs_inactive_ifree+0xcb/0x230
  xfs_inactive+0x2c8/0x380
  xfs_inodegc_worker+0xaa/0x180
  process_scheduled_works+0x1d4/0x400
  worker_thread+0x234/0x2e0
  kthread+0x147/0x170
  ret_from_fork+0x3e/0x50
  ret_from_fork_asm+0x1a/0x30
  </TASK>
 task:fsync-tester    state:D stack:12160 pid:2255943 tgid:2255943 ppid:3988702 flags:0x00004006
 Call Trace:
  <TASK>
  __schedule+0x650/0xb10
  schedule+0x6d/0xf0
  schedule_timeout+0x31/0x180
  __down_common+0xbe/0x1f0
  __down+0x1d/0x30
  down+0x48/0x50
  xfs_buf_lock+0x3d/0xe0
  xfs_iflush_shutdown_abort+0x51/0x1e0
  xfs_icwalk_ag+0x386/0x690
  xfs_reclaim_inodes_nr+0x114/0x160
  xfs_fs_free_cached_objects+0x19/0x20
  super_cache_scan+0x17b/0x1a0
  do_shrink_slab+0x180/0x350
  shrink_slab+0xf8/0x430
  drop_slab+0x97/0xf0
  drop_caches_sysctl_handler+0x59/0xc0
  proc_sys_call_handler+0x189/0x280
  proc_sys_write+0x13/0x20
  vfs_write+0x33d/0x3f0
  ksys_write+0x7c/0xf0
  __x64_sys_write+0x1b/0x30
  x64_sys_call+0x271d/0x2ee0
  do_syscall_64+0x68/0x130
  entry_SYSCALL_64_after_hwframe+0x76/0x7e

We can't change the lock order of xfs_ifree_cluster() - XFS_ISTALE
and XFS_IFLUSHING are serialised through to journal IO completion
by the cluster buffer lock being held.

There's quite a few asserts in the code that check that XFS_ISTALE
does not occur out of sync with buffer locking (e.g. in
xfs_iflush_cluster). There's also a dependency on the inode log item
being removed from the buffer before XFS_IFLUSHING is cleared, also
with asserts that trigger on this.

Further, we don't have a requirement for the inode to be locked when
completing or aborting inode flushing because all the inode state
updates are serialised by holding the cluster buffer lock across the
IO to completion.

We can't check for XFS_IRECLAIM in xfs_ifree_mark_inode_stale() and
skip the inode, because there is no guarantee that the inode will be
reclaimed. Hence it *must* be marked XFS_ISTALE regardless of
whether reclaim is preparing to free that inode. Similarly, we can't
check for IFLUSHING before locking the inode because that would
result in dirty inodes not being marked with ISTALE in the event of
racing with XFS_IRECLAIM.

Hence we have to address this issue from the xfs_reclaim_inode()
side. It is clear that we cannot hold the inode locked here when
calling xfs_iflush_shutdown_abort() because it is the inode->buffer
lock order that causes the deadlock against xfs_ifree_cluster().

Hence we need to drop the ILOCK before aborting the inode in the
shutdown case. Once we've aborted the inode, we can grab the ILOCK
again and then immediately reclaim it as it is now guaranteed to be
clean.

Note that dropping the ILOCK in xfs_reclaim_inode() means that it
can now be locked by xfs_ifree_mark_inode_stale() and seen whilst in
this state. This is safe because we have left the XFS_IFLUSHING flag
on the inode and so xfs_ifree_mark_inode_stale() will simply set
XFS_ISTALE and move to the next inode. An ASSERT check in this path
needs to be tweaked to take into account this new shutdown
interaction.

Signed-off-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 fs/xfs/xfs_icache.c | 8 ++++++++
 fs/xfs/xfs_inode.c  | 2 +-
 2 files changed, 9 insertions(+), 1 deletion(-)

diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index 726e29b837e6..bbc2f2973dcc 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -979,7 +979,15 @@ xfs_reclaim_inode(
 	 */
 	if (xlog_is_shutdown(ip->i_mount->m_log)) {
 		xfs_iunpin_wait(ip);
+		/*
+		 * Avoid a ABBA deadlock on the inode cluster buffer vs
+		 * concurrent xfs_ifree_cluster() trying to mark the inode
+		 * stale. We don't need the inode locked to run the flush abort
+		 * code, but the flush abort needs to lock the cluster buffer.
+		 */
+		xfs_iunlock(ip, XFS_ILOCK_EXCL);
 		xfs_iflush_shutdown_abort(ip);
+		xfs_ilock(ip, XFS_ILOCK_EXCL);
 		goto reclaim;
 	}
 	if (xfs_ipincount(ip))
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index ee3e0f284287..761a996a857c 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -1635,7 +1635,7 @@ retry:
 	iip = ip->i_itemp;
 	if (__xfs_iflags_test(ip, XFS_IFLUSHING)) {
 		ASSERT(!list_empty(&iip->ili_item.li_bio_list));
-		ASSERT(iip->ili_last_fields);
+		ASSERT(iip->ili_last_fields || xlog_is_shutdown(mp->m_log));
 		goto out_iunlock;
 	}
 

From db6a2274162de615ff74b927d38942fe3134d298 Mon Sep 17 00:00:00 2001
From: Dave Chinner <dchinner@redhat.com>
Date: Thu, 26 Jun 2025 08:48:55 +1000
Subject: [PATCH 0946/1334] xfs: catch stale AGF/AGF metadata

There is a race condition that can trigger in dmflakey fstests that
can result in asserts in xfs_ialloc_read_agi() and
xfs_alloc_read_agf() firing. The asserts look like this:

 XFS: Assertion failed: pag->pagf_freeblks == be32_to_cpu(agf->agf_freeblks), file: fs/xfs/libxfs/xfs_alloc.c, line: 3440
.....
 Call Trace:
  <TASK>
  xfs_alloc_read_agf+0x2ad/0x3a0
  xfs_alloc_fix_freelist+0x280/0x720
  xfs_alloc_vextent_prepare_ag+0x42/0x120
  xfs_alloc_vextent_iterate_ags+0x67/0x260
  xfs_alloc_vextent_start_ag+0xe4/0x1c0
  xfs_bmapi_allocate+0x6fe/0xc90
  xfs_bmapi_convert_delalloc+0x338/0x560
  xfs_map_blocks+0x354/0x580
  iomap_writepages+0x52b/0xa70
  xfs_vm_writepages+0xd7/0x100
  do_writepages+0xe1/0x2c0
  __writeback_single_inode+0x44/0x340
  writeback_sb_inodes+0x2d0/0x570
  __writeback_inodes_wb+0x9c/0xf0
  wb_writeback+0x139/0x2d0
  wb_workfn+0x23e/0x4c0
  process_scheduled_works+0x1d4/0x400
  worker_thread+0x234/0x2e0
  kthread+0x147/0x170
  ret_from_fork+0x3e/0x50
  ret_from_fork_asm+0x1a/0x30

I've seen the AGI variant from scrub running on the filesysetm
after unmount failed due to systemd interference:

 XFS: Assertion failed: pag->pagi_freecount == be32_to_cpu(agi->agi_freecount) || xfs_is_shutdown(pag->pag_mount), file: fs/xfs/libxfs/xfs_ialloc.c, line: 2804
.....
 Call Trace:
  <TASK>
  xfs_ialloc_read_agi+0xee/0x150
  xchk_perag_drain_and_lock+0x7d/0x240
  xchk_ag_init+0x34/0x90
  xchk_inode_xref+0x7b/0x220
  xchk_inode+0x14d/0x180
  xfs_scrub_metadata+0x2e2/0x510
  xfs_ioc_scrub_metadata+0x62/0xb0
  xfs_file_ioctl+0x446/0xbf0
  __se_sys_ioctl+0x6f/0xc0
  __x64_sys_ioctl+0x1d/0x30
  x64_sys_call+0x1879/0x2ee0
  do_syscall_64+0x68/0x130
  ? exc_page_fault+0x62/0xc0
  entry_SYSCALL_64_after_hwframe+0x76/0x7e

Essentially, it is the same problem. When _flakey_drop_and_remount()
loads the drop-writes table, it makes all writes silently fail. Writes
are reported to the fs as completed successfully, but they are not
issued to the backing store. The filesystem sees the successful
write completion and marks the metadata buffer clean and removes it
from the AIL.

If this happens at the same time as memory pressure is occuring,
the now-clean AGF and/or AGI buffers can be reclaimed from memory.

Shortly afterwards, but before _flakey_drop_and_remount() runs
unmount, background writeback is kicked and it tries to allocate
blocks for the dirty pages in memory. This then tries to access the
AGF buffer we just turfed out of memory. It's not found, so it gets
read in from disk.

This is all fine, except for the fact that the last writeback of the
AGF did not actually reach disk. The AGF on disk is stale compared
to the in-memory state held by the perag, and so they don't match
and the assert fires.

Then other operations on that inode hang because the task was killed
whilst holding inode locks. e.g:

 Workqueue: xfs-conv/dm-12 xfs_end_io
 Call Trace:
  <TASK>
  __schedule+0x650/0xb10
  schedule+0x6d/0xf0
  schedule_preempt_disabled+0x15/0x30
  rwsem_down_write_slowpath+0x31a/0x5f0
  down_write+0x43/0x60
  xfs_ilock+0x1a8/0x210
  xfs_trans_alloc_inode+0x9c/0x240
  xfs_iomap_write_unwritten+0xe3/0x300
  xfs_end_ioend+0x90/0x130
  xfs_end_io+0xce/0x100
  process_scheduled_works+0x1d4/0x400
  worker_thread+0x234/0x2e0
  kthread+0x147/0x170
  ret_from_fork+0x3e/0x50
  ret_from_fork_asm+0x1a/0x30
  </TASK>

and it's all down hill from there.

Memory pressure is one way to trigger this, another is to run "echo
3 > /proc/sys/vm/drop_caches" randomly while tests are running.

Regardless of how it is triggered, this effectively takes down the
system once umount hangs because it's holding a sb->s_umount lock
exclusive and now every sync(1) call gets stuck on it.

Fix this by replacing the asserts with a corruption detection check
and a shutdown.

Signed-off-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 fs/xfs/libxfs/xfs_alloc.c  | 41 ++++++++++++++++++++++++++++++--------
 fs/xfs/libxfs/xfs_ialloc.c | 31 ++++++++++++++++++++++++----
 2 files changed, 60 insertions(+), 12 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c
index 7839efe050bf..000cc7f4a3ce 100644
--- a/fs/xfs/libxfs/xfs_alloc.c
+++ b/fs/xfs/libxfs/xfs_alloc.c
@@ -3444,16 +3444,41 @@ xfs_alloc_read_agf(
 
 		set_bit(XFS_AGSTATE_AGF_INIT, &pag->pag_opstate);
 	}
+
 #ifdef DEBUG
-	else if (!xfs_is_shutdown(mp)) {
-		ASSERT(pag->pagf_freeblks == be32_to_cpu(agf->agf_freeblks));
-		ASSERT(pag->pagf_btreeblks == be32_to_cpu(agf->agf_btreeblks));
-		ASSERT(pag->pagf_flcount == be32_to_cpu(agf->agf_flcount));
-		ASSERT(pag->pagf_longest == be32_to_cpu(agf->agf_longest));
-		ASSERT(pag->pagf_bno_level == be32_to_cpu(agf->agf_bno_level));
-		ASSERT(pag->pagf_cnt_level == be32_to_cpu(agf->agf_cnt_level));
+	/*
+	 * It's possible for the AGF to be out of sync if the block device is
+	 * silently dropping writes. This can happen in fstests with dmflakey
+	 * enabled, which allows the buffer to be cleaned and reclaimed by
+	 * memory pressure and then re-read from disk here. We will get a
+	 * stale version of the AGF from disk, and nothing good can happen from
+	 * here. Hence if we detect this situation, immediately shut down the
+	 * filesystem.
+	 *
+	 * This can also happen if we are already in the middle of a forced
+	 * shutdown, so don't bother checking if we are already shut down.
+	 */
+	if (!xfs_is_shutdown(pag_mount(pag))) {
+		bool	ok = true;
+
+		ok &= pag->pagf_freeblks == be32_to_cpu(agf->agf_freeblks);
+		ok &= pag->pagf_freeblks == be32_to_cpu(agf->agf_freeblks);
+		ok &= pag->pagf_btreeblks == be32_to_cpu(agf->agf_btreeblks);
+		ok &= pag->pagf_flcount == be32_to_cpu(agf->agf_flcount);
+		ok &= pag->pagf_longest == be32_to_cpu(agf->agf_longest);
+		ok &= pag->pagf_bno_level == be32_to_cpu(agf->agf_bno_level);
+		ok &= pag->pagf_cnt_level == be32_to_cpu(agf->agf_cnt_level);
+
+		if (XFS_IS_CORRUPT(pag_mount(pag), !ok)) {
+			xfs_ag_mark_sick(pag, XFS_SICK_AG_AGF);
+			xfs_trans_brelse(tp, agfbp);
+			xfs_force_shutdown(pag_mount(pag),
+					SHUTDOWN_CORRUPT_ONDISK);
+			return -EFSCORRUPTED;
+		}
 	}
-#endif
+#endif /* DEBUG */
+
 	if (agfbpp)
 		*agfbpp = agfbp;
 	else
diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c
index 0c47b5c6ca7d..750111634d9f 100644
--- a/fs/xfs/libxfs/xfs_ialloc.c
+++ b/fs/xfs/libxfs/xfs_ialloc.c
@@ -2801,12 +2801,35 @@ xfs_ialloc_read_agi(
 		set_bit(XFS_AGSTATE_AGI_INIT, &pag->pag_opstate);
 	}
 
+#ifdef DEBUG
 	/*
-	 * It's possible for these to be out of sync if
-	 * we are in the middle of a forced shutdown.
+	 * It's possible for the AGF to be out of sync if the block device is
+	 * silently dropping writes. This can happen in fstests with dmflakey
+	 * enabled, which allows the buffer to be cleaned and reclaimed by
+	 * memory pressure and then re-read from disk here. We will get a
+	 * stale version of the AGF from disk, and nothing good can happen from
+	 * here. Hence if we detect this situation, immediately shut down the
+	 * filesystem.
+	 *
+	 * This can also happen if we are already in the middle of a forced
+	 * shutdown, so don't bother checking if we are already shut down.
 	 */
-	ASSERT(pag->pagi_freecount == be32_to_cpu(agi->agi_freecount) ||
-		xfs_is_shutdown(pag_mount(pag)));
+	if (!xfs_is_shutdown(pag_mount(pag))) {
+		bool	ok = true;
+
+		ok &= pag->pagi_freecount == be32_to_cpu(agi->agi_freecount);
+		ok &= pag->pagi_count == be32_to_cpu(agi->agi_count);
+
+		if (XFS_IS_CORRUPT(pag_mount(pag), !ok)) {
+			xfs_ag_mark_sick(pag, XFS_SICK_AG_AGI);
+			xfs_trans_brelse(tp, agibp);
+			xfs_force_shutdown(pag_mount(pag),
+					SHUTDOWN_CORRUPT_ONDISK);
+			return -EFSCORRUPTED;
+		}
+	}
+#endif /* DEBUG */
+
 	if (agibpp)
 		*agibpp = agibp;
 	else

From d62016b1a2df24c8608fe83cd3ae8090412881b3 Mon Sep 17 00:00:00 2001
From: Dave Chinner <dchinner@redhat.com>
Date: Thu, 26 Jun 2025 08:48:56 +1000
Subject: [PATCH 0947/1334] xfs: avoid dquot buffer pin deadlock

On shutdown when quotas are enabled, the shutdown can deadlock
trying to unpin the dquot buffer buf_log_item like so:

[ 3319.483590] task:kworker/20:0H   state:D stack:14360 pid:1962230 tgid:1962230 ppid:2      task_flags:0x4208060 flags:0x00004000
[ 3319.493966] Workqueue: xfs-log/dm-6 xlog_ioend_work
[ 3319.498458] Call Trace:
[ 3319.500800]  <TASK>
[ 3319.502809]  __schedule+0x699/0xb70
[ 3319.512672]  schedule+0x64/0xd0
[ 3319.515573]  schedule_timeout+0x30/0xf0
[ 3319.528125]  __down_common+0xc3/0x200
[ 3319.531488]  __down+0x1d/0x30
[ 3319.534186]  down+0x48/0x50
[ 3319.540501]  xfs_buf_lock+0x3d/0xe0
[ 3319.543609]  xfs_buf_item_unpin+0x85/0x1b0
[ 3319.547248]  xlog_cil_committed+0x289/0x570
[ 3319.571411]  xlog_cil_process_committed+0x6d/0x90
[ 3319.575590]  xlog_state_shutdown_callbacks+0x52/0x110
[ 3319.580017]  xlog_force_shutdown+0x169/0x1a0
[ 3319.583780]  xlog_ioend_work+0x7c/0xb0
[ 3319.587049]  process_scheduled_works+0x1d6/0x400
[ 3319.591127]  worker_thread+0x202/0x2e0
[ 3319.594452]  kthread+0x20c/0x240

The CIL push has seen the deadlock, so it has aborted the push and
is running CIL checkpoint completion to abort all the items in the
checkpoint. This calls ->iop_unpin(remove = true) to clean up the
log items in the checkpoint.

When a buffer log item is unpined like this, it needs to lock the
buffer to run io completion to correctly fail the buffer and run all
the required completions to fail attached log items as well. In this
case, the attempt to lock the buffer on unpin is hanging because the
buffer is already locked.

I suspected a leaked XFS_BLI_HOLD state because of XFS_BLI_STALE
handling changes I was testing, so I went looking for
pin events on HOLD buffers and unpin events on locked buffer. That
isolated this one buffer with these two events:

xfs_buf_item_pin:     dev 251:6 daddr 0xa910 bbcount 0x2 hold 2 pincount 0 lock 0 flags DONE|KMEM recur 0 refcount 1 bliflags HOLD|DIRTY|LOGGED liflags DIRTY
....
xfs_buf_item_unpin:   dev 251:6 daddr 0xa910 bbcount 0x2 hold 4 pincount 1 lock 0 flags DONE|KMEM recur 0 refcount 1 bliflags DIRTY liflags ABORTED

Firstly, bbcount = 0x2, which means it is not a single sector
structure. That rules out every xfs_trans_bhold() case except one:
dquot buffers.

Then hung task dumping gave this trace:

[ 3197.312078] task:fsync-tester    state:D stack:12080 pid:2051125 tgid:2051125 ppid:1643233 task_flags:0x400000 flags:0x00004002
[ 3197.323007] Call Trace:
[ 3197.325581]  <TASK>
[ 3197.327727]  __schedule+0x699/0xb70
[ 3197.334582]  schedule+0x64/0xd0
[ 3197.337672]  schedule_timeout+0x30/0xf0
[ 3197.350139]  wait_for_completion+0xbd/0x180
[ 3197.354235]  __flush_workqueue+0xef/0x4e0
[ 3197.362229]  xlog_cil_force_seq+0xa0/0x300
[ 3197.374447]  xfs_log_force+0x77/0x230
[ 3197.378015]  xfs_qm_dqunpin_wait+0x49/0xf0
[ 3197.382010]  xfs_qm_dqflush+0x55/0x460
[ 3197.385663]  xfs_qm_dquot_isolate+0x29e/0x4d0
[ 3197.389977]  __list_lru_walk_one+0x141/0x220
[ 3197.398867]  list_lru_walk_one+0x10/0x20
[ 3197.402713]  xfs_qm_shrink_scan+0x6a/0x100
[ 3197.406699]  do_shrink_slab+0x18a/0x350
[ 3197.410512]  shrink_slab+0xf7/0x430
[ 3197.413967]  drop_slab+0x97/0xf0
[ 3197.417121]  drop_caches_sysctl_handler+0x59/0xc0
[ 3197.421654]  proc_sys_call_handler+0x18b/0x280
[ 3197.426050]  proc_sys_write+0x13/0x20
[ 3197.429750]  vfs_write+0x2b8/0x3e0
[ 3197.438532]  ksys_write+0x7e/0xf0
[ 3197.441742]  __x64_sys_write+0x1b/0x30
[ 3197.445363]  x64_sys_call+0x2c72/0x2f60
[ 3197.449044]  do_syscall_64+0x6c/0x140
[ 3197.456341]  entry_SYSCALL_64_after_hwframe+0x76/0x7e

Yup, another test run by check-parallel is running drop_caches
concurrently and the dquot shrinker for the hung filesystem is
running. That's trying to flush a dirty dquot from reclaim context,
and it waiting on a log force to complete. xfs_qm_dqflush is called
with the dquot buffer held locked, and so we've called
xfs_log_force() with that buffer locked.

Now the log force is waiting for a workqueue flush to complete, and
that workqueue flush is waiting of CIL checkpoint processing to
finish.

The CIL checkpoint processing is aborting all the log items it has,
and that requires locking aborted buffers to cancel them.

Now, normally this isn't a problem if we are issuing a log force
to unpin an object, because the ->iop_unpin() method wakes pin
waiters first. That results in the pin waiter finishing off whatever
it was doing, dropping the lock and then xfs_buf_item_unpin() can
lock the buffer and fail it.

However, xfs_qm_dqflush() is waiting on the -dquot- unpin event, not
the dquot buffer unpin event, and so it never gets woken and so does
not drop the buffer lock.

Inodes do not have this problem, as they can only be written from
one spot (->iop_push) whilst dquots can be written from multiple
places (memory reclaim, ->iop_push, xfs_dq_dqpurge, and quotacheck).

The reason that the dquot buffer has an attached buffer log item is
that it has been recently allocated. Initialisation of the dquot
buffer logs the buffer directly, thereby pinning it in memory. We
then modify the dquot in a separate operation, and have memory
reclaim racing with a shutdown and we trigger this deadlock.

check-parallel reproduces this reliably on 1kB FSB filesystems with
quota enabled because it does all of these things concurrently
without having to explicitly write tests to exercise these corner
case conditions.

xfs_qm_dquot_logitem_push() doesn't have this deadlock because it
checks if the dquot is pinned before locking the dquot buffer and
skipping it if it is pinned. This means the xfs_qm_dqunpin_wait()
log force in xfs_qm_dqflush() never triggers and we unlock the
buffer safely allowing a concurrent shutdown to fail the buffer
appropriately.

xfs_qm_dqpurge() could have this problem as it is called from
quotacheck and we might have allocated dquot buffers when recording
the quota updates. This can be fixed by calling
xfs_qm_dqunpin_wait() before we lock the dquot buffer. Because we
hold the dquot locked, nothing will be able to add to the pin count
between the unpin_wait and the dqflush callout, so this now makes
xfs_qm_dqpurge() safe against this race.

xfs_qm_dquot_isolate() can also be fixed this same way but, quite
frankly, we shouldn't be doing IO in memory reclaim context. If the
dquot is pinned or dirty, simply rotate it and let memory reclaim
come back to it later, same as we do for inodes.

This then gets rid of the nasty issue in xfs_qm_flush_one() where
quotacheck writeback races with memory reclaim flushing the dquots.
We can lift xfs_qm_dqunpin_wait() up into this code, then get rid of
the "can't get the dqflush lock" buffer write to cycle the dqlfush
lock and enable it to be flushed again.  checking if the dquot is
pinned and returning -EAGAIN so that the dquot walk will revisit the
dquot again later.

Finally, with xfs_qm_dqunpin_wait() lifted into all the callers,
we can remove it from the xfs_qm_dqflush() code.

Signed-off-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 fs/xfs/xfs_buf.c   | 38 --------------------
 fs/xfs/xfs_buf.h   |  1 -
 fs/xfs/xfs_dquot.c |  4 +--
 fs/xfs/xfs_qm.c    | 86 ++++++++++------------------------------------
 fs/xfs/xfs_trace.h |  1 -
 5 files changed, 20 insertions(+), 110 deletions(-)

diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index 8af83bd161f9..ba5bd6031ece 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -2082,44 +2082,6 @@ xfs_buf_delwri_submit(
 	return error;
 }
 
-/*
- * Push a single buffer on a delwri queue.
- *
- * The purpose of this function is to submit a single buffer of a delwri queue
- * and return with the buffer still on the original queue.
- *
- * The buffer locking and queue management logic between _delwri_pushbuf() and
- * _delwri_queue() guarantee that the buffer cannot be queued to another list
- * before returning.
- */
-int
-xfs_buf_delwri_pushbuf(
-	struct xfs_buf		*bp,
-	struct list_head	*buffer_list)
-{
-	int			error;
-
-	ASSERT(bp->b_flags & _XBF_DELWRI_Q);
-
-	trace_xfs_buf_delwri_pushbuf(bp, _RET_IP_);
-
-	xfs_buf_lock(bp);
-	bp->b_flags &= ~(_XBF_DELWRI_Q | XBF_ASYNC);
-	bp->b_flags |= XBF_WRITE;
-	xfs_buf_submit(bp);
-
-	/*
-	 * The buffer is now locked, under I/O but still on the original delwri
-	 * queue. Wait for I/O completion, restore the DELWRI_Q flag and
-	 * return with the buffer unlocked and still on the original queue.
-	 */
-	error = xfs_buf_iowait(bp);
-	bp->b_flags |= _XBF_DELWRI_Q;
-	xfs_buf_unlock(bp);
-
-	return error;
-}
-
 void xfs_buf_set_ref(struct xfs_buf *bp, int lru_ref)
 {
 	/*
diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h
index 9d2ab567cf81..15fc56948346 100644
--- a/fs/xfs/xfs_buf.h
+++ b/fs/xfs/xfs_buf.h
@@ -326,7 +326,6 @@ extern bool xfs_buf_delwri_queue(struct xfs_buf *, struct list_head *);
 void xfs_buf_delwri_queue_here(struct xfs_buf *bp, struct list_head *bl);
 extern int xfs_buf_delwri_submit(struct list_head *);
 extern int xfs_buf_delwri_submit_nowait(struct list_head *);
-extern int xfs_buf_delwri_pushbuf(struct xfs_buf *, struct list_head *);
 
 static inline xfs_daddr_t xfs_buf_daddr(struct xfs_buf *bp)
 {
diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c
index b4e32f0860b7..0bd8022e47b4 100644
--- a/fs/xfs/xfs_dquot.c
+++ b/fs/xfs/xfs_dquot.c
@@ -1398,11 +1398,9 @@ xfs_qm_dqflush(
 
 	ASSERT(XFS_DQ_IS_LOCKED(dqp));
 	ASSERT(!completion_done(&dqp->q_flush));
+	ASSERT(atomic_read(&dqp->q_pincount) == 0);
 
 	trace_xfs_dqflush(dqp);
-
-	xfs_qm_dqunpin_wait(dqp);
-
 	fa = xfs_qm_dqflush_check(dqp);
 	if (fa) {
 		xfs_alert(mp, "corrupt dquot ID 0x%x in memory at %pS",
diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c
index 417439b58785..fa135ac26471 100644
--- a/fs/xfs/xfs_qm.c
+++ b/fs/xfs/xfs_qm.c
@@ -134,6 +134,7 @@ xfs_qm_dqpurge(
 
 	dqp->q_flags |= XFS_DQFLAG_FREEING;
 
+	xfs_qm_dqunpin_wait(dqp);
 	xfs_dqflock(dqp);
 
 	/*
@@ -465,6 +466,7 @@ xfs_qm_dquot_isolate(
 	struct xfs_dquot	*dqp = container_of(item,
 						struct xfs_dquot, q_lru);
 	struct xfs_qm_isolate	*isol = arg;
+	enum lru_status		ret = LRU_SKIP;
 
 	if (!xfs_dqlock_nowait(dqp))
 		goto out_miss_busy;
@@ -477,6 +479,16 @@ xfs_qm_dquot_isolate(
 	if (dqp->q_flags & XFS_DQFLAG_FREEING)
 		goto out_miss_unlock;
 
+	/*
+	 * If the dquot is pinned or dirty, rotate it to the end of the LRU to
+	 * give some time for it to be cleaned before we try to isolate it
+	 * again.
+	 */
+	ret = LRU_ROTATE;
+	if (XFS_DQ_IS_DIRTY(dqp) || atomic_read(&dqp->q_pincount) > 0) {
+		goto out_miss_unlock;
+	}
+
 	/*
 	 * This dquot has acquired a reference in the meantime remove it from
 	 * the freelist and try again.
@@ -492,41 +504,14 @@ xfs_qm_dquot_isolate(
 	}
 
 	/*
-	 * If the dquot is dirty, flush it. If it's already being flushed, just
-	 * skip it so there is time for the IO to complete before we try to
-	 * reclaim it again on the next LRU pass.
+	 * The dquot may still be under IO, in which case the flush lock will be
+	 * held. If we can't get the flush lock now, just skip over the dquot as
+	 * if it was dirty.
 	 */
 	if (!xfs_dqflock_nowait(dqp))
 		goto out_miss_unlock;
 
-	if (XFS_DQ_IS_DIRTY(dqp)) {
-		struct xfs_buf	*bp = NULL;
-		int		error;
-
-		trace_xfs_dqreclaim_dirty(dqp);
-
-		/* we have to drop the LRU lock to flush the dquot */
-		spin_unlock(&lru->lock);
-
-		error = xfs_dquot_use_attached_buf(dqp, &bp);
-		if (!bp || error == -EAGAIN) {
-			xfs_dqfunlock(dqp);
-			goto out_unlock_dirty;
-		}
-
-		/*
-		 * dqflush completes dqflock on error, and the delwri ioend
-		 * does it on success.
-		 */
-		error = xfs_qm_dqflush(dqp, bp);
-		if (error)
-			goto out_unlock_dirty;
-
-		xfs_buf_delwri_queue(bp, &isol->buffers);
-		xfs_buf_relse(bp);
-		goto out_unlock_dirty;
-	}
-
+	ASSERT(!XFS_DQ_IS_DIRTY(dqp));
 	xfs_dquot_detach_buf(dqp);
 	xfs_dqfunlock(dqp);
 
@@ -548,13 +533,7 @@ out_miss_unlock:
 out_miss_busy:
 	trace_xfs_dqreclaim_busy(dqp);
 	XFS_STATS_INC(dqp->q_mount, xs_qm_dqreclaim_misses);
-	return LRU_SKIP;
-
-out_unlock_dirty:
-	trace_xfs_dqreclaim_busy(dqp);
-	XFS_STATS_INC(dqp->q_mount, xs_qm_dqreclaim_misses);
-	xfs_dqunlock(dqp);
-	return LRU_RETRY;
+	return ret;
 }
 
 static unsigned long
@@ -1486,7 +1465,6 @@ xfs_qm_flush_one(
 	struct xfs_dquot	*dqp,
 	void			*data)
 {
-	struct xfs_mount	*mp = dqp->q_mount;
 	struct list_head	*buffer_list = data;
 	struct xfs_buf		*bp = NULL;
 	int			error = 0;
@@ -1497,34 +1475,8 @@ xfs_qm_flush_one(
 	if (!XFS_DQ_IS_DIRTY(dqp))
 		goto out_unlock;
 
-	/*
-	 * The only way the dquot is already flush locked by the time quotacheck
-	 * gets here is if reclaim flushed it before the dqadjust walk dirtied
-	 * it for the final time. Quotacheck collects all dquot bufs in the
-	 * local delwri queue before dquots are dirtied, so reclaim can't have
-	 * possibly queued it for I/O. The only way out is to push the buffer to
-	 * cycle the flush lock.
-	 */
-	if (!xfs_dqflock_nowait(dqp)) {
-		/* buf is pinned in-core by delwri list */
-		error = xfs_buf_incore(mp->m_ddev_targp, dqp->q_blkno,
-				mp->m_quotainfo->qi_dqchunklen, 0, &bp);
-		if (error)
-			goto out_unlock;
-
-		if (!(bp->b_flags & _XBF_DELWRI_Q)) {
-			error = -EAGAIN;
-			xfs_buf_relse(bp);
-			goto out_unlock;
-		}
-		xfs_buf_unlock(bp);
-
-		xfs_buf_delwri_pushbuf(bp, buffer_list);
-		xfs_buf_rele(bp);
-
-		error = -EAGAIN;
-		goto out_unlock;
-	}
+	xfs_qm_dqunpin_wait(dqp);
+	xfs_dqflock(dqp);
 
 	error = xfs_dquot_use_attached_buf(dqp, &bp);
 	if (error)
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index 01d284a1c759..9f0d6bc966b7 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -778,7 +778,6 @@ DEFINE_BUF_EVENT(xfs_buf_iowait_done);
 DEFINE_BUF_EVENT(xfs_buf_delwri_queue);
 DEFINE_BUF_EVENT(xfs_buf_delwri_queued);
 DEFINE_BUF_EVENT(xfs_buf_delwri_split);
-DEFINE_BUF_EVENT(xfs_buf_delwri_pushbuf);
 DEFINE_BUF_EVENT(xfs_buf_get_uncached);
 DEFINE_BUF_EVENT(xfs_buf_item_relse);
 DEFINE_BUF_EVENT(xfs_buf_iodone_async);

From fc48627b9c22f4d18651ca72ba171952d7a26004 Mon Sep 17 00:00:00 2001
From: Dave Chinner <dchinner@redhat.com>
Date: Thu, 26 Jun 2025 08:48:57 +1000
Subject: [PATCH 0948/1334] xfs: add tracepoints for stale pinned inode state
 debug

I needed more insight into how stale inodes were getting stuck on
the AIL after a forced shutdown when running fsstress. These are the
tracepoints I added for that purpose.

Signed-off-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 fs/xfs/xfs_inode_item.c | 5 ++++-
 fs/xfs/xfs_log_cil.c    | 4 +++-
 fs/xfs/xfs_trace.h      | 9 ++++++++-
 fs/xfs/xfs_trans.c      | 4 +++-
 4 files changed, 18 insertions(+), 4 deletions(-)

diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c
index c6cb0b6b9e46..285e27ff89e2 100644
--- a/fs/xfs/xfs_inode_item.c
+++ b/fs/xfs/xfs_inode_item.c
@@ -758,11 +758,14 @@ xfs_inode_item_push(
 		 * completed and items removed from the AIL before the next push
 		 * attempt.
 		 */
+		trace_xfs_inode_push_stale(ip, _RET_IP_);
 		return XFS_ITEM_PINNED;
 	}
 
-	if (xfs_ipincount(ip) > 0 || xfs_buf_ispinned(bp))
+	if (xfs_ipincount(ip) > 0 || xfs_buf_ispinned(bp)) {
+		trace_xfs_inode_push_pinned(ip, _RET_IP_);
 		return XFS_ITEM_PINNED;
+	}
 
 	if (xfs_iflags_test(ip, XFS_IFLUSHING))
 		return XFS_ITEM_FLUSHING;
diff --git a/fs/xfs/xfs_log_cil.c b/fs/xfs/xfs_log_cil.c
index f66d2d430e4f..a80cb6b9969a 100644
--- a/fs/xfs/xfs_log_cil.c
+++ b/fs/xfs/xfs_log_cil.c
@@ -793,8 +793,10 @@ xlog_cil_ail_insert(
 		struct xfs_log_item	*lip = lv->lv_item;
 		xfs_lsn_t		item_lsn;
 
-		if (aborted)
+		if (aborted) {
+			trace_xlog_ail_insert_abort(lip);
 			set_bit(XFS_LI_ABORTED, &lip->li_flags);
+		}
 
 		if (lip->li_ops->flags & XFS_ITEM_RELEASE_WHEN_COMMITTED) {
 			lip->li_ops->iop_release(lip);
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index 9f0d6bc966b7..ba45d801df1c 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -1146,6 +1146,7 @@ DECLARE_EVENT_CLASS(xfs_iref_class,
 		__field(xfs_ino_t, ino)
 		__field(int, count)
 		__field(int, pincount)
+		__field(unsigned long, iflags)
 		__field(unsigned long, caller_ip)
 	),
 	TP_fast_assign(
@@ -1153,13 +1154,15 @@ DECLARE_EVENT_CLASS(xfs_iref_class,
 		__entry->ino = ip->i_ino;
 		__entry->count = atomic_read(&VFS_I(ip)->i_count);
 		__entry->pincount = atomic_read(&ip->i_pincount);
+		__entry->iflags = ip->i_flags;
 		__entry->caller_ip = caller_ip;
 	),
-	TP_printk("dev %d:%d ino 0x%llx count %d pincount %d caller %pS",
+	TP_printk("dev %d:%d ino 0x%llx count %d pincount %d iflags 0x%lx caller %pS",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  __entry->ino,
 		  __entry->count,
 		  __entry->pincount,
+		  __entry->iflags,
 		  (char *)__entry->caller_ip)
 )
 
@@ -1249,6 +1252,8 @@ DEFINE_IREF_EVENT(xfs_irele);
 DEFINE_IREF_EVENT(xfs_inode_pin);
 DEFINE_IREF_EVENT(xfs_inode_unpin);
 DEFINE_IREF_EVENT(xfs_inode_unpin_nowait);
+DEFINE_IREF_EVENT(xfs_inode_push_pinned);
+DEFINE_IREF_EVENT(xfs_inode_push_stale);
 
 DECLARE_EVENT_CLASS(xfs_namespace_class,
 	TP_PROTO(struct xfs_inode *dp, const struct xfs_name *name),
@@ -1653,6 +1658,8 @@ DEFINE_LOG_ITEM_EVENT(xfs_ail_flushing);
 DEFINE_LOG_ITEM_EVENT(xfs_cil_whiteout_mark);
 DEFINE_LOG_ITEM_EVENT(xfs_cil_whiteout_skip);
 DEFINE_LOG_ITEM_EVENT(xfs_cil_whiteout_unpin);
+DEFINE_LOG_ITEM_EVENT(xlog_ail_insert_abort);
+DEFINE_LOG_ITEM_EVENT(xfs_trans_free_abort);
 
 DECLARE_EVENT_CLASS(xfs_ail_class,
 	TP_PROTO(struct xfs_log_item *lip, xfs_lsn_t old_lsn, xfs_lsn_t new_lsn),
diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c
index c6657072361a..b4a07af513ba 100644
--- a/fs/xfs/xfs_trans.c
+++ b/fs/xfs/xfs_trans.c
@@ -742,8 +742,10 @@ xfs_trans_free_items(
 
 	list_for_each_entry_safe(lip, next, &tp->t_items, li_trans) {
 		xfs_trans_del_item(lip);
-		if (abort)
+		if (abort) {
+			trace_xfs_trans_free_abort(lip);
 			set_bit(XFS_LI_ABORTED, &lip->li_flags);
+		}
 		if (lip->li_ops->iop_release)
 			lip->li_ops->iop_release(lip);
 	}

From d2fe5c4c8d25999862d615f616aea7befdd62799 Mon Sep 17 00:00:00 2001
From: Dave Chinner <dchinner@redhat.com>
Date: Thu, 26 Jun 2025 08:48:58 +1000
Subject: [PATCH 0949/1334] xfs: rearrange code in xfs_buf_item.c

The code to initialise, release and free items is all the way down
the bottom of the file. Upcoming fixes need to these functions
earlier in the file, so move them to the top.

There is one code change in this move - the parameter to
xfs_buf_item_relse() is changed from the xfs_buf to the
xfs_buf_log_item - the thing that the function is releasing.

Signed-off-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 fs/xfs/xfs_buf_item.c | 116 +++++++++++++++++++++---------------------
 fs/xfs/xfs_buf_item.h |   1 -
 2 files changed, 58 insertions(+), 59 deletions(-)

diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c
index 90139e0f3271..3e3c0f65a25c 100644
--- a/fs/xfs/xfs_buf_item.c
+++ b/fs/xfs/xfs_buf_item.c
@@ -32,6 +32,61 @@ static inline struct xfs_buf_log_item *BUF_ITEM(struct xfs_log_item *lip)
 	return container_of(lip, struct xfs_buf_log_item, bli_item);
 }
 
+static void
+xfs_buf_item_get_format(
+	struct xfs_buf_log_item	*bip,
+	int			count)
+{
+	ASSERT(bip->bli_formats == NULL);
+	bip->bli_format_count = count;
+
+	if (count == 1) {
+		bip->bli_formats = &bip->__bli_format;
+		return;
+	}
+
+	bip->bli_formats = kzalloc(count * sizeof(struct xfs_buf_log_format),
+				GFP_KERNEL | __GFP_NOFAIL);
+}
+
+static void
+xfs_buf_item_free_format(
+	struct xfs_buf_log_item	*bip)
+{
+	if (bip->bli_formats != &bip->__bli_format) {
+		kfree(bip->bli_formats);
+		bip->bli_formats = NULL;
+	}
+}
+
+static void
+xfs_buf_item_free(
+	struct xfs_buf_log_item	*bip)
+{
+	xfs_buf_item_free_format(bip);
+	kvfree(bip->bli_item.li_lv_shadow);
+	kmem_cache_free(xfs_buf_item_cache, bip);
+}
+
+/*
+ * xfs_buf_item_relse() is called when the buf log item is no longer needed.
+ */
+static void
+xfs_buf_item_relse(
+	struct xfs_buf_log_item	*bip)
+{
+	struct xfs_buf		*bp = bip->bli_buf;
+
+	trace_xfs_buf_item_relse(bp, _RET_IP_);
+
+	ASSERT(!test_bit(XFS_LI_IN_AIL, &bip->bli_item.li_flags));
+	ASSERT(atomic_read(&bip->bli_refcount) == 0);
+
+	bp->b_log_item = NULL;
+	xfs_buf_rele(bp);
+	xfs_buf_item_free(bip);
+}
+
 /* Is this log iovec plausibly large enough to contain the buffer log format? */
 bool
 xfs_buf_log_check_iovec(
@@ -468,7 +523,7 @@ xfs_buf_item_unpin(
 			ASSERT(list_empty(&bp->b_li_list));
 		} else {
 			xfs_trans_ail_delete(lip, SHUTDOWN_LOG_IO_ERROR);
-			xfs_buf_item_relse(bp);
+			xfs_buf_item_relse(bip);
 			ASSERT(bp->b_log_item == NULL);
 		}
 		xfs_buf_relse(bp);
@@ -578,7 +633,7 @@ xfs_buf_item_put(
 	 */
 	if (aborted)
 		xfs_trans_ail_delete(lip, 0);
-	xfs_buf_item_relse(bip->bli_buf);
+	xfs_buf_item_relse(bip);
 	return true;
 }
 
@@ -729,33 +784,6 @@ static const struct xfs_item_ops xfs_buf_item_ops = {
 	.iop_push	= xfs_buf_item_push,
 };
 
-STATIC void
-xfs_buf_item_get_format(
-	struct xfs_buf_log_item	*bip,
-	int			count)
-{
-	ASSERT(bip->bli_formats == NULL);
-	bip->bli_format_count = count;
-
-	if (count == 1) {
-		bip->bli_formats = &bip->__bli_format;
-		return;
-	}
-
-	bip->bli_formats = kzalloc(count * sizeof(struct xfs_buf_log_format),
-				GFP_KERNEL | __GFP_NOFAIL);
-}
-
-STATIC void
-xfs_buf_item_free_format(
-	struct xfs_buf_log_item	*bip)
-{
-	if (bip->bli_formats != &bip->__bli_format) {
-		kfree(bip->bli_formats);
-		bip->bli_formats = NULL;
-	}
-}
-
 /*
  * Allocate a new buf log item to go with the given buffer.
  * Set the buffer's b_log_item field to point to the new
@@ -976,34 +1004,6 @@ xfs_buf_item_dirty_format(
 	return false;
 }
 
-STATIC void
-xfs_buf_item_free(
-	struct xfs_buf_log_item	*bip)
-{
-	xfs_buf_item_free_format(bip);
-	kvfree(bip->bli_item.li_lv_shadow);
-	kmem_cache_free(xfs_buf_item_cache, bip);
-}
-
-/*
- * xfs_buf_item_relse() is called when the buf log item is no longer needed.
- */
-void
-xfs_buf_item_relse(
-	struct xfs_buf	*bp)
-{
-	struct xfs_buf_log_item	*bip = bp->b_log_item;
-
-	trace_xfs_buf_item_relse(bp, _RET_IP_);
-	ASSERT(!test_bit(XFS_LI_IN_AIL, &bip->bli_item.li_flags));
-
-	if (atomic_read(&bip->bli_refcount))
-		return;
-	bp->b_log_item = NULL;
-	xfs_buf_rele(bp);
-	xfs_buf_item_free(bip);
-}
-
 void
 xfs_buf_item_done(
 	struct xfs_buf		*bp)
@@ -1023,5 +1023,5 @@ xfs_buf_item_done(
 	xfs_trans_ail_delete(&bp->b_log_item->bli_item,
 			     (bp->b_flags & _XBF_LOGRECOVERY) ? 0 :
 			     SHUTDOWN_CORRUPT_INCORE);
-	xfs_buf_item_relse(bp);
+	xfs_buf_item_relse(bp->b_log_item);
 }
diff --git a/fs/xfs/xfs_buf_item.h b/fs/xfs/xfs_buf_item.h
index e10e324cd245..50dd79b59cf5 100644
--- a/fs/xfs/xfs_buf_item.h
+++ b/fs/xfs/xfs_buf_item.h
@@ -49,7 +49,6 @@ struct xfs_buf_log_item {
 
 int	xfs_buf_item_init(struct xfs_buf *, struct xfs_mount *);
 void	xfs_buf_item_done(struct xfs_buf *bp);
-void	xfs_buf_item_relse(struct xfs_buf *);
 bool	xfs_buf_item_put(struct xfs_buf_log_item *);
 void	xfs_buf_item_log(struct xfs_buf_log_item *, uint, uint);
 bool	xfs_buf_item_dirty_format(struct xfs_buf_log_item *);

From 816c330b605c3f4813c0dc0ab5af5cce17ff06b3 Mon Sep 17 00:00:00 2001
From: Dave Chinner <dchinner@redhat.com>
Date: Thu, 26 Jun 2025 08:48:59 +1000
Subject: [PATCH 0950/1334] xfs: factor out stale buffer item completion

The stale buffer item completion handling is currently only done
from BLI unpinning. We need to perform this function from where-ever
the last reference to the BLI is dropped, so first we need to
factor this code out into a helper.

Signed-off-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 fs/xfs/xfs_buf_item.c | 60 ++++++++++++++++++++++++++-----------------
 1 file changed, 37 insertions(+), 23 deletions(-)

diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c
index 3e3c0f65a25c..c95826863c82 100644
--- a/fs/xfs/xfs_buf_item.c
+++ b/fs/xfs/xfs_buf_item.c
@@ -444,6 +444,42 @@ xfs_buf_item_pin(
 	atomic_inc(&bip->bli_buf->b_pin_count);
 }
 
+/*
+ * For a stale BLI, process all the necessary completions that must be
+ * performed when the final BLI reference goes away. The buffer will be
+ * referenced and locked here - we return to the caller with the buffer still
+ * referenced and locked for them to finalise processing of the buffer.
+ */
+static void
+xfs_buf_item_finish_stale(
+	struct xfs_buf_log_item	*bip)
+{
+	struct xfs_buf		*bp = bip->bli_buf;
+	struct xfs_log_item	*lip = &bip->bli_item;
+
+	ASSERT(bip->bli_flags & XFS_BLI_STALE);
+	ASSERT(xfs_buf_islocked(bp));
+	ASSERT(bp->b_flags & XBF_STALE);
+	ASSERT(bip->__bli_format.blf_flags & XFS_BLF_CANCEL);
+	ASSERT(list_empty(&lip->li_trans));
+	ASSERT(!bp->b_transp);
+
+	if (bip->bli_flags & XFS_BLI_STALE_INODE) {
+		xfs_buf_item_done(bp);
+		xfs_buf_inode_iodone(bp);
+		ASSERT(list_empty(&bp->b_li_list));
+		return;
+	}
+
+	/*
+	 * We may or may not be on the AIL here, xfs_trans_ail_delete() will do
+	 * the right thing regardless of the situation in which we are called.
+	 */
+	xfs_trans_ail_delete(lip, SHUTDOWN_LOG_IO_ERROR);
+	xfs_buf_item_relse(bip);
+	ASSERT(bp->b_log_item == NULL);
+}
+
 /*
  * This is called to unpin the buffer associated with the buf log item which was
  * previously pinned with a call to xfs_buf_item_pin().  We enter this function
@@ -493,13 +529,6 @@ xfs_buf_item_unpin(
 	}
 
 	if (stale) {
-		ASSERT(bip->bli_flags & XFS_BLI_STALE);
-		ASSERT(xfs_buf_islocked(bp));
-		ASSERT(bp->b_flags & XBF_STALE);
-		ASSERT(bip->__bli_format.blf_flags & XFS_BLF_CANCEL);
-		ASSERT(list_empty(&lip->li_trans));
-		ASSERT(!bp->b_transp);
-
 		trace_xfs_buf_item_unpin_stale(bip);
 
 		/*
@@ -510,22 +539,7 @@ xfs_buf_item_unpin(
 		 * processing is complete.
 		 */
 		xfs_buf_rele(bp);
-
-		/*
-		 * If we get called here because of an IO error, we may or may
-		 * not have the item on the AIL. xfs_trans_ail_delete() will
-		 * take care of that situation. xfs_trans_ail_delete() drops
-		 * the AIL lock.
-		 */
-		if (bip->bli_flags & XFS_BLI_STALE_INODE) {
-			xfs_buf_item_done(bp);
-			xfs_buf_inode_iodone(bp);
-			ASSERT(list_empty(&bp->b_li_list));
-		} else {
-			xfs_trans_ail_delete(lip, SHUTDOWN_LOG_IO_ERROR);
-			xfs_buf_item_relse(bip);
-			ASSERT(bp->b_log_item == NULL);
-		}
+		xfs_buf_item_finish_stale(bip);
 		xfs_buf_relse(bp);
 		return;
 	}

From 7b5f775be14ac1532c049022feadcfe44769566d Mon Sep 17 00:00:00 2001
From: Dave Chinner <dchinner@redhat.com>
Date: Thu, 26 Jun 2025 08:49:00 +1000
Subject: [PATCH 0951/1334] xfs: fix unmount hang with unflushable inodes stuck
 in the AIL

Unmount of a shutdown filesystem can hang with stale inode cluster
buffers in the AIL like so:

[95964.140623] Call Trace:
[95964.144641]  __schedule+0x699/0xb70
[95964.154003]  schedule+0x64/0xd0
[95964.156851]  xfs_ail_push_all_sync+0x9b/0xf0
[95964.164816]  xfs_unmount_flush_inodes+0x41/0x70
[95964.168698]  xfs_unmountfs+0x7f/0x170
[95964.171846]  xfs_fs_put_super+0x3b/0x90
[95964.175216]  generic_shutdown_super+0x77/0x160
[95964.178060]  kill_block_super+0x1b/0x40
[95964.180553]  xfs_kill_sb+0x12/0x30
[95964.182796]  deactivate_locked_super+0x38/0x100
[95964.185735]  deactivate_super+0x41/0x50
[95964.188245]  cleanup_mnt+0x9f/0x160
[95964.190519]  __cleanup_mnt+0x12/0x20
[95964.192899]  task_work_run+0x89/0xb0
[95964.195221]  resume_user_mode_work+0x4f/0x60
[95964.197931]  syscall_exit_to_user_mode+0x76/0xb0
[95964.201003]  do_syscall_64+0x74/0x130

$ pstree -N mnt |grep umount
	     |-check-parallel---nsexec---run_test.sh---753---umount

It always seems to be generic/753 that triggers this, and repeating
a quick group test run triggers it every 10-15 iterations. Hence it
generally triggers once up every 30-40 minutes of test time. just
running generic/753 by itself or concurrently with a limited group
of tests doesn't reproduce this issue at all.

Tracing on a hung system shows the AIL repeating every 50ms a log
force followed by an attempt to push pinned, aborted inodes from the
AIL (trimmed for brevity):

 xfs_log_force:   lsn 0x1c caller xfsaild+0x18e
 xfs_log_force:   lsn 0x0 caller xlog_cil_flush+0xbd
 xfs_log_force:   lsn 0x1c caller xfs_log_force+0x77
 xfs_ail_pinned:  lip 0xffff88826014afa0 lsn 1/37472 type XFS_LI_INODE flags IN_AIL|ABORTED
 xfs_ail_pinned:  lip 0xffff88814000a708 lsn 1/37472 type XFS_LI_INODE flags IN_AIL|ABORTED
 xfs_ail_pinned:  lip 0xffff88810b850c80 lsn 1/37472 type XFS_LI_INODE flags IN_AIL|ABORTED
 xfs_ail_pinned:  lip 0xffff88810b850af0 lsn 1/37472 type XFS_LI_INODE flags IN_AIL|ABORTED
 xfs_ail_pinned:  lip 0xffff888165cf0a28 lsn 1/37472 type XFS_LI_INODE flags IN_AIL|ABORTED
 xfs_ail_pinned:  lip 0xffff88810b850bb8 lsn 1/37472 type XFS_LI_INODE flags IN_AIL|ABORTED
 ....

The inode log items are marked as aborted, which means that either:

a) a transaction commit has occurred, seen an error or shutdown, and
called xfs_trans_free_items() to abort the items. This should happen
before any pinning of log items occurs.

or

b) a dirty transaction has been cancelled. This should also happen
before any pinning of log items occurs.

or

c) AIL insertion at journal IO completion is marked as aborted. In
this case, the log item is pinned by the CIL until journal IO
completes and hence needs to be unpinned. This is then done after
the ->iop_committed() callback is run, so the pin count should be
balanced correctly.

Yet none of these seemed to be occurring. Further tracing indicated
this:

d) Shutdown during CIL pushing resulting in log item completion
being called from checkpoint abort processing. Items are unpinned
and released without serialisation against each other, journal IO
completion or transaction commit completion.

In this case, we may still have a transaction commit in flight that
holds a reference to a xfs_buf_log_item (BLI) after CIL insertion.
e.g. a synchronous transaction will flush the CIL before the
transaction is torn down.  The concurrent CIL push then aborts
insertion it and drops the commit/AIL reference to the BLI. This can
leave the transaction commit context with the last reference to the
BLI which is dropped here:

xfs_trans_free_items()
  ->iop_release
    xfs_buf_item_release
      xfs_buf_item_put
        if (XFS_LI_ABORTED)
	  xfs_trans_ail_delete
	xfs_buf_item_relse()

Unlike the journal completion ->iop_unpin path, this path does not
run stale buffer completion process when it drops the last
reference, hence leaving the stale inodes attached to the buffer
sitting the AIL. There are no other references to those inodes, so
there is no other mechanism to remove them from the AIL. Hence
unmount hangs.

The buffer lock context for stale buffers is passed to the last BLI
reference. This is normally the last BLI unpin on journal IO
completion. The unpin then processes the stale buffer completion and
releases the buffer lock.  However, if the final unpin from journal
IO completion (or CIL push abort) does not hold the last reference
to the BLI, there -must- still be a transaction context that
references the BLI, and so that context must perform the stale
buffer completion processing before the buffer is unlocked and the
BLI torn down.

The fix for this is to rework the xfs_buf_item_relse() path to run
stale buffer completion processing if it drops the last reference to
the BLI. We still hold the buffer locked, so the buffer owner and
lock context is the same as if we passed the BLI and buffer to the
->iop_unpin() context to finish stale process on journal commit.

However, we have to be careful here. In a shutdown state, we can be
freeing dirty BLIs from xfs_buf_item_put() via xfs_trans_brelse()
and xfs_trans_bdetach().  The existing code handles this case by
considering shutdown state as "aborted", but in doing so
largely masks the failure to clean up stale BLI state from the
xfs_buf_item_relse() path. i.e  regardless of the shutdown state and
whether the item is in the AIL, we must finish the stale buffer
cleanup if we are are dropping the last BLI reference from the
->iop_relse path in transaction commit context.

Signed-off-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 fs/xfs/xfs_buf_item.c | 123 +++++++++++++++++++++++++++++-------------
 fs/xfs/xfs_buf_item.h |   2 +-
 2 files changed, 87 insertions(+), 38 deletions(-)

diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c
index c95826863c82..7fc54725c5f6 100644
--- a/fs/xfs/xfs_buf_item.c
+++ b/fs/xfs/xfs_buf_item.c
@@ -612,43 +612,42 @@ xfs_buf_item_push(
  * Drop the buffer log item refcount and take appropriate action. This helper
  * determines whether the bli must be freed or not, since a decrement to zero
  * does not necessarily mean the bli is unused.
- *
- * Return true if the bli is freed, false otherwise.
  */
-bool
+void
 xfs_buf_item_put(
 	struct xfs_buf_log_item	*bip)
 {
-	struct xfs_log_item	*lip = &bip->bli_item;
-	bool			aborted;
-	bool			dirty;
+
+	ASSERT(xfs_buf_islocked(bip->bli_buf));
 
 	/* drop the bli ref and return if it wasn't the last one */
 	if (!atomic_dec_and_test(&bip->bli_refcount))
-		return false;
+		return;
+
+	/* If the BLI is in the AIL, then it is still dirty and in use */
+	if (test_bit(XFS_LI_IN_AIL, &bip->bli_item.li_flags)) {
+		ASSERT(bip->bli_flags & XFS_BLI_DIRTY);
+		return;
+	}
 
 	/*
-	 * We dropped the last ref and must free the item if clean or aborted.
-	 * If the bli is dirty and non-aborted, the buffer was clean in the
-	 * transaction but still awaiting writeback from previous changes. In
-	 * that case, the bli is freed on buffer writeback completion.
+	 * In shutdown conditions, we can be asked to free a dirty BLI that
+	 * isn't in the AIL. This can occur due to a checkpoint aborting a BLI
+	 * instead of inserting it into the AIL at checkpoint IO completion. If
+	 * there's another bli reference (e.g. a btree cursor holds a clean
+	 * reference) and it is released via xfs_trans_brelse(), we can get here
+	 * with that aborted, dirty BLI. In this case, it is safe to free the
+	 * dirty BLI immediately, as it is not in the AIL and there are no
+	 * other references to it.
+	 *
+	 * We should never get here with a stale BLI via that path as
+	 * xfs_trans_brelse() specifically holds onto stale buffers rather than
+	 * releasing them.
 	 */
-	aborted = test_bit(XFS_LI_ABORTED, &lip->li_flags) ||
-			xlog_is_shutdown(lip->li_log);
-	dirty = bip->bli_flags & XFS_BLI_DIRTY;
-	if (dirty && !aborted)
-		return false;
-
-	/*
-	 * The bli is aborted or clean. An aborted item may be in the AIL
-	 * regardless of dirty state.  For example, consider an aborted
-	 * transaction that invalidated a dirty bli and cleared the dirty
-	 * state.
-	 */
-	if (aborted)
-		xfs_trans_ail_delete(lip, 0);
+	ASSERT(!(bip->bli_flags & XFS_BLI_DIRTY) ||
+			test_bit(XFS_LI_ABORTED, &bip->bli_item.li_flags));
+	ASSERT(!(bip->bli_flags & XFS_BLI_STALE));
 	xfs_buf_item_relse(bip);
-	return true;
 }
 
 /*
@@ -669,6 +668,15 @@ xfs_buf_item_put(
  * if necessary but do not unlock the buffer.  This is for support of
  * xfs_trans_bhold(). Make sure the XFS_BLI_HOLD field is cleared if we don't
  * free the item.
+ *
+ * If the XFS_BLI_STALE flag is set, the last reference to the BLI *must*
+ * perform a completion abort of any objects attached to the buffer for IO
+ * tracking purposes. This generally only happens in shutdown situations,
+ * normally xfs_buf_item_unpin() will drop the last BLI reference and perform
+ * completion processing. However, because transaction completion can race with
+ * checkpoint completion during a shutdown, this release context may end up
+ * being the last active reference to the BLI and so needs to perform this
+ * cleanup.
  */
 STATIC void
 xfs_buf_item_release(
@@ -676,18 +684,19 @@ xfs_buf_item_release(
 {
 	struct xfs_buf_log_item	*bip = BUF_ITEM(lip);
 	struct xfs_buf		*bp = bip->bli_buf;
-	bool			released;
 	bool			hold = bip->bli_flags & XFS_BLI_HOLD;
 	bool			stale = bip->bli_flags & XFS_BLI_STALE;
-#if defined(DEBUG) || defined(XFS_WARN)
-	bool			ordered = bip->bli_flags & XFS_BLI_ORDERED;
-	bool			dirty = bip->bli_flags & XFS_BLI_DIRTY;
 	bool			aborted = test_bit(XFS_LI_ABORTED,
 						   &lip->li_flags);
+	bool			dirty = bip->bli_flags & XFS_BLI_DIRTY;
+#if defined(DEBUG) || defined(XFS_WARN)
+	bool			ordered = bip->bli_flags & XFS_BLI_ORDERED;
 #endif
 
 	trace_xfs_buf_item_release(bip);
 
+	ASSERT(xfs_buf_islocked(bp));
+
 	/*
 	 * The bli dirty state should match whether the blf has logged segments
 	 * except for ordered buffers, where only the bli should be dirty.
@@ -703,16 +712,56 @@ xfs_buf_item_release(
 	bp->b_transp = NULL;
 	bip->bli_flags &= ~(XFS_BLI_LOGGED | XFS_BLI_HOLD | XFS_BLI_ORDERED);
 
+	/* If there are other references, then we have nothing to do. */
+	if (!atomic_dec_and_test(&bip->bli_refcount))
+		goto out_release;
+
 	/*
-	 * Unref the item and unlock the buffer unless held or stale. Stale
-	 * buffers remain locked until final unpin unless the bli is freed by
-	 * the unref call. The latter implies shutdown because buffer
-	 * invalidation dirties the bli and transaction.
+	 * Stale buffer completion frees the BLI, unlocks and releases the
+	 * buffer. Neither the BLI or buffer are safe to reference after this
+	 * call, so there's nothing more we need to do here.
+	 *
+	 * If we get here with a stale buffer and references to the BLI remain,
+	 * we must not unlock the buffer as the last BLI reference owns lock
+	 * context, not us.
 	 */
-	released = xfs_buf_item_put(bip);
-	if (hold || (stale && !released))
+	if (stale) {
+		xfs_buf_item_finish_stale(bip);
+		xfs_buf_relse(bp);
+		ASSERT(!hold);
+		return;
+	}
+
+	/*
+	 * Dirty or clean, aborted items are done and need to be removed from
+	 * the AIL and released. This frees the BLI, but leaves the buffer
+	 * locked and referenced.
+	 */
+	if (aborted || xlog_is_shutdown(lip->li_log)) {
+		ASSERT(list_empty(&bip->bli_buf->b_li_list));
+		xfs_buf_item_done(bp);
+		goto out_release;
+	}
+
+	/*
+	 * Clean, unreferenced BLIs can be immediately freed, leaving the buffer
+	 * locked and referenced.
+	 *
+	 * Dirty, unreferenced BLIs *must* be in the AIL awaiting writeback.
+	 */
+	if (!dirty)
+		xfs_buf_item_relse(bip);
+	else
+		ASSERT(test_bit(XFS_LI_IN_AIL, &lip->li_flags));
+
+	/* Not safe to reference the BLI from here */
+out_release:
+	/*
+	 * If we get here with a stale buffer, we must not unlock the
+	 * buffer as the last BLI reference owns lock context, not us.
+	 */
+	if (stale || hold)
 		return;
-	ASSERT(!stale || aborted);
 	xfs_buf_relse(bp);
 }
 
diff --git a/fs/xfs/xfs_buf_item.h b/fs/xfs/xfs_buf_item.h
index 50dd79b59cf5..416890b84f8c 100644
--- a/fs/xfs/xfs_buf_item.h
+++ b/fs/xfs/xfs_buf_item.h
@@ -49,7 +49,7 @@ struct xfs_buf_log_item {
 
 int	xfs_buf_item_init(struct xfs_buf *, struct xfs_mount *);
 void	xfs_buf_item_done(struct xfs_buf *bp);
-bool	xfs_buf_item_put(struct xfs_buf_log_item *);
+void	xfs_buf_item_put(struct xfs_buf_log_item *bip);
 void	xfs_buf_item_log(struct xfs_buf_log_item *, uint, uint);
 bool	xfs_buf_item_dirty_format(struct xfs_buf_log_item *);
 void	xfs_buf_inode_iodone(struct xfs_buf *);

From 615cc4223fcbe1e0e6f68b8494b26bb6c08d917a Mon Sep 17 00:00:00 2001
From: Thomas Zimmermann <tzimmermann@suse.de>
Date: Tue, 17 Jun 2025 16:09:34 +0200
Subject: [PATCH 0952/1334] drm/vesadrm: Avoid NULL-ptr deref in
 vesadrm_pmi_cmap_write()

Only set PMI fields if the screen_info's Vesa PM segment has been
set. Vesa PMI is the power-management interface. It also provides
means to set the color palette. The interface is optional, so not
all VESA graphics cards support it. Print vesafb's warning [1] if
the hardware palette cannot be set at all.

If unsupported the field PrimaryPalette in struct vesadrm.pmi is
NULL, which results in a segmentation fault. Happens with qemu's
Cirrus emulation.

Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>
Fixes: 814d270b31d2 ("drm/sysfb: vesadrm: Add gamma correction")
Link: https://elixir.bootlin.com/linux/v6.15/source/drivers/video/fbdev/vesafb.c#L375 # 1
Cc: Thomas Zimmermann <tzimmermann@suse.de>
Cc: Javier Martinez Canillas <javierm@redhat.com>
Cc: dri-devel@lists.freedesktop.org
Acked-by: Javier Martinez Canillas <javierm@redhat.com>
Link: https://lore.kernel.org/r/20250617140944.142392-1-tzimmermann@suse.de
---
 drivers/gpu/drm/sysfb/vesadrm.c | 13 +++++++++----
 1 file changed, 9 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/sysfb/vesadrm.c b/drivers/gpu/drm/sysfb/vesadrm.c
index 4d62c78e7d1e..f7532db3831f 100644
--- a/drivers/gpu/drm/sysfb/vesadrm.c
+++ b/drivers/gpu/drm/sysfb/vesadrm.c
@@ -362,14 +362,19 @@ static struct vesadrm_device *vesadrm_device_create(struct drm_driver *drv,
 
 	if (!__screen_info_vbe_mode_nonvga(si)) {
 		vesa->cmap_write = vesadrm_vga_cmap_write;
-#if defined(CONFIG_X86_32)
 	} else {
+#if defined(CONFIG_X86_32)
 		phys_addr_t pmi_base = __screen_info_vesapm_info_base(si);
-		const u16 *pmi_addr = phys_to_virt(pmi_base);
 
-		vesa->pmi.PrimaryPalette = (u8 *)pmi_addr + pmi_addr[2];
-		vesa->cmap_write = vesadrm_pmi_cmap_write;
+		if (pmi_base) {
+			const u16 *pmi_addr = phys_to_virt(pmi_base);
+
+			vesa->pmi.PrimaryPalette = (u8 *)pmi_addr + pmi_addr[2];
+			vesa->cmap_write = vesadrm_pmi_cmap_write;
+		} else
 #endif
+		if (format->is_color_indexed)
+			drm_warn(dev, "hardware palette is unchangeable, colors may be incorrect\n");
 	}
 
 #ifdef CONFIG_X86

From 96de8f85203147e3d1e646da891307fa3e462c32 Mon Sep 17 00:00:00 2001
From: Bharadwaj Raju <bharadwaj.raju777@gmail.com>
Date: Fri, 27 Jun 2025 22:11:29 +0530
Subject: [PATCH 0953/1334] bcachefs: mark invalid_btree_id autofix

Checking for invalid IDs was introduced in 9e7cfb35e266 ("bcachefs: Check for invalid btree IDs")
to prevent an invalid shift later, but since 141526548052 ("bcachefs: Bad btree roots are now autofix")
which made btree_root_bkey_invalid autofix, the fsck_err_on call didn't
do anything.

We can mark this err type (invalid_btree_id) autofix as well, so it gets
handled.

Reported-by: syzbot+029d1989099aa5ae3e89@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=029d1989099aa5ae3e89
Fixes: 141526548052 ("bcachefs: Bad btree roots are now autofix")

Signed-off-by: Bharadwaj Raju <bharadwaj.raju777@gmail.com>
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/sb-errors_format.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/bcachefs/sb-errors_format.h b/fs/bcachefs/sb-errors_format.h
index 0641fb634bd4..d154b7651d28 100644
--- a/fs/bcachefs/sb-errors_format.h
+++ b/fs/bcachefs/sb-errors_format.h
@@ -314,7 +314,7 @@ enum bch_fsck_flags {
 	x(accounting_mismatch,					272,	FSCK_AUTOFIX)	\
 	x(accounting_replicas_not_marked,			273,	0)		\
 	x(accounting_to_invalid_device,				289,	0)		\
-	x(invalid_btree_id,					274,	0)		\
+	x(invalid_btree_id,					274,	FSCK_AUTOFIX)		\
 	x(alloc_key_io_time_bad,				275,	0)		\
 	x(alloc_key_fragmentation_lru_wrong,			276,	FSCK_AUTOFIX)	\
 	x(accounting_key_junk_at_end,				277,	FSCK_AUTOFIX)	\

From 1f029b4e30a602db33dedee5ac676e9236ad193c Mon Sep 17 00:00:00 2001
From: Yang Li <yang.li@amlogic.com>
Date: Thu, 19 Jun 2025 11:01:07 +0800
Subject: [PATCH 0954/1334] Bluetooth: Prevent unintended pause by checking if
 advertising is active

When PA Create Sync is enabled, advertising resumes unexpectedly.
Therefore, it's necessary to check whether advertising is currently
active before attempting to pause it.

  < HCI Command: LE Add Device To... (0x08|0x0011) plen 7  #1345 [hci0] 48.306205
  		Address type: Random (0x01)
  		Address: 4F:84:84:5F:88:17 (Resolvable)
  		Identity type: Random (0x01)
  		Identity: FC:5B:8C:F7:5D:FB (Static)
  < HCI Command: LE Set Address Re.. (0x08|0x002d) plen 1  #1347 [hci0] 48.308023
  		Address resolution: Enabled (0x01)
  ...
  < HCI Command: LE Set Extended A.. (0x08|0x0039) plen 6  #1349 [hci0] 48.309650
  		Extended advertising: Enabled (0x01)
  		Number of sets: 1 (0x01)
  		Entry 0
  		Handle: 0x01
  		Duration: 0 ms (0x00)
  		Max ext adv events: 0
  ...
  < HCI Command: LE Periodic Adve.. (0x08|0x0044) plen 14  #1355 [hci0] 48.314575
  		Options: 0x0000
  		Use advertising SID, Advertiser Address Type and address
  		Reporting initially enabled
  		SID: 0x02
  		Adv address type: Random (0x01)
  		Adv address: 4F:84:84:5F:88:17 (Resolvable)
  		Identity type: Random (0x01)
  		Identity: FC:5B:8C:F7:5D:FB (Static)
  		Skip: 0x0000
  		Sync timeout: 20000 msec (0x07d0)
  		Sync CTE type: 0x0000

Fixes: ad383c2c65a5 ("Bluetooth: hci_sync: Enable advertising when LL privacy is enabled")
Signed-off-by: Yang Li <yang.li@amlogic.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/hci_sync.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c
index 6687f2a4d1eb..42d3696227af 100644
--- a/net/bluetooth/hci_sync.c
+++ b/net/bluetooth/hci_sync.c
@@ -2481,6 +2481,10 @@ static int hci_pause_advertising_sync(struct hci_dev *hdev)
 	int err;
 	int old_state;
 
+	/* If controller is not advertising we are done. */
+	if (!hci_dev_test_flag(hdev, HCI_LE_ADV))
+		return 0;
+
 	/* If already been paused there is nothing to do. */
 	if (hdev->advertising_paused)
 		return 0;

From 1e6ed33cabba8f06f532f2e5851a102602823734 Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Sat, 7 Jun 2025 13:43:32 +0100
Subject: [PATCH 0955/1334] btrfs: fix failure to rebuild free space tree using
 multiple transactions

If we are rebuilding a free space tree, while modifying the free space
tree we may need to allocate a new metadata block group.
If we end up using multiple transactions for the rebuild, when we call
btrfs_end_transaction() we enter btrfs_create_pending_block_groups()
which calls add_block_group_free_space() to add items to the free space
tree for the block group.

Then later during the free space tree rebuild, at
btrfs_rebuild_free_space_tree(), we may find such new block groups
and call populate_free_space_tree() for them, which fails with -EEXIST
because there are already items in the free space tree. Then we abort the
transaction with -EEXIST at btrfs_rebuild_free_space_tree().
Notice that we say "may find" the new block groups because a new block
group may be inserted in the block groups rbtree, which is being iterated
by the rebuild process, before or after the current node where the rebuild
process is currently at.

Syzbot recently reported such case which produces a trace like the
following:

  ------------[ cut here ]------------
  BTRFS: Transaction aborted (error -17)
  WARNING: CPU: 1 PID: 7626 at fs/btrfs/free-space-tree.c:1341 btrfs_rebuild_free_space_tree+0x470/0x54c fs/btrfs/free-space-tree.c:1341
  Modules linked in:
  CPU: 1 UID: 0 PID: 7626 Comm: syz.2.25 Not tainted 6.15.0-rc7-syzkaller-00085-gd7fa1af5b33e-dirty #0 PREEMPT
  Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 05/07/2025
  pstate: 60400005 (nZCv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--)
  pc : btrfs_rebuild_free_space_tree+0x470/0x54c fs/btrfs/free-space-tree.c:1341
  lr : btrfs_rebuild_free_space_tree+0x470/0x54c fs/btrfs/free-space-tree.c:1341
  sp : ffff80009c4f7740
  x29: ffff80009c4f77b0 x28: ffff0000d4c3f400 x27: 0000000000000000
  x26: dfff800000000000 x25: ffff70001389eee8 x24: 0000000000000003
  x23: 1fffe000182b6e7b x22: 0000000000000000 x21: ffff0000c15b73d8
  x20: 00000000ffffffef x19: ffff0000c15b7378 x18: 1fffe0003386f276
  x17: ffff80008f31e000 x16: ffff80008adbe98c x15: 0000000000000001
  x14: 1fffe0001b281550 x13: 0000000000000000 x12: 0000000000000000
  x11: ffff60001b281551 x10: 0000000000000003 x9 : 1c8922000a902c00
  x8 : 1c8922000a902c00 x7 : ffff800080485878 x6 : 0000000000000000
  x5 : 0000000000000001 x4 : 0000000000000001 x3 : ffff80008047843c
  x2 : 0000000000000001 x1 : ffff80008b3ebc40 x0 : 0000000000000001
  Call trace:
   btrfs_rebuild_free_space_tree+0x470/0x54c fs/btrfs/free-space-tree.c:1341 (P)
   btrfs_start_pre_rw_mount+0xa78/0xe10 fs/btrfs/disk-io.c:3074
   btrfs_remount_rw fs/btrfs/super.c:1319 [inline]
   btrfs_reconfigure+0x828/0x2418 fs/btrfs/super.c:1543
   reconfigure_super+0x1d4/0x6f0 fs/super.c:1083
   do_remount fs/namespace.c:3365 [inline]
   path_mount+0xb34/0xde0 fs/namespace.c:4200
   do_mount fs/namespace.c:4221 [inline]
   __do_sys_mount fs/namespace.c:4432 [inline]
   __se_sys_mount fs/namespace.c:4409 [inline]
   __arm64_sys_mount+0x3e8/0x468 fs/namespace.c:4409
   __invoke_syscall arch/arm64/kernel/syscall.c:35 [inline]
   invoke_syscall+0x98/0x2b8 arch/arm64/kernel/syscall.c:49
   el0_svc_common+0x130/0x23c arch/arm64/kernel/syscall.c:132
   do_el0_svc+0x48/0x58 arch/arm64/kernel/syscall.c:151
   el0_svc+0x58/0x17c arch/arm64/kernel/entry-common.c:767
   el0t_64_sync_handler+0x78/0x108 arch/arm64/kernel/entry-common.c:786
   el0t_64_sync+0x198/0x19c arch/arm64/kernel/entry.S:600
  irq event stamp: 330
  hardirqs last  enabled at (329): [<ffff80008048590c>] raw_spin_rq_unlock_irq kernel/sched/sched.h:1525 [inline]
  hardirqs last  enabled at (329): [<ffff80008048590c>] finish_lock_switch+0xb0/0x1c0 kernel/sched/core.c:5130
  hardirqs last disabled at (330): [<ffff80008adb9e60>] el1_dbg+0x24/0x80 arch/arm64/kernel/entry-common.c:511
  softirqs last  enabled at (10): [<ffff8000801fbf10>] local_bh_enable+0x10/0x34 include/linux/bottom_half.h:32
  softirqs last disabled at (8): [<ffff8000801fbedc>] local_bh_disable+0x10/0x34 include/linux/bottom_half.h:19
  ---[ end trace 0000000000000000 ]---

Fix this by flagging new block groups which had their free space tree
entries already added and then skip them in the rebuild process. Also,
since the rebuild may be triggered when doing a remount, make sure that
when we clear an existing free space tree that we clear such flag from
every existing block group, otherwise we would skip those block groups
during the rebuild.

Reported-by: syzbot+d0014fb0fc39c5487ae5@syzkaller.appspotmail.com
Link: https://lore.kernel.org/linux-btrfs/68460a54.050a0220.daf97.0af5.GAE@google.com/
Fixes: 882af9f13e83 ("btrfs: handle free space tree rebuild in multiple transactions")
Reviewed-by: Boris Burkov <boris@bur.io>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/block-group.h     |  2 ++
 fs/btrfs/free-space-tree.c | 40 ++++++++++++++++++++++++++++++++++++++
 2 files changed, 42 insertions(+)

diff --git a/fs/btrfs/block-group.h b/fs/btrfs/block-group.h
index 9de356bcb411..aa176cc9a324 100644
--- a/fs/btrfs/block-group.h
+++ b/fs/btrfs/block-group.h
@@ -83,6 +83,8 @@ enum btrfs_block_group_flags {
 	BLOCK_GROUP_FLAG_ZONED_DATA_RELOC,
 	/* Does the block group need to be added to the free space tree? */
 	BLOCK_GROUP_FLAG_NEEDS_FREE_SPACE,
+	/* Set after we add a new block group to the free space tree. */
+	BLOCK_GROUP_FLAG_FREE_SPACE_ADDED,
 	/* Indicate that the block group is placed on a sequential zone */
 	BLOCK_GROUP_FLAG_SEQUENTIAL_ZONE,
 	/*
diff --git a/fs/btrfs/free-space-tree.c b/fs/btrfs/free-space-tree.c
index a3e2a2a81461..a83c268f7f87 100644
--- a/fs/btrfs/free-space-tree.c
+++ b/fs/btrfs/free-space-tree.c
@@ -1241,6 +1241,7 @@ static int clear_free_space_tree(struct btrfs_trans_handle *trans,
 {
 	BTRFS_PATH_AUTO_FREE(path);
 	struct btrfs_key key;
+	struct rb_node *node;
 	int nr;
 	int ret;
 
@@ -1269,6 +1270,16 @@ static int clear_free_space_tree(struct btrfs_trans_handle *trans,
 		btrfs_release_path(path);
 	}
 
+	node = rb_first_cached(&trans->fs_info->block_group_cache_tree);
+	while (node) {
+		struct btrfs_block_group *bg;
+
+		bg = rb_entry(node, struct btrfs_block_group, cache_node);
+		clear_bit(BLOCK_GROUP_FLAG_FREE_SPACE_ADDED, &bg->runtime_flags);
+		node = rb_next(node);
+		cond_resched();
+	}
+
 	return 0;
 }
 
@@ -1358,12 +1369,18 @@ int btrfs_rebuild_free_space_tree(struct btrfs_fs_info *fs_info)
 
 		block_group = rb_entry(node, struct btrfs_block_group,
 				       cache_node);
+
+		if (test_bit(BLOCK_GROUP_FLAG_FREE_SPACE_ADDED,
+			     &block_group->runtime_flags))
+			goto next;
+
 		ret = populate_free_space_tree(trans, block_group);
 		if (ret) {
 			btrfs_abort_transaction(trans, ret);
 			btrfs_end_transaction(trans);
 			return ret;
 		}
+next:
 		if (btrfs_should_end_transaction(trans)) {
 			btrfs_end_transaction(trans);
 			trans = btrfs_start_transaction(free_space_root, 1);
@@ -1390,6 +1407,29 @@ static int __add_block_group_free_space(struct btrfs_trans_handle *trans,
 
 	clear_bit(BLOCK_GROUP_FLAG_NEEDS_FREE_SPACE, &block_group->runtime_flags);
 
+	/*
+	 * While rebuilding the free space tree we may allocate new metadata
+	 * block groups while modifying the free space tree.
+	 *
+	 * Because during the rebuild (at btrfs_rebuild_free_space_tree()) we
+	 * can use multiple transactions, every time btrfs_end_transaction() is
+	 * called at btrfs_rebuild_free_space_tree() we finish the creation of
+	 * new block groups by calling btrfs_create_pending_block_groups(), and
+	 * that in turn calls us, through add_block_group_free_space(), to add
+	 * a free space info item and a free space extent item for the block
+	 * group.
+	 *
+	 * Then later btrfs_rebuild_free_space_tree() may find such new block
+	 * groups and processes them with populate_free_space_tree(), which can
+	 * fail with EEXIST since there are already items for the block group in
+	 * the free space tree. Notice that we say "may find" because a new
+	 * block group may be added to the block groups rbtree in a node before
+	 * or after the block group currently being processed by the rebuild
+	 * process. So signal the rebuild process to skip such new block groups
+	 * if it finds them.
+	 */
+	set_bit(BLOCK_GROUP_FLAG_FREE_SPACE_ADDED, &block_group->runtime_flags);
+
 	ret = add_new_free_space_info(trans, block_group, path);
 	if (ret)
 		return ret;

From 6561a40ceced9082f50c374a22d5966cf9fc5f5c Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Wed, 18 Jun 2025 16:57:07 +0100
Subject: [PATCH 0956/1334] btrfs: fix missing error handling when searching
 for inode refs during log replay

During log replay, at __add_inode_ref(), when we are searching for inode
ref keys we totally ignore if btrfs_search_slot() returns an error. This
may make a log replay succeed when there was an actual error and leave
some metadata inconsistency in a subvolume tree. Fix this by checking if
an error was returned from btrfs_search_slot() and if so, return it to
the caller.

Fixes: e02119d5a7b4 ("Btrfs: Add a write ahead tree log to optimize synchronous operations")
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/tree-log.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 858b609e292c..8b66173d9023 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -1073,7 +1073,9 @@ again:
 	search_key.type = BTRFS_INODE_REF_KEY;
 	search_key.offset = parent_objectid;
 	ret = btrfs_search_slot(NULL, root, &search_key, path, 0, 0);
-	if (ret == 0) {
+	if (ret < 0) {
+		return ret;
+	} else if (ret == 0) {
 		struct btrfs_inode_ref *victim_ref;
 		unsigned long ptr;
 		unsigned long ptr_end;

From 54a7081ed168b72a8a2d6ef4ba3a1259705a2926 Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Mon, 23 Jun 2025 12:11:58 +0100
Subject: [PATCH 0957/1334] btrfs: fix iteration of extrefs during log replay

At __inode_add_ref() when processing extrefs, if we jump into the next
label we have an undefined value of victim_name.len, since we haven't
initialized it before we did the goto. This results in an invalid memory
access in the next iteration of the loop since victim_name.len was not
initialized to the length of the name of the current extref.

Fix this by initializing victim_name.len with the current extref's name
length.

Fixes: e43eec81c516 ("btrfs: use struct qstr instead of name and namelen pairs")
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/tree-log.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 8b66173d9023..d514bf531b3b 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -1148,13 +1148,13 @@ again:
 			struct fscrypt_str victim_name;
 
 			extref = (struct btrfs_inode_extref *)(base + cur_offset);
+			victim_name.len = btrfs_inode_extref_name_len(leaf, extref);
 
 			if (btrfs_inode_extref_parent(leaf, extref) != parent_objectid)
 				goto next;
 
 			ret = read_alloc_one_name(leaf, &extref->name,
-				 btrfs_inode_extref_name_len(leaf, extref),
-				 &victim_name);
+						  victim_name.len, &victim_name);
 			if (ret)
 				return ret;
 

From 5f61b961599acbd2bed028d3089105a1f7d224b8 Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Wed, 18 Jun 2025 15:58:31 +0100
Subject: [PATCH 0958/1334] btrfs: fix inode lookup error handling during log
 replay

When replaying log trees we use read_one_inode() to get an inode, which is
just a wrapper around btrfs_iget_logging(), which in turn is a wrapper for
btrfs_iget(). But read_one_inode() always returns NULL for any error
that btrfs_iget_logging() / btrfs_iget() may return and this is a problem
because:

1) In many callers of read_one_inode() we convert the NULL into -EIO,
   which is not accurate since btrfs_iget() may return -ENOMEM and -ENOENT
   for example, besides -EIO and other errors. So during log replay we
   may end up reporting a false -EIO, which is confusing since we may
   not have had any IO error at all;

2) When replaying directory deletes, at replay_dir_deletes(), we assume
   the NULL returned from read_one_inode() means that the inode doesn't
   exist and then proceed as if no error had happened. This is wrong
   because unless btrfs_iget() returned ERR_PTR(-ENOENT), we had an
   actual error and the target inode may exist in the target subvolume
   root - this may later result in the log replay code failing at a
   later stage (if we are "lucky") or succeed but leaving some
   inconsistency in the filesystem.

So fix this by not ignoring errors from btrfs_iget_logging() and as
a consequence remove the read_one_inode() wrapper and just use
btrfs_iget_logging() directly. Also since btrfs_iget_logging() is
supposed to be called only against subvolume roots, just like
read_one_inode() which had a comment about it, add an assertion to
btrfs_iget_logging() to check that the target root corresponds to a
subvolume root.

Fixes: 5d4f98a28c7d ("Btrfs: Mixed back reference  (FORWARD ROLLING FORMAT CHANGE)")
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/tree-log.c | 127 +++++++++++++++++++++-----------------------
 1 file changed, 62 insertions(+), 65 deletions(-)

diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index d514bf531b3b..8cf5e5ae593c 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -143,6 +143,9 @@ static struct btrfs_inode *btrfs_iget_logging(u64 objectid, struct btrfs_root *r
 	unsigned int nofs_flag;
 	struct btrfs_inode *inode;
 
+	/* Only meant to be called for subvolume roots and not for log roots. */
+	ASSERT(is_fstree(btrfs_root_id(root)));
+
 	/*
 	 * We're holding a transaction handle whether we are logging or
 	 * replaying a log tree, so we must make sure NOFS semantics apply
@@ -604,21 +607,6 @@ static int read_alloc_one_name(struct extent_buffer *eb, void *start, int len,
 	return 0;
 }
 
-/*
- * simple helper to read an inode off the disk from a given root
- * This can only be called for subvolume roots and not for the log
- */
-static noinline struct btrfs_inode *read_one_inode(struct btrfs_root *root,
-						   u64 objectid)
-{
-	struct btrfs_inode *inode;
-
-	inode = btrfs_iget_logging(objectid, root);
-	if (IS_ERR(inode))
-		return NULL;
-	return inode;
-}
-
 /* replays a single extent in 'eb' at 'slot' with 'key' into the
  * subvolume 'root'.  path is released on entry and should be released
  * on exit.
@@ -674,9 +662,9 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans,
 		return -EUCLEAN;
 	}
 
-	inode = read_one_inode(root, key->objectid);
-	if (!inode)
-		return -EIO;
+	inode = btrfs_iget_logging(key->objectid, root);
+	if (IS_ERR(inode))
+		return PTR_ERR(inode);
 
 	/*
 	 * first check to see if we already have this extent in the
@@ -948,9 +936,10 @@ static noinline int drop_one_dir_item(struct btrfs_trans_handle *trans,
 
 	btrfs_release_path(path);
 
-	inode = read_one_inode(root, location.objectid);
-	if (!inode) {
-		ret = -EIO;
+	inode = btrfs_iget_logging(location.objectid, root);
+	if (IS_ERR(inode)) {
+		ret = PTR_ERR(inode);
+		inode = NULL;
 		goto out;
 	}
 
@@ -1169,10 +1158,10 @@ again:
 				kfree(victim_name.name);
 				return ret;
 			} else if (!ret) {
-				ret = -ENOENT;
-				victim_parent = read_one_inode(root,
-						parent_objectid);
-				if (victim_parent) {
+				victim_parent = btrfs_iget_logging(parent_objectid, root);
+				if (IS_ERR(victim_parent)) {
+					ret = PTR_ERR(victim_parent);
+				} else {
 					inc_nlink(&inode->vfs_inode);
 					btrfs_release_path(path);
 
@@ -1317,9 +1306,9 @@ again:
 			struct btrfs_inode *dir;
 
 			btrfs_release_path(path);
-			dir = read_one_inode(root, parent_id);
-			if (!dir) {
-				ret = -ENOENT;
+			dir = btrfs_iget_logging(parent_id, root);
+			if (IS_ERR(dir)) {
+				ret = PTR_ERR(dir);
 				kfree(name.name);
 				goto out;
 			}
@@ -1391,15 +1380,17 @@ static noinline int add_inode_ref(struct btrfs_trans_handle *trans,
 	 * copy the back ref in.  The link count fixup code will take
 	 * care of the rest
 	 */
-	dir = read_one_inode(root, parent_objectid);
-	if (!dir) {
-		ret = -ENOENT;
+	dir = btrfs_iget_logging(parent_objectid, root);
+	if (IS_ERR(dir)) {
+		ret = PTR_ERR(dir);
+		dir = NULL;
 		goto out;
 	}
 
-	inode = read_one_inode(root, inode_objectid);
-	if (!inode) {
-		ret = -EIO;
+	inode = btrfs_iget_logging(inode_objectid, root);
+	if (IS_ERR(inode)) {
+		ret = PTR_ERR(inode);
+		inode = NULL;
 		goto out;
 	}
 
@@ -1411,11 +1402,13 @@ static noinline int add_inode_ref(struct btrfs_trans_handle *trans,
 			 * parent object can change from one array
 			 * item to another.
 			 */
-			if (!dir)
-				dir = read_one_inode(root, parent_objectid);
 			if (!dir) {
-				ret = -ENOENT;
-				goto out;
+				dir = btrfs_iget_logging(parent_objectid, root);
+				if (IS_ERR(dir)) {
+					ret = PTR_ERR(dir);
+					dir = NULL;
+					goto out;
+				}
 			}
 		} else {
 			ret = ref_get_fields(eb, ref_ptr, &name, &ref_index);
@@ -1684,9 +1677,9 @@ static noinline int fixup_inode_link_counts(struct btrfs_trans_handle *trans,
 			break;
 
 		btrfs_release_path(path);
-		inode = read_one_inode(root, key.offset);
-		if (!inode) {
-			ret = -EIO;
+		inode = btrfs_iget_logging(key.offset, root);
+		if (IS_ERR(inode)) {
+			ret = PTR_ERR(inode);
 			break;
 		}
 
@@ -1722,9 +1715,9 @@ static noinline int link_to_fixup_dir(struct btrfs_trans_handle *trans,
 	struct btrfs_inode *inode;
 	struct inode *vfs_inode;
 
-	inode = read_one_inode(root, objectid);
-	if (!inode)
-		return -EIO;
+	inode = btrfs_iget_logging(objectid, root);
+	if (IS_ERR(inode))
+		return PTR_ERR(inode);
 
 	vfs_inode = &inode->vfs_inode;
 	key.objectid = BTRFS_TREE_LOG_FIXUP_OBJECTID;
@@ -1763,14 +1756,14 @@ static noinline int insert_one_name(struct btrfs_trans_handle *trans,
 	struct btrfs_inode *dir;
 	int ret;
 
-	inode = read_one_inode(root, location->objectid);
-	if (!inode)
-		return -ENOENT;
+	inode = btrfs_iget_logging(location->objectid, root);
+	if (IS_ERR(inode))
+		return PTR_ERR(inode);
 
-	dir = read_one_inode(root, dirid);
-	if (!dir) {
+	dir = btrfs_iget_logging(dirid, root);
+	if (IS_ERR(dir)) {
 		iput(&inode->vfs_inode);
-		return -EIO;
+		return PTR_ERR(dir);
 	}
 
 	ret = btrfs_add_link(trans, dir, inode, name, 1, index);
@@ -1847,9 +1840,9 @@ static noinline int replay_one_name(struct btrfs_trans_handle *trans,
 	bool update_size = true;
 	bool name_added = false;
 
-	dir = read_one_inode(root, key->objectid);
-	if (!dir)
-		return -EIO;
+	dir = btrfs_iget_logging(key->objectid, root);
+	if (IS_ERR(dir))
+		return PTR_ERR(dir);
 
 	ret = read_alloc_one_name(eb, di + 1, btrfs_dir_name_len(eb, di), &name);
 	if (ret)
@@ -2149,9 +2142,10 @@ static noinline int check_item_in_log(struct btrfs_trans_handle *trans,
 	btrfs_dir_item_key_to_cpu(eb, di, &location);
 	btrfs_release_path(path);
 	btrfs_release_path(log_path);
-	inode = read_one_inode(root, location.objectid);
-	if (!inode) {
-		ret = -EIO;
+	inode = btrfs_iget_logging(location.objectid, root);
+	if (IS_ERR(inode)) {
+		ret = PTR_ERR(inode);
+		inode = NULL;
 		goto out;
 	}
 
@@ -2303,14 +2297,17 @@ static noinline int replay_dir_deletes(struct btrfs_trans_handle *trans,
 	if (!log_path)
 		return -ENOMEM;
 
-	dir = read_one_inode(root, dirid);
-	/* it isn't an error if the inode isn't there, that can happen
-	 * because we replay the deletes before we copy in the inode item
-	 * from the log
+	dir = btrfs_iget_logging(dirid, root);
+	/*
+	 * It isn't an error if the inode isn't there, that can happen because
+	 * we replay the deletes before we copy in the inode item from the log.
 	 */
-	if (!dir) {
+	if (IS_ERR(dir)) {
 		btrfs_free_path(log_path);
-		return 0;
+		ret = PTR_ERR(dir);
+		if (ret == -ENOENT)
+			ret = 0;
+		return ret;
 	}
 
 	range_start = 0;
@@ -2469,9 +2466,9 @@ static int replay_one_buffer(struct btrfs_root *log, struct extent_buffer *eb,
 				struct btrfs_inode *inode;
 				u64 from;
 
-				inode = read_one_inode(root, key.objectid);
-				if (!inode) {
-					ret = -EIO;
+				inode = btrfs_iget_logging(key.objectid, root);
+				if (IS_ERR(inode)) {
+					ret = PTR_ERR(inode);
 					break;
 				}
 				from = ALIGN(i_size_read(&inode->vfs_inode),

From bf5bcf9a6fa070ec8a725b08db63fb1318f77366 Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Thu, 19 Jun 2025 13:13:38 +0100
Subject: [PATCH 0959/1334] btrfs: record new subvolume in parent dir earlier
 to avoid dir logging races

Instead of recording that a new subvolume was created in a directory after
we add the entry do the directory, record it before adding the entry. This
is to avoid races where after creating the entry and before recording the
new subvolume in the directory (the call to btrfs_record_new_subvolume()),
another task logs the directory, so we end up with a log tree where we
logged a directory that has an entry pointing to a root that was not yet
committed, resulting in an invalid entry if the log is persisted and
replayed later due to a power failure or crash.

Also state this requirement in the function comment for
btrfs_record_new_subvolume(), similar to what we do for the
btrfs_record_unlink_dir() and btrfs_record_snapshot_destroy().

Fixes: 45c4102f0d82 ("btrfs: avoid transaction commit on any fsync after subvolume creation")
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/ioctl.c    | 4 ++--
 fs/btrfs/tree-log.c | 2 ++
 2 files changed, 4 insertions(+), 2 deletions(-)

diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 1e8f7082239c..e6f7d24e3b47 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -666,14 +666,14 @@ static noinline int create_subvol(struct mnt_idmap *idmap,
 		goto out;
 	}
 
+	btrfs_record_new_subvolume(trans, BTRFS_I(dir));
+
 	ret = btrfs_create_new_inode(trans, &new_inode_args);
 	if (ret) {
 		btrfs_abort_transaction(trans, ret);
 		goto out;
 	}
 
-	btrfs_record_new_subvolume(trans, BTRFS_I(dir));
-
 	d_instantiate_new(dentry, new_inode_args.inode);
 	new_inode_args.inode = NULL;
 
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 8cf5e5ae593c..cea8a7e9d6d3 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -7447,6 +7447,8 @@ void btrfs_record_snapshot_destroy(struct btrfs_trans_handle *trans,
  * full log sync.
  * Also we don't need to worry with renames, since btrfs_rename() marks the log
  * for full commit when renaming a subvolume.
+ *
+ * Must be called before creating the subvolume entry in its parent directory.
  */
 void btrfs_record_new_subvolume(const struct btrfs_trans_handle *trans,
 				struct btrfs_inode *dir)

From c466e33e729a0ee017d10d919cba18f503853c60 Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Fri, 20 Jun 2025 15:54:05 +0100
Subject: [PATCH 0960/1334] btrfs: propagate last_unlink_trans earlier when
 doing a rmdir

In case the removed directory had a snapshot that was deleted, we are
propagating its inode's last_unlink_trans to the parent directory after
we removed the entry from the parent directory. This leaves a small race
window where someone can log the parent directory after we removed the
entry and before we updated last_unlink_trans, and as a result if we ever
try to replay such a log tree, we will fail since we will attempt to
remove a snapshot during log replay, which is currently not possible and
results in the log replay (and mount) to fail. This is the type of failure
described in commit 1ec9a1ae1e30 ("Btrfs: fix unreplayable log after
snapshot delete + parent dir fsync").

So fix this by propagating the last_unlink_trans to the parent directory
before we remove the entry from it.

Fixes: 44f714dae50a ("Btrfs: improve performance on fsync against new inode after rename/unlink")
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/inode.c | 36 ++++++++++++++++++------------------
 1 file changed, 18 insertions(+), 18 deletions(-)

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 26d6ed170a19..5a5c43586adf 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -4710,7 +4710,6 @@ static int btrfs_rmdir(struct inode *dir, struct dentry *dentry)
 	struct btrfs_fs_info *fs_info = BTRFS_I(inode)->root->fs_info;
 	int ret = 0;
 	struct btrfs_trans_handle *trans;
-	u64 last_unlink_trans;
 	struct fscrypt_name fname;
 
 	if (inode->i_size > BTRFS_EMPTY_DIR_SIZE)
@@ -4736,6 +4735,23 @@ static int btrfs_rmdir(struct inode *dir, struct dentry *dentry)
 		goto out_notrans;
 	}
 
+	/*
+	 * Propagate the last_unlink_trans value of the deleted dir to its
+	 * parent directory. This is to prevent an unrecoverable log tree in the
+	 * case we do something like this:
+	 * 1) create dir foo
+	 * 2) create snapshot under dir foo
+	 * 3) delete the snapshot
+	 * 4) rmdir foo
+	 * 5) mkdir foo
+	 * 6) fsync foo or some file inside foo
+	 *
+	 * This is because we can't unlink other roots when replaying the dir
+	 * deletes for directory foo.
+	 */
+	if (BTRFS_I(inode)->last_unlink_trans >= trans->transid)
+		BTRFS_I(dir)->last_unlink_trans = BTRFS_I(inode)->last_unlink_trans;
+
 	if (unlikely(btrfs_ino(BTRFS_I(inode)) == BTRFS_EMPTY_SUBVOL_DIR_OBJECTID)) {
 		ret = btrfs_unlink_subvol(trans, BTRFS_I(dir), dentry);
 		goto out;
@@ -4745,27 +4761,11 @@ static int btrfs_rmdir(struct inode *dir, struct dentry *dentry)
 	if (ret)
 		goto out;
 
-	last_unlink_trans = BTRFS_I(inode)->last_unlink_trans;
-
 	/* now the directory is empty */
 	ret = btrfs_unlink_inode(trans, BTRFS_I(dir), BTRFS_I(d_inode(dentry)),
 				 &fname.disk_name);
-	if (!ret) {
+	if (!ret)
 		btrfs_i_size_write(BTRFS_I(inode), 0);
-		/*
-		 * Propagate the last_unlink_trans value of the deleted dir to
-		 * its parent directory. This is to prevent an unrecoverable
-		 * log tree in the case we do something like this:
-		 * 1) create dir foo
-		 * 2) create snapshot under dir foo
-		 * 3) delete the snapshot
-		 * 4) rmdir foo
-		 * 5) mkdir foo
-		 * 6) fsync foo or some file inside foo
-		 */
-		if (last_unlink_trans >= trans->transid)
-			BTRFS_I(dir)->last_unlink_trans = last_unlink_trans;
-	}
 out:
 	btrfs_end_transaction(trans);
 out_notrans:

From 157501b0469969fc1ba53add5049575aadd79d80 Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Fri, 20 Jun 2025 16:37:01 +0100
Subject: [PATCH 0961/1334] btrfs: use btrfs_record_snapshot_destroy() during
 rmdir

We are setting the parent directory's last_unlink_trans directly which
may result in a concurrent task starting to log the directory not see the
update and therefore can log the directory after we removed a child
directory which had a snapshot within instead of falling back to a
transaction commit. Replaying such a log tree would result in a mount
failure since we can't currently delete snapshots (and subvolumes) during
log replay. This is the type of failure described in commit 1ec9a1ae1e30
("Btrfs: fix unreplayable log after snapshot delete + parent dir fsync").

Fix this by using btrfs_record_snapshot_destroy() which updates the
last_unlink_trans field while holding the inode's log_mutex lock.

Fixes: 44f714dae50a ("Btrfs: improve performance on fsync against new inode after rename/unlink")
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/inode.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 5a5c43586adf..fc66872b4c74 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -4750,7 +4750,7 @@ static int btrfs_rmdir(struct inode *dir, struct dentry *dentry)
 	 * deletes for directory foo.
 	 */
 	if (BTRFS_I(inode)->last_unlink_trans >= trans->transid)
-		BTRFS_I(dir)->last_unlink_trans = BTRFS_I(inode)->last_unlink_trans;
+		btrfs_record_snapshot_destroy(trans, BTRFS_I(dir));
 
 	if (unlikely(btrfs_ino(BTRFS_I(inode)) == BTRFS_EMPTY_SUBVOL_DIR_OBJECTID)) {
 		ret = btrfs_unlink_subvol(trans, BTRFS_I(dir), dentry);

From 46c0d947b64ac8efcf89dd754213dab5d1bd00aa Mon Sep 17 00:00:00 2001
From: Christian Eggers <ceggers@arri.de>
Date: Wed, 25 Jun 2025 15:09:29 +0200
Subject: [PATCH 0962/1334] Bluetooth: hci_sync: revert some mesh modifications

This reverts minor parts of the changes made in commit b338d91703fa
("Bluetooth: Implement support for Mesh"). It looks like these changes
were only made for development purposes but shouldn't have been part of
the commit.

Fixes: b338d91703fa ("Bluetooth: Implement support for Mesh")
Cc: stable@vger.kernel.org
Signed-off-by: Christian Eggers <ceggers@arri.de>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/hci_sync.c | 16 ++++------------
 1 file changed, 4 insertions(+), 12 deletions(-)

diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c
index 42d3696227af..106862d47964 100644
--- a/net/bluetooth/hci_sync.c
+++ b/net/bluetooth/hci_sync.c
@@ -1970,13 +1970,10 @@ static int hci_clear_adv_sets_sync(struct hci_dev *hdev, struct sock *sk)
 static int hci_clear_adv_sync(struct hci_dev *hdev, struct sock *sk, bool force)
 {
 	struct adv_info *adv, *n;
-	int err = 0;
 
 	if (ext_adv_capable(hdev))
 		/* Remove all existing sets */
-		err = hci_clear_adv_sets_sync(hdev, sk);
-	if (ext_adv_capable(hdev))
-		return err;
+		return hci_clear_adv_sets_sync(hdev, sk);
 
 	/* This is safe as long as there is no command send while the lock is
 	 * held.
@@ -2004,13 +2001,11 @@ static int hci_clear_adv_sync(struct hci_dev *hdev, struct sock *sk, bool force)
 static int hci_remove_adv_sync(struct hci_dev *hdev, u8 instance,
 			       struct sock *sk)
 {
-	int err = 0;
+	int err;
 
 	/* If we use extended advertising, instance has to be removed first. */
 	if (ext_adv_capable(hdev))
-		err = hci_remove_ext_adv_instance_sync(hdev, instance, sk);
-	if (ext_adv_capable(hdev))
-		return err;
+		return hci_remove_ext_adv_instance_sync(hdev, instance, sk);
 
 	/* This is safe as long as there is no command send while the lock is
 	 * held.
@@ -2109,16 +2104,13 @@ int hci_read_tx_power_sync(struct hci_dev *hdev, __le16 handle, u8 type)
 int hci_disable_advertising_sync(struct hci_dev *hdev)
 {
 	u8 enable = 0x00;
-	int err = 0;
 
 	/* If controller is not advertising we are done. */
 	if (!hci_dev_test_flag(hdev, HCI_LE_ADV))
 		return 0;
 
 	if (ext_adv_capable(hdev))
-		err = hci_disable_ext_adv_instance_sync(hdev, 0x00);
-	if (ext_adv_capable(hdev))
-		return err;
+		return hci_disable_ext_adv_instance_sync(hdev, 0x00);
 
 	return __hci_cmd_sync_status(hdev, HCI_OP_LE_SET_ADV_ENABLE,
 				     sizeof(enable), &enable, HCI_CMD_TIMEOUT);

From e5af67a870f738bb8a4594b6c60c2caf4c87a3c9 Mon Sep 17 00:00:00 2001
From: Christian Eggers <ceggers@arri.de>
Date: Wed, 25 Jun 2025 15:09:30 +0200
Subject: [PATCH 0963/1334] Bluetooth: MGMT: set_mesh: update LE scan interval
 and window

According to the message of commit b338d91703fa ("Bluetooth: Implement
support for Mesh"), MGMT_OP_SET_MESH_RECEIVER should set the passive scan
parameters.  Currently the scan interval and window parameters are
silently ignored, although user space (bluetooth-meshd) expects that
they can be used [1]

[1] https://git.kernel.org/pub/scm/bluetooth/bluez.git/tree/mesh/mesh-io-mgmt.c#n344
Fixes: b338d91703fa ("Bluetooth: Implement support for Mesh")
Cc: stable@vger.kernel.org
Signed-off-by: Christian Eggers <ceggers@arri.de>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/mgmt.c | 22 ++++++++++++++++++++++
 1 file changed, 22 insertions(+)

diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index d540f7b4f75f..5d0f772c7a99 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -2153,6 +2153,9 @@ static int set_mesh_sync(struct hci_dev *hdev, void *data)
 	else
 		hci_dev_clear_flag(hdev, HCI_MESH);
 
+	hdev->le_scan_interval = __le16_to_cpu(cp->period);
+	hdev->le_scan_window = __le16_to_cpu(cp->window);
+
 	len -= sizeof(*cp);
 
 	/* If filters don't fit, forward all adv pkts */
@@ -2167,6 +2170,7 @@ static int set_mesh(struct sock *sk, struct hci_dev *hdev, void *data, u16 len)
 {
 	struct mgmt_cp_set_mesh *cp = data;
 	struct mgmt_pending_cmd *cmd;
+	__u16 period, window;
 	int err = 0;
 
 	bt_dev_dbg(hdev, "sock %p", sk);
@@ -2180,6 +2184,23 @@ static int set_mesh(struct sock *sk, struct hci_dev *hdev, void *data, u16 len)
 		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_MESH_RECEIVER,
 				       MGMT_STATUS_INVALID_PARAMS);
 
+	/* Keep allowed ranges in sync with set_scan_params() */
+	period = __le16_to_cpu(cp->period);
+
+	if (period < 0x0004 || period > 0x4000)
+		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_MESH_RECEIVER,
+				       MGMT_STATUS_INVALID_PARAMS);
+
+	window = __le16_to_cpu(cp->window);
+
+	if (window < 0x0004 || window > 0x4000)
+		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_MESH_RECEIVER,
+				       MGMT_STATUS_INVALID_PARAMS);
+
+	if (window > period)
+		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_MESH_RECEIVER,
+				       MGMT_STATUS_INVALID_PARAMS);
+
 	hci_dev_lock(hdev);
 
 	cmd = mgmt_pending_add(sk, MGMT_OP_SET_MESH_RECEIVER, hdev, data, len);
@@ -6432,6 +6453,7 @@ static int set_scan_params(struct sock *sk, struct hci_dev *hdev,
 		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_SCAN_PARAMS,
 				       MGMT_STATUS_NOT_SUPPORTED);
 
+	/* Keep allowed ranges in sync with set_mesh() */
 	interval = __le16_to_cpu(cp->interval);
 
 	if (interval < 0x0004 || interval > 0x4000)

From f3cb5676e5c11c896ba647ee309a993e73531588 Mon Sep 17 00:00:00 2001
From: Christian Eggers <ceggers@arri.de>
Date: Wed, 25 Jun 2025 15:09:31 +0200
Subject: [PATCH 0964/1334] Bluetooth: MGMT: mesh_send: check instances prior
 disabling advertising

The unconditional call of hci_disable_advertising_sync() in
mesh_send_done_sync() also disables other LE advertisings (non mesh
related).

I am not sure whether this call is required at all, but checking the
adv_instances list (like done at other places) seems to solve the
problem.

Fixes: b338d91703fa ("Bluetooth: Implement support for Mesh")
Cc: stable@vger.kernel.org
Signed-off-by: Christian Eggers <ceggers@arri.de>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/mgmt.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 5d0f772c7a99..1485b455ade4 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -1080,7 +1080,8 @@ static int mesh_send_done_sync(struct hci_dev *hdev, void *data)
 	struct mgmt_mesh_tx *mesh_tx;
 
 	hci_dev_clear_flag(hdev, HCI_MESH_SENDING);
-	hci_disable_advertising_sync(hdev);
+	if (list_empty(&hdev->adv_instances))
+		hci_disable_advertising_sync(hdev);
 	mesh_tx = mgmt_mesh_next(hdev, NULL);
 
 	if (mesh_tx)

From 89fb8acc38852116d38d721ad394aad7f2871670 Mon Sep 17 00:00:00 2001
From: Christian Eggers <ceggers@arri.de>
Date: Fri, 27 Jun 2025 09:05:08 +0200
Subject: [PATCH 0965/1334] Bluetooth: HCI: Set extended advertising data
 synchronously

Currently, for controllers with extended advertising, the advertising
data is set in the asynchronous response handler for extended
adverstising params. As most advertising settings are performed in a
synchronous context, the (asynchronous) setting of the advertising data
is done too late (after enabling the advertising).

Move setting of adverstising data from asynchronous response handler
into synchronous context to fix ordering of HCI commands.

Signed-off-by: Christian Eggers <ceggers@arri.de>
Fixes: a0fb3726ba55 ("Bluetooth: Use Set ext adv/scan rsp data if controller supports")
Cc: stable@vger.kernel.org
v2: https://lore.kernel.org/linux-bluetooth/20250626115209.17839-1-ceggers@arri.de/
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/hci_event.c |  36 -------
 net/bluetooth/hci_sync.c  | 207 ++++++++++++++++++++++++--------------
 2 files changed, 130 insertions(+), 113 deletions(-)

diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 66052d6aaa1d..4d5ace9d245d 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -2150,40 +2150,6 @@ static u8 hci_cc_set_adv_param(struct hci_dev *hdev, void *data,
 	return rp->status;
 }
 
-static u8 hci_cc_set_ext_adv_param(struct hci_dev *hdev, void *data,
-				   struct sk_buff *skb)
-{
-	struct hci_rp_le_set_ext_adv_params *rp = data;
-	struct hci_cp_le_set_ext_adv_params *cp;
-	struct adv_info *adv_instance;
-
-	bt_dev_dbg(hdev, "status 0x%2.2x", rp->status);
-
-	if (rp->status)
-		return rp->status;
-
-	cp = hci_sent_cmd_data(hdev, HCI_OP_LE_SET_EXT_ADV_PARAMS);
-	if (!cp)
-		return rp->status;
-
-	hci_dev_lock(hdev);
-	hdev->adv_addr_type = cp->own_addr_type;
-	if (!cp->handle) {
-		/* Store in hdev for instance 0 */
-		hdev->adv_tx_power = rp->tx_power;
-	} else {
-		adv_instance = hci_find_adv_instance(hdev, cp->handle);
-		if (adv_instance)
-			adv_instance->tx_power = rp->tx_power;
-	}
-	/* Update adv data as tx power is known now */
-	hci_update_adv_data(hdev, cp->handle);
-
-	hci_dev_unlock(hdev);
-
-	return rp->status;
-}
-
 static u8 hci_cc_read_rssi(struct hci_dev *hdev, void *data,
 			   struct sk_buff *skb)
 {
@@ -4164,8 +4130,6 @@ static const struct hci_cc {
 	HCI_CC(HCI_OP_LE_READ_NUM_SUPPORTED_ADV_SETS,
 	       hci_cc_le_read_num_adv_sets,
 	       sizeof(struct hci_rp_le_read_num_supported_adv_sets)),
-	HCI_CC(HCI_OP_LE_SET_EXT_ADV_PARAMS, hci_cc_set_ext_adv_param,
-	       sizeof(struct hci_rp_le_set_ext_adv_params)),
 	HCI_CC_STATUS(HCI_OP_LE_SET_EXT_ADV_ENABLE,
 		      hci_cc_le_set_ext_adv_enable),
 	HCI_CC_STATUS(HCI_OP_LE_SET_ADV_SET_RAND_ADDR,
diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c
index 106862d47964..77b3691f3423 100644
--- a/net/bluetooth/hci_sync.c
+++ b/net/bluetooth/hci_sync.c
@@ -1205,9 +1205,126 @@ static int hci_set_adv_set_random_addr_sync(struct hci_dev *hdev, u8 instance,
 				     sizeof(cp), &cp, HCI_CMD_TIMEOUT);
 }
 
+static int
+hci_set_ext_adv_params_sync(struct hci_dev *hdev, struct adv_info *adv,
+			    const struct hci_cp_le_set_ext_adv_params *cp,
+			    struct hci_rp_le_set_ext_adv_params *rp)
+{
+	struct sk_buff *skb;
+
+	skb = __hci_cmd_sync(hdev, HCI_OP_LE_SET_EXT_ADV_PARAMS, sizeof(*cp),
+			     cp, HCI_CMD_TIMEOUT);
+
+	/* If command return a status event, skb will be set to -ENODATA */
+	if (skb == ERR_PTR(-ENODATA))
+		return 0;
+
+	if (IS_ERR(skb)) {
+		bt_dev_err(hdev, "Opcode 0x%4.4x failed: %ld",
+			   HCI_OP_LE_SET_EXT_ADV_PARAMS, PTR_ERR(skb));
+		return PTR_ERR(skb);
+	}
+
+	if (skb->len != sizeof(*rp)) {
+		bt_dev_err(hdev, "Invalid response length for 0x%4.4x: %u",
+			   HCI_OP_LE_SET_EXT_ADV_PARAMS, skb->len);
+		kfree_skb(skb);
+		return -EIO;
+	}
+
+	memcpy(rp, skb->data, sizeof(*rp));
+	kfree_skb(skb);
+
+	if (!rp->status) {
+		hdev->adv_addr_type = cp->own_addr_type;
+		if (!cp->handle) {
+			/* Store in hdev for instance 0 */
+			hdev->adv_tx_power = rp->tx_power;
+		} else if (adv) {
+			adv->tx_power = rp->tx_power;
+		}
+	}
+
+	return rp->status;
+}
+
+static int hci_set_ext_adv_data_sync(struct hci_dev *hdev, u8 instance)
+{
+	DEFINE_FLEX(struct hci_cp_le_set_ext_adv_data, pdu, data, length,
+		    HCI_MAX_EXT_AD_LENGTH);
+	u8 len;
+	struct adv_info *adv = NULL;
+	int err;
+
+	if (instance) {
+		adv = hci_find_adv_instance(hdev, instance);
+		if (!adv || !adv->adv_data_changed)
+			return 0;
+	}
+
+	len = eir_create_adv_data(hdev, instance, pdu->data,
+				  HCI_MAX_EXT_AD_LENGTH);
+
+	pdu->length = len;
+	pdu->handle = adv ? adv->handle : instance;
+	pdu->operation = LE_SET_ADV_DATA_OP_COMPLETE;
+	pdu->frag_pref = LE_SET_ADV_DATA_NO_FRAG;
+
+	err = __hci_cmd_sync_status(hdev, HCI_OP_LE_SET_EXT_ADV_DATA,
+				    struct_size(pdu, data, len), pdu,
+				    HCI_CMD_TIMEOUT);
+	if (err)
+		return err;
+
+	/* Update data if the command succeed */
+	if (adv) {
+		adv->adv_data_changed = false;
+	} else {
+		memcpy(hdev->adv_data, pdu->data, len);
+		hdev->adv_data_len = len;
+	}
+
+	return 0;
+}
+
+static int hci_set_adv_data_sync(struct hci_dev *hdev, u8 instance)
+{
+	struct hci_cp_le_set_adv_data cp;
+	u8 len;
+
+	memset(&cp, 0, sizeof(cp));
+
+	len = eir_create_adv_data(hdev, instance, cp.data, sizeof(cp.data));
+
+	/* There's nothing to do if the data hasn't changed */
+	if (hdev->adv_data_len == len &&
+	    memcmp(cp.data, hdev->adv_data, len) == 0)
+		return 0;
+
+	memcpy(hdev->adv_data, cp.data, sizeof(cp.data));
+	hdev->adv_data_len = len;
+
+	cp.length = len;
+
+	return __hci_cmd_sync_status(hdev, HCI_OP_LE_SET_ADV_DATA,
+				     sizeof(cp), &cp, HCI_CMD_TIMEOUT);
+}
+
+int hci_update_adv_data_sync(struct hci_dev *hdev, u8 instance)
+{
+	if (!hci_dev_test_flag(hdev, HCI_LE_ENABLED))
+		return 0;
+
+	if (ext_adv_capable(hdev))
+		return hci_set_ext_adv_data_sync(hdev, instance);
+
+	return hci_set_adv_data_sync(hdev, instance);
+}
+
 int hci_setup_ext_adv_instance_sync(struct hci_dev *hdev, u8 instance)
 {
 	struct hci_cp_le_set_ext_adv_params cp;
+	struct hci_rp_le_set_ext_adv_params rp;
 	bool connectable;
 	u32 flags;
 	bdaddr_t random_addr;
@@ -1316,8 +1433,12 @@ int hci_setup_ext_adv_instance_sync(struct hci_dev *hdev, u8 instance)
 		cp.secondary_phy = HCI_ADV_PHY_1M;
 	}
 
-	err = __hci_cmd_sync_status(hdev, HCI_OP_LE_SET_EXT_ADV_PARAMS,
-				    sizeof(cp), &cp, HCI_CMD_TIMEOUT);
+	err = hci_set_ext_adv_params_sync(hdev, adv, &cp, &rp);
+	if (err)
+		return err;
+
+	/* Update adv data as tx power is known now */
+	err = hci_set_ext_adv_data_sync(hdev, cp.handle);
 	if (err)
 		return err;
 
@@ -1822,79 +1943,6 @@ int hci_le_terminate_big_sync(struct hci_dev *hdev, u8 handle, u8 reason)
 				     sizeof(cp), &cp, HCI_CMD_TIMEOUT);
 }
 
-static int hci_set_ext_adv_data_sync(struct hci_dev *hdev, u8 instance)
-{
-	DEFINE_FLEX(struct hci_cp_le_set_ext_adv_data, pdu, data, length,
-		    HCI_MAX_EXT_AD_LENGTH);
-	u8 len;
-	struct adv_info *adv = NULL;
-	int err;
-
-	if (instance) {
-		adv = hci_find_adv_instance(hdev, instance);
-		if (!adv || !adv->adv_data_changed)
-			return 0;
-	}
-
-	len = eir_create_adv_data(hdev, instance, pdu->data,
-				  HCI_MAX_EXT_AD_LENGTH);
-
-	pdu->length = len;
-	pdu->handle = adv ? adv->handle : instance;
-	pdu->operation = LE_SET_ADV_DATA_OP_COMPLETE;
-	pdu->frag_pref = LE_SET_ADV_DATA_NO_FRAG;
-
-	err = __hci_cmd_sync_status(hdev, HCI_OP_LE_SET_EXT_ADV_DATA,
-				    struct_size(pdu, data, len), pdu,
-				    HCI_CMD_TIMEOUT);
-	if (err)
-		return err;
-
-	/* Update data if the command succeed */
-	if (adv) {
-		adv->adv_data_changed = false;
-	} else {
-		memcpy(hdev->adv_data, pdu->data, len);
-		hdev->adv_data_len = len;
-	}
-
-	return 0;
-}
-
-static int hci_set_adv_data_sync(struct hci_dev *hdev, u8 instance)
-{
-	struct hci_cp_le_set_adv_data cp;
-	u8 len;
-
-	memset(&cp, 0, sizeof(cp));
-
-	len = eir_create_adv_data(hdev, instance, cp.data, sizeof(cp.data));
-
-	/* There's nothing to do if the data hasn't changed */
-	if (hdev->adv_data_len == len &&
-	    memcmp(cp.data, hdev->adv_data, len) == 0)
-		return 0;
-
-	memcpy(hdev->adv_data, cp.data, sizeof(cp.data));
-	hdev->adv_data_len = len;
-
-	cp.length = len;
-
-	return __hci_cmd_sync_status(hdev, HCI_OP_LE_SET_ADV_DATA,
-				     sizeof(cp), &cp, HCI_CMD_TIMEOUT);
-}
-
-int hci_update_adv_data_sync(struct hci_dev *hdev, u8 instance)
-{
-	if (!hci_dev_test_flag(hdev, HCI_LE_ENABLED))
-		return 0;
-
-	if (ext_adv_capable(hdev))
-		return hci_set_ext_adv_data_sync(hdev, instance);
-
-	return hci_set_adv_data_sync(hdev, instance);
-}
-
 int hci_schedule_adv_instance_sync(struct hci_dev *hdev, u8 instance,
 				   bool force)
 {
@@ -6273,6 +6321,7 @@ static int hci_le_ext_directed_advertising_sync(struct hci_dev *hdev,
 						struct hci_conn *conn)
 {
 	struct hci_cp_le_set_ext_adv_params cp;
+	struct hci_rp_le_set_ext_adv_params rp;
 	int err;
 	bdaddr_t random_addr;
 	u8 own_addr_type;
@@ -6314,8 +6363,12 @@ static int hci_le_ext_directed_advertising_sync(struct hci_dev *hdev,
 	if (err)
 		return err;
 
-	err = __hci_cmd_sync_status(hdev, HCI_OP_LE_SET_EXT_ADV_PARAMS,
-				    sizeof(cp), &cp, HCI_CMD_TIMEOUT);
+	err = hci_set_ext_adv_params_sync(hdev, NULL, &cp, &rp);
+	if (err)
+		return err;
+
+	/* Update adv data as tx power is known now */
+	err = hci_set_ext_adv_data_sync(hdev, cp.handle);
 	if (err)
 		return err;
 

From 35ecea24b5ef7534b8c928bb9ddfa936bd2805ab Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Fri, 27 Jun 2025 12:23:20 -0700
Subject: [PATCH 0966/1334] Input: xpad - adjust error handling for disconnect

When a device supporting xpad is disconnected it's expected that a
URB will fail to transmit.

Only show an error message when the error isn't -ENODEV.

Fixes: 7fc595f4c0263 ("Input: xpad - correctly handle concurrent LED and FF requests")
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Link: https://lore.kernel.org/r/20250609014718.236827-2-superm1@kernel.org
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/joystick/xpad.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/input/joystick/xpad.c b/drivers/input/joystick/xpad.c
index c066a4da7c14..714a694fc0e5 100644
--- a/drivers/input/joystick/xpad.c
+++ b/drivers/input/joystick/xpad.c
@@ -1344,9 +1344,10 @@ static int xpad_try_sending_next_out_packet(struct usb_xpad *xpad)
 		usb_anchor_urb(xpad->irq_out, &xpad->irq_out_anchor);
 		error = usb_submit_urb(xpad->irq_out, GFP_ATOMIC);
 		if (error) {
-			dev_err(&xpad->intf->dev,
-				"%s - usb_submit_urb failed with result %d\n",
-				__func__, error);
+			if (error != -ENODEV)
+				dev_err(&xpad->intf->dev,
+					"%s - usb_submit_urb failed with result %d\n",
+					__func__, error);
 			usb_unanchor_urb(xpad->irq_out);
 			return -EIO;
 		}

From 77451cb102506a980cd299581e1c03a367af3c9a Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Fri, 27 Jun 2025 12:23:44 -0700
Subject: [PATCH 0967/1334] Input: xpad - return errors from
 xpad_try_sending_next_out_packet() up

Not all errors that occur in xpad_try_sending_next_out_packet() are
IO errors. Pass up the error code to the caller so that it can
decide what to do.

Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Link: https://lore.kernel.org/r/20250609014718.236827-3-superm1@kernel.org
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/joystick/xpad.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/input/joystick/xpad.c b/drivers/input/joystick/xpad.c
index 714a694fc0e5..e0374111d017 100644
--- a/drivers/input/joystick/xpad.c
+++ b/drivers/input/joystick/xpad.c
@@ -1349,7 +1349,7 @@ static int xpad_try_sending_next_out_packet(struct usb_xpad *xpad)
 					"%s - usb_submit_urb failed with result %d\n",
 					__func__, error);
 			usb_unanchor_urb(xpad->irq_out);
-			return -EIO;
+			return error;
 		}
 
 		xpad->irq_out_active = true;

From 6921d1e07cb5eddec830801087b419194fde0803 Mon Sep 17 00:00:00 2001
From: Edward Adam Davis <eadavis@qq.com>
Date: Tue, 24 Jun 2025 14:38:46 +0800
Subject: [PATCH 0968/1334] tracing: Fix filter logic error

If the processing of the tr->events loop fails, the filter that has been
added to filter_head will be released twice in free_filter_list(&head->rcu)
and __free_filter(filter).

After adding the filter of tr->events, add the filter to the filter_head
process to avoid triggering uaf.

Link: https://lore.kernel.org/tencent_4EF87A626D702F816CD0951CE956EC32CD0A@qq.com
Fixes: a9d0aab5eb33 ("tracing: Fix regression of filter waiting a long time on RCU synchronization")
Reported-by: syzbot+daba72c4af9915e9c894@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=daba72c4af9915e9c894
Tested-by: syzbot+daba72c4af9915e9c894@syzkaller.appspotmail.com
Acked-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Edward Adam Davis <eadavis@qq.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/trace_events_filter.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index 08141f105c95..3885aadc434d 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -1436,13 +1436,6 @@ static void filter_free_subsystem_filters(struct trace_subsystem_dir *dir,
 
 	INIT_LIST_HEAD(&head->list);
 
-	item = kmalloc(sizeof(*item), GFP_KERNEL);
-	if (!item)
-		goto free_now;
-
-	item->filter = filter;
-	list_add_tail(&item->list, &head->list);
-
 	list_for_each_entry(file, &tr->events, list) {
 		if (file->system != dir)
 			continue;
@@ -1454,6 +1447,13 @@ static void filter_free_subsystem_filters(struct trace_subsystem_dir *dir,
 		event_clear_filter(file);
 	}
 
+	item = kmalloc(sizeof(*item), GFP_KERNEL);
+	if (!item)
+		goto free_now;
+
+	item->filter = filter;
+	list_add_tail(&item->list, &head->list);
+
 	delay_free_filter(head);
 	return;
  free_now:

From 8550821a153558d49dffacbc1dc98ac9d3eed2fa Mon Sep 17 00:00:00 2001
From: Jan Karcher <jaka@linux.ibm.com>
Date: Thu, 26 Jun 2025 07:16:53 +0200
Subject: [PATCH 0969/1334] MAINTAINERS: update smc section

Due to changes of my responsibilities within IBM i
can no longer act as maintainer for smc.

As a result of the co-operation with Alibaba over
the last years we decided to, once more, give them
more responsibility for smc by appointing
D. Wythe <alibuda@linux.alibaba.com> and
Dust Li <dust.li@linux.alibaba.com>
as maintainers as well.

Within IBM Sidraya Jayagond <sidraya@linux.ibm.com>
and Mahanta Jambigi <mjambigi@linux.ibm.com>
are going to take over the maintainership for smc.

Signed-off-by: Jan Karcher <jaka@linux.ibm.com>
Reviewed-by: Wenjia Zhang <wenjia@linux.ibm.com>
Link: https://patch.msgid.link/20250626051653.4259-1-jaka@linux.ibm.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 MAINTAINERS | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index efb51ee92683..bb7e5f8c4455 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -22564,9 +22564,11 @@ S:	Maintained
 F:	drivers/misc/sgi-xp/
 
 SHARED MEMORY COMMUNICATIONS (SMC) SOCKETS
+M:	D. Wythe <alibuda@linux.alibaba.com>
+M:	Dust Li <dust.li@linux.alibaba.com>
+M:	Sidraya Jayagond <sidraya@linux.ibm.com>
 M:	Wenjia Zhang <wenjia@linux.ibm.com>
-M:	Jan Karcher <jaka@linux.ibm.com>
-R:	D. Wythe <alibuda@linux.alibaba.com>
+R:	Mahanta Jambigi <mjambigi@linux.ibm.com>
 R:	Tony Lu <tonylu@linux.alibaba.com>
 R:	Wen Gu <guwen@linux.alibaba.com>
 L:	linux-rdma@vger.kernel.org

From 6e457732c8a4431952a5cc075215268ce021dc0f Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Thu, 26 Jun 2025 11:20:55 -0700
Subject: [PATCH 0970/1334] docs: netdev: correct the heading level for
 co-posting selftests

"Co-posting selftests" belongs in the "netdev patch review" section,
same as "co-posting changes to user space components". It was
erroneously added as its own section.

Reviewed-by: Bagas Sanjaya <bagasdotme@gmail.com>
Link: https://patch.msgid.link/20250626182055.4161905-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/process/maintainer-netdev.rst | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/process/maintainer-netdev.rst b/Documentation/process/maintainer-netdev.rst
index 1ac62dc3a66f..e1755610b4bc 100644
--- a/Documentation/process/maintainer-netdev.rst
+++ b/Documentation/process/maintainer-netdev.rst
@@ -312,7 +312,7 @@ Posting as one thread is discouraged because it confuses patchwork
 (as of patchwork 2.2.2).
 
 Co-posting selftests
---------------------
+~~~~~~~~~~~~~~~~~~~~
 
 Selftests should be part of the same series as the code changes.
 Specifically for fixes both code change and related test should go into

From ba2f83eecd2b36b12f92e5edd8bdc0509c7cd44e Mon Sep 17 00:00:00 2001
From: Ulrich Weber <ulrich.weber@gmail.com>
Date: Thu, 26 Jun 2025 16:56:18 +0200
Subject: [PATCH 0971/1334] doc: tls: socket needs to be established to enable
 ulp

To enable TLS ulp socket needs to be in established state.
This was added in commit d91c3e17f75f ("net/tls: Only attach
to sockets in ESTABLISHED state"), in 2018.

Signed-off-by: Ulrich Weber <ulrich.weber@gmail.com>
Link: https://patch.msgid.link/20250626145618.15464-1-ulrich.weber@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/networking/tls.rst | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/Documentation/networking/tls.rst b/Documentation/networking/tls.rst
index c7904a1bc167..36cc7afc2527 100644
--- a/Documentation/networking/tls.rst
+++ b/Documentation/networking/tls.rst
@@ -16,11 +16,13 @@ User interface
 Creating a TLS connection
 -------------------------
 
-First create a new TCP socket and set the TLS ULP.
+First create a new TCP socket and once the connection is established set the
+TLS ULP.
 
 .. code-block:: c
 
   sock = socket(AF_INET, SOCK_STREAM, 0);
+  connect(sock, addr, addrlen);
   setsockopt(sock, SOL_TCP, TCP_ULP, "tls", sizeof("tls"));
 
 Setting the TLS ULP allows us to set/get TLS socket options. Currently

From 22c69d786ef8fb789c61ca75492a272774221324 Mon Sep 17 00:00:00 2001
From: Nilton Perim Neto <niltonperimneto@gmail.com>
Date: Fri, 27 Jun 2025 16:29:40 -0700
Subject: [PATCH 0972/1334] Input: xpad - support Acer NGR 200 Controller

Add the NGR 200 Xbox 360 to the list of recognized controllers.

Signed-off-by: Nilton Perim Neto <niltonperimneto@gmail.com>
Link: https://lore.kernel.org/r/20250608060517.14967-1-niltonperimneto@gmail.com
Cc: stable@vger.kernel.org
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/joystick/xpad.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/input/joystick/xpad.c b/drivers/input/joystick/xpad.c
index e0374111d017..5d9b7007a730 100644
--- a/drivers/input/joystick/xpad.c
+++ b/drivers/input/joystick/xpad.c
@@ -177,6 +177,7 @@ static const struct xpad_device {
 	{ 0x05fd, 0x107a, "InterAct 'PowerPad Pro' X-Box pad (Germany)", 0, XTYPE_XBOX },
 	{ 0x05fe, 0x3030, "Chic Controller", 0, XTYPE_XBOX },
 	{ 0x05fe, 0x3031, "Chic Controller", 0, XTYPE_XBOX },
+	{ 0x0502, 0x1305, "Acer NGR200", 0, XTYPE_XBOX },
 	{ 0x062a, 0x0020, "Logic3 Xbox GamePad", 0, XTYPE_XBOX },
 	{ 0x062a, 0x0033, "Competition Pro Steering Wheel", 0, XTYPE_XBOX },
 	{ 0x06a3, 0x0200, "Saitek Racing Wheel", 0, XTYPE_XBOX },
@@ -524,6 +525,7 @@ static const struct usb_device_id xpad_table[] = {
 	XPAD_XBOX360_VENDOR(0x045e),		/* Microsoft Xbox 360 controllers */
 	XPAD_XBOXONE_VENDOR(0x045e),		/* Microsoft Xbox One controllers */
 	XPAD_XBOX360_VENDOR(0x046d),		/* Logitech Xbox 360-style controllers */
+	XPAD_XBOX360_VENDOR(0x0502),		/* Acer Inc. Xbox 360 style controllers */
 	XPAD_XBOX360_VENDOR(0x056e),		/* Elecom JC-U3613M */
 	XPAD_XBOX360_VENDOR(0x06a3),		/* Saitek P3600 */
 	XPAD_XBOX360_VENDOR(0x0738),		/* Mad Catz Xbox 360 controllers */

From d72411d20905180cdc452c553be17481b24463d2 Mon Sep 17 00:00:00 2001
From: Thomas Fourier <fourier.thomas@gmail.com>
Date: Wed, 25 Jun 2025 16:16:24 +0200
Subject: [PATCH 0973/1334] ethernet: atl1: Add missing DMA mapping error
 checks and count errors

The `dma_map_XXX()` functions can fail and must be checked using
`dma_mapping_error()`.  This patch adds proper error handling for all
DMA mapping calls.

In `atl1_alloc_rx_buffers()`, if DMA mapping fails, the buffer is
deallocated and marked accordingly.

In `atl1_tx_map()`, previously mapped buffers are unmapped and the
packet is dropped on failure.

If `atl1_xmit_frame()` drops the packet, increment the tx_error counter.

Fixes: f3cc28c79760 ("Add Attansic L1 ethernet driver.")
Signed-off-by: Thomas Fourier <fourier.thomas@gmail.com>
Link: https://patch.msgid.link/20250625141629.114984-2-fourier.thomas@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/atheros/atlx/atl1.c | 79 +++++++++++++++++-------
 1 file changed, 57 insertions(+), 22 deletions(-)

diff --git a/drivers/net/ethernet/atheros/atlx/atl1.c b/drivers/net/ethernet/atheros/atlx/atl1.c
index cfdb546a09e7..98a4d089270e 100644
--- a/drivers/net/ethernet/atheros/atlx/atl1.c
+++ b/drivers/net/ethernet/atheros/atlx/atl1.c
@@ -1861,14 +1861,21 @@ static u16 atl1_alloc_rx_buffers(struct atl1_adapter *adapter)
 			break;
 		}
 
-		buffer_info->alloced = 1;
-		buffer_info->skb = skb;
-		buffer_info->length = (u16) adapter->rx_buffer_len;
 		page = virt_to_page(skb->data);
 		offset = offset_in_page(skb->data);
 		buffer_info->dma = dma_map_page(&pdev->dev, page, offset,
 						adapter->rx_buffer_len,
 						DMA_FROM_DEVICE);
+		if (dma_mapping_error(&pdev->dev, buffer_info->dma)) {
+			kfree_skb(skb);
+			adapter->soft_stats.rx_dropped++;
+			break;
+		}
+
+		buffer_info->alloced = 1;
+		buffer_info->skb = skb;
+		buffer_info->length = (u16)adapter->rx_buffer_len;
+
 		rfd_desc->buffer_addr = cpu_to_le64(buffer_info->dma);
 		rfd_desc->buf_len = cpu_to_le16(adapter->rx_buffer_len);
 		rfd_desc->coalese = 0;
@@ -2183,8 +2190,8 @@ static int atl1_tx_csum(struct atl1_adapter *adapter, struct sk_buff *skb,
 	return 0;
 }
 
-static void atl1_tx_map(struct atl1_adapter *adapter, struct sk_buff *skb,
-	struct tx_packet_desc *ptpd)
+static bool atl1_tx_map(struct atl1_adapter *adapter, struct sk_buff *skb,
+			struct tx_packet_desc *ptpd)
 {
 	struct atl1_tpd_ring *tpd_ring = &adapter->tpd_ring;
 	struct atl1_buffer *buffer_info;
@@ -2194,6 +2201,7 @@ static void atl1_tx_map(struct atl1_adapter *adapter, struct sk_buff *skb,
 	unsigned int nr_frags;
 	unsigned int f;
 	int retval;
+	u16 first_mapped;
 	u16 next_to_use;
 	u16 data_len;
 	u8 hdr_len;
@@ -2201,6 +2209,7 @@ static void atl1_tx_map(struct atl1_adapter *adapter, struct sk_buff *skb,
 	buf_len -= skb->data_len;
 	nr_frags = skb_shinfo(skb)->nr_frags;
 	next_to_use = atomic_read(&tpd_ring->next_to_use);
+	first_mapped = next_to_use;
 	buffer_info = &tpd_ring->buffer_info[next_to_use];
 	BUG_ON(buffer_info->skb);
 	/* put skb in last TPD */
@@ -2216,6 +2225,8 @@ static void atl1_tx_map(struct atl1_adapter *adapter, struct sk_buff *skb,
 		buffer_info->dma = dma_map_page(&adapter->pdev->dev, page,
 						offset, hdr_len,
 						DMA_TO_DEVICE);
+		if (dma_mapping_error(&adapter->pdev->dev, buffer_info->dma))
+			goto dma_err;
 
 		if (++next_to_use == tpd_ring->count)
 			next_to_use = 0;
@@ -2242,6 +2253,9 @@ static void atl1_tx_map(struct atl1_adapter *adapter, struct sk_buff *skb,
 								page, offset,
 								buffer_info->length,
 								DMA_TO_DEVICE);
+				if (dma_mapping_error(&adapter->pdev->dev,
+						      buffer_info->dma))
+					goto dma_err;
 				if (++next_to_use == tpd_ring->count)
 					next_to_use = 0;
 			}
@@ -2254,6 +2268,8 @@ static void atl1_tx_map(struct atl1_adapter *adapter, struct sk_buff *skb,
 		buffer_info->dma = dma_map_page(&adapter->pdev->dev, page,
 						offset, buf_len,
 						DMA_TO_DEVICE);
+		if (dma_mapping_error(&adapter->pdev->dev, buffer_info->dma))
+			goto dma_err;
 		if (++next_to_use == tpd_ring->count)
 			next_to_use = 0;
 	}
@@ -2277,6 +2293,9 @@ static void atl1_tx_map(struct atl1_adapter *adapter, struct sk_buff *skb,
 			buffer_info->dma = skb_frag_dma_map(&adapter->pdev->dev,
 				frag, i * ATL1_MAX_TX_BUF_LEN,
 				buffer_info->length, DMA_TO_DEVICE);
+			if (dma_mapping_error(&adapter->pdev->dev,
+					      buffer_info->dma))
+				goto dma_err;
 
 			if (++next_to_use == tpd_ring->count)
 				next_to_use = 0;
@@ -2285,6 +2304,22 @@ static void atl1_tx_map(struct atl1_adapter *adapter, struct sk_buff *skb,
 
 	/* last tpd's buffer-info */
 	buffer_info->skb = skb;
+
+	return true;
+
+ dma_err:
+	while (first_mapped != next_to_use) {
+		buffer_info = &tpd_ring->buffer_info[first_mapped];
+		dma_unmap_page(&adapter->pdev->dev,
+			       buffer_info->dma,
+			       buffer_info->length,
+			       DMA_TO_DEVICE);
+		buffer_info->dma = 0;
+
+		if (++first_mapped == tpd_ring->count)
+			first_mapped = 0;
+	}
+	return false;
 }
 
 static void atl1_tx_queue(struct atl1_adapter *adapter, u16 count,
@@ -2355,10 +2390,8 @@ static netdev_tx_t atl1_xmit_frame(struct sk_buff *skb,
 
 	len = skb_headlen(skb);
 
-	if (unlikely(skb->len <= 0)) {
-		dev_kfree_skb_any(skb);
-		return NETDEV_TX_OK;
-	}
+	if (unlikely(skb->len <= 0))
+		goto drop_packet;
 
 	nr_frags = skb_shinfo(skb)->nr_frags;
 	for (f = 0; f < nr_frags; f++) {
@@ -2371,10 +2404,9 @@ static netdev_tx_t atl1_xmit_frame(struct sk_buff *skb,
 	if (mss) {
 		if (skb->protocol == htons(ETH_P_IP)) {
 			proto_hdr_len = skb_tcp_all_headers(skb);
-			if (unlikely(proto_hdr_len > len)) {
-				dev_kfree_skb_any(skb);
-				return NETDEV_TX_OK;
-			}
+			if (unlikely(proto_hdr_len > len))
+				goto drop_packet;
+
 			/* need additional TPD ? */
 			if (proto_hdr_len != len)
 				count += (len - proto_hdr_len +
@@ -2406,23 +2438,26 @@ static netdev_tx_t atl1_xmit_frame(struct sk_buff *skb,
 	}
 
 	tso = atl1_tso(adapter, skb, ptpd);
-	if (tso < 0) {
-		dev_kfree_skb_any(skb);
-		return NETDEV_TX_OK;
-	}
+	if (tso < 0)
+		goto drop_packet;
 
 	if (!tso) {
 		ret_val = atl1_tx_csum(adapter, skb, ptpd);
-		if (ret_val < 0) {
-			dev_kfree_skb_any(skb);
-			return NETDEV_TX_OK;
-		}
+		if (ret_val < 0)
+			goto drop_packet;
 	}
 
-	atl1_tx_map(adapter, skb, ptpd);
+	if (!atl1_tx_map(adapter, skb, ptpd))
+		goto drop_packet;
+
 	atl1_tx_queue(adapter, count, ptpd);
 	atl1_update_mailbox(adapter);
 	return NETDEV_TX_OK;
+
+drop_packet:
+	adapter->soft_stats.tx_errors++;
+	dev_kfree_skb_any(skb);
+	return NETDEV_TX_OK;
 }
 
 static int atl1_rings_clean(struct napi_struct *napi, int budget)

From 2def09ead4ad5907988b655d1e1454003aaf8297 Mon Sep 17 00:00:00 2001
From: Fushuai Wang <wangfushuai@baidu.com>
Date: Thu, 26 Jun 2025 21:30:03 +0800
Subject: [PATCH 0974/1334] dpaa2-eth: fix xdp_rxq_info leak

The driver registered xdp_rxq_info structures via xdp_rxq_info_reg()
but failed to properly unregister them in error paths and during
removal.

Fixes: d678be1dc1ec ("dpaa2-eth: add XDP_REDIRECT support")
Signed-off-by: Fushuai Wang <wangfushuai@baidu.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Link: https://patch.msgid.link/20250626133003.80136-1-wangfushuai@baidu.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/ethernet/freescale/dpaa2/dpaa2-eth.c  | 26 +++++++++++++++++--
 1 file changed, 24 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
index 2ec2c3dab250..b82f121cadad 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
@@ -3939,6 +3939,7 @@ static int dpaa2_eth_setup_rx_flow(struct dpaa2_eth_priv *priv,
 					 MEM_TYPE_PAGE_ORDER0, NULL);
 	if (err) {
 		dev_err(dev, "xdp_rxq_info_reg_mem_model failed\n");
+		xdp_rxq_info_unreg(&fq->channel->xdp_rxq);
 		return err;
 	}
 
@@ -4432,17 +4433,25 @@ static int dpaa2_eth_bind_dpni(struct dpaa2_eth_priv *priv)
 			return -EINVAL;
 		}
 		if (err)
-			return err;
+			goto out;
 	}
 
 	err = dpni_get_qdid(priv->mc_io, 0, priv->mc_token,
 			    DPNI_QUEUE_TX, &priv->tx_qdid);
 	if (err) {
 		dev_err(dev, "dpni_get_qdid() failed\n");
-		return err;
+		goto out;
 	}
 
 	return 0;
+
+out:
+	while (i--) {
+		if (priv->fq[i].type == DPAA2_RX_FQ &&
+		    xdp_rxq_info_is_reg(&priv->fq[i].channel->xdp_rxq))
+			xdp_rxq_info_unreg(&priv->fq[i].channel->xdp_rxq);
+	}
+	return err;
 }
 
 /* Allocate rings for storing incoming frame descriptors */
@@ -4825,6 +4834,17 @@ static void dpaa2_eth_del_ch_napi(struct dpaa2_eth_priv *priv)
 	}
 }
 
+static void dpaa2_eth_free_rx_xdp_rxq(struct dpaa2_eth_priv *priv)
+{
+	int i;
+
+	for (i = 0; i < priv->num_fqs; i++) {
+		if (priv->fq[i].type == DPAA2_RX_FQ &&
+		    xdp_rxq_info_is_reg(&priv->fq[i].channel->xdp_rxq))
+			xdp_rxq_info_unreg(&priv->fq[i].channel->xdp_rxq);
+	}
+}
+
 static int dpaa2_eth_probe(struct fsl_mc_device *dpni_dev)
 {
 	struct device *dev;
@@ -5028,6 +5048,7 @@ err_alloc_percpu_extras:
 	free_percpu(priv->percpu_stats);
 err_alloc_percpu_stats:
 	dpaa2_eth_del_ch_napi(priv);
+	dpaa2_eth_free_rx_xdp_rxq(priv);
 err_bind:
 	dpaa2_eth_free_dpbps(priv);
 err_dpbp_setup:
@@ -5080,6 +5101,7 @@ static void dpaa2_eth_remove(struct fsl_mc_device *ls_dev)
 	free_percpu(priv->percpu_extras);
 
 	dpaa2_eth_del_ch_napi(priv);
+	dpaa2_eth_free_rx_xdp_rxq(priv);
 	dpaa2_eth_free_dpbps(priv);
 	dpaa2_eth_free_dpio(priv);
 	dpaa2_eth_free_dpni(priv);

From 30ad231a5029bfa16e46ce868497b1a5cdd3c24d Mon Sep 17 00:00:00 2001
From: JP Kobryn <inwardvessel@gmail.com>
Date: Fri, 27 Jun 2025 10:49:35 -0700
Subject: [PATCH 0975/1334] x86/mce: Make sure CMCI banks are cleared during
 shutdown on Intel

CMCI banks are not cleared during shutdown on Intel CPUs. As a side effect,
when a kexec is performed, CPUs coming back online are unable to
rediscover/claim these occupied banks which breaks MCE reporting.

Clear the CPU ownership during shutdown via cmci_clear() so the banks can
be reclaimed and MCE reporting will become functional once more.

  [ bp: Massage commit message. ]

Reported-by: Aijay Adams <aijay@meta.com>
Signed-off-by: JP Kobryn <inwardvessel@gmail.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Tony Luck <tony.luck@intel.com>
Reviewed-by: Qiuxu Zhuo <qiuxu.zhuo@intel.com>
Cc: <stable@kernel.org>
Link: https://lore.kernel.org/20250627174935.95194-1-inwardvessel@gmail.com
---
 arch/x86/kernel/cpu/mce/intel.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/x86/kernel/cpu/mce/intel.c b/arch/x86/kernel/cpu/mce/intel.c
index efcf21e9552e..9b149b9c4109 100644
--- a/arch/x86/kernel/cpu/mce/intel.c
+++ b/arch/x86/kernel/cpu/mce/intel.c
@@ -478,6 +478,7 @@ void mce_intel_feature_init(struct cpuinfo_x86 *c)
 void mce_intel_feature_clear(struct cpuinfo_x86 *c)
 {
 	intel_clear_lmce();
+	cmci_clear();
 }
 
 bool intel_filter_mce(struct mce *m)

From 80e08394377559ed5a2ccadd861e62d24b826911 Mon Sep 17 00:00:00 2001
From: SCHNEIDER Johannes <johannes.schneider@leica-geosystems.com>
Date: Wed, 25 Jun 2025 07:49:16 +0000
Subject: [PATCH 0976/1334] usb: dwc3: gadget: Fix TRB reclaim logic for short
 transfers and ZLPs

Commit 96c7bf8f6b3e ("usb: dwc3: gadget: Cleanup SG handling") updated
the TRB reclaim path to use the TRB CHN (Chain) bit to determine whether
a TRB was part of a chain. However, this inadvertently changed the
behavior of reclaiming the final TRB in some scatter-gather or short
transfer cases.

In particular, if the final TRB did not have the CHN bit set, the
cleanup path could incorrectly skip clearing the HWO (Hardware Own)
bit, leaving stale TRBs in the ring. This resulted in broken data
transfer completions in userspace, notably for MTP over FunctionFS.

Fix this by unconditionally clearing the HWO bit during TRB reclaim,
regardless of the CHN bit state. This restores correct behavior
especially for transfers that require ZLPs or end on non-CHN TRBs.

Fixes: 61440628a4ff ("usb: dwc3: gadget: Cleanup SG handling")
Signed-off-by: Johannes Schneider <johannes.schneider@leica-geosystems.com>
Acked-by: Thinh Nguyen <Thinh.Nguyen@synopsys.com>
Cc: stable <stable@kernel.org>
Link: https://lore.kernel.org/r/AM8PR06MB7521A29A8863C838B54987B6BC7BA@AM8PR06MB7521.eurprd06.prod.outlook.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/dwc3/gadget.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c
index b6b63b530148..74968f93d4a3 100644
--- a/drivers/usb/dwc3/gadget.c
+++ b/drivers/usb/dwc3/gadget.c
@@ -3516,7 +3516,7 @@ static int dwc3_gadget_ep_reclaim_completed_trb(struct dwc3_ep *dep,
 	 * We're going to do that here to avoid problems of HW trying
 	 * to use bogus TRBs for transfers.
 	 */
-	if (chain && (trb->ctrl & DWC3_TRB_CTRL_HWO))
+	if (trb->ctrl & DWC3_TRB_CTRL_HWO)
 		trb->ctrl &= ~DWC3_TRB_CTRL_HWO;
 
 	/*

From cbc889ab0122366f6cdbe3c28d477c683ebcebc2 Mon Sep 17 00:00:00 2001
From: Raju Rangoju <Raju.Rangoju@amd.com>
Date: Fri, 27 Jun 2025 17:41:19 +0300
Subject: [PATCH 0977/1334] usb: xhci: quirk for data loss in ISOC transfers

During the High-Speed Isochronous Audio transfers, xHCI
controller on certain AMD platforms experiences momentary data
loss. This results in Missed Service Errors (MSE) being
generated by the xHCI.

The root cause of the MSE is attributed to the ISOC OUT endpoint
being omitted from scheduling. This can happen when an IN
endpoint with a 64ms service interval either is pre-scheduled
prior to the ISOC OUT endpoint or the interval of the ISOC OUT
endpoint is shorter than that of the IN endpoint. Consequently,
the OUT service is neglected when an IN endpoint with a service
interval exceeding 32ms is scheduled concurrently (every 64ms in
this scenario).

This issue is particularly seen on certain older AMD platforms.
To mitigate this problem, it is recommended to adjust the service
interval of the IN endpoint to not exceed 32ms (interval 8). This
adjustment ensures that the OUT endpoint will not be bypassed,
even if a smaller interval value is utilized.

Cc: stable <stable@kernel.org>
Signed-off-by: Raju Rangoju <Raju.Rangoju@amd.com>
Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Link: https://lore.kernel.org/r/20250627144127.3889714-2-mathias.nyman@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/host/xhci-mem.c |  4 ++++
 drivers/usb/host/xhci-pci.c | 25 +++++++++++++++++++++++++
 drivers/usb/host/xhci.h     |  1 +
 3 files changed, 30 insertions(+)

diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c
index bd745a0f2f78..6680afa4f596 100644
--- a/drivers/usb/host/xhci-mem.c
+++ b/drivers/usb/host/xhci-mem.c
@@ -1449,6 +1449,10 @@ int xhci_endpoint_init(struct xhci_hcd *xhci,
 	/* Periodic endpoint bInterval limit quirk */
 	if (usb_endpoint_xfer_int(&ep->desc) ||
 	    usb_endpoint_xfer_isoc(&ep->desc)) {
+		if ((xhci->quirks & XHCI_LIMIT_ENDPOINT_INTERVAL_9) &&
+		    interval >= 9) {
+			interval = 8;
+		}
 		if ((xhci->quirks & XHCI_LIMIT_ENDPOINT_INTERVAL_7) &&
 		    udev->speed >= USB_SPEED_HIGH &&
 		    interval >= 7) {
diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c
index 0c481cbc8f08..00fac8b233d2 100644
--- a/drivers/usb/host/xhci-pci.c
+++ b/drivers/usb/host/xhci-pci.c
@@ -71,12 +71,22 @@
 #define PCI_DEVICE_ID_INTEL_TITAN_RIDGE_4C_XHCI		0x15ec
 #define PCI_DEVICE_ID_INTEL_TITAN_RIDGE_DD_XHCI		0x15f0
 
+#define PCI_DEVICE_ID_AMD_ARIEL_TYPEC_XHCI		0x13ed
+#define PCI_DEVICE_ID_AMD_ARIEL_TYPEA_XHCI		0x13ee
+#define PCI_DEVICE_ID_AMD_STARSHIP_XHCI			0x148c
+#define PCI_DEVICE_ID_AMD_FIREFLIGHT_15D4_XHCI		0x15d4
+#define PCI_DEVICE_ID_AMD_FIREFLIGHT_15D5_XHCI		0x15d5
+#define PCI_DEVICE_ID_AMD_RAVEN_15E0_XHCI		0x15e0
+#define PCI_DEVICE_ID_AMD_RAVEN_15E1_XHCI		0x15e1
+#define PCI_DEVICE_ID_AMD_RAVEN2_XHCI			0x15e5
 #define PCI_DEVICE_ID_AMD_RENOIR_XHCI			0x1639
 #define PCI_DEVICE_ID_AMD_PROMONTORYA_4			0x43b9
 #define PCI_DEVICE_ID_AMD_PROMONTORYA_3			0x43ba
 #define PCI_DEVICE_ID_AMD_PROMONTORYA_2			0x43bb
 #define PCI_DEVICE_ID_AMD_PROMONTORYA_1			0x43bc
 
+#define PCI_DEVICE_ID_ATI_NAVI10_7316_XHCI		0x7316
+
 #define PCI_DEVICE_ID_ASMEDIA_1042_XHCI			0x1042
 #define PCI_DEVICE_ID_ASMEDIA_1042A_XHCI		0x1142
 #define PCI_DEVICE_ID_ASMEDIA_1142_XHCI			0x1242
@@ -280,6 +290,21 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci)
 	if (pdev->vendor == PCI_VENDOR_ID_NEC)
 		xhci->quirks |= XHCI_NEC_HOST;
 
+	if (pdev->vendor == PCI_VENDOR_ID_AMD &&
+	    (pdev->device == PCI_DEVICE_ID_AMD_ARIEL_TYPEC_XHCI ||
+	     pdev->device == PCI_DEVICE_ID_AMD_ARIEL_TYPEA_XHCI ||
+	     pdev->device == PCI_DEVICE_ID_AMD_STARSHIP_XHCI ||
+	     pdev->device == PCI_DEVICE_ID_AMD_FIREFLIGHT_15D4_XHCI ||
+	     pdev->device == PCI_DEVICE_ID_AMD_FIREFLIGHT_15D5_XHCI ||
+	     pdev->device == PCI_DEVICE_ID_AMD_RAVEN_15E0_XHCI ||
+	     pdev->device == PCI_DEVICE_ID_AMD_RAVEN_15E1_XHCI ||
+	     pdev->device == PCI_DEVICE_ID_AMD_RAVEN2_XHCI))
+		xhci->quirks |= XHCI_LIMIT_ENDPOINT_INTERVAL_9;
+
+	if (pdev->vendor == PCI_VENDOR_ID_ATI &&
+	    pdev->device == PCI_DEVICE_ID_ATI_NAVI10_7316_XHCI)
+		xhci->quirks |= XHCI_LIMIT_ENDPOINT_INTERVAL_9;
+
 	if (pdev->vendor == PCI_VENDOR_ID_AMD && xhci->hci_version == 0x96)
 		xhci->quirks |= XHCI_AMD_0x96_HOST;
 
diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h
index fa1ea0e0c7fb..a20f4e7cd43a 100644
--- a/drivers/usb/host/xhci.h
+++ b/drivers/usb/host/xhci.h
@@ -1643,6 +1643,7 @@ struct xhci_hcd {
 #define XHCI_WRITE_64_HI_LO	BIT_ULL(47)
 #define XHCI_CDNS_SCTX_QUIRK	BIT_ULL(48)
 #define XHCI_ETRON_HOST	BIT_ULL(49)
+#define XHCI_LIMIT_ENDPOINT_INTERVAL_9 BIT_ULL(50)
 
 	unsigned int		num_active_eps;
 	unsigned int		limit_active_eps;

From cd65ee81240e8bc3c3119b46db7f60c80864b90b Mon Sep 17 00:00:00 2001
From: Hongyu Xie <xiehongyu1@kylinos.cn>
Date: Fri, 27 Jun 2025 17:41:20 +0300
Subject: [PATCH 0978/1334] xhci: Disable stream for xHC controller with
 XHCI_BROKEN_STREAMS

Disable stream for platform xHC controller with broken stream.

Fixes: 14aec589327a6 ("storage: accept some UAS devices if streams are unavailable")
Cc: stable <stable@kernel.org>
Signed-off-by: Hongyu Xie <xiehongyu1@kylinos.cn>
Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Link: https://lore.kernel.org/r/20250627144127.3889714-3-mathias.nyman@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/host/xhci-plat.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/usb/host/xhci-plat.c b/drivers/usb/host/xhci-plat.c
index 6dab142e7278..c79d5ed48a08 100644
--- a/drivers/usb/host/xhci-plat.c
+++ b/drivers/usb/host/xhci-plat.c
@@ -328,7 +328,8 @@ int xhci_plat_probe(struct platform_device *pdev, struct device *sysdev, const s
 	}
 
 	usb3_hcd = xhci_get_usb3_hcd(xhci);
-	if (usb3_hcd && HCC_MAX_PSA(xhci->hcc_params) >= 4)
+	if (usb3_hcd && HCC_MAX_PSA(xhci->hcc_params) >= 4 &&
+	    !(xhci->quirks & XHCI_BROKEN_STREAMS))
 		usb3_hcd->can_do_streams = 1;
 
 	if (xhci->shared_hcd) {

From 2b857d69a5e116150639a0c6c39c86cc329939ee Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=C5=81ukasz=20Bartosik?= <ukaszb@chromium.org>
Date: Fri, 27 Jun 2025 17:41:21 +0300
Subject: [PATCH 0979/1334] xhci: dbctty: disable ECHO flag by default
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When /dev/ttyDBC0 device is created then by default ECHO flag
is set for the terminal device. However if data arrives from
a peer before application using /dev/ttyDBC0 applies its set
of terminal flags then the arriving data will be echoed which
might not be desired behavior.

Fixes: 4521f1613940 ("xhci: dbctty: split dbc tty driver registration and unregistration functions.")
Cc: stable <stable@kernel.org>
Signed-off-by: Łukasz Bartosik <ukaszb@chromium.org>
Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Link: https://lore.kernel.org/stable/20250610111802.18742-1-ukaszb%40chromium.org
Link: https://lore.kernel.org/r/20250627144127.3889714-4-mathias.nyman@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/host/xhci-dbgtty.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/usb/host/xhci-dbgtty.c b/drivers/usb/host/xhci-dbgtty.c
index 60ed753c85bb..d894081d8d15 100644
--- a/drivers/usb/host/xhci-dbgtty.c
+++ b/drivers/usb/host/xhci-dbgtty.c
@@ -617,6 +617,7 @@ int dbc_tty_init(void)
 	dbc_tty_driver->type = TTY_DRIVER_TYPE_SERIAL;
 	dbc_tty_driver->subtype = SERIAL_TYPE_NORMAL;
 	dbc_tty_driver->init_termios = tty_std_termios;
+	dbc_tty_driver->init_termios.c_lflag &= ~ECHO;
 	dbc_tty_driver->init_termios.c_cflag =
 			B9600 | CS8 | CREAD | HUPCL | CLOCAL;
 	dbc_tty_driver->init_termios.c_ispeed = 9600;

From efe3e3ae5a66cb38ef29c909e951b4039044bae9 Mon Sep 17 00:00:00 2001
From: Mathias Nyman <mathias.nyman@linux.intel.com>
Date: Fri, 27 Jun 2025 17:41:22 +0300
Subject: [PATCH 0980/1334] xhci: dbc: Flush queued requests before stopping
 dbc

Flush dbc requests when dbc is stopped and transfer rings are freed.
Failure to flush them lead to leaking memory and dbc completing odd
requests after resuming from suspend, leading to error messages such as:

[   95.344392] xhci_hcd 0000:00:0d.0: no matched request

Cc: stable <stable@kernel.org>
Fixes: dfba2174dc42 ("usb: xhci: Add DbC support in xHCI driver")
Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Link: https://lore.kernel.org/r/20250627144127.3889714-5-mathias.nyman@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/host/xhci-dbgcap.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/usb/host/xhci-dbgcap.c b/drivers/usb/host/xhci-dbgcap.c
index 0d4ce5734165..06a2edb9e86e 100644
--- a/drivers/usb/host/xhci-dbgcap.c
+++ b/drivers/usb/host/xhci-dbgcap.c
@@ -652,6 +652,10 @@ static void xhci_dbc_stop(struct xhci_dbc *dbc)
 	case DS_DISABLED:
 		return;
 	case DS_CONFIGURED:
+		spin_lock(&dbc->lock);
+		xhci_dbc_flush_requests(dbc);
+		spin_unlock(&dbc->lock);
+
 		if (dbc->driver->disconnect)
 			dbc->driver->disconnect(dbc);
 		break;

From 45537926dd2aaa9190ac0fac5a0fbeefcadfea95 Mon Sep 17 00:00:00 2001
From: Niklas Schnelle <schnelle@linux.ibm.com>
Date: Wed, 25 Jun 2025 11:28:28 +0200
Subject: [PATCH 0981/1334] s390/pci: Fix stale function handles in error
 handling

The error event information for PCI error events contains a function
handle for the respective function. This handle is generally captured at
the time the error event was recorded. Due to delays in processing or
cascading issues, it may happen that during firmware recovery multiple
events are generated. When processing these events in order Linux may
already have recovered an affected function making the event information
stale. Fix this by doing an unconditional CLP List PCI function
retrieving the current function handle with the zdev->state_lock held
and ignoring the event if its function handle is stale.

Cc: stable@vger.kernel.org
Fixes: 4cdf2f4e24ff ("s390/pci: implement minimal PCI error recovery")
Reviewed-by: Julian Ruess <julianr@linux.ibm.com>
Reviewed-by: Gerd Bayer <gbayer@linux.ibm.com>
Reviewed-by: Farhan Ali <alifm@linux.ibm.com>
Signed-off-by: Niklas Schnelle <schnelle@linux.ibm.com>
Signed-off-by: Alexander Gordeev <agordeev@linux.ibm.com>
---
 arch/s390/pci/pci_event.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/arch/s390/pci/pci_event.c b/arch/s390/pci/pci_event.c
index 2fbee3887d13..82ee2578279a 100644
--- a/arch/s390/pci/pci_event.c
+++ b/arch/s390/pci/pci_event.c
@@ -273,6 +273,8 @@ static void __zpci_event_error(struct zpci_ccdf_err *ccdf)
 	struct zpci_dev *zdev = get_zdev_by_fid(ccdf->fid);
 	struct pci_dev *pdev = NULL;
 	pci_ers_result_t ers_res;
+	u32 fh = 0;
+	int rc;
 
 	zpci_dbg(3, "err fid:%x, fh:%x, pec:%x\n",
 		 ccdf->fid, ccdf->fh, ccdf->pec);
@@ -281,6 +283,15 @@ static void __zpci_event_error(struct zpci_ccdf_err *ccdf)
 
 	if (zdev) {
 		mutex_lock(&zdev->state_lock);
+		rc = clp_refresh_fh(zdev->fid, &fh);
+		if (rc)
+			goto no_pdev;
+		if (!fh || ccdf->fh != fh) {
+			/* Ignore events with stale handles */
+			zpci_dbg(3, "err fid:%x, fh:%x (stale %x)\n",
+				 ccdf->fid, fh, ccdf->fh);
+			goto no_pdev;
+		}
 		zpci_update_fh(zdev, ccdf->fh);
 		if (zdev->zbus->bus)
 			pdev = pci_get_slot(zdev->zbus->bus, zdev->devfn);

From b97a7972b1f4f81417840b9a2ab0c19722b577d5 Mon Sep 17 00:00:00 2001
From: Niklas Schnelle <schnelle@linux.ibm.com>
Date: Wed, 25 Jun 2025 11:28:29 +0200
Subject: [PATCH 0982/1334] s390/pci: Do not try re-enabling load/store if
 device is disabled

If a device is disabled unblocking load/store on its own is not useful
as a full re-enable of the function is necessary anyway. Note that SCLP
Write Event Data Action Qualifier 0 (Reset) leaves the device disabled
and triggers this case unless the driver already requests a reset.

Cc: stable@vger.kernel.org
Fixes: 4cdf2f4e24ff ("s390/pci: implement minimal PCI error recovery")
Reviewed-by: Farhan Ali <alifm@linux.ibm.com>
Signed-off-by: Niklas Schnelle <schnelle@linux.ibm.com>
Signed-off-by: Alexander Gordeev <agordeev@linux.ibm.com>
---
 arch/s390/pci/pci_event.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/arch/s390/pci/pci_event.c b/arch/s390/pci/pci_event.c
index 82ee2578279a..6c8922ad70f3 100644
--- a/arch/s390/pci/pci_event.c
+++ b/arch/s390/pci/pci_event.c
@@ -106,6 +106,10 @@ static pci_ers_result_t zpci_event_do_error_state_clear(struct pci_dev *pdev,
 	struct zpci_dev *zdev = to_zpci(pdev);
 	int rc;
 
+	/* The underlying device may have been disabled by the event */
+	if (!zdev_enabled(zdev))
+		return PCI_ERS_RESULT_NEED_RESET;
+
 	pr_info("%s: Unblocking device access for examination\n", pci_name(pdev));
 	rc = zpci_reset_load_store_blocked(zdev);
 	if (rc) {

From 62355f1f87b8c7f8785a8dd3cd5ca6e5b513566a Mon Sep 17 00:00:00 2001
From: Niklas Schnelle <schnelle@linux.ibm.com>
Date: Wed, 25 Jun 2025 11:28:30 +0200
Subject: [PATCH 0983/1334] s390/pci: Allow automatic recovery with minimal
 driver support

According to Documentation/PCI/pci-error-recovery.rst only the
error_detected() callback in the err_handler struct is mandatory for
a driver to support error recovery. So far s390's error recovery chose
a stricter approach also requiring slot_reset() and resume().

Relax this requirement and only require error_detected(). If a callback
is not implemented EEH and AER treat this as PCI_ERS_RESULT_NONE. This
return value is otherwise used by drivers abstaining from their vote
on how to proceed with recovery and currently also not supported by
s390's recovery code.

So to support missing callbacks in-line with other implementors of the
recovery flow, also handle PCI_ERS_RESULT_NONE. Since s390 only does per
PCI function recovery and does not do voting, treat PCI_ERS_RESULT_NONE
optimistically and proceed through recovery unless other failures
prevent this.

Reviewed-by: Farhan Ali <alifm@linux.ibm.com>
Reviewed-by: Julian Ruess <julianr@linux.ibm.com>
Signed-off-by: Niklas Schnelle <schnelle@linux.ibm.com>
Signed-off-by: Alexander Gordeev <agordeev@linux.ibm.com>
---
 arch/s390/pci/pci_event.c | 44 ++++++++++++++++++++++++++-------------
 1 file changed, 29 insertions(+), 15 deletions(-)

diff --git a/arch/s390/pci/pci_event.c b/arch/s390/pci/pci_event.c
index 6c8922ad70f3..d930416d4c90 100644
--- a/arch/s390/pci/pci_event.c
+++ b/arch/s390/pci/pci_event.c
@@ -54,6 +54,7 @@ static inline bool ers_result_indicates_abort(pci_ers_result_t ers_res)
 	case PCI_ERS_RESULT_CAN_RECOVER:
 	case PCI_ERS_RESULT_RECOVERED:
 	case PCI_ERS_RESULT_NEED_RESET:
+	case PCI_ERS_RESULT_NONE:
 		return false;
 	default:
 		return true;
@@ -78,10 +79,6 @@ static bool is_driver_supported(struct pci_driver *driver)
 		return false;
 	if (!driver->err_handler->error_detected)
 		return false;
-	if (!driver->err_handler->slot_reset)
-		return false;
-	if (!driver->err_handler->resume)
-		return false;
 	return true;
 }
 
@@ -118,16 +115,18 @@ static pci_ers_result_t zpci_event_do_error_state_clear(struct pci_dev *pdev,
 		return PCI_ERS_RESULT_NEED_RESET;
 	}
 
-	if (driver->err_handler->mmio_enabled) {
+	if (driver->err_handler->mmio_enabled)
 		ers_res = driver->err_handler->mmio_enabled(pdev);
-		if (ers_result_indicates_abort(ers_res)) {
-			pr_info("%s: Automatic recovery failed after MMIO re-enable\n",
-				pci_name(pdev));
-			return ers_res;
-		} else if (ers_res == PCI_ERS_RESULT_NEED_RESET) {
-			pr_debug("%s: Driver needs reset to recover\n", pci_name(pdev));
-			return ers_res;
-		}
+	else
+		ers_res = PCI_ERS_RESULT_NONE;
+
+	if (ers_result_indicates_abort(ers_res)) {
+		pr_info("%s: Automatic recovery failed after MMIO re-enable\n",
+			pci_name(pdev));
+		return ers_res;
+	} else if (ers_res == PCI_ERS_RESULT_NEED_RESET) {
+		pr_debug("%s: Driver needs reset to recover\n", pci_name(pdev));
+		return ers_res;
 	}
 
 	pr_debug("%s: Unblocking DMA\n", pci_name(pdev));
@@ -154,7 +153,12 @@ static pci_ers_result_t zpci_event_do_reset(struct pci_dev *pdev,
 		return ers_res;
 	}
 	pdev->error_state = pci_channel_io_normal;
-	ers_res = driver->err_handler->slot_reset(pdev);
+
+	if (driver->err_handler->slot_reset)
+		ers_res = driver->err_handler->slot_reset(pdev);
+	else
+		ers_res = PCI_ERS_RESULT_NONE;
+
 	if (ers_result_indicates_abort(ers_res)) {
 		pr_info("%s: Automatic recovery failed after slot reset\n", pci_name(pdev));
 		return ers_res;
@@ -218,7 +222,7 @@ static pci_ers_result_t zpci_event_attempt_error_recovery(struct pci_dev *pdev)
 		goto out_unlock;
 	}
 
-	if (ers_res == PCI_ERS_RESULT_CAN_RECOVER) {
+	if (ers_res != PCI_ERS_RESULT_NEED_RESET) {
 		ers_res = zpci_event_do_error_state_clear(pdev, driver);
 		if (ers_result_indicates_abort(ers_res)) {
 			status_str = "failed (abort on MMIO enable)";
@@ -229,6 +233,16 @@ static pci_ers_result_t zpci_event_attempt_error_recovery(struct pci_dev *pdev)
 	if (ers_res == PCI_ERS_RESULT_NEED_RESET)
 		ers_res = zpci_event_do_reset(pdev, driver);
 
+	/*
+	 * ers_res can be PCI_ERS_RESULT_NONE either because the driver
+	 * decided to return it, indicating that it abstains from voting
+	 * on how to recover, or because it didn't implement the callback.
+	 * Both cases assume, that if there is nothing else causing a
+	 * disconnect, we recovered successfully.
+	 */
+	if (ers_res == PCI_ERS_RESULT_NONE)
+		ers_res = PCI_ERS_RESULT_RECOVERED;
+
 	if (ers_res != PCI_ERS_RESULT_RECOVERED) {
 		pr_err("%s: Automatic recovery failed; operator intervention is required\n",
 		       pci_name(pdev));

From 14da58521ee5b31976f5b5b437438b8f28f9ba51 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Sat, 28 Jun 2025 21:54:58 -0400
Subject: [PATCH 0984/1334] bcachefs: fix btree_trans_peek_prev_journal()

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/btree_iter.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/bcachefs/btree_iter.c b/fs/bcachefs/btree_iter.c
index 352f9cd2634f..f8829b667ad3 100644
--- a/fs/bcachefs/btree_iter.c
+++ b/fs/bcachefs/btree_iter.c
@@ -2189,7 +2189,7 @@ void btree_trans_peek_prev_journal(struct btree_trans *trans,
 	struct btree_path *path = btree_iter_path(trans, iter);
 	struct bkey_i *next_journal =
 		bch2_btree_journal_peek_prev(trans, iter, search_key,
-				k->k ? k->k->p : path_l(path)->b->key.k.p);
+				k->k ? k->k->p : path_l(path)->b->data->min_key);
 
 	if (next_journal) {
 		iter->k = next_journal->k;

From 18665eaa2acbe17da11c2748ac43c2f4ec2fad85 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= <thomas.weissschuh@linutronix.de>
Date: Wed, 18 Jun 2025 09:52:21 +0200
Subject: [PATCH 0985/1334] drm/exynos: Don't use %pK through printk
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In the past %pK was preferable to %p as it would not leak raw pointer
values into the kernel log.
Since commit ad67b74d2469 ("printk: hash addresses printed with %p")
the regular %p has been improved to avoid this issue.
Furthermore, restricted pointers ("%pK") were never meant to be used
through printk(). They can still unintentionally leak raw pointers or
acquire sleeping locks in atomic contexts.

Switch to the regular pointer formatting which is safer and
easier to reason about.

Signed-off-by: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Signed-off-by: Inki Dae <inki.dae@samsung.com>
---
 drivers/gpu/drm/exynos/exynos_drm_gem.c |  2 +-
 drivers/gpu/drm/exynos/exynos_drm_ipp.c | 32 ++++++++++++-------------
 2 files changed, 17 insertions(+), 17 deletions(-)

diff --git a/drivers/gpu/drm/exynos/exynos_drm_gem.c b/drivers/gpu/drm/exynos/exynos_drm_gem.c
index 4787fee4696f..d44401a695e2 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_gem.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_gem.c
@@ -174,7 +174,7 @@ static struct exynos_drm_gem *exynos_drm_gem_init(struct drm_device *dev,
 		return ERR_PTR(ret);
 	}
 
-	DRM_DEV_DEBUG_KMS(dev->dev, "created file object = %pK\n", obj->filp);
+	DRM_DEV_DEBUG_KMS(dev->dev, "created file object = %p\n", obj->filp);
 
 	return exynos_gem;
 }
diff --git a/drivers/gpu/drm/exynos/exynos_drm_ipp.c b/drivers/gpu/drm/exynos/exynos_drm_ipp.c
index ea9f66037600..03c8490af4f4 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_ipp.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_ipp.c
@@ -271,7 +271,7 @@ static inline struct exynos_drm_ipp_task *
 	task->src.rect.h = task->dst.rect.h = UINT_MAX;
 	task->transform.rotation = DRM_MODE_ROTATE_0;
 
-	DRM_DEV_DEBUG_DRIVER(task->dev, "Allocated task %pK\n", task);
+	DRM_DEV_DEBUG_DRIVER(task->dev, "Allocated task %p\n", task);
 
 	return task;
 }
@@ -339,7 +339,7 @@ static int exynos_drm_ipp_task_set(struct exynos_drm_ipp_task *task,
 	}
 
 	DRM_DEV_DEBUG_DRIVER(task->dev,
-			     "Got task %pK configuration from userspace\n",
+			     "Got task %p configuration from userspace\n",
 			     task);
 	return 0;
 }
@@ -394,7 +394,7 @@ static void exynos_drm_ipp_task_release_buf(struct exynos_drm_ipp_buffer *buf)
 static void exynos_drm_ipp_task_free(struct exynos_drm_ipp *ipp,
 				 struct exynos_drm_ipp_task *task)
 {
-	DRM_DEV_DEBUG_DRIVER(task->dev, "Freeing task %pK\n", task);
+	DRM_DEV_DEBUG_DRIVER(task->dev, "Freeing task %p\n", task);
 
 	exynos_drm_ipp_task_release_buf(&task->src);
 	exynos_drm_ipp_task_release_buf(&task->dst);
@@ -559,7 +559,7 @@ static int exynos_drm_ipp_check_format(struct exynos_drm_ipp_task *task,
 					    DRM_EXYNOS_IPP_FORMAT_DESTINATION);
 	if (!fmt) {
 		DRM_DEV_DEBUG_DRIVER(task->dev,
-				     "Task %pK: %s format not supported\n",
+				     "Task %p: %s format not supported\n",
 				     task, buf == src ? "src" : "dst");
 		return -EINVAL;
 	}
@@ -609,7 +609,7 @@ static int exynos_drm_ipp_task_check(struct exynos_drm_ipp_task *task)
 	bool rotate = (rotation != DRM_MODE_ROTATE_0);
 	bool scale = false;
 
-	DRM_DEV_DEBUG_DRIVER(task->dev, "Checking task %pK\n", task);
+	DRM_DEV_DEBUG_DRIVER(task->dev, "Checking task %p\n", task);
 
 	if (src->rect.w == UINT_MAX)
 		src->rect.w = src->buf.width;
@@ -625,7 +625,7 @@ static int exynos_drm_ipp_task_check(struct exynos_drm_ipp_task *task)
 	    dst->rect.x + dst->rect.w > (dst->buf.width) ||
 	    dst->rect.y + dst->rect.h > (dst->buf.height)) {
 		DRM_DEV_DEBUG_DRIVER(task->dev,
-				     "Task %pK: defined area is outside provided buffers\n",
+				     "Task %p: defined area is outside provided buffers\n",
 				     task);
 		return -EINVAL;
 	}
@@ -642,7 +642,7 @@ static int exynos_drm_ipp_task_check(struct exynos_drm_ipp_task *task)
 	    (!(ipp->capabilities & DRM_EXYNOS_IPP_CAP_SCALE) && scale) ||
 	    (!(ipp->capabilities & DRM_EXYNOS_IPP_CAP_CONVERT) &&
 	     src->buf.fourcc != dst->buf.fourcc)) {
-		DRM_DEV_DEBUG_DRIVER(task->dev, "Task %pK: hw capabilities exceeded\n",
+		DRM_DEV_DEBUG_DRIVER(task->dev, "Task %p: hw capabilities exceeded\n",
 				     task);
 		return -EINVAL;
 	}
@@ -655,7 +655,7 @@ static int exynos_drm_ipp_task_check(struct exynos_drm_ipp_task *task)
 	if (ret)
 		return ret;
 
-	DRM_DEV_DEBUG_DRIVER(ipp->dev, "Task %pK: all checks done.\n",
+	DRM_DEV_DEBUG_DRIVER(ipp->dev, "Task %p: all checks done.\n",
 			     task);
 
 	return ret;
@@ -667,25 +667,25 @@ static int exynos_drm_ipp_task_setup_buffers(struct exynos_drm_ipp_task *task,
 	struct exynos_drm_ipp_buffer *src = &task->src, *dst = &task->dst;
 	int ret = 0;
 
-	DRM_DEV_DEBUG_DRIVER(task->dev, "Setting buffer for task %pK\n",
+	DRM_DEV_DEBUG_DRIVER(task->dev, "Setting buffer for task %p\n",
 			     task);
 
 	ret = exynos_drm_ipp_task_setup_buffer(src, filp);
 	if (ret) {
 		DRM_DEV_DEBUG_DRIVER(task->dev,
-				     "Task %pK: src buffer setup failed\n",
+				     "Task %p: src buffer setup failed\n",
 				     task);
 		return ret;
 	}
 	ret = exynos_drm_ipp_task_setup_buffer(dst, filp);
 	if (ret) {
 		DRM_DEV_DEBUG_DRIVER(task->dev,
-				     "Task %pK: dst buffer setup failed\n",
+				     "Task %p: dst buffer setup failed\n",
 				     task);
 		return ret;
 	}
 
-	DRM_DEV_DEBUG_DRIVER(task->dev, "Task %pK: buffers prepared.\n",
+	DRM_DEV_DEBUG_DRIVER(task->dev, "Task %p: buffers prepared.\n",
 			     task);
 
 	return ret;
@@ -764,7 +764,7 @@ void exynos_drm_ipp_task_done(struct exynos_drm_ipp_task *task, int ret)
 	struct exynos_drm_ipp *ipp = task->ipp;
 	unsigned long flags;
 
-	DRM_DEV_DEBUG_DRIVER(task->dev, "ipp: %d, task %pK done: %d\n",
+	DRM_DEV_DEBUG_DRIVER(task->dev, "ipp: %d, task %p done: %d\n",
 			     ipp->id, task, ret);
 
 	spin_lock_irqsave(&ipp->lock, flags);
@@ -807,7 +807,7 @@ static void exynos_drm_ipp_next_task(struct exynos_drm_ipp *ipp)
 	spin_unlock_irqrestore(&ipp->lock, flags);
 
 	DRM_DEV_DEBUG_DRIVER(ipp->dev,
-			     "ipp: %d, selected task %pK to run\n", ipp->id,
+			     "ipp: %d, selected task %p to run\n", ipp->id,
 			     task);
 
 	ret = ipp->funcs->commit(ipp, task);
@@ -917,14 +917,14 @@ int exynos_drm_ipp_commit_ioctl(struct drm_device *dev, void *data,
 	 */
 	if (arg->flags & DRM_EXYNOS_IPP_FLAG_NONBLOCK) {
 		DRM_DEV_DEBUG_DRIVER(ipp->dev,
-				     "ipp: %d, nonblocking processing task %pK\n",
+				     "ipp: %d, nonblocking processing task %p\n",
 				     ipp->id, task);
 
 		task->flags |= DRM_EXYNOS_IPP_TASK_ASYNC;
 		exynos_drm_ipp_schedule_task(task->ipp, task);
 		ret = 0;
 	} else {
-		DRM_DEV_DEBUG_DRIVER(ipp->dev, "ipp: %d, processing task %pK\n",
+		DRM_DEV_DEBUG_DRIVER(ipp->dev, "ipp: %d, processing task %p\n",
 				     ipp->id, task);
 		exynos_drm_ipp_schedule_task(ipp, task);
 		ret = wait_event_interruptible(ipp->done_wq,

From b846350aa272de99bf6fecfa6b08e64ebfb13173 Mon Sep 17 00:00:00 2001
From: Kaustabh Chakraborty <kauschluss@disroot.org>
Date: Fri, 27 Jun 2025 00:50:30 +0530
Subject: [PATCH 0986/1334] drm/exynos: exynos7_drm_decon: add vblank check in
 IRQ handling

If there's support for another console device (such as a TTY serial),
the kernel occasionally panics during boot. The panic message and a
relevant snippet of the call stack is as follows:

  Unable to handle kernel NULL pointer dereference at virtual address 000000000000000
  Call trace:
    drm_crtc_handle_vblank+0x10/0x30 (P)
    decon_irq_handler+0x88/0xb4
    [...]

Otherwise, the panics don't happen. This indicates that it's some sort
of race condition.

Add a check to validate if the drm device can handle vblanks before
calling drm_crtc_handle_vblank() to avoid this.

Cc: stable@vger.kernel.org
Fixes: 96976c3d9aff ("drm/exynos: Add DECON driver")
Signed-off-by: Kaustabh Chakraborty <kauschluss@disroot.org>
Signed-off-by: Inki Dae <inki.dae@samsung.com>
---
 drivers/gpu/drm/exynos/exynos7_drm_decon.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/gpu/drm/exynos/exynos7_drm_decon.c b/drivers/gpu/drm/exynos/exynos7_drm_decon.c
index f91daefa9d2b..805aa28c1723 100644
--- a/drivers/gpu/drm/exynos/exynos7_drm_decon.c
+++ b/drivers/gpu/drm/exynos/exynos7_drm_decon.c
@@ -636,6 +636,10 @@ static irqreturn_t decon_irq_handler(int irq, void *dev_id)
 	if (!ctx->drm_dev)
 		goto out;
 
+	/* check if crtc and vblank have been initialized properly */
+	if (!drm_dev_has_vblank(ctx->drm_dev))
+		goto out;
+
 	if (!ctx->i80_if) {
 		drm_crtc_handle_vblank(&ctx->crtc->base);
 

From 5d91394f236167ac624b823820faf4aa928b889e Mon Sep 17 00:00:00 2001
From: Marek Szyprowski <m.szyprowski@samsung.com>
Date: Wed, 18 Jun 2025 14:06:26 +0200
Subject: [PATCH 0987/1334] drm/exynos: fimd: Guard display clock control with
 runtime PM calls

Commit c9b1150a68d9 ("drm/atomic-helper: Re-order bridge chain pre-enable
and post-disable") changed the call sequence to the CRTC enable/disable
and bridge pre_enable/post_disable methods, so those bridge methods are
now called when CRTC is not yet enabled.

This causes a lockup observed on Samsung Peach-Pit/Pi Chromebooks. The
source of this lockup is a call to fimd_dp_clock_enable() function, when
FIMD device is not yet runtime resumed. It worked before the mentioned
commit only because the CRTC implemented by the FIMD driver was always
enabled what guaranteed the FIMD device to be runtime resumed.

This patch adds runtime PM guards to the fimd_dp_clock_enable() function
to enable its proper operation also when the CRTC implemented by FIMD is
not yet enabled.

Fixes: 196e059a8a6a ("drm/exynos: convert clock_enable crtc callback to pipeline clock")
Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>
Reviewed-by: Tomi Valkeinen <tomi.valkeinen@ideasonboard.com>
Signed-off-by: Inki Dae <inki.dae@samsung.com>
---
 drivers/gpu/drm/exynos/exynos_drm_fimd.c | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimd.c b/drivers/gpu/drm/exynos/exynos_drm_fimd.c
index c394cc702d7d..205c238cc73a 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_fimd.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_fimd.c
@@ -187,6 +187,7 @@ struct fimd_context {
 	u32				i80ifcon;
 	bool				i80_if;
 	bool				suspended;
+	bool				dp_clk_enabled;
 	wait_queue_head_t		wait_vsync_queue;
 	atomic_t			wait_vsync_event;
 	atomic_t			win_updated;
@@ -1047,7 +1048,18 @@ static void fimd_dp_clock_enable(struct exynos_drm_clk *clk, bool enable)
 	struct fimd_context *ctx = container_of(clk, struct fimd_context,
 						dp_clk);
 	u32 val = enable ? DP_MIE_CLK_DP_ENABLE : DP_MIE_CLK_DISABLE;
+
+	if (enable == ctx->dp_clk_enabled)
+		return;
+
+	if (enable)
+		pm_runtime_resume_and_get(ctx->dev);
+
+	ctx->dp_clk_enabled = enable;
 	writel(val, ctx->regs + DP_MIE_CLKCON);
+
+	if (!enable)
+		pm_runtime_put(ctx->dev);
 }
 
 static const struct exynos_drm_crtc_ops fimd_crtc_ops = {

From 2ab3ba39153dcdc9de7d2eec42bf19f84d4844cf Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= <thomas.weissschuh@linutronix.de>
Date: Wed, 18 Jun 2025 09:52:20 +0200
Subject: [PATCH 0988/1334] drm/bridge: samsung-dsim: Don't use %pK through
 printk
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In the past %pK was preferable to %p as it would not leak raw pointer
values into the kernel log.
Since commit ad67b74d2469 ("printk: hash addresses printed with %p")
the regular %p has been improved to avoid this issue.
Furthermore, restricted pointers ("%pK") were never meant to be used
through printk(). They can still unintentionally leak raw pointers or
acquire sleeping locks in atomic contexts.

Switch to the regular pointer formatting which is safer and
easier to reason about.

Signed-off-by: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Signed-off-by: Inki Dae <inki.dae@samsung.com>
---
 drivers/gpu/drm/bridge/samsung-dsim.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/bridge/samsung-dsim.c b/drivers/gpu/drm/bridge/samsung-dsim.c
index 0014c497e3fe..bccc88d25948 100644
--- a/drivers/gpu/drm/bridge/samsung-dsim.c
+++ b/drivers/gpu/drm/bridge/samsung-dsim.c
@@ -1095,7 +1095,7 @@ static void samsung_dsim_send_to_fifo(struct samsung_dsim *dsi,
 	bool first = !xfer->tx_done;
 	u32 reg;
 
-	dev_dbg(dev, "< xfer %pK: tx len %u, done %u, rx len %u, done %u\n",
+	dev_dbg(dev, "< xfer %p: tx len %u, done %u, rx len %u, done %u\n",
 		xfer, length, xfer->tx_done, xfer->rx_len, xfer->rx_done);
 
 	if (length > DSI_TX_FIFO_SIZE)
@@ -1293,7 +1293,7 @@ static bool samsung_dsim_transfer_finish(struct samsung_dsim *dsi)
 	spin_unlock_irqrestore(&dsi->transfer_lock, flags);
 
 	dev_dbg(dsi->dev,
-		"> xfer %pK, tx_len %zu, tx_done %u, rx_len %u, rx_done %u\n",
+		"> xfer %p, tx_len %zu, tx_done %u, rx_len %u, rx_done %u\n",
 		xfer, xfer->packet.payload_length, xfer->tx_done, xfer->rx_len,
 		xfer->rx_done);
 

From e0a911ac86857a73182edde9e50d9b4b949b7f01 Mon Sep 17 00:00:00 2001
From: Daniel Dadap <ddadap@nvidia.com>
Date: Thu, 26 Jun 2025 16:16:30 -0500
Subject: [PATCH 0989/1334] ALSA: hda: Add missing NVIDIA HDA codec IDs

Add codec IDs for several NVIDIA products with HDA controllers to the
snd_hda_id_hdmi[] patch table.

Signed-off-by: Daniel Dadap <ddadap@nvidia.com>
Cc: <stable@vger.kernel.org>
Link: https://patch.msgid.link/aF24rqwMKFWoHu12@ddadap-lakeline.nvidia.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/patch_hdmi.c | 19 +++++++++++++++++++
 1 file changed, 19 insertions(+)

diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c
index 08308231b4ed..9a7793eb16e9 100644
--- a/sound/pci/hda/patch_hdmi.c
+++ b/sound/pci/hda/patch_hdmi.c
@@ -4551,7 +4551,9 @@ HDA_CODEC_ENTRY(0x10de002e, "Tegra186 HDMI/DP1", patch_tegra_hdmi),
 HDA_CODEC_ENTRY(0x10de002f, "Tegra194 HDMI/DP2", patch_tegra_hdmi),
 HDA_CODEC_ENTRY(0x10de0030, "Tegra194 HDMI/DP3", patch_tegra_hdmi),
 HDA_CODEC_ENTRY(0x10de0031, "Tegra234 HDMI/DP", patch_tegra234_hdmi),
+HDA_CODEC_ENTRY(0x10de0033, "SoC 33 HDMI/DP",	patch_tegra234_hdmi),
 HDA_CODEC_ENTRY(0x10de0034, "Tegra264 HDMI/DP",	patch_tegra234_hdmi),
+HDA_CODEC_ENTRY(0x10de0035, "SoC 35 HDMI/DP",	patch_tegra234_hdmi),
 HDA_CODEC_ENTRY(0x10de0040, "GPU 40 HDMI/DP",	patch_nvhdmi),
 HDA_CODEC_ENTRY(0x10de0041, "GPU 41 HDMI/DP",	patch_nvhdmi),
 HDA_CODEC_ENTRY(0x10de0042, "GPU 42 HDMI/DP",	patch_nvhdmi),
@@ -4590,15 +4592,32 @@ HDA_CODEC_ENTRY(0x10de0097, "GPU 97 HDMI/DP",	patch_nvhdmi),
 HDA_CODEC_ENTRY(0x10de0098, "GPU 98 HDMI/DP",	patch_nvhdmi),
 HDA_CODEC_ENTRY(0x10de0099, "GPU 99 HDMI/DP",	patch_nvhdmi),
 HDA_CODEC_ENTRY(0x10de009a, "GPU 9a HDMI/DP",	patch_nvhdmi),
+HDA_CODEC_ENTRY(0x10de009b, "GPU 9b HDMI/DP",	patch_nvhdmi),
+HDA_CODEC_ENTRY(0x10de009c, "GPU 9c HDMI/DP",	patch_nvhdmi),
 HDA_CODEC_ENTRY(0x10de009d, "GPU 9d HDMI/DP",	patch_nvhdmi),
 HDA_CODEC_ENTRY(0x10de009e, "GPU 9e HDMI/DP",	patch_nvhdmi),
 HDA_CODEC_ENTRY(0x10de009f, "GPU 9f HDMI/DP",	patch_nvhdmi),
 HDA_CODEC_ENTRY(0x10de00a0, "GPU a0 HDMI/DP",	patch_nvhdmi),
+HDA_CODEC_ENTRY(0x10de00a1, "GPU a1 HDMI/DP",	patch_nvhdmi),
 HDA_CODEC_ENTRY(0x10de00a3, "GPU a3 HDMI/DP",	patch_nvhdmi),
 HDA_CODEC_ENTRY(0x10de00a4, "GPU a4 HDMI/DP",	patch_nvhdmi),
 HDA_CODEC_ENTRY(0x10de00a5, "GPU a5 HDMI/DP",	patch_nvhdmi),
 HDA_CODEC_ENTRY(0x10de00a6, "GPU a6 HDMI/DP",	patch_nvhdmi),
 HDA_CODEC_ENTRY(0x10de00a7, "GPU a7 HDMI/DP",	patch_nvhdmi),
+HDA_CODEC_ENTRY(0x10de00a8, "GPU a8 HDMI/DP",	patch_nvhdmi),
+HDA_CODEC_ENTRY(0x10de00a9, "GPU a9 HDMI/DP",	patch_nvhdmi),
+HDA_CODEC_ENTRY(0x10de00aa, "GPU aa HDMI/DP",	patch_nvhdmi),
+HDA_CODEC_ENTRY(0x10de00ab, "GPU ab HDMI/DP",	patch_nvhdmi),
+HDA_CODEC_ENTRY(0x10de00ad, "GPU ad HDMI/DP",	patch_nvhdmi),
+HDA_CODEC_ENTRY(0x10de00ae, "GPU ae HDMI/DP",	patch_nvhdmi),
+HDA_CODEC_ENTRY(0x10de00af, "GPU af HDMI/DP",	patch_nvhdmi),
+HDA_CODEC_ENTRY(0x10de00b0, "GPU b0 HDMI/DP",	patch_nvhdmi),
+HDA_CODEC_ENTRY(0x10de00b1, "GPU b1 HDMI/DP",	patch_nvhdmi),
+HDA_CODEC_ENTRY(0x10de00c0, "GPU c0 HDMI/DP",	patch_nvhdmi),
+HDA_CODEC_ENTRY(0x10de00c1, "GPU c1 HDMI/DP",	patch_nvhdmi),
+HDA_CODEC_ENTRY(0x10de00c3, "GPU c3 HDMI/DP",	patch_nvhdmi),
+HDA_CODEC_ENTRY(0x10de00c4, "GPU c4 HDMI/DP",	patch_nvhdmi),
+HDA_CODEC_ENTRY(0x10de00c5, "GPU c5 HDMI/DP",	patch_nvhdmi),
 HDA_CODEC_ENTRY(0x10de8001, "MCP73 HDMI",	patch_nvhdmi_2ch),
 HDA_CODEC_ENTRY(0x10de8067, "MCP67/68 HDMI",	patch_nvhdmi_2ch),
 HDA_CODEC_ENTRY(0x67663d82, "Arise 82 HDMI/DP",	patch_gf_hdmi),

From ce174b48aebb3fa18fe48c59a3d10a89c414fdf2 Mon Sep 17 00:00:00 2001
From: Edip Hazuri <edip@medip.dev>
Date: Fri, 27 Jun 2025 23:34:16 +0300
Subject: [PATCH 0990/1334] ALSA: hda/realtek - Add mute LED support for HP
 Victus 15-fb2xxx

The mute led on this laptop is using ALC245 but requires a quirk to work
This patch enables the existing quirk for the device.

Tested on my friend's Victus 15-fb2xxx Laptop. The LED behaviour works
as intended.

Cc: <stable@vger.kernel.org>
Signed-off-by: Edip Hazuri <edip@medip.dev>
Link: https://patch.msgid.link/20250627203415.56785-2-edip@medip.dev
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/patch_realtek.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 5d6d01ecfee2..a33e8a6541d4 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -10881,6 +10881,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x103c, 0x8ce0, "HP SnowWhite", ALC287_FIXUP_CS35L41_I2C_2_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8cf5, "HP ZBook Studio 16", ALC245_FIXUP_CS35L41_SPI_4_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8d01, "HP ZBook Power 14 G12", ALC285_FIXUP_HP_GPIO_LED),
+	SND_PCI_QUIRK(0x103c, 0x8d07, "HP Victus 15-fb2xxx (MB 8D07)", ALC245_FIXUP_HP_MUTE_LED_COEFBIT),
 	SND_PCI_QUIRK(0x103c, 0x8d18, "HP EliteStudio 8 AIO", ALC274_FIXUP_HP_AIO_BIND_DACS),
 	SND_PCI_QUIRK(0x103c, 0x8d84, "HP EliteBook X G1i", ALC285_FIXUP_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x103c, 0x8d85, "HP EliteBook 14 G12", ALC285_FIXUP_HP_GPIO_LED),

From d0b3b7b22dfa1f4b515fd3a295b3fd958f9e81af Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Sun, 29 Jun 2025 13:09:04 -0700
Subject: [PATCH 0991/1334] Linux 6.16-rc4

---
 Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Makefile b/Makefile
index f884dfe10246..1c9ea229809f 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
 VERSION = 6
 PATCHLEVEL = 16
 SUBLEVEL = 0
-EXTRAVERSION = -rc3
+EXTRAVERSION = -rc4
 NAME = Baby Opossum Posse
 
 # *DOCUMENTATION*

From cbe876121633dadb2b0ce52711985328638e9aab Mon Sep 17 00:00:00 2001
From: Shengjiu Wang <shengjiu.wang@nxp.com>
Date: Wed, 25 Jun 2025 10:05:04 +0800
Subject: [PATCH 0992/1334] ASoC: fsl_asrc: use internal measured ratio for
 non-ideal ratio mode

When USRC=0, there is underrun issue for the non-ideal ratio mode;
according to the reference mannual, the internal measured ratio can be
used with USRC=1 and IDRC=0.

Fixes: d0250cf4f2ab ("ASoC: fsl_asrc: Add an option to select internal ratio mode")
Signed-off-by: Shengjiu Wang <shengjiu.wang@nxp.com>
Reviewed-by: Daniel Baluta <daniel.baluta@nxp.com>
Link: https://patch.msgid.link/20250625020504.2728161-1-shengjiu.wang@nxp.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/fsl/fsl_asrc.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/sound/soc/fsl/fsl_asrc.c b/sound/soc/fsl/fsl_asrc.c
index 677529916dc0..745532ccbdba 100644
--- a/sound/soc/fsl/fsl_asrc.c
+++ b/sound/soc/fsl/fsl_asrc.c
@@ -517,7 +517,8 @@ static int fsl_asrc_config_pair(struct fsl_asrc_pair *pair, bool use_ideal_rate)
 	regmap_update_bits(asrc->regmap, REG_ASRCTR,
 			   ASRCTR_ATSi_MASK(index), ASRCTR_ATS(index));
 	regmap_update_bits(asrc->regmap, REG_ASRCTR,
-			   ASRCTR_USRi_MASK(index), 0);
+			   ASRCTR_IDRi_MASK(index) | ASRCTR_USRi_MASK(index),
+			   ASRCTR_USR(index));
 
 	/* Set the input and output clock sources */
 	regmap_update_bits(asrc->regmap, REG_ASRCSR,

From 960aed31eedbaeb2e47b1bc485b462fd38a53311 Mon Sep 17 00:00:00 2001
From: Bard Liao <yung-chuan.liao@linux.intel.com>
Date: Thu, 26 Jun 2025 14:44:20 +0800
Subject: [PATCH 0993/1334] ASoC: Intel: SND_SOC_INTEL_SOF_BOARD_HELPERS select
 SND_SOC_ACPI_INTEL_MATCH
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The helpers that are provided by SND_SOC_ACPI_INTEL_MATCH
(soc-acpi-intel-ssp-common) are used in SND_SOC_INTEL_SOF_BOARD_HELPERS
(sof_board_helpers).
SND_SOC_ACPI_INTEL_MATCH is selected by machine drivers. When
skl_hda_dsp_generic uses the board helpers, it select
SND_SOC_INTEL_SOF_BOARD_HELPERS only but not SND_SOC_ACPI_INTEL_MATCH
which initroduce the undefined symbol errors. However, it makes more
sense that SND_SOC_INTEL_SOF_BOARD_HELPERS select
SND_SOC_ACPI_INTEL_MATCH itself.

Fixes: b28b23dea314 ("ASoC: Intel: skl_hda_dsp_generic: use common module for DAI links")
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202506141543.dN0JJyZC-lkp@intel.com/
Signed-off-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Reviewed-by: Péter Ujfalusi <peter.ujfalusi@linux.intel.com>
Reviewed-by: Liam Girdwood <liam.r.girdwood@intel.com>
Link: https://patch.msgid.link/20250626064420.450334-1-yung-chuan.liao@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/intel/boards/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/soc/intel/boards/Kconfig b/sound/soc/intel/boards/Kconfig
index 2df7afa2f469..128b6876af83 100644
--- a/sound/soc/intel/boards/Kconfig
+++ b/sound/soc/intel/boards/Kconfig
@@ -42,6 +42,7 @@ config SND_SOC_INTEL_SOF_NUVOTON_COMMON
 	tristate
 
 config SND_SOC_INTEL_SOF_BOARD_HELPERS
+	select SND_SOC_ACPI_INTEL_MATCH
 	tristate
 
 if SND_SOC_INTEL_CATPT

From dc78f7e59169d3f0e6c3c95d23dc8e55e95741e2 Mon Sep 17 00:00:00 2001
From: Arun Raghavan <arun@asymptotic.io>
Date: Thu, 26 Jun 2025 09:08:25 -0400
Subject: [PATCH 0994/1334] ASoC: fsl_sai: Force a software reset when starting
 in consumer mode

On an imx8mm platform with an external clock provider, when running the
receiver (arecord) and triggering an xrun with xrun_injection, we see a
channel swap/offset. This happens sometimes when running only the
receiver, but occurs reliably if a transmitter (aplay) is also
concurrently running.

It seems that the SAI loses track of frame sync during the trigger stop
-> trigger start cycle that occurs during an xrun. Doing just a FIFO
reset in this case does not suffice, and only a software reset seems to
get it back on track.

This looks like the same h/w bug that is already handled for the
producer case, so we now do the reset unconditionally on config disable.

Signed-off-by: Arun Raghavan <arun@asymptotic.io>
Reported-by: Pieterjan Camerlynck <p.camerlynck@televic.com>
Fixes: 3e3f8bd56955 ("ASoC: fsl_sai: fix no frame clk in master mode")
Cc: stable@vger.kernel.org
Reviewed-by: Fabio Estevam <festevam@gmail.com>
Link: https://patch.msgid.link/20250626130858.163825-1-arun@arunraghavan.net
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/fsl/fsl_sai.c | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

diff --git a/sound/soc/fsl/fsl_sai.c b/sound/soc/fsl/fsl_sai.c
index af1a168d35e3..50af6b725670 100644
--- a/sound/soc/fsl/fsl_sai.c
+++ b/sound/soc/fsl/fsl_sai.c
@@ -803,13 +803,15 @@ static void fsl_sai_config_disable(struct fsl_sai *sai, int dir)
 	 * anymore. Add software reset to fix this issue.
 	 * This is a hardware bug, and will be fix in the
 	 * next sai version.
+	 *
+	 * In consumer mode, this can happen even after a
+	 * single open/close, especially if both tx and rx
+	 * are running concurrently.
 	 */
-	if (!sai->is_consumer_mode[tx]) {
-		/* Software Reset */
-		regmap_write(sai->regmap, FSL_SAI_xCSR(tx, ofs), FSL_SAI_CSR_SR);
-		/* Clear SR bit to finish the reset */
-		regmap_write(sai->regmap, FSL_SAI_xCSR(tx, ofs), 0);
-	}
+	/* Software Reset */
+	regmap_write(sai->regmap, FSL_SAI_xCSR(tx, ofs), FSL_SAI_CSR_SR);
+	/* Clear SR bit to finish the reset */
+	regmap_write(sai->regmap, FSL_SAI_xCSR(tx, ofs), 0);
 }
 
 static int fsl_sai_trigger(struct snd_pcm_substream *substream, int cmd,

From be2e1a63448b35bd6736b5934f7720534649b51e Mon Sep 17 00:00:00 2001
From: Srinivas Kandagatla <srinivas.kandagatla@oss.qualcomm.com>
Date: Fri, 27 Jun 2025 17:03:29 +0100
Subject: [PATCH 0995/1334] MAINTAINERS: update Qualcomm audio codec drivers
 list

Some of the codec drivers like wcd939x are missing in the MAINTAINERS
which is resulting in incorrect list from get_maintainers script.
Fix this by using wildcard matching on both wcd93* and wsa88* codec and
bindings.

Signed-off-by: Srinivas Kandagatla <srinivas.kandagatla@oss.qualcomm.com>
Link: https://patch.msgid.link/20250627160329.442795-1-srinivas.kandagatla@oss.qualcomm.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 MAINTAINERS | 16 +++++-----------
 1 file changed, 5 insertions(+), 11 deletions(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 4bac4ea21b64..5bfcaf0732ed 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -20153,21 +20153,15 @@ S:	Supported
 F:	Documentation/devicetree/bindings/soc/qcom/qcom,apr*
 F:	Documentation/devicetree/bindings/sound/qcom,*
 F:	drivers/soc/qcom/apr.c
-F:	include/dt-bindings/sound/qcom,wcd9335.h
-F:	include/dt-bindings/sound/qcom,wcd934x.h
-F:	sound/soc/codecs/lpass-rx-macro.*
-F:	sound/soc/codecs/lpass-tx-macro.*
-F:	sound/soc/codecs/lpass-va-macro.c
-F:	sound/soc/codecs/lpass-wsa-macro.*
+F:	drivers/soundwire/qcom.c
+F:	include/dt-bindings/sound/qcom,wcd93*
+F:	sound/soc/codecs/lpass-*.*
 F:	sound/soc/codecs/msm8916-wcd-analog.c
 F:	sound/soc/codecs/msm8916-wcd-digital.c
 F:	sound/soc/codecs/wcd-clsh-v2.*
 F:	sound/soc/codecs/wcd-mbhc-v2.*
-F:	sound/soc/codecs/wcd9335.*
-F:	sound/soc/codecs/wcd934x.c
-F:	sound/soc/codecs/wsa881x.c
-F:	sound/soc/codecs/wsa883x.c
-F:	sound/soc/codecs/wsa884x.c
+F:	sound/soc/codecs/wcd93*.*
+F:	sound/soc/codecs/wsa88*.*
 F:	sound/soc/qcom/
 
 QCOM EMBEDDED USB DEBUGGER (EUD)

From a7528e9beadbddcec21b394ce5fa8dc4e5cdaa24 Mon Sep 17 00:00:00 2001
From: Charles Keepax <ckeepax@opensource.cirrus.com>
Date: Thu, 26 Jun 2025 15:18:41 +0100
Subject: [PATCH 0996/1334] ASoC: Intel: soc-acpi: arl: Correct order of
 cs42l43 matches

Matches should go from more specific to less specific, correct the
ordering of two cs42l43 entries.

Fixes: c0524067653d ("ASoC: Intel: soc-acpi: arl: Add match entries for new cs42l43 laptops")
Signed-off-by: Charles Keepax <ckeepax@opensource.cirrus.com>
Link: https://patch.msgid.link/20250626141841.77780-1-ckeepax@opensource.cirrus.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/intel/common/soc-acpi-intel-arl-match.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/sound/soc/intel/common/soc-acpi-intel-arl-match.c b/sound/soc/intel/common/soc-acpi-intel-arl-match.c
index 73e581e93755..1ad704ca2c5f 100644
--- a/sound/soc/intel/common/soc-acpi-intel-arl-match.c
+++ b/sound/soc/intel/common/soc-acpi-intel-arl-match.c
@@ -467,13 +467,6 @@ struct snd_soc_acpi_mach snd_soc_acpi_intel_arl_sdw_machines[] = {
 		.sof_tplg_filename = "sof-arl-cs42l43-l0.tplg",
 		.get_function_tplg_files = sof_sdw_get_tplg_files,
 	},
-	{
-		.link_mask = BIT(2),
-		.links = arl_cs42l43_l2,
-		.drv_name = "sof_sdw",
-		.sof_tplg_filename = "sof-arl-cs42l43-l2.tplg",
-		.get_function_tplg_files = sof_sdw_get_tplg_files,
-	},
 	{
 		.link_mask = BIT(2) | BIT(3),
 		.links = arl_cs42l43_l2_cs35l56_l3,
@@ -481,6 +474,13 @@ struct snd_soc_acpi_mach snd_soc_acpi_intel_arl_sdw_machines[] = {
 		.sof_tplg_filename = "sof-arl-cs42l43-l2-cs35l56-l3.tplg",
 		.get_function_tplg_files = sof_sdw_get_tplg_files,
 	},
+	{
+		.link_mask = BIT(2),
+		.links = arl_cs42l43_l2,
+		.drv_name = "sof_sdw",
+		.sof_tplg_filename = "sof-arl-cs42l43-l2.tplg",
+		.get_function_tplg_files = sof_sdw_get_tplg_files,
+	},
 	{
 		.link_mask = 0x1, /* link0 required */
 		.links = arl_rvp,

From ca46946a482238b0cdea459fb82fc837fb36260e Mon Sep 17 00:00:00 2001
From: Alessandro Carminati <acarmina@redhat.com>
Date: Thu, 26 Jun 2025 08:38:09 +0000
Subject: [PATCH 0997/1334] regulator: core: fix NULL dereference on unbind due
 to stale coupling data

Failing to reset coupling_desc.n_coupled after freeing coupled_rdevs can
lead to NULL pointer dereference when regulators are accessed post-unbind.

This can happen during runtime PM or other regulator operations that rely
on coupling metadata.

For example, on ridesx4, unbinding the 'reg-dummy' platform device triggers
a panic in regulator_lock_recursive() due to stale coupling state.

Ensure n_coupled is set to 0 to prevent access to invalid pointers.

Signed-off-by: Alessandro Carminati <acarmina@redhat.com>
Link: https://patch.msgid.link/20250626083809.314842-1-acarmina@redhat.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/regulator/core.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c
index 7a248dc8d2e2..cbd6d53ebfb5 100644
--- a/drivers/regulator/core.c
+++ b/drivers/regulator/core.c
@@ -5639,6 +5639,7 @@ static void regulator_remove_coupling(struct regulator_dev *rdev)
 				 ERR_PTR(err));
 	}
 
+	rdev->coupling_desc.n_coupled = 0;
 	kfree(rdev->coupling_desc.coupled_rdevs);
 	rdev->coupling_desc.coupled_rdevs = NULL;
 }

From eeca209124bb694650026216d3e59cae02d91686 Mon Sep 17 00:00:00 2001
From: Shree Ramamoorthy <s-ramamoorthy@ti.com>
Date: Fri, 20 Jun 2025 10:45:41 -0500
Subject: [PATCH 0998/1334] regulator: tps65219: Fix devm_kmalloc size
 allocation

In probe(), two arrays of structs are allocated with the devm_kmalloc()
function, but the memory size of the allocations were given as the arrays'
length (pmic->common_irq_size for the first call and pmic->dev_irq_size for
the second devm_kmalloc call). The memory size should have been the total
memory needed.

This led to a heap overflow when the struct array was used. The issue was
first discovered with the PocketBeagle2 and BeaglePlay. The common and
device-specific structs are now allocated one at a time within the loop.

Fixes: 38c9f98db20a ("regulator: tps65219: Add support for TPS65215 Regulator IRQs")
Reported-by: Dhruva Gole <d-gole@ti.com>
Closes: https://lore.kernel.org/all/20250619153526.297398-1-d-gole@ti.com/
Tested-by: Robert Nelson <robertcnelson@gmail.com>
Acked-by: Andrew Davis <afd@ti.com>
Signed-off-by: Shree Ramamoorthy <s-ramamoorthy@ti.com>
Reviewed-by: Nishanth Menon <nm@ti.com>
Link: https://patch.msgid.link/20250620154541.2713036-1-s-ramamoorthy@ti.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/regulator/tps65219-regulator.c | 28 +++++++++++++-------------
 1 file changed, 14 insertions(+), 14 deletions(-)

diff --git a/drivers/regulator/tps65219-regulator.c b/drivers/regulator/tps65219-regulator.c
index b16b300d7f45..5e67fdc88f49 100644
--- a/drivers/regulator/tps65219-regulator.c
+++ b/drivers/regulator/tps65219-regulator.c
@@ -436,46 +436,46 @@ static int tps65219_regulator_probe(struct platform_device *pdev)
 					     pmic->rdesc[i].name);
 	}
 
-	irq_data = devm_kmalloc(tps->dev, pmic->common_irq_size, GFP_KERNEL);
-	if (!irq_data)
-		return -ENOMEM;
-
 	for (i = 0; i < pmic->common_irq_size; ++i) {
 		irq_type = &pmic->common_irq_types[i];
 		irq = platform_get_irq_byname(pdev, irq_type->irq_name);
 		if (irq < 0)
 			return -EINVAL;
 
-		irq_data[i].dev = tps->dev;
-		irq_data[i].type = irq_type;
+		irq_data = devm_kmalloc(tps->dev, sizeof(*irq_data), GFP_KERNEL);
+		if (!irq_data)
+			return -ENOMEM;
+
+		irq_data->dev = tps->dev;
+		irq_data->type = irq_type;
 		error = devm_request_threaded_irq(tps->dev, irq, NULL,
 						  tps65219_regulator_irq_handler,
 						  IRQF_ONESHOT,
 						  irq_type->irq_name,
-						  &irq_data[i]);
+						  irq_data);
 		if (error)
 			return dev_err_probe(tps->dev, PTR_ERR(rdev),
 					     "Failed to request %s IRQ %d: %d\n",
 					     irq_type->irq_name, irq, error);
 	}
 
-	irq_data = devm_kmalloc(tps->dev, pmic->dev_irq_size, GFP_KERNEL);
-	if (!irq_data)
-		return -ENOMEM;
-
 	for (i = 0; i < pmic->dev_irq_size; ++i) {
 		irq_type = &pmic->irq_types[i];
 		irq = platform_get_irq_byname(pdev, irq_type->irq_name);
 		if (irq < 0)
 			return -EINVAL;
 
-		irq_data[i].dev = tps->dev;
-		irq_data[i].type = irq_type;
+		irq_data = devm_kmalloc(tps->dev, sizeof(*irq_data), GFP_KERNEL);
+		if (!irq_data)
+			return -ENOMEM;
+
+		irq_data->dev = tps->dev;
+		irq_data->type = irq_type;
 		error = devm_request_threaded_irq(tps->dev, irq, NULL,
 						  tps65219_regulator_irq_handler,
 						  IRQF_ONESHOT,
 						  irq_type->irq_name,
-						  &irq_data[i]);
+						  irq_data);
 		if (error)
 			return dev_err_probe(tps->dev, PTR_ERR(rdev),
 					     "Failed to request %s IRQ %d: %d\n",

From d85d0380292a7e618915069c3579ae23c7c80339 Mon Sep 17 00:00:00 2001
From: Gabor Juhos <j4g8y7@gmail.com>
Date: Wed, 18 Jun 2025 22:22:49 +0200
Subject: [PATCH 0999/1334] spi: spi-qpic-snand: reallocate BAM transactions

Using the mtd_nandbiterrs module for testing the driver occasionally
results in weird things like below.

1. swiotlb mapping fails with the following message:

  [   85.926216] qcom_snand 79b0000.spi: swiotlb buffer is full (sz: 4294967294 bytes), total 512 (slots), used 0 (slots)
  [   85.932937] qcom_snand 79b0000.spi: failure in mapping desc
  [   87.999314] qcom_snand 79b0000.spi: failure to write raw page
  [   87.999352] mtd_nandbiterrs: error: write_oob failed (-110)

  Rebooting the board after this causes a panic due to a NULL pointer
  dereference.

2. If the swiotlb mapping does not fail, rebooting the board may result
   in a different panic due to a bad spinlock magic:

  [  256.104459] BUG: spinlock bad magic on CPU#3, procd/2241
  [  256.104488] Unable to handle kernel paging request at virtual address ffffffff0000049b
  ...

Investigating the issue revealed that these symptoms are results of
memory corruption which is caused by out of bounds access within the
driver.

The driver uses a dynamically allocated structure for BAM transactions,
which structure must have enough space for all possible variations of
different flash operations initiated by the driver. The required space
heavily depends on the actual number of 'codewords' which is calculated
from the pagesize of the actual NAND chip.

Although the qcom_nandc_alloc() function allocates memory for the BAM
transactions during probe, but since the actual number of 'codewords'
is not yet know the allocation is done for one 'codeword' only.

Because of this, whenever the driver does a flash operation, and the
number of the required transactions exceeds the size of the allocated
arrays the driver accesses memory out of the allocated range.

To avoid this, change the code to free the initially allocated BAM
transactions memory, and allocate a new one once the actual number of
'codewords' required for a given NAND chip is known.

Fixes: 7304d1909080 ("spi: spi-qpic: add driver for QCOM SPI NAND flash Interface")
Reviewed-by: Md Sadre Alam <quic_mdalam@quicinc.com>
Signed-off-by: Gabor Juhos <j4g8y7@gmail.com>
Link: https://patch.msgid.link/20250618-qpic-snand-avoid-mem-corruption-v3-1-319c71296cda@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-qpic-snand.c | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/drivers/spi/spi-qpic-snand.c b/drivers/spi/spi-qpic-snand.c
index 77d9cc65477a..f2e1a27b410d 100644
--- a/drivers/spi/spi-qpic-snand.c
+++ b/drivers/spi/spi-qpic-snand.c
@@ -315,6 +315,22 @@ static int qcom_spi_ecc_init_ctx_pipelined(struct nand_device *nand)
 
 	mtd_set_ooblayout(mtd, &qcom_spi_ooblayout);
 
+	/*
+	 * Free the temporary BAM transaction allocated initially by
+	 * qcom_nandc_alloc(), and allocate a new one based on the
+	 * updated max_cwperpage value.
+	 */
+	qcom_free_bam_transaction(snandc);
+
+	snandc->max_cwperpage = cwperpage;
+
+	snandc->bam_txn = qcom_alloc_bam_transaction(snandc);
+	if (!snandc->bam_txn) {
+		dev_err(snandc->dev, "failed to allocate BAM transaction\n");
+		ret = -ENOMEM;
+		goto err_free_ecc_cfg;
+	}
+
 	ecc_cfg->cfg0 = FIELD_PREP(CW_PER_PAGE_MASK, (cwperpage - 1)) |
 			FIELD_PREP(UD_SIZE_BYTES_MASK, ecc_cfg->cw_data) |
 			FIELD_PREP(DISABLE_STATUS_AFTER_WRITE, 1) |

From ddaad4ad774d4ae02047ef873a8e38f62a4b7b01 Mon Sep 17 00:00:00 2001
From: Gabor Juhos <j4g8y7@gmail.com>
Date: Wed, 18 Jun 2025 22:22:50 +0200
Subject: [PATCH 1000/1334] mtd: nand: qpic_common: prevent out of bounds
 access of BAM arrays

The common QPIC code does not do any boundary checking when it handles
the command elements and scatter gater list arrays of a BAM transaction,
thus it allows to access out of bounds elements in those.

Although it is the responsibility of the given driver to allocate enough
space for all possible BAM transaction variations, however there can be
mistakes in the driver code which can lead to hidden memory corruption
issues which are hard to debug.

This kind of problem has been observed during testing the 'spi-qpic-snand'
driver. Although the driver has been fixed with a preceding patch, but it
still makes sense to reduce the chance of having such errors again later.

In order to prevent such errors, change the qcom_alloc_bam_transaction()
function to store the number of elements of the arrays in the
'bam_transaction' strucutre during allocation. Also, add sanity checks to
the qcom_prep_bam_dma_desc_{cmd,data}() functions to avoid using out of
bounds indices for the arrays.

Tested-by: Lakshmi Sowjanya D <quic_laksd@quicinc.com>     # on SDX75
Acked-by: Miquel Raynal <miquel.raynal@bootlin.com>
Signed-off-by: Gabor Juhos <j4g8y7@gmail.com>
Link: https://patch.msgid.link/20250618-qpic-snand-avoid-mem-corruption-v3-2-319c71296cda@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/mtd/nand/qpic_common.c       | 30 ++++++++++++++++++++++++----
 include/linux/mtd/nand-qpic-common.h |  8 ++++++++
 2 files changed, 34 insertions(+), 4 deletions(-)

diff --git a/drivers/mtd/nand/qpic_common.c b/drivers/mtd/nand/qpic_common.c
index 4dc4d65e7d32..8e604cc22ca3 100644
--- a/drivers/mtd/nand/qpic_common.c
+++ b/drivers/mtd/nand/qpic_common.c
@@ -57,14 +57,15 @@ qcom_alloc_bam_transaction(struct qcom_nand_controller *nandc)
 	bam_txn_buf += sizeof(*bam_txn);
 
 	bam_txn->bam_ce = bam_txn_buf;
-	bam_txn_buf +=
-		sizeof(*bam_txn->bam_ce) * QPIC_PER_CW_CMD_ELEMENTS * num_cw;
+	bam_txn->bam_ce_nitems = QPIC_PER_CW_CMD_ELEMENTS * num_cw;
+	bam_txn_buf += sizeof(*bam_txn->bam_ce) * bam_txn->bam_ce_nitems;
 
 	bam_txn->cmd_sgl = bam_txn_buf;
-	bam_txn_buf +=
-		sizeof(*bam_txn->cmd_sgl) * QPIC_PER_CW_CMD_SGL * num_cw;
+	bam_txn->cmd_sgl_nitems = QPIC_PER_CW_CMD_SGL * num_cw;
+	bam_txn_buf += sizeof(*bam_txn->cmd_sgl) * bam_txn->cmd_sgl_nitems;
 
 	bam_txn->data_sgl = bam_txn_buf;
+	bam_txn->data_sgl_nitems = QPIC_PER_CW_DATA_SGL * num_cw;
 
 	init_completion(&bam_txn->txn_done);
 
@@ -238,6 +239,11 @@ int qcom_prep_bam_dma_desc_cmd(struct qcom_nand_controller *nandc, bool read,
 	struct bam_transaction *bam_txn = nandc->bam_txn;
 	u32 offset;
 
+	if (bam_txn->bam_ce_pos + size > bam_txn->bam_ce_nitems) {
+		dev_err(nandc->dev, "BAM %s array is full\n", "CE");
+		return -EINVAL;
+	}
+
 	bam_ce_buffer = &bam_txn->bam_ce[bam_txn->bam_ce_pos];
 
 	/* fill the command desc */
@@ -258,6 +264,12 @@ int qcom_prep_bam_dma_desc_cmd(struct qcom_nand_controller *nandc, bool read,
 
 	/* use the separate sgl after this command */
 	if (flags & NAND_BAM_NEXT_SGL) {
+		if (bam_txn->cmd_sgl_pos >= bam_txn->cmd_sgl_nitems) {
+			dev_err(nandc->dev, "BAM %s array is full\n",
+				"CMD sgl");
+			return -EINVAL;
+		}
+
 		bam_ce_buffer = &bam_txn->bam_ce[bam_txn->bam_ce_start];
 		bam_ce_size = (bam_txn->bam_ce_pos -
 				bam_txn->bam_ce_start) *
@@ -297,10 +309,20 @@ int qcom_prep_bam_dma_desc_data(struct qcom_nand_controller *nandc, bool read,
 	struct bam_transaction *bam_txn = nandc->bam_txn;
 
 	if (read) {
+		if (bam_txn->rx_sgl_pos >= bam_txn->data_sgl_nitems) {
+			dev_err(nandc->dev, "BAM %s array is full\n", "RX sgl");
+			return -EINVAL;
+		}
+
 		sg_set_buf(&bam_txn->data_sgl[bam_txn->rx_sgl_pos],
 			   vaddr, size);
 		bam_txn->rx_sgl_pos++;
 	} else {
+		if (bam_txn->tx_sgl_pos >= bam_txn->data_sgl_nitems) {
+			dev_err(nandc->dev, "BAM %s array is full\n", "TX sgl");
+			return -EINVAL;
+		}
+
 		sg_set_buf(&bam_txn->data_sgl[bam_txn->tx_sgl_pos],
 			   vaddr, size);
 		bam_txn->tx_sgl_pos++;
diff --git a/include/linux/mtd/nand-qpic-common.h b/include/linux/mtd/nand-qpic-common.h
index e8462deda6db..f0aa098a395f 100644
--- a/include/linux/mtd/nand-qpic-common.h
+++ b/include/linux/mtd/nand-qpic-common.h
@@ -237,6 +237,9 @@
  * @last_data_desc - last DMA desc in data channel (tx/rx).
  * @last_cmd_desc - last DMA desc in command channel.
  * @txn_done - completion for NAND transfer.
+ * @bam_ce_nitems - the number of elements in the @bam_ce array
+ * @cmd_sgl_nitems - the number of elements in the @cmd_sgl array
+ * @data_sgl_nitems - the number of elements in the @data_sgl array
  * @bam_ce_pos - the index in bam_ce which is available for next sgl
  * @bam_ce_start - the index in bam_ce which marks the start position ce
  *		   for current sgl. It will be used for size calculation
@@ -255,6 +258,11 @@ struct bam_transaction {
 	struct dma_async_tx_descriptor *last_data_desc;
 	struct dma_async_tx_descriptor *last_cmd_desc;
 	struct completion txn_done;
+
+	unsigned int bam_ce_nitems;
+	unsigned int cmd_sgl_nitems;
+	unsigned int data_sgl_nitems;
+
 	struct_group(bam_positions,
 		u32 bam_ce_pos;
 		u32 bam_ce_start;

From 96893cdd4760ad94a438c1523cc5ca2470e04670 Mon Sep 17 00:00:00 2001
From: Marc Kleine-Budde <mkl@pengutronix.de>
Date: Sun, 29 Jun 2025 18:15:32 +0200
Subject: [PATCH 1001/1334] spi: Raise limit on number of chip selects to 24

We have a system which uses 24 SPI chip selects, raise the hard coded
limit accordingly.

Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
Link: https://patch.msgid.link/20250629-spi-increase-number-of-cs-v2-1-85a0a09bab32@pengutronix.de
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/linux/spi/spi.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h
index 4789f91dae94..e9ea43234d9a 100644
--- a/include/linux/spi/spi.h
+++ b/include/linux/spi/spi.h
@@ -21,7 +21,7 @@
 #include <uapi/linux/spi/spi.h>
 
 /* Max no. of CS supported per spi device */
-#define SPI_CS_CNT_MAX 16
+#define SPI_CS_CNT_MAX 24
 
 struct dma_chan;
 struct software_node;

From fa60c094c19b97e103d653f528f8d9c178b6a5f5 Mon Sep 17 00:00:00 2001
From: James Clark <james.clark@linaro.org>
Date: Fri, 27 Jun 2025 11:21:37 +0100
Subject: [PATCH 1002/1334] spi: spi-fsl-dspi: Clear completion counter before
 initiating transfer

In target mode, extra interrupts can be received between the end of a
transfer and halting the module if the host continues sending more data.
If the interrupt from this occurs after the reinit_completion() then the
completion counter is left at a non-zero value. The next unrelated
transfer initiated by userspace will then complete immediately without
waiting for the interrupt or writing to the RX buffer.

Fix it by resetting the counter before the transfer so that lingering
values are cleared. This is done after clearing the FIFOs and the
status register but before the transfer is initiated, so no interrupts
should be received at this point resulting in other race conditions.

Fixes: 4f5ee75ea171 ("spi: spi-fsl-dspi: Replace interruptible wait queue with a simple completion")
Signed-off-by: James Clark <james.clark@linaro.org>
Reviewed-by: Frank Li <Frank.Li@nxp.com>
Link: https://patch.msgid.link/20250627-james-nxp-spi-dma-v4-1-178dba20c120@linaro.org
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-fsl-dspi.c | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/drivers/spi/spi-fsl-dspi.c b/drivers/spi/spi-fsl-dspi.c
index 863781ba6c16..0dcd49114095 100644
--- a/drivers/spi/spi-fsl-dspi.c
+++ b/drivers/spi/spi-fsl-dspi.c
@@ -983,11 +983,20 @@ static int dspi_transfer_one_message(struct spi_controller *ctlr,
 		if (dspi->devtype_data->trans_mode == DSPI_DMA_MODE) {
 			status = dspi_dma_xfer(dspi);
 		} else {
+			/*
+			 * Reinitialize the completion before transferring data
+			 * to avoid the case where it might remain in the done
+			 * state due to a spurious interrupt from a previous
+			 * transfer. This could falsely signal that the current
+			 * transfer has completed.
+			 */
+			if (dspi->irq)
+				reinit_completion(&dspi->xfer_done);
+
 			dspi_fifo_write(dspi);
 
 			if (dspi->irq) {
 				wait_for_completion(&dspi->xfer_done);
-				reinit_completion(&dspi->xfer_done);
 			} else {
 				do {
 					status = dspi_poll(dspi);

From b8f89cb723b9e66f5dbd7199e4036fee34fb0de0 Mon Sep 17 00:00:00 2001
From: Philipp Kerling <pkerling@casix.org>
Date: Sun, 29 Jun 2025 19:05:05 +0200
Subject: [PATCH 1003/1334] smb: client: fix readdir returning wrong type with
 POSIX extensions

When SMB 3.1.1 POSIX Extensions are negotiated, userspace applications
using readdir() or getdents() calls without stat() on each individual file
(such as a simple "ls" or "find") would misidentify file types and exhibit
strange behavior such as not descending into directories. The reason for
this behavior is an oversight in the cifs_posix_to_fattr conversion
function. Instead of extracting the entry type for cf_dtype from the
properly converted cf_mode field, it tries to extract the type from the
PDU. While the wire representation of the entry mode is similar in
structure to POSIX stat(), the assignments of the entry types are
different. Applying the S_DT macro to cf_mode instead yields the correct
result. This is also what the equivalent function
smb311_posix_info_to_fattr in inode.c already does for stat() etc.; which
is why "ls -l" would give the correct file type but "ls" would not (as
identified by the colors).

Cc: stable@vger.kernel.org
Signed-off-by: Philipp Kerling <pkerling@casix.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/readdir.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/smb/client/readdir.c b/fs/smb/client/readdir.c
index ba0193cf9033..4e5460206397 100644
--- a/fs/smb/client/readdir.c
+++ b/fs/smb/client/readdir.c
@@ -264,7 +264,7 @@ cifs_posix_to_fattr(struct cifs_fattr *fattr, struct smb2_posix_info *info,
 	/* The Mode field in the response can now include the file type as well */
 	fattr->cf_mode = wire_mode_to_posix(le32_to_cpu(info->Mode),
 					    fattr->cf_cifsattrs & ATTR_DIRECTORY);
-	fattr->cf_dtype = S_DT(le32_to_cpu(info->Mode));
+	fattr->cf_dtype = S_DT(fattr->cf_mode);
 
 	switch (fattr->cf_mode & S_IFMT) {
 	case S_IFLNK:

From 6f11adcc6f36ffd8f33dbdf5f5ce073368975bc3 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Sun, 29 Jun 2025 16:48:28 -0600
Subject: [PATCH 1004/1334] io_uring: gate REQ_F_ISREG on !S_ANON_INODE as well

io_uring marks a request as dealing with a regular file on S_ISREG. This
drives things like retries on short reads or writes, which is generally
not expected on a regular file (or bdev). Applications tend to not
expect that, so io_uring tries hard to ensure it doesn't deliver short
IO on regular files.

However, a recent commit added S_IFREG to anonymous inodes. When
io_uring is used to read from various things that are backed by anon
inodes, like eventfd, timerfd, etc, then it'll now all of a sudden wait
for more data when rather than deliver what was read or written in a
single operation. This breaks applications that issue reads on anon
inodes, if they ask for more data than a single read delivers.

Add a check for !S_ANON_INODE as well before setting REQ_F_ISREG to
prevent that.

Cc: Christian Brauner <brauner@kernel.org>
Cc: stable@vger.kernel.org
Link: https://github.com/ghostty-org/ghostty/discussions/7720
Fixes: cfd86ef7e8e7 ("anon_inode: use a proper mode internally")
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/io_uring.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index 5111ec040c53..73648d26a622 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -1666,11 +1666,12 @@ static void io_iopoll_req_issued(struct io_kiocb *req, unsigned int issue_flags)
 
 io_req_flags_t io_file_get_flags(struct file *file)
 {
+	struct inode *inode = file_inode(file);
 	io_req_flags_t res = 0;
 
 	BUILD_BUG_ON(REQ_F_ISREG_BIT != REQ_F_SUPPORT_NOWAIT_BIT + 1);
 
-	if (S_ISREG(file_inode(file)->i_mode))
+	if (S_ISREG(inode->i_mode) && !(inode->i_flags & S_ANON_INODE))
 		res |= REQ_F_ISREG;
 	if ((file->f_flags & O_NONBLOCK) || (file->f_mode & FMODE_NOWAIT))
 		res |= REQ_F_SUPPORT_NOWAIT;

From 63f4970a1219b5256e8ea952096c86dab666d312 Mon Sep 17 00:00:00 2001
From: Jeff LaBundy <jeff@labundy.com>
Date: Sun, 29 Jun 2025 18:33:30 -0700
Subject: [PATCH 1005/1334] Input: iqs7222 - explicitly define number of
 external channels

The number of external channels is assumed to be a multiple of 10,
but this is not the case for IQS7222D. As a result, some CRx pins
are wrongly prevented from being assigned to some channels.

Address this problem by explicitly defining the number of external
channels for cases in which the number of external channels is not
equal to the total number of available channels.

Fixes: dd24e202ac72 ("Input: iqs7222 - add support for Azoteq IQS7222D")
Signed-off-by: Jeff LaBundy <jeff@labundy.com>
Link: https://lore.kernel.org/r/aGHVf6HkyFZrzTPy@nixie71
Cc: stable@vger.kernel.org
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/misc/iqs7222.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/input/misc/iqs7222.c b/drivers/input/misc/iqs7222.c
index 80b917944b51..6fac31c0d99f 100644
--- a/drivers/input/misc/iqs7222.c
+++ b/drivers/input/misc/iqs7222.c
@@ -301,6 +301,7 @@ struct iqs7222_dev_desc {
 	int allow_offset;
 	int event_offset;
 	int comms_offset;
+	int ext_chan;
 	bool legacy_gesture;
 	struct iqs7222_reg_grp_desc reg_grps[IQS7222_NUM_REG_GRPS];
 };
@@ -315,6 +316,7 @@ static const struct iqs7222_dev_desc iqs7222_devs[] = {
 		.allow_offset = 9,
 		.event_offset = 10,
 		.comms_offset = 12,
+		.ext_chan = 10,
 		.reg_grps = {
 			[IQS7222_REG_GRP_STAT] = {
 				.base = IQS7222_SYS_STATUS,
@@ -373,6 +375,7 @@ static const struct iqs7222_dev_desc iqs7222_devs[] = {
 		.allow_offset = 9,
 		.event_offset = 10,
 		.comms_offset = 12,
+		.ext_chan = 10,
 		.legacy_gesture = true,
 		.reg_grps = {
 			[IQS7222_REG_GRP_STAT] = {
@@ -2244,7 +2247,7 @@ static int iqs7222_parse_chan(struct iqs7222_private *iqs7222,
 	const struct iqs7222_dev_desc *dev_desc = iqs7222->dev_desc;
 	struct i2c_client *client = iqs7222->client;
 	int num_chan = dev_desc->reg_grps[IQS7222_REG_GRP_CHAN].num_row;
-	int ext_chan = rounddown(num_chan, 10);
+	int ext_chan = dev_desc->ext_chan ? : num_chan;
 	int error, i;
 	u16 *chan_setup = iqs7222->chan_setup[chan_index];
 	u16 *sys_setup = iqs7222->sys_setup;
@@ -2445,7 +2448,7 @@ static int iqs7222_parse_sldr(struct iqs7222_private *iqs7222,
 	const struct iqs7222_dev_desc *dev_desc = iqs7222->dev_desc;
 	struct i2c_client *client = iqs7222->client;
 	int num_chan = dev_desc->reg_grps[IQS7222_REG_GRP_CHAN].num_row;
-	int ext_chan = rounddown(num_chan, 10);
+	int ext_chan = dev_desc->ext_chan ? : num_chan;
 	int count, error, reg_offset, i;
 	u16 *event_mask = &iqs7222->sys_setup[dev_desc->event_offset];
 	u16 *sldr_setup = iqs7222->sldr_setup[sldr_index];

From caa7c7a76b78ce41d347003f84975125383e6b59 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Wed, 25 Jun 2025 10:21:58 -0500
Subject: [PATCH 1006/1334] drm/i915/selftests: Change mock_request() to return
 error pointers

There was an error pointer vs NULL bug in __igt_breadcrumbs_smoketest().
The __mock_request_alloc() function implements the
smoketest->request_alloc() function pointer.  It was supposed to return
error pointers, but it propogates the NULL return from mock_request()
so in the event of a failure, it would lead to a NULL pointer
dereference.

To fix this, change the mock_request() function to return error pointers
and update all the callers to expect that.

Fixes: 52c0fdb25c7c ("drm/i915: Replace global breadcrumbs with per-context interrupt tracking")
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://lore.kernel.org/r/685c1417.050a0220.696f5.5c05@mx.google.com
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
(cherry picked from commit 778fa8ad5f0f23397d045c7ebca048ce8def1c43)
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
---
 drivers/gpu/drm/i915/selftests/i915_request.c | 20 +++++++++----------
 drivers/gpu/drm/i915/selftests/mock_request.c |  2 +-
 2 files changed, 11 insertions(+), 11 deletions(-)

diff --git a/drivers/gpu/drm/i915/selftests/i915_request.c b/drivers/gpu/drm/i915/selftests/i915_request.c
index 88870844b5bd..2fb7a9e7efec 100644
--- a/drivers/gpu/drm/i915/selftests/i915_request.c
+++ b/drivers/gpu/drm/i915/selftests/i915_request.c
@@ -73,8 +73,8 @@ static int igt_add_request(void *arg)
 	/* Basic preliminary test to create a request and let it loose! */
 
 	request = mock_request(rcs0(i915)->kernel_context, HZ / 10);
-	if (!request)
-		return -ENOMEM;
+	if (IS_ERR(request))
+		return PTR_ERR(request);
 
 	i915_request_add(request);
 
@@ -91,8 +91,8 @@ static int igt_wait_request(void *arg)
 	/* Submit a request, then wait upon it */
 
 	request = mock_request(rcs0(i915)->kernel_context, T);
-	if (!request)
-		return -ENOMEM;
+	if (IS_ERR(request))
+		return PTR_ERR(request);
 
 	i915_request_get(request);
 
@@ -160,8 +160,8 @@ static int igt_fence_wait(void *arg)
 	/* Submit a request, treat it as a fence and wait upon it */
 
 	request = mock_request(rcs0(i915)->kernel_context, T);
-	if (!request)
-		return -ENOMEM;
+	if (IS_ERR(request))
+		return PTR_ERR(request);
 
 	if (dma_fence_wait_timeout(&request->fence, false, T) != -ETIME) {
 		pr_err("fence wait success before submit (expected timeout)!\n");
@@ -219,8 +219,8 @@ static int igt_request_rewind(void *arg)
 	GEM_BUG_ON(IS_ERR(ce));
 	request = mock_request(ce, 2 * HZ);
 	intel_context_put(ce);
-	if (!request) {
-		err = -ENOMEM;
+	if (IS_ERR(request)) {
+		err = PTR_ERR(request);
 		goto err_context_0;
 	}
 
@@ -237,8 +237,8 @@ static int igt_request_rewind(void *arg)
 	GEM_BUG_ON(IS_ERR(ce));
 	vip = mock_request(ce, 0);
 	intel_context_put(ce);
-	if (!vip) {
-		err = -ENOMEM;
+	if (IS_ERR(vip)) {
+		err = PTR_ERR(vip);
 		goto err_context_1;
 	}
 
diff --git a/drivers/gpu/drm/i915/selftests/mock_request.c b/drivers/gpu/drm/i915/selftests/mock_request.c
index 09f747228dff..1b0cf073e964 100644
--- a/drivers/gpu/drm/i915/selftests/mock_request.c
+++ b/drivers/gpu/drm/i915/selftests/mock_request.c
@@ -35,7 +35,7 @@ mock_request(struct intel_context *ce, unsigned long delay)
 	/* NB the i915->requests slab cache is enlarged to fit mock_request */
 	request = intel_context_create_request(ce);
 	if (IS_ERR(request))
-		return NULL;
+		return request;
 
 	request->mock.delay = delay;
 	return request;

From 7da6c155a67d42a0c1e4e22bd3f492fabcb14f2c Mon Sep 17 00:00:00 2001
From: Hans de Goede <hansg@kernel.org>
Date: Thu, 26 Jun 2025 16:33:17 +0200
Subject: [PATCH 1007/1334] drm/i915/dsi: Fix NULL pointer deref in
 vlv_dphy_param_init()

Commit 77ba0b856225 ("drm/i915/dsi: convert vlv_dsi.[ch] to struct
intel_display") added a to_intel_display(connector) call to
vlv_dphy_param_init() but when vlv_dphy_param_init() gets called
the connector object has not been initialized yet, so this leads
to a NULL pointer deref:

 BUG: kernel NULL pointer dereference, address: 000000000000000c
 ...
 Hardware name: ASUSTeK COMPUTER INC. T100TA/T100TA, BIOS T100TA.314 08/13/2015
 RIP: 0010:vlv_dsi_init+0x4e6/0x1600 [i915]
 ...
 Call Trace:
  <TASK>
  ? intel_step_name+0x4be8/0x5c30 [i915]
  intel_setup_outputs+0x2d6/0xbd0 [i915]
  intel_display_driver_probe_nogem+0x13f/0x220 [i915]
  i915_driver_probe+0x3d9/0xaf0 [i915]

Use to_intel_display(&intel_dsi->base) instead to fix this.

Fixes: 77ba0b856225 ("drm/i915/dsi: convert vlv_dsi.[ch] to struct intel_display")
Signed-off-by: Hans de Goede <hansg@kernel.org>
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Link: https://lore.kernel.org/r/20250626143317.101706-1-hansg@kernel.org
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
(cherry picked from commit 0dc6bfb50a5d0759e726cd36a3d3b7529fd2a627)
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
---
 drivers/gpu/drm/i915/display/vlv_dsi.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/display/vlv_dsi.c b/drivers/gpu/drm/i915/display/vlv_dsi.c
index 21c1e10caf68..2007bb9d974d 100644
--- a/drivers/gpu/drm/i915/display/vlv_dsi.c
+++ b/drivers/gpu/drm/i915/display/vlv_dsi.c
@@ -1589,8 +1589,8 @@ static void vlv_dsi_add_properties(struct intel_connector *connector)
 
 static void vlv_dphy_param_init(struct intel_dsi *intel_dsi)
 {
+	struct intel_display *display = to_intel_display(&intel_dsi->base);
 	struct intel_connector *connector = intel_dsi->attached_connector;
-	struct intel_display *display = to_intel_display(connector);
 	struct mipi_config *mipi_config = connector->panel.vbt.dsi.config;
 	u32 tlpx_ns, extra_byte_count, tlpx_ui;
 	u32 ui_num, ui_den;

From 2e96d2d8c2a7a6c2cef45593c028d9c5ef180316 Mon Sep 17 00:00:00 2001
From: Alok Tiwari <alok.a.tiwari@oracle.com>
Date: Sat, 28 Jun 2025 11:12:32 -0700
Subject: [PATCH 1008/1334] nvme: Fix incorrect cdw15 value in passthru error
 logging

Fix an error in nvme_log_err_passthru() where cdw14 was incorrectly
printed twice instead of cdw15. This fix ensures accurate logging of
the full passthrough command payload.

Fixes: 9f079dda1433 ("nvme: allow passthru cmd error logging")
Signed-off-by: Alok Tiwari <alok.a.tiwari@oracle.com>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/nvme/host/core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index e533d791955d..2ae36bce615e 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -386,7 +386,7 @@ static void nvme_log_err_passthru(struct request *req)
 		nr->cmd->common.cdw12,
 		nr->cmd->common.cdw13,
 		nr->cmd->common.cdw14,
-		nr->cmd->common.cdw14);
+		nr->cmd->common.cdw15);
 }
 
 enum nvme_disposition {

From ba806c900379899e5cdd6ca165b900e2081e1c99 Mon Sep 17 00:00:00 2001
From: Nilay Shroff <nilay@linux.ibm.com>
Date: Thu, 26 Jun 2025 10:49:19 +0530
Subject: [PATCH 1009/1334] nvme: correctly account for namespace head
 reference counter
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The blktests nvme/058 manifests an issue where the NVMe subsystem
kobject entry remains stale in sysfs, causing a failure during
subsequent NVMe module reloads[1]. Specifically, when attempting to
register a new NVMe subsystem, the driver encounters a kobejct name
collision because a stale kobject still exists. Though, please note
that nvme/058 doesn't report any failure and test case passes and
it's only during subsequent NVMe module reloads, the stale nvme sub-
system kobject entry in sysfs causes the observed symptom[1].

This issue stems from an imbalance in the get/put usage of the namespace
head (nshead) reference counter. The nshead holds a reference to the
associated NVMe subsystem. If the nshead reference is not properly
released, it prevents the cleanup of the subsystem's kobject, leaving
nvme subsystem stale entry behind in sysfs.

During the failure case, the last namespace path referencing a nshead
is removed, but the nshead reference was not released. This occurs
because the release logic currently only puts the nshead reference
when its state is LIVE. However, in configurations where ANA (Asymmetric
Namespace Access) is enabled, a namespace may be associated with an ANA
state that is neither optimized nor non-optimized. In this case, the
nshead may never transition to LIVE, and the corresponding nshead
reference is then never dropped. In fact nvme/058 associates some of
nvme namespaces to an inaccessible ANA state and with that nshead is
created but it's state is not transitioned to LIVE. So the current
logic would then causes nshead reference to be leaked for non-LIVE
states.

Another scenario, during namespace allocation, the driver first
allocates a nshead and then issues an Identify Namespace command. If
this command fails — which can happen in tests like nvme/058 that
rapidly enables and disables namespaces — we must release the reference
to the newly allocated nshead. However this reference release is
currently missing in the failure, causing a nshead reference leak.

To fix this, we now unconditionally release the nshead reference when
the last nvme path referencing to the nshead is removed, regardless of
the head’s state. Also during identify namespace failure case we now
properly release the nshead reference. So this ensures proper cleanup
of the nshead, and consequently, the NVMe subsystem and its associated
kobject.

This change prevents stale kobject entries from lingering in sysfs and
eliminates the module reload failures observed just after running
nvme/058.

[1] https://lore.kernel.org/all/CAHj4cs8fOBS-eSjsd5LUBzy7faKXJtgLkCN+mDy_-ezCLLLq+Q@mail.gmail.com/

Reported-by: yi.zhang@redhat.com
Closes: https://lore.kernel.org/all/CAHj4cs8fOBS-eSjsd5LUBzy7faKXJtgLkCN+mDy_-ezCLLLq+Q@mail.gmail.com/
Fixes: 62188639ec16 ("nvme-multipath: introduce delayed removal of the multipath head node")
Tested-by: yi.zhang@redhat.com
Signed-off-by: Nilay Shroff <nilay@linux.ibm.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/nvme/host/core.c      | 16 +++++++++++++++-
 drivers/nvme/host/multipath.c |  5 ++++-
 2 files changed, 19 insertions(+), 2 deletions(-)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 2ae36bce615e..7493e5aa984c 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -4086,6 +4086,7 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, struct nvme_ns_info *info)
 	struct nvme_ns *ns;
 	struct gendisk *disk;
 	int node = ctrl->numa_node;
+	bool last_path = false;
 
 	ns = kzalloc_node(sizeof(*ns), GFP_KERNEL, node);
 	if (!ns)
@@ -4178,9 +4179,22 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, struct nvme_ns_info *info)
  out_unlink_ns:
 	mutex_lock(&ctrl->subsys->lock);
 	list_del_rcu(&ns->siblings);
-	if (list_empty(&ns->head->list))
+	if (list_empty(&ns->head->list)) {
 		list_del_init(&ns->head->entry);
+		/*
+		 * If multipath is not configured, we still create a namespace
+		 * head (nshead), but head->disk is not initialized in that
+		 * case.  As a result, only a single reference to nshead is held
+		 * (via kref_init()) when it is created. Therefore, ensure that
+		 * we do not release the reference to nshead twice if head->disk
+		 * is not present.
+		 */
+		if (ns->head->disk)
+			last_path = true;
+	}
 	mutex_unlock(&ctrl->subsys->lock);
+	if (last_path)
+		nvme_put_ns_head(ns->head);
 	nvme_put_ns_head(ns->head);
  out_cleanup_disk:
 	put_disk(disk);
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index 1062467595f3..e03f3a29bd75 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -690,8 +690,8 @@ static void nvme_remove_head(struct nvme_ns_head *head)
 		nvme_cdev_del(&head->cdev, &head->cdev_device);
 		synchronize_srcu(&head->srcu);
 		del_gendisk(head->disk);
-		nvme_put_ns_head(head);
 	}
+	nvme_put_ns_head(head);
 }
 
 static void nvme_remove_head_work(struct work_struct *work)
@@ -1291,6 +1291,9 @@ void nvme_mpath_remove_disk(struct nvme_ns_head *head)
 {
 	bool remove = false;
 
+	if (!head->disk)
+		return;
+
 	mutex_lock(&head->subsys->lock);
 	/*
 	 * We are called when all paths have been removed, and at that point

From 190f4c2c863af7cc5bb354b70e0805f06419c038 Mon Sep 17 00:00:00 2001
From: Dmitry Bogdanov <d.bogdanov@yadro.com>
Date: Wed, 25 Jun 2025 14:45:33 +0300
Subject: [PATCH 1010/1334] nvmet: fix memory leak of bio integrity

If nvmet receives commands with metadata there is a continuous memory
leak of kmalloc-128 slab or more precisely bio->bi_integrity.

Since commit bf4c89fc8797 ("block: don't call bio_uninit from bio_endio")
each user of bio_init has to use bio_uninit as well. Otherwise the bio
integrity is not getting free. Nvmet uses bio_init for inline bios.

Uninit the inline bio to complete deallocation of integrity in bio.

Fixes: bf4c89fc8797 ("block: don't call bio_uninit from bio_endio")
Signed-off-by: Dmitry Bogdanov <d.bogdanov@yadro.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/nvme/target/nvmet.h | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h
index df69a9dee71c..51df72f5e89b 100644
--- a/drivers/nvme/target/nvmet.h
+++ b/drivers/nvme/target/nvmet.h
@@ -867,6 +867,8 @@ static inline void nvmet_req_bio_put(struct nvmet_req *req, struct bio *bio)
 {
 	if (bio != &req->b.inline_bio)
 		bio_put(bio);
+	else
+		bio_uninit(bio);
 }
 
 #ifdef CONFIG_NVME_TARGET_TCP_TLS

From 14005c96d6649b27fa52d0cd0f492eb3b5586c07 Mon Sep 17 00:00:00 2001
From: Eugen Hristev <eugen.hristev@collabora.com>
Date: Fri, 13 Jun 2025 16:21:01 -0300
Subject: [PATCH 1011/1334] nvme-pci: refresh visible attrs after being checked
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The sysfs attributes are registered early, but the driver does not know
whether they are needed or not at that moment.

For the CMB attributes, commit e917a849c3fc ("nvme-pci: refresh visible
attrs for cmb attributes") solved this problem by
calling nvme_update_attrs after mapping the CMB.  However the issue
persists for the HMB attributes. To solve the problem, moved the call to
nvme_update_attrs after nvme_setup_host_mem, which sets up the HMB.

Fixes: e917a849c3fc ("nvme-pci: refresh visible attrs for cmb attributes")
Fixes: 86adbf0cdb9e ("nvme: simplify transport specific device attribute handling")
Signed-off-by: Eugen Hristev <eugen.hristev@collabora.com>
Signed-off-by: André Almeida <andrealmeid@igalia.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/nvme/host/pci.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 8ff12e415cb5..320aaa41ec39 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -2101,8 +2101,6 @@ static void nvme_map_cmb(struct nvme_dev *dev)
 	if ((dev->cmbsz & (NVME_CMBSZ_WDS | NVME_CMBSZ_RDS)) ==
 			(NVME_CMBSZ_WDS | NVME_CMBSZ_RDS))
 		pci_p2pmem_publish(pdev, true);
-
-	nvme_update_attrs(dev);
 }
 
 static int nvme_set_host_mem(struct nvme_dev *dev, u32 bits)
@@ -3010,6 +3008,8 @@ static void nvme_reset_work(struct work_struct *work)
 	if (result < 0)
 		goto out;
 
+	nvme_update_attrs(dev);
+
 	result = nvme_setup_io_queues(dev);
 	if (result)
 		goto out;
@@ -3343,6 +3343,8 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	if (result < 0)
 		goto out_disable;
 
+	nvme_update_attrs(dev);
+
 	result = nvme_setup_io_queues(dev);
 	if (result)
 		goto out_disable;

From 6f49743af42ca43ef6d5487fc6d32f6184909430 Mon Sep 17 00:00:00 2001
From: Nathan Chancellor <nathan@kernel.org>
Date: Thu, 12 Jun 2025 12:57:01 -0700
Subject: [PATCH 1012/1334] riscv: Require clang-17 or newer for kCFI

After the combination of commit c217157bcd1d ("riscv: Implement
HAVE_DYNAMIC_FTRACE_WITH_CALL_OPS"), which starts using
'-fpatchable-function-entry=M,N', and commit d0262e907e29 ("riscv:
ftrace: support PREEMPT"), which allows CONFIG_DYNAMIC_FTRACE to be
enabled by allmodconfig, allmodconfig builds with clang-16 begin
crashing in the generic LLVM kCFI pass (see [1] for the stack trace).

clang-17 avoids this crash by moving to target-specific lowering of the
kCFI operand bundles [2]. Require clang-17 to select CONFIG_CFI_CLANG to
avoid this crash.

Fixes: c217157bcd1d ("riscv: Implement HAVE_DYNAMIC_FTRACE_WITH_CALL_OPS")
Link: https://godbolt.org/z/xG39Pn16o [1]
Link: https://github.com/llvm/llvm-project/commit/62fa708ceb027713b386c7e0efda994f8bdc27e2 [2]
Signed-off-by: Nathan Chancellor <nathan@kernel.org>
Reviewed-by: Sami Tolvanen <samitolvanen@google.com>
Link: https://lore.kernel.org/r/20250612-riscv-require-clang-17-for-kcfi-v1-1-216f7cd7d87f@kernel.org
Signed-off-by: Alexandre Ghiti <alexghiti@rivosinc.com>
---
 arch/riscv/Kconfig | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 36061f4732b7..d71ea0f4466f 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -63,7 +63,8 @@ config RISCV
 	select ARCH_OPTIONAL_KERNEL_RWX_DEFAULT
 	select ARCH_STACKWALK
 	select ARCH_SUPPORTS_ATOMIC_RMW
-	select ARCH_SUPPORTS_CFI_CLANG
+	# clang >= 17: https://github.com/llvm/llvm-project/commit/62fa708ceb027713b386c7e0efda994f8bdc27e2
+	select ARCH_SUPPORTS_CFI_CLANG if CLANG_VERSION >= 170000
 	select ARCH_SUPPORTS_DEBUG_PAGEALLOC if MMU
 	select ARCH_SUPPORTS_HUGE_PFNMAP if TRANSPARENT_HUGEPAGE
 	select ARCH_SUPPORTS_HUGETLBFS if MMU

From 2b29be967ae456fc09c320d91d52278cf721be1e Mon Sep 17 00:00:00 2001
From: Vivian Wang <wangruikang@iscas.ac.cn>
Date: Tue, 24 Jun 2025 16:04:46 +0800
Subject: [PATCH 1013/1334] riscv: cpu_ops_sbi: Use static array for boot_data

Since commit 6b9f29b81b15 ("riscv: Enable pcpu page first chunk
allocator"), if NUMA is enabled, the page percpu allocator may be used
on very sparse configurations, or when requested on boot with
percpu_alloc=page.

In that case, percpu data gets put in the vmalloc area. However,
sbi_hsm_hart_start() needs the physical address of a sbi_hart_boot_data,
and simply assumes that __pa() would work. This causes the just started
hart to immediately access an invalid address and hang.

Fortunately, struct sbi_hart_boot_data is not too large, so we can
simply allocate an array for boot_data statically, putting it in the
kernel image.

This fixes NUMA=y SMP boot on Sophgo SG2042.

To reproduce on QEMU: Set CONFIG_NUMA=y and CONFIG_DEBUG_VIRTUAL=y, then
run with:

  qemu-system-riscv64 -M virt -smp 2 -nographic \
    -kernel arch/riscv/boot/Image \
    -append "percpu_alloc=page"

Kernel output:

[    0.000000] Booting Linux on hartid 0
[    0.000000] Linux version 6.16.0-rc1 (dram@sakuya) (riscv64-unknown-linux-gnu-gcc (GCC) 14.2.1 20250322, GNU ld (GNU Binutils) 2.44) #11 SMP Tue Jun 24 14:56:22 CST 2025
...
[    0.000000] percpu: 28 4K pages/cpu s85784 r8192 d20712
...
[    0.083192] smp: Bringing up secondary CPUs ...
[    0.086722] ------------[ cut here ]------------
[    0.086849] virt_to_phys used for non-linear address: (____ptrval____) (0xff2000000001d080)
[    0.088001] WARNING: CPU: 0 PID: 1 at arch/riscv/mm/physaddr.c:14 __virt_to_phys+0xae/0xe8
[    0.088376] Modules linked in:
[    0.088656] CPU: 0 UID: 0 PID: 1 Comm: swapper/0 Not tainted 6.16.0-rc1 #11 NONE
[    0.088833] Hardware name: riscv-virtio,qemu (DT)
[    0.088948] epc : __virt_to_phys+0xae/0xe8
[    0.089001]  ra : __virt_to_phys+0xae/0xe8
[    0.089037] epc : ffffffff80021eaa ra : ffffffff80021eaa sp : ff2000000004bbc0
[    0.089057]  gp : ffffffff817f49c0 tp : ff60000001d60000 t0 : 5f6f745f74726976
[    0.089076]  t1 : 0000000000000076 t2 : 705f6f745f747269 s0 : ff2000000004bbe0
[    0.089095]  s1 : ff2000000001d080 a0 : 0000000000000000 a1 : 0000000000000000
[    0.089113]  a2 : 0000000000000000 a3 : 0000000000000000 a4 : 0000000000000000
[    0.089131]  a5 : 0000000000000000 a6 : 0000000000000000 a7 : 0000000000000000
[    0.089155]  s2 : ffffffff8130dc00 s3 : 0000000000000001 s4 : 0000000000000001
[    0.089174]  s5 : ffffffff8185eff8 s6 : ff2000007f1eb000 s7 : ffffffff8002a2ec
[    0.089193]  s8 : 0000000000000001 s9 : 0000000000000001 s10: 0000000000000000
[    0.089211]  s11: 0000000000000000 t3 : ffffffff8180a9f7 t4 : ffffffff8180a9f7
[    0.089960]  t5 : ffffffff8180a9f8 t6 : ff2000000004b9d8
[    0.089984] status: 0000000200000120 badaddr: ffffffff80021eaa cause: 0000000000000003
[    0.090101] [<ffffffff80021eaa>] __virt_to_phys+0xae/0xe8
[    0.090228] [<ffffffff8001d796>] sbi_cpu_start+0x6e/0xe8
[    0.090247] [<ffffffff8001a5da>] __cpu_up+0x1e/0x8c
[    0.090260] [<ffffffff8002a32e>] bringup_cpu+0x42/0x258
[    0.090277] [<ffffffff8002914c>] cpuhp_invoke_callback+0xe0/0x40c
[    0.090292] [<ffffffff800294e0>] __cpuhp_invoke_callback_range+0x68/0xfc
[    0.090320] [<ffffffff8002a96a>] _cpu_up+0x11a/0x244
[    0.090334] [<ffffffff8002aae6>] cpu_up+0x52/0x90
[    0.090384] [<ffffffff80c09350>] bringup_nonboot_cpus+0x78/0x118
[    0.090411] [<ffffffff80c11060>] smp_init+0x34/0xb8
[    0.090425] [<ffffffff80c01220>] kernel_init_freeable+0x148/0x2e4
[    0.090442] [<ffffffff80b83802>] kernel_init+0x1e/0x14c
[    0.090455] [<ffffffff800124ca>] ret_from_fork_kernel+0xe/0xf0
[    0.090471] [<ffffffff80b8d9c2>] ret_from_fork_kernel_asm+0x16/0x18
[    0.090560] ---[ end trace 0000000000000000 ]---
[    1.179875] CPU1: failed to come online
[    1.190324] smp: Brought up 1 node, 1 CPU

Cc: stable@vger.kernel.org
Reported-by: Han Gao <rabenda.cn@gmail.com>
Fixes: 6b9f29b81b15 ("riscv: Enable pcpu page first chunk allocator")
Reviewed-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Tested-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Signed-off-by: Vivian Wang <wangruikang@iscas.ac.cn>
Link: https://lore.kernel.org/r/20250624-riscv-hsm-boot-data-array-v1-1-50b5eeafbe61@iscas.ac.cn
Signed-off-by: Alexandre Ghiti <alexghiti@rivosinc.com>
---
 arch/riscv/kernel/cpu_ops_sbi.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/arch/riscv/kernel/cpu_ops_sbi.c b/arch/riscv/kernel/cpu_ops_sbi.c
index e6fbaaf54956..87d655944803 100644
--- a/arch/riscv/kernel/cpu_ops_sbi.c
+++ b/arch/riscv/kernel/cpu_ops_sbi.c
@@ -18,10 +18,10 @@ const struct cpu_operations cpu_ops_sbi;
 
 /*
  * Ordered booting via HSM brings one cpu at a time. However, cpu hotplug can
- * be invoked from multiple threads in parallel. Define a per cpu data
+ * be invoked from multiple threads in parallel. Define an array of boot data
  * to handle that.
  */
-static DEFINE_PER_CPU(struct sbi_hart_boot_data, boot_data);
+static struct sbi_hart_boot_data boot_data[NR_CPUS];
 
 static int sbi_hsm_hart_start(unsigned long hartid, unsigned long saddr,
 			      unsigned long priv)
@@ -67,7 +67,7 @@ static int sbi_cpu_start(unsigned int cpuid, struct task_struct *tidle)
 	unsigned long boot_addr = __pa_symbol(secondary_start_sbi);
 	unsigned long hartid = cpuid_to_hartid_map(cpuid);
 	unsigned long hsm_data;
-	struct sbi_hart_boot_data *bdata = &per_cpu(boot_data, cpuid);
+	struct sbi_hart_boot_data *bdata = &boot_data[cpuid];
 
 	/* Make sure tidle is updated */
 	smp_mb();

From 05f254a6369ac020fc0382a7cbd3ef64ad997c92 Mon Sep 17 00:00:00 2001
From: Alexander Tsoy <alexander@tsoy.me>
Date: Mon, 30 Jun 2025 04:33:57 +0300
Subject: [PATCH 1014/1334] ALSA: usb-audio: Improve filtering of sample rates
 on Focusrite devices

Previously we were filtering out only upper unsupported sampling rates.
This patch adds filtering of the lower unsupported sampling rates. As a
result there is 1:1 mapping between altsetting and supported rates.

The issue was found on a Scarlett 3rd Gen card (see linked bug), but the
same filtering is likely needed for the Scarlett 1st and 2nd Gen as well
as the older Clarett cards which lacks Valid Alternate Setting Control.

Patch was not tested on a real hardware.

Link: https://bugzilla.kernel.org/show_bug.cgi?id=214493
Signed-off-by: Alexander Tsoy <alexander@tsoy.me>
Link: https://patch.msgid.link/20250630013357.1327420-1-alexander@tsoy.me
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/usb/format.c | 22 ++++++++++------------
 1 file changed, 10 insertions(+), 12 deletions(-)

diff --git a/sound/usb/format.c b/sound/usb/format.c
index 8cd54f7bf33a..0ee532acbb60 100644
--- a/sound/usb/format.c
+++ b/sound/usb/format.c
@@ -310,16 +310,14 @@ static bool focusrite_valid_sample_rate(struct snd_usb_audio *chip,
 					struct audioformat *fp,
 					unsigned int rate)
 {
-	struct usb_interface *iface;
 	struct usb_host_interface *alts;
 	unsigned char *fmt;
 	unsigned int max_rate;
 
-	iface = usb_ifnum_to_if(chip->dev, fp->iface);
-	if (!iface)
+	alts = snd_usb_get_host_interface(chip, fp->iface, fp->altsetting);
+	if (!alts)
 		return true;
 
-	alts = &iface->altsetting[fp->altset_idx];
 	fmt = snd_usb_find_csint_desc(alts->extra, alts->extralen,
 				      NULL, UAC_FORMAT_TYPE);
 	if (!fmt)
@@ -328,20 +326,20 @@ static bool focusrite_valid_sample_rate(struct snd_usb_audio *chip,
 	if (fmt[0] == 10) { /* bLength */
 		max_rate = combine_quad(&fmt[6]);
 
-		/* Validate max rate */
-		if (max_rate != 48000 &&
-		    max_rate != 96000 &&
-		    max_rate != 192000 &&
-		    max_rate != 384000) {
-
+		switch (max_rate) {
+		case 48000:
+			return (rate == 44100 || rate == 48000);
+		case 96000:
+			return (rate == 88200 || rate == 96000);
+		case 192000:
+			return (rate == 176400 || rate == 192000);
+		default:
 			usb_audio_info(chip,
 				"%u:%d : unexpected max rate: %u\n",
 				fp->iface, fp->altsetting, max_rate);
 
 			return true;
 		}
-
-		return rate <= max_rate;
 	}
 
 	return true;

From 7b4c5a37544ba22c6ebe72c0d4ea56c953459fa5 Mon Sep 17 00:00:00 2001
From: Luo Gengkun <luogengkun@huaweicloud.com>
Date: Thu, 26 Jun 2025 13:54:03 +0000
Subject: [PATCH 1015/1334] perf/core: Fix the WARN_ON_ONCE is out of lock
 protected region

commit 3172fb986666 ("perf/core: Fix WARN in perf_cgroup_switch()") try to
fix a concurrency problem between perf_cgroup_switch and
perf_cgroup_event_disable. But it does not to move the WARN_ON_ONCE into
lock-protected region, so the warning is still be triggered.

Fixes: 3172fb986666 ("perf/core: Fix WARN in perf_cgroup_switch()")
Signed-off-by: Luo Gengkun <luogengkun@huaweicloud.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20250626135403.2454105-1-luogengkun@huaweicloud.com
---
 kernel/events/core.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 7281230044d0..bf2118c22126 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -951,8 +951,6 @@ static void perf_cgroup_switch(struct task_struct *task)
 	if (READ_ONCE(cpuctx->cgrp) == NULL)
 		return;
 
-	WARN_ON_ONCE(cpuctx->ctx.nr_cgroups == 0);
-
 	cgrp = perf_cgroup_from_task(task, NULL);
 	if (READ_ONCE(cpuctx->cgrp) == cgrp)
 		return;
@@ -964,6 +962,8 @@ static void perf_cgroup_switch(struct task_struct *task)
 	if (READ_ONCE(cpuctx->cgrp) == NULL)
 		return;
 
+	WARN_ON_ONCE(cpuctx->ctx.nr_cgroups == 0);
+
 	perf_ctx_disable(&cpuctx->ctx, true);
 
 	ctx_sched_out(&cpuctx->ctx, NULL, EVENT_ALL|EVENT_CGROUP);

From eb617dd25ca176f3fee24f873f0fd60010773d67 Mon Sep 17 00:00:00 2001
From: Kurt Borja <kuurtb@gmail.com>
Date: Mon, 30 Jun 2025 00:43:12 -0300
Subject: [PATCH 1016/1334] platform/x86: dell-wmi-sysman: Fix WMI data block
 retrieval in sysfs callbacks
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

After retrieving WMI data blocks in sysfs callbacks, check for the
validity of them before dereferencing their content.

Reported-by: Jan Graczyk <jangraczyk@yahoo.ca>
Closes: https://lore.kernel.org/r/CAHk-=wgMiSKXf7SvQrfEnxVtmT=QVQPjJdNjfm3aXS7wc=rzTw@mail.gmail.com/
Fixes: e8a60aa7404b ("platform/x86: Introduce support for Systems Management Driver over WMI for Dell Systems")
Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Reviewed-by: Armin Wolf <W_Armin@gmx.de>
Signed-off-by: Kurt Borja <kuurtb@gmail.com>
Link: https://lore.kernel.org/r/20250630-sysman-fix-v2-1-d185674d0a30@gmail.com
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 .../platform/x86/dell/dell-wmi-sysman/dell-wmi-sysman.h   | 5 +++++
 .../platform/x86/dell/dell-wmi-sysman/enum-attributes.c   | 5 +++--
 .../platform/x86/dell/dell-wmi-sysman/int-attributes.c    | 5 +++--
 .../x86/dell/dell-wmi-sysman/passobj-attributes.c         | 5 +++--
 .../platform/x86/dell/dell-wmi-sysman/string-attributes.c | 5 +++--
 drivers/platform/x86/dell/dell-wmi-sysman/sysman.c        | 8 ++++----
 6 files changed, 21 insertions(+), 12 deletions(-)

diff --git a/drivers/platform/x86/dell/dell-wmi-sysman/dell-wmi-sysman.h b/drivers/platform/x86/dell/dell-wmi-sysman/dell-wmi-sysman.h
index 3ad33a094588..817ee7ba07ca 100644
--- a/drivers/platform/x86/dell/dell-wmi-sysman/dell-wmi-sysman.h
+++ b/drivers/platform/x86/dell/dell-wmi-sysman/dell-wmi-sysman.h
@@ -89,6 +89,11 @@ extern struct wmi_sysman_priv wmi_priv;
 
 enum { ENUM, INT, STR, PO };
 
+#define ENUM_MIN_ELEMENTS		8
+#define INT_MIN_ELEMENTS		9
+#define STR_MIN_ELEMENTS		8
+#define PO_MIN_ELEMENTS			4
+
 enum {
 	ATTR_NAME,
 	DISPL_NAME_LANG_CODE,
diff --git a/drivers/platform/x86/dell/dell-wmi-sysman/enum-attributes.c b/drivers/platform/x86/dell/dell-wmi-sysman/enum-attributes.c
index 8cc212c85266..fc2f58b4cbc6 100644
--- a/drivers/platform/x86/dell/dell-wmi-sysman/enum-attributes.c
+++ b/drivers/platform/x86/dell/dell-wmi-sysman/enum-attributes.c
@@ -23,9 +23,10 @@ static ssize_t current_value_show(struct kobject *kobj, struct kobj_attribute *a
 	obj = get_wmiobj_pointer(instance_id, DELL_WMI_BIOS_ENUMERATION_ATTRIBUTE_GUID);
 	if (!obj)
 		return -EIO;
-	if (obj->package.elements[CURRENT_VAL].type != ACPI_TYPE_STRING) {
+	if (obj->type != ACPI_TYPE_PACKAGE || obj->package.count < ENUM_MIN_ELEMENTS ||
+	    obj->package.elements[CURRENT_VAL].type != ACPI_TYPE_STRING) {
 		kfree(obj);
-		return -EINVAL;
+		return -EIO;
 	}
 	ret = snprintf(buf, PAGE_SIZE, "%s\n", obj->package.elements[CURRENT_VAL].string.pointer);
 	kfree(obj);
diff --git a/drivers/platform/x86/dell/dell-wmi-sysman/int-attributes.c b/drivers/platform/x86/dell/dell-wmi-sysman/int-attributes.c
index 951e75b538fa..735248064239 100644
--- a/drivers/platform/x86/dell/dell-wmi-sysman/int-attributes.c
+++ b/drivers/platform/x86/dell/dell-wmi-sysman/int-attributes.c
@@ -25,9 +25,10 @@ static ssize_t current_value_show(struct kobject *kobj, struct kobj_attribute *a
 	obj = get_wmiobj_pointer(instance_id, DELL_WMI_BIOS_INTEGER_ATTRIBUTE_GUID);
 	if (!obj)
 		return -EIO;
-	if (obj->package.elements[CURRENT_VAL].type != ACPI_TYPE_INTEGER) {
+	if (obj->type != ACPI_TYPE_PACKAGE || obj->package.count < INT_MIN_ELEMENTS ||
+	    obj->package.elements[CURRENT_VAL].type != ACPI_TYPE_INTEGER) {
 		kfree(obj);
-		return -EINVAL;
+		return -EIO;
 	}
 	ret = snprintf(buf, PAGE_SIZE, "%lld\n", obj->package.elements[CURRENT_VAL].integer.value);
 	kfree(obj);
diff --git a/drivers/platform/x86/dell/dell-wmi-sysman/passobj-attributes.c b/drivers/platform/x86/dell/dell-wmi-sysman/passobj-attributes.c
index d8f1bf5e58a0..3167e06d416e 100644
--- a/drivers/platform/x86/dell/dell-wmi-sysman/passobj-attributes.c
+++ b/drivers/platform/x86/dell/dell-wmi-sysman/passobj-attributes.c
@@ -26,9 +26,10 @@ static ssize_t is_enabled_show(struct kobject *kobj, struct kobj_attribute *attr
 	obj = get_wmiobj_pointer(instance_id, DELL_WMI_BIOS_PASSOBJ_ATTRIBUTE_GUID);
 	if (!obj)
 		return -EIO;
-	if (obj->package.elements[IS_PASS_SET].type != ACPI_TYPE_INTEGER) {
+	if (obj->type != ACPI_TYPE_PACKAGE || obj->package.count < PO_MIN_ELEMENTS ||
+	    obj->package.elements[IS_PASS_SET].type != ACPI_TYPE_INTEGER) {
 		kfree(obj);
-		return -EINVAL;
+		return -EIO;
 	}
 	ret = snprintf(buf, PAGE_SIZE, "%lld\n", obj->package.elements[IS_PASS_SET].integer.value);
 	kfree(obj);
diff --git a/drivers/platform/x86/dell/dell-wmi-sysman/string-attributes.c b/drivers/platform/x86/dell/dell-wmi-sysman/string-attributes.c
index c392f0ecf8b5..0d2c74f8d1aa 100644
--- a/drivers/platform/x86/dell/dell-wmi-sysman/string-attributes.c
+++ b/drivers/platform/x86/dell/dell-wmi-sysman/string-attributes.c
@@ -25,9 +25,10 @@ static ssize_t current_value_show(struct kobject *kobj, struct kobj_attribute *a
 	obj = get_wmiobj_pointer(instance_id, DELL_WMI_BIOS_STRING_ATTRIBUTE_GUID);
 	if (!obj)
 		return -EIO;
-	if (obj->package.elements[CURRENT_VAL].type != ACPI_TYPE_STRING) {
+	if (obj->type != ACPI_TYPE_PACKAGE || obj->package.count < STR_MIN_ELEMENTS ||
+	    obj->package.elements[CURRENT_VAL].type != ACPI_TYPE_STRING) {
 		kfree(obj);
-		return -EINVAL;
+		return -EIO;
 	}
 	ret = snprintf(buf, PAGE_SIZE, "%s\n", obj->package.elements[CURRENT_VAL].string.pointer);
 	kfree(obj);
diff --git a/drivers/platform/x86/dell/dell-wmi-sysman/sysman.c b/drivers/platform/x86/dell/dell-wmi-sysman/sysman.c
index d00389b860e4..3c74d5e8350a 100644
--- a/drivers/platform/x86/dell/dell-wmi-sysman/sysman.c
+++ b/drivers/platform/x86/dell/dell-wmi-sysman/sysman.c
@@ -407,10 +407,10 @@ static int init_bios_attributes(int attr_type, const char *guid)
 		return retval;
 
 	switch (attr_type) {
-	case ENUM:	min_elements = 8;	break;
-	case INT:	min_elements = 9;	break;
-	case STR:	min_elements = 8;	break;
-	case PO:	min_elements = 4;	break;
+	case ENUM:	min_elements = ENUM_MIN_ELEMENTS;	break;
+	case INT:	min_elements = INT_MIN_ELEMENTS;	break;
+	case STR:	min_elements = STR_MIN_ELEMENTS;	break;
+	case PO:	min_elements = PO_MIN_ELEMENTS;		break;
 	default:
 		pr_err("Error: Unknown attr_type: %d\n", attr_type);
 		return -EINVAL;

From 1e14ea901dc8d976d355ddc3e0de84ee86ef0596 Mon Sep 17 00:00:00 2001
From: Shiju Jose <shiju.jose@huawei.com>
Date: Thu, 26 Jun 2025 11:13:44 +0100
Subject: [PATCH 1017/1334] EDAC: Initialize EDAC features sysfs attributes

Fix the lockdep splat caused by missing sysfs_attr_init() calls for the
recently added EDAC feature's sysfs attributes.

In lockdep_init_map_type(), the check for the lock-class key if
(!static_obj(key) && !is_dynamic_key(key)) causes the splat.

  Backtrace:
  RIP: 0010:lockdep_init_map_type
  Call Trace:
   __kernfs_create_file
  sysfs_add_file_mode_ns
  internal_create_group
  internal_create_groups
  device_add
  ? __init_waitqueue_head
  edac_dev_register
  devm_cxl_memdev_edac_register
  ? lock_acquire
  ? find_held_lock
  ? cxl_mem_probe
  ? cxl_mem_probe
  ? lockdep_hardirqs_on
  ? cxl_mem_probe
  cxl_mem_probe

  [ bp: Massage. ]

Fixes: f90b738166fe ("EDAC: Add scrub control feature")
Fixes: bcbd069b11b0 ("EDAC: Add a Error Check Scrub control feature")
Fixes: 699ea5219c4b ("EDAC: Add a memory repair control feature")
Reported-by: Dave Jiang <dave.jiang@intel.com>
Suggested-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Shiju Jose <shiju.jose@huawei.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Jonathan Cameron <jonathan.cameron@huawei.com>
Link: https://lore.kernel.org/20250626101344.1726-1-shiju.jose@huawei.com
---
 drivers/edac/ecs.c        | 4 +++-
 drivers/edac/mem_repair.c | 1 +
 drivers/edac/scrub.c      | 1 +
 3 files changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/edac/ecs.c b/drivers/edac/ecs.c
index 1d51838a60c1..51c451c7f0f0 100755
--- a/drivers/edac/ecs.c
+++ b/drivers/edac/ecs.c
@@ -170,8 +170,10 @@ static int ecs_create_desc(struct device *ecs_dev, const struct attribute_group
 		fru_ctx->dev_attr[ECS_RESET]		= EDAC_ECS_ATTR_WO(reset, fru);
 		fru_ctx->dev_attr[ECS_THRESHOLD]	= EDAC_ECS_ATTR_RW(threshold, fru);
 
-		for (i = 0; i < ECS_MAX_ATTRS; i++)
+		for (i = 0; i < ECS_MAX_ATTRS; i++) {
+			sysfs_attr_init(&fru_ctx->dev_attr[i].dev_attr.attr);
 			fru_ctx->ecs_attrs[i] = &fru_ctx->dev_attr[i].dev_attr.attr;
+		}
 
 		sprintf(fru_ctx->name, "%s%d", EDAC_ECS_FRU_NAME, fru);
 		group->name = fru_ctx->name;
diff --git a/drivers/edac/mem_repair.c b/drivers/edac/mem_repair.c
index d1a8caa85369..70a033a76233 100755
--- a/drivers/edac/mem_repair.c
+++ b/drivers/edac/mem_repair.c
@@ -333,6 +333,7 @@ static int mem_repair_create_desc(struct device *dev,
 	for (i = 0; i < MR_MAX_ATTRS; i++) {
 		memcpy(&ctx->mem_repair_dev_attr[i],
 		       &dev_attr[i], sizeof(dev_attr[i]));
+		sysfs_attr_init(&ctx->mem_repair_dev_attr[i].dev_attr.attr);
 		ctx->mem_repair_attrs[i] =
 			&ctx->mem_repair_dev_attr[i].dev_attr.attr;
 	}
diff --git a/drivers/edac/scrub.c b/drivers/edac/scrub.c
index e421d3ebd959..f9d02af2fc3a 100755
--- a/drivers/edac/scrub.c
+++ b/drivers/edac/scrub.c
@@ -176,6 +176,7 @@ static int scrub_create_desc(struct device *scrub_dev,
 	group = &scrub_ctx->group;
 	for (i = 0; i < SCRUB_MAX_ATTRS; i++) {
 		memcpy(&scrub_ctx->scrub_dev_attr[i], &dev_attr[i], sizeof(dev_attr[i]));
+		sysfs_attr_init(&scrub_ctx->scrub_dev_attr[i].dev_attr.attr);
 		scrub_ctx->scrub_attrs[i] = &scrub_ctx->scrub_dev_attr[i].dev_attr.attr;
 	}
 	sprintf(scrub_ctx->name, "%s%d", "scrub", instance);

From e1af6f0146d64fc4fb142504ba128a97cd171558 Mon Sep 17 00:00:00 2001
From: Pratap Nirujogi <pratap.nirujogi@amd.com>
Date: Wed, 18 Jun 2025 16:29:48 -0400
Subject: [PATCH 1018/1334] platform/x86: Update swnode graph for amd isp4
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Existing swnode graph format is specific to sensor device
and is causing conflicts when accessing standard property
variables outside the sensor driver.

To address this issue, enhanced swnode graph format with
dedicated nodes for i2c and isp devices, with sensor node
added as child to i2c node. This approach allows to have
standard property variables (ex: 'clock-frequency') with
values applicable for each of the devices (sensor, i2c and
isp).

ACPI device driver_data handle is also initialized with root
camera swnode to access the property variables in the graph
in isp and i2c drivers.

Signed-off-by: Pratap Nirujogi <pratap.nirujogi@amd.com>
Reviewed-by: Mario Limonciello <mario.limonciello@amd.com>
Link: https://lore.kernel.org/r/20250618202958.3934822-1-pratap.nirujogi@amd.com
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/amd/amd_isp4.c | 181 ++++++++++++++++++++++------
 1 file changed, 144 insertions(+), 37 deletions(-)

diff --git a/drivers/platform/x86/amd/amd_isp4.c b/drivers/platform/x86/amd/amd_isp4.c
index 0cc01441bcbb..c440a7dfed27 100644
--- a/drivers/platform/x86/amd/amd_isp4.c
+++ b/drivers/platform/x86/amd/amd_isp4.c
@@ -20,6 +20,9 @@
 #define AMDISP_OV05C10_REMOTE_EP_NAME	"ov05c10_isp_4_1_1"
 #define AMD_ISP_PLAT_DRV_NAME		"amd-isp4"
 
+static const struct software_node isp4_mipi1_endpoint_node;
+static const struct software_node ov05c10_endpoint_node;
+
 /*
  * AMD ISP platform info definition to initialize sensor
  * specific platform configuration to prepare the amdisp
@@ -42,55 +45,116 @@ struct amdisp_platform {
 	struct mutex lock;	/* protects i2c client creation */
 };
 
-/* Top-level OV05C10 camera node property table */
+/* Root AMD CAMERA SWNODE */
+
+/* Root amd camera node definition */
+static const struct software_node amd_camera_node = {
+	.name = "amd_camera",
+};
+
+/* ISP4 SWNODE */
+
+/* ISP4 OV05C10 camera node definition */
+static const struct software_node isp4_node = {
+	.name = "isp4",
+	.parent = &amd_camera_node,
+};
+
+/*
+ * ISP4 Ports node definition. No properties defined for
+ * ports node.
+ */
+static const struct software_node isp4_ports = {
+	.name = "ports",
+	.parent = &isp4_node,
+};
+
+/*
+ * ISP4 Port node definition. No properties defined for
+ * port node.
+ */
+static const struct software_node isp4_port_node = {
+	.name = "port@0",
+	.parent = &isp4_ports,
+};
+
+/*
+ * ISP4 MIPI1 remote endpoint points to OV05C10 endpoint
+ * node.
+ */
+static const struct software_node_ref_args isp4_refs[] = {
+	SOFTWARE_NODE_REFERENCE(&ov05c10_endpoint_node),
+};
+
+/* ISP4 MIPI1 endpoint node properties table */
+static const struct property_entry isp4_mipi1_endpoint_props[] = {
+	PROPERTY_ENTRY_REF_ARRAY("remote-endpoint", isp4_refs),
+	{ }
+};
+
+/* ISP4 MIPI1 endpoint node definition */
+static const struct software_node isp4_mipi1_endpoint_node = {
+	.name = "endpoint",
+	.parent = &isp4_port_node,
+	.properties = isp4_mipi1_endpoint_props,
+};
+
+/* I2C1 SWNODE */
+
+/* I2C1 camera node property table */
+static const struct property_entry i2c1_camera_props[] = {
+	PROPERTY_ENTRY_U32("clock-frequency", 1 * HZ_PER_MHZ),
+	{ }
+};
+
+/* I2C1 camera node definition */
+static const struct software_node i2c1_node = {
+	.name = "i2c1",
+	.parent = &amd_camera_node,
+	.properties = i2c1_camera_props,
+};
+
+/* I2C1 camera node property table */
 static const struct property_entry ov05c10_camera_props[] = {
 	PROPERTY_ENTRY_U32("clock-frequency", 24 * HZ_PER_MHZ),
 	{ }
 };
 
-/* Root AMD ISP OV05C10 camera node definition */
-static const struct software_node camera_node = {
+/* OV05C10 camera node definition */
+static const struct software_node ov05c10_camera_node = {
 	.name = AMDISP_OV05C10_HID,
+	.parent = &i2c1_node,
 	.properties = ov05c10_camera_props,
 };
 
 /*
- * AMD ISP OV05C10 Ports node definition. No properties defined for
+ * OV05C10 Ports node definition. No properties defined for
  * ports node for OV05C10.
  */
-static const struct software_node ports = {
+static const struct software_node ov05c10_ports = {
 	.name = "ports",
-	.parent = &camera_node,
+	.parent = &ov05c10_camera_node,
 };
 
 /*
- * AMD ISP OV05C10 Port node definition. No properties defined for
- * port node for OV05C10.
+ * OV05C10 Port node definition.
  */
-static const struct software_node port_node = {
-	.name = "port@",
-	.parent = &ports,
+static const struct software_node ov05c10_port_node = {
+	.name = "port@0",
+	.parent = &ov05c10_ports,
 };
 
 /*
- * Remote endpoint AMD ISP node definition. No properties defined for
- * remote endpoint node for OV05C10.
- */
-static const struct software_node remote_ep_isp_node = {
-	.name = AMDISP_OV05C10_REMOTE_EP_NAME,
-};
-
-/*
- * Remote endpoint reference for isp node included in the
- * OV05C10 endpoint.
+ * OV05C10 remote endpoint points to ISP4 MIPI1 endpoint
+ * node.
  */
 static const struct software_node_ref_args ov05c10_refs[] = {
-	SOFTWARE_NODE_REFERENCE(&remote_ep_isp_node),
+	SOFTWARE_NODE_REFERENCE(&isp4_mipi1_endpoint_node),
 };
 
 /* OV05C10 supports one single link frequency */
 static const u64 ov05c10_link_freqs[] = {
-	925 * HZ_PER_MHZ,
+	900 * HZ_PER_MHZ,
 };
 
 /* OV05C10 supports only 2-lane configuration */
@@ -110,27 +174,64 @@ static const struct property_entry ov05c10_endpoint_props[] = {
 	{ }
 };
 
-/* AMD ISP endpoint node definition */
-static const struct software_node endpoint_node = {
+/* OV05C10 endpoint node definition */
+static const struct software_node ov05c10_endpoint_node = {
 	.name = "endpoint",
-	.parent = &port_node,
+	.parent = &ov05c10_port_node,
 	.properties = ov05c10_endpoint_props,
 };
 
 /*
- * AMD ISP swnode graph uses 5 nodes and also its relationship is
- * fixed to align with the structure that v4l2 expects for successful
- * endpoint fwnode parsing.
+ * AMD Camera swnode graph uses 10 nodes and also its relationship is
+ * fixed to align with the structure that v4l2 and i2c frameworks expects
+ * for successful parsing of fwnodes and its properties with standard names.
  *
  * It is only the node property_entries that will vary for each platform
  * supporting different sensor modules.
+ *
+ * AMD ISP4 SWNODE GRAPH Structure
+ *
+ * amd_camera {
+ *  isp4 {
+ *	  ports {
+ *		  port@0 {
+ *			  isp4_mipi1_ep: endpoint {
+ *					  remote-endpoint = &OMNI5C10_ep;
+ *			  };
+ *		  };
+ *	  };
+ *  };
+ *
+ *  i2c1 {
+ *	  clock-frequency = 1 MHz;
+ *	  OMNI5C10 {
+ *		  clock-frequency = 24MHz;
+ *		  ports {
+ *			  port@0 {
+ *				  OMNI5C10_ep: endpoint {
+ *					  bus-type = 4;
+ *					  data-lanes = <1 2>;
+ *					  link-frequencies = 900MHz;
+ *					  remote-endpoint = &isp4_mipi1;
+ *				  };
+ *			  };
+ *		  };
+ *	  };
+ *	};
+ * };
+ *
  */
-static const struct software_node *ov05c10_nodes[] = {
-	&camera_node,
-	&ports,
-	&port_node,
-	&endpoint_node,
-	&remote_ep_isp_node,
+static const struct software_node *amd_isp4_nodes[] = {
+	&amd_camera_node,
+	&isp4_node,
+	&isp4_ports,
+	&isp4_port_node,
+	&isp4_mipi1_endpoint_node,
+	&i2c1_node,
+	&ov05c10_camera_node,
+	&ov05c10_ports,
+	&ov05c10_port_node,
+	&ov05c10_endpoint_node,
 	NULL
 };
 
@@ -140,7 +241,7 @@ static const struct amdisp_platform_info ov05c10_platform_config = {
 		.dev_name = "ov05c10",
 		I2C_BOARD_INFO("ov05c10", AMDISP_OV05C10_I2C_ADDR),
 	},
-	.swnodes = ov05c10_nodes,
+	.swnodes = amd_isp4_nodes,
 };
 
 static const struct acpi_device_id amdisp_sensor_ids[] = {
@@ -232,7 +333,8 @@ static struct amdisp_platform *prepare_amdisp_platform(struct device *dev,
 	if (ret)
 		return ERR_PTR(ret);
 
-	isp4_platform->board_info.swnode = src->swnodes[0];
+	/* initialize ov05c10_camera_node */
+	isp4_platform->board_info.swnode = src->swnodes[6];
 
 	return isp4_platform;
 }
@@ -257,6 +359,7 @@ static int amd_isp_probe(struct platform_device *pdev)
 {
 	const struct amdisp_platform_info *pinfo;
 	struct amdisp_platform *isp4_platform;
+	struct acpi_device *adev;
 	int ret;
 
 	pinfo = device_get_match_data(&pdev->dev);
@@ -274,6 +377,10 @@ static int amd_isp_probe(struct platform_device *pdev)
 	if (ret)
 		goto error_unregister_sw_node;
 
+	adev = ACPI_COMPANION(&pdev->dev);
+	/* initialize root amd_camera_node */
+	adev->driver_data = (void *)pinfo->swnodes[0];
+
 	/* check if adapter is already registered and create i2c client instance */
 	i2c_for_each_dev(isp4_platform, try_to_instantiate_i2c_client);
 

From 11cba4793b95df3bc192149a6eb044f69aa0b99e Mon Sep 17 00:00:00 2001
From: Kurt Borja <kuurtb@gmail.com>
Date: Wed, 25 Jun 2025 22:17:35 -0300
Subject: [PATCH 1019/1334] platform/x86: hp-bioscfg: Fix class device
 unregistration
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Devices under the firmware_attributes_class do not have unique a dev_t.
Therefore, device_unregister() should be used instead of
device_destroy(), since the latter may match any device with a given
dev_t.

Fixes: a34fc329b189 ("platform/x86: hp-bioscfg: bioscfg")
Signed-off-by: Kurt Borja <kuurtb@gmail.com>
Link: https://lore.kernel.org/r/20250625-dest-fix-v1-1-3a0f342312bb@gmail.com
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/hp/hp-bioscfg/bioscfg.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/platform/x86/hp/hp-bioscfg/bioscfg.c b/drivers/platform/x86/hp/hp-bioscfg/bioscfg.c
index 13237890fc92..5bfa7159f5bc 100644
--- a/drivers/platform/x86/hp/hp-bioscfg/bioscfg.c
+++ b/drivers/platform/x86/hp/hp-bioscfg/bioscfg.c
@@ -1034,7 +1034,7 @@ err_release_attributes_data:
 	release_attributes_data();
 
 err_destroy_classdev:
-	device_destroy(&firmware_attributes_class, MKDEV(0, 0));
+	device_unregister(bioscfg_drv.class_dev);
 
 err_unregister_class:
 	hp_exit_attr_set_interface();
@@ -1045,7 +1045,7 @@ err_unregister_class:
 static void __exit hp_exit(void)
 {
 	release_attributes_data();
-	device_destroy(&firmware_attributes_class, MKDEV(0, 0));
+	device_unregister(bioscfg_drv.class_dev);
 
 	hp_exit_attr_set_interface();
 }

From 5ff1fbb3059730700b4823f43999fc1315984632 Mon Sep 17 00:00:00 2001
From: Kurt Borja <kuurtb@gmail.com>
Date: Wed, 25 Jun 2025 22:17:36 -0300
Subject: [PATCH 1020/1334] platform/x86: think-lmi: Fix class device
 unregistration
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Devices under the firmware_attributes_class do not have unique a dev_t.
Therefore, device_unregister() should be used instead of
device_destroy(), since the latter may match any device with a given
dev_t.

Fixes: a40cd7ef22fb ("platform/x86: think-lmi: Add WMI interface support on Lenovo platforms")
Signed-off-by: Kurt Borja <kuurtb@gmail.com>
Link: https://lore.kernel.org/r/20250625-dest-fix-v1-2-3a0f342312bb@gmail.com
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/think-lmi.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/platform/x86/think-lmi.c b/drivers/platform/x86/think-lmi.c
index 00b1e7c79a3d..28ce475f6c37 100644
--- a/drivers/platform/x86/think-lmi.c
+++ b/drivers/platform/x86/think-lmi.c
@@ -1554,7 +1554,7 @@ static int tlmi_sysfs_init(void)
 fail_create_attr:
 	tlmi_release_attr();
 fail_device_created:
-	device_destroy(&firmware_attributes_class, MKDEV(0, 0));
+	device_unregister(tlmi_priv.class_dev);
 fail_class_created:
 	return ret;
 }
@@ -1781,7 +1781,7 @@ fail_clear_attr:
 static void tlmi_remove(struct wmi_device *wdev)
 {
 	tlmi_release_attr();
-	device_destroy(&firmware_attributes_class, MKDEV(0, 0));
+	device_unregister(tlmi_priv.class_dev);
 }
 
 static int tlmi_probe(struct wmi_device *wdev, const void *context)

From 314e5ad4782d08858b3abc325c0487bd2abc23a1 Mon Sep 17 00:00:00 2001
From: Kurt Borja <kuurtb@gmail.com>
Date: Wed, 25 Jun 2025 22:17:37 -0300
Subject: [PATCH 1021/1334] platform/x86: dell-wmi-sysman: Fix class device
 unregistration
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Devices under the firmware_attributes_class do not have unique a dev_t.
Therefore, device_unregister() should be used instead of
device_destroy(), since the latter may match any device with a given
dev_t.

Fixes: e8a60aa7404b ("platform/x86: Introduce support for Systems Management Driver over WMI for Dell Systems")
Signed-off-by: Kurt Borja <kuurtb@gmail.com>
Link: https://lore.kernel.org/r/20250625-dest-fix-v1-3-3a0f342312bb@gmail.com
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/dell/dell-wmi-sysman/sysman.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/platform/x86/dell/dell-wmi-sysman/sysman.c b/drivers/platform/x86/dell/dell-wmi-sysman/sysman.c
index 3c74d5e8350a..f5402b714657 100644
--- a/drivers/platform/x86/dell/dell-wmi-sysman/sysman.c
+++ b/drivers/platform/x86/dell/dell-wmi-sysman/sysman.c
@@ -597,7 +597,7 @@ err_release_attributes_data:
 	release_attributes_data();
 
 err_destroy_classdev:
-	device_destroy(&firmware_attributes_class, MKDEV(0, 0));
+	device_unregister(wmi_priv.class_dev);
 
 err_exit_bios_attr_pass_interface:
 	exit_bios_attr_pass_interface();
@@ -611,7 +611,7 @@ err_exit_bios_attr_set_interface:
 static void __exit sysman_exit(void)
 {
 	release_attributes_data();
-	device_destroy(&firmware_attributes_class, MKDEV(0, 0));
+	device_unregister(wmi_priv.class_dev);
 	exit_bios_attr_set_interface();
 	exit_bios_attr_pass_interface();
 }

From 690be4bc589a145dc211b8d66b8f851713abd344 Mon Sep 17 00:00:00 2001
From: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Date: Tue, 17 Jun 2025 16:29:13 -0700
Subject: [PATCH 1022/1334] platform/x86/intel/hid: Add Wildcat Lake support
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add ACPI ID for Wildcat Lake.

Signed-off-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Link: https://lore.kernel.org/r/20250617232913.3314765-1-srinivas.pandruvada@linux.intel.com
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/intel/hid.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/platform/x86/intel/hid.c b/drivers/platform/x86/intel/hid.c
index 0b5e43444ed6..f25a427cccda 100644
--- a/drivers/platform/x86/intel/hid.c
+++ b/drivers/platform/x86/intel/hid.c
@@ -54,6 +54,7 @@ static const struct acpi_device_id intel_hid_ids[] = {
 	{ "INTC107B" },
 	{ "INTC10CB" },
 	{ "INTC10CC" },
+	{ "INTC10F1" },
 	{ }
 };
 MODULE_DEVICE_TABLE(acpi, intel_hid_ids);

From b1c26e059536d8acbf9d508374f4b76537e20fb7 Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Tue, 10 Jun 2025 15:58:16 -0500
Subject: [PATCH 1023/1334] Move FCH header to a location accessible by all
 archs
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

A new header fch.h was created to store registers used by different AMD
drivers.  This header was included by i2c-piix4 in
commit 624b0d5696a8 ("i2c: piix4, x86/platform: Move the SB800 PIIX4 FCH
definitions to <asm/amd/fch.h>"). To prevent compile failures on non-x86
archs i2c-piix4 was set to only compile on x86 by commit 7e173eb82ae9717
("i2c: piix4: Make CONFIG_I2C_PIIX4 dependent on CONFIG_X86").
This was not a good decision because loongarch and mips both actually
support i2c-piix4 and set it enabled in the defconfig.

Move the header to a location accessible by all architectures.

Fixes: 624b0d5696a89 ("i2c: piix4, x86/platform: Move the SB800 PIIX4 FCH definitions to <asm/amd/fch.h>")
Suggested-by: Hans de Goede <hansg@kernel.org>
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Reviewed-by: Hans de Goede <hansg@kernel.org>
Link: https://lore.kernel.org/r/20250610205817.3912944-1-superm1@kernel.org
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 arch/x86/kernel/cpu/amd.c                                       | 2 +-
 drivers/i2c/busses/i2c-piix4.c                                  | 2 +-
 drivers/platform/x86/amd/pmc/pmc-quirks.c                       | 2 +-
 .../asm/amd/fch.h => include/linux/platform_data/x86/amd-fch.h  | 0
 4 files changed, 3 insertions(+), 3 deletions(-)
 rename arch/x86/include/asm/amd/fch.h => include/linux/platform_data/x86/amd-fch.h (100%)

diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 93da466dfe2c..9543d5de4e7d 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -9,7 +9,7 @@
 #include <linux/sched/clock.h>
 #include <linux/random.h>
 #include <linux/topology.h>
-#include <asm/amd/fch.h>
+#include <linux/platform_data/x86/amd-fch.h>
 #include <asm/processor.h>
 #include <asm/apic.h>
 #include <asm/cacheinfo.h>
diff --git a/drivers/i2c/busses/i2c-piix4.c b/drivers/i2c/busses/i2c-piix4.c
index 9d3a4dc2bd60..ac3bb550303f 100644
--- a/drivers/i2c/busses/i2c-piix4.c
+++ b/drivers/i2c/busses/i2c-piix4.c
@@ -34,7 +34,7 @@
 #include <linux/dmi.h>
 #include <linux/acpi.h>
 #include <linux/io.h>
-#include <asm/amd/fch.h>
+#include <linux/platform_data/x86/amd-fch.h>
 
 #include "i2c-piix4.h"
 
diff --git a/drivers/platform/x86/amd/pmc/pmc-quirks.c b/drivers/platform/x86/amd/pmc/pmc-quirks.c
index f292111bd065..131f10b68308 100644
--- a/drivers/platform/x86/amd/pmc/pmc-quirks.c
+++ b/drivers/platform/x86/amd/pmc/pmc-quirks.c
@@ -11,7 +11,7 @@
 #include <linux/dmi.h>
 #include <linux/io.h>
 #include <linux/ioport.h>
-#include <asm/amd/fch.h>
+#include <linux/platform_data/x86/amd-fch.h>
 
 #include "pmc.h"
 
diff --git a/arch/x86/include/asm/amd/fch.h b/include/linux/platform_data/x86/amd-fch.h
similarity index 100%
rename from arch/x86/include/asm/amd/fch.h
rename to include/linux/platform_data/x86/amd-fch.h

From af14ed3fcb2703d1185bf10531fee87e6e1cc60b Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Tue, 10 Jun 2025 15:58:17 -0500
Subject: [PATCH 1024/1334] i2c: Re-enable piix4 driver on non-x86
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

loongarch and mips both support hardware that uses the i2c-piix4 driver.
It should not be restricted to x86, so drop the x86 dependency.

Reported-by: Geert Uytterhoeven <geert@linux-m68k.org>
Closes: https://lore.kernel.org/all/CAMuHMdVPQLjOox5sMp34Z5MTwKv2WOpHa=MpZr8hWG22fQKcjw@mail.gmail.com/
Fixes: 7e173eb82ae97175 ("i2c: piix4: Make CONFIG_I2C_PIIX4 dependent on CONFIG_X86").
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Reviewed-by: Hans de Goede <hansg@kernel.org>
Acked-by: Andi Shyti <andi.shyti@kernel.org>
Link: https://lore.kernel.org/r/20250610205817.3912944-2-superm1@kernel.org
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/i2c/busses/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/i2c/busses/Kconfig b/drivers/i2c/busses/Kconfig
index 48c5ab832009..3be623735ca8 100644
--- a/drivers/i2c/busses/Kconfig
+++ b/drivers/i2c/busses/Kconfig
@@ -200,7 +200,7 @@ config I2C_ISMT
 
 config I2C_PIIX4
 	tristate "Intel PIIX4 and compatible (ATI/AMD/Serverworks/Broadcom/SMSC)"
-	depends on PCI && HAS_IOPORT && X86
+	depends on PCI && HAS_IOPORT
 	select I2C_SMBUS
 	help
 	  If you say yes to this option, support will be included for the Intel

From 644bec18e705ca41d444053407419a21832fcb2f Mon Sep 17 00:00:00 2001
From: Alok Tiwari <alok.a.tiwari@oracle.com>
Date: Mon, 30 Jun 2025 03:58:08 -0700
Subject: [PATCH 1025/1334] platform/mellanox: mlxreg-lc: Fix logic error in
 power state check
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Fixes a logic issue in mlxreg_lc_completion_notify() where the
intention was to check if MLXREG_LC_POWERED flag is not set before
powering on the device.

The original code used "state & ~MLXREG_LC_POWERED" to check for the
absence of the POWERED bit. However this condition evaluates to true
even when other bits are set, leading to potentially incorrect
behavior.

Corrected the logic to explicitly check for the absence of
MLXREG_LC_POWERED using !(state & MLXREG_LC_POWERED).

Fixes: 62f9529b8d5c ("platform/mellanox: mlxreg-lc: Add initial support for Nvidia line card devices")
Suggested-by: Vadim Pasternak <vadimp@nvidia.com>
Signed-off-by: Alok Tiwari <alok.a.tiwari@oracle.com>
Link: https://lore.kernel.org/r/20250630105812.601014-1-alok.a.tiwari@oracle.com
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/mellanox/mlxreg-lc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/platform/mellanox/mlxreg-lc.c b/drivers/platform/mellanox/mlxreg-lc.c
index 8eef3d990d1a..d1518598dfed 100644
--- a/drivers/platform/mellanox/mlxreg-lc.c
+++ b/drivers/platform/mellanox/mlxreg-lc.c
@@ -688,7 +688,7 @@ static int mlxreg_lc_completion_notify(void *handle, struct i2c_adapter *parent,
 	if (regval & mlxreg_lc->data->mask) {
 		mlxreg_lc->state |= MLXREG_LC_SYNCED;
 		mlxreg_lc_state_update_locked(mlxreg_lc, MLXREG_LC_SYNCED, 1);
-		if (mlxreg_lc->state & ~MLXREG_LC_POWERED) {
+		if (!(mlxreg_lc->state & MLXREG_LC_POWERED)) {
 			err = mlxreg_lc_power_on_off(mlxreg_lc, 1);
 			if (err)
 				goto mlxreg_lc_regmap_power_on_off_fail;

From 2b95a7db6e0f75587bffddbb490399cbb87e4985 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Christian=20K=C3=B6nig?= <christian.koenig@amd.com>
Date: Tue, 28 Jan 2025 10:47:48 +0100
Subject: [PATCH 1026/1334] dma-buf: fix timeout handling in
 dma_resv_wait_timeout v2
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Even the kerneldoc says that with a zero timeout the function should not
wait for anything, but still return 1 to indicate that the fences are
signaled now.

Unfortunately that isn't what was implemented, instead of only returning
1 we also waited for at least one jiffies.

Fix that by adjusting the handling to what the function is actually
documented to do.

v2: improve code readability

Reported-by: Marek Olšák <marek.olsak@amd.com>
Reported-by: Lucas Stach <l.stach@pengutronix.de>
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Lucas Stach <l.stach@pengutronix.de>
Cc: <stable@vger.kernel.org>
Link: https://lore.kernel.org/r/20250129105841.1806-1-christian.koenig@amd.com
---
 drivers/dma-buf/dma-resv.c | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/drivers/dma-buf/dma-resv.c b/drivers/dma-buf/dma-resv.c
index b1ef4546346d..bea3e9858aca 100644
--- a/drivers/dma-buf/dma-resv.c
+++ b/drivers/dma-buf/dma-resv.c
@@ -685,11 +685,13 @@ long dma_resv_wait_timeout(struct dma_resv *obj, enum dma_resv_usage usage,
 	dma_resv_iter_begin(&cursor, obj, usage);
 	dma_resv_for_each_fence_unlocked(&cursor, fence) {
 
-		ret = dma_fence_wait_timeout(fence, intr, ret);
-		if (ret <= 0) {
-			dma_resv_iter_end(&cursor);
-			return ret;
-		}
+		ret = dma_fence_wait_timeout(fence, intr, timeout);
+		if (ret <= 0)
+			break;
+
+		/* Even for zero timeout the return value is 1 */
+		if (timeout)
+			timeout = ret;
 	}
 	dma_resv_iter_end(&cursor);
 

From 97e000acf2e20a86a50a0ec8c2739f0846f37509 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Christian=20K=C3=B6nig?= <christian.koenig@amd.com>
Date: Fri, 13 Jun 2025 13:16:38 +0200
Subject: [PATCH 1027/1334] drm/ttm: fix error handling in
 ttm_buffer_object_transfer
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Unlocking the resv object was missing in the error path, additionally to
that we should move over the resource only after the fence slot was
reserved.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Fixes: c8d4c18bfbc4a ("dma-buf/drivers: make reserving a shared slot mandatory v4")
Cc: <stable@vger.kernel.org>
Link: https://lore.kernel.org/r/20250616130726.22863-3-christian.koenig@amd.com
---
 drivers/gpu/drm/ttm/ttm_bo_util.c | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c
index 15cab9bda17f..bd90404ea609 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_util.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_util.c
@@ -254,6 +254,13 @@ static int ttm_buffer_object_transfer(struct ttm_buffer_object *bo,
 	ret = dma_resv_trylock(&fbo->base.base._resv);
 	WARN_ON(!ret);
 
+	ret = dma_resv_reserve_fences(&fbo->base.base._resv, 1);
+	if (ret) {
+		dma_resv_unlock(&fbo->base.base._resv);
+		kfree(fbo);
+		return ret;
+	}
+
 	if (fbo->base.resource) {
 		ttm_resource_set_bo(fbo->base.resource, &fbo->base);
 		bo->resource = NULL;
@@ -262,12 +269,6 @@ static int ttm_buffer_object_transfer(struct ttm_buffer_object *bo,
 		fbo->base.bulk_move = NULL;
 	}
 
-	ret = dma_resv_reserve_fences(&fbo->base.base._resv, 1);
-	if (ret) {
-		kfree(fbo);
-		return ret;
-	}
-
 	ttm_bo_get(bo);
 	fbo->bo = bo;
 

From 9e9b46672b1daac814b384286c21fb8332a87392 Mon Sep 17 00:00:00 2001
From: Youling Tang <tangyouling@kylinos.cn>
Date: Mon, 30 Jun 2025 09:11:48 +0800
Subject: [PATCH 1028/1334] xfs: add FALLOC_FL_ALLOCATE_RANGE to supported
 flags mask

Add FALLOC_FL_ALLOCATE_RANGE to the set of supported fallocate flags in
XFS_FALLOC_FL_SUPPORTED. This change improves code clarity and maintains
by explicitly showing this flag in the supported flags mask.

Note that since FALLOC_FL_ALLOCATE_RANGE is defined as 0x00, this addition
has no functional modifications.

Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>
Signed-off-by: Youling Tang <tangyouling@kylinos.cn>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 fs/xfs/xfs_file.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 48254a72071b..0b41b18debf3 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -1335,9 +1335,10 @@ xfs_falloc_allocate_range(
 }
 
 #define	XFS_FALLOC_FL_SUPPORTED						\
-		(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE |		\
-		 FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_ZERO_RANGE |	\
-		 FALLOC_FL_INSERT_RANGE | FALLOC_FL_UNSHARE_RANGE)
+		(FALLOC_FL_ALLOCATE_RANGE | FALLOC_FL_KEEP_SIZE |	\
+		 FALLOC_FL_PUNCH_HOLE |	FALLOC_FL_COLLAPSE_RANGE |	\
+		 FALLOC_FL_ZERO_RANGE |	FALLOC_FL_INSERT_RANGE |	\
+		 FALLOC_FL_UNSHARE_RANGE)
 
 STATIC long
 __xfs_file_fallocate(

From 1fe44a86ff0ff483aa1f1332f2b08f431fa51ce8 Mon Sep 17 00:00:00 2001
From: Lachlan Hodges <lachlan.hodges@morsemicro.com>
Date: Thu, 26 Jun 2025 21:51:18 +1000
Subject: [PATCH 1029/1334] wifi: cfg80211: fix S1G beacon head validation in
 nl80211

S1G beacons contain fixed length optional fields that precede the
variable length elements, ensure we take this into account when
validating the beacon. This particular case was missed in
1e1f706fc2ce ("wifi: cfg80211/mac80211: correctly parse S1G
beacon optional elements").

Fixes: 1d47f1198d58 ("nl80211: correctly validate S1G beacon head")
Signed-off-by: Lachlan Hodges <lachlan.hodges@morsemicro.com>
Link: https://patch.msgid.link/20250626115118.68660-1-lachlan.hodges@morsemicro.com
[shorten/reword subject]
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/wireless/nl80211.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 85f139016da2..50202d170f3a 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -229,6 +229,7 @@ static int validate_beacon_head(const struct nlattr *attr,
 	unsigned int len = nla_len(attr);
 	const struct element *elem;
 	const struct ieee80211_mgmt *mgmt = (void *)data;
+	const struct ieee80211_ext *ext;
 	unsigned int fixedlen, hdrlen;
 	bool s1g_bcn;
 
@@ -237,8 +238,10 @@ static int validate_beacon_head(const struct nlattr *attr,
 
 	s1g_bcn = ieee80211_is_s1g_beacon(mgmt->frame_control);
 	if (s1g_bcn) {
-		fixedlen = offsetof(struct ieee80211_ext,
-				    u.s1g_beacon.variable);
+		ext = (struct ieee80211_ext *)mgmt;
+		fixedlen =
+			offsetof(struct ieee80211_ext, u.s1g_beacon.variable) +
+			ieee80211_s1g_optional_len(ext->frame_control);
 		hdrlen = offsetof(struct ieee80211_ext, u.s1g_beacon);
 	} else {
 		fixedlen = offsetof(struct ieee80211_mgmt,

From 74b1ec9f5d627d2bdd5e5b6f3f81c23317657023 Mon Sep 17 00:00:00 2001
From: Daniil Dulov <d.dulov@aladdin.ru>
Date: Thu, 26 Jun 2025 14:46:19 +0300
Subject: [PATCH 1030/1334] wifi: zd1211rw: Fix potential NULL pointer
 dereference in zd_mac_tx_to_dev()

There is a potential NULL pointer dereference in zd_mac_tx_to_dev(). For
example, the following is possible:

    	T0			    		T1
zd_mac_tx_to_dev()
  /* len == skb_queue_len(q) */
  while (len > ZD_MAC_MAX_ACK_WAITERS) {

					  filter_ack()
					    spin_lock_irqsave(&q->lock, flags);
					    /* position == skb_queue_len(q) */
					    for (i=1; i<position; i++)
				    	      skb = __skb_dequeue(q)

					    if (mac->type == NL80211_IFTYPE_AP)
					      skb = __skb_dequeue(q);
					    spin_unlock_irqrestore(&q->lock, flags);

    skb_dequeue() -> NULL

Since there is a small gap between checking skb queue length and skb being
unconditionally dequeued in zd_mac_tx_to_dev(), skb_dequeue() can return NULL.
Then the pointer is passed to zd_mac_tx_status() where it is dereferenced.

In order to avoid potential NULL pointer dereference due to situations like
above, check if skb is not NULL before passing it to zd_mac_tx_status().

Found by Linux Verification Center (linuxtesting.org) with SVACE.

Fixes: 459c51ad6e1f ("zd1211rw: port to mac80211")
Signed-off-by: Daniil Dulov <d.dulov@aladdin.ru>
Link: https://patch.msgid.link/20250626114619.172631-1-d.dulov@aladdin.ru
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/zydas/zd1211rw/zd_mac.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/zydas/zd1211rw/zd_mac.c b/drivers/net/wireless/zydas/zd1211rw/zd_mac.c
index 9653dbaac3c0..781510a3ec6d 100644
--- a/drivers/net/wireless/zydas/zd1211rw/zd_mac.c
+++ b/drivers/net/wireless/zydas/zd1211rw/zd_mac.c
@@ -583,7 +583,11 @@ void zd_mac_tx_to_dev(struct sk_buff *skb, int error)
 
 		skb_queue_tail(q, skb);
 		while (skb_queue_len(q) > ZD_MAC_MAX_ACK_WAITERS) {
-			zd_mac_tx_status(hw, skb_dequeue(q),
+			skb = skb_dequeue(q);
+			if (!skb)
+				break;
+
+			zd_mac_tx_status(hw, skb,
 					 mac->ack_pending ? mac->ack_signal : 0,
 					 NULL);
 			mac->ack_pending = 0;

From 9bd9c8026341f75f25c53104eb7e656e357ca1a2 Mon Sep 17 00:00:00 2001
From: Mathias Nyman <mathias.nyman@linux.intel.com>
Date: Fri, 27 Jun 2025 19:43:48 +0300
Subject: [PATCH 1031/1334] usb: hub: Fix flushing of delayed work used for
 post resume purposes

Delayed work that prevents USB3 hubs from runtime-suspending too early
needed to be flushed in hub_quiesce() to resolve issues detected on
QC SC8280XP CRD board during suspend resume testing.

This flushing did however trigger new issues on Raspberry Pi 3B+, which
doesn't have USB3 ports, and doesn't queue any post resume delayed work.

The flushed 'hub->init_work' item is used for several purposes, and
is originally initialized with a 'NULL' work function. The work function
is also changed on the fly, which may contribute to the issue.

Solve this by creating a dedicated delayed work item for post resume work,
and flush that delayed work in hub_quiesce()

Cc: stable <stable@kernel.org>
Fixes: a49e1e2e785f ("usb: hub: Fix flushing and scheduling of delayed work that tunes runtime pm")
Reported-by: Mark Brown <broonie@kernel.org>
Closes: https://lore.kernel.org/linux-usb/aF5rNp1l0LWITnEB@finisterre.sirena.org.uk
Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Tested-by: Konrad Dybcio <konrad.dybcio@oss.qualcomm.com> # SC8280XP CRD
Tested-by: Mark Brown <broonie@kernel.org>
Link: https://lore.kernel.org/r/20250627164348.3982628-2-mathias.nyman@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/core/hub.c | 21 ++++++++-------------
 drivers/usb/core/hub.h |  1 +
 2 files changed, 9 insertions(+), 13 deletions(-)

diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c
index 08562711dcf2..3e1215f7a9a0 100644
--- a/drivers/usb/core/hub.c
+++ b/drivers/usb/core/hub.c
@@ -1074,12 +1074,11 @@ int usb_remove_device(struct usb_device *udev)
 
 enum hub_activation_type {
 	HUB_INIT, HUB_INIT2, HUB_INIT3,		/* INITs must come first */
-	HUB_POST_RESET, HUB_RESUME, HUB_RESET_RESUME, HUB_POST_RESUME,
+	HUB_POST_RESET, HUB_RESUME, HUB_RESET_RESUME,
 };
 
 static void hub_init_func2(struct work_struct *ws);
 static void hub_init_func3(struct work_struct *ws);
-static void hub_post_resume(struct work_struct *ws);
 
 static void hub_activate(struct usb_hub *hub, enum hub_activation_type type)
 {
@@ -1103,12 +1102,6 @@ static void hub_activate(struct usb_hub *hub, enum hub_activation_type type)
 		goto init3;
 	}
 
-	if (type == HUB_POST_RESUME) {
-		usb_autopm_put_interface_async(to_usb_interface(hub->intfdev));
-		hub_put(hub);
-		return;
-	}
-
 	hub_get(hub);
 
 	/* The superspeed hub except for root hub has to use Hub Depth
@@ -1362,8 +1355,8 @@ static void hub_activate(struct usb_hub *hub, enum hub_activation_type type)
 		usb_autopm_get_interface_no_resume(
 			to_usb_interface(hub->intfdev));
 
-		INIT_DELAYED_WORK(&hub->init_work, hub_post_resume);
-		queue_delayed_work(system_power_efficient_wq, &hub->init_work,
+		queue_delayed_work(system_power_efficient_wq,
+				   &hub->post_resume_work,
 				   msecs_to_jiffies(USB_SS_PORT_U0_WAKE_TIME));
 		return;
 	}
@@ -1388,9 +1381,10 @@ static void hub_init_func3(struct work_struct *ws)
 
 static void hub_post_resume(struct work_struct *ws)
 {
-	struct usb_hub *hub = container_of(ws, struct usb_hub, init_work.work);
+	struct usb_hub *hub = container_of(ws, struct usb_hub, post_resume_work.work);
 
-	hub_activate(hub, HUB_POST_RESUME);
+	usb_autopm_put_interface_async(to_usb_interface(hub->intfdev));
+	hub_put(hub);
 }
 
 enum hub_quiescing_type {
@@ -1418,7 +1412,7 @@ static void hub_quiesce(struct usb_hub *hub, enum hub_quiescing_type type)
 
 	/* Stop hub_wq and related activity */
 	timer_delete_sync(&hub->irq_urb_retry);
-	flush_delayed_work(&hub->init_work);
+	flush_delayed_work(&hub->post_resume_work);
 	usb_kill_urb(hub->urb);
 	if (hub->has_indicators)
 		cancel_delayed_work_sync(&hub->leds);
@@ -1977,6 +1971,7 @@ static int hub_probe(struct usb_interface *intf, const struct usb_device_id *id)
 	hub->hdev = hdev;
 	INIT_DELAYED_WORK(&hub->leds, led_work);
 	INIT_DELAYED_WORK(&hub->init_work, NULL);
+	INIT_DELAYED_WORK(&hub->post_resume_work, hub_post_resume);
 	INIT_WORK(&hub->events, hub_event);
 	INIT_LIST_HEAD(&hub->onboard_devs);
 	spin_lock_init(&hub->irq_urb_lock);
diff --git a/drivers/usb/core/hub.h b/drivers/usb/core/hub.h
index e6ae73f8a95d..9ebc5ef54a32 100644
--- a/drivers/usb/core/hub.h
+++ b/drivers/usb/core/hub.h
@@ -70,6 +70,7 @@ struct usb_hub {
 	u8			indicator[USB_MAXCHILDREN];
 	struct delayed_work	leds;
 	struct delayed_work	init_work;
+	struct delayed_work	post_resume_work;
 	struct work_struct      events;
 	spinlock_t		irq_urb_lock;
 	struct timer_list	irq_urb_retry;

From eb2c93e7028b4c9fe4761734d65ee40712d1c242 Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Mon, 30 Jun 2025 12:26:14 +0200
Subject: [PATCH 1032/1334] irqchip/irq-msi-lib: Select CONFIG_GENERIC_MSI_IRQ

irq-msi-lib directly uses struct msi_domain_info and more things which are
only available when CONFIG_GENERIC_MSI_IRQ=y.

However, there is no dependency specified and CONFIG_IRQ_MSI_LIB can be
enabled without CONFIG_GENERIC_MSI_IRQ, which causes the kernel build fail.

Make IRQ_MSI_LIB select GENEREIC_MSI_IRQ to prevent that.

Fixes: 72e257c6f058 ("irqchip: Provide irq-msi-lib")
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/b0c44007f3b7e062228349a2395f8d850050db33.1751277765.git.namcao@linutronix.de
Closes: https://lore.kernel.org/oe-kbuild-all/202506282256.cHlEHrdc-lkp@intel.com/
---
 drivers/irqchip/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/irqchip/Kconfig b/drivers/irqchip/Kconfig
index 0d196e447142..c3928ef79344 100644
--- a/drivers/irqchip/Kconfig
+++ b/drivers/irqchip/Kconfig
@@ -74,6 +74,7 @@ config ARM_VIC_NR
 
 config IRQ_MSI_LIB
 	bool
+	select GENERIC_MSI_IRQ
 
 config ARMADA_370_XP_IRQ
 	bool

From f172ffde18997aa401a74153cea4ae3bfdcb5124 Mon Sep 17 00:00:00 2001
From: Jisheng Zhang <jszhang@kernel.org>
Date: Sun, 29 Jun 2025 17:59:05 +0800
Subject: [PATCH 1033/1334] regulator: sy8824x: Fix ID table driver_data

Currently, the driver_data of the i2c ID table is wrong, so it won't
work if any sy8824x user makes use of the ID table. Fortunately, there's
no such user in upstream source code, we can fix the issue by using
different ID table entry for sy8824c, sy8824e, sy20276 and sy20278.

Signed-off-by: Jisheng Zhang <jszhang@kernel.org>
Link: https://patch.msgid.link/20250629095905.898-1-jszhang@kernel.org
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/regulator/sy8824x.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/regulator/sy8824x.c b/drivers/regulator/sy8824x.c
index c05b67e26ac8..5bec84db25f1 100644
--- a/drivers/regulator/sy8824x.c
+++ b/drivers/regulator/sy8824x.c
@@ -213,7 +213,10 @@ static const struct of_device_id sy8824_dt_ids[] = {
 MODULE_DEVICE_TABLE(of, sy8824_dt_ids);
 
 static const struct i2c_device_id sy8824_id[] = {
-	{ "sy8824", (kernel_ulong_t)&sy8824c_cfg },
+	{ "sy8824c", (kernel_ulong_t)&sy8824c_cfg },
+	{ "sy8824e", (kernel_ulong_t)&sy8824e_cfg },
+	{ "sy20276", (kernel_ulong_t)&sy20276_cfg },
+	{ "sy20278", (kernel_ulong_t)&sy20278_cfg },
 	{ }
 };
 MODULE_DEVICE_TABLE(i2c, sy8824_id);

From 6729c134ccc0d37d865c342e466b90df29081f1a Mon Sep 17 00:00:00 2001
From: Jisheng Zhang <jszhang@kernel.org>
Date: Sun, 29 Jun 2025 17:59:18 +0800
Subject: [PATCH 1034/1334] regulator: mp886x: Fix ID table driver_data

Currently, the driver_data of the i2c ID table is wrong, so it won't
work if any mp886x user makes use of the ID table. Fortunately, there's
no such user in upstream source code, we can fix the issue by using
different ID table entry for mp8867 and mp8869.

Signed-off-by: Jisheng Zhang <jszhang@kernel.org>
Link: https://patch.msgid.link/20250629095918.912-1-jszhang@kernel.org
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/regulator/mp886x.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/regulator/mp886x.c b/drivers/regulator/mp886x.c
index 48dcee5287f3..9ad16b04c913 100644
--- a/drivers/regulator/mp886x.c
+++ b/drivers/regulator/mp886x.c
@@ -348,7 +348,8 @@ static const struct of_device_id mp886x_dt_ids[] = {
 MODULE_DEVICE_TABLE(of, mp886x_dt_ids);
 
 static const struct i2c_device_id mp886x_id[] = {
-	{ "mp886x", (kernel_ulong_t)&mp8869_ci },
+	{ "mp8867", (kernel_ulong_t)&mp8867_ci },
+	{ "mp8869", (kernel_ulong_t)&mp8869_ci },
 	{ },
 };
 MODULE_DEVICE_TABLE(i2c, mp886x_id);

From eb028cd884e1b0976ff8c5944ee6650fe3ed0a6c Mon Sep 17 00:00:00 2001
From: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Date: Thu, 20 Feb 2025 17:07:26 +0200
Subject: [PATCH 1035/1334] drm/bridge: panel: move prepare_prev_first handling
 to drm_panel_bridge_add_typed

The commit 5ea6b1702781 ("drm/panel: Add prepare_prev_first flag to
drm_panel") and commit 0974687a19c3 ("drm/bridge: panel: Set
pre_enable_prev_first from drmm_panel_bridge_add") added handling of
panel's prepare_prev_first to devm_panel_bridge_add() and
drmm_panel_bridge_add(). However if the driver calls
drm_panel_bridge_add_typed() directly, then the flag won't be handled
and thus the drm_bridge.pre_enable_prev_first will not be set.

Move prepare_prev_first handling to the drm_panel_bridge_add_typed() so
that there is no way to miss the flag.

Fixes: 5ea6b1702781 ("drm/panel: Add prepare_prev_first flag to drm_panel")
Fixes: 0974687a19c3 ("drm/bridge: panel: Set pre_enable_prev_first from drmm_panel_bridge_add")
Reported-by: Svyatoslav Ryhel <clamor95@gmail.com>
Closes: https://lore.kernel.org/dri-devel/CAPVz0n3YZass3Bns1m0XrFxtAC0DKbEPiW6vXimQx97G243sXw@mail.gmail.com/
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Reviewed-by: Neil Armstrong <neil.armstrong@linaro.org>
Signed-off-by: Neil Armstrong <neil.armstrong@linaro.org>
Link: https://lore.kernel.org/r/20250220-panel_prev_first-v1-1-b9e787825a1a@linaro.org
---
 drivers/gpu/drm/bridge/panel.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/bridge/panel.c b/drivers/gpu/drm/bridge/panel.c
index 79b009ab9396..29b0358a7b6d 100644
--- a/drivers/gpu/drm/bridge/panel.c
+++ b/drivers/gpu/drm/bridge/panel.c
@@ -299,6 +299,7 @@ struct drm_bridge *drm_panel_bridge_add_typed(struct drm_panel *panel,
 	panel_bridge->bridge.of_node = panel->dev->of_node;
 	panel_bridge->bridge.ops = DRM_BRIDGE_OP_MODES;
 	panel_bridge->bridge.type = connector_type;
+	panel_bridge->bridge.pre_enable_prev_first = panel->prepare_prev_first;
 
 	drm_bridge_add(&panel_bridge->bridge);
 
@@ -413,8 +414,6 @@ struct drm_bridge *devm_drm_panel_bridge_add_typed(struct device *dev,
 		return bridge;
 	}
 
-	bridge->pre_enable_prev_first = panel->prepare_prev_first;
-
 	*ptr = bridge;
 	devres_add(dev, ptr);
 
@@ -456,8 +455,6 @@ struct drm_bridge *drmm_panel_bridge_add(struct drm_device *drm,
 	if (ret)
 		return ERR_PTR(ret);
 
-	bridge->pre_enable_prev_first = panel->prepare_prev_first;
-
 	return bridge;
 }
 EXPORT_SYMBOL(drmm_panel_bridge_add);

From e8537cad824065b0425fb0429e762e14a08067c2 Mon Sep 17 00:00:00 2001
From: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
Date: Sun, 8 Jun 2025 18:52:04 +0300
Subject: [PATCH 1036/1334] drm/bridge: aux-hpd-bridge: fix assignment of the
 of_node

Perform fix similar to the one in the commit 85e444a68126 ("drm/bridge:
Fix assignment of the of_node of the parent to aux bridge").

The assignment of the of_node to the aux HPD bridge needs to mark the
of_node as reused, otherwise driver core will attempt to bind resources
like pinctrl, which is going to fail as corresponding pins are already
marked as used by the parent device.
Fix that by using the device_set_of_node_from_dev() helper instead of
assigning it directly.

Fixes: e560518a6c2e ("drm/bridge: implement generic DP HPD bridge")
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
Reviewed-by: Neil Armstrong <neil.armstrong@linaro.org>
Signed-off-by: Neil Armstrong <neil.armstrong@linaro.org>
Link: https://lore.kernel.org/r/20250608-fix-aud-hpd-bridge-v1-1-4641a6f8e381@oss.qualcomm.com
---
 drivers/gpu/drm/bridge/aux-hpd-bridge.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/bridge/aux-hpd-bridge.c b/drivers/gpu/drm/bridge/aux-hpd-bridge.c
index b3f588b71a7d..af6f79793407 100644
--- a/drivers/gpu/drm/bridge/aux-hpd-bridge.c
+++ b/drivers/gpu/drm/bridge/aux-hpd-bridge.c
@@ -64,10 +64,11 @@ struct auxiliary_device *devm_drm_dp_hpd_bridge_alloc(struct device *parent, str
 	adev->id = ret;
 	adev->name = "dp_hpd_bridge";
 	adev->dev.parent = parent;
-	adev->dev.of_node = of_node_get(parent->of_node);
 	adev->dev.release = drm_aux_hpd_bridge_release;
 	adev->dev.platform_data = of_node_get(np);
 
+	device_set_of_node_from_dev(&adev->dev, parent);
+
 	ret = auxiliary_device_init(adev);
 	if (ret) {
 		of_node_put(adev->dev.platform_data);

From 60f7f4afaf6d09c27971f30f5ab69a3aab78b28f Mon Sep 17 00:00:00 2001
From: Mark Bloch <mbloch@nvidia.com>
Date: Thu, 26 Jun 2025 18:42:52 -0700
Subject: [PATCH 1037/1334] MAINTAINERS: Add myself as mlx5 core and mlx5e
 co-maintainer

I have been working on mlx5 related code for several years,
contributing features, code reviews, and occasional maintainer tasks
when needed. This patch makes my maintainer role official.

Signed-off-by: Mark Bloch <mbloch@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Link: https://patch.msgid.link/20250627014252.1262592-1-saeed@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 MAINTAINERS | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index bb7e5f8c4455..5f499ab23d6e 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -15550,6 +15550,7 @@ F:	drivers/net/ethernet/mellanox/mlx4/en_*
 MELLANOX ETHERNET DRIVER (mlx5e)
 M:	Saeed Mahameed <saeedm@nvidia.com>
 M:	Tariq Toukan <tariqt@nvidia.com>
+M:	Mark Bloch <mbloch@nvidia.com>
 L:	netdev@vger.kernel.org
 S:	Maintained
 W:	https://www.nvidia.com/networking/
@@ -15619,6 +15620,7 @@ MELLANOX MLX5 core VPI driver
 M:	Saeed Mahameed <saeedm@nvidia.com>
 M:	Leon Romanovsky <leonro@nvidia.com>
 M:	Tariq Toukan <tariqt@nvidia.com>
+M:	Mark Bloch <mbloch@nvidia.com>
 L:	netdev@vger.kernel.org
 L:	linux-rdma@vger.kernel.org
 S:	Maintained

From a106b6a888caf478d5fd31d123ffa09558500772 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Mon, 30 Jun 2025 11:21:52 +0300
Subject: [PATCH 1038/1334] Input: alps - use scnprintf() to suppress
 truncation warning

The commit 76c968e75715 ("Input: alps - switch to use scnprintf() to suppress
truncation warning") converted one place in the driver while the other left
untouched. Convert the other place as well.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lore.kernel.org/r/20250630082245.1416796-1-andriy.shevchenko@linux.intel.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/mouse/alps.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/input/mouse/alps.c b/drivers/input/mouse/alps.c
index 01f270509f03..51056f77a8c9 100644
--- a/drivers/input/mouse/alps.c
+++ b/drivers/input/mouse/alps.c
@@ -3103,8 +3103,8 @@ int alps_init(struct psmouse *psmouse)
 			goto init_fail;
 		}
 
-		snprintf(priv->phys2, sizeof(priv->phys2), "%s/input1",
-			 psmouse->ps2dev.serio->phys);
+		scnprintf(priv->phys2, sizeof(priv->phys2), "%s/input1",
+			  psmouse->ps2dev.serio->phys);
 		dev2->phys = priv->phys2;
 
 		/*

From 643c0c9d0496c5727ca28cd841d069b5afee06cf Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Wed, 25 Jun 2025 12:18:05 +0100
Subject: [PATCH 1039/1334] PCI: apple: Add tracking of probed root ports

The apple driver relies on being able to directly find the matching root
port structure from the platform device that represents this port.

A previous hack stashed a pointer to the root port structure in the config
window private pointer, but that ended up relying on assumptions that break
other drivers.

Instead, bite the bullet and track the association as part of the driver
itself as a list of probed root ports.

Signed-off-by: Marc Zyngier <maz@kernel.org>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Link: https://patch.msgid.link/20250625111806.4153773-3-maz@kernel.org
---
 drivers/pci/controller/pcie-apple.c | 53 ++++++++++++++++++++++++++---
 1 file changed, 49 insertions(+), 4 deletions(-)

diff --git a/drivers/pci/controller/pcie-apple.c b/drivers/pci/controller/pcie-apple.c
index 77fe73976654..0380d300adca 100644
--- a/drivers/pci/controller/pcie-apple.c
+++ b/drivers/pci/controller/pcie-apple.c
@@ -187,6 +187,7 @@ struct apple_pcie {
 	const struct hw_info	*hw;
 	unsigned long		*bitmap;
 	struct list_head	ports;
+	struct list_head	entry;
 	struct completion	event;
 	struct irq_fwspec	fwspec;
 	u32			nvecs;
@@ -205,6 +206,9 @@ struct apple_pcie_port {
 	int			idx;
 };
 
+static LIST_HEAD(pcie_list);
+static DEFINE_MUTEX(pcie_list_lock);
+
 static void rmw_set(u32 set, void __iomem *addr)
 {
 	writel_relaxed(readl_relaxed(addr) | set, addr);
@@ -720,13 +724,45 @@ static int apple_msi_init(struct apple_pcie *pcie)
 	return 0;
 }
 
+static void apple_pcie_register(struct apple_pcie *pcie)
+{
+	guard(mutex)(&pcie_list_lock);
+
+	list_add_tail(&pcie->entry, &pcie_list);
+}
+
+static void apple_pcie_unregister(struct apple_pcie *pcie)
+{
+	guard(mutex)(&pcie_list_lock);
+
+	list_del(&pcie->entry);
+}
+
+static struct apple_pcie *apple_pcie_lookup(struct device *dev)
+{
+	struct apple_pcie *pcie;
+
+	guard(mutex)(&pcie_list_lock);
+
+	list_for_each_entry(pcie, &pcie_list, entry) {
+		if (pcie->dev == dev)
+			return pcie;
+	}
+
+	return NULL;
+}
+
 static struct apple_pcie_port *apple_pcie_get_port(struct pci_dev *pdev)
 {
 	struct pci_config_window *cfg = pdev->sysdata;
-	struct apple_pcie *pcie = cfg->priv;
+	struct apple_pcie *pcie;
 	struct pci_dev *port_pdev;
 	struct apple_pcie_port *port;
 
+	pcie = apple_pcie_lookup(cfg->parent);
+	if (WARN_ON(!pcie))
+		return NULL;
+
 	/* Find the root port this device is on */
 	port_pdev = pcie_find_root_port(pdev);
 
@@ -806,10 +842,14 @@ static void apple_pcie_disable_device(struct pci_host_bridge *bridge, struct pci
 
 static int apple_pcie_init(struct pci_config_window *cfg)
 {
-	struct apple_pcie *pcie = cfg->priv;
 	struct device *dev = cfg->parent;
+	struct apple_pcie *pcie;
 	int ret;
 
+	pcie = apple_pcie_lookup(dev);
+	if (WARN_ON(!pcie))
+		return -ENOENT;
+
 	for_each_available_child_of_node_scoped(dev->of_node, of_port) {
 		ret = apple_pcie_setup_port(pcie, of_port);
 		if (ret) {
@@ -852,13 +892,18 @@ static int apple_pcie_probe(struct platform_device *pdev)
 
 	mutex_init(&pcie->lock);
 	INIT_LIST_HEAD(&pcie->ports);
-	dev_set_drvdata(dev, pcie);
 
 	ret = apple_msi_init(pcie);
 	if (ret)
 		return ret;
 
-	return pci_host_common_init(pdev, &apple_pcie_cfg_ecam_ops);
+	apple_pcie_register(pcie);
+
+	ret = pci_host_common_init(pdev, &apple_pcie_cfg_ecam_ops);
+	if (ret)
+		apple_pcie_unregister(pcie);
+
+	return ret;
 }
 
 static const struct of_device_id apple_pcie_of_match[] = {

From bdb32a0f6780660512d2335db2ebe32e6582cdc8 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert+renesas@glider.be>
Date: Wed, 25 Jun 2025 12:18:04 +0100
Subject: [PATCH 1040/1334] PCI: host-generic: Set driver_data before calling
 gen_pci_init()

On MicroChip MPFS Icicle:

  microchip-pcie 2000000000.pcie: host bridge /soc/pcie@2000000000 ranges:
  microchip-pcie 2000000000.pcie: Parsing ranges property...
  microchip-pcie 2000000000.pcie:      MEM 0x2008000000..0x2087ffffff -> 0x0008000000
  Unable to handle kernel NULL pointer dereference at virtual address 0000000000000368
  Current swapper/0 pgtable: 4K pagesize, 39-bit VAs, pgdp=0x00000000814f1000
  [0000000000000368] pgd=0000000000000000, p4d=0000000000000000, pud=0000000000000000
  Oops [#1]
  Modules linked in:
  CPU: 0 UID: 0 PID: 1 Comm: swapper/0 Not tainted 6.15.0-rc1-icicle-00003-gafc0a570bb61 #232 NONE
  Hardware name: Microchip PolarFire-SoC Icicle Kit (DT)
  [...]
  [<ffffffff803fb8a4>] plda_pcie_setup_iomems+0xe/0x78
  [<ffffffff803fc246>] mc_platform_init+0x80/0x1d2
  [<ffffffff803f9c88>] pci_ecam_create+0x104/0x1e2
  [<ffffffff8000adbe>] pci_host_common_init+0x120/0x228
  [<ffffffff8000af42>] pci_host_common_probe+0x7c/0x8a

The initialization of driver_data was moved after the call to
gen_pci_init(), while the pci_ecam_ops.init() callback
mc_platform_init() expects it has already been initialized.

Fix this by moving the initialization of driver_data up.

Fixes: afc0a570bb613871 ("PCI: host-generic: Extract an ECAM bridge creation helper from pci_host_common_probe()")
Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Link: https://lore.kernel.org/r/774290708a6f0f683711914fda110742c18a7fb2.1750787223.git.geert+renesas@glider.be
Link: https://patch.msgid.link/20250625111806.4153773-2-maz@kernel.org
---
 drivers/pci/controller/pci-host-common.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/pci/controller/pci-host-common.c b/drivers/pci/controller/pci-host-common.c
index b0992325dd65..b37052863847 100644
--- a/drivers/pci/controller/pci-host-common.c
+++ b/drivers/pci/controller/pci-host-common.c
@@ -64,13 +64,13 @@ int pci_host_common_init(struct platform_device *pdev,
 
 	of_pci_check_probe_only();
 
+	platform_set_drvdata(pdev, bridge);
+
 	/* Parse and map our Configuration Space windows */
 	cfg = gen_pci_init(dev, bridge, ops);
 	if (IS_ERR(cfg))
 		return PTR_ERR(cfg);
 
-	platform_set_drvdata(pdev, bridge);
-
 	bridge->sysdata = cfg;
 	bridge->ops = (struct pci_ops *)&ops->pci_ops;
 	bridge->enable_device = ops->enable_device;

From ba74278c638df7c333a970a265dfcc258e70807b Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Wed, 25 Jun 2025 12:18:06 +0100
Subject: [PATCH 1041/1334] Revert "PCI: ecam: Allow cfg->priv to be
 pre-populated from the root port device"

This reverts commit 4900454b4f819e88e9c57ed93542bf9325d7e161.

Now that nobody relies of cfg->priv containing anything useful before the
.init() callback is used, restore the previous behaviour.

Signed-off-by: Marc Zyngier <maz@kernel.org>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Link: https://patch.msgid.link/20250625111806.4153773-4-maz@kernel.org
---
 drivers/pci/ecam.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/pci/ecam.c b/drivers/pci/ecam.c
index 2c5e6446e00e..260b7de2dbd5 100644
--- a/drivers/pci/ecam.c
+++ b/drivers/pci/ecam.c
@@ -84,8 +84,6 @@ struct pci_config_window *pci_ecam_create(struct device *dev,
 			goto err_exit_iomap;
 	}
 
-	cfg->priv = dev_get_drvdata(dev);
-
 	if (ops->init) {
 		err = ops->init(cfg);
 		if (err)

From 905967e359f0a3345dce096504e8c0390d0a8f49 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Mon, 16 Jun 2025 14:04:54 -0400
Subject: [PATCH 1042/1334] drm/amdgpu/sdma5.x: suspend KFD queues in ring
 reset

SDMA 5.x only supports engine soft reset which resets
all queues on the engine.  As such, we need to suspend
KFD queues around resets like we do for SDMA 4.x.

Reviewed-by: Jesse Zhang <Jesse.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 61feed0baa1a0d094af0e07e968b1e6e875f07d0)
---
 drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c | 7 ++++++-
 drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c | 7 ++++++-
 2 files changed, 12 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
index 1813c3ed0aa6..37f4b5b4a098 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
@@ -1543,8 +1543,13 @@ static int sdma_v5_0_reset_queue(struct amdgpu_ring *ring, unsigned int vmid)
 {
 	struct amdgpu_device *adev = ring->adev;
 	u32 inst_id = ring->me;
+	int r;
 
-	return amdgpu_sdma_reset_engine(adev, inst_id);
+	amdgpu_amdkfd_suspend(adev, true);
+	r = amdgpu_sdma_reset_engine(adev, inst_id);
+	amdgpu_amdkfd_resume(adev, true);
+
+	return r;
 }
 
 static int sdma_v5_0_stop_queue(struct amdgpu_ring *ring)
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
index 23f97da62808..0b40411b92a0 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
@@ -1456,8 +1456,13 @@ static int sdma_v5_2_reset_queue(struct amdgpu_ring *ring, unsigned int vmid)
 {
 	struct amdgpu_device *adev = ring->adev;
 	u32 inst_id = ring->me;
+	int r;
 
-	return amdgpu_sdma_reset_engine(adev, inst_id);
+	amdgpu_amdkfd_suspend(adev, true);
+	r = amdgpu_sdma_reset_engine(adev, inst_id);
+	amdgpu_amdkfd_resume(adev, true);
+
+	return r;
 }
 
 static int sdma_v5_2_stop_queue(struct amdgpu_ring *ring)

From 62461367f4c0dcf4fab9cafb4ab3a7d346788df6 Mon Sep 17 00:00:00 2001
From: David Yat Sin <David.YatSin@amd.com>
Date: Thu, 19 Jun 2025 17:51:13 +0000
Subject: [PATCH 1043/1334] amdkfd: MTYPE_UC for ext-coherent system memory

Set memory mtype to UC host memory when ext-coherent
flag is set and memory is registered as a SVM allocation.

Reviewed-by: Amber Lin <Amber.Lin@amd.com>
Signed-off-by: David Yat Sin <David.YatSin@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 5d14fdab4778c29cfd39e62c3ce84d232b4a7d8c)
---
 drivers/gpu/drm/amd/amdkfd/kfd_svm.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
index 865dca2547de..7763e4742080 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
@@ -1278,7 +1278,7 @@ svm_range_get_pte_flags(struct kfd_node *node,
 				mapping_flags |= ext_coherent ? AMDGPU_VM_MTYPE_UC : AMDGPU_VM_MTYPE_NC;
 		/* system memory accessed by the dGPU */
 		} else {
-			if (gc_ip_version < IP_VERSION(9, 5, 0))
+			if (gc_ip_version < IP_VERSION(9, 5, 0) || ext_coherent)
 				mapping_flags |= AMDGPU_VM_MTYPE_UC;
 			else
 				mapping_flags |= AMDGPU_VM_MTYPE_NC;

From e54c5de901ea56fc68f8d56b3cce9940169346f4 Mon Sep 17 00:00:00 2001
From: Kent Russell <kent.russell@amd.com>
Date: Tue, 24 Jun 2025 11:42:06 -0400
Subject: [PATCH 1044/1334] drm/amdgpu: Include sdma_4_4_4.bin

This got missed during SDMA 4.4.4 support.

Fixes: 968e3811c3e8 ("drm/amdgpu: add initial support for sdma444")
Signed-off-by: Kent Russell <kent.russell@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 51526efe02714339ed6139f7bc348377d363200a)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c
index cef68df4c663..bb82c652e4c0 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c
@@ -45,6 +45,7 @@
 #include "amdgpu_ras.h"
 
 MODULE_FIRMWARE("amdgpu/sdma_4_4_2.bin");
+MODULE_FIRMWARE("amdgpu/sdma_4_4_4.bin");
 MODULE_FIRMWARE("amdgpu/sdma_4_4_5.bin");
 
 static const struct amdgpu_hwip_reg_entry sdma_reg_list_4_4_2[] = {

From 3d30048958e0d43425f6d4e76565e6249fa71050 Mon Sep 17 00:00:00 2001
From: "Michael J. Ruhl" <michael.j.ruhl@intel.com>
Date: Fri, 27 Jun 2025 10:35:11 -0400
Subject: [PATCH 1045/1334] i2c/designware: Fix an initialization issue

The i2c_dw_xfer_init() function requires msgs and msg_write_idx from the
dev context to be initialized.

amd_i2c_dw_xfer_quirk() inits msgs and msgs_num, but not msg_write_idx.

This could allow an out of bounds access (of msgs).

Initialize msg_write_idx before calling i2c_dw_xfer_init().

Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Fixes: 17631e8ca2d3 ("i2c: designware: Add driver support for AMD NAVI GPU")
Cc: <stable@vger.kernel.org> # v5.13+
Signed-off-by: Michael J. Ruhl <michael.j.ruhl@intel.com>
Signed-off-by: Andi Shyti <andi.shyti@kernel.org>
Link: https://lore.kernel.org/r/20250627143511.489570-1-michael.j.ruhl@intel.com
---
 drivers/i2c/busses/i2c-designware-master.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/i2c/busses/i2c-designware-master.c b/drivers/i2c/busses/i2c-designware-master.c
index 9d7d9e47564a..cbd88ffa5610 100644
--- a/drivers/i2c/busses/i2c-designware-master.c
+++ b/drivers/i2c/busses/i2c-designware-master.c
@@ -363,6 +363,7 @@ static int amd_i2c_dw_xfer_quirk(struct i2c_adapter *adap, struct i2c_msg *msgs,
 
 	dev->msgs = msgs;
 	dev->msgs_num = num_msgs;
+	dev->msg_write_idx = 0;
 	i2c_dw_xfer_init(dev);
 
 	/* Initiate messages read/write transaction */

From cf234231fcbc7d391e2135b9518613218cc5347f Mon Sep 17 00:00:00 2001
From: Philip Yang <Philip.Yang@amd.com>
Date: Fri, 20 Jun 2025 18:32:32 -0400
Subject: [PATCH 1046/1334] drm/amdkfd: Don't call mmput from MMU notifier
 callback

If the process is exiting, the mmput inside mmu notifier callback from
compactd or fork or numa balancing could release the last reference
of mm struct to call exit_mmap and free_pgtable, this triggers deadlock
with below backtrace.

The deadlock will leak kfd process as mmu notifier release is not called
and cause VRAM leaking.

The fix is to take mm reference mmget_non_zero when adding prange to the
deferred list to pair with mmput in deferred list work.

If prange split and add into pchild list, the pchild work_item.mm is not
used, so remove the mm parameter from svm_range_unmap_split and
svm_range_add_child.

The backtrace of hung task:

 INFO: task python:348105 blocked for more than 64512 seconds.
 Call Trace:
  __schedule+0x1c3/0x550
  schedule+0x46/0xb0
  rwsem_down_write_slowpath+0x24b/0x4c0
  unlink_anon_vmas+0xb1/0x1c0
  free_pgtables+0xa9/0x130
  exit_mmap+0xbc/0x1a0
  mmput+0x5a/0x140
  svm_range_cpu_invalidate_pagetables+0x2b/0x40 [amdgpu]
  mn_itree_invalidate+0x72/0xc0
  __mmu_notifier_invalidate_range_start+0x48/0x60
  try_to_unmap_one+0x10fa/0x1400
  rmap_walk_anon+0x196/0x460
  try_to_unmap+0xbb/0x210
  migrate_page_unmap+0x54d/0x7e0
  migrate_pages_batch+0x1c3/0xae0
  migrate_pages_sync+0x98/0x240
  migrate_pages+0x25c/0x520
  compact_zone+0x29d/0x590
  compact_zone_order+0xb6/0xf0
  try_to_compact_pages+0xbe/0x220
  __alloc_pages_direct_compact+0x96/0x1a0
  __alloc_pages_slowpath+0x410/0x930
  __alloc_pages_nodemask+0x3a9/0x3e0
  do_huge_pmd_anonymous_page+0xd7/0x3e0
  __handle_mm_fault+0x5e3/0x5f0
  handle_mm_fault+0xf7/0x2e0
  hmm_vma_fault.isra.0+0x4d/0xa0
  walk_pmd_range.isra.0+0xa8/0x310
  walk_pud_range+0x167/0x240
  walk_pgd_range+0x55/0x100
  __walk_page_range+0x87/0x90
  walk_page_range+0xf6/0x160
  hmm_range_fault+0x4f/0x90
  amdgpu_hmm_range_get_pages+0x123/0x230 [amdgpu]
  amdgpu_ttm_tt_get_user_pages+0xb1/0x150 [amdgpu]
  init_user_pages+0xb1/0x2a0 [amdgpu]
  amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu+0x543/0x7d0 [amdgpu]
  kfd_ioctl_alloc_memory_of_gpu+0x24c/0x4e0 [amdgpu]
  kfd_ioctl+0x29d/0x500 [amdgpu]

Fixes: fa582c6f3684 ("drm/amdkfd: Use mmget_not_zero in MMU notifier")
Signed-off-by: Philip Yang <Philip.Yang@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit a29e067bd38946f752b0ef855f3dfff87e77bec7)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/amdkfd/kfd_svm.c | 43 +++++++++++++---------------
 1 file changed, 20 insertions(+), 23 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
index 7763e4742080..a0f22ea6d15a 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
@@ -1171,13 +1171,12 @@ svm_range_split_head(struct svm_range *prange, uint64_t new_start,
 }
 
 static void
-svm_range_add_child(struct svm_range *prange, struct mm_struct *mm,
-		    struct svm_range *pchild, enum svm_work_list_ops op)
+svm_range_add_child(struct svm_range *prange, struct svm_range *pchild, enum svm_work_list_ops op)
 {
 	pr_debug("add child 0x%p [0x%lx 0x%lx] to prange 0x%p child list %d\n",
 		 pchild, pchild->start, pchild->last, prange, op);
 
-	pchild->work_item.mm = mm;
+	pchild->work_item.mm = NULL;
 	pchild->work_item.op = op;
 	list_add_tail(&pchild->child_list, &prange->child_list);
 }
@@ -2394,15 +2393,17 @@ svm_range_add_list_work(struct svm_range_list *svms, struct svm_range *prange,
 		    prange->work_item.op != SVM_OP_UNMAP_RANGE)
 			prange->work_item.op = op;
 	} else {
-		prange->work_item.op = op;
-
-		/* Pairs with mmput in deferred_list_work */
-		mmget(mm);
-		prange->work_item.mm = mm;
-		list_add_tail(&prange->deferred_list,
-			      &prange->svms->deferred_range_list);
-		pr_debug("add prange 0x%p [0x%lx 0x%lx] to work list op %d\n",
-			 prange, prange->start, prange->last, op);
+		/* Pairs with mmput in deferred_list_work.
+		 * If process is exiting and mm is gone, don't update mmu notifier.
+		 */
+		if (mmget_not_zero(mm)) {
+			prange->work_item.mm = mm;
+			prange->work_item.op = op;
+			list_add_tail(&prange->deferred_list,
+				      &prange->svms->deferred_range_list);
+			pr_debug("add prange 0x%p [0x%lx 0x%lx] to work list op %d\n",
+				 prange, prange->start, prange->last, op);
+		}
 	}
 	spin_unlock(&svms->deferred_list_lock);
 }
@@ -2416,8 +2417,7 @@ void schedule_deferred_list_work(struct svm_range_list *svms)
 }
 
 static void
-svm_range_unmap_split(struct mm_struct *mm, struct svm_range *parent,
-		      struct svm_range *prange, unsigned long start,
+svm_range_unmap_split(struct svm_range *parent, struct svm_range *prange, unsigned long start,
 		      unsigned long last)
 {
 	struct svm_range *head;
@@ -2438,12 +2438,12 @@ svm_range_unmap_split(struct mm_struct *mm, struct svm_range *parent,
 		svm_range_split(tail, last + 1, tail->last, &head);
 
 	if (head != prange && tail != prange) {
-		svm_range_add_child(parent, mm, head, SVM_OP_UNMAP_RANGE);
-		svm_range_add_child(parent, mm, tail, SVM_OP_ADD_RANGE);
+		svm_range_add_child(parent, head, SVM_OP_UNMAP_RANGE);
+		svm_range_add_child(parent, tail, SVM_OP_ADD_RANGE);
 	} else if (tail != prange) {
-		svm_range_add_child(parent, mm, tail, SVM_OP_UNMAP_RANGE);
+		svm_range_add_child(parent, tail, SVM_OP_UNMAP_RANGE);
 	} else if (head != prange) {
-		svm_range_add_child(parent, mm, head, SVM_OP_UNMAP_RANGE);
+		svm_range_add_child(parent, head, SVM_OP_UNMAP_RANGE);
 	} else if (parent != prange) {
 		prange->work_item.op = SVM_OP_UNMAP_RANGE;
 	}
@@ -2520,14 +2520,14 @@ svm_range_unmap_from_cpu(struct mm_struct *mm, struct svm_range *prange,
 		l = min(last, pchild->last);
 		if (l >= s)
 			svm_range_unmap_from_gpus(pchild, s, l, trigger);
-		svm_range_unmap_split(mm, prange, pchild, start, last);
+		svm_range_unmap_split(prange, pchild, start, last);
 		mutex_unlock(&pchild->lock);
 	}
 	s = max(start, prange->start);
 	l = min(last, prange->last);
 	if (l >= s)
 		svm_range_unmap_from_gpus(prange, s, l, trigger);
-	svm_range_unmap_split(mm, prange, prange, start, last);
+	svm_range_unmap_split(prange, prange, start, last);
 
 	if (unmap_parent)
 		svm_range_add_list_work(svms, prange, mm, SVM_OP_UNMAP_RANGE);
@@ -2570,8 +2570,6 @@ svm_range_cpu_invalidate_pagetables(struct mmu_interval_notifier *mni,
 
 	if (range->event == MMU_NOTIFY_RELEASE)
 		return true;
-	if (!mmget_not_zero(mni->mm))
-		return true;
 
 	start = mni->interval_tree.start;
 	last = mni->interval_tree.last;
@@ -2598,7 +2596,6 @@ svm_range_cpu_invalidate_pagetables(struct mmu_interval_notifier *mni,
 	}
 
 	svm_range_unlock(prange);
-	mmput(mni->mm);
 
 	return true;
 }

From f3e58d8e154dae5015c7400812c80789589fc36e Mon Sep 17 00:00:00 2001
From: "Lin.Cao" <lincao12@amd.com>
Date: Tue, 24 Jun 2025 17:05:34 +0800
Subject: [PATCH 1047/1334] drm/amdgpu: Fix memory leak in
 amdgpu_ctx_mgr_entity_fini
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

patch dd64956685fa ("drm/amdgpu: Remove duplicated "context still
alive" check") removed ctx put, which will cause amdgpu_ctx_fini()
cannot be called and then cause some finished fence that added by
amdgpu_ctx_add_fence() cannot be released and cause memleak.

Fixes: dd64956685fa ("drm/amdgpu: Remove duplicated "context still alive" check")
Signed-off-by: Lin.Cao <lincao12@amd.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@igalia.com>
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 8cf66089e28108dedd47e6156a48489303cf525c)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
index 85567d0d9545..f5d5c45ddc0d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
@@ -944,6 +944,7 @@ static void amdgpu_ctx_mgr_entity_fini(struct amdgpu_ctx_mgr *mgr)
 				drm_sched_entity_fini(entity);
 			}
 		}
+		kref_put(&ctx->refcount, amdgpu_ctx_fini);
 	}
 }
 

From 34659c1a1f4fd4c148ab13e13b11fd64df01ffcd Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Wed, 25 Jun 2025 18:15:37 -0400
Subject: [PATCH 1048/1334] drm/amdkfd: add hqd_sdma_get_doorbell callbacks for
 gfx7/8

These were missed when support was added for other generations.
The callbacks are called unconditionally so we need to make
sure all generations have them.

Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/4304
Link: https://github.com/ROCm/ROCm/issues/4965
Fixes: bac38ca8c475 ("drm/amdkfd: implement per queue sdma reset for gfx 9.4+")
Cc: Jonathan Kim <jonathan.kim@amd.com>
Reported-by: Johl Brown <johlbrown@gmail.com>
Reviewed-by: Jonathan Kim <jonathan.kim@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 1e9d17a5dcf1242e9518e461d8e63ad35240e49e)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c | 8 ++++++++
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c | 8 ++++++++
 2 files changed, 16 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c
index ca4a6b82817f..df77558e03ef 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c
@@ -561,6 +561,13 @@ static uint32_t read_vmid_from_vmfault_reg(struct amdgpu_device *adev)
 	return REG_GET_FIELD(status, VM_CONTEXT1_PROTECTION_FAULT_STATUS, VMID);
 }
 
+static uint32_t kgd_hqd_sdma_get_doorbell(struct amdgpu_device *adev,
+					  int engine, int queue)
+
+{
+	return 0;
+}
+
 const struct kfd2kgd_calls gfx_v7_kfd2kgd = {
 	.program_sh_mem_settings = kgd_program_sh_mem_settings,
 	.set_pasid_vmid_mapping = kgd_set_pasid_vmid_mapping,
@@ -578,4 +585,5 @@ const struct kfd2kgd_calls gfx_v7_kfd2kgd = {
 	.set_scratch_backing_va = set_scratch_backing_va,
 	.set_vm_context_page_table_base = set_vm_context_page_table_base,
 	.read_vmid_from_vmfault_reg = read_vmid_from_vmfault_reg,
+	.hqd_sdma_get_doorbell = kgd_hqd_sdma_get_doorbell,
 };
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c
index 0f3e2944edd7..e68c0fa8d751 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c
@@ -582,6 +582,13 @@ static void set_vm_context_page_table_base(struct amdgpu_device *adev,
 			lower_32_bits(page_table_base));
 }
 
+static uint32_t kgd_hqd_sdma_get_doorbell(struct amdgpu_device *adev,
+					  int engine, int queue)
+
+{
+	return 0;
+}
+
 const struct kfd2kgd_calls gfx_v8_kfd2kgd = {
 	.program_sh_mem_settings = kgd_program_sh_mem_settings,
 	.set_pasid_vmid_mapping = kgd_set_pasid_vmid_mapping,
@@ -599,4 +606,5 @@ const struct kfd2kgd_calls gfx_v8_kfd2kgd = {
 			get_atc_vmid_pasid_mapping_info,
 	.set_scratch_backing_va = set_scratch_backing_va,
 	.set_vm_context_page_table_base = set_vm_context_page_table_base,
+	.hqd_sdma_get_doorbell = kgd_hqd_sdma_get_doorbell,
 };

From 84f2902bfcfe79e94adf5dfe9bf85ad334a4c63a Mon Sep 17 00:00:00 2001
From: Harold Sun <Harold.Sun@amd.com>
Date: Thu, 19 Jun 2025 14:52:54 -0400
Subject: [PATCH 1049/1334] drm/amd/display: Added case for when RR equals
 panel's max RR using freesync

[WHY]
Rounding error sometimes occurs when the refresh rate is equal to a panel's
max refresh rate, causing HDMI compliance failures.

[HOW]
Added a case so that we round up to avoid v_total_min to be below a panel's
minimum bound.

Reviewed-by: Jun Lei <jun.lei@amd.com>
Signed-off-by: Harold Sun <Harold.Sun@amd.com>
Signed-off-by: Ray Wu <ray.wu@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit fe7645d22bc0f7c1558296538ec49987bf268ef6)
---
 drivers/gpu/drm/amd/display/dc/dc_hw_types.h            | 1 +
 drivers/gpu/drm/amd/display/modules/freesync/freesync.c | 8 ++++++++
 2 files changed, 9 insertions(+)

diff --git a/drivers/gpu/drm/amd/display/dc/dc_hw_types.h b/drivers/gpu/drm/amd/display/dc/dc_hw_types.h
index d562ddeca512..c9f6c6275ca1 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_hw_types.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_hw_types.h
@@ -974,6 +974,7 @@ struct dc_crtc_timing {
 	uint32_t pix_clk_100hz;
 
 	uint32_t min_refresh_in_uhz;
+	uint32_t max_refresh_in_uhz;
 
 	uint32_t vic;
 	uint32_t hdmi_vic;
diff --git a/drivers/gpu/drm/amd/display/modules/freesync/freesync.c b/drivers/gpu/drm/amd/display/modules/freesync/freesync.c
index 3ba9b62ba70b..250f09922d2f 100644
--- a/drivers/gpu/drm/amd/display/modules/freesync/freesync.c
+++ b/drivers/gpu/drm/amd/display/modules/freesync/freesync.c
@@ -155,6 +155,14 @@ unsigned int mod_freesync_calc_v_total_from_refresh(
 		v_total = div64_u64(div64_u64(((unsigned long long)(
 				frame_duration_in_ns) * (stream->timing.pix_clk_100hz / 10)),
 				stream->timing.h_total), 1000000);
+	} else if (refresh_in_uhz >= stream->timing.max_refresh_in_uhz) {
+		/* When the target refresh rate is the maximum panel refresh rate
+		 * round up the vtotal value to prevent off-by-one error causing
+		 * v_total_min to be below the panel's lower bound
+		 */
+		v_total = div64_u64(div64_u64(((unsigned long long)(
+				frame_duration_in_ns) * (stream->timing.pix_clk_100hz / 10)),
+				stream->timing.h_total) + (1000000 - 1), 1000000);
 	} else {
 		v_total = div64_u64(div64_u64(((unsigned long long)(
 				frame_duration_in_ns) * (stream->timing.pix_clk_100hz / 10)),

From 39d81457ad3417a98ac826161f9ca0e642677661 Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Thu, 19 Jun 2025 09:29:13 -0500
Subject: [PATCH 1050/1334] drm/amd/display: Don't allow OLED to go down to
 fully off

[Why]
OLED panels can be fully off, but this behavior is unexpected.

[How]
Ensure that minimum luminance is at least 1.

Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/4338
Reviewed-by: Alex Hung <alex.hung@amd.com>
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Ray Wu <ray.wu@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 51496c7737d06a74b599d0aa7974c3d5a4b1162e)
---
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 0b8ac9edc070..f58fa5da7fe5 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -3610,13 +3610,15 @@ static void update_connector_ext_caps(struct amdgpu_dm_connector *aconnector)
 
 	luminance_range = &conn_base->display_info.luminance_range;
 
-	if (luminance_range->max_luminance) {
-		caps->aux_min_input_signal = luminance_range->min_luminance;
+	if (luminance_range->max_luminance)
 		caps->aux_max_input_signal = luminance_range->max_luminance;
-	} else {
-		caps->aux_min_input_signal = 0;
+	else
 		caps->aux_max_input_signal = 512;
-	}
+
+	if (luminance_range->min_luminance)
+		caps->aux_min_input_signal = luminance_range->min_luminance;
+	else
+		caps->aux_min_input_signal = 1;
 
 	min_input_signal_override = drm_get_panel_min_brightness_quirk(aconnector->drm_edid);
 	if (min_input_signal_override >= 0)

From 3bbe46716092d8ef6b0df4b956f585c5cd0fc78e Mon Sep 17 00:00:00 2001
From: Paulo Alcantara <pc@manguebit.org>
Date: Wed, 25 Jun 2025 00:00:17 -0300
Subject: [PATCH 1051/1334] smb: client: fix warning when reconnecting channel

When reconnecting a channel in smb2_reconnect_server(), a dummy tcon
is passed down to smb2_reconnect() with ->query_interface
uninitialized, so we can't call queue_delayed_work() on it.

Fix the following warning by ensuring that we're queueing the delayed
worker from correct tcon.

WARNING: CPU: 4 PID: 1126 at kernel/workqueue.c:2498 __queue_delayed_work+0x1d2/0x200
Modules linked in: cifs cifs_arc4 nls_ucs2_utils cifs_md4 [last unloaded: cifs]
CPU: 4 UID: 0 PID: 1126 Comm: kworker/4:0 Not tainted 6.16.0-rc3 #5 PREEMPT(voluntary)
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.3-4.fc42 04/01/2014
Workqueue: cifsiod smb2_reconnect_server [cifs]
RIP: 0010:__queue_delayed_work+0x1d2/0x200
Code: 41 5e 41 5f e9 7f ee ff ff 90 0f 0b 90 e9 5d ff ff ff bf 02 00
00 00 e8 6c f3 07 00 89 c3 eb bd 90 0f 0b 90 e9 57 f> 0b 90 e9 65 fe
ff ff 90 0f 0b 90 e9 72 fe ff ff 90 0f 0b 90 e9
RSP: 0018:ffffc900014afad8 EFLAGS: 00010003
RAX: 0000000000000000 RBX: ffff888124d99988 RCX: ffffffff81399cc1
RDX: dffffc0000000000 RSI: ffff888114326e00 RDI: ffff888124d999f0
RBP: 000000000000ea60 R08: 0000000000000001 R09: ffffed10249b3331
R10: ffff888124d9998f R11: 0000000000000004 R12: 0000000000000040
R13: ffff888114326e00 R14: ffff888124d999d8 R15: ffff888114939020
FS:  0000000000000000(0000) GS:ffff88829f7fe000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007ffe7a2b4038 CR3: 0000000120a6f000 CR4: 0000000000750ef0
PKRU: 55555554
Call Trace:
 <TASK>
 queue_delayed_work_on+0xb4/0xc0
 smb2_reconnect+0xb22/0xf50 [cifs]
 smb2_reconnect_server+0x413/0xd40 [cifs]
 ? __pfx_smb2_reconnect_server+0x10/0x10 [cifs]
 ? local_clock_noinstr+0xd/0xd0
 ? local_clock+0x15/0x30
 ? lock_release+0x29b/0x390
 process_one_work+0x4c5/0xa10
 ? __pfx_process_one_work+0x10/0x10
 ? __list_add_valid_or_report+0x37/0x120
 worker_thread+0x2f1/0x5a0
 ? __kthread_parkme+0xde/0x100
 ? __pfx_worker_thread+0x10/0x10
 kthread+0x1fe/0x380
 ? kthread+0x10f/0x380
 ? __pfx_kthread+0x10/0x10
 ? local_clock_noinstr+0xd/0xd0
 ? ret_from_fork+0x1b/0x1f0
 ? local_clock+0x15/0x30
 ? lock_release+0x29b/0x390
 ? rcu_is_watching+0x20/0x50
 ? __pfx_kthread+0x10/0x10
 ret_from_fork+0x15b/0x1f0
 ? __pfx_kthread+0x10/0x10
 ret_from_fork_asm+0x1a/0x30
 </TASK>
irq event stamp: 1116206
hardirqs last  enabled at (1116205): [<ffffffff8143af42>] __up_console_sem+0x52/0x60
hardirqs last disabled at (1116206): [<ffffffff81399f0e>] queue_delayed_work_on+0x6e/0xc0
softirqs last  enabled at (1116138): [<ffffffffc04562fd>] __smb_send_rqst+0x42d/0x950 [cifs]
softirqs last disabled at (1116136): [<ffffffff823d35e1>] release_sock+0x21/0xf0

Cc: linux-cifs@vger.kernel.org
Reported-by: David Howells <dhowells@redhat.com>
Fixes: 42ca547b13a2 ("cifs: do not disable interface polling on failure")
Reviewed-by: David Howells <dhowells@redhat.com>
Tested-by: David Howells <dhowells@redhat.com>
Reviewed-by: Shyam Prasad N <nspmangalore@gmail.com>
Signed-off-by: Paulo Alcantara (Red Hat) <pc@manguebit.org>
Signed-off-by: David Howells <dhowells@redhat.com>
Tested-by: Steve French <stfrench@microsoft.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/cifsglob.h |  1 +
 fs/smb/client/smb2pdu.c  | 10 ++++------
 2 files changed, 5 insertions(+), 6 deletions(-)

diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h
index 318a8405d475..fdd95e5100cd 100644
--- a/fs/smb/client/cifsglob.h
+++ b/fs/smb/client/cifsglob.h
@@ -1303,6 +1303,7 @@ struct cifs_tcon {
 	bool use_persistent:1; /* use persistent instead of durable handles */
 	bool no_lease:1;    /* Do not request leases on files or directories */
 	bool use_witness:1; /* use witness protocol */
+	bool dummy:1; /* dummy tcon used for reconnecting channels */
 	__le32 capabilities;
 	__u32 share_flags;
 	__u32 maximal_access;
diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c
index a717be1626a3..13e1362d6575 100644
--- a/fs/smb/client/smb2pdu.c
+++ b/fs/smb/client/smb2pdu.c
@@ -424,9 +424,9 @@ skip_sess_setup:
 		free_xid(xid);
 		ses->flags &= ~CIFS_SES_FLAGS_PENDING_QUERY_INTERFACES;
 
-		/* regardless of rc value, setup polling */
-		queue_delayed_work(cifsiod_wq, &tcon->query_interfaces,
-				   (SMB_INTERFACE_POLL_INTERVAL * HZ));
+		if (!tcon->ipc && !tcon->dummy)
+			queue_delayed_work(cifsiod_wq, &tcon->query_interfaces,
+					   (SMB_INTERFACE_POLL_INTERVAL * HZ));
 
 		mutex_unlock(&ses->session_mutex);
 
@@ -4229,10 +4229,8 @@ void smb2_reconnect_server(struct work_struct *work)
 		}
 		goto done;
 	}
-
 	tcon->status = TID_GOOD;
-	tcon->retry = false;
-	tcon->need_reconnect = false;
+	tcon->dummy = true;
 
 	/* now reconnect sessions for necessary channels */
 	list_for_each_entry_safe(ses, ses2, &tmp_ses_list, rlist) {

From 964209202ebe1569c858337441e87ef0f9d71416 Mon Sep 17 00:00:00 2001
From: Zhang Rui <rui.zhang@intel.com>
Date: Thu, 19 Jun 2025 15:13:40 +0800
Subject: [PATCH 1052/1334] powercap: intel_rapl: Do not change CLAMPING bit if
 ENABLE bit cannot be changed

PL1 cannot be disabled on some platforms. The ENABLE bit is still set
after software clears it. This behavior leads to a scenario where, upon
user request to disable the Power Limit through the powercap sysfs, the
ENABLE bit remains set while the CLAMPING bit is inadvertently cleared.

According to the Intel Software Developer's Manual, the CLAMPING bit,
"When set, allows the processor to go below the OS requested P states in
order to maintain the power below specified Platform Power Limit value."

Thus this means the system may operate at higher power levels than
intended on such platforms.

Enhance the code to check ENABLE bit after writing to it, and stop
further processing if ENABLE bit cannot be changed.

Reported-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Fixes: 2d281d8196e3 ("PowerCap: Introduce Intel RAPL power capping driver")
Cc: All applicable <stable@vger.kernel.org>
Signed-off-by: Zhang Rui <rui.zhang@intel.com>
Link: https://patch.msgid.link/20250619071340.384782-1-rui.zhang@intel.com
[ rjw: Use str_enabled_disabled() instead of open-coded equivalent ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/powercap/intel_rapl_common.c | 18 +++++++++++++++++-
 1 file changed, 17 insertions(+), 1 deletion(-)

diff --git a/drivers/powercap/intel_rapl_common.c b/drivers/powercap/intel_rapl_common.c
index e3be40adc0d7..faa0b6bc5b53 100644
--- a/drivers/powercap/intel_rapl_common.c
+++ b/drivers/powercap/intel_rapl_common.c
@@ -341,12 +341,28 @@ static int set_domain_enable(struct powercap_zone *power_zone, bool mode)
 {
 	struct rapl_domain *rd = power_zone_to_rapl_domain(power_zone);
 	struct rapl_defaults *defaults = get_defaults(rd->rp);
+	u64 val;
 	int ret;
 
 	cpus_read_lock();
 	ret = rapl_write_pl_data(rd, POWER_LIMIT1, PL_ENABLE, mode);
-	if (!ret && defaults->set_floor_freq)
+	if (ret)
+		goto end;
+
+	ret = rapl_read_pl_data(rd, POWER_LIMIT1, PL_ENABLE, false, &val);
+	if (ret)
+		goto end;
+
+	if (mode != val) {
+		pr_debug("%s cannot be %s\n", power_zone->name,
+			 str_enabled_disabled(mode));
+		goto end;
+	}
+
+	if (defaults->set_floor_freq)
 		defaults->set_floor_freq(rd, mode);
+
+end:
 	cpus_read_unlock();
 
 	return ret;

From 74ebd02163fde05baa23129e06dde4b8f0f2377a Mon Sep 17 00:00:00 2001
From: Shyam Prasad N <sprasad@microsoft.com>
Date: Mon, 30 Jun 2025 23:09:34 +0530
Subject: [PATCH 1053/1334] cifs: all initializations for tcon should happen in
 tcon_info_alloc

Today, a few work structs inside tcon are initialized inside
cifs_get_tcon and not in tcon_info_alloc. As a result, if a tcon
is obtained from tcon_info_alloc, but not called as a part of
cifs_get_tcon, we may trip over.

Cc: <stable@vger.kernel.org>
Signed-off-by: Shyam Prasad N <sprasad@microsoft.com>
Reviewed-by: Paulo Alcantara (Red Hat) <pc@manguebit.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/cifsproto.h | 1 +
 fs/smb/client/connect.c   | 8 +-------
 fs/smb/client/misc.c      | 6 ++++++
 3 files changed, 8 insertions(+), 7 deletions(-)

diff --git a/fs/smb/client/cifsproto.h b/fs/smb/client/cifsproto.h
index 66093fa78aed..045227ed4efc 100644
--- a/fs/smb/client/cifsproto.h
+++ b/fs/smb/client/cifsproto.h
@@ -136,6 +136,7 @@ extern int SendReceiveBlockingLock(const unsigned int xid,
 			struct smb_hdr *out_buf,
 			int *bytes_returned);
 
+void smb2_query_server_interfaces(struct work_struct *work);
 void
 cifs_signal_cifsd_for_reconnect(struct TCP_Server_Info *server,
 				      bool all_channels);
diff --git a/fs/smb/client/connect.c b/fs/smb/client/connect.c
index 685c65dcb8c4..484b677143fd 100644
--- a/fs/smb/client/connect.c
+++ b/fs/smb/client/connect.c
@@ -97,7 +97,7 @@ static int reconn_set_ipaddr_from_hostname(struct TCP_Server_Info *server)
 	return rc;
 }
 
-static void smb2_query_server_interfaces(struct work_struct *work)
+void smb2_query_server_interfaces(struct work_struct *work)
 {
 	int rc;
 	int xid;
@@ -2880,20 +2880,14 @@ cifs_get_tcon(struct cifs_ses *ses, struct smb3_fs_context *ctx)
 	tcon->max_cached_dirs = ctx->max_cached_dirs;
 	tcon->nodelete = ctx->nodelete;
 	tcon->local_lease = ctx->local_lease;
-	INIT_LIST_HEAD(&tcon->pending_opens);
 	tcon->status = TID_GOOD;
 
-	INIT_DELAYED_WORK(&tcon->query_interfaces,
-			  smb2_query_server_interfaces);
 	if (ses->server->dialect >= SMB30_PROT_ID &&
 	    (ses->server->capabilities & SMB2_GLOBAL_CAP_MULTI_CHANNEL)) {
 		/* schedule query interfaces poll */
 		queue_delayed_work(cifsiod_wq, &tcon->query_interfaces,
 				   (SMB_INTERFACE_POLL_INTERVAL * HZ));
 	}
-#ifdef CONFIG_CIFS_DFS_UPCALL
-	INIT_DELAYED_WORK(&tcon->dfs_cache_work, dfs_cache_refresh);
-#endif
 	spin_lock(&cifs_tcp_ses_lock);
 	list_add(&tcon->tcon_list, &ses->tcon_list);
 	spin_unlock(&cifs_tcp_ses_lock);
diff --git a/fs/smb/client/misc.c b/fs/smb/client/misc.c
index e77017f47084..da23cc12a52c 100644
--- a/fs/smb/client/misc.c
+++ b/fs/smb/client/misc.c
@@ -151,6 +151,12 @@ tcon_info_alloc(bool dir_leases_enabled, enum smb3_tcon_ref_trace trace)
 #ifdef CONFIG_CIFS_DFS_UPCALL
 	INIT_LIST_HEAD(&ret_buf->dfs_ses_list);
 #endif
+	INIT_LIST_HEAD(&ret_buf->pending_opens);
+	INIT_DELAYED_WORK(&ret_buf->query_interfaces,
+			  smb2_query_server_interfaces);
+#ifdef CONFIG_CIFS_DFS_UPCALL
+	INIT_DELAYED_WORK(&ret_buf->dfs_cache_work, dfs_cache_refresh);
+#endif
 
 	return ret_buf;
 }

From fbf913cb72a52559ae98951fb4311b81d7b0650e Mon Sep 17 00:00:00 2001
From: Alan Huang <mmpgouride@gmail.com>
Date: Mon, 30 Jun 2025 20:36:33 +0800
Subject: [PATCH 1054/1334] bcachefs: Fix incorrect transaction restart
 handling

Reported-by: syzbot+cc7567f096079cb4146f@syzkaller.appspotmail.com
Signed-off-by: Alan Huang <mmpgouride@gmail.com>
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/fsck.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/bcachefs/fsck.c b/fs/bcachefs/fsck.c
index 9920f1affc5b..63093def85e3 100644
--- a/fs/bcachefs/fsck.c
+++ b/fs/bcachefs/fsck.c
@@ -2819,7 +2819,7 @@ static int check_path_loop(struct btree_trans *trans, struct bkey_s_c inode_k)
 				ret = remove_backpointer(trans, &inode);
 				bch_err_msg(c, ret, "removing dirent");
 				if (ret)
-					break;
+					goto out;
 
 				ret = reattach_inode(trans, &inode);
 				bch_err_msg(c, ret, "reattaching inode %llu", inode.bi_inum);

From 52e1a03e6cf61ae165f59f41c44394a653a0a788 Mon Sep 17 00:00:00 2001
From: Nikunj A Dadhania <nikunj@amd.com>
Date: Mon, 30 Jun 2025 13:48:58 +0530
Subject: [PATCH 1055/1334] x86/sev: Use TSC_FACTOR for Secure TSC frequency
 calculation

When using Secure TSC, the GUEST_TSC_FREQ MSR reports a frequency based on
the nominal P0 frequency, which deviates slightly (typically ~0.2%) from
the actual mean TSC frequency due to clocking parameters.

Over extended VM uptime, this discrepancy accumulates, causing clock skew
between the hypervisor and a SEV-SNP VM, leading to early timer interrupts as
perceived by the guest.

The guest kernel relies on the reported nominal frequency for TSC-based
timekeeping, while the actual frequency set during SNP_LAUNCH_START may
differ. This mismatch results in inaccurate time calculations, causing the
guest to perceive hrtimers as firing earlier than expected.

Utilize the TSC_FACTOR from the SEV firmware's secrets page (see "Secrets
Page Format" in the SNP Firmware ABI Specification) to calculate the mean
TSC frequency, ensuring accurate timekeeping and mitigating clock skew in
SEV-SNP VMs.

Use early_ioremap_encrypted() to map the secrets page as
ioremap_encrypted() uses kmalloc() which is not available during early TSC
initialization and causes a panic.

  [ bp: Drop the silly dummy var:
    https://lore.kernel.org/r/20250630192726.GBaGLlHl84xIopx4Pt@fat_crate.local ]

Fixes: 73bbf3b0fbba ("x86/tsc: Init the TSC for Secure TSC guests")
Signed-off-by: Nikunj A Dadhania <nikunj@amd.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/20250630081858.485187-1-nikunj@amd.com
---
 arch/x86/coco/sev/core.c   | 22 +++++++++++++++++++---
 arch/x86/include/asm/sev.h | 17 ++++++++++++++++-
 2 files changed, 35 insertions(+), 4 deletions(-)

diff --git a/arch/x86/coco/sev/core.c b/arch/x86/coco/sev/core.c
index b6db4e0b936b..7543a8b52c67 100644
--- a/arch/x86/coco/sev/core.c
+++ b/arch/x86/coco/sev/core.c
@@ -88,7 +88,7 @@ static const char * const sev_status_feat_names[] = {
  */
 static u64 snp_tsc_scale __ro_after_init;
 static u64 snp_tsc_offset __ro_after_init;
-static u64 snp_tsc_freq_khz __ro_after_init;
+static unsigned long snp_tsc_freq_khz __ro_after_init;
 
 DEFINE_PER_CPU(struct sev_es_runtime_data*, runtime_data);
 DEFINE_PER_CPU(struct sev_es_save_area *, sev_vmsa);
@@ -2167,15 +2167,31 @@ static unsigned long securetsc_get_tsc_khz(void)
 
 void __init snp_secure_tsc_init(void)
 {
-	unsigned long long tsc_freq_mhz;
+	struct snp_secrets_page *secrets;
+	unsigned long tsc_freq_mhz;
+	void *mem;
 
 	if (!cc_platform_has(CC_ATTR_GUEST_SNP_SECURE_TSC))
 		return;
 
+	mem = early_memremap_encrypted(sev_secrets_pa, PAGE_SIZE);
+	if (!mem) {
+		pr_err("Unable to get TSC_FACTOR: failed to map the SNP secrets page.\n");
+		sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_SECURE_TSC);
+	}
+
+	secrets = (__force struct snp_secrets_page *)mem;
+
 	setup_force_cpu_cap(X86_FEATURE_TSC_KNOWN_FREQ);
 	rdmsrq(MSR_AMD64_GUEST_TSC_FREQ, tsc_freq_mhz);
-	snp_tsc_freq_khz = (unsigned long)(tsc_freq_mhz * 1000);
+
+	/* Extract the GUEST TSC MHZ from BIT[17:0], rest is reserved space */
+	tsc_freq_mhz &= GENMASK_ULL(17, 0);
+
+	snp_tsc_freq_khz = SNP_SCALE_TSC_FREQ(tsc_freq_mhz * 1000, secrets->tsc_factor);
 
 	x86_platform.calibrate_cpu = securetsc_get_tsc_khz;
 	x86_platform.calibrate_tsc = securetsc_get_tsc_khz;
+
+	early_memunmap(mem, PAGE_SIZE);
 }
diff --git a/arch/x86/include/asm/sev.h b/arch/x86/include/asm/sev.h
index 58e028d42e41..a631f7d7c0c0 100644
--- a/arch/x86/include/asm/sev.h
+++ b/arch/x86/include/asm/sev.h
@@ -223,6 +223,18 @@ struct snp_tsc_info_resp {
 	u8 rsvd2[100];
 } __packed;
 
+/*
+ * Obtain the mean TSC frequency by decreasing the nominal TSC frequency with
+ * TSC_FACTOR as documented in the SNP Firmware ABI specification:
+ *
+ * GUEST_TSC_FREQ * (1 - (TSC_FACTOR * 0.00001))
+ *
+ * which is equivalent to:
+ *
+ * GUEST_TSC_FREQ -= (GUEST_TSC_FREQ * TSC_FACTOR) / 100000;
+ */
+#define SNP_SCALE_TSC_FREQ(freq, factor) ((freq) - (freq) * (factor) / 100000)
+
 struct snp_guest_req {
 	void *req_buf;
 	size_t req_sz;
@@ -282,8 +294,11 @@ struct snp_secrets_page {
 	u8 svsm_guest_vmpl;
 	u8 rsvd3[3];
 
+	/* The percentage decrease from nominal to mean TSC frequency. */
+	u32 tsc_factor;
+
 	/* Remainder of page */
-	u8 rsvd4[3744];
+	u8 rsvd4[3740];
 } __packed;
 
 struct snp_msg_desc {

From e39ed71c7a26e8e94c637e222bc373b511ca127f Mon Sep 17 00:00:00 2001
From: Jiawen Wu <jiawenwu@trustnetic.com>
Date: Thu, 26 Jun 2025 16:51:53 +0800
Subject: [PATCH 1056/1334] net: txgbe: fix the issue of TX failure

There is a occasional problem that ping is failed between AML devices.
That is because the manual enablement of the security Tx path on the
hardware is missing, no matter what its previous state was.

Fixes: 6f8b4c01a8cd ("net: txgbe: Implement PHYLINK for AML 25G/10G devices")
Signed-off-by: Jiawen Wu <jiawenwu@trustnetic.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/5BDFB14C57D1C42A+20250626085153.86122-1-jiawenwu@trustnetic.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/wangxun/txgbe/txgbe_aml.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_aml.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_aml.c
index 7dbcf41750c1..dc87ccad9652 100644
--- a/drivers/net/ethernet/wangxun/txgbe/txgbe_aml.c
+++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_aml.c
@@ -294,6 +294,7 @@ static void txgbe_mac_link_up_aml(struct phylink_config *config,
 	wx_fc_enable(wx, tx_pause, rx_pause);
 
 	txgbe_reconfig_mac(wx);
+	txgbe_enable_sec_tx_path(wx);
 
 	txcfg = rd32(wx, TXGBE_AML_MAC_TX_CFG);
 	txcfg &= ~TXGBE_AML_MAC_TX_CFG_SPEED_MASK;

From 6c7ffc9af7186ed79403a3ffee9a1e5199fc7450 Mon Sep 17 00:00:00 2001
From: Oleksij Rempel <o.rempel@pengutronix.de>
Date: Fri, 27 Jun 2025 07:13:46 +0200
Subject: [PATCH 1057/1334] net: usb: lan78xx: fix WARN in
 __netif_napi_del_locked on disconnect

Remove redundant netif_napi_del() call from disconnect path.

A WARN may be triggered in __netif_napi_del_locked() during USB device
disconnect:

  WARNING: CPU: 0 PID: 11 at net/core/dev.c:7417 __netif_napi_del_locked+0x2b4/0x350

This happens because netif_napi_del() is called in the disconnect path while
NAPI is still enabled. However, it is not necessary to call netif_napi_del()
explicitly, since unregister_netdev() will handle NAPI teardown automatically
and safely. Removing the redundant call avoids triggering the warning.

Full trace:
 lan78xx 1-1:1.0 enu1: Failed to read register index 0x000000c4. ret = -ENODEV
 lan78xx 1-1:1.0 enu1: Failed to set MAC down with error -ENODEV
 lan78xx 1-1:1.0 enu1: Link is Down
 lan78xx 1-1:1.0 enu1: Failed to read register index 0x00000120. ret = -ENODEV
 ------------[ cut here ]------------
 WARNING: CPU: 0 PID: 11 at net/core/dev.c:7417 __netif_napi_del_locked+0x2b4/0x350
 Modules linked in: flexcan can_dev fuse
 CPU: 0 UID: 0 PID: 11 Comm: kworker/0:1 Not tainted 6.16.0-rc2-00624-ge926949dab03 #9 PREEMPT
 Hardware name: SKOV IMX8MP CPU revC - bd500 (DT)
 Workqueue: usb_hub_wq hub_event
 pstate: 60000005 (nZCv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--)
 pc : __netif_napi_del_locked+0x2b4/0x350
 lr : __netif_napi_del_locked+0x7c/0x350
 sp : ffffffc085b673c0
 x29: ffffffc085b673c0 x28: ffffff800b7f2000 x27: ffffff800b7f20d8
 x26: ffffff80110bcf58 x25: ffffff80110bd978 x24: 1ffffff0022179eb
 x23: ffffff80110bc000 x22: ffffff800b7f5000 x21: ffffff80110bc000
 x20: ffffff80110bcf38 x19: ffffff80110bcf28 x18: dfffffc000000000
 x17: ffffffc081578940 x16: ffffffc08284cee0 x15: 0000000000000028
 x14: 0000000000000006 x13: 0000000000040000 x12: ffffffb0022179e8
 x11: 1ffffff0022179e7 x10: ffffffb0022179e7 x9 : dfffffc000000000
 x8 : 0000004ffdde8619 x7 : ffffff80110bcf3f x6 : 0000000000000001
 x5 : ffffff80110bcf38 x4 : ffffff80110bcf38 x3 : 0000000000000000
 x2 : 0000000000000000 x1 : 1ffffff0022179e7 x0 : 0000000000000000
 Call trace:
  __netif_napi_del_locked+0x2b4/0x350 (P)
  lan78xx_disconnect+0xf4/0x360
  usb_unbind_interface+0x158/0x718
  device_remove+0x100/0x150
  device_release_driver_internal+0x308/0x478
  device_release_driver+0x1c/0x30
  bus_remove_device+0x1a8/0x368
  device_del+0x2e0/0x7b0
  usb_disable_device+0x244/0x540
  usb_disconnect+0x220/0x758
  hub_event+0x105c/0x35e0
  process_one_work+0x760/0x17b0
  worker_thread+0x768/0xce8
  kthread+0x3bc/0x690
  ret_from_fork+0x10/0x20
 irq event stamp: 211604
 hardirqs last  enabled at (211603): [<ffffffc0828cc9ec>] _raw_spin_unlock_irqrestore+0x84/0x98
 hardirqs last disabled at (211604): [<ffffffc0828a9a84>] el1_dbg+0x24/0x80
 softirqs last  enabled at (211296): [<ffffffc080095f10>] handle_softirqs+0x820/0xbc8
 softirqs last disabled at (210993): [<ffffffc080010288>] __do_softirq+0x18/0x20
 ---[ end trace 0000000000000000 ]---
 lan78xx 1-1:1.0 enu1: failed to kill vid 0081/0

Fixes: ec4c7e12396b ("lan78xx: Introduce NAPI polling support")
Suggested-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Oleksij Rempel <o.rempel@pengutronix.de>
Link: https://patch.msgid.link/20250627051346.276029-1-o.rempel@pengutronix.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/usb/lan78xx.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c
index f53e255116ea..e3ca6e91efe1 100644
--- a/drivers/net/usb/lan78xx.c
+++ b/drivers/net/usb/lan78xx.c
@@ -4567,8 +4567,6 @@ static void lan78xx_disconnect(struct usb_interface *intf)
 	if (!dev)
 		return;
 
-	netif_napi_del(&dev->napi);
-
 	udev = interface_to_usbdev(intf);
 	net = dev->net;
 

From 3b2c45cb1b508014cee59cbabb1fc936f2f2dd3f Mon Sep 17 00:00:00 2001
From: Lukas Bulwahn <lukas.bulwahn@redhat.com>
Date: Fri, 27 Jun 2025 15:44:53 +0200
Subject: [PATCH 1058/1334] MAINTAINERS: adjust file entry after renaming
 rzv2h-gbeth dtb

Commit d53320aeef18 ("dt-bindings: net: Rename
renesas,r9a09g057-gbeth.yaml") renames the net devicetree binding
renesas,r9a09g057-gbeth.yaml to renesas,rzv2h-gbeth.yaml, but misses to
adjust the file entry in the RENESAS RZ/V2H(P) DWMAC GBETH GLUE LAYER
DRIVER section in MAINTAINERS.

Adjust the file entry after this file renaming.

Signed-off-by: Lukas Bulwahn <lukas.bulwahn@redhat.com>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
Link: https://patch.msgid.link/20250627134453.51780-1-lukas.bulwahn@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 MAINTAINERS | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 5f499ab23d6e..84c9e2dbe3f1 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -21178,7 +21178,7 @@ M:	Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
 L:	netdev@vger.kernel.org
 L:	linux-renesas-soc@vger.kernel.org
 S:	Maintained
-F:	Documentation/devicetree/bindings/net/renesas,r9a09g057-gbeth.yaml
+F:	Documentation/devicetree/bindings/net/renesas,rzv2h-gbeth.yaml
 F:	drivers/net/ethernet/stmicro/stmmac/dwmac-renesas-gbeth.c
 
 RENESAS RZ/V2H(P) USB2PHY PORT RESET DRIVER

From 7dfede7d7edd18c0c91ca854cde8eaaf4ccf97ea Mon Sep 17 00:00:00 2001
From: Marko Kiiskila <marko.kiiskila@broadcom.com>
Date: Wed, 18 Jun 2025 15:29:26 -0400
Subject: [PATCH 1059/1334] drm/vmwgfx: Fix guests running with TDX/SEV

Commit 81256a50aa0f ("x86/mm: Make memremap(MEMREMAP_WB) map memory as
encrypted by default") changed the default behavior of
memremap(MEMREMAP_WB) and started mapping memory as encrypted.
The driver requires the fifo memory to be decrypted to communicate with
the host but was relaying on the old default behavior of
memremap(MEMREMAP_WB) and thus broke.

Fix it by explicitly specifying the desired behavior and passing
MEMREMAP_DEC to memremap.

Fixes: 81256a50aa0f ("x86/mm: Make memremap(MEMREMAP_WB) map memory as encrypted by default")
Signed-off-by: Marko Kiiskila <marko.kiiskila@broadcom.com>
Signed-off-by: Zack Rusin <zack.rusin@broadcom.com>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: linux-mm@kvack.org
Cc: linux-kernel@vger.kernel.org
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Link: https://lore.kernel.org/r/20250618192926.1092450-1-zack.rusin@broadcom.com
---
 drivers/gpu/drm/vmwgfx/vmwgfx_drv.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
index 0695a342b1ef..5205552b1970 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
@@ -749,7 +749,7 @@ static int vmw_setup_pci_resources(struct vmw_private *dev,
 		dev->fifo_mem = devm_memremap(dev->drm.dev,
 					      fifo_start,
 					      fifo_size,
-					      MEMREMAP_WB);
+					      MEMREMAP_WB | MEMREMAP_DEC);
 
 		if (IS_ERR(dev->fifo_mem)) {
 			drm_err(&dev->drm,

From a5aa7bc1fca78c7fa127d9e33aa94a0c9066c1d6 Mon Sep 17 00:00:00 2001
From: Janusz Krzysztofik <janusz.krzysztofik@linux.intel.com>
Date: Wed, 11 Jun 2025 12:42:13 +0200
Subject: [PATCH 1060/1334] drm/i915/gt: Fix timeline left held on VMA alloc
 error

The following error has been reported sporadically by CI when a test
unbinds the i915 driver on a ring submission platform:

<4> [239.330153] ------------[ cut here ]------------
<4> [239.330166] i915 0000:00:02.0: [drm] drm_WARN_ON(dev_priv->mm.shrink_count)
<4> [239.330196] WARNING: CPU: 1 PID: 18570 at drivers/gpu/drm/i915/i915_gem.c:1309 i915_gem_cleanup_early+0x13e/0x150 [i915]
...
<4> [239.330640] RIP: 0010:i915_gem_cleanup_early+0x13e/0x150 [i915]
...
<4> [239.330942] Call Trace:
<4> [239.330944]  <TASK>
<4> [239.330949]  i915_driver_late_release+0x2b/0xa0 [i915]
<4> [239.331202]  i915_driver_release+0x86/0xa0 [i915]
<4> [239.331482]  devm_drm_dev_init_release+0x61/0x90
<4> [239.331494]  devm_action_release+0x15/0x30
<4> [239.331504]  release_nodes+0x3d/0x120
<4> [239.331517]  devres_release_all+0x96/0xd0
<4> [239.331533]  device_unbind_cleanup+0x12/0x80
<4> [239.331543]  device_release_driver_internal+0x23a/0x280
<4> [239.331550]  ? bus_find_device+0xa5/0xe0
<4> [239.331563]  device_driver_detach+0x14/0x20
...
<4> [357.719679] ---[ end trace 0000000000000000 ]---

If the test also unloads the i915 module then that's followed with:

<3> [357.787478] =============================================================================
<3> [357.788006] BUG i915_vma (Tainted: G     U  W        N ): Objects remaining on __kmem_cache_shutdown()
<3> [357.788031] -----------------------------------------------------------------------------
<3> [357.788204] Object 0xffff888109e7f480 @offset=29824
<3> [357.788670] Allocated in i915_vma_instance+0xee/0xc10 [i915] age=292729 cpu=4 pid=2244
<4> [357.788994]  i915_vma_instance+0xee/0xc10 [i915]
<4> [357.789290]  init_status_page+0x7b/0x420 [i915]
<4> [357.789532]  intel_engines_init+0x1d8/0x980 [i915]
<4> [357.789772]  intel_gt_init+0x175/0x450 [i915]
<4> [357.790014]  i915_gem_init+0x113/0x340 [i915]
<4> [357.790281]  i915_driver_probe+0x847/0xed0 [i915]
<4> [357.790504]  i915_pci_probe+0xe6/0x220 [i915]
...

Closer analysis of CI results history has revealed a dependency of the
error on a few IGT tests, namely:
- igt@api_intel_allocator@fork-simple-stress-signal,
- igt@api_intel_allocator@two-level-inception-interruptible,
- igt@gem_linear_blits@interruptible,
- igt@prime_mmap_coherency@ioctl-errors,
which invisibly trigger the issue, then exhibited with first driver unbind
attempt.

All of the above tests perform actions which are actively interrupted with
signals.  Further debugging has allowed to narrow that scope down to
DRM_IOCTL_I915_GEM_EXECBUFFER2, and ring_context_alloc(), specific to ring
submission, in particular.

If successful then that function, or its execlists or GuC submission
equivalent, is supposed to be called only once per GEM context engine,
followed by raise of a flag that prevents the function from being called
again.  The function is expected to unwind its internal errors itself, so
it may be safely called once more after it returns an error.

In case of ring submission, the function first gets a reference to the
engine's legacy timeline and then allocates a VMA.  If the VMA allocation
fails, e.g. when i915_vma_instance() called from inside is interrupted
with a signal, then ring_context_alloc() fails, leaving the timeline held
referenced.  On next I915_GEM_EXECBUFFER2 IOCTL, another reference to the
timeline is got, and only that last one is put on successful completion.
As a consequence, the legacy timeline, with its underlying engine status
page's VMA object, is still held and not released on driver unbind.

Get the legacy timeline only after successful allocation of the context
engine's VMA.

v2: Add a note on other submission methods (Krzysztof Karas):
    Both execlists and GuC submission use lrc_alloc() which seems free
    from a similar issue.

Fixes: 75d0a7f31eec ("drm/i915: Lift timeline into intel_context")
Closes: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/12061
Cc: Chris Wilson <chris.p.wilson@linux.intel.com>
Cc: Matthew Auld <matthew.auld@intel.com>
Cc: Krzysztof Karas <krzysztof.karas@intel.com>
Reviewed-by: Sebastian Brzezinka <sebastian.brzezinka@intel.com>
Reviewed-by: Krzysztof Niemiec <krzysztof.niemiec@intel.com>
Signed-off-by: Janusz Krzysztofik <janusz.krzysztofik@linux.intel.com>
Reviewed-by: Nitin Gote <nitin.r.gote@intel.com>
Reviewed-by: Andi Shyti <andi.shyti@linux.intel.com>
Signed-off-by: Andi Shyti <andi.shyti@linux.intel.com>
Link: https://lore.kernel.org/r/20250611104352.1014011-2-janusz.krzysztofik@linux.intel.com
(cherry picked from commit cc43422b3cc79eacff4c5a8ba0d224688ca9dd4f)
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
---
 drivers/gpu/drm/i915/gt/intel_ring_submission.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_ring_submission.c b/drivers/gpu/drm/i915/gt/intel_ring_submission.c
index a876a34455f1..2a6d79abf25b 100644
--- a/drivers/gpu/drm/i915/gt/intel_ring_submission.c
+++ b/drivers/gpu/drm/i915/gt/intel_ring_submission.c
@@ -610,7 +610,6 @@ static int ring_context_alloc(struct intel_context *ce)
 	/* One ringbuffer to rule them all */
 	GEM_BUG_ON(!engine->legacy.ring);
 	ce->ring = engine->legacy.ring;
-	ce->timeline = intel_timeline_get(engine->legacy.timeline);
 
 	GEM_BUG_ON(ce->state);
 	if (engine->context_size) {
@@ -623,6 +622,8 @@ static int ring_context_alloc(struct intel_context *ce)
 		ce->state = vma;
 	}
 
+	ce->timeline = intel_timeline_get(engine->legacy.timeline);
+
 	return 0;
 }
 

From 8cadce97bf264ed478669c6f32d5603b34608335 Mon Sep 17 00:00:00 2001
From: Junxiao Chang <junxiao.chang@intel.com>
Date: Fri, 25 Apr 2025 23:11:07 +0800
Subject: [PATCH 1061/1334] drm/i915/gsc: mei interrupt top half should be in
 irq disabled context

MEI GSC interrupt comes from i915. It has top half and bottom half.
Top half is called from i915 interrupt handler. It should be in
irq disabled context.

With RT kernel, by default i915 IRQ handler is in threaded IRQ. MEI GSC
top half might be in threaded IRQ context. generic_handle_irq_safe API
could be called from either IRQ or process context, it disables local
IRQ then calls MEI GSC interrupt top half.

This change fixes A380/A770 GPU boot hang issue with RT kernel.

Fixes: 1e3dc1d8622b ("drm/i915/gsc: add gsc as a mei auxiliary device")
Tested-by: Furong Zhou <furong.zhou@intel.com>
Suggested-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Acked-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Junxiao Chang <junxiao.chang@intel.com>
Link: https://lore.kernel.org/r/20250425151108.643649-1-junxiao.chang@intel.com
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
(cherry picked from commit dccf655f69002d496a527ba441b4f008aa5bebbf)
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
---
 drivers/gpu/drm/i915/gt/intel_gsc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_gsc.c b/drivers/gpu/drm/i915/gt/intel_gsc.c
index 1e925c75fb08..c43febc862dc 100644
--- a/drivers/gpu/drm/i915/gt/intel_gsc.c
+++ b/drivers/gpu/drm/i915/gt/intel_gsc.c
@@ -284,7 +284,7 @@ static void gsc_irq_handler(struct intel_gt *gt, unsigned int intf_id)
 	if (gt->gsc.intf[intf_id].irq < 0)
 		return;
 
-	ret = generic_handle_irq(gt->gsc.intf[intf_id].irq);
+	ret = generic_handle_irq_safe(gt->gsc.intf[intf_id].irq);
 	if (ret)
 		gt_err_ratelimited(gt, "error handling GSC irq: %d\n", ret);
 }

From d6811074203b13f715ce2480ac64c5b1c773f2a5 Mon Sep 17 00:00:00 2001
From: Geliang Tang <tanggeliang@kylinos.cn>
Date: Mon, 30 Jun 2025 15:48:32 +0800
Subject: [PATCH 1062/1334] nvme-multipath: fix suspicious RCU usage warning

When I run the NVME over TCP test in virtme-ng, I get the following
"suspicious RCU usage" warning in nvme_mpath_add_sysfs_link():

'''
[    5.024557][   T44] nvmet: Created nvm controller 1 for subsystem nqn.2025-06.org.nvmexpress.mptcp for NQN nqn.2014-08.org.nvmexpress:uuid:f7f6b5e0-ff97-4894-98ac-c85309e0bc77.
[    5.027401][  T183] nvme nvme0: creating 2 I/O queues.
[    5.029017][  T183] nvme nvme0: mapped 2/0/0 default/read/poll queues.
[    5.032587][  T183] nvme nvme0: new ctrl: NQN "nqn.2025-06.org.nvmexpress.mptcp", addr 127.0.0.1:4420, hostnqn: nqn.2014-08.org.nvmexpress:uuid:f7f6b5e0-ff97-4894-98ac-c85309e0bc77
[    5.042214][   T25]
[    5.042440][   T25] =============================
[    5.042579][   T25] WARNING: suspicious RCU usage
[    5.042705][   T25] 6.16.0-rc3+ #23 Not tainted
[    5.042812][   T25] -----------------------------
[    5.042934][   T25] drivers/nvme/host/multipath.c:1203 RCU-list traversed in non-reader section!!
[    5.043111][   T25]
[    5.043111][   T25] other info that might help us debug this:
[    5.043111][   T25]
[    5.043341][   T25]
[    5.043341][   T25] rcu_scheduler_active = 2, debug_locks = 1
[    5.043502][   T25] 3 locks held by kworker/u9:0/25:
[    5.043615][   T25]  #0: ffff888008730948 ((wq_completion)async){+.+.}-{0:0}, at: process_one_work+0x7ed/0x1350
[    5.043830][   T25]  #1: ffffc900001afd40 ((work_completion)(&entry->work)){+.+.}-{0:0}, at: process_one_work+0xcf3/0x1350
[    5.044084][   T25]  #2: ffff888013ee0020 (&head->srcu){.+.+}-{0:0}, at: nvme_mpath_add_sysfs_link.part.0+0xb4/0x3a0
[    5.044300][   T25]
[    5.044300][   T25] stack backtrace:
[    5.044439][   T25] CPU: 0 UID: 0 PID: 25 Comm: kworker/u9:0 Not tainted 6.16.0-rc3+ #23 PREEMPT(full)
[    5.044441][   T25] Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011
[    5.044442][   T25] Workqueue: async async_run_entry_fn
[    5.044445][   T25] Call Trace:
[    5.044446][   T25]  <TASK>
[    5.044449][   T25]  dump_stack_lvl+0x6f/0xb0
[    5.044453][   T25]  lockdep_rcu_suspicious.cold+0x4f/0xb1
[    5.044457][   T25]  nvme_mpath_add_sysfs_link.part.0+0x2fb/0x3a0
[    5.044459][   T25]  ? queue_work_on+0x90/0xf0
[    5.044461][   T25]  ? lockdep_hardirqs_on+0x78/0x110
[    5.044466][   T25]  nvme_mpath_set_live+0x1e9/0x4f0
[    5.044470][   T25]  nvme_mpath_add_disk+0x240/0x2f0
[    5.044472][   T25]  ? __pfx_nvme_mpath_add_disk+0x10/0x10
[    5.044475][   T25]  ? add_disk_fwnode+0x361/0x580
[    5.044480][   T25]  nvme_alloc_ns+0x81c/0x17c0
[    5.044483][   T25]  ? kasan_quarantine_put+0x104/0x240
[    5.044487][   T25]  ? __pfx_nvme_alloc_ns+0x10/0x10
[    5.044495][   T25]  ? __pfx_nvme_find_get_ns+0x10/0x10
[    5.044496][   T25]  ? rcu_read_lock_any_held+0x45/0xa0
[    5.044498][   T25]  ? validate_chain+0x232/0x4f0
[    5.044503][   T25]  nvme_scan_ns+0x4c8/0x810
[    5.044506][   T25]  ? __pfx_nvme_scan_ns+0x10/0x10
[    5.044508][   T25]  ? find_held_lock+0x2b/0x80
[    5.044512][   T25]  ? ktime_get+0x16d/0x220
[    5.044517][   T25]  ? kvm_clock_get_cycles+0x18/0x30
[    5.044520][   T25]  ? __pfx_nvme_scan_ns_async+0x10/0x10
[    5.044522][   T25]  async_run_entry_fn+0x97/0x560
[    5.044523][   T25]  ? rcu_is_watching+0x12/0xc0
[    5.044526][   T25]  process_one_work+0xd3c/0x1350
[    5.044532][   T25]  ? __pfx_process_one_work+0x10/0x10
[    5.044536][   T25]  ? assign_work+0x16c/0x240
[    5.044539][   T25]  worker_thread+0x4da/0xd50
[    5.044545][   T25]  ? __pfx_worker_thread+0x10/0x10
[    5.044546][   T25]  kthread+0x356/0x5c0
[    5.044548][   T25]  ? __pfx_kthread+0x10/0x10
[    5.044549][   T25]  ? ret_from_fork+0x1b/0x2e0
[    5.044552][   T25]  ? __lock_release.isra.0+0x5d/0x180
[    5.044553][   T25]  ? ret_from_fork+0x1b/0x2e0
[    5.044555][   T25]  ? rcu_is_watching+0x12/0xc0
[    5.044557][   T25]  ? __pfx_kthread+0x10/0x10
[    5.044559][   T25]  ret_from_fork+0x218/0x2e0
[    5.044561][   T25]  ? __pfx_kthread+0x10/0x10
[    5.044562][   T25]  ret_from_fork_asm+0x1a/0x30
[    5.044570][   T25]  </TASK>
'''

This patch uses sleepable RCU version of helper list_for_each_entry_srcu()
instead of list_for_each_entry_rcu() to fix it.

Fixes: 4dbd2b2ebe4c ("nvme-multipath: Add visibility for round-robin io-policy")
Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
Reviewed-by: Keith Busch <kbusch@kernel.org>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Nilay Shroff <nilay@linux.ibm.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/nvme/host/multipath.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index e03f3a29bd75..5d1ad28986e9 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -1200,7 +1200,8 @@ void nvme_mpath_add_sysfs_link(struct nvme_ns_head *head)
 	 */
 	srcu_idx = srcu_read_lock(&head->srcu);
 
-	list_for_each_entry_rcu(ns, &head->list, siblings) {
+	list_for_each_entry_srcu(ns, &head->list, siblings,
+				 srcu_read_lock_held(&head->srcu)) {
 		/*
 		 * Ensure that ns path disk node is already added otherwise we
 		 * may get invalid kobj name for target

From 3ebb1b6522392f64902b4e96954e35927354aa27 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= <thomas.weissschuh@linutronix.de>
Date: Thu, 26 Jun 2025 11:23:44 +0200
Subject: [PATCH 1063/1334] sched: Fix preemption string of
 preempt_dynamic_none
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Zero is a valid value for "preempt_dynamic_mode", namely
"preempt_dynamic_none".

Fix the off-by-one in preempt_model_str(), so that "preempty_dynamic_none"
is correctly formatted as PREEMPT(none) instead of PREEMPT(undef).

Fixes: 8bdc5daaa01e ("sched: Add a generic function to return the preemption string")
Signed-off-by: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Tested-by: Shrikanth Hegde <sshegde@linux.ibm.com>
Cc: stable@vger.kernel.org
Link: https://lkml.kernel.org/r/20250626-preempt-str-none-v2-1-526213b70a89@linutronix.de
---
 kernel/sched/core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 8988d38d46a3..cd80b66a960a 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -7663,7 +7663,7 @@ const char *preempt_model_str(void)
 
 		if (IS_ENABLED(CONFIG_PREEMPT_DYNAMIC)) {
 			seq_buf_printf(&s, "(%s)%s",
-				       preempt_dynamic_mode > 0 ?
+				       preempt_dynamic_mode >= 0 ?
 				       preempt_modes[preempt_dynamic_mode] : "undef",
 				       brace ? "}" : "");
 			return seq_buf_str(&s);

From 009836b4fa52f92cba33618e773b1094affa8cd2 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Thu, 5 Jun 2025 12:00:09 +0200
Subject: [PATCH 1064/1334] sched/core: Fix migrate_swap() vs. hotplug

On Mon, Jun 02, 2025 at 03:22:13PM +0800, Kuyo Chang wrote:

> So, the potential race scenario is:
>
> 	CPU0							CPU1
> 	// doing migrate_swap(cpu0/cpu1)
> 	stop_two_cpus()
> 							  ...
> 							 // doing _cpu_down()
> 							      sched_cpu_deactivate()
> 								set_cpu_active(cpu, false);
> 								balance_push_set(cpu, true);
> 	cpu_stop_queue_two_works
> 	    __cpu_stop_queue_work(stopper1,...);
> 	    __cpu_stop_queue_work(stopper2,..);
> 	stop_cpus_in_progress -> true
> 		preempt_enable();
> 								...
> 							1st balance_push
> 							stop_one_cpu_nowait
> 							cpu_stop_queue_work
> 							__cpu_stop_queue_work
> 							list_add_tail  -> 1st add push_work
> 							wake_up_q(&wakeq);  -> "wakeq is empty.
> 										This implies that the stopper is at wakeq@migrate_swap."
> 	preempt_disable
> 	wake_up_q(&wakeq);
> 	        wake_up_process // wakeup migrate/0
> 		    try_to_wake_up
> 		        ttwu_queue
> 		            ttwu_queue_cond ->meet below case
> 		                if (cpu == smp_processor_id())
> 			         return false;
> 			ttwu_do_activate
> 			//migrate/0 wakeup done
> 		wake_up_process // wakeup migrate/1
> 	           try_to_wake_up
> 		    ttwu_queue
> 			ttwu_queue_cond
> 		        ttwu_queue_wakelist
> 			__ttwu_queue_wakelist
> 			__smp_call_single_queue
> 	preempt_enable();
>
> 							2nd balance_push
> 							stop_one_cpu_nowait
> 							cpu_stop_queue_work
> 							__cpu_stop_queue_work
> 							list_add_tail  -> 2nd add push_work, so the double list add is detected
> 							...
> 							...
> 							cpu1 get ipi, do sched_ttwu_pending, wakeup migrate/1
>

So this balance_push() is part of schedule(), and schedule() is supposed
to switch to stopper task, but because of this race condition, stopper
task is stuck in WAKING state and not actually visible to be picked.

Therefore CPU1 can do another schedule() and end up doing another
balance_push() even though the last one hasn't been done yet.

This is a confluence of fail, where both wake_q and ttwu_wakelist can
cause crucial wakeups to be delayed, resulting in the malfunction of
balance_push.

Since there is only a single stopper thread to be woken, the wake_q
doesn't really add anything here, and can be removed in favour of
direct wakeups of the stopper thread.

Then add a clause to ttwu_queue_cond() to ensure the stopper threads
are never queued / delayed.

Of all 3 moving parts, the last addition was the balance_push()
machinery, so pick that as the point the bug was introduced.

Fixes: 2558aacff858 ("sched/hotplug: Ensure only per-cpu kthreads run during hotplug")
Reported-by: Kuyo Chang <kuyo.chang@mediatek.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Kuyo Chang <kuyo.chang@mediatek.com>
Link: https://lkml.kernel.org/r/20250605100009.GO39944@noisy.programming.kicks-ass.net
---
 kernel/sched/core.c   |  5 +++++
 kernel/stop_machine.c | 20 ++++++++++----------
 2 files changed, 15 insertions(+), 10 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index cd80b66a960a..ec68fc686bd7 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3943,6 +3943,11 @@ static inline bool ttwu_queue_cond(struct task_struct *p, int cpu)
 	if (!scx_allow_ttwu_queue(p))
 		return false;
 
+#ifdef CONFIG_SMP
+	if (p->sched_class == &stop_sched_class)
+		return false;
+#endif
+
 	/*
 	 * Do not complicate things with the async wake_list while the CPU is
 	 * in hotplug state.
diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c
index 5d2d0562115b..3fe6b0c99f3d 100644
--- a/kernel/stop_machine.c
+++ b/kernel/stop_machine.c
@@ -82,18 +82,15 @@ static void cpu_stop_signal_done(struct cpu_stop_done *done)
 }
 
 static void __cpu_stop_queue_work(struct cpu_stopper *stopper,
-					struct cpu_stop_work *work,
-					struct wake_q_head *wakeq)
+				  struct cpu_stop_work *work)
 {
 	list_add_tail(&work->list, &stopper->works);
-	wake_q_add(wakeq, stopper->thread);
 }
 
 /* queue @work to @stopper.  if offline, @work is completed immediately */
 static bool cpu_stop_queue_work(unsigned int cpu, struct cpu_stop_work *work)
 {
 	struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu);
-	DEFINE_WAKE_Q(wakeq);
 	unsigned long flags;
 	bool enabled;
 
@@ -101,12 +98,13 @@ static bool cpu_stop_queue_work(unsigned int cpu, struct cpu_stop_work *work)
 	raw_spin_lock_irqsave(&stopper->lock, flags);
 	enabled = stopper->enabled;
 	if (enabled)
-		__cpu_stop_queue_work(stopper, work, &wakeq);
+		__cpu_stop_queue_work(stopper, work);
 	else if (work->done)
 		cpu_stop_signal_done(work->done);
 	raw_spin_unlock_irqrestore(&stopper->lock, flags);
 
-	wake_up_q(&wakeq);
+	if (enabled)
+		wake_up_process(stopper->thread);
 	preempt_enable();
 
 	return enabled;
@@ -264,7 +262,6 @@ static int cpu_stop_queue_two_works(int cpu1, struct cpu_stop_work *work1,
 {
 	struct cpu_stopper *stopper1 = per_cpu_ptr(&cpu_stopper, cpu1);
 	struct cpu_stopper *stopper2 = per_cpu_ptr(&cpu_stopper, cpu2);
-	DEFINE_WAKE_Q(wakeq);
 	int err;
 
 retry:
@@ -300,8 +297,8 @@ retry:
 	}
 
 	err = 0;
-	__cpu_stop_queue_work(stopper1, work1, &wakeq);
-	__cpu_stop_queue_work(stopper2, work2, &wakeq);
+	__cpu_stop_queue_work(stopper1, work1);
+	__cpu_stop_queue_work(stopper2, work2);
 
 unlock:
 	raw_spin_unlock(&stopper2->lock);
@@ -316,7 +313,10 @@ unlock:
 		goto retry;
 	}
 
-	wake_up_q(&wakeq);
+	if (!err) {
+		wake_up_process(stopper1->thread);
+		wake_up_process(stopper2->thread);
+	}
 	preempt_enable();
 
 	return err;

From ccdd09e0fc0d5ce6dfc8360f0c88da9a5045b6ea Mon Sep 17 00:00:00 2001
From: Heiko Carstens <hca@linux.ibm.com>
Date: Mon, 30 Jun 2025 15:12:30 +0200
Subject: [PATCH 1065/1334] objtool: Add missing endian conversion to
 read_annotate()

Trying to compile an x86 kernel on big endian results in this error:

net/ipv4/netfilter/iptable_nat.o: warning: objtool: iptable_nat_table_init+0x150: Unknown annotation type: 50331648
make[5]: *** [scripts/Makefile.build:287: net/ipv4/netfilter/iptable_nat.o] Error 255

Reason is a missing endian conversion in read_annotate().
Add the missing conversion to fix this.

Fixes: 2116b349e29a ("objtool: Generic annotation infrastructure")
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20250630131230.4130185-1-hca@linux.ibm.com
---
 tools/objtool/check.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index f23bdda737aa..d967ac001498 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -2318,6 +2318,7 @@ static int read_annotate(struct objtool_file *file,
 
 	for_each_reloc(sec->rsec, reloc) {
 		type = *(u32 *)(sec->data->d_buf + (reloc_idx(reloc) * sec->sh.sh_entsize) + 4);
+		type = bswap_if_needed(file->elf, type);
 
 		offset = reloc->sym->offset + reloc_addend(reloc);
 		insn = find_insn(file, reloc->sym->sec, offset);

From 9a57c3773152a3ff2c35cc8325e088d011c9f83b Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Mon, 30 Jun 2025 16:50:34 +0200
Subject: [PATCH 1066/1334] futex: Temporary disable FUTEX_PRIVATE_HASH

Chris Mason reported a performance regression on big iron. Reports of
this kind were usually reported as part of a micro benchmark but Chris'
test did mimic his real workload. This makes it a real regression.

The root cause is rcuref_get() which is invoked during each futex
operation. If all threads of an application do this simultaneously then
it leads to cache line bouncing and the performance drops.

Disable FUTEX_PRIVATE_HASH entirely for this cycle. The performance
regression will be addressed in the following cycle enabling the option
again.

Closes: https://lore.kernel.org/all/3ad05298-351e-4d61-9972-ca45a0a50e33@meta.com/
Reported-by: Chris Mason <clm@meta.com>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20250630145034.8JnINEaS@linutronix.de
---
 init/Kconfig | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/init/Kconfig b/init/Kconfig
index af4c2f085455..666783eb50ab 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -1716,9 +1716,13 @@ config FUTEX_PI
 	depends on FUTEX && RT_MUTEXES
 	default y
 
+#
+# marked broken for performance reasons; gives us one more cycle to sort things out.
+#
 config FUTEX_PRIVATE_HASH
 	bool
 	depends on FUTEX && !BASE_SMALL && MMU
+	depends on BROKEN
 	default y
 
 config FUTEX_MPOL

From 04a8ff1bc3514808481ddebd454342ad902a3f60 Mon Sep 17 00:00:00 2001
From: Khairul Anuar Romli <khairul.anuar.romli@altera.com>
Date: Mon, 30 Jun 2025 17:11:56 +0800
Subject: [PATCH 1067/1334] spi: cadence-quadspi: fix cleanup of rx_chan on
 failure paths

Remove incorrect checks on cqspi->rx_chan that cause driver breakage
during failure cleanup. Ensure proper resource freeing on the success
path when operating in cqspi->use_direct_mode, preventing leaks and
improving stability.

Signed-off-by: Khairul Anuar Romli <khairul.anuar.romli@altera.com>
Reviewed-by: Dan Carpenter <dan.carpenter@linaro.org>
Link: https://patch.msgid.link/89765a2b94f047ded4f14babaefb7ef92ba07cb2.1751274389.git.khairul.anuar.romli@altera.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-cadence-quadspi.c | 5 -----
 1 file changed, 5 deletions(-)

diff --git a/drivers/spi/spi-cadence-quadspi.c b/drivers/spi/spi-cadence-quadspi.c
index aa1932ba17cb..d3c78f59b22c 100644
--- a/drivers/spi/spi-cadence-quadspi.c
+++ b/drivers/spi/spi-cadence-quadspi.c
@@ -1960,11 +1960,6 @@ static int cqspi_probe(struct platform_device *pdev)
 
 	pm_runtime_enable(dev);
 
-	if (cqspi->rx_chan) {
-		dma_release_channel(cqspi->rx_chan);
-		goto probe_setup_failed;
-	}
-
 	pm_runtime_set_autosuspend_delay(dev, CQSPI_AUTOSUSPEND_TIMEOUT);
 	pm_runtime_use_autosuspend(dev);
 	pm_runtime_get_noresume(dev);

From 01ed88aea527e19def9070349399684522c66c72 Mon Sep 17 00:00:00 2001
From: Ming Lei <ming.lei@redhat.com>
Date: Tue, 1 Jul 2025 15:23:25 +0800
Subject: [PATCH 1068/1334] ublk: don't queue request if the associated
 uring_cmd is canceled

Commit 524346e9d79f ("ublk: build batch from IOs in same io_ring_ctx and io task")
need to dereference `io->cmd` for checking if the IO can be added to current
batch, see ublk_belong_to_same_batch() and io_uring_cmd_ctx_handle(). However,
`io->cmd` may become invalid after the uring_cmd is canceled.

Fixes it by only allowing to queue this IO in case that ublk_prep_req()
returns `BLK_STS_OK`, when 'io->cmd' is guaranteed to be valid.

Reported-by: Changhui Zhong <czhong@redhat.com>
Fixes: 524346e9d79f ("ublk: build batch from IOs in same io_ring_ctx and io task")
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/20250701072325.1458109-1-ming.lei@redhat.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/ublk_drv.c | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c
index c3e3c3b65a6d..9fd284fa76dc 100644
--- a/drivers/block/ublk_drv.c
+++ b/drivers/block/ublk_drv.c
@@ -1442,15 +1442,16 @@ static void ublk_queue_rqs(struct rq_list *rqlist)
 		struct ublk_queue *this_q = req->mq_hctx->driver_data;
 		struct ublk_io *this_io = &this_q->ios[req->tag];
 
+		if (ublk_prep_req(this_q, req, true) != BLK_STS_OK) {
+			rq_list_add_tail(&requeue_list, req);
+			continue;
+		}
+
 		if (io && !ublk_belong_to_same_batch(io, this_io) &&
 				!rq_list_empty(&submit_list))
 			ublk_queue_cmd_list(io, &submit_list);
 		io = this_io;
-
-		if (ublk_prep_req(this_q, req, true) == BLK_STS_OK)
-			rq_list_add_tail(&submit_list, req);
-		else
-			rq_list_add_tail(&requeue_list, req);
+		rq_list_add_tail(&submit_list, req);
 	}
 
 	if (!rq_list_empty(&submit_list))

From 0d519bb0de3bf0ac9e6f401d4910fc119062d7be Mon Sep 17 00:00:00 2001
From: Yu Kuai <yukuai3@huawei.com>
Date: Mon, 30 Jun 2025 19:28:28 +0800
Subject: [PATCH 1069/1334] brd: fix sleeping function called from invalid
 context in brd_insert_page()

__xa_cmpxchg() is called with rcu_read_lock(), and it will allocate
memory if necessary.

Fix the problem by moving rcu_read_lock() after __xa_cmpxchg(), meanwhile,
it still should be held before xa_unlock(), prevent returned page to be
freed by concurrent discard.

Fixes: bbcacab2e8ee ("brd: avoid extra xarray lookups on first write")
Reported-by: syzbot+ea4c8fd177a47338881a@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/all/685ec4c9.a00a0220.129264.000c.GAE@google.com/
Signed-off-by: Yu Kuai <yukuai3@huawei.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20250630112828.421219-1-yukuai1@huaweicloud.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/brd.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/block/brd.c b/drivers/block/brd.c
index b1be6c510372..0c2eabe14af3 100644
--- a/drivers/block/brd.c
+++ b/drivers/block/brd.c
@@ -64,13 +64,15 @@ static struct page *brd_insert_page(struct brd_device *brd, sector_t sector,
 
 	rcu_read_unlock();
 	page = alloc_page(gfp | __GFP_ZERO | __GFP_HIGHMEM);
-	rcu_read_lock();
-	if (!page)
+	if (!page) {
+		rcu_read_lock();
 		return ERR_PTR(-ENOMEM);
+	}
 
 	xa_lock(&brd->brd_pages);
 	ret = __xa_cmpxchg(&brd->brd_pages, sector >> PAGE_SECTORS_SHIFT, NULL,
 			page, gfp);
+	rcu_read_lock();
 	if (ret) {
 		xa_unlock(&brd->brd_pages);
 		__free_page(page);

From f77bf1ebf8ff6301ccdbc346f7b52db928f9cbf8 Mon Sep 17 00:00:00 2001
From: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Date: Thu, 22 May 2025 10:52:06 +0200
Subject: [PATCH 1070/1334] idpf: return 0 size for RSS key if not supported

Returning -EOPNOTSUPP from function returning u32 is leading to
cast and invalid size value as a result.

-EOPNOTSUPP as a size probably will lead to allocation fail.

Command: ethtool -x eth0
It is visible on all devices that don't have RSS caps set.

[  136.615917] Call Trace:
[  136.615921]  <TASK>
[  136.615927]  ? __warn+0x89/0x130
[  136.615942]  ? __alloc_frozen_pages_noprof+0x322/0x330
[  136.615953]  ? report_bug+0x164/0x190
[  136.615968]  ? handle_bug+0x58/0x90
[  136.615979]  ? exc_invalid_op+0x17/0x70
[  136.615987]  ? asm_exc_invalid_op+0x1a/0x20
[  136.616001]  ? rss_prepare_get.constprop.0+0xb9/0x170
[  136.616016]  ? __alloc_frozen_pages_noprof+0x322/0x330
[  136.616028]  __alloc_pages_noprof+0xe/0x20
[  136.616038]  ___kmalloc_large_node+0x80/0x110
[  136.616072]  __kmalloc_large_node_noprof+0x1d/0xa0
[  136.616081]  __kmalloc_noprof+0x32c/0x4c0
[  136.616098]  ? rss_prepare_get.constprop.0+0xb9/0x170
[  136.616105]  rss_prepare_get.constprop.0+0xb9/0x170
[  136.616114]  ethnl_default_doit+0x107/0x3d0
[  136.616131]  genl_family_rcv_msg_doit+0x100/0x160
[  136.616147]  genl_rcv_msg+0x1b8/0x2c0
[  136.616156]  ? __pfx_ethnl_default_doit+0x10/0x10
[  136.616168]  ? __pfx_genl_rcv_msg+0x10/0x10
[  136.616176]  netlink_rcv_skb+0x58/0x110
[  136.616186]  genl_rcv+0x28/0x40
[  136.616195]  netlink_unicast+0x19b/0x290
[  136.616206]  netlink_sendmsg+0x222/0x490
[  136.616215]  __sys_sendto+0x1fd/0x210
[  136.616233]  __x64_sys_sendto+0x24/0x30
[  136.616242]  do_syscall_64+0x82/0x160
[  136.616252]  ? __sys_recvmsg+0x83/0xe0
[  136.616265]  ? syscall_exit_to_user_mode+0x10/0x210
[  136.616275]  ? do_syscall_64+0x8e/0x160
[  136.616282]  ? __count_memcg_events+0xa1/0x130
[  136.616295]  ? count_memcg_events.constprop.0+0x1a/0x30
[  136.616306]  ? handle_mm_fault+0xae/0x2d0
[  136.616319]  ? do_user_addr_fault+0x379/0x670
[  136.616328]  ? clear_bhb_loop+0x45/0xa0
[  136.616340]  ? clear_bhb_loop+0x45/0xa0
[  136.616349]  ? clear_bhb_loop+0x45/0xa0
[  136.616359]  entry_SYSCALL_64_after_hwframe+0x76/0x7e
[  136.616369] RIP: 0033:0x7fd30ba7b047
[  136.616376] Code: 0c 00 f7 d8 64 89 02 48 c7 c0 ff ff ff ff eb b8 0f 1f 00 f3 0f 1e fa 80 3d bd d5 0c 00 00 41 89 ca 74 10 b8 2c 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 71 c3 55 48 83 ec 30 44 89 4c 24 2c 4c 89 44
[  136.616381] RSP: 002b:00007ffde1796d68 EFLAGS: 00000202 ORIG_RAX: 000000000000002c
[  136.616388] RAX: ffffffffffffffda RBX: 000055d7bd89f2a0 RCX: 00007fd30ba7b047
[  136.616392] RDX: 0000000000000028 RSI: 000055d7bd89f3b0 RDI: 0000000000000003
[  136.616396] RBP: 00007ffde1796e10 R08: 00007fd30bb4e200 R09: 000000000000000c
[  136.616399] R10: 0000000000000000 R11: 0000000000000202 R12: 000055d7bd89f340
[  136.616403] R13: 000055d7bd89f3b0 R14: 000055d78943f200 R15: 0000000000000000

Fixes: 02cbfba1add5 ("idpf: add ethtool callbacks")
Reviewed-by: Ahmed Zaki <ahmed.zaki@intel.com>
Signed-off-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Tested-by: Samuel Salin <Samuel.salin@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/idpf/idpf_ethtool.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/intel/idpf/idpf_ethtool.c b/drivers/net/ethernet/intel/idpf/idpf_ethtool.c
index 9bdb309b668e..eaf7a2606faa 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_ethtool.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_ethtool.c
@@ -47,7 +47,7 @@ static u32 idpf_get_rxfh_key_size(struct net_device *netdev)
 	struct idpf_vport_user_config_data *user_config;
 
 	if (!idpf_is_cap_ena_all(np->adapter, IDPF_RSS_CAPS, IDPF_CAP_RSS))
-		return -EOPNOTSUPP;
+		return 0;
 
 	user_config = &np->adapter->vport_config[np->vport_idx]->user_config;
 
@@ -66,7 +66,7 @@ static u32 idpf_get_rxfh_indir_size(struct net_device *netdev)
 	struct idpf_vport_user_config_data *user_config;
 
 	if (!idpf_is_cap_ena_all(np->adapter, IDPF_RSS_CAPS, IDPF_CAP_RSS))
-		return -EOPNOTSUPP;
+		return 0;
 
 	user_config = &np->adapter->vport_config[np->vport_idx]->user_config;
 

From b2beb5bb2cd90d7939e470ed4da468683f41baa3 Mon Sep 17 00:00:00 2001
From: Ahmed Zaki <ahmed.zaki@intel.com>
Date: Fri, 23 May 2025 14:55:37 -0600
Subject: [PATCH 1071/1334] idpf: convert control queue mutex to a spinlock

With VIRTCHNL2_CAP_MACFILTER enabled, the following warning is generated
on module load:

[  324.701677] BUG: sleeping function called from invalid context at kernel/locking/mutex.c:578
[  324.701684] in_atomic(): 1, irqs_disabled(): 0, non_block: 0, pid: 1582, name: NetworkManager
[  324.701689] preempt_count: 201, expected: 0
[  324.701693] RCU nest depth: 0, expected: 0
[  324.701697] 2 locks held by NetworkManager/1582:
[  324.701702]  #0: ffffffff9f7be770 (rtnl_mutex){....}-{3:3}, at: rtnl_newlink+0x791/0x21e0
[  324.701730]  #1: ff1100216c380368 (_xmit_ETHER){....}-{2:2}, at: __dev_open+0x3f0/0x870
[  324.701749] Preemption disabled at:
[  324.701752] [<ffffffff9cd23b9d>] __dev_open+0x3dd/0x870
[  324.701765] CPU: 30 UID: 0 PID: 1582 Comm: NetworkManager Not tainted 6.15.0-rc5+ #2 PREEMPT(voluntary)
[  324.701771] Hardware name: Intel Corporation M50FCP2SBSTD/M50FCP2SBSTD, BIOS SE5C741.86B.01.01.0001.2211140926 11/14/2022
[  324.701774] Call Trace:
[  324.701777]  <TASK>
[  324.701779]  dump_stack_lvl+0x5d/0x80
[  324.701788]  ? __dev_open+0x3dd/0x870
[  324.701793]  __might_resched.cold+0x1ef/0x23d
<..>
[  324.701818]  __mutex_lock+0x113/0x1b80
<..>
[  324.701917]  idpf_ctlq_clean_sq+0xad/0x4b0 [idpf]
[  324.701935]  ? kasan_save_track+0x14/0x30
[  324.701941]  idpf_mb_clean+0x143/0x380 [idpf]
<..>
[  324.701991]  idpf_send_mb_msg+0x111/0x720 [idpf]
[  324.702009]  idpf_vc_xn_exec+0x4cc/0x990 [idpf]
[  324.702021]  ? rcu_is_watching+0x12/0xc0
[  324.702035]  idpf_add_del_mac_filters+0x3ed/0xb50 [idpf]
<..>
[  324.702122]  __hw_addr_sync_dev+0x1cf/0x300
[  324.702126]  ? find_held_lock+0x32/0x90
[  324.702134]  idpf_set_rx_mode+0x317/0x390 [idpf]
[  324.702152]  __dev_open+0x3f8/0x870
[  324.702159]  ? __pfx___dev_open+0x10/0x10
[  324.702174]  __dev_change_flags+0x443/0x650
<..>
[  324.702208]  netif_change_flags+0x80/0x160
[  324.702218]  do_setlink.isra.0+0x16a0/0x3960
<..>
[  324.702349]  rtnl_newlink+0x12fd/0x21e0

The sequence is as follows:
	rtnl_newlink()->
	__dev_change_flags()->
	__dev_open()->
	dev_set_rx_mode() - >  # disables BH and grabs "dev->addr_list_lock"
	idpf_set_rx_mode() ->  # proceed only if VIRTCHNL2_CAP_MACFILTER is ON
	__dev_uc_sync() ->
	idpf_add_mac_filter ->
	idpf_add_del_mac_filters ->
	idpf_send_mb_msg() ->
	idpf_mb_clean() ->
	idpf_ctlq_clean_sq()   # mutex_lock(cq_lock)

Fix by converting cq_lock to a spinlock. All operations under the new
lock are safe except freeing the DMA memory, which may use vunmap(). Fix
by requesting a contiguous physical memory for the DMA mapping.

Fixes: a251eee62133 ("idpf: add SRIOV support and other ndo_ops")
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Signed-off-by: Ahmed Zaki <ahmed.zaki@intel.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Tested-by: Samuel Salin <Samuel.salin@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 .../net/ethernet/intel/idpf/idpf_controlq.c   | 23 +++++++++----------
 .../ethernet/intel/idpf/idpf_controlq_api.h   |  2 +-
 drivers/net/ethernet/intel/idpf/idpf_lib.c    | 12 ++++++----
 3 files changed, 20 insertions(+), 17 deletions(-)

diff --git a/drivers/net/ethernet/intel/idpf/idpf_controlq.c b/drivers/net/ethernet/intel/idpf/idpf_controlq.c
index b28991dd1870..48b8e184f3db 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_controlq.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_controlq.c
@@ -96,7 +96,7 @@ static void idpf_ctlq_init_rxq_bufs(struct idpf_ctlq_info *cq)
  */
 static void idpf_ctlq_shutdown(struct idpf_hw *hw, struct idpf_ctlq_info *cq)
 {
-	mutex_lock(&cq->cq_lock);
+	spin_lock(&cq->cq_lock);
 
 	/* free ring buffers and the ring itself */
 	idpf_ctlq_dealloc_ring_res(hw, cq);
@@ -104,8 +104,7 @@ static void idpf_ctlq_shutdown(struct idpf_hw *hw, struct idpf_ctlq_info *cq)
 	/* Set ring_size to 0 to indicate uninitialized queue */
 	cq->ring_size = 0;
 
-	mutex_unlock(&cq->cq_lock);
-	mutex_destroy(&cq->cq_lock);
+	spin_unlock(&cq->cq_lock);
 }
 
 /**
@@ -173,7 +172,7 @@ int idpf_ctlq_add(struct idpf_hw *hw,
 
 	idpf_ctlq_init_regs(hw, cq, is_rxq);
 
-	mutex_init(&cq->cq_lock);
+	spin_lock_init(&cq->cq_lock);
 
 	list_add(&cq->cq_list, &hw->cq_list_head);
 
@@ -272,7 +271,7 @@ int idpf_ctlq_send(struct idpf_hw *hw, struct idpf_ctlq_info *cq,
 	int err = 0;
 	int i;
 
-	mutex_lock(&cq->cq_lock);
+	spin_lock(&cq->cq_lock);
 
 	/* Ensure there are enough descriptors to send all messages */
 	num_desc_avail = IDPF_CTLQ_DESC_UNUSED(cq);
@@ -332,7 +331,7 @@ int idpf_ctlq_send(struct idpf_hw *hw, struct idpf_ctlq_info *cq,
 	wr32(hw, cq->reg.tail, cq->next_to_use);
 
 err_unlock:
-	mutex_unlock(&cq->cq_lock);
+	spin_unlock(&cq->cq_lock);
 
 	return err;
 }
@@ -364,7 +363,7 @@ int idpf_ctlq_clean_sq(struct idpf_ctlq_info *cq, u16 *clean_count,
 	if (*clean_count > cq->ring_size)
 		return -EBADR;
 
-	mutex_lock(&cq->cq_lock);
+	spin_lock(&cq->cq_lock);
 
 	ntc = cq->next_to_clean;
 
@@ -397,7 +396,7 @@ int idpf_ctlq_clean_sq(struct idpf_ctlq_info *cq, u16 *clean_count,
 
 	cq->next_to_clean = ntc;
 
-	mutex_unlock(&cq->cq_lock);
+	spin_unlock(&cq->cq_lock);
 
 	/* Return number of descriptors actually cleaned */
 	*clean_count = i;
@@ -435,7 +434,7 @@ int idpf_ctlq_post_rx_buffs(struct idpf_hw *hw, struct idpf_ctlq_info *cq,
 	if (*buff_count > 0)
 		buffs_avail = true;
 
-	mutex_lock(&cq->cq_lock);
+	spin_lock(&cq->cq_lock);
 
 	if (tbp >= cq->ring_size)
 		tbp = 0;
@@ -524,7 +523,7 @@ post_buffs_out:
 		wr32(hw, cq->reg.tail, cq->next_to_post);
 	}
 
-	mutex_unlock(&cq->cq_lock);
+	spin_unlock(&cq->cq_lock);
 
 	/* return the number of buffers that were not posted */
 	*buff_count = *buff_count - i;
@@ -552,7 +551,7 @@ int idpf_ctlq_recv(struct idpf_ctlq_info *cq, u16 *num_q_msg,
 	u16 i;
 
 	/* take the lock before we start messing with the ring */
-	mutex_lock(&cq->cq_lock);
+	spin_lock(&cq->cq_lock);
 
 	ntc = cq->next_to_clean;
 
@@ -614,7 +613,7 @@ int idpf_ctlq_recv(struct idpf_ctlq_info *cq, u16 *num_q_msg,
 
 	cq->next_to_clean = ntc;
 
-	mutex_unlock(&cq->cq_lock);
+	spin_unlock(&cq->cq_lock);
 
 	*num_q_msg = i;
 	if (*num_q_msg == 0)
diff --git a/drivers/net/ethernet/intel/idpf/idpf_controlq_api.h b/drivers/net/ethernet/intel/idpf/idpf_controlq_api.h
index 9642494a67d8..3414c5f9a831 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_controlq_api.h
+++ b/drivers/net/ethernet/intel/idpf/idpf_controlq_api.h
@@ -99,7 +99,7 @@ struct idpf_ctlq_info {
 
 	enum idpf_ctlq_type cq_type;
 	int q_id;
-	struct mutex cq_lock;		/* control queue lock */
+	spinlock_t cq_lock;		/* control queue lock */
 	/* used for interrupt processing */
 	u16 next_to_use;
 	u16 next_to_clean;
diff --git a/drivers/net/ethernet/intel/idpf/idpf_lib.c b/drivers/net/ethernet/intel/idpf/idpf_lib.c
index 4eb20ec2accb..80382ff4a5fa 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_lib.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_lib.c
@@ -2314,8 +2314,12 @@ void *idpf_alloc_dma_mem(struct idpf_hw *hw, struct idpf_dma_mem *mem, u64 size)
 	struct idpf_adapter *adapter = hw->back;
 	size_t sz = ALIGN(size, 4096);
 
-	mem->va = dma_alloc_coherent(&adapter->pdev->dev, sz,
-				     &mem->pa, GFP_KERNEL);
+	/* The control queue resources are freed under a spinlock, contiguous
+	 * pages will avoid IOMMU remapping and the use vmap (and vunmap in
+	 * dma_free_*() path.
+	 */
+	mem->va = dma_alloc_attrs(&adapter->pdev->dev, sz, &mem->pa,
+				  GFP_KERNEL, DMA_ATTR_FORCE_CONTIGUOUS);
 	mem->size = sz;
 
 	return mem->va;
@@ -2330,8 +2334,8 @@ void idpf_free_dma_mem(struct idpf_hw *hw, struct idpf_dma_mem *mem)
 {
 	struct idpf_adapter *adapter = hw->back;
 
-	dma_free_coherent(&adapter->pdev->dev, mem->size,
-			  mem->va, mem->pa);
+	dma_free_attrs(&adapter->pdev->dev, mem->size,
+		       mem->va, mem->pa, DMA_ATTR_FORCE_CONTIGUOUS);
 	mem->size = 0;
 	mem->va = NULL;
 	mem->pa = 0;

From 0325143b59c6c6d79987afc57d2456e7a20d13b7 Mon Sep 17 00:00:00 2001
From: Vitaly Lifshits <vitaly.lifshits@intel.com>
Date: Wed, 11 Jun 2025 15:52:54 +0300
Subject: [PATCH 1072/1334] igc: disable L1.2 PCI-E link substate to avoid
 performance issue

I226 devices advertise support for the PCI-E link L1.2 substate. However,
due to a hardware limitation, the exit latency from this low-power state
is longer than the packet buffer can tolerate under high traffic
conditions. This can lead to packet loss and degraded performance.

To mitigate this, disable the L1.2 substate. The increased power draw
between L1.1 and L1.2 is insignificant.

Fixes: 43546211738e ("igc: Add new device ID's")
Link: https://lore.kernel.org/intel-wired-lan/15248b4f-3271-42dd-8e35-02bfc92b25e1@intel.com
Signed-off-by: Vitaly Lifshits <vitaly.lifshits@intel.com>
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Tested-by: Mor Bar-Gabay <morx.bar.gabay@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/igc/igc_main.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index 686793c539f2..031c332f66c4 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -7115,6 +7115,10 @@ static int igc_probe(struct pci_dev *pdev,
 	adapter->port_num = hw->bus.func;
 	adapter->msg_enable = netif_msg_init(debug, DEFAULT_MSG_ENABLE);
 
+	/* Disable ASPM L1.2 on I226 devices to avoid packet loss */
+	if (igc_is_device_id_i226(hw))
+		pci_disable_link_state(pdev, PCIE_LINK_STATE_L1_2);
+
 	err = pci_save_state(pdev);
 	if (err)
 		goto err_ioremap;
@@ -7500,6 +7504,9 @@ static int __igc_resume(struct device *dev, bool rpm)
 	pci_enable_wake(pdev, PCI_D3hot, 0);
 	pci_enable_wake(pdev, PCI_D3cold, 0);
 
+	if (igc_is_device_id_i226(hw))
+		pci_disable_link_state(pdev, PCIE_LINK_STATE_L1_2);
+
 	if (igc_init_interrupt_scheme(adapter, true)) {
 		netdev_err(netdev, "Unable to allocate memory for queues\n");
 		return -ENOMEM;
@@ -7625,6 +7632,9 @@ static pci_ers_result_t igc_io_slot_reset(struct pci_dev *pdev)
 		pci_enable_wake(pdev, PCI_D3hot, 0);
 		pci_enable_wake(pdev, PCI_D3cold, 0);
 
+		if (igc_is_device_id_i226(hw))
+			pci_disable_link_state_locked(pdev, PCIE_LINK_STATE_L1_2);
+
 		/* In case of PCI error, adapter loses its HW address
 		 * so we should re-assign it here.
 		 */

From c584c4f264c3bd7c27247688056a5c77907dbb07 Mon Sep 17 00:00:00 2001
From: Conor Dooley <conor.dooley@microchip.com>
Date: Mon, 30 Jun 2025 16:18:17 +0100
Subject: [PATCH 1073/1334] i2c: microchip-core: re-fix fake detections w/
 i2cdetect

Introducing support for smbus re-broke i2cdetect, causing it to detect
devices at every i2c address, just as it did prior to being fixed in
commit 49e1f0fd0d4cb ("i2c: microchip-core: fix "ghost" detections").
This was caused by an oversight, where the new smbus code failed to
check the return value of mchp_corei2c_xfer(). Check it, and propagate
any errors.

Fixes: d6ceb40538263 ("i2c: microchip-corei2c: add smbus support")
Signed-off-by: Conor Dooley <conor.dooley@microchip.com>
Signed-off-by: Andi Shyti <andi.shyti@kernel.org>
Link: https://lore.kernel.org/r/20250630-shopper-proven-500f4075e7d6@spud
---
 drivers/i2c/busses/i2c-microchip-corei2c.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/i2c/busses/i2c-microchip-corei2c.c b/drivers/i2c/busses/i2c-microchip-corei2c.c
index f173bda1c98c..c8599733633e 100644
--- a/drivers/i2c/busses/i2c-microchip-corei2c.c
+++ b/drivers/i2c/busses/i2c-microchip-corei2c.c
@@ -435,6 +435,7 @@ static int mchp_corei2c_smbus_xfer(struct i2c_adapter *adap, u16 addr, unsigned
 	u8 tx_buf[I2C_SMBUS_BLOCK_MAX + 2];
 	u8 rx_buf[I2C_SMBUS_BLOCK_MAX + 1];
 	int num_msgs = 1;
+	int ret;
 
 	msgs[CORE_I2C_SMBUS_MSG_WR].addr = addr;
 	msgs[CORE_I2C_SMBUS_MSG_WR].flags = 0;
@@ -505,7 +506,10 @@ static int mchp_corei2c_smbus_xfer(struct i2c_adapter *adap, u16 addr, unsigned
 		return -EOPNOTSUPP;
 	}
 
-	mchp_corei2c_xfer(&idev->adapter, msgs, num_msgs);
+	ret = mchp_corei2c_xfer(&idev->adapter, msgs, num_msgs);
+	if (ret < 0)
+		return ret;
+
 	if (read_write == I2C_SMBUS_WRITE || size <= I2C_SMBUS_BYTE_DATA)
 		return 0;
 

From 2d5cff2b4bc567dcaad7ab5b46c973ba534cc062 Mon Sep 17 00:00:00 2001
From: Jia Yao <jia.yao@intel.com>
Date: Thu, 12 Jun 2025 22:46:20 +0000
Subject: [PATCH 1074/1334] drm/xe: Fix out-of-bounds field write in
 MI_STORE_DATA_IMM

According to Bspec, bits 0~9 of MI_STORE_DATA_IMM must not exceed 0x3FE.
The macro MI_SDI_NUM_QW(x) evaluates to 2 * x + 1, which means the
condition 2 * x + 1 <= 0x3FE must be satisfied. Therefore, the maximum
valid value for x is 0x1FE, not 0x1FF.

v2
 - Replace 0x1fe with macro MAX_PTE_PER_SDI (Auld, Matthew & Patelczyk, Maciej)

v3
 - Change macro MAX_PTE_PER_SDI from 0x1fe to 0x1feU (De Marchi, Lucas)

Bspec: 60246

Fixes: 9c44fd5f6e8a ("drm/xe: Add migrate layer functions for SVM support")
Cc: Matthew Brost <matthew.brost@intel.com>
Cc: Brian3 Nguyen <brian3.nguyen@intel.com>
Cc: Alex Zuo <alex.zuo@intel.com>
Cc: Matthew Auld <matthew.auld@intel.com>
Cc: Maciej Patelczyk <maciej.patelczyk@intel.com>
Cc: Lucas De Marchi <lucas.demarchi@intel.com>
Suggested-by: Shuicheng Lin <shuicheng.lin@intel.com>
Signed-off-by: Jia Yao <jia.yao@intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Reviewed-by: Maciej Patelczyk <maciej.patelczyk@intel.com>
Link: https://lore.kernel.org/r/20250612224620.161105-1-jia.yao@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
(cherry picked from commit c038bdba98c9f6a36378044a9d4385531a194d3e)
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
---
 drivers/gpu/drm/xe/xe_migrate.c | 18 ++++++++++--------
 1 file changed, 10 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_migrate.c b/drivers/gpu/drm/xe/xe_migrate.c
index 8f8e9fdfb2a8..7acdc4c78866 100644
--- a/drivers/gpu/drm/xe/xe_migrate.c
+++ b/drivers/gpu/drm/xe/xe_migrate.c
@@ -82,7 +82,7 @@ struct xe_migrate {
  * of the instruction.  Subtracting the instruction header (1 dword) and
  * address (2 dwords), that leaves 0x3FD dwords (0x1FE qwords) for PTE values.
  */
-#define MAX_PTE_PER_SDI 0x1FE
+#define MAX_PTE_PER_SDI 0x1FEU
 
 /**
  * xe_tile_migrate_exec_queue() - Get this tile's migrate exec queue.
@@ -1553,15 +1553,17 @@ static u32 pte_update_cmd_size(u64 size)
 	u64 entries = DIV_U64_ROUND_UP(size, XE_PAGE_SIZE);
 
 	XE_WARN_ON(size > MAX_PREEMPTDISABLE_TRANSFER);
+
 	/*
 	 * MI_STORE_DATA_IMM command is used to update page table. Each
-	 * instruction can update maximumly 0x1ff pte entries. To update
-	 * n (n <= 0x1ff) pte entries, we need:
-	 * 1 dword for the MI_STORE_DATA_IMM command header (opcode etc)
-	 * 2 dword for the page table's physical location
-	 * 2*n dword for value of pte to fill (each pte entry is 2 dwords)
+	 * instruction can update maximumly MAX_PTE_PER_SDI pte entries. To
+	 * update n (n <= MAX_PTE_PER_SDI) pte entries, we need:
+	 *
+	 * - 1 dword for the MI_STORE_DATA_IMM command header (opcode etc)
+	 * - 2 dword for the page table's physical location
+	 * - 2*n dword for value of pte to fill (each pte entry is 2 dwords)
 	 */
-	num_dword = (1 + 2) * DIV_U64_ROUND_UP(entries, 0x1ff);
+	num_dword = (1 + 2) * DIV_U64_ROUND_UP(entries, MAX_PTE_PER_SDI);
 	num_dword += entries * 2;
 
 	return num_dword;
@@ -1577,7 +1579,7 @@ static void build_pt_update_batch_sram(struct xe_migrate *m,
 
 	ptes = DIV_ROUND_UP(size, XE_PAGE_SIZE);
 	while (ptes) {
-		u32 chunk = min(0x1ffU, ptes);
+		u32 chunk = min(MAX_PTE_PER_SDI, ptes);
 
 		bb->cs[bb->len++] = MI_STORE_DATA_IMM | MI_SDI_NUM_QW(chunk);
 		bb->cs[bb->len++] = pt_offset;

From 8c44dac8add7503c345c0f6c7962e4863b88ba42 Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Tue, 27 May 2025 11:08:36 +0200
Subject: [PATCH 1075/1334] eventpoll: Fix priority inversion problem

The ready event list of an epoll object is protected by read-write
semaphore:

  - The consumer (waiter) acquires the write lock and takes items.
  - the producer (waker) takes the read lock and adds items.

The point of this design is enabling epoll to scale well with large number
of producers, as multiple producers can hold the read lock at the same
time.

Unfortunately, this implementation may cause scheduling priority inversion
problem. Suppose the consumer has higher scheduling priority than the
producer. The consumer needs to acquire the write lock, but may be blocked
by the producer holding the read lock. Since read-write semaphore does not
support priority-boosting for the readers (even with CONFIG_PREEMPT_RT=y),
we have a case of priority inversion: a higher priority consumer is blocked
by a lower priority producer. This problem was reported in [1].

Furthermore, this could also cause stall problem, as described in [2].

To fix this problem, make the event list half-lockless:

  - The consumer acquires a mutex (ep->mtx) and takes items.
  - The producer locklessly adds items to the list.

Performance is not the main goal of this patch, but as the producer now can
add items without waiting for consumer to release the lock, performance
improvement is observed using the stress test from
https://github.com/rouming/test-tools/blob/master/stress-epoll.c. This is
the same test that justified using read-write semaphore in the past.

Testing using 12 x86_64 CPUs:

          Before     After        Diff
threads  events/ms  events/ms
      8       6932      19753    +185%
     16       7820      27923    +257%
     32       7648      35164    +360%
     64       9677      37780    +290%
    128      11166      38174    +242%

Testing using 1 riscv64 CPU (averaged over 10 runs, as the numbers are
noisy):

          Before     After        Diff
threads  events/ms  events/ms
      1         73        129     +77%
      2        151        216     +43%
      4        216        364     +69%
      8        234        382     +63%
     16        251        392     +56%

Reported-by: Frederic Weisbecker <frederic@kernel.org>
Closes: https://lore.kernel.org/linux-rt-users/20210825132754.GA895675@lothringen/ [1]
Reported-by: Valentin Schneider <vschneid@redhat.com>
Closes: https://lore.kernel.org/linux-rt-users/xhsmhttqvnall.mognet@vschneid.remote.csb/ [2]
Signed-off-by: Nam Cao <namcao@linutronix.de>
Link: https://lore.kernel.org/20250527090836.1290532-1-namcao@linutronix.de
Tested-by: K Prateek Nayak <kprateek.nayak@amd.com>
Acked-by: Frederic Weisbecker <frederic@kernel.org>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/eventpoll.c | 458 +++++++++++++++----------------------------------
 1 file changed, 134 insertions(+), 324 deletions(-)

diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index d4dbffdedd08..a97a771a459c 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -137,13 +137,7 @@ struct epitem {
 	};
 
 	/* List header used to link this structure to the eventpoll ready list */
-	struct list_head rdllink;
-
-	/*
-	 * Works together "struct eventpoll"->ovflist in keeping the
-	 * single linked chain of items.
-	 */
-	struct epitem *next;
+	struct llist_node rdllink;
 
 	/* The file descriptor information this item refers to */
 	struct epoll_filefd ffd;
@@ -191,22 +185,15 @@ struct eventpoll {
 	/* Wait queue used by file->poll() */
 	wait_queue_head_t poll_wait;
 
-	/* List of ready file descriptors */
-	struct list_head rdllist;
-
-	/* Lock which protects rdllist and ovflist */
-	rwlock_t lock;
+	/*
+	 * List of ready file descriptors. Adding to this list is lockless. Items can be removed
+	 * only with eventpoll::mtx
+	 */
+	struct llist_head rdllist;
 
 	/* RB tree root used to store monitored fd structs */
 	struct rb_root_cached rbr;
 
-	/*
-	 * This is a single linked list that chains all the "struct epitem" that
-	 * happened while transferring ready events to userspace w/out
-	 * holding ->lock.
-	 */
-	struct epitem *ovflist;
-
 	/* wakeup_source used when ep_send_events or __ep_eventpoll_poll is running */
 	struct wakeup_source *ws;
 
@@ -361,10 +348,14 @@ static inline int ep_cmp_ffd(struct epoll_filefd *p1,
 	        (p1->file < p2->file ? -1 : p1->fd - p2->fd));
 }
 
-/* Tells us if the item is currently linked */
-static inline int ep_is_linked(struct epitem *epi)
+/*
+ * Add the item to its container eventpoll's rdllist; do nothing if the item is already on rdllist.
+ */
+static void epitem_ready(struct epitem *epi)
 {
-	return !list_empty(&epi->rdllink);
+	if (&epi->rdllink == cmpxchg(&epi->rdllink.next, &epi->rdllink, NULL))
+		llist_add(&epi->rdllink, &epi->ep->rdllist);
+
 }
 
 static inline struct eppoll_entry *ep_pwq_from_wait(wait_queue_entry_t *p)
@@ -383,13 +374,26 @@ static inline struct epitem *ep_item_from_wait(wait_queue_entry_t *p)
  *
  * @ep: Pointer to the eventpoll context.
  *
- * Return: a value different than %zero if ready events are available,
- *          or %zero otherwise.
+ * Return: true if ready events might be available, false otherwise.
  */
-static inline int ep_events_available(struct eventpoll *ep)
+static inline bool ep_events_available(struct eventpoll *ep)
 {
-	return !list_empty_careful(&ep->rdllist) ||
-		READ_ONCE(ep->ovflist) != EP_UNACTIVE_PTR;
+	bool available;
+	int locked;
+
+	locked = mutex_trylock(&ep->mtx);
+	if (!locked) {
+		/*
+		 * The lock held and someone might have removed all items while inspecting it. The
+		 * llist_empty() check in this case is futile. Assume that something is enqueued and
+		 * let ep_try_send_events() figure it out.
+		 */
+		return true;
+	}
+
+	available = !llist_empty(&ep->rdllist);
+	mutex_unlock(&ep->mtx);
+	return available;
 }
 
 #ifdef CONFIG_NET_RX_BUSY_POLL
@@ -724,77 +728,6 @@ static inline void ep_pm_stay_awake_rcu(struct epitem *epi)
 	rcu_read_unlock();
 }
 
-
-/*
- * ep->mutex needs to be held because we could be hit by
- * eventpoll_release_file() and epoll_ctl().
- */
-static void ep_start_scan(struct eventpoll *ep, struct list_head *txlist)
-{
-	/*
-	 * Steal the ready list, and re-init the original one to the
-	 * empty list. Also, set ep->ovflist to NULL so that events
-	 * happening while looping w/out locks, are not lost. We cannot
-	 * have the poll callback to queue directly on ep->rdllist,
-	 * because we want the "sproc" callback to be able to do it
-	 * in a lockless way.
-	 */
-	lockdep_assert_irqs_enabled();
-	write_lock_irq(&ep->lock);
-	list_splice_init(&ep->rdllist, txlist);
-	WRITE_ONCE(ep->ovflist, NULL);
-	write_unlock_irq(&ep->lock);
-}
-
-static void ep_done_scan(struct eventpoll *ep,
-			 struct list_head *txlist)
-{
-	struct epitem *epi, *nepi;
-
-	write_lock_irq(&ep->lock);
-	/*
-	 * During the time we spent inside the "sproc" callback, some
-	 * other events might have been queued by the poll callback.
-	 * We re-insert them inside the main ready-list here.
-	 */
-	for (nepi = READ_ONCE(ep->ovflist); (epi = nepi) != NULL;
-	     nepi = epi->next, epi->next = EP_UNACTIVE_PTR) {
-		/*
-		 * We need to check if the item is already in the list.
-		 * During the "sproc" callback execution time, items are
-		 * queued into ->ovflist but the "txlist" might already
-		 * contain them, and the list_splice() below takes care of them.
-		 */
-		if (!ep_is_linked(epi)) {
-			/*
-			 * ->ovflist is LIFO, so we have to reverse it in order
-			 * to keep in FIFO.
-			 */
-			list_add(&epi->rdllink, &ep->rdllist);
-			ep_pm_stay_awake(epi);
-		}
-	}
-	/*
-	 * We need to set back ep->ovflist to EP_UNACTIVE_PTR, so that after
-	 * releasing the lock, events will be queued in the normal way inside
-	 * ep->rdllist.
-	 */
-	WRITE_ONCE(ep->ovflist, EP_UNACTIVE_PTR);
-
-	/*
-	 * Quickly re-inject items left on "txlist".
-	 */
-	list_splice(txlist, &ep->rdllist);
-	__pm_relax(ep->ws);
-
-	if (!list_empty(&ep->rdllist)) {
-		if (waitqueue_active(&ep->wq))
-			wake_up(&ep->wq);
-	}
-
-	write_unlock_irq(&ep->lock);
-}
-
 static void ep_get(struct eventpoll *ep)
 {
 	refcount_inc(&ep->refcount);
@@ -832,10 +765,12 @@ static void ep_free(struct eventpoll *ep)
 static bool __ep_remove(struct eventpoll *ep, struct epitem *epi, bool force)
 {
 	struct file *file = epi->ffd.file;
+	struct llist_node *put_back_last;
 	struct epitems_head *to_free;
 	struct hlist_head *head;
+	LLIST_HEAD(put_back);
 
-	lockdep_assert_irqs_enabled();
+	lockdep_assert_held(&ep->mtx);
 
 	/*
 	 * Removes poll wait queue hooks.
@@ -867,10 +802,20 @@ static bool __ep_remove(struct eventpoll *ep, struct epitem *epi, bool force)
 
 	rb_erase_cached(&epi->rbn, &ep->rbr);
 
-	write_lock_irq(&ep->lock);
-	if (ep_is_linked(epi))
-		list_del_init(&epi->rdllink);
-	write_unlock_irq(&ep->lock);
+	if (llist_on_list(&epi->rdllink)) {
+		put_back_last = NULL;
+		while (true) {
+			struct llist_node *n = llist_del_first(&ep->rdllist);
+
+			if (&epi->rdllink == n || WARN_ON(!n))
+				break;
+			if (!put_back_last)
+				put_back_last = n;
+			__llist_add(n, &put_back);
+		}
+		if (put_back_last)
+			llist_add_batch(put_back.first, put_back_last, &ep->rdllist);
+	}
 
 	wakeup_source_unregister(ep_wakeup_source(epi));
 	/*
@@ -974,8 +919,9 @@ static __poll_t ep_item_poll(const struct epitem *epi, poll_table *pt, int depth
 static __poll_t __ep_eventpoll_poll(struct file *file, poll_table *wait, int depth)
 {
 	struct eventpoll *ep = file->private_data;
-	LIST_HEAD(txlist);
-	struct epitem *epi, *tmp;
+	struct wakeup_source *ws;
+	struct llist_node *n;
+	struct epitem *epi;
 	poll_table pt;
 	__poll_t res = 0;
 
@@ -989,22 +935,39 @@ static __poll_t __ep_eventpoll_poll(struct file *file, poll_table *wait, int dep
 	 * the ready list.
 	 */
 	mutex_lock_nested(&ep->mtx, depth);
-	ep_start_scan(ep, &txlist);
-	list_for_each_entry_safe(epi, tmp, &txlist, rdllink) {
+	while (true) {
+		n = llist_del_first_init(&ep->rdllist);
+		if (!n)
+			break;
+
+		epi = llist_entry(n, struct epitem, rdllink);
+
 		if (ep_item_poll(epi, &pt, depth + 1)) {
 			res = EPOLLIN | EPOLLRDNORM;
+			epitem_ready(epi);
 			break;
 		} else {
 			/*
-			 * Item has been dropped into the ready list by the poll
-			 * callback, but it's not actually ready, as far as
-			 * caller requested events goes. We can remove it here.
+			 * We need to activate ep before deactivating epi, to prevent autosuspend
+			 * just in case epi becomes active after ep_item_poll() above.
+			 *
+			 * This is similar to ep_send_events().
 			 */
+			ws = ep_wakeup_source(epi);
+			if (ws) {
+				if (ws->active)
+					__pm_stay_awake(ep->ws);
+				__pm_relax(ws);
+			}
 			__pm_relax(ep_wakeup_source(epi));
-			list_del_init(&epi->rdllink);
+
+			/* Just in case epi becomes active right before __pm_relax() */
+			if (unlikely(ep_item_poll(epi, &pt, depth + 1)))
+				ep_pm_stay_awake(epi);
+
+			__pm_relax(ep->ws);
 		}
 	}
-	ep_done_scan(ep, &txlist);
 	mutex_unlock(&ep->mtx);
 	return res;
 }
@@ -1153,12 +1116,10 @@ static int ep_alloc(struct eventpoll **pep)
 		return -ENOMEM;
 
 	mutex_init(&ep->mtx);
-	rwlock_init(&ep->lock);
 	init_waitqueue_head(&ep->wq);
 	init_waitqueue_head(&ep->poll_wait);
-	INIT_LIST_HEAD(&ep->rdllist);
+	init_llist_head(&ep->rdllist);
 	ep->rbr = RB_ROOT_CACHED;
-	ep->ovflist = EP_UNACTIVE_PTR;
 	ep->user = get_current_user();
 	refcount_set(&ep->refcount, 1);
 
@@ -1240,94 +1201,11 @@ struct file *get_epoll_tfile_raw_ptr(struct file *file, int tfd,
 }
 #endif /* CONFIG_KCMP */
 
-/*
- * Adds a new entry to the tail of the list in a lockless way, i.e.
- * multiple CPUs are allowed to call this function concurrently.
- *
- * Beware: it is necessary to prevent any other modifications of the
- *         existing list until all changes are completed, in other words
- *         concurrent list_add_tail_lockless() calls should be protected
- *         with a read lock, where write lock acts as a barrier which
- *         makes sure all list_add_tail_lockless() calls are fully
- *         completed.
- *
- *        Also an element can be locklessly added to the list only in one
- *        direction i.e. either to the tail or to the head, otherwise
- *        concurrent access will corrupt the list.
- *
- * Return: %false if element has been already added to the list, %true
- * otherwise.
- */
-static inline bool list_add_tail_lockless(struct list_head *new,
-					  struct list_head *head)
-{
-	struct list_head *prev;
-
-	/*
-	 * This is simple 'new->next = head' operation, but cmpxchg()
-	 * is used in order to detect that same element has been just
-	 * added to the list from another CPU: the winner observes
-	 * new->next == new.
-	 */
-	if (!try_cmpxchg(&new->next, &new, head))
-		return false;
-
-	/*
-	 * Initially ->next of a new element must be updated with the head
-	 * (we are inserting to the tail) and only then pointers are atomically
-	 * exchanged.  XCHG guarantees memory ordering, thus ->next should be
-	 * updated before pointers are actually swapped and pointers are
-	 * swapped before prev->next is updated.
-	 */
-
-	prev = xchg(&head->prev, new);
-
-	/*
-	 * It is safe to modify prev->next and new->prev, because a new element
-	 * is added only to the tail and new->next is updated before XCHG.
-	 */
-
-	prev->next = new;
-	new->prev = prev;
-
-	return true;
-}
-
-/*
- * Chains a new epi entry to the tail of the ep->ovflist in a lockless way,
- * i.e. multiple CPUs are allowed to call this function concurrently.
- *
- * Return: %false if epi element has been already chained, %true otherwise.
- */
-static inline bool chain_epi_lockless(struct epitem *epi)
-{
-	struct eventpoll *ep = epi->ep;
-
-	/* Fast preliminary check */
-	if (epi->next != EP_UNACTIVE_PTR)
-		return false;
-
-	/* Check that the same epi has not been just chained from another CPU */
-	if (cmpxchg(&epi->next, EP_UNACTIVE_PTR, NULL) != EP_UNACTIVE_PTR)
-		return false;
-
-	/* Atomically exchange tail */
-	epi->next = xchg(&ep->ovflist, epi);
-
-	return true;
-}
-
 /*
  * This is the callback that is passed to the wait queue wakeup
  * mechanism. It is called by the stored file descriptors when they
  * have events to report.
  *
- * This callback takes a read lock in order not to contend with concurrent
- * events from another file descriptor, thus all modifications to ->rdllist
- * or ->ovflist are lockless.  Read lock is paired with the write lock from
- * ep_start/done_scan(), which stops all list modifications and guarantees
- * that lists state is seen correctly.
- *
  * Another thing worth to mention is that ep_poll_callback() can be called
  * concurrently for the same @epi from different CPUs if poll table was inited
  * with several wait queues entries.  Plural wakeup from different CPUs of a
@@ -1337,15 +1215,11 @@ static inline bool chain_epi_lockless(struct epitem *epi)
  */
 static int ep_poll_callback(wait_queue_entry_t *wait, unsigned mode, int sync, void *key)
 {
-	int pwake = 0;
 	struct epitem *epi = ep_item_from_wait(wait);
 	struct eventpoll *ep = epi->ep;
 	__poll_t pollflags = key_to_poll(key);
-	unsigned long flags;
 	int ewake = 0;
 
-	read_lock_irqsave(&ep->lock, flags);
-
 	ep_set_busy_poll_napi_id(epi);
 
 	/*
@@ -1355,7 +1229,7 @@ static int ep_poll_callback(wait_queue_entry_t *wait, unsigned mode, int sync, v
 	 * until the next EPOLL_CTL_MOD will be issued.
 	 */
 	if (!(epi->event.events & ~EP_PRIVATE_BITS))
-		goto out_unlock;
+		goto out;
 
 	/*
 	 * Check the events coming with the callback. At this stage, not
@@ -1364,22 +1238,10 @@ static int ep_poll_callback(wait_queue_entry_t *wait, unsigned mode, int sync, v
 	 * test for "key" != NULL before the event match test.
 	 */
 	if (pollflags && !(pollflags & epi->event.events))
-		goto out_unlock;
+		goto out;
 
-	/*
-	 * If we are transferring events to userspace, we can hold no locks
-	 * (because we're accessing user memory, and because of linux f_op->poll()
-	 * semantics). All the events that happen during that period of time are
-	 * chained in ep->ovflist and requeued later on.
-	 */
-	if (READ_ONCE(ep->ovflist) != EP_UNACTIVE_PTR) {
-		if (chain_epi_lockless(epi))
-			ep_pm_stay_awake_rcu(epi);
-	} else if (!ep_is_linked(epi)) {
-		/* In the usual case, add event to ready list. */
-		if (list_add_tail_lockless(&epi->rdllink, &ep->rdllist))
-			ep_pm_stay_awake_rcu(epi);
-	}
+	ep_pm_stay_awake_rcu(epi);
+	epitem_ready(epi);
 
 	/*
 	 * Wake up ( if active ) both the eventpoll wait list and the ->poll()
@@ -1408,15 +1270,9 @@ static int ep_poll_callback(wait_queue_entry_t *wait, unsigned mode, int sync, v
 			wake_up(&ep->wq);
 	}
 	if (waitqueue_active(&ep->poll_wait))
-		pwake++;
-
-out_unlock:
-	read_unlock_irqrestore(&ep->lock, flags);
-
-	/* We have to call this outside the lock */
-	if (pwake)
 		ep_poll_safewake(ep, epi, pollflags & EPOLL_URING_WAKE);
 
+out:
 	if (!(epi->event.events & EPOLLEXCLUSIVE))
 		ewake = 1;
 
@@ -1661,8 +1517,6 @@ static int ep_insert(struct eventpoll *ep, const struct epoll_event *event,
 	if (is_file_epoll(tfile))
 		tep = tfile->private_data;
 
-	lockdep_assert_irqs_enabled();
-
 	if (unlikely(percpu_counter_compare(&ep->user->epoll_watches,
 					    max_user_watches) >= 0))
 		return -ENOSPC;
@@ -1674,11 +1528,10 @@ static int ep_insert(struct eventpoll *ep, const struct epoll_event *event,
 	}
 
 	/* Item initialization follow here ... */
-	INIT_LIST_HEAD(&epi->rdllink);
+	init_llist_node(&epi->rdllink);
 	epi->ep = ep;
 	ep_set_ffd(&epi->ffd, tfile, fd);
 	epi->event = *event;
-	epi->next = EP_UNACTIVE_PTR;
 
 	if (tep)
 		mutex_lock_nested(&tep->mtx, 1);
@@ -1745,16 +1598,13 @@ static int ep_insert(struct eventpoll *ep, const struct epoll_event *event,
 		return -ENOMEM;
 	}
 
-	/* We have to drop the new item inside our item list to keep track of it */
-	write_lock_irq(&ep->lock);
-
 	/* record NAPI ID of new item if present */
 	ep_set_busy_poll_napi_id(epi);
 
 	/* If the file is already "ready" we drop it inside the ready list */
-	if (revents && !ep_is_linked(epi)) {
-		list_add_tail(&epi->rdllink, &ep->rdllist);
+	if (revents) {
 		ep_pm_stay_awake(epi);
+		epitem_ready(epi);
 
 		/* Notify waiting tasks that events are available */
 		if (waitqueue_active(&ep->wq))
@@ -1763,8 +1613,6 @@ static int ep_insert(struct eventpoll *ep, const struct epoll_event *event,
 			pwake++;
 	}
 
-	write_unlock_irq(&ep->lock);
-
 	/* We have to call this outside the lock */
 	if (pwake)
 		ep_poll_safewake(ep, NULL, 0);
@@ -1779,11 +1627,8 @@ static int ep_insert(struct eventpoll *ep, const struct epoll_event *event,
 static int ep_modify(struct eventpoll *ep, struct epitem *epi,
 		     const struct epoll_event *event)
 {
-	int pwake = 0;
 	poll_table pt;
 
-	lockdep_assert_irqs_enabled();
-
 	init_poll_funcptr(&pt, NULL);
 
 	/*
@@ -1827,24 +1672,16 @@ static int ep_modify(struct eventpoll *ep, struct epitem *epi,
 	 * list, push it inside.
 	 */
 	if (ep_item_poll(epi, &pt, 1)) {
-		write_lock_irq(&ep->lock);
-		if (!ep_is_linked(epi)) {
-			list_add_tail(&epi->rdllink, &ep->rdllist);
-			ep_pm_stay_awake(epi);
+		ep_pm_stay_awake(epi);
+		epitem_ready(epi);
 
-			/* Notify waiting tasks that events are available */
-			if (waitqueue_active(&ep->wq))
-				wake_up(&ep->wq);
-			if (waitqueue_active(&ep->poll_wait))
-				pwake++;
-		}
-		write_unlock_irq(&ep->lock);
+		/* Notify waiting tasks that events are available */
+		if (waitqueue_active(&ep->wq))
+			wake_up(&ep->wq);
+		if (waitqueue_active(&ep->poll_wait))
+			ep_poll_safewake(ep, NULL, 0);
 	}
 
-	/* We have to call this outside the lock */
-	if (pwake)
-		ep_poll_safewake(ep, NULL, 0);
-
 	return 0;
 }
 
@@ -1852,7 +1689,7 @@ static int ep_send_events(struct eventpoll *ep,
 			  struct epoll_event __user *events, int maxevents)
 {
 	struct epitem *epi, *tmp;
-	LIST_HEAD(txlist);
+	LLIST_HEAD(txlist);
 	poll_table pt;
 	int res = 0;
 
@@ -1867,19 +1704,18 @@ static int ep_send_events(struct eventpoll *ep,
 	init_poll_funcptr(&pt, NULL);
 
 	mutex_lock(&ep->mtx);
-	ep_start_scan(ep, &txlist);
 
-	/*
-	 * We can loop without lock because we are passed a task private list.
-	 * Items cannot vanish during the loop we are holding ep->mtx.
-	 */
-	list_for_each_entry_safe(epi, tmp, &txlist, rdllink) {
+	while (res < maxevents) {
 		struct wakeup_source *ws;
+		struct llist_node *n;
 		__poll_t revents;
 
-		if (res >= maxevents)
+		n = llist_del_first(&ep->rdllist);
+		if (!n)
 			break;
 
+		epi = llist_entry(n, struct epitem, rdllink);
+
 		/*
 		 * Activate ep->ws before deactivating epi->ws to prevent
 		 * triggering auto-suspend here (in case we reactive epi->ws
@@ -1896,21 +1732,30 @@ static int ep_send_events(struct eventpoll *ep,
 			__pm_relax(ws);
 		}
 
-		list_del_init(&epi->rdllink);
-
 		/*
 		 * If the event mask intersect the caller-requested one,
 		 * deliver the event to userspace. Again, we are holding ep->mtx,
 		 * so no operations coming from userspace can change the item.
 		 */
 		revents = ep_item_poll(epi, &pt, 1);
-		if (!revents)
+		if (!revents) {
+			init_llist_node(n);
+
+			/*
+			 * Just in case epi becomes ready after ep_item_poll() above, but before
+			 * init_llist_node(). Make sure to add it to the ready list, otherwise an
+			 * event may be lost.
+			 */
+			if (unlikely(ep_item_poll(epi, &pt, 1))) {
+				ep_pm_stay_awake(epi);
+				epitem_ready(epi);
+			}
 			continue;
+		}
 
 		events = epoll_put_uevent(revents, epi->event.data, events);
 		if (!events) {
-			list_add(&epi->rdllink, &txlist);
-			ep_pm_stay_awake(epi);
+			llist_add(&epi->rdllink, &ep->rdllist);
 			if (!res)
 				res = -EFAULT;
 			break;
@@ -1918,25 +1763,31 @@ static int ep_send_events(struct eventpoll *ep,
 		res++;
 		if (epi->event.events & EPOLLONESHOT)
 			epi->event.events &= EP_PRIVATE_BITS;
-		else if (!(epi->event.events & EPOLLET)) {
+		__llist_add(n, &txlist);
+	}
+
+	llist_for_each_entry_safe(epi, tmp, txlist.first, rdllink) {
+		init_llist_node(&epi->rdllink);
+
+		if (!(epi->event.events & EPOLLET)) {
 			/*
-			 * If this file has been added with Level
-			 * Trigger mode, we need to insert back inside
-			 * the ready list, so that the next call to
-			 * epoll_wait() will check again the events
-			 * availability. At this point, no one can insert
-			 * into ep->rdllist besides us. The epoll_ctl()
-			 * callers are locked out by
-			 * ep_send_events() holding "mtx" and the
-			 * poll callback will queue them in ep->ovflist.
+			 * If this file has been added with Level Trigger mode, we need to insert
+			 * back inside the ready list, so that the next call to epoll_wait() will
+			 * check again the events availability.
 			 */
-			list_add_tail(&epi->rdllink, &ep->rdllist);
 			ep_pm_stay_awake(epi);
+			epitem_ready(epi);
 		}
 	}
-	ep_done_scan(ep, &txlist);
+
+	__pm_relax(ep->ws);
 	mutex_unlock(&ep->mtx);
 
+	if (!llist_empty(&ep->rdllist)) {
+		if (waitqueue_active(&ep->wq))
+			wake_up(&ep->wq);
+	}
+
 	return res;
 }
 
@@ -2029,8 +1880,6 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events,
 	wait_queue_entry_t wait;
 	ktime_t expires, *to = NULL;
 
-	lockdep_assert_irqs_enabled();
-
 	if (timeout && (timeout->tv_sec | timeout->tv_nsec)) {
 		slack = select_estimate_accuracy(timeout);
 		to = &expires;
@@ -2090,54 +1939,15 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events,
 		init_wait(&wait);
 		wait.func = ep_autoremove_wake_function;
 
-		write_lock_irq(&ep->lock);
-		/*
-		 * Barrierless variant, waitqueue_active() is called under
-		 * the same lock on wakeup ep_poll_callback() side, so it
-		 * is safe to avoid an explicit barrier.
-		 */
-		__set_current_state(TASK_INTERRUPTIBLE);
+		prepare_to_wait_exclusive(&ep->wq, &wait, TASK_INTERRUPTIBLE);
 
-		/*
-		 * Do the final check under the lock. ep_start/done_scan()
-		 * plays with two lists (->rdllist and ->ovflist) and there
-		 * is always a race when both lists are empty for short
-		 * period of time although events are pending, so lock is
-		 * important.
-		 */
-		eavail = ep_events_available(ep);
-		if (!eavail)
-			__add_wait_queue_exclusive(&ep->wq, &wait);
-
-		write_unlock_irq(&ep->lock);
-
-		if (!eavail)
+		if (!ep_events_available(ep))
 			timed_out = !ep_schedule_timeout(to) ||
 				!schedule_hrtimeout_range(to, slack,
 							  HRTIMER_MODE_ABS);
-		__set_current_state(TASK_RUNNING);
 
-		/*
-		 * We were woken up, thus go and try to harvest some events.
-		 * If timed out and still on the wait queue, recheck eavail
-		 * carefully under lock, below.
-		 */
-		eavail = 1;
-
-		if (!list_empty_careful(&wait.entry)) {
-			write_lock_irq(&ep->lock);
-			/*
-			 * If the thread timed out and is not on the wait queue,
-			 * it means that the thread was woken up after its
-			 * timeout expired before it could reacquire the lock.
-			 * Thus, when wait.entry is empty, it needs to harvest
-			 * events.
-			 */
-			if (timed_out)
-				eavail = list_empty(&wait.entry);
-			__remove_wait_queue(&ep->wq, &wait);
-			write_unlock_irq(&ep->lock);
-		}
+		finish_wait(&ep->wq, &wait);
+		eavail = ep_events_available(ep);
 	}
 }
 

From da8cf4bd458722d090a788c6e581eeb72695c62f Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Tue, 1 Jul 2025 17:38:36 +0100
Subject: [PATCH 1076/1334] netfs: Fix hang due to missing case in final DIO
 read result collection

When doing a DIO read, if the subrequests we issue fail and cause the
request PAUSE flag to be set to put a pause on subrequest generation, we
may complete collection of the subrequests (possibly discarding them) prior
to the ALL_QUEUED flags being set.

In such a case, netfs_read_collection() doesn't see ALL_QUEUED being set
after netfs_collect_read_results() returns and will just return to the app
(the collector can be seen unpausing the generator in the trace log).

The subrequest generator can then set ALL_QUEUED and the app thread reaches
netfs_wait_for_request().  This causes netfs_collect_in_app() to be called
to see if we're done yet, but there's missing case here.

netfs_collect_in_app() will see that a thread is active and set inactive to
false, but won't see any subrequests in the read stream, and so won't set
need_collect to true.  The function will then just return 0, indicating
that the caller should just sleep until further activity (which won't be
forthcoming) occurs.

Fix this by making netfs_collect_in_app() check to see if an active thread
is complete - i.e. that ALL_QUEUED is set and the subrequests list is empty
- and to skip the sleep return path.  The collector will then be called
which will clear the request IN_PROGRESS flag, allowing the app to
progress.

Fixes: 2b1424cd131c ("netfs: Fix wait/wake to be consistent about the waitqueue used")
Reported-by: Steve French <sfrench@samba.org>
Signed-off-by: David Howells <dhowells@redhat.com>
Link: https://lore.kernel.org/20250701163852.2171681-2-dhowells@redhat.com
Tested-by: Steve French <sfrench@samba.org>
Reviewed-by: Paulo Alcantara <pc@manguebit.org>
cc: linux-cifs@vger.kernel.org
cc: netfs@lists.linux.dev
cc: linux-fsdevel@vger.kernel.org
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/netfs/misc.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/fs/netfs/misc.c b/fs/netfs/misc.c
index 43b67a28a8fa..0a54b1203486 100644
--- a/fs/netfs/misc.c
+++ b/fs/netfs/misc.c
@@ -381,7 +381,7 @@ void netfs_wait_for_in_progress_stream(struct netfs_io_request *rreq,
 static int netfs_collect_in_app(struct netfs_io_request *rreq,
 				bool (*collector)(struct netfs_io_request *rreq))
 {
-	bool need_collect = false, inactive = true;
+	bool need_collect = false, inactive = true, done = true;
 
 	for (int i = 0; i < NR_IO_STREAMS; i++) {
 		struct netfs_io_subrequest *subreq;
@@ -400,9 +400,11 @@ static int netfs_collect_in_app(struct netfs_io_request *rreq,
 			need_collect = true;
 			break;
 		}
+		if (subreq || !test_bit(NETFS_RREQ_ALL_QUEUED, &rreq->flags))
+			done = false;
 	}
 
-	if (!need_collect && !inactive)
+	if (!need_collect && !inactive && !done)
 		return 0; /* Sleep */
 
 	__set_current_state(TASK_RUNNING);

From 9df7b5ebead649b00bf9a53a798e4bf83a1318fd Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Tue, 1 Jul 2025 17:38:37 +0100
Subject: [PATCH 1077/1334] netfs: Fix double put of request

If a netfs request finishes during the pause loop, it will have the ref
that belongs to the IN_PROGRESS flag removed at that point - however, if it
then goes to the final wait loop, that will *also* put the ref because it
sees that the IN_PROGRESS flag is clear and incorrectly assumes that this
happened when it called the collector.

In fact, since IN_PROGRESS is clear, we shouldn't call the collector again
since it's done all the cleanup, such as calling ->ki_complete().

Fix this by making netfs_collect_in_app() just return, indicating that
we're done if IN_PROGRESS is removed.

Fixes: 2b1424cd131c ("netfs: Fix wait/wake to be consistent about the waitqueue used")
Signed-off-by: David Howells <dhowells@redhat.com>
Link: https://lore.kernel.org/20250701163852.2171681-3-dhowells@redhat.com
Tested-by: Steve French <sfrench@samba.org>
Reviewed-by: Paulo Alcantara <pc@manguebit.org>
cc: Steve French <sfrench@samba.org>
cc: netfs@lists.linux.dev
cc: linux-fsdevel@vger.kernel.org
cc: linux-cifs@vger.kernel.org
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/netfs/misc.c              | 5 +++++
 include/trace/events/netfs.h | 1 +
 2 files changed, 6 insertions(+)

diff --git a/fs/netfs/misc.c b/fs/netfs/misc.c
index 0a54b1203486..8cf73b237269 100644
--- a/fs/netfs/misc.c
+++ b/fs/netfs/misc.c
@@ -383,6 +383,11 @@ static int netfs_collect_in_app(struct netfs_io_request *rreq,
 {
 	bool need_collect = false, inactive = true, done = true;
 
+	if (!netfs_check_rreq_in_progress(rreq)) {
+		trace_netfs_rreq(rreq, netfs_rreq_trace_recollect);
+		return 1; /* Done */
+	}
+
 	for (int i = 0; i < NR_IO_STREAMS; i++) {
 		struct netfs_io_subrequest *subreq;
 		struct netfs_io_stream *stream = &rreq->io_streams[i];
diff --git a/include/trace/events/netfs.h b/include/trace/events/netfs.h
index 333d2e38dd2c..ba35dc66e986 100644
--- a/include/trace/events/netfs.h
+++ b/include/trace/events/netfs.h
@@ -56,6 +56,7 @@
 	EM(netfs_rreq_trace_dirty,		"DIRTY  ")	\
 	EM(netfs_rreq_trace_done,		"DONE   ")	\
 	EM(netfs_rreq_trace_free,		"FREE   ")	\
+	EM(netfs_rreq_trace_recollect,		"RECLLCT")	\
 	EM(netfs_rreq_trace_redirty,		"REDIRTY")	\
 	EM(netfs_rreq_trace_resubmit,		"RESUBMT")	\
 	EM(netfs_rreq_trace_set_abandon,	"S-ABNDN")	\

From 1a6d45fec33a03ca681eee125ea96987742a893f Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Tue, 1 Jul 2025 17:38:38 +0100
Subject: [PATCH 1078/1334] netfs: Provide helpers to perform
 NETFS_RREQ_IN_PROGRESS flag wangling

Provide helpers to clear and test the NETFS_RREQ_IN_PROGRESS and to insert
the appropriate barrierage.

Signed-off-by: David Howells <dhowells@redhat.com>
Link: https://lore.kernel.org/20250701163852.2171681-4-dhowells@redhat.com
Tested-by: Steve French <sfrench@samba.org>
Reviewed-by: Paulo Alcantara <pc@manguebit.org>
cc: netfs@lists.linux.dev
cc: linux-fsdevel@vger.kernel.org
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/netfs/internal.h      | 18 ++++++++++++++++++
 fs/netfs/misc.c          | 10 +++++-----
 fs/netfs/read_collect.c  |  4 ++--
 fs/netfs/write_collect.c |  4 ++--
 4 files changed, 27 insertions(+), 9 deletions(-)

diff --git a/fs/netfs/internal.h b/fs/netfs/internal.h
index e2ee9183392b..d6656d2b54ab 100644
--- a/fs/netfs/internal.h
+++ b/fs/netfs/internal.h
@@ -274,6 +274,24 @@ static inline void netfs_wake_rreq_flag(struct netfs_io_request *rreq,
 	}
 }
 
+/*
+ * Test the NETFS_RREQ_IN_PROGRESS flag, inserting an appropriate barrier.
+ */
+static inline bool netfs_check_rreq_in_progress(const struct netfs_io_request *rreq)
+{
+	/* Order read of flags before read of anything else, such as error. */
+	return test_bit_acquire(NETFS_RREQ_IN_PROGRESS, &rreq->flags);
+}
+
+/*
+ * Test the NETFS_SREQ_IN_PROGRESS flag, inserting an appropriate barrier.
+ */
+static inline bool netfs_check_subreq_in_progress(const struct netfs_io_subrequest *subreq)
+{
+	/* Order read of flags before read of anything else, such as error. */
+	return test_bit_acquire(NETFS_SREQ_IN_PROGRESS, &subreq->flags);
+}
+
 /*
  * fscache-cache.c
  */
diff --git a/fs/netfs/misc.c b/fs/netfs/misc.c
index 8cf73b237269..7f31c3cbfe01 100644
--- a/fs/netfs/misc.c
+++ b/fs/netfs/misc.c
@@ -356,14 +356,14 @@ void netfs_wait_for_in_progress_stream(struct netfs_io_request *rreq,
 	DEFINE_WAIT(myself);
 
 	list_for_each_entry(subreq, &stream->subrequests, rreq_link) {
-		if (!test_bit(NETFS_SREQ_IN_PROGRESS, &subreq->flags))
+		if (!netfs_check_subreq_in_progress(subreq))
 			continue;
 
 		trace_netfs_rreq(rreq, netfs_rreq_trace_wait_queue);
 		for (;;) {
 			prepare_to_wait(&rreq->waitq, &myself, TASK_UNINTERRUPTIBLE);
 
-			if (!test_bit(NETFS_SREQ_IN_PROGRESS, &subreq->flags))
+			if (!netfs_check_subreq_in_progress(subreq))
 				break;
 
 			trace_netfs_sreq(subreq, netfs_sreq_trace_wait_for);
@@ -400,7 +400,7 @@ static int netfs_collect_in_app(struct netfs_io_request *rreq,
 						  struct netfs_io_subrequest,
 						  rreq_link);
 		if (subreq &&
-		    (!test_bit(NETFS_SREQ_IN_PROGRESS, &subreq->flags) ||
+		    (!netfs_check_subreq_in_progress(subreq) ||
 		     test_bit(NETFS_SREQ_MADE_PROGRESS, &subreq->flags))) {
 			need_collect = true;
 			break;
@@ -451,7 +451,7 @@ static ssize_t netfs_wait_for_request(struct netfs_io_request *rreq,
 			}
 		}
 
-		if (!test_bit(NETFS_RREQ_IN_PROGRESS, &rreq->flags))
+		if (!netfs_check_rreq_in_progress(rreq))
 			break;
 
 		schedule();
@@ -518,7 +518,7 @@ static void netfs_wait_for_pause(struct netfs_io_request *rreq,
 			}
 		}
 
-		if (!test_bit(NETFS_RREQ_IN_PROGRESS, &rreq->flags) ||
+		if (!netfs_check_rreq_in_progress(rreq) ||
 		    !test_bit(NETFS_RREQ_PAUSE, &rreq->flags))
 			break;
 
diff --git a/fs/netfs/read_collect.c b/fs/netfs/read_collect.c
index 96ee18af28ef..cceed9d629c6 100644
--- a/fs/netfs/read_collect.c
+++ b/fs/netfs/read_collect.c
@@ -218,7 +218,7 @@ reassess:
 			stream->collected_to = front->start;
 		}
 
-		if (test_bit(NETFS_SREQ_IN_PROGRESS, &front->flags))
+		if (netfs_check_subreq_in_progress(front))
 			notes |= HIT_PENDING;
 		smp_rmb(); /* Read counters after IN_PROGRESS flag. */
 		transferred = READ_ONCE(front->transferred);
@@ -445,7 +445,7 @@ void netfs_read_collection_worker(struct work_struct *work)
 	struct netfs_io_request *rreq = container_of(work, struct netfs_io_request, work);
 
 	netfs_see_request(rreq, netfs_rreq_trace_see_work);
-	if (test_bit(NETFS_RREQ_IN_PROGRESS, &rreq->flags)) {
+	if (netfs_check_rreq_in_progress(rreq)) {
 		if (netfs_read_collection(rreq))
 			/* Drop the ref from the IN_PROGRESS flag. */
 			netfs_put_request(rreq, netfs_rreq_trace_put_work_ip);
diff --git a/fs/netfs/write_collect.c b/fs/netfs/write_collect.c
index e2b102ffb768..2ac85a819b71 100644
--- a/fs/netfs/write_collect.c
+++ b/fs/netfs/write_collect.c
@@ -240,7 +240,7 @@ reassess_streams:
 			}
 
 			/* Stall if the front is still undergoing I/O. */
-			if (test_bit(NETFS_SREQ_IN_PROGRESS, &front->flags)) {
+			if (netfs_check_subreq_in_progress(front)) {
 				notes |= HIT_PENDING;
 				break;
 			}
@@ -434,7 +434,7 @@ void netfs_write_collection_worker(struct work_struct *work)
 	struct netfs_io_request *rreq = container_of(work, struct netfs_io_request, work);
 
 	netfs_see_request(rreq, netfs_rreq_trace_see_work);
-	if (test_bit(NETFS_RREQ_IN_PROGRESS, &rreq->flags)) {
+	if (netfs_check_rreq_in_progress(rreq)) {
 		if (netfs_write_collection(rreq))
 			/* Drop the ref from the IN_PROGRESS flag. */
 			netfs_put_request(rreq, netfs_rreq_trace_put_work_ip);

From 09623e3a14c1c5465124350cd227457c2b0fb017 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Tue, 1 Jul 2025 17:38:39 +0100
Subject: [PATCH 1079/1334] netfs: Fix looping in wait functions

netfs_wait_for_request() and netfs_wait_for_pause() can loop forever if
netfs_collect_in_app() returns 2, indicating that it wants to repeat
because the ALL_QUEUED flag isn't yet set and there are no subreqs left
that haven't been collected.

The problem is that, unless collection is offloaded (OFFLOAD_COLLECTION),
we have to return to the application thread to continue and eventually set
ALL_QUEUED after pausing to deal with a retry - but we never get there.

Fix this by inserting checks for the IN_PROGRESS and PAUSE flags as
appropriate before cycling round - and add cond_resched() for good measure.

Fixes: 2b1424cd131c ("netfs: Fix wait/wake to be consistent about the waitqueue used")
Signed-off-by: David Howells <dhowells@redhat.com>
Link: https://lore.kernel.org/20250701163852.2171681-5-dhowells@redhat.com
Tested-by: Steve French <sfrench@samba.org>
Reviewed-by: Paulo Alcantara <pc@manguebit.org>
cc: netfs@lists.linux.dev
cc: linux-fsdevel@vger.kernel.org
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/netfs/misc.c | 15 +++++++++++----
 1 file changed, 11 insertions(+), 4 deletions(-)

diff --git a/fs/netfs/misc.c b/fs/netfs/misc.c
index 7f31c3cbfe01..127a269938bb 100644
--- a/fs/netfs/misc.c
+++ b/fs/netfs/misc.c
@@ -430,8 +430,8 @@ static int netfs_collect_in_app(struct netfs_io_request *rreq,
 /*
  * Wait for a request to complete, successfully or otherwise.
  */
-static ssize_t netfs_wait_for_request(struct netfs_io_request *rreq,
-				      bool (*collector)(struct netfs_io_request *rreq))
+static ssize_t netfs_wait_for_in_progress(struct netfs_io_request *rreq,
+					  bool (*collector)(struct netfs_io_request *rreq))
 {
 	DEFINE_WAIT(myself);
 	ssize_t ret;
@@ -447,6 +447,9 @@ static ssize_t netfs_wait_for_request(struct netfs_io_request *rreq,
 			case 1:
 				goto all_collected;
 			case 2:
+				if (!netfs_check_rreq_in_progress(rreq))
+					break;
+				cond_resched();
 				continue;
 			}
 		}
@@ -485,12 +488,12 @@ all_collected:
 
 ssize_t netfs_wait_for_read(struct netfs_io_request *rreq)
 {
-	return netfs_wait_for_request(rreq, netfs_read_collection);
+	return netfs_wait_for_in_progress(rreq, netfs_read_collection);
 }
 
 ssize_t netfs_wait_for_write(struct netfs_io_request *rreq)
 {
-	return netfs_wait_for_request(rreq, netfs_write_collection);
+	return netfs_wait_for_in_progress(rreq, netfs_write_collection);
 }
 
 /*
@@ -514,6 +517,10 @@ static void netfs_wait_for_pause(struct netfs_io_request *rreq,
 			case 1:
 				goto all_collected;
 			case 2:
+				if (!netfs_check_rreq_in_progress(rreq) ||
+				    !test_bit(NETFS_RREQ_PAUSE, &rreq->flags))
+					break;
+				cond_resched();
 				continue;
 			}
 		}

From 97d8e8e52cb8ab3d7675880a92626d9a4332f7a6 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Tue, 1 Jul 2025 17:38:40 +0100
Subject: [PATCH 1080/1334] netfs: Fix ref leak on inserted extra subreq in
 write retry

The write-retry algorithm will insert extra subrequests into the list if it
can't get sufficient capacity to split the range that needs to be retried
into the sequence of subrequests it currently has (for instance, if the
cifs credit pool has fewer credits available than it did when the range was
originally divided).

However, the allocator furnishes each new subreq with 2 refs and then
another is added for resubmission, causing one to be leaked.

Fix this by replacing the ref-getting line with a neutral trace line.

Fixes: 288ace2f57c9 ("netfs: New writeback implementation")
Signed-off-by: David Howells <dhowells@redhat.com>
Link: https://lore.kernel.org/20250701163852.2171681-6-dhowells@redhat.com
Tested-by: Steve French <sfrench@samba.org>
Reviewed-by: Paulo Alcantara <pc@manguebit.org>
cc: netfs@lists.linux.dev
cc: linux-fsdevel@vger.kernel.org
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/netfs/write_retry.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/netfs/write_retry.c b/fs/netfs/write_retry.c
index 9d1d8a8bab72..7158657061e9 100644
--- a/fs/netfs/write_retry.c
+++ b/fs/netfs/write_retry.c
@@ -153,7 +153,7 @@ static void netfs_retry_write_stream(struct netfs_io_request *wreq,
 			trace_netfs_sreq_ref(wreq->debug_id, subreq->debug_index,
 					     refcount_read(&subreq->ref),
 					     netfs_sreq_trace_new);
-			netfs_get_subrequest(subreq, netfs_sreq_trace_get_resubmit);
+			trace_netfs_sreq(subreq, netfs_sreq_trace_split);
 
 			list_add(&subreq->rreq_link, &to->rreq_link);
 			to = list_next_entry(to, rreq_link);

From e67e75edeb88022c04f8e0a173e1ff6dc688f155 Mon Sep 17 00:00:00 2001
From: Paulo Alcantara <pc@manguebit.org>
Date: Tue, 1 Jul 2025 17:38:41 +0100
Subject: [PATCH 1081/1334] smb: client: set missing retry flag in
 smb2_writev_callback()

Set NETFS_SREQ_NEED_RETRY flag to tell netfslib that the subreq needs
to be retried.

Fixes: ee4cdf7ba857 ("netfs: Speed up buffered reading")
Signed-off-by: Paulo Alcantara (Red Hat) <pc@manguebit.org>
Signed-off-by: David Howells <dhowells@redhat.com>
Link: https://lore.kernel.org/20250701163852.2171681-7-dhowells@redhat.com
Tested-by: Steve French <sfrench@samba.org>
Cc: linux-cifs@vger.kernel.org
Cc: netfs@lists.linux.dev
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/smb/client/smb2pdu.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c
index a717be1626a3..084ee66e73fd 100644
--- a/fs/smb/client/smb2pdu.c
+++ b/fs/smb/client/smb2pdu.c
@@ -4862,6 +4862,7 @@ smb2_writev_callback(struct mid_q_entry *mid)
 		break;
 	case MID_REQUEST_SUBMITTED:
 	case MID_RETRY_NEEDED:
+		__set_bit(NETFS_SREQ_NEED_RETRY, &wdata->subreq.flags);
 		result = -EAGAIN;
 		break;
 	case MID_RESPONSE_MALFORMED:

From 0e60bae24ad28ab06a485698077d3c626f1e54ab Mon Sep 17 00:00:00 2001
From: Paulo Alcantara <pc@manguebit.org>
Date: Tue, 1 Jul 2025 17:38:42 +0100
Subject: [PATCH 1082/1334] smb: client: set missing retry flag in
 cifs_readv_callback()

Set NETFS_SREQ_NEED_RETRY flag to tell netfslib that the subreq needs
to be retried.

Fixes: ee4cdf7ba857 ("netfs: Speed up buffered reading")
Signed-off-by: Paulo Alcantara (Red Hat) <pc@manguebit.org>
Signed-off-by: David Howells <dhowells@redhat.com>
Link: https://lore.kernel.org/20250701163852.2171681-8-dhowells@redhat.com
Tested-by: Steve French <sfrench@samba.org>
Cc: linux-cifs@vger.kernel.org
Cc: netfs@lists.linux.dev
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/smb/client/cifssmb.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/fs/smb/client/cifssmb.c b/fs/smb/client/cifssmb.c
index 7216fcec79e8..f9ccae5de5b8 100644
--- a/fs/smb/client/cifssmb.c
+++ b/fs/smb/client/cifssmb.c
@@ -1335,6 +1335,7 @@ cifs_readv_callback(struct mid_q_entry *mid)
 		break;
 	case MID_REQUEST_SUBMITTED:
 	case MID_RETRY_NEEDED:
+		__set_bit(NETFS_SREQ_NEED_RETRY, &rdata->subreq.flags);
 		rdata->result = -EAGAIN;
 		if (server->sign && rdata->got_bytes)
 			/* reset bytes number since we can not check a sign */

From 74ee76bea4b445c023d04806e0bcd78a912fd30b Mon Sep 17 00:00:00 2001
From: Paulo Alcantara <pc@manguebit.org>
Date: Tue, 1 Jul 2025 17:38:43 +0100
Subject: [PATCH 1083/1334] smb: client: set missing retry flag in
 cifs_writev_callback()

Set NETFS_SREQ_NEED_RETRY flag to tell netfslib that the subreq needs
to be retried.

Fixes: ee4cdf7ba857 ("netfs: Speed up buffered reading")
Signed-off-by: Paulo Alcantara (Red Hat) <pc@manguebit.org>
Signed-off-by: David Howells <dhowells@redhat.com>
Link: https://lore.kernel.org/20250701163852.2171681-9-dhowells@redhat.com
Tested-by: Steve French <sfrench@samba.org>
Cc: linux-cifs@vger.kernel.org
Cc: netfs@lists.linux.dev
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/smb/client/cifssmb.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/fs/smb/client/cifssmb.c b/fs/smb/client/cifssmb.c
index f9ccae5de5b8..0e509a0433fb 100644
--- a/fs/smb/client/cifssmb.c
+++ b/fs/smb/client/cifssmb.c
@@ -1715,6 +1715,7 @@ cifs_writev_callback(struct mid_q_entry *mid)
 		break;
 	case MID_REQUEST_SUBMITTED:
 	case MID_RETRY_NEEDED:
+		__set_bit(NETFS_SREQ_NEED_RETRY, &wdata->subreq.flags);
 		result = -EAGAIN;
 		break;
 	default:

From 2e0658940d90a3dc130bb3b7f75bae9f4100e01f Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Tue, 1 Jul 2025 17:38:45 +0100
Subject: [PATCH 1084/1334] netfs: Fix i_size updating

Fix the updating of i_size, particularly in regard to the completion of DIO
writes and especially async DIO writes by using a lock.

The bug is triggered occasionally by the generic/207 xfstest as it chucks a
bunch of AIO DIO writes at the filesystem and then checks that fstat()
returns a reasonable st_size as each completes.

The problem is that netfs is trying to do "if new_size > inode->i_size,
update inode->i_size" sort of thing but without a lock around it.

This can be seen with cifs, but shouldn't be seen with kafs because kafs
serialises modification ops on the client whereas cifs sends the requests
to the server as they're generated and lets the server order them.

Fixes: 153a9961b551 ("netfs: Implement unbuffered/DIO write support")
Signed-off-by: David Howells <dhowells@redhat.com>
Link: https://lore.kernel.org/20250701163852.2171681-11-dhowells@redhat.com
Reviewed-by: Paulo Alcantara (Red Hat) <pc@manguebit.org>
cc: Steve French <sfrench@samba.org>
cc: Paulo Alcantara <pc@manguebit.org>
cc: linux-cifs@vger.kernel.org
cc: netfs@lists.linux.dev
cc: linux-fsdevel@vger.kernel.org
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/netfs/buffered_write.c | 2 ++
 fs/netfs/direct_write.c   | 8 ++++++--
 2 files changed, 8 insertions(+), 2 deletions(-)

diff --git a/fs/netfs/buffered_write.c b/fs/netfs/buffered_write.c
index 72a3e6db2524..b87ef3fe4ea4 100644
--- a/fs/netfs/buffered_write.c
+++ b/fs/netfs/buffered_write.c
@@ -64,6 +64,7 @@ static void netfs_update_i_size(struct netfs_inode *ctx, struct inode *inode,
 		return;
 	}
 
+	spin_lock(&inode->i_lock);
 	i_size_write(inode, pos);
 #if IS_ENABLED(CONFIG_FSCACHE)
 	fscache_update_cookie(ctx->cache, NULL, &pos);
@@ -77,6 +78,7 @@ static void netfs_update_i_size(struct netfs_inode *ctx, struct inode *inode,
 					DIV_ROUND_UP(pos, SECTOR_SIZE),
 					inode->i_blocks + add);
 	}
+	spin_unlock(&inode->i_lock);
 }
 
 /**
diff --git a/fs/netfs/direct_write.c b/fs/netfs/direct_write.c
index fa9a5bf3c6d5..3efa5894b2c0 100644
--- a/fs/netfs/direct_write.c
+++ b/fs/netfs/direct_write.c
@@ -14,13 +14,17 @@ static void netfs_cleanup_dio_write(struct netfs_io_request *wreq)
 	struct inode *inode = wreq->inode;
 	unsigned long long end = wreq->start + wreq->transferred;
 
-	if (!wreq->error &&
-	    i_size_read(inode) < end) {
+	if (wreq->error || end <= i_size_read(inode))
+		return;
+
+	spin_lock(&inode->i_lock);
+	if (end > i_size_read(inode)) {
 		if (wreq->netfs_ops->update_i_size)
 			wreq->netfs_ops->update_i_size(inode, end);
 		else
 			i_size_write(inode, end);
 	}
+	spin_unlock(&inode->i_lock);
 }
 
 /*

From 5e1e6ec2e346c0850f304c31abdef4158007474e Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Tue, 1 Jul 2025 17:38:46 +0100
Subject: [PATCH 1085/1334] netfs: Merge i_size update functions

Netfslib has two functions for updating the i_size after a write: one for
buffered writes into the pagecache and one for direct/unbuffered writes.
However, what needs to be done is much the same in both cases, so merge
them together.

This does raise one question, though: should updating the i_size after a
direct write do the same estimated update of i_blocks as is done for
buffered writes.

Also get rid of the cleanup function pointer from netfs_io_request as it's
only used for direct write to update i_size; instead do the i_size setting
directly from write collection.

Signed-off-by: David Howells <dhowells@redhat.com>
Link: https://lore.kernel.org/20250701163852.2171681-12-dhowells@redhat.com
cc: Steve French <sfrench@samba.org>
cc: Paulo Alcantara <pc@manguebit.org>
cc: linux-cifs@vger.kernel.org
cc: netfs@lists.linux.dev
cc: linux-fsdevel@vger.kernel.org
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/netfs/buffered_write.c | 36 +++++++++++++++++++++---------------
 fs/netfs/direct_write.c   | 19 -------------------
 fs/netfs/internal.h       |  6 ++++++
 fs/netfs/write_collect.c  |  6 ++++--
 include/linux/netfs.h     |  1 -
 5 files changed, 31 insertions(+), 37 deletions(-)

diff --git a/fs/netfs/buffered_write.c b/fs/netfs/buffered_write.c
index b87ef3fe4ea4..f27ea5099a68 100644
--- a/fs/netfs/buffered_write.c
+++ b/fs/netfs/buffered_write.c
@@ -53,30 +53,38 @@ static struct folio *netfs_grab_folio_for_write(struct address_space *mapping,
  * data written into the pagecache until we can find out from the server what
  * the values actually are.
  */
-static void netfs_update_i_size(struct netfs_inode *ctx, struct inode *inode,
-				loff_t i_size, loff_t pos, size_t copied)
+void netfs_update_i_size(struct netfs_inode *ctx, struct inode *inode,
+			 loff_t pos, size_t copied)
 {
+	loff_t i_size, end = pos + copied;
 	blkcnt_t add;
 	size_t gap;
 
+	if (end <= i_size_read(inode))
+		return;
+
 	if (ctx->ops->update_i_size) {
-		ctx->ops->update_i_size(inode, pos);
+		ctx->ops->update_i_size(inode, end);
 		return;
 	}
 
 	spin_lock(&inode->i_lock);
-	i_size_write(inode, pos);
+
+	i_size = i_size_read(inode);
+	if (end > i_size) {
+		i_size_write(inode, end);
 #if IS_ENABLED(CONFIG_FSCACHE)
-	fscache_update_cookie(ctx->cache, NULL, &pos);
+		fscache_update_cookie(ctx->cache, NULL, &end);
 #endif
 
-	gap = SECTOR_SIZE - (i_size & (SECTOR_SIZE - 1));
-	if (copied > gap) {
-		add = DIV_ROUND_UP(copied - gap, SECTOR_SIZE);
+		gap = SECTOR_SIZE - (i_size & (SECTOR_SIZE - 1));
+		if (copied > gap) {
+			add = DIV_ROUND_UP(copied - gap, SECTOR_SIZE);
 
-		inode->i_blocks = min_t(blkcnt_t,
-					DIV_ROUND_UP(pos, SECTOR_SIZE),
-					inode->i_blocks + add);
+			inode->i_blocks = min_t(blkcnt_t,
+						DIV_ROUND_UP(end, SECTOR_SIZE),
+						inode->i_blocks + add);
+		}
 	}
 	spin_unlock(&inode->i_lock);
 }
@@ -113,7 +121,7 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter,
 	struct folio *folio = NULL, *writethrough = NULL;
 	unsigned int bdp_flags = (iocb->ki_flags & IOCB_NOWAIT) ? BDP_ASYNC : 0;
 	ssize_t written = 0, ret, ret2;
-	loff_t i_size, pos = iocb->ki_pos;
+	loff_t pos = iocb->ki_pos;
 	size_t max_chunk = mapping_max_folio_size(mapping);
 	bool maybe_trouble = false;
 
@@ -346,10 +354,8 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter,
 		flush_dcache_folio(folio);
 
 		/* Update the inode size if we moved the EOF marker */
+		netfs_update_i_size(ctx, inode, pos, copied);
 		pos += copied;
-		i_size = i_size_read(inode);
-		if (pos > i_size)
-			netfs_update_i_size(ctx, inode, i_size, pos, copied);
 		written += copied;
 
 		if (likely(!wreq)) {
diff --git a/fs/netfs/direct_write.c b/fs/netfs/direct_write.c
index 3efa5894b2c0..dcf2b096cc4e 100644
--- a/fs/netfs/direct_write.c
+++ b/fs/netfs/direct_write.c
@@ -9,24 +9,6 @@
 #include <linux/uio.h>
 #include "internal.h"
 
-static void netfs_cleanup_dio_write(struct netfs_io_request *wreq)
-{
-	struct inode *inode = wreq->inode;
-	unsigned long long end = wreq->start + wreq->transferred;
-
-	if (wreq->error || end <= i_size_read(inode))
-		return;
-
-	spin_lock(&inode->i_lock);
-	if (end > i_size_read(inode)) {
-		if (wreq->netfs_ops->update_i_size)
-			wreq->netfs_ops->update_i_size(inode, end);
-		else
-			i_size_write(inode, end);
-	}
-	spin_unlock(&inode->i_lock);
-}
-
 /*
  * Perform an unbuffered write where we may have to do an RMW operation on an
  * encrypted file.  This can also be used for direct I/O writes.
@@ -102,7 +84,6 @@ ssize_t netfs_unbuffered_write_iter_locked(struct kiocb *iocb, struct iov_iter *
 	if (async)
 		wreq->iocb = iocb;
 	wreq->len = iov_iter_count(&wreq->buffer.iter);
-	wreq->cleanup = netfs_cleanup_dio_write;
 	ret = netfs_unbuffered_write(wreq, is_sync_kiocb(iocb), wreq->len);
 	if (ret < 0) {
 		_debug("begin = %zd", ret);
diff --git a/fs/netfs/internal.h b/fs/netfs/internal.h
index d6656d2b54ab..f9bb9464a147 100644
--- a/fs/netfs/internal.h
+++ b/fs/netfs/internal.h
@@ -27,6 +27,12 @@ void netfs_cache_read_terminated(void *priv, ssize_t transferred_or_error);
 int netfs_prefetch_for_write(struct file *file, struct folio *folio,
 			     size_t offset, size_t len);
 
+/*
+ * buffered_write.c
+ */
+void netfs_update_i_size(struct netfs_inode *ctx, struct inode *inode,
+			 loff_t pos, size_t copied);
+
 /*
  * main.c
  */
diff --git a/fs/netfs/write_collect.c b/fs/netfs/write_collect.c
index 2ac85a819b71..33a93258f36e 100644
--- a/fs/netfs/write_collect.c
+++ b/fs/netfs/write_collect.c
@@ -393,8 +393,10 @@ bool netfs_write_collection(struct netfs_io_request *wreq)
 		ictx->ops->invalidate_cache(wreq);
 	}
 
-	if (wreq->cleanup)
-		wreq->cleanup(wreq);
+	if ((wreq->origin == NETFS_UNBUFFERED_WRITE ||
+	     wreq->origin == NETFS_DIO_WRITE) &&
+	    !wreq->error)
+		netfs_update_i_size(ictx, &ictx->inode, wreq->start, wreq->transferred);
 
 	if (wreq->origin == NETFS_DIO_WRITE &&
 	    wreq->mapping->nrpages) {
diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index 065c17385e53..d8186b90fb38 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -279,7 +279,6 @@ struct netfs_io_request {
 #define NETFS_RREQ_USE_PGPRIV2		31	/* [DEPRECATED] Use PG_private_2 to mark
 						 * write to cache on read */
 	const struct netfs_request_ops *netfs_ops;
-	void (*cleanup)(struct netfs_io_request *req);
 };
 
 /*

From 4e32541076833f5ce2e23523c9faa25f7b2cc96f Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Tue, 1 Jul 2025 17:38:47 +0100
Subject: [PATCH 1086/1334] netfs: Renumber the NETFS_RREQ_* flags to make
 traces easier to read

Renumber the NETFS_RREQ_* flags to put the most useful status bits in the
bottom nibble - and therefore the last hex digit in the trace output -
making it easier to grasp the state at a glance.

In particular, put the IN_PROGRESS flag in bit 0 and ALL_QUEUED at bit 1.

Also make the flags field in /proc/fs/netfs/requests larger to accommodate
all the flags.

Also make the flags field in the netfs_sreq tracepoint larger to
accommodate all the NETFS_SREQ_* flags.

Signed-off-by: David Howells <dhowells@redhat.com>
Link: https://lore.kernel.org/20250701163852.2171681-13-dhowells@redhat.com
Reviewed-by: Paulo Alcantara <pc@manguebit.org>
cc: netfs@lists.linux.dev
cc: linux-fsdevel@vger.kernel.org
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/netfs/main.c              |  6 +++---
 include/linux/netfs.h        | 20 ++++++++++----------
 include/trace/events/netfs.h |  2 +-
 3 files changed, 14 insertions(+), 14 deletions(-)

diff --git a/fs/netfs/main.c b/fs/netfs/main.c
index 3db401d269e7..73da6c9f5777 100644
--- a/fs/netfs/main.c
+++ b/fs/netfs/main.c
@@ -58,15 +58,15 @@ static int netfs_requests_seq_show(struct seq_file *m, void *v)
 
 	if (v == &netfs_io_requests) {
 		seq_puts(m,
-			 "REQUEST  OR REF FL ERR  OPS COVERAGE\n"
-			 "======== == === == ==== === =========\n"
+			 "REQUEST  OR REF FLAG ERR  OPS COVERAGE\n"
+			 "======== == === ==== ==== === =========\n"
 			 );
 		return 0;
 	}
 
 	rreq = list_entry(v, struct netfs_io_request, proc_link);
 	seq_printf(m,
-		   "%08x %s %3d %2lx %4ld %3d @%04llx %llx/%llx",
+		   "%08x %s %3d %4lx %4ld %3d @%04llx %llx/%llx",
 		   rreq->debug_id,
 		   netfs_origins[rreq->origin],
 		   refcount_read(&rreq->ref),
diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index d8186b90fb38..f43f075852c0 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -265,17 +265,17 @@ struct netfs_io_request {
 	bool			direct_bv_unpin; /* T if direct_bv[] must be unpinned */
 	refcount_t		ref;
 	unsigned long		flags;
-#define NETFS_RREQ_OFFLOAD_COLLECTION	0	/* Offload collection to workqueue */
-#define NETFS_RREQ_NO_UNLOCK_FOLIO	2	/* Don't unlock no_unlock_folio on completion */
-#define NETFS_RREQ_FAILED		4	/* The request failed */
-#define NETFS_RREQ_IN_PROGRESS		5	/* Unlocked when the request completes (has ref) */
-#define NETFS_RREQ_FOLIO_COPY_TO_CACHE	6	/* Copy current folio to cache from read */
-#define NETFS_RREQ_UPLOAD_TO_SERVER	8	/* Need to write to the server */
-#define NETFS_RREQ_PAUSE		11	/* Pause subrequest generation */
+#define NETFS_RREQ_IN_PROGRESS		0	/* Unlocked when the request completes (has ref) */
+#define NETFS_RREQ_ALL_QUEUED		1	/* All subreqs are now queued */
+#define NETFS_RREQ_PAUSE		2	/* Pause subrequest generation */
+#define NETFS_RREQ_FAILED		3	/* The request failed */
+#define NETFS_RREQ_RETRYING		4	/* Set if we're in the retry path */
+#define NETFS_RREQ_SHORT_TRANSFER	5	/* Set if we have a short transfer */
+#define NETFS_RREQ_OFFLOAD_COLLECTION	8	/* Offload collection to workqueue */
+#define NETFS_RREQ_NO_UNLOCK_FOLIO	9	/* Don't unlock no_unlock_folio on completion */
+#define NETFS_RREQ_FOLIO_COPY_TO_CACHE	10	/* Copy current folio to cache from read */
+#define NETFS_RREQ_UPLOAD_TO_SERVER	11	/* Need to write to the server */
 #define NETFS_RREQ_USE_IO_ITER		12	/* Use ->io_iter rather than ->i_pages */
-#define NETFS_RREQ_ALL_QUEUED		13	/* All subreqs are now queued */
-#define NETFS_RREQ_RETRYING		14	/* Set if we're in the retry path */
-#define NETFS_RREQ_SHORT_TRANSFER	15	/* Set if we have a short transfer */
 #define NETFS_RREQ_USE_PGPRIV2		31	/* [DEPRECATED] Use PG_private_2 to mark
 						 * write to cache on read */
 	const struct netfs_request_ops *netfs_ops;
diff --git a/include/trace/events/netfs.h b/include/trace/events/netfs.h
index ba35dc66e986..c2d581429a7b 100644
--- a/include/trace/events/netfs.h
+++ b/include/trace/events/netfs.h
@@ -367,7 +367,7 @@ TRACE_EVENT(netfs_sreq,
 		    __entry->slot	= sreq->io_iter.folioq_slot;
 			   ),
 
-	    TP_printk("R=%08x[%x] %s %s f=%02x s=%llx %zx/%zx s=%u e=%d",
+	    TP_printk("R=%08x[%x] %s %s f=%03x s=%llx %zx/%zx s=%u e=%d",
 		      __entry->rreq, __entry->index,
 		      __print_symbolic(__entry->source, netfs_sreq_sources),
 		      __print_symbolic(__entry->what, netfs_sreq_traces),

From 90b3ccf514578ca3a6ac25db51a29a48e34e0f1b Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Tue, 1 Jul 2025 17:38:48 +0100
Subject: [PATCH 1087/1334] netfs: Update tracepoints in a number of ways

Make a number of updates to the netfs tracepoints:

 (1) Remove a duplicate trace from netfs_unbuffered_write_iter_locked().

 (2) Move the trace in netfs_wake_rreq_flag() to after the flag is cleared
     so that the change appears in the trace.

 (3) Differentiate the use of netfs_rreq_trace_wait/woke_queue symbols.

 (4) Don't do so many trace emissions in the wait functions as some of them
     are redundant.

 (5) In netfs_collect_read_results(), differentiate a subreq that's being
     abandoned vs one that has been consumed in a regular way.

 (6) Add a tracepoint to indicate the call to ->ki_complete().

 (7) Don't double-increment the subreq_counter when retrying a write.

 (8) Move the netfs_sreq_trace_io_progress tracepoint within cifs code to
     just MID_RESPONSE_RECEIVED and add different tracepoints for other MID
     states and note check failure.

Signed-off-by: David Howells <dhowells@redhat.com>
Co-developed-by: Paulo Alcantara <pc@manguebit.org>
Signed-off-by: Paulo Alcantara <pc@manguebit.org>
Link: https://lore.kernel.org/20250701163852.2171681-14-dhowells@redhat.com
cc: Steve French <sfrench@samba.org>
cc: netfs@lists.linux.dev
cc: linux-fsdevel@vger.kernel.org
cc: linux-cifs@vger.kernel.org
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/netfs/direct_write.c      |  1 -
 fs/netfs/internal.h          |  2 +-
 fs/netfs/misc.c              | 14 ++++++--------
 fs/netfs/read_collect.c      | 12 +++++++++---
 fs/netfs/write_collect.c     |  4 +++-
 fs/netfs/write_retry.c       |  1 -
 fs/smb/client/cifssmb.c      | 24 ++++++++++++++++++++++--
 fs/smb/client/smb2pdu.c      | 28 +++++++++++++++++++++++-----
 include/trace/events/netfs.h | 26 ++++++++++++++++++--------
 9 files changed, 82 insertions(+), 30 deletions(-)

diff --git a/fs/netfs/direct_write.c b/fs/netfs/direct_write.c
index dcf2b096cc4e..a16660ab7f83 100644
--- a/fs/netfs/direct_write.c
+++ b/fs/netfs/direct_write.c
@@ -91,7 +91,6 @@ ssize_t netfs_unbuffered_write_iter_locked(struct kiocb *iocb, struct iov_iter *
 	}
 
 	if (!async) {
-		trace_netfs_rreq(wreq, netfs_rreq_trace_wait_ip);
 		ret = netfs_wait_for_write(wreq);
 		if (ret > 0)
 			iocb->ki_pos += ret;
diff --git a/fs/netfs/internal.h b/fs/netfs/internal.h
index f9bb9464a147..d4f16fefd965 100644
--- a/fs/netfs/internal.h
+++ b/fs/netfs/internal.h
@@ -273,9 +273,9 @@ static inline void netfs_wake_rreq_flag(struct netfs_io_request *rreq,
 					enum netfs_rreq_trace trace)
 {
 	if (test_bit(rreq_flag, &rreq->flags)) {
-		trace_netfs_rreq(rreq, trace);
 		clear_bit_unlock(rreq_flag, &rreq->flags);
 		smp_mb__after_atomic(); /* Set flag before task state */
+		trace_netfs_rreq(rreq, trace);
 		wake_up(&rreq->waitq);
 	}
 }
diff --git a/fs/netfs/misc.c b/fs/netfs/misc.c
index 127a269938bb..20748bcfbf59 100644
--- a/fs/netfs/misc.c
+++ b/fs/netfs/misc.c
@@ -359,7 +359,7 @@ void netfs_wait_for_in_progress_stream(struct netfs_io_request *rreq,
 		if (!netfs_check_subreq_in_progress(subreq))
 			continue;
 
-		trace_netfs_rreq(rreq, netfs_rreq_trace_wait_queue);
+		trace_netfs_rreq(rreq, netfs_rreq_trace_wait_quiesce);
 		for (;;) {
 			prepare_to_wait(&rreq->waitq, &myself, TASK_UNINTERRUPTIBLE);
 
@@ -368,10 +368,10 @@ void netfs_wait_for_in_progress_stream(struct netfs_io_request *rreq,
 
 			trace_netfs_sreq(subreq, netfs_sreq_trace_wait_for);
 			schedule();
-			trace_netfs_rreq(rreq, netfs_rreq_trace_woke_queue);
 		}
 	}
 
+	trace_netfs_rreq(rreq, netfs_rreq_trace_waited_quiesce);
 	finish_wait(&rreq->waitq, &myself);
 }
 
@@ -437,7 +437,6 @@ static ssize_t netfs_wait_for_in_progress(struct netfs_io_request *rreq,
 	ssize_t ret;
 
 	for (;;) {
-		trace_netfs_rreq(rreq, netfs_rreq_trace_wait_queue);
 		prepare_to_wait(&rreq->waitq, &myself, TASK_UNINTERRUPTIBLE);
 
 		if (!test_bit(NETFS_RREQ_OFFLOAD_COLLECTION, &rreq->flags)) {
@@ -457,11 +456,12 @@ static ssize_t netfs_wait_for_in_progress(struct netfs_io_request *rreq,
 		if (!netfs_check_rreq_in_progress(rreq))
 			break;
 
+		trace_netfs_rreq(rreq, netfs_rreq_trace_wait_ip);
 		schedule();
-		trace_netfs_rreq(rreq, netfs_rreq_trace_woke_queue);
 	}
 
 all_collected:
+	trace_netfs_rreq(rreq, netfs_rreq_trace_waited_ip);
 	finish_wait(&rreq->waitq, &myself);
 
 	ret = rreq->error;
@@ -504,10 +504,8 @@ static void netfs_wait_for_pause(struct netfs_io_request *rreq,
 {
 	DEFINE_WAIT(myself);
 
-	trace_netfs_rreq(rreq, netfs_rreq_trace_wait_pause);
-
 	for (;;) {
-		trace_netfs_rreq(rreq, netfs_rreq_trace_wait_queue);
+		trace_netfs_rreq(rreq, netfs_rreq_trace_wait_pause);
 		prepare_to_wait(&rreq->waitq, &myself, TASK_UNINTERRUPTIBLE);
 
 		if (!test_bit(NETFS_RREQ_OFFLOAD_COLLECTION, &rreq->flags)) {
@@ -530,10 +528,10 @@ static void netfs_wait_for_pause(struct netfs_io_request *rreq,
 			break;
 
 		schedule();
-		trace_netfs_rreq(rreq, netfs_rreq_trace_woke_queue);
 	}
 
 all_collected:
+	trace_netfs_rreq(rreq, netfs_rreq_trace_waited_pause);
 	finish_wait(&rreq->waitq, &myself);
 }
 
diff --git a/fs/netfs/read_collect.c b/fs/netfs/read_collect.c
index cceed9d629c6..3e804da1e1eb 100644
--- a/fs/netfs/read_collect.c
+++ b/fs/netfs/read_collect.c
@@ -293,7 +293,9 @@ reassess:
 		spin_lock(&rreq->lock);
 
 		remove = front;
-		trace_netfs_sreq(front, netfs_sreq_trace_discard);
+		trace_netfs_sreq(front,
+				 notes & ABANDON_SREQ ?
+				 netfs_sreq_trace_abandoned : netfs_sreq_trace_consumed);
 		list_del_init(&front->rreq_link);
 		front = list_first_entry_or_null(&stream->subrequests,
 						 struct netfs_io_subrequest, rreq_link);
@@ -353,9 +355,11 @@ static void netfs_rreq_assess_dio(struct netfs_io_request *rreq)
 
 	if (rreq->iocb) {
 		rreq->iocb->ki_pos += rreq->transferred;
-		if (rreq->iocb->ki_complete)
+		if (rreq->iocb->ki_complete) {
+			trace_netfs_rreq(rreq, netfs_rreq_trace_ki_complete);
 			rreq->iocb->ki_complete(
 				rreq->iocb, rreq->error ? rreq->error : rreq->transferred);
+		}
 	}
 	if (rreq->netfs_ops->done)
 		rreq->netfs_ops->done(rreq);
@@ -379,9 +383,11 @@ static void netfs_rreq_assess_single(struct netfs_io_request *rreq)
 
 	if (rreq->iocb) {
 		rreq->iocb->ki_pos += rreq->transferred;
-		if (rreq->iocb->ki_complete)
+		if (rreq->iocb->ki_complete) {
+			trace_netfs_rreq(rreq, netfs_rreq_trace_ki_complete);
 			rreq->iocb->ki_complete(
 				rreq->iocb, rreq->error ? rreq->error : rreq->transferred);
+		}
 	}
 	if (rreq->netfs_ops->done)
 		rreq->netfs_ops->done(rreq);
diff --git a/fs/netfs/write_collect.c b/fs/netfs/write_collect.c
index 33a93258f36e..0f3a36852a4d 100644
--- a/fs/netfs/write_collect.c
+++ b/fs/netfs/write_collect.c
@@ -421,9 +421,11 @@ bool netfs_write_collection(struct netfs_io_request *wreq)
 	if (wreq->iocb) {
 		size_t written = min(wreq->transferred, wreq->len);
 		wreq->iocb->ki_pos += written;
-		if (wreq->iocb->ki_complete)
+		if (wreq->iocb->ki_complete) {
+			trace_netfs_rreq(wreq, netfs_rreq_trace_ki_complete);
 			wreq->iocb->ki_complete(
 				wreq->iocb, wreq->error ? wreq->error : written);
+		}
 		wreq->iocb = VFS_PTR_POISON;
 	}
 
diff --git a/fs/netfs/write_retry.c b/fs/netfs/write_retry.c
index 7158657061e9..fc9c3e0d34d8 100644
--- a/fs/netfs/write_retry.c
+++ b/fs/netfs/write_retry.c
@@ -146,7 +146,6 @@ static void netfs_retry_write_stream(struct netfs_io_request *wreq,
 			subreq = netfs_alloc_subrequest(wreq);
 			subreq->source		= to->source;
 			subreq->start		= start;
-			subreq->debug_index	= atomic_inc_return(&wreq->subreq_counter);
 			subreq->stream_nr	= to->stream_nr;
 			subreq->retry_count	= 1;
 
diff --git a/fs/smb/client/cifssmb.c b/fs/smb/client/cifssmb.c
index 0e509a0433fb..75142f49d65d 100644
--- a/fs/smb/client/cifssmb.c
+++ b/fs/smb/client/cifssmb.c
@@ -1334,7 +1334,11 @@ cifs_readv_callback(struct mid_q_entry *mid)
 		cifs_stats_bytes_read(tcon, rdata->got_bytes);
 		break;
 	case MID_REQUEST_SUBMITTED:
+		trace_netfs_sreq(&rdata->subreq, netfs_sreq_trace_io_req_submitted);
+		goto do_retry;
 	case MID_RETRY_NEEDED:
+		trace_netfs_sreq(&rdata->subreq, netfs_sreq_trace_io_retry_needed);
+do_retry:
 		__set_bit(NETFS_SREQ_NEED_RETRY, &rdata->subreq.flags);
 		rdata->result = -EAGAIN;
 		if (server->sign && rdata->got_bytes)
@@ -1344,8 +1348,14 @@ cifs_readv_callback(struct mid_q_entry *mid)
 		task_io_account_read(rdata->got_bytes);
 		cifs_stats_bytes_read(tcon, rdata->got_bytes);
 		break;
-	default:
+	case MID_RESPONSE_MALFORMED:
+		trace_netfs_sreq(&rdata->subreq, netfs_sreq_trace_io_malformed);
 		rdata->result = -EIO;
+		break;
+	default:
+		trace_netfs_sreq(&rdata->subreq, netfs_sreq_trace_io_unknown);
+		rdata->result = -EIO;
+		break;
 	}
 
 	if (rdata->result == -ENODATA) {
@@ -1714,11 +1724,21 @@ cifs_writev_callback(struct mid_q_entry *mid)
 		}
 		break;
 	case MID_REQUEST_SUBMITTED:
-	case MID_RETRY_NEEDED:
+		trace_netfs_sreq(&wdata->subreq, netfs_sreq_trace_io_req_submitted);
 		__set_bit(NETFS_SREQ_NEED_RETRY, &wdata->subreq.flags);
 		result = -EAGAIN;
 		break;
+	case MID_RETRY_NEEDED:
+		trace_netfs_sreq(&wdata->subreq, netfs_sreq_trace_io_retry_needed);
+		__set_bit(NETFS_SREQ_NEED_RETRY, &wdata->subreq.flags);
+		result = -EAGAIN;
+		break;
+	case MID_RESPONSE_MALFORMED:
+		trace_netfs_sreq(&wdata->subreq, netfs_sreq_trace_io_malformed);
+		result = -EIO;
+		break;
 	default:
+		trace_netfs_sreq(&wdata->subreq, netfs_sreq_trace_io_unknown);
 		result = -EIO;
 		break;
 	}
diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c
index 084ee66e73fd..7f6186c2e60d 100644
--- a/fs/smb/client/smb2pdu.c
+++ b/fs/smb/client/smb2pdu.c
@@ -4567,7 +4567,11 @@ smb2_readv_callback(struct mid_q_entry *mid)
 		cifs_stats_bytes_read(tcon, rdata->got_bytes);
 		break;
 	case MID_REQUEST_SUBMITTED:
+		trace_netfs_sreq(&rdata->subreq, netfs_sreq_trace_io_req_submitted);
+		goto do_retry;
 	case MID_RETRY_NEEDED:
+		trace_netfs_sreq(&rdata->subreq, netfs_sreq_trace_io_retry_needed);
+do_retry:
 		__set_bit(NETFS_SREQ_NEED_RETRY, &rdata->subreq.flags);
 		rdata->result = -EAGAIN;
 		if (server->sign && rdata->got_bytes)
@@ -4578,11 +4582,15 @@ smb2_readv_callback(struct mid_q_entry *mid)
 		cifs_stats_bytes_read(tcon, rdata->got_bytes);
 		break;
 	case MID_RESPONSE_MALFORMED:
+		trace_netfs_sreq(&rdata->subreq, netfs_sreq_trace_io_malformed);
 		credits.value = le16_to_cpu(shdr->CreditRequest);
 		credits.instance = server->reconnect_instance;
-		fallthrough;
-	default:
 		rdata->result = -EIO;
+		break;
+	default:
+		trace_netfs_sreq(&rdata->subreq, netfs_sreq_trace_io_unknown);
+		rdata->result = -EIO;
+		break;
 	}
 #ifdef CONFIG_CIFS_SMB_DIRECT
 	/*
@@ -4835,11 +4843,14 @@ smb2_writev_callback(struct mid_q_entry *mid)
 
 	switch (mid->mid_state) {
 	case MID_RESPONSE_RECEIVED:
+		trace_netfs_sreq(&wdata->subreq, netfs_sreq_trace_io_progress);
 		credits.value = le16_to_cpu(rsp->hdr.CreditRequest);
 		credits.instance = server->reconnect_instance;
 		result = smb2_check_receive(mid, server, 0);
-		if (result != 0)
+		if (result != 0) {
+			trace_netfs_sreq(&wdata->subreq, netfs_sreq_trace_io_bad);
 			break;
+		}
 
 		written = le32_to_cpu(rsp->DataLength);
 		/*
@@ -4861,15 +4872,23 @@ smb2_writev_callback(struct mid_q_entry *mid)
 		}
 		break;
 	case MID_REQUEST_SUBMITTED:
+		trace_netfs_sreq(&wdata->subreq, netfs_sreq_trace_io_req_submitted);
+		__set_bit(NETFS_SREQ_NEED_RETRY, &wdata->subreq.flags);
+		result = -EAGAIN;
+		break;
 	case MID_RETRY_NEEDED:
+		trace_netfs_sreq(&wdata->subreq, netfs_sreq_trace_io_retry_needed);
 		__set_bit(NETFS_SREQ_NEED_RETRY, &wdata->subreq.flags);
 		result = -EAGAIN;
 		break;
 	case MID_RESPONSE_MALFORMED:
+		trace_netfs_sreq(&wdata->subreq, netfs_sreq_trace_io_malformed);
 		credits.value = le16_to_cpu(rsp->hdr.CreditRequest);
 		credits.instance = server->reconnect_instance;
-		fallthrough;
+		result = -EIO;
+		break;
 	default:
+		trace_netfs_sreq(&wdata->subreq, netfs_sreq_trace_io_unknown);
 		result = -EIO;
 		break;
 	}
@@ -4909,7 +4928,6 @@ smb2_writev_callback(struct mid_q_entry *mid)
 			      server->credits, server->in_flight,
 			      0, cifs_trace_rw_credits_write_response_clear);
 	wdata->credits.value = 0;
-	trace_netfs_sreq(&wdata->subreq, netfs_sreq_trace_io_progress);
 	cifs_write_subrequest_terminated(wdata, result ?: written);
 	release_mid(mid);
 	trace_smb3_rw_credits(rreq_debug_id, subreq_debug_index, 0,
diff --git a/include/trace/events/netfs.h b/include/trace/events/netfs.h
index c2d581429a7b..73e96ccbe830 100644
--- a/include/trace/events/netfs.h
+++ b/include/trace/events/netfs.h
@@ -50,12 +50,13 @@
 
 #define netfs_rreq_traces					\
 	EM(netfs_rreq_trace_assess,		"ASSESS ")	\
-	EM(netfs_rreq_trace_copy,		"COPY   ")	\
 	EM(netfs_rreq_trace_collect,		"COLLECT")	\
 	EM(netfs_rreq_trace_complete,		"COMPLET")	\
+	EM(netfs_rreq_trace_copy,		"COPY   ")	\
 	EM(netfs_rreq_trace_dirty,		"DIRTY  ")	\
 	EM(netfs_rreq_trace_done,		"DONE   ")	\
 	EM(netfs_rreq_trace_free,		"FREE   ")	\
+	EM(netfs_rreq_trace_ki_complete,	"KI-CMPL")	\
 	EM(netfs_rreq_trace_recollect,		"RECLLCT")	\
 	EM(netfs_rreq_trace_redirty,		"REDIRTY")	\
 	EM(netfs_rreq_trace_resubmit,		"RESUBMT")	\
@@ -64,13 +65,15 @@
 	EM(netfs_rreq_trace_unlock,		"UNLOCK ")	\
 	EM(netfs_rreq_trace_unlock_pgpriv2,	"UNLCK-2")	\
 	EM(netfs_rreq_trace_unmark,		"UNMARK ")	\
+	EM(netfs_rreq_trace_unpause,		"UNPAUSE")	\
 	EM(netfs_rreq_trace_wait_ip,		"WAIT-IP")	\
-	EM(netfs_rreq_trace_wait_pause,		"WT-PAUS")	\
-	EM(netfs_rreq_trace_wait_queue,		"WAIT-Q ")	\
+	EM(netfs_rreq_trace_wait_pause,		"--PAUSED--")	\
+	EM(netfs_rreq_trace_wait_quiesce,	"WAIT-QUIESCE")	\
+	EM(netfs_rreq_trace_waited_ip,		"DONE-IP")	\
+	EM(netfs_rreq_trace_waited_pause,	"--UNPAUSED--")	\
+	EM(netfs_rreq_trace_waited_quiesce,	"DONE-QUIESCE")	\
 	EM(netfs_rreq_trace_wake_ip,		"WAKE-IP")	\
 	EM(netfs_rreq_trace_wake_queue,		"WAKE-Q ")	\
-	EM(netfs_rreq_trace_woke_queue,		"WOKE-Q ")	\
-	EM(netfs_rreq_trace_unpause,		"UNPAUSE")	\
 	E_(netfs_rreq_trace_write_done,		"WR-DONE")
 
 #define netfs_sreq_sources					\
@@ -83,6 +86,7 @@
 	E_(NETFS_WRITE_TO_CACHE,		"WRIT")
 
 #define netfs_sreq_traces					\
+	EM(netfs_sreq_trace_abandoned,		"ABNDN")	\
 	EM(netfs_sreq_trace_add_donations,	"+DON ")	\
 	EM(netfs_sreq_trace_added,		"ADD  ")	\
 	EM(netfs_sreq_trace_cache_nowrite,	"CA-NW")	\
@@ -90,6 +94,7 @@
 	EM(netfs_sreq_trace_cache_write,	"CA-WR")	\
 	EM(netfs_sreq_trace_cancel,		"CANCL")	\
 	EM(netfs_sreq_trace_clear,		"CLEAR")	\
+	EM(netfs_sreq_trace_consumed,		"CONSM")	\
 	EM(netfs_sreq_trace_discard,		"DSCRD")	\
 	EM(netfs_sreq_trace_donate_to_prev,	"DON-P")	\
 	EM(netfs_sreq_trace_donate_to_next,	"DON-N")	\
@@ -97,7 +102,12 @@
 	EM(netfs_sreq_trace_fail,		"FAIL ")	\
 	EM(netfs_sreq_trace_free,		"FREE ")	\
 	EM(netfs_sreq_trace_hit_eof,		"EOF  ")	\
-	EM(netfs_sreq_trace_io_progress,	"IO   ")	\
+	EM(netfs_sreq_trace_io_bad,		"I-BAD")	\
+	EM(netfs_sreq_trace_io_malformed,	"I-MLF")	\
+	EM(netfs_sreq_trace_io_unknown,		"I-UNK")	\
+	EM(netfs_sreq_trace_io_progress,	"I-OK ")	\
+	EM(netfs_sreq_trace_io_req_submitted,	"I-RSB")	\
+	EM(netfs_sreq_trace_io_retry_needed,	"I-RTR")	\
 	EM(netfs_sreq_trace_limited,		"LIMIT")	\
 	EM(netfs_sreq_trace_need_clear,		"N-CLR")	\
 	EM(netfs_sreq_trace_partial_read,	"PARTR")	\
@@ -143,8 +153,8 @@
 
 #define netfs_sreq_ref_traces					\
 	EM(netfs_sreq_trace_get_copy_to_cache,	"GET COPY2C ")	\
-	EM(netfs_sreq_trace_get_resubmit,	"GET RESUBMIT")	\
-	EM(netfs_sreq_trace_get_submit,		"GET SUBMIT")	\
+	EM(netfs_sreq_trace_get_resubmit,	"GET RESUBMT")	\
+	EM(netfs_sreq_trace_get_submit,		"GET SUBMIT ")	\
 	EM(netfs_sreq_trace_get_short_read,	"GET SHORTRD")	\
 	EM(netfs_sreq_trace_new,		"NEW        ")	\
 	EM(netfs_sreq_trace_put_abandon,	"PUT ABANDON")	\

From afcad92411772a1f361339f22c49f855c6cc7d0f Mon Sep 17 00:00:00 2001
From: Matthew Brost <matthew.brost@intel.com>
Date: Wed, 11 Jun 2025 20:19:25 -0700
Subject: [PATCH 1088/1334] drm/xe: Make WA BB part of LRC BO

No idea why, but without this GuC context switches randomly fail when
running IGTs in a loop. Need to follow up why this fixes the
aforementioned issue but can live with a stable driver for now.

Fixes: 617d824c5323 ("drm/xe: Add WA BB to capture active context utilization")
Cc: stable@vger.kernel.org
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Tested-by: Shuicheng Lin <shuicheng.lin@intel.com>
Link: https://lore.kernel.org/r/20250612031925.4009701-1-matthew.brost@intel.com
(cherry picked from commit 3a1edef8f4b58b0ba826bc68bf4bce4bdf59ecf3)
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
---
 drivers/gpu/drm/xe/xe_lrc.c       | 37 ++++++++++++++++---------------
 drivers/gpu/drm/xe/xe_lrc_types.h |  3 ---
 2 files changed, 19 insertions(+), 21 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_lrc.c b/drivers/gpu/drm/xe/xe_lrc.c
index bf7c3981897d..6e7b70532d11 100644
--- a/drivers/gpu/drm/xe/xe_lrc.c
+++ b/drivers/gpu/drm/xe/xe_lrc.c
@@ -40,6 +40,7 @@
 
 #define LRC_PPHWSP_SIZE				SZ_4K
 #define LRC_INDIRECT_RING_STATE_SIZE		SZ_4K
+#define LRC_WA_BB_SIZE				SZ_4K
 
 static struct xe_device *
 lrc_to_xe(struct xe_lrc *lrc)
@@ -910,7 +911,11 @@ static void xe_lrc_finish(struct xe_lrc *lrc)
 {
 	xe_hw_fence_ctx_finish(&lrc->fence_ctx);
 	xe_bo_unpin_map_no_vm(lrc->bo);
-	xe_bo_unpin_map_no_vm(lrc->bb_per_ctx_bo);
+}
+
+static size_t wa_bb_offset(struct xe_lrc *lrc)
+{
+	return lrc->bo->size - LRC_WA_BB_SIZE;
 }
 
 /*
@@ -943,15 +948,16 @@ static void xe_lrc_finish(struct xe_lrc *lrc)
 #define CONTEXT_ACTIVE 1ULL
 static int xe_lrc_setup_utilization(struct xe_lrc *lrc)
 {
+	const size_t max_size = LRC_WA_BB_SIZE;
 	u32 *cmd, *buf = NULL;
 
-	if (lrc->bb_per_ctx_bo->vmap.is_iomem) {
-		buf = kmalloc(lrc->bb_per_ctx_bo->size, GFP_KERNEL);
+	if (lrc->bo->vmap.is_iomem) {
+		buf = kmalloc(max_size, GFP_KERNEL);
 		if (!buf)
 			return -ENOMEM;
 		cmd = buf;
 	} else {
-		cmd = lrc->bb_per_ctx_bo->vmap.vaddr;
+		cmd = lrc->bo->vmap.vaddr + wa_bb_offset(lrc);
 	}
 
 	*cmd++ = MI_STORE_REGISTER_MEM | MI_SRM_USE_GGTT | MI_SRM_ADD_CS_OFFSET;
@@ -974,13 +980,14 @@ static int xe_lrc_setup_utilization(struct xe_lrc *lrc)
 	*cmd++ = MI_BATCH_BUFFER_END;
 
 	if (buf) {
-		xe_map_memcpy_to(gt_to_xe(lrc->gt), &lrc->bb_per_ctx_bo->vmap, 0,
-				 buf, (cmd - buf) * sizeof(*cmd));
+		xe_map_memcpy_to(gt_to_xe(lrc->gt), &lrc->bo->vmap,
+				 wa_bb_offset(lrc), buf,
+				 (cmd - buf) * sizeof(*cmd));
 		kfree(buf);
 	}
 
-	xe_lrc_write_ctx_reg(lrc, CTX_BB_PER_CTX_PTR,
-			     xe_bo_ggtt_addr(lrc->bb_per_ctx_bo) | 1);
+	xe_lrc_write_ctx_reg(lrc, CTX_BB_PER_CTX_PTR, xe_bo_ggtt_addr(lrc->bo) +
+			     wa_bb_offset(lrc) + 1);
 
 	return 0;
 }
@@ -1018,20 +1025,13 @@ static int xe_lrc_init(struct xe_lrc *lrc, struct xe_hw_engine *hwe,
 	 * FIXME: Perma-pinning LRC as we don't yet support moving GGTT address
 	 * via VM bind calls.
 	 */
-	lrc->bo = xe_bo_create_pin_map(xe, tile, NULL, lrc_size,
+	lrc->bo = xe_bo_create_pin_map(xe, tile, NULL,
+				       lrc_size + LRC_WA_BB_SIZE,
 				       ttm_bo_type_kernel,
 				       bo_flags);
 	if (IS_ERR(lrc->bo))
 		return PTR_ERR(lrc->bo);
 
-	lrc->bb_per_ctx_bo = xe_bo_create_pin_map(xe, tile, NULL, SZ_4K,
-						  ttm_bo_type_kernel,
-						  bo_flags);
-	if (IS_ERR(lrc->bb_per_ctx_bo)) {
-		err = PTR_ERR(lrc->bb_per_ctx_bo);
-		goto err_lrc_finish;
-	}
-
 	lrc->size = lrc_size;
 	lrc->ring.size = ring_size;
 	lrc->ring.tail = 0;
@@ -1819,7 +1819,8 @@ struct xe_lrc_snapshot *xe_lrc_snapshot_capture(struct xe_lrc *lrc)
 	snapshot->seqno = xe_lrc_seqno(lrc);
 	snapshot->lrc_bo = xe_bo_get(lrc->bo);
 	snapshot->lrc_offset = xe_lrc_pphwsp_offset(lrc);
-	snapshot->lrc_size = lrc->bo->size - snapshot->lrc_offset;
+	snapshot->lrc_size = lrc->bo->size - snapshot->lrc_offset -
+		LRC_WA_BB_SIZE;
 	snapshot->lrc_snapshot = NULL;
 	snapshot->ctx_timestamp = lower_32_bits(xe_lrc_ctx_timestamp(lrc));
 	snapshot->ctx_job_timestamp = xe_lrc_ctx_job_timestamp(lrc);
diff --git a/drivers/gpu/drm/xe/xe_lrc_types.h b/drivers/gpu/drm/xe/xe_lrc_types.h
index ae24cf6f8dd9..883e550a9423 100644
--- a/drivers/gpu/drm/xe/xe_lrc_types.h
+++ b/drivers/gpu/drm/xe/xe_lrc_types.h
@@ -53,9 +53,6 @@ struct xe_lrc {
 
 	/** @ctx_timestamp: readout value of CTX_TIMESTAMP on last update */
 	u64 ctx_timestamp;
-
-	/** @bb_per_ctx_bo: buffer object for per context batch wa buffer */
-	struct xe_bo *bb_per_ctx_bo;
 };
 
 struct xe_lrc_snapshot;

From d8390768dcf6f5a78af56aa03797a076871b01f3 Mon Sep 17 00:00:00 2001
From: Lucas De Marchi <lucas.demarchi@intel.com>
Date: Wed, 18 Jun 2025 11:49:58 -0700
Subject: [PATCH 1089/1334] drm/xe/guc_pc: Add _locked variant for min/max freq

There are places in which the getters/setters are called one after the
other causing a multiple lock()/unlock(). These are not currently a
problem since they are all happening from the same thread, but there's a
race possibility as calls are added outside of the early init when the
max/min and stashed values need to be correlated.

Add the _locked() variants to prepare for that.

Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://lore.kernel.org/r/20250618-wa-22019338487-v5-1-b888388477f2@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
(cherry picked from commit 1beae9aa2b88d3a02eb666e7b777eb2d7bc645f4)
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
---
 drivers/gpu/drm/xe/xe_guc_pc.c | 123 ++++++++++++++++++---------------
 1 file changed, 69 insertions(+), 54 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_guc_pc.c b/drivers/gpu/drm/xe/xe_guc_pc.c
index 3beaaa7b25c1..2d9663acf2f2 100644
--- a/drivers/gpu/drm/xe/xe_guc_pc.c
+++ b/drivers/gpu/drm/xe/xe_guc_pc.c
@@ -5,6 +5,7 @@
 
 #include "xe_guc_pc.h"
 
+#include <linux/cleanup.h>
 #include <linux/delay.h>
 #include <linux/ktime.h>
 
@@ -553,6 +554,25 @@ u32 xe_guc_pc_get_rpn_freq(struct xe_guc_pc *pc)
 	return pc->rpn_freq;
 }
 
+static int xe_guc_pc_get_min_freq_locked(struct xe_guc_pc *pc, u32 *freq)
+{
+	int ret;
+
+	lockdep_assert_held(&pc->freq_lock);
+
+	/* Might be in the middle of a gt reset */
+	if (!pc->freq_ready)
+		return -EAGAIN;
+
+	ret = pc_action_query_task_state(pc);
+	if (ret)
+		return ret;
+
+	*freq = pc_get_min_freq(pc);
+
+	return 0;
+}
+
 /**
  * xe_guc_pc_get_min_freq - Get the min operational frequency
  * @pc: The GuC PC
@@ -562,27 +582,29 @@ u32 xe_guc_pc_get_rpn_freq(struct xe_guc_pc *pc)
  *         -EAGAIN if GuC PC not ready (likely in middle of a reset).
  */
 int xe_guc_pc_get_min_freq(struct xe_guc_pc *pc, u32 *freq)
+{
+	guard(mutex)(&pc->freq_lock);
+
+	return xe_guc_pc_get_min_freq_locked(pc, freq);
+}
+
+static int xe_guc_pc_set_min_freq_locked(struct xe_guc_pc *pc, u32 freq)
 {
 	int ret;
 
-	xe_device_assert_mem_access(pc_to_xe(pc));
+	lockdep_assert_held(&pc->freq_lock);
 
-	mutex_lock(&pc->freq_lock);
-	if (!pc->freq_ready) {
-		/* Might be in the middle of a gt reset */
-		ret = -EAGAIN;
-		goto out;
-	}
+	/* Might be in the middle of a gt reset */
+	if (!pc->freq_ready)
+		return -EAGAIN;
 
-	ret = pc_action_query_task_state(pc);
+	ret = pc_set_min_freq(pc, freq);
 	if (ret)
-		goto out;
+		return ret;
 
-	*freq = pc_get_min_freq(pc);
+	pc->user_requested_min = freq;
 
-out:
-	mutex_unlock(&pc->freq_lock);
-	return ret;
+	return 0;
 }
 
 /**
@@ -595,25 +617,29 @@ out:
  *         -EINVAL if value out of bounds.
  */
 int xe_guc_pc_set_min_freq(struct xe_guc_pc *pc, u32 freq)
+{
+	guard(mutex)(&pc->freq_lock);
+
+	return xe_guc_pc_set_min_freq_locked(pc, freq);
+}
+
+static int xe_guc_pc_get_max_freq_locked(struct xe_guc_pc *pc, u32 *freq)
 {
 	int ret;
 
-	mutex_lock(&pc->freq_lock);
-	if (!pc->freq_ready) {
-		/* Might be in the middle of a gt reset */
-		ret = -EAGAIN;
-		goto out;
-	}
+	lockdep_assert_held(&pc->freq_lock);
 
-	ret = pc_set_min_freq(pc, freq);
+	/* Might be in the middle of a gt reset */
+	if (!pc->freq_ready)
+		return -EAGAIN;
+
+	ret = pc_action_query_task_state(pc);
 	if (ret)
-		goto out;
+		return ret;
 
-	pc->user_requested_min = freq;
+	*freq = pc_get_max_freq(pc);
 
-out:
-	mutex_unlock(&pc->freq_lock);
-	return ret;
+	return 0;
 }
 
 /**
@@ -625,25 +651,29 @@ out:
  *         -EAGAIN if GuC PC not ready (likely in middle of a reset).
  */
 int xe_guc_pc_get_max_freq(struct xe_guc_pc *pc, u32 *freq)
+{
+	guard(mutex)(&pc->freq_lock);
+
+	return xe_guc_pc_get_max_freq_locked(pc, freq);
+}
+
+static int xe_guc_pc_set_max_freq_locked(struct xe_guc_pc *pc, u32 freq)
 {
 	int ret;
 
-	mutex_lock(&pc->freq_lock);
-	if (!pc->freq_ready) {
-		/* Might be in the middle of a gt reset */
-		ret = -EAGAIN;
-		goto out;
-	}
+	lockdep_assert_held(&pc->freq_lock);
 
-	ret = pc_action_query_task_state(pc);
+	/* Might be in the middle of a gt reset */
+	if (!pc->freq_ready)
+		return -EAGAIN;
+
+	ret = pc_set_max_freq(pc, freq);
 	if (ret)
-		goto out;
+		return ret;
 
-	*freq = pc_get_max_freq(pc);
+	pc->user_requested_max = freq;
 
-out:
-	mutex_unlock(&pc->freq_lock);
-	return ret;
+	return 0;
 }
 
 /**
@@ -657,24 +687,9 @@ out:
  */
 int xe_guc_pc_set_max_freq(struct xe_guc_pc *pc, u32 freq)
 {
-	int ret;
+	guard(mutex)(&pc->freq_lock);
 
-	mutex_lock(&pc->freq_lock);
-	if (!pc->freq_ready) {
-		/* Might be in the middle of a gt reset */
-		ret = -EAGAIN;
-		goto out;
-	}
-
-	ret = pc_set_max_freq(pc, freq);
-	if (ret)
-		goto out;
-
-	pc->user_requested_max = freq;
-
-out:
-	mutex_unlock(&pc->freq_lock);
-	return ret;
+	return xe_guc_pc_set_max_freq_locked(pc, freq);
 }
 
 /**

From 4cec9099b93a63eb0b1e8cbbe6419fdaeb72e09b Mon Sep 17 00:00:00 2001
From: Lucas De Marchi <lucas.demarchi@intel.com>
Date: Wed, 18 Jun 2025 11:49:59 -0700
Subject: [PATCH 1090/1334] drm/xe/xe_guc_pc: Lock once to update stashed
 frequencies

pc_set_mert_freq_cap() currently lock()/unlock() the mutex multiple times
to stash the current frequencies. It's not a problem since
xe_guc_pc_restore_stashed_freq() is guaranteed to be called only later
in the init sequence. However, now that we have _locked() variants for
this functions, use them and avoid potential issues when called from
other places or using the same pattern.

While at it, prefer and early return for the WA check to reduce
indentation.

Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://lore.kernel.org/r/20250618-wa-22019338487-v5-2-b888388477f2@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
(cherry picked from commit d878c97daa603573e5af01fd8beec2fffdb42ad1)
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
---
 drivers/gpu/drm/xe/xe_guc_pc.c | 39 +++++++++++++++++-----------------
 1 file changed, 20 insertions(+), 19 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_guc_pc.c b/drivers/gpu/drm/xe/xe_guc_pc.c
index 2d9663acf2f2..9f029acbd257 100644
--- a/drivers/gpu/drm/xe/xe_guc_pc.c
+++ b/drivers/gpu/drm/xe/xe_guc_pc.c
@@ -885,27 +885,28 @@ static int pc_adjust_requested_freq(struct xe_guc_pc *pc)
 
 static int pc_set_mert_freq_cap(struct xe_guc_pc *pc)
 {
-	int ret = 0;
+	int ret;
 
-	if (XE_WA(pc_to_gt(pc), 22019338487)) {
-		/*
-		 * Get updated min/max and stash them.
-		 */
-		ret = xe_guc_pc_get_min_freq(pc, &pc->stashed_min_freq);
-		if (!ret)
-			ret = xe_guc_pc_get_max_freq(pc, &pc->stashed_max_freq);
-		if (ret)
-			return ret;
+	if (!XE_WA(pc_to_gt(pc), 22019338487))
+		return 0;
 
-		/*
-		 * Ensure min and max are bound by MERT_FREQ_CAP until driver loads.
-		 */
-		mutex_lock(&pc->freq_lock);
-		ret = pc_set_min_freq(pc, min(pc->rpe_freq, pc_max_freq_cap(pc)));
-		if (!ret)
-			ret = pc_set_max_freq(pc, min(pc->rp0_freq, pc_max_freq_cap(pc)));
-		mutex_unlock(&pc->freq_lock);
-	}
+	guard(mutex)(&pc->freq_lock);
+
+	/*
+	 * Get updated min/max and stash them.
+	 */
+	ret = xe_guc_pc_get_min_freq_locked(pc, &pc->stashed_min_freq);
+	if (!ret)
+		ret = xe_guc_pc_get_max_freq_locked(pc, &pc->stashed_max_freq);
+	if (ret)
+		return ret;
+
+	/*
+	 * Ensure min and max are bound by MERT_FREQ_CAP until driver loads.
+	 */
+	ret = pc_set_min_freq(pc, min(pc->rpe_freq, pc_max_freq_cap(pc)));
+	if (!ret)
+		ret = pc_set_max_freq(pc, min(pc->rp0_freq, pc_max_freq_cap(pc)));
 
 	return ret;
 }

From a1eec6cae95a1a0888cb8370338822ca81cd9436 Mon Sep 17 00:00:00 2001
From: Lucas De Marchi <lucas.demarchi@intel.com>
Date: Wed, 18 Jun 2025 11:50:00 -0700
Subject: [PATCH 1091/1334] drm/xe: Split xe_device_td_flush()

xe_device_td_flush() has 2 possible implementations: an entire L2 flush
or a transient flush, depending on WA 16023588340. Make this clear by
splitting the function so it calls each of them.

Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://lore.kernel.org/r/20250618-wa-22019338487-v5-3-b888388477f2@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
(cherry picked from commit 5e300ed8a545bdffc26b579c526b5fef7b2d5365)
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
---
 drivers/gpu/drm/xe/xe_device.c | 68 ++++++++++++++++++++--------------
 1 file changed, 40 insertions(+), 28 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c
index c02c4c4e9412..a798914644fb 100644
--- a/drivers/gpu/drm/xe/xe_device.c
+++ b/drivers/gpu/drm/xe/xe_device.c
@@ -986,38 +986,15 @@ void xe_device_wmb(struct xe_device *xe)
 		xe_mmio_write32(xe_root_tile_mmio(xe), VF_CAP_REG, 0);
 }
 
-/**
- * xe_device_td_flush() - Flush transient L3 cache entries
- * @xe: The device
- *
- * Display engine has direct access to memory and is never coherent with L3/L4
- * caches (or CPU caches), however KMD is responsible for specifically flushing
- * transient L3 GPU cache entries prior to the flip sequence to ensure scanout
- * can happen from such a surface without seeing corruption.
- *
- * Display surfaces can be tagged as transient by mapping it using one of the
- * various L3:XD PAT index modes on Xe2.
- *
- * Note: On non-discrete xe2 platforms, like LNL, the entire L3 cache is flushed
- * at the end of each submission via PIPE_CONTROL for compute/render, since SA
- * Media is not coherent with L3 and we want to support render-vs-media
- * usescases. For other engines like copy/blt the HW internally forces uncached
- * behaviour, hence why we can skip the TDF on such platforms.
+/*
+ * Issue a TRANSIENT_FLUSH_REQUEST and wait for completion on each gt.
  */
-void xe_device_td_flush(struct xe_device *xe)
+static void tdf_request_sync(struct xe_device *xe)
 {
-	struct xe_gt *gt;
 	unsigned int fw_ref;
+	struct xe_gt *gt;
 	u8 id;
 
-	if (!IS_DGFX(xe) || GRAPHICS_VER(xe) < 20)
-		return;
-
-	if (XE_WA(xe_root_mmio_gt(xe), 16023588340)) {
-		xe_device_l2_flush(xe);
-		return;
-	}
-
 	for_each_gt(gt, xe, id) {
 		if (xe_gt_is_media_type(gt))
 			continue;
@@ -1027,6 +1004,7 @@ void xe_device_td_flush(struct xe_device *xe)
 			return;
 
 		xe_mmio_write32(&gt->mmio, XE2_TDF_CTRL, TRANSIENT_FLUSH_REQUEST);
+
 		/*
 		 * FIXME: We can likely do better here with our choice of
 		 * timeout. Currently we just assume the worst case, i.e. 150us,
@@ -1057,15 +1035,49 @@ void xe_device_l2_flush(struct xe_device *xe)
 		return;
 
 	spin_lock(&gt->global_invl_lock);
-	xe_mmio_write32(&gt->mmio, XE2_GLOBAL_INVAL, 0x1);
 
+	xe_mmio_write32(&gt->mmio, XE2_GLOBAL_INVAL, 0x1);
 	if (xe_mmio_wait32(&gt->mmio, XE2_GLOBAL_INVAL, 0x1, 0x0, 500, NULL, true))
 		xe_gt_err_once(gt, "Global invalidation timeout\n");
+
 	spin_unlock(&gt->global_invl_lock);
 
 	xe_force_wake_put(gt_to_fw(gt), fw_ref);
 }
 
+/**
+ * xe_device_td_flush() - Flush transient L3 cache entries
+ * @xe: The device
+ *
+ * Display engine has direct access to memory and is never coherent with L3/L4
+ * caches (or CPU caches), however KMD is responsible for specifically flushing
+ * transient L3 GPU cache entries prior to the flip sequence to ensure scanout
+ * can happen from such a surface without seeing corruption.
+ *
+ * Display surfaces can be tagged as transient by mapping it using one of the
+ * various L3:XD PAT index modes on Xe2.
+ *
+ * Note: On non-discrete xe2 platforms, like LNL, the entire L3 cache is flushed
+ * at the end of each submission via PIPE_CONTROL for compute/render, since SA
+ * Media is not coherent with L3 and we want to support render-vs-media
+ * usescases. For other engines like copy/blt the HW internally forces uncached
+ * behaviour, hence why we can skip the TDF on such platforms.
+ */
+void xe_device_td_flush(struct xe_device *xe)
+{
+	struct xe_gt *root_gt;
+
+	if (!IS_DGFX(xe) || GRAPHICS_VER(xe) < 20)
+		return;
+
+	root_gt = xe_root_mmio_gt(xe);
+	if (XE_WA(root_gt, 16023588340))
+		/* A transient flush is not sufficient: flush the L2 */
+		xe_device_l2_flush(xe);
+	else
+		tdf_request_sync(xe);
+}
+
 u32 xe_device_ccs_bytes(struct xe_device *xe, u64 size)
 {
 	return xe_device_has_flat_ccs(xe) ?

From a5c7dcdd969f2248cc91d65e5ac852859fc8dac2 Mon Sep 17 00:00:00 2001
From: Vinay Belgaumkar <vinay.belgaumkar@intel.com>
Date: Thu, 12 Jun 2025 00:09:02 -0700
Subject: [PATCH 1092/1334] drm/xe/bmg: Update Wa_14022085890

Set GT min frequency to 1200Mhz once driver load is complete.

v2: Review comments (Rodrigo)
v3: Apply Wa earlier so user_req_min is not clobbered.
v4: Apply to all GTs (Lucas)

Cc: Matt Roper <matthew.d.roper@intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Vinay Belgaumkar <vinay.belgaumkar@intel.com>
Reviewed-by: Stuart Summers <stuart.summers@intel.com>
Link: https://lore.kernel.org/r/20250612-wa-14022085890-v4-3-94ba5dcc1e30@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
(cherry picked from commit bdde16c9ac5cb56ad2ee19792222fa1853577af7)
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
---
 drivers/gpu/drm/xe/xe_guc_pc.c     | 5 +++++
 drivers/gpu/drm/xe/xe_wa_oob.rules | 4 ++++
 2 files changed, 9 insertions(+)

diff --git a/drivers/gpu/drm/xe/xe_guc_pc.c b/drivers/gpu/drm/xe/xe_guc_pc.c
index 9f029acbd257..9d9d0e815fea 100644
--- a/drivers/gpu/drm/xe/xe_guc_pc.c
+++ b/drivers/gpu/drm/xe/xe_guc_pc.c
@@ -52,6 +52,7 @@
 
 #define LNL_MERT_FREQ_CAP	800
 #define BMG_MERT_FREQ_CAP	2133
+#define BMG_MIN_FREQ		1200
 
 #define SLPC_RESET_TIMEOUT_MS 5 /* roughly 5ms, but no need for precision */
 #define SLPC_RESET_EXTENDED_TIMEOUT_MS 1000 /* To be used only at pc_start */
@@ -832,6 +833,7 @@ void xe_guc_pc_init_early(struct xe_guc_pc *pc)
 
 static int pc_adjust_freq_bounds(struct xe_guc_pc *pc)
 {
+	struct xe_tile *tile = gt_to_tile(pc_to_gt(pc));
 	int ret;
 
 	lockdep_assert_held(&pc->freq_lock);
@@ -858,6 +860,9 @@ static int pc_adjust_freq_bounds(struct xe_guc_pc *pc)
 	if (pc_get_min_freq(pc) > pc->rp0_freq)
 		ret = pc_set_min_freq(pc, pc->rp0_freq);
 
+	if (XE_WA(tile->primary_gt, 14022085890))
+		ret = pc_set_min_freq(pc, max(BMG_MIN_FREQ, pc_get_min_freq(pc)));
+
 out:
 	return ret;
 }
diff --git a/drivers/gpu/drm/xe/xe_wa_oob.rules b/drivers/gpu/drm/xe/xe_wa_oob.rules
index 9efc5accd43d..320766f6c5df 100644
--- a/drivers/gpu/drm/xe/xe_wa_oob.rules
+++ b/drivers/gpu/drm/xe/xe_wa_oob.rules
@@ -59,3 +59,7 @@ no_media_l3	MEDIA_VERSION(3000)
 		MEDIA_VERSION_RANGE(1301, 3000)
 16026508708	GRAPHICS_VERSION_RANGE(1200, 3001)
 		MEDIA_VERSION_RANGE(1300, 3000)
+
+# SoC workaround - currently applies to all platforms with the following
+# primary GT GMDID
+14022085890	GRAPHICS_VERSION(2001)

From 84c0b4a00610afbde650fdb8ad6db0424f7b2cc3 Mon Sep 17 00:00:00 2001
From: Vinay Belgaumkar <vinay.belgaumkar@intel.com>
Date: Wed, 18 Jun 2025 11:50:01 -0700
Subject: [PATCH 1093/1334] drm/xe/bmg: Update Wa_22019338487

Limit GT max frequency to 2600MHz and wait for frequency to reduce
before proceeding with a transient flush. This is really only needed for
the transient flush: if L2 flush is needed due to 16023588340 then
there's no need to do this additional wait since we are already using
the bigger hammer.

v2: Use generic names, ensure user set max frequency requests wait
for flush to complete (Rodrigo)
v3:
 - User requests wait via wait_var_event_timeout (Lucas)
 - Close races on flush + user requests (Lucas)
 - Fix xe_guc_pc_remove_flush_freq_limit() being called on last gt
   rather than root gt (Lucas)
v4:
 - Only apply the freq reducing part if a TDF is needed: L2 flush trumps
   the need for waiting a lower frequency

Fixes: aaa08078e725 ("drm/xe/bmg: Apply Wa_22019338487")
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Vinay Belgaumkar <vinay.belgaumkar@intel.com>
Link: https://lore.kernel.org/r/20250618-wa-22019338487-v5-4-b888388477f2@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
(cherry picked from commit deea6a7d6d803d6bb874a3e6f1b312e560e6c6df)
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
---
 drivers/gpu/drm/xe/xe_device.c       |   8 +-
 drivers/gpu/drm/xe/xe_guc_pc.c       | 125 +++++++++++++++++++++++++++
 drivers/gpu/drm/xe/xe_guc_pc.h       |   2 +
 drivers/gpu/drm/xe/xe_guc_pc_types.h |   2 +
 4 files changed, 135 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c
index a798914644fb..e9f3c1a53db2 100644
--- a/drivers/gpu/drm/xe/xe_device.c
+++ b/drivers/gpu/drm/xe/xe_device.c
@@ -40,6 +40,7 @@
 #include "xe_gt_printk.h"
 #include "xe_gt_sriov_vf.h"
 #include "xe_guc.h"
+#include "xe_guc_pc.h"
 #include "xe_hw_engine_group.h"
 #include "xe_hwmon.h"
 #include "xe_irq.h"
@@ -1071,11 +1072,14 @@ void xe_device_td_flush(struct xe_device *xe)
 		return;
 
 	root_gt = xe_root_mmio_gt(xe);
-	if (XE_WA(root_gt, 16023588340))
+	if (XE_WA(root_gt, 16023588340)) {
 		/* A transient flush is not sufficient: flush the L2 */
 		xe_device_l2_flush(xe);
-	else
+	} else {
+		xe_guc_pc_apply_flush_freq_limit(&root_gt->uc.guc.pc);
 		tdf_request_sync(xe);
+		xe_guc_pc_remove_flush_freq_limit(&root_gt->uc.guc.pc);
+	}
 }
 
 u32 xe_device_ccs_bytes(struct xe_device *xe, u64 size)
diff --git a/drivers/gpu/drm/xe/xe_guc_pc.c b/drivers/gpu/drm/xe/xe_guc_pc.c
index 9d9d0e815fea..c0ca61695d76 100644
--- a/drivers/gpu/drm/xe/xe_guc_pc.c
+++ b/drivers/gpu/drm/xe/xe_guc_pc.c
@@ -7,7 +7,9 @@
 
 #include <linux/cleanup.h>
 #include <linux/delay.h>
+#include <linux/jiffies.h>
 #include <linux/ktime.h>
+#include <linux/wait_bit.h>
 
 #include <drm/drm_managed.h>
 #include <drm/drm_print.h>
@@ -53,9 +55,11 @@
 #define LNL_MERT_FREQ_CAP	800
 #define BMG_MERT_FREQ_CAP	2133
 #define BMG_MIN_FREQ		1200
+#define BMG_MERT_FLUSH_FREQ_CAP	2600
 
 #define SLPC_RESET_TIMEOUT_MS 5 /* roughly 5ms, but no need for precision */
 #define SLPC_RESET_EXTENDED_TIMEOUT_MS 1000 /* To be used only at pc_start */
+#define SLPC_ACT_FREQ_TIMEOUT_MS 100
 
 /**
  * DOC: GuC Power Conservation (PC)
@@ -143,6 +147,36 @@ static int wait_for_pc_state(struct xe_guc_pc *pc,
 	return -ETIMEDOUT;
 }
 
+static int wait_for_flush_complete(struct xe_guc_pc *pc)
+{
+	const unsigned long timeout = msecs_to_jiffies(30);
+
+	if (!wait_var_event_timeout(&pc->flush_freq_limit,
+				    !atomic_read(&pc->flush_freq_limit),
+				    timeout))
+		return -ETIMEDOUT;
+
+	return 0;
+}
+
+static int wait_for_act_freq_limit(struct xe_guc_pc *pc, u32 freq)
+{
+	int timeout_us = SLPC_ACT_FREQ_TIMEOUT_MS * USEC_PER_MSEC;
+	int slept, wait = 10;
+
+	for (slept = 0; slept < timeout_us;) {
+		if (xe_guc_pc_get_act_freq(pc) <= freq)
+			return 0;
+
+		usleep_range(wait, wait << 1);
+		slept += wait;
+		wait <<= 1;
+		if (slept + wait > timeout_us)
+			wait = timeout_us - slept;
+	}
+
+	return -ETIMEDOUT;
+}
 static int pc_action_reset(struct xe_guc_pc *pc)
 {
 	struct xe_guc_ct *ct = pc_to_ct(pc);
@@ -688,6 +722,11 @@ static int xe_guc_pc_set_max_freq_locked(struct xe_guc_pc *pc, u32 freq)
  */
 int xe_guc_pc_set_max_freq(struct xe_guc_pc *pc, u32 freq)
 {
+	if (XE_WA(pc_to_gt(pc), 22019338487)) {
+		if (wait_for_flush_complete(pc) != 0)
+			return -EAGAIN;
+	}
+
 	guard(mutex)(&pc->freq_lock);
 
 	return xe_guc_pc_set_max_freq_locked(pc, freq);
@@ -888,6 +927,92 @@ static int pc_adjust_requested_freq(struct xe_guc_pc *pc)
 	return ret;
 }
 
+static bool needs_flush_freq_limit(struct xe_guc_pc *pc)
+{
+	struct xe_gt *gt = pc_to_gt(pc);
+
+	return  XE_WA(gt, 22019338487) &&
+		pc->rp0_freq > BMG_MERT_FLUSH_FREQ_CAP;
+}
+
+/**
+ * xe_guc_pc_apply_flush_freq_limit() - Limit max GT freq during L2 flush
+ * @pc: the xe_guc_pc object
+ *
+ * As per the WA, reduce max GT frequency during L2 cache flush
+ */
+void xe_guc_pc_apply_flush_freq_limit(struct xe_guc_pc *pc)
+{
+	struct xe_gt *gt = pc_to_gt(pc);
+	u32 max_freq;
+	int ret;
+
+	if (!needs_flush_freq_limit(pc))
+		return;
+
+	guard(mutex)(&pc->freq_lock);
+
+	ret = xe_guc_pc_get_max_freq_locked(pc, &max_freq);
+	if (!ret && max_freq > BMG_MERT_FLUSH_FREQ_CAP) {
+		ret = pc_set_max_freq(pc, BMG_MERT_FLUSH_FREQ_CAP);
+		if (ret) {
+			xe_gt_err_once(gt, "Failed to cap max freq on flush to %u, %pe\n",
+				       BMG_MERT_FLUSH_FREQ_CAP, ERR_PTR(ret));
+			return;
+		}
+
+		atomic_set(&pc->flush_freq_limit, 1);
+
+		/*
+		 * If user has previously changed max freq, stash that value to
+		 * restore later, otherwise use the current max. New user
+		 * requests wait on flush.
+		 */
+		if (pc->user_requested_max != 0)
+			pc->stashed_max_freq = pc->user_requested_max;
+		else
+			pc->stashed_max_freq = max_freq;
+	}
+
+	/*
+	 * Wait for actual freq to go below the flush cap: even if the previous
+	 * max was below cap, the current one might still be above it
+	 */
+	ret = wait_for_act_freq_limit(pc, BMG_MERT_FLUSH_FREQ_CAP);
+	if (ret)
+		xe_gt_err_once(gt, "Actual freq did not reduce to %u, %pe\n",
+			       BMG_MERT_FLUSH_FREQ_CAP, ERR_PTR(ret));
+}
+
+/**
+ * xe_guc_pc_remove_flush_freq_limit() - Remove max GT freq limit after L2 flush completes.
+ * @pc: the xe_guc_pc object
+ *
+ * Retrieve the previous GT max frequency value.
+ */
+void xe_guc_pc_remove_flush_freq_limit(struct xe_guc_pc *pc)
+{
+	struct xe_gt *gt = pc_to_gt(pc);
+	int ret = 0;
+
+	if (!needs_flush_freq_limit(pc))
+		return;
+
+	if (!atomic_read(&pc->flush_freq_limit))
+		return;
+
+	mutex_lock(&pc->freq_lock);
+
+	ret = pc_set_max_freq(&gt->uc.guc.pc, pc->stashed_max_freq);
+	if (ret)
+		xe_gt_err_once(gt, "Failed to restore max freq %u:%d",
+			       pc->stashed_max_freq, ret);
+
+	atomic_set(&pc->flush_freq_limit, 0);
+	mutex_unlock(&pc->freq_lock);
+	wake_up_var(&pc->flush_freq_limit);
+}
+
 static int pc_set_mert_freq_cap(struct xe_guc_pc *pc)
 {
 	int ret;
diff --git a/drivers/gpu/drm/xe/xe_guc_pc.h b/drivers/gpu/drm/xe/xe_guc_pc.h
index 0a2664d5c811..52ecdd5ddbff 100644
--- a/drivers/gpu/drm/xe/xe_guc_pc.h
+++ b/drivers/gpu/drm/xe/xe_guc_pc.h
@@ -38,5 +38,7 @@ u64 xe_guc_pc_mc6_residency(struct xe_guc_pc *pc);
 void xe_guc_pc_init_early(struct xe_guc_pc *pc);
 int xe_guc_pc_restore_stashed_freq(struct xe_guc_pc *pc);
 void xe_guc_pc_raise_unslice(struct xe_guc_pc *pc);
+void xe_guc_pc_apply_flush_freq_limit(struct xe_guc_pc *pc);
+void xe_guc_pc_remove_flush_freq_limit(struct xe_guc_pc *pc);
 
 #endif /* _XE_GUC_PC_H_ */
diff --git a/drivers/gpu/drm/xe/xe_guc_pc_types.h b/drivers/gpu/drm/xe/xe_guc_pc_types.h
index 2978ac9a249b..c02053948a57 100644
--- a/drivers/gpu/drm/xe/xe_guc_pc_types.h
+++ b/drivers/gpu/drm/xe/xe_guc_pc_types.h
@@ -15,6 +15,8 @@
 struct xe_guc_pc {
 	/** @bo: GGTT buffer object that is shared with GuC PC */
 	struct xe_bo *bo;
+	/** @flush_freq_limit: 1 when max freq changes are limited by driver */
+	atomic_t flush_freq_limit;
 	/** @rp0_freq: HW RP0 frequency - The Maximum one */
 	u32 rp0_freq;
 	/** @rpa_freq: HW RPa frequency - The Achievable one */

From de6acfdc390ec2eb64d43186721038ddc93228b3 Mon Sep 17 00:00:00 2001
From: Lucas De Marchi <lucas.demarchi@intel.com>
Date: Wed, 11 Jun 2025 12:38:37 -0700
Subject: [PATCH 1094/1334] drm/xe: Fix kconfig prompt

The xe driver is the official driver for Intel Xe2 and later, while
maintaining experimental support for earlier GPUs. Reword the help
message accordingly.

Reviewed-by: Maarten Lankhorst <dev@lankhorst.se>
Link: https://lore.kernel.org/r/20250611-xe-kconfig-help-v1-1-8bcc6b47d11a@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
(cherry picked from commit 1488a3089de3d0bcdc9532da7ce04cf0af9d7dd0)
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
---
 drivers/gpu/drm/xe/Kconfig  | 5 +++--
 drivers/gpu/drm/xe/xe_drv.h | 2 +-
 2 files changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/xe/Kconfig b/drivers/gpu/drm/xe/Kconfig
index fcc2677a4229..884a3199b5be 100644
--- a/drivers/gpu/drm/xe/Kconfig
+++ b/drivers/gpu/drm/xe/Kconfig
@@ -1,6 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0-only
 config DRM_XE
-	tristate "Intel Xe Graphics"
+	tristate "Intel Xe2 Graphics"
 	depends on DRM && PCI && (m || (y && KUNIT=y))
 	depends on INTEL_VSEC || !INTEL_VSEC
 	depends on X86_PLATFORM_DEVICES || !(X86 && ACPI)
@@ -46,7 +46,8 @@ config DRM_XE
 	select AUXILIARY_BUS
 	select HMM_MIRROR
 	help
-	  Experimental driver for Intel Xe series GPUs
+	  Driver for Intel Xe2 series GPUs and later. Experimental support
+	  for Xe series is also available.
 
 	  If "M" is selected, the module will be called xe.
 
diff --git a/drivers/gpu/drm/xe/xe_drv.h b/drivers/gpu/drm/xe/xe_drv.h
index d61650d4aa0b..95242a375e54 100644
--- a/drivers/gpu/drm/xe/xe_drv.h
+++ b/drivers/gpu/drm/xe/xe_drv.h
@@ -9,7 +9,7 @@
 #include <drm/drm_drv.h>
 
 #define DRIVER_NAME		"xe"
-#define DRIVER_DESC		"Intel Xe Graphics"
+#define DRIVER_DESC		"Intel Xe2 Graphics"
 
 /* Interface history:
  *

From aa18d5769fcafe645a3ba01a9a69dde4f8dc8cc3 Mon Sep 17 00:00:00 2001
From: Harry Austen <hpausten@protonmail.com>
Date: Fri, 27 Jun 2025 13:30:35 -0700
Subject: [PATCH 1095/1334] drm/xe: Allow dropping kunit dependency as built-in
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Fix Kconfig symbol dependency on KUNIT, which isn't actually required
for XE to be built-in. However, if KUNIT is enabled, it must be built-in
too.

Fixes: 08987a8b6820 ("drm/xe: Fix build with KUNIT=m")
Cc: Lucas De Marchi <lucas.demarchi@intel.com>
Cc: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Cc: Jani Nikula <jani.nikula@linux.intel.com>
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Signed-off-by: Harry Austen <hpausten@protonmail.com>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Acked-by: Randy Dunlap <rdunlap@infradead.org>
Tested-by: Randy Dunlap <rdunlap@infradead.org>
Link: https://lore.kernel.org/r/20250627-xe-kunit-v2-2-756fe5cd56cf@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
(cherry picked from commit a559434880b320b83733d739733250815aecf1b0)
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
---
 drivers/gpu/drm/xe/Kconfig | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/xe/Kconfig b/drivers/gpu/drm/xe/Kconfig
index 884a3199b5be..99a91355842e 100644
--- a/drivers/gpu/drm/xe/Kconfig
+++ b/drivers/gpu/drm/xe/Kconfig
@@ -1,7 +1,8 @@
 # SPDX-License-Identifier: GPL-2.0-only
 config DRM_XE
 	tristate "Intel Xe2 Graphics"
-	depends on DRM && PCI && (m || (y && KUNIT=y))
+	depends on DRM && PCI
+	depends on KUNIT || !KUNIT
 	depends on INTEL_VSEC || !INTEL_VSEC
 	depends on X86_PLATFORM_DEVICES || !(X86 && ACPI)
 	select INTERVAL_TREE

From 8af39ec5cf2be522c8eb43a3d8005ed59e4daaee Mon Sep 17 00:00:00 2001
From: Matthew Brost <matthew.brost@intel.com>
Date: Fri, 13 Jun 2025 14:20:13 -0700
Subject: [PATCH 1096/1334] drm/sched: Increment job count before swapping tail
 spsc queue
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

A small race exists between spsc_queue_push and the run-job worker, in
which spsc_queue_push may return not-first while the run-job worker has
already idled due to the job count being zero. If this race occurs, job
scheduling stops, leading to hangs while waiting on the job’s DMA
fences.

Seal this race by incrementing the job count before appending to the
SPSC queue.

This race was observed on a drm-tip 6.16-rc1 build with the Xe driver in
an SVM test case.

Fixes: 1b1f42d8fde4 ("drm: move amd_gpu_scheduler into common location")
Fixes: 27105db6c63a ("drm/amdgpu: Add SPSC queue to scheduler.")
Cc: stable@vger.kernel.org
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Jonathan Cavitt <jonathan.cavitt@intel.com>
Link: https://lore.kernel.org/r/20250613212013.719312-1-matthew.brost@intel.com
---
 include/drm/spsc_queue.h | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/include/drm/spsc_queue.h b/include/drm/spsc_queue.h
index 125f096c88cb..ee9df8cc67b7 100644
--- a/include/drm/spsc_queue.h
+++ b/include/drm/spsc_queue.h
@@ -70,9 +70,11 @@ static inline bool spsc_queue_push(struct spsc_queue *queue, struct spsc_node *n
 
 	preempt_disable();
 
+	atomic_inc(&queue->job_count);
+	smp_mb__after_atomic();
+
 	tail = (struct spsc_node **)atomic_long_xchg(&queue->tail, (long)&node->next);
 	WRITE_ONCE(*tail, node);
-	atomic_inc(&queue->job_count);
 
 	/*
 	 * In case of first element verify new node will be visible to the consumer

From c6e8d51b37d2ca37dee63753fd240bcbc6402ad3 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Tue, 1 Jul 2025 13:36:51 -0400
Subject: [PATCH 1097/1334] bcachefs: Work around deadlock to btree node
 rewrites in journal replay

Don't mark btree nodes for rewrites, if they are or would be degraded,
if journal replay hasn't finished, to avoid a deadlock.

This is because btree node rewrites generate more updates for the
interior updates (alloc, backpointers), and if those updates touch
new nodes and generate more rewrites - we can only have so many interior
btree updates in flight before we deadlock on open_buckets.

The biggest cause is that we don't use the btree write buffer (for
the backpointer updates - this needs some real thought on locking in
order to fix.

The problem with this workaround (not doing the rewrite for degraded
nodes in journal replay) is that those degraded nodes persist, and we
don't want that (this is a real bug when a btree node write completes
with fewer replicas than we wanted and leaves a degraded node due to
device _removal_, i.e. the device went away mid write).

It's less of a bug here, but still a problem because we don't yet
have a way of tracking degraded data - we another index (all
extents/btree nodes, by replicas entry) in order to fix properly
(re-replicate degraded data at the earliest possible time).

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/btree_io.c | 41 ++++++++++++++++++++++++++++++++++-------
 1 file changed, 34 insertions(+), 7 deletions(-)

diff --git a/fs/bcachefs/btree_io.c b/fs/bcachefs/btree_io.c
index 08b22bddd747..e874a4357f64 100644
--- a/fs/bcachefs/btree_io.c
+++ b/fs/bcachefs/btree_io.c
@@ -1337,15 +1337,42 @@ int bch2_btree_node_read_done(struct bch_fs *c, struct bch_dev *ca,
 
 	btree_node_reset_sib_u64s(b);
 
-	scoped_guard(rcu)
-		bkey_for_each_ptr(bch2_bkey_ptrs(bkey_i_to_s(&b->key)), ptr) {
-			struct bch_dev *ca2 = bch2_dev_rcu(c, ptr->dev);
+	/*
+	 * XXX:
+	 *
+	 * We deadlock if too many btree updates require node rewrites while
+	 * we're still in journal replay.
+	 *
+	 * This is because btree node rewrites generate more updates for the
+	 * interior updates (alloc, backpointers), and if those updates touch
+	 * new nodes and generate more rewrites - well, you see the problem.
+	 *
+	 * The biggest cause is that we don't use the btree write buffer (for
+	 * the backpointer updates - this needs some real thought on locking in
+	 * order to fix.
+	 *
+	 * The problem with this workaround (not doing the rewrite for degraded
+	 * nodes in journal replay) is that those degraded nodes persist, and we
+	 * don't want that (this is a real bug when a btree node write completes
+	 * with fewer replicas than we wanted and leaves a degraded node due to
+	 * device _removal_, i.e. the device went away mid write).
+	 *
+	 * It's less of a bug here, but still a problem because we don't yet
+	 * have a way of tracking degraded data - we another index (all
+	 * extents/btree nodes, by replicas entry) in order to fix properly
+	 * (re-replicate degraded data at the earliest possible time).
+	 */
+	if (c->recovery.passes_complete & BIT_ULL(BCH_RECOVERY_PASS_journal_replay)) {
+		scoped_guard(rcu)
+			bkey_for_each_ptr(bch2_bkey_ptrs(bkey_i_to_s(&b->key)), ptr) {
+				struct bch_dev *ca2 = bch2_dev_rcu(c, ptr->dev);
 
-			if (!ca2 || ca2->mi.state != BCH_MEMBER_STATE_rw) {
-				set_btree_node_need_rewrite(b);
-				set_btree_node_need_rewrite_degraded(b);
+				if (!ca2 || ca2->mi.state != BCH_MEMBER_STATE_rw) {
+					set_btree_node_need_rewrite(b);
+					set_btree_node_need_rewrite_degraded(b);
+				}
 			}
-		}
+	}
 
 	if (!ptr_written) {
 		set_btree_node_need_rewrite(b);

From 94426e4201fbb1c5ea4a697eb62a8b7cd7dfccbf Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Thu, 26 Jun 2025 09:46:35 -0400
Subject: [PATCH 1098/1334] bcachefs: opts.casefold_disabled

Add an option for completely disabling casefolding on a filesystem, as a
workaround for overlayfs.

This should only be needed as a temporary workaround, until the
overlayfs fix arrives.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/bcachefs.h | 11 +++++++++--
 fs/bcachefs/dirent.c   | 19 +++++++++----------
 fs/bcachefs/dirent.h   |  3 ++-
 fs/bcachefs/fs.c       |  7 +++----
 fs/bcachefs/fsck.c     |  2 --
 fs/bcachefs/inode.c    | 13 ++++++++-----
 fs/bcachefs/opts.h     |  5 +++++
 fs/bcachefs/str_hash.c |  5 +++--
 fs/bcachefs/str_hash.h |  2 --
 fs/bcachefs/super.c    | 31 ++++++++++++++++---------------
 10 files changed, 55 insertions(+), 43 deletions(-)

diff --git a/fs/bcachefs/bcachefs.h b/fs/bcachefs/bcachefs.h
index 8043943cdf6a..ddfacad0f70c 100644
--- a/fs/bcachefs/bcachefs.h
+++ b/fs/bcachefs/bcachefs.h
@@ -863,9 +863,7 @@ struct bch_fs {
 	DARRAY(enum bcachefs_metadata_version)
 				incompat_versions_requested;
 
-#ifdef CONFIG_UNICODE
 	struct unicode_map	*cf_encoding;
-#endif
 
 	struct bch_sb_handle	disk_sb;
 
@@ -1285,4 +1283,13 @@ static inline bool bch2_discard_opt_enabled(struct bch_fs *c, struct bch_dev *ca
 		: ca->mi.discard;
 }
 
+static inline bool bch2_fs_casefold_enabled(struct bch_fs *c)
+{
+#ifdef CONFIG_UNICODE
+	return !c->opts.casefold_disabled;
+#else
+	return false;
+#endif
+}
+
 #endif /* _BCACHEFS_H */
diff --git a/fs/bcachefs/dirent.c b/fs/bcachefs/dirent.c
index 300f7cc8abdf..a18d0f78704d 100644
--- a/fs/bcachefs/dirent.c
+++ b/fs/bcachefs/dirent.c
@@ -18,7 +18,9 @@ int bch2_casefold(struct btree_trans *trans, const struct bch_hash_info *info,
 {
 	*out_cf = (struct qstr) QSTR_INIT(NULL, 0);
 
-#ifdef CONFIG_UNICODE
+	if (!bch2_fs_casefold_enabled(trans->c))
+		return -EOPNOTSUPP;
+
 	unsigned char *buf = bch2_trans_kmalloc(trans, BCH_NAME_MAX + 1);
 	int ret = PTR_ERR_OR_ZERO(buf);
 	if (ret)
@@ -30,9 +32,6 @@ int bch2_casefold(struct btree_trans *trans, const struct bch_hash_info *info,
 
 	*out_cf = (struct qstr) QSTR_INIT(buf, ret);
 	return 0;
-#else
-	return -EOPNOTSUPP;
-#endif
 }
 
 static unsigned bch2_dirent_name_bytes(struct bkey_s_c_dirent d)
@@ -231,7 +230,8 @@ void bch2_dirent_to_text(struct printbuf *out, struct bch_fs *c, struct bkey_s_c
 	prt_printf(out, " type %s", bch2_d_type_str(d.v->d_type));
 }
 
-int bch2_dirent_init_name(struct bkey_i_dirent *dirent,
+int bch2_dirent_init_name(struct bch_fs *c,
+			  struct bkey_i_dirent *dirent,
 			  const struct bch_hash_info *hash_info,
 			  const struct qstr *name,
 			  const struct qstr *cf_name)
@@ -251,7 +251,9 @@ int bch2_dirent_init_name(struct bkey_i_dirent *dirent,
 		       offsetof(struct bch_dirent, d_name) -
 		       name->len);
 	} else {
-#ifdef CONFIG_UNICODE
+		if (!bch2_fs_casefold_enabled(c))
+			return -EOPNOTSUPP;
+
 		memcpy(&dirent->v.d_cf_name_block.d_names[0], name->name, name->len);
 
 		char *cf_out = &dirent->v.d_cf_name_block.d_names[name->len];
@@ -277,9 +279,6 @@ int bch2_dirent_init_name(struct bkey_i_dirent *dirent,
 		dirent->v.d_cf_name_block.d_cf_name_len = cpu_to_le16(cf_len);
 
 		EBUG_ON(bch2_dirent_get_casefold_name(dirent_i_to_s_c(dirent)).len != cf_len);
-#else
-	return -EOPNOTSUPP;
-#endif
 	}
 
 	unsigned u64s = dirent_val_u64s(name->len, cf_len);
@@ -313,7 +312,7 @@ struct bkey_i_dirent *bch2_dirent_create_key(struct btree_trans *trans,
 	dirent->v.d_type = type;
 	dirent->v.d_unused = 0;
 
-	int ret = bch2_dirent_init_name(dirent, hash_info, name, cf_name);
+	int ret = bch2_dirent_init_name(trans->c, dirent, hash_info, name, cf_name);
 	if (ret)
 		return ERR_PTR(ret);
 
diff --git a/fs/bcachefs/dirent.h b/fs/bcachefs/dirent.h
index 70fb0b581221..1e17199cc5c7 100644
--- a/fs/bcachefs/dirent.h
+++ b/fs/bcachefs/dirent.h
@@ -59,7 +59,8 @@ static inline void dirent_copy_target(struct bkey_i_dirent *dst,
 	dst->v.d_type = src.v->d_type;
 }
 
-int bch2_dirent_init_name(struct bkey_i_dirent *,
+int bch2_dirent_init_name(struct bch_fs *,
+			  struct bkey_i_dirent *,
 			  const struct bch_hash_info *,
 			  const struct qstr *,
 			  const struct qstr *);
diff --git a/fs/bcachefs/fs.c b/fs/bcachefs/fs.c
index db24a76563f8..e54e4f255b22 100644
--- a/fs/bcachefs/fs.c
+++ b/fs/bcachefs/fs.c
@@ -722,7 +722,6 @@ static struct dentry *bch2_lookup(struct inode *vdir, struct dentry *dentry,
 	if (IS_ERR(inode))
 		inode = NULL;
 
-#ifdef CONFIG_UNICODE
 	if (!inode && IS_CASEFOLDED(vdir)) {
 		/*
 		 * Do not cache a negative dentry in casefolded directories
@@ -737,7 +736,6 @@ static struct dentry *bch2_lookup(struct inode *vdir, struct dentry *dentry,
 		 */
 		return NULL;
 	}
-#endif
 
 	return d_splice_alias(&inode->v, dentry);
 }
@@ -2566,9 +2564,10 @@ got_sb:
 	sb->s_shrink->seeks = 0;
 
 #ifdef CONFIG_UNICODE
-	sb->s_encoding = c->cf_encoding;
-#endif
+	if (bch2_fs_casefold_enabled(c))
+		sb->s_encoding = c->cf_encoding;
 	generic_set_sb_d_ops(sb);
+#endif
 
 	vinode = bch2_vfs_inode_get(c, BCACHEFS_ROOT_SUBVOL_INUM);
 	ret = PTR_ERR_OR_ZERO(vinode);
diff --git a/fs/bcachefs/fsck.c b/fs/bcachefs/fsck.c
index 63093def85e3..dbf161e4311a 100644
--- a/fs/bcachefs/fsck.c
+++ b/fs/bcachefs/fsck.c
@@ -2302,9 +2302,7 @@ static int check_dirent(struct btree_trans *trans, struct btree_iter *iter,
 		*hash_info = bch2_hash_info_init(c, &i->inode);
 	dir->first_this_inode = false;
 
-#ifdef CONFIG_UNICODE
 	hash_info->cf_encoding = bch2_inode_casefold(c, &i->inode) ? c->cf_encoding : NULL;
-#endif
 
 	ret = bch2_str_hash_check_key(trans, s, &bch2_dirent_hash_desc, hash_info,
 				      iter, k, need_second_pass);
diff --git a/fs/bcachefs/inode.c b/fs/bcachefs/inode.c
index 53e5dc1f6ac1..ef4cc7395b86 100644
--- a/fs/bcachefs/inode.c
+++ b/fs/bcachefs/inode.c
@@ -1265,7 +1265,14 @@ int bch2_inode_set_casefold(struct btree_trans *trans, subvol_inum inum,
 {
 	struct bch_fs *c = trans->c;
 
-#ifdef CONFIG_UNICODE
+#ifndef CONFIG_UNICODE
+	bch_err(c, "Cannot use casefolding on a kernel without CONFIG_UNICODE");
+	return -EOPNOTSUPP;
+#endif
+
+	if (c->opts.casefold_disabled)
+		return -EOPNOTSUPP;
+
 	int ret = 0;
 	/* Not supported on individual files. */
 	if (!S_ISDIR(bi->bi_mode))
@@ -1289,10 +1296,6 @@ int bch2_inode_set_casefold(struct btree_trans *trans, subvol_inum inum,
 	bi->bi_fields_set |= BIT(Inode_opt_casefold);
 
 	return bch2_maybe_propagate_has_case_insensitive(trans, inum, bi);
-#else
-	bch_err(c, "Cannot use casefolding on a kernel without CONFIG_UNICODE");
-	return -EOPNOTSUPP;
-#endif
 }
 
 static noinline int __bch2_inode_rm_snapshot(struct btree_trans *trans, u64 inum, u32 snapshot)
diff --git a/fs/bcachefs/opts.h b/fs/bcachefs/opts.h
index b0a76bd6d6f5..63f8e254495c 100644
--- a/fs/bcachefs/opts.h
+++ b/fs/bcachefs/opts.h
@@ -234,6 +234,11 @@ enum fsck_err_opts {
 	  OPT_BOOL(),							\
 	  BCH_SB_CASEFOLD,		false,				\
 	  NULL,		"Dirent lookups are casefolded")		\
+	x(casefold_disabled,			u8,			\
+	  OPT_FS|OPT_MOUNT,						\
+	  OPT_BOOL(),							\
+	  BCH2_NO_SB_OPT,		false,				\
+	  NULL,		"Disable casefolding filesystem wide")		\
 	x(inodes_32bit,			u8,				\
 	  OPT_FS|OPT_INODE|OPT_FORMAT|OPT_MOUNT|OPT_RUNTIME,		\
 	  OPT_BOOL(),							\
diff --git a/fs/bcachefs/str_hash.c b/fs/bcachefs/str_hash.c
index 71b735a85026..3e9f59226bdf 100644
--- a/fs/bcachefs/str_hash.c
+++ b/fs/bcachefs/str_hash.c
@@ -38,6 +38,7 @@ static int bch2_fsck_rename_dirent(struct btree_trans *trans,
 				   struct bkey_s_c_dirent old,
 				   bool *updated_before_k_pos)
 {
+	struct bch_fs *c = trans->c;
 	struct qstr old_name = bch2_dirent_get_name(old);
 	struct bkey_i_dirent *new = bch2_trans_kmalloc(trans, BKEY_U64s_MAX * sizeof(u64));
 	int ret = PTR_ERR_OR_ZERO(new);
@@ -60,7 +61,7 @@ static int bch2_fsck_rename_dirent(struct btree_trans *trans,
 					sprintf(renamed_buf, "%.*s.fsck_renamed-%u",
 						old_name.len, old_name.name, i));
 
-		ret = bch2_dirent_init_name(new, hash_info, &renamed_name, NULL);
+		ret = bch2_dirent_init_name(c, new, hash_info, &renamed_name, NULL);
 		if (ret)
 			return ret;
 
@@ -79,7 +80,7 @@ static int bch2_fsck_rename_dirent(struct btree_trans *trans,
 	}
 
 	ret = ret ?: bch2_fsck_update_backpointers(trans, s, desc, hash_info, &new->k_i);
-	bch_err_fn(trans->c, ret);
+	bch_err_fn(c, ret);
 	return ret;
 }
 
diff --git a/fs/bcachefs/str_hash.h b/fs/bcachefs/str_hash.h
index 79d51aef70aa..8979ac2d7a3b 100644
--- a/fs/bcachefs/str_hash.h
+++ b/fs/bcachefs/str_hash.h
@@ -48,9 +48,7 @@ bch2_hash_info_init(struct bch_fs *c, const struct bch_inode_unpacked *bi)
 	struct bch_hash_info info = {
 		.inum_snapshot	= bi->bi_snapshot,
 		.type		= INODE_STR_HASH(bi),
-#ifdef CONFIG_UNICODE
 		.cf_encoding	= bch2_inode_casefold(c, bi) ? c->cf_encoding : NULL,
-#endif
 		.siphash_key	= { .k0 = bi->bi_hash_seed }
 	};
 
diff --git a/fs/bcachefs/super.c b/fs/bcachefs/super.c
index 69c097ff54e7..c46b1053a02c 100644
--- a/fs/bcachefs/super.c
+++ b/fs/bcachefs/super.c
@@ -1025,15 +1025,17 @@ static struct bch_fs *bch2_fs_alloc(struct bch_sb *sb, struct bch_opts *opts,
 	}
 
 #ifdef CONFIG_UNICODE
-	/* Default encoding until we can potentially have more as an option. */
-	c->cf_encoding = utf8_load(BCH_FS_DEFAULT_UTF8_ENCODING);
-	if (IS_ERR(c->cf_encoding)) {
-		printk(KERN_ERR "Cannot load UTF-8 encoding for filesystem. Version: %u.%u.%u",
-			unicode_major(BCH_FS_DEFAULT_UTF8_ENCODING),
-			unicode_minor(BCH_FS_DEFAULT_UTF8_ENCODING),
-			unicode_rev(BCH_FS_DEFAULT_UTF8_ENCODING));
-		ret = -EINVAL;
-		goto err;
+	if (bch2_fs_casefold_enabled(c)) {
+		/* Default encoding until we can potentially have more as an option. */
+		c->cf_encoding = utf8_load(BCH_FS_DEFAULT_UTF8_ENCODING);
+		if (IS_ERR(c->cf_encoding)) {
+			printk(KERN_ERR "Cannot load UTF-8 encoding for filesystem. Version: %u.%u.%u",
+			       unicode_major(BCH_FS_DEFAULT_UTF8_ENCODING),
+			       unicode_minor(BCH_FS_DEFAULT_UTF8_ENCODING),
+			       unicode_rev(BCH_FS_DEFAULT_UTF8_ENCODING));
+			ret = -EINVAL;
+			goto err;
+		}
 	}
 #else
 	if (c->sb.features & BIT_ULL(BCH_FEATURE_casefolding)) {
@@ -1160,12 +1162,11 @@ int bch2_fs_start(struct bch_fs *c)
 
 	print_mount_opts(c);
 
-#ifdef CONFIG_UNICODE
-	bch_info(c, "Using encoding defined by superblock: utf8-%u.%u.%u",
-		 unicode_major(BCH_FS_DEFAULT_UTF8_ENCODING),
-		 unicode_minor(BCH_FS_DEFAULT_UTF8_ENCODING),
-		 unicode_rev(BCH_FS_DEFAULT_UTF8_ENCODING));
-#endif
+	if (c->cf_encoding)
+		bch_info(c, "Using encoding defined by superblock: utf8-%u.%u.%u",
+			 unicode_major(BCH_FS_DEFAULT_UTF8_ENCODING),
+			 unicode_minor(BCH_FS_DEFAULT_UTF8_ENCODING),
+			 unicode_rev(BCH_FS_DEFAULT_UTF8_ENCODING));
 
 	if (!bch2_fs_may_start(c))
 		return bch_err_throw(c, insufficient_devices_to_start);

From e6ed134a4ef592fe1fd0cafac9683813b3c8f3e8 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Mon, 30 Jun 2025 14:36:40 -0500
Subject: [PATCH 1099/1334] lib: test_objagg: Set error message in
 check_expect_hints_stats()

Smatch complains that the error message isn't set in the caller:

    lib/test_objagg.c:923 test_hints_case2()
    error: uninitialized symbol 'errmsg'.

This static checker warning only showed up after a recent refactoring
but the bug dates back to when the code was originally added.  This
likely doesn't affect anything in real life.

Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/r/202506281403.DsuyHFTZ-lkp@intel.com/
Fixes: 0a020d416d0a ("lib: introduce initial implementation of object aggregation manager")
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/8548f423-2e3b-4bb7-b816-5041de2762aa@sabinyo.mountain
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 lib/test_objagg.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/lib/test_objagg.c b/lib/test_objagg.c
index d34df4306b87..222b39fc2629 100644
--- a/lib/test_objagg.c
+++ b/lib/test_objagg.c
@@ -899,8 +899,10 @@ static int check_expect_hints_stats(struct objagg_hints *objagg_hints,
 	int err;
 
 	stats = objagg_hints_stats_get(objagg_hints);
-	if (IS_ERR(stats))
+	if (IS_ERR(stats)) {
+		*errmsg = "objagg_hints_stats_get() failed.";
 		return PTR_ERR(stats);
+	}
 	err = __check_expect_stats(stats, expect_stats, errmsg);
 	objagg_stats_put(stats);
 	return err;

From 42fd432fe6d320323215ebdf4de4d0d7e56e6792 Mon Sep 17 00:00:00 2001
From: Raju Rangoju <Raju.Rangoju@amd.com>
Date: Tue, 1 Jul 2025 00:56:36 +0530
Subject: [PATCH 1100/1334] amd-xgbe: align CL37 AN sequence as per databook

Update the Clause 37 Auto-Negotiation implementation to properly align
with the PCS hardware specifications:
- Fix incorrect bit settings in Link Status and Link Duplex fields
- Implement missing sequence steps 2 and 7

These changes ensure CL37 auto-negotiation protocol follows the exact
sequence patterns as specified in the hardware databook.

Fixes: 1bf40ada6290 ("amd-xgbe: Add support for clause 37 auto-negotiation")
Signed-off-by: Raju Rangoju <Raju.Rangoju@amd.com>
Link: https://patch.msgid.link/20250630192636.3838291-1-Raju.Rangoju@amd.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/amd/xgbe/xgbe-common.h | 2 ++
 drivers/net/ethernet/amd/xgbe/xgbe-mdio.c   | 9 +++++++++
 drivers/net/ethernet/amd/xgbe/xgbe.h        | 4 ++--
 3 files changed, 13 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-common.h b/drivers/net/ethernet/amd/xgbe/xgbe-common.h
index e1296cbf4ff3..9316de4126cf 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-common.h
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-common.h
@@ -1269,6 +1269,8 @@
 #define MDIO_VEND2_CTRL1_SS13		BIT(13)
 #endif
 
+#define XGBE_VEND2_MAC_AUTO_SW		BIT(9)
+
 /* MDIO mask values */
 #define XGBE_AN_CL73_INT_CMPLT		BIT(0)
 #define XGBE_AN_CL73_INC_LINK		BIT(1)
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c
index 71449edbb76d..fb5b7eceb73f 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c
@@ -266,6 +266,10 @@ static void xgbe_an37_set(struct xgbe_prv_data *pdata, bool enable,
 		reg |= MDIO_VEND2_CTRL1_AN_RESTART;
 
 	XMDIO_WRITE(pdata, MDIO_MMD_VEND2, MDIO_CTRL1, reg);
+
+	reg = XMDIO_READ(pdata, MDIO_MMD_VEND2, MDIO_PCS_DIG_CTRL);
+	reg |= XGBE_VEND2_MAC_AUTO_SW;
+	XMDIO_WRITE(pdata, MDIO_MMD_VEND2, MDIO_PCS_DIG_CTRL, reg);
 }
 
 static void xgbe_an37_restart(struct xgbe_prv_data *pdata)
@@ -894,6 +898,11 @@ static void xgbe_an37_init(struct xgbe_prv_data *pdata)
 
 	netif_dbg(pdata, link, pdata->netdev, "CL37 AN (%s) initialized\n",
 		  (pdata->an_mode == XGBE_AN_MODE_CL37) ? "BaseX" : "SGMII");
+
+	reg = XMDIO_READ(pdata, MDIO_MMD_AN, MDIO_CTRL1);
+	reg &= ~MDIO_AN_CTRL1_ENABLE;
+	XMDIO_WRITE(pdata, MDIO_MMD_AN, MDIO_CTRL1, reg);
+
 }
 
 static void xgbe_an73_init(struct xgbe_prv_data *pdata)
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe.h b/drivers/net/ethernet/amd/xgbe/xgbe.h
index 6359bb87dc13..057379cd43ba 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe.h
+++ b/drivers/net/ethernet/amd/xgbe/xgbe.h
@@ -183,12 +183,12 @@
 #define XGBE_LINK_TIMEOUT		5
 #define XGBE_KR_TRAINING_WAIT_ITER	50
 
-#define XGBE_SGMII_AN_LINK_STATUS	BIT(1)
+#define XGBE_SGMII_AN_LINK_DUPLEX	BIT(1)
 #define XGBE_SGMII_AN_LINK_SPEED	(BIT(2) | BIT(3))
 #define XGBE_SGMII_AN_LINK_SPEED_10	0x00
 #define XGBE_SGMII_AN_LINK_SPEED_100	0x04
 #define XGBE_SGMII_AN_LINK_SPEED_1000	0x08
-#define XGBE_SGMII_AN_LINK_DUPLEX	BIT(4)
+#define XGBE_SGMII_AN_LINK_STATUS	BIT(4)
 
 /* ECC correctable error notification window (seconds) */
 #define XGBE_ECC_LIMIT			60

From aaf2b2480375099c022a82023e1cd772bf1c6a5d Mon Sep 17 00:00:00 2001
From: Alok Tiwari <alok.a.tiwari@oracle.com>
Date: Sat, 28 Jun 2025 07:56:05 -0700
Subject: [PATCH 1101/1334] enic: fix incorrect MTU comparison in
 enic_change_mtu()

The comparison in enic_change_mtu() incorrectly used the current
netdev->mtu instead of the new new_mtu value when warning about
an MTU exceeding the port MTU. This could suppress valid warnings
or issue incorrect ones.

Fix the condition and log to properly reflect the new_mtu.

Fixes: ab123fe071c9 ("enic: handle mtu change for vf properly")
Signed-off-by: Alok Tiwari <alok.a.tiwari@oracle.com>
Acked-by: John Daley <johndale@cisco.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250628145612.476096-1-alok.a.tiwari@oracle.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/cisco/enic/enic_main.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/cisco/enic/enic_main.c b/drivers/net/ethernet/cisco/enic/enic_main.c
index 773f5ad972a2..6bc8dfdb3d4b 100644
--- a/drivers/net/ethernet/cisco/enic/enic_main.c
+++ b/drivers/net/ethernet/cisco/enic/enic_main.c
@@ -1864,10 +1864,10 @@ static int enic_change_mtu(struct net_device *netdev, int new_mtu)
 	if (enic_is_dynamic(enic) || enic_is_sriov_vf(enic))
 		return -EOPNOTSUPP;
 
-	if (netdev->mtu > enic->port_mtu)
+	if (new_mtu > enic->port_mtu)
 		netdev_warn(netdev,
 			    "interface MTU (%d) set higher than port MTU (%d)\n",
-			    netdev->mtu, enic->port_mtu);
+			    new_mtu, enic->port_mtu);
 
 	return _enic_change_mtu(netdev, new_mtu);
 }

From 34a500caf48c47d5171f4aa1f237da39b07c6157 Mon Sep 17 00:00:00 2001
From: Kohei Enju <enjuk@amazon.com>
Date: Sun, 29 Jun 2025 12:06:31 +0900
Subject: [PATCH 1102/1334] rose: fix dangling neighbour pointers in
 rose_rt_device_down()

There are two bugs in rose_rt_device_down() that can cause
use-after-free:

1. The loop bound `t->count` is modified within the loop, which can
   cause the loop to terminate early and miss some entries.

2. When removing an entry from the neighbour array, the subsequent entries
   are moved up to fill the gap, but the loop index `i` is still
   incremented, causing the next entry to be skipped.

For example, if a node has three neighbours (A, A, B) with count=3 and A
is being removed, the second A is not checked.

    i=0: (A, A, B) -> (A, B) with count=2
          ^ checked
    i=1: (A, B)    -> (A, B) with count=2
             ^ checked (B, not A!)
    i=2: (doesn't occur because i < count is false)

This leaves the second A in the array with count=2, but the rose_neigh
structure has been freed. Code that accesses these entries assumes that
the first `count` entries are valid pointers, causing a use-after-free
when it accesses the dangling pointer.

Fix both issues by iterating over the array in reverse order with a fixed
loop bound. This ensures that all entries are examined and that the removal
of an entry doesn't affect subsequent iterations.

Reported-by: syzbot+e04e2c007ba2c80476cb@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=e04e2c007ba2c80476cb
Tested-by: syzbot+e04e2c007ba2c80476cb@syzkaller.appspotmail.com
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Kohei Enju <enjuk@amazon.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250629030833.6680-1-enjuk@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/rose/rose_route.c | 15 ++++-----------
 1 file changed, 4 insertions(+), 11 deletions(-)

diff --git a/net/rose/rose_route.c b/net/rose/rose_route.c
index 2dd6bd3a3011..b72bf8a08d48 100644
--- a/net/rose/rose_route.c
+++ b/net/rose/rose_route.c
@@ -497,22 +497,15 @@ void rose_rt_device_down(struct net_device *dev)
 			t         = rose_node;
 			rose_node = rose_node->next;
 
-			for (i = 0; i < t->count; i++) {
+			for (i = t->count - 1; i >= 0; i--) {
 				if (t->neighbour[i] != s)
 					continue;
 
 				t->count--;
 
-				switch (i) {
-				case 0:
-					t->neighbour[0] = t->neighbour[1];
-					fallthrough;
-				case 1:
-					t->neighbour[1] = t->neighbour[2];
-					break;
-				case 2:
-					break;
-				}
+				memmove(&t->neighbour[i], &t->neighbour[i + 1],
+					sizeof(t->neighbour[0]) *
+						(t->count - i));
 			}
 
 			if (t->count <= 0)

From 5307dce878d4126e1b375587318955bd019c3741 Mon Sep 17 00:00:00 2001
From: Thomas Zimmermann <tzimmermann@suse.de>
Date: Mon, 30 Jun 2025 10:36:47 +0200
Subject: [PATCH 1103/1334] drm/gem: Acquire references on GEM handles for
 framebuffers
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

A GEM handle can be released while the GEM buffer object is attached
to a DRM framebuffer. This leads to the release of the dma-buf backing
the buffer object, if any. [1] Trying to use the framebuffer in further
mode-setting operations leads to a segmentation fault. Most easily
happens with driver that use shadow planes for vmap-ing the dma-buf
during a page flip. An example is shown below.

[  156.791968] ------------[ cut here ]------------
[  156.796830] WARNING: CPU: 2 PID: 2255 at drivers/dma-buf/dma-buf.c:1527 dma_buf_vmap+0x224/0x430
[...]
[  156.942028] RIP: 0010:dma_buf_vmap+0x224/0x430
[  157.043420] Call Trace:
[  157.045898]  <TASK>
[  157.048030]  ? show_trace_log_lvl+0x1af/0x2c0
[  157.052436]  ? show_trace_log_lvl+0x1af/0x2c0
[  157.056836]  ? show_trace_log_lvl+0x1af/0x2c0
[  157.061253]  ? drm_gem_shmem_vmap+0x74/0x710
[  157.065567]  ? dma_buf_vmap+0x224/0x430
[  157.069446]  ? __warn.cold+0x58/0xe4
[  157.073061]  ? dma_buf_vmap+0x224/0x430
[  157.077111]  ? report_bug+0x1dd/0x390
[  157.080842]  ? handle_bug+0x5e/0xa0
[  157.084389]  ? exc_invalid_op+0x14/0x50
[  157.088291]  ? asm_exc_invalid_op+0x16/0x20
[  157.092548]  ? dma_buf_vmap+0x224/0x430
[  157.096663]  ? dma_resv_get_singleton+0x6d/0x230
[  157.101341]  ? __pfx_dma_buf_vmap+0x10/0x10
[  157.105588]  ? __pfx_dma_resv_get_singleton+0x10/0x10
[  157.110697]  drm_gem_shmem_vmap+0x74/0x710
[  157.114866]  drm_gem_vmap+0xa9/0x1b0
[  157.118763]  drm_gem_vmap_unlocked+0x46/0xa0
[  157.123086]  drm_gem_fb_vmap+0xab/0x300
[  157.126979]  drm_atomic_helper_prepare_planes.part.0+0x487/0xb10
[  157.133032]  ? lockdep_init_map_type+0x19d/0x880
[  157.137701]  drm_atomic_helper_commit+0x13d/0x2e0
[  157.142671]  ? drm_atomic_nonblocking_commit+0xa0/0x180
[  157.147988]  drm_mode_atomic_ioctl+0x766/0xe40
[...]
[  157.346424] ---[ end trace 0000000000000000 ]---

Acquiring GEM handles for the framebuffer's GEM buffer objects prevents
this from happening. The framebuffer's cleanup later puts the handle
references.

Commit 1a148af06000 ("drm/gem-shmem: Use dma_buf from GEM object
instance") triggers the segmentation fault easily by using the dma-buf
field more widely. The underlying issue with reference counting has
been present before.

v2:
- acquire the handle instead of the BO (Christian)
- fix comment style (Christian)
- drop the Fixes tag (Christian)
- rename err_ gotos
- add missing Link tag

Suggested-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>
Link: https://elixir.bootlin.com/linux/v6.15/source/drivers/gpu/drm/drm_gem.c#L241 # [1]
Cc: Thomas Zimmermann <tzimmermann@suse.de>
Cc: Anusha Srivatsa <asrivats@redhat.com>
Cc: Christian König <christian.koenig@amd.com>
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Cc: Maxime Ripard <mripard@kernel.org>
Cc: Sumit Semwal <sumit.semwal@linaro.org>
Cc: "Christian König" <christian.koenig@amd.com>
Cc: linux-media@vger.kernel.org
Cc: dri-devel@lists.freedesktop.org
Cc: linaro-mm-sig@lists.linaro.org
Cc: <stable@vger.kernel.org>
Reviewed-by: Christian König <christian.koenig@amd.com>
Link: https://lore.kernel.org/r/20250630084001.293053-1-tzimmermann@suse.de
---
 drivers/gpu/drm/drm_gem.c                    | 44 ++++++++++++++++++--
 drivers/gpu/drm/drm_gem_framebuffer_helper.c | 16 +++----
 drivers/gpu/drm/drm_internal.h               |  2 +
 3 files changed, 51 insertions(+), 11 deletions(-)

diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c
index 1e659d2660f7..4bf0a76bb35e 100644
--- a/drivers/gpu/drm/drm_gem.c
+++ b/drivers/gpu/drm/drm_gem.c
@@ -212,6 +212,35 @@ void drm_gem_private_object_fini(struct drm_gem_object *obj)
 }
 EXPORT_SYMBOL(drm_gem_private_object_fini);
 
+static void drm_gem_object_handle_get(struct drm_gem_object *obj)
+{
+	struct drm_device *dev = obj->dev;
+
+	drm_WARN_ON(dev, !mutex_is_locked(&dev->object_name_lock));
+
+	if (obj->handle_count++ == 0)
+		drm_gem_object_get(obj);
+}
+
+/**
+ * drm_gem_object_handle_get_unlocked - acquire reference on user-space handles
+ * @obj: GEM object
+ *
+ * Acquires a reference on the GEM buffer object's handle. Required
+ * to keep the GEM object alive. Call drm_gem_object_handle_put_unlocked()
+ * to release the reference.
+ */
+void drm_gem_object_handle_get_unlocked(struct drm_gem_object *obj)
+{
+	struct drm_device *dev = obj->dev;
+
+	guard(mutex)(&dev->object_name_lock);
+
+	drm_WARN_ON(dev, !obj->handle_count); /* first ref taken in create-tail helper */
+	drm_gem_object_handle_get(obj);
+}
+EXPORT_SYMBOL(drm_gem_object_handle_get_unlocked);
+
 /**
  * drm_gem_object_handle_free - release resources bound to userspace handles
  * @obj: GEM object to clean up.
@@ -242,8 +271,14 @@ static void drm_gem_object_exported_dma_buf_free(struct drm_gem_object *obj)
 	}
 }
 
-static void
-drm_gem_object_handle_put_unlocked(struct drm_gem_object *obj)
+/**
+ * drm_gem_object_handle_put_unlocked - releases reference on user-space handles
+ * @obj: GEM object
+ *
+ * Releases a reference on the GEM buffer object's handle. Possibly releases
+ * the GEM buffer object and associated dma-buf objects.
+ */
+void drm_gem_object_handle_put_unlocked(struct drm_gem_object *obj)
 {
 	struct drm_device *dev = obj->dev;
 	bool final = false;
@@ -268,6 +303,7 @@ drm_gem_object_handle_put_unlocked(struct drm_gem_object *obj)
 	if (final)
 		drm_gem_object_put(obj);
 }
+EXPORT_SYMBOL(drm_gem_object_handle_put_unlocked);
 
 /*
  * Called at device or object close to release the file's
@@ -389,8 +425,8 @@ drm_gem_handle_create_tail(struct drm_file *file_priv,
 	int ret;
 
 	WARN_ON(!mutex_is_locked(&dev->object_name_lock));
-	if (obj->handle_count++ == 0)
-		drm_gem_object_get(obj);
+
+	drm_gem_object_handle_get(obj);
 
 	/*
 	 * Get the user-visible handle using idr.  Preload and perform
diff --git a/drivers/gpu/drm/drm_gem_framebuffer_helper.c b/drivers/gpu/drm/drm_gem_framebuffer_helper.c
index 6f72e7a0f427..14a87788695d 100644
--- a/drivers/gpu/drm/drm_gem_framebuffer_helper.c
+++ b/drivers/gpu/drm/drm_gem_framebuffer_helper.c
@@ -99,7 +99,7 @@ void drm_gem_fb_destroy(struct drm_framebuffer *fb)
 	unsigned int i;
 
 	for (i = 0; i < fb->format->num_planes; i++)
-		drm_gem_object_put(fb->obj[i]);
+		drm_gem_object_handle_put_unlocked(fb->obj[i]);
 
 	drm_framebuffer_cleanup(fb);
 	kfree(fb);
@@ -182,8 +182,10 @@ int drm_gem_fb_init_with_funcs(struct drm_device *dev,
 		if (!objs[i]) {
 			drm_dbg_kms(dev, "Failed to lookup GEM object\n");
 			ret = -ENOENT;
-			goto err_gem_object_put;
+			goto err_gem_object_handle_put_unlocked;
 		}
+		drm_gem_object_handle_get_unlocked(objs[i]);
+		drm_gem_object_put(objs[i]);
 
 		min_size = (height - 1) * mode_cmd->pitches[i]
 			 + drm_format_info_min_pitch(info, i, width)
@@ -193,22 +195,22 @@ int drm_gem_fb_init_with_funcs(struct drm_device *dev,
 			drm_dbg_kms(dev,
 				    "GEM object size (%zu) smaller than minimum size (%u) for plane %d\n",
 				    objs[i]->size, min_size, i);
-			drm_gem_object_put(objs[i]);
+			drm_gem_object_handle_put_unlocked(objs[i]);
 			ret = -EINVAL;
-			goto err_gem_object_put;
+			goto err_gem_object_handle_put_unlocked;
 		}
 	}
 
 	ret = drm_gem_fb_init(dev, fb, mode_cmd, objs, i, funcs);
 	if (ret)
-		goto err_gem_object_put;
+		goto err_gem_object_handle_put_unlocked;
 
 	return 0;
 
-err_gem_object_put:
+err_gem_object_handle_put_unlocked:
 	while (i > 0) {
 		--i;
-		drm_gem_object_put(objs[i]);
+		drm_gem_object_handle_put_unlocked(objs[i]);
 	}
 	return ret;
 }
diff --git a/drivers/gpu/drm/drm_internal.h b/drivers/gpu/drm/drm_internal.h
index e44f28fd81d3..be77d61a16ce 100644
--- a/drivers/gpu/drm/drm_internal.h
+++ b/drivers/gpu/drm/drm_internal.h
@@ -161,6 +161,8 @@ void drm_sysfs_lease_event(struct drm_device *dev);
 
 /* drm_gem.c */
 int drm_gem_init(struct drm_device *dev);
+void drm_gem_object_handle_get_unlocked(struct drm_gem_object *obj);
+void drm_gem_object_handle_put_unlocked(struct drm_gem_object *obj);
 int drm_gem_handle_create_tail(struct drm_file *file_priv,
 			       struct drm_gem_object *obj,
 			       u32 *handlep);

From 8dab34ca77293b409c3223636dde915a22656748 Mon Sep 17 00:00:00 2001
From: Kurt Borja <kuurtb@gmail.com>
Date: Mon, 30 Jun 2025 14:31:19 -0300
Subject: [PATCH 1104/1334] platform/x86: think-lmi: Create ksets consecutively
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Avoid entering tlmi_release_attr() in error paths if both ksets are not
yet created.

This is accomplished by initializing them side by side.

Reviewed-by: Mark Pearson <mpearson-lenovo@squebb.ca>
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Cc: stable@vger.kernel.org
Signed-off-by: Kurt Borja <kuurtb@gmail.com>
Link: https://lore.kernel.org/r/20250630-lmi-fix-v3-1-ce4f81c9c481@gmail.com
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/think-lmi.c | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

diff --git a/drivers/platform/x86/think-lmi.c b/drivers/platform/x86/think-lmi.c
index 28ce475f6c37..39306951f234 100644
--- a/drivers/platform/x86/think-lmi.c
+++ b/drivers/platform/x86/think-lmi.c
@@ -1455,6 +1455,14 @@ static int tlmi_sysfs_init(void)
 		goto fail_device_created;
 	}
 
+	tlmi_priv.authentication_kset = kset_create_and_add("authentication", NULL,
+							    &tlmi_priv.class_dev->kobj);
+	if (!tlmi_priv.authentication_kset) {
+		kset_unregister(tlmi_priv.attribute_kset);
+		ret = -ENOMEM;
+		goto fail_device_created;
+	}
+
 	for (i = 0; i < TLMI_SETTINGS_COUNT; i++) {
 		/* Check if index is a valid setting - skip if it isn't */
 		if (!tlmi_priv.setting[i])
@@ -1496,12 +1504,6 @@ static int tlmi_sysfs_init(void)
 	}
 
 	/* Create authentication entries */
-	tlmi_priv.authentication_kset = kset_create_and_add("authentication", NULL,
-								&tlmi_priv.class_dev->kobj);
-	if (!tlmi_priv.authentication_kset) {
-		ret = -ENOMEM;
-		goto fail_create_attr;
-	}
 	tlmi_priv.pwd_admin->kobj.kset = tlmi_priv.authentication_kset;
 	ret = kobject_add(&tlmi_priv.pwd_admin->kobj, NULL, "%s", "Admin");
 	if (ret)

From 9110056fe10b0519529bdbbac37311a5037ea0c2 Mon Sep 17 00:00:00 2001
From: Kurt Borja <kuurtb@gmail.com>
Date: Mon, 30 Jun 2025 14:31:20 -0300
Subject: [PATCH 1105/1334] platform/x86: think-lmi: Fix kobject cleanup
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In tlmi_analyze(), allocated structs with an embedded kobject are freed
in error paths after the they were already initialized.

Fix this by first by avoiding the initialization of kobjects in
tlmi_analyze() and then by correctly cleaning them up in
tlmi_release_attr() using their kset's kobject list.

Fixes: a40cd7ef22fb ("platform/x86: think-lmi: Add WMI interface support on Lenovo platforms")
Fixes: 30e78435d3bf ("platform/x86: think-lmi: Split kobject_init() and kobject_add() calls")
Cc: stable@vger.kernel.org
Reviewed-by: Mark Pearson <mpearson-lenovo@squebb.ca>
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Kurt Borja <kuurtb@gmail.com>
Link: https://lore.kernel.org/r/20250630-lmi-fix-v3-2-ce4f81c9c481@gmail.com
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/think-lmi.c | 35 +++++++++++++++++---------------
 1 file changed, 19 insertions(+), 16 deletions(-)

diff --git a/drivers/platform/x86/think-lmi.c b/drivers/platform/x86/think-lmi.c
index 39306951f234..69f361f21f0f 100644
--- a/drivers/platform/x86/think-lmi.c
+++ b/drivers/platform/x86/think-lmi.c
@@ -1380,13 +1380,13 @@ static struct kobj_attribute debug_cmd = __ATTR_WO(debug_cmd);
 /* ---- Initialisation --------------------------------------------------------- */
 static void tlmi_release_attr(void)
 {
+	struct kobject *pos, *n;
 	int i;
 
 	/* Attribute structures */
 	for (i = 0; i < TLMI_SETTINGS_COUNT; i++) {
 		if (tlmi_priv.setting[i]) {
 			sysfs_remove_group(&tlmi_priv.setting[i]->kobj, &tlmi_attr_group);
-			kobject_put(&tlmi_priv.setting[i]->kobj);
 		}
 	}
 	sysfs_remove_file(&tlmi_priv.attribute_kset->kobj, &pending_reboot.attr);
@@ -1395,6 +1395,9 @@ static void tlmi_release_attr(void)
 	if (tlmi_priv.can_debug_cmd && debug_support)
 		sysfs_remove_file(&tlmi_priv.attribute_kset->kobj, &debug_cmd.attr);
 
+	list_for_each_entry_safe(pos, n, &tlmi_priv.attribute_kset->list, entry)
+		kobject_put(pos);
+
 	kset_unregister(tlmi_priv.attribute_kset);
 
 	/* Free up any saved signatures */
@@ -1403,19 +1406,17 @@ static void tlmi_release_attr(void)
 
 	/* Authentication structures */
 	sysfs_remove_group(&tlmi_priv.pwd_admin->kobj, &auth_attr_group);
-	kobject_put(&tlmi_priv.pwd_admin->kobj);
 	sysfs_remove_group(&tlmi_priv.pwd_power->kobj, &auth_attr_group);
-	kobject_put(&tlmi_priv.pwd_power->kobj);
 
 	if (tlmi_priv.opcode_support) {
 		sysfs_remove_group(&tlmi_priv.pwd_system->kobj, &auth_attr_group);
-		kobject_put(&tlmi_priv.pwd_system->kobj);
 		sysfs_remove_group(&tlmi_priv.pwd_hdd->kobj, &auth_attr_group);
-		kobject_put(&tlmi_priv.pwd_hdd->kobj);
 		sysfs_remove_group(&tlmi_priv.pwd_nvme->kobj, &auth_attr_group);
-		kobject_put(&tlmi_priv.pwd_nvme->kobj);
 	}
 
+	list_for_each_entry_safe(pos, n, &tlmi_priv.authentication_kset->list, entry)
+		kobject_put(pos);
+
 	kset_unregister(tlmi_priv.authentication_kset);
 }
 
@@ -1479,8 +1480,8 @@ static int tlmi_sysfs_init(void)
 
 		/* Build attribute */
 		tlmi_priv.setting[i]->kobj.kset = tlmi_priv.attribute_kset;
-		ret = kobject_add(&tlmi_priv.setting[i]->kobj, NULL,
-				  "%s", tlmi_priv.setting[i]->display_name);
+		ret = kobject_init_and_add(&tlmi_priv.setting[i]->kobj, &tlmi_attr_setting_ktype,
+					   NULL, "%s", tlmi_priv.setting[i]->display_name);
 		if (ret)
 			goto fail_create_attr;
 
@@ -1505,7 +1506,8 @@ static int tlmi_sysfs_init(void)
 
 	/* Create authentication entries */
 	tlmi_priv.pwd_admin->kobj.kset = tlmi_priv.authentication_kset;
-	ret = kobject_add(&tlmi_priv.pwd_admin->kobj, NULL, "%s", "Admin");
+	ret = kobject_init_and_add(&tlmi_priv.pwd_admin->kobj, &tlmi_pwd_setting_ktype,
+				   NULL, "%s", "Admin");
 	if (ret)
 		goto fail_create_attr;
 
@@ -1514,7 +1516,8 @@ static int tlmi_sysfs_init(void)
 		goto fail_create_attr;
 
 	tlmi_priv.pwd_power->kobj.kset = tlmi_priv.authentication_kset;
-	ret = kobject_add(&tlmi_priv.pwd_power->kobj, NULL, "%s", "Power-on");
+	ret = kobject_init_and_add(&tlmi_priv.pwd_power->kobj, &tlmi_pwd_setting_ktype,
+				   NULL, "%s", "Power-on");
 	if (ret)
 		goto fail_create_attr;
 
@@ -1524,7 +1527,8 @@ static int tlmi_sysfs_init(void)
 
 	if (tlmi_priv.opcode_support) {
 		tlmi_priv.pwd_system->kobj.kset = tlmi_priv.authentication_kset;
-		ret = kobject_add(&tlmi_priv.pwd_system->kobj, NULL, "%s", "System");
+		ret = kobject_init_and_add(&tlmi_priv.pwd_system->kobj, &tlmi_pwd_setting_ktype,
+					   NULL, "%s", "System");
 		if (ret)
 			goto fail_create_attr;
 
@@ -1533,7 +1537,8 @@ static int tlmi_sysfs_init(void)
 			goto fail_create_attr;
 
 		tlmi_priv.pwd_hdd->kobj.kset = tlmi_priv.authentication_kset;
-		ret = kobject_add(&tlmi_priv.pwd_hdd->kobj, NULL, "%s", "HDD");
+		ret = kobject_init_and_add(&tlmi_priv.pwd_hdd->kobj, &tlmi_pwd_setting_ktype,
+					   NULL, "%s", "HDD");
 		if (ret)
 			goto fail_create_attr;
 
@@ -1542,7 +1547,8 @@ static int tlmi_sysfs_init(void)
 			goto fail_create_attr;
 
 		tlmi_priv.pwd_nvme->kobj.kset = tlmi_priv.authentication_kset;
-		ret = kobject_add(&tlmi_priv.pwd_nvme->kobj, NULL, "%s", "NVMe");
+		ret = kobject_init_and_add(&tlmi_priv.pwd_nvme->kobj, &tlmi_pwd_setting_ktype,
+					   NULL, "%s", "NVMe");
 		if (ret)
 			goto fail_create_attr;
 
@@ -1579,8 +1585,6 @@ static struct tlmi_pwd_setting *tlmi_create_auth(const char *pwd_type,
 	new_pwd->maxlen = tlmi_priv.pwdcfg.core.max_length;
 	new_pwd->index = 0;
 
-	kobject_init(&new_pwd->kobj, &tlmi_pwd_setting_ktype);
-
 	return new_pwd;
 }
 
@@ -1685,7 +1689,6 @@ static int tlmi_analyze(struct wmi_device *wdev)
 		if (setting->possible_values)
 			strreplace(setting->possible_values, ',', ';');
 
-		kobject_init(&setting->kobj, &tlmi_attr_setting_ktype);
 		tlmi_priv.setting[i] = setting;
 		kfree(item);
 	}

From 4f30f946f27b7f044cf8f3f1f353dee1dcd3517a Mon Sep 17 00:00:00 2001
From: Kurt Borja <kuurtb@gmail.com>
Date: Mon, 30 Jun 2025 14:31:21 -0300
Subject: [PATCH 1106/1334] platform/x86: think-lmi: Fix sysfs group cleanup
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Many error paths in tlmi_sysfs_init() lead to sysfs groups being removed
when they were not even created.

Fix this by letting the kobject core manage these groups through their
kobj_type's defult_groups.

Fixes: a40cd7ef22fb ("platform/x86: think-lmi: Add WMI interface support on Lenovo platforms")
Cc: stable@vger.kernel.org
Reviewed-by: Mark Pearson <mpearson-lenovo@squebb.ca>
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Kurt Borja <kuurtb@gmail.com>
Link: https://lore.kernel.org/r/20250630-lmi-fix-v3-3-ce4f81c9c481@gmail.com
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/think-lmi.c | 43 +++-----------------------------
 1 file changed, 4 insertions(+), 39 deletions(-)

diff --git a/drivers/platform/x86/think-lmi.c b/drivers/platform/x86/think-lmi.c
index 69f361f21f0f..b73b84fdb15e 100644
--- a/drivers/platform/x86/think-lmi.c
+++ b/drivers/platform/x86/think-lmi.c
@@ -973,6 +973,7 @@ static const struct attribute_group auth_attr_group = {
 	.is_visible = auth_attr_is_visible,
 	.attrs = auth_attrs,
 };
+__ATTRIBUTE_GROUPS(auth_attr);
 
 /* ---- Attributes sysfs --------------------------------------------------------- */
 static ssize_t display_name_show(struct kobject *kobj, struct kobj_attribute *attr,
@@ -1188,6 +1189,7 @@ static const struct attribute_group tlmi_attr_group = {
 	.is_visible = attr_is_visible,
 	.attrs = tlmi_attrs,
 };
+__ATTRIBUTE_GROUPS(tlmi_attr);
 
 static void tlmi_attr_setting_release(struct kobject *kobj)
 {
@@ -1207,11 +1209,13 @@ static void tlmi_pwd_setting_release(struct kobject *kobj)
 static const struct kobj_type tlmi_attr_setting_ktype = {
 	.release        = &tlmi_attr_setting_release,
 	.sysfs_ops	= &kobj_sysfs_ops,
+	.default_groups = tlmi_attr_groups,
 };
 
 static const struct kobj_type tlmi_pwd_setting_ktype = {
 	.release        = &tlmi_pwd_setting_release,
 	.sysfs_ops	= &kobj_sysfs_ops,
+	.default_groups = auth_attr_groups,
 };
 
 static ssize_t pending_reboot_show(struct kobject *kobj, struct kobj_attribute *attr,
@@ -1381,14 +1385,8 @@ static struct kobj_attribute debug_cmd = __ATTR_WO(debug_cmd);
 static void tlmi_release_attr(void)
 {
 	struct kobject *pos, *n;
-	int i;
 
 	/* Attribute structures */
-	for (i = 0; i < TLMI_SETTINGS_COUNT; i++) {
-		if (tlmi_priv.setting[i]) {
-			sysfs_remove_group(&tlmi_priv.setting[i]->kobj, &tlmi_attr_group);
-		}
-	}
 	sysfs_remove_file(&tlmi_priv.attribute_kset->kobj, &pending_reboot.attr);
 	sysfs_remove_file(&tlmi_priv.attribute_kset->kobj, &save_settings.attr);
 
@@ -1405,15 +1403,6 @@ static void tlmi_release_attr(void)
 	kfree(tlmi_priv.pwd_admin->save_signature);
 
 	/* Authentication structures */
-	sysfs_remove_group(&tlmi_priv.pwd_admin->kobj, &auth_attr_group);
-	sysfs_remove_group(&tlmi_priv.pwd_power->kobj, &auth_attr_group);
-
-	if (tlmi_priv.opcode_support) {
-		sysfs_remove_group(&tlmi_priv.pwd_system->kobj, &auth_attr_group);
-		sysfs_remove_group(&tlmi_priv.pwd_hdd->kobj, &auth_attr_group);
-		sysfs_remove_group(&tlmi_priv.pwd_nvme->kobj, &auth_attr_group);
-	}
-
 	list_for_each_entry_safe(pos, n, &tlmi_priv.authentication_kset->list, entry)
 		kobject_put(pos);
 
@@ -1484,10 +1473,6 @@ static int tlmi_sysfs_init(void)
 					   NULL, "%s", tlmi_priv.setting[i]->display_name);
 		if (ret)
 			goto fail_create_attr;
-
-		ret = sysfs_create_group(&tlmi_priv.setting[i]->kobj, &tlmi_attr_group);
-		if (ret)
-			goto fail_create_attr;
 	}
 
 	ret = sysfs_create_file(&tlmi_priv.attribute_kset->kobj, &pending_reboot.attr);
@@ -1511,20 +1496,12 @@ static int tlmi_sysfs_init(void)
 	if (ret)
 		goto fail_create_attr;
 
-	ret = sysfs_create_group(&tlmi_priv.pwd_admin->kobj, &auth_attr_group);
-	if (ret)
-		goto fail_create_attr;
-
 	tlmi_priv.pwd_power->kobj.kset = tlmi_priv.authentication_kset;
 	ret = kobject_init_and_add(&tlmi_priv.pwd_power->kobj, &tlmi_pwd_setting_ktype,
 				   NULL, "%s", "Power-on");
 	if (ret)
 		goto fail_create_attr;
 
-	ret = sysfs_create_group(&tlmi_priv.pwd_power->kobj, &auth_attr_group);
-	if (ret)
-		goto fail_create_attr;
-
 	if (tlmi_priv.opcode_support) {
 		tlmi_priv.pwd_system->kobj.kset = tlmi_priv.authentication_kset;
 		ret = kobject_init_and_add(&tlmi_priv.pwd_system->kobj, &tlmi_pwd_setting_ktype,
@@ -1532,29 +1509,17 @@ static int tlmi_sysfs_init(void)
 		if (ret)
 			goto fail_create_attr;
 
-		ret = sysfs_create_group(&tlmi_priv.pwd_system->kobj, &auth_attr_group);
-		if (ret)
-			goto fail_create_attr;
-
 		tlmi_priv.pwd_hdd->kobj.kset = tlmi_priv.authentication_kset;
 		ret = kobject_init_and_add(&tlmi_priv.pwd_hdd->kobj, &tlmi_pwd_setting_ktype,
 					   NULL, "%s", "HDD");
 		if (ret)
 			goto fail_create_attr;
 
-		ret = sysfs_create_group(&tlmi_priv.pwd_hdd->kobj, &auth_attr_group);
-		if (ret)
-			goto fail_create_attr;
-
 		tlmi_priv.pwd_nvme->kobj.kset = tlmi_priv.authentication_kset;
 		ret = kobject_init_and_add(&tlmi_priv.pwd_nvme->kobj, &tlmi_pwd_setting_ktype,
 					   NULL, "%s", "NVMe");
 		if (ret)
 			goto fail_create_attr;
-
-		ret = sysfs_create_group(&tlmi_priv.pwd_nvme->kobj, &auth_attr_group);
-		if (ret)
-			goto fail_create_attr;
 	}
 
 	return ret;

From 561aa0e22b70a5e7246b73d62a824b3aef3fc375 Mon Sep 17 00:00:00 2001
From: Thomas Fourier <fourier.thomas@gmail.com>
Date: Mon, 30 Jun 2025 10:36:43 +0200
Subject: [PATCH 1107/1334] nui: Fix dma_mapping_error() check

dma_map_XXX() functions return values DMA_MAPPING_ERROR as error values
which is often ~0.  The error value should be tested with
dma_mapping_error().

This patch creates a new function in niu_ops to test if the mapping
failed.  The test is fixed in niu_rbr_add_page(), added in
niu_start_xmit() and the successfully mapped pages are unmaped upon error.

Fixes: ec2deec1f352 ("niu: Fix to check for dma mapping errors.")
Signed-off-by: Thomas Fourier <fourier.thomas@gmail.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/sun/niu.c | 31 ++++++++++++++++++++++++++++++-
 drivers/net/ethernet/sun/niu.h |  4 ++++
 2 files changed, 34 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/sun/niu.c b/drivers/net/ethernet/sun/niu.c
index ddca8fc7883e..26119d02a94d 100644
--- a/drivers/net/ethernet/sun/niu.c
+++ b/drivers/net/ethernet/sun/niu.c
@@ -3336,7 +3336,7 @@ static int niu_rbr_add_page(struct niu *np, struct rx_ring_info *rp,
 
 	addr = np->ops->map_page(np->device, page, 0,
 				 PAGE_SIZE, DMA_FROM_DEVICE);
-	if (!addr) {
+	if (np->ops->mapping_error(np->device, addr)) {
 		__free_page(page);
 		return -ENOMEM;
 	}
@@ -6676,6 +6676,8 @@ static netdev_tx_t niu_start_xmit(struct sk_buff *skb,
 	len = skb_headlen(skb);
 	mapping = np->ops->map_single(np->device, skb->data,
 				      len, DMA_TO_DEVICE);
+	if (np->ops->mapping_error(np->device, mapping))
+		goto out_drop;
 
 	prod = rp->prod;
 
@@ -6717,6 +6719,8 @@ static netdev_tx_t niu_start_xmit(struct sk_buff *skb,
 		mapping = np->ops->map_page(np->device, skb_frag_page(frag),
 					    skb_frag_off(frag), len,
 					    DMA_TO_DEVICE);
+		if (np->ops->mapping_error(np->device, mapping))
+			goto out_unmap;
 
 		rp->tx_buffs[prod].skb = NULL;
 		rp->tx_buffs[prod].mapping = mapping;
@@ -6741,6 +6745,19 @@ static netdev_tx_t niu_start_xmit(struct sk_buff *skb,
 out:
 	return NETDEV_TX_OK;
 
+out_unmap:
+	while (i--) {
+		const skb_frag_t *frag;
+
+		prod = PREVIOUS_TX(rp, prod);
+		frag = &skb_shinfo(skb)->frags[i];
+		np->ops->unmap_page(np->device, rp->tx_buffs[prod].mapping,
+				    skb_frag_size(frag), DMA_TO_DEVICE);
+	}
+
+	np->ops->unmap_single(np->device, rp->tx_buffs[rp->prod].mapping,
+			      skb_headlen(skb), DMA_TO_DEVICE);
+
 out_drop:
 	rp->tx_errors++;
 	kfree_skb(skb);
@@ -9644,6 +9661,11 @@ static void niu_pci_unmap_single(struct device *dev, u64 dma_address,
 	dma_unmap_single(dev, dma_address, size, direction);
 }
 
+static int niu_pci_mapping_error(struct device *dev, u64 addr)
+{
+	return dma_mapping_error(dev, addr);
+}
+
 static const struct niu_ops niu_pci_ops = {
 	.alloc_coherent	= niu_pci_alloc_coherent,
 	.free_coherent	= niu_pci_free_coherent,
@@ -9651,6 +9673,7 @@ static const struct niu_ops niu_pci_ops = {
 	.unmap_page	= niu_pci_unmap_page,
 	.map_single	= niu_pci_map_single,
 	.unmap_single	= niu_pci_unmap_single,
+	.mapping_error	= niu_pci_mapping_error,
 };
 
 static void niu_driver_version(void)
@@ -10019,6 +10042,11 @@ static void niu_phys_unmap_single(struct device *dev, u64 dma_address,
 	/* Nothing to do.  */
 }
 
+static int niu_phys_mapping_error(struct device *dev, u64 dma_address)
+{
+	return false;
+}
+
 static const struct niu_ops niu_phys_ops = {
 	.alloc_coherent	= niu_phys_alloc_coherent,
 	.free_coherent	= niu_phys_free_coherent,
@@ -10026,6 +10054,7 @@ static const struct niu_ops niu_phys_ops = {
 	.unmap_page	= niu_phys_unmap_page,
 	.map_single	= niu_phys_map_single,
 	.unmap_single	= niu_phys_unmap_single,
+	.mapping_error	= niu_phys_mapping_error,
 };
 
 static int niu_of_probe(struct platform_device *op)
diff --git a/drivers/net/ethernet/sun/niu.h b/drivers/net/ethernet/sun/niu.h
index 04c215f91fc0..0b169c08b0f2 100644
--- a/drivers/net/ethernet/sun/niu.h
+++ b/drivers/net/ethernet/sun/niu.h
@@ -2879,6 +2879,9 @@ struct tx_ring_info {
 #define NEXT_TX(tp, index) \
 	(((index) + 1) < (tp)->pending ? ((index) + 1) : 0)
 
+#define PREVIOUS_TX(tp, index) \
+	(((index) - 1) >= 0 ? ((index) - 1) : (((tp)->pending) - 1))
+
 static inline u32 niu_tx_avail(struct tx_ring_info *tp)
 {
 	return (tp->pending -
@@ -3140,6 +3143,7 @@ struct niu_ops {
 			  enum dma_data_direction direction);
 	void (*unmap_single)(struct device *dev, u64 dma_address,
 			     size_t size, enum dma_data_direction direction);
+	int (*mapping_error)(struct device *dev, u64 dma_address);
 };
 
 struct niu_link_config {

From f7690d058170dbc1520b0bfbc3d9daf046b59326 Mon Sep 17 00:00:00 2001
From: Simon Trimmer <simont@opensource.cirrus.com>
Date: Wed, 2 Jul 2025 11:22:35 +0000
Subject: [PATCH 1108/1334] ASoC: Intel: sof_sdw: Add quirks for Lenovo P1 and
 P16

These Lenovo Laptops have the DMICs connected to the host instead of the
CS42L43 and so need the SOC_SDW_CODEC_MIC quirk.

Signed-off-by: Simon Trimmer <simont@opensource.cirrus.com>
Link: https://patch.msgid.link/20250702112235.377479-1-simont@opensource.cirrus.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/intel/boards/sof_sdw.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/sound/soc/intel/boards/sof_sdw.c b/sound/soc/intel/boards/sof_sdw.c
index 81a914bd7ec2..504887505e68 100644
--- a/sound/soc/intel/boards/sof_sdw.c
+++ b/sound/soc/intel/boards/sof_sdw.c
@@ -783,6 +783,9 @@ static const struct dmi_system_id sof_sdw_quirk_table[] = {
 static const struct snd_pci_quirk sof_sdw_ssid_quirk_table[] = {
 	SND_PCI_QUIRK(0x1043, 0x1e13, "ASUS Zenbook S14", SOC_SDW_CODEC_MIC),
 	SND_PCI_QUIRK(0x1043, 0x1f43, "ASUS Zenbook S16", SOC_SDW_CODEC_MIC),
+	SND_PCI_QUIRK(0x17aa, 0x2347, "Lenovo P16", SOC_SDW_CODEC_MIC),
+	SND_PCI_QUIRK(0x17aa, 0x2348, "Lenovo P16", SOC_SDW_CODEC_MIC),
+	SND_PCI_QUIRK(0x17aa, 0x2349, "Lenovo P1", SOC_SDW_CODEC_MIC),
 	{}
 };
 

From 1e7ab6f67824343ee3e96f100f0937c393749a8a Mon Sep 17 00:00:00 2001
From: Christian Brauner <brauner@kernel.org>
Date: Wed, 2 Jul 2025 11:23:55 +0200
Subject: [PATCH 1109/1334] anon_inode: rework assertions

Making anonymous inodes regular files comes with a lot of risk and
regression potential as evidenced by a recent hickup in io_uring. We're
better of continuing to not have them be regular files. Since we have
S_ANON_INODE we can port all of our assertions easily.

Link: https://lore.kernel.org/20250702-work-fixes-v1-1-ff76ea589e33@kernel.org
Fixes: cfd86ef7e8e7 ("anon_inode: use a proper mode internally")
Acked-by: Jens Axboe <axboe@kernel.dk>
Cc: stable@kernel.org
Reported-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/exec.c  | 9 +++++++--
 fs/libfs.c | 8 +++-----
 fs/namei.c | 2 +-
 3 files changed, 11 insertions(+), 8 deletions(-)

diff --git a/fs/exec.c b/fs/exec.c
index 1f5fdd2e096e..ba400aafd640 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -114,6 +114,9 @@ static inline void put_binfmt(struct linux_binfmt * fmt)
 
 bool path_noexec(const struct path *path)
 {
+	/* If it's an anonymous inode make sure that we catch any shenanigans. */
+	VFS_WARN_ON_ONCE(IS_ANON_FILE(d_inode(path->dentry)) &&
+			 !(path->mnt->mnt_sb->s_iflags & SB_I_NOEXEC));
 	return (path->mnt->mnt_flags & MNT_NOEXEC) ||
 	       (path->mnt->mnt_sb->s_iflags & SB_I_NOEXEC);
 }
@@ -781,13 +784,15 @@ static struct file *do_open_execat(int fd, struct filename *name, int flags)
 	if (IS_ERR(file))
 		return file;
 
+	if (path_noexec(&file->f_path))
+		return ERR_PTR(-EACCES);
+
 	/*
 	 * In the past the regular type check was here. It moved to may_open() in
 	 * 633fb6ac3980 ("exec: move S_ISREG() check earlier"). Since then it is
 	 * an invariant that all non-regular files error out before we get here.
 	 */
-	if (WARN_ON_ONCE(!S_ISREG(file_inode(file)->i_mode)) ||
-	    path_noexec(&file->f_path))
+	if (WARN_ON_ONCE(!S_ISREG(file_inode(file)->i_mode)))
 		return ERR_PTR(-EACCES);
 
 	err = exe_file_deny_write_access(file);
diff --git a/fs/libfs.c b/fs/libfs.c
index 9ea0ecc325a8..6f487fc6be34 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -1649,12 +1649,10 @@ struct inode *alloc_anon_inode(struct super_block *s)
 	 */
 	inode->i_state = I_DIRTY;
 	/*
-	 * Historically anonymous inodes didn't have a type at all and
-	 * userspace has come to rely on this. Internally they're just
-	 * regular files but S_IFREG is masked off when reporting
-	 * information to userspace.
+	 * Historically anonymous inodes don't have a type at all and
+	 * userspace has come to rely on this.
 	 */
-	inode->i_mode = S_IFREG | S_IRUSR | S_IWUSR;
+	inode->i_mode = S_IRUSR | S_IWUSR;
 	inode->i_uid = current_fsuid();
 	inode->i_gid = current_fsgid();
 	inode->i_flags |= S_PRIVATE | S_ANON_INODE;
diff --git a/fs/namei.c b/fs/namei.c
index 4bb889fc980b..ceb0d47aa6b1 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -3471,7 +3471,7 @@ static int may_open(struct mnt_idmap *idmap, const struct path *path,
 			return -EACCES;
 		break;
 	default:
-		VFS_BUG_ON_INODE(1, inode);
+		VFS_BUG_ON_INODE(!IS_ANON_FILE(inode), inode);
 	}
 
 	error = inode_permission(idmap, inode, MAY_OPEN | acc_mode);

From db98ee56851061082fecd7e6b4b6a93600562ec2 Mon Sep 17 00:00:00 2001
From: Peter Ujfalusi <peter.ujfalusi@linux.intel.com>
Date: Tue, 1 Jul 2025 16:34:11 +0300
Subject: [PATCH 1110/1334] ALSA: hda/realtek: Add quirk for ASUS ExpertBook
 B9403CVAR

ASUS ExpertBook B9403CVAR needs the ALC294_FIXUP_ASUS_HPE for the
headphones to work.

Closes: https://github.com/thesofproject/linux/issues/5472
Signed-off-by: Peter Ujfalusi <peter.ujfalusi@linux.intel.com>
Tested-by: Anton Khirnov <anton@khirnov.net>
Link: https://patch.msgid.link/20250701133411.25275-1-peter.ujfalusi@linux.intel.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/patch_realtek.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index a33e8a6541d4..c7720a2f47c3 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -11041,6 +11041,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1043, 0x1e63, "ASUS H7606W", ALC285_FIXUP_ASUS_GU605_SPI_SPEAKER2_TO_DAC1),
 	SND_PCI_QUIRK(0x1043, 0x1e83, "ASUS GA605W", ALC285_FIXUP_ASUS_GU605_SPI_SPEAKER2_TO_DAC1),
 	SND_PCI_QUIRK(0x1043, 0x1e8e, "ASUS Zephyrus G15", ALC289_FIXUP_ASUS_GA401),
+	SND_PCI_QUIRK(0x1043, 0x1e93, "ASUS ExpertBook B9403CVAR", ALC294_FIXUP_ASUS_HPE),
 	SND_PCI_QUIRK(0x1043, 0x1eb3, "ASUS Ally RCLA72", ALC287_FIXUP_TAS2781_I2C),
 	SND_PCI_QUIRK(0x1043, 0x1ed3, "ASUS HN7306W", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x1043, 0x1ee2, "ASUS UM6702RA/RC", ALC287_FIXUP_CS35L41_I2C_2),

From 5f05fc6e2218db7ecc52c60eb34b707fe69262c2 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Wed, 2 Jul 2025 08:15:31 +0200
Subject: [PATCH 1111/1334] dt-bindings: i2c: realtek,rtl9301: Fix missing
 'reg' constraint

Lists should have fixed amount if items, so add missing constraint to
the 'reg' property (only one address space entry).

Fixes: c5eda0333076 ("dt-bindings: i2c: Add Realtek RTL I2C Controller")
Cc: <stable@vger.kernel.org> # v6.13+
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: Andi Shyti <andi.shyti@kernel.org>
Link: https://lore.kernel.org/r/20250702061530.6940-2-krzysztof.kozlowski@linaro.org
---
 Documentation/devicetree/bindings/i2c/realtek,rtl9301-i2c.yaml | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/i2c/realtek,rtl9301-i2c.yaml b/Documentation/devicetree/bindings/i2c/realtek,rtl9301-i2c.yaml
index eddfd329c67b..69ac5db8b914 100644
--- a/Documentation/devicetree/bindings/i2c/realtek,rtl9301-i2c.yaml
+++ b/Documentation/devicetree/bindings/i2c/realtek,rtl9301-i2c.yaml
@@ -26,7 +26,8 @@ properties:
       - const: realtek,rtl9301-i2c
 
   reg:
-    description: Register offset and size this I2C controller.
+    items:
+      - description: Register offset and size this I2C controller.
 
   "#address-cells":
     const: 1

From 3e7e5adcd2a86783c441edf6f518fc903e3c4e7c Mon Sep 17 00:00:00 2001
From: Sumanth Gavini <sumanth.gavini@yahoo.com>
Date: Fri, 23 May 2025 15:02:37 -0700
Subject: [PATCH 1112/1334] PM: sleep: docs: Replace "diasble" with "disable"

Fix misspelling reported by codespell.

Signed-off-by: Sumanth Gavini <sumanth.gavini@yahoo.com>
Link: https://patch.msgid.link/20250523220238.455718-1-sumanth.gavini@yahoo.com
[ rjw: Subject rewrite ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 Documentation/ABI/testing/sysfs-devices-power | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/ABI/testing/sysfs-devices-power b/Documentation/ABI/testing/sysfs-devices-power
index 54195530e97a..d3da88b26a53 100644
--- a/Documentation/ABI/testing/sysfs-devices-power
+++ b/Documentation/ABI/testing/sysfs-devices-power
@@ -56,7 +56,7 @@ Date:		January 2009
 Contact:	Rafael J. Wysocki <rjw@rjwysocki.net>
 Description:
 		The /sys/devices/.../async attribute allows the user space to
-		enable or diasble the device's suspend and resume callbacks to
+		enable or disable the device's suspend and resume callbacks to
 		be executed asynchronously (ie. in separate threads, in parallel
 		with the main suspend/resume thread) during system-wide power
 		transitions (eg. suspend to RAM, hibernation).

From 103406b38c600fec1fe375a77b27d87e314aea09 Mon Sep 17 00:00:00 2001
From: Lion Ackermann <nnamrec@gmail.com>
Date: Mon, 30 Jun 2025 15:27:30 +0200
Subject: [PATCH 1113/1334] net/sched: Always pass notifications when child
 class becomes empty

Certain classful qdiscs may invoke their classes' dequeue handler on an
enqueue operation. This may unexpectedly empty the child qdisc and thus
make an in-flight class passive via qlen_notify(). Most qdiscs do not
expect such behaviour at this point in time and may re-activate the
class eventually anyways which will lead to a use-after-free.

The referenced fix commit attempted to fix this behavior for the HFSC
case by moving the backlog accounting around, though this turned out to
be incomplete since the parent's parent may run into the issue too.
The following reproducer demonstrates this use-after-free:

    tc qdisc add dev lo root handle 1: drr
    tc filter add dev lo parent 1: basic classid 1:1
    tc class add dev lo parent 1: classid 1:1 drr
    tc qdisc add dev lo parent 1:1 handle 2: hfsc def 1
    tc class add dev lo parent 2: classid 2:1 hfsc rt m1 8 d 1 m2 0
    tc qdisc add dev lo parent 2:1 handle 3: netem
    tc qdisc add dev lo parent 3:1 handle 4: blackhole

    echo 1 | socat -u STDIN UDP4-DATAGRAM:127.0.0.1:8888
    tc class delete dev lo classid 1:1
    echo 1 | socat -u STDIN UDP4-DATAGRAM:127.0.0.1:8888

Since backlog accounting issues leading to a use-after-frees on stale
class pointers is a recurring pattern at this point, this patch takes
a different approach. Instead of trying to fix the accounting, the patch
ensures that qdisc_tree_reduce_backlog always calls qlen_notify when
the child qdisc is empty. This solves the problem because deletion of
qdiscs always involves a call to qdisc_reset() and / or
qdisc_purge_queue() which ultimately resets its qlen to 0 thus causing
the following qdisc_tree_reduce_backlog() to report to the parent. Note
that this may call qlen_notify on passive classes multiple times. This
is not a problem after the recent patch series that made all the
classful qdiscs qlen_notify() handlers idempotent.

Fixes: 3f981138109f ("sch_hfsc: Fix qlen accounting bug when using peek in hfsc_enqueue()")
Signed-off-by: Lion Ackermann <nnamrec@gmail.com>
Reviewed-by: Jamal Hadi Salim <jhs@mojatatu.com>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Link: https://patch.msgid.link/d912cbd7-193b-4269-9857-525bee8bbb6a@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/sched/sch_api.c | 19 +++++--------------
 1 file changed, 5 insertions(+), 14 deletions(-)

diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index c5e3673aadbe..d8a33486c511 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -780,15 +780,12 @@ static u32 qdisc_alloc_handle(struct net_device *dev)
 
 void qdisc_tree_reduce_backlog(struct Qdisc *sch, int n, int len)
 {
-	bool qdisc_is_offloaded = sch->flags & TCQ_F_OFFLOADED;
 	const struct Qdisc_class_ops *cops;
 	unsigned long cl;
 	u32 parentid;
 	bool notify;
 	int drops;
 
-	if (n == 0 && len == 0)
-		return;
 	drops = max_t(int, n, 0);
 	rcu_read_lock();
 	while ((parentid = sch->parent)) {
@@ -797,17 +794,8 @@ void qdisc_tree_reduce_backlog(struct Qdisc *sch, int n, int len)
 
 		if (sch->flags & TCQ_F_NOPARENT)
 			break;
-		/* Notify parent qdisc only if child qdisc becomes empty.
-		 *
-		 * If child was empty even before update then backlog
-		 * counter is screwed and we skip notification because
-		 * parent class is already passive.
-		 *
-		 * If the original child was offloaded then it is allowed
-		 * to be seem as empty, so the parent is notified anyway.
-		 */
-		notify = !sch->q.qlen && !WARN_ON_ONCE(!n &&
-						       !qdisc_is_offloaded);
+		/* Notify parent qdisc only if child qdisc becomes empty. */
+		notify = !sch->q.qlen;
 		/* TODO: perform the search on a per txq basis */
 		sch = qdisc_lookup_rcu(qdisc_dev(sch), TC_H_MAJ(parentid));
 		if (sch == NULL) {
@@ -816,6 +804,9 @@ void qdisc_tree_reduce_backlog(struct Qdisc *sch, int n, int len)
 		}
 		cops = sch->ops->cl_ops;
 		if (notify && cops->qlen_notify) {
+			/* Note that qlen_notify must be idempotent as it may get called
+			 * multiple times.
+			 */
 			cl = cops->find(sch, parentid);
 			cops->qlen_notify(sch, cl);
 		}

From 16ceda2ef683a50cd0783006c0504e1931cd8879 Mon Sep 17 00:00:00 2001
From: Raju Rangoju <Raju.Rangoju@amd.com>
Date: Tue, 1 Jul 2025 12:20:16 +0530
Subject: [PATCH 1114/1334] amd-xgbe: do not double read link status

The link status is latched low so that momentary link drops
can be detected. Always double-reading the status defeats this
design feature. Only double read if link was already down

This prevents unnecessary duplicate readings of the link status.

Fixes: 4f3b20bfbb75 ("amd-xgbe: add support for rx-adaptation")
Signed-off-by: Raju Rangoju <Raju.Rangoju@amd.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250701065016.4140707-1-Raju.Rangoju@amd.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/amd/xgbe/xgbe-mdio.c   |  4 ++++
 drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c | 24 +++++++++++++--------
 2 files changed, 19 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c
index fb5b7eceb73f..1a37ec45e650 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c
@@ -1304,6 +1304,10 @@ static void xgbe_phy_status(struct xgbe_prv_data *pdata)
 
 	pdata->phy.link = pdata->phy_if.phy_impl.link_status(pdata,
 							     &an_restart);
+	/* bail out if the link status register read fails */
+	if (pdata->phy.link < 0)
+		return;
+
 	if (an_restart) {
 		xgbe_phy_config_aneg(pdata);
 		goto adjust_link;
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c
index 7a4dfa4e19c7..23c39e92e783 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c
@@ -2746,8 +2746,7 @@ static bool xgbe_phy_valid_speed(struct xgbe_prv_data *pdata, int speed)
 static int xgbe_phy_link_status(struct xgbe_prv_data *pdata, int *an_restart)
 {
 	struct xgbe_phy_data *phy_data = pdata->phy_data;
-	unsigned int reg;
-	int ret;
+	int reg, ret;
 
 	*an_restart = 0;
 
@@ -2781,11 +2780,20 @@ static int xgbe_phy_link_status(struct xgbe_prv_data *pdata, int *an_restart)
 			return 0;
 	}
 
-	/* Link status is latched low, so read once to clear
-	 * and then read again to get current state
+	reg = XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_STAT1);
+	if (reg < 0)
+		return reg;
+
+	/* Link status is latched low so that momentary link drops
+	 * can be detected. If link was already down read again
+	 * to get the latest state.
 	 */
-	reg = XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_STAT1);
-	reg = XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_STAT1);
+
+	if (!pdata->phy.link && !(reg & MDIO_STAT1_LSTATUS)) {
+		reg = XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_STAT1);
+		if (reg < 0)
+			return reg;
+	}
 
 	if (pdata->en_rx_adap) {
 		/* if the link is available and adaptation is done,
@@ -2804,9 +2812,7 @@ static int xgbe_phy_link_status(struct xgbe_prv_data *pdata, int *an_restart)
 			xgbe_phy_set_mode(pdata, phy_data->cur_mode);
 		}
 
-		/* check again for the link and adaptation status */
-		reg = XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_STAT1);
-		if ((reg & MDIO_STAT1_LSTATUS) && pdata->rx_adapt_done)
+		if (pdata->rx_adapt_done)
 			return 1;
 	} else if (reg & MDIO_STAT1_LSTATUS)
 		return 1;

From 5186ff7e1d0e26aaef998ba18b31c79c28d1441f Mon Sep 17 00:00:00 2001
From: Jiawen Wu <jiawenwu@trustnetic.com>
Date: Tue, 1 Jul 2025 15:06:25 +0800
Subject: [PATCH 1115/1334] net: libwx: fix the incorrect display of the queue
 number

When setting "ethtool -L eth0 combined 1", the number of RX/TX queue is
changed to be 1. RSS is disabled at this moment, and the indices of FDIR
have not be changed in wx_set_rss_queues(). So the combined count still
shows the previous value. This issue was introduced when supporting
FDIR. Fix it for those devices that support FDIR.

Fixes: 34744a7749b3 ("net: txgbe: add FDIR info to ethtool ops")
Cc: stable@vger.kernel.org
Signed-off-by: Jiawen Wu <jiawenwu@trustnetic.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/A5C8FE56D6C04608+20250701070625.73680-1-jiawenwu@trustnetic.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/wangxun/libwx/wx_lib.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/wangxun/libwx/wx_lib.c b/drivers/net/ethernet/wangxun/libwx/wx_lib.c
index c57cc4f27249..59840ba9c1fe 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_lib.c
+++ b/drivers/net/ethernet/wangxun/libwx/wx_lib.c
@@ -1705,6 +1705,7 @@ static void wx_set_rss_queues(struct wx *wx)
 
 	clear_bit(WX_FLAG_FDIR_HASH, wx->flags);
 
+	wx->ring_feature[RING_F_FDIR].indices = 1;
 	/* Use Flow Director in addition to RSS to ensure the best
 	 * distribution of flows across cores, even when an FDIR flow
 	 * isn't matched.

From c2a2ff6b4db55647575260bf2227b0e09d46addb Mon Sep 17 00:00:00 2001
From: Antoine Tenart <atenart@kernel.org>
Date: Tue, 1 Jul 2025 09:49:34 +0200
Subject: [PATCH 1116/1334] net: ipv4: fix stat increase when udp early demux
 drops the packet

udp_v4_early_demux now returns drop reasons as it either returns 0 or
ip_mc_validate_source, which returns itself a drop reason. However its
use was not converted in ip_rcv_finish_core and the drop reason is
ignored, leading to potentially skipping increasing LINUX_MIB_IPRPFILTER
if the drop reason is SKB_DROP_REASON_IP_RPFILTER.

This is a fix and we're not converting udp_v4_early_demux to explicitly
return a drop reason to ease backports; this can be done as a follow-up.

Fixes: d46f827016d8 ("net: ip: make ip_mc_validate_source() return drop reason")
Cc: Menglong Dong <menglong8.dong@gmail.com>
Reported-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: Antoine Tenart <atenart@kernel.org>
Reviewed-by: Sabrina Dubroca <sd@queasysnail.net>
Link: https://patch.msgid.link/20250701074935.144134-1-atenart@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/ip_input.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
index 30a5e9460d00..5a49eb99e5c4 100644
--- a/net/ipv4/ip_input.c
+++ b/net/ipv4/ip_input.c
@@ -319,8 +319,8 @@ static int ip_rcv_finish_core(struct net *net,
 			      const struct sk_buff *hint)
 {
 	const struct iphdr *iph = ip_hdr(skb);
-	int err, drop_reason;
 	struct rtable *rt;
+	int drop_reason;
 
 	if (ip_can_use_hint(skb, iph, hint)) {
 		drop_reason = ip_route_use_hint(skb, iph->daddr, iph->saddr,
@@ -345,9 +345,10 @@ static int ip_rcv_finish_core(struct net *net,
 			break;
 		case IPPROTO_UDP:
 			if (READ_ONCE(net->ipv4.sysctl_udp_early_demux)) {
-				err = udp_v4_early_demux(skb);
-				if (unlikely(err))
+				drop_reason = udp_v4_early_demux(skb);
+				if (unlikely(drop_reason))
 					goto drop_error;
+				drop_reason = SKB_DROP_REASON_NOT_SPECIFIED;
 
 				/* must reload iph, skb->head might have changed */
 				iph = ip_hdr(skb);

From 226862f50a7a88e4e4de9abbf36c64d19acd6fd0 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ma=C3=ADra=20Canal?= <mcanal@igalia.com>
Date: Sat, 28 Jun 2025 19:42:42 -0300
Subject: [PATCH 1117/1334] drm/v3d: Disable interrupts before resetting the
 GPU
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Currently, an interrupt can be triggered during a GPU reset, which can
lead to GPU hangs and NULL pointer dereference in an interrupt context
as shown in the following trace:

 [  314.035040] Unable to handle kernel NULL pointer dereference at virtual address 00000000000000c0
 [  314.043822] Mem abort info:
 [  314.046606]   ESR = 0x0000000096000005
 [  314.050347]   EC = 0x25: DABT (current EL), IL = 32 bits
 [  314.055651]   SET = 0, FnV = 0
 [  314.058695]   EA = 0, S1PTW = 0
 [  314.061826]   FSC = 0x05: level 1 translation fault
 [  314.066694] Data abort info:
 [  314.069564]   ISV = 0, ISS = 0x00000005, ISS2 = 0x00000000
 [  314.075039]   CM = 0, WnR = 0, TnD = 0, TagAccess = 0
 [  314.080080]   GCS = 0, Overlay = 0, DirtyBit = 0, Xs = 0
 [  314.085382] user pgtable: 4k pages, 39-bit VAs, pgdp=0000000102728000
 [  314.091814] [00000000000000c0] pgd=0000000000000000, p4d=0000000000000000, pud=0000000000000000
 [  314.100511] Internal error: Oops: 0000000096000005 [#1] PREEMPT SMP
 [  314.106770] Modules linked in: v3d i2c_brcmstb vc4 snd_soc_hdmi_codec gpu_sched drm_shmem_helper drm_display_helper cec drm_dma_helper drm_kms_helper drm drm_panel_orientation_quirks snd_soc_core snd_compress snd_pcm_dmaengine snd_pcm snd_timer snd backlight
 [  314.129654] CPU: 0 UID: 0 PID: 0 Comm: swapper/0 Not tainted 6.12.25+rpt-rpi-v8 #1  Debian 1:6.12.25-1+rpt1
 [  314.139388] Hardware name: Raspberry Pi 4 Model B Rev 1.4 (DT)
 [  314.145211] pstate: 600000c5 (nZCv daIF -PAN -UAO -TCO -DIT -SSBS BTYPE=--)
 [  314.152165] pc : v3d_irq+0xec/0x2e0 [v3d]
 [  314.156187] lr : v3d_irq+0xe0/0x2e0 [v3d]
 [  314.160198] sp : ffffffc080003ea0
 [  314.163502] x29: ffffffc080003ea0 x28: ffffffec1f184980 x27: 021202b000000000
 [  314.170633] x26: ffffffec1f17f630 x25: ffffff8101372000 x24: ffffffec1f17d9f0
 [  314.177764] x23: 000000000000002a x22: 000000000000002a x21: ffffff8103252000
 [  314.184895] x20: 0000000000000001 x19: 00000000deadbeef x18: 0000000000000000
 [  314.192026] x17: ffffff94e51d2000 x16: ffffffec1dac3cb0 x15: c306000000000000
 [  314.199156] x14: 0000000000000000 x13: b2fc982e03cc5168 x12: 0000000000000001
 [  314.206286] x11: ffffff8103f8bcc0 x10: ffffffec1f196868 x9 : ffffffec1dac3874
 [  314.213416] x8 : 0000000000000000 x7 : 0000000000042a3a x6 : ffffff810017a180
 [  314.220547] x5 : ffffffec1ebad400 x4 : ffffffec1ebad320 x3 : 00000000000bebeb
 [  314.227677] x2 : 0000000000000000 x1 : 0000000000000000 x0 : 0000000000000000
 [  314.234807] Call trace:
 [  314.237243]  v3d_irq+0xec/0x2e0 [v3d]
 [  314.240906]  __handle_irq_event_percpu+0x58/0x218
 [  314.245609]  handle_irq_event+0x54/0xb8
 [  314.249439]  handle_fasteoi_irq+0xac/0x240
 [  314.253527]  handle_irq_desc+0x48/0x68
 [  314.257269]  generic_handle_domain_irq+0x24/0x38
 [  314.261879]  gic_handle_irq+0x48/0xd8
 [  314.265533]  call_on_irq_stack+0x24/0x58
 [  314.269448]  do_interrupt_handler+0x88/0x98
 [  314.273624]  el1_interrupt+0x34/0x68
 [  314.277193]  el1h_64_irq_handler+0x18/0x28
 [  314.281281]  el1h_64_irq+0x64/0x68
 [  314.284673]  default_idle_call+0x3c/0x168
 [  314.288675]  do_idle+0x1fc/0x230
 [  314.291895]  cpu_startup_entry+0x3c/0x50
 [  314.295810]  rest_init+0xe4/0xf0
 [  314.299030]  start_kernel+0x5e8/0x790
 [  314.302684]  __primary_switched+0x80/0x90
 [  314.306691] Code: 940029eb 360ffc13 f9442ea0 52800001 (f9406017)
 [  314.312775] ---[ end trace 0000000000000000 ]---
 [  314.317384] Kernel panic - not syncing: Oops: Fatal exception in interrupt
 [  314.324249] SMP: stopping secondary CPUs
 [  314.328167] Kernel Offset: 0x2b9da00000 from 0xffffffc080000000
 [  314.334076] PHYS_OFFSET: 0x0
 [  314.336946] CPU features: 0x08,00002013,c0200000,0200421b
 [  314.342337] Memory Limit: none
 [  314.345382] ---[ end Kernel panic - not syncing: Oops: Fatal exception in interrupt ]---

Before resetting the GPU, it's necessary to disable all interrupts and
deal with any interrupt handler still in-flight. Otherwise, the GPU might
reset with jobs still running, or yet, an interrupt could be handled
during the reset.

Cc: stable@vger.kernel.org
Fixes: 57692c94dcbe ("drm/v3d: Introduce a new DRM driver for Broadcom V3D V3.x+")
Reviewed-by: Juan A. Suarez <jasuarez@igalia.com>
Reviewed-by: Iago Toral Quiroga <itoral@igalia.com>
Link: https://lore.kernel.org/r/20250628224243.47599-1-mcanal@igalia.com
Signed-off-by: Maíra Canal <mcanal@igalia.com>
---
 drivers/gpu/drm/v3d/v3d_drv.h |  8 ++++++++
 drivers/gpu/drm/v3d/v3d_gem.c |  2 ++
 drivers/gpu/drm/v3d/v3d_irq.c | 37 +++++++++++++++++++++++++----------
 3 files changed, 37 insertions(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/v3d/v3d_drv.h b/drivers/gpu/drm/v3d/v3d_drv.h
index b51f0b648a08..411e47702f8a 100644
--- a/drivers/gpu/drm/v3d/v3d_drv.h
+++ b/drivers/gpu/drm/v3d/v3d_drv.h
@@ -101,6 +101,12 @@ enum v3d_gen {
 	V3D_GEN_71 = 71,
 };
 
+enum v3d_irq {
+	V3D_CORE_IRQ,
+	V3D_HUB_IRQ,
+	V3D_MAX_IRQS,
+};
+
 struct v3d_dev {
 	struct drm_device drm;
 
@@ -112,6 +118,8 @@ struct v3d_dev {
 
 	bool single_irq_line;
 
+	int irq[V3D_MAX_IRQS];
+
 	struct v3d_perfmon_info perfmon_info;
 
 	void __iomem *hub_regs;
diff --git a/drivers/gpu/drm/v3d/v3d_gem.c b/drivers/gpu/drm/v3d/v3d_gem.c
index d7d16da78db3..37bf5eecdd2c 100644
--- a/drivers/gpu/drm/v3d/v3d_gem.c
+++ b/drivers/gpu/drm/v3d/v3d_gem.c
@@ -134,6 +134,8 @@ v3d_reset(struct v3d_dev *v3d)
 	if (false)
 		v3d_idle_axi(v3d, 0);
 
+	v3d_irq_disable(v3d);
+
 	v3d_idle_gca(v3d);
 	v3d_reset_sms(v3d);
 	v3d_reset_v3d(v3d);
diff --git a/drivers/gpu/drm/v3d/v3d_irq.c b/drivers/gpu/drm/v3d/v3d_irq.c
index 2cca5d3a26a2..a515a301e480 100644
--- a/drivers/gpu/drm/v3d/v3d_irq.c
+++ b/drivers/gpu/drm/v3d/v3d_irq.c
@@ -260,7 +260,7 @@ v3d_hub_irq(int irq, void *arg)
 int
 v3d_irq_init(struct v3d_dev *v3d)
 {
-	int irq1, ret, core;
+	int irq, ret, core;
 
 	INIT_WORK(&v3d->overflow_mem_work, v3d_overflow_mem_work);
 
@@ -271,17 +271,24 @@ v3d_irq_init(struct v3d_dev *v3d)
 		V3D_CORE_WRITE(core, V3D_CTL_INT_CLR, V3D_CORE_IRQS(v3d->ver));
 	V3D_WRITE(V3D_HUB_INT_CLR, V3D_HUB_IRQS(v3d->ver));
 
-	irq1 = platform_get_irq_optional(v3d_to_pdev(v3d), 1);
-	if (irq1 == -EPROBE_DEFER)
-		return irq1;
-	if (irq1 > 0) {
-		ret = devm_request_irq(v3d->drm.dev, irq1,
+	irq = platform_get_irq_optional(v3d_to_pdev(v3d), 1);
+	if (irq == -EPROBE_DEFER)
+		return irq;
+	if (irq > 0) {
+		v3d->irq[V3D_CORE_IRQ] = irq;
+
+		ret = devm_request_irq(v3d->drm.dev, v3d->irq[V3D_CORE_IRQ],
 				       v3d_irq, IRQF_SHARED,
 				       "v3d_core0", v3d);
 		if (ret)
 			goto fail;
-		ret = devm_request_irq(v3d->drm.dev,
-				       platform_get_irq(v3d_to_pdev(v3d), 0),
+
+		irq = platform_get_irq(v3d_to_pdev(v3d), 0);
+		if (irq < 0)
+			return irq;
+		v3d->irq[V3D_HUB_IRQ] = irq;
+
+		ret = devm_request_irq(v3d->drm.dev, v3d->irq[V3D_HUB_IRQ],
 				       v3d_hub_irq, IRQF_SHARED,
 				       "v3d_hub", v3d);
 		if (ret)
@@ -289,8 +296,12 @@ v3d_irq_init(struct v3d_dev *v3d)
 	} else {
 		v3d->single_irq_line = true;
 
-		ret = devm_request_irq(v3d->drm.dev,
-				       platform_get_irq(v3d_to_pdev(v3d), 0),
+		irq = platform_get_irq(v3d_to_pdev(v3d), 0);
+		if (irq < 0)
+			return irq;
+		v3d->irq[V3D_CORE_IRQ] = irq;
+
+		ret = devm_request_irq(v3d->drm.dev, v3d->irq[V3D_CORE_IRQ],
 				       v3d_irq, IRQF_SHARED,
 				       "v3d", v3d);
 		if (ret)
@@ -331,6 +342,12 @@ v3d_irq_disable(struct v3d_dev *v3d)
 		V3D_CORE_WRITE(core, V3D_CTL_INT_MSK_SET, ~0);
 	V3D_WRITE(V3D_HUB_INT_MSK_SET, ~0);
 
+	/* Finish any interrupt handler still in flight. */
+	for (int i = 0; i < V3D_MAX_IRQS; i++) {
+		if (v3d->irq[i])
+			synchronize_irq(v3d->irq[i]);
+	}
+
 	/* Clear any pending interrupts we might have left. */
 	for (core = 0; core < v3d->cores; core++)
 		V3D_CORE_WRITE(core, V3D_CTL_INT_CLR, V3D_CORE_IRQS(v3d->ver));

From c80f2b047d5cc42fbd2dff9d1942d4ba7545100f Mon Sep 17 00:00:00 2001
From: Qasim Ijaz <qasdev00@gmail.com>
Date: Fri, 27 Jun 2025 12:01:21 +0100
Subject: [PATCH 1118/1334] HID: appletb-kbd: fix memory corruption of
 input_handler_list

In appletb_kbd_probe an input handler is initialised and then registered
with input core through input_register_handler(). When this happens input
core will add the input handler (specifically its node) to the global
input_handler_list. The input_handler_list is central to the functionality
of input core and is traversed in various places in input core. An example
of this is when a new input device is plugged in and gets registered with
input core.

The input_handler in probe is allocated as device managed memory. If a
probe failure occurs after input_register_handler() the input_handler
memory is freed, yet it will remain in the input_handler_list. This
effectively means the input_handler_list contains a dangling pointer
to data belonging to a freed input handler.

This causes an issue when any other input device is plugged in - in my
case I had an old PixArt HP USB optical mouse and I decided to
plug it in after a failure occurred after input_register_handler().
This lead to the registration of this input device via
input_register_device which involves traversing over every handler
in the corrupted input_handler_list and calling input_attach_handler(),
giving each handler a chance to bind to newly registered device.

The core of this bug is a UAF which causes memory corruption of
input_handler_list and to fix it we must ensure the input handler is
unregistered from input core, this is done through
input_unregister_handler().

[   63.191597] ==================================================================
[   63.192094] BUG: KASAN: slab-use-after-free in input_attach_handler.isra.0+0x1a9/0x1e0
[   63.192094] Read of size 8 at addr ffff888105ea7c80 by task kworker/0:2/54
[   63.192094]
[   63.192094] CPU: 0 UID: 0 PID: 54 Comm: kworker/0:2 Not tainted 6.16.0-rc2-00321-g2aa6621d
[   63.192094] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.16.2-debian-1.164
[   63.192094] Workqueue: usb_hub_wq hub_event
[   63.192094] Call Trace:
[   63.192094]  <TASK>
[   63.192094]  dump_stack_lvl+0x53/0x70
[   63.192094]  print_report+0xce/0x670
[   63.192094]  kasan_report+0xce/0x100
[   63.192094]  input_attach_handler.isra.0+0x1a9/0x1e0
[   63.192094]  input_register_device+0x76c/0xd00
[   63.192094]  hidinput_connect+0x686d/0xad60
[   63.192094]  hid_connect+0xf20/0x1b10
[   63.192094]  hid_hw_start+0x83/0x100
[   63.192094]  hid_device_probe+0x2d1/0x680
[   63.192094]  really_probe+0x1c3/0x690
[   63.192094]  __driver_probe_device+0x247/0x300
[   63.192094]  driver_probe_device+0x49/0x210
[   63.192094]  __device_attach_driver+0x160/0x320
[   63.192094]  bus_for_each_drv+0x10f/0x190
[   63.192094]  __device_attach+0x18e/0x370
[   63.192094]  bus_probe_device+0x123/0x170
[   63.192094]  device_add+0xd4d/0x1460
[   63.192094]  hid_add_device+0x30b/0x910
[   63.192094]  usbhid_probe+0x920/0xe00
[   63.192094]  usb_probe_interface+0x363/0x9a0
[   63.192094]  really_probe+0x1c3/0x690
[   63.192094]  __driver_probe_device+0x247/0x300
[   63.192094]  driver_probe_device+0x49/0x210
[   63.192094]  __device_attach_driver+0x160/0x320
[   63.192094]  bus_for_each_drv+0x10f/0x190
[   63.192094]  __device_attach+0x18e/0x370
[   63.192094]  bus_probe_device+0x123/0x170
[   63.192094]  device_add+0xd4d/0x1460
[   63.192094]  usb_set_configuration+0xd14/0x1880
[   63.192094]  usb_generic_driver_probe+0x78/0xb0
[   63.192094]  usb_probe_device+0xaa/0x2e0
[   63.192094]  really_probe+0x1c3/0x690
[   63.192094]  __driver_probe_device+0x247/0x300
[   63.192094]  driver_probe_device+0x49/0x210
[   63.192094]  __device_attach_driver+0x160/0x320
[   63.192094]  bus_for_each_drv+0x10f/0x190
[   63.192094]  __device_attach+0x18e/0x370
[   63.192094]  bus_probe_device+0x123/0x170
[   63.192094]  device_add+0xd4d/0x1460
[   63.192094]  usb_new_device+0x7b4/0x1000
[   63.192094]  hub_event+0x234d/0x3fa0
[   63.192094]  process_one_work+0x5bf/0xfe0
[   63.192094]  worker_thread+0x777/0x13a0
[   63.192094]  </TASK>
[   63.192094]
[   63.192094] Allocated by task 54:
[   63.192094]  kasan_save_stack+0x33/0x60
[   63.192094]  kasan_save_track+0x14/0x30
[   63.192094]  __kasan_kmalloc+0x8f/0xa0
[   63.192094]  __kmalloc_node_track_caller_noprof+0x195/0x420
[   63.192094]  devm_kmalloc+0x74/0x1e0
[   63.192094]  appletb_kbd_probe+0x39/0x440
[   63.192094]  hid_device_probe+0x2d1/0x680
[   63.192094]  really_probe+0x1c3/0x690
[   63.192094]  __driver_probe_device+0x247/0x300
[   63.192094]  driver_probe_device+0x49/0x210
[   63.192094]  __device_attach_driver+0x160/0x320
[...]
[   63.192094]
[   63.192094] Freed by task 54:
[   63.192094]  kasan_save_stack+0x33/0x60
[   63.192094]  kasan_save_track+0x14/0x30
[   63.192094]  kasan_save_free_info+0x3b/0x60
[   63.192094]  __kasan_slab_free+0x37/0x50
[   63.192094]  kfree+0xcf/0x360
[   63.192094]  devres_release_group+0x1f8/0x3c0
[   63.192094]  hid_device_probe+0x315/0x680
[   63.192094]  really_probe+0x1c3/0x690
[   63.192094]  __driver_probe_device+0x247/0x300
[   63.192094]  driver_probe_device+0x49/0x210
[   63.192094]  __device_attach_driver+0x160/0x320
[...]

Fixes: 7d62ba8deacf ("HID: hid-appletb-kbd: add support for fn toggle between media and function mode")
Cc: stable@vger.kernel.org
Reviewed-by: Aditya Garg <gargaditya08@live.com>
Signed-off-by: Qasim Ijaz <qasdev00@gmail.com>
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
 drivers/hid/hid-appletb-kbd.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/hid/hid-appletb-kbd.c b/drivers/hid/hid-appletb-kbd.c
index e06567886e50..b5d9e50bc231 100644
--- a/drivers/hid/hid-appletb-kbd.c
+++ b/drivers/hid/hid-appletb-kbd.c
@@ -430,13 +430,15 @@ static int appletb_kbd_probe(struct hid_device *hdev, const struct hid_device_id
 	ret = appletb_kbd_set_mode(kbd, appletb_tb_def_mode);
 	if (ret) {
 		dev_err_probe(dev, ret, "Failed to set touchbar mode\n");
-		goto close_hw;
+		goto unregister_handler;
 	}
 
 	hid_set_drvdata(hdev, kbd);
 
 	return 0;
 
+unregister_handler:
+	input_unregister_handler(&kbd->inp_handler);
 close_hw:
 	if (kbd->backlight_dev)
 		put_device(&kbd->backlight_dev->dev);

From 50f9ff52c078d66053bba791ded6fafc64055524 Mon Sep 17 00:00:00 2001
From: Leonard Dizon <leonard@snekbyte.com>
Date: Mon, 30 Jun 2025 05:48:30 +0800
Subject: [PATCH 1119/1334] HID: elecom: add support for ELECOM HUGE 019B
 variant

The ELECOM M-HT1DRBK trackball has an additional device ID (056E:019B)
not yet recognized by the driver, despite using the same report
descriptor as earlier variants. This patch adds the new ID and applies
the same fixups, enabling all 8 buttons to function properly.

Signed-off-by: Leonard Dizon <leonard@snekbyte.com>
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
 drivers/hid/hid-elecom.c | 6 ++++--
 drivers/hid/hid-ids.h    | 3 ++-
 drivers/hid/hid-quirks.c | 3 ++-
 3 files changed, 8 insertions(+), 4 deletions(-)

diff --git a/drivers/hid/hid-elecom.c b/drivers/hid/hid-elecom.c
index defcf91fdd14..0ad7d25d9864 100644
--- a/drivers/hid/hid-elecom.c
+++ b/drivers/hid/hid-elecom.c
@@ -89,7 +89,8 @@ static const __u8 *elecom_report_fixup(struct hid_device *hdev, __u8 *rdesc,
 		break;
 	case USB_DEVICE_ID_ELECOM_M_DT1URBK:
 	case USB_DEVICE_ID_ELECOM_M_DT1DRBK:
-	case USB_DEVICE_ID_ELECOM_M_HT1URBK:
+	case USB_DEVICE_ID_ELECOM_M_HT1URBK_010C:
+	case USB_DEVICE_ID_ELECOM_M_HT1URBK_019B:
 	case USB_DEVICE_ID_ELECOM_M_HT1DRBK_010D:
 		/*
 		 * Report descriptor format:
@@ -122,7 +123,8 @@ static const struct hid_device_id elecom_devices[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_XT4DRBK) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_DT1URBK) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_DT1DRBK) },
-	{ HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_HT1URBK) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_HT1URBK_010C) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_HT1URBK_019B) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_HT1DRBK_010D) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_HT1DRBK_011C) },
 	{ }
diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h
index c6468568aea1..33cc5820f2be 100644
--- a/drivers/hid/hid-ids.h
+++ b/drivers/hid/hid-ids.h
@@ -448,7 +448,8 @@
 #define USB_DEVICE_ID_ELECOM_M_XT4DRBK	0x00fd
 #define USB_DEVICE_ID_ELECOM_M_DT1URBK	0x00fe
 #define USB_DEVICE_ID_ELECOM_M_DT1DRBK	0x00ff
-#define USB_DEVICE_ID_ELECOM_M_HT1URBK	0x010c
+#define USB_DEVICE_ID_ELECOM_M_HT1URBK_010C	0x010c
+#define USB_DEVICE_ID_ELECOM_M_HT1URBK_019B	0x019b
 #define USB_DEVICE_ID_ELECOM_M_HT1DRBK_010D	0x010d
 #define USB_DEVICE_ID_ELECOM_M_HT1DRBK_011C	0x011c
 
diff --git a/drivers/hid/hid-quirks.c b/drivers/hid/hid-quirks.c
index 31508da93ba2..9bf9ce8dc803 100644
--- a/drivers/hid/hid-quirks.c
+++ b/drivers/hid/hid-quirks.c
@@ -410,7 +410,8 @@ static const struct hid_device_id hid_have_special_driver[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_XT4DRBK) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_DT1URBK) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_DT1DRBK) },
-	{ HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_HT1URBK) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_HT1URBK_010C) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_HT1URBK_019B) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_HT1DRBK_010D) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_HT1DRBK_011C) },
 #endif

From 194808a1ea391e35d364d6c9406e2eccb6174525 Mon Sep 17 00:00:00 2001
From: Vicki Pfau <vi@endrift.com>
Date: Tue, 1 Jul 2025 20:46:42 -0700
Subject: [PATCH 1120/1334] HID: Fix debug name for BTN_GEAR_DOWN, BTN_GEAR_UP,
 BTN_WHEEL

The name of BTN_GEAR_DOWN was WheelBtn and BTN_WHEEL was missing. Further,
BTN_GEAR_UP had a space in its name and no Btn, which is against convention.
This makes the names BtnGearDown, BtnGearUp, and BtnWheel, fixing the errors
and matching convention.

Signed-off-by: Vicki Pfau <vi@endrift.com>
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
 drivers/hid/hid-debug.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/hid/hid-debug.c b/drivers/hid/hid-debug.c
index 8433306148d5..c6b6b1029540 100644
--- a/drivers/hid/hid-debug.c
+++ b/drivers/hid/hid-debug.c
@@ -3298,8 +3298,8 @@ static const char *keys[KEY_MAX + 1] = {
 	[BTN_TOUCH] = "Touch",			[BTN_STYLUS] = "Stylus",
 	[BTN_STYLUS2] = "Stylus2",		[BTN_TOOL_DOUBLETAP] = "ToolDoubleTap",
 	[BTN_TOOL_TRIPLETAP] = "ToolTripleTap",	[BTN_TOOL_QUADTAP] = "ToolQuadrupleTap",
-	[BTN_GEAR_DOWN] = "WheelBtn",
-	[BTN_GEAR_UP] = "Gear up",		[KEY_OK] = "Ok",
+	[BTN_GEAR_DOWN] = "BtnGearDown",	[BTN_GEAR_UP] = "BtnGearUp",
+	[BTN_WHEEL] = "BtnWheel",		[KEY_OK] = "Ok",
 	[KEY_SELECT] = "Select",		[KEY_GOTO] = "Goto",
 	[KEY_CLEAR] = "Clear",			[KEY_POWER2] = "Power2",
 	[KEY_OPTION] = "Option",		[KEY_INFO] = "Info",

From ba677dbe77af5ffe6204e0f3f547f3ba059c6302 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Wed, 2 Jul 2025 18:21:44 +0200
Subject: [PATCH 1121/1334] perf: Revert to requiring CAP_SYS_ADMIN for uprobes

Jann reports that uprobes can be used destructively when used in the
middle of an instruction. The kernel only verifies there is a valid
instruction at the requested offset, but due to variable instruction
length cannot determine if this is an instruction as seen by the
intended execution stream.

Additionally, Mark Rutland notes that on architectures that mix data
in the text segment (like arm64), a similar things can be done if the
data word is 'mistaken' for an instruction.

As such, require CAP_SYS_ADMIN for uprobes.

Fixes: c9e0924e5c2b ("perf/core: open access to probes for CAP_PERFMON privileged process")
Reported-by: Jann Horn <jannh@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/CAG48ez1n4520sq0XrWYDHKiKxE_+WCfAK+qt9qkY4ZiBGmL-5g@mail.gmail.com
---
 kernel/events/core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index bf2118c22126..0db36b2b2448 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -11116,7 +11116,7 @@ static int perf_uprobe_event_init(struct perf_event *event)
 	if (event->attr.type != perf_uprobe.type)
 		return -ENOENT;
 
-	if (!perfmon_capable())
+	if (!capable(CAP_SYS_ADMIN))
 		return -EACCES;
 
 	/*

From 315dbdd7cdf6aa533829774caaf4d25f1fd20e73 Mon Sep 17 00:00:00 2001
From: Bui Quang Minh <minhquangbui99@gmail.com>
Date: Mon, 30 Jun 2025 21:42:10 +0700
Subject: [PATCH 1122/1334] virtio-net: ensure the received length does not
 exceed allocated size

In xdp_linearize_page, when reading the following buffers from the ring,
we forget to check the received length with the true allocate size. This
can lead to an out-of-bound read. This commit adds that missing check.

Cc: <stable@vger.kernel.org>
Fixes: 4941d472bf95 ("virtio-net: do not reset during XDP set")
Signed-off-by: Bui Quang Minh <minhquangbui99@gmail.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Link: https://patch.msgid.link/20250630144212.48471-2-minhquangbui99@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/virtio_net.c | 38 ++++++++++++++++++++++++++++++++++----
 1 file changed, 34 insertions(+), 4 deletions(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index e53ba600605a..31661bcb3932 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -778,6 +778,26 @@ static unsigned int mergeable_ctx_to_truesize(void *mrg_ctx)
 	return (unsigned long)mrg_ctx & ((1 << MRG_CTX_HEADER_SHIFT) - 1);
 }
 
+static int check_mergeable_len(struct net_device *dev, void *mrg_ctx,
+			       unsigned int len)
+{
+	unsigned int headroom, tailroom, room, truesize;
+
+	truesize = mergeable_ctx_to_truesize(mrg_ctx);
+	headroom = mergeable_ctx_to_headroom(mrg_ctx);
+	tailroom = headroom ? sizeof(struct skb_shared_info) : 0;
+	room = SKB_DATA_ALIGN(headroom + tailroom);
+
+	if (len > truesize - room) {
+		pr_debug("%s: rx error: len %u exceeds truesize %lu\n",
+			 dev->name, len, (unsigned long)(truesize - room));
+		DEV_STATS_INC(dev, rx_length_errors);
+		return -1;
+	}
+
+	return 0;
+}
+
 static struct sk_buff *virtnet_build_skb(void *buf, unsigned int buflen,
 					 unsigned int headroom,
 					 unsigned int len)
@@ -1797,7 +1817,8 @@ static unsigned int virtnet_get_headroom(struct virtnet_info *vi)
  * across multiple buffers (num_buf > 1), and we make sure buffers
  * have enough headroom.
  */
-static struct page *xdp_linearize_page(struct receive_queue *rq,
+static struct page *xdp_linearize_page(struct net_device *dev,
+				       struct receive_queue *rq,
 				       int *num_buf,
 				       struct page *p,
 				       int offset,
@@ -1817,18 +1838,27 @@ static struct page *xdp_linearize_page(struct receive_queue *rq,
 	memcpy(page_address(page) + page_off, page_address(p) + offset, *len);
 	page_off += *len;
 
+	/* Only mergeable mode can go inside this while loop. In small mode,
+	 * *num_buf == 1, so it cannot go inside.
+	 */
 	while (--*num_buf) {
 		unsigned int buflen;
 		void *buf;
+		void *ctx;
 		int off;
 
-		buf = virtnet_rq_get_buf(rq, &buflen, NULL);
+		buf = virtnet_rq_get_buf(rq, &buflen, &ctx);
 		if (unlikely(!buf))
 			goto err_buf;
 
 		p = virt_to_head_page(buf);
 		off = buf - page_address(p);
 
+		if (check_mergeable_len(dev, ctx, buflen)) {
+			put_page(p);
+			goto err_buf;
+		}
+
 		/* guard against a misconfigured or uncooperative backend that
 		 * is sending packet larger than the MTU.
 		 */
@@ -1917,7 +1947,7 @@ static struct sk_buff *receive_small_xdp(struct net_device *dev,
 		headroom = vi->hdr_len + header_offset;
 		buflen = SKB_DATA_ALIGN(GOOD_PACKET_LEN + headroom) +
 			SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
-		xdp_page = xdp_linearize_page(rq, &num_buf, page,
+		xdp_page = xdp_linearize_page(dev, rq, &num_buf, page,
 					      offset, header_offset,
 					      &tlen);
 		if (!xdp_page)
@@ -2252,7 +2282,7 @@ static void *mergeable_xdp_get_buf(struct virtnet_info *vi,
 	 */
 	if (!xdp_prog->aux->xdp_has_frags) {
 		/* linearize data for XDP */
-		xdp_page = xdp_linearize_page(rq, num_buf,
+		xdp_page = xdp_linearize_page(vi->dev, rq, num_buf,
 					      *page, offset,
 					      XDP_PACKET_HEADROOM,
 					      len);

From 4be2193b3393dca33504793fe7586fed547abb5d Mon Sep 17 00:00:00 2001
From: Bui Quang Minh <minhquangbui99@gmail.com>
Date: Mon, 30 Jun 2025 21:42:11 +0700
Subject: [PATCH 1123/1334] virtio-net: remove redundant truesize check with
 PAGE_SIZE

The truesize is guaranteed not to exceed PAGE_SIZE in
get_mergeable_buf_len(). It is saved in mergeable context, which is not
changeable by the host side, so the check in receive path is quite
redundant.

Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: Bui Quang Minh <minhquangbui99@gmail.com>
Link: https://patch.msgid.link/20250630144212.48471-3-minhquangbui99@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/virtio_net.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 31661bcb3932..535a4534c27f 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -2157,9 +2157,9 @@ static int virtnet_build_xdp_buff_mrg(struct net_device *dev,
 {
 	struct virtio_net_hdr_mrg_rxbuf *hdr = buf;
 	unsigned int headroom, tailroom, room;
-	unsigned int truesize, cur_frag_size;
 	struct skb_shared_info *shinfo;
 	unsigned int xdp_frags_truesz = 0;
+	unsigned int truesize;
 	struct page *page;
 	skb_frag_t *frag;
 	int offset;
@@ -2207,9 +2207,8 @@ static int virtnet_build_xdp_buff_mrg(struct net_device *dev,
 		tailroom = headroom ? sizeof(struct skb_shared_info) : 0;
 		room = SKB_DATA_ALIGN(headroom + tailroom);
 
-		cur_frag_size = truesize;
-		xdp_frags_truesz += cur_frag_size;
-		if (unlikely(len > truesize - room || cur_frag_size > PAGE_SIZE)) {
+		xdp_frags_truesz += truesize;
+		if (unlikely(len > truesize - room)) {
 			put_page(page);
 			pr_debug("%s: rx error: len %u exceeds truesize %lu\n",
 				 dev->name, len, (unsigned long)(truesize - room));

From 7d4a119e45828e643baedea2d2ac736804bc85ee Mon Sep 17 00:00:00 2001
From: Bui Quang Minh <minhquangbui99@gmail.com>
Date: Mon, 30 Jun 2025 21:42:12 +0700
Subject: [PATCH 1124/1334] virtio-net: use the check_mergeable_len helper

Replace the current repeated code to check received length in mergeable
mode with the new check_mergeable_len helper.

Signed-off-by: Bui Quang Minh <minhquangbui99@gmail.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Link: https://patch.msgid.link/20250630144212.48471-4-minhquangbui99@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/virtio_net.c | 34 +++++++---------------------------
 1 file changed, 7 insertions(+), 27 deletions(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 535a4534c27f..ecd3f46deb5d 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -2156,7 +2156,6 @@ static int virtnet_build_xdp_buff_mrg(struct net_device *dev,
 				      struct virtnet_rq_stats *stats)
 {
 	struct virtio_net_hdr_mrg_rxbuf *hdr = buf;
-	unsigned int headroom, tailroom, room;
 	struct skb_shared_info *shinfo;
 	unsigned int xdp_frags_truesz = 0;
 	unsigned int truesize;
@@ -2202,20 +2201,14 @@ static int virtnet_build_xdp_buff_mrg(struct net_device *dev,
 		page = virt_to_head_page(buf);
 		offset = buf - page_address(page);
 
-		truesize = mergeable_ctx_to_truesize(ctx);
-		headroom = mergeable_ctx_to_headroom(ctx);
-		tailroom = headroom ? sizeof(struct skb_shared_info) : 0;
-		room = SKB_DATA_ALIGN(headroom + tailroom);
-
-		xdp_frags_truesz += truesize;
-		if (unlikely(len > truesize - room)) {
+		if (check_mergeable_len(dev, ctx, len)) {
 			put_page(page);
-			pr_debug("%s: rx error: len %u exceeds truesize %lu\n",
-				 dev->name, len, (unsigned long)(truesize - room));
-			DEV_STATS_INC(dev, rx_length_errors);
 			goto err;
 		}
 
+		truesize = mergeable_ctx_to_truesize(ctx);
+		xdp_frags_truesz += truesize;
+
 		frag = &shinfo->frags[shinfo->nr_frags++];
 		skb_frag_fill_page_desc(frag, page, offset, len);
 		if (page_is_pfmemalloc(page))
@@ -2429,18 +2422,12 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 	struct sk_buff *head_skb, *curr_skb;
 	unsigned int truesize = mergeable_ctx_to_truesize(ctx);
 	unsigned int headroom = mergeable_ctx_to_headroom(ctx);
-	unsigned int tailroom = headroom ? sizeof(struct skb_shared_info) : 0;
-	unsigned int room = SKB_DATA_ALIGN(headroom + tailroom);
 
 	head_skb = NULL;
 	u64_stats_add(&stats->bytes, len - vi->hdr_len);
 
-	if (unlikely(len > truesize - room)) {
-		pr_debug("%s: rx error: len %u exceeds truesize %lu\n",
-			 dev->name, len, (unsigned long)(truesize - room));
-		DEV_STATS_INC(dev, rx_length_errors);
+	if (check_mergeable_len(dev, ctx, len))
 		goto err_skb;
-	}
 
 	if (unlikely(vi->xdp_enabled)) {
 		struct bpf_prog *xdp_prog;
@@ -2475,17 +2462,10 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 		u64_stats_add(&stats->bytes, len);
 		page = virt_to_head_page(buf);
 
-		truesize = mergeable_ctx_to_truesize(ctx);
-		headroom = mergeable_ctx_to_headroom(ctx);
-		tailroom = headroom ? sizeof(struct skb_shared_info) : 0;
-		room = SKB_DATA_ALIGN(headroom + tailroom);
-		if (unlikely(len > truesize - room)) {
-			pr_debug("%s: rx error: len %u exceeds truesize %lu\n",
-				 dev->name, len, (unsigned long)(truesize - room));
-			DEV_STATS_INC(dev, rx_length_errors);
+		if (check_mergeable_len(dev, ctx, len))
 			goto err_skb;
-		}
 
+		truesize = mergeable_ctx_to_truesize(ctx);
 		curr_skb  = virtnet_skb_append_frag(head_skb, curr_skb, page,
 						    buf, len, truesize);
 		if (!curr_skb)

From 5177373c31318c3c6a190383bfd232e6cf565c36 Mon Sep 17 00:00:00 2001
From: Bui Quang Minh <minhquangbui99@gmail.com>
Date: Mon, 30 Jun 2025 22:13:14 +0700
Subject: [PATCH 1125/1334] virtio-net: xsk: rx: fix the frame's length check

When calling buf_to_xdp, the len argument is the frame data's length
without virtio header's length (vi->hdr_len). We check that len with

	xsk_pool_get_rx_frame_size() + vi->hdr_len

to ensure the provided len does not larger than the allocated chunk
size. The additional vi->hdr_len is because in virtnet_add_recvbuf_xsk,
we use part of XDP_PACKET_HEADROOM for virtio header and ask the vhost
to start placing data from

	hard_start + XDP_PACKET_HEADROOM - vi->hdr_len
not
	hard_start + XDP_PACKET_HEADROOM

But the first buffer has virtio_header, so the maximum frame's length in
the first buffer can only be

	xsk_pool_get_rx_frame_size()
not
	xsk_pool_get_rx_frame_size() + vi->hdr_len

like in the current check.

This commit adds an additional argument to buf_to_xdp differentiate
between the first buffer and other ones to correctly calculate the maximum
frame's length.

Cc: stable@vger.kernel.org
Reviewed-by: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
Fixes: a4e7ba702701 ("virtio_net: xsk: rx: support recv small mode")
Signed-off-by: Bui Quang Minh <minhquangbui99@gmail.com>
Link: https://patch.msgid.link/20250630151315.86722-2-minhquangbui99@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/virtio_net.c | 22 ++++++++++++++++++----
 1 file changed, 18 insertions(+), 4 deletions(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index ecd3f46deb5d..50ff9a309ddc 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -1147,15 +1147,29 @@ static void check_sq_full_and_disable(struct virtnet_info *vi,
 	}
 }
 
+/* Note that @len is the length of received data without virtio header */
 static struct xdp_buff *buf_to_xdp(struct virtnet_info *vi,
-				   struct receive_queue *rq, void *buf, u32 len)
+				   struct receive_queue *rq, void *buf,
+				   u32 len, bool first_buf)
 {
 	struct xdp_buff *xdp;
 	u32 bufsize;
 
 	xdp = (struct xdp_buff *)buf;
 
-	bufsize = xsk_pool_get_rx_frame_size(rq->xsk_pool) + vi->hdr_len;
+	/* In virtnet_add_recvbuf_xsk, we use part of XDP_PACKET_HEADROOM for
+	 * virtio header and ask the vhost to fill data from
+	 *         hard_start + XDP_PACKET_HEADROOM - vi->hdr_len
+	 * The first buffer has virtio header so the remaining region for frame
+	 * data is
+	 *         xsk_pool_get_rx_frame_size()
+	 * While other buffers than the first one do not have virtio header, so
+	 * the maximum frame data's length can be
+	 *         xsk_pool_get_rx_frame_size() + vi->hdr_len
+	 */
+	bufsize = xsk_pool_get_rx_frame_size(rq->xsk_pool);
+	if (!first_buf)
+		bufsize += vi->hdr_len;
 
 	if (unlikely(len > bufsize)) {
 		pr_debug("%s: rx error: len %u exceeds truesize %u\n",
@@ -1280,7 +1294,7 @@ static int xsk_append_merge_buffer(struct virtnet_info *vi,
 
 		u64_stats_add(&stats->bytes, len);
 
-		xdp = buf_to_xdp(vi, rq, buf, len);
+		xdp = buf_to_xdp(vi, rq, buf, len, false);
 		if (!xdp)
 			goto err;
 
@@ -1378,7 +1392,7 @@ static void virtnet_receive_xsk_buf(struct virtnet_info *vi, struct receive_queu
 
 	u64_stats_add(&stats->bytes, len);
 
-	xdp = buf_to_xdp(vi, rq, buf, len);
+	xdp = buf_to_xdp(vi, rq, buf, len, true);
 	if (!xdp)
 		return;
 

From 38224c472a038fa9ccd4085511dd9f3d6119dbf9 Mon Sep 17 00:00:00 2001
From: Qasim Ijaz <qasdev00@gmail.com>
Date: Tue, 24 Jun 2025 13:52:56 +0100
Subject: [PATCH 1126/1334] HID: appletb-kbd: fix slab use-after-free bug in
 appletb_kbd_probe

In probe appletb_kbd_probe() a "struct appletb_kbd *kbd" is allocated
via devm_kzalloc() to store touch bar keyboard related data.
Later on if backlight_device_get_by_name() finds a backlight device
with name "appletb_backlight" a timer (kbd->inactivity_timer) is setup
with appletb_inactivity_timer() and the timer is armed to run after
appletb_tb_dim_timeout (60) seconds.

A use-after-free is triggered when failure occurs after the timer is
armed. This ultimately means probe failure occurs and as a result the
"struct appletb_kbd *kbd" which is device managed memory is freed.
After 60 seconds the timer will have expired and __run_timers will
attempt to access the timer (kbd->inactivity_timer) however the kdb
structure has been freed causing a use-after free.

[   71.636938] ==================================================================
[   71.637915] BUG: KASAN: slab-use-after-free in __run_timers+0x7ad/0x890
[   71.637915] Write of size 8 at addr ffff8881178c5958 by task swapper/1/0
[   71.637915]
[   71.637915] CPU: 1 UID: 0 PID: 0 Comm: swapper/1 Not tainted 6.16.0-rc2-00318-g739a6c93cc75-dirty #12 PREEMPT(voluntary)
[   71.637915] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.16.2-debian-1.16.2-1 04/01/2014
[   71.637915] Call Trace:
[   71.637915]  <IRQ>
[   71.637915]  dump_stack_lvl+0x53/0x70
[   71.637915]  print_report+0xce/0x670
[   71.637915]  ? __run_timers+0x7ad/0x890
[   71.637915]  kasan_report+0xce/0x100
[   71.637915]  ? __run_timers+0x7ad/0x890
[   71.637915]  __run_timers+0x7ad/0x890
[   71.637915]  ? __pfx___run_timers+0x10/0x10
[   71.637915]  ? update_process_times+0xfc/0x190
[   71.637915]  ? __pfx_update_process_times+0x10/0x10
[   71.637915]  ? _raw_spin_lock_irq+0x80/0xe0
[   71.637915]  ? _raw_spin_lock_irq+0x80/0xe0
[   71.637915]  ? __pfx__raw_spin_lock_irq+0x10/0x10
[   71.637915]  run_timer_softirq+0x141/0x240
[   71.637915]  ? __pfx_run_timer_softirq+0x10/0x10
[   71.637915]  ? __pfx___hrtimer_run_queues+0x10/0x10
[   71.637915]  ? kvm_clock_get_cycles+0x18/0x30
[   71.637915]  ? ktime_get+0x60/0x140
[   71.637915]  handle_softirqs+0x1b8/0x5c0
[   71.637915]  ? __pfx_handle_softirqs+0x10/0x10
[   71.637915]  irq_exit_rcu+0xaf/0xe0
[   71.637915]  sysvec_apic_timer_interrupt+0x6c/0x80
[   71.637915]  </IRQ>
[   71.637915]
[   71.637915] Allocated by task 39:
[   71.637915]  kasan_save_stack+0x33/0x60
[   71.637915]  kasan_save_track+0x14/0x30
[   71.637915]  __kasan_kmalloc+0x8f/0xa0
[   71.637915]  __kmalloc_node_track_caller_noprof+0x195/0x420
[   71.637915]  devm_kmalloc+0x74/0x1e0
[   71.637915]  appletb_kbd_probe+0x37/0x3c0
[   71.637915]  hid_device_probe+0x2d1/0x680
[   71.637915]  really_probe+0x1c3/0x690
[   71.637915]  __driver_probe_device+0x247/0x300
[   71.637915]  driver_probe_device+0x49/0x210
[...]
[   71.637915]
[   71.637915] Freed by task 39:
[   71.637915]  kasan_save_stack+0x33/0x60
[   71.637915]  kasan_save_track+0x14/0x30
[   71.637915]  kasan_save_free_info+0x3b/0x60
[   71.637915]  __kasan_slab_free+0x37/0x50
[   71.637915]  kfree+0xcf/0x360
[   71.637915]  devres_release_group+0x1f8/0x3c0
[   71.637915]  hid_device_probe+0x315/0x680
[   71.637915]  really_probe+0x1c3/0x690
[   71.637915]  __driver_probe_device+0x247/0x300
[   71.637915]  driver_probe_device+0x49/0x210
[...]

The root cause of the issue is that the timer is not disarmed
on failure paths leading to it remaining active and accessing
freed memory. To fix this call timer_delete_sync() to deactivate
the timer.

Another small issue is that timer_delete_sync is called
unconditionally in appletb_kbd_remove(), fix this by checking
for a valid kbd->backlight_dev before calling timer_delete_sync.

Fixes: 93a0fc489481 ("HID: hid-appletb-kbd: add support for automatic brightness control while using the touchbar")
Cc: stable@vger.kernel.org
Signed-off-by: Qasim Ijaz <qasdev00@gmail.com>
Reviewed-by: Aditya Garg <gargaditya08@live.com>
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
 drivers/hid/hid-appletb-kbd.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/drivers/hid/hid-appletb-kbd.c b/drivers/hid/hid-appletb-kbd.c
index b5d9e50bc231..271d1b27b8dd 100644
--- a/drivers/hid/hid-appletb-kbd.c
+++ b/drivers/hid/hid-appletb-kbd.c
@@ -440,8 +440,10 @@ static int appletb_kbd_probe(struct hid_device *hdev, const struct hid_device_id
 unregister_handler:
 	input_unregister_handler(&kbd->inp_handler);
 close_hw:
-	if (kbd->backlight_dev)
+	if (kbd->backlight_dev) {
 		put_device(&kbd->backlight_dev->dev);
+		timer_delete_sync(&kbd->inactivity_timer);
+	}
 	hid_hw_close(hdev);
 stop_hw:
 	hid_hw_stop(hdev);
@@ -455,10 +457,10 @@ static void appletb_kbd_remove(struct hid_device *hdev)
 	appletb_kbd_set_mode(kbd, APPLETB_KBD_MODE_OFF);
 
 	input_unregister_handler(&kbd->inp_handler);
-	timer_delete_sync(&kbd->inactivity_timer);
-
-	if (kbd->backlight_dev)
+	if (kbd->backlight_dev) {
 		put_device(&kbd->backlight_dev->dev);
+		timer_delete_sync(&kbd->inactivity_timer);
+	}
 
 	hid_hw_close(hdev);
 	hid_hw_stop(hdev);

From 105485a182dc6ba32e55db46839af756c105afae Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Tue, 1 Jul 2025 15:02:58 +0100
Subject: [PATCH 1127/1334] KVM: arm64: Fix handling of FEAT_GTG for
 unimplemented granule sizes

Booting an EL2 guest on a system only supporting a subset of the
possible page sizes leads to interesting situations.

For example, on a system that only supports 4kB and 64kB, and is
booted with a 4kB kernel, we end-up advertising 16kB support at
stage-2, which is pretty weird.

That's because we consider that any S2 bigger than our base granule
is fair game, irrespective of what the HW actually supports. While this
is not impossible to support (KVM would happily handle it), it is likely
to be confusing for the guest.

Add new checks that will verify that this granule size is actually
supported before publishing it to the guest.

Fixes: e7ef6ed4583ea ("KVM: arm64: Enforce NV limits on a per-idregs basis")
Reviewed-by: Oliver Upton <oliver.upton@linux.dev>
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/kvm/nested.c | 26 +++++++++++++++++++++++---
 1 file changed, 23 insertions(+), 3 deletions(-)

diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c
index 5b191f4dc566..dc1d26559bfa 100644
--- a/arch/arm64/kvm/nested.c
+++ b/arch/arm64/kvm/nested.c
@@ -1402,6 +1402,21 @@ static void kvm_map_l1_vncr(struct kvm_vcpu *vcpu)
 	}
 }
 
+#define has_tgran_2(__r, __sz)						\
+	({								\
+		u64 _s1, _s2, _mmfr0 = __r;				\
+									\
+		_s2 = SYS_FIELD_GET(ID_AA64MMFR0_EL1,			\
+				    TGRAN##__sz##_2, _mmfr0);		\
+									\
+		_s1 = SYS_FIELD_GET(ID_AA64MMFR0_EL1,			\
+				    TGRAN##__sz, _mmfr0);		\
+									\
+		((_s2 != ID_AA64MMFR0_EL1_TGRAN##__sz##_2_NI &&		\
+		  _s2 != ID_AA64MMFR0_EL1_TGRAN##__sz##_2_TGRAN##__sz) || \
+		 (_s2 == ID_AA64MMFR0_EL1_TGRAN##__sz##_2_TGRAN##__sz && \
+		  _s1 != ID_AA64MMFR0_EL1_TGRAN##__sz##_NI));		\
+	})
 /*
  * Our emulated CPU doesn't support all the possible features. For the
  * sake of simplicity (and probably mental sanity), wipe out a number
@@ -1411,6 +1426,8 @@ static void kvm_map_l1_vncr(struct kvm_vcpu *vcpu)
  */
 u64 limit_nv_id_reg(struct kvm *kvm, u32 reg, u64 val)
 {
+	u64 orig_val = val;
+
 	switch (reg) {
 	case SYS_ID_AA64ISAR0_EL1:
 		/* Support everything but TME */
@@ -1480,13 +1497,16 @@ u64 limit_nv_id_reg(struct kvm *kvm, u32 reg, u64 val)
 		 */
 		switch (PAGE_SIZE) {
 		case SZ_4K:
-			val |= SYS_FIELD_PREP_ENUM(ID_AA64MMFR0_EL1, TGRAN4_2, IMP);
+			if (has_tgran_2(orig_val, 4))
+				val |= SYS_FIELD_PREP_ENUM(ID_AA64MMFR0_EL1, TGRAN4_2, IMP);
 			fallthrough;
 		case SZ_16K:
-			val |= SYS_FIELD_PREP_ENUM(ID_AA64MMFR0_EL1, TGRAN16_2, IMP);
+			if (has_tgran_2(orig_val, 16))
+				val |= SYS_FIELD_PREP_ENUM(ID_AA64MMFR0_EL1, TGRAN16_2, IMP);
 			fallthrough;
 		case SZ_64K:
-			val |= SYS_FIELD_PREP_ENUM(ID_AA64MMFR0_EL1, TGRAN64_2, IMP);
+			if (has_tgran_2(orig_val, 64))
+				val |= SYS_FIELD_PREP_ENUM(ID_AA64MMFR0_EL1, TGRAN64_2, IMP);
 			break;
 		}
 

From 42ce432522a17685f5a84529de49e555477c0a1f Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Thu, 19 Jun 2025 14:48:17 +0100
Subject: [PATCH 1128/1334] KVM: arm64: Remove kvm_arch_vcpu_run_map_fp()

Historically KVM hyp code saved the host's FPSIMD state into the hosts's
fpsimd_state memory, and so it was necessary to map this into the hyp
Stage-1 mappings before running a vCPU.

This is no longer necessary as of commits:

* fbc7e61195e2 ("KVM: arm64: Unconditionally save+flush host FPSIMD/SVE/SME state")
* 8eca7f6d5100 ("KVM: arm64: Remove host FPSIMD saving for non-protected KVM")

Since those commits, we eagerly save the host's FPSIMD state before
calling into hyp to run a vCPU, and hyp code never reads nor writes the
host's fpsimd_state memory. There's no longer any need to map the host's
fpsimd_state memory into the hyp Stage-1, and kvm_arch_vcpu_run_map_fp()
is unnecessary but benign.

Remove kvm_arch_vcpu_run_map_fp(). Currently there is no code to perform
a corresponding unmap, and we never mapped the host's SVE or SME state
into the hyp Stage-1, so no other code needs to be removed.

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Fuad Tabba <tabba@google.com>
Cc: Marc Zyngier <maz@kernel.org>
Cc: Mark Brown <broonie@kernel.org>
Cc: Oliver Upton <oliver.upton@linux.dev>
Cc: Will Deacon <will@kernel.org>
Cc: kvmarm@lists.linux.dev
Reviewed-by: Mark Brown <broonie@kernel.org>
Tested-by: Fuad Tabba <tabba@google.com>
Reviewed-by: Fuad Tabba <tabba@google.com>
Link: https://lore.kernel.org/r/20250619134817.4075340-1-mark.rutland@arm.com
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/kvm_host.h |  1 -
 arch/arm64/kvm/arm.c              |  4 ----
 arch/arm64/kvm/fpsimd.c           | 26 --------------------------
 3 files changed, 31 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index d27079968341..3e41a880b062 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -1480,7 +1480,6 @@ int kvm_vm_ioctl_get_reg_writable_masks(struct kvm *kvm,
 					struct reg_mask_range *range);
 
 /* Guest/host FPSIMD coordination helpers */
-int kvm_arch_vcpu_run_map_fp(struct kvm_vcpu *vcpu);
 void kvm_arch_vcpu_load_fp(struct kvm_vcpu *vcpu);
 void kvm_arch_vcpu_ctxflush_fp(struct kvm_vcpu *vcpu);
 void kvm_arch_vcpu_ctxsync_fp(struct kvm_vcpu *vcpu);
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index b223d21c063c..23dd3f3fc3eb 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -825,10 +825,6 @@ int kvm_arch_vcpu_run_pid_change(struct kvm_vcpu *vcpu)
 	if (!kvm_arm_vcpu_is_finalized(vcpu))
 		return -EPERM;
 
-	ret = kvm_arch_vcpu_run_map_fp(vcpu);
-	if (ret)
-		return ret;
-
 	if (likely(vcpu_has_run_once(vcpu)))
 		return 0;
 
diff --git a/arch/arm64/kvm/fpsimd.c b/arch/arm64/kvm/fpsimd.c
index 8f6c8f57c6b9..15e17aca1dec 100644
--- a/arch/arm64/kvm/fpsimd.c
+++ b/arch/arm64/kvm/fpsimd.c
@@ -14,32 +14,6 @@
 #include <asm/kvm_mmu.h>
 #include <asm/sysreg.h>
 
-/*
- * Called on entry to KVM_RUN unless this vcpu previously ran at least
- * once and the most recent prior KVM_RUN for this vcpu was called from
- * the same task as current (highly likely).
- *
- * This is guaranteed to execute before kvm_arch_vcpu_load_fp(vcpu),
- * such that on entering hyp the relevant parts of current are already
- * mapped.
- */
-int kvm_arch_vcpu_run_map_fp(struct kvm_vcpu *vcpu)
-{
-	struct user_fpsimd_state *fpsimd = &current->thread.uw.fpsimd_state;
-	int ret;
-
-	/* pKVM has its own tracking of the host fpsimd state. */
-	if (is_protected_kvm_enabled())
-		return 0;
-
-	/* Make sure the host task fpsimd state is visible to hyp: */
-	ret = kvm_share_hyp(fpsimd, fpsimd + 1);
-	if (ret)
-		return ret;
-
-	return 0;
-}
-
 /*
  * Prepare vcpu for saving the host's FPSIMD state and loading the guest's.
  * The actual loading is done by the FPSIMD access trap taken to hyp.

From 45ebc7e6c125ce93d2ddf82cd5bea20121bb0258 Mon Sep 17 00:00:00 2001
From: Laurent Vivier <lvivier@redhat.com>
Date: Wed, 21 May 2025 11:22:34 +0200
Subject: [PATCH 1129/1334] virtio_ring: Fix error reporting in
 virtqueue_resize

The virtqueue_resize() function was not correctly propagating error codes
from its internal resize helper functions, specifically
virtqueue_resize_packet() and virtqueue_resize_split(). If these helpers
returned an error, but the subsequent call to virtqueue_enable_after_reset()
succeeded, the original error from the resize operation would be masked.
Consequently, virtqueue_resize() could incorrectly report success to its
caller despite an underlying resize failure.

This change restores the original code behavior:

       if (vdev->config->enable_vq_after_reset(_vq))
               return -EBUSY;

       return err;

Fix: commit ad48d53b5b3f ("virtio_ring: separate the logic of reset/enable from virtqueue_resize")
Cc: xuanzhuo@linux.alibaba.com
Signed-off-by: Laurent Vivier <lvivier@redhat.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Link: https://patch.msgid.link/20250521092236.661410-2-lvivier@redhat.com
Tested-by: Lei Yang <leiyang@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/virtio/virtio_ring.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
index b784aab66867..4397392bfef0 100644
--- a/drivers/virtio/virtio_ring.c
+++ b/drivers/virtio/virtio_ring.c
@@ -2797,7 +2797,7 @@ int virtqueue_resize(struct virtqueue *_vq, u32 num,
 		     void (*recycle_done)(struct virtqueue *vq))
 {
 	struct vring_virtqueue *vq = to_vvq(_vq);
-	int err;
+	int err, err_reset;
 
 	if (num > vq->vq.num_max)
 		return -E2BIG;
@@ -2819,7 +2819,11 @@ int virtqueue_resize(struct virtqueue *_vq, u32 num,
 	else
 		err = virtqueue_resize_split(_vq, num);
 
-	return virtqueue_enable_after_reset(_vq);
+	err_reset = virtqueue_enable_after_reset(_vq);
+	if (err_reset)
+		return err_reset;
+
+	return err;
 }
 EXPORT_SYMBOL_GPL(virtqueue_resize);
 

From bd2948d2581ebd31745c1b7094a470513789555f Mon Sep 17 00:00:00 2001
From: Laurent Vivier <lvivier@redhat.com>
Date: Wed, 21 May 2025 11:22:35 +0200
Subject: [PATCH 1130/1334] virtio_net: Cleanup '2+MAX_SKB_FRAGS'

Improve consistency by using everywhere it is needed
'MAX_SKB_FRAGS + 2' rather than '2+MAX_SKB_FRAGS' or
'2 + MAX_SKB_FRAGS'.

No functional change.

Signed-off-by: Laurent Vivier <lvivier@redhat.com>
Reviewed-by: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Link: https://patch.msgid.link/20250521092236.661410-3-lvivier@redhat.com
Tested-by: Lei Yang <leiyang@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/virtio_net.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 50ff9a309ddc..031f82275316 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -1104,7 +1104,7 @@ static bool tx_may_stop(struct virtnet_info *vi,
 	 * Since most packets only take 1 or 2 ring slots, stopping the queue
 	 * early means 16 slots are typically wasted.
 	 */
-	if (sq->vq->num_free < 2+MAX_SKB_FRAGS) {
+	if (sq->vq->num_free < MAX_SKB_FRAGS + 2) {
 		struct netdev_queue *txq = netdev_get_tx_queue(dev, qnum);
 
 		netif_tx_stop_queue(txq);
@@ -1136,7 +1136,7 @@ static void check_sq_full_and_disable(struct virtnet_info *vi,
 		} else if (unlikely(!virtqueue_enable_cb_delayed(sq->vq))) {
 			/* More just got used, free them then recheck. */
 			free_old_xmit(sq, txq, false);
-			if (sq->vq->num_free >= 2+MAX_SKB_FRAGS) {
+			if (sq->vq->num_free >= MAX_SKB_FRAGS + 2) {
 				netif_start_subqueue(dev, qnum);
 				u64_stats_update_begin(&sq->stats.syncp);
 				u64_stats_inc(&sq->stats.wake);
@@ -3021,7 +3021,7 @@ static void virtnet_poll_cleantx(struct receive_queue *rq, int budget)
 			free_old_xmit(sq, txq, !!budget);
 		} while (unlikely(!virtqueue_enable_cb_delayed(sq->vq)));
 
-		if (sq->vq->num_free >= 2 + MAX_SKB_FRAGS) {
+		if (sq->vq->num_free >= MAX_SKB_FRAGS + 2) {
 			if (netif_tx_queue_stopped(txq)) {
 				u64_stats_update_begin(&sq->stats.syncp);
 				u64_stats_inc(&sq->stats.wake);
@@ -3218,7 +3218,7 @@ static int virtnet_poll_tx(struct napi_struct *napi, int budget)
 	else
 		free_old_xmit(sq, txq, !!budget);
 
-	if (sq->vq->num_free >= 2 + MAX_SKB_FRAGS) {
+	if (sq->vq->num_free >= MAX_SKB_FRAGS + 2) {
 		if (netif_tx_queue_stopped(txq)) {
 			u64_stats_update_begin(&sq->stats.syncp);
 			u64_stats_inc(&sq->stats.wake);

From 24b2f5df86aaebbe7bac40304eaf5a146c02367c Mon Sep 17 00:00:00 2001
From: Laurent Vivier <lvivier@redhat.com>
Date: Wed, 21 May 2025 11:22:36 +0200
Subject: [PATCH 1131/1334] virtio_net: Enforce minimum TX ring size for
 reliability

The `tx_may_stop()` logic stops TX queues if free descriptors
(`sq->vq->num_free`) fall below the threshold of (`MAX_SKB_FRAGS` + 2).
If the total ring size (`ring_num`) is not strictly greater than this
value, queues can become persistently stopped or stop after minimal
use, severely degrading performance.

A single sk_buff transmission typically requires descriptors for:
- The virtio_net_hdr (1 descriptor)
- The sk_buff's linear data (head) (1 descriptor)
- Paged fragments (up to MAX_SKB_FRAGS descriptors)

This patch enforces that the TX ring size ('ring_num') must be strictly
greater than (MAX_SKB_FRAGS + 2). This ensures that the ring is
always large enough to hold at least one maximally-fragmented packet
plus at least one additional slot.

Reported-by: Lei Yang <leiyang@redhat.com>
Signed-off-by: Laurent Vivier <lvivier@redhat.com>
Reviewed-by: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Link: https://patch.msgid.link/20250521092236.661410-4-lvivier@redhat.com
Tested-by: Lei Yang <leiyang@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/virtio_net.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 031f82275316..5d674eb9a0f2 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -3504,6 +3504,12 @@ static int virtnet_tx_resize(struct virtnet_info *vi, struct send_queue *sq,
 {
 	int qindex, err;
 
+	if (ring_num <= MAX_SKB_FRAGS + 2) {
+		netdev_err(vi->dev, "tx size (%d) cannot be smaller than %d\n",
+			   ring_num, MAX_SKB_FRAGS + 2);
+		return -EINVAL;
+	}
+
 	qindex = sq - vi->sq;
 
 	virtnet_tx_pause(vi, sq);

From cc9f7f65cd2f31150b10e6956f1f0882e1bbae49 Mon Sep 17 00:00:00 2001
From: Jiawen Wu <jiawenwu@trustnetic.com>
Date: Tue, 1 Jul 2025 14:30:28 +0800
Subject: [PATCH 1132/1334] net: txgbe: request MISC IRQ in ndo_open

Move the creating of irq_domain for MISC IRQ from .probe to .ndo_open,
and free it in .ndo_stop, to maintain consistency with the queue IRQs.
This it for subsequent adjustments to the IRQ vectors.

Fixes: aefd013624a1 ("net: txgbe: use irq_domain for interrupt controller")
Cc: stable@vger.kernel.org
Signed-off-by: Jiawen Wu <jiawenwu@trustnetic.com>
Reviewed-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Link: https://patch.msgid.link/20250701063030.59340-2-jiawenwu@trustnetic.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../net/ethernet/wangxun/txgbe/txgbe_irq.c    |  2 +-
 .../net/ethernet/wangxun/txgbe/txgbe_main.c   | 22 +++++++++----------
 2 files changed, 11 insertions(+), 13 deletions(-)

diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_irq.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_irq.c
index 20b9a28bcb55..dc468053bdf8 100644
--- a/drivers/net/ethernet/wangxun/txgbe/txgbe_irq.c
+++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_irq.c
@@ -78,7 +78,6 @@ free_queue_irqs:
 		free_irq(wx->msix_q_entries[vector].vector,
 			 wx->q_vector[vector]);
 	}
-	wx_reset_interrupt_capability(wx);
 	return err;
 }
 
@@ -211,6 +210,7 @@ void txgbe_free_misc_irq(struct txgbe *txgbe)
 	free_irq(txgbe->link_irq, txgbe);
 	free_irq(txgbe->misc.irq, txgbe);
 	txgbe_del_irq_domain(txgbe);
+	txgbe->wx->misc_irq_domain = false;
 }
 
 int txgbe_setup_misc_irq(struct txgbe *txgbe)
diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c
index f3d2778b8e35..a5867f3c93fc 100644
--- a/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c
+++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c
@@ -458,10 +458,14 @@ static int txgbe_open(struct net_device *netdev)
 
 	wx_configure(wx);
 
-	err = txgbe_request_queue_irqs(wx);
+	err = txgbe_setup_misc_irq(wx->priv);
 	if (err)
 		goto err_free_resources;
 
+	err = txgbe_request_queue_irqs(wx);
+	if (err)
+		goto err_free_misc_irq;
+
 	/* Notify the stack of the actual queue counts. */
 	err = netif_set_real_num_tx_queues(netdev, wx->num_tx_queues);
 	if (err)
@@ -479,6 +483,9 @@ static int txgbe_open(struct net_device *netdev)
 
 err_free_irq:
 	wx_free_irq(wx);
+err_free_misc_irq:
+	txgbe_free_misc_irq(wx->priv);
+	wx_reset_interrupt_capability(wx);
 err_free_resources:
 	wx_free_resources(wx);
 err_reset:
@@ -519,6 +526,7 @@ static int txgbe_close(struct net_device *netdev)
 	wx_ptp_stop(wx);
 	txgbe_down(wx);
 	wx_free_irq(wx);
+	txgbe_free_misc_irq(wx->priv);
 	wx_free_resources(wx);
 	txgbe_fdir_filter_exit(wx);
 	wx_control_hw(wx, false);
@@ -564,7 +572,6 @@ static void txgbe_shutdown(struct pci_dev *pdev)
 int txgbe_setup_tc(struct net_device *dev, u8 tc)
 {
 	struct wx *wx = netdev_priv(dev);
-	struct txgbe *txgbe = wx->priv;
 
 	/* Hardware has to reinitialize queues and interrupts to
 	 * match packet buffer alignment. Unfortunately, the
@@ -575,7 +582,6 @@ int txgbe_setup_tc(struct net_device *dev, u8 tc)
 	else
 		txgbe_reset(wx);
 
-	txgbe_free_misc_irq(txgbe);
 	wx_clear_interrupt_scheme(wx);
 
 	if (tc)
@@ -584,7 +590,6 @@ int txgbe_setup_tc(struct net_device *dev, u8 tc)
 		netdev_reset_tc(dev);
 
 	wx_init_interrupt_scheme(wx);
-	txgbe_setup_misc_irq(txgbe);
 
 	if (netif_running(dev))
 		txgbe_open(dev);
@@ -882,13 +887,9 @@ static int txgbe_probe(struct pci_dev *pdev,
 
 	txgbe_init_fdir(txgbe);
 
-	err = txgbe_setup_misc_irq(txgbe);
-	if (err)
-		goto err_release_hw;
-
 	err = txgbe_init_phy(txgbe);
 	if (err)
-		goto err_free_misc_irq;
+		goto err_release_hw;
 
 	err = register_netdev(netdev);
 	if (err)
@@ -916,8 +917,6 @@ static int txgbe_probe(struct pci_dev *pdev,
 
 err_remove_phy:
 	txgbe_remove_phy(txgbe);
-err_free_misc_irq:
-	txgbe_free_misc_irq(txgbe);
 err_release_hw:
 	wx_clear_interrupt_scheme(wx);
 	wx_control_hw(wx, false);
@@ -957,7 +956,6 @@ static void txgbe_remove(struct pci_dev *pdev)
 	unregister_netdev(netdev);
 
 	txgbe_remove_phy(txgbe);
-	txgbe_free_misc_irq(txgbe);
 	wx_free_isb_resources(wx);
 
 	pci_release_selected_regions(pdev,

From e37546ad1f9b2c777d3a21d7e50ce265ee3dece8 Mon Sep 17 00:00:00 2001
From: Jiawen Wu <jiawenwu@trustnetic.com>
Date: Tue, 1 Jul 2025 14:30:29 +0800
Subject: [PATCH 1133/1334] net: wangxun: revert the adjustment of the IRQ
 vector sequence

Due to hardware limitations of NGBE, queue IRQs can only be requested
on vector 0 to 7. When the number of queues is set to the maximum 8,
the PCI IRQ vectors are allocated from 0 to 8. The vector 0 is used by
MISC interrupt, and althrough the vector 8 is used by queue interrupt,
it is unable to receive packets. This will cause some packets to be
dropped when RSS is enabled and they are assigned to queue 8.

So revert the adjustment of the MISC IRQ location, to make it be the
last one in IRQ vectors.

Fixes: 937d46ecc5f9 ("net: wangxun: add ethtool_ops for channel number")
Cc: stable@vger.kernel.org
Signed-off-by: Jiawen Wu <jiawenwu@trustnetic.com>
Reviewed-by: Larysa Zaremba <larysa.zaremba@intel.com>
Link: https://patch.msgid.link/20250701063030.59340-3-jiawenwu@trustnetic.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/wangxun/libwx/wx_lib.c     | 17 ++++++++---------
 drivers/net/ethernet/wangxun/libwx/wx_type.h    |  2 +-
 drivers/net/ethernet/wangxun/ngbe/ngbe_main.c   |  2 +-
 drivers/net/ethernet/wangxun/ngbe/ngbe_type.h   |  2 +-
 drivers/net/ethernet/wangxun/txgbe/txgbe_irq.c  |  6 +++---
 drivers/net/ethernet/wangxun/txgbe/txgbe_type.h |  4 ++--
 6 files changed, 16 insertions(+), 17 deletions(-)

diff --git a/drivers/net/ethernet/wangxun/libwx/wx_lib.c b/drivers/net/ethernet/wangxun/libwx/wx_lib.c
index 59840ba9c1fe..835d60bd5fbc 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_lib.c
+++ b/drivers/net/ethernet/wangxun/libwx/wx_lib.c
@@ -1747,7 +1747,7 @@ static void wx_set_num_queues(struct wx *wx)
  */
 static int wx_acquire_msix_vectors(struct wx *wx)
 {
-	struct irq_affinity affd = { .pre_vectors = 1 };
+	struct irq_affinity affd = { .post_vectors = 1 };
 	int nvecs, i;
 
 	/* We start by asking for one vector per queue pair */
@@ -1784,16 +1784,17 @@ static int wx_acquire_msix_vectors(struct wx *wx)
 		return nvecs;
 	}
 
-	wx->msix_entry->entry = 0;
-	wx->msix_entry->vector = pci_irq_vector(wx->pdev, 0);
 	nvecs -= 1;
 	for (i = 0; i < nvecs; i++) {
 		wx->msix_q_entries[i].entry = i;
-		wx->msix_q_entries[i].vector = pci_irq_vector(wx->pdev, i + 1);
+		wx->msix_q_entries[i].vector = pci_irq_vector(wx->pdev, i);
 	}
 
 	wx->num_q_vectors = nvecs;
 
+	wx->msix_entry->entry = nvecs;
+	wx->msix_entry->vector = pci_irq_vector(wx->pdev, nvecs);
+
 	return 0;
 }
 
@@ -2300,8 +2301,6 @@ static void wx_set_ivar(struct wx *wx, s8 direction,
 		wr32(wx, WX_PX_MISC_IVAR, ivar);
 	} else {
 		/* tx or rx causes */
-		if (!(wx->mac.type == wx_mac_em && wx->num_vfs == 7))
-			msix_vector += 1; /* offset for queue vectors */
 		msix_vector |= WX_PX_IVAR_ALLOC_VAL;
 		index = ((16 * (queue & 1)) + (8 * direction));
 		ivar = rd32(wx, WX_PX_IVAR(queue >> 1));
@@ -2340,7 +2339,7 @@ void wx_write_eitr(struct wx_q_vector *q_vector)
 
 	itr_reg |= WX_PX_ITR_CNT_WDIS;
 
-	wr32(wx, WX_PX_ITR(v_idx + 1), itr_reg);
+	wr32(wx, WX_PX_ITR(v_idx), itr_reg);
 }
 
 /**
@@ -2393,9 +2392,9 @@ void wx_configure_vectors(struct wx *wx)
 		wx_write_eitr(q_vector);
 	}
 
-	wx_set_ivar(wx, -1, 0, 0);
+	wx_set_ivar(wx, -1, 0, v_idx);
 	if (pdev->msix_enabled)
-		wr32(wx, WX_PX_ITR(0), 1950);
+		wr32(wx, WX_PX_ITR(v_idx), 1950);
 }
 EXPORT_SYMBOL(wx_configure_vectors);
 
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_type.h b/drivers/net/ethernet/wangxun/libwx/wx_type.h
index 7730c9fc3e02..d392394791b3 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_type.h
+++ b/drivers/net/ethernet/wangxun/libwx/wx_type.h
@@ -1343,7 +1343,7 @@ struct wx {
 };
 
 #define WX_INTR_ALL (~0ULL)
-#define WX_INTR_Q(i) BIT((i) + 1)
+#define WX_INTR_Q(i) BIT((i))
 
 /* register operations */
 #define wr32(a, reg, value)	writel((value), ((a)->hw_addr + (reg)))
diff --git a/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c b/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c
index b5022c49dc5e..68415a7ef12f 100644
--- a/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c
+++ b/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c
@@ -161,7 +161,7 @@ static void ngbe_irq_enable(struct wx *wx, bool queues)
 	if (queues)
 		wx_intr_enable(wx, NGBE_INTR_ALL);
 	else
-		wx_intr_enable(wx, NGBE_INTR_MISC);
+		wx_intr_enable(wx, NGBE_INTR_MISC(wx));
 }
 
 /**
diff --git a/drivers/net/ethernet/wangxun/ngbe/ngbe_type.h b/drivers/net/ethernet/wangxun/ngbe/ngbe_type.h
index bb74263f0498..6eca6de475f7 100644
--- a/drivers/net/ethernet/wangxun/ngbe/ngbe_type.h
+++ b/drivers/net/ethernet/wangxun/ngbe/ngbe_type.h
@@ -87,7 +87,7 @@
 #define NGBE_PX_MISC_IC_TIMESYNC		BIT(11) /* time sync */
 
 #define NGBE_INTR_ALL				0x1FF
-#define NGBE_INTR_MISC				BIT(0)
+#define NGBE_INTR_MISC(A)			BIT((A)->num_q_vectors)
 
 #define NGBE_PHY_CONFIG(reg_offset)		(0x14000 + ((reg_offset) * 4))
 #define NGBE_CFG_LAN_SPEED			0x14440
diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_irq.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_irq.c
index dc468053bdf8..3885283681ec 100644
--- a/drivers/net/ethernet/wangxun/txgbe/txgbe_irq.c
+++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_irq.c
@@ -31,7 +31,7 @@ void txgbe_irq_enable(struct wx *wx, bool queues)
 	wr32(wx, WX_PX_MISC_IEN, misc_ien);
 
 	/* unmask interrupt */
-	wx_intr_enable(wx, TXGBE_INTR_MISC);
+	wx_intr_enable(wx, TXGBE_INTR_MISC(wx));
 	if (queues)
 		wx_intr_enable(wx, TXGBE_INTR_QALL(wx));
 }
@@ -131,7 +131,7 @@ static irqreturn_t txgbe_misc_irq_handle(int irq, void *data)
 		txgbe->eicr = eicr;
 		if (eicr & TXGBE_PX_MISC_IC_VF_MBOX) {
 			wx_msg_task(txgbe->wx);
-			wx_intr_enable(wx, TXGBE_INTR_MISC);
+			wx_intr_enable(wx, TXGBE_INTR_MISC(wx));
 		}
 		return IRQ_WAKE_THREAD;
 	}
@@ -183,7 +183,7 @@ static irqreturn_t txgbe_misc_irq_thread_fn(int irq, void *data)
 		nhandled++;
 	}
 
-	wx_intr_enable(wx, TXGBE_INTR_MISC);
+	wx_intr_enable(wx, TXGBE_INTR_MISC(wx));
 	return (nhandled > 0 ? IRQ_HANDLED : IRQ_NONE);
 }
 
diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_type.h b/drivers/net/ethernet/wangxun/txgbe/txgbe_type.h
index 42ec815159e8..41915d7dd372 100644
--- a/drivers/net/ethernet/wangxun/txgbe/txgbe_type.h
+++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_type.h
@@ -302,8 +302,8 @@ struct txgbe_fdir_filter {
 #define TXGBE_DEFAULT_RX_WORK           128
 #endif
 
-#define TXGBE_INTR_MISC       BIT(0)
-#define TXGBE_INTR_QALL(A)    GENMASK((A)->num_q_vectors, 1)
+#define TXGBE_INTR_MISC(A)    BIT((A)->num_q_vectors)
+#define TXGBE_INTR_QALL(A)    (TXGBE_INTR_MISC(A) - 1)
 
 #define TXGBE_MAX_EITR        GENMASK(11, 3)
 

From 4174c0c331a2aa3322d3b3be532808deb041b37d Mon Sep 17 00:00:00 2001
From: Jiawen Wu <jiawenwu@trustnetic.com>
Date: Tue, 1 Jul 2025 14:30:30 +0800
Subject: [PATCH 1134/1334] net: ngbe: specify IRQ vector when the number of
 VFs is 7

For NGBE devices, the queue number is limited to be 1 when SRIOV is
enabled. In this case, IRQ vector[0] is used for MISC and vector[1] is
used for queue, based on the previous patches. But for the hardware
design, the IRQ vector[1] must be allocated for use by the VF[6] when
the number of VFs is 7. So the IRQ vector[0] should be shared for PF
MISC and QUEUE interrupts.

+-----------+----------------------+
| Vector    | Assigned To          |
+-----------+----------------------+
| Vector 0  | PF MISC and QUEUE    |
| Vector 1  | VF 6                 |
| Vector 2  | VF 5                 |
| Vector 3  | VF 4                 |
| Vector 4  | VF 3                 |
| Vector 5  | VF 2                 |
| Vector 6  | VF 1                 |
| Vector 7  | VF 0                 |
+-----------+----------------------+

Minimize code modifications, only adjust the IRQ vector number for this
case.

Fixes: 877253d2cbf2 ("net: ngbe: add sriov function support")
Signed-off-by: Jiawen Wu <jiawenwu@trustnetic.com>
Reviewed-by: Larysa Zaremba <larysa.zaremba@intel.com>
Link: https://patch.msgid.link/20250701063030.59340-4-jiawenwu@trustnetic.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/wangxun/libwx/wx_lib.c   | 9 +++++++++
 drivers/net/ethernet/wangxun/libwx/wx_sriov.c | 4 ++++
 drivers/net/ethernet/wangxun/libwx/wx_type.h  | 1 +
 drivers/net/ethernet/wangxun/ngbe/ngbe_main.c | 2 +-
 drivers/net/ethernet/wangxun/ngbe/ngbe_type.h | 2 +-
 5 files changed, 16 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/wangxun/libwx/wx_lib.c b/drivers/net/ethernet/wangxun/libwx/wx_lib.c
index 835d60bd5fbc..55e252789db3 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_lib.c
+++ b/drivers/net/ethernet/wangxun/libwx/wx_lib.c
@@ -1795,6 +1795,13 @@ static int wx_acquire_msix_vectors(struct wx *wx)
 	wx->msix_entry->entry = nvecs;
 	wx->msix_entry->vector = pci_irq_vector(wx->pdev, nvecs);
 
+	if (test_bit(WX_FLAG_IRQ_VECTOR_SHARED, wx->flags)) {
+		wx->msix_entry->entry = 0;
+		wx->msix_entry->vector = pci_irq_vector(wx->pdev, 0);
+		wx->msix_q_entries[0].entry = 0;
+		wx->msix_q_entries[0].vector = pci_irq_vector(wx->pdev, 1);
+	}
+
 	return 0;
 }
 
@@ -2293,6 +2300,8 @@ static void wx_set_ivar(struct wx *wx, s8 direction,
 
 	if (direction == -1) {
 		/* other causes */
+		if (test_bit(WX_FLAG_IRQ_VECTOR_SHARED, wx->flags))
+			msix_vector = 0;
 		msix_vector |= WX_PX_IVAR_ALLOC_VAL;
 		index = 0;
 		ivar = rd32(wx, WX_PX_MISC_IVAR);
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_sriov.c b/drivers/net/ethernet/wangxun/libwx/wx_sriov.c
index e8656d9d733b..c82ae137756c 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_sriov.c
+++ b/drivers/net/ethernet/wangxun/libwx/wx_sriov.c
@@ -64,6 +64,7 @@ static void wx_sriov_clear_data(struct wx *wx)
 	wr32m(wx, WX_PSR_VM_CTL, WX_PSR_VM_CTL_POOL_MASK, 0);
 	wx->ring_feature[RING_F_VMDQ].offset = 0;
 
+	clear_bit(WX_FLAG_IRQ_VECTOR_SHARED, wx->flags);
 	clear_bit(WX_FLAG_SRIOV_ENABLED, wx->flags);
 	/* Disable VMDq flag so device will be set in NM mode */
 	if (wx->ring_feature[RING_F_VMDQ].limit == 1)
@@ -78,6 +79,9 @@ static int __wx_enable_sriov(struct wx *wx, u8 num_vfs)
 	set_bit(WX_FLAG_SRIOV_ENABLED, wx->flags);
 	dev_info(&wx->pdev->dev, "SR-IOV enabled with %d VFs\n", num_vfs);
 
+	if (num_vfs == 7 && wx->mac.type == wx_mac_em)
+		set_bit(WX_FLAG_IRQ_VECTOR_SHARED, wx->flags);
+
 	/* Enable VMDq flag so device will be set in VM mode */
 	set_bit(WX_FLAG_VMDQ_ENABLED, wx->flags);
 	if (!wx->ring_feature[RING_F_VMDQ].limit)
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_type.h b/drivers/net/ethernet/wangxun/libwx/wx_type.h
index d392394791b3..c363379126c0 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_type.h
+++ b/drivers/net/ethernet/wangxun/libwx/wx_type.h
@@ -1191,6 +1191,7 @@ enum wx_pf_flags {
 	WX_FLAG_VMDQ_ENABLED,
 	WX_FLAG_VLAN_PROMISC,
 	WX_FLAG_SRIOV_ENABLED,
+	WX_FLAG_IRQ_VECTOR_SHARED,
 	WX_FLAG_FDIR_CAPABLE,
 	WX_FLAG_FDIR_HASH,
 	WX_FLAG_FDIR_PERFECT,
diff --git a/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c b/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c
index 68415a7ef12f..e0fc897b0a58 100644
--- a/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c
+++ b/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c
@@ -286,7 +286,7 @@ static int ngbe_request_msix_irqs(struct wx *wx)
 	 * for queue. But when num_vfs == 7, vector[1] is assigned to vf6.
 	 * Misc and queue should reuse interrupt vector[0].
 	 */
-	if (wx->num_vfs == 7)
+	if (test_bit(WX_FLAG_IRQ_VECTOR_SHARED, wx->flags))
 		err = request_irq(wx->msix_entry->vector,
 				  ngbe_misc_and_queue, 0, netdev->name, wx);
 	else
diff --git a/drivers/net/ethernet/wangxun/ngbe/ngbe_type.h b/drivers/net/ethernet/wangxun/ngbe/ngbe_type.h
index 6eca6de475f7..3b2ca7f47e33 100644
--- a/drivers/net/ethernet/wangxun/ngbe/ngbe_type.h
+++ b/drivers/net/ethernet/wangxun/ngbe/ngbe_type.h
@@ -87,7 +87,7 @@
 #define NGBE_PX_MISC_IC_TIMESYNC		BIT(11) /* time sync */
 
 #define NGBE_INTR_ALL				0x1FF
-#define NGBE_INTR_MISC(A)			BIT((A)->num_q_vectors)
+#define NGBE_INTR_MISC(A)			BIT((A)->msix_entry->entry)
 
 #define NGBE_PHY_CONFIG(reg_offset)		(0x14000 + ((reg_offset) * 4))
 #define NGBE_CFG_LAN_SPEED			0x14440

From f030713e5abf67d0a88864c8855f809c763af954 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Tue, 1 Jul 2025 08:36:22 +0200
Subject: [PATCH 1135/1334] dt-bindings: net: sophgo,sg2044-dwmac: Drop status
 from the example

Examples should be complete and should not have a 'status' property,
especially a disabled one because this disables the dt_binding_check of
the example against the schema.  Dropping 'status' property shows
missing other properties - phy-mode and phy-handle.

Fixes: 114508a89ddc ("dt-bindings: net: Add support for Sophgo SG2044 dwmac")
Cc: <stable@vger.kernel.org>
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Alexander Sverdlin <alexander.sverdlin@gmail.com>
Reviewed-by: Chen Wang <unicorn_wang@outlook.com>
Link: https://patch.msgid.link/20250701063621.23808-2-krzysztof.kozlowski@linaro.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 Documentation/devicetree/bindings/net/sophgo,sg2044-dwmac.yaml | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/net/sophgo,sg2044-dwmac.yaml b/Documentation/devicetree/bindings/net/sophgo,sg2044-dwmac.yaml
index 4dd2dc9c678b..8afbd9ebd73f 100644
--- a/Documentation/devicetree/bindings/net/sophgo,sg2044-dwmac.yaml
+++ b/Documentation/devicetree/bindings/net/sophgo,sg2044-dwmac.yaml
@@ -80,6 +80,8 @@ examples:
       interrupt-parent = <&intc>;
       interrupts = <296 IRQ_TYPE_LEVEL_HIGH>;
       interrupt-names = "macirq";
+      phy-handle = <&phy0>;
+      phy-mode = "rgmii-id";
       resets = <&rst 30>;
       reset-names = "stmmaceth";
       snps,multicast-filter-bins = <0>;
@@ -91,7 +93,6 @@ examples:
       snps,mtl-rx-config = <&gmac0_mtl_rx_setup>;
       snps,mtl-tx-config = <&gmac0_mtl_tx_setup>;
       snps,axi-config = <&gmac0_stmmac_axi_setup>;
-      status = "disabled";
 
       gmac0_mtl_rx_setup: rx-queues-config {
         snps,rx-queues-to-use = <8>;

From 223e2288f4b8c262a864e2c03964ffac91744cd5 Mon Sep 17 00:00:00 2001
From: HarshaVardhana S A <harshavardhana.sa@broadcom.com>
Date: Tue, 1 Jul 2025 14:22:54 +0200
Subject: [PATCH 1136/1334] vsock/vmci: Clear the vmci transport packet
 properly when initializing it

In vmci_transport_packet_init memset the vmci_transport_packet before
populating the fields to avoid any uninitialised data being left in the
structure.

Cc: Bryan Tan <bryan-bt.tan@broadcom.com>
Cc: Vishnu Dasa <vishnu.dasa@broadcom.com>
Cc: Broadcom internal kernel review list
Cc: Stefano Garzarella <sgarzare@redhat.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Jakub Kicinski <kuba@kernel.org>
Cc: Paolo Abeni <pabeni@redhat.com>
Cc: Simon Horman <horms@kernel.org>
Cc: virtualization@lists.linux.dev
Cc: netdev@vger.kernel.org
Cc: stable <stable@kernel.org>
Signed-off-by: HarshaVardhana S A <harshavardhana.sa@broadcom.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Fixes: d021c344051a ("VSOCK: Introduce VM Sockets")
Acked-by: Stefano Garzarella <sgarzare@redhat.com>
Link: https://patch.msgid.link/20250701122254.2397440-1-gregkh@linuxfoundation.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/vmw_vsock/vmci_transport.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c
index b370070194fa..7eccd6708d66 100644
--- a/net/vmw_vsock/vmci_transport.c
+++ b/net/vmw_vsock/vmci_transport.c
@@ -119,6 +119,8 @@ vmci_transport_packet_init(struct vmci_transport_packet *pkt,
 			   u16 proto,
 			   struct vmci_handle handle)
 {
+	memset(pkt, 0, sizeof(*pkt));
+
 	/* We register the stream control handler as an any cid handle so we
 	 * must always send from a source address of VMADDR_CID_ANY
 	 */
@@ -131,8 +133,6 @@ vmci_transport_packet_init(struct vmci_transport_packet *pkt,
 	pkt->type = type;
 	pkt->src_port = src->svm_port;
 	pkt->dst_port = dst->svm_port;
-	memset(&pkt->proto, 0, sizeof(pkt->proto));
-	memset(&pkt->_reserved2, 0, sizeof(pkt->_reserved2));
 
 	switch (pkt->type) {
 	case VMCI_TRANSPORT_PACKET_TYPE_INVALID:

From de1675de39aa945bad5937d1fde4df3682670639 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Thu, 3 Jul 2025 12:54:55 +0200
Subject: [PATCH 1137/1334] Revert "ACPI: battery: negate current when
 discharging"

Revert commit 234f71555019 ("ACPI: battery: negate current when
discharging") breaks not one but several userspace implementations
of battery monitoring: Steam and MangoHud. Perhaps it breaks more,
but those are the two that have been tested.

Reported-by: Matthew Schwartz <matthew.schwartz@linux.dev>
Closes: https://lore.kernel.org/linux-acpi/87C1B2AF-D430-4568-B620-14B941A8ABA4@linux.dev/
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/battery.c | 19 +++----------------
 1 file changed, 3 insertions(+), 16 deletions(-)

diff --git a/drivers/acpi/battery.c b/drivers/acpi/battery.c
index 45593612a4db..6905b56bf3e4 100644
--- a/drivers/acpi/battery.c
+++ b/drivers/acpi/battery.c
@@ -243,23 +243,10 @@ static int acpi_battery_get_property(struct power_supply *psy,
 		break;
 	case POWER_SUPPLY_PROP_CURRENT_NOW:
 	case POWER_SUPPLY_PROP_POWER_NOW:
-		if (battery->rate_now == ACPI_BATTERY_VALUE_UNKNOWN) {
+		if (battery->rate_now == ACPI_BATTERY_VALUE_UNKNOWN)
 			ret = -ENODEV;
-			break;
-		}
-
-		val->intval = battery->rate_now * 1000;
-		/*
-		 * When discharging, the current should be reported as a
-		 * negative number as per the power supply class interface
-		 * definition.
-		 */
-		if (psp == POWER_SUPPLY_PROP_CURRENT_NOW &&
-		    (battery->state & ACPI_BATTERY_STATE_DISCHARGING) &&
-		    acpi_battery_handle_discharging(battery)
-				== POWER_SUPPLY_STATUS_DISCHARGING)
-			val->intval = -val->intval;
-
+		else
+			val->intval = battery->rate_now * 1000;
 		break;
 	case POWER_SUPPLY_PROP_CHARGE_FULL_DESIGN:
 	case POWER_SUPPLY_PROP_ENERGY_FULL_DESIGN:

From 3b3312f28ee2d9c386602f8521e419cfc69f4823 Mon Sep 17 00:00:00 2001
From: Richard Fitzgerald <rf@opensource.cirrus.com>
Date: Thu, 3 Jul 2025 11:25:21 +0100
Subject: [PATCH 1138/1334] ASoC: cs35l56: probe() should fail if the device ID
 is not recognized

Return an error from driver probe if the DEVID read from the chip is not
one supported by this driver.

In cs35l56_hw_init() there is a check for valid DEVID, but the invalid
case was returning the value of ret. At this point in the code ret == 0
so the caller would think that cs35l56_hw_init() was successful.

Signed-off-by: Richard Fitzgerald <rf@opensource.cirrus.com>
Fixes: 84851aa055c8 ("ASoC: cs35l56: Move part of cs35l56_init() to shared library")
Link: https://patch.msgid.link/20250703102521.54204-1-rf@opensource.cirrus.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/cs35l56-shared.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/soc/codecs/cs35l56-shared.c b/sound/soc/codecs/cs35l56-shared.c
index d0831d609584..ba653f6ccfae 100644
--- a/sound/soc/codecs/cs35l56-shared.c
+++ b/sound/soc/codecs/cs35l56-shared.c
@@ -980,7 +980,7 @@ int cs35l56_hw_init(struct cs35l56_base *cs35l56_base)
 		break;
 	default:
 		dev_err(cs35l56_base->dev, "Unknown device %x\n", devid);
-		return ret;
+		return -ENODEV;
 	}
 
 	cs35l56_base->type = devid & 0xFF;

From c9764fd88bc744592b0604ccb6b6fc1a5f76b4e3 Mon Sep 17 00:00:00 2001
From: Manivannan Sadhasivam <mani@kernel.org>
Date: Thu, 3 Jul 2025 16:05:49 +0530
Subject: [PATCH 1139/1334] regulator: gpio: Fix the out-of-bounds access to
 drvdata::gpiods

drvdata::gpiods is supposed to hold an array of 'gpio_desc' pointers. But
the memory is allocated for only one pointer. This will lead to
out-of-bounds access later in the code if 'config::ngpios' is > 1. So
fix the code to allocate enough memory to hold 'config::ngpios' of GPIO
descriptors.

While at it, also move the check for memory allocation failure to be below
the allocation to make it more readable.

Cc: stable@vger.kernel.org # 5.0
Fixes: d6cd33ad7102 ("regulator: gpio: Convert to use descriptors")
Signed-off-by: Manivannan Sadhasivam <mani@kernel.org>
Link: https://patch.msgid.link/20250703103549.16558-1-mani@kernel.org
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/regulator/gpio-regulator.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/regulator/gpio-regulator.c b/drivers/regulator/gpio-regulator.c
index 75bd53445ba7..6351ceefdb3e 100644
--- a/drivers/regulator/gpio-regulator.c
+++ b/drivers/regulator/gpio-regulator.c
@@ -260,8 +260,10 @@ static int gpio_regulator_probe(struct platform_device *pdev)
 		return -ENOMEM;
 	}
 
-	drvdata->gpiods = devm_kzalloc(dev, sizeof(struct gpio_desc *),
-				       GFP_KERNEL);
+	drvdata->gpiods = devm_kcalloc(dev, config->ngpios,
+				       sizeof(struct gpio_desc *), GFP_KERNEL);
+	if (!drvdata->gpiods)
+		return -ENOMEM;
 
 	if (config->input_supply) {
 		drvdata->desc.supply_name = devm_kstrdup(&pdev->dev,
@@ -274,8 +276,6 @@ static int gpio_regulator_probe(struct platform_device *pdev)
 		}
 	}
 
-	if (!drvdata->gpiods)
-		return -ENOMEM;
 	for (i = 0; i < config->ngpios; i++) {
 		drvdata->gpiods[i] = devm_gpiod_get_index(dev,
 							  NULL,

From d008fc65ebbc7d0f36c5a90c8b1ef117c295d8d8 Mon Sep 17 00:00:00 2001
From: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Date: Fri, 13 Jun 2025 16:11:29 -0700
Subject: [PATCH 1140/1334] drm/xe: Extend WA 14018094691 to BMG

This WA is applicable to BMG as well.

Note that this is a GSC WA and we don't load the GSC on BMG, so
extending the WA to BMG won't do anything right now. However, it helps
future-proof the driver so that if we ever turn the GSC on we won't have
to remember to extend this WA.

v2: don't use VERSION_RANGE from 2001 to 2004 (Matt)

Signed-off-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Matt Roper <matthew.d.roper@intel.com>
Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
Link: https://lore.kernel.org/r/20250613231128.1261815-2-daniele.ceraolospurio@intel.com
(cherry picked from commit 1a5ce0c5b95b0624ebd44f574b98003a466973be)
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
---
 drivers/gpu/drm/xe/xe_wa_oob.rules | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/xe/xe_wa_oob.rules b/drivers/gpu/drm/xe/xe_wa_oob.rules
index 320766f6c5df..69c1d7fc695e 100644
--- a/drivers/gpu/drm/xe/xe_wa_oob.rules
+++ b/drivers/gpu/drm/xe/xe_wa_oob.rules
@@ -21,7 +21,8 @@
 		GRAPHICS_VERSION_RANGE(1270, 1274)
 		MEDIA_VERSION(1300)
 		PLATFORM(DG2)
-14018094691	GRAPHICS_VERSION(2004)
+14018094691	GRAPHICS_VERSION_RANGE(2001, 2002)
+		GRAPHICS_VERSION(2004)
 14019882105	GRAPHICS_VERSION(2004), GRAPHICS_STEP(A0, B0)
 18024947630	GRAPHICS_VERSION(2001)
 		GRAPHICS_VERSION(2004)

From 5459e16b215c18529782e7746992653f00de0779 Mon Sep 17 00:00:00 2001
From: Matthew Brost <matthew.brost@intel.com>
Date: Tue, 24 Jun 2025 10:41:03 -0700
Subject: [PATCH 1141/1334] drm/xe: Do not wedge device on killed exec queues

When a user closes an exec queue or interrupts an app with Ctrl-C,
this does not warrant wedging the device in mode 2.

Avoid this by skipping the wedge check for killed exec queues in
the TDR and LR exec queue cleanup worker.

Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://lore.kernel.org/r/20250624174103.2707941-1-matthew.brost@intel.com
(cherry picked from commit 5a2f117a80c207372513ca8964eeb178874f4990)
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
---
 drivers/gpu/drm/xe/xe_guc_submit.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c
index 9567f6700cf2..2ac87ff4a057 100644
--- a/drivers/gpu/drm/xe/xe_guc_submit.c
+++ b/drivers/gpu/drm/xe/xe_guc_submit.c
@@ -891,12 +891,13 @@ static void xe_guc_exec_queue_lr_cleanup(struct work_struct *w)
 	struct xe_exec_queue *q = ge->q;
 	struct xe_guc *guc = exec_queue_to_guc(q);
 	struct xe_gpu_scheduler *sched = &ge->sched;
-	bool wedged;
+	bool wedged = false;
 
 	xe_gt_assert(guc_to_gt(guc), xe_exec_queue_is_lr(q));
 	trace_xe_exec_queue_lr_cleanup(q);
 
-	wedged = guc_submit_hint_wedged(exec_queue_to_guc(q));
+	if (!exec_queue_killed(q))
+		wedged = guc_submit_hint_wedged(exec_queue_to_guc(q));
 
 	/* Kill the run_job / process_msg entry points */
 	xe_sched_submission_stop(sched);
@@ -1070,7 +1071,7 @@ guc_exec_queue_timedout_job(struct drm_sched_job *drm_job)
 	int err = -ETIME;
 	pid_t pid = -1;
 	int i = 0;
-	bool wedged, skip_timeout_check;
+	bool wedged = false, skip_timeout_check;
 
 	/*
 	 * TDR has fired before free job worker. Common if exec queue
@@ -1116,7 +1117,8 @@ guc_exec_queue_timedout_job(struct drm_sched_job *drm_job)
 	 * doesn't work for SRIOV. For now assuming timeouts in wedged mode are
 	 * genuine timeouts.
 	 */
-	wedged = guc_submit_hint_wedged(exec_queue_to_guc(q));
+	if (!exec_queue_killed(q))
+		wedged = guc_submit_hint_wedged(exec_queue_to_guc(q));
 
 	/* Engine state now stable, disable scheduling to check timestamp */
 	if (!wedged && exec_queue_registered(q)) {

From ef9675b0ef030d135413e8638989f3a7d1f3217a Mon Sep 17 00:00:00 2001
From: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Date: Fri, 27 Jun 2025 12:31:33 -0400
Subject: [PATCH 1142/1334] Bluetooth: hci_sync: Fix not disabling advertising
 instance

As the code comments on hci_setup_ext_adv_instance_sync suggests the
advertising instance needs to be disabled in order to update its
parameters, but it was wrongly checking that !adv->pending.

Fixes: cba6b758711c ("Bluetooth: hci_sync: Make use of hci_cmd_sync_queue set 2")
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/hci_sync.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c
index 77b3691f3423..0066627c05eb 100644
--- a/net/bluetooth/hci_sync.c
+++ b/net/bluetooth/hci_sync.c
@@ -1345,7 +1345,7 @@ int hci_setup_ext_adv_instance_sync(struct hci_dev *hdev, u8 instance)
 	 * Command Disallowed error, so we must first disable the
 	 * instance if it is active.
 	 */
-	if (adv && !adv->pending) {
+	if (adv) {
 		err = hci_disable_ext_adv_instance_sync(hdev, instance);
 		if (err)
 			return err;

From 59710a26a289ad4e7ef227d22063e964930928b0 Mon Sep 17 00:00:00 2001
From: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Date: Mon, 30 Jun 2025 15:37:46 -0400
Subject: [PATCH 1143/1334] Bluetooth: hci_core: Remove check of BDADDR_ANY in
 hci_conn_hash_lookup_big_state

The check for destination to be BDADDR_ANY is no longer necessary with
the introduction of BIS_LINK.

Fixes: 23205562ffc8 ("Bluetooth: separate CIS_LINK and BIS_LINK link types")
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 include/net/bluetooth/hci_core.h | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 9fc8f544e20e..0da011fc8146 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -1350,8 +1350,7 @@ hci_conn_hash_lookup_big_state(struct hci_dev *hdev, __u8 handle,  __u16 state)
 	rcu_read_lock();
 
 	list_for_each_entry_rcu(c, &h->list, list) {
-		if (c->type != BIS_LINK || bacmp(&c->dst, BDADDR_ANY) ||
-		    c->state != state)
+		if (c->type != BIS_LINK || c->state != state)
 			continue;
 
 		if (handle == c->iso_qos.bcast.big) {

From 314d30b1508682e27c8a324096262c66f23455d9 Mon Sep 17 00:00:00 2001
From: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Date: Thu, 3 Jul 2025 09:45:08 -0400
Subject: [PATCH 1144/1334] Bluetooth: hci_sync: Fix attempting to send
 HCI_Disconnect to BIS handle

BIS/PA connections do have their own cleanup proceedure which are
performed by hci_conn_cleanup/bis_cleanup.

Fixes: 23205562ffc8 ("Bluetooth: separate CIS_LINK and BIS_LINK link types")
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/hci_sync.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c
index 0066627c05eb..5f178db8d40d 100644
--- a/net/bluetooth/hci_sync.c
+++ b/net/bluetooth/hci_sync.c
@@ -5493,7 +5493,7 @@ static int hci_disconnect_sync(struct hci_dev *hdev, struct hci_conn *conn,
 {
 	struct hci_cp_disconnect cp;
 
-	if (test_bit(HCI_CONN_BIG_CREATED, &conn->flags)) {
+	if (conn->type == BIS_LINK) {
 		/* This is a BIS connection, hci_conn_del will
 		 * do the necessary cleanup.
 		 */

From c7349772c268ec3c91d83cbfbbcf63f1bd7c256c Mon Sep 17 00:00:00 2001
From: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Date: Fri, 27 Jun 2025 11:19:02 -0400
Subject: [PATCH 1145/1334] Bluetooth: hci_event: Fix not marking Broadcast
 Sink BIS as connected

Upon receiving HCI_EVT_LE_BIG_SYNC_ESTABLISHED with status 0x00
(success) the corresponding BIS hci_conn state shall be set to
BT_CONNECTED otherwise they will be left with BT_OPEN which is invalid
at that point, also create the debugfs and sysfs entries following the
same logic as the likes of Broadcast Source BIS and CIS connections.

Fixes: f777d8827817 ("Bluetooth: ISO: Notify user space about failed bis connections")
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/hci_event.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 4d5ace9d245d..992131f88a45 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -6966,7 +6966,10 @@ static void hci_le_big_sync_established_evt(struct hci_dev *hdev, void *data,
 		bis->iso_qos.bcast.in.sdu = le16_to_cpu(ev->max_pdu);
 
 		if (!ev->status) {
+			bis->state = BT_CONNECTED;
 			set_bit(HCI_CONN_BIG_SYNC, &bis->flags);
+			hci_debugfs_create_conn(bis);
+			hci_conn_add_sysfs(bis);
 			hci_iso_setup_path(bis);
 		}
 	}

From 68279380266a5fa70e664de754503338e2ec3f43 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@kernel.org>
Date: Thu, 3 Jul 2025 10:23:16 -0700
Subject: [PATCH 1146/1334] crypto: s390/sha - Fix uninitialized variable in
 SHA-1 and SHA-2

Commit 88c02b3f79a6 ("s390/sha3: Support sha3 performance enhancements")
added the field s390_sha_ctx::first_message_part and made it be used by
s390_sha_update() (now s390_sha_update_blocks()).  At the time,
s390_sha_update() was used by all the s390 SHA-1, SHA-2, and SHA-3
algorithms.  However, only the initialization functions for SHA-3 were
updated, leaving SHA-1 and SHA-2 using first_message_part uninitialized.

This could cause e.g. the function code CPACF_KIMD_SHA_512 |
CPACF_KIMD_NIP to be used instead of just CPACF_KIMD_SHA_512.  This
apparently was harmless, as the SHA-1 and SHA-2 function codes ignore
CPACF_KIMD_NIP; it is recognized only by the SHA-3 function codes
(https://lore.kernel.org/r/73477fe9-a1dc-4e38-98a6-eba9921e8afa@linux.ibm.com/).
Therefore, this bug was found only when first_message_part was later
converted to a boolean and UBSAN detected its uninitialized use.
Regardless, let's fix this by just initializing to zero.

Note: in 6.16, we need to patch SHA-1, SHA-384, and SHA-512.  In 6.15
and earlier, we'll also need to patch SHA-224 and SHA-256, as they
hadn't yet been librarified (which incidentally fixed this bug).

Fixes: 88c02b3f79a6 ("s390/sha3: Support sha3 performance enhancements")
Cc: stable@vger.kernel.org
Reported-by: Ingo Franzki <ifranzki@linux.ibm.com>
Closes: https://lore.kernel.org/r/12740696-595c-4604-873e-aefe8b405fbf@linux.ibm.com
Acked-by: Heiko Carstens <hca@linux.ibm.com>
Link: https://lore.kernel.org/r/20250703172316.7914-1-ebiggers@kernel.org
Signed-off-by: Eric Biggers <ebiggers@kernel.org>
---
 arch/s390/crypto/sha1_s390.c   | 2 ++
 arch/s390/crypto/sha512_s390.c | 3 +++
 2 files changed, 5 insertions(+)

diff --git a/arch/s390/crypto/sha1_s390.c b/arch/s390/crypto/sha1_s390.c
index d229cbd2ba22..9b0d55be1239 100644
--- a/arch/s390/crypto/sha1_s390.c
+++ b/arch/s390/crypto/sha1_s390.c
@@ -38,6 +38,7 @@ static int s390_sha1_init(struct shash_desc *desc)
 	sctx->state[4] = SHA1_H4;
 	sctx->count = 0;
 	sctx->func = CPACF_KIMD_SHA_1;
+	sctx->first_message_part = 0;
 
 	return 0;
 }
@@ -60,6 +61,7 @@ static int s390_sha1_import(struct shash_desc *desc, const void *in)
 	sctx->count = ictx->count;
 	memcpy(sctx->state, ictx->state, sizeof(ictx->state));
 	sctx->func = CPACF_KIMD_SHA_1;
+	sctx->first_message_part = 0;
 	return 0;
 }
 
diff --git a/arch/s390/crypto/sha512_s390.c b/arch/s390/crypto/sha512_s390.c
index 33711a29618c..6cbbf5e8555f 100644
--- a/arch/s390/crypto/sha512_s390.c
+++ b/arch/s390/crypto/sha512_s390.c
@@ -32,6 +32,7 @@ static int sha512_init(struct shash_desc *desc)
 	ctx->count = 0;
 	ctx->sha512.count_hi = 0;
 	ctx->func = CPACF_KIMD_SHA_512;
+	ctx->first_message_part = 0;
 
 	return 0;
 }
@@ -57,6 +58,7 @@ static int sha512_import(struct shash_desc *desc, const void *in)
 
 	memcpy(sctx->state, ictx->state, sizeof(ictx->state));
 	sctx->func = CPACF_KIMD_SHA_512;
+	sctx->first_message_part = 0;
 	return 0;
 }
 
@@ -97,6 +99,7 @@ static int sha384_init(struct shash_desc *desc)
 	ctx->count = 0;
 	ctx->sha512.count_hi = 0;
 	ctx->func = CPACF_KIMD_SHA_512;
+	ctx->first_message_part = 0;
 
 	return 0;
 }

From 78f88067d5c56d9aed69f27e238742841461cf67 Mon Sep 17 00:00:00 2001
From: Aaron Thompson <dev@aaront.org>
Date: Thu, 3 Jul 2025 21:19:49 +0000
Subject: [PATCH 1147/1334] drm/nouveau: Do not fail module init on debugfs
 errors

If CONFIG_DEBUG_FS is enabled, nouveau_drm_init() returns an error if it
fails to create the "nouveau" directory in debugfs. One case where that
will happen is when debugfs access is restricted by
CONFIG_DEBUG_FS_ALLOW_NONE or by the boot parameter debugfs=off, which
cause the debugfs APIs to return -EPERM.

So just ignore errors from debugfs. Note that nouveau_debugfs_root may
be an error now, but that is a standard pattern for debugfs. From
include/linux/debugfs.h:

"NOTE: it's expected that most callers should _ignore_ the errors
returned by this function. Other debugfs functions handle the fact that
the "dentry" passed to them could be an error and they don't crash in
that case. Drivers should generally work fine even if debugfs fails to
init anyway."

Fixes: 97118a1816d2 ("drm/nouveau: create module debugfs root")
Cc: stable@vger.kernel.org
Signed-off-by: Aaron Thompson <dev@aaront.org>
Acked-by: Timur Tabi <ttabi@nvidia.com>
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
Link: https://lore.kernel.org/r/20250703211949.9916-1-dev@aaront.org
---
 drivers/gpu/drm/nouveau/nouveau_debugfs.c | 6 +-----
 drivers/gpu/drm/nouveau/nouveau_debugfs.h | 5 ++---
 drivers/gpu/drm/nouveau/nouveau_drm.c     | 4 +---
 3 files changed, 4 insertions(+), 11 deletions(-)

diff --git a/drivers/gpu/drm/nouveau/nouveau_debugfs.c b/drivers/gpu/drm/nouveau/nouveau_debugfs.c
index 200e65a7cefc..c7869a639bef 100644
--- a/drivers/gpu/drm/nouveau/nouveau_debugfs.c
+++ b/drivers/gpu/drm/nouveau/nouveau_debugfs.c
@@ -314,14 +314,10 @@ nouveau_debugfs_fini(struct nouveau_drm *drm)
 	drm->debugfs = NULL;
 }
 
-int
+void
 nouveau_module_debugfs_init(void)
 {
 	nouveau_debugfs_root = debugfs_create_dir("nouveau", NULL);
-	if (IS_ERR(nouveau_debugfs_root))
-		return PTR_ERR(nouveau_debugfs_root);
-
-	return 0;
 }
 
 void
diff --git a/drivers/gpu/drm/nouveau/nouveau_debugfs.h b/drivers/gpu/drm/nouveau/nouveau_debugfs.h
index b7617b344ee2..d05ed0e641c4 100644
--- a/drivers/gpu/drm/nouveau/nouveau_debugfs.h
+++ b/drivers/gpu/drm/nouveau/nouveau_debugfs.h
@@ -24,7 +24,7 @@ extern void nouveau_debugfs_fini(struct nouveau_drm *);
 
 extern struct dentry *nouveau_debugfs_root;
 
-int  nouveau_module_debugfs_init(void);
+void nouveau_module_debugfs_init(void);
 void nouveau_module_debugfs_fini(void);
 #else
 static inline void
@@ -42,10 +42,9 @@ nouveau_debugfs_fini(struct nouveau_drm *drm)
 {
 }
 
-static inline int
+static inline void
 nouveau_module_debugfs_init(void)
 {
-	return 0;
 }
 
 static inline void
diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c
index 0c82a63cd49d..1527b801f013 100644
--- a/drivers/gpu/drm/nouveau/nouveau_drm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_drm.c
@@ -1461,9 +1461,7 @@ nouveau_drm_init(void)
 	if (!nouveau_modeset)
 		return 0;
 
-	ret = nouveau_module_debugfs_init();
-	if (ret)
-		return ret;
+	nouveau_module_debugfs_init();
 
 #ifdef CONFIG_NOUVEAU_PLATFORM_DRIVER
 	platform_driver_register(&nouveau_platform_driver);

From e79d0ba605d54dd47f3d8a487d00f264b896966c Mon Sep 17 00:00:00 2001
From: Dave Airlie <airlied@redhat.com>
Date: Thu, 3 Jul 2025 09:27:07 +1000
Subject: [PATCH 1148/1334] nouveau/gsp: add a 50ms delay between fbsr and
 driver unload rpcs

This fixes a bunch of command hangs after runtime suspend/resume.

This fixes a regression caused by code movement in the commit below,
the commit seems to just change timings enough to cause this to happen
now, and adding the sleep seems to avoid it.

I've spent some time trying to root cause it to no great avail,
it seems like a bug on the firmware side, but it could be a bug
in our rpc handling that I can't find.

Either way, we should land the workaround to fix the problem,
while we continue to work out the root cause.

Signed-off-by: Dave Airlie <airlied@redhat.com>
Cc: Ben Skeggs <bskeggs@nvidia.com>
Cc: Danilo Krummrich <dakr@kernel.org>
Fixes: c21b039715ce ("drm/nouveau/gsp: add hals for fbsr.suspend/resume()")
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
Link: https://lore.kernel.org/r/20250702232707.175679-1-airlied@gmail.com
---
 drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/gsp.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/gsp.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/gsp.c
index baf42339f93e..23f80e167705 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/gsp.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/gsp.c
@@ -1744,6 +1744,13 @@ r535_gsp_fini(struct nvkm_gsp *gsp, bool suspend)
 			nvkm_gsp_sg_free(gsp->subdev.device, &gsp->sr.sgt);
 			return ret;
 		}
+
+		/*
+		 * TODO: Debug the GSP firmware / RPC handling to find out why
+		 * without this Turing (but none of the other architectures)
+		 * ends up resetting all channels after resume.
+		 */
+		msleep(50);
 	}
 
 	ret = r535_gsp_rpc_unloading_guest_driver(gsp, suspend);

From 8ff4fb276e2384a87ae7f65f3c28e1e139dbb3fe Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Fri, 27 Jun 2025 10:01:46 -0500
Subject: [PATCH 1149/1334] pinctrl: amd: Clear GPIO debounce for suspend

soc-button-array hardcodes a debounce value by means of gpio_keys
which uses pinctrl-amd as a backend to program debounce for a GPIO.

This hardcoded value doesn't match what the firmware intended to be
programmed in _AEI. The hardcoded debounce leads to problems waking
from suspend. There isn't appetite to conditionalize the behavior in
soc-button-array or gpio-keys so clear it when the system suspends to
avoid problems with being able to resume.

Cc: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Cc: Hans de Goede <hansg@kernel.org>
Fixes: 5c4fa2a6da7fb ("Input: soc_button_array - debounce the buttons")
Link: https://lore.kernel.org/linux-input/mkgtrb5gt7miyg6kvqdlbu4nj3elym6ijudobpdi26gp4xxay5@rsa6ytrjvj2q/
Link: https://lore.kernel.org/linux-input/20250625215813.3477840-1-superm1@kernel.org/
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Reviewed-by: Hans de Goede <hansg@kernel.org>
Link: https://lore.kernel.org/20250627150155.3311574-1-superm1@kernel.org
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/pinctrl-amd.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/drivers/pinctrl/pinctrl-amd.c b/drivers/pinctrl/pinctrl-amd.c
index 5cf3db6d78b7..b3f0d02aeeb3 100644
--- a/drivers/pinctrl/pinctrl-amd.c
+++ b/drivers/pinctrl/pinctrl-amd.c
@@ -979,6 +979,17 @@ static int amd_gpio_suspend_hibernate_common(struct device *dev, bool is_suspend
 				  pin, is_suspend ? "suspend" : "hibernate");
 		}
 
+		/*
+		 * debounce enabled over suspend has shown issues with a GPIO
+		 * being unable to wake the system, as we're only interested in
+		 * the actual wakeup event, clear it.
+		 */
+		if (gpio_dev->saved_regs[i] & (DB_CNTRl_MASK << DB_CNTRL_OFF)) {
+			amd_gpio_set_debounce(gpio_dev, pin, 0);
+			pm_pr_dbg("Clearing debounce for GPIO #%d during %s.\n",
+				  pin, is_suspend ? "suspend" : "hibernate");
+		}
+
 		raw_spin_unlock_irqrestore(&gpio_dev->lock, flags);
 	}
 

From 2e9fdbe5ec7a65b66da9c202cac621a3a366fde3 Mon Sep 17 00:00:00 2001
From: Danilo Krummrich <dakr@kernel.org>
Date: Sun, 29 Jun 2025 17:37:42 +0200
Subject: [PATCH 1150/1334] rust: drm: device: drop_in_place() the drm::Device
 in release()

In drm::Device::new() we allocate with __drm_dev_alloc() and return an
ARef<drm::Device>.

When the reference count of the drm::Device falls to zero, the C code
automatically calls drm_dev_release(), which eventually frees the memory
allocated in drm::Device::new().

However, due to that, drm::Device::drop() is never called. As a result
the destructor of the user's private data, i.e. drm::Device::data is
never called. Hence, fix this by calling drop_in_place() from the DRM
device's release callback.

Fixes: 1e4b8896c0f3 ("rust: drm: add device abstraction")
Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
Link: https://lore.kernel.org/r/20250629153747.72536-1-dakr@kernel.org
---
 rust/kernel/drm/device.rs | 12 +++++++++++-
 1 file changed, 11 insertions(+), 1 deletion(-)

diff --git a/rust/kernel/drm/device.rs b/rust/kernel/drm/device.rs
index 624d7a4c83ea..14c1aa402951 100644
--- a/rust/kernel/drm/device.rs
+++ b/rust/kernel/drm/device.rs
@@ -66,7 +66,7 @@ impl<T: drm::Driver> Device<T> {
         open: Some(drm::File::<T::File>::open_callback),
         postclose: Some(drm::File::<T::File>::postclose_callback),
         unload: None,
-        release: None,
+        release: Some(Self::release),
         master_set: None,
         master_drop: None,
         debugfs_init: None,
@@ -162,6 +162,16 @@ impl<T: drm::Driver> Device<T> {
         // SAFETY: `ptr` is valid by the safety requirements of this function.
         unsafe { &*ptr.cast() }
     }
+
+    extern "C" fn release(ptr: *mut bindings::drm_device) {
+        // SAFETY: `ptr` is a valid pointer to a `struct drm_device` and embedded in `Self`.
+        let this = unsafe { Self::from_drm_device(ptr) };
+
+        // SAFETY:
+        // - When `release` runs it is guaranteed that there is no further access to `this`.
+        // - `this` is valid for dropping.
+        unsafe { core::ptr::drop_in_place(this) };
+    }
 }
 
 impl<T: drm::Driver> Deref for Device<T> {

From 266b5d02e14f3a0e07414e11f239397de0577a1d Mon Sep 17 00:00:00 2001
From: Wang Zhaolong <wangzhaolong@huaweicloud.com>
Date: Thu, 3 Jul 2025 21:29:52 +0800
Subject: [PATCH 1151/1334] smb: client: fix race condition in negotiate
 timeout by using more precise timing

When the SMB server reboots and the client immediately accesses the mount
point, a race condition can occur that causes operations to fail with
"Host is down" error.

Reproduction steps:
  # Mount SMB share
  mount -t cifs //192.168.245.109/TEST /mnt/ -o xxxx
  ls /mnt

  # Reboot server
  ssh root@192.168.245.109 reboot
  ssh root@192.168.245.109 /path/to/cifs_server_setup.sh
  ssh root@192.168.245.109 systemctl stop firewalld

  # Immediate access fails
  ls /mnt
  ls: cannot access '/mnt': Host is down

  # But works if there is a delay

The issue is caused by a race condition between negotiate and reconnect.
The 20-second negotiate timeout mechanism can interfere with the normal
recovery process when both are triggered simultaneously.

  ls                              cifsd
---------------------------------------------------
 cifs_getattr
 cifs_revalidate_dentry
 cifs_get_inode_info
 cifs_get_fattr
 smb2_query_path_info
 smb2_compound_op
 SMB2_open_init
 smb2_reconnect
 cifs_negotiate_protocol
  smb2_negotiate
   cifs_send_recv
    smb_send_rqst
    wait_for_response
                            cifs_demultiplex_thread
                              cifs_read_from_socket
                              cifs_readv_from_socket
                                server_unresponsive
                                cifs_reconnect
                                  __cifs_reconnect
                                  cifs_abort_connection
                                    mid->mid_state = MID_RETRY_NEEDED
                                    cifs_wake_up_task
    cifs_sync_mid_result
     // case MID_RETRY_NEEDED
     rc = -EAGAIN;
   // In smb2_negotiate()
   rc = -EHOSTDOWN;

The server_unresponsive() timeout triggers cifs_reconnect(), which aborts
ongoing mid requests and causes the ls command to receive -EAGAIN, leading
to -EHOSTDOWN.

Fix this by introducing a dedicated `neg_start` field to
precisely tracks when the negotiate process begins. The timeout check
now uses this accurate timestamp instead of `lstrp`, ensuring that:

1. Timeout is only triggered after negotiate has actually run for 20s
2. The mechanism doesn't interfere with concurrent recovery processes
3. Uninitialized timestamps (value 0) don't trigger false timeouts

Fixes: 7ccc1465465d ("smb: client: fix hang in wait_for_response() for negproto")
Signed-off-by: Wang Zhaolong <wangzhaolong@huaweicloud.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/cifsglob.h | 1 +
 fs/smb/client/connect.c  | 7 ++++---
 2 files changed, 5 insertions(+), 3 deletions(-)

diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h
index fdd95e5100cd..89160bc34d35 100644
--- a/fs/smb/client/cifsglob.h
+++ b/fs/smb/client/cifsglob.h
@@ -777,6 +777,7 @@ struct TCP_Server_Info {
 	__le32 session_key_id; /* retrieved from negotiate response and send in session setup request */
 	struct session_key session_key;
 	unsigned long lstrp; /* when we got last response from this server */
+	unsigned long neg_start; /* when negotiate started (jiffies) */
 	struct cifs_secmech secmech; /* crypto sec mech functs, descriptors */
 #define	CIFS_NEGFLAVOR_UNENCAP	1	/* wct == 17, but no ext_sec */
 #define	CIFS_NEGFLAVOR_EXTENDED	2	/* wct == 17, ext_sec bit set */
diff --git a/fs/smb/client/connect.c b/fs/smb/client/connect.c
index 484b677143fd..205f547ca49e 100644
--- a/fs/smb/client/connect.c
+++ b/fs/smb/client/connect.c
@@ -679,12 +679,12 @@ server_unresponsive(struct TCP_Server_Info *server)
 	/*
 	 * If we're in the process of mounting a share or reconnecting a session
 	 * and the server abruptly shut down (e.g. socket wasn't closed, packet
-	 * had been ACK'ed but no SMB response), don't wait longer than 20s to
-	 * negotiate protocol.
+	 * had been ACK'ed but no SMB response), don't wait longer than 20s from
+	 * when negotiate actually started.
 	 */
 	spin_lock(&server->srv_lock);
 	if (server->tcpStatus == CifsInNegotiate &&
-	    time_after(jiffies, server->lstrp + 20 * HZ)) {
+	    time_after(jiffies, server->neg_start + 20 * HZ)) {
 		spin_unlock(&server->srv_lock);
 		cifs_reconnect(server, false);
 		return true;
@@ -4209,6 +4209,7 @@ retry:
 
 	server->lstrp = jiffies;
 	server->tcpStatus = CifsInNegotiate;
+	server->neg_start = jiffies;
 	spin_unlock(&server->srv_lock);
 
 	rc = server->ops->negotiate(xid, ses, server);

From 3363da82e02f1bddc54faa92ea430c6532e2cd2e Mon Sep 17 00:00:00 2001
From: Paulo Alcantara <pc@manguebit.org>
Date: Thu, 3 Jul 2025 17:57:19 -0300
Subject: [PATCH 1152/1334] smb: client: fix native SMB symlink traversal

We've seen customers having shares mounted in paths like /??/C:/ or
/??/UNC/foo.example.com/share in order to get their native SMB
symlinks successfully followed from different mounts.

After commit 12b466eb52d9 ("cifs: Fix creating and resolving absolute NT-style symlinks"),
the client would then convert absolute paths from "/??/C:/" to "/mnt/c/"
by default.  The absolute paths would vary depending on the value of
symlinkroot= mount option.

Fix this by restoring old behavior of not trying to convert absolute
paths by default.  Only do this if symlinkroot= was _explicitly_ set.

Before patch:

  $ mount.cifs //w22-fs0/test2 /mnt/1 -o vers=3.1.1,username=xxx,password=yyy
  $ ls -l /mnt/1/symlink2
  lrwxr-xr-x 1 root root 15 Jun 20 14:22 /mnt/1/symlink2 -> /mnt/c/testfile
  $ mkdir -p /??/C:; echo foo > //??/C:/testfile
  $ cat /mnt/1/symlink2
  cat: /mnt/1/symlink2: No such file or directory

After patch:

  $ mount.cifs //w22-fs0/test2 /mnt/1 -o vers=3.1.1,username=xxx,password=yyy
  $ ls -l /mnt/1/symlink2
  lrwxr-xr-x 1 root root 15 Jun 20 14:22 /mnt/1/symlink2 -> '/??/C:/testfile'
  $ mkdir -p /??/C:; echo foo > //??/C:/testfile
  $ cat /mnt/1/symlink2
  foo

Cc: linux-cifs@vger.kernel.org
Reported-by: Pierguido Lambri <plambri@redhat.com>
Cc: David Howells <dhowells@redhat.com>
Cc: Stefan Metzmacher <metze@samba.org>
Fixes: 12b466eb52d9 ("cifs: Fix creating and resolving absolute NT-style symlinks")
Signed-off-by: Paulo Alcantara (Red Hat) <pc@manguebit.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/fs_context.c | 17 +++++++----------
 fs/smb/client/reparse.c    | 22 +++++++++++++---------
 2 files changed, 20 insertions(+), 19 deletions(-)

diff --git a/fs/smb/client/fs_context.c b/fs/smb/client/fs_context.c
index a634a34d4086..59ccc2229ab3 100644
--- a/fs/smb/client/fs_context.c
+++ b/fs/smb/client/fs_context.c
@@ -1824,10 +1824,14 @@ static int smb3_fs_context_parse_param(struct fs_context *fc,
 			cifs_errorf(fc, "symlinkroot mount options must be absolute path\n");
 			goto cifs_parse_mount_err;
 		}
-		kfree(ctx->symlinkroot);
-		ctx->symlinkroot = kstrdup(param->string, GFP_KERNEL);
-		if (!ctx->symlinkroot)
+		if (strnlen(param->string, PATH_MAX) == PATH_MAX) {
+			cifs_errorf(fc, "symlinkroot path too long (max path length: %u)\n",
+				    PATH_MAX - 1);
 			goto cifs_parse_mount_err;
+		}
+		kfree(ctx->symlinkroot);
+		ctx->symlinkroot = param->string;
+		param->string = NULL;
 		break;
 	}
 	/* case Opt_ignore: - is ignored as expected ... */
@@ -1837,13 +1841,6 @@ static int smb3_fs_context_parse_param(struct fs_context *fc,
 		goto cifs_parse_mount_err;
 	}
 
-	/*
-	 * By default resolve all native absolute symlinks relative to "/mnt/".
-	 * Same default has drvfs driver running in WSL for resolving SMB shares.
-	 */
-	if (!ctx->symlinkroot)
-		ctx->symlinkroot = kstrdup("/mnt/", GFP_KERNEL);
-
 	return 0;
 
  cifs_parse_mount_err:
diff --git a/fs/smb/client/reparse.c b/fs/smb/client/reparse.c
index 1c40e42e4d89..5fa29a97ac15 100644
--- a/fs/smb/client/reparse.c
+++ b/fs/smb/client/reparse.c
@@ -57,6 +57,7 @@ static int create_native_symlink(const unsigned int xid, struct inode *inode,
 	struct reparse_symlink_data_buffer *buf = NULL;
 	struct cifs_open_info_data data = {};
 	struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
+	const char *symroot = cifs_sb->ctx->symlinkroot;
 	struct inode *new;
 	struct kvec iov;
 	__le16 *path = NULL;
@@ -82,7 +83,8 @@ static int create_native_symlink(const unsigned int xid, struct inode *inode,
 		.symlink_target = symlink_target,
 	};
 
-	if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIX_PATHS) && symname[0] == '/') {
+	if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIX_PATHS) &&
+	    symroot && symname[0] == '/') {
 		/*
 		 * This is a request to create an absolute symlink on the server
 		 * which does not support POSIX paths, and expects symlink in
@@ -92,7 +94,7 @@ static int create_native_symlink(const unsigned int xid, struct inode *inode,
 		 * ensure compatibility of this symlink stored in absolute form
 		 * on the SMB server.
 		 */
-		if (!strstarts(symname, cifs_sb->ctx->symlinkroot)) {
+		if (!strstarts(symname, symroot)) {
 			/*
 			 * If the absolute Linux symlink target path is not
 			 * inside "symlinkroot" location then there is no way
@@ -101,12 +103,12 @@ static int create_native_symlink(const unsigned int xid, struct inode *inode,
 			cifs_dbg(VFS,
 				 "absolute symlink '%s' cannot be converted to NT format "
 				 "because it is outside of symlinkroot='%s'\n",
-				 symname, cifs_sb->ctx->symlinkroot);
+				 symname, symroot);
 			rc = -EINVAL;
 			goto out;
 		}
-		len = strlen(cifs_sb->ctx->symlinkroot);
-		if (cifs_sb->ctx->symlinkroot[len-1] != '/')
+		len = strlen(symroot);
+		if (symroot[len - 1] != '/')
 			len++;
 		if (symname[len] >= 'a' && symname[len] <= 'z' &&
 		    (symname[len+1] == '/' || symname[len+1] == '\0')) {
@@ -782,6 +784,7 @@ int smb2_parse_native_symlink(char **target, const char *buf, unsigned int len,
 			      const char *full_path,
 			      struct cifs_sb_info *cifs_sb)
 {
+	const char *symroot = cifs_sb->ctx->symlinkroot;
 	char sep = CIFS_DIR_SEP(cifs_sb);
 	char *linux_target = NULL;
 	char *smb_target = NULL;
@@ -815,7 +818,8 @@ int smb2_parse_native_symlink(char **target, const char *buf, unsigned int len,
 		goto out;
 	}
 
-	if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIX_PATHS) && !relative) {
+	if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIX_PATHS) &&
+	    symroot && !relative) {
 		/*
 		 * This is an absolute symlink from the server which does not
 		 * support POSIX paths, so the symlink is in NT-style path.
@@ -907,15 +911,15 @@ globalroot:
 		}
 
 		abs_path_len = strlen(abs_path)+1;
-		symlinkroot_len = strlen(cifs_sb->ctx->symlinkroot);
-		if (cifs_sb->ctx->symlinkroot[symlinkroot_len-1] == '/')
+		symlinkroot_len = strlen(symroot);
+		if (symroot[symlinkroot_len - 1] == '/')
 			symlinkroot_len--;
 		linux_target = kmalloc(symlinkroot_len + 1 + abs_path_len, GFP_KERNEL);
 		if (!linux_target) {
 			rc = -ENOMEM;
 			goto out;
 		}
-		memcpy(linux_target, cifs_sb->ctx->symlinkroot, symlinkroot_len);
+		memcpy(linux_target, symroot, symlinkroot_len);
 		linux_target[symlinkroot_len] = '/';
 		memcpy(linux_target + symlinkroot_len + 1, abs_path, abs_path_len);
 	} else if (smb_target[0] == sep && relative) {

From b969f9614885c20f903e1d1f9445611daf161d6d Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Mon, 30 Jun 2025 02:52:13 -0400
Subject: [PATCH 1153/1334] fix proc_sys_compare() handling of in-lookup
 dentries

There's one case where ->d_compare() can be called for an in-lookup
dentry; usually that's nothing special from ->d_compare() point of
view, but... proc_sys_compare() is weird.

The thing is, /proc/sys subdirectories can look differently for
different processes.  Up to and including having the same name
resolve to different dentries - all of them hashed.

The way it's done is ->d_compare() refusing to admit a match unless
this dentry is supposed to be visible to this caller.  The information
needed to discriminate between them is stored in inode; it is set
during proc_sys_lookup() and until it's done d_splice_alias() we really
can't tell who should that dentry be visible for.

Normally there's no negative dentries in /proc/sys; we can run into
a dying dentry in RCU dcache lookup, but those can be safely rejected.

However, ->d_compare() is also called for in-lookup dentries, before
they get positive - or hashed, for that matter.  In case of match
we will wait until dentry leaves in-lookup state and repeat ->d_compare()
afterwards.  In other words, the right behaviour is to treat the
name match as sufficient for in-lookup dentries; if dentry is not
for us, we'll see that when we recheck once proc_sys_lookup() is
done with it.

While we are at it, fix the misspelled READ_ONCE and WRITE_ONCE there.

Fixes: d9171b934526 ("parallel lookups machinery, part 4 (and last)")
Reported-by: NeilBrown <neilb@brown.name>
Reviewed-by: Christian Brauner <brauner@kernel.org>
Reviewed-by: NeilBrown <neil@brown.name>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/proc/inode.c       |  2 +-
 fs/proc/proc_sysctl.c | 18 +++++++++++-------
 2 files changed, 12 insertions(+), 8 deletions(-)

diff --git a/fs/proc/inode.c b/fs/proc/inode.c
index a3eb3b740f76..3604b616311c 100644
--- a/fs/proc/inode.c
+++ b/fs/proc/inode.c
@@ -42,7 +42,7 @@ static void proc_evict_inode(struct inode *inode)
 
 	head = ei->sysctl;
 	if (head) {
-		RCU_INIT_POINTER(ei->sysctl, NULL);
+		WRITE_ONCE(ei->sysctl, NULL);
 		proc_sys_evict_inode(inode, head);
 	}
 }
diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index cc9d74a06ff0..08b78150cdde 100644
--- a/fs/proc/proc_sysctl.c
+++ b/fs/proc/proc_sysctl.c
@@ -918,17 +918,21 @@ static int proc_sys_compare(const struct dentry *dentry,
 	struct ctl_table_header *head;
 	struct inode *inode;
 
-	/* Although proc doesn't have negative dentries, rcu-walk means
-	 * that inode here can be NULL */
-	/* AV: can it, indeed? */
-	inode = d_inode_rcu(dentry);
-	if (!inode)
-		return 1;
 	if (name->len != len)
 		return 1;
 	if (memcmp(name->name, str, len))
 		return 1;
-	head = rcu_dereference(PROC_I(inode)->sysctl);
+
+	// false positive is fine here - we'll recheck anyway
+	if (d_in_lookup(dentry))
+		return 0;
+
+	inode = d_inode_rcu(dentry);
+	// we just might have run into dentry in the middle of __dentry_kill()
+	if (!inode)
+		return 1;
+
+	head = READ_ONCE(PROC_I(inode)->sysctl);
 	return !head || !sysctl_is_seen(head);
 }
 

From 4cf65845fdd09d711fc7546d60c9abe010956922 Mon Sep 17 00:00:00 2001
From: Yunshui Jiang <jiangyunshui@kylinos.cn>
Date: Thu, 3 Jul 2025 21:56:02 -0700
Subject: [PATCH 1154/1334] Input: cs40l50-vibra - fix potential NULL
 dereference in cs40l50_upload_owt()

The cs40l50_upload_owt() function allocates memory via kmalloc()
without checking for allocation failure, which could lead to a
NULL pointer dereference.

Return -ENOMEM in case allocation fails.

Signed-off-by: Yunshui Jiang <jiangyunshui@kylinos.cn>
Fixes: c38fe1bb5d21 ("Input: cs40l50 - Add support for the CS40L50 haptic driver")
Link: https://lore.kernel.org/r/20250704024010.2353841-1-jiangyunshui@kylinos.cn
Cc: stable@vger.kernel.org
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/misc/cs40l50-vibra.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/input/misc/cs40l50-vibra.c b/drivers/input/misc/cs40l50-vibra.c
index dce3b0ec8cf3..330f09123631 100644
--- a/drivers/input/misc/cs40l50-vibra.c
+++ b/drivers/input/misc/cs40l50-vibra.c
@@ -238,6 +238,8 @@ static int cs40l50_upload_owt(struct cs40l50_work *work_data)
 	header.data_words = len / sizeof(u32);
 
 	new_owt_effect_data = kmalloc(sizeof(header) + len, GFP_KERNEL);
+	if (!new_owt_effect_data)
+		return -ENOMEM;
 
 	memcpy(new_owt_effect_data, &header, sizeof(header));
 	memcpy(new_owt_effect_data + sizeof(header), work_data->custom_data, len);

From 043faef334a1f3d96ae88e1b7618bfa2b4946388 Mon Sep 17 00:00:00 2001
From: Thorsten Blum <thorsten.blum@linux.dev>
Date: Thu, 3 Jul 2025 22:06:13 +0200
Subject: [PATCH 1155/1334] ALSA: ad1816a: Fix potential NULL pointer deref in
 snd_card_ad1816a_pnp()

Use pr_warn() instead of dev_warn() when 'pdev' is NULL to avoid a
potential NULL pointer dereference.

Cc: stable@vger.kernel.org
Fixes: 20869176d7a7 ("ALSA: ad1816a: Use standard print API")
Signed-off-by: Thorsten Blum <thorsten.blum@linux.dev>
Link: https://patch.msgid.link/20250703200616.304309-2-thorsten.blum@linux.dev
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/isa/ad1816a/ad1816a.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/isa/ad1816a/ad1816a.c b/sound/isa/ad1816a/ad1816a.c
index 99006dc4777e..5c9e2d41d900 100644
--- a/sound/isa/ad1816a/ad1816a.c
+++ b/sound/isa/ad1816a/ad1816a.c
@@ -98,7 +98,7 @@ static int snd_card_ad1816a_pnp(int dev, struct pnp_card_link *card,
 	pdev = pnp_request_card_device(card, id->devs[1].id, NULL);
 	if (pdev == NULL) {
 		mpu_port[dev] = -1;
-		dev_warn(&pdev->dev, "MPU401 device busy, skipping.\n");
+		pr_warn("MPU401 device busy, skipping.\n");
 		return 0;
 	}
 

From 30e0fd3c0273dc106320081793793a424f1f1950 Mon Sep 17 00:00:00 2001
From: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Date: Thu, 3 Jul 2025 15:18:29 -0400
Subject: [PATCH 1156/1334] gpiolib: fix performance regression when using
 gpio_chip_get_multiple()

commit 74abd086d2ee ("gpiolib: sanitize the return value of
gpio_chip::get_multiple()") altered the value returned by
gc->get_multiple() in case it is positive (> 0), but failed to return
for other cases (<= 0).

This may result in the "if (gc->get)" block being executed and thus
negates the performance gain that is normally obtained by using
gc->get_multiple().

Fix by returning the result of gc->get_multiple() if it is <= 0.

Also move the "ret" variable to the scope where it is used, which as an
added bonus fixes an indentation error introduced by the aforementioned
commit.

Fixes: 74abd086d2ee ("gpiolib: sanitize the return value of gpio_chip::get_multiple()")
Cc: stable@vger.kernel.org
Signed-off-by: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Link: https://lore.kernel.org/r/20250703191829.2952986-1-hugo@hugovil.com
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
---
 drivers/gpio/gpiolib.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index fdafa0df1b43..3a3eca5b4c40 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -3297,14 +3297,15 @@ static int gpiod_get_raw_value_commit(const struct gpio_desc *desc)
 static int gpio_chip_get_multiple(struct gpio_chip *gc,
 				  unsigned long *mask, unsigned long *bits)
 {
-	int ret;
-	
 	lockdep_assert_held(&gc->gpiodev->srcu);
 
 	if (gc->get_multiple) {
+		int ret;
+
 		ret = gc->get_multiple(gc, mask, bits);
 		if (ret > 0)
 			return -EBADE;
+		return ret;
 	}
 
 	if (gc->get) {

From 5285b5ed04ab6ad40f7b654eefbccd6ae8cbf415 Mon Sep 17 00:00:00 2001
From: Milan Krstic <milan.krstic@gmail.com>
Date: Thu, 3 Jul 2025 14:30:39 +0000
Subject: [PATCH 1157/1334] pinctrl: aw9523: fix can_sleep flag for GPIO chip

The GPIO expander is connected via I2C, thus the can_sleep flag has to
be set to true. This fixes spurious "scheduling while atomic" bugs
in the kernel ringbuffer.

Signed-off-by: David Bauer <mail@david-bauer.net>
Signed-off-by: Milan Krstic <milan.krstic@gmail.com>
Link: https://lore.kernel.org/20250703143039.5809-1-milan.krstic@gmail.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/pinctrl-aw9523.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/pinctrl/pinctrl-aw9523.c b/drivers/pinctrl/pinctrl-aw9523.c
index 9bf53de20be8..04afb344e9e5 100644
--- a/drivers/pinctrl/pinctrl-aw9523.c
+++ b/drivers/pinctrl/pinctrl-aw9523.c
@@ -784,7 +784,7 @@ static int aw9523_init_gpiochip(struct aw9523 *awi, unsigned int npins)
 	gc->set_config = gpiochip_generic_config;
 	gc->parent = dev;
 	gc->owner = THIS_MODULE;
-	gc->can_sleep = false;
+	gc->can_sleep = true;
 
 	return 0;
 }

From 25b1b75bbaf96331750fb01302825069657b2ff8 Mon Sep 17 00:00:00 2001
From: Lu Baolu <baolu.lu@linux.intel.com>
Date: Sat, 28 Jun 2025 18:03:51 +0800
Subject: [PATCH 1158/1334] iommu/vt-d: Assign devtlb cache tag on ATS
 enablement

Commit <4f1492efb495> ("iommu/vt-d: Revert ATS timing change to fix boot
failure") placed the enabling of ATS in the probe_finalize callback. This
occurs after the default domain attachment, which is when the ATS cache
tag is assigned. Consequently, the device TLB cache tag is missed when the
domain is attached, leading to the device TLB not being invalidated in the
iommu_unmap paths.

Fix this by assigning the CACHE_TAG_DEVTLB cache tag when ATS is enabled.

Fixes: 4f1492efb495 ("iommu/vt-d: Revert ATS timing change to fix boot failure")
Cc: stable@vger.kernel.org
Suggested-by: Kevin Tian <kevin.tian@intel.com>
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Tested-by: Shuicheng Lin <shuicheng.lin@intel.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Link: https://lore.kernel.org/r/20250625050135.3129955-1-baolu.lu@linux.intel.com
Link: https://lore.kernel.org/r/20250628100351.3198955-2-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
---
 drivers/iommu/intel/cache.c |  5 ++---
 drivers/iommu/intel/iommu.c | 11 ++++++++++-
 drivers/iommu/intel/iommu.h |  2 ++
 3 files changed, 14 insertions(+), 4 deletions(-)

diff --git a/drivers/iommu/intel/cache.c b/drivers/iommu/intel/cache.c
index fc35cba59145..47692cbfaabd 100644
--- a/drivers/iommu/intel/cache.c
+++ b/drivers/iommu/intel/cache.c
@@ -40,9 +40,8 @@ static bool cache_tage_match(struct cache_tag *tag, u16 domain_id,
 }
 
 /* Assign a cache tag with specified type to domain. */
-static int cache_tag_assign(struct dmar_domain *domain, u16 did,
-			    struct device *dev, ioasid_t pasid,
-			    enum cache_tag_type type)
+int cache_tag_assign(struct dmar_domain *domain, u16 did, struct device *dev,
+		     ioasid_t pasid, enum cache_tag_type type)
 {
 	struct device_domain_info *info = dev_iommu_priv_get(dev);
 	struct intel_iommu *iommu = info->iommu;
diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index 7aa3932251b2..148b944143b8 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -3780,8 +3780,17 @@ static void intel_iommu_probe_finalize(struct device *dev)
 	    !pci_enable_pasid(to_pci_dev(dev), info->pasid_supported & ~1))
 		info->pasid_enabled = 1;
 
-	if (sm_supported(iommu) && !dev_is_real_dma_subdevice(dev))
+	if (sm_supported(iommu) && !dev_is_real_dma_subdevice(dev)) {
 		iommu_enable_pci_ats(info);
+		/* Assign a DEVTLB cache tag to the default domain. */
+		if (info->ats_enabled && info->domain) {
+			u16 did = domain_id_iommu(info->domain, iommu);
+
+			if (cache_tag_assign(info->domain, did, dev,
+					     IOMMU_NO_PASID, CACHE_TAG_DEVTLB))
+				iommu_disable_pci_ats(info);
+		}
+	}
 	iommu_enable_pci_pri(info);
 }
 
diff --git a/drivers/iommu/intel/iommu.h b/drivers/iommu/intel/iommu.h
index 3ddbcc603de2..2d1afab5eedc 100644
--- a/drivers/iommu/intel/iommu.h
+++ b/drivers/iommu/intel/iommu.h
@@ -1289,6 +1289,8 @@ struct cache_tag {
 	unsigned int users;
 };
 
+int cache_tag_assign(struct dmar_domain *domain, u16 did, struct device *dev,
+		     ioasid_t pasid, enum cache_tag_type type);
 int cache_tag_assign_domain(struct dmar_domain *domain,
 			    struct device *dev, ioasid_t pasid);
 void cache_tag_unassign_domain(struct dmar_domain *domain,

From fc975cfb36393db1db517fbbe366e550bcdcff14 Mon Sep 17 00:00:00 2001
From: kuyo chang <kuyo.chang@mediatek.com>
Date: Wed, 2 Jul 2025 10:12:25 +0800
Subject: [PATCH 1159/1334] sched/deadline: Fix dl_server runtime calculation
 formula

In our testing with 6.12 based kernel on a big.LITTLE system, we were
seeing instances of RT tasks being blocked from running on the LITTLE
cpus for multiple seconds of time, apparently by the dl_server. This
far exceeds the default configured 50ms per second runtime.

This is due to the fair dl_server runtime calculation being scaled
for frequency & capacity of the cpu.

Consider the following case under a Big.LITTLE architecture:
Assume the runtime is: 50,000,000 ns, and Frequency/capacity
scale-invariance defined as below:
Frequency scale-invariance: 100
Capacity scale-invariance: 50
First by Frequency scale-invariance,
the runtime is scaled to 50,000,000 * 100 >> 10 = 4,882,812
Then by capacity scale-invariance,
it is further scaled to 4,882,812 * 50 >> 10 = 238,418.
So it will scaled to 238,418 ns.

This smaller "accounted runtime" value is what ends up being
subtracted against the fair-server's runtime for the current period.
Thus after 50ms of real time, we've only accounted ~238us against the
fair servers runtime. This 209:1 ratio in this example means that on
the smaller cpu the fair server is allowed to continue running,
blocking RT tasks, for over 10 seconds before it exhausts its supposed
50ms of runtime.  And on other hardware configurations it can be even
worse.

For the fair deadline_server, to prevent realtime tasks from being
unexpectedly delayed, we really do want to use fixed time, and not
scaled time for smaller capacity/frequency cpus. So remove the scaling
from the fair server's accounting to fix this.

Fixes: a110a81c52a9 ("sched/deadline: Deferrable dl server")
Suggested-by: Peter Zijlstra <peterz@infradead.org>
Suggested-by: John Stultz <jstultz@google.com>
Signed-off-by: kuyo chang <kuyo.chang@mediatek.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Juri Lelli <juri.lelli@redhat.com>
Acked-by: John Stultz <jstultz@google.com>
Tested-by: John Stultz <jstultz@google.com>
Link: https://lore.kernel.org/r/20250702021440.2594736-1-kuyo.chang@mediatek.com
---
 kernel/sched/deadline.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index ad45a8fea245..89019a140826 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -1504,7 +1504,9 @@ static void update_curr_dl_se(struct rq *rq, struct sched_dl_entity *dl_se, s64
 	if (dl_entity_is_special(dl_se))
 		return;
 
-	scaled_delta_exec = dl_scaled_delta_exec(rq, dl_se, delta_exec);
+	scaled_delta_exec = delta_exec;
+	if (!dl_server(dl_se))
+		scaled_delta_exec = dl_scaled_delta_exec(rq, dl_se, delta_exec);
 
 	dl_se->runtime -= scaled_delta_exec;
 
@@ -1611,7 +1613,7 @@ throttle:
  */
 void dl_server_update_idle_time(struct rq *rq, struct task_struct *p)
 {
-	s64 delta_exec, scaled_delta_exec;
+	s64 delta_exec;
 
 	if (!rq->fair_server.dl_defer)
 		return;
@@ -1624,9 +1626,7 @@ void dl_server_update_idle_time(struct rq *rq, struct task_struct *p)
 	if (delta_exec < 0)
 		return;
 
-	scaled_delta_exec = dl_scaled_delta_exec(rq, &rq->fair_server, delta_exec);
-
-	rq->fair_server.runtime -= scaled_delta_exec;
+	rq->fair_server.runtime -= delta_exec;
 
 	if (rq->fair_server.runtime < 0) {
 		rq->fair_server.dl_defer_running = 0;

From 44306a684cd1699b8562a54945ddc43e2abc9eab Mon Sep 17 00:00:00 2001
From: Mikko Perttunen <mperttunen@nvidia.com>
Date: Wed, 2 Jul 2025 11:08:07 +0900
Subject: [PATCH 1160/1334] drm/tegra: nvdec: Fix dma_alloc_coherent error
 check

Check for NULL return value with dma_alloc_coherent, in line with
Robin's fix for vic.c in 'drm/tegra: vic: Fix DMA API misuse'.

Fixes: 46f226c93d35 ("drm/tegra: Add NVDEC driver")
Signed-off-by: Mikko Perttunen <mperttunen@nvidia.com>
Signed-off-by: Thierry Reding <treding@nvidia.com>
Link: https://lore.kernel.org/r/20250702-nvdec-dma-error-check-v1-1-c388b402c53a@nvidia.com
---
 drivers/gpu/drm/tegra/nvdec.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/tegra/nvdec.c b/drivers/gpu/drm/tegra/nvdec.c
index 2d9a0a3f6c38..7a38664e890e 100644
--- a/drivers/gpu/drm/tegra/nvdec.c
+++ b/drivers/gpu/drm/tegra/nvdec.c
@@ -261,10 +261,8 @@ static int nvdec_load_falcon_firmware(struct nvdec *nvdec)
 
 	if (!client->group) {
 		virt = dma_alloc_coherent(nvdec->dev, size, &iova, GFP_KERNEL);
-
-		err = dma_mapping_error(nvdec->dev, iova);
-		if (err < 0)
-			return err;
+		if (!virt)
+			return -ENOMEM;
 	} else {
 		virt = tegra_drm_alloc(tegra, size, &iova);
 		if (IS_ERR(virt))

From b9fd9888a5654e59f6c6249337e36c53c1faa329 Mon Sep 17 00:00:00 2001
From: Jason Xing <kernelxing@tencent.com>
Date: Wed, 2 Jul 2025 14:48:22 +0800
Subject: [PATCH 1161/1334] bnxt_en: eliminate the compile warning in
 bnxt_request_irq due to CONFIG_RFS_ACCEL

I received a kernel-test-bot report[1] that shows the
[-Wunused-but-set-variable] warning. Since the previous commit I made, as
the 'Fixes' tag shows, gives users an option to turn on and off the
CONFIG_RFS_ACCEL, the issue then can be discovered and reproduced with
GCC specifically.

Like Simon and Jakub suggested, use fewer #ifdefs which leads to fewer
bugs.

[1]
All warnings (new ones prefixed by >>):

   drivers/net/ethernet/broadcom/bnxt/bnxt.c: In function 'bnxt_request_irq':
>> drivers/net/ethernet/broadcom/bnxt/bnxt.c:10703:9: warning: variable 'j' set but not used [-Wunused-but-set-variable]
   10703 |  int i, j, rc = 0;
         |         ^

Fixes: 9b6a30febddf ("net: allow rps/rfs related configs to be switched")
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202506282102.x1tXt0qz-lkp@intel.com/
Signed-off-by: Jason Xing <kernelxing@tencent.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index ae89a981e052..243cb13cb01c 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -11607,11 +11607,9 @@ static void bnxt_free_irq(struct bnxt *bp)
 
 static int bnxt_request_irq(struct bnxt *bp)
 {
+	struct cpu_rmap *rmap = NULL;
 	int i, j, rc = 0;
 	unsigned long flags = 0;
-#ifdef CONFIG_RFS_ACCEL
-	struct cpu_rmap *rmap;
-#endif
 
 	rc = bnxt_setup_int_mode(bp);
 	if (rc) {
@@ -11632,15 +11630,15 @@ static int bnxt_request_irq(struct bnxt *bp)
 		int map_idx = bnxt_cp_num_to_irq_num(bp, i);
 		struct bnxt_irq *irq = &bp->irq_tbl[map_idx];
 
-#ifdef CONFIG_RFS_ACCEL
-		if (rmap && bp->bnapi[i]->rx_ring) {
+		if (IS_ENABLED(CONFIG_RFS_ACCEL) &&
+		    rmap && bp->bnapi[i]->rx_ring) {
 			rc = irq_cpu_rmap_add(rmap, irq->vector);
 			if (rc)
 				netdev_warn(bp->dev, "failed adding irq rmap for ring %d\n",
 					    j);
 			j++;
 		}
-#endif
+
 		rc = request_irq(irq->vector, irq->handler, flags, irq->name,
 				 bp->bnapi[i]);
 		if (rc)

From ef8923e6c051a98164c2889db943df9695a39888 Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Fri, 4 Jul 2025 05:47:07 -0700
Subject: [PATCH 1162/1334] arm64: efi: Fix KASAN false positive for EFI
 runtime stack

KASAN reports invalid accesses during arch_stack_walk() for EFI runtime
services due to vmalloc tagging[1]. The EFI runtime stack must be allocated
with KASAN tags reset to avoid false positives.

This patch uses arch_alloc_vmap_stack() instead of __vmalloc_node() for
EFI stack allocation, which internally calls kasan_reset_tag()

The changes ensure EFI runtime stacks are properly sanitized for KASAN
while maintaining functional consistency.

Link: https://lore.kernel.org/all/aFVVEgD0236LdrL6@gmail.com/ [1]
Suggested-by: Andrey Konovalov <andreyknvl@gmail.com>
Suggested-by: Catalin Marinas <catalin.marinas@arm.com>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Breno Leitao <leitao@debian.org>
Link: https://lore.kernel.org/r/20250704-arm_kasan-v2-1-32ebb4fd7607@debian.org
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/kernel/efi.c | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/arch/arm64/kernel/efi.c b/arch/arm64/kernel/efi.c
index 3857fd7ee8d4..62230d6dd919 100644
--- a/arch/arm64/kernel/efi.c
+++ b/arch/arm64/kernel/efi.c
@@ -15,6 +15,7 @@
 
 #include <asm/efi.h>
 #include <asm/stacktrace.h>
+#include <asm/vmap_stack.h>
 
 static bool region_is_misaligned(const efi_memory_desc_t *md)
 {
@@ -214,9 +215,13 @@ static int __init arm64_efi_rt_init(void)
 	if (!efi_enabled(EFI_RUNTIME_SERVICES))
 		return 0;
 
-	p = __vmalloc_node(THREAD_SIZE, THREAD_ALIGN, GFP_KERNEL,
-			   NUMA_NO_NODE, &&l);
-l:	if (!p) {
+	if (!IS_ENABLED(CONFIG_VMAP_STACK)) {
+		clear_bit(EFI_RUNTIME_SERVICES, &efi.flags);
+		return -ENOMEM;
+	}
+
+	p = arch_alloc_vmap_stack(THREAD_SIZE, NUMA_NO_NODE);
+	if (!p) {
 		pr_warn("Failed to allocate EFI runtime stack\n");
 		clear_bit(EFI_RUNTIME_SERVICES, &efi.flags);
 		return -ENOMEM;

From 727c2a53cf959f599493c50a80fe2a356b8b1df6 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Fri, 13 Jun 2025 15:19:36 +0100
Subject: [PATCH 1163/1334] arm64: Unconditionally select CONFIG_JUMP_LABEL

Aneesh reports that his kernel fails to boot in nVHE mode with
KVM's protected mode enabled. Further investigation by Mostafa
reveals that this fails because CONFIG_JUMP_LABEL=n and that
we have static keys shared between EL1 and EL2.

While this can be worked around, it is obvious that we have long
relied on having CONFIG_JUMP_LABEL enabled at all times, as all
supported compilers now have 'asm goto' (which is the basic block
for jump labels).

Let's simplify our lives once and for all by mandating jump labels.
It's not like anyone else is testing anything without them, and
we already rely on them for other things (kfence, xfs, preempt).

Link: https://lore.kernel.org/r/yq5ah60pkq03.fsf@kernel.org
Reported-by: Aneesh Kumar K.V <aneesh.kumar@kernel.org>
Reported-by: Mostafa Saleh <smostafa@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Cc: Will Deacon <will@kernel.org>
Cc: Catalin marinas <catalin.marinas@arm.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Ard Biesheuvel <ardb@kernel.org>
Acked-by: Mark Rutland <mark.rutland@arm.com>
Link: https://lore.kernel.org/r/20250613141936.2219895-1-maz@kernel.org
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/Kconfig         | 1 +
 arch/arm64/kernel/Makefile | 3 +--
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 55fc331af337..393d71124f5d 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -256,6 +256,7 @@ config ARM64
 	select HOTPLUG_SMT if HOTPLUG_CPU
 	select IRQ_DOMAIN
 	select IRQ_FORCED_THREADING
+	select JUMP_LABEL
 	select KASAN_VMALLOC if KASAN
 	select LOCK_MM_AND_FIND_VMA
 	select MODULES_USE_ELF_RELA
diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile
index 2920b0a51403..a2faf0049dab 100644
--- a/arch/arm64/kernel/Makefile
+++ b/arch/arm64/kernel/Makefile
@@ -34,7 +34,7 @@ obj-y			:= debug-monitors.o entry.o irq.o fpsimd.o		\
 			   cpufeature.o alternative.o cacheinfo.o		\
 			   smp.o smp_spin_table.o topology.o smccc-call.o	\
 			   syscall.o proton-pack.o idle.o patching.o pi/	\
-			   rsi.o
+			   rsi.o jump_label.o
 
 obj-$(CONFIG_COMPAT)			+= sys32.o signal32.o			\
 					   sys_compat.o
@@ -47,7 +47,6 @@ obj-$(CONFIG_PERF_EVENTS)		+= perf_regs.o perf_callchain.o
 obj-$(CONFIG_HARDLOCKUP_DETECTOR_PERF)	+= watchdog_hld.o
 obj-$(CONFIG_HAVE_HW_BREAKPOINT)	+= hw_breakpoint.o
 obj-$(CONFIG_CPU_PM)			+= sleep.o suspend.o
-obj-$(CONFIG_JUMP_LABEL)		+= jump_label.o
 obj-$(CONFIG_KGDB)			+= kgdb.o
 obj-$(CONFIG_EFI)			+= efi.o efi-rt-wrapper.o
 obj-$(CONFIG_PCI)			+= pci.o

From 0d1c86b840966a278d9b25a9d7c18881980f306e Mon Sep 17 00:00:00 2001
From: Mark Brown <broonie@kernel.org>
Date: Thu, 19 Jun 2025 22:15:41 +0100
Subject: [PATCH 1164/1334] arm64/gcs: Don't try to access GCS registers if
 arm64.nogcs is enabled

During EL2 setup if GCS is advertised in the ID registers we will reset the
GCS control registers GCSCR_EL1 and GCSCRE0_EL1 to known values in order to
ensure it is disabled. This is done without taking into account overrides
supplied on the command line, meaning that if the user has configured
arm64.nogcs we will still access these GCS specific registers. If this was
done because EL3 does not enable GCS this results in traps to EL3 and a
failed boot which is not what users would expect from having set that
parameter.

Move the writes to these registers to finalise_el2_state where we can pay
attention to the command line overrides. For simplicity we leave the
updates to the traps in HCRX_EL2 and the FGT registers in place since these
should only be relevant for KVM guests and KVM will manage them itself for
guests. This follows the existing practice for other similar traps for
overridable features such as those for TPIDR2_EL0 and SMPRI_EL1.

Signed-off-by: Mark Brown <broonie@kernel.org>
Link: https://lore.kernel.org/r/20250619-arm64-fix-nogcs-v1-1-febf2973672e@kernel.org
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/include/asm/el2_setup.h | 19 +++++++------------
 1 file changed, 7 insertions(+), 12 deletions(-)

diff --git a/arch/arm64/include/asm/el2_setup.h b/arch/arm64/include/asm/el2_setup.h
index ba5df0df02a4..9f38340d24c2 100644
--- a/arch/arm64/include/asm/el2_setup.h
+++ b/arch/arm64/include/asm/el2_setup.h
@@ -287,17 +287,6 @@
 .Lskip_fgt2_\@:
 .endm
 
-.macro __init_el2_gcs
-	mrs_s	x1, SYS_ID_AA64PFR1_EL1
-	ubfx	x1, x1, #ID_AA64PFR1_EL1_GCS_SHIFT, #4
-	cbz	x1, .Lskip_gcs_\@
-
-	/* Ensure GCS is not enabled when we start trying to do BLs */
-	msr_s	SYS_GCSCR_EL1, xzr
-	msr_s	SYS_GCSCRE0_EL1, xzr
-.Lskip_gcs_\@:
-.endm
-
 /**
  * Initialize EL2 registers to sane values. This should be called early on all
  * cores that were booted in EL2. Note that everything gets initialised as
@@ -319,7 +308,6 @@
 	__init_el2_cptr
 	__init_el2_fgt
 	__init_el2_fgt2
-        __init_el2_gcs
 .endm
 
 #ifndef __KVM_NVHE_HYPERVISOR__
@@ -371,6 +359,13 @@
 	msr_s   SYS_MPAMHCR_EL2, xzr		// clear TRAP_MPAMIDR_EL1 -> EL2
 
 .Lskip_mpam_\@:
+	check_override id_aa64pfr1, ID_AA64PFR1_EL1_GCS_SHIFT, .Linit_gcs_\@, .Lskip_gcs_\@, x1, x2
+
+.Linit_gcs_\@:
+	msr_s	SYS_GCSCR_EL1, xzr
+	msr_s	SYS_GCSCRE0_EL1, xzr
+
+.Lskip_gcs_\@:
 	check_override id_aa64pfr0, ID_AA64PFR0_EL1_SVE_SHIFT, .Linit_sve_\@, .Lskip_sve_\@, x1, x2
 
 .Linit_sve_\@:	/* SVE register access */

From d38376b3ee48d073c64e75e150510d7e6b4b04f7 Mon Sep 17 00:00:00 2001
From: Alessio Belle <alessio.belle@imgtec.com>
Date: Tue, 24 Jun 2025 15:22:08 +0100
Subject: [PATCH 1165/1334] drm/imagination: Fix kernel crash when hard
 resetting the GPU

The GPU hard reset sequence calls pm_runtime_force_suspend() and
pm_runtime_force_resume(), which according to their documentation should
only be used during system-wide PM transitions to sleep states.

The main issue though is that depending on some internal runtime PM
state as seen by pm_runtime_force_suspend() (whether the usage count is
<= 1), pm_runtime_force_resume() might not resume the device unless
needed. If that happens, the runtime PM resume callback
pvr_power_device_resume() is not called, the GPU clocks are not
re-enabled, and the kernel crashes on the next attempt to access GPU
registers as part of the power-on sequence.

Replace calls to pm_runtime_force_suspend() and
pm_runtime_force_resume() with direct calls to the driver's runtime PM
callbacks, pvr_power_device_suspend() and pvr_power_device_resume(),
to ensure clocks are re-enabled and avoid the kernel crash.

Fixes: cc1aeedb98ad ("drm/imagination: Implement firmware infrastructure and META FW support")
Signed-off-by: Alessio Belle <alessio.belle@imgtec.com>
Reviewed-by: Matt Coster <matt.coster@imgtec.com>
Link: https://lore.kernel.org/r/20250624-fix-kernel-crash-gpu-hard-reset-v1-1-6d24810d72a6@imgtec.com
Cc: stable@vger.kernel.org
Signed-off-by: Matt Coster <matt.coster@imgtec.com>
---
 drivers/gpu/drm/imagination/pvr_power.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/imagination/pvr_power.c b/drivers/gpu/drm/imagination/pvr_power.c
index 41f5d89e78b8..3e349d039fc0 100644
--- a/drivers/gpu/drm/imagination/pvr_power.c
+++ b/drivers/gpu/drm/imagination/pvr_power.c
@@ -386,13 +386,13 @@ pvr_power_reset(struct pvr_device *pvr_dev, bool hard_reset)
 		if (!err) {
 			if (hard_reset) {
 				pvr_dev->fw_dev.booted = false;
-				WARN_ON(pm_runtime_force_suspend(from_pvr_device(pvr_dev)->dev));
+				WARN_ON(pvr_power_device_suspend(from_pvr_device(pvr_dev)->dev));
 
 				err = pvr_fw_hard_reset(pvr_dev);
 				if (err)
 					goto err_device_lost;
 
-				err = pm_runtime_force_resume(from_pvr_device(pvr_dev)->dev);
+				err = pvr_power_device_resume(from_pvr_device(pvr_dev)->dev);
 				pvr_dev->fw_dev.booted = true;
 				if (err)
 					goto err_device_lost;

From 6c66bb655ca3fd5e9304163cf70796d08de512ed Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Fri, 20 Jun 2025 13:10:41 +0200
Subject: [PATCH 1166/1334] arm64: move smp_send_stop() cpu mask off stack

For really large values of CONFIG_NR_CPUS, a CPU mask value should
not be put on the stack:

arch/arm64/kernel/smp.c:1188:1: error: the frame size of 8544 bytes is larger than 1536 bytes [-Werror=frame-larger-than=]

This could be achieved using alloc_cpumask_var(), which makes it
depend on CONFIG_CPUMASK_OFFSTACK, but as this function is already
serialized and can only run on one CPU, making the variable 'static'
is easier.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Link: https://lore.kernel.org/r/20250620111045.3364827-1-arnd@kernel.org
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/kernel/smp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index 3b3f6b56e733..21a795303568 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -1143,7 +1143,7 @@ static inline unsigned int num_other_online_cpus(void)
 void smp_send_stop(void)
 {
 	static unsigned long stop_in_progress;
-	cpumask_t mask;
+	static cpumask_t mask;
 	unsigned long timeout;
 
 	/*

From a75ad2fc76a2ab70817c7eed3163b66ea84ca6ac Mon Sep 17 00:00:00 2001
From: Mark Brown <broonie@kernel.org>
Date: Fri, 20 Jun 2025 12:28:48 +0100
Subject: [PATCH 1167/1334] arm64: Filter out SME hwcaps when FEAT_SME isn't
 implemented

We have a number of hwcaps for various SME subfeatures enumerated via
ID_AA64SMFR0_EL1. Currently we advertise these without cross checking
against the main SME feature, advertised in ID_AA64PFR1_EL1.SME which
means that if the two are out of sync userspace can see a confusing
situation where SME subfeatures are advertised without the base SME
hwcap. This can be readily triggered by using the arm64.nosme override
which only masks out ID_AA64PFR1_EL1.SME, and there have also been
reports of VMMs which do the same thing.

Fix this as we did previously for SVE in 064737920bdb ("arm64: Filter
out SVE hwcaps when FEAT_SVE isn't implemented") by filtering out the
SME subfeature hwcaps when FEAT_SME is not present.

Fixes: 5e64b862c482 ("arm64/sme: Basic enumeration support")
Reported-by: Yury Khrustalev <yury.khrustalev@arm.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20250620-arm64-sme-filter-hwcaps-v1-1-02b9d3c2d8ef@kernel.org
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/kernel/cpufeature.c | 57 +++++++++++++++++++---------------
 1 file changed, 32 insertions(+), 25 deletions(-)

diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index b34044e20128..e151585c6cca 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -3135,6 +3135,13 @@ static bool has_sve_feature(const struct arm64_cpu_capabilities *cap, int scope)
 }
 #endif
 
+#ifdef CONFIG_ARM64_SME
+static bool has_sme_feature(const struct arm64_cpu_capabilities *cap, int scope)
+{
+	return system_supports_sme() && has_user_cpuid_feature(cap, scope);
+}
+#endif
+
 static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = {
 	HWCAP_CAP(ID_AA64ISAR0_EL1, AES, PMULL, CAP_HWCAP, KERNEL_HWCAP_PMULL),
 	HWCAP_CAP(ID_AA64ISAR0_EL1, AES, AES, CAP_HWCAP, KERNEL_HWCAP_AES),
@@ -3223,31 +3230,31 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = {
 	HWCAP_CAP(ID_AA64ISAR2_EL1, BC, IMP, CAP_HWCAP, KERNEL_HWCAP_HBC),
 #ifdef CONFIG_ARM64_SME
 	HWCAP_CAP(ID_AA64PFR1_EL1, SME, IMP, CAP_HWCAP, KERNEL_HWCAP_SME),
-	HWCAP_CAP(ID_AA64SMFR0_EL1, FA64, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_FA64),
-	HWCAP_CAP(ID_AA64SMFR0_EL1, LUTv2, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_LUTV2),
-	HWCAP_CAP(ID_AA64SMFR0_EL1, SMEver, SME2p2, CAP_HWCAP, KERNEL_HWCAP_SME2P2),
-	HWCAP_CAP(ID_AA64SMFR0_EL1, SMEver, SME2p1, CAP_HWCAP, KERNEL_HWCAP_SME2P1),
-	HWCAP_CAP(ID_AA64SMFR0_EL1, SMEver, SME2, CAP_HWCAP, KERNEL_HWCAP_SME2),
-	HWCAP_CAP(ID_AA64SMFR0_EL1, I16I64, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_I16I64),
-	HWCAP_CAP(ID_AA64SMFR0_EL1, F64F64, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F64F64),
-	HWCAP_CAP(ID_AA64SMFR0_EL1, I16I32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_I16I32),
-	HWCAP_CAP(ID_AA64SMFR0_EL1, B16B16, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_B16B16),
-	HWCAP_CAP(ID_AA64SMFR0_EL1, F16F16, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F16F16),
-	HWCAP_CAP(ID_AA64SMFR0_EL1, F8F16, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F8F16),
-	HWCAP_CAP(ID_AA64SMFR0_EL1, F8F32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F8F32),
-	HWCAP_CAP(ID_AA64SMFR0_EL1, I8I32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_I8I32),
-	HWCAP_CAP(ID_AA64SMFR0_EL1, F16F32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F16F32),
-	HWCAP_CAP(ID_AA64SMFR0_EL1, B16F32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_B16F32),
-	HWCAP_CAP(ID_AA64SMFR0_EL1, BI32I32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_BI32I32),
-	HWCAP_CAP(ID_AA64SMFR0_EL1, F32F32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F32F32),
-	HWCAP_CAP(ID_AA64SMFR0_EL1, SF8FMA, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8FMA),
-	HWCAP_CAP(ID_AA64SMFR0_EL1, SF8DP4, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8DP4),
-	HWCAP_CAP(ID_AA64SMFR0_EL1, SF8DP2, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8DP2),
-	HWCAP_CAP(ID_AA64SMFR0_EL1, SBitPerm, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SBITPERM),
-	HWCAP_CAP(ID_AA64SMFR0_EL1, AES, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_AES),
-	HWCAP_CAP(ID_AA64SMFR0_EL1, SFEXPA, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SFEXPA),
-	HWCAP_CAP(ID_AA64SMFR0_EL1, STMOP, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_STMOP),
-	HWCAP_CAP(ID_AA64SMFR0_EL1, SMOP4, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SMOP4),
+	HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, FA64, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_FA64),
+	HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, LUTv2, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_LUTV2),
+	HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, SMEver, SME2p2, CAP_HWCAP, KERNEL_HWCAP_SME2P2),
+	HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, SMEver, SME2p1, CAP_HWCAP, KERNEL_HWCAP_SME2P1),
+	HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, SMEver, SME2, CAP_HWCAP, KERNEL_HWCAP_SME2),
+	HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, I16I64, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_I16I64),
+	HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, F64F64, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F64F64),
+	HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, I16I32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_I16I32),
+	HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, B16B16, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_B16B16),
+	HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, F16F16, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F16F16),
+	HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, F8F16, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F8F16),
+	HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, F8F32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F8F32),
+	HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, I8I32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_I8I32),
+	HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, F16F32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F16F32),
+	HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, B16F32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_B16F32),
+	HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, BI32I32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_BI32I32),
+	HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, F32F32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F32F32),
+	HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, SF8FMA, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8FMA),
+	HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, SF8DP4, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8DP4),
+	HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, SF8DP2, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8DP2),
+	HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, SBitPerm, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SBITPERM),
+	HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, AES, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_AES),
+	HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, SFEXPA, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SFEXPA),
+	HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, STMOP, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_STMOP),
+	HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, SMOP4, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SMOP4),
 #endif /* CONFIG_ARM64_SME */
 	HWCAP_CAP(ID_AA64FPFR0_EL1, F8CVT, IMP, CAP_HWCAP, KERNEL_HWCAP_F8CVT),
 	HWCAP_CAP(ID_AA64FPFR0_EL1, F8FMA, IMP, CAP_HWCAP, KERNEL_HWCAP_F8FMA),

From 22f3a4f6085951eff28bd1e44d3f388c1d9a5f44 Mon Sep 17 00:00:00 2001
From: Kevin Brodsky <kevin.brodsky@arm.com>
Date: Thu, 19 Jun 2025 17:00:41 +0100
Subject: [PATCH 1168/1334] arm64: poe: Handle spurious Overlay faults

We do not currently issue an ISB after updating POR_EL0 when
context-switching it, for instance. The rationale is that if the old
value of POR_EL0 is more restrictive and causes a fault during
uaccess, the access will be retried [1]. In other words, we are
trading an ISB on every context-switching for the (unlikely)
possibility of a spurious fault. We may also miss faults if the new
value of POR_EL0 is more restrictive, but that's considered
acceptable.

However, as things stand, a spurious Overlay fault results in
uaccess failing right away since it causes fault_from_pkey() to
return true. If an Overlay fault is reported, we therefore need to
double check POR_EL0 against vma_pkey(vma) - this is what
arch_vma_access_permitted() already does.

As it turns out, we already perform that explicit check if no
Overlay fault is reported, and we need to keep that check (see
comment added in fault_from_pkey()). Net result: the Overlay ISS2
bit isn't of much help to decide whether a pkey fault occurred.

Remove the check for the Overlay bit from fault_from_pkey() and
add a comment to try and explain the situation. While at it, also
add a comment to permission_overlay_switch() in case anyone gets
surprised by the lack of ISB.

[1] https://lore.kernel.org/linux-arm-kernel/ZtYNGBrcE-j35fpw@arm.com/

Fixes: 160a8e13de6c ("arm64: context switch POR_EL0 register")
Signed-off-by: Kevin Brodsky <kevin.brodsky@arm.com>
Link: https://lore.kernel.org/r/20250619160042.2499290-2-kevin.brodsky@arm.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/kernel/process.c |  5 +++++
 arch/arm64/mm/fault.c       | 30 +++++++++++++++++++++---------
 2 files changed, 26 insertions(+), 9 deletions(-)

diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index 5954cec19660..08b7042a2e2d 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -673,6 +673,11 @@ static void permission_overlay_switch(struct task_struct *next)
 	current->thread.por_el0 = read_sysreg_s(SYS_POR_EL0);
 	if (current->thread.por_el0 != next->thread.por_el0) {
 		write_sysreg_s(next->thread.por_el0, SYS_POR_EL0);
+		/*
+		 * No ISB required as we can tolerate spurious Overlay faults -
+		 * the fault handler will check again based on the new value
+		 * of POR_EL0.
+		 */
 	}
 }
 
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index ec0a337891dd..11eb8d1adc84 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -487,17 +487,29 @@ static void do_bad_area(unsigned long far, unsigned long esr,
 	}
 }
 
-static bool fault_from_pkey(unsigned long esr, struct vm_area_struct *vma,
-			unsigned int mm_flags)
+static bool fault_from_pkey(struct vm_area_struct *vma, unsigned int mm_flags)
 {
-	unsigned long iss2 = ESR_ELx_ISS2(esr);
-
 	if (!system_supports_poe())
 		return false;
 
-	if (esr_fsc_is_permission_fault(esr) && (iss2 & ESR_ELx_Overlay))
-		return true;
-
+	/*
+	 * We do not check whether an Overlay fault has occurred because we
+	 * cannot make a decision based solely on its value:
+	 *
+	 * - If Overlay is set, a fault did occur due to POE, but it may be
+	 *   spurious in those cases where we update POR_EL0 without ISB (e.g.
+	 *   on context-switch). We would then need to manually check POR_EL0
+	 *   against vma_pkey(vma), which is exactly what
+	 *   arch_vma_access_permitted() does.
+	 *
+	 * - If Overlay is not set, we may still need to report a pkey fault.
+	 *   This is the case if an access was made within a mapping but with no
+	 *   page mapped, and POR_EL0 forbids the access (according to
+	 *   vma_pkey()). Such access will result in a SIGSEGV regardless
+	 *   because core code checks arch_vma_access_permitted(), but in order
+	 *   to report the correct error code - SEGV_PKUERR - we must handle
+	 *   that case here.
+	 */
 	return !arch_vma_access_permitted(vma,
 			mm_flags & FAULT_FLAG_WRITE,
 			mm_flags & FAULT_FLAG_INSTRUCTION,
@@ -635,7 +647,7 @@ static int __kprobes do_page_fault(unsigned long far, unsigned long esr,
 		goto bad_area;
 	}
 
-	if (fault_from_pkey(esr, vma, mm_flags)) {
+	if (fault_from_pkey(vma, mm_flags)) {
 		pkey = vma_pkey(vma);
 		vma_end_read(vma);
 		fault = 0;
@@ -679,7 +691,7 @@ retry:
 		goto bad_area;
 	}
 
-	if (fault_from_pkey(esr, vma, mm_flags)) {
+	if (fault_from_pkey(vma, mm_flags)) {
 		pkey = vma_pkey(vma);
 		mmap_read_unlock(mm);
 		fault = 0;

From 9dd1757493416310a5e71146a08bc228869f8dae Mon Sep 17 00:00:00 2001
From: Anshuman Khandual <anshuman.khandual@arm.com>
Date: Fri, 4 Jul 2025 12:08:12 +0530
Subject: [PATCH 1169/1334] arm64/mm: Drop wrong writes into TCR2_EL1

Register X0 contains PIE_E1_ASM and should not be written into REG_TCR2_EL1
which could have an adverse impact otherwise. This has remained undetected
till now probably because current value for PIE_E1_ASM (0xcc880e0ac0800000)
clears TCR2_EL1 which again gets set subsequently with 'tcr2' after testing
for FEAT_TCR2.

Drop this unwarranted 'msr' which is a stray change from an earlier commit.
This line got re-introduced when rebasing on top of the commit 926b66e2ebc8
("arm64: setup: name 'tcr2' register").

Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will@kernel.org>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Marc Zyngier <maz@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-kernel@vger.kernel.org
Fixes: 7052e808c446 ("arm64/sysreg: Get rid of the TCR2_EL1x SysregFields")
Acked-by: Marc Zyngier <maz@kernel.org>
Signed-off-by: Anshuman Khandual <anshuman.khandual@arm.com>
Link: https://lore.kernel.org/r/20250704063812.298914-1-anshuman.khandual@arm.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/mm/proc.S | 1 -
 1 file changed, 1 deletion(-)

diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S
index 80d470aa469d..54dccfd6aa11 100644
--- a/arch/arm64/mm/proc.S
+++ b/arch/arm64/mm/proc.S
@@ -518,7 +518,6 @@ alternative_else_nop_endif
 	msr	REG_PIR_EL1, x0
 
 	orr	tcr2, tcr2, TCR2_EL1_PIE
-	msr	REG_TCR2_EL1, x0
 
 .Lskip_indirection:
 

From 63d6e9311999a3dd125ad3e0560a769e047fd7b1 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Wed, 2 Jul 2025 13:28:55 -0400
Subject: [PATCH 1170/1334] bcachefs: bch2_fpunch_snapshot()

Add a new version of fpunch for operating on a snapshot ID, not a
subvolume - and use it for "extent past end of inode" repair.

Previously, repair would try to delete everything at once, but deleting
too many extents at once can overflow the btree_trans bump allocator, as
well as causing other problems - the new helper properly uses
bch2_extent_trim_atomic().

Reported-and-tested-by: Edoardo Codeglia <bcachefs@404.blue>
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/fsck.c    | 33 ++++++---------------------------
 fs/bcachefs/io_misc.c | 27 +++++++++++++++++++++++++++
 fs/bcachefs/io_misc.h |  2 ++
 3 files changed, 35 insertions(+), 27 deletions(-)

diff --git a/fs/bcachefs/fsck.c b/fs/bcachefs/fsck.c
index dbf161e4311a..856eb2b41896 100644
--- a/fs/bcachefs/fsck.c
+++ b/fs/bcachefs/fsck.c
@@ -12,6 +12,7 @@
 #include "fs.h"
 #include "fsck.h"
 #include "inode.h"
+#include "io_misc.h"
 #include "keylist.h"
 #include "namei.h"
 #include "recovery_passes.h"
@@ -1919,33 +1920,11 @@ static int check_extent(struct btree_trans *trans, struct btree_iter *iter,
 					"extent type past end of inode %llu:%u, i_size %llu\n%s",
 					i->inode.bi_inum, i->inode.bi_snapshot, i->inode.bi_size,
 					(bch2_bkey_val_to_text(&buf, c, k), buf.buf))) {
-				struct bkey_i *whiteout = bch2_trans_kmalloc(trans, sizeof(*whiteout));
-				ret = PTR_ERR_OR_ZERO(whiteout);
-				if (ret)
-					goto err;
-
-				bkey_init(&whiteout->k);
-				whiteout->k.p = SPOS(k.k->p.inode,
-						     last_block,
-						     i->inode.bi_snapshot);
-				bch2_key_resize(&whiteout->k,
-						min(KEY_SIZE_MAX & (~0 << c->block_bits),
-						    U64_MAX - whiteout->k.p.offset));
-
-
-				/*
-				 * Need a normal (not BTREE_ITER_all_snapshots)
-				 * iterator, if we're deleting in a different
-				 * snapshot and need to emit a whiteout
-				 */
-				struct btree_iter iter2;
-				bch2_trans_iter_init(trans, &iter2, BTREE_ID_extents,
-						     bkey_start_pos(&whiteout->k),
-						     BTREE_ITER_intent);
-				ret =   bch2_btree_iter_traverse(trans, &iter2) ?:
-					bch2_trans_update(trans, &iter2, whiteout,
-						BTREE_UPDATE_internal_snapshot_node);
-				bch2_trans_iter_exit(trans, &iter2);
+				ret = bch2_fpunch_snapshot(trans,
+							   SPOS(i->inode.bi_inum,
+								last_block,
+								i->inode.bi_snapshot),
+							   POS(i->inode.bi_inum, U64_MAX));
 				if (ret)
 					goto err;
 
diff --git a/fs/bcachefs/io_misc.c b/fs/bcachefs/io_misc.c
index bf72b1d2e2cb..07023667a475 100644
--- a/fs/bcachefs/io_misc.c
+++ b/fs/bcachefs/io_misc.c
@@ -135,6 +135,33 @@ err_noprint:
 	return ret;
 }
 
+/* For fsck */
+int bch2_fpunch_snapshot(struct btree_trans *trans, struct bpos start, struct bpos end)
+{
+	u32 restart_count = trans->restart_count;
+	struct bch_fs *c = trans->c;
+	struct disk_reservation disk_res = bch2_disk_reservation_init(c, 0);
+	unsigned max_sectors	= KEY_SIZE_MAX & (~0 << c->block_bits);
+	struct bkey_i delete;
+
+	int ret = for_each_btree_key_max_commit(trans, iter, BTREE_ID_extents,
+			start, end, 0, k,
+			&disk_res, NULL, BCH_TRANS_COMMIT_no_enospc, ({
+		bkey_init(&delete.k);
+		delete.k.p = iter.pos;
+
+		/* create the biggest key we can */
+		bch2_key_resize(&delete.k, max_sectors);
+		bch2_cut_back(end, &delete);
+
+		bch2_extent_trim_atomic(trans, &iter, &delete) ?:
+		bch2_trans_update(trans, &iter, &delete, 0);
+	}));
+
+	bch2_disk_reservation_put(c, &disk_res);
+	return ret ?: trans_was_restarted(trans, restart_count);
+}
+
 /*
  * Returns -BCH_ERR_transacton_restart if we had to drop locks:
  */
diff --git a/fs/bcachefs/io_misc.h b/fs/bcachefs/io_misc.h
index 9cb44a7c43c1..b93e4d4b3c0c 100644
--- a/fs/bcachefs/io_misc.h
+++ b/fs/bcachefs/io_misc.h
@@ -5,6 +5,8 @@
 int bch2_extent_fallocate(struct btree_trans *, subvol_inum, struct btree_iter *,
 			  u64, struct bch_io_opts, s64 *,
 			  struct write_point_specifier);
+
+int bch2_fpunch_snapshot(struct btree_trans *, struct bpos, struct bpos);
 int bch2_fpunch_at(struct btree_trans *, struct btree_iter *,
 		   subvol_inum, u64, s64 *);
 int bch2_fpunch(struct bch_fs *c, subvol_inum, u64, u64, s64 *);

From ddb9680a7226d6081b42869d2875715a17ecb51d Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Thu, 3 Jul 2025 15:08:19 -0400
Subject: [PATCH 1171/1334] bcachefs: Fix bch2_io_failures_to_text()

This wasn't updated when we added tracking for btree validate errors.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/extents.c | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/fs/bcachefs/extents.c b/fs/bcachefs/extents.c
index 036e4ad95987..83cbd77dcb9c 100644
--- a/fs/bcachefs/extents.c
+++ b/fs/bcachefs/extents.c
@@ -50,19 +50,17 @@ void bch2_io_failures_to_text(struct printbuf *out,
 			      struct bch_io_failures *failed)
 {
 	static const char * const error_types[] = {
-		"io", "checksum", "ec reconstruct", NULL
+		"btree validate", "io", "checksum", "ec reconstruct", NULL
 	};
 
 	for (struct bch_dev_io_failures *f = failed->devs;
 	     f < failed->devs + failed->nr;
 	     f++) {
 		unsigned errflags =
-			((!!f->failed_io)	<< 0) |
-			((!!f->failed_csum_nr)	<< 1) |
-			((!!f->failed_ec)	<< 2);
-
-		if (!errflags)
-			continue;
+			((!!f->failed_btree_validate)	<< 0) |
+			((!!f->failed_io)		<< 1) |
+			((!!f->failed_csum_nr)		<< 2) |
+			((!!f->failed_ec)		<< 3);
 
 		bch2_printbuf_make_room(out, 1024);
 		out->atomic++;
@@ -77,7 +75,9 @@ void bch2_io_failures_to_text(struct printbuf *out,
 
 		prt_char(out, ' ');
 
-		if (is_power_of_2(errflags)) {
+		if (!errflags) {
+			prt_str(out, "no error - confused");
+		} else if (is_power_of_2(errflags)) {
 			prt_bitflags(out, error_types, errflags);
 			prt_str(out, " error");
 		} else {

From c72d628469b8f46251b3afc361269cb15de0c988 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Thu, 3 Jul 2025 15:53:51 -0400
Subject: [PATCH 1172/1334] bcachefs: Fix btree for nonexistent tree depth

The fix for when we should increase tree depth in journal replay was
entirely bogus.

We should only increase the tree depth in journal replay when recovery
from btree node scan, and then only for keys found by btree node scan.

This needs additional work - we should be shooting down existing
interior node pointers when recovery from scan, they shouldn't be
showing up here.

Fixes: b47a82ff4772 ("bcachefs: Only run 'increase_depth' for keys from btree node csan")
Cc: Alan Huang <mmpgouride@gmail.com>
Reported-by: syzbot+8deb6ff4415db67a9f18@syzkaller.appspotmail.com
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/recovery.c | 23 +++++++++++++++++------
 1 file changed, 17 insertions(+), 6 deletions(-)

diff --git a/fs/bcachefs/recovery.c b/fs/bcachefs/recovery.c
index d0b7e3a36a54..c94debb12d2f 100644
--- a/fs/bcachefs/recovery.c
+++ b/fs/bcachefs/recovery.c
@@ -273,24 +273,35 @@ static int bch2_journal_replay_key(struct btree_trans *trans,
 		goto out;
 
 	struct btree_path *path = btree_iter_path(trans, &iter);
-	if (unlikely(!btree_path_node(path, k->level) &&
-		     !k->allocated)) {
+	if (unlikely(!btree_path_node(path, k->level))) {
 		struct bch_fs *c = trans->c;
 
+		CLASS(printbuf, buf)();
+		prt_str(&buf, "btree=");
+		bch2_btree_id_to_text(&buf, k->btree_id);
+		prt_printf(&buf, " level=%u ", k->level);
+		bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(k->k));
+
 		if (!(c->recovery.passes_complete & (BIT_ULL(BCH_RECOVERY_PASS_scan_for_btree_nodes)|
 						     BIT_ULL(BCH_RECOVERY_PASS_check_topology)))) {
-			bch_err(c, "have key in journal replay for btree depth that does not exist, confused");
+			bch_err(c, "have key in journal replay for btree depth that does not exist, confused\n%s",
+				buf.buf);
 			ret = -EINVAL;
 		}
-#if 0
+
+		if (!k->allocated) {
+			bch_notice(c, "dropping key in journal replay for depth that does not exist because we're recovering from scan\n%s",
+				   buf.buf);
+			k->overwritten = true;
+			goto out;
+		}
+
 		bch2_trans_iter_exit(trans, &iter);
 		bch2_trans_node_iter_init(trans, &iter, k->btree_id, k->k->k.p,
 					  BTREE_MAX_DEPTH, 0, iter_flags);
 		ret =   bch2_btree_iter_traverse(trans, &iter) ?:
 			bch2_btree_increase_depth(trans, iter.path, 0) ?:
 			-BCH_ERR_transaction_restart_nested;
-#endif
-		k->overwritten = true;
 		goto out;
 	}
 

From c2b2c7d1da8f26c6db40de2bed142d66e238bd8a Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Thu, 3 Jul 2025 18:50:18 -0400
Subject: [PATCH 1173/1334] bcachefs: Tweak btree cache helpers for use by
 btree node scan

btree node scan needs to not use the btree node cache: that causes
interference from prior failed reads and parallel workers.

Instead we need to allocate btree nodes that don't live in the btree
cache, so that we can call bch2_btree_node_read_done() directly.

This patch tweaks the low level helpers so they don't touch the btree
cache lists.

Cc: Nikita Ofitserov <himikof@gmail.com>
Reviewed-by: Nikita Ofitserov <himikof@gmail.com>
Reported-and-tested-by: Edoardo Codeglia <bcachefs@404.blue>
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/btree_cache.c | 26 +++++++++++++-------------
 fs/bcachefs/btree_cache.h |  1 +
 fs/bcachefs/debug.c       |  2 --
 3 files changed, 14 insertions(+), 15 deletions(-)

diff --git a/fs/bcachefs/btree_cache.c b/fs/bcachefs/btree_cache.c
index 91e0aa796e6b..83c9860e6b82 100644
--- a/fs/bcachefs/btree_cache.c
+++ b/fs/bcachefs/btree_cache.c
@@ -85,7 +85,7 @@ void bch2_btree_node_to_freelist(struct bch_fs *c, struct btree *b)
 	six_unlock_intent(&b->c.lock);
 }
 
-static void __btree_node_data_free(struct btree_cache *bc, struct btree *b)
+void __btree_node_data_free(struct btree *b)
 {
 	BUG_ON(!list_empty(&b->list));
 	BUG_ON(btree_node_hashed(b));
@@ -112,16 +112,17 @@ static void __btree_node_data_free(struct btree_cache *bc, struct btree *b)
 	munmap(b->aux_data, btree_aux_data_bytes(b));
 #endif
 	b->aux_data = NULL;
-
-	btree_node_to_freedlist(bc, b);
 }
 
 static void btree_node_data_free(struct btree_cache *bc, struct btree *b)
 {
 	BUG_ON(list_empty(&b->list));
 	list_del_init(&b->list);
+
+	__btree_node_data_free(b);
+
 	--bc->nr_freeable;
-	__btree_node_data_free(bc, b);
+	btree_node_to_freedlist(bc, b);
 }
 
 static int bch2_btree_cache_cmp_fn(struct rhashtable_compare_arg *arg,
@@ -185,10 +186,7 @@ static struct btree *__btree_node_mem_alloc(struct bch_fs *c, gfp_t gfp)
 
 struct btree *__bch2_btree_node_mem_alloc(struct bch_fs *c)
 {
-	struct btree_cache *bc = &c->btree_cache;
-	struct btree *b;
-
-	b = __btree_node_mem_alloc(c, GFP_KERNEL);
+	struct btree *b = __btree_node_mem_alloc(c, GFP_KERNEL);
 	if (!b)
 		return NULL;
 
@@ -198,8 +196,6 @@ struct btree *__bch2_btree_node_mem_alloc(struct bch_fs *c)
 	}
 
 	bch2_btree_lock_init(&b->c, 0, GFP_KERNEL);
-
-	__bch2_btree_node_to_freelist(bc, b);
 	return b;
 }
 
@@ -524,7 +520,8 @@ restart:
 			--touched;;
 		} else if (!btree_node_reclaim(c, b)) {
 			__bch2_btree_node_hash_remove(bc, b);
-			__btree_node_data_free(bc, b);
+			__btree_node_data_free(b);
+			btree_node_to_freedlist(bc, b);
 
 			freed++;
 			bc->nr_freed++;
@@ -652,9 +649,12 @@ int bch2_fs_btree_cache_init(struct bch_fs *c)
 
 	bch2_recalc_btree_reserve(c);
 
-	for (i = 0; i < bc->nr_reserve; i++)
-		if (!__bch2_btree_node_mem_alloc(c))
+	for (i = 0; i < bc->nr_reserve; i++) {
+		struct btree *b = __bch2_btree_node_mem_alloc(c);
+		if (!b)
 			goto err;
+		__bch2_btree_node_to_freelist(bc, b);
+	}
 
 	list_splice_init(&bc->live[0].list, &bc->freeable);
 
diff --git a/fs/bcachefs/btree_cache.h b/fs/bcachefs/btree_cache.h
index ca3c1b145330..be275f87a60e 100644
--- a/fs/bcachefs/btree_cache.h
+++ b/fs/bcachefs/btree_cache.h
@@ -30,6 +30,7 @@ void bch2_btree_node_update_key_early(struct btree_trans *, enum btree_id, unsig
 void bch2_btree_cache_cannibalize_unlock(struct btree_trans *);
 int bch2_btree_cache_cannibalize_lock(struct btree_trans *, struct closure *);
 
+void __btree_node_data_free(struct btree *);
 struct btree *__bch2_btree_node_mem_alloc(struct bch_fs *);
 struct btree *bch2_btree_node_mem_alloc(struct btree_trans *, bool);
 
diff --git a/fs/bcachefs/debug.c b/fs/bcachefs/debug.c
index 901f643ead83..79d64052215c 100644
--- a/fs/bcachefs/debug.c
+++ b/fs/bcachefs/debug.c
@@ -153,8 +153,6 @@ void __bch2_btree_verify(struct bch_fs *c, struct btree *b)
 		c->verify_data = __bch2_btree_node_mem_alloc(c);
 		if (!c->verify_data)
 			goto out;
-
-		list_del_init(&c->verify_data->list);
 	}
 
 	BUG_ON(b->nsets != 1);

From 162c90154422e67c3b2dc209a4304a95e293cd58 Mon Sep 17 00:00:00 2001
From: Ofir Bitton <obitton@habana.ai>
Date: Mon, 29 Jul 2024 15:17:18 +0300
Subject: [PATCH 1174/1334] MAINTAINERS: Change habanalabs maintainer

I will be leaving Intel soon, Yaron Avizrat will take the role
of habanalabs driver maintainer.

Signed-off-by: Ofir Bitton <obitton@habana.ai>
Signed-off-by: Lukas Wunner <lukas@wunner.de>
Acked-by: Yaron Avizrat <yaron.avizrat@intel.com>
Acked-by: Jani Nikula <jani.nikula@intel.com>
Acked-by: Oded Gabbay <ogabbay@kernel.org>
Link: https://lore.kernel.org/r/20240729121718.540489-2-obitton@habana.ai
---
 MAINTAINERS | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index a92290fffa16..362e3ae900ee 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -10504,7 +10504,7 @@ S:	Maintained
 F:	block/partitions/efi.*
 
 HABANALABS PCI DRIVER
-M:	Ofir Bitton <obitton@habana.ai>
+M:	Yaron Avizrat <yaron.avizrat@intel.com>
 L:	dri-devel@lists.freedesktop.org
 S:	Supported
 C:	irc://irc.oftc.net/dri-devel

From 3d44147494385b245f021a3a3a5c1408be1d50d1 Mon Sep 17 00:00:00 2001
From: Tamir Duberstein <tamird@gmail.com>
Date: Fri, 4 Jul 2025 15:50:27 -0400
Subject: [PATCH 1175/1334] rust: drm: remove unnecessary imports

`kernel::str::CStr` is included in the prelude.

Signed-off-by: Tamir Duberstein <tamird@gmail.com>
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
Link: https://lore.kernel.org/r/20250704-cstr-include-drm-v1-1-a279dfc4d753@gmail.com
---
 drivers/gpu/drm/drm_panic_qr.rs | 2 +-
 rust/kernel/drm/driver.rs       | 1 -
 2 files changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/drm_panic_qr.rs b/drivers/gpu/drm/drm_panic_qr.rs
index dd55b1cb764d..18492daae4b3 100644
--- a/drivers/gpu/drm/drm_panic_qr.rs
+++ b/drivers/gpu/drm/drm_panic_qr.rs
@@ -27,7 +27,7 @@
 //! * <https://github.com/erwanvivien/fast_qr>
 //! * <https://github.com/bjguillot/qr>
 
-use kernel::{prelude::*, str::CStr};
+use kernel::prelude::*;
 
 #[derive(Debug, Clone, Copy, PartialEq, Eq, Ord, PartialOrd)]
 struct Version(usize);
diff --git a/rust/kernel/drm/driver.rs b/rust/kernel/drm/driver.rs
index acb638086131..af93d46d03d3 100644
--- a/rust/kernel/drm/driver.rs
+++ b/rust/kernel/drm/driver.rs
@@ -10,7 +10,6 @@ use crate::{
     drm,
     error::{to_result, Result},
     prelude::*,
-    str::CStr,
     types::ARef,
 };
 use macros::vtable;

From d67ed2ccd2d1dcfda9292c0ea8697a9d0f2f0d98 Mon Sep 17 00:00:00 2001
From: Wang Jinchao <wangjinchao600@gmail.com>
Date: Thu, 12 Jun 2025 19:28:40 +0800
Subject: [PATCH 1176/1334] md/raid1: Fix stack memory use after return in
 raid1_reshape

In the raid1_reshape function, newpool is
allocated on the stack and assigned to conf->r1bio_pool.
This results in conf->r1bio_pool.wait.head pointing
to a stack address.
Accessing this address later can lead to a kernel panic.

Example access path:

raid1_reshape()
{
	// newpool is on the stack
	mempool_t newpool, oldpool;
	// initialize newpool.wait.head to stack address
	mempool_init(&newpool, ...);
	conf->r1bio_pool = newpool;
}

raid1_read_request() or raid1_write_request()
{
	alloc_r1bio()
	{
		mempool_alloc()
		{
			// if pool->alloc fails
			remove_element()
			{
				--pool->curr_nr;
			}
		}
	}
}

mempool_free()
{
	if (pool->curr_nr < pool->min_nr) {
		// pool->wait.head is a stack address
		// wake_up() will try to access this invalid address
		// which leads to a kernel panic
		return;
		wake_up(&pool->wait);
	}
}

Fix:
reinit conf->r1bio_pool.wait after assigning newpool.

Fixes: afeee514ce7f ("md: convert to bioset_init()/mempool_init()")
Signed-off-by: Wang Jinchao <wangjinchao600@gmail.com>
Reviewed-by: Yu Kuai <yukuai3@huawei.com>
Link: https://lore.kernel.org/linux-raid/20250612112901.3023950-1-wangjinchao600@gmail.com
Signed-off-by: Yu Kuai <yukuai3@huawei.com>
---
 drivers/md/raid1.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 19c5a0ce5a40..fd4ce2a4136f 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -3428,6 +3428,7 @@ static int raid1_reshape(struct mddev *mddev)
 	/* ok, everything is stopped */
 	oldpool = conf->r1bio_pool;
 	conf->r1bio_pool = newpool;
+	init_waitqueue_head(&conf->r1bio_pool.wait);
 
 	for (d = d2 = 0; d < conf->raid_disks; d++) {
 		struct md_rdev *rdev = conf->mirrors[d].rdev;

From 43806c3d5b9bb7d74ba4e33a6a8a41ac988bde24 Mon Sep 17 00:00:00 2001
From: Nigel Croxon <ncroxon@redhat.com>
Date: Thu, 3 Jul 2025 11:23:04 -0400
Subject: [PATCH 1177/1334] raid10: cleanup memleak at raid10_make_request

If raid10_read_request or raid10_write_request registers a new
request and the REQ_NOWAIT flag is set, the code does not
free the malloc from the mempool.

unreferenced object 0xffff8884802c3200 (size 192):
   comm "fio", pid 9197, jiffies 4298078271
   hex dump (first 32 bytes):
     00 00 00 00 00 00 00 00 88 41 02 00 00 00 00 00  .........A......
     08 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
   backtrace (crc c1a049a2):
     __kmalloc+0x2bb/0x450
     mempool_alloc+0x11b/0x320
     raid10_make_request+0x19e/0x650 [raid10]
     md_handle_request+0x3b3/0x9e0
     __submit_bio+0x394/0x560
     __submit_bio_noacct+0x145/0x530
     submit_bio_noacct_nocheck+0x682/0x830
     __blkdev_direct_IO_async+0x4dc/0x6b0
     blkdev_read_iter+0x1e5/0x3b0
     __io_read+0x230/0x1110
     io_read+0x13/0x30
     io_issue_sqe+0x134/0x1180
     io_submit_sqes+0x48c/0xe90
     __do_sys_io_uring_enter+0x574/0x8b0
     do_syscall_64+0x5c/0xe0
     entry_SYSCALL_64_after_hwframe+0x76/0x7e

V4: changing backing tree to see if CKI tests will pass.
The patch code has not changed between any versions.

Fixes: c9aa889b035f ("md: raid10 add nowait support")
Signed-off-by: Nigel Croxon <ncroxon@redhat.com>
Link: https://lore.kernel.org/linux-raid/c0787379-9caa-42f3-b5fc-369aed784400@redhat.com
Signed-off-by: Yu Kuai <yukuai3@huawei.com>
---
 drivers/md/raid10.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index b74780af4c22..917055dc01ed 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -1182,8 +1182,11 @@ static void raid10_read_request(struct mddev *mddev, struct bio *bio,
 		}
 	}
 
-	if (!regular_request_wait(mddev, conf, bio, r10_bio->sectors))
+	if (!regular_request_wait(mddev, conf, bio, r10_bio->sectors)) {
+		raid_end_bio_io(r10_bio);
 		return;
+	}
+
 	rdev = read_balance(conf, r10_bio, &max_sectors);
 	if (!rdev) {
 		if (err_rdev) {
@@ -1370,8 +1373,11 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio,
 	}
 
 	sectors = r10_bio->sectors;
-	if (!regular_request_wait(mddev, conf, bio, sectors))
+	if (!regular_request_wait(mddev, conf, bio, sectors)) {
+		raid_end_bio_io(r10_bio);
 		return;
+	}
+
 	if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) &&
 	    (mddev->reshape_backwards
 	     ? (bio->bi_iter.bi_sector < conf->reshape_safe &&

From 5fa31c49928139fa948f078b094d80f12ed83f5f Mon Sep 17 00:00:00 2001
From: Zheng Qixing <zhengqixing@huawei.com>
Date: Wed, 2 Jul 2025 18:23:41 +0800
Subject: [PATCH 1178/1334] md/raid1,raid10: strip REQ_NOWAIT from member bios

RAID layers don't implement proper non-blocking semantics for
REQ_NOWAIT, making the flag potentially misleading when propagated
to member disks.

This patch clear REQ_NOWAIT from cloned bios in raid1/raid10. Retain
original bio's REQ_NOWAIT flag for upper layer error handling.

Maybe we can implement non-blocking I/O handling mechanisms within
RAID in future work.

Fixes: 9f346f7d4ea7 ("md/raid1,raid10: don't handle IO error for
REQ_RAHEAD and REQ_NOWAIT")
Signed-off-by: Zheng Qixing <zhengqixing@huawei.com>
Link: https://lore.kernel.org/linux-raid/20250702102341.1969154-1-zhengqixing@huaweicloud.com
Signed-off-by: Yu Kuai <yukuai3@huawei.com>
---
 drivers/md/raid1.c  | 3 ++-
 drivers/md/raid10.c | 2 ++
 2 files changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index fd4ce2a4136f..64b8176907a9 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -1399,7 +1399,7 @@ static void raid1_read_request(struct mddev *mddev, struct bio *bio,
 	}
 	read_bio = bio_alloc_clone(mirror->rdev->bdev, bio, gfp,
 				   &mddev->bio_set);
-
+	read_bio->bi_opf &= ~REQ_NOWAIT;
 	r1_bio->bios[rdisk] = read_bio;
 
 	read_bio->bi_iter.bi_sector = r1_bio->sector +
@@ -1649,6 +1649,7 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 				wait_for_serialization(rdev, r1_bio);
 		}
 
+		mbio->bi_opf &= ~REQ_NOWAIT;
 		r1_bio->bios[i] = mbio;
 
 		mbio->bi_iter.bi_sector	= (r1_bio->sector + rdev->data_offset);
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 917055dc01ed..c9bd2005bfd0 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -1224,6 +1224,7 @@ static void raid10_read_request(struct mddev *mddev, struct bio *bio,
 		r10_bio->master_bio = bio;
 	}
 	read_bio = bio_alloc_clone(rdev->bdev, bio, gfp, &mddev->bio_set);
+	read_bio->bi_opf &= ~REQ_NOWAIT;
 
 	r10_bio->devs[slot].bio = read_bio;
 	r10_bio->devs[slot].rdev = rdev;
@@ -1259,6 +1260,7 @@ static void raid10_write_one_disk(struct mddev *mddev, struct r10bio *r10_bio,
 			     conf->mirrors[devnum].rdev;
 
 	mbio = bio_alloc_clone(rdev->bdev, bio, GFP_NOIO, &mddev->bio_set);
+	mbio->bi_opf &= ~REQ_NOWAIT;
 	if (replacement)
 		r10_bio->devs[n_copy].repl_bio = mbio;
 	else

From c17fb542dbd1db745c9feac15617056506dd7195 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?H=C3=A5kon=20Bugge?= <haakon.bugge@oracle.com>
Date: Wed, 2 Jul 2025 11:10:34 +0200
Subject: [PATCH 1179/1334] md/md-bitmap: fix GPF in bitmap_get_stats()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The commit message of commit 6ec1f0239485 ("md/md-bitmap: fix stats
collection for external bitmaps") states:

    Remove the external bitmap check as the statistics should be
    available regardless of bitmap storage location.

    Return -EINVAL only for invalid bitmap with no storage (neither in
    superblock nor in external file).

But, the code does not adhere to the above, as it does only check for
a valid super-block for "internal" bitmaps. Hence, we observe:

Oops: GPF, probably for non-canonical address 0x1cd66f1f40000028
RIP: 0010:bitmap_get_stats+0x45/0xd0
Call Trace:

 seq_read_iter+0x2b9/0x46a
 seq_read+0x12f/0x180
 proc_reg_read+0x57/0xb0
 vfs_read+0xf6/0x380
 ksys_read+0x6d/0xf0
 do_syscall_64+0x8c/0x1b0
 entry_SYSCALL_64_after_hwframe+0x76/0x7e

We fix this by checking the existence of a super-block for both the
internal and external case.

Fixes: 6ec1f0239485 ("md/md-bitmap: fix stats collection for external bitmaps")
Cc: stable@vger.kernel.org
Reported-by: Gerald Gibson <gerald.gibson@oracle.com>
Signed-off-by: Håkon Bugge <haakon.bugge@oracle.com>
Link: https://lore.kernel.org/linux-raid/20250702091035.2061312-1-haakon.bugge@oracle.com
Signed-off-by: Yu Kuai <yukuai3@huawei.com>
---
 drivers/md/md-bitmap.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/md/md-bitmap.c b/drivers/md/md-bitmap.c
index bd694910b01b..7f524a26cebc 100644
--- a/drivers/md/md-bitmap.c
+++ b/drivers/md/md-bitmap.c
@@ -2366,8 +2366,7 @@ static int bitmap_get_stats(void *data, struct md_bitmap_stats *stats)
 
 	if (!bitmap)
 		return -ENOENT;
-	if (!bitmap->mddev->bitmap_info.external &&
-	    !bitmap->storage.sb_page)
+	if (!bitmap->storage.sb_page)
 		return -EINVAL;
 	sb = kmap_local_page(bitmap->storage.sb_page);
 	stats->sync_size = le64_to_cpu(sb->sync_size);

From a77ffbe34d450dd685e55ba942b025ded2517aff Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Thu, 3 Jul 2025 18:03:10 -0400
Subject: [PATCH 1180/1334] bcachefs: btree node scan no longer uses btree
 cache

Previously, btree node scan used the btree node cache to check if btree
nodes were readable, but this is subject to interference from threads
scanning different devices trying to read the same node - and more
critically, nodes that we already attempted and failed to read before
kicking off scan.

Instead, we now allocate a 'struct btree' that does not live in the
btree node cache, and call bch2_btree_node_read_done() directly.

Cc: Nikita Ofitserov <himikof@gmail.com>
Reviewed-by: Nikita Ofitserov <himikof@gmail.com>
Reported-and-tested-by: Edoardo Codeglia <bcachefs@404.blue>
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/btree_node_scan.c | 84 +++++++++++++++++------------------
 1 file changed, 41 insertions(+), 43 deletions(-)

diff --git a/fs/bcachefs/btree_node_scan.c b/fs/bcachefs/btree_node_scan.c
index 23d8c62ea4b6..42c9eb2c786e 100644
--- a/fs/bcachefs/btree_node_scan.c
+++ b/fs/bcachefs/btree_node_scan.c
@@ -75,39 +75,6 @@ static inline u64 bkey_journal_seq(struct bkey_s_c k)
 	}
 }
 
-static bool found_btree_node_is_readable(struct btree_trans *trans,
-					 struct found_btree_node *f)
-{
-	struct { __BKEY_PADDED(k, BKEY_BTREE_PTR_VAL_U64s_MAX); } tmp;
-
-	found_btree_node_to_key(&tmp.k, f);
-
-	struct btree *b = bch2_btree_node_get_noiter(trans, &tmp.k, f->btree_id, f->level, false);
-	bool ret = !IS_ERR_OR_NULL(b);
-	if (!ret)
-		return ret;
-
-	f->sectors_written = b->written;
-	f->journal_seq = le64_to_cpu(b->data->keys.journal_seq);
-
-	struct bkey_s_c k;
-	struct bkey unpacked;
-	struct btree_node_iter iter;
-	for_each_btree_node_key_unpack(b, k, &iter, &unpacked)
-		f->journal_seq = max(f->journal_seq, bkey_journal_seq(k));
-
-	six_unlock_read(&b->c.lock);
-
-	/*
-	 * We might update this node's range; if that happens, we need the node
-	 * to be re-read so the read path can trim keys that are no longer in
-	 * this node
-	 */
-	if (b != btree_node_root(trans->c, b))
-		bch2_btree_node_evict(trans, &tmp.k);
-	return ret;
-}
-
 static int found_btree_node_cmp_cookie(const void *_l, const void *_r)
 {
 	const struct found_btree_node *l = _l;
@@ -159,17 +126,17 @@ static const struct min_heap_callbacks found_btree_node_heap_cbs = {
 };
 
 static void try_read_btree_node(struct find_btree_nodes *f, struct bch_dev *ca,
-				struct bio *bio, struct btree_node *bn, u64 offset)
+				struct btree *b, struct bio *bio, u64 offset)
 {
 	struct bch_fs *c = container_of(f, struct bch_fs, found_btree_nodes);
+	struct btree_node *bn = b->data;
 
 	bio_reset(bio, ca->disk_sb.bdev, REQ_OP_READ);
 	bio->bi_iter.bi_sector	= offset;
-	bch2_bio_map(bio, bn, PAGE_SIZE);
+	bch2_bio_map(bio, b->data, c->opts.block_size);
 
 	u64 submit_time = local_clock();
 	submit_bio_wait(bio);
-
 	bch2_account_io_completion(ca, BCH_MEMBER_ERROR_read, submit_time, !bio->bi_status);
 
 	if (bio->bi_status) {
@@ -201,6 +168,14 @@ static void try_read_btree_node(struct find_btree_nodes *f, struct bch_dev *ca,
 	if (BTREE_NODE_ID(bn) >= BTREE_ID_NR_MAX)
 		return;
 
+	bio_reset(bio, ca->disk_sb.bdev, REQ_OP_READ);
+	bio->bi_iter.bi_sector	= offset;
+	bch2_bio_map(bio, b->data, c->opts.btree_node_size);
+
+	submit_time = local_clock();
+	submit_bio_wait(bio);
+	bch2_account_io_completion(ca, BCH_MEMBER_ERROR_read, submit_time, !bio->bi_status);
+
 	rcu_read_lock();
 	struct found_btree_node n = {
 		.btree_id	= BTREE_NODE_ID(bn),
@@ -217,7 +192,20 @@ static void try_read_btree_node(struct find_btree_nodes *f, struct bch_dev *ca,
 	};
 	rcu_read_unlock();
 
-	if (bch2_trans_run(c, found_btree_node_is_readable(trans, &n))) {
+	found_btree_node_to_key(&b->key, &n);
+
+	CLASS(printbuf, buf)();
+	if (!bch2_btree_node_read_done(c, ca, b, NULL, &buf)) {
+		/* read_done will swap out b->data for another buffer */
+		bn = b->data;
+		/*
+		 * Grab journal_seq here because we want the max journal_seq of
+		 * any bset; read_done sorts down to a single set and picks the
+		 * max journal_seq
+		 */
+		n.journal_seq		= le64_to_cpu(bn->keys.journal_seq),
+		n.sectors_written	= b->written;
+
 		mutex_lock(&f->lock);
 		if (BSET_BIG_ENDIAN(&bn->keys) != CPU_BIG_ENDIAN) {
 			bch_err(c, "try_read_btree_node() can't handle endian conversion");
@@ -237,12 +225,20 @@ static int read_btree_nodes_worker(void *p)
 	struct find_btree_nodes_worker *w = p;
 	struct bch_fs *c = container_of(w->f, struct bch_fs, found_btree_nodes);
 	struct bch_dev *ca = w->ca;
-	void *buf = (void *) __get_free_page(GFP_KERNEL);
-	struct bio *bio = bio_alloc(NULL, 1, 0, GFP_KERNEL);
 	unsigned long last_print = jiffies;
+	struct btree *b = NULL;
+	struct bio *bio = NULL;
 
-	if (!buf || !bio) {
-		bch_err(c, "read_btree_nodes_worker: error allocating bio/buf");
+	b = __bch2_btree_node_mem_alloc(c);
+	if (!b) {
+		bch_err(c, "read_btree_nodes_worker: error allocating buf");
+		w->f->ret = -ENOMEM;
+		goto err;
+	}
+
+	bio = bio_alloc(NULL, buf_pages(b->data, c->opts.btree_node_size), 0, GFP_KERNEL);
+	if (!bio) {
+		bch_err(c, "read_btree_nodes_worker: error allocating bio");
 		w->f->ret = -ENOMEM;
 		goto err;
 	}
@@ -266,11 +262,13 @@ static int read_btree_nodes_worker(void *p)
 			    !bch2_dev_btree_bitmap_marked_sectors(ca, sector, btree_sectors(c)))
 				continue;
 
-			try_read_btree_node(w->f, ca, bio, buf, sector);
+			try_read_btree_node(w->f, ca, b, bio, sector);
 		}
 err:
+	if (b)
+		__btree_node_data_free(b);
+	kfree(b);
 	bio_put(bio);
-	free_page((unsigned long) buf);
 	enumerated_ref_put(&ca->io_ref[READ], BCH_DEV_READ_REF_btree_node_scan);
 	closure_put(w->cl);
 	kfree(w);

From 14dd95647ea533c7d7c528b9bb7e163e433b47b9 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Thu, 3 Jul 2025 19:19:21 -0400
Subject: [PATCH 1181/1334] bcachefs: btree read retry fixes

Fix btree node read retries after validate errors:

__btree_err() is the wrong place to flag a topology error: that is done
by btree_lost_data().

Additionally, some calls to bch2_bkey_pick_read_device() were not
updated in the 6.16 rework for improved log messages; we were failing to
signal that we still had a retry.

Cc: Nikita Ofitserov <himikof@gmail.com>
Cc: Alan Huang <mmpgouride@gmail.com>
Reported-and-tested-by: Edoardo Codeglia <bcachefs@404.blue>
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/btree_io.c | 8 +++-----
 fs/bcachefs/errcode.h  | 1 -
 fs/bcachefs/error.c    | 2 +-
 3 files changed, 4 insertions(+), 7 deletions(-)

diff --git a/fs/bcachefs/btree_io.c b/fs/bcachefs/btree_io.c
index e874a4357f64..a4cc72986e36 100644
--- a/fs/bcachefs/btree_io.c
+++ b/fs/bcachefs/btree_io.c
@@ -568,9 +568,9 @@ static int __btree_err(int ret,
 		bch2_mark_btree_validate_failure(failed, ca->dev_idx);
 
 		struct extent_ptr_decoded pick;
-		have_retry = !bch2_bkey_pick_read_device(c,
+		have_retry = bch2_bkey_pick_read_device(c,
 					bkey_i_to_s_c(&b->key),
-					failed, &pick, -1);
+					failed, &pick, -1) == 1;
 	}
 
 	if (!have_retry && ret == -BCH_ERR_btree_node_read_err_want_retry)
@@ -615,7 +615,6 @@ static int __btree_err(int ret,
 			goto out;
 		case -BCH_ERR_btree_node_read_err_bad_node:
 			prt_str(&out, ", ");
-			ret = __bch2_topology_error(c, &out);
 			break;
 		}
 
@@ -644,7 +643,6 @@ static int __btree_err(int ret,
 		goto out;
 	case -BCH_ERR_btree_node_read_err_bad_node:
 		prt_str(&out, ", ");
-		ret = __bch2_topology_error(c, &out);
 		break;
 	}
 print:
@@ -1408,7 +1406,7 @@ static void btree_node_read_work(struct work_struct *work)
 		ret = bch2_bkey_pick_read_device(c,
 					bkey_i_to_s_c(&b->key),
 					&failed, &rb->pick, -1);
-		if (ret) {
+		if (ret <= 0) {
 			set_btree_node_read_error(b);
 			break;
 		}
diff --git a/fs/bcachefs/errcode.h b/fs/bcachefs/errcode.h
index 86a842f1e88e..acc3b7b67704 100644
--- a/fs/bcachefs/errcode.h
+++ b/fs/bcachefs/errcode.h
@@ -282,7 +282,6 @@
 	x(EIO,				sb_not_downgraded)			\
 	x(EIO,				btree_node_write_all_failed)		\
 	x(EIO,				btree_node_read_error)			\
-	x(EIO,				btree_node_read_validate_error)		\
 	x(EIO,				btree_need_topology_repair)		\
 	x(EIO,				bucket_ref_update)			\
 	x(EIO,				trigger_alloc)				\
diff --git a/fs/bcachefs/error.c b/fs/bcachefs/error.c
index b2a6c041e165..ea37f5af1800 100644
--- a/fs/bcachefs/error.c
+++ b/fs/bcachefs/error.c
@@ -103,7 +103,7 @@ int __bch2_topology_error(struct bch_fs *c, struct printbuf *out)
 		return bch_err_throw(c, btree_need_topology_repair);
 	} else {
 		return bch2_run_explicit_recovery_pass(c, out, BCH_RECOVERY_PASS_check_topology, 0) ?:
-			bch_err_throw(c, btree_node_read_validate_error);
+			bch_err_throw(c, btree_need_topology_repair);
 	}
 }
 

From 63a83463d278ea9f9eff7f58708322856e106d87 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Fri, 4 Jul 2025 12:18:02 -0400
Subject: [PATCH 1182/1334] bcachefs: Fix bch2_btree_transactions_read()
 synchronization

Since we're accessing btree_trans objects owned by another thread, we
need to guard against using pointers to freed key cache entries: we need
our own srcu read lock, and we should skip a btree_trans if it didn't
hold the srcu lock (and thus it might have pointers to freed key cache
entries).

00693 Mem abort info:
00693   ESR = 0x0000000096000005
00693   EC = 0x25: DABT (current EL), IL = 32 bits
00693   SET = 0, FnV = 0
00693   EA = 0, S1PTW = 0
00693   FSC = 0x05: level 1 translation fault
00693 Data abort info:
00693   ISV = 0, ISS = 0x00000005, ISS2 = 0x00000000
00693   CM = 0, WnR = 0, TnD = 0, TagAccess = 0
00693   GCS = 0, Overlay = 0, DirtyBit = 0, Xs = 0
00693 user pgtable: 4k pages, 39-bit VAs, pgdp=000000012e650000
00693 [000000008fb96218] pgd=0000000000000000, p4d=0000000000000000, pud=0000000000000000
00693 Internal error: Oops: 0000000096000005 [#1]  SMP
00693 Modules linked in:
00693 CPU: 0 UID: 0 PID: 4307 Comm: cat Not tainted 6.16.0-rc2-ktest-g9e15af94fd86 #27578 NONE
00693 Hardware name: linux,dummy-virt (DT)
00693 pstate: 60001005 (nZCv daif -PAN -UAO -TCO -DIT +SSBS BTYPE=--)
00693 pc : six_lock_counts+0x20/0xe8
00693 lr : bch2_btree_bkey_cached_common_to_text+0x38/0x130
00693 sp : ffffff80ca98bb60
00693 x29: ffffff80ca98bb60 x28: 000000008fb96200 x27: 0000000000000007
00693 x26: ffffff80eafd06b8 x25: 0000000000000000 x24: ffffffc080d75a60
00693 x23: ffffff80eafd0000 x22: ffffffc080bdfcc0 x21: ffffff80eafd0210
00693 x20: ffffff80c192ff08 x19: 000000008fb96200 x18: 00000000ffffffff
00693 x17: 0000000000000000 x16: 0000000000000000 x15: 00000000ffffffff
00693 x14: 0000000000000000 x13: ffffff80ceb5a29a x12: 20796220646c6568
00693 x11: 72205d3e303c5b20 x10: 0000000000000020 x9 : ffffffc0805fb6b0
00693 x8 : 0000000000000020 x7 : 0000000000000000 x6 : 0000000000000020
00693 x5 : ffffff80ceb5a29c x4 : 0000000000000001 x3 : 000000000000029c
00693 x2 : 0000000000000000 x1 : ffffff80ef66c000 x0 : 000000008fb96200
00693 Call trace:
00693  six_lock_counts+0x20/0xe8 (P)
00693  bch2_btree_bkey_cached_common_to_text+0x38/0x130
00693  bch2_btree_trans_to_text+0x260/0x2a8
00693  bch2_btree_transactions_read+0xac/0x1e8
00693  full_proxy_read+0x74/0xd8
00693  vfs_read+0x90/0x300
00693  ksys_read+0x6c/0x108
00693  __arm64_sys_read+0x20/0x30
00693  invoke_syscall.constprop.0+0x54/0xe8
00693  do_el0_svc+0x44/0xc8
00693  el0_svc+0x18/0x58
00693  el0t_64_sync_handler+0x104/0x130
00693  el0t_64_sync+0x154/0x158
00693 Code: 910003fd f9423c22 f90017e2 d2800002 (f9400c01)
00693 ---[ end trace 0000000000000000 ]---

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/debug.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/fs/bcachefs/debug.c b/fs/bcachefs/debug.c
index 79d64052215c..07c2a0f73cc2 100644
--- a/fs/bcachefs/debug.c
+++ b/fs/bcachefs/debug.c
@@ -584,6 +584,8 @@ static ssize_t bch2_btree_transactions_read(struct file *file, char __user *buf,
 	i->ubuf = buf;
 	i->size	= size;
 	i->ret	= 0;
+
+	int srcu_idx = srcu_read_lock(&c->btree_trans_barrier);
 restart:
 	seqmutex_lock(&c->btree_trans_lock);
 	list_sort(&c->btree_trans_list, list_ptr_order_cmp);
@@ -597,6 +599,11 @@ restart:
 		if (!closure_get_not_zero(&trans->ref))
 			continue;
 
+		if (!trans->srcu_held) {
+			closure_put(&trans->ref);
+			continue;
+		}
+
 		u32 seq = seqmutex_unlock(&c->btree_trans_lock);
 
 		bch2_btree_trans_to_text(&i->buf, trans);
@@ -618,6 +625,8 @@ restart:
 	}
 	seqmutex_unlock(&c->btree_trans_lock);
 unlocked:
+	srcu_read_unlock(&c->btree_trans_barrier, srcu_idx);
+
 	if (i->buf.allocation_failure)
 		ret = -ENOMEM;
 

From 46b0a67e8f22d2dbc679b37b26c5ff0f50424847 Mon Sep 17 00:00:00 2001
From: Terry Tritton <terry.tritton@linaro.org>
Date: Fri, 4 Jul 2025 11:37:49 +0100
Subject: [PATCH 1183/1334] selftests/futex: Add futex_numa to .gitignore
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

futex_numa was never added to the .gitignore file.
Add it.

Fixes: 9140f57c1c13 ("futex,selftests: Add another FUTEX2_NUMA selftest")
Signed-off-by: Terry Tritton <terry.tritton@linaro.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: André Almeida <andrealmeid@igalia.com>
Link: https://lore.kernel.org/all/20250704103749.10341-1-terry.tritton@linaro.org
---
 tools/testing/selftests/futex/functional/.gitignore | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/testing/selftests/futex/functional/.gitignore b/tools/testing/selftests/futex/functional/.gitignore
index 7b24ae89594a..776ad658f75e 100644
--- a/tools/testing/selftests/futex/functional/.gitignore
+++ b/tools/testing/selftests/futex/functional/.gitignore
@@ -11,3 +11,4 @@ futex_wait_timeout
 futex_wait_uninitialized_heap
 futex_wait_wouldblock
 futex_waitv
+futex_numa

From d7b8f8e20813f0179d8ef519541a3527e7661d3a Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Sun, 6 Jul 2025 14:10:26 -0700
Subject: [PATCH 1184/1334] Linux 6.16-rc5

---
 Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Makefile b/Makefile
index 1c9ea229809f..7eea2a41c905 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
 VERSION = 6
 PATCHLEVEL = 16
 SUBLEVEL = 0
-EXTRAVERSION = -rc4
+EXTRAVERSION = -rc5
 NAME = Baby Opossum Posse
 
 # *DOCUMENTATION*

From 9ee124caae1b0defd0e02c65686f539845a3ac9b Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@baylibre.com>
Date: Fri, 4 Jul 2025 19:24:17 +0200
Subject: [PATCH 1185/1334] pwm: Fix invalid state detection
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Commit 9dd42d019e63 ("pwm: Allow pwm state transitions from an invalid
state") intended to allow some state transitions that were not allowed
before. The idea is sane and back then I also got the code comment
right, but the check for enabled is bogus. This resulted in state
transitions for enabled states to be allowed to have invalid duty/period
settings and thus it can happen that low-level drivers get requests for
invalid states🙄.

Invert the check to allow state transitions for disabled states only.

Fixes: 9dd42d019e63 ("pwm: Allow pwm state transitions from an invalid state")
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@baylibre.com>
Link: https://lore.kernel.org/r/20250704172416.626433-2-u.kleine-koenig@baylibre.com
Cc: stable@vger.kernel.org
Signed-off-by: Uwe Kleine-König <ukleinek@kernel.org>
---
 drivers/pwm/core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/pwm/core.c b/drivers/pwm/core.c
index 4d842c692194..edf776b8ad53 100644
--- a/drivers/pwm/core.c
+++ b/drivers/pwm/core.c
@@ -596,7 +596,7 @@ static bool pwm_state_valid(const struct pwm_state *state)
 	 * and supposed to be ignored. So also ignore any strange values and
 	 * consider the state ok.
 	 */
-	if (state->enabled)
+	if (!state->enabled)
 		return true;
 
 	if (!state->period)

From 505b730ede7f5c4083ff212aa955155b5b92e574 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= <u.kleine-koenig@baylibre.com>
Date: Fri, 4 Jul 2025 19:27:27 +0200
Subject: [PATCH 1186/1334] pwm: mediatek: Ensure to disable clocks in error
 path
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

After enabling the clocks each error path must disable the clocks again.
One of them failed to do so. Unify the error paths to use goto to make it
harder for future changes to add a similar bug.

Fixes: 7ca59947b5fc ("pwm: mediatek: Prevent divide-by-zero in pwm_mediatek_config()")
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@baylibre.com>
Link: https://lore.kernel.org/r/20250704172728.626815-2-u.kleine-koenig@baylibre.com
Cc: stable@vger.kernel.org
Signed-off-by: Uwe Kleine-König <ukleinek@kernel.org>
---
 drivers/pwm/pwm-mediatek.c | 13 ++++++++-----
 1 file changed, 8 insertions(+), 5 deletions(-)

diff --git a/drivers/pwm/pwm-mediatek.c b/drivers/pwm/pwm-mediatek.c
index 7eaab5831499..33d3554b9197 100644
--- a/drivers/pwm/pwm-mediatek.c
+++ b/drivers/pwm/pwm-mediatek.c
@@ -130,8 +130,10 @@ static int pwm_mediatek_config(struct pwm_chip *chip, struct pwm_device *pwm,
 		return ret;
 
 	clk_rate = clk_get_rate(pc->clk_pwms[pwm->hwpwm]);
-	if (!clk_rate)
-		return -EINVAL;
+	if (!clk_rate) {
+		ret = -EINVAL;
+		goto out;
+	}
 
 	/* Make sure we use the bus clock and not the 26MHz clock */
 	if (pc->soc->has_ck_26m_sel)
@@ -150,9 +152,9 @@ static int pwm_mediatek_config(struct pwm_chip *chip, struct pwm_device *pwm,
 	}
 
 	if (clkdiv > PWM_CLK_DIV_MAX) {
-		pwm_mediatek_clk_disable(chip, pwm);
 		dev_err(pwmchip_parent(chip), "period of %d ns not supported\n", period_ns);
-		return -EINVAL;
+		ret = -EINVAL;
+		goto out;
 	}
 
 	if (pc->soc->pwm45_fixup && pwm->hwpwm > 2) {
@@ -169,9 +171,10 @@ static int pwm_mediatek_config(struct pwm_chip *chip, struct pwm_device *pwm,
 	pwm_mediatek_writel(pc, pwm->hwpwm, reg_width, cnt_period);
 	pwm_mediatek_writel(pc, pwm->hwpwm, reg_thres, cnt_duty);
 
+out:
 	pwm_mediatek_clk_disable(chip, pwm);
 
-	return 0;
+	return ret;
 }
 
 static int pwm_mediatek_enable(struct pwm_chip *chip, struct pwm_device *pwm)

From c5fd399a24c8e2865524361f7dc4d4a6899be4f4 Mon Sep 17 00:00:00 2001
From: Lachlan Hodges <lachlan.hodges@morsemicro.com>
Date: Tue, 1 Jul 2025 17:55:41 +1000
Subject: [PATCH 1187/1334] wifi: mac80211: correctly identify S1G short beacon

mac80211 identifies a short beacon by the presence of the next
TBTT field, however the standard actually doesn't explicitly state that
the next TBTT can't be in a long beacon or even that it is required in
a short beacon - and as a result this validation does not work for all
vendor implementations.

The standard explicitly states that an S1G long beacon shall contain
the S1G beacon compatibility element as the first element in a beacon
transmitted at a TBTT that is not a TSBTT (Target Short Beacon
Transmission Time) as per IEEE80211-2024 11.1.3.10.1. This is validated
by 9.3.4.3 Table 9-76 which states that the S1G beacon compatibility
element is only allowed in the full set and is not allowed in the
minimum set of elements permitted for use within short beacons.

Correctly identify short beacons by the lack of an S1G beacon
compatibility element as the first element in an S1G beacon frame.

Fixes: 9eaffe5078ca ("cfg80211: convert S1G beacon to scan results")
Signed-off-by: Simon Wadsworth <simon@morsemicro.com>
Signed-off-by: Lachlan Hodges <lachlan.hodges@morsemicro.com>
Link: https://patch.msgid.link/20250701075541.162619-1-lachlan.hodges@morsemicro.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/linux/ieee80211.h | 45 ++++++++++++++++++++++++++++-----------
 net/mac80211/mlme.c       |  7 ++++--
 2 files changed, 38 insertions(+), 14 deletions(-)

diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index 22f39e5e2ff1..996be3c2cff0 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -662,18 +662,6 @@ static inline bool ieee80211_s1g_has_cssid(__le16 fc)
 		(fc & cpu_to_le16(IEEE80211_S1G_BCN_CSSID));
 }
 
-/**
- * ieee80211_is_s1g_short_beacon - check if frame is an S1G short beacon
- * @fc: frame control bytes in little-endian byteorder
- * Return: whether or not the frame is an S1G short beacon,
- *	i.e. it is an S1G beacon with 'next TBTT' flag set
- */
-static inline bool ieee80211_is_s1g_short_beacon(__le16 fc)
-{
-	return ieee80211_is_s1g_beacon(fc) &&
-		(fc & cpu_to_le16(IEEE80211_S1G_BCN_NEXT_TBTT));
-}
-
 /**
  * ieee80211_is_atim - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_ATIM
  * @fc: frame control bytes in little-endian byteorder
@@ -4901,6 +4889,39 @@ static inline bool ieee80211_is_ftm(struct sk_buff *skb)
 	return false;
 }
 
+/**
+ * ieee80211_is_s1g_short_beacon - check if frame is an S1G short beacon
+ * @fc: frame control bytes in little-endian byteorder
+ * @variable: pointer to the beacon frame elements
+ * @variable_len: length of the frame elements
+ * Return: whether or not the frame is an S1G short beacon. As per
+ *	IEEE80211-2024 11.1.3.10.1, The S1G beacon compatibility element shall
+ *	always be present as the first element in beacon frames generated at a
+ *	TBTT (Target Beacon Transmission Time), so any frame not containing
+ *	this element must have been generated at a TSBTT (Target Short Beacon
+ *	Transmission Time) that is not a TBTT. Additionally, short beacons are
+ *	prohibited from containing the S1G beacon compatibility element as per
+ *	IEEE80211-2024 9.3.4.3 Table 9-76, so if we have an S1G beacon with
+ *	either no elements or the first element is not the beacon compatibility
+ *	element, we have a short beacon.
+ */
+static inline bool ieee80211_is_s1g_short_beacon(__le16 fc, const u8 *variable,
+						 size_t variable_len)
+{
+	if (!ieee80211_is_s1g_beacon(fc))
+		return false;
+
+	/*
+	 * If the frame does not contain at least 1 element (this is perfectly
+	 * valid in a short beacon) and is an S1G beacon, we have a short
+	 * beacon.
+	 */
+	if (variable_len < 2)
+		return true;
+
+	return variable[0] != WLAN_EID_S1G_BCN_COMPAT;
+}
+
 struct element {
 	u8 id;
 	u8 datalen;
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 2d46d4af60d7..7ddb8e77b4c7 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -7195,6 +7195,7 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_link_data *link,
 	struct ieee80211_bss_conf *bss_conf = link->conf;
 	struct ieee80211_vif_cfg *vif_cfg = &sdata->vif.cfg;
 	struct ieee80211_mgmt *mgmt = (void *) hdr;
+	struct ieee80211_ext *ext = NULL;
 	size_t baselen;
 	struct ieee802_11_elems *elems;
 	struct ieee80211_local *local = sdata->local;
@@ -7220,7 +7221,7 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_link_data *link,
 	/* Process beacon from the current BSS */
 	bssid = ieee80211_get_bssid(hdr, len, sdata->vif.type);
 	if (ieee80211_is_s1g_beacon(mgmt->frame_control)) {
-		struct ieee80211_ext *ext = (void *) mgmt;
+		ext = (void *)mgmt;
 		variable = ext->u.s1g_beacon.variable +
 			   ieee80211_s1g_optional_len(ext->frame_control);
 	}
@@ -7407,7 +7408,9 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_link_data *link,
 	}
 
 	if ((ncrc == link->u.mgd.beacon_crc && link->u.mgd.beacon_crc_valid) ||
-	    ieee80211_is_s1g_short_beacon(mgmt->frame_control))
+	    (ext && ieee80211_is_s1g_short_beacon(ext->frame_control,
+						  parse_params.start,
+						  parse_params.len)))
 		goto free;
 	link->u.mgd.beacon_crc = ncrc;
 	link->u.mgd.beacon_crc_valid = true;

From 8af596e8ae44c3bcf36d1aea09fc9a6f17c555e5 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Tue, 1 Jul 2025 09:22:13 +0200
Subject: [PATCH 1188/1334] wifi: mac80211: clear frame buffer to never leak
 stack

In disconnect paths paths, local frame buffers are used
to build deauthentication frames to send them over the
air and as notifications to userspace. Some internal
error paths (that, given no other bugs, cannot happen)
don't always initialize the buffers before sending them
to userspace, so in the presence of other bugs they can
leak stack content. Initialize the buffers to avoid the
possibility of this happening.

Suggested-by: Zhongqiu Han <quic_zhonhan@quicinc.com>
Link: https://patch.msgid.link/20250701072213.13004-2-johannes@sipsolutions.net
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/mlme.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 7ddb8e77b4c7..d26dcee5683a 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -3934,6 +3934,9 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata,
 
 	lockdep_assert_wiphy(local->hw.wiphy);
 
+	if (frame_buf)
+		memset(frame_buf, 0, IEEE80211_DEAUTH_FRAME_LEN);
+
 	if (WARN_ON(!ap_sta))
 		return;
 

From e1e6ebf490e55fee1ae573aa443c1d4aea5e4a40 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Mon, 30 Jun 2025 15:45:01 +0200
Subject: [PATCH 1189/1334] wifi: mac80211: fix non-transmitted BSSID profile
 search

When the non-transmitted BSSID profile is found, immediately return
from the search to not return the wrong profile_len when the profile
is found in a multiple BSSID element that isn't the last one in the
frame.

Fixes: 5023b14cf4df ("mac80211: support profile split between elements")
Reported-by: Michael-CY Lee <michael-cy.lee@mediatek.com>
Link: https://patch.msgid.link/20250630154501.f26cd45a0ecd.I28e0525d06e8a99e555707301bca29265cf20dc8@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/parse.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/net/mac80211/parse.c b/net/mac80211/parse.c
index 96584b39215e..c5e0f7f46004 100644
--- a/net/mac80211/parse.c
+++ b/net/mac80211/parse.c
@@ -758,7 +758,6 @@ static size_t ieee802_11_find_bssid_profile(const u8 *start, size_t len,
 {
 	const struct element *elem, *sub;
 	size_t profile_len = 0;
-	bool found = false;
 
 	if (!bss || !bss->transmitted_bss)
 		return profile_len;
@@ -809,15 +808,14 @@ static size_t ieee802_11_find_bssid_profile(const u8 *start, size_t len,
 					       index[2],
 					       new_bssid);
 			if (ether_addr_equal(new_bssid, bss->bssid)) {
-				found = true;
 				elems->bssid_index_len = index[1];
 				elems->bssid_index = (void *)&index[2];
-				break;
+				return profile_len;
 			}
 		}
 	}
 
-	return found ? profile_len : 0;
+	return 0;
 }
 
 static void

From 3b602ddc0df723992721b0d286c90c9bdd755b34 Mon Sep 17 00:00:00 2001
From: Vitor Soares <vitor.soares@toradex.com>
Date: Tue, 1 Jul 2025 15:26:43 +0100
Subject: [PATCH 1190/1334] wifi: mwifiex: discard erroneous disassoc frames on
 STA interface

When operating in concurrent STA/AP mode with host MLME enabled,
the firmware incorrectly sends disassociation frames to the STA
interface when clients disconnect from the AP interface.
This causes kernel warnings as the STA interface processes
disconnect events that don't apply to it:

[ 1303.240540] WARNING: CPU: 0 PID: 513 at net/wireless/mlme.c:141 cfg80211_process_disassoc+0x78/0xec [cfg80211]
[ 1303.250861] Modules linked in: 8021q garp stp mrp llc rfcomm bnep btnxpuart nls_iso8859_1 nls_cp437 onboard_us
[ 1303.327651] CPU: 0 UID: 0 PID: 513 Comm: kworker/u9:2 Not tainted 6.16.0-rc1+ #3 PREEMPT
[ 1303.335937] Hardware name: Toradex Verdin AM62 WB on Verdin Development Board (DT)
[ 1303.343588] Workqueue: MWIFIEX_RX_WORK_QUEUE mwifiex_rx_work_queue [mwifiex]
[ 1303.350856] pstate: 60000005 (nZCv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--)
[ 1303.357904] pc : cfg80211_process_disassoc+0x78/0xec [cfg80211]
[ 1303.364065] lr : cfg80211_process_disassoc+0x70/0xec [cfg80211]
[ 1303.370221] sp : ffff800083053be0
[ 1303.373590] x29: ffff800083053be0 x28: 0000000000000000 x27: 0000000000000000
[ 1303.380855] x26: 0000000000000000 x25: 00000000ffffffff x24: ffff000002c5b8ae
[ 1303.388120] x23: ffff000002c5b884 x22: 0000000000000001 x21: 0000000000000008
[ 1303.395382] x20: ffff000002c5b8ae x19: ffff0000064dd408 x18: 0000000000000006
[ 1303.402646] x17: 3a36333a61623a30 x16: 32206d6f72662063 x15: ffff800080bfe048
[ 1303.409910] x14: ffff000003625300 x13: 0000000000000001 x12: 0000000000000000
[ 1303.417173] x11: 0000000000000002 x10: ffff000003958600 x9 : ffff000003625300
[ 1303.424434] x8 : ffff00003fd9ef40 x7 : ffff0000039fc280 x6 : 0000000000000002
[ 1303.431695] x5 : ffff0000038976d4 x4 : 0000000000000000 x3 : 0000000000003186
[ 1303.438956] x2 : 000000004836ba20 x1 : 0000000000006986 x0 : 00000000d00479de
[ 1303.446221] Call trace:
[ 1303.448722]  cfg80211_process_disassoc+0x78/0xec [cfg80211] (P)
[ 1303.454894]  cfg80211_rx_mlme_mgmt+0x64/0xf8 [cfg80211]
[ 1303.460362]  mwifiex_process_mgmt_packet+0x1ec/0x460 [mwifiex]
[ 1303.466380]  mwifiex_process_sta_rx_packet+0x1bc/0x2a0 [mwifiex]
[ 1303.472573]  mwifiex_handle_rx_packet+0xb4/0x13c [mwifiex]
[ 1303.478243]  mwifiex_rx_work_queue+0x158/0x198 [mwifiex]
[ 1303.483734]  process_one_work+0x14c/0x28c
[ 1303.487845]  worker_thread+0x2cc/0x3d4
[ 1303.491680]  kthread+0x12c/0x208
[ 1303.495014]  ret_from_fork+0x10/0x20

Add validation in the STA receive path to verify that disassoc/deauth
frames originate from the connected AP. Frames that fail this check
are discarded early, preventing them from reaching the MLME layer and
triggering WARN_ON().

This filtering logic is similar with that used in the
ieee80211_rx_mgmt_disassoc() function in mac80211, which drops
disassoc frames that don't match the current BSSID
(!ether_addr_equal(mgmt->bssid, sdata->vif.cfg.ap_addr)), ensuring
only relevant frames are processed.

Tested on:
- 8997 with FW 16.68.1.p197

Fixes: 36995892c271 ("wifi: mwifiex: add host mlme for client mode")
Cc: stable@vger.kernel.org
Signed-off-by: Vitor Soares <vitor.soares@toradex.com>
Reviewed-by: Jeff Chen <jeff.chen_1@nxp.con>
Reviewed-by: Francesco Dolcini <francesco.dolcini@toradex.com>
Link: https://patch.msgid.link/20250701142643.658990-1-ivitro@gmail.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/marvell/mwifiex/util.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/marvell/mwifiex/util.c b/drivers/net/wireless/marvell/mwifiex/util.c
index 4c5b1de0e936..6882e90e90b2 100644
--- a/drivers/net/wireless/marvell/mwifiex/util.c
+++ b/drivers/net/wireless/marvell/mwifiex/util.c
@@ -459,7 +459,9 @@ mwifiex_process_mgmt_packet(struct mwifiex_private *priv,
 				    "auth: receive authentication from %pM\n",
 				    ieee_hdr->addr3);
 		} else {
-			if (!priv->wdev.connected)
+			if (!priv->wdev.connected ||
+			    !ether_addr_equal(ieee_hdr->addr3,
+					      priv->curr_bss_params.bss_descriptor.mac_address))
 				return 0;
 
 			if (ieee80211_is_deauth(ieee_hdr->frame_control)) {

From 58fcb1b4287ce38850402bb2bb16d09bf77b91d9 Mon Sep 17 00:00:00 2001
From: Moon Hee Lee <moonhee.lee.ca@gmail.com>
Date: Thu, 3 Jul 2025 12:37:57 -0700
Subject: [PATCH 1191/1334] wifi: mac80211: reject VHT opmode for unsupported
 channel widths

VHT operating mode notifications are not defined for channel widths
below 20 MHz. In particular, 5 MHz and 10 MHz are not valid under the
VHT specification and must be rejected.

Without this check, malformed notifications using these widths may
reach ieee80211_chan_width_to_rx_bw(), leading to a WARN_ON due to
invalid input. This issue was reported by syzbot.

Reject these unsupported widths early in sta_link_apply_parameters()
when opmode_notif is used. The accepted set includes 20, 40, 80, 160,
and 80+80 MHz, which are valid for VHT. While 320 MHz is not defined
for VHT, it is allowed to avoid rejecting HE or EHT clients that may
still send a VHT opmode notification.

Reported-by: syzbot+ededba317ddeca8b3f08@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=ededba317ddeca8b3f08
Fixes: 751e7489c1d7 ("wifi: mac80211: expose ieee80211_chan_width_to_rx_bw() to drivers")
Tested-by: syzbot+ededba317ddeca8b3f08@syzkaller.appspotmail.com
Signed-off-by: Moon Hee Lee <moonhee.lee.ca@gmail.com>
Link: https://patch.msgid.link/20250703193756.46622-2-moonhee.lee.ca@gmail.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/cfg.c | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index d9d88f2f2831..954795b0fe48 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -1959,6 +1959,20 @@ static int sta_link_apply_parameters(struct ieee80211_local *local,
 	ieee80211_sta_init_nss(link_sta);
 
 	if (params->opmode_notif_used) {
+		enum nl80211_chan_width width = link->conf->chanreq.oper.width;
+
+		switch (width) {
+		case NL80211_CHAN_WIDTH_20:
+		case NL80211_CHAN_WIDTH_40:
+		case NL80211_CHAN_WIDTH_80:
+		case NL80211_CHAN_WIDTH_160:
+		case NL80211_CHAN_WIDTH_80P80:
+		case NL80211_CHAN_WIDTH_320: /* not VHT, allowed for HE/EHT */
+			break;
+		default:
+			return -EINVAL;
+		}
+
 		/* returned value is only needed for rc update, but the
 		 * rc isn't initialized here yet, so ignore it
 		 */

From 2ce6ad9262256dd345cb104ba0ac6cf4aeed25a3 Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Sun, 6 Jul 2025 11:20:53 +0200
Subject: [PATCH 1192/1334] wifi: rt2x00: fix remove callback type mismatch

The function is used as remove callback for a platform driver.
It was missed during the conversion from int to void

Fixes: 0edb555a65d1 ("platform: Make platform_driver::remove() return void")
Signed-off-by: Felix Fietkau <nbd@nbd.name>
Link: https://patch.msgid.link/20250706092053.97724-1-nbd@nbd.name
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/ralink/rt2x00/rt2x00soc.c | 4 +---
 drivers/net/wireless/ralink/rt2x00/rt2x00soc.h | 2 +-
 2 files changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/net/wireless/ralink/rt2x00/rt2x00soc.c b/drivers/net/wireless/ralink/rt2x00/rt2x00soc.c
index eface610178d..f7f3a2340c39 100644
--- a/drivers/net/wireless/ralink/rt2x00/rt2x00soc.c
+++ b/drivers/net/wireless/ralink/rt2x00/rt2x00soc.c
@@ -108,7 +108,7 @@ exit_free_device:
 }
 EXPORT_SYMBOL_GPL(rt2x00soc_probe);
 
-int rt2x00soc_remove(struct platform_device *pdev)
+void rt2x00soc_remove(struct platform_device *pdev)
 {
 	struct ieee80211_hw *hw = platform_get_drvdata(pdev);
 	struct rt2x00_dev *rt2x00dev = hw->priv;
@@ -119,8 +119,6 @@ int rt2x00soc_remove(struct platform_device *pdev)
 	rt2x00lib_remove_dev(rt2x00dev);
 	rt2x00soc_free_reg(rt2x00dev);
 	ieee80211_free_hw(hw);
-
-	return 0;
 }
 EXPORT_SYMBOL_GPL(rt2x00soc_remove);
 
diff --git a/drivers/net/wireless/ralink/rt2x00/rt2x00soc.h b/drivers/net/wireless/ralink/rt2x00/rt2x00soc.h
index 021fd06b3627..d6226b8a10e0 100644
--- a/drivers/net/wireless/ralink/rt2x00/rt2x00soc.h
+++ b/drivers/net/wireless/ralink/rt2x00/rt2x00soc.h
@@ -17,7 +17,7 @@
  * SoC driver handlers.
  */
 int rt2x00soc_probe(struct platform_device *pdev, const struct rt2x00_ops *ops);
-int rt2x00soc_remove(struct platform_device *pdev);
+void rt2x00soc_remove(struct platform_device *pdev);
 #ifdef CONFIG_PM
 int rt2x00soc_suspend(struct platform_device *pdev, pm_message_t state);
 int rt2x00soc_resume(struct platform_device *pdev);

From 737bb912ebbe4571195c56eba557c4d7315b26fb Mon Sep 17 00:00:00 2001
From: Mathy Vanhoef <Mathy.Vanhoef@kuleuven.be>
Date: Mon, 16 Jun 2025 02:46:35 +0200
Subject: [PATCH 1193/1334] wifi: prevent A-MSDU attacks in mesh networks

This patch is a mitigation to prevent the A-MSDU spoofing vulnerability
for mesh networks. The initial update to the IEEE 802.11 standard, in
response to the FragAttacks, missed this case (CVE-2025-27558). It can
be considered a variant of CVE-2020-24588 but for mesh networks.

This patch tries to detect if a standard MSDU was turned into an A-MSDU
by an adversary. This is done by parsing a received A-MSDU as a standard
MSDU, calculating the length of the Mesh Control header, and seeing if
the 6 bytes after this header equal the start of an rfc1042 header. If
equal, this is a strong indication of an ongoing attack attempt.

This defense was tested with mac80211_hwsim against a mesh network that
uses an empty Mesh Address Extension field, i.e., when four addresses
are used, and when using a 12-byte Mesh Address Extension field, i.e.,
when six addresses are used. Functionality of normal MSDUs and A-MSDUs
was also tested, and confirmed working, when using both an empty and
12-byte Mesh Address Extension field.

It was also tested with mac80211_hwsim that A-MSDU attacks in non-mesh
networks keep being detected and prevented.

Note that the vulnerability being patched, and the defense being
implemented, was also discussed in the following paper and in the
following IEEE 802.11 presentation:

https://papers.mathyvanhoef.com/wisec2025.pdf
https://mentor.ieee.org/802.11/dcn/25/11-25-0949-00-000m-a-msdu-mesh-spoof-protection.docx

Cc: stable@vger.kernel.org
Signed-off-by: Mathy Vanhoef <Mathy.Vanhoef@kuleuven.be>
Link: https://patch.msgid.link/20250616004635.224344-1-Mathy.Vanhoef@kuleuven.be
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/wireless/util.c | 52 +++++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 50 insertions(+), 2 deletions(-)

diff --git a/net/wireless/util.c b/net/wireless/util.c
index ed868c0f7ca8..1ad5a6bdfd75 100644
--- a/net/wireless/util.c
+++ b/net/wireless/util.c
@@ -820,6 +820,52 @@ bool ieee80211_is_valid_amsdu(struct sk_buff *skb, u8 mesh_hdr)
 }
 EXPORT_SYMBOL(ieee80211_is_valid_amsdu);
 
+
+/*
+ * Detects if an MSDU frame was maliciously converted into an A-MSDU
+ * frame by an adversary. This is done by parsing the received frame
+ * as if it were a regular MSDU, even though the A-MSDU flag is set.
+ *
+ * For non-mesh interfaces, detection involves checking whether the
+ * payload, when interpreted as an MSDU, begins with a valid RFC1042
+ * header. This is done by comparing the A-MSDU subheader's destination
+ * address to the start of the RFC1042 header.
+ *
+ * For mesh interfaces, the MSDU includes a 6-byte Mesh Control field
+ * and an optional variable-length Mesh Address Extension field before
+ * the RFC1042 header. The position of the RFC1042 header must therefore
+ * be calculated based on the mesh header length.
+ *
+ * Since this function intentionally parses an A-MSDU frame as an MSDU,
+ * it only assumes that the A-MSDU subframe header is present, and
+ * beyond this it performs its own bounds checks under the assumption
+ * that the frame is instead parsed as a non-aggregated MSDU.
+ */
+static bool
+is_amsdu_aggregation_attack(struct ethhdr *eth, struct sk_buff *skb,
+			    enum nl80211_iftype iftype)
+{
+	int offset;
+
+	/* Non-mesh case can be directly compared */
+	if (iftype != NL80211_IFTYPE_MESH_POINT)
+		return ether_addr_equal(eth->h_dest, rfc1042_header);
+
+	offset = __ieee80211_get_mesh_hdrlen(eth->h_dest[0]);
+	if (offset == 6) {
+		/* Mesh case with empty address extension field */
+		return ether_addr_equal(eth->h_source, rfc1042_header);
+	} else if (offset + ETH_ALEN <= skb->len) {
+		/* Mesh case with non-empty address extension field */
+		u8 temp[ETH_ALEN];
+
+		skb_copy_bits(skb, offset, temp, ETH_ALEN);
+		return ether_addr_equal(temp, rfc1042_header);
+	}
+
+	return false;
+}
+
 void ieee80211_amsdu_to_8023s(struct sk_buff *skb, struct sk_buff_head *list,
 			      const u8 *addr, enum nl80211_iftype iftype,
 			      const unsigned int extra_headroom,
@@ -861,8 +907,10 @@ void ieee80211_amsdu_to_8023s(struct sk_buff *skb, struct sk_buff_head *list,
 		/* the last MSDU has no padding */
 		if (subframe_len > remaining)
 			goto purge;
-		/* mitigate A-MSDU aggregation injection attacks */
-		if (ether_addr_equal(hdr.eth.h_dest, rfc1042_header))
+		/* mitigate A-MSDU aggregation injection attacks, to be
+		 * checked when processing first subframe (offset == 0).
+		 */
+		if (offset == 0 && is_amsdu_aggregation_attack(&hdr.eth, skb, iftype))
 			goto purge;
 
 		offset += sizeof(struct ethhdr);

From 85e323bdbe28d4638aaefd8d9192763874efe9b0 Mon Sep 17 00:00:00 2001
From: Baojun Xu <baojun.xu@ti.com>
Date: Mon, 7 Jul 2025 17:05:13 +0800
Subject: [PATCH 1194/1334] ALSA: hda/tas2781: Fix calibration data parser
 issue

We will copy calibration data from position behind to front.
We have created a variable (tmp_val) point on top of calibration data
buffer, and tmp_val[1] is max of node number in original calibration
data structure, it will be overwritten after first data copy,
so can't be used as max node number check in for loop.
So we create a new variable to save max of node number (tmp_val[1]),
used to check if max node number was reached in for loop.
And a point need to be increased to point at calibration data in node.
Data saved position also need to be increased one byte.

Fixes: 4fe238513407 ("ALSA: hda/tas2781: Move and unified the calibrated-data getting function for SPI and I2C into the tas2781_hda lib")
Signed-off-by: Baojun Xu <baojun.xu@ti.com>
Link: https://patch.msgid.link/20250707090513.1462-1-baojun.xu@ti.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/tas2781_hda.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/sound/pci/hda/tas2781_hda.c b/sound/pci/hda/tas2781_hda.c
index 5f1d4b3e9688..34217ce9f28e 100644
--- a/sound/pci/hda/tas2781_hda.c
+++ b/sound/pci/hda/tas2781_hda.c
@@ -44,7 +44,7 @@ static void tas2781_apply_calib(struct tasdevice_priv *p)
 		TASDEVICE_REG(0, 0x13, 0x70),
 		TASDEVICE_REG(0, 0x18, 0x7c),
 	};
-	unsigned int crc, oft;
+	unsigned int crc, oft, node_num;
 	unsigned char *buf;
 	int i, j, k, l;
 
@@ -80,8 +80,9 @@ static void tas2781_apply_calib(struct tasdevice_priv *p)
 			dev_err(p->dev, "%s: CRC error\n", __func__);
 			return;
 		}
+		node_num = tmp_val[1];
 
-		for (j = 0, k = 0; j < tmp_val[1]; j++) {
+		for (j = 0, k = 0; j < node_num; j++) {
 			oft = j * 6 + 3;
 			if (tmp_val[oft] == TASDEV_UEFI_CALI_REG_ADDR_FLG) {
 				for (i = 0; i < TASDEV_CALIB_N; i++) {
@@ -99,8 +100,9 @@ static void tas2781_apply_calib(struct tasdevice_priv *p)
 				}
 
 				data[l] = k;
+				oft++;
 				for (i = 0; i < TASDEV_CALIB_N * 4; i++)
-					data[l + i] = data[4 * oft + i];
+					data[l + i + 1] = data[4 * oft + i];
 				k++;
 			}
 		}

From d78f76457d70d30e80b5d2e067d45de7a0505fc0 Mon Sep 17 00:00:00 2001
From: Edson Juliano Drosdeck <edson.drosdeck@gmail.com>
Date: Mon, 7 Jul 2025 08:45:37 -0300
Subject: [PATCH 1195/1334] ALSA: hda/realtek: Enable headset Mic on Positivo
 K116J

Positivo K116J is equipped with ALC269VC, and needs a fix to make
the headset mic to work.
Also must to limits the internal microphone boost.

Signed-off-by: Edson Juliano Drosdeck <edson.drosdeck@gmail.com>
Link: https://patch.msgid.link/20250707114537.8291-1-edson.drosdeck@gmail.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/patch_realtek.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index c7720a2f47c3..060db37eab83 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -11426,6 +11426,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x2782, 0x0228, "Infinix ZERO BOOK 13", ALC269VB_FIXUP_INFINIX_ZERO_BOOK_13),
 	SND_PCI_QUIRK(0x2782, 0x0232, "CHUWI CoreBook XPro", ALC269VB_FIXUP_CHUWI_COREBOOK_XPRO),
 	SND_PCI_QUIRK(0x2782, 0x1407, "Positivo P15X", ALC269_FIXUP_POSITIVO_P15X_HEADSET_MIC),
+	SND_PCI_QUIRK(0x2782, 0x1409, "Positivo K116J", ALC269_FIXUP_POSITIVO_P15X_HEADSET_MIC),
 	SND_PCI_QUIRK(0x2782, 0x1701, "Infinix Y4 Max", ALC269VC_FIXUP_INFINIX_Y4_MAX),
 	SND_PCI_QUIRK(0x2782, 0x1705, "MEDION E15433", ALC269VC_FIXUP_INFINIX_Y4_MAX),
 	SND_PCI_QUIRK(0x2782, 0x1707, "Vaio VJFE-ADL", ALC298_FIXUP_SPK_VOLUME),

From 203817de269539c062724d97dfa5af3cdf77a3ec Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Mon, 7 Jul 2025 09:52:33 +0100
Subject: [PATCH 1196/1334] io_uring/zcrx: fix pp destruction warnings

With multiple page pools and in some other cases we can have allocated
niovs on page pool destruction. Remove a misplaced warning checking that
all niovs are returned to zcrx on io_pp_zc_destroy(). It was reported
before but apparently got lost.

Reported-by: Pedro Tammela <pctammela@mojatatu.com>
Fixes: 34a3e60821ab9 ("io_uring/zcrx: implement zerocopy receive pp memory provider")
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/b9e6d919d2964bc48ddbf8eb52fc9f5d118e9bc1.1751878185.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/zcrx.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/io_uring/zcrx.c b/io_uring/zcrx.c
index ade4da9c4e31..67c518d22e0c 100644
--- a/io_uring/zcrx.c
+++ b/io_uring/zcrx.c
@@ -862,10 +862,7 @@ static int io_pp_zc_init(struct page_pool *pp)
 static void io_pp_zc_destroy(struct page_pool *pp)
 {
 	struct io_zcrx_ifq *ifq = io_pp_to_ifq(pp);
-	struct io_zcrx_area *area = ifq->area;
 
-	if (WARN_ON_ONCE(area->free_count != area->nia.num_niovs))
-		return;
 	percpu_ref_put(&ifq->ctx->refs);
 }
 

From d133036a0b23d3ef781d067ccdea6bbfb381e0cf Mon Sep 17 00:00:00 2001
From: Ben Skeggs <bskeggs@nvidia.com>
Date: Tue, 17 Jun 2025 14:00:36 +1000
Subject: [PATCH 1197/1334] drm/nouveau/gsp: fix potential leak of memory used
 during acpi init

If any of the ACPI calls fail, memory allocated for the input buffer
would be leaked.  Fix failure paths to free allocated memory.

Also add checks to ensure the allocations succeeded in the first place.

Reported-by: Danilo Krummrich <dakr@kernel.org>
Fixes: 176fdcbddfd2 ("drm/nouveau/gsp/r535: add support for booting GSP-RM")
Signed-off-by: Ben Skeggs <bskeggs@nvidia.com>
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
Link: https://lore.kernel.org/r/20250617040036.2932-1-bskeggs@nvidia.com
---
 .../drm/nouveau/nvkm/subdev/gsp/rm/r535/gsp.c | 20 +++++++++++++------
 1 file changed, 14 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/gsp.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/gsp.c
index 23f80e167705..588cb4ab85cb 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/gsp.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/gsp.c
@@ -719,7 +719,6 @@ r535_gsp_acpi_caps(acpi_handle handle, CAPS_METHOD_DATA *caps)
 	union acpi_object argv4 = {
 		.buffer.type    = ACPI_TYPE_BUFFER,
 		.buffer.length  = 4,
-		.buffer.pointer = kmalloc(argv4.buffer.length, GFP_KERNEL),
 	}, *obj;
 
 	caps->status = 0xffff;
@@ -727,17 +726,22 @@ r535_gsp_acpi_caps(acpi_handle handle, CAPS_METHOD_DATA *caps)
 	if (!acpi_check_dsm(handle, &NVOP_DSM_GUID, NVOP_DSM_REV, BIT_ULL(0x1a)))
 		return;
 
+	argv4.buffer.pointer = kmalloc(argv4.buffer.length, GFP_KERNEL);
+	if (!argv4.buffer.pointer)
+		return;
+
 	obj = acpi_evaluate_dsm(handle, &NVOP_DSM_GUID, NVOP_DSM_REV, 0x1a, &argv4);
 	if (!obj)
-		return;
+		goto done;
 
 	if (WARN_ON(obj->type != ACPI_TYPE_BUFFER) ||
 	    WARN_ON(obj->buffer.length != 4))
-		return;
+		goto done;
 
 	caps->status = 0;
 	caps->optimusCaps = *(u32 *)obj->buffer.pointer;
 
+done:
 	ACPI_FREE(obj);
 
 	kfree(argv4.buffer.pointer);
@@ -754,24 +758,28 @@ r535_gsp_acpi_jt(acpi_handle handle, JT_METHOD_DATA *jt)
 	union acpi_object argv4 = {
 		.buffer.type    = ACPI_TYPE_BUFFER,
 		.buffer.length  = sizeof(caps),
-		.buffer.pointer = kmalloc(argv4.buffer.length, GFP_KERNEL),
 	}, *obj;
 
 	jt->status = 0xffff;
 
+	argv4.buffer.pointer = kmalloc(argv4.buffer.length, GFP_KERNEL);
+	if (!argv4.buffer.pointer)
+		return;
+
 	obj = acpi_evaluate_dsm(handle, &JT_DSM_GUID, JT_DSM_REV, 0x1, &argv4);
 	if (!obj)
-		return;
+		goto done;
 
 	if (WARN_ON(obj->type != ACPI_TYPE_BUFFER) ||
 	    WARN_ON(obj->buffer.length != 4))
-		return;
+		goto done;
 
 	jt->status = 0;
 	jt->jtCaps = *(u32 *)obj->buffer.pointer;
 	jt->jtRevId = (jt->jtCaps & 0xfff00000) >> 20;
 	jt->bSBIOSCaps = 0;
 
+done:
 	ACPI_FREE(obj);
 
 	kfree(argv4.buffer.pointer);

From a0c5eac9181025b6d65ff25c203a7f10274f80c1 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Thu, 5 Jun 2025 13:14:16 +0200
Subject: [PATCH 1198/1334] wifi: mt76: Assume __mt76_connac_mcu_alloc_sta_req
 runs in atomic context

Rely on GFP_ATOMIC flag in __mt76_connac_mcu_alloc_sta_req since it can
run in atomic context. This is a preliminary patch to fix a 'sleep while
atomic' issue in mt7996_mac_sta_rc_work().

Fixes: 0762bdd30279 ("wifi: mt76: mt7996: rework mt7996_mac_sta_rc_work to support MLO")
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Link: https://patch.msgid.link/20250605-mt7996-sleep-while-atomic-v1-1-d46d15f9203c@kernel.org
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c b/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c
index cb13d0a76878..fa08e952dffa 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c
@@ -287,7 +287,7 @@ __mt76_connac_mcu_alloc_sta_req(struct mt76_dev *dev, struct mt76_vif_link *mvif
 
 	mt76_connac_mcu_get_wlan_idx(dev, wcid, &hdr.wlan_idx_lo,
 				     &hdr.wlan_idx_hi);
-	skb = mt76_mcu_msg_alloc(dev, NULL, len);
+	skb = __mt76_mcu_msg_alloc(dev, NULL, len, len, GFP_ATOMIC);
 	if (!skb)
 		return ERR_PTR(-ENOMEM);
 

From c772cd726eea6fe8fb81d2aeeacb18cecff73a7b Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Thu, 5 Jun 2025 13:14:17 +0200
Subject: [PATCH 1199/1334] wifi: mt76: Move RCU section in
 mt7996_mcu_set_fixed_field()

Since mt76_mcu_skb_send_msg() routine can't be executed in atomic context,
move RCU section in mt7996_mcu_set_fixed_field() and execute
mt76_mcu_skb_send_msg() in non-atomic context. This is a preliminary
patch to fix a 'sleep while atomic' issue in mt7996_mac_sta_rc_work().

Fixes: 0762bdd30279 ("wifi: mt76: mt7996: rework mt7996_mac_sta_rc_work to support MLO")
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Link: https://patch.msgid.link/20250605-mt7996-sleep-while-atomic-v1-2-d46d15f9203c@kernel.org
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 .../net/wireless/mediatek/mt76/mt7996/mac.c   |  5 +-
 .../net/wireless/mediatek/mt76/mt7996/main.c  |  3 +-
 .../net/wireless/mediatek/mt76/mt7996/mcu.c   | 68 +++++++++++++------
 .../wireless/mediatek/mt76/mt7996/mt7996.h    | 10 ++-
 4 files changed, 57 insertions(+), 29 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
index 0dbd4662bc84..7444bd374b50 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
@@ -2405,11 +2405,10 @@ void mt7996_mac_sta_rc_work(struct work_struct *work)
 			       IEEE80211_RC_BW_CHANGED))
 			mt7996_mcu_add_rate_ctrl(dev, vif, link_conf,
 						 link_sta, link, msta_link,
-						 true);
+						 link_id, true);
 
 		if (changed & IEEE80211_RC_SMPS_CHANGED)
-			mt7996_mcu_set_fixed_field(dev, link_sta, link,
-						   msta_link, NULL,
+			mt7996_mcu_set_fixed_field(dev, msta, NULL, link_id,
 						   RATE_PARAM_MMPS_UPDATE);
 
 		spin_lock_bh(&dev->mt76.sta_poll_lock);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/main.c b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
index 78ae9f5cb176..a096b5bab001 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
@@ -1114,7 +1114,8 @@ mt7996_mac_sta_event(struct mt7996_dev *dev, struct ieee80211_vif *vif,
 
 			err = mt7996_mcu_add_rate_ctrl(dev, vif, link_conf,
 						       link_sta, link,
-						       msta_link, false);
+						       msta_link, link_id,
+						       false);
 			if (err)
 				return err;
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
index f0adc0b4b8b6..33c61e795b73 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
@@ -1905,22 +1905,35 @@ int mt7996_mcu_set_fixed_rate_ctrl(struct mt7996_dev *dev,
 				     MCU_WM_UNI_CMD(RA), true);
 }
 
-int mt7996_mcu_set_fixed_field(struct mt7996_dev *dev,
-			       struct ieee80211_link_sta *link_sta,
-			       struct mt7996_vif_link *link,
-			       struct mt7996_sta_link *msta_link,
-			       void *data, u32 field)
+int mt7996_mcu_set_fixed_field(struct mt7996_dev *dev, struct mt7996_sta *msta,
+			       void *data, u8 link_id, u32 field)
 {
-	struct sta_phy_uni *phy = data;
+	struct mt7996_vif *mvif = msta->vif;
+	struct mt7996_sta_link *msta_link;
 	struct sta_rec_ra_fixed_uni *ra;
+	struct sta_phy_uni *phy = data;
+	struct mt76_vif_link *mlink;
 	struct sk_buff *skb;
+	int err = -ENODEV;
 	struct tlv *tlv;
 
-	skb = __mt76_connac_mcu_alloc_sta_req(&dev->mt76, &link->mt76,
+	rcu_read_lock();
+
+	mlink = rcu_dereference(mvif->mt76.link[link_id]);
+	if (!mlink)
+		goto error_unlock;
+
+	msta_link = rcu_dereference(msta->link[link_id]);
+	if (!msta_link)
+		goto error_unlock;
+
+	skb = __mt76_connac_mcu_alloc_sta_req(&dev->mt76, mlink,
 					      &msta_link->wcid,
 					      MT7996_STA_UPDATE_MAX_SIZE);
-	if (IS_ERR(skb))
-		return PTR_ERR(skb);
+	if (IS_ERR(skb)) {
+		err = PTR_ERR(skb);
+		goto error_unlock;
+	}
 
 	tlv = mt76_connac_mcu_add_tlv(skb, STA_REC_RA_UPDATE, sizeof(*ra));
 	ra = (struct sta_rec_ra_fixed_uni *)tlv;
@@ -1935,27 +1948,45 @@ int mt7996_mcu_set_fixed_field(struct mt7996_dev *dev,
 		if (phy)
 			ra->phy = *phy;
 		break;
-	case RATE_PARAM_MMPS_UPDATE:
+	case RATE_PARAM_MMPS_UPDATE: {
+		struct ieee80211_sta *sta = wcid_to_sta(&msta_link->wcid);
+		struct ieee80211_link_sta *link_sta;
+
+		link_sta = rcu_dereference(sta->link[link_id]);
+		if (!link_sta) {
+			dev_kfree_skb(skb);
+			goto error_unlock;
+		}
+
 		ra->mmps_mode = mt7996_mcu_get_mmps_mode(link_sta->smps_mode);
 		break;
+	}
 	default:
 		break;
 	}
 	ra->field = cpu_to_le32(field);
 
+	rcu_read_unlock();
+
 	return mt76_mcu_skb_send_msg(&dev->mt76, skb,
 				     MCU_WMWA_UNI_CMD(STA_REC_UPDATE), true);
+error_unlock:
+	rcu_read_unlock();
+
+	return err;
 }
 
 static int
 mt7996_mcu_add_rate_ctrl_fixed(struct mt7996_dev *dev,
 			       struct ieee80211_link_sta *link_sta,
 			       struct mt7996_vif_link *link,
-			       struct mt7996_sta_link *msta_link)
+			       struct mt7996_sta_link *msta_link,
+			       u8 link_id)
 {
 	struct cfg80211_chan_def *chandef = &link->phy->mt76->chandef;
 	struct cfg80211_bitrate_mask *mask = &link->bitrate_mask;
 	enum nl80211_band band = chandef->chan->band;
+	struct mt7996_sta *msta = msta_link->sta;
 	struct sta_phy_uni phy = {};
 	int ret, nrates = 0;
 
@@ -1996,8 +2027,7 @@ mt7996_mcu_add_rate_ctrl_fixed(struct mt7996_dev *dev,
 
 	/* fixed single rate */
 	if (nrates == 1) {
-		ret = mt7996_mcu_set_fixed_field(dev, link_sta, link,
-						 msta_link, &phy,
+		ret = mt7996_mcu_set_fixed_field(dev, msta, &phy, link_id,
 						 RATE_PARAM_FIXED_MCS);
 		if (ret)
 			return ret;
@@ -2018,8 +2048,7 @@ mt7996_mcu_add_rate_ctrl_fixed(struct mt7996_dev *dev,
 		else
 			mt76_rmw_field(dev, addr, GENMASK(15, 12), phy.sgi);
 
-		ret = mt7996_mcu_set_fixed_field(dev, link_sta, link,
-						 msta_link, &phy,
+		ret = mt7996_mcu_set_fixed_field(dev, msta, &phy, link_id,
 						 RATE_PARAM_FIXED_GI);
 		if (ret)
 			return ret;
@@ -2027,8 +2056,7 @@ mt7996_mcu_add_rate_ctrl_fixed(struct mt7996_dev *dev,
 
 	/* fixed HE_LTF */
 	if (mask->control[band].he_ltf != GENMASK(7, 0)) {
-		ret = mt7996_mcu_set_fixed_field(dev, link_sta, link,
-						 msta_link, &phy,
+		ret = mt7996_mcu_set_fixed_field(dev, msta, &phy, link_id,
 						 RATE_PARAM_FIXED_HE_LTF);
 		if (ret)
 			return ret;
@@ -2150,7 +2178,8 @@ int mt7996_mcu_add_rate_ctrl(struct mt7996_dev *dev,
 			     struct ieee80211_bss_conf *link_conf,
 			     struct ieee80211_link_sta *link_sta,
 			     struct mt7996_vif_link *link,
-			     struct mt7996_sta_link *msta_link, bool changed)
+			     struct mt7996_sta_link *msta_link,
+			     u8 link_id, bool changed)
 {
 	struct sk_buff *skb;
 	int ret;
@@ -2178,7 +2207,8 @@ int mt7996_mcu_add_rate_ctrl(struct mt7996_dev *dev,
 	if (ret)
 		return ret;
 
-	return mt7996_mcu_add_rate_ctrl_fixed(dev, link_sta, link, msta_link);
+	return mt7996_mcu_add_rate_ctrl_fixed(dev, link_sta, link, msta_link,
+					      link_id);
 }
 
 static int
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h b/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
index 1ad6bc046f7c..a529c2bae7cb 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
@@ -625,18 +625,16 @@ int mt7996_mcu_add_rate_ctrl(struct mt7996_dev *dev,
 			     struct ieee80211_bss_conf *link_conf,
 			     struct ieee80211_link_sta *link_sta,
 			     struct mt7996_vif_link *link,
-			     struct mt7996_sta_link *msta_link, bool changed);
+			     struct mt7996_sta_link *msta_link,
+			     u8 link_id, bool changed);
 int mt7996_set_channel(struct mt76_phy *mphy);
 int mt7996_mcu_set_chan_info(struct mt7996_phy *phy, u16 tag);
 int mt7996_mcu_set_tx(struct mt7996_dev *dev, struct ieee80211_vif *vif,
 		      struct ieee80211_bss_conf *link_conf);
 int mt7996_mcu_set_fixed_rate_ctrl(struct mt7996_dev *dev,
 				   void *data, u16 version);
-int mt7996_mcu_set_fixed_field(struct mt7996_dev *dev,
-			       struct ieee80211_link_sta *link_sta,
-			       struct mt7996_vif_link *link,
-			       struct mt7996_sta_link *msta_link,
-			       void *data, u32 field);
+int mt7996_mcu_set_fixed_field(struct mt7996_dev *dev, struct mt7996_sta *msta,
+			       void *data, u8 link_id, u32 field);
 int mt7996_mcu_set_eeprom(struct mt7996_dev *dev);
 int mt7996_mcu_get_eeprom(struct mt7996_dev *dev, u32 offset, u8 *buf, u32 buf_len);
 int mt7996_mcu_get_eeprom_free_block(struct mt7996_dev *dev, u8 *block_num);

From 28d519d0d493a8cf3f8ca01f10d962c56cec1825 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Thu, 5 Jun 2025 13:14:18 +0200
Subject: [PATCH 1200/1334] wifi: mt76: Move RCU section in
 mt7996_mcu_add_rate_ctrl_fixed()

Since mt7996_mcu_set_fixed_field() can't be executed in a RCU critical
section, move RCU section in mt7996_mcu_add_rate_ctrl_fixed() and run
mt7996_mcu_set_fixed_field() in non-atomic context. This is a
preliminary patch to fix a 'sleep while atomic' issue in
mt7996_mac_sta_rc_work().

Fixes: 0762bdd30279 ("wifi: mt76: mt7996: rework mt7996_mac_sta_rc_work to support MLO")
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Link: https://patch.msgid.link/20250605-mt7996-sleep-while-atomic-v1-3-d46d15f9203c@kernel.org
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 .../net/wireless/mediatek/mt76/mt7996/mcu.c   | 86 ++++++++++++-------
 1 file changed, 57 insertions(+), 29 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
index 33c61e795b73..742497ba2a6b 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
@@ -1977,51 +1977,74 @@ error_unlock:
 }
 
 static int
-mt7996_mcu_add_rate_ctrl_fixed(struct mt7996_dev *dev,
-			       struct ieee80211_link_sta *link_sta,
-			       struct mt7996_vif_link *link,
-			       struct mt7996_sta_link *msta_link,
-			       u8 link_id)
+mt7996_mcu_add_rate_ctrl_fixed(struct mt7996_dev *dev, struct mt7996_sta *msta,
+			       struct ieee80211_vif *vif, u8 link_id)
 {
-	struct cfg80211_chan_def *chandef = &link->phy->mt76->chandef;
-	struct cfg80211_bitrate_mask *mask = &link->bitrate_mask;
-	enum nl80211_band band = chandef->chan->band;
-	struct mt7996_sta *msta = msta_link->sta;
+	struct ieee80211_link_sta *link_sta;
+	struct cfg80211_bitrate_mask mask;
+	struct mt7996_sta_link *msta_link;
+	struct mt7996_vif_link *link;
 	struct sta_phy_uni phy = {};
-	int ret, nrates = 0;
+	struct ieee80211_sta *sta;
+	int ret, nrates = 0, idx;
+	enum nl80211_band band;
+	bool has_he;
 
 #define __sta_phy_bitrate_mask_check(_mcs, _gi, _ht, _he)			\
 	do {									\
-		u8 i, gi = mask->control[band]._gi;				\
+		u8 i, gi = mask.control[band]._gi;				\
 		gi = (_he) ? gi : gi == NL80211_TXRATE_FORCE_SGI;		\
 		phy.sgi = gi;							\
-		phy.he_ltf = mask->control[band].he_ltf;			\
-		for (i = 0; i < ARRAY_SIZE(mask->control[band]._mcs); i++) {	\
-			if (!mask->control[band]._mcs[i])			\
+		phy.he_ltf = mask.control[band].he_ltf;				\
+		for (i = 0; i < ARRAY_SIZE(mask.control[band]._mcs); i++) {	\
+			if (!mask.control[band]._mcs[i])			\
 				continue;					\
-			nrates += hweight16(mask->control[band]._mcs[i]);	\
-			phy.mcs = ffs(mask->control[band]._mcs[i]) - 1;		\
+			nrates += hweight16(mask.control[band]._mcs[i]);	\
+			phy.mcs = ffs(mask.control[band]._mcs[i]) - 1;		\
 			if (_ht)						\
 				phy.mcs += 8 * i;				\
 		}								\
 	} while (0)
 
-	if (link_sta->he_cap.has_he) {
+	rcu_read_lock();
+
+	link = mt7996_vif_link(dev, vif, link_id);
+	if (!link)
+		goto error_unlock;
+
+	msta_link = rcu_dereference(msta->link[link_id]);
+	if (!msta_link)
+		goto error_unlock;
+
+	sta = wcid_to_sta(&msta_link->wcid);
+	link_sta = rcu_dereference(sta->link[link_id]);
+	if (!link_sta)
+		goto error_unlock;
+
+	band = link->phy->mt76->chandef.chan->band;
+	has_he = link_sta->he_cap.has_he;
+	mask = link->bitrate_mask;
+	idx = msta_link->wcid.idx;
+
+	if (has_he) {
 		__sta_phy_bitrate_mask_check(he_mcs, he_gi, 0, 1);
 	} else if (link_sta->vht_cap.vht_supported) {
 		__sta_phy_bitrate_mask_check(vht_mcs, gi, 0, 0);
 	} else if (link_sta->ht_cap.ht_supported) {
 		__sta_phy_bitrate_mask_check(ht_mcs, gi, 1, 0);
 	} else {
-		nrates = hweight32(mask->control[band].legacy);
-		phy.mcs = ffs(mask->control[band].legacy) - 1;
+		nrates = hweight32(mask.control[band].legacy);
+		phy.mcs = ffs(mask.control[band].legacy) - 1;
 	}
+
+	rcu_read_unlock();
+
 #undef __sta_phy_bitrate_mask_check
 
 	/* fall back to auto rate control */
-	if (mask->control[band].gi == NL80211_TXRATE_DEFAULT_GI &&
-	    mask->control[band].he_gi == GENMASK(7, 0) &&
-	    mask->control[band].he_ltf == GENMASK(7, 0) &&
+	if (mask.control[band].gi == NL80211_TXRATE_DEFAULT_GI &&
+	    mask.control[band].he_gi == GENMASK(7, 0) &&
+	    mask.control[band].he_ltf == GENMASK(7, 0) &&
 	    nrates != 1)
 		return 0;
 
@@ -2034,16 +2057,16 @@ mt7996_mcu_add_rate_ctrl_fixed(struct mt7996_dev *dev,
 	}
 
 	/* fixed GI */
-	if (mask->control[band].gi != NL80211_TXRATE_DEFAULT_GI ||
-	    mask->control[band].he_gi != GENMASK(7, 0)) {
+	if (mask.control[band].gi != NL80211_TXRATE_DEFAULT_GI ||
+	    mask.control[band].he_gi != GENMASK(7, 0)) {
 		u32 addr;
 
 		/* firmware updates only TXCMD but doesn't take WTBL into
 		 * account, so driver should update here to reflect the
 		 * actual txrate hardware sends out.
 		 */
-		addr = mt7996_mac_wtbl_lmac_addr(dev, msta_link->wcid.idx, 7);
-		if (link_sta->he_cap.has_he)
+		addr = mt7996_mac_wtbl_lmac_addr(dev, idx, 7);
+		if (has_he)
 			mt76_rmw_field(dev, addr, GENMASK(31, 24), phy.sgi);
 		else
 			mt76_rmw_field(dev, addr, GENMASK(15, 12), phy.sgi);
@@ -2055,7 +2078,7 @@ mt7996_mcu_add_rate_ctrl_fixed(struct mt7996_dev *dev,
 	}
 
 	/* fixed HE_LTF */
-	if (mask->control[band].he_ltf != GENMASK(7, 0)) {
+	if (mask.control[band].he_ltf != GENMASK(7, 0)) {
 		ret = mt7996_mcu_set_fixed_field(dev, msta, &phy, link_id,
 						 RATE_PARAM_FIXED_HE_LTF);
 		if (ret)
@@ -2063,6 +2086,11 @@ mt7996_mcu_add_rate_ctrl_fixed(struct mt7996_dev *dev,
 	}
 
 	return 0;
+
+error_unlock:
+	rcu_read_unlock();
+
+	return -ENODEV;
 }
 
 static void
@@ -2181,6 +2209,7 @@ int mt7996_mcu_add_rate_ctrl(struct mt7996_dev *dev,
 			     struct mt7996_sta_link *msta_link,
 			     u8 link_id, bool changed)
 {
+	struct mt7996_sta *msta = msta_link->sta;
 	struct sk_buff *skb;
 	int ret;
 
@@ -2207,8 +2236,7 @@ int mt7996_mcu_add_rate_ctrl(struct mt7996_dev *dev,
 	if (ret)
 		return ret;
 
-	return mt7996_mcu_add_rate_ctrl_fixed(dev, link_sta, link, msta_link,
-					      link_id);
+	return mt7996_mcu_add_rate_ctrl_fixed(dev, msta, vif, link_id);
 }
 
 static int

From 3dd6f67c669c860b93ff533f790f23ee1cb36f25 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Thu, 5 Jun 2025 13:14:19 +0200
Subject: [PATCH 1201/1334] wifi: mt76: Move RCU section in
 mt7996_mcu_add_rate_ctrl()

Since mt76_mcu_skb_send_msg() routine can't be executed in atomic context,
move RCU section in mt7996_mcu_add_rate_ctrl() and execute
mt76_mcu_skb_send_msg() in non-atomic context. This is a preliminary
patch to fix a 'sleep while atomic' issue in mt7996_mac_sta_rc_work().

Fixes: 0762bdd30279 ("wifi: mt76: mt7996: rework mt7996_mac_sta_rc_work to support MLO")
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Link: https://patch.msgid.link/20250605-mt7996-sleep-while-atomic-v1-4-d46d15f9203c@kernel.org
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 .../net/wireless/mediatek/mt76/mt7996/mac.c   |  6 +--
 .../net/wireless/mediatek/mt76/mt7996/main.c  |  6 +--
 .../net/wireless/mediatek/mt76/mt7996/mcu.c   | 50 +++++++++++++++----
 .../wireless/mediatek/mt76/mt7996/mt7996.h    | 10 ++--
 4 files changed, 45 insertions(+), 27 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
index 7444bd374b50..329dc9edc80d 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
@@ -2356,7 +2356,6 @@ void mt7996_mac_sta_rc_work(struct work_struct *work)
 	struct ieee80211_bss_conf *link_conf;
 	struct ieee80211_link_sta *link_sta;
 	struct mt7996_sta_link *msta_link;
-	struct mt7996_vif_link *link;
 	struct mt76_vif_link *mlink;
 	struct ieee80211_sta *sta;
 	struct ieee80211_vif *vif;
@@ -2398,13 +2397,10 @@ void mt7996_mac_sta_rc_work(struct work_struct *work)
 
 		spin_unlock_bh(&dev->mt76.sta_poll_lock);
 
-		link = (struct mt7996_vif_link *)mlink;
-
 		if (changed & (IEEE80211_RC_SUPP_RATES_CHANGED |
 			       IEEE80211_RC_NSS_CHANGED |
 			       IEEE80211_RC_BW_CHANGED))
-			mt7996_mcu_add_rate_ctrl(dev, vif, link_conf,
-						 link_sta, link, msta_link,
+			mt7996_mcu_add_rate_ctrl(dev, msta_link->sta, vif,
 						 link_id, true);
 
 		if (changed & IEEE80211_RC_SMPS_CHANGED)
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/main.c b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
index a096b5bab001..07dd75ce94a5 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
@@ -1112,10 +1112,8 @@ mt7996_mac_sta_event(struct mt7996_dev *dev, struct ieee80211_vif *vif,
 			if (err)
 				return err;
 
-			err = mt7996_mcu_add_rate_ctrl(dev, vif, link_conf,
-						       link_sta, link,
-						       msta_link, link_id,
-						       false);
+			err = mt7996_mcu_add_rate_ctrl(dev, msta_link->sta, vif,
+						       link_id, false);
 			if (err)
 				return err;
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
index 742497ba2a6b..77ab1f4854a4 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
@@ -2201,23 +2201,44 @@ mt7996_mcu_sta_rate_ctrl_tlv(struct sk_buff *skb, struct mt7996_dev *dev,
 	memset(ra->rx_rcpi, INIT_RCPI, sizeof(ra->rx_rcpi));
 }
 
-int mt7996_mcu_add_rate_ctrl(struct mt7996_dev *dev,
-			     struct ieee80211_vif *vif,
-			     struct ieee80211_bss_conf *link_conf,
-			     struct ieee80211_link_sta *link_sta,
-			     struct mt7996_vif_link *link,
-			     struct mt7996_sta_link *msta_link,
-			     u8 link_id, bool changed)
+int mt7996_mcu_add_rate_ctrl(struct mt7996_dev *dev, struct mt7996_sta *msta,
+			     struct ieee80211_vif *vif, u8 link_id,
+			     bool changed)
 {
-	struct mt7996_sta *msta = msta_link->sta;
+	struct ieee80211_bss_conf *link_conf;
+	struct ieee80211_link_sta *link_sta;
+	struct mt7996_sta_link *msta_link;
+	struct mt7996_vif_link *link;
+	struct ieee80211_sta *sta;
 	struct sk_buff *skb;
-	int ret;
+	int ret = -ENODEV;
+
+	rcu_read_lock();
+
+	link = mt7996_vif_link(dev, vif, link_id);
+	if (!link)
+		goto error_unlock;
+
+	msta_link = rcu_dereference(msta->link[link_id]);
+	if (!msta_link)
+		goto error_unlock;
+
+	sta = wcid_to_sta(&msta_link->wcid);
+	link_sta = rcu_dereference(sta->link[link_id]);
+	if (!link_sta)
+		goto error_unlock;
+
+	link_conf = rcu_dereference(vif->link_conf[link_id]);
+	if (!link_conf)
+		goto error_unlock;
 
 	skb = __mt76_connac_mcu_alloc_sta_req(&dev->mt76, &link->mt76,
 					      &msta_link->wcid,
 					      MT7996_STA_UPDATE_MAX_SIZE);
-	if (IS_ERR(skb))
-		return PTR_ERR(skb);
+	if (IS_ERR(skb)) {
+		ret = PTR_ERR(skb);
+		goto error_unlock;
+	}
 
 	/* firmware rc algorithm refers to sta_rec_he for HE control.
 	 * once dev->rc_work changes the settings driver should also
@@ -2231,12 +2252,19 @@ int mt7996_mcu_add_rate_ctrl(struct mt7996_dev *dev,
 	 */
 	mt7996_mcu_sta_rate_ctrl_tlv(skb, dev, vif, link_conf, link_sta, link);
 
+	rcu_read_unlock();
+
 	ret = mt76_mcu_skb_send_msg(&dev->mt76, skb,
 				    MCU_WMWA_UNI_CMD(STA_REC_UPDATE), true);
 	if (ret)
 		return ret;
 
 	return mt7996_mcu_add_rate_ctrl_fixed(dev, msta, vif, link_id);
+
+error_unlock:
+	rcu_read_unlock();
+
+	return ret;
 }
 
 static int
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h b/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
index a529c2bae7cb..33ac16b64ef1 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
@@ -620,13 +620,9 @@ int mt7996_mcu_beacon_inband_discov(struct mt7996_dev *dev,
 int mt7996_mcu_add_obss_spr(struct mt7996_phy *phy,
 			    struct mt7996_vif_link *link,
 			    struct ieee80211_he_obss_pd *he_obss_pd);
-int mt7996_mcu_add_rate_ctrl(struct mt7996_dev *dev,
-			     struct ieee80211_vif *vif,
-			     struct ieee80211_bss_conf *link_conf,
-			     struct ieee80211_link_sta *link_sta,
-			     struct mt7996_vif_link *link,
-			     struct mt7996_sta_link *msta_link,
-			     u8 link_id, bool changed);
+int mt7996_mcu_add_rate_ctrl(struct mt7996_dev *dev, struct mt7996_sta *msta,
+			     struct ieee80211_vif *vif, u8 link_id,
+			     bool changed);
 int mt7996_set_channel(struct mt76_phy *mphy);
 int mt7996_mcu_set_chan_info(struct mt7996_phy *phy, u16 tag);
 int mt7996_mcu_set_tx(struct mt7996_dev *dev, struct ieee80211_vif *vif,

From 71532576f41e5b0ec967a82ed49d5dfb1027ccdb Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Thu, 5 Jun 2025 13:14:20 +0200
Subject: [PATCH 1202/1334] wifi: mt76: Remove RCU section in
 mt7996_mac_sta_rc_work()

Since mt7996_mcu_add_rate_ctrl() and mt7996_mcu_set_fixed_field() can't
run in atomic context, move RCU critical section in
mt7996_mcu_add_rate_ctrl() and mt7996_mcu_set_fixed_field(). This patch
fixes a 'sleep while atomic' issue in mt7996_mac_sta_rc_work().

Fixes: 0762bdd30279 ("wifi: mt76: mt7996: rework mt7996_mac_sta_rc_work to support MLO")
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Tested-by: Ben Greear <greearb@candelatech.com>
Link: https://patch.msgid.link/20250605-mt7996-sleep-while-atomic-v1-5-d46d15f9203c@kernel.org
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 .../net/wireless/mediatek/mt76/mt7996/mac.c   | 35 ++++---------------
 1 file changed, 7 insertions(+), 28 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
index 329dc9edc80d..445fe149ac0d 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
@@ -2353,19 +2353,12 @@ void mt7996_mac_update_stats(struct mt7996_phy *phy)
 void mt7996_mac_sta_rc_work(struct work_struct *work)
 {
 	struct mt7996_dev *dev = container_of(work, struct mt7996_dev, rc_work);
-	struct ieee80211_bss_conf *link_conf;
-	struct ieee80211_link_sta *link_sta;
 	struct mt7996_sta_link *msta_link;
-	struct mt76_vif_link *mlink;
-	struct ieee80211_sta *sta;
 	struct ieee80211_vif *vif;
-	struct mt7996_sta *msta;
 	struct mt7996_vif *mvif;
 	LIST_HEAD(list);
 	u32 changed;
-	u8 link_id;
 
-	rcu_read_lock();
 	spin_lock_bh(&dev->mt76.sta_poll_lock);
 	list_splice_init(&dev->sta_rc_list, &list);
 
@@ -2376,24 +2369,9 @@ void mt7996_mac_sta_rc_work(struct work_struct *work)
 
 		changed = msta_link->changed;
 		msta_link->changed = 0;
-
-		sta = wcid_to_sta(&msta_link->wcid);
-		link_id = msta_link->wcid.link_id;
-		msta = msta_link->sta;
-		mvif = msta->vif;
-		vif = container_of((void *)mvif, struct ieee80211_vif, drv_priv);
-
-		mlink = rcu_dereference(mvif->mt76.link[link_id]);
-		if (!mlink)
-			continue;
-
-		link_sta = rcu_dereference(sta->link[link_id]);
-		if (!link_sta)
-			continue;
-
-		link_conf = rcu_dereference(vif->link_conf[link_id]);
-		if (!link_conf)
-			continue;
+		mvif = msta_link->sta->vif;
+		vif = container_of((void *)mvif, struct ieee80211_vif,
+				   drv_priv);
 
 		spin_unlock_bh(&dev->mt76.sta_poll_lock);
 
@@ -2401,17 +2379,18 @@ void mt7996_mac_sta_rc_work(struct work_struct *work)
 			       IEEE80211_RC_NSS_CHANGED |
 			       IEEE80211_RC_BW_CHANGED))
 			mt7996_mcu_add_rate_ctrl(dev, msta_link->sta, vif,
-						 link_id, true);
+						 msta_link->wcid.link_id,
+						 true);
 
 		if (changed & IEEE80211_RC_SMPS_CHANGED)
-			mt7996_mcu_set_fixed_field(dev, msta, NULL, link_id,
+			mt7996_mcu_set_fixed_field(dev, msta_link->sta, NULL,
+						   msta_link->wcid.link_id,
 						   RATE_PARAM_MMPS_UPDATE);
 
 		spin_lock_bh(&dev->mt76.sta_poll_lock);
 	}
 
 	spin_unlock_bh(&dev->mt76.sta_poll_lock);
-	rcu_read_unlock();
 }
 
 void mt7996_mac_work(struct work_struct *work)

From d20de55332e92f9e614c34783c00bb6ce2fec067 Mon Sep 17 00:00:00 2001
From: Ming Yen Hsieh <mingyen.hsieh@mediatek.com>
Date: Thu, 12 Jun 2025 14:09:31 +0800
Subject: [PATCH 1203/1334] wifi: mt76: mt7925: fix the wrong config for tx
 interrupt

MT_INT_TX_DONE_MCU_WM may cause tx interrupt to be mishandled
during a reset failure, leading to the reset process failing.
By using MT_INT_TX_DONE_MCU instead of MT_INT_TX_DONE_MCU_WM,
the handling of tx interrupt is improved.

Cc: stable@vger.kernel.org
Fixes: c948b5da6bbe ("wifi: mt76: mt7925: add Mediatek Wi-Fi7 driver for mt7925 chips")
Signed-off-by: Ming Yen Hsieh <mingyen.hsieh@mediatek.com>
Link: https://patch.msgid.link/20250612060931.135635-1-mingyen.hsieh@mediatek.com
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt7925/regs.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/regs.h b/drivers/net/wireless/mediatek/mt76/mt7925/regs.h
index 547489092c29..341987e47f67 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7925/regs.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7925/regs.h
@@ -58,7 +58,7 @@
 
 #define MT_INT_TX_DONE_MCU		(MT_INT_TX_DONE_MCU_WM |	\
 					 MT_INT_TX_DONE_FWDL)
-#define MT_INT_TX_DONE_ALL		(MT_INT_TX_DONE_MCU_WM |	\
+#define MT_INT_TX_DONE_ALL		(MT_INT_TX_DONE_MCU |	\
 					 MT_INT_TX_DONE_BAND0 |	\
 					GENMASK(18, 4))
 

From c701574c54121af2720648572efbfe77564652d1 Mon Sep 17 00:00:00 2001
From: Michael Lo <michael.lo@mediatek.com>
Date: Thu, 12 Jun 2025 14:20:46 +0800
Subject: [PATCH 1204/1334] wifi: mt76: mt7925: fix invalid array index in ssid
 assignment during hw scan

Update the destination index to use 'n_ssids', which is incremented only
when a valid SSID is present. Previously, both mt76_connac_mcu_hw_scan()
and mt7925_mcu_hw_scan() used the loop index 'i' for the destination
array, potentially leaving gaps if any source SSIDs had zero length.

Cc: stable@vger.kernel.org
Fixes: c948b5da6bbe ("wifi: mt76: mt7925: add Mediatek Wi-Fi7 driver for mt7925 chips")
Signed-off-by: Michael Lo <michael.lo@mediatek.com>
Signed-off-by: Ming Yen Hsieh <mingyen.hsieh@mediatek.com>
Link: https://patch.msgid.link/20250612062046.160598-1-mingyen.hsieh@mediatek.com
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c | 4 ++--
 drivers/net/wireless/mediatek/mt76/mt7925/mcu.c      | 4 ++--
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c b/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c
index fa08e952dffa..16db0f2082d1 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c
@@ -1740,8 +1740,8 @@ int mt76_connac_mcu_hw_scan(struct mt76_phy *phy, struct ieee80211_vif *vif,
 		if (!sreq->ssids[i].ssid_len)
 			continue;
 
-		req->ssids[i].ssid_len = cpu_to_le32(sreq->ssids[i].ssid_len);
-		memcpy(req->ssids[i].ssid, sreq->ssids[i].ssid,
+		req->ssids[n_ssids].ssid_len = cpu_to_le32(sreq->ssids[i].ssid_len);
+		memcpy(req->ssids[n_ssids].ssid, sreq->ssids[i].ssid,
 		       sreq->ssids[i].ssid_len);
 		n_ssids++;
 	}
diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c
index b8542be0d945..0ba33409924a 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c
@@ -2869,8 +2869,8 @@ int mt7925_mcu_hw_scan(struct mt76_phy *phy, struct ieee80211_vif *vif,
 		if (i > MT7925_RNR_SCAN_MAX_BSSIDS)
 			break;
 
-		ssid->ssids[i].ssid_len = cpu_to_le32(sreq->ssids[i].ssid_len);
-		memcpy(ssid->ssids[i].ssid, sreq->ssids[i].ssid,
+		ssid->ssids[n_ssids].ssid_len = cpu_to_le32(sreq->ssids[i].ssid_len);
+		memcpy(ssid->ssids[n_ssids].ssid, sreq->ssids[i].ssid,
 		       sreq->ssids[i].ssid_len);
 		n_ssids++;
 	}

From 9f8f4a51f3c133030ac5a4bcd4759ae2b947b7bd Mon Sep 17 00:00:00 2001
From: Ming Yen Hsieh <mingyen.hsieh@mediatek.com>
Date: Mon, 16 Jun 2025 14:36:49 +0800
Subject: [PATCH 1205/1334] wifi: mt76: mt7925: fix incorrect scan probe IE
 handling for hw_scan

The IEs should be processed and filled into the command tlv separately
according to each band.

Cc: stable@vger.kernel.org
Fixes: c948b5da6bbe ("wifi: mt76: mt7925: add Mediatek Wi-Fi7 driver for mt7925 chips")
Signed-off-by: Ming Yen Hsieh <mingyen.hsieh@mediatek.com>
Link: https://patch.msgid.link/20250616063649.1100503-1-mingyen.hsieh@mediatek.com
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 .../net/wireless/mediatek/mt76/mt7925/main.c  |  2 +-
 .../net/wireless/mediatek/mt76/mt7925/mcu.c   | 75 +++++++++++++++----
 .../net/wireless/mediatek/mt76/mt7925/mcu.h   |  5 +-
 3 files changed, 63 insertions(+), 19 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/main.c b/drivers/net/wireless/mediatek/mt76/mt7925/main.c
index 94b0099dcd41..f0f1b1e4d507 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7925/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7925/main.c
@@ -1481,7 +1481,7 @@ mt7925_start_sched_scan(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 
 	mt792x_mutex_acquire(dev);
 
-	err = mt7925_mcu_sched_scan_req(mphy, vif, req);
+	err = mt7925_mcu_sched_scan_req(mphy, vif, req, ies);
 	if (err < 0)
 		goto out;
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c
index 0ba33409924a..8ac6fbb736ab 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c
@@ -164,6 +164,7 @@ mt7925_connac_mcu_set_wow_ctrl(struct mt76_phy *phy, struct ieee80211_vif *vif,
 			       bool suspend, struct cfg80211_wowlan *wowlan)
 {
 	struct mt76_vif_link *mvif = (struct mt76_vif_link *)vif->drv_priv;
+	struct ieee80211_scan_ies ies = {};
 	struct mt76_dev *dev = phy->dev;
 	struct {
 		struct {
@@ -194,7 +195,7 @@ mt7925_connac_mcu_set_wow_ctrl(struct mt76_phy *phy, struct ieee80211_vif *vif,
 		req.wow_ctrl_tlv.trigger |= (UNI_WOW_DETECT_TYPE_DISCONNECT |
 					     UNI_WOW_DETECT_TYPE_BCN_LOST);
 	if (wowlan->nd_config) {
-		mt7925_mcu_sched_scan_req(phy, vif, wowlan->nd_config);
+		mt7925_mcu_sched_scan_req(phy, vif, wowlan->nd_config, &ies);
 		req.wow_ctrl_tlv.trigger |= UNI_WOW_DETECT_TYPE_SCH_SCAN_HIT;
 		mt7925_mcu_sched_scan_enable(phy, vif, suspend);
 	}
@@ -2818,6 +2819,54 @@ int mt7925_mcu_set_dbdc(struct mt76_phy *phy, bool enable)
 	return err;
 }
 
+static void
+mt7925_mcu_build_scan_ie_tlv(struct mt76_dev *mdev,
+			     struct sk_buff *skb,
+			     struct ieee80211_scan_ies *scan_ies)
+{
+	u32 max_len = sizeof(struct scan_ie_tlv) + MT76_CONNAC_SCAN_IE_LEN;
+	struct scan_ie_tlv *ie;
+	enum nl80211_band i;
+	struct tlv *tlv;
+	const u8 *ies;
+	u16 ies_len;
+
+	for (i = 0; i <= NL80211_BAND_6GHZ; i++) {
+		if (i == NL80211_BAND_60GHZ)
+			continue;
+
+		ies = scan_ies->ies[i];
+		ies_len = scan_ies->len[i];
+
+		if (!ies || !ies_len)
+			continue;
+
+		if (ies_len > max_len)
+			return;
+
+		tlv = mt76_connac_mcu_add_tlv(skb, UNI_SCAN_IE,
+					      sizeof(*ie) + ies_len);
+		ie = (struct scan_ie_tlv *)tlv;
+
+		memcpy(ie->ies, ies, ies_len);
+		ie->ies_len = cpu_to_le16(ies_len);
+
+		switch (i) {
+		case NL80211_BAND_2GHZ:
+			ie->band = 1;
+			break;
+		case NL80211_BAND_6GHZ:
+			ie->band = 3;
+			break;
+		default:
+			ie->band = 2;
+			break;
+		}
+
+		max_len -= (sizeof(*ie) + ies_len);
+	}
+}
+
 int mt7925_mcu_hw_scan(struct mt76_phy *phy, struct ieee80211_vif *vif,
 		       struct ieee80211_scan_request *scan_req)
 {
@@ -2843,7 +2892,8 @@ int mt7925_mcu_hw_scan(struct mt76_phy *phy, struct ieee80211_vif *vif,
 
 	max_len = sizeof(*hdr) + sizeof(*req) + sizeof(*ssid) +
 		  sizeof(*bssid) * MT7925_RNR_SCAN_MAX_BSSIDS +
-		  sizeof(*chan_info) + sizeof(*misc) + sizeof(*ie);
+		  sizeof(*chan_info) + sizeof(*misc) + sizeof(*ie) +
+		  MT76_CONNAC_SCAN_IE_LEN;
 
 	skb = mt76_mcu_msg_alloc(mdev, NULL, max_len);
 	if (!skb)
@@ -2925,13 +2975,6 @@ int mt7925_mcu_hw_scan(struct mt76_phy *phy, struct ieee80211_vif *vif,
 	}
 	chan_info->channel_type = sreq->n_channels ? 4 : 0;
 
-	tlv = mt76_connac_mcu_add_tlv(skb, UNI_SCAN_IE, sizeof(*ie));
-	ie = (struct scan_ie_tlv *)tlv;
-	if (sreq->ie_len > 0) {
-		memcpy(ie->ies, sreq->ie, sreq->ie_len);
-		ie->ies_len = cpu_to_le16(sreq->ie_len);
-	}
-
 	req->scan_func |= SCAN_FUNC_SPLIT_SCAN;
 
 	tlv = mt76_connac_mcu_add_tlv(skb, UNI_SCAN_MISC, sizeof(*misc));
@@ -2942,6 +2985,9 @@ int mt7925_mcu_hw_scan(struct mt76_phy *phy, struct ieee80211_vif *vif,
 		req->scan_func |= SCAN_FUNC_RANDOM_MAC;
 	}
 
+	/* Append scan probe IEs as the last tlv */
+	mt7925_mcu_build_scan_ie_tlv(mdev, skb, &scan_req->ies);
+
 	err = mt76_mcu_skb_send_msg(mdev, skb, MCU_UNI_CMD(SCAN_REQ),
 				    true);
 	if (err < 0)
@@ -2953,7 +2999,8 @@ EXPORT_SYMBOL_GPL(mt7925_mcu_hw_scan);
 
 int mt7925_mcu_sched_scan_req(struct mt76_phy *phy,
 			      struct ieee80211_vif *vif,
-			      struct cfg80211_sched_scan_request *sreq)
+			      struct cfg80211_sched_scan_request *sreq,
+			      struct ieee80211_scan_ies *ies)
 {
 	struct mt76_vif_link *mvif = (struct mt76_vif_link *)vif->drv_priv;
 	struct ieee80211_channel **scan_list = sreq->channels;
@@ -3041,12 +3088,8 @@ int mt7925_mcu_sched_scan_req(struct mt76_phy *phy,
 	}
 	chan_info->channel_type = sreq->n_channels ? 4 : 0;
 
-	tlv = mt76_connac_mcu_add_tlv(skb, UNI_SCAN_IE, sizeof(*ie));
-	ie = (struct scan_ie_tlv *)tlv;
-	if (sreq->ie_len > 0) {
-		memcpy(ie->ies, sreq->ie, sreq->ie_len);
-		ie->ies_len = cpu_to_le16(sreq->ie_len);
-	}
+	/* Append scan probe IEs as the last tlv */
+	mt7925_mcu_build_scan_ie_tlv(mdev, skb, ies);
 
 	return mt76_mcu_skb_send_msg(mdev, skb, MCU_UNI_CMD(SCAN_REQ),
 				     true);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/mcu.h b/drivers/net/wireless/mediatek/mt76/mt7925/mcu.h
index ee6fb16e83c5..a40764d89a1f 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7925/mcu.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7925/mcu.h
@@ -269,7 +269,7 @@ struct scan_ie_tlv {
 	__le16 ies_len;
 	u8 band;
 	u8 pad;
-	u8 ies[MT76_CONNAC_SCAN_IE_LEN];
+	u8 ies[];
 };
 
 struct scan_misc_tlv {
@@ -673,7 +673,8 @@ int mt7925_mcu_cancel_hw_scan(struct mt76_phy *phy,
 			      struct ieee80211_vif *vif);
 int mt7925_mcu_sched_scan_req(struct mt76_phy *phy,
 			      struct ieee80211_vif *vif,
-			      struct cfg80211_sched_scan_request *sreq);
+			      struct cfg80211_sched_scan_request *sreq,
+			      struct ieee80211_scan_ies *ies);
 int mt7925_mcu_sched_scan_enable(struct mt76_phy *phy,
 				 struct ieee80211_vif *vif,
 				 bool enable);

From 35ad47c0b3da04b00b19a8b9ed5632e2f2520472 Mon Sep 17 00:00:00 2001
From: Deren Wu <deren.wu@mediatek.com>
Date: Sun, 25 May 2025 14:11:21 +0800
Subject: [PATCH 1206/1334] wifi: mt76: mt7925: prevent NULL pointer
 dereference in mt7925_sta_set_decap_offload()

Add a NULL check for msta->vif before accessing its members to prevent
a kernel panic in AP mode deployment. This also fix the issue reported
in [1].

The crash occurs when this function is triggered before the station is
fully initialized. The call trace shows a page fault at
mt7925_sta_set_decap_offload() due to accessing resources when msta->vif
is NULL.

Fix this by adding an early return if msta->vif is NULL and also check
wcid.sta is ready. This ensures we only proceed with decap offload
configuration when the station's state is properly initialized.

[14739.655703] Unable to handle kernel paging request at virtual address ffffffffffffffa0
[14739.811820] CPU: 0 UID: 0 PID: 895854 Comm: hostapd Tainted: G
[14739.821394] Tainted: [C]=CRAP, [O]=OOT_MODULE
[14739.825746] Hardware name: Raspberry Pi 4 Model B Rev 1.1 (DT)
[14739.831577] pstate: 60000005 (nZCv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--)
[14739.838538] pc : mt7925_sta_set_decap_offload+0xc0/0x1b8 [mt7925_common]
[14739.845271] lr : mt7925_sta_set_decap_offload+0x58/0x1b8 [mt7925_common]
[14739.851985] sp : ffffffc085efb500
[14739.855295] x29: ffffffc085efb500 x28: 0000000000000000 x27: ffffff807803a158
[14739.862436] x26: ffffff8041ececb8 x25: 0000000000000001 x24: 0000000000000001
[14739.869577] x23: 0000000000000001 x22: 0000000000000008 x21: ffffff8041ecea88
[14739.876715] x20: ffffff8041c19ca0 x19: ffffff8078031fe0 x18: 0000000000000000
[14739.883853] x17: 0000000000000000 x16: ffffffe2aeac1110 x15: 000000559da48080
[14739.890991] x14: 0000000000000001 x13: 0000000000000000 x12: 0000000000000000
[14739.898130] x11: 0a10020001008e88 x10: 0000000000001a50 x9 : ffffffe26457bfa0
[14739.905269] x8 : ffffff8042013bb0 x7 : ffffff807fb6cbf8 x6 : dead000000000100
[14739.912407] x5 : dead000000000122 x4 : ffffff80780326c8 x3 : 0000000000000000
[14739.919546] x2 : 0000000000000000 x1 : 0000000000000000 x0 : ffffff8041ececb8
[14739.926686] Call trace:
[14739.929130]  mt7925_sta_set_decap_offload+0xc0/0x1b8 [mt7925_common]
[14739.935505]  ieee80211_check_fast_rx+0x19c/0x510 [mac80211]
[14739.941344]  _sta_info_move_state+0xe4/0x510 [mac80211]
[14739.946860]  sta_info_move_state+0x1c/0x30 [mac80211]
[14739.952116]  sta_apply_auth_flags.constprop.0+0x90/0x1b0 [mac80211]
[14739.958708]  sta_apply_parameters+0x234/0x5e0 [mac80211]
[14739.964332]  ieee80211_add_station+0xdc/0x190 [mac80211]
[14739.969950]  nl80211_new_station+0x46c/0x670 [cfg80211]
[14739.975516]  genl_family_rcv_msg_doit+0xdc/0x150
[14739.980158]  genl_rcv_msg+0x218/0x298
[14739.983830]  netlink_rcv_skb+0x64/0x138
[14739.987670]  genl_rcv+0x40/0x60
[14739.990816]  netlink_unicast+0x314/0x380
[14739.994742]  netlink_sendmsg+0x198/0x3f0
[14739.998664]  __sock_sendmsg+0x64/0xc0
[14740.002324]  ____sys_sendmsg+0x260/0x298
[14740.006242]  ___sys_sendmsg+0xb4/0x110

Cc: stable@vger.kernel.org
Link: https://github.com/morrownr/USB-WiFi/issues/603 [1]
Fixes: b859ad65309a ("wifi: mt76: mt7925: add link handling in mt7925_sta_set_decap_offload")
Signed-off-by: Deren Wu <deren.wu@mediatek.com>
Link: https://patch.msgid.link/35aedbffa050e98939264300407a52ba4e236d52.1748149855.git.deren.wu@mediatek.com
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt7925/main.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/main.c b/drivers/net/wireless/mediatek/mt76/mt7925/main.c
index f0f1b1e4d507..5b001548dffc 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7925/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7925/main.c
@@ -1603,6 +1603,9 @@ static void mt7925_sta_set_decap_offload(struct ieee80211_hw *hw,
 	unsigned long valid = mvif->valid_links;
 	u8 i;
 
+	if (!msta->vif)
+		return;
+
 	mt792x_mutex_acquire(dev);
 
 	valid = ieee80211_vif_is_mld(vif) ? mvif->valid_links : BIT(0);
@@ -1617,6 +1620,9 @@ static void mt7925_sta_set_decap_offload(struct ieee80211_hw *hw,
 		else
 			clear_bit(MT_WCID_FLAG_HDR_TRANS, &mlink->wcid.flags);
 
+		if (!mlink->wcid.sta)
+			continue;
+
 		mt7925_mcu_wtbl_update_hdr_trans(dev, vif, sta, i);
 	}
 

From 7035a082348acf1d43ffb9ff735899f8e3863f8f Mon Sep 17 00:00:00 2001
From: Deren Wu <deren.wu@mediatek.com>
Date: Sun, 25 May 2025 14:11:22 +0800
Subject: [PATCH 1207/1334] wifi: mt76: mt7921: prevent decap offload config
 before STA initialization

The decap offload configuration should only be applied after the STA has
been successfully initialized. Attempting to configure it earlier can lead
to corruption of the MAC configuration in the chip's hardware state.

Add an early check for `msta->deflink.wcid.sta` to ensure the station peer
is properly initialized before proceeding with decapsulation offload
configuration.

Cc: stable@vger.kernel.org
Fixes: 24299fc869f7 ("mt76: mt7921: enable rx header traslation offload")
Signed-off-by: Deren Wu <deren.wu@mediatek.com>
Link: https://patch.msgid.link/f23a72ba7a3c1ad38ba9e13bb54ef21d6ef44ffb.1748149855.git.deren.wu@mediatek.com
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt7921/main.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/main.c b/drivers/net/wireless/mediatek/mt76/mt7921/main.c
index 1fffa43379b2..77f73ae1d7ec 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/main.c
@@ -1180,6 +1180,9 @@ static void mt7921_sta_set_decap_offload(struct ieee80211_hw *hw,
 	struct mt792x_sta *msta = (struct mt792x_sta *)sta->drv_priv;
 	struct mt792x_dev *dev = mt792x_hw_dev(hw);
 
+	if (!msta->deflink.wcid.sta)
+		return;
+
 	mt792x_mutex_acquire(dev);
 
 	if (enabled)

From dc66a129adf1f25e944d0b93cd2df2ee0f0bd4d6 Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Mon, 7 Jul 2025 17:47:01 +0200
Subject: [PATCH 1208/1334] wifi: mt76: add a wrapper for wcid access with
 validation

Several places use rcu_dereference to get a wcid entry without validating
if the index exceeds the array boundary. Fix this by using a helper function,
which handles validation.

Link: https://patch.msgid.link/20250707154702.1726-1-nbd@nbd.name
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt76.h            | 10 ++++++++++
 drivers/net/wireless/mediatek/mt76/mt7603/dma.c      |  2 +-
 drivers/net/wireless/mediatek/mt76/mt7603/mac.c      | 10 ++--------
 drivers/net/wireless/mediatek/mt76/mt7615/mac.c      |  7 ++-----
 drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c |  2 +-
 drivers/net/wireless/mediatek/mt76/mt76x02.h         |  5 +----
 drivers/net/wireless/mediatek/mt76/mt76x02_mac.c     |  4 +---
 drivers/net/wireless/mediatek/mt76/mt7915/mac.c      | 12 +++---------
 drivers/net/wireless/mediatek/mt76/mt7915/mcu.c      |  2 +-
 drivers/net/wireless/mediatek/mt76/mt7915/mmio.c     |  5 +----
 drivers/net/wireless/mediatek/mt76/mt7921/mac.c      |  6 +++---
 drivers/net/wireless/mediatek/mt76/mt7925/mac.c      |  6 +++---
 drivers/net/wireless/mediatek/mt76/mt792x_mac.c      |  5 +----
 drivers/net/wireless/mediatek/mt76/mt7996/mac.c      | 12 +++---------
 drivers/net/wireless/mediatek/mt76/mt7996/mcu.c      | 11 ++++-------
 drivers/net/wireless/mediatek/mt76/tx.c              |  8 +++-----
 drivers/net/wireless/mediatek/mt76/util.c            |  2 +-
 17 files changed, 41 insertions(+), 68 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76.h b/drivers/net/wireless/mediatek/mt76/mt76.h
index 5f8d81cda6cd..74b75035d361 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76.h
@@ -1224,6 +1224,16 @@ static inline int mt76_wed_dma_setup(struct mt76_dev *dev, struct mt76_queue *q,
 #define mt76_dereference(p, dev) \
 	rcu_dereference_protected(p, lockdep_is_held(&(dev)->mutex))
 
+static inline struct mt76_wcid *
+__mt76_wcid_ptr(struct mt76_dev *dev, u16 idx)
+{
+	if (idx >= ARRAY_SIZE(dev->wcid))
+		return NULL;
+	return rcu_dereference(dev->wcid[idx]);
+}
+
+#define mt76_wcid_ptr(dev, idx) __mt76_wcid_ptr(&(dev)->mt76, idx)
+
 struct mt76_dev *mt76_alloc_device(struct device *pdev, unsigned int size,
 				   const struct ieee80211_ops *ops,
 				   const struct mt76_driver_ops *drv_ops);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7603/dma.c b/drivers/net/wireless/mediatek/mt76/mt7603/dma.c
index 863e5770df51..e26cc78fff94 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7603/dma.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7603/dma.c
@@ -44,7 +44,7 @@ mt7603_rx_loopback_skb(struct mt7603_dev *dev, struct sk_buff *skb)
 	if (idx >= MT7603_WTBL_STA - 1)
 		goto free;
 
-	wcid = rcu_dereference(dev->mt76.wcid[idx]);
+	wcid = mt76_wcid_ptr(dev, idx);
 	if (!wcid)
 		goto free;
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7603/mac.c b/drivers/net/wireless/mediatek/mt76/mt7603/mac.c
index 413973d05b43..6387f9e61060 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7603/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7603/mac.c
@@ -487,10 +487,7 @@ mt7603_rx_get_wcid(struct mt7603_dev *dev, u8 idx, bool unicast)
 	struct mt7603_sta *sta;
 	struct mt76_wcid *wcid;
 
-	if (idx >= MT7603_WTBL_SIZE)
-		return NULL;
-
-	wcid = rcu_dereference(dev->mt76.wcid[idx]);
+	wcid = mt76_wcid_ptr(dev, idx);
 	if (unicast || !wcid)
 		return wcid;
 
@@ -1266,12 +1263,9 @@ void mt7603_mac_add_txs(struct mt7603_dev *dev, void *data)
 	if (pid == MT_PACKET_ID_NO_ACK)
 		return;
 
-	if (wcidx >= MT7603_WTBL_SIZE)
-		return;
-
 	rcu_read_lock();
 
-	wcid = rcu_dereference(dev->mt76.wcid[wcidx]);
+	wcid = mt76_wcid_ptr(dev, wcidx);
 	if (!wcid)
 		goto out;
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/mac.c b/drivers/net/wireless/mediatek/mt76/mt7615/mac.c
index 3ca4fae7c4b0..f8d2cc94b742 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7615/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7615/mac.c
@@ -90,10 +90,7 @@ static struct mt76_wcid *mt7615_rx_get_wcid(struct mt7615_dev *dev,
 	struct mt7615_sta *sta;
 	struct mt76_wcid *wcid;
 
-	if (idx >= MT7615_WTBL_SIZE)
-		return NULL;
-
-	wcid = rcu_dereference(dev->mt76.wcid[idx]);
+	wcid = mt76_wcid_ptr(dev, idx);
 	if (unicast || !wcid)
 		return wcid;
 
@@ -1504,7 +1501,7 @@ static void mt7615_mac_add_txs(struct mt7615_dev *dev, void *data)
 
 	rcu_read_lock();
 
-	wcid = rcu_dereference(dev->mt76.wcid[wcidx]);
+	wcid = mt76_wcid_ptr(dev, wcidx);
 	if (!wcid)
 		goto out;
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c b/drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c
index e9ac8a7317a1..0db00efe88b0 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c
@@ -1172,7 +1172,7 @@ void mt76_connac2_txwi_free(struct mt76_dev *dev, struct mt76_txwi_cache *t,
 		wcid_idx = wcid->idx;
 	} else {
 		wcid_idx = le32_get_bits(txwi[1], MT_TXD1_WLAN_IDX);
-		wcid = rcu_dereference(dev->wcid[wcid_idx]);
+		wcid = __mt76_wcid_ptr(dev, wcid_idx);
 
 		if (wcid && wcid->sta) {
 			sta = container_of((void *)wcid, struct ieee80211_sta,
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02.h b/drivers/net/wireless/mediatek/mt76/mt76x02.h
index 4cd63bacd742..9d7ee09b6cc9 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02.h
@@ -262,10 +262,7 @@ mt76x02_rx_get_sta(struct mt76_dev *dev, u8 idx)
 {
 	struct mt76_wcid *wcid;
 
-	if (idx >= MT76x02_N_WCIDS)
-		return NULL;
-
-	wcid = rcu_dereference(dev->wcid[idx]);
+	wcid = __mt76_wcid_ptr(dev, idx);
 	if (!wcid)
 		return NULL;
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_mac.c b/drivers/net/wireless/mediatek/mt76/mt76x02_mac.c
index d5db6ffd6d36..83488b2d6efb 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_mac.c
@@ -564,9 +564,7 @@ void mt76x02_send_tx_status(struct mt76x02_dev *dev,
 
 	rcu_read_lock();
 
-	if (stat->wcid < MT76x02_N_WCIDS)
-		wcid = rcu_dereference(dev->mt76.wcid[stat->wcid]);
-
+	wcid = mt76_wcid_ptr(dev, stat->wcid);
 	if (wcid && wcid->sta) {
 		void *priv;
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mac.c b/drivers/net/wireless/mediatek/mt76/mt7915/mac.c
index 9400e4af2a04..6639976afcee 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/mac.c
@@ -56,10 +56,7 @@ static struct mt76_wcid *mt7915_rx_get_wcid(struct mt7915_dev *dev,
 	struct mt7915_sta *sta;
 	struct mt76_wcid *wcid;
 
-	if (idx >= ARRAY_SIZE(dev->mt76.wcid))
-		return NULL;
-
-	wcid = rcu_dereference(dev->mt76.wcid[idx]);
+	wcid = mt76_wcid_ptr(dev, idx);
 	if (unicast || !wcid)
 		return wcid;
 
@@ -917,7 +914,7 @@ mt7915_mac_tx_free(struct mt7915_dev *dev, void *data, int len)
 			u16 idx;
 
 			idx = FIELD_GET(MT_TX_FREE_WLAN_ID, info);
-			wcid = rcu_dereference(dev->mt76.wcid[idx]);
+			wcid = mt76_wcid_ptr(dev, idx);
 			sta = wcid_to_sta(wcid);
 			if (!sta)
 				continue;
@@ -1013,12 +1010,9 @@ static void mt7915_mac_add_txs(struct mt7915_dev *dev, void *data)
 	if (pid < MT_PACKET_ID_WED)
 		return;
 
-	if (wcidx >= mt7915_wtbl_size(dev))
-		return;
-
 	rcu_read_lock();
 
-	wcid = rcu_dereference(dev->mt76.wcid[wcidx]);
+	wcid = mt76_wcid_ptr(dev, wcidx);
 	if (!wcid)
 		goto out;
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c
index 427542777abc..c6584d2b7509 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c
@@ -3986,7 +3986,7 @@ int mt7915_mcu_wed_wa_tx_stats(struct mt7915_dev *dev, u16 wlan_idx)
 
 	rcu_read_lock();
 
-	wcid = rcu_dereference(dev->mt76.wcid[wlan_idx]);
+	wcid = mt76_wcid_ptr(dev, wlan_idx);
 	if (wcid)
 		wcid->stats.tx_packets += le32_to_cpu(res->tx_packets);
 	else
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mmio.c b/drivers/net/wireless/mediatek/mt76/mt7915/mmio.c
index 9c4d5cea0c42..4a82f8e4c118 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/mmio.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/mmio.c
@@ -587,12 +587,9 @@ static void mt7915_mmio_wed_update_rx_stats(struct mtk_wed_device *wed,
 
 	dev = container_of(wed, struct mt7915_dev, mt76.mmio.wed);
 
-	if (idx >= mt7915_wtbl_size(dev))
-		return;
-
 	rcu_read_lock();
 
-	wcid = rcu_dereference(dev->mt76.wcid[idx]);
+	wcid = mt76_wcid_ptr(dev, idx);
 	if (wcid) {
 		wcid->stats.rx_bytes += le32_to_cpu(stats->rx_byte_cnt);
 		wcid->stats.rx_packets += le32_to_cpu(stats->rx_pkt_cnt);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mac.c b/drivers/net/wireless/mediatek/mt76/mt7921/mac.c
index 5dd57de59f27..f1f76506b0a5 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/mac.c
@@ -465,7 +465,7 @@ void mt7921_mac_add_txs(struct mt792x_dev *dev, void *data)
 
 	rcu_read_lock();
 
-	wcid = rcu_dereference(dev->mt76.wcid[wcidx]);
+	wcid = mt76_wcid_ptr(dev, wcidx);
 	if (!wcid)
 		goto out;
 
@@ -516,7 +516,7 @@ static void mt7921_mac_tx_free(struct mt792x_dev *dev, void *data, int len)
 
 			count++;
 			idx = FIELD_GET(MT_TX_FREE_WLAN_ID, info);
-			wcid = rcu_dereference(dev->mt76.wcid[idx]);
+			wcid = mt76_wcid_ptr(dev, idx);
 			sta = wcid_to_sta(wcid);
 			if (!sta)
 				continue;
@@ -816,7 +816,7 @@ void mt7921_usb_sdio_tx_complete_skb(struct mt76_dev *mdev,
 	u16 idx;
 
 	idx = le32_get_bits(txwi[1], MT_TXD1_WLAN_IDX);
-	wcid = rcu_dereference(mdev->wcid[idx]);
+	wcid = __mt76_wcid_ptr(mdev, idx);
 	sta = wcid_to_sta(wcid);
 
 	if (sta && likely(e->skb->protocol != cpu_to_be16(ETH_P_PAE)))
diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/mac.c b/drivers/net/wireless/mediatek/mt76/mt7925/mac.c
index c871d2f9688b..75823c9fd3a1 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7925/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7925/mac.c
@@ -1040,7 +1040,7 @@ void mt7925_mac_add_txs(struct mt792x_dev *dev, void *data)
 
 	rcu_read_lock();
 
-	wcid = rcu_dereference(dev->mt76.wcid[wcidx]);
+	wcid = mt76_wcid_ptr(dev, wcidx);
 	if (!wcid)
 		goto out;
 
@@ -1122,7 +1122,7 @@ mt7925_mac_tx_free(struct mt792x_dev *dev, void *data, int len)
 			u16 idx;
 
 			idx = FIELD_GET(MT_TXFREE_INFO_WLAN_ID, info);
-			wcid = rcu_dereference(dev->mt76.wcid[idx]);
+			wcid = mt76_wcid_ptr(dev, idx);
 			sta = wcid_to_sta(wcid);
 			if (!sta)
 				continue;
@@ -1445,7 +1445,7 @@ void mt7925_usb_sdio_tx_complete_skb(struct mt76_dev *mdev,
 	u16 idx;
 
 	idx = le32_get_bits(txwi[1], MT_TXD1_WLAN_IDX);
-	wcid = rcu_dereference(mdev->wcid[idx]);
+	wcid = __mt76_wcid_ptr(mdev, idx);
 	sta = wcid_to_sta(wcid);
 
 	if (sta && likely(e->skb->protocol != cpu_to_be16(ETH_P_PAE)))
diff --git a/drivers/net/wireless/mediatek/mt76/mt792x_mac.c b/drivers/net/wireless/mediatek/mt76/mt792x_mac.c
index 05978d9c7b91..3f1d9ba49076 100644
--- a/drivers/net/wireless/mediatek/mt76/mt792x_mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt792x_mac.c
@@ -142,10 +142,7 @@ struct mt76_wcid *mt792x_rx_get_wcid(struct mt792x_dev *dev, u16 idx,
 	struct mt792x_sta *sta;
 	struct mt76_wcid *wcid;
 
-	if (idx >= ARRAY_SIZE(dev->mt76.wcid))
-		return NULL;
-
-	wcid = rcu_dereference(dev->mt76.wcid[idx]);
+	wcid = mt76_wcid_ptr(dev, idx);
 	if (unicast || !wcid)
 		return wcid;
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
index 445fe149ac0d..92148518f6a5 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
@@ -61,10 +61,7 @@ static struct mt76_wcid *mt7996_rx_get_wcid(struct mt7996_dev *dev,
 	struct mt76_wcid *wcid;
 	int i;
 
-	if (idx >= ARRAY_SIZE(dev->mt76.wcid))
-		return NULL;
-
-	wcid = rcu_dereference(dev->mt76.wcid[idx]);
+	wcid = mt76_wcid_ptr(dev, idx);
 	if (!wcid)
 		return NULL;
 
@@ -1249,7 +1246,7 @@ mt7996_mac_tx_free(struct mt7996_dev *dev, void *data, int len)
 			u16 idx;
 
 			idx = FIELD_GET(MT_TXFREE_INFO_WLAN_ID, info);
-			wcid = rcu_dereference(dev->mt76.wcid[idx]);
+			wcid = mt76_wcid_ptr(dev, idx);
 			sta = wcid_to_sta(wcid);
 			if (!sta)
 				goto next;
@@ -1471,12 +1468,9 @@ static void mt7996_mac_add_txs(struct mt7996_dev *dev, void *data)
 	if (pid < MT_PACKET_ID_NO_SKB)
 		return;
 
-	if (wcidx >= mt7996_wtbl_size(dev))
-		return;
-
 	rcu_read_lock();
 
-	wcid = rcu_dereference(dev->mt76.wcid[wcidx]);
+	wcid = mt76_wcid_ptr(dev, wcidx);
 	if (!wcid)
 		goto out;
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
index 77ab1f4854a4..994526c65bfc 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
@@ -555,7 +555,7 @@ mt7996_mcu_rx_all_sta_info_event(struct mt7996_dev *dev, struct sk_buff *skb)
 		switch (le16_to_cpu(res->tag)) {
 		case UNI_ALL_STA_TXRX_RATE:
 			wlan_idx = le16_to_cpu(res->rate[i].wlan_idx);
-			wcid = rcu_dereference(dev->mt76.wcid[wlan_idx]);
+			wcid = mt76_wcid_ptr(dev, wlan_idx);
 
 			if (!wcid)
 				break;
@@ -565,7 +565,7 @@ mt7996_mcu_rx_all_sta_info_event(struct mt7996_dev *dev, struct sk_buff *skb)
 			break;
 		case UNI_ALL_STA_TXRX_ADM_STAT:
 			wlan_idx = le16_to_cpu(res->adm_stat[i].wlan_idx);
-			wcid = rcu_dereference(dev->mt76.wcid[wlan_idx]);
+			wcid = mt76_wcid_ptr(dev, wlan_idx);
 
 			if (!wcid)
 				break;
@@ -579,7 +579,7 @@ mt7996_mcu_rx_all_sta_info_event(struct mt7996_dev *dev, struct sk_buff *skb)
 			break;
 		case UNI_ALL_STA_TXRX_MSDU_COUNT:
 			wlan_idx = le16_to_cpu(res->msdu_cnt[i].wlan_idx);
-			wcid = rcu_dereference(dev->mt76.wcid[wlan_idx]);
+			wcid = mt76_wcid_ptr(dev, wlan_idx);
 
 			if (!wcid)
 				break;
@@ -676,10 +676,7 @@ mt7996_mcu_wed_rro_event(struct mt7996_dev *dev, struct sk_buff *skb)
 
 			e = (void *)skb->data;
 			idx = le16_to_cpu(e->wlan_id);
-			if (idx >= ARRAY_SIZE(dev->mt76.wcid))
-				break;
-
-			wcid = rcu_dereference(dev->mt76.wcid[idx]);
+			wcid = mt76_wcid_ptr(dev, idx);
 			if (!wcid || !wcid->sta)
 				break;
 
diff --git a/drivers/net/wireless/mediatek/mt76/tx.c b/drivers/net/wireless/mediatek/mt76/tx.c
index 513916469ca2..251ee3ce5e4d 100644
--- a/drivers/net/wireless/mediatek/mt76/tx.c
+++ b/drivers/net/wireless/mediatek/mt76/tx.c
@@ -64,7 +64,7 @@ mt76_tx_status_unlock(struct mt76_dev *dev, struct sk_buff_head *list)
 		struct mt76_tx_cb *cb = mt76_tx_skb_cb(skb);
 		struct mt76_wcid *wcid;
 
-		wcid = rcu_dereference(dev->wcid[cb->wcid]);
+		wcid = __mt76_wcid_ptr(dev, cb->wcid);
 		if (wcid) {
 			status.sta = wcid_to_sta(wcid);
 			if (status.sta && (wcid->rate.flags || wcid->rate.legacy)) {
@@ -251,9 +251,7 @@ void __mt76_tx_complete_skb(struct mt76_dev *dev, u16 wcid_idx, struct sk_buff *
 
 	rcu_read_lock();
 
-	if (wcid_idx < ARRAY_SIZE(dev->wcid))
-		wcid = rcu_dereference(dev->wcid[wcid_idx]);
-
+	wcid = __mt76_wcid_ptr(dev, wcid_idx);
 	mt76_tx_check_non_aql(dev, wcid, skb);
 
 #ifdef CONFIG_NL80211_TESTMODE
@@ -538,7 +536,7 @@ mt76_txq_schedule_list(struct mt76_phy *phy, enum mt76_txq_id qid)
 			break;
 
 		mtxq = (struct mt76_txq *)txq->drv_priv;
-		wcid = rcu_dereference(dev->wcid[mtxq->wcid]);
+		wcid = __mt76_wcid_ptr(dev, mtxq->wcid);
 		if (!wcid || test_bit(MT_WCID_FLAG_PS, &wcid->flags))
 			continue;
 
diff --git a/drivers/net/wireless/mediatek/mt76/util.c b/drivers/net/wireless/mediatek/mt76/util.c
index 95b3dc96e4c4..97249ebb4bc8 100644
--- a/drivers/net/wireless/mediatek/mt76/util.c
+++ b/drivers/net/wireless/mediatek/mt76/util.c
@@ -83,7 +83,7 @@ int mt76_get_min_avg_rssi(struct mt76_dev *dev, u8 phy_idx)
 			if (!(mask & 1))
 				continue;
 
-			wcid = rcu_dereference(dev->wcid[j]);
+			wcid = __mt76_wcid_ptr(dev, j);
 			if (!wcid || wcid->phy_idx != phy_idx)
 				continue;
 

From dedf2ec30fe417d181490896adf89cd6b9885b23 Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Mon, 7 Jul 2025 17:47:02 +0200
Subject: [PATCH 1209/1334] wifi: mt76: fix queue assignment for deauth packets

When running in AP mode and deauthenticating a client that's in powersave
mode, the disassoc/deauth packet can get stuck in a tx queue along with
other buffered frames. This can fill up hardware queues with frames
that are only released after the WTBL slot is reused for another client.

Fix this by moving deauth packets to the ALTX queue.

Reported-by: Chad Monroe <chad.monroe@adtran.com>
Link: https://patch.msgid.link/20250707154702.1726-2-nbd@nbd.name
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/tx.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/mediatek/mt76/tx.c b/drivers/net/wireless/mediatek/mt76/tx.c
index 251ee3ce5e4d..e6cf16706667 100644
--- a/drivers/net/wireless/mediatek/mt76/tx.c
+++ b/drivers/net/wireless/mediatek/mt76/tx.c
@@ -615,7 +615,8 @@ mt76_txq_schedule_pending_wcid(struct mt76_phy *phy, struct mt76_wcid *wcid,
 		if ((dev->drv->drv_flags & MT_DRV_HW_MGMT_TXQ) &&
 		    !(info->flags & IEEE80211_TX_CTL_HW_80211_ENCAP) &&
 		    !ieee80211_is_data(hdr->frame_control) &&
-		    !ieee80211_is_bufferable_mmpdu(skb))
+		    (!ieee80211_is_bufferable_mmpdu(skb) ||
+		     ieee80211_is_deauth(hdr->frame_control)))
 			qid = MT_TXQ_PSD;
 
 		q = phy->q_tx[qid];

From 03ee8f73801a8f46d83dfc2bf73fb9ffa5a21602 Mon Sep 17 00:00:00 2001
From: Henry Martin <bsdhenrymartin@gmail.com>
Date: Wed, 25 Jun 2025 20:49:01 +0800
Subject: [PATCH 1210/1334] wifi: mt76: mt7925: Fix null-ptr-deref in
 mt7925_thermal_init()

devm_kasprintf() returns NULL on error. Currently, mt7925_thermal_init()
does not check for this case, which results in a NULL pointer
dereference.

Add NULL check after devm_kasprintf() to prevent this issue.

Fixes: 396e41a74a88 ("wifi: mt76: mt7925: support temperature sensor")
Signed-off-by: Henry Martin <bsdhenryma@tencent.com>
Reviewed-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
Link: https://patch.msgid.link/20250625124901.1839832-1-bsdhenryma@tencent.com
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt7925/init.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/init.c b/drivers/net/wireless/mediatek/mt76/mt7925/init.c
index 2a83ff59a968..4249bad83c93 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7925/init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7925/init.c
@@ -52,6 +52,8 @@ static int mt7925_thermal_init(struct mt792x_phy *phy)
 
 	name = devm_kasprintf(&wiphy->dev, GFP_KERNEL, "mt7925_%s",
 			      wiphy_name(wiphy));
+	if (!name)
+		return -ENOMEM;
 
 	hwmon = devm_hwmon_device_register_with_groups(&wiphy->dev, name, phy,
 						       mt7925_hwmon_groups);

From eb8352ee2d1e70f916fac02094dca2b435076fa4 Mon Sep 17 00:00:00 2001
From: Leon Yen <leon.yen@mediatek.com>
Date: Wed, 25 Jun 2025 15:37:20 +0800
Subject: [PATCH 1211/1334] wifi: mt76: mt792x: Limit the concurrent STA and
 SoftAP to operate on the same channel

Due to the lack of NoA(Notice of Absence) mechanism in SoftAP mode, it is
inappropriate to allow concurrent SoftAP and STA to operate on the
different channels.

This patch restricts the concurrent SoftAP and STA to be setup on the same
channel only.

Signed-off-by: Leon Yen <leon.yen@mediatek.com>
Signed-off-by: Ming Yen Hsieh <mingyen.hsieh@mediatek.com>
Link: https://patch.msgid.link/20250625073720.1385210-1-mingyen.hsieh@mediatek.com
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 .../net/wireless/mediatek/mt76/mt792x_core.c  | 32 ++++++++++++++++---
 1 file changed, 27 insertions(+), 5 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt792x_core.c b/drivers/net/wireless/mediatek/mt76/mt792x_core.c
index a50c1723ca29..05130ec1e5f7 100644
--- a/drivers/net/wireless/mediatek/mt76/mt792x_core.c
+++ b/drivers/net/wireless/mediatek/mt76/mt792x_core.c
@@ -28,7 +28,7 @@ static const struct ieee80211_iface_combination if_comb[] = {
 	},
 };
 
-static const struct ieee80211_iface_limit if_limits_chanctx[] = {
+static const struct ieee80211_iface_limit if_limits_chanctx_mcc[] = {
 	{
 		.max = 2,
 		.types = BIT(NL80211_IFTYPE_STATION) |
@@ -36,8 +36,23 @@ static const struct ieee80211_iface_limit if_limits_chanctx[] = {
 	},
 	{
 		.max = 1,
-		.types = BIT(NL80211_IFTYPE_AP) |
-			 BIT(NL80211_IFTYPE_P2P_GO)
+		.types = BIT(NL80211_IFTYPE_P2P_GO)
+	},
+	{
+		.max = 1,
+		.types = BIT(NL80211_IFTYPE_P2P_DEVICE)
+	}
+};
+
+static const struct ieee80211_iface_limit if_limits_chanctx_scc[] = {
+	{
+		.max = 2,
+		.types = BIT(NL80211_IFTYPE_STATION) |
+			 BIT(NL80211_IFTYPE_P2P_CLIENT)
+	},
+	{
+		.max = 1,
+		.types = BIT(NL80211_IFTYPE_AP)
 	},
 	{
 		.max = 1,
@@ -47,11 +62,18 @@ static const struct ieee80211_iface_limit if_limits_chanctx[] = {
 
 static const struct ieee80211_iface_combination if_comb_chanctx[] = {
 	{
-		.limits = if_limits_chanctx,
-		.n_limits = ARRAY_SIZE(if_limits_chanctx),
+		.limits = if_limits_chanctx_mcc,
+		.n_limits = ARRAY_SIZE(if_limits_chanctx_mcc),
 		.max_interfaces = 3,
 		.num_different_channels = 2,
 		.beacon_int_infra_match = false,
+	},
+	{
+		.limits = if_limits_chanctx_scc,
+		.n_limits = ARRAY_SIZE(if_limits_chanctx_scc),
+		.max_interfaces = 3,
+		.num_different_channels = 1,
+		.beacon_int_infra_match = false,
 	}
 };
 

From aa9552438ebf015fc5f9f890dbfe39f0c53cf37e Mon Sep 17 00:00:00 2001
From: Zheng Qixing <zhengqixing@huawei.com>
Date: Thu, 12 Jun 2025 21:24:05 +0800
Subject: [PATCH 1212/1334] nbd: fix uaf in nbd_genl_connect() error path

There is a use-after-free issue in nbd:

block nbd6: Receive control failed (result -104)
block nbd6: shutting down sockets
==================================================================
BUG: KASAN: slab-use-after-free in recv_work+0x694/0xa80 drivers/block/nbd.c:1022
Write of size 4 at addr ffff8880295de478 by task kworker/u33:0/67

CPU: 2 UID: 0 PID: 67 Comm: kworker/u33:0 Not tainted 6.15.0-rc5-syzkaller-00123-g2c89c1b655c0 #0 PREEMPT(full)
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.3-debian-1.16.3-2~bpo12+1 04/01/2014
Workqueue: nbd6-recv recv_work
Call Trace:
 <TASK>
 __dump_stack lib/dump_stack.c:94 [inline]
 dump_stack_lvl+0x116/0x1f0 lib/dump_stack.c:120
 print_address_description mm/kasan/report.c:408 [inline]
 print_report+0xc3/0x670 mm/kasan/report.c:521
 kasan_report+0xe0/0x110 mm/kasan/report.c:634
 check_region_inline mm/kasan/generic.c:183 [inline]
 kasan_check_range+0xef/0x1a0 mm/kasan/generic.c:189
 instrument_atomic_read_write include/linux/instrumented.h:96 [inline]
 atomic_dec include/linux/atomic/atomic-instrumented.h:592 [inline]
 recv_work+0x694/0xa80 drivers/block/nbd.c:1022
 process_one_work+0x9cc/0x1b70 kernel/workqueue.c:3238
 process_scheduled_works kernel/workqueue.c:3319 [inline]
 worker_thread+0x6c8/0xf10 kernel/workqueue.c:3400
 kthread+0x3c2/0x780 kernel/kthread.c:464
 ret_from_fork+0x45/0x80 arch/x86/kernel/process.c:153
 ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:245
 </TASK>

nbd_genl_connect() does not properly stop the device on certain
error paths after nbd_start_device() has been called. This causes
the error path to put nbd->config while recv_work continue to use
the config after putting it, leading to use-after-free in recv_work.

This patch moves nbd_start_device() after the backend file creation.

Reported-by: syzbot+48240bab47e705c53126@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/all/68227a04.050a0220.f2294.00b5.GAE@google.com/T/
Fixes: 6497ef8df568 ("nbd: provide a way for userspace processes to identify device backends")
Signed-off-by: Zheng Qixing <zhengqixing@huawei.com>
Reviewed-by: Yu Kuai <yukuai3@huawei.com>
Link: https://lore.kernel.org/r/20250612132405.364904-1-zhengqixing@huaweicloud.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/nbd.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 7bdc7eb808ea..2592bd19ebc1 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -2198,9 +2198,7 @@ again:
 				goto out;
 		}
 	}
-	ret = nbd_start_device(nbd);
-	if (ret)
-		goto out;
+
 	if (info->attrs[NBD_ATTR_BACKEND_IDENTIFIER]) {
 		nbd->backend = nla_strdup(info->attrs[NBD_ATTR_BACKEND_IDENTIFIER],
 					  GFP_KERNEL);
@@ -2216,6 +2214,8 @@ again:
 		goto out;
 	}
 	set_bit(NBD_RT_HAS_BACKEND_FILE, &config->runtime_flags);
+
+	ret = nbd_start_device(nbd);
 out:
 	mutex_unlock(&nbd->config_lock);
 	if (!ret) {

From 4cdf1bdd45ac78a088773722f009883af30ad318 Mon Sep 17 00:00:00 2001
From: Pankaj Raghav <p.raghav@samsung.com>
Date: Fri, 4 Jul 2025 11:21:34 +0200
Subject: [PATCH 1213/1334] block: reject bs > ps block devices when THP is
 disabled

If THP is disabled and when a block device with logical block size >
page size is present, the following null ptr deref panic happens during
boot:

[   [13.2 mK  AOSAN: null-ptr-deref in range [0x0000000000000000-0x0000000000K0 0 0[07]
[   13.017749] RIP: 0010:create_empty_buffers+0x3b/0x380
<snip>
[   13.025448] Call Trace:
[   13.025692]  <TASK>
[   13.025895]  block_read_full_folio+0x610/0x780
[   13.026379]  ? __pfx_blkdev_get_block+0x10/0x10
[   13.027008]  ? __folio_batch_add_and_move+0x1fa/0x2b0
[   13.027548]  ? __pfx_blkdev_read_folio+0x10/0x10
[   13.028080]  filemap_read_folio+0x9b/0x200
[   13.028526]  ? __pfx_filemap_read_folio+0x10/0x10
[   13.029030]  ? __filemap_get_folio+0x43/0x620
[   13.029497]  do_read_cache_folio+0x155/0x3b0
[   13.029962]  ? __pfx_blkdev_read_folio+0x10/0x10
[   13.030381]  read_part_sector+0xb7/0x2a0
[   13.030805]  read_lba+0x174/0x2c0
<snip>
[   13.045348]  nvme_scan_ns+0x684/0x850 [nvme_core]
[   13.045858]  ? __pfx_nvme_scan_ns+0x10/0x10 [nvme_core]
[   13.046414]  ? _raw_spin_unlock+0x15/0x40
[   13.046843]  ? __switch_to+0x523/0x10a0
[   13.047253]  ? kvm_clock_get_cycles+0x14/0x30
[   13.047742]  ? __pfx_nvme_scan_ns_async+0x10/0x10 [nvme_core]
[   13.048353]  async_run_entry_fn+0x96/0x4f0
[   13.048787]  process_one_work+0x667/0x10a0
[   13.049219]  worker_thread+0x63c/0xf60

As large folio support depends on THP, only allow bs > ps block devices
if THP is enabled.

Fixes: 47dd67532303 ("block/bdev: lift block size restrictions to 64k")
Signed-off-by: Pankaj Raghav <p.raghav@samsung.com>
Reviewed-by: Luis Chamberlain <mcgrof@kernel.org>
Link: https://lore.kernel.org/r/20250704092134.289491-1-p.raghav@samsung.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/blkdev.h | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 332b56f323d9..369a8e63c865 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -269,11 +269,16 @@ static inline dev_t disk_devt(struct gendisk *disk)
 	return MKDEV(disk->major, disk->first_minor);
 }
 
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
 /*
  * We should strive for 1 << (PAGE_SHIFT + MAX_PAGECACHE_ORDER)
  * however we constrain this to what we can validate and test.
  */
 #define BLK_MAX_BLOCK_SIZE      SZ_64K
+#else
+#define BLK_MAX_BLOCK_SIZE      PAGE_SIZE
+#endif
+
 
 /* blk_validate_limits() validates bsize, so drivers don't usually need to */
 static inline int blk_validate_block_size(unsigned long bsize)

From 7de3c8b4077e052a6f7880a9ae0f42342c49631b Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Sun, 6 Jul 2025 19:25:27 -0400
Subject: [PATCH 1214/1334] bcachefs: Don't schedule non persistent passes
 persistently

  if (!(in_recovery && (flags & RUN_RECOVERY_PASS_nopersistent)))

should have been

  if (!in_recovery && !(flags & RUN_RECOVERY_PASS_nopersistent)))

But the !in_recovery part was also wrong: the assumption is that if
we're in recovery we'll just rewind and run the recovery pass
immediately, but we're not able to do so if we've already gone RW and
the pass must be run before we go RW. In that case, we need to schedule
it in the superblock so it can be run on the next mount attempt.

Scheduling it persistently is fine, because it'll be cleared in the
superblock immediately when the pass completes successfully.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/recovery_passes.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/bcachefs/recovery_passes.c b/fs/bcachefs/recovery_passes.c
index c09ed2dd4639..6a039e011064 100644
--- a/fs/bcachefs/recovery_passes.c
+++ b/fs/bcachefs/recovery_passes.c
@@ -360,7 +360,7 @@ int __bch2_run_explicit_recovery_pass(struct bch_fs *c,
 		!(r->passes_complete & BIT_ULL(pass));
 	bool ratelimit = flags & RUN_RECOVERY_PASS_ratelimit;
 
-	if (!(in_recovery && (flags & RUN_RECOVERY_PASS_nopersistent))) {
+	if (!(flags & RUN_RECOVERY_PASS_nopersistent)) {
 		struct bch_sb_field_ext *ext = bch2_sb_field_get(c->disk_sb.sb, ext);
 		__set_bit_le64(bch2_recovery_pass_to_stable(pass), ext->recovery_passes_required);
 	}

From 74f3931a1bfea5822e8953a15c8ebc587dc6b4bc Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Mon, 7 Jul 2025 13:54:31 -0400
Subject: [PATCH 1215/1334] bcachefs: Fix additional misalignment in journal
 space calculations
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Additional fix on top of

f54b2a80d0df bcachefs: Fix misaligned bucket check in journal space calculations

Make sure that when we calculate space for the next entry it's not
misaligned: we need to round_down() to filesystem block size in multiple
places (next entry size calculation as well as total space available).

Reported-by: Ondřej Kraus <neverberlerfellerer@gmail.com>
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/journal_reclaim.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/fs/bcachefs/journal_reclaim.c b/fs/bcachefs/journal_reclaim.c
index cd6201741c59..0042d43b8e57 100644
--- a/fs/bcachefs/journal_reclaim.c
+++ b/fs/bcachefs/journal_reclaim.c
@@ -169,6 +169,12 @@ static struct journal_space __journal_space_available(struct journal *j, unsigne
 	if (nr_devs < nr_devs_want)
 		return (struct journal_space) { 0, 0 };
 
+	/*
+	 * It's possible for bucket size to be misaligned w.r.t. the filesystem
+	 * block size:
+	 */
+	min_bucket_size = round_down(min_bucket_size, block_sectors(c));
+
 	/*
 	 * We sorted largest to smallest, and we want the smallest out of the
 	 * @nr_devs_want largest devices:

From e31cf3cce2102af984656fed6e2254cbdd46da02 Mon Sep 17 00:00:00 2001
From: Luo Jie <quic_luoj@quicinc.com>
Date: Fri, 4 Jul 2025 13:31:13 +0800
Subject: [PATCH 1216/1334] net: phy: qcom: move the WoL function to shared
 library

Move the WoL (Wake-on-LAN) functionality to a shared library to enable
its reuse by the QCA808X PHY driver, incorporating support for WoL
functionality similar to the implementation in at8031_set_wol().

Reviewed-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Signed-off-by: Luo Jie <quic_luoj@quicinc.com>
Link: https://patch.msgid.link/20250704-qcom_phy_wol_support-v1-1-053342b1538d@quicinc.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/qcom/at803x.c       | 27 ---------------------------
 drivers/net/phy/qcom/qcom-phy-lib.c | 25 +++++++++++++++++++++++++
 drivers/net/phy/qcom/qcom.h         |  5 +++++
 3 files changed, 30 insertions(+), 27 deletions(-)

diff --git a/drivers/net/phy/qcom/at803x.c b/drivers/net/phy/qcom/at803x.c
index 26350b962890..8f26e395e39f 100644
--- a/drivers/net/phy/qcom/at803x.c
+++ b/drivers/net/phy/qcom/at803x.c
@@ -26,9 +26,6 @@
 
 #define AT803X_LED_CONTROL			0x18
 
-#define AT803X_PHY_MMD3_WOL_CTRL		0x8012
-#define AT803X_WOL_EN				BIT(5)
-
 #define AT803X_REG_CHIP_CONFIG			0x1f
 #define AT803X_BT_BX_REG_SEL			0x8000
 
@@ -866,30 +863,6 @@ static int at8031_config_init(struct phy_device *phydev)
 	return at803x_config_init(phydev);
 }
 
-static int at8031_set_wol(struct phy_device *phydev,
-			  struct ethtool_wolinfo *wol)
-{
-	int ret;
-
-	/* First setup MAC address and enable WOL interrupt */
-	ret = at803x_set_wol(phydev, wol);
-	if (ret)
-		return ret;
-
-	if (wol->wolopts & WAKE_MAGIC)
-		/* Enable WOL function for 1588 */
-		ret = phy_modify_mmd(phydev, MDIO_MMD_PCS,
-				     AT803X_PHY_MMD3_WOL_CTRL,
-				     0, AT803X_WOL_EN);
-	else
-		/* Disable WoL function for 1588 */
-		ret = phy_modify_mmd(phydev, MDIO_MMD_PCS,
-				     AT803X_PHY_MMD3_WOL_CTRL,
-				     AT803X_WOL_EN, 0);
-
-	return ret;
-}
-
 static int at8031_config_intr(struct phy_device *phydev)
 {
 	struct at803x_priv *priv = phydev->priv;
diff --git a/drivers/net/phy/qcom/qcom-phy-lib.c b/drivers/net/phy/qcom/qcom-phy-lib.c
index d28815ef56bb..af7d0d8e81be 100644
--- a/drivers/net/phy/qcom/qcom-phy-lib.c
+++ b/drivers/net/phy/qcom/qcom-phy-lib.c
@@ -115,6 +115,31 @@ int at803x_set_wol(struct phy_device *phydev,
 }
 EXPORT_SYMBOL_GPL(at803x_set_wol);
 
+int at8031_set_wol(struct phy_device *phydev,
+		   struct ethtool_wolinfo *wol)
+{
+	int ret;
+
+	/* First setup MAC address and enable WOL interrupt */
+	ret = at803x_set_wol(phydev, wol);
+	if (ret)
+		return ret;
+
+	if (wol->wolopts & WAKE_MAGIC)
+		/* Enable WOL function for 1588 */
+		ret = phy_modify_mmd(phydev, MDIO_MMD_PCS,
+				     AT803X_PHY_MMD3_WOL_CTRL,
+				     0, AT803X_WOL_EN);
+	else
+		/* Disable WoL function for 1588 */
+		ret = phy_modify_mmd(phydev, MDIO_MMD_PCS,
+				     AT803X_PHY_MMD3_WOL_CTRL,
+				     AT803X_WOL_EN, 0);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(at8031_set_wol);
+
 void at803x_get_wol(struct phy_device *phydev,
 		    struct ethtool_wolinfo *wol)
 {
diff --git a/drivers/net/phy/qcom/qcom.h b/drivers/net/phy/qcom/qcom.h
index 4bb541728846..7f7151c8baca 100644
--- a/drivers/net/phy/qcom/qcom.h
+++ b/drivers/net/phy/qcom/qcom.h
@@ -172,6 +172,9 @@
 #define AT803X_LOC_MAC_ADDR_16_31_OFFSET	0x804B
 #define AT803X_LOC_MAC_ADDR_32_47_OFFSET	0x804A
 
+#define AT803X_PHY_MMD3_WOL_CTRL		0x8012
+#define AT803X_WOL_EN				BIT(5)
+
 #define AT803X_DEBUG_ADDR			0x1D
 #define AT803X_DEBUG_DATA			0x1E
 
@@ -215,6 +218,8 @@ int at803x_debug_reg_mask(struct phy_device *phydev, u16 reg,
 int at803x_debug_reg_write(struct phy_device *phydev, u16 reg, u16 data);
 int at803x_set_wol(struct phy_device *phydev,
 		   struct ethtool_wolinfo *wol);
+int at8031_set_wol(struct phy_device *phydev,
+		   struct ethtool_wolinfo *wol);
 void at803x_get_wol(struct phy_device *phydev,
 		    struct ethtool_wolinfo *wol);
 int at803x_ack_interrupt(struct phy_device *phydev);

From 4ab9ada765b7acb5cd02fe27632ec2586b7868ee Mon Sep 17 00:00:00 2001
From: Luo Jie <quic_luoj@quicinc.com>
Date: Fri, 4 Jul 2025 13:31:14 +0800
Subject: [PATCH 1217/1334] net: phy: qcom: qca808x: Fix WoL issue by utilizing
 at8031_set_wol()

The previous commit unintentionally removed the code responsible for
enabling WoL via MMD3 register 0x8012 BIT5. As a result, Wake-on-LAN
(WoL) support for the QCA808X PHY is no longer functional.

The WoL (Wake-on-LAN) feature for the QCA808X PHY is enabled via MMD3
register 0x8012, BIT5. This implementation is aligned with the approach
used in at8031_set_wol().

Fixes: e58f30246c35 ("net: phy: at803x: fix the wol setting functions")
Signed-off-by: Luo Jie <quic_luoj@quicinc.com>
Reviewed-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Link: https://patch.msgid.link/20250704-qcom_phy_wol_support-v1-2-053342b1538d@quicinc.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/qcom/qca808x.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/phy/qcom/qca808x.c b/drivers/net/phy/qcom/qca808x.c
index 71498c518f0f..6de16c0eaa08 100644
--- a/drivers/net/phy/qcom/qca808x.c
+++ b/drivers/net/phy/qcom/qca808x.c
@@ -633,7 +633,7 @@ static struct phy_driver qca808x_driver[] = {
 	.handle_interrupt	= at803x_handle_interrupt,
 	.get_tunable		= at803x_get_tunable,
 	.set_tunable		= at803x_set_tunable,
-	.set_wol		= at803x_set_wol,
+	.set_wol		= at8031_set_wol,
 	.get_wol		= at803x_get_wol,
 	.get_features		= qca808x_get_features,
 	.config_aneg		= qca808x_config_aneg,

From ae8f160e7eb24240a2a79fc4c815c6a0d4ee16cc Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@google.com>
Date: Fri, 4 Jul 2025 05:48:18 +0000
Subject: [PATCH 1218/1334] netlink: Fix wraparounds of sk->sk_rmem_alloc.

Netlink has this pattern in some places

  if (atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf)
  	atomic_add(skb->truesize, &sk->sk_rmem_alloc);

, which has the same problem fixed by commit 5a465a0da13e ("udp:
Fix multiple wraparounds of sk->sk_rmem_alloc.").

For example, if we set INT_MAX to SO_RCVBUFFORCE, the condition
is always false as the two operands are of int.

Then, a single socket can eat as many skb as possible until OOM
happens, and we can see multiple wraparounds of sk->sk_rmem_alloc.

Let's fix it by using atomic_add_return() and comparing the two
variables as unsigned int.

Before:
  [root@fedora ~]# ss -f netlink
  Recv-Q      Send-Q Local Address:Port                Peer Address:Port
  -1668710080 0               rtnl:nl_wraparound/293               *

After:
  [root@fedora ~]# ss -f netlink
  Recv-Q     Send-Q Local Address:Port                Peer Address:Port
  2147483072 0               rtnl:nl_wraparound/290               *
  ^
  `--- INT_MAX - 576

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Reported-by: Jason Baron <jbaron@akamai.com>
Closes: https://lore.kernel.org/netdev/cover.1750285100.git.jbaron@akamai.com/
Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Link: https://patch.msgid.link/20250704054824.1580222-1-kuniyu@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/netlink/af_netlink.c | 89 ++++++++++++++++++++++++----------------
 1 file changed, 53 insertions(+), 36 deletions(-)

diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index e8972a857e51..79fbaf7333ce 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -387,7 +387,6 @@ static void netlink_skb_set_owner_r(struct sk_buff *skb, struct sock *sk)
 	WARN_ON(skb->sk != NULL);
 	skb->sk = sk;
 	skb->destructor = netlink_skb_destructor;
-	atomic_add(skb->truesize, &sk->sk_rmem_alloc);
 	sk_mem_charge(sk, skb->truesize);
 }
 
@@ -1212,41 +1211,48 @@ struct sk_buff *netlink_alloc_large_skb(unsigned int size, int broadcast)
 int netlink_attachskb(struct sock *sk, struct sk_buff *skb,
 		      long *timeo, struct sock *ssk)
 {
+	DECLARE_WAITQUEUE(wait, current);
 	struct netlink_sock *nlk;
+	unsigned int rmem;
 
 	nlk = nlk_sk(sk);
+	rmem = atomic_add_return(skb->truesize, &sk->sk_rmem_alloc);
 
-	if ((atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf ||
-	     test_bit(NETLINK_S_CONGESTED, &nlk->state))) {
-		DECLARE_WAITQUEUE(wait, current);
-		if (!*timeo) {
-			if (!ssk || netlink_is_kernel(ssk))
-				netlink_overrun(sk);
-			sock_put(sk);
-			kfree_skb(skb);
-			return -EAGAIN;
-		}
-
-		__set_current_state(TASK_INTERRUPTIBLE);
-		add_wait_queue(&nlk->wait, &wait);
-
-		if ((atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf ||
-		     test_bit(NETLINK_S_CONGESTED, &nlk->state)) &&
-		    !sock_flag(sk, SOCK_DEAD))
-			*timeo = schedule_timeout(*timeo);
-
-		__set_current_state(TASK_RUNNING);
-		remove_wait_queue(&nlk->wait, &wait);
-		sock_put(sk);
-
-		if (signal_pending(current)) {
-			kfree_skb(skb);
-			return sock_intr_errno(*timeo);
-		}
-		return 1;
+	if ((rmem == skb->truesize || rmem < READ_ONCE(sk->sk_rcvbuf)) &&
+	    !test_bit(NETLINK_S_CONGESTED, &nlk->state)) {
+		netlink_skb_set_owner_r(skb, sk);
+		return 0;
 	}
-	netlink_skb_set_owner_r(skb, sk);
-	return 0;
+
+	atomic_sub(skb->truesize, &sk->sk_rmem_alloc);
+
+	if (!*timeo) {
+		if (!ssk || netlink_is_kernel(ssk))
+			netlink_overrun(sk);
+		sock_put(sk);
+		kfree_skb(skb);
+		return -EAGAIN;
+	}
+
+	__set_current_state(TASK_INTERRUPTIBLE);
+	add_wait_queue(&nlk->wait, &wait);
+	rmem = atomic_read(&sk->sk_rmem_alloc);
+
+	if (((rmem && rmem + skb->truesize > READ_ONCE(sk->sk_rcvbuf)) ||
+	     test_bit(NETLINK_S_CONGESTED, &nlk->state)) &&
+	    !sock_flag(sk, SOCK_DEAD))
+		*timeo = schedule_timeout(*timeo);
+
+	__set_current_state(TASK_RUNNING);
+	remove_wait_queue(&nlk->wait, &wait);
+	sock_put(sk);
+
+	if (signal_pending(current)) {
+		kfree_skb(skb);
+		return sock_intr_errno(*timeo);
+	}
+
+	return 1;
 }
 
 static int __netlink_sendskb(struct sock *sk, struct sk_buff *skb)
@@ -1307,6 +1313,7 @@ static int netlink_unicast_kernel(struct sock *sk, struct sk_buff *skb,
 	ret = -ECONNREFUSED;
 	if (nlk->netlink_rcv != NULL) {
 		ret = skb->len;
+		atomic_add(skb->truesize, &sk->sk_rmem_alloc);
 		netlink_skb_set_owner_r(skb, sk);
 		NETLINK_CB(skb).sk = ssk;
 		netlink_deliver_tap_kernel(sk, ssk, skb);
@@ -1383,13 +1390,19 @@ EXPORT_SYMBOL_GPL(netlink_strict_get_check);
 static int netlink_broadcast_deliver(struct sock *sk, struct sk_buff *skb)
 {
 	struct netlink_sock *nlk = nlk_sk(sk);
+	unsigned int rmem, rcvbuf;
 
-	if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf &&
+	rmem = atomic_add_return(skb->truesize, &sk->sk_rmem_alloc);
+	rcvbuf = READ_ONCE(sk->sk_rcvbuf);
+
+	if ((rmem != skb->truesize || rmem <= rcvbuf) &&
 	    !test_bit(NETLINK_S_CONGESTED, &nlk->state)) {
 		netlink_skb_set_owner_r(skb, sk);
 		__netlink_sendskb(sk, skb);
-		return atomic_read(&sk->sk_rmem_alloc) > (sk->sk_rcvbuf >> 1);
+		return rmem > (rcvbuf >> 1);
 	}
+
+	atomic_sub(skb->truesize, &sk->sk_rmem_alloc);
 	return -1;
 }
 
@@ -2249,6 +2262,7 @@ static int netlink_dump(struct sock *sk, bool lock_taken)
 	struct module *module;
 	int err = -ENOBUFS;
 	int alloc_min_size;
+	unsigned int rmem;
 	int alloc_size;
 
 	if (!lock_taken)
@@ -2258,9 +2272,6 @@ static int netlink_dump(struct sock *sk, bool lock_taken)
 		goto errout_skb;
 	}
 
-	if (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf)
-		goto errout_skb;
-
 	/* NLMSG_GOODSIZE is small to avoid high order allocations being
 	 * required, but it makes sense to _attempt_ a 32KiB allocation
 	 * to reduce number of system calls on dump operations, if user
@@ -2283,6 +2294,12 @@ static int netlink_dump(struct sock *sk, bool lock_taken)
 	if (!skb)
 		goto errout_skb;
 
+	rmem = atomic_add_return(skb->truesize, &sk->sk_rmem_alloc);
+	if (rmem >= READ_ONCE(sk->sk_rcvbuf)) {
+		atomic_sub(skb->truesize, &sk->sk_rmem_alloc);
+		goto errout_skb;
+	}
+
 	/* Trim skb to allocated size. User is expected to provide buffer as
 	 * large as max(min_dump_alloc, 32KiB (max_recvmsg_len capped at
 	 * netlink_recvmsg())). dump will pack as many smaller messages as

From 1e3b66e326015f77bc4b36976bebeedc2ac0f588 Mon Sep 17 00:00:00 2001
From: Stefano Garzarella <sgarzare@redhat.com>
Date: Thu, 3 Jul 2025 13:23:29 +0200
Subject: [PATCH 1219/1334] vsock: fix `vsock_proto` declaration

From commit 634f1a7110b4 ("vsock: support sockmap"), `struct proto
vsock_proto`, defined in af_vsock.c, is not static anymore, since it's
used by vsock_bpf.c.

If CONFIG_BPF_SYSCALL is not defined, `make C=2` will print a warning:
    $ make O=build C=2 W=1 net/vmw_vsock/
      ...
      CC [M]  net/vmw_vsock/af_vsock.o
      CHECK   ../net/vmw_vsock/af_vsock.c
    ../net/vmw_vsock/af_vsock.c:123:14: warning: symbol 'vsock_proto' was not declared. Should it be static?

Declare `vsock_proto` regardless of CONFIG_BPF_SYSCALL, since it's defined
in af_vsock.c, which is built regardless of CONFIG_BPF_SYSCALL.

Fixes: 634f1a7110b4 ("vsock: support sockmap")
Signed-off-by: Stefano Garzarella <sgarzare@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Link: https://patch.msgid.link/20250703112329.28365-1-sgarzare@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/af_vsock.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h
index d56e6e135158..d40e978126e3 100644
--- a/include/net/af_vsock.h
+++ b/include/net/af_vsock.h
@@ -243,8 +243,8 @@ int __vsock_dgram_recvmsg(struct socket *sock, struct msghdr *msg,
 int vsock_dgram_recvmsg(struct socket *sock, struct msghdr *msg,
 			size_t len, int flags);
 
-#ifdef CONFIG_BPF_SYSCALL
 extern struct proto vsock_proto;
+#ifdef CONFIG_BPF_SYSCALL
 int vsock_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore);
 void __init vsock_bpf_build_proto(void);
 #else

From 667eeab4999e981c96b447a4df5f20bdf5c26f13 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@google.com>
Date: Wed, 2 Jul 2025 01:43:40 +0000
Subject: [PATCH 1220/1334] tipc: Fix use-after-free in tipc_conn_close().

syzbot reported a null-ptr-deref in tipc_conn_close() during netns
dismantle. [0]

tipc_topsrv_stop() iterates tipc_net(net)->topsrv->conn_idr and calls
tipc_conn_close() for each tipc_conn.

The problem is that tipc_conn_close() is called after releasing the
IDR lock.

At the same time, there might be tipc_conn_recv_work() running and it
could call tipc_conn_close() for the same tipc_conn and release its
last ->kref.

Once we release the IDR lock in tipc_topsrv_stop(), there is no
guarantee that the tipc_conn is alive.

Let's hold the ref before releasing the lock and put the ref after
tipc_conn_close() in tipc_topsrv_stop().

[0]:
BUG: KASAN: use-after-free in tipc_conn_close+0x122/0x140 net/tipc/topsrv.c:165
Read of size 8 at addr ffff888099305a08 by task kworker/u4:3/435

CPU: 0 PID: 435 Comm: kworker/u4:3 Not tainted 4.19.204-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Workqueue: netns cleanup_net
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x1fc/0x2ef lib/dump_stack.c:118
 print_address_description.cold+0x54/0x219 mm/kasan/report.c:256
 kasan_report_error.cold+0x8a/0x1b9 mm/kasan/report.c:354
 kasan_report mm/kasan/report.c:412 [inline]
 __asan_report_load8_noabort+0x88/0x90 mm/kasan/report.c:433
 tipc_conn_close+0x122/0x140 net/tipc/topsrv.c:165
 tipc_topsrv_stop net/tipc/topsrv.c:701 [inline]
 tipc_topsrv_exit_net+0x27b/0x5c0 net/tipc/topsrv.c:722
 ops_exit_list+0xa5/0x150 net/core/net_namespace.c:153
 cleanup_net+0x3b4/0x8b0 net/core/net_namespace.c:553
 process_one_work+0x864/0x1570 kernel/workqueue.c:2153
 worker_thread+0x64c/0x1130 kernel/workqueue.c:2296
 kthread+0x33f/0x460 kernel/kthread.c:259
 ret_from_fork+0x24/0x30 arch/x86/entry/entry_64.S:415

Allocated by task 23:
 kmem_cache_alloc_trace+0x12f/0x380 mm/slab.c:3625
 kmalloc include/linux/slab.h:515 [inline]
 kzalloc include/linux/slab.h:709 [inline]
 tipc_conn_alloc+0x43/0x4f0 net/tipc/topsrv.c:192
 tipc_topsrv_accept+0x1b5/0x280 net/tipc/topsrv.c:470
 process_one_work+0x864/0x1570 kernel/workqueue.c:2153
 worker_thread+0x64c/0x1130 kernel/workqueue.c:2296
 kthread+0x33f/0x460 kernel/kthread.c:259
 ret_from_fork+0x24/0x30 arch/x86/entry/entry_64.S:415

Freed by task 23:
 __cache_free mm/slab.c:3503 [inline]
 kfree+0xcc/0x210 mm/slab.c:3822
 tipc_conn_kref_release net/tipc/topsrv.c:150 [inline]
 kref_put include/linux/kref.h:70 [inline]
 conn_put+0x2cd/0x3a0 net/tipc/topsrv.c:155
 process_one_work+0x864/0x1570 kernel/workqueue.c:2153
 worker_thread+0x64c/0x1130 kernel/workqueue.c:2296
 kthread+0x33f/0x460 kernel/kthread.c:259
 ret_from_fork+0x24/0x30 arch/x86/entry/entry_64.S:415

The buggy address belongs to the object at ffff888099305a00
 which belongs to the cache kmalloc-512 of size 512
The buggy address is located 8 bytes inside of
 512-byte region [ffff888099305a00, ffff888099305c00)
The buggy address belongs to the page:
page:ffffea000264c140 count:1 mapcount:0 mapping:ffff88813bff0940 index:0x0
flags: 0xfff00000000100(slab)
raw: 00fff00000000100 ffffea00028b6b88 ffffea0002cd2b08 ffff88813bff0940
raw: 0000000000000000 ffff888099305000 0000000100000006 0000000000000000
page dumped because: kasan: bad access detected

Memory state around the buggy address:
 ffff888099305900: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
 ffff888099305980: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
>ffff888099305a00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
                      ^
 ffff888099305a80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
 ffff888099305b00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb

Fixes: c5fa7b3cf3cb ("tipc: introduce new TIPC server infrastructure")
Reported-by: syzbot+d333febcf8f4bc5f6110@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=27169a847a70550d17be
Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Reviewed-by: Tung Nguyen <tung.quang.nguyen@est.tech>
Link: https://patch.msgid.link/20250702014350.692213-1-kuniyu@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/tipc/topsrv.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/tipc/topsrv.c b/net/tipc/topsrv.c
index 8ee0c07d00e9..ffe577bf6b51 100644
--- a/net/tipc/topsrv.c
+++ b/net/tipc/topsrv.c
@@ -704,8 +704,10 @@ static void tipc_topsrv_stop(struct net *net)
 	for (id = 0; srv->idr_in_use; id++) {
 		con = idr_find(&srv->conn_idr, id);
 		if (con) {
+			conn_get(con);
 			spin_unlock_bh(&srv->idr_lock);
 			tipc_conn_close(con);
+			conn_put(con);
 			spin_lock_bh(&srv->idr_lock);
 		}
 	}

From ffc2c8c4a714df53a715827d6334ab9474424f6a Mon Sep 17 00:00:00 2001
From: Ryo Takakura <ryotkkr98@gmail.com>
Date: Wed, 2 Jul 2025 18:24:17 +0900
Subject: [PATCH 1221/1334] net: bcmgenet: Initialize u64 stats seq counter

Initialize u64 stats as it uses seq counter on 32bit machines
as suggested by lockdep below.

[    1.830953][    T1] INFO: trying to register non-static key.
[    1.830993][    T1] The code is fine but needs lockdep annotation, or maybe
[    1.831027][    T1] you didn't initialize this object before use?
[    1.831057][    T1] turning off the locking correctness validator.
[    1.831090][    T1] CPU: 1 UID: 0 PID: 1 Comm: swapper/0 Tainted: G        W           6.16.0-rc2-v7l+ #1 PREEMPT
[    1.831097][    T1] Tainted: [W]=WARN
[    1.831099][    T1] Hardware name: BCM2711
[    1.831101][    T1] Call trace:
[    1.831104][    T1]  unwind_backtrace from show_stack+0x18/0x1c
[    1.831120][    T1]  show_stack from dump_stack_lvl+0x8c/0xcc
[    1.831129][    T1]  dump_stack_lvl from register_lock_class+0x9e8/0x9fc
[    1.831141][    T1]  register_lock_class from __lock_acquire+0x420/0x22c0
[    1.831154][    T1]  __lock_acquire from lock_acquire+0x130/0x3f8
[    1.831166][    T1]  lock_acquire from bcmgenet_get_stats64+0x4a4/0x4c8
[    1.831176][    T1]  bcmgenet_get_stats64 from dev_get_stats+0x4c/0x408
[    1.831184][    T1]  dev_get_stats from rtnl_fill_stats+0x38/0x120
[    1.831193][    T1]  rtnl_fill_stats from rtnl_fill_ifinfo+0x7f8/0x1890
[    1.831203][    T1]  rtnl_fill_ifinfo from rtmsg_ifinfo_build_skb+0xd0/0x138
[    1.831214][    T1]  rtmsg_ifinfo_build_skb from rtmsg_ifinfo+0x48/0x8c
[    1.831225][    T1]  rtmsg_ifinfo from register_netdevice+0x8c0/0x95c
[    1.831237][    T1]  register_netdevice from register_netdev+0x28/0x40
[    1.831247][    T1]  register_netdev from bcmgenet_probe+0x690/0x6bc
[    1.831255][    T1]  bcmgenet_probe from platform_probe+0x64/0xbc
[    1.831263][    T1]  platform_probe from really_probe+0xd0/0x2d4
[    1.831269][    T1]  really_probe from __driver_probe_device+0x90/0x1a4
[    1.831273][    T1]  __driver_probe_device from driver_probe_device+0x38/0x11c
[    1.831278][    T1]  driver_probe_device from __driver_attach+0x9c/0x18c
[    1.831282][    T1]  __driver_attach from bus_for_each_dev+0x84/0xd4
[    1.831291][    T1]  bus_for_each_dev from bus_add_driver+0xd4/0x1f4
[    1.831303][    T1]  bus_add_driver from driver_register+0x88/0x120
[    1.831312][    T1]  driver_register from do_one_initcall+0x78/0x360
[    1.831320][    T1]  do_one_initcall from kernel_init_freeable+0x2bc/0x314
[    1.831331][    T1]  kernel_init_freeable from kernel_init+0x1c/0x144
[    1.831339][    T1]  kernel_init from ret_from_fork+0x14/0x20
[    1.831344][    T1] Exception stack(0xf082dfb0 to 0xf082dff8)
[    1.831349][    T1] dfa0:                                     00000000 00000000 00000000 00000000
[    1.831353][    T1] dfc0: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
[    1.831356][    T1] dfe0: 00000000 00000000 00000000 00000000 00000013 00000000

Fixes: 59aa6e3072aa ("net: bcmgenet: switch to use 64bit statistics")
Reviewed-by: Florian Fainelli <florian.fainelli@broadcom.com>
Signed-off-by: Ryo Takakura <ryotkkr98@gmail.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250702092417.46486-1-ryotkkr98@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/genet/bcmgenet.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index fa0077bc67b7..97585c160de3 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -4092,6 +4092,12 @@ static int bcmgenet_probe(struct platform_device *pdev)
 	for (i = 0; i <= priv->hw_params->rx_queues; i++)
 		priv->rx_rings[i].rx_max_coalesced_frames = 1;
 
+	/* Initialize u64 stats seq counter for 32bit machines */
+	for (i = 0; i <= priv->hw_params->rx_queues; i++)
+		u64_stats_init(&priv->rx_rings[i].stats64.syncp);
+	for (i = 0; i <= priv->hw_params->tx_queues; i++)
+		u64_stats_init(&priv->tx_rings[i].stats64.syncp);
+
 	/* libphy will determine the link state */
 	netif_carrier_off(dev);
 

From 705a412a367f383430fa34bada387af2e52eb043 Mon Sep 17 00:00:00 2001
From: Michal Wajdeczko <michal.wajdeczko@intel.com>
Date: Wed, 2 Jul 2025 00:00:52 +0200
Subject: [PATCH 1222/1334] drm/xe/pf: Clear all LMTT pages on alloc
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Our LMEM buffer objects are not cleared by default on alloc
and during VF provisioning we only setup LMTT PTEs for the
actually provisioned LMEM range. But beyond that valid range
we might leave some stale data that could either point to some
other VFs allocations or even to the PF pages.

Explicitly clear all new LMTT page to avoid the risk that a
malicious VF would try to exploit that gap.

While around add asserts to catch any undesired PTE overwrites
and low-level debug traces to track LMTT PT life-cycle.

Fixes: b1d204058218 ("drm/xe/pf: Introduce Local Memory Translation Table")
Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Michał Winiarski <michal.winiarski@intel.com>
Cc: Lukasz Laguna <lukasz.laguna@intel.com>
Reviewed-by: Michał Winiarski <michal.winiarski@intel.com>
Reviewed-by: Piotr Piórkowski <piotr.piorkowski@intel.com>
Link: https://lore.kernel.org/r/20250701220052.1612-1-michal.wajdeczko@intel.com
(cherry picked from commit 3fae6918a3e27cce20ded2551f863fb05d4bef8d)
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
---
 drivers/gpu/drm/xe/xe_lmtt.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/drivers/gpu/drm/xe/xe_lmtt.c b/drivers/gpu/drm/xe/xe_lmtt.c
index 63db66df064b..023ed6a6b49d 100644
--- a/drivers/gpu/drm/xe/xe_lmtt.c
+++ b/drivers/gpu/drm/xe/xe_lmtt.c
@@ -78,6 +78,9 @@ static struct xe_lmtt_pt *lmtt_pt_alloc(struct xe_lmtt *lmtt, unsigned int level
 	}
 
 	lmtt_assert(lmtt, xe_bo_is_vram(bo));
+	lmtt_debug(lmtt, "level=%u addr=%#llx\n", level, (u64)xe_bo_main_addr(bo, XE_PAGE_SIZE));
+
+	xe_map_memset(lmtt_to_xe(lmtt), &bo->vmap, 0, 0, bo->size);
 
 	pt->level = level;
 	pt->bo = bo;
@@ -91,6 +94,9 @@ out:
 
 static void lmtt_pt_free(struct xe_lmtt_pt *pt)
 {
+	lmtt_debug(&pt->bo->tile->sriov.pf.lmtt, "level=%u addr=%llx\n",
+		   pt->level, (u64)xe_bo_main_addr(pt->bo, XE_PAGE_SIZE));
+
 	xe_bo_unpin_map_no_vm(pt->bo);
 	kfree(pt);
 }
@@ -226,9 +232,14 @@ static void lmtt_write_pte(struct xe_lmtt *lmtt, struct xe_lmtt_pt *pt,
 
 	switch (lmtt->ops->lmtt_pte_size(level)) {
 	case sizeof(u32):
+		lmtt_assert(lmtt, !overflows_type(pte, u32));
+		lmtt_assert(lmtt, !pte || !iosys_map_rd(&pt->bo->vmap, idx * sizeof(u32), u32));
+
 		xe_map_wr(lmtt_to_xe(lmtt), &pt->bo->vmap, idx * sizeof(u32), u32, pte);
 		break;
 	case sizeof(u64):
+		lmtt_assert(lmtt, !pte || !iosys_map_rd(&pt->bo->vmap, idx * sizeof(u64), u64));
+
 		xe_map_wr(lmtt_to_xe(lmtt), &pt->bo->vmap, idx * sizeof(u64), u64, pte);
 		break;
 	default:

From c9a95dbe06102cf01afee4cd83ecb29f8d587a72 Mon Sep 17 00:00:00 2001
From: Matthew Brost <matthew.brost@intel.com>
Date: Wed, 2 Jul 2025 14:35:11 -0700
Subject: [PATCH 1223/1334] drm/xe: Allocate PF queue size on pow2 boundary

CIRC_SPACE does not work unless the size argument is a power of 2,
allocate PF queue size on power of 2 boundary.

Cc: stable@vger.kernel.org
Fixes: 3338e4f90c14 ("drm/xe: Use topology to determine page fault queue size")
Fixes: 29582e0ea75c ("drm/xe: Add page queue multiplier")
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Francois Dugast <francois.dugast@intel.com>
Link: https://lore.kernel.org/r/20250702213511.3226167-1-matthew.brost@intel.com
(cherry picked from commit 491b9783126303755717c0cbde0b08ee59b6abab)
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
---
 drivers/gpu/drm/xe/xe_gt_pagefault.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/xe/xe_gt_pagefault.c b/drivers/gpu/drm/xe/xe_gt_pagefault.c
index 10622ca471a2..6717a636b1d9 100644
--- a/drivers/gpu/drm/xe/xe_gt_pagefault.c
+++ b/drivers/gpu/drm/xe/xe_gt_pagefault.c
@@ -444,6 +444,7 @@ static int xe_alloc_pf_queue(struct xe_gt *gt, struct pf_queue *pf_queue)
 #define PF_MULTIPLIER	8
 	pf_queue->num_dw =
 		(num_eus + XE_NUM_HW_ENGINES) * PF_MSG_LEN_DW * PF_MULTIPLIER;
+	pf_queue->num_dw = roundup_pow_of_two(pf_queue->num_dw);
 #undef PF_MULTIPLIER
 
 	pf_queue->gt = gt;

From daa099fed50a39256feb37d3fac146bf0d74152f Mon Sep 17 00:00:00 2001
From: Matthew Brost <matthew.brost@intel.com>
Date: Tue, 1 Jul 2025 20:58:46 -0700
Subject: [PATCH 1224/1334] Revert "drm/xe/xe2: Enable Indirect Ring State
 support for Xe2"

This reverts commit fe0154cf8222d9e38c60ccc124adb2f9b5272371.

Seeing some unexplained random failures during LRC context switches with
indirect ring state enabled. The failures were always there, but the
repro rate increased with the addition of WA BB as a separate BO.
Commit 3a1edef8f4b5 ("drm/xe: Make WA BB part of LRC BO") helped to
reduce the issues in the context switches, but didn't eliminate them
completely.

Indirect ring state is not required for any current features, so disable
for now until failures can be root caused.

Cc: stable@vger.kernel.org
Fixes: fe0154cf8222 ("drm/xe/xe2: Enable Indirect Ring State support for Xe2")
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://lore.kernel.org/r/20250702035846.3178344-1-matthew.brost@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
(cherry picked from commit 03d85ab36bcbcbe9dc962fccd3f8e54d7bb93b35)
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
---
 drivers/gpu/drm/xe/xe_pci.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/gpu/drm/xe/xe_pci.c b/drivers/gpu/drm/xe/xe_pci.c
index ac4beaed58ff..278af53c74dc 100644
--- a/drivers/gpu/drm/xe/xe_pci.c
+++ b/drivers/gpu/drm/xe/xe_pci.c
@@ -140,7 +140,6 @@ static const struct xe_graphics_desc graphics_xelpg = {
 	.has_asid = 1, \
 	.has_atomic_enable_pte_bit = 1, \
 	.has_flat_ccs = 1, \
-	.has_indirect_ring_state = 1, \
 	.has_range_tlb_invalidation = 1, \
 	.has_usm = 1, \
 	.has_64bit_timestamp = 1, \

From fee58ca135a7b979c8b75e6d2eac60d695f9209b Mon Sep 17 00:00:00 2001
From: Matthew Auld <matthew.auld@intel.com>
Date: Tue, 1 Jul 2025 11:39:50 +0100
Subject: [PATCH 1225/1334] drm/xe/bmg: fix compressed VRAM handling
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

There looks to be an issue in our compression handling when the BO pages
are very fragmented, where we choose to skip the identity map and
instead fall back to emitting the PTEs by hand when migrating memory,
such that we can hopefully do more work per blit operation. However in
such a case we need to ensure the src PTEs are correctly tagged with a
compression enabled PAT index on dgpu xe2+, otherwise the copy will
simply treat the src memory as uncompressed, leading to corruption if
the memory was compressed by the user.

To fix this pass along use_comp_pat into emit_pte() on the src side, to
indicate that compression should be considered.

v2 (Jonathan): tweak the commit message

Fixes: 523f191cc0c7 ("drm/xe/xe_migrate: Handle migration logic for xe2+ dgfx")
Signed-off-by: Matthew Auld <matthew.auld@intel.com>
Cc: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
Cc: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Cc: Akshata Jahagirdar <akshata.jahagirdar@intel.com>
Cc: <stable@vger.kernel.org> # v6.12+
Reviewed-by: Jonathan Cavitt <jonathan.cavitt@intel.com>
Link: https://lore.kernel.org/r/20250701103949.83116-2-matthew.auld@intel.com
(cherry picked from commit f7a2fd776e57bd6468644bdecd91ab3aba57ba58)
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
---
 drivers/gpu/drm/xe/xe_migrate.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/xe/xe_migrate.c b/drivers/gpu/drm/xe/xe_migrate.c
index 7acdc4c78866..66bc02302c55 100644
--- a/drivers/gpu/drm/xe/xe_migrate.c
+++ b/drivers/gpu/drm/xe/xe_migrate.c
@@ -863,7 +863,7 @@ struct dma_fence *xe_migrate_copy(struct xe_migrate *m,
 		if (src_is_vram && xe_migrate_allow_identity(src_L0, &src_it))
 			xe_res_next(&src_it, src_L0);
 		else
-			emit_pte(m, bb, src_L0_pt, src_is_vram, copy_system_ccs,
+			emit_pte(m, bb, src_L0_pt, src_is_vram, copy_system_ccs || use_comp_pat,
 				 &src_it, src_L0, src);
 
 		if (dst_is_vram && xe_migrate_allow_identity(src_L0, &dst_it))

From 70b9c0c11e55167b9552ef395bc00f4920299177 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= <thomas.weissschuh@linutronix.de>
Date: Mon, 30 Jun 2025 15:02:18 +0200
Subject: [PATCH 1226/1334] uapi: bitops: use UAPI-safe variant of
 BITS_PER_LONG again (2)
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

BITS_PER_LONG does not exist in UAPI headers, so can't be used by the UAPI
__GENMASK(). Instead __BITS_PER_LONG needs to be used.

When __GENMASK() was introduced in commit 3c7a8e190bc5 ("uapi: introduce uapi-friendly macros for GENMASK"),
the code was fine. A broken revert in 1e7933a575ed ("uapi: Revert "bitops: avoid integer overflow in GENMASK(_ULL)"")
introduced the incorrect usage of BITS_PER_LONG.
That was fixed in commit 11fcf368506d ("uapi: bitops: use UAPI-safe variant of BITS_PER_LONG again").
But a broken sync of the kernel headers with the tools/ headers in
commit fc92099902fb ("tools headers: Synchronize linux/bits.h with the kernel sources")
undid the fix.

Reapply the fix and while at it also fix the tools header.

Fixes: fc92099902fb ("tools headers: Synchronize linux/bits.h with the kernel sources")
Signed-off-by: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Acked-by: Yury Norov (NVIDIA) <yury.norov@gmail.com>
Signed-off-by: Yury Norov (NVIDIA) <yury.norov@gmail.com>
---
 include/uapi/linux/bits.h       | 4 ++--
 tools/include/uapi/linux/bits.h | 4 ++--
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/include/uapi/linux/bits.h b/include/uapi/linux/bits.h
index 682b406e1067..a04afef9efca 100644
--- a/include/uapi/linux/bits.h
+++ b/include/uapi/linux/bits.h
@@ -4,9 +4,9 @@
 #ifndef _UAPI_LINUX_BITS_H
 #define _UAPI_LINUX_BITS_H
 
-#define __GENMASK(h, l) (((~_UL(0)) << (l)) & (~_UL(0) >> (BITS_PER_LONG - 1 - (h))))
+#define __GENMASK(h, l) (((~_UL(0)) << (l)) & (~_UL(0) >> (__BITS_PER_LONG - 1 - (h))))
 
-#define __GENMASK_ULL(h, l) (((~_ULL(0)) << (l)) & (~_ULL(0) >> (BITS_PER_LONG_LONG - 1 - (h))))
+#define __GENMASK_ULL(h, l) (((~_ULL(0)) << (l)) & (~_ULL(0) >> (__BITS_PER_LONG_LONG - 1 - (h))))
 
 #define __GENMASK_U128(h, l) \
 	((_BIT128((h)) << 1) - (_BIT128(l)))
diff --git a/tools/include/uapi/linux/bits.h b/tools/include/uapi/linux/bits.h
index 682b406e1067..a04afef9efca 100644
--- a/tools/include/uapi/linux/bits.h
+++ b/tools/include/uapi/linux/bits.h
@@ -4,9 +4,9 @@
 #ifndef _UAPI_LINUX_BITS_H
 #define _UAPI_LINUX_BITS_H
 
-#define __GENMASK(h, l) (((~_UL(0)) << (l)) & (~_UL(0) >> (BITS_PER_LONG - 1 - (h))))
+#define __GENMASK(h, l) (((~_UL(0)) << (l)) & (~_UL(0) >> (__BITS_PER_LONG - 1 - (h))))
 
-#define __GENMASK_ULL(h, l) (((~_ULL(0)) << (l)) & (~_ULL(0) >> (BITS_PER_LONG_LONG - 1 - (h))))
+#define __GENMASK_ULL(h, l) (((~_ULL(0)) << (l)) & (~_ULL(0) >> (__BITS_PER_LONG_LONG - 1 - (h))))
 
 #define __GENMASK_U128(h, l) \
 	((_BIT128((h)) << 1) - (_BIT128(l)))

From 1afc85deecd32ff0f9972b38ecfbddb8be63143e Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= <thomas.weissschuh@linutronix.de>
Date: Mon, 30 Jun 2025 15:09:35 +0200
Subject: [PATCH 1227/1334] MAINTAINERS: bitmap: add UAPI headers
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The UAPI headers have been split out from the kernel-only headers.
They maintained as part of the bitmap library.

Signed-off-by: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Signed-off-by: Yury Norov (NVIDIA) <yury.norov@gmail.com>
---
 MAINTAINERS | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index fad6cb025a19..a4ff43498c35 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -4181,6 +4181,7 @@ F:	include/linux/cpumask_types.h
 F:	include/linux/find.h
 F:	include/linux/nodemask.h
 F:	include/linux/nodemask_types.h
+F:	include/uapi/linux/bits.h
 F:	include/vdso/bits.h
 F:	lib/bitmap-str.c
 F:	lib/bitmap.c
@@ -4193,6 +4194,7 @@ F:	tools/include/linux/bitfield.h
 F:	tools/include/linux/bitmap.h
 F:	tools/include/linux/bits.h
 F:	tools/include/linux/find.h
+F:	tools/include/uapi/linux/bits.h
 F:	tools/include/vdso/bits.h
 F:	tools/lib/bitmap.c
 F:	tools/lib/find_bit.c

From d3a5f2871adc0c61c61869f37f3e697d97f03d8c Mon Sep 17 00:00:00 2001
From: Jiayuan Chen <jiayuan.chen@linux.dev>
Date: Mon, 7 Jul 2025 13:41:11 +0800
Subject: [PATCH 1228/1334] tcp: Correct signedness in skb remaining space
 calculation

Syzkaller reported a bug [1] where sk->sk_forward_alloc can overflow.

When we send data, if an skb exists at the tail of the write queue, the
kernel will attempt to append the new data to that skb. However, the code
that checks for available space in the skb is flawed:
'''
copy = size_goal - skb->len
'''

The types of the variables involved are:
'''
copy: ssize_t (s64 on 64-bit systems)
size_goal: int
skb->len: unsigned int
'''

Due to C's type promotion rules, the signed size_goal is converted to an
unsigned int to match skb->len before the subtraction. The result is an
unsigned int.

When this unsigned int result is then assigned to the s64 copy variable,
it is zero-extended, preserving its non-negative value. Consequently, copy
is always >= 0.

Assume we are sending 2GB of data and size_goal has been adjusted to a
value smaller than skb->len. The subtraction will result in copy holding a
very large positive integer. In the subsequent logic, this large value is
used to update sk->sk_forward_alloc, which can easily cause it to overflow.

The syzkaller reproducer uses TCP_REPAIR to reliably create this
condition. However, this can also occur in real-world scenarios. The
tcp_bound_to_half_wnd() function can also reduce size_goal to a small
value. This would cause the subsequent tcp_wmem_schedule() to set
sk->sk_forward_alloc to a value close to INT_MAX. Further memory
allocation requests would then cause sk_forward_alloc to wrap around and
become negative.

[1]: https://syzkaller.appspot.com/bug?extid=de6565462ab540f50e47

Reported-by: syzbot+de6565462ab540f50e47@syzkaller.appspotmail.com
Fixes: 270a1c3de47e ("tcp: Support MSG_SPLICE_PAGES")
Signed-off-by: Jiayuan Chen <jiayuan.chen@linux.dev>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: David Howells <dhowells@redhat.com>
Link: https://patch.msgid.link/20250707054112.101081-1-jiayuan.chen@linux.dev
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/tcp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index f64f8276a73c..461a9ab540af 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1176,7 +1176,7 @@ restart:
 		goto do_error;
 
 	while (msg_data_left(msg)) {
-		ssize_t copy = 0;
+		int copy = 0;
 
 		skb = tcp_write_queue_tail(sk);
 		if (skb)

From b3603c0466a85bed302e80226950092ceaf09b94 Mon Sep 17 00:00:00 2001
From: Chen-Yu Tsai <wens@csie.org>
Date: Sat, 28 Jun 2025 13:44:37 +0800
Subject: [PATCH 1229/1334] dt-bindings: net: sun8i-emac: Rename A523 EMAC0 to
 GMAC0

The datasheets refer to the first Ethernet controller as GMAC0, not
EMAC0.

Rename the compatible string to align with the datasheets. A fix for
the device trees will be sent separately.

Fixes: 0454b9057e98 ("dt-bindings: net: sun8i-emac: Add A523 EMAC0 compatible")
Signed-off-by: Chen-Yu Tsai <wens@csie.org>
Acked-by: Rob Herring (Arm) <robh@kernel.org>
Link: https://patch.msgid.link/20250628054438.2864220-2-wens@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../devicetree/bindings/net/allwinner,sun8i-a83t-emac.yaml      | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/net/allwinner,sun8i-a83t-emac.yaml b/Documentation/devicetree/bindings/net/allwinner,sun8i-a83t-emac.yaml
index 7b6a2fde8175..19934d5c24e5 100644
--- a/Documentation/devicetree/bindings/net/allwinner,sun8i-a83t-emac.yaml
+++ b/Documentation/devicetree/bindings/net/allwinner,sun8i-a83t-emac.yaml
@@ -23,7 +23,7 @@ properties:
               - allwinner,sun20i-d1-emac
               - allwinner,sun50i-h6-emac
               - allwinner,sun50i-h616-emac0
-              - allwinner,sun55i-a523-emac0
+              - allwinner,sun55i-a523-gmac0
           - const: allwinner,sun50i-a64-emac
 
   reg:

From 95a234f6affbf51f06338383537ab80d637bb785 Mon Sep 17 00:00:00 2001
From: Haoxiang Li <haoxiang_li2024@163.com>
Date: Thu, 3 Jul 2025 18:01:09 +0800
Subject: [PATCH 1230/1334] net: ethernet: rtsn: Fix a null pointer dereference
 in rtsn_probe()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add check for the return value of rcar_gen4_ptp_alloc()
to prevent potential null pointer dereference.

Fixes: b0d3969d2b4d ("net: ethernet: rtsn: Add support for Renesas Ethernet-TSN")
Cc: stable@vger.kernel.org
Signed-off-by: Haoxiang Li <haoxiang_li2024@163.com>
Reviewed-by: Niklas Söderlund <niklas.soderlund+renesas@ragnatech.se>
Link: https://patch.msgid.link/20250703100109.2541018-1-haoxiang_li2024@163.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/renesas/rtsn.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/net/ethernet/renesas/rtsn.c b/drivers/net/ethernet/renesas/rtsn.c
index 6b3f7fca8d15..05c4b6c8c9c3 100644
--- a/drivers/net/ethernet/renesas/rtsn.c
+++ b/drivers/net/ethernet/renesas/rtsn.c
@@ -1259,7 +1259,12 @@ static int rtsn_probe(struct platform_device *pdev)
 	priv = netdev_priv(ndev);
 	priv->pdev = pdev;
 	priv->ndev = ndev;
+
 	priv->ptp_priv = rcar_gen4_ptp_alloc(pdev);
+	if (!priv->ptp_priv) {
+		ret = -ENOMEM;
+		goto error_free;
+	}
 
 	spin_lock_init(&priv->lock);
 	platform_set_drvdata(pdev, priv);

From 209fd720838aaf1420416494c5505096478156b4 Mon Sep 17 00:00:00 2001
From: Michal Luczaj <mhal@rbox.co>
Date: Thu, 3 Jul 2025 17:18:18 +0200
Subject: [PATCH 1231/1334] vsock: Fix transport_{g2h,h2g} TOCTOU

vsock_find_cid() and vsock_dev_do_ioctl() may race with module unload.
transport_{g2h,h2g} may become NULL after the NULL check.

Introduce vsock_transport_local_cid() to protect from a potential
null-ptr-deref.

KASAN: null-ptr-deref in range [0x0000000000000118-0x000000000000011f]
RIP: 0010:vsock_find_cid+0x47/0x90
Call Trace:
 __vsock_bind+0x4b2/0x720
 vsock_bind+0x90/0xe0
 __sys_bind+0x14d/0x1e0
 __x64_sys_bind+0x6e/0xc0
 do_syscall_64+0x92/0x1c0
 entry_SYSCALL_64_after_hwframe+0x4b/0x53

KASAN: null-ptr-deref in range [0x0000000000000118-0x000000000000011f]
RIP: 0010:vsock_dev_do_ioctl.isra.0+0x58/0xf0
Call Trace:
 __x64_sys_ioctl+0x12d/0x190
 do_syscall_64+0x92/0x1c0
 entry_SYSCALL_64_after_hwframe+0x4b/0x53

Fixes: c0cfa2d8a788 ("vsock: add multi-transports support")
Suggested-by: Stefano Garzarella <sgarzare@redhat.com>
Reviewed-by: Stefano Garzarella <sgarzare@redhat.com>
Signed-off-by: Michal Luczaj <mhal@rbox.co>
Link: https://patch.msgid.link/20250703-vsock-transports-toctou-v4-1-98f0eb530747@rbox.co
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/vmw_vsock/af_vsock.c | 27 +++++++++++++++++++++------
 1 file changed, 21 insertions(+), 6 deletions(-)

diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index 2e7a3034e965..39473b9e0829 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -531,9 +531,25 @@ int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk)
 }
 EXPORT_SYMBOL_GPL(vsock_assign_transport);
 
+/*
+ * Provide safe access to static transport_{h2g,g2h,dgram,local} callbacks.
+ * Otherwise we may race with module removal. Do not use on `vsk->transport`.
+ */
+static u32 vsock_registered_transport_cid(const struct vsock_transport **transport)
+{
+	u32 cid = VMADDR_CID_ANY;
+
+	mutex_lock(&vsock_register_mutex);
+	if (*transport)
+		cid = (*transport)->get_local_cid();
+	mutex_unlock(&vsock_register_mutex);
+
+	return cid;
+}
+
 bool vsock_find_cid(unsigned int cid)
 {
-	if (transport_g2h && cid == transport_g2h->get_local_cid())
+	if (cid == vsock_registered_transport_cid(&transport_g2h))
 		return true;
 
 	if (transport_h2g && cid == VMADDR_CID_HOST)
@@ -2536,18 +2552,17 @@ static long vsock_dev_do_ioctl(struct file *filp,
 			       unsigned int cmd, void __user *ptr)
 {
 	u32 __user *p = ptr;
-	u32 cid = VMADDR_CID_ANY;
 	int retval = 0;
+	u32 cid;
 
 	switch (cmd) {
 	case IOCTL_VM_SOCKETS_GET_LOCAL_CID:
 		/* To be compatible with the VMCI behavior, we prioritize the
 		 * guest CID instead of well-know host CID (VMADDR_CID_HOST).
 		 */
-		if (transport_g2h)
-			cid = transport_g2h->get_local_cid();
-		else if (transport_h2g)
-			cid = transport_h2g->get_local_cid();
+		cid = vsock_registered_transport_cid(&transport_g2h);
+		if (cid == VMADDR_CID_ANY)
+			cid = vsock_registered_transport_cid(&transport_h2g);
 
 		if (put_user(cid, p) != 0)
 			retval = -EFAULT;

From 687aa0c5581b8d4aa87fd92973e4ee576b550cdf Mon Sep 17 00:00:00 2001
From: Michal Luczaj <mhal@rbox.co>
Date: Thu, 3 Jul 2025 17:18:19 +0200
Subject: [PATCH 1232/1334] vsock: Fix transport_* TOCTOU

Transport assignment may race with module unload. Protect new_transport
from becoming a stale pointer.

This also takes care of an insecure call in vsock_use_local_transport();
add a lockdep assert.

BUG: unable to handle page fault for address: fffffbfff8056000
Oops: Oops: 0000 [#1] SMP KASAN
RIP: 0010:vsock_assign_transport+0x366/0x600
Call Trace:
 vsock_connect+0x59c/0xc40
 __sys_connect+0xe8/0x100
 __x64_sys_connect+0x6e/0xc0
 do_syscall_64+0x92/0x1c0
 entry_SYSCALL_64_after_hwframe+0x4b/0x53

Fixes: c0cfa2d8a788 ("vsock: add multi-transports support")
Reviewed-by: Stefano Garzarella <sgarzare@redhat.com>
Signed-off-by: Michal Luczaj <mhal@rbox.co>
Link: https://patch.msgid.link/20250703-vsock-transports-toctou-v4-2-98f0eb530747@rbox.co
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/vmw_vsock/af_vsock.c | 28 +++++++++++++++++++++++-----
 1 file changed, 23 insertions(+), 5 deletions(-)

diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index 39473b9e0829..66404c06bdaa 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -407,6 +407,8 @@ EXPORT_SYMBOL_GPL(vsock_enqueue_accept);
 
 static bool vsock_use_local_transport(unsigned int remote_cid)
 {
+	lockdep_assert_held(&vsock_register_mutex);
+
 	if (!transport_local)
 		return false;
 
@@ -464,6 +466,8 @@ int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk)
 
 	remote_flags = vsk->remote_addr.svm_flags;
 
+	mutex_lock(&vsock_register_mutex);
+
 	switch (sk->sk_type) {
 	case SOCK_DGRAM:
 		new_transport = transport_dgram;
@@ -479,12 +483,15 @@ int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk)
 			new_transport = transport_h2g;
 		break;
 	default:
-		return -ESOCKTNOSUPPORT;
+		ret = -ESOCKTNOSUPPORT;
+		goto err;
 	}
 
 	if (vsk->transport) {
-		if (vsk->transport == new_transport)
-			return 0;
+		if (vsk->transport == new_transport) {
+			ret = 0;
+			goto err;
+		}
 
 		/* transport->release() must be called with sock lock acquired.
 		 * This path can only be taken during vsock_connect(), where we
@@ -508,8 +515,16 @@ int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk)
 	/* We increase the module refcnt to prevent the transport unloading
 	 * while there are open sockets assigned to it.
 	 */
-	if (!new_transport || !try_module_get(new_transport->module))
-		return -ENODEV;
+	if (!new_transport || !try_module_get(new_transport->module)) {
+		ret = -ENODEV;
+		goto err;
+	}
+
+	/* It's safe to release the mutex after a successful try_module_get().
+	 * Whichever transport `new_transport` points at, it won't go away until
+	 * the last module_put() below or in vsock_deassign_transport().
+	 */
+	mutex_unlock(&vsock_register_mutex);
 
 	if (sk->sk_type == SOCK_SEQPACKET) {
 		if (!new_transport->seqpacket_allow ||
@@ -528,6 +543,9 @@ int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk)
 	vsk->transport = new_transport;
 
 	return 0;
+err:
+	mutex_unlock(&vsock_register_mutex);
+	return ret;
 }
 EXPORT_SYMBOL_GPL(vsock_assign_transport);
 

From 1e7d9df379a04ccd0c2f82f39fbb69d482e864cc Mon Sep 17 00:00:00 2001
From: Michal Luczaj <mhal@rbox.co>
Date: Thu, 3 Jul 2025 17:18:20 +0200
Subject: [PATCH 1233/1334] vsock: Fix IOCTL_VM_SOCKETS_GET_LOCAL_CID to check
 also `transport_local`

Support returning VMADDR_CID_LOCAL in case no other vsock transport is
available.

Fixes: 0e12190578d0 ("vsock: add local transport support in the vsock core")
Suggested-by: Stefano Garzarella <sgarzare@redhat.com>
Reviewed-by: Stefano Garzarella <sgarzare@redhat.com>
Signed-off-by: Michal Luczaj <mhal@rbox.co>
Link: https://patch.msgid.link/20250703-vsock-transports-toctou-v4-3-98f0eb530747@rbox.co
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/vmw_vsock/af_vsock.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index 66404c06bdaa..1053662725f8 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -2581,6 +2581,8 @@ static long vsock_dev_do_ioctl(struct file *filp,
 		cid = vsock_registered_transport_cid(&transport_g2h);
 		if (cid == VMADDR_CID_ANY)
 			cid = vsock_registered_transport_cid(&transport_h2g);
+		if (cid == VMADDR_CID_ANY)
+			cid = vsock_registered_transport_cid(&transport_local);
 
 		if (put_user(cid, p) != 0)
 			retval = -EFAULT;

From 3ef07434c7dbfba302df477bb6c70e082965f232 Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Sat, 5 Jul 2025 10:34:32 +0200
Subject: [PATCH 1234/1334] net: airoha: Fix an error handling path in
 airoha_probe()

If an error occurs after a successful airoha_hw_init() call,
airoha_ppe_deinit() needs to be called as already done in the remove
function.

Fixes: 00a7678310fe ("net: airoha: Introduce flowtable offload support")
Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Reviewed-by: Simon Horman <horms@kernel.org>
Acked-by: Lorenzo Bianconi <lorenzo@kernel.org>
Link: https://patch.msgid.link/1c940851b4fa3c3ed2a142910c821493a136f121.1746715755.git.christophe.jaillet@wanadoo.fr
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/airoha/airoha_eth.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/airoha/airoha_eth.c b/drivers/net/ethernet/airoha/airoha_eth.c
index 06dea3a13e77..9057180051df 100644
--- a/drivers/net/ethernet/airoha/airoha_eth.c
+++ b/drivers/net/ethernet/airoha/airoha_eth.c
@@ -2984,6 +2984,7 @@ static int airoha_probe(struct platform_device *pdev)
 error_napi_stop:
 	for (i = 0; i < ARRAY_SIZE(eth->qdma); i++)
 		airoha_qdma_stop_napi(&eth->qdma[i]);
+	airoha_ppe_deinit(eth);
 error_hw_cleanup:
 	for (i = 0; i < ARRAY_SIZE(eth->qdma); i++)
 		airoha_hw_cleanup(&eth->qdma[i]);

From 0c2b53997e8f5e2ec9e0fbd17ac0436466b65488 Mon Sep 17 00:00:00 2001
From: Stefan Metzmacher <metze@samba.org>
Date: Wed, 2 Jul 2025 09:18:05 +0200
Subject: [PATCH 1235/1334] smb: server: make use of rdma_destroy_qp()

The qp is created by rdma_create_qp() as t->cm_id->qp
and t->qp is just a shortcut.

rdma_destroy_qp() also calls ib_destroy_qp(cm_id->qp) internally,
but it is protected by a mutex, clears the cm_id and also calls
trace_cm_qp_destroy().

This should make the tracing more useful as both
rdma_create_qp() and rdma_destroy_qp() are traces and it makes
the code look more sane as functions from the same layer are used
for the specific qp object.

trace-cmd stream -e rdma_cma:cm_qp_create -e rdma_cma:cm_qp_destroy
shows this now while doing a mount and unmount from a client:

  <...>-80   [002] 378.514182: cm_qp_create:  cm.id=1 src=172.31.9.167:5445 dst=172.31.9.166:37113 tos=0 pd.id=0 qp_type=RC send_wr=867 recv_wr=255 qp_num=1 rc=0
  <...>-6283 [001] 381.686172: cm_qp_destroy: cm.id=1 src=172.31.9.167:5445 dst=172.31.9.166:37113 tos=0 qp_num=1

Before we only saw the first line.

Cc: Namjae Jeon <linkinjeon@kernel.org>
Cc: Steve French <stfrench@microsoft.com>
Cc: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Cc: Hyunchul Lee <hyc.lee@gmail.com>
Cc: Tom Talpey <tom@talpey.com>
Cc: linux-cifs@vger.kernel.org
Fixes: 0626e6641f6b ("cifsd: add server handler for central processing and tranport layers")
Signed-off-by: Stefan Metzmacher <metze@samba.org>
Reviewed-by: Tom Talpey <tom@talpey.com>
Acked-by: Namjae Jeon <linkinjeon@kernel.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/server/transport_rdma.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/fs/smb/server/transport_rdma.c b/fs/smb/server/transport_rdma.c
index 64a428a06ace..c6cbe0d56e32 100644
--- a/fs/smb/server/transport_rdma.c
+++ b/fs/smb/server/transport_rdma.c
@@ -433,7 +433,8 @@ static void free_transport(struct smb_direct_transport *t)
 	if (t->qp) {
 		ib_drain_qp(t->qp);
 		ib_mr_pool_destroy(t->qp, &t->qp->rdma_mrs);
-		ib_destroy_qp(t->qp);
+		t->qp = NULL;
+		rdma_destroy_qp(t->cm_id);
 	}
 
 	ksmbd_debug(RDMA, "drain the reassembly queue\n");
@@ -1940,8 +1941,8 @@ static int smb_direct_create_qpair(struct smb_direct_transport *t,
 	return 0;
 err:
 	if (t->qp) {
-		ib_destroy_qp(t->qp);
 		t->qp = NULL;
+		rdma_destroy_qp(t->cm_id);
 	}
 	if (t->recv_cq) {
 		ib_destroy_cq(t->recv_cq);

From 277627b431a0a6401635c416a21b2a0f77a77347 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sun, 6 Jul 2025 02:26:45 +0100
Subject: [PATCH 1236/1334] ksmbd: fix a mount write count leak in
 ksmbd_vfs_kern_path_locked()

If the call of ksmbd_vfs_lock_parent() fails, we drop the parent_path
references and return an error.  We need to drop the write access we
just got on parent_path->mnt before we drop the mount reference - callers
assume that ksmbd_vfs_kern_path_locked() returns with mount write
access grabbed if and only if it has returned 0.

Fixes: 864fb5d37163 ("ksmbd: fix possible deadlock in smb2_open")
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Acked-by: Namjae Jeon <linkinjeon@kernel.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/server/vfs.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/fs/smb/server/vfs.c b/fs/smb/server/vfs.c
index 0f3aad12e495..d3437f6644e3 100644
--- a/fs/smb/server/vfs.c
+++ b/fs/smb/server/vfs.c
@@ -1282,6 +1282,7 @@ out1:
 
 		err = ksmbd_vfs_lock_parent(parent_path->dentry, path->dentry);
 		if (err) {
+			mnt_drop_write(parent_path->mnt);
 			path_put(path);
 			path_put(parent_path);
 		}

From 50f930db22365738d9387c974416f38a06e8057e Mon Sep 17 00:00:00 2001
From: Namjae Jeon <linkinjeon@kernel.org>
Date: Tue, 8 Jul 2025 07:47:40 +0900
Subject: [PATCH 1237/1334] ksmbd: fix potential use-after-free in oplock/lease
 break ack

If ksmbd_iov_pin_rsp return error, use-after-free can happen by
accessing opinfo->state and opinfo_put and ksmbd_fd_put could
called twice.

Reported-by: Ziyan Xu <research@securitygossip.com>
Signed-off-by: Namjae Jeon <linkinjeon@kernel.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/server/smb2pdu.c | 29 +++++++++--------------------
 1 file changed, 9 insertions(+), 20 deletions(-)

diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c
index fafa86273f12..63d17cea2e95 100644
--- a/fs/smb/server/smb2pdu.c
+++ b/fs/smb/server/smb2pdu.c
@@ -8573,11 +8573,6 @@ static void smb20_oplock_break_ack(struct ksmbd_work *work)
 		goto err_out;
 	}
 
-	opinfo->op_state = OPLOCK_STATE_NONE;
-	wake_up_interruptible_all(&opinfo->oplock_q);
-	opinfo_put(opinfo);
-	ksmbd_fd_put(work, fp);
-
 	rsp->StructureSize = cpu_to_le16(24);
 	rsp->OplockLevel = rsp_oplevel;
 	rsp->Reserved = 0;
@@ -8585,16 +8580,15 @@ static void smb20_oplock_break_ack(struct ksmbd_work *work)
 	rsp->VolatileFid = volatile_id;
 	rsp->PersistentFid = persistent_id;
 	ret = ksmbd_iov_pin_rsp(work, rsp, sizeof(struct smb2_oplock_break));
-	if (!ret)
-		return;
-
+	if (ret) {
 err_out:
+		smb2_set_err_rsp(work);
+	}
+
 	opinfo->op_state = OPLOCK_STATE_NONE;
 	wake_up_interruptible_all(&opinfo->oplock_q);
-
 	opinfo_put(opinfo);
 	ksmbd_fd_put(work, fp);
-	smb2_set_err_rsp(work);
 }
 
 static int check_lease_state(struct lease *lease, __le32 req_state)
@@ -8724,11 +8718,6 @@ static void smb21_lease_break_ack(struct ksmbd_work *work)
 	}
 
 	lease_state = lease->state;
-	opinfo->op_state = OPLOCK_STATE_NONE;
-	wake_up_interruptible_all(&opinfo->oplock_q);
-	atomic_dec(&opinfo->breaking_cnt);
-	wake_up_interruptible_all(&opinfo->oplock_brk);
-	opinfo_put(opinfo);
 
 	rsp->StructureSize = cpu_to_le16(36);
 	rsp->Reserved = 0;
@@ -8737,16 +8726,16 @@ static void smb21_lease_break_ack(struct ksmbd_work *work)
 	rsp->LeaseState = lease_state;
 	rsp->LeaseDuration = 0;
 	ret = ksmbd_iov_pin_rsp(work, rsp, sizeof(struct smb2_lease_ack));
-	if (!ret)
-		return;
-
+	if (ret) {
 err_out:
+		smb2_set_err_rsp(work);
+	}
+
+	opinfo->op_state = OPLOCK_STATE_NONE;
 	wake_up_interruptible_all(&opinfo->oplock_q);
 	atomic_dec(&opinfo->breaking_cnt);
 	wake_up_interruptible_all(&opinfo->oplock_brk);
-
 	opinfo_put(opinfo);
-	smb2_set_err_rsp(work);
 }
 
 /**

From fc582cd26e888b0652bc1494f252329453fd3b23 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Tue, 8 Jul 2025 11:00:32 -0600
Subject: [PATCH 1238/1334] io_uring/msg_ring: ensure io_kiocb freeing is
 deferred for RCU

syzbot reports that defer/local task_work adding via msg_ring can hit
a request that has been freed:

CPU: 1 UID: 0 PID: 19356 Comm: iou-wrk-19354 Not tainted 6.16.0-rc4-syzkaller-00108-g17bbde2e1716 #0 PREEMPT(full)
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 05/07/2025
Call Trace:
 <TASK>
 dump_stack_lvl+0x189/0x250 lib/dump_stack.c:120
 print_address_description mm/kasan/report.c:408 [inline]
 print_report+0xd2/0x2b0 mm/kasan/report.c:521
 kasan_report+0x118/0x150 mm/kasan/report.c:634
 io_req_local_work_add io_uring/io_uring.c:1184 [inline]
 __io_req_task_work_add+0x589/0x950 io_uring/io_uring.c:1252
 io_msg_remote_post io_uring/msg_ring.c:103 [inline]
 io_msg_data_remote io_uring/msg_ring.c:133 [inline]
 __io_msg_ring_data+0x820/0xaa0 io_uring/msg_ring.c:151
 io_msg_ring_data io_uring/msg_ring.c:173 [inline]
 io_msg_ring+0x134/0xa00 io_uring/msg_ring.c:314
 __io_issue_sqe+0x17e/0x4b0 io_uring/io_uring.c:1739
 io_issue_sqe+0x165/0xfd0 io_uring/io_uring.c:1762
 io_wq_submit_work+0x6e9/0xb90 io_uring/io_uring.c:1874
 io_worker_handle_work+0x7cd/0x1180 io_uring/io-wq.c:642
 io_wq_worker+0x42f/0xeb0 io_uring/io-wq.c:696
 ret_from_fork+0x3fc/0x770 arch/x86/kernel/process.c:148
 ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:245
 </TASK>

which is supposed to be safe with how requests are allocated. But msg
ring requests alloc and free on their own, and hence must defer freeing
to a sane time.

Add an rcu_head and use kfree_rcu() in both spots where requests are
freed. Only the one in io_msg_tw_complete() is strictly required as it
has been visible on the other ring, but use it consistently in the other
spot as well.

This should not cause any other issues outside of KASAN rightfully
complaining about it.

Link: https://lore.kernel.org/io-uring/686cd2ea.a00a0220.338033.0007.GAE@google.com/
Reported-by: syzbot+54cbbfb4db9145d26fc2@syzkaller.appspotmail.com
Cc: stable@vger.kernel.org
Fixes: 0617bb500bfa ("io_uring/msg_ring: improve handling of target CQE posting")
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/io_uring_types.h | 2 ++
 io_uring/msg_ring.c            | 4 ++--
 2 files changed, 4 insertions(+), 2 deletions(-)

diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h
index 2922635986f5..a7efcec2e3d0 100644
--- a/include/linux/io_uring_types.h
+++ b/include/linux/io_uring_types.h
@@ -698,6 +698,8 @@ struct io_kiocb {
 		struct hlist_node	hash_node;
 		/* For IOPOLL setup queues, with hybrid polling */
 		u64                     iopoll_start;
+		/* for private io_kiocb freeing */
+		struct rcu_head		rcu_head;
 	};
 	/* internal polling, see IORING_FEAT_FAST_POLL */
 	struct async_poll		*apoll;
diff --git a/io_uring/msg_ring.c b/io_uring/msg_ring.c
index 71400d6cefc8..4c2578f2efcb 100644
--- a/io_uring/msg_ring.c
+++ b/io_uring/msg_ring.c
@@ -82,7 +82,7 @@ static void io_msg_tw_complete(struct io_kiocb *req, io_tw_token_t tw)
 		spin_unlock(&ctx->msg_lock);
 	}
 	if (req)
-		kmem_cache_free(req_cachep, req);
+		kfree_rcu(req, rcu_head);
 	percpu_ref_put(&ctx->refs);
 }
 
@@ -90,7 +90,7 @@ static int io_msg_remote_post(struct io_ring_ctx *ctx, struct io_kiocb *req,
 			      int res, u32 cflags, u64 user_data)
 {
 	if (!READ_ONCE(ctx->submitter_task)) {
-		kmem_cache_free(req_cachep, req);
+		kfree_rcu(req, rcu_head);
 		return -EOWNERDEAD;
 	}
 	req->opcode = IORING_OP_NOP;

From 9dff55ebaef7e94e5dedb6be28a1cafff65cc467 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Tue, 8 Jul 2025 11:04:45 -0600
Subject: [PATCH 1239/1334] Revert "io_uring: gate REQ_F_ISREG on !S_ANON_INODE
 as well"

This reverts commit 6f11adcc6f36ffd8f33dbdf5f5ce073368975bc3.

The problematic commit was fixed in mainline, so the work-around in
io_uring can be removed at this point. Anonymous inodes no longer
pretend to be regular files after:

1e7ab6f67824 ("anon_inode: rework assertions")

Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/io_uring.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index 73648d26a622..5111ec040c53 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -1666,12 +1666,11 @@ static void io_iopoll_req_issued(struct io_kiocb *req, unsigned int issue_flags)
 
 io_req_flags_t io_file_get_flags(struct file *file)
 {
-	struct inode *inode = file_inode(file);
 	io_req_flags_t res = 0;
 
 	BUILD_BUG_ON(REQ_F_ISREG_BIT != REQ_F_SUPPORT_NOWAIT_BIT + 1);
 
-	if (S_ISREG(inode->i_mode) && !(inode->i_flags & S_ANON_INODE))
+	if (S_ISREG(file_inode(file)->i_mode))
 		res |= REQ_F_ISREG;
 	if ((file->f_flags & O_NONBLOCK) || (file->f_mode & FMODE_NOWAIT))
 		res |= REQ_F_SUPPORT_NOWAIT;

From ca3881f6fd8e9b6eb2d51e8718d07d3b8029d886 Mon Sep 17 00:00:00 2001
From: Petr Pavlu <petr.pavlu@suse.com>
Date: Wed, 18 Jun 2025 14:26:26 +0200
Subject: [PATCH 1240/1334] module: Fix memory deallocation on error path in
 move_module()

The function move_module() uses the variable t to track how many memory
types it has allocated and consequently how many should be freed if an
error occurs.

The variable is initially set to 0 and is updated when a call to
module_memory_alloc() fails. However, move_module() can fail for other
reasons as well, in which case t remains set to 0 and no memory is freed.

Fix the problem by initializing t to MOD_MEM_NUM_TYPES. Additionally, make
the deallocation loop more robust by not relying on the mod_mem_type_t enum
having a signed integer as its underlying type.

Fixes: c7ee8aebf6c0 ("module: add stop-grap sanity check on module memcpy()")
Signed-off-by: Petr Pavlu <petr.pavlu@suse.com>
Reviewed-by: Sami Tolvanen <samitolvanen@google.com>
Reviewed-by: Daniel Gomez <da.gomez@samsung.com>
Link: https://lore.kernel.org/r/20250618122730.51324-2-petr.pavlu@suse.com
Signed-off-by: Daniel Gomez <da.gomez@samsung.com>
Message-ID: <20250618122730.51324-2-petr.pavlu@suse.com>
---
 kernel/module/main.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/kernel/module/main.c b/kernel/module/main.c
index 413ac6ea3702..9ac994b2f354 100644
--- a/kernel/module/main.c
+++ b/kernel/module/main.c
@@ -2697,7 +2697,7 @@ static int find_module_sections(struct module *mod, struct load_info *info)
 static int move_module(struct module *mod, struct load_info *info)
 {
 	int i;
-	enum mod_mem_type t = 0;
+	enum mod_mem_type t = MOD_MEM_NUM_TYPES;
 	int ret = -ENOMEM;
 	bool codetag_section_found = false;
 
@@ -2776,7 +2776,7 @@ static int move_module(struct module *mod, struct load_info *info)
 	return 0;
 out_err:
 	module_memory_restore_rox(mod);
-	for (t--; t >= 0; t--)
+	while (t--)
 		module_memory_free(mod, t);
 	if (codetag_section_found)
 		codetag_free_module_sections(mod);

From eb0994a954978f0edd3efb38d0cbe6744df8b83d Mon Sep 17 00:00:00 2001
From: Petr Pavlu <petr.pavlu@suse.com>
Date: Wed, 18 Jun 2025 14:26:27 +0200
Subject: [PATCH 1241/1334] module: Avoid unnecessary return value
 initialization in move_module()

All error conditions in move_module() set the return value by updating the
ret variable. Therefore, it is not necessary to the initialize the variable
when declaring it.

Remove the unnecessary initialization.

Signed-off-by: Petr Pavlu <petr.pavlu@suse.com>
Reviewed-by: Sami Tolvanen <samitolvanen@google.com>
Reviewed-by: Daniel Gomez <da.gomez@samsung.com>
Link: https://lore.kernel.org/r/20250618122730.51324-3-petr.pavlu@suse.com
Signed-off-by: Daniel Gomez <da.gomez@samsung.com>
Message-ID: <20250618122730.51324-3-petr.pavlu@suse.com>
---
 kernel/module/main.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/kernel/module/main.c b/kernel/module/main.c
index 9ac994b2f354..7822b91fca6b 100644
--- a/kernel/module/main.c
+++ b/kernel/module/main.c
@@ -2696,9 +2696,8 @@ static int find_module_sections(struct module *mod, struct load_info *info)
 
 static int move_module(struct module *mod, struct load_info *info)
 {
-	int i;
+	int i, ret;
 	enum mod_mem_type t = MOD_MEM_NUM_TYPES;
-	int ret = -ENOMEM;
 	bool codetag_section_found = false;
 
 	for_each_mod_mem_type(type) {

From 570db4b39f535a8bb722adb8be0280d09e34ca99 Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Tue, 10 Jun 2025 18:33:28 +0200
Subject: [PATCH 1242/1334] module: Make sure relocations are applied to the
 per-CPU section

The per-CPU data section is handled differently than the other sections.
The memory allocations requires a special __percpu pointer and then the
section is copied into the view of each CPU. Therefore the SHF_ALLOC
flag is removed to ensure move_module() skips it.

Later, relocations are applied and apply_relocations() skips sections
without SHF_ALLOC because they have not been copied. This also skips the
per-CPU data section.
The missing relocations result in a NULL pointer on x86-64 and very
small values on x86-32. This results in a crash because it is not
skipped like NULL pointer would and can't be dereferenced.

Such an assignment happens during static per-CPU lock initialisation
with lockdep enabled.

Allow relocation processing for the per-CPU section even if SHF_ALLOC is
missing.

Reported-by: kernel test robot <oliver.sang@intel.com>
Closes: https://lore.kernel.org/oe-lkp/202506041623.e45e4f7d-lkp@intel.com
Fixes: 1a6100caae425 ("Don't relocate non-allocated regions in modules.") #v2.6.1-rc3
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Reviewed-by: Petr Pavlu <petr.pavlu@suse.com>
Link: https://lore.kernel.org/r/20250610163328.URcsSUC1@linutronix.de
Signed-off-by: Daniel Gomez <da.gomez@samsung.com>
Message-ID: <20250610163328.URcsSUC1@linutronix.de>
---
 kernel/module/main.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/kernel/module/main.c b/kernel/module/main.c
index 7822b91fca6b..c2c08007029d 100644
--- a/kernel/module/main.c
+++ b/kernel/module/main.c
@@ -1573,8 +1573,14 @@ static int apply_relocations(struct module *mod, const struct load_info *info)
 		if (infosec >= info->hdr->e_shnum)
 			continue;
 
-		/* Don't bother with non-allocated sections */
-		if (!(info->sechdrs[infosec].sh_flags & SHF_ALLOC))
+		/*
+		 * Don't bother with non-allocated sections.
+		 * An exception is the percpu section, which has separate allocations
+		 * for individual CPUs. We relocate the percpu section in the initial
+		 * ELF template and subsequently copy it to the per-CPU destinations.
+		 */
+		if (!(info->sechdrs[infosec].sh_flags & SHF_ALLOC) &&
+		    (!infosec || infosec != info->index.pcpu))
 			continue;
 
 		if (info->sechdrs[i].sh_flags & SHF_RELA_LIVEPATCH)

From af1ccf546e5f2915fbbde26841db43a971d81cf3 Mon Sep 17 00:00:00 2001
From: Daniel Gomez <da.gomez@samsung.com>
Date: Fri, 4 Jul 2025 21:39:59 +0200
Subject: [PATCH 1243/1334] MAINTAINERS: update Daniel Gomez's role and email
 address

Update Daniel Gomez's modules reviewer role to maintainer. This is
according to the plan [1][2][3] of scaling with more reviewers for
modules (for the incoming Rust support [4]) and rotate [5] every 6
months.

Acked-by: Luis Chamberlain <mcgrof@kernel.org>
Link: https://lore.kernel.org/linux-modules/ZsPANzx4-5DrOl5m@bombadil.infradead.org [1]
Link: https://lore.kernel.org/linux-modules/20240821174021.2371547-1-mcgrof@kernel.org [2]
Link: https://lore.kernel.org/linux-modules/458901be-1da8-4987-9c72-5aa3da6db15e@suse.com [3]
Link: https://lore.kernel.org/linux-modules/20250702-module-params-v3-v14-0-5b1cc32311af@kernel.org [4]
Link: https://lore.kernel.org/linux-modules/Z3gDAnPlA3SZEbgl@bombadil.infradead.org [5]
Acked-by: Petr Pavlu <petr.pavlu@suse.com>
Signed-off-by: Daniel Gomez <da.gomez@samsung.com>
---
 MAINTAINERS | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index fad6cb025a19..aa9b3677276c 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -16822,8 +16822,8 @@ F:	include/dt-bindings/clock/mobileye,eyeq5-clk.h
 MODULE SUPPORT
 M:	Luis Chamberlain <mcgrof@kernel.org>
 M:	Petr Pavlu <petr.pavlu@suse.com>
+M:	Daniel Gomez <da.gomez@kernel.org>
 R:	Sami Tolvanen <samitolvanen@google.com>
-R:	Daniel Gomez <da.gomez@samsung.com>
 L:	linux-modules@vger.kernel.org
 L:	linux-kernel@vger.kernel.org
 S:	Maintained

From fec5e6f97dae5fbd628c444148b77728eae3bb93 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Tue, 8 Jul 2025 15:21:39 -0400
Subject: [PATCH 1244/1334] bcachefs: Don't set BCH_FS_error on transaction
 restart

This started showing up more when we started logging the error being
corrected in the journal - but __bch2_fsck_err() could return
transaction restarts before that.

Setting BCH_FS_error incorrectly causes recovery passes to not be
cleared, among other issues.

Fixes: b43f72492768 ("bcachefs: Log fsck errors in the journal")
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/error.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/fs/bcachefs/error.c b/fs/bcachefs/error.c
index ea37f5af1800..267e73d9d7e6 100644
--- a/fs/bcachefs/error.c
+++ b/fs/bcachefs/error.c
@@ -633,7 +633,9 @@ err:
 	 * log_fsck_err()s: that would require us to track for every error type
 	 * which recovery pass corrects it, to get the fsck exit status correct:
 	 */
-	if (bch2_err_matches(ret, BCH_ERR_fsck_fix)) {
+	if (bch2_err_matches(ret, BCH_ERR_transaction_restart)) {
+		/* nothing */
+	} else if (bch2_err_matches(ret, BCH_ERR_fsck_fix)) {
 		set_bit(BCH_FS_errors_fixed, &c->flags);
 	} else {
 		set_bit(BCH_FS_errors_not_fixed, &c->flags);

From 5b937a1ed64ebeba8876e398110a5790ad77407c Mon Sep 17 00:00:00 2001
From: Mikhail Paulyshka <me@mixaill.net>
Date: Sat, 24 May 2025 17:53:19 +0300
Subject: [PATCH 1245/1334] x86/rdrand: Disable RDSEED on AMD Cyan Skillfish

AMD Cyan Skillfish (Family 17h, Model 47h, Stepping 0h) has an error that
causes RDSEED to always return 0xffffffff, while RDRAND works correctly.

Mask the RDSEED cap for this CPU so that both /proc/cpuinfo and direct CPUID
read report RDSEED as unavailable.

  [ bp: Move to amd.c, massage. ]

Signed-off-by: Mikhail Paulyshka <me@mixaill.net>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Cc: <stable@kernel.org>
Link: https://lore.kernel.org/20250524145319.209075-1-me@mixaill.net
---
 arch/x86/include/asm/msr-index.h       | 1 +
 arch/x86/kernel/cpu/amd.c              | 7 +++++++
 tools/arch/x86/include/asm/msr-index.h | 1 +
 3 files changed, 9 insertions(+)

diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index b7dded3c8113..5cfb5d74dd5f 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -628,6 +628,7 @@
 #define MSR_AMD64_OSVW_STATUS		0xc0010141
 #define MSR_AMD_PPIN_CTL		0xc00102f0
 #define MSR_AMD_PPIN			0xc00102f1
+#define MSR_AMD64_CPUID_FN_7		0xc0011002
 #define MSR_AMD64_CPUID_FN_1		0xc0011004
 #define MSR_AMD64_LS_CFG		0xc0011020
 #define MSR_AMD64_DC_CFG		0xc0011022
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 655f44f89ded..e1c4661f4430 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -930,6 +930,13 @@ static void init_amd_zen2(struct cpuinfo_x86 *c)
 	init_spectral_chicken(c);
 	fix_erratum_1386(c);
 	zen2_zenbleed_check(c);
+
+	/* Disable RDSEED on AMD Cyan Skillfish because of an error. */
+	if (c->x86_model == 0x47 && c->x86_stepping == 0x0) {
+		clear_cpu_cap(c, X86_FEATURE_RDSEED);
+		msr_clear_bit(MSR_AMD64_CPUID_FN_7, 18);
+		pr_emerg("RDSEED is not reliable on this platform; disabling.\n");
+	}
 }
 
 static void init_amd_zen3(struct cpuinfo_x86 *c)
diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h
index b7dded3c8113..5cfb5d74dd5f 100644
--- a/tools/arch/x86/include/asm/msr-index.h
+++ b/tools/arch/x86/include/asm/msr-index.h
@@ -628,6 +628,7 @@
 #define MSR_AMD64_OSVW_STATUS		0xc0010141
 #define MSR_AMD_PPIN_CTL		0xc00102f0
 #define MSR_AMD_PPIN			0xc00102f1
+#define MSR_AMD64_CPUID_FN_7		0xc0011002
 #define MSR_AMD64_CPUID_FN_1		0xc0011004
 #define MSR_AMD64_LS_CFG		0xc0011020
 #define MSR_AMD64_DC_CFG		0xc0011022

From a74bb5f202dabddfea96abc1328fcedae8aa140a Mon Sep 17 00:00:00 2001
From: Mikhail Paulyshka <me@mixaill.net>
Date: Tue, 8 Jul 2025 16:39:10 +0200
Subject: [PATCH 1246/1334] x86/CPU/AMD: Disable INVLPGB on Zen2

AMD Cyan Skillfish (Family 17h, Model 47h, Stepping 0h) has an issue
that causes system oopses and panics when performing TLB flush using
INVLPGB.

However, the problem is that that machine has misconfigured CPUID and
should not report the INVLPGB bit in the first place. So zap the
kernel's representation of the flag so that nothing gets confused.

  [ bp: Massage. ]

Fixes: 767ae437a32d ("x86/mm: Add INVLPGB feature and Kconfig entry")
Signed-off-by: Mikhail Paulyshka <me@mixaill.net>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Cc: <stable@kernel.org>
Link: https://lore.kernel.org/r/1ebe845b-322b-4929-9093-b41074e9e939@mixaill.net
---
 arch/x86/kernel/cpu/amd.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index e1c4661f4430..1b1ff60e9202 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -937,6 +937,9 @@ static void init_amd_zen2(struct cpuinfo_x86 *c)
 		msr_clear_bit(MSR_AMD64_CPUID_FN_7, 18);
 		pr_emerg("RDSEED is not reliable on this platform; disabling.\n");
 	}
+
+	/* Correct misconfigured CPUID on some clients. */
+	clear_cpu_cap(c, X86_FEATURE_INVLPGB);
 }
 
 static void init_amd_zen3(struct cpuinfo_x86 *c)

From 31ec70afaaad11fb08970bd1b0dc9ebae3501e16 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Mon, 7 Jul 2025 11:24:33 +0100
Subject: [PATCH 1247/1334] rxrpc: Fix over large frame size warning

Under some circumstances, the compiler will emit the following warning for
rxrpc_send_response():

   net/rxrpc/output.c: In function 'rxrpc_send_response':
   net/rxrpc/output.c:974:1: warning: the frame size of 1160 bytes is larger than 1024 bytes

This occurs because the local variables include a 16-element scatterlist
array and a 16-element bio_vec array.  It's probably not actually a problem
as this function is only called by the rxrpc I/O thread function in a
kernel thread and there won't be much on the stack before it.

Fix this by overlaying the bio_vec array over the kvec array in the
rxrpc_local struct.  There is one of these per I/O thread and the kvec
array is intended for pointing at bits of a packet to be transmitted,
typically a DATA or an ACK packet.  As packets for a local endpoint are
only transmitted by its specific I/O thread, there can be no race, and so
overlaying this bit of memory should be no problem.

Fixes: 5800b1cf3fd8 ("rxrpc: Allow CHALLENGEs to the passed to the app for a RESPONSE")
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202506240423.E942yKJP-lkp@intel.com/
Signed-off-by: David Howells <dhowells@redhat.com>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: Simon Horman <horms@kernel.org>
cc: linux-afs@lists.infradead.org
Link: https://patch.msgid.link/20250707102435.2381045-2-dhowells@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/rxrpc/ar-internal.h | 15 +++++++++------
 net/rxrpc/output.c      |  5 ++++-
 2 files changed, 13 insertions(+), 7 deletions(-)

diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index 5bd3922c310d..376e33dce8c1 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -361,12 +361,15 @@ struct rxrpc_local {
 	struct list_head	new_client_calls; /* Newly created client calls need connection */
 	spinlock_t		client_call_lock; /* Lock for ->new_client_calls */
 	struct sockaddr_rxrpc	srx;		/* local address */
-	/* Provide a kvec table sufficiently large to manage either a DATA
-	 * packet with a maximum set of jumbo subpackets or a PING ACK padded
-	 * out to 64K with zeropages for PMTUD.
-	 */
-	struct kvec		kvec[1 + RXRPC_MAX_NR_JUMBO > 3 + 16 ?
-				     1 + RXRPC_MAX_NR_JUMBO : 3 + 16];
+	union {
+		/* Provide a kvec table sufficiently large to manage either a
+		 * DATA packet with a maximum set of jumbo subpackets or a PING
+		 * ACK padded out to 64K with zeropages for PMTUD.
+		 */
+		struct kvec		kvec[1 + RXRPC_MAX_NR_JUMBO > 3 + 16 ?
+					     1 + RXRPC_MAX_NR_JUMBO : 3 + 16];
+		struct bio_vec		bvec[3 + 16];
+	};
 };
 
 /*
diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c
index 0af19bcdc80a..ef7b3096c95e 100644
--- a/net/rxrpc/output.c
+++ b/net/rxrpc/output.c
@@ -924,7 +924,7 @@ void rxrpc_send_response(struct rxrpc_connection *conn, struct sk_buff *response
 {
 	struct rxrpc_skb_priv *sp = rxrpc_skb(response);
 	struct scatterlist sg[16];
-	struct bio_vec bvec[16];
+	struct bio_vec *bvec = conn->local->bvec;
 	struct msghdr msg;
 	size_t len = sp->resp.len;
 	__be32 wserial;
@@ -938,6 +938,9 @@ void rxrpc_send_response(struct rxrpc_connection *conn, struct sk_buff *response
 	if (ret < 0)
 		goto fail;
 	nr_sg = ret;
+	ret = -EIO;
+	if (WARN_ON_ONCE(nr_sg > ARRAY_SIZE(conn->local->bvec)))
+		goto fail;
 
 	for (int i = 0; i < nr_sg; i++)
 		bvec_set_page(&bvec[i], sg_page(&sg[i]), sg[i].length, sg[i].offset);

From 78b7920a03351a8402de2f81914c1d2e2bdf24b7 Mon Sep 17 00:00:00 2001
From: EricChan <chenchuangyu@xiaomi.com>
Date: Thu, 3 Jul 2025 10:04:49 +0800
Subject: [PATCH 1248/1334] net: stmmac: Fix interrupt handling for
 level-triggered mode in DWC_XGMAC2

According to the Synopsys Controller IP XGMAC-10G Ethernet MAC Databook
v3.30a (section 2.7.2), when the INTM bit in the DMA_Mode register is set
to 2, the sbd_perch_tx_intr_o[] and sbd_perch_rx_intr_o[] signals operate
in level-triggered mode. However, in this configuration, the DMA does not
assert the XGMAC_NIS status bit for Rx or Tx interrupt events.

This creates a functional regression where the condition
if (likely(intr_status & XGMAC_NIS)) in dwxgmac2_dma_interrupt() will
never evaluate to true, preventing proper interrupt handling for
level-triggered mode. The hardware specification explicitly states that
"The DMA does not assert the NIS status bit for the Rx or Tx interrupt
events" (Synopsys DWC_XGMAC2 Databook v3.30a, sec. 2.7.2).

The fix ensures correct handling of both edge and level-triggered
interrupts while maintaining backward compatibility with existing
configurations. It has been tested on the hardware device (not publicly
available), and it can properly trigger the RX and TX interrupt handling
in both the INTM=0 and INTM=2 configurations.

Fixes: d6ddfacd95c7 ("net: stmmac: Add DMA related callbacks for XGMAC2")
Tested-by: EricChan <chenchuangyu@xiaomi.com>
Signed-off-by: EricChan <chenchuangyu@xiaomi.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250703020449.105730-1-chenchuangyu@xiaomi.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../ethernet/stmicro/stmmac/dwxgmac2_dma.c    | 24 +++++++++----------
 1 file changed, 11 insertions(+), 13 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c
index 7840bc403788..5dcc95bc0ad2 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c
@@ -364,19 +364,17 @@ static int dwxgmac2_dma_interrupt(struct stmmac_priv *priv,
 	}
 
 	/* TX/RX NORMAL interrupts */
-	if (likely(intr_status & XGMAC_NIS)) {
-		if (likely(intr_status & XGMAC_RI)) {
-			u64_stats_update_begin(&stats->syncp);
-			u64_stats_inc(&stats->rx_normal_irq_n[chan]);
-			u64_stats_update_end(&stats->syncp);
-			ret |= handle_rx;
-		}
-		if (likely(intr_status & (XGMAC_TI | XGMAC_TBU))) {
-			u64_stats_update_begin(&stats->syncp);
-			u64_stats_inc(&stats->tx_normal_irq_n[chan]);
-			u64_stats_update_end(&stats->syncp);
-			ret |= handle_tx;
-		}
+	if (likely(intr_status & XGMAC_RI)) {
+		u64_stats_update_begin(&stats->syncp);
+		u64_stats_inc(&stats->rx_normal_irq_n[chan]);
+		u64_stats_update_end(&stats->syncp);
+		ret |= handle_rx;
+	}
+	if (likely(intr_status & (XGMAC_TI | XGMAC_TBU))) {
+		u64_stats_update_begin(&stats->syncp);
+		u64_stats_inc(&stats->tx_normal_irq_n[chan]);
+		u64_stats_update_end(&stats->syncp);
+		ret |= handle_tx;
 	}
 
 	/* Clear interrupts */

From a141af8eb2272ab0f677a7f2653874840bc9b214 Mon Sep 17 00:00:00 2001
From: Oleksij Rempel <o.rempel@pengutronix.de>
Date: Thu, 3 Jul 2025 13:49:39 +0200
Subject: [PATCH 1249/1334] net: phy: smsc: Fix Auto-MDIX configuration when
 disabled by strap

Correct the Auto-MDIX configuration to ensure userspace settings are
respected when the feature is disabled by the AUTOMDIX_EN hardware strap.

The LAN9500 PHY allows its default MDI-X mode to be configured via a
hardware strap. If this strap sets the default to "MDI-X off", the
driver was previously unable to enable Auto-MDIX from userspace.

When handling the ETH_TP_MDI_AUTO case, the driver would set the
SPECIAL_CTRL_STS_AMDIX_ENABLE_ bit but neglected to set the required
SPECIAL_CTRL_STS_OVRRD_AMDIX_ bit. Without the override flag, the PHY
falls back to its hardware strap default, ignoring the software request.

This patch corrects the behavior by also setting the override bit when
enabling Auto-MDIX. This ensures that the userspace configuration takes
precedence over the hardware strap, allowing Auto-MDIX to be enabled
correctly in all scenarios.

Fixes: 05b35e7eb9a1 ("smsc95xx: add phylib support")
Signed-off-by: Oleksij Rempel <o.rempel@pengutronix.de>
Cc: Andre Edich <andre.edich@microchip.com>
Reviewed-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Link: https://patch.msgid.link/20250703114941.3243890-2-o.rempel@pengutronix.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/smsc.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/phy/smsc.c b/drivers/net/phy/smsc.c
index 31463b9e5697..adf12d7108b5 100644
--- a/drivers/net/phy/smsc.c
+++ b/drivers/net/phy/smsc.c
@@ -167,7 +167,8 @@ static int lan87xx_config_aneg(struct phy_device *phydev)
 			SPECIAL_CTRL_STS_AMDIX_STATE_;
 		break;
 	case ETH_TP_MDI_AUTO:
-		val = SPECIAL_CTRL_STS_AMDIX_ENABLE_;
+		val = SPECIAL_CTRL_STS_OVRRD_AMDIX_ |
+			SPECIAL_CTRL_STS_AMDIX_ENABLE_;
 		break;
 	default:
 		return genphy_config_aneg(phydev);

From 0713e55533c88a20edb53eea6517dc56786a0078 Mon Sep 17 00:00:00 2001
From: Oleksij Rempel <o.rempel@pengutronix.de>
Date: Thu, 3 Jul 2025 13:49:40 +0200
Subject: [PATCH 1250/1334] net: phy: smsc: Force predictable MDI-X state on
 LAN87xx

Override the hardware strap configuration for MDI-X mode to ensure a
predictable initial state for the driver. The initial mode of the LAN87xx
PHY is determined by the AUTOMDIX_EN strap pin, but the driver has no
documented way to read its latched status.

This unpredictability means the driver cannot know if the PHY has
initialized with Auto-MDIX enabled or disabled, preventing it from
providing a reliable interface to the user.

This patch introduces a `config_init` hook that forces the PHY into a
known state by explicitly enabling Auto-MDIX.

Fixes: 05b35e7eb9a1 ("smsc95xx: add phylib support")
Signed-off-by: Oleksij Rempel <o.rempel@pengutronix.de>
Cc: Andre Edich <andre.edich@microchip.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/20250703114941.3243890-3-o.rempel@pengutronix.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/smsc.c | 29 ++++++++++++++++++++++++++++-
 1 file changed, 28 insertions(+), 1 deletion(-)

diff --git a/drivers/net/phy/smsc.c b/drivers/net/phy/smsc.c
index adf12d7108b5..ad9a3d91bb8a 100644
--- a/drivers/net/phy/smsc.c
+++ b/drivers/net/phy/smsc.c
@@ -262,6 +262,33 @@ int lan87xx_read_status(struct phy_device *phydev)
 }
 EXPORT_SYMBOL_GPL(lan87xx_read_status);
 
+static int lan87xx_phy_config_init(struct phy_device *phydev)
+{
+	int rc;
+
+	/* The LAN87xx PHY's initial MDI-X mode is determined by the AUTOMDIX_EN
+	 * hardware strap, but the driver cannot read the strap's status. This
+	 * creates an unpredictable initial state.
+	 *
+	 * To ensure consistent and reliable behavior across all boards,
+	 * override the strap configuration on initialization and force the PHY
+	 * into a known state with Auto-MDIX enabled, which is the expected
+	 * default for modern hardware.
+	 */
+	rc = phy_modify(phydev, SPECIAL_CTRL_STS,
+			SPECIAL_CTRL_STS_OVRRD_AMDIX_ |
+			SPECIAL_CTRL_STS_AMDIX_ENABLE_ |
+			SPECIAL_CTRL_STS_AMDIX_STATE_,
+			SPECIAL_CTRL_STS_OVRRD_AMDIX_ |
+			SPECIAL_CTRL_STS_AMDIX_ENABLE_);
+	if (rc < 0)
+		return rc;
+
+	phydev->mdix_ctrl = ETH_TP_MDI_AUTO;
+
+	return smsc_phy_config_init(phydev);
+}
+
 static int lan874x_phy_config_init(struct phy_device *phydev)
 {
 	u16 val;
@@ -696,7 +723,7 @@ static struct phy_driver smsc_phy_driver[] = {
 
 	/* basic functions */
 	.read_status	= lan87xx_read_status,
-	.config_init	= smsc_phy_config_init,
+	.config_init	= lan87xx_phy_config_init,
 	.soft_reset	= smsc_phy_reset,
 	.config_aneg	= lan87xx_config_aneg,
 

From 9dfe110cc0f6ef42af8e81ce52aef34a647d0b8a Mon Sep 17 00:00:00 2001
From: Oleksij Rempel <o.rempel@pengutronix.de>
Date: Thu, 3 Jul 2025 13:49:41 +0200
Subject: [PATCH 1251/1334] net: phy: smsc: Fix link failure in forced mode
 with Auto-MDIX

Force a fixed MDI-X mode when auto-negotiation is disabled to prevent
link instability.

When forcing the link speed and duplex on a LAN9500 PHY (e.g., with
`ethtool -s eth0 autoneg off ...`) while leaving MDI-X control in auto
mode, the PHY fails to establish a stable link. This occurs because the
PHY's Auto-MDIX algorithm is not designed to operate when
auto-negotiation is disabled. In this state, the PHY continuously
toggles the TX/RX signal pairs, which prevents the link partner from
synchronizing.

This patch resolves the issue by detecting when auto-negotiation is
disabled. If the MDI-X control mode is set to 'auto', the driver now
forces a specific, stable mode (ETH_TP_MDI) to prevent the pair
toggling. This choice of a fixed MDI mode mirrors the behavior the
hardware would exhibit if the AUTOMDIX_EN strap were configured for a
fixed MDI connection.

Fixes: 05b35e7eb9a1 ("smsc95xx: add phylib support")
Signed-off-by: Oleksij Rempel <o.rempel@pengutronix.de>
Cc: Andre Edich <andre.edich@microchip.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/20250703114941.3243890-4-o.rempel@pengutronix.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/smsc.c | 25 ++++++++++++++++++++++---
 1 file changed, 22 insertions(+), 3 deletions(-)

diff --git a/drivers/net/phy/smsc.c b/drivers/net/phy/smsc.c
index ad9a3d91bb8a..b6489da5cfcd 100644
--- a/drivers/net/phy/smsc.c
+++ b/drivers/net/phy/smsc.c
@@ -155,10 +155,29 @@ static int smsc_phy_reset(struct phy_device *phydev)
 
 static int lan87xx_config_aneg(struct phy_device *phydev)
 {
-	int rc;
+	u8 mdix_ctrl;
 	int val;
+	int rc;
 
-	switch (phydev->mdix_ctrl) {
+	/* When auto-negotiation is disabled (forced mode), the PHY's
+	 * Auto-MDIX will continue toggling the TX/RX pairs.
+	 *
+	 * To establish a stable link, we must select a fixed MDI mode.
+	 * If the user has not specified a fixed MDI mode (i.e., mdix_ctrl is
+	 * 'auto'), we default to ETH_TP_MDI. This choice of a ETH_TP_MDI mode
+	 * mirrors the behavior the hardware would exhibit if the AUTOMDIX_EN
+	 * strap were configured for a fixed MDI connection.
+	 */
+	if (phydev->autoneg == AUTONEG_DISABLE) {
+		if (phydev->mdix_ctrl == ETH_TP_MDI_AUTO)
+			mdix_ctrl = ETH_TP_MDI;
+		else
+			mdix_ctrl = phydev->mdix_ctrl;
+	} else {
+		mdix_ctrl = phydev->mdix_ctrl;
+	}
+
+	switch (mdix_ctrl) {
 	case ETH_TP_MDI:
 		val = SPECIAL_CTRL_STS_OVRRD_AMDIX_;
 		break;
@@ -184,7 +203,7 @@ static int lan87xx_config_aneg(struct phy_device *phydev)
 	rc |= val;
 	phy_write(phydev, SPECIAL_CTRL_STS, rc);
 
-	phydev->mdix = phydev->mdix_ctrl;
+	phydev->mdix = mdix_ctrl;
 	return genphy_config_aneg(phydev);
 }
 

From d88dfb756d557e40e88406e8c962c0684bc9eb87 Mon Sep 17 00:00:00 2001
From: Lukas Wunner <lukas@wunner.de>
Date: Wed, 2 Jul 2025 07:02:15 +0200
Subject: [PATCH 1252/1334] agp/amd64: Check AGP Capability before binding to
 unsupported devices

Since commit 172efbb40333 ("AGP: Try unsupported AGP chipsets on x86-64
by default"), the AGP driver for AMD Opteron/Athlon64 CPUs has attempted
to bind to any PCI device possessing an AGP Capability.

Commit 6fd024893911 ("amd64-agp: Probe unknown AGP devices the right
way") subsequently reworked the driver to perform a bind attempt to
any PCI device (regardless of AGP Capability) and reject a device in
the driver's ->probe() hook if it lacks the AGP Capability.

On modern CPUs exposing an AMD IOMMU, this subtle change results in an
annoying message with KERN_CRIT severity:

  pci 0000:00:00.2: Resources present before probing

The message is emitted by the driver core prior to invoking a driver's
->probe() hook.  The check for an AGP Capability in the ->probe() hook
happens too late to prevent the message.

The message has appeared only recently with commit 3be5fa236649 (Revert
"iommu/amd: Prevent binding other PCI drivers to IOMMU PCI devices").
Prior to the commit, no driver could bind to AMD IOMMUs.

The reason for the message is that an MSI is requested early on for the
AMD IOMMU, which results in a call from msi_sysfs_create_group() to
devm_device_add_group().  A devres resource is thus attached to the
driver-less AMD IOMMU, which is normally not allowed, but presumably
cannot be avoided because requesting the MSI from a regular PCI driver
might be too late.

Avoid the message by once again checking for an AGP Capability *before*
binding to an unsupported device.  Achieve that by way of the PCI core's
dynid functionality.

pci_add_dynid() can fail only with -ENOMEM (on allocation failure) or
-EINVAL (on bus_to_subsys() failure).  It doesn't seem worth the extra
code to propagate those error codes out of the for_each_pci_dev() loop,
so simply error out with -ENODEV if there was no successful bind attempt.
In the -ENOMEM case, a splat is emitted anyway, and the -EINVAL case can
never happen because it requires failure of bus_register(&pci_bus_type),
in which case there's no driver probing of PCI devices.

Hans has voiced a preference to no longer probe unsupported devices by
default (i.e. set agp_try_unsupported = 0).  In fact, the help text for
CONFIG_AGP_AMD64 pretends this to be the default.  Alternatively, he
proposes probing only devices with PCI_CLASS_BRIDGE_HOST.  However these
approaches risk regressing users who depend on the existing behavior.

Fixes: 3be5fa236649 (Revert "iommu/amd: Prevent binding other PCI drivers to IOMMU PCI devices")
Reported-by: Fedor Pchelkin <pchelkin@ispras.ru>
Closes: https://lore.kernel.org/r/wpoivftgshz5b5aovxbkxl6ivvquinukqfvb5z6yi4mv7d25ew@edtzr2p74ckg/
Reported-by: Hans de Goede <hansg@kernel.org>
Closes: https://lore.kernel.org/r/20250625112411.4123-1-hansg@kernel.org/
Tested-by: Hans de Goede <hansg@kernel.org>
Signed-off-by: Lukas Wunner <lukas@wunner.de>
Reviewed-by: Hans de Goede <hansg@kernel.org>
Link: https://lore.kernel.org/r/b29e7fbfc6d146f947603d0ebaef44cbd2f0d754.1751468802.git.lukas@wunner.de
---
 drivers/char/agp/amd64-agp.c | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/drivers/char/agp/amd64-agp.c b/drivers/char/agp/amd64-agp.c
index bf490967241a..2505df1f4e69 100644
--- a/drivers/char/agp/amd64-agp.c
+++ b/drivers/char/agp/amd64-agp.c
@@ -720,11 +720,6 @@ static const struct pci_device_id agp_amd64_pci_table[] = {
 
 MODULE_DEVICE_TABLE(pci, agp_amd64_pci_table);
 
-static const struct pci_device_id agp_amd64_pci_promisc_table[] = {
-	{ PCI_DEVICE_CLASS(0, 0) },
-	{ }
-};
-
 static DEFINE_SIMPLE_DEV_PM_OPS(agp_amd64_pm_ops, NULL, agp_amd64_resume);
 
 static struct pci_driver agp_amd64_pci_driver = {
@@ -739,6 +734,7 @@ static struct pci_driver agp_amd64_pci_driver = {
 /* Not static due to IOMMU code calling it early. */
 int __init agp_amd64_init(void)
 {
+	struct pci_dev *pdev = NULL;
 	int err = 0;
 
 	if (agp_off)
@@ -767,9 +763,13 @@ int __init agp_amd64_init(void)
 		}
 
 		/* Look for any AGP bridge */
-		agp_amd64_pci_driver.id_table = agp_amd64_pci_promisc_table;
-		err = driver_attach(&agp_amd64_pci_driver.driver);
-		if (err == 0 && agp_bridges_found == 0) {
+		for_each_pci_dev(pdev)
+			if (pci_find_capability(pdev, PCI_CAP_ID_AGP))
+				pci_add_dynid(&agp_amd64_pci_driver,
+					      pdev->vendor, pdev->device,
+					      pdev->subsystem_vendor,
+					      pdev->subsystem_device, 0, 0, 0);
+		if (agp_bridges_found == 0) {
 			pci_unregister_driver(&agp_amd64_pci_driver);
 			err = -ENODEV;
 		}

From a066917360ed5000c4f73fb190773cfac004c885 Mon Sep 17 00:00:00 2001
From: Pagadala Yesu Anjaneyulu <pagadala.yesu.anjaneyulu@intel.com>
Date: Mon, 9 Jun 2025 21:35:14 +0300
Subject: [PATCH 1253/1334] wifi: mac80211: Fix uninitialized variable with
 __free() in ieee80211_ml_epcs()

The cleanup attribute runs kfree() when the variable goes out of scope.
There is a possibility that the link_elems variable is uninitialized
if the loop ends before an assignment is made to this variable.
This leads to uninitialized variable bug.

Fix this by assigning link_elems to NULL.

Signed-off-by: Pagadala Yesu Anjaneyulu <pagadala.yesu.anjaneyulu@intel.com>
Reviewed-by: Ilan Peer <ilan.peer@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250609213231.eeacd3738a7b.I0f876fa1359daeec47ab3aef098255a9c23efd70@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/mlme.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index d26dcee5683a..0ed68182f79b 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -10705,8 +10705,8 @@ static void ieee80211_ml_epcs(struct ieee80211_sub_if_data *sdata,
 	 */
 	for_each_mle_subelement(sub, (const u8 *)elems->ml_epcs,
 				elems->ml_epcs_len) {
+		struct ieee802_11_elems *link_elems __free(kfree) = NULL;
 		struct ieee80211_link_data *link;
-		struct ieee802_11_elems *link_elems __free(kfree);
 		u8 *pos = (void *)sub->data;
 		u16 control;
 		ssize_t len;

From 3da6bb419750f3ad834786d6ba7c9d5d062c770b Mon Sep 17 00:00:00 2001
From: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Date: Wed, 9 Jul 2025 20:27:52 +0900
Subject: [PATCH 1254/1334] perf/core: Fix WARN in perf_sigtrap()

Since exit_task_work() runs after perf_event_exit_task_context() updated
ctx->task to TASK_TOMBSTONE, perf_sigtrap() from perf_pending_task() might
observe event->ctx->task == TASK_TOMBSTONE.

Swap the early exit tests in order not to hit WARN_ON_ONCE().

Closes: https://syzkaller.appspot.com/bug?extid=2fe61cb2a86066be6985
Reported-by: syzbot <syzbot+2fe61cb2a86066be6985@syzkaller.appspotmail.com>
Signed-off-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/b1c224bd-97f9-462c-a3e3-125d5e19c983@I-love.SAKURA.ne.jp
---
 kernel/events/core.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 0db36b2b2448..22fdf0c187cd 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -7203,6 +7203,13 @@ void perf_event_wakeup(struct perf_event *event)
 
 static void perf_sigtrap(struct perf_event *event)
 {
+	/*
+	 * Both perf_pending_task() and perf_pending_irq() can race with the
+	 * task exiting.
+	 */
+	if (current->flags & PF_EXITING)
+		return;
+
 	/*
 	 * We'd expect this to only occur if the irq_work is delayed and either
 	 * ctx->task or current has changed in the meantime. This can be the
@@ -7211,13 +7218,6 @@ static void perf_sigtrap(struct perf_event *event)
 	if (WARN_ON_ONCE(event->ctx->task != current))
 		return;
 
-	/*
-	 * Both perf_pending_task() and perf_pending_irq() can race with the
-	 * task exiting.
-	 */
-	if (current->flags & PF_EXITING)
-		return;
-
 	send_sig_perf((void __user *)event->pending_addr,
 		      event->orig_type, event->attr.sig_data);
 }

From f6bfc9afc7510cb5e6fbe0a17c507917b0120280 Mon Sep 17 00:00:00 2001
From: Thomas Zimmermann <tzimmermann@suse.de>
Date: Mon, 7 Jul 2025 15:11:55 +0200
Subject: [PATCH 1255/1334] drm/framebuffer: Acquire internal references on GEM
 handles
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Acquire GEM handles in drm_framebuffer_init() and release them in
the corresponding drm_framebuffer_cleanup(). Ties the handle's
lifetime to the framebuffer. Not all GEM buffer objects have GEM
handles. If not set, no refcounting takes place. This is the case
for some fbdev emulation. This is not a problem as these GEM objects
do not use dma-bufs and drivers will not release them while fbdev
emulation is running. Framebuffer flags keep a bit per color plane
of which the framebuffer holds a GEM handle reference.

As all drivers use drm_framebuffer_init(), they will now all hold
dma-buf references as fixed in commit 5307dce878d4 ("drm/gem: Acquire
references on GEM handles for framebuffers").

In the GEM framebuffer helpers, restore the original ref counting
on buffer objects. As the helpers for handle refcounting are now
no longer called from outside the DRM core, unexport the symbols.

v3:
- don't mix internal flags with mode flags (Christian)
v2:
- track framebuffer handle refs by flag
- drop gma500 cleanup (Christian)

Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>
Fixes: 5307dce878d4 ("drm/gem: Acquire references on GEM handles for framebuffers")
Reported-by: Bert Karwatzki <spasswolf@web.de>
Closes: https://lore.kernel.org/dri-devel/20250703115915.3096-1-spasswolf@web.de/
Tested-by: Bert Karwatzki <spasswolf@web.de>
Tested-by: Mario Limonciello <superm1@kernel.org>
Tested-by: Borislav Petkov (AMD) <bp@alien8.de>
Cc: Thomas Zimmermann <tzimmermann@suse.de>
Cc: Anusha Srivatsa <asrivats@redhat.com>
Cc: Christian König <christian.koenig@amd.com>
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Cc: Maxime Ripard <mripard@kernel.org>
Cc: Sumit Semwal <sumit.semwal@linaro.org>
Cc: "Christian König" <christian.koenig@amd.com>
Cc: linux-media@vger.kernel.org
Cc: dri-devel@lists.freedesktop.org
Cc: linaro-mm-sig@lists.linaro.org
Cc: <stable@vger.kernel.org>
Reviewed-by: Christian König <christian.koenig@amd.com>
Link: https://lore.kernel.org/r/20250707131224.249496-1-tzimmermann@suse.de
---
 drivers/gpu/drm/drm_framebuffer.c            | 31 ++++++++++++++--
 drivers/gpu/drm/drm_gem.c                    | 38 ++++++++++++--------
 drivers/gpu/drm/drm_gem_framebuffer_helper.c | 16 ++++-----
 drivers/gpu/drm/drm_internal.h               |  2 +-
 include/drm/drm_framebuffer.h                |  7 ++++
 5 files changed, 68 insertions(+), 26 deletions(-)

diff --git a/drivers/gpu/drm/drm_framebuffer.c b/drivers/gpu/drm/drm_framebuffer.c
index b781601946db..63a70f285cce 100644
--- a/drivers/gpu/drm/drm_framebuffer.c
+++ b/drivers/gpu/drm/drm_framebuffer.c
@@ -862,11 +862,23 @@ EXPORT_SYMBOL_FOR_TESTS_ONLY(drm_framebuffer_free);
 int drm_framebuffer_init(struct drm_device *dev, struct drm_framebuffer *fb,
 			 const struct drm_framebuffer_funcs *funcs)
 {
+	unsigned int i;
 	int ret;
+	bool exists;
 
 	if (WARN_ON_ONCE(fb->dev != dev || !fb->format))
 		return -EINVAL;
 
+	for (i = 0; i < fb->format->num_planes; i++) {
+		if (drm_WARN_ON_ONCE(dev, fb->internal_flags & DRM_FRAMEBUFFER_HAS_HANDLE_REF(i)))
+			fb->internal_flags &= ~DRM_FRAMEBUFFER_HAS_HANDLE_REF(i);
+		if (fb->obj[i]) {
+			exists = drm_gem_object_handle_get_if_exists_unlocked(fb->obj[i]);
+			if (exists)
+				fb->internal_flags |= DRM_FRAMEBUFFER_HAS_HANDLE_REF(i);
+		}
+	}
+
 	INIT_LIST_HEAD(&fb->filp_head);
 
 	fb->funcs = funcs;
@@ -875,7 +887,7 @@ int drm_framebuffer_init(struct drm_device *dev, struct drm_framebuffer *fb,
 	ret = __drm_mode_object_add(dev, &fb->base, DRM_MODE_OBJECT_FB,
 				    false, drm_framebuffer_free);
 	if (ret)
-		goto out;
+		goto err;
 
 	mutex_lock(&dev->mode_config.fb_lock);
 	dev->mode_config.num_fb++;
@@ -883,7 +895,16 @@ int drm_framebuffer_init(struct drm_device *dev, struct drm_framebuffer *fb,
 	mutex_unlock(&dev->mode_config.fb_lock);
 
 	drm_mode_object_register(dev, &fb->base);
-out:
+
+	return 0;
+
+err:
+	for (i = 0; i < fb->format->num_planes; i++) {
+		if (fb->internal_flags & DRM_FRAMEBUFFER_HAS_HANDLE_REF(i)) {
+			drm_gem_object_handle_put_unlocked(fb->obj[i]);
+			fb->internal_flags &= ~DRM_FRAMEBUFFER_HAS_HANDLE_REF(i);
+		}
+	}
 	return ret;
 }
 EXPORT_SYMBOL(drm_framebuffer_init);
@@ -960,6 +981,12 @@ EXPORT_SYMBOL(drm_framebuffer_unregister_private);
 void drm_framebuffer_cleanup(struct drm_framebuffer *fb)
 {
 	struct drm_device *dev = fb->dev;
+	unsigned int i;
+
+	for (i = 0; i < fb->format->num_planes; i++) {
+		if (fb->internal_flags & DRM_FRAMEBUFFER_HAS_HANDLE_REF(i))
+			drm_gem_object_handle_put_unlocked(fb->obj[i]);
+	}
 
 	mutex_lock(&dev->mode_config.fb_lock);
 	list_del(&fb->head);
diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c
index 4bf0a76bb35e..aad6ac9748cc 100644
--- a/drivers/gpu/drm/drm_gem.c
+++ b/drivers/gpu/drm/drm_gem.c
@@ -223,23 +223,34 @@ static void drm_gem_object_handle_get(struct drm_gem_object *obj)
 }
 
 /**
- * drm_gem_object_handle_get_unlocked - acquire reference on user-space handles
+ * drm_gem_object_handle_get_if_exists_unlocked - acquire reference on user-space handle, if any
  * @obj: GEM object
  *
- * Acquires a reference on the GEM buffer object's handle. Required
- * to keep the GEM object alive. Call drm_gem_object_handle_put_unlocked()
- * to release the reference.
+ * Acquires a reference on the GEM buffer object's handle. Required to keep
+ * the GEM object alive. Call drm_gem_object_handle_put_if_exists_unlocked()
+ * to release the reference. Does nothing if the buffer object has no handle.
+ *
+ * Returns:
+ * True if a handle exists, or false otherwise
  */
-void drm_gem_object_handle_get_unlocked(struct drm_gem_object *obj)
+bool drm_gem_object_handle_get_if_exists_unlocked(struct drm_gem_object *obj)
 {
 	struct drm_device *dev = obj->dev;
 
 	guard(mutex)(&dev->object_name_lock);
 
-	drm_WARN_ON(dev, !obj->handle_count); /* first ref taken in create-tail helper */
+	/*
+	 * First ref taken during GEM object creation, if any. Some
+	 * drivers set up internal framebuffers with GEM objects that
+	 * do not have a GEM handle. Hence, this counter can be zero.
+	 */
+	if (!obj->handle_count)
+		return false;
+
 	drm_gem_object_handle_get(obj);
+
+	return true;
 }
-EXPORT_SYMBOL(drm_gem_object_handle_get_unlocked);
 
 /**
  * drm_gem_object_handle_free - release resources bound to userspace handles
@@ -272,7 +283,7 @@ static void drm_gem_object_exported_dma_buf_free(struct drm_gem_object *obj)
 }
 
 /**
- * drm_gem_object_handle_put_unlocked - releases reference on user-space handles
+ * drm_gem_object_handle_put_unlocked - releases reference on user-space handle
  * @obj: GEM object
  *
  * Releases a reference on the GEM buffer object's handle. Possibly releases
@@ -283,14 +294,14 @@ void drm_gem_object_handle_put_unlocked(struct drm_gem_object *obj)
 	struct drm_device *dev = obj->dev;
 	bool final = false;
 
-	if (WARN_ON(READ_ONCE(obj->handle_count) == 0))
+	if (drm_WARN_ON(dev, READ_ONCE(obj->handle_count) == 0))
 		return;
 
 	/*
-	* Must bump handle count first as this may be the last
-	* ref, in which case the object would disappear before we
-	* checked for a name
-	*/
+	 * Must bump handle count first as this may be the last
+	 * ref, in which case the object would disappear before
+	 * we checked for a name.
+	 */
 
 	mutex_lock(&dev->object_name_lock);
 	if (--obj->handle_count == 0) {
@@ -303,7 +314,6 @@ void drm_gem_object_handle_put_unlocked(struct drm_gem_object *obj)
 	if (final)
 		drm_gem_object_put(obj);
 }
-EXPORT_SYMBOL(drm_gem_object_handle_put_unlocked);
 
 /*
  * Called at device or object close to release the file's
diff --git a/drivers/gpu/drm/drm_gem_framebuffer_helper.c b/drivers/gpu/drm/drm_gem_framebuffer_helper.c
index 14a87788695d..6f72e7a0f427 100644
--- a/drivers/gpu/drm/drm_gem_framebuffer_helper.c
+++ b/drivers/gpu/drm/drm_gem_framebuffer_helper.c
@@ -99,7 +99,7 @@ void drm_gem_fb_destroy(struct drm_framebuffer *fb)
 	unsigned int i;
 
 	for (i = 0; i < fb->format->num_planes; i++)
-		drm_gem_object_handle_put_unlocked(fb->obj[i]);
+		drm_gem_object_put(fb->obj[i]);
 
 	drm_framebuffer_cleanup(fb);
 	kfree(fb);
@@ -182,10 +182,8 @@ int drm_gem_fb_init_with_funcs(struct drm_device *dev,
 		if (!objs[i]) {
 			drm_dbg_kms(dev, "Failed to lookup GEM object\n");
 			ret = -ENOENT;
-			goto err_gem_object_handle_put_unlocked;
+			goto err_gem_object_put;
 		}
-		drm_gem_object_handle_get_unlocked(objs[i]);
-		drm_gem_object_put(objs[i]);
 
 		min_size = (height - 1) * mode_cmd->pitches[i]
 			 + drm_format_info_min_pitch(info, i, width)
@@ -195,22 +193,22 @@ int drm_gem_fb_init_with_funcs(struct drm_device *dev,
 			drm_dbg_kms(dev,
 				    "GEM object size (%zu) smaller than minimum size (%u) for plane %d\n",
 				    objs[i]->size, min_size, i);
-			drm_gem_object_handle_put_unlocked(objs[i]);
+			drm_gem_object_put(objs[i]);
 			ret = -EINVAL;
-			goto err_gem_object_handle_put_unlocked;
+			goto err_gem_object_put;
 		}
 	}
 
 	ret = drm_gem_fb_init(dev, fb, mode_cmd, objs, i, funcs);
 	if (ret)
-		goto err_gem_object_handle_put_unlocked;
+		goto err_gem_object_put;
 
 	return 0;
 
-err_gem_object_handle_put_unlocked:
+err_gem_object_put:
 	while (i > 0) {
 		--i;
-		drm_gem_object_handle_put_unlocked(objs[i]);
+		drm_gem_object_put(objs[i]);
 	}
 	return ret;
 }
diff --git a/drivers/gpu/drm/drm_internal.h b/drivers/gpu/drm/drm_internal.h
index be77d61a16ce..60c282881958 100644
--- a/drivers/gpu/drm/drm_internal.h
+++ b/drivers/gpu/drm/drm_internal.h
@@ -161,7 +161,7 @@ void drm_sysfs_lease_event(struct drm_device *dev);
 
 /* drm_gem.c */
 int drm_gem_init(struct drm_device *dev);
-void drm_gem_object_handle_get_unlocked(struct drm_gem_object *obj);
+bool drm_gem_object_handle_get_if_exists_unlocked(struct drm_gem_object *obj);
 void drm_gem_object_handle_put_unlocked(struct drm_gem_object *obj);
 int drm_gem_handle_create_tail(struct drm_file *file_priv,
 			       struct drm_gem_object *obj,
diff --git a/include/drm/drm_framebuffer.h b/include/drm/drm_framebuffer.h
index 668077009fce..38b24fc8978d 100644
--- a/include/drm/drm_framebuffer.h
+++ b/include/drm/drm_framebuffer.h
@@ -23,6 +23,7 @@
 #ifndef __DRM_FRAMEBUFFER_H__
 #define __DRM_FRAMEBUFFER_H__
 
+#include <linux/bits.h>
 #include <linux/ctype.h>
 #include <linux/list.h>
 #include <linux/sched.h>
@@ -100,6 +101,8 @@ struct drm_framebuffer_funcs {
 		     unsigned num_clips);
 };
 
+#define DRM_FRAMEBUFFER_HAS_HANDLE_REF(_i)	BIT(0u + (_i))
+
 /**
  * struct drm_framebuffer - frame buffer object
  *
@@ -188,6 +191,10 @@ struct drm_framebuffer {
 	 * DRM_MODE_FB_MODIFIERS.
 	 */
 	int flags;
+	/**
+	 * @internal_flags: Framebuffer flags like DRM_FRAMEBUFFER_HAS_HANDLE_REF.
+	 */
+	unsigned int internal_flags;
 	/**
 	 * @filp_head: Placed on &drm_file.fbs, protected by &drm_file.fbs_lock.
 	 */

From bd46cece51a36ef088f22ef0416ac13b0a46d5b0 Mon Sep 17 00:00:00 2001
From: Simona Vetter <simona.vetter@ffwll.ch>
Date: Mon, 7 Jul 2025 17:18:13 +0200
Subject: [PATCH 1256/1334] drm/gem: Fix race in drm_gem_handle_create_tail()

Object creation is a careful dance where we must guarantee that the
object is fully constructed before it is visible to other threads, and
GEM buffer objects are no difference.

Final publishing happens by calling drm_gem_handle_create(). After
that the only allowed thing to do is call drm_gem_object_put() because
a concurrent call to the GEM_CLOSE ioctl with a correctly guessed id
(which is trivial since we have a linear allocator) can already tear
down the object again.

Luckily most drivers get this right, the very few exceptions I've
pinged the relevant maintainers for. Unfortunately we also need
drm_gem_handle_create() when creating additional handles for an
already existing object (e.g. GETFB ioctl or the various bo import
ioctl), and hence we cannot have a drm_gem_handle_create_and_put() as
the only exported function to stop these issues from happening.

Now unfortunately the implementation of drm_gem_handle_create() isn't
living up to standards: It does correctly finishe object
initialization at the global level, and hence is safe against a
concurrent tear down. But it also sets up the file-private aspects of
the handle, and that part goes wrong: We fully register the object in
the drm_file.object_idr before calling drm_vma_node_allow() or
obj->funcs->open, which opens up races against concurrent removal of
that handle in drm_gem_handle_delete().

Fix this with the usual two-stage approach of first reserving the
handle id, and then only registering the object after we've completed
the file-private setup.

Jacek reported this with a testcase of concurrently calling GEM_CLOSE
on a freshly-created object (which also destroys the object), but it
should be possible to hit this with just additional handles created
through import or GETFB without completed destroying the underlying
object with the concurrent GEM_CLOSE ioctl calls.

Note that the close-side of this race was fixed in f6cd7daecff5 ("drm:
Release driver references to handle before making it available
again"), which means a cool 9 years have passed until someone noticed
that we need to make this symmetry or there's still gaps left :-/
Without the 2-stage close approach we'd still have a race, therefore
that's an integral part of this bugfix.

More importantly, this means we can have NULL pointers behind
allocated id in our drm_file.object_idr. We need to check for that
now:

- drm_gem_handle_delete() checks for ERR_OR_NULL already

- drm_gem.c:object_lookup() also chekcs for NULL

- drm_gem_release() should never be called if there's another thread
  still existing that could call into an IOCTL that creates a new
  handle, so cannot race. For paranoia I added a NULL check to
  drm_gem_object_release_handle() though.

- most drivers (etnaviv, i915, msm) are find because they use
  idr_find(), which maps both ENOENT and NULL to NULL.

- drivers using idr_for_each_entry() should also be fine, because
  idr_get_next does filter out NULL entries and continues the
  iteration.

- The same holds for drm_show_memory_stats().

v2: Use drm_WARN_ON (Thomas)

Reported-by: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
Tested-by: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
Reviewed-by: Thomas Zimmermann <tzimmermann@suse.de>
Cc: stable@vger.kernel.org
Cc: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Cc: Maxime Ripard <mripard@kernel.org>
Cc: Thomas Zimmermann <tzimmermann@suse.de>
Cc: David Airlie <airlied@gmail.com>
Cc: Simona Vetter <simona@ffwll.ch>
Signed-off-by: Simona Vetter <simona.vetter@intel.com>
Signed-off-by: Simona Vetter <simona.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20250707151814.603897-1-simona.vetter@ffwll.ch
---
 drivers/gpu/drm/drm_gem.c | 10 +++++++++-
 include/drm/drm_file.h    |  3 +++
 2 files changed, 12 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c
index aad6ac9748cc..ac0524595bd6 100644
--- a/drivers/gpu/drm/drm_gem.c
+++ b/drivers/gpu/drm/drm_gem.c
@@ -325,6 +325,9 @@ drm_gem_object_release_handle(int id, void *ptr, void *data)
 	struct drm_file *file_priv = data;
 	struct drm_gem_object *obj = ptr;
 
+	if (drm_WARN_ON(obj->dev, !data))
+		return 0;
+
 	if (obj->funcs->close)
 		obj->funcs->close(obj, file_priv);
 
@@ -445,7 +448,7 @@ drm_gem_handle_create_tail(struct drm_file *file_priv,
 	idr_preload(GFP_KERNEL);
 	spin_lock(&file_priv->table_lock);
 
-	ret = idr_alloc(&file_priv->object_idr, obj, 1, 0, GFP_NOWAIT);
+	ret = idr_alloc(&file_priv->object_idr, NULL, 1, 0, GFP_NOWAIT);
 
 	spin_unlock(&file_priv->table_lock);
 	idr_preload_end();
@@ -466,6 +469,11 @@ drm_gem_handle_create_tail(struct drm_file *file_priv,
 			goto err_revoke;
 	}
 
+	/* mirrors drm_gem_handle_delete to avoid races */
+	spin_lock(&file_priv->table_lock);
+	obj = idr_replace(&file_priv->object_idr, obj, handle);
+	WARN_ON(obj != NULL);
+	spin_unlock(&file_priv->table_lock);
 	*handlep = handle;
 	return 0;
 
diff --git a/include/drm/drm_file.h b/include/drm/drm_file.h
index 5c3b2aa3e69d..d344d41e6cfe 100644
--- a/include/drm/drm_file.h
+++ b/include/drm/drm_file.h
@@ -300,6 +300,9 @@ struct drm_file {
 	 *
 	 * Mapping of mm object handles to object pointers. Used by the GEM
 	 * subsystem. Protected by @table_lock.
+	 *
+	 * Note that allocated entries might be NULL as a transient state when
+	 * creating or deleting a handle.
 	 */
 	struct idr object_idr;
 

From d563e7f95c933816efe531c3a48e22bc099c0f55 Mon Sep 17 00:00:00 2001
From: Alexander Stein <alexander.stein@ew.tq-group.com>
Date: Tue, 8 Jul 2025 10:38:29 +0200
Subject: [PATCH 1257/1334] gpio: of: initialize local variable passed to the
 .of_xlate() callback

of_flags is passed down to GPIO chip's xlate function, so ensure this one
is properly initialized as - if the xlate callback does nothing with it
- we may end up with various configuration errors like:

    gpio-720 (enable): multiple pull-up, pull-down or pull-disable enabled, invalid configuration

Signed-off-by: Alexander Stein <alexander.stein@ew.tq-group.com>
Link: https://lore.kernel.org/r/20250708083829.658051-1-alexander.stein@ew.tq-group.com
[Bartosz: tweaked the commit message]
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
---
 drivers/gpio/gpiolib-of.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpio/gpiolib-of.c b/drivers/gpio/gpiolib-of.c
index 73ba73b31cb1..37ab78243fab 100644
--- a/drivers/gpio/gpiolib-of.c
+++ b/drivers/gpio/gpiolib-of.c
@@ -708,7 +708,7 @@ struct gpio_desc *of_find_gpio(struct device_node *np, const char *con_id,
 			       unsigned int idx, unsigned long *flags)
 {
 	char propname[32]; /* 32 is max size of property name */
-	enum of_gpio_flags of_flags;
+	enum of_gpio_flags of_flags = 0;
 	const of_find_gpio_quirk *q;
 	struct gpio_desc *desc;
 

From 76303ee8d54bff6d9a6d55997acd88a6c2ba63cf Mon Sep 17 00:00:00 2001
From: Jann Horn <jannh@google.com>
Date: Wed, 2 Jul 2025 10:32:04 +0200
Subject: [PATCH 1258/1334] x86/mm: Disable hugetlb page table sharing on
 32-bit

Only select ARCH_WANT_HUGE_PMD_SHARE on 64-bit x86.
Page table sharing requires at least three levels because it involves
shared references to PMD tables; 32-bit x86 has either two-level paging
(without PAE) or three-level paging (with PAE), but even with
three-level paging, having a dedicated PGD entry for hugetlb is only
barely possible (because the PGD only has four entries), and it seems
unlikely anyone's actually using PMD sharing on 32-bit.

Having ARCH_WANT_HUGE_PMD_SHARE enabled on non-PAE 32-bit X86 (which
has 2-level paging) became particularly problematic after commit
59d9094df3d7 ("mm: hugetlb: independent PMD page table shared count"),
since that changes `struct ptdesc` such that the `pt_mm` (for PGDs) and
the `pt_share_count` (for PMDs) share the same union storage - and with
2-level paging, PMDs are PGDs.

(For comparison, arm64 also gates ARCH_WANT_HUGE_PMD_SHARE on the
configuration of page tables such that it is never enabled with 2-level
paging.)

Closes: https://lore.kernel.org/r/srhpjxlqfna67blvma5frmy3aa@altlinux.org
Fixes: cfe28c5d63d8 ("x86: mm: Remove x86 version of huge_pmd_share.")
Reported-by: Vitaly Chikunov <vt@altlinux.org>
Suggested-by: Dave Hansen <dave.hansen@intel.com>
Signed-off-by: Jann Horn <jannh@google.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Acked-by: Oscar Salvador <osalvador@suse.de>
Acked-by: David Hildenbrand <david@redhat.com>
Tested-by: Vitaly Chikunov <vt@altlinux.org>
Cc:stable@vger.kernel.org
Link: https://lore.kernel.org/all/20250702-x86-2level-hugetlb-v2-1-1a98096edf92%40google.com
---
 arch/x86/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 71019b3b54ea..4e0fe688cc83 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -147,7 +147,7 @@ config X86
 	select ARCH_WANTS_DYNAMIC_TASK_STRUCT
 	select ARCH_WANTS_NO_INSTR
 	select ARCH_WANT_GENERAL_HUGETLB
-	select ARCH_WANT_HUGE_PMD_SHARE
+	select ARCH_WANT_HUGE_PMD_SHARE		if X86_64
 	select ARCH_WANT_LD_ORPHAN_WARN
 	select ARCH_WANT_OPTIMIZE_DAX_VMEMMAP	if X86_64
 	select ARCH_WANT_OPTIMIZE_HUGETLB_VMEMMAP	if X86_64

From 8c2e52ebbe885c7eeaabd3b7ddcdc1246fc400d2 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Wed, 9 Jul 2025 10:38:29 -0700
Subject: [PATCH 1259/1334] eventpoll: don't decrement ep refcount while still
 holding the ep mutex

Jann Horn points out that epoll is decrementing the ep refcount and then
doing a

    mutex_unlock(&ep->mtx);

afterwards. That's very wrong, because it can lead to a use-after-free.

That pattern is actually fine for the very last reference, because the
code in question will delay the actual call to "ep_free(ep)" until after
it has unlocked the mutex.

But it's wrong for the much subtler "next to last" case when somebody
*else* may also be dropping their reference and free the ep while we're
still using the mutex.

Note that this is true even if that other user is also using the same ep
mutex: mutexes, unlike spinlocks, can not be used for object ownership,
even if they guarantee mutual exclusion.

A mutex "unlock" operation is not atomic, and as one user is still
accessing the mutex as part of unlocking it, another user can come in
and get the now released mutex and free the data structure while the
first user is still cleaning up.

See our mutex documentation in Documentation/locking/mutex-design.rst,
in particular the section [1] about semantics:

	"mutex_unlock() may access the mutex structure even after it has
	 internally released the lock already - so it's not safe for
	 another context to acquire the mutex and assume that the
	 mutex_unlock() context is not using the structure anymore"

So if we drop our ep ref before the mutex unlock, but we weren't the
last one, we may then unlock the mutex, another user comes in, drops
_their_ reference and releases the 'ep' as it now has no users - all
while the mutex_unlock() is still accessing it.

Fix this by simply moving the ep refcount dropping to outside the mutex:
the refcount itself is atomic, and doesn't need mutex protection (that's
the whole _point_ of refcounts: unlike mutexes, they are inherently
about object lifetimes).

Reported-by: Jann Horn <jannh@google.com>
Link: https://docs.kernel.org/locking/mutex-design.html#semantics [1]
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Jan Kara <jack@suse.cz>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/eventpoll.c | 12 +++++-------
 1 file changed, 5 insertions(+), 7 deletions(-)

diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index a97a771a459c..895256cd2786 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -828,7 +828,7 @@ static bool __ep_remove(struct eventpoll *ep, struct epitem *epi, bool force)
 	kfree_rcu(epi, rcu);
 
 	percpu_counter_dec(&ep->user->epoll_watches);
-	return ep_refcount_dec_and_test(ep);
+	return true;
 }
 
 /*
@@ -836,14 +836,14 @@ static bool __ep_remove(struct eventpoll *ep, struct epitem *epi, bool force)
  */
 static void ep_remove_safe(struct eventpoll *ep, struct epitem *epi)
 {
-	WARN_ON_ONCE(__ep_remove(ep, epi, false));
+	if (__ep_remove(ep, epi, false))
+		WARN_ON_ONCE(ep_refcount_dec_and_test(ep));
 }
 
 static void ep_clear_and_put(struct eventpoll *ep)
 {
 	struct rb_node *rbp, *next;
 	struct epitem *epi;
-	bool dispose;
 
 	/* We need to release all tasks waiting for these file */
 	if (waitqueue_active(&ep->poll_wait))
@@ -876,10 +876,8 @@ static void ep_clear_and_put(struct eventpoll *ep)
 		cond_resched();
 	}
 
-	dispose = ep_refcount_dec_and_test(ep);
 	mutex_unlock(&ep->mtx);
-
-	if (dispose)
+	if (ep_refcount_dec_and_test(ep))
 		ep_free(ep);
 }
 
@@ -1100,7 +1098,7 @@ again:
 		dispose = __ep_remove(ep, epi, true);
 		mutex_unlock(&ep->mtx);
 
-		if (dispose)
+		if (dispose && ep_refcount_dec_and_test(ep))
 			ep_free(ep);
 		goto again;
 	}

From 4578a747f3c7950be3feb93c2db32eb597a3e55b Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Wed, 9 Jul 2025 13:45:14 -0400
Subject: [PATCH 1260/1334] KVM: x86: avoid underflow when scaling TSC
 frequency

In function kvm_guest_time_update(), __scale_tsc() is used to calculate
a TSC *frequency* rather than a TSC value.  With low-enough ratios,
a TSC value that is less than 1 would underflow to 0 and to an infinite
while loop in kvm_get_time_scale():

  kvm_guest_time_update(struct kvm_vcpu *v)
    if (kvm_caps.has_tsc_control)
      tgt_tsc_khz = kvm_scale_tsc(tgt_tsc_khz,
                                  v->arch.l1_tsc_scaling_ratio);
        __scale_tsc(u64 ratio, u64 tsc)
          ratio=122380531, tsc=2299998, N=48
          ratio*tsc >> N = 0.999... -> 0

Later in the function:

  Call Trace:
   <TASK>
   kvm_get_time_scale arch/x86/kvm/x86.c:2458 [inline]
   kvm_guest_time_update+0x926/0xb00 arch/x86/kvm/x86.c:3268
   vcpu_enter_guest.constprop.0+0x1e70/0x3cf0 arch/x86/kvm/x86.c:10678
   vcpu_run+0x129/0x8d0 arch/x86/kvm/x86.c:11126
   kvm_arch_vcpu_ioctl_run+0x37a/0x13d0 arch/x86/kvm/x86.c:11352
   kvm_vcpu_ioctl+0x56b/0xe60 virt/kvm/kvm_main.c:4188
   vfs_ioctl fs/ioctl.c:51 [inline]
   __do_sys_ioctl fs/ioctl.c:871 [inline]
   __se_sys_ioctl+0x12d/0x190 fs/ioctl.c:857
   do_syscall_x64 arch/x86/entry/common.c:51 [inline]
   do_syscall_64+0x59/0x110 arch/x86/entry/common.c:81
   entry_SYSCALL_64_after_hwframe+0x78/0xe2

This can really happen only when fuzzing, since the TSC frequency
would have to be nonsensically low.

Fixes: 35181e86df97 ("KVM: x86: Add a common TSC scaling function")
Reported-by: Yuntao Liu <liuyuntao12@huawei.com>
Suggested-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/x86.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index b58a74c1722d..de51dbd85a58 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -3258,9 +3258,11 @@ int kvm_guest_time_update(struct kvm_vcpu *v)
 
 	/* With all the info we got, fill in the values */
 
-	if (kvm_caps.has_tsc_control)
+	if (kvm_caps.has_tsc_control) {
 		tgt_tsc_khz = kvm_scale_tsc(tgt_tsc_khz,
 					    v->arch.l1_tsc_scaling_ratio);
+		tgt_tsc_khz = tgt_tsc_khz ? : 1;
+	}
 
 	if (unlikely(vcpu->hw_tsc_khz != tgt_tsc_khz)) {
 		kvm_get_time_scale(NSEC_PER_SEC, tgt_tsc_khz * 1000LL,

From ec3cae639482a8da11a3ae30d28ceceb9d6a3f56 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Wed, 9 Jul 2025 19:12:47 +0200
Subject: [PATCH 1261/1334] PM: sleep: Call pm_restore_gfp_mask() after
 dpm_resume()

Commit 12ffc3b1513e ("PM: Restrict swap use to later in the suspend
sequence") changed two pm_restore_gfp_mask() calls in enter_state()
and hibernation_restore() into one pm_restore_gfp_mask() call in
dpm_resume_end(), but it put that call before the dpm_resume()
invocation which is too early (some swap-backing devices may not be
ready at that point).

Moreover, this code ordering change was not even mentioned in the
changelog of the commit mentioned above.

Address this by moving that call after the dpm_resume() one.

Fixes: 12ffc3b1513e ("PM: Restrict swap use to later in the suspend sequence")
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Reviewed-by: Mario Limonciello <mario.limonciello@amd.com>
Link: https://patch.msgid.link/2797018.mvXUDI8C0e@rjwysocki.net
---
 drivers/base/power/main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c
index bf77d28e959f..a6ab666ef48a 100644
--- a/drivers/base/power/main.c
+++ b/drivers/base/power/main.c
@@ -1236,8 +1236,8 @@ void dpm_complete(pm_message_t state)
  */
 void dpm_resume_end(pm_message_t state)
 {
-	pm_restore_gfp_mask();
 	dpm_resume(state);
+	pm_restore_gfp_mask();
 	dpm_complete(state);
 }
 EXPORT_SYMBOL_GPL(dpm_resume_end);

From 706cc36477139c1616a9b2b96610a8bb520b7119 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@google.com>
Date: Fri, 4 Jul 2025 06:23:51 +0000
Subject: [PATCH 1262/1334] atm: clip: Fix potential null-ptr-deref in
 to_atmarpd().

atmarpd is protected by RTNL since commit f3a0592b37b8 ("[ATM]: clip
causes unregister hang").

However, it is not enough because to_atmarpd() is called without RTNL,
especially clip_neigh_solicit() / neigh_ops->solicit() is unsleepable.

Also, there is no RTNL dependency around atmarpd.

Let's use a private mutex and RCU to protect access to atmarpd in
to_atmarpd().

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250704062416.1613927-2-kuniyu@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/atm/clip.c | 44 +++++++++++++++++++++++++++++---------------
 1 file changed, 29 insertions(+), 15 deletions(-)

diff --git a/net/atm/clip.c b/net/atm/clip.c
index b234dc3bcb0d..f36f2c7d8714 100644
--- a/net/atm/clip.c
+++ b/net/atm/clip.c
@@ -45,7 +45,8 @@
 #include <net/atmclip.h>
 
 static struct net_device *clip_devs;
-static struct atm_vcc *atmarpd;
+static struct atm_vcc __rcu *atmarpd;
+static DEFINE_MUTEX(atmarpd_lock);
 static struct timer_list idle_timer;
 static const struct neigh_ops clip_neigh_ops;
 
@@ -53,24 +54,35 @@ static int to_atmarpd(enum atmarp_ctrl_type type, int itf, __be32 ip)
 {
 	struct sock *sk;
 	struct atmarp_ctrl *ctrl;
+	struct atm_vcc *vcc;
 	struct sk_buff *skb;
+	int err = 0;
 
 	pr_debug("(%d)\n", type);
-	if (!atmarpd)
-		return -EUNATCH;
+
+	rcu_read_lock();
+	vcc = rcu_dereference(atmarpd);
+	if (!vcc) {
+		err = -EUNATCH;
+		goto unlock;
+	}
 	skb = alloc_skb(sizeof(struct atmarp_ctrl), GFP_ATOMIC);
-	if (!skb)
-		return -ENOMEM;
+	if (!skb) {
+		err = -ENOMEM;
+		goto unlock;
+	}
 	ctrl = skb_put(skb, sizeof(struct atmarp_ctrl));
 	ctrl->type = type;
 	ctrl->itf_num = itf;
 	ctrl->ip = ip;
-	atm_force_charge(atmarpd, skb->truesize);
+	atm_force_charge(vcc, skb->truesize);
 
-	sk = sk_atm(atmarpd);
+	sk = sk_atm(vcc);
 	skb_queue_tail(&sk->sk_receive_queue, skb);
 	sk->sk_data_ready(sk);
-	return 0;
+unlock:
+	rcu_read_unlock();
+	return err;
 }
 
 static void link_vcc(struct clip_vcc *clip_vcc, struct atmarp_entry *entry)
@@ -607,10 +619,12 @@ static void atmarpd_close(struct atm_vcc *vcc)
 {
 	pr_debug("\n");
 
-	rtnl_lock();
-	atmarpd = NULL;
+	mutex_lock(&atmarpd_lock);
+	RCU_INIT_POINTER(atmarpd, NULL);
+	mutex_unlock(&atmarpd_lock);
+
+	synchronize_rcu();
 	skb_queue_purge(&sk_atm(vcc)->sk_receive_queue);
-	rtnl_unlock();
 
 	pr_debug("(done)\n");
 	module_put(THIS_MODULE);
@@ -631,15 +645,15 @@ static struct atm_dev atmarpd_dev = {
 
 static int atm_init_atmarp(struct atm_vcc *vcc)
 {
-	rtnl_lock();
+	mutex_lock(&atmarpd_lock);
 	if (atmarpd) {
-		rtnl_unlock();
+		mutex_unlock(&atmarpd_lock);
 		return -EADDRINUSE;
 	}
 
 	mod_timer(&idle_timer, jiffies + CLIP_CHECK_INTERVAL * HZ);
 
-	atmarpd = vcc;
+	rcu_assign_pointer(atmarpd, vcc);
 	set_bit(ATM_VF_META, &vcc->flags);
 	set_bit(ATM_VF_READY, &vcc->flags);
 	    /* allow replies and avoid getting closed if signaling dies */
@@ -648,7 +662,7 @@ static int atm_init_atmarp(struct atm_vcc *vcc)
 	vcc->push = NULL;
 	vcc->pop = NULL; /* crash */
 	vcc->push_oam = NULL; /* crash */
-	rtnl_unlock();
+	mutex_unlock(&atmarpd_lock);
 	return 0;
 }
 

From 62dba28275a9a3104d4e33595c7b3328d4032d8d Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@google.com>
Date: Fri, 4 Jul 2025 06:23:52 +0000
Subject: [PATCH 1263/1334] atm: clip: Fix memory leak of struct clip_vcc.

ioctl(ATMARP_MKIP) allocates struct clip_vcc and set it to
vcc->user_back.

The code assumes that vcc_destroy_socket() passes NULL skb
to vcc->push() when the socket is close()d, and then clip_push()
frees clip_vcc.

However, ioctl(ATMARPD_CTRL) sets NULL to vcc->push() in
atm_init_atmarp(), resulting in memory leak.

Let's serialise two ioctl() by lock_sock() and check vcc->push()
in atm_init_atmarp() to prevent memleak.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250704062416.1613927-3-kuniyu@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/atm/clip.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/net/atm/clip.c b/net/atm/clip.c
index f36f2c7d8714..9c9c6c3d9886 100644
--- a/net/atm/clip.c
+++ b/net/atm/clip.c
@@ -645,6 +645,9 @@ static struct atm_dev atmarpd_dev = {
 
 static int atm_init_atmarp(struct atm_vcc *vcc)
 {
+	if (vcc->push == clip_push)
+		return -EINVAL;
+
 	mutex_lock(&atmarpd_lock);
 	if (atmarpd) {
 		mutex_unlock(&atmarpd_lock);
@@ -669,6 +672,7 @@ static int atm_init_atmarp(struct atm_vcc *vcc)
 static int clip_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
 {
 	struct atm_vcc *vcc = ATM_SD(sock);
+	struct sock *sk = sock->sk;
 	int err = 0;
 
 	switch (cmd) {
@@ -689,14 +693,18 @@ static int clip_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
 		err = clip_create(arg);
 		break;
 	case ATMARPD_CTRL:
+		lock_sock(sk);
 		err = atm_init_atmarp(vcc);
 		if (!err) {
 			sock->state = SS_CONNECTED;
 			__module_get(THIS_MODULE);
 		}
+		release_sock(sk);
 		break;
 	case ATMARP_MKIP:
+		lock_sock(sk);
 		err = clip_mkip(vcc, arg);
+		release_sock(sk);
 		break;
 	case ATMARP_SETENTRY:
 		err = clip_setentry(vcc, (__force __be32)arg);

From c489f3283dbfc0f3c00c312149cae90d27552c45 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@google.com>
Date: Fri, 4 Jul 2025 06:23:53 +0000
Subject: [PATCH 1264/1334] atm: clip: Fix infinite recursive call of
 clip_push().

syzbot reported the splat below. [0]

This happens if we call ioctl(ATMARP_MKIP) more than once.

During the first call, clip_mkip() sets clip_push() to vcc->push(),
and the second call copies it to clip_vcc->old_push().

Later, when the socket is close()d, vcc_destroy_socket() passes
NULL skb to clip_push(), which calls clip_vcc->old_push(),
triggering the infinite recursion.

Let's prevent the second ioctl(ATMARP_MKIP) by checking
vcc->user_back, which is allocated by the first call as clip_vcc.

Note also that we use lock_sock() to prevent racy calls.

[0]:
BUG: TASK stack guard page was hit at ffffc9000d66fff8 (stack is ffffc9000d670000..ffffc9000d678000)
Oops: stack guard page: 0000 [#1] SMP KASAN NOPTI
CPU: 0 UID: 0 PID: 5322 Comm: syz.0.0 Not tainted 6.16.0-rc4-syzkaller #0 PREEMPT(full)
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.3-debian-1.16.3-2~bpo12+1 04/01/2014
RIP: 0010:clip_push+0x5/0x720 net/atm/clip.c:191
Code: e0 8f aa 8c e8 1c ad 5b fa eb ae 66 2e 0f 1f 84 00 00 00 00 00 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 f3 0f 1e fa 55 <41> 57 41 56 41 55 41 54 53 48 83 ec 20 48 89 f3 49 89 fd 48 bd 00
RSP: 0018:ffffc9000d670000 EFLAGS: 00010246
RAX: 1ffff1100235a4a5 RBX: ffff888011ad2508 RCX: ffff8880003c0000
RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffff888037f01000
RBP: dffffc0000000000 R08: ffffffff8fa104f7 R09: 1ffffffff1f4209e
R10: dffffc0000000000 R11: ffffffff8a99b300 R12: ffffffff8a99b300
R13: ffff888037f01000 R14: ffff888011ad2500 R15: ffff888037f01578
FS:  000055557ab6d500(0000) GS:ffff88808d250000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: ffffc9000d66fff8 CR3: 0000000043172000 CR4: 0000000000352ef0
Call Trace:
 <TASK>
 clip_push+0x6dc/0x720 net/atm/clip.c:200
 clip_push+0x6dc/0x720 net/atm/clip.c:200
 clip_push+0x6dc/0x720 net/atm/clip.c:200
...
 clip_push+0x6dc/0x720 net/atm/clip.c:200
 clip_push+0x6dc/0x720 net/atm/clip.c:200
 clip_push+0x6dc/0x720 net/atm/clip.c:200
 vcc_destroy_socket net/atm/common.c:183 [inline]
 vcc_release+0x157/0x460 net/atm/common.c:205
 __sock_release net/socket.c:647 [inline]
 sock_close+0xc0/0x240 net/socket.c:1391
 __fput+0x449/0xa70 fs/file_table.c:465
 task_work_run+0x1d1/0x260 kernel/task_work.c:227
 resume_user_mode_work include/linux/resume_user_mode.h:50 [inline]
 exit_to_user_mode_loop+0xec/0x110 kernel/entry/common.c:114
 exit_to_user_mode_prepare include/linux/entry-common.h:330 [inline]
 syscall_exit_to_user_mode_work include/linux/entry-common.h:414 [inline]
 syscall_exit_to_user_mode include/linux/entry-common.h:449 [inline]
 do_syscall_64+0x2bd/0x3b0 arch/x86/entry/syscall_64.c:100
 entry_SYSCALL_64_after_hwframe+0x77/0x7f
RIP: 0033:0x7ff31c98e929
Code: ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 40 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 a8 ff ff ff f7 d8 64 89 01 48
RSP: 002b:00007fffb5aa1f78 EFLAGS: 00000246 ORIG_RAX: 00000000000001b4
RAX: 0000000000000000 RBX: 0000000000012747 RCX: 00007ff31c98e929
RDX: 0000000000000000 RSI: 000000000000001e RDI: 0000000000000003
RBP: 00007ff31cbb7ba0 R08: 0000000000000001 R09: 0000000db5aa226f
R10: 00007ff31c7ff030 R11: 0000000000000246 R12: 00007ff31cbb608c
R13: 00007ff31cbb6080 R14: ffffffffffffffff R15: 00007fffb5aa2090
 </TASK>
Modules linked in:

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Reported-by: syzbot+0c77cccd6b7cd917b35a@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=2371d94d248d126c1eb1
Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250704062416.1613927-4-kuniyu@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/atm/clip.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/atm/clip.c b/net/atm/clip.c
index 9c9c6c3d9886..a30c5a270545 100644
--- a/net/atm/clip.c
+++ b/net/atm/clip.c
@@ -429,6 +429,8 @@ static int clip_mkip(struct atm_vcc *vcc, int timeout)
 
 	if (!vcc->push)
 		return -EBADFD;
+	if (vcc->user_back)
+		return -EINVAL;
 	clip_vcc = kmalloc(sizeof(struct clip_vcc), GFP_KERNEL);
 	if (!clip_vcc)
 		return -ENOMEM;

From 22fc46cea91df3dce140a7dc6847c6fcf0354505 Mon Sep 17 00:00:00 2001
From: Yue Haibing <yuehaibing@huawei.com>
Date: Sat, 5 Jul 2025 16:52:28 +0800
Subject: [PATCH 1265/1334] atm: clip: Fix NULL pointer dereference in
 vcc_sendmsg()

atmarpd_dev_ops does not implement the send method, which may cause crash
as bellow.

BUG: kernel NULL pointer dereference, address: 0000000000000000
PGD 0 P4D 0
Oops: Oops: 0010 [#1] SMP KASAN NOPTI
CPU: 0 UID: 0 PID: 5324 Comm: syz.0.0 Not tainted 6.15.0-rc6-syzkaller-00346-g5723cc3450bc #0 PREEMPT(full)
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.3-debian-1.16.3-2~bpo12+1 04/01/2014
RIP: 0010:0x0
Code: Unable to access opcode bytes at 0xffffffffffffffd6.
RSP: 0018:ffffc9000d3cf778 EFLAGS: 00010246
RAX: 1ffffffff1910dd1 RBX: 00000000000000c0 RCX: dffffc0000000000
RDX: ffffc9000dc82000 RSI: ffff88803e4c4640 RDI: ffff888052cd0000
RBP: ffffc9000d3cf8d0 R08: ffff888052c9143f R09: 1ffff1100a592287
R10: dffffc0000000000 R11: 0000000000000000 R12: 1ffff92001a79f00
R13: ffff888052cd0000 R14: ffff88803e4c4640 R15: ffffffff8c886e88
FS:  00007fbc762566c0(0000) GS:ffff88808d6c2000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: ffffffffffffffd6 CR3: 0000000041f1b000 CR4: 0000000000352ef0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
 <TASK>
 vcc_sendmsg+0xa10/0xc50 net/atm/common.c:644
 sock_sendmsg_nosec net/socket.c:712 [inline]
 __sock_sendmsg+0x219/0x270 net/socket.c:727
 ____sys_sendmsg+0x52d/0x830 net/socket.c:2566
 ___sys_sendmsg+0x21f/0x2a0 net/socket.c:2620
 __sys_sendmmsg+0x227/0x430 net/socket.c:2709
 __do_sys_sendmmsg net/socket.c:2736 [inline]
 __se_sys_sendmmsg net/socket.c:2733 [inline]
 __x64_sys_sendmmsg+0xa0/0xc0 net/socket.c:2733
 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline]
 do_syscall_64+0xf6/0x210 arch/x86/entry/syscall_64.c:94
 entry_SYSCALL_64_after_hwframe+0x77/0x7f

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Reported-by: syzbot+e34e5e6b5eddb0014def@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/all/682f82d5.a70a0220.1765ec.0143.GAE@google.com/T
Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com>
Link: https://patch.msgid.link/20250705085228.329202-1-yuehaibing@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/atm/clip.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/net/atm/clip.c b/net/atm/clip.c
index a30c5a270545..f7a5565e794e 100644
--- a/net/atm/clip.c
+++ b/net/atm/clip.c
@@ -632,8 +632,16 @@ static void atmarpd_close(struct atm_vcc *vcc)
 	module_put(THIS_MODULE);
 }
 
+static int atmarpd_send(struct atm_vcc *vcc, struct sk_buff *skb)
+{
+	atm_return_tx(vcc, skb);
+	dev_kfree_skb_any(skb);
+	return 0;
+}
+
 static const struct atmdev_ops atmarpd_dev_ops = {
-	.close = atmarpd_close
+	.close = atmarpd_close,
+	.send = atmarpd_send
 };
 
 

From d55683866c79a3af1e334126f32841d05e7e4143 Mon Sep 17 00:00:00 2001
From: Victor Nogueira <victor@mojatatu.com>
Date: Sat, 5 Jul 2025 17:36:38 -0300
Subject: [PATCH 1266/1334] selftests/tc-testing: Create test case for UAF
 scenario with DRR/NETEM/BLACKHOLE chain

Create a tdc test for the UAF scenario with DRR/NETEM/BLACKHOLE chain
shared by Lion on his report [1].

[1] https://lore.kernel.org/netdev/45876f14-cf28-4177-8ead-bb769fd9e57a@gmail.com/

Signed-off-by: Victor Nogueira <victor@mojatatu.com>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Link: https://patch.msgid.link/20250705203638.246350-1-victor@mojatatu.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../tc-testing/tc-tests/infra/qdiscs.json     | 37 +++++++++++++++++++
 1 file changed, 37 insertions(+)

diff --git a/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json b/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json
index 9aa44d8176d9..5c6851e8d311 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json
@@ -635,5 +635,42 @@
             "$TC qdisc del dev $DUMMY handle 1:0 root",
             "$IP addr del 10.10.10.10/24 dev $DUMMY || true"
         ]
+    },
+    {
+        "id": "d74b",
+        "name": "Test use-after-free with DRR/NETEM/BLACKHOLE chain",
+        "category": [
+            "qdisc",
+            "hfsc",
+            "drr",
+            "netem",
+            "blackhole"
+        ],
+        "plugins": {
+            "requires": [
+                "nsPlugin",
+                "scapyPlugin"
+            ]
+        },
+        "setup": [
+            "$IP link set dev $DUMMY up || true",
+            "$IP addr add 10.10.11.10/24 dev $DUMMY || true",
+            "$TC qdisc add dev $DUMMY root handle 1: drr",
+            "$TC filter add dev $DUMMY parent 1: basic classid 1:1",
+            "$TC class add dev $DUMMY parent 1: classid 1:1 drr",
+            "$TC qdisc add dev $DUMMY parent 1:1 handle 2: hfsc def 1",
+            "$TC class add dev $DUMMY parent 2: classid 2:1 hfsc rt m1 8 d 1 m2 0",
+            "$TC qdisc add dev $DUMMY parent 2:1 handle 3: netem",
+            "$TC qdisc add dev $DUMMY parent 3:1 handle 4: blackhole",
+            "ping -c1 -W0.01 -I $DUMMY 10.10.11.11 || true",
+            "$TC class del dev $DUMMY classid 1:1"
+        ],
+        "cmdUnderTest": "ping -c1 -W0.01 -I $DUMMY 10.10.11.11",
+        "expExitCode": "1",
+        "verifyCmd": "$TC -j class ls dev $DUMMY classid 1:1",
+        "matchJSON": [],
+        "teardown": [
+            "$TC qdisc del dev $DUMMY root handle 1: drr"
+        ]
     }
 ]

From 849704b8b2115647e12436e5076b8e7a4944f21a Mon Sep 17 00:00:00 2001
From: Alok Tiwari <alok.a.tiwari@oracle.com>
Date: Sun, 6 Jul 2025 12:43:21 -0700
Subject: [PATCH 1267/1334] net: thunderx: avoid direct MTU assignment after
 WRITE_ONCE()

The current logic in nicvf_change_mtu() writes the new MTU to
netdev->mtu using WRITE_ONCE() before verifying if the hardware
update succeeds. However on hardware update failure, it attempts
to revert to the original MTU using a direct assignment
(netdev->mtu = orig_mtu)
which violates the intended of WRITE_ONCE protection introduced in
commit 1eb2cded45b3 ("net: annotate writes on dev->mtu from
ndo_change_mtu()")

Additionally, WRITE_ONCE(netdev->mtu, new_mtu) is unnecessarily
performed even when the device is not running.

Fix this by:
  Only writing netdev->mtu after successfully updating the hardware.
  Skipping hardware update when the device is down, and setting MTU
  directly. Remove unused variable orig_mtu.

This ensures that all writes to netdev->mtu are consistent with
WRITE_ONCE expectations and avoids unintended state corruption
on failure paths.

Signed-off-by: Alok Tiwari <alok.a.tiwari@oracle.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://patch.msgid.link/20250706194327.1369390-1-alok.a.tiwari@oracle.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/cavium/thunder/nicvf_main.c | 12 +++---------
 1 file changed, 3 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
index aebb9fef3f6e..1be2dc40a1a6 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
@@ -1578,7 +1578,6 @@ napi_del:
 static int nicvf_change_mtu(struct net_device *netdev, int new_mtu)
 {
 	struct nicvf *nic = netdev_priv(netdev);
-	int orig_mtu = netdev->mtu;
 
 	/* For now just support only the usual MTU sized frames,
 	 * plus some headroom for VLAN, QinQ.
@@ -1589,15 +1588,10 @@ static int nicvf_change_mtu(struct net_device *netdev, int new_mtu)
 		return -EINVAL;
 	}
 
-	WRITE_ONCE(netdev->mtu, new_mtu);
-
-	if (!netif_running(netdev))
-		return 0;
-
-	if (nicvf_update_hw_max_frs(nic, new_mtu)) {
-		netdev->mtu = orig_mtu;
+	if (netif_running(netdev) && nicvf_update_hw_max_frs(nic, new_mtu))
 		return -EINVAL;
-	}
+
+	WRITE_ONCE(netdev->mtu, new_mtu);
 
 	return 0;
 }

From 02c4d6c26f1f662da8885b299c224ca6628ad232 Mon Sep 17 00:00:00 2001
From: Chintan Vankar <c-vankar@ti.com>
Date: Mon, 7 Jul 2025 14:22:01 +0530
Subject: [PATCH 1268/1334] net: ethernet: ti: am65-cpsw-nuss: Fix skb size by
 accounting for skb_shared_info

While transitioning from netdev_alloc_ip_align() to build_skb(), memory
for the "skb_shared_info" member of an "skb" was not allocated. Fix this
by allocating "PAGE_SIZE" as the skb length, accounting for the packet
length, headroom and tailroom, thereby including the required memory space
for skb_shared_info.

Fixes: 8acacc40f733 ("net: ethernet: ti: am65-cpsw: Add minimal XDP support")
Reviewed-by: Siddharth Vadapalli <s-vadapalli@ti.com>
Signed-off-by: Chintan Vankar <c-vankar@ti.com>
Link: https://patch.msgid.link/20250707085201.1898818-1-c-vankar@ti.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/ti/am65-cpsw-nuss.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c
index f20d1ff192ef..231ca141331f 100644
--- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c
+++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c
@@ -856,8 +856,6 @@ static struct sk_buff *am65_cpsw_build_skb(void *page_addr,
 {
 	struct sk_buff *skb;
 
-	len += AM65_CPSW_HEADROOM;
-
 	skb = build_skb(page_addr, len);
 	if (unlikely(!skb))
 		return NULL;
@@ -1344,7 +1342,7 @@ static int am65_cpsw_nuss_rx_packets(struct am65_cpsw_rx_flow *flow,
 	}
 
 	skb = am65_cpsw_build_skb(page_addr, ndev,
-				  AM65_CPSW_MAX_PACKET_SIZE, headroom);
+				  PAGE_SIZE, headroom);
 	if (unlikely(!skb)) {
 		new_page = page;
 		goto requeue;

From ffdde7bf5a439aaa1955ebd581f5c64ab1533963 Mon Sep 17 00:00:00 2001
From: Victor Nogueira <victor@mojatatu.com>
Date: Mon, 7 Jul 2025 18:08:01 -0300
Subject: [PATCH 1269/1334] net/sched: Abort __tc_modify_qdisc if parent class
 does not exist

Lion's patch [1] revealed an ancient bug in the qdisc API.
Whenever a user creates/modifies a qdisc specifying as a parent another
qdisc, the qdisc API will, during grafting, detect that the user is
not trying to attach to a class and reject. However grafting is
performed after qdisc_create (and thus the qdiscs' init callback) is
executed. In qdiscs that eventually call qdisc_tree_reduce_backlog
during init or change (such as fq, hhf, choke, etc), an issue
arises. For example, executing the following commands:

sudo tc qdisc add dev lo root handle a: htb default 2
sudo tc qdisc add dev lo parent a: handle beef fq

Qdiscs such as fq, hhf, choke, etc unconditionally invoke
qdisc_tree_reduce_backlog() in their control path init() or change() which
then causes a failure to find the child class; however, that does not stop
the unconditional invocation of the assumed child qdisc's qlen_notify with
a null class. All these qdiscs make the assumption that class is non-null.

The solution is ensure that qdisc_leaf() which looks up the parent
class, and is invoked prior to qdisc_create(), should return failure on
not finding the class.
In this patch, we leverage qdisc_leaf to return ERR_PTRs whenever the
parentid doesn't correspond to a class, so that we can detect it
earlier on and abort before qdisc_create is called.

[1] https://lore.kernel.org/netdev/d912cbd7-193b-4269-9857-525bee8bbb6a@gmail.com/

Fixes: 5e50da01d0ce ("[NET_SCHED]: Fix endless loops (part 2): "simple" qdiscs")
Reported-by: syzbot+d8b58d7b0ad89a678a16@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/netdev/68663c93.a70a0220.5d25f.0857.GAE@google.com/
Reported-by: syzbot+5eccb463fa89309d8bdc@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/netdev/68663c94.a70a0220.5d25f.0858.GAE@google.com/
Reported-by: syzbot+1261670bbdefc5485a06@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/netdev/686764a5.a00a0220.c7b3.0013.GAE@google.com/
Reported-by: syzbot+15b96fc3aac35468fe77@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/netdev/686764a5.a00a0220.c7b3.0014.GAE@google.com/
Reported-by: syzbot+4dadc5aecf80324d5a51@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/netdev/68679e81.a70a0220.29cf51.0016.GAE@google.com/
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Reviewed-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: Victor Nogueira <victor@mojatatu.com>
Link: https://patch.msgid.link/20250707210801.372995-1-victor@mojatatu.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/sched/sch_api.c | 23 ++++++++++++++++-------
 1 file changed, 16 insertions(+), 7 deletions(-)

diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index d8a33486c511..241e86cec9c5 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -336,17 +336,22 @@ out:
 	return q;
 }
 
-static struct Qdisc *qdisc_leaf(struct Qdisc *p, u32 classid)
+static struct Qdisc *qdisc_leaf(struct Qdisc *p, u32 classid,
+				struct netlink_ext_ack *extack)
 {
 	unsigned long cl;
 	const struct Qdisc_class_ops *cops = p->ops->cl_ops;
 
-	if (cops == NULL)
-		return NULL;
+	if (cops == NULL) {
+		NL_SET_ERR_MSG(extack, "Parent qdisc is not classful");
+		return ERR_PTR(-EOPNOTSUPP);
+	}
 	cl = cops->find(p, classid);
 
-	if (cl == 0)
-		return NULL;
+	if (cl == 0) {
+		NL_SET_ERR_MSG(extack, "Specified class not found");
+		return ERR_PTR(-ENOENT);
+	}
 	return cops->leaf(p, cl);
 }
 
@@ -1490,7 +1495,7 @@ static int __tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n,
 					NL_SET_ERR_MSG(extack, "Failed to find qdisc with specified classid");
 					return -ENOENT;
 				}
-				q = qdisc_leaf(p, clid);
+				q = qdisc_leaf(p, clid, extack);
 			} else if (dev_ingress_queue(dev)) {
 				q = rtnl_dereference(dev_ingress_queue(dev)->qdisc_sleeping);
 			}
@@ -1501,6 +1506,8 @@ static int __tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n,
 			NL_SET_ERR_MSG(extack, "Cannot find specified qdisc on specified device");
 			return -ENOENT;
 		}
+		if (IS_ERR(q))
+			return PTR_ERR(q);
 
 		if (tcm->tcm_handle && q->handle != tcm->tcm_handle) {
 			NL_SET_ERR_MSG(extack, "Invalid handle");
@@ -1602,7 +1609,9 @@ static int __tc_modify_qdisc(struct sk_buff *skb, struct nlmsghdr *n,
 					NL_SET_ERR_MSG(extack, "Failed to find specified qdisc");
 					return -ENOENT;
 				}
-				q = qdisc_leaf(p, clid);
+				q = qdisc_leaf(p, clid, extack);
+				if (IS_ERR(q))
+					return PTR_ERR(q);
 			} else if (dev_ingress_queue_create(dev)) {
 				q = rtnl_dereference(dev_ingress_queue(dev)->qdisc_sleeping);
 			}

From 1a03edeb84e6e3b9c6ca5a642557bced93d54434 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 7 Jul 2025 21:38:59 +0000
Subject: [PATCH 1270/1334] tcp: refine sk_rcvbuf increase for ooo packets

When a passive flow has not been accepted yet, it is
not wise to increase sk_rcvbuf when receiving ooo packets.

A very busy server might tune down tcp_rmem[1] to better
control how much memory can be used by sockets waiting
in its listeners accept queues.

Fixes: 63ad7dfedfae ("tcp: adjust rcvbuf in presence of reorders")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20250707213900.1543248-2-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/tcp_input.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 12c2e6fc85c6..68bc79eb9019 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -5181,7 +5181,9 @@ end:
 		skb_condense(skb);
 		skb_set_owner_r(skb, sk);
 	}
-	tcp_rcvbuf_grow(sk);
+	/* do not grow rcvbuf for not-yet-accepted or orphaned sockets. */
+	if (sk->sk_socket)
+		tcp_rcvbuf_grow(sk);
 }
 
 static int __must_check tcp_queue_rcv(struct sock *sk, struct sk_buff *skb,

From b939c074efc160648de884a41aeb5e857f2c5c68 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 7 Jul 2025 21:39:00 +0000
Subject: [PATCH 1271/1334] selftests/net: packetdrill: add
 tcp_ooo-before-and-after-accept.pkt

Test how new passive flows react to ooo incoming packets.

Their sk_rcvbuf can increase only after accept().

Signed-off-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20250707213900.1543248-3-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../tcp_ooo-before-and-after-accept.pkt       | 53 +++++++++++++++++++
 1 file changed, 53 insertions(+)
 create mode 100644 tools/testing/selftests/net/packetdrill/tcp_ooo-before-and-after-accept.pkt

diff --git a/tools/testing/selftests/net/packetdrill/tcp_ooo-before-and-after-accept.pkt b/tools/testing/selftests/net/packetdrill/tcp_ooo-before-and-after-accept.pkt
new file mode 100644
index 000000000000..09aabc775e80
--- /dev/null
+++ b/tools/testing/selftests/net/packetdrill/tcp_ooo-before-and-after-accept.pkt
@@ -0,0 +1,53 @@
+// SPDX-License-Identifier: GPL-2.0
+
+--mss=1000
+
+`./defaults.sh
+sysctl -q net.ipv4.tcp_rmem="4096 131072 $((32*1024*1024))"`
+
+// Test that a not-yet-accepted socket does not change
+// its initial sk_rcvbuf (tcp_rmem[1]) when receiving ooo packets.
+
+   +0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+   +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+   +0 bind(3, ..., ...) = 0
+   +0 listen(3, 1) = 0
+
+   +0 < S 0:0(0) win 65535 <mss 1000,nop,nop,sackOK,nop,wscale 7>
+   +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 10>
+  +.1 < . 1:1(0) ack 1 win 257
+  +0  < . 2001:41001(39000) ack 1 win 257
+  +0  > . 1:1(0) ack 1 <nop,nop,sack 2001:41001>
+  +0  < . 41001:101001(60000) ack 1 win 257
+  +0  > . 1:1(0) ack 1 <nop,nop,sack 2001:101001>
+  +0  < . 1:1001(1000) ack 1 win 257
+  +0  > . 1:1(0) ack 1001 <nop,nop,sack 2001:101001>
+  +0  < . 1001:2001(1000) ack 1 win 257
+  +0  > . 1:1(0) ack 101001
+
+  +0 accept(3, ..., ...) = 4
+
+  +0 %{ assert SK_MEMINFO_RCVBUF == 131072, SK_MEMINFO_RCVBUF }%
+
+  +0 close(4) = 0
+  +0 close(3) = 0
+
+// Test that ooo packets for accepted sockets do increase sk_rcvbuf
+   +0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+   +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+   +0 bind(3, ..., ...) = 0
+   +0 listen(3, 1) = 0
+
+   +0 < S 0:0(0) win 65535 <mss 1000,nop,nop,sackOK,nop,wscale 7>
+   +0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 10>
+  +.1 < . 1:1(0) ack 1 win 257
+
+   +0 accept(3, ..., ...) = 4
+
+  +0  < . 2001:41001(39000) ack 1 win 257
+  +0  > . 1:1(0) ack 1 <nop,nop,sack 2001:41001>
+  +0  < . 41001:101001(60000) ack 1 win 257
+  +0  > . 1:1(0) ack 1 <nop,nop,sack 2001:101001>
+
+  +0 %{ assert SK_MEMINFO_RCVBUF > 131072, SK_MEMINFO_RCVBUF }%
+

From ee48b0abeca9afcd5a8bcb92345002d2667893ba Mon Sep 17 00:00:00 2001
From: Louis Peens <louis.peens@corigine.com>
Date: Tue, 8 Jul 2025 10:20:51 +0200
Subject: [PATCH 1272/1334] MAINTAINERS: remove myself as netronome maintainer

I am moving on from Corigine to different things, for the moment
slightly removed from kernel development. Right now there is nobody I
can in good conscience recommend to take over the maintainer role, but
there are still people available for review, so put the driver state to
'Odd Fixes'.

Additionally add Simon Horman as reviewer - thanks Simon.

Signed-off-by: Louis Peens <louis.peens@corigine.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 MAINTAINERS | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index fad6cb025a19..3cf8ecc9f517 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -17222,10 +17222,10 @@ F:	drivers/rtc/rtc-ntxec.c
 F:	include/linux/mfd/ntxec.h
 
 NETRONOME ETHERNET DRIVERS
-M:	Louis Peens <louis.peens@corigine.com>
 R:	Jakub Kicinski <kuba@kernel.org>
+R:	Simon Horman <horms@kernel.org>
 L:	oss-drivers@corigine.com
-S:	Maintained
+S:	Odd Fixes
 F:	drivers/net/ethernet/netronome/
 
 NETWORK BLOCK DEVICE (NBD)

From 69e4186773c6445b258fb45b6e1df18df831ec45 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Tue, 8 Jul 2025 22:15:03 +0100
Subject: [PATCH 1273/1334] rxrpc: Fix bug due to prealloc collision

When userspace is using AF_RXRPC to provide a server, it has to preallocate
incoming calls and assign to them call IDs that will be used to thread
related recvmsg() and sendmsg() together.  The preallocated call IDs will
automatically be attached to calls as they come in until the pool is empty.

To the kernel, the call IDs are just arbitrary numbers, but userspace can
use the call ID to hold a pointer to prepared structs.  In any case, the
user isn't permitted to create two calls with the same call ID (call IDs
become available again when the call ends) and EBADSLT should result from
sendmsg() if an attempt is made to preallocate a call with an in-use call
ID.

However, the cleanup in the error handling will trigger both assertions in
rxrpc_cleanup_call() because the call isn't marked complete and isn't
marked as having been released.

Fix this by setting the call state in rxrpc_service_prealloc_one() and then
marking it as being released before calling the cleanup function.

Fixes: 00e907127e6f ("rxrpc: Preallocate peers, conns and calls for incoming service requests")
Reported-by: Junvyyang, Tencent Zhuque Lab <zhuque@tencent.com>
Signed-off-by: David Howells <dhowells@redhat.com>
cc: LePremierHomme <kwqcheii@proton.me>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: Simon Horman <horms@kernel.org>
cc: linux-afs@lists.infradead.org
Link: https://patch.msgid.link/20250708211506.2699012-2-dhowells@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/rxrpc/call_accept.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c
index a4b363b47cca..7271977b1683 100644
--- a/net/rxrpc/call_accept.c
+++ b/net/rxrpc/call_accept.c
@@ -149,6 +149,7 @@ static int rxrpc_service_prealloc_one(struct rxrpc_sock *rx,
 
 id_in_use:
 	write_unlock(&rx->call_lock);
+	rxrpc_prefail_call(call, RXRPC_CALL_LOCAL_ERROR, -EBADSLT);
 	rxrpc_cleanup_call(call);
 	_leave(" = -EBADSLT");
 	return -EBADSLT;

From 880a88f318cf1d2a0f4c0a7ff7b07e2062b434a4 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Tue, 8 Jul 2025 22:15:04 +0100
Subject: [PATCH 1274/1334] rxrpc: Fix oops due to non-existence of prealloc
 backlog struct

If an AF_RXRPC service socket is opened and bound, but calls are
preallocated, then rxrpc_alloc_incoming_call() will oops because the
rxrpc_backlog struct doesn't get allocated until the first preallocation is
made.

Fix this by returning NULL from rxrpc_alloc_incoming_call() if there is no
backlog struct.  This will cause the incoming call to be aborted.

Reported-by: Junvyyang, Tencent Zhuque Lab <zhuque@tencent.com>
Suggested-by: Junvyyang, Tencent Zhuque Lab <zhuque@tencent.com>
Signed-off-by: David Howells <dhowells@redhat.com>
cc: LePremierHomme <kwqcheii@proton.me>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: Willy Tarreau <w@1wt.eu>
cc: Simon Horman <horms@kernel.org>
cc: linux-afs@lists.infradead.org
Link: https://patch.msgid.link/20250708211506.2699012-3-dhowells@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/rxrpc/call_accept.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c
index 7271977b1683..49fccee1a726 100644
--- a/net/rxrpc/call_accept.c
+++ b/net/rxrpc/call_accept.c
@@ -255,6 +255,9 @@ static struct rxrpc_call *rxrpc_alloc_incoming_call(struct rxrpc_sock *rx,
 	unsigned short call_tail, conn_tail, peer_tail;
 	unsigned short call_count, conn_count;
 
+	if (!b)
+		return NULL;
+
 	/* #calls >= #conns >= #peers must hold true. */
 	call_head = smp_load_acquire(&b->call_backlog_head);
 	call_tail = b->call_backlog_tail;

From a95743b53031b015e8949e845a9f6fdfb2656347 Mon Sep 17 00:00:00 2001
From: Achill Gilgenast <fossdd@pwned.life>
Date: Sun, 22 Jun 2025 03:45:49 +0200
Subject: [PATCH 1275/1334] kallsyms: fix build without execinfo

Some libc's like musl libc don't provide execinfo.h since it's not part of
POSIX.  In order to fix compilation on musl, only include execinfo.h if
available (HAVE_BACKTRACE_SUPPORT)

This was discovered with c104c16073b7 ("Kunit to check the longest symbol
length") which starts to include linux/kallsyms.h with Alpine Linux'
configs.

Link: https://lkml.kernel.org/r/20250622014608.448718-1-fossdd@pwned.life
Fixes: c104c16073b7 ("Kunit to check the longest symbol length")
Signed-off-by: Achill Gilgenast <fossdd@pwned.life>
Cc: Luis Henriques <luis@igalia.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 tools/include/linux/kallsyms.h | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/tools/include/linux/kallsyms.h b/tools/include/linux/kallsyms.h
index 5a37ccbec54f..f61a01dd7eb7 100644
--- a/tools/include/linux/kallsyms.h
+++ b/tools/include/linux/kallsyms.h
@@ -18,6 +18,7 @@ static inline const char *kallsyms_lookup(unsigned long addr,
 	return NULL;
 }
 
+#ifdef HAVE_BACKTRACE_SUPPORT
 #include <execinfo.h>
 #include <stdlib.h>
 static inline void print_ip_sym(const char *loglvl, unsigned long ip)
@@ -30,5 +31,8 @@ static inline void print_ip_sym(const char *loglvl, unsigned long ip)
 
 	free(name);
 }
+#else
+static inline void print_ip_sym(const char *loglvl, unsigned long ip) {}
+#endif
 
 #endif

From 99af22cd34688cc0d535a1919e0bea4cbc6c1ea1 Mon Sep 17 00:00:00 2001
From: Harry Yoo <harry.yoo@oracle.com>
Date: Sat, 21 Jun 2025 04:53:05 +0900
Subject: [PATCH 1276/1334] lib/alloc_tag: do not acquire non-existent lock in
 alloc_tag_top_users()

alloc_tag_top_users() attempts to lock alloc_tag_cttype->mod_lock even
when the alloc_tag_cttype is not allocated because:

  1) alloc tagging is disabled because mem profiling is disabled
     (!alloc_tag_cttype)
  2) alloc tagging is enabled, but not yet initialized (!alloc_tag_cttype)
  3) alloc tagging is enabled, but failed initialization
     (!alloc_tag_cttype or IS_ERR(alloc_tag_cttype))

In all cases, alloc_tag_cttype is not allocated, and therefore
alloc_tag_top_users() should not attempt to acquire the semaphore.

This leads to a crash on memory allocation failure by attempting to
acquire a non-existent semaphore:

  Oops: general protection fault, probably for non-canonical address 0xdffffc000000001b: 0000 [#3] SMP KASAN NOPTI
  KASAN: null-ptr-deref in range [0x00000000000000d8-0x00000000000000df]
  CPU: 2 UID: 0 PID: 1 Comm: systemd Tainted: G      D             6.16.0-rc2 #1 VOLUNTARY
  Tainted: [D]=DIE
  Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.16.2-debian-1.16.2-1 04/01/2014
  RIP: 0010:down_read_trylock+0xaa/0x3b0
  Code: d0 7c 08 84 d2 0f 85 a0 02 00 00 8b 0d df 31 dd 04 85 c9 75 29 48 b8 00 00 00 00 00 fc ff df 48 8d 6b 68 48 89 ea 48 c1 ea 03 <80> 3c 02 00 0f 85 88 02 00 00 48 3b 5b 68 0f 85 53 01 00 00 65 ff
  RSP: 0000:ffff8881002ce9b8 EFLAGS: 00010016
  RAX: dffffc0000000000 RBX: 0000000000000070 RCX: 0000000000000000
  RDX: 000000000000001b RSI: 000000000000000a RDI: 0000000000000070
  RBP: 00000000000000d8 R08: 0000000000000001 R09: ffffed107dde49d1
  R10: ffff8883eef24e8b R11: ffff8881002cec20 R12: 1ffff11020059d37
  R13: 00000000003fff7b R14: ffff8881002cec20 R15: dffffc0000000000
  FS:  00007f963f21d940(0000) GS:ffff888458ca6000(0000) knlGS:0000000000000000
  CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
  CR2: 00007f963f5edf71 CR3: 000000010672c000 CR4: 0000000000350ef0
  Call Trace:
   <TASK>
   codetag_trylock_module_list+0xd/0x20
   alloc_tag_top_users+0x369/0x4b0
   __show_mem+0x1cd/0x6e0
   warn_alloc+0x2b1/0x390
   __alloc_frozen_pages_noprof+0x12b9/0x21a0
   alloc_pages_mpol+0x135/0x3e0
   alloc_slab_page+0x82/0xe0
   new_slab+0x212/0x240
   ___slab_alloc+0x82a/0xe00
   </TASK>

As David Wang points out, this issue became easier to trigger after commit
780138b12381 ("alloc_tag: check mem_profiling_support in alloc_tag_init").

Before the commit, the issue occurred only when it failed to allocate and
initialize alloc_tag_cttype or if a memory allocation fails before
alloc_tag_init() is called.  After the commit, it can be easily triggered
when memory profiling is compiled but disabled at boot.

To properly determine whether alloc_tag_init() has been called and its
data structures initialized, verify that alloc_tag_cttype is a valid
pointer before acquiring the semaphore.  If the variable is NULL or an
error value, it has not been properly initialized.  In such a case, just
skip and do not attempt to acquire the semaphore.

[harry.yoo@oracle.com: v3]
  Link: https://lkml.kernel.org/r/20250624072513.84219-1-harry.yoo@oracle.com
Link: https://lkml.kernel.org/r/20250620195305.1115151-1-harry.yoo@oracle.com
Fixes: 780138b12381 ("alloc_tag: check mem_profiling_support in alloc_tag_init")
Fixes: 1438d349d16b ("lib: add memory allocations report in show_mem()")
Signed-off-by: Harry Yoo <harry.yoo@oracle.com>
Reported-by: kernel test robot <oliver.sang@intel.com>
Closes: https://lore.kernel.org/oe-lkp/202506181351.bba867dd-lkp@intel.com
Acked-by: Suren Baghdasaryan <surenb@google.com>
Tested-by: Raghavendra K T <raghavendra.kt@amd.com>
Cc: Casey Chen <cachen@purestorage.com>
Cc: David Wang <00107082@163.com>
Cc: Kent Overstreet <kent.overstreet@linux.dev>
Cc: Yuanyuan Zhong <yzhong@purestorage.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 lib/alloc_tag.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/lib/alloc_tag.c b/lib/alloc_tag.c
index 3a74d63a959e..0142bc916f73 100644
--- a/lib/alloc_tag.c
+++ b/lib/alloc_tag.c
@@ -135,6 +135,9 @@ size_t alloc_tag_top_users(struct codetag_bytes *tags, size_t count, bool can_sl
 	struct codetag_bytes n;
 	unsigned int i, nr = 0;
 
+	if (IS_ERR_OR_NULL(alloc_tag_cttype))
+		return 0;
+
 	if (can_sleep)
 		codetag_lock_module_list(alloc_tag_cttype, true);
 	else if (!codetag_trylock_module_list(alloc_tag_cttype))

From 7627b459aa0737bdd62a8591a1481cda467f20e3 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <florian.fainelli@broadcom.com>
Date: Mon, 23 Jun 2025 09:41:52 -0700
Subject: [PATCH 1277/1334] scripts/gdb: fix interrupts display after MCP on
 x86

The text line would not be appended to as it should have, it should have
been a '+=' but ended up being a '==', fix that.

Link: https://lkml.kernel.org/r/20250623164153.746359-1-florian.fainelli@broadcom.com
Fixes: b0969d7687a7 ("scripts/gdb: print interrupts")
Signed-off-by: Florian Fainelli <florian.fainelli@broadcom.com>
Cc: Jan Kiszka <jan.kiszka@siemens.com>
Cc: Kieran Bingham <kbingham@kernel.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 scripts/gdb/linux/interrupts.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/scripts/gdb/linux/interrupts.py b/scripts/gdb/linux/interrupts.py
index 616a5f26377a..199d9e8193f4 100644
--- a/scripts/gdb/linux/interrupts.py
+++ b/scripts/gdb/linux/interrupts.py
@@ -142,7 +142,7 @@ def x86_show_interupts(prec):
 
     if constants.LX_CONFIG_X86_MCE:
         text += x86_show_mce(prec, "&mce_exception_count", "MCE", "Machine check exceptions")
-        text == x86_show_mce(prec, "&mce_poll_count", "MCP", "Machine check polls")
+        text += x86_show_mce(prec, "&mce_poll_count", "MCP", "Machine check polls")
 
     text += show_irq_err_count(prec)
 

From fea18c686320a53fce7ad62a87a3e1d10ad02f31 Mon Sep 17 00:00:00 2001
From: Alexander Gordeev <agordeev@linux.ibm.com>
Date: Mon, 23 Jun 2025 09:57:21 +0200
Subject: [PATCH 1278/1334] mm/vmalloc: leave lazy MMU mode on PTE mapping
 error

vmap_pages_pte_range() enters the lazy MMU mode, but fails to leave it in
case an error is encountered.

Link: https://lkml.kernel.org/r/20250623075721.2817094-1-agordeev@linux.ibm.com
Fixes: 2ba3e6947aed ("mm/vmalloc: track which page-table levels were modified")
Signed-off-by: Alexander Gordeev <agordeev@linux.ibm.com>
Reported-by: kernel test robot <lkp@intel.com>
Reported-by: Dan Carpenter <dan.carpenter@linaro.org>
Closes: https://lore.kernel.org/r/202506132017.T1l1l6ME-lkp@intel.com/
Reviewed-by: Ryan Roberts <ryan.roberts@arm.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/vmalloc.c | 22 +++++++++++++++-------
 1 file changed, 15 insertions(+), 7 deletions(-)

diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index ab986dd09b6a..6dbcdceecae1 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -514,6 +514,7 @@ static int vmap_pages_pte_range(pmd_t *pmd, unsigned long addr,
 		unsigned long end, pgprot_t prot, struct page **pages, int *nr,
 		pgtbl_mod_mask *mask)
 {
+	int err = 0;
 	pte_t *pte;
 
 	/*
@@ -530,12 +531,18 @@ static int vmap_pages_pte_range(pmd_t *pmd, unsigned long addr,
 	do {
 		struct page *page = pages[*nr];
 
-		if (WARN_ON(!pte_none(ptep_get(pte))))
-			return -EBUSY;
-		if (WARN_ON(!page))
-			return -ENOMEM;
-		if (WARN_ON(!pfn_valid(page_to_pfn(page))))
-			return -EINVAL;
+		if (WARN_ON(!pte_none(ptep_get(pte)))) {
+			err = -EBUSY;
+			break;
+		}
+		if (WARN_ON(!page)) {
+			err = -ENOMEM;
+			break;
+		}
+		if (WARN_ON(!pfn_valid(page_to_pfn(page)))) {
+			err = -EINVAL;
+			break;
+		}
 
 		set_pte_at(&init_mm, addr, pte, mk_pte(page, prot));
 		(*nr)++;
@@ -543,7 +550,8 @@ static int vmap_pages_pte_range(pmd_t *pmd, unsigned long addr,
 
 	arch_leave_lazy_mmu_mode();
 	*mask |= PGTBL_PTE_MODIFIED;
-	return 0;
+
+	return err;
 }
 
 static int vmap_pages_pmd_range(pud_t *pud, unsigned long addr,

From ea9b77f98d94c4d5c1bd1ac1db078f78b40e8bf5 Mon Sep 17 00:00:00 2001
From: Wei Yang <richard.weiyang@gmail.com>
Date: Tue, 24 Jun 2025 15:18:40 -0400
Subject: [PATCH 1279/1334] maple_tree: fix mt_destroy_walk() on root leaf node

On destroy, we should set each node dead.  But current code miss this when
the maple tree has only the root node.

The reason is mt_destroy_walk() leverage mte_destroy_descend() to set node
dead, but this is skipped since the only root node is a leaf.

Fixes this by setting the node dead if it is a leaf.

Link: https://lore.kernel.org/all/20250407231354.11771-1-richard.weiyang@gmail.com/
Link: https://lkml.kernel.org/r/20250624191841.64682-1-Liam.Howlett@oracle.com
Fixes: 54a611b60590 ("Maple Tree: add new data structure")
Signed-off-by: Wei Yang <richard.weiyang@gmail.com>
Signed-off-by: Liam R. Howlett <Liam.Howlett@oracle.com>
Reviewed-by: Dev Jain <dev.jain@arm.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 lib/maple_tree.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/lib/maple_tree.c b/lib/maple_tree.c
index 00524e55a21e..ef66be963798 100644
--- a/lib/maple_tree.c
+++ b/lib/maple_tree.c
@@ -5319,6 +5319,7 @@ static void mt_destroy_walk(struct maple_enode *enode, struct maple_tree *mt,
 	struct maple_enode *start;
 
 	if (mte_is_leaf(enode)) {
+		mte_set_node_dead(enode);
 		node->type = mte_node_type(enode);
 		goto free_leaf;
 	}

From a02b0cde8ee515ee0c8efd33e7fbe6830c282e69 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <florian.fainelli@broadcom.com>
Date: Tue, 24 Jun 2025 19:10:20 -0700
Subject: [PATCH 1280/1334] scripts/gdb: fix interrupts.py after maple tree
 conversion

In commit 721255b9826b ("genirq: Use a maple tree for interrupt descriptor
management"), the irq_desc_tree was replaced with a sparse_irqs tree using
a maple tree structure.  Since the script looked for the irq_desc_tree
symbol which is no longer available, no interrupts would be printed and
the script output would not be useful anymore.

In addition to looking up the correct symbol (sparse_irqs), a new module
(mapletree.py) is added whose mtree_load() implementation is largely
copied after the C version and uses the same variable and intermediate
function names wherever possible to ensure that both the C and Python
version be updated in the future.

This restores the scripts' output to match that of /proc/interrupts.

Link: https://lkml.kernel.org/r/20250625021020.1056930-1-florian.fainelli@broadcom.com
Fixes: 721255b9826b ("genirq: Use a maple tree for interrupt descriptor management")
Signed-off-by: Florian Fainelli <florian.fainelli@broadcom.com>
Cc: Jan Kiszka <jan.kiszka@siemens.com>
Cc: Kieran Bingham <kbingham@kernel.org>
Cc: Shanker Donthineni <sdonthineni@nvidia.com>
Cc: Thomas Gleinxer <tglx@linutronix.de>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 scripts/gdb/linux/constants.py.in |   7 +
 scripts/gdb/linux/interrupts.py   |  12 +-
 scripts/gdb/linux/mapletree.py    | 252 ++++++++++++++++++++++++++++++
 scripts/gdb/linux/xarray.py       |  28 ++++
 4 files changed, 293 insertions(+), 6 deletions(-)
 create mode 100644 scripts/gdb/linux/mapletree.py
 create mode 100644 scripts/gdb/linux/xarray.py

diff --git a/scripts/gdb/linux/constants.py.in b/scripts/gdb/linux/constants.py.in
index fd6bd69c5096..f795302ddfa8 100644
--- a/scripts/gdb/linux/constants.py.in
+++ b/scripts/gdb/linux/constants.py.in
@@ -20,6 +20,7 @@
 #include <linux/of_fdt.h>
 #include <linux/page_ext.h>
 #include <linux/radix-tree.h>
+#include <linux/maple_tree.h>
 #include <linux/slab.h>
 #include <linux/threads.h>
 #include <linux/vmalloc.h>
@@ -93,6 +94,12 @@ LX_GDBPARSED(RADIX_TREE_MAP_SIZE)
 LX_GDBPARSED(RADIX_TREE_MAP_SHIFT)
 LX_GDBPARSED(RADIX_TREE_MAP_MASK)
 
+/* linux/maple_tree.h */
+LX_VALUE(MAPLE_NODE_SLOTS)
+LX_VALUE(MAPLE_RANGE64_SLOTS)
+LX_VALUE(MAPLE_ARANGE64_SLOTS)
+LX_GDBPARSED(MAPLE_NODE_MASK)
+
 /* linux/vmalloc.h */
 LX_VALUE(VM_IOREMAP)
 LX_VALUE(VM_ALLOC)
diff --git a/scripts/gdb/linux/interrupts.py b/scripts/gdb/linux/interrupts.py
index 199d9e8193f4..492d1f1e9529 100644
--- a/scripts/gdb/linux/interrupts.py
+++ b/scripts/gdb/linux/interrupts.py
@@ -7,7 +7,7 @@ import gdb
 from linux import constants
 from linux import cpus
 from linux import utils
-from linux import radixtree
+from linux import mapletree
 
 irq_desc_type = utils.CachedType("struct irq_desc")
 
@@ -23,12 +23,12 @@ def irqd_is_level(desc):
 def show_irq_desc(prec, irq):
     text = ""
 
-    desc = radixtree.lookup(gdb.parse_and_eval("&irq_desc_tree"), irq)
+    desc = mapletree.mtree_load(gdb.parse_and_eval("&sparse_irqs"), irq)
     if desc is None:
         return text
 
-    desc = desc.cast(irq_desc_type.get_type())
-    if desc is None:
+    desc = desc.cast(irq_desc_type.get_type().pointer())
+    if desc == 0:
         return text
 
     if irq_settings_is_hidden(desc):
@@ -221,8 +221,8 @@ class LxInterruptList(gdb.Command):
             gdb.write("CPU%-8d" % cpu)
         gdb.write("\n")
 
-        if utils.gdb_eval_or_none("&irq_desc_tree") is None:
-            return
+        if utils.gdb_eval_or_none("&sparse_irqs") is None:
+            raise gdb.GdbError("Unable to find the sparse IRQ tree, is CONFIG_SPARSE_IRQ enabled?")
 
         for irq in range(nr_irqs):
             gdb.write(show_irq_desc(prec, irq))
diff --git a/scripts/gdb/linux/mapletree.py b/scripts/gdb/linux/mapletree.py
new file mode 100644
index 000000000000..d52d51c0a03f
--- /dev/null
+++ b/scripts/gdb/linux/mapletree.py
@@ -0,0 +1,252 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+#  Maple tree helpers
+#
+# Copyright (c) 2025 Broadcom
+#
+# Authors:
+#  Florian Fainelli <florian.fainelli@broadcom.com>
+
+import gdb
+
+from linux import utils
+from linux import constants
+from linux import xarray
+
+maple_tree_root_type = utils.CachedType("struct maple_tree")
+maple_node_type = utils.CachedType("struct maple_node")
+maple_enode_type = utils.CachedType("void")
+
+maple_dense = 0
+maple_leaf_64 = 1
+maple_range_64 = 2
+maple_arange_64 = 3
+
+class Mas(object):
+    ma_active = 0
+    ma_start = 1
+    ma_root = 2
+    ma_none = 3
+    ma_pause = 4
+    ma_overflow = 5
+    ma_underflow = 6
+    ma_error = 7
+
+    def __init__(self, mt, first, end):
+        if mt.type == maple_tree_root_type.get_type().pointer():
+            self.tree = mt.dereference()
+        elif mt.type != maple_tree_root_type.get_type():
+            raise gdb.GdbError("must be {} not {}"
+                               .format(maple_tree_root_type.get_type().pointer(), mt.type))
+        self.tree = mt
+        self.index = first
+        self.last = end
+        self.node = None
+        self.status = self.ma_start
+        self.min = 0
+        self.max = -1
+
+    def is_start(self):
+        # mas_is_start()
+        return self.status == self.ma_start
+
+    def is_ptr(self):
+        # mas_is_ptr()
+        return self.status == self.ma_root
+
+    def is_none(self):
+        # mas_is_none()
+        return self.status == self.ma_none
+
+    def root(self):
+        # mas_root()
+        return self.tree['ma_root'].cast(maple_enode_type.get_type().pointer())
+
+    def start(self):
+        # mas_start()
+        if self.is_start() is False:
+            return None
+
+        self.min = 0
+        self.max = ~0
+
+        while True:
+            self.depth = 0
+            root = self.root()
+            if xarray.xa_is_node(root):
+                self.depth = 0
+                self.status = self.ma_active
+                self.node = mte_safe_root(root)
+                self.offset = 0
+                if mte_dead_node(self.node) is True:
+                    continue
+
+                return None
+
+            self.node = None
+            # Empty tree
+            if root is None:
+                self.status = self.ma_none
+                self.offset = constants.LX_MAPLE_NODE_SLOTS
+                return None
+
+            # Single entry tree
+            self.status = self.ma_root
+            self.offset = constants.LX_MAPLE_NODE_SLOTS
+
+            if self.index != 0:
+                return None
+
+            return root
+
+        return None
+
+    def reset(self):
+        # mas_reset()
+        self.status = self.ma_start
+        self.node = None
+
+def mte_safe_root(node):
+    if node.type != maple_enode_type.get_type().pointer():
+        raise gdb.GdbError("{} must be {} not {}"
+                           .format(mte_safe_root.__name__, maple_enode_type.get_type().pointer(), node.type))
+    ulong_type = utils.get_ulong_type()
+    indirect_ptr = node.cast(ulong_type) & ~0x2
+    val = indirect_ptr.cast(maple_enode_type.get_type().pointer())
+    return val
+
+def mte_node_type(entry):
+    ulong_type = utils.get_ulong_type()
+    val = None
+    if entry.type == maple_enode_type.get_type().pointer():
+        val = entry.cast(ulong_type)
+    elif entry.type == ulong_type:
+        val = entry
+    else:
+        raise gdb.GdbError("{} must be {} not {}"
+                           .format(mte_node_type.__name__, maple_enode_type.get_type().pointer(), entry.type))
+    return (val >> 0x3) & 0xf
+
+def ma_dead_node(node):
+    if node.type != maple_node_type.get_type().pointer():
+        raise gdb.GdbError("{} must be {} not {}"
+                           .format(ma_dead_node.__name__, maple_node_type.get_type().pointer(), node.type))
+    ulong_type = utils.get_ulong_type()
+    parent = node['parent']
+    indirect_ptr = node['parent'].cast(ulong_type) & ~constants.LX_MAPLE_NODE_MASK
+    return indirect_ptr == node
+
+def mte_to_node(enode):
+    ulong_type = utils.get_ulong_type()
+    if enode.type == maple_enode_type.get_type().pointer():
+        indirect_ptr = enode.cast(ulong_type)
+    elif enode.type == ulong_type:
+        indirect_ptr = enode
+    else:
+        raise gdb.GdbError("{} must be {} not {}"
+                           .format(mte_to_node.__name__, maple_enode_type.get_type().pointer(), enode.type))
+    indirect_ptr = indirect_ptr & ~constants.LX_MAPLE_NODE_MASK
+    return indirect_ptr.cast(maple_node_type.get_type().pointer())
+
+def mte_dead_node(enode):
+    if enode.type != maple_enode_type.get_type().pointer():
+        raise gdb.GdbError("{} must be {} not {}"
+                           .format(mte_dead_node.__name__, maple_enode_type.get_type().pointer(), enode.type))
+    node = mte_to_node(enode)
+    return ma_dead_node(node)
+
+def ma_is_leaf(tp):
+    result = tp < maple_range_64
+    return tp < maple_range_64
+
+def mt_pivots(t):
+    if t == maple_dense:
+        return 0
+    elif t == maple_leaf_64 or t == maple_range_64:
+        return constants.LX_MAPLE_RANGE64_SLOTS - 1
+    elif t == maple_arange_64:
+        return constants.LX_MAPLE_ARANGE64_SLOTS - 1
+
+def ma_pivots(node, t):
+    if node.type != maple_node_type.get_type().pointer():
+        raise gdb.GdbError("{}: must be {} not {}"
+                           .format(ma_pivots.__name__, maple_node_type.get_type().pointer(), node.type))
+    if t == maple_arange_64:
+        return node['ma64']['pivot']
+    elif t == maple_leaf_64 or t == maple_range_64:
+        return node['mr64']['pivot']
+    else:
+        return None
+
+def ma_slots(node, tp):
+    if node.type != maple_node_type.get_type().pointer():
+        raise gdb.GdbError("{}: must be {} not {}"
+                           .format(ma_slots.__name__, maple_node_type.get_type().pointer(), node.type))
+    if tp == maple_arange_64:
+        return node['ma64']['slot']
+    elif tp == maple_range_64 or tp == maple_leaf_64:
+        return node['mr64']['slot']
+    elif tp == maple_dense:
+        return node['slot']
+    else:
+        return None
+
+def mt_slot(mt, slots, offset):
+    ulong_type = utils.get_ulong_type()
+    return slots[offset].cast(ulong_type)
+
+def mtree_lookup_walk(mas):
+    ulong_type = utils.get_ulong_type()
+    n = mas.node
+
+    while True:
+        node = mte_to_node(n)
+        tp = mte_node_type(n)
+        pivots = ma_pivots(node, tp)
+        end = mt_pivots(tp)
+        offset = 0
+        while True:
+            if pivots[offset] >= mas.index:
+                break
+            if offset >= end:
+                break
+            offset += 1
+
+        slots = ma_slots(node, tp)
+        n = mt_slot(mas.tree, slots, offset)
+        if ma_dead_node(node) is True:
+            mas.reset()
+            return None
+            break
+
+        if ma_is_leaf(tp) is True:
+            break
+
+    return n
+
+def mtree_load(mt, index):
+    ulong_type = utils.get_ulong_type()
+    # MT_STATE(...)
+    mas = Mas(mt, index, index)
+    entry = None
+
+    while True:
+        entry = mas.start()
+        if mas.is_none():
+            return None
+
+        if mas.is_ptr():
+            if index != 0:
+                entry = None
+            return entry
+
+        entry = mtree_lookup_walk(mas)
+        if entry is None and mas.is_start():
+            continue
+        else:
+            break
+
+    if xarray.xa_is_zero(entry):
+        return None
+
+    return entry
diff --git a/scripts/gdb/linux/xarray.py b/scripts/gdb/linux/xarray.py
new file mode 100644
index 000000000000..f4477b5def75
--- /dev/null
+++ b/scripts/gdb/linux/xarray.py
@@ -0,0 +1,28 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+#  Xarray helpers
+#
+# Copyright (c) 2025 Broadcom
+#
+# Authors:
+#  Florian Fainelli <florian.fainelli@broadcom.com>
+
+import gdb
+
+from linux import utils
+from linux import constants
+
+def xa_is_internal(entry):
+    ulong_type = utils.get_ulong_type()
+    return ((entry.cast(ulong_type) & 3) == 2)
+
+def xa_mk_internal(v):
+    return ((v << 2) | 2)
+
+def xa_is_zero(entry):
+    ulong_type = utils.get_ulong_type()
+    return entry.cast(ulong_type) == xa_mk_internal(257)
+
+def xa_is_node(entry):
+    ulong_type = utils.get_ulong_type()
+    return xa_is_internal(entry) and (entry.cast(ulong_type) > 4096)

From 50f4d2ba26d5c3a4687ae0569be3bbf1c8f0cbed Mon Sep 17 00:00:00 2001
From: Florian Fainelli <florian.fainelli@broadcom.com>
Date: Mon, 23 Jun 2025 20:00:19 -0700
Subject: [PATCH 1281/1334] scripts/gdb: de-reference per-CPU MCE interrupts

The per-CPU MCE interrupts are looked up by reference and need to be
de-referenced before printing, otherwise we print the addresses of the
variables instead of their contents:

MCE: 18379471554386948492   Machine check exceptions
MCP: 18379471554386948488   Machine check polls

The corrected output looks like this instead now:

MCE:          0   Machine check exceptions
MCP:          1   Machine check polls

Link: https://lkml.kernel.org/r/20250625021109.1057046-1-florian.fainelli@broadcom.com
Link: https://lkml.kernel.org/r/20250624030020.882472-1-florian.fainelli@broadcom.com
Fixes: b0969d7687a7 ("scripts/gdb: print interrupts")
Signed-off-by: Florian Fainelli <florian.fainelli@broadcom.com>
Cc: Jan Kiszka <jan.kiszka@siemens.com>
Cc: Kieran Bingham <kbingham@kernel.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 scripts/gdb/linux/interrupts.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/scripts/gdb/linux/interrupts.py b/scripts/gdb/linux/interrupts.py
index 492d1f1e9529..f4f715a8f0e3 100644
--- a/scripts/gdb/linux/interrupts.py
+++ b/scripts/gdb/linux/interrupts.py
@@ -110,7 +110,7 @@ def x86_show_mce(prec, var, pfx, desc):
     pvar = gdb.parse_and_eval(var)
     text = "%*s: " % (prec, pfx)
     for cpu in cpus.each_online_cpu():
-        text += "%10u " % (cpus.per_cpu(pvar, cpu))
+        text += "%10u " % (cpus.per_cpu(pvar, cpu).dereference())
     text += "  %s\n" % (desc)
     return text
 

From c39b87456411a7e4d97a0f6384ca31f2abb1a4b7 Mon Sep 17 00:00:00 2001
From: Vivek Kasireddy <vivek.kasireddy@intel.com>
Date: Thu, 26 Jun 2025 12:11:16 -0700
Subject: [PATCH 1282/1334] mm/hugetlb: don't crash when allocating a folio if
 there are no resv

There are cases when we try to pin a folio but discover that it has not
been faulted-in.  So, we try to allocate it in memfd_alloc_folio() but
there is a chance that we might encounter a fatal crash/failure
(VM_BUG_ON(!h->resv_huge_pages) in alloc_hugetlb_folio_reserve()) if there
are no active reservations at that instant.  This issue was reported by
syzbot:

kernel BUG at mm/hugetlb.c:2403!
Oops: invalid opcode: 0000 [#1] PREEMPT SMP KASAN NOPTI
CPU: 0 UID: 0 PID: 5315 Comm: syz.0.0 Not tainted
6.13.0-rc5-syzkaller-00161-g63676eefb7a0 #0
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS
1.16.3-debian-1.16.3-2~bpo12+1 04/01/2014
RIP: 0010:alloc_hugetlb_folio_reserve+0xbc/0xc0 mm/hugetlb.c:2403
Code: 1f eb 05 e8 56 18 a0 ff 48 c7 c7 40 56 61 8e e8 ba 21 cc 09 4c 89
f0 5b 41 5c 41 5e 41 5f 5d c3 cc cc cc cc e8 35 18 a0 ff 90 <0f> 0b 66
90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 f3 0f
RSP: 0018:ffffc9000d3d77f8 EFLAGS: 00010087
RAX: ffffffff81ff6beb RBX: 0000000000000000 RCX: 0000000000100000
RDX: ffffc9000e51a000 RSI: 00000000000003ec RDI: 00000000000003ed
RBP: 1ffffffff34810d9 R08: ffffffff81ff6ba3 R09: 1ffffd4000093005
R10: dffffc0000000000 R11: fffff94000093006 R12: dffffc0000000000
R13: dffffc0000000000 R14: ffffea0000498000 R15: ffffffff9a4086c8
FS:  00007f77ac12e6c0(0000) GS:ffff88801fc00000(0000)
knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007f77ab54b170 CR3: 0000000040b70000 CR4: 0000000000352ef0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
 <TASK>
 memfd_alloc_folio+0x1bd/0x370 mm/memfd.c:88
 memfd_pin_folios+0xf10/0x1570 mm/gup.c:3750
 udmabuf_pin_folios drivers/dma-buf/udmabuf.c:346 [inline]
 udmabuf_create+0x70e/0x10c0 drivers/dma-buf/udmabuf.c:443
 udmabuf_ioctl_create drivers/dma-buf/udmabuf.c:495 [inline]
 udmabuf_ioctl+0x301/0x4e0 drivers/dma-buf/udmabuf.c:526
 vfs_ioctl fs/ioctl.c:51 [inline]
 __do_sys_ioctl fs/ioctl.c:906 [inline]
 __se_sys_ioctl+0xf5/0x170 fs/ioctl.c:892
 do_syscall_x64 arch/x86/entry/common.c:52 [inline]
 do_syscall_64+0xf3/0x230 arch/x86/entry/common.c:83
 entry_SYSCALL_64_after_hwframe+0x77/0x7f

Therefore, prevent the above crash by removing the VM_BUG_ON() as there is
no need to crash the system in this situation and instead we could just
fail the allocation request.

Furthermore, as described above, the specific situation where this happens
is when we try to pin memfd folios before they are faulted-in.  Although,
this is a valid thing to do, it is not the regular or the common use-case.
Let us consider the following scenarios:

1) hugetlbfs_file_mmap()
    memfd_alloc_folio()
    hugetlb_fault()

2) memfd_alloc_folio()
    hugetlbfs_file_mmap()
    hugetlb_fault()

3) hugetlbfs_file_mmap()
    hugetlb_fault()
        alloc_hugetlb_folio()

3) is the most common use-case where first a memfd is allocated followed
by mmap(), user writes/updates and then the relevant folios are pinned
(memfd_pin_folios()).  The BUG this patch is fixing occurs in 2) because
we try to pin the folios before hugetlbfs_file_mmap() is called.  So, in
this situation we try to allocate the folios before pinning them but since
we did not make any reservations, resv_huge_pages would be 0, leading to
this issue.

Link: https://lkml.kernel.org/r/20250626191116.1377761-1-vivek.kasireddy@intel.com
Fixes: 26a8ea80929c ("mm/hugetlb: fix memfd_pin_folios resv_huge_pages leak")
Reported-by: syzbot+a504cb5bae4fe117ba94@syzkaller.appspotmail.com
Signed-off-by: Vivek Kasireddy <vivek.kasireddy@intel.com>
Closes: https://syzkaller.appspot.com/bug?extid=a504cb5bae4fe117ba94
Closes: https://lore.kernel.org/all/677928b5.050a0220.3b53b0.004d.GAE@google.com/T/
Acked-by: Oscar Salvador <osalvador@suse.de>
Cc: Steve Sistare <steven.sistare@oracle.com>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: David Hildenbrand <david@redhat.com>
Cc: Anshuman Khandual <anshuman.khandual@arm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/hugetlb.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 9dc95eac558c..a0d285d20992 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -2340,12 +2340,15 @@ struct folio *alloc_hugetlb_folio_reserve(struct hstate *h, int preferred_nid,
 	struct folio *folio;
 
 	spin_lock_irq(&hugetlb_lock);
+	if (!h->resv_huge_pages) {
+		spin_unlock_irq(&hugetlb_lock);
+		return NULL;
+	}
+
 	folio = dequeue_hugetlb_folio_nodemask(h, gfp_mask, preferred_nid,
 					       nmask);
-	if (folio) {
-		VM_BUG_ON(!h->resv_huge_pages);
+	if (folio)
 		h->resv_huge_pages--;
-	}
 
 	spin_unlock_irq(&hugetlb_lock);
 	return folio;

From ddd05742b45b083975a0855ef6ebbf88cf1f532a Mon Sep 17 00:00:00 2001
From: Lance Yang <lance.yang@linux.dev>
Date: Fri, 27 Jun 2025 14:23:19 +0800
Subject: [PATCH 1283/1334] mm/rmap: fix potential out-of-bounds page table
 access during batched unmap

As pointed out by David[1], the batched unmap logic in
try_to_unmap_one() may read past the end of a PTE table when a large
folio's PTE mappings are not fully contained within a single page
table.

While this scenario might be rare, an issue triggerable from userspace
must be fixed regardless of its likelihood.  This patch fixes the
out-of-bounds access by refactoring the logic into a new helper,
folio_unmap_pte_batch().

The new helper correctly calculates the safe batch size by capping the
scan at both the VMA and PMD boundaries.  To simplify the code, it also
supports partial batching (i.e., any number of pages from 1 up to the
calculated safe maximum), as there is no strong reason to special-case
for fully mapped folios.

Link: https://lkml.kernel.org/r/20250701143100.6970-1-lance.yang@linux.dev
Link: https://lkml.kernel.org/r/20250630011305.23754-1-lance.yang@linux.dev
Link: https://lkml.kernel.org/r/20250627062319.84936-1-lance.yang@linux.dev
Link: https://lore.kernel.org/linux-mm/a694398c-9f03-4737-81b9-7e49c857fcbe@redhat.com [1]
Fixes: 354dffd29575 ("mm: support batched unmap for lazyfree large folios during reclamation")
Signed-off-by: Lance Yang <lance.yang@linux.dev>
Suggested-by: David Hildenbrand <david@redhat.com>
Reported-by: David Hildenbrand <david@redhat.com>
Closes: https://lore.kernel.org/linux-mm/a694398c-9f03-4737-81b9-7e49c857fcbe@redhat.com
Suggested-by: Barry Song <baohua@kernel.org>
Acked-by: Barry Song <baohua@kernel.org>
Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Acked-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Harry Yoo <harry.yoo@oracle.com>
Cc: Baolin Wang <baolin.wang@linux.alibaba.com>
Cc: Chris Li <chrisl@kernel.org>
Cc: "Huang, Ying" <huang.ying.caritas@gmail.com>
Cc: Kairui Song <kasong@tencent.com>
Cc: Lance Yang <lance.yang@linux.dev>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Mingzhe Yang <mingzhe.yang@ly.com>
Cc: Rik van Riel <riel@surriel.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Tangquan Zheng <zhengtangquan@oppo.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/rmap.c | 46 ++++++++++++++++++++++++++++------------------
 1 file changed, 28 insertions(+), 18 deletions(-)

diff --git a/mm/rmap.c b/mm/rmap.c
index fb63d9256f09..1320b88fab74 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1845,23 +1845,32 @@ void folio_remove_rmap_pud(struct folio *folio, struct page *page,
 #endif
 }
 
-/* We support batch unmapping of PTEs for lazyfree large folios */
-static inline bool can_batch_unmap_folio_ptes(unsigned long addr,
-			struct folio *folio, pte_t *ptep)
+static inline unsigned int folio_unmap_pte_batch(struct folio *folio,
+			struct page_vma_mapped_walk *pvmw,
+			enum ttu_flags flags, pte_t pte)
 {
 	const fpb_t fpb_flags = FPB_IGNORE_DIRTY | FPB_IGNORE_SOFT_DIRTY;
-	int max_nr = folio_nr_pages(folio);
-	pte_t pte = ptep_get(ptep);
+	unsigned long end_addr, addr = pvmw->address;
+	struct vm_area_struct *vma = pvmw->vma;
+	unsigned int max_nr;
 
+	if (flags & TTU_HWPOISON)
+		return 1;
+	if (!folio_test_large(folio))
+		return 1;
+
+	/* We may only batch within a single VMA and a single page table. */
+	end_addr = pmd_addr_end(addr, vma->vm_end);
+	max_nr = (end_addr - addr) >> PAGE_SHIFT;
+
+	/* We only support lazyfree batching for now ... */
 	if (!folio_test_anon(folio) || folio_test_swapbacked(folio))
-		return false;
+		return 1;
 	if (pte_unused(pte))
-		return false;
-	if (pte_pfn(pte) != folio_pfn(folio))
-		return false;
+		return 1;
 
-	return folio_pte_batch(folio, addr, ptep, pte, max_nr, fpb_flags, NULL,
-			       NULL, NULL) == max_nr;
+	return folio_pte_batch(folio, addr, pvmw->pte, pte, max_nr, fpb_flags,
+			       NULL, NULL, NULL);
 }
 
 /*
@@ -2024,9 +2033,7 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma,
 			if (pte_dirty(pteval))
 				folio_mark_dirty(folio);
 		} else if (likely(pte_present(pteval))) {
-			if (folio_test_large(folio) && !(flags & TTU_HWPOISON) &&
-			    can_batch_unmap_folio_ptes(address, folio, pvmw.pte))
-				nr_pages = folio_nr_pages(folio);
+			nr_pages = folio_unmap_pte_batch(folio, &pvmw, flags, pteval);
 			end_addr = address + nr_pages * PAGE_SIZE;
 			flush_cache_range(vma, address, end_addr);
 
@@ -2206,13 +2213,16 @@ discard:
 			hugetlb_remove_rmap(folio);
 		} else {
 			folio_remove_rmap_ptes(folio, subpage, nr_pages, vma);
-			folio_ref_sub(folio, nr_pages - 1);
 		}
 		if (vma->vm_flags & VM_LOCKED)
 			mlock_drain_local();
-		folio_put(folio);
-		/* We have already batched the entire folio */
-		if (nr_pages > 1)
+		folio_put_refs(folio, nr_pages);
+
+		/*
+		 * If we are sure that we batched the entire folio and cleared
+		 * all PTEs, we can just optimize and stop right here.
+		 */
+		if (nr_pages == folio_nr_pages(folio))
 			goto walk_done;
 		continue;
 walk_abort:

From bb1b5929b4279b136816f95ce1e8f1fa689bf4a1 Mon Sep 17 00:00:00 2001
From: SeongJae Park <sj@kernel.org>
Date: Sun, 29 Jun 2025 13:49:14 -0700
Subject: [PATCH 1284/1334] mm/damon/core: handle damon_call_control as normal
 under kdmond deactivation

DAMON sysfs interface internally uses damon_call() to update DAMON
parameters as users requested, online.  However, DAMON core cancels any
damon_call() requests when it is deactivated by DAMOS watermarks.

As a result, users cannot change DAMON parameters online while DAMON is
deactivated.  Note that users can turn DAMON off and on with different
watermarks to work around.  Since deactivated DAMON is nearly same to
stopped DAMON, the work around should have no big problem.  Anyway, a bug
is a bug.

There is no real good reason to cancel the damon_call() request under
DAMOS deactivation.  Fix it by simply handling the request as normal,
rather than cancelling under the situation.

Link: https://lkml.kernel.org/r/20250629204914.54114-1-sj@kernel.org
Fixes: 42b7491af14c ("mm/damon/core: introduce damon_call()")
Signed-off-by: SeongJae Park <sj@kernel.org>
Cc: <stable@vger.kernel.org>	[6.14+]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/damon/core.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/mm/damon/core.c b/mm/damon/core.c
index b217e0120e09..bc2e58c1222d 100644
--- a/mm/damon/core.c
+++ b/mm/damon/core.c
@@ -2355,9 +2355,8 @@ static void kdamond_usleep(unsigned long usecs)
  *
  * If there is a &struct damon_call_control request that registered via
  * &damon_call() on @ctx, do or cancel the invocation of the function depending
- * on @cancel.  @cancel is set when the kdamond is deactivated by DAMOS
- * watermarks, or the kdamond is already out of the main loop and therefore
- * will be terminated.
+ * on @cancel.  @cancel is set when the kdamond is already out of the main loop
+ * and therefore will be terminated.
  */
 static void kdamond_call(struct damon_ctx *ctx, bool cancel)
 {
@@ -2405,7 +2404,7 @@ static int kdamond_wait_activation(struct damon_ctx *ctx)
 		if (ctx->callback.after_wmarks_check &&
 				ctx->callback.after_wmarks_check(ctx))
 			break;
-		kdamond_call(ctx, true);
+		kdamond_call(ctx, false);
 		damos_walk_cancel(ctx);
 	}
 	return -EBUSY;

From 10d04c26ab2b7da31dd66973f5a09d6fd8ff2a46 Mon Sep 17 00:00:00 2001
From: Christoph Berg <myon@debian.org>
Date: Tue, 24 Jun 2025 16:44:27 +0200
Subject: [PATCH 1285/1334] mm/migrate: fix do_pages_stat in compat mode

For arrays with more than 16 entries, the old code would incorrectly
advance the pages pointer by 16 words instead of 16 compat_uptr_t.  Fix by
doing the pointer arithmetic inside get_compat_pages_array where pages32
is already a correctly-typed pointer.

Discovered while working on PostgreSQL 18's new NUMA introspection code.

Link: https://lkml.kernel.org/r/aGREU0XTB48w9CwN@msg.df7cb.de
Fixes: 5b1b561ba73c ("mm: simplify compat_sys_move_pages")
Signed-off-by: Christoph Berg <myon@debian.org>
Acked-by: David Hildenbrand <david@redhat.com>
Suggested-by: David Hildenbrand <david@redhat.com>
Reported-by: Bertrand Drouvot <bertranddrouvot.pg@gmail.com>
Reported-by: Tomas Vondra <tomas@vondra.me>
Closes: https://www.postgresql.org/message-id/flat/6342f601-77de-4ee0-8c2a-3deb50ceac5b%40vondra.me#86402e3d80c031788f5f55b42c459471
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Byungchul Park <byungchul@sk.com>
Cc: Gregory Price <gourry@gourry.net>
Cc: "Huang, Ying" <ying.huang@linux.alibaba.com>
Cc: Joshua Hahn <joshua.hahnjy@gmail.com>
Cc: Mathew Brost <matthew.brost@intel.com>
Cc: Rakie Kim <rakie.kim@sk.com>
Cc: Zi Yan <ziy@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/migrate.c | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

diff --git a/mm/migrate.c b/mm/migrate.c
index 8cf0f9c9599d..2c88f3b33833 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -2399,6 +2399,7 @@ set_status:
 
 static int get_compat_pages_array(const void __user *chunk_pages[],
 				  const void __user * __user *pages,
+				  unsigned long chunk_offset,
 				  unsigned long chunk_nr)
 {
 	compat_uptr_t __user *pages32 = (compat_uptr_t __user *)pages;
@@ -2406,7 +2407,7 @@ static int get_compat_pages_array(const void __user *chunk_pages[],
 	int i;
 
 	for (i = 0; i < chunk_nr; i++) {
-		if (get_user(p, pages32 + i))
+		if (get_user(p, pages32 + chunk_offset + i))
 			return -EFAULT;
 		chunk_pages[i] = compat_ptr(p);
 	}
@@ -2425,27 +2426,28 @@ static int do_pages_stat(struct mm_struct *mm, unsigned long nr_pages,
 #define DO_PAGES_STAT_CHUNK_NR 16UL
 	const void __user *chunk_pages[DO_PAGES_STAT_CHUNK_NR];
 	int chunk_status[DO_PAGES_STAT_CHUNK_NR];
+	unsigned long chunk_offset = 0;
 
 	while (nr_pages) {
 		unsigned long chunk_nr = min(nr_pages, DO_PAGES_STAT_CHUNK_NR);
 
 		if (in_compat_syscall()) {
 			if (get_compat_pages_array(chunk_pages, pages,
-						   chunk_nr))
+						   chunk_offset, chunk_nr))
 				break;
 		} else {
-			if (copy_from_user(chunk_pages, pages,
+			if (copy_from_user(chunk_pages, pages + chunk_offset,
 				      chunk_nr * sizeof(*chunk_pages)))
 				break;
 		}
 
 		do_pages_stat_array(mm, chunk_nr, chunk_pages, chunk_status);
 
-		if (copy_to_user(status, chunk_status, chunk_nr * sizeof(*status)))
+		if (copy_to_user(status + chunk_offset, chunk_status,
+				 chunk_nr * sizeof(*status)))
 			break;
 
-		pages += chunk_nr;
-		status += chunk_nr;
+		chunk_offset += chunk_nr;
 		nr_pages -= chunk_nr;
 	}
 	return nr_pages ? -EFAULT : 0;

From e6d3e653b084f003977bf2e33820cb84d2e4541f Mon Sep 17 00:00:00 2001
From: Illia Ostapyshyn <illia@yshyn.com>
Date: Sun, 29 Jun 2025 02:38:11 +0200
Subject: [PATCH 1286/1334] scripts: gdb: vfs: support external dentry names

d_shortname of struct dentry only reserves D_NAME_INLINE_LEN characters
and contains garbage for longer names.  Use d_name instead, which always
references the valid name.

Link: https://lore.kernel.org/all/20250525213709.878287-2-illia@yshyn.com/
Link: https://lkml.kernel.org/r/20250629003811.2420418-1-illia@yshyn.com
Fixes: 79300ac805b6 ("scripts/gdb: fix dentry_name() lookup")
Signed-off-by: Illia Ostapyshyn <illia@yshyn.com>
Tested-by: Florian Fainelli <florian.fainelli@broadcom.com>
Reviewed-by: Florian Fainelli <florian.fainelli@broadcom.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Jan Kara <jack@suse.cz>
Cc: Jan Kiszka <jan.kiszka@siemens.com>
Cc: Kieran Bingham <kbingham@kernel.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 scripts/gdb/linux/vfs.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/scripts/gdb/linux/vfs.py b/scripts/gdb/linux/vfs.py
index b5fbb18ccb77..9e921b645a68 100644
--- a/scripts/gdb/linux/vfs.py
+++ b/scripts/gdb/linux/vfs.py
@@ -22,7 +22,7 @@ def dentry_name(d):
     if parent == d or parent == 0:
         return ""
     p = dentry_name(d['d_parent']) + "/"
-    return p + d['d_shortname']['string'].string()
+    return p + d['d_name']['name'].string()
 
 class DentryName(gdb.Function):
     """Return string of the full path of a dentry.

From 6ee9b3d84775944fb8c8a447961cd01274ac671c Mon Sep 17 00:00:00 2001
From: Yeoreum Yun <yeoreum.yun@arm.com>
Date: Thu, 3 Jul 2025 19:10:18 +0100
Subject: [PATCH 1287/1334] kasan: remove kasan_find_vm_area() to prevent
 possible deadlock

find_vm_area() couldn't be called in atomic_context.  If find_vm_area() is
called to reports vm area information, kasan can trigger deadlock like:

CPU0                                CPU1
vmalloc();
 alloc_vmap_area();
  spin_lock(&vn->busy.lock)
                                    spin_lock_bh(&some_lock);
   <interrupt occurs>
   <in softirq>
   spin_lock(&some_lock);
                                    <access invalid address>
                                    kasan_report();
                                     print_report();
                                      print_address_description();
                                       kasan_find_vm_area();
                                        find_vm_area();
                                         spin_lock(&vn->busy.lock) // deadlock!

To prevent possible deadlock while kasan reports, remove kasan_find_vm_area().

Link: https://lkml.kernel.org/r/20250703181018.580833-1-yeoreum.yun@arm.com
Fixes: c056a364e954 ("kasan: print virtual mapping info in reports")
Signed-off-by: Yeoreum Yun <yeoreum.yun@arm.com>
Reported-by: Yunseong Kim <ysk@kzalloc.com>
Reviewed-by: Andrey Ryabinin <ryabinin.a.a@gmail.com>
Cc: Alexander Potapenko <glider@google.com>
Cc: Andrey Konovalov <andreyknvl@gmail.com>
Cc: Byungchul Park <byungchul@sk.com>
Cc: Dmitriy Vyukov <dvyukov@google.com>
Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Vincenzo Frascino <vincenzo.frascino@arm.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/kasan/report.c | 45 ++-------------------------------------------
 1 file changed, 2 insertions(+), 43 deletions(-)

diff --git a/mm/kasan/report.c b/mm/kasan/report.c
index 8357e1a33699..b0877035491f 100644
--- a/mm/kasan/report.c
+++ b/mm/kasan/report.c
@@ -370,36 +370,6 @@ static inline bool init_task_stack_addr(const void *addr)
 			sizeof(init_thread_union.stack));
 }
 
-/*
- * This function is invoked with report_lock (a raw_spinlock) held. A
- * PREEMPT_RT kernel cannot call find_vm_area() as it will acquire a sleeping
- * rt_spinlock.
- *
- * For !RT kernel, the PROVE_RAW_LOCK_NESTING config option will print a
- * lockdep warning for this raw_spinlock -> spinlock dependency. This config
- * option is enabled by default to ensure better test coverage to expose this
- * kind of RT kernel problem. This lockdep splat, however, can be suppressed
- * by using DEFINE_WAIT_OVERRIDE_MAP() if it serves a useful purpose and the
- * invalid PREEMPT_RT case has been taken care of.
- */
-static inline struct vm_struct *kasan_find_vm_area(void *addr)
-{
-	static DEFINE_WAIT_OVERRIDE_MAP(vmalloc_map, LD_WAIT_SLEEP);
-	struct vm_struct *va;
-
-	if (IS_ENABLED(CONFIG_PREEMPT_RT))
-		return NULL;
-
-	/*
-	 * Suppress lockdep warning and fetch vmalloc area of the
-	 * offending address.
-	 */
-	lock_map_acquire_try(&vmalloc_map);
-	va = find_vm_area(addr);
-	lock_map_release(&vmalloc_map);
-	return va;
-}
-
 static void print_address_description(void *addr, u8 tag,
 				      struct kasan_report_info *info)
 {
@@ -429,19 +399,8 @@ static void print_address_description(void *addr, u8 tag,
 	}
 
 	if (is_vmalloc_addr(addr)) {
-		struct vm_struct *va = kasan_find_vm_area(addr);
-
-		if (va) {
-			pr_err("The buggy address belongs to the virtual mapping at\n"
-			       " [%px, %px) created by:\n"
-			       " %pS\n",
-			       va->addr, va->addr + va->size, va->caller);
-			pr_err("\n");
-
-			page = vmalloc_to_page(addr);
-		} else {
-			pr_err("The buggy address %px belongs to a vmalloc virtual mapping\n", addr);
-		}
+		pr_err("The buggy address %px belongs to a vmalloc virtual mapping\n", addr);
+		page = vmalloc_to_page(addr);
 	}
 
 	if (page) {

From d9e01c62b7a0c258a7481c083f84c766a8f5597c Mon Sep 17 00:00:00 2001
From: Honggyu Kim <honggyu.kim@sk.com>
Date: Wed, 2 Jul 2025 09:02:01 +0900
Subject: [PATCH 1288/1334] samples/damon: fix damon sample prcl for start
 failure

Patch series "mm/damon: fix divide by zero and its samples", v3.

This series includes fixes against damon and its samples to make it safer
when damon sample starting fails.

It includes the following changes.
- fix unexpected divide by zero crash for zero size regions
- fix bugs for damon samples in case of start failures


This patch (of 4):

The damon_sample_prcl_start() can fail so we must reset the "enable"
parameter to "false" again for proper rollback.

In such cases, setting Y to "enable" then N triggers the following crash
because damon sample start failed but the "enable" stays as Y.

  [ 2441.419649] damon_sample_prcl: start
  [ 2454.146817] damon_sample_prcl: stop
  [ 2454.146862] ------------[ cut here ]------------
  [ 2454.146865] kernel BUG at mm/slub.c:546!
  [ 2454.148183] Oops: invalid opcode: 0000 [#1] SMP NOPTI
  	...
  [ 2454.167555] Call Trace:
  [ 2454.167822]  <TASK>
  [ 2454.168061]  damon_destroy_ctx+0x78/0x140
  [ 2454.168454]  damon_sample_prcl_enable_store+0x8d/0xd0
  [ 2454.168932]  param_attr_store+0xa1/0x120
  [ 2454.169315]  module_attr_store+0x20/0x50
  [ 2454.169695]  sysfs_kf_write+0x72/0x90
  [ 2454.170065]  kernfs_fop_write_iter+0x150/0x1e0
  [ 2454.170491]  vfs_write+0x315/0x440
  [ 2454.170833]  ksys_write+0x69/0xf0
  [ 2454.171162]  __x64_sys_write+0x19/0x30
  [ 2454.171525]  x64_sys_call+0x18b2/0x2700
  [ 2454.171900]  do_syscall_64+0x7f/0x680
  [ 2454.172258]  ? exit_to_user_mode_loop+0xf6/0x180
  [ 2454.172694]  ? clear_bhb_loop+0x30/0x80
  [ 2454.173067]  ? clear_bhb_loop+0x30/0x80
  [ 2454.173439]  entry_SYSCALL_64_after_hwframe+0x76/0x7e

Link: https://lkml.kernel.org/r/20250702000205.1921-1-honggyu.kim@sk.com
Link: https://lkml.kernel.org/r/20250702000205.1921-2-honggyu.kim@sk.com
Fixes: 2aca254620a8 ("samples/damon: introduce a skeleton of a smaple DAMON module for proactive reclamation")
Signed-off-by: Honggyu Kim <honggyu.kim@sk.com>
Reviewed-by: SeongJae Park <sj@kernel.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 samples/damon/prcl.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/samples/damon/prcl.c b/samples/damon/prcl.c
index 056b1b21a0fe..5597e6a08ab2 100644
--- a/samples/damon/prcl.c
+++ b/samples/damon/prcl.c
@@ -122,8 +122,12 @@ static int damon_sample_prcl_enable_store(
 	if (enable == enabled)
 		return 0;
 
-	if (enable)
-		return damon_sample_prcl_start();
+	if (enable) {
+		err = damon_sample_prcl_start();
+		if (err)
+			enable = false;
+		return err;
+	}
 	damon_sample_prcl_stop();
 	return 0;
 }

From f1221c8442616a6927aff836327777144545cb29 Mon Sep 17 00:00:00 2001
From: Honggyu Kim <honggyu.kim@sk.com>
Date: Wed, 2 Jul 2025 09:02:02 +0900
Subject: [PATCH 1289/1334] samples/damon: fix damon sample wsse for start
 failure

The damon_sample_wsse_start() can fail so we must reset the "enable"
parameter to "false" again for proper rollback.

In such cases, setting Y to "enable" then N triggers the similar crash
with wsse because damon sample start failed but the "enable" stays as Y.

Link: https://lkml.kernel.org/r/20250702000205.1921-3-honggyu.kim@sk.com
Fixes: b757c6cfc696 ("samples/damon/wsse: start and stop DAMON as the user requests")
Signed-off-by: Honggyu Kim <honggyu.kim@sk.com>
Reviewed-by: SeongJae Park <sj@kernel.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 samples/damon/wsse.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/samples/damon/wsse.c b/samples/damon/wsse.c
index 11be25803274..e20238a249e7 100644
--- a/samples/damon/wsse.c
+++ b/samples/damon/wsse.c
@@ -102,8 +102,12 @@ static int damon_sample_wsse_enable_store(
 	if (enable == enabled)
 		return 0;
 
-	if (enable)
-		return damon_sample_wsse_start();
+	if (enable) {
+		err = damon_sample_wsse_start();
+		if (err)
+			enable = false;
+		return err;
+	}
 	damon_sample_wsse_stop();
 	return 0;
 }

From ddba1b6cf4791824f8b614ff8878353a6c6f79f5 Mon Sep 17 00:00:00 2001
From: Honggyu Kim <honggyu.kim@sk.com>
Date: Wed, 2 Jul 2025 09:02:03 +0900
Subject: [PATCH 1290/1334] samples/damon: fix damon sample mtier for start
 failure

The damon_sample_mtier_start() can fail so we must reset the "enable"
parameter to "false" again for proper rollback.

In such cases, setting Y to "enable" then N triggers the similar crash
with mtier because damon sample start failed but the "enable" stays as Y.

Link: https://lkml.kernel.org/r/20250702000205.1921-4-honggyu.kim@sk.com
Fixes: 82a08bde3cf7 ("samples/damon: implement a DAMON module for memory tiering")
Signed-off-by: Honggyu Kim <honggyu.kim@sk.com>
Reviewed-by: SeongJae Park <sj@kernel.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 samples/damon/mtier.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/samples/damon/mtier.c b/samples/damon/mtier.c
index 36d2cd933f5a..c94254b77fc9 100644
--- a/samples/damon/mtier.c
+++ b/samples/damon/mtier.c
@@ -164,8 +164,12 @@ static int damon_sample_mtier_enable_store(
 	if (enable == enabled)
 		return 0;
 
-	if (enable)
-		return damon_sample_mtier_start();
+	if (enable) {
+		err = damon_sample_mtier_start();
+		if (err)
+			enable = false;
+		return err;
+	}
 	damon_sample_mtier_stop();
 	return 0;
 }

From bd225b9591442065beb876da72656f4a2d627d03 Mon Sep 17 00:00:00 2001
From: Honggyu Kim <honggyu.kim@sk.com>
Date: Wed, 2 Jul 2025 09:02:04 +0900
Subject: [PATCH 1291/1334] mm/damon: fix divide by zero in
 damon_get_intervals_score()

The current implementation allows having zero size regions with no special
reasons, but damon_get_intervals_score() gets crashed by divide by zero
when the region size is zero.

  [   29.403950] Oops: divide error: 0000 [#1] SMP NOPTI

This patch fixes the bug, but does not disallow zero size regions to keep
the backward compatibility since disallowing zero size regions might be a
breaking change for some users.

In addition, the same crash can happen when intervals_goal.access_bp is
zero so this should be fixed in stable trees as well.

Link: https://lkml.kernel.org/r/20250702000205.1921-5-honggyu.kim@sk.com
Fixes: f04b0fedbe71 ("mm/damon/core: implement intervals auto-tuning")
Signed-off-by: Honggyu Kim <honggyu.kim@sk.com>
Reviewed-by: SeongJae Park <sj@kernel.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/damon/core.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/mm/damon/core.c b/mm/damon/core.c
index bc2e58c1222d..979b29e16ef4 100644
--- a/mm/damon/core.c
+++ b/mm/damon/core.c
@@ -1449,6 +1449,7 @@ static unsigned long damon_get_intervals_score(struct damon_ctx *c)
 		}
 	}
 	target_access_events = max_access_events * goal_bp / 10000;
+	target_access_events = target_access_events ? : 1;
 	return access_events * 10000 / target_access_events;
 }
 

From 82241a83cd15aaaf28200a40ad1a8b480012edaf Mon Sep 17 00:00:00 2001
From: Baolin Wang <baolin.wang@linux.alibaba.com>
Date: Thu, 5 Jun 2025 20:58:29 +0800
Subject: [PATCH 1292/1334] mm: fix the inaccurate memory statistics issue for
 users

On some large machines with a high number of CPUs running a 64K pagesize
kernel, we found that the 'RES' field is always 0 displayed by the top
command for some processes, which will cause a lot of confusion for users.

    PID USER      PR  NI    VIRT    RES    SHR S  %CPU  %MEM     TIME+ COMMAND
 875525 root      20   0   12480      0      0 R   0.3   0.0   0:00.08 top
      1 root      20   0  172800      0      0 S   0.0   0.0   0:04.52 systemd

The main reason is that the batch size of the percpu counter is quite
large on these machines, caching a significant percpu value, since
converting mm's rss stats into percpu_counter by commit f1a7941243c1 ("mm:
convert mm's rss stats into percpu_counter").  Intuitively, the batch
number should be optimized, but on some paths, performance may take
precedence over statistical accuracy.  Therefore, introducing a new
interface to add the percpu statistical count and display it to users,
which can remove the confusion.  In addition, this change is not expected
to be on a performance-critical path, so the modification should be
acceptable.

In addition, the 'mm->rss_stat' is updated by using add_mm_counter() and
dec/inc_mm_counter(), which are all wrappers around
percpu_counter_add_batch().  In percpu_counter_add_batch(), there is
percpu batch caching to avoid 'fbc->lock' contention.  This patch changes
task_mem() and task_statm() to get the accurate mm counters under the
'fbc->lock', but this should not exacerbate kernel 'mm->rss_stat' lock
contention due to the percpu batch caching of the mm counters.  The
following test also confirm the theoretical analysis.

I run the stress-ng that stresses anon page faults in 32 threads on my 32
cores machine, while simultaneously running a script that starts 32
threads to busy-loop pread each stress-ng thread's /proc/pid/status
interface.  From the following data, I did not observe any obvious impact
of this patch on the stress-ng tests.

w/o patch:
stress-ng: info:  [6848]          4,399,219,085,152 CPU Cycles          67.327 B/sec
stress-ng: info:  [6848]          1,616,524,844,832 Instructions          24.740 B/sec (0.367 instr. per cycle)
stress-ng: info:  [6848]          39,529,792 Page Faults Total           0.605 M/sec
stress-ng: info:  [6848]          39,529,792 Page Faults Minor           0.605 M/sec

w/patch:
stress-ng: info:  [2485]          4,462,440,381,856 CPU Cycles          68.382 B/sec
stress-ng: info:  [2485]          1,615,101,503,296 Instructions          24.750 B/sec (0.362 instr. per cycle)
stress-ng: info:  [2485]          39,439,232 Page Faults Total           0.604 M/sec
stress-ng: info:  [2485]          39,439,232 Page Faults Minor           0.604 M/sec

On comparing a very simple app which just allocates & touches some
memory against v6.1 (which doesn't have f1a7941243c1) and latest Linus
tree (4c06e63b9203) I can see that on latest Linus tree the values for
VmRSS, RssAnon and RssFile from /proc/self/status are all zeroes while
they do report values on v6.1 and a Linus tree with this patch.

Link: https://lkml.kernel.org/r/f4586b17f66f97c174f7fd1f8647374fdb53de1c.1749119050.git.baolin.wang@linux.alibaba.com
Fixes: f1a7941243c1 ("mm: convert mm's rss stats into percpu_counter")
Signed-off-by: Baolin Wang <baolin.wang@linux.alibaba.com>
Reviewed-by: Aboorva Devarajan <aboorvad@linux.ibm.com>
Tested-by: Aboorva Devarajan <aboorvad@linux.ibm.com>
Tested-by Donet Tom <donettom@linux.ibm.com>
Acked-by: Shakeel Butt <shakeel.butt@linux.dev>
Acked-by: SeongJae Park <sj@kernel.org>
Acked-by: Michal Hocko <mhocko@suse.com>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Cc: David Hildenbrand <david@redhat.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 fs/proc/task_mmu.c | 14 +++++++-------
 include/linux/mm.h |  5 +++++
 2 files changed, 12 insertions(+), 7 deletions(-)

diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 4be91eb6ea5c..751479eb128f 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -36,9 +36,9 @@ void task_mem(struct seq_file *m, struct mm_struct *mm)
 	unsigned long text, lib, swap, anon, file, shmem;
 	unsigned long hiwater_vm, total_vm, hiwater_rss, total_rss;
 
-	anon = get_mm_counter(mm, MM_ANONPAGES);
-	file = get_mm_counter(mm, MM_FILEPAGES);
-	shmem = get_mm_counter(mm, MM_SHMEMPAGES);
+	anon = get_mm_counter_sum(mm, MM_ANONPAGES);
+	file = get_mm_counter_sum(mm, MM_FILEPAGES);
+	shmem = get_mm_counter_sum(mm, MM_SHMEMPAGES);
 
 	/*
 	 * Note: to minimize their overhead, mm maintains hiwater_vm and
@@ -59,7 +59,7 @@ void task_mem(struct seq_file *m, struct mm_struct *mm)
 	text = min(text, mm->exec_vm << PAGE_SHIFT);
 	lib = (mm->exec_vm << PAGE_SHIFT) - text;
 
-	swap = get_mm_counter(mm, MM_SWAPENTS);
+	swap = get_mm_counter_sum(mm, MM_SWAPENTS);
 	SEQ_PUT_DEC("VmPeak:\t", hiwater_vm);
 	SEQ_PUT_DEC(" kB\nVmSize:\t", total_vm);
 	SEQ_PUT_DEC(" kB\nVmLck:\t", mm->locked_vm);
@@ -92,12 +92,12 @@ unsigned long task_statm(struct mm_struct *mm,
 			 unsigned long *shared, unsigned long *text,
 			 unsigned long *data, unsigned long *resident)
 {
-	*shared = get_mm_counter(mm, MM_FILEPAGES) +
-			get_mm_counter(mm, MM_SHMEMPAGES);
+	*shared = get_mm_counter_sum(mm, MM_FILEPAGES) +
+			get_mm_counter_sum(mm, MM_SHMEMPAGES);
 	*text = (PAGE_ALIGN(mm->end_code) - (mm->start_code & PAGE_MASK))
 								>> PAGE_SHIFT;
 	*data = mm->data_vm + mm->stack_vm;
-	*resident = *shared + get_mm_counter(mm, MM_ANONPAGES);
+	*resident = *shared + get_mm_counter_sum(mm, MM_ANONPAGES);
 	return mm->total_vm;
 }
 
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 0ef2ba0c667a..fa538feaa8d9 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2568,6 +2568,11 @@ static inline unsigned long get_mm_counter(struct mm_struct *mm, int member)
 	return percpu_counter_read_positive(&mm->rss_stat[member]);
 }
 
+static inline unsigned long get_mm_counter_sum(struct mm_struct *mm, int member)
+{
+	return percpu_counter_sum_positive(&mm->rss_stat[member]);
+}
+
 void mm_trace_rss_stat(struct mm_struct *mm, int member);
 
 static inline void add_mm_counter(struct mm_struct *mm, int member, long value)

From db6cc3f4ac2e6cdc898fc9cbc8b32ae1bf56bdad Mon Sep 17 00:00:00 2001
From: Chen Yu <yu.c.chen@intel.com>
Date: Fri, 4 Jul 2025 21:56:20 +0800
Subject: [PATCH 1293/1334] Revert "sched/numa: add statistics of numa balance
 task"

This reverts commit ad6b26b6a0a79166b53209df2ca1cf8636296382.

This commit introduces per-memcg/task NUMA balance statistics, but
unfortunately it introduced a NULL pointer exception due to the following
race condition: After a swap task candidate was chosen, its mm_struct
pointer was set to NULL due to task exit.  Later, when performing the
actual task swapping, the p->mm caused the problem.

CPU0                                   CPU1
:
...
task_numa_migrate
     task_numa_find_cpu
      task_numa_compare
        # a normal task p is chosen
        env->best_task = p

                                          # p exit:
                                          exit_signals(p);
                                             p->flags |= PF_EXITING
                                          exit_mm
                                             p->mm = NULL;

      migrate_swap_stop
        __migrate_swap_task((arg->src_task, arg->dst_cpu)
         count_memcg_event_mm(p->mm, NUMA_TASK_SWAP)# p->mm is NULL

task_lock() should be held and the PF_EXITING flag needs to be checked to
prevent this from happening.  After discussion, the conclusion was that
adding a lock is not worthwhile for some statistics calculations.  Revert
the change and rely on the tracepoint for this purpose.

Link: https://lkml.kernel.org/r/20250704135620.685752-1-yu.c.chen@intel.com
Link: https://lkml.kernel.org/r/20250708064917.BBD13C4CEED@smtp.kernel.org
Fixes: ad6b26b6a0a7 ("sched/numa: add statistics of numa balance task")
Signed-off-by: Chen Yu <yu.c.chen@intel.com>
Reported-by: Jirka Hladky <jhladky@redhat.com>
Closes: https://lore.kernel.org/all/CAE4VaGBLJxpd=NeRJXpSCuw=REhC5LWJpC29kDy-Zh2ZDyzQZA@mail.gmail.com/
Reported-by: Srikanth Aithal <Srikanth.Aithal@amd.com>
Reported-by: Suneeth D <Suneeth.D@amd.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Hladky <jhladky@redhat.com>
Cc: Libo Chen <libo.chen@oracle.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 Documentation/admin-guide/cgroup-v2.rst | 6 ------
 include/linux/sched.h                   | 4 ----
 include/linux/vm_event_item.h           | 2 --
 kernel/sched/core.c                     | 9 ++-------
 kernel/sched/debug.c                    | 4 ----
 mm/memcontrol.c                         | 2 --
 mm/vmstat.c                             | 2 --
 7 files changed, 2 insertions(+), 27 deletions(-)

diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst
index 0cc35a14afbe..bd98ea3175ec 100644
--- a/Documentation/admin-guide/cgroup-v2.rst
+++ b/Documentation/admin-guide/cgroup-v2.rst
@@ -1732,12 +1732,6 @@ The following nested keys are defined.
 	  numa_hint_faults (npn)
 		Number of NUMA hinting faults.
 
-	  numa_task_migrated (npn)
-		Number of task migration by NUMA balancing.
-
-	  numa_task_swapped (npn)
-		Number of task swap by NUMA balancing.
-
 	  pgdemote_kswapd
 		Number of pages demoted by kswapd.
 
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 4f78a64beb52..aa9c5be7a632 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -548,10 +548,6 @@ struct sched_statistics {
 	u64				nr_failed_migrations_running;
 	u64				nr_failed_migrations_hot;
 	u64				nr_forced_migrations;
-#ifdef CONFIG_NUMA_BALANCING
-	u64				numa_task_migrated;
-	u64				numa_task_swapped;
-#endif
 
 	u64				nr_wakeups;
 	u64				nr_wakeups_sync;
diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h
index 91a3ce9a2687..9e15a088ba38 100644
--- a/include/linux/vm_event_item.h
+++ b/include/linux/vm_event_item.h
@@ -66,8 +66,6 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
 		NUMA_HINT_FAULTS,
 		NUMA_HINT_FAULTS_LOCAL,
 		NUMA_PAGE_MIGRATE,
-		NUMA_TASK_MIGRATE,
-		NUMA_TASK_SWAP,
 #endif
 #ifdef CONFIG_MIGRATION
 		PGMIGRATE_SUCCESS, PGMIGRATE_FAIL,
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index ec68fc686bd7..81c6df746df1 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3362,10 +3362,6 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
 #ifdef CONFIG_NUMA_BALANCING
 static void __migrate_swap_task(struct task_struct *p, int cpu)
 {
-	__schedstat_inc(p->stats.numa_task_swapped);
-	count_vm_numa_event(NUMA_TASK_SWAP);
-	count_memcg_event_mm(p->mm, NUMA_TASK_SWAP);
-
 	if (task_on_rq_queued(p)) {
 		struct rq *src_rq, *dst_rq;
 		struct rq_flags srf, drf;
@@ -7939,9 +7935,8 @@ int migrate_task_to(struct task_struct *p, int target_cpu)
 	if (!cpumask_test_cpu(target_cpu, p->cpus_ptr))
 		return -EINVAL;
 
-	__schedstat_inc(p->stats.numa_task_migrated);
-	count_vm_numa_event(NUMA_TASK_MIGRATE);
-	count_memcg_event_mm(p->mm, NUMA_TASK_MIGRATE);
+	/* TODO: This is not properly updating schedstats */
+
 	trace_sched_move_numa(p, curr_cpu, target_cpu);
 	return stop_one_cpu(curr_cpu, migration_cpu_stop, &arg);
 }
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 9d71baf08075..557246880a7e 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -1210,10 +1210,6 @@ void proc_sched_show_task(struct task_struct *p, struct pid_namespace *ns,
 		P_SCHEDSTAT(nr_failed_migrations_running);
 		P_SCHEDSTAT(nr_failed_migrations_hot);
 		P_SCHEDSTAT(nr_forced_migrations);
-#ifdef CONFIG_NUMA_BALANCING
-		P_SCHEDSTAT(numa_task_migrated);
-		P_SCHEDSTAT(numa_task_swapped);
-#endif
 		P_SCHEDSTAT(nr_wakeups);
 		P_SCHEDSTAT(nr_wakeups_sync);
 		P_SCHEDSTAT(nr_wakeups_migrate);
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 902da8a9c643..70fdeda1120b 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -474,8 +474,6 @@ static const unsigned int memcg_vm_event_stat[] = {
 	NUMA_PAGE_MIGRATE,
 	NUMA_PTE_UPDATES,
 	NUMA_HINT_FAULTS,
-	NUMA_TASK_MIGRATE,
-	NUMA_TASK_SWAP,
 #endif
 };
 
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 429ae5339bfe..a78d70ddeacd 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1346,8 +1346,6 @@ const char * const vmstat_text[] = {
 	"numa_hint_faults",
 	"numa_hint_faults_local",
 	"numa_pages_migrated",
-	"numa_task_migrated",
-	"numa_task_swapped",
 #endif
 #ifdef CONFIG_MIGRATION
 	"pgmigrate_success",

From d53238b614e01266a3d36b417b60a502e0698504 Mon Sep 17 00:00:00 2001
From: Chao Yu <chao@kernel.org>
Date: Mon, 7 Jul 2025 16:48:32 +0800
Subject: [PATCH 1294/1334] erofs: fix to add missing tracepoint in
 erofs_readahead()

Commit 771c994ea51f ("erofs: convert all uncompressed cases to iomap")
converts to use iomap interface, it removed trace_erofs_readahead()
tracepoint in the meantime, let's add it back.

Fixes: 771c994ea51f ("erofs: convert all uncompressed cases to iomap")
Signed-off-by: Chao Yu <chao@kernel.org>
Reviewed-by: Gao Xiang <hsiangkao@linux.alibaba.com>
Link: https://lore.kernel.org/r/20250707084832.2725677-1-chao@kernel.org
Signed-off-by: Gao Xiang <hsiangkao@linux.alibaba.com>
---
 fs/erofs/data.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/fs/erofs/data.c b/fs/erofs/data.c
index 6a329c329f43..534ac359976e 100644
--- a/fs/erofs/data.c
+++ b/fs/erofs/data.c
@@ -356,6 +356,9 @@ static int erofs_read_folio(struct file *file, struct folio *folio)
 
 static void erofs_readahead(struct readahead_control *rac)
 {
+	trace_erofs_readahead(rac->mapping->host, readahead_index(rac),
+					readahead_count(rac), true);
+
 	return iomap_readahead(rac, &erofs_iomap_ops);
 }
 

From 99f7619a77a0a2e3e2bcae676d0f301769167754 Mon Sep 17 00:00:00 2001
From: Chao Yu <chao@kernel.org>
Date: Tue, 8 Jul 2025 19:19:42 +0800
Subject: [PATCH 1295/1334] erofs: fix to add missing tracepoint in
 erofs_read_folio()

Commit 771c994ea51f ("erofs: convert all uncompressed cases to iomap")
converts to use iomap interface, it removed trace_erofs_readpage()
tracepoint in the meantime, let's add it back.

Fixes: 771c994ea51f ("erofs: convert all uncompressed cases to iomap")
Signed-off-by: Chao Yu <chao@kernel.org>
Reviewed-by: Gao Xiang <hsiangkao@linux.alibaba.com>
Link: https://lore.kernel.org/r/20250708111942.3120926-1-chao@kernel.org
Signed-off-by: Gao Xiang <hsiangkao@linux.alibaba.com>
---
 fs/erofs/data.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/fs/erofs/data.c b/fs/erofs/data.c
index 534ac359976e..221e0ff1ed0d 100644
--- a/fs/erofs/data.c
+++ b/fs/erofs/data.c
@@ -351,6 +351,8 @@ int erofs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
  */
 static int erofs_read_folio(struct file *file, struct folio *folio)
 {
+	trace_erofs_read_folio(folio, true);
+
 	return iomap_read_folio(folio, &erofs_iomap_ops);
 }
 

From f5443d0d1ad775927f1473b1c256ef68f2515b9c Mon Sep 17 00:00:00 2001
From: Gao Xiang <hsiangkao@linux.alibaba.com>
Date: Wed, 9 Jul 2025 11:46:13 +0800
Subject: [PATCH 1296/1334] erofs: use memcpy_to_folio() to replace
 copy_to_iter()

Using copy_to_iter() here is overkill and even messy.

Signed-off-by: Gao Xiang <hsiangkao@linux.alibaba.com>
Link: https://lore.kernel.org/r/20250709034614.2780117-1-hsiangkao@linux.alibaba.com
---
 fs/erofs/fileio.c | 10 +---------
 1 file changed, 1 insertion(+), 9 deletions(-)

diff --git a/fs/erofs/fileio.c b/fs/erofs/fileio.c
index df5cc63f2c01..fe2cd2982b4b 100644
--- a/fs/erofs/fileio.c
+++ b/fs/erofs/fileio.c
@@ -96,8 +96,6 @@ static int erofs_fileio_scan_folio(struct erofs_fileio *io, struct folio *folio)
 	struct erofs_map_blocks *map = &io->map;
 	unsigned int cur = 0, end = folio_size(folio), len, attached = 0;
 	loff_t pos = folio_pos(folio), ofs;
-	struct iov_iter iter;
-	struct bio_vec bv;
 	int err = 0;
 
 	erofs_onlinefolio_init(folio);
@@ -122,13 +120,7 @@ static int erofs_fileio_scan_folio(struct erofs_fileio *io, struct folio *folio)
 				err = PTR_ERR(src);
 				break;
 			}
-			bvec_set_folio(&bv, folio, len, cur);
-			iov_iter_bvec(&iter, ITER_DEST, &bv, 1, len);
-			if (copy_to_iter(src, len, &iter) != len) {
-				erofs_put_metabuf(&buf);
-				err = -EIO;
-				break;
-			}
+			memcpy_to_folio(folio, cur, src, len);
 			erofs_put_metabuf(&buf);
 		} else if (!(map->m_flags & EROFS_MAP_MAPPED)) {
 			folio_zero_segment(folio, cur, cur + len);

From 27917e8194f91dffd8b4825350c63cb68e98ce58 Mon Sep 17 00:00:00 2001
From: Gao Xiang <hsiangkao@linux.alibaba.com>
Date: Wed, 9 Jul 2025 11:46:14 +0800
Subject: [PATCH 1297/1334] erofs: address D-cache aliasing

Flush the D-cache before unlocking folios for compressed inodes, as
they are dirtied during decompression.

Avoid calling flush_dcache_folio() on every CPU write, since it's more
like playing whack-a-mole without real benefit.

It has no impact on x86 and arm64/risc-v: on x86, flush_dcache_folio()
is a no-op, and on arm64/risc-v, PG_dcache_clean (PG_arch_1) is clear
for new page cache folios.  However, certain ARM boards are affected,
as reported.

Fixes: 3883a79abd02 ("staging: erofs: introduce VLE decompression support")
Closes: https://lore.kernel.org/r/c1e51e16-6cc6-49d0-a63e-4e9ff6c4dd53@pengutronix.de
Closes: https://lore.kernel.org/r/38d43fae-1182-4155-9c5b-ffc7382d9917@siemens.com
Tested-by: Jan Kiszka <jan.kiszka@siemens.com>
Tested-by: Stefan Kerkmann <s.kerkmann@pengutronix.de>
Signed-off-by: Gao Xiang <hsiangkao@linux.alibaba.com>
Link: https://lore.kernel.org/r/20250709034614.2780117-2-hsiangkao@linux.alibaba.com
---
 fs/erofs/data.c         | 16 +++++++++++-----
 fs/erofs/decompressor.c | 12 ++++--------
 fs/erofs/fileio.c       |  4 ++--
 fs/erofs/internal.h     |  2 +-
 fs/erofs/zdata.c        |  6 +++---
 5 files changed, 21 insertions(+), 19 deletions(-)

diff --git a/fs/erofs/data.c b/fs/erofs/data.c
index 221e0ff1ed0d..16e4a6bd9b97 100644
--- a/fs/erofs/data.c
+++ b/fs/erofs/data.c
@@ -214,9 +214,11 @@ int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *map)
 
 /*
  * bit 30: I/O error occurred on this folio
+ * bit 29: CPU has dirty data in D-cache (needs aliasing handling);
  * bit 0 - 29: remaining parts to complete this folio
  */
-#define EROFS_ONLINEFOLIO_EIO			(1 << 30)
+#define EROFS_ONLINEFOLIO_EIO		30
+#define EROFS_ONLINEFOLIO_DIRTY		29
 
 void erofs_onlinefolio_init(struct folio *folio)
 {
@@ -233,19 +235,23 @@ void erofs_onlinefolio_split(struct folio *folio)
 	atomic_inc((atomic_t *)&folio->private);
 }
 
-void erofs_onlinefolio_end(struct folio *folio, int err)
+void erofs_onlinefolio_end(struct folio *folio, int err, bool dirty)
 {
 	int orig, v;
 
 	do {
 		orig = atomic_read((atomic_t *)&folio->private);
-		v = (orig - 1) | (err ? EROFS_ONLINEFOLIO_EIO : 0);
+		DBG_BUGON(orig <= 0);
+		v = dirty << EROFS_ONLINEFOLIO_DIRTY;
+		v |= (orig - 1) | (!!err << EROFS_ONLINEFOLIO_EIO);
 	} while (atomic_cmpxchg((atomic_t *)&folio->private, orig, v) != orig);
 
-	if (v & ~EROFS_ONLINEFOLIO_EIO)
+	if (v & (BIT(EROFS_ONLINEFOLIO_DIRTY) - 1))
 		return;
 	folio->private = 0;
-	folio_end_read(folio, !(v & EROFS_ONLINEFOLIO_EIO));
+	if (v & BIT(EROFS_ONLINEFOLIO_DIRTY))
+		flush_dcache_folio(folio);
+	folio_end_read(folio, !(v & BIT(EROFS_ONLINEFOLIO_EIO)));
 }
 
 static int erofs_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
diff --git a/fs/erofs/decompressor.c b/fs/erofs/decompressor.c
index bf62e2836b60..358061d7b660 100644
--- a/fs/erofs/decompressor.c
+++ b/fs/erofs/decompressor.c
@@ -301,13 +301,11 @@ static int z_erofs_transform_plain(struct z_erofs_decompress_req *rq,
 		cur = min(cur, rq->outputsize);
 		if (cur && rq->out[0]) {
 			kin = kmap_local_page(rq->in[nrpages_in - 1]);
-			if (rq->out[0] == rq->in[nrpages_in - 1]) {
+			if (rq->out[0] == rq->in[nrpages_in - 1])
 				memmove(kin + rq->pageofs_out, kin + pi, cur);
-				flush_dcache_page(rq->out[0]);
-			} else {
+			else
 				memcpy_to_page(rq->out[0], rq->pageofs_out,
 					       kin + pi, cur);
-			}
 			kunmap_local(kin);
 		}
 		rq->outputsize -= cur;
@@ -325,14 +323,12 @@ static int z_erofs_transform_plain(struct z_erofs_decompress_req *rq,
 			po = (rq->pageofs_out + cur + pi) & ~PAGE_MASK;
 			DBG_BUGON(no >= nrpages_out);
 			cnt = min(insz - pi, PAGE_SIZE - po);
-			if (rq->out[no] == rq->in[ni]) {
+			if (rq->out[no] == rq->in[ni])
 				memmove(kin + po,
 					kin + rq->pageofs_in + pi, cnt);
-				flush_dcache_page(rq->out[no]);
-			} else if (rq->out[no]) {
+			else if (rq->out[no])
 				memcpy_to_page(rq->out[no], po,
 					       kin + rq->pageofs_in + pi, cnt);
-			}
 			pi += cnt;
 		} while (pi < insz);
 		kunmap_local(kin);
diff --git a/fs/erofs/fileio.c b/fs/erofs/fileio.c
index fe2cd2982b4b..91781718199e 100644
--- a/fs/erofs/fileio.c
+++ b/fs/erofs/fileio.c
@@ -38,7 +38,7 @@ static void erofs_fileio_ki_complete(struct kiocb *iocb, long ret)
 	} else {
 		bio_for_each_folio_all(fi, &rq->bio) {
 			DBG_BUGON(folio_test_uptodate(fi.folio));
-			erofs_onlinefolio_end(fi.folio, ret);
+			erofs_onlinefolio_end(fi.folio, ret, false);
 		}
 	}
 	bio_uninit(&rq->bio);
@@ -154,7 +154,7 @@ io_retry:
 		}
 		cur += len;
 	}
-	erofs_onlinefolio_end(folio, err);
+	erofs_onlinefolio_end(folio, err, false);
 	return err;
 }
 
diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h
index a32c03a80c70..0d19bde8c094 100644
--- a/fs/erofs/internal.h
+++ b/fs/erofs/internal.h
@@ -390,7 +390,7 @@ int erofs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 int erofs_map_blocks(struct inode *inode, struct erofs_map_blocks *map);
 void erofs_onlinefolio_init(struct folio *folio);
 void erofs_onlinefolio_split(struct folio *folio);
-void erofs_onlinefolio_end(struct folio *folio, int err);
+void erofs_onlinefolio_end(struct folio *folio, int err, bool dirty);
 struct inode *erofs_iget(struct super_block *sb, erofs_nid_t nid);
 int erofs_getattr(struct mnt_idmap *idmap, const struct path *path,
 		  struct kstat *stat, u32 request_mask,
diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c
index fe8071844724..32e3905e75fe 100644
--- a/fs/erofs/zdata.c
+++ b/fs/erofs/zdata.c
@@ -1091,7 +1091,7 @@ static int z_erofs_scan_folio(struct z_erofs_frontend *f,
 			tight = (bs == PAGE_SIZE);
 		}
 	} while ((end = cur) > 0);
-	erofs_onlinefolio_end(folio, err);
+	erofs_onlinefolio_end(folio, err, false);
 	return err;
 }
 
@@ -1196,7 +1196,7 @@ static void z_erofs_fill_other_copies(struct z_erofs_backend *be, int err)
 			cur += len;
 		}
 		kunmap_local(dst);
-		erofs_onlinefolio_end(page_folio(bvi->bvec.page), err);
+		erofs_onlinefolio_end(page_folio(bvi->bvec.page), err, true);
 		list_del(p);
 		kfree(bvi);
 	}
@@ -1355,7 +1355,7 @@ static int z_erofs_decompress_pcluster(struct z_erofs_backend *be, int err)
 
 		DBG_BUGON(z_erofs_page_is_invalidated(page));
 		if (!z_erofs_is_shortlived_page(page)) {
-			erofs_onlinefolio_end(page_folio(page), err);
+			erofs_onlinefolio_end(page_folio(page), err, true);
 			continue;
 		}
 		if (pcl->algorithmformat != Z_EROFS_COMPRESSION_LZ4) {

From d31fbdc4c7252846ea80235db8c1a8c932da9d39 Mon Sep 17 00:00:00 2001
From: Chao Yu <chao@kernel.org>
Date: Thu, 10 Jul 2025 15:36:18 +0800
Subject: [PATCH 1298/1334] erofs: allow readdir() to be interrupted

In a quick slow device, readdir() may loop for long time in large
directory, let's give a chance to allow it to be interrupted by
userspace.

Signed-off-by: Chao Yu <chao@kernel.org>
Reviewed-by: Gao Xiang <hsiangkao@linux.alibaba.com>
Link: https://lore.kernel.org/r/20250710073619.4083422-1-chao@kernel.org
[ Gao Xiang: move cond_resched() to the end of the while loop. ]
Signed-off-by: Gao Xiang <hsiangkao@linux.alibaba.com>
---
 fs/erofs/dir.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/fs/erofs/dir.c b/fs/erofs/dir.c
index 2fae209d0274..3e4b38bec0aa 100644
--- a/fs/erofs/dir.c
+++ b/fs/erofs/dir.c
@@ -58,6 +58,11 @@ static int erofs_readdir(struct file *f, struct dir_context *ctx)
 		struct erofs_dirent *de;
 		unsigned int nameoff, maxsize;
 
+		if (fatal_signal_pending(current)) {
+			err = -ERESTARTSYS;
+			break;
+		}
+
 		de = erofs_bread(&buf, dbstart, true);
 		if (IS_ERR(de)) {
 			erofs_err(sb, "failed to readdir of logical block %llu of nid %llu",
@@ -88,6 +93,7 @@ static int erofs_readdir(struct file *f, struct dir_context *ctx)
 			break;
 		ctx->pos = dbstart + maxsize;
 		ofs = 0;
+		cond_resched();
 	}
 	erofs_put_metabuf(&buf);
 	if (EROFS_I(dir)->dot_omitted && ctx->pos == dir->i_size) {

From dd831ac8221e691e9e918585b1003c7071df0379 Mon Sep 17 00:00:00 2001
From: Xiang Mei <xmei5@asu.edu>
Date: Sat, 5 Jul 2025 14:21:43 -0700
Subject: [PATCH 1299/1334] net/sched: sch_qfq: Fix null-deref in agg_dequeue

To prevent a potential crash in agg_dequeue (net/sched/sch_qfq.c)
when cl->qdisc->ops->peek(cl->qdisc) returns NULL, we check the return
value before using it, similar to the existing approach in sch_hfsc.c.

To avoid code duplication, the following changes are made:

1. Changed qdisc_warn_nonwc(include/net/pkt_sched.h) into a static
inline function.

2. Moved qdisc_peek_len from net/sched/sch_hfsc.c to
include/net/pkt_sched.h so that sch_qfq can reuse it.

3. Applied qdisc_peek_len in agg_dequeue to avoid crashing.

Signed-off-by: Xiang Mei <xmei5@asu.edu>
Reviewed-by: Cong Wang <xiyou.wangcong@gmail.com>
Link: https://patch.msgid.link/20250705212143.3982664-1-xmei5@asu.edu
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 include/net/pkt_sched.h | 25 ++++++++++++++++++++++++-
 net/sched/sch_api.c     | 10 ----------
 net/sched/sch_hfsc.c    | 16 ----------------
 net/sched/sch_qfq.c     |  2 +-
 4 files changed, 25 insertions(+), 28 deletions(-)

diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h
index d7b7b6cd4aa1..8a75c73fc555 100644
--- a/include/net/pkt_sched.h
+++ b/include/net/pkt_sched.h
@@ -114,7 +114,6 @@ struct qdisc_rate_table *qdisc_get_rtab(struct tc_ratespec *r,
 					struct netlink_ext_ack *extack);
 void qdisc_put_rtab(struct qdisc_rate_table *tab);
 void qdisc_put_stab(struct qdisc_size_table *tab);
-void qdisc_warn_nonwc(const char *txt, struct Qdisc *qdisc);
 bool sch_direct_xmit(struct sk_buff *skb, struct Qdisc *q,
 		     struct net_device *dev, struct netdev_queue *txq,
 		     spinlock_t *root_lock, bool validate);
@@ -290,4 +289,28 @@ static inline bool tc_qdisc_stats_dump(struct Qdisc *sch,
 	return true;
 }
 
+static inline void qdisc_warn_nonwc(const char *txt, struct Qdisc *qdisc)
+{
+	if (!(qdisc->flags & TCQ_F_WARN_NONWC)) {
+		pr_warn("%s: %s qdisc %X: is non-work-conserving?\n",
+			txt, qdisc->ops->id, qdisc->handle >> 16);
+		qdisc->flags |= TCQ_F_WARN_NONWC;
+	}
+}
+
+static inline unsigned int qdisc_peek_len(struct Qdisc *sch)
+{
+	struct sk_buff *skb;
+	unsigned int len;
+
+	skb = sch->ops->peek(sch);
+	if (unlikely(skb == NULL)) {
+		qdisc_warn_nonwc("qdisc_peek_len", sch);
+		return 0;
+	}
+	len = qdisc_pkt_len(skb);
+
+	return len;
+}
+
 #endif
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index 241e86cec9c5..d7c767b861a4 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -601,16 +601,6 @@ out:
 	qdisc_skb_cb(skb)->pkt_len = pkt_len;
 }
 
-void qdisc_warn_nonwc(const char *txt, struct Qdisc *qdisc)
-{
-	if (!(qdisc->flags & TCQ_F_WARN_NONWC)) {
-		pr_warn("%s: %s qdisc %X: is non-work-conserving?\n",
-			txt, qdisc->ops->id, qdisc->handle >> 16);
-		qdisc->flags |= TCQ_F_WARN_NONWC;
-	}
-}
-EXPORT_SYMBOL(qdisc_warn_nonwc);
-
 static enum hrtimer_restart qdisc_watchdog(struct hrtimer *timer)
 {
 	struct qdisc_watchdog *wd = container_of(timer, struct qdisc_watchdog,
diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c
index 5a7745170e84..d8fd35da32a7 100644
--- a/net/sched/sch_hfsc.c
+++ b/net/sched/sch_hfsc.c
@@ -835,22 +835,6 @@ update_vf(struct hfsc_class *cl, unsigned int len, u64 cur_time)
 	}
 }
 
-static unsigned int
-qdisc_peek_len(struct Qdisc *sch)
-{
-	struct sk_buff *skb;
-	unsigned int len;
-
-	skb = sch->ops->peek(sch);
-	if (unlikely(skb == NULL)) {
-		qdisc_warn_nonwc("qdisc_peek_len", sch);
-		return 0;
-	}
-	len = qdisc_pkt_len(skb);
-
-	return len;
-}
-
 static void
 hfsc_adjust_levels(struct hfsc_class *cl)
 {
diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c
index bf1282cb22eb..bcce36608871 100644
--- a/net/sched/sch_qfq.c
+++ b/net/sched/sch_qfq.c
@@ -989,7 +989,7 @@ static struct sk_buff *agg_dequeue(struct qfq_aggregate *agg,
 
 	if (cl->qdisc->q.qlen == 0) /* no more packets, remove from list */
 		list_del_init(&cl->alist);
-	else if (cl->deficit < qdisc_pkt_len(cl->qdisc->ops->peek(cl->qdisc))) {
+	else if (cl->deficit < qdisc_peek_len(cl->qdisc)) {
 		cl->deficit += agg->lmax;
 		list_move_tail(&cl->alist, &agg->active);
 	}

From d7a54d02db41f72f0581a3c77c75b0993ed3f6e2 Mon Sep 17 00:00:00 2001
From: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Date: Wed, 9 Jul 2025 23:34:10 +0300
Subject: [PATCH 1300/1334] wifi: mac80211: always initialize sdata::key_list

This is currently not initialized for a virtual monitor, leading to a
NULL pointer dereference when - for example - iterating over all the
keys of all the vifs.

Reviewed-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250709233400.8dcefe578497.I4c90a00ae3256520e063199d7f6f2580d5451acf@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/iface.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c
index 7c27f3cd841c..c01634fdba78 100644
--- a/net/mac80211/iface.c
+++ b/net/mac80211/iface.c
@@ -1150,6 +1150,8 @@ static void ieee80211_sdata_init(struct ieee80211_local *local,
 {
 	sdata->local = local;
 
+	INIT_LIST_HEAD(&sdata->key_list);
+
 	/*
 	 * Initialize the default link, so we can use link_id 0 for non-MLD,
 	 * and that continues to work for non-MLD-aware drivers that use just
@@ -2210,8 +2212,6 @@ int ieee80211_if_add(struct ieee80211_local *local, const char *name,
 
 	ieee80211_init_frag_cache(&sdata->frags);
 
-	INIT_LIST_HEAD(&sdata->key_list);
-
 	wiphy_delayed_work_init(&sdata->dec_tailroom_needed_wk,
 				ieee80211_delayed_tailroom_dec);
 

From c07981af55d3ba3ec3be880cfe4a0cc10f1f7138 Mon Sep 17 00:00:00 2001
From: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Date: Wed, 9 Jul 2025 23:34:56 +0300
Subject: [PATCH 1301/1334] wifi: mac80211: add the virtual monitor after
 reconfig complete

In reconfig we add the virtual monitor in 2 cases:
1. If we are resuming (it was deleted on suspend)
2. If it was added after an error but before the reconfig
   (due to the last non-monitor interface removal).

In the second case, the removal of the non-monitor interface will succeed
but the addition of the virtual monitor will fail, so we add it in the
reconfig.

The problem is that we mislead the driver to think that this is an existing
interface that is getting re-added - while it is actually a completely new
interface from the drivers' point of view.

Some drivers act differently when a interface is re-added. For example, it
might not initialize things because they were already initialized.
Such drivers will - in this case - be left with a partialy initialized vif.

To fix it, add the virtual monitor after reconfig_complete, so the
driver will know that this is a completely new interface.

Fixes: 3c3e21e7443b ("mac80211: destroy virtual monitor interface across suspend")
Reviewed-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250709233451.648d39b041e8.I2e37b68375278987e303d6c00cc5f3d8334d2f96@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/util.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index a125995ed252..e66da651678a 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -2144,11 +2144,6 @@ int ieee80211_reconfig(struct ieee80211_local *local)
 		cfg80211_sched_scan_stopped_locked(local->hw.wiphy, 0);
 
  wake_up:
-
-	if (local->virt_monitors > 0 &&
-	    local->virt_monitors == local->open_count)
-		ieee80211_add_virtual_monitor(local);
-
 	/*
 	 * Clear the WLAN_STA_BLOCK_BA flag so new aggregation
 	 * sessions can be established after a resume.
@@ -2202,6 +2197,10 @@ int ieee80211_reconfig(struct ieee80211_local *local)
 		}
 	}
 
+	if (local->virt_monitors > 0 &&
+	    local->virt_monitors == local->open_count)
+		ieee80211_add_virtual_monitor(local);
+
 	if (!suspended)
 		return 0;
 

From e778689390c71462a099b5d6e56d71c316486184 Mon Sep 17 00:00:00 2001
From: Hans de Goede <hansg@kernel.org>
Date: Mon, 7 Jul 2025 23:14:12 +0200
Subject: [PATCH 1302/1334] drm/i915/bios: Apply vlv_fixup_mipi_sequences() to
 v2 mipi-sequences too

It turns out that the fixup from vlv_fixup_mipi_sequences() is necessary
for some DSI panel's with version 2 mipi-sequences too.

Specifically the Acer Iconia One 8 A1-840 (not to be confused with the
A1-840FHD which is different) has the following sequences:

BDB block 53 (1284 bytes) - MIPI sequence block:
	Sequence block version v2
	Panel 0 *

Sequence 2 - MIPI_SEQ_INIT_OTP
	GPIO index 9, source 0, set 0 (0x00)
	Delay: 50000 us
	GPIO index 9, source 0, set 1 (0x01)
	Delay: 6000 us
	GPIO index 9, source 0, set 0 (0x00)
	Delay: 6000 us
	GPIO index 9, source 0, set 1 (0x01)
	Delay: 25000 us
	Send DCS: Port A, VC 0, LP, Type 39, Length 5, Data ff aa 55 a5 80
	Send DCS: Port A, VC 0, LP, Type 39, Length 3, Data 6f 11 00
	...
	Send DCS: Port A, VC 0, LP, Type 05, Length 1, Data 29
	Delay: 120000 us

Sequence 4 - MIPI_SEQ_DISPLAY_OFF
	Send DCS: Port A, VC 0, LP, Type 05, Length 1, Data 28
	Delay: 105000 us
	Send DCS: Port A, VC 0, LP, Type 05, Length 2, Data 10 00
	Delay: 10000 us

Sequence 5 - MIPI_SEQ_ASSERT_RESET
	Delay: 10000 us
	GPIO index 9, source 0, set 0 (0x00)

Notice how there is no MIPI_SEQ_DEASSERT_RESET, instead the deassert
is done at the beginning of MIPI_SEQ_INIT_OTP, which is exactly what
the fixup from vlv_fixup_mipi_sequences() fixes up.

Extend it to also apply to v2 sequences, this fixes the panel not working
on the Acer Iconia One 8 A1-840.

Closes: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/14605
Signed-off-by: Hans de Goede <hansg@kernel.org>
Acked-by: Jani Nikula <jani.nikula@intel.com>
Link: https://lore.kernel.org/r/20250703143824.7121-1-hansg@kernel.org
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
(cherry picked from commit 11895f375939d60efe7ed5dddc1cffe2e79f976c)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/i915/display/intel_bios.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_bios.c b/drivers/gpu/drm/i915/display/intel_bios.c
index ba7b8938b17c..166ee11831ab 100644
--- a/drivers/gpu/drm/i915/display/intel_bios.c
+++ b/drivers/gpu/drm/i915/display/intel_bios.c
@@ -1938,7 +1938,7 @@ static int get_init_otp_deassert_fragment_len(struct intel_display *display,
 	int index, len;
 
 	if (drm_WARN_ON(display->drm,
-			!data || panel->vbt.dsi.seq_version != 1))
+			!data || panel->vbt.dsi.seq_version >= 3))
 		return 0;
 
 	/* index = 1 to skip sequence byte */
@@ -1961,7 +1961,7 @@ static int get_init_otp_deassert_fragment_len(struct intel_display *display,
 }
 
 /*
- * Some v1 VBT MIPI sequences do the deassert in the init OTP sequence.
+ * Some v1/v2 VBT MIPI sequences do the deassert in the init OTP sequence.
  * The deassert must be done before calling intel_dsi_device_ready, so for
  * these devices we split the init OTP sequence into a deassert sequence and
  * the actual init OTP part.
@@ -1972,9 +1972,9 @@ static void vlv_fixup_mipi_sequences(struct intel_display *display,
 	u8 *init_otp;
 	int len;
 
-	/* Limit this to v1 vid-mode sequences */
+	/* Limit this to v1/v2 vid-mode sequences */
 	if (panel->vbt.dsi.config->is_cmd_mode ||
-	    panel->vbt.dsi.seq_version != 1)
+	    panel->vbt.dsi.seq_version >= 3)
 		return;
 
 	/* Only do this if there are otp and assert seqs and no deassert seq */

From 68ea85df15d111d82fc474cbe104174791169355 Mon Sep 17 00:00:00 2001
From: Himanshu Madhani <himanshu.madhani@oracle.com>
Date: Tue, 8 Jul 2025 22:25:30 +0000
Subject: [PATCH 1303/1334] PCI/MSI: Prevent recursive locking in
 pci_msix_write_tph_tag()

pci_msix_write_tph_tag() takes the per device MSI descriptor mutex and then
invokes msi_domain_get_virq(), which takes the same mutex again. That
obviously results in a system hang which is exposed by a softlockup or
lockdep warning.

Move the lock guard after the invocation of msi_domain_get_virq() to fix
this.

[ tglx: Massage changelog by adding a proper explanation and removing the
  	not really useful stacktrace ]

Fixes: d5124a9957b2 ("PCI/MSI: Provide a sane mechanism for TPH")
Reported-by: Jorge Lopez <jorge.jo.lopez@oracle.com>
Suggested-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Himanshu Madhani <himanshu.madhani@oracle.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Jorge Lopez <jorge.jo.lopez@oracle.com>
Link: https://lore.kernel.org/all/20250708222530.1041477-1-himanshu.madhani@oracle.com
---
 drivers/pci/msi/msi.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/pci/msi/msi.c b/drivers/pci/msi/msi.c
index 6ede55a7c5e6..d686488f4111 100644
--- a/drivers/pci/msi/msi.c
+++ b/drivers/pci/msi/msi.c
@@ -934,10 +934,12 @@ int pci_msix_write_tph_tag(struct pci_dev *pdev, unsigned int index, u16 tag)
 	if (!pdev->msix_enabled)
 		return -ENXIO;
 
-	guard(msi_descs_lock)(&pdev->dev);
 	virq = msi_get_virq(&pdev->dev, index);
 	if (!virq)
 		return -ENXIO;
+
+	guard(msi_descs_lock)(&pdev->dev);
+
 	/*
 	 * This is a horrible hack, but short of implementing a PCI
 	 * specific interrupt chip callback and a huge pile of

From a8b289f0f2dcbadd8c207ad8f33cf7ba2b4eb088 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Thu, 10 Jul 2025 10:00:12 +0200
Subject: [PATCH 1304/1334] irqchip/irq-msi-lib: Fix build with PCI disabled

The armada-370-xp irqchip fails in some randconfig builds because
of a missing declaration:

In file included from drivers/irqchip/irq-armada-370-xp.c:23:
include/linux/irqchip/irq-msi-lib.h:25:39: error: 'struct msi_domain_info' declared inside parameter list will not be visible outside of this definition or declaration [-Werror]

Add a forward declaration for the msi_domain_info structure.

[ tglx: Fixed up the subsystem prefix. Is it really that hard to get right? ]

Fixes: e51b27438a10 ("irqchip: Make irq-msi-lib.h globally available")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/all/20250710080021.2303640-1-arnd@kernel.org
---
 include/linux/irqchip/irq-msi-lib.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/include/linux/irqchip/irq-msi-lib.h b/include/linux/irqchip/irq-msi-lib.h
index dd8d1d138544..224ac28e88d7 100644
--- a/include/linux/irqchip/irq-msi-lib.h
+++ b/include/linux/irqchip/irq-msi-lib.h
@@ -17,6 +17,7 @@
 
 #define MATCH_PLATFORM_MSI	BIT(DOMAIN_BUS_PLATFORM_MSI)
 
+struct msi_domain_info;
 int msi_lib_irq_domain_select(struct irq_domain *d, struct irq_fwspec *fwspec,
 			      enum irq_domain_bus_token bus_token);
 

From 18cdb3d982da8976b28d57691eb256ec5688fad2 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 7 Jul 2025 12:45:17 +0000
Subject: [PATCH 1305/1334] netfilter: flowtable: account for Ethernet header
 in nf_flow_pppoe_proto()

syzbot found a potential access to uninit-value in nf_flow_pppoe_proto()

Blamed commit forgot the Ethernet header.

BUG: KMSAN: uninit-value in nf_flow_offload_inet_hook+0x7e4/0x940 net/netfilter/nf_flow_table_inet.c:27
  nf_flow_offload_inet_hook+0x7e4/0x940 net/netfilter/nf_flow_table_inet.c:27
  nf_hook_entry_hookfn include/linux/netfilter.h:157 [inline]
  nf_hook_slow+0xe1/0x3d0 net/netfilter/core.c:623
  nf_hook_ingress include/linux/netfilter_netdev.h:34 [inline]
  nf_ingress net/core/dev.c:5742 [inline]
  __netif_receive_skb_core+0x4aff/0x70c0 net/core/dev.c:5837
  __netif_receive_skb_one_core net/core/dev.c:5975 [inline]
  __netif_receive_skb+0xcc/0xac0 net/core/dev.c:6090
  netif_receive_skb_internal net/core/dev.c:6176 [inline]
  netif_receive_skb+0x57/0x630 net/core/dev.c:6235
  tun_rx_batched+0x1df/0x980 drivers/net/tun.c:1485
  tun_get_user+0x4ee0/0x6b40 drivers/net/tun.c:1938
  tun_chr_write_iter+0x3e9/0x5c0 drivers/net/tun.c:1984
  new_sync_write fs/read_write.c:593 [inline]
  vfs_write+0xb4b/0x1580 fs/read_write.c:686
  ksys_write fs/read_write.c:738 [inline]
  __do_sys_write fs/read_write.c:749 [inline]

Reported-by: syzbot+bf6ed459397e307c3ad2@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/netdev/686bc073.a00a0220.c7b3.0086.GAE@google.com/T/#u
Fixes: 87b3593bed18 ("netfilter: flowtable: validate pppoe header")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Pablo Neira Ayuso <pablo@netfilter.org>
Link: https://patch.msgid.link/20250707124517.614489-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/netfilter/nf_flow_table.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h
index d711642e78b5..c003cd194fa2 100644
--- a/include/net/netfilter/nf_flow_table.h
+++ b/include/net/netfilter/nf_flow_table.h
@@ -370,7 +370,7 @@ static inline __be16 __nf_flow_pppoe_proto(const struct sk_buff *skb)
 
 static inline bool nf_flow_pppoe_proto(struct sk_buff *skb, __be16 *inner_proto)
 {
-	if (!pskb_may_pull(skb, PPPOE_SES_HLEN))
+	if (!pskb_may_pull(skb, ETH_HLEN + PPPOE_SES_HLEN))
 		return false;
 
 	*inner_proto = __nf_flow_pppoe_proto(skb);

From 711c80f7d8b163d3ecd463cd96f07230f488e750 Mon Sep 17 00:00:00 2001
From: Kito Xu <veritas501@foxmail.com>
Date: Wed, 9 Jul 2025 03:52:51 +0000
Subject: [PATCH 1306/1334] net: appletalk: Fix device refcount leak in
 atrtr_create()

When updating an existing route entry in atrtr_create(), the old device
reference was not being released before assigning the new device,
leading to a device refcount leak. Fix this by calling dev_put() to
release the old device reference before holding the new one.

Fixes: c7f905f0f6d4 ("[ATALK]: Add missing dev_hold() to atrtr_create().")
Signed-off-by: Kito Xu <veritas501@foxmail.com>
Link: https://patch.msgid.link/tencent_E1A26771CDAB389A0396D1681A90A49E5D09@qq.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/appletalk/ddp.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c
index 73ea7e67f05a..30242fe10341 100644
--- a/net/appletalk/ddp.c
+++ b/net/appletalk/ddp.c
@@ -576,6 +576,7 @@ static int atrtr_create(struct rtentry *r, struct net_device *devhint)
 
 	/* Fill in the routing entry */
 	rt->target  = ta->sat_addr;
+	dev_put(rt->dev); /* Release old device */
 	dev_hold(devhint);
 	rt->dev     = devhint;
 	rt->flags   = r->rt_flags;

From 01b8114b432d7baaa5e51ab229c12c4f36b8e2c6 Mon Sep 17 00:00:00 2001
From: Mingming Cao <mmc@linux.ibm.com>
Date: Wed, 9 Jul 2025 08:33:32 -0700
Subject: [PATCH 1307/1334] ibmvnic: Fix hardcoded NUM_RX_STATS/NUM_TX_STATS
 with dynamic sizeof

The previous hardcoded definitions of NUM_RX_STATS and
NUM_TX_STATS were not updated when new fields were added
to the ibmvnic_{rx,tx}_queue_stats structures. Specifically,
commit 2ee73c54a615 ("ibmvnic: Add stat for tx direct vs tx
batched") added a fourth TX stat, but NUM_TX_STATS remained 3,
leading to a mismatch.

This patch replaces the static defines with dynamic sizeof-based
calculations to ensure the stat arrays are correctly sized.
This fixes incorrect indexing and prevents incomplete stat
reporting in tools like ethtool.

Fixes: 2ee73c54a615 ("ibmvnic: Add stat for tx direct vs tx batched")
Signed-off-by: Mingming Cao <mmc@linux.ibm.com>
Reviewed-by: Dave Marquardt <davemarq@linux.ibm.com>
Reviewed-by: Haren Myneni <haren@linux.ibm.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250709153332.73892-1-mmc@linux.ibm.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/ibm/ibmvnic.h | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/ibm/ibmvnic.h b/drivers/net/ethernet/ibm/ibmvnic.h
index a189038d88df..246ddce753f9 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.h
+++ b/drivers/net/ethernet/ibm/ibmvnic.h
@@ -211,7 +211,6 @@ struct ibmvnic_statistics {
 	u8 reserved[72];
 } __packed __aligned(8);
 
-#define NUM_TX_STATS 3
 struct ibmvnic_tx_queue_stats {
 	u64 batched_packets;
 	u64 direct_packets;
@@ -219,13 +218,18 @@ struct ibmvnic_tx_queue_stats {
 	u64 dropped_packets;
 };
 
-#define NUM_RX_STATS 3
+#define NUM_TX_STATS \
+	(sizeof(struct ibmvnic_tx_queue_stats) / sizeof(u64))
+
 struct ibmvnic_rx_queue_stats {
 	u64 packets;
 	u64 bytes;
 	u64 interrupts;
 };
 
+#define NUM_RX_STATS \
+	(sizeof(struct ibmvnic_rx_queue_stats) / sizeof(u64))
+
 struct ibmvnic_acl_buffer {
 	__be32 len;
 	__be32 version;

From b4517c363e0e005c7f81ae3be199eec68e87f122 Mon Sep 17 00:00:00 2001
From: Oleksij Rempel <o.rempel@pengutronix.de>
Date: Wed, 9 Jul 2025 15:07:52 +0200
Subject: [PATCH 1308/1334] net: phy: microchip: Use genphy_soft_reset() to
 purge stale LPA bits

Enable .soft_reset for the LAN88xx PHY driver by assigning
genphy_soft_reset() to ensure that the phylib core performs a proper
soft reset during reconfiguration.

Previously, the driver left .soft_reset unimplemented, so calls to
phy_init_hw() (e.g., from lan88xx_link_change_notify()) did not fully
reset the PHY. As a result, stale contents in the Link Partner Ability
(LPA) register could persist, causing the PHY to incorrectly report
that the link partner advertised autonegotiation even when it did not.

Using genphy_soft_reset() guarantees a clean reset of the PHY and
corrects the false autoneg reporting in these scenarios.

Fixes: ccb989e4d1ef ("net: phy: microchip: Reset LAN88xx PHY to ensure clean link state on LAN7800/7850")
Signed-off-by: Oleksij Rempel <o.rempel@pengutronix.de>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/20250709130753.3994461-2-o.rempel@pengutronix.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/microchip.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/phy/microchip.c b/drivers/net/phy/microchip.c
index 13570f628aa5..5e590b0a75e5 100644
--- a/drivers/net/phy/microchip.c
+++ b/drivers/net/phy/microchip.c
@@ -488,6 +488,7 @@ static struct phy_driver microchip_phy_driver[] = {
 	.config_init	= lan88xx_config_init,
 	.config_aneg	= lan88xx_config_aneg,
 	.link_change_notify = lan88xx_link_change_notify,
+	.soft_reset	= genphy_soft_reset,
 
 	/* Interrupt handling is broken, do not define related
 	 * functions to force polling.

From dd4360c0e8504f2f7639c7f5d07c93cfd6a98333 Mon Sep 17 00:00:00 2001
From: Oleksij Rempel <o.rempel@pengutronix.de>
Date: Wed, 9 Jul 2025 15:07:53 +0200
Subject: [PATCH 1309/1334] net: phy: microchip: limit 100M workaround to
 link-down events on LAN88xx

Restrict the 100Mbit forced-mode workaround to link-down transitions
only, to prevent repeated link reset cycles in certain configurations.

The workaround was originally introduced to improve signal reliability
when switching cables between long and short distances. It temporarily
forces the PHY into 10 Mbps before returning to 100 Mbps.

However, when used with autonegotiating link partners (e.g., Intel i350),
executing this workaround on every link change can confuse the partner
and cause constant renegotiation loops. This results in repeated link
down/up transitions and the PHY never reaching a stable state.

Limit the workaround to only run during the PHY_NOLINK state. This ensures
it is triggered only once per link drop, avoiding disruptive toggling
while still preserving its intended effect.

Note: I am not able to reproduce the original issue that this workaround
addresses. I can only confirm that 100 Mbit mode works correctly in my
test setup. Based on code inspection, I assume the workaround aims to
reset some internal state machine or signal block by toggling speeds.
However, a PHY reset is already performed earlier in the function via
phy_init_hw(), which may achieve a similar effect. Without a reproducer,
I conservatively keep the workaround but restrict its conditions.

Fixes: e57cf3639c32 ("net: lan78xx: fix accessing the LAN7800's internal phy specific registers from the MAC driver")
Signed-off-by: Oleksij Rempel <o.rempel@pengutronix.de>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/20250709130753.3994461-3-o.rempel@pengutronix.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/microchip.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/phy/microchip.c b/drivers/net/phy/microchip.c
index 5e590b0a75e5..dc8634e7bcbe 100644
--- a/drivers/net/phy/microchip.c
+++ b/drivers/net/phy/microchip.c
@@ -332,7 +332,7 @@ static void lan88xx_link_change_notify(struct phy_device *phydev)
 	 * As workaround, set to 10 before setting to 100
 	 * at forced 100 F/H mode.
 	 */
-	if (!phydev->autoneg && phydev->speed == 100) {
+	if (phydev->state == PHY_NOLINK && !phydev->autoneg && phydev->speed == 100) {
 		/* disable phy interrupt */
 		temp = phy_read(phydev, LAN88XX_INT_MASK);
 		temp &= ~LAN88XX_INT_MASK_MDINTPIN_EN_;

From 4e914ef063de40397e25a025c70d9737a9e45a8c Mon Sep 17 00:00:00 2001
From: Guillaume Nault <gnault@redhat.com>
Date: Wed, 9 Jul 2025 16:30:10 +0200
Subject: [PATCH 1310/1334] gre: Fix IPv6 multicast route creation.

Use addrconf_add_dev() instead of ipv6_find_idev() in
addrconf_gre_config() so that we don't just get the inet6_dev, but also
install the default ff00::/8 multicast route.

Before commit 3e6a0243ff00 ("gre: Fix again IPv6 link-local address
generation."), the multicast route was created at the end of the
function by addrconf_add_mroute(). But this code path is now only taken
in one particular case (gre devices not bound to a local IP address and
in EUI64 mode). For all other cases, the function exits early and
addrconf_add_mroute() is not called anymore.

Using addrconf_add_dev() instead of ipv6_find_idev() in
addrconf_gre_config(), fixes the problem as it will create the default
multicast route for all gre devices. This also brings
addrconf_gre_config() a bit closer to the normal netdevice IPv6
configuration code (addrconf_dev_config()).

Cc: stable@vger.kernel.org
Fixes: 3e6a0243ff00 ("gre: Fix again IPv6 link-local address generation.")
Reported-by: Aiden Yang <ling@moedove.com>
Closes: https://lore.kernel.org/netdev/CANR=AhRM7YHHXVxJ4DmrTNMeuEOY87K2mLmo9KMed1JMr20p6g@mail.gmail.com/
Reviewed-by: Gary Guo <gary@garyguo.net>
Tested-by: Gary Guo <gary@garyguo.net>
Signed-off-by: Guillaume Nault <gnault@redhat.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Link: https://patch.msgid.link/027a923dcb550ad115e6d93ee8bb7d310378bd01.1752070620.git.gnault@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv6/addrconf.c | 9 ++-------
 1 file changed, 2 insertions(+), 7 deletions(-)

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index ba2ec7c870cc..870a0bd6c2ba 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -3525,11 +3525,9 @@ static void addrconf_gre_config(struct net_device *dev)
 
 	ASSERT_RTNL();
 
-	idev = ipv6_find_idev(dev);
-	if (IS_ERR(idev)) {
-		pr_debug("%s: add_dev failed\n", __func__);
+	idev = addrconf_add_dev(dev);
+	if (IS_ERR(idev))
 		return;
-	}
 
 	/* Generate the IPv6 link-local address using addrconf_addr_gen(),
 	 * unless we have an IPv4 GRE device not bound to an IP address and
@@ -3543,9 +3541,6 @@ static void addrconf_gre_config(struct net_device *dev)
 	}
 
 	add_v4_addrs(idev);
-
-	if (dev->flags & IFF_POINTOPOINT)
-		addrconf_add_mroute(dev);
 }
 #endif
 

From 4d61a8a7334399f457867442445a4f916b40cddb Mon Sep 17 00:00:00 2001
From: Guillaume Nault <gnault@redhat.com>
Date: Wed, 9 Jul 2025 16:30:17 +0200
Subject: [PATCH 1311/1334] selftests: Add IPv6 multicast route generation
 tests for GRE devices.

The previous patch fixes a bug that prevented the creation of the
default IPv6 multicast route (ff00::/8) for some GRE devices. Now let's
extend the GRE IPv6 selftests to cover this case.

Also, rename check_ipv6_ll_addr() to check_ipv6_device_config() and
adapt comments and script output to take into account the fact that
we're not limited to link-local address generation.

Signed-off-by: Guillaume Nault <gnault@redhat.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Link: https://patch.msgid.link/65a89583bde3bf866a1922c2e5158e4d72c520e2.1752070620.git.gnault@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../testing/selftests/net/gre_ipv6_lladdr.sh  | 27 ++++++++++++-------
 1 file changed, 17 insertions(+), 10 deletions(-)

diff --git a/tools/testing/selftests/net/gre_ipv6_lladdr.sh b/tools/testing/selftests/net/gre_ipv6_lladdr.sh
index 5b34f6e1f831..48eb999a3120 100755
--- a/tools/testing/selftests/net/gre_ipv6_lladdr.sh
+++ b/tools/testing/selftests/net/gre_ipv6_lladdr.sh
@@ -24,7 +24,10 @@ setup_basenet()
 	ip -netns "${NS0}" address add dev lo 2001:db8::10/64 nodad
 }
 
-# Check if network device has an IPv6 link-local address assigned.
+# Check the IPv6 configuration of a network device.
+#
+# We currently check the generation of the link-local IPv6 address and the
+# creation of the ff00::/8 multicast route.
 #
 # Parameters:
 #
@@ -35,7 +38,7 @@ setup_basenet()
 #         a link-local address)
 #   * $4: The user visible name for the scenario being tested
 #
-check_ipv6_ll_addr()
+check_ipv6_device_config()
 {
 	local DEV="$1"
 	local EXTRA_MATCH="$2"
@@ -45,7 +48,11 @@ check_ipv6_ll_addr()
 	RET=0
 	set +e
 	ip -netns "${NS0}" -6 address show dev "${DEV}" scope link | grep "fe80::" | grep -q "${EXTRA_MATCH}"
-	check_err_fail "${XRET}" $? ""
+	check_err_fail "${XRET}" $? "IPv6 link-local address generation"
+
+	ip -netns "${NS0}" -6 route show table local type multicast ff00::/8 proto kernel | grep -q "${DEV}"
+	check_err_fail 0 $? "IPv6 multicast route creation"
+
 	log_test "${MSG}"
 	set -e
 }
@@ -102,20 +109,20 @@ test_gre_device()
 		;;
 	esac
 
-	# Check that IPv6 link-local address is generated when device goes up
+	# Check the IPv6 device configuration when it goes up
 	ip netns exec "${NS0}" sysctl -qw net.ipv6.conf.gretest.addr_gen_mode="${ADDR_GEN_MODE}"
 	ip -netns "${NS0}" link set dev gretest up
-	check_ipv6_ll_addr gretest "${MATCH_REGEXP}" "${XRET}" "config: ${MSG}"
+	check_ipv6_device_config gretest "${MATCH_REGEXP}" "${XRET}" "config: ${MSG}"
 
 	# Now disable link-local address generation
 	ip -netns "${NS0}" link set dev gretest down
 	ip netns exec "${NS0}" sysctl -qw net.ipv6.conf.gretest.addr_gen_mode=1
 	ip -netns "${NS0}" link set dev gretest up
 
-	# Check that link-local address generation works when re-enabled while
-	# the device is already up
+	# Check the IPv6 device configuration when link-local address
+	# generation is re-enabled while the device is already up
 	ip netns exec "${NS0}" sysctl -qw net.ipv6.conf.gretest.addr_gen_mode="${ADDR_GEN_MODE}"
-	check_ipv6_ll_addr gretest "${MATCH_REGEXP}" "${XRET}" "update: ${MSG}"
+	check_ipv6_device_config gretest "${MATCH_REGEXP}" "${XRET}" "update: ${MSG}"
 
 	ip -netns "${NS0}" link del dev gretest
 }
@@ -126,7 +133,7 @@ test_gre4()
 	local MODE
 
 	for GRE_TYPE in "gre" "gretap"; do
-		printf "\n####\nTesting IPv6 link-local address generation on ${GRE_TYPE} devices\n####\n\n"
+		printf "\n####\nTesting IPv6 configuration of ${GRE_TYPE} devices\n####\n\n"
 
 		for MODE in "eui64" "none" "stable-privacy" "random"; do
 			test_gre_device "${GRE_TYPE}" 192.0.2.10 192.0.2.11 "${MODE}"
@@ -142,7 +149,7 @@ test_gre6()
 	local MODE
 
 	for GRE_TYPE in "ip6gre" "ip6gretap"; do
-		printf "\n####\nTesting IPv6 link-local address generation on ${GRE_TYPE} devices\n####\n\n"
+		printf "\n####\nTesting IPv6 configuration of ${GRE_TYPE} devices\n####\n\n"
 
 		for MODE in "eui64" "none" "stable-privacy" "random"; do
 			test_gre_device "${GRE_TYPE}" 2001:db8::10 2001:db8::11 "${MODE}"

From 47c84997c686b4d43b225521b732492552b84758 Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Wed, 9 Jul 2025 09:12:44 +0000
Subject: [PATCH 1312/1334] selftests: net: lib: fix shift count out of range

I got the following warning when writing other tests:

  + handle_test_result_pass 'bond 802.3ad' '(lacp_active off)'
  + local 'test_name=bond 802.3ad'
  + shift
  + local 'opt_str=(lacp_active off)'
  + shift
  + log_test_result 'bond 802.3ad' '(lacp_active off)' ' OK '
  + local 'test_name=bond 802.3ad'
  + shift
  + local 'opt_str=(lacp_active off)'
  + shift
  + local 'result= OK '
  + shift
  + local retmsg=
  + shift
  /net/tools/testing/selftests/net/forwarding/../lib.sh: line 315: shift: shift count out of range

This happens because an extra shift is executed even after all arguments
have been consumed. Remove the last shift in log_test_result() to avoid
this warning.

Fixes: a923af1ceee7 ("selftests: forwarding: Convert log_test() to recognize RET values")
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Link: https://patch.msgid.link/20250709091244.88395-1-liuhangbin@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/lib.sh | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/net/lib.sh b/tools/testing/selftests/net/lib.sh
index 006fdadcc4b9..86a216e9aca8 100644
--- a/tools/testing/selftests/net/lib.sh
+++ b/tools/testing/selftests/net/lib.sh
@@ -312,7 +312,7 @@ log_test_result()
 	local test_name=$1; shift
 	local opt_str=$1; shift
 	local result=$1; shift
-	local retmsg=$1; shift
+	local retmsg=$1
 
 	printf "TEST: %-60s  [%s]\n" "$test_name $opt_str" "$result"
 	if [[ $retmsg ]]; then

From 6d33df611a39a1b4ad9f2b609ded5d6efa04d97e Mon Sep 17 00:00:00 2001
From: Shuicheng Lin <shuicheng.lin@intel.com>
Date: Tue, 8 Jul 2025 03:54:25 +0000
Subject: [PATCH 1313/1334] drm/xe/pm: Restore display pm if there is error
 after display suspend

xe_bo_evict_all() is called after xe_display_pm_suspend(). So if there
is error with xe_bo_evict_all(), display pm should be restored.

Fixes: 51462211f4a9 ("drm/xe/pxp: add PXP PM support")
Fixes: cb8f81c17531 ("drm/xe/display: Make display suspend/resume work on discrete")
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: John Harrison <John.C.Harrison@Intel.com>
Signed-off-by: Shuicheng Lin <shuicheng.lin@intel.com>
Reviewed-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Link: https://lore.kernel.org/r/20250708035424.3608190-2-shuicheng.lin@intel.com
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
(cherry picked from commit 83dcee17855c4e5af037ae3262809036de127903)
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
---
 drivers/gpu/drm/xe/xe_pm.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_pm.c b/drivers/gpu/drm/xe/xe_pm.c
index ff749edc005b..bcfda545e74f 100644
--- a/drivers/gpu/drm/xe/xe_pm.c
+++ b/drivers/gpu/drm/xe/xe_pm.c
@@ -134,7 +134,7 @@ int xe_pm_suspend(struct xe_device *xe)
 	/* FIXME: Super racey... */
 	err = xe_bo_evict_all(xe);
 	if (err)
-		goto err_pxp;
+		goto err_display;
 
 	for_each_gt(gt, xe, id) {
 		err = xe_gt_suspend(gt);
@@ -151,7 +151,6 @@ int xe_pm_suspend(struct xe_device *xe)
 
 err_display:
 	xe_display_pm_resume(xe);
-err_pxp:
 	xe_pxp_pm_resume(xe->pxp);
 err:
 	drm_dbg(&xe->drm, "Device suspend failed %d\n", err);

From 253a174c06f8c37aa71521623205b890022b6987 Mon Sep 17 00:00:00 2001
From: Shuicheng Lin <shuicheng.lin@intel.com>
Date: Mon, 7 Jul 2025 00:49:14 +0000
Subject: [PATCH 1314/1334] drm/xe: Release runtime pm for error path of
 xe_devcoredump_read()

xe_pm_runtime_put() is missed to be called for the error path in
xe_devcoredump_read().
Add function description comments for xe_devcoredump_read() to help
understand it.

v2: more detail function comments and refine goto logic (Matt)

Fixes: c4a2e5f865b7 ("drm/xe: Add devcoredump chunking")
Cc: stable@vger.kernel.org
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Signed-off-by: Shuicheng Lin <shuicheng.lin@intel.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Link: https://lore.kernel.org/r/20250707004911.3502904-6-shuicheng.lin@intel.com
(cherry picked from commit 017ef1228d735965419ff118fe1b89089e772c42)
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
---
 drivers/gpu/drm/xe/xe_devcoredump.c | 38 +++++++++++++++++++++--------
 1 file changed, 28 insertions(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_devcoredump.c b/drivers/gpu/drm/xe/xe_devcoredump.c
index 7a8af2311318..11e60d687572 100644
--- a/drivers/gpu/drm/xe/xe_devcoredump.c
+++ b/drivers/gpu/drm/xe/xe_devcoredump.c
@@ -171,14 +171,32 @@ static void xe_devcoredump_snapshot_free(struct xe_devcoredump_snapshot *ss)
 
 #define XE_DEVCOREDUMP_CHUNK_MAX	(SZ_512M + SZ_1G)
 
+/**
+ * xe_devcoredump_read() - Read data from the Xe device coredump snapshot
+ * @buffer: Destination buffer to copy the coredump data into
+ * @offset: Offset in the coredump data to start reading from
+ * @count: Number of bytes to read
+ * @data: Pointer to the xe_devcoredump structure
+ * @datalen: Length of the data (unused)
+ *
+ * Reads a chunk of the coredump snapshot data into the provided buffer.
+ * If the devcoredump is smaller than 1.5 GB (XE_DEVCOREDUMP_CHUNK_MAX),
+ * it is read directly from a pre-written buffer. For larger devcoredumps,
+ * the pre-written buffer must be periodically repopulated from the snapshot
+ * state due to kmalloc size limitations.
+ *
+ * Return: Number of bytes copied on success, or a negative error code on failure.
+ */
 static ssize_t xe_devcoredump_read(char *buffer, loff_t offset,
 				   size_t count, void *data, size_t datalen)
 {
 	struct xe_devcoredump *coredump = data;
 	struct xe_devcoredump_snapshot *ss;
-	ssize_t byte_copied;
+	ssize_t byte_copied = 0;
 	u32 chunk_offset;
 	ssize_t new_chunk_position;
+	bool pm_needed = false;
+	int ret = 0;
 
 	if (!coredump)
 		return -ENODEV;
@@ -188,20 +206,19 @@ static ssize_t xe_devcoredump_read(char *buffer, loff_t offset,
 	/* Ensure delayed work is captured before continuing */
 	flush_work(&ss->work);
 
-	if (ss->read.size > XE_DEVCOREDUMP_CHUNK_MAX)
+	pm_needed = ss->read.size > XE_DEVCOREDUMP_CHUNK_MAX;
+	if (pm_needed)
 		xe_pm_runtime_get(gt_to_xe(ss->gt));
 
 	mutex_lock(&coredump->lock);
 
 	if (!ss->read.buffer) {
-		mutex_unlock(&coredump->lock);
-		return -ENODEV;
+		ret = -ENODEV;
+		goto unlock;
 	}
 
-	if (offset >= ss->read.size) {
-		mutex_unlock(&coredump->lock);
-		return 0;
-	}
+	if (offset >= ss->read.size)
+		goto unlock;
 
 	new_chunk_position = div_u64_rem(offset,
 					 XE_DEVCOREDUMP_CHUNK_MAX,
@@ -221,12 +238,13 @@ static ssize_t xe_devcoredump_read(char *buffer, loff_t offset,
 		ss->read.size - offset;
 	memcpy(buffer, ss->read.buffer + chunk_offset, byte_copied);
 
+unlock:
 	mutex_unlock(&coredump->lock);
 
-	if (ss->read.size > XE_DEVCOREDUMP_CHUNK_MAX)
+	if (pm_needed)
 		xe_pm_runtime_put(gt_to_xe(ss->gt));
 
-	return byte_copied;
+	return byte_copied ? byte_copied : ret;
 }
 
 static void xe_devcoredump_free(void *data)

From 0539c5eaf81f3f844213bf6b3137a53e5b04b083 Mon Sep 17 00:00:00 2001
From: Shuicheng Lin <shuicheng.lin@intel.com>
Date: Tue, 8 Jul 2025 02:14:51 +0000
Subject: [PATCH 1315/1334] drm/xe/pm: Correct comment of
 xe_pm_set_vram_threshold()

The parameter threshold is with size in MiB, not in bits.
Correct it to avoid any confusion.

v2: s/mb/MiB, s/vram/VRAM, fix return section. (Michal)

Fixes: 30c399529f4c ("drm/xe: Document Xe PM component")
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Shuicheng Lin <shuicheng.lin@intel.com>
Link: https://lore.kernel.org/r/20250708021450.3602087-2-shuicheng.lin@intel.com
Reviewed-by: Stuart Summers <stuart.summers@intel.com>
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
(cherry picked from commit 0efec0500117947f924e5ac83be40f96378af85a)
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
---
 drivers/gpu/drm/xe/xe_pm.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_pm.c b/drivers/gpu/drm/xe/xe_pm.c
index bcfda545e74f..ad263de44111 100644
--- a/drivers/gpu/drm/xe/xe_pm.c
+++ b/drivers/gpu/drm/xe/xe_pm.c
@@ -752,11 +752,13 @@ void xe_pm_assert_unbounded_bridge(struct xe_device *xe)
 }
 
 /**
- * xe_pm_set_vram_threshold - Set a vram threshold for allowing/blocking D3Cold
+ * xe_pm_set_vram_threshold - Set a VRAM threshold for allowing/blocking D3Cold
  * @xe: xe device instance
- * @threshold: VRAM size in bites for the D3cold threshold
+ * @threshold: VRAM size in MiB for the D3cold threshold
  *
- * Returns 0 for success, negative error code otherwise.
+ * Return:
+ * * 0		- success
+ * * -EINVAL	- invalid argument
  */
 int xe_pm_set_vram_threshold(struct xe_device *xe, u32 threshold)
 {

From 8c018805097f52d0d35fbc273b4e6dd154811638 Mon Sep 17 00:00:00 2001
From: Julia Filipchuk <julia.filipchuk@intel.com>
Date: Thu, 26 Jun 2025 11:28:10 -0700
Subject: [PATCH 1316/1334] drm/xe/guc: Recommend GuC v70.46.2 for BMG, LNL,
 DG2

UAPI compatibility version 1.22.2

Resolves various bugs. Recommend newer version.

Signed-off-by: Julia Filipchuk <julia.filipchuk@intel.com>
Reviewed-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Signed-off-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://lore.kernel.org/r/20250626182805.1701096-13-daniele.ceraolospurio@intel.com
(cherry picked from commit 0b64addcae7f04745bc5f62d41e27268052f812e)
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
---
 drivers/gpu/drm/xe/xe_uc_fw.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_uc_fw.c b/drivers/gpu/drm/xe/xe_uc_fw.c
index 2741849bbf4d..a6612105201a 100644
--- a/drivers/gpu/drm/xe/xe_uc_fw.c
+++ b/drivers/gpu/drm/xe/xe_uc_fw.c
@@ -114,10 +114,10 @@ struct fw_blobs_by_type {
 #define XE_GT_TYPE_ANY XE_GT_TYPE_UNINITIALIZED
 
 #define XE_GUC_FIRMWARE_DEFS(fw_def, mmp_ver, major_ver)					\
-	fw_def(BATTLEMAGE,	GT_TYPE_ANY,	major_ver(xe,	guc,	bmg,	70, 44, 1))	\
-	fw_def(LUNARLAKE,	GT_TYPE_ANY,	major_ver(xe,	guc,	lnl,	70, 44, 1))	\
+	fw_def(BATTLEMAGE,	GT_TYPE_ANY,	major_ver(xe,	guc,	bmg,	70, 45, 2))	\
+	fw_def(LUNARLAKE,	GT_TYPE_ANY,	major_ver(xe,	guc,	lnl,	70, 45, 2))	\
 	fw_def(METEORLAKE,	GT_TYPE_ANY,	major_ver(i915,	guc,	mtl,	70, 44, 1))	\
-	fw_def(DG2,		GT_TYPE_ANY,	major_ver(i915,	guc,	dg2,	70, 44, 1))	\
+	fw_def(DG2,		GT_TYPE_ANY,	major_ver(i915,	guc,	dg2,	70, 45, 2))	\
 	fw_def(DG1,		GT_TYPE_ANY,	major_ver(i915,	guc,	dg1,	70, 44, 1))	\
 	fw_def(ALDERLAKE_N,	GT_TYPE_ANY,	major_ver(i915,	guc,	tgl,	70, 44, 1))	\
 	fw_def(ALDERLAKE_P,	GT_TYPE_ANY,	major_ver(i915,	guc,	adlp,	70, 44, 1))	\

From 7a10175a4220b3f77d74a61ef767f6c43bf39a3e Mon Sep 17 00:00:00 2001
From: Michal Wajdeczko <michal.wajdeczko@intel.com>
Date: Thu, 10 Jul 2025 10:30:39 +0000
Subject: [PATCH 1317/1334] drm/xe/bmg: Don't use WA 16023588340 and
 22019338487 on VF

These workarounds are not applicable for use by the VFs.

Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Tested-by: Jakub Kolakowski <jakub1.kolakowski@intel.com>
Reviewed-by: Satyanarayana K V P <satyanarayana.k.v.p@intel.com>
Signed-off-by: Jakub Kolakowski <jakub1.kolakowski@intel.com>
Link: https://lore.kernel.org/r/20250710103040.375610-2-jakub1.kolakowski@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
(cherry picked from commit 1d2e2503e506ddc499cbb7afdc8b70bcf6fe241f)
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
---
 drivers/gpu/drm/xe/xe_wa_oob.rules | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_wa_oob.rules b/drivers/gpu/drm/xe/xe_wa_oob.rules
index 69c1d7fc695e..6d70109fcc43 100644
--- a/drivers/gpu/drm/xe/xe_wa_oob.rules
+++ b/drivers/gpu/drm/xe/xe_wa_oob.rules
@@ -38,10 +38,10 @@
 		GRAPHICS_VERSION(2004)
 		GRAPHICS_VERSION_RANGE(3000, 3001)
 22019338487	MEDIA_VERSION(2000)
-		GRAPHICS_VERSION(2001)
+		GRAPHICS_VERSION(2001), FUNC(xe_rtp_match_not_sriov_vf)
 		MEDIA_VERSION(3000), MEDIA_STEP(A0, B0), FUNC(xe_rtp_match_not_sriov_vf)
 22019338487_display	PLATFORM(LUNARLAKE)
-16023588340	GRAPHICS_VERSION(2001)
+16023588340	GRAPHICS_VERSION(2001), FUNC(xe_rtp_match_not_sriov_vf)
 14019789679	GRAPHICS_VERSION(1255)
 		GRAPHICS_VERSION_RANGE(1270, 2004)
 no_media_l3	MEDIA_VERSION(3000)

From 74806f69b8668ea0e98cd9d461b7803ffa1fcdf3 Mon Sep 17 00:00:00 2001
From: Lucas De Marchi <lucas.demarchi@intel.com>
Date: Fri, 13 Jun 2025 13:00:37 -0700
Subject: [PATCH 1318/1334] drm/xe/guc: Default log level to non-verbose

Currently xe sets the guc log level to a verbose level since it's useful
to debug hangs and general development. However the verbose level may
already be too much and affect performance.

Michal Mrozek did some tests with the L0 compute stack for submission
latency with ULLS disabled. Below are the normalized numbers with log
level 3 (the current default) as baseline for each test:

                          Test \ Log Level                        3      0      1      2
 ----------------------------------------------------------- ------ ------ ------ ------
  BestWalkerNthCommandListSubmission(CmdListCount=2)           1.00   0.63   0.63   0.96
  BestWalkerNthSubmission(KernelCount=2)                       1.00   0.62   0.63   0.96
  BestWalkerNthSubmissionImmediate(KernelCount=2)              1.00   0.58   0.58   0.85
  BestWalkerSubmission                                         1.00   0.62   0.62   0.96
  BestWalkerSubmissionImmediate                                1.00   0.63   0.62   0.96
  BestWalkerSubmissionImmediateMultiCmdlists(cmdlistCount=2)   1.00   0.58   0.58   0.86
  BestWalkerSubmissionImmediateMultiCmdlists(cmdlistCount=4)   1.00   0.70   0.70   0.83
  BestWalkerSubmissionImmediateMultiCmdlists(cmdlistCount=8)   1.00   0.53   0.52   0.78

Log level 2 is the first "verbose level" for GuC, where the biggest
difference happens. Keep log level 3 for CONFIG_DRM_XE_DEBUG, but switch
to 1, i.e.  GUC_LOG_LEVEL_NON_VERBOSE, for "normal" builds.

Cc: Michal Mrozek <michal.mrozek@intel.com>
Cc: John Harrison <John.C.Harrison@Intel.com>
Reviewed-by: John Harrison <John.C.Harrison@Intel.com>
Link: https://lore.kernel.org/r/20250613-guc-log-level-v2-1-cb84a63e49fe@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
(cherry picked from commit a37128ba613ad6a5f81f382fa3cfe5c4a6527310)
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
---
 drivers/gpu/drm/xe/xe_module.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/xe/xe_module.c b/drivers/gpu/drm/xe/xe_module.c
index e4742e27e2cd..da6793c2f991 100644
--- a/drivers/gpu/drm/xe/xe_module.c
+++ b/drivers/gpu/drm/xe/xe_module.c
@@ -20,7 +20,7 @@
 
 struct xe_modparam xe_modparam = {
 	.probe_display = true,
-	.guc_log_level = 3,
+	.guc_log_level = IS_ENABLED(CONFIG_DRM_XE_DEBUG) ? 3 : 1,
 	.force_probe = CONFIG_DRM_XE_FORCE_PROBE,
 	.wedged_mode = 1,
 	.svm_notifier_size = 512,

From edb471108cf1477c44b95e87e8cec261825eb079 Mon Sep 17 00:00:00 2001
From: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Date: Wed, 9 Jul 2025 09:18:24 +0200
Subject: [PATCH 1319/1334] MAINTAINERS: remove bouncing address for Nandor Han

Nandor's address has been bouncing for some time now. Remove it from
MAINTAINERS. The affected driver falls under the wider umbrella of GPIO
modules.

Link: https://lore.kernel.org/r/20250709071825.16212-1-brgl@bgdev.pl
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
---
 MAINTAINERS | 7 -------
 1 file changed, 7 deletions(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 4bac4ea21b64..ac983cb1663d 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -27309,13 +27309,6 @@ S:	Supported
 W:	http://www.marvell.com
 F:	drivers/i2c/busses/i2c-xlp9xx.c
 
-XRA1403 GPIO EXPANDER
-M:	Nandor Han <nandor.han@ge.com>
-L:	linux-gpio@vger.kernel.org
-S:	Maintained
-F:	Documentation/devicetree/bindings/gpio/gpio-xra1403.txt
-F:	drivers/gpio/gpio-xra1403.c
-
 XTENSA XTFPGA PLATFORM SUPPORT
 M:	Max Filippov <jcmvbkbc@gmail.com>
 S:	Maintained

From 58805e9cbc6f6a28f35d90e740956e983a0e036e Mon Sep 17 00:00:00 2001
From: Sean Nyekjaer <sean@geanix.com>
Date: Fri, 11 Jul 2025 12:12:02 +0200
Subject: [PATCH 1320/1334] can: m_can: m_can_handle_lost_msg(): downgrade msg
 lost in rx message to debug level

Downgrade the "msg lost in rx" message to debug level, to prevent
flooding the kernel log with error messages.

Fixes: e0d1f4816f2a ("can: m_can: add Bosch M_CAN controller support")
Reviewed-by: Vincent Mailhol <mailhol.vincent@wanadoo.fr>
Signed-off-by: Sean Nyekjaer <sean@geanix.com>
Link: https://patch.msgid.link/20250711-mcan_ratelimit-v3-1-7413e8e21b84@geanix.com
[mkl: enhance commit message]
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/m_can/m_can.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/can/m_can/m_can.c b/drivers/net/can/m_can/m_can.c
index 6c656bfdb323..fe74dbd2c966 100644
--- a/drivers/net/can/m_can/m_can.c
+++ b/drivers/net/can/m_can/m_can.c
@@ -665,7 +665,7 @@ static int m_can_handle_lost_msg(struct net_device *dev)
 	struct can_frame *frame;
 	u32 timestamp = 0;
 
-	netdev_err(dev, "msg lost in rxf0\n");
+	netdev_dbg(dev, "msg lost in rxf0\n");
 
 	stats->rx_errors++;
 	stats->rx_over_errors++;

From cb73e53f7c0700285d743e7afbe37cba9f7df8f3 Mon Sep 17 00:00:00 2001
From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Date: Tue, 8 Jul 2025 13:19:22 +0300
Subject: [PATCH 1321/1334] MAINTAINERS: Update Kirill Shutemov's email address
 for TDX

Update MAINTAINERS to use my @kernel.org email address.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Link: https://lore.kernel.org/all/20250708101922.50560-4-kirill.shutemov%40linux.intel.com
---
 .mailmap    | 1 +
 MAINTAINERS | 2 +-
 2 files changed, 2 insertions(+), 1 deletion(-)

diff --git a/.mailmap b/.mailmap
index b0ace71968ab..85ad46d20220 100644
--- a/.mailmap
+++ b/.mailmap
@@ -416,6 +416,7 @@ Kenneth W Chen <kenneth.w.chen@intel.com>
 Kenneth Westfield <quic_kwestfie@quicinc.com> <kwestfie@codeaurora.org>
 Kiran Gunda <quic_kgunda@quicinc.com> <kgunda@codeaurora.org>
 Kirill Tkhai <tkhai@ya.ru> <ktkhai@virtuozzo.com>
+Kirill A. Shutemov <kas@kernel.org> <kirill.shutemov@linux.intel.com>
 Kishon Vijay Abraham I <kishon@kernel.org> <kishon@ti.com>
 Konrad Dybcio <konradybcio@kernel.org> <konrad.dybcio@linaro.org>
 Konrad Dybcio <konradybcio@kernel.org> <konrad.dybcio@somainline.org>
diff --git a/MAINTAINERS b/MAINTAINERS
index fad6cb025a19..adaf349fa4b1 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -26944,7 +26944,7 @@ F:	arch/x86/kernel/stacktrace.c
 F:	arch/x86/kernel/unwind_*.c
 
 X86 TRUST DOMAIN EXTENSIONS (TDX)
-M:	Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
+M:	Kirill A. Shutemov <kas@kernel.org>
 R:	Dave Hansen <dave.hansen@linux.intel.com>
 L:	x86@kernel.org
 L:	linux-coco@lists.linux.dev

From f7b76466894083c8f518cf29fef75fcd3ec670e5 Mon Sep 17 00:00:00 2001
From: Carolina Jubran <cjubran@nvidia.com>
Date: Thu, 10 Jul 2025 16:53:42 +0300
Subject: [PATCH 1322/1334] net/mlx5: Reset bw_share field when changing a
 node's parent

When changing a node's parent, its scheduling element is destroyed and
re-created with bw_share 0. However, the node's bw_share field was not
updated accordingly.

Set the node's bw_share to 0 after re-creation to keep the software
state in sync with the firmware configuration.

Fixes: 9c7bbf4c3304 ("net/mlx5: Add support for setting parent of nodes")
Signed-off-by: Carolina Jubran <cjubran@nvidia.com>
Reviewed-by: Cosmin Ratiu <cratiu@nvidia.com>
Reviewed-by: Dragos Tatulea <dtatulea@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://patch.msgid.link/1752155624-24095-2-git-send-email-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c
index b6ae384396b3..ad9f6fca9b6a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c
@@ -1076,6 +1076,7 @@ static int esw_qos_vports_node_update_parent(struct mlx5_esw_sched_node *node,
 		return err;
 	}
 	esw_qos_node_set_parent(node, parent);
+	node->bw_share = 0;
 
 	return 0;
 }

From eb41a264a3a576dc040ee37c3d9d6b7e2d9be968 Mon Sep 17 00:00:00 2001
From: Carolina Jubran <cjubran@nvidia.com>
Date: Thu, 10 Jul 2025 16:53:43 +0300
Subject: [PATCH 1323/1334] net/mlx5e: Fix race between DIM disable and
 net_dim()

There's a race between disabling DIM and NAPI callbacks using the dim
pointer on the RQ or SQ.

If NAPI checks the DIM state bit and sees it still set, it assumes
`rq->dim` or `sq->dim` is valid. But if DIM gets disabled right after
that check, the pointer might already be set to NULL, leading to a NULL
pointer dereference in net_dim().

Fix this by calling `synchronize_net()` before freeing the DIM context.
This ensures all in-progress NAPI callbacks are finished before the
pointer is cleared.

Kernel log:

BUG: kernel NULL pointer dereference, address: 0000000000000000
...
RIP: 0010:net_dim+0x23/0x190
...
Call Trace:
 <TASK>
 ? __die+0x20/0x60
 ? page_fault_oops+0x150/0x3e0
 ? common_interrupt+0xf/0xa0
 ? sysvec_call_function_single+0xb/0x90
 ? exc_page_fault+0x74/0x130
 ? asm_exc_page_fault+0x22/0x30
 ? net_dim+0x23/0x190
 ? mlx5e_poll_ico_cq+0x41/0x6f0 [mlx5_core]
 ? sysvec_apic_timer_interrupt+0xb/0x90
 mlx5e_handle_rx_dim+0x92/0xd0 [mlx5_core]
 mlx5e_napi_poll+0x2cd/0xac0 [mlx5_core]
 ? mlx5e_poll_ico_cq+0xe5/0x6f0 [mlx5_core]
 busy_poll_stop+0xa2/0x200
 ? mlx5e_napi_poll+0x1d9/0xac0 [mlx5_core]
 ? mlx5e_trigger_irq+0x130/0x130 [mlx5_core]
 __napi_busy_loop+0x345/0x3b0
 ? sysvec_call_function_single+0xb/0x90
 ? asm_sysvec_call_function_single+0x16/0x20
 ? sysvec_apic_timer_interrupt+0xb/0x90
 ? pcpu_free_area+0x1e4/0x2e0
 napi_busy_loop+0x11/0x20
 xsk_recvmsg+0x10c/0x130
 sock_recvmsg+0x44/0x70
 __sys_recvfrom+0xbc/0x130
 ? __schedule+0x398/0x890
 __x64_sys_recvfrom+0x20/0x30
 do_syscall_64+0x4c/0x100
 entry_SYSCALL_64_after_hwframe+0x4b/0x53
...
---[ end trace 0000000000000000 ]---
...
---[ end Kernel panic - not syncing: Fatal exception in interrupt ]---

Fixes: 445a25f6e1a2 ("net/mlx5e: Support updating coalescing configuration without resetting channels")
Signed-off-by: Carolina Jubran <cjubran@nvidia.com>
Reviewed-by: Cosmin Ratiu <cratiu@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://patch.msgid.link/1752155624-24095-3-git-send-email-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_dim.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_dim.c b/drivers/net/ethernet/mellanox/mlx5/core/en_dim.c
index 298bb74ec5e9..d1d629697e28 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_dim.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_dim.c
@@ -113,7 +113,7 @@ int mlx5e_dim_rx_change(struct mlx5e_rq *rq, bool enable)
 		__set_bit(MLX5E_RQ_STATE_DIM, &rq->state);
 	} else {
 		__clear_bit(MLX5E_RQ_STATE_DIM, &rq->state);
-
+		synchronize_net();
 		mlx5e_dim_disable(rq->dim);
 		rq->dim = NULL;
 	}
@@ -140,7 +140,7 @@ int mlx5e_dim_tx_change(struct mlx5e_txqsq *sq, bool enable)
 		__set_bit(MLX5E_SQ_STATE_DIM, &sq->state);
 	} else {
 		__clear_bit(MLX5E_SQ_STATE_DIM, &sq->state);
-
+		synchronize_net();
 		mlx5e_dim_disable(sq->dim);
 		sq->dim = NULL;
 	}

From 4c9fce56fa702059bbc5ab737265b68f79cbaac4 Mon Sep 17 00:00:00 2001
From: Jianbo Liu <jianbol@nvidia.com>
Date: Thu, 10 Jul 2025 16:53:44 +0300
Subject: [PATCH 1324/1334] net/mlx5e: Add new prio for promiscuous mode

An optimization for promiscuous mode adds a high-priority steering
table with a single catch-all rule to steer all traffic directly to
the TTC table.

However, a gap exists between the creation of this table and the
insertion of the catch-all rule. Packets arriving in this brief window
would miss as no rule was inserted yet, unnecessarily incrementing the
'rx_steer_missed_packets' counter and dropped.

This patch resolves the issue by introducing a new prio for this
table, placing it between MLX5E_TC_PRIO and MLX5E_NIC_PRIO. By doing
so, packets arriving during the window now fall through to the next
prio (at MLX5E_NIC_PRIO) instead of being dropped.

Fixes: 1c46d7409f30 ("net/mlx5e: Optimize promiscuous mode")
Signed-off-by: Jianbo Liu <jianbol@nvidia.com>
Reviewed-by: Mark Bloch <mbloch@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://patch.msgid.link/1752155624-24095-4-git-send-email-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/en/fs.h   |  9 +++++++--
 drivers/net/ethernet/mellanox/mlx5/core/en_fs.c   |  2 +-
 drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 13 +++++++++----
 3 files changed, 17 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h
index b5c3a2a9d2a5..9560fcba643f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h
@@ -18,7 +18,8 @@ enum {
 
 enum {
 	MLX5E_TC_PRIO = 0,
-	MLX5E_NIC_PRIO
+	MLX5E_PROMISC_PRIO,
+	MLX5E_NIC_PRIO,
 };
 
 struct mlx5e_flow_table {
@@ -68,9 +69,13 @@ struct mlx5e_l2_table {
 				 MLX5_HASH_FIELD_SEL_DST_IP   |\
 				 MLX5_HASH_FIELD_SEL_IPSEC_SPI)
 
-/* NIC prio FTS */
+/* NIC promisc FT level */
 enum {
 	MLX5E_PROMISC_FT_LEVEL,
+};
+
+/* NIC prio FTS */
+enum {
 	MLX5E_VLAN_FT_LEVEL,
 	MLX5E_L2_FT_LEVEL,
 	MLX5E_TTC_FT_LEVEL,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
index 04a969128161..265c4ca85f7d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
@@ -780,7 +780,7 @@ static int mlx5e_create_promisc_table(struct mlx5e_flow_steering *fs)
 	ft_attr.max_fte = MLX5E_PROMISC_TABLE_SIZE;
 	ft_attr.autogroup.max_num_groups = 1;
 	ft_attr.level = MLX5E_PROMISC_FT_LEVEL;
-	ft_attr.prio = MLX5E_NIC_PRIO;
+	ft_attr.prio = MLX5E_PROMISC_PRIO;
 
 	ft->t = mlx5_create_auto_grouped_flow_table(fs->ns, &ft_attr);
 	if (IS_ERR(ft->t)) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index a8046200d376..3dd9a6f40709 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -113,13 +113,16 @@
 #define ETHTOOL_PRIO_NUM_LEVELS 1
 #define ETHTOOL_NUM_PRIOS 11
 #define ETHTOOL_MIN_LEVEL (KERNEL_MIN_LEVEL + ETHTOOL_NUM_PRIOS)
-/* Promiscuous, Vlan, mac, ttc, inner ttc, {UDP/ANY/aRFS/accel/{esp, esp_err}}, IPsec policy,
+/* Vlan, mac, ttc, inner ttc, {UDP/ANY/aRFS/accel/{esp, esp_err}}, IPsec policy,
  * {IPsec RoCE MPV,Alias table},IPsec RoCE policy
  */
-#define KERNEL_NIC_PRIO_NUM_LEVELS 11
+#define KERNEL_NIC_PRIO_NUM_LEVELS 10
 #define KERNEL_NIC_NUM_PRIOS 1
-/* One more level for tc */
-#define KERNEL_MIN_LEVEL (KERNEL_NIC_PRIO_NUM_LEVELS + 1)
+/* One more level for tc, and one more for promisc */
+#define KERNEL_MIN_LEVEL (KERNEL_NIC_PRIO_NUM_LEVELS + 2)
+
+#define KERNEL_NIC_PROMISC_NUM_PRIOS 1
+#define KERNEL_NIC_PROMISC_NUM_LEVELS 1
 
 #define KERNEL_NIC_TC_NUM_PRIOS  1
 #define KERNEL_NIC_TC_NUM_LEVELS 3
@@ -187,6 +190,8 @@ static struct init_tree_node {
 			   ADD_NS(MLX5_FLOW_TABLE_MISS_ACTION_DEF,
 				  ADD_MULTIPLE_PRIO(KERNEL_NIC_TC_NUM_PRIOS,
 						    KERNEL_NIC_TC_NUM_LEVELS),
+				  ADD_MULTIPLE_PRIO(KERNEL_NIC_PROMISC_NUM_PRIOS,
+						    KERNEL_NIC_PROMISC_NUM_LEVELS),
 				  ADD_MULTIPLE_PRIO(KERNEL_NIC_NUM_PRIOS,
 						    KERNEL_NIC_PRIO_NUM_LEVELS))),
 		  ADD_PRIO(0, BY_PASS_MIN_LEVEL, 0, FS_CHAINING_CAPS,

From e81750b4e3826fedce7362dad839cb40384d60ae Mon Sep 17 00:00:00 2001
From: Alok Tiwari <alok.a.tiwari@oracle.com>
Date: Thu, 10 Jul 2025 11:06:17 -0700
Subject: [PATCH 1325/1334] net: ll_temac: Fix missing tx_pending check in
 ethtools_set_ringparam()

The function ll_temac_ethtools_set_ringparam() incorrectly checked
rx_pending twice, once correctly for RX and once mistakenly in place
of tx_pending. This caused tx_pending to be left unchecked against
TX_BD_NUM_MAX.
As a result, invalid TX ring sizes may have been accepted or valid
ones wrongly rejected based on the RX limit, leading to potential
misconfiguration or unexpected results.

This patch corrects the condition to properly validate tx_pending.

Fixes: f7b261bfc35e ("net: ll_temac: Make RX/TX ring sizes configurable")
Signed-off-by: Alok Tiwari <alok.a.tiwari@oracle.com>
Link: https://patch.msgid.link/20250710180621.2383000-1-alok.a.tiwari@oracle.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/xilinx/ll_temac_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/xilinx/ll_temac_main.c b/drivers/net/ethernet/xilinx/ll_temac_main.c
index edb36ff07a0c..6f82203a414c 100644
--- a/drivers/net/ethernet/xilinx/ll_temac_main.c
+++ b/drivers/net/ethernet/xilinx/ll_temac_main.c
@@ -1309,7 +1309,7 @@ ll_temac_ethtools_set_ringparam(struct net_device *ndev,
 	if (ering->rx_pending > RX_BD_NUM_MAX ||
 	    ering->rx_mini_pending ||
 	    ering->rx_jumbo_pending ||
-	    ering->rx_pending > TX_BD_NUM_MAX)
+	    ering->tx_pending > TX_BD_NUM_MAX)
 		return -EINVAL;
 
 	if (netif_running(ndev))

From b74c2a2e9cc471e847abd87e50a2354c07e02040 Mon Sep 17 00:00:00 2001
From: Shravya KN <shravya.k-n@broadcom.com>
Date: Thu, 10 Jul 2025 14:39:36 -0700
Subject: [PATCH 1326/1334] bnxt_en: Fix DCB ETS validation

In bnxt_ets_validate(), the code incorrectly loops over all possible
traffic classes to check and add the ETS settings.  Fix it to loop
over the configured traffic classes only.

The unconfigured traffic classes will default to TSA_ETS with 0
bandwidth.  Looping over these unconfigured traffic classes may
cause the validation to fail and trigger this error message:

"rejecting ETS config starving a TC\n"

The .ieee_setets() will then fail.

Fixes: 7df4ae9fe855 ("bnxt_en: Implement DCBNL to support host-based DCBX.")
Reviewed-by: Sreekanth Reddy <sreekanth.reddy@broadcom.com>
Signed-off-by: Shravya KN <shravya.k-n@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Link: https://patch.msgid.link/20250710213938.1959625-2-michael.chan@broadcom.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c
index 0dbb880a7aa0..71e14be2507e 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c
@@ -487,7 +487,9 @@ static int bnxt_ets_validate(struct bnxt *bp, struct ieee_ets *ets, u8 *tc)
 
 		if ((ets->tc_tx_bw[i] || ets->tc_tsa[i]) && i > bp->max_tc)
 			return -EINVAL;
+	}
 
+	for (i = 0; i < max_tc; i++) {
 		switch (ets->tc_tsa[i]) {
 		case IEEE_8021QAZ_TSA_STRICT:
 			break;

From 100c08c89d173b7fdf953e7d9f9ca8f69f80d1c5 Mon Sep 17 00:00:00 2001
From: Shruti Parab <shruti.parab@broadcom.com>
Date: Thu, 10 Jul 2025 14:39:37 -0700
Subject: [PATCH 1327/1334] bnxt_en: Flush FW trace before copying to the
 coredump

bnxt_fill_drv_seg_record() calls bnxt_dbg_hwrm_log_buffer_flush()
to flush the FW trace buffer.  This needs to be done before we
call bnxt_copy_ctx_mem() to copy the trace data.

Without this fix, the coredump may not contain all the FW
traces.

Fixes: 3c2179e66355 ("bnxt_en: Add FW trace coredump segments to the coredump")
Reviewed-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Signed-off-by: Shruti Parab <shruti.parab@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Link: https://patch.msgid.link/20250710213938.1959625-3-michael.chan@broadcom.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/ethernet/broadcom/bnxt/bnxt_coredump.c | 18 +++++++++++-------
 1 file changed, 11 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_coredump.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_coredump.c
index ce97befd3cb3..67e70d3d0980 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_coredump.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_coredump.c
@@ -368,23 +368,27 @@ static u32 bnxt_get_ctx_coredump(struct bnxt *bp, void *buf, u32 offset,
 		if (!ctxm->mem_valid || !seg_id)
 			continue;
 
-		if (trace)
+		if (trace) {
 			extra_hlen = BNXT_SEG_RCD_LEN;
+			if (buf) {
+				u16 trace_type = bnxt_bstore_to_trace[type];
+
+				bnxt_fill_drv_seg_record(bp, &record, ctxm,
+							 trace_type);
+			}
+		}
+
 		if (buf)
 			data = buf + BNXT_SEG_HDR_LEN + extra_hlen;
+
 		seg_len = bnxt_copy_ctx_mem(bp, ctxm, data, 0) + extra_hlen;
 		if (buf) {
 			bnxt_fill_coredump_seg_hdr(bp, &seg_hdr, NULL, seg_len,
 						   0, 0, 0, comp_id, seg_id);
 			memcpy(buf, &seg_hdr, BNXT_SEG_HDR_LEN);
 			buf += BNXT_SEG_HDR_LEN;
-			if (trace) {
-				u16 trace_type = bnxt_bstore_to_trace[type];
-
-				bnxt_fill_drv_seg_record(bp, &record, ctxm,
-							 trace_type);
+			if (trace)
 				memcpy(buf, &record, BNXT_SEG_RCD_LEN);
-			}
 			buf += seg_len;
 		}
 		len += BNXT_SEG_HDR_LEN + seg_len;

From 3cdf199d4755d477972ee87110b2aebc88b3cfad Mon Sep 17 00:00:00 2001
From: Somnath Kotur <somnath.kotur@broadcom.com>
Date: Thu, 10 Jul 2025 14:39:38 -0700
Subject: [PATCH 1328/1334] bnxt_en: Set DMA unmap len correctly for
 XDP_REDIRECT

When transmitting an XDP_REDIRECT packet, call dma_unmap_len_set()
with the proper length instead of 0.  This bug triggers this warning
on a system with IOMMU enabled:

WARNING: CPU: 36 PID: 0 at drivers/iommu/dma-iommu.c:842 __iommu_dma_unmap+0x159/0x170
RIP: 0010:__iommu_dma_unmap+0x159/0x170
Code: a8 00 00 00 00 48 c7 45 b0 00 00 00 00 48 c7 45 c8 00 00 00 00 48 c7 45 a0 ff ff ff ff 4c 89 45
b8 4c 89 45 c0 e9 77 ff ff ff <0f> 0b e9 60 ff ff ff e8 8b bf 6a 00 66 66 2e 0f 1f 84 00 00 00 00
RSP: 0018:ff22d31181150c88 EFLAGS: 00010206
RAX: 0000000000002000 RBX: 00000000e13a0000 RCX: 0000000000000000
RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000
RBP: ff22d31181150cf0 R08: ff22d31181150ca8 R09: 0000000000000000
R10: 0000000000000000 R11: ff22d311d36c9d80 R12: 0000000000001000
R13: ff13544d10645010 R14: ff22d31181150c90 R15: ff13544d0b2bac00
FS: 0000000000000000(0000) GS:ff13550908a00000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00005be909dacff8 CR3: 0008000173408003 CR4: 0000000000f71ef0
PKRU: 55555554
Call Trace:
<IRQ>
? show_regs+0x6d/0x80
? __warn+0x89/0x160
? __iommu_dma_unmap+0x159/0x170
? report_bug+0x17e/0x1b0
? handle_bug+0x46/0x90
? exc_invalid_op+0x18/0x80
? asm_exc_invalid_op+0x1b/0x20
? __iommu_dma_unmap+0x159/0x170
? __iommu_dma_unmap+0xb3/0x170
iommu_dma_unmap_page+0x4f/0x100
dma_unmap_page_attrs+0x52/0x220
? srso_alias_return_thunk+0x5/0xfbef5
? xdp_return_frame+0x2e/0xd0
bnxt_tx_int_xdp+0xdf/0x440 [bnxt_en]
__bnxt_poll_work_done+0x81/0x1e0 [bnxt_en]
bnxt_poll+0xd3/0x1e0 [bnxt_en]

Fixes: f18c2b77b2e4 ("bnxt_en: optimized XDP_REDIRECT support")
Signed-off-by: Somnath Kotur <somnath.kotur@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Link: https://patch.msgid.link/20250710213938.1959625-4-michael.chan@broadcom.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
index 4a6d8cb9f970..09e7e8efa6fa 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
@@ -115,7 +115,7 @@ static void __bnxt_xmit_xdp_redirect(struct bnxt *bp,
 	tx_buf->action = XDP_REDIRECT;
 	tx_buf->xdpf = xdpf;
 	dma_unmap_addr_set(tx_buf, mapping, mapping);
-	dma_unmap_len_set(tx_buf, len, 0);
+	dma_unmap_len_set(tx_buf, len, len);
 }
 
 void bnxt_tx_int_xdp(struct bnxt *bp, struct bnxt_napi *bnapi, int budget)

From a3c4a125ec725cefb40047eb05ff9eafd57830b4 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@google.com>
Date: Fri, 11 Jul 2025 05:32:07 +0000
Subject: [PATCH 1329/1334] netlink: Fix rmem check in
 netlink_broadcast_deliver().

We need to allow queuing at least one skb even when skb is
larger than sk->sk_rcvbuf.

The cited commit made a mistake while converting a condition
in netlink_broadcast_deliver().

Let's correct the rmem check for the allow-one-skb rule.

Fixes: ae8f160e7eb24 ("netlink: Fix wraparounds of sk->sk_rmem_alloc.")
Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Link: https://patch.msgid.link/20250711053208.2965945-1-kuniyu@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/netlink/af_netlink.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 79fbaf7333ce..2d107a8a75d9 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -1395,7 +1395,7 @@ static int netlink_broadcast_deliver(struct sock *sk, struct sk_buff *skb)
 	rmem = atomic_add_return(skb->truesize, &sk->sk_rmem_alloc);
 	rcvbuf = READ_ONCE(sk->sk_rcvbuf);
 
-	if ((rmem != skb->truesize || rmem <= rcvbuf) &&
+	if ((rmem == skb->truesize || rmem <= rcvbuf) &&
 	    !test_bit(NETLINK_S_CONGESTED, &nlk->state)) {
 		netlink_skb_set_owner_r(skb, sk);
 		__netlink_sendskb(sk, skb);

From a215b5723922f8099078478122f02100e489cb80 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Thu, 10 Jul 2025 17:11:21 -0700
Subject: [PATCH 1330/1334] netlink: make sure we allow at least one dump skb

Commit under Fixes tightened up the memory accounting for Netlink
sockets. Looks like the accounting is too strict for some existing
use cases, Marek reported issues with nl80211 / WiFi iw CLI.

To reduce number of iterations Netlink dumps try to allocate
messages based on the size of the buffer passed to previous
recvmsg() calls. If user space uses a larger buffer in recvmsg()
than sk_rcvbuf we will allocate an skb we won't be able to queue.

Make sure we always allow at least one skb to be queued.
Same workaround is already present in netlink_attachskb().
Alternative would be to cap the allocation size to
  rcvbuf - rmem_alloc
but as I said, the workaround is already present in other places.

Reported-by: Marek Szyprowski <m.szyprowski@samsung.com>
Link: https://lore.kernel.org/9794af18-4905-46c6-b12c-365ea2f05858@samsung.com
Fixes: ae8f160e7eb2 ("netlink: Fix wraparounds of sk->sk_rmem_alloc.")
Tested-by: Marek Szyprowski <m.szyprowski@samsung.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com>
Link: https://patch.msgid.link/20250711001121.3649033-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/netlink/af_netlink.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 2d107a8a75d9..6332a0e06596 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -2258,11 +2258,11 @@ static int netlink_dump(struct sock *sk, bool lock_taken)
 	struct netlink_ext_ack extack = {};
 	struct netlink_callback *cb;
 	struct sk_buff *skb = NULL;
+	unsigned int rmem, rcvbuf;
 	size_t max_recvmsg_len;
 	struct module *module;
 	int err = -ENOBUFS;
 	int alloc_min_size;
-	unsigned int rmem;
 	int alloc_size;
 
 	if (!lock_taken)
@@ -2294,8 +2294,9 @@ static int netlink_dump(struct sock *sk, bool lock_taken)
 	if (!skb)
 		goto errout_skb;
 
+	rcvbuf = READ_ONCE(sk->sk_rcvbuf);
 	rmem = atomic_add_return(skb->truesize, &sk->sk_rmem_alloc);
-	if (rmem >= READ_ONCE(sk->sk_rcvbuf)) {
+	if (rmem != skb->truesize && rmem >= rcvbuf) {
 		atomic_sub(skb->truesize, &sk->sk_rmem_alloc);
 		goto errout_skb;
 	}

From b44686c8391b427fb1c85a31c35077e6947c6d90 Mon Sep 17 00:00:00 2001
From: Gao Xiang <hsiangkao@linux.alibaba.com>
Date: Sat, 12 Jul 2025 03:58:26 +0800
Subject: [PATCH 1331/1334] erofs: fix large fragment handling

Fragments aren't limited by Z_EROFS_PCLUSTER_MAX_DSIZE. However, if
a fragment's logical length is larger than Z_EROFS_PCLUSTER_MAX_DSIZE
but the fragment is not the whole inode, it currently returns
-EOPNOTSUPP because m_flags has the wrong EROFS_MAP_ENCODED flag set.
It is not intended by design but should be rare, as it can only be
reproduced by mkfs with `-Eall-fragments` in a specific case.

Let's normalize fragment m_flags using the new EROFS_MAP_FRAGMENT.

Reported-by: Axel Fontaine <axel@axelfontaine.com>
Closes: https://github.com/erofs/erofs-utils/issues/23
Fixes: 7c3ca1838a78 ("erofs: restrict pcluster size limitations")
Signed-off-by: Gao Xiang <hsiangkao@linux.alibaba.com>
Link: https://lore.kernel.org/r/20250711195826.3601157-1-hsiangkao@linux.alibaba.com
---
 fs/erofs/internal.h | 4 +++-
 fs/erofs/zdata.c    | 2 +-
 fs/erofs/zmap.c     | 9 ++++-----
 3 files changed, 8 insertions(+), 7 deletions(-)

diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h
index 0d19bde8c094..06b867d2fc3b 100644
--- a/fs/erofs/internal.h
+++ b/fs/erofs/internal.h
@@ -315,10 +315,12 @@ static inline struct folio *erofs_grab_folio_nowait(struct address_space *as,
 /* The length of extent is full */
 #define EROFS_MAP_FULL_MAPPED	0x0008
 /* Located in the special packed inode */
-#define EROFS_MAP_FRAGMENT	0x0010
+#define __EROFS_MAP_FRAGMENT	0x0010
 /* The extent refers to partial decompressed data */
 #define EROFS_MAP_PARTIAL_REF	0x0020
 
+#define EROFS_MAP_FRAGMENT	(EROFS_MAP_MAPPED | __EROFS_MAP_FRAGMENT)
+
 struct erofs_map_blocks {
 	struct erofs_buf buf;
 
diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c
index 32e3905e75fe..e3f28a1bb945 100644
--- a/fs/erofs/zdata.c
+++ b/fs/erofs/zdata.c
@@ -1034,7 +1034,7 @@ static int z_erofs_scan_folio(struct z_erofs_frontend *f,
 		if (!(map->m_flags & EROFS_MAP_MAPPED)) {
 			folio_zero_segment(folio, cur, end);
 			tight = false;
-		} else if (map->m_flags & EROFS_MAP_FRAGMENT) {
+		} else if (map->m_flags & __EROFS_MAP_FRAGMENT) {
 			erofs_off_t fpos = offset + cur - map->m_la;
 
 			err = z_erofs_read_fragment(inode->i_sb, folio, cur,
diff --git a/fs/erofs/zmap.c b/fs/erofs/zmap.c
index 0bebc6e3a4d7..f1a15ff22147 100644
--- a/fs/erofs/zmap.c
+++ b/fs/erofs/zmap.c
@@ -413,8 +413,7 @@ static int z_erofs_map_blocks_fo(struct inode *inode,
 	    !vi->z_tailextent_headlcn) {
 		map->m_la = 0;
 		map->m_llen = inode->i_size;
-		map->m_flags = EROFS_MAP_MAPPED |
-			EROFS_MAP_FULL_MAPPED | EROFS_MAP_FRAGMENT;
+		map->m_flags = EROFS_MAP_FRAGMENT;
 		return 0;
 	}
 	initial_lcn = ofs >> lclusterbits;
@@ -489,7 +488,7 @@ static int z_erofs_map_blocks_fo(struct inode *inode,
 			goto unmap_out;
 		}
 	} else if (fragment && m.lcn == vi->z_tailextent_headlcn) {
-		map->m_flags |= EROFS_MAP_FRAGMENT;
+		map->m_flags = EROFS_MAP_FRAGMENT;
 	} else {
 		map->m_pa = erofs_pos(sb, m.pblk);
 		err = z_erofs_get_extent_compressedlen(&m, initial_lcn);
@@ -617,7 +616,7 @@ static int z_erofs_map_blocks_ext(struct inode *inode,
 	if (lstart < lend) {
 		map->m_la = lstart;
 		if (last && (vi->z_advise & Z_EROFS_ADVISE_FRAGMENT_PCLUSTER)) {
-			map->m_flags |= EROFS_MAP_MAPPED | EROFS_MAP_FRAGMENT;
+			map->m_flags = EROFS_MAP_FRAGMENT;
 			vi->z_fragmentoff = map->m_plen;
 			if (recsz > offsetof(struct z_erofs_extent, pstart_lo))
 				vi->z_fragmentoff |= map->m_pa << 32;
@@ -797,7 +796,7 @@ static int z_erofs_iomap_begin_report(struct inode *inode, loff_t offset,
 	iomap->length = map.m_llen;
 	if (map.m_flags & EROFS_MAP_MAPPED) {
 		iomap->type = IOMAP_MAPPED;
-		iomap->addr = map.m_flags & EROFS_MAP_FRAGMENT ?
+		iomap->addr = map.m_flags & __EROFS_MAP_FRAGMENT ?
 			      IOMAP_NULL_ADDR : map.m_pa;
 	} else {
 		iomap->type = IOMAP_HOLE;

From 5f02b80c21e1511c32a37f642497751041069076 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Fri, 11 Jul 2025 17:10:32 -0700
Subject: [PATCH 1332/1334] Revert "eventpoll: Fix priority inversion problem"

This reverts commit 8c44dac8add7503c345c0f6c7962e4863b88ba42.

I haven't figured out what the actual bug in this commit is, but I did
spend a lot of time chasing it down and eventually succeeded in
bisecting it down to this.

For some reason, this eventpoll commit ends up causing delays and stuck
user space processes, but it only happens on one of my machines, and
only during early boot or during the flurry of initial activity when
logging in.

I must be triggering some very subtle timing issue, but once I figured
out the behavior pattern that made it reasonably reliable to trigger, it
did bisect right to this, and reverting the commit fixes the problem.

Of course, that was only after I had failed at bisecting it several
times, and had flailed around blaming both the drm people and the
netlink people for the odd problems.  The most obvious of which happened
at the time of the first graphical login (the most common symptom being
that some gnome app aborted due to a 30s timeout, often leading to the
whole session then failing if it was some critical component like
gnome-shell or similar).

Acked-by: Nam Cao <namcao@linutronix.de>
Cc: Frederic Weisbecker <frederic@kernel.org>
Cc: Valentin Schneider <vschneid@redhat.com>
Cc: Christian Brauner <brauner@kernel.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/eventpoll.c | 458 ++++++++++++++++++++++++++++++++++---------------
 1 file changed, 324 insertions(+), 134 deletions(-)

diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 895256cd2786..0fbf5dfedb24 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -137,7 +137,13 @@ struct epitem {
 	};
 
 	/* List header used to link this structure to the eventpoll ready list */
-	struct llist_node rdllink;
+	struct list_head rdllink;
+
+	/*
+	 * Works together "struct eventpoll"->ovflist in keeping the
+	 * single linked chain of items.
+	 */
+	struct epitem *next;
 
 	/* The file descriptor information this item refers to */
 	struct epoll_filefd ffd;
@@ -185,15 +191,22 @@ struct eventpoll {
 	/* Wait queue used by file->poll() */
 	wait_queue_head_t poll_wait;
 
-	/*
-	 * List of ready file descriptors. Adding to this list is lockless. Items can be removed
-	 * only with eventpoll::mtx
-	 */
-	struct llist_head rdllist;
+	/* List of ready file descriptors */
+	struct list_head rdllist;
+
+	/* Lock which protects rdllist and ovflist */
+	rwlock_t lock;
 
 	/* RB tree root used to store monitored fd structs */
 	struct rb_root_cached rbr;
 
+	/*
+	 * This is a single linked list that chains all the "struct epitem" that
+	 * happened while transferring ready events to userspace w/out
+	 * holding ->lock.
+	 */
+	struct epitem *ovflist;
+
 	/* wakeup_source used when ep_send_events or __ep_eventpoll_poll is running */
 	struct wakeup_source *ws;
 
@@ -348,14 +361,10 @@ static inline int ep_cmp_ffd(struct epoll_filefd *p1,
 	        (p1->file < p2->file ? -1 : p1->fd - p2->fd));
 }
 
-/*
- * Add the item to its container eventpoll's rdllist; do nothing if the item is already on rdllist.
- */
-static void epitem_ready(struct epitem *epi)
+/* Tells us if the item is currently linked */
+static inline int ep_is_linked(struct epitem *epi)
 {
-	if (&epi->rdllink == cmpxchg(&epi->rdllink.next, &epi->rdllink, NULL))
-		llist_add(&epi->rdllink, &epi->ep->rdllist);
-
+	return !list_empty(&epi->rdllink);
 }
 
 static inline struct eppoll_entry *ep_pwq_from_wait(wait_queue_entry_t *p)
@@ -374,26 +383,13 @@ static inline struct epitem *ep_item_from_wait(wait_queue_entry_t *p)
  *
  * @ep: Pointer to the eventpoll context.
  *
- * Return: true if ready events might be available, false otherwise.
+ * Return: a value different than %zero if ready events are available,
+ *          or %zero otherwise.
  */
-static inline bool ep_events_available(struct eventpoll *ep)
+static inline int ep_events_available(struct eventpoll *ep)
 {
-	bool available;
-	int locked;
-
-	locked = mutex_trylock(&ep->mtx);
-	if (!locked) {
-		/*
-		 * The lock held and someone might have removed all items while inspecting it. The
-		 * llist_empty() check in this case is futile. Assume that something is enqueued and
-		 * let ep_try_send_events() figure it out.
-		 */
-		return true;
-	}
-
-	available = !llist_empty(&ep->rdllist);
-	mutex_unlock(&ep->mtx);
-	return available;
+	return !list_empty_careful(&ep->rdllist) ||
+		READ_ONCE(ep->ovflist) != EP_UNACTIVE_PTR;
 }
 
 #ifdef CONFIG_NET_RX_BUSY_POLL
@@ -728,6 +724,77 @@ static inline void ep_pm_stay_awake_rcu(struct epitem *epi)
 	rcu_read_unlock();
 }
 
+
+/*
+ * ep->mutex needs to be held because we could be hit by
+ * eventpoll_release_file() and epoll_ctl().
+ */
+static void ep_start_scan(struct eventpoll *ep, struct list_head *txlist)
+{
+	/*
+	 * Steal the ready list, and re-init the original one to the
+	 * empty list. Also, set ep->ovflist to NULL so that events
+	 * happening while looping w/out locks, are not lost. We cannot
+	 * have the poll callback to queue directly on ep->rdllist,
+	 * because we want the "sproc" callback to be able to do it
+	 * in a lockless way.
+	 */
+	lockdep_assert_irqs_enabled();
+	write_lock_irq(&ep->lock);
+	list_splice_init(&ep->rdllist, txlist);
+	WRITE_ONCE(ep->ovflist, NULL);
+	write_unlock_irq(&ep->lock);
+}
+
+static void ep_done_scan(struct eventpoll *ep,
+			 struct list_head *txlist)
+{
+	struct epitem *epi, *nepi;
+
+	write_lock_irq(&ep->lock);
+	/*
+	 * During the time we spent inside the "sproc" callback, some
+	 * other events might have been queued by the poll callback.
+	 * We re-insert them inside the main ready-list here.
+	 */
+	for (nepi = READ_ONCE(ep->ovflist); (epi = nepi) != NULL;
+	     nepi = epi->next, epi->next = EP_UNACTIVE_PTR) {
+		/*
+		 * We need to check if the item is already in the list.
+		 * During the "sproc" callback execution time, items are
+		 * queued into ->ovflist but the "txlist" might already
+		 * contain them, and the list_splice() below takes care of them.
+		 */
+		if (!ep_is_linked(epi)) {
+			/*
+			 * ->ovflist is LIFO, so we have to reverse it in order
+			 * to keep in FIFO.
+			 */
+			list_add(&epi->rdllink, &ep->rdllist);
+			ep_pm_stay_awake(epi);
+		}
+	}
+	/*
+	 * We need to set back ep->ovflist to EP_UNACTIVE_PTR, so that after
+	 * releasing the lock, events will be queued in the normal way inside
+	 * ep->rdllist.
+	 */
+	WRITE_ONCE(ep->ovflist, EP_UNACTIVE_PTR);
+
+	/*
+	 * Quickly re-inject items left on "txlist".
+	 */
+	list_splice(txlist, &ep->rdllist);
+	__pm_relax(ep->ws);
+
+	if (!list_empty(&ep->rdllist)) {
+		if (waitqueue_active(&ep->wq))
+			wake_up(&ep->wq);
+	}
+
+	write_unlock_irq(&ep->lock);
+}
+
 static void ep_get(struct eventpoll *ep)
 {
 	refcount_inc(&ep->refcount);
@@ -765,12 +832,10 @@ static void ep_free(struct eventpoll *ep)
 static bool __ep_remove(struct eventpoll *ep, struct epitem *epi, bool force)
 {
 	struct file *file = epi->ffd.file;
-	struct llist_node *put_back_last;
 	struct epitems_head *to_free;
 	struct hlist_head *head;
-	LLIST_HEAD(put_back);
 
-	lockdep_assert_held(&ep->mtx);
+	lockdep_assert_irqs_enabled();
 
 	/*
 	 * Removes poll wait queue hooks.
@@ -802,20 +867,10 @@ static bool __ep_remove(struct eventpoll *ep, struct epitem *epi, bool force)
 
 	rb_erase_cached(&epi->rbn, &ep->rbr);
 
-	if (llist_on_list(&epi->rdllink)) {
-		put_back_last = NULL;
-		while (true) {
-			struct llist_node *n = llist_del_first(&ep->rdllist);
-
-			if (&epi->rdllink == n || WARN_ON(!n))
-				break;
-			if (!put_back_last)
-				put_back_last = n;
-			__llist_add(n, &put_back);
-		}
-		if (put_back_last)
-			llist_add_batch(put_back.first, put_back_last, &ep->rdllist);
-	}
+	write_lock_irq(&ep->lock);
+	if (ep_is_linked(epi))
+		list_del_init(&epi->rdllink);
+	write_unlock_irq(&ep->lock);
 
 	wakeup_source_unregister(ep_wakeup_source(epi));
 	/*
@@ -917,9 +972,8 @@ static __poll_t ep_item_poll(const struct epitem *epi, poll_table *pt, int depth
 static __poll_t __ep_eventpoll_poll(struct file *file, poll_table *wait, int depth)
 {
 	struct eventpoll *ep = file->private_data;
-	struct wakeup_source *ws;
-	struct llist_node *n;
-	struct epitem *epi;
+	LIST_HEAD(txlist);
+	struct epitem *epi, *tmp;
 	poll_table pt;
 	__poll_t res = 0;
 
@@ -933,39 +987,22 @@ static __poll_t __ep_eventpoll_poll(struct file *file, poll_table *wait, int dep
 	 * the ready list.
 	 */
 	mutex_lock_nested(&ep->mtx, depth);
-	while (true) {
-		n = llist_del_first_init(&ep->rdllist);
-		if (!n)
-			break;
-
-		epi = llist_entry(n, struct epitem, rdllink);
-
+	ep_start_scan(ep, &txlist);
+	list_for_each_entry_safe(epi, tmp, &txlist, rdllink) {
 		if (ep_item_poll(epi, &pt, depth + 1)) {
 			res = EPOLLIN | EPOLLRDNORM;
-			epitem_ready(epi);
 			break;
 		} else {
 			/*
-			 * We need to activate ep before deactivating epi, to prevent autosuspend
-			 * just in case epi becomes active after ep_item_poll() above.
-			 *
-			 * This is similar to ep_send_events().
+			 * Item has been dropped into the ready list by the poll
+			 * callback, but it's not actually ready, as far as
+			 * caller requested events goes. We can remove it here.
 			 */
-			ws = ep_wakeup_source(epi);
-			if (ws) {
-				if (ws->active)
-					__pm_stay_awake(ep->ws);
-				__pm_relax(ws);
-			}
 			__pm_relax(ep_wakeup_source(epi));
-
-			/* Just in case epi becomes active right before __pm_relax() */
-			if (unlikely(ep_item_poll(epi, &pt, depth + 1)))
-				ep_pm_stay_awake(epi);
-
-			__pm_relax(ep->ws);
+			list_del_init(&epi->rdllink);
 		}
 	}
+	ep_done_scan(ep, &txlist);
 	mutex_unlock(&ep->mtx);
 	return res;
 }
@@ -1114,10 +1151,12 @@ static int ep_alloc(struct eventpoll **pep)
 		return -ENOMEM;
 
 	mutex_init(&ep->mtx);
+	rwlock_init(&ep->lock);
 	init_waitqueue_head(&ep->wq);
 	init_waitqueue_head(&ep->poll_wait);
-	init_llist_head(&ep->rdllist);
+	INIT_LIST_HEAD(&ep->rdllist);
 	ep->rbr = RB_ROOT_CACHED;
+	ep->ovflist = EP_UNACTIVE_PTR;
 	ep->user = get_current_user();
 	refcount_set(&ep->refcount, 1);
 
@@ -1199,11 +1238,94 @@ struct file *get_epoll_tfile_raw_ptr(struct file *file, int tfd,
 }
 #endif /* CONFIG_KCMP */
 
+/*
+ * Adds a new entry to the tail of the list in a lockless way, i.e.
+ * multiple CPUs are allowed to call this function concurrently.
+ *
+ * Beware: it is necessary to prevent any other modifications of the
+ *         existing list until all changes are completed, in other words
+ *         concurrent list_add_tail_lockless() calls should be protected
+ *         with a read lock, where write lock acts as a barrier which
+ *         makes sure all list_add_tail_lockless() calls are fully
+ *         completed.
+ *
+ *        Also an element can be locklessly added to the list only in one
+ *        direction i.e. either to the tail or to the head, otherwise
+ *        concurrent access will corrupt the list.
+ *
+ * Return: %false if element has been already added to the list, %true
+ * otherwise.
+ */
+static inline bool list_add_tail_lockless(struct list_head *new,
+					  struct list_head *head)
+{
+	struct list_head *prev;
+
+	/*
+	 * This is simple 'new->next = head' operation, but cmpxchg()
+	 * is used in order to detect that same element has been just
+	 * added to the list from another CPU: the winner observes
+	 * new->next == new.
+	 */
+	if (!try_cmpxchg(&new->next, &new, head))
+		return false;
+
+	/*
+	 * Initially ->next of a new element must be updated with the head
+	 * (we are inserting to the tail) and only then pointers are atomically
+	 * exchanged.  XCHG guarantees memory ordering, thus ->next should be
+	 * updated before pointers are actually swapped and pointers are
+	 * swapped before prev->next is updated.
+	 */
+
+	prev = xchg(&head->prev, new);
+
+	/*
+	 * It is safe to modify prev->next and new->prev, because a new element
+	 * is added only to the tail and new->next is updated before XCHG.
+	 */
+
+	prev->next = new;
+	new->prev = prev;
+
+	return true;
+}
+
+/*
+ * Chains a new epi entry to the tail of the ep->ovflist in a lockless way,
+ * i.e. multiple CPUs are allowed to call this function concurrently.
+ *
+ * Return: %false if epi element has been already chained, %true otherwise.
+ */
+static inline bool chain_epi_lockless(struct epitem *epi)
+{
+	struct eventpoll *ep = epi->ep;
+
+	/* Fast preliminary check */
+	if (epi->next != EP_UNACTIVE_PTR)
+		return false;
+
+	/* Check that the same epi has not been just chained from another CPU */
+	if (cmpxchg(&epi->next, EP_UNACTIVE_PTR, NULL) != EP_UNACTIVE_PTR)
+		return false;
+
+	/* Atomically exchange tail */
+	epi->next = xchg(&ep->ovflist, epi);
+
+	return true;
+}
+
 /*
  * This is the callback that is passed to the wait queue wakeup
  * mechanism. It is called by the stored file descriptors when they
  * have events to report.
  *
+ * This callback takes a read lock in order not to contend with concurrent
+ * events from another file descriptor, thus all modifications to ->rdllist
+ * or ->ovflist are lockless.  Read lock is paired with the write lock from
+ * ep_start/done_scan(), which stops all list modifications and guarantees
+ * that lists state is seen correctly.
+ *
  * Another thing worth to mention is that ep_poll_callback() can be called
  * concurrently for the same @epi from different CPUs if poll table was inited
  * with several wait queues entries.  Plural wakeup from different CPUs of a
@@ -1213,11 +1335,15 @@ struct file *get_epoll_tfile_raw_ptr(struct file *file, int tfd,
  */
 static int ep_poll_callback(wait_queue_entry_t *wait, unsigned mode, int sync, void *key)
 {
+	int pwake = 0;
 	struct epitem *epi = ep_item_from_wait(wait);
 	struct eventpoll *ep = epi->ep;
 	__poll_t pollflags = key_to_poll(key);
+	unsigned long flags;
 	int ewake = 0;
 
+	read_lock_irqsave(&ep->lock, flags);
+
 	ep_set_busy_poll_napi_id(epi);
 
 	/*
@@ -1227,7 +1353,7 @@ static int ep_poll_callback(wait_queue_entry_t *wait, unsigned mode, int sync, v
 	 * until the next EPOLL_CTL_MOD will be issued.
 	 */
 	if (!(epi->event.events & ~EP_PRIVATE_BITS))
-		goto out;
+		goto out_unlock;
 
 	/*
 	 * Check the events coming with the callback. At this stage, not
@@ -1236,10 +1362,22 @@ static int ep_poll_callback(wait_queue_entry_t *wait, unsigned mode, int sync, v
 	 * test for "key" != NULL before the event match test.
 	 */
 	if (pollflags && !(pollflags & epi->event.events))
-		goto out;
+		goto out_unlock;
 
-	ep_pm_stay_awake_rcu(epi);
-	epitem_ready(epi);
+	/*
+	 * If we are transferring events to userspace, we can hold no locks
+	 * (because we're accessing user memory, and because of linux f_op->poll()
+	 * semantics). All the events that happen during that period of time are
+	 * chained in ep->ovflist and requeued later on.
+	 */
+	if (READ_ONCE(ep->ovflist) != EP_UNACTIVE_PTR) {
+		if (chain_epi_lockless(epi))
+			ep_pm_stay_awake_rcu(epi);
+	} else if (!ep_is_linked(epi)) {
+		/* In the usual case, add event to ready list. */
+		if (list_add_tail_lockless(&epi->rdllink, &ep->rdllist))
+			ep_pm_stay_awake_rcu(epi);
+	}
 
 	/*
 	 * Wake up ( if active ) both the eventpoll wait list and the ->poll()
@@ -1268,9 +1406,15 @@ static int ep_poll_callback(wait_queue_entry_t *wait, unsigned mode, int sync, v
 			wake_up(&ep->wq);
 	}
 	if (waitqueue_active(&ep->poll_wait))
+		pwake++;
+
+out_unlock:
+	read_unlock_irqrestore(&ep->lock, flags);
+
+	/* We have to call this outside the lock */
+	if (pwake)
 		ep_poll_safewake(ep, epi, pollflags & EPOLL_URING_WAKE);
 
-out:
 	if (!(epi->event.events & EPOLLEXCLUSIVE))
 		ewake = 1;
 
@@ -1515,6 +1659,8 @@ static int ep_insert(struct eventpoll *ep, const struct epoll_event *event,
 	if (is_file_epoll(tfile))
 		tep = tfile->private_data;
 
+	lockdep_assert_irqs_enabled();
+
 	if (unlikely(percpu_counter_compare(&ep->user->epoll_watches,
 					    max_user_watches) >= 0))
 		return -ENOSPC;
@@ -1526,10 +1672,11 @@ static int ep_insert(struct eventpoll *ep, const struct epoll_event *event,
 	}
 
 	/* Item initialization follow here ... */
-	init_llist_node(&epi->rdllink);
+	INIT_LIST_HEAD(&epi->rdllink);
 	epi->ep = ep;
 	ep_set_ffd(&epi->ffd, tfile, fd);
 	epi->event = *event;
+	epi->next = EP_UNACTIVE_PTR;
 
 	if (tep)
 		mutex_lock_nested(&tep->mtx, 1);
@@ -1596,13 +1743,16 @@ static int ep_insert(struct eventpoll *ep, const struct epoll_event *event,
 		return -ENOMEM;
 	}
 
+	/* We have to drop the new item inside our item list to keep track of it */
+	write_lock_irq(&ep->lock);
+
 	/* record NAPI ID of new item if present */
 	ep_set_busy_poll_napi_id(epi);
 
 	/* If the file is already "ready" we drop it inside the ready list */
-	if (revents) {
+	if (revents && !ep_is_linked(epi)) {
+		list_add_tail(&epi->rdllink, &ep->rdllist);
 		ep_pm_stay_awake(epi);
-		epitem_ready(epi);
 
 		/* Notify waiting tasks that events are available */
 		if (waitqueue_active(&ep->wq))
@@ -1611,6 +1761,8 @@ static int ep_insert(struct eventpoll *ep, const struct epoll_event *event,
 			pwake++;
 	}
 
+	write_unlock_irq(&ep->lock);
+
 	/* We have to call this outside the lock */
 	if (pwake)
 		ep_poll_safewake(ep, NULL, 0);
@@ -1625,8 +1777,11 @@ static int ep_insert(struct eventpoll *ep, const struct epoll_event *event,
 static int ep_modify(struct eventpoll *ep, struct epitem *epi,
 		     const struct epoll_event *event)
 {
+	int pwake = 0;
 	poll_table pt;
 
+	lockdep_assert_irqs_enabled();
+
 	init_poll_funcptr(&pt, NULL);
 
 	/*
@@ -1670,16 +1825,24 @@ static int ep_modify(struct eventpoll *ep, struct epitem *epi,
 	 * list, push it inside.
 	 */
 	if (ep_item_poll(epi, &pt, 1)) {
-		ep_pm_stay_awake(epi);
-		epitem_ready(epi);
+		write_lock_irq(&ep->lock);
+		if (!ep_is_linked(epi)) {
+			list_add_tail(&epi->rdllink, &ep->rdllist);
+			ep_pm_stay_awake(epi);
 
-		/* Notify waiting tasks that events are available */
-		if (waitqueue_active(&ep->wq))
-			wake_up(&ep->wq);
-		if (waitqueue_active(&ep->poll_wait))
-			ep_poll_safewake(ep, NULL, 0);
+			/* Notify waiting tasks that events are available */
+			if (waitqueue_active(&ep->wq))
+				wake_up(&ep->wq);
+			if (waitqueue_active(&ep->poll_wait))
+				pwake++;
+		}
+		write_unlock_irq(&ep->lock);
 	}
 
+	/* We have to call this outside the lock */
+	if (pwake)
+		ep_poll_safewake(ep, NULL, 0);
+
 	return 0;
 }
 
@@ -1687,7 +1850,7 @@ static int ep_send_events(struct eventpoll *ep,
 			  struct epoll_event __user *events, int maxevents)
 {
 	struct epitem *epi, *tmp;
-	LLIST_HEAD(txlist);
+	LIST_HEAD(txlist);
 	poll_table pt;
 	int res = 0;
 
@@ -1702,18 +1865,19 @@ static int ep_send_events(struct eventpoll *ep,
 	init_poll_funcptr(&pt, NULL);
 
 	mutex_lock(&ep->mtx);
+	ep_start_scan(ep, &txlist);
 
-	while (res < maxevents) {
+	/*
+	 * We can loop without lock because we are passed a task private list.
+	 * Items cannot vanish during the loop we are holding ep->mtx.
+	 */
+	list_for_each_entry_safe(epi, tmp, &txlist, rdllink) {
 		struct wakeup_source *ws;
-		struct llist_node *n;
 		__poll_t revents;
 
-		n = llist_del_first(&ep->rdllist);
-		if (!n)
+		if (res >= maxevents)
 			break;
 
-		epi = llist_entry(n, struct epitem, rdllink);
-
 		/*
 		 * Activate ep->ws before deactivating epi->ws to prevent
 		 * triggering auto-suspend here (in case we reactive epi->ws
@@ -1730,30 +1894,21 @@ static int ep_send_events(struct eventpoll *ep,
 			__pm_relax(ws);
 		}
 
+		list_del_init(&epi->rdllink);
+
 		/*
 		 * If the event mask intersect the caller-requested one,
 		 * deliver the event to userspace. Again, we are holding ep->mtx,
 		 * so no operations coming from userspace can change the item.
 		 */
 		revents = ep_item_poll(epi, &pt, 1);
-		if (!revents) {
-			init_llist_node(n);
-
-			/*
-			 * Just in case epi becomes ready after ep_item_poll() above, but before
-			 * init_llist_node(). Make sure to add it to the ready list, otherwise an
-			 * event may be lost.
-			 */
-			if (unlikely(ep_item_poll(epi, &pt, 1))) {
-				ep_pm_stay_awake(epi);
-				epitem_ready(epi);
-			}
+		if (!revents)
 			continue;
-		}
 
 		events = epoll_put_uevent(revents, epi->event.data, events);
 		if (!events) {
-			llist_add(&epi->rdllink, &ep->rdllist);
+			list_add(&epi->rdllink, &txlist);
+			ep_pm_stay_awake(epi);
 			if (!res)
 				res = -EFAULT;
 			break;
@@ -1761,31 +1916,25 @@ static int ep_send_events(struct eventpoll *ep,
 		res++;
 		if (epi->event.events & EPOLLONESHOT)
 			epi->event.events &= EP_PRIVATE_BITS;
-		__llist_add(n, &txlist);
-	}
-
-	llist_for_each_entry_safe(epi, tmp, txlist.first, rdllink) {
-		init_llist_node(&epi->rdllink);
-
-		if (!(epi->event.events & EPOLLET)) {
+		else if (!(epi->event.events & EPOLLET)) {
 			/*
-			 * If this file has been added with Level Trigger mode, we need to insert
-			 * back inside the ready list, so that the next call to epoll_wait() will
-			 * check again the events availability.
+			 * If this file has been added with Level
+			 * Trigger mode, we need to insert back inside
+			 * the ready list, so that the next call to
+			 * epoll_wait() will check again the events
+			 * availability. At this point, no one can insert
+			 * into ep->rdllist besides us. The epoll_ctl()
+			 * callers are locked out by
+			 * ep_send_events() holding "mtx" and the
+			 * poll callback will queue them in ep->ovflist.
 			 */
+			list_add_tail(&epi->rdllink, &ep->rdllist);
 			ep_pm_stay_awake(epi);
-			epitem_ready(epi);
 		}
 	}
-
-	__pm_relax(ep->ws);
+	ep_done_scan(ep, &txlist);
 	mutex_unlock(&ep->mtx);
 
-	if (!llist_empty(&ep->rdllist)) {
-		if (waitqueue_active(&ep->wq))
-			wake_up(&ep->wq);
-	}
-
 	return res;
 }
 
@@ -1878,6 +2027,8 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events,
 	wait_queue_entry_t wait;
 	ktime_t expires, *to = NULL;
 
+	lockdep_assert_irqs_enabled();
+
 	if (timeout && (timeout->tv_sec | timeout->tv_nsec)) {
 		slack = select_estimate_accuracy(timeout);
 		to = &expires;
@@ -1937,15 +2088,54 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events,
 		init_wait(&wait);
 		wait.func = ep_autoremove_wake_function;
 
-		prepare_to_wait_exclusive(&ep->wq, &wait, TASK_INTERRUPTIBLE);
+		write_lock_irq(&ep->lock);
+		/*
+		 * Barrierless variant, waitqueue_active() is called under
+		 * the same lock on wakeup ep_poll_callback() side, so it
+		 * is safe to avoid an explicit barrier.
+		 */
+		__set_current_state(TASK_INTERRUPTIBLE);
 
-		if (!ep_events_available(ep))
+		/*
+		 * Do the final check under the lock. ep_start/done_scan()
+		 * plays with two lists (->rdllist and ->ovflist) and there
+		 * is always a race when both lists are empty for short
+		 * period of time although events are pending, so lock is
+		 * important.
+		 */
+		eavail = ep_events_available(ep);
+		if (!eavail)
+			__add_wait_queue_exclusive(&ep->wq, &wait);
+
+		write_unlock_irq(&ep->lock);
+
+		if (!eavail)
 			timed_out = !ep_schedule_timeout(to) ||
 				!schedule_hrtimeout_range(to, slack,
 							  HRTIMER_MODE_ABS);
+		__set_current_state(TASK_RUNNING);
 
-		finish_wait(&ep->wq, &wait);
-		eavail = ep_events_available(ep);
+		/*
+		 * We were woken up, thus go and try to harvest some events.
+		 * If timed out and still on the wait queue, recheck eavail
+		 * carefully under lock, below.
+		 */
+		eavail = 1;
+
+		if (!list_empty_careful(&wait.entry)) {
+			write_lock_irq(&ep->lock);
+			/*
+			 * If the thread timed out and is not on the wait queue,
+			 * it means that the thread was woken up after its
+			 * timeout expired before it could reacquire the lock.
+			 * Thus, when wait.entry is empty, it needs to harvest
+			 * events.
+			 */
+			if (timed_out)
+				eavail = list_empty(&wait.entry);
+			__remove_wait_queue(&ep->wq, &wait);
+			write_unlock_irq(&ep->lock);
+		}
 	}
 }
 

From 347e9f5043c89695b01e66b3ed111755afcf1911 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Sun, 13 Jul 2025 14:25:58 -0700
Subject: [PATCH 1333/1334] Linux 6.16-rc6

---
 Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Makefile b/Makefile
index 7eea2a41c905..c09766beb7ef 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
 VERSION = 6
 PATCHLEVEL = 16
 SUBLEVEL = 0
-EXTRAVERSION = -rc5
+EXTRAVERSION = -rc6
 NAME = Baby Opossum Posse
 
 # *DOCUMENTATION*

From 36569780b0d64de283f9d6c2195fd1a43e221ee8 Mon Sep 17 00:00:00 2001
From: Aruna Ramakrishna <aruna.ramakrishna@oracle.com>
Date: Wed, 9 Jul 2025 17:33:28 +0000
Subject: [PATCH 1334/1334] sched: Change nr_uninterruptible type to unsigned
 long

The commit e6fe3f422be1 ("sched: Make multiple runqueue task counters
32-bit") changed nr_uninterruptible to an unsigned int. But the
nr_uninterruptible values for each of the CPU runqueues can grow to
large numbers, sometimes exceeding INT_MAX. This is valid, if, over
time, a large number of tasks are migrated off of one CPU after going
into an uninterruptible state. Only the sum of all nr_interruptible
values across all CPUs yields the correct result, as explained in a
comment in kernel/sched/loadavg.c.

Change the type of nr_uninterruptible back to unsigned long to prevent
overflows, and thus the miscalculation of load average.

Fixes: e6fe3f422be1 ("sched: Make multiple runqueue task counters 32-bit")

Signed-off-by: Aruna Ramakrishna <aruna.ramakrishna@oracle.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20250709173328.606794-1-aruna.ramakrishna@oracle.com
---
 kernel/sched/loadavg.c | 2 +-
 kernel/sched/sched.h   | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/kernel/sched/loadavg.c b/kernel/sched/loadavg.c
index c48900b856a2..52ca8e268cfc 100644
--- a/kernel/sched/loadavg.c
+++ b/kernel/sched/loadavg.c
@@ -80,7 +80,7 @@ long calc_load_fold_active(struct rq *this_rq, long adjust)
 	long nr_active, delta = 0;
 
 	nr_active = this_rq->nr_running - adjust;
-	nr_active += (int)this_rq->nr_uninterruptible;
+	nr_active += (long)this_rq->nr_uninterruptible;
 
 	if (nr_active != this_rq->calc_load_active) {
 		delta = nr_active - this_rq->calc_load_active;
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 475bb5998295..83e3aa917142 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1149,7 +1149,7 @@ struct rq {
 	 * one CPU and if it got migrated afterwards it may decrease
 	 * it on another CPU. Always updated under the runqueue lock:
 	 */
-	unsigned int		nr_uninterruptible;
+	unsigned long 		nr_uninterruptible;
 
 	union {
 		struct task_struct __rcu *donor; /* Scheduler context */