Merge branch 'linus' into sched/core, to pick up fixes

Signed-off-by: Ingo Molnar <mingo@kernel.org>

kernel/Makefile

@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 #
 # Makefile for the linux kernel.
 #

kernel/acct.c

@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  *  linux/kernel/acct.c
  *

kernel/audit_tree.c

@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include "audit.h"
 #include <linux/fsnotify_backend.h>
 #include <linux/namei.h>

kernel/bounds.c

@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Generate definitions needed by the preprocessor.
  * This code generates raw asm output which is post-processed

kernel/bpf/Makefile

@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 obj-y := core.o
 
 obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o

kernel/bpf/arraymap.c

@@ -98,7 +98,7 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr)
 	array_size += (u64) attr->max_entries * elem_size * num_possible_cpus();
 
 	if (array_size >= U32_MAX - PAGE_SIZE ||
-	    elem_size > PCPU_MIN_UNIT_SIZE || bpf_array_alloc_percpu(array)) {
+	    bpf_array_alloc_percpu(array)) {
 		bpf_map_area_free(array);
 		return ERR_PTR(-ENOMEM);
 	}

kernel/bpf/devmap.c

@@ -69,7 +69,7 @@ static LIST_HEAD(dev_map_list);
 
 static u64 dev_map_bitmap_size(const union bpf_attr *attr)
 {
-	return BITS_TO_LONGS(attr->max_entries) * sizeof(unsigned long);
+	return BITS_TO_LONGS((u64) attr->max_entries) * sizeof(unsigned long);
 }
 
 static struct bpf_map *dev_map_alloc(union bpf_attr *attr)
@@ -78,6 +78,9 @@ static struct bpf_map *dev_map_alloc(union bpf_attr *attr)
 	int err = -EINVAL;
 	u64 cost;
 
+	if (!capable(CAP_NET_ADMIN))
+		return ERR_PTR(-EPERM);
+
 	/* check sanity of attributes */
 	if (attr->max_entries == 0 || attr->key_size != 4 ||
 	    attr->value_size != 4 || attr->map_flags & ~BPF_F_NUMA_NODE)
@@ -111,8 +114,9 @@ static struct bpf_map *dev_map_alloc(union bpf_attr *attr)
 	err = -ENOMEM;
 
 	/* A per cpu bitfield with a bit per possible net device */
-	dtab->flush_needed = __alloc_percpu(dev_map_bitmap_size(attr),
-					    __alignof__(unsigned long));
+	dtab->flush_needed = __alloc_percpu_gfp(dev_map_bitmap_size(attr),
+						__alignof__(unsigned long),
+						GFP_KERNEL | __GFP_NOWARN);
 	if (!dtab->flush_needed)
 		goto free_dtab;
 

kernel/bpf/hashtab.c

@@ -317,10 +317,6 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
 		 */
 		goto free_htab;
 
-	if (percpu && round_up(htab->map.value_size, 8) > PCPU_MIN_UNIT_SIZE)
-		/* make sure the size for pcpu_alloc() is reasonable */
-		goto free_htab;
-
 	htab->elem_size = sizeof(struct htab_elem) +
 			  round_up(htab->map.key_size, 8);
 	if (percpu)

kernel/bpf/sockmap.c

@@ -39,6 +39,7 @@
 #include <linux/workqueue.h>
 #include <linux/list.h>
 #include <net/strparser.h>
+#include <net/tcp.h>
 
 struct bpf_stab {
 	struct bpf_map map;
@@ -92,21 +93,45 @@ static inline struct smap_psock *smap_psock_sk(const struct sock *sk)
 	return rcu_dereference_sk_user_data(sk);
 }
 
+/* compute the linear packet data range [data, data_end) for skb when
+ * sk_skb type programs are in use.
+ */
+static inline void bpf_compute_data_end_sk_skb(struct sk_buff *skb)
+{
+	TCP_SKB_CB(skb)->bpf.data_end = skb->data + skb_headlen(skb);
+}
+
+enum __sk_action {
+	__SK_DROP = 0,
+	__SK_PASS,
+	__SK_REDIRECT,
+};
+
 static int smap_verdict_func(struct smap_psock *psock, struct sk_buff *skb)
 {
 	struct bpf_prog *prog = READ_ONCE(psock->bpf_verdict);
 	int rc;
 
 	if (unlikely(!prog))
-		return SK_DROP;
+		return __SK_DROP;
 
 	skb_orphan(skb);
+	/* We need to ensure that BPF metadata for maps is also cleared
+	 * when we orphan the skb so that we don't have the possibility
+	 * to reference a stale map.
+	 */
+	TCP_SKB_CB(skb)->bpf.map = NULL;
 	skb->sk = psock->sock;
-	bpf_compute_data_end(skb);
+	bpf_compute_data_end_sk_skb(skb);
+	preempt_disable();
 	rc = (*prog->bpf_func)(skb, prog->insnsi);
+	preempt_enable();
 	skb->sk = NULL;
 
-	return rc;
+	/* Moving return codes from UAPI namespace into internal namespace */
+	return rc == SK_PASS ?
+		(TCP_SKB_CB(skb)->bpf.map ? __SK_REDIRECT : __SK_PASS) :
+		__SK_DROP;
 }
 
 static void smap_do_verdict(struct smap_psock *psock, struct sk_buff *skb)
@@ -114,17 +139,10 @@ static void smap_do_verdict(struct smap_psock *psock, struct sk_buff *skb)
 	struct sock *sk;
 	int rc;
 
-	/* Because we use per cpu values to feed input from sock redirect
-	 * in BPF program to do_sk_redirect_map() call we need to ensure we
-	 * are not preempted. RCU read lock is not sufficient in this case
-	 * with CONFIG_PREEMPT_RCU enabled so we must be explicit here.
-	 */
-	preempt_disable();
 	rc = smap_verdict_func(psock, skb);
 	switch (rc) {
-	case SK_REDIRECT:
-		sk = do_sk_redirect_map();
-		preempt_enable();
+	case __SK_REDIRECT:
+		sk = do_sk_redirect_map(skb);
 		if (likely(sk)) {
 			struct smap_psock *peer = smap_psock_sk(sk);
 
@@ -139,10 +157,8 @@ static void smap_do_verdict(struct smap_psock *psock, struct sk_buff *skb)
 			}
 		}
 	/* Fall through and free skb otherwise */
-	case SK_DROP:
+	case __SK_DROP:
 	default:
-		if (rc != SK_REDIRECT)
-			preempt_enable();
 		kfree_skb(skb);
 	}
 }
@@ -369,7 +385,7 @@ static int smap_parse_func_strparser(struct strparser *strp,
 	 * any socket yet.
 	 */
 	skb->sk = psock->sock;
-	bpf_compute_data_end(skb);
+	bpf_compute_data_end_sk_skb(skb);
 	rc = (*prog->bpf_func)(skb, prog->insnsi);
 	skb->sk = NULL;
 	rcu_read_unlock();
@@ -487,6 +503,9 @@ static struct bpf_map *sock_map_alloc(union bpf_attr *attr)
 	int err = -EINVAL;
 	u64 cost;
 
+	if (!capable(CAP_NET_ADMIN))
+		return ERR_PTR(-EPERM);
+
 	/* check sanity of attributes */
 	if (attr->max_entries == 0 || attr->key_size != 4 ||
 	    attr->value_size != 4 || attr->map_flags & ~BPF_F_NUMA_NODE)
@@ -840,6 +859,12 @@ static int sock_map_update_elem(struct bpf_map *map,
 		return -EINVAL;
 	}
 
+	if (skops.sk->sk_type != SOCK_STREAM ||
+	    skops.sk->sk_protocol != IPPROTO_TCP) {
+		fput(socket->file);
+		return -EOPNOTSUPP;
+	}
+
 	err = sock_map_ctx_update_elem(&skops, map, key, flags);
 	fput(socket->file);
 	return err;

kernel/bpf/verifier.c

@@ -1116,7 +1116,12 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
 		/* ctx accesses must be at a fixed offset, so that we can
 		 * determine what type of data were returned.
 		 */
-		if (!tnum_is_const(reg->var_off)) {
+		if (reg->off) {
+			verbose("dereference of modified ctx ptr R%d off=%d+%d, ctx+const is allowed, ctx+const+const is not\n",
+				regno, reg->off, off - reg->off);
+			return -EACCES;
+		}
+		if (!tnum_is_const(reg->var_off) || reg->var_off.value) {
 			char tn_buf[48];
 
 			tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
@@ -1124,7 +1129,6 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
 				tn_buf, off, size);
 			return -EACCES;
 		}
-		off += reg->var_off.value;
 		err = check_ctx_access(env, insn_idx, off, size, t, &reg_type);
 		if (!err && t == BPF_READ && value_regno >= 0) {
 			/* ctx access returns either a scalar, or a
@@ -2426,12 +2430,15 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
 }
 
 static void find_good_pkt_pointers(struct bpf_verifier_state *state,
-				   struct bpf_reg_state *dst_reg)
+				   struct bpf_reg_state *dst_reg,
+				   bool range_right_open)
 {
 	struct bpf_reg_state *regs = state->regs, *reg;
+	u16 new_range;
 	int i;
 
-	if (dst_reg->off < 0)
+	if (dst_reg->off < 0 ||
+	    (dst_reg->off == 0 && range_right_open))
 		/* This doesn't give us any range */
 		return;
 
@@ -2442,9 +2449,13 @@ static void find_good_pkt_pointers(struct bpf_verifier_state *state,
 		 */
 		return;
 
-	/* LLVM can generate four kind of checks:
+	new_range = dst_reg->off;
+	if (range_right_open)
+		new_range--;
+
+	/* Examples for register markings:
 	 *
-	 * Type 1/2:
+	 * pkt_data in dst register:
 	 *
 	 *   r2 = r3;
 	 *   r2 += 8;
@@ -2461,7 +2472,7 @@ static void find_good_pkt_pointers(struct bpf_verifier_state *state,
 	 *     r2=pkt(id=n,off=8,r=0)
 	 *     r3=pkt(id=n,off=0,r=0)
 	 *
-	 * Type 3/4:
+	 * pkt_data in src register:
 	 *
 	 *   r2 = r3;
 	 *   r2 += 8;
@@ -2479,7 +2490,9 @@ static void find_good_pkt_pointers(struct bpf_verifier_state *state,
 	 *     r3=pkt(id=n,off=0,r=0)
 	 *
 	 * Find register r3 and mark its range as r3=pkt(id=n,off=0,r=8)
-	 * so that range of bytes [r3, r3 + 8) is safe to access.
+	 * or r3=pkt(id=n,off=0,r=8-1), so that range of bytes [r3, r3 + 8)
+	 * and [r3, r3 + 8-1) respectively is safe to access depending on
+	 * the check.
 	 */
 
 	/* If our ids match, then we must have the same max_value.  And we
@@ -2490,14 +2503,14 @@ static void find_good_pkt_pointers(struct bpf_verifier_state *state,
 	for (i = 0; i < MAX_BPF_REG; i++)
 		if (regs[i].type == PTR_TO_PACKET && regs[i].id == dst_reg->id)
 			/* keep the maximum range already checked */
-			regs[i].range = max_t(u16, regs[i].range, dst_reg->off);
+			regs[i].range = max(regs[i].range, new_range);
 
 	for (i = 0; i < MAX_BPF_STACK; i += BPF_REG_SIZE) {
 		if (state->stack_slot_type[i] != STACK_SPILL)
 			continue;
 		reg = &state->spilled_regs[i / BPF_REG_SIZE];
 		if (reg->type == PTR_TO_PACKET && reg->id == dst_reg->id)
-			reg->range = max_t(u16, reg->range, dst_reg->off);
+			reg->range = max(reg->range, new_range);
 	}
 }
 
@@ -2861,19 +2874,43 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env,
 	} else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JGT &&
 		   dst_reg->type == PTR_TO_PACKET &&
 		   regs[insn->src_reg].type == PTR_TO_PACKET_END) {
-		find_good_pkt_pointers(this_branch, dst_reg);
+		/* pkt_data' > pkt_end */
+		find_good_pkt_pointers(this_branch, dst_reg, false);
+	} else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JGT &&
+		   dst_reg->type == PTR_TO_PACKET_END &&
+		   regs[insn->src_reg].type == PTR_TO_PACKET) {
+		/* pkt_end > pkt_data' */
+		find_good_pkt_pointers(other_branch, &regs[insn->src_reg], true);
 	} else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JLT &&
 		   dst_reg->type == PTR_TO_PACKET &&
 		   regs[insn->src_reg].type == PTR_TO_PACKET_END) {
-		find_good_pkt_pointers(other_branch, dst_reg);
+		/* pkt_data' < pkt_end */
+		find_good_pkt_pointers(other_branch, dst_reg, true);
+	} else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JLT &&
+		   dst_reg->type == PTR_TO_PACKET_END &&
+		   regs[insn->src_reg].type == PTR_TO_PACKET) {
+		/* pkt_end < pkt_data' */
+		find_good_pkt_pointers(this_branch, &regs[insn->src_reg], false);
+	} else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JGE &&
+		   dst_reg->type == PTR_TO_PACKET &&
+		   regs[insn->src_reg].type == PTR_TO_PACKET_END) {
+		/* pkt_data' >= pkt_end */
+		find_good_pkt_pointers(this_branch, dst_reg, true);
 	} else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JGE &&
 		   dst_reg->type == PTR_TO_PACKET_END &&
 		   regs[insn->src_reg].type == PTR_TO_PACKET) {
-		find_good_pkt_pointers(other_branch, &regs[insn->src_reg]);
+		/* pkt_end >= pkt_data' */
+		find_good_pkt_pointers(other_branch, &regs[insn->src_reg], false);
+	} else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JLE &&
+		   dst_reg->type == PTR_TO_PACKET &&
+		   regs[insn->src_reg].type == PTR_TO_PACKET_END) {
+		/* pkt_data' <= pkt_end */
+		find_good_pkt_pointers(other_branch, dst_reg, false);
 	} else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JLE &&
 		   dst_reg->type == PTR_TO_PACKET_END &&
 		   regs[insn->src_reg].type == PTR_TO_PACKET) {
-		find_good_pkt_pointers(this_branch, &regs[insn->src_reg]);
+		/* pkt_end <= pkt_data' */
+		find_good_pkt_pointers(this_branch, &regs[insn->src_reg], true);
 	} else if (is_pointer_value(env, insn->dst_reg)) {
 		verbose("R%d pointer comparison prohibited\n", insn->dst_reg);
 		return -EACCES;

kernel/capability.c

@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * linux/kernel/capability.c
  *

kernel/cgroup/Makefile

@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 obj-y := cgroup.o namespace.o cgroup-v1.o
 
 obj-$(CONFIG_CGROUP_FREEZER) += freezer.o

kernel/cgroup/cgroup-internal.h

@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __CGROUP_INTERNAL_H
 #define __CGROUP_INTERNAL_H
 

kernel/cgroup/debug.c

@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Debug controller
  *

kernel/cgroup/namespace.c

@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include "cgroup-internal.h"
 
 #include <linux/sched/task.h>

kernel/cpu.c

@@ -632,6 +632,11 @@ cpuhp_invoke_ap_callback(int cpu, enum cpuhp_state state, bool bringup,
 		__cpuhp_kick_ap(st);
 	}
 
+	/*
+	 * Clean up the leftovers so the next hotplug operation wont use stale
+	 * data.
+	 */
+	st->node = st->last = NULL;
 	return ret;
 }
 

kernel/dma.c

@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * linux/kernel/dma.c: A DMA channel allocator. Inspired by linux/kernel/irq.c.
  *

kernel/elfcore.c

@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <linux/elf.h>
 #include <linux/fs.h>
 #include <linux/mm.h>

kernel/events/Makefile

@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 ifdef CONFIG_FUNCTION_TRACER
 CFLAGS_REMOVE_core.o = $(CC_FLAGS_FTRACE)
 endif

kernel/events/core.c

@@ -662,7 +662,7 @@ static inline void update_cgrp_time_from_event(struct perf_event *event)
 	/*
 	 * Do not update time when cgroup is not active
 	 */
-	if (cgrp == event->cgrp)
+       if (cgroup_is_descendant(cgrp->css.cgroup, event->cgrp->css.cgroup))
 		__update_cgrp_time(event->cgrp);
 }
 
@@ -901,9 +901,11 @@ list_update_cgroup_event(struct perf_event *event,
 	cpuctx_entry = &cpuctx->cgrp_cpuctx_entry;
 	/* cpuctx->cgrp is NULL unless a cgroup event is active in this CPU .*/
 	if (add) {
+		struct perf_cgroup *cgrp = perf_cgroup_from_task(current, ctx);
+
 		list_add(cpuctx_entry, this_cpu_ptr(&cgrp_cpuctx_list));
-		if (perf_cgroup_from_task(current, ctx) == event->cgrp)
-			cpuctx->cgrp = event->cgrp;
+		if (cgroup_is_descendant(cgrp->css.cgroup, event->cgrp->css.cgroup))
+			cpuctx->cgrp = cgrp;
 	} else {
 		list_del(cpuctx_entry);
 		cpuctx->cgrp = NULL;
@@ -8955,6 +8957,14 @@ static struct perf_cpu_context __percpu *find_pmu_context(int ctxn)
 
 static void free_pmu_context(struct pmu *pmu)
 {
+	/*
+	 * Static contexts such as perf_sw_context have a global lifetime
+	 * and may be shared between different PMUs. Avoid freeing them
+	 * when a single PMU is going away.
+	 */
+	if (pmu->task_ctx_nr > perf_invalid_context)
+		return;
+
 	mutex_lock(&pmus_lock);
 	free_percpu(pmu->pmu_cpu_context);
 	mutex_unlock(&pmus_lock);

kernel/events/internal.h

@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _KERNEL_EVENTS_INTERNAL_H
 #define _KERNEL_EVENTS_INTERNAL_H
 

kernel/exec_domain.c

@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Handling of different ABIs (personalities).
  *

kernel/exit.c

@@ -1610,6 +1610,9 @@ SYSCALL_DEFINE5(waitid, int, which, pid_t, upid, struct siginfo __user *,
 	if (!infop)
 		return err;
 
+	if (!access_ok(VERIFY_WRITE, infop, sizeof(*infop)))
+		return -EFAULT;
+
 	user_access_begin();
 	unsafe_put_user(signo, &infop->si_signo, Efault);
 	unsafe_put_user(0, &infop->si_errno, Efault);
@@ -1735,6 +1738,9 @@ COMPAT_SYSCALL_DEFINE5(waitid,
 	if (!infop)
 		return err;
 
+	if (!access_ok(VERIFY_WRITE, infop, sizeof(*infop)))
+		return -EFAULT;
+
 	user_access_begin();
 	unsafe_put_user(signo, &infop->si_signo, Efault);
 	unsafe_put_user(0, &infop->si_errno, Efault);

kernel/fork.c

@@ -215,6 +215,10 @@ static unsigned long *alloc_thread_stack_node(struct task_struct *tsk, int node)
 		if (!s)
 			continue;
 
+#ifdef CONFIG_DEBUG_KMEMLEAK
+		/* Clear stale pointers from reused stack. */
+		memset(s->addr, 0, THREAD_SIZE);
+#endif
 		tsk->stack_vm_area = s;
 		return s->addr;
 	}

kernel/futex.c

@@ -903,11 +903,27 @@ void exit_pi_state_list(struct task_struct *curr)
 	 */
 	raw_spin_lock_irq(&curr->pi_lock);
 	while (!list_empty(head)) {
-
 		next = head->next;
 		pi_state = list_entry(next, struct futex_pi_state, list);
 		key = pi_state->key;
 		hb = hash_futex(&key);
+
+		/*
+		 * We can race against put_pi_state() removing itself from the
+		 * list (a waiter going away). put_pi_state() will first
+		 * decrement the reference count and then modify the list, so
+		 * its possible to see the list entry but fail this reference
+		 * acquire.
+		 *
+		 * In that case; drop the locks to let put_pi_state() make
+		 * progress and retry the loop.
+		 */
+		if (!atomic_inc_not_zero(&pi_state->refcount)) {
+			raw_spin_unlock_irq(&curr->pi_lock);
+			cpu_relax();
+			raw_spin_lock_irq(&curr->pi_lock);
+			continue;
+		}
 		raw_spin_unlock_irq(&curr->pi_lock);
 
 		spin_lock(&hb->lock);
@@ -918,8 +934,10 @@ void exit_pi_state_list(struct task_struct *curr)
 		 * task still owns the PI-state:
 		 */
 		if (head->next != next) {
+			/* retain curr->pi_lock for the loop invariant */
 			raw_spin_unlock(&pi_state->pi_mutex.wait_lock);
 			spin_unlock(&hb->lock);
+			put_pi_state(pi_state);
 			continue;
 		}
 
@@ -927,9 +945,8 @@ void exit_pi_state_list(struct task_struct *curr)
 		WARN_ON(list_empty(&pi_state->list));
 		list_del_init(&pi_state->list);
 		pi_state->owner = NULL;
-		raw_spin_unlock(&curr->pi_lock);
 
-		get_pi_state(pi_state);
+		raw_spin_unlock(&curr->pi_lock);
 		raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
 		spin_unlock(&hb->lock);
 
@@ -1570,8 +1587,16 @@ static int futex_atomic_op_inuser(unsigned int encoded_op, u32 __user *uaddr)
 	int oldval, ret;
 
 	if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28)) {
-		if (oparg < 0 || oparg > 31)
-			return -EINVAL;
+		if (oparg < 0 || oparg > 31) {
+			char comm[sizeof(current->comm)];
+			/*
+			 * kill this print and return -EINVAL when userspace
+			 * is sane again
+			 */
+			pr_info_ratelimited("futex_wake_op: %s tries to shift op by %d; fix this program\n",
+					get_task_comm(comm, current), oparg);
+			oparg &= 31;
+		}
 		oparg = 1 << oparg;
 	}
 

kernel/futex_compat.c

@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * linux/kernel/futex_compat.c
  *

kernel/gcov/Makefile

@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 ccflags-y := -DSRCTREE='"$(srctree)"' -DOBJTREE='"$(objtree)"'
 
 obj-y := base.o fs.o

kernel/gcov/base.c

@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  *  This code maintains a list of active profiling data structures.
  *

kernel/gcov/fs.c

@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  *  This code exports profiling data as debugfs files to userspace.
  *

kernel/gcov/gcc_3_4.c

@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  *  This code provides functions to handle gcc's profiling data format
  *  introduced with gcc 3.4. Future versions of gcc may change the gcov

kernel/gcov/gcc_4_7.c

@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  *  This code provides functions to handle gcc's profiling data format
  *  introduced with gcc 4.7.

kernel/gcov/gcov.h

@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  *  Profiling infrastructure declarations.
  *

kernel/groups.c

@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Supplementary group IDs
  */

kernel/irq/Makefile

@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 
 obj-y := irqdesc.o handle.o manage.o spurious.o resend.o chip.o dummychip.o devres.o
 obj-$(CONFIG_IRQ_TIMINGS) += timings.o

kernel/irq/affinity.c

@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Copyright (C) 2016 Thomas Gleixner.
  * Copyright (C) 2016-2017 Christoph Hellwig.

kernel/irq/autoprobe.c

@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * linux/kernel/irq/autoprobe.c
  *

kernel/irq/chip.c

@@ -265,8 +265,8 @@ int irq_startup(struct irq_desc *desc, bool resend, bool force)
 			irq_setup_affinity(desc);
 			break;
 		case IRQ_STARTUP_MANAGED:
+			irq_do_set_affinity(d, aff, false);
 			ret = __irq_startup(desc);
-			irq_set_affinity_locked(d, aff, false);
 			break;
 		case IRQ_STARTUP_ABORT:
 			return 0;

kernel/irq/cpuhotplug.c

@@ -18,8 +18,34 @@
 static inline bool irq_needs_fixup(struct irq_data *d)
 {
 	const struct cpumask *m = irq_data_get_effective_affinity_mask(d);
+	unsigned int cpu = smp_processor_id();
 
-	return cpumask_test_cpu(smp_processor_id(), m);
+#ifdef CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK
+	/*
+	 * The cpumask_empty() check is a workaround for interrupt chips,
+	 * which do not implement effective affinity, but the architecture has
+	 * enabled the config switch. Use the general affinity mask instead.
+	 */
+	if (cpumask_empty(m))
+		m = irq_data_get_affinity_mask(d);
+
+	/*
+	 * Sanity check. If the mask is not empty when excluding the outgoing
+	 * CPU then it must contain at least one online CPU. The outgoing CPU
+	 * has been removed from the online mask already.
+	 */
+	if (cpumask_any_but(m, cpu) < nr_cpu_ids &&
+	    cpumask_any_and(m, cpu_online_mask) >= nr_cpu_ids) {
+		/*
+		 * If this happens then there was a missed IRQ fixup at some
+		 * point. Warn about it and enforce fixup.
+		 */
+		pr_warn("Eff. affinity %*pbl of IRQ %u contains only offline CPUs after offlining CPU %u\n",
+			cpumask_pr_args(m), d->irq, cpu);
+		return true;
+	}
+#endif
+	return cpumask_test_cpu(cpu, m);
 }
 
 static bool migrate_one_irq(struct irq_desc *desc)

kernel/irq/debug.h

@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Debugging printout:
  */

kernel/irq/generic-chip.c

@@ -135,17 +135,26 @@ void irq_gc_ack_clr_bit(struct irq_data *d)
 }
 
 /**
- * irq_gc_mask_disable_reg_and_ack - Mask and ack pending interrupt
+ * irq_gc_mask_disable_and_ack_set - Mask and ack pending interrupt
  * @d: irq_data
+ *
+ * This generic implementation of the irq_mask_ack method is for chips
+ * with separate enable/disable registers instead of a single mask
+ * register and where a pending interrupt is acknowledged by setting a
+ * bit.
+ *
+ * Note: This is the only permutation currently used.  Similar generic
+ * functions should be added here if other permutations are required.
  */
-void irq_gc_mask_disable_reg_and_ack(struct irq_data *d)
+void irq_gc_mask_disable_and_ack_set(struct irq_data *d)
 {
 	struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d);
 	struct irq_chip_type *ct = irq_data_get_chip_type(d);
 	u32 mask = d->mask;
 
 	irq_gc_lock(gc);
-	irq_reg_writel(gc, mask, ct->regs.mask);
+	irq_reg_writel(gc, mask, ct->regs.disable);
+	*ct->mask_cache &= ~mask;
 	irq_reg_writel(gc, mask, ct->regs.ack);
 	irq_gc_unlock(gc);
 }

kernel/irq/internals.h

@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * IRQ subsystem internal functions and variables:
  *

kernel/irq/manage.c

@@ -168,6 +168,19 @@ void irq_set_thread_affinity(struct irq_desc *desc)
 			set_bit(IRQTF_AFFINITY, &action->thread_flags);
 }
 
+static void irq_validate_effective_affinity(struct irq_data *data)
+{
+#ifdef CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK
+	const struct cpumask *m = irq_data_get_effective_affinity_mask(data);
+	struct irq_chip *chip = irq_data_get_irq_chip(data);
+
+	if (!cpumask_empty(m))
+		return;
+	pr_warn_once("irq_chip %s did not update eff. affinity mask of irq %u\n",
+		     chip->name, data->irq);
+#endif
+}
+
 int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask,
 			bool force)
 {
@@ -175,12 +188,16 @@ int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask,
 	struct irq_chip *chip = irq_data_get_irq_chip(data);
 	int ret;
 
+	if (!chip || !chip->irq_set_affinity)
+		return -EINVAL;
+
 	ret = chip->irq_set_affinity(data, mask, force);
 	switch (ret) {
 	case IRQ_SET_MASK_OK:
 	case IRQ_SET_MASK_OK_DONE:
 		cpumask_copy(desc->irq_common_data.affinity, mask);
 	case IRQ_SET_MASK_OK_NOCOPY:
+		irq_validate_effective_affinity(data);
 		irq_set_thread_affinity(desc);
 		ret = 0;
 	}

kernel/irq/migration.c

@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 
 #include <linux/irq.h>
 #include <linux/interrupt.h>

kernel/irq/proc.c

@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * linux/kernel/irq/proc.c
  *

kernel/irq/resend.c

@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * linux/kernel/irq/resend.c
  *

kernel/irq/settings.h

@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Internal header to deal with irq_desc->status which will be renamed
  * to irq_desc->settings.

kernel/irq/spurious.c

@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * linux/kernel/irq/spurious.c
  *

kernel/kcmp.c

@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <linux/kernel.h>
 #include <linux/syscalls.h>
 #include <linux/fdtable.h>

kernel/kcov.c

@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #define pr_fmt(fmt) "kcov: " fmt
 
 #define DISABLE_BRANCH_PROFILING

kernel/kexec_internal.h

@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef LINUX_KEXEC_INTERNAL_H
 #define LINUX_KEXEC_INTERNAL_H
 

kernel/livepatch/core.c

@@ -830,6 +830,41 @@ int klp_register_patch(struct klp_patch *patch)
 }
 EXPORT_SYMBOL_GPL(klp_register_patch);
 
+/*
+ * Remove parts of patches that touch a given kernel module. The list of
+ * patches processed might be limited. When limit is NULL, all patches
+ * will be handled.
+ */
+static void klp_cleanup_module_patches_limited(struct module *mod,
+					       struct klp_patch *limit)
+{
+	struct klp_patch *patch;
+	struct klp_object *obj;
+
+	list_for_each_entry(patch, &klp_patches, list) {
+		if (patch == limit)
+			break;
+
+		klp_for_each_object(patch, obj) {
+			if (!klp_is_module(obj) || strcmp(obj->name, mod->name))
+				continue;
+
+			/*
+			 * Only unpatch the module if the patch is enabled or
+			 * is in transition.
+			 */
+			if (patch->enabled || patch == klp_transition_patch) {
+				pr_notice("reverting patch '%s' on unloading module '%s'\n",
+					  patch->mod->name, obj->mod->name);
+				klp_unpatch_object(obj);
+			}
+
+			klp_free_object_loaded(obj);
+			break;
+		}
+	}
+}
+
 int klp_module_coming(struct module *mod)
 {
 	int ret;
@@ -894,7 +929,7 @@ err:
 	pr_warn("patch '%s' failed for module '%s', refusing to load module '%s'\n",
 		patch->mod->name, obj->mod->name, obj->mod->name);
 	mod->klp_alive = false;
-	klp_free_object_loaded(obj);
+	klp_cleanup_module_patches_limited(mod, patch);
 	mutex_unlock(&klp_mutex);
 
 	return ret;
@@ -902,9 +937,6 @@ err:
 
 void klp_module_going(struct module *mod)
 {
-	struct klp_patch *patch;
-	struct klp_object *obj;
-
 	if (WARN_ON(mod->state != MODULE_STATE_GOING &&
 		    mod->state != MODULE_STATE_COMING))
 		return;
@@ -917,25 +949,7 @@ void klp_module_going(struct module *mod)
 	 */
 	mod->klp_alive = false;
 
-	list_for_each_entry(patch, &klp_patches, list) {
-		klp_for_each_object(patch, obj) {
-			if (!klp_is_module(obj) || strcmp(obj->name, mod->name))
-				continue;
-
-			/*
-			 * Only unpatch the module if the patch is enabled or
-			 * is in transition.
-			 */
-			if (patch->enabled || patch == klp_transition_patch) {
-				pr_notice("reverting patch '%s' on unloading module '%s'\n",
-					  patch->mod->name, obj->mod->name);
-				klp_unpatch_object(obj);
-			}
-
-			klp_free_object_loaded(obj);
-			break;
-		}
-	}
+	klp_cleanup_module_patches_limited(mod, NULL);
 
 	mutex_unlock(&klp_mutex);
 }

kernel/livepatch/core.h

@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _LIVEPATCH_CORE_H
 #define _LIVEPATCH_CORE_H
 

kernel/livepatch/patch.h

@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _LIVEPATCH_PATCH_H
 #define _LIVEPATCH_PATCH_H
 

kernel/livepatch/transition.h

@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _LIVEPATCH_TRANSITION_H
 #define _LIVEPATCH_TRANSITION_H
 

kernel/locking/Makefile

@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 # Any varying coverage in these files is non-deterministic
 # and is generally not a function of system call inputs.
 KCOV_INSTRUMENT		:= n

kernel/locking/lockdep.c

@@ -1873,10 +1873,10 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev,
 	       struct held_lock *next, int distance, struct stack_trace *trace,
 	       int (*save)(struct stack_trace *trace))
 {
-	struct lock_list *entry;
-	int ret;
-	struct lock_list this;
 	struct lock_list *uninitialized_var(target_entry);
+	struct lock_list *entry;
+	struct lock_list this;
+	int ret;
 
 	/*
 	 * Prove that the new <prev> -> <next> dependency would not
@@ -1890,8 +1890,17 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev,
 	this.class = hlock_class(next);
 	this.parent = NULL;
 	ret = check_noncircular(&this, hlock_class(prev), &target_entry);
-	if (unlikely(!ret))
+	if (unlikely(!ret)) {
+		if (!trace->entries) {
+			/*
+			 * If @save fails here, the printing might trigger
+			 * a WARN but because of the !nr_entries it should
+			 * not do bad things.
+			 */
+			save(trace);
+		}
 		return print_circular_bug(&this, target_entry, next, prev, trace);
+	}
 	else if (unlikely(ret < 0))
 		return print_bfs_bug(ret);
 
@@ -1938,7 +1947,7 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev,
 		return print_bfs_bug(ret);
 
 
-	if (save && !save(trace))
+	if (!trace->entries && !save(trace))
 		return 0;
 
 	/*
@@ -1958,20 +1967,6 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev,
 	if (!ret)
 		return 0;
 
-	/*
-	 * Debugging printouts:
-	 */
-	if (verbose(hlock_class(prev)) || verbose(hlock_class(next))) {
-		graph_unlock();
-		printk("\n new dependency: ");
-		print_lock_name(hlock_class(prev));
-		printk(KERN_CONT " => ");
-		print_lock_name(hlock_class(next));
-		printk(KERN_CONT "\n");
-		dump_stack();
-		if (!graph_lock())
-			return 0;
-	}
 	return 2;
 }
 
@@ -1986,8 +1981,12 @@ check_prevs_add(struct task_struct *curr, struct held_lock *next)
 {
 	int depth = curr->lockdep_depth;
 	struct held_lock *hlock;
-	struct stack_trace trace;
-	int (*save)(struct stack_trace *trace) = save_trace;
+	struct stack_trace trace = {
+		.nr_entries = 0,
+		.max_entries = 0,
+		.entries = NULL,
+		.skip = 0,
+	};
 
 	/*
 	 * Debugging checks.
@@ -2018,17 +2017,10 @@ check_prevs_add(struct task_struct *curr, struct held_lock *next)
 			 */
 			if (hlock->read != 2 && hlock->check) {
 				int ret = check_prev_add(curr, hlock, next,
-							 distance, &trace, save);
+							 distance, &trace, save_trace);
 				if (!ret)
 					return 0;
 
-				/*
-				 * Stop saving stack_trace if save_trace() was
-				 * called at least once:
-				 */
-				if (save && ret == 2)
-					save = NULL;
-
 				/*
 				 * Stop after the first non-trylock entry,
 				 * as non-trylock entries have added their

kernel/locking/lockdep_internals.h

@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * kernel/lockdep_internals.h
  *

kernel/locking/lockdep_proc.c

@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * kernel/lockdep_proc.c
  *

kernel/locking/mcs_spinlock.h

@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * MCS lock defines
  *

kernel/locking/mutex-debug.h

@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Mutexes: blocking mutual exclusion locks
  *

kernel/locking/mutex.h

@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Mutexes: blocking mutual exclusion locks
  *

kernel/locking/osq_lock.c

@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <linux/percpu.h>
 #include <linux/sched.h>
 #include <linux/osq_lock.h>

kernel/locking/qspinlock_paravirt.h

@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _GEN_PV_LOCK_SLOWPATH
 #error "do not include this file"
 #endif

kernel/locking/rtmutex-debug.c

@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * RT-Mutexes: blocking mutual exclusion locks with PI support
  *

kernel/locking/rtmutex-debug.h

@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * RT-Mutexes: blocking mutual exclusion locks with PI support
  *

kernel/locking/rtmutex.h

@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * RT-Mutexes: blocking mutual exclusion locks with PI support
  *

kernel/locking/rtmutex_common.h

@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * RT Mutexes: blocking mutual exclusion locks with PI support
  *

kernel/locking/rwsem-spinlock.c

@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /* rwsem-spinlock.c: R/W semaphores: contention handling functions for
  * generic spinlock implementation
  *

kernel/locking/rwsem-xadd.c

@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /* rwsem.c: R/W semaphores: contention handling functions
  *
  * Written by David Howells (dhowells@redhat.com).

kernel/locking/rwsem.c

@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /* kernel/rwsem.c: R/W semaphores, public implementation
  *
  * Written by David Howells (dhowells@redhat.com).

kernel/locking/rwsem.h

@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * The owner field of the rw_semaphore structure will be set to
  * RWSEM_READ_OWNED when a reader grabs the lock. A writer will clear

kernel/locking/spinlock.c

@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Copyright (2004) Linus Torvalds
  *

kernel/power/Makefile

@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 
 ccflags-$(CONFIG_PM_DEBUG)	:= -DDEBUG
 

kernel/power/autosleep.c

@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * kernel/power/autosleep.c
  *

kernel/power/console.c

@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Functions for saving/restoring console.
  *

kernel/power/power.h

@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #include <linux/suspend.h>
 #include <linux/suspend_ioctls.h>
 #include <linux/utsname.h>

kernel/power/process.c

@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * drivers/power/process.c - Functions for starting/stopping processes on 
  *                           suspend transitions.

kernel/power/wakelock.c

@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * kernel/power/wakelock.c
  *

kernel/printk/braille.c

@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
 #include <linux/kernel.h>

kernel/printk/braille.h

@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _PRINTK_BRAILLE_H
 #define _PRINTK_BRAILLE_H
 

kernel/printk/console_cmdline.h

@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _CONSOLE_CMDLINE_H
 #define _CONSOLE_CMDLINE_H
 

kernel/range.c

@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Range add and subtract
  */

kernel/rcu/Makefile

@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 # Any varying coverage in these files is non-deterministic
 # and is generally not a function of system call inputs.
 KCOV_INSTRUMENT := n

kernel/rcu/srcutree.c

@@ -854,7 +854,7 @@ void __call_srcu(struct srcu_struct *sp, struct rcu_head *rhp,
 /**
  * call_srcu() - Queue a callback for invocation after an SRCU grace period
  * @sp: srcu_struct in queue the callback
- * @head: structure to be used for queueing the SRCU callback.
+ * @rhp: structure to be used for queueing the SRCU callback.
  * @func: function to be invoked after the SRCU grace period
  *
  * The callback function will be invoked some time after a full SRCU

kernel/rcu/sync.c

@@ -85,6 +85,9 @@ void rcu_sync_init(struct rcu_sync *rsp, enum rcu_sync_type type)
 }
 
 /**
+ * rcu_sync_enter_start - Force readers onto slow path for multiple updates
+ * @rsp: Pointer to rcu_sync structure to use for synchronization
+ *
  * Must be called after rcu_sync_init() and before first use.
  *
  * Ensures rcu_sync_is_idle() returns false and rcu_sync_{enter,exit}()
@@ -142,7 +145,7 @@ void rcu_sync_enter(struct rcu_sync *rsp)
 
 /**
  * rcu_sync_func() - Callback function managing reader access to fastpath
- * @rsp: Pointer to rcu_sync structure to use for synchronization
+ * @rhp: Pointer to rcu_head in rcu_sync structure to use for synchronization
  *
  * This function is passed to one of the call_rcu() functions by
  * rcu_sync_exit(), so that it is invoked after a grace period following the
@@ -158,9 +161,9 @@ void rcu_sync_enter(struct rcu_sync *rsp)
  * rcu_sync_exit().  Otherwise, set all state back to idle so that readers
  * can again use their fastpaths.
  */
-static void rcu_sync_func(struct rcu_head *rcu)
+static void rcu_sync_func(struct rcu_head *rhp)
 {
-	struct rcu_sync *rsp = container_of(rcu, struct rcu_sync, cb_head);
+	struct rcu_sync *rsp = container_of(rhp, struct rcu_sync, cb_head);
 	unsigned long flags;
 
 	BUG_ON(rsp->gp_state != GP_PASSED);

kernel/rcu/tree.c

@@ -3097,9 +3097,10 @@ __call_rcu(struct rcu_head *head, rcu_callback_t func,
  * read-side critical sections have completed. call_rcu_sched() assumes
  * that the read-side critical sections end on enabling of preemption
  * or on voluntary preemption.
- * RCU read-side critical sections are delimited by :
- *  - rcu_read_lock_sched() and rcu_read_unlock_sched(), OR
- *  - anything that disables preemption.
+ * RCU read-side critical sections are delimited by:
+ *
+ * - rcu_read_lock_sched() and rcu_read_unlock_sched(), OR
+ * - anything that disables preemption.
  *
  *  These may be nested.
  *
@@ -3124,11 +3125,12 @@ EXPORT_SYMBOL_GPL(call_rcu_sched);
  * handler. This means that read-side critical sections in process
  * context must not be interrupted by softirqs. This interface is to be
  * used when most of the read-side critical sections are in softirq context.
- * RCU read-side critical sections are delimited by :
- *  - rcu_read_lock() and  rcu_read_unlock(), if in interrupt context.
- *  OR
- *  - rcu_read_lock_bh() and rcu_read_unlock_bh(), if in process context.
- *  These may be nested.
+ * RCU read-side critical sections are delimited by:
+ *
+ * - rcu_read_lock() and  rcu_read_unlock(), if in interrupt context, OR
+ * - rcu_read_lock_bh() and rcu_read_unlock_bh(), if in process context.
+ *
+ * These may be nested.
  *
  * See the description of call_rcu() for more detailed information on
  * memory ordering guarantees.

kernel/sched/Makefile

@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 ifdef CONFIG_FUNCTION_TRACER
 CFLAGS_REMOVE_clock.o = $(CC_FLAGS_FTRACE)
 endif

kernel/sched/autogroup.c

@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include "sched.h"
 
 #include <linux/proc_fs.h>

kernel/sched/autogroup.h

@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifdef CONFIG_SCHED_AUTOGROUP
 
 #include <linux/kref.h>

kernel/sched/completion.c

@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Generic wait-for-completion handler;
  *

kernel/sched/cpuacct.c

@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <linux/cgroup.h>
 #include <linux/slab.h>
 #include <linux/percpu.h>

kernel/sched/cpuacct.h

@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifdef CONFIG_CGROUP_CPUACCT
 
 extern void cpuacct_charge(struct task_struct *tsk, u64 cputime);

kernel/sched/cpudeadline.h

@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _LINUX_CPUDL_H
 #define _LINUX_CPUDL_H
 

kernel/sched/cpupri.h

@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _LINUX_CPUPRI_H
 #define _LINUX_CPUPRI_H
 

kernel/sched/deadline.c

@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Deadline Scheduling Class (SCHED_DEADLINE)
  *

kernel/sched/fair.c

@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Completely Fair Scheduling (CFS) Class (SCHED_NORMAL/SCHED_BATCH)
  *

kernel/sched/features.h

@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Only give sleepers 50% of their service deficit. This allows
  * them to run sooner, but does not allow tons of sleepers to

kernel/sched/idle_task.c

@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 #include "sched.h"
 
 /*

kernel/sched/loadavg.c

@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * kernel/sched/loadavg.c
  *

kernel/sched/membarrier.c

@@ -18,6 +18,7 @@
 #include <linux/membarrier.h>
 #include <linux/tick.h>
 #include <linux/cpumask.h>
+#include <linux/atomic.h>
 
 #include "sched.h"	/* for cpu_rq(). */
 
@@ -26,21 +27,26 @@
  * except MEMBARRIER_CMD_QUERY.
  */
 #define MEMBARRIER_CMD_BITMASK	\
-	(MEMBARRIER_CMD_SHARED | MEMBARRIER_CMD_PRIVATE_EXPEDITED)
+	(MEMBARRIER_CMD_SHARED | MEMBARRIER_CMD_PRIVATE_EXPEDITED	\
+	| MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED)
 
 static void ipi_mb(void *info)
 {
 	smp_mb();	/* IPIs should be serializing but paranoid. */
 }
 
-static void membarrier_private_expedited(void)
+static int membarrier_private_expedited(void)
 {
 	int cpu;
 	bool fallback = false;
 	cpumask_var_t tmpmask;
 
+	if (!(atomic_read(&current->mm->membarrier_state)
+			& MEMBARRIER_STATE_PRIVATE_EXPEDITED_READY))
+		return -EPERM;
+
 	if (num_online_cpus() == 1)
-		return;
+		return 0;
 
 	/*
 	 * Matches memory barriers around rq->curr modification in
@@ -94,6 +100,24 @@ static void membarrier_private_expedited(void)
 	 * rq->curr modification in scheduler.
 	 */
 	smp_mb();	/* exit from system call is not a mb */
+	return 0;
+}
+
+static void membarrier_register_private_expedited(void)
+{
+	struct task_struct *p = current;
+	struct mm_struct *mm = p->mm;
+
+	/*
+	 * We need to consider threads belonging to different thread
+	 * groups, which use the same mm. (CLONE_VM but not
+	 * CLONE_THREAD).
+	 */
+	if (atomic_read(&mm->membarrier_state)
+			& MEMBARRIER_STATE_PRIVATE_EXPEDITED_READY)
+		return;
+	atomic_or(MEMBARRIER_STATE_PRIVATE_EXPEDITED_READY,
+			&mm->membarrier_state);
 }
 
 /**
@@ -144,7 +168,9 @@ SYSCALL_DEFINE2(membarrier, int, cmd, int, flags)
 			synchronize_sched();
 		return 0;
 	case MEMBARRIER_CMD_PRIVATE_EXPEDITED:
-		membarrier_private_expedited();
+		return membarrier_private_expedited();
+	case MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED:
+		membarrier_register_private_expedited();
 		return 0;
 	default:
 		return -EINVAL;