From 203817de269539c062724d97dfa5af3cdf77a3ec Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Mon, 7 Jul 2025 09:52:33 +0100 Subject: [PATCH 1/3] 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 Fixes: 34a3e60821ab9 ("io_uring/zcrx: implement zerocopy receive pp memory provider") Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/b9e6d919d2964bc48ddbf8eb52fc9f5d118e9bc1.1751878185.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- 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 fc582cd26e888b0652bc1494f252329453fd3b23 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 8 Jul 2025 11:00:32 -0600 Subject: [PATCH 2/3] 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: 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 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 --- 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 Date: Tue, 8 Jul 2025 11:04:45 -0600 Subject: [PATCH 3/3] 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 --- 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;