From 84965ff8a84f0368b154c9b367b62e59c1193f30 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Sat, 23 Jan 2021 15:51:11 -0700 Subject: [PATCH 1/9] io_uring: if we see flush on exit, cancel related tasks Ensure we match tasks that belong to a dead or dying task as well, as we need to reap those in addition to those belonging to the exiting task. Cc: stable@vger.kernel.org # 5.9+ Reported-by: Josef Grieb Signed-off-by: Jens Axboe --- fs/io_uring.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/fs/io_uring.c b/fs/io_uring.c index c07913ec0cca..695fe00bafdc 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -1069,8 +1069,12 @@ static bool io_match_task(struct io_kiocb *head, { struct io_kiocb *req; - if (task && head->task != task) + if (task && head->task != task) { + /* in terms of cancelation, always match if req task is dead */ + if (head->task->flags & PF_EXITING) + return true; return false; + } if (!files) return true; @@ -9136,6 +9140,9 @@ static int io_uring_flush(struct file *file, void *data) struct io_uring_task *tctx = current->io_uring; struct io_ring_ctx *ctx = file->private_data; + if (fatal_signal_pending(current) || (current->flags & PF_EXITING)) + io_uring_cancel_task_requests(ctx, NULL); + if (!tctx) return 0; From b18032bb0a883cd7edd22a7fe6c57e1059b81ed0 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Sun, 24 Jan 2021 16:58:56 -0700 Subject: [PATCH 2/9] io_uring: only call io_cqring_ev_posted() if events were posted This normally doesn't cause any extra harm, but it does mean that we'll increment the eventfd notification count, if one has been registered with the ring. This can confuse applications, when they see more notifications on the eventfd side than are available in the ring. Do the nice thing and only increment this count, if we actually posted (or even overflowed) events. Reported-and-tested-by: Dan Melnic Signed-off-by: Jens Axboe --- fs/io_uring.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/fs/io_uring.c b/fs/io_uring.c index 695fe00bafdc..2166c469789d 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -1779,12 +1779,13 @@ static bool __io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force, struct io_kiocb *req, *tmp; struct io_uring_cqe *cqe; unsigned long flags; - bool all_flushed; + bool all_flushed, posted; LIST_HEAD(list); if (!force && __io_cqring_events(ctx) == rings->cq_ring_entries) return false; + posted = false; spin_lock_irqsave(&ctx->completion_lock, flags); list_for_each_entry_safe(req, tmp, &ctx->cq_overflow_list, compl.list) { if (!io_match_task(req, tsk, files)) @@ -1804,6 +1805,7 @@ static bool __io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force, WRITE_ONCE(ctx->rings->cq_overflow, ctx->cached_cq_overflow); } + posted = true; } all_flushed = list_empty(&ctx->cq_overflow_list); @@ -1813,9 +1815,11 @@ static bool __io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force, ctx->rings->sq_flags &= ~IORING_SQ_CQ_OVERFLOW; } - io_commit_cqring(ctx); + if (posted) + io_commit_cqring(ctx); spin_unlock_irqrestore(&ctx->completion_lock, flags); - io_cqring_ev_posted(ctx); + if (posted) + io_cqring_ev_posted(ctx); while (!list_empty(&list)) { req = list_first_entry(&list, struct io_kiocb, compl.list); From a1bb3cd58913338e1b627ea6b8c03c2ae82d293f Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Tue, 26 Jan 2021 15:28:26 +0000 Subject: [PATCH 3/9] io_uring: fix __io_uring_files_cancel() with TASK_UNINTERRUPTIBLE If the tctx inflight number haven't changed because of cancellation, __io_uring_task_cancel() will continue leaving the task in TASK_UNINTERRUPTIBLE state, that's not expected by __io_uring_files_cancel(). Ensure we always call finish_wait() before retrying. Cc: stable@vger.kernel.org # 5.9+ Signed-off-by: Pavel Begunkov Signed-off-by: Jens Axboe --- fs/io_uring.c | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) diff --git a/fs/io_uring.c b/fs/io_uring.c index 2166c469789d..09aada153a71 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -9124,16 +9124,15 @@ void __io_uring_task_cancel(void) prepare_to_wait(&tctx->wait, &wait, TASK_UNINTERRUPTIBLE); /* - * If we've seen completions, retry. This avoids a race where - * a completion comes in before we did prepare_to_wait(). + * If we've seen completions, retry without waiting. This + * avoids a race where a completion comes in before we did + * prepare_to_wait(). */ - if (inflight != tctx_inflight(tctx)) - continue; - schedule(); + if (inflight == tctx_inflight(tctx)) + schedule(); finish_wait(&tctx->wait, &wait); } while (1); - finish_wait(&tctx->wait, &wait); atomic_dec(&tctx->in_idle); io_uring_remove_task_files(tctx); From ca70f00bed6cb255b7a9b91aa18a2717c9217f70 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Tue, 26 Jan 2021 15:28:27 +0000 Subject: [PATCH 4/9] io_uring: fix cancellation taking mutex while TASK_UNINTERRUPTIBLE do not call blocking ops when !TASK_RUNNING; state=2 set at [<00000000ced9dbfc>] prepare_to_wait+0x1f4/0x3b0 kernel/sched/wait.c:262 WARNING: CPU: 1 PID: 19888 at kernel/sched/core.c:7853 __might_sleep+0xed/0x100 kernel/sched/core.c:7848 RIP: 0010:__might_sleep+0xed/0x100 kernel/sched/core.c:7848 Call Trace: __mutex_lock_common+0xc4/0x2ef0 kernel/locking/mutex.c:935 __mutex_lock kernel/locking/mutex.c:1103 [inline] mutex_lock_nested+0x1a/0x20 kernel/locking/mutex.c:1118 io_wq_submit_work+0x39a/0x720 fs/io_uring.c:6411 io_run_cancel fs/io-wq.c:856 [inline] io_wqe_cancel_pending_work fs/io-wq.c:990 [inline] io_wq_cancel_cb+0x614/0xcb0 fs/io-wq.c:1027 io_uring_cancel_files fs/io_uring.c:8874 [inline] io_uring_cancel_task_requests fs/io_uring.c:8952 [inline] __io_uring_files_cancel+0x115d/0x19e0 fs/io_uring.c:9038 io_uring_files_cancel include/linux/io_uring.h:51 [inline] do_exit+0x2e6/0x2490 kernel/exit.c:780 do_group_exit+0x168/0x2d0 kernel/exit.c:922 get_signal+0x16b5/0x2030 kernel/signal.c:2770 arch_do_signal_or_restart+0x8e/0x6a0 arch/x86/kernel/signal.c:811 handle_signal_work kernel/entry/common.c:147 [inline] exit_to_user_mode_loop kernel/entry/common.c:171 [inline] exit_to_user_mode_prepare+0xac/0x1e0 kernel/entry/common.c:201 __syscall_exit_to_user_mode_work kernel/entry/common.c:291 [inline] syscall_exit_to_user_mode+0x48/0x190 kernel/entry/common.c:302 entry_SYSCALL_64_after_hwframe+0x44/0xa9 Rewrite io_uring_cancel_files() to mimic __io_uring_task_cancel()'s counting scheme, so it does all the heavy work before setting TASK_UNINTERRUPTIBLE. Cc: stable@vger.kernel.org # 5.9+ Reported-by: syzbot+f655445043a26a7cfab8@syzkaller.appspotmail.com Signed-off-by: Pavel Begunkov [axboe: fix inverted task check] Signed-off-by: Jens Axboe --- fs/io_uring.c | 39 ++++++++++++++++++++++----------------- 1 file changed, 22 insertions(+), 17 deletions(-) diff --git a/fs/io_uring.c b/fs/io_uring.c index 09aada153a71..bb0270eeb8cb 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -8873,30 +8873,31 @@ static void io_cancel_defer_files(struct io_ring_ctx *ctx, } } +static int io_uring_count_inflight(struct io_ring_ctx *ctx, + struct task_struct *task, + struct files_struct *files) +{ + struct io_kiocb *req; + int cnt = 0; + + spin_lock_irq(&ctx->inflight_lock); + list_for_each_entry(req, &ctx->inflight_list, inflight_entry) + cnt += io_match_task(req, task, files); + spin_unlock_irq(&ctx->inflight_lock); + return cnt; +} + static void io_uring_cancel_files(struct io_ring_ctx *ctx, struct task_struct *task, struct files_struct *files) { while (!list_empty_careful(&ctx->inflight_list)) { struct io_task_cancel cancel = { .task = task, .files = files }; - struct io_kiocb *req; DEFINE_WAIT(wait); - bool found = false; + int inflight; - spin_lock_irq(&ctx->inflight_lock); - list_for_each_entry(req, &ctx->inflight_list, inflight_entry) { - if (!io_match_task(req, task, files)) - continue; - found = true; - break; - } - if (found) - prepare_to_wait(&task->io_uring->wait, &wait, - TASK_UNINTERRUPTIBLE); - spin_unlock_irq(&ctx->inflight_lock); - - /* We need to keep going until we don't find a matching req */ - if (!found) + inflight = io_uring_count_inflight(ctx, task, files); + if (!inflight) break; io_wq_cancel_cb(ctx->io_wq, io_cancel_task_cb, &cancel, true); @@ -8905,7 +8906,11 @@ static void io_uring_cancel_files(struct io_ring_ctx *ctx, io_cqring_overflow_flush(ctx, true, task, files); /* cancellations _may_ trigger task work */ io_run_task_work(); - schedule(); + + prepare_to_wait(&task->io_uring->wait, &wait, + TASK_UNINTERRUPTIBLE); + if (inflight == io_uring_count_inflight(ctx, task, files)) + schedule(); finish_wait(&task->io_uring->wait, &wait); } } From 907d1df30a51cc1a1d25414a00cde0494b83df7b Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Tue, 26 Jan 2021 23:35:10 +0000 Subject: [PATCH 5/9] io_uring: fix wqe->lock/completion_lock deadlock Joseph reports following deadlock: CPU0: ... io_kill_linked_timeout // &ctx->completion_lock io_commit_cqring __io_queue_deferred __io_queue_async_work io_wq_enqueue io_wqe_enqueue // &wqe->lock CPU1: ... __io_uring_files_cancel io_wq_cancel_cb io_wqe_cancel_pending_work // &wqe->lock io_cancel_task_cb // &ctx->completion_lock Only __io_queue_deferred() calls queue_async_work() while holding ctx->completion_lock, enqueue drained requests via io_req_task_queue() instead. Cc: stable@vger.kernel.org # 5.9+ Reported-by: Joseph Qi Tested-by: Joseph Qi Signed-off-by: Pavel Begunkov Signed-off-by: Jens Axboe --- fs/io_uring.c | 10 ++-------- 1 file changed, 2 insertions(+), 8 deletions(-) diff --git a/fs/io_uring.c b/fs/io_uring.c index bb0270eeb8cb..c218deaf73a9 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -1026,6 +1026,7 @@ static int io_setup_async_rw(struct io_kiocb *req, const struct iovec *iovec, const struct iovec *fast_iov, struct iov_iter *iter, bool force); static void io_req_drop_files(struct io_kiocb *req); +static void io_req_task_queue(struct io_kiocb *req); static struct kmem_cache *req_cachep; @@ -1634,18 +1635,11 @@ static void __io_queue_deferred(struct io_ring_ctx *ctx) do { struct io_defer_entry *de = list_first_entry(&ctx->defer_list, struct io_defer_entry, list); - struct io_kiocb *link; if (req_need_defer(de->req, de->seq)) break; list_del_init(&de->list); - /* punt-init is done before queueing for defer */ - link = __io_queue_async_work(de->req); - if (link) { - __io_queue_linked_timeout(link); - /* drop submission reference */ - io_put_req_deferred(link, 1); - } + io_req_task_queue(de->req); kfree(de); } while (!list_empty(&ctx->defer_list)); } From 6195ba09822c87cad09189bbf550d0fbe714687a Mon Sep 17 00:00:00 2001 From: Hao Xu Date: Wed, 27 Jan 2021 15:14:09 +0800 Subject: [PATCH 6/9] io_uring: fix flush cqring overflow list while TASK_INTERRUPTIBLE Abaci reported the follow warning: [ 27.073425] do not call blocking ops when !TASK_RUNNING; state=1 set at [] prepare_to_wait_exclusive+0x3a/0xc0 [ 27.075805] WARNING: CPU: 0 PID: 951 at kernel/sched/core.c:7853 __might_sleep+0x80/0xa0 [ 27.077604] Modules linked in: [ 27.078379] CPU: 0 PID: 951 Comm: a.out Not tainted 5.11.0-rc3+ #1 [ 27.079637] Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 [ 27.080852] RIP: 0010:__might_sleep+0x80/0xa0 [ 27.081835] Code: 65 48 8b 04 25 80 71 01 00 48 8b 90 c0 15 00 00 48 8b 70 18 48 c7 c7 08 39 95 82 c6 05 f9 5f de 08 01 48 89 d1 e8 00 c6 fa ff 0b eb bf 41 0f b6 f5 48 c7 c7 40 23 c9 82 e8 f3 48 ec 00 eb a7 [ 27.084521] RSP: 0018:ffffc90000fe3ce8 EFLAGS: 00010286 [ 27.085350] RAX: 0000000000000000 RBX: ffffffff82956083 RCX: 0000000000000000 [ 27.086348] RDX: ffff8881057a0000 RSI: ffffffff8118cc9e RDI: ffff88813bc28570 [ 27.087598] RBP: 00000000000003a7 R08: 0000000000000001 R09: 0000000000000001 [ 27.088819] R10: ffffc90000fe3e00 R11: 00000000fffef9f0 R12: 0000000000000000 [ 27.089819] R13: 0000000000000000 R14: ffff88810576eb80 R15: ffff88810576e800 [ 27.091058] FS: 00007f7b144cf740(0000) GS:ffff88813bc00000(0000) knlGS:0000000000000000 [ 27.092775] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 27.093796] CR2: 00000000022da7b8 CR3: 000000010b928002 CR4: 00000000003706f0 [ 27.094778] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 27.095780] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 27.097011] Call Trace: [ 27.097685] __mutex_lock+0x5d/0xa30 [ 27.098565] ? prepare_to_wait_exclusive+0x71/0xc0 [ 27.099412] ? io_cqring_overflow_flush.part.101+0x6d/0x70 [ 27.100441] ? lockdep_hardirqs_on_prepare+0xe9/0x1c0 [ 27.101537] ? _raw_spin_unlock_irqrestore+0x2d/0x40 [ 27.102656] ? trace_hardirqs_on+0x46/0x110 [ 27.103459] ? io_cqring_overflow_flush.part.101+0x6d/0x70 [ 27.104317] io_cqring_overflow_flush.part.101+0x6d/0x70 [ 27.105113] io_cqring_wait+0x36e/0x4d0 [ 27.105770] ? find_held_lock+0x28/0xb0 [ 27.106370] ? io_uring_remove_task_files+0xa0/0xa0 [ 27.107076] __x64_sys_io_uring_enter+0x4fb/0x640 [ 27.107801] ? rcu_read_lock_sched_held+0x59/0xa0 [ 27.108562] ? lockdep_hardirqs_on_prepare+0xe9/0x1c0 [ 27.109684] ? syscall_enter_from_user_mode+0x26/0x70 [ 27.110731] do_syscall_64+0x2d/0x40 [ 27.111296] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 27.112056] RIP: 0033:0x7f7b13dc8239 [ 27.112663] Code: 01 00 48 81 c4 80 00 00 00 e9 f1 fe ff ff 0f 1f 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 3d 01 f0 ff ff 73 01 c3 48 8b 0d 27 ec 2c 00 f7 d8 64 89 01 48 [ 27.115113] RSP: 002b:00007ffd6d7f5c88 EFLAGS: 00000286 ORIG_RAX: 00000000000001aa [ 27.116562] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f7b13dc8239 [ 27.117961] RDX: 000000000000478e RSI: 0000000000000000 RDI: 0000000000000003 [ 27.118925] RBP: 00007ffd6d7f5cb0 R08: 0000000020000040 R09: 0000000000000008 [ 27.119773] R10: 0000000000000001 R11: 0000000000000286 R12: 0000000000400480 [ 27.120614] R13: 00007ffd6d7f5d90 R14: 0000000000000000 R15: 0000000000000000 [ 27.121490] irq event stamp: 5635 [ 27.121946] hardirqs last enabled at (5643): [] console_unlock+0x5c4/0x740 [ 27.123476] hardirqs last disabled at (5652): [] console_unlock+0x4e7/0x740 [ 27.125192] softirqs last enabled at (5272): [] __do_softirq+0x3c5/0x5aa [ 27.126430] softirqs last disabled at (5267): [] asm_call_irq_on_stack+0xf/0x20 [ 27.127634] ---[ end trace 289d7e28fa60f928 ]--- This is caused by calling io_cqring_overflow_flush() which may sleep after calling prepare_to_wait_exclusive() which set task state to TASK_INTERRUPTIBLE Reported-by: Abaci Fixes: 6c503150ae33 ("io_uring: patch up IOPOLL overflow_flush sync") Reviewed-by: Pavel Begunkov Signed-off-by: Hao Xu Signed-off-by: Jens Axboe --- fs/io_uring.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/fs/io_uring.c b/fs/io_uring.c index c218deaf73a9..ae388cc52843 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -7268,14 +7268,18 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events, TASK_INTERRUPTIBLE); /* make sure we run task_work before checking for signals */ ret = io_run_task_work_sig(); - if (ret > 0) + if (ret > 0) { + finish_wait(&ctx->wait, &iowq.wq); continue; + } else if (ret < 0) break; if (io_should_wake(&iowq)) break; - if (test_bit(0, &ctx->cq_check_overflow)) + if (test_bit(0, &ctx->cq_check_overflow)) { + finish_wait(&ctx->wait, &iowq.wq); continue; + } if (uts) { timeout = schedule_timeout(timeout); if (timeout == 0) { From f609cbb8911e40e15f9055e8f945f926ac906924 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Thu, 28 Jan 2021 18:39:24 +0000 Subject: [PATCH 7/9] io_uring: fix list corruption for splice file_get kernel BUG at lib/list_debug.c:29! Call Trace: __list_add include/linux/list.h:67 [inline] list_add include/linux/list.h:86 [inline] io_file_get+0x8cc/0xdb0 fs/io_uring.c:6466 __io_splice_prep+0x1bc/0x530 fs/io_uring.c:3866 io_splice_prep fs/io_uring.c:3920 [inline] io_req_prep+0x3546/0x4e80 fs/io_uring.c:6081 io_queue_sqe+0x609/0x10d0 fs/io_uring.c:6628 io_submit_sqe fs/io_uring.c:6705 [inline] io_submit_sqes+0x1495/0x2720 fs/io_uring.c:6953 __do_sys_io_uring_enter+0x107d/0x1f30 fs/io_uring.c:9353 do_syscall_64+0x2d/0x70 arch/x86/entry/common.c:46 entry_SYSCALL_64_after_hwframe+0x44/0xa9 io_file_get() may be called from splice, and so REQ_F_INFLIGHT may already be set. Fixes: 02a13674fa0e8 ("io_uring: account io_uring internal files as REQ_F_INFLIGHT") Cc: stable@vger.kernel.org # 5.9+ Reported-by: syzbot+6879187cf57845801267@syzkaller.appspotmail.com Signed-off-by: Pavel Begunkov Signed-off-by: Jens Axboe --- fs/io_uring.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/io_uring.c b/fs/io_uring.c index ae388cc52843..39ae1f821cef 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -6460,7 +6460,8 @@ static struct file *io_file_get(struct io_submit_state *state, file = __io_file_get(state, fd); } - if (file && file->f_op == &io_uring_fops) { + if (file && file->f_op == &io_uring_fops && + !(req->flags & REQ_F_INFLIGHT)) { io_req_init_async(req); req->flags |= REQ_F_INFLIGHT; From 70b2c60d3797bffe182dddb9bb55975b9be5889a Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Thu, 28 Jan 2021 18:39:25 +0000 Subject: [PATCH 8/9] io_uring: fix sqo ownership false positive warning WARNING: CPU: 0 PID: 21359 at fs/io_uring.c:9042 io_uring_cancel_task_requests+0xe55/0x10c0 fs/io_uring.c:9042 Call Trace: io_uring_flush+0x47b/0x6e0 fs/io_uring.c:9227 filp_close+0xb4/0x170 fs/open.c:1295 close_files fs/file.c:403 [inline] put_files_struct fs/file.c:418 [inline] put_files_struct+0x1cc/0x350 fs/file.c:415 exit_files+0x7e/0xa0 fs/file.c:435 do_exit+0xc22/0x2ae0 kernel/exit.c:820 do_group_exit+0x125/0x310 kernel/exit.c:922 get_signal+0x427/0x20f0 kernel/signal.c:2773 arch_do_signal_or_restart+0x2a8/0x1eb0 arch/x86/kernel/signal.c:811 handle_signal_work kernel/entry/common.c:147 [inline] exit_to_user_mode_loop kernel/entry/common.c:171 [inline] exit_to_user_mode_prepare+0x148/0x250 kernel/entry/common.c:201 __syscall_exit_to_user_mode_work kernel/entry/common.c:291 [inline] syscall_exit_to_user_mode+0x19/0x50 kernel/entry/common.c:302 entry_SYSCALL_64_after_hwframe+0x44/0xa9 Now io_uring_cancel_task_requests() can be called not through file notes but directly, remove a WARN_ONCE() there that give us false positives. That check is not very important and we catch it in other places. Fixes: 84965ff8a84f0 ("io_uring: if we see flush on exit, cancel related tasks") Cc: stable@vger.kernel.org # 5.9+ Reported-by: syzbot+3e3d9bd0c6ce9efbc3ef@syzkaller.appspotmail.com Signed-off-by: Pavel Begunkov Signed-off-by: Jens Axboe --- fs/io_uring.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/fs/io_uring.c b/fs/io_uring.c index 39ae1f821cef..12bf7180c0f1 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -8967,8 +8967,6 @@ static void io_uring_cancel_task_requests(struct io_ring_ctx *ctx, struct task_struct *task = current; if ((ctx->flags & IORING_SETUP_SQPOLL) && ctx->sq_data) { - /* for SQPOLL only sqo_task has task notes */ - WARN_ON_ONCE(ctx->sqo_task != current); io_disable_sqo_submit(ctx); task = ctx->sq_data->thread; atomic_inc(&task->io_uring->in_idle); From 3a7efd1ad269ccaf9c1423364d97c9661ba6dafa Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Thu, 28 Jan 2021 23:23:42 +0000 Subject: [PATCH 9/9] io_uring: reinforce cancel on flush during exit What 84965ff8a84f0 ("io_uring: if we see flush on exit, cancel related tasks") really wants is to cancel all relevant REQ_F_INFLIGHT requests reliably. That can be achieved by io_uring_cancel_files(), but we'll miss it calling io_uring_cancel_task_requests(files=NULL) from io_uring_flush(), because it will go through __io_uring_cancel_task_requests(). Just always call io_uring_cancel_files() during cancel, it's good enough for now. Cc: stable@vger.kernel.org # 5.9+ Signed-off-by: Pavel Begunkov Signed-off-by: Jens Axboe --- fs/io_uring.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/fs/io_uring.c b/fs/io_uring.c index 12bf7180c0f1..38c6cbe1ab38 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -8976,10 +8976,9 @@ static void io_uring_cancel_task_requests(struct io_ring_ctx *ctx, io_cancel_defer_files(ctx, task, files); io_cqring_overflow_flush(ctx, true, task, files); + io_uring_cancel_files(ctx, task, files); if (!files) __io_uring_cancel_task_requests(ctx, task); - else - io_uring_cancel_files(ctx, task, files); if ((ctx->flags & IORING_SETUP_SQPOLL) && ctx->sq_data) { atomic_dec(&task->io_uring->in_idle);