From 8257f6ec45ee07c6ed933c59d8982b03cc7bc1ca Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Thu, 15 Oct 2026 19:30:31 +0000 Subject: [PATCH] io_uring: don't lose the DEFER_TASKRUN wake up Since local task_work moved to the mpscq, ->cq_wait_nr is a credit: the add that counts it down to zero, or exchanges it for IO_CQ_WAKE_INIT, issues the only wake up of the wait cycle, and every later add returns early as the count is <= 0. An add looks at the count after it has queued its entry, so an add that gets delayed in between can take the credit of a later cycle. That was assumed to cause an early wake up at worst, but the waiter publishes the count before it changes its task state: CPU0 (submitter, io_cqring_wait) CPU1 (io_req_local_work_add) mpscq_push(req A) io_run_local_work() // runs req A atomic_set(&ctx->cq_wait_nr, 1) atomic_read(&ctx->cq_wait_nr) == 1 atomic_xchg(.., IO_CQ_WAKE_INIT) wake_up_state(.., TASK_INTERRUPTIBLE) // still TASK_RUNNING, no-op set_current_state(TASK_INTERRUPTIBLE) io_local_work_pending() == false schedule() mpscq_push(req B) cq_wait_nr <= 0, return The task now sleeps with req B queued, until a signal or a timeout ends the wait. Set the task state first and only then make the count visible, so that whoever takes the credit finds a task it can wake. The full barrier that orders the count against the check of the work list is kept. Do the same for the wait of the BPF driven loop, which copied the sequence. Fixes: d46ab2c98aba ("io_uring: switch local task_work to a mpscq") Assisted-by: LLM Signed-off-by: Josef Bacik Link: https://patch.msgid.link/20261015-b4-io-uring-fixes-v1-7-c1556f5d7bf5@toxicpanda.com Signed-off-by: Jens Axboe --- io_uring/loop.c | 8 +------- io_uring/tw.c | 2 +- io_uring/wait.c | 3 +-- io_uring/wait.h | 15 +++++++++++++++ 4 files changed, 18 insertions(+), 10 deletions(-) diff --git a/io_uring/loop.c b/io_uring/loop.c index 3d472b7827fa..2340459164a1 100644 --- a/io_uring/loop.c +++ b/io_uring/loop.c @@ -10,12 +10,6 @@ static inline int io_loop_nr_cqes(const struct io_ring_ctx *ctx, return lp->cq_wait_idx - READ_ONCE(ctx->rings->cq.tail); } -static inline void io_loop_wait_start(struct io_ring_ctx *ctx, unsigned nr_wait) -{ - atomic_set(&ctx->cq_wait_nr, nr_wait); - set_current_state(TASK_INTERRUPTIBLE); -} - static inline void io_loop_wait_finish(struct io_ring_ctx *ctx) { __set_current_state(TASK_RUNNING); @@ -25,7 +19,7 @@ static inline void io_loop_wait_finish(struct io_ring_ctx *ctx) static void io_loop_wait(struct io_ring_ctx *ctx, struct iou_loop_params *lp, unsigned nr_wait) { - io_loop_wait_start(ctx, nr_wait); + io_cq_wait_arm(ctx, nr_wait); if (unlikely(io_local_work_pending(ctx) || io_loop_nr_cqes(ctx, lp) <= 0) || diff --git a/io_uring/tw.c b/io_uring/tw.c index f9affd68dd26..98e3b1bc61b4 100644 --- a/io_uring/tw.c +++ b/io_uring/tw.c @@ -165,7 +165,7 @@ void io_req_local_work_add(struct io_kiocb *req, unsigned flags) /* * The xchg() in mpscq_push() implies a full barrier, which pairs with - * the barrier in set_current_state() on the io_cqring_wait() side. This + * the barrier in io_cq_wait_arm() on the io_cqring_wait() side. This * ensures that either we see the updated ->cq_wait_nr, or waiters going * to sleep will observe the work added to the list, which is similar to * the wait/wake task state sync. diff --git a/io_uring/wait.c b/io_uring/wait.c index e03b40d9c141..5093365e9eb2 100644 --- a/io_uring/wait.c +++ b/io_uring/wait.c @@ -257,8 +257,7 @@ int io_cqring_wait(struct io_ring_ctx *ctx, int min_events, u32 flags, unsigned long check_cq; if (ctx->flags & IORING_SETUP_DEFER_TASKRUN) { - atomic_set(&ctx->cq_wait_nr, nr_wait); - set_current_state(TASK_INTERRUPTIBLE); + io_cq_wait_arm(ctx, nr_wait); } else { prepare_to_wait_exclusive(&ctx->cq_wait, &iowq.wq, TASK_INTERRUPTIBLE); diff --git a/io_uring/wait.h b/io_uring/wait.h index b7b9c46b1b01..eb5ae8a6fc94 100644 --- a/io_uring/wait.h +++ b/io_uring/wait.h @@ -14,6 +14,21 @@ */ #define IO_CQ_WAKE_INIT (-1) +/* + * Start a wait cycle of the current task. The add that uses up ->cq_wait_nr + * may be one that queued its entry long ago and only now gets to look at the + * count. As nobody else wakes us after that, it has to find us sleeping, hence + * the task state must be visible before the count is. The barrier pairs with + * the xchg() in mpscq_push(), see io_req_local_work_add(). + */ +static inline void io_cq_wait_arm(struct io_ring_ctx *ctx, int nr_wait) +{ + __set_current_state(TASK_INTERRUPTIBLE); + atomic_set_release(&ctx->cq_wait_nr, nr_wait); + /* order the above against looking at the work list */ + smp_mb(); +} + struct ext_arg { size_t argsz; struct timespec64 ts;