[ upstream commit 45500dc4e01c167ee063f3dcc22f51ced5b2b1e9 ]
io-wq will retry iopoll even when it failed with -EAGAIN. If that races with task exit, which sets TIF_NOTIFY_SIGNAL for all its workers, such workers might potentially infinitely spin retrying iopoll again and again and each time failing on some allocation / waiting / etc. Don't keep spinning if io-wq is dying.
Fixes: 561fb04a6a225 ("io_uring: replace workqueue usage with io-wq") Cc: stable@vger.kernel.org Signed-off-by: Pavel Begunkov asml.silence@gmail.com Signed-off-by: Jens Axboe axboe@kernel.dk --- io_uring/io-wq.c | 10 ++++++++++ io_uring/io-wq.h | 1 + io_uring/io_uring.c | 3 ++- 3 files changed, 13 insertions(+), 1 deletion(-)
diff --git a/io_uring/io-wq.c b/io_uring/io-wq.c index 81485c1a9879..fe8594a0396c 100644 --- a/io_uring/io-wq.c +++ b/io_uring/io-wq.c @@ -176,6 +176,16 @@ static void io_worker_ref_put(struct io_wq *wq) complete(&wq->worker_done); }
+bool io_wq_worker_stopped(void) +{ + struct io_worker *worker = current->pf_io_worker; + + if (WARN_ON_ONCE(!io_wq_current_is_worker())) + return true; + + return test_bit(IO_WQ_BIT_EXIT, &worker->wqe->wq->state); +} + static void io_worker_cancel_cb(struct io_worker *worker) { struct io_wqe_acct *acct = io_wqe_get_acct(worker); diff --git a/io_uring/io-wq.h b/io_uring/io-wq.h index bf5c4c533760..48721cbd5f40 100644 --- a/io_uring/io-wq.h +++ b/io_uring/io-wq.h @@ -129,6 +129,7 @@ void io_wq_hash_work(struct io_wq_work *work, void *val);
int io_wq_cpu_affinity(struct io_wq *wq, cpumask_var_t mask); int io_wq_max_workers(struct io_wq *wq, int *new_count); +bool io_wq_worker_stopped(void);
static inline bool io_wq_is_hashed(struct io_wq_work *work) { diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index fec6b6a409e7..077c9527be37 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -7069,7 +7069,8 @@ static void io_wq_submit_work(struct io_wq_work *work) */ if (ret != -EAGAIN || !(req->ctx->flags & IORING_SETUP_IOPOLL)) break; - + if (io_wq_worker_stopped()) + break; /* * If REQ_F_NOWAIT is set, then don't wait or retry with * poll. -EAGAIN is final for that case.