The patch below does not apply to the 5.15-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable@xxxxxxxxxxxxxxx>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.15.y git checkout FETCH_HEAD git cherry-pick -x f58680085478dd292435727210122960d38e8014 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable@xxxxxxxxxxxxxxx>' --in-reply-to '1678099737150217@xxxxxxxxx' --subject-prefix 'PATCH 5.15.y' HEAD^.. Possible dependencies: f58680085478 ("io_uring: add reschedule point to handle_tw_list()") c6dd763c2460 ("io_uring: trace task_work_run") 3a0c037b0e16 ("io_uring: batch task_work") f88262e60bb9 ("io_uring: lockless task list") ed5ccb3beeba ("io_uring: remove priority tw list optimisation") 4a0fef62788b ("io_uring: optimize io_uring_task layout") 253993210bd8 ("io_uring: introduce locking helpers for CQE posting") 305bef988708 ("io_uring: hide eventfd assumptions in eventfd paths") d9dee4302a7c ("io_uring: remove ->flush_cqes optimisation") a830ffd28780 ("io_uring: move io_eventfd_signal()") 9046c6415be6 ("io_uring: reshuffle io_uring/io_uring.h") d142c3ec8d16 ("io_uring: remove extra io_commit_cqring()") 68494a65d0e2 ("io_uring: introduce io_req_cqe_overflow()") faf88dde060f ("io_uring: don't inline __io_get_cqe()") d245bca6375b ("io_uring: don't expose io_fill_cqe_aux()") 6a02e4be8187 ("io_uring: inline ->registered_rings") aa1e90f64ee5 ("io_uring: move small helpers to headers") aa1e90f64ee5 ("io_uring: move small helpers to headers") aa1e90f64ee5 ("io_uring: move small helpers to headers") aa1e90f64ee5 ("io_uring: move small helpers to headers") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From f58680085478dd292435727210122960d38e8014 Mon Sep 17 00:00:00 2001 From: Jens Axboe <axboe@xxxxxxxxx> Date: Fri, 27 Jan 2023 09:50:31 -0700 Subject: [PATCH] io_uring: add reschedule point to handle_tw_list() If CONFIG_PREEMPT_NONE is set and the task_work chains are long, we could be running into issues blocking others for too long. Add a reschedule check in handle_tw_list(), and flush the ctx if we need to reschedule. Cc: stable@xxxxxxxxxxxxxxx # 5.10+ Signed-off-by: Jens Axboe <axboe@xxxxxxxxx> diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index fab581a31dc1..acf6d9680d76 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -1179,10 +1179,16 @@ static unsigned int handle_tw_list(struct llist_node *node, /* if not contended, grab and improve batching */ *locked = mutex_trylock(&(*ctx)->uring_lock); percpu_ref_get(&(*ctx)->refs); - } + } else if (!*locked) + *locked = mutex_trylock(&(*ctx)->uring_lock); req->io_task_work.func(req, locked); node = next; count++; + if (unlikely(need_resched())) { + ctx_flush_and_put(*ctx, locked); + *ctx = NULL; + cond_resched(); + } } return count;
