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(a)vger.kernel.org>.
Possible dependencies:
12521a5d5cb7 ("io_uring: fix CQ waiting timeout handling")
35d90f95cfa7 ("io_uring: include task_work run after scheduling in wait for events")
3a08576b96e3 ("io_uring: remove check_cq checking from hot paths")
ed29b0b4fd83 ("io_uring: move to separate directory")
155bc9505dbd ("io_uring: return an error when cqe is dropped")
10988a0a67ba ("io_uring: use constants for cq_overflow bitfield")
3e813c902672 ("io_uring: rework io_uring_enter to simplify return value")
cef216fc32d7 ("io_uring: explicitly keep a CQE in io_kiocb")
b4f20bb4e6d5 ("io_uring: move finish_wait() outside of loop in cqring_wait()")
d487b43cd327 ("io_uring: optimise mutex locking for submit+iopoll")
773697b610bf ("io_uring: pre-calculate syscall iopolling decision")
f81440d33cc6 ("io_uring: split off IOPOLL argument verifiction")
b605a7fabb60 ("io_uring: move poll recycling later in compl flushing")
a538be5be328 ("io_uring: optimise io_free_batch_list")
c0713540f6d5 ("io_uring: fix leaks on IOPOLL and CQE_SKIP")
323b190ba2de ("io_uring: free iovec if file assignment fails")
7179c3ce3dbf ("io_uring: fix poll error reporting")
cce64ef01308 ("io_uring: fix poll file assign deadlock")
82733d168cbd ("io_uring: stop using io_wq_work as an fd placeholder")
2804ecd8d3e3 ("io_uring: move apoll->events cache")
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From 12521a5d5cb7ff0ad43eadfc9c135d86e1131fa8 Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence(a)gmail.com>
Date: Thu, 5 Jan 2023 10:49:15 +0000
Subject: [PATCH] io_uring: fix CQ waiting timeout handling
Jiffy to ktime CQ waiting conversion broke how we treat timeouts, in
particular we rearm it anew every time we get into
io_cqring_wait_schedule() without adjusting the timeout. Waiting for 2
CQEs and getting a task_work in the middle may double the timeout value,
or even worse in some cases task may wait indefinitely.
Cc: stable(a)vger.kernel.org
Fixes: 228339662b398 ("io_uring: don't convert to jiffies for waiting on timeouts")
Signed-off-by: Pavel Begunkov <asml.silence(a)gmail.com>
Link: https://lore.kernel.org/r/f7bffddd71b08f28a877d44d37ac953ddb01590d.16729156…
Signed-off-by: Jens Axboe <axboe(a)kernel.dk>
diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index 472574192dd6..2ac1cd8d23ea 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -2470,7 +2470,7 @@ int io_run_task_work_sig(struct io_ring_ctx *ctx)
/* when returns >0, the caller should retry */
static inline int io_cqring_wait_schedule(struct io_ring_ctx *ctx,
struct io_wait_queue *iowq,
- ktime_t timeout)
+ ktime_t *timeout)
{
int ret;
unsigned long check_cq;
@@ -2488,7 +2488,7 @@ static inline int io_cqring_wait_schedule(struct io_ring_ctx *ctx,
if (check_cq & BIT(IO_CHECK_CQ_DROPPED_BIT))
return -EBADR;
}
- if (!schedule_hrtimeout(&timeout, HRTIMER_MODE_ABS))
+ if (!schedule_hrtimeout(timeout, HRTIMER_MODE_ABS))
return -ETIME;
/*
@@ -2564,7 +2564,7 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events,
}
prepare_to_wait_exclusive(&ctx->cq_wait, &iowq.wq,
TASK_INTERRUPTIBLE);
- ret = io_cqring_wait_schedule(ctx, &iowq, timeout);
+ ret = io_cqring_wait_schedule(ctx, &iowq, &timeout);
if (__io_cqring_events_user(ctx) >= min_events)
break;
cond_resched();