From a06577ea675a19ddcc8914831313ec3ec2ced26c Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Mon, 13 Sep 2021 09:20:44 -0600
Subject: [PATCH] io-wq: fix wakeup race when adding new work
Git-commit: 87df7fb922d18e96992aa5e824aa34b2065fef59
Patch-mainline: v5.15-rc1
References: stable-5.14.6
commit 87df7fb922d18e96992aa5e824aa34b2065fef59 upstream.
When new work is added, io_wqe_enqueue() checks if we need to wake or
create a new worker. But that check is done outside the lock that
otherwise synchronizes us with a worker going to sleep, so we can end
up in the following situation:
CPU0 CPU1
lock
insert work
unlock
atomic_read(nr_running) != 0
lock
atomic_dec(nr_running)
no wakeup needed
Hold the wqe lock around the "need to wakeup" check. Then we can also get
rid of the temporary work_flags variable, as we know the work will remain
valid as long as we hold the lock.
Cc: stable@vger.kernel.org
Reported-by: Andres Freund <andres@anarazel.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Acked-by: Takashi Iwai <tiwai@suse.de>
---
fs/io-wq.c | 8 ++++----
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/fs/io-wq.c b/fs/io-wq.c
index 2cc7f75ff24d..22ac9806d215 100644
--- a/fs/io-wq.c
+++ b/fs/io-wq.c
@@ -793,7 +793,7 @@ static void io_wqe_insert_work(struct io_wqe *wqe, struct io_wq_work *work)
static void io_wqe_enqueue(struct io_wqe *wqe, struct io_wq_work *work)
{
struct io_wqe_acct *acct = io_work_get_acct(wqe, work);
- int work_flags;
+ bool do_wake;
unsigned long flags;
/*
@@ -806,14 +806,14 @@ static void io_wqe_enqueue(struct io_wqe *wqe, struct io_wq_work *work)
return;
}
- work_flags = work->flags;
raw_spin_lock_irqsave(&wqe->lock, flags);
io_wqe_insert_work(wqe, work);
wqe->flags &= ~IO_WQE_FLAG_STALLED;
+ do_wake = (work->flags & IO_WQ_WORK_CONCURRENT) ||
+ !atomic_read(&acct->nr_running);
raw_spin_unlock_irqrestore(&wqe->lock, flags);
- if ((work_flags & IO_WQ_WORK_CONCURRENT) ||
- !atomic_read(&acct->nr_running))
+ if (do_wake)
io_wqe_wake_worker(wqe, acct);
}
--
2.26.2