From: Sasha Levin <sashal@kernel.org>
To: stable@vger.kernel.org
Cc: Joanne Koong <joannelkoong@gmail.com>,
Bernd Schubert <bernd@bsbernd.com>,
Miklos Szeredi <mszeredi@redhat.com>,
Sasha Levin <sashal@kernel.org>
Subject: [PATCH 6.18.y 3/3] fuse: fix missing barrier when checking io-uring readiness
Date: Mon, 31 Aug 2026 12:42:50 -0400 [thread overview]
Message-ID: <20260831164250.269934-3-sashal@kernel.org> (raw)
In-Reply-To: <20260831164250.269934-1-sashal@kernel.org>
From: Joanne Koong <joannelkoong@gmail.com>
[ Upstream commit edb310bc27f0ad83e7fd558a3caf1a94ca511654 ]
fuse_block_alloc() reads fch->initialized and then fch->io_uring.
fch->io_uring is set before fch->initialized, ordered by the smp_wmb()
in fuse_chan_set_intialized(), but fuse_block_alloc() has no matching
read barrier between the two loads.
This may lead a CPU to observe fch->initialized=1 but fch->io_uring=0,
and skip the check that blocks request allocation until the io-uring
queues are ready. This can reintroduce the lock-order inversion deadlock
that commit 3393ff964e0f prevents.
Add an smp_rmb() barrier to pair with the smp_wmb() in
fuse_chan_set_initialized() to prevent this.
Fixes: 3393ff964e0f ("fuse: block request allocation until io-uring init is complete")
Cc: stable@vger.kernel.org
Reviewed-by: Bernd Schubert <bernd@bsbernd.com>
Signed-off-by: Joanne Koong <joannelkoong@gmail.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
[ renamed `fch`/`struct fuse_chan` to `fc`/`struct fuse_conn` and `fuse_chan_set_initialized()` to `fuse_set_initialized()` in the comment ]
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
fs/fuse/dev.c | 10 +++++++---
1 file changed, 7 insertions(+), 3 deletions(-)
diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index 8a38a263295fe..33e01d67e5151 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -172,7 +172,13 @@ void fuse_set_initialized(struct fuse_conn *fc)
static bool fuse_block_alloc(struct fuse_conn *fc, bool for_background)
{
- return !fc->initialized || (for_background && fc->blocked) ||
+ if (!fc->initialized)
+ return true;
+
+ /* Pairs with smp_wmb() in fuse_set_initialized() */
+ smp_rmb();
+
+ return (for_background && fc->blocked) ||
(fc->io_uring && fc->connected && !fuse_uring_ready(fc));
}
@@ -212,8 +218,6 @@ static struct fuse_req *fuse_get_req(struct mnt_idmap *idmap,
(TASK_KILLABLE | TASK_FREEZABLE)))
goto out;
}
- /* Matches smp_wmb() in fuse_set_initialized() */
- smp_rmb();
err = -ENOTCONN;
if (!fc->connected)
--
2.53.0
prev parent reply other threads:[~2026-08-31 16:42 UTC|newest]
Thread overview: 4+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-08-31 12:22 FAILED: patch "[PATCH] fuse: fix missing barrier when checking io-uring readiness" failed to apply to 6.18-stable tree gregkh
2026-08-31 16:42 ` [PATCH 6.18.y 1/3] fuse: split off fuse_args and related definitions into a separate header Sasha Levin
2026-08-31 16:42 ` [PATCH 6.18.y 2/3] fuse: remove fm arg of args->end callback Sasha Levin
2026-08-31 16:42 ` Sasha Levin [this message]
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20260831164250.269934-3-sashal@kernel.org \
--to=sashal@kernel.org \
--cc=bernd@bsbernd.com \
--cc=joannelkoong@gmail.com \
--cc=mszeredi@redhat.com \
--cc=stable@vger.kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox