From: Zhu Yanjun <yanjun.zhu@linux.dev>
To: Shuai Liu <847807867@qq.com>, linux-rdma@vger.kernel.org
Cc: zyjzyj2000@gmail.com, jgg@ziepe.ca, leon@kernel.org,
rpearsonhpe@gmail.com,
syzbot+fef38133c495aeb48297@syzkaller.appspotmail.com,
syzkaller-bugs@googlegroups.com, linux-kernel@vger.kernel.org,
sashiko-reviews@lists.linux.dev,
"yanjun.zhu@linux.dev" <yanjun.zhu@linux.dev>
Subject: Re: [PATCH rdma-next v2] RDMA/rxe: Mask the SQ producer index read from user space
Date: Sat, 21 Nov 2026 11:34:12 -0800 [thread overview]
Message-ID: <3a58ba4f-fd64-4144-8635-4b99983f7640@linux.dev> (raw)
In-Reply-To: <tencent_BEE58D9BBE7109C47C2796DDF5A4B958F609@qq.com>
在 2026/11/20 19:46, Shuai Liu 写道:
> The send queue producer index of a user space QP is stored in the
> queue buffer which is shared with and written by user space. The
> requester reads it without any validation in req_retry() and
> __req_next_wqe() and compares it against its own local index which
> is always masked.
>
> The requester stops processing WQEs when its local WQE index equals
> the producer index. If user space writes an out of range producer
> index into the queue buffer, that comparison can never become true.
> Once the QP is put into the error state, rxe_requester() then keeps
> flushing WQEs forever: the flush path advances the WQE index with the
> masked queue_next_index() but the producer index stays out of range,
> and each pass calls rxe_qp_error() which reschedules the send task,
> so the loop never converges. The send task holds a reference to the
> QP for as long as this lasts, so ib_destroy_qp() waits for the QP
> reference to drop until it times out after 50 seconds and the
> WARN_ON(!ret) fires in __rxe_cleanup():
>
> WARNING: drivers/infiniband/sw/rxe/rxe_pool.c:212 at __rxe_cleanup
> Call Trace:
> __rxe_cleanup
> rxe_destroy_qp
> ...
> rxe0: qp#17 rxe_destroy_qp: cleanup failed, err = -110
>
> Fix this by masking the producer index with q->index_mask when reading
> it in queue_get_producer() for QUEUE_TYPE_FROM_CLIENT. This restores
> what producer_index() did before commit ae6e843fe08d ("RDMA/rxe: Add memory
> barriers to kernel queues") replaced it with queue_get_producer() and
> dropped the mask, and keeps the requester, the completer and the queue
> helpers, which all compare the difference of the two indices modulo
> index_mask, consistent. rxe_qp_init_req() also initializes
> qp->req.wqe_index from this value so it gets validated as well.
>
> Masking the index in queue_get_producer() instead of checking it at
> the two requester call sites was suggested by the Sashiko AI review of
> v1 of this patch.
>
> Verified with the syzbot reproducer in QEMU: without this patch every
> destroy_qp hangs for 50 seconds and hits the WARNING above; with this
> patch the reproducer runs cleanly.
Thanks for the patch. A couple of questions/comments on this:
The commit message mentions that this fix was verified with the syzbot
reproducer in QEMU, but I didn't see any corresponding verification
email or test report thread on the list. Could you please share the
link/reference to that email or provide a bit more detail on the test
setup and baseline kernel used for verification?
In queue_get_producer(), there are also other queue types such as
QUEUE_TYPE_TO_CLIENT, QUEUE_TYPE_FROM_ULP, and QUEUE_TYPE_TO_ULP. Have
you checked whether any of those types could suffer from a similar
out-of-range producer index issue? If so, please let us know and include
any necessary fixes (either here or in a follow-up patch, as appropriate).
Thanks a lot.
Yanjun Zhu
>
> Reported-by: syzbot+fef38133c495aeb48297@syzkaller.appspotmail.com
> Closes: https://syzkaller.appspot.com/bug?extid=fef38133c495aeb48297
> Fixes: ae6e843fe08d ("RDMA/rxe: Add memory barriers to kernel queues")
> Signed-off-by: Shuai Liu <847807867@qq.com>
> ---
> Changes since v1:
> - Mask the producer index in queue_get_producer() for
> QUEUE_TYPE_FROM_CLIENT instead of checking it at the two requester
> call sites, as suggested by the Sashiko AI review of v1. This also
> covers rxe_qp_init_req(), which initializes qp->req.wqe_index from
> the same value, and keeps the requester, the completer and the queue
> helpers consistent with each other.
> - Point Fixes at commit ae6e843fe08d, which dropped the mask that
> producer_index() had, instead of commit 5bcf5a59c41e.
> - Reword the commit message: the flush loop never converges because
> the WQE index is advanced with the masked queue_next_index() while
> the producer index stays out of range; the req_retry() reset detail
> in the v1 description was inaccurate.
> - Update the subject to describe the actual mechanism.
>
> drivers/infiniband/sw/rxe/rxe_queue.h | 1 +
> 1 file changed, 1 insertion(+)
>
> diff --git a/drivers/infiniband/sw/rxe/rxe_queue.h b/drivers/infiniband/sw/rxe/rxe_queue.h
> index c711cb98b9496..fe65aecc60464 100644
> --- a/drivers/infiniband/sw/rxe/rxe_queue.h
> +++ b/drivers/infiniband/sw/rxe/rxe_queue.h
> @@ -106,6 +106,7 @@ static inline u32 queue_get_producer(const struct rxe_queue *q,
> case QUEUE_TYPE_FROM_CLIENT:
> /* used by rxe, client owns the index */
> prod = smp_load_acquire(&q->buf->producer_index);
> + prod &= q->index_mask;
> break;
> case QUEUE_TYPE_TO_CLIENT:
> /* used by rxe which owns the index */
prev parent reply other threads:[~2026-11-21 19:34 UTC|newest]
Thread overview: 7+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-10-23 12:35 [syzbot] [rdma?] WARNING in __rxe_cleanup syzbot
2026-10-24 3:31 ` Zhu Yanjun
2026-11-19 21:03 ` syzbot
2026-11-20 11:42 ` [PATCH rdma-next v1] RDMA/rxe: Don't trust the user space SQ producer index Shuai Liu
2026-11-21 3:42 ` [PATCH] RDMA/rxe: Mask the SQ producer index read from user space Shuai Liu
2026-11-21 3:46 ` [PATCH rdma-next v2] " Shuai Liu
2026-11-21 19:34 ` Zhu Yanjun [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=3a58ba4f-fd64-4144-8635-4b99983f7640@linux.dev \
--to=yanjun.zhu@linux.dev \
--cc=847807867@qq.com \
--cc=jgg@ziepe.ca \
--cc=leon@kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-rdma@vger.kernel.org \
--cc=rpearsonhpe@gmail.com \
--cc=sashiko-reviews@lists.linux.dev \
--cc=syzbot+fef38133c495aeb48297@syzkaller.appspotmail.com \
--cc=syzkaller-bugs@googlegroups.com \
--cc=zyjzyj2000@gmail.com \
/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