From mboxrd@z Thu Jan 1 00:00:00 1970 Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.remote-ip=95.215.58.116 ARC-Seal: i=1; d=subspace.kernel.org; s=arc20261015; a=rsa-sha256; cv=none; t=1795289663; b=bsst3Dyi2K8wfHcBrs5/qmciDdPJde/RtdyLP4PsfVAjM4VthHqloezUXxb9KF4r2tv7 CedPfKW/zsUWTic87CxMLrUawIQJuJMDyIreUPv4xmZb6aQ+g3OuTcd8+qL9GTWn+fHeZ gTzcFQSiYfh4i0jGgsmfLHsCMLA+doYBSwxG/G1vgEVMTnvB453miTVBArhKj5HRrlRz4 cLICbmFzIPnEVrFC8osTMPSx900DxUzoioI2jRyxV66Cf/VWE9KXugdEo3O1gOoVkgLL1 65kp4WaxUK4ea1l1vjRhyD526q0XFHGG6REeUgAPEiRiRmB2SFIj5KBR2Nnssz4mRLg== ARC-Message-Signature: i=1; d=subspace.kernel.org; s=arc20261015; a=rsa-sha256; c=relaxed/relaxed; t=1795289663; h=DMARC-Filter:X-Envelope-To:DKIM-Signature:X-Envelope-To:Received: X-Mizu-Trace-ID:X-Migadu-Flow:Message-ID:Date:MIME-Version:User-Agent: Subject:To:Cc:References:From:In-Reply-To:Content-Type: Content-Transfer-Encoding; bh=ORTW/L5hh1DC9F6jjZky2W0T49vigeZuL6otjngyggU=; b=H8Gu3EZZApWkrtkqAtNSSGQ1t15gfek+7C0JOv43HKbdGGYvkTEzb7LljS1guur60qc4 Fnc+dXXWHVohlGeriuPWCEnQa3vTnU/R+hRguAUSA1vY4/3wr75i+LIDQOZWA6Xe2bh/F ffKfe3MEIYQL6v3xjW1l358TVw82rTx7+9SI4NJGZlYIuylo83rltCIlxy3fZiQuXYr7J WuJ0JZLu9t1ChaOXXtC7h5rTgTzTSerjqua0w9iKuPaiLPalOClperoBbAthqGMEHhZkJ 1lDLSiqMwv/FsdDMI4nVWZEAPPloGRWKPdH7afmQO0E/rDPlIL1QkEZWN3HljkRGgdw== ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass header.from=linux.dev; spf=pass smtp.mailfrom=linux.dev; dkim=pass header.d=linux.dev header.i=@linux.dev header.a=rsa-sha256 header.s=key1 header.b=DBB7aNQg; arc=none smtp.remote-ip=95.215.58.116 Received: from mta1.migadu.com (out-116.mta1.migadu.com [95.215.58.116]) (using TLSv1.3 with cipher TLS_AES_128_GCM_SHA256 (128/128 bits) key-exchange X25519 server-signature ECDSA (prime256v1) server-digest SHA256) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 19C69606A320 for ; Sat, 21 Nov 2026 19:34:21 +0000 (UTC) DMARC-Filter: OpenDMARC Filter v1.4.2 smtp.subspace.kernel.org 19C69606A320 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=linux.dev Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=linux.dev Authentication-Results: smtp.subspace.kernel.org; dkim=pass (1024-bit key, unprotected) header.d=linux.dev header.i=@linux.dev header.a=rsa-sha256 header.s=key1 header.b=DBB7aNQg X-Envelope-To: linux-rdma@vger.kernel.org DKIM-Signature: a=rsa-sha256; bh=I9C/bgiJfXHgW926J6D3HYkewXOwJxbleb9jrP9kCpY=; c=simple/simple; d=linux.dev; h=from:to:subject:date:message-id:mime-version:content-type; s=key1; t=1795289660; v=1; x=1795894460; b=DBB7aNQgauNKvIny4sl0fzklqH8l1slINVYmwr4Dvt7SIpQVqC7N3fR9hj8RwL+Or0EcXEW2 bRX3vKqgJ4HCaHdlj7PhB7H8WKtY8x/j+g8tnWL/+TlSnLvTNUeBnXsLb/hls7uhRk3WJoRXa4J pOIKgax3y+odp8A9btAkFVsQ= X-Envelope-To: linux-rdma@vger.kernel.org Received: by smtp.migadu.com with ESMTPS id 0be58bc518feca3e; Sat, 21 Nov 2026 19:34:20 +0000 X-Mizu-Trace-ID: 0be58bc518feca3e X-Migadu-Flow: FLOW_OUT Message-ID: <3a58ba4f-fd64-4144-8635-4b99983f7640@linux.dev> Date: Sat, 21 Nov 2026 11:34:12 -0800 X-Mailing-List: linux-rdma@vger.kernel.org List-Id: List-Post: List-Help: List-Subscribe: List-Unsubscribe: List-Owner: Precedence: list MIME-Version: 1.0 User-Agent: Mozilla Thunderbird Subject: Re: [PATCH rdma-next v2] RDMA/rxe: Mask the SQ producer index read from user space 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" References: From: Zhu Yanjun In-Reply-To: Content-Type: text/plain; charset=UTF-8; format=flowed Content-Transfer-Encoding: 8bit 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 */