LKML Archive on lore.kernel.org
help / color / mirror / Atom feed
From: Sasha Levin <sashal@kernel.org>
To: linux-kernel@vger.kernel.org, stable@vger.kernel.org
Cc: Gerd Rausch <gerd.rausch@oracle.com>,
	Santosh Shilimkar <santosh.shilimkar@oracle.com>,
	Jakub Kicinski <kuba@kernel.org>, Sasha Levin <sashal@kernel.org>,
	netdev@vger.kernel.org, linux-rdma@vger.kernel.org,
	rds-devel@oss.oracle.com
Subject: [PATCH AUTOSEL 5.10 18/18] net/rds: dma_map_sg is entitled to merge entries
Date: Mon, 23 Aug 2021 20:54:32 -0400	[thread overview]
Message-ID: <20210824005432.631154-18-sashal@kernel.org> (raw)
In-Reply-To: <20210824005432.631154-1-sashal@kernel.org>

From: Gerd Rausch <gerd.rausch@oracle.com>

[ Upstream commit fb4b1373dcab086d0619c29310f0466a0b2ceb8a ]

Function "dma_map_sg" is entitled to merge adjacent entries
and return a value smaller than what was passed as "nents".

Subsequently "ib_map_mr_sg" needs to work with this value ("sg_dma_len")
rather than the original "nents" parameter ("sg_len").

This old RDS bug was exposed and reliably causes kernel panics
(using RDMA operations "rds-stress -D") on x86_64 starting with:
commit c588072bba6b ("iommu/vt-d: Convert intel iommu driver to the iommu ops")

Simply put: Linux 5.11 and later.

Signed-off-by: Gerd Rausch <gerd.rausch@oracle.com>
Acked-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
Link: https://lore.kernel.org/r/60efc69f-1f35-529d-a7ef-da0549cad143@oracle.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/rds/ib_frmr.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/rds/ib_frmr.c b/net/rds/ib_frmr.c
index 9b6ffff72f2d..28c1b0022178 100644
--- a/net/rds/ib_frmr.c
+++ b/net/rds/ib_frmr.c
@@ -131,9 +131,9 @@ static int rds_ib_post_reg_frmr(struct rds_ib_mr *ibmr)
 		cpu_relax();
 	}
 
-	ret = ib_map_mr_sg_zbva(frmr->mr, ibmr->sg, ibmr->sg_len,
+	ret = ib_map_mr_sg_zbva(frmr->mr, ibmr->sg, ibmr->sg_dma_len,
 				&off, PAGE_SIZE);
-	if (unlikely(ret != ibmr->sg_len))
+	if (unlikely(ret != ibmr->sg_dma_len))
 		return ret < 0 ? ret : -EINVAL;
 
 	if (cmpxchg(&frmr->fr_state,
-- 
2.30.2


      parent reply	other threads:[~2021-08-24  0:58 UTC|newest]

Thread overview: 19+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-08-24  0:54 [PATCH AUTOSEL 5.10 01/18] iwlwifi: pnvm: accept multiple HW-type TLVs Sasha Levin
2021-08-24  0:54 ` [PATCH AUTOSEL 5.10 02/18] opp: remove WARN when no valid OPPs remain Sasha Levin
2021-08-24  0:54 ` [PATCH AUTOSEL 5.10 03/18] cpufreq: blocklist Qualcomm sm8150 in cpufreq-dt-platdev Sasha Levin
2021-08-24  0:54 ` [PATCH AUTOSEL 5.10 04/18] virtio: Improve vq->broken access to avoid any compiler optimization Sasha Levin
2021-08-24  0:54 ` [PATCH AUTOSEL 5.10 05/18] virtio_pci: Support surprise removal of virtio pci device Sasha Levin
2021-08-24  0:54 ` [PATCH AUTOSEL 5.10 06/18] virtio_vdpa: reject invalid vq indices Sasha Levin
2021-08-24  0:54 ` [PATCH AUTOSEL 5.10 07/18] vringh: Use wiov->used to check for read/write desc order Sasha Levin
2021-08-24  0:54 ` [PATCH AUTOSEL 5.10 08/18] tools/virtio: fix build Sasha Levin
2021-08-24  0:54 ` [PATCH AUTOSEL 5.10 09/18] qed: qed ll2 race condition fixes Sasha Levin
2021-08-24  0:54 ` [PATCH AUTOSEL 5.10 10/18] qed: Fix null-pointer dereference in qed_rdma_create_qp() Sasha Levin
2021-08-24  0:54 ` [PATCH AUTOSEL 5.10 11/18] Revert "drm/amd/pm: fix workload mismatch on vega10" Sasha Levin
2021-08-24  0:54 ` [PATCH AUTOSEL 5.10 12/18] drm/amd/pm: change the workload type for some cards Sasha Levin
2021-08-24  0:54 ` [PATCH AUTOSEL 5.10 13/18] blk-mq: don't grab rq's refcount in blk_mq_check_expired() Sasha Levin
2021-08-24  0:54 ` [PATCH AUTOSEL 5.10 14/18] drm: Copy drm_wait_vblank to user before returning Sasha Levin
2021-08-24  0:54 ` [PATCH AUTOSEL 5.10 15/18] drm/nouveau/disp: power down unused DP links during init Sasha Levin
2021-08-24  0:54 ` [PATCH AUTOSEL 5.10 16/18] drm/nouveau/kms/nv50: workaround EFI GOP window channel format differences Sasha Levin
2021-08-24 17:07   ` Lyude Paul
2021-08-24  0:54 ` [PATCH AUTOSEL 5.10 17/18] drm/nouveau: block a bunch of classes from userspace Sasha Levin
2021-08-24  0:54 ` 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=20210824005432.631154-18-sashal@kernel.org \
    --to=sashal@kernel.org \
    --cc=gerd.rausch@oracle.com \
    --cc=kuba@kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-rdma@vger.kernel.org \
    --cc=netdev@vger.kernel.org \
    --cc=rds-devel@oss.oracle.com \
    --cc=santosh.shilimkar@oracle.com \
    --cc=stable@vger.kernel.org \
    --subject='Re: [PATCH AUTOSEL 5.10 18/18] net/rds: dma_map_sg is entitled to merge entries' \
    /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

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).