From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
To: linux-kernel@vger.kernel.org
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
stable@vger.kernel.org, Eli Cohen <eli@mellanox.com>,
Leon Romanovsky <leon@kernel.org>,
Doug Ledford <dledford@redhat.com>
Subject: [PATCH 3.14 35/46] IB/mlx5: Fix post send fence logic
Date: Thu, 18 Aug 2016 15:54:57 +0200 [thread overview]
Message-ID: <20160818135447.600782512@linuxfoundation.org> (raw)
In-Reply-To: <20160818135442.457400364@linuxfoundation.org>
3.14-stable review patch. If anyone has any objections, please let me know.
------------------
From: Eli Cohen <eli@mellanox.com>
commit c9b254955b9f8814966f5dabd34c39d0e0a2b437 upstream.
If the caller specified IB_SEND_FENCE in the send flags of the work
request and no previous work request stated that the successive one
should be fenced, the work request would be executed without a fence.
This could result in RDMA read or atomic operations failure due to a MR
being invalidated. Fix this by adding the mlx5 enumeration for fencing
RDMA/atomic operations and fix the logic to apply this.
Fixes: e126ba97dba9 ('mlx5: Add driver for Mellanox Connect-IB adapters')
Signed-off-by: Eli Cohen <eli@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Doug Ledford <dledford@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
drivers/infiniband/hw/mlx5/qp.c | 7 ++++---
include/linux/mlx5/qp.h | 1 +
2 files changed, 5 insertions(+), 3 deletions(-)
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -2037,10 +2037,11 @@ static u8 get_fence(u8 fence, struct ib_
return MLX5_FENCE_MODE_SMALL_AND_FENCE;
else
return fence;
-
- } else {
- return 0;
+ } else if (unlikely(wr->send_flags & IB_SEND_FENCE)) {
+ return MLX5_FENCE_MODE_FENCE;
}
+
+ return 0;
}
int mlx5_ib_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
--- a/include/linux/mlx5/qp.h
+++ b/include/linux/mlx5/qp.h
@@ -137,6 +137,7 @@ enum {
enum {
MLX5_FENCE_MODE_NONE = 0 << 5,
MLX5_FENCE_MODE_INITIATOR_SMALL = 1 << 5,
+ MLX5_FENCE_MODE_FENCE = 2 << 5,
MLX5_FENCE_MODE_STRONG_ORDERING = 3 << 5,
MLX5_FENCE_MODE_SMALL_AND_FENCE = 4 << 5,
};
next prev parent reply other threads:[~2016-08-18 13:56 UTC|newest]
Thread overview: 34+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <CGME20160818135526uscas1p209dc90415100838cf7c73a2d19ca32a3@uscas1p2.samsung.com>
2016-08-18 13:54 ` [PATCH 3.14 00/46] 3.14.77-stable review Greg Kroah-Hartman
2016-08-18 13:54 ` [PATCH 3.14 01/46] tcp: make challenge acks faster Greg Kroah-Hartman
2016-08-18 13:54 ` [PATCH 3.14 02/46] usb: renesas_usbhs: protect the CFIFOSEL setting in usbhsg_ep_enable() Greg Kroah-Hartman
2016-08-18 13:54 ` [PATCH 3.14 11/46] cifs: Check for existing directory when opening file with O_CREAT Greg Kroah-Hartman
2016-08-18 13:54 ` [PATCH 3.14 12/46] cifs: fix crash due to race in hmac(md5) handling Greg Kroah-Hartman
2016-08-18 13:54 ` [PATCH 3.14 14/46] random: properly align get_random_int_hash Greg Kroah-Hartman
2016-08-19 3:14 ` Eric Biggers
2016-08-19 7:33 ` Greg Kroah-Hartman
2016-08-18 13:54 ` [PATCH 3.14 15/46] random: print a warning for the first ten uninitialized random users Greg Kroah-Hartman
2016-08-18 13:54 ` [PATCH 3.14 16/46] [PATCH BACKPORT 3.10-3.15 1/4] MIPS: KVM: Fix mapped fault broken commpage handling Greg Kroah-Hartman
2016-08-18 13:54 ` [PATCH 3.14 17/46] [PATCH BACKPORT 3.10-3.15 2/4] MIPS: KVM: Add missing gfn range check Greg Kroah-Hartman
2016-08-18 13:54 ` [PATCH 3.14 18/46] [PATCH BACKPORT 3.10-3.15 3/4] MIPS: KVM: Fix gfn range check in kseg0 tlb faults Greg Kroah-Hartman
2016-08-18 13:54 ` [PATCH 3.14 19/46] [PATCH BACKPORT 3.10-3.15 4/4] MIPS: KVM: Propagate kseg0/mapped tlb fault errors Greg Kroah-Hartman
2016-08-18 13:54 ` [PATCH 3.14 20/46] nfs: dont create zero-length requests Greg Kroah-Hartman
2016-08-18 13:54 ` [PATCH 3.14 30/46] balloon: check the number of available pages in leak balloon Greg Kroah-Hartman
2016-08-18 13:54 ` [PATCH 3.14 31/46] ftrace/recordmcount: Work around for addition of metag magic but not relocations Greg Kroah-Hartman
2016-08-18 13:54 ` [PATCH 3.14 32/46] metag: Fix __cmpxchg_u32 asm constraint for CMP Greg Kroah-Hartman
2016-08-18 13:54 ` [PATCH 3.14 33/46] IB/mlx5: Fix MODIFY_QP command input structure Greg Kroah-Hartman
2016-08-18 13:54 ` [PATCH 3.14 34/46] IB/mlx5: Fix returned values of query QP Greg Kroah-Hartman
2016-08-18 13:54 ` Greg Kroah-Hartman [this message]
2016-08-18 13:54 ` [PATCH 3.14 36/46] IB/IPoIB: Dont update neigh validity for unresolved entries Greg Kroah-Hartman
2016-08-18 13:54 ` [PATCH 3.14 37/46] IB/mlx4: Fix the SQ size of an RC QP Greg Kroah-Hartman
2016-08-18 13:55 ` [PATCH 3.14 38/46] ubi: Make volume resize power cut aware Greg Kroah-Hartman
2016-08-18 13:55 ` [PATCH 3.14 39/46] ubi: Fix race condition between ubi device creation and udev Greg Kroah-Hartman
2016-08-18 13:55 ` [PATCH 3.14 40/46] target: Fix race between iscsi-target connection shutdown + ABORT_TASK Greg Kroah-Hartman
2016-08-18 13:55 ` [PATCH 3.14 41/46] target: Fix max_unmap_lba_count calc overflow Greg Kroah-Hartman
2016-08-18 13:55 ` [PATCH 3.14 42/46] Input: i8042 - break load dependency between atkbd/psmouse and i8042 Greg Kroah-Hartman
2016-08-18 13:55 ` [PATCH 3.14 43/46] PCI: Mark Atheros AR9485 and QCA9882 to avoid bus reset Greg Kroah-Hartman
2016-08-18 13:55 ` [PATCH 3.14 44/46] dm flakey: error READ bios during the down_interval Greg Kroah-Hartman
2016-08-18 13:55 ` [PATCH 3.14 45/46] module: Invalidate signatures on force-loaded modules Greg Kroah-Hartman
2016-08-18 13:55 ` [PATCH 3.14 46/46] Documentation/module-signing.txt: Note need for version info if reusing a key Greg Kroah-Hartman
2016-08-18 20:05 ` [PATCH 3.14 00/46] 3.14.77-stable review Guenter Roeck
2016-08-19 7:38 ` Greg Kroah-Hartman
2016-08-18 21:34 ` Shuah Khan
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=20160818135447.600782512@linuxfoundation.org \
--to=gregkh@linuxfoundation.org \
--cc=dledford@redhat.com \
--cc=eli@mellanox.com \
--cc=leon@kernel.org \
--cc=linux-kernel@vger.kernel.org \
--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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.