stable.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Sasha Levin <sashal@kernel.org>
To: linux-kernel@vger.kernel.org, stable@vger.kernel.org
Cc: Chuck Lever <chuck.lever@oracle.com>,
	Jason Gunthorpe <jgg@mellanox.com>,
	Sasha Levin <sashal@kernel.org>,
	linux-rdma@vger.kernel.org
Subject: [PATCH AUTOSEL 4.14 14/53] rxe: IB_WR_REG_MR does not capture MR's iova field
Date: Tue,  8 Jan 2019 14:31:42 -0500	[thread overview]
Message-ID: <20190108193222.123316-14-sashal@kernel.org> (raw)
In-Reply-To: <20190108193222.123316-1-sashal@kernel.org>

From: Chuck Lever <chuck.lever@oracle.com>

[ Upstream commit b024dd0eba6e6d568f69d63c5e3153aba94c23e3 ]

FRWR memory registration is done with a series of calls and WRs.
1. ULP invokes ib_dma_map_sg()
2. ULP invokes ib_map_mr_sg()
3. ULP posts an IB_WR_REG_MR on the Send queue

Step 2 generates an iova. It is permissible for ULPs to change this
iova (with certain restrictions) between steps 2 and 3.

rxe_map_mr_sg captures the MR's iova but later when rxe processes the
REG_MR WR, it ignores the MR's iova field. If a ULP alters the MR's iova
after step 2 but before step 3, rxe never captures that change.

When the remote sends an RDMA Read targeting that MR, rxe looks up the
R_key, but the altered iova does not match the iova stored in the MR,
causing the RDMA Read request to fail.

Reported-by: Anna Schumaker <schumaker.anna@gmail.com>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/infiniband/sw/rxe/rxe_req.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/infiniband/sw/rxe/rxe_req.c b/drivers/infiniband/sw/rxe/rxe_req.c
index de853bcc2384..08ae4f3a6a37 100644
--- a/drivers/infiniband/sw/rxe/rxe_req.c
+++ b/drivers/infiniband/sw/rxe/rxe_req.c
@@ -640,6 +640,7 @@ int rxe_requester(void *arg)
 			rmr->access = wqe->wr.wr.reg.access;
 			rmr->lkey = wqe->wr.wr.reg.key;
 			rmr->rkey = wqe->wr.wr.reg.key;
+			rmr->iova = wqe->wr.wr.reg.mr->iova;
 			wqe->state = wqe_state_done;
 			wqe->status = IB_WC_SUCCESS;
 		} else {
-- 
2.19.1


  parent reply	other threads:[~2019-01-08 19:47 UTC|newest]

Thread overview: 53+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-01-08 19:31 [PATCH AUTOSEL 4.14 01/53] gpio: pl061: Move irq_chip definition inside struct pl061 Sasha Levin
2019-01-08 19:31 ` [PATCH AUTOSEL 4.14 02/53] platform/x86: asus-wmi: Tell the EC the OS will handle the display off hotkey Sasha Levin
2019-01-08 19:31 ` [PATCH AUTOSEL 4.14 03/53] e1000e: allow non-monotonic SYSTIM readings Sasha Levin
2019-01-08 19:31 ` [PATCH AUTOSEL 4.14 04/53] writeback: don't decrement wb->refcnt if !wb->bdi Sasha Levin
2019-01-08 19:31 ` [PATCH AUTOSEL 4.14 05/53] serial: set suppress_bind_attrs flag only if builtin Sasha Levin
2019-01-08 19:31 ` [PATCH AUTOSEL 4.14 06/53] ALSA: oxfw: add support for APOGEE duet FireWire Sasha Levin
2019-01-08 19:31 ` [PATCH AUTOSEL 4.14 07/53] x86/mce: Fix -Wmissing-prototypes warnings Sasha Levin
2019-01-08 19:31 ` [PATCH AUTOSEL 4.14 08/53] MIPS: SiByte: Enable swiotlb for SWARM, LittleSur and BigSur Sasha Levin
2019-01-08 19:31 ` [PATCH AUTOSEL 4.14 09/53] arm64: perf: set suppress_bind_attrs flag to true Sasha Levin
2019-01-08 19:31 ` [PATCH AUTOSEL 4.14 10/53] USB: serial: ftdi_sio: use rounding when calculating baud rate divisors Sasha Levin
2019-01-08 19:31 ` [PATCH AUTOSEL 4.14 11/53] usb: gadget: udc: renesas_usb3: add a safety connection way for forced_b_device Sasha Levin
2019-01-08 19:31 ` [PATCH AUTOSEL 4.14 12/53] selinux: always allow mounting submounts Sasha Levin
2019-01-08 19:31 ` [PATCH AUTOSEL 4.14 13/53] drm/amdgpu: Correct get_crtc_scanoutpos behavior when vpos >= vtotal Sasha Levin
2019-01-08 19:31 ` Sasha Levin [this message]
2019-01-08 19:31 ` [PATCH AUTOSEL 4.14 15/53] jffs2: Fix use of uninitialized delayed_work, lockdep breakage Sasha Levin
2019-01-08 19:31 ` [PATCH AUTOSEL 4.14 16/53] clk: imx: make mux parent strings const Sasha Levin
2019-01-08 19:31 ` [PATCH AUTOSEL 4.14 17/53] pstore/ram: Do not treat empty buffers as valid Sasha Levin
2019-01-08 19:31 ` [PATCH AUTOSEL 4.14 18/53] powerpc/xmon: Fix invocation inside lock region Sasha Levin
2019-01-08 19:31 ` [PATCH AUTOSEL 4.14 19/53] powerpc/pseries/cpuidle: Fix preempt warning Sasha Levin
2019-01-08 19:31 ` [PATCH AUTOSEL 4.14 20/53] arm64: relocatable: fix inconsistencies in linker script and options Sasha Levin
2019-01-08 19:31 ` [PATCH AUTOSEL 4.14 21/53] media: firewire: Fix app_info parameter type in avc_ca{,_app}_info Sasha Levin
2019-01-08 19:31 ` [PATCH AUTOSEL 4.14 22/53] IB/hfi1: Incorrect sizing of sge for PIO will OOPs Sasha Levin
2019-01-08 19:31 ` [PATCH AUTOSEL 4.14 23/53] media: venus: core: Set dma maximum segment size Sasha Levin
2019-01-08 19:31 ` [PATCH AUTOSEL 4.14 24/53] net: call sk_dst_reset when set SO_DONTROUTE Sasha Levin
2019-01-08 19:31 ` [PATCH AUTOSEL 4.14 25/53] scsi: target: use consistent left-aligned ASCII INQUIRY data Sasha Levin
2019-01-08 19:31 ` [PATCH AUTOSEL 4.14 26/53] selftests: do not macro-expand failed assertion expressions Sasha Levin
2019-01-08 19:31 ` [PATCH AUTOSEL 4.14 27/53] clk: imx6q: reset exclusive gates on init Sasha Levin
2019-01-08 19:31 ` [PATCH AUTOSEL 4.14 28/53] arm64: Fix minor issues with the dcache_by_line_op macro Sasha Levin
2019-01-08 19:31 ` [PATCH AUTOSEL 4.14 29/53] kconfig: fix file name and line number of warn_ignored_character() Sasha Levin
2019-01-08 19:31 ` [PATCH AUTOSEL 4.14 30/53] kconfig: fix memory leak when EOF is encountered in quotation Sasha Levin
2019-01-08 19:31 ` [PATCH AUTOSEL 4.14 31/53] mmc: atmel-mci: do not assume idle after atmci_request_end Sasha Levin
2019-01-08 19:32 ` [PATCH AUTOSEL 4.14 32/53] btrfs: improve error handling of btrfs_add_link Sasha Levin
2019-01-08 19:32 ` [PATCH AUTOSEL 4.14 33/53] tty/serial: do not free trasnmit buffer page under port lock Sasha Levin
2019-01-08 19:32 ` [PATCH AUTOSEL 4.14 34/53] perf intel-pt: Fix error with config term "pt=0" Sasha Levin
2019-01-08 19:32 ` [PATCH AUTOSEL 4.14 35/53] perf svghelper: Fix unchecked usage of strncpy() Sasha Levin
2019-01-08 19:32 ` [PATCH AUTOSEL 4.14 36/53] perf parse-events: " Sasha Levin
2019-01-08 19:32 ` [PATCH AUTOSEL 4.14 37/53] netfilter: ipt_CLUSTERIP: check MAC address when duplicate config is set Sasha Levin
2019-01-08 19:32 ` [PATCH AUTOSEL 4.14 38/53] dm crypt: use u64 instead of sector_t to store iv_offset Sasha Levin
2019-01-08 19:32 ` [PATCH AUTOSEL 4.14 39/53] dm kcopyd: Fix bug causing workqueue stalls Sasha Levin
2019-01-08 19:32 ` [PATCH AUTOSEL 4.14 40/53] tools lib subcmd: Don't add the kernel sources to the include path Sasha Levin
2019-01-08 19:32 ` [PATCH AUTOSEL 4.14 41/53] dm snapshot: Fix excessive memory usage and workqueue stalls Sasha Levin
2019-01-08 19:32 ` [PATCH AUTOSEL 4.14 42/53] quota: Lock s_umount in exclusive mode for Q_XQUOTA{ON,OFF} quotactls Sasha Levin
2019-01-08 19:32 ` [PATCH AUTOSEL 4.14 43/53] clocksource/drivers/integrator-ap: Add missing of_node_put() Sasha Levin
2019-01-08 19:32 ` [PATCH AUTOSEL 4.14 44/53] ALSA: bebob: fix model-id of unit for Apogee Ensemble Sasha Levin
2019-01-08 19:32 ` [PATCH AUTOSEL 4.14 45/53] sysfs: Disable lockdep for driver bind/unbind files Sasha Levin
2019-01-08 19:32 ` [PATCH AUTOSEL 4.14 46/53] IB/usnic: Fix potential deadlock Sasha Levin
2019-01-08 19:32 ` [PATCH AUTOSEL 4.14 47/53] scsi: smartpqi: correct lun reset issues Sasha Levin
2019-01-08 19:32 ` [PATCH AUTOSEL 4.14 48/53] scsi: smartpqi: call pqi_free_interrupts() in pqi_shutdown() Sasha Levin
2019-01-08 19:32 ` [PATCH AUTOSEL 4.14 49/53] scsi: megaraid: fix out-of-bound array accesses Sasha Levin
2019-01-08 19:32 ` [PATCH AUTOSEL 4.14 50/53] ocfs2: fix panic due to unrecovered local alloc Sasha Levin
2019-01-08 19:32 ` [PATCH AUTOSEL 4.14 51/53] mm/page-writeback.c: don't break integrity writeback on ->writepage() error Sasha Levin
2019-01-08 19:32 ` [PATCH AUTOSEL 4.14 52/53] mm/swap: use nr_node_ids for avail_lists in swap_info_struct Sasha Levin
2019-01-08 19:32 ` [PATCH AUTOSEL 4.14 53/53] mm, proc: be more verbose about unstable VMA flags in /proc/<pid>/smaps Sasha Levin

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=20190108193222.123316-14-sashal@kernel.org \
    --to=sashal@kernel.org \
    --cc=chuck.lever@oracle.com \
    --cc=jgg@mellanox.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-rdma@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 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).