public inbox for linux-nfs@vger.kernel.org
 help / color / mirror / Atom feed
From: Chuck Lever <chuck.lever@oracle.com>
To: linux-rdma@vger.kernel.org, linux-nfs@vger.kernel.org
Cc: Moni Shoua <monis@mellanox.com>,
	Anna Schumaker <schumaker.anna@gmail.com>
Subject: [PATCH v2 01/20] rxe: IB_WR_REG_MR does not capture MR's iova field
Date: Mon, 26 Nov 2018 15:05:52 -0500	[thread overview]
Message-ID: <20181126200552.10321.73218.stgit@manet.1015granger.net> (raw)
In-Reply-To: <20181126194611.10321.71714.stgit@manet.1015granger.net>

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>
Cc: Moni Shoua <monis@mellanox.com>
---
 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 6c361d7..46f62f7 100644
--- a/drivers/infiniband/sw/rxe/rxe_req.c
+++ b/drivers/infiniband/sw/rxe/rxe_req.c
@@ -643,6 +643,7 @@ 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 {


  reply	other threads:[~2018-11-26 20:05 UTC|newest]

Thread overview: 24+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-11-26 20:05 [PATCH v2 00/20] NFS/RDMA client for next (complete) Chuck Lever
2018-11-26 20:05 ` Chuck Lever [this message]
2018-11-26 20:05 ` [PATCH v2 02/20] xprtrdma: Remove support for FMR memory registration Chuck Lever
2018-11-26 20:06 ` [PATCH v2 03/20] xprtrdma: Fix ri_max_segs and the result of ro_maxpages Chuck Lever
2018-11-26 20:06 ` [PATCH v2 04/20] xprtrdma: Reduce max_frwr_depth Chuck Lever
2018-11-26 20:06 ` [PATCH v2 05/20] xprtrdma: Plant XID in on-the-wire RDMA offset (FRWR) Chuck Lever
2018-11-26 20:06 ` [PATCH v2 06/20] xprtrdma: Recognize XDRBUF_SPARSE_PAGES Chuck Lever
2018-11-26 20:06 ` [PATCH v2 07/20] xprtrdma: Remove request_module from backchannel Chuck Lever
2018-11-26 20:06 ` [PATCH v2 08/20] xprtrdma: Expose transport header errors Chuck Lever
2018-11-26 20:06 ` [PATCH v2 09/20] xprtrdma: Simplify locking that protects the rl_allreqs list Chuck Lever
2018-11-26 20:06 ` [PATCH v2 10/20] xprtrdma: Refactor rpcrdma_create_req() Chuck Lever
2018-11-26 20:06 ` [PATCH v2 11/20] xprtrdma: Prevent req creation while unloading the underlying device Chuck Lever
2018-11-26 20:06 ` [PATCH v2 12/20] xprtrdma: Dynamically allocate rpcrdma_reqs Chuck Lever
2018-11-26 20:06 ` [PATCH v2 13/20] xprtrdma: Cull dprintk() call sites Chuck Lever
2018-11-26 20:07 ` [PATCH v2 14/20] xprtrdma: Clean up of xprtrdma chunk trace points Chuck Lever
2018-11-26 20:07 ` [PATCH v2 15/20] xprtrdma: Relocate the xprtrdma_mr_map " Chuck Lever
2018-11-26 20:07 ` [PATCH v2 16/20] NFS: Make "port=" mount option optional for RDMA mounts Chuck Lever
2018-11-26 20:07 ` [PATCH v2 17/20] SUNRPC: Remove support for kerberos_v1 Chuck Lever
2018-11-30 21:19   ` Anna Schumaker
2018-11-30 21:26     ` Chuck Lever
2018-11-30 21:57       ` Olga Kornievskaia
2018-11-26 20:07 ` [PATCH v2 18/20] SUNRPC: Fix some kernel doc complaints Chuck Lever
2018-11-26 20:07 ` [PATCH v2 19/20] NFS: Fix NFSv4 symbolic trace point output Chuck Lever
2018-11-26 20:07 ` [PATCH v2 20/20] SUNRPC: Simplify defining common RPC trace events Chuck Lever

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=20181126200552.10321.73218.stgit@manet.1015granger.net \
    --to=chuck.lever@oracle.com \
    --cc=linux-nfs@vger.kernel.org \
    --cc=linux-rdma@vger.kernel.org \
    --cc=monis@mellanox.com \
    --cc=schumaker.anna@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