Linux NFS development
 help / color / mirror / Atom feed
From: Chuck Lever <chuck.lever@oracle.com>
To: linux-rdma@vger.kernel.org, linux-nfs@vger.kernel.org
Subject: [PATCH v3 13/21] xprtrdma: Don't post a LOCAL_INV in rpcrdma_register_frmr_external()
Date: Tue, 15 Jul 2014 10:22:03 -0400	[thread overview]
Message-ID: <20140715142203.8908.19576.stgit@manet.1015granger.net> (raw)
In-Reply-To: <20140715142020.8908.80969.stgit@manet.1015granger.net>

Any FRMR arriving in rpcrdma_register_frmr_external() is now
guaranteed to be either invalid, or to be targeted by a queued
LOCAL_INV that will invalidate it before the adapter processes
the FAST_REG_MR being built here.

The problem with current arrangement of chaining a LOCAL_INV to the
FAST_REG_MR is that if the transport is not connected, the LOCAL_INV
is flushed and the FAST_REG_MR is flushed. This leaves the FRMR
valid with the old rkey. But rpcrdma_register_frmr_external() has
already bumped the in-memory rkey.

Next time through rpcrdma_register_frmr_external(), a LOCAL_INV and
FAST_REG_MR is attempted again because the FRMR is still valid. But
the rkey no longer matches the hardware's rkey, and a memory
management operation error occurs.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Tested-by: Steve Wise <swise@opengridcomputing.com>
---
 net/sunrpc/xprtrdma/verbs.c |   21 ++-------------------
 1 file changed, 2 insertions(+), 19 deletions(-)

diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c
index 24168e8..8429869 100644
--- a/net/sunrpc/xprtrdma/verbs.c
+++ b/net/sunrpc/xprtrdma/verbs.c
@@ -1692,7 +1692,7 @@ rpcrdma_register_frmr_external(struct rpcrdma_mr_seg *seg,
 	struct rpcrdma_mw *mw = seg1->mr_chunk.rl_mw;
 	struct rpcrdma_frmr *frmr = &mw->r.frmr;
 	struct ib_mr *mr = frmr->fr_mr;
-	struct ib_send_wr invalidate_wr, frmr_wr, *bad_wr, *post_wr;
+	struct ib_send_wr frmr_wr, *bad_wr;
 	int len, pageoff;
 	int i, rc;
 	int seg_len;
@@ -1724,22 +1724,6 @@ rpcrdma_register_frmr_external(struct rpcrdma_mr_seg *seg,
 	dprintk("RPC:       %s: Using frmr %p to map %d segments\n",
 		__func__, mw, i);
 
-	if (unlikely(frmr->fr_state != FRMR_IS_INVALID)) {
-		dprintk("RPC:       %s: frmr %x left valid, posting invalidate.\n",
-			__func__, mr->rkey);
-		/* Invalidate before using. */
-		memset(&invalidate_wr, 0, sizeof invalidate_wr);
-		invalidate_wr.wr_id = (unsigned long)(void *)mw;
-		invalidate_wr.next = &frmr_wr;
-		invalidate_wr.opcode = IB_WR_LOCAL_INV;
-		invalidate_wr.send_flags = IB_SEND_SIGNALED;
-		invalidate_wr.ex.invalidate_rkey = mr->rkey;
-		DECR_CQCOUNT(&r_xprt->rx_ep);
-		post_wr = &invalidate_wr;
-	} else
-		post_wr = &frmr_wr;
-
-	/* Prepare FRMR WR */
 	memset(&frmr_wr, 0, sizeof frmr_wr);
 	frmr_wr.wr_id = (unsigned long)(void *)mw;
 	frmr_wr.opcode = IB_WR_FAST_REG_MR;
@@ -1761,8 +1745,7 @@ rpcrdma_register_frmr_external(struct rpcrdma_mr_seg *seg,
 	frmr_wr.wr.fast_reg.rkey = mr->rkey;
 	DECR_CQCOUNT(&r_xprt->rx_ep);
 
-	rc = ib_post_send(ia->ri_id->qp, post_wr, &bad_wr);
-
+	rc = ib_post_send(ia->ri_id->qp, &frmr_wr, &bad_wr);
 	if (rc) {
 		dprintk("RPC:       %s: failed ib_post_send for register,"
 			" status %i\n", __func__, rc);


  parent reply	other threads:[~2014-07-15 14:22 UTC|newest]

Thread overview: 21+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2014-07-15 14:20 [PATCH v3 01/21] xprtrdma: Fix panic in rpcrdma_register_frmr_external() Chuck Lever
2014-07-15 14:20 ` [PATCH v3 02/21] xprtrdma: Protect ia->ri_id when unmapping/invalidating MRs Chuck Lever
2014-07-15 14:20 ` [PATCH v3 03/21] xprtrdma: Limit data payload size for ALLPHYSICAL Chuck Lever
2014-07-15 14:20 ` [PATCH v3 04/21] xprtrdma: Update rkeys after transport reconnect Chuck Lever
2014-07-15 14:20 ` [PATCH v3 05/21] xprtrdma: On disconnect, don't ignore pending CQEs Chuck Lever
2014-07-15 14:21 ` [PATCH v3 06/21] xprtrdma: Don't invalidate FRMRs if registration fails Chuck Lever
2014-07-15 14:21 ` [PATCH v3 07/21] xprtrdma: Unclutter struct rpcrdma_mr_seg Chuck Lever
2014-07-15 14:21 ` [PATCH v3 08/21] xprtrdma: Back off rkey when FAST_REG_MR fails Chuck Lever
2014-07-15 14:21 ` [PATCH v3 09/21] xprtrdma: Chain together all MWs in same buffer pool Chuck Lever
2014-07-15 14:21 ` [PATCH v3 10/21] xprtrdma: Properly handle exhaustion of the rb_mws list Chuck Lever
2014-07-15 14:21 ` [PATCH v3 11/21] xprtrdma: Reset FRMRs when FAST_REG_MR is flushed by a disconnect Chuck Lever
2014-07-15 14:21 ` [PATCH v3 12/21] xprtrdma: Reset FRMRs after a flushed LOCAL_INV Work Request Chuck Lever
2014-07-15 14:22 ` Chuck Lever [this message]
2014-07-15 14:22 ` [PATCH v3 14/21] xprtrdma: Disable completions for FAST_REG_MR Work Requests Chuck Lever
2014-07-15 14:22 ` [PATCH v3 15/21] xprtrdma: Disable completions for LOCAL_INV " Chuck Lever
2014-07-15 14:22 ` [PATCH v3 16/21] xprtrdma: Rename frmr_wr Chuck Lever
2014-07-15 14:22 ` [PATCH v3 17/21] xprtrdma: Allocate each struct rpcrdma_mw separately Chuck Lever
2014-07-15 14:22 ` [PATCH v3 18/21] xprtrdma: Schedule reply tasklet once per upcall Chuck Lever
2014-07-15 14:22 ` [PATCH v3 19/21] xprtrdma: Make rpcrdma_ep_disconnect() return void Chuck Lever
2014-07-15 14:23 ` [PATCH v3 20/21] xprtrdma: Remove RPCRDMA_PERSISTENT_REGISTRATION macro Chuck Lever
2014-07-15 14:23 ` [PATCH v3 21/21] xprtrdma: Handle additional connection 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=20140715142203.8908.19576.stgit@manet.1015granger.net \
    --to=chuck.lever@oracle.com \
    --cc=linux-nfs@vger.kernel.org \
    --cc=linux-rdma@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