linux-rdma.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Alex Vainman <alexonlists-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
To: roland <rolandd-FYB4Gu1CFyUAvxtiuMwx3w@public.gmane.org>,
	Roland Dreier <rdreier-FYB4Gu1CFyUAvxtiuMwx3w@public.gmane.org>,
	linux-rdma-u79uwXL29TY76Z2rM5mHXA@public.gmane.org,
	alexr-smomgflXvOZWk0Htik3J/w@public.gmane.org
Subject: [PATCH v2 2/4] libibverbs: Undo changes in memory range tree when madvise() fails
Date: Mon, 01 Feb 2010 07:58:00 +0200	[thread overview]
Message-ID: <4B666D68.8010103@gmail.com> (raw)

ibv_madvise_range() doesn't cleanup if madvise() fails.
This patch comes to handle reference counter update on madvise() failure:

ibv_madvise_range() first updates memory range reference counter
and only then calls to madvise(). If madvise() fails, the reference counter
of the failed node is incorrect. This issue is fixed by updating node's
reference counter only after a successful call to madvise() or if no call to
madvise() was need since it was done in the past.

Signed-off-by: Alex Vainman <alexv-smomgflXvOZWk0Htik3J/w@public.gmane.org>
---
 src/memory.c |    7 +++----
 1 files changed, 3 insertions(+), 4 deletions(-)

diff --git a/src/memory.c b/src/memory.c
index 51839e2..6a3305f 100644
--- a/src/memory.c
+++ b/src/memory.c
@@ -521,10 +521,8 @@ static int ibv_madvise_range(void *base, size_t size, int advice)
 			}
 		}
 
-		node->refcnt += inc;
-
-		if ((inc == -1 && node->refcnt == 0) ||
-		    (inc ==  1 && node->refcnt == 1)) {
+		if ((inc == -1 && node->refcnt == 1) ||
+		    (inc ==  1 && node->refcnt == 0)) {
 			/*
 			 * If this is the first time through the loop,
 			 * and we merged this node with the previous
@@ -547,6 +545,7 @@ static int ibv_madvise_range(void *base, size_t size, int advice)
 				goto out;
 		}
 
+		node->refcnt += inc;
 		node = __mm_next(node);
 	}
 
-- 
1.6.5.3


--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

                 reply	other threads:[~2010-02-01  5:58 UTC|newest]

Thread overview: [no followups] expand[flat|nested]  mbox.gz  Atom feed

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=4B666D68.8010103@gmail.com \
    --to=alexonlists-re5jqeeqqe8avxtiumwx3w@public.gmane.org \
    --cc=alexr-smomgflXvOZWk0Htik3J/w@public.gmane.org \
    --cc=alexv-smomgflXvOZWk0Htik3J/w@public.gmane.org \
    --cc=linux-rdma-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
    --cc=rdreier-FYB4Gu1CFyUAvxtiuMwx3w@public.gmane.org \
    --cc=rolandd-FYB4Gu1CFyUAvxtiuMwx3w@public.gmane.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).