This is a note to let you know that I've just added the patch titled
libceph: avoid unregistering osd request when not registered
to the 3.4-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary
The filename of the patch is:
0026-libceph-avoid-unregistering-osd-request-when-not-reg.patch
and it can be found in the queue-3.4 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <[email protected]> know about it.
>From 30b2118228f619ff7ec30651e914fe4d61ad7d3b Mon Sep 17 00:00:00 2001
From: Sage Weil <[email protected]>
Date: Wed, 16 May 2012 15:16:38 -0500
Subject: libceph: avoid unregistering osd request when not registered
From: Sage Weil <[email protected]>
(cherry picked from commit 35f9f8a09e1e88e31bd34a1e645ca0e5f070dd5c)
There is a race between two __unregister_request() callers: the
reply path and the ceph_osdc_wait_request(). If we get a reply
*and* the timeout expires at roughly the same time, both callers
will try to unregister the request, and the second one will do bad
things.
Simply check if the request is still already unregistered; if so,
return immediately and do nothing.
Fixes http://tracker.newdream.net/issues/2420
Signed-off-by: Sage Weil <[email protected]>
Reviewed-by: Alex Elder <[email protected]>
Signed-off-by: Greg Kroah-Hartman <[email protected]>
---
net/ceph/osd_client.c | 6 ++++++
1 file changed, 6 insertions(+)
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -841,6 +841,12 @@ static void register_request(struct ceph
static void __unregister_request(struct ceph_osd_client *osdc,
struct ceph_osd_request *req)
{
+ if (RB_EMPTY_NODE(&req->r_node)) {
+ dout("__unregister_request %p tid %lld not registered\n",
+ req, req->r_tid);
+ return;
+ }
+
dout("__unregister_request %p tid %lld\n", req, req->r_tid);
rb_erase(&req->r_node, &osdc->requests);
osdc->num_requests--;
Patches currently in stable-queue which might be from [email protected] are
queue-3.4/0020-ceph-ensure-auth-ops-are-defined-before-use.patch
queue-3.4/0025-ceph-add-auth-buf-in-prepare_write_connect.patch
queue-3.4/0021-ceph-have-get_authorizer-methods-return-pointers.patch
queue-3.4/0026-libceph-avoid-unregistering-osd-request-when-not-reg.patch
queue-3.4/0005-crush-fix-memory-leak-when-destroying-tree-buckets.patch
queue-3.4/0002-crush-adjust-local-retry-threshold.patch
queue-3.4/0023-ceph-return-pointer-from-prepare_connect_authorizer.patch
queue-3.4/0018-ceph-define-ceph_auth_handshake-type.patch
queue-3.4/0011-ceph-messenger-reset-connection-kvec-caller.patch
queue-3.4/0032-libceph-fix-messenger-retry.patch
queue-3.4/0019-ceph-messenger-reduce-args-to-create_authorizer.patch
queue-3.4/0029-libceph-use-con-get-put-ops-from-osd_client.patch
queue-3.4/0015-ceph-messenger-check-prepare_write_connect-result.patch
queue-3.4/0003-crush-be-more-tolerant-of-nonsensical-crush-maps.patch
queue-3.4/0028-libceph-osd_client-don-t-drop-reply-reference-too-ea.patch
queue-3.4/0014-ceph-don-t-set-WRITE_PENDING-too-early.patch
queue-3.4/0016-ceph-messenger-rework-prepare_connect_authorizer.patch
queue-3.4/0031-libceph-flush-msgr-queue-during-mon_client-shutdown.patch
queue-3.4/0013-ceph-drop-msgr-argument-from-prepare_write_connect.patch
queue-3.4/0009-ceph-messenger-change-read_partial-to-take-end-arg.patch
queue-3.4/0017-ceph-messenger-check-return-from-get_authorizer.patch
queue-3.4/0001-crush-clean-up-types-const-ness.patch
queue-3.4/0037-ceph-check-PG_Private-flag-before-accessing-page-pri.patch
queue-3.4/0022-ceph-use-info-returned-by-get_authorizer.patch
queue-3.4/0027-libceph-fix-pg_temp-updates.patch
queue-3.4/0008-ceph-messenger-update-to-in-read_partial-caller.patch
queue-3.4/0007-ceph-messenger-use-read_partial-in-read_partial_mess.patch
queue-3.4/0010-libceph-don-t-reset-kvec-in-prepare_write_banner.patch
queue-3.4/0012-ceph-messenger-send-banner-in-process_connect.patch
queue-3.4/0024-ceph-rename-prepare_connect_authorizer.patch
queue-3.4/0004-crush-fix-tree-node-weight-lookup.patch
--
To unsubscribe from this list: send the line "unsubscribe stable" in
the body of a message to [email protected]
More majordomo info at http://vger.kernel.org/majordomo-info.html
