This is a note to let you know that I've just added the patch titled
libceph: add lingering request reference when registered
to the 3.10-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:
libceph-add-lingering-request-reference-when-registered.patch
and it can be found in the queue-3.10 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@xxxxxxxxxxxxxxx> know about it.
>From 96e4dac66f69d28af2b736e723364efbbdf9fdee Mon Sep 17 00:00:00 2001
From: Alex Elder <elder@xxxxxxxxxxx>
Date: Wed, 22 May 2013 20:54:25 -0500
Subject: libceph: add lingering request reference when registered
From: Alex Elder <elder@xxxxxxxxxxx>
commit 96e4dac66f69d28af2b736e723364efbbdf9fdee upstream.
When an osd request is set to linger, the osd client holds onto the
request so it can be re-submitted following certain osd map changes.
The osd client holds a reference to the request until it is
unregistered. This is used by rbd for watch requests.
Currently, the reference is taken when the request is marked with
the linger flag. This means that if an error occurs after that
time but before the the request completes successfully, that
reference is leaked.
There's really no reason to take the reference until the request is
registered in the the osd client's list of lingering requests, and
that only happens when the lingering (watch) request completes
successfully.
So take that reference only when it gets registered following
succesful completion, and drop it (as before) when the request
gets unregistered. This avoids the reference problem on error
in rbd.
Rearrange ceph_osdc_unregister_linger_request() to avoid using
the request pointer after it may have been freed.
And hold an extra reference in kick_requests() while handling
a linger request that has not yet been registered, to ensure
it doesn't go away.
This resolves:
http://tracker.ceph.com/issues/3859
Signed-off-by: Alex Elder <elder@xxxxxxxxxxx>
Reviewed-by: Josh Durgin <josh.durgin@xxxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
net/ceph/osd_client.c | 12 +++++-------
1 file changed, 5 insertions(+), 7 deletions(-)
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -1174,6 +1174,7 @@ static void __register_linger_request(st
struct ceph_osd_request *req)
{
dout("__register_linger_request %p\n", req);
+ ceph_osdc_get_request(req);
list_add_tail(&req->r_linger_item, &osdc->req_linger);
if (req->r_osd)
list_add_tail(&req->r_linger_osd,
@@ -1196,6 +1197,7 @@ static void __unregister_linger_request(
if (list_empty(&req->r_osd_item))
req->r_osd = NULL;
}
+ ceph_osdc_put_request(req);
}
void ceph_osdc_unregister_linger_request(struct ceph_osd_client *osdc,
@@ -1203,9 +1205,8 @@ void ceph_osdc_unregister_linger_request
{
mutex_lock(&osdc->request_mutex);
if (req->r_linger) {
- __unregister_linger_request(osdc, req);
req->r_linger = 0;
- ceph_osdc_put_request(req);
+ __unregister_linger_request(osdc, req);
}
mutex_unlock(&osdc->request_mutex);
}
@@ -1217,11 +1218,6 @@ void ceph_osdc_set_request_linger(struct
if (!req->r_linger) {
dout("set_request_linger %p\n", req);
req->r_linger = 1;
- /*
- * caller is now responsible for calling
- * unregister_linger_request
- */
- ceph_osdc_get_request(req);
}
}
EXPORT_SYMBOL(ceph_osdc_set_request_linger);
@@ -1633,8 +1629,10 @@ static void kick_requests(struct ceph_os
dout("%p tid %llu restart on osd%d\n",
req, req->r_tid,
req->r_osd ? req->r_osd->o_osd : -1);
+ ceph_osdc_get_request(req);
__unregister_request(osdc, req);
__register_linger_request(osdc, req);
+ ceph_osdc_put_request(req);
continue;
}
Patches currently in stable-queue which might be from elder@xxxxxxxxxxx are
queue-3.10/libceph-add-lingering-request-reference-when-registered.patch
queue-3.10/rbd-set-removing-flag-while-holding-list-lock.patch
queue-3.10/rbd-flush-dcache-after-zeroing-page-data.patch
queue-3.10/rbd-protect-against-concurrent-unmaps.patch
--
To unsubscribe from this list: send the line "unsubscribe stable" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html