Home Home > GIT Browse
summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorIlya Dryomov <idryomov@gmail.com>2015-02-17 19:37:15 +0300
committerGreg Kroah-Hartman <gregkh@linuxfoundation.org>2015-03-06 14:40:54 -0800
commit6af167fbe6c42fda5203b8095b92669dd0a687d4 (patch)
tree88af72ffdbe62a32a35cfdbdb92ecdca8d7ded48
parent54ff4c89a5445fa8f313a338c1cf5478317df154 (diff)
libceph: fix double __remove_osd() problem
commit 7eb71e0351fbb1b242ae70abb7bb17107fe2f792 upstream. It turns out it's possible to get __remove_osd() called twice on the same OSD. That doesn't sit well with rb_erase() - depending on the shape of the tree we can get a NULL dereference, a soft lockup or a random crash at some point in the future as we end up touching freed memory. One scenario that I was able to reproduce is as follows: <osd3 is idle, on the osd lru list> <con reset - osd3> con_fault_finish() osd_reset() <osdmap - osd3 down> ceph_osdc_handle_map() <takes map_sem> kick_requests() <takes request_mutex> reset_changed_osds() __reset_osd() __remove_osd() <releases request_mutex> <releases map_sem> <takes map_sem> <takes request_mutex> __kick_osd_requests() __reset_osd() __remove_osd() <-- !!! A case can be made that osd refcounting is imperfect and reworking it would be a proper resolution, but for now Sage and I decided to fix this by adding a safe guard around __remove_osd(). Fixes: http://tracker.ceph.com/issues/8087 Cc: Sage Weil <sage@redhat.com> Signed-off-by: Ilya Dryomov <idryomov@gmail.com> Reviewed-by: Sage Weil <sage@redhat.com> Reviewed-by: Alex Elder <elder@linaro.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
-rw-r--r--net/ceph/osd_client.c26
1 files changed, 18 insertions, 8 deletions
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index 3f34304efd8a..1b51d9216e7e 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -967,14 +967,24 @@ static void put_osd(struct ceph_osd *osd)
*/
static void __remove_osd(struct ceph_osd_client *osdc, struct ceph_osd *osd)
{
- dout("__remove_osd %p\n", osd);
+ dout("%s %p osd%d\n", __func__, osd, osd->o_osd);
WARN_ON(!list_empty(&osd->o_requests));
WARN_ON(!list_empty(&osd->o_linger_requests));
- rb_erase(&osd->o_node, &osdc->osds);
list_del_init(&osd->o_osd_lru);
- ceph_con_close(&osd->o_con);
- put_osd(osd);
+ rb_erase(&osd->o_node, &osdc->osds);
+ RB_CLEAR_NODE(&osd->o_node);
+}
+
+static void remove_osd(struct ceph_osd_client *osdc, struct ceph_osd *osd)
+{
+ dout("%s %p osd%d\n", __func__, osd, osd->o_osd);
+
+ if (!RB_EMPTY_NODE(&osd->o_node)) {
+ ceph_con_close(&osd->o_con);
+ __remove_osd(osdc, osd);
+ put_osd(osd);
+ }
}
static void remove_all_osds(struct ceph_osd_client *osdc)
@@ -984,7 +994,7 @@ static void remove_all_osds(struct ceph_osd_client *osdc)
while (!RB_EMPTY_ROOT(&osdc->osds)) {
struct ceph_osd *osd = rb_entry(rb_first(&osdc->osds),
struct ceph_osd, o_node);
- __remove_osd(osdc, osd);
+ remove_osd(osdc, osd);
}
mutex_unlock(&osdc->request_mutex);
}
@@ -1014,7 +1024,7 @@ static void remove_old_osds(struct ceph_osd_client *osdc)
list_for_each_entry_safe(osd, nosd, &osdc->osd_lru, o_osd_lru) {
if (time_before(jiffies, osd->lru_ttl))
break;
- __remove_osd(osdc, osd);
+ remove_osd(osdc, osd);
}
mutex_unlock(&osdc->request_mutex);
}
@@ -1029,8 +1039,7 @@ static int __reset_osd(struct ceph_osd_client *osdc, struct ceph_osd *osd)
dout("__reset_osd %p osd%d\n", osd, osd->o_osd);
if (list_empty(&osd->o_requests) &&
list_empty(&osd->o_linger_requests)) {
- __remove_osd(osdc, osd);
-
+ remove_osd(osdc, osd);
return -ENODEV;
}
@@ -1612,6 +1621,7 @@ static void reset_changed_osds(struct ceph_osd_client *osdc)
{
struct rb_node *p, *n;
+ dout("%s %p\n", __func__, osdc);
for (p = rb_first(&osdc->osds); p; p = n) {
struct ceph_osd *osd = rb_entry(p, struct ceph_osd, o_node);