linux-toradex.git/net/ceph, branch v3.19.2 Linux kernel for Apalis and Colibri modules libceph: fix double __remove_osd() problem 2015-03-06T22:57:41+00:00 Ilya Dryomov idryomov@gmail.com 2015-02-17T16:37:15+00:00 1c9f7cbfc80535d0bc558518fd7613755b0cb34f 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> 
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>
libceph: fix sparse endianness warnings 2015-01-08T17:36:57+00:00 Ilya Dryomov idryomov@redhat.com 2014-12-19T11:00:41+00:00 d7d5a007b1c64c617ce3ee30c973ed0bb93443d9 The only real issue is the one in auth_x.c and it came with 3.19-rc1 merge. Signed-off-by: Ilya Dryomov <idryomov@redhat.com> 
The only real issue is the one in auth_x.c and it came with
3.19-rc1 merge.

Signed-off-by: Ilya Dryomov <idryomov@redhat.com>
libceph: specify position of extent operation 2014-12-17T17:09:52+00:00 Yan, Zheng zyan@redhat.com 2014-11-13T06:40:37+00:00 715e4cd405cfd67bd058e410b3e599bab2072645 allow specifying position of extent operation in multi-operations osd request. This is required for cephfs to convert inline data to normal data (compare xattr, then write object). Signed-off-by: Yan, Zheng <zyan@redhat.com> Reviewed-by: Ilya Dryomov <idryomov@redhat.com> 
allow specifying position of extent operation in multi-operations
osd request. This is required for cephfs to convert inline data to
normal data (compare xattr, then write object).

Signed-off-by: Yan, Zheng <zyan@redhat.com>
Reviewed-by: Ilya Dryomov <idryomov@redhat.com>
libceph: add CREATE osd operation support 2014-12-17T17:09:51+00:00 Yan, Zheng zyan@redhat.com 2014-11-13T02:47:25+00:00 864e9197f10c77053bbaf12932f5b200bb4ed3c5 Add CEPH_OSD_OP_CREATE support. Also change libceph to not treat CEPH_OSD_OP_DELETE as an extent op and add an assert to that end. Signed-off-by: Yan, Zheng <zyan@redhat.com> Reviewed-by: Ilya Dryomov <idryomov@redhat.com> 
Add CEPH_OSD_OP_CREATE support.  Also change libceph to not treat
CEPH_OSD_OP_DELETE as an extent op and add an assert to that end.

Signed-off-by: Yan, Zheng <zyan@redhat.com>
Reviewed-by: Ilya Dryomov <idryomov@redhat.com>
libceph: add SETXATTR/CMPXATTR osd operations support 2014-12-17T17:09:51+00:00 Yan, Zheng zyan@redhat.com 2014-11-12T06:00:43+00:00 d74b50bed037794135cb5a4e7418ad71d9848ce1 Signed-off-by: Yan, Zheng <zyan@redhat.com> Reviewed-by: Ilya Dryomov <idryomov@redhat.com> 
Signed-off-by: Yan, Zheng <zyan@redhat.com>
Reviewed-by: Ilya Dryomov <idryomov@redhat.com>
libceph: require cephx message signature by default 2014-12-17T17:09:51+00:00 Yan, Zheng zyan@redhat.com 2014-11-11T08:30:55+00:00 a3fc98005c9c6e4649d26bee0935a7048a95c9e6 Signed-off-by: Yan, Zheng <zyan@redhat.com> Reviewed-by: Ilya Dryomov <idryomov@redhat.com> 
Signed-off-by: Yan, Zheng <zyan@redhat.com>
Reviewed-by: Ilya Dryomov <idryomov@redhat.com>
libceph: message signature support 2014-12-17T17:09:50+00:00 Yan, Zheng zyan@redhat.com 2014-11-04T08:33:37+00:00 33d07337962c7bbd2fd5cf7f1106735c9507fbe2 Signed-off-by: Yan, Zheng <zyan@redhat.com> 
Signed-off-by: Yan, Zheng <zyan@redhat.com>
libceph: store session key in cephx authorizer 2014-12-17T17:09:50+00:00 Yan, Zheng zyan@redhat.com 2014-11-04T08:32:35+00:00 ae385eaf24dc39c1703049112e4265b9f93b7d86 Session key is required when calculating message signature. Save the session key in authorizer, this avoid lookup ticket handler for each message Signed-off-by: Yan, Zheng <zyan@redhat.com> 
Session key is required when calculating message signature. Save the session
key in authorizer, this avoid lookup ticket handler for each message

Signed-off-by: Yan, Zheng <zyan@redhat.com>
libceph: nuke ceph_kvfree() 2014-12-17T17:09:50+00:00 Ilya Dryomov idryomov@redhat.com 2014-10-23T12:32:57+00:00 4965fc38c460b274b2a1789e1165a25fb0409d7e Use kvfree() from linux/mm.h instead, which is identical. Also fix the ceph_buffer comment: we will allocate with kmalloc() up to 32k - the value of PAGE_ALLOC_COSTLY_ORDER, but that really is just an implementation detail so don't mention it at all. Signed-off-by: Ilya Dryomov <idryomov@redhat.com> 
Use kvfree() from linux/mm.h instead, which is identical.  Also fix the
ceph_buffer comment: we will allocate with kmalloc() up to 32k - the
value of PAGE_ALLOC_COSTLY_ORDER, but that really is just an
implementation detail so don't mention it at all.

Signed-off-by: Ilya Dryomov <idryomov@redhat.com>
libceph: change from BUG to WARN for __remove_osd() asserts 2014-11-13T19:26:34+00:00 Ilya Dryomov idryomov@redhat.com 2014-11-05T16:33:44+00:00 cc9f1f518cec079289d11d732efa490306b1ddad No reason to use BUG_ON for osd request list assertions. Signed-off-by: Ilya Dryomov <idryomov@redhat.com> Reviewed-by: Alex Elder <elder@linaro.org> 
No reason to use BUG_ON for osd request list assertions.

Signed-off-by: Ilya Dryomov <idryomov@redhat.com>
Reviewed-by: Alex Elder <elder@linaro.org>