linux-stable.git/fs/ceph/snap.c, branch v5.4.239 Linux kernel stable tree ceph: avoid putting the realm twice when decoding snaps fails 2022-12-08T10:23:00+00:00 Xiubo Li xiubli@redhat.com 2022-11-09T03:00:39+00:00 cb7495fe957526555782ce0723f79ce92a6db22e [ Upstream commit 51884d153f7ec85e18d607b2467820a90e0f4359 ] When decoding the snaps fails it maybe leaving the 'first_realm' and 'realm' pointing to the same snaprealm memory. And then it'll put it twice and could cause random use-after-free, BUG_ON, etc issues. Cc: stable@vger.kernel.org Link: https://tracker.ceph.com/issues/57686 Signed-off-by: Xiubo Li <xiubli@redhat.com> Reviewed-by: Ilya Dryomov <idryomov@gmail.com> Signed-off-by: Ilya Dryomov <idryomov@gmail.com> Signed-off-by: Sasha Levin <sashal@kernel.org> 
[ Upstream commit 51884d153f7ec85e18d607b2467820a90e0f4359 ]

When decoding the snaps fails it maybe leaving the 'first_realm'
and 'realm' pointing to the same snaprealm memory. And then it'll
put it twice and could cause random use-after-free, BUG_ON, etc
issues.

Cc: stable@vger.kernel.org
Link: https://tracker.ceph.com/issues/57686
Signed-off-by: Xiubo Li <xiubli@redhat.com>
Reviewed-by: Ilya Dryomov <idryomov@gmail.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
ceph: do not update snapshot context when there is no new snapshot 2022-12-08T10:23:00+00:00 Xiubo Li xiubli@redhat.com 2022-02-19T06:28:33+00:00 12a93545b2ed94caf85dd78c5537fcc5cd1596e1 [ Upstream commit 2e586641c950e7f3e7e008404bd783a466b9b590 ] We will only track the uppest parent snapshot realm from which we need to rebuild the snapshot contexts _downward_ in hierarchy. For all the others having no new snapshot we will do nothing. This fix will avoid calling ceph_queue_cap_snap() on some inodes inappropriately. For example, with the code in mainline, suppose there are 2 directory hierarchies (with 6 directories total), like this: /dir_X1/dir_X2/dir_X3/ /dir_Y1/dir_Y2/dir_Y3/ Firstly, make a snapshot under /dir_X1/dir_X2/.snap/snap_X2, then make a root snapshot under /.snap/root_snap. Every time we make snapshots under /dir_Y1/..., the kclient will always try to rebuild the snap context for snap_X2 realm and finally will always try to queue cap snaps for dir_Y2 and dir_Y3, which makes no sense. That's because the snap_X2's seq is 2 and root_snap's seq is 3. So when creating a new snapshot under /dir_Y1/... the new seq will be 4, and the mds will send the kclient a snapshot backtrace in _downward_ order: seqs 4, 3. When ceph_update_snap_trace() is called, it will always rebuild the from the last realm, that's the root_snap. So later when rebuilding the snap context, the current logic will always cause it to rebuild the snap_X2 realm and then try to queue cap snaps for all the inodes related in that realm, even though it's not necessary. This is accompanied by a lot of these sorts of dout messages: "ceph: queue_cap_snap 00000000a42b796b nothing dirty|writing" Fix the logic to avoid this situation. Also, the 'invalidate' word is not precise here. In actuality, it will cause a rebuild of the existing snapshot contexts or just build non-existent ones. Rename it to 'rebuild_snapcs'. URL: https://tracker.ceph.com/issues/44100 Signed-off-by: Xiubo Li <xiubli@redhat.com> Reviewed-by: Jeff Layton <jlayton@kernel.org> Signed-off-by: Ilya Dryomov <idryomov@gmail.com> Stable-dep-of: 51884d153f7e ("ceph: avoid putting the realm twice when decoding snaps fails") Signed-off-by: Sasha Levin <sashal@kernel.org> 
[ Upstream commit 2e586641c950e7f3e7e008404bd783a466b9b590 ]

We will only track the uppest parent snapshot realm from which we
need to rebuild the snapshot contexts _downward_ in hierarchy. For
all the others having no new snapshot we will do nothing.

This fix will avoid calling ceph_queue_cap_snap() on some inodes
inappropriately. For example, with the code in mainline, suppose there
are 2 directory hierarchies (with 6 directories total), like this:

/dir_X1/dir_X2/dir_X3/
/dir_Y1/dir_Y2/dir_Y3/

Firstly, make a snapshot under /dir_X1/dir_X2/.snap/snap_X2, then make a
root snapshot under /.snap/root_snap. Every time we make snapshots under
/dir_Y1/..., the kclient will always try to rebuild the snap context for
snap_X2 realm and finally will always try to queue cap snaps for dir_Y2
and dir_Y3, which makes no sense.

That's because the snap_X2's seq is 2 and root_snap's seq is 3. So when
creating a new snapshot under /dir_Y1/... the new seq will be 4, and
the mds will send the kclient a snapshot backtrace in _downward_
order: seqs 4, 3.

When ceph_update_snap_trace() is called, it will always rebuild the from
the last realm, that's the root_snap. So later when rebuilding the snap
context, the current logic will always cause it to rebuild the snap_X2
realm and then try to queue cap snaps for all the inodes related in that
realm, even though it's not necessary.

This is accompanied by a lot of these sorts of dout messages:

    "ceph:  queue_cap_snap 00000000a42b796b nothing dirty|writing"

Fix the logic to avoid this situation.

Also, the 'invalidate' word is not precise here. In actuality, it will
cause a rebuild of the existing snapshot contexts or just build
non-existent ones. Rename it to 'rebuild_snapcs'.

URL: https://tracker.ceph.com/issues/44100
Signed-off-by: Xiubo Li <xiubli@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Stable-dep-of: 51884d153f7e ("ceph: avoid putting the realm twice when decoding snaps fails")
Signed-off-by: Sasha Levin <sashal@kernel.org>
ceph: take snap_empty_lock atomically with snaprealm refcount change 2021-08-18T06:57:04+00:00 Jeff Layton jlayton@kernel.org 2021-08-03T16:47:34+00:00 e9b2b2b29ca837efbbd41aef23963326063c3649 commit 8434ffe71c874b9c4e184b88d25de98c2bf5fe3f upstream. There is a race in ceph_put_snap_realm. The change to the nref and the spinlock acquisition are not done atomically, so you could decrement nref, and before you take the spinlock, the nref is incremented again. At that point, you end up putting it on the empty list when it shouldn't be there. Eventually __cleanup_empty_realms runs and frees it when it's still in-use. Fix this by protecting the 1->0 transition with atomic_dec_and_lock, and just drop the spinlock if we can get the rwsem. Because these objects can also undergo a 0->1 refcount transition, we must protect that change as well with the spinlock. Increment locklessly unless the value is at 0, in which case we take the spinlock, increment and then take it off the empty list if it did the 0->1 transition. With these changes, I'm removing the dout() messages from these functions, as well as in __put_snap_realm. They've always been racy, and it's better to not print values that may be misleading. Cc: stable@vger.kernel.org URL: https://tracker.ceph.com/issues/46419 Reported-by: Mark Nelson <mnelson@redhat.com> Signed-off-by: Jeff Layton <jlayton@kernel.org> Reviewed-by: Luis Henriques <lhenriques@suse.de> Signed-off-by: Ilya Dryomov <idryomov@gmail.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> 
commit 8434ffe71c874b9c4e184b88d25de98c2bf5fe3f upstream.

There is a race in ceph_put_snap_realm. The change to the nref and the
spinlock acquisition are not done atomically, so you could decrement
nref, and before you take the spinlock, the nref is incremented again.
At that point, you end up putting it on the empty list when it
shouldn't be there. Eventually __cleanup_empty_realms runs and frees
it when it's still in-use.

Fix this by protecting the 1->0 transition with atomic_dec_and_lock,
and just drop the spinlock if we can get the rwsem.

Because these objects can also undergo a 0->1 refcount transition, we
must protect that change as well with the spinlock. Increment locklessly
unless the value is at 0, in which case we take the spinlock, increment
and then take it off the empty list if it did the 0->1 transition.

With these changes, I'm removing the dout() messages from these
functions, as well as in __put_snap_realm. They've always been racy, and
it's better to not print values that may be misleading.

Cc: stable@vger.kernel.org
URL: https://tracker.ceph.com/issues/46419
Reported-by: Mark Nelson <mnelson@redhat.com>
Signed-off-by: Jeff Layton <jlayton@kernel.org>
Reviewed-by: Luis Henriques <lhenriques@suse.de>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
ceph: clean up locking annotation for ceph_get_snap_realm and __lookup_snap_realm 2021-08-18T06:57:04+00:00 Jeff Layton jlayton@kernel.org 2021-06-01T13:24:38+00:00 95ff775df6ecedc0ffce488340befdcebcd1fc12 commit df2c0cb7f8e8c83e495260ad86df8c5da947f2a7 upstream. They both say that the snap_rwsem must be held for write, but I don't see any real reason for it, and it's not currently always called that way. The lookup is just walking the rbtree, so holding it for read should be fine there. The "get" is bumping the refcount and (possibly) removing it from the empty list. I see no need to hold the snap_rwsem for write for that. Signed-off-by: Jeff Layton <jlayton@kernel.org> Reviewed-by: Ilya Dryomov <idryomov@gmail.com> Signed-off-by: Ilya Dryomov <idryomov@gmail.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> 
commit df2c0cb7f8e8c83e495260ad86df8c5da947f2a7 upstream.

They both say that the snap_rwsem must be held for write, but I don't
see any real reason for it, and it's not currently always called that
way.

The lookup is just walking the rbtree, so holding it for read should be
fine there. The "get" is bumping the refcount and (possibly) removing
it from the empty list. I see no need to hold the snap_rwsem for write
for that.

Signed-off-by: Jeff Layton <jlayton@kernel.org>
Reviewed-by: Ilya Dryomov <idryomov@gmail.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
ceph: add some lockdep assertions around snaprealm handling 2021-08-18T06:57:04+00:00 Jeff Layton jlayton@kernel.org 2021-06-01T12:13:38+00:00 1d8c232afb039e068aaa62f3ff7d27832b9ad7f8 commit a6862e6708c15995bc10614b2ef34ca35b4b9078 upstream. Turn some comments into lockdep asserts. Signed-off-by: Jeff Layton <jlayton@kernel.org> Reviewed-by: Ilya Dryomov <idryomov@gmail.com> Signed-off-by: Ilya Dryomov <idryomov@gmail.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> 
commit a6862e6708c15995bc10614b2ef34ca35b4b9078 upstream.

Turn some comments into lockdep asserts.

Signed-off-by: Jeff Layton <jlayton@kernel.org>
Reviewed-by: Ilya Dryomov <idryomov@gmail.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
ceph: fix memory leak in ceph_cleanup_snapid_map() 2020-04-01T09:01:59+00:00 Luis Henriques lhenriques@suse.com 2020-03-19T11:43:48+00:00 7cdaa5cd79abe15935393b4504eaf008361aa517 commit c8d6ee01449cd0d2f30410681cccb616a88f50b1 upstream. kmemleak reports the following memory leak: unreferenced object 0xffff88821feac8a0 (size 96): comm "kworker/1:0", pid 17, jiffies 4294896362 (age 20.512s) hex dump (first 32 bytes): a0 c8 ea 1f 82 88 ff ff 00 c9 ea 1f 82 88 ff ff ................ 00 00 00 00 00 00 00 00 00 01 00 00 00 00 ad de ................ backtrace: [<00000000b3ea77fb>] ceph_get_snapid_map+0x75/0x2a0 [<00000000d4060942>] fill_inode+0xb26/0x1010 [<0000000049da6206>] ceph_readdir_prepopulate+0x389/0xc40 [<00000000e2fe2549>] dispatch+0x11ab/0x1521 [<000000007700b894>] ceph_con_workfn+0xf3d/0x3240 [<0000000039138a41>] process_one_work+0x24d/0x590 [<00000000eb751f34>] worker_thread+0x4a/0x3d0 [<000000007e8f0d42>] kthread+0xfb/0x130 [<00000000d49bd1fa>] ret_from_fork+0x3a/0x50 A kfree is missing while looping the 'to_free' list of ceph_snapid_map objects. Cc: stable@vger.kernel.org Fixes: 75c9627efb72 ("ceph: map snapid to anonymous bdev ID") Signed-off-by: Luis Henriques <lhenriques@suse.com> Reviewed-by: Jeff Layton <jlayton@kernel.org> Signed-off-by: Ilya Dryomov <idryomov@gmail.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> 
commit c8d6ee01449cd0d2f30410681cccb616a88f50b1 upstream.

kmemleak reports the following memory leak:

unreferenced object 0xffff88821feac8a0 (size 96):
  comm "kworker/1:0", pid 17, jiffies 4294896362 (age 20.512s)
  hex dump (first 32 bytes):
    a0 c8 ea 1f 82 88 ff ff 00 c9 ea 1f 82 88 ff ff  ................
    00 00 00 00 00 00 00 00 00 01 00 00 00 00 ad de  ................
  backtrace:
    [<00000000b3ea77fb>] ceph_get_snapid_map+0x75/0x2a0
    [<00000000d4060942>] fill_inode+0xb26/0x1010
    [<0000000049da6206>] ceph_readdir_prepopulate+0x389/0xc40
    [<00000000e2fe2549>] dispatch+0x11ab/0x1521
    [<000000007700b894>] ceph_con_workfn+0xf3d/0x3240
    [<0000000039138a41>] process_one_work+0x24d/0x590
    [<00000000eb751f34>] worker_thread+0x4a/0x3d0
    [<000000007e8f0d42>] kthread+0xfb/0x130
    [<00000000d49bd1fa>] ret_from_fork+0x3a/0x50

A kfree is missing while looping the 'to_free' list of ceph_snapid_map
objects.

Cc: stable@vger.kernel.org
Fixes: 75c9627efb72 ("ceph: map snapid to anonymous bdev ID")
Signed-off-by: Luis Henriques <lhenriques@suse.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
ceph: fix buffer free while holding i_ceph_lock in __ceph_build_xattrs_blob() 2019-08-22T08:47:41+00:00 Luis Henriques lhenriques@suse.com 2019-07-19T14:32:21+00:00 12fe3dda7ed89c95cc0ef7abc001ad1ad3e092f8 Calling ceph_buffer_put() in __ceph_build_xattrs_blob() may result in freeing the i_xattrs.blob buffer while holding the i_ceph_lock. This can be fixed by having this function returning the old blob buffer and have the callers of this function freeing it when the lock is released. The following backtrace was triggered by fstests generic/117. BUG: sleeping function called from invalid context at mm/vmalloc.c:2283 in_atomic(): 1, irqs_disabled(): 0, pid: 649, name: fsstress 4 locks held by fsstress/649: #0: 00000000a7478e7e (&type->s_umount_key#19){++++}, at: iterate_supers+0x77/0xf0 #1: 00000000f8de1423 (&(&ci->i_ceph_lock)->rlock){+.+.}, at: ceph_check_caps+0x7b/0xc60 #2: 00000000562f2b27 (&s->s_mutex){+.+.}, at: ceph_check_caps+0x3bd/0xc60 #3: 00000000f83ce16a (&mdsc->snap_rwsem){++++}, at: ceph_check_caps+0x3ed/0xc60 CPU: 1 PID: 649 Comm: fsstress Not tainted 5.2.0+ #439 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.12.1-0-ga5cab58-prebuilt.qemu.org 04/01/2014 Call Trace: dump_stack+0x67/0x90 ___might_sleep.cold+0x9f/0xb1 vfree+0x4b/0x60 ceph_buffer_release+0x1b/0x60 __ceph_build_xattrs_blob+0x12b/0x170 __send_cap+0x302/0x540 ? __lock_acquire+0x23c/0x1e40 ? __mark_caps_flushing+0x15c/0x280 ? _raw_spin_unlock+0x24/0x30 ceph_check_caps+0x5f0/0xc60 ceph_flush_dirty_caps+0x7c/0x150 ? __ia32_sys_fdatasync+0x20/0x20 ceph_sync_fs+0x5a/0x130 iterate_supers+0x8f/0xf0 ksys_sync+0x4f/0xb0 __ia32_sys_sync+0xa/0x10 do_syscall_64+0x50/0x1c0 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x7fc6409ab617 Signed-off-by: Luis Henriques <lhenriques@suse.com> Reviewed-by: Jeff Layton <jlayton@kernel.org> Signed-off-by: Ilya Dryomov <idryomov@gmail.com> 
Calling ceph_buffer_put() in __ceph_build_xattrs_blob() may result in
freeing the i_xattrs.blob buffer while holding the i_ceph_lock.  This can
be fixed by having this function returning the old blob buffer and have
the callers of this function freeing it when the lock is released.

The following backtrace was triggered by fstests generic/117.

  BUG: sleeping function called from invalid context at mm/vmalloc.c:2283
  in_atomic(): 1, irqs_disabled(): 0, pid: 649, name: fsstress
  4 locks held by fsstress/649:
   #0: 00000000a7478e7e (&type->s_umount_key#19){++++}, at: iterate_supers+0x77/0xf0
   #1: 00000000f8de1423 (&(&ci->i_ceph_lock)->rlock){+.+.}, at: ceph_check_caps+0x7b/0xc60
   #2: 00000000562f2b27 (&s->s_mutex){+.+.}, at: ceph_check_caps+0x3bd/0xc60
   #3: 00000000f83ce16a (&mdsc->snap_rwsem){++++}, at: ceph_check_caps+0x3ed/0xc60
  CPU: 1 PID: 649 Comm: fsstress Not tainted 5.2.0+ #439
  Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.12.1-0-ga5cab58-prebuilt.qemu.org 04/01/2014
  Call Trace:
   dump_stack+0x67/0x90
   ___might_sleep.cold+0x9f/0xb1
   vfree+0x4b/0x60
   ceph_buffer_release+0x1b/0x60
   __ceph_build_xattrs_blob+0x12b/0x170
   __send_cap+0x302/0x540
   ? __lock_acquire+0x23c/0x1e40
   ? __mark_caps_flushing+0x15c/0x280
   ? _raw_spin_unlock+0x24/0x30
   ceph_check_caps+0x5f0/0xc60
   ceph_flush_dirty_caps+0x7c/0x150
   ? __ia32_sys_fdatasync+0x20/0x20
   ceph_sync_fs+0x5a/0x130
   iterate_supers+0x8f/0xf0
   ksys_sync+0x4f/0xb0
   __ia32_sys_sync+0xa/0x10
   do_syscall_64+0x50/0x1c0
   entry_SYSCALL_64_after_hwframe+0x49/0xbe
  RIP: 0033:0x7fc6409ab617

Signed-off-by: Luis Henriques <lhenriques@suse.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
ceph: handle change_attr in cap messages 2019-07-08T12:01:43+00:00 Jeff Layton jlayton@kernel.org 2019-06-06T12:06:40+00:00 176c77c9c9b1f843332496a28f4545eb96d5dab9 Signed-off-by: Jeff Layton <jlayton@kernel.org> Reviewed-by: "Yan, Zheng" <zyan@redhat.com> Signed-off-by: Ilya Dryomov <idryomov@gmail.com> 
Signed-off-by: Jeff Layton <jlayton@kernel.org>
Reviewed-by: "Yan, Zheng" <zyan@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
ceph: handle btime in cap messages 2019-07-08T12:01:43+00:00 Jeff Layton jlayton@kernel.org 2019-05-29T16:23:14+00:00 ec62b894df1ae69eb8e66d69317dfff517f6d1f3 Signed-off-by: Jeff Layton <jlayton@kernel.org> Reviewed-by: "Yan, Zheng" <zyan@redhat.com> Signed-off-by: Ilya Dryomov <idryomov@gmail.com> 
Signed-off-by: Jeff Layton <jlayton@kernel.org>
Reviewed-by: "Yan, Zheng" <zyan@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
ceph: avoid iput_final() while holding mutex or in dispatch thread 2019-06-05T18:34:39+00:00 Yan, Zheng zyan@redhat.com 2019-05-18T12:39:55+00:00 3e1d0452edceebb903d23db53201013c940bf000 iput_final() may wait for reahahead pages. The wait can cause deadlock. For example: Workqueue: ceph-msgr ceph_con_workfn [libceph] Call Trace: schedule+0x36/0x80 io_schedule+0x16/0x40 __lock_page+0x101/0x140 truncate_inode_pages_range+0x556/0x9f0 truncate_inode_pages_final+0x4d/0x60 evict+0x182/0x1a0 iput+0x1d2/0x220 iterate_session_caps+0x82/0x230 [ceph] dispatch+0x678/0xa80 [ceph] ceph_con_workfn+0x95b/0x1560 [libceph] process_one_work+0x14d/0x410 worker_thread+0x4b/0x460 kthread+0x105/0x140 ret_from_fork+0x22/0x40 Workqueue: ceph-msgr ceph_con_workfn [libceph] Call Trace: __schedule+0x3d6/0x8b0 schedule+0x36/0x80 schedule_preempt_disabled+0xe/0x10 mutex_lock+0x2f/0x40 ceph_check_caps+0x505/0xa80 [ceph] ceph_put_wrbuffer_cap_refs+0x1e5/0x2c0 [ceph] writepages_finish+0x2d3/0x410 [ceph] __complete_request+0x26/0x60 [libceph] handle_reply+0x6c8/0xa10 [libceph] dispatch+0x29a/0xbb0 [libceph] ceph_con_workfn+0x95b/0x1560 [libceph] process_one_work+0x14d/0x410 worker_thread+0x4b/0x460 kthread+0x105/0x140 ret_from_fork+0x22/0x40 In above example, truncate_inode_pages_range() waits for readahead pages while holding s_mutex. ceph_check_caps() waits for s_mutex and blocks OSD dispatch thread. Later OSD replies (for readahead) can't be handled. ceph_check_caps() also may lock snap_rwsem for read. So similar deadlock can happen if iput_final() is called while holding snap_rwsem. In general, it's not good to call iput_final() inside MDS/OSD dispatch threads or while holding any mutex. The fix is introducing ceph_async_iput(), which calls iput_final() in workqueue. Signed-off-by: "Yan, Zheng" <zyan@redhat.com> Reviewed-by: Jeff Layton <jlayton@redhat.com> Signed-off-by: Ilya Dryomov <idryomov@gmail.com> 
iput_final() may wait for reahahead pages. The wait can cause deadlock.
For example:

  Workqueue: ceph-msgr ceph_con_workfn [libceph]
    Call Trace:
     schedule+0x36/0x80
     io_schedule+0x16/0x40
     __lock_page+0x101/0x140
     truncate_inode_pages_range+0x556/0x9f0
     truncate_inode_pages_final+0x4d/0x60
     evict+0x182/0x1a0
     iput+0x1d2/0x220
     iterate_session_caps+0x82/0x230 [ceph]
     dispatch+0x678/0xa80 [ceph]
     ceph_con_workfn+0x95b/0x1560 [libceph]
     process_one_work+0x14d/0x410
     worker_thread+0x4b/0x460
     kthread+0x105/0x140
     ret_from_fork+0x22/0x40

  Workqueue: ceph-msgr ceph_con_workfn [libceph]
    Call Trace:
     __schedule+0x3d6/0x8b0
     schedule+0x36/0x80
     schedule_preempt_disabled+0xe/0x10
     mutex_lock+0x2f/0x40
     ceph_check_caps+0x505/0xa80 [ceph]
     ceph_put_wrbuffer_cap_refs+0x1e5/0x2c0 [ceph]
     writepages_finish+0x2d3/0x410 [ceph]
     __complete_request+0x26/0x60 [libceph]
     handle_reply+0x6c8/0xa10 [libceph]
     dispatch+0x29a/0xbb0 [libceph]
     ceph_con_workfn+0x95b/0x1560 [libceph]
     process_one_work+0x14d/0x410
     worker_thread+0x4b/0x460
     kthread+0x105/0x140
     ret_from_fork+0x22/0x40

In above example, truncate_inode_pages_range() waits for readahead pages
while holding s_mutex. ceph_check_caps() waits for s_mutex and blocks
OSD dispatch thread. Later OSD replies (for readahead) can't be handled.

ceph_check_caps() also may lock snap_rwsem for read. So similar deadlock
can happen if iput_final() is called while holding snap_rwsem.

In general, it's not good to call iput_final() inside MDS/OSD dispatch
threads or while holding any mutex.

The fix is introducing ceph_async_iput(), which calls iput_final() in
workqueue.

Signed-off-by: "Yan, Zheng" <zyan@redhat.com>
Reviewed-by: Jeff Layton <jlayton@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>