linux-stable.git/drivers/md, branch v3.14.73

md: multipath: don't hardcopy bio in .make_request path

2016-04-12T16:12:46+00:00

commit fafcde3ac1a418688a734365203a12483b83907a upstream.

Inside multipath_make_request(), multipath maps the incoming
bio into low level device's bio, but it is totally wrong to
copy the bio into mapped bio via '*mapped_bio = *bio'. For
example, .__bi_remaining is kept in the copy, especially if
the incoming bio is chained to via bio splitting, so .bi_end_io
can't be called for the mapped bio at all in the completing path
in this kind of situation.

This patch fixes the issue by using clone style.

Reported-and-tested-by: Andrea Righi 
Signed-off-by: Ming Lei 
Signed-off-by: Shaohua Li 
Signed-off-by: Greg Kroah-Hartman

md/raid5: Compare apples to apples (or sectors to sectors)

2016-04-12T16:12:46+00:00

commit e7597e69dec59b65c5525db1626b9d34afdfa678 upstream.

'max_discard_sectors' is in sectors, while 'stripe' is in bytes.

This fixes the problem where DISCARD would get disabled on some larger
RAID5 configurations (6 or more drives in my testing), while it worked
as expected with smaller configurations.

Fixes: 620125f2bf8 ("MD: raid5 trim support")
Signed-off-by: Jes Sorensen 
Signed-off-by: Shaohua Li 
Signed-off-by: Greg Kroah-Hartman

bcache: fix cache_set_flush() NULL pointer dereference on OOM

2016-04-12T16:12:46+00:00

commit f8b11260a445169989d01df75d35af0f56178f95 upstream.

When bch_cache_set_alloc() fails to kzalloc the cache_set, the
asyncronous closure handling tries to dereference a cache_set that
hadn't yet been allocated inside of cache_set_flush() which is called
by __cache_set_unregister() during cleanup.  This appears to happen only
during an OOM condition on bcache_register.

Signed-off-by: Eric Wheeler 
Signed-off-by: Greg Kroah-Hartman

dm snapshot: fix hung bios when copy error occurs

2016-03-03T23:06:51+00:00

commit 385277bfb57faac44e92497104ba542cdd82d5fe upstream.

When there is an error copying a chunk dm-snapshot can incorrectly hold
associated bios indefinitely, resulting in hung IO.

The function copy_callback sets pe->error if there was error copying the
chunk, and then calls complete_exception.  complete_exception calls
pending_complete on error, otherwise it calls commit_exception with
commit_callback (and commit_callback calls complete_exception).

The persistent exception store (dm-snap-persistent.c) assumes that calls
to prepare_exception and commit_exception are paired.
persistent_prepare_exception increases ps->pending_count and
persistent_commit_exception decreases it.

If there is a copy error, persistent_prepare_exception is called but
persistent_commit_exception is not.  This results in the variable
ps->pending_count never returning to zero and that causes some pending
exceptions (and their associated bios) to be held forever.

Fix this by unconditionally calling commit_exception regardless of
whether the copy was successful.  A new "valid" parameter is added to
commit_exception -- when the copy fails this parameter is set to zero so
that the chunk that failed to copy (and all following chunks) is not
recorded in the snapshot store.  Also, remove commit_callback now that
it is merely a wrapper around pending_complete.

Signed-off-by: Mikulas Patocka 
Signed-off-by: Mike Snitzer 
Signed-off-by: Greg Kroah-Hartman

dm space map metadata: remove unused variable in brb_pop()

2016-03-03T23:06:51+00:00

commit 512167788a6fe9481a33a3cce5f80b684631a1bb upstream.

Remove the unused struct block_op pointer that was inadvertantly
introduced, via cut-and-paste of previous brb_op() code, as part of
commit 50dd842ad.

(Cc'ing stable@ because commit 50dd842ad did)

Fixes: 50dd842ad ("dm space map metadata: fix ref counting bug when bootstrapping a new space map")
Reported-by: David Binderman 
Signed-off-by: Mike Snitzer 
Signed-off-by: Greg Kroah-Hartman

dm btree: fix bufio buffer leaks in dm_btree_del() error path

2016-03-03T23:06:50+00:00

commit ed8b45a3679eb49069b094c0711b30833f27c734 upstream.

If dm_btree_del()'s call to push_frame() fails, e.g. due to
btree_node_validator finding invalid metadata, the dm_btree_del() error
path must unlock all frames (which have active dm-bufio buffers) that
were pushed onto the del_stack.

Otherwise, dm_bufio_client_destroy() will BUG_ON() because dm-bufio
buffers have leaked, e.g.:
  device-mapper: bufio: leaked buffer 3, hold count 1, list 0

Signed-off-by: Joe Thornber 
Signed-off-by: Mike Snitzer 
Signed-off-by: Greg Kroah-Hartman

dm space map metadata: fix ref counting bug when bootstrapping a new space map

2016-03-03T23:06:50+00:00

commit 50dd842ad83b43bed71790efb31cfb2f6c05c9c1 upstream.

When applying block operations (BOPs) do not remove them from the
uncommitted BOP ring-buffer until after they've been applied -- in case
we recurse.

Also, perform BOP_INC operation, in dm_sm_metadata_create() and
sm_metadata_extend(), in terms of the uncommitted BOP ring-buffer rather
than using direct calls to sm_ll_inc().

Signed-off-by: Joe Thornber 
Signed-off-by: Mike Snitzer 
Signed-off-by: Greg Kroah-Hartman

dm thin: fix race condition when destroying thin pool workqueue

2016-03-03T23:06:45+00:00

commit 18d03e8c25f173f4107a40d0b8c24defb6ed69f3 upstream.

When a thin pool is being destroyed delayed work items are
cancelled using cancel_delayed_work(), which doesn't guarantee that on
return the delayed item isn't running.  This can cause the work item to
requeue itself on an already destroyed workqueue.  Fix this by using
cancel_delayed_work_sync() which guarantees that on return the work item
is not running anymore.

Fixes: 905e51b39a555 ("dm thin: commit outstanding data every second")
Fixes: 85ad643b7e7e5 ("dm thin: add timeout to stop out-of-data-space mode holding IO forever")
Signed-off-by: Nikolay Borisov 
Signed-off-by: Mike Snitzer 
Signed-off-by: Greg Kroah-Hartman

dm thin metadata: fix bug when taking a metadata snapshot

2016-03-03T23:06:45+00:00

commit 49e99fc717f624aa75ca755d6e7bc029efd3f0e9 upstream.

When you take a metadata snapshot the btree roots for the mapping and
details tree need to have their reference counts incremented so they
persist for the lifetime of the metadata snap.

The roots being incremented were those currently written in the
superblock, which could possibly be out of date if concurrent IO is
triggering new mappings, breaking of sharing, etc.

Fix this by performing a commit with the metadata lock held while taking
a metadata snapshot.

Signed-off-by: Joe Thornber 
Signed-off-by: Mike Snitzer 
Signed-off-by: Greg Kroah-Hartman

dm thin: restore requested 'error_if_no_space' setting on OODS to WRITE transition

2016-03-03T23:06:45+00:00

commit 172c238612ebf81cabccc86b788c9209af591f61 upstream.

A thin-pool that is in out-of-data-space (OODS) mode may transition back
to write mode -- without the admin adding more space to the thin-pool --
if/when blocks are released (either by deleting thin devices or
discarding provisioned blocks).

But as part of the thin-pool's earlier transition to out-of-data-space
mode the thin-pool may have set the 'error_if_no_space' flag to true if
the no_space_timeout expires without more space having been made
available.  That implementation detail, of changing the pool's
error_if_no_space setting, needs to be reset back to the default that
the user specified when the thin-pool's table was loaded.

Otherwise we'll drop the user requested behaviour on the floor when this
out-of-data-space to write mode transition occurs.

Reported-by: Vivek Goyal 
Signed-off-by: Mike Snitzer 
Acked-by: Joe Thornber 
Fixes: 2c43fd26e4 ("dm thin: fix missing out-of-data-space to write mode transition if blocks are released")
Signed-off-by: Greg Kroah-Hartman