linux.git/drivers/md/dm.c, branch v3.11

dm: optimize reorder structure

2013-07-10T22:41:18+00:00

This reorder actually improves performance by 20% (from 39.1s to 32.8s)
on x86-64 quad core Opteron.

I have no explanation for this, possibly it makes some other entries are
better cache-aligned.

Signed-off-by: Mikulas Patocka 
Signed-off-by: Alasdair G Kergon

dm: optimize use SRCU and RCU

2013-07-10T22:41:18+00:00

This patch removes "io_lock" and "map_lock" in struct mapped_device and
"holders" in struct dm_table and replaces these mechanisms with
sleepable-rcu.

Previously, the code would call "dm_get_live_table" and "dm_table_put" to
get and release table. Now, the code is changed to call "dm_get_live_table"
and "dm_put_live_table". dm_get_live_table locks sleepable-rcu and
dm_put_live_table unlocks it.

dm_get_live_table_fast/dm_put_live_table_fast can be used instead of
dm_get_live_table/dm_put_live_table. These *_fast functions use
non-sleepable RCU, so the caller must not block between them.

If the code changes active or inactive dm table, it must call
dm_sync_table before destroying the old table.

Signed-off-by: Mikulas Patocka 
Signed-off-by: Jun'ichi Nomura 
Signed-off-by: Alasdair G Kergon

dm mpath: fix ioctl deadlock when no paths

2013-07-10T22:41:15+00:00

When multipath needs to retry an ioctl the reference to the
current live table needs to be dropped. Otherwise a deadlock
occurs when all paths are down:
- dm_blk_ioctl takes a reference to the current table
  and spins in multipath_ioctl().
- A new table is being loaded, but upon resume the process
  hangs in dm_table_destroy() waiting for references to
  drop to zero.

With this patch the reference to the old table is dropped
prior to retry, thereby avoiding the deadlock.

Signed-off-by: Hannes Reinecke 
Cc: Mike Snitzer 
Cc: stable@vger.kernel.org
Signed-off-by: Alasdair G Kergon

block_device_operations->release() should return void

2013-05-07T06:16:21+00:00

The value passed is 0 in all but "it can never happen" cases (and those
only in a couple of drivers) *and* it would've been lost on the way
out anyway, even if something tried to pass something meaningful.
Just don't bother.

Signed-off-by: Al Viro

Revert "block: add missing block_bio_complete() tracepoint"

2013-04-18T16:00:26+00:00

This reverts commit 3a366e614d0837d9fc23f78cdb1a1186ebc3387f.

Wanlong Gao reports that it causes a kernel panic on his machine several
minutes after boot. Reverting it removes the panic.

Jens says:
 "It's not quite clear why that is yet, so I think we should just revert
  the commit for 3.9 final (which I'm assuming is pretty close).

  The wifi is crap at the LSF hotel, so sending this email instead of
  queueing up a revert and pull request."

Reported-by: Wanlong Gao 
Requested-by: Jens Axboe 
Cc: Tejun Heo 
Cc: Steven Rostedt 
Signed-off-by: Linus Torvalds

dm: add target num_write_bios fn

2013-03-01T22:45:49+00:00

Add a num_write_bios function to struct target.

If an instance of a target sets this, it will be queried before the
target's mapping function is called on a write bio, and the response
controls the number of copies of the write bio that the target will
receive.

This provides a convenient way for a target to send the same data to
more than one device.  The new cache target uses this in writethrough
mode, to send the data both to the cache and the backing device.

Signed-off-by: Alasdair G Kergon

dm: merge io_pool and tio_pool

2013-03-01T22:45:48+00:00

This patch merges io_pool and tio_pool into io_pool and cleans up
related functions.

Though device-mapper used to have 2 pools of objects for each dm device,
the use of bioset frontbad for per-bio data has shrunk the number of
pools to 1 for both bio-based and request-based device types.
(See c0820cf5 "dm: introduce per_bio_data" and
 94818742 "dm: Use bioset's front_pad for dm_rq_clone_bio_info")

So dm no longer has to maintain 2 different pointers.

No functional changes.

Signed-off-by: Jun'ichi Nomura 
Signed-off-by: Alasdair G Kergon

dm: remove unused _rq_bio_info_cache

2013-03-01T22:45:48+00:00

Remove _rq_bio_info_cache, which is no longer used.
No functional changes.

Signed-off-by: Jun'ichi Nomura 
Signed-off-by: Alasdair G Kergon

dm: fix limits initialization when there are no data devices

2013-03-01T22:45:48+00:00

dm_calculate_queue_limits will first reset the provided limits to
defaults using blk_set_stacking_limits; whereby defeating the purpose of
retaining the original live table's limits -- as was intended via commit
3ae706561637331aa578e52bb89ecbba5edcb7a9 ("dm: retain table limits when
swapping to new table with no devices").

Fix this improper limits initialization (in the no data devices case) by
avoiding the call to dm_calculate_queue_limits.

[patch header revised by Mike Snitzer]

Signed-off-by: Mike Christie 
Signed-off-by: Mike Snitzer 
Cc: stable@vger.kernel.org # v3.6+
Signed-off-by: Alasdair G Kergon

dm: refactor bio cloning

2013-03-01T22:45:47+00:00

Refactor part of the bio splitting and cloning code to try to make it
easier to understand.

Signed-off-by: Alasdair G Kergon