linux-stable.git/drivers/md/raid10.c, branch v4.12.2

md: initialise ->writes_pending in personality modules.

2017-06-05T23:04:35+00:00

The new per-cpu counter for writes_pending is initialised in
md_alloc(), which is not called by dm-raid.
So dm-raid fails when md_write_start() is called.

Move the initialization to the personality modules
that need it.  This way it is always initialised when needed,
but isn't unnecessarily initialized (requiring memory allocation)
when the personality doesn't use writes_pending.

Reported-by: Heinz Mauelshagen 
Fixes: 4ad23a976413 ("MD: use per-cpu counter for writes_pending")
Signed-off-by: NeilBrown 
Signed-off-by: Shaohua Li

md/raid1/10: avoid unnecessary locking

2017-05-11T22:32:17+00:00

If we add bios to block plugging list, locking is unnecessry, since the block
unplug is guaranteed not to run at that time.

Reviewed-by: NeilBrown 
Signed-off-by: Shaohua Li

Merge branch 'md-next' into md-linus

2017-05-01T21:09:21+00:00

md/raid10: skip spare disk as 'first' disk

2017-05-01T19:24:10+00:00

Commit 6f287ca(md/raid10: reset the 'first' at the end of loop) ignores
a case in reshape, the first rdev could be a spare disk, which shouldn't
be accounted as the first disk since it doesn't include the offset info.

Fix: 6f287ca(md/raid10: reset the 'first' at the end of loop)
Cc: Guoqing Jiang 
Cc: NeilBrown 
Signed-off-by: Shaohua Li

md: clear WantReplacement once disk is removed

2017-04-25T16:36:29+00:00

We can clear 'WantReplacement' flag directly no
matter it's replacement existed or not since the
semantic is same as before.

Also since the disk is removed from array, then
it is straightforward to remove 'WantReplacement'
flag and the comments in raid10/5 can be removed
as well.

Signed-off-by: Guoqing Jiang 
Signed-off-by: Shaohua Li

md/raid1/10: remove unused queue

2017-04-23T23:59:13+00:00

A queue is declared and get from the disk of the array, but it's not
used anywhere. So removing it from the source.

Signed-off-by: Lidong Zhong 
Acted-by: Guoqing Jiang 
Signed-off-by: Shaohua Li

md/raid10: wait up frozen array in handle_write_completed

2017-04-20T16:55:52+00:00

Since nr_queued is changed, we need to call wake_up here
if the array is already frozen and waiting for condition
"nr_pending == nr_queued + extra" to be true.

And commit 824e47daddbf ("RAID1: avoid unnecessary spin
locks in I/O barrier code") which has already added the
wake_up for raid1.

Signed-off-by: Guoqing Jiang 
Reviewed-by: NeilBrown 
Signed-off-by: Shaohua Li

md/raid10: simplify handle_read_error()

2017-04-11T17:15:08+00:00

handle_read_error() duplicates a lot of the work that raid10_read_request()
does, so it makes sense to just use that function.

handle_read_error() relies on the same r10bio being re-used so that,
in the case of a read-only array, setting IO_BLOCKED in r1bio->devs[].bio
ensures read_balance() won't re-use that device.
So when called from raid10_make_request() we clear that array, but not
when called from handle_read_error().

Two parts of handle_read_error() that need to be preserved are the warning
message it prints, so they are conditionally added to
raid10_read_request().  If the failing rdev can be found, messages
are printed.  Otherwise they aren't.

Not that as rdev_dec_pending() has already been called on the failing
rdev, we need to use rcu_read_lock() to get a new reference from
the conf.  We only use this to get the name of the failing block device.

With this change, we no longer need inc_pending().

Signed-off-by: NeilBrown 
Signed-off-by: Shaohua Li

md/raid10: simplify the splitting of requests.

2017-04-11T17:13:02+00:00

raid10 splits requests in two different ways for two different
reasons.

First, bio_split() is used to ensure the bio fits with a chunk.
Second, multiple r10bio structures are allocated to represent the
different sections that need to go to different devices, to avoid
known bad blocks.

This can be simplified to just use bio_split() once, and not to use
multiple r10bios.
We delay the split until we know a maximum bio size that can
be handled with a single r10bio, and then split the bio and queue
the remainder for later handling.

As with raid1, we allocate a new bio_set to help with the splitting.
It is not correct to use fs_bio_set in a device driver.

Signed-off-by: NeilBrown 
Signed-off-by: Shaohua Li

md/raid10: reset the 'first' at the end of loop

2017-04-10T17:41:50+00:00

We need to set "first = 0' at the end of rdev_for_each
loop, so we can get the array's min_offset_diff correctly
otherwise min_offset_diff just means the last rdev's
offset diff.

Suggested-by: NeilBrown 
Signed-off-by: Guoqing Jiang 
Reviewed-by: NeilBrown 
Signed-off-by: Shaohua Li