Skip to content

cloud-kernel
cloud-kernel

openanolis / cloud-kernel
1 年多 前同步成功

通知 160
Star 36
Fork 7
cloud-kernel
cloud-kernel
切换分支/标签
  1. 22 7月, 2017 5 次提交
  3. 19 6月, 2017 1 次提交
  5. 17 6月, 2017 1 次提交
  7. 14 6月, 2017 2 次提交
    • M
      md: don't use flush_signals in userspace processes · f9c79bc0
      由 Mikulas Patocka 提交于 
      The function flush_signals clears all pending signals for the process. It
may be used by kernel threads when we need to prepare a kernel thread for
responding to signals. However using this function for an userspaces
processes is incorrect - clearing signals without the program expecting it
can cause misbehavior.

The raid1 and raid5 code uses flush_signals in its request routine because
it wants to prepare for an interruptible wait. This patch drops
flush_signals and uses sigprocmask instead to block all signals (including
SIGKILL) around the schedule() call. The signals are not lost, but the
schedule() call won't respond to them.
Signed-off-by: NMikulas Patocka <mpatocka@redhat.com>
Cc: stable@vger.kernel.org
Acked-by: NNeilBrown <neilb@suse.com>
Signed-off-by: NShaohua Li <shli@fb.com>
      f9c79bc0
    • N
      md: fix deadlock between mddev_suspend() and md_write_start() · cc27b0c7
      由 NeilBrown 提交于 
      If mddev_suspend() races with md_write_start() we can deadlock
with mddev_suspend() waiting for the request that is currently
in md_write_start() to complete the ->make_request() call,
and md_write_start() waiting for the metadata to be updated
to mark the array as 'dirty'.
As metadata updates done by md_check_recovery() only happen then
the mddev_lock() can be claimed, and as mddev_suspend() is often
called with the lock held, these threads wait indefinitely for each
other.

We fix this by having md_write_start() abort if mddev_suspend()
is happening, and ->make_request() aborts if md_write_start()
aborted.
md_make_request() can detect this abort, decrease the ->active_io
count, and wait for mddev_suspend().
Reported-by: NNix <nix@esperi.org.uk>
Fix: 68866e42(MD: no sync IO while suspended)
Cc: stable@vger.kernel.org
Signed-off-by: NNeilBrown <neilb@suse.com>
Signed-off-by: NShaohua Li <shli@fb.com>
      cc27b0c7
  9. 09 6月, 2017 1 次提交
  11. 06 6月, 2017 1 次提交
  13. 13 5月, 2017 1 次提交
    • T
      raid1: prefer disk without bad blocks · d82dd0e3
      由 Tomasz Majchrzak 提交于 
      If an array consists of two drives and the first drive has the bad
block, the read request to the region overlapping the bad block chooses
the same disk (with bad block) as device to read from over and over and
the request gets stuck. If the first disk only partially overlaps with
bad block, it becomes a candidate ("best disk") for shorter range of
sectors. The second disk is capable of reading the entire requested
range and it is updated accordingly, however it is not recorded as a
best device for the request. In the end the request is sent to the first
disk to read entire range of sectors. It fails and is re-tried in a
moment but with the same outcome.

Actually it is quite likely scenario but it had little exposure in my
test until commit 715d40b93b10 ("md/raid1: add failfast handling for
reads.") removed preference for idle disk. Such scenario had been
passing as second disk was always chosen when idle.

Reset a candidate ("best disk") to read from if disk can read entire
range. Do it only if other disk has already been chosen as a candidate
for a smaller range. The head position / disk type logic will select
the best disk to read from - it is fine as disk with bad block won't be
considered for it.
Signed-off-by: NTomasz Majchrzak <tomasz.majchrzak@intel.com>
Signed-off-by: NShaohua Li <shli@fb.com>
      d82dd0e3
  15. 12 5月, 2017 1 次提交
  17. 09 5月, 2017 1 次提交
  19. 28 4月, 2017 1 次提交
    • X
      md/raid1: Use a new variable to count flighting sync requests · 43ac9b84
      由 Xiao Ni 提交于 
      In new barrier codes, raise_barrier waits if conf->nr_pending[idx] is not zero.
After all the conditions are true, the resync request can go on be handled. But
it adds conf->nr_pending[idx] again. The next resync request hit the same bucket
idx need to wait the resync request which is submitted before. The performance
of resync/recovery is degraded.
So we should use a new variable to count sync requests which are in flight.

I did a simple test:
1. Without the patch, create a raid1 with two disks. The resync speed:
Device:         rrqm/s   wrqm/s     r/s     w/s    rMB/s    wMB/s avgrq-sz avgqu-sz   await r_await w_await  svctm  %util
sdb               0.00     0.00  166.00    0.00    10.38     0.00   128.00     0.03    0.20    0.20    0.00   0.19   3.20
sdc               0.00     0.00    0.00  166.00     0.00    10.38   128.00     0.96    5.77    0.00    5.77   5.75  95.50
2. With the patch, the result is:
sdb            2214.00     0.00  766.00    0.00   185.69     0.00   496.46     2.80    3.66    3.66    0.00   1.03  79.10
sdc               0.00  2205.00    0.00  769.00     0.00   186.44   496.52     5.25    6.84    0.00    6.84   1.30 100.10
Suggested-by: NShaohua Li <shli@kernel.org>
Signed-off-by: NXiao Ni <xni@redhat.com>
Acked-by: NColy Li <colyli@suse.de>
Signed-off-by: NShaohua Li <shli@fb.com>
      43ac9b84
  21. 26 4月, 2017 1 次提交
  23. 24 4月, 2017 1 次提交
  25. 12 4月, 2017 4 次提交
    • N
      md/raid1: factor out flush_bio_list() · 673ca68d
      由 NeilBrown 提交于 
      flush_pending_writes() and raid1_unplug() each contain identical
copies of a fairly large slab of code.  So factor that out into
new flush_bio_list() to simplify maintenance.
Signed-off-by: NNeilBrown <neilb@suse.com>
Signed-off-by: NShaohua Li <shli@fb.com>
      673ca68d
    • N
      md/raid1: simplify handle_read_error(). · 689389a0
      由 NeilBrown 提交于 
      handle_read_error() duplicates a lot of the work that raid1_read_request()
does, so it makes sense to just use that function.
This doesn't quite work as handle_read_error() relies on the same r1bio
being re-used so that, in the case of a read-only array, setting
IO_BLOCKED in r1bio->bios[] ensures read_balance() won't re-use
that device.
So we need to allow a r1bio to be passed to raid1_read_request(), and to
have that function mostly initialise the r1bio, but leave the bios[]
array untouched.

Two parts of handle_read_error() that need to be preserved are the warning
message it prints, so they are conditionally added to raid1_read_request().

Note that this highlights a minor bug on alloc_r1bio().  It doesn't
initalise the bios[] array, so it is possible that old content is there,
which might cause read_balance() to ignore some devices with no good reason.

With this change, we no longer need inc_pending(), or the sectors_handled
arg to alloc_r1bio().

As handle_read_error() is called from raid1d() and allocates memory,
there is tiny chance of a deadlock.  All element of various pools
could be queued waiting for raid1 to handle them, and there may be no
extra memory free.
Achieving guaranteed forward progress would probably require a second
thread and another mempool.  Instead of that complexity, add
__GFP_HIGH to any allocations when read1_read_request() is called
from raid1d.
Signed-off-by: NNeilBrown <neilb@suse.com>
Signed-off-by: NShaohua Li <shli@fb.com>
      689389a0
    • N
      md/raid1: simplify alloc_behind_master_bio() · cb83efcf
      由 NeilBrown 提交于 
      Now that we always always pass an offset of 0 and a size
that matches the bio to alloc_behind_master_bio(),
we can remove the offset/size args and simplify the code.

We could probably remove bio_copy_data_partial() too.
Signed-off-by: NNeilBrown <neilb@suse.com>
Signed-off-by: NShaohua Li <shli@fb.com>
      cb83efcf
    • N
      md/raid1: simplify the splitting of requests. · c230e7e5
      由 NeilBrown 提交于 
      raid1 currently splits requests in two different ways for
two different reasons.

First, bio_split() is used to ensure the bio fits within a
resync accounting region.
Second, multiple r1bios are allocated for each bio to handle
the possiblity of known bad blocks on some devices.

This can be simplified to just use bio_split() once, and not
use multiple r1bios.
We delay the split until we know a maximum bio size that can
be handled with a single r1bio, and then split the bio and
queue the remainder for later handling.

This avoids all loops inside raid1.c request handling.  Just
a single read, or a single set of writes, is submitted to
lower-level devices for each bio that comes from
generic_make_request().

When the bio needs to be split, generic_make_request() will
do the necessary looping and call md_make_request() multiple
times.

raid1_make_request() no longer queues request for raid1 to handle,
so we can remove that branch from the 'if'.

This patch also creates a new private bio_set
(conf->bio_split) for splitting bios.  Using fs_bio_set
is wrong, as it is meant to be used by filesystems, not
block devices.  Using it inside md can lead to deadlocks
under high memory pressure.

Delete unused variable in raid1_write_request() (Shaohua)
Signed-off-by: NNeilBrown <neilb@suse.com>
Signed-off-by: NShaohua Li <shli@fb.com>
      c230e7e5
  27. 11 4月, 2017 1 次提交
    • N
      md/raid1: avoid reusing a resync bio after error handling. · 0c9d5b12
      由 NeilBrown 提交于 
      fix_sync_read_error() modifies a bio on a newly faulty
device by setting bi_end_io to end_sync_write.
This ensure that put_buf() will still call rdev_dec_pending()
as required, but makes sure that subsequent code in
fix_sync_read_error() doesn't try to read from the device.

Unfortunately this interacts badly with sync_request_write()
which assumes that any bio with bi_end_io set to non-NULL
other than end_sync_read is safe to write to.

As the device is now faulty it doesn't make sense to write.
As the bio was recently used for a read, it is "dirty"
and not suitable for immediate submission.
In particular, ->bi_next might be non-NULL, which will cause
generic_make_request() to complain.

Break this interaction by refusing to write to devices
which are marked as Faulty.
Reported-and-tested-by: NMichael Wang <yun.wang@profitbricks.com>
Fixes: 2e52d449 ("md/raid1: add failfast handling for reads.")
Cc: stable@vger.kernel.org (v4.10+)
Signed-off-by: NNeilBrown <neilb@suse.com>
Signed-off-by: NShaohua Li <shli@fb.com>
      0c9d5b12
  29. 09 4月, 2017 1 次提交
  31. 28 3月, 2017 1 次提交
    • M
      md: raid1: kill warning on powerpc_pseries · 8fc04e6e
      由 Ming Lei 提交于 
      This patch kills the warning reported on powerpc_pseries,
and actually we don't need the initialization.

	After merging the md tree, today's linux-next build (powerpc
	pseries_le_defconfig) produced this warning:

	drivers/md/raid1.c: In function 'raid1d':
	drivers/md/raid1.c:2172:9: warning: 'page_len$' may be used uninitialized in this function [-Wmaybe-uninitialized]
	     if (memcmp(page_address(ppages[j]),
	         ^
	drivers/md/raid1.c:2160:7: note: 'page_len$' was declared here
	   int page_len[RESYNC_PAGES];
       ^
Signed-off-by: NMing Lei <tom.leiming@gmail.com>
Signed-off-by: NShaohua Li <shli@fb.com>
      8fc04e6e
  33. 26 3月, 2017 1 次提交
  35. 25 3月, 2017 8 次提交
  37. 23 3月, 2017 2 次提交
    • N
      md/raid1: stop using bi_phys_segment · 37011e3a
      由 NeilBrown 提交于 
      Change to use bio->__bi_remaining to count number of r1bio attached
to a bio.
See precious raid10 patch for more details.

Like the raid10.c patch, this fixes a bug as nr_queued and nr_pending
used to measure different things, but were being compared.

This patch fixes another bug in that nr_pending previously did not
could write-behind requests, so behind writes could continue while
resync was happening.  How that nr_pending counts all r1_bio,
the resync cannot commence until the behind writes have completed.
Signed-off-by: NNeilBrown <neilb@suse.com>
Signed-off-by: NShaohua Li <shli@fb.com>
      37011e3a
    • N
      md/raid1, raid10: move rXbio accounting closer to allocation. · 6b6c8110
      由 NeilBrown 提交于 
      When raid1 or raid10 find they will need to allocate a new
r1bio/r10bio, in order to work around a known bad block, they
account for the allocation well before the allocation is
made.  This separation makes the correctness less obvious
and requires comments.

The accounting needs to be a little before: before the first
rXbio is submitted, but that is all.

So move the accounting down to where it makes more sense.
Signed-off-by: NNeilBrown <neilb@suse.com>
Signed-off-by: NShaohua Li <shli@fb.com>
      6b6c8110
  39. 17 3月, 2017 1 次提交
  41. 15 3月, 2017 1 次提交
  43. 10 3月, 2017 2 次提交
    • S
      md/raid1/10: fix potential deadlock · 61eb2b43
      由 Shaohua Li 提交于 
      Neil Brown pointed out a potential deadlock in raid 10 code with
bio_split/chain. The raid1 code could have the same issue, but recent
barrier rework makes it less likely to happen. The deadlock happens in
below sequence:

1. generic_make_request(bio), this will set current->bio_list
2. raid10_make_request will split bio to bio1 and bio2
3. __make_request(bio1), wait_barrer, add underlayer disk bio to
current->bio_list
4. __make_request(bio2), wait_barrer

If raise_barrier happens between 3 & 4, since wait_barrier runs at 3,
raise_barrier waits for IO completion from 3. And since raise_barrier
sets barrier, 4 waits for raise_barrier. But IO from 3 can't be
dispatched because raid10_make_request() doesn't finished yet.

The solution is to adjust the IO ordering. Quotes from Neil:
"
It is much safer to:

    if (need to split) {
        split = bio_split(bio, ...)
        bio_chain(...)
        make_request_fn(split);
        generic_make_request(bio);
   } else
        make_request_fn(mddev, bio);

This way we first process the initial section of the bio (in 'split')
which will queue some requests to the underlying devices.  These
requests will be queued in generic_make_request.
Then we queue the remainder of the bio, which will be added to the end
of the generic_make_request queue.
Then we return.
generic_make_request() will pop the lower-level device requests off the
queue and handle them first.  Then it will process the remainder
of the original bio once the first section has been fully processed.
"

Note, this only happens in read path. In write path, the bio is flushed to
underlaying disks either by blk flush (from schedule) or offladed to raid1/10d.
It's queued in current->bio_list.

Cc: Coly Li <colyli@suse.de>
Cc: stable@vger.kernel.org (v3.14+, only the raid10 part)
Suggested-by: NNeilBrown <neilb@suse.com>
Reviewed-by: NJack Wang <jinpu.wang@profitbricks.com>
Signed-off-by: NShaohua Li <shli@fb.com>
      61eb2b43
    • G
      md: move funcs from pers->resize to update_size · c9483634
      由 Guoqing Jiang 提交于 
      raid1_resize and raid5_resize should also check the
mddev->queue if run underneath dm-raid.

And both set_capacity and revalidate_disk are used in
pers->resize such as raid1, raid10 and raid5. So
move them from personality file to common code.
Reviewed-by: NNeilBrown <neilb@suse.com>
Signed-off-by: NGuoqing Jiang <gqjiang@suse.com>
Signed-off-by: NShaohua Li <shli@fb.com>
      c9483634
  45. 02 3月, 2017 1 次提交