When we get any IO error during a recovery (rebuilding a spare), we abort
the recovery and restart it.

For RAID6 (and multi-drive RAID1) it may not be best to restart at the
beginning: when multiple failures can be tolerated, the recovery may be
able to continue and re-doing all that has already been done doesn't make
sense.

We already have the infrastructure to record where a recovery is up to
and restart from there, but it is not being used properly.
This is because:
  - We sometimes abort with MD_RECOVERY_ERR rather than just MD_RECOVERY_INTR,
    which causes the recovery not be be checkpointed.
  - We remove spares and then re-added them which loses important state
    information.

The distinction between MD_RECOVERY_ERR and MD_RECOVERY_INTR really isn't
needed.  If there is an error, the relevant drive will be marked as
Faulty, and that is enough to ensure correct handling of the error.  So we
first remove MD_RECOVERY_ERR, changing some of the uses of it to
MD_RECOVERY_INTR.

Then we cause the attempt to remove a non-faulty device from an array to
fail (unless recovery is impossible as the array is too degraded).  Then
when remove_and_add_spares attempts to remove the devices on which
recovery can continue, it will fail, they will remain in place, and
recovery will continue on them as desired.

Issue:  If we are halfway through rebuilding a spare and another drive
fails, and a new spare is immediately available,  do we want to:
 1/ complete the current rebuild, then go back and rebuild the new spare or
 2/ restart the rebuild from the start and rebuild both devices in
    parallel.

Both options can be argued for.  The code currently takes option 2 as
  a/ this requires least code change
  b/ this results in a minimally-degraded array in minimal time.

Cc: "Eivind Sarto" <ivan@kasenna.com>
Signed-off-by: NNeil Brown <neilb@suse.de>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

In some configurations, a raid6 resync can be limited by CPU speed
(Calculating P and Q and moving data) rather than by device speed.  In
these cases there is nothing to be gained byt serialising resync of arrays
that share a device, and doing the resync in parallel can provide benefit.
 So add a sysfs tunable to flag an array as being allowed to resync in
parallel with other arrays that use (a different part of) the same device.
Signed-off-by: NBernd Schubert <bs@q-leap.de>
Signed-off-by: NNeil Brown <neilb@suse.de>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

This additional notification to 'array_state' is needed to allow the
monitor application to learn about stop events via sysfs.  The
sysfs_notify("sync_action") call that comes at the end of do_md_stop()
(via md_new_event) is insufficient since the 'sync_action' attribute has
been removed by this point.

(Seems like a sysfs-notify-on-removal patch is a better fix.  Currently
removal updates the event count but does not wake up waiters)
Signed-off-by: NDan Williams <dan.j.williams@intel.com>
Signed-off-by: NNeil Brown <neilb@suse.de>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

When an array enters write pending, 'array_state' changes, so we must be
sure to sysfs_notify.

Also, when waiting for user-space to acknowledge 'write-pending' by
marking the metadata as dirty, we don't want to wait for MD_CHANGE_DEVS to
be cleared as that might not happen.  So explicity test for the bits that
we are really interested in.
Signed-off-by: NNeil Brown <neilb@suse.de>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

When performing a "recovery" or "check" pass on a RAID1 array, we read
from each device and possible, if there is a difference or a read error,
write back to some devices.

We use the same 'bio' for both read and write, resetting various fields
between the two operations.

We forgot to reset bv_offset and bv_len however.  These are often left
unchanged, but in the case where there is an IO error one or two sectors
into a page, they are changed.

This results in correctable errors not being corrected properly.  It does
not result in any data corruption.

Cc: "Fairbanks, David" <David.Fairbanks@stratus.com>
Signed-off-by: NNeil Brown <neilb@suse.de>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Last night we had scsi problems and a hardware raid unit was offlined
during heavy i/o.  While this happened we got for about 3 minutes a huge
number messages like these

Apr 12 03:36:07 pfs1n14 kernel: [197510.696595] raid5:md7: read error not correctable (sector 2993096568 on sdj2).

I guess the high error rate is responsible for not scheduling other events
- during this time the system was not pingable and in the end also other
devices run into scsi command timeouts causing problems on these unrelated
devices as well.
Signed-off-by: NBernd Schubert <bernd-schubert@gmx.de>
Signed-off-by: NDan Williams <dan.j.williams@intel.com>
Signed-off-by: NNeil Brown <neilb@suse.de>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Kill the trivial and rather pointless file_path wrapper around d_path.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NNeil Brown <neilb@suse.de>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

It is possible to add a write-intent bitmap to an active array, or remove
the bitmap that is there.

When we do with the 'quiesce' the array, which causes make_request to
block in "wait_barrier()".

However we are sampling the value of "mddev->bitmap" before the
wait_barrier call, and using it afterwards.  This can result in using a
bitmap structure that has been freed.
Signed-off-by: NNeil Brown <neilb@suse.de>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

As setting and clearing queue flags now requires that we hold a spinlock
on the queue, and as blk_queue_stack_limits is called without that lock,
get the lock inside blk_queue_stack_limits.

For blk_queue_stack_limits to be able to find the right lock, each md
personality needs to set q->queue_lock to point to the appropriate lock.
Those personalities which didn't previously use a spin_lock, us
q->__queue_lock.  So always initialise that lock when allocated.

With this in place, setting/clearing of the QUEUE_FLAG_PLUGGED bit will no
longer cause warnings as it will be clear that the proper lock is held.

Thanks to Dan Williams for review and fixing the silly bugs.
Signed-off-by: NNeilBrown <neilb@suse.de>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Jens Axboe <jens.axboe@oracle.com>
Cc: Alistair John Strachan <alistair@devzero.co.uk>
Cc: Nick Piggin <npiggin@suse.de>
Cc: "Rafael J. Wysocki" <rjw@sisk.pl>
Cc: Jacek Luczak <difrost.kernel@gmail.com>
Cc: Prakash Punnoor <prakash@punnoor.de>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

commit bd2ab670 "md: close a livelock window
in handle_parity_checks5" introduced a bug in handling 'repair' operations.
After a repair operation completes we clear the state bits tracking this
operation.  However, they are cleared too early and this results in the code
deciding to re-run the parity check operation.  Since we have done the repair
in memory the second check does not find a mismatch and thus does not do a
writeback.

Test results:
$ echo repair > /sys/block/md0/md/sync_action
$ cat /sys/block/md0/md/mismatch_cnt
51072
$ echo repair > /sys/block/md0/md/sync_action
$ cat /sys/block/md0/md/mismatch_cnt
0

(also fix incorrect indentation)

Cc: <stable@kernel.org>
Tested-by: NGeorge Spelvin <linux@horizon.com>
Acked-by: NNeilBrown <neilb@suse.de>
Signed-off-by: NDan Williams <dan.j.williams@intel.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

drivers/md/raid10.c:889:17: warning: Using plain integer as NULL pointer
drivers/media/video/cx18/cx18-driver.c:616:12: warning: Using plain integer as NULL pointer
sound/oss/kahlua.c:70:12: warning: Using plain integer as NULL pointer
Signed-off-by: NHarvey Harrison <harvey.harrison@gmail.com>
Cc: Neil Brown <neilb@suse.de>
Cc: Mauro Carvalho Chehab <mchehab@infradead.org>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Allows a userspace metadata handler to take action upon detecting a device
failure.

Based on an original patch by Neil Brown.

Changes:
-added blocked_wait waitqueue to rdev
-don't qualify Blocked with Faulty always let userspace block writes
-added md_wait_for_blocked_rdev to wait for the block device to be clear, if
 userspace misses the notification another one is sent every 5 seconds
-set MD_RECOVERY_NEEDED after clearing "blocked"
-kill DoBlock flag, just test mddev->external
Signed-off-by: NDan Williams <dan.j.williams@intel.com>
Signed-off-by: NNeil Brown <neilb@suse.de>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Found when trying to reassemble an active externally managed array.  Without
this check we hit the more noisy "sysfs duplicate" warning in the later call
to kobject_add.
Signed-off-by: NDan Williams <dan.j.williams@intel.com>
Signed-off-by: NNeil Brown <neilb@suse.de>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Signed-off-by: NDan Williams <dan.j.williams@intel.com>
Signed-off-by: NNeil Brown <neilb@suse.de>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

When setting an array to 'readonly' or to 'active' via sysfs, we must make the
appropriate set_disk_ro call too.

Also when switching to "read_auto" (which is like readonly, but blocks on the
first write so that metadata can be marked 'dirty') we need to be more careful
about what state we are changing from.
Signed-off-by: NNeil Brown <neilb@suse.de>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

'safemode' relates to marking an array as 'clean' if there has been no write
traffic for a while (a couple of seconds), to reduce the chance of the array
being found dirty on reboot.

->safemode is set to '1' when there have been no write for a while, and it
gets set to '0' when the superblock is updates with the 'clean' flag set.

This requires a few fixes for 'external' metadata:
 - When an array is set to 'clean' via sysfs, 'safemode' must be cleared.
 - when we write to an array that has 'safemode' set (there must have been
        some delay in updating the metadata), we need to clear safemode.
 - Don't try to update external metadata in md_check_recovery for safemode
        transitions - it won't work.

Also, don't try to support "immediate safe mode" (safemode==2) for external
metadata, it cannot really work (the safemode timeout can be set very low if
this is really needed).
Signed-off-by: NNeil Brown <neilb@suse.de>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

I keep finding problems where an mddev gets reused and some fields has a value
from a previous usage that confuses the new usage.  So clear all fields that
could possible need clearing when calling do_md_stop.

Also initialise the 'level' of a new array to LEVEL_NONE (which isn't 0).
Signed-off-by: NNeil Brown <neilb@suse.de>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

All the metadata update processing for external metadata is on in user-space
or through the sysfs interfaces, so make "md_update_sb" a no-op in that case.
Signed-off-by: NNeil Brown <neilb@suse.de>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

rdev->mddev is no longer valid upon return from entry->store() when the
'remove' command is given.

Cc: <stable@kernel.org>
Signed-off-by: NDan Williams <dan.j.williams@intel.com>
Signed-off-by: NNeil Brown <neilb@suse.de>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

dm.c already provides mutual exclusion through ->map_lock.
Signed-off-by: NJens Axboe <jens.axboe@oracle.com>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Use proc_create()/proc_create_data() to make sure that ->proc_fops and ->data
be setup before gluing PDE to main tree.
Signed-off-by: NDenis V. Lunev <den@openvz.org>
Cc: Greg Kroah-Hartman <gregkh@suse.de>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Peter Osterlund <petero2@telia.com>
Cc: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
Cc: Dmitry Torokhov <dtor@mail.ru>
Cc: Neil Brown <neilb@suse.de>
Cc: Mauro Carvalho Chehab <mchehab@infradead.org>
Cc: Bjorn Helgaas <bjorn.helgaas@hp.com>
Cc: Alessandro Zummo <a.zummo@towertech.it>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

blk_get_request initializes rq->cmd (rq_init does) so the users don't
need to do that.

The purpose of this patch is to remove sizeof(rq->cmd) and &rq->cmd,
as a preparation for large command support, which changes rq->cmd from
the static array to a pointer. sizeof(rq->cmd) will not make sense and
&rq->cmd won't work.
Signed-off-by: NFUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
Cc: James Bottomley <James.Bottomley@HansenPartnership.com>
Cc: Alasdair G Kergon <agk@redhat.com>
Cc: Jens Axboe <jens.axboe@oracle.com>
Signed-off-by: NJens Axboe <jens.axboe@oracle.com>

We can save some atomic ops in the IO path, if we clearly define
the rules of how to modify the queue flags.
Signed-off-by: NJens Axboe <jens.axboe@oracle.com>

The functions time_before, time_before_eq, time_after, and time_after_eq
are more robust for comparing jiffies against other values.

A simplified version of the semantic patch making this change is as follows:
(http://www.emn.fr/x-info/coccinelle/)

// <smpl>
@ change_compare_np @
expression E;
@@

(
- jiffies <= E
+ time_before_eq(jiffies,E)
|
- jiffies >= E
+ time_after_eq(jiffies,E)
|
- jiffies < E
+ time_before(jiffies,E)
|
- jiffies > E
+ time_after(jiffies,E)
)

@ include depends on change_compare_np @
@@

#include <linux/jiffies.h>

@ no_include depends on !include && change_compare_np @
@@

  #include <linux/...>
+ #include <linux/jiffies.h>
// </smpl>

[akpm@linux-foundation.org: coding-style fixes]
Signed-off-by: NJulia Lawall <julia@diku.dk>
Cc: Neil Brown <neilb@suse.de>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

MD drivers use one printk() call to print 2 log messages and the second line
may be prefixed by a TAB character.  It may also output a trailing space
before newline.  klogd (I think) turns the TAB character into the 2 characters
'^I' when logging to a file.  This looks ugly.

Instead of a leading TAB to indicate continuation, prefix both output lines
with 'raid:' or similar.  Also remove any trailing space in the vicinity of
the affected code and consistently end the sentences with a period.
Signed-off-by: NNick Andrew <nick@nick-andrew.net>
Cc: Neil Brown <neilb@suse.de>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

strict_strtoul handles the open-coded sanity checks in
raid5_store_stripe_cache_size and raid5_store_preread_threshold
Acked-by: NNeilBrown <neilb@suse.de>
Signed-off-by: NDan Williams <dan.j.williams@intel.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Improve write performance by preventing the delayed_list from dumping all its
stripes onto the handle_list in one shot.  Delayed stripes are now further
delayed by being held on the 'hold_list'.  The 'hold_list' is bypassed when:

  * a STRIPE_IO_STARTED stripe is found at the head of 'handle_list'
  * 'handle_list' is empty and i/o is being done to satisfy full stripe-width
    write requests
  * 'bypass_count' is less than 'bypass_threshold'.  By default the threshold
    is 1, i.e. every other stripe handled is a preread stripe provided the
    top two conditions are false.

Benchmark data:
System: 2x Xeon 5150, 4x SATA, mem=1GB
Baseline: 2.6.24-rc7
Configuration: mdadm --create /dev/md0 /dev/sd[b-e] -n 4 -l 5 --assume-clean
Test1: dd if=/dev/zero of=/dev/md0 bs=1024k count=2048
  * patched:  +33% (stripe_cache_size = 256), +25% (stripe_cache_size = 512)

Test2: tiobench --size 2048 --numruns 5 --block 4096 --block 131072 (XFS)
  * patched: +13%
  * patched + preread_bypass_threshold = 0: +37%

Changes since v1:
* reduce bypass_threshold from (chunk_size / sectors_per_chunk) to (1) and
  make it configurable.  This defaults to fairness and modest performance
  gains out of the box.
Changes since v2:
* [neilb@suse.de]: kill STRIPE_PRIO_HI and preread_needed as they are not
  necessary, the important change was clearing STRIPE_DELAYED in
  add_stripe_bio and this has been moved out to make_request for the hang
  fix.
* [neilb@suse.de]: simplify get_priority_stripe
* [dan.j.williams@intel.com]: reset the bypass_count when ->hold_list is
  sampled empty (+11%)
* [dan.j.williams@intel.com]: decrement the bypass_count at the detection
  of stripes being naturally promoted off of hold_list +2%.  Note, resetting
  bypass_count instead of decrementing on these events yields +4% but that is
  probably too aggressive.
Changes since v3:
* cosmetic fixups
Tested-by: NJames W. Laferriere <babydr@baby-dragons.com>
Signed-off-by: NDan Williams <dan.j.williams@intel.com>
Signed-off-by: NNeil Brown <neilb@suse.de>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

__FUNCTION__ is gcc-specific, use __func__
Signed-off-by: NHarvey Harrison <harvey.harrison@gmail.com>
Cc: Neil Brown <neilb@suse.de>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

drivers/md/md.c:734:16: warning: Using plain integer as NULL pointer
drivers/md/md.c:1115:16: warning: Using plain integer as NULL pointer

Add some braces to match the else-block as well.
Signed-off-by: NHarvey Harrison <harvey.harrison@gmail.com>
Cc: Neil Brown <neilb@suse.de>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

The small patch below:
- Removes the unused md argument from both specific_minor() and next_free_minor()
- Folds kmalloc + memset(0) into a single kzalloc call in alloc_dev()

This has been compile tested on x86.
Signed-off-by: NFrederik Deweerdt <frederik.deweerdt@gmail.com>
Signed-off-by: NAlasdair G Kergon <agk@redhat.com>

dm_create_error_table() was added in kernel 2.6.18 and never used...
Signed-off-by: NAdrian Bunk <bunk@kernel.org>
Signed-off-by: NAlasdair G Kergon <agk@redhat.com>

void returning functions returned the return value of another void
returning function...

Spotted by sparse.
Signed-off-by: NAdrian Bunk <bunk@kernel.org>
Signed-off-by: NAlasdair G Kergon <agk@redhat.com>

Remove an avoidable 3ms delay on some dm-raid1 and kcopyd I/O.

It is specified that any submitted bio without BIO_RW_SYNC flag may plug the
queue (i.e. block the requests from being dispatched to the physical device).

The queue is unplugged when the caller calls blk_unplug() function. Usually, the
sequence is that someone calls submit_bh to submit IO on a buffer. The IO plugs
the queue and waits (to be possibly joined with other adjacent bios). Then, when
the caller calls wait_on_buffer(), it unplugs the queue and submits the IOs to
the disk.

This was happenning:

When doing O_SYNC writes, function fsync_buffers_list() submits a list of
bios to dm_raid1, the bios are added to dm_raid1 write queue and kmirrord is
woken up.

fsync_buffers_list() calls wait_on_buffer().  That unplugs the queue, but
there are no bios on the device queue as they are still in the dm_raid1 queue.

wait_on_buffer() starts waiting until the IO is finished.

kmirrord is scheduled, kmirrord takes bios and submits them to the devices.

The submitted bio plugs the harddisk queue but there is no one to unplug it.
(The process that called wait_on_buffer() is already sleeping.)

So there is a 3ms timeout, after which the queues on the harddisks are
unplugged and requests are processed.

This 3ms timeout meant that in certain workloads (e.g. O_SYNC, 8kb writes),
dm-raid1 is 10 times slower than md raid1.

Every time we submit something asynchronously via dm_io, we must unplug the
queue actually to send the request to the device.

This patch adds an unplug call to kmirrord - while processing requests, it keeps
the queue plugged (so that adjacent bios can be merged); when it finishes
processing all the bios, it unplugs the queue to submit the bios.

It also fixes kcopyd which has the same potential problem. All kcopyd requests
are submitted with BIO_RW_SYNC.
Signed-off-by: NMikulas Patocka <mpatocka@redhat.com>
Signed-off-by: NAlasdair G Kergon <agk@redhat.com>
Acked-by: NJens Axboe <jens.axboe@oracle.com>

This patch replaces the schedule() in the main kmirrord thread with a timer.
The schedule() could introduce an unwanted delay when work is ready to be
processed.

The code instead calls wake() when there's work to be done immediately, and
delayed_wake() after a failure to give a short delay before retrying.
Signed-off-by: NMikulas Patocka <mpatocka@redhat.com>
Signed-off-by: NAlasdair G Kergon <agk@redhat.com>

Publish the dm-io, dm-log and dm-kcopyd headers in include/linux.
Signed-off-by: NAlasdair G Kergon <agk@redhat.com>

Rename kcopyd.[ch] to dm-kcopyd.[ch].
Signed-off-by: NAlasdair G Kergon <agk@redhat.com>

Make dm.h macros and inlines available in include/linux/device-mapper.h
Signed-off-by: NAlasdair G Kergon <agk@redhat.com>

Remove client counting code that is no longer needed.

Initialization and destruction is made globally from dm_init and dm_exit and is
not based on client counts. Initialization allocates only one empty slab cache,
so there is no negative impact from performing the initialization always,
regardless of whether some client uses kcopyd or not.
Signed-off-by: NMikulas Patocka <mpatocka@redhat.com>
Signed-off-by: NAlasdair G Kergon <agk@redhat.com>

Change the global mempool in kcopyd into a per-device mempool to avoid
deadlock possibilities.
Signed-off-by: NMikulas Patocka <mpatocka@redhat.com>
Signed-off-by: NAlasdair G Kergon <agk@redhat.com>

Make one kcopyd thread per device.

The original shared kcopyd could deadlock.

Configuration: