Part of the job of garbage collection is to add up however many sectors
of live data it finds in each bucket, but that doesn't work very well if
it doesn't reset GC_SECTORS_USED() when it starts. Whoops.

This wouldn't have broken anything horribly, but allocation tries to
preferentially reclaim buckets that are mostly empty and that's not
gonna work with an incorrect GC_SECTORS_USED() value.
Signed-off-by: NKent Overstreet <kmo@daterainc.com>
Cc: linux-stable <stable@vger.kernel.org> # >= v3.10

The journal replay code starts by finding something that looks like a
valid journal entry, then it does a binary search over the unchecked
region of the journal for the journal entries with the highest sequence
numbers.

Trouble is, the logic was wrong - journal_read_bucket() returns true if
it found journal entries we need, but if the range of journal entries
we're looking for loops around the end of the journal - in that case
journal_read_bucket() could return true when it hadn't found the highest
sequence number we'd seen yet, and in that case the binary search did
the wrong thing. Whoops.
Signed-off-by: NKent Overstreet <kmo@daterainc.com>
Cc: linux-stable <stable@vger.kernel.org> # >= v3.10

Stopping a cache set is supposed to make it stop attached backing
devices, but somewhere along the way that code got lost. Fixing this
mainly has the effect of fixing our reboot notifier.
Signed-off-by: NKent Overstreet <kmo@daterainc.com>
Cc: linux-stable <stable@vger.kernel.org> # >= v3.10

If we stopped a bcache device when we were already detaching (or
something like that), bcache_device_unlink() would try to remove a
symlink from sysfs that was already gone because the bcache dev kobject
had already been removed from sysfs.

So keep track of whether we've removed stuff from sysfs.
Signed-off-by: NKent Overstreet <kmo@daterainc.com>
Cc: linux-stable <stable@vger.kernel.org> # >= v3.10

Whoops - bcache's flush/FUA was mostly correct, but flushes get filtered
out unless we say we support them...
Signed-off-by: NKent Overstreet <kmo@daterainc.com>
Cc: linux-stable <stable@vger.kernel.org> # >= v3.10

There is a missing NULL check after the kzalloc().
Signed-off-by: NDan Carpenter <dan.carpenter@oracle.com>

In the far-too-complicated closure code - closures can have destructors,
for probably dubious reasons; they get run after the closure is no
longer waiting on anything but before dropping the parent ref, intended
just for freeing whatever memory the closure is embedded in.

Trouble is, when remaining goes to 0 and we've got nothing more to run -
we also have to unlock the closure, setting remaining to -1. If there's
a destructor, that unlock isn't doing anything - nobody could be trying
to lock it if we're about to free it - but if the unlock _is needed...
that check for a destructor was racy. Argh.
Signed-off-by: NKent Overstreet <kmo@daterainc.com>
Cc: linux-stable <stable@vger.kernel.org> # >= v3.10

Some of bcache's utility code has made it into the rest of the kernel,
so drop the bcache versions.

Bcache used to have a workaround for allocating from a bio set under
generic_make_request() (if you allocated more than once, the bios you
already allocated would get stuck on current->bio_list when you
submitted, and you'd risk deadlock) - bcache would mask out __GFP_WAIT
when allocating bios under generic_make_request() so that allocation
could fail and it could retry from workqueue. But bio_alloc_bioset() has
a workaround now, so we can drop this hack and the associated error
handling.
Signed-off-by: NKent Overstreet <koverstreet@google.com>

This code has rotted and it hasn't been used in ages anyways.
Signed-off-by: NKent Overstreet <kmo@daterainc.com>

Signed-off-by: NKent Overstreet <kmo@daterainc.com>

Journal writes need to be marked FUA, not just REQ_FLUSH. And btree node
writes have... weird ordering requirements.
Signed-off-by: NKent Overstreet <koverstreet@google.com>

Signed-off-by: NGabriel de Perthuis <g2p.code@gmail.com>
Signed-off-by: NKent Overstreet <koverstreet@google.com>

Signed-off-by: NGabriel de Perthuis <g2p.code@gmail.com>

Now that we're tracking dirty data per stripe, we can add two
optimizations for raid5/6:

 * If a stripe is already dirty, force writes to that stripe to
   writeback mode - to help build up full stripes of dirty data

 * When flushing dirty data, preferentially write out full stripes first
   if there are any.
Signed-off-by: NKent Overstreet <koverstreet@google.com>

To make background writeback aware of raid5/6 stripes, we first need to
track the amount of dirty data within each stripe - we do this by
breaking up the existing sectors_dirty into per stripe atomic_ts
Signed-off-by: NKent Overstreet <koverstreet@google.com>

Previously, dirty_data wouldn't get initialized until the first garbage
collection... which was a bit of a problem for background writeback (as
the PD controller keys off of it) and also confusing for users.

This is also prep work for making background writeback aware of raid5/6
stripes.
Signed-off-by: NKent Overstreet <koverstreet@google.com>

The old lazy sorting code was kind of hacky - rewrite in a way that
mathematically makes more sense; the idea is that the size of the sets
of keys in a btree node should increase by a more or less fixed ratio
from smallest to biggest.
Signed-off-by: NKent Overstreet <koverstreet@google.com>

Old gcc doesnt like the struct hack, and it is kind of ugly. So finish
off the work to convert pr_debug() statements to tracepoints, and delete
pkey()/pbtree().
Signed-off-by: NKent Overstreet <koverstreet@google.com>

The tracepoints were reworked to be more sensible, and fixed a null
pointer deref in one of the tracepoints.

Converted some of the pr_debug()s to tracepoints - this is partly a
performance optimization; it used to be that with DEBUG or
CONFIG_DYNAMIC_DEBUG pr_debug() was an empty macro; but at some point it
was changed to an empty inline function.

Some of the pr_debug() statements had rather expensive function calls as
part of the arguments, so this code was getting run unnecessarily even
on non debug kernels - in some fast paths, too.
Signed-off-by: NKent Overstreet <koverstreet@google.com>

The most significant change is that btree reads are now done
synchronously, instead of asynchronously and doing the post read stuff
from a workqueue.

This was originally done because we can't block on IO under
generic_make_request(). But - we already have a mechanism to punt cache
lookups to workqueue if needed, so if we just use that we don't have to
deal with the complexity of doing things asynchronously.

The main benefit is this makes the locking situation saner; we can hold
our write lock on the btree node until we're finished reading it, and we
don't need that btree_node_read_done() flag anymore.

Also, for writes, btree_write() was broken out into btree_node_write()
and btree_leaf_dirty() - the old code with the boolean argument was dumb
and confusing.

The prio_blocked mechanism was improved a bit too, now the only counter
is in struct btree_write, we don't mess with transfering a count from
struct btree anymore.

This required changing garbage collection to block prios at the start
and unblock when it finishes, which is cleaner than what it was doing
anyways (the old code had mostly the same effect, but was doing it in a
convoluted way)

And the btree iter btree_node_read_done() uses was converted to a real
mempool.
Signed-off-by: NKent Overstreet <koverstreet@google.com>

Using a workqueue when we just want a single thread is a bit silly.
Signed-off-by: NKent Overstreet <koverstreet@google.com>

Signed-off-by: NGabriel de Perthuis <g2p.code+bcache@gmail.com>
Signed-off-by: NKent Overstreet <koverstreet@google.com>

An old version of gcc was complaining about using a const int as the
size of a stack allocated array. Which should be fine - but using
ARRAY_SIZE() is better, anyways.

Also, refactor the code to use scnprintf().
Signed-off-by: NKent Overstreet <koverstreet@google.com>

bio_alloc_bioset returns NULL on failure. This fix adds a missing check
for potential NULL pointer dereferencing.
Signed-off-by: NKumar Amit Mehta <gmate.amit@gmail.com>
Signed-off-by: NKent Overstreet <koverstreet@google.com>

There are cases where the kernel will believe that the WRITE SAME
command is supported by a block device which does not, in fact,
support WRITE SAME.  This currently happens for SATA drivers behind a
SAS controller, but there are probably a hundred other ways that can
happen, including drive firmware bugs.

After receiving an error for WRITE SAME the block layer will retry the
request as a plain write of zeroes, but mdraid will consider the
failure as fatal and consider the drive failed.  This has the effect
that all the mirrors containing a specific set of data are each
offlined in very rapid succession resulting in data loss.

However, just bouncing the request back up to the block layer isn't
ideal either, because the whole initial request-retry sequence should
be inside the write bitmap fence, which probably means that md needs
to do its own conversion of WRITE SAME to write zero.

Until the failure scenario has been sorted out, disable WRITE SAME for
raid1, raid5, and raid10.

[neilb: added raid5]

This patch is appropriate for any -stable since 3.7 when write_same
support was added.

Cc: stable@vger.kernel.org
Signed-off-by: NH. Peter Anvin <hpa@linux.intel.com>
Signed-off-by: NNeilBrown <neilb@suse.de>

Various places in raid1 and raid10 are calling raise_barrier when they
really should call freeze_array.
The former is only intended to be called from "make_request".
The later has extra checks for 'nr_queued' and makes a call to
flush_pending_writes(), so it is safe to call it from within the
management thread.

Using raise_barrier will sometimes deadlock.  Using freeze_array
should not.

As 'freeze_array' currently expects one request to be pending (in
handle_read_error - the only previous caller), we need to pass
it the number of pending requests (extra) to ignore.

The deadlock was made particularly noticeable by commits
050b6615 (raid10) and 6b740b8d (raid1) which
appeared in 3.4, so the fix is appropriate for any -stable
kernel since then.

This patch probably won't apply directly to some early kernels and
will need to be applied by hand.

Cc: stable@vger.kernel.org
Reported-by: NAlexander Lyakas <alex.bolshoy@gmail.com>
Signed-off-by: NNeilBrown <neilb@suse.de>

md/raid1: consider WRITE as successful only if at least one non-Faulty and non-rebuilding drive completed it.

Without that fix, the following scenario could happen:

- RAID1 with drives A and B; drive B was freshly-added and is rebuilding
- Drive A fails
- WRITE request arrives to the array. It is failed by drive A, so
r1_bio is marked as R1BIO_WriteError, but the rebuilding drive B
succeeds in writing it, so the same r1_bio is marked as
R1BIO_Uptodate.
- r1_bio arrives to handle_write_finished, badblocks are disabled,
md_error()->error() does nothing because we don't fail the last drive
of raid1
- raid_end_bio_io()  calls call_bio_endio()
- As a result, in call_bio_endio():
        if (!test_bit(R1BIO_Uptodate, &r1_bio->state))
                clear_bit(BIO_UPTODATE, &bio->bi_flags);
this code doesn't clear the BIO_UPTODATE flag, and the whole master
WRITE succeeds, back to the upper layer.

So we returned success to the upper layer, even though we had written
the data onto the rebuilding drive only. But when we want to read the
data back, we would not read from the rebuilding drive, so this data
is lost.

[neilb - applied identical change to raid10 as well]

This bug can result in lost data, so it is suitable for any
-stable kernel.

Cc: stable@vger.kernel.org
Signed-off-by: NAlex Lyakas <alex@zadarastorage.com>
Signed-off-by: NNeilBrown <neilb@suse.de>

__md_stop_writes() will currently sometimes freeze recovery.
So any caller must be ready for that to happen, and indeed they are.

However if __md_stop_writes() doesn't freeze_recovery, then
a recovery could start before mddev_suspend() is called, which
could be awkward.  This can particularly cause problems or dm-raid.

So change __md_stop_writes() to always freeze recovery.  This is safe
and more predicatable.
Reported-by: NBrassow Jonathan <jbrassow@redhat.com>
Tested-by: NBrassow Jonathan <jbrassow@redhat.com>
Signed-off-by: NNeilBrown <neilb@suse.de>

The patch that converted raid5 to use bio_reset() forgot to initialize
bi_vcnt.
Signed-off-by: NKent Overstreet <koverstreet@google.com>
Cc: NeilBrown <neilb@suse.de>
Cc: linux-raid@vger.kernel.org
Tested-by: NIlia Mirkin <imirkin@alum.mit.edu>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Fix detection of the need to resize the dm thin metadata device.

The code incorrectly tried to extend the metadata device when it
didn't need to due to a merging error with patch 24347e95 ("dm thin:
detect metadata device resizing").

  device-mapper: transaction manager: couldn't open metadata space map
  device-mapper: thin metadata: tm_open_with_sm failed
  device-mapper: thin: aborting transaction failed
  device-mapper: thin: switching pool to failure mode
Signed-off-by: NAlasdair G Kergon <agk@redhat.com>

This code appears to have rotted... fix various bugs and do some
refactoring.
Signed-off-by: NKent Overstreet <koverstreet@google.com>

The Kconfig entry for BCACHE selects CLOSURES. But there's no Kconfig
symbol CLOSURES. That symbol was used in development versions of bcache,
but was removed when the closures code was no longer provided as a
kernel library. It can safely be dropped.
Signed-off-by: NPaul Bolle <pebolle@tiscali.nl>

The function pointer release in struct block_device_operations
should point to functions declared as void.

Sparse warnings:

drivers/md/bcache/super.c:656:27: warning:
	incorrect type in initializer (different base types)
	drivers/md/bcache/super.c:656:27:
	expected void ( *release )( ... )
	drivers/md/bcache/super.c:656:27:
	got int ( static [toplevel] *<noident> )( ... )

drivers/md/bcache/super.c:656:2: warning:
	initialization from incompatible pointer type [enabled by default]

drivers/md/bcache/super.c:656:2: warning:
	(near initialization for ‘bcache_ops.release’) [enabled by default]
Signed-off-by: NEmil Goode <emilgoode@gmail.com>
Signed-off-by: NKent Overstreet <koverstreet@google.com>

Share configuration option processing code between the dm cache
ctr and message functions.
Signed-off-by: NJoe Thornber <ejt@redhat.com>
Signed-off-by: NAlasdair G Kergon <agk@redhat.com>

Move process_config_option() in dm-cache-target.c to make the
next patch more readable.
Signed-off-by: NAlasdair G Kergon <agk@redhat.com>

Generate a dm event when the amount of remaining thin pool metadata
space falls below a certain level.

The threshold is taken to be a quarter of the size of the metadata
device with a minimum threshold of 4MB.
Signed-off-by: NJoe Thornber <ejt@redhat.com>
Signed-off-by: NAlasdair G Kergon <agk@redhat.com>

Add a threshold callback to dm persistent data space maps.
Signed-off-by: NJoe Thornber <ejt@redhat.com>
Signed-off-by: NAlasdair G Kergon <agk@redhat.com>

Add a threshold callback function to the persistent data space map
interface for a subsequent patch to use.

dm-thin and dm-cache are interested in knowing when they're getting
low on metadata or data blocks.  This patch introduces a new method
for registering a callback against a threshold.
Signed-off-by: NJoe Thornber <ejt@redhat.com>
Signed-off-by: NAlasdair G Kergon <agk@redhat.com>

Allow the dm thin pool metadata device to be extended.

Whenever a pool is resumed, detect whether the size of the metadata
device has increased, and if so, extend the metadata to use the new
space.
Signed-off-by: NJoe Thornber <ejt@redhat.com>
Signed-off-by: NAlasdair G Kergon <agk@redhat.com>

Support extending a dm persistent data metadata space map.

The extend itself is implemented by switching back to the boostrap
allocator and pointing to the new space.  The extra bitmap indexes are
then allocated from the new space, and finally we switch back to the
proper space map ops and tweak the reference counts.
Signed-off-by: NJoe Thornber <ejt@redhat.com>
Signed-off-by: NAlasdair G Kergon <agk@redhat.com>