Add a new API to dm-io.c that uses a private mempool and bio_set for each
client.

The new functions to use are dm_io_client_create(), dm_io_client_destroy(),
dm_io_client_resize() and dm_io().
Signed-off-by: NHeinz Mauelshagen <hjm@redhat.com>
Signed-off-by: NAlasdair G Kergon <agk@redhat.com>
Cc: Milan Broz <mbroz@redhat.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Introduce struct dm_io_client to prepare for per-client mempools and bio_sets.

Temporary functions bios() and io_pool() choose between the per-client
structures and the global ones so the old and new interfaces can co-exist.

Make error_bits optional.
Signed-off-by: NHeinz Mauelshagen <hjm@redhat.com>
Signed-off-by: NAlasdair G Kergon <agk@redhat.com>
Cc: Milan Broz <mbroz@redhat.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Delay decrementing the 'struct io' reference count until after the bio has
been freed so that a bio destructor function may reference it.  Required by a
later patch.
Signed-off-by: NHeinz Mauelshagen <hjm@redhat.com>
Signed-off-by: NAlasdair G Kergon <agk@redhat.com>
Cc: Milan Broz <mbroz@redhat.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

This patch adds the ability to specify desired features in the mirror
constructor/mapping table.

The first feature of interest is "handle_errors".  Currently, mirroring will
ignore any I/O errors from the devices.  Subsequent patches will check for
this flag and handle the errors.  If flag/feature is not present, mirror will
do nothing - maintaining backwards compatibility.
Signed-off-by: NJonathan E Brassow <jbrassow@redhat.com>
Signed-off-by: NAlasdair G Kergon <agk@redhat.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

This patch reports the status of the log device so that userspace can detect
the error and take appropriate action.
Signed-off-by: NJonathan E Brassow <jbrassow@redhat.com>
Signed-off-by: NAlasdair G Kergon <agk@redhat.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

This patch gives the disk logging code the ability to store the fact that an
error occured on the log device.  In addition, an event is raised when an
error is encountered during I/O to the log device.
Signed-off-by: NJonathan E Brassow <jbrassow@redhat.com>
Signed-off-by: NAlasdair G Kergon <agk@redhat.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Allow check_device_area to succeed if a device has an i_size of zero.  This
addresses an issue seen on DASD devices setting up a multipath table for paths
in online and offline state.
Signed-off-by: NMike Anderson <andmike@us.ibm.com>
Signed-off-by: NAlasdair G Kergon <agk@redhat.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Make the mapped device structure accessible to hardware handlers so error
messages can include the device name.
Signed-off-by: NEdward Goggin <egoggin@emc.com>
Signed-off-by: NAlasdair G Kergon <agk@redhat.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Add a new IV generation method 'null' to read old filesystem images created
with SuSE's loop_fish2 module.
Signed-off-by: NLudwig Nussel <ludwig.nussel@suse.de>
Acked-By: NChristophe Saout <christophe@saout.de>
Signed-off-by: NAlasdair G Kergon <agk@redhat.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Allocate smaller clones

With the previous dm-crypt fixes, there is no need for the clone bios to have
the same bvec size as the original - we just need to make them big enough for
the remaining number of pages.  The only requirement is that we clear the
"out" index in convert_context, so that crypt_convert starts storing data at
the right position within the clone bio.
Signed-off-by: NOlaf Kirch <olaf.kirch@oracle.com>
Signed-off-by: NAlasdair G Kergon <agk@redhat.com>
Cc: Jens Axboe <jens.axboe@oracle.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Get rid of first_clone in dm-crypt

This gets rid of first_clone, which is not really needed.  Apparently, cloned
bios used to share their bvec some time way in the past - this is no longer
the case.  Contrarily, this even hurts us if we try to create a clone off
first_clone after it has completed, and crypt_endio has destroyed its bvec.
Signed-off-by: NOlaf Kirch <olaf.kirch@oracle.com>
Signed-off-by: NAlasdair G Kergon <agk@redhat.com>
Cc: Jens Axboe <jens.axboe@oracle.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Do not access the bio after generic_make_request

We should never access a bio after generic_make_request - there's no guarantee
it still exists.
Signed-off-by: NOlaf Kirch <olaf.kirch@oracle.com>
Signed-off-by: NAlasdair G Kergon <agk@redhat.com>
Cc: Jens Axboe <jens.axboe@oracle.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Call clone_init early

We need to call clone_init as early as possible - at least before call
bio_put(clone) in any error path.  Otherwise, the destructor will try to
dereference bi_private, which may still be NULL.
Signed-off-by: NOlaf Kirch <olaf.kirch@oracle.com>
Signed-off-by: NAlasdair G Kergon <agk@redhat.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Disable barriers in dm-crypt because of current workqueue processing can
reorder requests.

This must be addresed later but for now disabling barriers is needed to
prevent data corruption.
Signed-off-by: NMilan Broz <mbroz@redhat.com>
Signed-off-by: NAlasdair G Kergon <agk@redhat.com>
Cc: Jens Axboe <jens.axboe@oracle.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

This patch replaces the single instance of kmirrord by one instance per mirror
set.  This change is required to avoid a deadlock in kmirrord when the
persistent dirty log of a mirror itself resides on a mirror.  The single
instance of kmirrord then issues a sync write to the dirty log in write_bits
which gets deferred to kmirrord itself later in the call chain.  But kmirrord
never does the deferred work because it is still waiting for the sync
write_bits.

_mirror_sets is removed as it no longer needed, and we always flush the
workqueue before destroying it to ensure all work is complete before
destroying it.
Signed-off-by: NHolger Smolinski <smolinski@de.ibm.com>
Signed-off-by: NAlasdair G Kergon <agk@redhat.com>
Cc: Oleg Nesterov <oleg@tv-sign.ru>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Remove do_sync_file_range() and convert callers to just use
do_sync_mapping_range().
Signed-off-by: NMark Fasheh <mark.fasheh@oracle.com>
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Remove the destroy_dirty_buffers argument from invalidate_bdev(), it hasn't
been used in 6 years (so akpm says).

find * -name \*.[ch] | xargs grep -l invalidate_bdev |
while read file; do
	quilt add $file;
	sed -ie 's/invalidate_bdev(\([^,]*\),[^)]*)/invalidate_bdev(\1)/g' $file;
done
Signed-off-by: NPeter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Currently we scale the mempool sizes depending on memory installed
in the machine, except for the bio pool itself which sits at a fixed
256 entry pre-allocation.

There's really no point in "optimizing" this OOM path, we just need
enough preallocated to make progress. A single unit is enough, lets
scale it down to 2 just to be on the safe side.

This patch saves ~150kb of pinned kernel memory on a 32-bit box.
Signed-off-by: NJens Axboe <jens.axboe@oracle.com>

If 'num_pages' were ever 1 more than a multiple of 8 (32bit platforms)
or of 16 (64 bit platforms).  filemap_attr would be allocated one
'unsigned long' shorter than required.  We need a round-up in there.
Signed-off-by: NNeil Brown <neilb@suse.de>
Cc: <stable@kernel.org>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

A device can be removed from an md array via e.g.
  echo remove > /sys/block/md3/md/dev-sde/state

This will try to remove the 'dev-sde' subtree which will deadlock
since
  commit e7b0d26a

With this patch we run the kobject_del via schedule_work so as to
avoid the deadlock.

Cc: Alan Stern <stern@rowland.harvard.edu>
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>

...  still not sure why we need this ....
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>

If this mddev and queue got reused for another array that doesn't register a
congested_fn, this function would get called incorretly.
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 that is missing the the function pointers in raid4_pers.
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 iterating through an array, one must be careful to test one's index
variable rather than another similarly-named variable.

The loop will read off the end of conf->disks[] in the following
(pathological) case:

  % dd bs=1 seek=840716287 if=/dev/zero of=d1 count=1
  % for i in 2 3 4; do dd if=/dev/zero of=d$i bs=1k count=$(($i+150)); done
  % ./vmlinux ubd0=root ubd1=d1 ubd2=d2 ubd3=d3 ubd4=d4
  # mdadm -C /dev/md0 --level=linear --raid-devices=4 /dev/ubd[1234]

adding some printks, I saw this:

  [42949374.960000] hash_spacing = 821120
  [42949374.960000] cnt          = 4
  [42949374.960000] min_spacing  = 801
  [42949374.960000] j=0 size=820928 sz=820928
  [42949374.960000] i=0 sz=820928 hash_spacing=820928
  [42949374.960000] j=1 size=64 sz=64
  [42949374.960000] j=2 size=64 sz=128
  [42949374.960000] j=3 size=64 sz=192
  [42949374.960000] j=4 size=1515870810 sz=1515871002

Cc: Gautham R Shenoy <ego@in.ibm.com>
Acked-by: NNeil Brown <neilb@cse.unsw.edu.au>
Cc: <stable@kernel.org>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Recent patch for raid6 reshape had a change missing that showed up in
subsequent review.

Many places in the raid5 code used "conf->raid_disks-1" to mean "number of
data disks".  With raid6 that had to be changed to "conf->raid_disk -
conf->max_degraded" or similar.  One place was missed.

This bug means that if a raid6 reshape were aborted in the middle the
recorded position would be wrong.  On restart it would either fail (as the
position wasn't on an appropriate boundary) or would leave a section of the
array unreshaped, causing data corruption.
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.e. one or more drives can be added and the array will re-stripe
while on-line.

Most of the interesting work was already done for raid5.  This just extends it
to raid6.

mdadm newer than 2.6 is needed for complete safety, however any version of
mdadm which support raid5 reshape will do a good enough job in almost all
cases (an 'echo repair > /sys/block/mdX/md/sync_action' is recommended after a
reshape that was aborted and had to be restarted with an such a version of
mdadm).
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>

An error always aborts any resync/recovery/reshape on the understanding that
it will immediately be restarted if that still makes sense.  However a reshape
currently doesn't get restarted.  With this patch it does.

To avoid restarting when it is not possible to do work, we call into the
personality to check that a reshape is ok, and strengthen raid5_check_reshape
to fail if there are too many failed devices.

We also break some code out into a separate function: remove_and_add_spares as
the indent level for that code was getting crazy.
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>

The mddev and queue might be used for another array which does not set these,
so they need to be cleared.
Signed-off-by: NNeilBrown <neilb@suse.de>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

md tries to warn the user if they e.g.  create a raid1 using two partitions of
the same device, as this does not provide true redundancy.

However it also warns if a raid0 is created like this, and there is nothing
wrong with that.

At the place where the warning is currently printer, we don't necessarily know
what level the array will be, so move the warning from the point where the
device is added to the point where the array is started.
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>

- Use kernel_fpu_begin() and kernel_fpu_end()
- Use boot_cpu_has() for feature testing even in userspace
Signed-off-by: NH. Peter Anvin <hpa@zytor.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>

There are two errors that can lead to recovery problems with raid10
when used in 'far' more (not the default).

Due to a '>' instead of '>=' the wrong block is located which would result in
garbage being written to some random location, quite possible outside the
range of the device, causing the newly reconstructed device to fail.

The device size calculation had some rounding errors (it didn't round when it
should) and so recovery would go a few blocks too far which would again cause
a write to a random block address and probably a device error.

The code for working with device sizes was fairly confused and spread out, so
this has been tided up a bit.
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>

The semantic effect of insert_at_head is that it would allow new registered
sysctl entries to override existing sysctl entries of the same name.  Which is
pain for caching and the proc interface never implemented.

I have done an audit and discovered that none of the current users of
register_sysctl care as (excpet for directories) they do not register
duplicate sysctl entries.

So this patch simply removes the support for overriding existing entries in
the sys_sysctl interface since no one uses it or cares and it makes future
enhancments harder.
Signed-off-by: NEric W. Biederman <ebiederm@xmission.com>
Acked-by: NRalf Baechle <ralf@linux-mips.org>
Acked-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Russell King <rmk@arm.linux.org.uk>
Cc: David Howells <dhowells@redhat.com>
Cc: "Luck, Tony" <tony.luck@intel.com>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Andi Kleen <ak@muc.de>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Corey Minyard <minyard@acm.org>
Cc: Neil Brown <neilb@suse.de>
Cc: "John W. Linville" <linville@tuxdriver.com>
Cc: James Bottomley <James.Bottomley@steeleye.com>
Cc: Jan Kara <jack@ucw.cz>
Cc: Trond Myklebust <trond.myklebust@fys.uio.no>
Cc: Mark Fasheh <mark.fasheh@oracle.com>
Cc: David Chinner <dgc@sgi.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Patrick McHardy <kaber@trash.net>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

The sysctls used by the md driver are have unique binary numbers so remove the
insert_at_head flag as it serves no useful purpose.
Signed-off-by: NEric W. Biederman <ebiederm@xmission.com>
Cc: Neil Brown <neilb@cse.unsw.edu.au>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Many struct file_operations in the kernel can be "const".  Marking them const
moves these to the .rodata section, which avoids false sharing with potential
dirty data.  In addition it'll catch accidental writes at compile time to
these shared resources.

[akpm@sdl.org: dvb fix]
Signed-off-by: NArjan van de Ven <arjan@linux.intel.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Convert all calls to invalidate_inode_pages() into open-coded calls to
invalidate_mapping_pages().

Leave the invalidate_inode_pages() wrapper in place for now, marked as
deprecated.
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

md/bitmap tracks how many active write requests are pending on blocks
associated with each bit in the bitmap, so that it knows when it can clear
the bit (when count hits zero).

The counter has 14 bits of space, so if there are ever more than 16383, we
cannot cope.

Currently the code just calles BUG_ON as "all" drivers have request queue
limits much smaller than this.

However is seems that some don't.  Apparently some multipath configurations
can allow more than 16383 concurrent write requests.

So, in this unlikely situation, instead of calling BUG_ON we now wait
for the count to drop down a bit.  This requires a new wait_queue_head,
some waiting code, and a wakeup call.

Tested by limiting the counter to 20 instead of 16383 (writes go a lot slower
in that case...).
Signed-off-by: NNeil Brown <neilb@suse.de>
Cc: <stable@kernel.org>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

It is possible for raid5 to be sent a bio that is too big for an underlying
device.  So if it is a READ that we pass stright down to a device, it will
fail and confuse RAID5.

So in 'chunk_aligned_read' we check that the bio fits within the parameters
for the target device and if it doesn't fit, fall back on reading through
the stripe cache and making lots of one-page requests.

Note that this is the earliest time we can check against the device because
earlier we don't have a lock on the device, so it could change underneath
us.

Also, the code for handling a retry through the cache when a read fails has
not been tested and was badly broken.  This patch fixes that code.
Signed-off-by: NNeil Brown <neilb@suse.de>
Cc: "Kai" <epimetreus@fastmail.fm>
Cc: <stable@suse.de>
Cc: <org@suse.de>
Cc: Jens Axboe <jens.axboe@oracle.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

raid5_mergeable_bvec tries to ensure that raid5 never sees a read request
that does not fit within just one chunk.  However as we must always accept
a single-page read, that is not always possible.

So when "in_chunk_boundary" fails, it might be unusual, but it is not a
problem and printing a message every time is a bad idea.
Signed-off-by: NNeil Brown <neilb@suse.de>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

If a GFP_KERNEL allocation is attempted in md while the mddev_lock is held,
it is possible for a deadlock to eventuate.

This happens if the array was marked 'clean', and the memalloc triggers a
write-out to the md device.

For the writeout to succeed, the array must be marked 'dirty', and that
requires getting the mddev_lock.

So, before attempting a GFP_KERNEL allocation while holding the lock, make
sure the array is marked 'dirty' (unless it is currently read-only).
Signed-off-by: NNeil Brown <neilb@suse.de>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Allow noflush suspend/resume of device-mapper device only for the case
where the device size is unchanged.

Otherwise, dm-multipath devices can stall when resumed if noflush was used
when suspending them, all paths have failed and queue_if_no_path is set.

Explanation:
 1. Something is doing fsync() on the block dev,
    holding inode->i_sem
 2. The fsync write is blocked by all-paths-down and queue_if_no_path
 3. Someone requests to suspend the dm device with noflush.
    Pending writes are left in queue.
 4. In the middle of dm_resume(), __bind() tries to get
    inode->i_sem to do __set_size() and waits forever.

'noflush suspend' is a new device-mapper feature introduced in
early 2.6.20. So I hope the fix being included before 2.6.20 is
released.

Example of reproducer:
 1. Create a multipath device by dmsetup
 2. Fail all paths during mkfs
 3. Do dmsetup suspend --noflush and load new map with healthy paths
 4. Do dmsetup resume
Signed-off-by: NJun'ichi Nomura <j-nomura@ce.jp.nec.com>
Acked-by: NAlasdair G Kergon <agk@redhat.com>
Signed-off-by: NAndrew Morton <akpm@osdl.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>