The io context sharing introduced a per-ioc spinlock, that would protect
the cfq io context lookup. That is a regression from the original, since
we never needed any locking there because the ioc/cic were process private.

The cic lookup is changed from an rbtree construct to a radix tree, which
we can then use RCU to make the reader side lockless. That is the performance
critical path, modifying the radix tree is only done on process creation
(when that process first does IO, actually) and on process exit (if that
process has done IO).

As it so happens, radix trees are also much faster for this type of
lookup where the key is a pointer. It's a very sparse tree.
Signed-off-by: NJens Axboe <jens.axboe@oracle.com>

changes in the cfq for io_context sharing
Signed-off-by: NJens Axboe <jens.axboe@oracle.com>

Detach task state from ioc, instead keep track of how many processes
are accessing the ioc.
Signed-off-by: NJens Axboe <jens.axboe@oracle.com>

This is where it belongs and then it doesn't take up space for a
process that doesn't do IO.
Signed-off-by: NJens Axboe <jens.axboe@oracle.com>

Now that the old kobject_init() function is gone, rename
kobject_init_ng() to kobject_init() to clean up the namespace.

Cc: Kay Sievers <kay.sievers@vrfy.org>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

Now that the old kobject_add() function is gone, rename kobject_add_ng()
to kobject_add() to clean up the namespace.

Cc: Kay Sievers <kay.sievers@vrfy.org>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

This converts the code to use the new kobject functions, cleaning up the
logic in doing so.

Cc: Jens Axboe <axboe@kernel.dk>
Cc: Kay Sievers <kay.sievers@vrfy.org>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

This converts the code to use the new kobject functions, cleaning up the
logic in doing so.

Cc: Jens Axboe <axboe@kernel.dk>
Cc: Kay Sievers <kay.sievers@vrfy.org>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

This moves the block devices to /sys/class/block. It will create a
flat list of all block devices, with the disks and partitions in one
directory. For compatibility /sys/block is created and contains symlinks
to the disks.

  /sys/class/block
  |-- sda -> ../../devices/pci0000:00/0000:00:1f.2/host0/target0:0:0/0:0:0:0/block/sda
  |-- sda1 -> ../../devices/pci0000:00/0000:00:1f.2/host0/target0:0:0/0:0:0:0/block/sda/sda1
  |-- sda10 -> ../../devices/pci0000:00/0000:00:1f.2/host0/target0:0:0/0:0:0:0/block/sda/sda10
  |-- sda5 -> ../../devices/pci0000:00/0000:00:1f.2/host0/target0:0:0/0:0:0:0/block/sda/sda5
  |-- sda6 -> ../../devices/pci0000:00/0000:00:1f.2/host0/target0:0:0/0:0:0:0/block/sda/sda6
  |-- sda7 -> ../../devices/pci0000:00/0000:00:1f.2/host0/target0:0:0/0:0:0:0/block/sda/sda7
  |-- sda8 -> ../../devices/pci0000:00/0000:00:1f.2/host0/target0:0:0/0:0:0:0/block/sda/sda8
  |-- sda9 -> ../../devices/pci0000:00/0000:00:1f.2/host0/target0:0:0/0:0:0:0/block/sda/sda9
  `-- sr0 -> ../../devices/pci0000:00/0000:00:1f.2/host1/target1:0:0/1:0:0:0/block/sr0

  /sys/block/
  |-- sda -> ../devices/pci0000:00/0000:00:1f.2/host0/target0:0:0/0:0:0:0/block/sda
  `-- sr0 -> ../devices/pci0000:00/0000:00:1f.2/host1/target1:0:0/1:0:0:0/block/sr0
Signed-off-by: NKay Sievers <kay.sievers@vrfy.org>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

Dynamically create the kset instead of declaring it statically.  We also
rename block_subsys to block_kset to catch all users of this symbol
with a build error instead of an easy-to-ignore build warning.

Cc: Kay Sievers <kay.sievers@vrfy.org>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

We don't need a "default" ktype for a kset.  We should set this
explicitly every time for each kset.  This change is needed so that we
can make ksets dynamic, and cleans up one of the odd, undocumented
assumption that the kset/kobject/ktype model has.

This patch is based on a lot of help from Kay Sievers.

Nasty bug in the block code was found by Dave Young
<hidave.darkstar@gmail.com>

Cc: Kay Sievers <kay.sievers@vrfy.org>
Cc: Dave Young <hidave.darkstar@gmail.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@suse.de>

The purpose of this is to allow stacked alignment settings, with the
ultimate queue alignment being set to the largest alignment requirement
in the stack.

The reason for this is so that the SCSI mid-layer can relax the default
alignment requirements (which are basically causing a lot of superfluous
copying to go on in the SG_IO interface) while allowing transports,
devices or HBAs to add stricter limits if they need them.
Acked-by: NJens Axboe <jens.axboe@oracle.com>
Signed-off-by: NJames Bottomley <James.Bottomley@HansenPartnership.com>

Currently in BSG, errors returned in req->errors aren't passed back to
the calling programme (either via SG_IO or via read/write).  Fix this,
while preserving the SCSI convention of returning status in
req->errors.

Now update libsas to return errors correctly instead of to ignore
them.
Acked-by: NFUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
Signed-off-by: NJames Bottomley <James.Bottomley@HansenPartnership.com>

It just inits the mutex, we can do that with DEFINE_MUTEX() instead.
Signed-off-by: NJens Axboe <jens.axboe@oracle.com>

David Dillow reported broken blktrace timestamps. The reason
is cpu_clock() which is not a global time source.

Fix bkltrace timestamps by using ktime_get() like the networking
code does for packet timestamps. This also removes a whole lot
of complexity from bkltrace.c and shrinks the code by 500 bytes:

   text    data     bss     dec     hex filename
   2888     124      44    3056     bf0 blktrace.o.before
   2390     116      44    2550     9f6 blktrace.o.after
Signed-off-by: NIngo Molnar <mingo@elte.hu>
Signed-off-by: NJens Axboe <jens.axboe@oracle.com>

elv_register() always returns 0, and there isn't anything it does where
it should return an error (the only error condition is so grave that
it's handled with a BUG_ON).
Signed-off-by: NAdrian Bunk <bunk@kernel.org>
Signed-off-by: NJens Axboe <jens.axboe@oracle.com>

New write batches currently start from where the last one completed.
We have no idea where the head is after switching batches, so this
makes little sense.  Instead, start the next batch from the request
with the earliest deadline in the hope that we avoid a deadline
expiry later on.
Signed-off-by: NAaron Carroll <aaronc@gelato.unsw.edu.au>
Acked-by: NNick Piggin <npiggin@suse.de>
Signed-off-by: NJens Axboe <jens.axboe@oracle.com>

Two comments refer to deadlines applying to reads only.  This is
not the case.
Signed-off-by: NAaron Carroll <aaronc@gelato.unsw.edu.au>
Acked-by: NNick Piggin <npiggin@suse.de>
Signed-off-by: NJens Axboe <jens.axboe@oracle.com>

Use msecs_to_jiffies() and jiffies_to_msecs() in scsi_ioctl().
Sometimes callers use very large values for e.g. vendor specific media
clear command and calculation can overflow.
Signed-off-by: NTejun Heo <htejun@gmail.com>
Signed-off-by: NJens Axboe <jens.axboe@oracle.com>

This was a temporary debugging thing for sg chaining testing, revert
it now as it has served its purpose.

This reverts commit 563063a8.
Signed-off-by: NJens Axboe <jens.axboe@oracle.com>

Fix a memory leak in alloc_disk_node(). Don't forget to free 'dkstats' when the allocation of 'part' failed.
Signed-off-by: NJerome Marchand <jmarchan@redhat.com>
Signed-off-by: NJens Axboe <jens.axboe@oracle.com>

if blktrace program segfault it will not be able
to call BLKTRACETEARDOWN. Now if we run the blktrace
again that would result in a failure to create the
block/<device> debugfs directory.This will result
in blk_remove_root() to be called which will set
blk_tree_root to NULL. But the  debugfs block dir
still exist because it contain subdirectory.

Now if we try to fix it using BLKTRACETEARDOWN
it won't work because blk_tree_root is NULL.

Fix the same.

Tested as below

root@qemu-image:/home/kvaneesh/blktrace# ./blktrace  -d /dev/hdc
Segmentation fault
root@qemu-image:/home/kvaneesh/blktrace# ./blktrace  -d /dev/hdc
BLKTRACESETUP: No such file or directory
Failed to start trace on /dev/hdc
root@qemu-image:/home/kvaneesh/blktrace# ./blktrace  -k /dev/hdc
root@qemu-image:/home/kvaneesh/blktrace# ./blktrace  -d /dev/hdc
Signed-off-by: NAneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: NJens Axboe <jens.axboe@oracle.com>

Added blk_unplug interface, allowing all invocations of unplugs to result
in a generated blktrace UNPLUG.
Signed-off-by: NAlan D. Brunelle <Alan.Brunelle@hp.com>
Signed-off-by: NJens Axboe <jens.axboe@oracle.com>

Credit goes to juergen.kadidlo@exasol.com for diagnosing this issue
and supplying the initial patch.

blk_queue_invalidate_tags() must use the proper requeueing paths instead
of open coding the re-add of the request, otherwise we bug out in rq
accounting. Just switch to using blk_requeue_request(), that takes care
of end-tag handling as well and also adds the blktrace REQUEUE notify
event that is also appropriate here.
Signed-off-by: NJens Axboe <jens.axboe@oracle.com>

In theory, if the queue was idle long enough, cfq_idle_class_timer may have
a false (and very long) timeout because jiffies can wrap into the past wrt
->last_end_request.
Signed-off-by: NOleg Nesterov <oleg@tv-sign.ru>
Signed-off-by: NJens Axboe <jens.axboe@oracle.com>

After the fresh boot:

	ionice -c3 -p $$
	echo cfq >> /sys/block/XXX/queue/scheduler
	dd if=/dev/XXX of=/dev/null bs=512 count=1

Now dd hangs in D state and the queue is completely stalled for approximately
INITIAL_JIFFIES + CFQ_IDLE_GRACE jiffies. This is because cfq_init_queue()
forgets to initialize cfq_data->last_end_request.

(I guess this patch is not complete, overflow is still possible)
Signed-off-by: NOleg Nesterov <oleg@tv-sign.ru>
Signed-off-by: NJens Axboe <jens.axboe@oracle.com>

Spotted by Nick <gentuu@gmail.com>, hopefully can explain the second trace in
http://bugzilla.kernel.org/show_bug.cgi?id=9180.

If ->async_idle_cfqq != NULL cfq_put_async_queues() puts it IOPRIO_BE_NR times
in a loop. Fix this.
Signed-off-by: NOleg Nesterov <oleg@tv-sign.ru>
Signed-off-by: NJens Axboe <jens.axboe@oracle.com>

Signed-off-by: NJens Axboe <jens.axboe@oracle.com>

After switching data directions, deadline always starts the next batch
from the lowest-sector request.  This gives excessive deadline expiries
and large latency and throughput disparity between high- and low-sector
requests; an order of magnitude in some tests.

This patch changes the batching behaviour so new batches start from the
request whose expiry is earliest.
Signed-off-by: NAaron Carroll <aaronc@gelato.unsw.edu.au>
Signed-off-by: NJens Axboe <jens.axboe@oracle.com>

The deadline I/O scheduler does not reset the batch count when starting
a new batch at a higher-sectored request.  This means the second and
subsequent batch in the same data direction will never exceed a single
request in size whenever higher-sectored requests are pending.

This patch gives new batches in the same data direction as old ones
their full quota of requests by resetting the batch count.
Signed-off-by: NAaron Carroll <aaronc@gelato.unsw.edu.au>
Signed-off-by: NJens Axboe <jens.axboe@oracle.com>

Factor finding the next request in sector-sorted order into
a function deadline_latter_request.
Signed-off-by: NAaron Carroll <aaronc@gelato.unsw.edu.au>
Signed-off-by: NJens Axboe <jens.axboe@oracle.com>

sg_mark_end() overwrites the page_link information, but all users want
__sg_mark_end() behaviour where we just set the end bit. That is the most
natural way to use the sg list, since you'll fill it in and then mark the
end point.

So change sg_mark_end() to only set the termination bit. Add a sg_magic
debug check as well, and clear a chain pointer if it is set.
Signed-off-by: NJens Axboe <jens.axboe@oracle.com>

The conversion of handlers to compat_blkdev_ioctl accidentally
disabled handling of most ioctl numbers on block devices because
of a typo. Fix the one line to enable it all again.
Signed-off-by: NArnd Bergmann <arnd@arndb.de>
Signed-off-by: NJens Axboe <axboe@carl.home.kernel.dk>

For the locking to work, only the tag map and tag bit map may be shared
(incidentally, I was just explaining this to Nick yesterday, but I
apparently didn't review the code well enough myself). But we also share
the busy list!  The busy_list must be queue private, or we need a
block_queue_tag covering lock as well.

So we have to move the busy_list to the queue. This'll work fine, and
it'll actually also fix a problem with blk_queue_invalidate_tags() which
will invalidate tags across all shared queues. This is a bit confusing,
the low level driver should call it for each queue seperately since
otherwise you cannot kill tags on just a single queue for eg a hard
drive that stops responding. Since the function has no callers
currently, it's not an issue.
Signed-off-by: NJens Axboe <jens.axboe@oracle.com>

The block queue tag map can use lock bitops.
Signed-off-by: NNick Piggin <npiggin@suse.de>
Signed-off-by: NJens Axboe <jens.axboe@oracle.com>

cfq_get_queue()->cfq_find_alloc_queue() can fail, check the returned value.
Signed-off-by: NOleg Nesterov <oleg@tv-sign.ru>

Note that this isn't a bug at the moment, since the regular IO path
does not call this path without __GFP_WAIT set. However, it could be a
future bug, so I've applied it.
Signed-off-by: NJens Axboe <jens.axboe@oracle.com>

blk_sync_queue() cancels the timer, but forgets to cancel the work.
Signed-off-by: NOleg Nesterov <oleg@tv-sign.ru>
Signed-off-by: NJens Axboe <jens.axboe@oracle.com>

Spotted by Nick <gentuu@gmail.com>, perhaps explains the first trace in
http://bugzilla.kernel.org/show_bug.cgi?id=9180.

cfq_exit_queue() should cancel cfqd->unplug_work before freeing cfqd.
blk_sync_queue() seems unneeded, removed.

Q: why cfq_exit_queue() calls cfq_shutdown_timer_wq() twice?
Signed-off-by: NOleg Nesterov <oleg@tv-sign.ru>
Signed-off-by: NJens Axboe <jens.axboe@oracle.com>

The nr_sector argument of drive_stat_acct() is not used anymore since the read and write sectors statistics are now updated in end_that_request_first(). This patch removes the useless argument.
Signed-off-by: NJerome Marchand <jmarchan@redhat.com>
Signed-off-by: NJens Axboe <jens.axboe@oracle.com>

Most drivers need to set length and offset as well, so may as well fold
those three lines into one.

Add sg_assign_page() for those two locations that only needed to set
the page, where the offset/length is set outside of the function context.
Signed-off-by: NJens Axboe <jens.axboe@oracle.com>