This provides a band-aid to provide stable page writes on jbd without
needing to backport the fixed locking and page writeback bit handling
schemes of jbd2.  The band-aid works by using bounce buffers to snapshot
page contents instead of waiting.

For those wondering about the ext3 bandage -- fixing the jbd locking
(which was done as part of ext4dev years ago) is a lot of surgery, and
setting PG_writeback on data pages when we actually hold the page lock
dropped ext3 performance by nearly an order of magnitude.  If we're
going to migrate iscsi and raid to use stable page writes, the
complaints about high latency will likely return.  We might as well
centralize their page snapshotting thing to one place.
Signed-off-by: NDarrick J. Wong <darrick.wong@oracle.com>
Tested-by: NAndy Lutomirski <luto@amacapital.net>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Artem Bityutskiy <dedekind1@gmail.com>
Reviewed-by: NJan Kara <jack@suse.cz>
Cc: Joel Becker <jlbec@evilplan.org>
Cc: Mark Fasheh <mfasheh@suse.com>
Cc: Steven Whitehouse <swhiteho@redhat.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Eric Van Hensbergen <ericvh@gmail.com>
Cc: Ron Minnich <rminnich@sandia.gov>
Cc: Latchesar Ionkov <lucho@ionkov.net>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

bio_{front|back}_merge tracepoints report a bio merging into an
existing request but didn't specify which request the bio is being
merged into.  Add @req to it.  This makes it impossible to share the
event template with block_bio_queue - split it out.

@req isn't used or exported to userland at this point and there is no
userland visible behavior change.  Later changes will make use of the
extra parameter.
Signed-off-by: NTejun Heo <tj@kernel.org>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

bio completion didn't kick block_bio_complete TP.  Only dm was
explicitly triggering the TP on IO completion.  This makes
block_bio_complete TP useless for tracers which want to know about
bios, and all other bio based drivers skip generating blktrace
completion events.

This patch makes all bio completions via bio_endio() generate
block_bio_complete TP.

* Explicit trace_block_bio_complete() invocation removed from dm and
  the trace point is unexported.

* @rq dropped from trace_block_bio_complete().  bios may fly around
  w/o queue associated.  Verifying and accessing the assocaited queue
  belongs to TP probes.

* blktrace now gets both request and bio completions.  Make it ignore
  bio completions if request completion path is happening.

This makes all bio based drivers generate blktrace completion events
properly and makes the block_bio_complete TP actually useful.

v2: With this change, block_bio_complete TP could be invoked on sg
    commands which have bio's with %NULL bi_bdev.  Update TP
    assignment code to check whether bio->bi_bdev is %NULL before
    dereferencing.
Signed-off-by: NTejun Heo <tj@kernel.org>
Original-patch-by: NNamhyung Kim <namhyung@gmail.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Alasdair Kergon <agk@redhat.com>
Cc: dm-devel@redhat.com
Cc: Neil Brown <neilb@suse.de>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

In commit 975927b9,it add blk_rq_pos to sort rq when flushing.
Although this commit was used for the situation which blk_plug handled
multi devices on the same time like md device.
I think there must be some situations like this but only single
device.
So remove the should_sort judgement.
Because the parameter should_sort is only for this purpose,it can delete
should_sort from blk_plug.

CC: Shaohua Li <shli@kernel.org>
Signed-off-by: NJianpeng Ma <majianpeng@gmail.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

This allows stacked devices (like md/raid5) to provide blktrace
tracing, including unplug events.
Reported-by: NFengguang Wu <fengguang.wu@intel.com>
Signed-off-by: NNeilBrown <neilb@suse.de>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Some request_fn implementations, e.g. scsi_request_fn(), unlock
the queue lock internally. This may result in multiple threads
executing request_fn for the same queue simultaneously. Keep
track of the number of active request_fn calls and make sure that
blk_cleanup_queue() waits until all active request_fn invocations
have finished. A block driver may start cleaning up resources
needed by its request_fn as soon as blk_cleanup_queue() finished,
so blk_cleanup_queue() must wait for all outstanding request_fn
invocations to finish.
Signed-off-by: NBart Van Assche <bvanassche@acm.org>
Reported-by: NChanho Min <chanho.min@lge.com>
Cc: James Bottomley <JBottomley@Parallels.com>
Cc: Mike Christie <michaelc@cs.wisc.edu>
Acked-by: NTejun Heo <tj@kernel.org>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Running a queue must continue after it has been marked dying until
it has been marked dead. So the function blk_run_queue_async() must
not schedule delayed work after blk_cleanup_queue() has marked a queue
dead. Hence add a test for that queue state in blk_run_queue_async()
and make sure that queue_unplugged() invokes that function with the
queue lock held. This avoids that the queue state can change after
it has been tested and before mod_delayed_work() is invoked. Drop
the queue dying test in queue_unplugged() since it is now
superfluous: __blk_run_queue() already tests whether or not the
queue is dead.
Signed-off-by: NBart Van Assche <bvanassche@acm.org>
Cc: Mike Christie <michaelc@cs.wisc.edu>
Acked-by: NTejun Heo <tj@kernel.org>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

A block driver may start cleaning up resources needed by its
request_fn as soon as blk_cleanup_queue() finished, so request_fn
must not be invoked after draining finished. This is important
when blk_run_queue() is invoked without any requests in progress.
As an example, if blk_drain_queue() and scsi_run_queue() run in
parallel, blk_drain_queue() may have finished all requests after
scsi_run_queue() has taken a SCSI device off the starved list but
before that last function has had a chance to run the queue.
Signed-off-by: NBart Van Assche <bvanassche@acm.org>
Cc: James Bottomley <JBottomley@Parallels.com>
Cc: Mike Christie <michaelc@cs.wisc.edu>
Cc: Chanho Min <chanho.min@lge.com>
Acked-by: NTejun Heo <tj@kernel.org>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Let the caller of blk_drain_queue() obtain the queue lock to improve
readability of the patch called "Avoid that request_fn is invoked on
a dead queue".
Signed-off-by: NBart Van Assche <bvanassche@acm.org>
Acked-by: NTejun Heo <tj@kernel.org>
Cc: James Bottomley <JBottomley@Parallels.com>
Cc: Mike Christie <michaelc@cs.wisc.edu>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Chanho Min <chanho.min@lge.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

QUEUE_FLAG_DEAD is used to indicate that queuing new requests must
stop. After this flag has been set queue draining starts. However,
during the queue draining phase it is still safe to invoke the
queue's request_fn, so QUEUE_FLAG_DYING is a better name for this
flag.

This patch has been generated by running the following command
over the kernel source tree:

git grep -lEw 'blk_queue_dead|QUEUE_FLAG_DEAD' |
    xargs sed -i.tmp -e 's/blk_queue_dead/blk_queue_dying/g'      \
        -e 's/QUEUE_FLAG_DEAD/QUEUE_FLAG_DYING/g';                \
sed -i.tmp -e "s/QUEUE_FLAG_DYING$(printf \\t)*5/QUEUE_FLAG_DYING$(printf \\t)5/g" \
    include/linux/blkdev.h;                                       \
sed -i.tmp -e 's/ DEAD/ DYING/g' -e 's/dead queue/a dying queue/' \
    -e 's/Dead queue/A dying queue/' block/blk-core.c
Signed-off-by: NBart Van Assche <bvanassche@acm.org>
Acked-by: NTejun Heo <tj@kernel.org>
Cc: James Bottomley <JBottomley@Parallels.com>
Cc: Mike Christie <michaelc@cs.wisc.edu>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Chanho Min <chanho.min@lge.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Signed-off-by: NEzequiel Garcia <elezegarcia@gmail.com>

Modified by me to cover blk_init_queue() as well.
Signed-off-by: NJens Axboe <axboe@kernel.dk>

My workload is a raid5 which had 16 disks. And used our filesystem to
write using direct-io mode.

I used the blktrace to find those message:
8,16   0     6647     2.453665504  2579  M   W 7493152 + 8 [md0_raid5]
8,16   0     6648     2.453672411  2579  Q   W 7493160 + 8 [md0_raid5]
8,16   0     6649     2.453672606  2579  M   W 7493160 + 8 [md0_raid5]
8,16   0     6650     2.453679255  2579  Q   W 7493168 + 8 [md0_raid5]
8,16   0     6651     2.453679441  2579  M   W 7493168 + 8 [md0_raid5]
8,16   0     6652     2.453685948  2579  Q   W 7493176 + 8 [md0_raid5]
8,16   0     6653     2.453686149  2579  M   W 7493176 + 8 [md0_raid5]
8,16   0     6654     2.453693074  2579  Q   W 7493184 + 8 [md0_raid5]
8,16   0     6655     2.453693254  2579  M   W 7493184 + 8 [md0_raid5]
8,16   0     6656     2.453704290  2579  Q   W 7493192 + 8 [md0_raid5]
8,16   0     6657     2.453704482  2579  M   W 7493192 + 8 [md0_raid5]
8,16   0     6658     2.453715016  2579  Q   W 7493200 + 8 [md0_raid5]
8,16   0     6659     2.453715247  2579  M   W 7493200 + 8 [md0_raid5]
8,16   0     6660     2.453721730  2579  Q   W 7493208 + 8 [md0_raid5]
8,16   0     6661     2.453721974  2579  M   W 7493208 + 8 [md0_raid5]
8,16   0     6662     2.453728202  2579  Q   W 7493216 + 8 [md0_raid5]
8,16   0     6663     2.453728436  2579  M   W 7493216 + 8 [md0_raid5]
8,16   0     6664     2.453734782  2579  Q   W 7493224 + 8 [md0_raid5]
8,16   0     6665     2.453735019  2579  M   W 7493224 + 8 [md0_raid5]
8,16   0     6666     2.453741401  2579  Q   W 7493232 + 8 [md0_raid5]
8,16   0     6667     2.453741632  2579  M   W 7493232 + 8 [md0_raid5]
8,16   0     6668     2.453748148  2579  Q   W 7493240 + 8 [md0_raid5]
8,16   0     6669     2.453748386  2579  M   W 7493240 + 8 [md0_raid5]
8,16   0     6670     2.453851843  2579  I   W 7493144 + 104 [md0_raid5]
8,16   0        0     2.453853661     0  m   N cfq2579 insert_request
8,16   0     6671     2.453854064  2579  I   W 7493120 + 24 [md0_raid5]
8,16   0        0     2.453854439     0  m   N cfq2579 insert_request
8,16   0     6672     2.453854793  2579  U   N [md0_raid5] 2
8,16   0        0     2.453855513     0  m   N cfq2579 Not idling.st->count:1
8,16   0        0     2.453855927     0  m   N cfq2579 dispatch_insert
8,16   0        0     2.453861771     0  m   N cfq2579 dispatched a request
8,16   0        0     2.453862248     0  m   N cfq2579 activate rq,drv=1
8,16   0     6673     2.453862332  2579  D   W 7493120 + 24 [md0_raid5]
8,16   0        0     2.453865957     0  m   N cfq2579 Not idling.st->count:1
8,16   0        0     2.453866269     0  m   N cfq2579 dispatch_insert
8,16   0        0     2.453866707     0  m   N cfq2579 dispatched a request
8,16   0        0     2.453867061     0  m   N cfq2579 activate rq,drv=2
8,16   0     6674     2.453867145  2579  D   W 7493144 + 104 [md0_raid5]
8,16   0     6675     2.454147608     0  C   W 7493120 + 24 [0]
8,16   0        0     2.454149357     0  m   N cfq2579 complete rqnoidle 0
8,16   0     6676     2.454791505     0  C   W 7493144 + 104 [0]
8,16   0        0     2.454794803     0  m   N cfq2579 complete rqnoidle 0
8,16   0        0     2.454795160     0  m   N cfq schedule dispatch

From above messages,we can find rq[W 7493144 + 104] and rq[W
7493120 + 24] do not merge.
Because the bio order is:
  8,16   0     6638     2.453619407  2579  Q   W 7493144 + 8 [md0_raid5]
  8,16   0     6639     2.453620460  2579  G   W 7493144 + 8 [md0_raid5]
  8,16   0     6640     2.453639311  2579  Q   W 7493120 + 8 [md0_raid5]
  8,16   0     6641     2.453639842  2579  G   W 7493120 + 8 [md0_raid5]
The bio(7493144) first and bio(7493120) later.So the subsequent
bios will be divided into two parts.
When flushing plug-list,because elv_attempt_insert_merge only support
backmerge,not supporting frontmerge.
So rq[7493120 + 24] can't merge with rq[7493144 + 104].

From my test,i found those situation can count 25% in our system.
Using this patch, there is no this situation.
Signed-off-by: NJianpeng Ma <majianpeng@gmail.com>
CC:Shaohua Li <shli@kernel.org>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

A queue newly allocated with blk_alloc_queue_node() has only
QUEUE_FLAG_BYPASS set.  For request-based drivers,
blk_init_allocated_queue() is called and q->queue_flags is overwritten
with QUEUE_FLAG_DEFAULT which doesn't include BYPASS even though the
initial bypass is still in effect.

In blk_init_allocated_queue(), or QUEUE_FLAG_DEFAULT to q->queue_flags
instead of overwriting.
Signed-off-by: NTejun Heo <tj@kernel.org>
Cc: stable@vger.kernel.org
Acked-by: NVivek Goyal <vgoyal@redhat.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

block: lift the initial queue bypass mode on blk_register_queue() instead of blk_init_allocated_queue()

b82d4b19 ("blkcg: make request_queue bypassing on allocation") made
request_queues bypassed on allocation to avoid switching on and off
bypass mode on a queue being initialized.  Some drivers allocate and
then destroy a lot of queues without fully initializing them and
incurring bypass latency overhead on each of them could add upto
significant overhead.

Unfortunately, blk_init_allocated_queue() is never used by queues of
bio-based drivers, which means that all bio-based driver queues are in
bypass mode even after initialization and registration complete
successfully.

Due to the limited way request_queues are used by bio drivers, this
problem is hidden pretty well but it shows up when blk-throttle is
used in combination with a bio-based driver.  Trying to configure
(echoing to cgroupfs file) blk-throttle for a bio-based driver hangs
indefinitely in blkg_conf_prep() waiting for bypass mode to end.

This patch moves the initial blk_queue_bypass_end() call from
blk_init_allocated_queue() to blk_register_queue() which is called for
any userland-visible queues regardless of its type.

I believe this is correct because I don't think there is any block
driver which needs or wants working elevator and blk-cgroup on a queue
which isn't visible to userland.  If there are such users, we need a
different solution.
Signed-off-by: NTejun Heo <tj@kernel.org>
Reported-by: NJoseph Glanville <joseph.glanville@orionvm.com.au>
Cc: stable@vger.kernel.org
Acked-by: NVivek Goyal <vgoyal@redhat.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

The WRITE SAME command supported on some SCSI devices allows the same
block to be efficiently replicated throughout a block range. Only a
single logical block is transferred from the host and the storage device
writes the same data to all blocks described by the I/O.

This patch implements support for WRITE SAME in the block layer. The
blkdev_issue_write_same() function can be used by filesystems and block
drivers to replicate a buffer across a block range. This can be used to
efficiently initialize software RAID devices, etc.
Signed-off-by: NMartin K. Petersen <martin.petersen@oracle.com>
Acked-by: NMike Snitzer <snitzer@redhat.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

 - blk_check_merge_flags() verifies that cmd_flags / bi_rw are
   compatible. This function is called for both req-req and req-bio
   merging.

 - blk_rq_get_max_sectors() and blk_queue_get_max_sectors() can be used
   to query the maximum sector count for a given request or queue. The
   calls will return the right value from the queue limits given the
   type of command (RW, discard, write same, etc.)
Signed-off-by: NMartin K. Petersen <martin.petersen@oracle.com>
Acked-by: NMike Snitzer <snitzer@redhat.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Remove special-casing of non-rw fs style requests (discard). The nomerge
flags are consolidated in blk_types.h, and rq_mergeable() and
bio_mergeable() have been modified to use them.

bio_is_rw() is used in place of bio_has_data() a few places. This is
done to to distinguish true reads and writes from other fs type requests
that carry a payload (e.g. write same).
Signed-off-by: NMartin K. Petersen <martin.petersen@oracle.com>
Acked-by: NMike Snitzer <snitzer@redhat.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Before call the blk_queue_congestion_threshold(),
the blk_queue_congestion_threshold() is already called at blk_queue_make_rquest().
Because this code is the duplicated, it has removed.
Signed-off-by: NJaehoon Chung <jh80.chung@samsung.com>
Signed-off-by: NKyungmin Park <kyungmin.park@samsung.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Previously, there was bio_clone() but it only allocated from the fs bio
set; as a result various users were open coding it and using
__bio_clone().

This changes bio_clone() to become bio_clone_bioset(), and then we add
bio_clone() and bio_clone_kmalloc() as wrappers around it, making use of
the functionality the last patch adedd.

This will also help in a later patch changing how bio cloning works.
Signed-off-by: NKent Overstreet <koverstreet@google.com>
CC: Jens Axboe <axboe@kernel.dk>
CC: NeilBrown <neilb@suse.de>
CC: Alasdair Kergon <agk@redhat.com>
CC: Boaz Harrosh <bharrosh@panasas.com>
CC: Jeff Garzik <jeff@garzik.org>
Acked-by: NJeff Garzik <jgarzik@redhat.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Now that we've got generic code for freeing bios allocated from bio
pools, this isn't needed anymore.

This patch also makes bio_free() static, since without bi_destructor
there should be no need for it to be called anywhere else.

bio_free() is now only called from bio_put, so we can refactor those a
bit - move some code from bio_put() to bio_free() and kill the redundant
bio->bi_next = NULL.

v5: Switch to BIO_KMALLOC_POOL ((void *)~0), per Boaz
v6: BIO_KMALLOC_POOL now NULL, drop bio_free's EXPORT_SYMBOL
v7: No #define BIO_KMALLOC_POOL anymore
Signed-off-by: NKent Overstreet <koverstreet@google.com>
CC: Jens Axboe <axboe@kernel.dk>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Now that bios keep track of where they were allocated from,
bio_integrity_alloc_bioset() becomes redundant.

Remove bio_integrity_alloc_bioset() and drop bio_set argument from the
related functions and make them use bio->bi_pool.
Signed-off-by: NKent Overstreet <koverstreet@google.com>
CC: Jens Axboe <axboe@kernel.dk>
CC: Martin K. Petersen <martin.petersen@oracle.com>
Acked-by: NTejun Heo <tj@kernel.org>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

When performing a cable pull test w/ active stress I/O using fio over
a dual port Intel 82599 FCoE CNA, w/ 256LUNs on one port and about 32LUNs
on the other, it is observed that the system becomes not usable due to
scsi-ml being busy printing the error messages for all the failing commands.
I don't believe this problem is specific to FCoE and these commands are
anyway failing due to link being down (DID_NO_CONNECT), just rate-limit
the messages here to solve this issue.

v2->v1: use __ratelimit() as Tomas Henzl mentioned as the proper way for
rate-limit per function. However, in this case, the failed i/o gets to
blk_end_request_err() and then blk_update_request(), which also has to
be rate-limited, as added in the v2 of this patch.

v3-v2: resolved conflict to apply on current 3.6-rc3 upstream tip.
Signed-off-by: NYi Zou <yi.zou@intel.com>
Cc: www.Open-FCoE.org <devel@open-fcoe.org>
Cc: Tomas Henzl <thenzl@redhat.com>
Cc: <linux-scsi@vger.kernel.org>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Now that cancel_delayed_work() can be safely called from IRQ handlers,
there's no reason to use __cancel_delayed_work().  Use
cancel_delayed_work() instead of __cancel_delayed_work() and mark the
latter deprecated.
Signed-off-by: NTejun Heo <tj@kernel.org>
Acked-by: NJens Axboe <axboe@kernel.dk>
Cc: Jiri Kosina <jkosina@suse.cz>
Cc: Roland Dreier <roland@kernel.org>
Cc: Tomi Valkeinen <tomi.valkeinen@ti.com>

Now that mod_delayed_work() is safe to call from IRQ handlers,
__cancel_delayed_work() followed by queue_delayed_work() can be
replaced with mod_delayed_work().

Most conversions are straight-forward except for the following.

* net/core/link_watch.c: linkwatch_schedule_work() was doing a quite
  elaborate dancing around its delayed_work.  Collapse it such that
  linkwatch_work is queued for immediate execution if LW_URGENT and
  existing timer is kept otherwise.
Signed-off-by: NTejun Heo <tj@kernel.org>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Tomi Valkeinen <tomi.valkeinen@ti.com> 

This will allow md/raid to know why the unplug was called,
and will be able to act according - if !from_schedule it
is safe to perform tasks which could themselves schedule.
Signed-off-by: NNeilBrown <neilb@suse.de>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

MD raid1 prepares to dispatch request in unplug callback. If make_request in
low level queue also uses unplug callback to dispatch request, the low level
queue's unplug callback will not be called. Recheck the callback list helps
this case.
Signed-off-by: NShaohua Li <shli@fusionio.com>
Signed-off-by: NNeilBrown <neilb@suse.de>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Both md and umem has similar code for getting notified on an
blk_finish_plug event.
Centralize this code in block/ and allow each driver to
provide its distinctive difference.
Signed-off-by: NNeilBrown <neilb@suse.de>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Currently, request_queue has one request_list to allocate requests
from regardless of blkcg of the IO being issued.  When the unified
request pool is used up, cfq proportional IO limits become meaningless
- whoever grabs the next request being freed wins the race regardless
of the configured weights.

This can be easily demonstrated by creating a blkio cgroup w/ very low
weight, put a program which can issue a lot of random direct IOs there
and running a sequential IO from a different cgroup.  As soon as the
request pool is used up, the sequential IO bandwidth crashes.

This patch implements per-blkg request_list.  Each blkg has its own
request_list and any IO allocates its request from the matching blkg
making blkcgs completely isolated in terms of request allocation.

* Root blkcg uses the request_list embedded in each request_queue,
  which was renamed to @q->root_rl from @q->rq.  While making blkcg rl
  handling a bit harier, this enables avoiding most overhead for root
  blkcg.

* Queue fullness is properly per request_list but bdi isn't blkcg
  aware yet, so congestion state currently just follows the root
  blkcg.  As writeback isn't aware of blkcg yet, this works okay for
  async congestion but readahead may get the wrong signals.  It's
  better than blkcg completely collapsing with shared request_list but
  needs to be improved with future changes.

* After this change, each block cgroup gets a full request pool making
  resource consumption of each cgroup higher.  This makes allowing
  non-root users to create cgroups less desirable; however, note that
  allowing non-root users to directly manage cgroups is already
  severely broken regardless of this patch - each block cgroup
  consumes kernel memory and skews IO weight (IO weights are not
  hierarchical).

v2: queue-sysfs.txt updated and patch description udpated as suggested
    by Vivek.

v3: blk_get_rl() wasn't checking error return from
    blkg_lookup_create() and may cause oops on lookup failure.  Fix it
    by falling back to root_rl on blkg lookup failures.  This problem
    was spotted by Rakesh Iyer <rni@google.com>.

v4: Updated to accomodate 458f27a9 "block: Avoid missed wakeup in
    request waitqueue".  blk_drain_queue() now wakes up waiters on all
    blkg->rl on the target queue.
Signed-off-by: NTejun Heo <tj@kernel.org>
Acked-by: NVivek Goyal <vgoyal@redhat.com>
Cc: Wu Fengguang <fengguang.wu@intel.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Request allocation is about to be made per-blkg meaning that there'll
be multiple request lists.

* Make queue full state per request_list.  blk_*queue_full() functions
  are renamed to blk_*rl_full() and takes @rl instead of @q.

* Rename blk_init_free_list() to blk_init_rl() and make it take @rl
  instead of @q.  Also add @gfp_mask parameter.

* Add blk_exit_rl() instead of destroying rl directly from
  blk_release_queue().

* Add request_list->q and make request alloc/free functions -
  blk_free_request(), [__]freed_request(), __get_request() - take @rl
  instead of @q.

This patch doesn't introduce any functional difference.
Signed-off-by: NTejun Heo <tj@kernel.org>
Acked-by: NVivek Goyal <vgoyal@redhat.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Add q->nr_rqs[] which currently behaves the same as q->rq.count[] and
move q->rq.elvpriv to q->nr_rqs_elvpriv.  blk_drain_queue() is updated
to use q->nr_rqs[] instead of q->rq.count[].

These counters separates queue-wide request statistics from the
request list and allow implementation of per-queue request allocation.

While at it, properly indent fields of struct request_list.
Signed-off-by: NTejun Heo <tj@kernel.org>
Acked-by: NVivek Goyal <vgoyal@redhat.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Block layer very lazy allocation of ioc.  It waits until the moment
ioc is absolutely necessary; unfortunately, that time could be inside
queue lock and __get_request() performs unlock - try alloc - retry
dancing.

Just allocate it up-front on entry to block layer.  We're not saving
the rain forest by deferring it to the last possible moment and
complicating things unnecessarily.

This patch is to prepare for further updates to request allocation
path.
Signed-off-by: NTejun Heo <tj@kernel.org>
Acked-by: NVivek Goyal <vgoyal@redhat.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Currently, there are two request allocation functions - get_request()
and get_request_wait().  The former tries to allocate a request once
and the latter keeps retrying until it succeeds.  The latter wraps the
former and keeps retrying until allocation succeeds.

The combination of two functions deliver fallible non-wait allocation,
fallible wait allocation and unfailing wait allocation.  However,
given that forward progress is guaranteed, fallible wait allocation
isn't all that useful and in fact nobody uses it.

This patch simplifies the interface as follows.

* get_request() is renamed to __get_request() and is only used by the
  wrapper function.

* get_request_wait() is renamed to get_request().  It now takes
  @gfp_mask and retries iff it contains %__GFP_WAIT.

This patch doesn't introduce any functional change and is to prepare
for further updates to request allocation path.
Signed-off-by: NTejun Heo <tj@kernel.org>
Acked-by: NVivek Goyal <vgoyal@redhat.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

mempool_create_node() currently assumes %GFP_KERNEL.  Its only user,
blk_init_free_list(), is about to be updated to use other allocation
flags - add @gfp_mask argument to the function.
Signed-off-by: NTejun Heo <tj@kernel.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Commit 777eb1bf disconnects externally
supplied queue_lock before blk_drain_queue(). Switching the lock would
introduce lock unbalance because theads which have taken the external
lock might unlock the internal lock in the during the queue drain. This
patch mitigate this by disconnecting the lock after the queue draining
since queue draining makes a lot of request_queue users go away.

However, please note, this patch only makes the problem less likely to
happen. Anyone who still holds a ref might try to issue a new request on
a dead queue after the blk_cleanup_queue() finishes draining, the lock
unbalance might still happen in this case.

 =====================================
 [ BUG: bad unlock balance detected! ]
 3.4.0+ #288 Not tainted
 -------------------------------------
 fio/17706 is trying to release lock (&(&q->__queue_lock)->rlock) at:
 [<ffffffff81329372>] blk_queue_bio+0x2a2/0x380
 but there are no more locks to release!

 other info that might help us debug this:
 1 lock held by fio/17706:
  #0:  (&(&vblk->lock)->rlock){......}, at: [<ffffffff81327f1a>]
 get_request_wait+0x19a/0x250

 stack backtrace:
 Pid: 17706, comm: fio Not tainted 3.4.0+ #288
 Call Trace:
  [<ffffffff81329372>] ? blk_queue_bio+0x2a2/0x380
  [<ffffffff810dea49>] print_unlock_inbalance_bug+0xf9/0x100
  [<ffffffff810dfe4f>] lock_release_non_nested+0x1df/0x330
  [<ffffffff811dae24>] ? dio_bio_end_aio+0x34/0xc0
  [<ffffffff811d6935>] ? bio_check_pages_dirty+0x85/0xe0
  [<ffffffff811daea1>] ? dio_bio_end_aio+0xb1/0xc0
  [<ffffffff81329372>] ? blk_queue_bio+0x2a2/0x380
  [<ffffffff81329372>] ? blk_queue_bio+0x2a2/0x380
  [<ffffffff810e0079>] lock_release+0xd9/0x250
  [<ffffffff81a74553>] _raw_spin_unlock_irq+0x23/0x40
  [<ffffffff81329372>] blk_queue_bio+0x2a2/0x380
  [<ffffffff81328faa>] generic_make_request+0xca/0x100
  [<ffffffff81329056>] submit_bio+0x76/0xf0
  [<ffffffff8115470c>] ? set_page_dirty_lock+0x3c/0x60
  [<ffffffff811d69e1>] ? bio_set_pages_dirty+0x51/0x70
  [<ffffffff811dd1a8>] do_blockdev_direct_IO+0xbf8/0xee0
  [<ffffffff811d8620>] ? blkdev_get_block+0x80/0x80
  [<ffffffff811dd4e5>] __blockdev_direct_IO+0x55/0x60
  [<ffffffff811d8620>] ? blkdev_get_block+0x80/0x80
  [<ffffffff811d92e7>] blkdev_direct_IO+0x57/0x60
  [<ffffffff811d8620>] ? blkdev_get_block+0x80/0x80
  [<ffffffff8114c6ae>] generic_file_aio_read+0x70e/0x760
  [<ffffffff810df7c5>] ? __lock_acquire+0x215/0x5a0
  [<ffffffff811e9924>] ? aio_run_iocb+0x54/0x1a0
  [<ffffffff8114bfa0>] ? grab_cache_page_nowait+0xc0/0xc0
  [<ffffffff811e82cc>] aio_rw_vect_retry+0x7c/0x1e0
  [<ffffffff811e8250>] ? aio_fsync+0x30/0x30
  [<ffffffff811e9936>] aio_run_iocb+0x66/0x1a0
  [<ffffffff811ea9b0>] do_io_submit+0x6f0/0xb80
  [<ffffffff8134de2e>] ? trace_hardirqs_on_thunk+0x3a/0x3f
  [<ffffffff811eae50>] sys_io_submit+0x10/0x20
  [<ffffffff81a7c9e9>] system_call_fastpath+0x16/0x1b

Changes since v2: Update commit log to explain how the code is still
                  broken even if we delay the lock switching after the drain.
Changes since v1: Update commit log as Tejun suggested.
Acked-by: NTejun Heo <tj@kernel.org>
Signed-off-by: NAsias He <asias@redhat.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

After hot-unplug a stressed disk, I found that rl->wait[] is not empty
while rl->count[] is empty and there are theads still sleeping on
get_request after the queue cleanup. With simple debug code, I found
there are exactly nr_sleep - nr_wakeup of theads in D state. So there
are missed wakeup.

  $ dmesg | grep nr_sleep
  [   52.917115] ---> nr_sleep=1046, nr_wakeup=873, delta=173
  $ vmstat 1
  1 173  0 712640  24292  96172 0 0  0  0  419  757  0  0  0 100  0

To quote Tejun:

  Ah, okay, freed_request() wakes up single waiter with the assumption
  that after the wakeup there will at least be one successful allocation
  which in turn will continue the wakeup chain until the wait list is
  empty - ie. waiter wakeup is dependent on successful request
  allocation happening after each wakeup.  With queue marked dead, any
  woken up waiter fails the allocation path, so the wakeup chaining is
  lost and we're left with hung waiters. What we need is wake_up_all()
  after drain completion.

This patch fixes the missed wakeup by waking up all the theads which
are sleeping on wait queue after queue drain.

Changes in v2: Drop waitqueue_active() optimization
Acked-by: NTejun Heo <tj@kernel.org>
Signed-off-by: NAsias He <asias@redhat.com>

Fixed a bug by me, where stacked devices would oops on calling
blk_drain_queue() since ->rq.wait[] do not get initialized unless
it's a full queue setup.
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Request allocation is mempool backed to guarantee forward progress
under memory pressure; unfortunately, this property got broken while
adding elvpriv data.  Failures during elvpriv allocation, including
ioc and icq creation failures, currently make get_request() fail as
whole.  There's no forward progress guarantee for these allocations -
they may fail indefinitely under memory pressure stalling IO and
deadlocking the system.

This patch updates get_request() such that elvpriv allocation failure
doesn't make the whole function fail.  If elvpriv allocation fails,
the allocation is degraded into !ELVPRIV.  This will force the request
to ELEVATOR_INSERT_BACK disturbing scheduling but elvpriv alloc
failures should be rare (nothing is per-request) and anything is
better than deadlocking.
Signed-off-by: NTejun Heo <tj@kernel.org>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Allocation failure handling in get_request() is about to be updated.
To ease the update, collapse blk_alloc_request() into get_request().

This patch doesn't introduce any functional change.
Signed-off-by: NTejun Heo <tj@kernel.org>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

With the previous change to guarantee bypass visiblity for RCU read
lock regions, entering bypass mode involves non-trivial overhead and
future changes are scheduled to make use of bypass mode during init
path.  Combined it may end up adding noticeable delay during boot.

This patch makes request_queue start its life in bypass mode, which is
ended on queue init completion at the end of
blk_init_allocated_queue(), and updates blk_queue_bypass_start() such
that draining and RCU synchronization are performed only when the
queue actually enters bypass mode.

This avoids unnecessarily switching in and out of bypass mode during
init avoiding the overhead and any nasty surprises which may step from
leaving bypass mode on half-initialized queues.

The boot time overhead was pointed out by Vivek.
Signed-off-by: NTejun Heo <tj@kernel.org>
Cc: Vivek Goyal <vgoyal@redhat.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Currently, blkg_lookup() doesn't check @q bypass state.  This patch
updates blk_queue_bypass_start() to do synchronize_rcu() before
returning and updates blkg_lookup() to check blk_queue_bypass() and
return %NULL if bypassing.  This ensures blkg_lookup() returns %NULL
if @q is bypassing.

This is to guarantee that nobody is accessing policy data while @q is
bypassing, which is necessary to allow replacing blkio_cgroup->pd[] in
place on policy [de]activation.

v2: Added more comments explaining bypass guarantees as suggested by
    Vivek.

v3: Added more comments explaining why there's no synchronize_rcu() in
    blk_cleanup_queue() as suggested by Vivek.
Signed-off-by: NTejun Heo <tj@kernel.org>
Cc: Vivek Goyal <vgoyal@redhat.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

We do auto block plug flush to reduce latency, the threshold is 16
requests. This works well if the task is accessing one or two drives.
The problem is if the task is accessing a raid 0 device and the raid
disk number is big, say 8 or 16, 16/8 = 2 or 16/16=1, we will have
heavy lock contention.

This patch makes the threshold per-disk based. The latency should be
still ok accessing one or two drives. The setup with application
accessing a lot of drives in the meantime uaually is big machine,
avoiding lock contention is more important, because any contention
will actually increase latency.
Signed-off-by: NShaohua Li <shli@fusionio.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>