This patch supports to run one single flush machinery for
each blk-mq dispatch queue, so that:

- current init_request and exit_request callbacks can
cover flush request too, then the buggy copying way of
initializing flush request's pdu can be fixed

- flushing performance gets improved in case of multi hw-queue

In fio sync write test over virtio-blk(4 hw queues, ioengine=sync,
iodepth=64, numjobs=4, bs=4K), it is observed that througput gets
increased a lot over my test environment:
	- throughput: +70% in case of virtio-blk over null_blk
	- throughput: +30% in case of virtio-blk over SSD image

The multi virtqueue feature isn't merged to QEMU yet, and patches for
the feature can be found in below tree:

	git://kernel.ubuntu.com/ming/qemu.git  	v2.1.0-mq.4

And simply passing 'num_queues=4 vectors=5' should be enough to
enable multi queue(quad queue) feature for QEMU virtio-blk.
Suggested-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NMing Lei <ming.lei@canonical.com>
Signed-off-by: NJens Axboe <axboe@fb.com>

blk-mq uses percpu_ref for its usage counter which tracks the number
of in-flight commands and used to synchronously drain the queue on
freeze.  percpu_ref shutdown takes measureable wallclock time as it
involves a sched RCU grace period.  This means that draining a blk-mq
takes measureable wallclock time.  One would think that this shouldn't
matter as queue shutdown should be a rare event which takes place
asynchronously w.r.t. userland.

Unfortunately, SCSI probing involves synchronously setting up and then
tearing down a lot of request_queues back-to-back for non-existent
LUNs.  This means that SCSI probing may take above ten seconds when
scsi-mq is used.

  [    0.949892] scsi host0: Virtio SCSI HBA
  [    1.007864] scsi 0:0:0:0: Direct-Access     QEMU     QEMU HARDDISK    1.1. PQ: 0 ANSI: 5
  [    1.021299] scsi 0:0:1:0: Direct-Access     QEMU     QEMU HARDDISK    1.1. PQ: 0 ANSI: 5
  [    1.520356] tsc: Refined TSC clocksource calibration: 2491.910 MHz

  <stall>

  [   16.186549] sd 0:0:0:0: Attached scsi generic sg0 type 0
  [   16.190478] sd 0:0:1:0: Attached scsi generic sg1 type 0
  [   16.194099] osd: LOADED open-osd 0.2.1
  [   16.203202] sd 0:0:0:0: [sda] 31457280 512-byte logical blocks: (16.1 GB/15.0 GiB)
  [   16.208478] sd 0:0:0:0: [sda] Write Protect is off
  [   16.211439] sd 0:0:0:0: [sda] Write cache: enabled, read cache: enabled, doesn't support DPO or FUA
  [   16.218771] sd 0:0:1:0: [sdb] 31457280 512-byte logical blocks: (16.1 GB/15.0 GiB)
  [   16.223264] sd 0:0:1:0: [sdb] Write Protect is off
  [   16.225682] sd 0:0:1:0: [sdb] Write cache: enabled, read cache: enabled, doesn't support DPO or FUA

This is also the reason why request_queues start in bypass mode which
is ended on blk_register_queue() as shutting down a fully functional
queue also involves a RCU grace period and the queues for non-existent
SCSI devices never reach registration.

blk-mq basically needs to do the same thing - start the mq in a
degraded mode which is faster to shut down and then make it fully
functional only after the queue reaches registration.  percpu_ref
recently grew facilities to force atomic operation until explicitly
switched to percpu mode, which can be used for this purpose.  This
patch makes blk-mq initialize q->mq_usage_counter in atomic mode and
switch it to percpu mode only once blk_register_queue() is reached.

Note that this issue was previously worked around by 0a30288d
("blk-mq, percpu_ref: implement a kludge for SCSI blk-mq stall during
probe") for v3.17.  The temp fix was reverted in preparation of adding
persistent atomic mode to percpu_ref by 9eca8046 ("Revert "blk-mq,
percpu_ref: implement a kludge for SCSI blk-mq stall during probe"").
This patch and the prerequisite percpu_ref changes will be merged
during v3.18 devel cycle.
Signed-off-by: NTejun Heo <tj@kernel.org>
Reported-by: NChristoph Hellwig <hch@infradead.org>
Link: http://lkml.kernel.org/g/20140919113815.GA10791@lst.de
Fixes: add703fd ("blk-mq: use percpu_ref for mq usage count")
Reviewed-by: NKent Overstreet <kmo@daterainc.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Johannes Weiner <hannes@cmpxchg.org>

Allow blk-mq to pass an argument to the timeout handler to indicate
if we're timing out a reserved or regular command.  For many drivers
those need to be handled different.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJens Axboe <axboe@fb.com>

Don't do a kmalloc from timer to handle timeouts, chances are we could be
under heavy load or similar and thus just miss out on the timeouts.
Fortunately it is very easy to just iterate over all in use tags, and doing
this properly actually cleans up the blk_mq_busy_iter API as well, and
prepares us for the next patch by passing a reserved argument to the
iterator.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJens Axboe <axboe@fb.com>

Now that we've changed the driver API on the submission side use the
opportunity to fix up the name on the completion side to fit into the
general scheme.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJens Axboe <axboe@fb.com>

When we call blk_mq_start_request from the core blk-mq code before calling into
->queue_rq there is a racy window where the timeout handler can hit before we've
fully set up the driver specific part of the command.

Move the call to blk_mq_start_request into the driver so the driver can start
the request only once it is fully set up.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJens Axboe <axboe@fb.com>

Pass an explicit parameter for the last request in a batch to ->queue_rq
instead of using a request flag.  Besides being a cleaner and non-stateful
interface this is also required for the next patch, which fixes the blk-mq
I/O submission code to not start a time too early.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJens Axboe <axboe@fb.com>

We used to use this for determining whether to sort the dispatch list,
but it's unused now.
Signed-off-by: NJens Axboe <axboe@fb.com>

Fix racy updates of shared blk_mq_bitmap_tags::wake_index
and blk_mq_hw_ctx::wake_index fields.

Cc: Ming Lei <tom.leiming@gmail.com>
Signed-off-by: NAlexander Gordeev <agordeev@redhat.com>
Signed-off-by: NJens Axboe <axboe@fb.com>

For some scsi-mq cases, the tag map can be huge. So increase the
max number of tags we support.

Additionally, don't fail with EINVAL if a user requests too many
tags. Warn that the tag depth has been adjusted down, and store
the new value inside the tag_set passed in.
Signed-off-by: NJens Axboe <axboe@fb.com>

We currently pass in the hardware queue, and get the tags from there.
But from scsi-mq, with a shared tag space, it's a lot more convenient
to pass in the blk_mq_tags instead as the hardware queue isn't always
directly available. So instead of having to re-map to a given
hardware queue from rq->mq_ctx, just pass in the tags structure.
Signed-off-by: NJens Axboe <axboe@fb.com>

Currently blk-mq registers all the hardware queues in sysfs,
regardless of whether it uses them (e.g. they have CPU mappings)
or not. The unused hardware queues lack the cpux/ directories,
and the other sysfs entries (like active, pending, etc) are all
zeroes.

Change this so that sysfs correctly reflects the current mappings
of the hardware queues.
Signed-off-by: NJens Axboe <axboe@fb.com>

flush request is special, which borrows the tag from the parent
request. Hence blk_mq_tag_to_rq needs special handling to return
the flush request from the tag.
Signed-off-by: NShaohua Li <shli@fusionio.com>
Signed-off-by: NJens Axboe <axboe@fb.com>

If devices are not SG starved, we waste a lot of time potentially
collapsing SG segments. Enough that 1.5% of the CPU time goes
to this, at only 400K IOPS. Add a queue flag, QUEUE_FLAG_NO_SG_MERGE,
which just returns the number of vectors in a bio instead of looping
over all segments and checking for collapsible ones.

Add a BLK_MQ_F_SG_MERGE flag so that drivers can opt-in on the sg
merging, if they so desire.
Signed-off-by: NJens Axboe <axboe@fb.com>

There is no need for drivers to control hardware context allocation
now that we do the context to node mapping in common code.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJens Axboe <axboe@fb.com>

Instead of having two almost identical copies of the same code just let
the callers pass in the reserved flag directly.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJens Axboe <axboe@fb.com>

Both the cache flush state machine and the SCSI midlayer want to submit
requests from irq context, and the current per-request requeue_work
unfortunately causes corruption due to sharing with the csd field for
flushes.  Replace them with a per-request_queue list of requests to
be requeued.

Based on an earlier test by Ming Lei.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Reported-by: NMing Lei <tom.leiming@gmail.com>
Tested-by: NMing Lei <tom.leiming@gmail.com>
Signed-off-by: NJens Axboe <axboe@fb.com>

It works for both IPI and local completions as of commit
95f09684.
Signed-off-by: NJens Axboe <axboe@fb.com>

Right now we export two ways of completing a request:

1) blk_mq_complete_request(). This uses an IPI (if needed) and
   completes through q->softirq_done_fn(). It also works with
   timeouts.

2) blk_mq_end_io(). This completes inline, and ignores any timeout
   state of the request.

Let blk_mq_complete_request() handle non-softirq_done_fn completions
as well, by just completing inline. If a driver has enough completion
ports to place completions correctly, it need not define a
mq_ops->complete() and we can avoid an indirect function call by
doing the completion inline.
Signed-off-by: NJens Axboe <axboe@fb.com>

Drivers currently have to figure this out on their own, and they
are missing information to do it properly. The ones that did
attempt to do it, do it wrong.

So just pass in the suggested node directly to the alloc
function.
Signed-off-by: NJens Axboe <axboe@fb.com>

Export the blk-mq in-flight tag iterator for driver consumption.
This is particularly useful in exception paths or SRSI where
in-flight IOs need to be cancelled and/or reissued. The NVMe driver
conversion will use this.
Signed-off-by: NSam Bradshaw <sbradshaw@micron.com>
Signed-off-by: NMatias Bjørling <m@bjorling.me>
Signed-off-by: NJens Axboe <axboe@fb.com>

Prepare this for the next patch which adds more smarts in the
plugging logic, so that we can save some memory.
Signed-off-by: NJens Axboe <axboe@fb.com>

For request_fn based devices, the block layer exports a 'nr_requests'
file through sysfs to allow adjusting of queue depth on the fly.
Currently this returns -EINVAL for blk-mq, since it's not wired up.
Wire this up for blk-mq, so that it now also always dynamic
adjustments of the allowed queue depth for any given block device
managed by blk-mq.
Signed-off-by: NJens Axboe <axboe@fb.com>

Each hardware queue has a bitmap of software queues with pending
requests. When new IO is queued on a software queue, the bit is
set, and when IO is pruned on a hardware queue run, the bit is
cleared. This causes a lot of traffic. Switch this from the regular
BITS_PER_LONG bitmap to a sparser layout, similarly to what was
done for blk-mq tagging.

20% performance increase was observed for single threaded IO, and
about 15% performanc increase on multiple threads driving the
same device.
Signed-off-by: NJens Axboe <axboe@fb.com>

This adds support for active queue tracking, meaning that the
blk-mq tagging maintains a count of active users of a tag set.
This allows us to maintain a notion of fairness between users,
so that we can distribute the tag depth evenly without starving
some users while allowing others to try unfair deep queues.

If sharing of a tag set is detected, each hardware queue will
track the depth of its own queue. And if this exceeds the total
depth divided by the number of active queues, the user is actively
throttled down.

The active queue count is done lazily to avoid bouncing that data
between submitter and completer. Each hardware queue gets marked
active when it allocates its first tag, and gets marked inactive
when 1) the last tag is cleared, and 2) the queue timeout grace
period has passed.
Signed-off-by: NJens Axboe <axboe@fb.com>

blk-mq currently uses percpu_ida for tag allocation. But that only
works well if the ratio between tag space and number of CPUs is
sufficiently high. For most devices and systems, that is not the
case. The end result if that we either only utilize the tag space
partially, or we end up attempting to fully exhaust it and run
into lots of lock contention with stealing between CPUs. This is
not optimal.

This new tagging scheme is a hybrid bitmap allocator. It uses
two tricks to both be SMP friendly and allow full exhaustion
of the space:

1) We cache the last allocated (or freed) tag on a per blk-mq
   software context basis. This allows us to limit the space
   we have to search. The key element here is not caching it
   in the shared tag structure, otherwise we end up dirtying
   more shared cache lines on each allocate/free operation.

2) The tag space is split into cache line sized groups, and
   each context will start off randomly in that space. Even up
   to full utilization of the space, this divides the tag users
   efficiently into cache line groups, avoiding dirtying the same
   one both between allocators and between allocator and freeer.

This scheme shows drastically better behaviour, both on small
tag spaces but on large ones as well. It has been tested extensively
to show better performance for all the cases blk-mq cares about.
Signed-off-by: NJens Axboe <axboe@fb.com>

Right now we just pick the first CPU in the mask, but that can
easily overload that one. Add some basic batching and round-robin
all the entries in the mask instead.
Signed-off-by: NJens Axboe <axboe@fb.com>

The blk-mq code is using it's own version of the I/O completion affinity
tunables, which causes a few issues:

 - the rq_affinity sysfs file doesn't work for blk-mq devices, even if it
   still is present, thus breaking existing tuning setups.
 - the rq_affinity = 1 mode, which is the defauly for legacy request based
   drivers isn't implemented at all.
 - blk-mq drivers don't implement any completion affinity with the default
   flag settings.

This patches removes the blk-mq ipi_redirect flag and sysfs file, as well
as the internal BLK_MQ_F_SHOULD_IPI flag and replaces it with code that
respects the queue-wide rq_affinity flags and also implements the
rq_affinity = 1 mode.

This means I/O completion affinity can now only be tuned block-queue wide
instead of per context, which seems more sensible to me anyway.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJens Axboe <axboe@fb.com>

This allows to requeue a request that has been accepted by ->queue_rq
earlier.  This is needed by the SCSI layer in various error conditions.

The existing internal blk_mq_requeue_request is renamed to
__blk_mq_requeue_request as it is a lower level building block for this
funtionality.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJens Axboe <axboe@fb.com>

Add a helper to unconditionally kick contexts of a queue.  This will
be needed by the SCSI layer to provide fair queueing between multiple
devices on a single host.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJens Axboe <axboe@fb.com>

Add a blk-mq equivalent to blk_delay_queue so that the scsi layer can ask
to be kicked again after a delay.
Signed-off-by: NChristoph Hellwig <hch@lst.de>

Modified by me to kill the unnecessary preempt disable/enable
in the delayed workqueue handler.
Signed-off-by: NJens Axboe <axboe@fb.com>

Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJens Axboe <axboe@fb.com>

Split out the bottom half of blk_mq_end_io so that drivers can perform
work when they know a request has been completed, but before it has been
freed.  This also obsoletes blk_mq_end_io_partial as drivers can now
pass any value to blk_update_request directly.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJens Axboe <axboe@fb.com>

Add a new blk_mq_tag_set structure that gets set up before we initialize
the queue.  A single blk_mq_tag_set structure can be shared by multiple
queues.
Signed-off-by: NChristoph Hellwig <hch@lst.de>

Modular export of blk_mq_{alloc,free}_tagset added by me.
Signed-off-by: NJens Axboe <axboe@fb.com>

The current blk_mq_init_commands/blk_mq_free_commands interface has a
two problems:

 1) Because only the constructor is passed to blk_mq_init_commands there
    is no easy way to clean up when a comman initialization failed.  The
    current code simply leaks the allocations done in the constructor.

 2) There is no good place to call blk_mq_free_commands: before
    blk_cleanup_queue there is no guarantee that all outstanding
    commands have completed, so we can't free them yet.  After
    blk_cleanup_queue the queue has usually been freed.  This can be
    worked around by grabbing an unconditional reference before calling
    blk_cleanup_queue and dropping it after blk_mq_free_commands is
    done, although that's not exatly pretty and driver writers are
    guaranteed to get it wrong sooner or later.

Both issues are easily fixed by making the request constructor and
destructor normal blk_mq_ops methods.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJens Axboe <axboe@fb.com>

Instead of providing soft mappings with no guarantees on hardware
queues always being run on the right CPU, switch to a hard mapping
guarantee that ensure that we always run the hardware queue on
(one of, if more) the mapped CPU.
Signed-off-by: NJens Axboe <axboe@fb.com>

It's almost identical to blk_mq_insert_request, so fold the two into one
slightly more generic function by making the flush special case a bit
smarted.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJens Axboe <axboe@fb.com>

BLK_MQ_F_* flags are for hctx->flags, and are non-atomic and
set at registration time. BLK_MQ_S_* flags are dynamic and
atomic, and are accessed through hctx->state.

Some of the BLK_MQ_S_STOPPED uses were wrong. Additionally,
the header file should not use a bit shift for the _S_ flags,
as they are done through the set/test_bit functions.
Signed-off-by: NJens Axboe <axboe@fb.com>

If drivers do dynamic allocation in the hardware command init
path, then we need to be able to handle and return failures.

And if they do allocations or mappings in the init command path,
then we need a cleanup function to free up that space at exit
time. So add blk_mq_free_commands() as the cleanup function.

This is required for the mtip32xx driver conversion to blk-mq.
Signed-off-by: NJens Axboe <axboe@fb.com>

Add a new blk_mq_end_io_partial function to partially complete requests
as needed by the SCSI layer.  We do this by reusing blk_update_request
to advance the bio instead of having a simplified version of it in
the blk-mq code.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJens Axboe <axboe@fb.com>