Background:
  We do not have a dependable block layer interface to determine whether
block device has io requests which have not been completed for somewhat
long time. Currently we have 'in_flight' interface, it counts the number
of I/O requests that have been issued to the device driver but have
not yet completed, and it does not include I/O requests that are in the
queue but not yet issued to the device driver, which means it will not
count io requests that have been stucked in block layer.
  Also say that there are steady io requests issued to device driver,
'in_flight' maybe always non-zero, but you could not determine whether
there is one io request which has not been completed for too long.

Solution:
  To find io requests which have not been completed for too long, here
add 3 new inferfaces:
  /sys/block/vdb/queue/hang_threshold
If one io request's running time has been greater than this value, count
this io as hang.

  /sys/block/vdb/hang
Show read/write io requests' hang counter.

  /sys/kernel/debug/block/vdb/rq_hang
Show all hang io requests's detailed info, like below:
  ffff97db96301200 {.op=WRITE, .cmd_flags=SYNC, .rq_flags=STARTED|
ELVPRIV|IO_STAT|STATS, .state=in_flight, .tag=30, .internal_tag=169,
.start_time_ns=140634088407, .io_start_time_ns=140634102958,
.current_time=146497371953, .bio = ffff97db91e8e000,
.bio_pages = { ffffd096a0602540 }, .bio = ffff97db91e8ec00,
.bio_pages = { ffffd096a070eec0 }, .bio = ffff97db91e8f600,
.bio_pages = { ffffd096a0424cc0 }, .bio = ffff97db91e8f300,
.bio_pages = { ffffd096a0600a80 }}

With above info, we can easily see this request's latency distribution,
and see next patch for bio_pages's usage.

Note, /sys/kernel/debug/block/vdb/rq_hang only exists in blk-mq device driver
and needs CONFIG_BLK_DEBUG_FS enabled.
Signed-off-by: NXiaoguang Wang <xiaoguang.wang@linux.alibaba.com>
Reviewed-by: NJoseph Qi <joseph.qi@linux.alibaba.com>

commit cd84a62e0078dce09f4ed349bec84f86c9d54b30 upstream.

The RQF_PREEMPT flag is used for three purposes:
- In the SCSI core, for making sure that power management requests
  are executed even if a device is in the "quiesced" state.
- For domain validation by SCSI drivers that use the parallel port.
- In the IDE driver, for IDE preempt requests.
Rename "preempt-only" into "pm-only" because the primary purpose of
this mode is power management. Since the power management core may
but does not have to resume a runtime suspended device before
performing system-wide suspend and since a later patch will set
"pm-only" mode as long as a block device is runtime suspended, make
it possible to set "pm-only" mode from more than one context. Since
with this change scsi_device_quiesce() is no longer idempotent, make
that function return early if it is called for a quiesced queue.
Signed-off-by: NBart Van Assche <bvanassche@acm.org>
Acked-by: NMartin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: NHannes Reinecke <hare@suse.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NMing Lei <ming.lei@redhat.com>
Cc: Jianchao Wang <jianchao.w.wang@oracle.com>
Cc: Johannes Thumshirn <jthumshirn@suse.de>
Cc: Alan Stern <stern@rowland.harvard.edu>
Signed-off-by: NJens Axboe <axboe@kernel.dk>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>

It won't be efficient to dequeue request one by one from sw queue,
but we have to do that when queue is busy for better merge performance.

This patch takes the Exponential Weighted Moving Average(EWMA) to figure
out if queue is busy, then only dequeue request one by one from sw queue
when queue is busy.

Fixes: b347689f ("blk-mq-sched: improve dispatching from sw queue")
Cc: Kashyap Desai <kashyap.desai@broadcom.com>
Cc: Laurence Oberman <loberman@redhat.com>
Cc: Omar Sandoval <osandov@fb.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Bart Van Assche <bart.vanassche@wdc.com>
Cc: Hannes Reinecke <hare@suse.de>
Reported-by: NKashyap Desai <kashyap.desai@broadcom.com>
Tested-by: NKashyap Desai <kashyap.desai@broadcom.com>
Signed-off-by: NMing Lei <ming.lei@redhat.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Exclude zoned block device members from struct request_queue for
CONFIG_BLK_DEV_ZONED == n. Avoid breaking the build by only building
the code that uses these struct request_queue members if
CONFIG_BLK_DEV_ZONED != n.
Signed-off-by: NBart Van Assche <bart.vanassche@wdc.com>
Reviewed-by: NDamien Le Moal <damien.lemoal@wdc.com>
Cc: Matias Bjorling <mb@lightnvm.io>
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Since the implementation of blk_queue_nr_zones() is trivial and since
it only has a single caller, inline this function.
Signed-off-by: NBart Van Assche <bart.vanassche@wdc.com>
Reviewed-by: NDamien Le Moal <damien.lemoal@wdc.com>
Cc: Matias Bjorling <mb@lightnvm.io>
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

If rq_state == ARRAY_SIZE() then we read one element beyond the end of
the blk_mq_rq_state_name_array[] array.

Fixes: ec6dcf63 ("blk-mq-debugfs: Show more request state information")
Reviewed-by: NBart Van Assche <bart.vanassche@wdc.com>
Signed-off-by: NDan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

This patch simplifies the timeout handling by relying on the request
reference counting to ensure the iterator is operating on an inflight
and truly timed out request. Since the reference counting prevents the
tag from being reallocated, the block layer no longer needs to prevent
drivers from completing their requests while the timeout handler is
operating on it: a driver completing a request is allowed to proceed to
the next state without additional syncronization with the block layer.

This also removes any need for generation sequence numbers since the
request lifetime is prevented from being reallocated as a new sequence
while timeout handling is operating on it.

To enables this a refcount is added to struct request so that request
users can be sure they're operating on the same request without it
changing while they're processing it.  The request's tag won't be
released for reuse until both the timeout handler and the completion
are done with it.
Signed-off-by: NKeith Busch <keith.busch@intel.com>
[hch: slight cleanups, added back submission side hctx lock, use cmpxchg
 for completions]
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

No driver uses this interface any more, so remove it.

Cc: Stefan Haberland <sth@linux.vnet.ibm.com>
Tested-by: NChristian Borntraeger <borntraeger@de.ibm.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NSagi Grimberg <sagi@grimberg.me>
Signed-off-by: NMing Lei <ming.lei@redhat.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Since commit 634f9e46 ("blk-mq: remove REQ_ATOM_COMPLETE usages
from blk-mq") blk_rq_is_complete() only reports whether or not a
request has completed for legacy queues. Hence modify the
blk-mq-debugfs code such that it shows the blk-mq request state
again.

Fixes: 634f9e46 ("blk-mq: remove REQ_ATOM_COMPLETE usages from blk-mq")
Signed-off-by: NBart Van Assche <bart.vanassche@wdc.com>
Cc: Tejun Heo <tj@kernel.org>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

When debugging the ZBC code in the mq-deadline scheduler it is very
important to know which zones are locked and which zones are not
locked. Hence this patch that exports the zone locking information
through debugfs.

Cc: Omar Sandoval <osandov@fb.com>
Cc: Ming Lei <ming.lei@redhat.com>
Cc: Hannes Reinecke <hare@suse.de>
Cc: Johannes Thumshirn <jthumshirn@suse.de>
Reviewed-by: NDamien Le Moal <damien.lemoal@wdc.com>
Tested-by: NDamien Le Moal <damien.lemoal@wdc.com>
Signed-off-by: NBart Van Assche <bart.vanassche@wdc.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Make sure that the queue show and store methods are contiguous and
also that these appear in alphabetical order.
Signed-off-by: NBart Van Assche <bart.vanassche@wdc.com>
Cc: Omar Sandoval <osandov@fb.com>
Cc: Damien Le Moal <damien.lemoal@wdc.com>
Cc: Ming Lei <ming.lei@redhat.com>
Cc: Hannes Reinecke <hare@suse.de>
Cc: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Attributes that only implement .seq_ops are read-only, any write to
them should be rejected. But currently kernel would crash when
writing to such debugfs entries, e.g.

chmod +w /sys/kernel/debug/block/<dev>/requeue_list
echo 0 > /sys/kernel/debug/block/<dev>/requeue_list
chmod -w /sys/kernel/debug/block/<dev>/requeue_list

Fix it by returning -EPERM in blk_mq_debugfs_write() when writing to
such attributes.

Cc: Ming Lei <ming.lei@redhat.com>
Signed-off-by: NEryu Guan <eguan@redhat.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Looking at debug output, we see:

./000000009ddfa913/requeue_list:000000009646711c {.op=READ, .state=idle, gen=0x1
18, abort_gen=0x0, .cmd_flags=, .rq_flags=SORTED|1|SOFTBARRIER|IO_STAT, complete
=0, .tag=-1, .internal_tag=217}

Note the '1' between SORTED and SOFTBARRIER - that's because no name
as defined for RQF_STARTED. Fixed that.
Signed-off-by: NJens Axboe <axboe@kernel.dk>

We only have one atomic flag left. Instead of using an entire
unsigned long for that, steal the bottom bit of the deadline
field that we already reserved.

Remove ->atomic_flags, since it's now unused.
Reviewed-by: NBart Van Assche <bart.vanassche@wdc.com>
Reviewed-by: NOmar Sandoval <osandov@fb.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

We don't need this to be an atomic flag, it can be a regular
flag. We either end up on the same CPU for the polling, in which
case the state is sane, or we did the sleep which would imply
the needed barrier to ensure we see the right state.
Reviewed-by: NBart Van Assche <bart.vanassche@wdc.com>
Reviewed-by: NOmar Sandoval <osandov@fb.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

We are missing ZONE_WRITE_LOCKED and MQ_TIMEOUT_EXPIRED, add them
so the debugfs bits can decode them.
Signed-off-by: NJens Axboe <axboe@kernel.dk>

After the recent updates to use generation number and state based
synchronization, we can easily replace REQ_ATOM_STARTED usages by
adding an extra state to distinguish completed but not yet freed
state.

Add MQ_RQ_COMPLETE and replace REQ_ATOM_STARTED usages with
blk_mq_rq_state() tests.  REQ_ATOM_STARTED no longer has any users
left and is removed.
Signed-off-by: NTejun Heo <tj@kernel.org>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

This flag will be used in the next patch to let the block layer
core know whether or not a SCSI request queue has been quiesced.
A quiesced SCSI queue namely only processes RQF_PREEMPT requests.
Signed-off-by: NBart Van Assche <bart.vanassche@wdc.com>
Reviewed-by: NHannes Reinecke <hare@suse.com>
Tested-by: NMartin Steigerwald <martin@lichtvoll.de>
Tested-by: NOleksandr Natalenko <oleksandr@natalenko.name>
Cc: Ming Lei <ming.lei@redhat.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

This patch attempts to make the case of hctx re-running on driver tag
failure more robust. Without this patch, it's pretty easy to trigger a
stall condition with shared tags. An example is using null_blk like
this:

modprobe null_blk queue_mode=2 nr_devices=4 shared_tags=1 submit_queues=1 hw_queue_depth=1

which sets up 4 devices, sharing the same tag set with a depth of 1.
Running a fio job ala:

[global]
bs=4k
rw=randread
norandommap
direct=1
ioengine=libaio
iodepth=4

[nullb0]
filename=/dev/nullb0
[nullb1]
filename=/dev/nullb1
[nullb2]
filename=/dev/nullb2
[nullb3]
filename=/dev/nullb3

will inevitably end with one or more threads being stuck waiting for a
scheduler tag. That IO is then stuck forever, until someone else
triggers a run of the queue.

Ensure that we always re-run the hardware queue, if the driver tag we
were waiting for got freed before we added our leftover request entries
back on the dispatch list.
Reviewed-by: NBart Van Assche <bart.vanassche@wdc.com>
Tested-by: NBart Van Assche <bart.vanassche@wdc.com>
Reviewed-by: NMing Lei <ming.lei@redhat.com>
Reviewed-by: NOmar Sandoval <osandov@fb.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

We already have a queue_is_rq_based helper to check if a request_queue
is request based, so we can remove the flag for it.
Acked-by: NMike Snitzer <snitzer@redhat.com>
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

In blk_mq_debugfs_register(), I remembered to set up the per-hctx sched
directories if a default scheduler was already configured by
blk_mq_sched_init() from blk_mq_init_allocated_queue(), but I didn't do
the same for the device-wide sched directory. Fix it.

Fixes: d332ce09 ("blk-mq-debugfs: allow schedulers to register debugfs attributes")
Signed-off-by: NOmar Sandoval <osandov@fb.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

The symbolic constants QUEUE_FLAG_SCSI_PASSTHROUGH, QUEUE_FLAG_QUIESCED
and REQ_NOWAIT are missing from blk-mq-debugfs.c. Add these to
blk-mq-debugfs.c such that these appear as names in debugfs instead of
as numbers.
Reviewed-by: NOmar Sandoval <osandov@fb.com>
Signed-off-by: NBart Van Assche <bart.vanassche@wdc.com>
Cc: Hannes Reinecke <hare@suse.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

This was detected by sparse.
Signed-off-by: NBart Van Assche <bart.vanassche@sandisk.com>
Reviewed-by: NOmar Sandoval <osandov@fb.com>
Reviewed-by: NHannes Reinecke <hare@suse.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

We haven't used these in years, but somehow the definitions still
remained. Kill them, and renumber the QUEUE_FLAG_ space. We had
a hole in the beginning of the space, too.
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Useful to verify that things are working the way they should.
Reading the file will return number of kb written with each
write hint. Writing the file will reset the statistics. No care
is taken to ensure that we don't race on updates.

Drivers will write to q->write_hints[] if they handle a given
write hint.
Reviewed-by: NAndreas Dilger <adilger@dilger.ca>
Reviewed-by: NMartin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Running a queue causes the block layer to examine the per-CPU and
hw queues but not the requeue list. Hence add a 'kick' operation
that also examines the requeue list.
Signed-off-by: NBart Van Assche <bart.vanassche@sandisk.com>
Reviewed-by: NMing Lei <ming.lei@redhat.com>
Reviewed-by: NEduardo Valentin <eduval@amazon.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Hannes Reinecke <hare@suse.com>
Cc: Omar Sandoval <osandov@fb.com>
Signed-off-by: NJens Axboe <axboe@fb.com>

Requests that got stuck in a block driver are neither on
blk_mq_ctx.rq_list nor on any hw dispatch queue. Make these
visible in debugfs through the "busy" attribute.
Signed-off-by: NBart Van Assche <bart.vanassche@sandisk.com>
Reviewed-by: NEduardo Valentin <eduval@amazon.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Hannes Reinecke <hare@suse.com>
Cc: Omar Sandoval <osandov@fb.com>
Cc: Ming Lei <ming.lei@redhat.com>
Signed-off-by: NJens Axboe <axboe@fb.com>

When verifying whether or not a blk-mq driver forgot to kick the
requeue list after having requeued a request it is important to
be able to verify the contents of the requeue list. Hence export
that list through debugfs.
Signed-off-by: NBart Van Assche <bart.vanassche@sandisk.com>
Reviewed-by: NHannes Reinecke <hare@suse.com>
Reviewed-by: NMing Lei <ming.lei@redhat.com>
Reviewed-by: NEduardo Valentin <eduval@amazon.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Omar Sandoval <osandov@fb.com>
Signed-off-by: NJens Axboe <axboe@fb.com>

When analyzing e.g. queue lockups it is important to know whether
or not a request has already been started. Hence also show the
atomic request flags.
Signed-off-by: NBart Van Assche <bart.vanassche@sandisk.com>
Reviewed-by: NHannes Reinecke <hare@suse.com>
Reviewed-by: NMing Lei <ming.lei@redhat.com>
Reviewed-by: NEduardo Valentin <eduval@amazon.com>
Cc: Omar Sandoval <osandov@fb.com>
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: NJens Axboe <axboe@fb.com>

Expose the fifo lists, cached next requests, batching state, and
dispatch list. It'd also be possible to add the sorted lists, but there
aren't already seq_file helpers for rbtrees.
Signed-off-by: NOmar Sandoval <osandov@fb.com>
Reviewed-by: NHannes Reinecke <hare@suse.com>
Signed-off-by: NJens Axboe <axboe@fb.com>

Expose the domain token pools, asynchronous sbitmap depth, domain
request lists, and batching state.
Signed-off-by: NOmar Sandoval <osandov@fb.com>
Reviewed-by: NHannes Reinecke <hare@suse.com>
Signed-off-by: NJens Axboe <axboe@fb.com>

This provides the infrastructure for schedulers to expose their internal
state through debugfs. We add a list of queue attributes and a list of
hctx attributes to struct elevator_type and wire them up when switching
schedulers.
Signed-off-by: NOmar Sandoval <osandov@fb.com>
Reviewed-by: NHannes Reinecke <hare@suse.com>

Add missing seq_file.h header in blk-mq-debugfs.h
Signed-off-by: NJens Axboe <axboe@fb.com>

Originally, I tied debugfs registration/unregistration together with
sysfs. There's no reason to do this, and it's getting in the way of
letting schedulers define their own debugfs attributes. Instead, tie the
debugfs registration to the lifetime of the structures themselves.

The saner lifetimes mean we can also get rid of the extra mq directory
and move everything one level up. I.e., nvme0n1/mq/hctx0/tags is now
just nvme0n1/hctx0/tags.
Signed-off-by: NOmar Sandoval <osandov@fb.com>
Signed-off-by: NJens Axboe <axboe@fb.com>

Preparation for adding more declarations.
Signed-off-by: NOmar Sandoval <osandov@fb.com>
Reviewed-by: NHannes Reinecke <hare@suse.com>
Signed-off-by: NJens Axboe <axboe@fb.com>

In commit e869b546 ("blk-mq: Unregister debugfs attributes
earlier"), we shuffled the debugfs cleanup around so that the "state"
attribute was removed before we freed the blk-mq data structures.
However, later changes are going to undo that, so we need to explicitly
disallow running a dead queue.

[Omar: rebased and updated commit message]
Signed-off-by: NOmar Sandoval <osandov@fb.com>
Signed-off-by: NBart Van Assche <bart.vanassche@sandisk.com>
Reviewed-by: NHannes Reinecke <hare@suse.com>
Signed-off-by: NJens Axboe <axboe@fb.com>

A large part of blk-mq-debugfs.c is file_operations and seq_file
boilerplate. This sucks as is but will suck even more when schedulers
can define their own debugfs entries. Factor it all out into a single
blk_mq_debugfs_fops which multiplexes as needed. We store the
request_queue, blk_mq_hw_ctx, or blk_mq_ctx in the parent directory
dentry, which is kind of hacky, but it works.
Signed-off-by: NOmar Sandoval <osandov@fb.com>
Reviewed-by: NHannes Reinecke <hare@suse.com>
Signed-off-by: NJens Axboe <axboe@fb.com>

It's not clear what these numbered directories represent unless you
consult the code. We're about to get rid of the intermediate "mq"
directory, so these would be even more confusing without that context.
Signed-off-by: NOmar Sandoval <osandov@fb.com>
Signed-off-by: NJens Axboe <axboe@fb.com>

Slightly more readable, plus we also strip leading spaces.
Signed-off-by: NOmar Sandoval <osandov@fb.com>
Reviewed-by: NHannes Reinecke <hare@suse.com>
Signed-off-by: NJens Axboe <axboe@fb.com>

blk_queue_flags_store() currently truncates and returns a short write if
the operation being written is too long. This can give us weird results,
like here:

$ echo "run            bar"
echo: write error: invalid argument
$ dmesg
[ 1103.075435] blk_queue_flags_store: unsupported operation bar. Use either 'run' or 'start'

Instead, return an error if the user does this. While we're here, make
the argument names consistent with everywhere else in this file.
Signed-off-by: NOmar Sandoval <osandov@fb.com>
Reviewed-by: NHannes Reinecke <hare@suse.com>
Signed-off-by: NJens Axboe <axboe@fb.com>

Make sure the spelled out flag names match the definition. This also
adds a missing hctx state, BLK_MQ_S_START_ON_RUN, and a missing
cmd_flag, __REQ_NOUNMAP.
Signed-off-by: NOmar Sandoval <osandov@fb.com>
Reviewed-by: NHannes Reinecke <hare@suse.com>
Signed-off-by: NJens Axboe <axboe@fb.com>