Tests on slower machines showed current window to be way too
small. This commit increases it.
Tested-by: NJan Kara <jack@suse.cz>
Signed-off-by: NPaolo Valente <paolo.valente@linaro.org>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Since commit c5089591c3ba ("block, bfq: detect wakers and
unconditionally inject their I/O"), when the in-service bfq_queue, say
Q, is temporarily empty, BFQ checks whether there are I/O requests to
inject (also) from the waker bfq_queue for Q. To this goal, the value
pointed by bfqq->waker_bfqq->next_rq must be controlled. However, the
current implementation mistakenly looks at bfqq->next_rq, which
instead points to the next request of the currently served queue.

This mistake evidently causes losses of throughput in scenarios with
waker bfq_queues.

This commit corrects this mistake.

Fixes: c5089591c3ba ("block, bfq: detect wakers and unconditionally inject their I/O")
Signed-off-by: NJia Cheng Hu <jia.jiachenghu@gmail.com>
Signed-off-by: NJan Kara <jack@suse.cz>
Signed-off-by: NPaolo Valente <paolo.valente@linaro.org>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

The value of the I/O plugging (idling) timeout is used also as the
think-time threshold to decide whether a process has a short think
time.  In this respect, a good value of this timeout for rotational
drives is un the order of several ms. Yet, this is often too long a
time interval to be effective as a think-time threshold. This commit
mitigates this problem (by a lot, according to tests), by halving the
threshold.
Tested-by: NJan Kara <jack@suse.cz>
Signed-off-by: NPaolo Valente <paolo.valente@linaro.org>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

BFQ computes number of tags it allows to be allocated for each request type
based on tag bitmap. However it uses 1 << bitmap.shift as number of
available tags which is wrong. 'shift' is just an internal bitmap value
containing logarithm of how many bits bitmap uses in each bitmap word.
Thus number of tags allowed for some request types can be far to low.
Use proper bitmap.depth which has the number of tags instead.
Signed-off-by: NJan Kara <jack@suse.cz>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Yang Yang reported the following crash caused by requeueing a flush
request in Kyber:

  [    2.517297] Unable to handle kernel paging request at virtual address ffffffd8071c0b00
  ...
  [    2.517468] pc : clear_bit+0x18/0x2c
  [    2.517502] lr : sbitmap_queue_clear+0x40/0x228
  [    2.517503] sp : ffffff800832bc60 pstate : 00c00145
  ...
  [    2.517599] Process ksoftirqd/5 (pid: 51, stack limit = 0xffffff8008328000)
  [    2.517602] Call trace:
  [    2.517606]  clear_bit+0x18/0x2c
  [    2.517619]  kyber_finish_request+0x74/0x80
  [    2.517627]  blk_mq_requeue_request+0x3c/0xc0
  [    2.517637]  __scsi_queue_insert+0x11c/0x148
  [    2.517640]  scsi_softirq_done+0x114/0x130
  [    2.517643]  blk_done_softirq+0x7c/0xb0
  [    2.517651]  __do_softirq+0x208/0x3bc
  [    2.517657]  run_ksoftirqd+0x34/0x60
  [    2.517663]  smpboot_thread_fn+0x1c4/0x2c0
  [    2.517667]  kthread+0x110/0x120
  [    2.517669]  ret_from_fork+0x10/0x18

This happens because Kyber doesn't track flush requests, so
kyber_finish_request() reads a garbage domain token. Only call the
scheduler's requeue_request() hook if RQF_ELVPRIV is set (like we do for
the finish_request() hook in blk_mq_free_request()). Now that we're
handling it in blk-mq, also remove the check from BFQ.
Reported-by: NYang Yang <yang.yang@vivo.com>
Signed-off-by: NOmar Sandoval <osandov@fb.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

High CPU utilization on "native_queued_spin_lock_slowpath" due to lock
contention is possible for mq-deadline and bfq IO schedulers
when nr_hw_queues is more than one.

It is because kblockd work queue can submit IO from all online CPUs
(through blk_mq_run_hw_queues()) even though only one hctx has pending
commands.

The elevator callback .has_work for mq-deadline and bfq scheduler considers
pending work if there are any IOs on request queue but it does not account
hctx context.

Add a per-hctx 'elevator_queued' count to the hctx to avoid triggering
the elevator even though there are no requests queued.

[jpg: Relocated atomic_dec() in dd_dispatch_request(), update commit message per Kashyap]
Signed-off-by: NKashyap Desai <kashyap.desai@broadcom.com>
Signed-off-by: NHannes Reinecke <hare@suse.de>
Signed-off-by: NJohn Garry <john.garry@huawei.com>
Tested-by: NDouglas Gilbert <dgilbert@interlog.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Introduce pointers for the blk_mq_tags regular and reserved bitmap tags,
with the goal of later being able to use a common shared tag bitmap across
all HW contexts in a set.
Signed-off-by: NJohn Garry <john.garry@huawei.com>
Tested-by: Don Brace<don.brace@microsemi.com> #SCSI resv cmds patches used
Tested-by: NDouglas Gilbert <dgilbert@interlog.com>
Reviewed-by: NHannes Reinecke <hare@suse.de>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Replace the existing /* fall through */ comments and its variants with
the new pseudo-keyword macro fallthrough[1]. Also, remove unnecessary
fall-through markings when it is the case.

[1] https://www.kernel.org/doc/html/v5.7/process/deprecated.html?highlight=fallthrough#implicit-switch-case-fall-throughSigned-off-by: NGustavo A. R. Silva <gustavoars@kernel.org>

Change "at at" to "at a".
Signed-off-by: NRandy Dunlap <rdunlap@infradead.org>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: linux-block@vger.kernel.org
Signed-off-by: NJens Axboe <axboe@kernel.dk>

None of the I/O schedulers actually needs it.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NMing Lei <ming.lei@redhat.com>
Reviewed-by: NHannes Reinecke <hare@suse.de>
Reviewed-by: NJohannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: NBart Van Assche <bvanassche@acm.org>
Reviewed-by: NDaniel Wagner <dwagner@suse.de>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Use the common interface bdi_dev_name() to get device name.
Signed-off-by: NYufen Yu <yuyufen@huawei.com>
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>
Reviewed-by: NJan Kara <jack@suse.cz>
Reviewed-by: NBart Van Assche <bvanassche@acm.org>

Add missing <linux/backing-dev.h> include BFQ
Signed-off-by: NJens Axboe <axboe@kernel.dk>

A bfq_put_queue() may be invoked in __bfq_bic_change_cgroup(). The
goal of this put is to release a process reference to a bfq_queue. But
process-reference releases may trigger also some extra operation, and,
to this goal, are handled through bfq_release_process_ref(). So, turn
the invocation of bfq_put_queue() into an invocation of
bfq_release_process_ref().

Tested-by: cki-project@redhat.com
Signed-off-by: NPaolo Valente <paolo.valente@linaro.org>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

In bfq_idle_slice_timer func, bfqq = bfqd->in_service_queue is
not in bfqd-lock critical section. The bfqq, which is not
equal to NULL in bfq_idle_slice_timer, may be freed after passing
to bfq_idle_slice_timer_body. So we will access the freed memory.

In addition, considering the bfqq may be in race, we should
firstly check whether bfqq is in service before doing something
on it in bfq_idle_slice_timer_body func. If the bfqq in race is
not in service, it means the bfqq has been expired through
__bfq_bfqq_expire func, and wait_request flags has been cleared in
__bfq_bfqd_reset_in_service func. So we do not need to re-clear the
wait_request of bfqq which is not in service.

KASAN log is given as follows:
[13058.354613] ==================================================================
[13058.354640] BUG: KASAN: use-after-free in bfq_idle_slice_timer+0xac/0x290
[13058.354644] Read of size 8 at addr ffffa02cf3e63f78 by task fork13/19767
[13058.354646]
[13058.354655] CPU: 96 PID: 19767 Comm: fork13
[13058.354661] Call trace:
[13058.354667]  dump_backtrace+0x0/0x310
[13058.354672]  show_stack+0x28/0x38
[13058.354681]  dump_stack+0xd8/0x108
[13058.354687]  print_address_description+0x68/0x2d0
[13058.354690]  kasan_report+0x124/0x2e0
[13058.354697]  __asan_load8+0x88/0xb0
[13058.354702]  bfq_idle_slice_timer+0xac/0x290
[13058.354707]  __hrtimer_run_queues+0x298/0x8b8
[13058.354710]  hrtimer_interrupt+0x1b8/0x678
[13058.354716]  arch_timer_handler_phys+0x4c/0x78
[13058.354722]  handle_percpu_devid_irq+0xf0/0x558
[13058.354731]  generic_handle_irq+0x50/0x70
[13058.354735]  __handle_domain_irq+0x94/0x110
[13058.354739]  gic_handle_irq+0x8c/0x1b0
[13058.354742]  el1_irq+0xb8/0x140
[13058.354748]  do_wp_page+0x260/0xe28
[13058.354752]  __handle_mm_fault+0x8ec/0x9b0
[13058.354756]  handle_mm_fault+0x280/0x460
[13058.354762]  do_page_fault+0x3ec/0x890
[13058.354765]  do_mem_abort+0xc0/0x1b0
[13058.354768]  el0_da+0x24/0x28
[13058.354770]
[13058.354773] Allocated by task 19731:
[13058.354780]  kasan_kmalloc+0xe0/0x190
[13058.354784]  kasan_slab_alloc+0x14/0x20
[13058.354788]  kmem_cache_alloc_node+0x130/0x440
[13058.354793]  bfq_get_queue+0x138/0x858
[13058.354797]  bfq_get_bfqq_handle_split+0xd4/0x328
[13058.354801]  bfq_init_rq+0x1f4/0x1180
[13058.354806]  bfq_insert_requests+0x264/0x1c98
[13058.354811]  blk_mq_sched_insert_requests+0x1c4/0x488
[13058.354818]  blk_mq_flush_plug_list+0x2d4/0x6e0
[13058.354826]  blk_flush_plug_list+0x230/0x548
[13058.354830]  blk_finish_plug+0x60/0x80
[13058.354838]  read_pages+0xec/0x2c0
[13058.354842]  __do_page_cache_readahead+0x374/0x438
[13058.354846]  ondemand_readahead+0x24c/0x6b0
[13058.354851]  page_cache_sync_readahead+0x17c/0x2f8
[13058.354858]  generic_file_buffered_read+0x588/0xc58
[13058.354862]  generic_file_read_iter+0x1b4/0x278
[13058.354965]  ext4_file_read_iter+0xa8/0x1d8 [ext4]
[13058.354972]  __vfs_read+0x238/0x320
[13058.354976]  vfs_read+0xbc/0x1c0
[13058.354980]  ksys_read+0xdc/0x1b8
[13058.354984]  __arm64_sys_read+0x50/0x60
[13058.354990]  el0_svc_common+0xb4/0x1d8
[13058.354994]  el0_svc_handler+0x50/0xa8
[13058.354998]  el0_svc+0x8/0xc
[13058.354999]
[13058.355001] Freed by task 19731:
[13058.355007]  __kasan_slab_free+0x120/0x228
[13058.355010]  kasan_slab_free+0x10/0x18
[13058.355014]  kmem_cache_free+0x288/0x3f0
[13058.355018]  bfq_put_queue+0x134/0x208
[13058.355022]  bfq_exit_icq_bfqq+0x164/0x348
[13058.355026]  bfq_exit_icq+0x28/0x40
[13058.355030]  ioc_exit_icq+0xa0/0x150
[13058.355035]  put_io_context_active+0x250/0x438
[13058.355038]  exit_io_context+0xd0/0x138
[13058.355045]  do_exit+0x734/0xc58
[13058.355050]  do_group_exit+0x78/0x220
[13058.355054]  __wake_up_parent+0x0/0x50
[13058.355058]  el0_svc_common+0xb4/0x1d8
[13058.355062]  el0_svc_handler+0x50/0xa8
[13058.355066]  el0_svc+0x8/0xc
[13058.355067]
[13058.355071] The buggy address belongs to the object at ffffa02cf3e63e70#012 which belongs to the cache bfq_queue of size 464
[13058.355075] The buggy address is located 264 bytes inside of#012 464-byte region [ffffa02cf3e63e70, ffffa02cf3e64040)
[13058.355077] The buggy address belongs to the page:
[13058.355083] page:ffff7e80b3cf9800 count:1 mapcount:0 mapping:ffff802db5c90780 index:0xffffa02cf3e606f0 compound_mapcount: 0
[13058.366175] flags: 0x2ffffe0000008100(slab|head)
[13058.370781] raw: 2ffffe0000008100 ffff7e80b53b1408 ffffa02d730c1c90 ffff802db5c90780
[13058.370787] raw: ffffa02cf3e606f0 0000000000370023 00000001ffffffff 0000000000000000
[13058.370789] page dumped because: kasan: bad access detected
[13058.370791]
[13058.370792] Memory state around the buggy address:
[13058.370797]  ffffa02cf3e63e00: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fb fb
[13058.370801]  ffffa02cf3e63e80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
[13058.370805] >ffffa02cf3e63f00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
[13058.370808]                                                                 ^
[13058.370811]  ffffa02cf3e63f80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
[13058.370815]  ffffa02cf3e64000: fb fb fb fb fb fb fb fb fc fc fc fc fc fc fc fc
[13058.370817] ==================================================================
[13058.370820] Disabling lock debugging due to kernel taint

Here, we directly pass the bfqd to bfq_idle_slice_timer_body func.
--
V2->V3: rewrite the comment as suggested by Paolo Valente
V1->V2: add one comment, and add Fixes and Reported-by tag.

Fixes: aee69d78 ("block, bfq: introduce the BFQ-v0 I/O scheduler as an extra scheduler")
Acked-by: NPaolo Valente <paolo.valente@linaro.org>
Reported-by: NWang Wang <wangwang2@huawei.com>
Signed-off-by: NZhiqiang Liu <liuzhiqiang26@huawei.com>
Signed-off-by: NFeilong Lin <linfeilong@huawei.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

The exact, general goal of the function bfq_split_bfqq() is not that
apparent. Add a comment to make it clear.
Tested-by: NOleksandr Natalenko <oleksandr@natalenko.name>
Signed-off-by: NPaolo Valente <paolo.valente@linaro.org>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

ifdefs around gets and puts of bfq groups reduce readability, remove them.
Tested-by: NOleksandr Natalenko <oleksandr@natalenko.name>
Reported-by: NJens Axboe <axboe@kernel.dk>
Signed-off-by: NPaolo Valente <paolo.valente@linaro.org>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

The flag on_st in the bfq_entity data structure is true if the entity
is on a service tree or is in service. Yet the name of the field,
confusingly, does not mention the second, very important case. Extend
the name to mention the second case too.
Tested-by: NOleksandr Natalenko <oleksandr@natalenko.name>
Signed-off-by: NPaolo Valente <paolo.valente@linaro.org>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

BFQ maintains an ordered list, implemented with an RB tree, of
head-request positions of non-empty bfq_queues. This position tree,
inherited from CFQ, is used to find bfq_queues that contain I/O close
to each other. BFQ merges these bfq_queues into a single shared queue,
if this boosts throughput on the device at hand.

There is however a special-purpose bfq_queue that does not participate
in queue merging, the oom bfq_queue. Yet, also this bfq_queue could be
wrongly added to the position tree. So bfqq_find_close() could return
the oom bfq_queue, which is a source of further troubles in an
out-of-memory situation. This commit prevents the oom bfq_queue from
being inserted into the position tree.
Tested-by: NPatrick Dung <patdung100@gmail.com>
Tested-by: NOleksandr Natalenko <oleksandr@natalenko.name>
Signed-off-by: NPaolo Valente <paolo.valente@linaro.org>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Commit 478de338 ("block, bfq: deschedule empty bfq_queues not
referred by any process") fixed commit 3726112e ("block, bfq:
re-schedule empty queues if they deserve I/O plugging") by
descheduling an empty bfq_queue when it remains with not process
reference. Yet, this still left a case uncovered: an empty bfq_queue
with not process reference that remains in service. This happens for
an in-service sync bfq_queue that is deemed to deserve I/O-dispatch
plugging when it remains empty. Yet no new requests will arrive for
such a bfq_queue if no process sends requests to it any longer. Even
worse, the bfq_queue may happen to be prematurely freed while still in
service (because there may remain no reference to it any longer).

This commit solves this problem by preventing I/O dispatch from being
plugged for the in-service bfq_queue, if the latter has no process
reference (the bfq_queue is then prevented from remaining in service).

Fixes: 3726112e ("block, bfq: re-schedule empty queues if they deserve I/O plugging")
Tested-by: NOleksandr Natalenko <oleksandr@natalenko.name>
Reported-by: NPatrick Dung <patdung100@gmail.com>
Tested-by: NPatrick Dung <patdung100@gmail.com>
Signed-off-by: NPaolo Valente <paolo.valente@linaro.org>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

This macro is never used after introduced from commit aee69d78
("block, bfq: introduce the BFQ-v0 I/O scheduler as an extra scheduler")

Better to remove it.
Signed-off-by: NAlex Shi <alex.shi@linux.alibaba.com>
Cc: Paolo Valente <paolo.valente@linaro.org>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: linux-block@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Since commit 3726112e ("block, bfq: re-schedule empty queues if
they deserve I/O plugging"), to prevent the service guarantees of a
bfq_queue from being violated, the bfq_queue may be left busy, i.e.,
scheduled for service, even if empty (see comments in
__bfq_bfqq_expire() for details). But, if no process will send
requests to the bfq_queue any longer, then there is no point in
keeping the bfq_queue scheduled for service.

In addition, keeping the bfq_queue scheduled for service, but with no
process reference any longer, may cause the bfq_queue to be freed when
descheduled from service. But this is assumed to never happen, and
causes a UAF if it happens. This, in turn, caused crashes [1, 2].

This commit fixes this issue by descheduling an empty bfq_queue when
it remains with not process reference.

[1] https://bugzilla.redhat.com/show_bug.cgi?id=1767539
[2] https://bugzilla.kernel.org/show_bug.cgi?id=205447

Fixes: 3726112e ("block, bfq: re-schedule empty queues if they deserve I/O plugging")
Reported-by: NChris Evich <cevich@redhat.com>
Reported-by: NPatrick Dung <patdung100@gmail.com>
Reported-by: NThorsten Schubert <tschubert@bafh.org>
Tested-by: NThorsten Schubert <tschubert@bafh.org>
Tested-by: NOleksandr Natalenko <oleksandr@natalenko.name>
Signed-off-by: NPaolo Valente <paolo.valente@linaro.org>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

When used on cgroup1, bfq uses the blkg->stat_bytes and ->stat_ios
from blk-cgroup core to populate six stat knobs.  blk-cgroup core is
moving away from blkg_rwstat to improve scalability and won't be able
to support this usage.

It isn't like the sharing gains all that much.  Let's break it out to
dedicated rwstat counters which are updated when on cgroup1.  This
makes use of bfqg_*rwstat*() helpers outside of
CONFIG_BFQ_CGROUP_DEBUG.  Move them out.

v2: Compile fix when !CONFIG_BFQ_CGROUP_DEBUG.
Signed-off-by: NTejun Heo <tj@kernel.org>
Cc: Paolo Valente <paolo.valente@linaro.org>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

If equal to 0, the injection limit for a bfq_queue is pushed to 1
after a first sample of the total service time of the I/O requests of
the queue is computed (to allow injection to start). Yet, because of a
mistake in the branch that performs this action, the push may happen
also in some other case. This commit fixes this issue.
Tested-by: NOleksandr Natalenko <oleksandr@natalenko.name>
Signed-off-by: NPaolo Valente <paolo.valente@linaro.org>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

The update period of the injection limit has been tentatively set to
100 ms, to reduce fluctuations. This value however proved to cause,
occasionally, the limit to be decremented for some bfq_queue only
after the queue underwent excessive injection for a lot of time. This
commit reduces the period to 10 ms.
Tested-by: NOleksandr Natalenko <oleksandr@natalenko.name>
Signed-off-by: NPaolo Valente <paolo.valente@linaro.org>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Upon an increment attempt of the injection limit, the latter is
constrained not to become higher than twice the maximum number
max_rq_in_driver of I/O requests that have happened to be in service
in the drive. This high bound allows the injection limit to grow
beyond max_rq_in_driver, which may then cause max_rq_in_driver itself
to grow.

However, since the limit is incremented by only one unit at a time,
there is no need for such a high bound, and just max_rq_in_driver+1 is
enough.
Tested-by: NOleksandr Natalenko <oleksandr@natalenko.name>
Signed-off-by: NPaolo Valente <paolo.valente@linaro.org>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

BFQ updates the injection limit of each bfq_queue as a function of how
much the limit inflates the service times experienced by the I/O
requests of the queue. So only service times affected by injection
must be taken into account. Unfortunately, in the current
implementation of this update scheme, the service time of an I/O
request rq not affected by injection may happen to be considered in
the following case: there is no I/O request in service when rq
arrives.

This commit fixes this issue by making sure that only service times
affected by injection are considered for updating the injection
limit. In particular, the service time of an I/O request rq is now
considered only if at least one of the following two conditions holds:
- the destination bfq_queue for rq underwent injection before rq
arrival, and there is still I/O in service in the drive on rq arrival
(the service of such unfinished I/O may delay the service of rq);
- injection occurs between the arrival and the completion time of rq.
Tested-by: NOleksandr Natalenko <oleksandr@natalenko.name>
Signed-off-by: NPaolo Valente <paolo.valente@linaro.org>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

As reported in [1], the call bfq_init_rq(rq) may return NULL in case
of OOM (in particular, if rq->elv.icq is NULL because memory
allocation failed in failed in ioc_create_icq()).

This commit handles this circumstance.

[1] https://lkml.org/lkml/2019/7/22/824

Cc: Hsin-Yi Wang <hsinyi@google.com>
Cc: Nicolas Boichat <drinkcat@chromium.org>
Cc: Doug Anderson <dianders@chromium.org>
Reported-by: NGuenter Roeck <linux@roeck-us.net>
Reported-by: NHsin-Yi Wang <hsinyi@google.com>
Reviewed-by: NGuenter Roeck <linux@roeck-us.net>
Signed-off-by: NPaolo Valente <paolo.valente@linaro.org>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Since commit 13a857a4 ("block, bfq: detect wakers and
unconditionally inject their I/O"), every bfq_queue has a pointer to a
waker bfq_queue and a list of the bfq_queues it may wake. In this
respect, when a bfq_queue, say Q, remains with no I/O source attached
to it, Q cannot be woken by any other bfq_queue, and cannot wake any
other bfq_queue. Then Q must be removed from the woken list of its
possible waker bfq_queue, and all bfq_queues in the woken list of Q
must stop having a waker bfq_queue.

Q remains with no I/O source in two cases: when the last process
associated with Q exits or when such a process gets associated with a
different bfq_queue. Unfortunately, commit 13a857a4 ("block, bfq:
detect wakers and unconditionally inject their I/O") performed the
above updates only in the first case.

This commit fixes this bug by moving these updates to when Q gets
freed. This is a simple and safe way to handle all cases, as both the
above events, process exit and re-association, lead to Q being freed
soon, and because dangling references would come out only after Q gets
freed (if no update were performed).

Fixes: 13a857a4 ("block, bfq: detect wakers and unconditionally inject their I/O")
Reported-by: NDouglas Anderson <dianders@chromium.org>
Tested-by: NDouglas Anderson <dianders@chromium.org>
Signed-off-by: NPaolo Valente <paolo.valente@linaro.org>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Since commit 13a857a4 ("block, bfq: detect wakers and
unconditionally inject their I/O"), BFQ stores, in a per-device
pointer last_completed_rq_bfqq, the last bfq_queue that had an I/O
request completed. If some bfq_queue receives new I/O right after the
last request of last_completed_rq_bfqq has been completed, then
last_completed_rq_bfqq may be a waker bfq_queue.

But if the bfq_queue last_completed_rq_bfqq points to is freed, then
last_completed_rq_bfqq becomes a dangling reference. This commit
resets last_completed_rq_bfqq if the pointed bfq_queue is freed.

Fixes: 13a857a4 ("block, bfq: detect wakers and unconditionally inject their I/O")
Reported-by: NDouglas Anderson <dianders@chromium.org>
Tested-by: NDouglas Anderson <dianders@chromium.org>
Signed-off-by: NPaolo Valente <paolo.valente@linaro.org>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Consider a sync bfq_queue Q that remains empty while in service, and
suppose that, when this happens, there is a fair amount of already
in-flight I/O not belonging to Q. In such a situation, I/O dispatching
may need to be plugged (until new I/O arrives for Q), for the
following reason.

The drive may decide to serve in-flight non-Q's I/O requests before
Q's ones, thereby delaying the arrival of new I/O requests for Q
(recall that Q is sync). If I/O-dispatching is not plugged, then,
while Q remains empty, a basically uncontrolled amount of I/O from
other queues may be dispatched too, possibly causing the service of
Q's I/O to be delayed even longer in the drive. This problem gets more
and more serious as the speed and the queue depth of the drive grow,
because, as these two quantities grow, the probability to find no
queue busy but many requests in flight grows too.

If Q has the same weight and priority as the other queues, then the
above delay is unlikely to cause any issue, because all queues tend to
undergo the same treatment. So, since not plugging I/O dispatching is
convenient for throughput, it is better not to plug. Things change in
case Q has a higher weight or priority than some other queue, because
Q's service guarantees may simply be violated. For this reason,
commit 1de0c4cd ("block, bfq: reduce idling only in symmetric
scenarios") does plug I/O in such an asymmetric scenario. Plugging
minimizes the delay induced by already in-flight I/O, and enables Q to
recover the bandwidth it may lose because of this delay.

Yet the above commit does not cover the case of weight-raised queues,
for efficiency concerns. For weight-raised queues, I/O-dispatch
plugging is activated simply if not all bfq_queues are
weight-raised. But this check does not handle the case of in-flight
requests, because a bfq_queue may become non busy *before* all its
in-flight requests are completed.

This commit performs I/O-dispatch plugging for weight-raised queues if
there are some in-flight requests.

As a practical example of the resulting recover of control, under
write load on a Samsung SSD 970 PRO, gnome-terminal starts in 1.5
seconds after this fix, against 15 seconds before the fix (as a
reference, gnome-terminal takes about 35 seconds to start with any of
the other I/O schedulers).

Fixes: 1de0c4cd ("block, bfq: reduce idling only in symmetric scenarios")
Signed-off-by: NPaolo Valente <paolo.valente@linaro.org>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Rename the block documentation files to ReST, add an
index for them and adjust in order to produce a nice html
output via the Sphinx build system.

At its new index.rst, let's add a :orphan: while this is not linked to
the main index.rst file, in order to avoid build warnings.
Signed-off-by: NMauro Carvalho Chehab <mchehab+samsung@kernel.org>

In reboot tests on several devices we were seeing a "use after free"
when slub_debug or KASAN was enabled.  The kernel complained about:

  Unable to handle kernel paging request at virtual address 6b6b6c2b

...which is a classic sign of use after free under slub_debug.  The
stack crawl in kgdb looked like:

 0  test_bit (addr=<optimized out>, nr=<optimized out>)
 1  bfq_bfqq_busy (bfqq=<optimized out>)
 2  bfq_select_queue (bfqd=<optimized out>)
 3  __bfq_dispatch_request (hctx=<optimized out>)
 4  bfq_dispatch_request (hctx=<optimized out>)
 5  0xc056ef00 in blk_mq_do_dispatch_sched (hctx=0xed249440)
 6  0xc056f728 in blk_mq_sched_dispatch_requests (hctx=0xed249440)
 7  0xc0568d24 in __blk_mq_run_hw_queue (hctx=0xed249440)
 8  0xc0568d94 in blk_mq_run_work_fn (work=<optimized out>)
 9  0xc024c5c4 in process_one_work (worker=0xec6d4640, work=0xed249480)
 10 0xc024cff4 in worker_thread (__worker=0xec6d4640)

Digging in kgdb, it could be found that, though bfqq looked fine,
bfqq->bic had been freed.

Through further digging, I postulated that perhaps it is illegal to
access a "bic" (AKA an "icq") after bfq_exit_icq() had been called
because the "bic" can be freed at some point in time after this call
is made.  I confirmed that there certainly were cases where the exact
crashing code path would access the "bic" after bfq_exit_icq() had
been called.  Sspecifically I set the "bfqq->bic" to (void *)0x7 and
saw that the bic was 0x7 at the time of the crash.

To understand a bit more about why this crash was fairly uncommon (I
saw it only once in a few hundred reboots), you can see that much of
the time bfq_exit_icq_fbqq() fully frees the bfqq and thus it can't
access the ->bic anymore.  The only case it doesn't is if
bfq_put_queue() sees a reference still held.

However, even in the case when bfqq isn't freed, the crash is still
rare.  Why?  I tracked what happened to the "bic" after the exit
routine.  It doesn't get freed right away.  Rather,
put_io_context_active() eventually called put_io_context() which
queued up freeing on a workqueue.  The freeing then actually happened
later than that through call_rcu().  Despite all these delays, some
extra debugging showed that all the hoops could be jumped through in
time and the memory could be freed causing the original crash.  Phew!

To make a long story short, assuming it truly is illegal to access an
icq after the "exit_icq" callback is finished, this patch is needed.

Cc: stable@vger.kernel.org
Reviewed-by: NPaolo Valente <paolo.valente@unimore.it>
Signed-off-by: NDouglas Anderson <dianders@chromium.org>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Some debug code suggested by Paolo was tripping when I did reboot
stress tests.  Specifically in bfq_bfqq_resume_state()
"bic->saved_wr_start_at_switch_to_srt" was later than the current
value of "jiffies".  A bit of debugging showed that
"bic->saved_wr_start_at_switch_to_srt" was actually 0 and a bit more
debugging showed that was because we had run through the "unlikely"
case in the bfq_bfqq_save_state() function.

Let's init "saved_wr_start_at_switch_to_srt" in the unlikely case to
something sane.

NOTE: this fixes no known real-world errors.
Reviewed-by: NPaolo Valente <paolo.valente@linaro.org>
Reviewed-by: NGuenter Roeck <groeck@chromium.org>
Signed-off-by: NDouglas Anderson <dianders@chromium.org>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

By mistake, there is a '&' instead of a '==' in the definition of the
macro BFQQ_TOTALLY_SEEKY. This commit replaces the wrong operator with
the correct one.

Fixes: 7074f076 ("block, bfq: do not tag totally seeky queues as soft rt")
Signed-off-by: NPaolo Valente <paolo.valente@linaro.org>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Consider, on one side, a bfq_queue Q that remains empty while in
service, and, on the other side, the pending I/O of bfq_queues that,
according to their timestamps, have to be served after Q.  If an
uncontrolled amount of I/O from the latter bfq_queues were dispatched
while Q is waiting for its new I/O to arrive, then Q's bandwidth
guarantees would be violated. To prevent this, I/O dispatch is plugged
until Q receives new I/O (except for a properly controlled amount of
injected I/O). Unfortunately, preemption breaks I/O-dispatch plugging,
for the following reason.

Preemption is performed in two steps. First, Q is expired and
re-scheduled. Second, the new bfq_queue to serve is chosen. The first
step is needed by the second, as the second can be performed only
after Q's timestamps have been properly updated (done in the
expiration step), and Q has been re-queued for service. This
dependency is a consequence of the way how BFQ's scheduling algorithm
is currently implemented.

But Q is not re-scheduled at all in the first step, because Q is
empty. As a consequence, an uncontrolled amount of I/O may be
dispatched until Q becomes non empty again. This breaks Q's service
guarantees.

This commit addresses this issue by re-scheduling Q even if it is
empty. This in turn breaks the assumption that all scheduled queues
are non empty. Then a few extra checks are now needed.
Signed-off-by: NPaolo Valente <paolo.valente@linaro.org>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

BFQ enqueues the I/O coming from each process into a separate
bfq_queue, and serves bfq_queues one at a time. Each bfq_queue may be
served for at most timeout_sync milliseconds (default: 125 ms). This
service scheme is prone to the following inaccuracy.

While a bfq_queue Q1 is in service, some empty bfq_queue Q2 may
receive I/O, and, according to BFQ's scheduling policy, may become the
right bfq_queue to serve, in place of the currently in-service
bfq_queue. In this respect, postponing the service of Q2 to after the
service of Q1 finishes may delay the completion of Q2's I/O, compared
with an ideal service in which all non-empty bfq_queues are served in
parallel, and every non-empty bfq_queue is served at a rate
proportional to the bfq_queue's weight. This additional delay is equal
at most to the time Q1 may unjustly remain in service before switching
to Q2.

If Q1 and Q2 have the same weight, then this time is most likely
negligible compared with the completion time to be guaranteed to Q2's
I/O. In addition, first, one of the reasons why BFQ may want to serve
Q1 for a while is that this boosts throughput and, second, serving Q1
longer reduces BFQ's overhead. As a conclusion, it is usually better
not to preempt Q1 if both Q1 and Q2 have the same weight.

In contrast, as Q2's weight or priority becomes higher and higher
compared with that of Q1, the above delay becomes larger and larger,
compared with the I/O completion times that have to be guaranteed to
Q2 according to Q2's weight. So reducing this delay may be more
important than avoiding the costs of preempting Q1.

Accordingly, this commit preempts Q1 if Q2 has a higher weight or a
higher priority than Q1. Preemption causes Q1 to be re-scheduled, and
triggers a new choice of the next bfq_queue to serve. If Q2 really is
the next bfq_queue to serve, then Q2 will be set in service
immediately.

This change reduces the component of the I/O latency caused by the
above delay by about 80%. For example, on an (old) PLEXTOR PX-256M5
SSD, the maximum latency reported by fio drops from 15.1 to 3.2 ms for
a process doing sporadic random reads while another process is doing
continuous sequential reads.
Signed-off-by: NNicola Bottura <bottura.nicola95@gmail.com>
Signed-off-by: NPaolo Valente <paolo.valente@linaro.org>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

A bfq_queue Q may happen to be synchronized with another
bfq_queue Q2, i.e., the I/O of Q2 may need to be completed for Q to
receive new I/O. We call Q2 "waker queue".

If I/O plugging is being performed for Q, and Q is not receiving any
more I/O because of the above synchronization, then, thanks to BFQ's
injection mechanism, the waker queue is likely to get served before
the I/O-plugging timeout fires.

Unfortunately, this fact may not be sufficient to guarantee a high
throughput during the I/O plugging, because the inject limit for Q may
be too low to guarantee a lot of injected I/O. In addition, the
duration of the plugging, i.e., the time before Q finally receives new
I/O, may not be minimized, because the waker queue may happen to be
served only after other queues.

To address these issues, this commit introduces the explicit detection
of the waker queue, and the unconditional injection of a pending I/O
request of the waker queue on each invocation of
bfq_dispatch_request().

One may be concerned that this systematic injection of I/O from the
waker queue delays the service of Q's I/O. Fortunately, it doesn't. On
the contrary, next Q's I/O is brought forward dramatically, for it is
not blocked for milliseconds.
Reported-by: NSrivatsa S. Bhat (VMware) <srivatsa@csail.mit.edu>
Tested-by: NSrivatsa S. Bhat (VMware) <srivatsa@csail.mit.edu>
Signed-off-by: NPaolo Valente <paolo.valente@linaro.org>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Until the base value for request service times gets finally computed
for a bfq_queue, the inject limit for that queue does depend on the
think-time state (short|long) of the queue. A timely update of the
think time then guarantees a quicker activation or deactivation of the
injection. Fortunately, the think time of a bfq_queue is updated in
the same code path as the inject limit; but after the inject limit.

This commits moves the update of the think time before the update of
the inject limit. For coherence, it moves the update of the seek time
too.
Reported-by: NSrivatsa S. Bhat (VMware) <srivatsa@csail.mit.edu>
Tested-by: NSrivatsa S. Bhat (VMware) <srivatsa@csail.mit.edu>
Signed-off-by: NPaolo Valente <paolo.valente@linaro.org>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

I/O injection gets reduced if it increases the request service times
of the victim queue beyond a certain threshold.  The threshold, in its
turn, is computed as a function of the base service time enjoyed by
the queue when it undergoes no injection.

As a consequence, for injection to work properly, the above base value
has to be accurate. In this respect, such a value may vary over
time. For example, it varies if the size or the spatial locality of
the I/O requests in the queue change. It is then important to update
this value whenever possible. This commit performs this update.
Reported-by: NSrivatsa S. Bhat (VMware) <srivatsa@csail.mit.edu>
Tested-by: NSrivatsa S. Bhat (VMware) <srivatsa@csail.mit.edu>
Signed-off-by: NPaolo Valente <paolo.valente@linaro.org>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

One of the cases where the parameters for injection may be updated is
when there are no more in-flight I/O requests. The number of in-flight
requests is stored in the field bfqd->rq_in_driver of the descriptor
bfqd of the device. So, the controlled condition is
bfqd->rq_in_driver == 0.

Unfortunately, this is wrong because, the instruction that checks this
condition is in the code path that handles the completion of a
request, and, in particular, the instruction is executed before
bfqd->rq_in_driver is decremented in such a code path.

This commit fixes this issue by just replacing 0 with 1 in the
comparison.
Reported-by: NSrivatsa S. Bhat (VMware) <srivatsa@csail.mit.edu>
Tested-by: NSrivatsa S. Bhat (VMware) <srivatsa@csail.mit.edu>
Signed-off-by: NPaolo Valente <paolo.valente@linaro.org>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Until the base value of the request service times gets finally
computed for a bfq_queue, the inject limit does depend on the
think-time state (short|long). The limit must be 0 or 1 if the think
time is deemed, respectively, as short or long. However, such a check
and possible limit update is performed only periodically, once per
second. So, to make the injection mechanism much more reactive, this
commit performs the update also every time the think-time state
changes.

In addition, in the following special case, this commit lets the
inject limit of a bfq_queue bfqq remain equal to 1 even if bfqq's
think time is short: bfqq's I/O is synchronized with that of some
other queue, i.e., bfqq may receive new I/O only after the I/O of the
other queue is completed. Keeping the inject limit to 1 allows the
blocking I/O to be served while bfqq is in service. And this is very
convenient both for bfqq and for the total throughput, as explained
in detail in the comments in bfq_update_has_short_ttime().
Reported-by: NSrivatsa S. Bhat (VMware) <srivatsa@csail.mit.edu>
Tested-by: NSrivatsa S. Bhat (VMware) <srivatsa@csail.mit.edu>
Signed-off-by: NPaolo Valente <paolo.valente@linaro.org>
Signed-off-by: NJens Axboe <axboe@kernel.dk>