linux-stable.git/block, branch v4.16.3

blk-mq: don't keep offline CPUs mapped to hctx 0

2018-04-19T06:54:09+00:00

commit bffa9909a6b48d8ca3398dec601bc9162a4020c4 upstream.

From commit 4b855ad37194 ("blk-mq: Create hctx for each present CPU),
blk-mq doesn't remap queue after CPU topo is changed, that said when
some of these offline CPUs become online, they are still mapped to
hctx 0, then hctx 0 may become the bottleneck of IO dispatch and
completion.

This patch sets up the mapping from the beginning, and aligns to
queue mapping for PCI device (blk_mq_pci_map_queues()).

Cc: Stefan Haberland 
Cc: Keith Busch 
Cc: stable@vger.kernel.org
Fixes: 4b855ad37194 ("blk-mq: Create hctx for each present CPU)
Tested-by: Christian Borntraeger 
Reviewed-by: Christoph Hellwig 
Reviewed-by: Sagi Grimberg 
Signed-off-by: Ming Lei 
Signed-off-by: Jens Axboe 
Signed-off-by: Greg Kroah-Hartman

blk-mq: make sure that correct hctx->next_cpu is set

2018-04-19T06:54:09+00:00

commit a1c735fb790745f94a359df45c11df4a69760389 upstream.

From commit 20e4d81393196 (blk-mq: simplify queue mapping & schedule
with each possisble CPU), one hctx can be mapped from all offline CPUs,
then hctx->next_cpu can be set as wrong.

This patch fixes this issue by making hctx->next_cpu pointing to the
first CPU in hctx->cpumask if all CPUs in hctx->cpumask are offline.

Cc: Stefan Haberland 
Tested-by: Christian Borntraeger 
Reviewed-by: Christoph Hellwig 
Reviewed-by: Sagi Grimberg 
Fixes: 20e4d81393196 ("blk-mq: simplify queue mapping & schedule with each possisble CPU")
Cc: stable@vger.kernel.org
Signed-off-by: Ming Lei 
Signed-off-by: Jens Axboe 
Signed-off-by: Greg Kroah-Hartman

blk-mq: order getting budget and driver tag

2018-04-19T06:54:09+00:00

commit 0bca799b92807ee9be0890690f5dde7d8c6a8e25 upstream.

This patch orders getting budget and driver tag by making sure to acquire
driver tag after budget is got, this way can help to avoid the following
race:

1) before dispatch request from scheduler queue, get one budget first, then
dequeue a request, call it request A.

2) in another IO path for dispatching request B which is from hctx->dispatch,
driver tag is got, then try to get budget in blk_mq_dispatch_rq_list(),
unfortunately the budget is held by request A.

3) meantime blk_mq_dispatch_rq_list() is called for dispatching request
A, and try to get driver tag first, unfortunately no driver tag is
available because the driver tag is held by request B

4) both two IO pathes can't move on, and IO stall is caused.

This issue can be observed when running dbench on USB storage.

This patch fixes this issue by always getting budget before getting
driver tag.

Cc: stable@vger.kernel.org
Fixes: de1482974080ec9e ("blk-mq: introduce .get_budget and .put_budget in blk_mq_ops")
Cc: Christoph Hellwig 
Cc: Bart Van Assche 
Cc: Omar Sandoval 
Signed-off-by: Ming Lei 
Signed-off-by: Jens Axboe 
Signed-off-by: Greg Kroah-Hartman

blk-mq: Directly schedule q->timeout_work when aborting a request

2018-04-19T06:54:09+00:00

commit bc6d65e6dc89c3b7ff78e4ad797117c122ffde8e upstream.

Request abortion is performed by overriding deadline to now and
scheduling timeout handling immediately.  For the latter part, the
code was using mod_timer(timeout, 0) which can't guarantee that the
timer runs afterwards.  Let's schedule the underlying work item
directly instead.

This fixes the hangs during probing reported by Sitsofe but it isn't
yet clear to me how the failure can happen reliably if it's just the
above described race condition.

Signed-off-by: Tejun Heo 
Reported-by: Sitsofe Wheeler 
Reported-by: Meelis Roos 
Fixes: 358f70da49d7 ("blk-mq: make blk_abort_request() trigger timeout path")
Cc: stable@vger.kernel.org # v4.16
Link: http://lkml.kernel.org/r/CALjAwxh-PVYFnYFCJpGOja+m5SzZ8Sa4J7ohxdK=r8NyOF-EMA@mail.gmail.com
Link: http://lkml.kernel.org/r/alpine.LRH.2.21.1802261049140.4893@math.ut.ee
Signed-off-by: Jens Axboe 
Signed-off-by: Greg Kroah-Hartman

block: Change a rcu_read_{lock,unlock}_sched() pair into rcu_read_{lock,unlock}()

2018-04-19T06:54:08+00:00

commit 818e0fa293ca836eba515615c64680ea916fd7cd upstream.

scsi_device_quiesce() uses synchronize_rcu() to guarantee that the
effect of blk_set_preempt_only() will be visible for percpu_ref_tryget()
calls that occur after the queue unfreeze by using the approach
explained in https://lwn.net/Articles/573497/. The rcu read lock and
unlock calls in blk_queue_enter() form a pair with the synchronize_rcu()
call in scsi_device_quiesce(). Both scsi_device_quiesce() and
blk_queue_enter() must either use regular RCU or RCU-sched.
Since neither the RCU-protected code in blk_queue_enter() nor
blk_queue_usage_counter_release() sleeps, regular RCU protection
is sufficient. Note: scsi_device_quiesce() does not have to be
modified since it already uses synchronize_rcu().

Reported-by: Tejun Heo 
Fixes: 3a0a529971ec ("block, scsi: Make SCSI quiesce and resume work reliably")
Signed-off-by: Bart Van Assche 
Acked-by: Tejun Heo 
Cc: Tejun Heo 
Cc: Hannes Reinecke 
Cc: Ming Lei 
Cc: Christoph Hellwig 
Cc: Johannes Thumshirn 
Cc: Oleksandr Natalenko 
Cc: Martin Steigerwald 
Cc: stable@vger.kernel.org # v4.15
Signed-off-by: Jens Axboe 
Signed-off-by: Greg Kroah-Hartman

Fix slab name "biovec-(1<<(21-12))"

2018-04-08T12:29:52+00:00

commit bd5c4facf59648581d2f1692dad7b107bf429954 upstream.

I'm getting a slab named "biovec-(1<<(21-12))". It is caused by unintended
expansion of the macro BIO_MAX_PAGES. This patch renames it to biovec-max.

Signed-off-by: Mikulas Patocka 
Cc: stable@vger.kernel.org	# v4.14+
Signed-off-by: Jens Axboe 
Signed-off-by: Greg Kroah-Hartman

Merge tag 'for-linus-20180302' of git://git.kernel.dk/linux-block

2018-03-02T17:35:36+00:00

Pull block fixes from Jens Axboe:
 "A collection of fixes for this series. This is a little larger than
  usual at this time, but that's mainly because I was out on vacation
  last week. Nothing in here is major in any way, it's just two weeks of
  fixes. This contains:

   - NVMe pull from Keith, with a set of fixes from the usual suspects.

   - mq-deadline zone unlock fix from Damien, fixing an issue with the
     SMR zone locking added for 4.16.

   - two bcache fixes sent in by Michael, with changes from Coly and
     Tang.

   - comment typo fix from Eric for blktrace.

   - return-value error handling fix for nbd, from Gustavo.

   - fix a direct-io case where we don't defer to a completion handler,
     making us sleep from IRQ device completion. From Jan.

   - a small series from Jan fixing up holes around handling of bdev
     references.

   - small set of regression fixes from Jiufei, mostly fixing problems
     around the gendisk pointer -> partition index change.

   - regression fix from Ming, fixing a boundary issue with the discard
     page cache invalidation.

   - two-patch series from Ming, fixing both a core blk-mq-sched and
     kyber issue around token freeing on a requeue condition"

* tag 'for-linus-20180302' of git://git.kernel.dk/linux-block: (24 commits)
  block: fix a typo
  block: display the correct diskname for bio
  block: fix the count of PGPGOUT for WRITE_SAME
  mq-deadline: Make sure to always unlock zones
  nvmet: fix PSDT field check in command format
  nvme-multipath: fix sysfs dangerously created links
  nbd: fix return value in error handling path
  bcache: fix kcrashes with fio in RAID5 backend dev
  bcache: correct flash only vols (check all uuids)
  blktrace_api.h: fix comment for struct blk_user_trace_setup
  blockdev: Avoid two active bdev inodes for one device
  genhd: Fix BUG in blkdev_open()
  genhd: Fix use after free in __blkdev_get()
  genhd: Add helper put_disk_and_module()
  genhd: Rename get_disk() to get_disk_and_module()
  genhd: Fix leaked module reference for NVME devices
  direct-io: Fix sleep in atomic due to sync AIO
  nvme-pci: Fix nvme queue cleanup if IRQ setup fails
  block: kyber: fix domain token leak during requeue
  blk-mq: don't call io sched's .requeue_request when requeueing rq to ->dispatch
  ...

block: display the correct diskname for bio

2018-03-01T15:41:25+00:00

bio_devname use __bdevname to display the device name, and can
only show the major and minor of the part0,
Fix this by using disk_name to display the correct name.

Fixes: 74d46992e0d9 ("block: replace bi_bdev with a gendisk pointer and partitions index")
Reviewed-by: Omar Sandoval 
Reviewed-by: Christoph Hellwig 
Signed-off-by: Jiufei Xue 
Signed-off-by: Jens Axboe

block: fix the count of PGPGOUT for WRITE_SAME

2018-03-01T15:41:23+00:00

The vm counters is counted in sectors, so we should do the conversation
in submit_bio.

Fixes: 74d46992e0d9 ("block: replace bi_bdev with a gendisk pointer and partitions index")
Cc: stable@vger.kernel.org
Reviewed-by: Omar Sandoval 
Reviewed-by: Christoph Hellwig 
Signed-off-by: Jiufei Xue 
Signed-off-by: Jens Axboe

mq-deadline: Make sure to always unlock zones

2018-03-01T15:39:24+00:00

In case of a failed write request (all retries failed) and when using
libata, the SCSI error handler calls scsi_finish_command(). In the
case of blk-mq this means that scsi_mq_done() does not get called,
that blk_mq_complete_request() does not get called and also that the
mq-deadline .completed_request() method is not called. This results in
the target zone of the failed write request being left in a locked
state, preventing that any new write requests are issued to the same
zone.

Fix this by replacing the .completed_request() method with the
.finish_request() method as this method is always called whether or
not a request completes successfully. Since the .finish_request()
method is only called by the blk-mq core if a .prepare_request()
method exists, add a dummy .prepare_request() method.

Fixes: 5700f69178e9 ("mq-deadline: Introduce zone locking support")
Cc: Hannes Reinecke 
Reviewed-by: Ming Lei 
Signed-off-by: Damien Le Moal 
[ bvanassche: edited patch description ]
Signed-off-by: Bart Van Assche 
Signed-off-by: Jens Axboe