lightnvm: pblk: fix bad error check

Fix bad error check

Fixes: a4bd217b4326 "lightnvm: physical block device (pblk) target"

Signed-off-by: Javier González <javier@cnexlabs.com>
Reviewed-by: Matias Bjørling <matias@cnexlabs.com>
Signed-off-by: Jens Axboe <axboe@fb.com>

lightnvm: pblk: fix race condition on line retry

When a pblk line fails (or is recovered), make sure to take the line
management lock.

Fixes: a4bd217b4326 "lightnvm: physical block device (pblk) target"

Signed-off-by: Javier González <javier@cnexlabs.com>
Reviewed-by: Matias Bjørling <matias@cnexlabs.com>
Signed-off-by: Jens Axboe <axboe@fb.com>

block: fix blk_integrity_register to use template's interval_exp if not 0

When registering an integrity profile: if the template's interval_exp is
not 0 use it, otherwise use the ilog2() of logical block size of the
provided gendisk.

This fixes a long-standing DM linear target bug where it cannot pass
integrity data to the underlying device if its logical block size
conflicts with the underlying device's logical block size.

Cc: stable@vger.kernel.org
Reported-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Acked-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Jens Axboe <axboe@fb.com>

lightnvm: don't print a warning for ADDR_EMPTY

Reading from ADDR_EMPTY is out of bounds.  The current code generates a
static checker warning because we check for out of bounds "lba" before
we check for ADDR_EMPTY, so the second check is always false.  It looks
like we intended ADDR_EMPTY to be a no-op without printing a warning.

Fixes: a4bd217b4326 ("lightnvm: physical block device (pblk) target")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Reviewed-by: Javier González <javier@cnexlabs.com>
Signed-off-by: Jens Axboe <axboe@fb.com>

lightnvm: potential underflow in pblk_read_rq()

This is a static checker fix, and perhaps not a real bug.  The static
checker thinks that nr_secs could be negative.  It would result in
zeroing more memory than intended.  Anyway, even if it's not a bug,
changing this variable to unsigned makes the code easier to audit.

Fixes: a4bd217b4326 ("lightnvm: physical block device (pblk) target")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Reviewed-by: Javier González <javier@cnexlabs.com>
Signed-off-by: Jens Axboe <axboe@fb.com>

block: get rid of blk_integrity_revalidate()

Commit 25520d55cdb6 ("block: Inline blk_integrity in struct gendisk")
introduced blk_integrity_revalidate(), which seems to assume ownership
of the stable pages flag and unilaterally clears it if no blk_integrity
profile is registered:

    if (bi->profile)
            disk->queue->backing_dev_info->capabilities |=
                    BDI_CAP_STABLE_WRITES;
    else
            disk->queue->backing_dev_info->capabilities &=
                    ~BDI_CAP_STABLE_WRITES;

It's called from revalidate_disk() and rescan_partitions(), making it
impossible to enable stable pages for drivers that support partitions
and don't use blk_integrity: while the call in revalidate_disk() can be
trivially worked around (see zram, which doesn't support partitions and
hence gets away with zram_revalidate_disk()), rescan_partitions() can
be triggered from userspace at any time.  This breaks rbd, where the
ceph messenger is responsible for generating/verifying CRCs.

Since blk_integrity_{un,}register() "must" be used for (un)registering
the integrity profile with the block layer, move BDI_CAP_STABLE_WRITES
setting there.  This way drivers that call blk_integrity_register() and
use integrity infrastructure won't interfere with drivers that don't
but still want stable pages.

Fixes: 25520d55cdb6 ("block: Inline blk_integrity in struct gendisk")
Cc: "Martin K. Petersen" <martin.petersen@oracle.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Mike Snitzer <snitzer@redhat.com>
Cc: stable@vger.kernel.org # 4.4+, needs backporting
Tested-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Signed-off-by: Jens Axboe <axboe@fb.com>

lightnvm: propagate pblk_init return to userspace

From userspace calling ioctl(NVM_DEV_CREATE) was returning ENOMEM for
invalid arguments even though pblk (pblk_init) was returning correctly
-EINVAL to nvm_create_tgt inside core.  This patch propagates the
correct return value to userspace.

Because pblk was introduced recently this only needs to go in 4.12.

Fixes: a4bd217b4326 ("lightnvm: physical block device (pblk) target")
Signed-off-by: Rakesh Pandit <rakesh@tuxera.com>
Signed-off-by: Jens Axboe <axboe@fb.com>

blk-mq: Fix preempt count imbalance

Avoid that the following kernel bug gets triggered:

BUG: sleeping function called from invalid context at ./include/linux/buffer_head.h:349
in_atomic(): 1, irqs_disabled(): 0, pid: 8019, name: find
CPU: 10 PID: 8019 Comm: find Tainted: G        W I     4.11.0-rc4-dbg+ #2
Call Trace:
 dump_stack+0x68/0x93
 ___might_sleep+0x16e/0x230
 __might_sleep+0x4a/0x80
 __ext4_get_inode_loc+0x1e0/0x4e0
 ext4_iget+0x70/0xbc0
 ext4_iget_normal+0x2f/0x40
 ext4_lookup+0xb6/0x1f0
 lookup_slow+0x104/0x1e0
 walk_component+0x19a/0x330
 path_lookupat+0x4b/0x100
 filename_lookup+0x9a/0x110
 user_path_at_empty+0x36/0x40
 vfs_statx+0x67/0xc0
 SYSC_newfstatat+0x20/0x40
 SyS_newfstatat+0xe/0x10
 entry_SYSCALL_64_fastpath+0x18/0xad

This happens since the big if/else in blk_mq_make_request() doesn't
have final else section that also drops the ctx. Add that.

Fixes: b00c53e8f411 ("blk-mq: fix schedule-while-atomic with scheduler attached")
Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Cc: Omar Sandoval <osandov@fb.com>
Added a bit more to the commit log.

Signed-off-by: Jens Axboe <axboe@fb.com>

Merge branch 'nvme-4.12' of git://git.infradead.org/nvme into for-4.12/block

Christoph writes:

This is the current NVMe pile: virtualization extensions, lots of FC
updates and various misc bits.  There are a few more FC bits that didn't
make the cut, but we'd like to get this request out before the merge
window for sure.

mtip32xx: fix dereference of stack garbage

We need to get the command payload from the request before
we attempt to dereference it.

Fixes: 4dda4735c581 ("mtip32xx: add a status field to struct mtip_cmd")
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@fb.com>

nvme: let dm-mpath distinguish nvme error codes

Currently most IOs which return the nvme error codes are retried on
the other path if those IOs returns EIO from NVMe driver. This
patch let Multipath distinguish nvme media error codes and some
generic or cmd-specific nvme error codes so that multipath will
not retry those kinds of IO, to save bandwidth.

Signed-off-by: Junxiong Guan <guanjunxiong@huawei.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>

nvme/pci: Poll CQ on timeout

If an IO timeout occurs, it's helpful to know if the controller did not
post a completion or the driver missed an interrupt. While we never expect
the latter, this patch will make it possible to tell the difference so
we don't have to guess.

Signed-off-by: Keith Busch <keith.busch@intel.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Tested-by: Johannes Thumshirn <jthumshirn@suse.de>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>

nvmet_fc: Change traddr field separator to a colon

The FC-NVME spec revised syntax to avoid comma separators.
Sync with the change in the parser for traddr on port attachments.

Signed-off-by: James Smart <james.smart@broadcom.com>
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>

nvme_fc: Add ls aborts on remote port teardown

remoteport teardown never aborted the LS opertions. Add support.

Signed-off-by: James Smart <james.smart@broadcom.com>
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>

nvme_fc: Move LS's to rport

Link LS's on the remoteport rather than the controller. LS's are
between nport's. Makes more sense, especially on async teardown where
the controller is torn down regardless of the LS (LS is more of a notifier
to the target of the teardown), to have them on the remoteport.

While revising ls send/done routines, issues were seen relative to
refcounting and cleanup, especially in async path. Reworked these code
paths.

Signed-off-by: James Smart <james.smart@broadcom.com>
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>

nvmet_fc: add missing reference in add_port

Add missing reference in add_port

Signed-off-by: James Smart <james.smart@broadcom.com>
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>

nvmet_fc: Rework target side abort handling

target transport:
----------------------
There are cases when there is a need to abort in-progress target
operations (writedata) so that controller termination or errors can
clean up. That can't happen currently as the abort is another target
op type, so it can't be used till the running one finishes (and it may
not).  Solve by removing the abort op type and creating a separate
downcall from the transport to the lldd to request an io to be aborted.

The transport will abort ios on queue teardown or io errors. In general
the transport tries to call the lldd abort only when the io state is
idle. Meaning: ops that transmit data (readdata or rsp) will always
finish their transmit (or the lldd will see a state on the
link or initiator port that fails the transmit) and the done call for
the operation will occur. The transport will wait for the op done
upcall before calling the abort function, and as the io is idle, the
io can be cleaned up immediately after the abort call; Similarly, ios
that are not waiting for data or transmitting data must be in the nvmet
layer being processed. The transport will wait for the nvmet layer
completion before calling the abort function, and as the io is idle,
the io can be cleaned up immediately after the abort call; As for ops
that are waiting for data (writedata), they may be outstanding
indefinitely if the lldd doesn't see a condition where the initiatior
port or link is bad. In those cases, the transport will call the abort
function and wait for the lldd's op done upcall for the operation, where
it will then clean up the io.

Additionally, if a lldd receives an ABTS and matches it to an outstanding
request in the transport, A new new transport upcall was created to abort
the outstanding request in the transport. The transport expects any
outstanding op call (readdata or writedata) will completed by the lldd and
the operation upcall made. The transport doesn't act on the reported
abort (e.g. clean up the io) until an op done upcall occurs, a new op is
attempted, or the nvmet layer completes the io processing.

fcloop:
----------------------
Updated to support the new target apis.
On fcp io aborts from the initiator, the loopback context is updated to
NULL out the half that has completed. The initiator side is immediately
called after the abort request with an io completion (abort status).
On fcp io aborts from the target, the io is stopped and the initiator side
sees it as an aborted io. Target side ops, perhaps in progress while the
initiator side is done, continue but noop the data movement as there's no
structure on the initiator side to reference.

patch also contains:
----------------------
Revised lpfc to support the new abort api

commonized rsp buffer syncing and nulling of private data based on
calling paths.

errors in op done calls don't take action on the fod. They're bad
operations which implies the fod may be bad.

Signed-off-by: James Smart <james.smart@broadcom.com>
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>

nvme_fcloop: split job struct from transport for req_release

Current design has the fcloop job struct, used for both initiator and
target processing, allocated as part of the initiator request structure.
On aborts, the initiator side (based on the request) may terminate, yet
the target side wants to continue processing. the target side can't do
that if the initiator side goes away.
Revise fcloop to allocate an independent target side structure when it
starts an io from the initiator.

Added a lock to the request struct as well to synchronize pointer updates
on abort calls.

Modified target downcalls to recognize conditions where initiator has
aborted the io (thus nulled the pointer between job structs), thus
avoid referencing sgl lists which are gone and no longer making upcalls
to the initiator.

In conditions where the targetport is no longer connected, have the
initiator return an access failure rather than simulating a command
completion.

Signed-off-by: James Smart <james.smart@broadcom.com>
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>

nvmet_fc: add req_release to lldd api

With the advent of the opdone calls changing context, the lldd can no
longer assume that once the op->done call returns for RSP operations
that the request struct is no longer being accessed.

As such, revise the lldd api for a req_release callback that the
transport will call when the job is complete. This will also be used
with abort cases.

Fixed text in api header for change in io complete semantics.

Revised lpfc to support the new req_release api.

Signed-off-by: James Smart <james.smart@broadcom.com>
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>

nvmet_fc: add target feature flags for upcall isr contexts

Two new feature flags were added to control whether upcalls to the
transport result in context switches or stay in the calling context.

NVMET_FCTGTFEAT_CMD_IN_ISR:
  By default, if the flag is not set, the transport assumes the
  lldd is in a non-isr context and in the cpu context it should be
  for the io queue. As such, the cmd handler is called directly in the
  calling context.
  If the flag is set, indicating the upcall is an isr context, the
  transport mandates a transition to a workqueue. The workqueue assigned
  to the queue is used for the context.
NVMET_FCTGTFEAT_OPDONE_IN_ISR
  By default, if the flag is not set, the transport assumes the
  lldd is in a non-isr context and in the cpu context it should be
  for the io queue. As such, the fcp operation done callback is called
  directly in the calling context.
  If the flag is set, indicating the upcall is an isr context, the
  transport mandates a transition to a workqueue. The workqueue assigned
  to the queue is used for the context.

Updated lpfc for flags

Signed-off-by: James Smart <james.smart@broadcom.com>
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>

nvmet: convert from kmap to nvmet_copy_from_sgl

This is safer as it doesn't rely on the data being stored in
a single page in an sgl.

It also aids our effort to start phasing out users of sg_page. See [1].

For this we kmalloc some memory, copy to it and free at the end. Note:
we can't allocate this memory on the stack as the kbuild test robot
reports some frame size overflows on i386.

[1] https://lwn.net/Articles/720053/

Signed-off-by: Logan Gunthorpe <logang@deltatee.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Max Gurtovoy <maxg@mellanox.com>
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>

nvme: improve performance for virtual NVMe devices

This change provides a mechanism to reduce the number of MMIO doorbell
writes for the NVMe driver. When running in a virtualized environment
like QEMU, the cost of an MMIO is quite hefy here. The main idea for
the patch is provide the device two memory location locations:
 1) to store the doorbell values so they can be lookup without the doorbell
    MMIO write
 2) to store an event index.
I believe the doorbell value is obvious, the event index not so much.
Similar to the virtio specification, the virtual device can tell the
driver (guest OS) not to write MMIO unless you are writing past this
value.

FYI: doorbell values are written by the nvme driver (guest OS) and the
event index is written by the virtual device (host OS).

The patch implements a new admin command that will communicate where
these two memory locations reside. If the command fails, the nvme
driver will work as before without any optimizations.

Contributions:
  Eric Northup <digitaleric@google.com>
  Frank Swiderski <fes@google.com>
  Ted Tso <tytso@mit.edu>
  Keith Busch <keith.busch@intel.com>

Just to give an idea on the performance boost with the vendor
extension: Running fio [1], a stock NVMe driver I get about 200K read
IOPs with my vendor patch I get about 1000K read IOPs. This was
running with a null device i.e. the backing device simply returned
success on every read IO request.

[1] Running on a 4 core machine:
  fio --time_based --name=benchmark --runtime=30
  --filename=/dev/nvme0n1 --nrfiles=1 --ioengine=libaio --iodepth=32
  --direct=1 --invalidate=1 --verify=0 --verify_fatal=0 --numjobs=4
  --rw=randread --blocksize=4k --randrepeat=false

Signed-off-by: Rob Nelson <rlnelson@google.com>
[mlin: port for upstream]
Signed-off-by: Ming Lin <mlin@kernel.org>
[koike: updated for upstream]
Signed-off-by: Helen Koike <helen.koike@collabora.co.uk>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Keith Busch <keith.busch@intel.com>

nvme/pci: Don't set reserved SQ create flags

The QPRIO field is only valid if weighted round robin arbitration is used,
and this driver doesn't enable that controller configuration option.

Signed-off-by: Keith Busch <keith.busch@intel.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>

blk-stat: kill blk_stat_rq_ddir()

No point in providing and exporting this helper. There's just
one (real) user of it, just use rq_data_dir().

Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@fb.com>

nbd: set the max segments to USHRT_MAX

I lack the basic understanding of what segments mean, so we were being
limited to 512kib requests even with higher max_sectors sizes set.
Setting the maximum number of segments to unlimited allows us to
actually have arbitrarily large IO's go through NBD.

Signed-off-by: Josef Bacik <jbacik@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>

blk-mq: Remove blk_mq_sched_move_to_dispatch()

commit c13660a08c8b ("blk-mq-sched: change ->dispatch_requests()
to ->dispatch_request()") removed the last user of this function.
Hence also remove the function itself.

Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Cc: Omar Sandoval <osandov@fb.com>
Cc: Hannes Reinecke <hare@suse.com>
Signed-off-by: Jens Axboe <axboe@fb.com>

blk-mq: add might_sleep check to blk_mq_get_driver_tag()

If the caller passes in wait=true, it has to be able to block
for a driver tag. We just had a bug where flush insertion
would block on tag allocation, while we had preempt disabled.
Ensure that we catch cases like that earlier next time.

Reviewed-by: Bart Van Assche <Bart.VanAssche@sandisk.com>
Signed-off-by: Jens Axboe <axboe@fb.com>

blk-mq: Fix poll_stat for new size-based bucketing.

Fixes an issue where the size of the poll_stat array in request_queue
does not match the size expected by the new size based bucketing for
IO completion polling.

Fixes: 720b8ccc4500 ("blk-mq: Add a polling specific stats function")
Signed-off-by: Stephen Bates <sbates@raithlin.com>
Signed-off-by: Jens Axboe <axboe@fb.com>

blk-mq: fix schedule-while-atomic with scheduler attached

We must have dropped the ctx before we call
blk_mq_sched_insert_request() with can_block=true, otherwise we risk
that a flush request can block on insertion if we are currently out of
tags.

[   47.667190] BUG: scheduling while atomic: jbd2/sda2-8/2089/0x00000002
[   47.674493] Modules linked in: x86_pkg_temp_thermal btrfs xor zlib_deflate raid6_pq sr_mod cdre
[   47.690572] Preemption disabled at:
[   47.690584] [<ffffffff81326c7c>] blk_mq_sched_get_request+0x6c/0x280
[   47.701764] CPU: 1 PID: 2089 Comm: jbd2/sda2-8 Not tainted 4.11.0-rc7+ #271
[   47.709630] Hardware name: Dell Inc. PowerEdge T630/0NT78X, BIOS 2.3.4 11/09/2016
[   47.718081] Call Trace:
[   47.720903]  dump_stack+0x4f/0x73
[   47.724694]  ? blk_mq_sched_get_request+0x6c/0x280
[   47.730137]  __schedule_bug+0x6c/0xc0
[   47.734314]  __schedule+0x559/0x780
[   47.738302]  schedule+0x3b/0x90
[   47.741899]  io_schedule+0x11/0x40
[   47.745788]  blk_mq_get_tag+0x167/0x2a0
[   47.750162]  ? remove_wait_queue+0x70/0x70
[   47.754901]  blk_mq_get_driver_tag+0x92/0xf0
[   47.759758]  blk_mq_sched_insert_request+0x134/0x170
[   47.765398]  ? blk_account_io_start+0xd0/0x270
[   47.770679]  blk_mq_make_request+0x1b2/0x850
[   47.775766]  generic_make_request+0xf7/0x2d0
[   47.780860]  submit_bio+0x5f/0x120
[   47.784979]  ? submit_bio+0x5f/0x120
[   47.789631]  submit_bh_wbc.isra.46+0x10d/0x130
[   47.794902]  submit_bh+0xb/0x10
[   47.798719]  journal_submit_commit_record+0x190/0x210
[   47.804686]  ? _raw_spin_unlock+0x13/0x30
[   47.809480]  jbd2_journal_commit_transaction+0x180a/0x1d00
[   47.815925]  kjournald2+0xb6/0x250
[   47.820022]  ? kjournald2+0xb6/0x250
[   47.824328]  ? remove_wait_queue+0x70/0x70
[   47.829223]  kthread+0x10e/0x140
[   47.833147]  ? commit_timeout+0x10/0x10
[   47.837742]  ? kthread_create_on_node+0x40/0x40
[   47.843122]  ret_from_fork+0x29/0x40

Fixes: a4d907b6a33b ("blk-mq: streamline blk_mq_make_request")
Reviewed-by: Omar Sandoval <osandov@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>

blk-mq: Add a polling specific stats function

Rather than bucketing IO statisics based on direction only we also
bucket based on the IO size. This leads to improved polling
performance. Update the bucket callback function and use it in the
polling latency estimation.

Signed-off-by: Stephen Bates <sbates@raithlin.com>
Signed-off-by: Jens Axboe <axboe@fb.com>

blk-stat: convert blk-stat bucket callback to signed

In order to allow for filtering of IO based on some other properties
of the request than direction we allow the bucket function to return
an int.

If the bucket callback returns a negative do no count it in the stats
accumulation.

Signed-off-by: Stephen Bates <sbates@raithlin.com>
Fixed up Kyber scheduler stat callback.

Signed-off-by: Jens Axboe <axboe@fb.com>

block: remove the errors field from struct request

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Bart Van Assche <Bart.VanAssche@sandisk.com>
Acked-by: Roger Pau Monné <roger.pau@citrix.com>
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: Jens Axboe <axboe@fb.com>

blktrace: remove the unused block_rq_abort tracepoint

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: Jens Axboe <axboe@fb.com>

swim3: remove (commented out) printing of req->errors

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: Jens Axboe <axboe@fb.com>

ataflop: switch from req->errors to req->error_count

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

floppy: switch from req->errors to req->error_count

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

block: add a error_count field to struct request

This is for the legacy floppy and ataflop drivers that currently abuse
->errors for this purpose.  It's stashed away in a union to not grow
the struct size, the other fields are either used by modern drivers
for different purposes or the I/O scheduler before queing the I/O
to drivers.

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

blk-mq: simplify __blk_mq_complete_request

Merge blk_mq_ipi_complete_request and blk_mq_stat_add into their only
caller.

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

blk-mq: remove the error argument to blk_mq_complete_request

Now that all drivers that call blk_mq_complete_requests have a
->complete callback we can remove the direct call to blk_mq_end_request,
as well as the error argument to blk_mq_complete_request.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Reviewed-by: Bart Van Assche <Bart.VanAssche@sandisk.com>
Signed-off-by: Jens Axboe <axboe@fb.com>

xen-blkfront: don't use req->errors

xen-blkfron is the last users using rq->errros for passing back error to
blk-mq, and I'd like to get rid of that.  In the longer run the driver
should be moving more of the completion processing into .complete, but
this is the minimal change to move forward for now.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Roger Pau Monné <roger.pau@citrix.com>
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: Jens Axboe <axboe@fb.com>

mtip32xx: add a status field to struct mtip_cmd

Instead of using req->errors, which will go away.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: Jens Axboe <axboe@fb.com>

nbd: don't use req->errors

Add a nbd-specific field instead.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Josef Bacik <jbacik@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>

dm mpath: don't check for req->errors

We'll get all proper errors reported through ->end_io and ->errors will
go away soon.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: Jens Axboe <axboe@fb.com>

dm rq: don't pass irrelevant error code to blk_mq_complete_request

dm never uses rq->errors, so there is no need to pass an error argument
to blk_mq_complete_request.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Reviewed-by: Bart Van Assche <Bart.VanAssche@sandisk.com>
Signed-off-by: Jens Axboe <axboe@fb.com>

null_blk: don't pass always-0 req->errors to blk_mq_complete_request

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: Jens Axboe <axboe@fb.com>

loop: zero-fill bio on the submitting cpu

In thruth I've just audited which blk-mq drivers don't currently have a
complete callback, but I think this change is at least borderline useful.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@fb.com>

scsi: introduce a result field in struct scsi_request

This passes on the scsi_cmnd result field to users of passthrough
requests.  Currently we abuse req->errors for this purpose, but that
field will go away in its current form.

Note that the old IDE code abuses the errors field in very creative
ways and stores all kinds of different values in it.  I didn't dare
to touch this magic, so the abuses are brought forward 1:1.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Bart Van Assche <Bart.VanAssche@sandisk.com>
Signed-off-by: Jens Axboe <axboe@fb.com>

virtio_blk: don't use req->errors

Remove passing req->errors (which at that point is always 0) to
blk_mq_complete_request, and rely on the virtio status code for the
serial number passthrough request.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: Jens Axboe <axboe@fb.com>

virtio: fix spelling of virtblk_scsi_request_done

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Reviewed-by: Bart Van Assche <Bart.VanAssche@sandisk.com>
Signed-off-by: Jens Axboe <axboe@fb.com>

nvme: make nvme_error_status private

Currently it's used by the lighnvm passthrough ioctl, but we'd like to make
it private in preparation of block layer specific error code.  Lighnvm already
returns the real NVMe status anyway, so I think we can just limit it to
returning -EIO for any status set.

This will need a careful audit from the lightnvm folks, though.

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

nvme: split nvme status from block req->errors

We want our own clearly defined error field for NVMe passthrough commands,
and the request errors field is going away in its current form.

Just store the status and result field in the nvme_request field from
hardirq completion context (using a new helper) and then generate a
Linux errno for the block layer only when we actually need it.

Because we can't overload the status value with a negative error code
for cancelled command we now have a flags filed in struct nvme_request
that contains a bit for this condition.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: Jens Axboe <axboe@fb.com>

nvme-fc: fix status code handling in nvme_fc_fcpio_done

nvme_complete_async_event expects the little endian status code
including the phase bit, and a new completion handler I plan to
introduce will do so as well.

Change the status variable into the little endian format with the
phase bit used in the NVMe CQE to fix / enable this.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: Jens Axboe <axboe@fb.com>

block: remove the blk_execute_rq return value

The function only returns -EIO if rq->errors is non-zero, which is not
very useful and lets a large number of callers ignore the return value.

Just let the callers figure out their error themselves.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Reviewed-by: Bart Van Assche <Bart.VanAssche@sandisk.com>
Signed-off-by: Jens Axboe <axboe@fb.com>

pd: don't check blk_execute_rq return value.

The driver never sets req->errors, so blk_execute_rq will always return 0.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Bart Van Assche <Bart.VanAssche@sandisk.com>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: Jens Axboe <axboe@fb.com>

bdi: Drop 'parent' argument from bdi_register[_va]()

Drop 'parent' argument of bdi_register() and bdi_register_va().  It is
always NULL.

Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Jens Axboe <axboe@fb.com>

block: Remove unused functions

Now that all backing_dev_info structure are allocated separately, we can
drop some unused functions.

Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Jens Axboe <axboe@fb.com>

fs: Remove SB_I_DYNBDI flag

Now that all bdi structures filesystems use are properly refcounted, we
can remove the SB_I_DYNBDI flag.

Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Jens Axboe <axboe@fb.com>

ubifs: Convert to separately allocated bdi

Allocate struct backing_dev_info separately instead of embedding it
inside the superblock. This unifies handling of bdi among users.

CC: Richard Weinberger <richard@nod.at>
CC: Artem Bityutskiy <dedekind1@gmail.com>
CC: Adrian Hunter <adrian.hunter@intel.com>
CC: linux-mtd@lists.infradead.org
Acked-by: Richard Weinberger <richard@nod.at>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Jens Axboe <axboe@fb.com>

nfs: Convert to separately allocated bdi

Allocate struct backing_dev_info separately instead of embedding it
inside the superblock. This unifies handling of bdi among users.

CC: Anna Schumaker <anna.schumaker@netapp.com>
CC: linux-nfs@vger.kernel.org
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jan Kara <jack@suse.cz>
Acked-by: Trond Myklebust <trond.myklebust@primarydata.com>
Signed-off-by: Jens Axboe <axboe@fb.com>

ncpfs: Convert to separately allocated bdi

Allocate struct backing_dev_info separately instead of embedding it
inside the superblock. This unifies handling of bdi among users.

CC: Petr Vandrovec <petr@vandrovec.name>
Acked-by: Petr Vandrovec <petr@vandrovec.name>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Jens Axboe <axboe@fb.com>

nilfs2: Convert to properly refcounting bdi

Similarly to set_bdev_super() NILFS2 just used block device reference to
bdi. Convert it to properly getting bdi reference. The reference will
get automatically dropped on superblock destruction.

CC: linux-nilfs@vger.kernel.org
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jan Kara <jack@suse.cz>
Acked-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
Signed-off-by: Jens Axboe <axboe@fb.com>

gfs2: Convert to properly refcounting bdi

Similarly to set_bdev_super() GFS2 just used block device reference to
bdi. Convert it to properly getting bdi reference. The reference will
get automatically dropped on superblock destruction.

CC: Steven Whitehouse <swhiteho@redhat.com>
CC: Bob Peterson <rpeterso@redhat.com>
CC: cluster-devel@redhat.com
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Jens Axboe <axboe@fb.com>

fuse: Get rid of bdi_initialized

It is not needed anymore since bdi is initialized whenever superblock
exists.

CC: Miklos Szeredi <miklos@szeredi.hu>
CC: linux-fsdevel@vger.kernel.org
Suggested-by: Miklos Szeredi <mszeredi@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Jens Axboe <axboe@fb.com>

fuse: Convert to separately allocated bdi

Allocate struct backing_dev_info separately instead of embedding it
inside the superblock. This unifies handling of bdi among users.

CC: Miklos Szeredi <miklos@szeredi.hu>
CC: linux-fsdevel@vger.kernel.org
Acked-by: Miklos Szeredi <mszeredi@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Jens Axboe <axboe@fb.com>

exofs: Convert to separately allocated bdi

Allocate struct backing_dev_info separately instead of embedding it
inside the superblock. This unifies handling of bdi among users.

CC: Boaz Harrosh <ooo@electrozaur.com>
CC: Benny Halevy <bhalevy@primarydata.com>
Acked-by: Boaz Harrosh <ooo@electrozaur.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Jens Axboe <axboe@fb.com>

coda: Convert to separately allocated bdi

Allocate struct backing_dev_info separately instead of embedding it
inside the superblock. This unifies handling of bdi among users.

CC: Jan Harkes <jaharkes@cs.cmu.edu>
CC: coda@cs.cmu.edu
CC: codalist@coda.cs.cmu.edu
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Jens Axboe <axboe@fb.com>

mtd: Convert to dynamically allocated bdi infrastructure

MTD already allocates backing_dev_info dynamically. Convert it to use
generic infrastructure for this including proper refcounting. We drop
mtd->backing_dev_info as its only use was to pass mtd_bdi pointer from
one file into another and if we wanted to keep that in a clean way, we'd
have to make mtd hold and drop bdi reference as needed which seems
pointless for passing one global pointer...

CC: David Woodhouse <dwmw2@infradead.org>
CC: Brian Norris <computersforpeace@gmail.com>
CC: linux-mtd@lists.infradead.org
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Jens Axboe <axboe@fb.com>

afs: Convert to separately allocated bdi

Allocate struct backing_dev_info separately instead of embedding it
inside the superblock. This unifies handling of bdi among users.

CC: David Howells <dhowells@redhat.com>
CC: linux-afs@lists.infradead.org
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Jens Axboe <axboe@fb.com>

ecryptfs: Convert to separately allocated bdi

Allocate struct backing_dev_info separately instead of embedding it
inside the superblock. This unifies handling of bdi among users.

CC: Tyler Hicks <tyhicks@canonical.com>
CC: ecryptfs@vger.kernel.org
Acked-by: Tyler Hicks <tyhicks@canonical.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Jens Axboe <axboe@fb.com>

cifs: Convert to separately allocated bdi

Allocate struct backing_dev_info separately instead of embedding it
inside superblock. This unifies handling of bdi among users.

CC: Steve French <sfrench@samba.org>
CC: linux-cifs@vger.kernel.org
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Jens Axboe <axboe@fb.com>

ceph: Convert to separately allocated bdi

Allocate struct backing_dev_info separately instead of embedding it
inside client structure. This unifies handling of bdi among users.

CC: Ilya Dryomov <idryomov@gmail.com>
CC: "Yan, Zheng" <zyan@redhat.com>
CC: Sage Weil <sage@redhat.com>
CC: ceph-devel@vger.kernel.org
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Jens Axboe <axboe@fb.com>

btrfs: Convert to separately allocated bdi

Allocate struct backing_dev_info separately instead of embedding it
inside superblock. This unifies handling of bdi among users.

CC: Chris Mason <clm@fb.com>
CC: Josef Bacik <jbacik@fb.com>
CC: David Sterba <dsterba@suse.com>
CC: linux-btrfs@vger.kernel.org
Reviewed-by: Liu Bo <bo.li.liu@oracle.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Jens Axboe <axboe@fb.com>

9p: Convert to separately allocated bdi

Allocate struct backing_dev_info separately instead of embedding it
inside session. This unifies handling of bdi among users.

CC: Eric Van Hensbergen <ericvh@gmail.com>
CC: Ron Minnich <rminnich@sandia.gov>
CC: Latchesar Ionkov <lucho@ionkov.net>
CC: v9fs-developer@lists.sourceforge.net
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Jens Axboe <axboe@fb.com>

lustre: Convert to separately allocated bdi

Allocate struct backing_dev_info separately instead of embedding it
inside superblock. This unifies handling of bdi among users.

CC: Oleg Drokin <oleg.drokin@intel.com>
CC: Andreas Dilger <andreas.dilger@intel.com>
CC: James Simmons <jsimmons@infradead.org>
CC: lustre-devel@lists.lustre.org
Reviewed-by: Andreas Dilger <andreas.dilger@intel.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Jens Axboe <axboe@fb.com>

fs: Get proper reference for s_bdi

So far we just relied on block device to hold a bdi reference for us
while the filesystem is mounted. While that works perfectly fine, it is
a bit awkward that we have a pointer to a refcounted structure in the
superblock without proper reference. So make s_bdi hold a proper
reference to block device's BDI. No filesystem using mount_bdev()
actually changes s_bdi so this is safe and will make bdev filesystems
work the same way as filesystems needing to set up their private bdi.

Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Jens Axboe <axboe@fb.com>

fs: Provide infrastructure for dynamic BDIs in filesystems

Provide helper functions for setting up dynamically allocated
backing_dev_info structures for filesystems and cleaning them up on
superblock destruction.

CC: linux-mtd@lists.infradead.org
CC: linux-nfs@vger.kernel.org
CC: Petr Vandrovec <petr@vandrovec.name>
CC: linux-nilfs@vger.kernel.org
CC: cluster-devel@redhat.com
CC: osd-dev@open-osd.org
CC: codalist@coda.cs.cmu.edu
CC: linux-afs@lists.infradead.org
CC: ecryptfs@vger.kernel.org
CC: linux-cifs@vger.kernel.org
CC: ceph-devel@vger.kernel.org
CC: linux-btrfs@vger.kernel.org
CC: v9fs-developer@lists.sourceforge.net
CC: lustre-devel@lists.lustre.org
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Jens Axboe <axboe@fb.com>

bdi: Export bdi_alloc_node() and bdi_put()

MTD will want to call bdi_alloc_node() and bdi_put() directly. Export
these functions.

Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Jens Axboe <axboe@fb.com>

block: Unregister bdi on last reference drop

Most users will want to unregister bdi when dropping last reference to a
bdi. Only a few users (like block devices) want to play more complex
tricks with bdi registration and unregistration. So unregister bdi when
the last reference to bdi is dropped and just make sure we don't
unregister the bdi the second time if it is already unregistered.

Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Jens Axboe <axboe@fb.com>

bdi: Provide bdi_register_va() and bdi_alloc()

Add function that registers bdi and takes va_list instead of variable
number of arguments.

Add bdi_alloc() as simple wrapper for NUMA-unaware users allocating BDI.

Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Jens Axboe <axboe@fb.com>

blk-throttle: fix unused variable warning with BLK_DEV_THROTTLING_LOW=n

We trigger this warning:

block/blk-throttle.c: In function ‘blk_throtl_bio’:
block/blk-throttle.c:2042:6: warning: variable ‘ret’ set but not used [-Wunused-but-set-variable]
  int ret;
      ^~~

since we only assign 'ret' if BLK_DEV_THROTTLING_LOW is off, we never
check it.

Reported-by: Bart Van Assche <bart.vanassche@sandisk.com>
Reviewed-by: Bart Van Assche <bart.vanassche@sandisk.com>
Signed-off-by: Jens Axboe <axboe@fb.com>

bfq: fix compile error if CONFIG_CGROUPS=n

If we don't have CGROUPS enabled, the compile ends in the
following misery:

In file included from ../block/bfq-iosched.c:105:0:
../block/bfq-iosched.h:819:22: error: array type has incomplete element type
 extern struct cftype bfq_blkcg_legacy_files[];
                      ^
../block/bfq-iosched.h:820:22: error: array type has incomplete element type
 extern struct cftype bfq_blkg_files[];
                      ^

Move the declarations under the right ifdef.

Reported-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Jens Axboe <axboe@fb.com>

block, bfq: don't dereference bic before null checking it

The call to bfq_check_ioprio_change will dereference bic, however,
the null check for bic is after this call.  Move the the null
check on bic to before the call to avoid any potential null
pointer dereference issues.

Detected by CoverityScan, CID#1430138 ("Dereference before null check")

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Jens Axboe <axboe@fb.com>

ligtnvm: fix double blk_put_queue on same queue

On an error path in NVM_DEV_CREATE ioctl blk_put_queue is being called
twice: one via blk_cleanup_queue and another via put_disk.  Straight fix
seems to remove queue pointer so that disk_release never ends up caling
blk_put_queue again.

  [  391.808827] WARNING: CPU: 1 PID: 1250 at lib/refcount.c:128 refcount_sub_and_test+0x70/0x80
  [  391.808830] refcount_t: underflow; use-after-free.
  [ 391.808832] Modules linked in: nf_conntrack_netbios_ns............
  [  391.809052] CPU: 1 PID: 1250 Comm: nvme Not tainted.........
  [  391.809057] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996),
             BIOS rel-1.7.5-0-ge51488c-20140602_164612-nilsson.home.kraxel.org 04/01/2014
  [  391.809060] Call Trace:
  [  391.809079]  dump_stack+0x63/0x86
  [  391.809094]  __warn+0xcb/0xf0
  [  391.809103]  warn_slowpath_fmt+0x5f/0x80
  [  391.809118]  refcount_sub_and_test+0x70/0x80
  [  391.809125]  refcount_dec_and_test+0x11/0x20
  [  391.809136]  kobject_put+0x1f/0x60
  [  391.809149]  blk_put_queue+0x15/0x20
  [  391.809159]  disk_release+0xae/0xf0
  [  391.809172]  device_release+0x32/0x90
  [  391.809184]  kobject_release+0x6a/0x170
  [  391.809196]  kobject_put+0x2f/0x60
  [  391.809206]  put_disk+0x17/0x20
  [  391.809219]  nvm_ioctl_dev_create.isra.16+0x897/0xa30
  [  391.809236]  nvm_ctl_ioctl+0x23c/0x4c0
  [  391.809248]  do_vfs_ioctl+0xa3/0x5f0
  [  391.809258]  SyS_ioctl+0x79/0x90
  [  391.809271]  entry_SYSCALL_64_fastpath+0x1a/0xa9
  [  391.809280] RIP: 0033:0x7f5d3ef363c7
  [  391.809286] RSP: 002b:00007ffc72ed8d78 EFLAGS: 00000206 ORIG_RAX: 0000000000000010
  [  391.809296] RAX: ffffffffffffffda RBX: 00007ffc72edb552 RCX: 00007f5d3ef363c7
  [  391.809301] RDX: 00007ffc72ed8d90 RSI: 0000000040804c22 RDI: 0000000000000003
  [  391.809306] RBP: 0000000000000001 R08: 0000000000000020 R09: 0000000000000001
  [  391.809311] R10: 000000000000053f R11: 0000000000000206 R12: 0000000000000000
  [  391.809316] R13: 0000000000000000 R14: 00007ffc72edb58d R15: 00007ffc72edb581

Signed-off-by: Rakesh Pandit <rakesh@tuxera.com>
Reviewed-by: Matias Bjørling <matias@cnexlabs.com>
Fixes: 7d1ef2f408ab "lightnvm: fix cleanup order of disk on init error"
Signed-off-by: Jens Axboe <axboe@fb.com>

block: Optimize ioprio_best()

Since ioprio_best() translates IOPRIO_CLASS_NONE into IOPRIO_CLASS_BE
and since lower numerical priority values represent a higher priority
a simple numerical comparison is sufficient.

Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Reviewed-by: Adam Manzanares <adam.manzanares@wdc.com>
Tested-by: Adam Manzanares <adam.manzanares@wdc.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Cc: Matias Bjørling <m@bjorling.me>
Signed-off-by: Jens Axboe <axboe@fb.com>

block: Inline blk_rq_set_prio()

Since only a single caller remains, inline blk_rq_set_prio(). Initialize
req->ioprio even if no I/O priority has been set in the bio nor in the
I/O context.

Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Reviewed-by: Adam Manzanares <adam.manzanares@wdc.com>
Tested-by: Adam Manzanares <adam.manzanares@wdc.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Cc: Matias Bjørling <m@bjorling.me>
Signed-off-by: Jens Axboe <axboe@fb.com>

lightnvm: Use blk_init_request_from_bio() instead of open-coding it

This patch changes the behavior of the lightnvm driver as follows:
* REQ_FAILFAST_MASK is set for read-ahead requests.
* If no I/O priority has been set in the bio, the I/O priority is
  copied from the I/O context.
* The rq_disk member is initialized if bio->bi_bdev != NULL.
* The bio sector offset is copied into req->__sector instead of
  retaining the value -1 set by blk_mq_alloc_request().
* req->errors is initialized to zero.

Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Cc: Matias Bjørling <m@bjorling.me>
Cc: Adam Manzanares <adam.manzanares@wdc.com>
Signed-off-by: Jens Axboe <axboe@fb.com>

null_blk: Use blk_init_request_from_bio() instead of open-coding it

This patch changes the behavior of the null_blk driver for the
LightNVM mode as follows:
* REQ_FAILFAST_MASK is set for read-ahead requests.
* If no I/O priority has been set in the bio, the I/O priority is
  copied from the I/O context.
* The rq_disk member is initialized if bio->bi_bdev != NULL.
* req->errors is initialized to zero.

Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Cc: Matias Bjørling <m@bjorling.me>
Cc: Adam Manzanares <adam.manzanares@wdc.com>
Signed-off-by: Jens Axboe <axboe@fb.com>

block: Export blk_init_request_from_bio()

Export this function such that it becomes available to block
drivers.

Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Cc: Matias Bjørling <m@bjorling.me>
Cc: Adam Manzanares <adam.manzanares@wdc.com>
Signed-off-by: Jens Axboe <axboe@fb.com>

lightnvm: assume 64-bit lba numbers

The driver uses both u64 and sector_t to refer to offsets, and assigns between the
two. This causes one harmless warning when sector_t is 32-bit:

drivers/lightnvm/pblk-rb.c: In function 'pblk_rb_write_entry_gc':
include/linux/lightnvm.h:215:20: error: large integer implicitly truncated to unsigned type [-Werror=overflow]
drivers/lightnvm/pblk-rb.c:324:22: note: in expansion of macro 'ADDR_EMPTY'

As the driver is already doing this inconsistently, changing the type
won't make it worse and is an easy way to avoid the warning.

Fixes: a4bd217b4326 ("lightnvm: physical block device (pblk) target")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Jens Axboe <axboe@fb.com>

block: make __blk_end_bidi_request private

blk_insert_flush should be using __blk_end_request to start with.

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

block: remove blk_end_request_cur

This function is not used anywhere in the kernel.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: Jens Axboe <axboe@fb.com>

block: remove blk_end_request_err and __blk_end_request_err

Both functions are entirely unused.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: Jens Axboe <axboe@fb.com>

block: remove the osdblk driver

This was just a proof of concept user for the SCSI OSD library, and
never had any real users.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Boaz Harrosh <ooo@electrozaur.com>
Signed-off-by: Jens Axboe <axboe@fb.com>

block: Make writeback throttling defaults consistent for SQ devices

When CFQ is used as an elevator, it disables writeback throttling
because they don't play well together. Later when a different elevator
is chosen for the device, writeback throttling doesn't get enabled
again as it should. Make sure CFQ enables writeback throttling (if it
should be enabled by default) when we switch from it to another IO
scheduler.

Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Jens Axboe <axboe@fb.com>

block, bfq: split bfq-iosched.c into multiple source files

The BFQ I/O scheduler features an optimal fair-queuing
(proportional-share) scheduling algorithm, enriched with several
mechanisms to boost throughput and reduce latency for interactive and
real-time applications. This makes BFQ a large and complex piece of
code. This commit addresses this issue by splitting BFQ into three
main, independent components, and by moving each component into a
separate source file:
1. Main algorithm: handles the interaction with the kernel, and
decides which requests to dispatch; it uses the following two further
components to achieve its goals.
2. Scheduling engine (Hierarchical B-WF2Q+ scheduling algorithm):
computes the schedule, using weights and budgets provided by the above
component.
3. cgroups support: handles group operations (creation, destruction,
move, ...).

Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Signed-off-by: Jens Axboe <axboe@fb.com>

block, bfq: remove all get and put of I/O contexts

When a bfq queue is set in service and when it is merged, a reference
to the I/O context associated with the queue is taken. This reference
is then released when the queue is deselected from service or
split. More precisely, the release of the reference is postponed to
when the scheduler lock is released, to avoid nesting between the
scheduler and the I/O-context lock. In fact, such nesting would lead
to deadlocks, because of other code paths that take the same locks in
the opposite order. This postponing of I/O-context releases does
complicate code.

This commit addresses these issue by modifying involved operations in
such a way to not need to get the above I/O-context references any
more. Then it also removes any get and release of these references.

Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Signed-off-by: Jens Axboe <axboe@fb.com>

block, bfq: handle bursts of queue activations

Many popular I/O-intensive services or applications spawn or
reactivate many parallel threads/processes during short time
intervals. Examples are systemd during boot or git grep.  These
services or applications benefit mostly from a high throughput: the
quicker the I/O generated by their processes is cumulatively served,
the sooner the target job of these services or applications gets
completed. As a consequence, it is almost always counterproductive to
weight-raise any of the queues associated to the processes of these
services or applications: in most cases it would just lower the
throughput, mainly because weight-raising also implies device idling.

To address this issue, an I/O scheduler needs, first, to detect which
queues are associated with these services or applications. In this
respect, we have that, from the I/O-scheduler standpoint, these
services or applications cause bursts of activations, i.e.,
activations of different queues occurring shortly after each
other. However, a shorter burst of activations may be caused also by
the start of an application that does not consist in a lot of parallel
I/O-bound threads (see the comments on the function bfq_handle_burst
for details).

In view of these facts, this commit introduces:
1) an heuristic to detect (only) bursts of queue activations caused by
   services or applications consisting in many parallel I/O-bound
   threads;
2) the prevention of device idling and weight-raising for the queues
   belonging to these bursts.

Signed-off-by: Arianna Avanzini <avanzini.arianna@gmail.com>
Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Signed-off-by: Jens Axboe <axboe@fb.com>

block, bfq: boost the throughput with random I/O on NCQ-capable HDDs

This patch is basically the counterpart, for NCQ-capable rotational
devices, of the previous patch. Exactly as the previous patch does on
flash-based devices and for any workload, this patch disables device
idling on rotational devices, but only for random I/O. In fact, only
with these queues disabling idling boosts the throughput on
NCQ-capable rotational devices. To not break service guarantees,
idling is disabled for NCQ-enabled rotational devices only when the
same symmetry conditions considered in the previous patches hold.

Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Signed-off-by: Arianna Avanzini <avanzini.arianna@gmail.com>
Signed-off-by: Jens Axboe <axboe@fb.com>

block, bfq: boost the throughput on NCQ-capable flash-based devices

This patch boosts the throughput on NCQ-capable flash-based devices,
while still preserving latency guarantees for interactive and soft
real-time applications. The throughput is boosted by just not idling
the device when the in-service queue remains empty, even if the queue
is sync and has a non-null idle window. This helps to keep the drive's
internal queue full, which is necessary to achieve maximum
performance. This solution to boost the throughput is a port of
commits a68bbdd and f7d7b7a for CFQ.

As already highlighted in a previous patch, allowing the device to
prefetch and internally reorder requests trivially causes loss of
control on the request service order, and hence on service guarantees.
Fortunately, as discussed in detail in the comments on the function
bfq_bfqq_may_idle(), if every process has to receive the same
fraction of the throughput, then the service order enforced by the
internal scheduler of a flash-based device is relatively close to that
enforced by BFQ. In particular, it is close enough to let service
guarantees be substantially preserved.

Things change in an asymmetric scenario, i.e., if not every process
has to receive the same fraction of the throughput. In this case, to
guarantee the desired throughput distribution, the device must be
prevented from prefetching requests. This is exactly what this patch
does in asymmetric scenarios.

Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Signed-off-by: Arianna Avanzini <avanzini.arianna@gmail.com>
Signed-off-by: Jens Axboe <axboe@fb.com>

block, bfq: reduce idling only in symmetric scenarios

A seeky queue (i..e, a queue containing random requests) is assigned a
very small device-idling slice, for throughput issues. Unfortunately,
given the process associated with a seeky queue, this behavior causes
the following problem: if the process, say P, performs sync I/O and
has a higher weight than some other processes doing I/O and associated
with non-seeky queues, then BFQ may fail to guarantee to P its
reserved share of the throughput. The reason is that idling is key
for providing service guarantees to processes doing sync I/O [1].

This commit addresses this issue by allowing the device-idling slice
to be reduced for a seeky queue only if the scenario happens to be
symmetric, i.e., if all the queues are to receive the same share of
the throughput.

[1] P. Valente, A. Avanzini, "Evolution of the BFQ Storage I/O
    Scheduler", Proceedings of the First Workshop on Mobile System
    Technologies (MST-2015), May 2015.
    http://algogroup.unimore.it/people/paolo/disk_sched/mst-2015.pdf

Signed-off-by: Arianna Avanzini <avanzini.arianna@gmail.com>
Signed-off-by: Riccardo Pizzetti <riccardo.pizzetti@gmail.com>
Signed-off-by: Samuele Zecchini <samuele.zecchini92@gmail.com>
Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Signed-off-by: Jens Axboe <axboe@fb.com>