nvme: track subsystems

This adds a new nvme_subsystem structure so that we can track multiple
controllers that belong to a single subsystem.  For now we only use it
to store the NQN, and to check that we don't have duplicate NQNs unless
the involved subsystems support multiple controllers.

Includes code originally from Hannes Reinecke to expose the subsystems
in sysfs.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Keith Busch <keith.busch@intel.com>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

block, nvme: Introduce blk_mq_req_flags_t

Several block layer and NVMe core functions accept a combination
of BLK_MQ_REQ_* flags through the 'flags' argument but there is
no verification at compile time whether the right type of block
layer flags is passed. Make it possible for sparse to verify this.
This patch does not change any functionality.

Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Tested-by: Oleksandr Natalenko <oleksandr@natalenko.name>
Cc: linux-nvme@lists.infradead.org
Cc: Christoph Hellwig <hch@lst.de>
Cc: Johannes Thumshirn <jthumshirn@suse.de>
Cc: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

block, scsi: Make SCSI quiesce and resume work reliably

The contexts from which a SCSI device can be quiesced or resumed are:
* Writing into /sys/class/scsi_device/*/device/state.
* SCSI parallel (SPI) domain validation.
* The SCSI device power management methods. See also scsi_bus_pm_ops.

It is essential during suspend and resume that neither the filesystem
state nor the filesystem metadata in RAM changes. This is why while
the hibernation image is being written or restored that SCSI devices
are quiesced. The SCSI core quiesces devices through scsi_device_quiesce()
and scsi_device_resume(). In the SDEV_QUIESCE state execution of
non-preempt requests is deferred. This is realized by returning
BLKPREP_DEFER from inside scsi_prep_state_check() for quiesced SCSI
devices. Avoid that a full queue prevents power management requests
to be submitted by deferring allocation of non-preempt requests for
devices in the quiesced state. This patch has been tested by running
the following commands and by verifying that after each resume the
fio job was still running:

for ((i=0; i<10; i++)); do
  (
    cd /sys/block/md0/md &&
    while true; do
      [ "$(<sync_action)" = "idle" ] && echo check > sync_action
      sleep 1
    done
  ) &
  pids=($!)
  for d in /sys/class/block/sd*[a-z]; do
    bdev=${d#/sys/class/block/}
    hcil=$(readlink "$d/device")
    hcil=${hcil#../../../}
    echo 4 > "$d/queue/nr_requests"
    echo 1 > "/sys/class/scsi_device/$hcil/device/queue_depth"
    fio --name="$bdev" --filename="/dev/$bdev" --buffered=0 --bs=512 \
      --rw=randread --ioengine=libaio --numjobs=4 --iodepth=16       \
      --iodepth_batch=1 --thread --loops=$((2**31)) &
    pids+=($!)
  done
  sleep 1
  echo "$(date) Hibernating ..." >>hibernate-test-log.txt
  systemctl hibernate
  sleep 10
  kill "${pids[@]}"
  echo idle > /sys/block/md0/md/sync_action
  wait
  echo "$(date) Done." >>hibernate-test-log.txt
done

Reported-by: Oleksandr Natalenko <oleksandr@natalenko.name>
References: "I/O hangs after resuming from suspend-to-ram" (https://marc.info/?l=linux-block&m=150340235201348).
Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Tested-by: Martin Steigerwald <martin@lichtvoll.de>
Tested-by: Oleksandr Natalenko <oleksandr@natalenko.name>
Cc: Martin K. Petersen <martin.petersen@oracle.com>
Cc: Ming Lei <ming.lei@redhat.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

block: Add the QUEUE_FLAG_PREEMPT_ONLY request queue flag

This flag will be used in the next patch to let the block layer
core know whether or not a SCSI request queue has been quiesced.
A quiesced SCSI queue namely only processes RQF_PREEMPT requests.

Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Tested-by: Martin Steigerwald <martin@lichtvoll.de>
Tested-by: Oleksandr Natalenko <oleksandr@natalenko.name>
Cc: Ming Lei <ming.lei@redhat.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

ide, scsi: Tell the block layer at request allocation time about preempt requests

Convert blk_get_request(q, op, __GFP_RECLAIM) into
blk_get_request_flags(q, op, BLK_MQ_PREEMPT). This patch does not
change any functionality.

Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Tested-by: Martin Steigerwald <martin@lichtvoll.de>
Acked-by: David S. Miller <davem@davemloft.net> [ for IDE ]
Acked-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Tested-by: Oleksandr Natalenko <oleksandr@natalenko.name>
Cc: Ming Lei <ming.lei@redhat.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

block: Introduce BLK_MQ_REQ_PREEMPT

Set RQF_PREEMPT if BLK_MQ_REQ_PREEMPT is passed to
blk_get_request_flags().

Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Tested-by: Martin Steigerwald <martin@lichtvoll.de>
Tested-by: Oleksandr Natalenko <oleksandr@natalenko.name>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Ming Lei <ming.lei@redhat.com>
Cc: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

block: Introduce blk_get_request_flags()

A side effect of this patch is that the GFP mask that is passed to
several allocation functions in the legacy block layer is changed
from GFP_KERNEL into __GFP_DIRECT_RECLAIM.

Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Tested-by: Martin Steigerwald <martin@lichtvoll.de>
Tested-by: Oleksandr Natalenko <oleksandr@natalenko.name>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Ming Lei <ming.lei@redhat.com>
Cc: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

block: Make q_usage_counter also track legacy requests

This patch makes it possible to pause request allocation for
the legacy block layer by calling blk_mq_freeze_queue() and
blk_mq_unfreeze_queue().

Signed-off-by: Ming Lei <ming.lei@redhat.com>
[ bvanassche: Combined two patches into one, edited a comment and made sure
  REQ_NOWAIT is handled properly in blk_old_get_request() ]
Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Tested-by: Martin Steigerwald <martin@lichtvoll.de>
Tested-by: Oleksandr Natalenko <oleksandr@natalenko.name>
Cc: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

blk-mq: fix issue with shared tag queue re-running

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

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

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

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

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

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

Ensure that we always re-run the hardware queue, if the driver tag we
were waiting for got freed before we added our leftover request entries
back on the dispatch list.

Reviewed-by: Bart Van Assche <bart.vanassche@wdc.com>
Tested-by: Bart Van Assche <bart.vanassche@wdc.com>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Reviewed-by: Omar Sandoval <osandov@fb.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

nvmet: kill nvmet_inline_bio_init

Much easier to just opencode this helper.  Also use ARRAY_SIZE instead of
passing the inline bvec array size manually.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Sagi Grimberg <sagi@rimberg.me>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

nvmet: better data length validation

Currently the NVMe target stores the expexted data length in req->data_len
and uses that for data transfer decisions, but that does not take the
actual transfer length in the SGLs into account.  So this adds a new
transfer_len field, into which the transport drivers store the actual
transfer length.  We then check the two match before actually executing
the command.

The FC transport driver already had such a field, which is removed in
favour of the common one.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

nvme-pci: avoid dereference of symbol from unloaded module

The 'remove_work' may be scheduled to run after nvme_remove()
returns since we can't simply cancel it in nvme_remove() for
avoiding deadlock. Once nvme_remove() returns, this module(nvme)
can be unloaded.

On the other hand, nvme_put_ctrl() calls ctr->ops->free_ctrl
which may point to nvme_pci_free_ctrl() in unloaded module.

This patch avoids this issue by queuing 'remove_work' via 'nvme_wq',
and flush this worqueue in nvme_exit() as suggested by Sagi.

Suggested-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Reviewed-by: Keith Busch <keith.busch@intel.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

nvme: send uevent for some asynchronous events

This will give udev a chance to observe and handle asynchronous event
notifications and clear the log to unmask future events of the same type.
The driver will create a change uevent of the asyncronuos event result
before submitting the next AEN request to the device if a completed AEN
event is of type error, smart, command set or vendor specific,

Signed-off-by: Keith Busch <keith.busch@intel.com>
Reviewed-by: Guan Junxiong <guanjunxiong@huawei.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

nvme: unexport starting async event work

Async event work is for core use only and should not be called directly
from drivers.

Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Keith Busch <keith.busch@intel.com>
Reviewed-by: Guan Junxiong <guanjunxiong@huawei.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

nvme: remove handling of multiple AEN requests

The driver can handle tracking only one AEN request, so this patch
removes handling for multiple ones.

Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: James Smart <james.smart@broadcom.com>
Signed-off-by: Keith Busch <keith.busch@intel.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

nvme-fc: remove unused "queue_size" field

This was being saved in a structure, but never used anywhere. The queue
size is obtained through other means, so there's no reason to duplicate
this without a user for it.

Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Keith Busch <keith.busch@intel.com>
Reviewed-by: Guan Junxiong <guanjunxiong@huawei.com>
Reviewed-by: James Smart <james.smart@broadcom.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

nvme: centralize AEN defines

All the transports were unnecessarilly duplicating the AEN request
accounting. This patch defines everything in one place.

Signed-off-by: Keith Busch <keith.busch@intel.com>
Reviewed-by: Guan Junxiong <guanjunxiong@huawei.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

nvmet: remove redundant local variable

the status is either success or some status id and
we don't need a local variable for it.

Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

nvmet: remove redundant memset if failed to get_smart_log failed

We already allocated the buffer with kzalloc.

Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

blk-mq: Avoid that request queue removal can trigger list corruption

Avoid that removal of a request queue sporadically triggers the
following warning:

list_del corruption. next->prev should be ffff8807d649b970, but was 6b6b6b6b6b6b6b6b
WARNING: CPU: 3 PID: 342 at lib/list_debug.c:56 __list_del_entry_valid+0x92/0xa0
Call Trace:
 process_one_work+0x11b/0x660
 worker_thread+0x3d/0x3b0
 kthread+0x129/0x140
 ret_from_fork+0x27/0x40

Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Hannes Reinecke <hare@suse.com>
Cc: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

nvme: fix eui_show() print format

Fix print formatting, but keep the original output to prevent user
breakage as suggested by Joe Perches.

Signed-off-by: Javier González <javier@cnexlabs.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Reviewed-by: Keith Busch <keith.busch@intel.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

nvme: compare NQN string with right size

Copy subnqns using NVMF_NQN_SIZE as it is < 256

Signed-off-by: Javier González <javier@cnexlabs.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

blk-mq: put driver tag if dispatch budget can't be got

We have to put the driver tag if dispatch budget can't be got, otherwise
it might cause IO deadlock, especially in case that size of tags is very
small.

Fixes: de1482974080(blk-mq: introduce .get_budget and .put_budget in blk_mq_ops)
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

block: pass full fmode_t to blk_verify_command

Use the obvious calling convention.

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

block: remove __bio_kmap_atomic

This helper doesn't buy us much over calling kmap_atomic directly.
In fact in the only caller it does a bit of useless work as the
caller already has the bvec at hand, and said caller would even
buggy for a multi-segment bio due to the use of this helper.

So just remove it.

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

block: kill bio_kmap/kunmap_irq()

There are no users of it anymore.

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

Revert "blk-mq: don't handle TAG_SHARED in restart"

This reverts commit 358a3a6bccb74da9d63a26b2dd5f09f1e9970e0b.

We have cases that aren't covered 100% in the drivers, so for now
we have to retain the shared tag restart loops.

Signed-off-by: Jens Axboe <axboe@kernel.dk>

kthread: zero the kthread data structure

kthread() could bail out early before we initialize blkcg_css (if the
kthread is killed very early. Please see xchg() statement in kthread()),
which confuses free_kthread_struct. Instead of moving the blkcg_css
initialization early, we simply zero the whole 'self' data structure,
which doesn't sound much overhead.

Reported-by: syzbot <syzkaller@googlegroups.com>
Fixes: 05e3db95ebfc ("kthread: add a mechanism to store cgroup info")
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Dmitry Vyukov <dvyukov@google.com>
Acked-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Shaohua Li <shli@fb.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

nvmet: fix comment typos in admin-cmd.c

small typos fixed in admin-cmd.c

Signed-off-by: Minwoo Im <minwoo.im.dev@gmail.com>
Reviewed-by: Max Gurtovoy <maxg@mellanox.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

nvme-rdma: fix nvme_rdma_create_queue_ib error flow

QP object is created using rdma_cm api, therefore the destruction
should use the same api for symmetry.

Signed-off-by: Max Gurtovoy <maxg@mellanox.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

nvmet-rdma: update queue list during ib_device removal

A NULL deref happens when nvmet_rdma_remove_one() is called more than once
(e.g. while connected via 2 ports).
The first call frees the queues related to the first ib_device but
doesn't remove them from the queue list.
While calling nvmet_rdma_remove_one() for the second ib_device it goes over
the full queue list again and we get the NULL deref.

Fixes: f1d4ef7d ("nvmet-rdma: register ib_client to not deadlock in device removal")
Signed-off-by: Israel Rukshin <israelr@mellanox.com>
Reviewed-by: Max Gurtovoy <maxg@mellanox.com>
Reviewed-by: Sagi Grimberg <sagi@grmberg.me>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

lpfc: tie in to new dev_loss_tmo interface in nvme transport

This patch calls the new nvme transport routine for dev_loss_tmo
whenever the SCSI fc transport calls the lldd to make a dynamic
change to a remote ports dev_loss_tmo.

Signed-off-by: James Smart <james.smart@broadcom.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

nvme-fc: decouple ns references from lldd references

In the lldd api, a lldd may unregister a remoteport (loss of connectivity
or driver unload) or localport (driver unload). The lldd must wait for the
remoteport_delete or localport_delete before completing its actions post
the unregister.  The xxx_deletes currently occur only when the xxxport
structure is fully freed after all references are removed. Thus the lldd
may be held hostage until an app or in-kernel entity that has a namespace
open finally closes so the namespace can be removed, the controller
removed, thus the transport objects, thus the lldd.

This patch decouples the transport and os-facing objects from the lldd
and the remoteport and localport. There is a point in all deletions
where the transport will no longer interact with the lldd on behalf of
a controller. That point centers around the association established
with the target/subsystem. It will access the lldd whenever it attempts
to create an association and while the association is active. New
associations may only be created if the remoteport is live (thus the
localport is live). It will not access the lldd after deleting the
association.

Therefore, the patch tracks the count of active controllers - those with
associations being created or that are active - on a remoteport. It also
tracks the number of remoteports that have active controllers, on a
a localport. When a remoteport is unregistered, as soon as there are no
active controllers, the lldd's remoteport_delete may be called and the
lldd may continue. Similarly, when a localport is unregistered, as soon
as there are no remoteports with active controllers, the localport_delete
callback may be made. This significantly speeds up unregistration with
the lldd.

The transport objects continue in suspended status with reconnect timers
running, and upon expiration, normal ref-counting will occur and the
objects will be freed. The transport object may still be held hostage
by the application/kernel module, but that is acceptable.

With this change, the lldd may be fully unloaded and reloaded, and
if registrations occur prior to the timeouts, the nvme controller and
namespaces will resume normally as if a link bounce.

Signed-off-by: James Smart <james.smart@broadcom.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

nvme-fc: fix localport resume using stale values

The localport resume was not updating the lldd ops structure. If the
lldd is unloaded and reloaded, the ops pointers will differ.

Additionally, as there are device references taken by the localport,
ensure that resume only resumes if the device matches as well.

Signed-off-by: James Smart <james.smart@broadcom.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

nvme: check admin passthru command effects

The NVMe standard provides a command effects log page so the host may
be aware of special requirements it may need to do for a particular
command. For example, the command may need to run with IO quiesced to
prevent timeouts or undefined behavior, or it may change the logical block
formats that determine how the host needs to construct future commands.

This patch saves the nvme command effects log page if the controller
supports it, and performs appropriate actions before and after an admin
passthrough command is completed. If the controller does not support the
command effects log page, the driver will define the effects for known
opcodes. The nvme format and santize are the only commands in this patch
with known effects.

Signed-off-by: Keith Busch <keith.busch@intel.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

nvme: factor get log into a helper

And fix the warning on a successful firmware log.

Reviewed-by: Javier González <javier@cnexlabs.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Keith Busch <keith.busch@intel.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

nvme: fix and clarify the check for missing metadata

Update the check in nvme_setup_rw for missing metadata so that it is
together with the other metadata handling, does not contain impossible
to reach conditions and warns if we get an impossible requests for
a (non-PI) metadata-enabled namespace when CONFIG_BLK_DEV_INTEGRITY
is not set.

Also add a little helper that checks if a given metadata configuration
contains protection information

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reported-by: Javier González <jg@lightnvm.io>
Reviewed-by: Keith Busch <keith.busch@intel.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

nvme: split __nvme_revalidate_disk

Split out the code that applies the calculate value to a given disk/queue
into new helper that can be reused by the multipath code.

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

nvme: set the chunk size before freezing the queue

We don't need a frozen queue to update the chunk_size, which just is a
hint, and moving it a little earlier will allow for some better code
reuse with the multipath code.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Keith Busch <keith.busch@intel.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

nvme: don't pass struct nvme_ns to nvme_config_discard

To allow reusing this function for the multipath node.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Keith Busch <keith.busch@intel.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

nvme: don't pass struct nvme_ns to nvme_init_integrity

To allow reusing this function for the multipath node.

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

nvme: always unregister the integrity profile in __nvme_revalidate_disk

This is safe because the queue is always frozen when we revalidate, and
it simplifies both the existing code as well as the multipath
implementation.

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

nvme: move the dying queue check from cancel to completion

With multipath we don't want a hard DNR bit on a request that is cancelled
by a controller reset, but instead want to be able to retry it on another
patch.  To archive this don't always set the DNR bit when the queue is
dying in nvme_cancel_request, but defer that decision to
nvme_req_needs_retry.  Note that it applies to any command there and not
just cancelled commands, but one the queue is dying that is the right
thing to do anyway.

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

blktrace: fix unlocked registration of tracepoints

We need to ensure that tracepoints are registered and unregistered
with the users of them. The existing atomic count isn't enough for
that. Add a lock around the tracepoints, so we serialize access
to them.

This fixes cases where we have multiple users setting up and
tearing down tracepoints, like this:

CPU: 0 PID: 2995 Comm: syzkaller857118 Not tainted
4.14.0-rc5-next-20171018+ #36
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS
Google 01/01/2011
Call Trace:
  __dump_stack lib/dump_stack.c:16 [inline]
  dump_stack+0x194/0x257 lib/dump_stack.c:52
  panic+0x1e4/0x41c kernel/panic.c:183
  __warn+0x1c4/0x1e0 kernel/panic.c:546
  report_bug+0x211/0x2d0 lib/bug.c:183
  fixup_bug+0x40/0x90 arch/x86/kernel/traps.c:177
  do_trap_no_signal arch/x86/kernel/traps.c:211 [inline]
  do_trap+0x260/0x390 arch/x86/kernel/traps.c:260
  do_error_trap+0x120/0x390 arch/x86/kernel/traps.c:297
  do_invalid_op+0x1b/0x20 arch/x86/kernel/traps.c:310
  invalid_op+0x18/0x20 arch/x86/entry/entry_64.S:905
RIP: 0010:tracepoint_add_func kernel/tracepoint.c:210 [inline]
RIP: 0010:tracepoint_probe_register_prio+0x397/0x9a0 kernel/tracepoint.c:283
RSP: 0018:ffff8801d1d1f6c0 EFLAGS: 00010293
RAX: ffff8801d22e8540 RBX: 00000000ffffffef RCX: ffffffff81710f07
RDX: 0000000000000000 RSI: ffffffff85b679c0 RDI: ffff8801d5f19818
RBP: ffff8801d1d1f7c8 R08: ffffffff81710c10 R09: 0000000000000004
R10: ffff8801d1d1f6b0 R11: 0000000000000003 R12: ffffffff817597f0
R13: 0000000000000000 R14: 00000000ffffffff R15: ffff8801d1d1f7a0
  tracepoint_probe_register+0x2a/0x40 kernel/tracepoint.c:304
  register_trace_block_rq_insert include/trace/events/block.h:191 [inline]
  blk_register_tracepoints+0x1e/0x2f0 kernel/trace/blktrace.c:1043
  do_blk_trace_setup+0xa10/0xcf0 kernel/trace/blktrace.c:542
  blk_trace_setup+0xbd/0x180 kernel/trace/blktrace.c:564
  sg_ioctl+0xc71/0x2d90 drivers/scsi/sg.c:1089
  vfs_ioctl fs/ioctl.c:45 [inline]
  do_vfs_ioctl+0x1b1/0x1520 fs/ioctl.c:685
  SYSC_ioctl fs/ioctl.c:700 [inline]
  SyS_ioctl+0x8f/0xc0 fs/ioctl.c:691
  entry_SYSCALL_64_fastpath+0x1f/0xbe
RIP: 0033:0x444339
RSP: 002b:00007ffe05bb5b18 EFLAGS: 00000206 ORIG_RAX: 0000000000000010
RAX: ffffffffffffffda RBX: 00000000006d66c0 RCX: 0000000000444339
RDX: 000000002084cf90 RSI: 00000000c0481273 RDI: 0000000000000009
RBP: 0000000000000082 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000206 R12: ffffffffffffffff
R13: 00000000c0481273 R14: 0000000000000000 R15: 0000000000000000

since we can now run these in parallel. Ensure that the exported helpers
for doing this are grabbing the queue trace mutex.

Reported-by: Steven Rostedt <rostedt@goodmis.org>
Tested-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

blktrace: fix unlocked access to init/start-stop/teardown

sg.c calls into the blktrace functions without holding the proper queue
mutex for doing setup, start/stop, or teardown.

Add internal unlocked variants, and export the ones that do the proper
locking.

Fixes: 6da127ad0918 ("blktrace: Add blktrace ioctls to SCSI generic devices")
Tested-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

null_blk: add an usage for shared tags in documentation

Add usage explanation for a shared_tags, introduced by commit:

82f402fefa50 ("null_blk: add support for shared tags")

Signed-off-by: Minwoo Im <minwoo.im.dev@gmail.com>
Reworded slightly.

Signed-off-by: Jens Axboe <axboe@kernel.dk>

null_blk: fix default values in documentation

null_blk.c has initial value of
(1) nr_devices as 1.
(2) completion_nsec as 10,000ns, not 10.000ns.
documentation should be updated for fixes above.

Signed-off-by: Minwoo Im <minwoo.im.dev@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

nbd: don't start req until after the dead connection logic

We can end up sleeping for a while waiting for the dead timeout, which
means we could get the per request timer to fire.  We did handle this
case, but if the dead timeout happened right after we submitted we'd
either tear down the connection or possibly requeue as we're handling an
error and race with the endio which can lead to panics and other
hilarity.

Fixes: 560bc4b39952 ("nbd: handle dead connections")
Cc: stable@vger.kernel.org
Signed-off-by: Josef Bacik <jbacik@fb.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

nbd: wait uninterruptible for the dead timeout

If we have a pending signal or the user kills their application then
it'll bring down the whole device, which is less than awesome.  Instead
wait uninterruptible for the dead timeout so we're sure we gave it our
best shot.

Fixes: 560bc4b39952 ("nbd: handle dead connections")
Cc: stable@vger.kernel.org
Signed-off-by: Josef Bacik <jbacik@fb.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

blk-mq: don't allocate driver tag upfront for flush rq

The idea behind it is simple:

1) for none scheduler, driver tag has to be borrowed for flush rq,
   otherwise we may run out of tag, and that causes an IO hang. And
   get/put driver tag is actually noop for none, so reordering tags
   isn't necessary at all.

2) for a real I/O scheduler, we need not allocate a driver tag upfront
   for flush rq. It works just fine to follow the same approach as
   normal requests: allocate driver tag for each rq just before calling
   ->queue_rq().

One driver visible change is that the driver tag isn't shared in the
flush request sequence. That won't be a problem, since we always do that
in legacy path.

Then flush rq need not be treated specially wrt. get/put driver tag.
This cleans up the code - for instance, reorder_tags_to_front() can be
removed, and we needn't worry about request ordering in dispatch list
for avoiding I/O deadlock.

Also we have to put the driver tag before requeueing.

Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

blk-mq: move blk_mq_put_driver_tag*() into blk-mq.h

We need this helper to put the driver tag for flush rq, since we will
not share tag in the flush request sequence in the following patch
in case that I/O scheduler is applied.

Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

blk-mq-sched: decide how to handle flush rq via RQF_FLUSH_SEQ

In case of IO scheduler we always pre-allocate one driver tag before
calling blk_insert_flush(), and flush request will be marked as
RQF_FLUSH_SEQ once it is in flush machinery.

So if RQF_FLUSH_SEQ isn't set, we call blk_insert_flush() to handle
the request, otherwise the flush request is dispatched to ->dispatch
list directly.

This is a preparation patch for not preallocating a driver tag for flush
requests, and for not treating flush requests as a special case. This is
similar to what the legacy path does.

Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

blk-flush: use blk_mq_request_bypass_insert()

In the following patch, we will use RQF_FLUSH_SEQ to decide:

1) if the flag isn't set, the flush rq need to be inserted via
blk_insert_flush()

2) otherwise, the flush rq need to be dispatched directly since
it is in flush machinery now.

So we use blk_mq_request_bypass_insert() for requests of bypassing
flush machinery, just like the legacy path did.

Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

block: pass 'run_queue' to blk_mq_request_bypass_insert

Block flush need this function without running the queue, so add a
parameter controlling whether we run it or not.

Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

blk-flush: don't run queue for requests bypassing flush

blk_insert_flush() should only insert request since run queue always
follows it.

In case of bypassing flush, we don't need to run queue because every
blk_insert_flush() follows one run queue.

Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

blk-mq: put the driver tag of nxt rq before first one is requeued

When freeing the driver tag of the next rq with an I/O scheduler
configured, we get the first entry of the list. However, this can
race with requeue of a request, and we end up getting the wrong request
from the head of the list. Free the driver tag of next rq before the
failed one is requeued in the failure branch of queue_rq callback.

Signed-off-by: Jianchao Wang <jianchao.w.wang@oracle.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

blkcg: add sanity check for blkcg policy operations

blkcg policy should keep cpd/pd's alloc_fn and free_fn in pairs,
otherwise policy would register fail.

Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: weiping zhang <zhangweiping@didichuxing.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

blk-mq: don't handle failure in .get_budget

It is enough to just check if we can get the budget via .get_budget().
And we don't need to deal with device state change in .get_budget().

For SCSI, one issue to be fixed is that we have to call
scsi_mq_uninit_cmd() to free allocated ressources if SCSI device fails
to handle the request. And it isn't enough to simply call
blk_mq_end_request() to do that if this request is marked as
RQF_DONTPREP.

Fixes: 0df21c86bdbf(scsi: implement .get_budget and .put_budget for blk-mq)
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

SCSI: don't get target/host busy_count in scsi_mq_get_budget()

It is very expensive to atomic_inc/atomic_dec the host wide counter of
host->busy_count, and it should have been avoided via blk-mq's mechanism
of getting driver tag, which uses the more efficient way of sbitmap queue.

Also we don't check atomic_read(&sdev->device_busy) in scsi_mq_get_budget()
and don't run queue if the counter becomes zero, so IO hang may be caused
if all requests are completed just before the current SCSI device
is added to shost->starved_list.

Fixes: 0df21c86bdbf(scsi: implement .get_budget and .put_budget for blk-mq)
Reported-by: Bart Van Assche <bart.vanassche@wdc.com>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

block: fix peeking requests during PM

We need to look for an active PM request until the next softbarrier
instead of looking for the first non-PM request.  Otherwise any cause
of request reordering might starve the PM request(s).

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

blk-mq: Make blk_mq_get_request() error path less confusing

blk_mq_get_tag() can modify data->ctx. This means that in the
error path of blk_mq_get_request() data->ctx should be passed to
blk_mq_put_ctx() instead of local_ctx. Note: since blk_mq_put_ctx()
ignores its argument, this patch does not change any functionality.

References: commit 1ad43c0078b7 ("blk-mq: don't leak preempt counter/q_usage_counter when allocating rq failed")
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Cc: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

blk-mq: fix nr_requests wrong value when modify it from sysfs

if blk-mq use "none" io scheduler, nr_request get a wrong value when
input a number > tag_set->queue_depth. blk_mq_tag_update_depth will get
the smaller one min(nr, set->queue_depth), and then q->nr_request get a
wrong value.

Reproduce:

echo none > /sys/block/nvme0n1/queue/scheduler
echo 1000000 > /sys/block/nvme0n1/queue/nr_requests
cat /sys/block/nvme0n1/queue/nr_requests
1000000

Signed-off-by: weiping zhang <zhangweiping@didichuxing.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

cdrom: hide CONFIG_CDROM menu selection

We don't need to expose this. The point is that drivers select
the uniform CDROM layer, if they need it, the user should not
have to make a conscious decision on whether to include this
separately or not.

Fixes: 2a750166a5be ("block: Rework drivers/cdrom/Makefile")
Signed-off-by: Jens Axboe <axboe@kernel.dk>

block: add a poll_fn callback to struct request_queue

That we we can also poll non blk-mq queues.  Mostly needed for
the NVMe multipath code, but could also be useful elsewhere.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

block: introduce GENHD_FL_HIDDEN

With this flag a driver can create a gendisk that can be used for I/O
submission inside the kernel, but which is not registered as user
facing block device.  This will be useful for the NVMe multipath
implementation.

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

block: don't look at the struct device dev_t in disk_devt

The hidden gendisks introduced in the next patch need to keep the dev
field in their struct device empty so that udev won't try to create
block device nodes for them.  To support that rewrite disk_devt to
look at the major and first_minor fields in the gendisk itself instead
of looking into the struct device.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

block: add a blk_steal_bios helper

This helpers allows to bounce steal the uncompleted bios from a request so
that they can be reissued on another path.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

block: provide a direct_make_request helper

This helper allows reinserting a bio into a new queue without much
overhead, but requires all queue limits to be the same for the upper
and lower queues, and it does not provide any recursion preventions.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Reviewed-by: Javier González <javier@cnexlabs.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

block: add REQ_DRV bit

Set aside a bit in the request/bio flags for driver use.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

block: move REQ_NOWAIT

This flag should be before the operation-specific REQ_NOUNMAP bit.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

Merge branch 'nvme-4.15' of git://git.infradead.org/nvme into for-4.15/block

Pull NVMe changes from Christoph:

"Below are the currently queue nvme updates for Linux 4.15.  There are
a few more things that could make it for this merge window, but I'd
like to get things into linux-next, especially for the unlikely case
that Linus decided to cut -rc8.

Highlights:
 - support for SGLs in the PCIe driver (Chaitanya Kulkarni)
 - disable I/O schedulers for the admin queue (Israel Rukshin)
 - various Fibre Channel fixes and enhancements (James Smart)
 - various refactoring for better code sharing between transports
   (Sagi Grimberg and me)

as well as lots of little bits from various contributors."

nvme: comment typo fixed in clearing AER

a tiny typo fixed in a comment.

Signed-off-by: Minwoo Im <minwoo.im.dev@gmail.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>

skd: use ktime_get_real_seconds()

Like many storage drivers, skd uses an unsigned 32-bit number for
interchanging the current time with the firmware. This will overflow in
y2106 and is otherwise safe.

However, the get_seconds() function is generally considered deprecated
since the behavior is different between 32-bit and 64-bit architectures,
and using it may indicate a bigger problem.

To annotate that we've thought about this, let's add a comment here
and migrate to the ktime_get_real_seconds() function that consistently
returns a 64-bit number.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

block: fix CDROM dependency on BLK_DEV

After the cdrom cleanup, I get randconfig warnings for some configurations:

warning: (BLK_DEV_IDECD && BLK_DEV_SR) selects CDROM which has unmet direct dependencies (BLK_DEV)

This adds an explicit BLK_DEV dependency for both drivers. The other
drivers that select 'CDROM' already have this and don't need a change.

Fixes: 2a750166a5be ("block: Rework drivers/cdrom/Makefile")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

nvme: Remove unused headers

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

nvmet: fix fatal_err_work deadlock

Below is a stack trace for an issue that was reported.

What's happening is that the nvmet layer had it's controller kato
timeout fire, which causes it to schedule its fatal error handler
via the fatal_err_work element. The error handler is invoked, which
calls the transport delete_ctrl() entry point, and as the transport
tears down the controller, nvmet_sq_destroy ends up doing the final
put on the ctlr causing it to enter its free routine. The ctlr free
routine does a cancel_work_sync() on fatal_err_work element, which
then does a flush_work and wait_for_completion. But, as the wait is
in the context of the work element being flushed, its in a catch-22
and the thread hangs.

[  326.903131] nvmet: ctrl 1 keep-alive timer (15 seconds) expired!
[  326.909832] nvmet: ctrl 1 fatal error occurred!
[  327.643100] lpfc 0000:04:00.0: 0:6313 NVMET Defer ctx release xri
x114 flg x2
[  494.582064] INFO: task kworker/0:2:243 blocked for more than 120
seconds.
[  494.589638]       Not tainted 4.14.0-rc1.James+ #1
[  494.594986] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs"
disables this message.
[  494.603718] kworker/0:2     D    0   243      2 0x80000000
[  494.609839] Workqueue: events nvmet_fatal_error_handler [nvmet]
[  494.616447] Call Trace:
[  494.619177]  __schedule+0x28d/0x890
[  494.623070]  schedule+0x36/0x80
[  494.626571]  schedule_timeout+0x1dd/0x300
[  494.631044]  ? dequeue_task_fair+0x592/0x840
[  494.635810]  ? pick_next_task_fair+0x23b/0x5c0
[  494.640756]  wait_for_completion+0x121/0x180
[  494.645521]  ? wake_up_q+0x80/0x80
[  494.649315]  flush_work+0x11d/0x1a0
[  494.653206]  ? wake_up_worker+0x30/0x30
[  494.657484]  __cancel_work_timer+0x10b/0x190
[  494.662249]  cancel_work_sync+0x10/0x20
[  494.666525]  nvmet_ctrl_put+0xa3/0x100 [nvmet]
[  494.671482]  nvmet_sq_:q+0x64/0xd0 [nvmet]
[  494.676540]  nvmet_fc_delete_target_queue+0x202/0x220 [nvmet_fc]
[  494.683245]  nvmet_fc_delete_target_assoc+0x6d/0xc0 [nvmet_fc]
[  494.689743]  nvmet_fc_delete_ctrl+0x137/0x1a0 [nvmet_fc]
[  494.695673]  nvmet_fatal_error_handler+0x30/0x40 [nvmet]
[  494.701589]  process_one_work+0x149/0x360
[  494.706064]  worker_thread+0x4d/0x3c0
[  494.710148]  kthread+0x109/0x140
[  494.713751]  ? rescuer_thread+0x380/0x380
[  494.718214]  ? kthread_park+0x60/0x60

Correct by having the fc transport convert to a different workq context
for the actual controller teardown which may call the cancel_work_sync.

Signed-off-by: James Smart <james.smart@broadcom.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Christoph Hellwig <hch@lst.de>

nvme-fc: add dev_loss_tmo timeout and remoteport resume support

When a remoteport is unregistered (connectivity lost), the following
actions are taken:

 - the remoteport is marked DELETED
 - the time when dev_loss_tmo would expire is set in the remoteport
 - all controllers on the remoteport are reset.

After a controller resets, it will stall in a RECONNECTING state waiting
for one of the following:

 - the controller will continue to attempt reconnect per max_retries and
   reconnect_delay.  As no remoteport connectivity, the reconnect attempt
   will immediately fail.  If max reconnects has not been reached, a new
   reconnect_delay timer will be schedule.  If the current time plus
   another reconnect_delay exceeds when dev_loss_tmo expires on the remote
   port, then the reconnect_delay will be shortend to schedule no later
   than when dev_loss_tmo expires.  If max reconnect attempts are reached
   (e.g. ctrl_loss_tmo reached) or dev_loss_tmo ix exceeded without
   connectivity, the controller is deleted.
 - the remoteport is re-registered prior to dev_loss_tmo expiring.
   The resume of the remoteport will immediately attempt to reconnect
   each of its suspended controllers.

Signed-off-by: James Smart <james.smart@broadcom.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
[hch: updated to use nvme_delete_ctrl]
Signed-off-by: Christoph Hellwig <hch@lst.de>

nvme: allow controller RESETTING to RECONNECTING transition

Transport will typically transition from LIVE to RESETTING when initially
performing a reset or recovering from an error.  Adding this transition
allows a transport to transition to RECONNECTING when it checks/waits for
connectivity then creates new transport connections and reinits the
controller.

Signed-off-by: James Smart <james.smart@broadcom.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>

nvme-fc: check connectivity before initiating reconnects

Check remoteport connectivity before initiating reconnects

Signed-off-by: James Smart <james.smart@broadcom.com>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>

nvme-fc: add a dev_loss_tmo field to the remoteport

Add a dev_loss_tmo value, paralleling the SCSI FC transport, for device
connectivity loss.

The transport initializes the value in the nvme_fc_register_remoteport()
call. If the value is not set, a default of 60s is set.

Add a new routine to the api, nvme_fc_set_remoteport_devloss() routine,
which allows the lldd to dynamically update the value on an existing
remoteport.

Signed-off-by: James Smart <james.smart@broadcom.com>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>

nvme-fc: change ctlr state assignments during reset/reconnect

Clean up some of the controller state checks and add the
RESETTING->RECONNECTING state transition.

Specifically:
- the movement of the RESETTING state change and schedule of reset_work
  to core doesn't work wiht nvme_fc_error_recovery setting state to
  RECONNECTING before attempting to reset.  Remove the state change as
  the reset request does it.
- In the rare cases where an error occurs right as we're transitioning
  to LIVE, defer the controller start actions.
- In error handling on teardown of associations while performing initial
  controller creation - avoid quiesce calls on the admin_q.  They are
  unneeded.
- Add the RESETTING->RECONNECTING transition in the reset handler.

Signed-off-by: James Smart <james.smart@broadcom.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>

nvme: flush reset_work before safely continuing with delete operation

Prevent racing controller reset and delete flows. reset_work must not
ever self-requeue so flushing it suffices.

Reported-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Christoph Hellwig <hch@lst.de>

nvme-rdma: reuse nvme_delete_ctrl when reconnect attempts expire

instead of just queueing delete work

Reported-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Christoph Hellwig <hch@lst.de>

nvme: consolidate common code from ->reset_work

No change in behavior except that the FC code cancels two work items a
little later now.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Reviewed-by: James Smart <james.smart@broadcom.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>

nvme-rdma: remove nvme_rdma_remove_ctrl

It is only used in two places, and some of the work done by it will
be taken into common code soon.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Christoph Hellwig <hch@lst.de>

nvme: move controller deletion to common code

Move the ->delete_work and the associated helpers to common code instead
of duplicating them in every driver.  This also adds the missing reference
get/put for the loop driver.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Reviewed-by: James Smart <james.smart@broadcom.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>

nvme-fc: merge __nvme_fc_schedule_delete_work into __nvme_fc_del_ctrl

No need to have two functions doing the same thing.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Reviewed-by: James Smart <james.smart@broadcom.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>

nvme-fc: avoid workqueue flush stalls

There's no need to wait for the full nvme_wq, which is now shared,
to flush. flush only the delete_work item.

Signed-off-by: James Smart <james.smart@broadcom.com>
Reviewed-by: Sagi Grimberg <sgi@grimberg.me>
Signed-off-by: Christoph Hellwig <hch@lst.de>

block: Rework drivers/cdrom/Makefile

Instead of referring from inside drivers/cdrom/Makefile to all the
drivers that use this driver, let these drivers select the cdrom
driver. This change makes the cdrom build code follow the approach
that is used for most other drivers, namely refer from the higher
layers to the lower layer instead of from the lower layer to the
higher layers.

Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

blk-mq: don't restart queue when .get_budget returns BLK_STS_RESOURCE

SCSI restarts its queue in scsi_end_request() automatically, so we don't
need to handle this case in blk-mq.

Especailly any request won't be dequeued in this case, we needn't to
worry about IO hang caused by restart vs. dispatch.

Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

blk-mq: don't handle TAG_SHARED in restart

Now restart is used in the following cases, and TAG_SHARED is for
SCSI only.

1) .get_budget() returns BLK_STS_RESOURCE
- if resource in target/host level isn't satisfied, this SCSI device
will be added in shost->starved_list, and the whole queue will be rerun
(via SCSI's built-in RESTART) in scsi_end_request() after any request
initiated from this host/targe is completed. Forget to mention, host level
resource can't be an issue for blk-mq at all.

- the same is true if resource in the queue level isn't satisfied.

- if there isn't outstanding request on this queue, then SCSI's RESTART
can't work(blk-mq's can't work too), and the queue will be run after
SCSI_QUEUE_DELAY, and finally all starved sdevs will be handled by SCSI's
RESTART when this request is finished

2) scsi_dispatch_cmd() returns BLK_STS_RESOURCE
- if there isn't onprogressing request on this queue, the queue
will be run after SCSI_QUEUE_DELAY

- otherwise, SCSI's RESTART covers the rerun.

3) blk_mq_get_driver_tag() failed
- BLK_MQ_S_TAG_WAITING covers the cross-queue RESTART for driver
allocation.

In one word, SCSI's built-in RESTART is enough to cover the queue
rerun, and we don't need to pay special attention to TAG_SHARED wrt. restart.

In my test on scsi_debug(8 luns), this patch improves IOPS by 20% ~ 30% when
running I/O on these 8 luns concurrently.

Aslo Roman Pen reported the current RESTART is very expensive especialy
when there are lots of LUNs attached in one host, such as in his
test, RESTART causes half of IOPS be cut.

Fixes: https://marc.info/?l=linux-kernel&m=150832216727524&w=2
Fixes: 6d8c6c0f97ad ("blk-mq: Restart a single queue if tag sets are shared")
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

scsi: implement .get_budget and .put_budget for blk-mq

We need to tell blk-mq to reserve resources before queuing one request,
so implement these two callbacks. Then blk-mq can avoid to dequeue
request too early, and IO merging can be improved a lot.

Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

scsi: allow passing in null rq to scsi_prep_state_check()

In the following patch, we will implement scsi_get_budget()
which need to call scsi_prep_state_check() when rq isn't
dequeued yet.

Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

blk-mq-sched: improve dispatching from sw queue

SCSI devices use host-wide tagset, and the shared driver tag space is
often quite big. However, there is also a queue depth for each lun(
.cmd_per_lun), which is often small, for example, on both lpfc and
qla2xxx, .cmd_per_lun is just 3.

So lots of requests may stay in sw queue, and we always flush all
belonging to same hw queue and dispatch them all to driver.
Unfortunately it is easy to cause queue busy because of the small
.cmd_per_lun.  Once these requests are flushed out, they have to stay in
hctx->dispatch, and no bio merge can happen on these requests, and
sequential IO performance is harmed.

This patch introduces blk_mq_dequeue_from_ctx for dequeuing a request
from a sw queue, so that we can dispatch them in scheduler's way. We can
then avoid dequeueing too many requests from sw queue, since we don't
flush ->dispatch completely.

This patch improves dispatching from sw queue by using the .get_budget
and .put_budget callbacks.

Reviewed-by: Omar Sandoval <osandov@fb.com>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

blk-mq: introduce .get_budget and .put_budget in blk_mq_ops

For SCSI devices, there is often a per-request-queue depth, which needs
to be respected before queuing one request.

Currently blk-mq always dequeues the request first, then calls
.queue_rq() to dispatch the request to lld. One obvious issue with this
approach is that I/O merging may not be successful, because when the
per-request-queue depth can't be respected, .queue_rq() has to return
BLK_STS_RESOURCE, and then this request has to stay in hctx->dispatch
list. This means it never gets a chance to be merged with other IO.

This patch introduces .get_budget and .put_budget callback in blk_mq_ops,
then we can try to get reserved budget first before dequeuing request.
If the budget for queueing I/O can't be satisfied, we don't need to
dequeue request at all. Hence the request can be left in the IO
scheduler queue, for more merging opportunities.

Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

block: kyber: check if there are requests in ctx in kyber_has_work()

There may be request in sw queue, and not fetched to domain queue
yet, so check it in kyber_has_work().

Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

sbitmap: introduce __sbitmap_for_each_set()

For blk-mq, we need to be able to iterate software queues starting
from any queue in a round robin fashion, so introduce this helper.

Reviewed-by: Omar Sandoval <osandov@fb.com>
Cc: Omar Sandoval <osandov@fb.com>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

blk-mq-sched: move actual dispatching into one helper

So that it becomes easy to support to dispatch from sw queue in the
following patch.

No functional change.

Reviewed-by: Bart Van Assche <bart.vanassche@wdc.com>
Reviewed-by: Omar Sandoval <osandov@fb.com>
Suggested-by: Christoph Hellwig <hch@lst.de> # for simplifying dispatch logic
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

blk-mq-sched: dispatch from scheduler IFF progress is made in ->dispatch

When the hw queue is busy, we shouldn't take requests from the scheduler
queue any more, otherwise it is difficult to do IO merge.

This patch fixes the awful IO performance on some SCSI devices(lpfc,
qla2xxx, ...) when mq-deadline/kyber is used by not taking requests if
hw queue is busy.

Reviewed-by: Omar Sandoval <osandov@fb.com>
Reviewed-by: Bart Van Assche <bart.vanassche@wdc.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

MAINTAINERS: Remove Rafael from Opal maintainers.

He is no longer working on storage.

Signed-off-by: Scott Bauer <scott.bauer@intel.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>