Pull followup NVMe (mostly) changes from Sagi:

I added the quiesce/unquiesce patches in here as it's
easy for me easily apply changes on top. It has accumulated
reviews and includes mostly nvme anyway, please tell me if
you don't want to take them with this.

This includes:
- quiesce/unquiesce fixes in nvme and others from me
- nvme-fc add create association padding spec updates from James
- some more quirking from MKP
- nvmet nit cleanup from Max
- Fix nvme-rdma racy RDMA completion signalling from Marta
- some centralization patches from me
- add tagset nr_hw_queues updates on controller resets in
  nvme drivers from me
- nvme-rdma fix resources recycling when doing error recovery from me
- minor cleanups in nvme-fc from me

We actually using the cookie returned from the last submit_bio
call.
Signed-off-by: NMax Gurtovoy <maxg@mellanox.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NSagi Grimberg <sagi@grimberg.me>

Adjust io queue depth more easily, and make sure io queue depth >= 2.
Signed-off-by: Nweiping zhang <zhangweiping@didichuxing.com>
Signed-off-by: NSagi Grimberg <sagi@grimberg.me>

"i" should be signed or it could cause a forever loop on the cleanup
path. "size" can be used uninitialized.

Fixes: 87ad72a5 ("nvme-pci: implement host memory buffer support")
Signed-off-by: NDan Carpenter <dan.carpenter@oracle.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NSagi Grimberg <sagi@grimberg.me>

Target validation of the Create Association LS revised to accept any
LS as long as all non-pad data has been received. This allows a (newer)
target to accept the LS from older initiators with varying pad lengths.
Signed-off-by: NJames Smart <james.smart@broadcom.com>
Signed-off-by: NSagi Grimberg <sagi@grimberg.me>

Revises the Create Association LS for the amount of pad expected in 1.16.

Add defines for the minimum lengths that a target can accept (e.g. variable
pad lengths)
Signed-off-by: NJames Smart <james.smart@broadcom.com>
Signed-off-by: NSagi Grimberg <sagi@grimberg.me>

Remove unnecessary checks when freeing dma memory in the completion
path.
Signed-off-by: NJavier González <javier@cnexlabs.com>
Signed-off-by: NMatias Bjørling <matias@cnexlabs.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

When removing a pblk instance, control the write I/O flow to the
controller as we do in the fast path.
Signed-off-by: NJavier González <javier@cnexlabs.com>
Signed-off-by: NMatias Bjørling <matias@cnexlabs.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

The changes in "block: Make most scsi_req_init() calls implicit" mean
that every driver that supports the generic scsi ioctls needs to
call scsi_req_init on newly allocated requests, but that commit didn't
add the call to the ccіss driver.  Fix that to avoid crashes when
udev issues SG_IO commands.

Fixes: ca18d6f7 ("block: Make most scsi_req_init() calls implicit")
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Reported-by: NMeelis Roos <mroos@linux.ee>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

In case we use shared tags feature, blk_mq_alloc_tag_set might fail
during module initialization. In that case, fail the load with a
suitable error code. Also move the tagset initialization process after
defining the amount of submission queues.
Signed-off-by: NMax Gurtovoy <maxg@mellanox.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

The BIO issuing loop in __blkdev_issue_zeroout() is allocating BIOs
with a maximum number of bvec (pages) equal to

min(nr_sects, (sector_t)BIO_MAX_PAGES)

This works since the requested number of bvecs will always be limited
to the absolute maximum number supported (BIO_MAX_PAGES), but this is
ineficient as too many bvec entries may be requested due to the
different units being used in the min() operation (number of sectors vs
number of pages).
To fix this, introduce the helper __blkdev_sectors_to_bio_pages() to
correctly calculate the number of bvecs for zeroout BIOs as the issuing
loop progresses. The calculation is done using consistent units and
makes sure that the number of pages return is at least 1 (for cases
where the number of sectors is less that the number of sectors in
a page).

Also remove a trailing space after the bit shift in the internal loop
min() call.
Signed-off-by: NDamien Le Moal <damien.lemoal@wdc.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

When our RDMA queue-pair is torn down with high load
of I/O traffic, we have no way of knowing if the
memory region was actually registered by the reg_mr
work request as it completion flushes with error (hw
might have done it or not).

So in order to not deal with all this uncertanty, we
simply recycle the MR in reinit_request.
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NSagi Grimberg <sagi@grimberg.me>

Usually before we teardown the controller we want to:
1. complete/cancel any ctrl inflight works
2. remove ctrl namespaces (only for removal though, resets
   shouldn't remove any namespaces).

but we do not want to destroy the controller device as
we might use it for logging during the teardown stage.

This patch adds nvme_start_ctrl() which queues inflight
controller works (aen, ns scan, queue start and keep-alive
if kato is set) and nvme_stop_ctrl() which cancels the works
namespace removal is left to the callers to handle.

Move nvme_uninit_ctrl after we are done with the
controller device.
Reviewed-by: NKeith Busch <keith.busch@intel.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NSagi Grimberg <sagi@grimberg.me>

Without it its not guaranteed that no .queue_rq is inflight.
Reviewed-by: NMing Lei <ming.lei@redhat.com>
Acked-by: NMichael S. Tsirkin <mst@redhat.com>
Cc: virtio-dev@lists.oasis-open.org
Cc: Jason Wang <jasowang@redhat.com>
Signed-off-by: NSagi Grimberg <sagi@grimberg.me>

Unlike blk_mq_stop_hw_queues, blk_mq_quiesce_queue respects the
submission path rcu grace. quiesce the queue before iterating
on live tags, or performing device io quiescing.

While were at it, verify that the request started in mtip_abort_cmd
amd mtip_queue_cmd tag iteration calls.
Reviewed-by: NMing Lei <ming.lei@redhat.com>
Signed-off-by: NSagi Grimberg <sagi@grimberg.me>

Unlike blk_mq_stop_hw_queues, blk_mq_quiesce_queue respects the
submission path rcu grace. quiesce the queue before iterating
on live tags.
Reviewed-by: NMing Lei <ming.lei@redhat.com>
Acked-by: NJosef Bacik <jbacik@fb.com>
Signed-off-by: NSagi Grimberg <sagi@grimberg.me>

When we requeue a request, we can always insert the request
back to the scheduler instead of doing it when restarting
the queues and kicking the requeue work, so get rid of
the requeue kick in nvme (core and drivers).

Also, now there is no need start hw queues in nvme_kill_queues
We don't stop the hw queues anymore, so no need to
start them.
Reviewed-by: NMing Lei <ming.lei@redhat.com>
Signed-off-by: NSagi Grimberg <sagi@grimberg.me>

unlike blk_mq_stop_hw_queues and blk_mq_start_stopped_hw_queues
quiescing/unquiescing respects the submission path rcu grace.
Reviewed-by: NMing Lei <ming.lei@redhat.com>
Signed-off-by: NSagi Grimberg <sagi@grimberg.me>

unlike blk_mq_stop_hw_queues and blk_mq_start_stopped_hw_queues
quiescing/unquiescing respects the submission path rcu grace.
Reviewed-by: NMing Lei <ming.lei@redhat.com>
Signed-off-by: NSagi Grimberg <sagi@grimberg.me>

unlike blk_mq_stop_hw_queues and blk_mq_start_stopped_hw_queues
quiescing/unquiescing respects the submission path rcu grace.

Also, make sure to unquiesce before cleanup the admin queue.
Reviewed-by: NMing Lei <ming.lei@redhat.com>
Reviewed-By: NJames Smart <james.smart@broadcom.com>
Signed-off-by: NSagi Grimberg <sagi@grimberg.me>

unlike blk_mq_stop_hw_queues and blk_mq_start_stopped_hw_queues
quiescing/unquiescing respects the submission path rcu grace.
Also make sure to kick the requeue list when appropriate.
Reviewed-by: NMing Lei <ming.lei@redhat.com>
Signed-off-by: NSagi Grimberg <sagi@grimberg.me>

This patch improves the way the RDMA IB signalling is done by using atomic
operations for the signalling variable. This avoids race conditions on
sig_count.

The signalling interval changes slightly and is now the largest power of
two not larger than queue depth / 2.

ilog() usage idea by Bart Van Assche.
Signed-off-by: NMarta Rybczynska <marta.rybczynska@kalray.eu>
Reviewed-by: NSagi Grimberg <sagi@grimberg.me>
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Cc: stable@vger.kernel.org

It is observed reading the register from HW takes a bit long,
for example in my box, the following difference of 'perf report
--no-children fio ...' can be seen when running I/O:

1) V4.12 without patch
+    9.28%       fio  [mtip32xx]           [k] mtip_irq_handler
+    8.48%       fio  [mtip32xx]           [k] mtip_init_cmd_header

2) V4.12 with the following patch
+    9.14%       fio  [mtip32xx]           [k] mtip_irq_handler
......
+    1.14%       fio  [mtip32xx]           [k] mtip_init_cmd_header

IOPS can be increased by ~5% with this patch too.

Fixes: a4e84aae(mtip32xx: use runtime tag to initialize command header)
Signed-off-by: NMing Lei <ming.lei@redhat.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

block/bio-integrity.c:318:10-11: WARNING: return of 0/1 in function 'bio_integrity_prep' with return type bool

 Return statements in functions returning bool should use
 true/false instead of 1/0.
Generated by: scripts/coccinelle/misc/boolreturn.cocci

Fixes: e23947bd ("bio-integrity: fold bio_integrity_enabled to bio_integrity_prep")
CC: Dmitry Monakhov <dmonakhov@openvz.org>
Signed-off-by: NFengguang Wu <fengguang.wu@intel.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

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

We might have more/less queues once we reconnect/reset. For
example due to cpu going online/offline or controller constraints.
Reviewed-by: NJohannes Thumshirn <jthumshirn@suse.de>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NSagi Grimberg <sagi@grimberg.me>

We might have more/less queues once we reconnect/reset. For
example due to cpu going online/offline
Reviewed-by: NJohannes Thumshirn <jthumshirn@suse.de>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NSagi Grimberg <sagi@grimberg.me>

We might have more/less queues once we reconnect/reset. For
example due to cpu going online/offline or controller constraints.
Reviewed-by: NJohannes Thumshirn <jthumshirn@suse.de>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NSagi Grimberg <sagi@grimberg.me>

Its what the user passed, so its probably a better
idea to keep it intact. Also, limit the number of
I/O queues to max online cpus and the lport maximum
hw queues.
Reviewed-by: NJohannes Thumshirn <jthumshirn@suse.de>
Reviewed-by: NMax Gurtovoy <maxg@mellanox.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NSagi Grimberg <sagi@grimberg.me>

And instead call directly into the integrity code from bio_end_io.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Currently ->verify_fn not woks at all because at the moment it is called
bio->bi_iter.bi_size == 0, so we do not iterate integrity bvecs at all.

In order to perform verification we need to know original data vector,
with new bvec rewind API this is trivial.

testcase: https://github.com/dmonakhov/xfstests/commit/3c6509eaa83b9c17cd0bc95d73fcdd76e1c54a85Reviewed-by: NHannes Reinecke <hare@suse.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NDmitry Monakhov <dmonakhov@openvz.org>
[hch: adopted for new status values]
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Some ->bi_end_io handlers (for example: pi_verify or decrypt handlers)
need to know original data vector, but after bio traverse io-stack it may
be advanced, splited and relocated many times so it is hard to guess
original iterator. Let's add 'bi_done' conter which accounts number
of bytes iterator was advanced during it's evolution. Later end_io handler
may easily restore original iterator by rewinding iterator to
iter->bi_done.

Note: this change makes sizeof (struct bvec_iter) multiple to 8
Reviewed-by: NHannes Reinecke <hare@suse.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NDmitry Monakhov <dmonakhov@openvz.org>
[hch: switched to true/false return]
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Currently if some one try to advance bvec beyond it's size we simply
dump WARN_ONCE and continue to iterate beyond bvec array boundaries.
This simply means that we endup dereferencing/corrupting random memory
region.

Sane reaction would be to propagate error back to calling context
But bvec_iter_advance's calling context is not always good for error
handling. For safity reason let truncate iterator size to zero which
will break external iteration loop which prevent us from unpredictable
memory range corruption. And even it caller ignores an error, it will
corrupt it's own bvecs, not others.

This patch does:
- Return error back to caller with hope that it will react on this
- Truncate iterator size

Code was added long time ago here 4550dd6c, luckily no one hit it
in real life :)
Signed-off-by: NDmitry Monakhov <dmonakhov@openvz.org>
Reviewed-by: NMing Lei <ming.lei@redhat.com>
Reviewed-by: NMartin K. Petersen <martin.petersen@oracle.com>
[hch: switch to true/false returns instead of errno values]
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Signed-off-by: NDmitry Monakhov <dmonakhov@openvz.org>
Reviewed-by: NMartin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Currently all integrity prep hooks are open-coded, and if prepare fails
we ignore it's code and fail bio with EIO. Let's return real error to
upper layer, so later caller may react accordingly.

In fact no one want to use bio_integrity_prep() w/o bio_integrity_enabled,
so it is reasonable to fold it in to one function.
Signed-off-by: NDmitry Monakhov <dmonakhov@openvz.org>
Reviewed-by: NMartin K. Petersen <martin.petersen@oracle.com>
[hch: merged with the latest block tree,
	return bool from bio_integrity_prep]
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

bio_integrity_trim inherent it's interface from bio_trim and accept
offset and size, but this API is error prone because data offset
must always be insync with bio's data offset. That is why we have
integrity update hook in bio_advance()

So only meaningful values are: offset == 0, sectors == bio_sectors(bio)
Let's just remove them completely.
Reviewed-by: NHannes Reinecke <hare@suse.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NMartin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: NDmitry Monakhov <dmonakhov@openvz.org>
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

SCSI drivers do care about bip_seed so we must update it accordingly.
Reviewed-by: NHannes Reinecke <hare@suse.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NMartin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: NDmitry Monakhov <dmonakhov@openvz.org>
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Reviewed-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NHannes Reinecke <hare@suse.com>
Reviewed-by: NMartin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: NDmitry Monakhov <dmonakhov@openvz.org>
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

When mq-deadline is taken, IOPS of sequential read and
seqential write is observed more than 20% drop on sata(scsi-mq)
devices, compared with using 'none' scheduler.

The reason is that the default nr_requests for scheduler is
too big for small queuedepth devices, and latency is increased
much.

Since the principle of taking 256 requests for mq scheduler
is based on 128 queue depth, this patch changes into
double size of min(hw queue_depth, 128).
Signed-off-by: NMing Lei <ming.lei@redhat.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

On each deactivation or re-scheduling (after being served) of a
bfq_queue, BFQ invokes the function __bfq_entity_update_weight_prio(),
to perform pending updates of ioprio, weight and ioprio class for the
bfq_queue. BFQ also invokes this function on I/O-request dispatches,
to raise or lower weights more quickly when needed, thereby improving
latency. However, the entity representing the bfq_queue may be on the
active (sub)tree of a service tree when this happens, and, although
with a very low probability, the bfq_queue may happen to also have a
pending change of its ioprio class. If both conditions hold when
__bfq_entity_update_weight_prio() is invoked, then the entity moves to
a sort of hybrid state: the new service tree for the entity, as
returned by bfq_entity_service_tree(), differs from service tree on
which the entity still is. The functions that handle activations and
deactivations of entities do not cope with such a hybrid state (and
would need to become more complex to cope).

This commit addresses this issue by just making
__bfq_entity_update_weight_prio() not perform also a possible pending
change of ioprio class, when invoked on an I/O-request dispatch for a
bfq_queue. Such a change is thus postponed to when
__bfq_entity_update_weight_prio() is invoked on deactivation or
re-scheduling of the bfq_queue.
Reported-by: NMarco Piazza <mpiazza@gmail.com>
Reported-by: NLaurentiu Nicola <lnicola@dend.ro>
Signed-off-by: NPaolo Valente <paolo.valente@linaro.org>
Tested-by: NMarco Piazza <mpiazza@gmail.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>