If the "irq_queues" are greater than num_possible_cpus(),
nvme_calc_irq_sets() can have irq set_size for HCTX_TYPE_DEFAULT greater
than it can be afforded.
2039         affd->set_size[HCTX_TYPE_DEFAULT] = nrirqs - nr_read_queues;

It might cause a WARN() from the irq_build_affinity_masks() like [1]:
220         if (nr_present < numvecs)
221                 WARN_ON(nr_present + nr_others < numvecs);

This patch prevents it from the WARN() by adjusting the max_vector value
from the nvme_setup_irqs().

[1] WARN messages when modprobe nvme write_queues=32 poll_queues=0:
root@target:~/nvme# nproc
8
root@target:~/nvme# modprobe nvme write_queues=32 poll_queues=0
[   17.925326] nvme nvme0: pci function 0000:00:04.0
[   17.940601] WARNING: CPU: 3 PID: 1030 at kernel/irq/affinity.c:221 irq_create_affinity_masks+0x222/0x330
[   17.940602] Modules linked in: nvme nvme_core [last unloaded: nvme]
[   17.940605] CPU: 3 PID: 1030 Comm: kworker/u17:4 Tainted: G        W         5.1.0+ #156
[   17.940605] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.12.1-0-ga5cab58e9a3f-prebuilt.qemu.org 04/01/2014
[   17.940608] Workqueue: nvme-reset-wq nvme_reset_work [nvme]
[   17.940609] RIP: 0010:irq_create_affinity_masks+0x222/0x330
[   17.940611] Code: 4c 8d 4c 24 28 4c 8d 44 24 30 e8 c9 fa ff ff 89 44 24 18 e8 c0 38 fa ff 8b 44 24 18 44 8b 54 24 1c 5a 44 01 d0 41 39 c4 76 02 <0f> 0b 48 89 df 44 01 e5 e8 f1 ce 10 00 48 8b 34 24 44 89 f0 44 01
[   17.940611] RSP: 0018:ffffc90002277c50 EFLAGS: 00010216
[   17.940612] RAX: 0000000000000008 RBX: ffff88807ca48860 RCX: 0000000000000000
[   17.940612] RDX: ffff88807bc03800 RSI: 0000000000000020 RDI: 0000000000000000
[   17.940613] RBP: 0000000000000001 R08: ffffc90002277c78 R09: ffffc90002277c70
[   17.940613] R10: 0000000000000008 R11: 0000000000000001 R12: 0000000000000020
[   17.940614] R13: 0000000000025d08 R14: 0000000000000001 R15: ffff88807bc03800
[   17.940614] FS:  0000000000000000(0000) GS:ffff88807db80000(0000) knlGS:0000000000000000
[   17.940616] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[   17.940617] CR2: 00005635e583f790 CR3: 000000000240a000 CR4: 00000000000006e0
[   17.940617] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[   17.940618] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[   17.940618] Call Trace:
[   17.940622]  __pci_enable_msix_range+0x215/0x540
[   17.940623]  ? kernfs_put+0x117/0x160
[   17.940625]  pci_alloc_irq_vectors_affinity+0x74/0x110
[   17.940626]  nvme_reset_work+0xc30/0x1397 [nvme]
[   17.940628]  ? __switch_to_asm+0x34/0x70
[   17.940628]  ? __switch_to_asm+0x40/0x70
[   17.940629]  ? __switch_to_asm+0x34/0x70
[   17.940630]  ? __switch_to_asm+0x40/0x70
[   17.940630]  ? __switch_to_asm+0x34/0x70
[   17.940631]  ? __switch_to_asm+0x40/0x70
[   17.940632]  ? nvme_irq_check+0x30/0x30 [nvme]
[   17.940633]  process_one_work+0x20b/0x3e0
[   17.940634]  worker_thread+0x1f9/0x3d0
[   17.940635]  ? cancel_delayed_work+0xa0/0xa0
[   17.940636]  kthread+0x117/0x120
[   17.940637]  ? kthread_stop+0xf0/0xf0
[   17.940638]  ret_from_fork+0x3a/0x50
[   17.940639] ---[ end trace aca8a131361cd42a ]---
[   17.942124] nvme nvme0: 7/1/0 default/read/poll queues
Signed-off-by: NMinwoo Im <minwoo.im.dev@gmail.com>
Signed-off-by: NChristoph Hellwig <hch@lst.de>

queue_count_set() seems like that it has been provided to limit the
number of queue entries for write/poll queues.  But, the
queue_count_set() has been doing nothing but a parameter check even it
has num_possible_cpus() which is nop.

This patch removes entire queue_count_ops from the write_queues and
poll_queues.
Signed-off-by: NMinwoo Im <minwoo.im.dev@gmail.com>
Signed-off-by: NChristoph Hellwig <hch@lst.de>

poll_queues will be zero even without zero initialization here.
Signed-off-by: NMinwoo Im <minwoo.im.dev@gmail.com>
Reviewed-by: NChaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
Signed-off-by: NChristoph Hellwig <hch@lst.de>

The nvme pci driver prepares its devices for power loss during suspend
by shutting down the controllers. The power setting is deferred to
pci driver's power management before the platform removes power. The
suspend-to-idle mode, however, does not remove power.

NVMe devices that implement host managed power settings can achieve
lower power and better transition latencies than using generic PCI power
settings. Try to use this feature if the platform is not involved with
the suspend. If successful, restore the previous power state on resume.
Tested-by: NKai-Heng Feng <kai.heng.feng@canonical.com>
Tested-by: NMario Limonciello <mario.limonciello@dell.com>
Reviewed-by: NRafael J. Wysocki <rafael.j.wysocki@intel.com>
Signed-off-by: NKeith Busch <keith.busch@intel.com>
Signed-off-by: NSagi Grimberg <sagi@grimberg.me>
[hch: fixed the compilation for the !CONFIG_PM_SLEEP case]
Signed-off-by: NChristoph Hellwig <hch@lst.de>

This patch introduces a nvme_is_fabrics() inline function to check
whether or not the given command structure is for fabrics.
Signed-off-by: NMinwoo Im <minwoo.im.dev@gmail.com>
Reviewed-by: NSagi Grimberg <sagi@grimberg.me>
Signed-off-by: NSagi Grimberg <sagi@grimberg.me>
Signed-off-by: NChristoph Hellwig <hch@lst.de>

Future use intends to make use of both, so export these functions. And
since their implementation is identical except for the opcode, provide a
new function that implement both.

[akinobu.mita@gmail.com>: fix line over 80 characters]
Signed-off-by: NKeith Busch <keith.busch@intel.com>
Signed-off-by: NAkinobu Mita <akinobu.mita@gmail.com>
Reviewed-by: NChaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
Reviewed-by: NMinwoo Im <minwoo.im.dev@gmail.com>
Signed-off-by: NSagi Grimberg <sagi@grimberg.me>
Signed-off-by: NChristoph Hellwig <hch@lst.de>

When a shared namespace is removed, we call blk_cleanup_queue()
when the device can still be accessed as the current path and this can
result in submission to a dying queue. Hence, direct_make_request()
called by our mpath device may fail (propagating the failure to userspace).
Instead, we want to failover this I/O to a different path if one exists.
Thus, before we cleanup the request queue, we make sure that the device is
cleared from the current path nor it can be selected again as such.

Fix this by:
- clear the ns from the head->list and synchronize rcu to make sure there is
  no concurrent path search that restores it as the current path
- clear the mpath current path in order to trigger a subsequent path search
  and sync srcu to wait for any ongoing request submissions
- safely continue to namespace removal and blk_cleanup_queue
Signed-off-by: NAnton Eidelman <anton@lightbitslabs.com>
Signed-off-by: NSagi Grimberg <sagi@grimberg.me>
Signed-off-by: NChristoph Hellwig <hch@lst.de>

When looking at console messages to troubleshoot, there are one
maybe two messages before creation of the controller is complete.
However, a lot of io takes place to reach that point. It's unclear
when things have started.

Add a message when the controller is attempting to create a new
association. Thus we know what controller, between what host and
remote port, and what NQN is being put into place for any
subsequent success or failure messages.
Signed-off-by: NJames Smart <jsmart2021@gmail.com>
Reviewed-by: NChaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
Reviewed-by: NGiridhar Malavali <gmalavali@marvell.com>
Signed-off-by: NSagi Grimberg <sagi@grimberg.me>
Signed-off-by: NChristoph Hellwig <hch@lst.de>

To support scenarios which aren't bound to nvmetcli add port scenarios,
which is currently where the nvmet_fc transport invokes the discovery
event callbacks, a syfs attribute is added to lpfc which can be written
to cause an RSCN to be generated for the nport.
Signed-off-by: NDick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: NJames Smart <jsmart2021@gmail.com>
Reviewed-by: NHannes Reinecke <hare@suse.com>
Reviewed-by: NArun Easi <aeasi@marvell.com>
Signed-off-by: NSagi Grimberg <sagi@grimberg.me>
Signed-off-by: NChristoph Hellwig <hch@lst.de>

This patch updates RSCN receive processing to check for the remote
port being an NVME port, and if so, invoke the nvme_fc callback to
rescan the remote port.  The rescan will generate a discovery udev
event.
Signed-off-by: NDick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: NJames Smart <jsmart2021@gmail.com>
Reviewed-by: NHannes Reinecke <hare@suse.com>
Reviewed-by: NArun Easi <aeasi@marvell.com>
Signed-off-by: NSagi Grimberg <sagi@grimberg.me>
Signed-off-by: NChristoph Hellwig <hch@lst.de>

This patch adds support for the nvmet discovery op. When the callback
routine is called, the driver will call the routine to generate an RSCN
to the port on the other end of the link.
Signed-off-by: NDick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: NJames Smart <jsmart2021@gmail.com>
Reviewed-by: NHannes Reinecke <hare@suse.com>
Reviewed-by: NArun Easi <aeasi@marvell.com>
Signed-off-by: NSagi Grimberg <sagi@grimberg.me>
Signed-off-by: NChristoph Hellwig <hch@lst.de>

This patch adds general RSCN support:

 - The ability to transmit an RSCN to the port on the other end of
   the link (regular port if pt2pt, or fabric controller if fabric).
 - And general recognition of an RSCN ELS when an ELS is received.
Signed-off-by: NDick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: NJames Smart <jsmart2021@gmail.com>
Reviewed-by: NHannes Reinecke <hare@suse.com>
Reviewed-by: NArun Easi <aeasi@marvell.com>
Signed-off-by: NSagi Grimberg <sagi@grimberg.me>
Signed-off-by: NChristoph Hellwig <hch@lst.de>

Update fcloop to support the discovery_event operation and
invoke a nvme rescan. In a real fc adapter, this would generate an
RSCN, which the host would receive and convert into a nvme rescan
on the remote port specified in the rscn payload.
Signed-off-by: NJames Smart <jsmart2021@gmail.com>
[kbuild-bot: fcloop_tgt_discovery_evt can be static]
Reviewed-by: NHannes Reinecke <hare@suse.com>
Reviewed-by: NArun Easi <aeasi@marvell.com>
Signed-off-by: NSagi Grimberg <sagi@grimberg.me>
Signed-off-by: NChristoph Hellwig <hch@lst.de>

This patch adds support for the nvmet discovery_change transport op.
In turn, the transport adds it's own LLDD api callback discovery_event
op to request the LLDD to generate an RSCN for the discovery change.
Signed-off-by: NJames Smart <jsmart2021@gmail.com>
Reviewed-by: NHannes Reinecke <hare@suse.com>
Reviewed-by: NArun Easi <aeasi@marvell.com>
Signed-off-by: NSagi Grimberg <sagi@grimberg.me>
Signed-off-by: NChristoph Hellwig <hch@lst.de>

Some transports, such as FC-NVME, support discovery controller change
events without the use of a persistent discovery controller. FC receives
events via RSCN from the FC Fabric Controller or subsystem FC port.

This patch adds a nvmet transport op that is called whenever a
discovery change event occurs in the nvmet layer.

To facilitate the callback without adding another layer to cross into
core.c to reference the transport ops, the port structure snapshots
the transport ops when the port is enabled and clears them when disabled.
Signed-off-by: NJames Smart <jsmart2021@gmail.com>
Reviewed-by: NHannes Reinecke <hare@suse.com>
Reviewed-by: NArun Easi <aeasi@marvell.com>
Signed-off-by: NSagi Grimberg <sagi@grimberg.me>
Signed-off-by: NChristoph Hellwig <hch@lst.de>

The bfq schedule now uses css_next_descendant_pre directly after
the stats functionality depending on it has been from the core
blk-cgroup code to bfq.  Export the symbol so that bfq can still
be build modular.

Fixes: d6258980 ("bfq-iosched: move bfq_stat_recursive_sum into the only caller")
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Pull MD changes from Song.

* 'md-next' of https://github.com/liu-song-6/linux:
  md: add bitmap_abort label in md_run
  md-bitmap: create and destroy wb_info_pool with the change of bitmap
  md-bitmap: create and destroy wb_info_pool with the change of backlog
  md: introduce mddev_create/destroy_wb_pool for the change of member device
  md/raid1: fix potential data inconsistency issue with write behind device

Now, there are two places need to consider about
the failure of destroy bitmap, so move the common
part between bitmap_abort and abort label.
Reviewed-by: NNeilBrown <neilb@suse.com>
Signed-off-by: NGuoqing Jiang <gqjiang@suse.com>
Signed-off-by: NSong Liu <songliubraving@fb.com>

The write-behind attribute is part of bitmap, since bitmap
can be added/removed dynamically with the following.

1. mdadm --grow /dev/md0 --bitmap=none
2. mdadm --grow /dev/md0 --bitmap=internal --write-behind

So we need to destroy wb_info_pool in md_bitmap_destroy,
and create the pool before load bitmap.
Reviewed-by: NNeilBrown <neilb@suse.com>
Signed-off-by: NGuoqing Jiang <gqjiang@suse.com>
Signed-off-by: NSong Liu <songliubraving@fb.com>

Since we can enable write-behind mode by write backlog node,
so create wb_info_pool if the mode is just enabled, also call
call md_bitmap_update_sb to make user aware the write-behind
mode is enabled. Conversely, wb_info_pool should be destroyed
when write-behind mode is disabled.

Beside above, it is better to update bitmap sb if we change
the number of max_write_behind.
Reviewed-by: NNeilBrown <neilb@suse.com>
Signed-off-by: NGuoqing Jiang <gqjiang@suse.com>
Signed-off-by: NSong Liu <songliubraving@fb.com>

Previously, we called rdev_init_wb to avoid potential data
inconsistency when array is created.

Now, we need to call the function and create mempool if a
device is added or just be flaged as "writemostly". So
mddev_create_wb_pool is introduced and called accordingly.
And for safety reason, we mark implicit GFP_NOIO allocation
scope for create mempool during mddev_suspend/mddev_resume.

And mempool should be removed conversely after remove a
member device or its's "writemostly" flag, which is done
by call mddev_destroy_wb_pool.
Reviewed-by: NNeilBrown <neilb@suse.com>
Signed-off-by: NGuoqing Jiang <gqjiang@suse.com>
Signed-off-by: NSong Liu <songliubraving@fb.com>

For write-behind mode, we think write IO is complete once it has
reached all the non-writemostly devices. It works fine for single
queue devices.

But for multiqueue device, if there are lots of IOs come from upper
layer, then the write-behind device could issue those IOs to different
queues, depends on the each queue's delay, so there is no guarantee
that those IOs can arrive in order.

To address the issue, we need to check the collision among write
behind IOs, we can only continue without collision, otherwise wait
for the completion of previous collisioned IO.

And WBCollision is introduced for multiqueue device which is worked
under write-behind mode.

But this patch doesn't handle below cases which could have the data
inconsistency issue as well, these cases will be handled in later
patches.

1. modify max_write_behind by write backlog node.
2. add or remove array's bitmap dynamically.
3. the change of member disk.
Reviewed-by: NNeilBrown <neilb@suse.com>
Signed-off-by: NGuoqing Jiang <gqjiang@suse.com>
Signed-off-by: NSong Liu <songliubraving@fb.com>

Adjust the f2fs tracing code to use newly introduced block layer
function blk_op_str() which converts the REQ_OP_XXX into the string
XXX.
Reviewed-by: NChao Yu <yuchao0@huawei.com>
Signed-off-by: NChaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Improve the print_req_error with additional request fields which are
helpful for debugging. Use newly introduced blk_op_str() to print the
REQ_OP_XXX in the string format.
Reviewed-by: NChao Yu <yuchao0@huawei.com>
Signed-off-by: NChaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Now that we've a helper function blk_op_str() to convert the
REQ_OP_XXX to string XXX, adjust the code to use that. Get rid of
the duplicate array op_name which is now present in the blk-core.c
which we renamed it to "blk_op_name" and open coding in the
blk-mq-debugfs.c.
Reviewed-by: NBart Van Assche <bvanassche@acm.org>
Signed-off-by: NChaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

In order to centralize the REQ_OP_XXX to string conversion which can be
used in the block layer and different places in the kernel like f2fs,
this patch adds a new helper function along with an array similar to the
one present in the blk-mq-debugfs.c.

We keep this helper functionality centralize under blk-core.c instead of
blk-mq-debugfs.c since blk-core.c is configured using CONFIG_BLOCK and
it will not be dependent on blk-mq-debugfs.c which is configured using
CONFIG_BLK_DEBUG_FS.

Next patch adjusts the code in the blk-mq-debugfs.c with newly
introduced helper.
Reviewed-by: NBart Van Assche <bvanassche@acm.org>
Signed-off-by: NChaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Print the calling function instead of print_req_error as a prefix, and
print the operation and op_flags separately instead of the whole field.
Reviewed-by: NBart Van Assche <bvanassche@acm.org>
Reviewed-by: NHannes Reinecke <hare@suse.de>
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NChaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

This option is entirely bfq specific, give it an appropinquate name.

Also make it depend on CONFIG_BFQ_GROUP_IOSCHED in Kconfig, as all
the functionality already does so anyway.
Acked-by: NTejun Heo <tj@kernel.org>
Acked-by: NPaolo Valente <paolo.valente@linaro.org>
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

This function was moved from core block code and is way to generic.
Fold it into the only caller and simplify it based on the actually
passed arguments.
Acked-by: NTejun Heo <tj@kernel.org>
Acked-by: NPaolo Valente <paolo.valente@linaro.org>
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

This structure and assorted infrastructure is only used by the bfq I/O
scheduler.  Move it there instead of bloating the common code.
Acked-by: NTejun Heo <tj@kernel.org>
Acked-by: NPaolo Valente <paolo.valente@linaro.org>
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

When sampling the blkcg counts we don't need atomics or per-cpu
variables.  Introduce a new structure just containing plain u64
counters.
Acked-by: NTejun Heo <tj@kernel.org>
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Returning a structure generates rather bad code, so switch to passing
by reference.  Also don't require the structure to be zeroed and add
to the 0-initialized counters, but actually set the counters to the
calculated value.
Acked-by: NTejun Heo <tj@kernel.org>
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Trying to break up the crazy statements to something readable.
Also switch to an unsigned counter as it can't ever turn negative.
Reviewed-by: NChaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
Acked-by: NTejun Heo <tj@kernel.org>
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

This function just has a few trivial assignments, has two callers with
one of them being in the fastpath.
Reviewed-by: NHannes Reinecke <hare@suse.com>
Reviewed-by: NChaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Now that we don't need to assign the front/back segment sizes, we can
duplicating the segs assignment for the split vs no-split case and
remove a whole chunk of boilerplate code.
Reviewed-by: NHannes Reinecke <hare@suse.com>
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Return the segement and let the callers assign them, which makes the code
a littler more obvious.  Also pass the request instead of q plus bio
chain, allowing for the use of rq_for_each_bvec.
Reviewed-by: NHannes Reinecke <hare@suse.com>
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

We only need the number of segments in the blk-mq submission path.
Remove the field from struct bio, and return it from a variant of
blk_queue_split instead of that it can passed as an argument to
those functions that need the value.

This also means we stop recounting segments except for cloning
and partial segments.

To keep the number of arguments in this how path down remove
pointless struct request_queue arguments from any of the functions
that had it and grew a nr_segs argument.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

lightnvm should have never used this function, as it is sending
passthrough requests, so switch it to blk_rq_append_bio like all the
other passthrough request users.  Inline blk_init_request_from_bio into
the only remaining caller.
Reviewed-by: NHannes Reinecke <hare@suse.com>
Reviewed-by: NMinwoo Im <minwoo.im.dev@gmail.com>
Reviewed-by: NJavier González <javier@javigon.com>
Reviewed-by: NMatias Bjørling <mb@lightnvm.io>
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

The priority field also makes sense for passthrough requests, so
initialize it in blk_rq_bio_prep.
Reviewed-by: NMinwoo Im <minwoo.im.dev@gmail.com>
Reviewed-by: NHannes Reinecke <hare@suse.com>
Reviewed-by: NChaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

As is, iolatency recognizes done_bio and cleanup as ending paths. If a
request is marked REQ_NOWAIT and fails to get a request, the bio is
cleaned up via rq_qos_cleanup() and ended in bio_wouldblock_error().
This results in underflowing the inflight counter. Fix this by only
accounting bios that were actually submitted.
Signed-off-by: NDennis Zhou <dennis@kernel.org>
Cc: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>