With recent CQ handling improvements we can now move the locking into
__nvme_submit_cmd.  Also remove the local tail variable to make the code
more obvious, remove the __ prefix in the name, and fix the comments
describing the function.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NJens Axboe <axboe@kernel.dk>
Reviewed-by: NMax Gurtovoy <maxg@mellanox.com>

The block layer's timeout handling currently prevents drivers from
completing commands outside the timeout callback once blk-mq decides
they've expired. If a device breaks, this could potentially create many
thousands of timed out commands. There's nothing of value to be gleaned
from observing each of those messages, so this patch adds a rate limit
on them.
Signed-off-by: NKeith Busch <keith.busch@intel.com>
Signed-off-by: NChristoph Hellwig <hch@lst.de>

The current checks for whether a new controller request "matches" an
existing controller ignores controller state and checks identity strings.
There are cases where an existing controller may be in its last steps of
deletion when they are "matched" by a new connection.

Change the behavior so that the new connection ignores controllers that
are deleted.
Signed-off-by: NJames Smart <james.smart@broadcom.com>
Signed-off-by: NChristoph Hellwig <hch@lst.de>

NVMe always completes the request before returning from ->timeout, either
by polling for it, or by disabling the controller.  Return BLK_EH_DONE so
that the block layer doesn't even try to complete it again.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NHannes Reinecke <hare@suse.com>
Reviewed-by: NJohannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

If nvme_get_effects_log() failed the 'id' buffer from the previous
nvme_identify_ctrl() call will never be freed.
Signed-off-by: NHannes Reinecke <hare@suse.com>
Reviewed-by: NJohannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: NChristoph Hellwig <hch@lst.de>

The host nqn actually is smaller than the space reserved for it,
so we should be using strlcpy to keep KASAN happy.
Signed-off-by: NHannes Reinecke <hare@suse.com>
Signed-off-by: NChristoph Hellwig <hch@lst.de>

The whole point of the discovery controller is that it can accept
multiple connections. Additionally the cmic field is not even defined for
the discovery controller identify page.
Signed-off-by: NHannes Reinecke <hare@suse.com>
Reviewed-by: NJames Smart <james.smart@broadcom.com>
Signed-off-by: NChristoph Hellwig <hch@lst.de>

When connecting to the discovery controller we have certain defaults
to observe, so centralize them to avoid inconsistencies due to argument
ordering.
Signed-off-by: NHannes Reinecke <hare@suse.com>
Reviewed-by: NJames Smart <james.smart@broadcom.com>
Signed-off-by: NChristoph Hellwig <hch@lst.de>

After creating the nvme controller, nvmf_create_ctrl() validates
the newly created subsysnqn vs the one specified by the options.

In general, this is an unnecessary check as the Connect message
should implicitly ensure this value matches.

With the change to the FC transport to do an asynchronous connect
for the first association create, the transport will return to
nvmf_create_ctrl() before that first association has been established,
thus the subnqn will not yet be set.

Remove the unnecessary validation.
Signed-off-by: NJames Smart <james.smart@broadcom.com>
Reviewed-by: NHannes Reinecke <hare@suse.com>
Signed-off-by: NChristoph Hellwig <hch@lst.de>

Current code will set DNR if the controller is deleting or there is
an error during controller init. None of this is necessary.

Remove the code that sets DNR
Signed-off-by: NJames Smart <james.smart@broadcom.com>
Reviewed-by: NHannes Reinecke <hare@suse.com>
Signed-off-by: NChristoph Hellwig <hch@lst.de>

For any failure after nvme_rdma_start_queue in
nvme_rdma_configure_admin_queue, the admin queue will be freed with the
NVME_RDMA_Q_LIVE flag still set.  Once nvme_rdma_stop_queue is invoked,
that will cause a use-after-free.
BUG: KASAN: use-after-free in rdma_disconnect+0x1f/0xe0 [rdma_cm]

To fix it, call nvme_rdma_stop_queue for all the failed cases after
nvme_rdma_start_queue.
Signed-off-by: NJianchao Wang <jianchao.w.wang@oracle.com>
Suggested-by: NSagi Grimberg <sagi@grimberg.me>
Reviewed-by: NMax Gurtovoy <maxg@mellanox.com>
Signed-off-by: NChristoph Hellwig <hch@lst.de>

The nvme timeout handling doesn't do anything if the pci channel is
offline, which is the case when recovering from PCI error event, so it
was a bad idea to sync the controller reset in this state. This patch
flushes the reset work in the error_resume callback instead when the
channel is back to online. This keeps AER handling serialized and
can recover from timeouts.

Link: https://bugzilla.kernel.org/show_bug.cgi?id=199757
Fixes: cc1d5e74 ("nvme/pci: Sync controller reset for AER slot_reset")
Reported-by: NAlex Gagniuc <mr.nuke.me@gmail.com>
Tested-by: NAlex Gagniuc <mr.nuke.me@gmail.com>
Signed-off-by: NKeith Busch <keith.busch@intel.com>
Signed-off-by: NChristoph Hellwig <hch@lst.de>

Set cq_vector after alloc cq/sq, otherwise nvme_suspend_queue will invoke
free_irq for it and cause a 'Trying to free already-free IRQ  xxx'
warning if the create CQ/SQ command times out.
Signed-off-by: NJianchao Wang <jianchao.w.wang@oracle.com>
Reviewed-by: NKeith Busch <keith.busch@intel.com>
[hch: fixed to pass a s16 and clean up the comment]
Signed-off-by: NChristoph Hellwig <hch@lst.de>

Ternary operator have lower precedence then bitwise or, so 'cdw10' was
calculated wrong.
Signed-off-by: NIvan Bornyakov <brnkv.i1@gmail.com>
Reviewed-by: NMax Gurtovoy <maxg@mellanox.com>
Signed-off-by: NKeith Busch <keith.busch@intel.com>

When running blktest's nvme/005 with a lockdep enabled kernel the test
case fails due to the following lockdep splat in dmesg:

 =============================
 WARNING: suspicious RCU usage
 4.17.0-rc5 #881 Not tainted
 -----------------------------
 drivers/nvme/host/nvme.h:457 suspicious rcu_dereference_check() usage!

 other info that might help us debug this:

 rcu_scheduler_active = 2, debug_locks = 1
 3 locks held by kworker/u32:5/1102:
  #0:         (ptrval) ((wq_completion)"nvme-wq"){+.+.}, at: process_one_work+0x152/0x5c0
  #1:         (ptrval) ((work_completion)(&ctrl->scan_work)){+.+.}, at: process_one_work+0x152/0x5c0
  #2:         (ptrval) (&subsys->lock#2){+.+.}, at: nvme_ns_remove+0x43/0x1c0 [nvme_core]

The only caller of nvme_mpath_clear_current_path() is nvme_ns_remove()
which holds the subsys lock so it's likely a false positive, but when
using rcu_access_pointer(), we're telling rcu and lockdep that we're
only after the pointer falue.

Fixes: 32acab31 ("nvme: implement multipath access to nvme subsystems")
Signed-off-by: NJohannes Thumshirn <jthumshirn@suse.de>
Suggested-by: NPaul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NKeith Busch <keith.busch@intel.com>

If polling completions are racing with the IRQ triggered by a
completion, the IRQ handler will find no work and return IRQ_NONE.
This can trigger complaints about spurious interrupts:

[  560.169153] irq 630: nobody cared (try booting with the "irqpoll" option)
[  560.175988] CPU: 40 PID: 0 Comm: swapper/40 Not tainted 4.17.0-rc2+ #65
[  560.175990] Hardware name: Intel Corporation S2600STB/S2600STB, BIOS SE5C620.86B.00.01.0010.010920180151 01/09/2018
[  560.175991] Call Trace:
[  560.175994]  <IRQ>
[  560.176005]  dump_stack+0x5c/0x7b
[  560.176010]  __report_bad_irq+0x30/0xc0
[  560.176013]  note_interrupt+0x235/0x280
[  560.176020]  handle_irq_event_percpu+0x51/0x70
[  560.176023]  handle_irq_event+0x27/0x50
[  560.176026]  handle_edge_irq+0x6d/0x180
[  560.176031]  handle_irq+0xa5/0x110
[  560.176036]  do_IRQ+0x41/0xc0
[  560.176042]  common_interrupt+0xf/0xf
[  560.176043]  </IRQ>
[  560.176050] RIP: 0010:cpuidle_enter_state+0x9b/0x2b0
[  560.176052] RSP: 0018:ffffa0ed4659fe98 EFLAGS: 00000246 ORIG_RAX: ffffffffffffffdd
[  560.176055] RAX: ffff9527beb20a80 RBX: 000000826caee491 RCX: 000000000000001f
[  560.176056] RDX: 000000826caee491 RSI: 00000000335206ee RDI: 0000000000000000
[  560.176057] RBP: 0000000000000001 R08: 00000000ffffffff R09: 0000000000000008
[  560.176059] R10: ffffa0ed4659fe78 R11: 0000000000000001 R12: ffff9527beb29358
[  560.176060] R13: ffffffffa235d4b8 R14: 0000000000000000 R15: 000000826caed593
[  560.176065]  ? cpuidle_enter_state+0x8b/0x2b0
[  560.176071]  do_idle+0x1f4/0x260
[  560.176075]  cpu_startup_entry+0x6f/0x80
[  560.176080]  start_secondary+0x184/0x1d0
[  560.176085]  secondary_startup_64+0xa5/0xb0
[  560.176088] handlers:
[  560.178387] [<00000000efb612be>] nvme_irq [nvme]
[  560.183019] Disabling IRQ #630

A previous commit removed ->cqe_seen that was handling this case,
but we need to handle this a bit differently due to completions
now running outside the queue lock. Return IRQ_HANDLED from the
IRQ handler, if the completion ring head was moved since we last
saw it.

Fixes: 5cb525c8 ("nvme-pci: handle completions outside of the queue lock")
Reported-by: NKeith Busch <keith.busch@intel.com>
Reviewed-by: NKeith Busch <keith.busch@intel.com>
Tested-by: NKeith Busch <keith.busch@intel.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Since we aren't sharing the lock for completions now, we don't
have to make it IRQ safe.
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJens Axboe <axboe@kernel.dk>
Signed-off-by: NChristoph Hellwig <hch@lst.de>

This is now feasible. We protect the submission queue ring with
->sq_lock, and the completion side with ->cq_lock.
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJens Axboe <axboe@kernel.dk>
Signed-off-by: NChristoph Hellwig <hch@lst.de>

Split the completion of events into a two part process:

1) Reap the events inside the queue lock
2) Complete the events outside the queue lock

Since we never wrap the queue, we can access it locklessly after we've
updated the completion queue head. This patch started off with batching
events on the stack, but with this trick we don't have to. Keith Busch
<keith.busch@intel.com> came up with that idea.

Note that this kills the ->cqe_seen as well. I haven't been able to
trigger any ill effects of this. If we do race with polling every so
often, it should be rare enough NOT to trigger any issues.
Signed-off-by: NJens Axboe <axboe@kernel.dk>
Signed-off-by: NKeith Busch <keith.busch@intel.com>
[hch: refactored, restored poll early exit optimization]
Signed-off-by: NChristoph Hellwig <hch@lst.de>

We only clear it dynamically in nvme_suspend_queue(). When we do, ensure
to do a full flush so that any nvme_queue_rq() invocation will see it.

Ideally we'd kill this check completely, but we're using it to flush
requests on a dying queue.
Signed-off-by: NJens Axboe <axboe@kernel.dk>
Signed-off-by: NChristoph Hellwig <hch@lst.de>

We always check the completion queue after submitting, but in my testing
this isn't a win even on DRAM/xpoint devices. In some cases it's
actually worse. Kill it.
Signed-off-by: NJens Axboe <axboe@kernel.dk>
Signed-off-by: NKeith Busch <keith.busch@intel.com>
Signed-off-by: NChristoph Hellwig <hch@lst.de>

We always look at the current CQ head and phase, so don't pass these
as separate arguments, and rename the function to nvme_cqe_pending.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

We'll need that in the PCIe driver soon as we'll read it straight off the
CQ.
Signed-off-by: NChristoph Hellwig <hch@lst.de>

AER handling expects a successful return from slot_reset means the
driver made the device functional again. The nvme driver had been using
an asynchronous reset to recover the device, so the device
may still be initializing after control is returned to the
AER handler. This creates problems for subsequent event handling,
causing the initializion to fail.

This patch fixes that by syncing the controller reset before returning
to the AER driver, and reporting the true state of the reset.

Link: https://bugzilla.kernel.org/show_bug.cgi?id=199657Reported-by: NAlex Gagniuc <mr.nuke.me@gmail.com>
Cc: Sinan Kaya <okaya@codeaurora.org>
Cc: Bjorn Helgaas <bhelgaas@google.com>
Cc: stable@vger.kernel.org
Tested-by: NAlex Gagniuc <mr.nuke.me@gmail.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NMartin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: NKeith Busch <keith.busch@intel.com>

It is possible the driver's remove may have freed the controller if
the remove callback is invoked prior to the async_schedule starting
the reset_work. This patch fixes that by holding a reference on the
controller.
Reported-by: NMikulas Patocka <mpatocka@redhat.com>
Signed-off-by: NKeith Busch <keith.busch@intel.com>

When CONFIG_NVME_MULTIPATH is set, but we're not using nvme to multipath,
namespaces with multiple paths were not creating unique names due to
reusing the same instance number from the namespace's head.

This patch fixes this by falling back to the non-multipath naming method
when the parameter disabled using multipath.
Reported-by: NMike Snitzer <snitzer@redhat.com>
Signed-off-by: NKeith Busch <keith.busch@intel.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

We can't allow the user to change multipath settings at runtime, as this
will create naming conflicts due to the different naming schemes used
for each mode.
Signed-off-by: NKeith Busch <keith.busch@intel.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

If the command a separate metadata buffer attached, the request needs
to have the integrity flag set so the driver knows to map it.
Signed-off-by: NKeith Busch <keith.busch@intel.com>
Reviewed-by: NMartin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

When specifying same string type option several times,
current option parsing may cause memory leak. Hence,
call kfree for previous one in this case.
Signed-off-by: NChengguang Xu <cgxu519@gmx.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NSagi Grimberg <sagi@grimberg.me>
Signed-off-by: NKeith Busch <keith.busch@intel.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Currently nvme reconfigures discard for every disk revalidation. This
is problematic because any O_WRONLY or O_RDWR open will trigger a
partition scan through udev/systemd, and we will reconfigure discard.
This blows away any user settings, like discard_max_bytes.

Only re-configure the user settable settings if we need to.
Signed-off-by: NJens Axboe <axboe@kernel.dk>
[removed redundant queue flag setting]
Signed-off-by: NKeith Busch <keith.busch@intel.com>

This patch schedules the initial controller reset in an async_domain
so that it can be synchronized from wait_for_device_probe(). This way
the kernel waits for the initial nvme controller scan to complete for
all devices before proceeding with the boot sequence, which may have
nvme dependencies.
Reported-by: NMikulas Patocka <mpatocka@redhat.com>
Tested-by: NMikulas Patocka <mpatocka@redhat.com>
Signed-off-by: NKeith Busch <keith.busch@intel.com>

NVME_RDMA code depends on INFINIBAND_ADDR_TRANS provided symbols.  So
declare the kconfig dependency.  This is necessary to allow for enabling
INFINIBAND without INFINIBAND_ADDR_TRANS.
Signed-off-by: NGreg Thelen <gthelen@google.com>
Cc: Tarick Bedeir <tarick@google.com>
Signed-off-by: NDoug Ledford <dledford@redhat.com>

Add a new lightnvm quirk to identify CNEX’s Granby controller.
Signed-off-by: NWei Xu <wxu@cnexlabs.com>
Reviewed-by: NJavier González <javier@cnexlabs.com>
Reviewed-by: NMatias Bjørling <mb@lightnvm.io>
Signed-off-by: NKeith Busch <keith.busch@intel.com>

Add Seagate Nytro Flash Storage nvme drive to quirk list for
NVME_QUIRK_DELAY_BEFORE_CHK_RDY, which solves a bug where the drive is
probed on hot-add before the firmare is ready, I/O errors are generated
while reading sector 0, and linux is "unable to read partition table".
Signed-off-by: NMicah Parrish <micah.parrish@hpe.com>
Reviewed-by: NMartin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: NKeith Busch <keith.busch@intel.com>

Keith reported that command submission and command completion
tracepoints have the order of the cmdid and qid fields swapped.

While it isn't easily possible to change the command submission
tracepoint, as there is a regression test parsing it in blktests we
can swap the command completion tracepoint to have the fields aligned.
Signed-off-by: NJohannes Thumshirn <jthumshirn@suse.de>
Reported-by: NKeith Busch <keith.busch@intel.com>
Reviewed-by: NJens Axboe <axboe@kernel.dk>
Signed-off-by: NKeith Busch <keith.busch@intel.com>

Provide a descriptive error in case an lport to rport association
isn't found when creating the FC-NVME controller.

Currently it's very hard to debug the reason for a failed connect
attempt without a look at the source.
Signed-off-by: NJohannes Thumshirn <jthumshirn@suse.de>
Reviewed-by: NJames Smart  <james.smart@broadcom.com>
Reviewed-by: NHannes Reinecke <hare@suse.com>
Signed-off-by: NKeith Busch <keith.busch@intel.com>

The nvmf_check_if_ready() checks that were added are very simplistic.
As such, the routine allows a lot of cases to fail ios during windows
of reset or re-connection. In cases where there are not multi-path
options present, the error goes back to the callee - the filesystem
or application. Not good.

The common routine was rewritten and calling syntax slightly expanded
so that per-transport is_ready routines don't need to be present.
The transports now call the routine directly. The routine is now a
fabrics routine rather than an inline function.

The routine now looks at controller state to decide the action to
take. Some states mandate io failure. Others define the condition where
a command can be accepted.  When the decision is unclear, a generic
queue-or-reject check is made to look for failfast or multipath ios and
only fails the io if it is so marked. Otherwise, the io will be queued
and wait for the controller state to resolve.

Admin commands issued via ioctl share a live admin queue with commands
from the transport for controller init. The ioctls could be intermixed
with the initialization commands. It's possible for the ioctl cmd to
be issued prior to the controller being enabled. To block this, the
ioctl admin commands need to be distinguished from admin commands used
for controller init. Added a USERCMD nvme_req(req)->rq_flags bit to
reflect this division and set it on ioctls requests.  As the
nvmf_check_if_ready() routine is called prior to nvme_setup_cmd(),
ensure that commands allocated by the ioctl path (actually anything
in core.c) preps the nvme_req(req) before starting the io. This will
preserve the USERCMD flag during execution and/or retry.
Signed-off-by: NJames Smart <james.smart@broadcom.com>
Reviewed-by: NSagi Grimberg <sagi@grimberg.e>
Reviewed-by: NJohannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: NKeith Busch <keith.busch@intel.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Signed-off-by: NKeith Busch <keith.busch@intel.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Also add error flow in case srcu initialization function fails.
Signed-off-by: NMax Gurtovoy <maxg@mellanox.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NKeith Busch <keith.busch@intel.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

The admin and first IO queues shared the first irq vector, which has an
affinity mask including cpu0. If a system allows cpu0 to be offlined,
the admin queue may not be usable if no other CPUs in the affinity mask
are online. This is a problem since unlike IO queues, there is only
one admin queue that always needs to be usable.

To fix, this patch allocates one pre_vector for the admin queue that
is assigned all CPUs, so will always be accessible. The IO queues are
assigned the remaining managed vectors.

In case a controller has only one interrupt vector available, the admin
and IO queues will share the pre_vector with all CPUs assigned.

Cc: Jianchao Wang <jianchao.w.wang@oracle.com>
Cc: Ming Lei <ming.lei@redhat.com>
Signed-off-by: NKeith Busch <keith.busch@intel.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NMing Lei <ming.lei@redhat.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>