Register the CMB buffer as p2pmem and use the appropriate allocation
functions to create and destroy the IO submission queues.

If the CMB supports WDS and RDS, publish it for use as P2P memory by other
devices.

Kernels without CONFIG_PCI_P2PDMA will also no longer support NVMe CMB.
However, seeing the main use-cases for the CMB is P2P operations, this
seems like a reasonable dependency.

We drop the __iomem safety on the buffer seeing that, by convention, it's
safe to directly access memory mapped by memremap()/devm_memremap_pages().
Architectures where this is not safe will not be supported by memremap()
and therefore will not support PCI P2P and have no support for CMB.
Signed-off-by: NLogan Gunthorpe <logang@deltatee.com>
Signed-off-by: NBjorn Helgaas <bhelgaas@google.com>
Reviewed-by: NKeith Busch <keith.busch@intel.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>

In many architectures loads may be reordered with older stores to
different locations.  In the nvme driver the following two operations
could be reordered:

 - Write shadow doorbell (dbbuf_db) into memory.
 - Read EventIdx (dbbuf_ei) from memory.

This can result in a potential race condition between driver and VM host
processing requests (if given virtual NVMe controller has a support for
shadow doorbell).  If that occurs, then the NVMe controller may decide to
wait for MMIO doorbell from guest operating system, and guest driver may
decide not to issue MMIO doorbell on any of subsequent commands.

This issue is purely timing-dependent one, so there is no easy way to
reproduce it. Currently the easiest known approach is to run "Oracle IO
Numbers" (orion) that is shipped with Oracle DB:

orion -run advanced -num_large 0 -size_small 8 -type rand -simulate \
	concat -write 40 -duration 120 -matrix row -testname nvme_test

Where nvme_test is a .lun file that contains a list of NVMe block
devices to run test against. Limiting number of vCPUs assigned to given
VM instance seems to increase chances for this bug to occur. On test
environment with VM that got 4 NVMe drives and 1 vCPU assigned the
virtual NVMe controller hang could be observed within 10-20 minutes.
That correspond to about 400-500k IO operations processed (or about
100GB of IO read/writes).

Orion tool was used as a validation and set to run in a loop for 36
hours (equivalent of pushing 550M IO operations). No issues were
observed. That suggest that the patch fixes the issue.

Fixes: f9f38e33 ("nvme: improve performance for virtual NVMe devices")
Signed-off-by: NMichal Wnukowski <wnukowski@google.com>
Reviewed-by: NKeith Busch <keith.busch@intel.com>
Reviewed-by: NSagi Grimberg <sagi@grimberg.me>
[hch: updated changelog and comment a bit]
Signed-off-by: NChristoph Hellwig <hch@lst.de>

When the user supplies a ctrl_loss_tmo < 0, we warn them that this will
cause the fabrics layer to attempt reconnection forever.  However, in
reality the fabrics layer never attempts to reconnect because the
condition to test whether we should reconnect is backwards in this case.
Signed-off-by: NTal Shorer <tal.shorer@gmail.com>
Reviewed-by: NChaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
Signed-off-by: NChristoph Hellwig <hch@lst.de>

NVMe 1.3 TP 4005 introduces new filed (NSATTR). This field indicates
whether given namespace is write protected or not. This patch sets the
gendisk associated with the namespace to read only based on the identify
namespace nsattr field.
Signed-off-by: NChaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
Signed-off-by: NChristoph Hellwig <hch@lst.de>

When the initial discovery fails the subsystem hasn't been setup yet
in nvme_mpath_stop, and we can't dereference ctrl->subsys.

Fixes: 0d0b660f ("nvme: add ANA support")
Signed-off-by: NHannes Reinecke <hare@suse.com>
Signed-off-by: NChristoph Hellwig <hch@lst.de>

A minor version number increase should not break backwards
compatibility.

Fixes: 3cb98f84 ("lightnvm: add minor version to generic geometry")
Reviewed-by: NJavier González <javier@cnexlabs.com>
Signed-off-by: NMatias Bjørling <mb@lightnvm.io>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Also moved the logic of the remapping to the nvme core driver instead
of implementing it in the nvme pci driver. This way all the other nvme
transport drivers will benefit from it (in case they'll implement metadata
support).
Suggested-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NMartin K. Petersen <martin.petersen@oracle.com>
Acked-by: NKeith Busch <keith.busch@intel.com>
Signed-off-by: NMax Gurtovoy <maxg@mellanox.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Currently this function is implemented in the scsi layer, but it's
actual place should be the block layer since T10-PI is a general
data integrity feature that is used in the nvme protocol as well.
Suggested-by: NChristoph Hellwig <hch@lst.de>
Cc: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: NMax Gurtovoy <maxg@mellanox.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Add support for Asynchronous Namespace Access as specified in NVMe 1.3
TP 4004.  With ANA each namespace attached to a controller belongs to an
ANA group that describes the characteristics of accessing the namespaces
through this controller.  In the optimized and non-optimized states
namespaces can be accessed regularly, although in a multi-pathing
environment we should always prefer to access a namespace through a
controller where an optimized relationship exists.  Namespaces in
Inaccessible, Permanent-Loss or Change state for a given controller
should not be accessed.

The states are updated through reading the ANA log page, which is read
once during controller initialization, whenever the ANA change notice
AEN is received, or when one of the ANA specific status codes that
signal a state change is received on a command.

The ANA state is kept in the nvme_ns structure, which makes the checks in
the fast path very simple.  Updating the ANA state when reading the log
page is also very simple, the only downside is that finding the initial
ANA state when scanning for namespaces is a bit cumbersome.

The gendisk for a ns_head is only registered once a live path for it
exists.  Without that the kernel would hang during partition scanning.

Includes fixes and improvements from Hannes Reinecke.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NKeith Busch <keith.busch@intel.com>
Reviewed-by: NMartin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: NJohannes Thumshirn <jthumshirn@suse.de>

Now that we just call out to blk_path_error there isn't really any good
reason to not merge it into the only caller.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NKeith Busch <keith.busch@intel.com>
Reviewed-by: NSagi Grimberg <sagi@grimberg.me>
Reviewed-by: NMartin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: NHannes Reinecke <hare@suse.com>
Reviewed-by: NJohannes Thumshirn <jthumshirn@suse.de>

Merge nvme_get_log and nvme_get_log_ext into a single helper, which takes
a plain nsid instead of the nvme_ns pointer.  Also add support for the
log specific field while we're at it.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NKeith Busch <keith.busch@intel.com>
Reviewed-by: NSagi Grimberg <sagi@grimberg.me>
Reviewed-by: NMartin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: NHannes Reinecke <hare@suse.com>
Reviewed-by: NJohannes Thumshirn <jthumshirn@suse.de>

Instead of declaring and passing a dummy 'bad_wr' pointer, pass NULL
as third argument to ib_post_(send|recv|srq_recv)().
Signed-off-by: NBart Van Assche <bart.vanassche@wdc.com>
Reviewed-by: NSagi Grimberg <sagi@grimberg.me>
Reviewed-by: NMax Gurtovoy <maxg@mellanox.com>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

We follow the same queue teardown sequence in delete, reset and error
recovery. Centralize the logic.  This patch does not change any
functionality.
Signed-off-by: NSagi Grimberg <sagi@grimberg.me>
Signed-off-by: NChristoph Hellwig <hch@lst.de>

Centralize controller sequence to a single routine that correctly cleans
up after failures instead of having multiple apperances in several flows
(create, reset, reconnect).

One thing that we also gain here are the sanity/boundary checks also
when connecting back to a dynamic controller.
Signed-off-by: NSagi Grimberg <sagi@grimberg.me>
Signed-off-by: NChristoph Hellwig <hch@lst.de>

If the controller is going away, we need to unquiesce the IO queues so
that all pending request can fail gracefully before moving forward with
controller deletion. Do that before we destroy the IO queues so
blk_cleanup_queue won't block in freeze.
Signed-off-by: NSagi Grimberg <sagi@grimberg.me>
Signed-off-by: NChristoph Hellwig <hch@lst.de>

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.
Signed-off-by: NGustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: NChristoph Hellwig <hch@lst.de>

This will print the disk name to the nvme event trace for io requests so
a user can better distinguish traffic to different disks. This can be used
to  create disk based filters. For example, to see only nvme0n2 traffic:

  echo "disk == \"nvme0n2\"" > /sys/kernel/debug/tracing/events/nvme/filter
Signed-off-by: NKeith Busch <keith.busch@intel.com>
Reviewed-by: NSagi Grimberg <sagi@grimberg.me>
Reviewed-by: NJohannes Thumshirn <jthumshirn@suse.de>
[hch: turned __assign_disk_name into an inline function]
Signed-off-by: NChristoph Hellwig <hch@lst.de>

This appends the controller instance to the nvme trace buffer to
distinguish which controller is dispatching and completing a command.
Signed-off-by: NKeith Busch <keith.busch@intel.com>
Reviewed-by: NSagi Grimberg <sagi@grimberg.me>
Reviewed-by: NJohannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: NChristoph Hellwig <hch@lst.de>

The revised if_ready checks skipped over the case of returning error when
the controller is being deleted.  Instead it was returning BUSY, which
caused the ios to retry, which caused the ns delete to hang waiting for
the ios to drain.

Stack trace of hang looks like:
 kworker/u64:2   D    0    74      2 0x80000000
 Workqueue: nvme-delete-wq nvme_delete_ctrl_work [nvme_core]
 Call Trace:
  ? __schedule+0x26d/0x820
  schedule+0x32/0x80
  blk_mq_freeze_queue_wait+0x36/0x80
  ? remove_wait_queue+0x60/0x60
  blk_cleanup_queue+0x72/0x160
  nvme_ns_remove+0x106/0x140 [nvme_core]
  nvme_remove_namespaces+0x7e/0xa0 [nvme_core]
  nvme_delete_ctrl_work+0x4d/0x80 [nvme_core]
  process_one_work+0x160/0x350
  worker_thread+0x1c3/0x3d0
  kthread+0xf5/0x130
  ? process_one_work+0x350/0x350
  ? kthread_bind+0x10/0x10
  ret_from_fork+0x1f/0x30

Extend nvmf_fail_nonready_command() to supply the controller pointer so
that the controller state can be looked at. Fail any io to a controller
that is deleting.

Fixes: 3bc32bb1 ("nvme-fabrics: refactor queue ready check")
Fixes: 35897b92 ("nvme-fabrics: fix and refine state checks in __nvmf_check_ready")
Signed-off-by: NJames Smart <james.smart@broadcom.com>
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Tested-by: NEwan D. Milne <emilne@redhat.com>
Reviewed-by: NEwan D. Milne <emilne@redhat.com>

We can not match a command to its completion based on the command
id alone. We need the submitting queue identifier to pair with the
completion, so this patch adds that to the trace buffer.

This patch is also collapsing the admin and IO submission traces into a
single one so we don't need to duplicate this and creating unnecessary
code branches: we know if the command is an admin vs IO based on the qid.

And since we're here, the patch fixes code formatting in the area.
Signed-off-by: NKeith Busch <keith.busch@intel.com>
Reviewed-by: NSagi Grimberg <sagi@grimberg.me>
Reviewed-by: NJohannes Thumshirn <jthumshirn@suse.de>
[hch: move the qid helper to nvme.h and made it an inline function]
Signed-off-by: NChristoph Hellwig <hch@lst.de>

We will need to reference the controller in the setup and completion
time for tracing and future traffic based keep alive support.
Reviewed-by: NJohannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: NSagi Grimberg <sagi@grimberg.me>
Signed-off-by: NChristoph Hellwig <hch@lst.de>

Allow up to 4 segments of inline data for NVMF WRITE operations. This
reduces latency for small WRITEs by removing the need for the target to
issue a READ WR for IB, or a REG_MR + READ WR chain for iWarp.

Also cap the inline segments used based on the limitations of the
device.
Reviewed-by: NSagi Grimberg <sagi@grimberg.me>
Reviewed-by: NMax Gurtovoy <maxg@mellanox.com>
Signed-off-by: NSteve Wise <swise@opengridcomputing.com>
Signed-off-by: NChristoph Hellwig <hch@lst.de>

Currently, the code initializes the keep alive work item whenever
nvme_start_keep_alive() is called. However, this routine is called
several times while reconnecting, etc. Although it's hoped that keep
alive is always disabled and not scheduled when start is called,
re-initing if it were scheduled or completing can have very bad
side effects. There's no need for re-initialization.

Move the keep_alive work item and cmd struct initialization to
controller init.
Signed-off-by: NJames Smart <james.smart@broadcom.com>
Signed-off-by: NChristoph Hellwig <hch@lst.de>

The old code in nvme_user_cmd() passed the userspace virtual address
from nvme_passthru_cmd.metadata as the length of the metadata buffer
as well as the address to nvme_submit_user_cmd().

Fixes: 63263d60 ("nvme: Use metadata for passthrough commands")
Signed-off-by: NRoland Dreier <roland@purestorage.com>
Reviewed-by: NKeith Busch <keith.busch@intel.com>
Signed-off-by: NChristoph Hellwig <hch@lst.de>

Avoid excuting set_feature command if there is no supported bit in
Optional Asynchronous Events Supported (OAES).

Fixes: c0561f82 ("nvme: submit AEN event configuration on startup")
Reviewed-by: NSagi Grimberg <sagi@grimberg.me>
Signed-off-by: NWeiping Zhang <zhangweiping@didichuxing.com>
Signed-off-by: NChristoph Hellwig <hch@lst.de>

If the controller supports effects and goes down during the passthru admin
command we will deadlock during namespace revalidation.

[  363.488275] INFO: task kworker/u16:5:231 blocked for more than 120 seconds.
[  363.488290]       Not tainted 4.17.0+ #2
[  363.488296] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
[  363.488303] kworker/u16:5   D    0   231      2 0x80000000
[  363.488331] Workqueue: nvme-reset-wq nvme_reset_work [nvme]
[  363.488338] Call Trace:
[  363.488385]  schedule+0x75/0x190
[  363.488396]  rwsem_down_read_failed+0x1c3/0x2f0
[  363.488481]  call_rwsem_down_read_failed+0x14/0x30
[  363.488504]  down_read+0x1d/0x80
[  363.488523]  nvme_stop_queues+0x1e/0xa0 [nvme_core]
[  363.488536]  nvme_dev_disable+0xae4/0x1620 [nvme]
[  363.488614]  nvme_reset_work+0xd1e/0x49d9 [nvme]
[  363.488911]  process_one_work+0x81a/0x1400
[  363.488934]  worker_thread+0x87/0xe80
[  363.488955]  kthread+0x2db/0x390
[  363.488977]  ret_from_fork+0x35/0x40

Fixes: 84fef62d ("nvme: check admin passthru command effects")
Signed-off-by: NScott Bauer <scott.bauer@intel.com>
Reviewed-by: NKeith Busch <keith.busch@linux.intel.com>
Signed-off-by: NChristoph Hellwig <hch@lst.de>

For devices that does not specify a limit on its transfer size, the
get_chk_meta command may send down a single I/O retrieving the full
chunk metadata table. Resulting in large 2-4MB I/O requests. Instead,
split up the I/Os to a maximum of 256KB and issue them separately to
reduce memory requirements.
Signed-off-by: NMatias Bjørling <mb@lightnvm.io>
Reviewed-by: NJavier González <javier@cnexlabs.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Since both blk_old_get_request() and blk_mq_alloc_request() initialize
rq->__data_len to zero, it is not necessary to initialize that member
in nvme_nvm_alloc_request(). Hence remove the rq->__data_len
initialization from nvme_nvm_alloc_request().
Signed-off-by: NBart Van Assche <bart.vanassche@wdc.com>
Signed-off-by: NMatias Bjørling <mb@lightnvm.io>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

The nvme driver specific structures need to be initialized prior to
enabling the generic controller so we can unwind on failure with out
using the reference counting callbacks so that 'probe' and 'remove'
can be symmetric.

The newly added iod_mempool is the only resource that was being
allocated out of order, and a failure there would leak the generic
controller memory. This patch just moves that allocation above the
controller initialization.

Fixes: 943e942e ("nvme-pci: limit max IO size and segments to avoid high order allocations")
Reported-by: NWeiping Zhang <zwp10758@gmail.com>
Signed-off-by: NKeith Busch <keith.busch@intel.com>
Signed-off-by: NChristoph Hellwig <hch@lst.de>

If reconnect/reset failed where the controller async event buffer
was freed, we might end up freeing it again as we call
nvme_rdma_destroy_admin_queue again in the remove path. Given that
the sequence is guaranteed to serialize by .ctrl_stop, we simply
set ctrl->async_event_sqe.data to NULL and don't free it in future
visits.
Reported-by: NMax Gurtovoy <maxg@mellanox.com>
Tested-by: NMax Gurtovoy <maxg@mellanox.com>
Signed-off-by: NSagi Grimberg <sagi@grimberg.me>
Signed-off-by: NChristoph Hellwig <hch@lst.de>

nvme requires an sg table allocation for each request. If the request
is large, then the allocation can become quite large. For instance,
with our default software settings of 1280KB IO size, we'll need
10248 bytes of sg table. That turns into a 2nd order allocation,
which we can't always guarantee. If we fail the allocation, blk-mq
will retry it later. But there's no guarantee that we'll EVER be
able to allocate that much contigious memory.

Limit the IO size such that we never need more than a single page
of memory. That's a lot faster and more reliable. Then back that
allocation with a mempool, so that we know we'll always be able
to succeed the allocation at some point.
Signed-off-by: NJens Axboe <axboe@kernel.dk>
Acked-by: NKeith Busch <keith.busch@intel.com>
Signed-off-by: NChristoph Hellwig <hch@lst.de>

There is race between nvme_remove and nvme_reset_work that can
lead to io hang.

nvme_remove                    nvme_reset_work
                               -> nvme_remove_dead_ctrl
                                 -> nvme_dev_disable
                                   -> quiesce request_queue
                                 -> queue remove_work
-> cancel_work_sync reset_work
-> nvme_remove_namespaces
  -> splice ctrl->namespaces
                               nvme_remove_dead_ctrl_work
                               -> nvme_kill_queues
  -> nvme_ns_remove               do nothing
    -> blk_cleanup_queue
      -> blk_freeze_queue

Finally, the request_queue is quiesced state when wait freeze,
we will get io hang here. To fix it, move the nvme_kill_queues
from nvme_remove_dead_ctrl_work to nvme_remove_dead_ctrl.
Suggested-by: NKeith Busch <keith.busch@linux.intel.com>
Signed-off-by: NJianchao Wang <jianchao.w.wang@oracle.com>
Reviewed-by: NKeith Busch <keith.busch@intel.com>
Signed-off-by: NChristoph Hellwig <hch@lst.de>

Rather than leaving io queues quiesced after tearing down an association,
restart them. This allows ios to be replayed, with fastfail ios terminating
and non-fastfail getting into loops of retry.

This follows rdma's lead.
Signed-off-by: NJames Smart <james.smart@broadcom.com>
Reviewed-by: NSagi Grimberg <sagi@grimber.me>
Signed-off-by: NChristoph Hellwig <hch@lst.de>

That is user argument, and theoretically controller limits can change
over time (over reconnects/resets).  Instead, use the sqsize controller
attribute to check queue depth boundaries and use it to the tagset
allocation.
Signed-off-by: NSagi Grimberg <sagi@grimberg.me>
Signed-off-by: NChristoph Hellwig <hch@lst.de>

The race is between completing the request at error recovery work and
rdma completions.  If we cancel the request before getting the good
rdma completion we get a NULL deref of the request MR at
nvme_rdma_process_nvme_rsp().

When Canceling the request we return its mr to the mr pool (set mr to
NULL) and also unmap its data.  Canceling the requests while the rdma
queues are active is not safe.  Because rdma queues are active and we
get good rdma completions that can use the mr pointer which may be NULL.
Completing the request too soon may lead also to performing DMA to/from
user buffers which might have been already unmapped.

The commit fixes the race by draining the QP before starting the abort
commands mechanism.
Signed-off-by: NIsrael Rukshin <israelr@mellanox.com>
Reviewed-by: NMax Gurtovoy <maxg@mellanox.com>
Signed-off-by: NSagi Grimberg <sagi@grimberg.me>
Signed-off-by: NChristoph Hellwig <hch@lst.de>

If nvme_rdma_configure_admin_queue fails before we allocated
the async event buffer, we will falsly free it because
nvme_rdma_free_queue is freeing it. Fix it by allocating the buffer right
after nvme_rdma_alloc_queue and free it right before nvme_rdma_queue_free
to maintain orderly reverse cleanup sequence.
Reported-by: NIsrael Rukshin <israelr@mellanox.com>
Signed-off-by: NSagi Grimberg <sagi@grimberg.me>
Reviewed-by: NMax Gurtovoy <maxg@mellanox.com>
Signed-off-by: NChristoph Hellwig <hch@lst.de>

Failures after nvme_init_ctrl will defer resource cleanups to .free_ctrl
when the reference is released, hence we should not free the controller
queues for these failures.

Fix that by moving controller queues allocation before controller
initialization and correctly freeing them for failures before
initialization and skip them for failures after initialization.
Signed-off-by: NSagi Grimberg <sagi@grimberg.me>
Signed-off-by: NChristoph Hellwig <hch@lst.de>

 - make sure we only allow internally generates commands in any non-live
   state
 - only allow connect commands on non-live queues when actually in the
   new or connecting states
 - treat all other non-live, non-dead states the same as a default
   cach-all

This fixes a regression where we could not shutdown a controller
orderly as we didn't allow the internal generated Property Set
command, and also ensures we don't accidentally let a Connect command
through in the wrong state.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NJames Smart <james.smart@broadcom.com>

In the ADMIN_ONLY state we don't have any I/O queues, but we should accept
all admin commands without further checks.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NJohannes Thumshirn <jthumshirn@suse.de>
Reviewed-by: N James Smart <james.smart@broadcom.com>

Move the is_connected check to the fibre channel transport, as it has no
meaning for other transports.  To facilitate this split out a new
nvmf_fail_nonready_command helper that is called by the transport when
it is asked to handle a command on a queue that is not ready.

Also avoid a function call for the queue live fast path by inlining
the check.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NJames Smart <james.smart@broadcom.com>