Commit Graph

1372 Commits

Author SHA1 Message Date
Keith Busch 4726bcf30f nvme-pci: add missing unlock for reset error
The reset work holds a mutex to prevent races with removal modifying the
same resources, but was unlocking only on success. Unlock on failure
too.

Fixes: 5c959d73db ("nvme-pci: fix rapid add remove sequence")
Signed-off-by: Keith Busch <keith.busch@intel.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
2019-02-12 09:29:07 +01:00
Keith Busch 5c959d73db nvme-pci: fix rapid add remove sequence
A surprise removal may fail to tear down request queues if it is racing
with the initial asynchronous probe. If that happens, the remove path
won't see the queue resources to tear down, and the controller reset
path may create a new request queue on a removed device, but will not
be able to make forward progress, deadlocking the pci removal.

Protect setting up non-blocking resources from a shutdown by holding the
same mutex, and transition to the CONNECTING state after these resources
are initialized so the probe path may see the dead controller state
before dispatching new IO.

Link: https://bugzilla.kernel.org/show_bug.cgi?id=202081
Reported-by: Alex Gagniuc <Alex_Gagniuc@Dellteam.com>
Signed-off-by: Keith Busch <keith.busch@intel.com>
Tested-by: Alex Gagniuc <mr.nuke.me@gmail.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
2019-02-06 16:35:33 +01:00
Keith Busch e7ad43c3ed nvme: lock NS list changes while handling command effects
If a controller supports the NS Change Notification, the namespace
scan_work is automatically triggered after attaching a new namespace.

Occasionally the namespace scan_work may append the new namespace to the
list before the admin command effects handling is completed. The effects
handling unfreezes namespaces, but if it unfreezes the newly attached
namespace, its request_queue freeze depth will be off and we'll hit the
warning in blk_mq_unfreeze_queue().

On the next namespace add, we will fail to freeze that queue due to the
previous bad accounting and deadlock waiting for frozen.

Fix that by preventing scan work from altering the namespace list while
command effects handling needs to pair freeze with unfreeze.

Reported-by: Wen Xiong <wenxiong@us.ibm.com>
Tested-by: Wen Xiong <wenxiong@us.ibm.com>
Signed-off-by: Keith Busch <keith.busch@intel.com>
Reviewed-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
2019-02-06 16:35:33 +01:00
Linus Torvalds 6b8f915916 for-linus-20190125
-----BEGIN PGP SIGNATURE-----
 
 iQJEBAABCAAuFiEEwPw5LcreJtl1+l5K99NY+ylx4KYFAlxLdgsQHGF4Ym9lQGtl
 cm5lbC5kawAKCRD301j7KXHgpoVGD/4sGYQqfiXogQIJYbPH2RRPrJuLIIITjiAv
 lPXX1wx/tvz/ktwKJE2OiWTES0JjdH1HlC+7/0L/fLb8DXiKBmFuUHlwhureoL9Y
 o//BIQKuaje35kyHITTy2UAJOOqnNtJTaAP2AfkL+eOcj/V/G5rJIfLGs9QtuAR7
 sRJ+uhg1EbW/+uO0bULDmG6WUjxFu8mqcw3i6g0VVLVOnXB2EKcZTl3KPrdAXrUp
 XtmouERga6OfAUSJyZmTSV136mL+opRB2WFFVeIzjQfLmyItDGbSX/YPS8oJ2pow
 v7630F+CMrd4aKpqqtnAhfWpGqd0Xw7cYfZ9MKTJmZPmGzf9a1fQFpmgZosD4Dh3
 7MrhboU4TUt9PdXESA7CmE7LkTp99ghfj5/ysKrSV5h3HsH2RbLxJk91Rx3vmAWD
 u1xWRYL+GYLH6ZwOLvM1iqBrrLN3mUyrx98SaMgoXuqNzmQmgz9LPeA0Gt09FJbo
 uj+ebg4dRwuThjni4xQhl3zL2RQy7nlTDFDdKOz/XoiYk2NUVksss+sxGjNarHj0
 b5pCD4HOp57OreGExaOARpBRah5HSNdQtBRsIOnbyEq6f/e1LsIY23Z9nNF0deGO
 sZzgsbnsn+zg8bC6T/Gk4UY6XdCcgaS3SL04SVKAE3lO6A4C/Awo8DgD9Bl1zpC1
 HQlNkl5fBg==
 =iucY
 -----END PGP SIGNATURE-----

Merge tag 'for-linus-20190125' of git://git.kernel.dk/linux-block

Pull block fixes from Jens Axboe:
 "A collection of fixes for this release. This contains:

   - Silence sparse rightfully complaining about non-static wbt
     functions (Bart)

   - Fixes for the zoned comments/ioctl documentation (Damien)

   - direct-io fix that's been lingering for a while (Ernesto)

   - cgroup writeback fix (Tejun)

   - Set of NVMe patches for nvme-rdma/tcp (Sagi, Hannes, Raju)

   - Block recursion tracking fix (Ming)

   - Fix debugfs command flag naming for a few flags (Jianchao)"

* tag 'for-linus-20190125' of git://git.kernel.dk/linux-block:
  block: Fix comment typo
  uapi: fix ioctl documentation
  blk-wbt: Declare local functions static
  blk-mq: fix the cmd_flag_name array
  nvme-multipath: drop optimization for static ANA group IDs
  nvmet-rdma: fix null dereference under heavy load
  nvme-rdma: rework queue maps handling
  nvme-tcp: fix timeout handler
  nvme-rdma: fix timeout handler
  writeback: synchronize sync(2) against cgroup writeback membership switches
  block: cover another queue enter recursion via BIO_QUEUE_ENTERED
  direct-io: allow direct writes to empty inodes
2019-01-26 12:42:41 -08:00
Hannes Reinecke 78a61cd42a nvme-multipath: drop optimization for static ANA group IDs
Bit 6 in the ANACAP field is used to indicate that the ANA group ID
doesn't change while the namespace is attached to the controller.
There is an optimisation in the code to only allocate space
for the ANA group header, as the namespace list won't change and
hence would not need to be refreshed.
However, this optimisation was never carried over to the actual
workflow, which always assumes that the buffer is large enough
to hold the ANA header _and_ the namespace list.
So drop this optimisation and always allocate enough space.

Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
2019-01-23 17:16:59 -07:00
Raju Rangoju 5cbab6303b nvmet-rdma: fix null dereference under heavy load
Under heavy load if we don't have any pre-allocated rsps left, we
dynamically allocate a rsp, but we are not actually allocating memory
for nvme_completion (rsp->req.rsp). In such a case, accessing pointer
fields (req->rsp->status) in nvmet_req_init() will result in crash.

To fix this, allocate the memory for nvme_completion by calling
nvmet_rdma_alloc_rsp()

Fixes: 8407879c("nvmet-rdma:fix possible bogus dereference under heavy load")

Cc: <stable@vger.kernel.org>
Reviewed-by: Max Gurtovoy <maxg@mellanox.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Raju Rangoju <rajur@chelsio.com>
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
2019-01-23 17:16:59 -07:00
Sagi Grimberg b1064d3e33 nvme-rdma: rework queue maps handling
If the device supports less queues than provided (if the device has less
completion vectors), we might hit a bug due to the fact that we ignore
that in nvme_rdma_map_queues (we override the maps nr_queues with user
opts).

Instead, keep track of how many default/read/poll queues we actually
allocated (rather than asked by the user) and use that to assign our
queue mappings.

Fixes: b65bb777ef (" nvme-rdma: support separate queue maps for read and write")
Reported-by: Saleem, Shiraz <shiraz.saleem@intel.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
2019-01-23 17:16:59 -07:00
Sagi Grimberg 39d5775746 nvme-tcp: fix timeout handler
Currently, we have several problems with the timeout
handler:
1. If we timeout on the controller establishment flow, we will hang
because we don't execute the error recovery (and we shouldn't because
the create_ctrl flow needs to fail and cleanup on its own)
2. We might also hang if we get a disconnet on a queue while the
controller is already deleting. This racy flow can cause the controller
disable/shutdown admin command to hang.

We cannot complete a timed out request from the timeout handler without
mutual exclusion from the teardown flow (e.g. nvme_rdma_error_recovery_work).
So we serialize it in the timeout handler and teardown io and admin
queues to guarantee that no one races with us from completing the
request.

Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
2019-01-23 17:16:59 -07:00
Sagi Grimberg 4c174e6366 nvme-rdma: fix timeout handler
Currently, we have several problems with the timeout
handler:
1. If we timeout on the controller establishment flow, we will hang
because we don't execute the error recovery (and we shouldn't because
the create_ctrl flow needs to fail and cleanup on its own)
2. We might also hang if we get a disconnet on a queue while the
controller is already deleting. This racy flow can cause the controller
disable/shutdown admin command to hang.

We cannot complete a timed out request from the timeout handler without
mutual exclusion from the teardown flow (e.g. nvme_rdma_error_recovery_work).
So we serialize it in the timeout handler and teardown io and admin
queues to guarantee that no one races with us from completing the
request.

Reported-by: Jaesoo Lee <jalee@purestorage.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
2019-01-23 17:16:59 -07:00
Linus Torvalds 0facb89245 for-linus-20190118
-----BEGIN PGP SIGNATURE-----
 
 iQJEBAABCAAuFiEEwPw5LcreJtl1+l5K99NY+ylx4KYFAlxCLxcQHGF4Ym9lQGtl
 cm5lbC5kawAKCRD301j7KXHgpmBID/0SpsLsnoeki37Wei0HzBZeRdFGIXFfg1XB
 +s66nJUL+igHIIwH+EO7Ct+vw8jfCWZfasI+ThGtkgRg88bqJO3HEbE1MQY8KlTh
 Dm9LRHH9Jp4OYbbag2RXammaD4XKi980fIyVTp9R0keszQroSUTXXS40fksszTtB
 K4LEBiAxGJgin60W9RgbbK93n/pw17U5Wu2WID6ZfVxZYVzpXl0iIQXUz1zmnpy5
 3aP7ORqJGnH7WQiV57LMpq5/QFBoKrfUsjtxpnJ+i2694sLYX8NCqnH82SUliSU+
 NN3Vxic1ozmZEADFKg4dfmgVqqyJaoVCRvsA5i5YjqG9m65G/S7/BmsaWbq5Ixf2
 N1KQr/36vkYGYWqtb2rbYRVf9XfbxWKp1wuSaX3N1Vh1/Ee180qD68+wpa/0mtkh
 2dXV6CQP9De4BXH6mxj3Yr7LI2a2r7KLYhULZCAvLMvDtsBrPyHAmRRgXxaLlKL8
 QMFYYO/1wjlzpGnn4IxP8sDMH6N2shtZHAmC2n9TM2gmk5tA0OmajJJ4uxNbtyhw
 +ZlDco3aw/x0v2onjlbTiPij2cReRgwN+tVaEvn0dj3uxaisCru60iYdnr9FX4nL
 g3NxNUJbUhl6YMwvNMI0GKfz1IILzjPgJIhDqSHvYhtCA1w0DMVXs3Qv4HXoVh3m
 ffdby6/Yqw==
 =5yJp
 -----END PGP SIGNATURE-----

Merge tag 'for-linus-20190118' of git://git.kernel.dk/linux-block

Pull block fixes from Jens Axboe:

 - block size setting fixes for loop/nbd (Jan Kara)

 - md bio_alloc_mddev() cleanup (Marcos)

 - Ensure we don't lose the REQ_INTEGRITY flag (Ming)

 - Two NVMe fixes by way of Christoph:
    - Fix NVMe IRQ calculation (Ming)
    - Uninitialized variable in nvmet-tcp (Sagi)

 - BFQ comment fix (Paolo)

 - License cleanup for recently added blk-mq-debugfs-zoned (Thomas)

* tag 'for-linus-20190118' of git://git.kernel.dk/linux-block:
  block: Cleanup license notice
  nvme-pci: fix nvme_setup_irqs()
  nvmet-tcp: fix uninitialized variable access
  block: don't lose track of REQ_INTEGRITY flag
  blockdev: Fix livelocks on loop device
  nbd: Use set_blocksize() to set device blocksize
  md: Make bio_alloc_mddev use bio_alloc_bioset
  block, bfq: fix comments on __bfq_deactivate_entity
2019-01-20 09:12:50 +12:00
Ming Lei c45b1fa243 nvme-pci: fix nvme_setup_irqs()
When -ENOSPC is returned from pci_alloc_irq_vectors_affinity(),
we still try to allocate multiple irq vectors again, so irq queues
covers the admin queue actually. But we don't consider that, then
number of the allocated irq vector may be same with sum of
io_queues[HCTX_TYPE_DEFAULT] and io_queues[HCTX_TYPE_READ], this way
is obviously wrong, and finally breaks nvme_pci_map_queues(), and
warning from pci_irq_get_affinity() is triggered.

IRQ queues should cover admin queues, this patch makes this
point explicitely in nvme_calc_io_queues().

We got severl boot failure internal report on aarch64, so please
consider to fix it in v4.20.

Fixes: 6451fe73fa ("nvme: fix irq vs io_queue calculations")
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Reviewed-by: Keith Busch <keith.busch@intel.com>
Tested-by: fin4478 <fin4478@hotmail.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
2019-01-16 09:44:28 -07:00
Sagi Grimberg fb8658581a nvmet-tcp: fix uninitialized variable access
If we end up in nvmet_tcp_try_recv_one with a bogus state
queue receive state we will access result which is uninitialized.

Initialize restult to 0 which will be considered as if no data
was received by the tcp socket.

Fixes: 872d26a391 ("nvmet-tcp: add NVMe over TCP target driver")
Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
2019-01-16 09:44:20 -07:00
Linus Torvalds b8c3b8992f for-linus-20190112
-----BEGIN PGP SIGNATURE-----
 
 iQJEBAABCAAuFiEEwPw5LcreJtl1+l5K99NY+ylx4KYFAlw6VoIQHGF4Ym9lQGtl
 cm5lbC5kawAKCRD301j7KXHgptaHD/wLDzVDkptMK7Essk73vjBaz6w2MYl/Bvb4
 2YtktHlrCB8S/0Xze7t5tvsGxym2fv1ymsV48Sdnl+lW+2tf6e3LJEfAp7yLWoEs
 K6UdFkhYK7fdKx84dHIcslvyY0id9qjRteRiFHrd/023N4FZDkbKOtfeRBZi7e4Q
 yTP2FzQEnSV5a0ngh9J+xxHUXF7a4LfeVj9ddhwcBIAeJ1MUfLTaHxRR8Qc3nw3F
 7nGvLHu2vrWK3EDBBA/PsBqMJhsoW2AV0G7Xbv6Ai7e14GWVYr+MGjIYC41yIlRm
 46oBoveIRI5dkhR5/mO685vB774yAN6RExOP9Xlg/cA3XxbpdWP9uDtfRbuvo64O
 WOm2btWKjxOldCao4wClaJARcjSyocPTKwlWQE7OfVcN+3WbsD26sd+GdCvrSG7a
 +E3xcyPUURN1e7t4YyDGDL1wKBPuZP6jvcGUfoqLMr3O12aIjlAiJFPhm1Hqv+dA
 KaJjsCwShSDJfeWLvP/Lt1KtVoBinrKA/5qkkB7zJA7I+qNP7bAR25BtuXKo1U7t
 5vRGk7rfvdtsE5oH7y1we9AxoA7jD6t5Z60mPRdkVaXzi9SSw3th/YAuUhcU2g0V
 0I2icAGQI8bbZzFgJe+d4f1L57EQ/7fWfcwENNLkLu57E/gZlYYqt//tSrF8W0ur
 wcthJWqOZg==
 =OFV3
 -----END PGP SIGNATURE-----

Merge tag 'for-linus-20190112' of git://git.kernel.dk/linux-block

Pull block fixes from Jens Axboe:

 - NVMe pull request from Christoph, with little fixes all over the map

 - Loop caching fix for offset/bs change (Jaegeuk Kim)

 - Block documentation tweaks (Jeff, Jon, Weiping, John)

 - null_blk zoned tweak (John)

 - ahch mvebu suspend/resume support. Should have gone into the merge
   window, but there was some confusion on which tree had it. (Miquel)

* tag 'for-linus-20190112' of git://git.kernel.dk/linux-block: (22 commits)
  ata: ahci: mvebu: request PHY suspend/resume for Armada 3700
  ata: ahci: mvebu: add Armada 3700 initialization needed for S2RAM
  ata: ahci: mvebu: do Armada 38x configuration only on relevant SoCs
  ata: ahci: mvebu: remove stale comment
  ata: libahci_platform: comply to PHY framework
  loop: drop caches if offset or block_size are changed
  block: fix kerneldoc comment for blk_attempt_plug_merge()
  nvme: don't initlialize ctrl->cntlid twice
  nvme: introduce NVME_QUIRK_IGNORE_DEV_SUBNQN
  nvme: pad fake subsys NQN vid and ssvid with zeros
  nvme-multipath: zero out ANA log buffer
  nvme-fabrics: unset write/poll queues for discovery controllers
  nvme-tcp: don't ask if controller is fabrics
  nvme-tcp: remove dead code
  nvme-pci: fix out of bounds access in nvme_cqe_pending
  nvme-pci: rerun irq setup on IO queue init errors
  nvme-pci: use the same attributes when freeing host_mem_desc_bufs.
  nvme-pci: fix the wrong setting of nr_maps
  block: doc: add slice_idle_us to bfq documentation
  block: clarify documentation for blk_{start|finish}_plug
  ...
2019-01-12 13:40:51 -08:00
Andrey Smirnov b8a38ea64d nvme: don't initlialize ctrl->cntlid twice
ctrl->cntlid will already be initialized from id->cntlid for
non-NVME_F_FABRICS controllers few lines below. For NVME_F_FABRICS
controllers this field should already be initialized, otherwise the
check

	if (ctrl->cntlid != le16_to_cpu(id->cntlid))

below will always be a no-op.

Signed-off-by: Andrey Smirnov <andrew.smirnov@gmail.com>
Reviewed-by: Keith Busch <keith.busch@intel.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Christoph Hellwig <hch@lst.de>
2019-01-09 13:47:08 -05:00
James Dingwall 6299358d19 nvme: introduce NVME_QUIRK_IGNORE_DEV_SUBNQN
If a device provides an NQN it is expected to be globally unique.
Unfortunately some firmware revisions for Intel 760p/Pro 7600p devices did
not satisfy this requirement.  In these circumstances if a system has >1
affected device then only one device is enabled.  If this quirk is enabled
then the device supplied subnqn is ignored and we fallback to generating
one as if the field was empty.  In this case we also suppress the version
check so we don't print a warning when the quirk is enabled.

Reviewed-by: Keith Busch <keith.busch@intel.com>
Signed-off-by: James Dingwall <james@dingwall.me.uk>
Signed-off-by: Christoph Hellwig <hch@lst.de>
2019-01-09 13:47:08 -05:00
Keith Busch 3da584f571 nvme: pad fake subsys NQN vid and ssvid with zeros
We need to preserve the leading zeros in the vid and ssvid when generating
a unique NQN. Truncating these may lead to naming collisions.

Signed-off-by: Keith Busch <keith.busch@intel.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
2019-01-09 13:47:06 -05:00
Hannes Reinecke c7055fd15f nvme-multipath: zero out ANA log buffer
When nvme_init_identify() fails the ANA log buffer is deallocated
but _not_ set to NULL. This can cause double free oops when this
controller is deleted without ever being reconnected.

Signed-off-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
2019-01-09 13:47:06 -05:00
Sagi Grimberg 9846ac0143 nvme-fabrics: unset write/poll queues for discovery controllers
Even if user-space sent it to us, it got it wrong so lets
help by disallowing it.

Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Christoph Hellwig <hch@lst.de>
2019-01-09 13:47:06 -05:00
Sagi Grimberg e85037a2e9 nvme-tcp: don't ask if controller is fabrics
For sure we are a fabric driver.

Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Christoph Hellwig <hch@lst.de>
2019-01-09 13:47:06 -05:00
Sagi Grimberg e9c2edc098 nvme-tcp: remove dead code
We should never touch the opal device from the transport driver.

Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Christoph Hellwig <hch@lst.de>
2019-01-09 13:47:06 -05:00
Hongbo Yao dcca166272 nvme-pci: fix out of bounds access in nvme_cqe_pending
There is an out of bounds array access in nvme_cqe_peding().

When enable irq_thread for nvme interrupt, there is racing between the
nvmeq->cq_head updating and reading.

nvmeq->cq_head is updated in nvme_update_cq_head(), if nvmeq->cq_head
equals nvmeq->q_depth and before its value set to zero, nvme_cqe_pending()
uses its value as an array index, the index will be out of bounds.

Signed-off-by: Hongbo Yao <yaohongbo@huawei.com>
[hch: slight coding style update]
Signed-off-by: Christoph Hellwig <hch@lst.de>
2019-01-09 13:47:05 -05:00
Keith Busch 8fae268b40 nvme-pci: rerun irq setup on IO queue init errors
If the driver is unable to create a subset of IO queues for any reason,
the read/write and polled queue sets will not match the actual allocated
hardware contexts. This leaves gaps in the CPU affinity mappings and
causes the following kernel panic after blk_mq_map_queue_type() returns
a NULL hctx.

  BUG: unable to handle kernel NULL pointer dereference at 0000000000000198
  #PF error: [normal kernel read fault]
  PGD 0 P4D 0
  Oops: 0000 [#1] SMP
  CPU: 64 PID: 1171 Comm: kworker/u259:1 Not tainted 4.20.0+ #241
  Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-2.fc27 04/01/2014
  Workqueue: nvme-wq nvme_scan_work [nvme_core]
  RIP: 0010:blk_mq_init_allocated_queue+0x2d9/0x440
  RSP: 0018:ffffb1bf0abc3cd0 EFLAGS: 00010286
  RAX: 000000000000001f RBX: ffff8ea744cf0718 RCX: 0000000000000000
  RDX: 0000000000000002 RSI: 000000000000007c RDI: ffffffff9109a820
  RBP: ffff8ea7565f7008 R08: 000000000000001f R09: 000000000000003f
  R10: ffffb1bf0abc3c00 R11: 0000000000000000 R12: 000000000001d008
  R13: ffff8ea7565f7008 R14: 000000000000003f R15: 0000000000000001
  FS:  0000000000000000(0000) GS:ffff8ea757200000(0000) knlGS:0000000000000000
  CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
  CR2: 0000000000000198 CR3: 0000000013058000 CR4: 00000000000006e0
  DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
  DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
  Call Trace:
   blk_mq_init_queue+0x35/0x60
   nvme_validate_ns+0xc6/0x7c0 [nvme_core]
   ? nvme_identify_ctrl.isra.56+0x7e/0xc0 [nvme_core]
   nvme_scan_work+0xc8/0x340 [nvme_core]
   ? __wake_up_common+0x6d/0x120
   ? try_to_wake_up+0x55/0x410
   process_one_work+0x1e9/0x3d0
   worker_thread+0x2d/0x3d0
   ? process_one_work+0x3d0/0x3d0
   kthread+0x111/0x130
   ? kthread_park+0x90/0x90
   ret_from_fork+0x1f/0x30
  Modules linked in: nvme nvme_core serio_raw
  CR2: 0000000000000198

Fix by re-running the interrupt vector setup from scratch using a reduced
count that may be successful until the created queues matches the irq
affinity plus polling queue sets.

Signed-off-by: Keith Busch <keith.busch@intel.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
2019-01-09 13:47:02 -05:00
Liviu Dudau cc667f6d5d nvme-pci: use the same attributes when freeing host_mem_desc_bufs.
When using HMB the PCIe host driver allocates host_mem_desc_bufs using
dma_alloc_attrs() but frees them using dma_free_coherent(). Use the
correct dma_free_attrs() function to free the buffers.

Signed-off-by: Liviu Dudau <liviu@dudau.co.uk>
Signed-off-by: Christoph Hellwig <hch@lst.de>
2019-01-09 13:47:02 -05:00
Jianchao Wang c61e678f30 nvme-pci: fix the wrong setting of nr_maps
We only set the nr_maps to 3 if poll queues are supported.

Signed-off-by: Jianchao Wang <jianchao.w.wang@oracle.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
2019-01-09 13:47:02 -05:00
Luis Chamberlain 750afb08ca cross-tree: phase out dma_zalloc_coherent()
We already need to zero out memory for dma_alloc_coherent(), as such
using dma_zalloc_coherent() is superflous. Phase it out.

This change was generated with the following Coccinelle SmPL patch:

@ replace_dma_zalloc_coherent @
expression dev, size, data, handle, flags;
@@

-dma_zalloc_coherent(dev, size, handle, flags)
+dma_alloc_coherent(dev, size, handle, flags)

Suggested-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
[hch: re-ran the script on the latest tree]
Signed-off-by: Christoph Hellwig <hch@lst.de>
2019-01-08 07:58:37 -05:00
yupeng 604c01d567 nvme-pci: trace SQ status on completions
Export the disk name, queue id, sq_head, sq_tail to a trace event in
completion handling.

Usage example:

cd /sys/kernel/debug/tracing/events/nvme/nvme_sq

echo 'disk=="nvme1n1"' > filter

echo 1 > enable

cat /sys/kernel/debug/tracing/trace_pipe

Signed-off-by: yupeng <yupeng0921@gmail.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Reviewed-by: Keith Busch <keith.busch@intel.com>
[hch: slight formatting tweaks, use standard nvme tracepoint
 conventions]
Signed-off-by: Christoph Hellwig <hch@lst.de>

wip
2018-12-19 08:35:36 +01:00
Sagi Grimberg ff8519f9e9 nvme-rdma: implement polling queue map
When passed with nr_poll_queues setup additional queues with cq polling
context IB_POLL_DIRECT (no interrupts) and make sure to set
QUEUE_FLAG_POLL on the connect_q. In addition add the third queue
mapping for polling queues.

nvmf connect on this queue is polled for like all other requests so make
nvmf_connect_io_queue poll for polling queues.

Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Christoph Hellwig <hch@lst.de>
2018-12-18 17:50:49 +01:00
Sagi Grimberg 89d43802b0 nvme-fabrics: allow user to pass in nr_poll_queues
This argument will specify how many polling I/O queues to connect when
creating the controller. These I/O queues will host I/O that is set with
REQ_HIPRI.

Reviewed-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Christoph Hellwig <hch@lst.de>
2018-12-18 17:50:49 +01:00
Sagi Grimberg 26c682274e nvme-fabrics: allow nvmf_connect_io_queue to poll
Preparation for polling support for fabrics. Polling support
means that our completion queues are not generating any interrupts
which means we need to poll for the nvmf io queue connect as well.

Reviewed by Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Christoph Hellwig <hch@lst.de>
2018-12-18 17:50:48 +01:00
Sagi Grimberg 6287b51c77 nvme-core: optionally poll sync commands
Pass poll bool to indicate that we need it to poll. This prepares us for
polling support in nvmf since connect is an I/O that will be queued
and has to be polled in order to complete. If poll is passed,
we call nvme_execute_rq_polled which sends the requests and polls
for its completion.

Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Christoph Hellwig <hch@lst.de>
2018-12-18 17:50:48 +01:00
Colin Ian King 56a77d26d6 nvme-tcp: fix spelling mistake "attepmpt" -> "attempt"
There is a spelling mistake in a dev_info message, fix it.

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Christoph Hellwig <hch@lst.de>
2018-12-18 17:50:47 +01:00
Christoph Hellwig a7273d4023 nvme-tcp: fix endianess annotations
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
2018-12-18 17:50:46 +01:00
Christoph Hellwig f4d10b5c85 nvmet-tcp: fix endianess annotations
Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Sagi Grimberg <sagi@grimberg.me>
2018-12-18 17:50:45 +01:00
Christoph Hellwig 91a509f8b7 nvme-pci: refactor nvme_poll_irqdisable to make sparse happy
By duplicating the nvme_process_cq in both branches we keep the
sparse lock context checking happy, so do it.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
2018-12-18 17:50:45 +01:00
Christoph Hellwig ed92ad37e8 nvme-pci: only set nr_maps to 2 if poll queues are supported
The block layer now enables polling support on a queue if nr_maps
includes the poll map, so we should only set that if we actually
support poll queues.

Fixes:  6544d229bf ("block: enable polling by default if a poll map is initalized")
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jens Axboe <axboe@kernel.dk>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
2018-12-18 17:50:44 +01:00
Chaitanya Kulkarni 5698b805fb nvmet: use a macro for default error location
This patch defines a new macro NVMET_NO_ERROR_LOC to represent the
default error location value in the nvme-error-log-page.
This is a pure cleanup patch and it does not change any functionality.

Signed-off-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
2018-12-18 17:50:44 +01:00
Colin Ian King 66c6afbd73 nvmet: fix comparison of a u16 with -1
Currently the u16 req->error_loc is being compared to -1 which
will always be false.  Fix this by casting -1 to u16 to fix this.

Detected by clang:
  warning: result of comparison of constant -1 with expression of
  type 'u16' (aka 'unsigned short') is always false
  [-Wtautological-constant-out-of-range-compare]

Fixes: 76574f37bf ("nvmet: add interface to update error-log page")
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
2018-12-18 17:50:43 +01:00
Christoph Hellwig 7e849dd9cf nvme-pci: don't share queue maps
Now that the block layer checks if a queue map has any queues inside
it there is no more reason to duplicate the maps for the non-default
types.

Reviewed-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
2018-12-17 05:44:45 -07:00
Sagi Grimberg 092ff05200 nvme: fix kernel paging oops
free the controller discard_page correctly.

Fixes: cb5b7262b0 ("nvme: provide fallback for discard alloc failure")
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
2018-12-13 13:58:23 -07:00
Sagi Grimberg b65bb777ef nvme-rdma: support separate queue maps for read and write
llow NVMF_OPT_NR_WRITE_QUEUES to describe additional write queues.  In
addition, implement .map_queues that will apply 2 queue maps for read
and write queue sets.

Note that with the separate queue map, HCTX_TYPE_READ will always use
nr_io_queues and HCTX_TYPE_DEFAULT will use nr_write_queues.

Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Christoph Hellwig <hch@lst.de>
2018-12-13 09:59:10 +01:00
Sagi Grimberg 873946f4b9 nvme-tcp: support separate queue maps for read and write
Allow NVMF_OPT_NR_WRITE_QUEUES to describe additional write queues.  In
addition, implement .map_queues that will apply 2 queue maps for read
and write queue sets.

Note that with the separate queue map, HCTX_TYPE_READ will always use
nr_io_queues and HCTX_TYPE_DEFAULT will use nr_write_queues.

Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Christoph Hellwig <hch@lst.de>
2018-12-13 09:59:09 +01:00
Sagi Grimberg 330f6b8a70 nvme-fabrics: allow user to set nr_write_queues for separate queue maps
This argument will specify how many I/O queues will be connected in
create_ctrl in addition to nr_io_queues. With this configuration, I/O
that carries payload from the host to the target, will use the default
hctx queue map, and I/O that involves target to host transfers will use
the read hctx queue map.

Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Christoph Hellwig <hch@lst.de>
2018-12-13 09:59:09 +01:00
Sagi Grimberg fa9a1811e0 nvme-fabrics: add missing nvmf_ctrl_options documentation
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Christoph Hellwig <hch@lst.de>
2018-12-13 09:59:08 +01:00
Sagi Grimberg e42b3867de blk-mq-rdma: pass in queue map to blk_mq_rdma_map_queues
Will be used by nvme-rdma for queue map separation support.

Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Christoph Hellwig <hch@lst.de>
2018-12-13 09:59:08 +01:00
Chaitanya Kulkarni 23454d59cc nvmet: update smart log with num err log entries
Now that we have error log page implementation update smart log command
handler to provide number of error log entries in the lifetime of the
controller field.

Signed-off-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Christoph Hellwig <hch@lst.de>
2018-12-13 09:59:07 +01:00
Chaitanya Kulkarni 11ad507784 nvmet: add error log page cmd handler
Now that we have support for all the major parts of the target we add
a NVMe error log page handler so that host can read the log page.

Signed-off-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Christoph Hellwig <hch@lst.de>
2018-12-13 09:59:06 +01:00
Chaitanya Kulkarni c6aa3542e0 nvmet: add error log support for file backend
This patch adds support for the file backend to populate the
error log entries. Here we map the errno to the NVMe status codes.

Signed-off-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Christoph Hellwig <hch@lst.de>
2018-12-13 09:59:06 +01:00
Chaitanya Kulkarni 3b031d1599 nvmet: add error log support for bdev backend
This patch adds the support for the block device backend to populate the
error log entries. Here we map the blk_status_t to the NVMe status.

Signed-off-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Christoph Hellwig <hch@lst.de>
2018-12-13 09:59:05 +01:00
Chaitanya Kulkarni 2da6e00580 nvmet: add error log support for admin-cmd
This patch adds the support to maintain the error log page for admin
commands.

Signed-off-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Christoph Hellwig <hch@lst.de>
2018-12-13 09:59:05 +01:00
Chaitanya Kulkarni 762a11dfee nvmet: add error log support for rdma backend
This patch adds the support to maintain the error log page for rdma
transport, we mainly focus here on the NVME_INVALID_FIELD errors.

Signed-off-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Christoph Hellwig <hch@lst.de>
2018-12-13 09:59:04 +01:00