linux-stable.git/drivers/nvme, branch v4.18.2

Merge tag 'for-linus-20180727' of git://git.kernel.dk/linux-block

2018-07-27T19:51:00+00:00

Pull block fixes from Jens Axboe:
 "Bigger than usual at this time, mostly due to the O_DIRECT corruption
  issue and the fact that I was on vacation last week. This contains:

   - NVMe pull request with two fixes for the FC code, and two target
     fixes (Christoph)

   - a DIF bio reset iteration fix (Greg Edwards)

   - two nbd reply and requeue fixes (Josef)

   - SCSI timeout fixup (Keith)

   - a small series that fixes an issue with bio_iov_iter_get_pages(),
     which ended up causing corruption for larger sized O_DIRECT writes
     that ended up racing with buffered writes (Martin Wilck)"

* tag 'for-linus-20180727' of git://git.kernel.dk/linux-block:
  block: reset bi_iter.bi_done after splitting bio
  block: bio_iov_iter_get_pages: pin more pages for multi-segment IOs
  blkdev: __blkdev_direct_IO_simple: fix leak in error case
  block: bio_iov_iter_get_pages: fix size of last iovec
  nvmet: only check for filebacking on -ENOTBLK
  nvmet: fixup crash on NULL device path
  scsi: set timed out out mq requests to complete
  blk-mq: export setting request completion state
  nvme: if_ready checks to fail io to deleting controller
  nvmet-fc: fix target sgl list on large transfers
  nbd: handle unexpected replies better
  nbd: don't requeue the same request twice.

nvmet: only check for filebacking on -ENOTBLK

2018-07-25T11:14:04+00:00

We only need to check for a file-backed namespace if
nvmet_bdev_ns_enable() returns -ENOTBLK. For any other error
it's pointless as the open() error will remain the same.

Fixes: d5eff33e ("nvmet: add simple file backed ns support")
Signed-off-by: Hannes Reinecke 
Reviewed-by: Chaitanya Kulkarni 
Signed-off-by: Christoph Hellwig

nvmet: fixup crash on NULL device path

2018-07-25T11:14:03+00:00

When writing an empty string into the device_path attribute the kernel
will crash with

nvmet: failed to open block device (null): (-22)
BUG: unable to handle kernel NULL pointer dereference at 0000000000000000

This patch sanitizes the error handling for invalid device path settings.

Fixes: a07b4970 ("nvmet: add a generic NVMe target")
Signed-off-by: Hannes Reinecke 
Reviewed-by: Chaitanya Kulkarni 
Signed-off-by: Christoph Hellwig

nvme: if_ready checks to fail io to deleting controller

2018-07-24T11:44:40+00:00

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: 3bc32bb1186c ("nvme-fabrics: refactor queue ready check")
Fixes: 35897b920c8a ("nvme-fabrics: fix and refine state checks in __nvmf_check_ready")
Signed-off-by: James Smart 
Signed-off-by: Christoph Hellwig 
Tested-by: Ewan D. Milne 
Reviewed-by: Ewan D. Milne

nvmet-fc: fix target sgl list on large transfers

2018-07-24T11:44:09+00:00

The existing code to carve up the sg list expected an sg element-per-page
which can be very incorrect with iommu's remapping multiple memory pages
to fewer bus addresses. To hit this error required a large io payload
(greater than 256k) and a system that maps on a per-page basis. It's
possible that large ios could get by fine if the system condensed the
sgl list into the first 64 elements.

This patch corrects the sg list handling by specifically walking the
sg list element by element and attempting to divide the transfer up
on a per-sg element boundary. While doing so, it still tries to keep
sequences under 256k, but will exceed that rule if a single sg element
is larger than 256k.

Fixes: 48fa362b6c3f ("nvmet-fc: simplify sg list handling")
Cc:  # 4.14
Signed-off-by: James Smart 
Signed-off-by: Christoph Hellwig

nvme: fix handling of metadata_len for NVME_IOCTL_IO_CMD

2018-07-20T14:43:59+00:00

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: Roland Dreier 
Reviewed-by: Keith Busch 
Signed-off-by: Christoph Hellwig

nvme: don't enable AEN if not supported

2018-07-17T14:30:27+00:00

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: Sagi Grimberg 
Signed-off-by: Weiping Zhang 
Signed-off-by: Christoph Hellwig

nvme: ensure forward progress during Admin passthru

2018-07-17T12:46:19+00:00

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: 84fef62d135b6 ("nvme: check admin passthru command effects")
Signed-off-by: Scott Bauer 
Reviewed-by: Keith Busch 
Signed-off-by: Christoph Hellwig

nvme-pci: fix memory leak on probe failure

2018-07-12T06:23:56+00:00

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: 943e942e6266f ("nvme-pci: limit max IO size and segments to avoid high order allocations")
Reported-by: Weiping Zhang 
Signed-off-by: Keith Busch 
Signed-off-by: Christoph Hellwig

nvme-rdma: fix possible double free of controller async event buffer

2018-06-28T14:29:54+00:00

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: Max Gurtovoy 
Tested-by: Max Gurtovoy 
Signed-off-by: Sagi Grimberg 
Signed-off-by: Christoph Hellwig