linux-stable.git/drivers/nvme, branch v6.5.6

nvme-pci: do not set the NUMA node of device if it has none

2023-10-06T11:16:12+00:00

[ Upstream commit dad651b2a44eb6b201738f810254279dca29d30d ]

If a device has no NUMA node information associated with it, the driver
puts the device in node first_memory_node (say node 0). Not having a
NUMA node and being associated with node 0 are completely different
things and it makes little sense to mix the two.

Signed-off-by: Pratyush Yadav 
Signed-off-by: Keith Busch 
Signed-off-by: Sasha Levin

nvme-fc: Prevent null pointer dereference in nvme_fc_io_getuuid()

2023-10-06T11:16:08+00:00

[ Upstream commit 8ae5b3a685dc59a8cf7ccfe0e850999ba9727a3c ]

The nvme_fc_fcp_op structure describing an AEN operation is initialized with a
null request structure pointer. An FC LLDD may make a call to
nvme_fc_io_getuuid passing a pointer to an nvmefc_fcp_req for an AEN operation.

Add validation of the request structure pointer before dereference.

Signed-off-by: Nigel Kirkland 
Reviewed-by: James Smart 
Signed-off-by: Keith Busch 
Signed-off-by: Sasha Levin

nvme: avoid bogus CRTO values

2023-09-23T09:14:34+00:00

commit 6cc834ba62998c65c42d0c63499bdd35067151ec upstream.

Some devices are reporting controller ready mode support, but return 0
for CRTO. These devices require a much higher time to ready than that,
so they are failing to initialize after the driver starter preferring
that value over CAP.TO.

The spec requires that CAP.TO match the appropritate CRTO value, or be
set to 0xff if CRTO is larger than that. This means that CAP.TO can be
used to validate if CRTO is reliable, and provides an appropriate
fallback for setting the timeout value if not. Use whichever is larger.

Link: https://bugzilla.kernel.org/show_bug.cgi?id=217863
Reported-by: Cláudio Sampaio 
Reported-by: Felix Yan 
Tested-by: Felix Yan 
Based-on-a-patch-by: Felix Yan 
Cc: stable@vger.kernel.org
Signed-off-by: Keith Busch 
Signed-off-by: Greg Kroah-Hartman

nvmet-tcp: pass iov_len instead of sg->length to bvec_set_page()

2023-09-23T09:14:31+00:00

[ Upstream commit 1f0bbf28940cf5edad90ab57b62aa8197bf5e836 ]

iov_len is the valid data length, so pass iov_len instead of sg->length to
bvec_set_page().

Fixes: 5bfaba275ae6 ("nvmet-tcp: don't map pages which can't come from HIGHMEM")
Signed-off-by: Rakshana Sridhar 
Signed-off-by: Varun Prakash 
Reviewed-by: Sagi Grimberg 
Reviewed-by: Christoph Hellwig 
Signed-off-by: Keith Busch 
Signed-off-by: Sasha Levin

Merge tag 'block-6.5-2023-08-11' of git://git.kernel.dk/linux

2023-08-11T19:14:08+00:00

Pull block fixes from Jens Axboe:

 - NVMe pull request via Keith:
      - Fixes for request_queue state (Ming)
      - Another uuid quirk (August)

 - RCU poll fix for NVMe (Ming)

 - Fix for an IO stall with polled IO (me)

 - Fix for blk-iocost stats enable/disable accounting (Chengming)

 - Regression fix for large pages for zram (Christoph)

* tag 'block-6.5-2023-08-11' of git://git.kernel.dk/linux:
  nvme: core: don't hold rcu read lock in nvme_ns_chr_uring_cmd_iopoll
  blk-iocost: fix queue stats accounting
  block: don't make REQ_POLLED imply REQ_NOWAIT
  block: get rid of unused plug->nowait flag
  zram: take device and not only bvec offset into account
  nvme-pci: add NVME_QUIRK_BOGUS_NID for Samsung PM9B1 256G and 512G
  nvme-rdma: fix potential unbalanced freeze & unfreeze
  nvme-tcp: fix potential unbalanced freeze & unfreeze
  nvme: fix possible hang when removing a controller during error recovery

nvme: core: don't hold rcu read lock in nvme_ns_chr_uring_cmd_iopoll

2023-08-11T14:12:32+00:00

Now nvme_ns_chr_uring_cmd_iopoll() has switched to request based io
polling, and the associated NS is guaranteed to be live in case of
io polling, so request is guaranteed to be valid because blk-mq uses
pre-allocated request pool.

Remove the rcu read lock in nvme_ns_chr_uring_cmd_iopoll(), which
isn't needed any more after switching to request based io polling.

Fix "BUG: sleeping function called from invalid context" because
set_page_dirty_lock() from blk_rq_unmap_user() may sleep.

Fixes: 585079b6e425 ("nvme: wire up async polling for io passthrough commands")
Reported-by: Guangwu Zhang 
Cc: Kanchan Joshi 
Cc: Anuj Gupta 
Signed-off-by: Ming Lei 
Tested-by: Guangwu Zhang 
Link: https://lore.kernel.org/r/20230809020440.174682-1-ming.lei@redhat.com
Signed-off-by: Jens Axboe

nvme-pci: add NVME_QUIRK_BOGUS_NID for Samsung PM9B1 256G and 512G

2023-08-01T20:28:29+00:00

The Samsung PM9B1 512G SSD found in some Lenovo Yoga 7 14ARB7 laptop units
reports eui as 0001000200030004 when resuming from s2idle, causing the
device to be removed with this error in dmesg:

nvme nvme0: identifiers changed for nsid 1

To fix this, add a quirk to ignore namespace identifiers for this device.

Signed-off-by: August Wikerfors 
Signed-off-by: Keith Busch

nvme-rdma: fix potential unbalanced freeze & unfreeze

2023-07-21T07:53:33+00:00

Move start_freeze into nvme_rdma_configure_io_queues(), and there is
at least two benefits:

1) fix unbalanced freeze and unfreeze, since re-connection work may
fail or be broken by removal

2) IO during error recovery can be failfast quickly because nvme fabrics
unquiesces queues after teardown.

One side-effect is that !mpath request may timeout during connecting
because of queue topo change, but that looks not one big deal:

1) same problem exists with current code base

2) compared with !mpath, mpath use case is dominant

Fixes: 9f98772ba307 ("nvme-rdma: fix controller reset hang during traffic")
Cc: stable@vger.kernel.org
Signed-off-by: Ming Lei 
Tested-by: Yi Zhang 
Reviewed-by: Sagi Grimberg 
Signed-off-by: Keith Busch

nvme-tcp: fix potential unbalanced freeze & unfreeze

2023-07-21T07:53:29+00:00

Move start_freeze into nvme_tcp_configure_io_queues(), and there is
at least two benefits:

1) fix unbalanced freeze and unfreeze, since re-connection work may
fail or be broken by removal

2) IO during error recovery can be failfast quickly because nvme fabrics
unquiesces queues after teardown.

One side-effect is that !mpath request may timeout during connecting
because of queue topo change, but that looks not one big deal:

1) same problem exists with current code base

2) compared with !mpath, mpath use case is dominant

Fixes: 2875b0aecabe ("nvme-tcp: fix controller reset hang during traffic")
Cc: stable@vger.kernel.org
Signed-off-by: Ming Lei 
Tested-by: Yi Zhang 
Reviewed-by: Sagi Grimberg 
Signed-off-by: Keith Busch

nvme: fix possible hang when removing a controller during error recovery

2023-07-21T07:53:26+00:00

Error recovery can be interrupted by controller removal, then the
controller is left as quiesced, and IO hang can be caused.

Fix the issue by unquiescing controller unconditionally when removing
namespaces.

This way is reasonable and safe given forward progress can be made
when removing namespaces.

Reviewed-by: Keith Busch 
Reviewed-by: Sagi Grimberg 
Reported-by: Chunguang Xu 
Closes: https://lore.kernel.org/linux-nvme/cover.1685350577.git.chunguang.xu@shopee.com/
Cc: stable@vger.kernel.org
Signed-off-by: Ming Lei 
Signed-off-by: Keith Busch