linux.git/drivers/nvme/host, branch for-next

Merge tag 'nvme-6.13-2024-12-31' of git://git.infradead.org/nvme into block-6.13

2024-12-31T17:41:58+00:00

Pull NVMe fixes from Keith:

"nvme fixes for Linux 6.13

 - Fix device specific quirk for PRP list alignment (Robert)
 - Fix target name overflow (Leo)
 - Fix target write granularity (Luis)
 - Fix target sleeping in atomic context (Nilay)
 - Remove unnecessary tcp queue teardown (Chunguang)"

* tag 'nvme-6.13-2024-12-31' of git://git.infradead.org/nvme:
  nvme-tcp: remove nvme_tcp_destroy_io_queues()
  nvmet-loop: avoid using mutex in IO hotpath
  nvmet: propagate npwg topology
  nvmet: Don't overflow subsysnqn
  nvme-pci: 512 byte aligned dma pool segment quirk

nvme-tcp: remove nvme_tcp_destroy_io_queues()

2024-12-27T21:33:48+00:00

Now when destroying the IO queue we call nvme_tcp_stop_io_queues()
twice, nvme_tcp_destroy_io_queues() has an unnecessary call. Here we
try to remove nvme_tcp_destroy_io_queues() and merge it into
nvme_tcp_teardown_io_queues(), simplify the code and align with
nvme-rdma, make it easy to maintaince.

Signed-off-by: Chunguang.xu 
Reviewed-by: Sagi Grimberg 
Reviewed-by: Christoph Hellwig 
Signed-off-by: Keith Busch

nvme: use blk_validate_block_size() for max LBA check

2024-12-18T14:22:30+00:00

The block layer already has support to validates proper block sizes
with blk_validate_block_size(), we can leverage that as well.

No functional changes.

Signed-off-by: Luis Chamberlain 
Reviewed-by: John Garry 
Reviewed-by: Keith Busch 
Reviewed-by: Christoph Hellwig 
Link: https://lore.kernel.org/r/20241218020212.3657139-3-mcgrof@kernel.org
Signed-off-by: Jens Axboe

nvme-pci: 512 byte aligned dma pool segment quirk

2024-12-11T22:46:23+00:00

We initially introduced a quick fix limiting the queue depth to 1 as
experimentation showed that it fixed data corruption on 64GB steamdecks.

Further experimentation revealed corruption only happens when the last
PRP data element aligns to the end of the page boundary. The device
appears to treat this as a PRP chain to a new list instead of the data
element that it actually is. This implementation is in violation of the
spec. Encountering this errata with the Linux driver requires the host
request a 128k transfer and coincidently be handed the last small pool
dma buffer within a page.

The QD1 quirk effectly works around this because the last data PRP
always was at a 248 byte offset from the page start, so it never
appeared at the end of the page, but comes at the expense of throttling
IO and wasting the remainder of the PRP page beyond 256 bytes. Also to
note, the MDTS on these devices is small enough that the "large" prp
pool can hold enough PRP elements to never reach the end, so that pool
is not a problem either.

Introduce a new quirk to ensure the small pool is always aligned such
that the last PRP element can't appear a the end of the page. This comes
at the expense of wasting 256 bytes per small pool page allocated.

Link: https://lore.kernel.org/linux-nvme/20241113043151.GA20077@lst.de/T/#u
Fixes: 83bdfcbdbe5d ("nvme-pci: qdepth 1 quirk")
Cc: Paweł Anikiel 
Signed-off-by: Robert Beckett 
Signed-off-by: Keith Busch

Merge tag 'nvme-6.13-2024-12-05' of git://git.infradead.org/nvme into block-6.13

2024-12-05T17:14:36+00:00

Pull NVMe fixess from Keith:

"nvme fixes for Linux 6.13

 - Target fix using incorrect zero buffer (Nilay)
 - Device specifc deallocate quirk fixes (Christoph, Keith)
 - Fabrics fix for handling max command target bugs (Maurizio)
 - Cocci fix usage for kzalloc (Yu-Chen)
 - DMA size fix for host memory buffer feature (Christoph)
 - Fabrics queue cleanup fixes (Chunguang)"

* tag 'nvme-6.13-2024-12-05' of git://git.infradead.org/nvme:
  nvme-tcp: simplify nvme_tcp_teardown_io_queues()
  nvme-tcp: no need to quiesce admin_q in nvme_tcp_teardown_io_queues()
  nvme-rdma: unquiesce admin_q before destroy it
  nvme-tcp: fix the memleak while create new ctrl failed
  nvme-pci: don't use dma_alloc_noncontiguous with 0 merge boundary
  nvmet: replace kmalloc + memset with kzalloc for data allocation
  nvme-fabrics: handle zero MAXCMD without closing the connection
  nvme-pci: remove two deallocate zeroes quirks
  nvme: don't apply NVME_QUIRK_DEALLOCATE_ZEROES when DSM is not supported
  nvmet: use kzalloc instead of ZERO_PAGE in nvme_execute_identify_ns_nvm()

nvme-tcp: simplify nvme_tcp_teardown_io_queues()

2024-12-04T18:15:46+00:00

As nvme_tcp_teardown_io_queues() is the only one caller of
nvme_tcp_destroy_admin_queue(), so we can merge it into
nvme_tcp_teardown_io_queues() to simplify the code.

Signed-off-by: Chunguang.xu 
Reviewed-by: Christoph Hellwig 
Reviewed-by: Hannes Reinecke 
Signed-off-by: Keith Busch

nvme-tcp: no need to quiesce admin_q in nvme_tcp_teardown_io_queues()

2024-12-04T18:15:46+00:00

As we quiesce admin_q in nvme_tcp_teardown_admin_queue(), so we should no
need to quiesce it in nvme_tcp_reaardown_io_queues(), make things simple.

Signed-off-by: Chunguang.xu 
Reviewed-by: Christoph Hellwig 
Reviewed-by: Hannes Reinecke 
Signed-off-by: Keith Busch

nvme-rdma: unquiesce admin_q before destroy it

2024-12-04T18:15:46+00:00

Kernel will hang on destroy admin_q while we create ctrl failed, such
as following calltrace:

PID: 23644    TASK: ff2d52b40f439fc0  CPU: 2    COMMAND: "nvme"
 #0 [ff61d23de260fb78] __schedule at ffffffff8323bc15
 #1 [ff61d23de260fc08] schedule at ffffffff8323c014
 #2 [ff61d23de260fc28] blk_mq_freeze_queue_wait at ffffffff82a3dba1
 #3 [ff61d23de260fc78] blk_freeze_queue at ffffffff82a4113a
 #4 [ff61d23de260fc90] blk_cleanup_queue at ffffffff82a33006
 #5 [ff61d23de260fcb0] nvme_rdma_destroy_admin_queue at ffffffffc12686ce
 #6 [ff61d23de260fcc8] nvme_rdma_setup_ctrl at ffffffffc1268ced
 #7 [ff61d23de260fd28] nvme_rdma_create_ctrl at ffffffffc126919b
 #8 [ff61d23de260fd68] nvmf_dev_write at ffffffffc024f362
 #9 [ff61d23de260fe38] vfs_write at ffffffff827d5f25
    RIP: 00007fda7891d574  RSP: 00007ffe2ef06958  RFLAGS: 00000202
    RAX: ffffffffffffffda  RBX: 000055e8122a4d90  RCX: 00007fda7891d574
    RDX: 000000000000012b  RSI: 000055e8122a4d90  RDI: 0000000000000004
    RBP: 00007ffe2ef079c0   R8: 000000000000012b   R9: 000055e8122a4d90
    R10: 0000000000000000  R11: 0000000000000202  R12: 0000000000000004
    R13: 000055e8122923c0  R14: 000000000000012b  R15: 00007fda78a54500
    ORIG_RAX: 0000000000000001  CS: 0033  SS: 002b

This due to we have quiesced admi_q before cancel requests, but forgot
to unquiesce before destroy it, as a result we fail to drain the
pending requests, and hang on blk_mq_freeze_queue_wait() forever. Here
try to reuse nvme_rdma_teardown_admin_queue() to fix this issue and
simplify the code.

Fixes: 958dc1d32c80 ("nvme-rdma: add clean action for failed reconnection")
Reported-by: Yingfu.zhou 
Signed-off-by: Chunguang.xu 
Signed-off-by: Yue.zhao 
Reviewed-by: Christoph Hellwig 
Reviewed-by: Hannes Reinecke 
Signed-off-by: Keith Busch

nvme-tcp: fix the memleak while create new ctrl failed

2024-12-04T18:15:46+00:00

Now while we create new ctrl failed, we have not free the
tagset occupied by admin_q, here try to fix it.

Fixes: fd1418de10b9 ("nvme-tcp: avoid open-coding nvme_tcp_teardown_admin_queue()")
Signed-off-by: Chunguang.xu 
Reviewed-by: Christoph Hellwig 
Reviewed-by: Hannes Reinecke 
Signed-off-by: Keith Busch

nvme-pci: don't use dma_alloc_noncontiguous with 0 merge boundary

2024-12-04T17:23:11+00:00

Only call into nvme_alloc_host_mem_single which uses
dma_alloc_noncontiguous when there is non-null dma merge boundary.
Without this we'll call into dma_alloc_noncontiguous for device using
dma-direct, which can work fine as long as the preferred size is below the
MAX_ORDER of the page allocator, but blows up with a warning if it is
too large.

Fixes: 63a5c7a4b4c4 ("nvme-pci: use dma_alloc_noncontigous if possible")
Reported-by: Leon Romanovsky 
Reported-by: Chaitanya Kumar Borah 
Signed-off-by: Christoph Hellwig 
Reviewed-by: Leon Romanovsky 
Tested-by: Chaitanya Kumar Borah 
Signed-off-by: Keith Busch