Linux SCSI subsystem development
 help / color / mirror / Atom feed
* [PATCH v4 00/13] Introduce functionality for NVMe initiator
@ 2026-06-12 18:09 Karan Tilak Kumar
  2026-06-12 18:09 ` [PATCH v4 01/13] scsi: fnic: Make debug logging protocol independent Karan Tilak Kumar
                   ` (12 more replies)
  0 siblings, 13 replies; 24+ messages in thread
From: Karan Tilak Kumar @ 2026-06-12 18:09 UTC (permalink / raw)
  To: sebaddel
  Cc: arulponn, djhawar, gcboffa, mkai2, satishkh, aeasi, jejb,
	martin.petersen, linux-scsi, linux-kernel, jmeneghi, revers,
	adakopou, lduncan, Karan Tilak Kumar

Hi Martin, reviewers,

This series adds functionality for NVMe initiator to the fnic driver.

The changes enable the fnic driver to act as an NVMe initiator over
Fibre Channel (FC-NVMe), allowing the host to discover and communicate
with NVMe targets using the existing fnic infrastructure. The patches
prepare the driver for full FC-NVMe initiator operation while
maintaining existing SCSI/FC functionality.

These are some of the salient patches:

o. Make fnic debug logging usable by SCSI and NVMe initiator roles.
o. Use fnic instance numbers for non-SCSI-facing identifiers.
o. Decode firmware roles for FCP, NVMe, and unsupported targets.
o. Advertise NVMe initiator service parameters during FC discovery.
o. Add FDLS role handling for NVMe initiator discovery flows.
o. Add the NVMe/FC transport path and port registration.
o. Route completions, resets, and LS frames by initiator role.
o. Add NVMe LS timeouts, statistics, and debugfs state reporting.

Even though the patches have been made into a series, some patches are
heavier than others. But, every effort has been made to keep the
purpose of each patch as a single-purpose, and to compile cleanly.
All the individual patches compile cleanly. The compiler used is GCC
14.2.

This patch set has been tested as a whole. Therefore, the tested-by
fields have been added only to one patch in the set.
I've refrained from adding tested-by to most of the patches, so as to
not mislead the reviewer/reader.

A brief note on the unit tests:

o. Configure multipathing, and run link flaps on single link. IOs drop
   briefly, but pick up as expected.
o. Configure multipathing, and run link flaps on two links, with a 30
   second delay in between. IOs drop briefly, but pick up as expected.
o. Repeat the above tests with 1 queue and 64 queues.
o. Perform tests with Netapp and Pure targets.

All tests were successful.

This set of patches was reviewed before submitting upstream,
and the following review comments were incorporated.

Incorporate review comments from Hannes Reinecke:

Decode target roles explicitly and report unsupported roles.
Remove the empty line before the FLOGI completion else block.
Add a short comment for the NVMe ERSP completion case.

Incorporate review comments from Lee Duncan:

Replace the NVMe LS OXID switch with a direct frame-type check.
Rename the NVMe frame helper to follow fnic function naming style.
Convert the NVMe opcode stats helper to a switch statement.
Share NVMe completion stats accounting and compute duration once.

Changes between v1 and v2:
	Incorporate review comments from Marco Crivellari:
		Explicitly use WQ_PERCPU for the fnic completion workqueue.

Changes between v2 and v3:
	Fix issues reported by kernel bot.
	Add the active OXID to the tport timeout debug print.
	Guard NVMe I/O and LS request debug logs when tport is NULL.
	Validate ERSP response length before copying the response.
	Validate LS response frame and payload lengths before copying.
	Limit nvmef_info debugfs output to the allocated buffer.

Changes between v3 and v4:
	Incorporate review comments from Sashiko:
		Keep role strings private and const.
		Clear NVMe SGL DMA address on map failure.
		Drop fnic lock around NVMe tport registration.
		Unlink unregistered NVMe tports before freeing them.
		Clear NVMe unload completion pointer on exit.
		Take fnic lock before NVMe tport cleanup tag lookup.
		Clear NVMe tport delete completion pointer on unregister failure.
		Arm NVMe LS request timer before exposing the request.
		Free LS ABTS frame when send fails.
		Reuse NVMe LS request cleanup for abort failure.
		Decrement NVMe completion wait queue counter when draining completions.
		Preserve jiffies wrap when computing NVMe abort stats.

Thanks,
Karan

Karan Tilak Kumar (13):
  scsi: fnic: Make debug logging protocol independent
  scsi: fnic: Use fnic_num for non-SCSI identifiers
  scsi: fnic: Decode firmware role configuration
  scsi: fnic: Advertise NVMe initiator service parameters
  scsi: fnic: Add FDLS role handling for NVMe initiators
  scsi: fnic: Add the NVMe/FC transport path
  scsi: fnic: Route completions and resets by initiator role
  scsi: fnic: Handle NVMe LS frames in FDLS
  scsi: fnic: Send NVMe LS requests through FDLS
  scsi: fnic: Abort timed-out NVMe LS requests
  scsi: fnic: Track NVMe transport statistics
  scsi: fnic: Expose NVMe transport state in debugfs
  scsi: fnic: Bump up version number

 drivers/scsi/fnic/Makefile       |    1 +
 drivers/scsi/fnic/fcpio.h        |   35 +
 drivers/scsi/fnic/fdls_disc.c    |  959 +++++++------
 drivers/scsi/fnic/fdls_fc.h      |   12 +
 drivers/scsi/fnic/fip.c          |  117 +-
 drivers/scsi/fnic/fip.h          |    2 +-
 drivers/scsi/fnic/fnic.h         |  104 +-
 drivers/scsi/fnic/fnic_debugfs.c |  101 +-
 drivers/scsi/fnic/fnic_fcs.c     |  196 +--
 drivers/scsi/fnic/fnic_fdls.h    |   48 +-
 drivers/scsi/fnic/fnic_io.h      |   23 +-
 drivers/scsi/fnic/fnic_isr.c     |   28 +-
 drivers/scsi/fnic/fnic_main.c    |  212 ++-
 drivers/scsi/fnic/fnic_nvme.c    | 2185 ++++++++++++++++++++++++++++++
 drivers/scsi/fnic/fnic_nvme.h    |  209 +++
 drivers/scsi/fnic/fnic_res.c     |   31 +-
 drivers/scsi/fnic/fnic_res.h     |   32 +-
 drivers/scsi/fnic/fnic_scsi.c    |  249 ++--
 drivers/scsi/fnic/fnic_stats.h   |   28 +
 drivers/scsi/fnic/fnic_trace.c   |    3 +-
 drivers/scsi/fnic/vnic_devcmd.h  |    2 +-
 21 files changed, 3800 insertions(+), 777 deletions(-)
 create mode 100644 drivers/scsi/fnic/fnic_nvme.c
 create mode 100644 drivers/scsi/fnic/fnic_nvme.h

-- 
2.47.1


^ permalink raw reply	[flat|nested] 24+ messages in thread

end of thread, other threads:[~2026-06-12 23:22 UTC | newest]

Thread overview: 24+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2026-06-12 18:09 [PATCH v4 00/13] Introduce functionality for NVMe initiator Karan Tilak Kumar
2026-06-12 18:09 ` [PATCH v4 01/13] scsi: fnic: Make debug logging protocol independent Karan Tilak Kumar
2026-06-12 18:42   ` sashiko-bot
2026-06-12 18:09 ` [PATCH v4 02/13] scsi: fnic: Use fnic_num for non-SCSI identifiers Karan Tilak Kumar
2026-06-12 18:57   ` sashiko-bot
2026-06-12 18:09 ` [PATCH v4 03/13] scsi: fnic: Decode firmware role configuration Karan Tilak Kumar
2026-06-12 18:09 ` [PATCH v4 04/13] scsi: fnic: Advertise NVMe initiator service parameters Karan Tilak Kumar
2026-06-12 18:09 ` [PATCH v4 05/13] scsi: fnic: Add FDLS role handling for NVMe initiators Karan Tilak Kumar
2026-06-12 21:42   ` sashiko-bot
2026-06-12 18:09 ` [PATCH v4 06/13] scsi: fnic: Add the NVMe/FC transport path Karan Tilak Kumar
2026-06-12 21:59   ` sashiko-bot
2026-06-12 18:09 ` [PATCH v4 07/13] scsi: fnic: Route completions and resets by initiator role Karan Tilak Kumar
2026-06-12 22:15   ` sashiko-bot
2026-06-12 18:09 ` [PATCH v4 08/13] scsi: fnic: Handle NVMe LS frames in FDLS Karan Tilak Kumar
2026-06-12 22:29   ` sashiko-bot
2026-06-12 18:09 ` [PATCH v4 09/13] scsi: fnic: Send NVMe LS requests through FDLS Karan Tilak Kumar
2026-06-12 22:45   ` sashiko-bot
2026-06-12 18:09 ` [PATCH v4 10/13] scsi: fnic: Abort timed-out NVMe LS requests Karan Tilak Kumar
2026-06-12 22:57   ` sashiko-bot
2026-06-12 18:09 ` [PATCH v4 11/13] scsi: fnic: Track NVMe transport statistics Karan Tilak Kumar
2026-06-12 23:16   ` sashiko-bot
2026-06-12 18:09 ` [PATCH v4 12/13] scsi: fnic: Expose NVMe transport state in debugfs Karan Tilak Kumar
2026-06-12 23:22   ` sashiko-bot
2026-06-12 18:09 ` [PATCH v4 13/13] scsi: fnic: Bump up version number Karan Tilak Kumar

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox