[PATCH v3 0/5] ublk: support device recovery without I/O queueing

[Uday Shankar <ushankar@purestorage.com>]

ublk currently supports the following behaviors on ublk server exit:

A: outstanding I/Os get errors, subsequently issued I/Os get errors
B: outstanding I/Os get errors, subsequently issued I/Os queue
C: outstanding I/Os get reissued, subsequently issued I/Os queue

and the following behaviors for recovery of preexisting block devices by
a future incarnation of the ublk server:

1: ublk devices stopped on ublk server exit (no recovery possible)
2: ublk devices are recoverable using start/end_recovery commands

The userspace interface allows selection of combinations of these
behaviors using flags specified at device creation time, namely:

default behavior: A + 1
UBLK_F_USER_RECOVERY: B + 2
UBLK_F_USER_RECOVERY|UBLK_F_USER_RECOVERY_REISSUE: C + 2

A + 2 is a currently unsupported behavior. This patch series aims to add
support for it.

Userspace support and testing for this flag are available at:
https://github.com/ublk-org/ublksrv/pull/73

Uday Shankar (5):
  ublk: check recovery flags for validity
  ublk: refactor recovery configuration flag helpers
  ublk: merge stop_work and quiesce_work
  ublk: support device recovery without I/O queueing
  Documentation: ublk: document UBLK_F_USER_RECOVERY_FAIL_IO

 Documentation/block/ublk.rst  |  24 +++--
 drivers/block/ublk_drv.c      | 191 +++++++++++++++++++++++-----------
 include/uapi/linux/ublk_cmd.h |  18 ++++
 3 files changed, 165 insertions(+), 68 deletions(-)


base-commit: 52d980df51c607867e40e11eef125cb51f8769a5
-- 
2.34.1