[PATCH v6 0/3] keepalive bugfixes

[Uday Shankar]

While reviewing the Linux KATO implementation in an attempt to better
understand the current NVMe Keep Alive specification, we found a
few issues in the host implementation that could contribute to spurious
Keep Alive timeouts being detected by controllers.

Changes v5-v6 (https://lore.kernel.org/linux-nvme/20230524232218.1584605-1-ushankar@purestorage.com/):
- Patch 2: fix line length and extra empty line, add comment about
  	   req->deadline - req->timeout

Changes v4-v5 (https://lore.kernel.org/linux-nvme/20230524193809.1360269-1-ushankar@purestorage.com/):
- Patch 2: revert changes to start_time; use req->deadline -
           req->timeout instead

Changes v3-v4 (https://lore.kernel.org/linux-nvme/20230518183311.3224326-1-ushankar@purestorage.com/):
- Patch 1: fix style, improve readability, include helper from patch 3
- Patch 2: refactor to remove need for WRITE_ONCE/barriers
- Patch 3: fix comment style, move helper to patch 1

Changes v2-v3 (https://lore.kernel.org/linux-nvme/20230424232225.1975793-1-ushankar@purestorage.com/):
- Patch 3: add a warning log line for long keepalive RTT

Changes v1-v2 (https://lore.kernel.org/linux-nvme/20230417225558.2890062-1-ushankar@purestorage.com/):
- Patch 2: fix indentation, set start_time even when stats disabled

Uday Shankar (3):
  nvme: double KA polling frequency to avoid KATO with TBKAS on
  nvme: check IO start time when deciding to defer KA
  nvme: improve handling of long keep alives

 drivers/nvme/host/core.c | 48 +++++++++++++++++++++++++++++++++++++---
 drivers/nvme/host/nvme.h |  1 +
 2 files changed, 46 insertions(+), 3 deletions(-)

-- 
2.25.1