]> www.infradead.org Git - users/jedix/linux-maple.git/commit
NVMe: Remove queue freezing on resets
authorKeith Busch <keith.busch@intel.com>
Mon, 4 Jan 2016 16:10:57 +0000 (09:10 -0700)
committerChuck Anderson <chuck.anderson@oracle.com>
Thu, 1 Jun 2017 20:40:55 +0000 (13:40 -0700)
commitc65adda5fd063454266f8704b78b6004f6fb8f7e
tree504cd369bf21085468d939e920c26a3eca878544
parentdb51ddd3c746c1ca517c64a6b916945d25ff9bb6
NVMe: Remove queue freezing on resets

NVMe submits all commands through the block layer now. This means we
can let requests queue at the blk-mq hardware context since there is no
path that bypasses this anymore so we don't need to freeze the queues
anymore. The driver can simply stop the h/w queues from running during
a reset instead.

This also fixes a WARN in percpu_ref_reinit when the queue was unfrozen
with requeued requests.

Signed-off-by: Keith Busch <keith.busch@intel.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
(cherry picked from commit 25646264e15af96c5c630fc742708b1eb3339222)

Orabug: 25130845

Signed-off-by: Ashok Vairavan <ashok.vairavan@oracle.com>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
drivers/nvme/host/core.c
drivers/nvme/host/nvme.h
drivers/nvme/host/pci.c