diff options
| author | Jens Axboe <axboe@kernel.dk> | 2018-02-15 03:01:53 +0100 |
|---|---|---|
| committer | Jens Axboe <axboe@kernel.dk> | 2018-02-15 03:01:53 +0100 |
| commit | 7ddbc29fe4efea44e120c8dc085fa78fc28bb65f (patch) | |
| tree | 34e4692decb422461a719dafbeb7d4bc86535950 /drivers/nvme/host/fabrics.h | |
| parent | blk: optimization for classic polling (diff) | |
| parent | nvme-rdma: fix sysfs invoked reset_ctrl error flow (diff) | |
| download | linux-7ddbc29fe4efea44e120c8dc085fa78fc28bb65f.tar.xz linux-7ddbc29fe4efea44e120c8dc085fa78fc28bb65f.zip | |
Merge branch 'nvme-4.16-rc' of git://git.infradead.org/nvme into for-linus
Pull NVMe fixes from Keith:
"After syncing with Christoph and Sagi, we feel this is a good time to
send our latest fixes across most of the nvme components for 4.16"
* 'nvme-4.16-rc' of git://git.infradead.org/nvme:
nvme-rdma: fix sysfs invoked reset_ctrl error flow
nvmet: Change return code of discard command if not supported
nvme-pci: Fix timeouts in connecting state
nvme-pci: Remap CMB SQ entries on every controller reset
nvme: fix the deadlock in nvme_update_formats
nvme: Don't use a stack buffer for keep-alive command
nvme_fc: cleanup io completion
nvme_fc: correct abort race condition on resets
nvme: Fix discard buffer overrun
nvme: delete NVME_CTRL_LIVE --> NVME_CTRL_CONNECTING transition
nvme-rdma: use NVME_CTRL_CONNECTING state to mark init process
nvme: rename NVME_CTRL_RECONNECTING state to NVME_CTRL_CONNECTING
Diffstat (limited to 'drivers/nvme/host/fabrics.h')
| -rw-r--r-- | drivers/nvme/host/fabrics.h | 9 |
1 files changed, 5 insertions, 4 deletions
diff --git a/drivers/nvme/host/fabrics.h b/drivers/nvme/host/fabrics.h index 25b19f722f5b..a3145d90c1d2 100644 --- a/drivers/nvme/host/fabrics.h +++ b/drivers/nvme/host/fabrics.h @@ -171,13 +171,14 @@ static inline blk_status_t nvmf_check_init_req(struct nvme_ctrl *ctrl, cmd->common.opcode != nvme_fabrics_command || cmd->fabrics.fctype != nvme_fabrics_type_connect) { /* - * Reconnecting state means transport disruption, which can take - * a long time and even might fail permanently, fail fast to - * give upper layers a chance to failover. + * Connecting state means transport disruption or initial + * establishment, which can take a long time and even might + * fail permanently, fail fast to give upper layers a chance + * to failover. * Deleting state means that the ctrl will never accept commands * again, fail it permanently. */ - if (ctrl->state == NVME_CTRL_RECONNECTING || + if (ctrl->state == NVME_CTRL_CONNECTING || ctrl->state == NVME_CTRL_DELETING) { nvme_req(rq)->status = NVME_SC_ABORT_REQ; return BLK_STS_IOERR; |