[PATCH v5 07/16] nvme: Introduce FENCING and FENCED controller states

[Mohamed Khalfella]

Introduce two new controller states, FENCING and FENCED, and the state
machine transitions needed to support them. Transports will move a LIVE
controller into these states when an error is encountered; this patch
only adds the states themselves.

FENCING is entered from LIVE. While in FENCING the queues remain alive
but new requests are not allowed to be sent, and the controller can be
neither reset nor deleted (there is no transition from FENCING to
RESETTING, DELETING or DELETING_NOIO). This is intentional because
resetting or deleting the controller cancels inflight IOs, which should
be held until either CCR succeeds or time-based recovery completes.

FENCED is a short-lived state entered from FENCING before a reset. It is
the only state from which RESETTING is reachable, so it exists to
prevent a manual reset from taking effect while the controller is still
in FENCING.

Both states are treated as non-terminal by nvme_state_terminal(), and
their names are exposed via the sysfs state attribute.

Signed-off-by: Mohamed Khalfella <mkhalfella at purestorage.com>
Reviewed-by: Hannes Reinecke <hare at suse.de>
Reviewed-by: Randy Jennings <randyj at purestorage.com>
---
 drivers/nvme/host/core.c  | 27 +++++++++++++++++++++++++--
 drivers/nvme/host/nvme.h  |  4 ++++
 drivers/nvme/host/sysfs.c |  2 ++
 3 files changed, 31 insertions(+), 2 deletions(-)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 203ecafc1aec..1ef4dc38f755 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -591,10 +591,29 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl,
 			break;
 		}
 		break;
+	case NVME_CTRL_FENCING:
+		switch (old_state) {
+		case NVME_CTRL_LIVE:
+			changed = true;
+			fallthrough;
+		default:
+			break;
+		}
+		break;
+	case NVME_CTRL_FENCED:
+		switch (old_state) {
+		case NVME_CTRL_FENCING:
+			changed = true;
+			fallthrough;
+		default:
+			break;
+		}
+		break;
 	case NVME_CTRL_RESETTING:
 		switch (old_state) {
 		case NVME_CTRL_NEW:
 		case NVME_CTRL_LIVE:
+		case NVME_CTRL_FENCED:
 			changed = true;
 			atomic_long_inc(&ctrl->nr_reset);
 			fallthrough;
@@ -776,6 +795,8 @@ blk_status_t nvme_fail_nonready_command(struct nvme_ctrl *ctrl,
 
 	if (state != NVME_CTRL_DELETING_NOIO &&
 	    state != NVME_CTRL_DELETING &&
+	    state != NVME_CTRL_FENCING &&
+	    state != NVME_CTRL_FENCED &&
 	    state != NVME_CTRL_DEAD &&
 	    !test_bit(NVME_CTRL_FAILFAST_EXPIRED, &ctrl->flags) &&
 	    !blk_noretry_request(rq) && !(rq->cmd_flags & REQ_NVME_MPATH))
@@ -818,10 +839,12 @@ bool __nvme_check_ready(struct nvme_ctrl *ctrl, struct request *rq,
 			     req->cmd->fabrics.fctype == nvme_fabrics_type_auth_receive))
 				return true;
 			break;
-		default:
-			break;
+		case NVME_CTRL_FENCING:
+		case NVME_CTRL_FENCED:
 		case NVME_CTRL_DEAD:
 			return false;
+		default:
+			break;
 		}
 	}
 
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 9b071076c9f4..e558a19781bd 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -305,6 +305,8 @@ static inline u16 nvme_req_qid(struct request *req)
 enum nvme_ctrl_state {
 	NVME_CTRL_NEW,
 	NVME_CTRL_LIVE,
+	NVME_CTRL_FENCING,
+	NVME_CTRL_FENCED,
 	NVME_CTRL_RESETTING,
 	NVME_CTRL_CONNECTING,
 	NVME_CTRL_DELETING,
@@ -850,6 +852,8 @@ static inline bool nvme_state_terminal(struct nvme_ctrl *ctrl)
 	switch (nvme_ctrl_state(ctrl)) {
 	case NVME_CTRL_NEW:
 	case NVME_CTRL_LIVE:
+	case NVME_CTRL_FENCING:
+	case NVME_CTRL_FENCED:
 	case NVME_CTRL_RESETTING:
 	case NVME_CTRL_CONNECTING:
 		return false;
diff --git a/drivers/nvme/host/sysfs.c b/drivers/nvme/host/sysfs.c
index dd48c0989301..3853c9a6356e 100644
--- a/drivers/nvme/host/sysfs.c
+++ b/drivers/nvme/host/sysfs.c
@@ -542,6 +542,8 @@ static ssize_t nvme_sysfs_show_state(struct device *dev,
 	static const char *const state_name[] = {
 		[NVME_CTRL_NEW]		= "new",
 		[NVME_CTRL_LIVE]	= "live",
+		[NVME_CTRL_FENCING]	= "fencing",
+		[NVME_CTRL_FENCED]	= "fenced",
 		[NVME_CTRL_RESETTING]	= "resetting",
 		[NVME_CTRL_CONNECTING]	= "connecting",
 		[NVME_CTRL_DELETING]	= "deleting",
-- 
2.54.0