scsi_transport_srp: Add transport layer error handling

Add the necessary functions in the SRP transport module to allow an
SRP initiator driver to implement transport layer error handling
similar to the functionality already provided by the FC transport
layer. This includes:

- Support for implementing fast_io_fail_tmo, the time that should
  elapse after having detected a transport layer problem and
  before failing I/O.
- Support for implementing dev_loss_tmo, the time that should
  elapse after having detected a transport layer problem and
  before removing a remote port.

Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Acked-by: David Dillow <dillowda@ornl.gov>
Signed-off-by: Roland Dreier <roland@purestorage.com>

1 files changed, 72 insertions, 2 deletions

diff --git a/include/scsi/scsi_transport_srp.h b/include/scsi/scsi_transport_srp.h
index 5a2d2d1..ee70016 100644
--- a/include/scsi/scsi_transport_srp.h
+++ b/include/scsi/scsi_transport_srp.h
@@ -13,6 +13,26 @@ struct srp_rport_identifiers {
 	u8 roles;
 };
 
+/**
+ * enum srp_rport_state - SRP transport layer state
+ * @SRP_RPORT_RUNNING:   Transport layer operational.
+ * @SRP_RPORT_BLOCKED:   Transport layer not operational; fast I/O fail timer
+ *                       is running and I/O has been blocked.
+ * @SRP_RPORT_FAIL_FAST: Fast I/O fail timer has expired; fail I/O fast.
+ * @SRP_RPORT_LOST:      Device loss timer has expired; port is being removed.
+ */
+enum srp_rport_state {
+	SRP_RPORT_RUNNING,
+	SRP_RPORT_BLOCKED,
+	SRP_RPORT_FAIL_FAST,
+	SRP_RPORT_LOST,
+};
+
+/**
+ * struct srp_rport
+ * @lld_data: LLD private data.
+ * @mutex:    Protects against concurrent rport fast_io_fail / dev_loss_tmo.
+ */
 struct srp_rport {
 	/* for initiator and target drivers */
 
@@ -23,11 +43,38 @@ struct srp_rport {
 
 	/* for initiator drivers */
 
-	void *lld_data;	/* LLD private data */
+	void			*lld_data;
+
+	struct mutex		mutex;
+	enum srp_rport_state	state;
+	bool			deleted;
+	int			fast_io_fail_tmo;
+	int			dev_loss_tmo;
+	struct delayed_work	fast_io_fail_work;
+	struct delayed_work	dev_loss_work;
 };
 
+/**
+ * struct srp_function_template
+ * @has_rport_state: Whether or not to create the state, fast_io_fail_tmo and
+ *     dev_loss_tmo sysfs attribute for an rport.
+ * @reset_timer_if_blocked: Whether or srp_timed_out() should reset the command
+ *     timer if the device on which it has been queued is blocked.
+ * @fast_io_fail_tmo: If not NULL, points to the default fast_io_fail_tmo value.
+ * @dev_loss_tmo: If not NULL, points to the default dev_loss_tmo value.
+ * @reconnect: Callback function for reconnecting to the target. See also
+ *     srp_reconnect_rport().
+ * @terminate_rport_io: Callback function for terminating all outstanding I/O
+ *     requests for an rport.
+ */
 struct srp_function_template {
 	/* for initiator drivers */
+	bool has_rport_state;
+	bool reset_timer_if_blocked;
+	int *fast_io_fail_tmo;
+	int *dev_loss_tmo;
+	int (*reconnect)(struct srp_rport *rport);
+	void (*terminate_rport_io)(struct srp_rport *rport);
 	void (*rport_delete)(struct srp_rport *rport);
 	/* for target drivers */
 	int (* tsk_mgmt_response)(struct Scsi_Host *, u64, u64, int);
@@ -43,7 +90,30 @@ extern void srp_rport_put(struct srp_rport *rport);
 extern struct srp_rport *srp_rport_add(struct Scsi_Host *,
 				       struct srp_rport_identifiers *);
 extern void srp_rport_del(struct srp_rport *);
-
+extern int srp_tmo_valid(int fast_io_fail_tmo, int dev_loss_tmo);
+extern int srp_reconnect_rport(struct srp_rport *rport);
+extern void srp_start_tl_fail_timers(struct srp_rport *rport);
 extern void srp_remove_host(struct Scsi_Host *);
 
+/**
+ * srp_chkready() - evaluate the transport layer state before I/O
+ *
+ * Returns a SCSI result code that can be returned by the LLD queuecommand()
+ * implementation. The role of this function is similar to that of
+ * fc_remote_port_chkready().
+ */
+static inline int srp_chkready(struct srp_rport *rport)
+{
+	switch (rport->state) {
+	case SRP_RPORT_RUNNING:
+	case SRP_RPORT_BLOCKED:
+	default:
+		return 0;
+	case SRP_RPORT_FAIL_FAST:
+		return DID_TRANSPORT_FAILFAST << 16;
+	case SRP_RPORT_LOST:
+		return DID_NO_CONNECT << 16;
+	}
+}
+
 #endif