scsi: core: Add limitless cmd retry support

Add infinite retry support to SCSI midlayer by combining common checks for
retries into some helper functions, and then checking for the
-1/SCSI_CMD_RETRIES_NO_LIMIT.

Link: https://lore.kernel.org/r/1601566554-26752-2-git-send-email-michael.christie@oracle.com
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Mike Christie <michael.christie@oracle.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>

drivers/scsi/scsi_error.c

@@ -116,6 +116,14 @@ static int scsi_host_eh_past_deadline(struct Scsi_Host *shost)
 	return 1;
 }
 
+static bool scsi_cmd_retry_allowed(struct scsi_cmnd *cmd)
+{
+	if (cmd->allowed == SCSI_CMD_RETRIES_NO_LIMIT)
+		return true;
+
+	return ++cmd->retries <= cmd->allowed;
+}
+
 /**
  * scmd_eh_abort_handler - Handle command aborts
  * @work:	command to be aborted.
@@ -151,7 +159,7 @@ scmd_eh_abort_handler(struct work_struct *work)
 						    "eh timeout, not retrying "
 						    "aborted command\n"));
 			} else if (!scsi_noretry_cmd(scmd) &&
-			    (++scmd->retries <= scmd->allowed)) {
+				   scsi_cmd_retry_allowed(scmd)) {
 				SCSI_LOG_ERROR_RECOVERY(3,
 					scmd_printk(KERN_WARNING, scmd,
 						    "retry aborted command\n"));
@@ -1264,11 +1272,18 @@ int scsi_eh_get_sense(struct list_head *work_q,
 		 * upper level.
 		 */
 		if (rtn == SUCCESS)
-			/* we don't want this command reissued, just
+			/*
-			 * finished with the sense data, so set
+			 * We don't want this command reissued, just finished
-			 * retries to the max allowed to ensure it
+			 * with the sense data, so set retries to the max
-			 * won't get reissued */
+			 * allowed to ensure it won't get reissued. If the user
-			scmd->retries = scmd->allowed;
+			 * has requested infinite retries, we also want to
+			 * finish this command, so force completion by setting
+			 * retries and allowed to the same value.
+			 */
+			if (scmd->allowed == SCSI_CMD_RETRIES_NO_LIMIT)
+				scmd->retries = scmd->allowed = 1;
+			else
+				scmd->retries = scmd->allowed;
 		else if (rtn != NEEDS_RETRY)
 			continue;
 
@@ -1944,8 +1959,7 @@ maybe_retry:
 	 * the request was not marked fast fail.  Note that above,
 	 * even if the request is marked fast fail, we still requeue
 	 * for queue congestion conditions (QUEUE_FULL or BUSY) */
-	if ((++scmd->retries) <= scmd->allowed
+	if (scsi_cmd_retry_allowed(scmd) && !scsi_noretry_cmd(scmd)) {
-	    && !scsi_noretry_cmd(scmd)) {
 		return NEEDS_RETRY;
 	} else {
 		/*
@@ -2091,8 +2105,7 @@ void scsi_eh_flush_done_q(struct list_head *done_q)
 	list_for_each_entry_safe(scmd, next, done_q, eh_entry) {
 		list_del_init(&scmd->eh_entry);
 		if (scsi_device_online(scmd->device) &&
-		    !scsi_noretry_cmd(scmd) &&
+		    !scsi_noretry_cmd(scmd) && scsi_cmd_retry_allowed(scmd)) {
-		    (++scmd->retries <= scmd->allowed)) {
 			SCSI_LOG_ERROR_RECOVERY(3,
 				scmd_printk(KERN_INFO, scmd,
 					     "%s: flush retry cmd\n",

drivers/scsi/scsi_lib.c

@@ -669,6 +669,23 @@ static void scsi_io_completion_reprep(struct scsi_cmnd *cmd,
 	scsi_mq_requeue_cmd(cmd);
 }
 
+static bool scsi_cmd_runtime_exceeced(struct scsi_cmnd *cmd)
+{
+	struct request *req = cmd->request;
+	unsigned long wait_for;
+
+	if (cmd->allowed == SCSI_CMD_RETRIES_NO_LIMIT)
+		return false;
+
+	wait_for = (cmd->allowed + 1) * req->timeout;
+	if (time_before(cmd->jiffies_at_alloc + wait_for, jiffies)) {
+		scmd_printk(KERN_ERR, cmd, "timing out command, waited %lus\n",
+			    wait_for/HZ);
+		return true;
+	}
+	return false;
+}
+
 /* Helper for scsi_io_completion() when special action required. */
 static void scsi_io_completion_action(struct scsi_cmnd *cmd, int result)
 {
@@ -677,7 +694,6 @@ static void scsi_io_completion_action(struct scsi_cmnd *cmd, int result)
 	int level = 0;
 	enum {ACTION_FAIL, ACTION_REPREP, ACTION_RETRY,
 	      ACTION_DELAYED_RETRY} action;
-	unsigned long wait_for = (cmd->allowed + 1) * req->timeout;
 	struct scsi_sense_hdr sshdr;
 	bool sense_valid;
 	bool sense_current = true;      /* false implies "deferred sense" */
@@ -782,8 +798,7 @@ static void scsi_io_completion_action(struct scsi_cmnd *cmd, int result)
 	} else
 		action = ACTION_FAIL;
 
-	if (action != ACTION_FAIL &&
+	if (action != ACTION_FAIL && scsi_cmd_runtime_exceeced(cmd))
-	    time_before(cmd->jiffies_at_alloc + wait_for, jiffies))
 		action = ACTION_FAIL;
 
 	switch (action) {
@@ -1456,7 +1471,6 @@ static bool scsi_mq_lld_busy(struct request_queue *q)
 static void scsi_softirq_done(struct request *rq)
 {
 	struct scsi_cmnd *cmd = blk_mq_rq_to_pdu(rq);
-	unsigned long wait_for = (cmd->allowed + 1) * rq->timeout;
 	int disposition;
 
 	INIT_LIST_HEAD(&cmd->eh_entry);
@@ -1466,13 +1480,8 @@ static void scsi_softirq_done(struct request *rq)
 		atomic_inc(&cmd->device->ioerr_cnt);
 
 	disposition = scsi_decide_disposition(cmd);
-	if (disposition != SUCCESS &&
+	if (disposition != SUCCESS && scsi_cmd_runtime_exceeced(cmd))
-	    time_before(cmd->jiffies_at_alloc + wait_for, jiffies)) {
-		scmd_printk(KERN_ERR, cmd,
-			    "timing out command, waited %lus\n",
-			    wait_for/HZ);
 		disposition = SUCCESS;
-	}
 
 	scsi_log_completion(cmd, disposition);
 

drivers/scsi/scsi_priv.h

@@ -15,6 +15,7 @@ struct scsi_host_template;
 struct Scsi_Host;
 struct scsi_nl_hdr;
 
+#define SCSI_CMD_RETRIES_NO_LIMIT -1
 
 /*
  * Scsi Error Handler Flags