scsi: sd: Have midlayer retry sd_spinup_disk() errors

This simplifies sd_spinup_disk() so the SCSI midlayer retries errors for
it. Note that we retried every UA except Medium Not Present and also if
scsi_status_is_good() returned failed which would happen for all check
conditions. In this patch we use SCMD_FAILURE_STAT_ANY which will trigger
for the same conditions as when scsi_status_is_good() returns false and
there is status. This will cover all CCs including UAs so there is no
explicit failures array entry for UAs except for Medium Not Present which
we don't want to retry.

There is one behavior change where we no longer retry when
scsi_execute_cmd() returns < 0, but we should be ok. We don't need to retry
for failures like the queue being removed, and for the case where there are
no tags/reqs the block layer waits/retries for us. For possible memory
allocation failures from blk_rq_map_kern() we use GFP_NOIO, so retrying
will probably not help.

We do not handle the outside loop's retries because we want to sleep
between tries and we don't support that yet.
Signed-off-by: Mike Christie <michael.christie@oracle.com>
Link: https://lore.kernel.org/r/20240123002220.129141-6-michael.christie@oracle.comAcked-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>

drivers/scsi/sd.c

@@ -2235,40 +2235,59 @@ static int sd_done(struct scsi_cmnd *SCpnt)
 static void
 sd_spinup_disk(struct scsi_disk *sdkp)
 {
-	unsigned char cmd[10];
+	static const u8 cmd[10] = { TEST_UNIT_READY };
 	unsigned long spintime_expire = 0;
-	int retries, spintime;
+	int spintime, sense_valid = 0;
 	unsigned int the_result;
 	struct scsi_sense_hdr sshdr;
+	struct scsi_failure failure_defs[] = {
+		/* Do not retry Medium Not Present */
+		{
+			.sense = UNIT_ATTENTION,
+			.asc = 0x3A,
+			.ascq = SCMD_FAILURE_ASCQ_ANY,
+			.result = SAM_STAT_CHECK_CONDITION,
+		},
+		{
+			.sense = NOT_READY,
+			.asc = 0x3A,
+			.ascq = SCMD_FAILURE_ASCQ_ANY,
+			.result = SAM_STAT_CHECK_CONDITION,
+		},
+		/* Retry when scsi_status_is_good would return false 3 times */
+		{
+			.result = SCMD_FAILURE_STAT_ANY,
+			.allowed = 3,
+		},
+		{}
+	};
+	struct scsi_failures failures = {
+		.failure_definitions = failure_defs,
+	};
 	const struct scsi_exec_args exec_args = {
 		.sshdr = &sshdr,
+		.failures = &failures,
 	};
-	int sense_valid = 0;
 
 	spintime = 0;
 
 	/* Spin up drives, as required.  Only do this at boot time */
 	/* Spinup needs to be done for module loads too. */
-	do {
-		retries = 0;
-
 	do {
 		bool media_was_present = sdkp->media_present;
 
-			cmd[0] = TEST_UNIT_READY;
-			memset((void *) &cmd[1], 0, 9);
+		scsi_failures_reset_retries(&failures);
+
+		the_result = scsi_execute_cmd(sdkp->device, cmd, REQ_OP_DRV_IN,
+					      NULL, 0, SD_TIMEOUT,
+					      sdkp->max_retries, &exec_args);
 
-			the_result = scsi_execute_cmd(sdkp->device, cmd,
-						      REQ_OP_DRV_IN, NULL, 0,
-						      SD_TIMEOUT,
-						      sdkp->max_retries,
-						      &exec_args);
 
 		if (the_result > 0) {
 			/*
-				 * If the drive has indicated to us that it
-				 * doesn't have any media in it, don't bother
-				 * with any more polling.
+			 * If the drive has indicated to us that it doesn't
+			 * have any media in it, don't bother with any more
+			 * polling.
 			 */
 			if (media_not_present(sdkp, &sshdr)) {
 				if (media_was_present)
@@ -2276,14 +2295,8 @@ sd_spinup_disk(struct scsi_disk *sdkp)
 						  "Media removed, stopped polling\n");
 				return;
 			}
-
 			sense_valid = scsi_sense_valid(&sshdr);
 		}
-			retries++;
-		} while (retries < 3 &&
-			 (!scsi_status_is_good(the_result) ||
-			  (scsi_status_is_check_condition(the_result) &&
-			  sense_valid && sshdr.sense_key == UNIT_ATTENTION)));
 
 		if (!scsi_status_is_check_condition(the_result)) {
 			/* no sense, TUR either succeeded or failed