Merge patch series "scsi: Allow scsi_execute users to request retries"

Mike Christie <michael.christie@oracle.com> says:

The following patches were made over Linus's tree which contains a fix
for sd which was not in Martin's branches.

The patches allow scsi_execute_cmd users to have scsi-ml retry the cmd
for it instead of the caller having to parse the error and loop
itself.

Link: https://lore.kernel.org/r/20240123002220.129141-1-michael.christie@oracle.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>

1 files changed, 65 insertions, 42 deletions

diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c
index 44680f65ea14..70c0319be34c 100644
--- a/drivers/scsi/scsi_scan.c
+++ b/drivers/scsi/scsi_scan.c
@@ -626,6 +626,7 @@ void scsi_sanitize_inquiry_string(unsigned char *s, int len)
 }
 EXPORT_SYMBOL(scsi_sanitize_inquiry_string);
 
+
 /**
  * scsi_probe_lun - probe a single LUN using a SCSI INQUIRY
  * @sdev:	scsi_device to probe
@@ -647,10 +648,36 @@ static int scsi_probe_lun(struct scsi_device *sdev, unsigned char *inq_result,
 	int first_inquiry_len, try_inquiry_len, next_inquiry_len;
 	int response_len = 0;
 	int pass, count, result, resid;
-	struct scsi_sense_hdr sshdr;
+	struct scsi_failure failure_defs[] = {
+		/*
+		 * not-ready to ready transition [asc/ascq=0x28/0x0] or
+		 * power-on, reset [asc/ascq=0x29/0x0], continue. INQUIRY
+		 * should not yield UNIT_ATTENTION but many buggy devices do
+		 * so anyway.
+		 */
+		{
+			.sense = UNIT_ATTENTION,
+			.asc = 0x28,
+			.result = SAM_STAT_CHECK_CONDITION,
+		},
+		{
+			.sense = UNIT_ATTENTION,
+			.asc = 0x29,
+			.result = SAM_STAT_CHECK_CONDITION,
+		},
+		{
+			.allowed = 1,
+			.result = DID_TIME_OUT << 16,
+		},
+		{}
+	};
+	struct scsi_failures failures = {
+		.total_allowed = 3,
+		.failure_definitions = failure_defs,
+	};
 	const struct scsi_exec_args exec_args = {
-		.sshdr = &sshdr,
 		.resid = &resid,
+		.failures = &failures,
 	};
 
 	*bflags = 0;
@@ -668,6 +695,8 @@ static int scsi_probe_lun(struct scsi_device *sdev, unsigned char *inq_result,
 				pass, try_inquiry_len));
 
 	/* Each pass gets up to three chances to ignore Unit Attention */
+	scsi_failures_reset_retries(&failures);
+
 	for (count = 0; count < 3; ++count) {
 		memset(scsi_cmd, 0, 6);
 		scsi_cmd[0] = INQUIRY;
@@ -684,22 +713,7 @@ static int scsi_probe_lun(struct scsi_device *sdev, unsigned char *inq_result,
 				"scsi scan: INQUIRY %s with code 0x%x\n",
 				result ? "failed" : "successful", result));
 
-		if (result > 0) {
-			/*
-			 * not-ready to ready transition [asc/ascq=0x28/0x0]
-			 * or power-on, reset [asc/ascq=0x29/0x0], continue.
-			 * INQUIRY should not yield UNIT_ATTENTION
-			 * but many buggy devices do so anyway. 
-			 */
-			if (scsi_status_is_check_condition(result) &&
-			    scsi_sense_valid(&sshdr)) {
-				if ((sshdr.sense_key == UNIT_ATTENTION) &&
-				    ((sshdr.asc == 0x28) ||
-				     (sshdr.asc == 0x29)) &&
-				    (sshdr.ascq == 0))
-					continue;
-			}
-		} else if (result == 0) {
+		if (result == 0) {
 			/*
 			 * if nothing was transferred, we try
 			 * again. It's a workaround for some USB
@@ -1402,14 +1416,34 @@ static int scsi_report_lun_scan(struct scsi_target *starget, blist_flags_t bflag
 	unsigned int length;
 	u64 lun;
 	unsigned int num_luns;
-	unsigned int retries;
 	int result;
 	struct scsi_lun *lunp, *lun_data;
-	struct scsi_sense_hdr sshdr;
 	struct scsi_device *sdev;
 	struct Scsi_Host *shost = dev_to_shost(&starget->dev);
+	struct scsi_failure failure_defs[] = {
+		{
+			.sense = UNIT_ATTENTION,
+			.asc = SCMD_FAILURE_ASC_ANY,
+			.ascq = SCMD_FAILURE_ASCQ_ANY,
+			.result = SAM_STAT_CHECK_CONDITION,
+		},
+		/* Fail all CCs except the UA above */
+		{
+			.sense = SCMD_FAILURE_SENSE_ANY,
+			.result = SAM_STAT_CHECK_CONDITION,
+		},
+		/* Retry any other errors not listed above */
+		{
+			.result = SCMD_FAILURE_RESULT_ANY,
+		},
+		{}
+	};
+	struct scsi_failures failures = {
+		.total_allowed = 3,
+		.failure_definitions = failure_defs,
+	};
 	const struct scsi_exec_args exec_args = {
-		.sshdr = &sshdr,
+		.failures = &failures,
 	};
 	int ret = 0;
 
@@ -1480,29 +1514,18 @@ retry:
 	 * should come through as a check condition, and will not generate
 	 * a retry.
 	 */
-	for (retries = 0; retries < 3; retries++) {
-		SCSI_LOG_SCAN_BUS(3, sdev_printk (KERN_INFO, sdev,
-				"scsi scan: Sending REPORT LUNS to (try %d)\n",
-				retries));
-
-		result = scsi_execute_cmd(sdev, scsi_cmd, REQ_OP_DRV_IN,
-					  lun_data, length,
-					  SCSI_REPORT_LUNS_TIMEOUT, 3,
-					  &exec_args);
+	scsi_failures_reset_retries(&failures);
 
-		SCSI_LOG_SCAN_BUS(3, sdev_printk (KERN_INFO, sdev,
-				"scsi scan: REPORT LUNS"
-				" %s (try %d) result 0x%x\n",
-				result ?  "failed" : "successful",
-				retries, result));
-		if (result == 0)
-			break;
-		else if (scsi_sense_valid(&sshdr)) {
-			if (sshdr.sense_key != UNIT_ATTENTION)
-				break;
-		}
-	}
+	SCSI_LOG_SCAN_BUS(3, sdev_printk (KERN_INFO, sdev,
+			  "scsi scan: Sending REPORT LUNS\n"));
 
+	result = scsi_execute_cmd(sdev, scsi_cmd, REQ_OP_DRV_IN, lun_data,
+				  length, SCSI_REPORT_LUNS_TIMEOUT, 3,
+				  &exec_args);
+
+	SCSI_LOG_SCAN_BUS(3, sdev_printk (KERN_INFO, sdev,
+			  "scsi scan: REPORT LUNS  %s result 0x%x\n",
+			  result ?  "failed" : "successful", result));
 	if (result) {
 		/*
 		 * The device probably does not support a REPORT LUN command