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, 138 insertions, 80 deletions

diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index d1b87670764c..a54cd1864a92 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -1645,36 +1645,35 @@ out:
 
 static int sd_sync_cache(struct scsi_disk *sdkp)
 {
-	int retries, res;
+	int res;
 	struct scsi_device *sdp = sdkp->device;
 	const int timeout = sdp->request_queue->rq_timeout
 		* SD_FLUSH_TIMEOUT_MULTIPLIER;
+	/* Leave the rest of the command zero to indicate flush everything. */
+	const unsigned char cmd[16] = { sdp->use_16_for_sync ?
+				SYNCHRONIZE_CACHE_16 : SYNCHRONIZE_CACHE };
 	struct scsi_sense_hdr sshdr;
+	struct scsi_failure failure_defs[] = {
+		{
+			.allowed = 3,
+			.result = SCMD_FAILURE_RESULT_ANY,
+		},
+		{}
+	};
+	struct scsi_failures failures = {
+		.failure_definitions = failure_defs,
+	};
 	const struct scsi_exec_args exec_args = {
 		.req_flags = BLK_MQ_REQ_PM,
 		.sshdr = &sshdr,
+		.failures = &failures,
 	};
 
 	if (!scsi_device_online(sdp))
 		return -ENODEV;
 
-	for (retries = 3; retries > 0; --retries) {
-		unsigned char cmd[16] = { 0 };
-
-		if (sdp->use_16_for_sync)
-			cmd[0] = SYNCHRONIZE_CACHE_16;
-		else
-			cmd[0] = SYNCHRONIZE_CACHE;
-		/*
-		 * Leave the rest of the command zero to indicate
-		 * flush everything.
-		 */
-		res = scsi_execute_cmd(sdp, cmd, REQ_OP_DRV_IN, NULL, 0,
-				       timeout, sdkp->max_retries, &exec_args);
-		if (res == 0)
-			break;
-	}
-
+	res = scsi_execute_cmd(sdp, cmd, REQ_OP_DRV_IN, NULL, 0, timeout,
+			       sdkp->max_retries, &exec_args);
 	if (res) {
 		sd_print_result(sdkp, "Synchronize Cache(10) failed", res);
 
@@ -1801,8 +1800,22 @@ static int sd_pr_in_command(struct block_device *bdev, u8 sa,
 	struct scsi_device *sdev = sdkp->device;
 	struct scsi_sense_hdr sshdr;
 	u8 cmd[10] = { PERSISTENT_RESERVE_IN, sa };
+	struct scsi_failure failure_defs[] = {
+		{
+			.sense = UNIT_ATTENTION,
+			.asc = SCMD_FAILURE_ASC_ANY,
+			.ascq = SCMD_FAILURE_ASCQ_ANY,
+			.allowed = 5,
+			.result = SAM_STAT_CHECK_CONDITION,
+		},
+		{}
+	};
+	struct scsi_failures failures = {
+		.failure_definitions = failure_defs,
+	};
 	const struct scsi_exec_args exec_args = {
 		.sshdr = &sshdr,
+		.failures = &failures,
 	};
 	int result;
 
@@ -1889,8 +1902,22 @@ static int sd_pr_out_command(struct block_device *bdev, u8 sa, u64 key,
 	struct scsi_disk *sdkp = scsi_disk(bdev->bd_disk);
 	struct scsi_device *sdev = sdkp->device;
 	struct scsi_sense_hdr sshdr;
+	struct scsi_failure failure_defs[] = {
+		{
+			.sense = UNIT_ATTENTION,
+			.asc = SCMD_FAILURE_ASC_ANY,
+			.ascq = SCMD_FAILURE_ASCQ_ANY,
+			.allowed = 5,
+			.result = SAM_STAT_CHECK_CONDITION,
+		},
+		{}
+	};
+	struct scsi_failures failures = {
+		.failure_definitions = failure_defs,
+	};
 	const struct scsi_exec_args exec_args = {
 		.sshdr = &sshdr,
+		.failures = &failures,
 	};
 	int result;
 	u8 cmd[16] = { 0, };
@@ -2235,55 +2262,68 @@ 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;
+		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 (media_not_present(sdkp, &sshdr)) {
-					if (media_was_present)
-						sd_printk(KERN_NOTICE, sdkp,
-							  "Media removed, stopped polling\n");
-					return;
-				}
 
-				sense_valid = scsi_sense_valid(&sshdr);
+		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 (media_not_present(sdkp, &sshdr)) {
+				if (media_was_present)
+					sd_printk(KERN_NOTICE, sdkp,
+						  "Media removed, stopped polling\n");
+				return;
 			}
-			retries++;
-		} while (retries < 3 &&
-			 (!scsi_status_is_good(the_result) ||
-			  (scsi_status_is_check_condition(the_result) &&
-			  sense_valid && sshdr.sense_key == UNIT_ATTENTION)));
+			sense_valid = scsi_sense_valid(&sshdr);
+		}
 
 		if (!scsi_status_is_check_condition(the_result)) {
 			/* no sense, TUR either succeeded or failed
@@ -2318,14 +2358,16 @@ sd_spinup_disk(struct scsi_disk *sdkp)
 			 * Issue command to spin up drive when not ready
 			 */
 			if (!spintime) {
+				/* Return immediately and start spin cycle */
+				const u8 start_cmd[10] = {
+					[0] = START_STOP,
+					[1] = 1,
+					[4] = sdkp->device->start_stop_pwr_cond ?
+						0x11 : 1,
+				};
+
 				sd_printk(KERN_NOTICE, sdkp, "Spinning up disk...");
-				cmd[0] = START_STOP;
-				cmd[1] = 1;	/* Return immediately */
-				memset((void *) &cmd[2], 0, 8);
-				cmd[4] = 1;	/* Start spin cycle */
-				if (sdkp->device->start_stop_pwr_cond)
-					cmd[4] |= 1 << 4;
-				scsi_execute_cmd(sdkp->device, cmd,
+				scsi_execute_cmd(sdkp->device, start_cmd,
 						 REQ_OP_DRV_IN, NULL, 0,
 						 SD_TIMEOUT, sdkp->max_retries,
 						 &exec_args);
@@ -2546,42 +2588,58 @@ static int read_capacity_16(struct scsi_disk *sdkp, struct scsi_device *sdp,
 static int read_capacity_10(struct scsi_disk *sdkp, struct scsi_device *sdp,
 						unsigned char *buffer)
 {
-	unsigned char cmd[16];
+	static const u8 cmd[10] = { READ_CAPACITY };
 	struct scsi_sense_hdr sshdr;
+	struct scsi_failure failure_defs[] = {
+		/* Do not retry Medium Not Present */
+		{
+			.sense = UNIT_ATTENTION,
+			.asc = 0x3A,
+			.result = SAM_STAT_CHECK_CONDITION,
+		},
+		{
+			.sense = NOT_READY,
+			.asc = 0x3A,
+			.result = SAM_STAT_CHECK_CONDITION,
+		},
+		 /* Device reset might occur several times so retry a lot */
+		{
+			.sense = UNIT_ATTENTION,
+			.asc = 0x29,
+			.allowed = READ_CAPACITY_RETRIES_ON_RESET,
+			.result = SAM_STAT_CHECK_CONDITION,
+		},
+		/* Any other error not listed above retry 3 times */
+		{
+			.result = SCMD_FAILURE_RESULT_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;
 	int the_result;
-	int retries = 3, reset_retries = READ_CAPACITY_RETRIES_ON_RESET;
 	sector_t lba;
 	unsigned sector_size;
 
-	do {
-		cmd[0] = READ_CAPACITY;
-		memset(&cmd[1], 0, 9);
-		memset(buffer, 0, 8);
+	memset(buffer, 0, 8);
+
+	the_result = scsi_execute_cmd(sdp, cmd, REQ_OP_DRV_IN, buffer,
+				      8, SD_TIMEOUT, sdkp->max_retries,
+				      &exec_args);
 
-		the_result = scsi_execute_cmd(sdp, cmd, REQ_OP_DRV_IN, buffer,
-					      8, SD_TIMEOUT, sdkp->max_retries,
-					      &exec_args);
+	if (the_result > 0) {
+		sense_valid = scsi_sense_valid(&sshdr);
 
 		if (media_not_present(sdkp, &sshdr))
 			return -ENODEV;
-
-		if (the_result > 0) {
-			sense_valid = scsi_sense_valid(&sshdr);
-			if (sense_valid &&
-			    sshdr.sense_key == UNIT_ATTENTION &&
-			    sshdr.asc == 0x29 && sshdr.ascq == 0x00)
-				/* Device reset might occur several times,
-				 * give it one more chance */
-				if (--reset_retries > 0)
-					continue;
-		}
-		retries--;
-
-	} while (the_result && retries);
+	}
 
 	if (the_result) {
 		sd_print_result(sdkp, "Read Capacity(10) failed", the_result);