Merge patch series "scsi: sshdr and retry fixes"

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

The following patches were made over Linus tree (Martin's 6.7 branch
was missing some changes to sd.c). They only contain the sshdr and
rdac retry fixes from the "Allow scsi_execute users to control
retries" patchset.

The patches in this set are reviewed and tested but the changes to how
we do retries will take a little longer and require more testing, so I
broke up the series to make them easier to review.

Link: https://lore.kernel.org/r/20231004210013.5601-1-michael.christie@oracle.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>

7 files changed, 82 insertions, 75 deletions

diff --git a/drivers/scsi/device_handler/scsi_dh_hp_sw.c b/drivers/scsi/device_handler/scsi_dh_hp_sw.c
index 5f2f943d926c..944ea4e0cc45 100644
--- a/drivers/scsi/device_handler/scsi_dh_hp_sw.c
+++ b/drivers/scsi/device_handler/scsi_dh_hp_sw.c
@@ -82,7 +82,7 @@ static int hp_sw_tur(struct scsi_device *sdev, struct hp_sw_dh_data *h)
 {
 	unsigned char cmd[6] = { TEST_UNIT_READY };
 	struct scsi_sense_hdr sshdr;
-	int ret = SCSI_DH_OK, res;
+	int ret, res;
 	blk_opf_t opf = REQ_OP_DRV_IN | REQ_FAILFAST_DEV |
 				REQ_FAILFAST_TRANSPORT | REQ_FAILFAST_DRIVER;
 	const struct scsi_exec_args exec_args = {
@@ -92,19 +92,18 @@ static int hp_sw_tur(struct scsi_device *sdev, struct hp_sw_dh_data *h)
 retry:
 	res = scsi_execute_cmd(sdev, cmd, opf, NULL, 0, HP_SW_TIMEOUT,
 			       HP_SW_RETRIES, &exec_args);
-	if (res) {
-		if (scsi_sense_valid(&sshdr))
-			ret = tur_done(sdev, h, &sshdr);
-		else {
-			sdev_printk(KERN_WARNING, sdev,
-				    "%s: sending tur failed with %x\n",
-				    HP_SW_NAME, res);
-			ret = SCSI_DH_IO;
-		}
-	} else {
+	if (res > 0 && scsi_sense_valid(&sshdr)) {
+		ret = tur_done(sdev, h, &sshdr);
+	} else if (res == 0) {
 		h->path_state = HP_SW_PATH_ACTIVE;
 		ret = SCSI_DH_OK;
+	} else {
+		sdev_printk(KERN_WARNING, sdev,
+			    "%s: sending tur failed with %x\n",
+			    HP_SW_NAME, res);
+		ret = SCSI_DH_IO;
 	}
+
 	if (ret == SCSI_DH_IMM_RETRY)
 		goto retry;
 
@@ -122,7 +121,7 @@ static int hp_sw_start_stop(struct hp_sw_dh_data *h)
 	unsigned char cmd[6] = { START_STOP, 0, 0, 0, 1, 0 };
 	struct scsi_sense_hdr sshdr;
 	struct scsi_device *sdev = h->sdev;
-	int res, rc = SCSI_DH_OK;
+	int res, rc;
 	int retry_cnt = HP_SW_RETRIES;
 	blk_opf_t opf = REQ_OP_DRV_IN | REQ_FAILFAST_DEV |
 				REQ_FAILFAST_TRANSPORT | REQ_FAILFAST_DRIVER;
@@ -133,35 +132,37 @@ static int hp_sw_start_stop(struct hp_sw_dh_data *h)
 retry:
 	res = scsi_execute_cmd(sdev, cmd, opf, NULL, 0, HP_SW_TIMEOUT,
 			       HP_SW_RETRIES, &exec_args);
-	if (res) {
-		if (!scsi_sense_valid(&sshdr)) {
-			sdev_printk(KERN_WARNING, sdev,
-				    "%s: sending start_stop_unit failed, "
-				    "no sense available\n", HP_SW_NAME);
-			return SCSI_DH_IO;
-		}
-		switch (sshdr.sense_key) {
-		case NOT_READY:
-			if (sshdr.asc == 0x04 && sshdr.ascq == 3) {
-				/*
-				 * LUN not ready - manual intervention required
-				 *
-				 * Switch-over in progress, retry.
-				 */
-				if (--retry_cnt)
-					goto retry;
-				rc = SCSI_DH_RETRY;
-				break;
-			}
-			fallthrough;
-		default:
-			sdev_printk(KERN_WARNING, sdev,
-				    "%s: sending start_stop_unit failed, "
-				    "sense %x/%x/%x\n", HP_SW_NAME,
-				    sshdr.sense_key, sshdr.asc, sshdr.ascq);
-			rc = SCSI_DH_IO;
+	if (!res) {
+		return SCSI_DH_OK;
+	} else if (res < 0 || !scsi_sense_valid(&sshdr)) {
+		sdev_printk(KERN_WARNING, sdev,
+			    "%s: sending start_stop_unit failed, "
+			    "no sense available\n", HP_SW_NAME);
+		return SCSI_DH_IO;
+	}
+
+	switch (sshdr.sense_key) {
+	case NOT_READY:
+		if (sshdr.asc == 0x04 && sshdr.ascq == 3) {
+			/*
+			 * LUN not ready - manual intervention required
+			 *
+			 * Switch-over in progress, retry.
+			 */
+			if (--retry_cnt)
+				goto retry;
+			rc = SCSI_DH_RETRY;
+			break;
 		}
+		fallthrough;
+	default:
+		sdev_printk(KERN_WARNING, sdev,
+			    "%s: sending start_stop_unit failed, "
+			    "sense %x/%x/%x\n", HP_SW_NAME,
+			    sshdr.sense_key, sshdr.asc, sshdr.ascq);
+		rc = SCSI_DH_IO;
 	}
+
 	return rc;
 }
 
diff --git a/drivers/scsi/device_handler/scsi_dh_rdac.c b/drivers/scsi/device_handler/scsi_dh_rdac.c
index c5538645057a..1ac2ae17e8be 100644
--- a/drivers/scsi/device_handler/scsi_dh_rdac.c
+++ b/drivers/scsi/device_handler/scsi_dh_rdac.c
@@ -530,7 +530,7 @@ static void send_mode_select(struct work_struct *work)
 		container_of(work, struct rdac_controller, ms_work);
 	struct scsi_device *sdev = ctlr->ms_sdev;
 	struct rdac_dh_data *h = sdev->handler_data;
-	int err = SCSI_DH_OK, retry_cnt = RDAC_RETRY_COUNT;
+	int rc, err, retry_cnt = RDAC_RETRY_COUNT;
 	struct rdac_queue_data *tmp, *qdata;
 	LIST_HEAD(list);
 	unsigned char cdb[MAX_COMMAND_SIZE];
@@ -558,20 +558,23 @@ static void send_mode_select(struct work_struct *work)
 		(char *) h->ctlr->array_name, h->ctlr->index,
 		(retry_cnt == RDAC_RETRY_COUNT) ? "queueing" : "retrying");
 
-	if (scsi_execute_cmd(sdev, cdb, opf, &h->ctlr->mode_select, data_size,
-			     RDAC_TIMEOUT * HZ, RDAC_RETRIES, &exec_args)) {
+	rc = scsi_execute_cmd(sdev, cdb, opf, &h->ctlr->mode_select, data_size,
+			      RDAC_TIMEOUT * HZ, RDAC_RETRIES, &exec_args);
+	if (!rc) {
+		h->state = RDAC_STATE_ACTIVE;
+		RDAC_LOG(RDAC_LOG_FAILOVER, sdev, "array %s, ctlr %d, "
+				"MODE_SELECT completed",
+				(char *) h->ctlr->array_name, h->ctlr->index);
+		err = SCSI_DH_OK;
+	} else if (rc < 0) {
+		err = SCSI_DH_IO;
+	} else {
 		err = mode_select_handle_sense(sdev, &sshdr);
 		if (err == SCSI_DH_RETRY && retry_cnt--)
 			goto retry;
 		if (err == SCSI_DH_IMM_RETRY)
 			goto retry;
 	}
-	if (err == SCSI_DH_OK) {
-		h->state = RDAC_STATE_ACTIVE;
-		RDAC_LOG(RDAC_LOG_FAILOVER, sdev, "array %s, ctlr %d, "
-				"MODE_SELECT completed",
-				(char *) h->ctlr->array_name, h->ctlr->index);
-	}
 
 	list_for_each_entry_safe(qdata, tmp, &list, entry) {
 		list_del(&qdata->entry);
diff --git a/drivers/scsi/scsi.c b/drivers/scsi/scsi.c
index d0911bc28663..d1c0ba3ef1f5 100644
--- a/drivers/scsi/scsi.c
+++ b/drivers/scsi/scsi.c
@@ -692,7 +692,7 @@ int scsi_cdl_enable(struct scsi_device *sdev, bool enable)
 		ret = scsi_mode_select(sdev, 1, 0, buf_data, len, 5 * HZ, 3,
 				       &data, &sshdr);
 		if (ret) {
-			if (scsi_sense_valid(&sshdr))
+			if (ret > 0 && scsi_sense_valid(&sshdr))
 				scsi_print_sense_hdr(sdev,
 					dev_name(&sdev->sdev_gendev), &sshdr);
 			return ret;
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index c2f647a7c1b0..195ca80667d0 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -2299,10 +2299,10 @@ scsi_test_unit_ready(struct scsi_device *sdev, int timeout, int retries,
 	do {
 		result = scsi_execute_cmd(sdev, cmd, REQ_OP_DRV_IN, NULL, 0,
 					  timeout, 1, &exec_args);
-		if (sdev->removable && scsi_sense_valid(sshdr) &&
+		if (sdev->removable && result > 0 && scsi_sense_valid(sshdr) &&
 		    sshdr->sense_key == UNIT_ATTENTION)
 			sdev->changed = 1;
-	} while (scsi_sense_valid(sshdr) &&
+	} while (result > 0 && scsi_sense_valid(sshdr) &&
 		 sshdr->sense_key == UNIT_ATTENTION && --retries);
 
 	return result;
diff --git a/drivers/scsi/scsi_transport_spi.c b/drivers/scsi/scsi_transport_spi.c
index 2442d4d2e3f3..f668c1c0a98f 100644
--- a/drivers/scsi/scsi_transport_spi.c
+++ b/drivers/scsi/scsi_transport_spi.c
@@ -676,10 +676,10 @@ spi_dv_device_echo_buffer(struct scsi_device *sdev, u8 *buffer,
 	for (r = 0; r < retries; r++) {
 		result = spi_execute(sdev, spi_write_buffer, REQ_OP_DRV_OUT,
 				     buffer, len, &sshdr);
-		if(result || !scsi_device_online(sdev)) {
+		if (result || !scsi_device_online(sdev)) {
 
 			scsi_device_set_state(sdev, SDEV_QUIESCE);
-			if (scsi_sense_valid(&sshdr)
+			if (result > 0 && scsi_sense_valid(&sshdr)
 			    && sshdr.sense_key == ILLEGAL_REQUEST
 			    /* INVALID FIELD IN CDB */
 			    && sshdr.asc == 0x24 && sshdr.ascq == 0x00)
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index c92a317ba547..ce091ffcf3de 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -143,7 +143,7 @@ cache_type_store(struct device *dev, struct device_attribute *attr,
 	struct scsi_mode_data data;
 	struct scsi_sense_hdr sshdr;
 	static const char temp[] = "temporary ";
-	int len;
+	int len, ret;
 
 	if (sdp->type != TYPE_DISK && sdp->type != TYPE_ZBC)
 		/* no cache control on RBC devices; theoretically they
@@ -190,9 +190,10 @@ cache_type_store(struct device *dev, struct device_attribute *attr,
 	 */
 	data.device_specific = 0;
 
-	if (scsi_mode_select(sdp, 1, sp, buffer_data, len, SD_TIMEOUT,
-			     sdkp->max_retries, &data, &sshdr)) {
-		if (scsi_sense_valid(&sshdr))
+	ret = scsi_mode_select(sdp, 1, sp, buffer_data, len, SD_TIMEOUT,
+			       sdkp->max_retries, &data, &sshdr);
+	if (ret) {
+		if (ret > 0 && scsi_sense_valid(&sshdr))
 			sd_print_sense_hdr(sdkp, &sshdr);
 		return -EINVAL;
 	}
@@ -2180,19 +2181,21 @@ sd_spinup_disk(struct scsi_disk *sdkp)
 						      sdkp->max_retries,
 						      &exec_args);
 
-			/*
-			 * 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;
-			}
+			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;
+				}
 
-			if (the_result)
 				sense_valid = scsi_sense_valid(&sshdr);
+			}
 			retries++;
 		} while (retries < 3 &&
 			 (!scsi_status_is_good(the_result) ||
@@ -2388,11 +2391,10 @@ static int read_capacity_16(struct scsi_disk *sdkp, struct scsi_device *sdp,
 		the_result = scsi_execute_cmd(sdp, cmd, REQ_OP_DRV_IN,
 					      buffer, RC16_LEN, SD_TIMEOUT,
 					      sdkp->max_retries, &exec_args);
-
-		if (media_not_present(sdkp, &sshdr))
-			return -ENODEV;
-
 		if (the_result > 0) {
+			if (media_not_present(sdkp, &sshdr))
+				return -ENODEV;
+
 			sense_valid = scsi_sense_valid(&sshdr);
 			if (sense_valid &&
 			    sshdr.sense_key == ILLEGAL_REQUEST &&
@@ -2889,7 +2891,7 @@ sd_read_cache_type(struct scsi_disk *sdkp, unsigned char *buffer)
 	}
 
 bad_sense:
-	if (scsi_sense_valid(&sshdr) &&
+	if (res == -EIO && scsi_sense_valid(&sshdr) &&
 	    sshdr.sense_key == ILLEGAL_REQUEST &&
 	    sshdr.asc == 0x24 && sshdr.ascq == 0x0)
 		/* Invalid field in CDB */
@@ -2937,7 +2939,7 @@ static void sd_read_app_tag_own(struct scsi_disk *sdkp, unsigned char *buffer)
 		sd_first_printk(KERN_WARNING, sdkp,
 			  "getting Control mode page failed, assume no ATO\n");
 
-		if (scsi_sense_valid(&sshdr))
+		if (res == -EIO && scsi_sense_valid(&sshdr))
 			sd_print_sense_hdr(sdkp, &sshdr);
 
 		return;
diff --git a/drivers/scsi/sr.c b/drivers/scsi/sr.c
index 07ef3db3d1a1..d093dd187b2f 100644
--- a/drivers/scsi/sr.c
+++ b/drivers/scsi/sr.c
@@ -177,7 +177,8 @@ static unsigned int sr_get_events(struct scsi_device *sdev)
 
 	result = scsi_execute_cmd(sdev, cmd, REQ_OP_DRV_IN, buf, sizeof(buf),
 				  SR_TIMEOUT, MAX_RETRIES, &exec_args);
-	if (scsi_sense_valid(&sshdr) && sshdr.sense_key == UNIT_ATTENTION)
+	if (result > 0 && scsi_sense_valid(&sshdr) &&
+	    sshdr.sense_key == UNIT_ATTENTION)
 		return DISK_EVENT_MEDIA_CHANGE;
 
 	if (result || be16_to_cpu(eh->data_len) < sizeof(*med))