scsi: sd: Have midlayer retry read_capacity_10() errors

This has read_capacity_10() have the SCSI midlayer retry errors instead of
driving them itself.

There are 2 behavior changes with this patch:

 1. 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 since 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.

 2. For the specific UAs we checked for and retried, we would get
    READ_CAPACITY_RETRIES_ON_RESET retries plus whatever retries were left
    from the main loop's retries. Each UA now gets
    READ_CAPACITY_RETRIES_ON_RESET retries, and the other errors get up to
    3 retries. This is most likely ok, because
    READ_CAPACITY_RETRIES_ON_RESET is already 10 and is not based on
    anything specific like a spec or device, so the extra 3 we got from the
    main loop was probably just an accident and is not going to help.

Signed-off-by: Mike Christie <michael.christie@oracle.com>
Link: https://lore.kernel.org/r/20240123002220.129141-16-michael.christie@oracle.com
Acked-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>

1 files changed, 39 insertions, 23 deletions

diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index 4196f722c3f6..49159dcd638d 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -2588,42 +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);