diff mbox series

[v2,22/35] scsi: Have scsi-ml retry read_capacity_16 errors

Message ID 20220929025407.119804-23-michael.christie@oracle.com (mailing list archive)
State Superseded
Headers show
Series Allow scsi_execute users to control retries | expand

Commit Message

Mike Christie Sept. 29, 2022, 2:53 a.m. UTC 
This has read_capacity_16 have scsi-ml retry errors instead of driving
them itself.

Signed-off-by: Mike Christie <michael.christie@oracle.com>
---
 drivers/scsi/sd.c | 82 +++++++++++++++++++++++++----------------------
 1 file changed, 43 insertions(+), 39 deletions(-)

Comments

Martin Wilck Sept. 29, 2022, 2:12 p.m. UTC | #1 
On Wed, 2022-09-28 at 21:53 -0500, Mike Christie wrote:
> This has read_capacity_16 have scsi-ml retry errors instead of
> driving
> them itself.
> 
> Signed-off-by: Mike Christie <michael.christie@oracle.com>
> ---
>  drivers/scsi/sd.c | 82 +++++++++++++++++++++++++--------------------
> --
>  1 file changed, 43 insertions(+), 39 deletions(-)
> 
> diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
> index 37eafa968116..a35c089c3097 100644
> --- a/drivers/scsi/sd.c
> +++ b/drivers/scsi/sd.c
> @@ -2283,55 +2283,59 @@ static int read_capacity_16(struct scsi_disk
> *sdkp, struct scsi_device *sdp,
>         struct scsi_sense_hdr sshdr;
>         int sense_valid = 0;
>         int the_result;
> -       int retries = 3, reset_retries =
> READ_CAPACITY_RETRIES_ON_RESET;
>         unsigned int alignment;
>         unsigned long long lba;
>         unsigned sector_size;
> +       struct scsi_failure failures[] = {
> +               {
> +                       .sense = UNIT_ATTENTION,
> +                       .asc = 0x29,
> +                       .ascq = 0,
> +                       /* Device reset might occur several times */
> +                       .allowed = READ_CAPACITY_RETRIES_ON_RESET,
> +                       .result = SAM_STAT_CHECK_CONDITION,
> +               },
> +               {
> +                       .result = SCMD_FAILURE_ANY,
> +                       .allowed = 3,
> +               },
> +               {},
> +       };

I first wondered whether this was correct, until I realized that
the logic in patch 02/35 actually treats the counts for different
failures independently, so that the maximum overall retry count is
the sum of the individual retry counts.

I wonder if we should give callers the chance to set a limit for the
overall retry count in addition to the retry counts for individual 
failures.

Martin
diff mbox series

Patch

diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index 37eafa968116..a35c089c3097 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -2283,55 +2283,59 @@  static int read_capacity_16(struct scsi_disk *sdkp, struct scsi_device *sdp,
 	struct scsi_sense_hdr sshdr;
 	int sense_valid = 0;
 	int the_result;
-	int retries = 3, reset_retries = READ_CAPACITY_RETRIES_ON_RESET;
 	unsigned int alignment;
 	unsigned long long lba;
 	unsigned sector_size;
+	struct scsi_failure failures[] = {
+		{
+			.sense = UNIT_ATTENTION,
+			.asc = 0x29,
+			.ascq = 0,
+			/* Device reset might occur several times */
+			.allowed = READ_CAPACITY_RETRIES_ON_RESET,
+			.result = SAM_STAT_CHECK_CONDITION,
+		},
+		{
+			.result = SCMD_FAILURE_ANY,
+			.allowed = 3,
+		},
+		{},
+	};
 
 	if (sdp->no_read_capacity_16)
 		return -EINVAL;
 
-	do {
-		memset(cmd, 0, 16);
-		cmd[0] = SERVICE_ACTION_IN_16;
-		cmd[1] = SAI_READ_CAPACITY_16;
-		cmd[13] = RC16_LEN;
-		memset(buffer, 0, RC16_LEN);
+	memset(cmd, 0, 16);
+	cmd[0] = SERVICE_ACTION_IN_16;
+	cmd[1] = SAI_READ_CAPACITY_16;
+	cmd[13] = RC16_LEN;
+	memset(buffer, 0, RC16_LEN);
 
-		the_result = scsi_exec_req(((struct scsi_exec_args) {
-						.sdev = sdp,
-						.cmd = cmd,
-						.data_dir = DMA_FROM_DEVICE,
-						.buf = buffer,
-						.buf_len = RC16_LEN,
-						.sshdr = &sshdr,
-						.timeout = SD_TIMEOUT,
-						.retries = sdkp->max_retries }));
-
-		if (media_not_present(sdkp, &sshdr))
-			return -ENODEV;
+	the_result = scsi_exec_req(((struct scsi_exec_args) {
+					.sdev = sdp,
+					.cmd = cmd,
+					.data_dir = DMA_FROM_DEVICE,
+					.buf = buffer,
+					.buf_len = RC16_LEN,
+					.sshdr = &sshdr,
+					.timeout = SD_TIMEOUT,
+					.retries = sdkp->max_retries,
+					.failures = failures }));
 
-		if (the_result > 0) {
-			sense_valid = scsi_sense_valid(&sshdr);
-			if (sense_valid &&
-			    sshdr.sense_key == ILLEGAL_REQUEST &&
-			    (sshdr.asc == 0x20 || sshdr.asc == 0x24) &&
-			    sshdr.ascq == 0x00)
-				/* Invalid Command Operation Code or
-				 * Invalid Field in CDB, just retry
-				 * silently with RC10 */
-				return -EINVAL;
-			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--;
+	if (media_not_present(sdkp, &sshdr))
+		return -ENODEV;
 
-	} while (the_result && retries);
+	if (the_result > 0) {
+		sense_valid = scsi_sense_valid(&sshdr);
+		if (sense_valid && sshdr.sense_key == ILLEGAL_REQUEST &&
+		    (sshdr.asc == 0x20 || sshdr.asc == 0x24) &&
+		     sshdr.ascq == 0x00)
+			/*
+			 * Invalid Command Operation Code or Invalid Field in
+			 * CDB, just retry silently with RC10
+			 */
+			return -EINVAL;
+	}
 
 	if (the_result) {
 		sd_print_result(sdkp, "Read Capacity(16) failed", the_result);