[SCSI] Handle disk devices which can not process medium access commands

We have experienced several devices which fail in a fashion we do not
currently handle gracefully in SCSI. After a failure these devices will
respond to the SCSI primary command set (INQUIRY, TEST UNIT READY, etc.)
but any command accessing the storage medium will time out.

The following patch adds an callback that can be used by upper level
drivers to inspect the results of an error handling command. This in
turn has been used to implement additional checking in the SCSI disk
driver.

If a medium access command fails twice but TEST UNIT READY succeeds both
times in the subsequent error handling we will offline the device. The
maximum number of failed commands required to take a device offline can
be tweaked in sysfs.

Also add a new error flag to scsi_debug which allows this scenario to be
easily reproduced.

[jejb: fix up integer parsing to use kstrtouint]
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: James Bottomley <JBottomley@Parallels.com>

1 files changed, 35 insertions, 0 deletions

diff --git a/drivers/scsi/sd.h b/drivers/scsi/sd.h
index 4163f2910e3d..f703f4827b6f 100644
--- a/drivers/scsi/sd.h
+++ b/drivers/scsi/sd.h
@@ -20,6 +20,7 @@
  */
 #define SD_MAX_RETRIES          5
 #define SD_PASSTHROUGH_RETRIES  1
+#define SD_MAX_MEDIUM_TIMEOUTS  2
 
 /*
  * Size of the initial data buffer for mode and read capacity data
@@ -59,6 +60,8 @@ struct scsi_disk {
         u32             unmap_alignment;
         u32             index;
         unsigned int    physical_block_size;
+        unsigned int    max_medium_access_timeouts;
+        unsigned int    medium_access_timed_out;
         u8              media_present;
         u8              write_prot;
         u8              protection_type;/* Data Integrity Field */
@@ -88,6 +91,38 @@ static inline struct scsi_disk *scsi_disk(struct gendisk *disk)
                     (sdsk)->disk->disk_name, ##a) :                     \
         sdev_printk(prefix, (sdsk)->device, fmt, ##a)
 
+static inline int scsi_medium_access_command(struct scsi_cmnd *scmd)
+{
+        switch (scmd->cmnd[0]) {
+        case READ_6:
+        case READ_10:
+        case READ_12:
+        case READ_16:
+        case SYNCHRONIZE_CACHE:
+        case VERIFY:
+        case VERIFY_12:
+        case VERIFY_16:
+        case WRITE_6:
+        case WRITE_10:
+        case WRITE_12:
+        case WRITE_16:
+        case WRITE_SAME:
+        case WRITE_SAME_16:
+        case UNMAP:
+                return 1;
+        case VARIABLE_LENGTH_CMD:
+                switch (scmd->cmnd[9]) {
+                case READ_32:
+                case VERIFY_32:
+                case WRITE_32:
+                case WRITE_SAME_32:
+                        return 1;
+                }
+        }
+
+        return 0;
+}
+
 /*
  * A DIF-capable target device can be formatted with different
  * protection schemes.  Currently 0 through 3 are defined: