[SCSI] sd: Implement support for WRITE SAME

Implement support for WRITE SAME(10) and WRITE SAME(16) in the SCSI disk
driver.

 - We set the default maximum to 0xFFFF because there are several
   devices out there that only support two-byte block counts even with
   WRITE SAME(16). We only enable transfers bigger than 0xFFFF if the
   device explicitly reports MAXIMUM WRITE SAME LENGTH in the BLOCK
   LIMITS VPD.

 - max_write_same_blocks can be overriden per-device basis in sysfs.

 - The UNMAP discovery heuristics remain unchanged but the discard
   limits are tweaked to match the "real" WRITE SAME commands.

 - In the error handling logic we now distinguish between WRITE SAME
   with and without UNMAP set.

The discovery process heuristics are:

 - If the device reports a SCSI level of SPC-3 or greater we'll issue
   READ SUPPORTED OPERATION CODES to find out whether WRITE SAME(16) is
   supported. If that's the case we will use it.

 - If the device supports the block limits VPD and reports a MAXIMUM
   WRITE SAME LENGTH bigger than 0xFFFF we will use WRITE SAME(16).

 - Otherwise we will use WRITE SAME(10) unless the target LBA is beyond
   0xFFFFFFFF or the block count exceeds 0xFFFF.

 - no_write_same is set for ATA, FireWire and USB.

Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Mike Snitzer <snitzer@redhat.com>
Reviewed-by: Jeff Garzik <jgarzik@redhat.com>
Signed-off-by: James Bottomley <JBottomley@Parallels.com>

7 files changed, 191 insertions, 16 deletions

diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
index 7c2dead60518..a6df6a351d6e 100644
--- a/drivers/ata/libata-scsi.c
+++ b/drivers/ata/libata-scsi.c
@@ -1053,6 +1053,7 @@ static void ata_scsi_sdev_config(struct scsi_device *sdev)
         sdev->use_10_for_rw = 1;
         sdev->use_10_for_ms = 1;
         sdev->no_report_opcodes = 1;
+        sdev->no_write_same = 1;
 
         /* Schedule policy is determined by ->qc_defer() callback and
          * it needs to see every deferred qc.  Set dev_blocked to 1 to
diff --git a/drivers/firewire/sbp2.c b/drivers/firewire/sbp2.c
index f82e9d4295d0..bb1b392f5cda 100644
--- a/drivers/firewire/sbp2.c
+++ b/drivers/firewire/sbp2.c
@@ -1547,6 +1547,7 @@ static int sbp2_scsi_slave_configure(struct scsi_device *sdev)
 
         sdev->use_10_for_rw = 1;
         sdev->no_report_opcodes = 1;
+        sdev->no_write_same = 1;
 
         if (sbp2_param_exclusive_login)
                 sdev->manage_start_stop = 1;
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index da36a3a81a9e..9032e910bca3 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -900,11 +900,23 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes)
                                 action = ACTION_FAIL;
                                 error = -EILSEQ;
                         /* INVALID COMMAND OPCODE or INVALID FIELD IN CDB */
-                        } else if ((sshdr.asc == 0x20 || sshdr.asc == 0x24) &&
-                                   (cmd->cmnd[0] == UNMAP ||
-                                    cmd->cmnd[0] == WRITE_SAME_16 ||
-                                    cmd->cmnd[0] == WRITE_SAME)) {
-                                description = "Discard failure";
+                        } else if (sshdr.asc == 0x20 || sshdr.asc == 0x24) {
+                                switch (cmd->cmnd[0]) {
+                                case UNMAP:
+                                        description = "Discard failure";
+                                        break;
+                                case WRITE_SAME:
+                                case WRITE_SAME_16:
+                                        if (cmd->cmnd[1] & 0x8)
+                                                description = "Discard failure";
+                                        else
+                                                description =
+                                                        "Write same failure";
+                                        break;
+                                default:
+                                        description = "Invalid command failure";
+                                        break;
+                                }
                                 action = ACTION_FAIL;
                                 error = -EREMOTEIO;
                         } else
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index c6af4c1a9ca3..352bc77b7c88 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -99,6 +99,7 @@ MODULE_ALIAS_SCSI_DEVICE(TYPE_RBC);
 #endif
 
 static void sd_config_discard(struct scsi_disk *, unsigned int);
+static void sd_config_write_same(struct scsi_disk *);
 static int  sd_revalidate_disk(struct gendisk *);
 static void sd_unlock_native_capacity(struct gendisk *disk);
 static int  sd_probe(struct device *);
@@ -395,6 +396,45 @@ sd_store_max_medium_access_timeouts(struct device *dev,
         return err ? err : count;
 }
 
+static ssize_t
+sd_show_write_same_blocks(struct device *dev, struct device_attribute *attr,
+                          char *buf)
+{
+        struct scsi_disk *sdkp = to_scsi_disk(dev);
+
+        return snprintf(buf, 20, "%u\n", sdkp->max_ws_blocks);
+}
+
+static ssize_t
+sd_store_write_same_blocks(struct device *dev, struct device_attribute *attr,
+                           const char *buf, size_t count)
+{
+        struct scsi_disk *sdkp = to_scsi_disk(dev);
+        struct scsi_device *sdp = sdkp->device;
+        unsigned long max;
+        int err;
+
+        if (!capable(CAP_SYS_ADMIN))
+                return -EACCES;
+
+        if (sdp->type != TYPE_DISK)
+                return -EINVAL;
+
+        err = kstrtoul(buf, 10, &max);
+
+        if (err)
+                return err;
+
+        if (max == 0)
+                sdp->no_write_same = 1;
+        else if (max <= SD_MAX_WS16_BLOCKS)
+                sdkp->max_ws_blocks = max;
+
+        sd_config_write_same(sdkp);
+
+        return count;
+}
+
 static struct device_attribute sd_disk_attrs[] = {
         __ATTR(cache_type, S_IRUGO|S_IWUSR, sd_show_cache_type,
                sd_store_cache_type),
@@ -410,6 +450,8 @@ static struct device_attribute sd_disk_attrs[] = {
         __ATTR(thin_provisioning, S_IRUGO, sd_show_thin_provisioning, NULL),
         __ATTR(provisioning_mode, S_IRUGO|S_IWUSR, sd_show_provisioning_mode,
                sd_store_provisioning_mode),
+        __ATTR(max_write_same_blocks, S_IRUGO|S_IWUSR,
+               sd_show_write_same_blocks, sd_store_write_same_blocks),
         __ATTR(max_medium_access_timeouts, S_IRUGO|S_IWUSR,
                sd_show_max_medium_access_timeouts,
                sd_store_max_medium_access_timeouts),
@@ -561,19 +603,23 @@ static void sd_config_discard(struct scsi_disk *sdkp, unsigned int mode)
                 return;
 
         case SD_LBP_UNMAP:
-                max_blocks = min_not_zero(sdkp->max_unmap_blocks, 0xffffffff);
+                max_blocks = min_not_zero(sdkp->max_unmap_blocks,
+                                          (u32)SD_MAX_WS16_BLOCKS);
                 break;
 
         case SD_LBP_WS16:
-                max_blocks = min_not_zero(sdkp->max_ws_blocks, 0xffffffff);
+                max_blocks = min_not_zero(sdkp->max_ws_blocks,
+                                          (u32)SD_MAX_WS16_BLOCKS);
                 break;
 
         case SD_LBP_WS10:
-                max_blocks = min_not_zero(sdkp->max_ws_blocks, (u32)0xffff);
+                max_blocks = min_not_zero(sdkp->max_ws_blocks,
+                                          (u32)SD_MAX_WS10_BLOCKS);
                 break;
 
         case SD_LBP_ZERO:
-                max_blocks = min_not_zero(sdkp->max_ws_blocks, (u32)0xffff);
+                max_blocks = min_not_zero(sdkp->max_ws_blocks,
+                                          (u32)SD_MAX_WS10_BLOCKS);
                 q->limits.discard_zeroes_data = 1;
                 break;
         }
@@ -667,6 +713,83 @@ out:
         return ret;
 }
 
+static void sd_config_write_same(struct scsi_disk *sdkp)
+{
+        struct request_queue *q = sdkp->disk->queue;
+        unsigned int logical_block_size = sdkp->device->sector_size;
+        unsigned int blocks = 0;
+
+        if (sdkp->device->no_write_same) {
+                sdkp->max_ws_blocks = 0;
+                goto out;
+        }
+
+        /* Some devices can not handle block counts above 0xffff despite
+         * supporting WRITE SAME(16). Consequently we default to 64k
+         * blocks per I/O unless the device explicitly advertises a
+         * bigger limit.