Commit e6bd9312 authored by Martin K. Petersen's avatar Martin K. Petersen Committed by Jens Axboe

scsi: sd: Separate zeroout and discard command choices

Now that zeroout and discards are distinct operations we need to
separate the policy of choosing the appropriate command. Create a
zeroing_mode which can be one of:

write:			Zeroout assist not present, use regular WRITE
writesame:		Allow WRITE SAME(10/16) with a zeroed payload
writesame_16_unmap:	Allow WRITE SAME(16) with UNMAP
writesame_10_unmap:	Allow WRITE SAME(10) with UNMAP

The last two are conditional on the device being thin provisioned with
LBPRZ=1 and LBPWS=1 or LBPWS10=1 respectively.

Whether to set the UNMAP bit or not depends on the REQ_NOUNMAP flag. And
if none of the _unmap variants are supported, regular WRITE SAME will be
used if the device supports it.

The zeroout_mode is exported in sysfs and the detected mode for a given
device can be overridden using the string constants above.

With this change in place we can now issue WRITE SAME(16) with UNMAP set
for block zeroing applications that require hard guarantees and
logical_block_size granularity. And at the same time use the UNMAP
command with the device's preferred granulary and alignment for discard
operations.
Signed-off-by: default avatarMartin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: default avatarChristoph Hellwig <hch@lst.de>
Reviewed-by: default avatarHannes Reinecke <hare@suse.com>
Signed-off-by: default avatarJens Axboe <axboe@fb.com>
parent 48920ff2
...@@ -418,6 +418,46 @@ provisioning_mode_store(struct device *dev, struct device_attribute *attr, ...@@ -418,6 +418,46 @@ provisioning_mode_store(struct device *dev, struct device_attribute *attr,
} }
static DEVICE_ATTR_RW(provisioning_mode); static DEVICE_ATTR_RW(provisioning_mode);
static const char *zeroing_mode[] = {
[SD_ZERO_WRITE] = "write",
[SD_ZERO_WS] = "writesame",
[SD_ZERO_WS16_UNMAP] = "writesame_16_unmap",
[SD_ZERO_WS10_UNMAP] = "writesame_10_unmap",
};
static ssize_t
zeroing_mode_show(struct device *dev, struct device_attribute *attr,
char *buf)
{
struct scsi_disk *sdkp = to_scsi_disk(dev);
return snprintf(buf, 20, "%s\n", zeroing_mode[sdkp->zeroing_mode]);
}
static ssize_t
zeroing_mode_store(struct device *dev, struct device_attribute *attr,
const char *buf, size_t count)
{
struct scsi_disk *sdkp = to_scsi_disk(dev);
if (!capable(CAP_SYS_ADMIN))
return -EACCES;
if (!strncmp(buf, zeroing_mode[SD_ZERO_WRITE], 20))
sdkp->zeroing_mode = SD_ZERO_WRITE;
else if (!strncmp(buf, zeroing_mode[SD_ZERO_WS], 20))
sdkp->zeroing_mode = SD_ZERO_WS;
else if (!strncmp(buf, zeroing_mode[SD_ZERO_WS16_UNMAP], 20))
sdkp->zeroing_mode = SD_ZERO_WS16_UNMAP;
else if (!strncmp(buf, zeroing_mode[SD_ZERO_WS10_UNMAP], 20))
sdkp->zeroing_mode = SD_ZERO_WS10_UNMAP;
else
return -EINVAL;
return count;
}
static DEVICE_ATTR_RW(zeroing_mode);
static ssize_t static ssize_t
max_medium_access_timeouts_show(struct device *dev, max_medium_access_timeouts_show(struct device *dev,
struct device_attribute *attr, char *buf) struct device_attribute *attr, char *buf)
...@@ -496,6 +536,7 @@ static struct attribute *sd_disk_attrs[] = { ...@@ -496,6 +536,7 @@ static struct attribute *sd_disk_attrs[] = {
&dev_attr_app_tag_own.attr, &dev_attr_app_tag_own.attr,
&dev_attr_thin_provisioning.attr, &dev_attr_thin_provisioning.attr,
&dev_attr_provisioning_mode.attr, &dev_attr_provisioning_mode.attr,
&dev_attr_zeroing_mode.attr,
&dev_attr_max_write_same_blocks.attr, &dev_attr_max_write_same_blocks.attr,
&dev_attr_max_medium_access_timeouts.attr, &dev_attr_max_medium_access_timeouts.attr,
NULL, NULL,
...@@ -799,10 +840,10 @@ static int sd_setup_write_zeroes_cmnd(struct scsi_cmnd *cmd) ...@@ -799,10 +840,10 @@ static int sd_setup_write_zeroes_cmnd(struct scsi_cmnd *cmd)
u32 nr_sectors = blk_rq_sectors(rq) >> (ilog2(sdp->sector_size) - 9); u32 nr_sectors = blk_rq_sectors(rq) >> (ilog2(sdp->sector_size) - 9);
if (!(rq->cmd_flags & REQ_NOUNMAP)) { if (!(rq->cmd_flags & REQ_NOUNMAP)) {
switch (sdkp->provisioning_mode) { switch (sdkp->zeroing_mode) {
case SD_LBP_WS16: case SD_ZERO_WS16_UNMAP:
return sd_setup_write_same16_cmnd(cmd, true); return sd_setup_write_same16_cmnd(cmd, true);
case SD_LBP_WS10: case SD_ZERO_WS10_UNMAP:
return sd_setup_write_same10_cmnd(cmd, true); return sd_setup_write_same10_cmnd(cmd, true);
} }
} }
...@@ -840,6 +881,15 @@ static void sd_config_write_same(struct scsi_disk *sdkp) ...@@ -840,6 +881,15 @@ static void sd_config_write_same(struct scsi_disk *sdkp)
sdkp->max_ws_blocks = 0; sdkp->max_ws_blocks = 0;
} }
if (sdkp->lbprz && sdkp->lbpws)
sdkp->zeroing_mode = SD_ZERO_WS16_UNMAP;
else if (sdkp->lbprz && sdkp->lbpws10)
sdkp->zeroing_mode = SD_ZERO_WS10_UNMAP;
else if (sdkp->max_ws_blocks)
sdkp->zeroing_mode = SD_ZERO_WS;
else
sdkp->zeroing_mode = SD_ZERO_WRITE;
out: out:
blk_queue_max_write_same_sectors(q, sdkp->max_ws_blocks * blk_queue_max_write_same_sectors(q, sdkp->max_ws_blocks *
(logical_block_size >> 9)); (logical_block_size >> 9));
......
...@@ -59,6 +59,13 @@ enum { ...@@ -59,6 +59,13 @@ enum {
SD_LBP_DISABLE, /* Discard disabled due to failed cmd */ SD_LBP_DISABLE, /* Discard disabled due to failed cmd */
}; };
enum {
SD_ZERO_WRITE = 0, /* Use WRITE(10/16) command */
SD_ZERO_WS, /* Use WRITE SAME(10/16) command */
SD_ZERO_WS16_UNMAP, /* Use WRITE SAME(16) with UNMAP */
SD_ZERO_WS10_UNMAP, /* Use WRITE SAME(10) with UNMAP */
};
struct scsi_disk { struct scsi_disk {
struct scsi_driver *driver; /* always &sd_template */ struct scsi_driver *driver; /* always &sd_template */
struct scsi_device *device; struct scsi_device *device;
...@@ -89,6 +96,7 @@ struct scsi_disk { ...@@ -89,6 +96,7 @@ struct scsi_disk {
u8 write_prot; u8 write_prot;
u8 protection_type;/* Data Integrity Field */ u8 protection_type;/* Data Integrity Field */
u8 provisioning_mode; u8 provisioning_mode;
u8 zeroing_mode;
unsigned ATO : 1; /* state of disk ATO bit */ unsigned ATO : 1; /* state of disk ATO bit */
unsigned cache_override : 1; /* temp override of WCE,RCD */ unsigned cache_override : 1; /* temp override of WCE,RCD */
unsigned WCE : 1; /* state of disk WCE bit */ unsigned WCE : 1; /* state of disk WCE bit */
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment