Merge tag 'scsi-misc' of git://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsi

Pull more SCSI updates from James Bottomley:
 "The vfs has long had a write lifetime hint mechanism that gives the
  expected longevity on storage of the data being written. f2fs was the
  original consumer of this and used the hint for flash data placement
  (mostly to avoid write amplification by placing objects with similar
  lifetimes in the same erase block).

  More recently the SCSI based UFS (Universal Flash Storage) drivers
  have wanted to take advantage of this as well, for the same reasons as
  f2fs, necessitating plumbing the write hints through the block layer
  and then adding it to the SCSI core.

  The vfs write_hints already taken plumbs this as far as block and this
  completes the SCSI core enabling based on a recently agreed reuse of
  the old write command group number. The additions to the scsi_debug
  driver are for emulating this property so we can run tests on it in
  the absence of an actual UFS device"

* tag 'scsi-misc' of git://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsi:
  scsi: scsi_debug: Maintain write statistics per group number
  scsi: scsi_debug: Implement GET STREAM STATUS
  scsi: scsi_debug: Implement the IO Advice Hints Grouping mode page
  scsi: scsi_debug: Allocate the MODE SENSE response from the heap
  scsi: scsi_debug: Rework subpage code error handling
  scsi: scsi_debug: Rework page code error handling
  scsi: scsi_debug: Support the block limits extension VPD page
  scsi: scsi_debug: Reduce code duplication
  scsi: sd: Translate data lifetime information
  scsi: scsi_proto: Add structures and constants related to I/O groups and streams
  scsi: core: Query the Block Limits Extension VPD page

1 files changed, 108 insertions, 3 deletions

diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index 2cc73c650ca6..ccff8f2e2e75 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -47,6 +47,7 @@
 #include <linux/blkpg.h>
 #include <linux/blk-pm.h>
 #include <linux/delay.h>
+#include <linux/rw_hint.h>
 #include <linux/major.h>
 #include <linux/mutex.h>
 #include <linux/string_helpers.h>
@@ -1080,12 +1081,38 @@ static blk_status_t sd_setup_flush_cmnd(struct scsi_cmnd *cmd)
 	return BLK_STS_OK;
 }
 
+/**
+ * sd_group_number() - Compute the GROUP NUMBER field
+ * @cmd: SCSI command for which to compute the value of the six-bit GROUP NUMBER
+ *	field.
+ *
+ * From SBC-5 r05 (https://www.t10.org/cgi-bin/ac.pl?t=f&f=sbc5r05.pdf):
+ * 0: no relative lifetime.
+ * 1: shortest relative lifetime.
+ * 2: second shortest relative lifetime.
+ * 3 - 0x3d: intermediate relative lifetimes.
+ * 0x3e: second longest relative lifetime.
+ * 0x3f: longest relative lifetime.
+ */
+static u8 sd_group_number(struct scsi_cmnd *cmd)
+{
+	const struct request *rq = scsi_cmd_to_rq(cmd);
+	struct scsi_disk *sdkp = scsi_disk(rq->q->disk);
+
+	if (!sdkp->rscs)
+		return 0;
+
+	return min3((u32)rq->write_hint, (u32)sdkp->permanent_stream_count,
+		    0x3fu);
+}
+
 static blk_status_t sd_setup_rw32_cmnd(struct scsi_cmnd *cmd, bool write,
 				       sector_t lba, unsigned int nr_blocks,
 				       unsigned char flags, unsigned int dld)
 {
 	cmd->cmd_len = SD_EXT_CDB_SIZE;
 	cmd->cmnd[0]  = VARIABLE_LENGTH_CMD;
+	cmd->cmnd[6]  = sd_group_number(cmd);
 	cmd->cmnd[7]  = 0x18; /* Additional CDB len */
 	cmd->cmnd[9]  = write ? WRITE_32 : READ_32;
 	cmd->cmnd[10] = flags;
@@ -1104,7 +1131,7 @@ static blk_status_t sd_setup_rw16_cmnd(struct scsi_cmnd *cmd, bool write,
 	cmd->cmd_len  = 16;
 	cmd->cmnd[0]  = write ? WRITE_16 : READ_16;
 	cmd->cmnd[1]  = flags | ((dld >> 2) & 0x01);
-	cmd->cmnd[14] = (dld & 0x03) << 6;
+	cmd->cmnd[14] = ((dld & 0x03) << 6) | sd_group_number(cmd);
 	cmd->cmnd[15] = 0;
 	put_unaligned_be64(lba, &cmd->cmnd[2]);
 	put_unaligned_be32(nr_blocks, &cmd->cmnd[10]);
@@ -1119,7 +1146,7 @@ static blk_status_t sd_setup_rw10_cmnd(struct scsi_cmnd *cmd, bool write,
 	cmd->cmd_len = 10;
 	cmd->cmnd[0] = write ? WRITE_10 : READ_10;
 	cmd->cmnd[1] = flags;
-	cmd->cmnd[6] = 0;
+	cmd->cmnd[6] = sd_group_number(cmd);
 	cmd->cmnd[9] = 0;
 	put_unaligned_be32(lba, &cmd->cmnd[2]);
 	put_unaligned_be16(nr_blocks, &cmd->cmnd[7]);
@@ -1256,7 +1283,7 @@ static blk_status_t sd_setup_read_write_cmnd(struct scsi_cmnd *cmd)
 		ret = sd_setup_rw16_cmnd(cmd, write, lba, nr_blocks,
 					 protect | fua, dld);
 	} else if ((nr_blocks > 0xff) || (lba > 0x1fffff) ||
-		   sdp->use_10_for_rw || protect) {
+		   sdp->use_10_for_rw || protect || rq->write_hint) {
 		ret = sd_setup_rw10_cmnd(cmd, write, lba, nr_blocks,
 					 protect | fua);
 	} else {
@@ -3059,6 +3086,70 @@ defaults:
 	sdkp->DPOFUA = 0;
 }
 
+static bool sd_is_perm_stream(struct scsi_disk *sdkp, unsigned int stream_id)
+{
+	u8 cdb[16] = { SERVICE_ACTION_IN_16, SAI_GET_STREAM_STATUS };
+	struct {
+		struct scsi_stream_status_header h;
+		struct scsi_stream_status s;
+	} buf;
+	struct scsi_device *sdev = sdkp->device;
+	struct scsi_sense_hdr sshdr;
+	const struct scsi_exec_args exec_args = {
+		.sshdr = &sshdr,
+	};
+	int res;
+
+	put_unaligned_be16(stream_id, &cdb[4]);
+	put_unaligned_be32(sizeof(buf), &cdb[10]);
+
+	res = scsi_execute_cmd(sdev, cdb, REQ_OP_DRV_IN, &buf, sizeof(buf),
+			       SD_TIMEOUT, sdkp->max_retries, &exec_args);
+	if (res < 0)
+		return false;
+	if (scsi_status_is_check_condition(res) && scsi_sense_valid(&sshdr))
+		sd_print_sense_hdr(sdkp, &sshdr);
+	if (res)
+		return false;
+	if (get_unaligned_be32(&buf.h.len) < sizeof(struct scsi_stream_status))
+		return false;
+	return buf.h.stream_status[0].perm;
+}
+
+static void sd_read_io_hints(struct scsi_disk *sdkp, unsigned char *buffer)
+{
+	struct scsi_device *sdp = sdkp->device;
+	const struct scsi_io_group_descriptor *desc, *start, *end;
+	struct scsi_sense_hdr sshdr;
+	struct scsi_mode_data data;
+	int res;
+
+	res = scsi_mode_sense(sdp, /*dbd=*/0x8, /*modepage=*/0x0a,
+			      /*subpage=*/0x05, buffer, SD_BUF_SIZE, SD_TIMEOUT,
+			      sdkp->max_retries, &data, &sshdr);
+	if (res < 0)
+		return;
+	start = (void *)buffer + data.header_length + 16;
+	end = (void *)buffer + ALIGN_DOWN(data.header_length + data.length,
+					  sizeof(*end));
+	/*
+	 * From "SBC-5 Constrained Streams with Data Lifetimes": Device severs
+	 * should assign the lowest numbered stream identifiers to permanent
+	 * streams.
+	 */
+	for (desc = start; desc < end; desc++)
+		if (!desc->st_enble || !sd_is_perm_stream(sdkp, desc - start))
+			break;
+	sdkp->permanent_stream_count = desc - start;
+	if (sdkp->rscs && sdkp->permanent_stream_count < 2)
+		sd_printk(KERN_INFO, sdkp,
+			  "Unexpected: RSCS has been set and the permanent stream count is %u\n",
+			  sdkp->permanent_stream_count);
+	else if (sdkp->permanent_stream_count)
+		sd_printk(KERN_INFO, sdkp, "permanent stream count = %d\n",
+			  sdkp->permanent_stream_count);
+}
+
 /*
  * The ATO bit indicates whether the DIF application tag is available
  * for use by the operating system.
@@ -3166,6 +3257,18 @@ static void sd_read_block_limits(struct scsi_disk *sdkp)
 	rcu_read_unlock();
 }
 
+/* Parse the Block Limits Extension VPD page (0xb7) */
+static void sd_read_block_limits_ext(struct scsi_disk *sdkp)
+{
+	struct scsi_vpd *vpd;
+
+	rcu_read_lock();
+	vpd = rcu_dereference(sdkp->device->vpd_pgb7);
+	if (vpd && vpd->len >= 2)
+		sdkp->rscs = vpd->data[5] & 1;
+	rcu_read_unlock();
+}
+
 /**
  * sd_read_block_characteristics - Query block dev. characteristics
  * @sdkp: disk to query
@@ -3541,6 +3644,7 @@ static int sd_revalidate_disk(struct gendisk *disk)
 		if (scsi_device_supports_vpd(sdp)) {
 			sd_read_block_provisioning(sdkp);
 			sd_read_block_limits(sdkp);
+			sd_read_block_limits_ext(sdkp);
 			sd_read_block_characteristics(sdkp);
 			sd_zbc_read_zones(sdkp, buffer);
 			sd_read_cpr(sdkp);
@@ -3550,6 +3654,7 @@ static int sd_revalidate_disk(struct gendisk *disk)
 
 		sd_read_write_protect_flag(sdkp, buffer);
 		sd_read_cache_type(sdkp, buffer);
+		sd_read_io_hints(sdkp, buffer);
 		sd_read_app_tag_own(sdkp, buffer);
 		sd_read_write_same(sdkp, buffer);
 		sd_read_security(sdkp, buffer);