Merge tag 'for-5.16/scsi-ma-2021-10-29' of git://git.kernel.dk/linux-block

Pull SCSI multi-actuator support from Jens Axboe:
 "This adds SCSI support for the recently merged block multi-actuator
  support. Since this was sitting on top of the block tree, the SCSI
  side asked me to queue it up."

* tag 'for-5.16/scsi-ma-2021-10-29' of git://git.kernel.dk/linux-block:
  doc: Fix typo in request queue sysfs documentation
  doc: document sysfs queue/independent_access_ranges attributes
  libata: support concurrent positioning ranges log
  scsi: sd: add concurrent positioning ranges support

Documentation/block/queue-sysfs.rst

@@ -4,7 +4,7 @@ Queue sysfs files
 
 This text file will detail the queue files that are located in the sysfs tree
 for each block device. Note that stacked devices typically do not export
-any settings, since their queue merely functions are a remapping target.
+any settings, since their queue merely functions as a remapping target.
 These files are the ones found in the /sys/block/xxx/queue/ directory.
 
 Files denoted with a RO postfix are readonly and the RW postfix means
@@ -286,4 +286,35 @@ sequential zones of zoned block devices (devices with a zoned attributed
 that reports "host-managed" or "host-aware"). This value is always 0 for
 regular block devices.
 
+independent_access_ranges (RO)
+------------------------------
+
+The presence of this sub-directory of the /sys/block/xxx/queue/ directory
+indicates that the device is capable of executing requests targeting
+different sector ranges in parallel. For instance, single LUN multi-actuator
+hard-disks will have an independent_access_ranges directory if the device
+correctly advertizes the sector ranges of its actuators.
+
+The independent_access_ranges directory contains one directory per access
+range, with each range described using the sector (RO) attribute file to
+indicate the first sector of the range and the nr_sectors (RO) attribute file
+to indicate the total number of sectors in the range starting from the first
+sector of the range.  For example, a dual-actuator hard-disk will have the
+following independent_access_ranges entries.::
+
+        $ tree /sys/block/<device>/queue/independent_access_ranges/
+        /sys/block/<device>/queue/independent_access_ranges/
+        |-- 0
+        |   |-- nr_sectors
+        |   `-- sector
+        `-- 1
+            |-- nr_sectors
+            `-- sector
+
+The sector and nr_sectors attributes use 512B sector unit, regardless of
+the actual block size of the device. Independent access ranges do not
+overlap and include all sectors within the device capacity. The access
+ranges are numbered in increasing order of the range start sector,
+that is, the sector attribute of range 0 always has the value 0.
+
 Jens Axboe <jens.axboe@oracle.com>, February 2009

drivers/ata/libata-core.c

@@ -2459,18 +2459,70 @@ static void ata_dev_config_devslp(struct ata_device *dev)
 	}
 }
 
+static void ata_dev_config_cpr(struct ata_device *dev)
+{
+	unsigned int err_mask;
+	size_t buf_len;
+	int i, nr_cpr = 0;
+	struct ata_cpr_log *cpr_log = NULL;
+	u8 *desc, *buf = NULL;
+
+	if (!ata_identify_page_supported(dev,
+				 ATA_LOG_CONCURRENT_POSITIONING_RANGES))
+		goto out;
+
+	/*
+	 * Read IDENTIFY DEVICE data log, page 0x47
+	 * (concurrent positioning ranges). We can have at most 255 32B range
+	 * descriptors plus a 64B header.
+	 */
+	buf_len = (64 + 255 * 32 + 511) & ~511;
+	buf = kzalloc(buf_len, GFP_KERNEL);
+	if (!buf)
+		goto out;
+
+	err_mask = ata_read_log_page(dev, ATA_LOG_IDENTIFY_DEVICE,
+				     ATA_LOG_CONCURRENT_POSITIONING_RANGES,
+				     buf, buf_len >> 9);
+	if (err_mask)
+		goto out;
+
+	nr_cpr = buf[0];
+	if (!nr_cpr)
+		goto out;
+
+	cpr_log = kzalloc(struct_size(cpr_log, cpr, nr_cpr), GFP_KERNEL);
+	if (!cpr_log)
+		goto out;
+
+	cpr_log->nr_cpr = nr_cpr;
+	desc = &buf[64];
+	for (i = 0; i < nr_cpr; i++, desc += 32) {
+		cpr_log->cpr[i].num = desc[0];
+		cpr_log->cpr[i].num_storage_elements = desc[1];
+		cpr_log->cpr[i].start_lba = get_unaligned_le64(&desc[8]);
+		cpr_log->cpr[i].num_lbas = get_unaligned_le64(&desc[16]);
+	}
+
+out:
+	swap(dev->cpr_log, cpr_log);
+	kfree(cpr_log);
+	kfree(buf);
+}
+
 static void ata_dev_print_features(struct ata_device *dev)
 {
 	if (!(dev->flags & ATA_DFLAG_FEATURES_MASK))
 		return;
 
 	ata_dev_info(dev,
-		     "Features:%s%s%s%s%s\n",
+		     "Features:%s%s%s%s%s%s\n",
 		     dev->flags & ATA_DFLAG_TRUSTED ? " Trust" : "",
 		     dev->flags & ATA_DFLAG_DA ? " Dev-Attention" : "",
 		     dev->flags & ATA_DFLAG_DEVSLP ? " Dev-Sleep" : "",
 		     dev->flags & ATA_DFLAG_NCQ_SEND_RECV ? " NCQ-sndrcv" : "",
-		     dev->flags & ATA_DFLAG_NCQ_PRIO ? " NCQ-prio" : "");
+		     dev->flags & ATA_DFLAG_NCQ_PRIO ? " NCQ-prio" : "",
+		     dev->cpr_log ? " CPR" : "");
 }
 
 /**
@@ -2634,6 +2686,7 @@ int ata_dev_configure(struct ata_device *dev)
 		ata_dev_config_sense_reporting(dev);
 		ata_dev_config_zac(dev);
 		ata_dev_config_trusted(dev);
+		ata_dev_config_cpr(dev);
 		dev->cdb_len = 32;
 
 		if (ata_msg_drv(ap) && print_info)

drivers/ata/libata-scsi.c

@@ -1895,7 +1895,7 @@ static unsigned int ata_scsiop_inq_std(struct ata_scsi_args *args, u8 *rbuf)
  */
 static unsigned int ata_scsiop_inq_00(struct ata_scsi_args *args, u8 *rbuf)
 {
-	int num_pages;
+	int i, num_pages = 0;
 	static const u8 pages[] = {
 		0x00,	/* page 0x00, this page */
 		0x80,	/* page 0x80, unit serial no page */
@@ -1905,13 +1905,17 @@ static unsigned int ata_scsiop_inq_00(struct ata_scsi_args *args, u8 *rbuf)
 		0xb1,	/* page 0xb1, block device characteristics page */
 		0xb2,	/* page 0xb2, thin provisioning page */
 		0xb6,	/* page 0xb6, zoned block device characteristics */
+		0xb9,	/* page 0xb9, concurrent positioning ranges */
 	};
 
-	num_pages = sizeof(pages);
-	if (!(args->dev->flags & ATA_DFLAG_ZAC))
-		num_pages--;
+	for (i = 0; i < sizeof(pages); i++) {
+		if (pages[i] == 0xb6 &&
+		    !(args->dev->flags & ATA_DFLAG_ZAC))
+			continue;
+		rbuf[num_pages + 4] = pages[i];
+		num_pages++;
+	}
 	rbuf[3] = num_pages;	/* number of supported VPD pages */
-	memcpy(rbuf + 4, pages, num_pages);
 	return 0;
 }
 
@@ -2121,6 +2125,26 @@ static unsigned int ata_scsiop_inq_b6(struct ata_scsi_args *args, u8 *rbuf)
 	return 0;
 }
 
+static unsigned int ata_scsiop_inq_b9(struct ata_scsi_args *args, u8 *rbuf)
+{
+	struct ata_cpr_log *cpr_log = args->dev->cpr_log;
+	u8 *desc = &rbuf[64];
+	int i;
+
+	/* SCSI Concurrent Positioning Ranges VPD page: SBC-5 rev 1 or later */
+	rbuf[1] = 0xb9;
+	put_unaligned_be16(64 + (int)cpr_log->nr_cpr * 32 - 4, &rbuf[3]);
+
+	for (i = 0; i < cpr_log->nr_cpr; i++, desc += 32) {
+		desc[0] = cpr_log->cpr[i].num;
+		desc[1] = cpr_log->cpr[i].num_storage_elements;
+		put_unaligned_be64(cpr_log->cpr[i].start_lba, &desc[8]);
+		put_unaligned_be64(cpr_log->cpr[i].num_lbas, &desc[16]);
+	}
+
+	return 0;
+}
+
 /**
  *	modecpy - Prepare response for MODE SENSE
  *	@dest: output buffer
@@ -4120,11 +4144,17 @@ void ata_scsi_simulate(struct ata_device *dev, struct scsi_cmnd *cmd)
 			ata_scsi_rbuf_fill(&args, ata_scsiop_inq_b2);
 			break;
 		case 0xb6:
-			if (dev->flags & ATA_DFLAG_ZAC) {
+			if (dev->flags & ATA_DFLAG_ZAC)
 				ata_scsi_rbuf_fill(&args, ata_scsiop_inq_b6);
+			else
+				ata_scsi_set_invalid_field(dev, cmd, 2, 0xff);
+			break;
+		case 0xb9:
+			if (dev->cpr_log)
+				ata_scsi_rbuf_fill(&args, ata_scsiop_inq_b9);
+			else
+				ata_scsi_set_invalid_field(dev, cmd, 2, 0xff);
 			break;
-			}
-			fallthrough;
 		default:
 			ata_scsi_set_invalid_field(dev, cmd, 2, 0xff);
 			break;

drivers/scsi/sd.c

@@ -3088,6 +3088,86 @@ static void sd_read_security(struct scsi_disk *sdkp, unsigned char *buffer)
 		sdkp->security = 1;
 }
 
+static inline sector_t sd64_to_sectors(struct scsi_disk *sdkp, u8 *buf)
+{
+	return logical_to_sectors(sdkp->device, get_unaligned_be64(buf));
+}
+
+/**
+ * sd_read_cpr - Query concurrent positioning ranges
+ * @sdkp:	disk to query
+ */
+static void sd_read_cpr(struct scsi_disk *sdkp)
+{
+	struct blk_independent_access_ranges *iars = NULL;
+	unsigned char *buffer = NULL;
+	unsigned int nr_cpr = 0;
+	int i, vpd_len, buf_len = SD_BUF_SIZE;
+	u8 *desc;
+
+	/*
+	 * We need to have the capacity set first for the block layer to be
+	 * able to check the ranges.
+	 */
+	if (sdkp->first_scan)
+		return;
+
+	if (!sdkp->capacity)
+		goto out;
+
+	/*
+	 * Concurrent Positioning Ranges VPD: there can be at most 256 ranges,
+	 * leading to a maximum page size of 64 + 256*32 bytes.
+	 */
+	buf_len = 64 + 256*32;
+	buffer = kmalloc(buf_len, GFP_KERNEL);
+	if (!buffer || scsi_get_vpd_page(sdkp->device, 0xb9, buffer, buf_len))
+		goto out;
+
+	/* We must have at least a 64B header and one 32B range descriptor */
+	vpd_len = get_unaligned_be16(&buffer[2]) + 3;
+	if (vpd_len > buf_len || vpd_len < 64 + 32 || (vpd_len & 31)) {
+		sd_printk(KERN_ERR, sdkp,
+			  "Invalid Concurrent Positioning Ranges VPD page\n");
+		goto out;
+	}
+
+	nr_cpr = (vpd_len - 64) / 32;
+	if (nr_cpr == 1) {
+		nr_cpr = 0;
+		goto out;
+	}
+
+	iars = disk_alloc_independent_access_ranges(sdkp->disk, nr_cpr);
+	if (!iars) {
+		nr_cpr = 0;
+		goto out;
+	}
+
+	desc = &buffer[64];
+	for (i = 0; i < nr_cpr; i++, desc += 32) {
+		if (desc[0] != i) {
+			sd_printk(KERN_ERR, sdkp,
+				"Invalid Concurrent Positioning Range number\n");
+			nr_cpr = 0;
+			break;
+		}
+
+		iars->ia_range[i].sector = sd64_to_sectors(sdkp, desc + 8);
+		iars->ia_range[i].nr_sectors = sd64_to_sectors(sdkp, desc + 16);
+	}
+
+out:
+	disk_set_independent_access_ranges(sdkp->disk, iars);
+	if (nr_cpr && sdkp->nr_actuators != nr_cpr) {
+		sd_printk(KERN_NOTICE, sdkp,
+			  "%u concurrent positioning ranges\n", nr_cpr);
+		sdkp->nr_actuators = nr_cpr;
+	}
+
+	kfree(buffer);
+}
+
 /*
  * Determine the device's preferred I/O size for reads and writes
  * unless the reported value is unreasonably small, large, not a
@@ -3203,6 +3283,7 @@ static int sd_revalidate_disk(struct gendisk *disk)
 		sd_read_app_tag_own(sdkp, buffer);
 		sd_read_write_same(sdkp, buffer);
 		sd_read_security(sdkp, buffer);
+		sd_read_cpr(sdkp);
 	}
 
 	/*

drivers/scsi/sd.h

@@ -106,6 +106,7 @@ struct scsi_disk {
 	u8		protection_type;/* Data Integrity Field */
 	u8		provisioning_mode;
 	u8		zeroing_mode;
+	u8		nr_actuators;		/* Number of actuators */
 	unsigned	ATO : 1;	/* state of disk ATO bit */
 	unsigned	cache_override : 1; /* temp override of WCE,RCD */
 	unsigned	WCE : 1;	/* state of disk WCE bit */

include/linux/ata.h

@@ -329,6 +329,7 @@ enum {
 	ATA_LOG_SECURITY	  = 0x06,
 	ATA_LOG_SATA_SETTINGS	  = 0x08,
 	ATA_LOG_ZONED_INFORMATION = 0x09,
+	ATA_LOG_CONCURRENT_POSITIONING_RANGES = 0x47,
 
 	/* Identify device SATA settings log:*/
 	ATA_LOG_DEVSLP_OFFSET	  = 0x30,

include/linux/libata.h

@@ -676,6 +676,18 @@ struct ata_ering {
 	struct ata_ering_entry	ring[ATA_ERING_SIZE];
 };
 
+struct ata_cpr {
+	u8			num;
+	u8			num_storage_elements;
+	u64			start_lba;
+	u64			num_lbas;
+};
+
+struct ata_cpr_log {
+	u8			nr_cpr;
+	struct ata_cpr		cpr[];
+};
+
 struct ata_device {
 	struct ata_link		*link;
 	unsigned int		devno;		/* 0 or 1 */
@@ -735,6 +747,9 @@ struct ata_device {
 	u32			zac_zones_optimal_nonseq;
 	u32			zac_zones_max_open;
 
+	/* Concurrent positioning ranges */
+	struct ata_cpr_log	*cpr_log;
+
 	/* error history */
 	int			spdn_cnt;
 	/* ering is CLEAR_END, read comment above CLEAR_END */