1 files changed, 365 insertions, 37 deletions

diff --git a/drivers/scsi/sd_zbc.c b/drivers/scsi/sd_zbc.c
index f45c22b09726..6f7eba66687e 100644
--- a/drivers/scsi/sd_zbc.c
+++ b/drivers/scsi/sd_zbc.c
@@ -11,6 +11,7 @@
 #include <linux/blkdev.h>
 #include <linux/vmalloc.h>
 #include <linux/sched/mm.h>
+#include <linux/mutex.h>
 
 #include <asm/unaligned.h>
 
@@ -19,11 +20,36 @@
 
 #include "sd.h"
 
+static unsigned int sd_zbc_get_zone_wp_offset(struct blk_zone *zone)
+{
+	if (zone->type == ZBC_ZONE_TYPE_CONV)
+		return 0;
+
+	switch (zone->cond) {
+	case BLK_ZONE_COND_IMP_OPEN:
+	case BLK_ZONE_COND_EXP_OPEN:
+	case BLK_ZONE_COND_CLOSED:
+		return zone->wp - zone->start;
+	case BLK_ZONE_COND_FULL:
+		return zone->len;
+	case BLK_ZONE_COND_EMPTY:
+	case BLK_ZONE_COND_OFFLINE:
+	case BLK_ZONE_COND_READONLY:
+	default:
+		/*
+		 * Offline and read-only zones do not have a valid
+		 * write pointer. Use 0 as for an empty zone.
+		 */
+		return 0;
+	}
+}
+
 static int sd_zbc_parse_report(struct scsi_disk *sdkp, u8 *buf,
 			       unsigned int idx, report_zones_cb cb, void *data)
 {
 	struct scsi_device *sdp = sdkp->device;
 	struct blk_zone zone = { 0 };
+	int ret;
 
 	zone.type = buf[0] & 0x0f;
 	zone.cond = (buf[1] >> 4) & 0xf;
@@ -39,7 +65,14 @@ static int sd_zbc_parse_report(struct scsi_disk *sdkp, u8 *buf,
 	    zone.cond == ZBC_ZONE_COND_FULL)
 		zone.wp = zone.start + zone.len;
 
-	return cb(&zone, idx, data);
+	ret = cb(&zone, idx, data);
+	if (ret)
+		return ret;
+
+	if (sdkp->rev_wp_offset)
+		sdkp->rev_wp_offset[idx] = sd_zbc_get_zone_wp_offset(&zone);
+
+	return 0;
 }
 
 /**
@@ -136,8 +169,7 @@ static void *sd_zbc_alloc_report_buffer(struct scsi_disk *sdkp,
 
 	while (bufsize >= SECTOR_SIZE) {
 		buf = __vmalloc(bufsize,
-				GFP_KERNEL | __GFP_ZERO | __GFP_NORETRY,
-				PAGE_KERNEL);
+				GFP_KERNEL | __GFP_ZERO | __GFP_NORETRY);
 		if (buf) {
 			*buflen = bufsize;
 			return buf;
@@ -209,6 +241,136 @@ out:
 	return ret;
 }
 
+static blk_status_t sd_zbc_cmnd_checks(struct scsi_cmnd *cmd)
+{
+	struct request *rq = cmd->request;
+	struct scsi_disk *sdkp = scsi_disk(rq->rq_disk);
+	sector_t sector = blk_rq_pos(rq);
+
+	if (!sd_is_zoned(sdkp))
+		/* Not a zoned device */
+		return BLK_STS_IOERR;
+
+	if (sdkp->device->changed)
+		return BLK_STS_IOERR;
+
+	if (sector & (sd_zbc_zone_sectors(sdkp) - 1))
+		/* Unaligned request */
+		return BLK_STS_IOERR;
+
+	return BLK_STS_OK;
+}
+
+#define SD_ZBC_INVALID_WP_OFST	(~0u)
+#define SD_ZBC_UPDATING_WP_OFST	(SD_ZBC_INVALID_WP_OFST - 1)
+
+static int sd_zbc_update_wp_offset_cb(struct blk_zone *zone, unsigned int idx,
+				    void *data)
+{
+	struct scsi_disk *sdkp = data;
+
+	lockdep_assert_held(&sdkp->zones_wp_offset_lock);
+
+	sdkp->zones_wp_offset[idx] = sd_zbc_get_zone_wp_offset(zone);
+
+	return 0;
+}
+
+static void sd_zbc_update_wp_offset_workfn(struct work_struct *work)
+{
+	struct scsi_disk *sdkp;
+	unsigned int zno;
+	int ret;
+
+	sdkp = container_of(work, struct scsi_disk, zone_wp_offset_work);
+
+	spin_lock_bh(&sdkp->zones_wp_offset_lock);
+	for (zno = 0; zno < sdkp->nr_zones; zno++) {
+		if (sdkp->zones_wp_offset[zno] != SD_ZBC_UPDATING_WP_OFST)
+			continue;
+
+		spin_unlock_bh(&sdkp->zones_wp_offset_lock);
+		ret = sd_zbc_do_report_zones(sdkp, sdkp->zone_wp_update_buf,
+					     SD_BUF_SIZE,
+					     zno * sdkp->zone_blocks, true);
+		spin_lock_bh(&sdkp->zones_wp_offset_lock);
+		if (!ret)
+			sd_zbc_parse_report(sdkp, sdkp->zone_wp_update_buf + 64,
+					    zno, sd_zbc_update_wp_offset_cb,
+					    sdkp);
+	}
+	spin_unlock_bh(&sdkp->zones_wp_offset_lock);
+
+	scsi_device_put(sdkp->device);
+}
+
+/**
+ * sd_zbc_prepare_zone_append() - Prepare an emulated ZONE_APPEND command.
+ * @cmd: the command to setup
+ * @lba: the LBA to patch
+ * @nr_blocks: the number of LBAs to be written
+ *
+ * Called from sd_setup_read_write_cmnd() for REQ_OP_ZONE_APPEND.
+ * @sd_zbc_prepare_zone_append() handles the necessary zone wrote locking and
+ * patching of the lba for an emulated ZONE_APPEND command.
+ *
+ * In case the cached write pointer offset is %SD_ZBC_INVALID_WP_OFST it will
+ * schedule a REPORT ZONES command and return BLK_STS_IOERR.
+ */
+blk_status_t sd_zbc_prepare_zone_append(struct scsi_cmnd *cmd, sector_t *lba,
+					unsigned int nr_blocks)
+{
+	struct request *rq = cmd->request;
+	struct scsi_disk *sdkp = scsi_disk(rq->rq_disk);
+	unsigned int wp_offset, zno = blk_rq_zone_no(rq);
+	blk_status_t ret;
+
+	ret = sd_zbc_cmnd_checks(cmd);
+	if (ret != BLK_STS_OK)
+		return ret;
+
+	if (!blk_rq_zone_is_seq(rq))
+		return BLK_STS_IOERR;
+
+	/* Unlock of the write lock will happen in sd_zbc_complete() */
+	if (!blk_req_zone_write_trylock(rq))
+		return BLK_STS_ZONE_RESOURCE;
+
+	spin_lock_bh(&sdkp->zones_wp_offset_lock);
+	wp_offset = sdkp->zones_wp_offset[zno];
+	switch (wp_offset) {
+	case SD_ZBC_INVALID_WP_OFST:
+		/*
+		 * We are about to schedule work to update a zone write pointer
+		 * offset, which will cause the zone append command to be
+		 * requeued. So make sure that the scsi device does not go away
+		 * while the work is being processed.
+		 */
+		if (scsi_device_get(sdkp->device)) {
+			ret = BLK_STS_IOERR;
+			break;
+		}
+		sdkp->zones_wp_offset[zno] = SD_ZBC_UPDATING_WP_OFST;
+		schedule_work(&sdkp->zone_wp_offset_work);
+		fallthrough;
+	case SD_ZBC_UPDATING_WP_OFST:
+		ret = BLK_STS_DEV_RESOURCE;
+		break;
+	default:
+		wp_offset = sectors_to_logical(sdkp->device, wp_offset);
+		if (wp_offset + nr_blocks > sdkp->zone_blocks) {
+			ret = BLK_STS_IOERR;
+			break;
+		}
+
+		*lba += wp_offset;
+	}
+	spin_unlock_bh(&sdkp->zones_wp_offset_lock);
+	if (ret)
+		blk_req_zone_write_unlock(rq);
+	return ret;
+}
+
 /**
  * sd_zbc_setup_zone_mgmt_cmnd - Prepare a zone ZBC_OUT command. The operations
  *			can be RESET WRITE POINTER, OPEN, CLOSE or FINISH.
@@ -223,20 +385,14 @@ blk_status_t sd_zbc_setup_zone_mgmt_cmnd(struct scsi_cmnd *cmd,
 					 unsigned char op, bool all)
 {
 	struct request *rq = cmd->request;
-	struct scsi_disk *sdkp = scsi_disk(rq->rq_disk);
 	sector_t sector = blk_rq_pos(rq);
+	struct scsi_disk *sdkp = scsi_disk(rq->rq_disk);
 	sector_t block = sectors_to_logical(sdkp->device, sector);
+	blk_status_t ret;
 
-	if (!sd_is_zoned(sdkp))
-		/* Not a zoned device */
-		return BLK_STS_IOERR;
-
-	if (sdkp->device->changed)
-		return BLK_STS_IOERR;
-
-	if (sector & (sd_zbc_zone_sectors(sdkp) - 1))
-		/* Unaligned request */
-		return BLK_STS_IOERR;
+	ret = sd_zbc_cmnd_checks(cmd);
+	if (ret != BLK_STS_OK)
+		return ret;
 
 	cmd->cmd_len = 16;
 	memset(cmd->cmnd, 0, cmd->cmd_len);
@@ -255,16 +411,105 @@ blk_status_t sd_zbc_setup_zone_mgmt_cmnd(struct scsi_cmnd *cmd,
 	return BLK_STS_OK;
 }
 
+static bool sd_zbc_need_zone_wp_update(struct request *rq)
+{
+	switch (req_op(rq)) {
+	case REQ_OP_ZONE_APPEND:
+	case REQ_OP_ZONE_FINISH:
+	case REQ_OP_ZONE_RESET:
+	case REQ_OP_ZONE_RESET_ALL:
+		return true;
+	case REQ_OP_WRITE:
+	case REQ_OP_WRITE_ZEROES:
+	case REQ_OP_WRITE_SAME:
+		return blk_rq_zone_is_seq(rq);
+	default:
+		return false;
+	}
+}
+
+/**
+ * sd_zbc_zone_wp_update - Update cached zone write pointer upon cmd completion
+ * @cmd: Completed command
+ * @good_bytes: Command reply bytes
+ *
+ * Called from sd_zbc_complete() to handle the update of the cached zone write
+ * pointer value in case an update is needed.
+ */
+static unsigned int sd_zbc_zone_wp_update(struct scsi_cmnd *cmd,
+					  unsigned int good_bytes)
+{
+	int result = cmd->result;
+	struct request *rq = cmd->request;
+	struct scsi_disk *sdkp = scsi_disk(rq->rq_disk);
+	unsigned int zno = blk_rq_zone_no(rq);
+	enum req_opf op = req_op(rq);
+
+	/*
+	 * If we got an error for a command that needs updating the write
+	 * pointer offset cache, we must mark the zone wp offset entry as
+	 * invalid to force an update from disk the next time a zone append
+	 * command is issued.
+	 */
+	spin_lock_bh(&sdkp->zones_wp_offset_lock);
+
+	if (result && op != REQ_OP_ZONE_RESET_ALL) {
+		if (op == REQ_OP_ZONE_APPEND) {
+			/* Force complete completion (no retry) */
+			good_bytes = 0;
+			scsi_set_resid(cmd, blk_rq_bytes(rq));
+		}
+
+		/*
+		 * Force an update of the zone write pointer offset on
+		 * the next zone append access.
+		 */
+		if (sdkp->zones_wp_offset[zno] != SD_ZBC_UPDATING_WP_OFST)
+			sdkp->zones_wp_offset[zno] = SD_ZBC_INVALID_WP_OFST;
+		goto unlock_wp_offset;
+	}
+
+	switch (op) {
+	case REQ_OP_ZONE_APPEND:
+		rq->__sector += sdkp->zones_wp_offset[zno];
+		fallthrough;
+	case REQ_OP_WRITE_ZEROES:
+	case REQ_OP_WRITE_SAME:
+	case REQ_OP_WRITE:
+		if (sdkp->zones_wp_offset[zno] < sd_zbc_zone_sectors(sdkp))
+			sdkp->zones_wp_offset[zno] +=
+						good_bytes >> SECTOR_SHIFT;
+		break;
+	case REQ_OP_ZONE_RESET:
+		sdkp->zones_wp_offset[zno] = 0;
+		break;
+	case REQ_OP_ZONE_FINISH:
+		sdkp->zones_wp_offset[zno] = sd_zbc_zone_sectors(sdkp);
+		break;
+	case REQ_OP_ZONE_RESET_ALL:
+		memset(sdkp->zones_wp_offset, 0,
+		       sdkp->nr_zones * sizeof(unsigned int));
+		break;
+	default:
+		break;
+	}
+
+unlock_wp_offset:
+	spin_unlock_bh(&sdkp->zones_wp_offset_lock);
+
+	return good_bytes;
+}
+
 /**
  * sd_zbc_complete - ZBC command post processing.
  * @cmd: Completed command
  * @good_bytes: Command reply bytes
  * @sshdr: command sense header
  *
- * Called from sd_done(). Process report zones reply and handle reset zone
- * and write commands errors.
+ * Called from sd_done() to handle zone commands errors and updates to the
+ * device queue zone write pointer offset cahce.
  */
-void sd_zbc_complete(struct scsi_cmnd *cmd, unsigned int good_bytes,
+unsigned int sd_zbc_complete(struct scsi_cmnd *cmd, unsigned int good_bytes,
 		     struct scsi_sense_hdr *sshdr)
 {
 	int result = cmd->result;
@@ -280,7 +525,13 @@ void sd_zbc_complete(struct scsi_cmnd *cmd, unsigned int good_bytes,
 		 * so be quiet about the error.
 		 */
 		rq->rq_flags |= RQF_QUIET;
-	}
+	} else if (sd_zbc_need_zone_wp_update(rq))
+		good_bytes = sd_zbc_zone_wp_update(cmd, good_bytes);
+
+	if (req_op(rq) == REQ_OP_ZONE_APPEND)
+		blk_req_zone_write_unlock(rq);
+
+	return good_bytes;
 }
 
 /**
@@ -382,11 +633,67 @@ static int sd_zbc_check_capacity(struct scsi_disk *sdkp, unsigned char *buf,
 	return 0;
 }
 
+static void sd_zbc_revalidate_zones_cb(struct gendisk *disk)
+{
+	struct scsi_disk *sdkp = scsi_disk(disk);
+
+	swap(sdkp->zones_wp_offset, sdkp->rev_wp_offset);
+}
+
+static int sd_zbc_revalidate_zones(struct scsi_disk *sdkp,
+				   u32 zone_blocks,
+				   unsigned int nr_zones)
+{
+	struct gendisk *disk = sdkp->disk;
+	int ret = 0;
+
+	/*
+	 * Make sure revalidate zones are serialized to ensure exclusive
+	 * updates of the scsi disk data.
+	 */
+	mutex_lock(&sdkp->rev_mutex);
+
+	/*
+	 * Revalidate the disk zones to update the device request queue zone
+	 * bitmaps and the zone write pointer offset array. Do this only once
+	 * the device capacity is set on the second revalidate execution for
+	 * disk scan or if something changed when executing a normal revalidate.
+	 */
+	if (sdkp->first_scan) {
+		sdkp->zone_blocks = zone_blocks;
+		sdkp->nr_zones = nr_zones;
+		goto unlock;
+	}
+
+	if (sdkp->zone_blocks == zone_blocks &&
+	    sdkp->nr_zones == nr_zones &&
+	    disk->queue->nr_zones == nr_zones)
+		goto unlock;
+
+	sdkp->rev_wp_offset = kvcalloc(nr_zones, sizeof(u32), GFP_NOIO);
+	if (!sdkp->rev_wp_offset) {
+		ret = -ENOMEM;
+		goto unlock;
+	}
+
+	ret = blk_revalidate_disk_zones(disk, sd_zbc_revalidate_zones_cb);
+
+	kvfree(sdkp->rev_wp_offset);
+	sdkp->rev_wp_offset = NULL;
+
+unlock:
+	mutex_unlock(&sdkp->rev_mutex);
+
+	return ret;
+}
+
 int sd_zbc_read_zones(struct scsi_disk *sdkp, unsigned char *buf)
 {
 	struct gendisk *disk = sdkp->disk;
+	struct request_queue *q = disk->queue;
 	unsigned int nr_zones;
 	u32 zone_blocks = 0;
+	u32 max_append;
 	int ret;
 
 	if (!sd_is_zoned(sdkp))
@@ -407,35 +714,31 @@ int sd_zbc_read_zones(struct scsi_disk *sdkp, unsigned char *buf)
 		goto err;
 
 	/* The drive satisfies the kernel restrictions: set it up */
-	blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, sdkp->disk->queue);
-	blk_queue_required_elevator_features(sdkp->disk->queue,
-					     ELEVATOR_F_ZBD_SEQ_WRITE);
+	blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, q);
+	blk_queue_required_elevator_features(q, ELEVATOR_F_ZBD_SEQ_WRITE);
 	nr_zones = round_up(sdkp->capacity, zone_blocks) >> ilog2(zone_blocks);
 
 	/* READ16/WRITE16 is mandatory for ZBC disks */
 	sdkp->device->use_16_for_rw = 1;
 	sdkp->device->use_10_for_rw = 0;
 
+	ret = sd_zbc_revalidate_zones(sdkp, zone_blocks, nr_zones);
+	if (ret)
+		goto err;
+
 	/*
-	 * Revalidate the disk zone bitmaps once the block device capacity is
-	 * set on the second revalidate execution during disk scan and if
-	 * something changed when executing a normal revalidate.
+	 * On the first scan 'chunk_sectors' isn't setup yet, so calling
+	 * blk_queue_max_zone_append_sectors() will result in a WARN(). Defer
+	 * this setting to the second scan.
 	 */
-	if (sdkp->first_scan) {
-		sdkp->zone_blocks = zone_blocks;
-		sdkp->nr_zones = nr_zones;
+	if (sdkp->first_scan)
 		return 0;
-	}
 
-	if (sdkp->zone_blocks != zone_blocks ||
-	    sdkp->nr_zones != nr_zones ||
-	    disk->queue->nr_zones != nr_zones) {
-		ret = blk_revalidate_disk_zones(disk);
-		if (ret != 0)
-			goto err;
-		sdkp->zone_blocks = zone_blocks;
-		sdkp->nr_zones = nr_zones;
-	}
+	max_append = min_t(u32, logical_to_sectors(sdkp->device, zone_blocks),
+			   q->limits.max_segments << (PAGE_SHIFT - 9));
+	max_append = min_t(u32, max_append, queue_max_hw_sectors(q));
+
+	blk_queue_max_zone_append_sectors(q, max_append);
 
 	return 0;
 
@@ -461,3 +764,28 @@ void sd_zbc_print_zones(struct scsi_disk *sdkp)
 			  sdkp->nr_zones,
 			  sdkp->zone_blocks);
 }
+
+int sd_zbc_init_disk(struct scsi_disk *sdkp)
+{
+	if (!sd_is_zoned(sdkp))
+		return 0;
+
+	sdkp->zones_wp_offset = NULL;
+	spin_lock_init(&sdkp->zones_wp_offset_lock);
+	sdkp->rev_wp_offset = NULL;
+	mutex_init(&sdkp->rev_mutex);
+	INIT_WORK(&sdkp->zone_wp_offset_work, sd_zbc_update_wp_offset_workfn);
+	sdkp->zone_wp_update_buf = kzalloc(SD_BUF_SIZE, GFP_KERNEL);
+	if (!sdkp->zone_wp_update_buf)
+		return -ENOMEM;
+
+	return 0;
+}
+
+void sd_zbc_release_disk(struct scsi_disk *sdkp)
+{
+	kvfree(sdkp->zones_wp_offset);
+	sdkp->zones_wp_offset = NULL;
+	kfree(sdkp->zone_wp_update_buf);
+	sdkp->zone_wp_update_buf = NULL;
+}