5 files changed, 191 insertions, 145 deletions

diff --git a/drivers/scsi/scsi_debugfs.c b/drivers/scsi/scsi_debugfs.c
index c3765d29fd3f..b784002ef0bd 100644
--- a/drivers/scsi/scsi_debugfs.c
+++ b/drivers/scsi/scsi_debugfs.c
@@ -4,15 +4,49 @@
 #include <scsi/scsi_dbg.h>
 #include "scsi_debugfs.h"
 
+#define SCSI_CMD_FLAG_NAME(name) [ilog2(SCMD_##name)] = #name
+static const char *const scsi_cmd_flags[] = {
+	SCSI_CMD_FLAG_NAME(TAGGED),
+	SCSI_CMD_FLAG_NAME(UNCHECKED_ISA_DMA),
+	SCSI_CMD_FLAG_NAME(INITIALIZED),
+};
+#undef SCSI_CMD_FLAG_NAME
+
+static int scsi_flags_show(struct seq_file *m, const unsigned long flags,
+			   const char *const *flag_name, int flag_name_count)
+{
+	bool sep = false;
+	int i;
+
+	for (i = 0; i < sizeof(flags) * BITS_PER_BYTE; i++) {
+		if (!(flags & BIT(i)))
+			continue;
+		if (sep)
+			seq_puts(m, "|");
+		sep = true;
+		if (i < flag_name_count && flag_name[i])
+			seq_puts(m, flag_name[i]);
+		else
+			seq_printf(m, "%d", i);
+	}
+	return 0;
+}
+
 void scsi_show_rq(struct seq_file *m, struct request *rq)
 {
 	struct scsi_cmnd *cmd = container_of(scsi_req(rq), typeof(*cmd), req);
-	int msecs = jiffies_to_msecs(jiffies - cmd->jiffies_at_alloc);
+	int alloc_ms = jiffies_to_msecs(jiffies - cmd->jiffies_at_alloc);
+	int timeout_ms = jiffies_to_msecs(rq->timeout);
 	const u8 *const cdb = READ_ONCE(cmd->cmnd);
 	char buf[80] = "(?)";
 
 	if (cdb)
 		__scsi_format_command(buf, sizeof(buf), cdb, cmd->cmd_len);
-	seq_printf(m, ", .cmd=%s, .retries=%d, allocated %d.%03d s ago", buf,
-		   cmd->retries, msecs / 1000, msecs % 1000);
+	seq_printf(m, ", .cmd=%s, .retries=%d, .result = %#x, .flags=", buf,
+		   cmd->retries, cmd->result);
+	scsi_flags_show(m, cmd->flags, scsi_cmd_flags,
+			ARRAY_SIZE(scsi_cmd_flags));
+	seq_printf(m, ", .timeout=%d.%03d, allocated %d.%03d s ago",
+		   timeout_ms / 1000, timeout_ms % 1000,
+		   alloc_ms / 1000, alloc_ms % 1000);
 }
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 9bdf9200cacb..a86df9ca7d1c 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -79,14 +79,15 @@ int scsi_init_sense_cache(struct Scsi_Host *shost)
 	if (shost->unchecked_isa_dma) {
 		scsi_sense_isadma_cache =
 			kmem_cache_create("scsi_sense_cache(DMA)",
-			SCSI_SENSE_BUFFERSIZE, 0,
-			SLAB_HWCACHE_ALIGN | SLAB_CACHE_DMA, NULL);
+				SCSI_SENSE_BUFFERSIZE, 0,
+				SLAB_HWCACHE_ALIGN | SLAB_CACHE_DMA, NULL);
 		if (!scsi_sense_isadma_cache)
 			ret = -ENOMEM;
 	} else {
 		scsi_sense_cache =
-			kmem_cache_create("scsi_sense_cache",
-			SCSI_SENSE_BUFFERSIZE, 0, SLAB_HWCACHE_ALIGN, NULL);
+			kmem_cache_create_usercopy("scsi_sense_cache",
+				SCSI_SENSE_BUFFERSIZE, 0, SLAB_HWCACHE_ALIGN,
+				0, SCSI_SENSE_BUFFERSIZE, NULL);
 		if (!scsi_sense_cache)
 			ret = -ENOMEM;
 	}
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index ce756d575aff..bff21e636ddd 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -851,16 +851,13 @@ static int sd_setup_write_zeroes_cmnd(struct scsi_cmnd *cmd)
 	struct scsi_disk *sdkp = scsi_disk(rq->rq_disk);
 	u64 sector = blk_rq_pos(rq) >> (ilog2(sdp->sector_size) - 9);
 	u32 nr_sectors = blk_rq_sectors(rq) >> (ilog2(sdp->sector_size) - 9);
-	int ret;
 
 	if (!(rq->cmd_flags & REQ_NOUNMAP)) {
 		switch (sdkp->zeroing_mode) {
 		case SD_ZERO_WS16_UNMAP:
-			ret = sd_setup_write_same16_cmnd(cmd, true);
-			goto out;
+			return sd_setup_write_same16_cmnd(cmd, true);
 		case SD_ZERO_WS10_UNMAP:
-			ret = sd_setup_write_same10_cmnd(cmd, true);
-			goto out;
+			return sd_setup_write_same10_cmnd(cmd, true);
 		}
 	}
 
@@ -868,15 +865,9 @@ static int sd_setup_write_zeroes_cmnd(struct scsi_cmnd *cmd)
 		return BLKPREP_INVALID;
 
 	if (sdkp->ws16 || sector > 0xffffffff || nr_sectors > 0xffff)
-		ret = sd_setup_write_same16_cmnd(cmd, false);
-	else
-		ret = sd_setup_write_same10_cmnd(cmd, false);
-
-out:
-	if (sd_is_zoned(sdkp) && ret == BLKPREP_OK)
-		return sd_zbc_write_lock_zone(cmd);
+		return sd_setup_write_same16_cmnd(cmd, false);
 
-	return ret;
+	return sd_setup_write_same10_cmnd(cmd, false);
 }
 
 static void sd_config_write_same(struct scsi_disk *sdkp)
@@ -964,12 +955,6 @@ static int sd_setup_write_same_cmnd(struct scsi_cmnd *cmd)
 
 	BUG_ON(bio_offset(bio) || bio_iovec(bio).bv_len != sdp->sector_size);
 
-	if (sd_is_zoned(sdkp)) {
-		ret = sd_zbc_write_lock_zone(cmd);
-		if (ret != BLKPREP_OK)
-			return ret;
-	}
-
 	sector >>= ilog2(sdp->sector_size) - 9;
 	nr_sectors >>= ilog2(sdp->sector_size) - 9;
 
@@ -1004,9 +989,6 @@ static int sd_setup_write_same_cmnd(struct scsi_cmnd *cmd)
 	ret = scsi_init_io(cmd);
 	rq->__data_len = nr_bytes;
 
-	if (sd_is_zoned(sdkp) && ret != BLKPREP_OK)
-		sd_zbc_write_unlock_zone(cmd);
-
 	return ret;
 }
 
@@ -1036,19 +1018,12 @@ static int sd_setup_read_write_cmnd(struct scsi_cmnd *SCpnt)
 	sector_t threshold;
 	unsigned int this_count = blk_rq_sectors(rq);
 	unsigned int dif, dix;
-	bool zoned_write = sd_is_zoned(sdkp) && rq_data_dir(rq) == WRITE;
 	int ret;
 	unsigned char protect;
 
-	if (zoned_write) {
-		ret = sd_zbc_write_lock_zone(SCpnt);
-		if (ret != BLKPREP_OK)
-			return ret;
-	}
-
 	ret = scsi_init_io(SCpnt);
 	if (ret != BLKPREP_OK)
-		goto out;
+		return ret;
 	WARN_ON_ONCE(SCpnt != rq->special);
 
 	/* from here on until we're complete, any goto out
@@ -1267,9 +1242,6 @@ static int sd_setup_read_write_cmnd(struct scsi_cmnd *SCpnt)
 	 */
 	ret = BLKPREP_OK;
  out:
-	if (zoned_write && ret != BLKPREP_OK)
-		sd_zbc_write_unlock_zone(SCpnt);
-
 	return ret;
 }
 
@@ -1314,9 +1286,6 @@ static void sd_uninit_command(struct scsi_cmnd *SCpnt)
 	struct request *rq = SCpnt->request;
 	u8 *cmnd;
 
-	if (SCpnt->flags & SCMD_ZONE_WRITE_LOCK)
-		sd_zbc_write_unlock_zone(SCpnt);
-
 	if (rq->rq_flags & RQF_SPECIAL_PAYLOAD)
 		__free_page(rq->special_vec.bv_page);
 
diff --git a/drivers/scsi/sd.h b/drivers/scsi/sd.h
index 320de758323e..0d663b5e45bb 100644
--- a/drivers/scsi/sd.h
+++ b/drivers/scsi/sd.h
@@ -77,7 +77,6 @@ struct scsi_disk {
 	unsigned int	nr_zones;
 	unsigned int	zone_blocks;
 	unsigned int	zone_shift;
-	unsigned long	*zones_wlock;
 	unsigned int	zones_optimal_open;
 	unsigned int	zones_optimal_nonseq;
 	unsigned int	zones_max_open;
@@ -283,8 +282,6 @@ static inline int sd_is_zoned(struct scsi_disk *sdkp)
 extern int sd_zbc_read_zones(struct scsi_disk *sdkp, unsigned char *buffer);
 extern void sd_zbc_remove(struct scsi_disk *sdkp);
 extern void sd_zbc_print_zones(struct scsi_disk *sdkp);
-extern int sd_zbc_write_lock_zone(struct scsi_cmnd *cmd);
-extern void sd_zbc_write_unlock_zone(struct scsi_cmnd *cmd);
 extern int sd_zbc_setup_report_cmnd(struct scsi_cmnd *cmd);
 extern int sd_zbc_setup_reset_cmnd(struct scsi_cmnd *cmd);
 extern void sd_zbc_complete(struct scsi_cmnd *cmd, unsigned int good_bytes,
@@ -302,14 +299,6 @@ static inline void sd_zbc_remove(struct scsi_disk *sdkp) {}
 
 static inline void sd_zbc_print_zones(struct scsi_disk *sdkp) {}
 
-static inline int sd_zbc_write_lock_zone(struct scsi_cmnd *cmd)
-{
-	/* Let the drive fail requests */
-	return BLKPREP_OK;
-}
-
-static inline void sd_zbc_write_unlock_zone(struct scsi_cmnd *cmd) {}
-
 static inline int sd_zbc_setup_report_cmnd(struct scsi_cmnd *cmd)
 {
 	return BLKPREP_INVALID;
diff --git a/drivers/scsi/sd_zbc.c b/drivers/scsi/sd_zbc.c
index 27793b9f54c0..6c348a211ebb 100644
--- a/drivers/scsi/sd_zbc.c
+++ b/drivers/scsi/sd_zbc.c
@@ -230,17 +230,6 @@ static inline sector_t sd_zbc_zone_sectors(struct scsi_disk *sdkp)
 }
 
 /**
- * sd_zbc_zone_no - Get the number of the zone conataining a sector.
- * @sdkp: The target disk
- * @sector: 512B sector address contained in the zone
- */
-static inline unsigned int sd_zbc_zone_no(struct scsi_disk *sdkp,
-					  sector_t sector)
-{
-	return sectors_to_logical(sdkp->device, sector) >> sdkp->zone_shift;
-}
-
-/**
  * sd_zbc_setup_reset_cmnd - Prepare a RESET WRITE POINTER scsi command.
  * @cmd: the command to setup
  *
@@ -279,78 +268,6 @@ int sd_zbc_setup_reset_cmnd(struct scsi_cmnd *cmd)
 }
 
 /**
- * sd_zbc_write_lock_zone - Write lock a sequential zone.
- * @cmd: write command
- *
- * Called from sd_init_cmd() for write requests (standard write, write same or
- * write zeroes operations). If the request target zone is not already locked,
- * the zone is locked and BLKPREP_OK returned, allowing the request to proceed
- * through dispatch in scsi_request_fn(). Otherwise, BLKPREP_DEFER is returned,
- * forcing the request to wait for the zone to be unlocked, that is, for the
- * previously issued write request targeting the same zone to complete.
- *
- * This is called from blk_peek_request() context with the queue lock held and
- * before the request is removed from the scheduler. As a result, multiple
- * contexts executing concurrently scsi_request_fn() cannot result in write
- * sequence reordering as only a single write request per zone is allowed to
- * proceed.
- */
-int sd_zbc_write_lock_zone(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);
-	sector_t zone_sectors = sd_zbc_zone_sectors(sdkp);
-	unsigned int zno = sd_zbc_zone_no(sdkp, sector);
-
-	/*
-	 * Note: Checks of the alignment of the write command on
-	 * logical blocks is done in sd.c
-	 */
-
-	/* Do not allow zone boundaries crossing on host-managed drives */
-	if (blk_queue_zoned_model(sdkp->disk->queue) == BLK_ZONED_HM &&
-	    (sector & (zone_sectors - 1)) + blk_rq_sectors(rq) > zone_sectors)
-		return BLKPREP_KILL;
-
-	/*
-	 * Do not issue more than one write at a time per
-	 * zone. This solves write ordering problems due to
-	 * the unlocking of the request queue in the dispatch
-	 * path in the non scsi-mq case.
-	 */
-	if (sdkp->zones_wlock &&
-	    test_and_set_bit(zno, sdkp->zones_wlock))
-		return BLKPREP_DEFER;
-
-	WARN_ON_ONCE(cmd->flags & SCMD_ZONE_WRITE_LOCK);
-	cmd->flags |= SCMD_ZONE_WRITE_LOCK;
-
-	return BLKPREP_OK;
-}
-
-/**
- * sd_zbc_write_unlock_zone - Write unlock a sequential zone.
- * @cmd: write command
- *
- * Called from sd_uninit_cmd(). Unlocking the request target zone will allow
- * dispatching the next write request for the zone.
- */
-void sd_zbc_write_unlock_zone(struct scsi_cmnd *cmd)
-{
-	struct request *rq = cmd->request;
-	struct scsi_disk *sdkp = scsi_disk(rq->rq_disk);
-
-	if (sdkp->zones_wlock && cmd->flags & SCMD_ZONE_WRITE_LOCK) {
-		unsigned int zno = sd_zbc_zone_no(sdkp, blk_rq_pos(rq));
-		WARN_ON_ONCE(!test_bit(zno, sdkp->zones_wlock));
-		cmd->flags &= ~SCMD_ZONE_WRITE_LOCK;
-		clear_bit_unlock(zno, sdkp->zones_wlock);
-		smp_mb__after_atomic();
-	}
-}
-
-/**
  * sd_zbc_complete - ZBC command post processing.
  * @cmd: Completed command
  * @good_bytes: Command reply bytes
@@ -586,8 +503,123 @@ out:
 	return 0;
 }
 
+/**
+ * sd_zbc_alloc_zone_bitmap - Allocate a zone bitmap (one bit per zone).
+ * @sdkp: The disk of the bitmap
+ */
+static inline unsigned long *sd_zbc_alloc_zone_bitmap(struct scsi_disk *sdkp)
+{
+	struct request_queue *q = sdkp->disk->queue;
+
+	return kzalloc_node(BITS_TO_LONGS(sdkp->nr_zones)
+			    * sizeof(unsigned long),
+			    GFP_KERNEL, q->node);
+}
+
+/**
+ * sd_zbc_get_seq_zones - Parse report zones reply to identify sequential zones
+ * @sdkp: disk used
+ * @buf: report reply buffer
+ * @seq_zone_bitamp: bitmap of sequential zones to set
+ *
+ * Parse reported zone descriptors in @buf to identify sequential zones and
+ * set the reported zone bit in @seq_zones_bitmap accordingly.
+ * Since read-only and offline zones cannot be written, do not
+ * mark them as sequential in the bitmap.
+ * Return the LBA after the last zone reported.
+ */
+static sector_t sd_zbc_get_seq_zones(struct scsi_disk *sdkp, unsigned char *buf,
+				     unsigned int buflen,
+				     unsigned long *seq_zones_bitmap)
+{
+	sector_t lba, next_lba = sdkp->capacity;
+	unsigned int buf_len, list_length;
+	unsigned char *rec;
+	u8 type, cond;
+
+	list_length = get_unaligned_be32(&buf[0]) + 64;
+	buf_len = min(list_length, buflen);
+	rec = buf + 64;
+
+	while (rec < buf + buf_len) {
+		type = rec[0] & 0x0f;
+		cond = (rec[1] >> 4) & 0xf;
+		lba = get_unaligned_be64(&rec[16]);
+		if (type != ZBC_ZONE_TYPE_CONV &&
+		    cond != ZBC_ZONE_COND_READONLY &&
+		    cond != ZBC_ZONE_COND_OFFLINE)
+			set_bit(lba >> sdkp->zone_shift, seq_zones_bitmap);
+		next_lba = lba + get_unaligned_be64(&rec[8]);
+		rec += 64;
+	}
+
+	return next_lba;
+}
+
+/**
+ * sd_zbc_setup_seq_zones_bitmap - Initialize the disk seq zone bitmap.
+ * @sdkp: target disk
+ *
+ * Allocate a zone bitmap and initialize it by identifying sequential zones.
+ */
+static int sd_zbc_setup_seq_zones_bitmap(struct scsi_disk *sdkp)
+{
+	struct request_queue *q = sdkp->disk->queue;
+	unsigned long *seq_zones_bitmap;
+	sector_t lba = 0;
+	unsigned char *buf;
+	int ret = -ENOMEM;
+
+	seq_zones_bitmap = sd_zbc_alloc_zone_bitmap(sdkp);
+	if (!seq_zones_bitmap)
+		return -ENOMEM;
+
+	buf = kmalloc(SD_ZBC_BUF_SIZE, GFP_KERNEL);
+	if (!buf)
+		goto out;
+
+	while (lba < sdkp->capacity) {
+		ret = sd_zbc_report_zones(sdkp, buf, SD_ZBC_BUF_SIZE, lba);
+		if (ret)
+			goto out;
+		lba = sd_zbc_get_seq_zones(sdkp, buf, SD_ZBC_BUF_SIZE,
+					   seq_zones_bitmap);
+	}
+
+	if (lba != sdkp->capacity) {
+		/* Something went wrong */
+		ret = -EIO;
+	}
+
+out:
+	kfree(buf);
+	if (ret) {
+		kfree(seq_zones_bitmap);
+		return ret;
+	}
+
+	q->seq_zones_bitmap = seq_zones_bitmap;
+
+	return 0;
+}
+
+static void sd_zbc_cleanup(struct scsi_disk *sdkp)
+{
+	struct request_queue *q = sdkp->disk->queue;
+
+	kfree(q->seq_zones_bitmap);
+	q->seq_zones_bitmap = NULL;
+
+	kfree(q->seq_zones_wlock);
+	q->seq_zones_wlock = NULL;
+
+	q->nr_zones = 0;
+}
+
 static int sd_zbc_setup(struct scsi_disk *sdkp)
 {
+	struct request_queue *q = sdkp->disk->queue;
+	int ret;
 
 	/* READ16/WRITE16 is mandatory for ZBC disks */
 	sdkp->device->use_16_for_rw = 1;
@@ -599,15 +631,36 @@ static int sd_zbc_setup(struct scsi_disk *sdkp)
 	sdkp->nr_zones =
 		round_up(sdkp->capacity, sdkp->zone_blocks) >> sdkp->zone_shift;
 
-	if (!sdkp->zones_wlock) {
-		sdkp->zones_wlock = kcalloc(BITS_TO_LONGS(sdkp->nr_zones),
-					    sizeof(unsigned long),
-					    GFP_KERNEL);
-		if (!sdkp->zones_wlock)
-			return -ENOMEM;
+	/*
+	 * Initialize the device request queue information if the number
+	 * of zones changed.
+	 */
+	if (sdkp->nr_zones != q->nr_zones) {
+
+		sd_zbc_cleanup(sdkp);
+
+		q->nr_zones = sdkp->nr_zones;
+		if (sdkp->nr_zones) {
+			q->seq_zones_wlock = sd_zbc_alloc_zone_bitmap(sdkp);
+			if (!q->seq_zones_wlock) {
+				ret = -ENOMEM;
+				goto err;
+			}
+
+			ret = sd_zbc_setup_seq_zones_bitmap(sdkp);
+			if (ret) {
+				sd_zbc_cleanup(sdkp);
+				goto err;
+			}
+		}
+
 	}
 
 	return 0;
+
+err:
+	sd_zbc_cleanup(sdkp);
+	return ret;
 }
 
 int sd_zbc_read_zones(struct scsi_disk *sdkp, unsigned char *buf)
@@ -661,14 +714,14 @@ int sd_zbc_read_zones(struct scsi_disk *sdkp, unsigned char *buf)
 
 err:
 	sdkp->capacity = 0;
+	sd_zbc_cleanup(sdkp);
 
 	return ret;
 }
 
 void sd_zbc_remove(struct scsi_disk *sdkp)
 {
-	kfree(sdkp->zones_wlock);
-	sdkp->zones_wlock = NULL;
+	sd_zbc_cleanup(sdkp);
 }
 
 void sd_zbc_print_zones(struct scsi_disk *sdkp)