Write same support v3

index 3a78b00..5575230 100644
@@ -1545,8 +1545,8 @@ generic_make_request_checks(struct bio *bio)
 		goto end_io;
 	}
 
-	if (unlikely(!(bio->bi_rw & REQ_DISCARD) &&
-		     nr_sectors > queue_max_hw_sectors(q))) {
+	if (likely(bio_is_rw(bio) &&
+		   nr_sectors > queue_max_hw_sectors(q))) {
 		printk(KERN_ERR "bio too big device %s (%u > %u)\n",
 		       bdevname(bio->bi_bdev, b),
 		       bio_sectors(bio),

@@ -1698,7 +1698,7 @@ void submit_bio(int rw, struct bio *bio)
 	 * If it's a regular read/write or a barrier with data attached,
 	 * go through the normal accounting stuff before submission.
 	 */
-	if (bio_has_data(bio) && !(rw & REQ_DISCARD)) {
+	if (bio_has_data(bio)) {
 		if (rw & WRITE) {
 			count_vm_events(PGPGOUT, count);
 		} else {

@@ -1744,7 +1744,7 @@ EXPORT_SYMBOL(submit_bio);
  */
 int blk_rq_check_limits(struct request_queue *q, struct request *rq)
 {
-	if (rq->cmd_flags & REQ_DISCARD)
+	if (!rq_mergeable(rq))
 		return 0;
 
 	if (blk_rq_sectors(rq) > queue_max_sectors(q) ||

@@ -2218,7 +2218,7 @@ bool blk_update_request(struct request *req, int error, unsigned int nr_bytes)
 	req->buffer = bio_data(req->bio);
 
 	/* update sector only for requests with clear definition of sector */
-	if (req->cmd_type == REQ_TYPE_FS || (req->cmd_flags & REQ_DISCARD))
+	if (req->cmd_type == REQ_TYPE_FS)
 		req->__sector += total_bytes >> 9;
 
 	/* mixed attributes always follow the first bio */

index 160035f..9172606 100644
@@ -371,18 +371,6 @@ static int attempt_merge(struct request_queue *q, struct request *req,
 		return 0;
 
 	/*
-	 * Don't merge file system requests and discard requests
-	 */
-	if ((req->cmd_flags & REQ_DISCARD) != (next->cmd_flags & REQ_DISCARD))
-		return 0;
-
-	/*
-	 * Don't merge discard requests and secure discard requests
-	 */
-	if ((req->cmd_flags & REQ_SECURE) != (next->cmd_flags & REQ_SECURE))
-		return 0;
-
-	/*
 	 * not contiguous
 	 */
 	if (blk_rq_pos(req) + blk_rq_sectors(req) != blk_rq_pos(next))

@@ -474,15 +462,7 @@ int blk_attempt_req_merge(struct request_queue *q, struct request *rq,
 
 bool blk_rq_merge_ok(struct request *rq, struct bio *bio)
 {
-	if (!rq_mergeable(rq))
-		return false;
-
-	/* don't merge file system requests and discard requests */
-	if ((bio->bi_rw & REQ_DISCARD) != (rq->bio->bi_rw & REQ_DISCARD))
-		return false;
-
-	/* don't merge discard requests and secure discard requests */
-	if ((bio->bi_rw & REQ_SECURE) != (rq->bio->bi_rw & REQ_SECURE))
+	if (!rq_mergeable(rq) || !bio_mergeable(bio))
 		return false;
 
 	/* different data direction or already started, don't merge */

index f016855..cccfdbf 100644
@@ -591,8 +591,7 @@ void __elv_add_request(struct request_queue *q, struct request *rq, int where)
 
 	if (rq->cmd_flags & REQ_SOFTBARRIER) {
 		/* barriers are scheduling boundary, update end_sector */
-		if (rq->cmd_type == REQ_TYPE_FS ||
-		    (rq->cmd_flags & REQ_DISCARD)) {
+		if (rq->cmd_type == REQ_TYPE_FS) {
 			q->end_sector = rq_end_sector(rq);
 			q->boundary_rq = rq;
 		}

@@ -634,8 +633,7 @@ void __elv_add_request(struct request_queue *q, struct request *rq, int where)
 		if (elv_attempt_insert_merge(q, rq))
 			break;
 	case ELEVATOR_INSERT_SORT:
-		BUG_ON(rq->cmd_type != REQ_TYPE_FS &&
-		       !(rq->cmd_flags & REQ_DISCARD));
+		BUG_ON(rq->cmd_type != REQ_TYPE_FS);
 		rq->cmd_flags |= REQ_SORTED;
 		q->nr_sorted++;
 		if (rq_mergeable(rq)) {

index 129a9c0..cad2a9c 100644
@@ -358,9 +358,28 @@ static inline char *__bio_kmap_irq(struct bio *bio, unsigned short idx,
 /*
  * Check whether this bio carries any data or not. A NULL bio is allowed.
  */
-static inline int bio_has_data(struct bio *bio)
+static inline bool bio_has_data(struct bio *bio)
 {
-	return bio && bio->bi_io_vec != NULL;
+	if (bio && bio->bi_io_vec)
+		return true;
+
+	return false;
+}
+
+static inline bool bio_is_rw(struct bio *bio)
+{
+	if (!bio_has_data(bio))
+		return false;
+
+	return true;
+}
+
+static inline bool bio_mergeable(struct bio *bio)
+{
+	if (bio->bi_rw & REQ_NOMERGE_FLAGS)
+		return false;
+
+	return true;
 }
 
 /*

index 4053cbd..1a2727c 100644
@@ -170,6 +170,10 @@ enum rq_flag_bits {
 	 REQ_DISCARD | REQ_NOIDLE | REQ_FLUSH | REQ_FUA | REQ_SECURE)
 #define REQ_CLONE_MASK		REQ_COMMON_MASK
 
+#define REQ_NOMERGE_FLAGS \
+	(REQ_NOMERGE | REQ_STARTED | REQ_SOFTBARRIER | REQ_FLUSH | REQ_FUA | \
+	 REQ_DISCARD)
+
 #define REQ_RAHEAD		(1 << __REQ_RAHEAD)
 #define REQ_THROTTLED		(1 << __REQ_THROTTLED)
 

index 606cf33..3943933 100644
@@ -512,8 +512,7 @@ static inline void queue_flag_clear(unsigned int flag, struct request_queue *q)
 
 #define blk_account_rq(rq) \
 	(((rq)->cmd_flags & REQ_STARTED) && \
-	 ((rq)->cmd_type == REQ_TYPE_FS || \
-	  ((rq)->cmd_flags & REQ_DISCARD)))
+	 ((rq)->cmd_type == REQ_TYPE_FS))
 
 #define blk_pm_request(rq)	\
 	((rq)->cmd_type == REQ_TYPE_PM_SUSPEND || \

@@ -569,17 +568,17 @@ static inline void blk_clear_queue_full(struct request_queue *q, int sync)
 		queue_flag_clear(QUEUE_FLAG_ASYNCFULL, q);
 }
 
+static inline bool rq_mergeable(struct request *rq)
+{
+	if (rq->cmd_type != REQ_TYPE_FS)
+		return false;
+
+	if (rq->cmd_flags & REQ_NOMERGE_FLAGS)
+		return false;
+
+	return true;
+}
 
-/*
- * mergeable request must not have _NOMERGE or _BARRIER bit set, nor may
- * it already be started by driver.
- */
-#define RQ_NOMERGE_FLAGS	\
-	(REQ_NOMERGE | REQ_STARTED | REQ_SOFTBARRIER | REQ_FLUSH | REQ_FUA)
-#define rq_mergeable(rq)	\
-	(!((rq)->cmd_flags & RQ_NOMERGE_FLAGS) && \
-	 (((rq)->cmd_flags & REQ_DISCARD) || \
-	  (rq)->cmd_type == REQ_TYPE_FS))
 
 /*
  * q->prep_rq_fn return values

index 5575230..1cd55be 100644
@@ -1593,6 +1593,11 @@ generic_make_request_checks(struct bio *bio)
 		goto end_io;
 	}
 
+	if (bio->bi_rw & REQ_WRITE_SAME && !bdev_write_same(bio->bi_bdev)) {
+		err = -EOPNOTSUPP;
+		goto end_io;
+	}
+
 	if (blk_throtl_bio(q, bio))
 		return false;	/* throttled, will be resubmitted later */
 

@@ -1690,8 +1695,6 @@ EXPORT_SYMBOL(generic_make_request);
  */
 void submit_bio(int rw, struct bio *bio)
 {
-	int count = bio_sectors(bio);
-
 	bio->bi_rw |= rw;
 
 	/*

@@ -1699,6 +1702,13 @@ void submit_bio(int rw, struct bio *bio)
 	 * go through the normal accounting stuff before submission.
 	 */
 	if (bio_has_data(bio)) {
+		unsigned int count;
+
+		if (unlikely(rw & REQ_WRITE_SAME))
+			count = bdev_logical_block_size(bio->bi_bdev) >> 9;
+		else
+			count = bio_sectors(bio);
+
 		if (rw & WRITE) {
 			count_vm_events(PGPGOUT, count);
 		} else {

80 lines not on this page · raw message

index d3234fc..5680b91 100644
@@ -113,6 +113,7 @@ void blk_set_default_limits(struct queue_limits *lim)
 	lim->seg_boundary_mask = BLK_SEG_BOUNDARY_MASK;
 	lim->max_segment_size = BLK_MAX_SEGMENT_SIZE;
 	lim->max_sectors = lim->max_hw_sectors = BLK_SAFE_MAX_SECTORS;
+	lim->max_write_same_sectors = 0;
 	lim->max_discard_sectors = 0;
 	lim->discard_granularity = 0;
 	lim->discard_alignment = 0;

@@ -143,6 +144,7 @@ void blk_set_stacking_limits(struct queue_limits *lim)
 	lim->discard_zeroes_data = 1;
 	lim->max_segments = USHRT_MAX;
 	lim->max_hw_sectors = UINT_MAX;
+	lim->max_write_same_sectors = UINT_MAX;
 
 	lim->max_sectors = BLK_DEF_MAX_SECTORS;
 }

@@ -287,6 +289,18 @@ void blk_queue_max_discard_sectors(struct request_queue *q,
 EXPORT_SYMBOL(blk_queue_max_discard_sectors);
 
 /**
+ * blk_queue_max_write_same_sectors - set max sectors for a single write same
+ * @q:  the request queue for the device
+ * @max_write_same_sectors: maximum number of sectors to write per command
+ **/
+void blk_queue_max_write_same_sectors(struct request_queue *q,
+				      unsigned int max_write_same_sectors)
+{
+	q->limits.max_write_same_sectors = max_write_same_sectors;
+}
+EXPORT_SYMBOL(blk_queue_max_write_same_sectors);
+
+/**
  * blk_queue_max_segments - set max hw segments for a request for this queue
  * @q:  the request queue for the device
  * @max_segments:  max number of segments

@@ -511,6 +525,8 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
 
 	t->max_sectors = min_not_zero(t->max_sectors, b->max_sectors);
 	t->max_hw_sectors = min_not_zero(t->max_hw_sectors, b->max_hw_sectors);
+	t->max_write_same_sectors = min(t->max_write_same_sectors,
+					b->max_write_same_sectors);
 	t->bounce_pfn = min_not_zero(t->bounce_pfn, b->bounce_pfn);
 
 	t->seg_boundary_mask = min_not_zero(t->seg_boundary_mask,

index cf15001..5b85d91 100644
@@ -161,6 +161,13 @@ static ssize_t queue_discard_zeroes_data_show(struct request_queue *q, char *pag
 	return queue_var_show(queue_discard_zeroes_data(q), page);
 }
 
+static ssize_t queue_write_same_max_show(struct request_queue *q, char *page)
+{
+	return sprintf(page, "%llu\n",
+		(unsigned long long)q->limits.max_write_same_sectors << 9);
+}
+
+
 static ssize_t
 queue_max_sectors_store(struct request_queue *q, const char *page, size_t count)
 {

@@ -357,6 +364,11 @@ static struct queue_sysfs_entry queue_discard_zeroes_data_entry = {
 	.show = queue_discard_zeroes_data_show,
 };
 
+static struct queue_sysfs_entry queue_write_same_max_entry = {
+	.attr = {.name = "write_same_max_bytes", .mode = S_IRUGO },
+	.show = queue_write_same_max_show,
+};
+
 static struct queue_sysfs_entry queue_nonrot_entry = {
 	.attr = {.name = "rotational", .mode = S_IRUGO | S_IWUSR },
 	.show = queue_show_nonrot,

@@ -404,6 +416,7 @@ static struct attribute *default_attrs[] = {
 	&queue_discard_granularity_entry.attr,
 	&queue_discard_max_entry.attr,
 	&queue_discard_zeroes_data_entry.attr,
+	&queue_write_same_max_entry.attr,
 	&queue_nonrot_entry.attr,
 	&queue_nomerges_entry.attr,
 	&queue_rq_affinity_entry.attr,

index cad2a9c..df4b91e 100644
@@ -371,6 +371,9 @@ static inline bool bio_is_rw(struct bio *bio)
 	if (!bio_has_data(bio))
 		return false;
 
+	if (bio->bi_rw & REQ_WRITE_SAME)
+		return false;
+
 	return true;
 }
 

index 1a2727c..ac1e03e 100644
@@ -124,6 +124,7 @@ enum rq_flag_bits {
 	__REQ_PRIO,		/* boost priority in cfq */
 	__REQ_DISCARD,		/* request to discard sectors */
 	__REQ_SECURE,		/* secure discard (used with __REQ_DISCARD) */
+	__REQ_WRITE_SAME,	/* write same block many times */
 
 	__REQ_NOIDLE,		/* don't anticipate more IO after this one */
 	__REQ_FUA,		/* forced unit access */

@@ -162,17 +163,19 @@ enum rq_flag_bits {
 #define REQ_PRIO		(1 << __REQ_PRIO)
 #define REQ_DISCARD		(1 << __REQ_DISCARD)
 #define REQ_NOIDLE		(1 << __REQ_NOIDLE)
+#define REQ_WRITE_SAME		(1 << __REQ_WRITE_SAME)
 
 #define REQ_FAILFAST_MASK \
 	(REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT | REQ_FAILFAST_DRIVER)
 #define REQ_COMMON_MASK \
 	(REQ_WRITE | REQ_FAILFAST_MASK | REQ_SYNC | REQ_META | REQ_PRIO | \
-	 REQ_DISCARD | REQ_NOIDLE | REQ_FLUSH | REQ_FUA | REQ_SECURE)
+	 REQ_DISCARD | REQ_WRITE_SAME | REQ_NOIDLE | REQ_FLUSH | REQ_FUA | \
+	 REQ_SECURE)
 #define REQ_CLONE_MASK		REQ_COMMON_MASK
 
 #define REQ_NOMERGE_FLAGS \
 	(REQ_NOMERGE | REQ_STARTED | REQ_SOFTBARRIER | REQ_FLUSH | REQ_FUA | \
-	 REQ_DISCARD)
+	 REQ_DISCARD | REQ_WRITE_SAME)
 
 #define REQ_RAHEAD		(1 << __REQ_RAHEAD)
 #define REQ_THROTTLED		(1 << __REQ_THROTTLED)

index 3943933..8c97ee9 100644
@@ -254,6 +254,7 @@ struct queue_limits {
 	unsigned int		io_min;
 	unsigned int		io_opt;
 	unsigned int		max_discard_sectors;
+	unsigned int		max_write_same_sectors;
 	unsigned int		discard_granularity;
 	unsigned int		discard_alignment;
 

@@ -831,6 +832,8 @@ extern void blk_queue_max_segments(struct request_queue *, unsigned short);
 extern void blk_queue_max_segment_size(struct request_queue *, unsigned int);
 extern void blk_queue_max_discard_sectors(struct request_queue *q,
 		unsigned int max_discard_sectors);
+extern void blk_queue_max_write_same_sectors(struct request_queue *q,
+		unsigned int max_write_same_sectors);
 extern void blk_queue_logical_block_size(struct request_queue *, unsigned short);
 extern void blk_queue_physical_block_size(struct request_queue *, unsigned int);
 extern void blk_queue_alignment_offset(struct request_queue *q,

@@ -955,6 +958,9 @@ static inline struct request *blk_map_queue_find_tag(struct blk_queue_tag *bqt,
 extern int blkdev_issue_flush(struct block_device *, gfp_t, sector_t *);
 extern int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 		sector_t nr_sects, gfp_t gfp_mask, unsigned long flags);
+extern int blkdev_issue_write_same(struct block_device *bdev, sector_t sector,
+		sector_t nr_sects, gfp_t gfp_mask, void *buffer,
+		unsigned int length);
 extern int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
 			sector_t nr_sects, gfp_t gfp_mask);
 static inline int sb_issue_discard(struct super_block *sb, sector_t block,

@@ -1122,6 +1128,16 @@ static inline unsigned int bdev_discard_zeroes_data(struct block_device *bdev)
 	return queue_discard_zeroes_data(bdev_get_queue(bdev));
 }
 
+static inline unsigned int bdev_write_same(struct block_device *bdev)
+{
+	struct request_queue *q = bdev_get_queue(bdev);
+
+	if (q)
+		return q->limits.max_write_same_sectors;
+
+	return 0;
+}
+
 static inline int queue_dma_alignment(struct request_queue *q)
 {
 	return q ? q->dma_alignment : 511;

index e6cb5b4..5a8d026 100644
@@ -199,7 +199,7 @@ EXPORT_SYMBOL(blkdev_issue_write_same);
  *  Generate and issue number of bios with zerofiled pages.
  */
 
-int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
+int __blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
 			sector_t nr_sects, gfp_t gfp_mask)
 {
 	int ret;

@@ -249,4 +249,33 @@ int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
 
 	return ret;
 }
+
+/**
+ * blkdev_issue_zeroout - zero-fill a block range
+ * @bdev:	blockdev to write
+ * @sector:	start sector
+ * @nr_sects:	number of sectors to write
+ * @gfp_mask:	memory allocation flags (for bio_alloc)
+ *
+ * Description:
+ *  Generate and issue number of bios with zerofiled pages.
+ */
+
+int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
+			 sector_t nr_sects, gfp_t gfp_mask)
+{
+	if (bdev_write_same(bdev)) {
+		unsigned char bdn[BDEVNAME_SIZE];
+
+		if (!blkdev_issue_write_same(bdev, sector, nr_sects, gfp_mask,
+					     ZERO_PAGE(0)))
+			return 0;
+
+		bdevname(bdev, bdn);
+		printk(KERN_ERR "%s: WRITE SAME failed. Manually zeroing.\n",
+		       bdn);
+	}
+
+	return __blkdev_issue_zeroout(bdev, sector, nr_sects, gfp_mask);
+}
 EXPORT_SYMBOL(blkdev_issue_zeroout);

index 8c97ee9..92956b7 100644
@@ -959,8 +959,7 @@ extern int blkdev_issue_flush(struct block_device *, gfp_t, sector_t *);
 extern int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 		sector_t nr_sects, gfp_t gfp_mask, unsigned long flags);
 extern int blkdev_issue_write_same(struct block_device *bdev, sector_t sector,
-		sector_t nr_sects, gfp_t gfp_mask, void *buffer,
-		unsigned int length);
+		sector_t nr_sects, gfp_t gfp_mask, struct page *page);
 extern int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
 			sector_t nr_sects, gfp_t gfp_mask);
 static inline int sb_issue_discard(struct super_block *sb, sector_t block,

index ba15b2d..0c6e633 100644
@@ -132,6 +132,22 @@ static int blk_ioctl_discard(struct block_device *bdev, uint64_t start,
 	return blkdev_issue_discard(bdev, start, len, GFP_KERNEL, flags);
 }
 
+static int blk_ioctl_zeroout(struct block_device *bdev, uint64_t start,
+			     uint64_t len)
+{
+	if (start & 511)
+		return -EINVAL;
+	if (len & 511)
+		return -EINVAL;
+	start >>= 9;
+	len >>= 9;
+
+	if (start + len > (i_size_read(bdev->bd_inode) >> 9))
+		return -EINVAL;
+
+	return blkdev_issue_zeroout(bdev, start, len, GFP_KERNEL);
+}
+
 static int put_ushort(unsigned long arg, unsigned short val)
 {
 	return put_user(val, (unsigned short __user *)arg);

@@ -247,6 +263,17 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,
 		return blk_ioctl_discard(bdev, range[0], range[1],
 					 cmd == BLKSECDISCARD);
 	}
+	case BLKZEROOUT: {
+		uint64_t range[2];
+
+		if (!(mode & FMODE_WRITE))
+			return -EBADF;
+
+		if (copy_from_user(range, (void __user *)arg, sizeof(range)))
+			return -EFAULT;
+
+		return blk_ioctl_zeroout(bdev, range[0], range[1]);
+	}
 
 	case HDIO_GETGEO: {
 		struct hd_geometry geo;

index 386da09..e918ef7 100644
@@ -320,6 +320,7 @@ struct inodes_stat_t {
 #define BLKDISCARDZEROES _IO(0x12,124)
 #define BLKSECDISCARD _IO(0x12,125)
 #define BLKROTATIONAL _IO(0x12,126)
+#define BLKZEROOUT _IO(0x12,127)
 
 #define BMAP_IOCTL 1		/* obsolete - kept for compatibility */
 #define FIBMAP	   _IO(0x00,1)	/* bmap access */

index 508a60b..b6db28f 100644
@@ -1052,6 +1052,7 @@ static void ata_scsi_sdev_config(struct scsi_device *sdev)
 {
 	sdev->use_10_for_rw = 1;
 	sdev->use_10_for_ms = 1;
+	sdev->no_report_opcodes = 1;
 
 	/* Schedule policy is determined by ->qc_defer() callback and
 	 * it needs to see every deferred qc.  Set dev_blocked to 1 to

index 80e95aa..d956dd38 100644
@@ -1517,6 +1517,7 @@ static int sbp2_scsi_slave_configure(struct scsi_device *sdev)
 	struct sbp2_logical_unit *lu = sdev->hostdata;
 
 	sdev->use_10_for_rw = 1;
+	sdev->no_report_opcodes = 1;
 
 	if (sbp2_param_exclusive_login)
 		sdev->manage_start_stop = 1;

57 lines not on this page · raw message

index 13b8bcd..61178b8 100644
@@ -197,6 +197,9 @@ static int slave_configure(struct scsi_device *sdev)
 		 * page x08, so we will skip it. */
 		sdev->skip_ms_page_8 = 1;
 
+		/* Do not attempt to use REPORT SUPPORTED OPERATION CODES */
+		sdev->no_report_opcodes = 1;
+
 		/* Some disks return the total number of blocks in response
 		 * to READ CAPACITY rather than the highest block number.
 		 * If this device makes that mistake, tell the sd driver. */

index 77273f2..59f31dc 100644
@@ -134,6 +134,7 @@ struct scsi_device {
 				     * because we did a bus reset. */
 	unsigned use_10_for_rw:1; /* first try 10-byte read / write */
 	unsigned use_10_for_ms:1; /* first try 10-byte mode sense/select */
+	unsigned no_report_opcodes:1;	/* no REPORT SUPPORTED OPERATION CODES */
 	unsigned skip_ms_page_8:1;	/* do not use MODE SENSE page 0x08 */
 	unsigned skip_ms_page_3f:1;	/* do not use MODE SENSE page 0x3f */
 	unsigned use_192_bytes_for_3f:1; /* ask for 192 bytes from page 0x3f */

@@ -354,6 +355,8 @@ extern int scsi_test_unit_ready(struct scsi_device *sdev, int timeout,
 				int retries, struct scsi_sense_hdr *sshdr);
 extern int scsi_get_vpd_page(struct scsi_device *, u8 page, unsigned char *buf,
 			     int buf_len);
+extern int scsi_report_opcode(struct scsi_device *sdp, unsigned char *buffer,
+			      unsigned int len, unsigned char opcode);
 extern int scsi_device_set_state(struct scsi_device *sdev,
 				 enum scsi_device_state state);
 extern struct scsi_event *sdev_evt_alloc(enum scsi_device_event evt_type,

index b6db28f..dde907b 100644
@@ -1053,6 +1053,7 @@ static void ata_scsi_sdev_config(struct scsi_device *sdev)
 	sdev->use_10_for_rw = 1;
 	sdev->use_10_for_ms = 1;
 	sdev->no_report_opcodes = 1;
+	sdev->no_write_same = 1;
 
 	/* Schedule policy is determined by ->qc_defer() callback and
 	 * it needs to see every deferred qc.  Set dev_blocked to 1 to

index d956dd38..52b2bac 100644
@@ -1518,6 +1518,7 @@ static int sbp2_scsi_slave_configure(struct scsi_device *sdev)
 
 	sdev->use_10_for_rw = 1;
 	sdev->no_report_opcodes = 1;
+	sdev->no_write_same = 1;
 
 	if (sbp2_param_exclusive_login)
 		sdev->manage_start_stop = 1;

index b2c95db..560b63f 100644
@@ -874,11 +874,23 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes)
 				action = ACTION_FAIL;
 				error = -EILSEQ;
 			/* INVALID COMMAND OPCODE or INVALID FIELD IN CDB */
-			} else if ((sshdr.asc == 0x20 || sshdr.asc == 0x24) &&
-				   (cmd->cmnd[0] == UNMAP ||
-				    cmd->cmnd[0] == WRITE_SAME_16 ||
-				    cmd->cmnd[0] == WRITE_SAME)) {
-				description = "Discard failure";
+			} else if (sshdr.asc == 0x20 || sshdr.asc == 0x24) {
+				switch(cmd->cmnd[0]) {
+				case UNMAP:
+					description = "Discard failure";
+					break;
+				case WRITE_SAME:
+				case WRITE_SAME_16:
+					if (cmd->cmnd[1] & 0x8)
+						description = "Discard failure";
+					else
+						description =
+							"Write same failure";
+					break;
+				default:
+					description = "Invalid command failure";
+					break;
+				}
 				action = ACTION_FAIL;
 			} else
 				action = ACTION_FAIL;

261 lines not on this page · raw message

index 4163f29..5923e42 100644
@@ -14,6 +14,7 @@
 #define SD_TIMEOUT		(30 * HZ)
 #define SD_MOD_TIMEOUT		(75 * HZ)
 #define SD_FLUSH_TIMEOUT	(60 * HZ)
+#define SD_WRITE_SAME_TIMEOUT	(120 * HZ)
 
 /*
  * Number of allowed retries

@@ -38,6 +39,11 @@ enum {
 };
 
 enum {
+	SD_MAX_WS10_BLOCKS = 0xffff,
+	SD_MAX_WS16_BLOCKS = 0x7fffff,
+};
+
+enum {
 	SD_LBP_FULL = 0,	/* Full logical block provisioning */
 	SD_LBP_UNMAP,		/* Use UNMAP command */
 	SD_LBP_WS16,		/* Use WRITE SAME(16) with UNMAP bit */

@@ -74,6 +80,7 @@ struct scsi_disk {
 	unsigned	lbpws : 1;
 	unsigned	lbpws10 : 1;
 	unsigned	lbpvpd : 1;
+	unsigned	ws16 : 1;
 };
 #define to_scsi_disk(obj) container_of(obj,struct scsi_disk,dev)
 

index 61178b8..7aaf5d4 100644
@@ -200,6 +200,9 @@ static int slave_configure(struct scsi_device *sdev)
 		/* Do not attempt to use REPORT SUPPORTED OPERATION CODES */
 		sdev->no_report_opcodes = 1;
 
+		/* Do not attempt to use WRITE SAME */
+		sdev->no_write_same = 1;
+
 		/* Some disks return the total number of blocks in response
 		 * to READ CAPACITY rather than the highest block number.
 		 * If this device makes that mistake, tell the sd driver. */

index 59f31dc..c1d8c2f 100644
@@ -135,6 +135,7 @@ struct scsi_device {
 	unsigned use_10_for_rw:1; /* first try 10-byte read / write */
 	unsigned use_10_for_ms:1; /* first try 10-byte mode sense/select */
 	unsigned no_report_opcodes:1;	/* no REPORT SUPPORTED OPERATION CODES */
+	unsigned no_write_same:1;	/* no WRITE SAME command */
 	unsigned skip_ms_page_8:1;	/* do not use MODE SENSE page 0x08 */
 	unsigned skip_ms_page_3f:1;	/* do not use MODE SENSE page 0x3f */
 	unsigned use_192_bytes_for_3f:1; /* ask for 192 bytes from page 0x3f */

index 34b2f3b..0191f1d 100644
@@ -575,14 +575,14 @@ static void sd_config_discard(struct scsi_disk *sdkp, unsigned int mode)
 }
 
 /**
- * scsi_setup_discard_cmnd - unmap blocks on thinly provisioned device
+ * sd_setup_discard_cmnd - unmap blocks on thinly provisioned device
  * @sdp: scsi device to operate one
  * @rq: Request to prepare
  *
  * Will issue either UNMAP or WRITE SAME(16) depending on preference
  * indicated by target device.
  **/
-static int scsi_setup_discard_cmnd(struct scsi_device *sdp, struct request *rq)
+static int sd_setup_discard_cmnd(struct scsi_device *sdp, struct request *rq)
 {
 	struct scsi_disk *sdkp = scsi_disk(rq->rq_disk);
 	struct bio *bio = rq->bio;

@@ -734,7 +734,7 @@ static int sd_setup_write_same_cmnd(struct scsi_device *sdp, struct request *rq)
 	return scsi_setup_blk_pc_cmnd(sdp, rq);
 }
 
-static int scsi_setup_flush_cmnd(struct scsi_device *sdp, struct request *rq)
+static int sd_setup_flush_cmnd(struct scsi_device *sdp, struct request *rq)
 {
 	rq->timeout = SD_FLUSH_TIMEOUT;
 	rq->retries = SD_MAX_RETRIES;

@@ -777,13 +777,13 @@ static int sd_prep_fn(struct request_queue *q, struct request *rq)
 	 * block PC requests to make life easier.
 	 */
 	if (rq->cmd_flags & REQ_DISCARD) {
-		ret = scsi_setup_discard_cmnd(sdp, rq);
+		ret = sd_setup_discard_cmnd(sdp, rq);
 		goto out;
 	} else if (rq->cmd_flags & REQ_WRITE_SAME) {
 		ret = sd_setup_write_same_cmnd(sdp, rq);
 		goto out;
 	} else if (rq->cmd_flags & REQ_FLUSH) {
-		ret = scsi_setup_flush_cmnd(sdp, rq);
+		ret = sd_setup_flush_cmnd(sdp, rq);
 		goto out;
 	} else if (rq->cmd_type == REQ_TYPE_BLOCK_PC) {
 		ret = scsi_setup_blk_pc_cmnd(sdp, rq);

index ea5dd28..32e19e3 100644
@@ -297,7 +297,8 @@ static void do_region(int rw, unsigned region, struct dm_io_region *where,
 	unsigned num_bvecs;
 	sector_t remaining = where->count;
 	struct request_queue *q = bdev_get_queue(where->bdev);
-	sector_t discard_sectors;
+	unsigned short logical_block_size = queue_logical_block_size(q);
+	sector_t num_sectors;
 
 	/*
 	 * where->count may be zero if rw holds a flush and we need to

@@ -307,7 +308,7 @@ static void do_region(int rw, unsigned region, struct dm_io_region *where,
 		/*
 		 * Allocate a suitably sized-bio.
 		 */
-		if (rw & REQ_DISCARD)
+		if ((rw & REQ_DISCARD) || (rw & REQ_WRITE_SAME))
 			num_bvecs = 1;
 		else
 			num_bvecs = min_t(int, bio_get_nr_vecs(where->bdev),

@@ -321,9 +322,21 @@ static void do_region(int rw, unsigned region, struct dm_io_region *where,
 		store_io_and_region_in_bio(bio, io, region);
 
 		if (rw & REQ_DISCARD) {
-			discard_sectors = min_t(sector_t, q->limits.max_discard_sectors, remaining);
-			bio->bi_size = discard_sectors << SECTOR_SHIFT;
-			remaining -= discard_sectors;
+			num_sectors = min_t(sector_t, q->limits.max_discard_sectors, remaining);
+			bio->bi_size = num_sectors << SECTOR_SHIFT;
+			remaining -= num_sectors;
+		} else if (rw & REQ_WRITE_SAME) {
+			/*
+			 * WRITE SAME only uses a single page.
+			 */
+			dp->get_page(dp, &page, &len, &offset);
+			bio_add_page(bio, page, logical_block_size, offset);
+			num_sectors = min_t(sector_t, q->limits.max_write_same_sectors, remaining);
+			bio->bi_size = num_sectors << SECTOR_SHIFT;
+
+			offset = 0;
+			remaining -= num_sectors;
+			dp->next_page(dp);
 		} else while (remaining) {
 			/*
 			 * Try and add as many pages as possible.

index bed444c..3cd00aa 100644
@@ -349,7 +349,7 @@ static void complete_io(unsigned long error, void *context)
 	struct dm_kcopyd_client *kc = job->kc;
 
 	if (error) {
-		if (job->rw == WRITE)
+		if (job->rw & WRITE)
 			job->write_err |= error;
 		else
 			job->read_err = 1;

@@ -361,7 +361,7 @@ static void complete_io(unsigned long error, void *context)
 		}
 	}
 
-	if (job->rw == WRITE)
+	if (job->rw & WRITE)
 		push(&kc->complete_jobs, job);
 
 	else {

@@ -432,7 +432,7 @@ static int process_jobs(struct list_head *jobs, struct dm_kcopyd_client *kc,
 
 		if (r < 0) {
 			/* error this rogue job */
-			if (job->rw == WRITE)
+			if (job->rw & WRITE)
 				job->write_err = (unsigned long) -1L;
 			else
 				job->read_err = 1;

@@ -608,10 +608,22 @@ int dm_kcopyd_copy(struct dm_kcopyd_client *kc, struct dm_io_region *from,
 		job->pages = NULL;
 		job->rw = READ;
 	} else {
+		int i;
+
 		memset(&job->source, 0, sizeof job->source);
 		job->source.count = job->dests[0].count;
 		job->pages = &zero_page_list;
 		job->rw = WRITE;
+		/*
+		 * Optimize zeroing via WRITE SAME if all dests support it.
+		 */
+		job->rw |= REQ_WRITE_SAME;
+		for (i = 0; i < job->num_dests; i++) {
+			if (!bdev_write_same(job->dests[i].bdev)) {
+				job->rw &= ~REQ_WRITE_SAME;
+				break;
+			}
+		}
 	}
 
 	job->fn = fn;