[PATCH v9 1/3] block: Introduce provisioning primitives

[Sarthak Kukreti <sarthakkukreti@chromium.org>]

Introduce block request REQ_OP_PROVISION. The intent of this request is
to request underlying storage to preallocate disk space for the given
block range. Block devices that support this capability will export a
provision limit within their request queues.

This patch also adds the capability to call fallocate() in mode 0 on block
devices, which will send REQ_OP_PROVISION to the block device for the
specified range.

Signed-off-by: Sarthak Kukreti <sarthakkukreti@chromium.org>
Signed-off-by: Mike Snitzer <snitzer@kernel.org>
---
 block/blk-core.c          |  5 ++++
 block/blk-lib.c           | 51 +++++++++++++++++++++++++++++++++++++++
 block/blk-merge.c         | 18 ++++++++++++++
 block/blk-settings.c      | 19 +++++++++++++++
 block/blk-sysfs.c         |  9 +++++++
 block/bounce.c            |  1 +
 block/fops.c              |  5 ++++
 include/linux/bio.h       |  6 +++--
 include/linux/blk_types.h |  5 +++-
 include/linux/blkdev.h    | 16 ++++++++++++
 10 files changed, 132 insertions(+), 3 deletions(-)

diff --git a/block/blk-core.c b/block/blk-core.c
index 9d51e9894ece..e1615ffa71bc 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -123,6 +123,7 @@ static const char *const blk_op_name[] = {
 	REQ_OP_NAME(WRITE_ZEROES),
 	REQ_OP_NAME(DRV_IN),
 	REQ_OP_NAME(DRV_OUT),
+	REQ_OP_NAME(PROVISION)
 };
 #undef REQ_OP_NAME
 
@@ -792,6 +793,10 @@ void submit_bio_noacct(struct bio *bio)
 		if (!q->limits.max_write_zeroes_sectors)
 			goto not_supported;
 		break;
+	case REQ_OP_PROVISION:
+		if (!q->limits.max_provision_sectors)
+			goto not_supported;
+		break;
 	default:
 		break;
 	}
diff --git a/block/blk-lib.c b/block/blk-lib.c
index e59c3069e835..b1f720e198cd 100644
--- a/block/blk-lib.c
+++ b/block/blk-lib.c
@@ -343,3 +343,54 @@ int blkdev_issue_secure_erase(struct block_device *bdev, sector_t sector,
 	return ret;
 }
 EXPORT_SYMBOL(blkdev_issue_secure_erase);
+
+/**
+ * blkdev_issue_provision - provision a block range
+ * @bdev:	blockdev to write
+ * @sector:	start sector
+ * @nr_sects:	number of sectors to provision
+ * @gfp_mask:	memory allocation flags (for bio_alloc)
+ *
+ * Description:
+ *  Issues a provision request to the block device for the range of sectors.
+ *  For thinly provisioned block devices, this acts as a signal for the
+ *  underlying storage pool to allocate space for this block range.
+ */
+int blkdev_issue_provision(struct block_device *bdev, sector_t sector,
+		sector_t nr_sects, gfp_t gfp)
+{
+	sector_t bs_mask = (bdev_logical_block_size(bdev) >> 9) - 1;
+	unsigned int max_sectors = bdev_max_provision_sectors(bdev);
+	struct bio *bio = NULL;
+	struct blk_plug plug;
+	int ret = 0;
+
+	if (max_sectors == 0)
+		return -EOPNOTSUPP;
+	if ((sector | nr_sects) & bs_mask)
+		return -EINVAL;
+	if (bdev_read_only(bdev))
+		return -EPERM;
+
+	blk_start_plug(&plug);
+	for (;;) {
+		unsigned int req_sects = min_t(sector_t, nr_sects, max_sectors);
+
+		bio = blk_next_bio(bio, bdev, 0, REQ_OP_PROVISION, gfp);
+		bio->bi_iter.bi_sector = sector;
+		bio->bi_iter.bi_size = req_sects << SECTOR_SHIFT;
+
+		sector += req_sects;
+		nr_sects -= req_sects;
+		if (!nr_sects) {
+			ret = submit_bio_wait(bio);
+			bio_put(bio);
+			break;
+		}
+		cond_resched();
+	}
+	blk_finish_plug(&plug);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(blkdev_issue_provision);
diff --git a/block/blk-merge.c b/block/blk-merge.c
index 65e75efa9bd3..83e516d2121f 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -158,6 +158,21 @@ static struct bio *bio_split_write_zeroes(struct bio *bio,
 	return bio_split(bio, lim->max_write_zeroes_sectors, GFP_NOIO, bs);
 }
 
+static struct bio *bio_split_provision(struct bio *bio,
+					const struct queue_limits *lim,
+					unsigned int *nsegs, struct bio_set *bs)
+{
+	*nsegs = 0;
+
+	if (!lim->max_provision_sectors)
+		return NULL;
+
+	if (bio_sectors(bio) <= lim->max_provision_sectors)
+		return NULL;
+
+	return bio_split(bio, lim->max_provision_sectors, GFP_NOIO, bs);
+}
+
 /*
  * Return the maximum number of sectors from the start of a bio that may be
  * submitted as a single request to a block device. If enough sectors remain,
@@ -366,6 +381,9 @@ struct bio *__bio_split_to_limits(struct bio *bio,
 	case REQ_OP_WRITE_ZEROES:
 		split = bio_split_write_zeroes(bio, lim, nr_segs, bs);
 		break;
+	case REQ_OP_PROVISION:
+		split = bio_split_provision(bio, lim, nr_segs, bs);
+		break;
 	default:
 		split = bio_split_rw(bio, lim, nr_segs, bs,
 				get_max_io_size(bio, lim) << SECTOR_SHIFT);
diff --git a/block/blk-settings.c b/block/blk-settings.c
index 0046b447268f..c81820406f2f 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -59,6 +59,7 @@ void blk_set_default_limits(struct queue_limits *lim)
 	lim->zoned = BLK_ZONED_NONE;
 	lim->zone_write_granularity = 0;
 	lim->dma_alignment = 511;
+	lim->max_provision_sectors = 0;
 }
 
 /**
@@ -82,6 +83,7 @@ void blk_set_stacking_limits(struct queue_limits *lim)
 	lim->max_dev_sectors = UINT_MAX;
 	lim->max_write_zeroes_sectors = UINT_MAX;
 	lim->max_zone_append_sectors = UINT_MAX;
+	lim->max_provision_sectors = UINT_MAX;
 }
 EXPORT_SYMBOL(blk_set_stacking_limits);
 
@@ -208,6 +210,20 @@ void blk_queue_max_write_zeroes_sectors(struct request_queue *q,
 }
 EXPORT_SYMBOL(blk_queue_max_write_zeroes_sectors);
 
+/**
+ * blk_queue_max_provision_sectors - set max sectors for a single provision
+ *
+ * @q:  the request queue for the device
+ * @max_provision_sectors: maximum number of sectors to provision per command
+ **/
+
+void blk_queue_max_provision_sectors(struct request_queue *q,
+		unsigned int max_provision_sectors)
+{
+	q->limits.max_provision_sectors = max_provision_sectors;
+}
+EXPORT_SYMBOL(blk_queue_max_provision_sectors);
+
 /**
  * blk_queue_max_zone_append_sectors - set max sectors for a single zone append
  * @q:  the request queue for the device
@@ -578,6 +594,9 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
 	t->max_segment_size = min_not_zero(t->max_segment_size,
 					   b->max_segment_size);
 
+	t->max_provision_sectors = min(t->max_provision_sectors,
+				       b->max_provision_sectors);
+
 	t->misaligned |= b->misaligned;
 
 	alignment = queue_limit_alignment_offset(b, start);
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 63e481262336..9a78c36f3199 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -199,6 +199,13 @@ static ssize_t queue_discard_zeroes_data_show(struct request_queue *q, char *pag
 	return queue_var_show(0, page);
 }
 
+static ssize_t queue_provision_max_show(struct request_queue *q,
+		char *page)
+{
+	return sprintf(page, "%llu\n",
+		(unsigned long long)q->limits.max_provision_sectors << 9);
+}
+
 static ssize_t queue_write_same_max_show(struct request_queue *q, char *page)
 {
 	return queue_var_show(0, page);
@@ -507,6 +514,7 @@ QUEUE_RO_ENTRY(queue_discard_max_hw, "discard_max_hw_bytes");
 QUEUE_RW_ENTRY(queue_discard_max, "discard_max_bytes");
 QUEUE_RO_ENTRY(queue_discard_zeroes_data, "discard_zeroes_data");
 
+QUEUE_RO_ENTRY(queue_provision_max, "provision_max_bytes");
 QUEUE_RO_ENTRY(queue_write_same_max, "write_same_max_bytes");
 QUEUE_RO_ENTRY(queue_write_zeroes_max, "write_zeroes_max_bytes");
 QUEUE_RO_ENTRY(queue_zone_append_max, "zone_append_max_bytes");
@@ -633,6 +641,7 @@ static struct attribute *queue_attrs[] = {
 	&queue_discard_max_entry.attr,
 	&queue_discard_max_hw_entry.attr,
 	&queue_discard_zeroes_data_entry.attr,
+	&queue_provision_max_entry.attr,
 	&queue_write_same_max_entry.attr,
 	&queue_write_zeroes_max_entry.attr,
 	&queue_zone_append_max_entry.attr,
diff --git a/block/bounce.c b/block/bounce.c
index 7cfcb242f9a1..ab9d8723ae64 100644
--- a/block/bounce.c
+++ b/block/bounce.c
@@ -176,6 +176,7 @@ static struct bio *bounce_clone_bio(struct bio *bio_src)
 	case REQ_OP_DISCARD:
 	case REQ_OP_SECURE_ERASE:
 	case REQ_OP_WRITE_ZEROES:
+	case REQ_OP_PROVISION:
 		break;
 	default:
 		bio_for_each_segment(bv, bio_src, iter)
diff --git a/block/fops.c b/block/fops.c
index 0abaac705daf..193caf7ab500 100644
--- a/block/fops.c
+++ b/block/fops.c
@@ -789,6 +789,11 @@ static long blkdev_fallocate(struct file *file, int mode, loff_t start,
 	 * de-allocate mode calls to fallocate().
 	 */
 	switch (mode) {
+	case 0:
+	case FALLOC_FL_KEEP_SIZE:
+		error = blkdev_issue_provision(bdev, start >> SECTOR_SHIFT,
+					       len >> SECTOR_SHIFT, GFP_KERNEL);
+		break;
 	case FALLOC_FL_ZERO_RANGE:
 	case FALLOC_FL_ZERO_RANGE | FALLOC_FL_KEEP_SIZE:
 		error = truncate_bdev_range(bdev, file_to_blk_mode(file), start, end);
diff --git a/include/linux/bio.h b/include/linux/bio.h
index 41d417ee1349..aa2119f7cd5a 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -57,7 +57,8 @@ static inline bool bio_has_data(struct bio *bio)
 	    bio->bi_iter.bi_size &&
 	    bio_op(bio) != REQ_OP_DISCARD &&
 	    bio_op(bio) != REQ_OP_SECURE_ERASE &&
-	    bio_op(bio) != REQ_OP_WRITE_ZEROES)
+	    bio_op(bio) != REQ_OP_WRITE_ZEROES &&
+	    bio_op(bio) != REQ_OP_PROVISION)
 		return true;
 
 	return false;
@@ -67,7 +68,8 @@ static inline bool bio_no_advance_iter(const struct bio *bio)
 {
 	return bio_op(bio) == REQ_OP_DISCARD ||
 	       bio_op(bio) == REQ_OP_SECURE_ERASE ||
-	       bio_op(bio) == REQ_OP_WRITE_ZEROES;
+	       bio_op(bio) == REQ_OP_WRITE_ZEROES ||
+	       bio_op(bio) == REQ_OP_PROVISION;
 }
 
 static inline void *bio_data(struct bio *bio)
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index d5c5e59ddbd2..e55828ddfafe 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -397,7 +397,10 @@ enum req_op {
 	REQ_OP_DRV_IN		= (__force blk_opf_t)34,
 	REQ_OP_DRV_OUT		= (__force blk_opf_t)35,
 
-	REQ_OP_LAST		= (__force blk_opf_t)36,
+	/* request device to provision block */
+	REQ_OP_PROVISION        = (__force blk_opf_t)37,
+
+	REQ_OP_LAST		= (__force blk_opf_t)38,
 };
 
 enum req_flag_bits {
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 51fa7ffdee83..c40f2b590e5d 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -308,6 +308,7 @@ struct queue_limits {
 	unsigned int		discard_granularity;
 	unsigned int		discard_alignment;
 	unsigned int		zone_write_granularity;
+	unsigned int		max_provision_sectors;
 
 	unsigned short		max_segments;
 	unsigned short		max_integrity_segments;
@@ -900,6 +901,8 @@ extern void blk_queue_max_discard_sectors(struct request_queue *q,
 		unsigned int max_discard_sectors);
 extern void blk_queue_max_write_zeroes_sectors(struct request_queue *q,
 		unsigned int max_write_same_sectors);
+extern void blk_queue_max_provision_sectors(struct request_queue *q,
+		unsigned int max_provision_sectors);
 extern void blk_queue_logical_block_size(struct request_queue *, unsigned int);
 extern void blk_queue_max_zone_append_sectors(struct request_queue *q,
 		unsigned int max_zone_append_sectors);
@@ -1038,6 +1041,9 @@ int __blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 int blkdev_issue_secure_erase(struct block_device *bdev, sector_t sector,
 		sector_t nr_sects, gfp_t gfp);
 
+extern int blkdev_issue_provision(struct block_device *bdev, sector_t sector,
+		sector_t nr_sects, gfp_t gfp_mask);
+
 #define BLKDEV_ZERO_NOUNMAP	(1 << 0)  /* do not free blocks */
 #define BLKDEV_ZERO_NOFALLBACK	(1 << 1)  /* don't write explicit zeroes */
 
@@ -1117,6 +1123,11 @@ static inline unsigned short queue_max_discard_segments(const struct request_que
 	return q->limits.max_discard_segments;
 }
 
+static inline unsigned short queue_max_provision_sectors(const struct request_queue *q)
+{
+	return q->limits.max_provision_sectors;
+}
+
 static inline unsigned int queue_max_segment_size(const struct request_queue *q)
 {
 	return q->limits.max_segment_size;
@@ -1259,6 +1270,11 @@ static inline bool bdev_nowait(struct block_device *bdev)
 	return test_bit(QUEUE_FLAG_NOWAIT, &bdev_get_queue(bdev)->queue_flags);
 }
 
+static inline unsigned int bdev_max_provision_sectors(struct block_device *bdev)
+{
+	return bdev_get_queue(bdev)->limits.max_provision_sectors;
+}
+
 static inline enum blk_zoned_model bdev_zoned_model(struct block_device *bdev)
 {
 	return blk_queue_zoned_model(bdev_get_queue(bdev));
-- 
2.39.2