Re: Thin provisioning update

["Martin K. Petersen" <martin.petersen@oracle.com>]

>>>>> "Christoph" == Christoph Hellwig <hch@infradead.org> writes:

Christoph> So actually I'll take my previous comment back.  I think
Christoph> these patches are good enough to put them in now to have
Christoph> something we can build on.

Ok.  Jens, please queue the patch below.  And then we'll have to see
about getting James to rebase and/or postpone the SCSI portion to round
#2.


block: Expose discard granularity

While SSDs track block usage on a per-sector basis, RAID arrays often
have allocation blocks that are bigger.  Allow the discard granularity
and alignment to be set and teach the topology stacking logic how to
handle them.

Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>

diff --git a/block/blk-settings.c b/block/blk-settings.c
index 66d4aa8..7f986ca 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -96,7 +96,10 @@ void blk_set_default_limits(struct queue_limits *lim)
 	lim->max_segment_size = MAX_SEGMENT_SIZE;
 	lim->max_sectors = BLK_DEF_MAX_SECTORS;
 	lim->max_hw_sectors = INT_MAX;
-	lim->max_discard_sectors = SAFE_MAX_SECTORS;
+	lim->max_discard_sectors = 0;
+	lim->discard_granularity = 0;
+	lim->discard_alignment = 0;
+	lim->discard_misaligned = 0;
 	lim->logical_block_size = lim->physical_block_size = lim->io_min = 512;
 	lim->bounce_pfn = (unsigned long)(BLK_BOUNCE_ANY >> PAGE_SHIFT);
 	lim->alignment_offset = 0;
@@ -488,6 +491,16 @@ void blk_queue_stack_limits(struct request_queue *t, struct request_queue *b)
 }
 EXPORT_SYMBOL(blk_queue_stack_limits);
 
+static unsigned int lcm(unsigned int a, unsigned int b)
+{
+	if (a && b)
+		return (a * b) / gcd(a, b);
+	else if (b)
+		return b;
+
+	return a;
+}
+
 /**
  * blk_stack_limits - adjust queue_limits for stacked devices
  * @t:	the stacking driver limits (top)
@@ -502,6 +515,10 @@ EXPORT_SYMBOL(blk_queue_stack_limits);
 int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
 		     sector_t offset)
 {
+	int ret;
+
+	ret = 0;
+
 	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->bounce_pfn = min_not_zero(t->bounce_pfn, b->bounce_pfn);
@@ -531,7 +548,13 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
 	if (offset &&
 	    (offset & (b->physical_block_size - 1)) != b->alignment_offset) {
 		t->misaligned = 1;
-		return -1;
+		ret = -1;
+	}
+
+	if (offset &&
+	    (offset & (b->discard_granularity - 1)) != b->discard_alignment) {
+		t->discard_misaligned = 1;
+		ret = -1;
 	}
 
 	/* If top has no alignment offset, inherit from bottom */
@@ -539,23 +562,26 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
 		t->alignment_offset =
 			b->alignment_offset & (b->physical_block_size - 1);
 
+	if (!t->discard_alignment)
+		t->discard_alignment =
+			b->discard_alignment & (b->discard_granularity - 1);
+
 	/* Top device aligned on logical block boundary? */
 	if (t->alignment_offset & (t->logical_block_size - 1)) {
 		t->misaligned = 1;
-		return -1;
+		ret = -1;
 	}
 
-	/* Find lcm() of optimal I/O size */
-	if (t->io_opt && b->io_opt)
-		t->io_opt = (t->io_opt * b->io_opt) / gcd(t->io_opt, b->io_opt);
-	else if (b->io_opt)
-		t->io_opt = b->io_opt;
+	/* Find lcm() of optimal I/O size and granularity */
+	t->io_opt = lcm(t->io_opt, b->io_opt);
+	t->discard_granularity = lcm(t->discard_granularity,
+				     b->discard_granularity);
 
 	/* Verify that optimal I/O size is a multiple of io_min */
 	if (t->io_min && t->io_opt % t->io_min)
-		return -1;
+		ret = -1;
 
-	return 0;
+	return ret;
 }
 EXPORT_SYMBOL(blk_stack_limits);
 
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 8a6d81a..3147145 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -126,6 +126,16 @@ static ssize_t queue_io_opt_show(struct request_queue *q, char *page)
 	return queue_var_show(queue_io_opt(q), page);
 }
 
+static ssize_t queue_discard_granularity_show(struct request_queue *q, char *page)
+{
+	return queue_var_show(q->limits.discard_granularity, page);
+}
+
+static ssize_t queue_discard_max_show(struct request_queue *q, char *page)
+{
+	return queue_var_show(q->limits.max_discard_sectors << 9, page);
+}
+
 static ssize_t
 queue_max_sectors_store(struct request_queue *q, const char *page, size_t count)
 {
@@ -293,6 +303,16 @@ static struct queue_sysfs_entry queue_io_opt_entry = {
 	.show = queue_io_opt_show,
 };
 
+static struct queue_sysfs_entry queue_discard_granularity_entry = {
+	.attr = {.name = "discard_granularity", .mode = S_IRUGO },
+	.show = queue_discard_granularity_show,
+};
+
+static struct queue_sysfs_entry queue_discard_max_entry = {
+	.attr = {.name = "discard_max_bytes", .mode = S_IRUGO },
+	.show = queue_discard_max_show,
+};
+
 static struct queue_sysfs_entry queue_nonrot_entry = {
 	.attr = {.name = "rotational", .mode = S_IRUGO | S_IWUSR },
 	.show = queue_nonrot_show,
@@ -328,6 +348,8 @@ static struct attribute *default_attrs[] = {
 	&queue_physical_block_size_entry.attr,
 	&queue_io_min_entry.attr,
 	&queue_io_opt_entry.attr,
+	&queue_discard_granularity_entry.attr,
+	&queue_discard_max_entry.attr,
 	&queue_nonrot_entry.attr,
 	&queue_nomerges_entry.attr,
 	&queue_rq_affinity_entry.attr,
diff --git a/block/genhd.c b/block/genhd.c
index 517e433..b11a4ad 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -861,12 +861,23 @@ static ssize_t disk_alignment_offset_show(struct device *dev,
 	return sprintf(buf, "%d\n", queue_alignment_offset(disk->queue));
 }
 
+static ssize_t disk_discard_alignment_show(struct device *dev,
+					   struct device_attribute *attr,
+					   char *buf)
+{
+	struct gendisk *disk = dev_to_disk(dev);
+
+	return sprintf(buf, "%u\n", queue_discard_alignment(disk->queue));
+}
+
 static DEVICE_ATTR(range, S_IRUGO, disk_range_show, NULL);
 static DEVICE_ATTR(ext_range, S_IRUGO, disk_ext_range_show, NULL);
 static DEVICE_ATTR(removable, S_IRUGO, disk_removable_show, NULL);
 static DEVICE_ATTR(ro, S_IRUGO, disk_ro_show, NULL);
 static DEVICE_ATTR(size, S_IRUGO, part_size_show, NULL);
 static DEVICE_ATTR(alignment_offset, S_IRUGO, disk_alignment_offset_show, NULL);
+static DEVICE_ATTR(discard_alignment, S_IRUGO, disk_discard_alignment_show,
+		   NULL);
 static DEVICE_ATTR(capability, S_IRUGO, disk_capability_show, NULL);
 static DEVICE_ATTR(stat, S_IRUGO, part_stat_show, NULL);
 static DEVICE_ATTR(inflight, S_IRUGO, part_inflight_show, NULL);
@@ -887,6 +898,7 @@ static struct attribute *disk_attrs[] = {
 	&dev_attr_ro.attr,
 	&dev_attr_size.attr,
 	&dev_attr_alignment_offset.attr,
+	&dev_attr_discard_alignment.attr,
 	&dev_attr_capability.attr,
 	&dev_attr_stat.attr,
 	&dev_attr_inflight.attr,
diff --git a/fs/partitions/check.c b/fs/partitions/check.c
index 7b685e1..64bc899 100644
--- a/fs/partitions/check.c
+++ b/fs/partitions/check.c
@@ -226,6 +226,13 @@ ssize_t part_alignment_offset_show(struct device *dev,
 	return sprintf(buf, "%llu\n", (unsigned long long)p->alignment_offset);
 }
 
+ssize_t part_discard_alignment_show(struct device *dev,
+				   struct device_attribute *attr, char *buf)
+{
+	struct hd_struct *p = dev_to_part(dev);
+	return sprintf(buf, "%u\n", p->discard_alignment);
+}
+
 ssize_t part_stat_show(struct device *dev,
 		       struct device_attribute *attr, char *buf)
 {
@@ -288,6 +295,8 @@ static DEVICE_ATTR(partition, S_IRUGO, part_partition_show, NULL);
 static DEVICE_ATTR(start, S_IRUGO, part_start_show, NULL);
 static DEVICE_ATTR(size, S_IRUGO, part_size_show, NULL);
 static DEVICE_ATTR(alignment_offset, S_IRUGO, part_alignment_offset_show, NULL);
+static DEVICE_ATTR(discard_alignment, S_IRUGO, part_discard_alignment_show,
+		   NULL);
 static DEVICE_ATTR(stat, S_IRUGO, part_stat_show, NULL);
 static DEVICE_ATTR(inflight, S_IRUGO, part_inflight_show, NULL);
 #ifdef CONFIG_FAIL_MAKE_REQUEST
@@ -300,6 +309,7 @@ static struct attribute *part_attrs[] = {
 	&dev_attr_start.attr,
 	&dev_attr_size.attr,
 	&dev_attr_alignment_offset.attr,
+	&dev_attr_discard_alignment.attr,
 	&dev_attr_stat.attr,
 	&dev_attr_inflight.attr,
 #ifdef CONFIG_FAIL_MAKE_REQUEST
@@ -403,6 +413,8 @@ struct hd_struct *add_partition(struct gendisk *disk, int partno,
 
 	p->start_sect = start;
 	p->alignment_offset = queue_sector_alignment_offset(disk->queue, start);
+	p->discard_alignment = queue_sector_discard_alignment(disk->queue,
+							      start);
 	p->nr_sects = len;
 	p->partno = partno;
 	p->policy = get_disk_ro(disk);
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 221cecd..3b67221 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -312,12 +312,15 @@ struct queue_limits {
 	unsigned int		io_min;
 	unsigned int		io_opt;
 	unsigned int		max_discard_sectors;
+	unsigned int		discard_granularity;
+	unsigned int		discard_alignment;
 
 	unsigned short		logical_block_size;
 	unsigned short		max_hw_segments;
 	unsigned short		max_phys_segments;
 
 	unsigned char		misaligned;
+	unsigned char		discard_misaligned;
 	unsigned char		no_cluster;
 };
 
@@ -1134,6 +1137,21 @@ static inline int bdev_alignment_offset(struct block_device *bdev)
 	return q->limits.alignment_offset;
 }
 
+static inline int queue_discard_alignment(struct request_queue *q)
+{
+	if (q->limits.discard_misaligned)
+		return -1;
+
+	return q->limits.discard_alignment;
+}
+
+static inline int queue_sector_discard_alignment(struct request_queue *q,
+						 sector_t sector)
+{
+	return ((sector << 9) - q->limits.discard_alignment)
+		& (q->limits.discard_granularity - 1);
+}
+
 static inline int queue_dma_alignment(struct request_queue *q)
 {
 	return q ? q->dma_alignment : 511;
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index 297df45..c6c0c41 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -91,6 +91,7 @@ struct hd_struct {
 	sector_t start_sect;
 	sector_t nr_sects;
 	sector_t alignment_offset;
+	unsigned int discard_alignment;
 	struct device __dev;
 	struct kobject *holder_dir;
 	int policy, partno;