block: allow large discard requests

Currently we set the bio size to the byte equivalent of the blocks to
be trimmed when submitting the initial DISCARD ioctl.  That means it
is subject to the max_hw_sectors limitation of the HBA which is
much lower than the size of a DISCARD request we can support.
Add a separate max_discard_sectors tunable to limit the size for discard
requests.

We limit the max discard request size in bytes to 32bit as that is the
limit for bio->bi_size.  This could be much larger if we had a way to pass
that information through the block layer.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>

4 files changed, 24 insertions, 5 deletions

diff --git a/block/blk-barrier.c b/block/blk-barrier.c
index 21f5025c394..8873b9b439f 100644
--- a/block/blk-barrier.c
+++ b/block/blk-barrier.c
@@ -385,6 +385,8 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 
 	while (nr_sects && !ret) {
 		unsigned int sector_size = q->limits.logical_block_size;
+		unsigned int max_discard_sectors =
+			min(q->limits.max_discard_sectors, UINT_MAX >> 9);
 
 		bio = bio_alloc(gfp_mask, 1);
 		if (!bio)
@@ -411,10 +413,10 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 		 * touch many more blocks on disk than the actual payload
 		 * length.
 		 */
-		if (nr_sects > queue_max_hw_sectors(q)) {
-			bio->bi_size = queue_max_hw_sectors(q) << 9;
-			nr_sects -= queue_max_hw_sectors(q);
-			sector += queue_max_hw_sectors(q);
+		if (nr_sects > max_discard_sectors) {
+			bio->bi_size = max_discard_sectors << 9;
+			nr_sects -= max_discard_sectors;
+			sector += max_discard_sectors;
 		} else {
 			bio->bi_size = nr_sects << 9;
 			nr_sects = 0;
diff --git a/block/blk-core.c b/block/blk-core.c
index 80a020dd158..34504f30972 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -1436,7 +1436,8 @@ static inline void __generic_make_request(struct bio *bio)
 			goto end_io;
 		}
 
-		if (unlikely(nr_sectors > queue_max_hw_sectors(q))) {
+		if (unlikely(!bio_rw_flagged(bio, BIO_RW_DISCARD) &&
+			     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),
diff --git a/block/blk-settings.c b/block/blk-settings.c
index d29498ef1eb..e0695bca702 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -96,6 +96,7 @@ 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->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;
@@ -239,6 +240,18 @@ void blk_queue_max_hw_sectors(struct request_queue *q, unsigned int max_sectors)
 EXPORT_SYMBOL(blk_queue_max_hw_sectors);
 
 /**
+ * blk_queue_max_discard_sectors - set max sectors for a single discard
+ * @q:  the request queue for the device
+ * @max_discard: maximum number of sectors to discard
+ **/
+void blk_queue_max_discard_sectors(struct request_queue *q,
+		unsigned int max_discard_sectors)
+{
+	q->limits.max_discard_sectors = max_discard_sectors;
+}
+EXPORT_SYMBOL(blk_queue_max_discard_sectors);
+
+/**
  * blk_queue_max_phys_segments - set max phys segments for a request for this queue
  * @q:  the request queue for the device
  * @max_segments:  max number of segments
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index f62d45e8761..1a03b715dfa 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -311,6 +311,7 @@ struct queue_limits {
 	unsigned int		alignment_offset;
 	unsigned int		io_min;
 	unsigned int		io_opt;
+	unsigned int		max_discard_sectors;
 
 	unsigned short		logical_block_size;
 	unsigned short		max_hw_segments;
@@ -928,6 +929,8 @@ extern void blk_queue_max_hw_sectors(struct request_queue *, unsigned int);
 extern void blk_queue_max_phys_segments(struct request_queue *, unsigned short);
 extern void blk_queue_max_hw_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_logical_block_size(struct request_queue *, unsigned short);
 extern void blk_queue_physical_block_size(struct request_queue *, unsigned short);
 extern void blk_queue_alignment_offset(struct request_queue *q,