2 files changed, 34 insertions, 10 deletions

diff --git a/block/blk-lib.c b/block/blk-lib.c
index 16b06f62e68c..19cc761cacb2 100644
--- a/block/blk-lib.c
+++ b/block/blk-lib.c
@@ -44,7 +44,7 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
         struct request_queue *q = bdev_get_queue(bdev);
         int type = REQ_WRITE | REQ_DISCARD;
         unsigned int max_discard_sectors;
-        unsigned int granularity;
+        unsigned int granularity, alignment, mask;
         struct bio_batch bb;
         struct bio *bio;
         int ret = 0;
@@ -57,10 +57,12 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 
         /* Zero-sector (unknown) and one-sector granularities are the same.  */
         granularity = max(q->limits.discard_granularity >> 9, 1U);
+        mask = granularity - 1;
+        alignment = (bdev_discard_alignment(bdev) >> 9) & mask;
 
         /*
          * Ensure that max_discard_sectors is of the proper
-         * granularity
+         * granularity, so that requests stay aligned after a split.
          */
         max_discard_sectors = min(q->limits.max_discard_sectors, UINT_MAX >> 9);
         max_discard_sectors = round_down(max_discard_sectors, granularity);
@@ -80,25 +82,37 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
         bb.wait = &wait;
 
         while (nr_sects) {
+                unsigned int req_sects;
+                sector_t end_sect;
+
                 bio = bio_alloc(gfp_mask, 1);
                 if (!bio) {
                         ret = -ENOMEM;
                         break;
                 }
 
+                req_sects = min_t(sector_t, nr_sects, max_discard_sectors);
+
+                /*
+                 * If splitting a request, and the next starting sector would be
+                 * misaligned, stop the discard at the previous aligned sector.
+                 */
+                end_sect = sector + req_sects;
+                if (req_sects < nr_sects && (end_sect & mask) != alignment) {
+                        end_sect =
+                                round_down(end_sect - alignment, granularity)
+                                + alignment;
+                        req_sects = end_sect - sector;
+                }
+
                 bio->bi_sector = sector;
                 bio->bi_end_io = bio_batch_end_io;
                 bio->bi_bdev = bdev;
                 bio->bi_private = &bb;
 
-                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;
-                }
+                bio->bi_size = req_sects << 9;
+                nr_sects -= req_sects;
+                sector = end_sect;
 
                 atomic_inc(&bb.done);
                 submit_bio(type, bio);
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 4e72a9d48232..281516ae8b4e 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1139,6 +1139,16 @@ static inline int queue_limit_discard_alignment(struct queue_limits *lim, sector
                 & (lim->discard_granularity - 1);
 }
 
+static inline int bdev_discard_alignment(struct block_device *bdev)
+{
+        struct request_queue *q = bdev_get_queue(bdev);
+
+        if (bdev != bdev->bd_contains)
+                return bdev->bd_part->discard_alignment;
+
+        return q->limits.discard_alignment;
+}
+
 static inline unsigned int queue_discard_zeroes_data(struct request_queue *q)
 {
         if (q->limits.max_discard_sectors && q->limits.discard_zeroes_data == 1)