block: re-add discard_granularity and alignment checks

In commit b49a087("block: remove split code in
blkdev_issue_{discard,write_same}"), discard_granularity and alignment
checks were removed. Ideally, with bio late splitting, the upper layers
shouldn't need to depend on device's limits.

Christoph reported a discard regression on the HGST Ultrastar SN100 NVMe
device when mkfs.xfs. We have not found the root cause yet.

This patch re-adds discard_granularity and alignment checks by reverting
the related changes in commit b49a087. The good thing is now we can
remove the 2G discard size cap and just use UINT_MAX to avoid bi_size
overflow.

Reviewed-by: Christoph Hellwig <hch@lst.de>
Tested-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Ming Lin <ming.l@ssi.samsung.com>
Reviewed-by: Mike Snitzer <snitzer@redhat.com>
Signed-off-by: Jens Axboe <axboe@fb.com>

1 files changed, 22 insertions, 9 deletions

diff --git a/block/blk-lib.c b/block/blk-lib.c
index bd40292e5009..9ebf65379556 100644
--- a/block/blk-lib.c
+++ b/block/blk-lib.c
@@ -26,13 +26,6 @@ static void bio_batch_end_io(struct bio *bio)
         bio_put(bio);
 }
 
-/*
- * Ensure that max discard sectors doesn't overflow bi_size and hopefully
- * it is of the proper granularity as long as the granularity is a power
- * of two.
- */
-#define MAX_BIO_SECTORS ((1U << 31) >> 9)
-
 /**
  * blkdev_issue_discard - queue a discard
  * @bdev:       blockdev to issue discard for
@@ -50,6 +43,8 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
         DECLARE_COMPLETION_ONSTACK(wait);
         struct request_queue *q = bdev_get_queue(bdev);
         int type = REQ_WRITE | REQ_DISCARD;
+        unsigned int granularity;
+        int alignment;
         struct bio_batch bb;
         struct bio *bio;
         int ret = 0;
@@ -61,6 +56,10 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
         if (!blk_queue_discard(q))
                 return -EOPNOTSUPP;
 
+        /* Zero-sector (unknown) and one-sector granularities are the same.  */
+        granularity = max(q->limits.discard_granularity >> 9, 1U);
+        alignment = (bdev_discard_alignment(bdev) >> 9) % granularity;
+
         if (flags & BLKDEV_DISCARD_SECURE) {
                 if (!blk_queue_secdiscard(q))
                         return -EOPNOTSUPP;
@@ -74,7 +73,7 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
         blk_start_plug(&plug);
         while (nr_sects) {
                 unsigned int req_sects;
-                sector_t end_sect;
+                sector_t end_sect, tmp;
 
                 bio = bio_alloc(gfp_mask, 1);
                 if (!bio) {
@@ -82,8 +81,22 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
                         break;
                 }
 
-                req_sects = min_t(sector_t, nr_sects, MAX_BIO_SECTORS);
+                /* Make sure bi_size doesn't overflow */
+                req_sects = min_t(sector_t, nr_sects, UINT_MAX >> 9);
+
+                /*
+                 * 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;
+                tmp = end_sect;
+                if (req_sects < nr_sects &&
+                    sector_div(tmp, granularity) != alignment) {
+                        end_sect = end_sect - alignment;
+                        sector_div(end_sect, granularity);
+                        end_sect = end_sect * granularity + alignment;
+                        req_sects = end_sect - sector;
+                }
 
                 bio->bi_iter.bi_sector = sector;
                 bio->bi_end_io = bio_batch_end_io;