3 files changed, 111 insertions, 49 deletions

diff --git a/block/blk-lib.c b/block/blk-lib.c
index 2b461b496a78..19cc761cacb2 100644
--- a/block/blk-lib.c
+++ b/block/blk-lib.c
@@ -44,6 +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, alignment, mask;
         struct bio_batch bb;
         struct bio *bio;
         int ret = 0;
@@ -54,18 +55,20 @@ 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);
+        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);
         if (unlikely(!max_discard_sectors)) {
                 /* Avoid infinite loop below. Being cautious never hurts. */
                 return -EOPNOTSUPP;
-        } else if (q->limits.discard_granularity) {
-                unsigned int disc_sects = q->limits.discard_granularity >> 9;
-
-                max_discard_sectors &= ~(disc_sects - 1);
         }
 
         if (flags & BLKDEV_DISCARD_SECURE) {
@@ -79,25 +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/block/blk-merge.c b/block/blk-merge.c
index 160035f54882..e76279e41162 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -110,6 +110,49 @@ static int blk_phys_contig_segment(struct request_queue *q, struct bio *bio,
         return 0;
 }
 
+static void
+__blk_segment_map_sg(struct request_queue *q, struct bio_vec *bvec,
+                     struct scatterlist *sglist, struct bio_vec **bvprv,
+                     struct scatterlist **sg, int *nsegs, int *cluster)
+{
+
+        int nbytes = bvec->bv_len;
+
+        if (*bvprv && *cluster) {
+                if ((*sg)->length + nbytes > queue_max_segment_size(q))
+                        goto new_segment;
+
+                if (!BIOVEC_PHYS_MERGEABLE(*bvprv, bvec))
+                        goto new_segment;
+                if (!BIOVEC_SEG_BOUNDARY(q, *bvprv, bvec))
+                        goto new_segment;
+
+                (*sg)->length += nbytes;
+        } else {
+new_segment:
+                if (!*sg)
+                        *sg = sglist;
+                else {
+                        /*
+                         * If the driver previously mapped a shorter
+                         * list, we could see a termination bit
+                         * prematurely unless it fully inits the sg
+                         * table on each mapping. We KNOW that there
+                         * must be more entries here or the driver
+                         * would be buggy, so force clear the
+                         * termination bit to avoid doing a full
+                         * sg_init_table() in drivers for each command.
+                         */
+                        (*sg)->page_link &= ~0x02;
+                        *sg = sg_next(*sg);
+                }
+
+                sg_set_page(*sg, bvec->bv_page, nbytes, bvec->bv_offset);
+                (*nsegs)++;
+        }
+        *bvprv = bvec;
+}
+
 /*
  * map a request to scatterlist, return number of sg entries setup. Caller
  * must make sure sg can hold rq->nr_phys_segments entries
@@ -131,41 +174,8 @@ int blk_rq_map_sg(struct request_queue *q, struct request *rq,
         bvprv = NULL;
         sg = NULL;
         rq_for_each_segment(bvec, rq, iter) {
-                int nbytes = bvec->bv_len;
-
-                if (bvprv && cluster) {
-                        if (sg->length + nbytes > queue_max_segment_size(q))
-                                goto new_segment;
-
-                        if (!BIOVEC_PHYS_MERGEABLE(bvprv, bvec))
-                                goto new_segment;
-                        if (!BIOVEC_SEG_BOUNDARY(q, bvprv, bvec))
-                                goto new_segment;
-
-                        sg->length += nbytes;
-                } else {
-new_segment:
-                        if (!sg)
-                                sg = sglist;
-                        else {
-                                /*
-                                 * If the driver previously mapped a shorter
-                                 * list, we could see a termination bit
-                                 * prematurely unless it fully inits the sg
-                                 * table on each mapping. We KNOW that there
-                                 * must be more entries here or the driver
-                                 * would be buggy, so force clear the
-                                 * termination bit to avoid doing a full
-                                 * sg_init_table() in drivers for each command.
-                                 */
-                                sg->page_link &= ~0x02;
-                                sg = sg_next(sg);
-                        }
-
-                        sg_set_page(sg, bvec->bv_page, nbytes, bvec->bv_offset);
-                        nsegs++;
-                }
-                bvprv = bvec;
+                __blk_segment_map_sg(q, bvec, sglist, &bvprv, &sg,
+                                     &nsegs, &cluster);
         } /* segments in rq */
 
 
@@ -199,6 +209,43 @@ new_segment:
 }
 EXPORT_SYMBOL(blk_rq_map_sg);
 
+/**
+ * blk_bio_map_sg - map a bio to a scatterlist
+ * @q: request_queue in question
+ * @bio: bio being mapped
+ * @sglist: scatterlist being mapped
+ *
+ * Note:
+ *    Caller must make sure sg can hold bio->bi_phys_segments entries
+ *
+ * Will return the number of sg entries setup
+ */
+int blk_bio_map_sg(struct request_queue *q, struct bio *bio,
+                   struct scatterlist *sglist)
+{
+        struct bio_vec *bvec, *bvprv;
+        struct scatterlist *sg;
+        int nsegs, cluster;
+        unsigned long i;
+
+        nsegs = 0;
+        cluster = blk_queue_cluster(q);
+
+        bvprv = NULL;
+        sg = NULL;
+        bio_for_each_segment(bvec, bio, i) {
+                __blk_segment_map_sg(q, bvec, sglist, &bvprv, &sg,
+                                     &nsegs, &cluster);
+        } /* segments in bio */
+
+        if (sg)
+                sg_mark_end(sg);
+
+        BUG_ON(bio->bi_phys_segments && nsegs > bio->bi_phys_segments);
+        return nsegs;
+}
+EXPORT_SYMBOL(blk_bio_map_sg);
+
 static inline int ll_new_hw_segment(struct request_queue *q,
                                     struct request *req,
                                     struct bio *bio)
diff --git a/block/genhd.c b/block/genhd.c
index cac7366957c3..d839723303c8 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -835,7 +835,7 @@ static void disk_seqf_stop(struct seq_file *seqf, void *v)
 
 static void *show_partition_start(struct seq_file *seqf, loff_t *pos)
 {
-        static void *p;
+        void *p;
 
         p = disk_seqf_start(seqf, pos);
         if (!IS_ERR_OR_NULL(p) && !*pos)