1 files changed, 160 insertions, 71 deletions

diff --git a/block/blk-merge.c b/block/blk-merge.c
index 71e9ac03f621..22467f475ab4 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -161,6 +161,73 @@ static inline unsigned get_max_io_size(struct request_queue *q,
 	return sectors;
 }
 
+static unsigned get_max_segment_size(struct request_queue *q,
+				     unsigned offset)
+{
+	unsigned long mask = queue_segment_boundary(q);
+
+	/* default segment boundary mask means no boundary limit */
+	if (mask == BLK_SEG_BOUNDARY_MASK)
+		return queue_max_segment_size(q);
+
+	return min_t(unsigned long, mask - (mask & offset) + 1,
+		     queue_max_segment_size(q));
+}
+
+/*
+ * Split the bvec @bv into segments, and update all kinds of
+ * variables.
+ */
+static bool bvec_split_segs(struct request_queue *q, struct bio_vec *bv,
+		unsigned *nsegs, unsigned *last_seg_size,
+		unsigned *front_seg_size, unsigned *sectors)
+{
+	unsigned len = bv->bv_len;
+	unsigned total_len = 0;
+	unsigned new_nsegs = 0, seg_size = 0;
+
+	/*
+	 * Multi-page bvec may be too big to hold in one segment, so the
+	 * current bvec has to be splitted as multiple segments.
+	 */
+	while (len && new_nsegs + *nsegs < queue_max_segments(q)) {
+		seg_size = get_max_segment_size(q, bv->bv_offset + total_len);
+		seg_size = min(seg_size, len);
+
+		new_nsegs++;
+		total_len += seg_size;
+		len -= seg_size;
+
+		if ((bv->bv_offset + total_len) & queue_virt_boundary(q))
+			break;
+	}
+
+	if (!new_nsegs)
+		return !!len;
+
+	/* update front segment size */
+	if (!*nsegs) {
+		unsigned first_seg_size;
+
+		if (new_nsegs == 1)
+			first_seg_size = get_max_segment_size(q, bv->bv_offset);
+		else
+			first_seg_size = queue_max_segment_size(q);
+
+		if (*front_seg_size < first_seg_size)
+			*front_seg_size = first_seg_size;
+	}
+
+	/* update other varibles */
+	*last_seg_size = seg_size;
+	*nsegs += new_nsegs;
+	if (sectors)
+		*sectors += total_len >> 9;
+
+	/* split in the middle of the bvec if len != 0 */
+	return !!len;
+}
+
 static struct bio *blk_bio_segment_split(struct request_queue *q,
 					 struct bio *bio,
 					 struct bio_set *bs,
@@ -174,7 +241,7 @@ static struct bio *blk_bio_segment_split(struct request_queue *q,
 	struct bio *new = NULL;
 	const unsigned max_sectors = get_max_io_size(q, bio);
 
-	bio_for_each_segment(bv, bio, iter) {
+	bio_for_each_bvec(bv, bio, iter) {
 		/*
 		 * If the queue doesn't support SG gaps and adding this
 		 * offset would create a gap, disallow it.
@@ -189,8 +256,12 @@ static struct bio *blk_bio_segment_split(struct request_queue *q,
 			 */
 			if (nsegs < queue_max_segments(q) &&
 			    sectors < max_sectors) {
-				nsegs++;
-				sectors = max_sectors;
+				/* split in the middle of bvec */
+				bv.bv_len = (max_sectors - sectors) << 9;
+				bvec_split_segs(q, &bv, &nsegs,
+						&seg_size,
+						&front_seg_size,
+						&sectors);
 			}
 			goto split;
 		}
@@ -206,21 +277,28 @@ static struct bio *blk_bio_segment_split(struct request_queue *q,
 			bvprvp = &bvprv;
 			sectors += bv.bv_len >> 9;
 
+			if (nsegs == 1 && seg_size > front_seg_size)
+				front_seg_size = seg_size;
+
 			continue;
 		}
 new_segment:
 		if (nsegs == queue_max_segments(q))
 			goto split;
 
-		if (nsegs == 1 && seg_size > front_seg_size)
-			front_seg_size = seg_size;
-
-		nsegs++;
 		bvprv = bv;
 		bvprvp = &bvprv;
-		seg_size = bv.bv_len;
-		sectors += bv.bv_len >> 9;
 
+		if (bv.bv_offset + bv.bv_len <= PAGE_SIZE) {
+			nsegs++;
+			seg_size = bv.bv_len;
+			sectors += bv.bv_len >> 9;
+			if (nsegs == 1 && seg_size > front_seg_size)
+				front_seg_size = seg_size;
+		} else if (bvec_split_segs(q, &bv, &nsegs, &seg_size,
+				    &front_seg_size, &sectors)) {
+			goto split;
+		}
 	}
 
 	do_split = false;
@@ -233,8 +311,6 @@ split:
 			bio = new;
 	}
 
-	if (nsegs == 1 && seg_size > front_seg_size)
-		front_seg_size = seg_size;
 	bio->bi_seg_front_size = front_seg_size;
 	if (seg_size > bio->bi_seg_back_size)
 		bio->bi_seg_back_size = seg_size;
@@ -291,18 +367,20 @@ void blk_queue_split(struct request_queue *q, struct bio **bio)
 EXPORT_SYMBOL(blk_queue_split);
 
 static unsigned int __blk_recalc_rq_segments(struct request_queue *q,
-					     struct bio *bio,
-					     bool no_sg_merge)
+					     struct bio *bio)
 {
 	struct bio_vec bv, bvprv = { NULL };
 	int prev = 0;
 	unsigned int seg_size, nr_phys_segs;
+	unsigned front_seg_size;
 	struct bio *fbio, *bbio;
 	struct bvec_iter iter;
 
 	if (!bio)
 		return 0;
 
+	front_seg_size = bio->bi_seg_front_size;
+
 	switch (bio_op(bio)) {
 	case REQ_OP_DISCARD:
 	case REQ_OP_SECURE_ERASE:
@@ -316,14 +394,7 @@ static unsigned int __blk_recalc_rq_segments(struct request_queue *q,
 	seg_size = 0;
 	nr_phys_segs = 0;
 	for_each_bio(bio) {
-		bio_for_each_segment(bv, bio, iter) {
-			/*
-			 * If SG merging is disabled, each bio vector is
-			 * a segment
-			 */
-			if (no_sg_merge)
-				goto new_segment;
-
+		bio_for_each_bvec(bv, bio, iter) {
 			if (prev) {
 				if (seg_size + bv.bv_len
 				    > queue_max_segment_size(q))
@@ -333,23 +404,23 @@ static unsigned int __blk_recalc_rq_segments(struct request_queue *q,
 
 				seg_size += bv.bv_len;
 				bvprv = bv;
+
+				if (nr_phys_segs == 1 && seg_size >
+						front_seg_size)
+					front_seg_size = seg_size;
+
 				continue;
 			}
 new_segment:
-			if (nr_phys_segs == 1 && seg_size >
-			    fbio->bi_seg_front_size)
-				fbio->bi_seg_front_size = seg_size;
-
-			nr_phys_segs++;
 			bvprv = bv;
 			prev = 1;
-			seg_size = bv.bv_len;
+			bvec_split_segs(q, &bv, &nr_phys_segs, &seg_size,
+					&front_seg_size, NULL);
 		}
 		bbio = bio;
 	}
 
-	if (nr_phys_segs == 1 && seg_size > fbio->bi_seg_front_size)
-		fbio->bi_seg_front_size = seg_size;
+	fbio->bi_seg_front_size = front_seg_size;
 	if (seg_size > bbio->bi_seg_back_size)
 		bbio->bi_seg_back_size = seg_size;
 
@@ -358,33 +429,16 @@ new_segment:
 
 void blk_recalc_rq_segments(struct request *rq)
 {
-	bool no_sg_merge = !!test_bit(QUEUE_FLAG_NO_SG_MERGE,
-			&rq->q->queue_flags);
-
-	rq->nr_phys_segments = __blk_recalc_rq_segments(rq->q, rq->bio,
-			no_sg_merge);
+	rq->nr_phys_segments = __blk_recalc_rq_segments(rq->q, rq->bio);
 }
 
 void blk_recount_segments(struct request_queue *q, struct bio *bio)
 {
-	unsigned short seg_cnt;
-
-	/* estimate segment number by bi_vcnt for non-cloned bio */
-	if (bio_flagged(bio, BIO_CLONED))
-		seg_cnt = bio_segments(bio);
-	else
-		seg_cnt = bio->bi_vcnt;
+	struct bio *nxt = bio->bi_next;
 
-	if (test_bit(QUEUE_FLAG_NO_SG_MERGE, &q->queue_flags) &&
-			(seg_cnt < queue_max_segments(q)))
-		bio->bi_phys_segments = seg_cnt;
-	else {
-		struct bio *nxt = bio->bi_next;
-
-		bio->bi_next = NULL;
-		bio->bi_phys_segments = __blk_recalc_rq_segments(q, bio, false);
-		bio->bi_next = nxt;
-	}
+	bio->bi_next = NULL;
+	bio->bi_phys_segments = __blk_recalc_rq_segments(q, bio);
+	bio->bi_next = nxt;
 
 	bio_set_flag(bio, BIO_SEG_VALID);
 }
@@ -407,6 +461,54 @@ static int blk_phys_contig_segment(struct request_queue *q, struct bio *bio,
 	return biovec_phys_mergeable(q, &end_bv, &nxt_bv);
 }
 
+static inline struct scatterlist *blk_next_sg(struct scatterlist **sg,
+		struct scatterlist *sglist)
+{
+	if (!*sg)
+		return sglist;
+
+	/*
+	 * 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_unmark_end(*sg);
+	return sg_next(*sg);
+}
+
+static unsigned blk_bvec_map_sg(struct request_queue *q,
+		struct bio_vec *bvec, struct scatterlist *sglist,
+		struct scatterlist **sg)
+{
+	unsigned nbytes = bvec->bv_len;
+	unsigned nsegs = 0, total = 0, offset = 0;
+
+	while (nbytes > 0) {
+		unsigned seg_size;
+		struct page *pg;
+		unsigned idx;
+
+		*sg = blk_next_sg(sg, sglist);
+
+		seg_size = get_max_segment_size(q, bvec->bv_offset + total);
+		seg_size = min(nbytes, seg_size);
+
+		offset = (total + bvec->bv_offset) % PAGE_SIZE;
+		idx = (total + bvec->bv_offset) / PAGE_SIZE;
+		pg = bvec_nth_page(bvec->bv_page, idx);
+
+		sg_set_page(*sg, pg, seg_size, offset);
+
+		total += seg_size;
+		nbytes -= seg_size;
+		nsegs++;
+	}
+
+	return nsegs;
+}
+
 static inline void
 __blk_segment_map_sg(struct request_queue *q, struct bio_vec *bvec,
 		     struct scatterlist *sglist, struct bio_vec *bvprv,
@@ -424,25 +526,12 @@ __blk_segment_map_sg(struct request_queue *q, struct bio_vec *bvec,
 		(*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_unmark_end(*sg);
-			*sg = sg_next(*sg);
-		}
-
-		sg_set_page(*sg, bvec->bv_page, nbytes, bvec->bv_offset);
-		(*nsegs)++;
+		if (bvec->bv_offset + bvec->bv_len <= PAGE_SIZE) {
+			*sg = blk_next_sg(sg, sglist);
+			sg_set_page(*sg, bvec->bv_page, nbytes, bvec->bv_offset);
+			(*nsegs) += 1;
+		} else
+			(*nsegs) += blk_bvec_map_sg(q, bvec, sglist, sg);
 	}
 	*bvprv = *bvec;
 }
@@ -464,7 +553,7 @@ static int __blk_bios_map_sg(struct request_queue *q, struct bio *bio,
 	int nsegs = 0;
 
 	for_each_bio(bio)
-		bio_for_each_segment(bvec, bio, iter)
+		bio_for_each_bvec(bvec, bio, iter)
 			__blk_segment_map_sg(q, &bvec, sglist, &bvprv, sg,
 					     &nsegs);