Add bvec_merge_data to handle stacked devices and ->merge_bvec()

When devices are stacked, one device's merge_bvec_fn may need to perform
the mapping and then call one or more functions for its underlying devices.

The following bio fields are used:
  bio->bi_sector
  bio->bi_bdev
  bio->bi_size
  bio->bi_rw  using bio_data_dir()

This patch creates a new struct bvec_merge_data holding a copy of those
fields to avoid having to change them directly in the struct bio when
going down the stack only to have to change them back again on the way
back up.  (And then when the bio gets mapped for real, the whole
exercise gets repeated, but that's a problem for another day...)

Signed-off-by: Alasdair G Kergon <agk@redhat.com>
Cc: Neil Brown <neilb@suse.de>
Cc: Milan Broz <mbroz@redhat.com>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>

drivers/block/pktcdvd.c

@@ -2633,11 +2633,12 @@ end_io:
 
 
 
-static int pkt_merge_bvec(struct request_queue *q, struct bio *bio, struct bio_vec *bvec)
+static int pkt_merge_bvec(struct request_queue *q, struct bvec_merge_data *bmd,
+			  struct bio_vec *bvec)
 {
 	struct pktcdvd_device *pd = q->queuedata;
-	sector_t zone = ZONE(bio->bi_sector, pd);
-	int used = ((bio->bi_sector - zone) << 9) + bio->bi_size;
+	sector_t zone = ZONE(bmd->bi_sector, pd);
+	int used = ((bmd->bi_sector - zone) << 9) + bmd->bi_size;
 	int remaining = (pd->settings.size << 9) - used;
 	int remaining2;
 
@@ -2645,7 +2646,7 @@ static int pkt_merge_bvec(struct request_queue *q, struct bio *bio, struct bio_v
 	 * A bio <= PAGE_SIZE must be allowed. If it crosses a packet
 	 * boundary, pkt_make_request() will split the bio.
 	 */
-	remaining2 = PAGE_SIZE - bio->bi_size;
+	remaining2 = PAGE_SIZE - bmd->bi_size;
 	remaining = max(remaining, remaining2);
 
 	BUG_ON(remaining < 0);

drivers/md/linear.c

@@ -50,17 +50,19 @@ static inline dev_info_t *which_dev(mddev_t *mddev, sector_t sector)
 /**
  *	linear_mergeable_bvec -- tell bio layer if two requests can be merged
  *	@q: request queue
- *	@bio: the buffer head that's been built up so far
+ *	@bvm: properties of new bio
  *	@biovec: the request that could be merged to it.
  *
  *	Return amount of bytes we can take at this offset
  */
-static int linear_mergeable_bvec(struct request_queue *q, struct bio *bio, struct bio_vec *biovec)
+static int linear_mergeable_bvec(struct request_queue *q,
+				 struct bvec_merge_data *bvm,
+				 struct bio_vec *biovec)
 {
 	mddev_t *mddev = q->queuedata;
 	dev_info_t *dev0;
-	unsigned long maxsectors, bio_sectors = bio->bi_size >> 9;
-	sector_t sector = bio->bi_sector + get_start_sect(bio->bi_bdev);
+	unsigned long maxsectors, bio_sectors = bvm->bi_size >> 9;
+	sector_t sector = bvm->bi_sector + get_start_sect(bvm->bi_bdev);
 
 	dev0 = which_dev(mddev, sector);
 	maxsectors = (dev0->size << 1) - (sector - (dev0->offset<<1));

drivers/md/raid0.c

@@ -241,18 +241,20 @@ static int create_strip_zones (mddev_t *mddev)
 /**
  *	raid0_mergeable_bvec -- tell bio layer if a two requests can be merged
  *	@q: request queue
- *	@bio: the buffer head that's been built up so far
+ *	@bvm: properties of new bio
  *	@biovec: the request that could be merged to it.
  *
  *	Return amount of bytes we can accept at this offset
  */
-static int raid0_mergeable_bvec(struct request_queue *q, struct bio *bio, struct bio_vec *biovec)
+static int raid0_mergeable_bvec(struct request_queue *q,
+				struct bvec_merge_data *bvm,
+				struct bio_vec *biovec)
 {
 	mddev_t *mddev = q->queuedata;
-	sector_t sector = bio->bi_sector + get_start_sect(bio->bi_bdev);
+	sector_t sector = bvm->bi_sector + get_start_sect(bvm->bi_bdev);
 	int max;
 	unsigned int chunk_sectors = mddev->chunk_size >> 9;
-	unsigned int bio_sectors = bio->bi_size >> 9;
+	unsigned int bio_sectors = bvm->bi_size >> 9;
 
 	max =  (chunk_sectors - ((sector & (chunk_sectors - 1)) + bio_sectors)) << 9;
 	if (max < 0) max = 0; /* bio_add cannot handle a negative return */

drivers/md/raid10.c

@@ -439,26 +439,27 @@ static sector_t raid10_find_virt(conf_t *conf, sector_t sector, int dev)
 /**
  *	raid10_mergeable_bvec -- tell bio layer if a two requests can be merged
  *	@q: request queue
- *	@bio: the buffer head that's been built up so far
+ *	@bvm: properties of new bio
  *	@biovec: the request that could be merged to it.
  *
  *	Return amount of bytes we can accept at this offset
  *      If near_copies == raid_disk, there are no striping issues,
  *      but in that case, the function isn't called at all.
  */
-static int raid10_mergeable_bvec(struct request_queue *q, struct bio *bio,
-				struct bio_vec *bio_vec)
+static int raid10_mergeable_bvec(struct request_queue *q,
+				 struct bvec_merge_data *bvm,
+				 struct bio_vec *biovec)
 {
 	mddev_t *mddev = q->queuedata;
-	sector_t sector = bio->bi_sector + get_start_sect(bio->bi_bdev);
+	sector_t sector = bvm->bi_sector + get_start_sect(bvm->bi_bdev);
 	int max;
 	unsigned int chunk_sectors = mddev->chunk_size >> 9;
-	unsigned int bio_sectors = bio->bi_size >> 9;
+	unsigned int bio_sectors = bvm->bi_size >> 9;
 
 	max =  (chunk_sectors - ((sector & (chunk_sectors - 1)) + bio_sectors)) << 9;
 	if (max < 0) max = 0; /* bio_add cannot handle a negative return */
-	if (max <= bio_vec->bv_len && bio_sectors == 0)
-		return bio_vec->bv_len;
+	if (max <= biovec->bv_len && bio_sectors == 0)
+		return biovec->bv_len;
 	else
 		return max;
 }

drivers/md/raid5.c

@@ -3319,15 +3319,17 @@ static int raid5_congested(void *data, int bits)
 /* We want read requests to align with chunks where possible,
  * but write requests don't need to.
  */
-static int raid5_mergeable_bvec(struct request_queue *q, struct bio *bio, struct bio_vec *biovec)
+static int raid5_mergeable_bvec(struct request_queue *q,
+				struct bvec_merge_data *bvm,
+				struct bio_vec *biovec)
 {
 	mddev_t *mddev = q->queuedata;
-	sector_t sector = bio->bi_sector + get_start_sect(bio->bi_bdev);
+	sector_t sector = bvm->bi_sector + get_start_sect(bvm->bi_bdev);
 	int max;
 	unsigned int chunk_sectors = mddev->chunk_size >> 9;
-	unsigned int bio_sectors = bio->bi_size >> 9;
+	unsigned int bio_sectors = bvm->bi_size >> 9;
 
-	if (bio_data_dir(bio) == WRITE)
+	if ((bvm->bi_rw & 1) == WRITE)
 		return biovec->bv_len; /* always allow writes to be mergeable */
 
 	max =  (chunk_sectors - ((sector & (chunk_sectors - 1)) + bio_sectors)) << 9;

fs/bio.c

@@ -325,10 +325,19 @@ static int __bio_add_page(struct request_queue *q, struct bio *bio, struct page
 		if (page == prev->bv_page &&
 		    offset == prev->bv_offset + prev->bv_len) {
 			prev->bv_len += len;
-			if (q->merge_bvec_fn &&
-			    q->merge_bvec_fn(q, bio, prev) < len) {
-				prev->bv_len -= len;
-				return 0;
+
+			if (q->merge_bvec_fn) {
+				struct bvec_merge_data bvm = {
+					.bi_bdev = bio->bi_bdev,
+					.bi_sector = bio->bi_sector,
+					.bi_size = bio->bi_size,
+					.bi_rw = bio->bi_rw,
+				};
+
+				if (q->merge_bvec_fn(q, &bvm, prev) < len) {
+					prev->bv_len -= len;
+					return 0;
+				}
 			}
 
 			goto done;
@@ -369,11 +378,18 @@ static int __bio_add_page(struct request_queue *q, struct bio *bio, struct page
 	 * queue to get further control
 	 */
 	if (q->merge_bvec_fn) {
+		struct bvec_merge_data bvm = {
+			.bi_bdev = bio->bi_bdev,
+			.bi_sector = bio->bi_sector,
+			.bi_size = bio->bi_size,
+			.bi_rw = bio->bi_rw,
+		};
+
 		/*
 		 * merge_bvec_fn() returns number of bytes it can accept
 		 * at this offset
 		 */
-		if (q->merge_bvec_fn(q, bio, bvec) < len) {
+		if (q->merge_bvec_fn(q, &bvm, bvec) < len) {
 			bvec->bv_page = NULL;
 			bvec->bv_len = 0;
 			bvec->bv_offset = 0;

include/linux/blkdev.h

@@ -254,7 +254,14 @@ typedef int (prep_rq_fn) (struct request_queue *, struct request *);
 typedef void (unplug_fn) (struct request_queue *);
 
 struct bio_vec;
-typedef int (merge_bvec_fn) (struct request_queue *, struct bio *, struct bio_vec *);
+struct bvec_merge_data {
+	struct block_device *bi_bdev;
+	sector_t bi_sector;
+	unsigned bi_size;
+	unsigned long bi_rw;
+};
+typedef int (merge_bvec_fn) (struct request_queue *, struct bvec_merge_data *,
+			     struct bio_vec *);
 typedef void (prepare_flush_fn) (struct request_queue *, struct request *);
 typedef void (softirq_done_fn)(struct request *);
 typedef int (dma_drain_needed_fn)(struct request *);