block: replace bi_bdev with a gendisk pointer and partitions index

This way we don't need a block_device structure to submit I/O.  The
block_device has different life time rules from the gendisk and
request_queue and is usually only available when the block device node
is open.  Other callers need to explicitly create one (e.g. the lightnvm
passthrough code, or the new nvme multipathing code).

For the actual I/O path all that we need is the gendisk, which exists
once per block device.  But given that the block layer also does
partition remapping we additionally need a partition index, which is
used for said remapping in generic_make_request.

Note that all the block drivers generally want request_queue or
sometimes the gendisk, so this removes a layer of indirection all
over the stack.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

1 files changed, 15 insertions, 19 deletions

diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index f50958ded9f0..baf5e358d22a 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -786,13 +786,13 @@ static void flush_bio_list(struct r1conf *conf, struct bio *bio)
 
 	while (bio) { /* submit pending writes */
 		struct bio *next = bio->bi_next;
-		struct md_rdev *rdev = (void*)bio->bi_bdev;
+		struct md_rdev *rdev = (void *)bio->bi_disk;
 		bio->bi_next = NULL;
-		bio->bi_bdev = rdev->bdev;
+		bio_set_dev(bio, rdev->bdev);
 		if (test_bit(Faulty, &rdev->flags)) {
 			bio_io_error(bio);
 		} else if (unlikely((bio_op(bio) == REQ_OP_DISCARD) &&
-				    !blk_queue_discard(bdev_get_queue(bio->bi_bdev))))
+				    !blk_queue_discard(bio->bi_disk->queue)))
 			/* Just ignore it */
 			bio_endio(bio);
 		else
@@ -1273,7 +1273,7 @@ static void raid1_read_request(struct mddev *mddev, struct bio *bio,
 
 	read_bio->bi_iter.bi_sector = r1_bio->sector +
 		mirror->rdev->data_offset;
-	read_bio->bi_bdev = mirror->rdev->bdev;
+	bio_set_dev(read_bio, mirror->rdev->bdev);
 	read_bio->bi_end_io = raid1_end_read_request;
 	bio_set_op_attrs(read_bio, op, do_sync);
 	if (test_bit(FailFast, &mirror->rdev->flags) &&
@@ -1282,9 +1282,8 @@ static void raid1_read_request(struct mddev *mddev, struct bio *bio,
 	read_bio->bi_private = r1_bio;
 
 	if (mddev->gendisk)
-	        trace_block_bio_remap(bdev_get_queue(read_bio->bi_bdev),
-	                              read_bio, disk_devt(mddev->gendisk),
-	                              r1_bio->sector);
+	        trace_block_bio_remap(read_bio->bi_disk->queue, read_bio,
+				disk_devt(mddev->gendisk), r1_bio->sector);
 
 	generic_make_request(read_bio);
 }
@@ -1496,7 +1495,7 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 
 		mbio->bi_iter.bi_sector	= (r1_bio->sector +
 				   conf->mirrors[i].rdev->data_offset);
-		mbio->bi_bdev = conf->mirrors[i].rdev->bdev;
+		bio_set_dev(mbio, conf->mirrors[i].rdev->bdev);
 		mbio->bi_end_io	= raid1_end_write_request;
 		mbio->bi_opf = bio_op(bio) | (bio->bi_opf & (REQ_SYNC | REQ_FUA));
 		if (test_bit(FailFast, &conf->mirrors[i].rdev->flags) &&
@@ -1508,11 +1507,11 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 		atomic_inc(&r1_bio->remaining);
 
 		if (mddev->gendisk)
-			trace_block_bio_remap(bdev_get_queue(mbio->bi_bdev),
+			trace_block_bio_remap(mbio->bi_disk->queue,
 					      mbio, disk_devt(mddev->gendisk),
 					      r1_bio->sector);
 		/* flush_pending_writes() needs access to the rdev so...*/
-		mbio->bi_bdev = (void*)conf->mirrors[i].rdev;
+		mbio->bi_disk = (void *)conf->mirrors[i].rdev;
 
 		cb = blk_check_plugged(raid1_unplug, mddev, sizeof(*plug));
 		if (cb)
@@ -1990,8 +1989,7 @@ static int fix_sync_read_error(struct r1bio *r1_bio)
 			 * Don't fail devices as that won't really help.
 			 */
 			pr_crit_ratelimited("md/raid1:%s: %s: unrecoverable I/O read error for block %llu\n",
-					    mdname(mddev),
-					    bdevname(bio->bi_bdev, b),
+					    mdname(mddev), bio_devname(bio, b),
 					    (unsigned long long)r1_bio->sector);
 			for (d = 0; d < conf->raid_disks * 2; d++) {
 				rdev = conf->mirrors[d].rdev;
@@ -2082,7 +2080,7 @@ static void process_checks(struct r1bio *r1_bio)
 		b->bi_status = status;
 		b->bi_iter.bi_sector = r1_bio->sector +
 			conf->mirrors[i].rdev->data_offset;
-		b->bi_bdev = conf->mirrors[i].rdev->bdev;
+		bio_set_dev(b, conf->mirrors[i].rdev->bdev);
 		b->bi_end_io = end_sync_read;
 		rp->raid_bio = r1_bio;
 		b->bi_private = rp;
@@ -2350,7 +2348,7 @@ static int narrow_write_error(struct r1bio *r1_bio, int i)
 
 		bio_trim(wbio, sector - r1_bio->sector, sectors);
 		wbio->bi_iter.bi_sector += rdev->data_offset;
-		wbio->bi_bdev = rdev->bdev;
+		bio_set_dev(wbio, rdev->bdev);
 
 		if (submit_bio_wait(wbio) < 0)
 			/* failure! */
@@ -2440,7 +2438,6 @@ static void handle_read_error(struct r1conf *conf, struct r1bio *r1_bio)
 	struct mddev *mddev = conf->mddev;
 	struct bio *bio;
 	struct md_rdev *rdev;
-	dev_t bio_dev;
 	sector_t bio_sector;
 
 	clear_bit(R1BIO_ReadError, &r1_bio->state);
@@ -2454,7 +2451,6 @@ static void handle_read_error(struct r1conf *conf, struct r1bio *r1_bio)
 	 */
 
 	bio = r1_bio->bios[r1_bio->read_disk];
-	bio_dev = bio->bi_bdev->bd_dev;
 	bio_sector = conf->mirrors[r1_bio->read_disk].rdev->data_offset + r1_bio->sector;
 	bio_put(bio);
 	r1_bio->bios[r1_bio->read_disk] = NULL;
@@ -2727,7 +2723,7 @@ static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr,
 		if (bio->bi_end_io) {
 			atomic_inc(&rdev->nr_pending);
 			bio->bi_iter.bi_sector = sector_nr + rdev->data_offset;
-			bio->bi_bdev = rdev->bdev;
+			bio_set_dev(bio, rdev->bdev);
 			if (test_bit(FailFast, &rdev->flags))
 				bio->bi_opf |= MD_FAILFAST;
 		}
@@ -2853,7 +2849,7 @@ static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr,
 			bio = r1_bio->bios[i];
 			if (bio->bi_end_io == end_sync_read) {
 				read_targets--;
-				md_sync_acct(bio->bi_bdev, nr_sectors);
+				md_sync_acct_bio(bio, nr_sectors);
 				if (read_targets == 1)
 					bio->bi_opf &= ~MD_FAILFAST;
 				generic_make_request(bio);
@@ -2862,7 +2858,7 @@ static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr,
 	} else {
 		atomic_set(&r1_bio->remaining, 1);
 		bio = r1_bio->bios[r1_bio->read_disk];
-		md_sync_acct(bio->bi_bdev, nr_sectors);
+		md_sync_acct_bio(bio, nr_sectors);
 		if (read_targets == 1)
 			bio->bi_opf &= ~MD_FAILFAST;
 		generic_make_request(bio);