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, 24 insertions, 26 deletions

diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index f55d4cc085f6..d1f948e371e0 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -901,13 +901,13 @@ static void flush_pending_writes(struct r10conf *conf)
 
 		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
@@ -1085,13 +1085,13 @@ static void raid10_unplug(struct blk_plug_cb *cb, bool from_schedule)
 
 	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
@@ -1200,7 +1200,7 @@ static void raid10_read_request(struct mddev *mddev, struct bio *bio,
 
 	read_bio->bi_iter.bi_sector = r10_bio->devs[slot].addr +
 		choose_data_offset(r10_bio, rdev);
-	read_bio->bi_bdev = rdev->bdev;
+	bio_set_dev(read_bio, rdev->bdev);
 	read_bio->bi_end_io = raid10_end_read_request;
 	bio_set_op_attrs(read_bio, op, do_sync);
 	if (test_bit(FailFast, &rdev->flags) &&
@@ -1209,7 +1209,7 @@ static void raid10_read_request(struct mddev *mddev, struct bio *bio,
 	read_bio->bi_private = r10_bio;
 
 	if (mddev->gendisk)
-	        trace_block_bio_remap(bdev_get_queue(read_bio->bi_bdev),
+	        trace_block_bio_remap(read_bio->bi_disk->queue,
 	                              read_bio, disk_devt(mddev->gendisk),
 	                              r10_bio->sector);
 	generic_make_request(read_bio);
@@ -1249,7 +1249,7 @@ static void raid10_write_one_disk(struct mddev *mddev, struct r10bio *r10_bio,
 
 	mbio->bi_iter.bi_sector	= (r10_bio->devs[n_copy].addr +
 				   choose_data_offset(r10_bio, rdev));
-	mbio->bi_bdev = rdev->bdev;
+	bio_set_dev(mbio, rdev->bdev);
 	mbio->bi_end_io	= raid10_end_write_request;
 	bio_set_op_attrs(mbio, op, do_sync | do_fua);
 	if (!replacement && test_bit(FailFast,
@@ -1259,11 +1259,11 @@ static void raid10_write_one_disk(struct mddev *mddev, struct r10bio *r10_bio,
 	mbio->bi_private = r10_bio;
 
 	if (conf->mddev->gendisk)
-		trace_block_bio_remap(bdev_get_queue(mbio->bi_bdev),
+		trace_block_bio_remap(mbio->bi_disk->queue,
 				      mbio, disk_devt(conf->mddev->gendisk),
 				      r10_bio->sector);
 	/* flush_pending_writes() needs access to the rdev so...*/
-	mbio->bi_bdev = (void *)rdev;
+	mbio->bi_disk = (void *)rdev;
 
 	atomic_inc(&r10_bio->remaining);
 
@@ -2094,7 +2094,7 @@ static void sync_request_write(struct mddev *mddev, struct r10bio *r10_bio)
 		if (test_bit(FailFast, &conf->mirrors[d].rdev->flags))
 			tbio->bi_opf |= MD_FAILFAST;
 		tbio->bi_iter.bi_sector += conf->mirrors[d].rdev->data_offset;
-		tbio->bi_bdev = conf->mirrors[d].rdev->bdev;
+		bio_set_dev(tbio, conf->mirrors[d].rdev->bdev);
 		generic_make_request(tbio);
 	}
 
@@ -2552,7 +2552,7 @@ static int narrow_write_error(struct r10bio *r10_bio, int i)
 		wsector = r10_bio->devs[i].addr + (sector - r10_bio->sector);
 		wbio->bi_iter.bi_sector = wsector +
 				   choose_data_offset(r10_bio, rdev);
-		wbio->bi_bdev = rdev->bdev;
+		bio_set_dev(wbio, rdev->bdev);
 		bio_set_op_attrs(wbio, REQ_OP_WRITE, 0);
 
 		if (submit_bio_wait(wbio) < 0)
@@ -2575,7 +2575,6 @@ static void handle_read_error(struct mddev *mddev, struct r10bio *r10_bio)
 	struct bio *bio;
 	struct r10conf *conf = mddev->private;
 	struct md_rdev *rdev = r10_bio->devs[slot].rdev;
-	dev_t bio_dev;
 	sector_t bio_last_sector;
 
 	/* we got a read error. Maybe the drive is bad.  Maybe just
@@ -2587,7 +2586,6 @@ static void handle_read_error(struct mddev *mddev, struct r10bio *r10_bio)
 	 * frozen.
 	 */
 	bio = r10_bio->devs[slot].bio;
-	bio_dev = bio->bi_bdev->bd_dev;
 	bio_last_sector = r10_bio->devs[slot].addr + rdev->data_offset + r10_bio->sectors;
 	bio_put(bio);
 	r10_bio->devs[slot].bio = NULL;
@@ -2950,7 +2948,7 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 
 	/* Again, very different code for resync and recovery.
 	 * Both must result in an r10bio with a list of bios that
-	 * have bi_end_io, bi_sector, bi_bdev set,
+	 * have bi_end_io, bi_sector, bi_disk set,
 	 * and bi_private set to the r10bio.
 	 * For recovery, we may actually create several r10bios
 	 * with 2 bios in each, that correspond to the bios in the main one.
@@ -3095,7 +3093,7 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 				from_addr = r10_bio->devs[j].addr;
 				bio->bi_iter.bi_sector = from_addr +
 					rdev->data_offset;
-				bio->bi_bdev = rdev->bdev;
+				bio_set_dev(bio, rdev->bdev);
 				atomic_inc(&rdev->nr_pending);
 				/* and we write to 'i' (if not in_sync) */
 
@@ -3117,7 +3115,7 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 					bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
 					bio->bi_iter.bi_sector = to_addr
 						+ mrdev->data_offset;
-					bio->bi_bdev = mrdev->bdev;
+					bio_set_dev(bio, mrdev->bdev);
 					atomic_inc(&r10_bio->remaining);
 				} else
 					r10_bio->devs[1].bio->bi_end_io = NULL;
@@ -3143,7 +3141,7 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 				bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
 				bio->bi_iter.bi_sector = to_addr +
 					mreplace->data_offset;
-				bio->bi_bdev = mreplace->bdev;
+				bio_set_dev(bio, mreplace->bdev);
 				atomic_inc(&r10_bio->remaining);
 				break;
 			}
@@ -3289,7 +3287,7 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 			if (test_bit(FailFast, &rdev->flags))
 				bio->bi_opf |= MD_FAILFAST;
 			bio->bi_iter.bi_sector = sector + rdev->data_offset;
-			bio->bi_bdev = rdev->bdev;
+			bio_set_dev(bio, rdev->bdev);
 			count++;
 
 			rdev = rcu_dereference(conf->mirrors[d].replacement);
@@ -3311,7 +3309,7 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 			if (test_bit(FailFast, &rdev->flags))
 				bio->bi_opf |= MD_FAILFAST;
 			bio->bi_iter.bi_sector = sector + rdev->data_offset;
-			bio->bi_bdev = rdev->bdev;
+			bio_set_dev(bio, rdev->bdev);
 			count++;
 			rcu_read_unlock();
 		}
@@ -3367,7 +3365,7 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 		r10_bio->sectors = nr_sectors;
 
 		if (bio->bi_end_io == end_sync_read) {
-			md_sync_acct(bio->bi_bdev, nr_sectors);
+			md_sync_acct_bio(bio, nr_sectors);
 			bio->bi_status = 0;
 			generic_make_request(bio);
 		}
@@ -4383,7 +4381,7 @@ read_more:
 
 	read_bio = bio_alloc_mddev(GFP_KERNEL, RESYNC_PAGES, mddev);
 
-	read_bio->bi_bdev = rdev->bdev;
+	bio_set_dev(read_bio, rdev->bdev);
 	read_bio->bi_iter.bi_sector = (r10_bio->devs[r10_bio->read_slot].addr
 			       + rdev->data_offset);
 	read_bio->bi_private = r10_bio;
@@ -4417,7 +4415,7 @@ read_more:
 		if (!rdev2 || test_bit(Faulty, &rdev2->flags))
 			continue;
 
-		b->bi_bdev = rdev2->bdev;
+		bio_set_dev(b, rdev2->bdev);
 		b->bi_iter.bi_sector = r10_bio->devs[s/2].addr +
 			rdev2->new_data_offset;
 		b->bi_end_io = end_reshape_write;
@@ -4449,7 +4447,7 @@ read_more:
 	r10_bio->sectors = nr_sectors;
 
 	/* Now submit the read */
-	md_sync_acct(read_bio->bi_bdev, r10_bio->sectors);
+	md_sync_acct_bio(read_bio, r10_bio->sectors);
 	atomic_inc(&r10_bio->remaining);
 	read_bio->bi_next = NULL;
 	generic_make_request(read_bio);
@@ -4511,7 +4509,7 @@ static void reshape_request_write(struct mddev *mddev, struct r10bio *r10_bio)
 		}
 		atomic_inc(&rdev->nr_pending);
 		rcu_read_unlock();
-		md_sync_acct(b->bi_bdev, r10_bio->sectors);
+		md_sync_acct_bio(b, r10_bio->sectors);
 		atomic_inc(&r10_bio->remaining);
 		b->bi_next = NULL;
 		generic_make_request(b);