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, 49 insertions, 51 deletions

diff --git a/block/blk-core.c b/block/blk-core.c
index d579501f24ba..fc1af9097dff 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -1910,40 +1910,15 @@ out_unlock:
 	return BLK_QC_T_NONE;
 }
 
-/*
- * If bio->bi_dev is a partition, remap the location
- */
-static inline void blk_partition_remap(struct bio *bio)
-{
-	struct block_device *bdev = bio->bi_bdev;
-
-	/*
-	 * Zone reset does not include bi_size so bio_sectors() is always 0.
-	 * Include a test for the reset op code and perform the remap if needed.
-	 */
-	if (bdev != bdev->bd_contains &&
-	    (bio_sectors(bio) || bio_op(bio) == REQ_OP_ZONE_RESET)) {
-		struct hd_struct *p = bdev->bd_part;
-
-		bio->bi_iter.bi_sector += p->start_sect;
-		bio->bi_bdev = bdev->bd_contains;
-
-		trace_block_bio_remap(bdev_get_queue(bio->bi_bdev), bio,
-				      bdev->bd_dev,
-				      bio->bi_iter.bi_sector - p->start_sect);
-	}
-}
-
 static void handle_bad_sector(struct bio *bio)
 {
 	char b[BDEVNAME_SIZE];
 
 	printk(KERN_INFO "attempt to access beyond end of device\n");
 	printk(KERN_INFO "%s: rw=%d, want=%Lu, limit=%Lu\n",
-			bdevname(bio->bi_bdev, b),
-			bio->bi_opf,
+			bio_devname(bio, b), bio->bi_opf,
 			(unsigned long long)bio_end_sector(bio),
-			(long long)(i_size_read(bio->bi_bdev->bd_inode) >> 9));
+			(long long)get_capacity(bio->bi_disk));
 }
 
 #ifdef CONFIG_FAIL_MAKE_REQUEST
@@ -1982,6 +1957,38 @@ static inline bool should_fail_request(struct hd_struct *part,
 #endif /* CONFIG_FAIL_MAKE_REQUEST */
 
 /*
+ * Remap block n of partition p to block n+start(p) of the disk.
+ */
+static inline int blk_partition_remap(struct bio *bio)
+{
+	struct hd_struct *p;
+	int ret = 0;
+
+	/*
+	 * Zone reset does not include bi_size so bio_sectors() is always 0.
+	 * Include a test for the reset op code and perform the remap if needed.
+	 */
+	if (!bio->bi_partno ||
+	    (!bio_sectors(bio) && bio_op(bio) != REQ_OP_ZONE_RESET))
+		return 0;
+
+	rcu_read_lock();
+	p = __disk_get_part(bio->bi_disk, bio->bi_partno);
+	if (likely(p && !should_fail_request(p, bio->bi_iter.bi_size))) {
+		bio->bi_iter.bi_sector += p->start_sect;
+		bio->bi_partno = 0;
+		trace_block_bio_remap(bio->bi_disk->queue, bio, part_devt(p),
+				bio->bi_iter.bi_sector - p->start_sect);
+	} else {
+		printk("%s: fail for partition %d\n", __func__, bio->bi_partno);
+		ret = -EIO;
+	}
+	rcu_read_unlock();
+
+	return ret;
+}
+
+/*
  * Check whether this bio extends beyond the end of the device.
  */
 static inline int bio_check_eod(struct bio *bio, unsigned int nr_sectors)
@@ -1992,7 +1999,7 @@ static inline int bio_check_eod(struct bio *bio, unsigned int nr_sectors)
 		return 0;
 
 	/* Test device or partition size, when known. */
-	maxsector = i_size_read(bio->bi_bdev->bd_inode) >> 9;
+	maxsector = get_capacity(bio->bi_disk);
 	if (maxsector) {
 		sector_t sector = bio->bi_iter.bi_sector;
 
@@ -2017,20 +2024,18 @@ generic_make_request_checks(struct bio *bio)
 	int nr_sectors = bio_sectors(bio);
 	blk_status_t status = BLK_STS_IOERR;
 	char b[BDEVNAME_SIZE];
-	struct hd_struct *part;
 
 	might_sleep();
 
 	if (bio_check_eod(bio, nr_sectors))
 		goto end_io;
 
-	q = bdev_get_queue(bio->bi_bdev);
+	q = bio->bi_disk->queue;
 	if (unlikely(!q)) {
 		printk(KERN_ERR
 		       "generic_make_request: Trying to access "
 			"nonexistent block-device %s (%Lu)\n",
-			bdevname(bio->bi_bdev, b),
-			(long long) bio->bi_iter.bi_sector);
+			bio_devname(bio, b), (long long)bio->bi_iter.bi_sector);
 		goto end_io;
 	}
 
@@ -2042,17 +2047,11 @@ generic_make_request_checks(struct bio *bio)
 	if ((bio->bi_opf & REQ_NOWAIT) && !queue_is_rq_based(q))
 		goto not_supported;
 
-	part = bio->bi_bdev->bd_part;
-	if (should_fail_request(part, bio->bi_iter.bi_size) ||
-	    should_fail_request(&part_to_disk(part)->part0,
-				bio->bi_iter.bi_size))
+	if (should_fail_request(&bio->bi_disk->part0, bio->bi_iter.bi_size))
 		goto end_io;
 
-	/*
-	 * If this device has partitions, remap block n
-	 * of partition p to block n+start(p) of the disk.
-	 */
-	blk_partition_remap(bio);
+	if (blk_partition_remap(bio))
+		goto end_io;
 
 	if (bio_check_eod(bio, nr_sectors))
 		goto end_io;
@@ -2081,16 +2080,16 @@ generic_make_request_checks(struct bio *bio)
 			goto not_supported;
 		break;
 	case REQ_OP_WRITE_SAME:
-		if (!bdev_write_same(bio->bi_bdev))
+		if (!q->limits.max_write_same_sectors)
 			goto not_supported;
 		break;
 	case REQ_OP_ZONE_REPORT:
 	case REQ_OP_ZONE_RESET:
-		if (!bdev_is_zoned(bio->bi_bdev))
+		if (!blk_queue_is_zoned(q))
 			goto not_supported;
 		break;
 	case REQ_OP_WRITE_ZEROES:
-		if (!bdev_write_zeroes_sectors(bio->bi_bdev))
+		if (!q->limits.max_write_zeroes_sectors)
 			goto not_supported;
 		break;
 	default:
@@ -2197,7 +2196,7 @@ blk_qc_t generic_make_request(struct bio *bio)
 	bio_list_init(&bio_list_on_stack[0]);
 	current->bio_list = bio_list_on_stack;
 	do {
-		struct request_queue *q = bdev_get_queue(bio->bi_bdev);
+		struct request_queue *q = bio->bi_disk->queue;
 
 		if (likely(blk_queue_enter(q, bio->bi_opf & REQ_NOWAIT) == 0)) {
 			struct bio_list lower, same;
@@ -2215,7 +2214,7 @@ blk_qc_t generic_make_request(struct bio *bio)
 			bio_list_init(&lower);
 			bio_list_init(&same);
 			while ((bio = bio_list_pop(&bio_list_on_stack[0])) != NULL)
-				if (q == bdev_get_queue(bio->bi_bdev))
+				if (q == bio->bi_disk->queue)
 					bio_list_add(&same, bio);
 				else
 					bio_list_add(&lower, bio);
@@ -2258,7 +2257,7 @@ blk_qc_t submit_bio(struct bio *bio)
 		unsigned int count;
 
 		if (unlikely(bio_op(bio) == REQ_OP_WRITE_SAME))
-			count = bdev_logical_block_size(bio->bi_bdev) >> 9;
+			count = queue_logical_block_size(bio->bi_disk->queue);
 		else
 			count = bio_sectors(bio);
 
@@ -2275,8 +2274,7 @@ blk_qc_t submit_bio(struct bio *bio)
 			current->comm, task_pid_nr(current),
 				op_is_write(bio_op(bio)) ? "WRITE" : "READ",
 				(unsigned long long)bio->bi_iter.bi_sector,
-				bdevname(bio->bi_bdev, b),
-				count);
+				bio_devname(bio, b), count);
 		}
 	}
 
@@ -3049,8 +3047,8 @@ void blk_rq_bio_prep(struct request_queue *q, struct request *rq,
 	rq->__data_len = bio->bi_iter.bi_size;
 	rq->bio = rq->biotail = bio;
 
-	if (bio->bi_bdev)
-		rq->rq_disk = bio->bi_bdev->bd_disk;
+	if (bio->bi_disk)
+		rq->rq_disk = bio->bi_disk;
 }
 
 #if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE