block: switch partition lookup to use struct block_device

Use struct block_device to lookup partitions on a disk.  This removes
all usage of struct hd_struct from the I/O path.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jan Kara <jack@suse.cz>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Acked-by: Coly Li <colyli@suse.de>			[bcache]
Acked-by: Chao Yu <yuchao0@huawei.com>			[f2fs]
Signed-off-by: Jens Axboe <axboe@kernel.dk>

8 files changed, 78 insertions, 78 deletions

diff --git a/block/bio.c b/block/bio.c
index 669bb47a3198..ebb18136b86f 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -608,12 +608,12 @@ void bio_truncate(struct bio *bio, unsigned new_size)
 void guard_bio_eod(struct bio *bio)
 {
 	sector_t maxsector;
-	struct hd_struct *part;
+	struct block_device *part;
 
 	rcu_read_lock();
 	part = __disk_get_part(bio->bi_disk, bio->bi_partno);
 	if (part)
-		maxsector = bdev_nr_sectors(part->bdev);
+		maxsector = bdev_nr_sectors(part);
 	else	
 		maxsector = get_capacity(bio->bi_disk);
 	rcu_read_unlock();
diff --git a/block/blk-core.c b/block/blk-core.c
index 9ea70275fc1c..cee568389b7e 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -666,10 +666,9 @@ static int __init setup_fail_make_request(char *str)
 }
 __setup("fail_make_request=", setup_fail_make_request);
 
-static bool should_fail_request(struct hd_struct *part, unsigned int bytes)
+static bool should_fail_request(struct block_device *part, unsigned int bytes)
 {
-	return part->bdev->bd_make_it_fail &&
-		should_fail(&fail_make_request, bytes);
+	return part->bd_make_it_fail && should_fail(&fail_make_request, bytes);
 }
 
 static int __init fail_make_request_debugfs(void)
@@ -684,7 +683,7 @@ late_initcall(fail_make_request_debugfs);
 
 #else /* CONFIG_FAIL_MAKE_REQUEST */
 
-static inline bool should_fail_request(struct hd_struct *part,
+static inline bool should_fail_request(struct block_device *part,
 					unsigned int bytes)
 {
 	return false;
@@ -692,11 +691,11 @@ static inline bool should_fail_request(struct hd_struct *part,
 
 #endif /* CONFIG_FAIL_MAKE_REQUEST */
 
-static inline bool bio_check_ro(struct bio *bio, struct hd_struct *part)
+static inline bool bio_check_ro(struct bio *bio, struct block_device *part)
 {
 	const int op = bio_op(bio);
 
-	if (part->bdev->bd_read_only && op_is_write(op)) {
+	if (part->bd_read_only && op_is_write(op)) {
 		char b[BDEVNAME_SIZE];
 
 		if (op_is_flush(bio->bi_opf) && !bio_sectors(bio))
@@ -704,7 +703,7 @@ static inline bool bio_check_ro(struct bio *bio, struct hd_struct *part)
 
 		WARN_ONCE(1,
 		       "Trying to write to read-only block-device %s (partno %d)\n",
-			bio_devname(bio, b), part->partno);
+			bio_devname(bio, b), part->bd_partno);
 		/* Older lvm-tools actually trigger this */
 		return false;
 	}
@@ -714,8 +713,7 @@ static inline bool bio_check_ro(struct bio *bio, struct hd_struct *part)
 
 static noinline int should_fail_bio(struct bio *bio)
 {
-	if (should_fail_request(bio->bi_disk->part0->bd_part,
-			bio->bi_iter.bi_size))
+	if (should_fail_request(bio->bi_disk->part0, bio->bi_iter.bi_size))
 		return -EIO;
 	return 0;
 }
@@ -744,7 +742,7 @@ static inline int bio_check_eod(struct bio *bio, sector_t maxsector)
  */
 static inline int blk_partition_remap(struct bio *bio)
 {
-	struct hd_struct *p;
+	struct block_device *p;
 	int ret = -EIO;
 
 	rcu_read_lock();
@@ -757,12 +755,12 @@ static inline int blk_partition_remap(struct bio *bio)
 		goto out;
 
 	if (bio_sectors(bio)) {
-		if (bio_check_eod(bio, bdev_nr_sectors(p->bdev)))
+		if (bio_check_eod(bio, bdev_nr_sectors(p)))
 			goto out;
-		bio->bi_iter.bi_sector += p->bdev->bd_start_sect;
-		trace_block_bio_remap(bio->bi_disk->queue, bio, part_devt(p),
+		bio->bi_iter.bi_sector += p->bd_start_sect;
+		trace_block_bio_remap(bio->bi_disk->queue, bio, p->bd_dev,
 				      bio->bi_iter.bi_sector -
-				      p->bdev->bd_start_sect);
+				      p->bd_start_sect);
 	}
 	bio->bi_partno = 0;
 	ret = 0;
@@ -832,7 +830,7 @@ static noinline_for_stack bool submit_bio_checks(struct bio *bio)
 		if (unlikely(blk_partition_remap(bio)))
 			goto end_io;
 	} else {
-		if (unlikely(bio_check_ro(bio, bio->bi_disk->part0->bd_part)))
+		if (unlikely(bio_check_ro(bio, bio->bi_disk->part0)))
 			goto end_io;
 		if (unlikely(bio_check_eod(bio, get_capacity(bio->bi_disk))))
 			goto end_io;
@@ -1204,7 +1202,7 @@ blk_status_t blk_insert_cloned_request(struct request_queue *q, struct request *
 		return ret;
 
 	if (rq->rq_disk &&
-	    should_fail_request(rq->rq_disk->part0->bd_part, blk_rq_bytes(rq)))
+	    should_fail_request(rq->rq_disk->part0, blk_rq_bytes(rq)))
 		return BLK_STS_IOERR;
 
 	if (blk_crypto_insert_cloned_request(rq))
@@ -1263,17 +1261,18 @@ unsigned int blk_rq_err_bytes(const struct request *rq)
 }
 EXPORT_SYMBOL_GPL(blk_rq_err_bytes);
 
-static void update_io_ticks(struct hd_struct *part, unsigned long now, bool end)
+static void update_io_ticks(struct block_device *part, unsigned long now,
+		bool end)
 {
 	unsigned long stamp;
 again:
-	stamp = READ_ONCE(part->bdev->bd_stamp);
+	stamp = READ_ONCE(part->bd_stamp);
 	if (unlikely(stamp != now)) {
-		if (likely(cmpxchg(&part->bdev->bd_stamp, stamp, now) == stamp))
+		if (likely(cmpxchg(&part->bd_stamp, stamp, now) == stamp))
 			__part_stat_add(part, io_ticks, end ? now - stamp : 1);
 	}
-	if (part->partno) {
-		part = part_to_disk(part)->part0->bd_part;
+	if (part->bd_partno) {
+		part = bdev_whole(part);
 		goto again;
 	}
 }
@@ -1282,11 +1281,9 @@ static void blk_account_io_completion(struct request *req, unsigned int bytes)
 {
 	if (req->part && blk_do_io_stat(req)) {
 		const int sgrp = op_stat_group(req_op(req));
-		struct hd_struct *part;
 
 		part_stat_lock();
-		part = req->part;
-		part_stat_add(part, sectors[sgrp], bytes >> 9);
+		part_stat_add(req->part, sectors[sgrp], bytes >> 9);
 		part_stat_unlock();
 	}
 }
@@ -1301,14 +1298,11 @@ void blk_account_io_done(struct request *req, u64 now)
 	if (req->part && blk_do_io_stat(req) &&
 	    !(req->rq_flags & RQF_FLUSH_SEQ)) {
 		const int sgrp = op_stat_group(req_op(req));
-		struct hd_struct *part;
 
 		part_stat_lock();
-		part = req->part;
-
-		update_io_ticks(part, jiffies, true);
-		part_stat_inc(part, ios[sgrp]);
-		part_stat_add(part, nsecs[sgrp], now - req->start_time_ns);
+		update_io_ticks(req->part, jiffies, true);
+		part_stat_inc(req->part, ios[sgrp]);
+		part_stat_add(req->part, nsecs[sgrp], now - req->start_time_ns);
 		part_stat_unlock();
 	}
 }
@@ -1325,7 +1319,7 @@ void blk_account_io_start(struct request *rq)
 	part_stat_unlock();
 }
 
-static unsigned long __part_start_io_acct(struct hd_struct *part,
+static unsigned long __part_start_io_acct(struct block_device *part,
 					  unsigned int sectors, unsigned int op)
 {
 	const int sgrp = op_stat_group(op);
@@ -1341,7 +1335,7 @@ static unsigned long __part_start_io_acct(struct hd_struct *part,
 	return now;
 }
 
-unsigned long part_start_io_acct(struct gendisk *disk, struct hd_struct **part,
+unsigned long part_start_io_acct(struct gendisk *disk, struct block_device **part,
 				 struct bio *bio)
 {
 	*part = disk_map_sector_rcu(disk, bio->bi_iter.bi_sector);
@@ -1353,11 +1347,11 @@ EXPORT_SYMBOL_GPL(part_start_io_acct);
 unsigned long disk_start_io_acct(struct gendisk *disk, unsigned int sectors,
 				 unsigned int op)
 {
-	return __part_start_io_acct(disk->part0->bd_part, sectors, op);
+	return __part_start_io_acct(disk->part0, sectors, op);
 }
 EXPORT_SYMBOL(disk_start_io_acct);
 
-static void __part_end_io_acct(struct hd_struct *part, unsigned int op,
+static void __part_end_io_acct(struct block_device *part, unsigned int op,
 			       unsigned long start_time)
 {
 	const int sgrp = op_stat_group(op);
@@ -1371,7 +1365,7 @@ static void __part_end_io_acct(struct hd_struct *part, unsigned int op,
 	part_stat_unlock();
 }
 
-void part_end_io_acct(struct hd_struct *part, struct bio *bio,
+void part_end_io_acct(struct block_device *part, struct bio *bio,
 		      unsigned long start_time)
 {
 	__part_end_io_acct(part, bio_op(bio), start_time);
@@ -1381,7 +1375,7 @@ EXPORT_SYMBOL_GPL(part_end_io_acct);
 void disk_end_io_acct(struct gendisk *disk, unsigned int op,
 		      unsigned long start_time)
 {
-	__part_end_io_acct(disk->part0->bd_part, op, start_time);
+	__part_end_io_acct(disk->part0, op, start_time);
 }
 EXPORT_SYMBOL(disk_end_io_acct);
 
diff --git a/block/blk-flush.c b/block/blk-flush.c
index fcd0a60574df..9507dcdd5881 100644
--- a/block/blk-flush.c
+++ b/block/blk-flush.c
@@ -139,7 +139,7 @@ static void blk_flush_queue_rq(struct request *rq, bool add_front)
 
 static void blk_account_io_flush(struct request *rq)
 {
-	struct hd_struct *part = rq->rq_disk->part0->bd_part;
+	struct block_device *part = rq->rq_disk->part0;
 
 	part_stat_lock();
 	part_stat_inc(part, ios[STAT_FLUSH]);
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 55bcee5dc032..a2593748fa53 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -95,7 +95,7 @@ static void blk_mq_hctx_clear_pending(struct blk_mq_hw_ctx *hctx,
 }
 
 struct mq_inflight {
-	struct hd_struct *part;
+	struct block_device *part;
 	unsigned int inflight[2];
 };
 
@@ -111,7 +111,8 @@ static bool blk_mq_check_inflight(struct blk_mq_hw_ctx *hctx,
 	return true;
 }
 
-unsigned int blk_mq_in_flight(struct request_queue *q, struct hd_struct *part)
+unsigned int blk_mq_in_flight(struct request_queue *q,
+		struct block_device *part)
 {
 	struct mq_inflight mi = { .part = part };
 
@@ -120,8 +121,8 @@ unsigned int blk_mq_in_flight(struct request_queue *q, struct hd_struct *part)
 	return mi.inflight[0] + mi.inflight[1];
 }
 
-void blk_mq_in_flight_rw(struct request_queue *q, struct hd_struct *part,
-			 unsigned int inflight[2])
+void blk_mq_in_flight_rw(struct request_queue *q, struct block_device *part,
+		unsigned int inflight[2])
 {
 	struct mq_inflight mi = { .part = part };
 
diff --git a/block/blk-mq.h b/block/blk-mq.h
index a52703c98b77..c696515766c7 100644
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -182,9 +182,10 @@ static inline bool blk_mq_hw_queue_mapped(struct blk_mq_hw_ctx *hctx)
 	return hctx->nr_ctx && hctx->tags;
 }
 
-unsigned int blk_mq_in_flight(struct request_queue *q, struct hd_struct *part);
-void blk_mq_in_flight_rw(struct request_queue *q, struct hd_struct *part,
-			 unsigned int inflight[2]);
+unsigned int blk_mq_in_flight(struct request_queue *q,
+		struct block_device *part);
+void blk_mq_in_flight_rw(struct request_queue *q, struct block_device *part,
+		unsigned int inflight[2]);
 
 static inline void blk_mq_put_dispatch_budget(struct request_queue *q)
 {
diff --git a/block/blk.h b/block/blk.h
index 32ac41f7557f..d5bf8f3a0781 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -215,7 +215,7 @@ static inline void elevator_exit(struct request_queue *q,
 	__elevator_exit(q, e);
 }
 
-struct hd_struct *__disk_get_part(struct gendisk *disk, int partno);
+struct block_device *__disk_get_part(struct gendisk *disk, int partno);
 
 ssize_t part_size_show(struct device *dev, struct device_attribute *attr,
 		char *buf);
@@ -348,7 +348,7 @@ void blk_queue_free_zone_bitmaps(struct request_queue *q);
 static inline void blk_queue_free_zone_bitmaps(struct request_queue *q) {}
 #endif
 
-struct hd_struct *disk_map_sector_rcu(struct gendisk *disk, sector_t sector);
+struct block_device *disk_map_sector_rcu(struct gendisk *disk, sector_t sector);
 
 int blk_alloc_devt(struct hd_struct *part, dev_t *devt);
 void blk_free_devt(dev_t devt);
diff --git a/block/genhd.c b/block/genhd.c
index c35b03dac5e5..ed06466b305d 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -126,7 +126,7 @@ static void part_stat_read_all(struct hd_struct *part, struct disk_stats *stat)
 	}
 }
 
-static unsigned int part_in_flight(struct hd_struct *part)
+static unsigned int part_in_flight(struct block_device *part)
 {
 	unsigned int inflight = 0;
 	int cpu;
@@ -141,7 +141,8 @@ static unsigned int part_in_flight(struct hd_struct *part)
 	return inflight;
 }
 
-static void part_in_flight_rw(struct hd_struct *part, unsigned int inflight[2])
+static void part_in_flight_rw(struct block_device *part,
+		unsigned int inflight[2])
 {
 	int cpu;
 
@@ -157,7 +158,7 @@ static void part_in_flight_rw(struct hd_struct *part, unsigned int inflight[2])
 		inflight[1] = 0;
 }
 
-struct hd_struct *__disk_get_part(struct gendisk *disk, int partno)
+struct block_device *__disk_get_part(struct gendisk *disk, int partno)
 {
 	struct disk_part_tbl *ptbl = rcu_dereference(disk->part_tbl);
 
@@ -182,15 +183,21 @@ struct hd_struct *__disk_get_part(struct gendisk *disk, int partno)
  */
 struct hd_struct *disk_get_part(struct gendisk *disk, int partno)
 {
+	struct block_device *bdev;
 	struct hd_struct *part;
 
 	rcu_read_lock();
-	part = __disk_get_part(disk, partno);
-	if (part)
-		get_device(part_to_dev(part));
+	bdev = __disk_get_part(disk, partno);
+	if (!bdev)
+		goto fail;
+	part = bdev->bd_part;
+	if (!kobject_get_unless_zero(&part_to_dev(part)->kobj))
+		goto fail;
 	rcu_read_unlock();
-
 	return part;
+fail:
+	rcu_read_unlock();
+	return NULL;
 }
 
 /**
@@ -264,19 +271,19 @@ struct hd_struct *disk_part_iter_next(struct disk_part_iter *piter)
 
 	/* iterate to the next partition */
 	for (; piter->idx != end; piter->idx += inc) {
-		struct hd_struct *part;
+		struct block_device *part;
 
 		part = rcu_dereference(ptbl->part[piter->idx]);
 		if (!part)
 			continue;
-		if (!bdev_nr_sectors(part->bdev) &&
+		if (!bdev_nr_sectors(part) &&
 		    !(piter->flags & DISK_PITER_INCL_EMPTY) &&
 		    !(piter->flags & DISK_PITER_INCL_EMPTY_PART0 &&
 		      piter->idx == 0))
 			continue;
 
-		get_device(part_to_dev(part));
-		piter->part = part;
+		get_device(part_to_dev(part->bd_part));
+		piter->part = part->bd_part;
 		piter->idx += inc;
 		break;
 	}
@@ -303,10 +310,10 @@ void disk_part_iter_exit(struct disk_part_iter *piter)
 }
 EXPORT_SYMBOL_GPL(disk_part_iter_exit);
 
-static inline int sector_in_part(struct hd_struct *part, sector_t sector)
+static inline int sector_in_part(struct block_device *part, sector_t sector)
 {
-	return part->bdev->bd_start_sect <= sector &&
-		sector < part->bdev->bd_start_sect + bdev_nr_sectors(part->bdev);
+	return part->bd_start_sect <= sector &&
+		sector < part->bd_start_sect + bdev_nr_sectors(part);
 }
 
 /**
@@ -324,10 +331,10 @@ static inline int sector_in_part(struct hd_struct *part, sector_t sector)
  * Found partition on success, part0 is returned if no partition matches
  * or the matched partition is being deleted.
  */
-struct hd_struct *disk_map_sector_rcu(struct gendisk *disk, sector_t sector)
+struct block_device *disk_map_sector_rcu(struct gendisk *disk, sector_t sector)
 {
 	struct disk_part_tbl *ptbl;
-	struct hd_struct *part;
+	struct block_device *part;
 	int i;
 
 	rcu_read_lock();
@@ -346,7 +353,7 @@ struct hd_struct *disk_map_sector_rcu(struct gendisk *disk, sector_t sector)
 		}
 	}
 
-	part = disk->part0->bd_part;
+	part = disk->part0;
 out_unlock:
 	rcu_read_unlock();
 	return part;
@@ -882,7 +889,7 @@ void del_gendisk(struct gendisk *disk)
 	kobject_put(disk->part0->bd_holder_dir);
 	kobject_put(disk->slave_dir);
 
-	part_stat_set_all(disk->part0->bd_part, 0);
+	part_stat_set_all(disk->part0, 0);
 	disk->part0->bd_stamp = 0;
 	if (!sysfs_deprecated)
 		sysfs_remove_link(block_depr, dev_name(disk_to_dev(disk)));
@@ -1189,9 +1196,9 @@ ssize_t part_stat_show(struct device *dev,
 
 	part_stat_read_all(p, &stat);
 	if (queue_is_mq(q))
-		inflight = blk_mq_in_flight(q, p);
+		inflight = blk_mq_in_flight(q, p->bdev);
 	else
-		inflight = part_in_flight(p);
+		inflight = part_in_flight(p->bdev);
 
 	return sprintf(buf,
 		"%8lu %8lu %8llu %8u "
@@ -1231,9 +1238,9 @@ ssize_t part_inflight_show(struct device *dev, struct device_attribute *attr,
 	unsigned int inflight[2];
 
 	if (queue_is_mq(q))
-		blk_mq_in_flight_rw(q, p, inflight);
+		blk_mq_in_flight_rw(q, p->bdev, inflight);
 	else
-		part_in_flight_rw(p, inflight);
+		part_in_flight_rw(p->bdev, inflight);
 
 	return sprintf(buf, "%8u %8u\n", inflight[0], inflight[1]);
 }
@@ -1506,9 +1513,9 @@ static int diskstats_show(struct seq_file *seqf, void *v)
 	while ((hd = disk_part_iter_next(&piter))) {
 		part_stat_read_all(hd, &stat);
 		if (queue_is_mq(gp->queue))
-			inflight = blk_mq_in_flight(gp->queue, hd);
+			inflight = blk_mq_in_flight(gp->queue, hd->bdev);
 		else
-			inflight = part_in_flight(hd);
+			inflight = part_in_flight(hd->bdev);
 
 		seq_printf(seqf, "%4d %7d %s "
 			   "%lu %lu %lu %u "
@@ -1626,7 +1633,7 @@ struct gendisk *__alloc_disk_node(int minors, int node_id)
 		goto out_bdput;
 
 	ptbl = rcu_dereference_protected(disk->part_tbl, 1);
-	rcu_assign_pointer(ptbl->part[0], disk->part0->bd_part);
+	rcu_assign_pointer(ptbl->part[0], disk->part0);
 
 	disk->minors = minors;
 	rand_initialize_disk(disk);
diff --git a/block/partitions/core.c b/block/partitions/core.c
index 6d1fca193cbd..c2f6721633b8 100644
--- a/block/partitions/core.c
+++ b/block/partitions/core.c
@@ -298,12 +298,9 @@ void delete_partition(struct hd_struct *part)
 	struct disk_part_tbl *ptbl =
 		rcu_dereference_protected(disk->part_tbl, 1);
 
-	/*
-	 * ->part_tbl is referenced in this part's release handler, so
-	 *  we have to hold the disk device
-	 */
 	rcu_assign_pointer(ptbl->part[part->partno], NULL);
 	rcu_assign_pointer(ptbl->last_lookup, NULL);
+
 	kobject_put(part->bdev->bd_holder_dir);
 	device_del(part_to_dev(part));
 
@@ -421,7 +418,7 @@ static struct hd_struct *add_partition(struct gendisk *disk, int partno,
 
 	/* everything is up and running, commence */
 	bdev_add(bdev, devt);
-	rcu_assign_pointer(ptbl->part[partno], p);
+	rcu_assign_pointer(ptbl->part[partno], bdev);
 
 	/* suppress uevent if the disk suppresses it */
 	if (!dev_get_uevent_suppress(ddev))