Merge tag 'block-5.10-2020-10-12' of git://git.kernel.dk/linux-block

Pull block updates from Jens Axboe:

 - Series of merge handling cleanups (Baolin, Christoph)

 - Series of blk-throttle fixes and cleanups (Baolin)

 - Series cleaning up BDI, seperating the block device from the
   backing_dev_info (Christoph)

 - Removal of bdget() as a generic API (Christoph)

 - Removal of blkdev_get() as a generic API (Christoph)

 - Cleanup of is-partition checks (Christoph)

 - Series reworking disk revalidation (Christoph)

 - Series cleaning up bio flags (Christoph)

 - bio crypt fixes (Eric)

 - IO stats inflight tweak (Gabriel)

 - blk-mq tags fixes (Hannes)

 - Buffer invalidation fixes (Jan)

 - Allow soft limits for zone append (Johannes)

 - Shared tag set improvements (John, Kashyap)

 - Allow IOPRIO_CLASS_RT for CAP_SYS_NICE (Khazhismel)

 - DM no-wait support (Mike, Konstantin)

 - Request allocation improvements (Ming)

 - Allow md/dm/bcache to use IO stat helpers (Song)

 - Series improving blk-iocost (Tejun)

 - Various cleanups (Geert, Damien, Danny, Julia, Tetsuo, Tian, Wang,
   Xianting, Yang, Yufen, yangerkun)

* tag 'block-5.10-2020-10-12' of git://git.kernel.dk/linux-block: (191 commits)
  block: fix uapi blkzoned.h comments
  blk-mq: move cancel of hctx->run_work to the front of blk_exit_queue
  blk-mq: get rid of the dead flush handle code path
  block: get rid of unnecessary local variable
  block: fix comment and add lockdep assert
  blk-mq: use helper function to test hw stopped
  block: use helper function to test queue register
  block: remove redundant mq check
  block: invoke blk_mq_exit_sched no matter whether have .exit_sched
  percpu_ref: don't refer to ref->data if it isn't allocated
  block: ratelimit handle_bad_sector() message
  blk-throttle: Re-use the throtl_set_slice_end()
  blk-throttle: Open code __throtl_de/enqueue_tg()
  blk-throttle: Move service tree validation out of the throtl_rb_first()
  blk-throttle: Move the list operation after list validation
  blk-throttle: Fix IO hang for a corner case
  blk-throttle: Avoid tracking latency if low limit is invalid
  blk-throttle: Avoid getting the current time if tg->last_finish_time is 0
  blk-throttle: Remove a meaningless parameter for throtl_downgrade_state()
  block: Remove redundant 'return' statement
  ...

1 files changed, 52 insertions, 32 deletions

diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 868e11face00..1d99bf70a90a 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -24,6 +24,7 @@
 #include <linux/percpu-refcount.h>
 #include <linux/scatterlist.h>
 #include <linux/blkzoned.h>
+#include <linux/pm.h>
 
 struct module;
 struct scsi_ioctl_command;
@@ -398,6 +399,8 @@ struct request_queue {
 	struct request		*last_merge;
 	struct elevator_queue	*elevator;
 
+	struct percpu_ref	q_usage_counter;
+
 	struct blk_queue_stats	*stats;
 	struct rq_qos		*rq_qos;
 
@@ -460,7 +463,7 @@ struct request_queue {
 
 #ifdef CONFIG_PM
 	struct device		*dev;
-	int			rpm_status;
+	enum rpm_status		rpm_status;
 	unsigned int		nr_pending;
 #endif
 
@@ -486,6 +489,8 @@ struct request_queue {
 	struct timer_list	timeout;
 	struct work_struct	timeout_work;
 
+	atomic_t		nr_active_requests_shared_sbitmap;
+
 	struct list_head	icq_list;
 #ifdef CONFIG_BLK_CGROUP
 	DECLARE_BITMAP		(blkcg_pols, BLKCG_MAX_POLS);
@@ -568,7 +573,6 @@ struct request_queue {
 	 * percpu_ref_kill() and percpu_ref_reinit().
 	 */
 	struct mutex		mq_freeze_lock;
-	struct percpu_ref	q_usage_counter;
 
 	struct blk_mq_tag_set	*tag_set;
 	struct list_head	tag_set_list;
@@ -605,6 +609,7 @@ struct request_queue {
 #define QUEUE_FLAG_SAME_FORCE	12	/* force complete on same CPU */
 #define QUEUE_FLAG_DEAD		13	/* queue tear-down finished */
 #define QUEUE_FLAG_INIT_DONE	14	/* queue is initialized */
+#define QUEUE_FLAG_STABLE_WRITES 15	/* don't modify blks until WB is done */
 #define QUEUE_FLAG_POLL		16	/* IO polling enabled if set */
 #define QUEUE_FLAG_WC		17	/* Write back caching */
 #define QUEUE_FLAG_FUA		18	/* device supports FUA writes */
@@ -617,9 +622,12 @@ struct request_queue {
 #define QUEUE_FLAG_PCI_P2PDMA	25	/* device supports PCI p2p requests */
 #define QUEUE_FLAG_ZONE_RESETALL 26	/* supports Zone Reset All */
 #define QUEUE_FLAG_RQ_ALLOC_TIME 27	/* record rq->alloc_time_ns */
+#define QUEUE_FLAG_HCTX_ACTIVE	28	/* at least one blk-mq hctx is active */
+#define QUEUE_FLAG_NOWAIT       29	/* device supports NOWAIT */
 
 #define QUEUE_FLAG_MQ_DEFAULT	((1 << QUEUE_FLAG_IO_STAT) |		\
-				 (1 << QUEUE_FLAG_SAME_COMP))
+				 (1 << QUEUE_FLAG_SAME_COMP) |		\
+				 (1 << QUEUE_FLAG_NOWAIT))
 
 void blk_queue_flag_set(unsigned int flag, struct request_queue *q);
 void blk_queue_flag_clear(unsigned int flag, struct request_queue *q);
@@ -633,6 +641,8 @@ bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q);
 #define blk_queue_noxmerges(q)	\
 	test_bit(QUEUE_FLAG_NOXMERGES, &(q)->queue_flags)
 #define blk_queue_nonrot(q)	test_bit(QUEUE_FLAG_NONROT, &(q)->queue_flags)
+#define blk_queue_stable_writes(q) \
+	test_bit(QUEUE_FLAG_STABLE_WRITES, &(q)->queue_flags)
 #define blk_queue_io_stat(q)	test_bit(QUEUE_FLAG_IO_STAT, &(q)->queue_flags)
 #define blk_queue_add_random(q)	test_bit(QUEUE_FLAG_ADD_RANDOM, &(q)->queue_flags)
 #define blk_queue_discard(q)	test_bit(QUEUE_FLAG_DISCARD, &(q)->queue_flags)
@@ -659,6 +669,7 @@ bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q);
 #define blk_queue_pm_only(q)	atomic_read(&(q)->pm_only)
 #define blk_queue_fua(q)	test_bit(QUEUE_FLAG_FUA, &(q)->queue_flags)
 #define blk_queue_registered(q)	test_bit(QUEUE_FLAG_REGISTERED, &(q)->queue_flags)
+#define blk_queue_nowait(q)	test_bit(QUEUE_FLAG_NOWAIT, &(q)->queue_flags)
 
 extern void blk_set_pm_only(struct request_queue *q);
 extern void blk_clear_pm_only(struct request_queue *q);
@@ -1061,11 +1072,17 @@ static inline unsigned int blk_queue_get_max_sectors(struct request_queue *q,
 static inline unsigned int blk_max_size_offset(struct request_queue *q,
 					       sector_t offset)
 {
-	if (!q->limits.chunk_sectors)
+	unsigned int chunk_sectors = q->limits.chunk_sectors;
+
+	if (!chunk_sectors)
 		return q->limits.max_sectors;
 
-	return min(q->limits.max_sectors, (unsigned int)(q->limits.chunk_sectors -
-			(offset & (q->limits.chunk_sectors - 1))));
+	if (likely(is_power_of_2(chunk_sectors)))
+		chunk_sectors -= offset & (chunk_sectors - 1);
+	else
+		chunk_sectors -= sector_div(offset, chunk_sectors);
+
+	return min(q->limits.max_sectors, chunk_sectors);
 }
 
 static inline unsigned int blk_rq_get_max_sectors(struct request *rq,
@@ -1132,6 +1149,7 @@ extern void blk_queue_max_zone_append_sectors(struct request_queue *q,
 extern void blk_queue_physical_block_size(struct request_queue *, unsigned int);
 extern void blk_queue_alignment_offset(struct request_queue *q,
 				       unsigned int alignment);
+void blk_queue_update_readahead(struct request_queue *q);
 extern void blk_limits_io_min(struct queue_limits *limits, unsigned int min);
 extern void blk_queue_io_min(struct request_queue *q, unsigned int min);
 extern void blk_limits_io_opt(struct queue_limits *limits, unsigned int opt);
@@ -1341,6 +1359,11 @@ static inline int sb_issue_zeroout(struct super_block *sb, sector_t block,
 
 extern int blk_verify_command(unsigned char *cmd, fmode_t mode);
 
+static inline bool bdev_is_partition(struct block_device *bdev)
+{
+	return bdev->bd_partno;
+}
+
 enum blk_default_limits {
 	BLK_MAX_SEGMENTS	= 128,
 	BLK_SAFE_MAX_SECTORS	= 255,
@@ -1386,7 +1409,10 @@ static inline unsigned int queue_max_segment_size(const struct request_queue *q)
 
 static inline unsigned int queue_max_zone_append_sectors(const struct request_queue *q)
 {
-	return q->limits.max_zone_append_sectors;
+
+	const struct queue_limits *l = &q->limits;
+
+	return min(l->max_zone_append_sectors, l->max_sectors);
 }
 
 static inline unsigned queue_logical_block_size(const struct request_queue *q)
@@ -1457,10 +1483,9 @@ static inline int bdev_alignment_offset(struct block_device *bdev)
 
 	if (q->limits.misaligned)
 		return -1;
-
-	if (bdev != bdev->bd_contains)
-		return bdev->bd_part->alignment_offset;
-
+	if (bdev_is_partition(bdev))
+		return queue_limit_alignment_offset(&q->limits,
+				bdev->bd_part->start_sect);
 	return q->limits.alignment_offset;
 }
 
@@ -1499,9 +1524,9 @@ static inline int bdev_discard_alignment(struct block_device *bdev)
 {
 	struct request_queue *q = bdev_get_queue(bdev);
 
-	if (bdev != bdev->bd_contains)
-		return bdev->bd_part->discard_alignment;
-
+	if (bdev_is_partition(bdev))
+		return queue_limit_discard_alignment(&q->limits,
+				bdev->bd_part->start_sect);
 	return q->limits.discard_alignment;
 }
 
@@ -1644,10 +1669,6 @@ extern int blk_integrity_compare(struct gendisk *, struct gendisk *);
 extern int blk_rq_map_integrity_sg(struct request_queue *, struct bio *,
 				   struct scatterlist *);
 extern int blk_rq_count_integrity_sg(struct request_queue *, struct bio *);
-extern bool blk_integrity_merge_rq(struct request_queue *, struct request *,
-				   struct request *);
-extern bool blk_integrity_merge_bio(struct request_queue *, struct request *,
-				    struct bio *);
 
 static inline struct blk_integrity *blk_get_integrity(struct gendisk *disk)
 {
@@ -1775,18 +1796,6 @@ static inline unsigned short queue_max_integrity_segments(const struct request_q
 {
 	return 0;
 }
-static inline bool blk_integrity_merge_rq(struct request_queue *rq,
-					  struct request *r1,
-					  struct request *r2)
-{
-	return true;
-}
-static inline bool blk_integrity_merge_bio(struct request_queue *rq,
-					   struct request *r,
-					   struct bio *b)
-{
-	return true;
-}
 
 static inline unsigned int bio_integrity_intervals(struct blk_integrity *bi,
 						   unsigned int sectors)
@@ -1932,6 +1941,11 @@ unsigned long disk_start_io_acct(struct gendisk *disk, unsigned int sectors,
 void disk_end_io_acct(struct gendisk *disk, unsigned int op,
 		unsigned long start_time);
 
+unsigned long part_start_io_acct(struct gendisk *disk, struct hd_struct **part,
+				 struct bio *bio);
+void part_end_io_acct(struct hd_struct *part, struct bio *bio,
+		      unsigned long start_time);
+
 /**
  * bio_start_io_acct - start I/O accounting for bio based drivers
  * @bio:	bio to start account for
@@ -1969,7 +1983,6 @@ void blkdev_show(struct seq_file *seqf, off_t offset);
 #define BLKDEV_MAJOR_MAX	0
 #endif
 
-int blkdev_get(struct block_device *bdev, fmode_t mode, void *holder);
 struct block_device *blkdev_get_by_path(const char *path, fmode_t mode,
 		void *holder);
 struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder);
@@ -1980,17 +1993,24 @@ void bd_abort_claiming(struct block_device *bdev, struct block_device *whole,
 void blkdev_put(struct block_device *bdev, fmode_t mode);
 
 struct block_device *I_BDEV(struct inode *inode);
-struct block_device *bdget(dev_t);
+struct block_device *bdget_part(struct hd_struct *part);
 struct block_device *bdgrab(struct block_device *bdev);
 void bdput(struct block_device *);
 
 #ifdef CONFIG_BLOCK
 void invalidate_bdev(struct block_device *bdev);
+int truncate_bdev_range(struct block_device *bdev, fmode_t mode, loff_t lstart,
+			loff_t lend);
 int sync_blockdev(struct block_device *bdev);
 #else
 static inline void invalidate_bdev(struct block_device *bdev)
 {
 }
+static inline int truncate_bdev_range(struct block_device *bdev, fmode_t mode,
+				      loff_t lstart, loff_t lend)
+{
+	return 0;
+}
 static inline int sync_blockdev(struct block_device *bdev)
 {
 	return 0;