1 files changed, 198 insertions, 97 deletions

diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 0ce8a372d506..9af3e0f430bc 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -27,6 +27,8 @@
 #include <linux/percpu-refcount.h>
 #include <linux/scatterlist.h>
 #include <linux/blkzoned.h>
+#include <linux/seqlock.h>
+#include <linux/u64_stats_sync.h>
 
 struct module;
 struct scsi_ioctl_command;
@@ -47,7 +49,7 @@ struct blk_stat_callback;
 #define BLKDEV_MIN_RQ	4
 #define BLKDEV_MAX_RQ	128	/* Default maximum */
 
-/* Must be consisitent with blk_mq_poll_stats_bkt() */
+/* Must be consistent with blk_mq_poll_stats_bkt() */
 #define BLK_MQ_POLL_STATS_BKTS 16
 
 /*
@@ -121,6 +123,12 @@ typedef __u32 __bitwise req_flags_t;
 /* Look at ->special_vec for the actual data payload instead of the
    bio chain. */
 #define RQF_SPECIAL_PAYLOAD	((__force req_flags_t)(1 << 18))
+/* The per-zone write lock is held for this request */
+#define RQF_ZONE_WRITE_LOCKED	((__force req_flags_t)(1 << 19))
+/* timeout is expired */
+#define RQF_MQ_TIMEOUT_EXPIRED	((__force req_flags_t)(1 << 20))
+/* already slept for hybrid poll */
+#define RQF_MQ_POLL_SLEPT	((__force req_flags_t)(1 << 21))
 
 /* flags that prevent us from merging requests: */
 #define RQF_NOMERGE_FLAGS \
@@ -133,12 +141,6 @@ typedef __u32 __bitwise req_flags_t;
  * especially blk_mq_rq_ctx_init() to take care of the added fields.
  */
 struct request {
-	struct list_head queuelist;
-	union {
-		struct __call_single_data csd;
-		u64 fifo_time;
-	};
-
 	struct request_queue *q;
 	struct blk_mq_ctx *mq_ctx;
 
@@ -148,8 +150,6 @@ struct request {
 
 	int internal_tag;
 
-	unsigned long atomic_flags;
-
 	/* the following two fields are internal, NEVER access directly */
 	unsigned int __data_len;	/* total data len */
 	int tag;
@@ -158,6 +158,8 @@ struct request {
 	struct bio *bio;
 	struct bio *biotail;
 
+	struct list_head queuelist;
+
 	/*
 	 * The hash is used inside the scheduler, and killed once the
 	 * request reaches the dispatch list. The ipi_list is only used
@@ -205,19 +207,16 @@ struct request {
 	struct hd_struct *part;
 	unsigned long start_time;
 	struct blk_issue_stat issue_stat;
-#ifdef CONFIG_BLK_CGROUP
-	struct request_list *rl;		/* rl this rq is alloced from */
-	unsigned long long start_time_ns;
-	unsigned long long io_start_time_ns;    /* when passed to hardware */
-#endif
 	/* Number of scatter-gather DMA addr+len pairs after
 	 * physical address coalescing is performed.
 	 */
 	unsigned short nr_phys_segments;
+
 #if defined(CONFIG_BLK_DEV_INTEGRITY)
 	unsigned short nr_integrity_segments;
 #endif
 
+	unsigned short write_hint;
 	unsigned short ioprio;
 
 	unsigned int timeout;
@@ -226,11 +225,37 @@ struct request {
 
 	unsigned int extra_len;	/* length of alignment and padding */
 
-	unsigned short write_hint;
+	/*
+	 * On blk-mq, the lower bits of ->gstate (generation number and
+	 * state) carry the MQ_RQ_* state value and the upper bits the
+	 * generation number which is monotonically incremented and used to
+	 * distinguish the reuse instances.
+	 *
+	 * ->gstate_seq allows updates to ->gstate and other fields
+	 * (currently ->deadline) during request start to be read
+	 * atomically from the timeout path, so that it can operate on a
+	 * coherent set of information.
+	 */
+	seqcount_t gstate_seq;
+	u64 gstate;
+
+	/*
+	 * ->aborted_gstate is used by the timeout to claim a specific
+	 * recycle instance of this request.  See blk_mq_timeout_work().
+	 */
+	struct u64_stats_sync aborted_gstate_sync;
+	u64 aborted_gstate;
+
+	/* access through blk_rq_set_deadline, blk_rq_deadline */
+	unsigned long __deadline;
 
-	unsigned long deadline;
 	struct list_head timeout_list;
 
+	union {
+		struct __call_single_data csd;
+		u64 fifo_time;
+	};
+
 	/*
 	 * completion callback.
 	 */
@@ -239,6 +264,12 @@ struct request {
 
 	/* for bidi */
 	struct request *next_rq;
+
+#ifdef CONFIG_BLK_CGROUP
+	struct request_list *rl;		/* rl this rq is alloced from */
+	unsigned long long start_time_ns;
+	unsigned long long io_start_time_ns;    /* when passed to hardware */
+#endif
 };
 
 static inline bool blk_op_is_scsi(unsigned int op)
@@ -564,6 +595,22 @@ struct request_queue {
 	struct queue_limits	limits;
 
 	/*
+	 * Zoned block device information for request dispatch control.
+	 * nr_zones is the total number of zones of the device. This is always
+	 * 0 for regular block devices. seq_zones_bitmap is a bitmap of nr_zones
+	 * bits which indicates if a zone is conventional (bit clear) or
+	 * sequential (bit set). seq_zones_wlock is a bitmap of nr_zones
+	 * bits which indicates if a zone is write locked, that is, if a write
+	 * request targeting the zone was dispatched. All three fields are
+	 * initialized by the low level device driver (e.g. scsi/sd.c).
+	 * Stacking drivers (device mappers) may or may not initialize
+	 * these fields.
+	 */
+	unsigned int		nr_zones;
+	unsigned long		*seq_zones_bitmap;
+	unsigned long		*seq_zones_wlock;
+
+	/*
 	 * sg stuff
 	 */
 	unsigned int		sg_timeout;
@@ -660,73 +707,10 @@ struct request_queue {
 				 (1 << QUEUE_FLAG_SAME_COMP)	|	\
 				 (1 << QUEUE_FLAG_POLL))
 
-/*
- * @q->queue_lock is set while a queue is being initialized. Since we know
- * that no other threads access the queue object before @q->queue_lock has
- * been set, it is safe to manipulate queue flags without holding the
- * queue_lock if @q->queue_lock == NULL. See also blk_alloc_queue_node() and
- * blk_init_allocated_queue().
- */
-static inline void queue_lockdep_assert_held(struct request_queue *q)
-{
-	if (q->queue_lock)
-		lockdep_assert_held(q->queue_lock);
-}
-
-static inline void queue_flag_set_unlocked(unsigned int flag,
-					   struct request_queue *q)
-{
-	__set_bit(flag, &q->queue_flags);
-}
-
-static inline int queue_flag_test_and_clear(unsigned int flag,
-					    struct request_queue *q)
-{
-	queue_lockdep_assert_held(q);
-
-	if (test_bit(flag, &q->queue_flags)) {
-		__clear_bit(flag, &q->queue_flags);
-		return 1;
-	}
-
-	return 0;
-}
-
-static inline int queue_flag_test_and_set(unsigned int flag,
-					  struct request_queue *q)
-{
-	queue_lockdep_assert_held(q);
-
-	if (!test_bit(flag, &q->queue_flags)) {
-		__set_bit(flag, &q->queue_flags);
-		return 0;
-	}
-
-	return 1;
-}
-
-static inline void queue_flag_set(unsigned int flag, struct request_queue *q)
-{
-	queue_lockdep_assert_held(q);
-	__set_bit(flag, &q->queue_flags);
-}
-
-static inline void queue_flag_clear_unlocked(unsigned int flag,
-					     struct request_queue *q)
-{
-	__clear_bit(flag, &q->queue_flags);
-}
-
-static inline int queue_in_flight(struct request_queue *q)
-{
-	return q->in_flight[0] + q->in_flight[1];
-}
-
-static inline void queue_flag_clear(unsigned int flag, struct request_queue *q)
-{
-	queue_lockdep_assert_held(q);
-	__clear_bit(flag, &q->queue_flags);
-}
+void blk_queue_flag_set(unsigned int flag, struct request_queue *q);
+void blk_queue_flag_clear(unsigned int flag, struct request_queue *q);
+bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q);
+bool blk_queue_flag_test_and_clear(unsigned int flag, struct request_queue *q);
 
 #define blk_queue_tagged(q)	test_bit(QUEUE_FLAG_QUEUED, &(q)->queue_flags)
 #define blk_queue_stopped(q)	test_bit(QUEUE_FLAG_STOPPED, &(q)->queue_flags)
@@ -757,6 +741,11 @@ static inline void queue_flag_clear(unsigned int flag, struct request_queue *q)
 extern int blk_set_preempt_only(struct request_queue *q);
 extern void blk_clear_preempt_only(struct request_queue *q);
 
+static inline int queue_in_flight(struct request_queue *q)
+{
+	return q->in_flight[0] + q->in_flight[1];
+}
+
 static inline bool blk_account_rq(struct request *rq)
 {
 	return (rq->rq_flags & RQF_STARTED) && !blk_rq_is_passthrough(rq);
@@ -807,6 +796,27 @@ static inline unsigned int blk_queue_zone_sectors(struct request_queue *q)
 	return blk_queue_is_zoned(q) ? q->limits.chunk_sectors : 0;
 }
 
+static inline unsigned int blk_queue_nr_zones(struct request_queue *q)
+{
+	return q->nr_zones;
+}
+
+static inline unsigned int blk_queue_zone_no(struct request_queue *q,
+					     sector_t sector)
+{
+	if (!blk_queue_is_zoned(q))
+		return 0;
+	return sector >> ilog2(q->limits.chunk_sectors);
+}
+
+static inline bool blk_queue_zone_is_seq(struct request_queue *q,
+					 sector_t sector)
+{
+	if (!blk_queue_is_zoned(q) || !q->seq_zones_bitmap)
+		return false;
+	return test_bit(blk_queue_zone_no(q, sector), q->seq_zones_bitmap);
+}
+
 static inline bool rq_is_sync(struct request *rq)
 {
 	return op_is_sync(rq->cmd_flags);
@@ -1012,6 +1022,19 @@ static inline struct request_queue *bdev_get_queue(struct block_device *bdev)
 }
 
 /*
+ * The basic unit of block I/O is a sector. It is used in a number of contexts
+ * in Linux (blk, bio, genhd). The size of one sector is 512 = 2**9
+ * bytes. Variables of type sector_t represent an offset or size that is a
+ * multiple of 512 bytes. Hence these two constants.
+ */
+#ifndef SECTOR_SHIFT
+#define SECTOR_SHIFT 9
+#endif
+#ifndef SECTOR_SIZE
+#define SECTOR_SIZE (1 << SECTOR_SHIFT)
+#endif
+
+/*
  * blk_rq_pos()			: the current sector
  * blk_rq_bytes()		: bytes left in the entire request
  * blk_rq_cur_bytes()		: bytes left in the current segment
@@ -1038,12 +1061,22 @@ extern unsigned int blk_rq_err_bytes(const struct request *rq);
 
 static inline unsigned int blk_rq_sectors(const struct request *rq)
 {
-	return blk_rq_bytes(rq) >> 9;
+	return blk_rq_bytes(rq) >> SECTOR_SHIFT;
 }
 
 static inline unsigned int blk_rq_cur_sectors(const struct request *rq)
 {
-	return blk_rq_cur_bytes(rq) >> 9;
+	return blk_rq_cur_bytes(rq) >> SECTOR_SHIFT;
+}
+
+static inline unsigned int blk_rq_zone_no(struct request *rq)
+{
+	return blk_queue_zone_no(rq->q, blk_rq_pos(rq));
+}
+
+static inline unsigned int blk_rq_zone_is_seq(struct request *rq)
+{
+	return blk_queue_zone_is_seq(rq->q, blk_rq_pos(rq));
 }
 
 /*
@@ -1063,7 +1096,8 @@ static inline unsigned int blk_queue_get_max_sectors(struct request_queue *q,
 						     int op)
 {
 	if (unlikely(op == REQ_OP_DISCARD || op == REQ_OP_SECURE_ERASE))
-		return min(q->limits.max_discard_sectors, UINT_MAX >> 9);
+		return min(q->limits.max_discard_sectors,
+			   UINT_MAX >> SECTOR_SHIFT);
 
 	if (unlikely(op == REQ_OP_WRITE_SAME))
 		return q->limits.max_write_same_sectors;
@@ -1243,7 +1277,8 @@ extern long nr_blockdev_pages(void);
 
 bool __must_check blk_get_queue(struct request_queue *);
 struct request_queue *blk_alloc_queue(gfp_t);
-struct request_queue *blk_alloc_queue_node(gfp_t, int);
+struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id,
+					   spinlock_t *lock);
 extern void blk_put_queue(struct request_queue *);
 extern void blk_set_queue_dying(struct request_queue *);
 
@@ -1374,16 +1409,21 @@ extern int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
 static inline int sb_issue_discard(struct super_block *sb, sector_t block,
 		sector_t nr_blocks, gfp_t gfp_mask, unsigned long flags)
 {
-	return blkdev_issue_discard(sb->s_bdev, block << (sb->s_blocksize_bits - 9),
-				    nr_blocks << (sb->s_blocksize_bits - 9),
+	return blkdev_issue_discard(sb->s_bdev,
+				    block << (sb->s_blocksize_bits -
+					      SECTOR_SHIFT),
+				    nr_blocks << (sb->s_blocksize_bits -
+						  SECTOR_SHIFT),
 				    gfp_mask, flags);
 }
 static inline int sb_issue_zeroout(struct super_block *sb, sector_t block,
 		sector_t nr_blocks, gfp_t gfp_mask)
 {
 	return blkdev_issue_zeroout(sb->s_bdev,
-				    block << (sb->s_blocksize_bits - 9),
-				    nr_blocks << (sb->s_blocksize_bits - 9),
+				    block << (sb->s_blocksize_bits -
+					      SECTOR_SHIFT),
+				    nr_blocks << (sb->s_blocksize_bits -
+						  SECTOR_SHIFT),
 				    gfp_mask, 0);
 }
 
@@ -1490,7 +1530,8 @@ static inline int queue_alignment_offset(struct request_queue *q)
 static inline int queue_limit_alignment_offset(struct queue_limits *lim, sector_t sector)
 {
 	unsigned int granularity = max(lim->physical_block_size, lim->io_min);
-	unsigned int alignment = sector_div(sector, granularity >> 9) << 9;
+	unsigned int alignment = sector_div(sector, granularity >> SECTOR_SHIFT)
+		<< SECTOR_SHIFT;
 
 	return (granularity + lim->alignment_offset - alignment) % granularity;
 }
@@ -1524,8 +1565,8 @@ static inline int queue_limit_discard_alignment(struct queue_limits *lim, sector
 		return 0;
 
 	/* Why are these in bytes, not sectors? */
-	alignment = lim->discard_alignment >> 9;
-	granularity = lim->discard_granularity >> 9;
+	alignment = lim->discard_alignment >> SECTOR_SHIFT;
+	granularity = lim->discard_granularity >> SECTOR_SHIFT;
 	if (!granularity)
 		return 0;
 
@@ -1536,7 +1577,7 @@ static inline int queue_limit_discard_alignment(struct queue_limits *lim, sector
 	offset = (granularity + alignment - offset) % granularity;
 
 	/* Turn it back into bytes, gaah */
-	return offset << 9;
+	return offset << SECTOR_SHIFT;
 }
 
 static inline int bdev_discard_alignment(struct block_device *bdev)
@@ -1595,7 +1636,15 @@ static inline unsigned int bdev_zone_sectors(struct block_device *bdev)
 
 	if (q)
 		return blk_queue_zone_sectors(q);
+	return 0;
+}
+
+static inline unsigned int bdev_nr_zones(struct block_device *bdev)
+{
+	struct request_queue *q = bdev_get_queue(bdev);
 
+	if (q)
+		return blk_queue_nr_zones(q);
 	return 0;
 }
 
@@ -1731,8 +1780,6 @@ static inline bool req_gap_front_merge(struct request *req, struct bio *bio)
 
 int kblockd_schedule_work(struct work_struct *work);
 int kblockd_schedule_work_on(int cpu, struct work_struct *work);
-int kblockd_schedule_delayed_work(struct delayed_work *dwork, unsigned long delay);
-int kblockd_schedule_delayed_work_on(int cpu, struct delayed_work *dwork, unsigned long delay);
 int kblockd_mod_delayed_work_on(int cpu, struct delayed_work *dwork, unsigned long delay);
 
 #ifdef CONFIG_BLK_CGROUP
@@ -1971,6 +2018,60 @@ extern int __blkdev_driver_ioctl(struct block_device *, fmode_t, unsigned int,
 extern int bdev_read_page(struct block_device *, sector_t, struct page *);
 extern int bdev_write_page(struct block_device *, sector_t, struct page *,
 						struct writeback_control *);
+
+#ifdef CONFIG_BLK_DEV_ZONED
+bool blk_req_needs_zone_write_lock(struct request *rq);
+void __blk_req_zone_write_lock(struct request *rq);
+void __blk_req_zone_write_unlock(struct request *rq);
+
+static inline void blk_req_zone_write_lock(struct request *rq)
+{
+	if (blk_req_needs_zone_write_lock(rq))
+		__blk_req_zone_write_lock(rq);
+}
+
+static inline void blk_req_zone_write_unlock(struct request *rq)
+{
+	if (rq->rq_flags & RQF_ZONE_WRITE_LOCKED)
+		__blk_req_zone_write_unlock(rq);
+}
+
+static inline bool blk_req_zone_is_write_locked(struct request *rq)
+{
+	return rq->q->seq_zones_wlock &&
+		test_bit(blk_rq_zone_no(rq), rq->q->seq_zones_wlock);
+}
+
+static inline bool blk_req_can_dispatch_to_zone(struct request *rq)
+{
+	if (!blk_req_needs_zone_write_lock(rq))
+		return true;
+	return !blk_req_zone_is_write_locked(rq);
+}
+#else
+static inline bool blk_req_needs_zone_write_lock(struct request *rq)
+{
+	return false;
+}
+
+static inline void blk_req_zone_write_lock(struct request *rq)
+{
+}
+
+static inline void blk_req_zone_write_unlock(struct request *rq)
+{
+}
+static inline bool blk_req_zone_is_write_locked(struct request *rq)
+{
+	return false;
+}
+
+static inline bool blk_req_can_dispatch_to_zone(struct request *rq)
+{
+	return true;
+}
+#endif /* CONFIG_BLK_DEV_ZONED */
+
 #else /* CONFIG_BLOCK */
 
 struct block_device;