Merge branch 'next' into for-linus

Prepare input updates for 5.11 merge window.

1 files changed, 252 insertions, 81 deletions

diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 32868fbedc9e..868e11face00 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -4,9 +4,6 @@
 
 #include <linux/sched.h>
 #include <linux/sched/clock.h>
-
-#ifdef CONFIG_BLOCK
-
 #include <linux/major.h>
 #include <linux/genhd.h>
 #include <linux/list.h>
@@ -43,6 +40,7 @@ struct pr_ops;
 struct rq_qos;
 struct blk_queue_stats;
 struct blk_stat_callback;
+struct blk_keyslot_manager;
 
 #define BLKDEV_MIN_RQ	4
 #define BLKDEV_MAX_RQ	128	/* Default maximum */
@@ -82,8 +80,6 @@ typedef __u32 __bitwise req_flags_t;
 /* set for "ide_preempt" requests and also for requests for which the SCSI
    "quiesce" state must be ignored. */
 #define RQF_PREEMPT		((__force req_flags_t)(1 << 8))
-/* contains copies of user pages */
-#define RQF_COPY_USER		((__force req_flags_t)(1 << 9))
 /* vaguely specified driver internal error.  Ignored by the block layer */
 #define RQF_FAILED		((__force req_flags_t)(1 << 10))
 /* don't warn about errors */
@@ -223,11 +219,14 @@ struct request {
 	unsigned short nr_integrity_segments;
 #endif
 
+#ifdef CONFIG_BLK_INLINE_ENCRYPTION
+	struct bio_crypt_ctx *crypt_ctx;
+	struct blk_ksm_keyslot *crypt_keyslot;
+#endif
+
 	unsigned short write_hint;
 	unsigned short ioprio;
 
-	unsigned int extra_len;	/* length of alignment and padding */
-
 	enum mq_rq_state state;
 	refcount_t ref;
 
@@ -287,10 +286,7 @@ static inline unsigned short req_get_ioprio(struct request *req)
 
 struct blk_queue_ctx;
 
-typedef blk_qc_t (make_request_fn) (struct request_queue *q, struct bio *bio);
-
 struct bio_vec;
-typedef int (dma_drain_needed_fn)(struct request *);
 
 enum blk_eh_timer_return {
 	BLK_EH_DONE,		/* drivers has completed the command */
@@ -310,11 +306,14 @@ enum blk_queue_state {
 
 /*
  * Zoned block device models (zoned limit).
+ *
+ * Note: This needs to be ordered from the least to the most severe
+ * restrictions for the inheritance in blk_stack_limits() to work.
  */
 enum blk_zoned_model {
-	BLK_ZONED_NONE,	/* Regular block device */
-	BLK_ZONED_HA,	/* Host-aware zoned block device */
-	BLK_ZONED_HM,	/* Host-managed zoned block device */
+	BLK_ZONED_NONE = 0,	/* Regular block device */
+	BLK_ZONED_HA,		/* Host-aware zoned block device */
+	BLK_ZONED_HM,		/* Host-managed zoned block device */
 };
 
 struct queue_limits {
@@ -336,6 +335,7 @@ struct queue_limits {
 	unsigned int		max_hw_discard_sectors;
 	unsigned int		max_write_same_sectors;
 	unsigned int		max_write_zeroes_sectors;
+	unsigned int		max_zone_append_sectors;
 	unsigned int		discard_granularity;
 	unsigned int		discard_alignment;
 
@@ -352,6 +352,8 @@ struct queue_limits {
 typedef int (*report_zones_cb)(struct blk_zone *zone, unsigned int idx,
 			       void *data);
 
+void blk_queue_set_zoned(struct gendisk *disk, enum blk_zoned_model model);
+
 #ifdef CONFIG_BLK_DEV_ZONED
 
 #define BLK_ALL_ZONES  ((unsigned int)-1)
@@ -361,7 +363,8 @@ unsigned int blkdev_nr_zones(struct gendisk *disk);
 extern int blkdev_zone_mgmt(struct block_device *bdev, enum req_opf op,
 			    sector_t sectors, sector_t nr_sectors,
 			    gfp_t gfp_mask);
-extern int blk_revalidate_disk_zones(struct gendisk *disk);
+int blk_revalidate_disk_zones(struct gendisk *disk,
+			      void (*update_driver_data)(struct gendisk *disk));
 
 extern int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode,
 				     unsigned int cmd, unsigned long arg);
@@ -398,9 +401,6 @@ struct request_queue {
 	struct blk_queue_stats	*stats;
 	struct rq_qos		*rq_qos;
 
-	make_request_fn		*make_request_fn;
-	dma_drain_needed_fn	*dma_drain_needed;
-
 	const struct blk_mq_ops	*mq_ops;
 
 	/* sw queues */
@@ -469,11 +469,14 @@ struct request_queue {
 	 */
 	unsigned long		nr_requests;	/* Max # of requests */
 
-	unsigned int		dma_drain_size;
-	void			*dma_drain_buffer;
 	unsigned int		dma_pad_mask;
 	unsigned int		dma_alignment;
 
+#ifdef CONFIG_BLK_INLINE_ENCRYPTION
+	/* Inline crypto capabilities */
+	struct blk_keyslot_manager *ksm;
+#endif
+
 	unsigned int		rq_timeout;
 	int			poll_nsec;
 
@@ -515,6 +518,8 @@ struct request_queue {
 	unsigned int		nr_zones;
 	unsigned long		*conv_zones_bitmap;
 	unsigned long		*seq_zones_wlock;
+	unsigned int		max_open_zones;
+	unsigned int		max_active_zones;
 #endif /* CONFIG_BLK_DEV_ZONED */
 
 	/*
@@ -523,9 +528,9 @@ struct request_queue {
 	unsigned int		sg_timeout;
 	unsigned int		sg_reserved_size;
 	int			node;
+	struct mutex		debugfs_mutex;
 #ifdef CONFIG_BLK_DEV_IO_TRACE
 	struct blk_trace __rcu	*blk_trace;
-	struct mutex		blk_trace_mutex;
 #endif
 	/*
 	 * for flush operations
@@ -569,8 +574,9 @@ struct request_queue {
 	struct list_head	tag_set_list;
 	struct bio_set		bio_split;
 
-#ifdef CONFIG_BLK_DEBUG_FS
 	struct dentry		*debugfs_dir;
+
+#ifdef CONFIG_BLK_DEBUG_FS
 	struct dentry		*sched_debugfs_dir;
 	struct dentry		*rqos_debugfs_dir;
 #endif
@@ -579,12 +585,11 @@ struct request_queue {
 
 	size_t			cmd_size;
 
-	struct work_struct	release_work;
-
 #define BLK_MAX_WRITE_HINTS	5
 	u64			write_hints[BLK_MAX_WRITE_HINTS];
 };
 
+/* Keep blk_queue_flag_name[] in sync with the definitions below */
 #define QUEUE_FLAG_STOPPED	0	/* queue is stopped */
 #define QUEUE_FLAG_DYING	1	/* queue being torn down */
 #define QUEUE_FLAG_NOMERGES     3	/* disable merge attempts */
@@ -724,11 +729,51 @@ static inline bool blk_queue_zone_is_seq(struct request_queue *q,
 		return true;
 	return !test_bit(blk_queue_zone_no(q, sector), q->conv_zones_bitmap);
 }
+
+static inline void blk_queue_max_open_zones(struct request_queue *q,
+		unsigned int max_open_zones)
+{
+	q->max_open_zones = max_open_zones;
+}
+
+static inline unsigned int queue_max_open_zones(const struct request_queue *q)
+{
+	return q->max_open_zones;
+}
+
+static inline void blk_queue_max_active_zones(struct request_queue *q,
+		unsigned int max_active_zones)
+{
+	q->max_active_zones = max_active_zones;
+}
+
+static inline unsigned int queue_max_active_zones(const struct request_queue *q)
+{
+	return q->max_active_zones;
+}
 #else /* CONFIG_BLK_DEV_ZONED */
 static inline unsigned int blk_queue_nr_zones(struct request_queue *q)
 {
 	return 0;
 }
+static inline bool blk_queue_zone_is_seq(struct request_queue *q,
+					 sector_t sector)
+{
+	return false;
+}
+static inline unsigned int blk_queue_zone_no(struct request_queue *q,
+					     sector_t sector)
+{
+	return 0;
+}
+static inline unsigned int queue_max_open_zones(const struct request_queue *q)
+{
+	return 0;
+}
+static inline unsigned int queue_max_active_zones(const struct request_queue *q)
+{
+	return 0;
+}
 #endif /* CONFIG_BLK_DEV_ZONED */
 
 static inline bool rq_is_sync(struct request *rq)
@@ -747,6 +792,9 @@ static inline bool rq_mergeable(struct request *rq)
 	if (req_op(rq) == REQ_OP_WRITE_ZEROES)
 		return false;
 
+	if (req_op(rq) == REQ_OP_ZONE_APPEND)
+		return false;
+
 	if (rq->cmd_flags & REQ_NOMERGE_FLAGS)
 		return false;
 	if (rq->rq_flags & RQF_NOMERGE_FLAGS)
@@ -842,8 +890,7 @@ static inline void rq_flush_dcache_pages(struct request *rq)
 
 extern int blk_register_queue(struct gendisk *disk);
 extern void blk_unregister_queue(struct gendisk *disk);
-extern blk_qc_t generic_make_request(struct bio *bio);
-extern blk_qc_t direct_make_request(struct bio *bio);
+blk_qc_t submit_bio_noacct(struct bio *bio);
 extern void blk_rq_init(struct request_queue *q, struct request *rq);
 extern void blk_put_request(struct request *);
 extern struct request *blk_get_request(struct request_queue *, unsigned int op,
@@ -857,7 +904,7 @@ extern void blk_rq_unprep_clone(struct request *rq);
 extern blk_status_t blk_insert_cloned_request(struct request_queue *q,
 				     struct request *rq);
 extern int blk_rq_append_bio(struct request *rq, struct bio **bio);
-extern void blk_queue_split(struct request_queue *, struct bio **);
+extern void blk_queue_split(struct bio **);
 extern int scsi_verify_blk_ioctl(struct block_device *, unsigned int);
 extern int scsi_cmd_blk_ioctl(struct block_device *, fmode_t,
 			      unsigned int, void __user *);
@@ -1060,7 +1107,6 @@ void blk_steal_bios(struct bio_list *list, struct request *rq);
 extern bool blk_update_request(struct request *rq, blk_status_t error,
 			       unsigned int nr_bytes);
 
-extern void __blk_complete_request(struct request *);
 extern void blk_abort_request(struct request *);
 
 /*
@@ -1081,6 +1127,8 @@ extern void blk_queue_max_write_same_sectors(struct request_queue *q,
 extern void blk_queue_max_write_zeroes_sectors(struct request_queue *q,
 		unsigned int max_write_same_sectors);
 extern void blk_queue_logical_block_size(struct request_queue *, unsigned int);
+extern void blk_queue_max_zone_append_sectors(struct request_queue *q,
+		unsigned int max_zone_append_sectors);
 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);
@@ -1093,15 +1141,9 @@ extern void blk_set_default_limits(struct queue_limits *lim);
 extern void blk_set_stacking_limits(struct queue_limits *lim);
 extern int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
 			    sector_t offset);
-extern int bdev_stack_limits(struct queue_limits *t, struct block_device *bdev,
-			    sector_t offset);
 extern void disk_stack_limits(struct gendisk *disk, struct block_device *bdev,
 			      sector_t offset);
-extern void blk_queue_stack_limits(struct request_queue *t, struct request_queue *b);
 extern void blk_queue_update_dma_pad(struct request_queue *, unsigned int);
-extern int blk_queue_dma_drain(struct request_queue *q,
-			       dma_drain_needed_fn *dma_drain_needed,
-			       void *buf, unsigned int size);
 extern void blk_queue_segment_boundary(struct request_queue *, unsigned long);
 extern void blk_queue_virt_boundary(struct request_queue *, unsigned long);
 extern void blk_queue_dma_alignment(struct request_queue *, int);
@@ -1138,15 +1180,23 @@ static inline unsigned short blk_rq_nr_discard_segments(struct request *rq)
 	return max_t(unsigned short, rq->nr_phys_segments, 1);
 }
 
-extern int blk_rq_map_sg(struct request_queue *, struct request *, struct scatterlist *);
+int __blk_rq_map_sg(struct request_queue *q, struct request *rq,
+		struct scatterlist *sglist, struct scatterlist **last_sg);
+static inline int blk_rq_map_sg(struct request_queue *q, struct request *rq,
+		struct scatterlist *sglist)
+{
+	struct scatterlist *last_sg = NULL;
+
+	return __blk_rq_map_sg(q, rq, sglist, &last_sg);
+}
 extern void blk_dump_rq_flags(struct request *, char *);
-extern long nr_blockdev_pages(void);
 
 bool __must_check blk_get_queue(struct request_queue *);
-struct request_queue *blk_alloc_queue(make_request_fn make_request, int node_id);
+struct request_queue *blk_alloc_queue(int node_id);
 extern void blk_put_queue(struct request_queue *);
 extern void blk_set_queue_dying(struct request_queue *);
 
+#ifdef CONFIG_BLOCK
 /*
  * blk_plug permits building a queue of related requests by holding the I/O
  * fragments for a short period. This allows merging of sequential requests
@@ -1164,6 +1214,7 @@ struct blk_plug {
 	struct list_head cb_list; /* md requires an unplug callback */
 	unsigned short rq_count;
 	bool multiple_queues;
+	bool nowait;
 };
 #define BLK_MAX_REQUEST_COUNT 16
 #define BLK_PLUG_FLUSH_SIZE (128 * 1024)
@@ -1206,7 +1257,47 @@ static inline bool blk_needs_flush_plug(struct task_struct *tsk)
 		 !list_empty(&plug->cb_list));
 }
 
-extern int blkdev_issue_flush(struct block_device *, gfp_t, sector_t *);
+int blkdev_issue_flush(struct block_device *, gfp_t);
+long nr_blockdev_pages(void);
+#else /* CONFIG_BLOCK */
+struct blk_plug {
+};
+
+static inline void blk_start_plug(struct blk_plug *plug)
+{
+}
+
+static inline void blk_finish_plug(struct blk_plug *plug)
+{
+}
+
+static inline void blk_flush_plug(struct task_struct *task)
+{
+}
+
+static inline void blk_schedule_flush_plug(struct task_struct *task)
+{
+}
+
+
+static inline bool blk_needs_flush_plug(struct task_struct *tsk)
+{
+	return false;
+}
+
+static inline int blkdev_issue_flush(struct block_device *bdev, gfp_t gfp_mask)
+{
+	return 0;
+}
+
+static inline long nr_blockdev_pages(void)
+{
+	return 0;
+}
+#endif /* CONFIG_BLOCK */
+
+extern void blk_io_schedule(void);
+
 extern int blkdev_issue_write_same(struct block_device *bdev, sector_t sector,
 		sector_t nr_sects, gfp_t gfp_mask, struct page *page);
 
@@ -1293,6 +1384,11 @@ static inline unsigned int queue_max_segment_size(const struct request_queue *q)
 	return q->limits.max_segment_size;
 }
 
+static inline unsigned int queue_max_zone_append_sectors(const struct request_queue *q)
+{
+	return q->limits.max_zone_append_sectors;
+}
+
 static inline unsigned queue_logical_block_size(const struct request_queue *q)
 {
 	int retval = 512;
@@ -1458,6 +1554,24 @@ static inline sector_t bdev_zone_sectors(struct block_device *bdev)
 	return 0;
 }
 
+static inline unsigned int bdev_max_open_zones(struct block_device *bdev)
+{
+	struct request_queue *q = bdev_get_queue(bdev);
+
+	if (q)
+		return queue_max_open_zones(q);
+	return 0;
+}
+
+static inline unsigned int bdev_max_active_zones(struct block_device *bdev)
+{
+	struct request_queue *q = bdev_get_queue(bdev);
+
+	if (q)
+		return queue_max_active_zones(q);
+	return 0;
+}
+
 static inline int queue_dma_alignment(const struct request_queue *q)
 {
 	return q ? q->dma_alignment : 511;
@@ -1483,7 +1597,7 @@ static inline unsigned int blksize_bits(unsigned int size)
 
 static inline unsigned int block_size(struct block_device *bdev)
 {
-	return bdev->bd_block_size;
+	return 1 << bdev->bd_inode->i_blkbits;
 }
 
 int kblockd_schedule_work(struct work_struct *work);
@@ -1551,6 +1665,12 @@ struct blk_integrity *bdev_get_integrity(struct block_device *bdev)
 	return blk_get_integrity(bdev->bd_disk);
 }
 
+static inline bool
+blk_integrity_queue_supports_integrity(struct request_queue *q)
+{
+	return q->integrity.profile;
+}
+
 static inline bool blk_integrity_rq(struct request *rq)
 {
 	return rq->cmd_flags & REQ_INTEGRITY;
@@ -1631,6 +1751,11 @@ static inline struct blk_integrity *blk_get_integrity(struct gendisk *disk)
 {
 	return NULL;
 }
+static inline bool
+blk_integrity_queue_supports_integrity(struct request_queue *q)
+{
+	return false;
+}
 static inline int blk_integrity_compare(struct gendisk *a, struct gendisk *b)
 {
 	return 0;
@@ -1682,7 +1807,27 @@ static inline struct bio_vec *rq_integrity_vec(struct request *rq)
 
 #endif /* CONFIG_BLK_DEV_INTEGRITY */
 
+#ifdef CONFIG_BLK_INLINE_ENCRYPTION
+
+bool blk_ksm_register(struct blk_keyslot_manager *ksm, struct request_queue *q);
+
+void blk_ksm_unregister(struct request_queue *q);
+
+#else /* CONFIG_BLK_INLINE_ENCRYPTION */
+
+static inline bool blk_ksm_register(struct blk_keyslot_manager *ksm,
+				    struct request_queue *q)
+{
+	return true;
+}
+
+static inline void blk_ksm_unregister(struct request_queue *q) { }
+
+#endif /* CONFIG_BLK_INLINE_ENCRYPTION */
+
+
 struct block_device_operations {
+	blk_qc_t (*submit_bio) (struct bio *bio);
 	int (*open) (struct block_device *, fmode_t);
 	void (*release) (struct gendisk *, fmode_t);
 	int (*rw_page)(struct block_device *, sector_t, struct page *, unsigned int);
@@ -1690,8 +1835,6 @@ struct block_device_operations {
 	int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
 	unsigned int (*check_events) (struct gendisk *disk,
 				      unsigned int clearing);
-	/* ->media_changed() is DEPRECATED, use ->check_events() instead */
-	int (*media_changed) (struct gendisk *);
 	void (*unlock_native_capacity) (struct gendisk *);
 	int (*revalidate_disk) (struct gendisk *);
 	int (*getgeo)(struct block_device *, struct hd_geometry *);
@@ -1719,6 +1862,7 @@ extern int bdev_write_page(struct block_device *, sector_t, struct page *,
 
 #ifdef CONFIG_BLK_DEV_ZONED
 bool blk_req_needs_zone_write_lock(struct request *rq);
+bool blk_req_zone_write_trylock(struct request *rq);
 void __blk_req_zone_write_lock(struct request *rq);
 void __blk_req_zone_write_unlock(struct request *rq);
 
@@ -1770,64 +1914,91 @@ static inline bool blk_req_can_dispatch_to_zone(struct request *rq)
 }
 #endif /* CONFIG_BLK_DEV_ZONED */
 
-#else /* CONFIG_BLOCK */
-
-struct block_device;
-
-/*
- * stubs for when the block layer is configured out
- */
-#define buffer_heads_over_limit 0
-
-static inline long nr_blockdev_pages(void)
+static inline void blk_wake_io_task(struct task_struct *waiter)
 {
-	return 0;
+	/*
+	 * If we're polling, the task itself is doing the completions. For
+	 * that case, we don't need to signal a wakeup, it's enough to just
+	 * mark us as RUNNING.
+	 */
+	if (waiter == current)
+		__set_current_state(TASK_RUNNING);
+	else
+		wake_up_process(waiter);
 }
 
-struct blk_plug {
-};
+unsigned long disk_start_io_acct(struct gendisk *disk, unsigned int sectors,
+		unsigned int op);
+void disk_end_io_acct(struct gendisk *disk, unsigned int op,
+		unsigned long start_time);
 
-static inline void blk_start_plug(struct blk_plug *plug)
+/**
+ * bio_start_io_acct - start I/O accounting for bio based drivers
+ * @bio:	bio to start account for
+ *
+ * Returns the start time that should be passed back to bio_end_io_acct().
+ */
+static inline unsigned long bio_start_io_acct(struct bio *bio)
 {
+	return disk_start_io_acct(bio->bi_disk, bio_sectors(bio), bio_op(bio));
 }
 
-static inline void blk_finish_plug(struct blk_plug *plug)
+/**
+ * bio_end_io_acct - end I/O accounting for bio based drivers
+ * @bio:	bio to end account for
+ * @start:	start time returned by bio_start_io_acct()
+ */
+static inline void bio_end_io_acct(struct bio *bio, unsigned long start_time)
 {
+	return disk_end_io_acct(bio->bi_disk, bio_op(bio), start_time);
 }
 
-static inline void blk_flush_plug(struct task_struct *task)
-{
-}
+int bdev_read_only(struct block_device *bdev);
+int set_blocksize(struct block_device *bdev, int size);
 
-static inline void blk_schedule_flush_plug(struct task_struct *task)
-{
-}
+const char *bdevname(struct block_device *bdev, char *buffer);
+struct block_device *lookup_bdev(const char *);
 
+void blkdev_show(struct seq_file *seqf, off_t offset);
 
-static inline bool blk_needs_flush_plug(struct task_struct *tsk)
+#define BDEVNAME_SIZE	32	/* Largest string for a blockdev identifier */
+#define BDEVT_SIZE	10	/* Largest string for MAJ:MIN for blkdev */
+#ifdef CONFIG_BLOCK
+#define BLKDEV_MAJOR_MAX	512
+#else
+#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);
+int bd_prepare_to_claim(struct block_device *bdev, struct block_device *whole,
+		void *holder);
+void bd_abort_claiming(struct block_device *bdev, struct block_device *whole,
+		void *holder);
+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 *bdgrab(struct block_device *bdev);
+void bdput(struct block_device *);
+
+#ifdef CONFIG_BLOCK
+void invalidate_bdev(struct block_device *bdev);
+int sync_blockdev(struct block_device *bdev);
+#else
+static inline void invalidate_bdev(struct block_device *bdev)
 {
-	return false;
 }
-
-static inline int blkdev_issue_flush(struct block_device *bdev, gfp_t gfp_mask,
-				     sector_t *error_sector)
+static inline int sync_blockdev(struct block_device *bdev)
 {
 	return 0;
 }
+#endif
+int fsync_bdev(struct block_device *bdev);
 
-#endif /* CONFIG_BLOCK */
-
-static inline void blk_wake_io_task(struct task_struct *waiter)
-{
-	/*
-	 * If we're polling, the task itself is doing the completions. For
-	 * that case, we don't need to signal a wakeup, it's enough to just
-	 * mark us as RUNNING.
-	 */
-	if (waiter == current)
-		__set_current_state(TASK_RUNNING);
-	else
-		wake_up_process(waiter);
-}
+struct super_block *freeze_bdev(struct block_device *bdev);
+int thaw_bdev(struct block_device *bdev, struct super_block *sb);
 
-#endif
+#endif /* _LINUX_BLKDEV_H */