Merge branch 'for-3.20/core' of git://git.kernel.dk/linux-block

Pull core block IO changes from Jens Axboe:
 "This contains:

   - A series from Christoph that cleans up and refactors various parts
     of the REQ_BLOCK_PC handling.  Contributions in that series from
     Dongsu Park and Kent Overstreet as well.

   - CFQ:
        - A bug fix for cfq for realtime IO scheduling from Jeff Moyer.
        - A stable patch fixing a potential crash in CFQ in OOM
          situations.  From Konstantin Khlebnikov.

   - blk-mq:
        - Add support for tag allocation policies, from Shaohua. This is
          a prep patch enabling libata (and other SCSI parts) to use the
          blk-mq tagging, instead of rolling their own.
        - Various little tweaks from Keith and Mike, in preparation for
          DM blk-mq support.
        - Minor little fixes or tweaks from me.
        - A double free error fix from Tony Battersby.

   - The partition 4k issue fixes from Matthew and Boaz.

   - Add support for zero+unprovision for blkdev_issue_zeroout() from
     Martin"

* 'for-3.20/core' of git://git.kernel.dk/linux-block: (27 commits)
  block: remove unused function blk_bio_map_sg
  block: handle the null_mapped flag correctly in blk_rq_map_user_iov
  blk-mq: fix double-free in error path
  block: prevent request-to-request merging with gaps if not allowed
  blk-mq: make blk_mq_run_queues() static
  dm: fix multipath regression due to initializing wrong request
  cfq-iosched: handle failure of cfq group allocation
  block: Quiesce zeroout wrapper
  block: rewrite and split __bio_copy_iov()
  block: merge __bio_map_user_iov into bio_map_user_iov
  block: merge __bio_map_kern into bio_map_kern
  block: pass iov_iter to the BLOCK_PC mapping functions
  block: add a helper to free bio bounce buffer pages
  block: use blk_rq_map_user_iov to implement blk_rq_map_user
  block: simplify bio_map_kern
  block: mark blk-mq devices as stackable
  block: keep established cmd_flags when cloning into a blk-mq request
  block: add blk-mq support to blk_insert_cloned_request()
  block: require blk_rq_prep_clone() be given an initialized clone request
  blk-mq: add tag allocation policy
  ...

5 files changed, 32 insertions, 21 deletions

diff --git a/include/linux/bio.h b/include/linux/bio.h
index efead0b532c4..da3a127c9958 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -428,13 +428,9 @@ extern int bio_add_page(struct bio *, struct page *, unsigned int,unsigned int);
 extern int bio_add_pc_page(struct request_queue *, struct bio *, struct page *,
 			   unsigned int, unsigned int);
 extern int bio_get_nr_vecs(struct block_device *);
-extern struct bio *bio_map_user(struct request_queue *, struct block_device *,
-				unsigned long, unsigned int, int, gfp_t);
-struct sg_iovec;
 struct rq_map_data;
 extern struct bio *bio_map_user_iov(struct request_queue *,
-				    struct block_device *,
-				    const struct sg_iovec *, int, int, gfp_t);
+				    const struct iov_iter *, gfp_t);
 extern void bio_unmap_user(struct bio *);
 extern struct bio *bio_map_kern(struct request_queue *, void *, unsigned int,
 				gfp_t);
@@ -462,12 +458,10 @@ static inline void bio_flush_dcache_pages(struct bio *bi)
 extern void bio_copy_data(struct bio *dst, struct bio *src);
 extern int bio_alloc_pages(struct bio *bio, gfp_t gfp);
 
-extern struct bio *bio_copy_user(struct request_queue *, struct rq_map_data *,
-				 unsigned long, unsigned int, int, gfp_t);
 extern struct bio *bio_copy_user_iov(struct request_queue *,
 				     struct rq_map_data *,
-				     const struct sg_iovec *,
-				     int, int, gfp_t);
+				     const struct iov_iter *,
+				     gfp_t);
 extern int bio_uncopy_user(struct bio *);
 void zero_fill_bio(struct bio *bio);
 extern struct bio_vec *bvec_alloc(gfp_t, int, unsigned long *, mempool_t *);
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 5735e7130d63..7aec86127335 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -146,6 +146,8 @@ enum {
 	BLK_MQ_F_SG_MERGE	= 1 << 2,
 	BLK_MQ_F_SYSFS_UP	= 1 << 3,
 	BLK_MQ_F_DEFER_ISSUE	= 1 << 4,
+	BLK_MQ_F_ALLOC_POLICY_START_BIT = 8,
+	BLK_MQ_F_ALLOC_POLICY_BITS = 1,
 
 	BLK_MQ_S_STOPPED	= 0,
 	BLK_MQ_S_TAG_ACTIVE	= 1,
@@ -154,6 +156,12 @@ enum {
 
 	BLK_MQ_CPU_WORK_BATCH	= 8,
 };
+#define BLK_MQ_FLAG_TO_ALLOC_POLICY(flags) \
+	((flags >> BLK_MQ_F_ALLOC_POLICY_START_BIT) & \
+		((1 << BLK_MQ_F_ALLOC_POLICY_BITS) - 1))
+#define BLK_ALLOC_POLICY_TO_MQ_FLAG(policy) \
+	((policy & ((1 << BLK_MQ_F_ALLOC_POLICY_BITS) - 1)) \
+		<< BLK_MQ_F_ALLOC_POLICY_START_BIT)
 
 struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *);
 void blk_mq_finish_init(struct request_queue *q);
@@ -166,7 +174,6 @@ void blk_mq_free_tag_set(struct blk_mq_tag_set *set);
 void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule);
 
 void blk_mq_insert_request(struct request *, bool, bool, bool);
-void blk_mq_run_queues(struct request_queue *q, bool async);
 void blk_mq_free_request(struct request *rq);
 void blk_mq_free_hctx_request(struct blk_mq_hw_ctx *, struct request *rq);
 bool blk_mq_can_queue(struct blk_mq_hw_ctx *);
@@ -214,6 +221,7 @@ void blk_mq_start_stopped_hw_queues(struct request_queue *q, bool async);
 void blk_mq_delay_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs);
 void blk_mq_tag_busy_iter(struct blk_mq_hw_ctx *hctx, busy_iter_fn *fn,
 		void *priv);
+void blk_mq_freeze_queue(struct request_queue *q);
 void blk_mq_unfreeze_queue(struct request_queue *q);
 void blk_mq_freeze_queue_start(struct request_queue *q);
 
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 92f4b4b288dd..7f9a516f24de 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -272,7 +272,11 @@ struct blk_queue_tag {
 	int max_depth;			/* what we will send to device */
 	int real_max_depth;		/* what the array can hold */
 	atomic_t refcnt;		/* map can be shared */
+	int alloc_policy;		/* tag allocation policy */
+	int next_tag;			/* next tag */
 };
+#define BLK_TAG_ALLOC_FIFO 0 /* allocate starting from 0 */
+#define BLK_TAG_ALLOC_RR 1 /* allocate starting from last allocated tag */
 
 #define BLK_SCSI_MAX_CMDS	(256)
 #define BLK_SCSI_CMD_PER_LONG	(BLK_SCSI_MAX_CMDS / (sizeof(long) * 8))
@@ -516,6 +520,7 @@ struct request_queue {
 				 (1 << QUEUE_FLAG_ADD_RANDOM))
 
 #define QUEUE_FLAG_MQ_DEFAULT	((1 << QUEUE_FLAG_IO_STAT) |		\
+				 (1 << QUEUE_FLAG_STACKABLE)	|	\
 				 (1 << QUEUE_FLAG_SAME_COMP))
 
 static inline void queue_lockdep_assert_held(struct request_queue *q)
@@ -850,8 +855,8 @@ extern int blk_rq_map_user(struct request_queue *, struct request *,
 extern int blk_rq_unmap_user(struct bio *);
 extern int blk_rq_map_kern(struct request_queue *, struct request *, void *, unsigned int, gfp_t);
 extern int blk_rq_map_user_iov(struct request_queue *, struct request *,
-			       struct rq_map_data *, const struct sg_iovec *,
-			       int, unsigned int, gfp_t);
+			       struct rq_map_data *, const struct iov_iter *,
+			       gfp_t);
 extern int blk_execute_rq(struct request_queue *, struct gendisk *,
 			  struct request *, int);
 extern void blk_execute_rq_nowait(struct request_queue *, struct gendisk *,
@@ -1044,8 +1049,6 @@ extern void blk_queue_flush_queueable(struct request_queue *q, bool queueable);
 extern struct backing_dev_info *blk_get_backing_dev_info(struct block_device *bdev);
 
 extern int blk_rq_map_sg(struct request_queue *, struct request *, struct scatterlist *);
-extern int blk_bio_map_sg(struct request_queue *q, struct bio *bio,
-			  struct scatterlist *sglist);
 extern void blk_dump_rq_flags(struct request *, char *);
 extern long nr_blockdev_pages(void);
 
@@ -1139,11 +1142,11 @@ static inline bool blk_needs_flush_plug(struct task_struct *tsk)
 extern int blk_queue_start_tag(struct request_queue *, struct request *);
 extern struct request *blk_queue_find_tag(struct request_queue *, int);
 extern void blk_queue_end_tag(struct request_queue *, struct request *);
-extern int blk_queue_init_tags(struct request_queue *, int, struct blk_queue_tag *);
+extern int blk_queue_init_tags(struct request_queue *, int, struct blk_queue_tag *, int);
 extern void blk_queue_free_tags(struct request_queue *);
 extern int blk_queue_resize_tags(struct request_queue *, int);
 extern void blk_queue_invalidate_tags(struct request_queue *);
-extern struct blk_queue_tag *blk_init_tags(int);
+extern struct blk_queue_tag *blk_init_tags(int, int);
 extern void blk_free_tags(struct blk_queue_tag *);
 
 static inline struct request *blk_map_queue_find_tag(struct blk_queue_tag *bqt,
@@ -1162,7 +1165,7 @@ extern int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 extern int blkdev_issue_write_same(struct block_device *bdev, sector_t sector,
 		sector_t nr_sects, gfp_t gfp_mask, struct page *page);
 extern int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
-			sector_t nr_sects, gfp_t gfp_mask);
+		sector_t nr_sects, gfp_t gfp_mask, bool discard);
 static inline int sb_issue_discard(struct super_block *sb, sector_t block,
 		sector_t nr_blocks, gfp_t gfp_mask, unsigned long flags)
 {
@@ -1176,7 +1179,7 @@ static inline int sb_issue_zeroout(struct super_block *sb, sector_t block,
 	return blkdev_issue_zeroout(sb->s_bdev,
 				    block << (sb->s_blocksize_bits - 9),
 				    nr_blocks << (sb->s_blocksize_bits - 9),
-				    gfp_mask);
+				    gfp_mask, true);
 }
 
 extern int blk_verify_command(unsigned char *cmd, fmode_t has_write_perm);
@@ -1601,8 +1604,8 @@ struct block_device_operations {
 	int (*rw_page)(struct block_device *, sector_t, struct page *, int rw);
 	int (*ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
 	int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
-	int (*direct_access) (struct block_device *, sector_t,
-						void **, unsigned long *);
+	long (*direct_access)(struct block_device *, sector_t,
+					void **, unsigned long *pfn, long size);
 	unsigned int (*check_events) (struct gendisk *disk,
 				      unsigned int clearing);
 	/* ->media_changed() is DEPRECATED, use ->check_events() instead */
@@ -1620,6 +1623,8 @@ 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 *);
+extern long bdev_direct_access(struct block_device *, sector_t, void **addr,
+						unsigned long *pfn, long size);
 #else /* CONFIG_BLOCK */
 
 struct block_device;
diff --git a/include/scsi/scsi_host.h b/include/scsi/scsi_host.h
index 019e66858ce6..e113c757d555 100644
--- a/include/scsi/scsi_host.h
+++ b/include/scsi/scsi_host.h
@@ -402,6 +402,9 @@ struct scsi_host_template {
 	 */
 	unsigned char present;
 
+	/* If use block layer to manage tags, this is tag allocation policy */
+	int tag_alloc_policy;
+
 	/*
 	 * Let the block layer assigns tags to all commands.
 	 */
diff --git a/include/scsi/scsi_tcq.h b/include/scsi/scsi_tcq.h
index 9708b28bd2aa..b27977e8aaed 100644
--- a/include/scsi/scsi_tcq.h
+++ b/include/scsi/scsi_tcq.h
@@ -66,7 +66,8 @@ static inline int scsi_init_shared_tag_map(struct Scsi_Host *shost, int depth)
 	 * devices on the shared host (for libata)
 	 */
 	if (!shost->bqt) {
-		shost->bqt = blk_init_tags(depth);
+		shost->bqt = blk_init_tags(depth,
+			shost->hostt->tag_alloc_policy);
 		if (!shost->bqt)
 			return -ENOMEM;
 	}