Merge branch 'for-2.6.38/core' of git://git.kernel.dk/linux-2.6-block

* 'for-2.6.38/core' of git://git.kernel.dk/linux-2.6-block: (43 commits)
  block: ensure that completion error gets properly traced
  blktrace: add missing probe argument to block_bio_complete
  block cfq: don't use atomic_t for cfq_group
  block cfq: don't use atomic_t for cfq_queue
  block: trace event block fix unassigned field
  block: add internal hd part table references
  block: fix accounting bug on cross partition merges
  kref: add kref_test_and_get
  bio-integrity: mark kintegrityd_wq highpri and CPU intensive
  block: make kblockd_workqueue smarter
  Revert "sd: implement sd_check_events()"
  block: Clean up exit_io_context() source code.
  Fix compile warnings due to missing removal of a 'ret' variable
  fs/block: type signature of major_to_index(int) to major_to_index(unsigned)
  block: convert !IS_ERR(p) && p to !IS_ERR_NOR_NULL(p)
  cfq-iosched: don't check cfqg in choose_service_tree()
  fs/splice: Pull buf->ops->confirm() from splice_from_pipe actors
  cdrom: export cdrom_check_events()
  sd: implement sd_check_events()
  sr: implement sr_check_events()
  ...

6 files changed, 74 insertions, 21 deletions

diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 36ab42c9bb99..4d18ff34670a 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -115,6 +115,7 @@ struct request {
 	void *elevator_private3;
 
 	struct gendisk *rq_disk;
+	struct hd_struct *part;
 	unsigned long start_time;
 #ifdef CONFIG_BLK_CGROUP
 	unsigned long long start_time_ns;
@@ -646,7 +647,6 @@ 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 void register_disk(struct gendisk *dev);
 extern void generic_make_request(struct bio *bio);
 extern void blk_rq_init(struct request_queue *q, struct request *rq);
 extern void blk_put_request(struct request *);
@@ -1256,6 +1256,9 @@ struct block_device_operations {
 	int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
 	int (*direct_access) (struct block_device *, sector_t,
 						void **, 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 *);
diff --git a/include/linux/cdrom.h b/include/linux/cdrom.h
index 78e904796622..35eae4b67503 100644
--- a/include/linux/cdrom.h
+++ b/include/linux/cdrom.h
@@ -946,6 +946,8 @@ struct cdrom_device_info {
 /* device-related storage */
 	unsigned int options	: 30;	/* options flags */
 	unsigned mc_flags	: 2;	/* media change buffer flags */
+	unsigned int vfs_events;	/* cached events for vfs path */
+	unsigned int ioctl_events;	/* cached events for ioctl path */
     	int use_count;                  /* number of times device opened */
     	char name[20];                  /* name of the device type */
 /* per-device flags */
@@ -965,6 +967,8 @@ struct cdrom_device_ops {
 	int (*open) (struct cdrom_device_info *, int);
 	void (*release) (struct cdrom_device_info *);
 	int (*drive_status) (struct cdrom_device_info *, int);
+	unsigned int (*check_events) (struct cdrom_device_info *cdi,
+				      unsigned int clearing, int slot);
 	int (*media_changed) (struct cdrom_device_info *, int);
 	int (*tray_move) (struct cdrom_device_info *, int);
 	int (*lock_door) (struct cdrom_device_info *, int);
@@ -993,6 +997,8 @@ extern int cdrom_open(struct cdrom_device_info *cdi, struct block_device *bdev,
 extern void cdrom_release(struct cdrom_device_info *cdi, fmode_t mode);
 extern int cdrom_ioctl(struct cdrom_device_info *cdi, struct block_device *bdev,
 		       fmode_t mode, unsigned int cmd, unsigned long arg);
+extern unsigned int cdrom_check_events(struct cdrom_device_info *cdi,
+				       unsigned int clearing);
 extern int cdrom_media_changed(struct cdrom_device_info *);
 
 extern int register_cdrom(struct cdrom_device_info *cdi);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index c0701288d204..3984f2358d1f 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -664,8 +664,9 @@ struct block_device {
 	void *			bd_claiming;
 	void *			bd_holder;
 	int			bd_holders;
+	bool			bd_write_holder;
 #ifdef CONFIG_SYSFS
-	struct list_head	bd_holder_list;
+	struct gendisk *	bd_holder_disk;	/* for sysfs slave linkng */
 #endif
 	struct block_device *	bd_contains;
 	unsigned		bd_block_size;
@@ -2019,7 +2020,6 @@ extern struct block_device *bdgrab(struct block_device *bdev);
 extern void bd_set_size(struct block_device *, loff_t size);
 extern void bd_forget(struct inode *inode);
 extern void bdput(struct block_device *);
-extern struct block_device *open_by_devnum(dev_t, fmode_t);
 extern void invalidate_bdev(struct block_device *);
 extern int sync_blockdev(struct block_device *bdev);
 extern struct super_block *freeze_bdev(struct block_device *);
@@ -2050,16 +2050,20 @@ extern const struct file_operations def_fifo_fops;
 extern int ioctl_by_bdev(struct block_device *, unsigned, unsigned long);
 extern int blkdev_ioctl(struct block_device *, fmode_t, unsigned, unsigned long);
 extern long compat_blkdev_ioctl(struct file *, unsigned, unsigned long);
-extern int blkdev_get(struct block_device *, fmode_t);
-extern int blkdev_put(struct block_device *, fmode_t);
-extern int bd_claim(struct block_device *, void *);
-extern void bd_release(struct block_device *);
+extern int blkdev_get(struct block_device *bdev, fmode_t mode, void *holder);
+extern struct block_device *blkdev_get_by_path(const char *path, fmode_t mode,
+					       void *holder);
+extern struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode,
+					      void *holder);
+extern int blkdev_put(struct block_device *bdev, fmode_t mode);
 #ifdef CONFIG_SYSFS
-extern int bd_claim_by_disk(struct block_device *, void *, struct gendisk *);
-extern void bd_release_from_disk(struct block_device *, struct gendisk *);
+extern int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk);
 #else
-#define bd_claim_by_disk(bdev, holder, disk)	bd_claim(bdev, holder)
-#define bd_release_from_disk(bdev, disk)	bd_release(bdev)
+static inline int bd_link_disk_holder(struct block_device *bdev,
+				      struct gendisk *disk)
+{
+	return 0;
+}
 #endif
 #endif
 
@@ -2095,8 +2099,6 @@ static inline void unregister_chrdev(unsigned int major, const char *name)
 extern const char *__bdevname(dev_t, char *buffer);
 extern const char *bdevname(struct block_device *bdev, char *buffer);
 extern struct block_device *lookup_bdev(const char *);
-extern struct block_device *open_bdev_exclusive(const char *, fmode_t, void *);
-extern void close_bdev_exclusive(struct block_device *, fmode_t);
 extern void blkdev_show(struct seq_file *,off_t);
 
 #else
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index 7a7b9c1644e4..c0d5f6945c1e 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -115,6 +115,7 @@ struct hd_struct {
 #else
 	struct disk_stats dkstats;
 #endif
+	atomic_t ref;
 	struct rcu_head rcu_head;
 };
 
@@ -127,6 +128,11 @@ struct hd_struct {
 #define GENHD_FL_EXT_DEVT			64 /* allow extended devt */
 #define GENHD_FL_NATIVE_CAPACITY		128
 
+enum {
+	DISK_EVENT_MEDIA_CHANGE			= 1 << 0, /* media changed */
+	DISK_EVENT_EJECT_REQUEST		= 1 << 1, /* eject requested */
+};
+
 #define BLK_SCSI_MAX_CMDS	(256)
 #define BLK_SCSI_CMD_PER_LONG	(BLK_SCSI_MAX_CMDS / (sizeof(long) * 8))
 
@@ -143,6 +149,8 @@ struct disk_part_tbl {
 	struct hd_struct __rcu *part[];
 };
 
+struct disk_events;
+
 struct gendisk {
 	/* major, first_minor and minors are input parameters only,
 	 * don't use directly.  Use disk_devt() and disk_max_parts().
@@ -154,6 +162,10 @@ struct gendisk {
 
 	char disk_name[DISK_NAME_LEN];	/* name of major driver */
 	char *(*devnode)(struct gendisk *gd, mode_t *mode);
+
+	unsigned int events;		/* supported events */
+	unsigned int async_events;	/* async events, subset of all */
+
 	/* Array of pointers to partitions indexed by partno.
 	 * Protected with matching bdev lock but stat and other
 	 * non-critical accesses use RCU.  Always access through
@@ -171,9 +183,8 @@ struct gendisk {
 	struct kobject *slave_dir;
 
 	struct timer_rand_state *random;
-
 	atomic_t sync_io;		/* RAID */
-	struct work_struct async_notify;
+	struct disk_events *ev;
 #ifdef  CONFIG_BLK_DEV_INTEGRITY
 	struct blk_integrity *integrity;
 #endif
@@ -395,7 +406,6 @@ extern void part_round_stats(int cpu, struct hd_struct *part);
 /* block/genhd.c */
 extern void add_disk(struct gendisk *disk);
 extern void del_gendisk(struct gendisk *gp);
-extern void unlink_gendisk(struct gendisk *gp);
 extern struct gendisk *get_gendisk(dev_t dev, int *partno);
 extern struct block_device *bdget_disk(struct gendisk *disk, int partno);
 
@@ -407,6 +417,11 @@ static inline int get_disk_ro(struct gendisk *disk)
 	return disk->part0.policy;
 }
 
+extern void disk_block_events(struct gendisk *disk);
+extern void disk_unblock_events(struct gendisk *disk);
+extern void disk_check_events(struct gendisk *disk);
+extern unsigned int disk_clear_events(struct gendisk *disk, unsigned int mask);
+
 /* drivers/char/random.c */
 extern void add_disk_randomness(struct gendisk *disk);
 extern void rand_initialize_disk(struct gendisk *disk);
@@ -583,6 +598,7 @@ extern struct hd_struct * __must_check add_partition(struct gendisk *disk,
 						     sector_t len, int flags,
 						     struct partition_meta_info
 						       *info);
+extern void __delete_partition(struct hd_struct *);
 extern void delete_partition(struct gendisk *, int);
 extern void printk_all_partitions(void);
 
@@ -611,6 +627,29 @@ extern ssize_t part_fail_store(struct device *dev,
 			       const char *buf, size_t count);
 #endif /* CONFIG_FAIL_MAKE_REQUEST */
 
+static inline void hd_ref_init(struct hd_struct *part)
+{
+	atomic_set(&part->ref, 1);
+	smp_mb();
+}
+
+static inline void hd_struct_get(struct hd_struct *part)
+{
+	atomic_inc(&part->ref);
+	smp_mb__after_atomic_inc();
+}
+
+static inline int hd_struct_try_get(struct hd_struct *part)
+{
+	return atomic_inc_not_zero(&part->ref);
+}
+
+static inline void hd_struct_put(struct hd_struct *part)
+{
+	if (atomic_dec_and_test(&part->ref))
+		__delete_partition(part);
+}
+
 #else /* CONFIG_BLOCK */
 
 static inline void printk_all_partitions(void) { }
diff --git a/include/scsi/scsi.h b/include/scsi/scsi.h
index 1651fef18831..648d23358038 100644
--- a/include/scsi/scsi.h
+++ b/include/scsi/scsi.h
@@ -104,6 +104,7 @@ struct scsi_cmnd;
 #define UNMAP		      0x42
 #define READ_TOC              0x43
 #define READ_HEADER           0x44
+#define GET_EVENT_STATUS_NOTIFICATION 0x4a
 #define LOG_SELECT            0x4c
 #define LOG_SENSE             0x4d
 #define XDWRITEREAD_10        0x53
diff --git a/include/trace/events/block.h b/include/trace/events/block.h
index d8ce278515c3..aba421d68f6f 100644
--- a/include/trace/events/block.h
+++ b/include/trace/events/block.h
@@ -206,15 +206,16 @@ TRACE_EVENT(block_bio_bounce,
  * block_bio_complete - completed all work on the block operation
  * @q: queue holding the block operation
  * @bio: block operation completed
+ * @error: io error value
  *
  * This tracepoint indicates there is no further work to do on this
  * block IO operation @bio.
  */
 TRACE_EVENT(block_bio_complete,
 
-	TP_PROTO(struct request_queue *q, struct bio *bio),
+	TP_PROTO(struct request_queue *q, struct bio *bio, int error),
 
-	TP_ARGS(q, bio),
+	TP_ARGS(q, bio, error),
 
 	TP_STRUCT__entry(
 		__field( dev_t,		dev		)
@@ -228,6 +229,7 @@ TRACE_EVENT(block_bio_complete,
 		__entry->dev		= bio->bi_bdev->bd_dev;
 		__entry->sector		= bio->bi_sector;
 		__entry->nr_sector	= bio->bi_size >> 9;
+		__entry->error		= error;
 		blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_size);
 	),
 
@@ -486,16 +488,16 @@ TRACE_EVENT(block_split,
 );
 
 /**
- * block_remap - map request for a partition to the raw device
+ * block_bio_remap - map request for a logical device to the raw device
  * @q: queue holding the operation
  * @bio: revised operation
  * @dev: device for the operation
  * @from: original sector for the operation
  *
- * An operation for a partition on a block device has been mapped to the
+ * An operation for a logical device has been mapped to the
  * raw block device.
  */
-TRACE_EVENT(block_remap,
+TRACE_EVENT(block_bio_remap,
 
 	TP_PROTO(struct request_queue *q, struct bio *bio, dev_t dev,
 		 sector_t from),