Merge branch 'for-2.6.35' of git://git.kernel.dk/linux-2.6-block

* 'for-2.6.35' of git://git.kernel.dk/linux-2.6-block: (86 commits)
  pipe: set lower and upper limit on max pages in the pipe page array
  pipe: add support for shrinking and growing pipes
  drbd: This is now equivalent to drbd release 8.3.8rc1
  drbd: Do not free p_uuid early, this is done in the exit code of the receiver
  drbd: Null pointer deref fix to the large "multi bio rewrite"
  drbd: Fix: Do not detach, if a bio with a barrier fails
  drbd: Ensure to not trigger late-new-UUID creation multiple times
  drbd: Do not Oops when C_STANDALONE when uuid gets generated
  writeback: fix mixed up arguments to bdi_start_writeback()
  writeback: fix problem with !CONFIG_BLOCK compilation
  block: improve automatic native capacity unlocking
  block: use struct parsed_partitions *state universally in partition check code
  block,ide: simplify bdops->set_capacity() to ->unlock_native_capacity()
  block: restart partition scan after resizing a device
  buffer: make invalidate_bdev() drain all percpu LRU add caches
  block: remove all rcu head initializations
  writeback: fixups for !dirty_writeback_centisecs
  writeback: bdi_writeback_task() must set task state before calling schedule()
  writeback: ensure that WB_SYNC_NONE writeback with sb pinned is sync
  drivers/block/drbd: Use kzalloc
  ...

12 files changed, 134 insertions, 21 deletions

diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index bd0e3c6f323f..e6e0cb5437e6 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -14,6 +14,7 @@
 #include <linux/kernel.h>
 #include <linux/fs.h>
 #include <linux/sched.h>
+#include <linux/timer.h>
 #include <linux/writeback.h>
 #include <asm/atomic.h>
 
@@ -88,6 +89,8 @@ struct backing_dev_info {
 
 	struct device *dev;
 
+	struct timer_list laptop_mode_wb_timer;
+
 #ifdef CONFIG_DEBUG_FS
 	struct dentry *debug_dir;
 	struct dentry *debug_stats;
@@ -103,9 +106,10 @@ int bdi_register_dev(struct backing_dev_info *bdi, dev_t dev);
 void bdi_unregister(struct backing_dev_info *bdi);
 int bdi_setup_and_register(struct backing_dev_info *, char *, unsigned int);
 void bdi_start_writeback(struct backing_dev_info *bdi, struct super_block *sb,
-				long nr_pages);
+				long nr_pages, int sb_locked);
 int bdi_writeback_task(struct bdi_writeback *wb);
 int bdi_has_dirty_io(struct backing_dev_info *bdi);
+void bdi_arm_supers_timer(void);
 
 extern spinlock_t bdi_lock;
 extern struct list_head bdi_list;
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 6690e8bae7bb..be411c12ebbe 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -186,15 +186,19 @@ struct request {
 	};
 
 	/*
-	 * two pointers are available for the IO schedulers, if they need
+	 * Three pointers are available for the IO schedulers, if they need
 	 * more they have to dynamically allocate it.
 	 */
 	void *elevator_private;
 	void *elevator_private2;
+	void *elevator_private3;
 
 	struct gendisk *rq_disk;
 	unsigned long start_time;
-
+#ifdef CONFIG_BLK_CGROUP
+	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.
 	 */
@@ -917,7 +921,12 @@ extern void blk_abort_queue(struct request_queue *);
  */
 extern struct request_queue *blk_init_queue_node(request_fn_proc *rfn,
 					spinlock_t *lock, int node_id);
+extern struct request_queue *blk_init_allocated_queue_node(struct request_queue *,
+							   request_fn_proc *,
+							   spinlock_t *, int node_id);
 extern struct request_queue *blk_init_queue(request_fn_proc *, spinlock_t *);
+extern struct request_queue *blk_init_allocated_queue(struct request_queue *,
+						      request_fn_proc *, spinlock_t *);
 extern void blk_cleanup_queue(struct request_queue *);
 extern void blk_queue_make_request(struct request_queue *, make_request_fn *);
 extern void blk_queue_bounce_limit(struct request_queue *, u64);
@@ -994,20 +1003,25 @@ static inline struct request *blk_map_queue_find_tag(struct blk_queue_tag *bqt,
 		return NULL;
 	return bqt->tag_index[tag];
 }
-
-extern int blkdev_issue_flush(struct block_device *, sector_t *);
-#define DISCARD_FL_WAIT		0x01	/* wait for completion */
-#define DISCARD_FL_BARRIER	0x02	/* issue DISCARD_BARRIER request */
-extern int blkdev_issue_discard(struct block_device *, sector_t sector,
-		sector_t nr_sects, gfp_t, int flags);
-
+enum{
+	BLKDEV_WAIT,	/* wait for completion */
+	BLKDEV_BARRIER,	/*issue request with barrier */
+};
+#define BLKDEV_IFL_WAIT		(1 << BLKDEV_WAIT)
+#define BLKDEV_IFL_BARRIER	(1 << BLKDEV_BARRIER)
+extern int blkdev_issue_flush(struct block_device *, gfp_t, sector_t *,
+			unsigned long);
+extern int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
+		sector_t nr_sects, gfp_t gfp_mask, unsigned long flags);
+extern int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
+			sector_t nr_sects, gfp_t gfp_mask, unsigned long flags);
 static inline int sb_issue_discard(struct super_block *sb,
 				   sector_t block, sector_t nr_blocks)
 {
 	block <<= (sb->s_blocksize_bits - 9);
 	nr_blocks <<= (sb->s_blocksize_bits - 9);
 	return blkdev_issue_discard(sb->s_bdev, block, nr_blocks, GFP_KERNEL,
-				    DISCARD_FL_BARRIER);
+				   BLKDEV_IFL_WAIT | BLKDEV_IFL_BARRIER);
 }
 
 extern int blk_verify_command(unsigned char *cmd, fmode_t has_write_perm);
@@ -1196,6 +1210,39 @@ static inline void put_dev_sector(Sector p)
 struct work_struct;
 int kblockd_schedule_work(struct request_queue *q, struct work_struct *work);
 
+#ifdef CONFIG_BLK_CGROUP
+static inline void set_start_time_ns(struct request *req)
+{
+	req->start_time_ns = sched_clock();
+}
+
+static inline void set_io_start_time_ns(struct request *req)
+{
+	req->io_start_time_ns = sched_clock();
+}
+
+static inline uint64_t rq_start_time_ns(struct request *req)
+{
+        return req->start_time_ns;
+}
+
+static inline uint64_t rq_io_start_time_ns(struct request *req)
+{
+        return req->io_start_time_ns;
+}
+#else
+static inline void set_start_time_ns(struct request *req) {}
+static inline void set_io_start_time_ns(struct request *req) {}
+static inline uint64_t rq_start_time_ns(struct request *req)
+{
+	return 0;
+}
+static inline uint64_t rq_io_start_time_ns(struct request *req)
+{
+	return 0;
+}
+#endif
+
 #define MODULE_ALIAS_BLOCKDEV(major,minor) \
 	MODULE_ALIAS("block-major-" __stringify(major) "-" __stringify(minor))
 #define MODULE_ALIAS_BLOCKDEV_MAJOR(major) \
@@ -1283,8 +1330,7 @@ struct block_device_operations {
 	int (*direct_access) (struct block_device *, sector_t,
 						void **, unsigned long *);
 	int (*media_changed) (struct gendisk *);
-	unsigned long long (*set_capacity) (struct gendisk *,
-						unsigned long long);
+	void (*unlock_native_capacity) (struct gendisk *);
 	int (*revalidate_disk) (struct gendisk *);
 	int (*getgeo)(struct block_device *, struct hd_geometry *);
 	struct module *owner;
diff --git a/include/linux/drbd.h b/include/linux/drbd.h
index 4341b1a97a34..68530521ad00 100644
--- a/include/linux/drbd.h
+++ b/include/linux/drbd.h
@@ -53,10 +53,10 @@
 
 
 extern const char *drbd_buildtag(void);
-#define REL_VERSION "8.3.7"
+#define REL_VERSION "8.3.8rc1"
 #define API_VERSION 88
 #define PRO_VERSION_MIN 86
-#define PRO_VERSION_MAX 92
+#define PRO_VERSION_MAX 94
 
 
 enum drbd_io_error_p {
@@ -139,6 +139,7 @@ enum drbd_ret_codes {
 	ERR_DATA_NOT_CURRENT	= 150,
 	ERR_CONNECTED		= 151, /* DRBD 8.3 only */
 	ERR_PERM		= 152,
+	ERR_NEED_APV_93		= 153,
 
 	/* insert new ones above this line */
 	AFTER_LAST_ERR_CODE
diff --git a/include/linux/drbd_limits.h b/include/linux/drbd_limits.h
index 51f47a586ad8..440b42e38e89 100644
--- a/include/linux/drbd_limits.h
+++ b/include/linux/drbd_limits.h
@@ -133,5 +133,21 @@
 #define DRBD_MAX_BIO_BVECS_MAX 128
 #define DRBD_MAX_BIO_BVECS_DEF 0
 
+#define DRBD_DP_VOLUME_MIN 4
+#define DRBD_DP_VOLUME_MAX 1048576
+#define DRBD_DP_VOLUME_DEF 16384
+
+#define DRBD_DP_INTERVAL_MIN 1
+#define DRBD_DP_INTERVAL_MAX 600
+#define DRBD_DP_INTERVAL_DEF 5
+
+#define DRBD_RS_THROTTLE_TH_MIN 1
+#define DRBD_RS_THROTTLE_TH_MAX 600
+#define DRBD_RS_THROTTLE_TH_DEF 20
+
+#define DRBD_RS_HOLD_OFF_TH_MIN 1
+#define DRBD_RS_HOLD_OFF_TH_MAX 6000
+#define DRBD_RS_HOLD_OFF_TH_DEF 100
+
 #undef RANGE
 #endif
diff --git a/include/linux/drbd_nl.h b/include/linux/drbd_nl.h
index f7431a4ca608..ce77a746fc9d 100644
--- a/include/linux/drbd_nl.h
+++ b/include/linux/drbd_nl.h
@@ -71,12 +71,17 @@ NL_PACKET(disconnect, 6, )
 NL_PACKET(resize, 7,
 	NL_INT64(		29,	T_MAY_IGNORE,	resize_size)
 	NL_BIT(			68,	T_MAY_IGNORE,	resize_force)
+	NL_BIT(			69,	T_MANDATORY,	no_resync)
 )
 
 NL_PACKET(syncer_conf, 8,
 	NL_INTEGER(	30,	T_MAY_IGNORE,	rate)
 	NL_INTEGER(	31,	T_MAY_IGNORE,	after)
 	NL_INTEGER(	32,	T_MAY_IGNORE,	al_extents)
+	NL_INTEGER(     71,	T_MAY_IGNORE,	dp_volume)
+	NL_INTEGER(     72,	T_MAY_IGNORE,	dp_interval)
+	NL_INTEGER(     73,	T_MAY_IGNORE,	throttle_th)
+	NL_INTEGER(     74,	T_MAY_IGNORE,	hold_off_th)
 	NL_STRING(      52,     T_MAY_IGNORE,   verify_alg,     SHARED_SECRET_MAX)
 	NL_STRING(      51,     T_MAY_IGNORE,   cpu_mask,       32)
 	NL_STRING(	64,	T_MAY_IGNORE,	csums_alg,	SHARED_SECRET_MAX)
diff --git a/include/linux/elevator.h b/include/linux/elevator.h
index 1cb3372e65d8..2c958f4fce1e 100644
--- a/include/linux/elevator.h
+++ b/include/linux/elevator.h
@@ -14,6 +14,9 @@ typedef void (elevator_merged_fn) (struct request_queue *, struct request *, int
 
 typedef int (elevator_allow_merge_fn) (struct request_queue *, struct request *, struct bio *);
 
+typedef void (elevator_bio_merged_fn) (struct request_queue *,
+						struct request *, struct bio *);
+
 typedef int (elevator_dispatch_fn) (struct request_queue *, int);
 
 typedef void (elevator_add_req_fn) (struct request_queue *, struct request *);
@@ -36,6 +39,7 @@ struct elevator_ops
 	elevator_merged_fn *elevator_merged_fn;
 	elevator_merge_req_fn *elevator_merge_req_fn;
 	elevator_allow_merge_fn *elevator_allow_merge_fn;
+	elevator_bio_merged_fn *elevator_bio_merged_fn;
 
 	elevator_dispatch_fn *elevator_dispatch_fn;
 	elevator_add_req_fn *elevator_add_req_fn;
@@ -103,6 +107,8 @@ extern int elv_merge(struct request_queue *, struct request **, struct bio *);
 extern void elv_merge_requests(struct request_queue *, struct request *,
 			       struct request *);
 extern void elv_merged_request(struct request_queue *, struct request *, int);
+extern void elv_bio_merged(struct request_queue *q, struct request *,
+				struct bio *);
 extern void elv_requeue_request(struct request_queue *, struct request *);
 extern int elv_queue_empty(struct request_queue *);
 extern struct request *elv_former_request(struct request_queue *, struct request *);
diff --git a/include/linux/fcntl.h b/include/linux/fcntl.h
index 86037400a6e3..afc00af3229b 100644
--- a/include/linux/fcntl.h
+++ b/include/linux/fcntl.h
@@ -22,6 +22,12 @@
 #define F_NOTIFY	(F_LINUX_SPECIFIC_BASE+2)
 
 /*
+ * Set and get of pipe page size array
+ */
+#define F_SETPIPE_SZ	(F_LINUX_SPECIFIC_BASE + 7)
+#define F_GETPIPE_SZ	(F_LINUX_SPECIFIC_BASE + 8)
+
+/*
  * Types of directory notifications that may be requested.
  */
 #define DN_ACCESS	0x00000001	/* File accessed */
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 4079ef99900f..1775d362732d 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -651,6 +651,7 @@ struct block_device {
 	int			bd_openers;
 	struct mutex		bd_mutex;	/* open/close mutex */
 	struct list_head	bd_inodes;
+	void *			bd_claiming;
 	void *			bd_holder;
 	int			bd_holders;
 #ifdef CONFIG_SYSFS
diff --git a/include/linux/ide.h b/include/linux/ide.h
index 3239d1c10acb..b6d448048ae2 100644
--- a/include/linux/ide.h
+++ b/include/linux/ide.h
@@ -362,7 +362,7 @@ struct ide_drive_s;
 struct ide_disk_ops {
 	int		(*check)(struct ide_drive_s *, const char *);
 	int		(*get_capacity)(struct ide_drive_s *);
-	u64		(*set_capacity)(struct ide_drive_s *, u64);
+	void		(*unlock_native_capacity)(struct ide_drive_s *);
 	void		(*setup)(struct ide_drive_s *);
 	void		(*flush)(struct ide_drive_s *);
 	int		(*init_media)(struct ide_drive_s *, struct gendisk *);
diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h
index b43a9e039059..16de3933c45e 100644
--- a/include/linux/pipe_fs_i.h
+++ b/include/linux/pipe_fs_i.h
@@ -3,7 +3,7 @@
 
 #define PIPEFS_MAGIC 0x50495045
 
-#define PIPE_BUFFERS (16)
+#define PIPE_DEF_BUFFERS	16
 
 #define PIPE_BUF_FLAG_LRU	0x01	/* page is on the LRU */
 #define PIPE_BUF_FLAG_ATOMIC	0x02	/* was atomically mapped */
@@ -44,17 +44,17 @@ struct pipe_buffer {
  **/
 struct pipe_inode_info {
 	wait_queue_head_t wait;
-	unsigned int nrbufs, curbuf;
-	struct page *tmp_page;
+	unsigned int nrbufs, curbuf, buffers;
 	unsigned int readers;
 	unsigned int writers;
 	unsigned int waiting_writers;
 	unsigned int r_counter;
 	unsigned int w_counter;
+	struct page *tmp_page;
 	struct fasync_struct *fasync_readers;
 	struct fasync_struct *fasync_writers;
 	struct inode *inode;
-	struct pipe_buffer bufs[PIPE_BUFFERS];
+	struct pipe_buffer *bufs;
 };
 
 /*
@@ -139,6 +139,8 @@ void pipe_lock(struct pipe_inode_info *);
 void pipe_unlock(struct pipe_inode_info *);
 void pipe_double_lock(struct pipe_inode_info *, struct pipe_inode_info *);
 
+extern unsigned int pipe_max_pages;
+
 /* Drop the inode semaphore and wait for a pipe event, atomically */
 void pipe_wait(struct pipe_inode_info *pipe);
 
@@ -154,4 +156,7 @@ int generic_pipe_buf_confirm(struct pipe_inode_info *, struct pipe_buffer *);
 int generic_pipe_buf_steal(struct pipe_inode_info *, struct pipe_buffer *);
 void generic_pipe_buf_release(struct pipe_inode_info *, struct pipe_buffer *);
 
+/* for F_SETPIPE_SZ and F_GETPIPE_SZ */
+long pipe_fcntl(struct file *, unsigned int, unsigned long arg);
+
 #endif
diff --git a/include/linux/splice.h b/include/linux/splice.h
index 18e7c7c0cae6..997c3b4c212b 100644
--- a/include/linux/splice.h
+++ b/include/linux/splice.h
@@ -82,4 +82,11 @@ extern ssize_t splice_to_pipe(struct pipe_inode_info *,
 extern ssize_t splice_direct_to_actor(struct file *, struct splice_desc *,
 				      splice_direct_actor *);
 
+/*
+ * for dynamic pipe sizing
+ */
+extern int splice_grow_spd(struct pipe_inode_info *, struct splice_pipe_desc *);
+extern void splice_shrink_spd(struct pipe_inode_info *,
+				struct splice_pipe_desc *);
+
 #endif
diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index 36520ded3e06..cc97d6caf2b3 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -65,6 +65,15 @@ struct writeback_control {
 	 * so we use a single control to update them
 	 */
 	unsigned no_nrwrite_index_update:1;
+
+	/*
+	 * For WB_SYNC_ALL, the sb must always be pinned. For WB_SYNC_NONE,
+	 * the writeback code will pin the sb for the caller. However,
+	 * for eg umount, the caller does WB_SYNC_NONE but already has
+	 * the sb pinned. If the below is set, caller already has the
+	 * sb pinned.
+	 */
+	unsigned sb_pinned:1;
 };
 
 /*
@@ -73,6 +82,7 @@ struct writeback_control {
 struct bdi_writeback;
 int inode_wait(void *);
 void writeback_inodes_sb(struct super_block *);
+void writeback_inodes_sb_locked(struct super_block *);
 int writeback_inodes_sb_if_idle(struct super_block *);
 void sync_inodes_sb(struct super_block *);
 void writeback_inodes_wbc(struct writeback_control *wbc);
@@ -96,8 +106,14 @@ static inline void inode_sync_wait(struct inode *inode)
 /*
  * mm/page-writeback.c
  */
-void laptop_io_completion(void);
+#ifdef CONFIG_BLOCK
+void laptop_io_completion(struct backing_dev_info *info);
 void laptop_sync_completion(void);
+void laptop_mode_sync(struct work_struct *work);
+void laptop_mode_timer_fn(unsigned long data);
+#else
+static inline void laptop_sync_completion(void) { }
+#endif
 void throttle_vm_writeout(gfp_t gfp_mask);
 
 /* These are exported to sysctl. */