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

* 'writeback' of git://git.kernel.dk/linux-2.6-block:
  writeback: check for registered bdi in flusher add and inode dirty
  writeback: add name to backing_dev_info
  writeback: add some debug inode list counters to bdi stats
  writeback: get rid of pdflush completely
  writeback: switch to per-bdi threads for flushing data
  writeback: move dirty inodes from super_block to backing_dev_info
  writeback: get rid of generic_sync_sb_inodes() export

3 files changed, 64 insertions, 23 deletions

diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index 1d52425a611..f169bcb90b5 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -13,6 +13,8 @@
 #include <linux/proportions.h>
 #include <linux/kernel.h>
 #include <linux/fs.h>
+#include <linux/sched.h>
+#include <linux/writeback.h>
 #include <asm/atomic.h>
 
 struct page;
@@ -23,9 +25,11 @@ struct dentry;
  * Bits in backing_dev_info.state
  */
 enum bdi_state {
-	BDI_pdflush,		/* A pdflush thread is working this device */
+	BDI_pending,		/* On its way to being activated */
+	BDI_wb_alloc,		/* Default embedded wb allocated */
 	BDI_async_congested,	/* The async (write) queue is getting full */
 	BDI_sync_congested,	/* The sync queue is getting full */
+	BDI_registered,		/* bdi_register() was done */
 	BDI_unused,		/* Available bits start here */
 };
 
@@ -39,7 +43,22 @@ enum bdi_stat_item {
 
 #define BDI_STAT_BATCH (8*(1+ilog2(nr_cpu_ids)))
 
+struct bdi_writeback {
+	struct list_head list;			/* hangs off the bdi */
+
+	struct backing_dev_info *bdi;		/* our parent bdi */
+	unsigned int nr;
+
+	unsigned long last_old_flush;		/* last old data flush */
+
+	struct task_struct	*task;		/* writeback task */
+	struct list_head	b_dirty;	/* dirty inodes */
+	struct list_head	b_io;		/* parked for writeback */
+	struct list_head	b_more_io;	/* parked for more writeback */
+};
+
 struct backing_dev_info {
+	struct list_head bdi_list;
 	unsigned long ra_pages;	/* max readahead in PAGE_CACHE_SIZE units */
 	unsigned long state;	/* Always use atomic bitops on this */
 	unsigned int capabilities; /* Device capabilities */
@@ -48,6 +67,8 @@ struct backing_dev_info {
 	void (*unplug_io_fn)(struct backing_dev_info *, struct page *);
 	void *unplug_io_data;
 
+	char *name;
+
 	struct percpu_counter bdi_stat[NR_BDI_STAT_ITEMS];
 
 	struct prop_local_percpu completions;
@@ -56,6 +77,14 @@ struct backing_dev_info {
 	unsigned int min_ratio;
 	unsigned int max_ratio, max_prop_frac;
 
+	struct bdi_writeback wb;  /* default writeback info for this bdi */
+	spinlock_t wb_lock;	  /* protects update side of wb_list */
+	struct list_head wb_list; /* the flusher threads hanging off this bdi */
+	unsigned long wb_mask;	  /* bitmask of registered tasks */
+	unsigned int wb_cnt;	  /* number of registered tasks */
+
+	struct list_head work_list;
+
 	struct device *dev;
 
 #ifdef CONFIG_DEBUG_FS
@@ -71,6 +100,19 @@ int bdi_register(struct backing_dev_info *bdi, struct device *parent,
 		const char *fmt, ...);
 int bdi_register_dev(struct backing_dev_info *bdi, dev_t dev);
 void bdi_unregister(struct backing_dev_info *bdi);
+void bdi_start_writeback(struct writeback_control *wbc);
+int bdi_writeback_task(struct bdi_writeback *wb);
+int bdi_has_dirty_io(struct backing_dev_info *bdi);
+
+extern spinlock_t bdi_lock;
+extern struct list_head bdi_list;
+
+static inline int wb_has_dirty_io(struct bdi_writeback *wb)
+{
+	return !list_empty(&wb->b_dirty) ||
+	       !list_empty(&wb->b_io) ||
+	       !list_empty(&wb->b_more_io);
+}
 
 static inline void __add_bdi_stat(struct backing_dev_info *bdi,
 		enum bdi_stat_item item, s64 amount)
@@ -261,6 +303,11 @@ static inline bool bdi_cap_swap_backed(struct backing_dev_info *bdi)
 	return bdi->capabilities & BDI_CAP_SWAP_BACKED;
 }
 
+static inline bool bdi_cap_flush_forker(struct backing_dev_info *bdi)
+{
+	return bdi == &default_backing_dev_info;
+}
+
 static inline bool mapping_cap_writeback_dirty(struct address_space *mapping)
 {
 	return bdi_cap_writeback_dirty(mapping->backing_dev_info);
@@ -276,4 +323,10 @@ static inline bool mapping_cap_swap_backed(struct address_space *mapping)
 	return bdi_cap_swap_backed(mapping->backing_dev_info);
 }
 
+static inline int bdi_sched_wait(void *word)
+{
+	schedule();
+	return 0;
+}
+
 #endif		/* _LINUX_BACKING_DEV_H */
diff --git a/include/linux/fs.h b/include/linux/fs.h
index c1f993515f5..26da98f6111 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -715,7 +715,7 @@ struct posix_acl;
 
 struct inode {
 	struct hlist_node	i_hash;
-	struct list_head	i_list;
+	struct list_head	i_list;		/* backing dev IO list */
 	struct list_head	i_sb_list;
 	struct list_head	i_dentry;
 	unsigned long		i_ino;
@@ -1336,9 +1336,6 @@ struct super_block {
 	struct xattr_handler	**s_xattr;
 
 	struct list_head	s_inodes;	/* all inodes */
-	struct list_head	s_dirty;	/* dirty inodes */
-	struct list_head	s_io;		/* parked for writeback */
-	struct list_head	s_more_io;	/* parked for more writeback */
 	struct hlist_head	s_anon;		/* anonymous dentries for (nfs) exporting */
 	struct list_head	s_files;
 	/* s_dentry_lru and s_nr_dentry_unused are protected by dcache_lock */
@@ -1789,6 +1786,7 @@ extern int get_sb_pseudo(struct file_system_type *, char *,
 	struct vfsmount *mnt);
 extern void simple_set_mnt(struct vfsmount *mnt, struct super_block *sb);
 int __put_super_and_need_restart(struct super_block *sb);
+void put_super(struct super_block *sb);
 
 /* Alas, no aliases. Too much hassle with bringing module.h everywhere */
 #define fops_get(fops) \
@@ -2071,8 +2069,6 @@ static inline void invalidate_remote_inode(struct inode *inode)
 extern int invalidate_inode_pages2(struct address_space *mapping);
 extern int invalidate_inode_pages2_range(struct address_space *mapping,
 					 pgoff_t start, pgoff_t end);
-extern void generic_sync_sb_inodes(struct super_block *sb,
-				struct writeback_control *wbc);
 extern int write_inode_now(struct inode *, int);
 extern int filemap_fdatawrite(struct address_space *);
 extern int filemap_flush(struct address_space *);
@@ -2187,7 +2183,6 @@ extern int bdev_read_only(struct block_device *);
 extern int set_blocksize(struct block_device *, int);
 extern int sb_set_blocksize(struct super_block *, int);
 extern int sb_min_blocksize(struct super_block *, int);
-extern int sb_has_dirty_inodes(struct super_block *);
 
 extern int generic_file_mmap(struct file *, struct vm_area_struct *);
 extern int generic_file_readonly_mmap(struct file *, struct vm_area_struct *);
diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index 3224820c851..78b1e4684cc 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -14,17 +14,6 @@ extern struct list_head inode_in_use;
 extern struct list_head inode_unused;
 
 /*
- * Yes, writeback.h requires sched.h
- * No, sched.h is not included from here.
- */
-static inline int task_is_pdflush(struct task_struct *task)
-{
-	return task->flags & PF_FLUSHER;
-}
-
-#define current_is_pdflush()	task_is_pdflush(current)
-
-/*
  * fs/fs-writeback.c
  */
 enum writeback_sync_modes {
@@ -40,6 +29,8 @@ enum writeback_sync_modes {
 struct writeback_control {
 	struct backing_dev_info *bdi;	/* If !NULL, only write back this
 					   queue */
+	struct super_block *sb;		/* if !NULL, only write inodes from
+					   this super_block */
 	enum writeback_sync_modes sync_mode;
 	unsigned long *older_than_this;	/* If !NULL, only write back inodes
 					   older than this */
@@ -76,9 +67,13 @@ struct writeback_control {
 /*
  * fs/fs-writeback.c
  */	
-void writeback_inodes(struct writeback_control *wbc);
+struct bdi_writeback;
 int inode_wait(void *);
-void sync_inodes_sb(struct super_block *, int wait);
+long writeback_inodes_sb(struct super_block *);
+long sync_inodes_sb(struct super_block *);
+void writeback_inodes_wbc(struct writeback_control *wbc);
+long wb_do_writeback(struct bdi_writeback *wb, int force_wait);
+void wakeup_flusher_threads(long nr_pages);
 
 /* writeback.h requires fs.h; it, too, is not included from here. */
 static inline void wait_on_inode(struct inode *inode)
@@ -98,7 +93,6 @@ static inline void inode_sync_wait(struct inode *inode)
 /*
  * mm/page-writeback.c
  */
-int wakeup_pdflush(long nr_pages);
 void laptop_io_completion(void);
 void laptop_sync_completion(void);
 void throttle_vm_writeout(gfp_t gfp_mask);
@@ -150,7 +144,6 @@ balance_dirty_pages_ratelimited(struct address_space *mapping)
 typedef int (*writepage_t)(struct page *page, struct writeback_control *wbc,
 				void *data);
 
-int pdflush_operation(void (*fn)(unsigned long), unsigned long arg0);
 int generic_writepages(struct address_space *mapping,
 		       struct writeback_control *wbc);
 int write_cache_pages(struct address_space *mapping,