From 1905b1bfc0de6f69a61dc03cac0d86a04b3216bd Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 6 Aug 2009 18:13:23 +0900 Subject: chrdev: implement __[un]register_chrdev() [un]register_chrdev() assume minor range 0-255. This patch adds __ prefixed versions which take @minorbase and @count explicitly. Signed-off-by: Tejun Heo Cc: Al Viro Cc: Greg Kroah-Hartman Signed-off-by: Takashi Iwai --- include/linux/fs.h | 19 ++++++++++++++++--- 1 file changed, 16 insertions(+), 3 deletions(-) (limited to 'include/linux/fs.h') diff --git a/include/linux/fs.h b/include/linux/fs.h index a36ffa5a77a..6c36ab78885 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1998,12 +1998,25 @@ extern void bd_release_from_disk(struct block_device *, struct gendisk *); #define CHRDEV_MAJOR_HASH_SIZE 255 extern int alloc_chrdev_region(dev_t *, unsigned, unsigned, const char *); extern int register_chrdev_region(dev_t, unsigned, const char *); -extern int register_chrdev(unsigned int, const char *, - const struct file_operations *); -extern void unregister_chrdev(unsigned int, const char *); +extern int __register_chrdev(unsigned int major, unsigned int baseminor, + unsigned int count, const char *name, + const struct file_operations *fops); +extern void __unregister_chrdev(unsigned int major, unsigned int baseminor, + unsigned int count, const char *name); extern void unregister_chrdev_region(dev_t, unsigned); extern void chrdev_show(struct seq_file *,off_t); +static inline int register_chrdev(unsigned int major, const char *name, + const struct file_operations *fops) +{ + return __register_chrdev(major, 0, 256, name, fops); +} + +static inline void unregister_chrdev(unsigned int major, const char *name) +{ + __unregister_chrdev(major, 0, 256, name); +} + /* fs/block_dev.c */ #define BDEVNAME_SIZE 32 /* Largest string for a blockdev identifier */ #define BDEVT_SIZE 10 /* Largest string for MAJ:MIN for blkdev */ -- cgit v1.2.3-70-g09d2 From 5909ccaa300a4a834ffa275327af4df0b9cb5295 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Fri, 28 Aug 2009 11:51:25 -0700 Subject: Make 'check_acl()' a first-class filesystem op This is stage one in flattening out the callchains for the common permission testing. Rather than have most filesystem implement their own inode->i_op->permission function that just calls back down to the VFS layers 'generic_permission()' with the per-filesystem ACL checking function, the filesystem can just expose its 'check_acl' function directly, and let the VFS layer do everything for it. This is all just preparatory - no filesystem actually enables this yet. Reviewed-by: James Morris Acked-by: Serge Hallyn Signed-off-by: Linus Torvalds --- fs/namei.c | 62 ++++++++++++++++++++++++++++++------------------------ include/linux/fs.h | 1 + 2 files changed, 36 insertions(+), 27 deletions(-) (limited to 'include/linux/fs.h') diff --git a/fs/namei.c b/fs/namei.c index e645e307036..ed27bb205b7 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -169,19 +169,10 @@ void putname(const char *name) EXPORT_SYMBOL(putname); #endif - -/** - * generic_permission - check for access rights on a Posix-like filesystem - * @inode: inode to check access rights for - * @mask: right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC) - * @check_acl: optional callback to check for Posix ACLs - * - * Used to check for read/write/execute permissions on a file. - * We use "fsuid" for this, letting us set arbitrary permissions - * for filesystem access without changing the "normal" uids which - * are used for other things.. +/* + * This does basic POSIX ACL permission checking */ -int generic_permission(struct inode *inode, int mask, +static int acl_permission_check(struct inode *inode, int mask, int (*check_acl)(struct inode *inode, int mask)) { umode_t mode = inode->i_mode; @@ -193,9 +184,7 @@ int generic_permission(struct inode *inode, int mask, else { if (IS_POSIXACL(inode) && (mode & S_IRWXG) && check_acl) { int error = check_acl(inode, mask); - if (error == -EACCES) - goto check_capabilities; - else if (error != -EAGAIN) + if (error != -EAGAIN) return error; } @@ -208,8 +197,32 @@ int generic_permission(struct inode *inode, int mask, */ if ((mask & ~mode) == 0) return 0; + return -EACCES; +} + +/** + * generic_permission - check for access rights on a Posix-like filesystem + * @inode: inode to check access rights for + * @mask: right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC) + * @check_acl: optional callback to check for Posix ACLs + * + * Used to check for read/write/execute permissions on a file. + * We use "fsuid" for this, letting us set arbitrary permissions + * for filesystem access without changing the "normal" uids which + * are used for other things.. + */ +int generic_permission(struct inode *inode, int mask, + int (*check_acl)(struct inode *inode, int mask)) +{ + int ret; + + /* + * Do the basic POSIX ACL permission checks. + */ + ret = acl_permission_check(inode, mask, check_acl); + if (ret != -EACCES) + return ret; - check_capabilities: /* * Read/write DACs are always overridable. * Executable DACs are overridable if at least one exec bit is set. @@ -262,7 +275,7 @@ int inode_permission(struct inode *inode, int mask) if (inode->i_op->permission) retval = inode->i_op->permission(inode, mask); else - retval = generic_permission(inode, mask, NULL); + retval = generic_permission(inode, mask, inode->i_op->check_acl); if (retval) return retval; @@ -432,27 +445,22 @@ static struct dentry * cached_lookup(struct dentry * parent, struct qstr * name, */ static int exec_permission_lite(struct inode *inode) { - umode_t mode = inode->i_mode; + int ret; if (inode->i_op->permission) { - int ret = inode->i_op->permission(inode, MAY_EXEC); + ret = inode->i_op->permission(inode, MAY_EXEC); if (!ret) goto ok; return ret; } - - if (current_fsuid() == inode->i_uid) - mode >>= 6; - else if (in_group_p(inode->i_gid)) - mode >>= 3; - - if (mode & MAY_EXEC) + ret = acl_permission_check(inode, MAY_EXEC, inode->i_op->check_acl); + if (!ret) goto ok; if (capable(CAP_DAC_OVERRIDE) || capable(CAP_DAC_READ_SEARCH)) goto ok; - return -EACCES; + return ret; ok: return security_inode_permission(inode, MAY_EXEC); } diff --git a/include/linux/fs.h b/include/linux/fs.h index 73e9b643e45..c1f993515f5 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1528,6 +1528,7 @@ struct inode_operations { void (*put_link) (struct dentry *, struct nameidata *, void *); void (*truncate) (struct inode *); int (*permission) (struct inode *, int); + int (*check_acl)(struct inode *, int); int (*setattr) (struct dentry *, struct iattr *); int (*getattr) (struct vfsmount *mnt, struct dentry *, struct kstat *); int (*setxattr) (struct dentry *, const char *,const void *,size_t,int); -- cgit v1.2.3-70-g09d2 From d8a8559cd7a9ccac98d5f6f13297a2ff68a43627 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 2 Sep 2009 12:34:32 +0200 Subject: writeback: get rid of generic_sync_sb_inodes() export This adds two new exported functions: - writeback_inodes_sb(), which only attempts to writeback dirty inodes on this super_block, for WB_SYNC_NONE writeout. - sync_inodes_sb(), which writes out all dirty inodes on this super_block and also waits for the IO to complete. Acked-by: Jan Kara Signed-off-by: Jens Axboe --- drivers/staging/pohmelfs/inode.c | 9 +----- fs/fs-writeback.c | 70 ++++++++++++++++++++++++---------------- fs/sync.c | 18 ++++++----- fs/ubifs/budget.c | 16 ++------- fs/ubifs/super.c | 8 +---- include/linux/fs.h | 2 -- include/linux/writeback.h | 3 +- 7 files changed, 58 insertions(+), 68 deletions(-) (limited to 'include/linux/fs.h') diff --git a/drivers/staging/pohmelfs/inode.c b/drivers/staging/pohmelfs/inode.c index 7b605795b77..e63c9bea6c5 100644 --- a/drivers/staging/pohmelfs/inode.c +++ b/drivers/staging/pohmelfs/inode.c @@ -1950,14 +1950,7 @@ static int pohmelfs_get_sb(struct file_system_type *fs_type, */ static void pohmelfs_kill_super(struct super_block *sb) { - struct writeback_control wbc = { - .sync_mode = WB_SYNC_ALL, - .range_start = 0, - .range_end = LLONG_MAX, - .nr_to_write = LONG_MAX, - }; - generic_sync_sb_inodes(sb, &wbc); - + sync_inodes_sb(sb); kill_anon_super(sb); } diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index c54226be529..271e5f44e87 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -458,8 +458,8 @@ writeback_single_inode(struct inode *inode, struct writeback_control *wbc) * on the writer throttling path, and we get decent balancing between many * throttled threads: we don't want them all piling up on inode_sync_wait. */ -void generic_sync_sb_inodes(struct super_block *sb, - struct writeback_control *wbc) +static void generic_sync_sb_inodes(struct super_block *sb, + struct writeback_control *wbc) { const unsigned long start = jiffies; /* livelock avoidance */ int sync = wbc->sync_mode == WB_SYNC_ALL; @@ -593,13 +593,6 @@ void generic_sync_sb_inodes(struct super_block *sb, return; /* Leave any unwritten inodes on s_io */ } -EXPORT_SYMBOL_GPL(generic_sync_sb_inodes); - -static void sync_sb_inodes(struct super_block *sb, - struct writeback_control *wbc) -{ - generic_sync_sb_inodes(sb, wbc); -} /* * Start writeback of dirty pagecache data against all unlocked inodes. @@ -640,7 +633,7 @@ restart: */ if (down_read_trylock(&sb->s_umount)) { if (sb->s_root) - sync_sb_inodes(sb, wbc); + generic_sync_sb_inodes(sb, wbc); up_read(&sb->s_umount); } spin_lock(&sb_lock); @@ -653,35 +646,56 @@ restart: spin_unlock(&sb_lock); } -/* - * writeback and wait upon the filesystem's dirty inodes. The caller will - * do this in two passes - one to write, and one to wait. - * - * A finite limit is set on the number of pages which will be written. - * To prevent infinite livelock of sys_sync(). +/** + * writeback_inodes_sb - writeback dirty inodes from given super_block + * @sb: the superblock * - * We add in the number of potentially dirty inodes, because each inode write - * can dirty pagecache in the underlying blockdev. + * Start writeback on some inodes on this super_block. No guarantees are made + * on how many (if any) will be written, and this function does not wait + * for IO completion of submitted IO. The number of pages submitted is + * returned. */ -void sync_inodes_sb(struct super_block *sb, int wait) +long writeback_inodes_sb(struct super_block *sb) { struct writeback_control wbc = { - .sync_mode = wait ? WB_SYNC_ALL : WB_SYNC_NONE, + .sync_mode = WB_SYNC_NONE, .range_start = 0, .range_end = LLONG_MAX, }; + unsigned long nr_dirty = global_page_state(NR_FILE_DIRTY); + unsigned long nr_unstable = global_page_state(NR_UNSTABLE_NFS); + long nr_to_write; - if (!wait) { - unsigned long nr_dirty = global_page_state(NR_FILE_DIRTY); - unsigned long nr_unstable = global_page_state(NR_UNSTABLE_NFS); - - wbc.nr_to_write = nr_dirty + nr_unstable + + nr_to_write = nr_dirty + nr_unstable + (inodes_stat.nr_inodes - inodes_stat.nr_unused); - } else - wbc.nr_to_write = LONG_MAX; /* doesn't actually matter */ - sync_sb_inodes(sb, &wbc); + wbc.nr_to_write = nr_to_write; + generic_sync_sb_inodes(sb, &wbc); + return nr_to_write - wbc.nr_to_write; +} +EXPORT_SYMBOL(writeback_inodes_sb); + +/** + * sync_inodes_sb - sync sb inode pages + * @sb: the superblock + * + * This function writes and waits on any dirty inode belonging to this + * super_block. The number of pages synced is returned. + */ +long sync_inodes_sb(struct super_block *sb) +{ + struct writeback_control wbc = { + .sync_mode = WB_SYNC_ALL, + .range_start = 0, + .range_end = LLONG_MAX, + }; + long nr_to_write = LONG_MAX; /* doesn't actually matter */ + + wbc.nr_to_write = nr_to_write; + generic_sync_sb_inodes(sb, &wbc); + return nr_to_write - wbc.nr_to_write; } +EXPORT_SYMBOL(sync_inodes_sb); /** * write_inode_now - write an inode to disk diff --git a/fs/sync.c b/fs/sync.c index 3422ba61d86..66f210476f4 100644 --- a/fs/sync.c +++ b/fs/sync.c @@ -19,20 +19,22 @@ SYNC_FILE_RANGE_WAIT_AFTER) /* - * Do the filesystem syncing work. For simple filesystems sync_inodes_sb(sb, 0) - * just dirties buffers with inodes so we have to submit IO for these buffers - * via __sync_blockdev(). This also speeds up the wait == 1 case since in that - * case write_inode() functions do sync_dirty_buffer() and thus effectively - * write one block at a time. + * Do the filesystem syncing work. For simple filesystems + * writeback_inodes_sb(sb) just dirties buffers with inodes so we have to + * submit IO for these buffers via __sync_blockdev(). This also speeds up the + * wait == 1 case since in that case write_inode() functions do + * sync_dirty_buffer() and thus effectively write one block at a time. */ static int __sync_filesystem(struct super_block *sb, int wait) { /* Avoid doing twice syncing and cache pruning for quota sync */ - if (!wait) + if (!wait) { writeout_quota_sb(sb, -1); - else + writeback_inodes_sb(sb); + } else { sync_quota_sb(sb, -1); - sync_inodes_sb(sb, wait); + sync_inodes_sb(sb); + } if (sb->s_op->sync_fs) sb->s_op->sync_fs(sb, wait); return __sync_blockdev(sb->s_bdev, wait); diff --git a/fs/ubifs/budget.c b/fs/ubifs/budget.c index eaf6d891d46..1c8991b0db1 100644 --- a/fs/ubifs/budget.c +++ b/fs/ubifs/budget.c @@ -65,26 +65,14 @@ static int shrink_liability(struct ubifs_info *c, int nr_to_write) { int nr_written; - struct writeback_control wbc = { - .sync_mode = WB_SYNC_NONE, - .range_end = LLONG_MAX, - .nr_to_write = nr_to_write, - }; - - generic_sync_sb_inodes(c->vfs_sb, &wbc); - nr_written = nr_to_write - wbc.nr_to_write; + nr_written = writeback_inodes_sb(c->vfs_sb); if (!nr_written) { /* * Re-try again but wait on pages/inodes which are being * written-back concurrently (e.g., by pdflush). */ - memset(&wbc, 0, sizeof(struct writeback_control)); - wbc.sync_mode = WB_SYNC_ALL; - wbc.range_end = LLONG_MAX; - wbc.nr_to_write = nr_to_write; - generic_sync_sb_inodes(c->vfs_sb, &wbc); - nr_written = nr_to_write - wbc.nr_to_write; + nr_written = sync_inodes_sb(c->vfs_sb); } dbg_budg("%d pages were written back", nr_written); diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c index 26d2e0d8046..8d6050a5966 100644 --- a/fs/ubifs/super.c +++ b/fs/ubifs/super.c @@ -438,12 +438,6 @@ static int ubifs_sync_fs(struct super_block *sb, int wait) { int i, err; struct ubifs_info *c = sb->s_fs_info; - struct writeback_control wbc = { - .sync_mode = WB_SYNC_ALL, - .range_start = 0, - .range_end = LLONG_MAX, - .nr_to_write = LONG_MAX, - }; /* * Zero @wait is just an advisory thing to help the file system shove @@ -462,7 +456,7 @@ static int ubifs_sync_fs(struct super_block *sb, int wait) * the user be able to get more accurate results of 'statfs()' after * they synchronize the file system. */ - generic_sync_sb_inodes(sb, &wbc); + sync_inodes_sb(sb); /* * Synchronize write buffers, because 'ubifs_run_commit()' does not diff --git a/include/linux/fs.h b/include/linux/fs.h index c1f993515f5..46ff7dd6e16 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2071,8 +2071,6 @@ 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 *); diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 3224820c851..07039299603 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -78,7 +78,8 @@ struct writeback_control { */ void writeback_inodes(struct writeback_control *wbc); 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 *); /* writeback.h requires fs.h; it, too, is not included from here. */ static inline void wait_on_inode(struct inode *inode) -- cgit v1.2.3-70-g09d2 From 66f3b8e2e103a0b93b945764d98e9ba46cb926dd Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 2 Sep 2009 09:19:46 +0200 Subject: writeback: move dirty inodes from super_block to backing_dev_info This is a first step at introducing per-bdi flusher threads. We should have no change in behaviour, although sb_has_dirty_inodes() is now ridiculously expensive, as there's no easy way to answer that question. Not a huge problem, since it'll be deleted in subsequent patches. Signed-off-by: Jens Axboe --- fs/fs-writeback.c | 197 ++++++++++++++++++++++++++++---------------- fs/super.c | 3 - include/linux/backing-dev.h | 9 ++ include/linux/fs.h | 5 +- mm/backing-dev.c | 24 ++++++ mm/page-writeback.c | 11 +-- 6 files changed, 165 insertions(+), 84 deletions(-) (limited to 'include/linux/fs.h') diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 271e5f44e87..45ad4bb700e 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -25,6 +25,7 @@ #include #include "internal.h" +#define inode_to_bdi(inode) ((inode)->i_mapping->backing_dev_info) /** * writeback_acquire - attempt to get exclusive writeback access to a device @@ -165,12 +166,13 @@ void __mark_inode_dirty(struct inode *inode, int flags) goto out; /* - * If the inode was already on s_dirty/s_io/s_more_io, don't - * reposition it (that would break s_dirty time-ordering). + * If the inode was already on b_dirty/b_io/b_more_io, don't + * reposition it (that would break b_dirty time-ordering). */ if (!was_dirty) { inode->dirtied_when = jiffies; - list_move(&inode->i_list, &sb->s_dirty); + list_move(&inode->i_list, + &inode_to_bdi(inode)->b_dirty); } } out: @@ -191,31 +193,30 @@ static int write_inode(struct inode *inode, int sync) * furthest end of its superblock's dirty-inode list. * * Before stamping the inode's ->dirtied_when, we check to see whether it is - * already the most-recently-dirtied inode on the s_dirty list. If that is + * already the most-recently-dirtied inode on the b_dirty list. If that is * the case then the inode must have been redirtied while it was being written * out and we don't reset its dirtied_when. */ static void redirty_tail(struct inode *inode) { - struct super_block *sb = inode->i_sb; + struct backing_dev_info *bdi = inode_to_bdi(inode); - if (!list_empty(&sb->s_dirty)) { - struct inode *tail_inode; + if (!list_empty(&bdi->b_dirty)) { + struct inode *tail; - tail_inode = list_entry(sb->s_dirty.next, struct inode, i_list); - if (time_before(inode->dirtied_when, - tail_inode->dirtied_when)) + tail = list_entry(bdi->b_dirty.next, struct inode, i_list); + if (time_before(inode->dirtied_when, tail->dirtied_when)) inode->dirtied_when = jiffies; } - list_move(&inode->i_list, &sb->s_dirty); + list_move(&inode->i_list, &bdi->b_dirty); } /* - * requeue inode for re-scanning after sb->s_io list is exhausted. + * requeue inode for re-scanning after bdi->b_io list is exhausted. */ static void requeue_io(struct inode *inode) { - list_move(&inode->i_list, &inode->i_sb->s_more_io); + list_move(&inode->i_list, &inode_to_bdi(inode)->b_more_io); } static void inode_sync_complete(struct inode *inode) @@ -262,18 +263,50 @@ static void move_expired_inodes(struct list_head *delaying_queue, /* * Queue all expired dirty inodes for io, eldest first. */ -static void queue_io(struct super_block *sb, - unsigned long *older_than_this) +static void queue_io(struct backing_dev_info *bdi, + unsigned long *older_than_this) +{ + list_splice_init(&bdi->b_more_io, bdi->b_io.prev); + move_expired_inodes(&bdi->b_dirty, &bdi->b_io, older_than_this); +} + +static int sb_on_inode_list(struct super_block *sb, struct list_head *list) { - list_splice_init(&sb->s_more_io, sb->s_io.prev); - move_expired_inodes(&sb->s_dirty, &sb->s_io, older_than_this); + struct inode *inode; + int ret = 0; + + spin_lock(&inode_lock); + list_for_each_entry(inode, list, i_list) { + if (inode->i_sb == sb) { + ret = 1; + break; + } + } + spin_unlock(&inode_lock); + return ret; } int sb_has_dirty_inodes(struct super_block *sb) { - return !list_empty(&sb->s_dirty) || - !list_empty(&sb->s_io) || - !list_empty(&sb->s_more_io); + struct backing_dev_info *bdi; + int ret = 0; + + /* + * This is REALLY expensive right now, but it'll go away + * when the bdi writeback is introduced + */ + mutex_lock(&bdi_lock); + list_for_each_entry(bdi, &bdi_list, bdi_list) { + if (sb_on_inode_list(sb, &bdi->b_dirty) || + sb_on_inode_list(sb, &bdi->b_io) || + sb_on_inode_list(sb, &bdi->b_more_io)) { + ret = 1; + break; + } + } + mutex_unlock(&bdi_lock); + + return ret; } EXPORT_SYMBOL(sb_has_dirty_inodes); @@ -322,11 +355,11 @@ writeback_single_inode(struct inode *inode, struct writeback_control *wbc) if (inode->i_state & I_SYNC) { /* * If this inode is locked for writeback and we are not doing - * writeback-for-data-integrity, move it to s_more_io so that + * writeback-for-data-integrity, move it to b_more_io so that * writeback can proceed with the other inodes on s_io. * * We'll have another go at writing back this inode when we - * completed a full scan of s_io. + * completed a full scan of b_io. */ if (!wait) { requeue_io(inode); @@ -371,11 +404,11 @@ writeback_single_inode(struct inode *inode, struct writeback_control *wbc) /* * We didn't write back all the pages. nfs_writepages() * sometimes bales out without doing anything. Redirty - * the inode; Move it from s_io onto s_more_io/s_dirty. + * the inode; Move it from b_io onto b_more_io/b_dirty. */ /* * akpm: if the caller was the kupdate function we put - * this inode at the head of s_dirty so it gets first + * this inode at the head of b_dirty so it gets first * consideration. Otherwise, move it to the tail, for * the reasons described there. I'm not really sure * how much sense this makes. Presumably I had a good @@ -385,7 +418,7 @@ writeback_single_inode(struct inode *inode, struct writeback_control *wbc) if (wbc->for_kupdate) { /* * For the kupdate function we move the inode - * to s_more_io so it will get more writeout as + * to b_more_io so it will get more writeout as * soon as the queue becomes uncongested. */ inode->i_state |= I_DIRTY_PAGES; @@ -433,51 +466,34 @@ writeback_single_inode(struct inode *inode, struct writeback_control *wbc) return ret; } -/* - * Write out a superblock's list of dirty inodes. A wait will be performed - * upon no inodes, all inodes or the final one, depending upon sync_mode. - * - * If older_than_this is non-NULL, then only write out inodes which - * had their first dirtying at a time earlier than *older_than_this. - * - * If we're a pdflush thread, then implement pdflush collision avoidance - * against the entire list. - * - * If `bdi' is non-zero then we're being asked to writeback a specific queue. - * This function assumes that the blockdev superblock's inodes are backed by - * a variety of queues, so all inodes are searched. For other superblocks, - * assume that all inodes are backed by the same queue. - * - * FIXME: this linear search could get expensive with many fileystems. But - * how to fix? We need to go from an address_space to all inodes which share - * a queue with that address_space. (Easy: have a global "dirty superblocks" - * list). - * - * The inodes to be written are parked on sb->s_io. They are moved back onto - * sb->s_dirty as they are selected for writing. This way, none can be missed - * on the writer throttling path, and we get decent balancing between many - * throttled threads: we don't want them all piling up on inode_sync_wait. - */ -static void generic_sync_sb_inodes(struct super_block *sb, - struct writeback_control *wbc) +static void generic_sync_bdi_inodes(struct backing_dev_info *bdi, + struct writeback_control *wbc, + struct super_block *sb) { + const int is_blkdev_sb = sb_is_blkdev_sb(sb); const unsigned long start = jiffies; /* livelock avoidance */ - int sync = wbc->sync_mode == WB_SYNC_ALL; spin_lock(&inode_lock); - if (!wbc->for_kupdate || list_empty(&sb->s_io)) - queue_io(sb, wbc->older_than_this); - while (!list_empty(&sb->s_io)) { - struct inode *inode = list_entry(sb->s_io.prev, + if (!wbc->for_kupdate || list_empty(&bdi->b_io)) + queue_io(bdi, wbc->older_than_this); + + while (!list_empty(&bdi->b_io)) { + struct inode *inode = list_entry(bdi->b_io.prev, struct inode, i_list); - struct address_space *mapping = inode->i_mapping; - struct backing_dev_info *bdi = mapping->backing_dev_info; long pages_skipped; + /* + * super block given and doesn't match, skip this inode + */ + if (sb && sb != inode->i_sb) { + redirty_tail(inode); + continue; + } + if (!bdi_cap_writeback_dirty(bdi)) { redirty_tail(inode); - if (sb_is_blkdev_sb(sb)) { + if (is_blkdev_sb) { /* * Dirty memory-backed blockdev: the ramdisk * driver does this. Skip just this inode @@ -499,14 +515,14 @@ static void generic_sync_sb_inodes(struct super_block *sb, if (wbc->nonblocking && bdi_write_congested(bdi)) { wbc->encountered_congestion = 1; - if (!sb_is_blkdev_sb(sb)) + if (!is_blkdev_sb) break; /* Skip a congested fs */ requeue_io(inode); continue; /* Skip a congested blockdev */ } if (wbc->bdi && bdi != wbc->bdi) { - if (!sb_is_blkdev_sb(sb)) + if (!is_blkdev_sb) break; /* fs has the wrong queue */ requeue_io(inode); continue; /* blockdev has wrong queue */ @@ -544,13 +560,57 @@ static void generic_sync_sb_inodes(struct super_block *sb, wbc->more_io = 1; break; } - if (!list_empty(&sb->s_more_io)) + if (!list_empty(&bdi->b_more_io)) wbc->more_io = 1; } - if (sync) { + spin_unlock(&inode_lock); + /* Leave any unwritten inodes on b_io */ +} + +/* + * Write out a superblock's list of dirty inodes. A wait will be performed + * upon no inodes, all inodes or the final one, depending upon sync_mode. + * + * If older_than_this is non-NULL, then only write out inodes which + * had their first dirtying at a time earlier than *older_than_this. + * + * If we're a pdlfush thread, then implement pdflush collision avoidance + * against the entire list. + * + * If `bdi' is non-zero then we're being asked to writeback a specific queue. + * This function assumes that the blockdev superblock's inodes are backed by + * a variety of queues, so all inodes are searched. For other superblocks, + * assume that all inodes are backed by the same queue. + * + * FIXME: this linear search could get expensive with many fileystems. But + * how to fix? We need to go from an address_space to all inodes which share + * a queue with that address_space. (Easy: have a global "dirty superblocks" + * list). + * + * The inodes to be written are parked on bdi->b_io. They are moved back onto + * bdi->b_dirty as they are selected for writing. This way, none can be missed + * on the writer throttling path, and we get decent balancing between many + * throttled threads: we don't want them all piling up on inode_sync_wait. + */ +static void generic_sync_sb_inodes(struct super_block *sb, + struct writeback_control *wbc) +{ + struct backing_dev_info *bdi; + + if (!wbc->bdi) { + mutex_lock(&bdi_lock); + list_for_each_entry(bdi, &bdi_list, bdi_list) + generic_sync_bdi_inodes(bdi, wbc, sb); + mutex_unlock(&bdi_lock); + } else + generic_sync_bdi_inodes(wbc->bdi, wbc, sb); + + if (wbc->sync_mode == WB_SYNC_ALL) { struct inode *inode, *old_inode = NULL; + spin_lock(&inode_lock); + /* * Data integrity sync. Must wait for all pages under writeback, * because there may have been pages dirtied before our sync @@ -588,10 +648,7 @@ static void generic_sync_sb_inodes(struct super_block *sb, } spin_unlock(&inode_lock); iput(old_inode); - } else - spin_unlock(&inode_lock); - - return; /* Leave any unwritten inodes on s_io */ + } } /* @@ -599,8 +656,8 @@ static void generic_sync_sb_inodes(struct super_block *sb, * * Note: * We don't need to grab a reference to superblock here. If it has non-empty - * ->s_dirty it's hadn't been killed yet and kill_super() won't proceed - * past sync_inodes_sb() until the ->s_dirty/s_io/s_more_io lists are all + * ->b_dirty it's hadn't been killed yet and kill_super() won't proceed + * past sync_inodes_sb() until the ->b_dirty/b_io/b_more_io lists are all * empty. Since __sync_single_inode() regains inode_lock before it finally moves * inode from superblock lists we are OK. * diff --git a/fs/super.c b/fs/super.c index 2761d3e22ed..0d22ce3be4a 100644 --- a/fs/super.c +++ b/fs/super.c @@ -62,9 +62,6 @@ static struct super_block *alloc_super(struct file_system_type *type) s = NULL; goto out; } - INIT_LIST_HEAD(&s->s_dirty); - INIT_LIST_HEAD(&s->s_io); - INIT_LIST_HEAD(&s->s_more_io); INIT_LIST_HEAD(&s->s_files); INIT_LIST_HEAD(&s->s_instances); INIT_HLIST_HEAD(&s->s_anon); diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 1d52425a611..928cd5484f4 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -40,6 +40,8 @@ enum bdi_stat_item { #define BDI_STAT_BATCH (8*(1+ilog2(nr_cpu_ids))) 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 */ @@ -58,6 +60,10 @@ struct backing_dev_info { struct device *dev; + 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 */ + #ifdef CONFIG_DEBUG_FS struct dentry *debug_dir; struct dentry *debug_stats; @@ -72,6 +78,9 @@ int bdi_register(struct backing_dev_info *bdi, struct device *parent, int bdi_register_dev(struct backing_dev_info *bdi, dev_t dev); void bdi_unregister(struct backing_dev_info *bdi); +extern struct mutex bdi_lock; +extern struct list_head bdi_list; + static inline void __add_bdi_stat(struct backing_dev_info *bdi, enum bdi_stat_item item, s64 amount) { diff --git a/include/linux/fs.h b/include/linux/fs.h index 46ff7dd6e16..56371be1be6 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 */ diff --git a/mm/backing-dev.c b/mm/backing-dev.c index c86edd24429..6f163e0f050 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -22,6 +22,8 @@ struct backing_dev_info default_backing_dev_info = { EXPORT_SYMBOL_GPL(default_backing_dev_info); static struct class *bdi_class; +DEFINE_MUTEX(bdi_lock); +LIST_HEAD(bdi_list); #ifdef CONFIG_DEBUG_FS #include @@ -211,6 +213,10 @@ int bdi_register(struct backing_dev_info *bdi, struct device *parent, goto exit; } + mutex_lock(&bdi_lock); + list_add_tail(&bdi->bdi_list, &bdi_list); + mutex_unlock(&bdi_lock); + bdi->dev = dev; bdi_debug_register(bdi, dev_name(dev)); @@ -225,9 +231,17 @@ int bdi_register_dev(struct backing_dev_info *bdi, dev_t dev) } EXPORT_SYMBOL(bdi_register_dev); +static void bdi_remove_from_list(struct backing_dev_info *bdi) +{ + mutex_lock(&bdi_lock); + list_del(&bdi->bdi_list); + mutex_unlock(&bdi_lock); +} + void bdi_unregister(struct backing_dev_info *bdi) { if (bdi->dev) { + bdi_remove_from_list(bdi); bdi_debug_unregister(bdi); device_unregister(bdi->dev); bdi->dev = NULL; @@ -245,6 +259,10 @@ int bdi_init(struct backing_dev_info *bdi) bdi->min_ratio = 0; bdi->max_ratio = 100; bdi->max_prop_frac = PROP_FRAC_BASE; + INIT_LIST_HEAD(&bdi->bdi_list); + INIT_LIST_HEAD(&bdi->b_io); + INIT_LIST_HEAD(&bdi->b_dirty); + INIT_LIST_HEAD(&bdi->b_more_io); for (i = 0; i < NR_BDI_STAT_ITEMS; i++) { err = percpu_counter_init(&bdi->bdi_stat[i], 0); @@ -259,6 +277,8 @@ int bdi_init(struct backing_dev_info *bdi) err: while (i--) percpu_counter_destroy(&bdi->bdi_stat[i]); + + bdi_remove_from_list(bdi); } return err; @@ -269,6 +289,10 @@ void bdi_destroy(struct backing_dev_info *bdi) { int i; + WARN_ON(!list_empty(&bdi->b_dirty)); + WARN_ON(!list_empty(&bdi->b_io)); + WARN_ON(!list_empty(&bdi->b_more_io)); + bdi_unregister(bdi); for (i = 0; i < NR_BDI_STAT_ITEMS; i++) diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 81627ebcd31..f8341b6019b 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -320,15 +320,13 @@ static void task_dirty_limit(struct task_struct *tsk, unsigned long *pdirty) /* * */ -static DEFINE_SPINLOCK(bdi_lock); static unsigned int bdi_min_ratio; int bdi_set_min_ratio(struct backing_dev_info *bdi, unsigned int min_ratio) { int ret = 0; - unsigned long flags; - spin_lock_irqsave(&bdi_lock, flags); + mutex_lock(&bdi_lock); if (min_ratio > bdi->max_ratio) { ret = -EINVAL; } else { @@ -340,27 +338,26 @@ int bdi_set_min_ratio(struct backing_dev_info *bdi, unsigned int min_ratio) ret = -EINVAL; } } - spin_unlock_irqrestore(&bdi_lock, flags); + mutex_unlock(&bdi_lock); return ret; } int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned max_ratio) { - unsigned long flags; int ret = 0; if (max_ratio > 100) return -EINVAL; - spin_lock_irqsave(&bdi_lock, flags); + mutex_lock(&bdi_lock); if (bdi->min_ratio > max_ratio) { ret = -EINVAL; } else { bdi->max_ratio = max_ratio; bdi->max_prop_frac = (PROP_FRAC_BASE * max_ratio) / 100; } - spin_unlock_irqrestore(&bdi_lock, flags); + mutex_unlock(&bdi_lock); return ret; } -- cgit v1.2.3-70-g09d2 From 03ba3782e8dcc5b0e1efe440d33084f066e38cae Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 9 Sep 2009 09:08:54 +0200 Subject: writeback: switch to per-bdi threads for flushing data This gets rid of pdflush for bdi writeout and kupdated style cleaning. pdflush writeout suffers from lack of locality and also requires more threads to handle the same workload, since it has to work in a non-blocking fashion against each queue. This also introduces lumpy behaviour and potential request starvation, since pdflush can be starved for queue access if others are accessing it. A sample ffsb workload that does random writes to files is about 8% faster here on a simple SATA drive during the benchmark phase. File layout also seems a LOT more smooth in vmstat: r b swpd free buff cache si so bi bo in cs us sy id wa 0 1 0 608848 2652 375372 0 0 0 71024 604 24 1 10 48 42 0 1 0 549644 2712 433736 0 0 0 60692 505 27 1 8 48 44 1 0 0 476928 2784 505192 0 0 4 29540 553 24 0 9 53 37 0 1 0 457972 2808 524008 0 0 0 54876 331 16 0 4 38 58 0 1 0 366128 2928 614284 0 0 4 92168 710 58 0 13 53 34 0 1 0 295092 3000 684140 0 0 0 62924 572 23 0 9 53 37 0 1 0 236592 3064 741704 0 0 4 58256 523 17 0 8 48 44 0 1 0 165608 3132 811464 0 0 0 57460 560 21 0 8 54 38 0 1 0 102952 3200 873164 0 0 4 74748 540 29 1 10 48 41 0 1 0 48604 3252 926472 0 0 0 53248 469 29 0 7 47 45 where vanilla tends to fluctuate a lot in the creation phase: r b swpd free buff cache si so bi bo in cs us sy id wa 1 1 0 678716 5792 303380 0 0 0 74064 565 50 1 11 52 36 1 0 0 662488 5864 319396 0 0 4 352 302 329 0 2 47 51 0 1 0 599312 5924 381468 0 0 0 78164 516 55 0 9 51 40 0 1 0 519952 6008 459516 0 0 4 78156 622 56 1 11 52 37 1 1 0 436640 6092 541632 0 0 0 82244 622 54 0 11 48 41 0 1 0 436640 6092 541660 0 0 0 8 152 39 0 0 51 49 0 1 0 332224 6200 644252 0 0 4 102800 728 46 1 13 49 36 1 0 0 274492 6260 701056 0 0 4 12328 459 49 0 7 50 43 0 1 0 211220 6324 763356 0 0 0 106940 515 37 1 10 51 39 1 0 0 160412 6376 813468 0 0 0 8224 415 43 0 6 49 45 1 1 0 85980 6452 886556 0 0 4 113516 575 39 1 11 54 34 0 2 0 85968 6452 886620 0 0 0 1640 158 211 0 0 46 54 A 10 disk test with btrfs performs 26% faster with per-bdi flushing. A SSD based writeback test on XFS performs over 20% better as well, with the throughput being very stable around 1GB/sec, where pdflush only manages 750MB/sec and fluctuates wildly while doing so. Random buffered writes to many files behave a lot better as well, as does random mmap'ed writes. A separate thread is added to sync the super blocks. In the long term, adding sync_supers_bdi() functionality could get rid of this thread again. Signed-off-by: Jens Axboe --- fs/buffer.c | 2 +- fs/fs-writeback.c | 999 +++++++++++++++++++++++++++++++------------- fs/super.c | 2 +- fs/sync.c | 2 +- include/linux/backing-dev.h | 55 ++- include/linux/fs.h | 2 +- include/linux/writeback.h | 8 +- mm/backing-dev.c | 341 ++++++++++++++- mm/page-writeback.c | 179 ++------ mm/vmscan.c | 2 +- 10 files changed, 1120 insertions(+), 472 deletions(-) (limited to 'include/linux/fs.h') diff --git a/fs/buffer.c b/fs/buffer.c index 28f320fac4d..90a98865b0c 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -281,7 +281,7 @@ static void free_more_memory(void) struct zone *zone; int nid; - wakeup_pdflush(1024); + wakeup_flusher_threads(1024); yield(); for_each_online_node(nid) { diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 45ad4bb700e..7f6dae8aa47 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -19,6 +19,8 @@ #include #include #include +#include +#include #include #include #include @@ -27,165 +29,208 @@ #define inode_to_bdi(inode) ((inode)->i_mapping->backing_dev_info) -/** - * writeback_acquire - attempt to get exclusive writeback access to a device - * @bdi: the device's backing_dev_info structure - * - * It is a waste of resources to have more than one pdflush thread blocked on - * a single request queue. Exclusion at the request_queue level is obtained - * via a flag in the request_queue's backing_dev_info.state. - * - * Non-request_queue-backed address_spaces will share default_backing_dev_info, - * unless they implement their own. Which is somewhat inefficient, as this - * may prevent concurrent writeback against multiple devices. +/* + * Work items for the bdi_writeback threads */ -static int writeback_acquire(struct backing_dev_info *bdi) +struct bdi_work { + struct list_head list; + struct list_head wait_list; + struct rcu_head rcu_head; + + unsigned long seen; + atomic_t pending; + + struct super_block *sb; + unsigned long nr_pages; + enum writeback_sync_modes sync_mode; + + unsigned long state; +}; + +enum { + WS_USED_B = 0, + WS_ONSTACK_B, +}; + +#define WS_USED (1 << WS_USED_B) +#define WS_ONSTACK (1 << WS_ONSTACK_B) + +static inline bool bdi_work_on_stack(struct bdi_work *work) +{ + return test_bit(WS_ONSTACK_B, &work->state); +} + +static inline void bdi_work_init(struct bdi_work *work, + struct writeback_control *wbc) +{ + INIT_RCU_HEAD(&work->rcu_head); + work->sb = wbc->sb; + work->nr_pages = wbc->nr_to_write; + work->sync_mode = wbc->sync_mode; + work->state = WS_USED; +} + +static inline void bdi_work_init_on_stack(struct bdi_work *work, + struct writeback_control *wbc) { - return !test_and_set_bit(BDI_pdflush, &bdi->state); + bdi_work_init(work, wbc); + work->state |= WS_ONSTACK; } /** * writeback_in_progress - determine whether there is writeback in progress * @bdi: the device's backing_dev_info structure. * - * Determine whether there is writeback in progress against a backing device. + * Determine whether there is writeback waiting to be handled against a + * backing device. */ int writeback_in_progress(struct backing_dev_info *bdi) { - return test_bit(BDI_pdflush, &bdi->state); + return !list_empty(&bdi->work_list); } -/** - * writeback_release - relinquish exclusive writeback access against a device. - * @bdi: the device's backing_dev_info structure - */ -static void writeback_release(struct backing_dev_info *bdi) +static void bdi_work_clear(struct bdi_work *work) { - BUG_ON(!writeback_in_progress(bdi)); - clear_bit(BDI_pdflush, &bdi->state); + clear_bit(WS_USED_B, &work->state); + smp_mb__after_clear_bit(); + wake_up_bit(&work->state, WS_USED_B); } -static noinline void block_dump___mark_inode_dirty(struct inode *inode) +static void bdi_work_free(struct rcu_head *head) { - if (inode->i_ino || strcmp(inode->i_sb->s_id, "bdev")) { - struct dentry *dentry; - const char *name = "?"; + struct bdi_work *work = container_of(head, struct bdi_work, rcu_head); - dentry = d_find_alias(inode); - if (dentry) { - spin_lock(&dentry->d_lock); - name = (const char *) dentry->d_name.name; - } - printk(KERN_DEBUG - "%s(%d): dirtied inode %lu (%s) on %s\n", - current->comm, task_pid_nr(current), inode->i_ino, - name, inode->i_sb->s_id); - if (dentry) { - spin_unlock(&dentry->d_lock); - dput(dentry); - } - } + if (!bdi_work_on_stack(work)) + kfree(work); + else + bdi_work_clear(work); } -/** - * __mark_inode_dirty - internal function - * @inode: inode to mark - * @flags: what kind of dirty (i.e. I_DIRTY_SYNC) - * Mark an inode as dirty. Callers should use mark_inode_dirty or - * mark_inode_dirty_sync. - * - * Put the inode on the super block's dirty list. - * - * CAREFUL! We mark it dirty unconditionally, but move it onto the - * dirty list only if it is hashed or if it refers to a blockdev. - * If it was not hashed, it will never be added to the dirty list - * even if it is later hashed, as it will have been marked dirty already. - * - * In short, make sure you hash any inodes _before_ you start marking - * them dirty. - * - * This function *must* be atomic for the I_DIRTY_PAGES case - - * set_page_dirty() is called under spinlock in several places. - * - * Note that for blockdevs, inode->dirtied_when represents the dirtying time of - * the block-special inode (/dev/hda1) itself. And the ->dirtied_when field of - * the kernel-internal blockdev inode represents the dirtying time of the - * blockdev's pages. This is why for I_DIRTY_PAGES we always use - * page->mapping->host, so the page-dirtying time is recorded in the internal - * blockdev inode. - */ -void __mark_inode_dirty(struct inode *inode, int flags) +static void wb_work_complete(struct bdi_work *work) { - struct super_block *sb = inode->i_sb; + const enum writeback_sync_modes sync_mode = work->sync_mode; /* - * Don't do this for I_DIRTY_PAGES - that doesn't actually - * dirty the inode itself + * For allocated work, we can clear the done/seen bit right here. + * For on-stack work, we need to postpone both the clear and free + * to after the RCU grace period, since the stack could be invalidated + * as soon as bdi_work_clear() has done the wakeup. */ - if (flags & (I_DIRTY_SYNC | I_DIRTY_DATASYNC)) { - if (sb->s_op->dirty_inode) - sb->s_op->dirty_inode(inode); - } + if (!bdi_work_on_stack(work)) + bdi_work_clear(work); + if (sync_mode == WB_SYNC_NONE || bdi_work_on_stack(work)) + call_rcu(&work->rcu_head, bdi_work_free); +} +static void wb_clear_pending(struct bdi_writeback *wb, struct bdi_work *work) +{ /* - * make sure that changes are seen by all cpus before we test i_state - * -- mikulas + * The caller has retrieved the work arguments from this work, + * drop our reference. If this is the last ref, delete and free it */ - smp_mb(); + if (atomic_dec_and_test(&work->pending)) { + struct backing_dev_info *bdi = wb->bdi; - /* avoid the locking if we can */ - if ((inode->i_state & flags) == flags) - return; - - if (unlikely(block_dump)) - block_dump___mark_inode_dirty(inode); + spin_lock(&bdi->wb_lock); + list_del_rcu(&work->list); + spin_unlock(&bdi->wb_lock); - spin_lock(&inode_lock); - if ((inode->i_state & flags) != flags) { - const int was_dirty = inode->i_state & I_DIRTY; + wb_work_complete(work); + } +} - inode->i_state |= flags; +static void bdi_queue_work(struct backing_dev_info *bdi, struct bdi_work *work) +{ + if (work) { + work->seen = bdi->wb_mask; + BUG_ON(!work->seen); + atomic_set(&work->pending, bdi->wb_cnt); + BUG_ON(!bdi->wb_cnt); /* - * If the inode is being synced, just update its dirty state. - * The unlocker will place the inode on the appropriate - * superblock list, based upon its state. + * Make sure stores are seen before it appears on the list */ - if (inode->i_state & I_SYNC) - goto out; + smp_mb(); - /* - * Only add valid (hashed) inodes to the superblock's - * dirty list. Add blockdev inodes as well. - */ - if (!S_ISBLK(inode->i_mode)) { - if (hlist_unhashed(&inode->i_hash)) - goto out; - } - if (inode->i_state & (I_FREEING|I_CLEAR)) - goto out; + spin_lock(&bdi->wb_lock); + list_add_tail_rcu(&work->list, &bdi->work_list); + spin_unlock(&bdi->wb_lock); + } + + /* + * If the default thread isn't there, make sure we add it. When + * it gets created and wakes up, we'll run this work. + */ + if (unlikely(list_empty_careful(&bdi->wb_list))) + wake_up_process(default_backing_dev_info.wb.task); + else { + struct bdi_writeback *wb = &bdi->wb; /* - * If the inode was already on b_dirty/b_io/b_more_io, don't - * reposition it (that would break b_dirty time-ordering). + * If we failed allocating the bdi work item, wake up the wb + * thread always. As a safety precaution, it'll flush out + * everything */ - if (!was_dirty) { - inode->dirtied_when = jiffies; - list_move(&inode->i_list, - &inode_to_bdi(inode)->b_dirty); - } + if (!wb_has_dirty_io(wb)) { + if (work) + wb_clear_pending(wb, work); + } else if (wb->task) + wake_up_process(wb->task); } -out: - spin_unlock(&inode_lock); } -EXPORT_SYMBOL(__mark_inode_dirty); +/* + * Used for on-stack allocated work items. The caller needs to wait until + * the wb threads have acked the work before it's safe to continue. + */ +static void bdi_wait_on_work_clear(struct bdi_work *work) +{ + wait_on_bit(&work->state, WS_USED_B, bdi_sched_wait, + TASK_UNINTERRUPTIBLE); +} -static int write_inode(struct inode *inode, int sync) +static struct bdi_work *bdi_alloc_work(struct writeback_control *wbc) { - if (inode->i_sb->s_op->write_inode && !is_bad_inode(inode)) - return inode->i_sb->s_op->write_inode(inode, sync); - return 0; + struct bdi_work *work; + + work = kmalloc(sizeof(*work), GFP_ATOMIC); + if (work) + bdi_work_init(work, wbc); + + return work; +} + +void bdi_start_writeback(struct writeback_control *wbc) +{ + const bool must_wait = wbc->sync_mode == WB_SYNC_ALL; + struct bdi_work work_stack, *work = NULL; + + if (!must_wait) + work = bdi_alloc_work(wbc); + + if (!work) { + work = &work_stack; + bdi_work_init_on_stack(work, wbc); + } + + bdi_queue_work(wbc->bdi, work); + + /* + * If the sync mode is WB_SYNC_ALL, block waiting for the work to + * complete. If not, we only need to wait for the work to be started, + * if we allocated it on-stack. We use the same mechanism, if the + * wait bit is set in the bdi_work struct, then threads will not + * clear pending until after they are done. + * + * Note that work == &work_stack if must_wait is true, so we don't + * need to do call_rcu() here ever, since the completion path will + * have done that for us. + */ + if (must_wait || work == &work_stack) { + bdi_wait_on_work_clear(work); + if (work != &work_stack) + call_rcu(&work->rcu_head, bdi_work_free); + } } /* @@ -199,16 +244,16 @@ static int write_inode(struct inode *inode, int sync) */ static void redirty_tail(struct inode *inode) { - struct backing_dev_info *bdi = inode_to_bdi(inode); + struct bdi_writeback *wb = &inode_to_bdi(inode)->wb; - if (!list_empty(&bdi->b_dirty)) { + if (!list_empty(&wb->b_dirty)) { struct inode *tail; - tail = list_entry(bdi->b_dirty.next, struct inode, i_list); + tail = list_entry(wb->b_dirty.next, struct inode, i_list); if (time_before(inode->dirtied_when, tail->dirtied_when)) inode->dirtied_when = jiffies; } - list_move(&inode->i_list, &bdi->b_dirty); + list_move(&inode->i_list, &wb->b_dirty); } /* @@ -216,7 +261,9 @@ static void redirty_tail(struct inode *inode) */ static void requeue_io(struct inode *inode) { - list_move(&inode->i_list, &inode_to_bdi(inode)->b_more_io); + struct bdi_writeback *wb = &inode_to_bdi(inode)->wb; + + list_move(&inode->i_list, &wb->b_more_io); } static void inode_sync_complete(struct inode *inode) @@ -263,52 +310,18 @@ static void move_expired_inodes(struct list_head *delaying_queue, /* * Queue all expired dirty inodes for io, eldest first. */ -static void queue_io(struct backing_dev_info *bdi, - unsigned long *older_than_this) +static void queue_io(struct bdi_writeback *wb, unsigned long *older_than_this) { - list_splice_init(&bdi->b_more_io, bdi->b_io.prev); - move_expired_inodes(&bdi->b_dirty, &bdi->b_io, older_than_this); + list_splice_init(&wb->b_more_io, wb->b_io.prev); + move_expired_inodes(&wb->b_dirty, &wb->b_io, older_than_this); } -static int sb_on_inode_list(struct super_block *sb, struct list_head *list) -{ - struct inode *inode; - int ret = 0; - - spin_lock(&inode_lock); - list_for_each_entry(inode, list, i_list) { - if (inode->i_sb == sb) { - ret = 1; - break; - } - } - spin_unlock(&inode_lock); - return ret; -} - -int sb_has_dirty_inodes(struct super_block *sb) +static int write_inode(struct inode *inode, int sync) { - struct backing_dev_info *bdi; - int ret = 0; - - /* - * This is REALLY expensive right now, but it'll go away - * when the bdi writeback is introduced - */ - mutex_lock(&bdi_lock); - list_for_each_entry(bdi, &bdi_list, bdi_list) { - if (sb_on_inode_list(sb, &bdi->b_dirty) || - sb_on_inode_list(sb, &bdi->b_io) || - sb_on_inode_list(sb, &bdi->b_more_io)) { - ret = 1; - break; - } - } - mutex_unlock(&bdi_lock); - - return ret; + if (inode->i_sb->s_op->write_inode && !is_bad_inode(inode)) + return inode->i_sb->s_op->write_inode(inode, sync); + return 0; } -EXPORT_SYMBOL(sb_has_dirty_inodes); /* * Wait for writeback on an inode to complete. @@ -466,20 +479,71 @@ writeback_single_inode(struct inode *inode, struct writeback_control *wbc) return ret; } -static void generic_sync_bdi_inodes(struct backing_dev_info *bdi, - struct writeback_control *wbc, - struct super_block *sb) +/* + * For WB_SYNC_NONE writeback, the caller does not have the sb pinned + * before calling writeback. So make sure that we do pin it, so it doesn't + * go away while we are writing inodes from it. + * + * Returns 0 if the super was successfully pinned (or pinning wasn't needed), + * 1 if we failed. + */ +static int pin_sb_for_writeback(struct writeback_control *wbc, + struct inode *inode) +{ + struct super_block *sb = inode->i_sb; + + /* + * Caller must already hold the ref for this + */ + if (wbc->sync_mode == WB_SYNC_ALL) { + WARN_ON(!rwsem_is_locked(&sb->s_umount)); + return 0; + } + + spin_lock(&sb_lock); + sb->s_count++; + if (down_read_trylock(&sb->s_umount)) { + if (sb->s_root) { + spin_unlock(&sb_lock); + return 0; + } + /* + * umounted, drop rwsem again and fall through to failure + */ + up_read(&sb->s_umount); + } + + sb->s_count--; + spin_unlock(&sb_lock); + return 1; +} + +static void unpin_sb_for_writeback(struct writeback_control *wbc, + struct inode *inode) +{ + struct super_block *sb = inode->i_sb; + + if (wbc->sync_mode == WB_SYNC_ALL) + return; + + up_read(&sb->s_umount); + put_super(sb); +} + +static void writeback_inodes_wb(struct bdi_writeback *wb, + struct writeback_control *wbc) { + struct super_block *sb = wbc->sb; const int is_blkdev_sb = sb_is_blkdev_sb(sb); const unsigned long start = jiffies; /* livelock avoidance */ spin_lock(&inode_lock); - if (!wbc->for_kupdate || list_empty(&bdi->b_io)) - queue_io(bdi, wbc->older_than_this); + if (!wbc->for_kupdate || list_empty(&wb->b_io)) + queue_io(wb, wbc->older_than_this); - while (!list_empty(&bdi->b_io)) { - struct inode *inode = list_entry(bdi->b_io.prev, + while (!list_empty(&wb->b_io)) { + struct inode *inode = list_entry(wb->b_io.prev, struct inode, i_list); long pages_skipped; @@ -491,7 +555,7 @@ static void generic_sync_bdi_inodes(struct backing_dev_info *bdi, continue; } - if (!bdi_cap_writeback_dirty(bdi)) { + if (!bdi_cap_writeback_dirty(wb->bdi)) { redirty_tail(inode); if (is_blkdev_sb) { /* @@ -513,7 +577,7 @@ static void generic_sync_bdi_inodes(struct backing_dev_info *bdi, continue; } - if (wbc->nonblocking && bdi_write_congested(bdi)) { + if (wbc->nonblocking && bdi_write_congested(wb->bdi)) { wbc->encountered_congestion = 1; if (!is_blkdev_sb) break; /* Skip a congested fs */ @@ -521,13 +585,6 @@ static void generic_sync_bdi_inodes(struct backing_dev_info *bdi, continue; /* Skip a congested blockdev */ } - if (wbc->bdi && bdi != wbc->bdi) { - if (!is_blkdev_sb) - break; /* fs has the wrong queue */ - requeue_io(inode); - continue; /* blockdev has wrong queue */ - } - /* * Was this inode dirtied after sync_sb_inodes was called? * This keeps sync from extra jobs and livelock. @@ -535,16 +592,16 @@ static void generic_sync_bdi_inodes(struct backing_dev_info *bdi, if (inode_dirtied_after(inode, start)) break; - /* Is another pdflush already flushing this queue? */ - if (current_is_pdflush() && !writeback_acquire(bdi)) - break; + if (pin_sb_for_writeback(wbc, inode)) { + requeue_io(inode); + continue; + } BUG_ON(inode->i_state & (I_FREEING | I_CLEAR)); __iget(inode); pages_skipped = wbc->pages_skipped; writeback_single_inode(inode, wbc); - if (current_is_pdflush()) - writeback_release(bdi); + unpin_sb_for_writeback(wbc, inode); if (wbc->pages_skipped != pages_skipped) { /* * writeback is not making progress due to locked @@ -560,7 +617,7 @@ static void generic_sync_bdi_inodes(struct backing_dev_info *bdi, wbc->more_io = 1; break; } - if (!list_empty(&bdi->b_more_io)) + if (!list_empty(&wb->b_more_io)) wbc->more_io = 1; } @@ -568,139 +625,500 @@ static void generic_sync_bdi_inodes(struct backing_dev_info *bdi, /* Leave any unwritten inodes on b_io */ } +void writeback_inodes_wbc(struct writeback_control *wbc) +{ + struct backing_dev_info *bdi = wbc->bdi; + + writeback_inodes_wb(&bdi->wb, wbc); +} + /* - * Write out a superblock's list of dirty inodes. A wait will be performed - * upon no inodes, all inodes or the final one, depending upon sync_mode. - * - * If older_than_this is non-NULL, then only write out inodes which - * had their first dirtying at a time earlier than *older_than_this. - * - * If we're a pdlfush thread, then implement pdflush collision avoidance - * against the entire list. + * The maximum number of pages to writeout in a single bdi flush/kupdate + * operation. We do this so we don't hold I_SYNC against an inode for + * enormous amounts of time, which would block a userspace task which has + * been forced to throttle against that inode. Also, the code reevaluates + * the dirty each time it has written this many pages. + */ +#define MAX_WRITEBACK_PAGES 1024 + +static inline bool over_bground_thresh(void) +{ + unsigned long background_thresh, dirty_thresh; + + get_dirty_limits(&background_thresh, &dirty_thresh, NULL, NULL); + + return (global_page_state(NR_FILE_DIRTY) + + global_page_state(NR_UNSTABLE_NFS) >= background_thresh); +} + +/* + * Explicit flushing or periodic writeback of "old" data. * - * If `bdi' is non-zero then we're being asked to writeback a specific queue. - * This function assumes that the blockdev superblock's inodes are backed by - * a variety of queues, so all inodes are searched. For other superblocks, - * assume that all inodes are backed by the same queue. + * Define "old": the first time one of an inode's pages is dirtied, we mark the + * dirtying-time in the inode's address_space. So this periodic writeback code + * just walks the superblock inode list, writing back any inodes which are + * older than a specific point in time. * - * FIXME: this linear search could get expensive with many fileystems. But - * how to fix? We need to go from an address_space to all inodes which share - * a queue with that address_space. (Easy: have a global "dirty superblocks" - * list). + * Try to run once per dirty_writeback_interval. But if a writeback event + * takes longer than a dirty_writeback_interval interval, then leave a + * one-second gap. * - * The inodes to be written are parked on bdi->b_io. They are moved back onto - * bdi->b_dirty as they are selected for writing. This way, none can be missed - * on the writer throttling path, and we get decent balancing between many - * throttled threads: we don't want them all piling up on inode_sync_wait. + * older_than_this takes precedence over nr_to_write. So we'll only write back + * all dirty pages if they are all attached to "old" mappings. */ -static void generic_sync_sb_inodes(struct super_block *sb, - struct writeback_control *wbc) +static long wb_writeback(struct bdi_writeback *wb, long nr_pages, + struct super_block *sb, + enum writeback_sync_modes sync_mode, int for_kupdate) { - struct backing_dev_info *bdi; - - if (!wbc->bdi) { - mutex_lock(&bdi_lock); - list_for_each_entry(bdi, &bdi_list, bdi_list) - generic_sync_bdi_inodes(bdi, wbc, sb); - mutex_unlock(&bdi_lock); - } else - generic_sync_bdi_inodes(wbc->bdi, wbc, sb); + struct writeback_control wbc = { + .bdi = wb->bdi, + .sb = sb, + .sync_mode = sync_mode, + .older_than_this = NULL, + .for_kupdate = for_kupdate, + .range_cyclic = 1, + }; + unsigned long oldest_jif; + long wrote = 0; - if (wbc->sync_mode == WB_SYNC_ALL) { - struct inode *inode, *old_inode = NULL; + if (wbc.for_kupdate) { + wbc.older_than_this = &oldest_jif; + oldest_jif = jiffies - + msecs_to_jiffies(dirty_expire_interval * 10); + } - spin_lock(&inode_lock); + for (;;) { + /* + * Don't flush anything for non-integrity writeback where + * no nr_pages was given + */ + if (!for_kupdate && nr_pages <= 0 && sync_mode == WB_SYNC_NONE) + break; /* - * Data integrity sync. Must wait for all pages under writeback, - * because there may have been pages dirtied before our sync - * call, but which had writeout started before we write it out. - * In which case, the inode may not be on the dirty list, but - * we still have to wait for that writeout. + * If no specific pages were given and this is just a + * periodic background writeout and we are below the + * background dirty threshold, don't do anything */ - list_for_each_entry(inode, &sb->s_inodes, i_sb_list) { - struct address_space *mapping; + if (for_kupdate && nr_pages <= 0 && !over_bground_thresh()) + break; - if (inode->i_state & - (I_FREEING|I_CLEAR|I_WILL_FREE|I_NEW)) - continue; - mapping = inode->i_mapping; - if (mapping->nrpages == 0) + wbc.more_io = 0; + wbc.encountered_congestion = 0; + wbc.nr_to_write = MAX_WRITEBACK_PAGES; + wbc.pages_skipped = 0; + writeback_inodes_wb(wb, &wbc); + nr_pages -= MAX_WRITEBACK_PAGES - wbc.nr_to_write; + wrote += MAX_WRITEBACK_PAGES - wbc.nr_to_write; + + /* + * If we ran out of stuff to write, bail unless more_io got set + */ + if (wbc.nr_to_write > 0 || wbc.pages_skipped > 0) { + if (wbc.more_io && !wbc.for_kupdate) continue; - __iget(inode); - spin_unlock(&inode_lock); + break; + } + } + + return wrote; +} + +/* + * Return the next bdi_work struct that hasn't been processed by this + * wb thread yet + */ +static struct bdi_work *get_next_work_item(struct backing_dev_info *bdi, + struct bdi_writeback *wb) +{ + struct bdi_work *work, *ret = NULL; + + rcu_read_lock(); + + list_for_each_entry_rcu(work, &bdi->work_list, list) { + if (!test_and_clear_bit(wb->nr, &work->seen)) + continue; + + ret = work; + break; + } + + rcu_read_unlock(); + return ret; +} + +static long wb_check_old_data_flush(struct bdi_writeback *wb) +{ + unsigned long expired; + long nr_pages; + + expired = wb->last_old_flush + + msecs_to_jiffies(dirty_writeback_interval * 10); + if (time_before(jiffies, expired)) + return 0; + + wb->last_old_flush = jiffies; + nr_pages = global_page_state(NR_FILE_DIRTY) + + global_page_state(NR_UNSTABLE_NFS) + + (inodes_stat.nr_inodes - inodes_stat.nr_unused); + + if (nr_pages) + return wb_writeback(wb, nr_pages, NULL, WB_SYNC_NONE, 1); + + return 0; +} + +/* + * Retrieve work items and do the writeback they describe + */ +long wb_do_writeback(struct bdi_writeback *wb, int force_wait) +{ + struct backing_dev_info *bdi = wb->bdi; + struct bdi_work *work; + long nr_pages, wrote = 0; + + while ((work = get_next_work_item(bdi, wb)) != NULL) { + enum writeback_sync_modes sync_mode; + + nr_pages = work->nr_pages; + + /* + * Override sync mode, in case we must wait for completion + */ + if (force_wait) + work->sync_mode = sync_mode = WB_SYNC_ALL; + else + sync_mode = work->sync_mode; + + /* + * If this isn't a data integrity operation, just notify + * that we have seen this work and we are now starting it. + */ + if (sync_mode == WB_SYNC_NONE) + wb_clear_pending(wb, work); + + wrote += wb_writeback(wb, nr_pages, work->sb, sync_mode, 0); + + /* + * This is a data integrity writeback, so only do the + * notification when we have completed the work. + */ + if (sync_mode == WB_SYNC_ALL) + wb_clear_pending(wb, work); + } + + /* + * Check for periodic writeback, kupdated() style + */ + wrote += wb_check_old_data_flush(wb); + + return wrote; +} + +/* + * Handle writeback of dirty data for the device backed by this bdi. Also + * wakes up periodically and does kupdated style flushing. + */ +int bdi_writeback_task(struct bdi_writeback *wb) +{ + unsigned long last_active = jiffies; + unsigned long wait_jiffies = -1UL; + long pages_written; + + while (!kthread_should_stop()) { + pages_written = wb_do_writeback(wb, 0); + + if (pages_written) + last_active = jiffies; + else if (wait_jiffies != -1UL) { + unsigned long max_idle; + /* - * We hold a reference to 'inode' so it couldn't have - * been removed from s_inodes list while we dropped the - * inode_lock. We cannot iput the inode now as we can - * be holding the last reference and we cannot iput it - * under inode_lock. So we keep the reference and iput - * it later. + * Longest period of inactivity that we tolerate. If we + * see dirty data again later, the task will get + * recreated automatically. */ - iput(old_inode); - old_inode = inode; + max_idle = max(5UL * 60 * HZ, wait_jiffies); + if (time_after(jiffies, max_idle + last_active)) + break; + } + + wait_jiffies = msecs_to_jiffies(dirty_writeback_interval * 10); + set_current_state(TASK_INTERRUPTIBLE); + schedule_timeout(wait_jiffies); + try_to_freeze(); + } + + return 0; +} + +/* + * Schedule writeback for all backing devices. Expensive! If this is a data + * integrity operation, writeback will be complete when this returns. If + * we are simply called for WB_SYNC_NONE, then writeback will merely be + * scheduled to run. + */ +static void bdi_writeback_all(struct writeback_control *wbc) +{ + const bool must_wait = wbc->sync_mode == WB_SYNC_ALL; + struct backing_dev_info *bdi; + struct bdi_work *work; + LIST_HEAD(list); + +restart: + spin_lock(&bdi_lock); + + list_for_each_entry(bdi, &bdi_list, bdi_list) { + struct bdi_work *work; + + if (!bdi_has_dirty_io(bdi)) + continue; - filemap_fdatawait(mapping); + /* + * If work allocation fails, do the writes inline. We drop + * the lock and restart the list writeout. This should be OK, + * since this happens rarely and because the writeout should + * eventually make more free memory available. + */ + work = bdi_alloc_work(wbc); + if (!work) { + struct writeback_control __wbc; - cond_resched(); + /* + * Not a data integrity writeout, just continue + */ + if (!must_wait) + continue; - spin_lock(&inode_lock); + spin_unlock(&bdi_lock); + __wbc = *wbc; + __wbc.bdi = bdi; + writeback_inodes_wbc(&__wbc); + goto restart; } - spin_unlock(&inode_lock); - iput(old_inode); + if (must_wait) + list_add_tail(&work->wait_list, &list); + + bdi_queue_work(bdi, work); + } + + spin_unlock(&bdi_lock); + + /* + * If this is for WB_SYNC_ALL, wait for pending work to complete + * before returning. + */ + while (!list_empty(&list)) { + work = list_entry(list.next, struct bdi_work, wait_list); + list_del(&work->wait_list); + bdi_wait_on_work_clear(work); + call_rcu(&work->rcu_head, bdi_work_free); } } /* - * Start writeback of dirty pagecache data against all unlocked inodes. + * Start writeback of `nr_pages' pages. If `nr_pages' is zero, write back + * the whole world. + */ +void wakeup_flusher_threads(long nr_pages) +{ + struct writeback_control wbc = { + .sync_mode = WB_SYNC_NONE, + .older_than_this = NULL, + .range_cyclic = 1, + }; + + if (nr_pages == 0) + nr_pages = global_page_state(NR_FILE_DIRTY) + + global_page_state(NR_UNSTABLE_NFS); + wbc.nr_to_write = nr_pages; + bdi_writeback_all(&wbc); +} + +static noinline void block_dump___mark_inode_dirty(struct inode *inode) +{ + if (inode->i_ino || strcmp(inode->i_sb->s_id, "bdev")) { + struct dentry *dentry; + const char *name = "?"; + + dentry = d_find_alias(inode); + if (dentry) { + spin_lock(&dentry->d_lock); + name = (const char *) dentry->d_name.name; + } + printk(KERN_DEBUG + "%s(%d): dirtied inode %lu (%s) on %s\n", + current->comm, task_pid_nr(current), inode->i_ino, + name, inode->i_sb->s_id); + if (dentry) { + spin_unlock(&dentry->d_lock); + dput(dentry); + } + } +} + +/** + * __mark_inode_dirty - internal function + * @inode: inode to mark + * @flags: what kind of dirty (i.e. I_DIRTY_SYNC) + * Mark an inode as dirty. Callers should use mark_inode_dirty or + * mark_inode_dirty_sync. * - * Note: - * We don't need to grab a reference to superblock here. If it has non-empty - * ->b_dirty it's hadn't been killed yet and kill_super() won't proceed - * past sync_inodes_sb() until the ->b_dirty/b_io/b_more_io lists are all - * empty. Since __sync_single_inode() regains inode_lock before it finally moves - * inode from superblock lists we are OK. + * Put the inode on the super block's dirty list. + * + * CAREFUL! We mark it dirty unconditionally, but move it onto the + * dirty list only if it is hashed or if it refers to a blockdev. + * If it was not hashed, it will never be added to the dirty list + * even if it is later hashed, as it will have been marked dirty already. + * + * In short, make sure you hash any inodes _before_ you start marking + * them dirty. * - * If `older_than_this' is non-zero then only flush inodes which have a - * flushtime older than *older_than_this. + * This function *must* be atomic for the I_DIRTY_PAGES case - + * set_page_dirty() is called under spinlock in several places. * - * If `bdi' is non-zero then we will scan the first inode against each - * superblock until we find the matching ones. One group will be the dirty - * inodes against a filesystem. Then when we hit the dummy blockdev superblock, - * sync_sb_inodes will seekout the blockdev which matches `bdi'. Maybe not - * super-efficient but we're about to do a ton of I/O... + * Note that for blockdevs, inode->dirtied_when represents the dirtying time of + * the block-special inode (/dev/hda1) itself. And the ->dirtied_when field of + * the kernel-internal blockdev inode represents the dirtying time of the + * blockdev's pages. This is why for I_DIRTY_PAGES we always use + * page->mapping->host, so the page-dirtying time is recorded in the internal + * blockdev inode. */ -void -writeback_inodes(struct writeback_control *wbc) +void __mark_inode_dirty(struct inode *inode, int flags) { - struct super_block *sb; + struct super_block *sb = inode->i_sb; - might_sleep(); - spin_lock(&sb_lock); -restart: - list_for_each_entry_reverse(sb, &super_blocks, s_list) { - if (sb_has_dirty_inodes(sb)) { - /* we're making our own get_super here */ - sb->s_count++; - spin_unlock(&sb_lock); - /* - * If we can't get the readlock, there's no sense in - * waiting around, most of the time the FS is going to - * be unmounted by the time it is released. - */ - if (down_read_trylock(&sb->s_umount)) { - if (sb->s_root) - generic_sync_sb_inodes(sb, wbc); - up_read(&sb->s_umount); - } - spin_lock(&sb_lock); - if (__put_super_and_need_restart(sb)) - goto restart; + /* + * Don't do this for I_DIRTY_PAGES - that doesn't actually + * dirty the inode itself + */ + if (flags & (I_DIRTY_SYNC | I_DIRTY_DATASYNC)) { + if (sb->s_op->dirty_inode) + sb->s_op->dirty_inode(inode); + } + + /* + * make sure that changes are seen by all cpus before we test i_state + * -- mikulas + */ + smp_mb(); + + /* avoid the locking if we can */ + if ((inode->i_state & flags) == flags) + return; + + if (unlikely(block_dump)) + block_dump___mark_inode_dirty(inode); + + spin_lock(&inode_lock); + if ((inode->i_state & flags) != flags) { + const int was_dirty = inode->i_state & I_DIRTY; + + inode->i_state |= flags; + + /* + * If the inode is being synced, just update its dirty state. + * The unlocker will place the inode on the appropriate + * superblock list, based upon its state. + */ + if (inode->i_state & I_SYNC) + goto out; + + /* + * Only add valid (hashed) inodes to the superblock's + * dirty list. Add blockdev inodes as well. + */ + if (!S_ISBLK(inode->i_mode)) { + if (hlist_unhashed(&inode->i_hash)) + goto out; + } + if (inode->i_state & (I_FREEING|I_CLEAR)) + goto out; + + /* + * If the inode was already on b_dirty/b_io/b_more_io, don't + * reposition it (that would break b_dirty time-ordering). + */ + if (!was_dirty) { + struct bdi_writeback *wb = &inode_to_bdi(inode)->wb; + + inode->dirtied_when = jiffies; + list_move(&inode->i_list, &wb->b_dirty); } - if (wbc->nr_to_write <= 0) - break; } - spin_unlock(&sb_lock); +out: + spin_unlock(&inode_lock); +} +EXPORT_SYMBOL(__mark_inode_dirty); + +/* + * Write out a superblock's list of dirty inodes. A wait will be performed + * upon no inodes, all inodes or the final one, depending upon sync_mode. + * + * If older_than_this is non-NULL, then only write out inodes which + * had their first dirtying at a time earlier than *older_than_this. + * + * If we're a pdlfush thread, then implement pdflush collision avoidance + * against the entire list. + * + * If `bdi' is non-zero then we're being asked to writeback a specific queue. + * This function assumes that the blockdev superblock's inodes are backed by + * a variety of queues, so all inodes are searched. For other superblocks, + * assume that all inodes are backed by the same queue. + * + * The inodes to be written are parked on bdi->b_io. They are moved back onto + * bdi->b_dirty as they are selected for writing. This way, none can be missed + * on the writer throttling path, and we get decent balancing between many + * throttled threads: we don't want them all piling up on inode_sync_wait. + */ +static void wait_sb_inodes(struct writeback_control *wbc) +{ + struct inode *inode, *old_inode = NULL; + + /* + * We need to be protected against the filesystem going from + * r/o to r/w or vice versa. + */ + WARN_ON(!rwsem_is_locked(&wbc->sb->s_umount)); + + spin_lock(&inode_lock); + + /* + * Data integrity sync. Must wait for all pages under writeback, + * because there may have been pages dirtied before our sync + * call, but which had writeout started before we write it out. + * In which case, the inode may not be on the dirty list, but + * we still have to wait for that writeout. + */ + list_for_each_entry(inode, &wbc->sb->s_inodes, i_sb_list) { + struct address_space *mapping; + + if (inode->i_state & (I_FREEING|I_CLEAR|I_WILL_FREE|I_NEW)) + continue; + mapping = inode->i_mapping; + if (mapping->nrpages == 0) + continue; + __iget(inode); + spin_unlock(&inode_lock); + /* + * We hold a reference to 'inode' so it couldn't have + * been removed from s_inodes list while we dropped the + * inode_lock. We cannot iput the inode now as we can + * be holding the last reference and we cannot iput it + * under inode_lock. So we keep the reference and iput + * it later. + */ + iput(old_inode); + old_inode = inode; + + filemap_fdatawait(mapping); + + cond_resched(); + + spin_lock(&inode_lock); + } + spin_unlock(&inode_lock); + iput(old_inode); } /** @@ -715,6 +1133,7 @@ restart: long writeback_inodes_sb(struct super_block *sb) { struct writeback_control wbc = { + .sb = sb, .sync_mode = WB_SYNC_NONE, .range_start = 0, .range_end = LLONG_MAX, @@ -727,7 +1146,7 @@ long writeback_inodes_sb(struct super_block *sb) (inodes_stat.nr_inodes - inodes_stat.nr_unused); wbc.nr_to_write = nr_to_write; - generic_sync_sb_inodes(sb, &wbc); + bdi_writeback_all(&wbc); return nr_to_write - wbc.nr_to_write; } EXPORT_SYMBOL(writeback_inodes_sb); @@ -742,6 +1161,7 @@ EXPORT_SYMBOL(writeback_inodes_sb); long sync_inodes_sb(struct super_block *sb) { struct writeback_control wbc = { + .sb = sb, .sync_mode = WB_SYNC_ALL, .range_start = 0, .range_end = LLONG_MAX, @@ -749,7 +1169,8 @@ long sync_inodes_sb(struct super_block *sb) long nr_to_write = LONG_MAX; /* doesn't actually matter */ wbc.nr_to_write = nr_to_write; - generic_sync_sb_inodes(sb, &wbc); + bdi_writeback_all(&wbc); + wait_sb_inodes(&wbc); return nr_to_write - wbc.nr_to_write; } EXPORT_SYMBOL(sync_inodes_sb); diff --git a/fs/super.c b/fs/super.c index 0d22ce3be4a..9cda337ddae 100644 --- a/fs/super.c +++ b/fs/super.c @@ -168,7 +168,7 @@ int __put_super_and_need_restart(struct super_block *sb) * Drops a temporary reference, frees superblock if there's no * references left. */ -static void put_super(struct super_block *sb) +void put_super(struct super_block *sb) { spin_lock(&sb_lock); __put_super(sb); diff --git a/fs/sync.c b/fs/sync.c index 66f210476f4..103cc7fdd3d 100644 --- a/fs/sync.c +++ b/fs/sync.c @@ -120,7 +120,7 @@ restart: */ SYSCALL_DEFINE0(sync) { - wakeup_pdflush(0); + wakeup_flusher_threads(0); sync_filesystems(0); sync_filesystems(1); if (unlikely(laptop_mode)) diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 928cd5484f4..d045f5f615c 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -13,6 +13,8 @@ #include #include #include +#include +#include #include struct page; @@ -23,7 +25,8 @@ 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_unused, /* Available bits start here */ @@ -39,9 +42,22 @@ 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 */ @@ -58,11 +74,15 @@ struct backing_dev_info { unsigned int min_ratio; unsigned int max_ratio, max_prop_frac; - struct device *dev; + 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 b_dirty; /* dirty inodes */ - struct list_head b_io; /* parked for writeback */ - struct list_head b_more_io; /* parked for more writeback */ + struct list_head work_list; + + struct device *dev; #ifdef CONFIG_DEBUG_FS struct dentry *debug_dir; @@ -77,10 +97,20 @@ 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 struct mutex bdi_lock; +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) { @@ -270,6 +300,11 @@ 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); @@ -285,4 +320,10 @@ 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 56371be1be6..26da98f6111 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1786,6 +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) \ @@ -2182,7 +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 07039299603..cef75527a14 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -40,6 +40,8 @@ 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 */ @@ -76,10 +78,13 @@ struct writeback_control { /* * fs/fs-writeback.c */ -void writeback_inodes(struct writeback_control *wbc); +struct bdi_writeback; int inode_wait(void *); 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) @@ -99,7 +104,6 @@ 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); diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 6f163e0f050..7f3fa79f25c 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -1,8 +1,11 @@ #include #include +#include +#include #include #include +#include #include #include #include @@ -22,8 +25,18 @@ struct backing_dev_info default_backing_dev_info = { EXPORT_SYMBOL_GPL(default_backing_dev_info); static struct class *bdi_class; -DEFINE_MUTEX(bdi_lock); +DEFINE_SPINLOCK(bdi_lock); LIST_HEAD(bdi_list); +LIST_HEAD(bdi_pending_list); + +static struct task_struct *sync_supers_tsk; +static struct timer_list sync_supers_timer; + +static int bdi_sync_supers(void *); +static void sync_supers_timer_fn(unsigned long); +static void arm_supers_timer(void); + +static void bdi_add_default_flusher_task(struct backing_dev_info *bdi); #ifdef CONFIG_DEBUG_FS #include @@ -187,6 +200,13 @@ static int __init default_bdi_init(void) { int err; + sync_supers_tsk = kthread_run(bdi_sync_supers, NULL, "sync_supers"); + BUG_ON(IS_ERR(sync_supers_tsk)); + + init_timer(&sync_supers_timer); + setup_timer(&sync_supers_timer, sync_supers_timer_fn, 0); + arm_supers_timer(); + err = bdi_init(&default_backing_dev_info); if (!err) bdi_register(&default_backing_dev_info, NULL, "default"); @@ -195,6 +215,242 @@ static int __init default_bdi_init(void) } subsys_initcall(default_bdi_init); +static void bdi_wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi) +{ + memset(wb, 0, sizeof(*wb)); + + wb->bdi = bdi; + wb->last_old_flush = jiffies; + INIT_LIST_HEAD(&wb->b_dirty); + INIT_LIST_HEAD(&wb->b_io); + INIT_LIST_HEAD(&wb->b_more_io); +} + +static void bdi_task_init(struct backing_dev_info *bdi, + struct bdi_writeback *wb) +{ + struct task_struct *tsk = current; + + spin_lock(&bdi->wb_lock); + list_add_tail_rcu(&wb->list, &bdi->wb_list); + spin_unlock(&bdi->wb_lock); + + tsk->flags |= PF_FLUSHER | PF_SWAPWRITE; + set_freezable(); + + /* + * Our parent may run at a different priority, just set us to normal + */ + set_user_nice(tsk, 0); +} + +static int bdi_start_fn(void *ptr) +{ + struct bdi_writeback *wb = ptr; + struct backing_dev_info *bdi = wb->bdi; + int ret; + + /* + * Add us to the active bdi_list + */ + spin_lock(&bdi_lock); + list_add(&bdi->bdi_list, &bdi_list); + spin_unlock(&bdi_lock); + + bdi_task_init(bdi, wb); + + /* + * Clear pending bit and wakeup anybody waiting to tear us down + */ + clear_bit(BDI_pending, &bdi->state); + smp_mb__after_clear_bit(); + wake_up_bit(&bdi->state, BDI_pending); + + ret = bdi_writeback_task(wb); + + /* + * Remove us from the list + */ + spin_lock(&bdi->wb_lock); + list_del_rcu(&wb->list); + spin_unlock(&bdi->wb_lock); + + /* + * Flush any work that raced with us exiting. No new work + * will be added, since this bdi isn't discoverable anymore. + */ + if (!list_empty(&bdi->work_list)) + wb_do_writeback(wb, 1); + + wb->task = NULL; + return ret; +} + +int bdi_has_dirty_io(struct backing_dev_info *bdi) +{ + return wb_has_dirty_io(&bdi->wb); +} + +static void bdi_flush_io(struct backing_dev_info *bdi) +{ + struct writeback_control wbc = { + .bdi = bdi, + .sync_mode = WB_SYNC_NONE, + .older_than_this = NULL, + .range_cyclic = 1, + .nr_to_write = 1024, + }; + + writeback_inodes_wbc(&wbc); +} + +/* + * kupdated() used to do this. We cannot do it from the bdi_forker_task() + * or we risk deadlocking on ->s_umount. The longer term solution would be + * to implement sync_supers_bdi() or similar and simply do it from the + * bdi writeback tasks individually. + */ +static int bdi_sync_supers(void *unused) +{ + set_user_nice(current, 0); + + while (!kthread_should_stop()) { + set_current_state(TASK_INTERRUPTIBLE); + schedule(); + + /* + * Do this periodically, like kupdated() did before. + */ + sync_supers(); + } + + return 0; +} + +static void arm_supers_timer(void) +{ + unsigned long next; + + next = msecs_to_jiffies(dirty_writeback_interval * 10) + jiffies; + mod_timer(&sync_supers_timer, round_jiffies_up(next)); +} + +static void sync_supers_timer_fn(unsigned long unused) +{ + wake_up_process(sync_supers_tsk); + arm_supers_timer(); +} + +static int bdi_forker_task(void *ptr) +{ + struct bdi_writeback *me = ptr; + + bdi_task_init(me->bdi, me); + + for (;;) { + struct backing_dev_info *bdi, *tmp; + struct bdi_writeback *wb; + + /* + * Temporary measure, we want to make sure we don't see + * dirty data on the default backing_dev_info + */ + if (wb_has_dirty_io(me) || !list_empty(&me->bdi->work_list)) + wb_do_writeback(me, 0); + + spin_lock(&bdi_lock); + + /* + * Check if any existing bdi's have dirty data without + * a thread registered. If so, set that up. + */ + list_for_each_entry_safe(bdi, tmp, &bdi_list, bdi_list) { + if (bdi->wb.task) + continue; + if (list_empty(&bdi->work_list) && + !bdi_has_dirty_io(bdi)) + continue; + + bdi_add_default_flusher_task(bdi); + } + + set_current_state(TASK_INTERRUPTIBLE); + + if (list_empty(&bdi_pending_list)) { + unsigned long wait; + + spin_unlock(&bdi_lock); + wait = msecs_to_jiffies(dirty_writeback_interval * 10); + schedule_timeout(wait); + try_to_freeze(); + continue; + } + + __set_current_state(TASK_RUNNING); + + /* + * This is our real job - check for pending entries in + * bdi_pending_list, and create the tasks that got added + */ + bdi = list_entry(bdi_pending_list.next, struct backing_dev_info, + bdi_list); + list_del_init(&bdi->bdi_list); + spin_unlock(&bdi_lock); + + wb = &bdi->wb; + wb->task = kthread_run(bdi_start_fn, wb, "flush-%s", + dev_name(bdi->dev)); + /* + * If task creation fails, then readd the bdi to + * the pending list and force writeout of the bdi + * from this forker thread. That will free some memory + * and we can try again. + */ + if (IS_ERR(wb->task)) { + wb->task = NULL; + + /* + * Add this 'bdi' to the back, so we get + * a chance to flush other bdi's to free + * memory. + */ + spin_lock(&bdi_lock); + list_add_tail(&bdi->bdi_list, &bdi_pending_list); + spin_unlock(&bdi_lock); + + bdi_flush_io(bdi); + } + } + + return 0; +} + +/* + * Add the default flusher task that gets created for any bdi + * that has dirty data pending writeout + */ +void static bdi_add_default_flusher_task(struct backing_dev_info *bdi) +{ + if (!bdi_cap_writeback_dirty(bdi)) + return; + + /* + * Check with the helper whether to proceed adding a task. Will only + * abort if we two or more simultanous calls to + * bdi_add_default_flusher_task() occured, further additions will block + * waiting for previous additions to finish. + */ + if (!test_and_set_bit(BDI_pending, &bdi->state)) { + list_move_tail(&bdi->bdi_list, &bdi_pending_list); + + /* + * We are now on the pending list, wake up bdi_forker_task() + * to finish the job and add us back to the active bdi_list + */ + wake_up_process(default_backing_dev_info.wb.task); + } +} + int bdi_register(struct backing_dev_info *bdi, struct device *parent, const char *fmt, ...) { @@ -213,13 +469,34 @@ int bdi_register(struct backing_dev_info *bdi, struct device *parent, goto exit; } - mutex_lock(&bdi_lock); + spin_lock(&bdi_lock); list_add_tail(&bdi->bdi_list, &bdi_list); - mutex_unlock(&bdi_lock); + spin_unlock(&bdi_lock); bdi->dev = dev; - bdi_debug_register(bdi, dev_name(dev)); + /* + * Just start the forker thread for our default backing_dev_info, + * and add other bdi's to the list. They will get a thread created + * on-demand when they need it. + */ + if (bdi_cap_flush_forker(bdi)) { + struct bdi_writeback *wb = &bdi->wb; + + wb->task = kthread_run(bdi_forker_task, wb, "bdi-%s", + dev_name(dev)); + if (IS_ERR(wb->task)) { + wb->task = NULL; + ret = -ENOMEM; + + spin_lock(&bdi_lock); + list_del(&bdi->bdi_list); + spin_unlock(&bdi_lock); + goto exit; + } + } + + bdi_debug_register(bdi, dev_name(dev)); exit: return ret; } @@ -231,17 +508,42 @@ int bdi_register_dev(struct backing_dev_info *bdi, dev_t dev) } EXPORT_SYMBOL(bdi_register_dev); -static void bdi_remove_from_list(struct backing_dev_info *bdi) +/* + * Remove bdi from the global list and shutdown any threads we have running + */ +static void bdi_wb_shutdown(struct backing_dev_info *bdi) { - mutex_lock(&bdi_lock); + struct bdi_writeback *wb; + + if (!bdi_cap_writeback_dirty(bdi)) + return; + + /* + * If setup is pending, wait for that to complete first + */ + wait_on_bit(&bdi->state, BDI_pending, bdi_sched_wait, + TASK_UNINTERRUPTIBLE); + + /* + * Make sure nobody finds us on the bdi_list anymore + */ + spin_lock(&bdi_lock); list_del(&bdi->bdi_list); - mutex_unlock(&bdi_lock); + spin_unlock(&bdi_lock); + + /* + * Finally, kill the kernel threads. We don't need to be RCU + * safe anymore, since the bdi is gone from visibility. + */ + list_for_each_entry(wb, &bdi->wb_list, list) + kthread_stop(wb->task); } void bdi_unregister(struct backing_dev_info *bdi) { if (bdi->dev) { - bdi_remove_from_list(bdi); + if (!bdi_cap_flush_forker(bdi)) + bdi_wb_shutdown(bdi); bdi_debug_unregister(bdi); device_unregister(bdi->dev); bdi->dev = NULL; @@ -251,18 +553,25 @@ EXPORT_SYMBOL(bdi_unregister); int bdi_init(struct backing_dev_info *bdi) { - int i; - int err; + int i, err; bdi->dev = NULL; bdi->min_ratio = 0; bdi->max_ratio = 100; bdi->max_prop_frac = PROP_FRAC_BASE; + spin_lock_init(&bdi->wb_lock); INIT_LIST_HEAD(&bdi->bdi_list); - INIT_LIST_HEAD(&bdi->b_io); - INIT_LIST_HEAD(&bdi->b_dirty); - INIT_LIST_HEAD(&bdi->b_more_io); + INIT_LIST_HEAD(&bdi->wb_list); + INIT_LIST_HEAD(&bdi->work_list); + + bdi_wb_init(&bdi->wb, bdi); + + /* + * Just one thread support for now, hard code mask and count + */ + bdi->wb_mask = 1; + bdi->wb_cnt = 1; for (i = 0; i < NR_BDI_STAT_ITEMS; i++) { err = percpu_counter_init(&bdi->bdi_stat[i], 0); @@ -277,8 +586,6 @@ int bdi_init(struct backing_dev_info *bdi) err: while (i--) percpu_counter_destroy(&bdi->bdi_stat[i]); - - bdi_remove_from_list(bdi); } return err; @@ -289,9 +596,7 @@ void bdi_destroy(struct backing_dev_info *bdi) { int i; - WARN_ON(!list_empty(&bdi->b_dirty)); - WARN_ON(!list_empty(&bdi->b_io)); - WARN_ON(!list_empty(&bdi->b_more_io)); + WARN_ON(bdi_has_dirty_io(bdi)); bdi_unregister(bdi); diff --git a/mm/page-writeback.c b/mm/page-writeback.c index f8341b6019b..25e7770309b 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -35,15 +35,6 @@ #include #include -/* - * The maximum number of pages to writeout in a single bdflush/kupdate - * operation. We do this so we don't hold I_SYNC against an inode for - * enormous amounts of time, which would block a userspace task which has - * been forced to throttle against that inode. Also, the code reevaluates - * the dirty each time it has written this many pages. - */ -#define MAX_WRITEBACK_PAGES 1024 - /* * After a CPU has dirtied this many pages, balance_dirty_pages_ratelimited * will look to see if it needs to force writeback or throttling. @@ -117,8 +108,6 @@ EXPORT_SYMBOL(laptop_mode); /* End of sysctl-exported parameters */ -static void background_writeout(unsigned long _min_pages); - /* * Scale the writeback cache size proportional to the relative writeout speeds. * @@ -326,7 +315,7 @@ int bdi_set_min_ratio(struct backing_dev_info *bdi, unsigned int min_ratio) { int ret = 0; - mutex_lock(&bdi_lock); + spin_lock(&bdi_lock); if (min_ratio > bdi->max_ratio) { ret = -EINVAL; } else { @@ -338,7 +327,7 @@ int bdi_set_min_ratio(struct backing_dev_info *bdi, unsigned int min_ratio) ret = -EINVAL; } } - mutex_unlock(&bdi_lock); + spin_unlock(&bdi_lock); return ret; } @@ -350,14 +339,14 @@ int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned max_ratio) if (max_ratio > 100) return -EINVAL; - mutex_lock(&bdi_lock); + spin_lock(&bdi_lock); if (bdi->min_ratio > max_ratio) { ret = -EINVAL; } else { bdi->max_ratio = max_ratio; bdi->max_prop_frac = (PROP_FRAC_BASE * max_ratio) / 100; } - mutex_unlock(&bdi_lock); + spin_unlock(&bdi_lock); return ret; } @@ -543,7 +532,7 @@ static void balance_dirty_pages(struct address_space *mapping) * up. */ if (bdi_nr_reclaimable > bdi_thresh) { - writeback_inodes(&wbc); + writeback_inodes_wbc(&wbc); pages_written += write_chunk - wbc.nr_to_write; get_dirty_limits(&background_thresh, &dirty_thresh, &bdi_thresh, bdi); @@ -572,7 +561,7 @@ static void balance_dirty_pages(struct address_space *mapping) if (pages_written >= write_chunk) break; /* We've done our duty */ - congestion_wait(BLK_RW_ASYNC, HZ/10); + schedule_timeout(1); } if (bdi_nr_reclaimable + bdi_nr_writeback < bdi_thresh && @@ -591,10 +580,18 @@ static void balance_dirty_pages(struct address_space *mapping) * background_thresh, to keep the amount of dirty memory low. */ if ((laptop_mode && pages_written) || - (!laptop_mode && (global_page_state(NR_FILE_DIRTY) - + global_page_state(NR_UNSTABLE_NFS) - > background_thresh))) - pdflush_operation(background_writeout, 0); + (!laptop_mode && ((nr_writeback = global_page_state(NR_FILE_DIRTY) + + global_page_state(NR_UNSTABLE_NFS)) + > background_thresh))) { + struct writeback_control wbc = { + .bdi = bdi, + .sync_mode = WB_SYNC_NONE, + .nr_to_write = nr_writeback, + }; + + + bdi_start_writeback(&wbc); + } } void set_page_dirty_balance(struct page *page, int page_mkwrite) @@ -678,124 +675,10 @@ void throttle_vm_writeout(gfp_t gfp_mask) } } -/* - * writeback at least _min_pages, and keep writing until the amount of dirty - * memory is less than the background threshold, or until we're all clean. - */ -static void background_writeout(unsigned long _min_pages) -{ - long min_pages = _min_pages; - struct writeback_control wbc = { - .bdi = NULL, - .sync_mode = WB_SYNC_NONE, - .older_than_this = NULL, - .nr_to_write = 0, - .nonblocking = 1, - .range_cyclic = 1, - }; - - for ( ; ; ) { - unsigned long background_thresh; - unsigned long dirty_thresh; - - get_dirty_limits(&background_thresh, &dirty_thresh, NULL, NULL); - if (global_page_state(NR_FILE_DIRTY) + - global_page_state(NR_UNSTABLE_NFS) < background_thresh - && min_pages <= 0) - break; - wbc.more_io = 0; - wbc.encountered_congestion = 0; - wbc.nr_to_write = MAX_WRITEBACK_PAGES; - wbc.pages_skipped = 0; - writeback_inodes(&wbc); - min_pages -= MAX_WRITEBACK_PAGES - wbc.nr_to_write; - if (wbc.nr_to_write > 0 || wbc.pages_skipped > 0) { - /* Wrote less than expected */ - if (wbc.encountered_congestion || wbc.more_io) - congestion_wait(BLK_RW_ASYNC, HZ/10); - else - break; - } - } -} - -/* - * Start writeback of `nr_pages' pages. If `nr_pages' is zero, write back - * the whole world. Returns 0 if a pdflush thread was dispatched. Returns - * -1 if all pdflush threads were busy. - */ -int wakeup_pdflush(long nr_pages) -{ - if (nr_pages == 0) - nr_pages = global_page_state(NR_FILE_DIRTY) + - global_page_state(NR_UNSTABLE_NFS); - return pdflush_operation(background_writeout, nr_pages); -} - -static void wb_timer_fn(unsigned long unused); static void laptop_timer_fn(unsigned long unused); -static DEFINE_TIMER(wb_timer, wb_timer_fn, 0, 0); static DEFINE_TIMER(laptop_mode_wb_timer, laptop_timer_fn, 0, 0); -/* - * Periodic writeback of "old" data. - * - * Define "old": the first time one of an inode's pages is dirtied, we mark the - * dirtying-time in the inode's address_space. So this periodic writeback code - * just walks the superblock inode list, writing back any inodes which are - * older than a specific point in time. - * - * Try to run once per dirty_writeback_interval. But if a writeback event - * takes longer than a dirty_writeback_interval interval, then leave a - * one-second gap. - * - * older_than_this takes precedence over nr_to_write. So we'll only write back - * all dirty pages if they are all attached to "old" mappings. - */ -static void wb_kupdate(unsigned long arg) -{ - unsigned long oldest_jif; - unsigned long start_jif; - unsigned long next_jif; - long nr_to_write; - struct writeback_control wbc = { - .bdi = NULL, - .sync_mode = WB_SYNC_NONE, - .older_than_this = &oldest_jif, - .nr_to_write = 0, - .nonblocking = 1, - .for_kupdate = 1, - .range_cyclic = 1, - }; - - sync_supers(); - - oldest_jif = jiffies - msecs_to_jiffies(dirty_expire_interval * 10); - start_jif = jiffies; - next_jif = start_jif + msecs_to_jiffies(dirty_writeback_interval * 10); - nr_to_write = global_page_state(NR_FILE_DIRTY) + - global_page_state(NR_UNSTABLE_NFS) + - (inodes_stat.nr_inodes - inodes_stat.nr_unused); - while (nr_to_write > 0) { - wbc.more_io = 0; - wbc.encountered_congestion = 0; - wbc.nr_to_write = MAX_WRITEBACK_PAGES; - writeback_inodes(&wbc); - if (wbc.nr_to_write > 0) { - if (wbc.encountered_congestion || wbc.more_io) - congestion_wait(BLK_RW_ASYNC, HZ/10); - else - break; /* All the old data is written */ - } - nr_to_write -= MAX_WRITEBACK_PAGES - wbc.nr_to_write; - } - if (time_before(next_jif, jiffies + HZ)) - next_jif = jiffies + HZ; - if (dirty_writeback_interval) - mod_timer(&wb_timer, next_jif); -} - /* * sysctl handler for /proc/sys/vm/dirty_writeback_centisecs */ @@ -803,28 +686,24 @@ int dirty_writeback_centisecs_handler(ctl_table *table, int write, struct file *file, void __user *buffer, size_t *length, loff_t *ppos) { proc_dointvec(table, write, file, buffer, length, ppos); - if (dirty_writeback_interval) - mod_timer(&wb_timer, jiffies + - msecs_to_jiffies(dirty_writeback_interval * 10)); - else - del_timer(&wb_timer); return 0; } -static void wb_timer_fn(unsigned long unused) -{ - if (pdflush_operation(wb_kupdate, 0) < 0) - mod_timer(&wb_timer, jiffies + HZ); /* delay 1 second */ -} - -static void laptop_flush(unsigned long unused) +static void do_laptop_sync(struct work_struct *work) { - sys_sync(); + wakeup_flusher_threads(0); + kfree(work); } static void laptop_timer_fn(unsigned long unused) { - pdflush_operation(laptop_flush, 0); + struct work_struct *work; + + work = kmalloc(sizeof(*work), GFP_ATOMIC); + if (work) { + INIT_WORK(work, do_laptop_sync); + schedule_work(work); + } } /* @@ -907,8 +786,6 @@ void __init page_writeback_init(void) { int shift; - mod_timer(&wb_timer, - jiffies + msecs_to_jiffies(dirty_writeback_interval * 10)); writeback_set_ratelimit(); register_cpu_notifier(&ratelimit_nb); diff --git a/mm/vmscan.c b/mm/vmscan.c index 94e86dd6954..ba8228e0a80 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1720,7 +1720,7 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist, */ if (total_scanned > sc->swap_cluster_max + sc->swap_cluster_max / 2) { - wakeup_pdflush(laptop_mode ? 0 : total_scanned); + wakeup_flusher_threads(laptop_mode ? 0 : total_scanned); sc->may_writepage = 1; } -- cgit v1.2.3-70-g09d2 From 3d2257f157c2324acbc0fa0fa54e8626a987edd2 Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Sat, 12 Sep 2009 07:35:37 +0200 Subject: Make DISCARD_BARRIER and DISCARD_NOBARRIER writes instead of reads The commands are conceptually writes, and in the case of IDE and SCSI commands actually are writes. They were only reads because we thought that would interact better with the elevators. Now the elevators know about discard requests, that advantage no longer exists. Signed-off-by: David Woodhouse Signed-off-by: Matthew Wilcox Signed-off-by: Jens Axboe --- include/linux/fs.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux/fs.h') diff --git a/include/linux/fs.h b/include/linux/fs.h index c1f993515f5..7f5a8ad2500 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -161,8 +161,8 @@ struct inodes_stat_t { * These aren't really reads or writes, they pass down information about * parts of device that are now unused by the file system. */ -#define DISCARD_NOBARRIER (1 << BIO_RW_DISCARD) -#define DISCARD_BARRIER ((1 << BIO_RW_DISCARD) | (1 << BIO_RW_BARRIER)) +#define DISCARD_NOBARRIER (WRITE | (1 << BIO_RW_DISCARD)) +#define DISCARD_BARRIER (DISCARD_NOBARRIER | (1 << BIO_RW_BARRIER)) #define SEL_IN 1 #define SEL_OUT 2 -- cgit v1.2.3-70-g09d2 From d3bccb6f4b886060aa0f58976b92b77d951f5434 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 17 Aug 2009 19:30:27 +0200 Subject: vfs: Introduce filemap_fdatawait_range This simple helper saves some filesystems conversion from byte offset to page numbers and also makes the fdata* interface more complete. Reviewed-by: Christoph Hellwig Signed-off-by: Jan Kara --- include/linux/fs.h | 2 ++ mm/filemap.c | 20 ++++++++++++++++++++ 2 files changed, 22 insertions(+) (limited to 'include/linux/fs.h') diff --git a/include/linux/fs.h b/include/linux/fs.h index a79f48373e7..beb0e2774b2 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2086,6 +2086,8 @@ extern int write_inode_now(struct inode *, int); extern int filemap_fdatawrite(struct address_space *); extern int filemap_flush(struct address_space *); extern int filemap_fdatawait(struct address_space *); +extern int filemap_fdatawait_range(struct address_space *, loff_t lstart, + loff_t lend); extern int filemap_write_and_wait(struct address_space *mapping); extern int filemap_write_and_wait_range(struct address_space *mapping, loff_t lstart, loff_t lend); diff --git a/mm/filemap.c b/mm/filemap.c index ccea3b665c1..65b2e50efcd 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -306,6 +306,26 @@ int wait_on_page_writeback_range(struct address_space *mapping, return ret; } +/** + * filemap_fdatawait_range - wait for all under-writeback pages to complete in a given range + * @mapping: address space structure to wait for + * @start: offset in bytes where the range starts + * @end: offset in bytes where the range ends (inclusive) + * + * Walk the list of under-writeback pages of the given address space + * in the given range and wait for all of them. + * + * This is just a simple wrapper so that callers don't have to convert offsets + * to page indexes themselves + */ +int filemap_fdatawait_range(struct address_space *mapping, loff_t start, + loff_t end) +{ + return wait_on_page_writeback_range(mapping, start >> PAGE_CACHE_SHIFT, + end >> PAGE_CACHE_SHIFT); +} +EXPORT_SYMBOL(filemap_fdatawait_range); + /** * sync_page_range - write and wait on all pages in the passed range * @inode: target inode -- cgit v1.2.3-70-g09d2 From e4dd9de3c66bc7e26c5c7f149a060c5a67cf06a0 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 17 Aug 2009 18:10:06 +0200 Subject: vfs: Export __generic_file_aio_write() and add some comments Rename __generic_file_aio_write_nolock() to __generic_file_aio_write(), add comments to write helpers explaining how they should be used and export __generic_file_aio_write() since it will be used by some filesystems. CC: ocfs2-devel@oss.oracle.com CC: Joel Becker Acked-by: Evgeniy Polyakov Reviewed-by: Christoph Hellwig Signed-off-by: Jan Kara --- include/linux/fs.h | 2 ++ mm/filemap.c | 57 +++++++++++++++++++++++++++++++++++++++++++++++------- 2 files changed, 52 insertions(+), 7 deletions(-) (limited to 'include/linux/fs.h') diff --git a/include/linux/fs.h b/include/linux/fs.h index beb0e2774b2..ea099d3a18d 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2204,6 +2204,8 @@ extern int generic_file_readonly_mmap(struct file *, struct vm_area_struct *); extern int file_read_actor(read_descriptor_t * desc, struct page *page, unsigned long offset, unsigned long size); int generic_write_checks(struct file *file, loff_t *pos, size_t *count, int isblk); extern ssize_t generic_file_aio_read(struct kiocb *, const struct iovec *, unsigned long, loff_t); +extern ssize_t __generic_file_aio_write(struct kiocb *, const struct iovec *, unsigned long, + loff_t *); extern ssize_t generic_file_aio_write(struct kiocb *, const struct iovec *, unsigned long, loff_t); extern ssize_t generic_file_aio_write_nolock(struct kiocb *, const struct iovec *, unsigned long, loff_t); diff --git a/mm/filemap.c b/mm/filemap.c index 65b2e50efcd..554a396d85e 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2368,9 +2368,27 @@ generic_file_buffered_write(struct kiocb *iocb, const struct iovec *iov, } EXPORT_SYMBOL(generic_file_buffered_write); -static ssize_t -__generic_file_aio_write_nolock(struct kiocb *iocb, const struct iovec *iov, - unsigned long nr_segs, loff_t *ppos) +/** + * __generic_file_aio_write - write data to a file + * @iocb: IO state structure (file, offset, etc.) + * @iov: vector with data to write + * @nr_segs: number of segments in the vector + * @ppos: position where to write + * + * This function does all the work needed for actually writing data to a + * file. It does all basic checks, removes SUID from the file, updates + * modification times and calls proper subroutines depending on whether we + * do direct IO or a standard buffered write. + * + * It expects i_mutex to be grabbed unless we work on a block device or similar + * object which does not need locking at all. + * + * This function does *not* take care of syncing data in case of O_SYNC write. + * A caller has to handle it. This is mainly due to the fact that we want to + * avoid syncing under i_mutex. + */ +ssize_t __generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t *ppos) { struct file *file = iocb->ki_filp; struct address_space * mapping = file->f_mapping; @@ -2467,7 +2485,23 @@ out: current->backing_dev_info = NULL; return written ? written : err; } +EXPORT_SYMBOL(__generic_file_aio_write); + +/** + * generic_file_aio_write_nolock - write data, usually to a device + * @iocb: IO state structure + * @iov: vector with data to write + * @nr_segs: number of segments in the vector + * @pos: position in file where to write + * + * This is a wrapper around __generic_file_aio_write() which takes care of + * syncing the file in case of O_SYNC file. It does not take i_mutex for the + * write itself but may do so during syncing. It is meant for users like block + * devices which do not need i_mutex during write. If your filesystem needs to + * do a write but already holds i_mutex, use __generic_file_aio_write() + * directly and then sync the file like generic_file_aio_write(). + */ ssize_t generic_file_aio_write_nolock(struct kiocb *iocb, const struct iovec *iov, unsigned long nr_segs, loff_t pos) { @@ -2478,8 +2512,7 @@ ssize_t generic_file_aio_write_nolock(struct kiocb *iocb, BUG_ON(iocb->ki_pos != pos); - ret = __generic_file_aio_write_nolock(iocb, iov, nr_segs, - &iocb->ki_pos); + ret = __generic_file_aio_write(iocb, iov, nr_segs, &iocb->ki_pos); if (ret > 0 && ((file->f_flags & O_SYNC) || IS_SYNC(inode))) { ssize_t err; @@ -2492,6 +2525,17 @@ ssize_t generic_file_aio_write_nolock(struct kiocb *iocb, } EXPORT_SYMBOL(generic_file_aio_write_nolock); +/** + * generic_file_aio_write - write data to a file + * @iocb: IO state structure + * @iov: vector with data to write + * @nr_segs: number of segments in the vector + * @pos: position in file where to write + * + * This is a wrapper around __generic_file_aio_write() to be used by most + * filesystems. It takes care of syncing the file in case of O_SYNC file + * and acquires i_mutex as needed. + */ ssize_t generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov, unsigned long nr_segs, loff_t pos) { @@ -2503,8 +2547,7 @@ ssize_t generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov, BUG_ON(iocb->ki_pos != pos); mutex_lock(&inode->i_mutex); - ret = __generic_file_aio_write_nolock(iocb, iov, nr_segs, - &iocb->ki_pos); + ret = __generic_file_aio_write(iocb, iov, nr_segs, &iocb->ki_pos); mutex_unlock(&inode->i_mutex); if (ret > 0 && ((file->f_flags & O_SYNC) || IS_SYNC(inode))) { -- cgit v1.2.3-70-g09d2 From eef99380679e20e7edc096aa4d8a98b875404d79 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 20 Aug 2009 17:43:41 +0200 Subject: vfs: Rename generic_file_aio_write_nolock generic_file_aio_write_nolock() is now used only by block devices and raw character device. Filesystems should use __generic_file_aio_write() in case generic_file_aio_write() doesn't suit them. So rename the function to blkdev_aio_write() and move it to fs/blockdev.c. Signed-off-by: Christoph Hellwig Signed-off-by: Jan Kara --- drivers/char/raw.c | 2 +- fs/block_dev.c | 29 ++++++++++++++++++++++++++++- include/linux/fs.h | 6 ++++-- mm/filemap.c | 39 --------------------------------------- 4 files changed, 33 insertions(+), 43 deletions(-) (limited to 'include/linux/fs.h') diff --git a/drivers/char/raw.c b/drivers/char/raw.c index 05f9d18b936..40268db02e2 100644 --- a/drivers/char/raw.c +++ b/drivers/char/raw.c @@ -246,7 +246,7 @@ static const struct file_operations raw_fops = { .read = do_sync_read, .aio_read = generic_file_aio_read, .write = do_sync_write, - .aio_write = generic_file_aio_write_nolock, + .aio_write = blkdev_aio_write, .open = raw_open, .release= raw_release, .ioctl = raw_ioctl, diff --git a/fs/block_dev.c b/fs/block_dev.c index 94dfda24c06..3581a4e5394 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -1404,6 +1404,33 @@ static long block_ioctl(struct file *file, unsigned cmd, unsigned long arg) return blkdev_ioctl(bdev, mode, cmd, arg); } +/* + * Write data to the block device. Only intended for the block device itself + * and the raw driver which basically is a fake block device. + * + * Does not take i_mutex for the write and thus is not for general purpose + * use. + */ +ssize_t blkdev_aio_write(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t pos) +{ + struct file *file = iocb->ki_filp; + ssize_t ret; + + BUG_ON(iocb->ki_pos != pos); + + ret = __generic_file_aio_write(iocb, iov, nr_segs, &iocb->ki_pos); + if (ret > 0 || ret == -EIOCBQUEUED) { + ssize_t err; + + err = generic_write_sync(file, pos, ret); + if (err < 0 && ret > 0) + ret = err; + } + return ret; +} +EXPORT_SYMBOL_GPL(blkdev_aio_write); + /* * Try to release a page associated with block device when the system * is under memory pressure. @@ -1436,7 +1463,7 @@ const struct file_operations def_blk_fops = { .read = do_sync_read, .write = do_sync_write, .aio_read = generic_file_aio_read, - .aio_write = generic_file_aio_write_nolock, + .aio_write = blkdev_aio_write, .mmap = generic_file_mmap, .fsync = block_fsync, .unlocked_ioctl = block_ioctl, diff --git a/include/linux/fs.h b/include/linux/fs.h index ea099d3a18d..6c1be3a4ede 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2207,8 +2207,6 @@ extern ssize_t generic_file_aio_read(struct kiocb *, const struct iovec *, unsig extern ssize_t __generic_file_aio_write(struct kiocb *, const struct iovec *, unsigned long, loff_t *); extern ssize_t generic_file_aio_write(struct kiocb *, const struct iovec *, unsigned long, loff_t); -extern ssize_t generic_file_aio_write_nolock(struct kiocb *, const struct iovec *, - unsigned long, loff_t); extern ssize_t generic_file_direct_write(struct kiocb *, const struct iovec *, unsigned long *, loff_t, loff_t *, size_t, size_t); extern ssize_t generic_file_buffered_write(struct kiocb *, const struct iovec *, @@ -2218,6 +2216,10 @@ extern ssize_t do_sync_write(struct file *filp, const char __user *buf, size_t l extern int generic_segment_checks(const struct iovec *iov, unsigned long *nr_segs, size_t *count, int access_flags); +/* fs/block_dev.c */ +extern ssize_t blkdev_aio_write(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t pos); + /* fs/splice.c */ extern ssize_t generic_file_splice_read(struct file *, loff_t *, struct pipe_inode_info *, size_t, unsigned int); diff --git a/mm/filemap.c b/mm/filemap.c index f863e1d7e22..3587554f45e 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2462,45 +2462,6 @@ out: } EXPORT_SYMBOL(__generic_file_aio_write); - -/** - * generic_file_aio_write_nolock - write data, usually to a device - * @iocb: IO state structure - * @iov: vector with data to write - * @nr_segs: number of segments in the vector - * @pos: position in file where to write - * - * This is a wrapper around __generic_file_aio_write() which takes care of - * syncing the file in case of O_SYNC file. It does not take i_mutex for the - * write itself but may do so during syncing. It is meant for users like block - * devices which do not need i_mutex during write. If your filesystem needs to - * do a write but already holds i_mutex, use __generic_file_aio_write() - * directly and then sync the file like generic_file_aio_write(). - */ -ssize_t generic_file_aio_write_nolock(struct kiocb *iocb, - const struct iovec *iov, unsigned long nr_segs, loff_t pos) -{ - struct file *file = iocb->ki_filp; - struct address_space *mapping = file->f_mapping; - struct inode *inode = mapping->host; - ssize_t ret; - - BUG_ON(iocb->ki_pos != pos); - - ret = __generic_file_aio_write(iocb, iov, nr_segs, &iocb->ki_pos); - - if ((ret > 0 || ret == -EIOCBQUEUED) && - ((file->f_flags & O_SYNC) || IS_SYNC(inode))) { - ssize_t err; - - err = sync_page_range_nolock(inode, mapping, pos, ret); - if (err < 0 && ret > 0) - ret = err; - } - return ret; -} -EXPORT_SYMBOL(generic_file_aio_write_nolock); - /** * generic_file_aio_write - write data to a file * @iocb: IO state structure -- cgit v1.2.3-70-g09d2 From 148f948ba877f4d3cdef036b1ff6d9f68986706a Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 17 Aug 2009 19:52:36 +0200 Subject: vfs: Introduce new helpers for syncing after writing to O_SYNC file or IS_SYNC inode Introduce new function for generic inode syncing (vfs_fsync_range) and use it from fsync() path. Introduce also new helper for syncing after a sync write (generic_write_sync) using the generic function. Use these new helpers for syncing from generic VFS functions. This makes O_SYNC writes to block devices acquire i_mutex for syncing. If we really care about this, we can make block_fsync() drop the i_mutex and reacquire it before it returns. CC: Evgeniy Polyakov CC: ocfs2-devel@oss.oracle.com CC: Joel Becker CC: Felix Blyakher CC: xfs@oss.sgi.com CC: Anton Altaparmakov CC: linux-ntfs-dev@lists.sourceforge.net CC: OGAWA Hirofumi CC: linux-ext4@vger.kernel.org CC: tytso@mit.edu Acked-by: Christoph Hellwig Signed-off-by: Jan Kara --- fs/splice.c | 22 ++++++---------------- fs/sync.c | 55 +++++++++++++++++++++++++++++++++++++++++++++++------- include/linux/fs.h | 3 +++ mm/filemap.c | 11 ++++------- 4 files changed, 61 insertions(+), 30 deletions(-) (limited to 'include/linux/fs.h') diff --git a/fs/splice.c b/fs/splice.c index 73766d24f97..819023733f8 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -976,25 +976,15 @@ generic_file_splice_write(struct pipe_inode_info *pipe, struct file *out, if (ret > 0) { unsigned long nr_pages; + int err; - *ppos += ret; nr_pages = (ret + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; - /* - * If file or inode is SYNC and we actually wrote some data, - * sync it. - */ - if (unlikely((out->f_flags & O_SYNC) || IS_SYNC(inode))) { - int err; - - mutex_lock(&inode->i_mutex); - err = generic_osync_inode(inode, mapping, - OSYNC_METADATA|OSYNC_DATA); - mutex_unlock(&inode->i_mutex); - - if (err) - ret = err; - } + err = generic_write_sync(out, *ppos, ret); + if (err) + ret = err; + else + *ppos += ret; balance_dirty_pages_ratelimited_nr(mapping, nr_pages); } diff --git a/fs/sync.c b/fs/sync.c index 103cc7fdd3d..4e15da01923 100644 --- a/fs/sync.c +++ b/fs/sync.c @@ -178,19 +178,23 @@ int file_fsync(struct file *filp, struct dentry *dentry, int datasync) } /** - * vfs_fsync - perform a fsync or fdatasync on a file + * vfs_fsync_range - helper to sync a range of data & metadata to disk * @file: file to sync * @dentry: dentry of @file - * @data: only perform a fdatasync operation + * @start: offset in bytes of the beginning of data range to sync + * @end: offset in bytes of the end of data range (inclusive) + * @datasync: perform only datasync * - * Write back data and metadata for @file to disk. If @datasync is - * set only metadata needed to access modified file data is written. + * Write back data in range @start..@end and metadata for @file to disk. If + * @datasync is set only metadata needed to access modified file data is + * written. * * In case this function is called from nfsd @file may be %NULL and * only @dentry is set. This can only happen when the filesystem * implements the export_operations API. */ -int vfs_fsync(struct file *file, struct dentry *dentry, int datasync) +int vfs_fsync_range(struct file *file, struct dentry *dentry, loff_t start, + loff_t end, int datasync) { const struct file_operations *fop; struct address_space *mapping; @@ -214,7 +218,7 @@ int vfs_fsync(struct file *file, struct dentry *dentry, int datasync) goto out; } - ret = filemap_fdatawrite(mapping); + ret = filemap_fdatawrite_range(mapping, start, end); /* * We need to protect against concurrent writers, which could cause @@ -225,12 +229,32 @@ int vfs_fsync(struct file *file, struct dentry *dentry, int datasync) if (!ret) ret = err; mutex_unlock(&mapping->host->i_mutex); - err = filemap_fdatawait(mapping); + + err = filemap_fdatawait_range(mapping, start, end); if (!ret) ret = err; out: return ret; } +EXPORT_SYMBOL(vfs_fsync_range); + +/** + * vfs_fsync - perform a fsync or fdatasync on a file + * @file: file to sync + * @dentry: dentry of @file + * @datasync: only perform a fdatasync operation + * + * Write back data and metadata for @file to disk. If @datasync is + * set only metadata needed to access modified file data is written. + * + * In case this function is called from nfsd @file may be %NULL and + * only @dentry is set. This can only happen when the filesystem + * implements the export_operations API. + */ +int vfs_fsync(struct file *file, struct dentry *dentry, int datasync) +{ + return vfs_fsync_range(file, dentry, 0, LLONG_MAX, datasync); +} EXPORT_SYMBOL(vfs_fsync); static int do_fsync(unsigned int fd, int datasync) @@ -256,6 +280,23 @@ SYSCALL_DEFINE1(fdatasync, unsigned int, fd) return do_fsync(fd, 1); } +/** + * generic_write_sync - perform syncing after a write if file / inode is sync + * @file: file to which the write happened + * @pos: offset where the write started + * @count: length of the write + * + * This is just a simple wrapper about our general syncing function. + */ +int generic_write_sync(struct file *file, loff_t pos, loff_t count) +{ + if (!(file->f_flags & O_SYNC) && !IS_SYNC(file->f_mapping->host)) + return 0; + return vfs_fsync_range(file, file->f_path.dentry, pos, + pos + count - 1, 1); +} +EXPORT_SYMBOL(generic_write_sync); + /* * sys_sync_file_range() permits finely controlled syncing over a segment of * a file in the range offset .. (offset+nbytes-1) inclusive. If nbytes is diff --git a/include/linux/fs.h b/include/linux/fs.h index 6c1be3a4ede..e2c7f516766 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2098,7 +2098,10 @@ extern int __filemap_fdatawrite_range(struct address_space *mapping, extern int filemap_fdatawrite_range(struct address_space *mapping, loff_t start, loff_t end); +extern int vfs_fsync_range(struct file *file, struct dentry *dentry, + loff_t start, loff_t end, int datasync); extern int vfs_fsync(struct file *file, struct dentry *dentry, int datasync); +extern int generic_write_sync(struct file *file, loff_t pos, loff_t count); extern void sync_supers(void); extern void emergency_sync(void); extern void emergency_remount(void); diff --git a/mm/filemap.c b/mm/filemap.c index 3587554f45e..849293c4f41 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -39,11 +39,10 @@ /* * FIXME: remove all knowledge of the buffer layer from the core VM */ -#include /* for generic_osync_inode */ +#include /* for try_to_free_buffers */ #include - /* * Shared mappings implemented 30.11.1994. It's not fully working yet, * though. @@ -2477,8 +2476,7 @@ ssize_t generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov, unsigned long nr_segs, loff_t pos) { struct file *file = iocb->ki_filp; - struct address_space *mapping = file->f_mapping; - struct inode *inode = mapping->host; + struct inode *inode = file->f_mapping->host; ssize_t ret; BUG_ON(iocb->ki_pos != pos); @@ -2487,11 +2485,10 @@ ssize_t generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov, ret = __generic_file_aio_write(iocb, iov, nr_segs, &iocb->ki_pos); mutex_unlock(&inode->i_mutex); - if ((ret > 0 || ret == -EIOCBQUEUED) && - ((file->f_flags & O_SYNC) || IS_SYNC(inode))) { + if (ret > 0 || ret == -EIOCBQUEUED) { ssize_t err; - err = sync_page_range(inode, mapping, pos, ret); + err = generic_write_sync(file, pos, ret); if (err < 0 && ret > 0) ret = err; } -- cgit v1.2.3-70-g09d2 From 18f2ee705d98034b0f229a3202d827468d4bffd9 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Tue, 18 Aug 2009 18:43:15 +0200 Subject: vfs: Remove generic_osync_inode() and sync_page_range{_nolock}() Remove these three functions since nobody uses them anymore. Signed-off-by: Jan Kara --- fs/fs-writeback.c | 54 --------------------------------------- include/linux/fs.h | 5 ---- include/linux/writeback.h | 4 --- mm/filemap.c | 64 ----------------------------------------------- 4 files changed, 127 deletions(-) (limited to 'include/linux/fs.h') diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index da86ef58e42..628235cf44b 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -1242,57 +1242,3 @@ int sync_inode(struct inode *inode, struct writeback_control *wbc) return ret; } EXPORT_SYMBOL(sync_inode); - -/** - * generic_osync_inode - flush all dirty data for a given inode to disk - * @inode: inode to write - * @mapping: the address_space that should be flushed - * @what: what to write and wait upon - * - * This can be called by file_write functions for files which have the - * O_SYNC flag set, to flush dirty writes to disk. - * - * @what is a bitmask, specifying which part of the inode's data should be - * written and waited upon. - * - * OSYNC_DATA: i_mapping's dirty data - * OSYNC_METADATA: the buffers at i_mapping->private_list - * OSYNC_INODE: the inode itself - */ - -int generic_osync_inode(struct inode *inode, struct address_space *mapping, int what) -{ - int err = 0; - int need_write_inode_now = 0; - int err2; - - if (what & OSYNC_DATA) - err = filemap_fdatawrite(mapping); - if (what & (OSYNC_METADATA|OSYNC_DATA)) { - err2 = sync_mapping_buffers(mapping); - if (!err) - err = err2; - } - if (what & OSYNC_DATA) { - err2 = filemap_fdatawait(mapping); - if (!err) - err = err2; - } - - spin_lock(&inode_lock); - if ((inode->i_state & I_DIRTY) && - ((what & OSYNC_INODE) || (inode->i_state & I_DIRTY_DATASYNC))) - need_write_inode_now = 1; - spin_unlock(&inode_lock); - - if (need_write_inode_now) { - err2 = write_inode_now(inode, 1); - if (!err) - err = err2; - } - else - inode_sync_wait(inode); - - return err; -} -EXPORT_SYMBOL(generic_osync_inode); diff --git a/include/linux/fs.h b/include/linux/fs.h index e2c7f516766..37f53216998 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1455,11 +1455,6 @@ int fiemap_check_flags(struct fiemap_extent_info *fieinfo, u32 fs_flags); #define DT_SOCK 12 #define DT_WHT 14 -#define OSYNC_METADATA (1<<0) -#define OSYNC_DATA (1<<1) -#define OSYNC_INODE (1<<2) -int generic_osync_inode(struct inode *, struct address_space *, int); - /* * This is the "filldir" function type, used by readdir() to let * the kernel specify what kind of dirent layout it wants to have. diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 78b1e4684cc..d347632f186 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -150,10 +150,6 @@ int write_cache_pages(struct address_space *mapping, struct writeback_control *wbc, writepage_t writepage, void *data); int do_writepages(struct address_space *mapping, struct writeback_control *wbc); -int sync_page_range(struct inode *inode, struct address_space *mapping, - loff_t pos, loff_t count); -int sync_page_range_nolock(struct inode *inode, struct address_space *mapping, - loff_t pos, loff_t count); void set_page_dirty_balance(struct page *page, int page_mkwrite); void writeback_set_ratelimit(void); diff --git a/mm/filemap.c b/mm/filemap.c index 849293c4f41..dd51c68e2b8 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -325,70 +325,6 @@ int filemap_fdatawait_range(struct address_space *mapping, loff_t start, } EXPORT_SYMBOL(filemap_fdatawait_range); -/** - * sync_page_range - write and wait on all pages in the passed range - * @inode: target inode - * @mapping: target address_space - * @pos: beginning offset in pages to write - * @count: number of bytes to write - * - * Write and wait upon all the pages in the passed range. This is a "data - * integrity" operation. It waits upon in-flight writeout before starting and - * waiting upon new writeout. If there was an IO error, return it. - * - * We need to re-take i_mutex during the generic_osync_inode list walk because - * it is otherwise livelockable. - */ -int sync_page_range(struct inode *inode, struct address_space *mapping, - loff_t pos, loff_t count) -{ - pgoff_t start = pos >> PAGE_CACHE_SHIFT; - pgoff_t end = (pos + count - 1) >> PAGE_CACHE_SHIFT; - int ret; - - if (!mapping_cap_writeback_dirty(mapping) || !count) - return 0; - ret = filemap_fdatawrite_range(mapping, pos, pos + count - 1); - if (ret == 0) { - mutex_lock(&inode->i_mutex); - ret = generic_osync_inode(inode, mapping, OSYNC_METADATA); - mutex_unlock(&inode->i_mutex); - } - if (ret == 0) - ret = wait_on_page_writeback_range(mapping, start, end); - return ret; -} -EXPORT_SYMBOL(sync_page_range); - -/** - * sync_page_range_nolock - write & wait on all pages in the passed range without locking - * @inode: target inode - * @mapping: target address_space - * @pos: beginning offset in pages to write - * @count: number of bytes to write - * - * Note: Holding i_mutex across sync_page_range_nolock() is not a good idea - * as it forces O_SYNC writers to different parts of the same file - * to be serialised right until io completion. - */ -int sync_page_range_nolock(struct inode *inode, struct address_space *mapping, - loff_t pos, loff_t count) -{ - pgoff_t start = pos >> PAGE_CACHE_SHIFT; - pgoff_t end = (pos + count - 1) >> PAGE_CACHE_SHIFT; - int ret; - - if (!mapping_cap_writeback_dirty(mapping) || !count) - return 0; - ret = filemap_fdatawrite_range(mapping, pos, pos + count - 1); - if (ret == 0) - ret = generic_osync_inode(inode, mapping, OSYNC_METADATA); - if (ret == 0) - ret = wait_on_page_writeback_range(mapping, start, end); - return ret; -} -EXPORT_SYMBOL(sync_page_range_nolock); - /** * filemap_fdatawait - wait for all under-writeback pages to complete * @mapping: address space structure to wait for -- cgit v1.2.3-70-g09d2