From 8aa7e847d834ed937a9ad37a0f2ad5b8584c1ab0 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 9 Jul 2009 14:52:32 +0200 Subject: Fix congestion_wait() sync/async vs read/write confusion Commit 1faa16d22877f4839bd433547d770c676d1d964c accidentally broke the bdi congestion wait queue logic, causing us to wait on congestion for WRITE (== 1) when we really wanted BLK_RW_ASYNC (== 0) instead. Signed-off-by: Jens Axboe --- include/linux/backing-dev.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux/backing-dev.h') diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 0ec2c594868e..3a52a63c1351 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -229,9 +229,9 @@ static inline int bdi_rw_congested(struct backing_dev_info *bdi) (1 << BDI_async_congested)); } -void clear_bdi_congested(struct backing_dev_info *bdi, int rw); -void set_bdi_congested(struct backing_dev_info *bdi, int rw); -long congestion_wait(int rw, long timeout); +void clear_bdi_congested(struct backing_dev_info *bdi, int sync); +void set_bdi_congested(struct backing_dev_info *bdi, int sync); +long congestion_wait(int sync, long timeout); static inline bool bdi_cap_writeback_dirty(struct backing_dev_info *bdi) -- cgit v1.2.3 From 373c0a7ed3ea3b34efedb7c83ffb521adff7c894 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sat, 11 Jul 2009 10:06:54 -0400 Subject: Fix compile error due to congestion_wait() changes Move the definition of BLK_RW_ASYNC/BLK_RW_SYNC into linux/backing-dev.h so that it is available to all callers of set/clear_bdi_congested(). This replaces commit 097041e576ee3a50d92dd643ee8ca65bf6a62e21 ("fuse: Fix build error"), which will be reverted. Signed-off-by: Trond Myklebust Acked-by: Larry Finger Cc: Jens Axboe Cc: Miklos Szeredi Signed-off-by: Linus Torvalds --- include/linux/backing-dev.h | 5 +++++ include/linux/blkdev.h | 5 ----- 2 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux/backing-dev.h') diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 3a52a63c1351..1d52425a6118 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -229,6 +229,11 @@ static inline int bdi_rw_congested(struct backing_dev_info *bdi) (1 << BDI_async_congested)); } +enum { + BLK_RW_ASYNC = 0, + BLK_RW_SYNC = 1, +}; + void clear_bdi_congested(struct backing_dev_info *bdi, int sync); void set_bdi_congested(struct backing_dev_info *bdi, int sync); long congestion_wait(int sync, long timeout); diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 0146e0fecf1a..e7cb5dbf6c26 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -70,11 +70,6 @@ enum rq_cmd_type_bits { REQ_TYPE_ATA_PC, }; -enum { - BLK_RW_ASYNC = 0, - BLK_RW_SYNC = 1, -}; - /* * For request of type REQ_TYPE_LINUX_BLOCK, rq->cmd[0] is the opcode being * sent down (similar to how REQ_TYPE_BLOCK_PC means that ->cmd[] holds a -- cgit v1.2.3 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/backing-dev.h') diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 271e5f44e871..45ad4bb700e6 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 2761d3e22ed9..0d22ce3be4aa 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 1d52425a6118..928cd5484f4d 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 46ff7dd6e164..56371be1be65 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 c86edd244294..6f163e0f0509 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 81627ebcd313..f8341b6019bf 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 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/backing-dev.h') diff --git a/fs/buffer.c b/fs/buffer.c index 28f320fac4d4..90a98865b0cc 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 45ad4bb700e6..7f6dae8aa47f 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 0d22ce3be4aa..9cda337ddae2 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 66f210476f40..103cc7fdd3df 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 928cd5484f4d..d045f5f615c7 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 56371be1be65..26da98f61116 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 07039299603d..cef75527a14c 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 6f163e0f0509..7f3fa79f25c0 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 f8341b6019bf..25e7770309b8 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 94e86dd6954c..ba8228e0a806 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 From d993831fa7ffeb89e994f046f93eeb09ec91df08 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 12 Jun 2009 14:45:52 +0200 Subject: writeback: add name to backing_dev_info This enables us to track who does what and print info. Its main use is catching dirty inodes on the default_backing_dev_info, so we can fix that up. Signed-off-by: Jens Axboe --- block/blk-core.c | 1 + drivers/block/aoe/aoeblk.c | 1 + drivers/char/mem.c | 1 + fs/btrfs/disk-io.c | 1 + fs/char_dev.c | 1 + fs/configfs/inode.c | 1 + fs/fuse/inode.c | 1 + fs/hugetlbfs/inode.c | 1 + fs/nfs/client.c | 1 + fs/ocfs2/dlm/dlmfs.c | 1 + fs/ramfs/inode.c | 1 + fs/sysfs/inode.c | 1 + fs/ubifs/super.c | 1 + include/linux/backing-dev.h | 2 ++ kernel/cgroup.c | 1 + mm/backing-dev.c | 1 + mm/swap_state.c | 1 + 17 files changed, 18 insertions(+) (limited to 'include/linux/backing-dev.h') diff --git a/block/blk-core.c b/block/blk-core.c index e3299a77a0d8..e695634882a6 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -501,6 +501,7 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id) (VM_MAX_READAHEAD * 1024) / PAGE_CACHE_SIZE; q->backing_dev_info.state = 0; q->backing_dev_info.capabilities = BDI_CAP_MAP_COPY; + q->backing_dev_info.name = "block"; err = bdi_init(&q->backing_dev_info); if (err) { diff --git a/drivers/block/aoe/aoeblk.c b/drivers/block/aoe/aoeblk.c index 1e15889c4b98..95d344971eda 100644 --- a/drivers/block/aoe/aoeblk.c +++ b/drivers/block/aoe/aoeblk.c @@ -268,6 +268,7 @@ aoeblk_gdalloc(void *vp) if (!d->blkq) goto err_mempool; blk_queue_make_request(d->blkq, aoeblk_make_request); + d->blkq->backing_dev_info.name = "aoe"; if (bdi_init(&d->blkq->backing_dev_info)) goto err_blkq; spin_lock_irqsave(&d->lock, flags); diff --git a/drivers/char/mem.c b/drivers/char/mem.c index afa8813e737a..645237bda682 100644 --- a/drivers/char/mem.c +++ b/drivers/char/mem.c @@ -822,6 +822,7 @@ static const struct file_operations zero_fops = { * - permits private mappings, "copies" are taken of the source of zeros */ static struct backing_dev_info zero_bdi = { + .name = "char/mem", .capabilities = BDI_CAP_MAP_COPY, }; diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index e83be2e4602c..15831d5c7367 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1352,6 +1352,7 @@ static int setup_bdi(struct btrfs_fs_info *info, struct backing_dev_info *bdi) { int err; + bdi->name = "btrfs"; bdi->capabilities = BDI_CAP_MAP_COPY; err = bdi_init(bdi); if (err) diff --git a/fs/char_dev.c b/fs/char_dev.c index a173551e19d7..7c27a8ebef6a 100644 --- a/fs/char_dev.c +++ b/fs/char_dev.c @@ -31,6 +31,7 @@ * - no readahead or I/O queue unplugging required */ struct backing_dev_info directly_mappable_cdev_bdi = { + .name = "char", .capabilities = ( #ifdef CONFIG_MMU /* permit private copies of the data to be taken */ diff --git a/fs/configfs/inode.c b/fs/configfs/inode.c index 4921e7426d95..a2f746066c5d 100644 --- a/fs/configfs/inode.c +++ b/fs/configfs/inode.c @@ -51,6 +51,7 @@ static const struct address_space_operations configfs_aops = { }; static struct backing_dev_info configfs_backing_dev_info = { + .name = "configfs", .ra_pages = 0, /* No readahead */ .capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK, }; diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index f91ccc4a189d..4567db6f9430 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -801,6 +801,7 @@ static int fuse_bdi_init(struct fuse_conn *fc, struct super_block *sb) { int err; + fc->bdi.name = "fuse"; fc->bdi.ra_pages = (VM_MAX_READAHEAD * 1024) / PAGE_CACHE_SIZE; fc->bdi.unplug_io_fn = default_unplug_io_fn; /* fuse does it's own writeback accounting */ diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index cb88dac8ccaa..a93b885311d8 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -44,6 +44,7 @@ static const struct inode_operations hugetlbfs_dir_inode_operations; static const struct inode_operations hugetlbfs_inode_operations; static struct backing_dev_info hugetlbfs_backing_dev_info = { + .name = "hugetlbfs", .ra_pages = 0, /* No readahead */ .capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK, }; diff --git a/fs/nfs/client.c b/fs/nfs/client.c index 8d25ccb2d51d..c6be84a161f6 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -879,6 +879,7 @@ static void nfs_server_set_fsinfo(struct nfs_server *server, struct nfs_fsinfo * server->rsize = NFS_MAX_FILE_IO_SIZE; server->rpages = (server->rsize + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; + server->backing_dev_info.name = "nfs"; server->backing_dev_info.ra_pages = server->rpages * NFS_MAX_READAHEAD; if (server->wsize > max_rpc_payload) diff --git a/fs/ocfs2/dlm/dlmfs.c b/fs/ocfs2/dlm/dlmfs.c index 1c9efb406a96..02bf17808bdc 100644 --- a/fs/ocfs2/dlm/dlmfs.c +++ b/fs/ocfs2/dlm/dlmfs.c @@ -325,6 +325,7 @@ clear_fields: } static struct backing_dev_info dlmfs_backing_dev_info = { + .name = "ocfs2-dlmfs", .ra_pages = 0, /* No readahead */ .capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK, }; diff --git a/fs/ramfs/inode.c b/fs/ramfs/inode.c index 0ff7566c767c..a7f0110fca4c 100644 --- a/fs/ramfs/inode.c +++ b/fs/ramfs/inode.c @@ -46,6 +46,7 @@ static const struct super_operations ramfs_ops; static const struct inode_operations ramfs_dir_inode_operations; static struct backing_dev_info ramfs_backing_dev_info = { + .name = "ramfs", .ra_pages = 0, /* No readahead */ .capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK | BDI_CAP_MAP_DIRECT | BDI_CAP_MAP_COPY | diff --git a/fs/sysfs/inode.c b/fs/sysfs/inode.c index 555f0ff988df..e57f98e54fce 100644 --- a/fs/sysfs/inode.c +++ b/fs/sysfs/inode.c @@ -29,6 +29,7 @@ static const struct address_space_operations sysfs_aops = { }; static struct backing_dev_info sysfs_backing_dev_info = { + .name = "sysfs", .ra_pages = 0, /* No readahead */ .capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK, }; diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c index 8d6050a5966c..51763aa8f4de 100644 --- a/fs/ubifs/super.c +++ b/fs/ubifs/super.c @@ -1965,6 +1965,7 @@ static int ubifs_fill_super(struct super_block *sb, void *data, int silent) * * Read-ahead will be disabled because @c->bdi.ra_pages is 0. */ + c->bdi.name = "ubifs", c->bdi.capabilities = BDI_CAP_MAP_COPY; c->bdi.unplug_io_fn = default_unplug_io_fn; err = bdi_init(&c->bdi); diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index d045f5f615c7..2f218b7cb063 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -66,6 +66,8 @@ struct backing_dev_info { void (*unplug_io_fn)(struct backing_dev_info *, struct page *); void *unplug_io_data; + char *name; + struct percpu_counter bdi_stat[NR_BDI_STAT_ITEMS]; struct prop_local_percpu completions; diff --git a/kernel/cgroup.c b/kernel/cgroup.c index b6eadfe30e7b..c7ece8f027f2 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -600,6 +600,7 @@ static struct inode_operations cgroup_dir_inode_operations; static struct file_operations proc_cgroupstats_operations; static struct backing_dev_info cgroup_backing_dev_info = { + .name = "cgroup", .capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK, }; diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 22c45e932e3a..5cb32c5b93d8 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -17,6 +17,7 @@ void default_unplug_io_fn(struct backing_dev_info *bdi, struct page *page) EXPORT_SYMBOL(default_unplug_io_fn); struct backing_dev_info default_backing_dev_info = { + .name = "default", .ra_pages = VM_MAX_READAHEAD * 1024 / PAGE_CACHE_SIZE, .state = 0, .capabilities = BDI_CAP_MAP_COPY, diff --git a/mm/swap_state.c b/mm/swap_state.c index 42cd38eba79f..5ae6b8b78c80 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -34,6 +34,7 @@ static const struct address_space_operations swap_aops = { }; static struct backing_dev_info swap_backing_dev_info = { + .name = "swap", .capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK | BDI_CAP_SWAP_BACKED, .unplug_io_fn = swap_unplug_io_fn, }; -- cgit v1.2.3 From 500b067c5e6ceea49cf280a02597b1169320e08c Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 9 Sep 2009 09:10:25 +0200 Subject: writeback: check for registered bdi in flusher add and inode dirty Also a debugging aid. We want to catch dirty inodes being added to backing devices that don't do writeback. Signed-off-by: Jens Axboe --- fs/fs-writeback.c | 8 ++++++++ include/linux/backing-dev.h | 1 + mm/backing-dev.c | 7 +++++++ 3 files changed, 16 insertions(+) (limited to 'include/linux/backing-dev.h') diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 2e601ce581c9..da86ef58e427 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -1046,6 +1046,14 @@ void __mark_inode_dirty(struct inode *inode, int flags) */ if (!was_dirty) { struct bdi_writeback *wb = &inode_to_bdi(inode)->wb; + struct backing_dev_info *bdi = wb->bdi; + + if (bdi_cap_writeback_dirty(bdi) && + !test_bit(BDI_registered, &bdi->state)) { + WARN_ON(1); + printk(KERN_ERR "bdi-%s not registered\n", + bdi->name); + } inode->dirtied_when = jiffies; list_move(&inode->i_list, &wb->b_dirty); diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 2f218b7cb063..f169bcb90b58 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -29,6 +29,7 @@ enum bdi_state { BDI_wb_alloc, /* Default embedded wb allocated */ BDI_async_congested, /* The async (write) queue is getting full */ BDI_sync_congested, /* The sync queue is getting full */ + BDI_registered, /* bdi_register() was done */ BDI_unused, /* Available bits start here */ }; diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 5cb32c5b93d8..d3ca0dac1111 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -465,6 +465,12 @@ void static bdi_add_default_flusher_task(struct backing_dev_info *bdi) if (!bdi_cap_writeback_dirty(bdi)) return; + if (WARN_ON(!test_bit(BDI_registered, &bdi->state))) { + printk(KERN_ERR "bdi %p/%s is not registered!\n", + bdi, bdi->name); + return; + } + /* * Check with the helper whether to proceed adding a task. Will only * abort if we two or more simultanous calls to @@ -528,6 +534,7 @@ int bdi_register(struct backing_dev_info *bdi, struct device *parent, } bdi_debug_register(bdi, dev_name(dev)); + set_bit(BDI_registered, &bdi->state); exit: return ret; } -- cgit v1.2.3 From cfc4ba5365449cb6b5c9f68d755a142f17da1e47 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 14 Sep 2009 13:12:40 +0200 Subject: writeback: use RCU to protect bdi_list Now that bdi_writeback_all() no longer handles integrity writeback, it doesn't have to block anymore. This means that we can switch bdi_list reader side protection to RCU. Signed-off-by: Jens Axboe --- fs/fs-writeback.c | 6 ++-- include/linux/backing-dev.h | 1 + mm/backing-dev.c | 76 ++++++++++++++++++++++++++++++++------------- mm/page-writeback.c | 8 ++--- 4 files changed, 63 insertions(+), 28 deletions(-) (limited to 'include/linux/backing-dev.h') diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 14f06b459197..f8cd7a97f5b7 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -868,16 +868,16 @@ static void bdi_writeback_all(struct writeback_control *wbc) WARN_ON(wbc->sync_mode == WB_SYNC_ALL); - spin_lock(&bdi_lock); + rcu_read_lock(); - list_for_each_entry(bdi, &bdi_list, bdi_list) { + list_for_each_entry_rcu(bdi, &bdi_list, bdi_list) { if (!bdi_has_dirty_io(bdi)) continue; bdi_alloc_queue_work(bdi, wbc); } - spin_unlock(&bdi_lock); + rcu_read_unlock(); } /* diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index f169bcb90b58..859e797f4576 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -59,6 +59,7 @@ struct bdi_writeback { struct backing_dev_info { struct list_head bdi_list; + struct rcu_head rcu_head; 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 */ diff --git a/mm/backing-dev.c b/mm/backing-dev.c index d3ca0dac1111..fd93566345b6 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -26,6 +26,12 @@ struct backing_dev_info default_backing_dev_info = { EXPORT_SYMBOL_GPL(default_backing_dev_info); static struct class *bdi_class; + +/* + * bdi_lock protects updates to bdi_list and bdi_pending_list, as well as + * reader side protection for bdi_pending_list. bdi_list has RCU reader side + * locking. + */ DEFINE_SPINLOCK(bdi_lock); LIST_HEAD(bdi_list); LIST_HEAD(bdi_pending_list); @@ -284,9 +290,9 @@ static int bdi_start_fn(void *ptr) /* * Add us to the active bdi_list */ - spin_lock(&bdi_lock); - list_add(&bdi->bdi_list, &bdi_list); - spin_unlock(&bdi_lock); + spin_lock_bh(&bdi_lock); + list_add_rcu(&bdi->bdi_list, &bdi_list); + spin_unlock_bh(&bdi_lock); bdi_task_init(bdi, wb); @@ -389,7 +395,7 @@ static int bdi_forker_task(void *ptr) if (wb_has_dirty_io(me) || !list_empty(&me->bdi->work_list)) wb_do_writeback(me, 0); - spin_lock(&bdi_lock); + spin_lock_bh(&bdi_lock); /* * Check if any existing bdi's have dirty data without @@ -410,7 +416,7 @@ static int bdi_forker_task(void *ptr) if (list_empty(&bdi_pending_list)) { unsigned long wait; - spin_unlock(&bdi_lock); + spin_unlock_bh(&bdi_lock); wait = msecs_to_jiffies(dirty_writeback_interval * 10); schedule_timeout(wait); try_to_freeze(); @@ -426,7 +432,7 @@ static int bdi_forker_task(void *ptr) bdi = list_entry(bdi_pending_list.next, struct backing_dev_info, bdi_list); list_del_init(&bdi->bdi_list); - spin_unlock(&bdi_lock); + spin_unlock_bh(&bdi_lock); wb = &bdi->wb; wb->task = kthread_run(bdi_start_fn, wb, "flush-%s", @@ -445,9 +451,9 @@ static int bdi_forker_task(void *ptr) * a chance to flush other bdi's to free * memory. */ - spin_lock(&bdi_lock); + spin_lock_bh(&bdi_lock); list_add_tail(&bdi->bdi_list, &bdi_pending_list); - spin_unlock(&bdi_lock); + spin_unlock_bh(&bdi_lock); bdi_flush_io(bdi); } @@ -456,6 +462,24 @@ static int bdi_forker_task(void *ptr) return 0; } +static void bdi_add_to_pending(struct rcu_head *head) +{ + struct backing_dev_info *bdi; + + bdi = container_of(head, struct backing_dev_info, rcu_head); + INIT_LIST_HEAD(&bdi->bdi_list); + + spin_lock(&bdi_lock); + list_add_tail(&bdi->bdi_list, &bdi_pending_list); + spin_unlock(&bdi_lock); + + /* + * 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); +} + /* * Add the default flusher task that gets created for any bdi * that has dirty data pending writeout @@ -478,16 +502,29 @@ void static bdi_add_default_flusher_task(struct backing_dev_info *bdi) * waiting for previous additions to finish. */ if (!test_and_set_bit(BDI_pending, &bdi->state)) { - list_move_tail(&bdi->bdi_list, &bdi_pending_list); + list_del_rcu(&bdi->bdi_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 + * We must wait for the current RCU period to end before + * moving to the pending list. So schedule that operation + * from an RCU callback. */ - wake_up_process(default_backing_dev_info.wb.task); + call_rcu(&bdi->rcu_head, bdi_add_to_pending); } } +/* + * Remove bdi from bdi_list, and ensure that it is no longer visible + */ +static void bdi_remove_from_list(struct backing_dev_info *bdi) +{ + spin_lock_bh(&bdi_lock); + list_del_rcu(&bdi->bdi_list); + spin_unlock_bh(&bdi_lock); + + synchronize_rcu(); +} + int bdi_register(struct backing_dev_info *bdi, struct device *parent, const char *fmt, ...) { @@ -506,9 +543,9 @@ int bdi_register(struct backing_dev_info *bdi, struct device *parent, goto exit; } - spin_lock(&bdi_lock); - list_add_tail(&bdi->bdi_list, &bdi_list); - spin_unlock(&bdi_lock); + spin_lock_bh(&bdi_lock); + list_add_tail_rcu(&bdi->bdi_list, &bdi_list); + spin_unlock_bh(&bdi_lock); bdi->dev = dev; @@ -526,9 +563,7 @@ int bdi_register(struct backing_dev_info *bdi, struct device *parent, wb->task = NULL; ret = -ENOMEM; - spin_lock(&bdi_lock); - list_del(&bdi->bdi_list); - spin_unlock(&bdi_lock); + bdi_remove_from_list(bdi); goto exit; } } @@ -565,9 +600,7 @@ static void bdi_wb_shutdown(struct backing_dev_info *bdi) /* * Make sure nobody finds us on the bdi_list anymore */ - spin_lock(&bdi_lock); - list_del(&bdi->bdi_list); - spin_unlock(&bdi_lock); + bdi_remove_from_list(bdi); /* * Finally, kill the kernel threads. We don't need to be RCU @@ -599,6 +632,7 @@ int bdi_init(struct backing_dev_info *bdi) bdi->max_ratio = 100; bdi->max_prop_frac = PROP_FRAC_BASE; spin_lock_init(&bdi->wb_lock); + INIT_RCU_HEAD(&bdi->rcu_head); INIT_LIST_HEAD(&bdi->bdi_list); INIT_LIST_HEAD(&bdi->wb_list); INIT_LIST_HEAD(&bdi->work_list); diff --git a/mm/page-writeback.c b/mm/page-writeback.c index abc648f5de00..12c3d843ce93 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -315,7 +315,7 @@ int bdi_set_min_ratio(struct backing_dev_info *bdi, unsigned int min_ratio) { int ret = 0; - spin_lock(&bdi_lock); + spin_lock_bh(&bdi_lock); if (min_ratio > bdi->max_ratio) { ret = -EINVAL; } else { @@ -327,7 +327,7 @@ int bdi_set_min_ratio(struct backing_dev_info *bdi, unsigned int min_ratio) ret = -EINVAL; } } - spin_unlock(&bdi_lock); + spin_unlock_bh(&bdi_lock); return ret; } @@ -339,14 +339,14 @@ int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned max_ratio) if (max_ratio > 100) return -EINVAL; - spin_lock(&bdi_lock); + spin_lock_bh(&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(&bdi_lock); + spin_unlock_bh(&bdi_lock); return ret; } -- cgit v1.2.3 From b6e51316daede0633e9274e1e30391cfa4747877 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 16 Sep 2009 15:13:54 +0200 Subject: writeback: separate starting of sync vs opportunistic writeback bdi_start_writeback() is currently split into two paths, one for WB_SYNC_NONE and one for WB_SYNC_ALL. Add bdi_sync_writeback() for WB_SYNC_ALL writeback and let bdi_start_writeback() handle only WB_SYNC_NONE. Push down the writeback_control allocation and only accept the parameters that make sense for each function. This cleans up the API considerably. Signed-off-by: Jens Axboe --- fs/fs-writeback.c | 132 ++++++++++++++++++++++---------------------- fs/ubifs/budget.c | 20 +------ include/linux/backing-dev.h | 2 +- include/linux/writeback.h | 4 +- mm/page-writeback.c | 12 +--- 5 files changed, 75 insertions(+), 95 deletions(-) (limited to 'include/linux/backing-dev.h') diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 59b3ee63b624..5887328b5a06 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -74,14 +74,10 @@ static inline bool bdi_work_on_stack(struct bdi_work *work) } static inline void bdi_work_init(struct bdi_work *work, - struct writeback_control *wbc) + struct wb_writeback_args *args) { INIT_RCU_HEAD(&work->rcu_head); - work->args.sb = wbc->sb; - work->args.nr_pages = wbc->nr_to_write; - work->args.sync_mode = wbc->sync_mode; - work->args.range_cyclic = wbc->range_cyclic; - work->args.for_kupdate = 0; + work->args = *args; work->state = WS_USED; } @@ -194,7 +190,7 @@ static void bdi_wait_on_work_clear(struct bdi_work *work) } static void bdi_alloc_queue_work(struct backing_dev_info *bdi, - struct writeback_control *wbc) + struct wb_writeback_args *args) { struct bdi_work *work; @@ -204,7 +200,7 @@ static void bdi_alloc_queue_work(struct backing_dev_info *bdi, */ work = kmalloc(sizeof(*work), GFP_ATOMIC); if (work) { - bdi_work_init(work, wbc); + bdi_work_init(work, args); bdi_queue_work(bdi, work); } else { struct bdi_writeback *wb = &bdi->wb; @@ -214,24 +210,54 @@ static void bdi_alloc_queue_work(struct backing_dev_info *bdi, } } -void bdi_start_writeback(struct writeback_control *wbc) +/** + * bdi_sync_writeback - start and wait for writeback + * @bdi: the backing device to write from + * @sb: write inodes from this super_block + * + * Description: + * This does WB_SYNC_ALL data integrity writeback and waits for the + * IO to complete. Callers must hold the sb s_umount semaphore for + * reading, to avoid having the super disappear before we are done. + */ +static void bdi_sync_writeback(struct backing_dev_info *bdi, + struct super_block *sb) { - /* - * WB_SYNC_NONE is opportunistic writeback. If this allocation fails, - * bdi_queue_work() will wake up the thread and flush old data. This - * should ensure some amount of progress in freeing memory. - */ - if (wbc->sync_mode != WB_SYNC_ALL) - bdi_alloc_queue_work(wbc->bdi, wbc); - else { - struct bdi_work work; + struct wb_writeback_args args = { + .sb = sb, + .sync_mode = WB_SYNC_ALL, + .nr_pages = LONG_MAX, + .range_cyclic = 0, + }; + struct bdi_work work; - bdi_work_init(&work, wbc); - work.state |= WS_ONSTACK; + bdi_work_init(&work, &args); + work.state |= WS_ONSTACK; - bdi_queue_work(wbc->bdi, &work); - bdi_wait_on_work_clear(&work); - } + bdi_queue_work(bdi, &work); + bdi_wait_on_work_clear(&work); +} + +/** + * bdi_start_writeback - start writeback + * @bdi: the backing device to write from + * @nr_pages: the number of pages to write + * + * Description: + * This does WB_SYNC_NONE opportunistic writeback. The IO is only + * started when this function returns, we make no guarentees on + * completion. Caller need not hold sb s_umount semaphore. + * + */ +void bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages) +{ + struct wb_writeback_args args = { + .sync_mode = WB_SYNC_NONE, + .nr_pages = nr_pages, + .range_cyclic = 1, + }; + + bdi_alloc_queue_work(bdi, &args); } /* @@ -863,23 +889,25 @@ int bdi_writeback_task(struct bdi_writeback *wb) } /* - * Schedule writeback for all backing devices. Can only be used for - * WB_SYNC_NONE writeback, WB_SYNC_ALL should use bdi_start_writeback() - * and pass in the superblock. + * Schedule writeback for all backing devices. This does WB_SYNC_NONE + * writeback, for integrity writeback see bdi_sync_writeback(). */ -static void bdi_writeback_all(struct writeback_control *wbc) +static void bdi_writeback_all(struct super_block *sb, long nr_pages) { + struct wb_writeback_args args = { + .sb = sb, + .nr_pages = nr_pages, + .sync_mode = WB_SYNC_NONE, + }; struct backing_dev_info *bdi; - WARN_ON(wbc->sync_mode == WB_SYNC_ALL); - rcu_read_lock(); list_for_each_entry_rcu(bdi, &bdi_list, bdi_list) { if (!bdi_has_dirty_io(bdi)) continue; - bdi_alloc_queue_work(bdi, wbc); + bdi_alloc_queue_work(bdi, &args); } rcu_read_unlock(); @@ -891,17 +919,10 @@ static void bdi_writeback_all(struct writeback_control *wbc) */ 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); + bdi_writeback_all(NULL, nr_pages); } static noinline void block_dump___mark_inode_dirty(struct inode *inode) @@ -1048,7 +1069,7 @@ EXPORT_SYMBOL(__mark_inode_dirty); * 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) +static void wait_sb_inodes(struct super_block *sb) { struct inode *inode, *old_inode = NULL; @@ -1056,7 +1077,7 @@ static void wait_sb_inodes(struct writeback_control *wbc) * 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)); + WARN_ON(!rwsem_is_locked(&sb->s_umount)); spin_lock(&inode_lock); @@ -1067,7 +1088,7 @@ static void wait_sb_inodes(struct writeback_control *wbc) * 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) { + list_for_each_entry(inode, &sb->s_inodes, i_sb_list) { struct address_space *mapping; if (inode->i_state & (I_FREEING|I_CLEAR|I_WILL_FREE|I_NEW)) @@ -1107,14 +1128,8 @@ static void wait_sb_inodes(struct writeback_control *wbc) * for IO completion of submitted IO. The number of pages submitted is * returned. */ -long writeback_inodes_sb(struct super_block *sb) +void 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, - }; unsigned long nr_dirty = global_page_state(NR_FILE_DIRTY); unsigned long nr_unstable = global_page_state(NR_UNSTABLE_NFS); long nr_to_write; @@ -1122,9 +1137,7 @@ long writeback_inodes_sb(struct super_block *sb) nr_to_write = nr_dirty + nr_unstable + (inodes_stat.nr_inodes - inodes_stat.nr_unused); - wbc.nr_to_write = nr_to_write; - bdi_writeback_all(&wbc); - return nr_to_write - wbc.nr_to_write; + bdi_writeback_all(sb, nr_to_write); } EXPORT_SYMBOL(writeback_inodes_sb); @@ -1135,21 +1148,10 @@ EXPORT_SYMBOL(writeback_inodes_sb); * 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) +void sync_inodes_sb(struct super_block *sb) { - struct writeback_control wbc = { - .sb = sb, - .bdi = sb->s_bdi, - .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; - bdi_start_writeback(&wbc); - wait_sb_inodes(&wbc); - return nr_to_write - wbc.nr_to_write; + bdi_sync_writeback(sb->s_bdi, sb); + wait_sb_inodes(sb); } EXPORT_SYMBOL(sync_inodes_sb); diff --git a/fs/ubifs/budget.c b/fs/ubifs/budget.c index 1c8991b0db13..ee1ce68fd98b 100644 --- a/fs/ubifs/budget.c +++ b/fs/ubifs/budget.c @@ -54,29 +54,15 @@ * @nr_to_write: how many dirty pages to write-back * * This function shrinks UBIFS liability by means of writing back some amount - * of dirty inodes and their pages. Returns the amount of pages which were - * written back. The returned value does not include dirty inodes which were - * synchronized. + * of dirty inodes and their pages. * * Note, this function synchronizes even VFS inodes which are locked * (@i_mutex) by the caller of the budgeting function, because write-back does * not touch @i_mutex. */ -static int shrink_liability(struct ubifs_info *c, int nr_to_write) +static void shrink_liability(struct ubifs_info *c, int nr_to_write) { - int nr_written; - - 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). - */ - nr_written = sync_inodes_sb(c->vfs_sb); - } - - dbg_budg("%d pages were written back", nr_written); - return nr_written; + writeback_inodes_sb(c->vfs_sb); } /** diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 859e797f4576..0ee33c2e6129 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -101,7 +101,7 @@ 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); +void bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages); int bdi_writeback_task(struct bdi_writeback *wb); int bdi_has_dirty_io(struct backing_dev_info *bdi); diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 48a054e2b716..75cf58666ff9 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -68,8 +68,8 @@ struct writeback_control { */ struct bdi_writeback; int inode_wait(void *); -long writeback_inodes_sb(struct super_block *); -long sync_inodes_sb(struct super_block *); +void writeback_inodes_sb(struct super_block *); +void 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); diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 12c3d843ce93..1eea4fa0d410 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -582,16 +582,8 @@ static void balance_dirty_pages(struct address_space *mapping) if ((laptop_mode && pages_written) || (!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); - } + > background_thresh))) + bdi_start_writeback(bdi, nr_writeback); } void set_page_dirty_balance(struct page *page, int page_mkwrite) -- cgit v1.2.3 From a72bfd4dea053bb8e2233902c3f1893ef5485802 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Sat, 26 Sep 2009 00:07:46 +0200 Subject: writeback: pass in super_block to bdi_start_writeback() Sometimes we only want to write pages from a specific super_block, so allow that to be passed in. This fixes a problem with commit 56a131dcf7ed36c3c6e36bea448b674ea85ed5bb causing writeback on all super_blocks on a bdi, where we only really want to sync a specific sb from writeback_inodes_sb(). Signed-off-by: Jens Axboe --- fs/fs-writeback.c | 6 ++++-- include/linux/backing-dev.h | 3 ++- mm/page-writeback.c | 2 +- 3 files changed, 7 insertions(+), 4 deletions(-) (limited to 'include/linux/backing-dev.h') diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index fb61178c86e3..9d5360c4c2af 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -250,9 +250,11 @@ static void bdi_sync_writeback(struct backing_dev_info *bdi, * completion. Caller need not hold sb s_umount semaphore. * */ -void bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages) +void bdi_start_writeback(struct backing_dev_info *bdi, struct super_block *sb, + long nr_pages) { struct wb_writeback_args args = { + .sb = sb, .sync_mode = WB_SYNC_NONE, .nr_pages = nr_pages, .range_cyclic = 1, @@ -1206,7 +1208,7 @@ void writeback_inodes_sb(struct super_block *sb) nr_to_write = nr_dirty + nr_unstable + (inodes_stat.nr_inodes - inodes_stat.nr_unused); - bdi_start_writeback(sb->s_bdi, nr_to_write); + bdi_start_writeback(sb->s_bdi, sb, nr_to_write); } EXPORT_SYMBOL(writeback_inodes_sb); diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 0ee33c2e6129..b449e738533a 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -101,7 +101,8 @@ 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 backing_dev_info *bdi, long nr_pages); +void bdi_start_writeback(struct backing_dev_info *bdi, struct super_block *sb, + long nr_pages); int bdi_writeback_task(struct bdi_writeback *wb); int bdi_has_dirty_io(struct backing_dev_info *bdi); diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 69b5fbabc8bd..a3b14090b1fb 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -596,7 +596,7 @@ static void balance_dirty_pages(struct address_space *mapping, (!laptop_mode && ((global_page_state(NR_FILE_DIRTY) + global_page_state(NR_UNSTABLE_NFS)) > background_thresh))) - bdi_start_writeback(bdi, 0); + bdi_start_writeback(bdi, NULL, 0); } void set_page_dirty_balance(struct page *page, int page_mkwrite) -- cgit v1.2.3 From b9d128f1088ea5245109dfc9bbceb128b6371a77 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 29 Oct 2009 13:59:26 +0100 Subject: block: move bdi/address_space unplug functions to backing-dev.h There's nothing block related about them, the backing device is used by things like NFS etc as well. This gets rid of the need to protect such calls by CONFIG_BLOCK. Signed-off-by: Jens Axboe --- fs/aio.c | 1 + include/linux/backing-dev.h | 13 +++++++++++++ include/linux/blkdev.h | 13 ------------- 3 files changed, 14 insertions(+), 13 deletions(-) (limited to 'include/linux/backing-dev.h') diff --git a/fs/aio.c b/fs/aio.c index cf0bef428f88..c30dfc006108 100644 --- a/fs/aio.c +++ b/fs/aio.c @@ -15,6 +15,7 @@ #include #include #include +#include #include #define DEBUG 0 diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index b449e738533a..fcbc26af00e4 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -331,4 +331,17 @@ static inline int bdi_sched_wait(void *word) return 0; } +static inline void blk_run_backing_dev(struct backing_dev_info *bdi, + struct page *page) +{ + if (bdi && bdi->unplug_io_fn) + bdi->unplug_io_fn(bdi, page); +} + +static inline void blk_run_address_space(struct address_space *mapping) +{ + if (mapping) + blk_run_backing_dev(mapping->backing_dev_info, NULL); +} + #endif /* _LINUX_BACKING_DEV_H */ diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 221cecd86bd3..39c601f783a0 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -823,19 +823,6 @@ static inline struct request_queue *bdev_get_queue(struct block_device *bdev) return bdev->bd_disk->queue; } -static inline void blk_run_backing_dev(struct backing_dev_info *bdi, - struct page *page) -{ - if (bdi && bdi->unplug_io_fn) - bdi->unplug_io_fn(bdi, page); -} - -static inline void blk_run_address_space(struct address_space *mapping) -{ - if (mapping) - blk_run_backing_dev(mapping->backing_dev_info, NULL); -} - /* * blk_rq_pos() : the current sector * blk_rq_bytes() : bytes left in the entire request -- cgit v1.2.3 From 31373d09da5b7fe21fe6f781e92bd534a3495f00 Mon Sep 17 00:00:00 2001 From: Matthew Garrett Date: Tue, 6 Apr 2010 14:25:14 +0200 Subject: laptop-mode: Make flushes per-device One of the features of laptop-mode is that it forces a writeout of dirty pages if something else triggers a physical read or write from a device. The current implementation flushes pages on all devices, rather than only the one that triggered the flush. This patch alters the behaviour so that only the recently accessed block device is flushed, preventing other disks being spun up for no terribly good reason. Signed-off-by: Matthew Garrett Signed-off-by: Jens Axboe --- block/blk-core.c | 5 ++++- include/linux/backing-dev.h | 3 +++ include/linux/writeback.h | 4 +++- mm/page-writeback.c | 39 ++++++++++++++++++++------------------- 4 files changed, 30 insertions(+), 21 deletions(-) (limited to 'include/linux/backing-dev.h') diff --git a/block/blk-core.c b/block/blk-core.c index 1d94f15d7f0d..4b1b29ef2cb0 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -451,6 +451,7 @@ void blk_cleanup_queue(struct request_queue *q) */ blk_sync_queue(q); + del_timer_sync(&q->backing_dev_info.laptop_mode_wb_timer); mutex_lock(&q->sysfs_lock); queue_flag_set_unlocked(QUEUE_FLAG_DEAD, q); mutex_unlock(&q->sysfs_lock); @@ -511,6 +512,8 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id) return NULL; } + setup_timer(&q->backing_dev_info.laptop_mode_wb_timer, + laptop_mode_timer_fn, (unsigned long) q); init_timer(&q->unplug_timer); setup_timer(&q->timeout, blk_rq_timed_out_timer, (unsigned long) q); INIT_LIST_HEAD(&q->timeout_list); @@ -2101,7 +2104,7 @@ static void blk_finish_request(struct request *req, int error) BUG_ON(blk_queued_rq(req)); if (unlikely(laptop_mode) && blk_fs_request(req)) - laptop_io_completion(); + laptop_io_completion(&req->q->backing_dev_info); blk_delete_timer(req); diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index fcbc26af00e4..2742e1adfc30 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -14,6 +14,7 @@ #include #include #include +#include #include #include @@ -88,6 +89,8 @@ struct backing_dev_info { struct device *dev; + struct timer_list laptop_mode_wb_timer; + #ifdef CONFIG_DEBUG_FS struct dentry *debug_dir; struct dentry *debug_stats; diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 36520ded3e06..eb38a2c645f6 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -96,8 +96,10 @@ static inline void inode_sync_wait(struct inode *inode) /* * mm/page-writeback.c */ -void laptop_io_completion(void); +void laptop_io_completion(struct backing_dev_info *info); void laptop_sync_completion(void); +void laptop_mode_sync(struct work_struct *work); +void laptop_mode_timer_fn(unsigned long data); void throttle_vm_writeout(gfp_t gfp_mask); /* These are exported to sysctl. */ diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 0b19943ecf8b..d0f2b3765f8d 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -683,10 +683,6 @@ void throttle_vm_writeout(gfp_t gfp_mask) } } -static void laptop_timer_fn(unsigned long unused); - -static DEFINE_TIMER(laptop_mode_wb_timer, laptop_timer_fn, 0, 0); - /* * sysctl handler for /proc/sys/vm/dirty_writeback_centisecs */ @@ -697,21 +693,19 @@ int dirty_writeback_centisecs_handler(ctl_table *table, int write, return 0; } -static void do_laptop_sync(struct work_struct *work) +void laptop_mode_timer_fn(unsigned long data) { - wakeup_flusher_threads(0); - kfree(work); -} + struct request_queue *q = (struct request_queue *)data; + int nr_pages = global_page_state(NR_FILE_DIRTY) + + global_page_state(NR_UNSTABLE_NFS); -static void laptop_timer_fn(unsigned long unused) -{ - struct work_struct *work; + /* + * We want to write everything out, not just down to the dirty + * threshold + */ - work = kmalloc(sizeof(*work), GFP_ATOMIC); - if (work) { - INIT_WORK(work, do_laptop_sync); - schedule_work(work); - } + if (bdi_has_dirty_io(&q->backing_dev_info)) + bdi_start_writeback(&q->backing_dev_info, NULL, nr_pages); } /* @@ -719,9 +713,9 @@ static void laptop_timer_fn(unsigned long unused) * of all dirty data a few seconds from now. If the flush is already scheduled * then push it back - the user is still using the disk. */ -void laptop_io_completion(void) +void laptop_io_completion(struct backing_dev_info *info) { - mod_timer(&laptop_mode_wb_timer, jiffies + laptop_mode); + mod_timer(&info->laptop_mode_wb_timer, jiffies + laptop_mode); } /* @@ -731,7 +725,14 @@ void laptop_io_completion(void) */ void laptop_sync_completion(void) { - del_timer(&laptop_mode_wb_timer); + struct backing_dev_info *bdi; + + rcu_read_lock(); + + list_for_each_entry_rcu(bdi, &bdi_list, bdi_list) + del_timer(&bdi->laptop_mode_wb_timer); + + rcu_read_unlock(); } /* -- cgit v1.2.3 From c3c532061e46156e8aab1268f38d66cfb63aeb2d Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 22 Apr 2010 11:37:01 +0200 Subject: bdi: add helper function for doing init and register of a bdi for a file system Pretty trivial helper, just sets up the bdi and registers it. An atomic sequence count is used to ensure that the registered sysfs names are unique. Signed-off-by: Jens Axboe --- include/linux/backing-dev.h | 1 + mm/backing-dev.c | 29 +++++++++++++++++++++++++++++ 2 files changed, 30 insertions(+) (limited to 'include/linux/backing-dev.h') diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index fcbc26af00e4..e19c677f219c 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -101,6 +101,7 @@ 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); +int bdi_setup_and_register(struct backing_dev_info *, char *, unsigned int); void bdi_start_writeback(struct backing_dev_info *bdi, struct super_block *sb, long nr_pages); int bdi_writeback_task(struct bdi_writeback *wb); diff --git a/mm/backing-dev.c b/mm/backing-dev.c index f13e067e1467..dbda4707f593 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -11,6 +11,8 @@ #include #include +static atomic_long_t bdi_seq = ATOMIC_LONG_INIT(0); + void default_unplug_io_fn(struct backing_dev_info *bdi, struct page *page) { } @@ -715,6 +717,33 @@ void bdi_destroy(struct backing_dev_info *bdi) } EXPORT_SYMBOL(bdi_destroy); +/* + * For use from filesystems to quickly init and register a bdi associated + * with dirty writeback + */ +int bdi_setup_and_register(struct backing_dev_info *bdi, char *name, + unsigned int cap) +{ + char tmp[32]; + int err; + + bdi->name = name; + bdi->capabilities = cap; + err = bdi_init(bdi); + if (err) + return err; + + sprintf(tmp, "%.28s%s", name, "-%d"); + err = bdi_register(bdi, NULL, tmp, atomic_long_inc_return(&bdi_seq)); + if (err) { + bdi_destroy(bdi); + return err; + } + + return 0; +} +EXPORT_SYMBOL(bdi_setup_and_register); + static wait_queue_head_t congestion_wqh[2] = { __WAIT_QUEUE_HEAD_INITIALIZER(congestion_wqh[0]), __WAIT_QUEUE_HEAD_INITIALIZER(congestion_wqh[1]) -- cgit v1.2.3 From 5129a469a91a91427334c40e29e64c6d0ab68caf Mon Sep 17 00:00:00 2001 From: Jörn Engel Date: Sun, 25 Apr 2010 08:54:42 +0200 Subject: Catch filesystems lacking s_bdi noop_backing_dev_info is used only as a flag to mark filesystems that don't have any backing store, like tmpfs, procfs, spufs, etc. Signed-off-by: Joern Engel Changed the BUG_ON() to a WARN_ON(). Note that adding dirty inodes to the noop_backing_dev_info is not legal and will not result in them being flushed, but we already catch this condition in __mark_inode_dirty() when checking for a registered bdi. Signed-off-by: Jens Axboe --- fs/super.c | 8 +++++--- fs/sync.c | 3 ++- include/linux/backing-dev.h | 1 + mm/backing-dev.c | 5 +++++ 4 files changed, 13 insertions(+), 4 deletions(-) (limited to 'include/linux/backing-dev.h') diff --git a/fs/super.c b/fs/super.c index f35ac6022109..dc72491a19f9 100644 --- a/fs/super.c +++ b/fs/super.c @@ -693,6 +693,7 @@ int set_anon_super(struct super_block *s, void *data) return -EMFILE; } s->s_dev = MKDEV(0, dev & MINORMASK); + s->s_bdi = &noop_backing_dev_info; return 0; } @@ -954,10 +955,11 @@ vfs_kern_mount(struct file_system_type *type, int flags, const char *name, void if (error < 0) goto out_free_secdata; BUG_ON(!mnt->mnt_sb); + WARN_ON(!mnt->mnt_sb->s_bdi); - error = security_sb_kern_mount(mnt->mnt_sb, flags, secdata); - if (error) - goto out_sb; + error = security_sb_kern_mount(mnt->mnt_sb, flags, secdata); + if (error) + goto out_sb; /* * filesystems should never set s_maxbytes larger than MAX_LFS_FILESIZE diff --git a/fs/sync.c b/fs/sync.c index fc5c3d75cf3c..92b228176f7c 100644 --- a/fs/sync.c +++ b/fs/sync.c @@ -14,6 +14,7 @@ #include #include #include +#include #include "internal.h" #define VALID_FLAGS (SYNC_FILE_RANGE_WAIT_BEFORE|SYNC_FILE_RANGE_WRITE| \ @@ -32,7 +33,7 @@ static int __sync_filesystem(struct super_block *sb, int wait) * This should be safe, as we require bdi backing to actually * write out data in the first place */ - if (!sb->s_bdi) + if (!sb->s_bdi || sb->s_bdi == &noop_backing_dev_info) return 0; if (sb->s_qcop && sb->s_qcop->quota_sync) diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index e19c677f219c..bd0e3c6f323f 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -247,6 +247,7 @@ int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio); #endif extern struct backing_dev_info default_backing_dev_info; +extern struct backing_dev_info noop_backing_dev_info; void default_unplug_io_fn(struct backing_dev_info *bdi, struct page *page); int writeback_in_progress(struct backing_dev_info *bdi); diff --git a/mm/backing-dev.c b/mm/backing-dev.c index dbda4707f593..707d0dc6da0f 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -27,6 +27,11 @@ struct backing_dev_info default_backing_dev_info = { }; EXPORT_SYMBOL_GPL(default_backing_dev_info); +struct backing_dev_info noop_backing_dev_info = { + .name = "noop", +}; +EXPORT_SYMBOL_GPL(noop_backing_dev_info); + static struct class *bdi_class; /* -- cgit v1.2.3 From e913fc825dc685a444cb4c1d0f9d32f372f59861 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 17 May 2010 12:55:07 +0200 Subject: writeback: fix WB_SYNC_NONE writeback from umount When umount calls sync_filesystem(), we first do a WB_SYNC_NONE writeback to kick off writeback of pending dirty inodes, then follow that up with a WB_SYNC_ALL to wait for it. Since umount already holds the sb s_umount mutex, WB_SYNC_NONE ends up doing nothing and all writeback happens as WB_SYNC_ALL. This can greatly slow down umount, since WB_SYNC_ALL writeback is a data integrity operation and thus a bigger hammer than simple WB_SYNC_NONE. For barrier aware file systems it's a lot slower. Signed-off-by: Jens Axboe --- fs/fs-writeback.c | 48 ++++++++++++++++++++++++++++++++++----------- fs/sync.c | 2 +- include/linux/backing-dev.h | 2 +- include/linux/writeback.h | 10 ++++++++++ mm/page-writeback.c | 4 ++-- 5 files changed, 51 insertions(+), 15 deletions(-) (limited to 'include/linux/backing-dev.h') diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 760dc8d0b4ff..67db89786e7d 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -45,6 +45,7 @@ struct wb_writeback_args { int for_kupdate:1; int range_cyclic:1; int for_background:1; + int sb_pinned:1; }; /* @@ -230,6 +231,11 @@ static void bdi_sync_writeback(struct backing_dev_info *bdi, .sync_mode = WB_SYNC_ALL, .nr_pages = LONG_MAX, .range_cyclic = 0, + /* + * Setting sb_pinned is not necessary for WB_SYNC_ALL, but + * lets make it explicitly clear. + */ + .sb_pinned = 1, }; struct bdi_work work; @@ -245,21 +251,23 @@ static void bdi_sync_writeback(struct backing_dev_info *bdi, * @bdi: the backing device to write from * @sb: write inodes from this super_block * @nr_pages: the number of pages to write + * @sb_locked: caller already holds sb umount sem. * * Description: * This does WB_SYNC_NONE opportunistic writeback. The IO is only * started when this function returns, we make no guarentees on - * completion. Caller need not hold sb s_umount semaphore. + * completion. Caller specifies whether sb umount sem is held already or not. * */ void bdi_start_writeback(struct backing_dev_info *bdi, struct super_block *sb, - long nr_pages) + long nr_pages, int sb_locked) { struct wb_writeback_args args = { .sb = sb, .sync_mode = WB_SYNC_NONE, .nr_pages = nr_pages, .range_cyclic = 1, + .sb_pinned = sb_locked, }; /* @@ -577,7 +585,7 @@ static enum sb_pin_state pin_sb_for_writeback(struct writeback_control *wbc, /* * Caller must already hold the ref for this */ - if (wbc->sync_mode == WB_SYNC_ALL) { + if (wbc->sync_mode == WB_SYNC_ALL || wbc->sb_pinned) { WARN_ON(!rwsem_is_locked(&sb->s_umount)); return SB_NOT_PINNED; } @@ -751,6 +759,7 @@ static long wb_writeback(struct bdi_writeback *wb, .for_kupdate = args->for_kupdate, .for_background = args->for_background, .range_cyclic = args->range_cyclic, + .sb_pinned = args->sb_pinned, }; unsigned long oldest_jif; long wrote = 0; @@ -1193,6 +1202,18 @@ static void wait_sb_inodes(struct super_block *sb) iput(old_inode); } +static void __writeback_inodes_sb(struct super_block *sb, int sb_locked) +{ + unsigned long nr_dirty = global_page_state(NR_FILE_DIRTY); + unsigned long nr_unstable = global_page_state(NR_UNSTABLE_NFS); + long nr_to_write; + + nr_to_write = nr_dirty + nr_unstable + + (inodes_stat.nr_inodes - inodes_stat.nr_unused); + + bdi_start_writeback(sb->s_bdi, sb, nr_to_write, sb_locked); +} + /** * writeback_inodes_sb - writeback dirty inodes from given super_block * @sb: the superblock @@ -1204,17 +1225,22 @@ static void wait_sb_inodes(struct super_block *sb) */ void writeback_inodes_sb(struct super_block *sb) { - unsigned long nr_dirty = global_page_state(NR_FILE_DIRTY); - unsigned long nr_unstable = global_page_state(NR_UNSTABLE_NFS); - long nr_to_write; - - nr_to_write = nr_dirty + nr_unstable + - (inodes_stat.nr_inodes - inodes_stat.nr_unused); - - bdi_start_writeback(sb->s_bdi, sb, nr_to_write); + __writeback_inodes_sb(sb, 0); } EXPORT_SYMBOL(writeback_inodes_sb); +/** + * writeback_inodes_sb_locked - writeback dirty inodes from given super_block + * @sb: the superblock + * + * Like writeback_inodes_sb(), except the caller already holds the + * sb umount sem. + */ +void writeback_inodes_sb_locked(struct super_block *sb) +{ + __writeback_inodes_sb(sb, 1); +} + /** * writeback_inodes_sb_if_idle - start writeback if none underway * @sb: the superblock diff --git a/fs/sync.c b/fs/sync.c index 92b228176f7c..de6a44192832 100644 --- a/fs/sync.c +++ b/fs/sync.c @@ -42,7 +42,7 @@ static int __sync_filesystem(struct super_block *sb, int wait) if (wait) sync_inodes_sb(sb); else - writeback_inodes_sb(sb); + writeback_inodes_sb_locked(sb); if (sb->s_op->sync_fs) sb->s_op->sync_fs(sb, wait); diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 7534979d83bd..ff8bac63213f 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -106,7 +106,7 @@ int bdi_register_dev(struct backing_dev_info *bdi, dev_t dev); void bdi_unregister(struct backing_dev_info *bdi); int bdi_setup_and_register(struct backing_dev_info *, char *, unsigned int); void bdi_start_writeback(struct backing_dev_info *bdi, struct super_block *sb, - long nr_pages); + long nr_pages, int sb_locked); int bdi_writeback_task(struct bdi_writeback *wb); int bdi_has_dirty_io(struct backing_dev_info *bdi); diff --git a/include/linux/writeback.h b/include/linux/writeback.h index eb38a2c645f6..47e1c686cb02 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -65,6 +65,15 @@ struct writeback_control { * so we use a single control to update them */ unsigned no_nrwrite_index_update:1; + + /* + * For WB_SYNC_ALL, the sb must always be pinned. For WB_SYNC_NONE, + * the writeback code will pin the sb for the caller. However, + * for eg umount, the caller does WB_SYNC_NONE but already has + * the sb pinned. If the below is set, caller already has the + * sb pinned. + */ + unsigned sb_pinned:1; }; /* @@ -73,6 +82,7 @@ struct writeback_control { struct bdi_writeback; int inode_wait(void *); void writeback_inodes_sb(struct super_block *); +void writeback_inodes_sb_locked(struct super_block *); int writeback_inodes_sb_if_idle(struct super_block *); void sync_inodes_sb(struct super_block *); void writeback_inodes_wbc(struct writeback_control *wbc); diff --git a/mm/page-writeback.c b/mm/page-writeback.c index d0f2b3765f8d..53b2fcf2d283 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -597,7 +597,7 @@ static void balance_dirty_pages(struct address_space *mapping, (!laptop_mode && ((global_page_state(NR_FILE_DIRTY) + global_page_state(NR_UNSTABLE_NFS)) > background_thresh))) - bdi_start_writeback(bdi, NULL, 0); + bdi_start_writeback(bdi, NULL, 0, 0); } void set_page_dirty_balance(struct page *page, int page_mkwrite) @@ -705,7 +705,7 @@ void laptop_mode_timer_fn(unsigned long data) */ if (bdi_has_dirty_io(&q->backing_dev_info)) - bdi_start_writeback(&q->backing_dev_info, NULL, nr_pages); + bdi_start_writeback(&q->backing_dev_info, NULL, 0, nr_pages); } /* -- cgit v1.2.3 From 6423104b6a1e6f0c18be60e8c33f02d263331d5e Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 21 May 2010 20:00:35 +0200 Subject: writeback: fixups for !dirty_writeback_centisecs Commit 69b62d01 fixed up most of the places where we would enter busy schedule() spins when disabling the periodic background writeback. This fixes up the sb timer so that it doesn't get hammered on with the delay disabled, and ensures that it gets rearmed if needed when /proc/sys/vm/dirty_writeback_centisecs gets modified. bdi_forker_task() also needs to check for !dirty_writeback_centisecs and use schedule() appropriately, fix that up too. Signed-off-by: Jens Axboe --- include/linux/backing-dev.h | 1 + mm/backing-dev.c | 15 ++++++++++----- mm/page-writeback.c | 1 + 3 files changed, 12 insertions(+), 5 deletions(-) (limited to 'include/linux/backing-dev.h') diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index ff8bac63213f..e6e0cb5437e6 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -109,6 +109,7 @@ void bdi_start_writeback(struct backing_dev_info *bdi, struct super_block *sb, long nr_pages, int sb_locked); int bdi_writeback_task(struct bdi_writeback *wb); int bdi_has_dirty_io(struct backing_dev_info *bdi); +void bdi_arm_supers_timer(void); extern spinlock_t bdi_lock; extern struct list_head bdi_list; diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 707d0dc6da0f..660a87a22511 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -48,7 +48,6 @@ 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); @@ -252,7 +251,7 @@ static int __init default_bdi_init(void) init_timer(&sync_supers_timer); setup_timer(&sync_supers_timer, sync_supers_timer_fn, 0); - arm_supers_timer(); + bdi_arm_supers_timer(); err = bdi_init(&default_backing_dev_info); if (!err) @@ -374,10 +373,13 @@ static int bdi_sync_supers(void *unused) return 0; } -static void arm_supers_timer(void) +void bdi_arm_supers_timer(void) { unsigned long next; + if (!dirty_writeback_interval) + return; + next = msecs_to_jiffies(dirty_writeback_interval * 10) + jiffies; mod_timer(&sync_supers_timer, round_jiffies_up(next)); } @@ -385,7 +387,7 @@ static void arm_supers_timer(void) static void sync_supers_timer_fn(unsigned long unused) { wake_up_process(sync_supers_tsk); - arm_supers_timer(); + bdi_arm_supers_timer(); } static int bdi_forker_task(void *ptr) @@ -428,7 +430,10 @@ static int bdi_forker_task(void *ptr) spin_unlock_bh(&bdi_lock); wait = msecs_to_jiffies(dirty_writeback_interval * 10); - schedule_timeout(wait); + if (wait) + schedule_timeout(wait); + else + schedule(); try_to_freeze(); continue; } diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 53b2fcf2d283..0d7bbe859550 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -690,6 +690,7 @@ int dirty_writeback_centisecs_handler(ctl_table *table, int write, void __user *buffer, size_t *length, loff_t *ppos) { proc_dointvec(table, write, buffer, length, ppos); + bdi_arm_supers_timer(); return 0; } -- cgit v1.2.3 From 0e3c9a2284f5417f196e327c254d0b84c9ee8929 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 1 Jun 2010 11:08:43 +0200 Subject: Revert "writeback: fix WB_SYNC_NONE writeback from umount" This reverts commit e913fc825dc685a444cb4c1d0f9d32f372f59861. We are investigating a hang associated with the WB_SYNC_NONE changes, so revert them for now. Conflicts: fs/fs-writeback.c mm/page-writeback.c Signed-off-by: Jens Axboe --- fs/fs-writeback.c | 48 +++++++++++---------------------------------- fs/sync.c | 2 +- include/linux/backing-dev.h | 2 +- include/linux/writeback.h | 10 ---------- mm/page-writeback.c | 4 ++-- 5 files changed, 15 insertions(+), 51 deletions(-) (limited to 'include/linux/backing-dev.h') diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 6753912641b4..408a7877b79d 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -45,7 +45,6 @@ struct wb_writeback_args { unsigned int for_kupdate:1; unsigned int range_cyclic:1; unsigned int for_background:1; - unsigned int sb_pinned:1; }; /* @@ -231,11 +230,6 @@ static void bdi_sync_writeback(struct backing_dev_info *bdi, .sync_mode = WB_SYNC_ALL, .nr_pages = LONG_MAX, .range_cyclic = 0, - /* - * Setting sb_pinned is not necessary for WB_SYNC_ALL, but - * lets make it explicitly clear. - */ - .sb_pinned = 1, }; struct bdi_work work; @@ -251,23 +245,21 @@ static void bdi_sync_writeback(struct backing_dev_info *bdi, * @bdi: the backing device to write from * @sb: write inodes from this super_block * @nr_pages: the number of pages to write - * @sb_locked: caller already holds sb umount sem. * * Description: * This does WB_SYNC_NONE opportunistic writeback. The IO is only * started when this function returns, we make no guarentees on - * completion. Caller specifies whether sb umount sem is held already or not. + * completion. Caller need not hold sb s_umount semaphore. * */ void bdi_start_writeback(struct backing_dev_info *bdi, struct super_block *sb, - long nr_pages, int sb_locked) + long nr_pages) { struct wb_writeback_args args = { .sb = sb, .sync_mode = WB_SYNC_NONE, .nr_pages = nr_pages, .range_cyclic = 1, - .sb_pinned = sb_locked, }; /* @@ -592,7 +584,7 @@ static enum sb_pin_state pin_sb_for_writeback(struct writeback_control *wbc, /* * Caller must already hold the ref for this */ - if (wbc->sync_mode == WB_SYNC_ALL || wbc->sb_pinned) { + if (wbc->sync_mode == WB_SYNC_ALL) { WARN_ON(!rwsem_is_locked(&sb->s_umount)); return SB_NOT_PINNED; } @@ -766,7 +758,6 @@ static long wb_writeback(struct bdi_writeback *wb, .for_kupdate = args->for_kupdate, .for_background = args->for_background, .range_cyclic = args->range_cyclic, - .sb_pinned = args->sb_pinned, }; unsigned long oldest_jif; long wrote = 0; @@ -1214,18 +1205,6 @@ static void wait_sb_inodes(struct super_block *sb) iput(old_inode); } -static void __writeback_inodes_sb(struct super_block *sb, int sb_locked) -{ - unsigned long nr_dirty = global_page_state(NR_FILE_DIRTY); - unsigned long nr_unstable = global_page_state(NR_UNSTABLE_NFS); - long nr_to_write; - - nr_to_write = nr_dirty + nr_unstable + - (inodes_stat.nr_inodes - inodes_stat.nr_unused); - - bdi_start_writeback(sb->s_bdi, sb, nr_to_write, sb_locked); -} - /** * writeback_inodes_sb - writeback dirty inodes from given super_block * @sb: the superblock @@ -1237,21 +1216,16 @@ static void __writeback_inodes_sb(struct super_block *sb, int sb_locked) */ void writeback_inodes_sb(struct super_block *sb) { - __writeback_inodes_sb(sb, 0); -} -EXPORT_SYMBOL(writeback_inodes_sb); + unsigned long nr_dirty = global_page_state(NR_FILE_DIRTY); + unsigned long nr_unstable = global_page_state(NR_UNSTABLE_NFS); + long nr_to_write; -/** - * writeback_inodes_sb_locked - writeback dirty inodes from given super_block - * @sb: the superblock - * - * Like writeback_inodes_sb(), except the caller already holds the - * sb umount sem. - */ -void writeback_inodes_sb_locked(struct super_block *sb) -{ - __writeback_inodes_sb(sb, 1); + nr_to_write = nr_dirty + nr_unstable + + (inodes_stat.nr_inodes - inodes_stat.nr_unused); + + bdi_start_writeback(sb->s_bdi, sb, nr_to_write); } +EXPORT_SYMBOL(writeback_inodes_sb); /** * writeback_inodes_sb_if_idle - start writeback if none underway diff --git a/fs/sync.c b/fs/sync.c index e8cbd415e50a..5a537ccd2e85 100644 --- a/fs/sync.c +++ b/fs/sync.c @@ -42,7 +42,7 @@ static int __sync_filesystem(struct super_block *sb, int wait) if (wait) sync_inodes_sb(sb); else - writeback_inodes_sb_locked(sb); + writeback_inodes_sb(sb); if (sb->s_op->sync_fs) sb->s_op->sync_fs(sb, wait); diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index e6e0cb5437e6..aee5f6ce166e 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -106,7 +106,7 @@ int bdi_register_dev(struct backing_dev_info *bdi, dev_t dev); void bdi_unregister(struct backing_dev_info *bdi); int bdi_setup_and_register(struct backing_dev_info *, char *, unsigned int); void bdi_start_writeback(struct backing_dev_info *bdi, struct super_block *sb, - long nr_pages, int sb_locked); + long nr_pages); int bdi_writeback_task(struct bdi_writeback *wb); int bdi_has_dirty_io(struct backing_dev_info *bdi); void bdi_arm_supers_timer(void); diff --git a/include/linux/writeback.h b/include/linux/writeback.h index cc97d6caf2b3..f64134653a8c 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -65,15 +65,6 @@ struct writeback_control { * so we use a single control to update them */ unsigned no_nrwrite_index_update:1; - - /* - * For WB_SYNC_ALL, the sb must always be pinned. For WB_SYNC_NONE, - * the writeback code will pin the sb for the caller. However, - * for eg umount, the caller does WB_SYNC_NONE but already has - * the sb pinned. If the below is set, caller already has the - * sb pinned. - */ - unsigned sb_pinned:1; }; /* @@ -82,7 +73,6 @@ struct writeback_control { struct bdi_writeback; int inode_wait(void *); void writeback_inodes_sb(struct super_block *); -void writeback_inodes_sb_locked(struct super_block *); int writeback_inodes_sb_if_idle(struct super_block *); void sync_inodes_sb(struct super_block *); void writeback_inodes_wbc(struct writeback_control *wbc); diff --git a/mm/page-writeback.c b/mm/page-writeback.c index b289310e2c89..5fa63bdf52e4 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -597,7 +597,7 @@ static void balance_dirty_pages(struct address_space *mapping, (!laptop_mode && ((global_page_state(NR_FILE_DIRTY) + global_page_state(NR_UNSTABLE_NFS)) > background_thresh))) - bdi_start_writeback(bdi, NULL, 0, 0); + bdi_start_writeback(bdi, NULL, 0); } void set_page_dirty_balance(struct page *page, int page_mkwrite) @@ -707,7 +707,7 @@ void laptop_mode_timer_fn(unsigned long data) */ if (bdi_has_dirty_io(&q->backing_dev_info)) - bdi_start_writeback(&q->backing_dev_info, NULL, nr_pages, 0); + bdi_start_writeback(&q->backing_dev_info, NULL, nr_pages); } /* -- cgit v1.2.3 From c5444198ca210498e8ac0ba121b4cd3537aa12f7 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 8 Jun 2010 18:15:15 +0200 Subject: writeback: simplify and split bdi_start_writeback bdi_start_writeback now never gets a superblock passed, so we can just remove that case. And to further untangle the code and flatten the call stack split it into two trivial helpers for it's two callers. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- fs/fs-writeback.c | 32 ++++++++++++++++++++------------ include/linux/backing-dev.h | 4 ++-- mm/page-writeback.c | 5 ++--- 3 files changed, 24 insertions(+), 17 deletions(-) (limited to 'include/linux/backing-dev.h') diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 4fcca4f74940..0079bf59b583 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -200,7 +200,6 @@ static void bdi_queue_work_onstack(struct wb_writeback_args *args) /** * bdi_start_writeback - start writeback * @bdi: the backing device to write from - * @sb: write inodes from this super_block * @nr_pages: the number of pages to write * * Description: @@ -209,25 +208,34 @@ static void bdi_queue_work_onstack(struct wb_writeback_args *args) * completion. Caller need not hold sb s_umount semaphore. * */ -void bdi_start_writeback(struct backing_dev_info *bdi, struct super_block *sb, - long nr_pages) +void bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages) { struct wb_writeback_args args = { - .sb = sb, .sync_mode = WB_SYNC_NONE, .nr_pages = nr_pages, .range_cyclic = 1, }; - /* - * We treat @nr_pages=0 as the special case to do background writeback, - * ie. to sync pages until the background dirty threshold is reached. - */ - if (!nr_pages) { - args.nr_pages = LONG_MAX; - args.for_background = 1; - } + bdi_alloc_queue_work(bdi, &args); +} +/** + * bdi_start_background_writeback - start background writeback + * @bdi: the backing device to write from + * + * Description: + * This does WB_SYNC_NONE background writeback. The IO is only + * started when this function returns, we make no guarentees on + * completion. Caller need not hold sb s_umount semaphore. + */ +void bdi_start_background_writeback(struct backing_dev_info *bdi) +{ + struct wb_writeback_args args = { + .sync_mode = WB_SYNC_NONE, + .nr_pages = LONG_MAX, + .for_background = 1, + .range_cyclic = 1, + }; bdi_alloc_queue_work(bdi, &args); } diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index aee5f6ce166e..9ae2889096b6 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -105,8 +105,8 @@ 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); int bdi_setup_and_register(struct backing_dev_info *, char *, unsigned int); -void bdi_start_writeback(struct backing_dev_info *bdi, struct super_block *sb, - long nr_pages); +void bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages); +void bdi_start_background_writeback(struct backing_dev_info *bdi); int bdi_writeback_task(struct bdi_writeback *wb); int bdi_has_dirty_io(struct backing_dev_info *bdi); void bdi_arm_supers_timer(void); diff --git a/mm/page-writeback.c b/mm/page-writeback.c index bbd396ac9546..54f28bd493d3 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -597,7 +597,7 @@ static void balance_dirty_pages(struct address_space *mapping, (!laptop_mode && ((global_page_state(NR_FILE_DIRTY) + global_page_state(NR_UNSTABLE_NFS)) > background_thresh))) - bdi_start_writeback(bdi, NULL, 0); + bdi_start_background_writeback(bdi); } void set_page_dirty_balance(struct page *page, int page_mkwrite) @@ -705,9 +705,8 @@ void laptop_mode_timer_fn(unsigned long data) * We want to write everything out, not just down to the dirty * threshold */ - if (bdi_has_dirty_io(&q->backing_dev_info)) - bdi_start_writeback(&q->backing_dev_info, NULL, nr_pages); + bdi_start_writeback(&q->backing_dev_info, nr_pages); } /* -- cgit v1.2.3 From 83ba7b071f30f7c01f72518ad72d5cd203c27502 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 6 Jul 2010 08:59:53 +0200 Subject: writeback: simplify the write back thread queue First remove items from work_list as soon as we start working on them. This means we don't have to track any pending or visited state and can get rid of all the RCU magic freeing the work items - we can simply free them once the operation has finished. Second use a real completion for tracking synchronous requests - if the caller sets the completion pointer we complete it, otherwise use it as a boolean indicator that we can free the work item directly. Third unify struct wb_writeback_args and struct bdi_work into a single data structure, wb_writeback_work. Previous we set all parameters into a struct wb_writeback_args, copied it into struct bdi_work, copied it again on the stack to use it there. Instead of just allocate one structure dynamically or on the stack and use it all the way through the stack. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- fs/fs-writeback.c | 253 ++++++++++++-------------------------------- include/linux/backing-dev.h | 2 - mm/backing-dev.c | 14 +-- 3 files changed, 72 insertions(+), 197 deletions(-) (limited to 'include/linux/backing-dev.h') diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 8cc06d5432b5..d5be1693ac93 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -38,43 +38,18 @@ int nr_pdflush_threads; /* * Passed into wb_writeback(), essentially a subset of writeback_control */ -struct wb_writeback_args { +struct wb_writeback_work { long nr_pages; struct super_block *sb; enum writeback_sync_modes sync_mode; unsigned int for_kupdate:1; unsigned int range_cyclic:1; unsigned int for_background:1; -}; -/* - * Work items for the bdi_writeback threads - */ -struct bdi_work { struct list_head list; /* pending work list */ - struct rcu_head rcu_head; /* for RCU free/clear of work */ - - unsigned long seen; /* threads that have seen this work */ - atomic_t pending; /* number of threads still to do work */ - - struct wb_writeback_args args; /* writeback arguments */ - - unsigned long state; /* flag bits, see WS_* */ -}; - -enum { - WS_INPROGRESS = 0, - WS_ONSTACK, + struct completion *done; /* set if the caller waits */ }; -static inline void bdi_work_init(struct bdi_work *work, - struct wb_writeback_args *args) -{ - INIT_RCU_HEAD(&work->rcu_head); - work->args = *args; - __set_bit(WS_INPROGRESS, &work->state); -} - /** * writeback_in_progress - determine whether there is writeback in progress * @bdi: the device's backing_dev_info structure. @@ -87,49 +62,11 @@ int writeback_in_progress(struct backing_dev_info *bdi) return !list_empty(&bdi->work_list); } -static void bdi_work_free(struct rcu_head *head) -{ - struct bdi_work *work = container_of(head, struct bdi_work, rcu_head); - - clear_bit(WS_INPROGRESS, &work->state); - smp_mb__after_clear_bit(); - wake_up_bit(&work->state, WS_INPROGRESS); - - if (!test_bit(WS_ONSTACK, &work->state)) - kfree(work); -} - -static void wb_clear_pending(struct bdi_writeback *wb, struct bdi_work *work) -{ - /* - * The caller has retrieved the work arguments from this work, - * drop our reference. If this is the last ref, delete and free it - */ - if (atomic_dec_and_test(&work->pending)) { - struct backing_dev_info *bdi = wb->bdi; - - spin_lock(&bdi->wb_lock); - list_del_rcu(&work->list); - spin_unlock(&bdi->wb_lock); - - call_rcu(&work->rcu_head, bdi_work_free); - } -} - -static void bdi_queue_work(struct backing_dev_info *bdi, struct bdi_work *work) +static void bdi_queue_work(struct backing_dev_info *bdi, + struct wb_writeback_work *work) { - work->seen = bdi->wb_mask; - BUG_ON(!work->seen); - atomic_set(&work->pending, bdi->wb_cnt); - BUG_ON(!bdi->wb_cnt); - - /* - * list_add_tail_rcu() contains the necessary barriers to - * make sure the above stores are seen before the item is - * noticed on the list - */ spin_lock(&bdi->wb_lock); - list_add_tail_rcu(&work->list, &bdi->work_list); + list_add_tail(&work->list, &bdi->work_list); spin_unlock(&bdi->wb_lock); /* @@ -146,55 +83,29 @@ static void bdi_queue_work(struct backing_dev_info *bdi, struct bdi_work *work) } } -/* - * 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_done(struct bdi_work *work) -{ - wait_on_bit(&work->state, WS_INPROGRESS, bdi_sched_wait, - TASK_UNINTERRUPTIBLE); -} - -static void bdi_alloc_queue_work(struct backing_dev_info *bdi, - struct wb_writeback_args *args) +static void +__bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages, + bool range_cyclic, bool for_background) { - struct bdi_work *work; + struct wb_writeback_work *work; /* * This is WB_SYNC_NONE writeback, so if allocation fails just * wakeup the thread for old dirty data writeback */ - work = kmalloc(sizeof(*work), GFP_ATOMIC); - if (work) { - bdi_work_init(work, args); - bdi_queue_work(bdi, work); - } else { - struct bdi_writeback *wb = &bdi->wb; - - if (wb->task) - wake_up_process(wb->task); + work = kzalloc(sizeof(*work), GFP_ATOMIC); + if (!work) { + if (bdi->wb.task) + wake_up_process(bdi->wb.task); + return; } -} -/** - * bdi_queue_work_onstack - start and wait for writeback - * @args: parameters to control the work queue writeback - * - * Description: - * This function initiates writeback and waits for the operation to - * complete. Callers must hold the sb s_umount semaphore for - * reading, to avoid having the super disappear before we are done. - */ -static void bdi_queue_work_onstack(struct wb_writeback_args *args) -{ - struct bdi_work work; + work->sync_mode = WB_SYNC_NONE; + work->nr_pages = nr_pages; + work->range_cyclic = range_cyclic; + work->for_background = for_background; - bdi_work_init(&work, args); - __set_bit(WS_ONSTACK, &work.state); - - bdi_queue_work(args->sb->s_bdi, &work); - bdi_wait_on_work_done(&work); + bdi_queue_work(bdi, work); } /** @@ -210,13 +121,7 @@ static void bdi_queue_work_onstack(struct wb_writeback_args *args) */ void bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages) { - struct wb_writeback_args args = { - .sync_mode = WB_SYNC_NONE, - .nr_pages = nr_pages, - .range_cyclic = 1, - }; - - bdi_alloc_queue_work(bdi, &args); + __bdi_start_writeback(bdi, nr_pages, true, false); } /** @@ -230,13 +135,7 @@ void bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages) */ void bdi_start_background_writeback(struct backing_dev_info *bdi) { - struct wb_writeback_args args = { - .sync_mode = WB_SYNC_NONE, - .nr_pages = LONG_MAX, - .for_background = 1, - .range_cyclic = 1, - }; - bdi_alloc_queue_work(bdi, &args); + __bdi_start_writeback(bdi, LONG_MAX, true, true); } /* @@ -703,14 +602,14 @@ static inline bool over_bground_thresh(void) * all dirty pages if they are all attached to "old" mappings. */ static long wb_writeback(struct bdi_writeback *wb, - struct wb_writeback_args *args) + struct wb_writeback_work *work) { struct writeback_control wbc = { - .sync_mode = args->sync_mode, + .sync_mode = work->sync_mode, .older_than_this = NULL, - .for_kupdate = args->for_kupdate, - .for_background = args->for_background, - .range_cyclic = args->range_cyclic, + .for_kupdate = work->for_kupdate, + .for_background = work->for_background, + .range_cyclic = work->range_cyclic, }; unsigned long oldest_jif; long wrote = 0; @@ -730,24 +629,24 @@ static long wb_writeback(struct bdi_writeback *wb, /* * Stop writeback when nr_pages has been consumed */ - if (args->nr_pages <= 0) + if (work->nr_pages <= 0) break; /* * For background writeout, stop when we are below the * background dirty threshold */ - if (args->for_background && !over_bground_thresh()) + if (work->for_background && !over_bground_thresh()) break; wbc.more_io = 0; wbc.nr_to_write = MAX_WRITEBACK_PAGES; wbc.pages_skipped = 0; - if (args->sb) - __writeback_inodes_sb(args->sb, wb, &wbc); + if (work->sb) + __writeback_inodes_sb(work->sb, wb, &wbc); else writeback_inodes_wb(wb, &wbc); - args->nr_pages -= MAX_WRITEBACK_PAGES - wbc.nr_to_write; + work->nr_pages -= MAX_WRITEBACK_PAGES - wbc.nr_to_write; wrote += MAX_WRITEBACK_PAGES - wbc.nr_to_write; /* @@ -783,31 +682,21 @@ static long wb_writeback(struct bdi_writeback *wb, } /* - * Return the next bdi_work struct that hasn't been processed by this - * wb thread yet. ->seen is initially set for each thread that exists - * for this device, when a thread first notices a piece of work it - * clears its bit. Depending on writeback type, the thread will notify - * completion on either receiving the work (WB_SYNC_NONE) or after - * it is done (WB_SYNC_ALL). + * Return the next wb_writeback_work struct that hasn't been processed yet. */ -static struct bdi_work *get_next_work_item(struct backing_dev_info *bdi, - struct bdi_writeback *wb) +static struct wb_writeback_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_bit(wb->nr, &work->seen)) - continue; - clear_bit(wb->nr, &work->seen); + struct wb_writeback_work *work = NULL; - ret = work; - break; + spin_lock(&bdi->wb_lock); + if (!list_empty(&bdi->work_list)) { + work = list_entry(bdi->work_list.next, + struct wb_writeback_work, list); + list_del_init(&work->list); } - - rcu_read_unlock(); - return ret; + spin_unlock(&bdi->wb_lock); + return work; } static long wb_check_old_data_flush(struct bdi_writeback *wb) @@ -832,14 +721,14 @@ static long wb_check_old_data_flush(struct bdi_writeback *wb) (inodes_stat.nr_inodes - inodes_stat.nr_unused); if (nr_pages) { - struct wb_writeback_args args = { + struct wb_writeback_work work = { .nr_pages = nr_pages, .sync_mode = WB_SYNC_NONE, .for_kupdate = 1, .range_cyclic = 1, }; - return wb_writeback(wb, &args); + return wb_writeback(wb, &work); } return 0; @@ -851,33 +740,27 @@ static long wb_check_old_data_flush(struct bdi_writeback *wb) long wb_do_writeback(struct bdi_writeback *wb, int force_wait) { struct backing_dev_info *bdi = wb->bdi; - struct bdi_work *work; + struct wb_writeback_work *work; long wrote = 0; while ((work = get_next_work_item(bdi, wb)) != NULL) { - struct wb_writeback_args args = work->args; - /* * Override sync mode, in case we must wait for completion + * because this thread is exiting now. */ if (force_wait) - work->args.sync_mode = args.sync_mode = WB_SYNC_ALL; + work->sync_mode = WB_SYNC_ALL; - /* - * If this isn't a data integrity operation, just notify - * that we have seen this work and we are now starting it. - */ - if (!test_bit(WS_ONSTACK, &work->state)) - wb_clear_pending(wb, work); - - wrote += wb_writeback(wb, &args); + wrote += wb_writeback(wb, work); /* - * This is a data integrity writeback, so only do the - * notification when we have completed the work. + * Notify the caller of completion if this is a synchronous + * work item, otherwise just free it. */ - if (test_bit(WS_ONSTACK, &work->state)) - wb_clear_pending(wb, work); + if (work->done) + complete(work->done); + else + kfree(work); } /* @@ -940,14 +823,9 @@ int bdi_writeback_task(struct bdi_writeback *wb) void wakeup_flusher_threads(long nr_pages) { struct backing_dev_info *bdi; - struct wb_writeback_args args = { - .sync_mode = WB_SYNC_NONE, - }; - if (nr_pages) { - args.nr_pages = nr_pages; - } else { - args.nr_pages = global_page_state(NR_FILE_DIRTY) + + if (!nr_pages) { + nr_pages = global_page_state(NR_FILE_DIRTY) + global_page_state(NR_UNSTABLE_NFS); } @@ -955,7 +833,7 @@ void wakeup_flusher_threads(long nr_pages) list_for_each_entry_rcu(bdi, &bdi_list, bdi_list) { if (!bdi_has_dirty_io(bdi)) continue; - bdi_alloc_queue_work(bdi, &args); + __bdi_start_writeback(bdi, nr_pages, false, false); } rcu_read_unlock(); } @@ -1164,17 +1042,20 @@ void writeback_inodes_sb(struct super_block *sb) { unsigned long nr_dirty = global_page_state(NR_FILE_DIRTY); unsigned long nr_unstable = global_page_state(NR_UNSTABLE_NFS); - struct wb_writeback_args args = { + DECLARE_COMPLETION_ONSTACK(done); + struct wb_writeback_work work = { .sb = sb, .sync_mode = WB_SYNC_NONE, + .done = &done, }; WARN_ON(!rwsem_is_locked(&sb->s_umount)); - args.nr_pages = nr_dirty + nr_unstable + + work.nr_pages = nr_dirty + nr_unstable + (inodes_stat.nr_inodes - inodes_stat.nr_unused); - bdi_queue_work_onstack(&args); + bdi_queue_work(sb->s_bdi, &work); + wait_for_completion(&done); } EXPORT_SYMBOL(writeback_inodes_sb); @@ -1206,16 +1087,20 @@ EXPORT_SYMBOL(writeback_inodes_sb_if_idle); */ void sync_inodes_sb(struct super_block *sb) { - struct wb_writeback_args args = { + DECLARE_COMPLETION_ONSTACK(done); + struct wb_writeback_work work = { .sb = sb, .sync_mode = WB_SYNC_ALL, .nr_pages = LONG_MAX, .range_cyclic = 0, + .done = &done, }; WARN_ON(!rwsem_is_locked(&sb->s_umount)); - bdi_queue_work_onstack(&args); + bdi_queue_work(sb->s_bdi, &work); + wait_for_completion(&done); + wait_sb_inodes(sb); } EXPORT_SYMBOL(sync_inodes_sb); diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 9ae2889096b6..e9aec0d099df 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -82,8 +82,6 @@ struct backing_dev_info { struct bdi_writeback wb; /* default writeback info for this bdi */ spinlock_t wb_lock; /* protects update side of wb_list */ struct list_head wb_list; /* the flusher threads hanging off this bdi */ - unsigned long wb_mask; /* bitmask of registered tasks */ - unsigned int wb_cnt; /* number of registered tasks */ struct list_head work_list; diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 6e0b09a1ec2c..123bcef13e51 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -104,15 +104,13 @@ static int bdi_debug_stats_show(struct seq_file *m, void *v) "b_more_io: %8lu\n" "bdi_list: %8u\n" "state: %8lx\n" - "wb_mask: %8lx\n" - "wb_list: %8u\n" - "wb_cnt: %8u\n", + "wb_list: %8u\n", (unsigned long) K(bdi_stat(bdi, BDI_WRITEBACK)), (unsigned long) K(bdi_stat(bdi, BDI_RECLAIMABLE)), K(bdi_thresh), K(dirty_thresh), K(background_thresh), nr_wb, nr_dirty, nr_io, nr_more_io, - !list_empty(&bdi->bdi_list), bdi->state, bdi->wb_mask, - !list_empty(&bdi->wb_list), bdi->wb_cnt); + !list_empty(&bdi->bdi_list), bdi->state, + !list_empty(&bdi->wb_list)); #undef K return 0; @@ -674,12 +672,6 @@ int bdi_init(struct backing_dev_info *bdi) 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); if (err) -- cgit v1.2.3 From c1955ce32fdb0877b7a1b22feb2669358f65be76 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 19 Jun 2010 23:08:06 +0200 Subject: writeback: remove wb_list The wb_list member of struct backing_device_info always has exactly one element. Just use the direct bdi->wb pointer instead and simplify some code. Also remove bdi_task_init which is now trivial to prepare for the next patch. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- fs/fs-writeback.c | 4 +-- include/linux/backing-dev.h | 5 +-- mm/backing-dev.c | 83 ++++++++++++++++----------------------------- 3 files changed, 32 insertions(+), 60 deletions(-) (limited to 'include/linux/backing-dev.h') diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index d5be1693ac93..d67989b8ba44 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -73,9 +73,9 @@ static void bdi_queue_work(struct backing_dev_info *bdi, * 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))) + if (unlikely(!bdi->wb.task)) { wake_up_process(default_backing_dev_info.wb.task); - else { + } else { struct bdi_writeback *wb = &bdi->wb; if (wb->task) diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index e9aec0d099df..50f146146169 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -45,8 +45,6 @@ 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; @@ -80,8 +78,7 @@ struct backing_dev_info { unsigned int max_ratio, max_prop_frac; struct bdi_writeback wb; /* default writeback info for this bdi */ - spinlock_t wb_lock; /* protects update side of wb_list */ - struct list_head wb_list; /* the flusher threads hanging off this bdi */ + spinlock_t wb_lock; /* protects work_list */ struct list_head work_list; diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 123bcef13e51..6c2a09c8922c 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -65,28 +65,21 @@ static void bdi_debug_init(void) static int bdi_debug_stats_show(struct seq_file *m, void *v) { struct backing_dev_info *bdi = m->private; - struct bdi_writeback *wb; + struct bdi_writeback *wb = &bdi->wb; unsigned long background_thresh; unsigned long dirty_thresh; unsigned long bdi_thresh; unsigned long nr_dirty, nr_io, nr_more_io, nr_wb; struct inode *inode; - /* - * inode lock is enough here, the bdi->wb_list is protected by - * RCU on the reader side - */ nr_wb = nr_dirty = nr_io = nr_more_io = 0; spin_lock(&inode_lock); - list_for_each_entry(wb, &bdi->wb_list, list) { - nr_wb++; - list_for_each_entry(inode, &wb->b_dirty, i_list) - nr_dirty++; - list_for_each_entry(inode, &wb->b_io, i_list) - nr_io++; - list_for_each_entry(inode, &wb->b_more_io, i_list) - nr_more_io++; - } + list_for_each_entry(inode, &wb->b_dirty, i_list) + nr_dirty++; + list_for_each_entry(inode, &wb->b_io, i_list) + nr_io++; + list_for_each_entry(inode, &wb->b_more_io, i_list) + nr_more_io++; spin_unlock(&inode_lock); get_dirty_limits(&background_thresh, &dirty_thresh, &bdi_thresh, bdi); @@ -98,19 +91,16 @@ static int bdi_debug_stats_show(struct seq_file *m, void *v) "BdiDirtyThresh: %8lu kB\n" "DirtyThresh: %8lu kB\n" "BackgroundThresh: %8lu kB\n" - "WritebackThreads: %8lu\n" "b_dirty: %8lu\n" "b_io: %8lu\n" "b_more_io: %8lu\n" "bdi_list: %8u\n" - "state: %8lx\n" - "wb_list: %8u\n", + "state: %8lx\n", (unsigned long) K(bdi_stat(bdi, BDI_WRITEBACK)), (unsigned long) K(bdi_stat(bdi, BDI_RECLAIMABLE)), K(bdi_thresh), K(dirty_thresh), - K(background_thresh), nr_wb, nr_dirty, nr_io, nr_more_io, - !list_empty(&bdi->bdi_list), bdi->state, - !list_empty(&bdi->wb_list)); + K(background_thresh), nr_dirty, nr_io, nr_more_io, + !list_empty(&bdi->bdi_list), bdi->state); #undef K return 0; @@ -270,24 +260,6 @@ static void bdi_wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi) 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; @@ -301,7 +273,13 @@ static int bdi_start_fn(void *ptr) list_add_rcu(&bdi->bdi_list, &bdi_list); spin_unlock_bh(&bdi_lock); - bdi_task_init(bdi, wb); + current->flags |= PF_FLUSHER | PF_SWAPWRITE; + set_freezable(); + + /* + * Our parent may run at a different priority, just set us to normal + */ + set_user_nice(current, 0); /* * Clear pending bit and wakeup anybody waiting to tear us down @@ -312,12 +290,7 @@ static int bdi_start_fn(void *ptr) 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); + wb->task = NULL; /* * Flush any work that raced with us exiting. No new work @@ -326,7 +299,6 @@ static int bdi_start_fn(void *ptr) if (!list_empty(&bdi->work_list)) wb_do_writeback(wb, 1); - wb->task = NULL; return ret; } @@ -391,7 +363,13 @@ static int bdi_forker_task(void *ptr) { struct bdi_writeback *me = ptr; - bdi_task_init(me->bdi, me); + current->flags |= PF_FLUSHER | PF_SWAPWRITE; + set_freezable(); + + /* + * Our parent may run at a different priority, just set us to normal + */ + set_user_nice(current, 0); for (;;) { struct backing_dev_info *bdi, *tmp; @@ -598,8 +576,6 @@ EXPORT_SYMBOL(bdi_register_dev); */ static void bdi_wb_shutdown(struct backing_dev_info *bdi) { - struct bdi_writeback *wb; - if (!bdi_cap_writeback_dirty(bdi)) return; @@ -615,14 +591,14 @@ static void bdi_wb_shutdown(struct backing_dev_info *bdi) bdi_remove_from_list(bdi); /* - * Finally, kill the kernel threads. We don't need to be RCU + * Finally, kill the kernel thread. We don't need to be RCU * safe anymore, since the bdi is gone from visibility. Force * unfreeze of the thread before calling kthread_stop(), otherwise * it would never exet if it is currently stuck in the refrigerator. */ - list_for_each_entry(wb, &bdi->wb_list, list) { - thaw_process(wb->task); - kthread_stop(wb->task); + if (bdi->wb.task) { + thaw_process(bdi->wb.task); + kthread_stop(bdi->wb.task); } } @@ -667,7 +643,6 @@ int bdi_init(struct backing_dev_info *bdi) spin_lock_init(&bdi->wb_lock); INIT_RCU_HEAD(&bdi->rcu_head); INIT_LIST_HEAD(&bdi->bdi_list); - INIT_LIST_HEAD(&bdi->wb_list); INIT_LIST_HEAD(&bdi->work_list); bdi_wb_init(&bdi->wb, bdi); -- cgit v1.2.3 From 082439004b31adc146e96e5f1c574dd2b57dcd93 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 19 Jun 2010 23:08:22 +0200 Subject: writeback: merge bdi_writeback_task and bdi_start_fn Move all code for the writeback thread into fs/fs-writeback.c instead of splitting it over two functions in two files. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- fs/fs-writeback.c | 35 ++++++++++++++++++++++++++++++++++- include/linux/backing-dev.h | 2 +- mm/backing-dev.c | 44 +------------------------------------------- 3 files changed, 36 insertions(+), 45 deletions(-) (limited to 'include/linux/backing-dev.h') diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index d67989b8ba44..c8471b3ddccf 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -775,12 +775,36 @@ long wb_do_writeback(struct bdi_writeback *wb, int force_wait) * 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) +int bdi_writeback_thread(void *data) { + struct bdi_writeback *wb = data; + struct backing_dev_info *bdi = wb->bdi; unsigned long last_active = jiffies; unsigned long wait_jiffies = -1UL; long pages_written; + /* + * Add us to the active bdi_list + */ + spin_lock_bh(&bdi_lock); + list_add_rcu(&bdi->bdi_list, &bdi_list); + spin_unlock_bh(&bdi_lock); + + current->flags |= PF_FLUSHER | PF_SWAPWRITE; + set_freezable(); + + /* + * Our parent may run at a different priority, just set us to normal + */ + set_user_nice(current, 0); + + /* + * 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); + while (!kthread_should_stop()) { pages_written = wb_do_writeback(wb, 0); @@ -813,9 +837,18 @@ int bdi_writeback_task(struct bdi_writeback *wb) try_to_freeze(); } + wb->task = NULL; + + /* + * 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); return 0; } + /* * Start writeback of `nr_pages' pages. If `nr_pages' is zero, write back * the whole world. diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 50f146146169..e536f3a74e60 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -102,7 +102,7 @@ void bdi_unregister(struct backing_dev_info *bdi); int bdi_setup_and_register(struct backing_dev_info *, char *, unsigned int); void bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages); void bdi_start_background_writeback(struct backing_dev_info *bdi); -int bdi_writeback_task(struct bdi_writeback *wb); +int bdi_writeback_thread(void *data); int bdi_has_dirty_io(struct backing_dev_info *bdi); void bdi_arm_supers_timer(void); diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 6c2a09c8922c..bceac647e4d1 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -260,48 +260,6 @@ static void bdi_wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi) INIT_LIST_HEAD(&wb->b_more_io); } -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_bh(&bdi_lock); - list_add_rcu(&bdi->bdi_list, &bdi_list); - spin_unlock_bh(&bdi_lock); - - current->flags |= PF_FLUSHER | PF_SWAPWRITE; - set_freezable(); - - /* - * Our parent may run at a different priority, just set us to normal - */ - set_user_nice(current, 0); - - /* - * 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); - - wb->task = NULL; - - /* - * 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); - - return ret; -} - int bdi_has_dirty_io(struct backing_dev_info *bdi) { return wb_has_dirty_io(&bdi->wb); @@ -425,7 +383,7 @@ static int bdi_forker_task(void *ptr) spin_unlock_bh(&bdi_lock); wb = &bdi->wb; - wb->task = kthread_run(bdi_start_fn, wb, "flush-%s", + wb->task = kthread_run(bdi_writeback_thread, wb, "flush-%s", dev_name(bdi->dev)); /* * If task creation fails, then readd the bdi to -- cgit v1.2.3 From 6f904ff0e39ea88f81eb77e8dfb4e1238492f0a8 Mon Sep 17 00:00:00 2001 From: Artem Bityutskiy Date: Sun, 25 Jul 2010 14:29:11 +0300 Subject: writeback: harmonize writeback threads naming The write-back code mixes words "thread" and "task" for the same things. This is not a big deal, but still an inconsistency. hch: a convention I tend to use and I've seen in various places is to always use _task for the storage of the task_struct pointer, and thread everywhere else. This especially helps with having foo_thread for the actual thread and foo_task for a global variable keeping the task_struct pointer This patch renames: * 'bdi_add_default_flusher_task()' -> 'bdi_add_default_flusher_thread()' * 'bdi_forker_task()' -> 'bdi_forker_thread()' because bdi threads are 'bdi_writeback_thread()', so these names are more consistent. This patch also amends commentaries and makes them refer the forker and bdi threads as "thread", not "task". Also, while on it, make 'bdi_add_default_flusher_thread()' declaration use 'static void' instead of 'void static' and make checkpatch.pl happy. Signed-off-by: Artem Bityutskiy Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe --- fs/fs-writeback.c | 2 +- include/linux/backing-dev.h | 2 +- mm/backing-dev.c | 26 +++++++++++++------------- 3 files changed, 15 insertions(+), 15 deletions(-) (limited to 'include/linux/backing-dev.h') diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 261570deb22c..002be0ff2ab3 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -840,7 +840,7 @@ int bdi_writeback_thread(void *data) /* * Longest period of inactivity that we tolerate. If we - * see dirty data again later, the task will get + * see dirty data again later, the thread will get * recreated automatically. */ max_idle = max(5UL * 60 * HZ, wait_jiffies); diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index e536f3a74e60..f0936f5f85dd 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -50,7 +50,7 @@ struct bdi_writeback { unsigned long last_old_flush; /* last old data flush */ - struct task_struct *task; /* writeback task */ + struct task_struct *task; /* writeback thread */ 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 */ diff --git a/mm/backing-dev.c b/mm/backing-dev.c index ac78a3336181..4e9ed2a8521f 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -50,7 +50,7 @@ static struct timer_list sync_supers_timer; static int bdi_sync_supers(void *); static void sync_supers_timer_fn(unsigned long); -static void bdi_add_default_flusher_task(struct backing_dev_info *bdi); +static void bdi_add_default_flusher_thread(struct backing_dev_info *bdi); #ifdef CONFIG_DEBUG_FS #include @@ -279,10 +279,10 @@ static void bdi_flush_io(struct backing_dev_info *bdi) } /* - * kupdated() used to do this. We cannot do it from the bdi_forker_task() + * kupdated() used to do this. We cannot do it from the bdi_forker_thread() * 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. + * bdi writeback thread individually. */ static int bdi_sync_supers(void *unused) { @@ -318,7 +318,7 @@ static void sync_supers_timer_fn(unsigned long unused) bdi_arm_supers_timer(); } -static int bdi_forker_task(void *ptr) +static int bdi_forker_thread(void *ptr) { struct bdi_writeback *me = ptr; @@ -354,7 +354,7 @@ static int bdi_forker_task(void *ptr) !bdi_has_dirty_io(bdi)) continue; - bdi_add_default_flusher_task(bdi); + bdi_add_default_flusher_thread(bdi); } set_current_state(TASK_INTERRUPTIBLE); @@ -376,7 +376,7 @@ static int bdi_forker_task(void *ptr) /* * This is our real job - check for pending entries in - * bdi_pending_list, and create the tasks that got added + * bdi_pending_list, and create the threads that got added */ bdi = list_entry(bdi_pending_list.next, struct backing_dev_info, bdi_list); @@ -387,7 +387,7 @@ static int bdi_forker_task(void *ptr) wb->task = kthread_run(bdi_writeback_thread, wb, "flush-%s", dev_name(bdi->dev)); /* - * If task creation fails, then readd the bdi to + * If thread 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. @@ -430,10 +430,10 @@ static void bdi_add_to_pending(struct rcu_head *head) } /* - * Add the default flusher task that gets created for any bdi + * Add the default flusher thread that gets created for any bdi * that has dirty data pending writeout */ -void static bdi_add_default_flusher_task(struct backing_dev_info *bdi) +static void bdi_add_default_flusher_thread(struct backing_dev_info *bdi) { if (!bdi_cap_writeback_dirty(bdi)) return; @@ -445,10 +445,10 @@ void static bdi_add_default_flusher_task(struct backing_dev_info *bdi) } /* - * Check with the helper whether to proceed adding a task. Will only + * Check with the helper whether to proceed adding a thread. 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. + * bdi_add_default_flusher_thread() occured, further additions will + * block waiting for previous additions to finish. */ if (!test_and_set_bit(BDI_pending, &bdi->state)) { list_del_rcu(&bdi->bdi_list); @@ -506,7 +506,7 @@ int bdi_register(struct backing_dev_info *bdi, struct device *parent, if (bdi_cap_flush_forker(bdi)) { struct bdi_writeback *wb = &bdi->wb; - wb->task = kthread_run(bdi_forker_task, wb, "bdi-%s", + wb->task = kthread_run(bdi_forker_thread, wb, "bdi-%s", dev_name(dev)); if (IS_ERR(wb->task)) { wb->task = NULL; -- cgit v1.2.3 From 080dcec41709be72613133f695be75b98dd43e88 Mon Sep 17 00:00:00 2001 From: Artem Bityutskiy Date: Sun, 25 Jul 2010 14:29:16 +0300 Subject: writeback: simplify bdi code a little This patch simplifies bdi code a little by removing the 'pending_list' which is redundant. Indeed, currently the forker thread ('bdi_forker_thread()') is working like this: 1. In a loop, fetch all bdi's which have works but have no writeback thread and move them to the 'pending_list'. 2. If the list is empty, sleep for 5 sec. 3. Otherwise, take one bdi from the list, fork the writeback thread for this bdi, and repeat the loop. IOW, it first moves everything to the 'pending_list', then process only one element, and so on. This patch simplifies the algorithm, which is now as follows. 1. Find the first bdi which has a work and remove it from the global list of bdi's (bdi_list). 2. If there was not such bdi, sleep 5 sec. 3. Fork the writeback thread for this bdi and repeat the loop. IOW, now we find the first bdi to process, process it, and so on. This is simpler and involves less lists. The bonus now is that we can get rid of a couple of functions, as well as remove complications which involve 'rcu_call()' and 'bdi->rcu_head'. This patch also makes sure we use 'list_add_tail_rcu()', instead of plain 'list_add_tail()', but this piece of code is going to be removed in the next patch anyway. Signed-off-by: Artem Bityutskiy Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/backing-dev.h | 1 - mm/backing-dev.c | 82 ++++++++++----------------------------------- 2 files changed, 18 insertions(+), 65 deletions(-) (limited to 'include/linux/backing-dev.h') diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index f0936f5f85dd..95ecb2bebca8 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -58,7 +58,6 @@ struct bdi_writeback { struct backing_dev_info { struct list_head bdi_list; - struct rcu_head rcu_head; 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 */ diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 72e6eb96efe2..dbc66815a0fe 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -50,8 +50,6 @@ static struct timer_list sync_supers_timer; static int bdi_sync_supers(void *); static void sync_supers_timer_fn(unsigned long); -static void bdi_add_default_flusher_thread(struct backing_dev_info *bdi); - #ifdef CONFIG_DEBUG_FS #include #include @@ -331,6 +329,7 @@ static int bdi_forker_thread(void *ptr) set_user_nice(current, 0); for (;;) { + bool fork = false; struct task_struct *task; struct backing_dev_info *bdi, *tmp; @@ -349,23 +348,30 @@ static int bdi_forker_thread(void *ptr) * a thread registered. If so, set that up. */ list_for_each_entry_safe(bdi, tmp, &bdi_list, bdi_list) { + if (!bdi_cap_writeback_dirty(bdi)) + continue; if (bdi->wb.task) continue; if (list_empty(&bdi->work_list) && !bdi_has_dirty_io(bdi)) continue; - bdi_add_default_flusher_thread(bdi); + WARN(!test_bit(BDI_registered, &bdi->state), + "bdi %p/%s is not registered!\n", bdi, bdi->name); + + list_del_rcu(&bdi->bdi_list); + fork = true; + break; } + spin_unlock_bh(&bdi_lock); /* Keep working if default bdi still has things to do */ if (!list_empty(&me->bdi->work_list)) __set_current_state(TASK_RUNNING); - if (list_empty(&bdi_pending_list)) { + if (!fork) { unsigned long wait; - spin_unlock_bh(&bdi_lock); wait = msecs_to_jiffies(dirty_writeback_interval * 10); if (wait) schedule_timeout(wait); @@ -378,13 +384,13 @@ static int bdi_forker_thread(void *ptr) __set_current_state(TASK_RUNNING); /* - * This is our real job - check for pending entries in - * bdi_pending_list, and create the threads that got added + * Set the pending bit - if someone will try to unregister this + * bdi - it'll wait on this bit. */ - bdi = list_entry(bdi_pending_list.next, struct backing_dev_info, - bdi_list); - list_del_init(&bdi->bdi_list); - spin_unlock_bh(&bdi_lock); + set_bit(BDI_pending, &bdi->state); + + /* Make sure no one uses the picked bdi */ + synchronize_rcu(); task = kthread_run(bdi_writeback_thread, &bdi->wb, "flush-%s", dev_name(bdi->dev)); @@ -397,7 +403,7 @@ static int bdi_forker_thread(void *ptr) * flush other bdi's to free memory. */ spin_lock_bh(&bdi_lock); - list_add_tail(&bdi->bdi_list, &bdi_pending_list); + list_add_tail_rcu(&bdi->bdi_list, &bdi_list); spin_unlock_bh(&bdi_lock); bdi_flush_io(bdi); @@ -408,57 +414,6 @@ static int bdi_forker_thread(void *ptr) return 0; } -static void bdi_add_to_pending(struct rcu_head *head) -{ - struct backing_dev_info *bdi; - - bdi = container_of(head, struct backing_dev_info, rcu_head); - INIT_LIST_HEAD(&bdi->bdi_list); - - spin_lock(&bdi_lock); - list_add_tail(&bdi->bdi_list, &bdi_pending_list); - spin_unlock(&bdi_lock); - - /* - * 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); -} - -/* - * Add the default flusher thread that gets created for any bdi - * that has dirty data pending writeout - */ -static void bdi_add_default_flusher_thread(struct backing_dev_info *bdi) -{ - if (!bdi_cap_writeback_dirty(bdi)) - return; - - if (WARN_ON(!test_bit(BDI_registered, &bdi->state))) { - printk(KERN_ERR "bdi %p/%s is not registered!\n", - bdi, bdi->name); - return; - } - - /* - * Check with the helper whether to proceed adding a thread. Will only - * abort if we two or more simultanous calls to - * bdi_add_default_flusher_thread() occured, further additions will - * block waiting for previous additions to finish. - */ - if (!test_and_set_bit(BDI_pending, &bdi->state)) { - list_del_rcu(&bdi->bdi_list); - - /* - * We must wait for the current RCU period to end before - * moving to the pending list. So schedule that operation - * from an RCU callback. - */ - call_rcu(&bdi->rcu_head, bdi_add_to_pending); - } -} - /* * Remove bdi from bdi_list, and ensure that it is no longer visible */ @@ -599,7 +554,6 @@ int bdi_init(struct backing_dev_info *bdi) bdi->max_ratio = 100; bdi->max_prop_frac = PROP_FRAC_BASE; spin_lock_init(&bdi->wb_lock); - INIT_RCU_HEAD(&bdi->rcu_head); INIT_LIST_HEAD(&bdi->bdi_list); INIT_LIST_HEAD(&bdi->work_list); -- cgit v1.2.3 From ecd584030da67ede1bf17955746a6ce834d9fc6b Mon Sep 17 00:00:00 2001 From: Artem Bityutskiy Date: Sun, 25 Jul 2010 14:29:18 +0300 Subject: writeback: move last_active to bdi Currently bdi threads use local variable 'last_active' which stores last time when the bdi thread did some useful work. Move this local variable to 'struct bdi_writeback'. This is just a preparation for the further patches which will make the forker thread decide when bdi threads should be killed. Signed-off-by: Artem Bityutskiy Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe --- fs/fs-writeback.c | 6 +++--- include/linux/backing-dev.h | 13 +++++++------ 2 files changed, 10 insertions(+), 9 deletions(-) (limited to 'include/linux/backing-dev.h') diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 57fbfd0ebc52..9f5cab75c157 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -800,12 +800,12 @@ int bdi_writeback_thread(void *data) { struct bdi_writeback *wb = data; struct backing_dev_info *bdi = wb->bdi; - unsigned long last_active = jiffies; unsigned long wait_jiffies = -1UL; long pages_written; current->flags |= PF_FLUSHER | PF_SWAPWRITE; set_freezable(); + wb->last_active = jiffies; /* * Our parent may run at a different priority, just set us to normal @@ -827,7 +827,7 @@ int bdi_writeback_thread(void *data) trace_writeback_pages_written(pages_written); if (pages_written) - last_active = jiffies; + wb->last_active = jiffies; else if (wait_jiffies != -1UL) { unsigned long max_idle; @@ -837,7 +837,7 @@ int bdi_writeback_thread(void *data) * recreated automatically. */ max_idle = max(5UL * 60 * HZ, wait_jiffies); - if (time_after(jiffies, max_idle + last_active)) + if (time_after(jiffies, max_idle + wb->last_active)) break; } diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 95ecb2bebca8..71b6223e0a77 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -45,15 +45,16 @@ enum bdi_stat_item { #define BDI_STAT_BATCH (8*(1+ilog2(nr_cpu_ids))) struct bdi_writeback { - struct backing_dev_info *bdi; /* our parent bdi */ + struct backing_dev_info *bdi; /* our parent bdi */ unsigned int nr; - unsigned long last_old_flush; /* last old data flush */ + unsigned long last_old_flush; /* last old data flush */ + unsigned long last_active; /* last time bdi thread was active */ - struct task_struct *task; /* writeback thread */ - 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 task_struct *task; /* writeback thread */ + 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 { -- cgit v1.2.3 From 6467716a37673e8d47b4984eb19839bdad0a8353 Mon Sep 17 00:00:00 2001 From: Artem Bityutskiy Date: Sun, 25 Jul 2010 14:29:22 +0300 Subject: writeback: optimize periodic bdi thread wakeups Whe the first inode for a bdi is marked dirty, we wake up the bdi thread which should take care of the periodic background write-out. However, the write-out will actually start only 'dirty_writeback_interval' centisecs later, so we can delay the wake-up. This change was requested by Nick Piggin who pointed out that if we delay the wake-up, we weed out 2 unnecessary contex switches, which matters because '__mark_inode_dirty()' is a hot-path function. This patch introduces a new function - 'bdi_wakeup_thread_delayed()', which sets up a timer to wake-up the bdi thread and returns. So the wake-up is delayed. We also delete the timer in bdi threads just before writing-back. And synchronously delete it when unregistering bdi. At the unregister point the bdi does not have any users, so no one can arm it again. Since now we take 'bdi->wb_lock' in the timer, which can execute in softirq context, we have to use 'spin_lock_bh()' for 'bdi->wb_lock'. This patch makes this change as well. This patch also moves the 'bdi_wb_init()' function down in the file to avoid forward-declaration of 'bdi_wakeup_thread_delayed()'. Signed-off-by: Artem Bityutskiy Signed-off-by: Jens Axboe --- fs/fs-writeback.c | 36 +++++++--------------- include/linux/backing-dev.h | 2 ++ mm/backing-dev.c | 73 +++++++++++++++++++++++++++++++++++---------- 3 files changed, 70 insertions(+), 41 deletions(-) (limited to 'include/linux/backing-dev.h') diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 55f6e46e06f1..bfa2df2c7ce2 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -76,7 +76,7 @@ static void bdi_queue_work(struct backing_dev_info *bdi, { trace_writeback_queue(bdi, work); - spin_lock(&bdi->wb_lock); + spin_lock_bh(&bdi->wb_lock); list_add_tail(&work->list, &bdi->work_list); if (bdi->wb.task) { wake_up_process(bdi->wb.task); @@ -88,7 +88,7 @@ static void bdi_queue_work(struct backing_dev_info *bdi, trace_writeback_nothread(bdi, work); wake_up_process(default_backing_dev_info.wb.task); } - spin_unlock(&bdi->wb_lock); + spin_unlock_bh(&bdi->wb_lock); } static void @@ -704,13 +704,13 @@ get_next_work_item(struct backing_dev_info *bdi) { struct wb_writeback_work *work = NULL; - spin_lock(&bdi->wb_lock); + spin_lock_bh(&bdi->wb_lock); if (!list_empty(&bdi->work_list)) { work = list_entry(bdi->work_list.next, struct wb_writeback_work, list); list_del_init(&work->list); } - spin_unlock(&bdi->wb_lock); + spin_unlock_bh(&bdi->wb_lock); return work; } @@ -810,6 +810,12 @@ int bdi_writeback_thread(void *data) trace_writeback_thread_start(bdi); while (!kthread_should_stop()) { + /* + * Remove own delayed wake-up timer, since we are already awake + * and we'll take care of the preriodic write-back. + */ + del_timer(&wb->wakeup_timer); + pages_written = wb_do_writeback(wb, 0); trace_writeback_pages_written(pages_written); @@ -868,26 +874,6 @@ void wakeup_flusher_threads(long nr_pages) rcu_read_unlock(); } -/* - * This function is used when the first inode for this bdi is marked dirty. It - * wakes-up the corresponding bdi thread which should then take care of the - * periodic background write-out of dirty inodes. - */ -static void wakeup_bdi_thread(struct backing_dev_info *bdi) -{ - spin_lock(&bdi->wb_lock); - if (bdi->wb.task) - wake_up_process(bdi->wb.task); - else - /* - * When bdi tasks are inactive for long time, they are killed. - * In this case we have to wake-up the forker thread which - * should create and run the bdi thread. - */ - wake_up_process(default_backing_dev_info.wb.task); - spin_unlock(&bdi->wb_lock); -} - static noinline void block_dump___mark_inode_dirty(struct inode *inode) { if (inode->i_ino || strcmp(inode->i_sb->s_id, "bdev")) { @@ -1019,7 +1005,7 @@ out: spin_unlock(&inode_lock); if (wakeup_bdi) - wakeup_bdi_thread(bdi); + bdi_wakeup_thread_delayed(bdi); } EXPORT_SYMBOL(__mark_inode_dirty); diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 71b6223e0a77..7628219e5386 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -52,6 +52,7 @@ struct bdi_writeback { unsigned long last_active; /* last time bdi thread was active */ struct task_struct *task; /* writeback thread */ + struct timer_list wakeup_timer; /* used for delayed bdi thread wakeup */ 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 */ @@ -105,6 +106,7 @@ void bdi_start_background_writeback(struct backing_dev_info *bdi); int bdi_writeback_thread(void *data); int bdi_has_dirty_io(struct backing_dev_info *bdi); void bdi_arm_supers_timer(void); +void bdi_wakeup_thread_delayed(struct backing_dev_info *bdi); extern spinlock_t bdi_lock; extern struct list_head bdi_list; diff --git a/mm/backing-dev.c b/mm/backing-dev.c index a9a08d88a745..cfff7225138c 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -248,17 +248,6 @@ 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); -} - int bdi_has_dirty_io(struct backing_dev_info *bdi) { return wb_has_dirty_io(&bdi->wb); @@ -316,6 +305,43 @@ static void sync_supers_timer_fn(unsigned long unused) bdi_arm_supers_timer(); } +static void wakeup_timer_fn(unsigned long data) +{ + struct backing_dev_info *bdi = (struct backing_dev_info *)data; + + spin_lock_bh(&bdi->wb_lock); + if (bdi->wb.task) { + wake_up_process(bdi->wb.task); + } else { + /* + * When bdi tasks are inactive for long time, they are killed. + * In this case we have to wake-up the forker thread which + * should create and run the bdi thread. + */ + wake_up_process(default_backing_dev_info.wb.task); + } + spin_unlock_bh(&bdi->wb_lock); +} + +/* + * This function is used when the first inode for this bdi is marked dirty. It + * wakes-up the corresponding bdi thread which should then take care of the + * periodic background write-out of dirty inodes. Since the write-out would + * starts only 'dirty_writeback_interval' centisecs from now anyway, we just + * set up a timer which wakes the bdi thread up later. + * + * Note, we wouldn't bother setting up the timer, but this function is on the + * fast-path (used by '__mark_inode_dirty()'), so we save few context switches + * by delaying the wake-up. + */ +void bdi_wakeup_thread_delayed(struct backing_dev_info *bdi) +{ + unsigned long timeout; + + timeout = msecs_to_jiffies(dirty_writeback_interval * 10); + mod_timer(&bdi->wb.wakeup_timer, jiffies + timeout); +} + /* * Calculate the longest interval (jiffies) bdi threads are allowed to be * inactive. @@ -353,8 +379,10 @@ static int bdi_forker_thread(void *ptr) * 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)) + if (wb_has_dirty_io(me) || !list_empty(&me->bdi->work_list)) { + del_timer(&me->wakeup_timer); wb_do_writeback(me, 0); + } spin_lock_bh(&bdi_lock); set_current_state(TASK_INTERRUPTIBLE); @@ -386,7 +414,7 @@ static int bdi_forker_thread(void *ptr) break; } - spin_lock(&bdi->wb_lock); + spin_lock_bh(&bdi->wb_lock); /* * If there is no work to do and the bdi thread was * inactive long enough - kill it. The wb_lock is taken @@ -403,7 +431,7 @@ static int bdi_forker_thread(void *ptr) action = KILL_THREAD; break; } - spin_unlock(&bdi->wb_lock); + spin_unlock_bh(&bdi->wb_lock); } spin_unlock_bh(&bdi_lock); @@ -427,9 +455,9 @@ static int bdi_forker_thread(void *ptr) * The spinlock makes sure we do not lose * wake-ups when racing with 'bdi_queue_work()'. */ - spin_lock(&bdi->wb_lock); + spin_lock_bh(&bdi->wb_lock); bdi->wb.task = task; - spin_unlock(&bdi->wb_lock); + spin_unlock_bh(&bdi->wb_lock); } break; @@ -586,6 +614,7 @@ void bdi_unregister(struct backing_dev_info *bdi) if (bdi->dev) { trace_writeback_bdi_unregister(bdi); bdi_prune_sb(bdi); + del_timer_sync(&bdi->wb.wakeup_timer); if (!bdi_cap_flush_forker(bdi)) bdi_wb_shutdown(bdi); @@ -596,6 +625,18 @@ void bdi_unregister(struct backing_dev_info *bdi) } EXPORT_SYMBOL(bdi_unregister); +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); + setup_timer(&wb->wakeup_timer, wakeup_timer_fn, (unsigned long)bdi); +} + int bdi_init(struct backing_dev_info *bdi) { int i, err; -- cgit v1.2.3 From 81d73a32d775ae9674ea6edf0b5b721fc3bc57d9 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Wed, 11 Aug 2010 14:17:44 -0700 Subject: mm: fix writeback_in_progress() Commit 83ba7b071f3 ("writeback: simplify the write back thread queue") broke writeback_in_progress() as in that commit we started to remove work items from the list at the moment we start working on them and not at the moment they are finished. Thus if the flusher thread was doing some work but there was no other work queued, writeback_in_progress() returned false. This could in particular cause unnecessary queueing of background writeback from balance_dirty_pages() or writeout work from writeback_sb_if_idle(). This patch fixes the problem by introducing a bit in the bdi state which indicates that the flusher thread is processing some work and uses this bit for writeback_in_progress() test. NOTE: Both callsites of writeback_in_progress() (namely, writeback_inodes_sb_if_idle() and balance_dirty_pages()) would actually need a different information than what writeback_in_progress() provides. They would need to know whether *the kind of writeback they are going to submit* is already queued. But this information isn't that simple to provide so let's fix writeback_in_progress() for the time being. Signed-off-by: Jan Kara Cc: Christoph Hellwig Cc: Wu Fengguang Acked-by: Jens Axboe Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/fs-writeback.c | 4 +++- include/linux/backing-dev.h | 1 + 2 files changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux/backing-dev.h') diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 8a5807d2fb9d..7d9d06ba184b 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -68,7 +68,7 @@ int nr_pdflush_threads; */ int writeback_in_progress(struct backing_dev_info *bdi) { - return !list_empty(&bdi->work_list); + return test_bit(BDI_writeback_running, &bdi->state); } static void bdi_queue_work(struct backing_dev_info *bdi, @@ -740,6 +740,7 @@ long wb_do_writeback(struct bdi_writeback *wb, int force_wait) struct wb_writeback_work *work; long wrote = 0; + set_bit(BDI_writeback_running, &wb->bdi->state); while ((work = get_next_work_item(bdi)) != NULL) { /* * Override sync mode, in case we must wait for completion @@ -766,6 +767,7 @@ long wb_do_writeback(struct bdi_writeback *wb, int force_wait) * Check for periodic writeback, kupdated() style */ wrote += wb_check_old_data_flush(wb); + clear_bit(BDI_writeback_running, &wb->bdi->state); return wrote; } diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 7628219e5386..35b00746c712 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -31,6 +31,7 @@ enum bdi_state { BDI_async_congested, /* The async (write) queue is getting full */ BDI_sync_congested, /* The sync queue is getting full */ BDI_registered, /* bdi_register() was done */ + BDI_writeback_running, /* Writeback is in progress */ BDI_unused, /* Available bits start here */ }; -- cgit v1.2.3 From 0e093d99763eb4cea09f8ca4f1d01f34e121d10b Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Tue, 26 Oct 2010 14:21:45 -0700 Subject: writeback: do not sleep on the congestion queue if there are no congested BDIs or if significant congestion is not being encountered in the current zone If congestion_wait() is called with no BDI congested, the caller will sleep for the full timeout and this may be an unnecessary sleep. This patch adds a wait_iff_congested() that checks congestion and only sleeps if a BDI is congested else, it calls cond_resched() to ensure the caller is not hogging the CPU longer than its quota but otherwise will not sleep. This is aimed at reducing some of the major desktop stalls reported during IO. For example, while kswapd is operating, it calls congestion_wait() but it could just have been reclaiming clean page cache pages with no congestion. Without this patch, it would sleep for a full timeout but after this patch, it'll just call schedule() if it has been on the CPU too long. Similar logic applies to direct reclaimers that are not making enough progress. Signed-off-by: Mel Gorman Cc: Johannes Weiner Cc: Minchan Kim Cc: Wu Fengguang Cc: KAMEZAWA Hiroyuki Cc: KOSAKI Motohiro Cc: Rik van Riel Cc: Jens Axboe Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/backing-dev.h | 2 +- include/linux/mmzone.h | 8 ++++++ include/trace/events/writeback.h | 7 +++++ mm/backing-dev.c | 61 ++++++++++++++++++++++++++++++++++++++-- mm/page_alloc.c | 4 +-- mm/vmscan.c | 42 ++++++++++++++++++++++----- 6 files changed, 112 insertions(+), 12 deletions(-) (limited to 'include/linux/backing-dev.h') diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 35b00746c712..f1b402a50679 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -285,7 +285,7 @@ enum { void clear_bdi_congested(struct backing_dev_info *bdi, int sync); void set_bdi_congested(struct backing_dev_info *bdi, int sync); long congestion_wait(int sync, long timeout); - +long wait_iff_congested(struct zone *zone, int sync, long timeout); static inline bool bdi_cap_writeback_dirty(struct backing_dev_info *bdi) { diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index c3c17fb675ee..39c24ebe9cfd 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -423,6 +423,9 @@ struct zone { typedef enum { ZONE_RECLAIM_LOCKED, /* prevents concurrent reclaim */ ZONE_OOM_LOCKED, /* zone is in OOM killer zonelist */ + ZONE_CONGESTED, /* zone has many dirty pages backed by + * a congested BDI + */ } zone_flags_t; static inline void zone_set_flag(struct zone *zone, zone_flags_t flag) @@ -440,6 +443,11 @@ static inline void zone_clear_flag(struct zone *zone, zone_flags_t flag) clear_bit(flag, &zone->flags); } +static inline int zone_is_reclaim_congested(const struct zone *zone) +{ + return test_bit(ZONE_CONGESTED, &zone->flags); +} + static inline int zone_is_reclaim_locked(const struct zone *zone) { return test_bit(ZONE_RECLAIM_LOCKED, &zone->flags); diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h index d2b2654606ec..89a2b2db4375 100644 --- a/include/trace/events/writeback.h +++ b/include/trace/events/writeback.h @@ -179,6 +179,13 @@ DEFINE_EVENT(writeback_congest_waited_template, writeback_congestion_wait, TP_ARGS(usec_timeout, usec_delayed) ); +DEFINE_EVENT(writeback_congest_waited_template, writeback_wait_iff_congested, + + TP_PROTO(unsigned int usec_timeout, unsigned int usec_delayed), + + TP_ARGS(usec_timeout, usec_delayed) +); + #endif /* _TRACE_WRITEBACK_H */ /* This part must be outside protection */ diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 55627306abe0..5ad3c106606b 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -729,6 +729,7 @@ static wait_queue_head_t congestion_wqh[2] = { __WAIT_QUEUE_HEAD_INITIALIZER(congestion_wqh[0]), __WAIT_QUEUE_HEAD_INITIALIZER(congestion_wqh[1]) }; +static atomic_t nr_bdi_congested[2]; void clear_bdi_congested(struct backing_dev_info *bdi, int sync) { @@ -736,7 +737,8 @@ void clear_bdi_congested(struct backing_dev_info *bdi, int sync) wait_queue_head_t *wqh = &congestion_wqh[sync]; bit = sync ? BDI_sync_congested : BDI_async_congested; - clear_bit(bit, &bdi->state); + if (test_and_clear_bit(bit, &bdi->state)) + atomic_dec(&nr_bdi_congested[sync]); smp_mb__after_clear_bit(); if (waitqueue_active(wqh)) wake_up(wqh); @@ -748,7 +750,8 @@ void set_bdi_congested(struct backing_dev_info *bdi, int sync) enum bdi_state bit; bit = sync ? BDI_sync_congested : BDI_async_congested; - set_bit(bit, &bdi->state); + if (!test_and_set_bit(bit, &bdi->state)) + atomic_inc(&nr_bdi_congested[sync]); } EXPORT_SYMBOL(set_bdi_congested); @@ -779,3 +782,57 @@ long congestion_wait(int sync, long timeout) } EXPORT_SYMBOL(congestion_wait); +/** + * wait_iff_congested - Conditionally wait for a backing_dev to become uncongested or a zone to complete writes + * @zone: A zone to check if it is heavily congested + * @sync: SYNC or ASYNC IO + * @timeout: timeout in jiffies + * + * In the event of a congested backing_dev (any backing_dev) and the given + * @zone has experienced recent congestion, this waits for up to @timeout + * jiffies for either a BDI to exit congestion of the given @sync queue + * or a write to complete. + * + * In the absense of zone congestion, cond_resched() is called to yield + * the processor if necessary but otherwise does not sleep. + * + * The return value is 0 if the sleep is for the full timeout. Otherwise, + * it is the number of jiffies that were still remaining when the function + * returned. return_value == timeout implies the function did not sleep. + */ +long wait_iff_congested(struct zone *zone, int sync, long timeout) +{ + long ret; + unsigned long start = jiffies; + DEFINE_WAIT(wait); + wait_queue_head_t *wqh = &congestion_wqh[sync]; + + /* + * If there is no congestion, or heavy congestion is not being + * encountered in the current zone, yield if necessary instead + * of sleeping on the congestion queue + */ + if (atomic_read(&nr_bdi_congested[sync]) == 0 || + !zone_is_reclaim_congested(zone)) { + cond_resched(); + + /* In case we scheduled, work out time remaining */ + ret = timeout - (jiffies - start); + if (ret < 0) + ret = 0; + + goto out; + } + + /* Sleep until uncongested or a write happens */ + prepare_to_wait(wqh, &wait, TASK_UNINTERRUPTIBLE); + ret = io_schedule_timeout(timeout); + finish_wait(wqh, &wait); + +out: + trace_writeback_wait_iff_congested(jiffies_to_usecs(timeout), + jiffies_to_usecs(jiffies - start)); + + return ret; +} +EXPORT_SYMBOL(wait_iff_congested); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 6a683f819439..b13bc5e5bd7d 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1907,7 +1907,7 @@ __alloc_pages_high_priority(gfp_t gfp_mask, unsigned int order, preferred_zone, migratetype); if (!page && gfp_mask & __GFP_NOFAIL) - congestion_wait(BLK_RW_ASYNC, HZ/50); + wait_iff_congested(preferred_zone, BLK_RW_ASYNC, HZ/50); } while (!page && (gfp_mask & __GFP_NOFAIL)); return page; @@ -2095,7 +2095,7 @@ rebalance: pages_reclaimed += did_some_progress; if (should_alloc_retry(gfp_mask, order, pages_reclaimed)) { /* Wait for some write requests to complete then retry */ - congestion_wait(BLK_RW_ASYNC, HZ/50); + wait_iff_congested(preferred_zone, BLK_RW_ASYNC, HZ/50); goto rebalance; } diff --git a/mm/vmscan.c b/mm/vmscan.c index 130ad0239f52..30fd658bb289 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -401,10 +401,8 @@ static pageout_t pageout(struct page *page, struct address_space *mapping, } if (mapping->a_ops->writepage == NULL) return PAGE_ACTIVATE; - if (!may_write_to_queue(mapping->backing_dev_info, sc)) { - disable_lumpy_reclaim_mode(sc); + if (!may_write_to_queue(mapping->backing_dev_info, sc)) return PAGE_KEEP; - } if (clear_page_dirty_for_io(page)) { int res; @@ -681,11 +679,14 @@ static noinline_for_stack void free_page_list(struct list_head *free_pages) * shrink_page_list() returns the number of reclaimed pages */ static unsigned long shrink_page_list(struct list_head *page_list, + struct zone *zone, struct scan_control *sc) { LIST_HEAD(ret_pages); LIST_HEAD(free_pages); int pgactivate = 0; + unsigned long nr_dirty = 0; + unsigned long nr_congested = 0; unsigned long nr_reclaimed = 0; cond_resched(); @@ -705,6 +706,7 @@ static unsigned long shrink_page_list(struct list_head *page_list, goto keep; VM_BUG_ON(PageActive(page)); + VM_BUG_ON(page_zone(page) != zone); sc->nr_scanned++; @@ -782,6 +784,8 @@ static unsigned long shrink_page_list(struct list_head *page_list, } if (PageDirty(page)) { + nr_dirty++; + if (references == PAGEREF_RECLAIM_CLEAN) goto keep_locked; if (!may_enter_fs) @@ -792,6 +796,7 @@ static unsigned long shrink_page_list(struct list_head *page_list, /* Page is dirty, try to write it out here */ switch (pageout(page, mapping, sc)) { case PAGE_KEEP: + nr_congested++; goto keep_locked; case PAGE_ACTIVATE: goto activate_locked; @@ -902,6 +907,15 @@ keep_lumpy: VM_BUG_ON(PageLRU(page) || PageUnevictable(page)); } + /* + * Tag a zone as congested if all the dirty pages encountered were + * backed by a congested BDI. In this case, reclaimers should just + * back off and wait for congestion to clear because further reclaim + * will encounter the same problem + */ + if (nr_dirty == nr_congested) + zone_set_flag(zone, ZONE_CONGESTED); + free_page_list(&free_pages); list_splice(&ret_pages, page_list); @@ -1386,12 +1400,12 @@ shrink_inactive_list(unsigned long nr_to_scan, struct zone *zone, spin_unlock_irq(&zone->lru_lock); - nr_reclaimed = shrink_page_list(&page_list, sc); + nr_reclaimed = shrink_page_list(&page_list, zone, sc); /* Check if we should syncronously wait for writeback */ if (should_reclaim_stall(nr_taken, nr_reclaimed, priority, sc)) { set_lumpy_reclaim_mode(priority, sc, true); - nr_reclaimed += shrink_page_list(&page_list, sc); + nr_reclaimed += shrink_page_list(&page_list, zone, sc); } local_irq_disable(); @@ -1982,8 +1996,13 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist, /* Take a nap, wait for some writeback to complete */ if (!sc->hibernation_mode && sc->nr_scanned && - priority < DEF_PRIORITY - 2) - congestion_wait(BLK_RW_ASYNC, HZ/10); + priority < DEF_PRIORITY - 2) { + struct zone *preferred_zone; + + first_zones_zonelist(zonelist, gfp_zone(sc->gfp_mask), + NULL, &preferred_zone); + wait_iff_congested(preferred_zone, BLK_RW_ASYNC, HZ/10); + } } out: @@ -2282,6 +2301,15 @@ loop_again: if (!zone_watermark_ok(zone, order, min_wmark_pages(zone), end_zone, 0)) has_under_min_watermark_zone = 1; + } else { + /* + * If a zone reaches its high watermark, + * consider it to be no longer congested. It's + * possible there are dirty pages backed by + * congested BDIs but as pressure is relieved, + * spectulatively avoid congestion waits + */ + zone_clear_flag(zone, ZONE_CONGESTED); } } -- cgit v1.2.3 From 92c09c041f15fc88b35f8628e07639f52e1fbb38 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Tue, 26 Oct 2010 14:22:03 -0700 Subject: mm: declare some external symbols Declare 'bdi_pending_list' and 'tag_pages_for_writeback()' to remove following sparse warnings: mm/backing-dev.c:46:1: warning: symbol 'bdi_pending_list' was not declared. Should it be static? mm/page-writeback.c:825:6: warning: symbol 'tag_pages_for_writeback' was not declared. Should it be static? Signed-off-by: Namhyung Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/backing-dev.h | 1 + include/linux/writeback.h | 2 ++ 2 files changed, 3 insertions(+) (limited to 'include/linux/backing-dev.h') diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index f1b402a50679..4ce34fa937d4 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -111,6 +111,7 @@ void bdi_wakeup_thread_delayed(struct backing_dev_info *bdi); extern spinlock_t bdi_lock; extern struct list_head bdi_list; +extern struct list_head bdi_pending_list; static inline int wb_has_dirty_io(struct bdi_writeback *wb) { diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 72a5d647a5f2..c7299d2ace6b 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -149,6 +149,8 @@ int write_cache_pages(struct address_space *mapping, int do_writepages(struct address_space *mapping, struct writeback_control *wbc); void set_page_dirty_balance(struct page *page, int page_mkwrite); void writeback_set_ratelimit(void); +void tag_pages_for_writeback(struct address_space *mapping, + pgoff_t start, pgoff_t end); /* pdflush.c */ extern int nr_pdflush_threads; /* Global so it can be exported to sysctl -- cgit v1.2.3