From 7ccf19a8042e343f8159f8a5fdd6a9422aa90c78 Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Thu, 21 Oct 2010 11:49:30 +1100 Subject: [PATCH] fs: inode split IO and LRU lists The use of the same inode list structure (inode->i_list) for two different list constructs with different lifecycles and purposes makes it impossible to separate the locking of the different operations. Therefore, to enable the separation of the locking of the writeback and reclaim lists, split the inode->i_list into two separate lists dedicated to their specific tracking functions. Signed-off-by: Nick Piggin Signed-off-by: Dave Chinner Reviewed-by: Christoph Hellwig Signed-off-by: Al Viro --- fs/block_dev.c | 2 +- fs/fs-writeback.c | 35 +++++++++++++++--------------- fs/inode.c | 53 +++++++++++++++++++++++++++++----------------- include/linux/fs.h | 3 ++- mm/backing-dev.c | 6 +++--- 5 files changed, 58 insertions(+), 41 deletions(-) diff --git a/fs/block_dev.c b/fs/block_dev.c index 4e847e53051f..dea3b628a6ce 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -59,7 +59,7 @@ static void bdev_inode_switch_bdi(struct inode *inode, spin_lock(&inode_lock); inode->i_data.backing_dev_info = dst; if (inode->i_state & I_DIRTY) - list_move(&inode->i_list, &dst->wb.b_dirty); + list_move(&inode->i_wb_list, &dst->wb.b_dirty); spin_unlock(&inode_lock); } diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index e8f65290e836..7a24cc957f05 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -79,6 +79,11 @@ static inline struct backing_dev_info *inode_to_bdi(struct inode *inode) return sb->s_bdi; } +static inline struct inode *wb_inode(struct list_head *head) +{ + return list_entry(head, struct inode, i_wb_list); +} + static void bdi_queue_work(struct backing_dev_info *bdi, struct wb_writeback_work *work) { @@ -172,11 +177,11 @@ static void redirty_tail(struct inode *inode) if (!list_empty(&wb->b_dirty)) { struct inode *tail; - tail = list_entry(wb->b_dirty.next, struct inode, i_list); + tail = wb_inode(wb->b_dirty.next); if (time_before(inode->dirtied_when, tail->dirtied_when)) inode->dirtied_when = jiffies; } - list_move(&inode->i_list, &wb->b_dirty); + list_move(&inode->i_wb_list, &wb->b_dirty); } /* @@ -186,7 +191,7 @@ static void requeue_io(struct inode *inode) { struct bdi_writeback *wb = &inode_to_bdi(inode)->wb; - list_move(&inode->i_list, &wb->b_more_io); + list_move(&inode->i_wb_list, &wb->b_more_io); } static void inode_sync_complete(struct inode *inode) @@ -227,14 +232,14 @@ static void move_expired_inodes(struct list_head *delaying_queue, int do_sb_sort = 0; while (!list_empty(delaying_queue)) { - inode = list_entry(delaying_queue->prev, struct inode, i_list); + inode = wb_inode(delaying_queue->prev); if (older_than_this && inode_dirtied_after(inode, *older_than_this)) break; if (sb && sb != inode->i_sb) do_sb_sort = 1; sb = inode->i_sb; - list_move(&inode->i_list, &tmp); + list_move(&inode->i_wb_list, &tmp); } /* just one sb in list, splice to dispatch_queue and we're done */ @@ -245,12 +250,11 @@ static void move_expired_inodes(struct list_head *delaying_queue, /* Move inodes from one superblock together */ while (!list_empty(&tmp)) { - inode = list_entry(tmp.prev, struct inode, i_list); - sb = inode->i_sb; + sb = wb_inode(tmp.prev)->i_sb; list_for_each_prev_safe(pos, node, &tmp) { - inode = list_entry(pos, struct inode, i_list); + inode = wb_inode(pos); if (inode->i_sb == sb) - list_move(&inode->i_list, dispatch_queue); + list_move(&inode->i_wb_list, dispatch_queue); } } } @@ -414,7 +418,7 @@ writeback_single_inode(struct inode *inode, struct writeback_control *wbc) * a reference to the inode or it's on it's way out. * No need to add it back to the LRU. */ - list_del_init(&inode->i_list); + list_del_init(&inode->i_wb_list); } } inode_sync_complete(inode); @@ -462,8 +466,7 @@ static int writeback_sb_inodes(struct super_block *sb, struct bdi_writeback *wb, { while (!list_empty(&wb->b_io)) { long pages_skipped; - struct inode *inode = list_entry(wb->b_io.prev, - struct inode, i_list); + struct inode *inode = wb_inode(wb->b_io.prev); if (inode->i_sb != sb) { if (only_this_sb) { @@ -533,8 +536,7 @@ void writeback_inodes_wb(struct bdi_writeback *wb, queue_io(wb, wbc->older_than_this); while (!list_empty(&wb->b_io)) { - struct inode *inode = list_entry(wb->b_io.prev, - struct inode, i_list); + struct inode *inode = wb_inode(wb->b_io.prev); struct super_block *sb = inode->i_sb; if (!pin_sb_for_writeback(sb)) { @@ -672,8 +674,7 @@ static long wb_writeback(struct bdi_writeback *wb, */ spin_lock(&inode_lock); if (!list_empty(&wb->b_more_io)) { - inode = list_entry(wb->b_more_io.prev, - struct inode, i_list); + inode = wb_inode(wb->b_more_io.prev); trace_wbc_writeback_wait(&wbc, wb->bdi); inode_wait_for_writeback(inode); } @@ -987,7 +988,7 @@ void __mark_inode_dirty(struct inode *inode, int flags) } inode->dirtied_when = jiffies; - list_move(&inode->i_list, &bdi->wb.b_dirty); + list_move(&inode->i_wb_list, &bdi->wb.b_dirty); } } out: diff --git a/fs/inode.c b/fs/inode.c index 4bedac32154f..09e2d7a5f1d2 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -71,7 +71,7 @@ static unsigned int i_hash_shift __read_mostly; * allowing for low-overhead inode sync() operations. */ -static LIST_HEAD(inode_unused); +static LIST_HEAD(inode_lru); static struct hlist_head *inode_hashtable __read_mostly; /* @@ -271,6 +271,7 @@ EXPORT_SYMBOL(__destroy_inode); static void destroy_inode(struct inode *inode) { + BUG_ON(!list_empty(&inode->i_lru)); __destroy_inode(inode); if (inode->i_sb->s_op->destroy_inode) inode->i_sb->s_op->destroy_inode(inode); @@ -289,7 +290,8 @@ void inode_init_once(struct inode *inode) INIT_HLIST_NODE(&inode->i_hash); INIT_LIST_HEAD(&inode->i_dentry); INIT_LIST_HEAD(&inode->i_devices); - INIT_LIST_HEAD(&inode->i_list); + INIT_LIST_HEAD(&inode->i_wb_list); + INIT_LIST_HEAD(&inode->i_lru); INIT_RADIX_TREE(&inode->i_data.page_tree, GFP_ATOMIC); spin_lock_init(&inode->i_data.tree_lock); spin_lock_init(&inode->i_data.i_mmap_lock); @@ -330,16 +332,16 @@ EXPORT_SYMBOL(ihold); static void inode_lru_list_add(struct inode *inode) { - if (list_empty(&inode->i_list)) { - list_add(&inode->i_list, &inode_unused); + if (list_empty(&inode->i_lru)) { + list_add(&inode->i_lru, &inode_lru); percpu_counter_inc(&nr_inodes_unused); } } static void inode_lru_list_del(struct inode *inode) { - if (!list_empty(&inode->i_list)) { - list_del_init(&inode->i_list); + if (!list_empty(&inode->i_lru)) { + list_del_init(&inode->i_lru); percpu_counter_dec(&nr_inodes_unused); } } @@ -460,8 +462,8 @@ static void dispose_list(struct list_head *head) while (!list_empty(head)) { struct inode *inode; - inode = list_first_entry(head, struct inode, i_list); - list_del_init(&inode->i_list); + inode = list_first_entry(head, struct inode, i_lru); + list_del_init(&inode->i_lru); evict(inode); @@ -507,8 +509,14 @@ static int invalidate_list(struct list_head *head, struct list_head *dispose) continue; } - list_move(&inode->i_list, dispose); inode->i_state |= I_FREEING; + + /* + * Move the inode off the IO lists and LRU once I_FREEING is + * set so that it won't get moved back on there if it is dirty. + */ + list_move(&inode->i_lru, dispose); + list_del_init(&inode->i_wb_list); if (!(inode->i_state & (I_DIRTY | I_SYNC))) percpu_counter_dec(&nr_inodes_unused); } @@ -580,10 +588,10 @@ static void prune_icache(int nr_to_scan) for (nr_scanned = 0; nr_scanned < nr_to_scan; nr_scanned++) { struct inode *inode; - if (list_empty(&inode_unused)) + if (list_empty(&inode_lru)) break; - inode = list_entry(inode_unused.prev, struct inode, i_list); + inode = list_entry(inode_lru.prev, struct inode, i_lru); /* * Referenced or dirty inodes are still in use. Give them @@ -591,14 +599,14 @@ static void prune_icache(int nr_to_scan) */ if (atomic_read(&inode->i_count) || (inode->i_state & ~I_REFERENCED)) { - list_del_init(&inode->i_list); + list_del_init(&inode->i_lru); percpu_counter_dec(&nr_inodes_unused); continue; } /* recently referenced inodes get one more pass */ if (inode->i_state & I_REFERENCED) { - list_move(&inode->i_list, &inode_unused); + list_move(&inode->i_lru, &inode_lru); inode->i_state &= ~I_REFERENCED; continue; } @@ -611,15 +619,21 @@ static void prune_icache(int nr_to_scan) iput(inode); spin_lock(&inode_lock); - if (inode != list_entry(inode_unused.next, - struct inode, i_list)) + if (inode != list_entry(inode_lru.next, + struct inode, i_lru)) continue; /* wrong inode or list_empty */ if (!can_unuse(inode)) continue; } - list_move(&inode->i_list, &freeable); WARN_ON(inode->i_state & I_NEW); inode->i_state |= I_FREEING; + + /* + * Move the inode off the IO lists and LRU once I_FREEING is + * set so that it won't get moved back on there if it is dirty. + */ + list_move(&inode->i_lru, &freeable); + list_del_init(&inode->i_wb_list); percpu_counter_dec(&nr_inodes_unused); } if (current_is_kswapd()) @@ -1340,15 +1354,16 @@ static void iput_final(struct inode *inode) inode->i_state &= ~I_WILL_FREE; __remove_inode_hash(inode); } + WARN_ON(inode->i_state & I_NEW); inode->i_state |= I_FREEING; /* - * After we delete the inode from the LRU here, we avoid moving dirty - * inodes back onto the LRU now because I_FREEING is set and hence - * writeback_single_inode() won't move the inode around. + * Move the inode off the IO lists and LRU once I_FREEING is + * set so that it won't get moved back on there if it is dirty. */ inode_lru_list_del(inode); + list_del_init(&inode->i_wb_list); __inode_sb_list_del(inode); spin_unlock(&inode_lock); diff --git a/include/linux/fs.h b/include/linux/fs.h index d58059944801..f300a6508818 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -723,7 +723,8 @@ struct posix_acl; struct inode { struct hlist_node i_hash; - struct list_head i_list; /* backing dev IO list */ + struct list_head i_wb_list; /* backing dev IO list */ + struct list_head i_lru; /* inode LRU list */ struct list_head i_sb_list; struct list_head i_dentry; unsigned long i_ino; diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 65d420499a61..15d5097de821 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -74,11 +74,11 @@ static int bdi_debug_stats_show(struct seq_file *m, void *v) nr_wb = nr_dirty = nr_io = nr_more_io = 0; spin_lock(&inode_lock); - list_for_each_entry(inode, &wb->b_dirty, i_list) + list_for_each_entry(inode, &wb->b_dirty, i_wb_list) nr_dirty++; - list_for_each_entry(inode, &wb->b_io, i_list) + list_for_each_entry(inode, &wb->b_io, i_wb_list) nr_io++; - list_for_each_entry(inode, &wb->b_more_io, i_list) + list_for_each_entry(inode, &wb->b_more_io, i_wb_list) nr_more_io++; spin_unlock(&inode_lock);