From: Dave Chinner <dchinner@xxxxxxxxxx> All the functionality that the inode_lock protected has now been wrapped up in new independent locks and/or functionality. Hence the inode_lock does not serve a purpose any longer and hence can now be removed. Based on work originally done by Nick Piggin. Signed-off-by: Dave Chinner <dchinner@xxxxxxxxxx> --- Documentation/filesystems/Locking | 2 +- Documentation/filesystems/porting | 10 ++++- Documentation/filesystems/vfs.txt | 2 +- fs/buffer.c | 2 +- fs/drop_caches.c | 4 -- fs/fs-writeback.c | 47 ++++----------------- fs/inode.c | 82 ++++--------------------------------- fs/logfs/inode.c | 2 +- fs/notify/inode_mark.c | 11 ++--- fs/notify/mark.c | 1 - fs/notify/vfsmount_mark.c | 1 - fs/ntfs/inode.c | 4 +- fs/ocfs2/inode.c | 2 +- fs/quota/dquot.c | 12 +---- include/linux/fs.h | 2 +- include/linux/writeback.h | 3 - mm/backing-dev.c | 6 --- mm/filemap.c | 6 +- mm/rmap.c | 6 +- 19 files changed, 48 insertions(+), 157 deletions(-) diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking index 2db4283..e92dad2 100644 --- a/Documentation/filesystems/Locking +++ b/Documentation/filesystems/Locking @@ -114,7 +114,7 @@ alloc_inode: destroy_inode: dirty_inode: (must not sleep) write_inode: -drop_inode: !!!inode_lock!!! +drop_inode: !!!i_lock, sb_inode_list_lock!!! evict_inode: put_super: write write_super: read diff --git a/Documentation/filesystems/porting b/Documentation/filesystems/porting index b12c895..ab07213 100644 --- a/Documentation/filesystems/porting +++ b/Documentation/filesystems/porting @@ -299,7 +299,7 @@ be used instead. It gets called whenever the inode is evicted, whether it has remaining links or not. Caller does *not* evict the pagecache or inode-associated metadata buffers; getting rid of those is responsibility of method, as it had been for ->delete_inode(). - ->drop_inode() returns int now; it's called on final iput() with inode_lock + ->drop_inode() returns int now; it's called on final iput() with i_lock held and it returns true if filesystems wants the inode to be dropped. As before, generic_drop_inode() is still the default and it's been updated appropriately. generic_delete_inode() is also alive and it consists simply of return 1. Note that @@ -318,3 +318,11 @@ if it's zero is not *and* *never* *had* *been* enough. Final unlink() and iput( may happen while the inode is in the middle of ->write_inode(); e.g. if you blindly free the on-disk inode, you may end up doing that while ->write_inode() is writing to it. + + +[mandatory] + inode_lock is gone, replaced by fine grained locks. See fs/inode.c +for details of what locks to replace inode_lock with in order to protect +particular things. Most of the time, a filesystem only needs ->i_lock, which +protects *all* the inode state and its membership on lists that was +previously protected with inode_lock. diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt index ed7e5ef..405beb2 100644 --- a/Documentation/filesystems/vfs.txt +++ b/Documentation/filesystems/vfs.txt @@ -246,7 +246,7 @@ or bottom half). should be synchronous or not, not all filesystems check this flag. drop_inode: called when the last access to the inode is dropped, - with the inode_lock spinlock held. + with the i_lock and sb_inode_list_lock spinlock held. This method should be either NULL (normal UNIX filesystem semantics) or "generic_delete_inode" (for filesystems that do not diff --git a/fs/buffer.c b/fs/buffer.c index b5c4153..99a9f8d 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -1145,7 +1145,7 @@ __getblk_slow(struct block_device *bdev, sector_t block, int size) * inode list. * * mark_buffer_dirty() is atomic. It takes bh->b_page->mapping->private_lock, - * mapping->tree_lock and the global inode_lock. + * and mapping->tree_lock. */ void mark_buffer_dirty(struct buffer_head *bh) { diff --git a/fs/drop_caches.c b/fs/drop_caches.c index 00180dc..2105713 100644 --- a/fs/drop_caches.c +++ b/fs/drop_caches.c @@ -16,7 +16,6 @@ static void drop_pagecache_sb(struct super_block *sb, void *unused) { struct inode *inode, *toput_inode = NULL; - spin_lock(&inode_lock); spin_lock(&sb->s_inodes_lock); list_for_each_entry(inode, &sb->s_inodes, i_sb_list) { spin_lock(&inode->i_lock); @@ -28,15 +27,12 @@ static void drop_pagecache_sb(struct super_block *sb, void *unused) iref_locked(inode); spin_unlock(&inode->i_lock); spin_unlock(&sb->s_inodes_lock); - spin_unlock(&inode_lock); invalidate_mapping_pages(inode->i_mapping, 0, -1); iput(toput_inode); toput_inode = inode; - spin_lock(&inode_lock); spin_lock(&sb->s_inodes_lock); } spin_unlock(&sb->s_inodes_lock); - spin_unlock(&inode_lock); iput(toput_inode); } diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 404d449..f8eb27c 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -184,7 +184,7 @@ static void requeue_io(struct inode *inode) static void inode_sync_complete(struct inode *inode) { /* - * Prevent speculative execution through spin_unlock(&inode_lock); + * Prevent speculative execution through spin_unlock(&inode->i_lock); */ smp_mb(); wake_up_bit(&inode->i_state, __I_SYNC); @@ -283,25 +283,21 @@ static void inode_wait_for_writeback(struct inode *inode) wqh = bit_waitqueue(&inode->i_state, __I_SYNC); while (inode->i_state & I_SYNC) { spin_unlock(&inode->i_lock); - spin_unlock(&inode_lock); __wait_on_bit(wqh, &wq, inode_wait, TASK_UNINTERRUPTIBLE); - spin_lock(&inode_lock); spin_lock(&inode->i_lock); } } /* - * Write out an inode's dirty pages. Called under inode_lock. Either the - * caller has ref on the inode (either via iref_locked or via syscall against an fd) - * or the inode has I_WILL_FREE set (via generic_forget_inode) + * Write out an inode's dirty pages. Either the caller has ref on the inode + * (either via iref_locked or via syscall against an fd) or the inode has + * I_WILL_FREE set (via generic_forget_inode) * * If `wait' is set, wait on the writeout. * * The whole writeout design is quite complex and fragile. We want to avoid * starvation of particular inodes when others are being redirtied, prevent * livelocks, etc. - * - * Called under inode_lock. */ static int writeback_single_inode(struct inode *inode, struct writeback_control *wbc) @@ -346,7 +342,6 @@ writeback_single_inode(struct inode *inode, struct writeback_control *wbc) inode->i_state |= I_SYNC; inode->i_state &= ~I_DIRTY_PAGES; spin_unlock(&inode->i_lock); - spin_unlock(&inode_lock); ret = do_writepages(mapping, wbc); @@ -366,12 +361,10 @@ writeback_single_inode(struct inode *inode, struct writeback_control *wbc) * due to delalloc, clear dirty metadata flags right before * write_inode() */ - spin_lock(&inode_lock); spin_lock(&inode->i_lock); dirty = inode->i_state & I_DIRTY; inode->i_state &= ~(I_DIRTY_SYNC | I_DIRTY_DATASYNC); spin_unlock(&inode->i_lock); - spin_unlock(&inode_lock); /* Don't write the inode if only I_DIRTY_PAGES was set */ if (dirty & (I_DIRTY_SYNC | I_DIRTY_DATASYNC)) { int err = write_inode(inode, wbc); @@ -379,7 +372,6 @@ writeback_single_inode(struct inode *inode, struct writeback_control *wbc) ret = err; } - spin_lock(&inode_lock); spin_lock(&inode->i_lock); inode->i_state &= ~I_SYNC; if (!(inode->i_state & I_FREEING)) { @@ -527,10 +519,8 @@ static int writeback_sb_inodes(struct super_block *sb, struct bdi_writeback *wb, redirty_tail(inode); spin_unlock(&wb->b_lock); } - spin_unlock(&inode_lock); iput(inode); cond_resched(); - spin_lock(&inode_lock); spin_lock(&wb->b_lock); if (wbc->nr_to_write <= 0) { wbc->more_io = 1; @@ -550,9 +540,7 @@ void writeback_inodes_wb(struct bdi_writeback *wb, if (!wbc->wb_start) wbc->wb_start = jiffies; /* livelock avoidance */ - spin_lock(&inode_lock); spin_lock(&wb->b_lock); - if (!wbc->for_kupdate || list_empty(&wb->b_io)) queue_io(wb, wbc->older_than_this); @@ -572,7 +560,6 @@ void writeback_inodes_wb(struct bdi_writeback *wb, break; } spin_unlock(&wb->b_lock); - spin_unlock(&inode_lock); /* Leave any unwritten inodes on b_io */ } @@ -581,13 +568,11 @@ static void __writeback_inodes_sb(struct super_block *sb, { WARN_ON(!rwsem_is_locked(&sb->s_umount)); - spin_lock(&inode_lock); spin_lock(&wb->b_lock); if (!wbc->for_kupdate || list_empty(&wb->b_io)) queue_io(wb, wbc->older_than_this); writeback_sb_inodes(sb, wb, wbc, true); spin_unlock(&wb->b_lock); - spin_unlock(&inode_lock); } /* @@ -697,7 +682,6 @@ static long wb_writeback(struct bdi_writeback *wb, * become available for writeback. Otherwise * we'll just busyloop. */ - spin_lock(&inode_lock); if (!list_empty(&wb->b_more_io)) { spin_lock(&wb->b_lock); inode = list_entry(wb->b_more_io.prev, @@ -708,7 +692,6 @@ static long wb_writeback(struct bdi_writeback *wb, inode_wait_for_writeback(inode); spin_unlock(&inode->i_lock); } - spin_unlock(&inode_lock); } return wrote; @@ -971,7 +954,6 @@ void __mark_inode_dirty(struct inode *inode, int flags) if (unlikely(block_dump)) block_dump___mark_inode_dirty(inode); - spin_lock(&inode_lock); spin_lock(&inode->i_lock); if ((inode->i_state & flags) != flags) { const int was_dirty = inode->i_state & I_DIRTY; @@ -1029,8 +1011,6 @@ void __mark_inode_dirty(struct inode *inode, int flags) out_unlock: spin_unlock(&inode->i_lock); out: - spin_unlock(&inode_lock); - if (wakeup_bdi) bdi_wakeup_thread_delayed(bdi); } @@ -1063,7 +1043,6 @@ static void wait_sb_inodes(struct super_block *sb) */ WARN_ON(!rwsem_is_locked(&sb->s_umount)); - spin_lock(&inode_lock); spin_lock(&sb->s_inodes_lock); /* @@ -1086,14 +1065,12 @@ static void wait_sb_inodes(struct super_block *sb) iref_locked(inode); spin_unlock(&inode->i_lock); spin_unlock(&sb->s_inodes_lock); - 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. + * We hold a reference to 'inode' so it couldn't have been + * removed from s_inodes list while we dropped the + * s_inodes_lock. We cannot iput the inode now as we can be + * holding the last reference and we cannot iput it under + * s_inodes_lock. So we keep the reference and iput it later. */ iput(old_inode); old_inode = inode; @@ -1102,11 +1079,9 @@ static void wait_sb_inodes(struct super_block *sb) cond_resched(); - spin_lock(&inode_lock); spin_lock(&sb->s_inodes_lock); } spin_unlock(&sb->s_inodes_lock); - spin_unlock(&inode_lock); iput(old_inode); } @@ -1209,9 +1184,7 @@ int write_inode_now(struct inode *inode, int sync) wbc.nr_to_write = 0; might_sleep(); - spin_lock(&inode_lock); ret = writeback_single_inode(inode, &wbc); - spin_unlock(&inode_lock); if (sync) inode_sync_wait(inode); return ret; @@ -1233,9 +1206,7 @@ int sync_inode(struct inode *inode, struct writeback_control *wbc) { int ret; - spin_lock(&inode_lock); ret = writeback_single_inode(inode, wbc); - spin_unlock(&inode_lock); return ret; } EXPORT_SYMBOL(sync_inode); diff --git a/fs/inode.c b/fs/inode.c index 4ec360e..c778ec4 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -41,11 +41,9 @@ * inode_lru, i_lru * * Lock orders - * inode_lock * inode hash bucket lock * inode->i_lock * - * inode_lock * sb inode lock * inode_lru_lock * wb->b_lock @@ -118,14 +116,6 @@ static inline void spin_unlock_bucket(struct inode_hash_bucket *b) static struct inode_hash_bucket *inode_hashtable __read_mostly; /* - * A simple spinlock to protect the list manipulations. - * - * NOTE! You also have to own the lock if you change - * the i_state of an inode while it is in use.. - */ -DEFINE_SPINLOCK(inode_lock); - -/* * iprune_sem provides exclusion between the kswapd or try_to_free_pages * icache shrinking path, and the umount path. Without this exclusion, * by the time prune_icache calls iput for the inode whose pages it has @@ -357,7 +347,7 @@ static void init_once(void *foo) } /* - * inode_lock must be held + * i_lock must be held */ void iref_locked(struct inode *inode) { @@ -369,11 +359,9 @@ EXPORT_SYMBOL_GPL(iref_locked); void iref(struct inode *inode) { - spin_lock(&inode_lock); spin_lock(&inode->i_lock); iref_locked(inode); spin_unlock(&inode->i_lock); - spin_unlock(&inode_lock); } EXPORT_SYMBOL_GPL(iref); @@ -439,11 +427,9 @@ void __insert_inode_hash(struct inode *inode, unsigned long hashval) struct inode_hash_bucket *b; b = inode_hashtable + hash(inode->i_sb, hashval); - spin_lock(&inode_lock); spin_lock_bucket(b); hlist_bl_add_head(&inode->i_hash, &b->head); spin_unlock_bucket(b); - spin_unlock(&inode_lock); } EXPORT_SYMBOL(__insert_inode_hash); @@ -472,9 +458,7 @@ static void __remove_inode_hash(struct inode *inode) */ void remove_inode_hash(struct inode *inode) { - spin_lock(&inode_lock); __remove_inode_hash(inode); - spin_unlock(&inode_lock); } EXPORT_SYMBOL(remove_inode_hash); @@ -526,12 +510,10 @@ static void dispose_list(struct list_head *head) evict(inode); - spin_lock(&inode_lock); __remove_inode_hash(inode); spin_lock(&inode->i_sb->s_inodes_lock); list_del_init(&inode->i_sb_list); spin_unlock(&inode->i_sb->s_inodes_lock); - spin_unlock(&inode_lock); wake_up_inode(inode); destroy_inode(inode); @@ -558,7 +540,6 @@ static int invalidate_list(struct super_block *sb, struct list_head *head, * change during umount anymore, and because iprune_sem keeps * shrink_icache_memory() away. */ - cond_resched_lock(&inode_lock); cond_resched_lock(&sb->s_inodes_lock); next = next->next; @@ -614,12 +595,10 @@ int invalidate_inodes(struct super_block *sb) LIST_HEAD(throw_away); down_write(&iprune_sem); - spin_lock(&inode_lock); spin_lock(&sb->s_inodes_lock); fsnotify_unmount_inodes(&sb->s_inodes); busy = invalidate_list(sb, &sb->s_inodes, &throw_away); spin_unlock(&sb->s_inodes_lock); - spin_unlock(&inode_lock); dispose_list(&throw_away); up_write(&iprune_sem); @@ -644,7 +623,7 @@ static int can_unuse(struct inode *inode) /* * Scan `goal' inodes on the unused list for freeable ones. They are moved to - * a temporary list and then are freed outside inode_lock by dispose_list(). + * a temporary list and then are freed outside LRU lock by dispose_list(). * * Any inodes which are pinned purely because of attached pagecache have their * pagecache removed. We expect the final iput() on that inode to add it to @@ -662,7 +641,6 @@ static void prune_icache(int nr_to_scan) unsigned long reap = 0; down_read(&iprune_sem); - spin_lock(&inode_lock); spin_lock(&inode_lru_lock); for (nr_scanned = 0; nr_scanned < nr_to_scan; nr_scanned++) { struct inode *inode; @@ -690,12 +668,10 @@ static void prune_icache(int nr_to_scan) iref_locked(inode); spin_unlock(&inode->i_lock); spin_unlock(&inode_lru_lock); - spin_unlock(&inode_lock); if (remove_inode_buffers(inode)) reap += invalidate_mapping_pages(&inode->i_data, 0, -1); iput(inode); - spin_lock(&inode_lock); spin_lock(&inode_lru_lock); spin_lock(&inode->i_lock); @@ -733,7 +709,6 @@ static void prune_icache(int nr_to_scan) else __count_vm_events(PGINODESTEAL, reap); spin_unlock(&inode_lru_lock); - spin_unlock(&inode_lock); dispose_list(&freeable); up_read(&iprune_sem); @@ -854,9 +829,9 @@ __inode_add_to_lists(struct super_block *sb, struct inode_hash_bucket *b, * @inode: inode to mark in use * * When an inode is allocated it needs to be accounted for, added to the in use - * list, the owning superblock and the inode hash. This needs to be done under - * the inode_lock, so export a function to do this rather than the inode lock - * itself. We calculate the hash list to add to here so it is all internal + * list, the owning superblock and the inode hash. + * + * We calculate the hash list to add to here so it is all internal * which requires the caller to have already set up the inode number in the * inode to add. */ @@ -864,9 +839,7 @@ void inode_add_to_lists(struct super_block *sb, struct inode *inode) { struct inode_hash_bucket *b = inode_hashtable + hash(sb, inode->i_ino); - spin_lock(&inode_lock); __inode_add_to_lists(sb, b, inode); - spin_unlock(&inode_lock); } EXPORT_SYMBOL_GPL(inode_add_to_lists); @@ -923,15 +896,11 @@ struct inode *new_inode(struct super_block *sb) { struct inode *inode; - spin_lock_prefetch(&inode_lock); - inode = alloc_inode(sb); if (inode) { - spin_lock(&inode_lock); inode->i_ino = last_ino_get(); inode->i_state = 0; __inode_add_to_lists(sb, NULL, inode); - spin_unlock(&inode_lock); } return inode; } @@ -990,7 +959,6 @@ static struct inode *get_new_inode(struct super_block *sb, if (inode) { struct inode *old; - spin_lock(&inode_lock); /* We released the lock, so.. */ old = find_inode(sb, b, test, data); if (!old) { @@ -999,7 +967,6 @@ static struct inode *get_new_inode(struct super_block *sb, inode->i_state = I_NEW; __inode_add_to_lists(sb, b, inode); - spin_unlock(&inode_lock); /* Return the locked inode with I_NEW set, the * caller is responsible for filling in the contents @@ -1014,7 +981,6 @@ static struct inode *get_new_inode(struct super_block *sb, */ iref_locked(old); spin_unlock(&old->i_lock); - spin_unlock(&inode_lock); destroy_inode(inode); inode = old; wait_on_inode(inode); @@ -1022,7 +988,6 @@ static struct inode *get_new_inode(struct super_block *sb, return inode; set_failed: - spin_unlock(&inode_lock); destroy_inode(inode); return NULL; } @@ -1040,14 +1005,12 @@ static struct inode *get_new_inode_fast(struct super_block *sb, if (inode) { struct inode *old; - spin_lock(&inode_lock); /* We released the lock, so.. */ old = find_inode_fast(sb, b, ino); if (!old) { inode->i_ino = ino; __inode_add_to_lists(sb, b, inode); inode->i_state = I_NEW; - spin_unlock(&inode_lock); /* Return the locked inode with I_NEW set, the * caller is responsible for filling in the contents @@ -1062,7 +1025,6 @@ static struct inode *get_new_inode_fast(struct super_block *sb, */ iref_locked(old); spin_unlock(&old->i_lock); - spin_unlock(&inode_lock); destroy_inode(inode); inode = old; wait_on_inode(inode); @@ -1119,7 +1081,6 @@ ino_t iunique(struct super_block *sb, ino_t max_reserved) static unsigned int counter; ino_t res; - spin_lock(&inode_lock); spin_lock(&unique_lock); do { if (counter <= max_reserved) @@ -1127,7 +1088,6 @@ ino_t iunique(struct super_block *sb, ino_t max_reserved) res = counter++; } while (!test_inode_iunique(sb, res)); spin_unlock(&unique_lock); - spin_unlock(&inode_lock); return res; } @@ -1135,7 +1095,6 @@ EXPORT_SYMBOL(iunique); struct inode *igrab(struct inode *inode) { - spin_lock(&inode_lock); spin_lock(&inode->i_lock); if (!(inode->i_state & (I_FREEING|I_WILL_FREE))) { iref_locked(inode); @@ -1149,7 +1108,6 @@ struct inode *igrab(struct inode *inode) */ inode = NULL; } - spin_unlock(&inode_lock); return inode; } EXPORT_SYMBOL(igrab); @@ -1171,7 +1129,7 @@ EXPORT_SYMBOL(igrab); * * Otherwise NULL is returned. * - * Note, @test is called with the inode_lock held, so can't sleep. + * Note, @test is called with the i_lock held, so can't sleep. */ static struct inode *ifind(struct super_block *sb, struct inode_hash_bucket *b, @@ -1180,17 +1138,14 @@ static struct inode *ifind(struct super_block *sb, { struct inode *inode; - spin_lock(&inode_lock); inode = find_inode(sb, b, test, data); if (inode) { iref_locked(inode); spin_unlock(&inode->i_lock); - spin_unlock(&inode_lock); if (likely(wait)) wait_on_inode(inode); return inode; } - spin_unlock(&inode_lock); return NULL; } @@ -1215,16 +1170,13 @@ static struct inode *ifind_fast(struct super_block *sb, { struct inode *inode; - spin_lock(&inode_lock); inode = find_inode_fast(sb, b, ino); if (inode) { iref_locked(inode); spin_unlock(&inode->i_lock); - spin_unlock(&inode_lock); wait_on_inode(inode); return inode; } - spin_unlock(&inode_lock); return NULL; } @@ -1247,7 +1199,7 @@ static struct inode *ifind_fast(struct super_block *sb, * * Otherwise NULL is returned. * - * Note, @test is called with the inode_lock held, so can't sleep. + * Note, @test is called with the i_lock held, so can't sleep. */ struct inode *ilookup5_nowait(struct super_block *sb, unsigned long hashval, int (*test)(struct inode *, void *), void *data) @@ -1275,7 +1227,7 @@ EXPORT_SYMBOL(ilookup5_nowait); * * Otherwise NULL is returned. * - * Note, @test is called with the inode_lock held, so can't sleep. + * Note, @test is called with the i_lock held, so can't sleep. */ struct inode *ilookup5(struct super_block *sb, unsigned long hashval, int (*test)(struct inode *, void *), void *data) @@ -1326,7 +1278,7 @@ EXPORT_SYMBOL(ilookup); * inode and this is returned locked, hashed, and with the I_NEW flag set. The * file system gets to fill it in before unlocking it via unlock_new_inode(). * - * Note both @test and @set are called with the inode_lock held, so can't sleep. + * Note both @test and @set are called with the i_lock held, so can't sleep. */ struct inode *iget5_locked(struct super_block *sb, unsigned long hashval, int (*test)(struct inode *, void *), @@ -1391,7 +1343,6 @@ int insert_inode_locked(struct inode *inode) while (1) { struct hlist_bl_node *node; struct inode *old = NULL; - spin_lock(&inode_lock); spin_lock_bucket(b); hlist_bl_for_each_entry(old, node, &b->head, i_hash) { if (old->i_ino != ino) @@ -1408,13 +1359,11 @@ int insert_inode_locked(struct inode *inode) if (likely(!node)) { hlist_bl_add_head(&inode->i_hash, &b->head); spin_unlock_bucket(b); - spin_unlock(&inode_lock); return 0; } iref_locked(old); spin_unlock(&old->i_lock); spin_unlock_bucket(b); - spin_unlock(&inode_lock); wait_on_inode(old); if (unlikely(!hlist_bl_unhashed(&old->i_hash))) { iput(old); @@ -1437,7 +1386,6 @@ int insert_inode_locked4(struct inode *inode, unsigned long hashval, struct hlist_bl_node *node; struct inode *old = NULL; - spin_lock(&inode_lock); spin_lock_bucket(b); hlist_bl_for_each_entry(old, node, &b->head, i_hash) { if (old->i_sb != sb) @@ -1454,13 +1402,11 @@ int insert_inode_locked4(struct inode *inode, unsigned long hashval, if (likely(!node)) { hlist_bl_add_head(&inode->i_hash, &b->head); spin_unlock_bucket(b); - spin_unlock(&inode_lock); return 0; } iref_locked(old); spin_unlock(&old->i_lock); spin_unlock_bucket(b); - spin_unlock(&inode_lock); wait_on_inode(old); if (unlikely(!hlist_bl_unhashed(&old->i_hash))) { iput(old); @@ -1523,15 +1469,12 @@ static void iput_final(struct inode *inode) return; } spin_unlock(&inode->i_lock); - spin_unlock(&inode_lock); return; } WARN_ON(inode->i_state & I_NEW); inode->i_state |= I_WILL_FREE; spin_unlock(&inode->i_lock); - spin_unlock(&inode_lock); write_inode_now(inode, 1); - spin_lock(&inode_lock); spin_lock(&inode->i_lock); WARN_ON(inode->i_state & I_NEW); inode->i_state &= ~I_WILL_FREE; @@ -1556,7 +1499,6 @@ static void iput_final(struct inode *inode) list_del_init(&inode->i_sb_list); spin_unlock(&sb->s_inodes_lock); - spin_unlock(&inode_lock); evict(inode); remove_inode_hash(inode); wake_up_inode(inode); @@ -1576,7 +1518,6 @@ static void iput_final(struct inode *inode) void iput(struct inode *inode) { if (inode) { - spin_lock(&inode_lock); spin_lock(&inode->i_lock); BUG_ON(inode->i_state & I_CLEAR); @@ -1586,7 +1527,6 @@ void iput(struct inode *inode) return; } spin_unlock(&inode->i_lock); - spin_lock(&inode_lock); } } EXPORT_SYMBOL(iput); @@ -1766,8 +1706,6 @@ EXPORT_SYMBOL(inode_wait); * It doesn't matter if I_NEW is not set initially, a call to * wake_up_inode() after removing from the hash list will DTRT. * - * This is called with inode_lock held. - * * Called with i_lock held and returns with it dropped. */ static void __wait_on_freeing_inode(struct inode *inode) @@ -1777,10 +1715,8 @@ static void __wait_on_freeing_inode(struct inode *inode) wq = bit_waitqueue(&inode->i_state, __I_NEW); prepare_to_wait(wq, &wait.wait, TASK_UNINTERRUPTIBLE); spin_unlock(&inode->i_lock); - spin_unlock(&inode_lock); schedule(); finish_wait(wq, &wait.wait); - spin_lock(&inode_lock); } static __initdata unsigned long ihash_entries; diff --git a/fs/logfs/inode.c b/fs/logfs/inode.c index d8c71ec..a67b607 100644 --- a/fs/logfs/inode.c +++ b/fs/logfs/inode.c @@ -286,7 +286,7 @@ static int logfs_write_inode(struct inode *inode, struct writeback_control *wbc) return ret; } -/* called with inode_lock held */ +/* called with i_lock held */ static int logfs_drop_inode(struct inode *inode) { struct logfs_super *super = logfs_super(inode->i_sb); diff --git a/fs/notify/inode_mark.c b/fs/notify/inode_mark.c index 8a05213..57c28ae 100644 --- a/fs/notify/inode_mark.c +++ b/fs/notify/inode_mark.c @@ -22,7 +22,7 @@ #include <linux/module.h> #include <linux/mutex.h> #include <linux/spinlock.h> -#include <linux/writeback.h> /* for inode_lock */ +#include <linux/writeback.h> #include <asm/atomic.h> @@ -232,9 +232,8 @@ out: * fsnotify_unmount_inodes - an sb is unmounting. handle any watched inodes. * @list: list of inodes being unmounted (sb->s_inodes) * - * Called with inode_lock held, protecting the unmounting super block's list - * of inodes, and with iprune_mutex held, keeping shrink_icache_memory() at bay. - * We temporarily drop inode_lock, however, and CAN block. + * Called with iprune_mutex held, keeping shrink_icache_memory() at bay. + * sb_inode_list_lock to protect the super block's list of inodes. */ void fsnotify_unmount_inodes(struct list_head *list) { @@ -288,13 +287,12 @@ void fsnotify_unmount_inodes(struct list_head *list) } /* - * We can safely drop inode_lock here because we hold + * We can safely drop sb->s_inodes_lock here because we hold * references on both inode and next_i. Also no new inodes * will be added since the umount has begun. Finally, * iprune_mutex keeps shrink_icache_memory() away. */ spin_unlock(&sb->s_inodes_lock); - spin_unlock(&inode_lock); if (need_iput_tmp) iput(need_iput_tmp); @@ -306,7 +304,6 @@ void fsnotify_unmount_inodes(struct list_head *list) iput(inode); - spin_lock(&inode_lock); spin_lock(&sb->s_inodes_lock); } } diff --git a/fs/notify/mark.c b/fs/notify/mark.c index 325185e..50c0085 100644 --- a/fs/notify/mark.c +++ b/fs/notify/mark.c @@ -91,7 +91,6 @@ #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/srcu.h> -#include <linux/writeback.h> /* for inode_lock */ #include <asm/atomic.h> diff --git a/fs/notify/vfsmount_mark.c b/fs/notify/vfsmount_mark.c index 56772b5..6f8eefe 100644 --- a/fs/notify/vfsmount_mark.c +++ b/fs/notify/vfsmount_mark.c @@ -23,7 +23,6 @@ #include <linux/mount.h> #include <linux/mutex.h> #include <linux/spinlock.h> -#include <linux/writeback.h> /* for inode_lock */ #include <asm/atomic.h> diff --git a/fs/ntfs/inode.c b/fs/ntfs/inode.c index 93622b1..7c530f3 100644 --- a/fs/ntfs/inode.c +++ b/fs/ntfs/inode.c @@ -54,7 +54,7 @@ * * Return 1 if the attributes match and 0 if not. * - * NOTE: This function runs with the inode_lock spin lock held so it is not + * NOTE: This function runs with the i_lock spin lock held so it is not * allowed to sleep. */ int ntfs_test_inode(struct inode *vi, ntfs_attr *na) @@ -98,7 +98,7 @@ int ntfs_test_inode(struct inode *vi, ntfs_attr *na) * * Return 0 on success and -errno on error. * - * NOTE: This function runs with the inode_lock spin lock held so it is not + * NOTE: This function runs with the i_lock spin lock held so it is not * allowed to sleep. (Hence the GFP_ATOMIC allocation.) */ static int ntfs_init_locked_inode(struct inode *vi, ntfs_attr *na) diff --git a/fs/ocfs2/inode.c b/fs/ocfs2/inode.c index eece3e0..65c61e2 100644 --- a/fs/ocfs2/inode.c +++ b/fs/ocfs2/inode.c @@ -1195,7 +1195,7 @@ void ocfs2_evict_inode(struct inode *inode) ocfs2_clear_inode(inode); } -/* Called under inode_lock, with no more references on the +/* Called under i_lock, with no more references on the * struct inode, so it's safe here to check the flags field * and to manipulate i_nlink without any other locks. */ int ocfs2_drop_inode(struct inode *inode) diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index c7b5fc6..533cd95 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -76,7 +76,7 @@ #include <linux/buffer_head.h> #include <linux/capability.h> #include <linux/quotaops.h> -#include <linux/writeback.h> /* for inode_lock, oddly enough.. */ +#include <linux/writeback.h> #include <asm/uaccess.h> @@ -896,7 +896,6 @@ static void add_dquot_ref(struct super_block *sb, int type) int reserved = 0; #endif - spin_lock(&inode_lock); spin_lock(&sb->s_inodes_lock); list_for_each_entry(inode, &sb->s_inodes, i_sb_list) { spin_lock(&inode->i_lock); @@ -914,21 +913,18 @@ static void add_dquot_ref(struct super_block *sb, int type) iref_locked(inode); spin_unlock(&inode->i_lock); spin_unlock(&sb->s_inodes_lock); - spin_unlock(&inode_lock); iput(old_inode); __dquot_initialize(inode, type); /* We hold a reference to 'inode' so it couldn't have been - * removed from s_inodes list while we dropped the inode_lock. + * removed from s_inodes list while we dropped the 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 + * reference and we cannot iput it under the lock. So we * keep the reference and iput it later. */ old_inode = inode; - spin_lock(&inode_lock); spin_lock(&sb->s_inodes_lock); } spin_unlock(&sb->s_inodes_lock); - spin_unlock(&inode_lock); iput(old_inode); #ifdef CONFIG_QUOTA_DEBUG @@ -1009,7 +1005,6 @@ static void remove_dquot_ref(struct super_block *sb, int type, struct inode *inode; int reserved = 0; - spin_lock(&inode_lock); spin_lock(&sb->s_inodes_lock); list_for_each_entry(inode, &sb->s_inodes, i_sb_list) { /* @@ -1025,7 +1020,6 @@ static void remove_dquot_ref(struct super_block *sb, int type, } } spin_unlock(&sb->s_inodes_lock); - spin_unlock(&inode_lock); #ifdef CONFIG_QUOTA_DEBUG if (reserved) { printk(KERN_WARNING "VFS (%s): Writes happened after quota" diff --git a/include/linux/fs.h b/include/linux/fs.h index 54c4e86..453e0b4 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1588,7 +1588,7 @@ struct super_operations { }; /* - * Inode state bits. Protected by inode_lock. + * Inode state bits. Protected by i_lock. * * Three bits determine the dirty state of the inode, I_DIRTY_SYNC, * I_DIRTY_DATASYNC and I_DIRTY_PAGES. diff --git a/include/linux/writeback.h b/include/linux/writeback.h index b182ccc..67be7a2 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -9,9 +9,6 @@ struct backing_dev_info; -extern spinlock_t inode_lock; - - /* * fs/fs-writeback.c */ diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 74e8269..0c0586b 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -73,7 +73,6 @@ static int bdi_debug_stats_show(struct seq_file *m, void *v) struct inode *inode; nr_wb = nr_dirty = nr_io = nr_more_io = 0; - spin_lock(&inode_lock); spin_lock(&wb->b_lock); list_for_each_entry(inode, &wb->b_dirty, i_io) nr_dirty++; @@ -82,7 +81,6 @@ static int bdi_debug_stats_show(struct seq_file *m, void *v) list_for_each_entry(inode, &wb->b_more_io, i_io) nr_more_io++; spin_unlock(&wb->b_lock); - spin_unlock(&inode_lock); global_dirty_limits(&background_thresh, &dirty_thresh); bdi_thresh = bdi_dirty_limit(bdi, dirty_thresh); @@ -695,7 +693,6 @@ void mapping_set_bdi(struct address_space *mapping, if (unlikely(old == bdi)) return; - spin_lock(&inode_lock); bdi_lock_two(bdi, old); if (!list_empty(&inode->i_io)) { struct inode *i; @@ -727,7 +724,6 @@ found: mapping->a_bdi = bdi; spin_unlock(&bdi->wb.b_lock); spin_unlock(&old->wb.b_lock); - spin_unlock(&inode_lock); } EXPORT_SYMBOL(mapping_set_bdi); @@ -743,7 +739,6 @@ void bdi_destroy(struct backing_dev_info *bdi) struct bdi_writeback *dst = &default_backing_dev_info.wb; struct inode *i, *tmp; - spin_lock(&inode_lock); bdi_lock_two(bdi, &default_backing_dev_info); list_for_each_entry_safe(i, tmp, &bdi->wb.b_dirty, i_io) { list_del(&i->i_io); @@ -762,7 +757,6 @@ void bdi_destroy(struct backing_dev_info *bdi) } spin_unlock(&bdi->wb.b_lock); spin_unlock(&dst->b_lock); - spin_unlock(&inode_lock); } bdi_unregister(bdi); diff --git a/mm/filemap.c b/mm/filemap.c index 454d5ec..857fb34 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -80,7 +80,7 @@ * ->i_mutex * ->i_alloc_sem (various) * - * ->inode_lock + * ->i_lock * ->sb_lock (fs/fs-writeback.c) * ->mapping->tree_lock (__sync_single_inode) * @@ -98,8 +98,8 @@ * ->zone.lru_lock (check_pte_range->isolate_lru_page) * ->private_lock (page_remove_rmap->set_page_dirty) * ->tree_lock (page_remove_rmap->set_page_dirty) - * ->inode_lock (page_remove_rmap->set_page_dirty) - * ->inode_lock (zap_pte_range->set_page_dirty) + * ->i_lock (page_remove_rmap->set_page_dirty) + * ->i_lock (zap_pte_range->set_page_dirty) * ->private_lock (zap_pte_range->__set_page_dirty_buffers) * * ->task->proc_lock diff --git a/mm/rmap.c b/mm/rmap.c index 92e6757..dbfccae 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -31,11 +31,11 @@ * swap_lock (in swap_duplicate, swap_info_get) * mmlist_lock (in mmput, drain_mmlist and others) * mapping->private_lock (in __set_page_dirty_buffers) - * inode_lock (in set_page_dirty's __mark_inode_dirty) - * sb_lock (within inode_lock in fs/fs-writeback.c) + * i_lock (in set_page_dirty's __mark_inode_dirty) + * sb_lock (within i_lock in fs/fs-writeback.c) * mapping->tree_lock (widely used, in set_page_dirty, * in arch-dependent flush_dcache_mmap_lock, - * within inode_lock in __sync_single_inode) + * within i_lock in __sync_single_inode) * * (code doesn't rely on that order so it could be switched around) * ->tasklist_lock -- 1.7.1 -- To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html