From: Dave Chinner <dchinner@xxxxxxxxxx> Protect the inode hash lists with a new global lock inode_hash_lock and use it to protect the list manipulations and traversals. This lock replaces the inode_lock as the inodes on the list can be validity checked while holding the inode->i_lock and hence the inode_lock is no longer needed to protect the lists. Signed-off-by: Dave Chinner <dchinner@xxxxxxxxxx> --- fs/inode.c | 69 ++++++++++++++++++++++++++++++++++------------------------- 1 files changed, 40 insertions(+), 29 deletions(-) diff --git a/fs/inode.c b/fs/inode.c index 130aa74..738ba4e 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -37,6 +37,8 @@ * sb->s_inodes, inode->i_sb_list * inode_sb_list_lock protects: * bdi->wb.b_{dirty,io,more_io}, inode->i_wb_list + * inode_hash_lock protects: + * inode_hashtable, inode->i_hash * * Lock ordering: * inode_lock @@ -48,6 +50,12 @@ * * inode_wb_list_lock * inode->i_lock + * + * inode_hash_lock + * inode->i_lock + * + * iunique_lock + * inode_hash_lock */ /* @@ -83,6 +91,8 @@ static unsigned int i_hash_mask __read_mostly; static unsigned int i_hash_shift __read_mostly; +static struct hlist_head *inode_hashtable __read_mostly; +static __cacheline_aligned_in_smp DEFINE_SPINLOCK(inode_hash_lock); /* * Each inode can be on two separate lists. One is @@ -98,7 +108,6 @@ static unsigned int i_hash_shift __read_mostly; static LIST_HEAD(inode_lru); static DEFINE_SPINLOCK(inode_lru_lock); -static struct hlist_head *inode_hashtable __read_mostly; /* * A simple spinlock to protect the list manipulations. @@ -420,9 +429,9 @@ void __insert_inode_hash(struct inode *inode, unsigned long hashval) { struct hlist_head *b = inode_hashtable + hash(inode->i_sb, hashval); - spin_lock(&inode_lock); + spin_lock(&inode_hash_lock); hlist_add_head(&inode->i_hash, b); - spin_unlock(&inode_lock); + spin_unlock(&inode_hash_lock); } EXPORT_SYMBOL(__insert_inode_hash); @@ -434,9 +443,9 @@ EXPORT_SYMBOL(__insert_inode_hash); */ void remove_inode_hash(struct inode *inode) { - spin_lock(&inode_lock); + spin_lock(&inode_hash_lock); hlist_del_init(&inode->i_hash); - spin_unlock(&inode_lock); + spin_unlock(&inode_hash_lock); } EXPORT_SYMBOL(remove_inode_hash); @@ -914,7 +923,7 @@ static struct inode *get_new_inode(struct super_block *sb, if (inode) { struct inode *old; - spin_lock(&inode_lock); + spin_lock(&inode_hash_lock); /* We released the lock, so.. */ old = find_inode(sb, head, test, data); if (!old) { @@ -925,8 +934,8 @@ static struct inode *get_new_inode(struct super_block *sb, inode->i_state = I_NEW; spin_unlock(&inode->i_lock); hlist_add_head(&inode->i_hash, head); + spin_unlock(&inode_hash_lock); inode_sb_list_add(inode); - spin_unlock(&inode_lock); /* Return the locked inode with I_NEW set, the * caller is responsible for filling in the contents @@ -939,7 +948,7 @@ static struct inode *get_new_inode(struct super_block *sb, * us. Use the old inode instead of the one we just * allocated. */ - spin_unlock(&inode_lock); + spin_unlock(&inode_hash_lock); destroy_inode(inode); inode = old; wait_on_inode(inode); @@ -947,7 +956,7 @@ static struct inode *get_new_inode(struct super_block *sb, return inode; set_failed: - spin_unlock(&inode_lock); + spin_unlock(&inode_hash_lock); destroy_inode(inode); return NULL; } @@ -965,7 +974,7 @@ static struct inode *get_new_inode_fast(struct super_block *sb, if (inode) { struct inode *old; - spin_lock(&inode_lock); + spin_lock(&inode_hash_lock); /* We released the lock, so.. */ old = find_inode_fast(sb, head, ino); if (!old) { @@ -974,8 +983,8 @@ static struct inode *get_new_inode_fast(struct super_block *sb, inode->i_state = I_NEW; spin_unlock(&inode->i_lock); hlist_add_head(&inode->i_hash, head); + spin_unlock(&inode_hash_lock); inode_sb_list_add(inode); - spin_unlock(&inode_lock); /* Return the locked inode with I_NEW set, the * caller is responsible for filling in the contents @@ -988,7 +997,7 @@ static struct inode *get_new_inode_fast(struct super_block *sb, * us. Use the old inode instead of the one we just * allocated. */ - spin_unlock(&inode_lock); + spin_unlock(&inode_hash_lock); destroy_inode(inode); inode = old; wait_on_inode(inode); @@ -1009,10 +1018,14 @@ static int test_inode_iunique(struct super_block *sb, unsigned long ino) struct hlist_node *node; struct inode *inode; + spin_lock(&inode_hash_lock); hlist_for_each_entry(inode, node, b, i_hash) { - if (inode->i_ino == ino && inode->i_sb == sb) + if (inode->i_ino == ino && inode->i_sb == sb) { + spin_unlock(&inode_hash_lock); return 0; + } } + spin_unlock(&inode_hash_lock); return 1; } @@ -1042,7 +1055,6 @@ ino_t iunique(struct super_block *sb, ino_t max_reserved) static unsigned int counter; ino_t res; - spin_lock(&inode_lock); spin_lock(&iunique_lock); do { if (counter <= max_reserved) @@ -1050,7 +1062,6 @@ ino_t iunique(struct super_block *sb, ino_t max_reserved) res = counter++; } while (!test_inode_iunique(sb, res)); spin_unlock(&iunique_lock); - spin_unlock(&inode_lock); return res; } @@ -1102,15 +1113,15 @@ static struct inode *ifind(struct super_block *sb, { struct inode *inode; - spin_lock(&inode_lock); + spin_lock(&inode_hash_lock); inode = find_inode(sb, head, test, data); if (inode) { - spin_unlock(&inode_lock); + spin_unlock(&inode_hash_lock); if (likely(wait)) wait_on_inode(inode); return inode; } - spin_unlock(&inode_lock); + spin_unlock(&inode_hash_lock); return NULL; } @@ -1134,14 +1145,14 @@ static struct inode *ifind_fast(struct super_block *sb, { struct inode *inode; - spin_lock(&inode_lock); + spin_lock(&inode_hash_lock); inode = find_inode_fast(sb, head, ino); if (inode) { - spin_unlock(&inode_lock); + spin_unlock(&inode_hash_lock); wait_on_inode(inode); return inode; } - spin_unlock(&inode_lock); + spin_unlock(&inode_hash_lock); return NULL; } @@ -1306,7 +1317,7 @@ int insert_inode_locked(struct inode *inode) while (1) { struct hlist_node *node; struct inode *old = NULL; - spin_lock(&inode_lock); + spin_lock(&inode_hash_lock); hlist_for_each_entry(old, node, head, i_hash) { if (old->i_ino != ino) continue; @@ -1321,12 +1332,12 @@ int insert_inode_locked(struct inode *inode) } if (likely(!node)) { hlist_add_head(&inode->i_hash, head); - spin_unlock(&inode_lock); + spin_unlock(&inode_hash_lock); return 0; } __iget(old); spin_unlock(&old->i_lock); - spin_unlock(&inode_lock); + spin_unlock(&inode_hash_lock); wait_on_inode(old); if (unlikely(!inode_unhashed(old))) { iput(old); @@ -1351,7 +1362,7 @@ int insert_inode_locked4(struct inode *inode, unsigned long hashval, struct hlist_node *node; struct inode *old = NULL; - spin_lock(&inode_lock); + spin_lock(&inode_hash_lock); hlist_for_each_entry(old, node, head, i_hash) { if (old->i_sb != sb) continue; @@ -1366,12 +1377,12 @@ int insert_inode_locked4(struct inode *inode, unsigned long hashval, } if (likely(!node)) { hlist_add_head(&inode->i_hash, head); - spin_unlock(&inode_lock); + spin_unlock(&inode_hash_lock); return 0; } __iget(old); spin_unlock(&old->i_lock); - spin_unlock(&inode_lock); + spin_unlock(&inode_hash_lock); wait_on_inode(old); if (unlikely(!inode_unhashed(old))) { iput(old); @@ -1651,10 +1662,10 @@ 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); + spin_unlock(&inode_hash_lock); schedule(); finish_wait(wq, &wait.wait); - spin_lock(&inode_lock); + spin_lock(&inode_hash_lock); } static __initdata unsigned long ihash_entries; -- 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