fs-inode_lock-scale-3

Protect i_state updates with i_lock

Signed-off-by: Nick Piggin <npiggin@suse.de>
Signed-off-by: John Stultz <johnstul@us.ibm.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

5 files changed, 115 insertions, 20 deletions

diff --git a/fs/drop_caches.c b/fs/drop_caches.c
index 8b6ef854aacc..16efb486c693 100644
--- a/fs/drop_caches.c
+++ b/fs/drop_caches.c
@@ -19,11 +19,14 @@ static void drop_pagecache_sb(struct super_block *sb)
 	spin_lock(&inode_lock);
 	spin_lock(&sb_inode_list_lock);
 	list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
-		if (inode->i_state & (I_FREEING|I_CLEAR|I_WILL_FREE|I_NEW))
-			continue;
-		if (inode->i_mapping->nrpages == 0)
+		spin_lock(&inode->i_lock);
+		if (inode->i_state & (I_FREEING|I_CLEAR|I_WILL_FREE|I_NEW)
+				|| inode->i_mapping->nrpages == 0) {
+			spin_unlock(&inode->i_lock);
 			continue;
+		}
 		__iget(inode);
+		spin_unlock(&inode->i_lock);
 		spin_unlock(&sb_inode_list_lock);
 		spin_unlock(&inode_lock);
 		invalidate_mapping_pages(inode->i_mapping, 0, -1);
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index f04a95a76b3f..8d57f0e14ebb 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -398,9 +398,11 @@ static void inode_wait_for_writeback(struct inode *inode)
 
 	wqh = bit_waitqueue(&inode->i_state, __I_SYNC);
 	do {
+		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);
 	} while (inode->i_state & I_SYNC);
 }
 
@@ -457,6 +459,7 @@ writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
 	inode->i_state |= I_SYNC;
 	inode->i_state &= ~I_DIRTY;
 
+	spin_unlock(&inode->i_lock);
 	spin_unlock(&inode_lock);
 
 	ret = do_writepages(mapping, wbc);
@@ -475,6 +478,7 @@ writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
 	}
 
 	spin_lock(&inode_lock);
+	spin_lock(&inode->i_lock);
 	inode->i_state &= ~I_SYNC;
 	if (!(inode->i_state & (I_FREEING | I_CLEAR))) {
 		if ((inode->i_state & I_DIRTY_PAGES) && wbc->for_kupdate) {
@@ -635,7 +639,9 @@ static void writeback_inodes_wb(struct bdi_writeback *wb,
 			continue;
 		}
 
+		spin_lock(&inode->i_lock);
 		if (inode->i_state & (I_NEW | I_WILL_FREE)) {
+			spin_unlock(&inode->i_lock);
 			requeue_io(inode);
 			continue;
 		}
@@ -644,10 +650,13 @@ static void writeback_inodes_wb(struct bdi_writeback *wb,
 		 * Was this inode dirtied after sync_sb_inodes was called?
 		 * This keeps sync from extra jobs and livelock.
 		 */
-		if (inode_dirtied_after(inode, start))
+		if (inode_dirtied_after(inode, start)) {
+			spin_unlock(&inode->i_lock);
 			break;
+		}
 
 		if (pin_sb_for_writeback(wbc, inode, &pin_sb)) {
+			spin_unlock(&inode->i_lock);
 			requeue_io(inode);
 			continue;
 		}
@@ -663,6 +672,7 @@ static void writeback_inodes_wb(struct bdi_writeback *wb,
 			 */
 			redirty_tail(inode);
 		}
+		spin_unlock(&inode->i_lock);
 		spin_unlock(&inode_lock);
 		iput(inode);
 		cond_resched();
@@ -1050,6 +1060,7 @@ void __mark_inode_dirty(struct inode *inode, int flags)
 		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;
 
@@ -1094,6 +1105,7 @@ void __mark_inode_dirty(struct inode *inode, int flags)
 		}
 	}
 out:
+	spin_unlock(&inode->i_lock);
 	spin_unlock(&inode_lock);
 }
 EXPORT_SYMBOL(__mark_inode_dirty);
@@ -1138,12 +1150,17 @@ static void wait_sb_inodes(struct super_block *sb)
 	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))
-			continue;
 		mapping = inode->i_mapping;
 		if (mapping->nrpages == 0)
 			continue;
+
+		spin_lock(&inode->i_lock);
+		if (inode->i_state & (I_FREEING|I_CLEAR|I_WILL_FREE|I_NEW)) {
+			spin_unlock(&inode->i_lock);
+			continue;
+		}
 		__iget(inode);
+		spin_unlock(&inode->i_lock);
 		spin_unlock(&sb_inode_list_lock);
 		spin_unlock(&inode_lock);
 		/*
@@ -1247,7 +1264,9 @@ int write_inode_now(struct inode *inode, int sync)
 
 	might_sleep();
 	spin_lock(&inode_lock);
+	spin_lock(&inode->i_lock);
 	ret = writeback_single_inode(inode, &wbc);
+	spin_unlock(&inode->i_lock);
 	spin_unlock(&inode_lock);
 	if (sync)
 		inode_sync_wait(inode);
@@ -1271,7 +1290,9 @@ int sync_inode(struct inode *inode, struct writeback_control *wbc)
 	int ret;
 
 	spin_lock(&inode_lock);
+	spin_lock(&inode->i_lock);
 	ret = writeback_single_inode(inode, wbc);
+	spin_unlock(&inode->i_lock);
 	spin_unlock(&inode_lock);
 	return ret;
 }
diff --git a/fs/inode.c b/fs/inode.c
index d6ad2ab68e93..a1f5c2fa1d4a 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -289,6 +289,7 @@ static void init_once(void *foo)
  */
 void __iget(struct inode *inode)
 {
+	assert_spin_locked(&inode->i_lock);
 	if (atomic_read(&inode->i_count)) {
 		atomic_inc(&inode->i_count);
 		return;
@@ -392,16 +393,21 @@ static int invalidate_list(struct list_head *head, struct list_head *dispose)
 		if (tmp == head)
 			break;
 		inode = list_entry(tmp, struct inode, i_sb_list);
-		if (inode->i_state & I_NEW)
+		spin_lock(&inode->i_lock);
+		if (inode->i_state & I_NEW) {
+			spin_unlock(&inode->i_lock);
 			continue;
+		}
 		invalidate_inode_buffers(inode);
 		if (!atomic_read(&inode->i_count)) {
 			list_move(&inode->i_list, dispose);
 			WARN_ON(inode->i_state & I_NEW);
 			inode->i_state |= I_FREEING;
+			spin_unlock(&inode->i_lock);
 			count++;
 			continue;
 		}
+		spin_unlock(&inode->i_lock);
 		busy = 1;
 	}
 	/* only unused inodes may be cached with i_count zero */
@@ -481,12 +487,15 @@ static void prune_icache(int nr_to_scan)
 
 		inode = list_entry(inode_unused.prev, struct inode, i_list);
 
+		spin_lock(&inode->i_lock);
 		if (inode->i_state || atomic_read(&inode->i_count)) {
 			list_move(&inode->i_list, &inode_unused);
+			spin_unlock(&inode->i_lock);
 			continue;
 		}
 		if (inode_has_buffers(inode) || inode->i_data.nrpages) {
 			__iget(inode);
+			spin_unlock(&inode->i_lock);
 			spin_unlock(&inode_lock);
 			if (remove_inode_buffers(inode))
 				reap += invalidate_mapping_pages(&inode->i_data,
@@ -497,12 +506,16 @@ static void prune_icache(int nr_to_scan)
 			if (inode != list_entry(inode_unused.next,
 						struct inode, i_list))
 				continue;	/* wrong inode or list_empty */
-			if (!can_unuse(inode))
+			spin_lock(&inode->i_lock);
+			if (!can_unuse(inode)) {
+				spin_unlock(&inode->i_lock);
 				continue;
+			}
 		}
 		list_move(&inode->i_list, &freeable);
 		WARN_ON(inode->i_state & I_NEW);
 		inode->i_state |= I_FREEING;
+		spin_unlock(&inode->i_lock);
 		nr_pruned++;
 	}
 	inodes_stat.nr_unused -= nr_pruned;
@@ -565,8 +578,14 @@ repeat:
 	hlist_for_each_entry(inode, node, head, i_hash) {
 		if (inode->i_sb != sb)
 			continue;
-		if (!test(inode, data))
+		if (!spin_trylock(&inode->i_lock)) {
+			spin_unlock(&inode_hash_lock);
+			goto repeat;
+		}
+		if (!test(inode, data)) {
+			spin_unlock(&inode->i_lock);
 			continue;
+		}
 		if (inode->i_state & (I_FREEING|I_CLEAR|I_WILL_FREE)) {
 			spin_unlock(&inode_hash_lock);
 			__wait_on_freeing_inode(inode);
@@ -595,6 +614,10 @@ repeat:
 			continue;
 		if (inode->i_sb != sb)
 			continue;
+		if (!spin_trylock(&inode->i_lock)) {
+			spin_unlock(&inode_hash_lock);
+			goto repeat;
+		}
 		if (inode->i_state & (I_FREEING|I_CLEAR|I_WILL_FREE)) {
 			spin_unlock(&inode_hash_lock);
 			__wait_on_freeing_inode(inode);
@@ -621,10 +644,10 @@ __inode_add_to_lists(struct super_block *sb, struct hlist_head *head,
 			struct inode *inode)
 {
 	inodes_stat.nr_inodes++;
-	list_add(&inode->i_list, &inode_in_use);
 	spin_lock(&sb_inode_list_lock);
 	list_add(&inode->i_sb_list, &sb->s_inodes);
 	spin_unlock(&sb_inode_list_lock);
+	list_add(&inode->i_list, &inode_in_use);
 	if (head) {
 		spin_lock(&inode_hash_lock);
 		hlist_add_head(&inode->i_hash, head);
@@ -681,9 +704,9 @@ struct inode *new_inode(struct super_block *sb)
 	inode = alloc_inode(sb);
 	if (inode) {
 		spin_lock(&inode_lock);
-		__inode_add_to_lists(sb, NULL, inode);
 		inode->i_ino = ++last_ino;
 		inode->i_state = 0;
+		__inode_add_to_lists(sb, NULL, inode);
 		spin_unlock(&inode_lock);
 	}
 	return inode;
@@ -750,8 +773,8 @@ static struct inode *get_new_inode(struct super_block *sb,
 			if (set(inode, data))
 				goto set_failed;
 
-			__inode_add_to_lists(sb, head, inode);
 			inode->i_state = I_NEW;
+			__inode_add_to_lists(sb, head, inode);
 			spin_unlock(&inode_lock);
 
 			/* Return the locked inode with I_NEW set, the
@@ -766,6 +789,7 @@ static struct inode *get_new_inode(struct super_block *sb,
 		 * allocated.
 		 */
 		__iget(old);
+		spin_unlock(&old->i_lock);
 		spin_unlock(&inode_lock);
 		destroy_inode(inode);
 		inode = old;
@@ -774,6 +798,7 @@ static struct inode *get_new_inode(struct super_block *sb,
 	return inode;
 
 set_failed:
+	spin_unlock(&inode->i_lock);
 	spin_unlock(&inode_lock);
 	destroy_inode(inode);
 	return NULL;
@@ -797,8 +822,8 @@ static struct inode *get_new_inode_fast(struct super_block *sb,
 		old = find_inode_fast(sb, head, ino);
 		if (!old) {
 			inode->i_ino = ino;
-			__inode_add_to_lists(sb, head, inode);
 			inode->i_state = I_NEW;
+			__inode_add_to_lists(sb, head, inode);
 			spin_unlock(&inode_lock);
 
 			/* Return the locked inode with I_NEW set, the
@@ -813,6 +838,7 @@ static struct inode *get_new_inode_fast(struct super_block *sb,
 		 * allocated.
 		 */
 		__iget(old);
+		spin_unlock(&old->i_lock);
 		spin_unlock(&inode_lock);
 		destroy_inode(inode);
 		inode = old;
@@ -854,6 +880,7 @@ ino_t iunique(struct super_block *sb, ino_t max_reserved)
 		res = counter++;
 		head = inode_hashtable + hash(sb, res);
 		inode = find_inode_fast(sb, head, res);
+		spin_unlock(&inode->i_lock);
 	} while (inode != NULL);
 	spin_unlock(&inode_lock);
 
@@ -863,7 +890,10 @@ EXPORT_SYMBOL(iunique);
 
 struct inode *igrab(struct inode *inode)
 {
+	struct inode *ret = inode;
+
 	spin_lock(&inode_lock);
+	spin_lock(&inode->i_lock);
 	if (!(inode->i_state & (I_FREEING|I_CLEAR|I_WILL_FREE)))
 		__iget(inode);
 	else
@@ -872,9 +902,11 @@ struct inode *igrab(struct inode *inode)
 		 * called yet, and somebody is calling igrab
 		 * while the inode is getting freed.
 		 */
-		inode = NULL;
+		ret = NULL;
+	spin_unlock(&inode->i_lock);
 	spin_unlock(&inode_lock);
-	return inode;
+
+	return ret;
 }
 EXPORT_SYMBOL(igrab);
 
@@ -907,6 +939,7 @@ static struct inode *ifind(struct super_block *sb,
 	inode = find_inode(sb, head, test, data);
 	if (inode) {
 		__iget(inode);
+		spin_unlock(&inode->i_lock);
 		spin_unlock(&inode_lock);
 		if (likely(wait))
 			wait_on_inode(inode);
@@ -940,6 +973,7 @@ static struct inode *ifind_fast(struct super_block *sb,
 	inode = find_inode_fast(sb, head, ino);
 	if (inode) {
 		__iget(inode);
+		spin_unlock(&inode->i_lock);
 		spin_unlock(&inode_lock);
 		wait_on_inode(inode);
 		return inode;
@@ -1109,6 +1143,7 @@ int insert_inode_locked(struct inode *inode)
 		struct inode *old = NULL;
 
 		spin_lock(&inode_lock);
+repeat:
 		spin_lock(&inode_hash_lock);
 		hlist_for_each_entry(old, node, head, i_hash) {
 			if (old->i_ino != ino)
@@ -1117,6 +1152,10 @@ int insert_inode_locked(struct inode *inode)
 				continue;
 			if (old->i_state & (I_FREEING|I_CLEAR|I_WILL_FREE))
 				continue;
+			if (!spin_trylock(&old->i_lock)) {
+				spin_unlock(&inode_hash_lock);
+				goto repeat;
+			}
 			break;
 		}
 		if (likely(!node)) {
@@ -1127,6 +1166,7 @@ int insert_inode_locked(struct inode *inode)
 		}
 		spin_unlock(&inode_hash_lock);
 		__iget(old);
+		spin_unlock(&old->i_lock);
 		spin_unlock(&inode_lock);
 		wait_on_inode(old);
 		if (unlikely(!hlist_unhashed(&old->i_hash))) {
@@ -1151,6 +1191,7 @@ int insert_inode_locked4(struct inode *inode, unsigned long hashval,
 		struct inode *old = NULL;
 
 		spin_lock(&inode_lock);
+repeat:
 		spin_lock(&inode_hash_lock);
 		hlist_for_each_entry(old, node, head, i_hash) {
 			if (old->i_sb != sb)
@@ -1159,6 +1200,10 @@ int insert_inode_locked4(struct inode *inode, unsigned long hashval,
 				continue;
 			if (old->i_state & (I_FREEING|I_CLEAR|I_WILL_FREE))
 				continue;
+			if (!spin_trylock(&old->i_lock)) {
+				spin_unlock(&inode_hash_lock);
+				goto repeat;
+			}
 			break;
 		}
 		if (likely(!node)) {
@@ -1169,6 +1214,7 @@ int insert_inode_locked4(struct inode *inode, unsigned long hashval,
 		}
 		spin_unlock(&inode_hash_lock);
 		__iget(old);
+		spin_unlock(&old->i_lock);
 		spin_unlock(&inode_lock);
 		wait_on_inode(old);
 		if (unlikely(!hlist_unhashed(&old->i_hash))) {
@@ -1231,12 +1277,14 @@ void generic_delete_inode(struct inode *inode)
 {
 	const struct super_operations *op = inode->i_sb->s_op;
 
-	list_del_init(&inode->i_list);
 	spin_lock(&sb_inode_list_lock);
+	spin_lock(&inode->i_lock);
+	list_del_init(&inode->i_list);
 	list_del_init(&inode->i_sb_list);
 	spin_unlock(&sb_inode_list_lock);
 	WARN_ON(inode->i_state & I_NEW);
 	inode->i_state |= I_FREEING;
+	spin_unlock(&inode->i_lock);
 	inodes_stat.nr_inodes--;
 	spin_unlock(&inode_lock);
 
@@ -1279,19 +1327,27 @@ int generic_detach_inode(struct inode *inode)
 {
 	struct super_block *sb = inode->i_sb;
 
+	spin_lock(&sb_inode_list_lock);
+	spin_lock(&inode->i_lock);
 	if (!hlist_unhashed(&inode->i_hash)) {
 		if (!(inode->i_state & (I_DIRTY|I_SYNC)))
 			list_move(&inode->i_list, &inode_unused);
 		inodes_stat.nr_unused++;
 		if (sb->s_flags & MS_ACTIVE) {
+			spin_unlock(&inode->i_lock);
+			spin_unlock(&sb_inode_list_lock);
 			spin_unlock(&inode_lock);
 			return 0;
 		}
 		WARN_ON(inode->i_state & I_NEW);
 		inode->i_state |= I_WILL_FREE;
+		spin_unlock(&inode->i_lock);
+		spin_unlock(&sb_inode_list_lock);
 		spin_unlock(&inode_lock);
 		write_inode_now(inode, 1);
 		spin_lock(&inode_lock);
+		spin_lock(&sb_inode_list_lock);
+		spin_lock(&inode->i_lock);
 		WARN_ON(inode->i_state & I_NEW);
 		inode->i_state &= ~I_WILL_FREE;
 		inodes_stat.nr_unused--;
@@ -1300,12 +1356,12 @@ int generic_detach_inode(struct inode *inode)
 		spin_unlock(&inode_hash_lock);
 	}
 	list_del_init(&inode->i_list);
-	spin_lock(&sb_inode_list_lock);
 	list_del_init(&inode->i_sb_list);
 	spin_unlock(&sb_inode_list_lock);
 	WARN_ON(inode->i_state & I_NEW);
 	inode->i_state |= I_FREEING;
 	inodes_stat.nr_inodes--;
+	spin_unlock(&inode->i_lock);
 	spin_unlock(&inode_lock);
 	return 1;
 }
@@ -1553,6 +1609,8 @@ EXPORT_SYMBOL(inode_wait);
  * 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)
 {
@@ -1560,6 +1618,7 @@ static void __wait_on_freeing_inode(struct inode *inode)
 	DEFINE_WAIT_BIT(wait, &inode->i_state, __I_NEW);
 	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);
diff --git a/fs/nilfs2/gcdat.c b/fs/nilfs2/gcdat.c
index dd5f7e0a95f6..fa6dd36e2ee1 100644
--- a/fs/nilfs2/gcdat.c
+++ b/fs/nilfs2/gcdat.c
@@ -27,6 +27,7 @@
 #include "page.h"
 #include "mdt.h"
 
+/* XXX: what protects i_state? */
 int nilfs_init_gcdat_inode(struct the_nilfs *nilfs)
 {
 	struct inode *dat = nilfs->ns_dat, *gcdat = nilfs->ns_gc_dat;
diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c
index c2620d25d1ac..3cbb87192d7a 100644
--- a/fs/quota/dquot.c
+++ b/fs/quota/dquot.c
@@ -847,16 +847,27 @@ static void add_dquot_ref(struct super_block *sb, int type)
 	spin_lock(&inode_lock);
 	spin_lock(&sb_inode_list_lock);
 	list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
-		if (inode->i_state & (I_FREEING|I_CLEAR|I_WILL_FREE|I_NEW))
+		spin_lock(&inode->i_lock);
+		if (inode->i_state & (I_FREEING|I_CLEAR|I_WILL_FREE|I_NEW)) {
+			spin_unlock(&inode->i_lock);
 			continue;
+		}
+
 		if (unlikely(inode_get_rsv_space(inode) > 0))
 			reserved = 1;
-		if (!atomic_read(&inode->i_writecount))
+
+		if (!atomic_read(&inode->i_writecount)) {
+			spin_unlock(&inode->i_lock);
 			continue;
-		if (!dqinit_needed(inode, type))
+		}
+
+		if (!dqinit_needed(inode, type)) {
+			spin_unlock(&inode->i_lock);
 			continue;
+		}
 
 		__iget(inode);
+		spin_unlock(&inode->i_lock);
 		spin_unlock(&sb_inode_list_lock);
 		spin_unlock(&inode_lock);