vfs, afs, ext4: Make the inode hash table RCU searchable

Make the inode hash table RCU searchable so that searches that want to
access or modify an inode without taking a ref on that inode can do so
without taking the inode hash table lock.

The main thing this requires is some RCU annotation on the list
manipulation operations.  Inodes are already freed by RCU in most cases.

Users of this interface must take care as the inode may be still under
construction or may be being torn down around them.

There are at least three instances where this can be of use:

 (1) Testing whether the inode number iunique() is going to return is
     currently unique (the iunique_lock is still held).

 (2) Ext4 date stamp updating.

 (3) AFS callback breaking.

Signed-off-by: David Howells <dhowells@redhat.com>
Acked-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
cc: linux-ext4@vger.kernel.org
cc: linux-afs@lists.infradead.org

1 files changed, 96 insertions, 16 deletions

diff --git a/fs/inode.c b/fs/inode.c
index 93d9252a00ab4..b7bd7162c9029 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -497,7 +497,7 @@ void __insert_inode_hash(struct inode *inode, unsigned long hashval)
 
 	spin_lock(&inode_hash_lock);
 	spin_lock(&inode->i_lock);
-	hlist_add_head(&inode->i_hash, b);
+	hlist_add_head_rcu(&inode->i_hash, b);
 	spin_unlock(&inode->i_lock);
 	spin_unlock(&inode_hash_lock);
 }
@@ -513,7 +513,7 @@ void __remove_inode_hash(struct inode *inode)
 {
 	spin_lock(&inode_hash_lock);
 	spin_lock(&inode->i_lock);
-	hlist_del_init(&inode->i_hash);
+	hlist_del_init_rcu(&inode->i_hash);
 	spin_unlock(&inode->i_lock);
 	spin_unlock(&inode_hash_lock);
 }
@@ -1107,7 +1107,7 @@ again:
 	 */
 	spin_lock(&inode->i_lock);
 	inode->i_state |= I_NEW;
-	hlist_add_head(&inode->i_hash, head);
+	hlist_add_head_rcu(&inode->i_hash, head);
 	spin_unlock(&inode->i_lock);
 	if (!creating)
 		inode_sb_list_add(inode);
@@ -1201,7 +1201,7 @@ again:
 			inode->i_ino = ino;
 			spin_lock(&inode->i_lock);
 			inode->i_state = I_NEW;
-			hlist_add_head(&inode->i_hash, head);
+			hlist_add_head_rcu(&inode->i_hash, head);
 			spin_unlock(&inode->i_lock);
 			inode_sb_list_add(inode);
 			spin_unlock(&inode_hash_lock);
@@ -1244,15 +1244,10 @@ static int test_inode_iunique(struct super_block *sb, unsigned long ino)
 	struct hlist_head *b = inode_hashtable + hash(sb, ino);
 	struct inode *inode;
 
-	spin_lock(&inode_hash_lock);
-	hlist_for_each_entry(inode, b, i_hash) {
-		if (inode->i_ino == ino && inode->i_sb == sb) {
-			spin_unlock(&inode_hash_lock);
+	hlist_for_each_entry_rcu(inode, b, i_hash) {
+		if (inode->i_ino == ino && inode->i_sb == sb)
 			return 0;
-		}
 	}
-	spin_unlock(&inode_hash_lock);
-
 	return 1;
 }
 
@@ -1281,6 +1276,7 @@ ino_t iunique(struct super_block *sb, ino_t max_reserved)
 	static unsigned int counter;
 	ino_t res;
 
+	rcu_read_lock();
 	spin_lock(&iunique_lock);
 	do {
 		if (counter <= max_reserved)
@@ -1288,6 +1284,7 @@ ino_t iunique(struct super_block *sb, ino_t max_reserved)
 		res = counter++;
 	} while (!test_inode_iunique(sb, res));
 	spin_unlock(&iunique_lock);
+	rcu_read_unlock();
 
 	return res;
 }
@@ -1456,6 +1453,84 @@ out:
 }
 EXPORT_SYMBOL(find_inode_nowait);
 
+/**
+ * find_inode_rcu - find an inode in the inode cache
+ * @sb:		Super block of file system to search
+ * @hashval:	Key to hash
+ * @test:	Function to test match on an inode
+ * @data:	Data for test function
+ *
+ * Search for the inode specified by @hashval and @data in the inode cache,
+ * where the helper function @test will return 0 if the inode does not match
+ * and 1 if it does.  The @test function must be responsible for taking the
+ * i_lock spin_lock and checking i_state for an inode being freed or being
+ * initialized.
+ *
+ * If successful, this will return the inode for which the @test function
+ * returned 1 and NULL otherwise.
+ *
+ * The @test function is not permitted to take a ref on any inode presented.
+ * It is also not permitted to sleep.
+ *
+ * The caller must hold the RCU read lock.
+ */
+struct inode *find_inode_rcu(struct super_block *sb, unsigned long hashval,
+			     int (*test)(struct inode *, void *), void *data)
+{
+	struct hlist_head *head = inode_hashtable + hash(sb, hashval);
+	struct inode *inode;
+
+	RCU_LOCKDEP_WARN(!rcu_read_lock_held(),
+			 "suspicious find_inode_rcu() usage");
+
+	hlist_for_each_entry_rcu(inode, head, i_hash) {
+		if (inode->i_sb == sb &&
+		    !(READ_ONCE(inode->i_state) & (I_FREEING | I_WILL_FREE)) &&
+		    test(inode, data))
+			return inode;
+	}
+	return NULL;
+}
+EXPORT_SYMBOL(find_inode_rcu);
+
+/**
+ * find_inode_by_rcu - Find an inode in the inode cache
+ * @sb:		Super block of file system to search
+ * @ino:	The inode number to match
+ *
+ * Search for the inode specified by @hashval and @data in the inode cache,
+ * where the helper function @test will return 0 if the inode does not match
+ * and 1 if it does.  The @test function must be responsible for taking the
+ * i_lock spin_lock and checking i_state for an inode being freed or being
+ * initialized.
+ *
+ * If successful, this will return the inode for which the @test function
+ * returned 1 and NULL otherwise.
+ *
+ * The @test function is not permitted to take a ref on any inode presented.
+ * It is also not permitted to sleep.
+ *
+ * The caller must hold the RCU read lock.
+ */
+struct inode *find_inode_by_ino_rcu(struct super_block *sb,
+				    unsigned long ino)
+{
+	struct hlist_head *head = inode_hashtable + hash(sb, ino);
+	struct inode *inode;
+
+	RCU_LOCKDEP_WARN(!rcu_read_lock_held(),
+			 "suspicious find_inode_by_ino_rcu() usage");
+
+	hlist_for_each_entry_rcu(inode, head, i_hash) {
+		if (inode->i_ino == ino &&
+		    inode->i_sb == sb &&
+		    !(READ_ONCE(inode->i_state) & (I_FREEING | I_WILL_FREE)))
+		    return inode;
+	}
+	return NULL;
+}
+EXPORT_SYMBOL(find_inode_by_ino_rcu);
+
 int insert_inode_locked(struct inode *inode)
 {
 	struct super_block *sb = inode->i_sb;
@@ -1480,7 +1555,7 @@ int insert_inode_locked(struct inode *inode)
 		if (likely(!old)) {
 			spin_lock(&inode->i_lock);
 			inode->i_state |= I_NEW | I_CREATING;
-			hlist_add_head(&inode->i_hash, head);
+			hlist_add_head_rcu(&inode->i_hash, head);
 			spin_unlock(&inode->i_lock);
 			spin_unlock(&inode_hash_lock);
 			return 0;
@@ -1540,6 +1615,7 @@ static void iput_final(struct inode *inode)
 {
 	struct super_block *sb = inode->i_sb;
 	const struct super_operations *op = inode->i_sb->s_op;
+	unsigned long state;
 	int drop;
 
 	WARN_ON(inode->i_state & I_NEW);
@@ -1555,16 +1631,20 @@ static void iput_final(struct inode *inode)
 		return;
 	}
 
+	state = inode->i_state;
 	if (!drop) {
-		inode->i_state |= I_WILL_FREE;
+		WRITE_ONCE(inode->i_state, state | I_WILL_FREE);
 		spin_unlock(&inode->i_lock);
+
 		write_inode_now(inode, 1);
+
 		spin_lock(&inode->i_lock);
-		WARN_ON(inode->i_state & I_NEW);
-		inode->i_state &= ~I_WILL_FREE;
+		state = inode->i_state;
+		WARN_ON(state & I_NEW);
+		state &= ~I_WILL_FREE;
 	}
 
-	inode->i_state |= I_FREEING;
+	WRITE_ONCE(inode->i_state, state | I_FREEING);
 	if (!list_empty(&inode->i_lru))
 		inode_lru_list_del(inode);
 	spin_unlock(&inode->i_lock);