[PATCH V2 03/12] kernfs: add an API to get kernfs node from inode number

[Shaohua Li <shli@kernel.org>]

From: Shaohua Li <shli@fb.com>

Add an API to get kernfs node from inode number. We will need this to
implement exportfs operations.

To make the API lock free, kernfs node is freed in RCU context. And we
depend on kernfs_node count/ino number to filter stale kernfs nodes.

Signed-off-by: Shaohua Li <shli@fb.com>
---
 fs/kernfs/dir.c             | 53 +++++++++++++++++++++++++++++++++++++++++++++
 fs/kernfs/kernfs-internal.h |  2 ++
 fs/kernfs/mount.c           |  4 +++-
 3 files changed, 58 insertions(+), 1 deletion(-)

diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c
index 8e8545a..646b56b 100644
--- a/fs/kernfs/dir.c
+++ b/fs/kernfs/dir.c
@@ -508,6 +508,10 @@ void kernfs_put(struct kernfs_node *kn)
 	struct kernfs_node *parent;
 	struct kernfs_root *root;
 
+	/*
+	 * kernfs_node is freed with ->count 0, kernfs_find_and_get_node_by_ino
+	 * depends on this to filter reused stale node
+	 */
 	if (!kn || !atomic_dec_and_test(&kn->count))
 		return;
 	root = kernfs_root(kn);
@@ -643,6 +647,7 @@ static struct kernfs_node *__kernfs_new_node(struct kernfs_root *root,
 	kn->ino = ret;
 	kn->generation = atomic_inc_return(&root->next_generation);
 
+	/* set ino first. Above atomic_inc_return has a barrier */
 	atomic_set(&kn->count, 1);
 	atomic_set(&kn->active, KN_DEACTIVATED_BIAS);
 	RB_CLEAR_NODE(&kn->rb);
@@ -674,6 +679,54 @@ struct kernfs_node *kernfs_new_node(struct kernfs_node *parent,
 	return kn;
 }
 
+/*
+ * kernfs_find_and_get_node_by_ino - get kernfs_node from inode number
+ * @root: the kernfs root
+ * @ino: inode number
+ *
+ * RETURNS:
+ * NULL on failure. Return a kernfs node with reference counter incremented
+ */
+struct kernfs_node *kernfs_find_and_get_node_by_ino(struct kernfs_root *root,
+						    unsigned int ino)
+{
+	struct kernfs_node *kn;
+
+	rcu_read_lock();
+	kn = idr_find(&root->ino_idr, ino);
+	if (!kn)
+		goto out;
+
+	/*
+	 * Since kernfs_node is freed in RCU, it's possible an old node for ino
+	 * is freed, but reused before RCU grace period. But a freed node (see
+	 * kernfs_put) or an incompletedly initialized node (see
+	 * __kernfs_new_node) should have 'count' 0. We can use this fact to
+	 * filter out such node.
+	 */
+	if (!atomic_inc_not_zero(&kn->count)) {
+		kn = NULL;
+		goto out;
+	}
+
+	/*
+	 * The node could be a new node or a reused node. If it's a new node,
+	 * we are ok. If it's reused because of RCU, the __kernfs_new_node
+	 * always sets its 'ino' before 'count'. So if 'count' is uptodate,
+	 * 'ino' should be uptodate, hence we can use 'ino' to filter stale
+	 * node.
+	 */
+	if (kn->ino != ino)
+		goto out;
+	rcu_read_unlock();
+
+	return kn;
+out:
+	rcu_read_unlock();
+	kernfs_put(kn);
+	return NULL;
+}
+
 /**
  *	kernfs_add_one - add kernfs_node to parent without warning
  *	@kn: kernfs_node to be added
diff --git a/fs/kernfs/kernfs-internal.h b/fs/kernfs/kernfs-internal.h
index 2d5144a..e9c226f 100644
--- a/fs/kernfs/kernfs-internal.h
+++ b/fs/kernfs/kernfs-internal.h
@@ -98,6 +98,8 @@ int kernfs_add_one(struct kernfs_node *kn);
 struct kernfs_node *kernfs_new_node(struct kernfs_node *parent,
 				    const char *name, umode_t mode,
 				    unsigned flags);
+struct kernfs_node *kernfs_find_and_get_node_by_ino(struct kernfs_root *root,
+						    unsigned int ino);
 
 /*
  * file.c
diff --git a/fs/kernfs/mount.c b/fs/kernfs/mount.c
index d5b149a..343dfeb 100644
--- a/fs/kernfs/mount.c
+++ b/fs/kernfs/mount.c
@@ -332,5 +332,7 @@ void __init kernfs_init(void)
 {
 	kernfs_node_cache = kmem_cache_create("kernfs_node_cache",
 					      sizeof(struct kernfs_node),
-					      0, SLAB_PANIC, NULL);
+					      0,
+					      SLAB_PANIC | SLAB_TYPESAFE_BY_RCU,
+					      NULL);
 }
-- 
2.9.3