5 files changed, 114 insertions, 99 deletions

diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c
index 6ebae6bbe6a5..b2d9f79c4a7c 100644
--- a/fs/kernfs/dir.c
+++ b/fs/kernfs/dir.c
@@ -508,10 +508,6 @@ 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);
@@ -536,7 +532,7 @@ void kernfs_put(struct kernfs_node *kn)
 		kmem_cache_free(kernfs_iattrs_cache, kn->iattr);
 	}
 	spin_lock(&kernfs_idr_lock);
-	idr_remove(&root->ino_idr, kn->id.ino);
+	idr_remove(&root->ino_idr, (u32)kernfs_ino(kn));
 	spin_unlock(&kernfs_idr_lock);
 	kmem_cache_free(kernfs_node_cache, kn);
 
@@ -621,8 +617,7 @@ static struct kernfs_node *__kernfs_new_node(struct kernfs_root *root,
 					     unsigned flags)
 {
 	struct kernfs_node *kn;
-	u32 gen;
-	int cursor;
+	u32 id_highbits;
 	int ret;
 
 	name = kstrdup_const(name, GFP_KERNEL);
@@ -635,23 +630,19 @@ static struct kernfs_node *__kernfs_new_node(struct kernfs_root *root,
 
 	idr_preload(GFP_KERNEL);
 	spin_lock(&kernfs_idr_lock);
-	cursor = idr_get_cursor(&root->ino_idr);
 	ret = idr_alloc_cyclic(&root->ino_idr, kn, 1, 0, GFP_ATOMIC);
-	if (ret >= 0 && ret < cursor)
-		root->next_generation++;
-	gen = root->next_generation;
+	if (ret >= 0 && ret < root->last_id_lowbits)
+		root->id_highbits++;
+	id_highbits = root->id_highbits;
+	root->last_id_lowbits = ret;
 	spin_unlock(&kernfs_idr_lock);
 	idr_preload_end();
 	if (ret < 0)
 		goto err_out2;
-	kn->id.ino = ret;
-	kn->id.generation = gen;
 
-	/*
-	 * set ino first. This RELEASE is paired with atomic_inc_not_zero in
-	 * kernfs_find_and_get_node_by_ino
-	 */
-	atomic_set_release(&kn->count, 1);
+	kn->id = (u64)id_highbits << 32 | ret;
+
+	atomic_set(&kn->count, 1);
 	atomic_set(&kn->active, KN_DEACTIVATED_BIAS);
 	RB_CLEAR_NODE(&kn->rb);
 
@@ -680,7 +671,7 @@ static struct kernfs_node *__kernfs_new_node(struct kernfs_root *root,
 	return kn;
 
  err_out3:
-	idr_remove(&root->ino_idr, kn->id.ino);
+	idr_remove(&root->ino_idr, (u32)kernfs_ino(kn));
  err_out2:
 	kmem_cache_free(kernfs_node_cache, kn);
  err_out1:
@@ -705,50 +696,52 @@ struct kernfs_node *kernfs_new_node(struct kernfs_node *parent,
 }
 
 /*
- * kernfs_find_and_get_node_by_ino - get kernfs_node from inode number
+ * kernfs_find_and_get_node_by_id - get kernfs_node from node id
  * @root: the kernfs root
- * @ino: inode number
+ * @id: the target node id
+ *
+ * @id's lower 32bits encode ino and upper gen.  If the gen portion is
+ * zero, all generations are matched.
  *
  * 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 *kernfs_find_and_get_node_by_id(struct kernfs_root *root,
+						   u64 id)
 {
 	struct kernfs_node *kn;
+	ino_t ino = kernfs_id_ino(id);
+	u32 gen = kernfs_id_gen(id);
 
-	rcu_read_lock();
-	kn = idr_find(&root->ino_idr, ino);
+	spin_lock(&kernfs_idr_lock);
+
+	kn = idr_find(&root->ino_idr, (u32)ino);
 	if (!kn)
-		goto out;
+		goto err_unlock;
 
-	/*
-	 * 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;
+	if (sizeof(ino_t) >= sizeof(u64)) {
+		/* we looked up with the low 32bits, compare the whole */
+		if (kernfs_ino(kn) != ino)
+			goto err_unlock;
+	} else {
+		/* 0 matches all generations */
+		if (unlikely(gen && kernfs_gen(kn) != gen))
+			goto err_unlock;
 	}
 
 	/*
-	 * 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 (because of
-	 * SLAB_TYPESAFE_BY_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.
+	 * ACTIVATED is protected with kernfs_mutex but it was clear when
+	 * @kn was added to idr and we just wanna see it set.  No need to
+	 * grab kernfs_mutex.
 	 */
-	if (kn->id.ino != ino)
-		goto out;
-	rcu_read_unlock();
+	if (unlikely(!(kn->flags & KERNFS_ACTIVATED) ||
+		     !atomic_inc_not_zero(&kn->count)))
+		goto err_unlock;
 
+	spin_unlock(&kernfs_idr_lock);
 	return kn;
-out:
-	rcu_read_unlock();
-	kernfs_put(kn);
+err_unlock:
+	spin_unlock(&kernfs_idr_lock);
 	return NULL;
 }
 
@@ -962,7 +955,17 @@ struct kernfs_root *kernfs_create_root(struct kernfs_syscall_ops *scops,
 
 	idr_init(&root->ino_idr);
 	INIT_LIST_HEAD(&root->supers);
-	root->next_generation = 1;
+
+	/*
+	 * On 64bit ino setups, id is ino.  On 32bit, low 32bits are ino.
+	 * High bits generation.  The starting value for both ino and
+	 * genenration is 1.  Initialize upper 32bit allocation
+	 * accordingly.
+	 */
+	if (sizeof(ino_t) >= sizeof(u64))
+		root->id_highbits = 0;
+	else
+		root->id_highbits = 1;
 
 	kn = __kernfs_new_node(root, NULL, "", S_IFDIR | S_IRUGO | S_IXUGO,
 			       GLOBAL_ROOT_UID, GLOBAL_ROOT_GID,
@@ -1678,7 +1681,7 @@ static int kernfs_fop_readdir(struct file *file, struct dir_context *ctx)
 		const char *name = pos->name;
 		unsigned int type = dt_type(pos);
 		int len = strlen(name);
-		ino_t ino = pos->id.ino;
+		ino_t ino = kernfs_ino(pos);
 
 		ctx->pos = pos->hash;
 		file->private_data = pos;
diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c
index e8c792b49616..34366db3620d 100644
--- a/fs/kernfs/file.c
+++ b/fs/kernfs/file.c
@@ -892,7 +892,7 @@ repeat:
 		 * have the matching @file available.  Look up the inodes
 		 * and generate the events manually.
 		 */
-		inode = ilookup(info->sb, kn->id.ino);
+		inode = ilookup(info->sb, kernfs_ino(kn));
 		if (!inode)
 			continue;
 
@@ -901,7 +901,7 @@ repeat:
 		if (parent) {
 			struct inode *p_inode;
 
-			p_inode = ilookup(info->sb, parent->id.ino);
+			p_inode = ilookup(info->sb, kernfs_ino(parent));
 			if (p_inode) {
 				fsnotify(p_inode, FS_MODIFY | FS_EVENT_ON_CHILD,
 					 inode, FSNOTIFY_EVENT_INODE, &name, 0);
diff --git a/fs/kernfs/inode.c b/fs/kernfs/inode.c
index f3eaa8869f42..eac277c63d42 100644
--- a/fs/kernfs/inode.c
+++ b/fs/kernfs/inode.c
@@ -201,7 +201,7 @@ static void kernfs_init_inode(struct kernfs_node *kn, struct inode *inode)
 	inode->i_private = kn;
 	inode->i_mapping->a_ops = &kernfs_aops;
 	inode->i_op = &kernfs_iops;
-	inode->i_generation = kn->id.generation;
+	inode->i_generation = kernfs_gen(kn);
 
 	set_default_inode_attr(inode, kn->mode);
 	kernfs_refresh_inode(kn, inode);
@@ -247,7 +247,7 @@ struct inode *kernfs_get_inode(struct super_block *sb, struct kernfs_node *kn)
 {
 	struct inode *inode;
 
-	inode = iget_locked(sb, kn->id.ino);
+	inode = iget_locked(sb, kernfs_ino(kn));
 	if (inode && (inode->i_state & I_NEW))
 		kernfs_init_inode(kn, inode);
 
diff --git a/fs/kernfs/kernfs-internal.h b/fs/kernfs/kernfs-internal.h
index 02ce570a9a3c..2f3c51d55261 100644
--- a/fs/kernfs/kernfs-internal.h
+++ b/fs/kernfs/kernfs-internal.h
@@ -109,8 +109,6 @@ struct kernfs_node *kernfs_new_node(struct kernfs_node *parent,
 				    const char *name, umode_t mode,
 				    kuid_t uid, kgid_t gid,
 				    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 6c12fac2c287..4d31503abaee 100644
--- a/fs/kernfs/mount.c
+++ b/fs/kernfs/mount.c
@@ -53,63 +53,85 @@ const struct super_operations kernfs_sops = {
 	.show_path	= kernfs_sop_show_path,
 };
 
-/*
- * Similar to kernfs_fh_get_inode, this one gets kernfs node from inode
- * number and generation
- */
-struct kernfs_node *kernfs_get_node_by_id(struct kernfs_root *root,
-	const union kernfs_node_id *id)
+static int kernfs_encode_fh(struct inode *inode, __u32 *fh, int *max_len,
+			    struct inode *parent)
 {
-	struct kernfs_node *kn;
+	struct kernfs_node *kn = inode->i_private;
 
-	kn = kernfs_find_and_get_node_by_ino(root, id->ino);
-	if (!kn)
-		return NULL;
-	if (kn->id.generation != id->generation) {
-		kernfs_put(kn);
-		return NULL;
+	if (*max_len < 2) {
+		*max_len = 2;
+		return FILEID_INVALID;
 	}
-	return kn;
+
+	*max_len = 2;
+	*(u64 *)fh = kn->id;
+	return FILEID_KERNFS;
 }
 
-static struct inode *kernfs_fh_get_inode(struct super_block *sb,
-		u64 ino, u32 generation)
+static struct dentry *__kernfs_fh_to_dentry(struct super_block *sb,
+					    struct fid *fid, int fh_len,
+					    int fh_type, bool get_parent)
 {
 	struct kernfs_super_info *info = kernfs_info(sb);
-	struct inode *inode;
 	struct kernfs_node *kn;
+	struct inode *inode;
+	u64 id;
 
-	if (ino == 0)
-		return ERR_PTR(-ESTALE);
+	if (fh_len < 2)
+		return NULL;
+
+	switch (fh_type) {
+	case FILEID_KERNFS:
+		id = *(u64 *)fid;
+		break;
+	case FILEID_INO32_GEN:
+	case FILEID_INO32_GEN_PARENT:
+		/*
+		 * blk_log_action() exposes "LOW32,HIGH32" pair without
+		 * type and userland can call us with generic fid
+		 * constructed from them.  Combine it back to ID.  See
+		 * blk_log_action().
+		 */
+		id = ((u64)fid->i32.gen << 32) | fid->i32.ino;
+		break;
+	default:
+		return NULL;
+	}
 
-	kn = kernfs_find_and_get_node_by_ino(info->root, ino);
+	kn = kernfs_find_and_get_node_by_id(info->root, id);
 	if (!kn)
 		return ERR_PTR(-ESTALE);
+
+	if (get_parent) {
+		struct kernfs_node *parent;
+
+		parent = kernfs_get_parent(kn);
+		kernfs_put(kn);
+		kn = parent;
+		if (!kn)
+			return ERR_PTR(-ESTALE);
+	}
+
 	inode = kernfs_get_inode(sb, kn);
 	kernfs_put(kn);
 	if (!inode)
 		return ERR_PTR(-ESTALE);
 
-	if (generation && inode->i_generation != generation) {
-		/* we didn't find the right inode.. */
-		iput(inode);
-		return ERR_PTR(-ESTALE);
-	}
-	return inode;
+	return d_obtain_alias(inode);
 }
 
-static struct dentry *kernfs_fh_to_dentry(struct super_block *sb, struct fid *fid,
-		int fh_len, int fh_type)
+static struct dentry *kernfs_fh_to_dentry(struct super_block *sb,
+					  struct fid *fid, int fh_len,
+					  int fh_type)
 {
-	return generic_fh_to_dentry(sb, fid, fh_len, fh_type,
-				    kernfs_fh_get_inode);
+	return __kernfs_fh_to_dentry(sb, fid, fh_len, fh_type, false);
 }
 
-static struct dentry *kernfs_fh_to_parent(struct super_block *sb, struct fid *fid,
-		int fh_len, int fh_type)
+static struct dentry *kernfs_fh_to_parent(struct super_block *sb,
+					  struct fid *fid, int fh_len,
+					  int fh_type)
 {
-	return generic_fh_to_parent(sb, fid, fh_len, fh_type,
-				    kernfs_fh_get_inode);
+	return __kernfs_fh_to_dentry(sb, fid, fh_len, fh_type, true);
 }
 
 static struct dentry *kernfs_get_parent_dentry(struct dentry *child)
@@ -120,6 +142,7 @@ static struct dentry *kernfs_get_parent_dentry(struct dentry *child)
 }
 
 static const struct export_operations kernfs_export_ops = {
+	.encode_fh	= kernfs_encode_fh,
 	.fh_to_dentry	= kernfs_fh_to_dentry,
 	.fh_to_parent	= kernfs_fh_to_parent,
 	.get_parent	= kernfs_get_parent_dentry,
@@ -363,18 +386,9 @@ void kernfs_kill_sb(struct super_block *sb)
 
 void __init kernfs_init(void)
 {
-
-	/*
-	 * the slab is freed in RCU context, so kernfs_find_and_get_node_by_ino
-	 * can access the slab lock free. This could introduce stale nodes,
-	 * please see how kernfs_find_and_get_node_by_ino filters out stale
-	 * nodes.
-	 */
 	kernfs_node_cache = kmem_cache_create("kernfs_node_cache",
 					      sizeof(struct kernfs_node),
-					      0,
-					      SLAB_PANIC | SLAB_TYPESAFE_BY_RCU,
-					      NULL);
+					      0, SLAB_PANIC, NULL);
 
 	/* Creates slab cache for kernfs inode attributes */
 	kernfs_iattrs_cache  = kmem_cache_create("kernfs_iattrs_cache",