Update Linux to v5.10.109

Sourced from [1]

[1] https://cdn.kernel.org/pub/linux/kernel/v5.x/linux-5.10.109.tar.xz

Change-Id: I19bca9fc6762d4e63bcf3e4cba88bbe560d9c76c
Signed-off-by: Olivier Deprez <olivier.deprez@arm.com>
diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c
index 7d4af6c..9aec80b 100644
--- a/fs/kernfs/dir.c
+++ b/fs/kernfs/dir.c
@@ -438,7 +438,7 @@
 		return;
 
 	if (kernfs_lockdep(kn))
-		rwsem_release(&kn->dep_map, 1, _RET_IP_);
+		rwsem_release(&kn->dep_map, _RET_IP_);
 	v = atomic_dec_return(&kn->active);
 	if (likely(v != KN_DEACTIVATED_BIAS))
 		return;
@@ -476,7 +476,7 @@
 
 	if (kernfs_lockdep(kn)) {
 		lock_acquired(&kn->dep_map, _RET_IP_);
-		rwsem_release(&kn->dep_map, 1, _RET_IP_);
+		rwsem_release(&kn->dep_map, _RET_IP_);
 	}
 
 	kernfs_drain_open_files(kn);
@@ -508,10 +508,6 @@
 	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 @@
 		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);
 
@@ -621,7 +617,7 @@
 					     unsigned flags)
 {
 	struct kernfs_node *kn;
-	u32 gen;
+	u32 id_highbits;
 	int ret;
 
 	name = kstrdup_const(name, GFP_KERNEL);
@@ -635,22 +631,18 @@
 	idr_preload(GFP_KERNEL);
 	spin_lock(&kernfs_idr_lock);
 	ret = idr_alloc_cyclic(&root->ino_idr, kn, 1, 0, GFP_ATOMIC);
-	if (ret >= 0 && ret < root->last_ino)
-		root->next_generation++;
-	gen = root->next_generation;
-	root->last_ino = ret;
+	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);
 
@@ -679,7 +671,7 @@
 	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:
@@ -704,50 +696,52 @@
 }
 
 /*
- * 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;
 }
 
@@ -961,7 +955,17 @@
 
 	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,
@@ -1262,7 +1266,7 @@
 
 	pos = NULL;
 	while ((pos = kernfs_next_descendant_post(pos, kn))) {
-		if (!pos || (pos->flags & KERNFS_ACTIVATED))
+		if (pos->flags & KERNFS_ACTIVATED)
 			continue;
 
 		WARN_ON_ONCE(pos->parent && RB_EMPTY_NODE(&pos->rb));
@@ -1677,7 +1681,7 @@
 		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 c35bbaa..c757193 100644
--- a/fs/kernfs/file.c
+++ b/fs/kernfs/file.c
@@ -14,6 +14,7 @@
 #include <linux/pagemap.h>
 #include <linux/sched/mm.h>
 #include <linux/fsnotify.h>
+#include <linux/uio.h>
 
 #include "kernfs-internal.h"
 
@@ -180,11 +181,10 @@
  * it difficult to use seq_file.  Implement simplistic custom buffering for
  * bin files.
  */
-static ssize_t kernfs_file_direct_read(struct kernfs_open_file *of,
-				       char __user *user_buf, size_t count,
-				       loff_t *ppos)
+static ssize_t kernfs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter)
 {
-	ssize_t len = min_t(size_t, count, PAGE_SIZE);
+	struct kernfs_open_file *of = kernfs_of(iocb->ki_filp);
+	ssize_t len = min_t(size_t, iov_iter_count(iter), PAGE_SIZE);
 	const struct kernfs_ops *ops;
 	char *buf;
 
@@ -210,7 +210,7 @@
 	of->event = atomic_read(&of->kn->attr.open->event);
 	ops = kernfs_ops(of->kn);
 	if (ops->read)
-		len = ops->read(of, buf, len, *ppos);
+		len = ops->read(of, buf, len, iocb->ki_pos);
 	else
 		len = -EINVAL;
 
@@ -220,12 +220,12 @@
 	if (len < 0)
 		goto out_free;
 
-	if (copy_to_user(user_buf, buf, len)) {
+	if (copy_to_iter(buf, len, iter) != len) {
 		len = -EFAULT;
 		goto out_free;
 	}
 
-	*ppos += len;
+	iocb->ki_pos += len;
 
  out_free:
 	if (buf == of->prealloc_buf)
@@ -235,31 +235,14 @@
 	return len;
 }
 
-/**
- * kernfs_fop_read - kernfs vfs read callback
- * @file: file pointer
- * @user_buf: data to write
- * @count: number of bytes
- * @ppos: starting offset
- */
-static ssize_t kernfs_fop_read(struct file *file, char __user *user_buf,
-			       size_t count, loff_t *ppos)
+static ssize_t kernfs_fop_read_iter(struct kiocb *iocb, struct iov_iter *iter)
 {
-	struct kernfs_open_file *of = kernfs_of(file);
-
-	if (of->kn->flags & KERNFS_HAS_SEQ_SHOW)
-		return seq_read(file, user_buf, count, ppos);
-	else
-		return kernfs_file_direct_read(of, user_buf, count, ppos);
+	if (kernfs_of(iocb->ki_filp)->kn->flags & KERNFS_HAS_SEQ_SHOW)
+		return seq_read_iter(iocb, iter);
+	return kernfs_file_read_iter(iocb, iter);
 }
 
-/**
- * kernfs_fop_write - kernfs vfs write callback
- * @file: file pointer
- * @user_buf: data to write
- * @count: number of bytes
- * @ppos: starting offset
- *
+/*
  * Copy data in from userland and pass it to the matching kernfs write
  * operation.
  *
@@ -269,20 +252,18 @@
  * modify only the the value you're changing, then write entire buffer
  * back.
  */
-static ssize_t kernfs_fop_write(struct file *file, const char __user *user_buf,
-				size_t count, loff_t *ppos)
+static ssize_t kernfs_fop_write_iter(struct kiocb *iocb, struct iov_iter *iter)
 {
-	struct kernfs_open_file *of = kernfs_of(file);
+	struct kernfs_open_file *of = kernfs_of(iocb->ki_filp);
+	ssize_t len = iov_iter_count(iter);
 	const struct kernfs_ops *ops;
-	ssize_t len;
 	char *buf;
 
 	if (of->atomic_write_len) {
-		len = count;
 		if (len > of->atomic_write_len)
 			return -E2BIG;
 	} else {
-		len = min_t(size_t, count, PAGE_SIZE);
+		len = min_t(size_t, len, PAGE_SIZE);
 	}
 
 	buf = of->prealloc_buf;
@@ -293,7 +274,7 @@
 	if (!buf)
 		return -ENOMEM;
 
-	if (copy_from_user(buf, user_buf, len)) {
+	if (copy_from_iter(buf, len, iter) != len) {
 		len = -EFAULT;
 		goto out_free;
 	}
@@ -312,7 +293,7 @@
 
 	ops = kernfs_ops(of->kn);
 	if (ops->write)
-		len = ops->write(of, buf, len, *ppos);
+		len = ops->write(of, buf, len, iocb->ki_pos);
 	else
 		len = -EINVAL;
 
@@ -320,7 +301,7 @@
 	mutex_unlock(&of->mutex);
 
 	if (len > 0)
-		*ppos += len;
+		iocb->ki_pos += len;
 
 out_free:
 	if (buf == of->prealloc_buf)
@@ -652,9 +633,9 @@
 	 * The following is done to give a different lockdep key to
 	 * @of->mutex for files which implement mmap.  This is a rather
 	 * crude way to avoid false positive lockdep warning around
-	 * mm->mmap_sem - mmap nests @of->mutex under mm->mmap_sem and
+	 * mm->mmap_lock - mmap nests @of->mutex under mm->mmap_lock and
 	 * reading /sys/block/sda/trace/act_mask grabs sr_mutex, under
-	 * which mm->mmap_sem nests, while holding @of->mutex.  As each
+	 * which mm->mmap_lock nests, while holding @of->mutex.  As each
 	 * open file has a separate mutex, it's okay as long as those don't
 	 * happen on the same file.  At this point, we can't easily give
 	 * each file a separate locking class.  Let's differentiate on
@@ -673,7 +654,7 @@
 
 	/*
 	 * Write path needs to atomic_write_len outside active reference.
-	 * Cache it in open_file.  See kernfs_fop_write() for details.
+	 * Cache it in open_file.  See kernfs_fop_write_iter() for details.
 	 */
 	of->atomic_write_len = ops->atomic_write_len;
 
@@ -883,6 +864,7 @@
 
 	list_for_each_entry(info, &kernfs_root(kn)->supers, node) {
 		struct kernfs_node *parent;
+		struct inode *p_inode = NULL;
 		struct inode *inode;
 		struct qstr name;
 
@@ -892,27 +874,27 @@
 		 * 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;
 
 		name = (struct qstr)QSTR_INIT(kn->name, strlen(kn->name));
 		parent = kernfs_get_parent(kn);
 		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);
+				fsnotify(FS_MODIFY | FS_EVENT_ON_CHILD,
+					 inode, FSNOTIFY_EVENT_INODE,
+					 p_inode, &name, inode, 0);
 				iput(p_inode);
 			}
 
 			kernfs_put(parent);
 		}
 
-		fsnotify(inode, FS_MODIFY, inode, FSNOTIFY_EVENT_INODE,
-			 NULL, 0);
+		if (!p_inode)
+			fsnotify_inode(inode, FS_MODIFY);
+
 		iput(inode);
 	}
 
@@ -959,14 +941,16 @@
 EXPORT_SYMBOL_GPL(kernfs_notify);
 
 const struct file_operations kernfs_file_fops = {
-	.read		= kernfs_fop_read,
-	.write		= kernfs_fop_write,
+	.read_iter	= kernfs_fop_read_iter,
+	.write_iter	= kernfs_fop_write_iter,
 	.llseek		= generic_file_llseek,
 	.mmap		= kernfs_fop_mmap,
 	.open		= kernfs_fop_open,
 	.release	= kernfs_fop_release,
 	.poll		= kernfs_fop_poll,
 	.fsync		= noop_fsync,
+	.splice_read	= generic_file_splice_read,
+	.splice_write	= iter_file_splice_write,
 };
 
 /**
@@ -1010,7 +994,7 @@
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 	if (key) {
-		lockdep_init_map(&kn->dep_map, "kn->count", key, 0);
+		lockdep_init_map(&kn->dep_map, "kn->active", key, 0);
 		kn->flags |= KERNFS_LOCKDEP;
 	}
 #endif
diff --git a/fs/kernfs/inode.c b/fs/kernfs/inode.c
index f3eaa88..fc2469a 100644
--- a/fs/kernfs/inode.c
+++ b/fs/kernfs/inode.c
@@ -53,6 +53,8 @@
 	kn->iattr->ia_ctime = kn->iattr->ia_atime;
 
 	simple_xattrs_init(&kn->iattr->xattrs);
+	atomic_set(&kn->iattr->nr_user_xattrs, 0);
+	atomic_set(&kn->iattr->user_xattr_size, 0);
 out_unlock:
 	ret = kn->iattr;
 	mutex_unlock(&iattr_mutex);
@@ -160,9 +162,9 @@
 {
 	inode->i_uid = attrs->ia_uid;
 	inode->i_gid = attrs->ia_gid;
-	inode->i_atime = timestamp_truncate(attrs->ia_atime, inode);
-	inode->i_mtime = timestamp_truncate(attrs->ia_mtime, inode);
-	inode->i_ctime = timestamp_truncate(attrs->ia_ctime, inode);
+	inode->i_atime = attrs->ia_atime;
+	inode->i_mtime = attrs->ia_mtime;
+	inode->i_ctime = attrs->ia_ctime;
 }
 
 static void kernfs_refresh_inode(struct kernfs_node *kn, struct inode *inode)
@@ -201,7 +203,7 @@
 	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 +249,7 @@
 {
 	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);
 
@@ -303,7 +305,7 @@
 	if (!attrs)
 		return -ENOMEM;
 
-	return simple_xattr_set(&attrs->xattrs, name, value, size, flags);
+	return simple_xattr_set(&attrs->xattrs, name, value, size, flags, NULL);
 }
 
 static int kernfs_vfs_xattr_get(const struct xattr_handler *handler,
@@ -327,6 +329,86 @@
 	return kernfs_xattr_set(kn, name, value, size, flags);
 }
 
+static int kernfs_vfs_user_xattr_add(struct kernfs_node *kn,
+				     const char *full_name,
+				     struct simple_xattrs *xattrs,
+				     const void *value, size_t size, int flags)
+{
+	atomic_t *sz = &kn->iattr->user_xattr_size;
+	atomic_t *nr = &kn->iattr->nr_user_xattrs;
+	ssize_t removed_size;
+	int ret;
+
+	if (atomic_inc_return(nr) > KERNFS_MAX_USER_XATTRS) {
+		ret = -ENOSPC;
+		goto dec_count_out;
+	}
+
+	if (atomic_add_return(size, sz) > KERNFS_USER_XATTR_SIZE_LIMIT) {
+		ret = -ENOSPC;
+		goto dec_size_out;
+	}
+
+	ret = simple_xattr_set(xattrs, full_name, value, size, flags,
+			       &removed_size);
+
+	if (!ret && removed_size >= 0)
+		size = removed_size;
+	else if (!ret)
+		return 0;
+dec_size_out:
+	atomic_sub(size, sz);
+dec_count_out:
+	atomic_dec(nr);
+	return ret;
+}
+
+static int kernfs_vfs_user_xattr_rm(struct kernfs_node *kn,
+				    const char *full_name,
+				    struct simple_xattrs *xattrs,
+				    const void *value, size_t size, int flags)
+{
+	atomic_t *sz = &kn->iattr->user_xattr_size;
+	atomic_t *nr = &kn->iattr->nr_user_xattrs;
+	ssize_t removed_size;
+	int ret;
+
+	ret = simple_xattr_set(xattrs, full_name, value, size, flags,
+			       &removed_size);
+
+	if (removed_size >= 0) {
+		atomic_sub(removed_size, sz);
+		atomic_dec(nr);
+	}
+
+	return ret;
+}
+
+static int kernfs_vfs_user_xattr_set(const struct xattr_handler *handler,
+				     struct dentry *unused, struct inode *inode,
+				     const char *suffix, const void *value,
+				     size_t size, int flags)
+{
+	const char *full_name = xattr_full_name(handler, suffix);
+	struct kernfs_node *kn = inode->i_private;
+	struct kernfs_iattrs *attrs;
+
+	if (!(kernfs_root(kn)->flags & KERNFS_ROOT_SUPPORT_USER_XATTR))
+		return -EOPNOTSUPP;
+
+	attrs = kernfs_iattrs(kn);
+	if (!attrs)
+		return -ENOMEM;
+
+	if (value)
+		return kernfs_vfs_user_xattr_add(kn, full_name, &attrs->xattrs,
+						 value, size, flags);
+	else
+		return kernfs_vfs_user_xattr_rm(kn, full_name, &attrs->xattrs,
+						value, size, flags);
+
+}
+
 static const struct xattr_handler kernfs_trusted_xattr_handler = {
 	.prefix = XATTR_TRUSTED_PREFIX,
 	.get = kernfs_vfs_xattr_get,
@@ -339,8 +421,15 @@
 	.set = kernfs_vfs_xattr_set,
 };
 
+static const struct xattr_handler kernfs_user_xattr_handler = {
+	.prefix = XATTR_USER_PREFIX,
+	.get = kernfs_vfs_xattr_get,
+	.set = kernfs_vfs_user_xattr_set,
+};
+
 const struct xattr_handler *kernfs_xattr_handlers[] = {
 	&kernfs_trusted_xattr_handler,
 	&kernfs_security_xattr_handler,
+	&kernfs_user_xattr_handler,
 	NULL
 };
diff --git a/fs/kernfs/kernfs-internal.h b/fs/kernfs/kernfs-internal.h
index 02ce570..7ee97ef 100644
--- a/fs/kernfs/kernfs-internal.h
+++ b/fs/kernfs/kernfs-internal.h
@@ -26,6 +26,8 @@
 	struct timespec64	ia_ctime;
 
 	struct simple_xattrs	xattrs;
+	atomic_t		nr_user_xattrs;
+	atomic_t		user_xattr_size;
 };
 
 /* +1 to avoid triggering overflow warning when negating it */
@@ -109,8 +111,6 @@
 				    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 6c12fac..9dc7e7a 100644
--- a/fs/kernfs/mount.c
+++ b/fs/kernfs/mount.c
@@ -53,63 +53,85 @@
 	.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;
 
-	kn = kernfs_find_and_get_node_by_ino(info->root, ino);
+	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_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 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,
@@ -200,7 +223,7 @@
 			dput(dentry);
 			return ERR_PTR(-EINVAL);
 		}
-		dtmp = lookup_one_len_unlocked(kntmp->name, dentry,
+		dtmp = lookup_positive_unlocked(kntmp->name, dentry,
 					       strlen(kntmp->name));
 		dput(dentry);
 		if (IS_ERR(dtmp))
@@ -363,18 +386,9 @@
 
 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",