5 files changed, 64 insertions, 77 deletions

diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c
index b068ed32d7b3..5dc90a498e75 100644
--- a/fs/kernfs/dir.c
+++ b/fs/kernfs/dir.c
@@ -54,9 +54,9 @@ static bool kernfs_lockdep(struct kernfs_node *kn)
 static int kernfs_name_locked(struct kernfs_node *kn, char *buf, size_t buflen)
 {
 	if (!kn)
-		return strlcpy(buf, "(null)", buflen);
+		return strscpy(buf, "(null)", buflen);
 
-	return strlcpy(buf, kn->parent ? kn->name : "/", buflen);
+	return strscpy(buf, kn->parent ? kn->name : "/", buflen);
 }
 
 /* kernfs_node_depth - compute depth from @from to @to */
@@ -184,12 +184,12 @@ static int kernfs_path_from_node_locked(struct kernfs_node *kn_to,
  * @buflen: size of @buf
  *
  * Copies the name of @kn into @buf of @buflen bytes.  The behavior is
- * similar to strlcpy().
+ * similar to strscpy().
  *
  * Fills buffer with "(null)" if @kn is %NULL.
  *
- * Return: the length of @kn's name and if @buf isn't long enough,
- * it's filled up to @buflen-1 and nul terminated.
+ * Return: the resulting length of @buf. If @buf isn't long enough,
+ * it's filled up to @buflen-1 and nul terminated, and returns -E2BIG.
  *
  * This function can be called from any context.
  */
@@ -871,16 +871,16 @@ static struct kernfs_node *kernfs_walk_ns(struct kernfs_node *parent,
 					  const unsigned char *path,
 					  const void *ns)
 {
-	size_t len;
+	ssize_t len;
 	char *p, *name;
 
 	lockdep_assert_held_read(&kernfs_root(parent)->kernfs_rwsem);
 
 	spin_lock_irq(&kernfs_pr_cont_lock);
 
-	len = strlcpy(kernfs_pr_cont_buf, path, sizeof(kernfs_pr_cont_buf));
+	len = strscpy(kernfs_pr_cont_buf, path, sizeof(kernfs_pr_cont_buf));
 
-	if (len >= sizeof(kernfs_pr_cont_buf)) {
+	if (len < 0) {
 		spin_unlock_irq(&kernfs_pr_cont_lock);
 		return NULL;
 	}
@@ -1560,8 +1560,9 @@ void kernfs_break_active_protection(struct kernfs_node *kn)
  * invoked before finishing the kernfs operation.  Note that while this
  * function restores the active reference, it doesn't and can't actually
  * restore the active protection - @kn may already or be in the process of
- * being removed.  Once kernfs_break_active_protection() is invoked, that
- * protection is irreversibly gone for the kernfs operation instance.
+ * being drained and removed.  Once kernfs_break_active_protection() is
+ * invoked, that protection is irreversibly gone for the kernfs operation
+ * instance.
  *
  * While this function may be called at any point after
  * kernfs_break_active_protection() is invoked, its most useful location
diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c
index 332d08d2fe0d..2d9d5dfa19b8 100644
--- a/fs/kernfs/file.c
+++ b/fs/kernfs/file.c
@@ -429,60 +429,11 @@ static int kernfs_vma_access(struct vm_area_struct *vma, unsigned long addr,
 	return ret;
 }
 
-#ifdef CONFIG_NUMA
-static int kernfs_vma_set_policy(struct vm_area_struct *vma,
-				 struct mempolicy *new)
-{
-	struct file *file = vma->vm_file;
-	struct kernfs_open_file *of = kernfs_of(file);
-	int ret;
-
-	if (!of->vm_ops)
-		return 0;
-
-	if (!kernfs_get_active(of->kn))
-		return -EINVAL;
-
-	ret = 0;
-	if (of->vm_ops->set_policy)
-		ret = of->vm_ops->set_policy(vma, new);
-
-	kernfs_put_active(of->kn);
-	return ret;
-}
-
-static struct mempolicy *kernfs_vma_get_policy(struct vm_area_struct *vma,
-					       unsigned long addr)
-{
-	struct file *file = vma->vm_file;
-	struct kernfs_open_file *of = kernfs_of(file);
-	struct mempolicy *pol;
-
-	if (!of->vm_ops)
-		return vma->vm_policy;
-
-	if (!kernfs_get_active(of->kn))
-		return vma->vm_policy;
-
-	pol = vma->vm_policy;
-	if (of->vm_ops->get_policy)
-		pol = of->vm_ops->get_policy(vma, addr);
-
-	kernfs_put_active(of->kn);
-	return pol;
-}
-
-#endif
-
 static const struct vm_operations_struct kernfs_vm_ops = {
 	.open		= kernfs_vma_open,
 	.fault		= kernfs_vma_fault,
 	.page_mkwrite	= kernfs_vma_page_mkwrite,
 	.access		= kernfs_vma_access,
-#ifdef CONFIG_NUMA
-	.set_policy	= kernfs_vma_set_policy,
-	.get_policy	= kernfs_vma_get_policy,
-#endif
 };
 
 static int kernfs_fop_mmap(struct file *file, struct vm_area_struct *vma)
@@ -496,7 +447,7 @@ static int kernfs_fop_mmap(struct file *file, struct vm_area_struct *vma)
 	 * warnings and we don't want to add spurious locking dependency
 	 * between the two.  Check whether mmap is actually implemented
 	 * without grabbing @of->mutex by testing HAS_MMAP flag.  See the
-	 * comment in kernfs_file_open() for more details.
+	 * comment in kernfs_fop_open() for more details.
 	 */
 	if (!(of->kn->flags & KERNFS_HAS_MMAP))
 		return -ENODEV;
@@ -685,11 +636,18 @@ static int kernfs_fop_open(struct inode *inode, struct file *file)
 	 * each file a separate locking class.  Let's differentiate on
 	 * whether the file has mmap or not for now.
 	 *
-	 * Both paths of the branch look the same.  They're supposed to
+	 * For similar reasons, writable and readonly files are given different
+	 * lockdep key, because the writable file /sys/power/resume may call vfs
+	 * lookup helpers for arbitrary paths and readonly files can be read by
+	 * overlayfs from vfs helpers when sysfs is a lower layer of overalyfs.
+	 *
+	 * All three cases look the same.  They're supposed to
 	 * look that way and give @of->mutex different static lockdep keys.
 	 */
 	if (has_mmap)
 		mutex_init(&of->mutex);
+	else if (file->f_mode & FMODE_WRITE)
+		mutex_init(&of->mutex);
 	else
 		mutex_init(&of->mutex);
 
@@ -820,8 +778,9 @@ bool kernfs_should_drain_open_files(struct kernfs_node *kn)
 	/*
 	 * @kn being deactivated guarantees that @kn->attr.open can't change
 	 * beneath us making the lockless test below safe.
+	 * Callers post kernfs_unbreak_active_protection may be counted in
+	 * kn->active by now, do not WARN_ON because of them.
 	 */
-	WARN_ON_ONCE(atomic_read(&kn->active) != KN_DEACTIVATED_BIAS);
 
 	rcu_read_lock();
 	on = rcu_dereference(kn->attr.open);
@@ -905,6 +864,33 @@ static __poll_t kernfs_fop_poll(struct file *filp, poll_table *wait)
 	return ret;
 }
 
+static loff_t kernfs_fop_llseek(struct file *file, loff_t offset, int whence)
+{
+	struct kernfs_open_file *of = kernfs_of(file);
+	const struct kernfs_ops *ops;
+	loff_t ret;
+
+	/*
+	 * @of->mutex nests outside active ref and is primarily to ensure that
+	 * the ops aren't called concurrently for the same open file.
+	 */
+	mutex_lock(&of->mutex);
+	if (!kernfs_get_active(of->kn)) {
+		mutex_unlock(&of->mutex);
+		return -ENODEV;
+	}
+
+	ops = kernfs_ops(of->kn);
+	if (ops->llseek)
+		ret = ops->llseek(of, offset, whence);
+	else
+		ret = generic_file_llseek(file, offset, whence);
+
+	kernfs_put_active(of->kn);
+	mutex_unlock(&of->mutex);
+	return ret;
+}
+
 static void kernfs_notify_workfn(struct work_struct *work)
 {
 	struct kernfs_node *kn;
@@ -942,7 +928,7 @@ repeat:
 		if (!inode)
 			continue;
 
-		name = (struct qstr)QSTR_INIT(kn->name, strlen(kn->name));
+		name = QSTR(kn->name);
 		parent = kernfs_get_parent(kn);
 		if (parent) {
 			p_inode = ilookup(info->sb, kernfs_ino(parent));
@@ -1007,7 +993,7 @@ EXPORT_SYMBOL_GPL(kernfs_notify);
 const struct file_operations kernfs_file_fops = {
 	.read_iter	= kernfs_fop_read_iter,
 	.write_iter	= kernfs_fop_write_iter,
-	.llseek		= generic_file_llseek,
+	.llseek		= kernfs_fop_llseek,
 	.mmap		= kernfs_fop_mmap,
 	.open		= kernfs_fop_open,
 	.release	= kernfs_fop_release,
diff --git a/fs/kernfs/inode.c b/fs/kernfs/inode.c
index 922719a343a7..b83054da68b3 100644
--- a/fs/kernfs/inode.c
+++ b/fs/kernfs/inode.c
@@ -151,7 +151,7 @@ ssize_t kernfs_iop_listxattr(struct dentry *dentry, char *buf, size_t size)
 static inline void set_default_inode_attr(struct inode *inode, umode_t mode)
 {
 	inode->i_mode = mode;
-	inode->i_atime = inode->i_mtime = inode_set_ctime_current(inode);
+	simple_inode_init_ts(inode);
 }
 
 static inline void set_inode_attr(struct inode *inode,
@@ -159,8 +159,8 @@ static inline void set_inode_attr(struct inode *inode,
 {
 	inode->i_uid = attrs->ia_uid;
 	inode->i_gid = attrs->ia_gid;
-	inode->i_atime = attrs->ia_atime;
-	inode->i_mtime = attrs->ia_mtime;
+	inode_set_atime_to_ts(inode, attrs->ia_atime);
+	inode_set_mtime_to_ts(inode, attrs->ia_mtime);
 	inode_set_ctime_to_ts(inode, attrs->ia_ctime);
 }
 
@@ -445,7 +445,7 @@ static const struct xattr_handler kernfs_user_xattr_handler = {
 	.set = kernfs_vfs_user_xattr_set,
 };
 
-const struct xattr_handler *kernfs_xattr_handlers[] = {
+const struct xattr_handler * const kernfs_xattr_handlers[] = {
 	&kernfs_trusted_xattr_handler,
 	&kernfs_security_xattr_handler,
 	&kernfs_user_xattr_handler,
diff --git a/fs/kernfs/kernfs-internal.h b/fs/kernfs/kernfs-internal.h
index 210dac7e9ee2..b42ee6547cdc 100644
--- a/fs/kernfs/kernfs-internal.h
+++ b/fs/kernfs/kernfs-internal.h
@@ -129,7 +129,7 @@ extern struct kmem_cache *kernfs_node_cache, *kernfs_iattrs_cache;
 /*
  * inode.c
  */
-extern const struct xattr_handler *kernfs_xattr_handlers[];
+extern const struct xattr_handler * const kernfs_xattr_handlers[];
 void kernfs_evict_inode(struct inode *inode);
 int kernfs_iop_permission(struct mnt_idmap *idmap,
 			  struct inode *inode, int mask);
diff --git a/fs/kernfs/mount.c b/fs/kernfs/mount.c
index c4bf26142eec..1358c21837f1 100644
--- a/fs/kernfs/mount.c
+++ b/fs/kernfs/mount.c
@@ -21,8 +21,9 @@
 
 #include "kernfs-internal.h"
 
-struct kmem_cache *kernfs_node_cache, *kernfs_iattrs_cache;
-struct kernfs_global_locks *kernfs_locks;
+struct kmem_cache *kernfs_node_cache __ro_after_init;
+struct kmem_cache *kernfs_iattrs_cache __ro_after_init;
+struct kernfs_global_locks *kernfs_locks __ro_after_init;
 
 static int kernfs_sop_show_options(struct seq_file *sf, struct dentry *dentry)
 {
@@ -124,9 +125,6 @@ static struct dentry *__kernfs_fh_to_dentry(struct super_block *sb,
 
 	inode = kernfs_get_inode(sb, kn);
 	kernfs_put(kn);
-	if (!inode)
-		return ERR_PTR(-ESTALE);
-
 	return d_obtain_alias(inode);
 }
 
@@ -208,7 +206,7 @@ struct dentry *kernfs_node_dentry(struct kernfs_node *kn,
 				  struct super_block *sb)
 {
 	struct dentry *dentry;
-	struct kernfs_node *knparent = NULL;
+	struct kernfs_node *knparent;
 
 	BUG_ON(sb->s_op != &kernfs_sops);
 
@@ -265,7 +263,7 @@ static int kernfs_fill_super(struct super_block *sb, struct kernfs_fs_context *k
 	sb->s_time_gran = 1;
 
 	/* sysfs dentries and inodes don't require IO to create */
-	sb->s_shrink.seeks = 0;
+	sb->s_shrink->seeks = 0;
 
 	/* get root inode, initialize and unlock it */
 	down_read(&kf_root->kernfs_rwsem);
@@ -360,7 +358,9 @@ int kernfs_get_tree(struct fs_context *fc)
 		}
 		sb->s_flags |= SB_ACTIVE;
 
-		uuid_gen(&sb->s_uuid);
+		uuid_t uuid;
+		uuid_gen(&uuid);
+		super_set_uuid(sb, uuid.b, sizeof(uuid));
 
 		down_write(&root->kernfs_supers_rwsem);
 		list_add(&info->node, &info->root->supers);