Merge tag 'vfs-6.11.misc' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs

Pull misc vfs updates from Christian Brauner:
 "Features:

   - Support passing NULL along AT_EMPTY_PATH for statx().

     NULL paths with any flag value other than AT_EMPTY_PATH go the
     usual route and end up with -EFAULT to retain compatibility (Rust
     is abusing calls of the sort to detect availability of statx)

     This avoids path lookup code, lockref management, memory allocation
     and in case of NULL path userspace memory access (which can be
     quite expensive with SMAP on x86_64)

   - Don't block i_writecount during exec. Remove the
     deny_write_access() mechanism for executables

   - Relax open_by_handle_at() permissions in specific cases where we
     can prove that the caller had sufficient privileges to open a file

   - Switch timespec64 fields in struct inode to discrete integers
     freeing up 4 bytes

  Fixes:

   - Fix false positive circular locking warning in hfsplus

   - Initialize hfs_inode_info after hfs_alloc_inode() in hfs

   - Avoid accidental overflows in vfs_fallocate()

   - Don't interrupt fallocate with EINTR in tmpfs to avoid constantly
     restarting shmem_fallocate()

   - Add missing quote in comment in fs/readdir

  Cleanups:

   - Don't assign and test in an if statement in mqueue. Move the
     assignment out of the if statement

   - Reflow the logic in may_create_in_sticky()

   - Remove the usage of the deprecated ida_simple_xx() API from procfs

   - Reject FSCONFIG_CMD_CREATE_EXCL requets that depend on the new
     mount api early

   - Rename variables in copy_tree() to make it easier to understand

   - Replace WARN(down_read_trylock, ...) abuse with proper asserts in
     various places in the VFS

   - Get rid of user_path_at_empty() and drop the empty argument from
     getname_flags()

   - Check for error while copying and no path in one branch in
     getname_flags()

   - Avoid redundant smp_mb() for THP handling in do_dentry_open()

   - Rename parent_ino to d_parent_ino and make it use RCU

   - Remove unused header include in fs/readdir

   - Export in_group_capable() helper and switch f2fs and fuse over to
     it instead of open-coding the logic in both places"

* tag 'vfs-6.11.misc' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs: (27 commits)
  ipc: mqueue: remove assignment from IS_ERR argument
  vfs: rename parent_ino to d_parent_ino and make it use RCU
  vfs: support statx(..., NULL, AT_EMPTY_PATH, ...)
  stat: use vfs_empty_path() helper
  fs: new helper vfs_empty_path()
  fs: reflow may_create_in_sticky()
  vfs: remove redundant smp_mb for thp handling in do_dentry_open
  fuse: Use in_group_or_capable() helper
  f2fs: Use in_group_or_capable() helper
  fs: Export in_group_or_capable()
  vfs: reorder checks in may_create_in_sticky
  hfs: fix to initialize fields of hfs_inode_info after hfs_alloc_inode()
  proc: Remove usage of the deprecated ida_simple_xx() API
  hfsplus: fix to avoid false alarm of circular locking
  Improve readability of copy_tree
  vfs: shave a branch in getname_flags
  vfs: retire user_path_at_empty and drop empty arg from getname_flags
  vfs: stop using user_path_at_empty in do_readlinkat
  tmpfs: don't interrupt fallocate with EINTR
  fs: don't block i_writecount during exec
  ...

fs/attr.c

@@ -17,8 +17,6 @@
 #include <linux/filelock.h>
 #include <linux/security.h>
 
-#include "internal.h"
-
 /**
  * setattr_should_drop_sgid - determine whether the setgid bit needs to be
  *                            removed

fs/binfmt_elf.c

@@ -1216,7 +1216,6 @@ out_free_interp:
 		}
 		reloc_func_desc = interp_load_addr;
 
-		allow_write_access(interpreter);
 		fput(interpreter);
 
 		kfree(interp_elf_ex);
@@ -1308,7 +1307,6 @@ out_free_dentry:
 	kfree(interp_elf_ex);
 	kfree(interp_elf_phdata);
 out_free_file:
-	allow_write_access(interpreter);
 	if (interpreter)
 		fput(interpreter);
 out_free_ph:

fs/binfmt_elf_fdpic.c

@@ -394,7 +394,6 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm)
 			goto error;
 		}
 
-		allow_write_access(interpreter);
 		fput(interpreter);
 		interpreter = NULL;
 	}
@@ -466,10 +465,8 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm)
 	retval = 0;
 
 error:
-	if (interpreter) {
-		allow_write_access(interpreter);
+	if (interpreter)
 		fput(interpreter);
-	}
 	kfree(interpreter_name);
 	kfree(exec_params.phdrs);
 	kfree(exec_params.loadmap);

fs/binfmt_misc.c

@@ -247,13 +247,10 @@ static int load_misc_binary(struct linux_binprm *bprm)
 	if (retval < 0)
 		goto ret;
 
-	if (fmt->flags & MISC_FMT_OPEN_FILE) {
+	if (fmt->flags & MISC_FMT_OPEN_FILE)
 		interp_file = file_clone_open(fmt->interp_file);
-		if (!IS_ERR(interp_file))
-			deny_write_access(interp_file);
-	} else {
+	else
 		interp_file = open_exec(fmt->interpreter);
-	}
 	retval = PTR_ERR(interp_file);
 	if (IS_ERR(interp_file))
 		goto ret;

fs/dcache.c

@@ -1555,7 +1555,7 @@ void shrink_dcache_for_umount(struct super_block *sb)
 {
 	struct dentry *dentry;
 
-	WARN(down_read_trylock(&sb->s_umount), "s_umount should've been locked");
+	rwsem_assert_held_write(&sb->s_umount);
 
 	dentry = sb->s_root;
 	sb->s_root = NULL;
@@ -3106,6 +3106,34 @@ void d_tmpfile(struct file *file, struct inode *inode)
 }
 EXPORT_SYMBOL(d_tmpfile);
 
+/*
+ * Obtain inode number of the parent dentry.
+ */
+ino_t d_parent_ino(struct dentry *dentry)
+{
+	struct dentry *parent;
+	struct inode *iparent;
+	unsigned seq;
+	ino_t ret;
+
+	scoped_guard(rcu) {
+		seq = raw_seqcount_begin(&dentry->d_seq);
+		parent = READ_ONCE(dentry->d_parent);
+		iparent = d_inode_rcu(parent);
+		if (likely(iparent)) {
+			ret = iparent->i_ino;
+			if (!read_seqcount_retry(&dentry->d_seq, seq))
+				return ret;
+		}
+	}
+
+	spin_lock(&dentry->d_lock);
+	ret = dentry->d_parent->d_inode->i_ino;
+	spin_unlock(&dentry->d_lock);
+	return ret;
+}
+EXPORT_SYMBOL(d_parent_ino);
+
 static __initdata unsigned long dhash_entries;
 static int __init set_dhash_entries(char *str)
 {

fs/exec.c

@@ -952,10 +952,6 @@ static struct file *do_open_execat(int fd, struct filename *name, int flags)
 			 path_noexec(&file->f_path)))
 		goto exit;
 
-	err = deny_write_access(file);
-	if (err)
-		goto exit;
-
 out:
 	return file;
 
@@ -971,8 +967,7 @@ exit:
  *
  * Returns ERR_PTR on failure or allocated struct file on success.
  *
- * As this is a wrapper for the internal do_open_execat(), callers
- * must call allow_write_access() before fput() on release. Also see
+ * As this is a wrapper for the internal do_open_execat(). Also see
  * do_close_execat().
  */
 struct file *open_exec(const char *name)
@@ -1524,10 +1519,8 @@ static int prepare_bprm_creds(struct linux_binprm *bprm)
 /* Matches do_open_execat() */
 static void do_close_execat(struct file *file)
 {
-	if (!file)
-		return;
-	allow_write_access(file);
-	fput(file);
+	if (file)
+		fput(file);
 }
 
 static void free_bprm(struct linux_binprm *bprm)
@@ -1846,7 +1839,6 @@ static int exec_binprm(struct linux_binprm *bprm)
 		bprm->file = bprm->interpreter;
 		bprm->interpreter = NULL;
 
-		allow_write_access(exec);
 		if (unlikely(bprm->have_execfd)) {
 			if (bprm->executable) {
 				fput(exec);

fs/exportfs/expfs.c

@@ -427,7 +427,7 @@ EXPORT_SYMBOL_GPL(exportfs_encode_fh);
 
 struct dentry *
 exportfs_decode_fh_raw(struct vfsmount *mnt, struct fid *fid, int fh_len,
-		       int fileid_type,
+		       int fileid_type, unsigned int flags,
 		       int (*acceptable)(void *, struct dentry *),
 		       void *context)
 {
@@ -445,6 +445,11 @@ exportfs_decode_fh_raw(struct vfsmount *mnt, struct fid *fid, int fh_len,
 	if (IS_ERR_OR_NULL(result))
 		return result;
 
+	if ((flags & EXPORT_FH_DIR_ONLY) && !d_is_dir(result)) {
+		err = -ENOTDIR;
+		goto err_result;
+	}
+
 	/*
 	 * If no acceptance criteria was specified by caller, a disconnected
 	 * dentry is also accepatable. Callers may use this mode to query if
@@ -581,7 +586,7 @@ struct dentry *exportfs_decode_fh(struct vfsmount *mnt, struct fid *fid,
 {
 	struct dentry *ret;
 
-	ret = exportfs_decode_fh_raw(mnt, fid, fh_len, fileid_type,
+	ret = exportfs_decode_fh_raw(mnt, fid, fh_len, fileid_type, 0,
 				     acceptable, context);
 	if (IS_ERR_OR_NULL(ret)) {
 		if (ret == ERR_PTR(-ENOMEM))

fs/f2fs/acl.c

@@ -219,8 +219,7 @@ static int f2fs_acl_update_mode(struct mnt_idmap *idmap,
 		return error;
 	if (error == 0)
 		*acl = NULL;
-	if (!vfsgid_in_group_p(i_gid_into_vfsgid(idmap, inode)) &&
-	    !capable_wrt_inode_uidgid(idmap, inode, CAP_FSETID))
+	if (!in_group_or_capable(idmap, inode, i_gid_into_vfsgid(idmap, inode)))
 		mode &= ~S_ISGID;
 	*mode_p = mode;
 	return 0;

fs/f2fs/file.c

@@ -185,7 +185,7 @@ static int get_parent_ino(struct inode *inode, nid_t *pino)
 	if (!dentry)
 		return 0;
 
-	*pino = parent_ino(dentry);
+	*pino = d_parent_ino(dentry);
 	dput(dentry);
 	return 1;
 }
@@ -923,10 +923,8 @@ static void __setattr_copy(struct mnt_idmap *idmap,
 		inode_set_ctime_to_ts(inode, attr->ia_ctime);
 	if (ia_valid & ATTR_MODE) {
 		umode_t mode = attr->ia_mode;
-		vfsgid_t vfsgid = i_gid_into_vfsgid(idmap, inode);
 
-		if (!vfsgid_in_group_p(vfsgid) &&
-		    !capable_wrt_inode_uidgid(idmap, inode, CAP_FSETID))
+		if (!in_group_or_capable(idmap, inode, i_gid_into_vfsgid(idmap, inode)))
 			mode &= ~S_ISGID;
 		set_acl_inode(inode, mode);
 	}

fs/fhandle.c

@@ -115,88 +115,188 @@ SYSCALL_DEFINE5(name_to_handle_at, int, dfd, const char __user *, name,
 	return err;
 }
 
-static struct vfsmount *get_vfsmount_from_fd(int fd)
+static int get_path_from_fd(int fd, struct path *root)
 {
-	struct vfsmount *mnt;
-
 	if (fd == AT_FDCWD) {
 		struct fs_struct *fs = current->fs;
 		spin_lock(&fs->lock);
-		mnt = mntget(fs->pwd.mnt);
+		*root = fs->pwd;
+		path_get(root);
 		spin_unlock(&fs->lock);
 	} else {
 		struct fd f = fdget(fd);
 		if (!f.file)
-			return ERR_PTR(-EBADF);
-		mnt = mntget(f.file->f_path.mnt);
+			return -EBADF;
+		*root = f.file->f_path;
+		path_get(root);
 		fdput(f);
 	}
-	return mnt;
+
+	return 0;
 }
 
+enum handle_to_path_flags {
+	HANDLE_CHECK_PERMS   = (1 << 0),
+	HANDLE_CHECK_SUBTREE = (1 << 1),
+};
+
+struct handle_to_path_ctx {
+	struct path root;
+	enum handle_to_path_flags flags;
+	unsigned int fh_flags;
+};
+
 static int vfs_dentry_acceptable(void *context, struct dentry *dentry)
 {
-	return 1;
-}
-
-static int do_handle_to_path(int mountdirfd, struct file_handle *handle,
-			     struct path *path)
-{
+	struct handle_to_path_ctx *ctx = context;
+	struct user_namespace *user_ns = current_user_ns();
+	struct dentry *d, *root = ctx->root.dentry;
+	struct mnt_idmap *idmap = mnt_idmap(ctx->root.mnt);
 	int retval = 0;
-	int handle_dwords;
 
-	path->mnt = get_vfsmount_from_fd(mountdirfd);
-	if (IS_ERR(path->mnt)) {
-		retval = PTR_ERR(path->mnt);
-		goto out_err;
+	if (!root)
+		return 1;
+
+	/* Old permission model with global CAP_DAC_READ_SEARCH. */
+	if (!ctx->flags)
+		return 1;
+
+	/*
+	 * It's racy as we're not taking rename_lock but we're able to ignore
+	 * permissions and we just need an approximation whether we were able
+	 * to follow a path to the file.
+	 *
+	 * It's also potentially expensive on some filesystems especially if
+	 * there is a deep path.
+	 */
+	d = dget(dentry);
+	while (d != root && !IS_ROOT(d)) {
+		struct dentry *parent = dget_parent(d);
+
+		/*
+		 * We know that we have the ability to override DAC permissions
+		 * as we've verified this earlier via CAP_DAC_READ_SEARCH. But
+		 * we also need to make sure that there aren't any unmapped
+		 * inodes in the path that would prevent us from reaching the
+		 * file.
+		 */
+		if (!privileged_wrt_inode_uidgid(user_ns, idmap,
+						 d_inode(parent))) {
+			dput(d);
+			dput(parent);
+			return retval;
+		}
+
+		dput(d);
+		d = parent;
 	}
-	/* change the handle size to multiple of sizeof(u32) */
-	handle_dwords = handle->handle_bytes >> 2;
-	path->dentry = exportfs_decode_fh(path->mnt,
-					  (struct fid *)handle->f_handle,
-					  handle_dwords, handle->handle_type,
-					  vfs_dentry_acceptable, NULL);
-	if (IS_ERR(path->dentry)) {
-		retval = PTR_ERR(path->dentry);
-		goto out_mnt;
-	}
-	return 0;
-out_mnt:
-	mntput(path->mnt);
-out_err:
+
+	if (!(ctx->flags & HANDLE_CHECK_SUBTREE) || d == root)
+		retval = 1;
+	WARN_ON_ONCE(d != root && d != root->d_sb->s_root);
+	dput(d);
 	return retval;
 }
 
+static int do_handle_to_path(struct file_handle *handle, struct path *path,
+			     struct handle_to_path_ctx *ctx)
+{
+	int handle_dwords;
+	struct vfsmount *mnt = ctx->root.mnt;
+
+	/* change the handle size to multiple of sizeof(u32) */
+	handle_dwords = handle->handle_bytes >> 2;
+	path->dentry = exportfs_decode_fh_raw(mnt,
+					  (struct fid *)handle->f_handle,
+					  handle_dwords, handle->handle_type,
+					  ctx->fh_flags,
+					  vfs_dentry_acceptable, ctx);
+	if (IS_ERR_OR_NULL(path->dentry)) {
+		if (path->dentry == ERR_PTR(-ENOMEM))
+			return -ENOMEM;
+		return -ESTALE;
+	}
+	path->mnt = mntget(mnt);
+	return 0;
+}
+
+/*
+ * Allow relaxed permissions of file handles if the caller has the
+ * ability to mount the filesystem or create a bind-mount of the
+ * provided @mountdirfd.
+ *
+ * In both cases the caller may be able to get an unobstructed way to
+ * the encoded file handle. If the caller is only able to create a
+ * bind-mount we need to verify that there are no locked mounts on top
+ * of it that could prevent us from getting to the encoded file.
+ *
+ * In principle, locked mounts can prevent the caller from mounting the
+ * filesystem but that only applies to procfs and sysfs neither of which
+ * support decoding file handles.
+ */
+static inline bool may_decode_fh(struct handle_to_path_ctx *ctx,
+				 unsigned int o_flags)
+{
+	struct path *root = &ctx->root;
+
+	/*
+	 * Restrict to O_DIRECTORY to provide a deterministic API that avoids a
+	 * confusing api in the face of disconnected non-dir dentries.
+	 *
+	 * There's only one dentry for each directory inode (VFS rule)...
+	 */
+	if (!(o_flags & O_DIRECTORY))
+		return false;
+
+	if (ns_capable(root->mnt->mnt_sb->s_user_ns, CAP_SYS_ADMIN))
+		ctx->flags = HANDLE_CHECK_PERMS;
+	else if (is_mounted(root->mnt) &&
+		 ns_capable(real_mount(root->mnt)->mnt_ns->user_ns,
+			    CAP_SYS_ADMIN) &&
+		 !has_locked_children(real_mount(root->mnt), root->dentry))
+		ctx->flags = HANDLE_CHECK_PERMS | HANDLE_CHECK_SUBTREE;
+	else
+		return false;
+
+	/* Are we able to override DAC permissions? */
+	if (!ns_capable(current_user_ns(), CAP_DAC_READ_SEARCH))
+		return false;
+
+	ctx->fh_flags = EXPORT_FH_DIR_ONLY;
+	return true;
+}
+
 static int handle_to_path(int mountdirfd, struct file_handle __user *ufh,
-		   struct path *path)
+		   struct path *path, unsigned int o_flags)
 {
 	int retval = 0;
 	struct file_handle f_handle;
 	struct file_handle *handle = NULL;
+	struct handle_to_path_ctx ctx = {};
 
-	/*
-	 * With handle we don't look at the execute bit on the
-	 * directory. Ideally we would like CAP_DAC_SEARCH.
-	 * But we don't have that
-	 */
-	if (!capable(CAP_DAC_READ_SEARCH)) {
-		retval = -EPERM;
+	retval = get_path_from_fd(mountdirfd, &ctx.root);
+	if (retval)
 		goto out_err;
+
+	if (!capable(CAP_DAC_READ_SEARCH) && !may_decode_fh(&ctx, o_flags)) {
+		retval = -EPERM;
+		goto out_path;
 	}
+
 	if (copy_from_user(&f_handle, ufh, sizeof(struct file_handle))) {
 		retval = -EFAULT;
-		goto out_err;
+		goto out_path;
 	}
 	if ((f_handle.handle_bytes > MAX_HANDLE_SZ) ||
 	    (f_handle.handle_bytes == 0)) {
 		retval = -EINVAL;
-		goto out_err;
+		goto out_path;
 	}
 	handle = kmalloc(struct_size(handle, f_handle, f_handle.handle_bytes),
 			 GFP_KERNEL);
 	if (!handle) {
 		retval = -ENOMEM;
-		goto out_err;
+		goto out_path;
 	}
 	/* copy the full handle */
 	*handle = f_handle;
@@ -207,10 +307,12 @@ static int handle_to_path(int mountdirfd, struct file_handle __user *ufh,
 		goto out_handle;
 	}
 
-	retval = do_handle_to_path(mountdirfd, handle, path);
+	retval = do_handle_to_path(handle, path, &ctx);
 
 out_handle:
 	kfree(handle);
+out_path:
+	path_put(&ctx.root);
 out_err:
 	return retval;
 }
@@ -223,7 +325,7 @@ static long do_handle_open(int mountdirfd, struct file_handle __user *ufh,
 	struct file *file;
 	int fd;
 
-	retval = handle_to_path(mountdirfd, ufh, &path);
+	retval = handle_to_path(mountdirfd, ufh, &path, open_flag);
 	if (retval)
 		return retval;
 

fs/fsopen.c

@@ -220,10 +220,6 @@ static int vfs_cmd_create(struct fs_context *fc, bool exclusive)
 	if (!mount_capable(fc))
 		return -EPERM;
 
-	/* require the new mount api */
-	if (exclusive && fc->ops == &legacy_fs_context_ops)
-		return -EOPNOTSUPP;
-
 	fc->phase = FS_CONTEXT_CREATING;
 	fc->exclusive = exclusive;
 
@@ -411,6 +407,7 @@ SYSCALL_DEFINE5(fsconfig,
 		case FSCONFIG_SET_PATH:
 		case FSCONFIG_SET_PATH_EMPTY:
 		case FSCONFIG_SET_FD:
+		case FSCONFIG_CMD_CREATE_EXCL:
 			ret = -EOPNOTSUPP;
 			goto out_f;
 		}
@@ -451,7 +448,7 @@ SYSCALL_DEFINE5(fsconfig,
 		fallthrough;
 	case FSCONFIG_SET_PATH:
 		param.type = fs_value_is_filename;
-		param.name = getname_flags(_value, lookup_flags, NULL);
+		param.name = getname_flags(_value, lookup_flags);
 		if (IS_ERR(param.name)) {
 			ret = PTR_ERR(param.name);
 			goto out_key;

fs/fuse/acl.c

@@ -146,8 +146,8 @@ int fuse_set_acl(struct mnt_idmap *idmap, struct dentry *dentry,
 		 * be stripped.
 		 */
 		if (fc->posix_acl &&
-		    !vfsgid_in_group_p(i_gid_into_vfsgid(&nop_mnt_idmap, inode)) &&
-		    !capable_wrt_inode_uidgid(&nop_mnt_idmap, inode, CAP_FSETID))
+		    !in_group_or_capable(&nop_mnt_idmap, inode,
+					 i_gid_into_vfsgid(&nop_mnt_idmap, inode)))
 			extra_flags |= FUSE_SETXATTR_ACL_KILL_SGID;
 
 		ret = fuse_setxattr(inode, name, value, size, 0, extra_flags);

fs/hfs/inode.c

@@ -200,6 +200,7 @@ struct inode *hfs_new_inode(struct inode *dir, const struct qstr *name, umode_t
 	HFS_I(inode)->flags = 0;
 	HFS_I(inode)->rsrc_inode = NULL;
 	HFS_I(inode)->fs_blocks = 0;
+	HFS_I(inode)->tz_secondswest = sys_tz.tz_minuteswest * 60;
 	if (S_ISDIR(mode)) {
 		inode->i_size = 2;
 		HFS_SB(sb)->folder_count++;
@@ -275,6 +276,8 @@ void hfs_inode_read_fork(struct inode *inode, struct hfs_extent *ext,
 	for (count = 0, i = 0; i < 3; i++)
 		count += be16_to_cpu(ext[i].count);
 	HFS_I(inode)->first_blocks = count;
+	HFS_I(inode)->cached_start = 0;
+	HFS_I(inode)->cached_blocks = 0;
 
 	inode->i_size = HFS_I(inode)->phys_size = log_size;
 	HFS_I(inode)->fs_blocks = (log_size + sb->s_blocksize - 1) >> sb->s_blocksize_bits;

fs/hfsplus/bfind.c

@@ -25,19 +25,8 @@ int hfs_find_init(struct hfs_btree *tree, struct hfs_find_data *fd)
 	fd->key = ptr + tree->max_key_len + 2;
 	hfs_dbg(BNODE_REFS, "find_init: %d (%p)\n",
 		tree->cnid, __builtin_return_address(0));
-	switch (tree->cnid) {
-	case HFSPLUS_CAT_CNID:
-		mutex_lock_nested(&tree->tree_lock, CATALOG_BTREE_MUTEX);
-		break;
-	case HFSPLUS_EXT_CNID:
-		mutex_lock_nested(&tree->tree_lock, EXTENTS_BTREE_MUTEX);
-		break;
-	case HFSPLUS_ATTR_CNID:
-		mutex_lock_nested(&tree->tree_lock, ATTR_BTREE_MUTEX);
-		break;
-	default:
-		BUG();
-	}
+	mutex_lock_nested(&tree->tree_lock,
+			hfsplus_btree_lock_class(tree));
 	return 0;
 }
 

fs/hfsplus/extents.c

@@ -430,7 +430,8 @@ int hfsplus_free_fork(struct super_block *sb, u32 cnid,
 		hfsplus_free_extents(sb, ext_entry, total_blocks - start,
 				     total_blocks);
 		total_blocks = start;
-		mutex_lock(&fd.tree->tree_lock);
+		mutex_lock_nested(&fd.tree->tree_lock,
+			hfsplus_btree_lock_class(fd.tree));
 	} while (total_blocks > blocks);
 	hfs_find_exit(&fd);
 
@@ -592,7 +593,8 @@ void hfsplus_file_truncate(struct inode *inode)
 					     alloc_cnt, alloc_cnt - blk_cnt);
 			hfsplus_dump_extent(hip->first_extents);
 			hip->first_blocks = blk_cnt;
-			mutex_lock(&fd.tree->tree_lock);
+			mutex_lock_nested(&fd.tree->tree_lock,
+				hfsplus_btree_lock_class(fd.tree));
 			break;
 		}
 		res = __hfsplus_ext_cache_extent(&fd, inode, alloc_cnt);
@@ -606,7 +608,8 @@ void hfsplus_file_truncate(struct inode *inode)
 		hfsplus_free_extents(sb, hip->cached_extents,
 				     alloc_cnt - start, alloc_cnt - blk_cnt);
 		hfsplus_dump_extent(hip->cached_extents);
-		mutex_lock(&fd.tree->tree_lock);
+		mutex_lock_nested(&fd.tree->tree_lock,
+				hfsplus_btree_lock_class(fd.tree));
 		if (blk_cnt > start) {
 			hip->extent_state |= HFSPLUS_EXT_DIRTY;
 			break;

fs/hfsplus/hfsplus_fs.h

@@ -553,6 +553,27 @@ static inline __be32 __hfsp_ut2mt(time64_t ut)
 	return cpu_to_be32(lower_32_bits(ut) + HFSPLUS_UTC_OFFSET);
 }
 
+static inline enum hfsplus_btree_mutex_classes
+hfsplus_btree_lock_class(struct hfs_btree *tree)
+{
+	enum hfsplus_btree_mutex_classes class;
+
+	switch (tree->cnid) {
+	case HFSPLUS_CAT_CNID:
+		class = CATALOG_BTREE_MUTEX;
+		break;
+	case HFSPLUS_EXT_CNID:
+		class = EXTENTS_BTREE_MUTEX;
+		break;
+	case HFSPLUS_ATTR_CNID:
+		class = ATTR_BTREE_MUTEX;
+		break;
+	default:
+		BUG();
+	}
+	return class;
+}
+
 /* compatibility */
 #define hfsp_mt2ut(t)		(struct timespec64){ .tv_sec = __hfsp_mt2ut(t) }
 #define hfsp_ut2mt(t)		__hfsp_ut2mt((t).tv_sec)

fs/hfsplus/ioctl.c

@@ -40,7 +40,7 @@ static int hfsplus_ioctl_bless(struct file *file, int __user *user_flags)
 
 	/* Directory containing the bootable system */
 	vh->finder_info[0] = bvh->finder_info[0] =
-		cpu_to_be32(parent_ino(dentry));
+		cpu_to_be32(d_parent_ino(dentry));
 
 	/*
 	 * Bootloader. Just using the inode here breaks in the case of
@@ -51,7 +51,7 @@ static int hfsplus_ioctl_bless(struct file *file, int __user *user_flags)
 
 	/* Per spec, the OS X system folder - same as finder_info[0] here */
 	vh->finder_info[5] = bvh->finder_info[5] =
-		cpu_to_be32(parent_ino(dentry));
+		cpu_to_be32(d_parent_ino(dentry));
 
 	mutex_unlock(&sbi->vh_mutex);
 	return 0;

fs/inode.c

@@ -2538,6 +2538,7 @@ bool in_group_or_capable(struct mnt_idmap *idmap,
 		return true;
 	return false;
 }
+EXPORT_SYMBOL(in_group_or_capable);
 
 /**
  * mode_strip_sgid - handle the sgid bit for non-directories

fs/internal.h

@@ -247,6 +247,8 @@ extern const struct dentry_operations ns_dentry_operations;
 int getname_statx_lookup_flags(int flags);
 int do_statx(int dfd, struct filename *filename, unsigned int flags,
 	     unsigned int mask, struct statx __user *buffer);
+int do_statx_fd(int fd, unsigned int flags, unsigned int mask,
+		struct statx __user *buffer);
 
 /*
  * fs/splice.c:
@@ -321,3 +323,15 @@ struct stashed_operations {
 int path_from_stashed(struct dentry **stashed, struct vfsmount *mnt, void *data,
 		      struct path *path);
 void stashed_dentry_prune(struct dentry *dentry);
+/**
+ * path_mounted - check whether path is mounted
+ * @path: path to check
+ *
+ * Determine whether @path refers to the root of a mount.
+ *
+ * Return: true if @path is the root of a mount, false if not.
+ */
+static inline bool path_mounted(const struct path *path)
+{
+	return path->mnt->mnt_root == path->dentry;
+}

fs/mount.h

@@ -152,3 +152,4 @@ static inline void move_from_ns(struct mount *mnt, struct list_head *dt_list)
 }
 
 extern void mnt_cursor_del(struct mnt_namespace *ns, struct mount *cursor);
+bool has_locked_children(struct mount *mnt, struct dentry *dentry);