Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs

Pull vfs pile 1 from Al Viro:
 "Unfortunately, this merge window it'll have a be a lot of small piles -
  my fault, actually, for not keeping #for-next in anything that would
  resemble a sane shape ;-/

  This pile: assorted fixes (the first 3 are -stable fodder, IMO) and
  cleanups + %pd/%pD formats (dentry/file pathname, up to 4 last
  components) + several long-standing patches from various folks.

  There definitely will be a lot more (starting with Miklos'
  check_submount_and_drop() series)"

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: (26 commits)
  direct-io: Handle O_(D)SYNC AIO
  direct-io: Implement generic deferred AIO completions
  add formats for dentry/file pathnames
  kvm eventfd: switch to fdget
  powerpc kvm: use fdget
  switch fchmod() to fdget
  switch epoll_ctl() to fdget
  switch copy_module_from_fd() to fdget
  git simplify nilfs check for busy subtree
  ibmasmfs: don't bother passing superblock when not needed
  don't pass superblock to hypfs_{mkdir,create*}
  don't pass superblock to hypfs_diag_create_files
  don't pass superblock to hypfs_vm_create_files()
  oprofile: get rid of pointless forward declarations of struct super_block
  oprofilefs_create_...() do not need superblock argument
  oprofilefs_mkdir() doesn't need superblock argument
  don't bother with passing superblock to oprofile_create_stats_files()
  oprofile: don't bother with passing superblock to ->create_files()
  don't bother passing sb to oprofile_create_files()
  coh901318: don't open-code simple_read_from_buffer()
  ...

1 files changed, 182 insertions, 0 deletions

diff --git a/fs/namei.c b/fs/namei.c
index 2c30c84d4ea1..f415c6683a83 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -2222,6 +2222,188 @@ user_path_parent(int dfd, const char __user *path, struct nameidata *nd,
 	return s;
 }
 
+/**
+ * umount_lookup_last - look up last component for umount
+ * @nd:   pathwalk nameidata - currently pointing at parent directory of "last"
+ * @path: pointer to container for result
+ *
+ * This is a special lookup_last function just for umount. In this case, we
+ * need to resolve the path without doing any revalidation.
+ *
+ * The nameidata should be the result of doing a LOOKUP_PARENT pathwalk. Since
+ * mountpoints are always pinned in the dcache, their ancestors are too. Thus,
+ * in almost all cases, this lookup will be served out of the dcache. The only
+ * cases where it won't are if nd->last refers to a symlink or the path is
+ * bogus and it doesn't exist.
+ *
+ * Returns:
+ * -error: if there was an error during lookup. This includes -ENOENT if the
+ *         lookup found a negative dentry. The nd->path reference will also be
+ *         put in this case.
+ *
+ * 0:      if we successfully resolved nd->path and found it to not to be a
+ *         symlink that needs to be followed. "path" will also be populated.
+ *         The nd->path reference will also be put.
+ *
+ * 1:      if we successfully resolved nd->last and found it to be a symlink
+ *         that needs to be followed. "path" will be populated with the path
+ *         to the link, and nd->path will *not* be put.
+ */
+static int
+umount_lookup_last(struct nameidata *nd, struct path *path)
+{
+	int error = 0;
+	struct dentry *dentry;
+	struct dentry *dir = nd->path.dentry;
+
+	if (unlikely(nd->flags & LOOKUP_RCU)) {
+		WARN_ON_ONCE(1);
+		error = -ECHILD;
+		goto error_check;
+	}
+
+	nd->flags &= ~LOOKUP_PARENT;
+
+	if (unlikely(nd->last_type != LAST_NORM)) {
+		error = handle_dots(nd, nd->last_type);
+		if (!error)
+			dentry = dget(nd->path.dentry);
+		goto error_check;
+	}
+
+	mutex_lock(&dir->d_inode->i_mutex);
+	dentry = d_lookup(dir, &nd->last);
+	if (!dentry) {
+		/*
+		 * No cached dentry. Mounted dentries are pinned in the cache,
+		 * so that means that this dentry is probably a symlink or the
+		 * path doesn't actually point to a mounted dentry.
+		 */
+		dentry = d_alloc(dir, &nd->last);
+		if (!dentry) {
+			error = -ENOMEM;
+		} else {
+			dentry = lookup_real(dir->d_inode, dentry, nd->flags);
+			if (IS_ERR(dentry))
+				error = PTR_ERR(dentry);
+		}
+	}
+	mutex_unlock(&dir->d_inode->i_mutex);
+
+error_check:
+	if (!error) {
+		if (!dentry->d_inode) {
+			error = -ENOENT;
+			dput(dentry);
+		} else {
+			path->dentry = dentry;
+			path->mnt = mntget(nd->path.mnt);
+			if (should_follow_link(dentry->d_inode,
+						nd->flags & LOOKUP_FOLLOW))
+				return 1;
+			follow_mount(path);
+		}
+	}
+	terminate_walk(nd);
+	return error;
+}
+
+/**
+ * path_umountat - look up a path to be umounted
+ * @dfd:	directory file descriptor to start walk from
+ * @name:	full pathname to walk
+ * @flags:	lookup flags
+ * @nd:		pathwalk nameidata
+ *
+ * Look up the given name, but don't attempt to revalidate the last component.
+ * Returns 0 and "path" will be valid on success; Retuns error otherwise.
+ */
+static int
+path_umountat(int dfd, const char *name, struct path *path, unsigned int flags)
+{
+	struct file *base = NULL;
+	struct nameidata nd;
+	int err;
+
+	err = path_init(dfd, name, flags | LOOKUP_PARENT, &nd, &base);
+	if (unlikely(err))
+		return err;
+
+	current->total_link_count = 0;
+	err = link_path_walk(name, &nd);
+	if (err)
+		goto out;
+
+	/* If we're in rcuwalk, drop out of it to handle last component */
+	if (nd.flags & LOOKUP_RCU) {
+		err = unlazy_walk(&nd, NULL);
+		if (err) {
+			terminate_walk(&nd);
+			goto out;
+		}
+	}
+
+	err = umount_lookup_last(&nd, path);
+	while (err > 0) {
+		void *cookie;
+		struct path link = *path;
+		err = may_follow_link(&link, &nd);
+		if (unlikely(err))
+			break;
+		nd.flags |= LOOKUP_PARENT;
+		err = follow_link(&link, &nd, &cookie);
+		if (err)
+			break;
+		err = umount_lookup_last(&nd, path);
+		put_link(&nd, &link, cookie);
+	}
+out:
+	if (base)
+		fput(base);
+
+	if (nd.root.mnt && !(nd.flags & LOOKUP_ROOT))
+		path_put(&nd.root);
+
+	return err;
+}
+
+/**
+ * user_path_umountat - lookup a path from userland in order to umount it
+ * @dfd:	directory file descriptor
+ * @name:	pathname from userland
+ * @flags:	lookup flags
+ * @path:	pointer to container to hold result
+ *
+ * A umount is a special case for path walking. We're not actually interested
+ * in the inode in this situation, and ESTALE errors can be a problem. We
+ * simply want track down the dentry and vfsmount attached at the mountpoint
+ * and avoid revalidating the last component.
+ *
+ * Returns 0 and populates "path" on success.
+ */
+int
+user_path_umountat(int dfd, const char __user *name, unsigned int flags,
+			struct path *path)
+{
+	struct filename *s = getname(name);
+	int error;
+
+	if (IS_ERR(s))
+		return PTR_ERR(s);
+
+	error = path_umountat(dfd, s->name, path, flags | LOOKUP_RCU);
+	if (unlikely(error == -ECHILD))
+		error = path_umountat(dfd, s->name, path, flags);
+	if (unlikely(error == -ESTALE))
+		error = path_umountat(dfd, s->name, path, flags | LOOKUP_REVAL);
+
+	if (likely(!error))
+		audit_inode(s, path->dentry, 0);
+
+	putname(s);
+	return error;
+}
+
 /*
  * It's inline, so penalty for filesystems that don't use sticky bit is
  * minimal.