Merge tag 'pull-automount' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs

Pull automount updates from Al Viro:
 "Automount wart removal

  A bunch of odd boilerplate gone from instances - the reason for
  those was the need to protect the yet-to-be-attched mount from
  mark_mounts_for_expiry() deciding to take it out.

  But that's easy to detect and take care of in mark_mounts_for_expiry()
  itself; no need to have every instance simulate mount being busy by
  grabbing an extra reference to it, with finish_automount() undoing
  that once it attaches that mount.

  Should've done it that way from the very beginning... This is a
  flagday change, thankfully there are very few instances.

  vfs_submount() is gone - its sole remaining user (trace_automount)
  had been switched to saner primitives"

* tag 'pull-automount' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs:
  kill vfs_submount()
  saner calling conventions for ->d_automount()

Author: torvalds

Documentation/filesystems/porting.rst

@@ -1243,3 +1243,9 @@ arguments in the opposite order but is otherwise identical.
 
 Using try_lookup_noperm() will require linux/namei.h to be included.
 
+---
+
+**mandatory**
+
+Calling conventions for ->d_automount() have changed; we should *not* grab
+an extra reference to new mount - it should be returned with refcount 1.

Documentation/filesystems/vfs.rst

@@ -1390,9 +1390,7 @@ defined:
 
 	If a vfsmount is returned, the caller will attempt to mount it
 	on the mountpoint and will remove the vfsmount from its
-	expiration list in the case of failure.  The vfsmount should be
-	returned with 2 refs on it to prevent automatic expiration - the
-	caller will clean up the additional ref.
+	expiration list in the case of failure.
 
 	This function is only used if DCACHE_NEED_AUTOMOUNT is set on
 	the dentry.  This is set by __d_instantiate() if S_AUTOMOUNT is

fs/afs/mntpt.c

@@ -189,7 +189,6 @@ struct vfsmount *afs_d_automount(struct path *path)
 	if (IS_ERR(newmnt))
 		return newmnt;
 
-	mntget(newmnt); /* prevent immediate expiration */
 	mnt_set_expiry(newmnt, &afs_vfsmounts);
 	queue_delayed_work(afs_wq, &afs_mntpt_expiry_timer,
 			   afs_mntpt_expiry_timeout * HZ);

fs/fuse/dir.c

@@ -319,9 +319,6 @@ static struct vfsmount *fuse_dentry_automount(struct path *path)
 
 	/* Create the submount */
 	mnt = fc_mount(fsc);
-	if (!IS_ERR(mnt))
-		mntget(mnt);
-
 	put_fs_context(fsc);
 	return mnt;
 }

fs/namespace.c

@@ -1326,21 +1326,6 @@ struct vfsmount *vfs_kern_mount(struct file_system_type *type,
 }
 EXPORT_SYMBOL_GPL(vfs_kern_mount);
 
-struct vfsmount *
-vfs_submount(const struct dentry *mountpoint, struct file_system_type *type,
-	     const char *name, void *data)
-{
-	/* Until it is worked out how to pass the user namespace
-	 * through from the parent mount to the submount don't support
-	 * unprivileged mounts with submounts.
-	 */
-	if (mountpoint->d_sb->s_user_ns != &init_user_ns)
-		return ERR_PTR(-EPERM);
-
-	return vfs_kern_mount(type, SB_SUBMOUNT, name, data);
-}
-EXPORT_SYMBOL_GPL(vfs_submount);
-
 static struct mount *clone_mnt(struct mount *old, struct dentry *root,
 					int flag)
 {
@@ -3889,10 +3874,6 @@ int finish_automount(struct vfsmount *m, const struct path *path)
 		return PTR_ERR(m);
 
 	mnt = real_mount(m);
-	/* The new mount record should have at least 2 refs to prevent it being
-	 * expired before we get a chance to add it
-	 */
-	BUG_ON(mnt_get_count(mnt) < 2);
 
 	if (m->mnt_sb == path->mnt->mnt_sb &&
 	    m->mnt_root == dentry) {
@@ -3925,7 +3906,6 @@ int finish_automount(struct vfsmount *m, const struct path *path)
 	unlock_mount(mp);
 	if (unlikely(err))
 		goto discard;
-	mntput(m);
 	return 0;
 
 discard_locked:
@@ -3939,7 +3919,6 @@ int finish_automount(struct vfsmount *m, const struct path *path)
 		namespace_unlock();
 	}
 	mntput(m);
-	mntput(m);
 	return err;
 }
 
@@ -3976,11 +3955,14 @@ void mark_mounts_for_expiry(struct list_head *mounts)
 
 	/* extract from the expiration list every vfsmount that matches the
 	 * following criteria:
+	 * - already mounted
 	 * - only referenced by its parent vfsmount
 	 * - still marked for expiry (marked on the last call here; marks are
 	 *   cleared by mntput())
 	 */
 	list_for_each_entry_safe(mnt, next, mounts, mnt_expire) {
+		if (!is_mounted(&mnt->mnt))
+			continue;
 		if (!xchg(&mnt->mnt_expiry_mark, 1) ||
 			propagate_mount_busy(mnt, 1))
 			continue;

fs/nfs/namespace.c

@@ -195,7 +195,6 @@ struct vfsmount *nfs_d_automount(struct path *path)
 	if (IS_ERR(mnt))
 		goto out_fc;
 
-	mntget(mnt); /* prevent immediate expiration */
 	if (timeout <= 0)
 		goto out_fc;
 

fs/smb/client/namespace.c

@@ -283,7 +283,6 @@ struct vfsmount *cifs_d_automount(struct path *path)
 		return newmnt;
 	}
 
-	mntget(newmnt); /* prevent immediate expiration */
 	mnt_set_expiry(newmnt, &cifs_automount_list);
 	schedule_delayed_work(&cifs_automount_task,
 			      cifs_mountpoint_expiry_timeout);

fs/super.c

@@ -824,13 +824,6 @@ struct super_block *sget(struct file_system_type *type,
 	struct super_block *old;
 	int err;
 
-	/* We don't yet pass the user namespace of the parent
-	 * mount through to here so always use &init_user_ns
-	 * until that changes.
-	 */
-	if (flags & SB_SUBMOUNT)
-		user_ns = &init_user_ns;
-
 retry:
 	spin_lock(&sb_lock);
 	if (test) {
@@ -850,7 +843,7 @@ struct super_block *sget(struct file_system_type *type,
 	}
 	if (!s) {
 		spin_unlock(&sb_lock);
-		s = alloc_super(type, (flags & ~SB_SUBMOUNT), user_ns);
+		s = alloc_super(type, flags, user_ns);
 		if (!s)
 			return ERR_PTR(-ENOMEM);
 		goto retry;

include/linux/fs.h

@@ -1250,7 +1250,6 @@ extern int send_sigurg(struct file *file);
 /* These sb flags are internal to the kernel */
 #define SB_DEAD         BIT(21)
 #define SB_DYING        BIT(24)
-#define SB_SUBMOUNT     BIT(26)
 #define SB_FORCE        BIT(27)
 #define SB_NOSEC        BIT(28)
 #define SB_BORN         BIT(29)

include/linux/mount.h

@@ -101,9 +101,6 @@ extern struct vfsmount *vfs_create_mount(struct fs_context *fc);
 extern struct vfsmount *vfs_kern_mount(struct file_system_type *type,
 				      int flags, const char *name,
 				      void *data);
-extern struct vfsmount *vfs_submount(const struct dentry *mountpoint,
-				     struct file_system_type *type,
-				     const char *name, void *data);
 
 extern void mnt_set_expiry(struct vfsmount *mnt, struct list_head *expiry_list);
 extern void mark_mounts_for_expiry(struct list_head *mounts);

kernel/trace/trace.c

@@ -51,6 +51,7 @@
 #include <linux/workqueue.h>
 #include <linux/sort.h>
 #include <linux/io.h> /* vmap_page_range() */
+#include <linux/fs_context.h>
 
 #include <asm/setup.h> /* COMMAND_LINE_SIZE */
 
@@ -10241,6 +10242,8 @@ static struct vfsmount *trace_automount(struct dentry *mntpt, void *ingore)
 {
 	struct vfsmount *mnt;
 	struct file_system_type *type;
+	struct fs_context *fc;
+	int ret;
 
 	/*
 	 * To maintain backward compatibility for tools that mount
@@ -10250,12 +10253,20 @@ static struct vfsmount *trace_automount(struct dentry *mntpt, void *ingore)
 	type = get_fs_type("tracefs");
 	if (!type)
 		return NULL;
-	mnt = vfs_submount(mntpt, type, "tracefs", NULL);
+
+	fc = fs_context_for_submount(type, mntpt);
 	put_filesystem(type);
-	if (IS_ERR(mnt))
-		return NULL;
-	mntget(mnt);
+	if (IS_ERR(fc))
+		return ERR_CAST(fc);
+
+	ret = vfs_parse_fs_string(fc, "source",
+				  "tracefs", strlen("tracefs"));
+	if (!ret)
+		mnt = fc_mount(fc);
+	else
+		mnt = ERR_PTR(ret);
 
+	put_fs_context(fc);
 	return mnt;
 }