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

Pull vfs mount query updates from Christian Brauner:
 "This contains work to extend the abilities of listmount() and
  statmount() and various fixes and cleanups.

  Features:

   - Allow iterating through mounts via listmount() from newest to
     oldest. This makes it possible for mount(8) to keep iterating the
     mount table in reverse order so it gets newest mounts first.

   - Relax permissions on listmount() and statmount().

     It's not necessary to have capabilities in the initial namespace:
     it is sufficient to have capabilities in the owning namespace of
     the mount namespace we're located in to list unreachable mounts in
     that namespace.

   - Extend both listmount() and statmount() to list and stat mounts in
     foreign mount namespaces.

     Currently the only way to iterate over mount entries in mount
     namespaces that aren't in the caller's mount namespace is by
     crawling through /proc in order to find /proc/<pid>/mountinfo for
     the relevant mount namespace.

     This is both very clumsy and hugely inefficient. So extend struct
     mnt_id_req with a new member that allows to specify the mount
     namespace id of the mount namespace we want to look at.

     Luckily internally we already have most of the infrastructure for
     this so we just need to expose it to userspace. Give userspace a
     way to retrieve the id of a mount namespace via statmount() and
     through a new nsfs ioctl() on mount namespace file descriptor.

     This comes with appropriate selftests.

   - Expose mount options through statmount().

     Currently if userspace wants to get mount options for a mount and
     with statmount(), they still have to open /proc/<pid>/mountinfo to
     parse mount options. Simply the information through statmount()
     directly.

     Afterwards it's possible to only rely on statmount() and
     listmount() to retrieve all and more information than
     /proc/<pid>/mountinfo provides.

     This comes with appropriate selftests.

  Fixes:

   - Avoid copying to userspace under the namespace semaphore in
     listmount.

  Cleanups:

   - Simplify the error handling in listmount by relying on our newly
     added cleanup infrastructure.

   - Refuse invalid mount ids early for both listmount and statmount"

* tag 'vfs-6.11.mount' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs:
  fs: reject invalid last mount id early
  fs: refuse mnt id requests with invalid ids early
  fs: find rootfs mount of the mount namespace
  fs: only copy to userspace on success in listmount()
  sefltests: extend the statmount test for mount options
  fs: use guard for namespace_sem in statmount()
  fs: export mount options via statmount()
  fs: rename show_mnt_opts -> show_vfsmnt_opts
  selftests: add a test for the foreign mnt ns extensions
  fs: add an ioctl to get the mnt ns id from nsfs
  fs: Allow statmount() in foreign mount namespace
  fs: Allow listmount() in foreign mount namespace
  fs: export the mount ns id via statmount
  fs: keep an index of current mount namespaces
  fs: relax permissions for statmount()
  listmount: allow listing in reverse order
  fs: relax permissions for listmount()
  fs: simplify error handling
  fs: don't copy to userspace under namespace semaphore
  path: add cleanup helper

3 files changed, 19 insertions, 2 deletions

diff --git a/include/linux/path.h b/include/linux/path.h
index 475225a03d0d..ca073e70decd 100644
--- a/include/linux/path.h
+++ b/include/linux/path.h
@@ -24,4 +24,13 @@ static inline void path_put_init(struct path *path)
 	*path = (struct path) { };
 }
 
+/*
+ * Cleanup macro for use with __free(path_put). Avoids dereference and
+ * copying @path unlike DEFINE_FREE(). path_put() will handle the empty
+ * path correctly just ensure @path is initialized:
+ *
+ * struct path path __free(path_put) = {};
+ */
+#define __free_path_put path_put
+
 #endif  /* _LINUX_PATH_H */
diff --git a/include/uapi/linux/mount.h b/include/uapi/linux/mount.h
index ad5478dbad00..225bc366ffcb 100644
--- a/include/uapi/linux/mount.h
+++ b/include/uapi/linux/mount.h
@@ -154,7 +154,7 @@ struct mount_attr {
  */
 struct statmount {
 	__u32 size;		/* Total size, including strings */
-	__u32 __spare1;
+	__u32 mnt_opts;		/* [str] Mount options of the mount */
 	__u64 mask;		/* What results were written */
 	__u32 sb_dev_major;	/* Device ID */
 	__u32 sb_dev_minor;
@@ -172,7 +172,8 @@ struct statmount {
 	__u64 propagate_from;	/* Propagation from in current namespace */
 	__u32 mnt_root;		/* [str] Root of mount relative to root of fs */
 	__u32 mnt_point;	/* [str] Mountpoint relative to current root */
-	__u64 __spare2[50];
+	__u64 mnt_ns_id;	/* ID of the mount namespace */
+	__u64 __spare2[49];
 	char str[];		/* Variable size part containing strings */
 };
 
@@ -188,10 +189,12 @@ struct mnt_id_req {
 	__u32 spare;
 	__u64 mnt_id;
 	__u64 param;
+	__u64 mnt_ns_id;
 };
 
 /* List of all mnt_id_req versions. */
 #define MNT_ID_REQ_SIZE_VER0	24 /* sizeof first published struct */
+#define MNT_ID_REQ_SIZE_VER1	32 /* sizeof second published struct */
 
 /*
  * @mask bits for statmount(2)
@@ -202,10 +205,13 @@ struct mnt_id_req {
 #define STATMOUNT_MNT_ROOT		0x00000008U	/* Want/got mnt_root  */
 #define STATMOUNT_MNT_POINT		0x00000010U	/* Want/got mnt_point */
 #define STATMOUNT_FS_TYPE		0x00000020U	/* Want/got fs_type */
+#define STATMOUNT_MNT_NS_ID		0x00000040U	/* Want/got mnt_ns_id */
+#define STATMOUNT_MNT_OPTS		0x00000080U	/* Want/got mnt_opts */
 
 /*
  * Special @mnt_id values that can be passed to listmount
  */
 #define LSMT_ROOT		0xffffffffffffffff	/* root mount */
+#define LISTMOUNT_REVERSE	(1 << 0) /* List later mounts first */
 
 #endif /* _UAPI_LINUX_MOUNT_H */
diff --git a/include/uapi/linux/nsfs.h b/include/uapi/linux/nsfs.h
index a0c8552b64ee..56e8b1639b98 100644
--- a/include/uapi/linux/nsfs.h
+++ b/include/uapi/linux/nsfs.h
@@ -15,5 +15,7 @@
 #define NS_GET_NSTYPE		_IO(NSIO, 0x3)
 /* Get owner UID (in the caller's user namespace) for a user namespace */
 #define NS_GET_OWNER_UID	_IO(NSIO, 0x4)
+/* Get the id for a mount namespace */
+#define NS_GET_MNTNS_ID		_IO(NSIO, 0x5)
 
 #endif /* __LINUX_NSFS_H */