Merge tag 'vfs-6.15-rc1.mount' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs

Pull vfs mount updates from Christian Brauner:

 - Mount notifications

   The day has come where we finally provide a new api to listen for
   mount topology changes outside of /proc/<pid>/mountinfo. A mount
   namespace file descriptor can be supplied and registered with
   fanotify to listen for mount topology changes.

   Currently notifications for mount, umount and moving mounts are
   generated. The generated notification record contains the unique
   mount id of the mount.

   The listmount() and statmount() api can be used to query detailed
   information about the mount using the received unique mount id.

   This allows userspace to figure out exactly how the mount topology
   changed without having to generating diffs of /proc/<pid>/mountinfo
   in userspace.

 - Support O_PATH file descriptors with FSCONFIG_SET_FD in the new mount
   api

 - Support detached mounts in overlayfs

   Since last cycle we support specifying overlayfs layers via file
   descriptors. However, we don't allow detached mounts which means
   userspace cannot user file descriptors received via
   open_tree(OPEN_TREE_CLONE) and fsmount() directly. They have to
   attach them to a mount namespace via move_mount() first.

   This is cumbersome and means they have to undo mounts via umount().
   Allow them to directly use detached mounts.

 - Allow to retrieve idmappings with statmount

   Currently it isn't possible to figure out what idmapping has been
   attached to an idmapped mount. Add an extension to statmount() which
   allows to read the idmapping from the mount.

 - Allow creating idmapped mounts from mounts that are already idmapped

   So far it isn't possible to allow the creation of idmapped mounts
   from already idmapped mounts as this has significant lifetime
   implications. Make the creation of idmapped mounts atomic by allow to
   pass struct mount_attr together with the open_tree_attr() system call
   allowing to solve these issues without complicating VFS lookup in any
   way.

   The system call has in general the benefit that creating a detached
   mount and applying mount attributes to it becomes an atomic operation
   for userspace.

 - Add a way to query statmount() for supported options

   Allow userspace to query which mount information can be retrieved
   through statmount().

 - Allow superblock owners to force unmount

* tag 'vfs-6.15-rc1.mount' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs: (21 commits)
  umount: Allow superblock owners to force umount
  selftests: add tests for mount notification
  selinux: add FILE__WATCH_MOUNTNS
  samples/vfs: fix printf format string for size_t
  fs: allow changing idmappings
  fs: add kflags member to struct mount_kattr
  fs: add open_tree_attr()
  fs: add copy_mount_setattr() helper
  fs: add vfs_open_tree() helper
  statmount: add a new supported_mask field
  samples/vfs: add STATMOUNT_MNT_{G,U}IDMAP
  selftests: add tests for using detached mount with overlayfs
  samples/vfs: check whether flag was raised
  statmount: allow to retrieve idmappings
  uidgid: add map_id_range_up()
  fs: allow detached mounts in clone_private_mount()
  selftests/overlayfs: test specifying layers as O_PATH file descriptors
  fs: support O_PATH fds with FSCONFIG_SET_FD
  vfs: add notifications for mount attach and detach
  fanotify: notify on mount attach and detach
  ...

2 files changed, 42 insertions, 7 deletions

diff --git a/samples/vfs/samples-vfs.h b/samples/vfs/samples-vfs.h
index 103e1e7c4cec..498baf581b56 100644
--- a/samples/vfs/samples-vfs.h
+++ b/samples/vfs/samples-vfs.h
@@ -42,7 +42,11 @@ struct statmount {
 	__u32 opt_array;	/* [str] Array of nul terminated fs options */
 	__u32 opt_sec_num;	/* Number of security options */
 	__u32 opt_sec_array;	/* [str] Array of nul terminated security options */
-	__u64 __spare2[46];
+	__u32 mnt_uidmap_num;	/* Number of uid mappings */
+	__u32 mnt_uidmap;	/* [str] Array of uid mappings */
+	__u32 mnt_gidmap_num;	/* Number of gid mappings */
+	__u32 mnt_gidmap;	/* [str] Array of gid mappings */
+	__u64 __spare2[44];
 	char str[];		/* Variable size part containing strings */
 };
 
@@ -158,6 +162,14 @@ struct mnt_ns_info {
 #define STATX_MNT_ID_UNIQUE 0x00004000U /* Want/got extended stx_mount_id */
 #endif
 
+#ifndef STATMOUNT_MNT_UIDMAP
+#define STATMOUNT_MNT_UIDMAP		0x00002000U	/* Want/got uidmap... */
+#endif
+
+#ifndef STATMOUNT_MNT_GIDMAP
+#define STATMOUNT_MNT_GIDMAP		0x00004000U	/* Want/got gidmap... */
+#endif
+
 #ifndef MOUNT_ATTR_RDONLY
 #define MOUNT_ATTR_RDONLY	0x00000001 /* Mount read-only */
 #endif
diff --git a/samples/vfs/test-list-all-mounts.c b/samples/vfs/test-list-all-mounts.c
index 1a02ea4593e3..713c174626aa 100644
--- a/samples/vfs/test-list-all-mounts.c
+++ b/samples/vfs/test-list-all-mounts.c
@@ -128,20 +128,43 @@ next:
 					      STATMOUNT_MNT_POINT |
 					      STATMOUNT_MNT_NS_ID |
 					      STATMOUNT_MNT_OPTS |
-					      STATMOUNT_FS_TYPE, 0);
+					      STATMOUNT_FS_TYPE |
+					      STATMOUNT_MNT_UIDMAP |
+					      STATMOUNT_MNT_GIDMAP, 0);
 			if (!stmnt) {
 				printf("Failed to statmount(%" PRIu64 ") in mount namespace(%" PRIu64 ")\n",
 				       (uint64_t)last_mnt_id, (uint64_t)info.mnt_ns_id);
 				continue;
 			}
 
-			printf("mnt_id:\t\t%" PRIu64 "\nmnt_parent_id:\t%" PRIu64 "\nfs_type:\t%s\nmnt_root:\t%s\nmnt_point:\t%s\nmnt_opts:\t%s\n\n",
+			printf("mnt_id:\t\t%" PRIu64 "\nmnt_parent_id:\t%" PRIu64 "\nfs_type:\t%s\nmnt_root:\t%s\nmnt_point:\t%s\nmnt_opts:\t%s\n",
 			       (uint64_t)stmnt->mnt_id,
 			       (uint64_t)stmnt->mnt_parent_id,
-			       stmnt->str + stmnt->fs_type,
-			       stmnt->str + stmnt->mnt_root,
-			       stmnt->str + stmnt->mnt_point,
-			       stmnt->str + stmnt->mnt_opts);
+			       (stmnt->mask & STATMOUNT_FS_TYPE)   ? stmnt->str + stmnt->fs_type   : "",
+			       (stmnt->mask & STATMOUNT_MNT_ROOT)  ? stmnt->str + stmnt->mnt_root  : "",
+			       (stmnt->mask & STATMOUNT_MNT_POINT) ? stmnt->str + stmnt->mnt_point : "",
+			       (stmnt->mask & STATMOUNT_MNT_OPTS)  ? stmnt->str + stmnt->mnt_opts  : "");
+
+			if (stmnt->mask & STATMOUNT_MNT_UIDMAP) {
+				const char *idmap = stmnt->str + stmnt->mnt_uidmap;
+
+				for (size_t idx = 0; idx < stmnt->mnt_uidmap_num; idx++) {
+					printf("mnt_uidmap[%zu]:\t%s\n", idx, idmap);
+					idmap += strlen(idmap) + 1;
+				}
+			}
+
+			if (stmnt->mask & STATMOUNT_MNT_GIDMAP) {
+				const char *idmap = stmnt->str + stmnt->mnt_gidmap;
+
+				for (size_t idx = 0; idx < stmnt->mnt_gidmap_num; idx++) {
+					printf("mnt_gidmap[%zu]:\t%s\n", idx, idmap);
+					idmap += strlen(idmap) + 1;
+				}
+			}
+
+			printf("\n");
+
 			free(stmnt);
 		}
 	}