Merge tag 'vfs-7.0-rc1.namespace' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs

Pull vfs mount updates from Christian Brauner:

 - statmount: accept fd as a parameter

   Extend struct mnt_id_req with a file descriptor field and a new
   STATMOUNT_BY_FD flag. When set, statmount() returns mount information
   for the mount the fd resides on — including detached mounts
   (unmounted via umount2(MNT_DETACH)).

   For detached mounts the STATMOUNT_MNT_POINT and STATMOUNT_MNT_NS_ID
   mask bits are cleared since neither is meaningful. The capability
   check is skipped for STATMOUNT_BY_FD since holding an fd already
   implies prior access to the mount and equivalent information is
   available through fstatfs() and /proc/pid/mountinfo without
   privilege. Includes comprehensive selftests covering both attached
   and detached mount cases.

 - fs: Remove internal old mount API code (1 patch)

   Now that every in-tree filesystem has been converted to the new
   mount API, remove all the legacy shim code in fs_context.c that
   handled unconverted filesystems. This deletes ~280 lines including
   legacy_init_fs_context(), the legacy_fs_context struct, and
   associated wrappers. The mount(2) syscall path for userspace remains
   untouched. Documentation references to the legacy callbacks are
   cleaned up.

 - mount: add OPEN_TREE_NAMESPACE to open_tree()

   Container runtimes currently use CLONE_NEWNS to copy the caller's
   entire mount namespace — only to then pivot_root() and recursively
   unmount everything they just copied. With large mount tables and
   thousands of parallel container launches this creates significant
   contention on the namespace semaphore.

   OPEN_TREE_NAMESPACE copies only the specified mount tree (like
   OPEN_TREE_CLONE) but returns a mount namespace fd instead of a
   detached mount fd. The new namespace contains the copied tree mounted
   on top of a clone of the real rootfs.

   This functions as a combined unshare(CLONE_NEWNS) + pivot_root() in a
   single syscall. Works with user namespaces: an unshare(CLONE_NEWUSER)
   followed by OPEN_TREE_NAMESPACE creates a mount namespace owned by
   the new user namespace. Mount namespace file mounts are excluded from
   the copy to prevent cycles. Includes ~1000 lines of selftests"

* tag 'vfs-7.0-rc1.namespace' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs:
  selftests/open_tree: add OPEN_TREE_NAMESPACE tests
  mount: add OPEN_TREE_NAMESPACE
  fs: Remove internal old mount API code
  selftests: statmount: tests for STATMOUNT_BY_FD
  statmount: accept fd as a parameter
  statmount: permission check should return EPERM

3 files changed, 11 insertions, 5 deletions

diff --git a/include/linux/fs.h b/include/linux/fs.h
index 01f73f1eeb7b..ca31bc9308a3 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2282,8 +2282,6 @@ struct file_system_type {
 #define FS_RENAME_DOES_D_MOVE	32768	/* FS will handle d_move() during rename() internally. */
 	int (*init_fs_context)(struct fs_context *);
 	const struct fs_parameter_spec *parameters;
-	struct dentry *(*mount) (struct file_system_type *, int,
-		       const char *, void *);
 	void (*kill_sb) (struct super_block *);
 	struct module *owner;
 	struct file_system_type * next;
diff --git a/include/linux/fs/super_types.h b/include/linux/fs/super_types.h
index 97a8552d8f2b..fa7638b81246 100644
--- a/include/linux/fs/super_types.h
+++ b/include/linux/fs/super_types.h
@@ -97,7 +97,6 @@ struct super_operations {
 			  const void *owner);
 	int (*unfreeze_fs)(struct super_block *sb);
 	int (*statfs)(struct dentry *dentry, struct kstatfs *kstatfs);
-	int (*remount_fs) (struct super_block *, int *, char *);
 	void (*umount_begin)(struct super_block *sb);
 
 	int (*show_options)(struct seq_file *seq, struct dentry *dentry);
diff --git a/include/uapi/linux/mount.h b/include/uapi/linux/mount.h
index 5d3f8c9e3a62..d9d86598d100 100644
--- a/include/uapi/linux/mount.h
+++ b/include/uapi/linux/mount.h
@@ -61,7 +61,8 @@
 /*
  * open_tree() flags.
  */
-#define OPEN_TREE_CLONE		1		/* Clone the target tree and attach the clone */
+#define OPEN_TREE_CLONE		(1 << 0)	/* Clone the target tree and attach the clone */
+#define OPEN_TREE_NAMESPACE	(1 << 1)	/* Clone the target tree into a new mount namespace */
 #define OPEN_TREE_CLOEXEC	O_CLOEXEC	/* Close the file on execve() */
 
 /*
@@ -197,7 +198,10 @@ struct statmount {
  */
 struct mnt_id_req {
 	__u32 size;
-	__u32 mnt_ns_fd;
+	union {
+		__u32 mnt_ns_fd;
+		__u32 mnt_fd;
+	};
 	__u64 mnt_id;
 	__u64 param;
 	__u64 mnt_ns_id;
@@ -232,4 +236,9 @@ struct mnt_id_req {
 #define LSMT_ROOT		0xffffffffffffffff	/* root mount */
 #define LISTMOUNT_REVERSE	(1 << 0) /* List later mounts first */
 
+/*
+ * @flag bits for statmount(2)
+ */
+#define STATMOUNT_BY_FD		0x00000001U	/* want mountinfo for given fd */
+
 #endif /* _UAPI_LINUX_MOUNT_H */