Merge tag 'vfs-7.3-rc1.kthread' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs

Pull kthread vfs updates from Christian Brauner:
 "This stops kernel threads from sharing filesystem state with
  userspace. This work is about 3 cycles old and has been in -next
  for about that time.

  When the kernel boots init_task creates PID 1 and then kthreadd. From
  that point every kthread and PID 1 share the same fs_struct. That is
  why pivot_root() has to rewrite the fs_struct of all kthreads. The
  rewriting exists so that kthreads can use init's filesystem state when
  they want to. It also means userspace can move the ground out from
  under the kernel.

  PID 1 now gets a completely separate fs_struct. All kthreads are
  anchored in a private SB_KERNMOUNT instance of nullfs that cannot be
  mounted on and cannot be used to follow other mounts. Userspace init
  can no longer affect kthread filesystem state and kthreads can no
  longer affect userspace fs state without explicit opting in to that.

  Path lookup from a kthread now fails by default. It makes it
  deliberately hard to offload security sensitive operations into init's
  filesystem state from a kthread.

  Places that legitimately need to look something up there opt in
  through the new scoped_with_init_fs() which temporarily overrides the
  caller's fs_struct with init's. usermodehelpers remain the only kernel
  tasks that genuinely share init's filesystem state, since they execute
  random binaries in the root filesystem (excellent...).

  The visible result is that /proc/2/root is a nullfs with an empty
  mountinfo while /proc/1/root is the real root"

* tag 'vfs-7.3-rc1.kthread' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs: (26 commits)
  initramfs_test: use test init/exit hooks to override init fs
  fs: stop rewriting paths for PF_EXITING | PF_DUMPCORE
  fs: stop rewriting kthread fs structs
  fs: start all kthreads in nullfs
  nullfs: make nullfs multi-instance
  devtmpfs: create private mount namespace
  fs: add umh argument to struct kernel_clone_args
  fs: stop sharing fs_struct between init_task and pid 1
  af_unix: use scoped_with_init_fs() for coredump socket lookup
  initramfs: use scoped_with_init_fs() for rootfs unpacking
  pnfs/blocklayout: use scoped_with_init_fs() for SCSI device lookup
  ksmbd: use scoped_with_init_fs() for VFS path operations
  ksmbd: use scoped_with_init_fs() for filesystem info path lookup
  ksmbd: use scoped_with_init_fs() for share path resolution
  fs: use scoped_with_init_fs() for kernel_read_file_from_path_initns()
  coredump: use scoped_with_init_fs() for coredump path resolution
  btrfs: use scoped_with_init_fs() for update_dev_time()
  scsi: target: use scoped_with_init_fs() for APTPL metadata
  scsi: target: use scoped_with_init_fs() for ALUA metadata
  crypto: ccp: use scoped_with_init_fs() for SEV file access
  ...

3 files changed, 36 insertions, 25 deletions

diff --git a/kernel/fork.c b/kernel/fork.c
index f0e2e131a9a5..94e021eabf1d 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1618,9 +1618,27 @@ static int copy_exec_state(u64 clone_flags, struct task_struct *tsk)
 	return task_exec_state_copy(tsk);
 }
 
-static int copy_fs(u64 clone_flags, struct task_struct *tsk)
+static int copy_fs(u64 clone_flags, struct task_struct *tsk, bool umh)
 {
-	struct fs_struct *fs = current->fs;
+	struct fs_struct *fs;
+
+	/*
+	 * Usermodehelper may copy userspace_init_fs filesystem state but
+	 * they don't get to create mount namespaces, share the
+	 * filesystem state, or be started from a non-initial mount
+	 * namespace.
+	 */
+	if (umh) {
+		if (clone_flags & (CLONE_NEWNS | CLONE_FS))
+			return -EINVAL;
+		if (current->nsproxy->mnt_ns != &init_mnt_ns)
+			return -EINVAL;
+		fs = userspace_init_fs;
+	} else {
+		fs = current->fs;
+		VFS_WARN_ON_ONCE(current->fs != current->real_fs);
+	}
+
 	if (clone_flags & CLONE_FS) {
 		/* tsk->fs is already what we want */
 		read_seqlock_excl(&fs->seq);
@@ -1633,7 +1651,7 @@ static int copy_fs(u64 clone_flags, struct task_struct *tsk)
 		read_sequnlock_excl(&fs->seq);
 		return 0;
 	}
-	tsk->fs = copy_fs_struct(fs);
+	tsk->real_fs = tsk->fs = copy_fs_struct(fs);
 	if (!tsk->fs)
 		return -ENOMEM;
 	return 0;
@@ -2277,7 +2295,7 @@ __latent_entropy struct task_struct *copy_process(
 	retval = copy_files(clone_flags, p, args->no_files);
 	if (retval)
 		goto bad_fork_cleanup_semundo;
-	retval = copy_fs(clone_flags, p);
+	retval = copy_fs(clone_flags, p, args->umh);
 	if (retval)
 		goto bad_fork_cleanup_files;
 	retval = copy_sighand(clone_flags, p);
@@ -2819,6 +2837,7 @@ pid_t user_mode_thread(int (*fn)(void *), void *arg, unsigned long flags)
 		.exit_signal	= (flags & CSIGNAL),
 		.fn		= fn,
 		.fn_arg		= arg,
+		.umh		= 1,
 	};
 
 	return kernel_clone(&args);
@@ -3216,7 +3235,7 @@ static int unshare_fd(unsigned long unshare_flags, struct files_struct **new_fdp
  */
 int ksys_unshare(unsigned long unshare_flags)
 {
-	struct fs_struct *fs, *new_fs = NULL;
+	struct fs_struct *new_fs = NULL;
 	struct files_struct *new_fd = NULL;
 	struct cred *new_cred = NULL;
 	struct nsproxy *new_nsproxy = NULL;
@@ -3247,6 +3266,10 @@ int ksys_unshare(unsigned long unshare_flags)
 	if (unshare_flags & CLONE_NEWNS)
 		unshare_flags |= CLONE_FS;
 
+	/* No unsharing with overriden fs state */
+	VFS_WARN_ON_ONCE(unshare_flags & (CLONE_NEWNS | CLONE_FS) &&
+			 current->fs != current->real_fs);
+
 	err = check_unshare_flags(unshare_flags);
 	if (err)
 		goto bad_unshare_out;
@@ -3294,23 +3317,13 @@ int ksys_unshare(unsigned long unshare_flags)
 			new_nsproxy = NULL;
 		}
 
-		task_lock(current);
+		if (new_fs)
+			new_fs = switch_fs_struct(new_fs);
 
-		if (new_fs) {
-			fs = current->fs;
-			read_seqlock_excl(&fs->seq);
-			current->fs = new_fs;
-			if (--fs->users)
-				new_fs = NULL;
-			else
-				new_fs = fs;
-			read_sequnlock_excl(&fs->seq);
-		}
-
-		if (new_fd)
+		if (new_fd) {
+			guard(task_lock)(current);
 			swap(current->files, new_fd);
-
-		task_unlock(current);
+		}
 
 		if (new_cred) {
 			/* Install the new user namespace */
diff --git a/kernel/kcmp.c b/kernel/kcmp.c
index 7c1a65bd5f8d..76476aeee067 100644
--- a/kernel/kcmp.c
+++ b/kernel/kcmp.c
@@ -186,7 +186,7 @@ SYSCALL_DEFINE5(kcmp, pid_t, pid1, pid_t, pid2, int, type,
 		ret = kcmp_ptr(task1->files, task2->files, KCMP_FILES);
 		break;
 	case KCMP_FS:
-		ret = kcmp_ptr(task1->fs, task2->fs, KCMP_FS);
+		ret = kcmp_ptr(task1->real_fs, task2->real_fs, KCMP_FS);
 		break;
 	case KCMP_SIGHAND:
 		ret = kcmp_ptr(task1->sighand, task2->sighand, KCMP_SIGHAND);
diff --git a/kernel/umh.c b/kernel/umh.c
index 48117c569e1a..6e2c7bb315c6 100644
--- a/kernel/umh.c
+++ b/kernel/umh.c
@@ -71,10 +71,8 @@ static int call_usermodehelper_exec_async(void *data)
 	spin_unlock_irq(&current->sighand->siglock);
 
 	/*
-	 * Initial kernel threads share ther FS with init, in order to
-	 * get the init root directory. But we've now created a new
-	 * thread that is going to execve a user process and has its own
-	 * 'struct fs_struct'. Reset umask to the default.
+	 * Usermodehelper threads get a copy of userspace init's
+	 * fs_struct. Reset umask to the default.
 	 */
 	current->fs->umask = 0022;