exec: fix the racy usage of fs_struct->in_exec

check_unsafe_exec() sets fs->in_exec under cred_guard_mutex, then execve()
paths clear fs->in_exec lockless. This is fine if exec succeeds, but if it
fails we have the following race:

	T1 sets fs->in_exec = 1, fails, drops cred_guard_mutex

	T2 sets fs->in_exec = 1

	T1 clears fs->in_exec

	T2 continues with fs->in_exec == 0

Change fs/exec.c to clear fs->in_exec with cred_guard_mutex held.

Reported-by: [email protected]
Closes: https://lore.kernel.org/all/[email protected]/
Cc: [email protected]
Signed-off-by: Oleg Nesterov <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Christian Brauner <[email protected]>

Author: oleg-nesterov

fs/exec.c

@@ -1227,13 +1227,12 @@ int begin_new_exec(struct linux_binprm * bprm)
 	 */
 	bprm->point_of_no_return = true;
 
-	/*
-	 * Make this the only thread in the thread group.
-	 */
+	/* Make this the only thread in the thread group */
 	retval = de_thread(me);
 	if (retval)
 		goto out;
-
+	/* see the comment in check_unsafe_exec() */
+	current->fs->in_exec = 0;
 	/*
 	 * Cancel any io_uring activity across execve
 	 */
@@ -1495,6 +1494,8 @@ static void free_bprm(struct linux_binprm *bprm)
 	}
 	free_arg_pages(bprm);
 	if (bprm->cred) {
+		/* in case exec fails before de_thread() succeeds */
+		current->fs->in_exec = 0;
 		mutex_unlock(&current->signal->cred_guard_mutex);
 		abort_creds(bprm->cred);
 	}
@@ -1616,6 +1617,10 @@ static void check_unsafe_exec(struct linux_binprm *bprm)
 	 * suid exec because the differently privileged task
 	 * will be able to manipulate the current directory, etc.
 	 * It would be nice to force an unshare instead...
+	 *
+	 * Otherwise we set fs->in_exec = 1 to deny clone(CLONE_FS)
+	 * from another sub-thread until de_thread() succeeds, this
+	 * state is protected by cred_guard_mutex we hold.
 	 */
 	n_fs = 1;
 	spin_lock(&p->fs->lock);
@@ -1860,7 +1865,6 @@ static int bprm_execve(struct linux_binprm *bprm)
 
 	sched_mm_cid_after_execve(current);
 	/* execve succeeded */
-	current->fs->in_exec = 0;
 	current->in_execve = 0;
 	rseq_execve(current);
 	user_events_execve(current);
@@ -1879,7 +1883,6 @@ static int bprm_execve(struct linux_binprm *bprm)
 		force_fatal_sig(SIGSEGV);
 
 	sched_mm_cid_after_execve(current);
-	current->fs->in_exec = 0;
 	current->in_execve = 0;
 
 	return retval;