do_execve() must not clear fs->in_exec if it was set by another thread

If do_execve() fails after check_unsafe_exec(), it clears fs->in_exec
unconditionally. This is wrong if we race with our sub-thread which
also does do_execve:

	Two threads T1 and T2 and another process P, all share the same
	->fs.

	T1 starts do_execve(BAD_FILE). It calls check_unsafe_exec(), since
	->fs is shared, we set LSM_UNSAFE but not ->in_exec.

	P exits and decrements fs->users.

	T2 starts do_execve(), calls check_unsafe_exec(), now ->fs is not
	shared, we set fs->in_exec.

	T1 continues, open_exec(BAD_FILE) fails, we clear ->in_exec and
	return to the user-space.

	T1 does clone(CLONE_FS /* without CLONE_THREAD */).

	T2 continues without LSM_UNSAFE_SHARE while ->fs is shared with
	another process.

Change check_unsafe_exec() to return res = 1 if we set ->in_exec, and change
do_execve() to clear ->in_exec depending on res.

When do_execve() suceeds, it is safe to clear ->in_exec unconditionally.
It can be set only if we don't share ->fs with another process, and since
we already killed all sub-threads either ->in_exec == 0 or we are the
only user of this ->fs.

Also, we do not need fs->lock to clear fs->in_exec.

Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Acked-by: Roland McGrath <roland@redhat.com>
Acked-by: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
diff --git a/fs/exec.c b/fs/exec.c
index 052a961..a2e6989 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1077,9 +1077,11 @@
 	if (p->fs->users > n_fs) {
 		bprm->unsafe |= LSM_UNSAFE_SHARE;
 	} else {
-		if (p->fs->in_exec)
-			res = -EAGAIN;
-		p->fs->in_exec = 1;
+		res = -EAGAIN;
+		if (!p->fs->in_exec) {
+			p->fs->in_exec = 1;
+			res = 1;
+		}
 	}
 
 	unlock_task_sighand(p, &flags);
@@ -1284,6 +1286,7 @@
 	struct linux_binprm *bprm;
 	struct file *file;
 	struct files_struct *displaced;
+	bool clear_in_exec;
 	int retval;
 
 	retval = unshare_files(&displaced);
@@ -1306,8 +1309,9 @@
 		goto out_unlock;
 
 	retval = check_unsafe_exec(bprm);
-	if (retval)
+	if (retval < 0)
 		goto out_unlock;
+	clear_in_exec = retval;
 
 	file = open_exec(filename);
 	retval = PTR_ERR(file);
@@ -1355,9 +1359,7 @@
 		goto out;
 
 	/* execve succeeded */
-	write_lock(&current->fs->lock);
 	current->fs->in_exec = 0;
-	write_unlock(&current->fs->lock);
 	current->in_execve = 0;
 	mutex_unlock(&current->cred_exec_mutex);
 	acct_update_integrals(current);
@@ -1377,9 +1379,8 @@
 	}
 
 out_unmark:
-	write_lock(&current->fs->lock);
-	current->fs->in_exec = 0;
-	write_unlock(&current->fs->lock);
+	if (clear_in_exec)
+		current->fs->in_exec = 0;
 
 out_unlock:
 	current->in_execve = 0;