exec: Transform exec_update_mutex into a rw_semaphore

[ Upstream commit f7cfd871ae0c5008d94b6f66834e7845caa93c15 ]

Recently syzbot reported[0] that there is a deadlock amongst the users
of exec_update_mutex.  The problematic lock ordering found by lockdep
was:

   perf_event_open  (exec_update_mutex -> ovl_i_mutex)
   chown            (ovl_i_mutex       -> sb_writes)
   sendfile         (sb_writes         -> p->lock)
     by reading from a proc file and writing to overlayfs
   proc_pid_syscall (p->lock           -> exec_update_mutex)

While looking at possible solutions it occured to me that all of the
users and possible users involved only wanted to state of the given
process to remain the same.  They are all readers.  The only writer is
exec.

There is no reason for readers to block on each other.  So fix
this deadlock by transforming exec_update_mutex into a rw_semaphore
named exec_update_lock that only exec takes for writing.

Cc: Jann Horn <jannh@google.com>
Cc: Vasiliy Kulikov <segoon@openwall.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Bernd Edlinger <bernd.edlinger@hotmail.de>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Christopher Yeoh <cyeoh@au1.ibm.com>
Cc: Cyrill Gorcunov <gorcunov@gmail.com>
Cc: Sargun Dhillon <sargun@sargun.me>
Cc: Christian Brauner <christian.brauner@ubuntu.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Fixes: eea9673250db ("exec: Add exec_update_mutex to replace cred_guard_mutex")
[0] https://lkml.kernel.org/r/00000000000063640c05ade8e3de@google.com
Reported-by: syzbot+db9cdf3dd1f64252c6ef@syzkaller.appspotmail.com
Link: https://lkml.kernel.org/r/87ft4mbqen.fsf@x220.int.ebiederm.org
Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>

2 files changed, 11 insertions, 11 deletions

diff --git a/fs/exec.c b/fs/exec.c
index 2441eb1a1e2d..1b4d2206d53a 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1009,8 +1009,8 @@ EXPORT_SYMBOL(read_code);
 
 /*
  * Maps the mm_struct mm into the current task struct.
- * On success, this function returns with the mutex
- * exec_update_mutex locked.
+ * On success, this function returns with exec_update_lock
+ * held for writing.
  */
 static int exec_mmap(struct mm_struct *mm)
 {
@@ -1023,7 +1023,7 @@ static int exec_mmap(struct mm_struct *mm)
 	old_mm = current->mm;
 	exec_mm_release(tsk, old_mm);
 
-	ret = mutex_lock_killable(&tsk->signal->exec_update_mutex);
+	ret = down_write_killable(&tsk->signal->exec_update_lock);
 	if (ret)
 		return ret;
 
@@ -1038,7 +1038,7 @@ static int exec_mmap(struct mm_struct *mm)
 		down_read(&old_mm->mmap_sem);
 		if (unlikely(old_mm->core_state)) {
 			up_read(&old_mm->mmap_sem);
-			mutex_unlock(&tsk->signal->exec_update_mutex);
+			up_write(&tsk->signal->exec_update_lock);
 			return -EINTR;
 		}
 	}
@@ -1450,7 +1450,7 @@ static void free_bprm(struct linux_binprm *bprm)
 	free_arg_pages(bprm);
 	if (bprm->cred) {
 		if (bprm->called_exec_mmap)
-			mutex_unlock(&current->signal->exec_update_mutex);
+			up_write(&current->signal->exec_update_lock);
 		mutex_unlock(&current->signal->cred_guard_mutex);
 		abort_creds(bprm->cred);
 	}
@@ -1500,7 +1500,7 @@ void install_exec_creds(struct linux_binprm *bprm)
 	 * credentials; any time after this it may be unlocked.
 	 */
 	security_bprm_committed_creds(bprm);
-	mutex_unlock(&current->signal->exec_update_mutex);
+	up_write(&current->signal->exec_update_lock);
 	mutex_unlock(&current->signal->cred_guard_mutex);
 }
 EXPORT_SYMBOL(install_exec_creds);
diff --git a/fs/proc/base.c b/fs/proc/base.c
index b690074e65ff..653c2d8aa1cd 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -403,11 +403,11 @@ print0:
 
 static int lock_trace(struct task_struct *task)
 {
-	int err = mutex_lock_killable(&task->signal->exec_update_mutex);
+	int err = down_read_killable(&task->signal->exec_update_lock);
 	if (err)
 		return err;
 	if (!ptrace_may_access(task, PTRACE_MODE_ATTACH_FSCREDS)) {
-		mutex_unlock(&task->signal->exec_update_mutex);
+		up_read(&task->signal->exec_update_lock);
 		return -EPERM;
 	}
 	return 0;
@@ -415,7 +415,7 @@ static int lock_trace(struct task_struct *task)
 
 static void unlock_trace(struct task_struct *task)
 {
-	mutex_unlock(&task->signal->exec_update_mutex);
+	up_read(&task->signal->exec_update_lock);
 }
 
 #ifdef CONFIG_STACKTRACE
@@ -2769,7 +2769,7 @@ static int do_io_accounting(struct task_struct *task, struct seq_file *m, int wh
 	unsigned long flags;
 	int result;
 
-	result = mutex_lock_killable(&task->signal->exec_update_mutex);
+	result = down_read_killable(&task->signal->exec_update_lock);
 	if (result)
 		return result;
 
@@ -2805,7 +2805,7 @@ static int do_io_accounting(struct task_struct *task, struct seq_file *m, int wh
 	result = 0;
 
 out_unlock:
-	mutex_unlock(&task->signal->exec_update_mutex);
+	up_read(&task->signal->exec_update_lock);
 	return result;
 }