[RFC PATCH 1/2] futex: Create reproducer for robust_list race condition

@@ -0,0 +1,178 @@
+/*
+ *  gcc robust_bug.c -o robust_bug
+ *
+ * This is a reproducer for "File corruption race condition in robust
+ * mutex unlocking" from https://sourceware.org/bugzilla/show_bug.cgi?id=14485
+ *
+ * To increase the changes of reaching the race condition, a delay can be added
+ * to the kernel function handle_futex_death(), just before the user memory
+ * write futex_cmpxchg_value_locked().
+ */
+
+#define _GNU_SOURCE
+#include <errno.h>
+#include <linux/futex.h>
+#include <pthread.h>
+#include <stddef.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <string.h>
+#include <sys/mman.h>
+#include <sys/syscall.h>
+#include <unistd.h>
+#include <time.h>
+
+#define cpu_relax() asm volatile("rep; nop");
+
+/*
+ * This struct is an example of a lock struct, shared between the threads.
+ */
+struct lock_struct {
+	uint32_t 		futex;
+	struct robust_list	list;
+};
+
+static struct lock_struct *lock;
+
+/*
+ * This is the struct that we are going to use to allocate on top of the 
+ * freed memory to observe the race condition.
+ */
+struct another_struct {
+	uint64_t value;
+};
+
+static pthread_barrier_t barrier;
+
+static int set_robust_list(struct robust_list_head *head)
+{
+	return syscall(SYS_set_robust_list, head, sizeof(*head));
+}
+
+/*
+ * This thread emulates the behaviour of a thread releasing a robust mutex:
+ * - It starts by adding the mutex to the op_pending field
+ * - Remove the mutex from the robust list
+ * - Release the lock and wake up waiters
+ * - Remove the mutex from the op_pending field
+ *
+ * However, this thread dies before doing this last step, leaving the mutex
+ * behind in the op_pending field.
+ */
+void *func_b(void *arg)
+{
+	static struct robust_list_head head;
+	pid_t tid = gettid() | FUTEX_WAITERS;
+
+	/*
+	 * Initial thread setup. This would happen in an earlier stage of the
+	 * thread execution.
+	 */
+	set_robust_list(&head);
+	head.list.next = &head.list;
+	head.futex_offset = (size_t) offsetof(struct lock_struct, futex) -
+		(size_t) offsetof(struct lock_struct, list);
+
+	/* This thread takes the lock... */
+	lock->futex = tid;
+
+	/* ...would do some work here... */
+
+	/*
+	 * ...and starts the release process. Adds the mutex to be released on
+	 * the op_pending.
+	 */
+	head.list_op_pending = &lock->list;
+
+	/* Barrier to synchronize thread B taking the lock */
+	pthread_barrier_wait(&barrier);
+	usleep(100);
+
+	/*
+	 * Here we would release the lock and wake up any waiters.
+	 *
+	 * lock->futex = LOCK_FREE;
+	 * futex_wake(lock->futex, 1);
+	 */
+
+	/*
+	 * We would remove the lock from op_pending, but we emulate a thread
+	 * exiting before doing it.
+	 */
+	return NULL;
+}
+
+int main(int argc, char *argv[])
+{
+	struct another_struct *new;
+	uint64_t original_val;
+	pthread_t thread_b;
+	uint32_t value;
+	int ret;
+
+	ret = pthread_barrier_init(&barrier, NULL, 2);
+	if (ret) {
+		puts("pthread_barrier_init failed");
+		return -1;
+	}
+
+	/* Initialize the lock */
+	lock = mmap(NULL, sizeof(struct lock_struct), PROT_READ | PROT_WRITE,
+		    MAP_SHARED | MAP_ANONYMOUS, -1, 0);
+	if (lock == MAP_FAILED) {
+		puts("mmap failed");
+		return -1;
+	}
+	memset(lock, 0, sizeof(*lock));
+
+	/* Create the thread B that will take the lock */
+	pthread_create(&thread_b, NULL, func_b, NULL);
+
+	/* Barrier to synchronize thread B taking the lock */
+	pthread_barrier_wait(&barrier);
+
+	/* Copy this value as we will use it later */
+	value = lock->futex;
+
+	/*
+	 * Here, this thread would do the following:
+	 * - It would wait for the lock, and be wake from thread B
+	 * - Take the lock, do some work, and release it
+	 * - After releasing the lock and being the last user, it can correctly
+	 *   free it
+	 */
+	munmap(lock, sizeof(struct lock_struct));
+
+	/*
+	 * After freeing the lock, this thread allocates memory, which
+	 * happens to be at the same address of the lock, and by chance, it fills
+	 * the memory with the TID of thread B.
+	 */
+	new = mmap(NULL, sizeof(struct another_struct), PROT_READ | PROT_WRITE,
+		    MAP_SHARED | MAP_ANONYMOUS, -1, 0);
+	if (new == MAP_FAILED) {
+		puts("mmap failed");
+		return -1;
+	}
+	if ((uintptr_t) lock != (uintptr_t) new) {
+		puts("mmap got a different address");
+		return -1;
+	}
+
+	new->value = ((uint64_t) value << 32) + value;
+
+	/* Create a backup of the current value */
+	original_val = new->value;
+
+	/* Wait for the memory corruption to happen... */	
+	while (new->value == original_val)
+		cpu_relax();
+
+	/* ...and now the kernel just overwrote an unrelated user memory! */
+	printf("Memory was corrupted by the kernel: %lx vs %lx\n",
+		original_val, new->value);
+
+	munmap(new, sizeof(struct another_struct));
+
+	return 0;
+}