diff --git a/amdgpu/amdgpu-symbol-check b/amdgpu/amdgpu-symbol-check
index 4d1ae65c..81ef9b4e 100755
--- a/amdgpu/amdgpu-symbol-check
+++ b/amdgpu/amdgpu-symbol-check
@@ -33,6 +33,7 @@ amdgpu_cs_query_fence_status
 amdgpu_cs_query_reset_state
 amdgpu_cs_signal_semaphore
 amdgpu_cs_submit
+amdgpu_cs_wait_fences
 amdgpu_cs_wait_semaphore
 amdgpu_device_deinitialize
 amdgpu_device_initialize
diff --git a/amdgpu/amdgpu.h b/amdgpu/amdgpu.h
index 55884b24..fdea9050 100644
--- a/amdgpu/amdgpu.h
+++ b/amdgpu/amdgpu.h
@@ -907,6 +907,29 @@ int amdgpu_cs_query_fence_status(struct amdgpu_cs_fence *fence,
 				 uint64_t flags,
 				 uint32_t *expired);
 
+/**
+ *  Wait for multiple fences
+ *
+ * \param   fences      - \c [in] The fence array to wait
+ * \param   fence_count - \c [in] The fence count
+ * \param   wait_all    - \c [in] If true, wait all fences to be signaled,
+ *                                otherwise, wait at least one fence
+ * \param   timeout_ns  - \c [in] The timeout to wait, in nanoseconds
+ * \param   status      - \c [out] '1' for signaled, '0' for timeout
+ * \param   first       - \c [out] the index of the first signaled fence from @fences
+ *
+ * \return  0 on success
+ *          <0 - Negative POSIX Error code
+ *
+ * \note    Currently it supports only one amdgpu_device. All fences come from
+ *          the same amdgpu_device with the same fd.
+*/
+int amdgpu_cs_wait_fences(struct amdgpu_cs_fence *fences,
+			  uint32_t fence_count,
+			  bool wait_all,
+			  uint64_t timeout_ns,
+			  uint32_t *status, uint32_t *first);
+
 /*
  * Query / Info API
  *
diff --git a/amdgpu/amdgpu_cs.c b/amdgpu/amdgpu_cs.c
index fb5b3a8c..779c7dbc 100644
--- a/amdgpu/amdgpu_cs.c
+++ b/amdgpu/amdgpu_cs.c
@@ -443,6 +443,77 @@ int amdgpu_cs_query_fence_status(struct amdgpu_cs_fence *fence,
 	return r;
 }
 
+static int amdgpu_ioctl_wait_fences(struct amdgpu_cs_fence *fences,
+				    uint32_t fence_count,
+				    bool wait_all,
+				    uint64_t timeout_ns,
+				    uint32_t *status,
+				    uint32_t *first)
+{
+	struct drm_amdgpu_fence *drm_fences;
+	amdgpu_device_handle dev = fences[0].context->dev;
+	union drm_amdgpu_wait_fences args;
+	int r;
+	uint32_t i;
+
+	drm_fences = alloca(sizeof(struct drm_amdgpu_fence) * fence_count);
+	for (i = 0; i < fence_count; i++) {
+		drm_fences[i].ctx_id = fences[i].context->id;
+		drm_fences[i].ip_type = fences[i].ip_type;
+		drm_fences[i].ip_instance = fences[i].ip_instance;
+		drm_fences[i].ring = fences[i].ring;
+		drm_fences[i].seq_no = fences[i].fence;
+	}
+
+	memset(&args, 0, sizeof(args));
+	args.in.fences = (uint64_t)(uintptr_t)drm_fences;
+	args.in.fence_count = fence_count;
+	args.in.wait_all = wait_all;
+	args.in.timeout_ns = amdgpu_cs_calculate_timeout(timeout_ns);
+
+	r = drmIoctl(dev->fd, DRM_IOCTL_AMDGPU_WAIT_FENCES, &args);
+	if (r)
+		return -errno;
+
+	*status = args.out.status;
+
+	if (first)
+		*first = args.out.first_signaled;
+
+	return 0;
+}
+
+int amdgpu_cs_wait_fences(struct amdgpu_cs_fence *fences,
+			  uint32_t fence_count,
+			  bool wait_all,
+			  uint64_t timeout_ns,
+			  uint32_t *status,
+			  uint32_t *first)
+{
+	uint32_t i;
+
+	/* Sanity check */
+	if (NULL == fences)
+		return -EINVAL;
+	if (NULL == status)
+		return -EINVAL;
+	if (fence_count <= 0)
+		return -EINVAL;
+	for (i = 0; i < fence_count; i++) {
+		if (NULL == fences[i].context)
+			return -EINVAL;
+		if (fences[i].ip_type >= AMDGPU_HW_IP_NUM)
+			return -EINVAL;
+		if (fences[i].ring >= AMDGPU_CS_MAX_RINGS)
+			return -EINVAL;
+	}
+
+	*status = 0;
+
+	return amdgpu_ioctl_wait_fences(fences, fence_count, wait_all,
+					timeout_ns, status, first);
+}
+
 int amdgpu_cs_create_semaphore(amdgpu_semaphore_handle *sem)
 {
 	struct amdgpu_semaphore *gpu_semaphore;