diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c
index 9b8fa2ad0d84..1594ae39d54f 100644
--- a/drivers/gpu/drm/msm/msm_drv.c
+++ b/drivers/gpu/drm/msm/msm_drv.c
@@ -911,6 +911,7 @@ static int msm_ioctl_wait_fence(struct drm_device *dev, void *data,
 	ktime_t timeout = to_ktime(args->timeout);
 	struct msm_gpu_submitqueue *queue;
 	struct msm_gpu *gpu = priv->gpu;
+	struct dma_fence *fence;
 	int ret;
 
 	if (args->pad) {
@@ -925,10 +926,35 @@ static int msm_ioctl_wait_fence(struct drm_device *dev, void *data,
 	if (!queue)
 		return -ENOENT;
 
-	ret = msm_wait_fence(gpu->rb[queue->prio]->fctx, args->fence, &timeout,
-		true);
+	/*
+	 * Map submitqueue scoped "seqno" (which is actually an idr key)
+	 * back to underlying dma-fence
+	 *
+	 * The fence is removed from the fence_idr when the submit is
+	 * retired, so if the fence is not found it means there is nothing
+	 * to wait for
+	 */
+	ret = mutex_lock_interruptible(&queue->lock);
+	if (ret)
+		return ret;
+	fence = idr_find(&queue->fence_idr, args->fence);
+	if (fence)
+		fence = dma_fence_get_rcu(fence);
+	mutex_unlock(&queue->lock);
 
+	if (!fence)
+		return 0;
+
+	ret = dma_fence_wait_timeout(fence, true, timeout_to_jiffies(&timeout));
+	if (ret == 0) {
+		ret = -ETIMEDOUT;
+	} else if (ret != -ERESTARTSYS) {
+		ret = 0;
+	}
+
+	dma_fence_put(fence);
 	msm_submitqueue_put(queue);
+
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/msm/msm_fence.c b/drivers/gpu/drm/msm/msm_fence.c
index b92a9091a1e2..f2cece542c3f 100644
--- a/drivers/gpu/drm/msm/msm_fence.c
+++ b/drivers/gpu/drm/msm/msm_fence.c
@@ -24,7 +24,6 @@ msm_fence_context_alloc(struct drm_device *dev, volatile uint32_t *fenceptr,
 	strncpy(fctx->name, name, sizeof(fctx->name));
 	fctx->context = dma_fence_context_alloc(1);
 	fctx->fenceptr = fenceptr;
-	init_waitqueue_head(&fctx->event);
 	spin_lock_init(&fctx->spinlock);
 
 	return fctx;
@@ -45,53 +44,12 @@ static inline bool fence_completed(struct msm_fence_context *fctx, uint32_t fenc
 		(int32_t)(*fctx->fenceptr - fence) >= 0;
 }
 
-/* legacy path for WAIT_FENCE ioctl: */
-int msm_wait_fence(struct msm_fence_context *fctx, uint32_t fence,
-		ktime_t *timeout, bool interruptible)
-{
-	int ret;
-
-	if (fence > fctx->last_fence) {
-		DRM_ERROR_RATELIMITED("%s: waiting on invalid fence: %u (of %u)\n",
-				fctx->name, fence, fctx->last_fence);
-		return -EINVAL;
-	}
-
-	if (!timeout) {
-		/* no-wait: */
-		ret = fence_completed(fctx, fence) ? 0 : -EBUSY;
-	} else {
-		unsigned long remaining_jiffies = timeout_to_jiffies(timeout);
-
-		if (interruptible)
-			ret = wait_event_interruptible_timeout(fctx->event,
-				fence_completed(fctx, fence),
-				remaining_jiffies);
-		else
-			ret = wait_event_timeout(fctx->event,
-				fence_completed(fctx, fence),
-				remaining_jiffies);
-
-		if (ret == 0) {
-			DBG("timeout waiting for fence: %u (completed: %u)",
-					fence, fctx->completed_fence);
-			ret = -ETIMEDOUT;
-		} else if (ret != -ERESTARTSYS) {
-			ret = 0;
-		}
-	}
-
-	return ret;
-}
-
 /* called from workqueue */
 void msm_update_fence(struct msm_fence_context *fctx, uint32_t fence)
 {
 	spin_lock(&fctx->spinlock);
 	fctx->completed_fence = max(fence, fctx->completed_fence);
 	spin_unlock(&fctx->spinlock);
-
-	wake_up_all(&fctx->event);
 }
 
 struct msm_fence {
diff --git a/drivers/gpu/drm/msm/msm_fence.h b/drivers/gpu/drm/msm/msm_fence.h
index 6ab97062ff1a..4783db528bcc 100644
--- a/drivers/gpu/drm/msm/msm_fence.h
+++ b/drivers/gpu/drm/msm/msm_fence.h
@@ -49,7 +49,6 @@ struct msm_fence_context {
 	 */
 	volatile uint32_t *fenceptr;
 
-	wait_queue_head_t event;
 	spinlock_t spinlock;
 };
 
@@ -57,8 +56,6 @@ struct msm_fence_context * msm_fence_context_alloc(struct drm_device *dev,
 		volatile uint32_t *fenceptr, const char *name);
 void msm_fence_context_free(struct msm_fence_context *fctx);
 
-int msm_wait_fence(struct msm_fence_context *fctx, uint32_t fence,
-		ktime_t *timeout, bool interruptible);
 void msm_update_fence(struct msm_fence_context *fctx, uint32_t fence);
 
 struct dma_fence * msm_fence_alloc(struct msm_fence_context *fctx);
diff --git a/drivers/gpu/drm/msm/msm_gem.h b/drivers/gpu/drm/msm/msm_gem.h
index da3af702a6c8..e0579abda5b9 100644
--- a/drivers/gpu/drm/msm/msm_gem.h
+++ b/drivers/gpu/drm/msm/msm_gem.h
@@ -320,6 +320,7 @@ struct msm_gem_submit {
 	struct ww_acquire_ctx ticket;
 	uint32_t seqno;		/* Sequence number of the submit on the ring */
 	struct dma_fence *fence;
+	int fence_id;       /* key into queue->fence_idr */
 	struct msm_gpu_submitqueue *queue;
 	struct pid *pid;    /* submitting process */
 	bool fault_dumped;  /* Limit devcoredump dumping to one per submit */
diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c
index 4f02fa3c78f9..f6f595aae2c5 100644
--- a/drivers/gpu/drm/msm/msm_gem_submit.c
+++ b/drivers/gpu/drm/msm/msm_gem_submit.c
@@ -68,7 +68,14 @@ void __msm_gem_submit_destroy(struct kref *kref)
 			container_of(kref, struct msm_gem_submit, ref);
 	unsigned i;
 
+	if (submit->fence_id) {
+		mutex_lock(&submit->queue->lock);
+		idr_remove(&submit->queue->fence_idr, submit->fence_id);
+		mutex_unlock(&submit->queue->lock);
+	}
+
 	dma_fence_put(submit->fence);
+
 	put_pid(submit->pid);
 	msm_submitqueue_put(submit->queue);
 
@@ -872,6 +879,20 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data,
 		goto out;
 	}
 
+	/*
+	 * Allocate an id which can be used by WAIT_FENCE ioctl to map back
+	 * to the underlying fence.
+	 */
+	mutex_lock(&queue->lock);
+	submit->fence_id = idr_alloc_cyclic(&queue->fence_idr,
+			submit->fence, 0, INT_MAX, GFP_KERNEL);
+	mutex_unlock(&queue->lock);
+	if (submit->fence_id < 0) {
+		ret = submit->fence_id = 0;
+		submit->fence_id = 0;
+		goto out;
+	}
+
 	if (args->flags & MSM_SUBMIT_FENCE_FD_OUT) {
 		struct sync_file *sync_file = sync_file_create(submit->fence);
 		if (!sync_file) {
@@ -886,7 +907,7 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data,
 
 	msm_gpu_submit(gpu, submit);
 
-	args->fence = submit->fence->seqno;
+	args->fence = submit->fence_id;
 
 	msm_reset_syncobjs(syncobjs_to_reset, args->nr_in_syncobjs);
 	msm_process_post_deps(post_deps, args->nr_out_syncobjs,
diff --git a/drivers/gpu/drm/msm/msm_gpu.h b/drivers/gpu/drm/msm/msm_gpu.h
index 96efcb31e502..579627252540 100644
--- a/drivers/gpu/drm/msm/msm_gpu.h
+++ b/drivers/gpu/drm/msm/msm_gpu.h
@@ -263,6 +263,9 @@ struct msm_gpu_perfcntr {
  *             which set of pgtables do submits jobs associated with the
  *             submitqueue use)
  * @node:      node in the context's list of submitqueues
+ * @fence_idr: maps fence-id to dma_fence for userspace visible fence
+ *             seqno, protected by submitqueue lock
+ * @lock:      submitqueue lock
  * @ref:       reference count
  */
 struct msm_gpu_submitqueue {
@@ -272,6 +275,8 @@ struct msm_gpu_submitqueue {
 	int faults;
 	struct msm_file_private *ctx;
 	struct list_head node;
+	struct idr fence_idr;
+	struct mutex lock;
 	struct kref ref;
 };
 
diff --git a/drivers/gpu/drm/msm/msm_submitqueue.c b/drivers/gpu/drm/msm/msm_submitqueue.c
index 9e9fec61d629..66f8d0fb38b0 100644
--- a/drivers/gpu/drm/msm/msm_submitqueue.c
+++ b/drivers/gpu/drm/msm/msm_submitqueue.c
@@ -12,6 +12,8 @@ void msm_submitqueue_destroy(struct kref *kref)
 	struct msm_gpu_submitqueue *queue = container_of(kref,
 		struct msm_gpu_submitqueue, ref);
 
+	idr_destroy(&queue->fence_idr);
+
 	msm_file_private_put(queue->ctx);
 
 	kfree(queue);
@@ -89,6 +91,9 @@ int msm_submitqueue_create(struct drm_device *drm, struct msm_file_private *ctx,
 	if (id)
 		*id = queue->id;
 
+	idr_init(&queue->fence_idr);
+	mutex_init(&queue->lock);
+
 	list_add_tail(&queue->node, &ctx->submitqueues);
 
 	write_unlock(&ctx->queuelock);