diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 457fb8f548ed8814a8409849cf27998e000c868f..e83ee118843ae9719ce37db79755f7a134a2a053 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -4738,37 +4738,6 @@ i915_gem_suspend(struct drm_device *dev)
 	return ret;
 }
 
-int i915_gem_l3_remap(struct drm_i915_gem_request *req, int slice)
-{
-	struct intel_engine_cs *engine = req->engine;
-	struct drm_device *dev = engine->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	u32 *remap_info = dev_priv->l3_parity.remap_info[slice];
-	int i, ret;
-
-	if (!HAS_L3_DPF(dev) || !remap_info)
-		return 0;
-
-	ret = intel_ring_begin(req, GEN7_L3LOG_SIZE / 4 * 3);
-	if (ret)
-		return ret;
-
-	/*
-	 * Note: We do not worry about the concurrent register cacheline hang
-	 * here because no other code should access these registers other than
-	 * at initialization time.
-	 */
-	for (i = 0; i < GEN7_L3LOG_SIZE / 4; i++) {
-		intel_ring_emit(engine, MI_LOAD_REGISTER_IMM(1));
-		intel_ring_emit_reg(engine, GEN7_L3LOG(slice, i));
-		intel_ring_emit(engine, remap_info[i]);
-	}
-
-	intel_ring_advance(engine);
-
-	return ret;
-}
-
 void i915_gem_init_swizzling(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
index fb269e4dff3fd1c2cb7b4ab103717d4f88fce7ba..ec0122bc42632aca8a105d87472eb97ed2f58df6 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -601,6 +601,37 @@ mi_set_context(struct drm_i915_gem_request *req, u32 hw_flags)
 	return ret;
 }
 
+int i915_gem_l3_remap(struct drm_i915_gem_request *req, int slice)
+{
+	struct intel_engine_cs *engine = req->engine;
+	struct drm_device *dev = engine->dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	u32 *remap_info = dev_priv->l3_parity.remap_info[slice];
+	int i, ret;
+
+	if (!HAS_L3_DPF(dev) || !remap_info)
+		return 0;
+
+	ret = intel_ring_begin(req, GEN7_L3LOG_SIZE / 4 * 3);
+	if (ret)
+		return ret;
+
+	/*
+	 * Note: We do not worry about the concurrent register cacheline hang
+	 * here because no other code should access these registers other than
+	 * at initialization time.
+	 */
+	for (i = 0; i < GEN7_L3LOG_SIZE / 4; i++) {
+		intel_ring_emit(engine, MI_LOAD_REGISTER_IMM(1));
+		intel_ring_emit_reg(engine, GEN7_L3LOG(slice, i));
+		intel_ring_emit(engine, remap_info[i]);
+	}
+
+	intel_ring_advance(engine);
+
+	return ret;
+}
+
 static inline bool skip_rcs_switch(struct intel_engine_cs *engine,
 				   struct intel_context *to)
 {