drm/i915/kbl: Add WaClearSlmSpaceAtContextSwitch

This workaround for bdw and chv, is also needed for kbl A0.

References: HSD#1911519, BSID#569
Signed-off-by: Mika Kuoppala <mika.kuoppala@intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1465309159-30531-24-git-send-email-mika.kuoppala@intel.com
(cherry picked from commit 066d462888514af727008a450f4078b1a23d5cbe)
Signed-off-by: Mika Kuoppala <mika.kuoppala@intel.com>
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 3138d2f..7f2d841 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -1275,6 +1275,7 @@
 {
 	int ret;
 	struct drm_device *dev = engine->dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
 	uint32_t index = wa_ctx_start(wa_ctx, *offset, CACHELINE_DWORDS);
 
 	/* WaDisableCtxRestoreArbitration:skl,bxt */
@@ -1288,6 +1289,22 @@
 		return ret;
 	index = ret;
 
+	/* WaClearSlmSpaceAtContextSwitch:kbl */
+	/* Actual scratch location is at 128 bytes offset */
+	if (IS_KBL_REVID(dev_priv, 0, KBL_REVID_A0)) {
+		uint32_t scratch_addr
+			= engine->scratch.gtt_offset + 2*CACHELINE_BYTES;
+
+		wa_ctx_emit(batch, index, GFX_OP_PIPE_CONTROL(6));
+		wa_ctx_emit(batch, index, (PIPE_CONTROL_FLUSH_L3 |
+					   PIPE_CONTROL_GLOBAL_GTT_IVB |
+					   PIPE_CONTROL_CS_STALL |
+					   PIPE_CONTROL_QW_WRITE));
+		wa_ctx_emit(batch, index, scratch_addr);
+		wa_ctx_emit(batch, index, 0);
+		wa_ctx_emit(batch, index, 0);
+		wa_ctx_emit(batch, index, 0);
+	}
 	/* Pad to end of cacheline */
 	while (index % CACHELINE_DWORDS)
 		wa_ctx_emit(batch, index, MI_NOOP);