[CI 07/13] drm/xe/xelp: Add AuxCCS invalidation to the indirect context workarounds

[Tvrtko Ursulin <tvrtko.ursulin@igalia.com>]

Following from the i915 reference implementation, we add the AuxCCS
invalidation to the indirect context workarounds page.

Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@igalia.com>
---
 drivers/gpu/drm/xe/xe_lrc.c | 47 +++++++++++++++++++++++++++++++++++++
 1 file changed, 47 insertions(+)

diff --git a/drivers/gpu/drm/xe/xe_lrc.c b/drivers/gpu/drm/xe/xe_lrc.c
index 8f6c3ba47882..0b0ecdf09f9f 100644
--- a/drivers/gpu/drm/xe/xe_lrc.c
+++ b/drivers/gpu/drm/xe/xe_lrc.c
@@ -25,6 +25,7 @@
 #include "xe_map.h"
 #include "xe_memirq.h"
 #include "xe_mmio.h"
+#include "xe_ring_ops.h"
 #include "xe_sriov.h"
 #include "xe_trace_lrc.h"
 #include "xe_vm.h"
@@ -75,11 +76,23 @@ lrc_to_xe(struct xe_lrc *lrc)
 static bool
 gt_engine_needs_indirect_ctx(struct xe_gt *gt, enum xe_engine_class class)
 {
+	struct xe_device *xe = gt_to_xe(gt);
+
 	if (XE_GT_WA(gt, 16010904313) &&
 	    (class == XE_ENGINE_CLASS_RENDER ||
 	     class == XE_ENGINE_CLASS_COMPUTE))
 		return true;
 
+	/* AuxCCS invalidation */
+	if (GRAPHICS_VERx100(xe) >= 1200 &&
+	    GRAPHICS_VERx100(xe) <= 1210 &&
+	    (class == XE_ENGINE_CLASS_RENDER ||
+	     class == XE_ENGINE_CLASS_COMPUTE ||
+	     class == XE_ENGINE_CLASS_COPY ||
+	     class == XE_ENGINE_CLASS_VIDEO_DECODE ||
+	     class == XE_ENGINE_CLASS_VIDEO_ENHANCE))
+		return true;
+
 	return false;
 }
 
@@ -1122,6 +1135,31 @@ static ssize_t setup_invalidate_state_cache_wa(struct xe_lrc *lrc,
 	return cmd - batch;
 }
 
+static ssize_t setup_invalidate_auxccs_wa(struct xe_lrc *lrc,
+					  struct xe_hw_engine *hwe,
+					  u32 *batch, size_t max_len)
+{
+	struct xe_gt *gt = lrc->gt;
+	struct xe_device *xe = gt_to_xe(gt);
+	const unsigned int class = hwe->class;
+	u32 *cmd;
+
+	if (GRAPHICS_VERx100(xe) < 1200 || GRAPHICS_VERx100(xe) > 1210 ||
+	    !(class == XE_ENGINE_CLASS_RENDER ||
+	      class == XE_ENGINE_CLASS_COMPUTE ||
+	      class == XE_ENGINE_CLASS_COPY ||
+	      class == XE_ENGINE_CLASS_VIDEO_DECODE ||
+	      class == XE_ENGINE_CLASS_VIDEO_ENHANCE))
+		return 0;
+
+	if (xe_gt_WARN_ON(gt, max_len < 8))
+		return -ENOSPC;
+
+	cmd = xe_emit_aux_table_inv(hwe, batch);
+
+	return cmd - batch;
+}
+
 struct bo_setup {
 	ssize_t (*setup)(struct xe_lrc *lrc, struct xe_hw_engine *hwe,
 			 u32 *batch, size_t max_size);
@@ -1251,6 +1289,10 @@ setup_indirect_ctx(struct xe_lrc *lrc, struct xe_hw_engine *hwe)
 {
 	static struct bo_setup rcs_funcs[] = {
 		{ .setup = setup_timestamp_wa },
+		{ .setup = setup_invalidate_auxccs_wa },
+	};
+	static struct bo_setup xcs_funcs[] = {
+		{ .setup = setup_invalidate_auxccs_wa },
 	};
 	struct bo_setup_state state = {
 		.lrc = lrc,
@@ -1268,6 +1310,11 @@ setup_indirect_ctx(struct xe_lrc *lrc, struct xe_hw_engine *hwe)
 	    hwe->class == XE_ENGINE_CLASS_COMPUTE) {
 		state.funcs = rcs_funcs;
 		state.num_funcs = ARRAY_SIZE(rcs_funcs);
+	} else if (hwe->class == XE_ENGINE_CLASS_COPY ||
+		   hwe->class == XE_ENGINE_CLASS_VIDEO_DECODE ||
+		   hwe->class == XE_ENGINE_CLASS_VIDEO_ENHANCE) {
+		state.funcs = xcs_funcs;
+		state.num_funcs = ARRAY_SIZE(xcs_funcs);
 	}
 
 	if (xe_gt_WARN_ON(lrc->gt, !state.funcs))
-- 
2.48.0