drm/i915: Enable Wa_16019325821

Some platforms require holding RCS context switches until CCS is idle
(the reverse w/a of Wa_14014475959). Some platforms require both
versions.
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
Reviewed-by: Vinay Belgaumkar <vinay.belgaumkar@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240223205632.1621019-2-John.C.Harrison@Intel.com

drivers/gpu/drm/i915/gt/gen8_engine_cs.c

@@ -743,21 +743,23 @@ static u32 *gen12_emit_preempt_busywait(struct i915_request *rq, u32 *cs)
 }
 
 /* Wa_14014475959:dg2 */
-#define CCS_SEMAPHORE_PPHWSP_OFFSET	0x540
-static u32 ccs_semaphore_offset(struct i915_request *rq)
+/* Wa_16019325821 */
+#define HOLD_SWITCHOUT_SEMAPHORE_PPHWSP_OFFSET	0x540
+static u32 hold_switchout_semaphore_offset(struct i915_request *rq)
 {
 	return i915_ggtt_offset(rq->context->state) +
-		(LRC_PPHWSP_PN * PAGE_SIZE) + CCS_SEMAPHORE_PPHWSP_OFFSET;
+		(LRC_PPHWSP_PN * PAGE_SIZE) + HOLD_SWITCHOUT_SEMAPHORE_PPHWSP_OFFSET;
 }
 
 /* Wa_14014475959:dg2 */
-static u32 *ccs_emit_wa_busywait(struct i915_request *rq, u32 *cs)
+/* Wa_16019325821 */
+static u32 *hold_switchout_emit_wa_busywait(struct i915_request *rq, u32 *cs)
 {
 	int i;
 
 	*cs++ = MI_ATOMIC_INLINE | MI_ATOMIC_GLOBAL_GTT | MI_ATOMIC_CS_STALL |
 		MI_ATOMIC_MOVE;
-	*cs++ = ccs_semaphore_offset(rq);
+	*cs++ = hold_switchout_semaphore_offset(rq);
 	*cs++ = 0;
 	*cs++ = 1;
 
@@ -773,7 +775,7 @@ static u32 *ccs_emit_wa_busywait(struct i915_request *rq, u32 *cs)
 		MI_SEMAPHORE_POLL |
 		MI_SEMAPHORE_SAD_EQ_SDD;
 	*cs++ = 0;
-	*cs++ = ccs_semaphore_offset(rq);
+	*cs++ = hold_switchout_semaphore_offset(rq);
 	*cs++ = 0;
 
 	return cs;
@@ -790,8 +792,9 @@ gen12_emit_fini_breadcrumb_tail(struct i915_request *rq, u32 *cs)
 		cs = gen12_emit_preempt_busywait(rq, cs);
 
 	/* Wa_14014475959:dg2 */
-	if (intel_engine_uses_wa_hold_ccs_switchout(rq->engine))
-		cs = ccs_emit_wa_busywait(rq, cs);
+	/* Wa_16019325821 */
+	if (intel_engine_uses_wa_hold_switchout(rq->engine))
+		cs = hold_switchout_emit_wa_busywait(rq, cs);
 
 	rq->tail = intel_ring_offset(rq, cs);
 	assert_ring_tail_valid(rq->ring, rq->tail);

drivers/gpu/drm/i915/gt/intel_engine_types.h

@@ -586,7 +586,7 @@ struct intel_engine_cs {
 #define I915_ENGINE_HAS_RCS_REG_STATE  BIT(9)
 #define I915_ENGINE_HAS_EU_PRIORITY    BIT(10)
 #define I915_ENGINE_FIRST_RENDER_COMPUTE BIT(11)
-#define I915_ENGINE_USES_WA_HOLD_CCS_SWITCHOUT BIT(12)
+#define I915_ENGINE_USES_WA_HOLD_SWITCHOUT BIT(12)
 	unsigned int flags;
 
 	/*
@@ -696,10 +696,11 @@ intel_engine_has_relative_mmio(const struct intel_engine_cs * const engine)
 }
 
 /* Wa_14014475959:dg2 */
+/* Wa_16019325821 */
 static inline bool
-intel_engine_uses_wa_hold_ccs_switchout(struct intel_engine_cs *engine)
+intel_engine_uses_wa_hold_switchout(struct intel_engine_cs *engine)
 {
-	return engine->flags & I915_ENGINE_USES_WA_HOLD_CCS_SWITCHOUT;
+	return engine->flags & I915_ENGINE_USES_WA_HOLD_SWITCHOUT;
 }
 
 #endif /* __INTEL_ENGINE_TYPES_H__ */

drivers/gpu/drm/i915/gt/uc/intel_guc.c

@@ -294,6 +294,10 @@ static u32 guc_ctl_wa_flags(struct intel_guc *guc)
 	    IS_DG2(gt->i915))
 		flags |= GUC_WA_HOLD_CCS_SWITCHOUT;
 
+	/* Wa_16019325821 */
+	if (IS_GFX_GT_IP_RANGE(gt, IP_VER(12, 70), IP_VER(12, 71)))
+		flags |= GUC_WA_RCS_CCS_SWITCHOUT;
+
 	/*
 	 * Wa_14012197797
 	 * Wa_22011391025

drivers/gpu/drm/i915/gt/uc/intel_guc_fwif.h

@@ -96,8 +96,9 @@
 #define   GUC_WA_GAM_CREDITS		BIT(10)
 #define   GUC_WA_DUAL_QUEUE		BIT(11)
 #define   GUC_WA_RCS_RESET_BEFORE_RC6	BIT(13)
-#define   GUC_WA_CONTEXT_ISOLATION	BIT(15)
 #define   GUC_WA_PRE_PARSER		BIT(14)
+#define   GUC_WA_CONTEXT_ISOLATION	BIT(15)
+#define   GUC_WA_RCS_CCS_SWITCHOUT	BIT(16)
 #define   GUC_WA_HOLD_CCS_SWITCHOUT	BIT(17)
 #define   GUC_WA_POLLCS			BIT(18)
 #define   GUC_WA_RCS_REGS_IN_CCS_REGS_LIST	BIT(21)

drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c

@@ -4502,7 +4502,12 @@ static void guc_default_vfuncs(struct intel_engine_cs *engine)
 	if (engine->class == COMPUTE_CLASS)
 		if (IS_GFX_GT_IP_STEP(engine->gt, IP_VER(12, 70), STEP_A0, STEP_B0) ||
 		    IS_DG2(engine->i915))
-			engine->flags |= I915_ENGINE_USES_WA_HOLD_CCS_SWITCHOUT;
+			engine->flags |= I915_ENGINE_USES_WA_HOLD_SWITCHOUT;
+
+	/* Wa_16019325821 */
+	if ((engine->class == COMPUTE_CLASS || engine->class == RENDER_CLASS) &&
+	    IS_GFX_GT_IP_RANGE(engine->gt, IP_VER(12, 70), IP_VER(12, 71)))
+		engine->flags |= I915_ENGINE_USES_WA_HOLD_SWITCHOUT;
 
 	/*
 	 * TODO: GuC supports timeslicing and semaphores as well, but they're