1 files changed, 107 insertions, 17 deletions

diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 40c6aff57256..9121646d7c4d 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -746,9 +746,9 @@ static int intel_rcs_ctx_init(struct drm_i915_gem_request *req)
 
 	ret = i915_gem_render_state_init(req);
 	if (ret)
-		DRM_ERROR("init render state: %d\n", ret);
+		return ret;
 
-	return ret;
+	return 0;
 }
 
 static int wa_add(struct drm_i915_private *dev_priv,
@@ -789,6 +789,22 @@ static int wa_add(struct drm_i915_private *dev_priv,
 
 #define WA_WRITE(addr, val) WA_REG(addr, 0xffffffff, val)
 
+static int wa_ring_whitelist_reg(struct intel_engine_cs *ring, i915_reg_t reg)
+{
+	struct drm_i915_private *dev_priv = ring->dev->dev_private;
+	struct i915_workarounds *wa = &dev_priv->workarounds;
+	const uint32_t index = wa->hw_whitelist_count[ring->id];
+
+	if (WARN_ON(index >= RING_MAX_NONPRIV_SLOTS))
+		return -EINVAL;
+
+	WA_WRITE(RING_FORCE_TO_NONPRIV(ring->mmio_base, index),
+		 i915_mmio_reg_offset(reg));
+	wa->hw_whitelist_count[ring->id]++;
+
+	return 0;
+}
+
 static int gen8_init_workarounds(struct intel_engine_cs *ring)
 {
 	struct drm_device *dev = ring->dev;
@@ -894,6 +910,7 @@ static int gen9_init_workarounds(struct intel_engine_cs *ring)
 	struct drm_device *dev = ring->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	uint32_t tmp;
+	int ret;
 
 	/* WaEnableLbsSlaRetryTimerDecrement:skl */
 	I915_WRITE(BDW_SCRATCH1, I915_READ(BDW_SCRATCH1) |
@@ -951,7 +968,7 @@ static int gen9_init_workarounds(struct intel_engine_cs *ring)
 
 	/* WaForceContextSaveRestoreNonCoherent:skl,bxt */
 	tmp = HDC_FORCE_CONTEXT_SAVE_RESTORE_NON_COHERENT;
-	if (IS_SKL_REVID(dev, SKL_REVID_F0, SKL_REVID_F0) ||
+	if (IS_SKL_REVID(dev, SKL_REVID_F0, REVID_FOREVER) ||
 	    IS_BXT_REVID(dev, BXT_REVID_B0, REVID_FOREVER))
 		tmp |= HDC_FORCE_CSR_NON_COHERENT_OVR_DISABLE;
 	WA_SET_BIT_MASKED(HDC_CHICKEN0, tmp);
@@ -964,6 +981,20 @@ static int gen9_init_workarounds(struct intel_engine_cs *ring)
 	/* WaDisableSTUnitPowerOptimization:skl,bxt */
 	WA_SET_BIT_MASKED(HALF_SLICE_CHICKEN2, GEN8_ST_PO_DISABLE);
 
+	/* WaOCLCoherentLineFlush:skl,bxt */
+	I915_WRITE(GEN8_L3SQCREG4, (I915_READ(GEN8_L3SQCREG4) |
+				    GEN8_LQSC_FLUSH_COHERENT_LINES));
+
+	/* WaEnablePreemptionGranularityControlByUMD:skl,bxt */
+	ret= wa_ring_whitelist_reg(ring, GEN8_CS_CHICKEN1);
+	if (ret)
+		return ret;
+
+	/* WaAllowUMDToModifyHDCChicken1:skl,bxt */
+	ret = wa_ring_whitelist_reg(ring, GEN8_HDC_CHICKEN1);
+	if (ret)
+		return ret;
+
 	return 0;
 }
 
@@ -1019,6 +1050,16 @@ static int skl_init_workarounds(struct intel_engine_cs *ring)
 	if (ret)
 		return ret;
 
+	/*
+	 * Actual WA is to disable percontext preemption granularity control
+	 * until D0 which is the default case so this is equivalent to
+	 * !WaDisablePerCtxtPreemptionGranularityControl:skl
+	 */
+	if (IS_SKL_REVID(dev, SKL_REVID_E0, REVID_FOREVER)) {
+		I915_WRITE(GEN7_FF_SLICE_CS_CHICKEN1,
+			   _MASKED_BIT_ENABLE(GEN9_FFSC_PERCTX_PREEMPT_CTRL));
+	}
+
 	if (IS_SKL_REVID(dev, 0, SKL_REVID_D0)) {
 		/* WaDisableChickenBitTSGBarrierAckForFFSliceCS:skl */
 		I915_WRITE(FF_SLICE_CS_CHICKEN2,
@@ -1044,7 +1085,8 @@ static int skl_init_workarounds(struct intel_engine_cs *ring)
 		WA_SET_BIT_MASKED(HIZ_CHICKEN,
 				  BDW_HIZ_POWER_COMPILER_CLOCK_GATING_DISABLE);
 
-	if (IS_SKL_REVID(dev, 0, SKL_REVID_F0)) {
+	/* This is tied to WaForceContextSaveRestoreNonCoherent */
+	if (IS_SKL_REVID(dev, 0, REVID_FOREVER)) {
 		/*
 		 *Use Force Non-Coherent whenever executing a 3D context. This
 		 * is a workaround for a possible hang in the unlikely event
@@ -1071,6 +1113,11 @@ static int skl_init_workarounds(struct intel_engine_cs *ring)
 			GEN7_HALF_SLICE_CHICKEN1,
 			GEN7_SBE_SS_CACHE_DISPATCH_PORT_SHARING_DISABLE);
 
+	/* WaDisableLSQCROPERFforOCL:skl */
+	ret = wa_ring_whitelist_reg(ring, GEN8_L3SQCREG4);
+	if (ret)
+		return ret;
+
 	return skl_tune_iz_hashing(ring);
 }
 
@@ -1106,6 +1153,20 @@ static int bxt_init_workarounds(struct intel_engine_cs *ring)
 			GEN7_SBE_SS_CACHE_DISPATCH_PORT_SHARING_DISABLE);
 	}
 
+	/* WaDisableObjectLevelPreemptionForTrifanOrPolygon:bxt */
+	/* WaDisableObjectLevelPreemptionForInstancedDraw:bxt */
+	/* WaDisableObjectLevelPreemtionForInstanceId:bxt */
+	/* WaDisableLSQCROPERFforOCL:bxt */
+	if (IS_BXT_REVID(dev, 0, BXT_REVID_A1)) {
+		ret = wa_ring_whitelist_reg(ring, GEN9_CS_DEBUG_MODE1);
+		if (ret)
+			return ret;
+
+		ret = wa_ring_whitelist_reg(ring, GEN8_L3SQCREG4);
+		if (ret)
+			return ret;
+	}
+
 	return 0;
 }
 
@@ -1117,6 +1178,7 @@ int init_workarounds_ring(struct intel_engine_cs *ring)
 	WARN_ON(ring->id != RCS);
 
 	dev_priv->workarounds.count = 0;
+	dev_priv->workarounds.hw_whitelist_count[RCS] = 0;
 
 	if (IS_BROADWELL(dev))
 		return bdw_init_workarounds(ring);
@@ -1867,15 +1929,13 @@ i830_dispatch_execbuffer(struct drm_i915_gem_request *req,
 		offset = cs_offset;
 	}
 
-	ret = intel_ring_begin(req, 4);
+	ret = intel_ring_begin(req, 2);
 	if (ret)
 		return ret;
 
-	intel_ring_emit(ring, MI_BATCH_BUFFER);
+	intel_ring_emit(ring, MI_BATCH_BUFFER_START | MI_BATCH_GTT);
 	intel_ring_emit(ring, offset | (dispatch_flags & I915_DISPATCH_SECURE ?
 					0 : MI_BATCH_NON_SECURE));
-	intel_ring_emit(ring, offset + len - 8);
-	intel_ring_emit(ring, MI_NOOP);
 	intel_ring_advance(ring);
 
 	return 0;
@@ -1901,6 +1961,17 @@ i915_dispatch_execbuffer(struct drm_i915_gem_request *req,
 	return 0;
 }
 
+static void cleanup_phys_status_page(struct intel_engine_cs *ring)
+{
+	struct drm_i915_private *dev_priv = to_i915(ring->dev);
+
+	if (!dev_priv->status_page_dmah)
+		return;
+
+	drm_pci_free(ring->dev, dev_priv->status_page_dmah);
+	ring->status_page.page_addr = NULL;
+}
+
 static void cleanup_status_page(struct intel_engine_cs *ring)
 {
 	struct drm_i915_gem_object *obj;
@@ -1917,9 +1988,9 @@ static void cleanup_status_page(struct intel_engine_cs *ring)
 
 static int init_status_page(struct intel_engine_cs *ring)
 {
-	struct drm_i915_gem_object *obj;
+	struct drm_i915_gem_object *obj = ring->status_page.obj;
 
-	if ((obj = ring->status_page.obj) == NULL) {
+	if (obj == NULL) {
 		unsigned flags;
 		int ret;
 
@@ -1990,6 +2061,7 @@ void intel_unpin_ringbuffer_obj(struct intel_ringbuffer *ringbuf)
 	else
 		iounmap(ringbuf->virtual_start);
 	ringbuf->virtual_start = NULL;
+	ringbuf->vma = NULL;
 	i915_gem_object_ggtt_unpin(ringbuf->obj);
 }
 
@@ -2019,10 +2091,12 @@ int intel_pin_and_map_ringbuffer_obj(struct drm_device *dev,
 {
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct drm_i915_gem_object *obj = ringbuf->obj;
+	/* Ring wraparound at offset 0 sometimes hangs. No idea why. */
+	unsigned flags = PIN_OFFSET_BIAS | 4096;
 	int ret;
 
 	if (HAS_LLC(dev_priv) && !obj->stolen) {
-		ret = i915_gem_obj_ggtt_pin(obj, PAGE_SIZE, 0);
+		ret = i915_gem_obj_ggtt_pin(obj, PAGE_SIZE, flags);
 		if (ret)
 			return ret;
 
@@ -2038,7 +2112,8 @@ int intel_pin_and_map_ringbuffer_obj(struct drm_device *dev,
 			return -ENOMEM;
 		}
 	} else {
-		ret = i915_gem_obj_ggtt_pin(obj, PAGE_SIZE, PIN_MAPPABLE);
+		ret = i915_gem_obj_ggtt_pin(obj, PAGE_SIZE,
+					    flags | PIN_MAPPABLE);
 		if (ret)
 			return ret;
 
@@ -2048,6 +2123,9 @@ int intel_pin_and_map_ringbuffer_obj(struct drm_device *dev,
 			return ret;
 		}
 
+		/* Access through the GTT requires the device to be awake. */
+		assert_rpm_wakelock_held(dev_priv);
+
 		ringbuf->virtual_start = ioremap_wc(dev_priv->gtt.mappable_base +
 						    i915_gem_obj_ggtt_offset(obj), ringbuf->size);
 		if (ringbuf->virtual_start == NULL) {
@@ -2056,6 +2134,8 @@ int intel_pin_and_map_ringbuffer_obj(struct drm_device *dev,
 		}
 	}
 
+	ringbuf->vma = i915_gem_obj_to_ggtt(obj);
+
 	return 0;
 }
 
@@ -2164,7 +2244,7 @@ static int intel_init_ring_buffer(struct drm_device *dev,
 		if (ret)
 			goto error;
 	} else {
-		BUG_ON(ring->id != RCS);
+		WARN_ON(ring->id != RCS);
 		ret = init_phys_status_page(ring);
 		if (ret)
 			goto error;
@@ -2210,7 +2290,12 @@ void intel_cleanup_ring_buffer(struct intel_engine_cs *ring)
 	if (ring->cleanup)
 		ring->cleanup(ring);
 
-	cleanup_status_page(ring);
+	if (I915_NEED_GFX_HWS(ring->dev)) {
+		cleanup_status_page(ring);
+	} else {
+		WARN_ON(ring->id != RCS);
+		cleanup_phys_status_page(ring);
+	}
 
 	i915_cmd_parser_fini_ring(ring);
 	i915_gem_batch_pool_fini(&ring->batch_pool);
@@ -2373,11 +2458,11 @@ static int __intel_ring_prepare(struct intel_engine_cs *ring, int bytes)
 		if (unlikely(total_bytes > remain_usable)) {
 			/*
 			 * The base request will fit but the reserved space
-			 * falls off the end. So only need to to wait for the
-			 * reserved size after flushing out the remainder.
+			 * falls off the end. So don't need an immediate wrap
+			 * and only need to effectively wait for the reserved
+			 * size space from the start of ringbuffer.
 			 */
 			wait_bytes = remain_actual + ringbuf->reserved_size;
-			need_wrap = true;
 		} else if (total_bytes > ringbuf->space) {
 			/* No wrapping required, just waiting. */
 			wait_bytes = total_bytes;
@@ -2666,6 +2751,7 @@ int intel_init_render_ring_buffer(struct drm_device *dev)
 
 	ring->name = "render ring";
 	ring->id = RCS;
+	ring->exec_id = I915_EXEC_RENDER;
 	ring->mmio_base = RENDER_RING_BASE;
 
 	if (INTEL_INFO(dev)->gen >= 8) {
@@ -2814,6 +2900,7 @@ int intel_init_bsd_ring_buffer(struct drm_device *dev)
 
 	ring->name = "bsd ring";
 	ring->id = VCS;
+	ring->exec_id = I915_EXEC_BSD;
 
 	ring->write_tail = ring_write_tail;
 	if (INTEL_INFO(dev)->gen >= 6) {
@@ -2890,6 +2977,7 @@ int intel_init_bsd2_ring_buffer(struct drm_device *dev)
 
 	ring->name = "bsd2 ring";
 	ring->id = VCS2;
+	ring->exec_id = I915_EXEC_BSD;
 
 	ring->write_tail = ring_write_tail;
 	ring->mmio_base = GEN8_BSD2_RING_BASE;
@@ -2920,6 +3008,7 @@ int intel_init_blt_ring_buffer(struct drm_device *dev)
 
 	ring->name = "blitter ring";
 	ring->id = BCS;
+	ring->exec_id = I915_EXEC_BLT;
 
 	ring->mmio_base = BLT_RING_BASE;
 	ring->write_tail = ring_write_tail;
@@ -2977,6 +3066,7 @@ int intel_init_vebox_ring_buffer(struct drm_device *dev)
 
 	ring->name = "video enhancement ring";
 	ring->id = VECS;
+	ring->exec_id = I915_EXEC_VEBOX;
 
 	ring->mmio_base = VEBOX_RING_BASE;
 	ring->write_tail = ring_write_tail;