1 files changed, 85 insertions, 158 deletions

diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index f457146ff6a4..c7bc93d28d84 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -362,12 +362,15 @@ gen7_render_ring_flush(struct intel_engine_cs *ring,
 		flags |= PIPE_CONTROL_VF_CACHE_INVALIDATE;
 		flags |= PIPE_CONTROL_CONST_CACHE_INVALIDATE;
 		flags |= PIPE_CONTROL_STATE_CACHE_INVALIDATE;
+		flags |= PIPE_CONTROL_MEDIA_STATE_CLEAR;
 		/*
 		 * TLB invalidate requires a post-sync write.
 		 */
 		flags |= PIPE_CONTROL_QW_WRITE;
 		flags |= PIPE_CONTROL_GLOBAL_GTT_IVB;
 
+		flags |= PIPE_CONTROL_STALL_AT_SCOREBOARD;
+
 		/* Workaround: we must issue a pipe_control with CS-stall bit
 		 * set before a pipe_control command that has the state cache
 		 * invalidate bit set. */
@@ -589,14 +592,10 @@ static int init_ring_common(struct intel_engine_cs *ring)
 		goto out;
 	}
 
-	if (!drm_core_check_feature(ring->dev, DRIVER_MODESET))
-		i915_kernel_lost_context(ring->dev);
-	else {
-		ringbuf->head = I915_READ_HEAD(ring);
-		ringbuf->tail = I915_READ_TAIL(ring) & TAIL_ADDR;
-		ringbuf->space = intel_ring_space(ringbuf);
-		ringbuf->last_retired_head = -1;
-	}
+	ringbuf->head = I915_READ_HEAD(ring);
+	ringbuf->tail = I915_READ_TAIL(ring) & TAIL_ADDR;
+	ringbuf->space = intel_ring_space(ringbuf);
+	ringbuf->last_retired_head = -1;
 
 	memset(&ring->hangcheck, 0, sizeof(ring->hangcheck));
 
@@ -665,7 +664,8 @@ err:
 	return ret;
 }
 
-static int intel_ring_workarounds_emit(struct intel_engine_cs *ring)
+static int intel_ring_workarounds_emit(struct intel_engine_cs *ring,
+				       struct intel_context *ctx)
 {
 	int ret, i;
 	struct drm_device *dev = ring->dev;
@@ -704,7 +704,7 @@ static int intel_ring_workarounds_emit(struct intel_engine_cs *ring)
 }
 
 static int wa_add(struct drm_i915_private *dev_priv,
-		  const u32 addr, const u32 val, const u32 mask)
+		  const u32 addr, const u32 mask, const u32 val)
 {
 	const u32 idx = dev_priv->workarounds.count;
 
@@ -720,22 +720,25 @@ static int wa_add(struct drm_i915_private *dev_priv,
 	return 0;
 }
 
-#define WA_REG(addr, val, mask) { \
-		const int r = wa_add(dev_priv, (addr), (val), (mask)); \
+#define WA_REG(addr, mask, val) { \
+		const int r = wa_add(dev_priv, (addr), (mask), (val)); \
 		if (r) \
 			return r; \
 	}
 
 #define WA_SET_BIT_MASKED(addr, mask) \
-	WA_REG(addr, _MASKED_BIT_ENABLE(mask), (mask) & 0xffff)
+	WA_REG(addr, (mask), _MASKED_BIT_ENABLE(mask))
 
 #define WA_CLR_BIT_MASKED(addr, mask) \
-	WA_REG(addr, _MASKED_BIT_DISABLE(mask), (mask) & 0xffff)
+	WA_REG(addr, (mask), _MASKED_BIT_DISABLE(mask))
 
-#define WA_SET_BIT(addr, mask) WA_REG(addr, I915_READ(addr) | (mask), mask)
-#define WA_CLR_BIT(addr, mask) WA_REG(addr, I915_READ(addr) & ~(mask), mask)
+#define WA_SET_FIELD_MASKED(addr, mask, value) \
+	WA_REG(addr, mask, _MASKED_FIELD(mask, value))
 
-#define WA_WRITE(addr, val) WA_REG(addr, val, 0xffffffff)
+#define WA_SET_BIT(addr, mask) WA_REG(addr, mask, I915_READ(addr) | (mask))
+#define WA_CLR_BIT(addr, mask) WA_REG(addr, mask, I915_READ(addr) & ~(mask))
+
+#define WA_WRITE(addr, val) WA_REG(addr, 0xffffffff, val)
 
 static int bdw_init_workarounds(struct intel_engine_cs *ring)
 {
@@ -776,8 +779,9 @@ static int bdw_init_workarounds(struct intel_engine_cs *ring)
 	 * disable bit, which we don't touch here, but it's good
 	 * to keep in mind (see 3DSTATE_PS and 3DSTATE_WM).
 	 */
-	WA_SET_BIT_MASKED(GEN7_GT_MODE,
-			  GEN6_WIZ_HASHING_MASK | GEN6_WIZ_HASHING_16x4);
+	WA_SET_FIELD_MASKED(GEN7_GT_MODE,
+			    GEN6_WIZ_HASHING_MASK,
+			    GEN6_WIZ_HASHING_16x4);
 
 	return 0;
 }
@@ -788,25 +792,25 @@ static int chv_init_workarounds(struct intel_engine_cs *ring)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
 	/* WaDisablePartialInstShootdown:chv */
-	WA_SET_BIT_MASKED(GEN8_ROW_CHICKEN,
-		  PARTIAL_INSTRUCTION_SHOOTDOWN_DISABLE);
-
 	/* WaDisableThreadStallDopClockGating:chv */
 	WA_SET_BIT_MASKED(GEN8_ROW_CHICKEN,
-		  STALL_DOP_GATING_DISABLE);
-
-	/* WaDisableDopClockGating:chv (pre-production hw) */
-	WA_SET_BIT_MASKED(GEN7_ROW_CHICKEN2,
-		  DOP_CLOCK_GATING_DISABLE);
+			  PARTIAL_INSTRUCTION_SHOOTDOWN_DISABLE |
+			  STALL_DOP_GATING_DISABLE);
 
-	/* WaDisableSamplerPowerBypass:chv (pre-production hw) */
-	WA_SET_BIT_MASKED(HALF_SLICE_CHICKEN3,
-		  GEN8_SAMPLER_POWER_BYPASS_DIS);
+	/* Use Force Non-Coherent whenever executing a 3D context. This is a
+	 * workaround for a possible hang in the unlikely event a TLB
+	 * invalidation occurs during a PSD flush.
+	 */
+	/* WaForceEnableNonCoherent:chv */
+	/* WaHdcDisableFetchWhenMasked:chv */
+	WA_SET_BIT_MASKED(HDC_CHICKEN0,
+			  HDC_FORCE_NON_COHERENT |
+			  HDC_DONOT_FETCH_MEM_WHEN_MASKED);
 
 	return 0;
 }
 
-static int init_workarounds_ring(struct intel_engine_cs *ring)
+int init_workarounds_ring(struct intel_engine_cs *ring)
 {
 	struct drm_device *dev = ring->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -1721,13 +1725,42 @@ static int init_phys_status_page(struct intel_engine_cs *ring)
 	return 0;
 }
 
-void intel_destroy_ringbuffer_obj(struct intel_ringbuffer *ringbuf)
+void intel_unpin_ringbuffer_obj(struct intel_ringbuffer *ringbuf)
 {
-	if (!ringbuf->obj)
-		return;
-
 	iounmap(ringbuf->virtual_start);
+	ringbuf->virtual_start = NULL;
 	i915_gem_object_ggtt_unpin(ringbuf->obj);
+}
+
+int intel_pin_and_map_ringbuffer_obj(struct drm_device *dev,
+				     struct intel_ringbuffer *ringbuf)
+{
+	struct drm_i915_private *dev_priv = to_i915(dev);
+	struct drm_i915_gem_object *obj = ringbuf->obj;
+	int ret;
+
+	ret = i915_gem_obj_ggtt_pin(obj, PAGE_SIZE, PIN_MAPPABLE);
+	if (ret)
+		return ret;
+
+	ret = i915_gem_object_set_to_gtt_domain(obj, true);
+	if (ret) {
+		i915_gem_object_ggtt_unpin(obj);
+		return ret;
+	}
+
+	ringbuf->virtual_start = ioremap_wc(dev_priv->gtt.mappable_base +
+			i915_gem_obj_ggtt_offset(obj), ringbuf->size);
+	if (ringbuf->virtual_start == NULL) {
+		i915_gem_object_ggtt_unpin(obj);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+void intel_destroy_ringbuffer_obj(struct intel_ringbuffer *ringbuf)
+{
 	drm_gem_object_unreference(&ringbuf->obj->base);
 	ringbuf->obj = NULL;
 }
@@ -1735,12 +1768,7 @@ void intel_destroy_ringbuffer_obj(struct intel_ringbuffer *ringbuf)
 int intel_alloc_ringbuffer_obj(struct drm_device *dev,
 			       struct intel_ringbuffer *ringbuf)
 {
-	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct drm_i915_gem_object *obj;
-	int ret;
-
-	if (ringbuf->obj)
-		return 0;
 
 	obj = NULL;
 	if (!HAS_LLC(dev))
@@ -1753,30 +1781,9 @@ int intel_alloc_ringbuffer_obj(struct drm_device *dev,
 	/* mark ring buffers as read-only from GPU side by default */
 	obj->gt_ro = 1;
 
-	ret = i915_gem_obj_ggtt_pin(obj, PAGE_SIZE, PIN_MAPPABLE);
-	if (ret)
-		goto err_unref;
-
-	ret = i915_gem_object_set_to_gtt_domain(obj, true);
-	if (ret)
-		goto err_unpin;
-
-	ringbuf->virtual_start =
-		ioremap_wc(dev_priv->gtt.mappable_base + i915_gem_obj_ggtt_offset(obj),
-				ringbuf->size);
-	if (ringbuf->virtual_start == NULL) {
-		ret = -EINVAL;
-		goto err_unpin;
-	}
-
 	ringbuf->obj = obj;
-	return 0;
 
-err_unpin:
-	i915_gem_object_ggtt_unpin(obj);
-err_unref:
-	drm_gem_object_unreference(&obj->base);
-	return ret;
+	return 0;
 }
 
 static int intel_init_ring_buffer(struct drm_device *dev,
@@ -1813,10 +1820,21 @@ static int intel_init_ring_buffer(struct drm_device *dev,
 			goto error;
 	}
 
-	ret = intel_alloc_ringbuffer_obj(dev, ringbuf);
-	if (ret) {
-		DRM_ERROR("Failed to allocate ringbuffer %s: %d\n", ring->name, ret);
-		goto error;
+	if (ringbuf->obj == NULL) {
+		ret = intel_alloc_ringbuffer_obj(dev, ringbuf);
+		if (ret) {
+			DRM_ERROR("Failed to allocate ringbuffer %s: %d\n",
+					ring->name, ret);
+			goto error;
+		}
+
+		ret = intel_pin_and_map_ringbuffer_obj(dev, ringbuf);
+		if (ret) {
+			DRM_ERROR("Failed to pin and map ringbuffer %s: %d\n",
+					ring->name, ret);
+			intel_destroy_ringbuffer_obj(ringbuf);
+			goto error;
+		}
 	}
 
 	/* Workaround an erratum on the i830 which causes a hang if
@@ -1857,6 +1875,7 @@ void intel_cleanup_ring_buffer(struct intel_engine_cs *ring)
 	intel_stop_ring_buffer(ring);
 	WARN_ON(!IS_GEN2(ring->dev) && (I915_READ_MODE(ring) & MODE_IDLE) == 0);
 
+	intel_unpin_ringbuffer_obj(ringbuf);
 	intel_destroy_ringbuffer_obj(ringbuf);
 	ring->preallocated_lazy_request = NULL;
 	ring->outstanding_lazy_seqno = 0;
@@ -1942,13 +1961,6 @@ static int ring_wait_for_space(struct intel_engine_cs *ring, int n)
 			break;
 		}
 
-		if (!drm_core_check_feature(dev, DRIVER_MODESET) &&
-		    dev->primary->master) {
-			struct drm_i915_master_private *master_priv = dev->primary->master->driver_priv;
-			if (master_priv->sarea_priv)
-				master_priv->sarea_priv->perf_boxes |= I915_BOX_WAIT;
-		}
-
 		msleep(1);
 
 		if (dev_priv->mm.interruptible && signal_pending(current)) {
@@ -2439,91 +2451,6 @@ int intel_init_render_ring_buffer(struct drm_device *dev)
 	return intel_init_ring_buffer(dev, ring);
 }
 
-int intel_render_ring_init_dri(struct drm_device *dev, u64 start, u32 size)
-{
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_engine_cs *ring = &dev_priv->ring[RCS];
-	struct intel_ringbuffer *ringbuf = ring->buffer;
-	int ret;
-
-	if (ringbuf == NULL) {
-		ringbuf = kzalloc(sizeof(*ringbuf), GFP_KERNEL);
-		if (!ringbuf)
-			return -ENOMEM;
-		ring->buffer = ringbuf;
-	}
-
-	ring->name = "render ring";
-	ring->id = RCS;
-	ring->mmio_base = RENDER_RING_BASE;
-
-	if (INTEL_INFO(dev)->gen >= 6) {
-		/* non-kms not supported on gen6+ */
-		ret = -ENODEV;
-		goto err_ringbuf;
-	}
-
-	/* Note: gem is not supported on gen5/ilk without kms (the corresponding
-	 * gem_init ioctl returns with -ENODEV). Hence we do not need to set up
-	 * the special gen5 functions. */
-	ring->add_request = i9xx_add_request;
-	if (INTEL_INFO(dev)->gen < 4)
-		ring->flush = gen2_render_ring_flush;
-	else
-		ring->flush = gen4_render_ring_flush;
-	ring->get_seqno = ring_get_seqno;
-	ring->set_seqno = ring_set_seqno;
-	if (IS_GEN2(dev)) {
-		ring->irq_get = i8xx_ring_get_irq;
-		ring->irq_put = i8xx_ring_put_irq;
-	} else {
-		ring->irq_get = i9xx_ring_get_irq;
-		ring->irq_put = i9xx_ring_put_irq;
-	}
-	ring->irq_enable_mask = I915_USER_INTERRUPT;
-	ring->write_tail = ring_write_tail;
-	if (INTEL_INFO(dev)->gen >= 4)
-		ring->dispatch_execbuffer = i965_dispatch_execbuffer;
-	else if (IS_I830(dev) || IS_845G(dev))
-		ring->dispatch_execbuffer = i830_dispatch_execbuffer;
-	else
-		ring->dispatch_execbuffer = i915_dispatch_execbuffer;
-	ring->init = init_render_ring;
-	ring->cleanup = render_ring_cleanup;
-
-	ring->dev = dev;
-	INIT_LIST_HEAD(&ring->active_list);
-	INIT_LIST_HEAD(&ring->request_list);
-
-	ringbuf->size = size;
-	ringbuf->effective_size = ringbuf->size;
-	if (IS_I830(ring->dev) || IS_845G(ring->dev))
-		ringbuf->effective_size -= 2 * CACHELINE_BYTES;
-
-	ringbuf->virtual_start = ioremap_wc(start, size);
-	if (ringbuf->virtual_start == NULL) {
-		DRM_ERROR("can not ioremap virtual address for"
-			  " ring buffer\n");
-		ret = -ENOMEM;
-		goto err_ringbuf;
-	}
-
-	if (!I915_NEED_GFX_HWS(dev)) {
-		ret = init_phys_status_page(ring);
-		if (ret)
-			goto err_vstart;
-	}
-
-	return 0;
-
-err_vstart:
-	iounmap(ringbuf->virtual_start);
-err_ringbuf:
-	kfree(ringbuf);
-	ring->buffer = NULL;
-	return ret;
-}
-
 int intel_init_bsd_ring_buffer(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;