[PATCH 8/11] drm/i915: add frontbuffer tracking to FBC

[Paulo Zanoni <przanoni@gmail.com>]

From: Paulo Zanoni <paulo.r.zanoni@intel.com>

Kill the blt/render tracking we currently have and use the frontbuffer
tracking infrastructure.

Don't enable things by default yet.

v2: (Rodrigo) Fix small conflict on rebase and typo at subject.
v3: (Paulo) Rebase on RENDER_CS change.

Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com> (v2)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
---
 drivers/gpu/drm/i915/i915_drv.h          |   9 +--
 drivers/gpu/drm/i915/intel_drv.h         |   6 +-
 drivers/gpu/drm/i915/intel_fbc.c         | 107 ++++++++++++++++++++-----------
 drivers/gpu/drm/i915/intel_frontbuffer.c |  14 +---
 drivers/gpu/drm/i915/intel_ringbuffer.c  |  41 +-----------
 drivers/gpu/drm/i915/intel_ringbuffer.h  |   1 -
 6 files changed, 80 insertions(+), 98 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 5de5c77..d81ecd7 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -708,6 +708,7 @@ struct i915_fbc {
 	unsigned long size;
 	unsigned threshold;
 	unsigned int fb_id;
+	unsigned int possible_framebuffer_bits;
 	struct intel_crtc *crtc;
 	int y;
 
@@ -720,14 +721,6 @@ struct i915_fbc {
 	 * possible. */
 	bool enabled;
 
-	/* On gen8 some rings cannont perform fbc clean operation so for now
-	 * we are doing this on SW with mmio.
-	 * This variable works in the opposite information direction
-	 * of ring->fbc_dirty telling software on frontbuffer tracking
-	 * to perform the cache clean on sw side.
-	 */
-	bool need_sw_cache_clean;
-
 	struct intel_fbc_work {
 		struct delayed_work work;
 		struct drm_crtc *crtc;
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index 633fb9a..3a1c3d82 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -1071,7 +1071,11 @@ bool intel_fbc_enabled(struct drm_device *dev);
 void intel_fbc_update(struct drm_device *dev);
 void intel_fbc_init(struct drm_i915_private *dev_priv);
 void intel_fbc_disable(struct drm_device *dev);
-void bdw_fbc_sw_flush(struct drm_device *dev, u32 value);
+void intel_fbc_invalidate(struct drm_i915_private *dev_priv,
+			  unsigned int frontbuffer_bits,
+			  enum fb_op_origin origin);
+void intel_fbc_flush(struct drm_i915_private *dev_priv,
+		     unsigned int frontbuffer_bits, enum fb_op_origin origin);
 
 /* intel_hdmi.c */
 void intel_hdmi_init(struct drm_device *dev, int hdmi_reg, enum port port);
diff --git a/drivers/gpu/drm/i915/intel_fbc.c b/drivers/gpu/drm/i915/intel_fbc.c
index f658dc0..c71b435 100644
--- a/drivers/gpu/drm/i915/intel_fbc.c
+++ b/drivers/gpu/drm/i915/intel_fbc.c
@@ -173,29 +173,10 @@ static bool g4x_fbc_enabled(struct drm_device *dev)
 	return I915_READ(DPFC_CONTROL) & DPFC_CTL_EN;
 }
 
-static void snb_fbc_blit_update(struct drm_device *dev)
+static void intel_fbc_nuke(struct drm_i915_private *dev_priv)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	u32 blt_ecoskpd;
-
-	/* Make sure blitter notifies FBC of writes */
-
-	/* Blitter is part of Media powerwell on VLV. No impact of
-	 * his param in other platforms for now */
-	gen6_gt_force_wake_get(dev_priv, FORCEWAKE_MEDIA);
-
-	blt_ecoskpd = I915_READ(GEN6_BLITTER_ECOSKPD);
-	blt_ecoskpd |= GEN6_BLITTER_FBC_NOTIFY <<
-		GEN6_BLITTER_LOCK_SHIFT;
-	I915_WRITE(GEN6_BLITTER_ECOSKPD, blt_ecoskpd);
-	blt_ecoskpd |= GEN6_BLITTER_FBC_NOTIFY;
-	I915_WRITE(GEN6_BLITTER_ECOSKPD, blt_ecoskpd);
-	blt_ecoskpd &= ~(GEN6_BLITTER_FBC_NOTIFY <<
-			 GEN6_BLITTER_LOCK_SHIFT);
-	I915_WRITE(GEN6_BLITTER_ECOSKPD, blt_ecoskpd);
-	POSTING_READ(GEN6_BLITTER_ECOSKPD);
-
-	gen6_gt_force_wake_put(dev_priv, FORCEWAKE_MEDIA);
+	I915_WRITE(MSG_FBC_REND_STATE, FBC_REND_NUKE);
+	POSTING_READ(MSG_FBC_REND_STATE);
 }
 
 static void ilk_fbc_enable(struct drm_crtc *crtc)
@@ -238,9 +219,10 @@ static void ilk_fbc_enable(struct drm_crtc *crtc)
 		I915_WRITE(SNB_DPFC_CTL_SA,
 			   SNB_CPU_FENCE_ENABLE | obj->fence_reg);
 		I915_WRITE(DPFC_CPU_FENCE_OFFSET, crtc->y);
-		snb_fbc_blit_update(dev);
 	}
 
+	intel_fbc_nuke(dev_priv);
+
 	DRM_DEBUG_KMS("enabled fbc on plane %c\n", plane_name(intel_crtc->plane));
 }
 
@@ -319,7 +301,7 @@ static void gen7_fbc_enable(struct drm_crtc *crtc)
 		   SNB_CPU_FENCE_ENABLE | obj->fence_reg);
 	I915_WRITE(DPFC_CPU_FENCE_OFFSET, crtc->y);
 
-	snb_fbc_blit_update(dev);
+	intel_fbc_nuke(dev_priv);
 
 	DRM_DEBUG_KMS("enabled fbc on plane %c\n", plane_name(intel_crtc->plane));
 }
@@ -339,19 +321,6 @@ bool intel_fbc_enabled(struct drm_device *dev)
 	return dev_priv->fbc.enabled;
 }
 
-void bdw_fbc_sw_flush(struct drm_device *dev, u32 value)
-{
-	struct drm_i915_private *dev_priv = dev->dev_private;
-
-	if (!IS_GEN8(dev))
-		return;
-
-	if (!intel_fbc_enabled(dev))
-		return;
-
-	I915_WRITE(MSG_FBC_REND_STATE, value);
-}
-
 static void intel_fbc_work_fn(struct work_struct *__work)
 {
 	struct intel_fbc_work *work =
@@ -657,6 +626,63 @@ out_disable:
 	i915_gem_stolen_cleanup_compression(dev);
 }
 
+void intel_fbc_invalidate(struct drm_i915_private *dev_priv,
+			  unsigned int frontbuffer_bits,
+			  enum fb_op_origin origin)
+{
+	struct drm_device *dev = dev_priv->dev;
+	unsigned int fbc_bits;
+
+	if (origin == ORIGIN_GTT)
+		return;
+
+	if (dev_priv->fbc.enabled)
+		fbc_bits = INTEL_FRONTBUFFER_PRIMARY(dev_priv->fbc.crtc->pipe);
+	else if (dev_priv->fbc.fbc_work)
+		fbc_bits = INTEL_FRONTBUFFER_PRIMARY(
+			to_intel_crtc(dev_priv->fbc.fbc_work->crtc)->pipe);
+	else
+		fbc_bits = dev_priv->fbc.possible_framebuffer_bits;
+
+	if ((fbc_bits & frontbuffer_bits) == 0)
+		return;
+
+	intel_fbc_disable(dev);
+}
+
+void intel_fbc_flush(struct drm_i915_private *dev_priv,
+		     unsigned int frontbuffer_bits,
+		     enum fb_op_origin origin)
+{
+	struct drm_device *dev = dev_priv->dev;
+	unsigned int fbc_bits = 0;
+	bool fbc_enabled;
+
+	if (dev_priv->fbc.enabled)
+		fbc_bits = INTEL_FRONTBUFFER_PRIMARY(dev_priv->fbc.crtc->pipe);
+	else
+		fbc_bits = dev_priv->fbc.possible_framebuffer_bits;
+
+	/* These are not the planes you are looking for. */
+	if ((frontbuffer_bits & fbc_bits) == 0)
+		return;
+
+	fbc_enabled = intel_fbc_enabled(dev);
+
+	if ((dev_priv->fb_tracking.busy_bits & frontbuffer_bits &
+	     fbc_bits) == 0) {
+		if (fbc_enabled) {
+			if (origin == ORIGIN_CS || origin == ORIGIN_CPU)
+				intel_fbc_nuke(dev_priv);
+		} else {
+			intel_fbc_update(dev);
+		}
+	} else {
+		if (fbc_enabled)
+			intel_fbc_disable(dev);
+	}
+}
+
 /**
  * intel_fbc_init - Initialize FBC
  * @dev_priv: the i915 device
@@ -665,12 +691,19 @@ out_disable:
  */
 void intel_fbc_init(struct drm_i915_private *dev_priv)
 {
+	enum pipe pipe;
+
 	if (!HAS_FBC(dev_priv)) {
 		dev_priv->fbc.enabled = false;
 		dev_priv->fbc.no_fbc_reason = FBC_UNSUPPORTED;
 		return;
 	}
 
+	/* TODO: some platforms have FBC tied to a specific plane! */
+	for_each_pipe(dev_priv, pipe)
+		dev_priv->fbc.possible_framebuffer_bits |=
+				INTEL_FRONTBUFFER_PRIMARY(pipe);
+
 	if (INTEL_INFO(dev_priv)->gen >= 7) {
 		dev_priv->display.fbc_enabled = ilk_fbc_enabled;
 		dev_priv->display.enable_fbc = gen7_fbc_enable;
diff --git a/drivers/gpu/drm/i915/intel_frontbuffer.c b/drivers/gpu/drm/i915/intel_frontbuffer.c
index 3d35f31..0f5e926 100644
--- a/drivers/gpu/drm/i915/intel_frontbuffer.c
+++ b/drivers/gpu/drm/i915/intel_frontbuffer.c
@@ -118,8 +118,6 @@ static void intel_mark_fb_busy(struct drm_device *dev,
 			continue;
 
 		intel_increase_pllclock(dev, pipe);
-		if (ring && intel_fbc_enabled(dev))
-			ring->fbc_dirty = true;
 	}
 }
 
@@ -159,6 +157,7 @@ void intel_fb_obj_invalidate(struct drm_i915_gem_object *obj,
 	intel_mark_fb_busy(dev, obj->frontbuffer_bits, ring);
 
 	intel_psr_invalidate(dev, obj->frontbuffer_bits);
+	intel_fbc_invalidate(dev_priv, obj->frontbuffer_bits, origin);
 }
 
 /**
@@ -187,16 +186,7 @@ void intel_frontbuffer_flush(struct drm_device *dev,
 	intel_mark_fb_busy(dev, frontbuffer_bits, NULL);
 
 	intel_psr_flush(dev, frontbuffer_bits);
-
-	/*
-	 * FIXME: Unconditional fbc flushing here is a rather gross hack and
-	 * needs to be reworked into a proper frontbuffer tracking scheme like
-	 * psr employs.
-	 */
-	if (dev_priv->fbc.need_sw_cache_clean) {
-		dev_priv->fbc.need_sw_cache_clean = false;
-		bdw_fbc_sw_flush(dev, FBC_REND_CACHE_CLEAN);
-	}
+	intel_fbc_flush(dev_priv, frontbuffer_bits, origin);
 }
 
 /**
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 4702e7b..0d64d72 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -317,29 +317,6 @@ gen7_render_ring_cs_stall_wa(struct intel_engine_cs *ring)
 	return 0;
 }
 
-static int gen7_ring_fbc_flush(struct intel_engine_cs *ring, u32 value)
-{
-	int ret;
-
-	if (!ring->fbc_dirty)
-		return 0;
-
-	ret = intel_ring_begin(ring, 6);
-	if (ret)
-		return ret;
-	/* WaFbcNukeOn3DBlt:ivb/hsw */
-	intel_ring_emit(ring, MI_LOAD_REGISTER_IMM(1));
-	intel_ring_emit(ring, MSG_FBC_REND_STATE);
-	intel_ring_emit(ring, value);
-	intel_ring_emit(ring, MI_STORE_REGISTER_MEM(1) | MI_SRM_LRM_GLOBAL_GTT);
-	intel_ring_emit(ring, MSG_FBC_REND_STATE);
-	intel_ring_emit(ring, ring->scratch.gtt_offset + 256);
-	intel_ring_advance(ring);
-
-	ring->fbc_dirty = false;
-	return 0;
-}
-
 static int
 gen7_render_ring_flush(struct intel_engine_cs *ring,
 		       u32 invalidate_domains, u32 flush_domains)
@@ -395,9 +372,6 @@ gen7_render_ring_flush(struct intel_engine_cs *ring,
 	intel_ring_emit(ring, 0);
 	intel_ring_advance(ring);
 
-	if (!invalidate_domains && flush_domains)
-		return gen7_ring_fbc_flush(ring, FBC_REND_NUKE);
-
 	return 0;
 }
 
@@ -459,9 +433,6 @@ gen8_render_ring_flush(struct intel_engine_cs *ring,
 	if (ret)
 		return ret;
 
-	if (!invalidate_domains && flush_domains)
-		return gen7_ring_fbc_flush(ring, FBC_REND_NUKE);
-
 	return 0;
 }
 
@@ -2296,7 +2267,6 @@ static int gen6_ring_flush(struct intel_engine_cs *ring,
 			   u32 invalidate, u32 flush)
 {
 	struct drm_device *dev = ring->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
 	uint32_t cmd;
 	int ret;
 
@@ -2305,7 +2275,7 @@ static int gen6_ring_flush(struct intel_engine_cs *ring,
 		return ret;
 
 	cmd = MI_FLUSH_DW;
-	if (INTEL_INFO(ring->dev)->gen >= 8)
+	if (INTEL_INFO(dev)->gen >= 8)
 		cmd += 1;
 	/*
 	 * Bspec vol 1c.3 - blitter engine command streamer:
@@ -2318,7 +2288,7 @@ static int gen6_ring_flush(struct intel_engine_cs *ring,
 			MI_FLUSH_DW_OP_STOREDW;
 	intel_ring_emit(ring, cmd);
 	intel_ring_emit(ring, I915_GEM_HWS_SCRATCH_ADDR | MI_FLUSH_DW_USE_GTT);
-	if (INTEL_INFO(ring->dev)->gen >= 8) {
+	if (INTEL_INFO(dev)->gen >= 8) {
 		intel_ring_emit(ring, 0); /* upper addr */
 		intel_ring_emit(ring, 0); /* value */
 	} else  {
@@ -2327,13 +2297,6 @@ static int gen6_ring_flush(struct intel_engine_cs *ring,
 	}
 	intel_ring_advance(ring);
 
-	if (!invalidate && flush) {
-		if (IS_GEN7(dev))
-			return gen7_ring_fbc_flush(ring, FBC_REND_CACHE_CLEAN);
-		else if (IS_BROADWELL(dev))
-			dev_priv->fbc.need_sw_cache_clean = true;
-	}
-
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 6dbb6f4..7e31ec8 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -269,7 +269,6 @@ struct  intel_engine_cs {
 	 */
 	struct drm_i915_gem_request *outstanding_lazy_request;
 	bool gpu_caches_dirty;
-	bool fbc_dirty;
 
 	wait_queue_head_t irq_queue;
 
-- 
2.1.3

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx