[Intel-gfx] [PATCH 8/9] drm/i915: Use Write-Through cacheing for the display plane on Iris

[Chris Wilson]

Haswell GT3e has the unique feature of supporting Write-Through cacheing
of objects within the eLLC/LLC. The purpose of this is to enable the display
plane to remain coherent whilst objects lie resident in the eLLC/LLC - so
that we, in theory, get the best of both worlds, perfect display and fast
access.

However, we still need to be careful as the CPU does not see the WT when
accessing the cache. In particular, this means that we need to flush the
cache lines after writing to an object through the CPU, and on
transitioning from a cached state to WT.

v2: Actually do the clflush on transition to WT, nagging by Ville.
v3: Flush the CPU cache after writes into WT objects.
v4: Rease onto LLC updates and report WT as "uncached" for
get_cache_level_ioctl to remain symmetric with set_cache_level_ioctl.

Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
Cc: Ville Syrjälä <ville.syrjala at linux.intel.com>
Cc: Kenneth Graunke <kenneth at whitecape.org>
---
 drivers/gpu/drm/i915/i915_dma.c     |  3 +++
 drivers/gpu/drm/i915/i915_drv.h     |  4 +++-
 drivers/gpu/drm/i915/i915_gem.c     | 14 ++++++++++++--
 drivers/gpu/drm/i915/i915_gem_gtt.c | 11 ++++++++++-
 include/uapi/drm/i915_drm.h         |  1 +
 5 files changed, 29 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c
index 9decc5b..de0b86a 100644
--- a/drivers/gpu/drm/i915/i915_dma.c
+++ b/drivers/gpu/drm/i915/i915_dma.c
@@ -976,6 +976,9 @@ static int i915_getparam(struct drm_device *dev, void *data,
 	case I915_PARAM_HAS_LLC:
 		value = HAS_LLC(dev);
 		break;
+	case I915_PARAM_HAS_WT:
+		value = HAS_WT(dev);
+		break;
 	case I915_PARAM_HAS_ALIASING_PPGTT:
 		value = dev_priv->mm.aliasing_ppgtt ? 1 : 0;
 		break;
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index c51a771..0a903c4 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -457,6 +457,7 @@ enum i915_cache_level {
 			      caches, eg sampler/render caches, and the
 			      large Last-Level-Cache. LLC is coherent with
 			      the CPU, but L3 is only visible to the GPU. */
+	I915_CACHE_WT, /* hsw:gt3e WriteThrough for scanouts */
 };
 
 typedef uint32_t gen6_gtt_pte_t;
@@ -1388,7 +1389,7 @@ struct drm_i915_gem_object {
 	unsigned int pending_fenced_gpu_access:1;
 	unsigned int fenced_gpu_access:1;
 
-	unsigned int cache_level:2;
+	unsigned int cache_level:3;
 
 	unsigned int has_aliasing_ppgtt_mapping:1;
 	unsigned int has_global_gtt_mapping:1;
@@ -1545,6 +1546,7 @@ struct drm_i915_file_private {
 #define HAS_BLT(dev)            (INTEL_INFO(dev)->has_blt_ring)
 #define HAS_VEBOX(dev)          (INTEL_INFO(dev)->has_vebox_ring)
 #define HAS_LLC(dev)            (INTEL_INFO(dev)->has_llc)
+#define HAS_WT(dev)            (IS_HASWELL(dev) && to_i915(dev)->ellc_size)
 #define I915_NEED_GFX_HWS(dev)	(INTEL_INFO(dev)->need_gfx_hws)
 
 #define HAS_HW_CONTEXTS(dev)	(INTEL_INFO(dev)->gen >= 5)
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 2656c69..2b897f2 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -3551,7 +3551,16 @@ int i915_gem_get_caching_ioctl(struct drm_device *dev, void *data,
 		goto unlock;
 	}
 
-	args->caching = obj->cache_level != I915_CACHE_NONE;
+	switch (obj->cache_level) {
+	case I915_CACHE_LLC:
+	case I915_CACHE_L3_LLC:
+		args->caching = I915_CACHING_CACHED;
+		break;
+
+	default:
+		args->caching = I915_CACHING_NONE;
+		break;
+	}
 
 	drm_gem_object_unreference(&obj->base);
 unlock:
@@ -3634,7 +3643,8 @@ i915_gem_object_pin_to_display_plane(struct drm_i915_gem_object *obj,
 	 * of uncaching, which would allow us to flush all the LLC-cached data
 	 * with that bit in the PTE to main memory with just one PIPE_CONTROL.
 	 */
-	ret = i915_gem_object_set_cache_level(obj, I915_CACHE_NONE);
+	ret = i915_gem_object_set_cache_level(obj,
+					      HAS_WT(obj->base.dev) ? I915_CACHE_WT : I915_CACHE_NONE);
 	if (ret)
 		goto err_unpin_display;
 
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 89d8cc8..1791643 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -55,6 +55,7 @@
 #define HSW_WB_LLC_AGE3			HSW_CACHEABILITY_CONTROL(0x2)
 #define HSW_WB_LLC_AGE0			HSW_CACHEABILITY_CONTROL(0x3)
 #define HSW_WB_ELLC_LLC_AGE0		HSW_CACHEABILITY_CONTROL(0xb)
+#define HSW_WT_ELLC_LLC_AGE0		HSW_CACHEABILITY_CONTROL(0x6)
 
 static gen6_gtt_pte_t snb_pte_encode(dma_addr_t addr,
 				     enum i915_cache_level level)
@@ -138,8 +139,16 @@ static gen6_gtt_pte_t iris_pte_encode(dma_addr_t addr,
 	gen6_gtt_pte_t pte = GEN6_PTE_VALID;
 	pte |= HSW_PTE_ADDR_ENCODE(addr);
 
-	if (level != I915_CACHE_NONE)
+	switch (level) {
+	case I915_CACHE_NONE:
+		break;
+	case I915_CACHE_WT:
+		pte |= HSW_WT_ELLC_LLC_AGE0;
+		break;
+	default:
 		pte |= HSW_WB_ELLC_LLC_AGE0;
+		break;
+	}
 
 	return pte;
 }
diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h
index 2b282a2..39d14b3 100644
--- a/include/uapi/drm/i915_drm.h
+++ b/include/uapi/drm/i915_drm.h
@@ -338,6 +338,7 @@ typedef struct drm_i915_irq_wait {
 #define I915_PARAM_HAS_PINNED_BATCHES	 24
 #define I915_PARAM_HAS_EXEC_NO_RELOC	 25
 #define I915_PARAM_HAS_EXEC_HANDLE_LUT   26
+#define I915_PARAM_HAS_WT     	 	 27
 
 typedef struct drm_i915_getparam {
 	int param;
-- 
1.8.4.rc1