drm/i915: Use eLLC/LLC by default when available
DRI clients really should be using MOCS to get fine grained streaming
cache controls. With that note, I *hope* that this patch doesn't improve
performance overwhelmingly, because if it does - it means there is a
problem elsewhere.
In any case, the kernel, and old userspace should get some benefit from
this, so let's do it. eLLC is always a good default, and really not
using it is the special case for MOCS.
References: http://www.intel.com/newsroom/kits/restricted/ha$well!/pdfs/4th_Gen_Intel_Core_PressBriefing_5-29.pdf (page 57)
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@gmail.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 5534dd5..4222733 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -53,6 +53,7 @@
#define HSW_CACHEABILITY_CONTROL(bits) ((((bits) & 0x7) << 1) | \
(((bits) & 0x8) << (11 - 3)))
#define HSW_WB_LLC_AGE0 HSW_CACHEABILITY_CONTROL(0x3)
+#define HSW_WB_ELLC_LLC_AGE0 HSW_CACHEABILITY_CONTROL(0xb)
static gen6_gtt_pte_t gen6_pte_encode(dma_addr_t addr,
enum i915_cache_level level)
@@ -109,6 +110,18 @@
return pte;
}
+static gen6_gtt_pte_t iris_pte_encode(dma_addr_t addr,
+ enum i915_cache_level level)
+{
+ gen6_gtt_pte_t pte = GEN6_PTE_VALID;
+ pte |= HSW_PTE_ADDR_ENCODE(addr);
+
+ if (level != I915_CACHE_NONE)
+ pte |= HSW_WB_ELLC_LLC_AGE0;
+
+ return pte;
+}
+
static void gen6_write_pdes(struct i915_hw_ppgtt *ppgtt)
{
struct drm_i915_private *dev_priv = ppgtt->dev->dev_private;
@@ -861,7 +874,9 @@
} else {
gtt->gtt_probe = gen6_gmch_probe;
gtt->gtt_remove = gen6_gmch_remove;
- if (IS_HASWELL(dev))
+ if (IS_HASWELL(dev) && dev_priv->ellc_size)
+ gtt->pte_encode = iris_pte_encode;
+ else if (IS_HASWELL(dev))
gtt->pte_encode = hsw_pte_encode;
else if (IS_VALLEYVIEW(dev))
gtt->pte_encode = byt_pte_encode;