[Intel-gfx] [PATCH 05/17] drm/i915/gtt: Invalidate GGTT caches after writing the gen6 page directories

[Chris Wilson]

When we update the gen6 ppgtt page directories, we do so by writing the
new address into a reserved slot in the GGTT. It appears that when the
GPU reads that entry from the gsm, it uses its small cache and that we
need to invalidate that cache after writing. We don't see an issue
currently as we prefill the ppgtt page directories on creation; and only
create the single aliasing_ppgtt long before we start using the GGTT
(and so before the cache mayhave a conflicting entry).

Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen at linux.intel.com>
Cc: Mika Kuoppala <mika.kuoppala at linux.intel.com>
Cc: Matthew Auld <matthew.william.auld at gmail.com>
---
 drivers/gpu/drm/i915/i915_gem_gtt.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 9966845a7f22..63569bd71fef 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -1693,8 +1693,8 @@ static inline void gen6_write_pde(const struct i915_hw_ppgtt *ppgtt,
 				  const struct i915_page_table *pt)
 {
 	/* Caller needs to make sure the write completes if necessary */
-	writel_relaxed(GEN6_PDE_ADDR_ENCODE(px_dma(pt)) | GEN6_PDE_VALID,
-		       ppgtt->pd_addr + pde);
+	iowrite32(GEN6_PDE_ADDR_ENCODE(px_dma(pt)) | GEN6_PDE_VALID,
+		  ppgtt->pd_addr + pde);
 }
 
 /* Write all the page tables found in the ppgtt structure to incrementing page
@@ -1709,7 +1709,7 @@ static void gen6_write_page_range(struct i915_hw_ppgtt *ppgtt,
 		gen6_write_pde(ppgtt, pde, pt);
 
 	mark_tlbs_dirty(ppgtt);
-	wmb();
+	gen6_ggtt_invalidate(ppgtt->vm.i915);
 }
 
 static void gen8_ppgtt_enable(struct drm_i915_private *dev_priv)
@@ -1864,7 +1864,7 @@ static int gen6_alloc_va_range(struct i915_address_space *vm,
 
 	if (flush) {
 		mark_tlbs_dirty(ppgtt);
-		wmb();
+		gen6_ggtt_invalidate(ppgtt->vm.i915);
 	}
 
 	return 0;
-- 
2.17.1