[Intel-gfx] [PATCH 13/18] drm/i915/gtt: Cache the PTE encoding of the scratch page

[Chris Wilson]

As the most frequent PTE encoding is for the scratch page, cache it upon
creation.

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>
Reviewed-by: Matthew Auld <matthew.william.auld at gmail.com>
---
 drivers/gpu/drm/i915/i915_gem_gtt.c | 20 ++++++++++----------
 drivers/gpu/drm/i915/i915_gem_gtt.h |  1 +
 2 files changed, 11 insertions(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 79d63e16c2d4..58fd2ea77d00 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -640,11 +640,10 @@ static void gen8_initialize_pt(struct i915_address_space *vm,
 		gen8_pte_encode(vm->scratch_page.daddr, I915_CACHE_LLC));
 }
 
-static void gen6_initialize_pt(struct i915_address_space *vm,
+static void gen6_initialize_pt(struct gen6_hw_ppgtt *ppgtt,
 			       struct i915_page_table *pt)
 {
-	fill32_px(vm, pt,
-		  vm->pte_encode(vm->scratch_page.daddr, I915_CACHE_LLC, 0));
+	fill32_px(&ppgtt->base.vm, pt, ppgtt->scratch_pte);
 }
 
 static struct i915_page_directory *alloc_pd(struct i915_address_space *vm)
@@ -1631,9 +1630,7 @@ static struct i915_hw_ppgtt *gen8_ppgtt_create(struct drm_i915_private *i915)
 static void gen6_dump_ppgtt(struct i915_hw_ppgtt *base, struct seq_file *m)
 {
 	struct gen6_hw_ppgtt *ppgtt = to_gen6_ppgtt(base);
-	struct i915_address_space *vm = &base->vm;
-	const gen6_pte_t scratch_pte =
-		vm->pte_encode(vm->scratch_page.daddr, I915_CACHE_LLC, 0);
+	const gen6_pte_t scratch_pte = ppgtt->scratch_pte;
 	struct i915_page_table *pt;
 	u32 pte, pde;
 
@@ -1819,8 +1816,7 @@ static void gen6_ppgtt_clear_range(struct i915_address_space *vm,
 	unsigned int pde = first_entry / GEN6_PTES;
 	unsigned int pte = first_entry % GEN6_PTES;
 	unsigned int num_entries = length >> PAGE_SHIFT;
-	const gen6_pte_t scratch_pte =
-		vm->pte_encode(vm->scratch_page.daddr, I915_CACHE_LLC, 0);
+	const gen6_pte_t scratch_pte = ppgtt->scratch_pte;
 
 	while (num_entries) {
 		struct i915_page_table *pt = ppgtt->base.pd.page_table[pde++];
@@ -1912,7 +1908,7 @@ static int gen6_alloc_va_range(struct i915_address_space *vm,
 				goto unwind_out;
 
 			if (count < GEN6_PTES)
-				gen6_initialize_pt(vm, pt);
+				gen6_initialize_pt(ppgtt, pt);
 			ppgtt->base.pd.page_table[pde] = pt;
 
 			if (i915_vma_is_bound(ppgtt->vma,
@@ -1950,13 +1946,17 @@ static int gen6_ppgtt_init_scratch(struct gen6_hw_ppgtt *ppgtt)
 	if (ret)
 		return ret;
 
+	ppgtt->scratch_pte =
+		vm->pte_encode(vm->scratch_page.daddr,
+			       I915_CACHE_NONE, PTE_READ_ONLY);
+
 	vm->scratch_pt = alloc_pt(vm);
 	if (IS_ERR(vm->scratch_pt)) {
 		cleanup_scratch_page(vm);
 		return PTR_ERR(vm->scratch_pt);
 	}
 
-	gen6_initialize_pt(vm, vm->scratch_pt);
+	gen6_initialize_pt(ppgtt, vm->scratch_pt);
 	gen6_for_all_pdes(unused, &ppgtt->base.pd, pde)
 		ppgtt->base.pd.page_table[pde] = vm->scratch_pt;
 
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.h b/drivers/gpu/drm/i915/i915_gem_gtt.h
index dc98830fae69..c50bbde007f8 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.h
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.h
@@ -412,6 +412,7 @@ struct gen6_hw_ppgtt {
 
 	struct i915_vma *vma;
 	gen6_pte_t __iomem *pd_addr;
+	gen6_pte_t scratch_pte;
 
 	unsigned int pin_count;
 	bool scan_for_unused_pt;
-- 
2.17.1