[Intel-gfx] [PATCH v6 28/32] drm/i915/bdw: Generalize PTE writing for GEN8 PPGTT

[Michel Thierry]

From: Ben Widawsky <benjamin.widawsky at intel.com>

The insert_entries function was the function used to write PTEs. For the
PPGTT it was "hardcoded" to only understand two level page tables, which
was the case for GEN7. We can reuse this for 4 level page tables, and
remove the concept of insert_entries, which was never viable past 2
level page tables anyway, but it requires a bit of rework to make the
function a bit more generic.

This patch begins the generalization work, and it will be heavily used
upon when the 48b code is complete. The patch series attempts to make
each function which touches a part of code specific to the page table
level and here is no exception. Having extra variables (such as the
PPGTT) distracts and provides room to add bugs since the function
shouldn't be touching anything in the higher order page tables.

Signed-off-by: Ben Widawsky <ben at bwidawsk.net>
Signed-off-by: Michel Thierry <michel.thierry at intel.com>
---
 drivers/gpu/drm/i915/i915_gem_gtt.c | 55 +++++++++++++++++++++++++------------
 1 file changed, 38 insertions(+), 17 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 88a3c49..d5271e3 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -619,23 +619,19 @@ static int gen8_48b_mm_switch(struct i915_hw_ppgtt *ppgtt,
 	return gen8_write_pdp(ring, 0, ppgtt->pml4.daddr);
 }
 
-static void gen8_ppgtt_clear_range(struct i915_address_space *vm,
-				   uint64_t start,
-				   uint64_t length,
-				   bool use_scratch)
+static void gen8_ppgtt_clear_pte_range(struct i915_page_directory_pointer_entry *pdp,
+				       uint64_t start,
+				       uint64_t length,
+				       gen8_gtt_pte_t scratch_pte,
+				       const bool flush)
 {
-	struct i915_hw_ppgtt *ppgtt =
-		container_of(vm, struct i915_hw_ppgtt, base);
-	struct i915_page_directory_pointer_entry *pdp = &ppgtt->pdp; /* FIXME: 48b */
-	gen8_gtt_pte_t *pt_vaddr, scratch_pte;
+	gen8_gtt_pte_t *pt_vaddr;
 	unsigned pdpe = start >> GEN8_PDPE_SHIFT & GEN8_PDPE_MASK;
 	unsigned pde = start >> GEN8_PDE_SHIFT & GEN8_PDE_MASK;
 	unsigned pte = start >> GEN8_PTE_SHIFT & GEN8_PTE_MASK;
 	unsigned num_entries = length >> PAGE_SHIFT;
 	unsigned last_pte, i;
 
-	scratch_pte = gen8_pte_encode(ppgtt->base.scratch.addr,
-				      I915_CACHE_LLC, use_scratch);
 
 	while (num_entries) {
 		struct i915_page_directory_entry *pd;
@@ -668,7 +664,7 @@ static void gen8_ppgtt_clear_range(struct i915_address_space *vm,
 			num_entries--;
 		}
 
-		if (!HAS_LLC(ppgtt->base.dev))
+		if (flush)
 			drm_clflush_virt_range(pt_vaddr, PAGE_SIZE);
 		kunmap_atomic(pt_vaddr);
 
@@ -680,14 +676,27 @@ static void gen8_ppgtt_clear_range(struct i915_address_space *vm,
 	}
 }
 
-static void gen8_ppgtt_insert_entries(struct i915_address_space *vm,
-				      struct sg_table *pages,
-				      uint64_t start,
-				      enum i915_cache_level cache_level, u32 unused)
+static void gen8_ppgtt_clear_range(struct i915_address_space *vm,
+				   uint64_t start,
+				   uint64_t length,
+				   bool use_scratch)
 {
 	struct i915_hw_ppgtt *ppgtt =
 		container_of(vm, struct i915_hw_ppgtt, base);
 	struct i915_page_directory_pointer_entry *pdp = &ppgtt->pdp; /* FIXME: 48b */
+
+	gen8_gtt_pte_t scratch_pte = gen8_pte_encode(ppgtt->base.scratch.addr,
+						     I915_CACHE_LLC, use_scratch);
+
+	gen8_ppgtt_clear_pte_range(pdp, start, length, scratch_pte, !HAS_LLC(vm->dev));
+}
+
+static void gen8_ppgtt_insert_pte_entries(struct i915_page_directory_pointer_entry *pdp,
+					  struct sg_table *pages,
+					  uint64_t start,
+					  enum i915_cache_level cache_level,
+					  const bool flush)
+{
 	gen8_gtt_pte_t *pt_vaddr;
 	unsigned pdpe = start >> GEN8_PDPE_SHIFT & GEN8_PDPE_MASK;
 	unsigned pde = start >> GEN8_PDE_SHIFT & GEN8_PDE_MASK;
@@ -709,7 +718,7 @@ static void gen8_ppgtt_insert_entries(struct i915_address_space *vm,
 			gen8_pte_encode(sg_page_iter_dma_address(&sg_iter),
 					cache_level, true);
 		if (++pte == GEN8_PTES_PER_PAGE) {
-			if (!HAS_LLC(ppgtt->base.dev))
+			if (flush)
 				drm_clflush_virt_range(pt_vaddr, PAGE_SIZE);
 			kunmap_atomic(pt_vaddr);
 			pt_vaddr = NULL;
@@ -721,12 +730,24 @@ static void gen8_ppgtt_insert_entries(struct i915_address_space *vm,
 		}
 	}
 	if (pt_vaddr) {
-		if (!HAS_LLC(ppgtt->base.dev))
+		if (flush)
 			drm_clflush_virt_range(pt_vaddr, PAGE_SIZE);
 		kunmap_atomic(pt_vaddr);
 	}
 }
 
+static void gen8_ppgtt_insert_entries(struct i915_address_space *vm,
+				      struct sg_table *pages,
+				      uint64_t start,
+				      enum i915_cache_level cache_level,
+				      u32 unused)
+{
+	struct i915_hw_ppgtt *ppgtt = container_of(vm, struct i915_hw_ppgtt, base);
+	struct i915_page_directory_pointer_entry *pdp = &ppgtt->pdp; /* FIXME: 48b */
+
+	gen8_ppgtt_insert_pte_entries(pdp, pages, start, cache_level, !HAS_LLC(vm->dev));
+}
+
 static void __gen8_do_map_pt(gen8_ppgtt_pde_t * const pde,
 			     struct i915_page_table_entry *pt,
 			     struct drm_device *dev)
-- 
2.1.1