[Intel-gfx] [PATCH 03/16] drm/i915/gen8: Abstract PDP usage

Michel Thierry michel.thierry at intel.com
Tue May 26 07:21:10 PDT 2015


Up until now, ppgtt->pdp has always been the root of our page tables.
Legacy 32b addresses acted like it had 1 PDP with 4 PDPEs.

In preparation for 4 level page tables, we need to stop use ppgtt->pdp
directly unless we know it's what we want. The future structure will use
ppgtt->pml4 for the top level, and the pdp is just one of the entries
being pointed to by a pml4e.

v2: Updated after dynamic page allocation changes.
v3: Rebase after s/page_tables/page_table/.
v4: Rebase after changes in "Dynamic page table allocations" patch.

Signed-off-by: Ben Widawsky <ben at bwidawsk.net>
Signed-off-by: Michel Thierry <michel.thierry at intel.com> (v2+)
---
 drivers/gpu/drm/i915/i915_gem_gtt.c | 141 +++++++++++++++++++++++-------------
 1 file changed, 90 insertions(+), 51 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index a288f6b..a950f26 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -550,6 +550,7 @@ static void gen8_ppgtt_clear_range(struct i915_address_space *vm,
 {
 	struct i915_hw_ppgtt *ppgtt =
 		container_of(vm, struct i915_hw_ppgtt, base);
+	struct i915_page_directory_pointer *pdp = &ppgtt->pdp; /* FIXME: 48b */
 	gen8_pte_t *pt_vaddr, scratch_pte;
 	unsigned pdpe = start >> GEN8_PDPE_SHIFT & GEN8_PDPE_MASK;
 	unsigned pde = start >> GEN8_PDE_SHIFT & GEN8_PDE_MASK;
@@ -565,10 +566,10 @@ static void gen8_ppgtt_clear_range(struct i915_address_space *vm,
 		struct i915_page_table *pt;
 		struct page *page_table;
 
-		if (WARN_ON(!ppgtt->pdp.page_directory[pdpe]))
+		if (WARN_ON(!pdp->page_directory[pdpe]))
 			continue;
 
-		pd = ppgtt->pdp.page_directory[pdpe];
+		pd = pdp->page_directory[pdpe];
 
 		if (WARN_ON(!pd->page_table[pde]))
 			continue;
@@ -610,6 +611,7 @@ static void gen8_ppgtt_insert_entries(struct i915_address_space *vm,
 {
 	struct i915_hw_ppgtt *ppgtt =
 		container_of(vm, struct i915_hw_ppgtt, base);
+	struct i915_page_directory_pointer *pdp = &ppgtt->pdp; /* FIXME: 48b */
 	gen8_pte_t *pt_vaddr;
 	unsigned pdpe = start >> GEN8_PDPE_SHIFT & GEN8_PDPE_MASK;
 	unsigned pde = start >> GEN8_PDE_SHIFT & GEN8_PDE_MASK;
@@ -620,7 +622,7 @@ static void gen8_ppgtt_insert_entries(struct i915_address_space *vm,
 
 	for_each_sg_page(pages->sgl, &sg_iter, pages->nents, 0) {
 		if (pt_vaddr == NULL) {
-			struct i915_page_directory *pd = ppgtt->pdp.page_directory[pdpe];
+			struct i915_page_directory *pd = pdp->page_directory[pdpe];
 			struct i915_page_table *pt = pd->page_table[pde];
 			struct page *page_table = pt->page;
 
@@ -675,6 +677,28 @@ static void gen8_initialize_pd(struct i915_address_space *vm,
 
 	if (!HAS_LLC(vm->dev))
 		drm_clflush_virt_range(page_directory, PAGE_SIZE);
+
+	kunmap_atomic(page_directory);
+}
+
+/* It's likely we'll map more than one pagetable at a time. This function will
+ * save us unnecessary kmap calls, but do no more functionally than multiple
+ * calls to map_pt. */
+static void gen8_map_pagetable_range(struct i915_page_directory *pd,
+				     uint64_t start,
+				     uint64_t length,
+				     struct drm_device *dev)
+{
+	gen8_pde_t * const page_directory = kmap_atomic(pd->page);
+	struct i915_page_table *pt;
+	uint64_t temp, pde;
+
+	gen8_for_each_pde(pt, pd, start, length, temp, pde)
+		__gen8_do_map_pt(page_directory + pde, pt, dev);
+
+	if (!HAS_LLC(dev))
+		drm_clflush_virt_range(page_directory, PAGE_SIZE);
+
 	kunmap_atomic(page_directory);
 }
 
@@ -700,23 +724,29 @@ static void gen8_ppgtt_cleanup(struct i915_address_space *vm)
 		container_of(vm, struct i915_hw_ppgtt, base);
 	int i;
 
-	for_each_set_bit(i, ppgtt->pdp.used_pdpes,
-				I915_PDPES_PER_PDP(ppgtt->base.dev)) {
-		if (WARN_ON(!ppgtt->pdp.page_directory[i]))
-			continue;
+	if (!USES_FULL_48BIT_PPGTT(ppgtt->base.dev)) {
+		for_each_set_bit(i, ppgtt->pdp.used_pdpes,
+				 I915_PDPES_PER_PDP(ppgtt->base.dev)) {
+			if (WARN_ON(!ppgtt->pdp.page_directory[i]))
+				continue;
 
-		gen8_free_page_tables(ppgtt->pdp.page_directory[i], ppgtt->base.dev);
-		unmap_and_free_pd(ppgtt->pdp.page_directory[i], ppgtt->base.dev);
+			gen8_free_page_tables(ppgtt->pdp.page_directory[i],
+					      ppgtt->base.dev);
+			unmap_and_free_pd(ppgtt->pdp.page_directory[i],
+					  ppgtt->base.dev);
+		}
+		unmap_and_free_pdp(&ppgtt->pdp, ppgtt->base.dev);
+	} else {
+		WARN_ON(1); /* to be implemented later */
 	}
 
-	unmap_and_free_pdp(&ppgtt->pdp, ppgtt->base.dev);
 	unmap_and_free_pd(ppgtt->scratch_pd, ppgtt->base.dev);
 	unmap_and_free_pt(ppgtt->scratch_pt, ppgtt->base.dev);
 }
 
 /**
  * gen8_ppgtt_alloc_pagetabs() - Allocate page tables for VA range.
- * @ppgtt:	Master ppgtt structure.
+ * @vm:		Master vm structure.
  * @pd:		Page directory for this address range.
  * @start:	Starting virtual address to begin allocations.
  * @length	Size of the allocations.
@@ -732,13 +762,15 @@ static void gen8_ppgtt_cleanup(struct i915_address_space *vm)
  *
  * Return: 0 if success; negative error code otherwise.
  */
-static int gen8_ppgtt_alloc_pagetabs(struct i915_hw_ppgtt *ppgtt,
+static int gen8_ppgtt_alloc_pagetabs(struct i915_address_space *vm,
 				     struct i915_page_directory *pd,
 				     uint64_t start,
 				     uint64_t length,
 				     unsigned long *new_pts)
 {
-	struct drm_device *dev = ppgtt->base.dev;
+	struct i915_hw_ppgtt *ppgtt =
+	    container_of(vm, struct i915_hw_ppgtt, base);
+	struct drm_device *dev = vm->dev;
 	struct i915_page_table *pt;
 	uint64_t temp;
 	uint32_t pde;
@@ -755,7 +787,7 @@ static int gen8_ppgtt_alloc_pagetabs(struct i915_hw_ppgtt *ppgtt,
 		if (IS_ERR(pt))
 			goto unwind_out;
 
-		gen8_initialize_pt(&ppgtt->base, pt);
+		gen8_initialize_pt(vm, pt);
 		pd->page_table[pde] = pt;
 		set_bit(pde, new_pts);
 	}
@@ -771,7 +803,7 @@ unwind_out:
 
 /**
  * gen8_ppgtt_alloc_page_directories() - Allocate page directories for VA range.
- * @ppgtt:	Master ppgtt structure.
+ * @vm:		Master vm structure.
  * @pdp:	Page directory pointer for this address range.
  * @start:	Starting virtual address to begin allocations.
  * @length	Size of the allocations.
@@ -792,17 +824,18 @@ unwind_out:
  *
  * Return: 0 if success; negative error code otherwise.
  */
-static int gen8_ppgtt_alloc_page_directories(struct i915_hw_ppgtt *ppgtt,
-				     struct i915_page_directory_pointer *pdp,
-				     uint64_t start,
-				     uint64_t length,
-				     unsigned long *new_pds)
+static int
+gen8_ppgtt_alloc_page_directories(struct i915_address_space *vm,
+				  struct i915_page_directory_pointer *pdp,
+				  uint64_t start,
+				  uint64_t length,
+				  unsigned long *new_pds)
 {
-	struct drm_device *dev = ppgtt->base.dev;
+	struct drm_device *dev = vm->dev;
 	struct i915_page_directory *pd;
 	uint64_t temp;
 	uint32_t pdpe;
-	size_t pdpes =  I915_PDPES_PER_PDP(ppgtt->base.dev);
+	size_t pdpes =  I915_PDPES_PER_PDP(vm->dev);
 
 	WARN_ON(!bitmap_empty(new_pds, pdpes));
 
@@ -817,7 +850,7 @@ static int gen8_ppgtt_alloc_page_directories(struct i915_hw_ppgtt *ppgtt,
 		if (IS_ERR(pd))
 			goto unwind_out;
 
-		gen8_initialize_pd(&ppgtt->base, pd);
+		gen8_initialize_pd(vm, pd);
 		pdp->page_directory[pdpe] = pd;
 		set_bit(pdpe, new_pds);
 	}
@@ -882,13 +915,13 @@ err_out:
 	return -ENOMEM;
 }
 
-static int gen8_alloc_va_range(struct i915_address_space *vm,
-			       uint64_t start,
-			       uint64_t length)
+static int gen8_alloc_va_range_3lvl(struct i915_address_space *vm,
+				    struct i915_page_directory_pointer *pdp,
+				    uint64_t start,
+				    uint64_t length)
 {
-	struct i915_hw_ppgtt *ppgtt =
-		container_of(vm, struct i915_hw_ppgtt, base);
 	unsigned long *new_page_dirs, **new_page_tables;
+	struct drm_device *dev = vm->dev;
 	struct i915_page_directory *pd;
 	const uint64_t orig_start = start;
 	const uint64_t orig_length = length;
@@ -908,16 +941,14 @@ static int gen8_alloc_va_range(struct i915_address_space *vm,
 		return ret;
 
 	/* Do the allocations first so we can easily bail out */
-	ret = gen8_ppgtt_alloc_page_directories(ppgtt, &ppgtt->pdp, start, length,
-					new_page_dirs);
+	ret = gen8_ppgtt_alloc_page_directories(vm, pdp, start, length, new_page_dirs);
 	if (ret) {
 		free_gen8_temp_bitmaps(new_page_dirs, new_page_tables, pdpes);
 		return ret;
 	}
 
-	/* For every page directory referenced, allocate page tables */
-	gen8_for_each_pdpe(pd, &ppgtt->pdp, start, length, temp, pdpe) {
-		ret = gen8_ppgtt_alloc_pagetabs(ppgtt, pd, start, length,
+	gen8_for_each_pdpe(pd, pdp, start, length, temp, pdpe) {
+		ret = gen8_ppgtt_alloc_pagetabs(vm, pd, start, length,
 						new_page_tables[pdpe]);
 		if (ret)
 			goto err_out;
@@ -926,10 +957,7 @@ static int gen8_alloc_va_range(struct i915_address_space *vm,
 	start = orig_start;
 	length = orig_length;
 
-	/* Allocations have completed successfully, so set the bitmaps, and do
-	 * the mappings. */
-	gen8_for_each_pdpe(pd, &ppgtt->pdp, start, length, temp, pdpe) {
-		gen8_pde_t *const page_directory = kmap_atomic(pd->page);
+	gen8_for_each_pdpe(pd, pdp, start, length, temp, pdpe) {
 		struct i915_page_table *pt;
 		uint64_t pd_len = length;
 		uint64_t pd_start = start;
@@ -951,20 +979,10 @@ static int gen8_alloc_va_range(struct i915_address_space *vm,
 
 			/* Our pde is now pointing to the pagetable, pt */
 			set_bit(pde, pd->used_pdes);
-
-			/* Map the PDE to the page table */
-			__gen8_do_map_pt(page_directory + pde, pt, vm->dev);
-
-			/* NB: We haven't yet mapped ptes to pages. At this
-			 * point we're still relying on insert_entries() */
 		}
 
-		if (!HAS_LLC(vm->dev))
-			drm_clflush_virt_range(page_directory, PAGE_SIZE);
-
-		kunmap_atomic(page_directory);
-
-		set_bit(pdpe, ppgtt->pdp.used_pdpes);
+		set_bit(pdpe, pdp->used_pdpes);
+		gen8_map_pagetable_range(pd, start, length, dev);
 	}
 
 	free_gen8_temp_bitmaps(new_page_dirs, new_page_tables, pdpes);
@@ -973,16 +991,37 @@ static int gen8_alloc_va_range(struct i915_address_space *vm,
 err_out:
 	while (pdpe--) {
 		for_each_set_bit(temp, new_page_tables[pdpe], I915_PDES)
-			unmap_and_free_pt(ppgtt->pdp.page_directory[pdpe]->page_table[temp], vm->dev);
+			unmap_and_free_pt(pdp->page_directory[pdpe]->page_table[temp], dev);
 	}
 
 	for_each_set_bit(pdpe, new_page_dirs, pdpes)
-		unmap_and_free_pd(ppgtt->pdp.page_directory[pdpe], vm->dev);
+		unmap_and_free_pd(pdp->page_directory[pdpe], dev);
 
 	free_gen8_temp_bitmaps(new_page_dirs, new_page_tables, pdpes);
 	return ret;
 }
 
+static int gen8_alloc_va_range_4lvl(struct i915_address_space *vm,
+				    struct i915_pml4 *pml4,
+				    uint64_t start,
+				    uint64_t length)
+{
+	WARN_ON(1); /* to be implemented later */
+	return 0;
+}
+
+static int gen8_alloc_va_range(struct i915_address_space *vm,
+			       uint64_t start, uint64_t length)
+{
+	struct i915_hw_ppgtt *ppgtt =
+		container_of(vm, struct i915_hw_ppgtt, base);
+
+	if (!USES_FULL_48BIT_PPGTT(vm->dev))
+		return gen8_alloc_va_range_3lvl(vm, &ppgtt->pdp, start, length);
+	else
+		return gen8_alloc_va_range_4lvl(vm, &ppgtt->pml4, start, length);
+}
+
 /*
  * GEN8 legacy ppgtt programming is accomplished through a max 4 PDP registers
  * with a net effect resembling a 2-level page table in normal x86 terms. Each
-- 
2.4.0



More information about the Intel-gfx mailing list