[PATCH 20/20] drm/i915/gtt: One instance of scratch page table/directory

[Mika Kuoppala <mika.kuoppala@linux.intel.com>]

As we use one scratch page for all ppgtt instances, we can
use one scratch page table and scratch directory across
all ppgtt instances, saving 2 pages + structs per ppgtt.

Signed-off-by: Mika Kuoppala <mika.kuoppala@intel.com>
---
 drivers/gpu/drm/i915/i915_gem_gtt.c | 288 +++++++++++++++++++++++-------------
 1 file changed, 184 insertions(+), 104 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 6910996..6706081 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -349,7 +349,10 @@ static void kunmap_page_dma(struct drm_device *dev, void *vaddr, bool dirty)
 }
 
 #define kmap_px(px) kmap_page_dma(px_base(px))
-#define kunmap_px(ppgtt, vaddr) kunmap_page_dma((ppgtt)->base.dev, (vaddr), true);
+#define kunmap_px(ppgtt, vaddr) \
+	kunmap_page_dma((ppgtt)->base.dev, (vaddr), true)
+#define kunmap_readonly_px(ppgtt, vaddr) \
+	kunmap_page_dma((ppgtt)->base.dev, (vaddr), false)
 
 #define setup_px(dev, px) setup_page_dma((dev), px_base(px))
 #define cleanup_px(dev, px) cleanup_page_dma((dev), px_base(px))
@@ -403,16 +406,6 @@ static void free_pt(struct drm_device *dev, struct i915_page_table *pt)
 	kfree(pt);
 }
 
-static void gen8_setup_scratch_pt(struct i915_address_space *vm)
-{
-	gen8_pte_t scratch_pte;
-
-	scratch_pte = gen8_pte_encode(px_dma(vm->scratch_page),
-				      I915_CACHE_LLC, true);
-
-	fill_px(vm->dev, vm->scratch_pt, scratch_pte);
-}
-
 static struct i915_page_table *alloc_pt(struct drm_device *dev)
 {
 	struct i915_page_table *pt;
@@ -481,6 +474,175 @@ free_pd:
 	return ERR_PTR(ret);
 }
 
+static int alloc_scratch_page(struct i915_address_space *vm)
+{
+	struct i915_page_scratch *sp;
+	int ret;
+
+	WARN_ON(vm->scratch_page);
+
+	sp = kzalloc(sizeof(*sp), GFP_KERNEL);
+	if (sp == NULL)
+		return -ENOMEM;
+
+	ret = __setup_page_dma(vm->dev, px_base(sp), GFP_DMA32);
+	if (ret) {
+		kfree(sp);
+		return ret;
+	}
+
+	fill_px(vm->dev, sp, ~0ULL);
+	set_pages_uc(px_page(sp), 1);
+
+	vm->scratch_page = sp;
+
+	return 0;
+}
+
+static void free_scratch_page(struct i915_address_space *vm)
+{
+	struct i915_page_scratch *sp = vm->scratch_page;
+
+	set_pages_wb(px_page(sp), 1);
+
+	cleanup_px(vm->dev, sp);
+	kfree(sp);
+
+	vm->scratch_page = NULL;
+}
+
+static void gen6_setup_scratch_pt(struct i915_address_space *vm)
+{
+	gen6_pte_t scratch_pte;
+
+	WARN_ON(px_dma(vm->scratch_page) == 0);
+
+	scratch_pte = vm->pte_encode(px_dma(vm->scratch_page),
+				     I915_CACHE_LLC, true, 0);
+
+	fill32_px(vm->dev, vm->scratch_pt, scratch_pte);
+}
+
+static void gen8_setup_scratch_pt(struct i915_address_space *vm)
+{
+	gen8_pte_t scratch_pte;
+
+	WARN_ON(px_dma(vm->scratch_page) == 0);
+
+	scratch_pte = gen8_pte_encode(px_dma(vm->scratch_page),
+				      I915_CACHE_LLC, true);
+
+	fill_px(vm->dev, vm->scratch_pt, scratch_pte);
+}
+
+static void gen8_setup_scratch_pd(struct i915_address_space *vm)
+{
+	gen8_pde_t scratch_pde;
+
+	WARN_ON(px_dma(vm->scratch_pt) == 0);
+
+	scratch_pde = gen8_pde_encode(px_dma(vm->scratch_pt), I915_CACHE_LLC);
+
+	fill_px(vm->dev, vm->scratch_pd, scratch_pde);
+}
+
+static int setup_scratch_ggtt(struct i915_address_space *vm)
+{
+	int ret;
+
+	ret = alloc_scratch_page(vm);
+	if (ret)
+		return ret;
+
+	WARN_ON(vm->scratch_pt);
+
+	if (INTEL_INFO(vm->dev)->gen < 6)
+		return 0;
+
+	vm->scratch_pt = alloc_pt(vm->dev);
+	if (IS_ERR(vm->scratch_pt))
+		return PTR_ERR(vm->scratch_pt);
+
+	if (INTEL_INFO(vm->dev)->gen >= 8) {
+		gen8_setup_scratch_pt(vm);
+
+		WARN_ON(vm->scratch_pd);
+
+		vm->scratch_pd = alloc_pd(vm->dev);
+		if (IS_ERR(vm->scratch_pd)) {
+			ret = PTR_ERR(vm->scratch_pd);
+			goto err_pd;
+		}
+
+		gen8_setup_scratch_pd(vm);
+	} else {
+		gen6_setup_scratch_pt(vm);
+	}
+
+	return 0;
+
+err_pd:
+	free_pt(vm->dev, vm->scratch_pt);
+	return ret;
+}
+
+static int setup_scratch(struct i915_address_space *vm)
+{
+	struct i915_address_space *ggtt_vm = &to_i915(vm->dev)->gtt.base;
+
+	if (i915_is_ggtt(vm))
+		return setup_scratch_ggtt(vm);
+
+	vm->scratch_page = ggtt_vm->scratch_page;
+	vm->scratch_pt = ggtt_vm->scratch_pt;
+	vm->scratch_pd = ggtt_vm->scratch_pd;
+
+	return 0;
+}
+
+static void check_scratch_page(struct i915_address_space *vm)
+{
+	struct i915_hw_ppgtt *ppgtt =
+		container_of(vm, struct i915_hw_ppgtt, base);
+	u32 i, *vaddr;
+
+	vaddr = kmap_px(vm->scratch_page);
+
+	for (i = 0; i < PAGE_SIZE / sizeof(u32); i++) {
+		if (vaddr[i] == 0xffffffff)
+			continue;
+
+		DRM_ERROR("%p scratch[%u] = 0x%08x\n", vm, i, vaddr[i]);
+		break;
+	}
+
+	kunmap_readonly_px(ppgtt, vaddr);
+}
+
+static void cleanup_scratch_ggtt(struct i915_address_space *vm)
+{
+	check_scratch_page(vm);
+	free_scratch_page(vm);
+
+	if (INTEL_INFO(vm->dev)->gen < 6)
+		return;
+
+	free_pt(vm->dev, vm->scratch_pt);
+
+	if (INTEL_INFO(vm->dev)->gen >= 8)
+		free_pd(vm->dev, vm->scratch_pd);
+}
+
+static void cleanup_scratch(struct i915_address_space *vm)
+{
+	if (i915_is_ggtt(vm))
+		cleanup_scratch_ggtt(vm);
+
+	vm->scratch_page = NULL;
+	vm->scratch_pt = NULL;
+	vm->scratch_pd = NULL;
+}
+
 /* Broadwell Page Directory Pointer Descriptors */
 static int gen8_write_pdp(struct intel_engine_cs *ring,
 			  unsigned entry,
@@ -535,7 +697,7 @@ static void gen8_ppgtt_clear_range(struct i915_address_space *vm,
 	unsigned num_entries = length >> PAGE_SHIFT;
 	unsigned last_pte, i;
 
-	scratch_pte = gen8_pte_encode(px_dma(ppgtt->base.scratch_page),
+	scratch_pte = gen8_pte_encode(px_dma(vm->scratch_page),
 				      I915_CACHE_LLC, use_scratch);
 
 	while (num_entries) {
@@ -619,15 +781,6 @@ static void gen8_ppgtt_insert_entries(struct i915_address_space *vm,
 		kunmap_px(ppgtt, pt_vaddr);
 }
 
-static void gen8_setup_scratch_pd(struct i915_address_space *vm)
-{
-	gen8_pde_t scratch_pde;
-
-	scratch_pde = gen8_pde_encode(px_dma(vm->scratch_pt), I915_CACHE_LLC);
-
-	fill_px(vm->dev, vm->scratch_pd, scratch_pde);
-}
-
 static void gen8_free_page_tables(struct i915_page_directory *pd, struct drm_device *dev)
 {
 	int i;
@@ -658,8 +811,7 @@ static void gen8_ppgtt_cleanup(struct i915_address_space *vm)
 		free_pd(ppgtt->base.dev, ppgtt->pdp.page_directory[i]);
 	}
 
-	free_pd(vm->dev, vm->scratch_pd);
-	free_pt(vm->dev, vm->scratch_pt);
+	cleanup_scratch(vm);
 }
 
 /**
@@ -947,17 +1099,6 @@ err_out:
  */
 static int gen8_ppgtt_init(struct i915_hw_ppgtt *ppgtt)
 {
-	ppgtt->base.scratch_pt = alloc_pt(ppgtt->base.dev);
-	if (IS_ERR(ppgtt->base.scratch_pt))
-		return PTR_ERR(ppgtt->base.scratch_pt);
-
-	ppgtt->base.scratch_pd = alloc_pd(ppgtt->base.dev);
-	if (IS_ERR(ppgtt->base.scratch_pd))
-		return PTR_ERR(ppgtt->base.scratch_pd);
-
-	gen8_setup_scratch_pt(&ppgtt->base);
-	gen8_setup_scratch_pd(&ppgtt->base);
-
 	ppgtt->base.start = 0;
 	ppgtt->base.total = 1ULL << 32;
 	ppgtt->base.cleanup = gen8_ppgtt_cleanup;
@@ -969,7 +1110,7 @@ static int gen8_ppgtt_init(struct i915_hw_ppgtt *ppgtt)
 
 	ppgtt->switch_mm = gen8_mm_switch;
 
-	return 0;
+	return setup_scratch(&ppgtt->base);
 }
 
 static void gen6_dump_ppgtt(struct i915_hw_ppgtt *ppgtt, struct seq_file *m)
@@ -1021,7 +1162,7 @@ static void gen6_dump_ppgtt(struct i915_hw_ppgtt *ppgtt, struct seq_file *m)
 			}
 			seq_puts(m, "\n");
 		}
-		kunmap_px(ppgtt, pt_vaddr);
+		kunmap_readonly_px(ppgtt, pt_vaddr);
 	}
 }
 
@@ -1271,18 +1412,6 @@ static void gen6_ppgtt_insert_entries(struct i915_address_space *vm,
 		kunmap_px(ppgtt, pt_vaddr);
 }
 
-static void gen6_setup_scratch_pt(struct i915_address_space *vm)
-{
-	gen6_pte_t scratch_pte;
-
-	WARN_ON(px_dma(vm->scratch_page) == 0);
-
-	scratch_pte = vm->pte_encode(px_dma(vm->scratch_page),
-				     I915_CACHE_LLC, true, 0);
-
-	fill32_px(vm->dev, vm->scratch_pt, scratch_pte);
-}
-
 static int gen6_alloc_va_range(struct i915_address_space *vm,
 			       uint64_t start_in, uint64_t length_in)
 {
@@ -1387,7 +1516,7 @@ static void gen6_ppgtt_cleanup(struct i915_address_space *vm)
 			free_pt(ppgtt->base.dev, pt);
 	}
 
-	free_pt(vm->dev, vm->scratch_pt);
+	cleanup_scratch(vm);
 }
 
 static int gen6_ppgtt_allocate_page_directories(struct i915_hw_ppgtt *ppgtt)
@@ -1402,11 +1531,10 @@ static int gen6_ppgtt_allocate_page_directories(struct i915_hw_ppgtt *ppgtt)
 	 * size. We allocate at the top of the GTT to avoid fragmentation.
 	 */
 	BUG_ON(!drm_mm_initialized(&dev_priv->gtt.base.mm));
-	ppgtt->base.scratch_pt = alloc_pt(ppgtt->base.dev);
-	if (IS_ERR(ppgtt->base.scratch_pt))
-		return PTR_ERR(ppgtt->base.scratch_pt);
 
-	gen6_setup_scratch_pt(&ppgtt->base);
+	ret = setup_scratch(&ppgtt->base);
+	if (ret)
+		return ret;
 
 alloc:
 	ret = drm_mm_insert_node_in_range_generic(&dev_priv->gtt.base.mm,
@@ -1437,7 +1565,7 @@ alloc:
 	return 0;
 
 err_out:
-	free_pt(ppgtt->base.dev, ppgtt->base.scratch_pt);
+	cleanup_scratch(&ppgtt->base);
 	return ret;
 }
 
@@ -1511,10 +1639,7 @@ static int gen6_ppgtt_init(struct i915_hw_ppgtt *ppgtt)
 
 static int __hw_ppgtt_init(struct drm_device *dev, struct i915_hw_ppgtt *ppgtt)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
-
 	ppgtt->base.dev = dev;
-	ppgtt->base.scratch_page = dev_priv->gtt.base.scratch_page;
 
 	if (INTEL_INFO(dev)->gen < 8)
 		return gen6_ppgtt_init(ppgtt);
@@ -2120,43 +2245,6 @@ void i915_global_gtt_cleanup(struct drm_device *dev)
 	vm->cleanup(vm);
 }
 
-static int alloc_scratch_page(struct i915_address_space *vm)
-{
-	struct i915_page_scratch *sp;
-	int ret;
-
-	WARN_ON(vm->scratch_page);
-
-	sp = kzalloc(sizeof(*sp), GFP_KERNEL);
-	if (sp == NULL)
-		return -ENOMEM;
-
-	ret = __setup_page_dma(vm->dev, px_base(sp), GFP_DMA32 | __GFP_ZERO);
-	if (ret) {
-		kfree(sp);
-		return ret;
-	}
-
-	fill_px(vm->dev, sp, ~0ULL);
-	set_pages_uc(px_page(sp), 1);
-
-	vm->scratch_page = sp;
-
-	return 0;
-}
-
-static void free_scratch_page(struct i915_address_space *vm)
-{
-	struct i915_page_scratch *sp = vm->scratch_page;
-
-	set_pages_wb(px_page(sp), 1);
-
-	cleanup_px(vm->dev, sp);
-	kfree(sp);
-
-	vm->scratch_page = NULL;
-}
-
 static unsigned int gen6_get_total_gtt_size(u16 snb_gmch_ctl)
 {
 	snb_gmch_ctl >>= SNB_GMCH_GGMS_SHIFT;
@@ -2240,7 +2328,6 @@ static int ggtt_probe_common(struct drm_device *dev,
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	phys_addr_t gtt_phys_addr;
-	int ret;
 
 	/* For Modern GENs the PTEs and register space are split in the BAR */
 	gtt_phys_addr = pci_resource_start(dev->pdev, 0) +
@@ -2262,14 +2349,7 @@ static int ggtt_probe_common(struct drm_device *dev,
 		return -ENOMEM;
 	}
 
-	ret = alloc_scratch_page(&dev_priv->gtt.base);
-	if (ret) {
-		DRM_ERROR("Scratch setup failed\n");
-		/* iounmap will also get called at remove, but meh */
-		iounmap(dev_priv->gtt.gsm);
-	}
-
-	return ret;
+	return setup_scratch(&dev_priv->gtt.base);
 }
 
 /* The GGTT and PPGTT need a private PPAT setup in order to handle cacheability
@@ -2441,7 +2521,7 @@ static void gen6_gmch_remove(struct i915_address_space *vm)
 	struct i915_gtt *gtt = container_of(vm, struct i915_gtt, base);
 
 	iounmap(gtt->gsm);
-	free_scratch_page(vm);
+	cleanup_scratch(vm);
 }
 
 static int i915_gmch_probe(struct drm_device *dev,
-- 
1.9.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx