[Intel-gfx] [PATCH v8 06/19] drm/i915/gen8: Add PML4 structure

[Michel Thierry]

Introduces the Page Map Level 4 (PML4), ie. the new top level structure
of the page tables.

To facilitate testing, 48b mode will be available on Broadwell and
GEN9+, when i915.enable_ppgtt = 3.

v2: Remove unnecessary CONFIG_X86_64 checks, ppgtt code is already
32/64-bit safe (Chris).
v3: Add goto free_scratch in temp 48-bit mode init code (Akash).
v4: kfree the pdp until the 4lvl alloc/free patch (Akash).
v5: Postpone 48-bit code in sanitize_enable_ppgtt (Akash).

Cc: Akash Goel <akash.goel at intel.com>
Signed-off-by: Michel Thierry <michel.thierry at intel.com>
---
 drivers/gpu/drm/i915/i915_drv.h     |  3 ++-
 drivers/gpu/drm/i915/i915_gem_gtt.c | 30 +++++++++++++++++-------------
 drivers/gpu/drm/i915/i915_gem_gtt.h | 26 +++++++++++++++++++++-----
 3 files changed, 40 insertions(+), 19 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 04aa34a..4729eaf 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -2498,7 +2498,8 @@ struct drm_i915_cmd_table {
 #define HAS_HW_CONTEXTS(dev)	(INTEL_INFO(dev)->gen >= 6)
 #define HAS_LOGICAL_RING_CONTEXTS(dev)	(INTEL_INFO(dev)->gen >= 8)
 #define USES_PPGTT(dev)		(i915.enable_ppgtt)
-#define USES_FULL_PPGTT(dev)	(i915.enable_ppgtt == 2)
+#define USES_FULL_PPGTT(dev)	(i915.enable_ppgtt >= 2)
+#define USES_FULL_48BIT_PPGTT(dev)	(i915.enable_ppgtt == 3)
 
 #define HAS_OVERLAY(dev)		(INTEL_INFO(dev)->has_overlay)
 #define OVERLAY_NEEDS_PHYSICAL(dev)	(INTEL_INFO(dev)->overlay_needs_physical)
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 7f71746..ba99b67 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -689,9 +689,6 @@ gen8_ppgtt_insert_pte_entries(struct i915_address_space *vm,
 	pt_vaddr = NULL;
 
 	for_each_sg_page(pages->sgl, &sg_iter, pages->nents, 0) {
-		if (WARN_ON(pdpe >= GEN8_LEGACY_PDPES))
-			break;
-
 		if (pt_vaddr == NULL) {
 			struct i915_page_directory *pd = pdp->page_directory[pdpe];
 			struct i915_page_table *pt = pd->page_table[pde];
@@ -1105,14 +1102,6 @@ static int gen8_ppgtt_init(struct i915_hw_ppgtt *ppgtt)
 		return ret;
 
 	ppgtt->base.start = 0;
-	ppgtt->base.total = 1ULL << 32;
-	if (IS_ENABLED(CONFIG_X86_32))
-		/* While we have a proliferation of size_t variables
-		 * we cannot represent the full ppgtt size on 32bit,
-		 * so limit it to the same size as the GGTT (currently
-		 * 2GiB).
-		 */
-		ppgtt->base.total = to_i915(ppgtt->base.dev)->gtt.base.total;
 	ppgtt->base.cleanup = gen8_ppgtt_cleanup;
 	ppgtt->base.allocate_va_range = gen8_alloc_va_range;
 	ppgtt->base.insert_entries = gen8_ppgtt_insert_entries;
@@ -1122,10 +1111,25 @@ static int gen8_ppgtt_init(struct i915_hw_ppgtt *ppgtt)
 
 	ppgtt->switch_mm = gen8_mm_switch;
 
-	ret = __pdp_init(false, &ppgtt->pdp);
+	if (!USES_FULL_48BIT_PPGTT(ppgtt->base.dev)) {
+		ret = __pdp_init(false, &ppgtt->pdp);
 
-	if (ret)
+		if (ret)
+			goto free_scratch;
+
+		ppgtt->base.total = 1ULL << 32;
+		if (IS_ENABLED(CONFIG_X86_32))
+			/* While we have a proliferation of size_t variables
+			 * we cannot represent the full ppgtt size on 32bit,
+			 * so limit it to the same size as the GGTT (currently
+			 * 2GiB).
+			 */
+			ppgtt->base.total = to_i915(ppgtt->base.dev)->gtt.base.total;
+	} else {
+		ppgtt->base.total = 1ULL << 48;
+		ret = -EPERM; /* Not yet implemented */
 		goto free_scratch;
+	}
 
 	return 0;
 
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.h b/drivers/gpu/drm/i915/i915_gem_gtt.h
index 87e389c..04bc66f 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.h
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.h
@@ -88,9 +88,17 @@ typedef uint64_t gen8_pde_t;
  * PDPE  |  PDE  |  PTE  | offset
  * The difference as compared to normal x86 3 level page table is the PDPEs are
  * programmed via register.
+ *
+ * GEN8 48b legacy style address is defined as a 4 level page table:
+ * 47:39 | 38:30 | 29:21 | 20:12 |  11:0
+ * PML4E | PDPE  |  PDE  |  PTE  | offset
  */
+#define GEN8_PML4ES_PER_PML4		512
+#define GEN8_PML4E_SHIFT		39
 #define GEN8_PDPE_SHIFT			30
-#define GEN8_PDPE_MASK			0x3
+/* NB: GEN8_PDPE_MASK is untrue for 32b platforms, but it has no impact on 32b page
+ * tables */
+#define GEN8_PDPE_MASK			0x1ff
 #define GEN8_PDE_SHIFT			21
 #define GEN8_PDE_MASK			0x1ff
 #define GEN8_PTE_SHIFT			12
@@ -98,8 +106,8 @@ typedef uint64_t gen8_pde_t;
 #define GEN8_LEGACY_PDPES		4
 #define GEN8_PTES			I915_PTES(sizeof(gen8_pte_t))
 
-/* FIXME: Next patch will use dev */
-#define I915_PDPES_PER_PDP(dev)		GEN8_LEGACY_PDPES
+#define I915_PDPES_PER_PDP(dev) (USES_FULL_48BIT_PPGTT(dev) ?\
+				 GEN8_PML4ES_PER_PML4 : GEN8_LEGACY_PDPES)
 
 #define PPAT_UNCACHED_INDEX		(_PAGE_PWT | _PAGE_PCD)
 #define PPAT_CACHED_PDE_INDEX		0 /* WB LLC */
@@ -250,6 +258,13 @@ struct i915_page_directory_pointer {
 	struct i915_page_directory **page_directory;
 };
 
+struct i915_pml4 {
+	struct i915_page_dma base;
+
+	DECLARE_BITMAP(used_pml4es, GEN8_PML4ES_PER_PML4);
+	struct i915_page_directory_pointer *pdps[GEN8_PML4ES_PER_PML4];
+};
+
 struct i915_address_space {
 	struct drm_mm mm;
 	struct drm_device *dev;
@@ -345,8 +360,9 @@ struct i915_hw_ppgtt {
 	struct drm_mm_node node;
 	unsigned long pd_dirty_rings;
 	union {
-		struct i915_page_directory_pointer pdp;
-		struct i915_page_directory pd;
+		struct i915_pml4 pml4;		/* GEN8+ & 48b PPGTT */
+		struct i915_page_directory_pointer pdp;	/* GEN8+ */
+		struct i915_page_directory pd;		/* GEN6-7 */
 	};
 
 	struct drm_i915_file_private *file_priv;
-- 
2.5.0