[Intel-gfx] [PATCH 13/17] drm/i915: support inserting 1G pages into the 48b PPGTT

[Matthew Auld]

To enable 1G pages we set the PS bit in the PDPE, aka PDPE[7] to
indicate a 1G page, and not a PD.

Signed-off-by: Matthew Auld <matthew.auld at intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen at linux.intel.com>
---
 drivers/gpu/drm/i915/i915_gem_gtt.c | 47 +++++++++++++++++++++++++++++++++++++
 drivers/gpu/drm/i915/i915_gem_gtt.h |  2 ++
 2 files changed, 49 insertions(+)

diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 3dadb501daa6..e81c78ffbea5 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -854,6 +854,50 @@ static __always_inline struct gen8_insert_pte gen8_insert_pte(u64 start)
 }
 
 static __always_inline bool
+gen8_ppgtt_insert_1G_pdpe_entries(struct i915_hw_ppgtt *ppgtt,
+				  struct i915_page_directory_pointer *pdp,
+				  struct sgt_dma *iter,
+				  struct gen8_insert_pte *idx,
+				  enum i915_cache_level cache_level)
+{
+	const gen8_pte_t pdpe_encode = gen8_pte_encode(GEN8_PDPE_PS_1G,
+						       cache_level);
+	gen8_pte_t *vaddr;
+	bool ret;
+
+	GEM_BUG_ON(idx->pte);
+	GEM_BUG_ON(idx->pde);
+	GEM_BUG_ON(idx->pdpe >= i915_pdpes_per_pdp(&ppgtt->base));
+	vaddr = kmap_atomic_px(pdp);
+	do {
+		vaddr[idx->pdpe] = pdpe_encode | iter->dma;
+		iter->dma += I915_GTT_PAGE_SIZE_1G;
+		if (iter->dma >= iter->max) {
+			iter->sg = __sg_next(iter->sg);
+			if (!iter->sg) {
+				ret = false;
+				break;
+			}
+
+			iter->dma = sg_dma_address(iter->sg);
+			iter->max = iter->dma + iter->sg->length;
+		}
+
+		if (++idx->pdpe == GEN8_PML4ES_PER_PML4) {
+			idx->pdpe = 0;
+			ret = true;
+			break;
+		}
+
+	} while (1);
+	kunmap_atomic(vaddr);
+
+	mark_tlbs_dirty(ppgtt);
+
+	return ret;
+}
+
+static __always_inline bool
 gen8_ppgtt_insert_2M_pde_entries(struct i915_hw_ppgtt *ppgtt,
 				 struct i915_page_directory_pointer *pdp,
 				 struct sgt_dma *iter,
@@ -1081,6 +1125,9 @@ static void gen8_ppgtt_insert_4lvl(struct i915_address_space *vm,
 	case I915_GTT_PAGE_SIZE_2M:
 		insert_entries = gen8_ppgtt_insert_2M_pde_entries;
 		break;
+	case I915_GTT_PAGE_SIZE_1G:
+		insert_entries = gen8_ppgtt_insert_1G_pdpe_entries;
+		break;
 	default:
 		MISSING_CASE(page_size);
 		return;
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.h b/drivers/gpu/drm/i915/i915_gem_gtt.h
index 840d08be8fa3..1517cfdbd5ce 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.h
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.h
@@ -152,6 +152,8 @@ typedef u64 gen8_ppgtt_pml4e_t;
 #define GEN8_PDE_IPS_64K BIT(11)
 #define GEN8_PDE_PS_2M   BIT(7)
 
+#define GEN8_PDPE_PS_1G  BIT(7)
+
 struct sg_table;
 
 struct intel_rotation_info {
-- 
2.9.4