[Intel-gfx] [PATCH v4 09/16] drm/i915/gtt: add xehpsdv_ppgtt_insert_entry

[Ramalingam C <ramalingam.c@intel.com>]

From: Matthew Auld <matthew.auld@intel.com>

If this is LMEM then we get a 32 entry PT, with each PTE pointing to
some 64K block of memory, otherwise it's just the usual 512 entry PT.
This very much assumes the caller knows what they are doing.

Signed-off-by: Matthew Auld <matthew.auld@intel.com>
Cc: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Cc: Ramalingam C <ramalingam.c@intel.com>
Reviewed-by: Ramalingam C <ramalingam.c@intel.com>
---
 drivers/gpu/drm/i915/gt/gen8_ppgtt.c | 50 ++++++++++++++++++++++++++--
 1 file changed, 48 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/gen8_ppgtt.c b/drivers/gpu/drm/i915/gt/gen8_ppgtt.c
index 5db11d8f7c7a..b6e9bfecb023 100644
--- a/drivers/gpu/drm/i915/gt/gen8_ppgtt.c
+++ b/drivers/gpu/drm/i915/gt/gen8_ppgtt.c
@@ -728,13 +728,56 @@ static void gen8_ppgtt_insert_entry(struct i915_address_space *vm,
 		gen8_pdp_for_page_index(vm, idx);
 	struct i915_page_directory *pd =
 		i915_pd_entry(pdp, gen8_pd_index(idx, 2));
+	struct i915_page_table *pt = i915_pt_entry(pd, gen8_pd_index(idx, 1));
 	gen8_pte_t *vaddr;
 
-	vaddr = px_vaddr(i915_pt_entry(pd, gen8_pd_index(idx, 1)));
+	GEM_BUG_ON(pt->is_compact);
+
+	vaddr = px_vaddr(pt);
 	vaddr[gen8_pd_index(idx, 0)] = gen8_pte_encode(addr, level, flags);
 	clflush_cache_range(&vaddr[gen8_pd_index(idx, 0)], sizeof(*vaddr));
 }
 
+static void __xehpsdv_ppgtt_insert_entry_lm(struct i915_address_space *vm,
+					    dma_addr_t addr,
+					    u64 offset,
+					    enum i915_cache_level level,
+					    u32 flags)
+{
+	u64 idx = offset >> GEN8_PTE_SHIFT;
+	struct i915_page_directory * const pdp =
+		gen8_pdp_for_page_index(vm, idx);
+	struct i915_page_directory *pd =
+		i915_pd_entry(pdp, gen8_pd_index(idx, 2));
+	struct i915_page_table *pt = i915_pt_entry(pd, gen8_pd_index(idx, 1));
+	gen8_pte_t *vaddr;
+
+	GEM_BUG_ON(!IS_ALIGNED(addr, SZ_64K));
+	GEM_BUG_ON(!IS_ALIGNED(offset, SZ_64K));
+
+	if (!pt->is_compact) {
+		vaddr = px_vaddr(pd);
+		vaddr[gen8_pd_index(idx, 1)] |= GEN12_PDE_64K;
+		pt->is_compact = true;
+	}
+
+	vaddr = px_vaddr(pt);
+	vaddr[gen8_pd_index(idx, 0) / 16] = gen8_pte_encode(addr, level, flags);
+}
+
+static void xehpsdv_ppgtt_insert_entry(struct i915_address_space *vm,
+				       dma_addr_t addr,
+				       u64 offset,
+				       enum i915_cache_level level,
+				       u32 flags)
+{
+	if (flags & PTE_LM)
+		return __xehpsdv_ppgtt_insert_entry_lm(vm, addr, offset,
+						       level, flags);
+
+	return gen8_ppgtt_insert_entry(vm, addr, offset, level, flags);
+}
+
 static int gen8_init_scratch(struct i915_address_space *vm)
 {
 	u32 pte_flags;
@@ -937,7 +980,10 @@ struct i915_ppgtt *gen8_ppgtt_create(struct intel_gt *gt,
 
 	ppgtt->vm.bind_async_flags = I915_VMA_LOCAL_BIND;
 	ppgtt->vm.insert_entries = gen8_ppgtt_insert;
-	ppgtt->vm.insert_page = gen8_ppgtt_insert_entry;
+	if (HAS_64K_PAGES(gt->i915))
+		ppgtt->vm.insert_page = xehpsdv_ppgtt_insert_entry;
+	else
+		ppgtt->vm.insert_page = gen8_ppgtt_insert_entry;
 	ppgtt->vm.allocate_va_range = gen8_ppgtt_alloc;
 	ppgtt->vm.clear_range = gen8_ppgtt_clear;
 	ppgtt->vm.foreach = gen8_ppgtt_foreach;
-- 
2.20.1