From f2c505c7ea7718a392ac99451368ccb058523e7c Mon Sep 17 00:00:00 2001
From: Matthew Auld <matthew.auld@intel.com>
Date: Wed, 8 Dec 2021 19:46:12 +0530
Subject: drm/i915/gtt/xehpsdv: move scratch page to system memory
Git-commit: fef53be028740aed15c288534e8f15719fb49947
Patch-mainline: v5.17-rc1
References: jsc#PED-1166 jsc#PED-1168 jsc#PED-1170 jsc#PED-1218 jsc#PED-1220 jsc#PED-1222 jsc#PED-1223 jsc#PED-1225
On some platforms the hw has dropped support for 4K GTT pages when
dealing with LMEM, and due to the design of 64K GTT pages in the hw, we
can only mark the *entire* page-table as operating in 64K GTT mode,
since the enable bit is still on the pde, and not the pte. And since we
we still need to allow 4K GTT pages for SMEM objects, we can't have a
"normal" 4K page-table with scratch pointing to LMEM, since that's
undefined from the hw pov. The simplest solution is to just move the 64K
scratch page to SMEM on such platforms and call it a day, since that
should work for all configurations.
Signed-off-by: Matthew Auld <matthew.auld@intel.com>
Signed-off-by: Ramalingam C <ramalingam.c@intel.com>
Reviewed-by: Thomas Hellstrom <thomas.hellstrom@linux.intel.com>
Reviewed-by: Andi Shyti <andi.shyti@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20211208141613.7251-4-ramalingam.c@intel.com
Acked-by: Patrik Jakobsson <pjakobsson@suse.de>
---
drivers/gpu/drm/i915/gt/gen6_ppgtt.c | 1 +
drivers/gpu/drm/i915/gt/gen8_ppgtt.c | 23 +++++++++++++++++++++--
drivers/gpu/drm/i915/gt/intel_ggtt.c | 3 +++
drivers/gpu/drm/i915/gt/intel_gtt.c | 2 +-
drivers/gpu/drm/i915/gt/intel_gtt.h | 2 ++
drivers/gpu/drm/i915/selftests/mock_gtt.c | 2 ++
6 files changed, 30 insertions(+), 3 deletions(-)
diff --git a/drivers/gpu/drm/i915/gt/gen6_ppgtt.c b/drivers/gpu/drm/i915/gt/gen6_ppgtt.c
index 4a166d25fe60..c0d149f04949 100644
--- a/drivers/gpu/drm/i915/gt/gen6_ppgtt.c
+++ b/drivers/gpu/drm/i915/gt/gen6_ppgtt.c
@@ -454,6 +454,7 @@ struct i915_ppgtt *gen6_ppgtt_create(struct intel_gt *gt)
ppgtt->base.vm.cleanup = gen6_ppgtt_cleanup;
ppgtt->base.vm.alloc_pt_dma = alloc_pt_dma;
+ ppgtt->base.vm.alloc_scratch_dma = alloc_pt_dma;
ppgtt->base.vm.pte_encode = ggtt->vm.pte_encode;
err = gen6_ppgtt_init_scratch(ppgtt);
diff --git a/drivers/gpu/drm/i915/gt/gen8_ppgtt.c b/drivers/gpu/drm/i915/gt/gen8_ppgtt.c
index 95c02096a61b..b012c50f7ce7 100644
--- a/drivers/gpu/drm/i915/gt/gen8_ppgtt.c
+++ b/drivers/gpu/drm/i915/gt/gen8_ppgtt.c
@@ -776,10 +776,29 @@ struct i915_ppgtt *gen8_ppgtt_create(struct intel_gt *gt,
*/
ppgtt->vm.has_read_only = !IS_GRAPHICS_VER(gt->i915, 11, 12);
- if (HAS_LMEM(gt->i915))
+ if (HAS_LMEM(gt->i915)) {
ppgtt->vm.alloc_pt_dma = alloc_pt_lmem;
- else
+
+ /*
+ * On some platforms the hw has dropped support for 4K GTT pages
+ * when dealing with LMEM, and due to the design of 64K GTT
+ * pages in the hw, we can only mark the *entire* page-table as
+ * operating in 64K GTT mode, since the enable bit is still on
+ * the pde, and not the pte. And since we still need to allow
+ * 4K GTT pages for SMEM objects, we can't have a "normal" 4K
+ * page-table with scratch pointing to LMEM, since that's
+ * undefined from the hw pov. The simplest solution is to just
+ * move the 64K scratch page to SMEM on such platforms and call
+ * it a day, since that should work for all configurations.
+ */
+ if (HAS_64K_PAGES(gt->i915))
+ ppgtt->vm.alloc_scratch_dma = alloc_pt_dma;
+ else
+ ppgtt->vm.alloc_scratch_dma = alloc_pt_lmem;
+ } else {
ppgtt->vm.alloc_pt_dma = alloc_pt_dma;
+ ppgtt->vm.alloc_scratch_dma = alloc_pt_dma;
+ }
err = gen8_init_scratch(&ppgtt->vm);
if (err)
diff --git a/drivers/gpu/drm/i915/gt/intel_ggtt.c b/drivers/gpu/drm/i915/gt/intel_ggtt.c
index cbc6d2b1fd9e..d85a1050f4a8 100644
--- a/drivers/gpu/drm/i915/gt/intel_ggtt.c
+++ b/drivers/gpu/drm/i915/gt/intel_ggtt.c
@@ -941,6 +941,7 @@ static int gen8_gmch_probe(struct i915_ggtt *ggtt)
size = gen8_get_total_gtt_size(snb_gmch_ctl);
ggtt->vm.alloc_pt_dma = alloc_pt_dma;
+ ggtt->vm.alloc_scratch_dma = alloc_pt_dma;
ggtt->vm.lmem_pt_obj_flags = I915_BO_ALLOC_PM_EARLY;
ggtt->vm.total = (size / sizeof(gen8_pte_t)) * I915_GTT_PAGE_SIZE;
@@ -1094,6 +1095,7 @@ static int gen6_gmch_probe(struct i915_ggtt *ggtt)
ggtt->vm.total = (size / sizeof(gen6_pte_t)) * I915_GTT_PAGE_SIZE;
ggtt->vm.alloc_pt_dma = alloc_pt_dma;
+ ggtt->vm.alloc_scratch_dma = alloc_pt_dma;
ggtt->vm.clear_range = nop_clear_range;
if (!HAS_FULL_PPGTT(i915) || intel_scanout_needs_vtd_wa(i915))
@@ -1146,6 +1148,7 @@ static int i915_gmch_probe(struct i915_ggtt *ggtt)
(struct resource)DEFINE_RES_MEM(gmadr_base, ggtt->mappable_end);
ggtt->vm.alloc_pt_dma = alloc_pt_dma;
+ ggtt->vm.alloc_scratch_dma = alloc_pt_dma;
if (needs_idle_maps(i915)) {
drm_notice(&i915->drm,
diff --git a/drivers/gpu/drm/i915/gt/intel_gtt.c b/drivers/gpu/drm/i915/gt/intel_gtt.c
index 9fee968d57db..20372bcb394a 100644
--- a/drivers/gpu/drm/i915/gt/intel_gtt.c
+++ b/drivers/gpu/drm/i915/gt/intel_gtt.c
@@ -302,7 +302,7 @@ int setup_scratch_page(struct i915_address_space *vm)
do {
struct drm_i915_gem_object *obj;
- obj = vm->alloc_pt_dma(vm, size);
+ obj = vm->alloc_scratch_dma(vm, size);
if (IS_ERR(obj))
goto skip;
diff --git a/drivers/gpu/drm/i915/gt/intel_gtt.h b/drivers/gpu/drm/i915/gt/intel_gtt.h
index 51afe66d00f2..15b98321e89a 100644
--- a/drivers/gpu/drm/i915/gt/intel_gtt.h
+++ b/drivers/gpu/drm/i915/gt/intel_gtt.h
@@ -268,6 +268,8 @@ struct i915_address_space {
struct drm_i915_gem_object *
(*alloc_pt_dma)(struct i915_address_space *vm, int sz);
+ struct drm_i915_gem_object *
+ (*alloc_scratch_dma)(struct i915_address_space *vm, int sz);
u64 (*pte_encode)(dma_addr_t addr,
enum i915_cache_level level,
diff --git a/drivers/gpu/drm/i915/selftests/mock_gtt.c b/drivers/gpu/drm/i915/selftests/mock_gtt.c
index cc047ec594f9..32ca8962d0ab 100644
--- a/drivers/gpu/drm/i915/selftests/mock_gtt.c
+++ b/drivers/gpu/drm/i915/selftests/mock_gtt.c
@@ -78,6 +78,7 @@ struct i915_ppgtt *mock_ppgtt(struct drm_i915_private *i915, const char *name)
i915_address_space_init(&ppgtt->vm, VM_CLASS_PPGTT);
ppgtt->vm.alloc_pt_dma = alloc_pt_dma;
+ ppgtt->vm.alloc_scratch_dma = alloc_pt_dma;
ppgtt->vm.clear_range = mock_clear_range;
ppgtt->vm.insert_page = mock_insert_page;
@@ -118,6 +119,7 @@ void mock_init_ggtt(struct drm_i915_private *i915, struct i915_ggtt *ggtt)
ggtt->vm.total = 4096 * PAGE_SIZE;
ggtt->vm.alloc_pt_dma = alloc_pt_dma;
+ ggtt->vm.alloc_scratch_dma = alloc_pt_dma;
ggtt->vm.clear_range = mock_clear_range;
ggtt->vm.insert_page = mock_insert_page;
--
2.38.1