On 06/03/2017 23:54, Matthew Auld wrote:
Signed-off-by: Matthew Auld <matthew.auld@xxxxxxxxx>
---
drivers/gpu/drm/i915/i915_gem_gtt.c | 32 ++++++++++++++++++++++-----
drivers/gpu/drm/i915/i915_gem_gtt.h | 1 +
drivers/gpu/drm/i915/selftests/i915_gem_gtt.c | 3 ++-
drivers/gpu/drm/i915/selftests/mock_gtt.c | 1 +
4 files changed, 30 insertions(+), 7 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index cee9c4fec52a..9274974956b3 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -205,7 +205,7 @@ static int ppgtt_bind_vma(struct i915_vma *vma,
pte_flags |= PTE_READ_ONLY;
vma->vm->insert_entries(vma->vm, vma->pages, vma->node.start,
- cache_level, pte_flags);
+ vma->obj->page_size, cache_level, pte_flags);
return 0;
}
@@ -906,6 +906,7 @@ gen8_ppgtt_insert_pte_entries(struct i915_hw_ppgtt *ppgtt,
static void gen8_ppgtt_insert_3lvl(struct i915_address_space *vm,
struct sg_table *pages,
u64 start,
+ unsigned long page_size,
enum i915_cache_level cache_level,
u32 unused)
{
@@ -924,6 +925,7 @@ static void gen8_ppgtt_insert_3lvl(struct i915_address_space *vm,
static void gen8_ppgtt_insert_4lvl(struct i915_address_space *vm,
struct sg_table *pages,
u64 start,
+ unsigned long page_size,
enum i915_cache_level cache_level,
u32 unused)
{
@@ -935,9 +937,23 @@ static void gen8_ppgtt_insert_4lvl(struct i915_address_space *vm,
};
struct i915_page_directory_pointer **pdps = ppgtt->pml4.pdps;
struct gen8_insert_pte idx = gen8_insert_pte(start);
+ bool (*insert_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);
+
+ switch (page_size) {
+ case I915_GTT_PAGE_SIZE:
+ insert_entries = gen8_ppgtt_insert_pte_entries;
+ break;
+ default:
+ MISSING_CASE(page_size);
+ return;
+ }
Hm, if you stored obj->page_size as an enum of known possible sizes,
then perhaps we could have an array of vm->insert_entries indexed by
that enum. You would then pass around this enum (could also use for
colouring I guess?) and instead of the above, maybe in ppgtt_bind_vma
just do something like
vma->vm->insert_entries[vma->obj->page_size_id](...). Or something like
that. Just thinking on how keep the vfunc approach as much as possible.
Regards,
Tvrtko
- while (gen8_ppgtt_insert_pte_entries(ppgtt, pdps[idx.pml4e++], &iter,
- &idx, cache_level))
+ while (insert_entries(ppgtt, pdps[idx.pml4e++], &iter, &idx,
+ cache_level))
GEM_BUG_ON(idx.pml4e >= GEN8_PML4ES_PER_PML4);
}
@@ -1620,6 +1636,7 @@ static void gen6_ppgtt_clear_range(struct i915_address_space *vm,
static void gen6_ppgtt_insert_entries(struct i915_address_space *vm,
struct sg_table *pages,
u64 start,
+ unsigned long page_size,
enum i915_cache_level cache_level,
u32 flags)
{
@@ -2093,6 +2110,7 @@ static void gen8_ggtt_insert_page(struct i915_address_space *vm,
static void gen8_ggtt_insert_entries(struct i915_address_space *vm,
struct sg_table *st,
u64 start,
+ unsigned long page_size,
enum i915_cache_level level,
u32 unused)
{
@@ -2140,6 +2158,7 @@ static void gen6_ggtt_insert_page(struct i915_address_space *vm,
static void gen6_ggtt_insert_entries(struct i915_address_space *vm,
struct sg_table *st,
u64 start,
+ unsigned long page_size,
enum i915_cache_level level,
u32 flags)
{
@@ -2224,6 +2243,7 @@ static void i915_ggtt_insert_page(struct i915_address_space *vm,
static void i915_ggtt_insert_entries(struct i915_address_space *vm,
struct sg_table *pages,
u64 start,
+ unsigned long page_size,
enum i915_cache_level cache_level,
u32 unused)
{
@@ -2260,7 +2280,7 @@ static int ggtt_bind_vma(struct i915_vma *vma,
intel_runtime_pm_get(i915);
vma->vm->insert_entries(vma->vm, vma->pages, vma->node.start,
- cache_level, pte_flags);
+ I915_GTT_PAGE_SIZE, cache_level, pte_flags);
intel_runtime_pm_put(i915);
/*
@@ -2314,14 +2334,14 @@ static int aliasing_gtt_bind_vma(struct i915_vma *vma,
appgtt->base.insert_entries(&appgtt->base,
vma->pages, vma->node.start,
- cache_level, pte_flags);
+ I915_GTT_PAGE_SIZE, cache_level, pte_flags);
}
if (flags & I915_VMA_GLOBAL_BIND) {
intel_runtime_pm_get(i915);
vma->vm->insert_entries(vma->vm,
vma->pages, vma->node.start,
- cache_level, pte_flags);
+ I915_GTT_PAGE_SIZE, cache_level, pte_flags);
intel_runtime_pm_put(i915);
}
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.h b/drivers/gpu/drm/i915/i915_gem_gtt.h
index 6c90a2ffd0e1..1f51402cf816 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.h
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.h
@@ -328,6 +328,7 @@ struct i915_address_space {
void (*insert_entries)(struct i915_address_space *vm,
struct sg_table *st,
u64 start,
+ unsigned long page_size,
enum i915_cache_level cache_level,
u32 flags);
void (*cleanup)(struct i915_address_space *vm);
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
index c4a39b7d7dd0..c7963efe46ba 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
@@ -256,7 +256,8 @@ static int lowlevel_hole(struct drm_i915_private *i915,
break;
vm->insert_entries(vm, obj->mm.pages, addr,
- I915_CACHE_NONE, 0);
+ I915_GTT_PAGE_SIZE, I915_CACHE_NONE,
+ 0);
}
count = n;
diff --git a/drivers/gpu/drm/i915/selftests/mock_gtt.c b/drivers/gpu/drm/i915/selftests/mock_gtt.c
index a61309c7cb3e..a2137100d2f5 100644
--- a/drivers/gpu/drm/i915/selftests/mock_gtt.c
+++ b/drivers/gpu/drm/i915/selftests/mock_gtt.c
@@ -35,6 +35,7 @@ static void mock_insert_page(struct i915_address_space *vm,
static void mock_insert_entries(struct i915_address_space *vm,
struct sg_table *st,
u64 start,
+ unsigned long page_size,
enum i915_cache_level level, u32 flags)
{
}
_______________________________________________
Intel-gfx mailing list
Intel-gfx@xxxxxxxxxxxxxxxxxxxxx
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
