[PATCH 15/25] drm/i915/ttm: Add io sgt caching to i915_ttm_io_mem_pfn
Matthew Auld
matthew.auld at intel.com
Tue May 18 13:43:27 UTC 2021
From: Maarten Lankhorst <maarten.lankhorst at linux.intel.com>
Instead of walking the sg table manually, use our caching helpers
to do the sgt caching. To prevent lifetime issues of ttm_bo vs
i915_gem_object, we will use a separate member, instead of re-using
the dma page member.
Signed-off-by: Maarten Lankhorst <maarten.lankhorst at linux.intel.com>
Reviewed-by: Thomas Hellström <thomas.hellstrom at linux.intel.com>
---
drivers/gpu/drm/i915/gem/i915_gem_object.h | 6 +--
.../gpu/drm/i915/gem/i915_gem_object_types.h | 1 +
drivers/gpu/drm/i915/gem/i915_gem_pages.c | 3 +-
drivers/gpu/drm/i915/gem/i915_gem_ttm.c | 46 ++++++++++---------
4 files changed, 30 insertions(+), 26 deletions(-)
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.h b/drivers/gpu/drm/i915/gem/i915_gem_object.h
index a3ad8cf4eefd..ff59e6c640e6 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object.h
@@ -342,14 +342,14 @@ struct scatterlist *
__i915_gem_object_get_sg(struct drm_i915_gem_object *obj,
struct i915_gem_object_page_iter *iter,
unsigned int n,
- unsigned int *offset, bool allow_alloc);
+ unsigned int *offset, bool allow_alloc, bool dma);
static inline struct scatterlist *
i915_gem_object_get_sg(struct drm_i915_gem_object *obj,
unsigned int n,
unsigned int *offset, bool allow_alloc)
{
- return __i915_gem_object_get_sg(obj, &obj->mm.get_page, n, offset, allow_alloc);
+ return __i915_gem_object_get_sg(obj, &obj->mm.get_page, n, offset, allow_alloc, false);
}
static inline struct scatterlist *
@@ -357,7 +357,7 @@ i915_gem_object_get_sg_dma(struct drm_i915_gem_object *obj,
unsigned int n,
unsigned int *offset, bool allow_alloc)
{
- return __i915_gem_object_get_sg(obj, &obj->mm.get_dma_page, n, offset, allow_alloc);
+ return __i915_gem_object_get_sg(obj, &obj->mm.get_dma_page, n, offset, allow_alloc, true);
}
struct page *
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
index 31d828e91cf4..828310802b9f 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
@@ -324,6 +324,7 @@ struct drm_i915_gem_object {
struct {
struct sg_table *cached_io_st;
+ struct i915_gem_object_page_iter get_io_page;
} ttm;
/** Record of address bit 17 of each page at last unbind. */
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_pages.c b/drivers/gpu/drm/i915/gem/i915_gem_pages.c
index 6444e097016d..086005c1c7ea 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_pages.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_pages.c
@@ -467,9 +467,8 @@ __i915_gem_object_get_sg(struct drm_i915_gem_object *obj,
struct i915_gem_object_page_iter *iter,
unsigned int n,
unsigned int *offset,
- bool allow_alloc)
+ bool allow_alloc, bool dma)
{
- const bool dma = iter == &obj->mm.get_dma_page;
struct scatterlist *sg;
unsigned int idx, count;
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
index fe9ac50b2470..1eaefb89e859 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
@@ -167,11 +167,20 @@ static int i915_ttm_move_notify(struct ttm_buffer_object *bo)
static void i915_ttm_free_cached_io_st(struct drm_i915_gem_object *obj)
{
- if (obj->ttm.cached_io_st) {
- sg_free_table(obj->ttm.cached_io_st);
- kfree(obj->ttm.cached_io_st);
- obj->ttm.cached_io_st = NULL;
- }
+ struct radix_tree_iter iter;
+ void __rcu **slot;
+
+ if (!obj->ttm.cached_io_st)
+ return;
+
+ rcu_read_lock();
+ radix_tree_for_each_slot(slot, &obj->ttm.get_io_page.radix, &iter, 0)
+ radix_tree_delete(&obj->ttm.get_io_page.radix, iter.index);
+ rcu_read_unlock();
+
+ sg_free_table(obj->ttm.cached_io_st);
+ kfree(obj->ttm.cached_io_st);
+ obj->ttm.cached_io_st = NULL;
}
static void i915_ttm_purge(struct drm_i915_gem_object *obj)
@@ -340,8 +349,11 @@ static int i915_ttm_move(struct ttm_buffer_object *bo, bool evict,
i915_ttm_move_memcpy(bo, new_mem, new_iter, old_iter);
i915_ttm_free_cached_io_st(obj);
- if (!new_man->use_tt)
+ if (!new_man->use_tt) {
obj->ttm.cached_io_st = new_st;
+ obj->ttm.get_io_page.sg_pos = new_st->sgl;
+ obj->ttm.get_io_page.sg_idx = 0;
+ }
return 0;
}
@@ -362,26 +374,15 @@ static unsigned long i915_ttm_io_mem_pfn(struct ttm_buffer_object *bo,
unsigned long page_offset)
{
struct drm_i915_gem_object *obj = i915_ttm_to_gem(bo);
- struct sg_table *sgt = obj->ttm.cached_io_st;
+ unsigned long base = obj->mm.region->iomap.base - obj->mm.region->region.start;
struct scatterlist *sg;
- unsigned int i;
+ unsigned int ofs;
GEM_WARN_ON(bo->ttm);
- for_each_sgtable_dma_sg(sgt, sg, i) {
- unsigned long sg_max = sg->length >> PAGE_SHIFT;
+ sg = __i915_gem_object_get_sg(obj, &obj->ttm.get_io_page, page_offset, &ofs, true, true);
- if (page_offset < sg_max) {
- unsigned long base =
- obj->mm.region->iomap.base - obj->mm.region->region.start;
-
- return ((base + sg_dma_address(sg)) >> PAGE_SHIFT) + page_offset;
- }
-
- page_offset -= sg_max;
- }
- GEM_BUG_ON(1);
- return 0;
+ return ((base + sg_dma_address(sg)) >> PAGE_SHIFT) + ofs;
}
struct ttm_device_funcs i915_ttm_bo_driver = {
@@ -613,6 +614,9 @@ int __i915_gem_ttm_object_init(struct intel_memory_region *mem,
obj->read_domains = I915_GEM_DOMAIN_WC | I915_GEM_DOMAIN_GTT;
i915_gem_object_set_cache_coherency(obj, I915_CACHE_NONE);
+ INIT_RADIX_TREE(&obj->ttm.get_io_page.radix, GFP_KERNEL | __GFP_NOWARN);
+ mutex_init(&obj->ttm.get_io_page.lock);
+
ret = ttm_bo_init(&i915->bdev, i915_gem_to_ttm(obj), size,
ttm_bo_type_kernel, &i915_sys_placement, alignment,
true, NULL, NULL, i915_ttm_bo_destroy);
--
2.26.3
More information about the Intel-gfx-trybot
mailing list