Hi, Ram,
On 2/7/22 10:37, Ramalingam C wrote:
While evicting the local memory data on flat-ccs capable platform we
need to evict the ccs data associated to the data.
For this, we are
adding extra pages ((size / 256) >> PAGE_SIZE) into the ttm_tt.
To achieve this we are adding a new param into the ttm_tt_init as
ccs_pages_needed, which will be added into the ttm_tt->num_pages.
Please use imperative form above, Instead of "We are adding..", use "Add"
Signed-off-by: Ramalingam C <ramalingam.c@xxxxxxxxx>
Suggested-by: Thomas Hellstorm <thomas.hellstrom@xxxxxxxxx>
Hellstorm instead of Hellstrom might scare people off. :)
---
drivers/gpu/drm/drm_gem_vram_helper.c | 2 +-
drivers/gpu/drm/i915/gem/i915_gem_ttm.c | 23 +++++++++++++++++++++-
drivers/gpu/drm/qxl/qxl_ttm.c | 2 +-
drivers/gpu/drm/ttm/ttm_agp_backend.c | 2 +-
drivers/gpu/drm/ttm/ttm_tt.c | 12 ++++++-----
drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c | 2 +-
include/drm/ttm/ttm_tt.h | 4 +++-
7 files changed, 36 insertions(+), 11 deletions(-)
diff --git a/drivers/gpu/drm/drm_gem_vram_helper.c b/drivers/gpu/drm/drm_gem_vram_helper.c
index 3f00192215d1..eef1f4dc7232 100644
--- a/drivers/gpu/drm/drm_gem_vram_helper.c
+++ b/drivers/gpu/drm/drm_gem_vram_helper.c
@@ -864,7 +864,7 @@ static struct ttm_tt *bo_driver_ttm_tt_create(struct ttm_buffer_object *bo,
if (!tt)
return NULL;
- ret = ttm_tt_init(tt, bo, page_flags, ttm_cached);
+ ret = ttm_tt_init(tt, bo, page_flags, ttm_cached, 0);
if (ret < 0)
goto err_ttm_tt_init;
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
index 84cae740b4a5..bb71aa6d66c0 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
@@ -16,6 +16,7 @@
#include "gem/i915_gem_ttm.h"
#include "gem/i915_gem_ttm_move.h"
#include "gem/i915_gem_ttm_pm.h"
+#include "gt/intel_gpu_commands.h"
#define I915_TTM_PRIO_PURGE 0
#define I915_TTM_PRIO_NO_PAGES 1
@@ -242,12 +243,27 @@ static const struct i915_refct_sgt_ops tt_rsgt_ops = {
.release = i915_ttm_tt_release
};
+static inline bool
+i915_gem_object_has_lmem_placement(struct drm_i915_gem_object *obj)
+{
+ int i;
+
+ for (i = 0; i < obj->mm.n_placements; i++)
+ if (obj->mm.placements[i]->type == INTEL_MEMORY_LOCAL)
+ return true;
+
+ return false;
+}
+
static struct ttm_tt *i915_ttm_tt_create(struct ttm_buffer_object *bo,
uint32_t page_flags)
{
+ struct drm_i915_private *i915 = container_of(bo->bdev, typeof(*i915),
+ bdev);
struct ttm_resource_manager *man =
ttm_manager_type(bo->bdev, bo->resource->mem_type);
struct drm_i915_gem_object *obj = i915_ttm_to_gem(bo);
+ unsigned long ccs_pages_needed = 0;
enum ttm_caching caching;
struct i915_ttm_tt *i915_tt;
int ret;
@@ -270,7 +286,12 @@ static struct ttm_tt *i915_ttm_tt_create(struct ttm_buffer_object *bo,
i915_tt->is_shmem = true;
}
- ret = ttm_tt_init(&i915_tt->ttm, bo, page_flags, caching);
+ if (HAS_FLAT_CCS(i915) && i915_gem_object_has_lmem_placement(obj))
+ ccs_pages_needed = DIV_ROUND_UP(DIV_ROUND_UP(bo->base.size,
+ NUM_CCS_BYTES_PER_BLOCK), PAGE_SIZE);
+
+ ret = ttm_tt_init(&i915_tt->ttm, bo, page_flags,
+ caching, ccs_pages_needed);
I'd suggest a patch that first adds the functionality to TTM, where even
i915 passes in 0 here, and a follow-up patch for the i915 functionality
where we add the ccs requirement.
if (ret)
goto err_free;
diff --git a/drivers/gpu/drm/qxl/qxl_ttm.c b/drivers/gpu/drm/qxl/qxl_ttm.c
index b2e33d5ba5d0..52156b54498f 100644
--- a/drivers/gpu/drm/qxl/qxl_ttm.c
+++ b/drivers/gpu/drm/qxl/qxl_ttm.c
@@ -113,7 +113,7 @@ static struct ttm_tt *qxl_ttm_tt_create(struct ttm_buffer_object *bo,
ttm = kzalloc(sizeof(struct ttm_tt), GFP_KERNEL);
if (ttm == NULL)
return NULL;
- if (ttm_tt_init(ttm, bo, page_flags, ttm_cached)) {
+ if (ttm_tt_init(ttm, bo, page_flags, ttm_cached, 0)) {
kfree(ttm);
return NULL;
}
diff --git a/drivers/gpu/drm/ttm/ttm_agp_backend.c b/drivers/gpu/drm/ttm/ttm_agp_backend.c
index 6ddc16f0fe2b..d27691f2e451 100644
--- a/drivers/gpu/drm/ttm/ttm_agp_backend.c
+++ b/drivers/gpu/drm/ttm/ttm_agp_backend.c
@@ -134,7 +134,7 @@ struct ttm_tt *ttm_agp_tt_create(struct ttm_buffer_object *bo,
agp_be->mem = NULL;
agp_be->bridge = bridge;
- if (ttm_tt_init(&agp_be->ttm, bo, page_flags, ttm_write_combined)) {
+ if (ttm_tt_init(&agp_be->ttm, bo, page_flags, ttm_write_combined, 0)) {
kfree(agp_be);
return NULL;
}
diff --git a/drivers/gpu/drm/ttm/ttm_tt.c b/drivers/gpu/drm/ttm/ttm_tt.c
index 79c870a3bef8..80355465f717 100644
--- a/drivers/gpu/drm/ttm/ttm_tt.c
+++ b/drivers/gpu/drm/ttm/ttm_tt.c
@@ -134,9 +134,10 @@ void ttm_tt_destroy(struct ttm_device *bdev, struct ttm_tt *ttm)
static void ttm_tt_init_fields(struct ttm_tt *ttm,
struct ttm_buffer_object *bo,
uint32_t page_flags,
- enum ttm_caching caching)
+ enum ttm_caching caching,
+ unsigned long ccs_pages)
{
- ttm->num_pages = PAGE_ALIGN(bo->base.size) >> PAGE_SHIFT;
+ ttm->num_pages = (PAGE_ALIGN(bo->base.size) >> PAGE_SHIFT) + ccs_pages;
ttm->caching = ttm_cached;
ttm->page_flags = page_flags;
ttm->dma_address = NULL;
@@ -146,9 +147,10 @@ static void ttm_tt_init_fields(struct ttm_tt *ttm,
}
int ttm_tt_init(struct ttm_tt *ttm, struct ttm_buffer_object *bo,
- uint32_t page_flags, enum ttm_caching caching)
+ uint32_t page_flags, enum ttm_caching caching,
+ unsigned long ccs_pages)
{
- ttm_tt_init_fields(ttm, bo, page_flags, caching);
+ ttm_tt_init_fields(ttm, bo, page_flags, caching, ccs_pages);
if (ttm_tt_alloc_page_directory(ttm)) {
pr_err("Failed allocating page table\n");
@@ -180,7 +182,7 @@ int ttm_sg_tt_init(struct ttm_tt *ttm, struct ttm_buffer_object *bo,
{
int ret;
- ttm_tt_init_fields(ttm, bo, page_flags, caching);
+ ttm_tt_init_fields(ttm, bo, page_flags, caching, 0);
if (page_flags & TTM_TT_FLAG_EXTERNAL)
ret = ttm_sg_tt_alloc_page_directory(ttm);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c
index b84ecc6d6611..4e3938e62c08 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c
@@ -517,7 +517,7 @@ static struct ttm_tt *vmw_ttm_tt_create(struct ttm_buffer_object *bo,
ttm_cached);
else
ret = ttm_tt_init(&vmw_be->dma_ttm, bo, page_flags,
- ttm_cached);
+ ttm_cached, 0);
if (unlikely(ret != 0))
goto out_no_init;
diff --git a/include/drm/ttm/ttm_tt.h b/include/drm/ttm/ttm_tt.h
index f20832139815..2c4ff08ea354 100644
--- a/include/drm/ttm/ttm_tt.h
+++ b/include/drm/ttm/ttm_tt.h
@@ -140,6 +140,7 @@ int ttm_tt_create(struct ttm_buffer_object *bo, bool zero_alloc);
* @bo: The buffer object we create the ttm for.
* @page_flags: Page flags as identified by TTM_TT_FLAG_XX flags.
* @caching: the desired caching state of the pages
+ * @ccs_pages_needed: Extra pages needed for the ccs data of compression.
The name and use-case ccs is driver specific, and TTM knows nothing
about CCS. Hence we should use "additional_pages", "additional_size" or
something similar for this. Christian might have some additional
guidance here.
*
* Create a struct ttm_tt to back data with system memory pages.
* No pages are actually allocated.
@@ -147,7 +148,8 @@ int ttm_tt_create(struct ttm_buffer_object *bo, bool zero_alloc);
* NULL: Out of memory.
*/
int ttm_tt_init(struct ttm_tt *ttm, struct ttm_buffer_object *bo,
- uint32_t page_flags, enum ttm_caching caching);
+ uint32_t page_flags, enum ttm_caching caching,
+ unsigned long ccs_pages_needed);
int ttm_sg_tt_init(struct ttm_tt *ttm_dma, struct ttm_buffer_object *bo,
uint32_t page_flags, enum ttm_caching caching);
Thanks,
Thomas
