@@ -276,14 +276,21 @@ static struct sg_table *amdgpu_dma_buf_map(struct dma_buf_attachment *attach,
struct dma_buf *dma_buf = attach->dmabuf;
struct drm_gem_object *obj = dma_buf->priv;
struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj);
+ struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
struct sg_table *sgt;
long r;
if (!bo->pin_count) {
- /* move buffer into GTT */
+ /* move buffer into GTT or VRAM */
struct ttm_operation_ctx ctx = { false, false };
+ unsigned domains = AMDGPU_GEM_DOMAIN_GTT;
- amdgpu_bo_placement_from_domain(bo, AMDGPU_GEM_DOMAIN_GTT);
+ if (bo->preferred_domains & AMDGPU_GEM_DOMAIN_VRAM &&
+ attach->peer2peer) {
+ bo->flags |= AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED;
+ domains |= AMDGPU_GEM_DOMAIN_VRAM;
+ }
+ amdgpu_bo_placement_from_domain(bo, domains);
r = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
if (r)
return ERR_PTR(r);
@@ -293,20 +300,34 @@ static struct sg_table *amdgpu_dma_buf_map(struct dma_buf_attachment *attach,
return ERR_PTR(-EBUSY);
}
- sgt = drm_prime_pages_to_sg(bo->tbo.ttm->pages, bo->tbo.num_pages);
- if (IS_ERR(sgt))
- return sgt;
-
- if (!dma_map_sg_attrs(attach->dev, sgt->sgl, sgt->nents, dir,
- DMA_ATTR_SKIP_CPU_SYNC))
- goto error_free;
+ switch (bo->tbo.mem.mem_type) {
+ case TTM_PL_TT:
+ sgt = drm_prime_pages_to_sg(bo->tbo.ttm->pages,
+ bo->tbo.num_pages);
+ if (IS_ERR(sgt))
+ return sgt;
+
+ if (!dma_map_sg_attrs(attach->dev, sgt->sgl, sgt->nents, dir,
+ DMA_ATTR_SKIP_CPU_SYNC))
+ goto error_free;
+ break;
+
+ case TTM_PL_VRAM:
+ r = amdgpu_vram_mgr_alloc_sgt(adev, &bo->tbo.mem, attach->dev,
+ dir, &sgt);
+ if (r)
+ return ERR_PTR(r);
+ break;
+ default:
+ return ERR_PTR(-EINVAL);
+ }
return sgt;
error_free:
sg_free_table(sgt);
kfree(sgt);
- return ERR_PTR(-ENOMEM);
+ return ERR_PTR(-EBUSY);
}
/**
@@ -322,9 +343,18 @@ static void amdgpu_dma_buf_unmap(struct dma_buf_attachment *attach,
struct sg_table *sgt,
enum dma_data_direction dir)
{
- dma_unmap_sg(attach->dev, sgt->sgl, sgt->nents, dir);
- sg_free_table(sgt);
- kfree(sgt);
+ struct dma_buf *dma_buf = attach->dmabuf;
+ struct drm_gem_object *obj = dma_buf->priv;
+ struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj);
+ struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
+
+ if (sgt->sgl->page_link) {
+ dma_unmap_sg(attach->dev, sgt->sgl, sgt->nents, dir);
+ sg_free_table(sgt);
+ kfree(sgt);
+ } else {
+ amdgpu_vram_mgr_free_sgt(adev, attach->dev, dir, sgt);
+ }
}
/**
@@ -24,8 +24,9 @@
#ifndef __AMDGPU_TTM_H__
#define __AMDGPU_TTM_H__
-#include "amdgpu.h"
+#include <linux/dma-direction.h>
#include <drm/gpu_scheduler.h>
+#include "amdgpu.h"
#define AMDGPU_PL_GDS (TTM_PL_PRIV + 0)
#define AMDGPU_PL_GWS (TTM_PL_PRIV + 1)
@@ -74,6 +75,15 @@ uint64_t amdgpu_gtt_mgr_usage(struct ttm_mem_type_manager *man);
int amdgpu_gtt_mgr_recover(struct ttm_mem_type_manager *man);
u64 amdgpu_vram_mgr_bo_visible_size(struct amdgpu_bo *bo);
+int amdgpu_vram_mgr_alloc_sgt(struct amdgpu_device *adev,
+ struct ttm_mem_reg *mem,
+ struct device *dev,
+ enum dma_data_direction dir,
+ struct sg_table **sgt);
+void amdgpu_vram_mgr_free_sgt(struct amdgpu_device *adev,
+ struct device *dev,
+ enum dma_data_direction dir,
+ struct sg_table *sgt);
uint64_t amdgpu_vram_mgr_usage(struct ttm_mem_type_manager *man);
uint64_t amdgpu_vram_mgr_vis_usage(struct ttm_mem_type_manager *man);
@@ -22,6 +22,7 @@
* Authors: Christian König
*/
+#include <linux/dma-mapping.h>
#include "amdgpu.h"
#include "amdgpu_vm.h"
#include "amdgpu_atomfirmware.h"
@@ -458,6 +459,102 @@ static void amdgpu_vram_mgr_del(struct ttm_mem_type_manager *man,
mem->mm_node = NULL;
}
+/**
+ * amdgpu_vram_mgr_alloc_sgt - allocate and fill a sg table
+ *
+ * @adev: amdgpu device pointer
+ * @mem: TTM memory object
+ * @dev: the other device
+ * @dir: dma direction
+ * @sgt: resulting sg table
+ *
+ * Allocate and fill a sg table from a VRAM allocation.
+ */
+int amdgpu_vram_mgr_alloc_sgt(struct amdgpu_device *adev,
+ struct ttm_mem_reg *mem,
+ struct device *dev,
+ enum dma_data_direction dir,
+ struct sg_table **sgt)
+{
+ struct drm_mm_node *node;
+ struct scatterlist *sg;
+ int num_entries = 0;
+ unsigned int pages;
+ int i, r;
+
+ *sgt = kmalloc(sizeof(*sg), GFP_KERNEL);
+ if (!*sgt)
+ return -ENOMEM;
+
+ for (pages = mem->num_pages, node = mem->mm_node;
+ pages; pages -= node->size, ++node)
+ ++num_entries;
+
+ r = sg_alloc_table(*sgt, num_entries, GFP_KERNEL);
+ if (r)
+ goto error_free;
+
+ for_each_sg((*sgt)->sgl, sg, num_entries, i)
+ sg->length = 0;
+
+ node = mem->mm_node;
+ for_each_sg((*sgt)->sgl, sg, num_entries, i) {
+ phys_addr_t phys = (node->start << PAGE_SHIFT) +
+ adev->gmc.aper_base;
+ size_t size = node->size << PAGE_SHIFT;
+ dma_addr_t addr;
+
+ ++node;
+ addr = dma_map_resource(dev, phys, size, dir,
+ DMA_ATTR_SKIP_CPU_SYNC);
+ r = dma_mapping_error(dev, addr);
+ if (r)
+ goto error_unmap;
+
+ sg_set_dma_addr(sg, addr, size, 0);
+ }
+ return 0;
+
+error_unmap:
+ for_each_sg((*sgt)->sgl, sg, num_entries, i) {
+ if (!sg->length)
+ continue;
+
+ dma_unmap_resource(dev, sg->dma_address,
+ sg->length, dir,
+ DMA_ATTR_SKIP_CPU_SYNC);
+ }
+ sg_free_table(*sgt);
+
+error_free:
+ kfree(*sgt);
+ return r;
+}
+
+/**
+ * amdgpu_vram_mgr_alloc_sgt - allocate and fill a sg table
+ *
+ * @adev: amdgpu device pointer
+ * @sgt: sg table to free
+ *
+ * Free a previously allocate sg table.
+ */
+void amdgpu_vram_mgr_free_sgt(struct amdgpu_device *adev,
+ struct device *dev,
+ enum dma_data_direction dir,
+ struct sg_table *sgt)
+{
+ struct scatterlist *sg;
+ int i;
+
+ for_each_sg(sgt->sgl, sg, sgt->nents, i)
+ dma_unmap_resource(dev, sg->dma_address,
+ sg->length, dir,
+ DMA_ATTR_SKIP_CPU_SYNC);
+ sg_free_table(sgt);
+ kfree(sgt);
+}
+
/**
* amdgpu_vram_mgr_usage - how many bytes are used in this domain
*
We should be able to do this now after checking all the prerequisites. v2: fix entrie count in the sgt Signed-off-by: Christian König <christian.koenig@amd.com> --- drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c | 56 ++++++++--- drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h | 12 ++- drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c | 97 ++++++++++++++++++++ 3 files changed, 151 insertions(+), 14 deletions(-)