@@ -420,31 +420,28 @@ struct dma_buf *amdgpu_gem_prime_export(struct drm_device *dev,
}
/**
- * amdgpu_gem_prime_import_sg_table - &drm_driver.gem_prime_import_sg_table
- * implementation
+ * amdgpu_dma_buf_create_obj - create BO for DMA-buf import
+ *
* @dev: DRM device
- * @attach: DMA-buf attachment
- * @sg: Scatter/gather table
+ * @dma_buf: DMA-buf
*
- * Imports shared DMA buffer memory exported by another device.
+ * Creates an empty SG BO for DMA-buf import.
*
* Returns:
* A new GEM BO of the given DRM device, representing the memory
* described by the given DMA-buf attachment and scatter/gather table.
*/
-struct drm_gem_object *
-amdgpu_gem_prime_import_sg_table(struct drm_device *dev,
- struct dma_buf_attachment *attach,
- struct sg_table *sg)
+static struct drm_gem_object *
+amdgpu_dma_buf_create_obj(struct drm_device *dev, struct dma_buf *dma_buf)
{
- struct reservation_object *resv = attach->dmabuf->resv;
+ struct reservation_object *resv = dma_buf->resv;
struct amdgpu_device *adev = dev->dev_private;
struct amdgpu_bo *bo;
struct amdgpu_bo_param bp;
int ret;
memset(&bp, 0, sizeof(bp));
- bp.size = attach->dmabuf->size;
+ bp.size = dma_buf->size;
bp.byte_align = PAGE_SIZE;
bp.domain = AMDGPU_GEM_DOMAIN_CPU;
bp.flags = 0;
@@ -455,11 +452,9 @@ amdgpu_gem_prime_import_sg_table(struct drm_device *dev,
if (ret)
goto error;
- bo->tbo.sg = sg;
- bo->tbo.ttm->sg = sg;
bo->allowed_domains = AMDGPU_GEM_DOMAIN_GTT;
bo->preferred_domains = AMDGPU_GEM_DOMAIN_GTT;
- if (attach->dmabuf->ops != &amdgpu_dmabuf_ops)
+ if (dma_buf->ops != &amdgpu_dmabuf_ops)
bo->prime_shared_count = 1;
ww_mutex_unlock(&resv->lock);
@@ -470,6 +465,32 @@ amdgpu_gem_prime_import_sg_table(struct drm_device *dev,
return ERR_PTR(ret);
}
+/**
+ * amdgpu_gem_prime_invalidate_mappings - &attach.invalidate implementation
+ *
+ * @attach: the DMA-buf attachment
+ *
+ * Invalidate the DMA-buf attachment, making sure that the we re-create the
+ * mapping before the next use.
+ */
+static void
+amdgpu_gem_prime_invalidate_mappings(struct dma_buf_attachment *attach)
+{
+ struct ttm_operation_ctx ctx = { false, false };
+ struct drm_gem_object *obj = attach->importer_priv;
+ struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj);
+ struct ttm_placement placement = {};
+ int r;
+
+ r = ttm_bo_validate(&bo->tbo, &placement, &ctx);
+ if (r)
+ DRM_ERROR("Failed to invalidate DMA-buf import (%d))\n", r);
+}
+
+static const struct dma_buf_attach_ops amdgpu_dma_buf_attach_ops = {
+ .invalidate = amdgpu_gem_prime_invalidate_mappings
+};
+
/**
* amdgpu_gem_prime_import - &drm_driver.gem_prime_import implementation
* @dev: DRM device
@@ -484,6 +505,7 @@ amdgpu_gem_prime_import_sg_table(struct drm_device *dev,
struct drm_gem_object *amdgpu_gem_prime_import(struct drm_device *dev,
struct dma_buf *dma_buf)
{
+ struct dma_buf_attachment *attach;
struct drm_gem_object *obj;
if (dma_buf->ops == &amdgpu_dmabuf_ops) {
@@ -498,5 +520,18 @@ struct drm_gem_object *amdgpu_gem_prime_import(struct drm_device *dev,
}
}
- return drm_gem_prime_import(dev, dma_buf);
+ obj = amdgpu_dma_buf_create_obj(dev, dma_buf);
+ if (IS_ERR(obj))
+ return obj;
+
+ attach = dma_buf_dynamic_attach(dma_buf, dev->dev,
+ &amdgpu_dma_buf_attach_ops, obj);
+ if (IS_ERR(attach)) {
+ drm_gem_object_put(obj);
+ return ERR_CAST(attach);
+ }
+
+ get_dma_buf(dma_buf);
+ obj->import_attach = attach;
+ return obj;
}
@@ -25,10 +25,6 @@
#include <drm/drm_gem.h>
-struct drm_gem_object *
-amdgpu_gem_prime_import_sg_table(struct drm_device *dev,
- struct dma_buf_attachment *attach,
- struct sg_table *sg);
struct dma_buf *amdgpu_gem_prime_export(struct drm_device *dev,
struct drm_gem_object *gobj,
int flags);
@@ -1333,7 +1333,6 @@ static struct drm_driver kms_driver = {
.gem_prime_export = amdgpu_gem_prime_export,
.gem_prime_import = amdgpu_gem_prime_import,
.gem_prime_res_obj = amdgpu_gem_prime_res_obj,
- .gem_prime_import_sg_table = amdgpu_gem_prime_import_sg_table,
.gem_prime_vmap = amdgpu_gem_prime_vmap,
.gem_prime_vunmap = amdgpu_gem_prime_vunmap,
.gem_prime_mmap = amdgpu_gem_prime_mmap,
@@ -854,6 +854,9 @@ int amdgpu_bo_pin_restricted(struct amdgpu_bo *bo, u32 domain,
return 0;
}
+ if (bo->gem_base.import_attach)
+ dma_buf_pin(bo->gem_base.import_attach);
+
bo->flags |= AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS;
/* force to pin into visible video ram */
if (!(bo->flags & AMDGPU_GEM_CREATE_NO_CPU_ACCESS))
@@ -937,6 +940,9 @@ int amdgpu_bo_unpin(struct amdgpu_bo *bo)
amdgpu_bo_subtract_pin_size(bo);
+ if (bo->gem_base.import_attach)
+ dma_buf_unpin(bo->gem_base.import_attach);
+
for (i = 0; i < bo->placement.num_placement; i++) {
bo->placements[i].lpfn = 0;
bo->placements[i].flags &= ~TTM_PL_FLAG_NO_EVICT;
@@ -44,6 +44,7 @@
#include <linux/debugfs.h>
#include <linux/iommu.h>
#include <linux/hmm.h>
+#include <linux/dma-buf.h>
#include "amdgpu.h"
#include "amdgpu_object.h"
#include "amdgpu_trace.h"
@@ -706,6 +707,7 @@ static unsigned long amdgpu_ttm_io_mem_pfn(struct ttm_buffer_object *bo,
*/
struct amdgpu_ttm_tt {
struct ttm_dma_tt ttm;
+ struct drm_gem_object *gobj;
u64 offset;
uint64_t userptr;
struct task_struct *usertask;
@@ -1193,6 +1195,7 @@ static struct ttm_tt *amdgpu_ttm_tt_create(struct ttm_buffer_object *bo,
return NULL;
}
gtt->ttm.ttm.func = &amdgpu_backend_func;
+ gtt->gobj = &ttm_to_amdgpu_bo(bo)->gem_base;
/* allocate space for the uninitialized page entries */
if (ttm_sg_tt_init(>t->ttm, bo, page_flags)) {
@@ -1213,7 +1216,6 @@ static int amdgpu_ttm_tt_populate(struct ttm_tt *ttm,
{
struct amdgpu_device *adev = amdgpu_ttm_adev(ttm->bdev);
struct amdgpu_ttm_tt *gtt = (void *)ttm;
- bool slave = !!(ttm->page_flags & TTM_PAGE_FLAG_SG);
/* user pages are bound by amdgpu_ttm_tt_pin_userptr() */
if (gtt && gtt->userptr) {
@@ -1226,7 +1228,19 @@ static int amdgpu_ttm_tt_populate(struct ttm_tt *ttm,
return 0;
}
- if (slave && ttm->sg) {
+ if (ttm->page_flags & TTM_PAGE_FLAG_SG) {
+ if (!ttm->sg) {
+ struct dma_buf_attachment *attach;
+ struct sg_table *sgt;
+
+ attach = gtt->gobj->import_attach;
+ sgt = dma_buf_map_attachment(attach, DMA_BIDIRECTIONAL);
+ if (IS_ERR(sgt))
+ return PTR_ERR(sgt);
+
+ ttm->sg = sgt;
+ }
+
drm_prime_sg_to_page_addr_arrays(ttm->sg, ttm->pages,
gtt->ttm.dma_address,
ttm->num_pages);
@@ -1253,9 +1267,8 @@ static int amdgpu_ttm_tt_populate(struct ttm_tt *ttm,
*/
static void amdgpu_ttm_tt_unpopulate(struct ttm_tt *ttm)
{
- struct amdgpu_device *adev;
struct amdgpu_ttm_tt *gtt = (void *)ttm;
- bool slave = !!(ttm->page_flags & TTM_PAGE_FLAG_SG);
+ struct amdgpu_device *adev;
if (gtt && gtt->userptr) {
amdgpu_ttm_tt_set_user_pages(ttm, NULL);
@@ -1264,7 +1277,16 @@ static void amdgpu_ttm_tt_unpopulate(struct ttm_tt *ttm)
return;
}
- if (slave)
+ if (ttm->sg && gtt->gobj->import_attach) {
+ struct dma_buf_attachment *attach;
+
+ attach = gtt->gobj->import_attach;
+ dma_buf_unmap_attachment(attach, ttm->sg, DMA_BIDIRECTIONAL);
+ ttm->sg = NULL;
+ return;
+ }
+
+ if (ttm->page_flags & TTM_PAGE_FLAG_SG)
return;
adev = amdgpu_ttm_adev(ttm->bdev);
Instead of relying on the DRM functions just implement our own import functions. This prepares support for taking care of unpinned DMA-buf. v2: enable for all exporters, not just amdgpu, fix invalidation handling, lock reservation object while setting callback v3: change to new dma_buf attach interface v4: split out from unpinned DMA-buf work v5: rebased and cleanup on new DMA-buf interface v6: squash with invalidation callback change, stop using _(map|unmap)_locked Signed-off-by: Christian König <christian.koenig@amd.com> --- drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c | 65 ++++++++++++++++----- drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.h | 4 -- drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 1 - drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 6 ++ drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 32 ++++++++-- 5 files changed, 83 insertions(+), 25 deletions(-)