This add the support for the new fault callback and also the infrastructure for supporting unmappable VRAM.
V2 validate BO with no_wait = true V3 don't derefence bo->mem.mm_node as it's not NULL only for VRAM or GTT V4 update to splitted no_wait ttm change V5 update to new balanced io_mem_reserve/free change Signed-off-by: Jerome Glisse <jgli...@redhat.com> --- drivers/gpu/drm/radeon/radeon_object.c | 26 ++++++++++++++++- drivers/gpu/drm/radeon/radeon_object.h | 2 +- drivers/gpu/drm/radeon/radeon_ttm.c | 47 +++++++++++++++++++++++++++++++- 3 files changed, 71 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/radeon/radeon_object.c b/drivers/gpu/drm/radeon/radeon_object.c index 3adfa88..aef44f3 100644 --- a/drivers/gpu/drm/radeon/radeon_object.c +++ b/drivers/gpu/drm/radeon/radeon_object.c @@ -496,11 +496,33 @@ void radeon_bo_move_notify(struct ttm_buffer_object *bo, radeon_bo_check_tiling(rbo, 0, 1); } -void radeon_bo_fault_reserve_notify(struct ttm_buffer_object *bo) +int radeon_bo_fault_reserve_notify(struct ttm_buffer_object *bo) { + struct radeon_device *rdev; struct radeon_bo *rbo; + unsigned long offset, size; + int r; + if (!radeon_ttm_bo_is_radeon_bo(bo)) - return; + return 0; rbo = container_of(bo, struct radeon_bo, tbo); radeon_bo_check_tiling(rbo, 0, 0); + rdev = rbo->rdev; + if (bo->mem.mem_type == TTM_PL_VRAM) { + size = bo->mem.num_pages << PAGE_SHIFT; + offset = bo->mem.mm_node->start << PAGE_SHIFT; + if ((offset + size) > rdev->mc.visible_vram_size) { + /* hurrah the memory is not visible ! */ + radeon_ttm_placement_from_domain(rbo, RADEON_GEM_DOMAIN_VRAM); + rbo->placement.lpfn = rdev->mc.visible_vram_size >> PAGE_SHIFT; + r = ttm_bo_validate(bo, &rbo->placement, false, true, false); + if (unlikely(r != 0)) + return r; + offset = bo->mem.mm_node->start << PAGE_SHIFT; + /* this should not happen */ + if ((offset + size) > rdev->mc.visible_vram_size) + return -EINVAL; + } + } + return 0; } diff --git a/drivers/gpu/drm/radeon/radeon_object.h b/drivers/gpu/drm/radeon/radeon_object.h index 7ab43de..353998d 100644 --- a/drivers/gpu/drm/radeon/radeon_object.h +++ b/drivers/gpu/drm/radeon/radeon_object.h @@ -168,6 +168,6 @@ extern int radeon_bo_check_tiling(struct radeon_bo *bo, bool has_moved, bool force_drop); extern void radeon_bo_move_notify(struct ttm_buffer_object *bo, struct ttm_mem_reg *mem); -extern void radeon_bo_fault_reserve_notify(struct ttm_buffer_object *bo); +extern int radeon_bo_fault_reserve_notify(struct ttm_buffer_object *bo); extern int radeon_bo_get_surface_reg(struct radeon_bo *bo); #endif diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c index ba4724c..d2700b8 100644 --- a/drivers/gpu/drm/radeon/radeon_ttm.c +++ b/drivers/gpu/drm/radeon/radeon_ttm.c @@ -437,10 +437,53 @@ static int radeon_bo_move(struct ttm_buffer_object *bo, memcpy: r = ttm_bo_move_memcpy(bo, evict, no_wait_reserve, no_wait_gpu, new_mem); } - return r; } +static int radeon_ttm_io_mem_reserve(struct ttm_bo_device *bdev, struct ttm_mem_reg *mem) +{ + struct ttm_mem_type_manager *man = &bdev->man[mem->mem_type]; + struct radeon_device *rdev = radeon_get_rdev(bdev); + + mem->bus.offset = 0; + mem->bus.size = mem->num_pages << PAGE_SHIFT; + mem->bus.base = 0; + mem->bus.is_iomem = false; + if (!(man->flags & TTM_MEMTYPE_FLAG_MAPPABLE)) + return -EINVAL; + switch (mem->mem_type) { + case TTM_PL_SYSTEM: + /* system memory */ + return 0; + case TTM_PL_TT: +#if __OS_HAS_AGP + if (rdev->flags & RADEON_IS_AGP) { + /* RADEON_IS_AGP is set only if AGP is active */ + mem->bus.offset = mem->mm_node->start << PAGE_SHIFT; + mem->bus.base = rdev->mc.agp_base; + mem->bus.is_iomem = true; + } +#endif + return 0; + case TTM_PL_VRAM: + mem->bus.offset = mem->mm_node->start << PAGE_SHIFT; + /* check if it's visible */ + if ((mem->bus.offset + mem->bus.size) > rdev->mc.visible_vram_size) + return -EINVAL; + mem->bus.base = rdev->mc.aper_base; + mem->bus.is_iomem = true; + break; + default: + return -EINVAL; + } + return 0; +} + +static void radeon_ttm_io_mem_free(struct ttm_bo_device *bdev, struct ttm_mem_reg *mem) +{ + /* hopefully will be usefull soon */ +} + static int radeon_sync_obj_wait(void *sync_obj, void *sync_arg, bool lazy, bool interruptible) { @@ -481,6 +524,8 @@ static struct ttm_bo_driver radeon_bo_driver = { .sync_obj_ref = &radeon_sync_obj_ref, .move_notify = &radeon_bo_move_notify, .fault_reserve_notify = &radeon_bo_fault_reserve_notify, + .io_mem_reserve = &radeon_ttm_io_mem_reserve, + .io_mem_free = &radeon_ttm_io_mem_free, }; int radeon_ttm_init(struct radeon_device *rdev) -- 1.6.6.1 ------------------------------------------------------------------------------ Download Intel® Parallel Studio Eval Try the new software tools for yourself. Speed compiling, find bugs proactively, and fine-tune applications for parallel performance. See why Intel Parallel Studio got high marks during beta. http://p.sf.net/sfu/intel-sw-dev -- _______________________________________________ Dri-devel mailing list Dri-devel@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/dri-devel