Update the copy function i915_gem_obj_copy_ttm() to be asynchronous for future users and update the only current user to sync the objects as needed after this function.
Signed-off-by: Thomas Hellström thomas.hellstrom@linux.intel.com --- drivers/gpu/drm/i915/gem/i915_gem_ttm_move.c | 40 ++++++++++++++------ drivers/gpu/drm/i915/gem/i915_gem_ttm_pm.c | 2 + 2 files changed, 30 insertions(+), 12 deletions(-)
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm_move.c b/drivers/gpu/drm/i915/gem/i915_gem_ttm_move.c index 38623fde170a..d377c86232f1 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_ttm_move.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm_move.c @@ -822,33 +822,49 @@ int i915_gem_obj_copy_ttm(struct drm_i915_gem_object *dst, .interruptible = intr, }; struct i915_refct_sgt *dst_rsgt; - struct dma_fence *copy_fence; - int ret; + struct dma_fence *copy_fence, *dep_fence; + struct i915_deps deps; + int ret, shared_err;
assert_object_held(dst); assert_object_held(src); + i915_deps_init(&deps, GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN);
/* - * Sync for now. This will change with async moves. + * We plan to add a shared fence only for the source. If that + * fails, we await all source fences before commencing + * the copy instead of only the exclusive. */ - ret = ttm_bo_wait_ctx(dst_bo, &ctx); + shared_err = dma_resv_reserve_shared(src_bo->base.resv, 1); + ret = i915_deps_add_resv(&deps, dst_bo->base.resv, true, false, &ctx); if (!ret) - ret = ttm_bo_wait_ctx(src_bo, &ctx); + ret = i915_deps_add_resv(&deps, src_bo->base.resv, + !!shared_err, false, &ctx); if (ret) return ret;
+ dep_fence = i915_deps_to_fence(&deps, &ctx); + if (IS_ERR(dep_fence)) + return PTR_ERR(dep_fence); + dst_rsgt = i915_ttm_resource_get_st(dst, dst_bo->resource); copy_fence = __i915_ttm_move(src_bo, false, dst_bo->resource, - dst_bo->ttm, dst_rsgt, allow_accel, NULL); + dst_bo->ttm, dst_rsgt, allow_accel, + dep_fence);
i915_refct_sgt_put(dst_rsgt); - if (IS_ERR(copy_fence)) - return PTR_ERR(copy_fence); + if (IS_ERR_OR_NULL(copy_fence)) + return PTR_ERR_OR_ZERO(copy_fence);
- if (copy_fence) { - dma_fence_wait(copy_fence, false); - dma_fence_put(copy_fence); - } + dma_resv_add_excl_fence(dst_bo->base.resv, copy_fence); + + /* If we failed to reserve a shared slot, add an exclusive fence */ + if (shared_err) + dma_resv_add_excl_fence(src_bo->base.resv, copy_fence); + else + dma_resv_add_shared_fence(src_bo->base.resv, copy_fence); + + dma_fence_put(copy_fence);
return 0; } diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm_pm.c b/drivers/gpu/drm/i915/gem/i915_gem_ttm_pm.c index 60d10ab55d1e..9aad84059d56 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_ttm_pm.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm_pm.c @@ -80,6 +80,7 @@ static int i915_ttm_backup(struct i915_gem_apply_to_region *apply,
err = i915_gem_obj_copy_ttm(backup, obj, pm_apply->allow_gpu, false); GEM_WARN_ON(err); + ttm_bo_wait_ctx(backup_bo, &ctx);
obj->ttm.backup = backup; return 0; @@ -170,6 +171,7 @@ static int i915_ttm_restore(struct i915_gem_apply_to_region *apply, err = i915_gem_obj_copy_ttm(obj, backup, pm_apply->allow_gpu, false); GEM_WARN_ON(err); + ttm_bo_wait_ctx(backup_bo, &ctx);
obj->ttm.backup = NULL; err = 0;