aboutsummaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorChristian König <christian.koenig@amd.com>2021-12-21 21:00:48 +0100
committerThomas Hellström <thomas.hellstrom@linux.intel.com>2021-12-22 08:52:24 +0100
commit33654ef470a97f9fcb19abc7e7ef660ea37e3aed (patch)
treee0a78cb70bd5448b6f616efddd73bcc8b318d744
parentdrm/i915: Avoid using the i915_fence_array when collecting dependencies (diff)
downloadlinux-dev-33654ef470a97f9fcb19abc7e7ef660ea37e3aed.tar.xz
linux-dev-33654ef470a97f9fcb19abc7e7ef660ea37e3aed.zip
drm/i915: remove questionable fence optimization during copy
First of all as discussed multiple times now kernel copies *must* always wait for all fences in a BO before actually doing the copy. This is mandatory. Additional to that drop the handling when there can't be a shared slot allocated on the source BO and just properly return an error code. Otherwise this code path would only be tested under out of memory conditions. Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Thomas Hellström <thomas.hellstrom@linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20211221200050.436316-3-thomas.hellstrom@linux.intel.com Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
-rw-r--r--drivers/gpu/drm/i915/gem/i915_gem_ttm_move.c43
1 files changed, 14 insertions, 29 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 62a6fd2d127d..5dbaccf3f201 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_ttm_move.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm_move.c
@@ -195,19 +195,14 @@ static int i915_deps_add_dependency(struct i915_deps *deps,
}
static int i915_deps_add_resv(struct i915_deps *deps, struct dma_resv *resv,
- bool all, const bool no_excl,
const struct ttm_operation_ctx *ctx)
{
struct dma_resv_iter iter;
struct dma_fence *fence;
+ int ret;
dma_resv_assert_held(resv);
- dma_resv_for_each_fence(&iter, resv, all, fence) {
- int ret;
-
- if (no_excl && dma_resv_iter_is_exclusive(&iter))
- continue;
-
+ dma_resv_for_each_fence(&iter, resv, true, fence) {
ret = i915_deps_add_dependency(deps, fence, ctx);
if (ret)
return ret;
@@ -634,11 +629,7 @@ prev_deps(struct ttm_buffer_object *bo, struct ttm_operation_ctx *ctx,
ret = i915_deps_add_dependency(deps, bo->moving, ctx);
if (!ret)
- /*
- * TODO: Only await excl fence here, and shared fences before
- * signaling the migration fence.
- */
- ret = i915_deps_add_resv(deps, bo->base.resv, true, false, ctx);
+ ret = i915_deps_add_resv(deps, bo->base.resv, ctx);
return ret;
}
@@ -768,22 +759,21 @@ int i915_gem_obj_copy_ttm(struct drm_i915_gem_object *dst,
struct i915_refct_sgt *dst_rsgt;
struct dma_fence *copy_fence;
struct i915_deps deps;
- int ret, shared_err;
+ int ret;
assert_object_held(dst);
assert_object_held(src);
i915_deps_init(&deps, GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN);
- /*
- * 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.
- */
- 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 = i915_deps_add_resv(&deps, src_bo->base.resv,
- !!shared_err, false, &ctx);
+ ret = dma_resv_reserve_shared(src_bo->base.resv, 1);
+ if (ret)
+ return ret;
+
+ ret = i915_deps_add_resv(&deps, dst_bo->base.resv, &ctx);
+ if (ret)
+ return ret;
+
+ ret = i915_deps_add_resv(&deps, src_bo->base.resv, &ctx);
if (ret)
return ret;
@@ -798,12 +788,7 @@ int i915_gem_obj_copy_ttm(struct drm_i915_gem_object *dst,
return PTR_ERR_OR_ZERO(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_resv_add_shared_fence(src_bo->base.resv, copy_fence);
dma_fence_put(copy_fence);