drm/vc4: Fix races when the CS reads from render targets.
With the introduction of bin/render pipelining, the previous job may
not be completed when we start binning the next one. If the previous
job wrote our VBO, IB, or CS textures, then the binning stage might
get stale or uninitialized results.
Fixes the major rendering failure in glmark2 -b terrain.
Signed-off-by: Eric Anholt <eric@anholt.net>
Fixes: ca26d28bbaa3 ("drm/vc4: improve throughput by pipelining binning and rendering jobs")
Cc: stable@vger.kernel.org
diff --git a/drivers/gpu/drm/vc4/vc4_validate.c b/drivers/gpu/drm/vc4/vc4_validate.c
index 9ce1d0a..26503e3 100644
--- a/drivers/gpu/drm/vc4/vc4_validate.c
+++ b/drivers/gpu/drm/vc4/vc4_validate.c
@@ -267,6 +267,9 @@
if (!ib)
return -EINVAL;
+ exec->bin_dep_seqno = max(exec->bin_dep_seqno,
+ to_vc4_bo(&ib->base)->write_seqno);
+
if (offset > ib->base.size ||
(ib->base.size - offset) / index_size < length) {
DRM_ERROR("IB access overflow (%d + %d*%d > %zd)\n",
@@ -555,8 +558,7 @@
reloc_tex(struct vc4_exec_info *exec,
void *uniform_data_u,
struct vc4_texture_sample_info *sample,
- uint32_t texture_handle_index)
-
+ uint32_t texture_handle_index, bool is_cs)
{
struct drm_gem_cma_object *tex;
uint32_t p0 = *(uint32_t *)(uniform_data_u + sample->p_offset[0]);
@@ -714,6 +716,11 @@
*validated_p0 = tex->paddr + p0;
+ if (is_cs) {
+ exec->bin_dep_seqno = max(exec->bin_dep_seqno,
+ to_vc4_bo(&tex->base)->write_seqno);
+ }
+
return true;
fail:
DRM_INFO("Texture p0 at %d: 0x%08x\n", sample->p_offset[0], p0);
@@ -835,7 +842,8 @@
if (!reloc_tex(exec,
uniform_data_u,
&validated_shader->texture_samples[tex],
- texture_handles_u[tex])) {
+ texture_handles_u[tex],
+ i == 2)) {
return -EINVAL;
}
}
@@ -867,6 +875,9 @@
uint32_t stride = *(uint8_t *)(pkt_u + o + 5);
uint32_t max_index;
+ exec->bin_dep_seqno = max(exec->bin_dep_seqno,
+ to_vc4_bo(&vbo->base)->write_seqno);
+
if (state->addr & 0x8)
stride |= (*(uint32_t *)(pkt_u + 100 + i * 4)) & ~0xff;