nv50: wait on the buf's fence before sticking it into pushbuf

This resolves some rendering issues in source games.
See https://bugs.freedesktop.org/show_bug.cgi?id=64323

Signed-off-by: Ilia Mirkin <[email protected]>
Cc: "9.2 10.0" <[email protected]>
(cherry picked from commit 0e5bf8565106833e1a678ebdae81fdf1657391c9)

2 files changed, 12 insertions, 0 deletions

diff --git a/src/gallium/drivers/nouveau/nouveau_buffer.c b/src/gallium/drivers/nouveau/nouveau_buffer.c
index 3e0404983fe..95905a8776f 100644
--- a/src/gallium/drivers/nouveau/nouveau_buffer.c
+++ b/src/gallium/drivers/nouveau/nouveau_buffer.c
@@ -205,6 +205,9 @@ nouveau_transfer_write(struct nouveau_context *nv, struct nouveau_transfer *tx,
                   base, size / 4, (const uint32_t *)data);
    else
       nv->push_data(nv, buf->bo, buf->offset + base, buf->domain, size, data);
+
+   nouveau_fence_ref(nv->screen->fence.current, &buf->fence);
+   nouveau_fence_ref(nv->screen->fence.current, &buf->fence_wr);
 }
 
 
diff --git a/src/gallium/drivers/nouveau/nv50/nv50_vbo.c b/src/gallium/drivers/nouveau/nv50/nv50_vbo.c
index c6162b5f415..947c67d6a75 100644
--- a/src/gallium/drivers/nouveau/nv50/nv50_vbo.c
+++ b/src/gallium/drivers/nouveau/nv50/nv50_vbo.c
@@ -597,6 +597,15 @@ nv50_draw_elements(struct nv50_context *nv50, boolean shorten,
 
       assert(nouveau_resource_mapped_by_gpu(nv50->idxbuf.buffer));
 
+      /* This shouldn't have to be here. The going theory is that the buffer
+       * is being filled in by PGRAPH, and it's not done yet by the time it
+       * gets submitted to PFIFO, which in turn starts immediately prefetching
+       * the not-yet-written data. Ideally this wait would only happen on
+       * pushbuf submit, but it's probably not a big performance difference.
+       */
+      if (buf->fence_wr && !nouveau_fence_signalled(buf->fence_wr))
+         nouveau_fence_wait(buf->fence_wr);
+
       while (instance_count--) {
          BEGIN_NV04(push, NV50_3D(VERTEX_BEGIN_GL), 1);
          PUSH_DATA (push, prim);