virgl: don't mark buffers as unclean after a write

We can mark the buffer unclean if it's ever bound as a TBO,
SSBO, ABO, or image.

This improves

dEQP-GLES3.performance.buffer.data_upload.function_call.map_buffer_range.new_specified_buffer.flag_write_full.stream_draw

from 9.58 MB/s to 451.17 MB/s.

v2: Track buffer cleanliness as a function of bindings (Ilia).
v3: virgl_modify_clean --> virgl_dirty_res (Erik)

Tested-By: Gert Wollny <gert.wollny@collabora.com>
Reviewed-by: Erik Faye-Lund <erik.faye-lund@collabora.com>
(cherry picked from commit 89b4798c0619a2ba99046d5ad36f0e6851625f7a)

With this and previous two patches, the performance of virgl on top of
a r600 (AMD 6870 HD) host improves as follows:

         | FPS avg |  Score
--------------------------------
 before  |   8.2   |   343
 after   |  21.9   |   916

         | FPS avg |  Score
--------------------------------
 before  |  13.2   |   333
 after   |  32.3   |   790

2 files changed, 10 insertions, 1 deletions

diff --git a/src/gallium/drivers/virgl/virgl_buffer.c b/src/gallium/drivers/virgl/virgl_buffer.c
index 88a22b56f9a..f72c93f4995 100644
--- a/src/gallium/drivers/virgl/virgl_buffer.c
+++ b/src/gallium/drivers/virgl/virgl_buffer.c
@@ -106,7 +106,6 @@ static void virgl_buffer_transfer_unmap(struct pipe_context *ctx,
    if (trans->base.usage & PIPE_TRANSFER_WRITE) {
       if (!(transfer->usage & PIPE_TRANSFER_FLUSH_EXPLICIT)) {
          struct virgl_screen *vs = virgl_screen(ctx->screen);
-         vbuf->base.clean = FALSE;
          vctx->num_transfers++;
          vs->vws->transfer_put(vs->vws, vbuf->base.hw_res,
                                &transfer->box, trans->base.stride, trans->base.layer_stride, trans->offset, transfer->level);
diff --git a/src/gallium/drivers/virgl/virgl_encode.c b/src/gallium/drivers/virgl/virgl_encode.c
index e86d0711a57..ee2764d74ea 100644
--- a/src/gallium/drivers/virgl/virgl_encode.c
+++ b/src/gallium/drivers/virgl/virgl_encode.c
@@ -61,6 +61,12 @@ static void virgl_encoder_write_res(struct virgl_context *ctx,
    }
 }
 
+static void virgl_dirty_res(struct virgl_resource *res)
+{
+   if (res)
+      res->clean = FALSE;
+}
+
 int virgl_encode_bind_object(struct virgl_context *ctx,
                             uint32_t handle, uint32_t object)
 {
@@ -615,6 +621,7 @@ int virgl_encode_sampler_view(struct virgl_context *ctx,
    if (res->u.b.target == PIPE_BUFFER) {
       virgl_encoder_write_dword(ctx->cbuf, state->u.buf.offset / elem_size);
       virgl_encoder_write_dword(ctx->cbuf, (state->u.buf.offset + state->u.buf.size) / elem_size - 1);
+      virgl_dirty_res(res);
    } else {
       virgl_encoder_write_dword(ctx->cbuf, state->u.tex.first_layer | state->u.tex.last_layer << 16);
       virgl_encoder_write_dword(ctx->cbuf, state->u.tex.first_level | state->u.tex.last_level << 8);
@@ -949,6 +956,7 @@ int virgl_encode_set_shader_buffers(struct virgl_context *ctx,
          virgl_encoder_write_dword(ctx->cbuf, buffers[i].buffer_offset);
          virgl_encoder_write_dword(ctx->cbuf, buffers[i].buffer_size);
          virgl_encoder_write_res(ctx, res);
+         virgl_dirty_res(res);
       } else {
          virgl_encoder_write_dword(ctx->cbuf, 0);
          virgl_encoder_write_dword(ctx->cbuf, 0);
@@ -972,6 +980,7 @@ int virgl_encode_set_hw_atomic_buffers(struct virgl_context *ctx,
          virgl_encoder_write_dword(ctx->cbuf, buffers[i].buffer_offset);
          virgl_encoder_write_dword(ctx->cbuf, buffers[i].buffer_size);
          virgl_encoder_write_res(ctx, res);
+         virgl_dirty_res(res);
       } else {
          virgl_encoder_write_dword(ctx->cbuf, 0);
          virgl_encoder_write_dword(ctx->cbuf, 0);
@@ -999,6 +1008,7 @@ int virgl_encode_set_shader_images(struct virgl_context *ctx,
          virgl_encoder_write_dword(ctx->cbuf, images[i].u.buf.offset);
          virgl_encoder_write_dword(ctx->cbuf, images[i].u.buf.size);
          virgl_encoder_write_res(ctx, res);
+         virgl_dirty_res(res);
       } else {
          virgl_encoder_write_dword(ctx->cbuf, 0);
          virgl_encoder_write_dword(ctx->cbuf, 0);