gallium: improve the pipe_stream_output_info struct (v2)

There are 3 changes:

1) stride is specified for each buffer, not just one, so that drivers don't
   have to derive it from the outputs

2) new per-output property dst_offset, which specifies the offset
   into the buffer in dwords where the output should be stored,
   so that drivers don't have to compute the offsets manually;
   this will also be useful for gl_SkipComponents
   from ARB_transform_feedback3

3) register_mask is removed, instead, there is start_component
   and num_components; register_mask with non-consecutive 1s
   doesn't make much sense (some hardware cannot do packing of components)

Christoph Bumiller: fixed nvc0.

v2: resolve merge conflicts in Draw and clean it up

3 files changed, 14 insertions, 83 deletions

diff --git a/src/gallium/auxiliary/draw/draw_pt_so_emit.c b/src/gallium/auxiliary/draw/draw_pt_so_emit.c
index 466f46abab3..ecf287f9128 100644
--- a/src/gallium/auxiliary/draw/draw_pt_so_emit.c
+++ b/src/gallium/auxiliary/draw/draw_pt_so_emit.c
@@ -79,72 +79,6 @@ void draw_pt_so_emit_prepare(struct pt_so_emit *emit)
    draw_do_flush( draw, DRAW_FLUSH_BACKEND );
 }
 
-static boolean
-is_component_writable(unsigned mask,
-                      unsigned compo)
-{
-   switch (mask) {
-   case TGSI_WRITEMASK_NONE:
-      return FALSE;
-   case TGSI_WRITEMASK_X:
-      return compo == 0;
-   case TGSI_WRITEMASK_Y:
-      return compo == 1;
-   case TGSI_WRITEMASK_XY:
-      return compo == 0 || compo == 1;
-   case TGSI_WRITEMASK_Z:
-      return compo == 2;
-   case TGSI_WRITEMASK_XZ:
-      return compo == 0 || compo == 2;
-   case TGSI_WRITEMASK_YZ:
-      return compo == 1 || compo == 2;
-   case TGSI_WRITEMASK_XYZ:
-      return compo == 0 || compo == 1 || compo == 2;
-   case TGSI_WRITEMASK_W:
-      return compo == 3;
-   case TGSI_WRITEMASK_XW:
-      return compo == 0 || compo == 3;
-   case TGSI_WRITEMASK_YW:
-      return compo == 1 || compo == 3;
-   case TGSI_WRITEMASK_XYW:
-      return compo == 0 || compo == 1 || compo == 3;
-   case TGSI_WRITEMASK_ZW:
-      return compo == 2 || compo == 3;
-   case TGSI_WRITEMASK_XZW:
-      return compo == 0 || compo == 1 || compo == 3;
-   case TGSI_WRITEMASK_YZW:
-      return compo == 1 || compo == 2 || compo == 4;
-   case TGSI_WRITEMASK_XYZW:
-      return compo < 4;
-   default:
-      debug_assert(!"Unknown writemask in stream out");
-      return compo < 4;
-   }
-}
-
-static INLINE int mask_num_comps(int register_mask)
-{
-   int comps = 0;
-   switch (register_mask) {
-   case TGSI_WRITEMASK_XYZW:
-      comps = 4;
-      break;
-   case TGSI_WRITEMASK_XYZ:
-      comps = 3;
-      break;
-   case TGSI_WRITEMASK_XY:
-      comps = 2;
-      break;
-   case TGSI_WRITEMASK_X:
-      comps = 1;
-      break;
-   default:
-      assert(0);
-      break;
-   }
-   return comps;
-}
-
 static void so_emit_prim(struct pt_so_emit *so,
                          unsigned *indices,
                          unsigned num_vertices)
@@ -170,14 +104,14 @@ static void so_emit_prim(struct pt_so_emit *so,
    /* check have we space to emit prim first - if not don't do anything */
    for (i = 0; i < num_vertices; ++i) {
       for (slot = 0; slot < state->num_outputs; ++slot) {
-         unsigned writemask = state->output[slot].register_mask;
+         unsigned num_comps = state->output[slot].num_components;
          int ob = state->output[slot].output_buffer;
 
-         if ((buffer_total_bytes[ob] + mask_num_comps(writemask) * sizeof(float)) >
+         if ((buffer_total_bytes[ob] + num_comps * sizeof(float)) >
              draw->so.targets[ob]->target.buffer_size) {
             return;
          }
-         buffer_total_bytes[ob] += mask_num_comps(writemask) * sizeof(float);
+         buffer_total_bytes[ob] += num_comps * sizeof(float);
       }
    }
 
@@ -190,21 +124,16 @@ static void so_emit_prim(struct pt_so_emit *so,
 
       for (slot = 0; slot < state->num_outputs; ++slot) {
          unsigned idx = state->output[slot].register_index;
-         unsigned writemask = state->output[slot].register_mask;
-         unsigned written_compos = 0;
-         unsigned compo;
+         unsigned start_comp = state->output[slot].start_component;
+         unsigned num_comps = state->output[slot].num_components;
          int ob = state->output[slot].output_buffer;
 
          buffer = (float *)((char *)draw->so.targets[ob]->mapping +
                             draw->so.targets[ob]->target.buffer_offset +
                             draw->so.targets[ob]->internal_offset);
-         for (compo = 0; compo < 4; ++compo) {
-            if (is_component_writable(writemask, compo)) {
-               buffer[written_compos++] = input[idx][compo];
-            }
-         }
-         draw->so.targets[ob]->internal_offset += written_compos * sizeof(float);
-         total_written_compos += written_compos;
+         memcpy(buffer, &input[idx][start_comp], num_comps * sizeof(float));
+         draw->so.targets[ob]->internal_offset += num_comps * sizeof(float);
+         total_written_compos += num_comps;
       }
    }
    so->emitted_vertices += num_vertices;
diff --git a/src/gallium/auxiliary/util/u_blitter.c b/src/gallium/auxiliary/util/u_blitter.c
index 59940d9cbe7..6a32de619ef 100644
--- a/src/gallium/auxiliary/util/u_blitter.c
+++ b/src/gallium/auxiliary/util/u_blitter.c
@@ -263,8 +263,8 @@ struct blitter_context *util_blitter_create(struct pipe_context *pipe)
 
       memset(&so, 0, sizeof(so));
       so.num_outputs = 1;
-      so.output[0].register_mask = TGSI_WRITEMASK_XYZW;
-      so.stride = 4;
+      so.output[0].num_components = 4;
+      so.stride[0] = 4;
 
       ctx->vs_pos_only =
          util_make_vertex_passthrough_shader_with_so(pipe, 1, semantic_names,
diff --git a/src/gallium/auxiliary/util/u_dump_state.c b/src/gallium/auxiliary/util/u_dump_state.c
index c728bc4021c..c346a0ba5ca 100644
--- a/src/gallium/auxiliary/util/u_dump_state.c
+++ b/src/gallium/auxiliary/util/u_dump_state.c
@@ -444,13 +444,15 @@ util_dump_shader_state(FILE *stream, const struct pipe_shader_state *state)
    util_dump_member_begin(stream, "stream_output");
    util_dump_struct_begin(stream, "pipe_stream_output_info");
    util_dump_member(stream, uint, &state->stream_output, num_outputs);
-   util_dump_member(stream, uint, &state->stream_output, stride);
+   util_dump_array(stream, uint, state->stream_output.stride,
+                   Elements(state->stream_output.stride));
    util_dump_array_begin(stream);
    for(i = 0; i < state->stream_output.num_outputs; ++i) {
       util_dump_elem_begin(stream);
       util_dump_struct_begin(stream, ""); /* anonymous */
       util_dump_member(stream, uint, &state->stream_output.output[i], register_index);
-      util_dump_member(stream, uint, &state->stream_output.output[i], register_mask);
+      util_dump_member(stream, uint, &state->stream_output.output[i], start_component);
+      util_dump_member(stream, uint, &state->stream_output.output[i], num_components);
       util_dump_member(stream, uint, &state->stream_output.output[i], output_buffer);
       util_dump_struct_end(stream);
       util_dump_elem_end(stream);