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

1 files changed, 8 insertions, 5 deletions

diff --git a/src/gallium/include/pipe/p_state.h b/src/gallium/include/pipe/p_state.h
index 024d544e3ef..f6486f01dce 100644
--- a/src/gallium/include/pipe/p_state.h
+++ b/src/gallium/include/pipe/p_state.h
@@ -190,16 +190,19 @@ struct pipe_clip_state
 struct pipe_stream_output_info
 {
    unsigned num_outputs;
-   /** stride for an entire vertex, only used if all output_buffers are 0 */
-   unsigned stride;
+   /** stride for an entire vertex for each buffer in dwords */
+   unsigned stride[PIPE_MAX_SO_BUFFERS];
+
    /**
     * Array of stream outputs, in the order they are to be written in.
     * Selected components are tightly packed into the output buffer.
     */
    struct {
-      unsigned register_index:8; /**< 0 to PIPE_MAX_SHADER_OUTPUTS */
-      unsigned register_mask:4;  /**< TGSI_WRITEMASK_x */
-      unsigned output_buffer:4;  /**< 0 to PIPE_MAX_SO_BUFFERS */
+      unsigned register_index:8;  /**< 0 to PIPE_MAX_SHADER_OUTPUTS */
+      unsigned start_component:2; /** 0 to 3 */
+      unsigned num_components:3;  /** 1 to 4 */
+      unsigned output_buffer:3;   /**< 0 to PIPE_MAX_SO_BUFFERS */
+      unsigned dst_offset:16;     /**< offset into the buffer in dwords */
    } output[PIPE_MAX_SHADER_OUTPUTS];
 };