etnaviv: Do GC3000 resolve-in-place when possible

If an RS blit is done with source exactly the same as destination, and
the hardware supports this, do an in-place resolve. This only fills in
tiles that have not been rendered to using information from the TS.

This is the same as the blob does and potentially saves significant
bandwidth when doing i.MX6qp scanout using PRE, and when rendering to
textures (though here using sampler TS would be even better).

Signed-off-by: Wladimir J. van der Laan <laanwj@gmail.com>
Reviewed-by: Lucas Stach <l.stach@pengutronix.de>

4 files changed, 25 insertions, 4 deletions

diff --git a/src/gallium/drivers/etnaviv/etnaviv_clear_blit.c b/src/gallium/drivers/etnaviv/etnaviv_clear_blit.c
index c85ada9266..c62287b133 100644
--- a/src/gallium/drivers/etnaviv/etnaviv_clear_blit.c
+++ b/src/gallium/drivers/etnaviv/etnaviv_clear_blit.c
@@ -591,6 +591,7 @@ etna_try_rs_blit(struct pipe_context *pctx,
       .source = src->bo,
       .source_offset = src_offset,
       .source_stride = src_lev->stride,
+      .source_padded_width = src_lev->padded_width,
       .source_padded_height = src_lev->padded_height,
       .dest_format = translate_rs_format(dst_format),
       .dest_tiling = dst->layout,
diff --git a/src/gallium/drivers/etnaviv/etnaviv_emit.c b/src/gallium/drivers/etnaviv/etnaviv_emit.c
index c2117d563d..707b1e7349 100644
--- a/src/gallium/drivers/etnaviv/etnaviv_emit.c
+++ b/src/gallium/drivers/etnaviv/etnaviv_emit.c
@@ -173,7 +173,14 @@ etna_submit_rs_state(struct etna_context *ctx,
 
    ctx->stats.rs_operations++;
 
-   if (screen->specs.pixel_pipes == 1) {
+   if (cs->RS_KICKER_INPLACE) {
+      etna_cmd_stream_reserve(stream, 6);
+      etna_coalesce_start(stream, &coalesce);
+      /* 0/1 */ EMIT_STATE(RS_EXTRA_CONFIG, cs->RS_EXTRA_CONFIG);
+      /* 2/3 */ EMIT_STATE(RS_SOURCE_STRIDE, cs->RS_SOURCE_STRIDE);
+      /* 4/5 */ EMIT_STATE(RS_KICKER_INPLACE, cs->RS_KICKER_INPLACE);
+      etna_coalesce_end(stream, &coalesce);
+   } else if (screen->specs.pixel_pipes == 1) {
       etna_cmd_stream_reserve(stream, 22);
       etna_coalesce_start(stream, &coalesce);
       /* 0/1 */ EMIT_STATE(RS_CONFIG, cs->RS_CONFIG);
diff --git a/src/gallium/drivers/etnaviv/etnaviv_rs.c b/src/gallium/drivers/etnaviv/etnaviv_rs.c
index 5c108a6c7a..c9072c2645 100644
--- a/src/gallium/drivers/etnaviv/etnaviv_rs.c
+++ b/src/gallium/drivers/etnaviv/etnaviv_rs.c
@@ -118,10 +118,21 @@ etna_compile_rs_state(struct etna_context *ctx, struct compiled_rs_state *cs,
    cs->RS_FILL_VALUE[3] = rs->clear_value[3];
    cs->RS_EXTRA_CONFIG = VIVS_RS_EXTRA_CONFIG_AA(rs->aa) |
                          VIVS_RS_EXTRA_CONFIG_ENDIAN(rs->endian_mode);
-   /* TODO: cs->RS_UNK016B0 = s->size / 64 ?
-    * The blob does this consistently but there seems to be no currently supported
-    * model that needs it.
+
+   /* If source the same as destination, and the hardware supports this,
+    * do an in-place resolve to fill in unrendered tiles.
     */
+   if (ctx->specs.single_buffer && rs->source == rs->dest &&
+         rs->source_offset == rs->dest_offset &&
+         rs->source_format == rs->dest_format &&
+         rs->source_tiling == rs->dest_tiling &&
+         rs->source_stride == rs->dest_stride &&
+         !rs->downsample_x && !rs->downsample_y &&
+         !rs->swap_rb && !rs->flip &&
+         !rs->clear_mode && rs->source_padded_width) {
+      /* Total number of tiles (same as for autodisable) */
+      cs->RS_KICKER_INPLACE = rs->source_padded_width * rs->source_padded_height / 16;
+   }
 }
 
 void
diff --git a/src/gallium/drivers/etnaviv/etnaviv_rs.h b/src/gallium/drivers/etnaviv/etnaviv_rs.h
index ec5b659ccd..171d3fa009 100644
--- a/src/gallium/drivers/etnaviv/etnaviv_rs.h
+++ b/src/gallium/drivers/etnaviv/etnaviv_rs.h
@@ -43,6 +43,7 @@ struct rs_state {
    struct etna_bo *source;
    uint32_t source_offset;
    uint32_t source_stride;
+   uint32_t source_padded_width; /* total padded width (only needed for source) */
    uint32_t source_padded_height; /* total padded height */
    struct etna_bo *dest;
    uint32_t dest_offset;
@@ -69,6 +70,7 @@ struct compiled_rs_state {
    uint32_t RS_FILL_VALUE[4];
    uint32_t RS_EXTRA_CONFIG;
    uint32_t RS_PIPE_OFFSET[2];
+   uint32_t RS_KICKER_INPLACE; /* Set if source is destination */
 
    struct etna_reloc source[2];
    struct etna_reloc dest[2];