freedreno: add basic query support

Add for now some simple/basic query support (ie. things not actually
requiring the GPU).  Might change around a bit when I actually add
GPU queries, but for now this enables some useful performance info
in the GALLIUM_HUD.  For example:

  GALLIUM_HUD=fps+batches+batches-sysmem+batches-gmem+restores,draw-calls

The driver specific specific queries are:

  + draw-calls
  + batches - number of batches per second, sum of batches-sysmem
    plus batches-gmem
  + batches-gmem - render a set of tiles in GMEM, for each tile
    (optionally) system mem -> gmem (restore), plus N draws,
    plus gmem -> system mem (resolve) per second
  + batches-sysmem - N draws to system memory (GMEM bypass) per
    second
  + restores - number of GMEM batches that required restore per
    second

Ideally for GMEM rendering, you want batches-gmem to equal fps.  If
the app is doing something that triggers multiple passes (ie. requires
extra round trip gmem <-> system memory) then the # of batches per
second will go up relative to fps.

Signed-off-by: Rob Clark <robclark@freedesktop.org>

1 files changed, 7 insertions, 0 deletions

diff --git a/src/gallium/drivers/freedreno/freedreno_gmem.c b/src/gallium/drivers/freedreno/freedreno_gmem.c
index 0270538a3d0..6a55aa4c133 100644
--- a/src/gallium/drivers/freedreno/freedreno_gmem.c
+++ b/src/gallium/drivers/freedreno/freedreno_gmem.c
@@ -260,6 +260,9 @@ render_tiles(struct fd_context *ctx)
 
 	ctx->emit_tile_init(ctx);
 
+	if (ctx->restore)
+		ctx->stats.batch_restore++;
+
 	for (i = 0; i < (gmem->nbins_x * gmem->nbins_y); i++) {
 		struct fd_tile *tile = &ctx->tile[i];
 
@@ -311,11 +314,14 @@ fd_gmem_render_tiles(struct pipe_context *pctx)
 	fd_ringmarker_mark(ctx->draw_end);
 	fd_ringmarker_mark(ctx->binning_end);
 
+	ctx->stats.batch_total++;
+
 	if (sysmem) {
 		DBG("rendering sysmem (%s/%s)",
 			util_format_short_name(pipe_surface_format(pfb->cbufs[0])),
 			util_format_short_name(pipe_surface_format(pfb->zsbuf)));
 		render_sysmem(ctx);
+		ctx->stats.batch_sysmem++;
 	} else {
 		struct fd_gmem_stateobj *gmem = &ctx->gmem;
 		calculate_tiles(ctx);
@@ -323,6 +329,7 @@ fd_gmem_render_tiles(struct pipe_context *pctx)
 			util_format_short_name(pipe_surface_format(pfb->cbufs[0])),
 			util_format_short_name(pipe_surface_format(pfb->zsbuf)));
 		render_tiles(ctx);
+		ctx->stats.batch_gmem++;
 	}
 
 	/* GPU executes starting from tile cmds, which IB back to draw cmds: */