r600g,radeonsi: Consolidate logic for short-circuiting flushes

Fixes radeonsi emitting command streams to the kernel even when there
have been no draw calls before a flush, potentially powering up the GPU
needlessly.

Incidentally, this also cuts the runtime of piglit gpu.py in about half
on my Kaveri system, probably because an X11 client going away no longer
always results in a command stream being submitted to the kernel via
glamor.

Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=65761
Cc: "10.1" mesa-stable@lists.freedesktop.org
Reviewed-by: Marek Olšák <marek.olsak@amd.com>

6 files changed, 8 insertions, 6 deletions

diff --git a/src/gallium/drivers/r600/r600_hw_context.c b/src/gallium/drivers/r600/r600_hw_context.c
index dc3c221..ef077b2 100644
--- a/src/gallium/drivers/r600/r600_hw_context.c
+++ b/src/gallium/drivers/r600/r600_hw_context.c
@@ -355,7 +355,7 @@ void r600_begin_new_cs(struct r600_context *ctx)
 	ctx->last_primitive_type = -1;
 	ctx->last_start_instance = -1;
 
-	ctx->initial_gfx_cs_size = ctx->b.rings.gfx.cs->cdw;
+	ctx->b.initial_gfx_cs_size = ctx->b.rings.gfx.cs->cdw;
 }
 
 /* The max number of bytes to copy per packet. */
diff --git a/src/gallium/drivers/r600/r600_pipe.c b/src/gallium/drivers/r600/r600_pipe.c
index 8ea192a..0f75a53 100644
--- a/src/gallium/drivers/r600/r600_pipe.c
+++ b/src/gallium/drivers/r600/r600_pipe.c
@@ -74,7 +74,7 @@ static void r600_flush(struct pipe_context *ctx, unsigned flags)
 	unsigned render_cond_mode = 0;
 	boolean render_cond_cond = FALSE;
 
-	if (rctx->b.rings.gfx.cs->cdw == rctx->initial_gfx_cs_size)
+	if (rctx->b.rings.gfx.cs->cdw == rctx->b.initial_gfx_cs_size)
 		return;
 
 	rctx->b.rings.gfx.flushing = true;
@@ -95,7 +95,7 @@ static void r600_flush(struct pipe_context *ctx, unsigned flags)
 		ctx->render_condition(ctx, render_cond, render_cond_cond, render_cond_mode);
 	}
 
-	rctx->initial_gfx_cs_size = rctx->b.rings.gfx.cs->cdw;
+	rctx->b.initial_gfx_cs_size = rctx->b.rings.gfx.cs->cdw;
 }
 
 static void r600_flush_from_st(struct pipe_context *ctx,
diff --git a/src/gallium/drivers/r600/r600_pipe.h b/src/gallium/drivers/r600/r600_pipe.h
index 15052da..83b0e4f 100644
--- a/src/gallium/drivers/r600/r600_pipe.h
+++ b/src/gallium/drivers/r600/r600_pipe.h
@@ -377,7 +377,6 @@ struct r600_context {
 	struct r600_screen		*screen;
 	struct blitter_context		*blitter;
 	struct u_suballocator		*allocator_fetch_shader;
-	unsigned			initial_gfx_cs_size;
 
 	/* Hardware info. */
 	boolean				has_vertex_cache;
diff --git a/src/gallium/drivers/radeon/r600_buffer_common.c b/src/gallium/drivers/radeon/r600_buffer_common.c
index 068141c..e75b337 100644
--- a/src/gallium/drivers/radeon/r600_buffer_common.c
+++ b/src/gallium/drivers/radeon/r600_buffer_common.c
@@ -60,7 +60,7 @@ void *r600_buffer_map_sync_with_rings(struct r600_common_context *ctx,
 		rusage = RADEON_USAGE_WRITE;
 	}
 
-	if (ctx->rings.gfx.cs->cdw &&
+	if (ctx->rings.gfx.cs->cdw != ctx->initial_gfx_cs_size &&
 	    ctx->ws->cs_is_buffer_referenced(ctx->rings.gfx.cs,
 					     resource->cs_buf, rusage)) {
 		if (usage & PIPE_TRANSFER_DONTBLOCK) {
diff --git a/src/gallium/drivers/radeon/r600_pipe_common.h b/src/gallium/drivers/radeon/r600_pipe_common.h
index 2fbc6a3..d604f65 100644
--- a/src/gallium/drivers/radeon/r600_pipe_common.h
+++ b/src/gallium/drivers/radeon/r600_pipe_common.h
@@ -241,6 +241,7 @@ struct r600_common_context {
 	enum radeon_family		family;
 	enum chip_class			chip_class;
 	struct r600_rings		rings;
+	unsigned			initial_gfx_cs_size;
 
 	struct u_upload_mgr		*uploader;
 	struct u_suballocator		*allocator_so_filled_size;
diff --git a/src/gallium/drivers/radeonsi/si_hw_context.c b/src/gallium/drivers/radeonsi/si_hw_context.c
index 7e40255..3437f59 100644
--- a/src/gallium/drivers/radeonsi/si_hw_context.c
+++ b/src/gallium/drivers/radeonsi/si_hw_context.c
@@ -81,7 +81,7 @@ void si_context_flush(struct si_context *ctx, unsigned flags)
 {
 	struct radeon_winsys_cs *cs = ctx->b.rings.gfx.cs;
 
-	if (!cs->cdw)
+	if (cs->cdw == ctx->b.initial_gfx_cs_size)
 		return;
 
 	/* suspend queries */
@@ -177,6 +177,8 @@ void si_begin_new_cs(struct si_context *ctx)
 	}
 
 	si_all_descriptors_begin_new_cs(ctx);
+
+	ctx->b.initial_gfx_cs_size = ctx->b.rings.gfx.cs->cdw;
 }
 
 #if SI_TRACE_CS