radeonsi: always use compute rings for clover on CI and newer (v2)

initialize all non-compute context functions to NULL.

v2: fix SI

11 files changed, 130 insertions, 75 deletions

diff --git a/src/gallium/drivers/radeonsi/si_blit.c b/src/gallium/drivers/radeonsi/si_blit.c
index bb8d1cbd12d..f39cb5d143f 100644
--- a/src/gallium/drivers/radeonsi/si_blit.c
+++ b/src/gallium/drivers/radeonsi/si_blit.c
@@ -1352,7 +1352,10 @@ static void si_flush_resource(struct pipe_context *ctx,
 
 void si_decompress_dcc(struct si_context *sctx, struct si_texture *tex)
 {
-	if (!tex->dcc_offset)
+	/* If graphics is disabled, we can't decompress DCC, but it shouldn't
+	 * be compressed either. The caller should simply discard it.
+	 */
+	if (!tex->dcc_offset || !sctx->has_graphics)
 		return;
 
 	si_blit_decompress_color(sctx, tex, 0, tex->buffer.b.b.last_level,
@@ -1363,7 +1366,10 @@ void si_decompress_dcc(struct si_context *sctx, struct si_texture *tex)
 void si_init_blit_functions(struct si_context *sctx)
 {
 	sctx->b.resource_copy_region = si_resource_copy_region;
-	sctx->b.blit = si_blit;
-	sctx->b.flush_resource = si_flush_resource;
-	sctx->b.generate_mipmap = si_generate_mipmap;
+
+	if (sctx->has_graphics) {
+		sctx->b.blit = si_blit;
+		sctx->b.flush_resource = si_flush_resource;
+		sctx->b.generate_mipmap = si_generate_mipmap;
+	}
 }
diff --git a/src/gallium/drivers/radeonsi/si_clear.c b/src/gallium/drivers/radeonsi/si_clear.c
index 9a00bb73b94..e1805f2a1c9 100644
--- a/src/gallium/drivers/radeonsi/si_clear.c
+++ b/src/gallium/drivers/radeonsi/si_clear.c
@@ -771,8 +771,11 @@ static void si_clear_texture(struct pipe_context *pipe,
 
 void si_init_clear_functions(struct si_context *sctx)
 {
-	sctx->b.clear = si_clear;
 	sctx->b.clear_render_target = si_clear_render_target;
-	sctx->b.clear_depth_stencil = si_clear_depth_stencil;
 	sctx->b.clear_texture = si_clear_texture;
+
+	if (sctx->has_graphics) {
+		sctx->b.clear = si_clear;
+		sctx->b.clear_depth_stencil = si_clear_depth_stencil;
+	}
 }
diff --git a/src/gallium/drivers/radeonsi/si_compute.c b/src/gallium/drivers/radeonsi/si_compute.c
index 1a62b3e0844..87addd53976 100644
--- a/src/gallium/drivers/radeonsi/si_compute.c
+++ b/src/gallium/drivers/radeonsi/si_compute.c
@@ -887,12 +887,14 @@ static void si_launch_grid(
 	    program->shader.compilation_failed)
 		return;
 
-	if (sctx->last_num_draw_calls != sctx->num_draw_calls) {
-		si_update_fb_dirtiness_after_rendering(sctx);
-		sctx->last_num_draw_calls = sctx->num_draw_calls;
-	}
+	if (sctx->has_graphics) {
+		if (sctx->last_num_draw_calls != sctx->num_draw_calls) {
+			si_update_fb_dirtiness_after_rendering(sctx);
+			sctx->last_num_draw_calls = sctx->num_draw_calls;
+		}
 
-	si_decompress_textures(sctx, 1 << PIPE_SHADER_COMPUTE);
+		si_decompress_textures(sctx, 1 << PIPE_SHADER_COMPUTE);
+	}
 
 	/* Add buffer sizes for memory checking in need_cs_space. */
 	si_context_add_resource_size(sctx, &program->shader.bo->b.b);
@@ -924,7 +926,8 @@ static void si_launch_grid(
 	si_upload_compute_shader_descriptors(sctx);
 	si_emit_compute_shader_pointers(sctx);
 
-	if (si_is_atom_dirty(sctx, &sctx->atoms.s.render_cond)) {
+	if (sctx->has_graphics &&
+	    si_is_atom_dirty(sctx, &sctx->atoms.s.render_cond)) {
 		sctx->atoms.s.render_cond.emit(sctx);
 		si_set_atom_dirty(sctx, &sctx->atoms.s.render_cond, false);
 	}
diff --git a/src/gallium/drivers/radeonsi/si_descriptors.c b/src/gallium/drivers/radeonsi/si_descriptors.c
index 21d4ca946d3..0f22c55723c 100644
--- a/src/gallium/drivers/radeonsi/si_descriptors.c
+++ b/src/gallium/drivers/radeonsi/si_descriptors.c
@@ -2647,8 +2647,10 @@ void si_all_resident_buffers_begin_new_cs(struct si_context *sctx)
 void si_init_all_descriptors(struct si_context *sctx)
 {
 	int i;
+	unsigned first_shader =
+		sctx->has_graphics ? 0 : PIPE_SHADER_COMPUTE;
 
-	for (i = 0; i < SI_NUM_SHADERS; i++) {
+	for (i = first_shader; i < SI_NUM_SHADERS; i++) {
 		bool is_2nd = sctx->chip_class >= GFX9 &&
 				     (i == PIPE_SHADER_TESS_CTRL ||
 				      i == PIPE_SHADER_GEOMETRY);
@@ -2721,7 +2723,6 @@ void si_init_all_descriptors(struct si_context *sctx)
 	sctx->b.bind_sampler_states = si_bind_sampler_states;
 	sctx->b.set_shader_images = si_set_shader_images;
 	sctx->b.set_constant_buffer = si_pipe_set_constant_buffer;
-	sctx->b.set_polygon_stipple = si_set_polygon_stipple;
 	sctx->b.set_shader_buffers = si_set_shader_buffers;
 	sctx->b.set_sampler_views = si_set_sampler_views;
 	sctx->b.create_texture_handle = si_create_texture_handle;
@@ -2731,6 +2732,11 @@ void si_init_all_descriptors(struct si_context *sctx)
 	sctx->b.delete_image_handle = si_delete_image_handle;
 	sctx->b.make_image_handle_resident = si_make_image_handle_resident;
 
+	if (!sctx->has_graphics)
+		return;
+
+	sctx->b.set_polygon_stipple = si_set_polygon_stipple;
+
 	/* Shader user data. */
 	sctx->atoms.s.shader_pointers.emit = si_emit_graphics_shader_pointers;
 
diff --git a/src/gallium/drivers/radeonsi/si_gfx_cs.c b/src/gallium/drivers/radeonsi/si_gfx_cs.c
index 13d5b5a959a..922fc560d74 100644
--- a/src/gallium/drivers/radeonsi/si_gfx_cs.c
+++ b/src/gallium/drivers/radeonsi/si_gfx_cs.c
@@ -140,13 +140,15 @@ void si_flush_gfx_cs(struct si_context *ctx, unsigned flags,
 	if (radeon_emitted(ctx->dma_cs, 0))
 		si_flush_dma_cs(ctx, flags, NULL);
 
-	if (!LIST_IS_EMPTY(&ctx->active_queries))
-		si_suspend_queries(ctx);
-
-	ctx->streamout.suspended = false;
-	if (ctx->streamout.begin_emitted) {
-		si_emit_streamout_end(ctx);
-		ctx->streamout.suspended = true;
+	if (ctx->has_graphics) {
+		if (!LIST_IS_EMPTY(&ctx->active_queries))
+			si_suspend_queries(ctx);
+
+		ctx->streamout.suspended = false;
+		if (ctx->streamout.begin_emitted) {
+			si_emit_streamout_end(ctx);
+			ctx->streamout.suspended = true;
+		}
 	}
 
 	/* Make sure CP DMA is idle at the end of IBs after L2 prefetches
@@ -246,6 +248,15 @@ void si_begin_new_gfx_cs(struct si_context *ctx)
 		      SI_CONTEXT_INV_GLOBAL_L2 |
 		      SI_CONTEXT_START_PIPELINE_STATS;
 
+	ctx->cs_shader_state.initialized = false;
+	si_all_descriptors_begin_new_cs(ctx);
+	si_all_resident_buffers_begin_new_cs(ctx);
+
+	if (!ctx->has_graphics) {
+		ctx->initial_gfx_cs_size = ctx->gfx_cs->current.cdw;
+		return;
+	}
+
 	/* set all valid group as dirty so they get reemited on
 	 * next draw command
 	 */
@@ -310,8 +321,6 @@ void si_begin_new_gfx_cs(struct si_context *ctx)
 	/* CLEAR_STATE disables all window rectangles. */
 	if (!has_clear_state || ctx->num_window_rectangles > 0)
 		si_mark_atom_dirty(ctx, &ctx->atoms.s.window_rectangles);
-	si_all_descriptors_begin_new_cs(ctx);
-	si_all_resident_buffers_begin_new_cs(ctx);
 
 	ctx->scissors.dirty_mask = (1 << SI_MAX_VIEWPORTS) - 1;
 	ctx->viewports.dirty_mask = (1 << SI_MAX_VIEWPORTS) - 1;
@@ -353,8 +362,6 @@ void si_begin_new_gfx_cs(struct si_context *ctx)
 	ctx->last_num_tcs_input_cp = -1;
 	ctx->last_ls_hs_config = -1; /* impossible value */
 
-	ctx->cs_shader_state.initialized = false;
-
 	if (has_clear_state) {
 		ctx->tracked_regs.reg_value[SI_TRACKED_DB_RENDER_CONTROL] = 0x00000000;
 		ctx->tracked_regs.reg_value[SI_TRACKED_DB_COUNT_CONTROL] = 0x00000000;
diff --git a/src/gallium/drivers/radeonsi/si_pipe.c b/src/gallium/drivers/radeonsi/si_pipe.c
index b965d9d64d4..9b1eab8284b 100644
--- a/src/gallium/drivers/radeonsi/si_pipe.c
+++ b/src/gallium/drivers/radeonsi/si_pipe.c
@@ -389,16 +389,15 @@ static struct pipe_context *si_create_context(struct pipe_screen *screen,
 	if (!sctx)
 		return NULL;
 
+	sctx->has_graphics = sscreen->info.chip_class == SI ||
+			     !(flags & PIPE_CONTEXT_COMPUTE_ONLY);
+
 	if (flags & PIPE_CONTEXT_DEBUG)
 		sscreen->record_llvm_ir = true; /* racy but not critical */
 
 	sctx->b.screen = screen; /* this must be set first */
 	sctx->b.priv = NULL;
 	sctx->b.destroy = si_destroy_context;
-	sctx->b.emit_string_marker = si_emit_string_marker;
-	sctx->b.set_debug_callback = si_set_debug_callback;
-	sctx->b.set_log_context = si_set_log_context;
-	sctx->b.set_context_param = si_set_context_param;
 	sctx->screen = sscreen; /* Easy accessing of screen/winsys. */
 	sctx->is_debug = (flags & PIPE_CONTEXT_DEBUG) != 0;
 
@@ -414,11 +413,6 @@ static struct pipe_context *si_create_context(struct pipe_screen *screen,
 			sctx->ws->query_value(sctx->ws, RADEON_GPU_RESET_COUNTER);
 	}
 
-	sctx->b.get_device_reset_status = si_get_reset_status;
-	sctx->b.set_device_reset_callback = si_set_device_reset_callback;
-
-	si_init_context_texture_functions(sctx);
-	si_init_query_functions(sctx);
 
 	if (sctx->chip_class == CIK ||
 	    sctx->chip_class == VI ||
@@ -430,6 +424,7 @@ static struct pipe_context *si_create_context(struct pipe_screen *screen,
 			goto fail;
 	}
 
+	/* Initialize context allocators. */
 	sctx->allocator_zeroed_memory =
 		u_suballocator_create(&sctx->b, 128 * 1024,
 				      0, PIPE_USAGE_DEFAULT,
@@ -473,24 +468,8 @@ static struct pipe_context *si_create_context(struct pipe_screen *screen,
 	if (use_sdma_upload)
 		u_upload_enable_flush_explicit(sctx->b.const_uploader);
 
-	si_init_buffer_functions(sctx);
-	si_init_clear_functions(sctx);
-	si_init_blit_functions(sctx);
-	si_init_compute_functions(sctx);
-	si_init_compute_blit_functions(sctx);
-	si_init_debug_functions(sctx);
-	si_init_msaa_functions(sctx);
-	si_init_streamout_functions(sctx);
-
-	if (sscreen->info.has_hw_decode) {
-		sctx->b.create_video_codec = si_uvd_create_decoder;
-		sctx->b.create_video_buffer = si_video_buffer_create;
-	} else {
-		sctx->b.create_video_codec = vl_create_decoder;
-		sctx->b.create_video_buffer = vl_video_buffer_create;
-	}
-
-	sctx->gfx_cs = ws->cs_create(sctx->ctx, RING_GFX,
+	sctx->gfx_cs = ws->cs_create(sctx->ctx,
+				     sctx->has_graphics ? RING_GFX : RING_COMPUTE,
 				     (void*)si_flush_gfx_cs, sctx, stop_exec_on_failure);
 
 	/* Border colors. */
@@ -512,29 +491,62 @@ static struct pipe_context *si_create_context(struct pipe_screen *screen,
 	if (!sctx->border_color_map)
 		goto fail;
 
+	/* Initialize context functions used by graphics and compute. */
+	sctx->b.emit_string_marker = si_emit_string_marker;
+	sctx->b.set_debug_callback = si_set_debug_callback;
+	sctx->b.set_log_context = si_set_log_context;
+	sctx->b.set_context_param = si_set_context_param;
+	sctx->b.get_device_reset_status = si_get_reset_status;
+	sctx->b.set_device_reset_callback = si_set_device_reset_callback;
+	sctx->b.memory_barrier = si_memory_barrier;
+
 	si_init_all_descriptors(sctx);
+	si_init_buffer_functions(sctx);
+	si_init_clear_functions(sctx);
+	si_init_blit_functions(sctx);
+	si_init_compute_functions(sctx);
+	si_init_compute_blit_functions(sctx);
+	si_init_debug_functions(sctx);
 	si_init_fence_functions(sctx);
-	si_init_state_functions(sctx);
-	si_init_shader_functions(sctx);
-	si_init_viewport_functions(sctx);
-
-	if (sctx->chip_class >= CIK)
-		cik_init_sdma_functions(sctx);
-	else
-		si_init_dma_functions(sctx);
 
 	if (sscreen->debug_flags & DBG(FORCE_DMA))
 		sctx->b.resource_copy_region = sctx->dma_copy;
 
-	sctx->blitter = util_blitter_create(&sctx->b);
-	if (sctx->blitter == NULL)
-		goto fail;
-	sctx->blitter->skip_viewport_restore = true;
+	/* Initialize graphics-only context functions. */
+	if (sctx->has_graphics) {
+		si_init_context_texture_functions(sctx);
+		si_init_query_functions(sctx);
+		si_init_msaa_functions(sctx);
+		si_init_shader_functions(sctx);
+		si_init_state_functions(sctx);
+		si_init_streamout_functions(sctx);
+		si_init_viewport_functions(sctx);
+
+		sctx->blitter = util_blitter_create(&sctx->b);
+		if (sctx->blitter == NULL)
+			goto fail;
+		sctx->blitter->skip_viewport_restore = true;
 
-	si_init_draw_functions(sctx);
+		si_init_draw_functions(sctx);
+	}
+
+	/* Initialize SDMA functions. */
+	if (sctx->chip_class >= CIK)
+		cik_init_sdma_functions(sctx);
+	else
+		si_init_dma_functions(sctx);
 
 	sctx->sample_mask = 0xffff;
 
+	/* Initialize multimedia functions. */
+	if (sscreen->info.has_hw_decode) {
+		sctx->b.create_video_codec = si_uvd_create_decoder;
+		sctx->b.create_video_buffer = si_video_buffer_create;
+	} else {
+		sctx->b.create_video_codec = vl_create_decoder;
+		sctx->b.create_video_buffer = vl_video_buffer_create;
+	}
+
 	if (sctx->chip_class >= GFX9) {
 		sctx->wait_mem_scratch = si_resource(
 			pipe_buffer_create(screen, 0, PIPE_USAGE_DEFAULT, 4));
@@ -558,7 +570,8 @@ static struct pipe_context *si_create_context(struct pipe_screen *screen,
 			goto fail;
 		sctx->null_const_buf.buffer_size = sctx->null_const_buf.buffer->width0;
 
-		for (shader = 0; shader < SI_NUM_SHADERS; shader++) {
+		unsigned start_shader = sctx->has_graphics ? 0 :  PIPE_SHADER_COMPUTE;
+		for (shader = start_shader; shader < SI_NUM_SHADERS; shader++) {
 			for (i = 0; i < SI_NUM_CONST_BUFFERS; i++) {
 				sctx->b.set_constant_buffer(&sctx->b, shader, i,
 							      &sctx->null_const_buf);
diff --git a/src/gallium/drivers/radeonsi/si_pipe.h b/src/gallium/drivers/radeonsi/si_pipe.h
index b208bdeb848..b3198d45ea6 100644
--- a/src/gallium/drivers/radeonsi/si_pipe.h
+++ b/src/gallium/drivers/radeonsi/si_pipe.h
@@ -794,7 +794,7 @@ struct si_context {
 
 	struct radeon_winsys		*ws;
 	struct radeon_winsys_ctx	*ctx;
-	struct radeon_cmdbuf		*gfx_cs;
+	struct radeon_cmdbuf		*gfx_cs; /* compute IB if graphics is disabled */
 	struct radeon_cmdbuf		*dma_cs;
 	struct pipe_fence_handle	*last_gfx_fence;
 	struct pipe_fence_handle	*last_sdma_fence;
@@ -832,6 +832,7 @@ struct si_context {
 	unsigned			wait_mem_number;
 	uint16_t			prefetch_L2_mask;
 
+	bool				has_graphics;
 	bool				gfx_flush_in_progress:1;
 	bool				gfx_last_ib_is_busy:1;
 	bool				compute_is_busy:1;
diff --git a/src/gallium/drivers/radeonsi/si_state.c b/src/gallium/drivers/radeonsi/si_state.c
index b49a1b3695e..458b108a7e3 100644
--- a/src/gallium/drivers/radeonsi/si_state.c
+++ b/src/gallium/drivers/radeonsi/si_state.c
@@ -4706,7 +4706,7 @@ static void si_texture_barrier(struct pipe_context *ctx, unsigned flags)
 }
 
 /* This only ensures coherency for shader image/buffer stores. */
-static void si_memory_barrier(struct pipe_context *ctx, unsigned flags)
+void si_memory_barrier(struct pipe_context *ctx, unsigned flags)
 {
 	struct si_context *sctx = (struct si_context *)ctx;
 
@@ -4820,7 +4820,6 @@ void si_init_state_functions(struct si_context *sctx)
 	sctx->b.set_vertex_buffers = si_set_vertex_buffers;
 
 	sctx->b.texture_barrier = si_texture_barrier;
-	sctx->b.memory_barrier = si_memory_barrier;
 	sctx->b.set_min_samples = si_set_min_samples;
 	sctx->b.set_tess_state = si_set_tess_state;
 
diff --git a/src/gallium/drivers/radeonsi/si_state.h b/src/gallium/drivers/radeonsi/si_state.h
index 767e789276a..6faa4c511b1 100644
--- a/src/gallium/drivers/radeonsi/si_state.h
+++ b/src/gallium/drivers/radeonsi/si_state.h
@@ -489,6 +489,7 @@ void si_bindless_descriptor_slab_free(void *priv, struct pb_slab *pslab);
 void si_rebind_buffer(struct si_context *sctx, struct pipe_resource *buf,
 		      uint64_t old_va);
 /* si_state.c */
+void si_memory_barrier(struct pipe_context *ctx, unsigned flags);
 void si_init_state_functions(struct si_context *sctx);
 void si_init_screen_state_functions(struct si_screen *sscreen);
 void
diff --git a/src/gallium/drivers/radeonsi/si_state_draw.c b/src/gallium/drivers/radeonsi/si_state_draw.c
index 9c968e39c2c..2a514f144b9 100644
--- a/src/gallium/drivers/radeonsi/si_state_draw.c
+++ b/src/gallium/drivers/radeonsi/si_state_draw.c
@@ -879,7 +879,7 @@ static void si_emit_surface_sync(struct si_context *sctx,
 {
 	struct radeon_cmdbuf *cs = sctx->gfx_cs;
 
-	if (sctx->chip_class >= GFX9) {
+	if (sctx->chip_class >= GFX9 || !sctx->has_graphics) {
 		/* Flush caches and wait for the caches to assert idle. */
 		radeon_emit(cs, PKT3(PKT3_ACQUIRE_MEM, 5, 0));
 		radeon_emit(cs, cp_coher_cntl);	/* CP_COHER_CNTL */
@@ -902,6 +902,18 @@ void si_emit_cache_flush(struct si_context *sctx)
 {
 	struct radeon_cmdbuf *cs = sctx->gfx_cs;
 	uint32_t flags = sctx->flags;
+
+	if (!sctx->has_graphics) {
+		/* Only process compute flags. */
+		flags &= SI_CONTEXT_INV_ICACHE |
+			 SI_CONTEXT_INV_SMEM_L1 |
+			 SI_CONTEXT_INV_VMEM_L1 |
+			 SI_CONTEXT_INV_GLOBAL_L2 |
+			 SI_CONTEXT_WRITEBACK_GLOBAL_L2 |
+			 SI_CONTEXT_INV_L2_METADATA |
+			 SI_CONTEXT_CS_PARTIAL_FLUSH;
+	}
+
 	uint32_t cp_coher_cntl = 0;
 	uint32_t flush_cb_db = flags & (SI_CONTEXT_FLUSH_AND_INV_CB |
 					SI_CONTEXT_FLUSH_AND_INV_DB);
@@ -1068,11 +1080,12 @@ void si_emit_cache_flush(struct si_context *sctx)
 	/* Make sure ME is idle (it executes most packets) before continuing.
 	 * This prevents read-after-write hazards between PFP and ME.
 	 */
-	if (cp_coher_cntl ||
-	    (flags & (SI_CONTEXT_CS_PARTIAL_FLUSH |
-			    SI_CONTEXT_INV_VMEM_L1 |
-			    SI_CONTEXT_INV_GLOBAL_L2 |
-			    SI_CONTEXT_WRITEBACK_GLOBAL_L2))) {
+	if (sctx->has_graphics &&
+	    (cp_coher_cntl ||
+	     (flags & (SI_CONTEXT_CS_PARTIAL_FLUSH |
+		       SI_CONTEXT_INV_VMEM_L1 |
+		       SI_CONTEXT_INV_GLOBAL_L2 |
+		       SI_CONTEXT_WRITEBACK_GLOBAL_L2)))) {
 		radeon_emit(cs, PKT3(PKT3_PFP_SYNC_ME, 0, 0));
 		radeon_emit(cs, 0);
 	}
diff --git a/src/gallium/drivers/radeonsi/si_texture.c b/src/gallium/drivers/radeonsi/si_texture.c
index a50088d2d8f..581f90a7b2f 100644
--- a/src/gallium/drivers/radeonsi/si_texture.c
+++ b/src/gallium/drivers/radeonsi/si_texture.c
@@ -464,6 +464,9 @@ bool si_texture_disable_dcc(struct si_context *sctx,
 {
 	struct si_screen *sscreen = sctx->screen;
 
+	if (!sctx->has_graphics)
+		return si_texture_discard_dcc(sscreen, tex);
+
 	if (!si_can_disable_dcc(tex))
 		return false;