radv: add initial trap handler support with RADV_TRAP_HANDLER=1

A trap handler is used to handle shader exceptions like memory
violations, divide by zero etc. The trap handler shader code will
help to identify the faulty shader/instruction and to report
more information for better debugging.

This has only been tested on GFX8, though it should work on GFX6-GFX7.
It seems we need a different implemenation for GFX9+.

Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6384>

src/amd/vulkan/radv_debug.c

@@ -36,6 +36,7 @@
 #include "radv_shader.h"
 
 #define TRACE_BO_SIZE 4096
+#define TMA_BO_SIZE 4096
 
 #define COLOR_RESET	"\033[0m"
 #define COLOR_RED	"\033[31m"
@@ -678,3 +679,58 @@ fail:
 	close(fd);
 	unlink(path);
 }
+
+bool
+radv_trap_handler_init(struct radv_device *device)
+{
+	struct radeon_winsys *ws = device->ws;
+
+	/* Create the trap handler shader and upload it like other shaders. */
+	device->trap_handler_shader = radv_create_trap_handler_shader(device);
+	if (!device->trap_handler_shader) {
+		fprintf(stderr, "radv: failed to create the trap handler shader.\n");
+		return false;
+	}
+
+	device->tma_bo = ws->buffer_create(ws, TMA_BO_SIZE, 8,
+					   RADEON_DOMAIN_VRAM,
+					   RADEON_FLAG_CPU_ACCESS |
+					   RADEON_FLAG_NO_INTERPROCESS_SHARING |
+					   RADEON_FLAG_ZERO_VRAM,
+					   RADV_BO_PRIORITY_SCRATCH);
+	if (!device->tma_bo)
+		return false;
+
+	device->tma_ptr = ws->buffer_map(device->tma_bo);
+	if (!device->tma_ptr)
+		return false;
+
+	/* Upload a buffer descriptor to store various info from the trap. */
+	uint64_t tma_va = radv_buffer_get_va(device->tma_bo) + 16;
+	uint32_t desc[4];
+
+	desc[0] = tma_va;
+	desc[1] = S_008F04_BASE_ADDRESS_HI(tma_va >> 32);
+	desc[2] = TMA_BO_SIZE;
+	desc[3] = S_008F0C_DST_SEL_X(V_008F0C_SQ_SEL_X) |
+		  S_008F0C_DST_SEL_Y(V_008F0C_SQ_SEL_Y) |
+		  S_008F0C_DST_SEL_Z(V_008F0C_SQ_SEL_Z) |
+		  S_008F0C_DST_SEL_W(V_008F0C_SQ_SEL_W) |
+		  S_008F0C_DATA_FORMAT(V_008F0C_BUF_DATA_FORMAT_32);
+
+	memcpy(device->tma_ptr, desc, sizeof(desc));
+
+	return true;
+}
+
+void
+radv_trap_handler_finish(struct radv_device *device)
+{
+	struct radeon_winsys *ws = device->ws;
+
+	if (unlikely(device->trap_handler_shader))
+		radv_shader_variant_destroy(device, device->trap_handler_shader);
+
+	if (unlikely(device->tma_bo))
+		ws->buffer_destroy(device->tma_bo);
+}

src/amd/vulkan/radv_debug.h

@@ -82,4 +82,7 @@ radv_print_spirv(const char *data, uint32_t size, FILE *fp);
 void
 radv_dump_enabled_options(struct radv_device *device, FILE *f);
 
+bool radv_trap_handler_init(struct radv_device *device);
+void radv_trap_handler_finish(struct radv_device *device);
+
 #endif

src/amd/vulkan/radv_device.c

@@ -2817,6 +2817,19 @@ VkResult radv_CreateDevice(
 			goto fail;
 	}
 
+	if (getenv("RADV_TRAP_HANDLER")) {
+		/* TODO: Add support for more hardware. */
+		assert(device->physical_device->rad_info.chip_class == GFX8);
+
+		/* To get the disassembly of the faulty shaders, we have to
+		 * keep some shader info around.
+		 */
+		keep_shader_info = true;
+
+		if (!radv_trap_handler_init(device))
+			goto fail;
+	}
+
 	device->keep_shader_info = keep_shader_info;
 	result = radv_device_init_meta(device);
 	if (result != VK_SUCCESS)
@@ -2893,6 +2906,8 @@ fail:
 
 	radv_thread_trace_finish(device);
 
+	radv_trap_handler_finish(device);
+
 	if (device->trace_bo)
 		device->ws->buffer_destroy(device->trace_bo);
 
@@ -2942,6 +2957,8 @@ void radv_DestroyDevice(
 	VkPipelineCache pc = radv_pipeline_cache_to_handle(device->mem_cache);
 	radv_DestroyPipelineCache(radv_device_to_handle(device), pc, NULL);
 
+	radv_trap_handler_finish(device);
+
 	radv_destroy_shader_slabs(device);
 
 	pthread_cond_destroy(&device->timeline_cond);
@@ -3420,6 +3437,50 @@ radv_emit_global_shader_pointers(struct radv_queue *queue,
 	}
 }
 
+static void
+radv_emit_trap_handler(struct radv_queue *queue,
+		       struct radeon_cmdbuf *cs,
+		       struct radeon_winsys_bo *tma_bo)
+{
+	struct radv_device *device = queue->device;
+	struct radeon_winsys_bo *tba_bo;
+	uint64_t tba_va, tma_va;
+
+	if (!device->trap_handler_shader || !tma_bo)
+		return;
+
+	tba_bo = device->trap_handler_shader->bo;
+
+	tba_va = radv_buffer_get_va(tba_bo) + device->trap_handler_shader->bo_offset;
+	tma_va = radv_buffer_get_va(tma_bo);
+
+	radv_cs_add_buffer(queue->device->ws, cs, tba_bo);
+	radv_cs_add_buffer(queue->device->ws, cs, tma_bo);
+
+	if (queue->queue_family_index == RADV_QUEUE_GENERAL) {
+		uint32_t regs[] = {R_00B000_SPI_SHADER_TBA_LO_PS,
+				   R_00B100_SPI_SHADER_TBA_LO_VS,
+				   R_00B200_SPI_SHADER_TBA_LO_GS,
+				   R_00B300_SPI_SHADER_TBA_LO_ES,
+				   R_00B400_SPI_SHADER_TBA_LO_HS,
+				   R_00B500_SPI_SHADER_TBA_LO_LS};
+
+		for (int i = 0; i < ARRAY_SIZE(regs); ++i) {
+			radeon_set_sh_reg_seq(cs, regs[i], 4);
+			radeon_emit(cs, tba_va >> 8);
+			radeon_emit(cs, tba_va >> 40);
+			radeon_emit(cs, tma_va >> 8);
+			radeon_emit(cs, tma_va >> 40);
+		}
+	} else {
+		radeon_set_sh_reg_seq(cs, R_00B838_COMPUTE_TBA_LO, 4);
+		radeon_emit(cs, tba_va >> 8);
+		radeon_emit(cs, tba_va >> 40);
+		radeon_emit(cs, tma_va >> 8);
+		radeon_emit(cs, tma_va >> 40);
+	}
+}
+
 static void
 radv_init_graphics_state(struct radeon_cmdbuf *cs, struct radv_queue *queue)
 {
@@ -3724,6 +3785,7 @@ radv_get_preamble_cs(struct radv_queue *queue,
 		                          compute_scratch_waves, compute_scratch_bo);
 		radv_emit_graphics_scratch(queue, cs, scratch_size_per_wave,
 		                           scratch_waves, scratch_bo);
+		radv_emit_trap_handler(queue, cs, queue->device->tma_bo);
 
 		if (gds_bo)
 			radv_cs_add_buffer(queue->device->ws, cs, gds_bo);

src/amd/vulkan/radv_private.h

@@ -847,6 +847,11 @@ struct radv_device {
 	uint32_t thread_trace_buffer_size;
 	int thread_trace_start_frame;
 
+	/* Trap handler. */
+	struct radv_shader_variant *trap_handler_shader;
+	struct radeon_winsys_bo *tma_bo; /* Trap Memory Address */
+	uint32_t *tma_ptr;
+
 	/* Overallocation. */
 	bool overallocation_disallowed;
 	uint64_t allocated_memory_size[VK_MAX_MEMORY_HEAPS];