intel/xe_exec_sip: add shader sanity test

xe_exec_sip will contain tests for shader and system routine (SIP)
interaction. Shaders (also called kernels) are programs running on
execution units(EUs).
They can generate exceptions, which should be handled by SIP.
For starters let's implement test checking if shader runs correctly.

v2:
 - use introduced helper to access sysfs attributes,
 - remove redundant xe_device_get,
 - use drm_close_driver
v3:
 - switched to old style multiline string literals to satisfy clang
v6:
 - updated test description and commit subject
v7:
 - fix comment tags

Signed-off-by: Andrzej Hajda <andrzej.hajda@intel.com>
Reviewed-by: Dominik Grzegorzek <dominik.grzegorzek@intel.com>

4 files changed, 342 insertions, 1 deletions

diff --git a/lib/gpgpu_shader.c b/lib/gpgpu_shader.c
index 62171952e..991455c49 100644
--- a/lib/gpgpu_shader.c
+++ b/lib/gpgpu_shader.c
@@ -250,3 +250,66 @@ void gpgpu_shader_destroy(struct gpgpu_shader *shdr)
 	free(shdr->code);
 	free(shdr);
 }
+
+/**
+ * gpgpu_shader__eot:
+ * @shdr: shader to be modified
+ *
+ * Append end of thread instruction to @shdr.
+ */
+void gpgpu_shader__eot(struct gpgpu_shader *shdr)
+{
+	emit_iga64_code(shdr, eot, "						\n\
+(W)	mov (8|M0)               r112.0<1>:ud  r0.0<8;8,1>:ud			\n\
+#if GEN_VER < 1250								\n\
+(W)	send.ts (16|M0)          null r112 null 0x10000000 0x02000010 {EOT,@1}	\n\
+#else										\n\
+(W)	send.gtwy (8|M0)         null r112 src1_null     0 0x02000000 {EOT}	\n\
+#endif										\n\
+	");
+}
+
+/**
+ * gpgpu_shader__write_dword:
+ * @shdr: shader to be modified
+ * @value: dword to be written
+ * @y_offset: write target offset within the surface in rows
+ *
+ * Fill dword in (row, column/dword) == (tg_id_y + @y_offset, tg_id_x).
+ */
+void gpgpu_shader__write_dword(struct gpgpu_shader *shdr, uint32_t value,
+			       uint32_t y_offset)
+{
+	emit_iga64_code(shdr, media_block_write, "				\n\
+	// Payload								\n\
+(W)	mov (1|M0)               r5.0<1>:ud    ARG(3):ud			\n\
+(W)	mov (1|M0)               r5.1<1>:ud    ARG(4):ud			\n\
+(W)	mov (1|M0)               r5.2<1>:ud    ARG(5):ud			\n\
+(W)	mov (1|M0)               r5.3<1>:ud    ARG(6):ud			\n\
+#if GEN_VER < 2000 // Media Block Write						\n\
+	// X offset of the block in bytes := (thread group id X << ARG(0))	\n\
+(W)	shl (1|M0)               r4.0<1>:ud    r0.1<0;1,0>:ud    ARG(0):ud	\n\
+	// Y offset of the block in rows := thread group id Y			\n\
+(W)	mov (1|M0)               r4.1<1>:ud    r0.6<0;1,0>:ud			\n\
+(W)	add (1|M0)               r4.1<1>:ud    r4.1<0;1,0>:ud   ARG(1):ud	\n\
+	// block width [0,63] representing 1 to 64 bytes			\n\
+(W)	mov (1|M0)               r4.2<1>:ud    ARG(2):ud			\n\
+	// FFTID := FFTID from R0 header					\n\
+(W)	mov (1|M0)               r4.4<1>:ud    r0.5<0;1,0>:ud			\n\
+(W)	send.dc1 (16|M0)         null     r4   src1_null 0    0x40A8000		\n\
+#else // Typed 2D Block Store							\n\
+	// Load r2.0-3 with tg id X << ARG(0)					\n\
+(W)	shl (1|M0)               r2.0<1>:ud    r0.1<0;1,0>:ud    ARG(0):ud	\n\
+	// Load r2.4-7 with tg id Y + ARG(1):ud					\n\
+(W)	mov (1|M0)               r2.1<1>:ud    r0.6<0;1,0>:ud			\n\
+(W)	add (1|M0)               r2.1<1>:ud    r2.1<0;1,0>:ud    ARG(1):ud	\n\
+	// payload setup							\n\
+(W)	mov (16|M0)              r4.0<1>:ud    0x0:ud				\n\
+	// Store X and Y block start (160:191 and 192:223)			\n\
+(W)	mov (2|M0)               r4.5<1>:ud    r2.0<2;2,1>:ud			\n\
+	// Store X and Y block max_size (224:231 and 232:239)			\n\
+(W)	mov (1|M0)               r4.7<1>:ud    ARG(2):ud			\n\
+(W)	send.tgm (16|M0)         null     r4   null:0    0    0x64000007	\n\
+#endif										\n\
+	", 2, y_offset, 3, value, value, value, value);
+}
diff --git a/lib/iga64_generated_codes.c b/lib/iga64_generated_codes.c
index 452d4b3da..f609ad711 100644
--- a/lib/iga64_generated_codes.c
+++ b/lib/iga64_generated_codes.c
@@ -3,4 +3,85 @@
 
 #include "gpgpu_shader.h"
 
-#define MD5_SUM_IGA64_ASMS 68b329da9893e34099c7d8ad5cb9c940
+#define MD5_SUM_IGA64_ASMS 2c503cbfbd7b3043e9a52188ae4da7a8
+
+struct iga64_template const iga64_code_media_block_write[] = {
+	{ .gen_ver = 2000, .size = 56, .code = (const uint32_t []) {
+		0x80000061, 0x05054220, 0x00000000, 0xc0ded003,
+		0x80000061, 0x05154220, 0x00000000, 0xc0ded004,
+		0x80000061, 0x05254220, 0x00000000, 0xc0ded005,
+		0x80000061, 0x05354220, 0x00000000, 0xc0ded006,
+		0x80000069, 0x02058220, 0x02000014, 0xc0ded000,
+		0x80000061, 0x02150220, 0x00000064, 0x00000000,
+		0x80001940, 0x02158220, 0x02000214, 0xc0ded001,
+		0x80100061, 0x04054220, 0x00000000, 0x00000000,
+		0x80041a61, 0x04550220, 0x00220205, 0x00000000,
+		0x80000061, 0x04754220, 0x00000000, 0xc0ded002,
+		0x80132031, 0x00000000, 0xd00e0494, 0x04000000,
+		0x80000001, 0x00010000, 0x20000000, 0x00000000,
+		0x80000001, 0x00010000, 0x30000000, 0x00000000,
+		0x80000901, 0x00010000, 0x00000000, 0x00000000,
+	}},
+	{ .gen_ver = 1272, .size = 52, .code = (const uint32_t []) {
+		0x80000061, 0x05054220, 0x00000000, 0xc0ded003,
+		0x80000061, 0x05154220, 0x00000000, 0xc0ded004,
+		0x80000061, 0x05254220, 0x00000000, 0xc0ded005,
+		0x80000061, 0x05354220, 0x00000000, 0xc0ded006,
+		0x80000069, 0x04058220, 0x02000014, 0xc0ded000,
+		0x80000061, 0x04150220, 0x00000064, 0x00000000,
+		0x80001940, 0x04158220, 0x02000414, 0xc0ded001,
+		0x80000061, 0x04254220, 0x00000000, 0xc0ded002,
+		0x80000061, 0x04450220, 0x00000054, 0x00000000,
+		0x80132031, 0x00000000, 0xc0000414, 0x02a00000,
+		0x80000001, 0x00010000, 0x20000000, 0x00000000,
+		0x80000001, 0x00010000, 0x30000000, 0x00000000,
+		0x80000901, 0x00010000, 0x00000000, 0x00000000,
+	}},
+	{ .gen_ver = 1250, .size = 56, .code = (const uint32_t []) {
+		0x80000061, 0x05054220, 0x00000000, 0xc0ded003,
+		0x80000061, 0x05254220, 0x00000000, 0xc0ded004,
+		0x80000061, 0x05454220, 0x00000000, 0xc0ded005,
+		0x80000061, 0x05654220, 0x00000000, 0xc0ded006,
+		0x80000069, 0x04058220, 0x02000024, 0xc0ded000,
+		0x80000061, 0x04250220, 0x000000c4, 0x00000000,
+		0x80001940, 0x04258220, 0x02000424, 0xc0ded001,
+		0x80000061, 0x04454220, 0x00000000, 0xc0ded002,
+		0x80000061, 0x04850220, 0x000000a4, 0x00000000,
+		0x80001901, 0x00010000, 0x00000000, 0x00000000,
+		0x80044031, 0x00000000, 0xc0000414, 0x02a00000,
+		0x80000001, 0x00010000, 0x20000000, 0x00000000,
+		0x80000001, 0x00010000, 0x30000000, 0x00000000,
+		0x80000901, 0x00010000, 0x00000000, 0x00000000,
+	}},
+	{ .gen_ver = 0, .size = 52, .code = (const uint32_t []) {
+		0x80000061, 0x05054220, 0x00000000, 0xc0ded003,
+		0x80000061, 0x05254220, 0x00000000, 0xc0ded004,
+		0x80000061, 0x05454220, 0x00000000, 0xc0ded005,
+		0x80000061, 0x05654220, 0x00000000, 0xc0ded006,
+		0x80000069, 0x04058220, 0x02000024, 0xc0ded000,
+		0x80000061, 0x04250220, 0x000000c4, 0x00000000,
+		0x80000140, 0x04258220, 0x02000424, 0xc0ded001,
+		0x80000061, 0x04454220, 0x00000000, 0xc0ded002,
+		0x80000061, 0x04850220, 0x000000a4, 0x00000000,
+		0x80049031, 0x00000000, 0xc0000414, 0x02a00000,
+		0x80000001, 0x00010000, 0x20000000, 0x00000000,
+		0x80000001, 0x00010000, 0x30000000, 0x00000000,
+		0x80000101, 0x00010000, 0x00000000, 0x00000000,
+	}}
+};
+
+struct iga64_template const iga64_code_eot[] = {
+	{ .gen_ver = 1272, .size = 8, .code = (const uint32_t []) {
+		0x800c0061, 0x70050220, 0x00460005, 0x00000000,
+		0x800f2031, 0x00000004, 0x3000700c, 0x00000000,
+	}},
+	{ .gen_ver = 1250, .size = 12, .code = (const uint32_t []) {
+		0x80030061, 0x70050220, 0x00460005, 0x00000000,
+		0x80001901, 0x00010000, 0x00000000, 0x00000000,
+		0x80034031, 0x00000004, 0x3000700c, 0x00000000,
+	}},
+	{ .gen_ver = 0, .size = 8, .code = (const uint32_t []) {
+		0x80030061, 0x70050220, 0x00460005, 0x00000000,
+		0x80049031, 0x00000004, 0x7020700c, 0x10000000,
+	}}
+};
diff --git a/tests/intel/xe_exec_sip.c b/tests/intel/xe_exec_sip.c
new file mode 100644
index 000000000..4b599e7f6
--- /dev/null
+++ b/tests/intel/xe_exec_sip.c
@@ -0,0 +1,196 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2024 Intel Corporation
+ */
+
+/**
+ * TEST: Tests for GPGPU shader and system routine (SIP) execution
+ * Category: Software building block
+ * Description: Exercise interaction between GPGPU shader and system routine
+ *              (SIP), which should handle exceptions raised on Execution Unit.
+ * Functionality: system routine
+ * Mega feature: Compute
+ * Sub-category: GPGPU tests
+ * Test category: functionality test
+ */
+
+#include <dirent.h>
+#include <fcntl.h>
+#include <stdio.h>
+
+#include "gpgpu_shader.h"
+#include "igt.h"
+#include "igt_sysfs.h"
+#include "xe/xe_ioctl.h"
+#include "xe/xe_query.h"
+
+#define WIDTH 64
+#define HEIGHT 64
+
+#define COLOR_C4 0xc4
+
+#define SHADER_CANARY 0x01010101
+
+#define NSEC_PER_MSEC (1000 * 1000ull)
+
+static struct intel_buf *
+create_fill_buf(int fd, int width, int height, uint8_t color)
+{
+	struct intel_buf *buf;
+	uint8_t *ptr;
+
+	buf = calloc(1, sizeof(*buf));
+	igt_assert(buf);
+
+	intel_buf_init(buf_ops_create(fd), buf, width / 4, height, 32, 0,
+		       I915_TILING_NONE, 0);
+
+	ptr = xe_bo_map(fd, buf->handle, buf->surface[0].size);
+	memset(ptr, color, buf->surface[0].size);
+	munmap(ptr, buf->surface[0].size);
+
+	return buf;
+}
+
+static struct gpgpu_shader *get_shader(int fd)
+{
+	static struct gpgpu_shader *shader;
+
+	shader = gpgpu_shader_create(fd);
+	gpgpu_shader__write_dword(shader, SHADER_CANARY, 0);
+	gpgpu_shader__eot(shader);
+	return shader;
+}
+
+static uint32_t gpgpu_shader(int fd, struct intel_bb *ibb, unsigned int threads,
+			     unsigned int width, unsigned int height)
+{
+	struct intel_buf *buf = create_fill_buf(fd, width, height, COLOR_C4);
+	struct gpgpu_shader *shader = get_shader(fd);
+
+	gpgpu_shader_exec(ibb, buf, 1, threads, shader, NULL, 0, 0);
+	gpgpu_shader_destroy(shader);
+	return buf->handle;
+}
+
+static void check_fill_buf(uint8_t *ptr, const int width, const int x,
+			   const int y, const uint8_t color)
+{
+	const uint8_t val = ptr[y * width + x];
+
+	igt_assert_f(val == color,
+		     "Expected 0x%02x, found 0x%02x at (%d,%d)\n",
+		     color, val, x, y);
+}
+
+static void check_buf(int fd, uint32_t handle, int width, int height,
+		      uint8_t poison_c)
+{
+	unsigned int sz = ALIGN(width * height, 4096);
+	int thread_count = 0;
+	uint32_t *ptr;
+	int i, j;
+
+	ptr = xe_bo_mmap_ext(fd, handle, sz, PROT_READ);
+
+	for (i = 0, j = 0; j < height / 2; ++j) {
+		if (ptr[j * width / 4] == SHADER_CANARY) {
+			++thread_count;
+			i = 4;
+		}
+
+		for (; i < width; i++)
+			check_fill_buf((uint8_t *)ptr, width, i, j, poison_c);
+
+		i = 0;
+	}
+
+	igt_assert(thread_count);
+
+	munmap(ptr, sz);
+}
+
+static uint64_t
+xe_sysfs_get_job_timeout_ms(int fd, struct drm_xe_engine_class_instance *eci)
+{
+	int engine_fd = -1;
+	uint64_t ret;
+
+	engine_fd = xe_sysfs_engine_open(fd, eci->gt_id, eci->engine_class);
+	ret = igt_sysfs_get_u64(engine_fd, "job_timeout_ms");
+	close(engine_fd);
+
+	return ret;
+}
+
+/**
+ * SUBTEST: sanity
+ * Description: check basic shader with write operation
+ * Run type: BAT
+ *
+ */
+static void test_sip(struct drm_xe_engine_class_instance *eci, uint32_t flags)
+{
+	unsigned int threads = 512;
+	unsigned int height = max_t(threads, HEIGHT, threads * 2);
+	uint32_t exec_queue_id, handle, vm_id;
+	unsigned int width = WIDTH;
+	struct timespec ts = { };
+	uint64_t timeout;
+	struct intel_bb *ibb;
+	int fd;
+
+	igt_debug("Using %s\n", xe_engine_class_string(eci->engine_class));
+
+	fd = drm_open_driver(DRIVER_XE);
+	xe_device_get(fd);
+
+	vm_id = xe_vm_create(fd, 0, 0);
+
+	/* Get timeout for job, and add 4s to ensure timeout processes in subtest. */
+	timeout = xe_sysfs_get_job_timeout_ms(fd, eci) + 4ull * MSEC_PER_SEC;
+	timeout *= NSEC_PER_MSEC;
+	timeout *= igt_run_in_simulation() ? 10 : 1;
+
+	exec_queue_id = xe_exec_queue_create(fd, vm_id, eci, 0);
+	ibb = intel_bb_create_with_context(fd, exec_queue_id, vm_id, NULL, 4096);
+
+	igt_nsec_elapsed(&ts);
+	handle = gpgpu_shader(fd, ibb, threads, width, height);
+
+	intel_bb_sync(ibb);
+	igt_assert_lt_u64(igt_nsec_elapsed(&ts), timeout);
+
+	check_buf(fd, handle, width, height, COLOR_C4);
+
+	gem_close(fd, handle);
+	intel_bb_destroy(ibb);
+
+	xe_exec_queue_destroy(fd, exec_queue_id);
+	xe_vm_destroy(fd, vm_id);
+	xe_device_put(fd);
+	close(fd);
+}
+
+#define test_render_and_compute(t, __fd, __eci) \
+	igt_subtest_with_dynamic(t) \
+		xe_for_each_engine(__fd, __eci) \
+			if (__eci->engine_class == DRM_XE_ENGINE_CLASS_RENDER || \
+			    __eci->engine_class == DRM_XE_ENGINE_CLASS_COMPUTE) \
+				igt_dynamic_f("%s%d", xe_engine_class_string(__eci->engine_class), \
+					      __eci->engine_instance)
+
+igt_main
+{
+	struct drm_xe_engine_class_instance *eci;
+	int fd;
+
+	igt_fixture
+		fd = drm_open_driver(DRIVER_XE);
+
+	test_render_and_compute("sanity", fd, eci)
+		test_sip(eci, 0);
+
+	igt_fixture
+		drm_close_driver(fd);
+}
diff --git a/tests/meson.build b/tests/meson.build
index 122fbd07c..5a7db3923 100644
--- a/tests/meson.build
+++ b/tests/meson.build
@@ -288,6 +288,7 @@ intel_xe_progs = [
 	'xe_exec_fault_mode',
 	'xe_exec_queue_property',
 	'xe_exec_reset',
+	'xe_exec_sip',
 	'xe_exec_store',
 	'xe_exec_threads',
 	'xe_exercise_blt',