lib/gpgpu_shader: add inline support for iga64 assembly

With this patch adding iga64 assembly should be similar to
adding x86 assembly inline. Simple example:
    emit_iga64_code(shdr, set_exception, R"ASM(
        or (1|M0) cr0.1<1>:ud cr0.1<0;1,0>:ud ARG(0):ud
    )ASM", value);
Note presence of 'ARG(0)', it will be replaced by 'value' argument,
multiple arguments are possible.
More sophisticated examples in following patches.
How does it works:
1. Raw string literals (C++ feature available in gcc as extension):
   R"ASM(...)ASM" allows to use multiline/unescaped string literals.
   If for some reason they cannot be used we could always fallback to
   old ugly way of handling multiline strings with escape characters:
    emit_iga64_code(shdr, set_exception, "\n\
        or (1|M0) cr0.1<1>:ud cr0.1<0;1,0>:ud ARG(0):ud\n\
    ", value);
2. emit_iga64_code puts the assembly string into special linker section,
   and calls __emit_iga64_code with pointer to external variable
   which will contain code templates generated from the assembly for all
   supported platforms, remaining arguments are put to temporal array
   to eventually patch the code with positional arguments.
3. During build phase the linker section is scanned for assemblies.
   Every assembly is preprocessed with cpp, to replace ARG(x) macros with
   magic numbers, and to provide different code for different platforms
   if needed. Then output file is compiled with iga64, and then .c file
   is generated with global variables pointing to hexified iga64 codes.

v2:
 - fixed meson paths to script,
 - added check if compiler supports all platforms,
 - include assembly names in MD5 calculations,
 - use more specific name for MD5 sum
v3:
 - bump minimal meson version to kill "ERROR:  Expecting eol got id." bug
v4:
 - set minimal meson to 0.49.2 - builder uses it
v5:
 - revert back minimal ver of meson, instead use old syntax a.contains(b)
v6:
 - generate_iga64_codes moved to scripts dir,
 - added include guards to iga64_macros.h
v7:
 - use C++ style comments in generated file,
 - style fixes
v8:
 - added sanity check for assembly

Signed-off-by: Andrzej Hajda <andrzej.hajda@intel.com>
Reviewed-by: Zbigniew Kempczyński <zbigniew.kempczynski@intel.com>

5 files changed, 104 insertions, 0 deletions

diff --git a/lib/gpgpu_shader.c b/lib/gpgpu_shader.c
index 3b5ba8222..62171952e 100644
--- a/lib/gpgpu_shader.c
+++ b/lib/gpgpu_shader.c
@@ -11,6 +11,9 @@
 #include "gpgpu_shader.h"
 #include "gpu_cmds.h"
 
+#define IGA64_ARG0 0xc0ded000
+#define IGA64_ARG_MASK 0xffffff00
+
 #define SUPPORTED_GEN_VER 1200 /* Support TGL and up */
 
 #define PAGE_SIZE 4096
@@ -22,6 +25,43 @@
 #define GPGPU_CURBE_SIZE 0
 #define GEN7_VFE_STATE_GPGPU_MODE 1
 
+static void gpgpu_shader_extend(struct gpgpu_shader *shdr)
+{
+	shdr->max_size <<= 1;
+	shdr->code = realloc(shdr->code, 4 * shdr->max_size);
+	igt_assert(shdr->code);
+}
+
+void
+__emit_iga64_code(struct gpgpu_shader *shdr, struct iga64_template const *tpls,
+		  int argc, uint32_t *argv)
+{
+	uint32_t *ptr;
+
+	igt_require_f(shdr->gen_ver >= SUPPORTED_GEN_VER,
+		      "No available shader templates for platforms older than XeLP\n");
+
+	while (shdr->gen_ver < tpls->gen_ver)
+		tpls++;
+
+	while (shdr->max_size < shdr->size + tpls->size)
+		gpgpu_shader_extend(shdr);
+
+	ptr = shdr->code + shdr->size;
+	memcpy(ptr, tpls->code, 4 * tpls->size);
+
+	/* patch the template */
+	for (int n, i = 0; i < tpls->size; ++i) {
+		if ((ptr[i] & IGA64_ARG_MASK) != IGA64_ARG0)
+			continue;
+		n = ptr[i] - IGA64_ARG0;
+		igt_assert(n < argc);
+		ptr[i] = argv[n];
+	}
+
+	shdr->size += tpls->size;
+}
+
 static uint32_t fill_sip(struct intel_bb *ibb,
 			 const uint32_t sip[][4],
 			 const size_t size)
diff --git a/lib/gpgpu_shader.h b/lib/gpgpu_shader.h
index 02f6f1aad..255f93b4d 100644
--- a/lib/gpgpu_shader.h
+++ b/lib/gpgpu_shader.h
@@ -23,6 +23,27 @@ struct gpgpu_shader {
 	};
 };
 
+struct iga64_template {
+	uint32_t gen_ver;
+	uint32_t size;
+	const uint32_t *code;
+};
+
+#pragma GCC diagnostic ignored "-Wnested-externs"
+
+void
+__emit_iga64_code(struct gpgpu_shader *shdr, const struct iga64_template *tpls,
+		  int argc, uint32_t *argv);
+
+#define emit_iga64_code(__shdr, __name, __txt, __args...) \
+({ \
+	static const char t[] __attribute__ ((section(".iga64_assembly"), used)) =\
+		"iga64_assembly_" #__name ":" __txt "\n"; \
+	extern struct iga64_template const iga64_code_ ## __name[]; \
+	u32 args[] = { __args }; \
+	__emit_iga64_code(__shdr, iga64_code_ ## __name, ARRAY_SIZE(args), args); \
+})
+
 struct gpgpu_shader *gpgpu_shader_create(int fd);
 void gpgpu_shader_destroy(struct gpgpu_shader *shdr);
 
@@ -35,4 +56,8 @@ void gpgpu_shader_exec(struct intel_bb *ibb,
 		       struct gpgpu_shader *sip,
 		       uint64_t ring, bool explicit_engine);
 
+void gpgpu_shader__eot(struct gpgpu_shader *shdr);
+void gpgpu_shader__write_dword(struct gpgpu_shader *shdr, uint32_t value,
+			       uint32_t y_offset);
+
 #endif /* GPGPU_SHADER_H */
diff --git a/lib/iga64_generated_codes.c b/lib/iga64_generated_codes.c
new file mode 100644
index 000000000..452d4b3da
--- /dev/null
+++ b/lib/iga64_generated_codes.c
@@ -0,0 +1,6 @@
+// SPDX-License-Identifier: MIT
+// Generated using Intel Graphics Assembler 1.1.0-int
+
+#include "gpgpu_shader.h"
+
+#define MD5_SUM_IGA64_ASMS 68b329da9893e34099c7d8ad5cb9c940
diff --git a/lib/iga64_macros.h b/lib/iga64_macros.h
new file mode 100644
index 000000000..f4ef5cb16
--- /dev/null
+++ b/lib/iga64_macros.h
@@ -0,0 +1,16 @@
+/* SPDX-License-Identifier: MIT */
+/* Copyright © 2024 Intel Corporation */
+
+/* Header used during pre-process phase of iga64 assembly. */
+
+#ifndef IGA64_MACROS_H
+#define IGA64_MACROS_H
+
+/* send instruction for DG2+ requires 0 length in case src1 is null, BSpec: 47443 */
+#if GEN_VER < 1271
+#define src1_null null
+#else
+#define src1_null null:0
+#endif
+
+#endif
diff --git a/lib/meson.build b/lib/meson.build
index 7dc99f718..8c032cbb6 100644
--- a/lib/meson.build
+++ b/lib/meson.build
@@ -216,7 +216,10 @@ lib_version = vcs_tag(input : 'version.h.in', output : 'version.h',
 		      fallback : 'NO-GIT',
 		      command : vcs_command )
 
+iga64_assembly_sources = [ 'gpgpu_shader.c' ]
+
 lib_intermediates = []
+iga64_assembly_libs = []
 foreach f: lib_sources
     name = f.underscorify()
     lib = static_library('igt-' + name,
@@ -230,8 +233,22 @@ foreach f: lib_sources
 	])
 
     lib_intermediates += lib
+    if iga64_assembly_sources.contains(f)
+	iga64_assembly_libs += lib
+    endif
 endforeach
 
+iga64_generated_codes = custom_target(
+    'iga64_generated_codes.c',
+    input : [ 'iga64_generated_codes.c' ] + iga64_assembly_libs,
+    output : 'iga64_generated_codes.c',
+    command : [ generate_iga64_codes, '-o', '@OUTPUT@', '-i', '@INPUT@' ]
+)
+
+lib_intermediates += static_library('igt-iga64_generated_codes.c',
+			[ iga64_generated_codes, lib_version ]
+		     )
+
 lib_igt_build = shared_library('igt',
     ['dummy.c'],
     link_whole: lib_intermediates,