// Copyright (c) 2026 Petr Balvín <opensource@petrbalvin.org> (https://petrbalvin.org)
// SPDX-License-Identifier: BSD-3-Clause

//go:build integration

// Package asm integration tests against the production go-libraries kernels.
// These are excluded from the default test run (go test ./...) so that the
// coverage numbers are identical locally and in CI, where go-libraries is
// not checked out.  Run them explicitly with:  go test -tags=integration ./asm/
package asm

import (
	"bytes"
	"os"
	"testing"

	"golang.org/x/arch/x86/x86asm"

	"sourcedock.dev/petrbalvin/gasm-devkit/parser"
)

// TestAssembleGoFlacAVX2Kernel assembles the whole production AVX2 kernel;
// all functions plus the file-local mask24 constant; and checks that every
// static-symbol load resolves to the right bytes in the image.
func TestAssembleGoFlacAVX2Kernel(t *testing.T) {
	path := "../../go-libraries/go-flac/avx2_amd64.s"
	if _, err := os.Stat(path); err != nil {
		t.Skip("go-libraries repository not present next to gasm-devkit")
	}
	src, err := os.ReadFile(path)
	if err != nil {
		t.Fatal(err)
	}
	f, errs := parser.Parse(path, string(src))
	if len(errs) > 0 {
		t.Fatalf("parse: %v", errs)
	}
	img, err := AssembleFile(f)
	if err != nil {
		t.Fatalf("AssembleFile: %v", err)
	}
	if len(img.Funcs) != 17 {
		t.Errorf("functions = %d, want 17", len(img.Funcs))
	}

	// mask24 as the DATA directives define it.
	mask := []byte{
		0x00, 0x01, 0x02, 0x80, 0x03, 0x04, 0x05, 0x80,
		0x06, 0x07, 0x08, 0x80, 0x09, 0x0a, 0x0b, 0x80,
	}
	image := img.Bytes()
	if got := image[img.Symbols["mask24"] : img.Symbols["mask24"]+16]; !bytes.Equal(got, mask) {
		t.Errorf("mask24 contents %x, want %x", got, mask)
	}

	// Every VMOVDQU mask24<>(SB), X15 (c5 7a 6f 3d + rel32, i.e. a VMOVDQU
	// with a RIP-relative r/m) must land on the mask bytes within the image.
	loads := 0
	for _, fn := range img.Funcs {
		code := img.Code[fn.Offset : fn.Offset+fn.Size]
		for pc := 0; pc < len(code); {
			inst, err := x86asm.Decode(code[pc:], 64)
			if err != nil {
				t.Fatalf("%s: decode at +%d: %v", fn.Name, pc, err)
			}
			// mod=00, rm=101 → RIP-relative.
			if inst.Op == x86asm.VMOVDQU && inst.Len == 8 && code[pc+3]&0xC7 == 0x05 {
				rel := int32(uint32(code[pc+4]) | uint32(code[pc+5])<<8 | uint32(code[pc+6])<<16 | uint32(code[pc+7])<<24)
				target := fn.Offset + pc + 8 + int(rel)
				if !bytes.Equal(image[target:target+16], mask) {
					t.Errorf("%s: mask load at +%d lands on %x, want %x", fn.Name, pc, image[target:target+16], mask)
				}
				loads++
			}
			pc += inst.Len
		}
	}
	if loads != 2 {
		t.Errorf("mask loads found = %d, want 2", loads)
	}
}

// TestAssembleGoFlacAVX512Kernel assembles the whole production AVX-512
// kernel, all functions plus the file-global idx16 constant, and checks
// that the static-symbol load resolves to the right bytes in the image.
func TestAssembleGoFlacAVX512Kernel(t *testing.T) {
	path := "../../go-libraries/go-flac/avx512_amd64.s"
	if _, err := os.Stat(path); err != nil {
		t.Skip("go-libraries repository not present next to gasm-devkit")
	}
	src, err := os.ReadFile(path)
	if err != nil {
		t.Fatal(err)
	}
	f, errs := parser.Parse(path, string(src))
	if len(errs) > 0 {
		t.Fatalf("parse: %v", errs)
	}
	img, err := AssembleFile(f)
	if err != nil {
		t.Fatalf("AssembleFile: %v", err)
	}
	if len(img.Funcs) != 10 {
		t.Errorf("functions = %d, want 10", len(img.Funcs))
	}

	// idx16 as the DATA directives define it: dwords 1..16.
	idx := make([]byte, 0, 64)
	for i := 1; i <= 16; i++ {
		idx = append(idx, byte(i), 0, 0, 0)
	}
	image := img.Bytes()
	base := img.Symbols["idx16"]
	if base == 0 {
		t.Fatal("idx16 not laid out")
	}
	if got := image[base : base+64]; hexCompact(got) != hexCompact(idx) {
		t.Errorf("idx16 contents %x, want %x", got, idx)
	}

	// The VMOVDQU32 idx16(SB), Z13 load (62 71 7e 48 6f 2d + rel32) must
	// resolve to idx16 within the image.
	loads := 0
	for _, fn := range img.Funcs {
		code := img.Code[fn.Offset : fn.Offset+fn.Size]
		pat := []byte{0x62, 0x71, 0x7e, 0x48, 0x6f, 0x2d}
		for pos := 0; ; {
			i := indexOf(code[pos:], pat)
			if i < 0 {
				break
			}
			i += pos
			rel := int32(uint32(code[i+6]) | uint32(code[i+7])<<8 | uint32(code[i+8])<<16 | uint32(code[i+9])<<24)
			target := fn.Offset + i + 10 + int(rel)
			if target != base {
				t.Errorf("%s: idx16 load at +%d targets 0x%x, want 0x%x", fn.Name, i, target, base)
			}
			loads++
			pos = i + 10
		}
	}
	if loads != 1 {
		t.Errorf("idx16 loads found = %d, want 1", loads)
	}
}

// indexOf returns the index of the first occurrence of pat in b, or -1.
func indexOf(b, pat []byte) int {
	for i := 0; i+len(pat) <= len(b); i++ {
		j := 0
		for j < len(pat) && b[i+j] == pat[j] {
			j++
		}
		if j == len(pat) {
			return i
		}
	}
	return -1
}