feat(verify): add --call and --buf flags for single-function invocation

Assisted-by: GLM 5.2
2026-08-05 20:46:39 +02:00
parent ece0d3f127
commit b0c62be8ce
6 changed files with 518 additions and 17 deletions
@@ -0,0 +1,150 @@
+// Copyright (c) 2026 Petr Balvín <opensource@petrbalvin.org> (https://petrbalvin.org)
+// SPDX-License-Identifier: BSD-3-Clause
+
+package verify
+
+import (
+	"encoding/binary"
+	"encoding/hex"
+	"fmt"
+	"strings"
+	"unsafe"
+)
+
+// BufSpec is one buffer allocation request parsed from the user's --buf spec.
+type BufSpec struct {
+	Name    string
+	Size    int    // declared slice length and capacity
+	Pattern string // "zero", "ones", "seq", or a hex blob
+}
+
+// ParseBufSpec parses a "name:size:pattern[,name:size:pattern]" spec string
+// into individual buffer specs.  Empty input yields an empty slice.
+func ParseBufSpec(spec string) ([]BufSpec, error) {
+	if spec == "" {
+		return nil, nil
+	}
+	var out []BufSpec
+	for _, part := range strings.Split(spec, ",") {
+		fields := strings.SplitN(part, ":", 3)
+		if len(fields) != 3 {
+			return nil, fmt.Errorf("verify: invalid buffer spec %q (expected name:size:pattern)", part)
+		}
+		var size int
+		if _, err := fmt.Sscanf(fields[1], "%d", &size); err != nil || size <= 0 {
+			return nil, fmt.Errorf("verify: invalid buffer size %q in %q", fields[1], part)
+		}
+		out = append(out, BufSpec{Name: fields[0], Size: size, Pattern: fields[2]})
+	}
+	return out, nil
+}
+
+// allocatedBuf is one live buffer in a pool.
+type allocatedBuf struct {
+	spec BufSpec
+	data []byte // Size + safetyMargin bytes; the first Size are the live region
+}
+
+// safetyMargin is the extra bytes allocated past the declared size so SIMD
+// over-reads and functions that read slightly past len never touch unmapped
+// memory.  Matches the margin used by the fuzz generator.
+const safetyMargin = 8192
+
+// BufPool is a set of allocated buffers held alive for the duration of one or
+// more calls.  Buffers live on the Go heap (the JIT call is in-process); the
+// pool keeps the backing slices referenced so the GC does not collect them
+// before the call returns.
+type BufPool struct {
+	bufs []allocatedBuf
+}
+
+// Alloc allocates and fills the buffers described by specs.  The returned
+// pool must be kept alive until every call using it has returned.
+func (p *BufPool) Alloc(specs []BufSpec) error {
+	for _, s := range specs {
+		data := make([]byte, s.Size+safetyMargin)
+		fillBuffer(data, s.Pattern)
+		p.bufs = append(p.bufs, allocatedBuf{spec: s, data: data})
+	}
+	return nil
+}
+
+// Close releases the pool.  No-op for Go-heap buffers, but keeps the API
+// symmetric with debug's mmap-backed pool.
+func (p *BufPool) Close() {
+	p.bufs = nil
+}
+
+// findByName returns the buffer with the given spec name, if any.
+func (p *BufPool) findByName(name string) *allocatedBuf {
+	for i := range p.bufs {
+		if p.bufs[i].spec.Name == name {
+			return &p.bufs[i]
+		}
+	}
+	return nil
+}
+
+// BuildArgs constructs an ABI0 argument block of argSize bytes for the given
+// layout, placing each buffer's pointer/length/capacity at the matching
+// parameter offset.  Parameters whose names match a buffer spec get the
+// buffer address; non-pointer parameters and unmatched pointers are zeroed.
+//
+// Matching is by exact name, then by prefix (a buffer named "src" matches a
+// parameter named "src" or "srcBuf"), mirroring the debug allocator.
+func (p *BufPool) BuildArgs(layout []ArgOffset, argSize int) []byte {
+	args := make([]byte, argSize)
+	for _, a := range layout {
+		if !a.IsPtr {
+			continue
+		}
+		buf := p.matchBuf(a.Name)
+		if buf == nil {
+			continue
+		}
+		if a.Offset+8 <= len(args) {
+			binary.LittleEndian.PutUint64(args[a.Offset:a.Offset+8], uint64(uintptr(unsafe.Pointer(&buf.data[0]))))
+		}
+		if strings.HasPrefix(a.Typ, "[]") && a.Offset+24 <= len(args) {
+			binary.LittleEndian.PutUint64(args[a.Offset+8:a.Offset+16], uint64(buf.spec.Size))
+			binary.LittleEndian.PutUint64(args[a.Offset+16:a.Offset+24], uint64(buf.spec.Size))
+		}
+	}
+	return args
+}
+
+// matchBuf finds a buffer matching the parameter name (exact, then prefix).
+func (p *BufPool) matchBuf(name string) *allocatedBuf {
+	if b := p.findByName(name); b != nil {
+		return b
+	}
+	for i := range p.bufs {
+		if strings.HasPrefix(name, p.bufs[i].spec.Name) {
+			return &p.bufs[i]
+		}
+	}
+	return nil
+}
+
+// fillBuffer fills buf with the named pattern: "zero" (no-op, already zeroed),
+// "ones" (0xFF), "seq" (i mod 256), or a hex blob repeated to fill.
+func fillBuffer(buf []byte, pattern string) {
+	switch pattern {
+	case "zero":
+		// Already zeroed by make.
+	case "ones":
+		for i := range buf {
+			buf[i] = 0xFF
+		}
+	case "seq":
+		for i := range buf {
+			buf[i] = byte(i)
+		}
+	default:
+		if data, err := hex.DecodeString(pattern); err == nil && len(data) > 0 {
+			for i := range buf {
+				buf[i] = data[i%len(data)]
+			}
+		}
+	}
+}
@@ -0,0 +1,158 @@
+// Copyright (c) 2026 Petr Balvín <opensource@petrbalvin.org> (https://petrbalvin.org)
+// SPDX-License-Identifier: BSD-3-Clause
+
+package verify
+
+import (
+	"testing"
+)
+
+func TestParseParamsExported(t *testing.T) {
+	tests := []struct {
+		input string
+		names []string
+		types []string
+		isPtr []bool
+	}{
+		{
+			input: "dst []byte, src []byte",
+			names: []string{"dst", "src"},
+			types: []string{"[]byte", "[]byte"},
+			isPtr: []bool{true, true},
+		},
+		{
+			input: "dst, src []byte",
+			names: []string{"dst", "src"},
+			types: []string{"[]byte", "[]byte"},
+			isPtr: []bool{true, true},
+		},
+		{
+			input: "a, b int",
+			names: []string{"a", "b"},
+			types: []string{"int", "int"},
+			isPtr: []bool{false, false},
+		},
+		{
+			input: "src []byte, dst []byte",
+			names: []string{"src", "dst"},
+			types: []string{"[]byte", "[]byte"},
+			isPtr: []bool{true, true},
+		},
+		{
+			input: "swin []int32, dstP []uint32, hist *[32]uint16",
+			names: []string{"swin", "dstP", "hist"},
+			types: []string{"[]int32", "[]uint32", "*[32]uint16"},
+			isPtr: []bool{true, true, true},
+		},
+		{
+			input: "n int, code int",
+			names: []string{"n", "code"},
+			types: []string{"int", "int"},
+			isPtr: []bool{false, false},
+		},
+	}
+	for _, tt := range tests {
+		params := parseParamsExported(tt.input)
+		if len(params) != len(tt.names) {
+			t.Errorf("parseParamsExported(%q): got %d params, want %d", tt.input, len(params), len(tt.names))
+			continue
+		}
+		for i, p := range params {
+			if p.Name != tt.names[i] {
+				t.Errorf("parseParamsExported(%q)[%d].Name = %q, want %q", tt.input, i, p.Name, tt.names[i])
+			}
+			if p.Typ != tt.types[i] {
+				t.Errorf("parseParamsExported(%q)[%d].Typ = %q, want %q", tt.input, i, p.Typ, tt.types[i])
+			}
+			if p.IsPointer() != tt.isPtr[i] {
+				t.Errorf("parseParamsExported(%q)[%d].IsPointer() = %v, want %v", tt.input, i, p.IsPointer(), tt.isPtr[i])
+			}
+		}
+	}
+}
+
+func TestParseBufSpec(t *testing.T) {
+	t.Run("empty", func(t *testing.T) {
+		specs, err := ParseBufSpec("")
+		if err != nil || len(specs) != 0 {
+			t.Errorf("ParseBufSpec(\"\") = %v, %v; want nil, nil", specs, err)
+		}
+	})
+
+	t.Run("single", func(t *testing.T) {
+		specs, err := ParseBufSpec("dst:64:zero")
+		if err != nil {
+			t.Fatal(err)
+		}
+		if len(specs) != 1 || specs[0].Name != "dst" || specs[0].Size != 64 || specs[0].Pattern != "zero" {
+			t.Errorf("ParseBufSpec(\"dst:64:zero\") = %+v; want [{dst 64 zero}]", specs)
+		}
+	})
+
+	t.Run("multiple", func(t *testing.T) {
+		specs, err := ParseBufSpec("dst:64:zero,src:128:seq")
+		if err != nil {
+			t.Fatal(err)
+		}
+		if len(specs) != 2 {
+			t.Fatalf("got %d specs, want 2", len(specs))
+		}
+		if specs[0].Name != "dst" || specs[1].Name != "src" {
+			t.Errorf("names = %s, %s; want dst, src", specs[0].Name, specs[1].Name)
+		}
+	})
+
+	t.Run("invalid", func(t *testing.T) {
+		_, err := ParseBufSpec("bad")
+		if err == nil {
+			t.Error("ParseBufSpec(\"bad\") should error")
+		}
+	})
+
+	t.Run("zero-size", func(t *testing.T) {
+		_, err := ParseBufSpec("dst:0:zero")
+		if err == nil {
+			t.Error("ParseBufSpec(\"dst:0:zero\") should error on zero size")
+		}
+	})
+}
+
+func TestBufPoolBuildArgs(t *testing.T) {
+	specs, err := ParseBufSpec("dst:64:seq,src:128:zero")
+	if err != nil {
+		t.Fatal(err)
+	}
+	var pool BufPool
+	if err := pool.Alloc(specs); err != nil {
+		t.Fatal(err)
+	}
+	defer pool.Close()
+
+	// Layout for wideCopyAVX2(dst, src []byte): dst at 0, src at 24.
+	layout := []ArgOffset{
+		{Name: "dst", Typ: "[]byte", Offset: 0, Size: 24, IsPtr: true},
+		{Name: "src", Typ: "[]byte", Offset: 24, Size: 24, IsPtr: true},
+	}
+	args := pool.BuildArgs(layout, 48)
+
+	// dst.ptr should be non-zero.
+	if args[0] == 0 && args[1] == 0 && args[2] == 0 && args[3] == 0 {
+		t.Error("dst.ptr is zero; expected a buffer address")
+	}
+	// dst.len should be 64 (0x40).
+	if args[8] != 0x40 {
+		t.Errorf("dst.len = %d, want 64", args[8])
+	}
+	// dst.cap should be 64.
+	if args[16] != 0x40 {
+		t.Errorf("dst.cap = %d, want 64", args[16])
+	}
+	// src.ptr should be non-zero.
+	if args[24] == 0 && args[25] == 0 && args[26] == 0 && args[27] == 0 {
+		t.Error("src.ptr is zero; expected a buffer address")
+	}
+	// src.len should be 128 (0x80).
+	if args[32] != 0x80 {
+		t.Errorf("src.len = %d, want 128", args[32])
+	}
+}
@@ -79,22 +79,39 @@ func parseParams(s string) []param {
 	if s == "" {
 		return nil
 	}
+	fields := strings.Split(s, ",")
+	// First pass: extract the type from each field (if present).
+	types := make([]string, len(fields))
+	for i, field := range fields {
+		parts := strings.Fields(strings.TrimSpace(field))
+		if len(parts) >= 2 {
+			types[i] = parts[len(parts)-1]
+		}
+	}
+	// Propagate types backward: a field without a type inherits from the next
+	// field that has one (e.g. "dst" inherits "[]byte" from "src []byte").
+	for i := range fields {
+		if types[i] == "" {
+			for j := i + 1; j < len(fields); j++ {
+				if types[j] != "" {
+					types[i] = types[j]
+					break
+				}
+			}
+		}
+	}
 	var out []param
-	for _, field := range strings.Split(s, ",") {
+	for i, field := range fields {
 		field = strings.TrimSpace(field)
 		if field == "" {
 			continue
 		}
 		parts := strings.Fields(field)
-		if len(parts) == 1 {
-			// Unnamed: "int" or "[]byte".
+		typ := types[i]
+		if typ == "" {
 			out = append(out, param{typ: parts[0]})
 		} else {
-			// Named: "a []byte" or shared "a, b []int32" (handled by the
-			// comma split above — "a" alone means the type follows in the
-			// next field; this is a simplification that covers the common
-			// case where each param has its own type).
-			out = append(out, param{name: parts[0], typ: parts[1]})
+			out = append(out, param{name: parts[0], typ: typ})
 		}
 	}
 	return out
@@ -44,25 +44,49 @@ func ParseFuncSig(comment string) (FuncSig, bool) {
 	return sig, true
 }

-// parseParamsExported splits "a []byte, b []int32" into typed parameters.
+// parseParamsExported splits a parameter list like "a []byte, b []int32" or
+// "dst, src []byte" into typed parameters.  Go syntax allows grouped names
+// where the type at the end applies to every name in the group:// "dst, src []byte" means both dst and src are []byte.
 func parseParamsExported(s string) []Param {
 	s = strings.TrimSpace(s)
 	if s == "" {
 		return nil
 	}
+	fields := strings.Split(s, ",")
+	// First pass: extract the type from each field (if present).
+	types := make([]string, len(fields))
+	for i, field := range fields {
+		parts := strings.Fields(strings.TrimSpace(field))
+		if len(parts) >= 2 {
+			types[i] = parts[len(parts)-1]
+		}
+	}
+	// Propagate types backward: a field without a type inherits the type from
+	// the next field that has one (e.g. "dst" inherits "[]byte" from "src []byte").
+	for i := range fields {
+		if types[i] == "" {
+			for j := i + 1; j < len(fields); j++ {
+				if types[j] != "" {
+					types[i] = types[j]
+					break
+				}
+			}
+		}
+	}
+	// Second pass: build params.
 	var out []Param
-	for _, field := range strings.Split(s, ",") {
+	for i, field := range fields {
 		field = strings.TrimSpace(field)
 		if field == "" {
 			continue
 		}
 		parts := strings.Fields(field)
-		if len(parts) == 1 {
-			// Unnamed: "int" or "[]byte".
-			out = append(out, Param{Typ: parts[0]})
+		typ := types[i]
+		if typ == "" {
+			typ = parts[0] // unnamed: the whole field is the type
+			out = append(out, Param{Typ: typ})
 		} else {
-			// Named: "a []byte".
-			out = append(out, Param{Name: parts[0], Typ: parts[1]})
+			out = append(out, Param{Name: parts[0], Typ: typ})
 		}
 	}
 	return out