[release-branch.go1.5] cmd/go: fix loading of buildid on OS X executables

This is a bit of a belt-and-suspenders fix.
On OS X, we now parse the Mach-O file to find the __text section,
which is arguably the more proper fix. But it's a bit worrisome to
depend on a name like __text not changing, so we also read more
of the initial file (now 32 kB, up from 8 kB) and scan that too.

Fixes #12327.

Change-Id: I3a201a3dc278d24707109bb3961c3bdd8b8a0b7b
Reviewed-on: https://go-review.googlesource.com/17038Reviewed-by: Ian Lance Taylor <iant@golang.org>
Reviewed-on: https://go-review.googlesource.com/17127

src/cmd/dist/build.go

@@ -894,6 +894,7 @@ var buildorder = []string{
 	"crypto/sha1",
 	"debug/dwarf",
 	"debug/elf",
+	"debug/macho",
 	"cmd/go",
 }
 

src/cmd/go/note.go

@@ -7,6 +7,7 @@ package main
 import (
 	"bytes"
 	"debug/elf"
+	"debug/macho"
 	"encoding/binary"
 	"fmt"
 	"io"
@@ -114,3 +115,42 @@ func readELFGoBuildID(filename string, f *os.File, data []byte) (buildid string,
 	// No note. Treat as successful but build ID empty.
 	return "", nil
 }
+
+// The Go build ID is stored at the beginning of the Mach-O __text segment.
+// The caller has already opened filename, to get f, and read a few kB out, in data.
+// Sadly, that's not guaranteed to hold the note, because there is an arbitrary amount
+// of other junk placed in the file ahead of the main text.
+func readMachoGoBuildID(filename string, f *os.File, data []byte) (buildid string, err error) {
+	// If the data we want has already been read, don't worry about Mach-O parsing.
+	// This is both an optimization and a hedge against the Mach-O parsing failing
+	// in the future due to, for example, the name of the __text section changing.
+	if b, err := readRawGoBuildID(filename, data); b != "" && err == nil {
+		return b, err
+	}
+
+	mf, err := macho.NewFile(f)
+	if err != nil {
+		return "", &os.PathError{Path: filename, Op: "parse", Err: err}
+	}
+
+	sect := mf.Section("__text")
+	if sect == nil {
+		// Every binary has a __text section. Something is wrong.
+		return "", &os.PathError{Path: filename, Op: "parse", Err: fmt.Errorf("cannot find __text section")}
+	}
+
+	// It should be in the first few bytes, but read a lot just in case,
+	// especially given our past problems on OS X with the build ID moving.
+	// There shouldn't be much difference between reading 4kB and 32kB:
+	// the hard part is getting to the data, not transferring it.
+	n := sect.Size
+	if n > uint64(BuildIDReadSize) {
+		n = uint64(BuildIDReadSize)
+	}
+	buf := make([]byte, n)
+	if _, err := f.ReadAt(buf, int64(sect.Offset)); err != nil {
+		return "", err
+	}
+
+	return readRawGoBuildID(filename, buf)
+}

src/cmd/go/note_test.go

@@ -11,6 +11,20 @@ import (
 )
 
 func TestNoteReading(t *testing.T) {
+	testNoteReading(t)
+}
+
+func TestNoteReading2K(t *testing.T) {
+	// Set BuildIDReadSize to 2kB to exercise Mach-O parsing more strictly.
+	defer func(old int) {
+		main.BuildIDReadSize = old
+	}(main.BuildIDReadSize)
+	main.BuildIDReadSize = 2 * 1024
+
+	testNoteReading(t)
+}
+
+func testNoteReading(t *testing.T) {
 	tg := testgo(t)
 	defer tg.cleanup()
 	tg.tempFile("hello.go", `package main; func main() { print("hello, world\n") }`)

src/cmd/go/pkg.go

@@ -1781,8 +1781,17 @@ var (
 	goBuildEnd    = []byte("\"\n \xff")
 
 	elfPrefix = []byte("\x7fELF")
+
+	machoPrefixes = [][]byte{
+		{0xfe, 0xed, 0xfa, 0xce},
+		{0xfe, 0xed, 0xfa, 0xcf},
+		{0xce, 0xfa, 0xed, 0xfe},
+		{0xcf, 0xfa, 0xed, 0xfe},
+	}
 )
 
+var BuildIDReadSize = 32 * 1024 // changed for testing
+
 // ReadBuildIDFromBinary reads the build ID from a binary.
 //
 // ELF binaries store the build ID in a proper PT_NOTE section.
@@ -1797,10 +1806,11 @@ func ReadBuildIDFromBinary(filename string) (id string, err error) {
 		return "", &os.PathError{Op: "parse", Path: filename, Err: errBuildIDUnknown}
 	}
 
-	// Read the first 16 kB of the binary file.
+	// Read the first 32 kB of the binary file.
 	// That should be enough to find the build ID.
 	// In ELF files, the build ID is in the leading headers,
-	// which are typically less than 4 kB, not to mention 16 kB.
+	// which are typically less than 4 kB, not to mention 32 kB.
+	// In Mach-O files, there's no limit, so we have to parse the file.
 	// On other systems, we're trying to read enough that
 	// we get the beginning of the text segment in the read.
 	// The offset where the text segment begins in a hello
@@ -1808,7 +1818,6 @@ func ReadBuildIDFromBinary(filename string) (id string, err error) {
 	//
 	//	Plan 9: 0x20
 	//	Windows: 0x600
-	//	Mach-O: 0x2000
 	//
 	f, err := os.Open(filename)
 	if err != nil {
@@ -1816,7 +1825,7 @@ func ReadBuildIDFromBinary(filename string) (id string, err error) {
 	}
 	defer f.Close()
 
-	data := make([]byte, 16*1024)
+	data := make([]byte, BuildIDReadSize)
 	_, err = io.ReadFull(f, data)
 	if err == io.ErrUnexpectedEOF {
 		err = nil
@@ -1828,7 +1837,17 @@ func ReadBuildIDFromBinary(filename string) (id string, err error) {
 	if bytes.HasPrefix(data, elfPrefix) {
 		return readELFGoBuildID(filename, f, data)
 	}
+	for _, m := range machoPrefixes {
+		if bytes.HasPrefix(data, m) {
+			return readMachoGoBuildID(filename, f, data)
+		}
+	}
+
+	return readRawGoBuildID(filename, data)
+}
 
+// readRawGoBuildID finds the raw build ID stored in text segment data.
+func readRawGoBuildID(filename string, data []byte) (id string, err error) {
 	i := bytes.Index(data, goBuildPrefix)
 	if i < 0 {
 		// Missing. Treat as successful but build ID empty.