debug/dwarf: heuristically handle both UNIX and Windows paths

Currently debug/dwarf assumes all paths in line tables will be
UNIX-style paths, which obviously isn't the case for binaries built on
Windows. However, we can't simply switch from the path package to the
filepath package because we don't know that we're running on the same
host type that built the binary and we want this to work even if we're
not. This is essentially the approach taken by GDB, which treats paths
in accordance with the system GDB itself is compiled for. In fact, we
can't even guess the compilation system from the type of the binary
because it may have been cross-compiled.

We fix this by heuristically determining whether paths are UNIX-style
or DOS-style by looking for a drive letter or UNC path. If we see a
DOS-style path, we use appropriate logic for determining whether the
path is absolute and for joining two paths. This is helped by the fact
that we should basically always be starting with an absolute path.
However, it could mistake a relative UNIX-style path that begins with
a directory like "C:" for an absolute DOS-style path. There doesn't
seem to be any way around this.

Fixes #19784.

Change-Id: Ie13b546d2f1dcd8b02e668583a627b571b281588
Reviewed-on: https://go-review.googlesource.com/44017
Run-TryBot: Austin Clements <[email protected]>
TryBot-Result: Gobot Gobot <[email protected]>
Reviewed-by: Ian Lance Taylor <[email protected]>
Reviewed-by: Alex Brainman <[email protected]>

Author: aclements

src/debug/dwarf/export_test.go

@@ -0,0 +1,7 @@
+// Copyright 2017 The Go Authors. All rights reserved.
+// Use of this source code is governed by a BSD-style
+// license that can be found in the LICENSE file.
+
+package dwarf
+
+var PathJoin = pathJoin

src/debug/dwarf/line.go

@@ -9,6 +9,7 @@ import (
 	"fmt"
 	"io"
 	"path"
+	"strings"
 )
 
 // A LineReader reads a sequence of LineEntry structures from a DWARF
@@ -247,10 +248,10 @@ func (r *LineReader) readHeader() error {
 		if len(directory) == 0 {
 			break
 		}
-		if !path.IsAbs(directory) {
+		if !pathIsAbs(directory) {
 			// Relative paths are implicitly relative to
 			// the compilation directory.
-			directory = path.Join(r.directories[0], directory)
+			directory = pathJoin(r.directories[0], directory)
 		}
 		r.directories = append(r.directories, directory)
 	}
@@ -283,11 +284,11 @@ func (r *LineReader) readFileEntry() (bool, error) {
 	}
 	off := r.buf.off
 	dirIndex := int(r.buf.uint())
-	if !path.IsAbs(name) {
+	if !pathIsAbs(name) {
 		if dirIndex >= len(r.directories) {
 			return false, DecodeError{"line", off, "directory index too large"}
 		}
-		name = path.Join(r.directories[dirIndex], name)
+		name = pathJoin(r.directories[dirIndex], name)
 	}
 	mtime := r.buf.uint()
 	length := int(r.buf.uint())
@@ -588,3 +589,68 @@ func (r *LineReader) SeekPC(pc uint64, entry *LineEntry) error {
 		*entry = next
 	}
 }
+
+// pathIsAbs returns whether path is an absolute path (or "full path
+// name" in DWARF parlance). This is in "whatever form makes sense for
+// the host system", so this accepts both UNIX-style and DOS-style
+// absolute paths. We avoid the filepath package because we want this
+// to behave the same regardless of our host system and because we
+// don't know what system the paths came from.
+func pathIsAbs(path string) bool {
+	_, path = splitDrive(path)
+	return len(path) > 0 && (path[0] == '/' || path[0] == '\\')
+}
+
+// pathJoin joins dirname and filename. filename must be relative.
+// DWARF paths can be UNIX-style or DOS-style, so this handles both.
+func pathJoin(dirname, filename string) string {
+	if len(dirname) == 0 {
+		return filename
+	}
+	// dirname should be absolute, which means we can determine
+	// whether it's a DOS path reasonably reliably by looking for
+	// a drive letter or UNC path.
+	drive, dirname := splitDrive(dirname)
+	if drive == "" {
+		// UNIX-style path.
+		return path.Join(dirname, filename)
+	}
+	// DOS-style path.
+	drive2, filename := splitDrive(filename)
+	if drive2 != "" {
+		if strings.ToLower(drive) != strings.ToLower(drive2) {
+			// Different drives. There's not much we can
+			// do here, so just ignore the directory.
+			return drive2 + filename
+		}
+		// Drives are the same. Ignore drive on filename.
+	}
+	if !(strings.HasSuffix(dirname, "/") || strings.HasSuffix(dirname, `\`)) && dirname != "" {
+		dirname += `\`
+	}
+	return drive + dirname + filename
+}
+
+// splitDrive splits the DOS drive letter or UNC share point from
+// path, if any. path == drive + rest
+func splitDrive(path string) (drive, rest string) {
+	if len(path) >= 2 && path[1] == ':' {
+		if c := path[0]; 'a' <= c && c <= 'z' || 'A' <= c && c <= 'Z' {
+			return path[:2], path[2:]
+		}
+	}
+	if len(path) > 3 && (path[0] == '\\' || path[0] == '/') && (path[1] == '\\' || path[1] == '/') {
+		// Normalize the path so we can search for just \ below.
+		npath := strings.Replace(path, "/", `\`, -1)
+		// Get the host part, which must be non-empty.
+		slash1 := strings.IndexByte(npath[2:], '\\') + 2
+		if slash1 > 2 {
+			// Get the mount-point part, which must be non-empty.
+			slash2 := strings.IndexByte(npath[slash1+1:], '\\') + slash1 + 1
+			if slash2 > slash1 {
+				return path[:slash2], path[slash2:]
+			}
+		}
+	}
+	return "", path
+}

src/debug/dwarf/line_test.go

@@ -7,6 +7,7 @@ package dwarf_test
 import (
 	. "debug/dwarf"
 	"io"
+	"strings"
 	"testing"
 )
 
@@ -46,6 +47,46 @@ func TestLineELFGCC(t *testing.T) {
 	testLineTable(t, want, elfData(t, "testdata/line-gcc.elf"))
 }
 
+func TestLineGCCWindows(t *testing.T) {
+	// Generated by:
+	//   > gcc --version
+	//   gcc (tdm64-1) 4.9.2
+	//   > gcc -g -o line-gcc-win.bin line1.c C:\workdir\go\src\debug\dwarf\testdata\line2.c
+
+	toWindows := func(lf *LineFile) *LineFile {
+		lf2 := *lf
+		lf2.Name = strings.Replace(lf2.Name, "/home/austin/go.dev/", "C:\\workdir\\go\\", -1)
+		lf2.Name = strings.Replace(lf2.Name, "/", "\\", -1)
+		return &lf2
+	}
+	file1C := toWindows(file1C)
+	file1H := toWindows(file1H)
+	file2C := toWindows(file2C)
+
+	// Line table based on objdump --dwarf=rawline,decodedline
+	want := []LineEntry{
+		{Address: 0x401530, File: file1H, Line: 2, IsStmt: true},
+		{Address: 0x401538, File: file1H, Line: 5, IsStmt: true},
+		{Address: 0x401541, File: file1H, Line: 6, IsStmt: true, Discriminator: 3},
+		{Address: 0x40154b, File: file1H, Line: 5, IsStmt: true, Discriminator: 3},
+		{Address: 0x40154f, File: file1H, Line: 5, IsStmt: false, Discriminator: 1},
+		{Address: 0x401555, File: file1H, Line: 7, IsStmt: true},
+		{Address: 0x40155b, File: file1C, Line: 6, IsStmt: true},
+		{Address: 0x401563, File: file1C, Line: 6, IsStmt: true},
+		{Address: 0x401568, File: file1C, Line: 7, IsStmt: true},
+		{Address: 0x40156d, File: file1C, Line: 8, IsStmt: true},
+		{Address: 0x401572, File: file1C, Line: 9, IsStmt: true},
+		{Address: 0x401578, EndSequence: true},
+
+		{Address: 0x401580, File: file2C, Line: 4, IsStmt: true},
+		{Address: 0x401588, File: file2C, Line: 5, IsStmt: true},
+		{Address: 0x401595, File: file2C, Line: 6, IsStmt: true},
+		{Address: 0x40159b, EndSequence: true},
+	}
+
+	testLineTable(t, want, peData(t, "testdata/line-gcc-win.bin"))
+}
+
 func TestLineELFClang(t *testing.T) {
 	// Generated by:
 	//   # clang --version | head -n1
@@ -183,6 +224,11 @@ func testLineTable(t *testing.T, want []LineEntry, d *Data) {
 				}
 				t.Fatal("lr.Next:", err)
 			}
+			// Ignore sources from the Windows build environment.
+			if strings.HasPrefix(line.File.Name, "C:\\crossdev\\") ||
+				strings.HasPrefix(line.File.Name, "C:/crossdev/") {
+				continue
+			}
 			got = append(got, line)
 		}
 	}
@@ -227,3 +273,42 @@ func dumpLines(t *testing.T, lines []LineEntry) {
 		t.Logf("  %+v File:%+v", l, l.File)
 	}
 }
+
+type joinTest struct {
+	dirname, filename string
+	path              string
+}
+
+var joinTests = []joinTest{
+	{"a", "b", "a/b"},
+	{"a", "", "a"},
+	{"", "b", "b"},
+	{"/a", "b", "/a/b"},
+	{"/a/", "b", "/a/b"},
+
+	{`C:\Windows\`, `System32`, `C:\Windows\System32`},
+	{`C:\Windows\`, ``, `C:\Windows\`},
+	{`C:\`, `Windows`, `C:\Windows`},
+	{`C:\Windows\`, `C:System32`, `C:\Windows\System32`},
+	{`C:\Windows`, `a/b`, `C:\Windows\a/b`},
+	{`\\host\share\`, `foo`, `\\host\share\foo`},
+	{`\\host\share\`, `foo\bar`, `\\host\share\foo\bar`},
+	{`//host/share/`, `foo/bar`, `//host/share/foo/bar`},
+
+	// The following are "best effort". We shouldn't see relative
+	// base directories in DWARF, but these test that pathJoin
+	// doesn't fail miserably if it sees one.
+	{`C:`, `a`, `C:a`},
+	{`C:`, `a\b`, `C:a\b`},
+	{`C:.`, `a`, `C:.\a`},
+	{`C:a`, `b`, `C:a\b`},
+}
+
+func TestPathJoin(t *testing.T) {
+	for _, test := range joinTests {
+		got := PathJoin(test.dirname, test.filename)
+		if test.path != got {
+			t.Errorf("pathJoin(%q, %q) = %q, want %q", test.dirname, test.filename, got, test.path)
+		}
+	}
+}

src/debug/dwarf/testdata/line-gcc-win.bin

@@ -8,6 +8,7 @@ import (
 	. "debug/dwarf"
 	"debug/elf"
 	"debug/macho"
+	"debug/pe"
 	"testing"
 )
 
@@ -67,6 +68,19 @@ func machoData(t *testing.T, name string) *Data {
 	return d
 }
 
+func peData(t *testing.T, name string) *Data {
+	f, err := pe.Open(name)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	d, err := f.DWARF()
+	if err != nil {
+		t.Fatal(err)
+	}
+	return d
+}
+
 func TestTypedefsELF(t *testing.T) { testTypedefs(t, elfData(t, "testdata/typedef.elf"), "elf") }
 
 func TestTypedefsMachO(t *testing.T) {