debug/pe: add APIs for reading section def aux info

Add hooks to support reading of section definition symbol aux data
(including COMDAT information) from the aux symbols associated with
section definition symbols. The COFF symbol array made available by
"pe.File" includes entries for aux symbols, but doesn't expose their
structure (since it varies depending on the type of aux symbol). This
patch adds a function for returning a specific class of aux symbol
("type 5") that immediately follows a COFF symbol corresponding to a
section definition.

Updates #35006.
Updates #51868.

Change-Id: I21fcc057150f7a3c64f01a5961aabca0fa43399e
Reviewed-on: https://go-review.googlesource.com/c/go/+/394534
Reviewed-by: Alex Brainman <alex.brainman@gmail.com>
Reviewed-by: Cherry Mui <cherryyz@google.com>
Trust: Alex Brainman <alex.brainman@gmail.com>
Trust: Than McIntosh <thanm@google.com>
Run-TryBot: Than McIntosh <thanm@google.com>
TryBot-Result: Gopher Robot <gobot@golang.org>

4 files changed, 162 insertions, 0 deletions

diff --git a/src/debug/pe/section.go b/src/debug/pe/section.go
index b641158ecc..ee59dedeb4 100644
--- a/src/debug/pe/section.go
+++ b/src/debug/pe/section.go
@@ -109,3 +109,15 @@ func (s *Section) Data() ([]byte, error) {
 func (s *Section) Open() io.ReadSeeker {
 	return io.NewSectionReader(s.sr, 0, 1<<63-1)
 }
+
+// Section characteristics flags.
+const (
+	IMAGE_SCN_CNT_CODE               = 0x00000020
+	IMAGE_SCN_CNT_INITIALIZED_DATA   = 0x00000040
+	IMAGE_SCN_CNT_UNINITIALIZED_DATA = 0x00000080
+	IMAGE_SCN_LNK_COMDAT             = 0x00001000
+	IMAGE_SCN_MEM_DISCARDABLE        = 0x02000000
+	IMAGE_SCN_MEM_EXECUTE            = 0x20000000
+	IMAGE_SCN_MEM_READ               = 0x40000000
+	IMAGE_SCN_MEM_WRITE              = 0x80000000
+)
diff --git a/src/debug/pe/symbol.go b/src/debug/pe/symbol.go
index 7fa5948641..0dfd5d90b8 100644
--- a/src/debug/pe/symbol.go
+++ b/src/debug/pe/symbol.go
@@ -8,6 +8,7 @@ import (
 	"encoding/binary"
 	"fmt"
 	"io"
+	"unsafe"
 )
 
 const COFFSymbolSize = 18
@@ -96,3 +97,61 @@ type Symbol struct {
 	Type          uint16
 	StorageClass  uint8
 }
+
+// COFFSymbolAuxFormat5 describes the expected form of an aux symbol
+// attached to a section definition symbol. The PE format defines a
+// number of different aux symbol formats: format 1 for function
+// definitions, format 2 for .be and .ef symbols, and so on. Format 5
+// holds extra info associated with a section definition, including
+// number of relocations + line numbers, as well as COMDAT info. See
+// https://docs.microsoft.com/en-us/windows/win32/debug/pe-format#auxiliary-format-5-section-definitions
+// for more on what's going on here.
+type COFFSymbolAuxFormat5 struct {
+	Size           uint32
+	NumRelocs      uint16
+	NumLineNumbers uint16
+	Checksum       uint32
+	SecNum         uint16
+	Selection      uint8
+	_              [3]uint8 // padding
+}
+
+// These constants make up the possible values for the 'Selection'
+// field in an AuxFormat5.
+const (
+	IMAGE_COMDAT_SELECT_NODUPLICATES = 1
+	IMAGE_COMDAT_SELECT_ANY          = 2
+	IMAGE_COMDAT_SELECT_SAME_SIZE    = 3
+	IMAGE_COMDAT_SELECT_EXACT_MATCH  = 4
+	IMAGE_COMDAT_SELECT_ASSOCIATIVE  = 5
+	IMAGE_COMDAT_SELECT_LARGEST      = 6
+)
+
+// COFFSymbolReadSectionDefAux returns a blob of axiliary information
+// (including COMDAT info) for a section definition symbol. Here 'idx'
+// is the index of a section symbol in the main COFFSymbol array for
+// the File. Return value is a pointer to the appropriate aux symbol
+// struct. For more info, see:
+//
+// auxiliary symbols: https://docs.microsoft.com/en-us/windows/win32/debug/pe-format#auxiliary-symbol-records
+// COMDAT sections: https://docs.microsoft.com/en-us/windows/win32/debug/pe-format#comdat-sections-object-only
+// auxiliary info for section definitions: https://docs.microsoft.com/en-us/windows/win32/debug/pe-format#auxiliary-format-5-section-definitions
+//
+func (f *File) COFFSymbolReadSectionDefAux(idx int) (*COFFSymbolAuxFormat5, error) {
+	var rv *COFFSymbolAuxFormat5
+	if idx < 0 || idx > len(f.COFFSymbols) {
+		return rv, fmt.Errorf("invalid symbol index")
+	}
+	pesym := &f.COFFSymbols[idx]
+	const IMAGE_SYM_CLASS_STATIC = 3
+	if pesym.StorageClass != uint8(IMAGE_SYM_CLASS_STATIC) {
+		return rv, fmt.Errorf("incorrect symbol storage class")
+	}
+	if pesym.NumberOfAuxSymbols == 0 || idx+1 >= len(f.COFFSymbols) {
+		return rv, fmt.Errorf("aux symbol unavailable")
+	}
+	// Locate and return a pointer to the successor aux symbol.
+	pesymn := &f.COFFSymbols[idx+1]
+	rv = (*COFFSymbolAuxFormat5)(unsafe.Pointer(pesymn))
+	return rv, nil
+}
diff --git a/src/debug/pe/symbols_test.go b/src/debug/pe/symbols_test.go
new file mode 100644
index 0000000000..c4dcd95391
--- /dev/null
+++ b/src/debug/pe/symbols_test.go
@@ -0,0 +1,91 @@
+// Copyright 2022 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 pe
+
+import (
+	"fmt"
+	"testing"
+)
+
+type testpoint struct {
+	name   string
+	ok     bool
+	err    string
+	auxstr string
+}
+
+func TestReadCOFFSymbolAuxInfo(t *testing.T) {
+	testpoints := map[int]testpoint{
+		39: testpoint{
+			name:   ".rdata$.refptr.__native_startup_lock",
+			ok:     true,
+			auxstr: "{Size:8 NumRelocs:1 NumLineNumbers:0 Checksum:0 SecNum:16 Selection:2 _:[0 0 0]}",
+		},
+		81: testpoint{
+			name:   ".debug_line",
+			ok:     true,
+			auxstr: "{Size:994 NumRelocs:1 NumLineNumbers:0 Checksum:1624223678 SecNum:32 Selection:0 _:[0 0 0]}",
+		},
+		155: testpoint{
+			name: ".file",
+			ok:   false,
+			err:  "incorrect symbol storage class",
+		},
+	}
+
+	// The testdata PE object file below was selected from a release
+	// build from https://github.com/mstorsjo/llvm-mingw/releases; it
+	// corresponds to the mingw "crt2.o" object. The object itself was
+	// built using an x86_64 HOST=linux TARGET=windows clang cross
+	// compiler based on LLVM 13. More build details can be found at
+	// https://github.com/mstorsjo/llvm-mingw/releases.
+	f, err := Open("testdata/llvm-mingw-20211002-msvcrt-x86_64-crt2")
+	if err != nil {
+		t.Errorf("open failed with %v", err)
+	}
+	defer f.Close()
+	for k := range f.COFFSymbols {
+		tp, ok := testpoints[k]
+		if !ok {
+			continue
+		}
+		sym := &f.COFFSymbols[k]
+		if sym.NumberOfAuxSymbols == 0 {
+			t.Errorf("expected aux symbols for sym %d", k)
+			continue
+		}
+		name, nerr := sym.FullName(f.StringTable)
+		if nerr != nil {
+			t.Errorf("FullName(%d) failed with %v", k, nerr)
+			continue
+		}
+		if name != tp.name {
+			t.Errorf("name check for %d, got %s want %s", k, name, tp.name)
+			continue
+		}
+		ap, err := f.COFFSymbolReadSectionDefAux(k)
+		if tp.ok {
+			if err != nil {
+				t.Errorf("unexpected failure on %d, got error %v", k, err)
+				continue
+			}
+			got := fmt.Sprintf("%+v", *ap)
+			if got != tp.auxstr {
+				t.Errorf("COFFSymbolReadSectionDefAux on %d bad return, got:\n%s\nwant:\n%s\n", k, got, tp.auxstr)
+				continue
+			}
+		} else {
+			if err == nil {
+				t.Errorf("unexpected non-failure on %d", k)
+				continue
+			}
+			got := fmt.Sprintf("%v", err)
+			if got != tp.err {
+				t.Errorf("COFFSymbolReadSectionDefAux %d wrong error, got %q want %q", k, got, tp.err)
+				continue
+			}
+		}
+	}
+}
diff --git a/src/debug/pe/testdata/llvm-mingw-20211002-msvcrt-x86_64-crt2 b/src/debug/pe/testdata/llvm-mingw-20211002-msvcrt-x86_64-crt2
new file mode 100644
index 0000000000..5576c1c49e
--- /dev/null
+++ b/src/debug/pe/testdata/llvm-mingw-20211002-msvcrt-x86_64-crt2