[COFF] Move section name encoding into BinaryFormat

Large COFF section names are moved into the string table and the
section header field is the offset into the string table encoded in
ASCII for offset smaller than 7 digits and in base64 for larger
offsets.

The operation of taking the string table offsets is done in a few
places in the codebase, so it is helpful to move this operation into
`BinaryFormat` so that it can be shared everywhere it's done.

So this patch takes the implementation of this operation from
`llvm/lib/MC/WinCOFFObjectWriter.cpp` and moves it into `BinaryFormat`.

Reviewed By: jhenderson, rnk

Differential Revision: https://reviews.llvm.org/D118793

Author: npmiller

llvm/include/llvm/BinaryFormat/COFF.h

@@ -731,6 +731,10 @@ inline bool isReservedSectionNumber(int32_t SectionNumber) {
   return SectionNumber <= 0;
 }
 
+/// Encode section name based on string table offset.
+/// The size of Out must be at least COFF::NameSize.
+bool encodeSectionName(char *Out, uint64_t Offset);
+
 } // End namespace COFF.
 } // End namespace llvm.
 

llvm/lib/BinaryFormat/CMakeLists.txt

@@ -1,5 +1,6 @@
 add_llvm_component_library(LLVMBinaryFormat
   AMDGPUMetadataVerifier.cpp
+  COFF.cpp
   Dwarf.cpp
   ELF.cpp
   MachO.cpp

llvm/lib/BinaryFormat/COFF.cpp

@@ -0,0 +1,57 @@
+//===- llvm/BinaryFormat/COFF.cpp - The COFF format -----------------------===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+
+#include "llvm/BinaryFormat/COFF.h"
+#include "llvm/ADT/SmallVector.h"
+#include "llvm/ADT/Twine.h"
+
+// Maximum offsets for different string table entry encodings.
+enum : unsigned { Max7DecimalOffset = 9999999U };
+enum : uint64_t { MaxBase64Offset = 0xFFFFFFFFFULL }; // 64^6, including 0
+
+// Encode a string table entry offset in base 64, padded to 6 chars, and
+// prefixed with a double slash: '//AAAAAA', '//AAAAAB', ...
+// Buffer must be at least 8 bytes large. No terminating null appended.
+static void encodeBase64StringEntry(char *Buffer, uint64_t Value) {
+  assert(Value > Max7DecimalOffset && Value <= MaxBase64Offset &&
+         "Illegal section name encoding for value");
+
+  static const char Alphabet[] = "ABCDEFGHIJKLMNOPQRSTUVWXYZ"
+                                 "abcdefghijklmnopqrstuvwxyz"
+                                 "0123456789+/";
+
+  Buffer[0] = '/';
+  Buffer[1] = '/';
+
+  char *Ptr = Buffer + 7;
+  for (unsigned i = 0; i < 6; ++i) {
+    unsigned Rem = Value % 64;
+    Value /= 64;
+    *(Ptr--) = Alphabet[Rem];
+  }
+}
+
+bool llvm::COFF::encodeSectionName(char *Out, uint64_t Offset) {
+  if (Offset <= Max7DecimalOffset) {
+    // Offsets of 7 digits or less are encoded in ASCII.
+    SmallVector<char, COFF::NameSize> Buffer;
+    Twine('/').concat(Twine(Offset)).toVector(Buffer);
+    assert(Buffer.size() <= COFF::NameSize && Buffer.size() >= 2);
+    std::memcpy(Out, Buffer.data(), Buffer.size());
+    return true;
+  }
+
+  if (Offset <= MaxBase64Offset) {
+    // Starting with 10,000,000, offsets are encoded as base64.
+    encodeBase64StringEntry(Out, Offset);
+    return true;
+  }
+
+  // The offset is too large to be encoded.
+  return false;
+}

llvm/lib/MC/WinCOFFObjectWriter.cpp

@@ -451,52 +451,15 @@ void WinCOFFObjectWriter::DefineSymbol(const MCSymbol &MCSym,
   Sym->MC = &MCSym;
 }
 
-// Maximum offsets for different string table entry encodings.
-enum : unsigned { Max7DecimalOffset = 9999999U };
-enum : uint64_t { MaxBase64Offset = 0xFFFFFFFFFULL }; // 64^6, including 0
-
-// Encode a string table entry offset in base 64, padded to 6 chars, and
-// prefixed with a double slash: '//AAAAAA', '//AAAAAB', ...
-// Buffer must be at least 8 bytes large. No terminating null appended.
-static void encodeBase64StringEntry(char *Buffer, uint64_t Value) {
-  assert(Value > Max7DecimalOffset && Value <= MaxBase64Offset &&
-         "Illegal section name encoding for value");
-
-  static const char Alphabet[] = "ABCDEFGHIJKLMNOPQRSTUVWXYZ"
-                                 "abcdefghijklmnopqrstuvwxyz"
-                                 "0123456789+/";
-
-  Buffer[0] = '/';
-  Buffer[1] = '/';
-
-  char *Ptr = Buffer + 7;
-  for (unsigned i = 0; i < 6; ++i) {
-    unsigned Rem = Value % 64;
-    Value /= 64;
-    *(Ptr--) = Alphabet[Rem];
-  }
-}
-
 void WinCOFFObjectWriter::SetSectionName(COFFSection &S) {
   if (S.Name.size() <= COFF::NameSize) {
     std::memcpy(S.Header.Name, S.Name.c_str(), S.Name.size());
     return;
   }
 
   uint64_t StringTableEntry = Strings.getOffset(S.Name);
-  if (StringTableEntry <= Max7DecimalOffset) {
-    SmallVector<char, COFF::NameSize> Buffer;
-    Twine('/').concat(Twine(StringTableEntry)).toVector(Buffer);
-    assert(Buffer.size() <= COFF::NameSize && Buffer.size() >= 2);
-    std::memcpy(S.Header.Name, Buffer.data(), Buffer.size());
-    return;
-  }
-  if (StringTableEntry <= MaxBase64Offset) {
-    // Starting with 10,000,000, offsets are encoded as base64.
-    encodeBase64StringEntry(S.Header.Name, StringTableEntry);
-    return;
-  }
-  report_fatal_error("COFF string table is greater than 64 GB.");
+  if (!COFF::encodeSectionName(S.Header.Name, StringTableEntry))
+    report_fatal_error("COFF string table is greater than 64 GB.");
 }
 
 void WinCOFFObjectWriter::SetSymbolName(COFFSymbol &S) {