[lld-macho] Support Obj-C symbols in order files

[int3]

Summary

Obj-C symbols may have spaces and colons, which our previous order file
parser would be confused by. The order file format has made the very unfortunate
choice of using colons for its delimiters, which means that we have to use
heuristics to determine if a given colon is part of a symbol or not...

[int3]

line wrapping

[int3]

lld/test/MachO/order-file.s

8

I'm not sure why objdump decided to start printing _bar instead of our foo symbol, but I guess it doesn't really matter (they alias to the same address)

[int3]

rebase

lld/MachO/Driver.cpp

static void addFileList(StringRef path) {
   Optional<MemoryBufferRef> buffer = readFile(path);
   if (!buffer)
     return;
   MemoryBufferRef mbref = *buffer;
   for (StringRef path : args::getLines(mbref))
     addFile(path, false);
 }
 
-static std::array<StringRef, 6> archNames{"arm",    "arm64", "i386",
-                                          "x86_64", "ppc",   "ppc64"};
-static bool isArchString(StringRef s) {
-  static DenseSet<StringRef> archNamesSet(archNames.begin(), archNames.end());
-  return archNamesSet.find(s) != archNamesSet.end();
-}
-
 // An order file has one entry per line, in the following format:
 //
-//   <arch>:<object file>:<symbol name>
+//   <cpu>:<object file>:<symbol name>
 //
-// <arch> and <object file> are optional. If not specified, then that entry
-// matches any symbol of that name.
+// <cpu> and <object file> are optional. If not specified, then that entry
+// matches any symbol of that name. Parsing this format is not quite
+// straightforward because the symbol name itself can contain colons, so when
+// encountering a colon, we consider the preceding characters to decide if it
+// can be a valid CPU type or file path.
 //
 // If a symbol is matched by multiple entries, then it takes the lowest-ordered
 // entry (the one nearest to the front of the list.)
 //
 // The file can also have line comments that start with '#'.
 static void parseOrderFile(StringRef path) {
   Optional<MemoryBufferRef> buffer = readFile(path);
   if (!buffer) {
     error("Could not read order file at " + path);
     return;
   }
 
   MemoryBufferRef mbref = *buffer;
   size_t priority = std::numeric_limits<size_t>::max();
-  for (StringRef rest : args::getLines(mbref)) {
-    StringRef arch, objectFile, symbol;
-
-    std::array<StringRef, 3> fields;
-    uint8_t fieldCount = 0;
-    while (rest != "" && fieldCount < 3) {
-      std::pair<StringRef, StringRef> p = getToken(rest, ": \t\n\v\f\r");
-      StringRef tok = p.first;
-      rest = p.second;
-
-      // Check if we have a comment
-      if (tok == "" || tok[0] == '#')
-        break;
-
-      fields[fieldCount++] = tok;
-    }
-
-    switch (fieldCount) {
-    case 3:
-      arch = fields[0];
-      objectFile = fields[1];
-      symbol = fields[2];
-      break;
-    case 2:
-      (isArchString(fields[0]) ? arch : objectFile) = fields[0];
-      symbol = fields[1];
-      break;
-    case 1:
-      symbol = fields[0];
-      break;
-    case 0:
-      break;
-    default:
-      llvm_unreachable("too many fields in order file");
-    }
-
-    if (!arch.empty()) {
-      if (!isArchString(arch)) {
-        error("invalid arch \"" + arch + "\" in order file: expected one of " +
-              llvm::join(archNames, ", "));
-        continue;
-      }
+  for (StringRef line : args::getLines(mbref)) {
+    StringRef objectFile, symbol;
+    line = line.take_until([](char c) { return c == '#'; }); // ignore comments
+    line = line.ltrim();
+
+    CPUType cpuType = StringSwitch<CPUType>(line)
+                          .StartsWith("i386:", CPU_TYPE_I386)
+                          .StartsWith("x86_64:", CPU_TYPE_X86_64)
+                          .StartsWith("arm:", CPU_TYPE_ARM)
+                          .StartsWith("arm64:", CPU_TYPE_ARM64)
+                          .StartsWith("ppc:", CPU_TYPE_POWERPC)
+                          .StartsWith("ppc64:", CPU_TYPE_POWERPC64)
+                          .Default(CPU_TYPE_ANY);
+    // Drop the CPU type as well as the colon
+    if (cpuType != CPU_TYPE_ANY)
+      line = line.drop_until([](char c) { return c == ':'; }).drop_front();
+    // TODO: Update when we extend support for other CPUs
+    if (cpuType != CPU_TYPE_ANY && cpuType != CPU_TYPE_X86_64)
 
-      // TODO: Update when we extend support for other archs
-      if (arch != "x86_64")
-        continue;
+    constexpr std::array<StringRef, 2> fileEnds = {".o:", ".o):"};
+    for (StringRef fileEnd : fileEnds) {
+      size_t pos = line.find(fileEnd);
+      if (pos != StringRef::npos) {
+        // Split the string around the colon
+        objectFile = line.take_front(pos + fileEnd.size() - 1);
+        line = line.drop_front(pos + fileEnd.size());
+        break;
       }
-
-    if (!objectFile.empty() && !objectFile.endswith(".o")) {
-      error("invalid object file name \"" + objectFile +
-            "\" in order file: should end with .o");
-      continue;
     }
+    symbol = line.trim();
 
     if (!symbol.empty()) {
       SymbolPriorityEntry &entry = config->priorities[symbol];
       if (!objectFile.empty())
         entry.objectFiles.insert(std::make_pair(objectFile, priority));
       else
         entry.anyObjectFile = std::max(entry.anyObjectFile, priority);
     }

lld/test/MachO/invalid/order-file-bad-arch.test

-# REQUIRES: x86
-# RUN: echo ".globl _main; .text; _main: ret" | llvm-mc -filetype=obj -triple=x86_64-apple-darwin -o %t.o
-# RUN: not %lld -o %t %t.o -order_file %s 2>&1 | FileCheck %s
-# CHECK: error: invalid arch "sparc" in order file:  expected one of arm, arm64, i386, x86_64, ppc, ppc64
-# CHECK-EMPTY:
-
-_barsymbol
-sparc:hello.o:_foosymbol
-i386:hello.o:_foosymbol

lld/test/MachO/invalid/order-file-bad-objfile.test

-# REQUIRES: x86
-# RUN: echo ".globl _main; .text; _main: ret" | llvm-mc -filetype=obj -triple=x86_64-apple-darwin -o %t.o
-# RUN: not %lld -o %t %t.o -order_file %s 2>&1 | FileCheck %s
-# CHECK: invalid object file name "helloo" in order file: should end with .o
-# CHECK: invalid object file name "z80" in order file: should end with .o
-# CHECK-EMPTY:
-
-_barsymbol
-x86_64:helloo:_foosymbol
-z80:_foosymbol

lld/test/MachO/order-file.s

 # REQUIRES: x86
 # RUN: rm -rf %t; split-file %s %t
 # RUN: llvm-mc -filetype=obj -triple=x86_64-apple-darwin %t/test.s -o %t/test.o
 # RUN: llvm-mc -filetype=obj -triple=x86_64-apple-darwin %t/foo.s -o %t/foo.o
 # RUN: rm -f %t/foo.a
 # RUN: llvm-ar rcs %t/foo.a %t/foo.o
 
-# FOO-FIRST: <_foo>:
+# FOO-FIRST: <_bar>:
 # FOO-FIRST: <_main>:
 
 # FOO-SECOND: <_main>:
-# FOO-SECOND: <_foo>:
+# FOO-SECOND: <_bar>:
 
 #--- ord-1
-_foo # just a comment
+-[Foo doFoo:andBar:] # just a comment
 _main # another comment
 # RUN: %lld -lSystem -o %t/test-1 %t/test.o %t/foo.o -order_file %t/ord-1
 # RUN: llvm-objdump -d %t/test-1 | FileCheck %s --check-prefix=FOO-FIRST
 ## Output should be the same regardless of the command-line order of object files
 # RUN: %lld -lSystem -o %t/test-1 %t/foo.o %t/test.o -order_file %t/ord-1
 # RUN: llvm-objdump -d %t/test-1 | FileCheck %s --check-prefix=FOO-FIRST
 
 #--- ord-2
 _main # just a comment
-_foo # another comment
+-[Foo doFoo:andBar:] # another comment
 # RUN: %lld -lSystem -o %t/test-2 %t/test.o %t/foo.o -order_file %t/ord-2
 # RUN: llvm-objdump -d %t/test-2 | FileCheck %s --check-prefix=FOO-SECOND
 # RUN: %lld -lSystem -o %t/test-2 %t/foo.o %t/test.o -order_file %t/ord-2
 # RUN: llvm-objdump -d %t/test-2 | FileCheck %s --check-prefix=FOO-SECOND
 
 #--- ord-file-match
-foo.o:_foo
+foo.o:-[Foo doFoo:andBar:]
 _main
 # RUN: %lld -lSystem -o %t/test-file-match %t/test.o %t/foo.o -order_file %t/ord-file-match
 # RUN: llvm-objdump -d %t/test-file-match | FileCheck %s --check-prefix=FOO-FIRST
 ## Output should be the same regardless of the command-line order of object files
 # RUN: %lld -lSystem -o %t/test-file-match %t/foo.o %t/test.o -order_file %t/ord-file-match
 # RUN: llvm-objdump -d %t/test-file-match | FileCheck %s --check-prefix=FOO-FIRST
 
 #--- ord-file-nomatch
-bar.o:_foo
+bar.o:-[Foo doFoo:andBar:]
 _main
-_foo
+-[Foo doFoo:andBar:]
 # RUN: %lld -lSystem -o %t/test-file-nomatch %t/test.o %t/foo.o -order_file %t/ord-file-nomatch
 # RUN: llvm-objdump -d %t/test-file-nomatch | FileCheck %s --check-prefix=FOO-SECOND
 # RUN: %lld -lSystem -o %t/test-file-nomatch %t/foo.o %t/test.o -order_file %t/ord-file-nomatch
 # RUN: llvm-objdump -d %t/test-file-nomatch | FileCheck %s --check-prefix=FOO-SECOND
 
 #--- ord-arch-match
-x86_64:_foo
+x86_64:-[Foo doFoo:andBar:]
 _main
 # RUN: %lld -lSystem -o %t/test-arch-match %t/test.o %t/foo.o -order_file %t/ord-arch-match
 # RUN: llvm-objdump -d %t/test-arch-match | FileCheck %s --check-prefix=FOO-FIRST
 # RUN: %lld -lSystem -o %t/test-arch-match %t/foo.o %t/test.o -order_file %t/ord-arch-match
 # RUN: llvm-objdump -d %t/test-arch-match | FileCheck %s --check-prefix=FOO-FIRST
 
 #--- ord-arch-nomatch
-ppc:_foo
+ppc:-[Foo doFoo:andBar:]
 _main
-_foo
+-[Foo doFoo:andBar:]
 # RUN: %lld -lSystem -o %t/test-arch-nomatch %t/test.o %t/foo.o -order_file %t/ord-arch-nomatch
 # RUN: llvm-objdump -d %t/test-arch-nomatch | FileCheck %s --check-prefix=FOO-SECOND
 # RUN: %lld -lSystem -o %t/test-arch-nomatch %t/foo.o %t/test.o -order_file %t/ord-arch-nomatch
 # RUN: llvm-objdump -d %t/test-arch-nomatch | FileCheck %s --check-prefix=FOO-SECOND
 
 #--- ord-arch-file-match
-x86_64:bar.o:_foo
+x86_64:bar.o:-[Foo doFoo:andBar:]
 _main
 # RUN: %lld -lSystem -o %t/test-arch-match %t/test.o %t/foo.o -order_file %t/ord-arch-match
 # RUN: llvm-objdump -d %t/test-arch-match | FileCheck %s --check-prefix=FOO-FIRST
 # RUN: %lld -lSystem -o %t/test-arch-match %t/foo.o %t/test.o -order_file %t/ord-arch-match
 # RUN: llvm-objdump -d %t/test-arch-match | FileCheck %s --check-prefix=FOO-FIRST
 
 ## Test archives
 
 # RUN: %lld -lSystem -o %t/test-archive-1 %t/test.o %t/foo.a -order_file %t/ord-1
 # RUN: llvm-objdump -d %t/test-archive-1 | FileCheck %s --check-prefix=FOO-FIRST
 # RUN: %lld -lSystem -o %t/test-archive-1 %t/foo.a %t/test.o -order_file %t/ord-1
 # RUN: llvm-objdump -d %t/test-archive-1 | FileCheck %s --check-prefix=FOO-FIRST
 
 # RUN: %lld -lSystem -o %t/test-archive-file-no-match %t/test.o %t/foo.a -order_file %t/ord-file-nomatch
 # RUN: llvm-objdump -d %t/test-archive-file-no-match | FileCheck %s --check-prefix=FOO-SECOND
 # RUN: %lld -lSystem -o %t/test-archive %t/foo.a %t/test.o -order_file %t/ord-file-nomatch
 # RUN: llvm-objdump -d %t/test-archive-file-no-match | FileCheck %s --check-prefix=FOO-SECOND
 
 ## The following tests check that if an address is matched by multiple order
 ## file entries, it should always use the lowest-ordered match.
 
 #--- ord-multiple-1
-_foo
+-[Foo doFoo:andBar:]
 _main
-foo.o:_foo
+foo.o:-[Foo doFoo:andBar:]
 # RUN: %lld -lSystem -o %t/test-1 %t/test.o %t/foo.o -order_file %t/ord-multiple-1
 # RUN: llvm-objdump -d %t/test-1 | FileCheck %s --check-prefix=FOO-FIRST
 # RUN: %lld -lSystem -o %t/test-1 %t/foo.o %t/test.o -order_file %t/ord-multiple-1
 # RUN: llvm-objdump -d %t/test-1 | FileCheck %s --check-prefix=FOO-FIRST
 
 #--- ord-multiple-2
-foo.o:_foo
+foo.o:-[Foo doFoo:andBar:]
 _main
-_foo
+-[Foo doFoo:andBar:]
 # RUN: %lld -lSystem -o %t/test-2 %t/test.o %t/foo.o -order_file %t/ord-multiple-2
 # RUN: llvm-objdump -d %t/test-2 | FileCheck %s --check-prefix=FOO-FIRST
 # RUN: %lld -lSystem -o %t/test-2 %t/foo.o %t/test.o -order_file %t/ord-multiple-2
 # RUN: llvm-objdump -d %t/test-2 | FileCheck %s --check-prefix=FOO-FIRST
 
 #--- ord-multiple-3
-_foo
+-[Foo doFoo:andBar:]
 _main
-_foo
+-[Foo doFoo:andBar:]
 # RUN: %lld -lSystem -o %t/test-3 %t/test.o %t/foo.o -order_file %t/ord-multiple-3
 # RUN: llvm-objdump -d %t/test-3 | FileCheck %s --check-prefix=FOO-FIRST
 # RUN: %lld -lSystem -o %t/test-3 %t/foo.o %t/test.o -order_file %t/ord-multiple-3
 # RUN: llvm-objdump -d %t/test-3 | FileCheck %s --check-prefix=FOO-FIRST
 
 #--- ord-multiple-4
-foo.o:_foo
+foo.o:-[Foo doFoo:andBar:]
 _main
-foo.o:_foo
+foo.o:-[Foo doFoo:andBar:]
 # RUN: %lld -lSystem -o %t/test-4 %t/test.o %t/foo.o -order_file %t/ord-multiple-4
 # RUN: llvm-objdump -d %t/test-4 | FileCheck %s --check-prefix=FOO-FIRST
 # RUN: %lld -lSystem -o %t/test-4 %t/foo.o %t/test.o -order_file %t/ord-multiple-4
 # RUN: llvm-objdump -d %t/test-4 | FileCheck %s --check-prefix=FOO-FIRST
 
-## _foo and _bar both point to the same location. When both symbols appear in
+## -[Foo doFoo:andBar:] and _bar both point to the same location. When both symbols appear in
 ## an order file, the location in question should be ordered according to the
 ## lowest-ordered symbol that references it.
 #--- ord-alias
 _bar
 _main
-_foo
+-[Foo doFoo:andBar:]
 # RUN: %lld -lSystem -o %t/test-alias %t/test.o %t/foo.o -order_file %t/ord-alias
 # RUN: llvm-objdump -d %t/test-alias | FileCheck %s --check-prefix=FOO-FIRST
 # RUN: %lld -lSystem -o %t/test-alias %t/foo.o %t/test.o -order_file %t/ord-alias
 # RUN: llvm-objdump -d %t/test-alias | FileCheck %s --check-prefix=FOO-FIRST
 
 #--- foo.s
-.globl _foo
-_foo:
+.globl "-[Foo doFoo:andBar:]"
+"-[Foo doFoo:andBar:]":
 _bar:
   ret
 
 #--- test.s
 .globl _main
 
 _main:
-  callq _foo
+  callq "-[Foo doFoo:andBar:]"
   ret