[lld] 4f2c46c - Print C-string literals in mapfile

[Jez Ng via llvm-commits]

Author: Roger Kim
Date: 2022-02-11T19:42:20-05:00
New Revision: 4f2c46c35ccd17ef726c4b4e8e9500d7972e757a

URL: https://github.com/llvm/llvm-project/commit/4f2c46c35ccd17ef726c4b4e8e9500d7972e757a
DIFF: https://github.com/llvm/llvm-project/commit/4f2c46c35ccd17ef726c4b4e8e9500d7972e757a.diff

LOG: Print C-string literals in mapfile

This diff has the C-string literals printed into the mapfile in the symbol table like how ld64 does.

Here is what ld64's mapfile looks like with C-string literals:
```
# Path: out
# Arch: x86_64
# Object files:
[  0] linker synthesized
[  1] foo.o
# Sections:
# Address       Size            Segment Section
0x100003F7D     0x0000001D      __TEXT  __text
0x100003F9A     0x0000001E      __TEXT  __cstring
0x100003FB8     0x00000048      __TEXT  __unwind_info
# Symbols:
# Address       Size            File  Name
0x100003F7D     0x0000001D      [  1] _main
0x100003F9A     0x0000000E      [  1] literal string: Hello world!\n
0x100003FA8     0x00000010      [  1] literal string: Hello, it's me\n
0x100003FB8     0x00000048      [  0] compact unwind info
```

Here is what the new lld's Mach-O mapfile looks like:
```
# Path: /Users/rgr/local/llvm-project/build/Debug/tools/lld/test/MachO/Output/map-file.s.tmp/c-string-liter
al-out
# Arch: x86_64
# Object files:
[  0] linker synthesized
[  1] /Users/rgr/local/llvm-project/build/Debug/tools/lld/test/MachO/Output/map-file.s.tmp/c-string-literal
.o
# Sections:
# Address       Size            Segment Section
0x1000002E0     0x0000001D      __TEXT  __text
0x1000002FD     0x0000001D      __TEXT  __cstring
# Symbols:
# Address           File  Name
0x1000002E0     [  1] _main
0x1000002FD     [  1] literal string: Hello world!\n
0x10000030B     [  1] literal string: Hello, it's me\n
```

Reviewed By: #lld-macho, int3

Differential Revision: https://reviews.llvm.org/D118077

Added: 
    

Modified: 
    lld/MachO/MapFile.cpp
    lld/test/MachO/map-file.s

Removed: 
    


################################################################################
diff  --git a/lld/MachO/MapFile.cpp b/lld/MachO/MapFile.cpp
index 8f9381ff0d792..a4a0065c28165 100644
--- a/lld/MachO/MapFile.cpp
+++ b/lld/MachO/MapFile.cpp
@@ -31,6 +31,7 @@
 #include "OutputSection.h"
 #include "OutputSegment.h"
 #include "Symbols.h"
+#include "SyntheticSections.h"
 #include "Target.h"
 #include "llvm/Support/Parallel.h"
 #include "llvm/Support/TimeProfiler.h"
@@ -76,7 +77,27 @@ getSymbolStrings(ArrayRef<Defined *> syms) {
   std::vector<std::string> str(syms.size());
   parallelForEachN(0, syms.size(), [&](size_t i) {
     raw_string_ostream os(str[i]);
-    os << toString(*syms[i]);
+    Defined *sym = syms[i];
+
+    switch (sym->isec->kind()) {
+    case InputSection::CStringLiteralKind: {
+      // Output "literal string: <string literal>"
+      const auto *isec = cast<CStringInputSection>(sym->isec);
+      const StringPiece &piece = isec->getStringPiece(sym->value);
+      assert(
+          sym->value == piece.inSecOff &&
+          "We expect symbols to always point to the start of a StringPiece.");
+      StringRef str = isec->getStringRef(&piece - &(*isec->pieces.begin()));
+      assert(str.back() == '\000');
+      (os << "literal string: ")
+          // Remove null sequence at the end
+          .write_escaped(str.substr(0, str.size() - 1));
+      break;
+    }
+    case InputSection::ConcatKind:
+    case InputSection::WordLiteralKind:
+      os << toString(*sym);
+    }
   });
 
   DenseMap<Symbol *, std::string> ret;

diff  --git a/lld/test/MachO/map-file.s b/lld/test/MachO/map-file.s
index 85c23e763e9ef..aa0bc6a8caf1b 100644
--- a/lld/test/MachO/map-file.s
+++ b/lld/test/MachO/map-file.s
@@ -2,6 +2,7 @@
 # RUN: rm -rf %t; split-file %s %t
 # RUN: llvm-mc -filetype=obj -triple=x86_64-apple-darwin %t/foo.s -o %t/foo.o
 # 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/c-string-literal.s -o %t/c-string-literal.o
 
 # RUN: %lld -map %t/map %t/test.o %t/foo.o --time-trace -o %t/test-map
 # RUN: llvm-objdump --syms --section-headers %t/test-map > %t/objdump
@@ -51,4 +52,42 @@ _main:
 # CHECK-NEXT: 0x[[#FOO]]       [  2]  _foo
 # CHECK-NEXT: 0x[[#NUMBER]]    [  1]  _number
 
+#--- c-string-literal.s
+.section __TEXT,__cstring
+.globl _hello_world, _hello_its_me, _main
+
+_hello_world:
+.asciz "Hello world!\n"
+
+_hello_its_me:
+.asciz "Hello, it's me"
+
+.text
+_main:
+  movl $0x2000004, %eax # write() syscall
+  mov $1, %rdi # stdout
+  leaq _hello_world(%rip), %rsi
+  mov $13, %rdx # length of str
+  syscall
+  ret
+
+# RUN: %lld -map %t/c-string-literal-map %t/c-string-literal.o -o %t/c-string-literal-out
+# RUN: FileCheck --check-prefix=CSTRING %s < %t/c-string-literal-map
+
+## C-string literals should be printed as "literal string: <C string literal>"
+# CSTRING-LABEL: Symbols:
+# CSTRING-DAG: _main
+# CSTRING-DAG: literal string: Hello world!\n
+# CSTRING-DAG: literal string: Hello, it's me
+
+# RUN: %lld -dead_strip -map %t/dead-c-string-literal-map %t/c-string-literal.o -o %t/dead-c-string-literal-out
+# RUN: FileCheck --check-prefix=DEADCSTRING %s < %t/dead-c-string-literal-map
+
+## C-string literals should be printed as "literal string: <C string literal>"
+# DEADCSTRING-LABEL: Symbols:
+# DEADCSTRING-DAG: _main
+# DEADCSTRING-DAG: literal string: Hello world!\n
+# DEADCSTRING-LABEL: Dead Stripped Symbols:
+# DEADCSTRING-DAG: literal string: Hello, it's me
+
 # MAPFILE: "name":"Total Write map file"