From 97d990323607d6eb50a84f672b2169ac4ba1697d Mon Sep 17 00:00:00 2001
From: Bill Wendling <isanbard@gmail.com>
Date: Thu, 5 Apr 2012 21:26:44 +0000
Subject: [PATCH] The internalize pass can be dangerous for LTO.

Consider the following program:

$ cat main.c
void foo(void) { }

int main(int argc, char *argv[]) {
    foo();
    return 0;
}
$ cat bundle.c
extern void foo(void);

void bar(void) {
     foo();
}
$ clang -o main main.c
$ clang -o bundle.so bundle.c -bundle -bundle_loader ./main
$ nm -m bundle.so
0000000000000f40 (__TEXT,__text) external _bar
                 (undefined) external _foo (from executable)
                 (undefined) external dyld_stub_binder (from libSystem)
$ clang -o main main.c -O4
$ clang -o bundle.so bundle.c -bundle -bundle_loader ./main
Undefined symbols for architecture x86_64:
  "_foo", referenced from:
      _bar in bundle-elQN6d.o
ld: symbol(s) not found for architecture x86_64
clang: error: linker command failed with exit code 1 (use -v to see invocation)

The linker was told that the 'foo' in 'main' was 'internal' and had no uses, so
it was dead stripped.

Another situation is something like:

define void @foo() {
  ret void
}

define void @bar() {
  call asm volatile "call _foo" ...
  ret void
}

The only use of 'foo' is inside of an inline ASM call. Since we don't look
inside those for uses of functions, we don't specify this as a "use."

Get around this by not invoking the 'internalize' pass by default. This is an
admitted hack for LTO correctness.
<rdar://problem/11185386>


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@154124 91177308-0d34-0410-b5e6-96231b3b80d8
---
 tools/lto/LTOCodeGenerator.cpp | 15 +++++++++++++--
 1 file changed, 13 insertions(+), 2 deletions(-)

diff --git a/tools/lto/LTOCodeGenerator.cpp b/tools/lto/LTOCodeGenerator.cpp
index f0640c22063..0e61c2fb2a5 100644
--- a/tools/lto/LTOCodeGenerator.cpp
+++ b/tools/lto/LTOCodeGenerator.cpp
@@ -46,10 +46,13 @@
 #include "llvm/ADT/StringExtras.h"
 using namespace llvm;
 
-static cl::opt<bool> DisableInline("disable-inlining",
+static cl::opt<bool> EnableInternalizing("enable-internalizing", cl::init(false),
+  cl::desc("Internalize functions during LTO"));
+
+static cl::opt<bool> DisableInline("disable-inlining", cl::init(false),
   cl::desc("Do not run the inliner pass"));
 
-static cl::opt<bool> DisableGVNLoadPRE("disable-gvn-loadpre",
+static cl::opt<bool> DisableGVNLoadPRE("disable-gvn-loadpre", cl::init(false),
   cl::desc("Do not run the GVN load PRE pass"));
 
 const char* LTOCodeGenerator::getVersionString() {
@@ -275,6 +278,14 @@ static void findUsedValues(GlobalVariable *LLVMUsed,
 }
 
 void LTOCodeGenerator::applyScopeRestrictions() {
+  // Internalize only if specifically asked for. Otherwise, global symbols which
+  // exist in the final image, but which are used outside of that image
+  // (e.g. bundling) may be removed. This also happens when a function is used
+  // only in inline asm. LLVM doesn't recognize that as a "use", so it could be
+  // stripped.
+  if (!EnableInternalizing)
+    return;
+
   if (_scopeRestrictionsDone) return;
   Module *mergedModule = _linker.getModule();