The basic problem is that some mainstream programs cannot deal with the way

clang optimizes tail calls, as in this example:

int foo(void);
int bar(void) {
 return foo();
}

where the call is transformed to:

  calll .L0$pb
.L0$pb:
  popl  %eax
.Ltmp0:
  addl  $_GLOBAL_OFFSET_TABLE_+(.Ltmp0-.L0$pb), %eax
  movl  foo@GOT(%eax), %eax
  popl  %ebp
  jmpl  *%eax                   # TAILCALL

However, the GOT references must all be resolved at dlopen() time, and so this
approach cannot be used with lazy dynamic linking (e.g. using RTLD_LAZY), which
usually populates the PLT with stubs that perform the actual resolving.

This patch changes X86TargetLowering::LowerCall() to skip tail call
optimization, if the called function is a global or external symbol.

Patch by Dimitry Andric!

PR15086

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@195318 91177308-0d34-0410-b5e6-96231b3b80d8

1 files changed, 2 insertions, 4 deletions

diff --git a/test/CodeGen/X86/tail-call-got.ll b/test/CodeGen/X86/tail-call-got.ll
index 84d561dcd8..bdfdeb5987 100644
--- a/test/CodeGen/X86/tail-call-got.ll
+++ b/test/CodeGen/X86/tail-call-got.ll
@@ -5,8 +5,7 @@ target triple = "i386-unknown-freebsd9.0"
 
 define double @test1(double %x) nounwind readnone {
 ; CHECK-LABEL: test1:
-; CHECK: movl foo@GOT
-; CHECK-NEXT: jmpl
+; CHECK: calll foo@PLT
   %1 = tail call double @foo(double %x) nounwind readnone
   ret double %1
 }
@@ -15,8 +14,7 @@ declare double @foo(double) readnone
 
 define double @test2(double %x) nounwind readnone {
 ; CHECK-LABEL: test2:
-; CHECK: movl sin@GOT
-; CHECK-NEXT: jmpl
+; CHECK: calll sin@PLT
   %1 = tail call double @sin(double %x) nounwind readnone
   ret double %1
 }