From 072ebe59e2b05af9e67a691163273b9ab2b96b3b Mon Sep 17 00:00:00 2001
From: Bill Wendling <isanbard@gmail.com>
Date: Thu, 21 Nov 2013 07:04:30 +0000
Subject: [PATCH] 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
---
 lib/Target/X86/X86ISelLowering.cpp | 22 ++++++++--------------
 test/CodeGen/X86/tail-call-got.ll  |  6 ++----
 test/CodeGen/X86/tailcallpic2.ll   |  4 ++--
 3 files changed, 12 insertions(+), 20 deletions(-)

diff --git a/lib/Target/X86/X86ISelLowering.cpp b/lib/Target/X86/X86ISelLowering.cpp
index 4576f3ce20b..ec5ae33ef58 100644
--- a/lib/Target/X86/X86ISelLowering.cpp
+++ b/lib/Target/X86/X86ISelLowering.cpp
@@ -2665,21 +2665,15 @@ X86TargetLowering::LowerCall(TargetLowering::CallLoweringInfo &CLI,
       RegsToPass.push_back(std::make_pair(unsigned(X86::EBX),
                DAG.getNode(X86ISD::GlobalBaseReg, SDLoc(), getPointerTy())));
     } else {
-      // If we are tail calling and generating PIC/GOT style code load the
-      // address of the callee into ECX. The value in ecx is used as target of
-      // the tail jump. This is done to circumvent the ebx/callee-saved problem
-      // for tail calls on PIC/GOT architectures. Normally we would just put the
-      // address of GOT into ebx and then call target@PLT. But for tail calls
-      // ebx would be restored (since ebx is callee saved) before jumping to the
-      // target@PLT.
-
-      // Note: The actual moving to ECX is done further down.
+      // If we are tail calling a global or external symbol in GOT pic mode, we
+      // cannot use a direct jump, since that would make lazy dynamic linking
+      // impossible (see PR15086).  So pretend this is not a tail call, to
+      // prevent the optimization to a jump.
       GlobalAddressSDNode *G = dyn_cast<GlobalAddressSDNode>(Callee);
-      if (G && !G->getGlobal()->hasHiddenVisibility() &&
-          !G->getGlobal()->hasProtectedVisibility())
-        Callee = LowerGlobalAddress(Callee, DAG);
-      else if (isa<ExternalSymbolSDNode>(Callee))
-        Callee = LowerExternalSymbol(Callee, DAG);
+      if ((G && !G->getGlobal()->hasHiddenVisibility() &&
+          !G->getGlobal()->hasProtectedVisibility()) ||
+          isa<ExternalSymbolSDNode>(Callee))
+        isTailCall = false;
     }
   }
 
diff --git a/test/CodeGen/X86/tail-call-got.ll b/test/CodeGen/X86/tail-call-got.ll
index 84d561dcd8c..bdfdeb59870 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
 }
diff --git a/test/CodeGen/X86/tailcallpic2.ll b/test/CodeGen/X86/tailcallpic2.ll
index 1b6bdb76986..c35cee3a987 100644
--- a/test/CodeGen/X86/tailcallpic2.ll
+++ b/test/CodeGen/X86/tailcallpic2.ll
@@ -9,7 +9,7 @@ define fastcc i32 @tailcaller(i32 %in1, i32 %in2) {
 entry:
 	%tmp11 = tail call fastcc i32 @tailcallee( i32 %in1, i32 %in2, i32 %in1, i32 %in2 )		; <i32> [#uses=1]
 	ret i32 %tmp11
-; CHECK: movl tailcallee@GOT
-; CHECK: jmpl
+; Note that this call via PLT could be further optimized into a direct call (no GOT, no PLT):
+; CHECK: calll tailcallee@PLT
 }