Disable x86 tail call optimizations that jump through GOT

For x86 targets, do not do sibling call optimization when materializing
the callee's address would require a GOT relocation. We can still do
tail calls to internal functions, hidden functions, and protected
functions, because they do not require this kind of relocation. It is
still possible to get GOT relocations when the user explicitly asks for
it with musttail or -tailcallopt, both of which are supposed to
guarantee TCO.

Based on a patch by Chih-hung Hsieh.

Reviewers: srhines, timmurray, danalbert, enh, void, nadav, rnk

Subscribers: joerg, davidxl, llvm-commits

Differential Revision: http://reviews.llvm.org/D9799

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@238487 91177308-0d34-0410-b5e6-96231b3b80d8

lib/Target/X86/X86ISelLowering.cpp

@@ -2780,6 +2780,24 @@ X86TargetLowering::LowerCall(TargetLowering::CallLoweringInfo &CLI,
   if (MF.getTarget().Options.DisableTailCalls)
     isTailCall = false;
 
+  if (Subtarget->isPICStyleGOT() &&
+      !MF.getTarget().Options.GuaranteedTailCallOpt) {
+    // If we are using a GOT, disable tail calls to external symbols with
+    // default visibility. Tail calling such a symbol requires using a GOT
+    // relocation, which forces early binding of the symbol. This breaks code
+    // that require lazy function symbol resolution. Using musttail or
+    // GuaranteedTailCallOpt will override this.
+    GlobalAddressSDNode *G = dyn_cast<GlobalAddressSDNode>(Callee);
+    if (!G || (!G->getGlobal()->hasLocalLinkage() &&
+               G->getGlobal()->hasDefaultVisibility())) {
+      isTailCall = false;
+      if (G) {
+        llvm::errs() << "disabling tail call for default visibility symbol\n";
+        G->getGlobal()->dump();
+      }
+    }
+  }
+
   bool IsMustTail = CLI.CS && CLI.CS->isMustTailCall();
   if (IsMustTail) {
     // Force this to be a tail call.  The verifier rules are enough to ensure
@@ -2964,8 +2982,8 @@ X86TargetLowering::LowerCall(TargetLowering::CallLoweringInfo &CLI,
 
       // Note: The actual moving to ECX is done further down.
       GlobalAddressSDNode *G = dyn_cast<GlobalAddressSDNode>(Callee);
-      if (G && !G->getGlobal()->hasHiddenVisibility() &&
-          !G->getGlobal()->hasProtectedVisibility())
+      if (G && !G->getGlobal()->hasLocalLinkage() &&
+          G->getGlobal()->hasDefaultVisibility())
         Callee = LowerGlobalAddress(Callee, DAG);
       else if (isa<ExternalSymbolSDNode>(Callee))
         Callee = LowerExternalSymbol(Callee, DAG);

test/CodeGen/X86/pic.ll

@@ -196,9 +196,11 @@ bb12:
 ; LINUX-NEXT: .LJTI7_0:
 ; LINUX:   .long	 .LBB7_2@GOTOFF
 ; LINUX:   .long	 .LBB7_8@GOTOFF
-; LINUX:   .long	 .LBB7_14@GOTOFF
-; LINUX:   .long	 .LBB7_9@GOTOFF
-; LINUX:   .long	 .LBB7_10@GOTOFF
+; LINUX:   .long	 .LBB7_4@GOTOFF
+; LINUX:   .long	 .LBB7_6@GOTOFF
+; LINUX:   .long	 .LBB7_5@GOTOFF
+; LINUX:   .long	 .LBB7_8@GOTOFF
+; LINUX:   .long	 .LBB7_7@GOTOFF
 }
 
 declare void @foo1(...)

test/CodeGen/X86/tail-call-got.ll

@@ -1,12 +1,14 @@
 ; RUN: llc < %s -relocation-model=pic -mattr=+sse2 | FileCheck %s
 
+; We used to do tail calls through the GOT for these symbols, but it was
+; disabled due to PR15086.
+
 target datalayout = "e-p:32:32:32-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-f32:32:32-f64:32:64-v64:64:64-v128:128:128-a0:0:64-f80:32:32-n8:16:32"
 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
 }
@@ -15,10 +17,18 @@ 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
 }
 
 declare double @sin(double) readnone
+
+define double @test3(double %x) nounwind readnone {
+; CHECK-LABEL: test3:
+; CHECK:  calll sin2@PLT
+  %1 = tail call double @sin2(double %x) nounwind readnone
+  ret double %1
+}
+
+declare double @sin2(double) readnone

test/CodeGen/X86/tailcallpic1.ll

@@ -1,5 +1,8 @@
 ; RUN: llc < %s  -tailcallopt -mtriple=i686-pc-linux-gnu -relocation-model=pic | FileCheck %s
 
+; This test uses guaranteed TCO so these will be tail calls, despite the early
+; binding issues.
+
 define protected fastcc i32 @tailcallee(i32 %a1, i32 %a2, i32 %a3, i32 %a4) {
 entry:
 	ret i32 %a3

test/CodeGen/X86/tailcallpic3.ll

@@ -0,0 +1,73 @@
+; RUN: llc < %s -mtriple=i686-pc-linux-gnu -relocation-model=pic | FileCheck %s
+
+; While many of these could be tail called, we don't do it because it forces
+; early binding.
+
+declare void @external()
+
+define hidden void @tailcallee_hidden() {
+entry:
+  ret void
+}
+
+define void @tailcall_hidden() {
+entry:
+  tail call void @tailcallee_hidden()
+  ret void
+}
+; CHECK: tailcall_hidden:
+; CHECK: jmp tailcallee_hidden
+
+define internal void @tailcallee_internal() {
+entry:
+  ret void
+}
+
+define void @tailcall_internal() {
+entry:
+  tail call void @tailcallee_internal()
+  ret void
+}
+; CHECK: tailcall_internal:
+; CHECK: jmp tailcallee_internal
+
+define default void @tailcallee_default() {
+entry:
+  ret void
+}
+
+define void @tailcall_default() {
+entry:
+  tail call void @tailcallee_default()
+  ret void
+}
+; CHECK: tailcall_default:
+; CHECK: calll tailcallee_default@PLT
+
+define void @tailcallee_default_implicit() {
+entry:
+  ret void
+}
+
+define void @tailcall_default_implicit() {
+entry:
+  tail call void @tailcallee_default_implicit()
+  ret void
+}
+; CHECK: tailcall_default_implicit:
+; CHECK: calll tailcallee_default_implicit@PLT
+
+define void @tailcall_external() {
+  tail call void @external()
+  ret void
+}
+; CHECK: tailcall_external:
+; CHECK: calll external@PLT
+
+define void @musttail_external() {
+  musttail call void @external()
+  ret void
+}
+; CHECK: musttail_external:
+; CHECK: movl external@GOT
+; CHECK: jmpl