[GlobalDCE] In VFE support for relative pointers, allow GEP references to the base symbol

[kubamracek]

Summary

This is for Swift VFE support. In some vtable forms that Swift emits, the "base" of a relative pointer is not the global symbol itself directly, but a GEP into it -- so the pointer is relative to a particular field in the global. So getPointerAtOffset() needs to be able to see through the GEP and allow it in a SUB expression, to correctly recognize the offset as a vtable slot.

[fhahn]

LGTM, thanks!

llvm/lib/Analysis/TypeMetadataUtils.cpp

129

given that this is only used at a single point, maybe define it as a lambda at the use, so all the swift specific code is kept close together?

llvm/test/Transforms/GlobalDCE/virtual-functions-relative-pointers-gep.ll

2

new tests probably should use the new pm syntax (-passes='globaldce')

llvm/lib/Analysis/TypeMetadataUtils.cpp

for (const Use &U : CI->uses()) {
     HasNonCallUses = true;
   }
 
   for (Value *LoadedPtr : LoadedPtrs)
     findCallsAtConstantOffset(DevirtCalls, &HasNonCallUses, LoadedPtr,
                               Offset->getZExtValue(), CI, DT);
 }
 
 Constant *llvm::getPointerAtOffset(Constant *I, uint64_t Offset, Module &M,
                                    Constant *TopLevelGlobal) {
   if (I->getType()->isPointerTy()) {
     if (Offset == 0)
       return I;
     return nullptr;
   }
 
   const DataLayout &DL = M.getDataLayout();
if (auto *C = dyn_cast<ConstantExpr>(I)) {
     switch (C->getOpcode()) {
     case Instruction::Trunc:
     case Instruction::PtrToInt:
       return getPointerAtOffset(cast<Constant>(C->getOperand(0)), Offset, M,
                                 TopLevelGlobal);
     case Instruction::Sub: {
       auto *Operand0 = cast<Constant>(C->getOperand(0));
       auto *Operand1 = cast<Constant>(C->getOperand(1));
-      auto *Operand1TargetGlobal = getPointerAtOffset(Operand1, 0, M);
+
+      auto StripGEP = [](Constant *C) {
+        auto *CE = dyn_cast<ConstantExpr>(C);
+        if (!CE)
+          return C;
+        if (CE->getOpcode() != Instruction::GetElementPtr)
+          return C;
+        return CE->getOperand(0);
+      };
+      auto *Operand1TargetGlobal = StripGEP(getPointerAtOffset(Operand1, 0, M));
 
       // Check that in the "sub (@a, @b)" expression, @b points back to the top
-      // level global that we're processing. Otherwise bail.
+      // level global (or a GEP thereof) that we're processing. Otherwise bail.
       if (Operand1TargetGlobal != TopLevelGlobal)
         return nullptr;
 
       return getPointerAtOffset(Operand0, Offset, M, TopLevelGlobal);
     }
     default:
       return nullptr;
     }
   }
   return nullptr;
 }

llvm/test/Transforms/GlobalDCE/virtual-functions-relative-pointers-gep.ll

+; RUN: opt < %s -passes='globaldce' -S | FileCheck %s
+
+target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
+
+declare { i8*, i1 } @llvm.type.checked.load(i8*, i32, metadata)
+
+; A vtable with "relative pointers", slots don't contain pointers to implementations, but instead have an i32 offset from the vtable itself to the implementation.
+@vtable = internal unnamed_addr constant { [4 x i32] } { [4 x i32] [
+  i32 42,
+  i32 1337,
+  i32 trunc (i64 sub (i64 ptrtoint (void ()* @vfunc1_live              to i64), i64 ptrtoint (i32* getelementptr inbounds ({ [4 x i32] }, { [4 x i32] }* @vtable, i32 0, i32 0, i32 2) to i64)) to i32),
+  i32 trunc (i64 sub (i64 ptrtoint (void ()* @vfunc2_dead              to i64), i64 ptrtoint (i32* getelementptr inbounds ({ [4 x i32] }, { [4 x i32] }* @vtable, i32 0, i32 0, i32 2) to i64)) to i32)
+]}, align 8, !type !0, !type !1, !vcall_visibility !{i64 2}
+!0 = !{i64 8, !"vfunc1.type"}
+!1 = !{i64 12, !"vfunc2.type"}
+
+; CHECK:      @vtable = internal unnamed_addr constant { [4 x i32] } { [4 x i32] [
+; CHECK-SAME:   i32 trunc (i64 sub (i64 ptrtoint (void ()* @vfunc1_live              to i64), i64 ptrtoint (i32* getelementptr inbounds ({ [4 x i32] }, { [4 x i32] }* @vtable, i32 0, i32 0, i32 2) to i64)) to i32),
+; CHECK-SAME:   i32 trunc (i64 sub (i64 0,                                                    i64 ptrtoint (i32* getelementptr inbounds ({ [4 x i32] }, { [4 x i32] }* @vtable, i32 0, i32 0, i32 2) to i64)) to i32)
+; CHECK-SAME: ] }, align 8, !type !0, !type !1, !vcall_visibility !2
+
+; (1) vfunc1_live is referenced from @main, stays alive
+define internal void @vfunc1_live() {
+  ; CHECK: define internal void @vfunc1_live(
+  ret void
+}
+
+; (2) vfunc2_dead is never referenced, gets removed and vtable slot is null'd
+define internal void @vfunc2_dead() {
+  ; CHECK-NOT: define internal void @vfunc2_dead(
+  ret void
+}
+
+define void @main() {
+  %1 = ptrtoint { [4 x i32] }* @vtable to i64 ; to keep @vtable alive
+  %2 = tail call { i8*, i1 } @llvm.type.checked.load(i8* null, i32 0, metadata !"vfunc1.type")
+  ret void
+}
+
+!999 = !{i32 1, !"Virtual Function Elim", i32 1}
+!llvm.module.flags = !{!999}