Fix one-after-the-end type metadata handling in globalsplit

[eugenis]

Summary

Itanium ABI may have an address point one byte after the end of a
vtable. When such vtable global is split, the !type metadata needs to
follow the right vtable.

[pcc]

LGTM

This is a bit of a hack because we're assuming that vtable groups are the only kinds of global variables that !type metadata can be attached to, and that they are either Itanium ABI vtable groups or contain a single vtable (i.e. Microsoft ABI vtables). To avoid needing to make that assumption we may want to represent the type metadata offsets as something like a set of GEP indices instead of a byte offset. But this is fine for now. Please leave a comment stating that we're making this assumption.

llvm/trunk/lib/Transforms/IPO/GlobalSplit.cpp

unsigned SplitEnd = (I == Init->getNumOperands() - 1)
                             : SL->getElementOffset(I + 1);
 
     // Rebuild type metadata, adjusting by the split offset.
     // FIXME: See if we can use DW_OP_piece to preserve debug metadata here.
     for (MDNode *Type : Types) {
       uint64_t ByteOffset = cast<ConstantInt>(
               cast<ConstantAsMetadata>(Type->getOperand(0))->getValue())
               ->getZExtValue();
-      if (ByteOffset < SplitBegin || ByteOffset >= SplitEnd)
+      // Type metadata may be attached one byte after the end of the vtable, for
+      // classes without virtual methods in Itanium ABI. AFAIK, it is never
+      // attached to the first byte of a vtable. Subtract one to get the right
+      // slice.
+      // This is making an assumption that vtable groups are the only kinds of
+      // global variables that !type metadata can be attached to, and that they
+      // are either Itanium ABI vtable groups or contain a single vtable (i.e.
+      // Microsoft ABI vtables).
+      uint64_t AttachedTo = (ByteOffset == 0) ? ByteOffset : ByteOffset - 1;
+      if (AttachedTo < SplitBegin || AttachedTo >= SplitEnd)
         continue;
       SplitGV->addMetadata(
           LLVMContext::MD_type,
           *MDNode::get(GV.getContext(),
                        {ConstantAsMetadata::get(
                             ConstantInt::get(Int32Ty, ByteOffset - SplitBegin)),
                         Type->getOperand(1)}));
     }

llvm/trunk/test/Transforms/GlobalSplit/basic.ll

 ; RUN: opt -S -globalsplit %s | FileCheck %s
 ; RUN: opt -S -passes=globalsplit %s | FileCheck %s
 
 target datalayout = "e-p:64:64"
 target triple = "x86_64-unknown-linux-gnu"
 
 ; CHECK: @vtt = constant [3 x i8*] [i8* bitcast ([2 x i8* ()*]* @global.0 to i8*), i8* bitcast (i8* ()** getelementptr inbounds ([2 x i8* ()*], [2 x i8* ()*]* @global.0, i32 0, i32 1) to i8*), i8* bitcast ([1 x i8* ()*]* @global.1 to i8*)]
 @vtt = constant [3 x i8*] [
   i8* bitcast (i8* ()** getelementptr ({ [2 x i8* ()*], [1 x i8* ()*] }, { [2 x i8* ()*], [1 x i8* ()*] }* @global, i32 0, inrange i32 0, i32 0) to i8*),
   i8* bitcast (i8* ()** getelementptr ({ [2 x i8* ()*], [1 x i8* ()*] }, { [2 x i8* ()*], [1 x i8* ()*] }* @global, i32 0, inrange i32 0, i32 1) to i8*),
   i8* bitcast (i8* ()** getelementptr ({ [2 x i8* ()*], [1 x i8* ()*] }, { [2 x i8* ()*], [1 x i8* ()*] }* @global, i32 0, inrange i32 1, i32 0) to i8*)
 ]
 
 ; CHECK-NOT: @global =
-; CHECK: @global.0 = private constant [2 x i8* ()*] [i8* ()* @f1, i8* ()* @f2], !type [[T1:![0-9]+$]]
-; CHECK: @global.1 = private constant [1 x i8* ()*] [i8* ()* @f3], !type [[T2:![0-9]+$]]
+; CHECK: @global.0 = private constant [2 x i8* ()*] [i8* ()* @f1, i8* ()* @f2], !type [[T1:![0-9]+]], !type [[T2:![0-9]+]], !type [[T3:![0-9]+$]]
+; CHECK: @global.1 = private constant [1 x i8* ()*] [i8* ()* @f3], !type [[T4:![0-9]+]], !type [[T5:![0-9]+$]]
 ; CHECK-NOT: @global =
 @global = internal constant { [2 x i8* ()*], [1 x i8* ()*] } {
   [2 x i8* ()*] [i8* ()* @f1, i8* ()* @f2],
   [1 x i8* ()*] [i8* ()* @f3]
-}, !type !0, !type !1
+}, !type !0, !type !1, !type !2, !type !3, !type !4
 
 ; CHECK: define i8* @f1()
 define i8* @f1() {
   ; CHECK-NEXT: ret i8* bitcast ([2 x i8* ()*]* @global.0 to i8*)
   ret i8* bitcast (i8* ()** getelementptr ({ [2 x i8* ()*], [1 x i8* ()*] }, { [2 x i8* ()*], [1 x i8* ()*] }* @global, i32 0, inrange i32 0, i32 0) to i8*)
 }
 
 ; CHECK: define i8* @f2()

 
 define void @foo() {
   %p = call i1 @llvm.type.test(i8* null, metadata !"")
   ret void
 }
 
 declare i1 @llvm.type.test(i8*, metadata) nounwind readnone
 
-; CHECK: [[T1]] = !{i32 8, !"foo"}
-; CHECK: [[T2]] = !{i32 0, !"bar"}
-!0 = !{i32 8, !"foo"}
-!1 = !{i32 16, !"bar"}
+; CHECK: [[T1]] = !{i32 0, !"foo"}
+; CHECK: [[T2]] = !{i32 15, !"bar"}
+; CHECK: [[T3]] = !{i32 16, !"a"}
+; CHECK: [[T4]] = !{i32 1, !"b"}
+; CHECK: [[T5]] = !{i32 8, !"c"}
+!0 = !{i32 0, !"foo"}
+!1 = !{i32 15, !"bar"}
+!2 = !{i32 16, !"a"}
+!3 = !{i32 17, !"b"}
+!4 = !{i32 24, !"c"}