[MergeFuncs] Fix callsite attributes in thunk generation

This change correctly sets the attributes on the callsites
generated in thunks. This makes sure things such as sret, sext, etc.
are correctly set, so that the call can be a proper tailcall.

Also, the transfer of attributes in the replaceDirectCallers function
appears to be unnecessary, but until this is confirmed it will remain.

Author: jrkoenig
Reviewers: dschuff, jfb
Subscribers: llvm-commits, nlewycky
Differential revision: http://reviews.llvm.org/D12581

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@247313 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Transforms/IPO/MergeFunctions.cpp b/lib/Transforms/IPO/MergeFunctions.cpp
index fa6c4ea385998a7b7dc0754ace3e40773a52b8d1..a8a85982e18d5fc4e6f4a65677f3a4b0557aa4ee 100644 (file)
--- a/lib/Transforms/IPO/MergeFunctions.cpp
+++ b/lib/Transforms/IPO/MergeFunctions.cpp
@@ -1559,9 +1559,16 @@ void MergeFunctions::replaceDirectCallers(Function *Old, Function *New) {
     CallSite CS(U->getUser());
     if (CS && CS.isCallee(U)) {
       // Transfer the called function's attributes to the call site. Due to the
-      // bitcast we will 'loose' ABI changing attributes because the 'called
+      // bitcast we will 'lose' ABI changing attributes because the 'called
       // function' is no longer a Function* but the bitcast. Code that looks up
       // the attributes from the called function will fail.
+
+      // FIXME: This is not actually true, at least not anymore. The callsite
+      // will always have the same ABI affecting attributes as the callee,
+      // because otherwise the original input has UB. Note that Old and New
+      // always have matching ABI, so no attributes need to be changed.
+      // Transferring other attributes may help other optimizations, but that
+      // should be done uniformly and not in this ad-hoc way.
       auto &Context = New->getContext();
       auto NewFuncAttrs = New->getAttributes();
       auto CallSiteAttrs = CS.getAttributes();
@@ -1656,6 +1663,7 @@ void MergeFunctions::writeThunk(Function *F, Function *G) {
   CallInst *CI = Builder.CreateCall(F, Args);
   CI->setTailCall();
   CI->setCallingConv(F->getCallingConv());
+  CI->setAttributes(F->getAttributes());
   if (NewG->getReturnType()->isVoidTy()) {
     Builder.CreateRetVoid();
   } else {

diff --git a/test/Transforms/MergeFunc/apply_function_attributes.ll b/test/Transforms/MergeFunc/apply_function_attributes.ll
index fa7f052f7ffd0244375949c06b2795c0253cf21d..e9ede4518206a3e20091e6916c5fac224e00a92f 100644 (file)
--- a/test/Transforms/MergeFunc/apply_function_attributes.ll
+++ b/test/Transforms/MergeFunc/apply_function_attributes.ll
@@ -38,3 +38,10 @@ define void @A(%Opaque_type* sret %a, %D2i* %b, i32* %xp, i32* %yp) {
 ; CHECK:  tail call void bitcast (void (%Opaque_type*, %D2i*, i32*, i32*)* @A to void (%Opaque_type*, %S2i*, i32*, i32*)*)(%Opaque_type* sret %0, %S2i* %1, i32* %2, i32* %3)
 ; CHECK:  ret void
 
+
+; Make sure we transfer the parameter attributes to the call site.
+; CHECK-LABEL: define void @B(%Opaque_type* sret
+; CHECK:  %5 = bitcast
+; CHECK:  tail call void @A(%Opaque_type* sret %0, %D2i* %5, i32* %2, i32* %3)
+; CHECK:  ret void
+

diff --git a/test/Transforms/MergeFunc/inttoptr-address-space.ll b/test/Transforms/MergeFunc/inttoptr-address-space.ll
index 5f672debd919b8081842ed13142fcf6b1cbc5e8a..86deb2c9495347c310e67eacb3f14f16ea3437fc 100644 (file)
--- a/test/Transforms/MergeFunc/inttoptr-address-space.ll
+++ b/test/Transforms/MergeFunc/inttoptr-address-space.ll
@@ -21,7 +21,7 @@ define internal i8* @func35(%.qux.2585 addrspace(1)* nocapture %this) align 2 {
 bb:
 ; CHECK-LABEL: @func35(
 ; CHECK: %[[V2:.+]] = bitcast %.qux.2585 addrspace(1)* %{{.*}} to %.qux.2496 addrspace(1)*
-; CHECK: %[[V3:.+]] = tail call i32 @func10(%.qux.2496 addrspace(1)* %[[V2]])
+; CHECK: %[[V3:.+]] = tail call i32 @func10(%.qux.2496 addrspace(1)* nocapture %[[V2]])
 ; CHECK: %{{.*}} = inttoptr i32 %[[V3]] to i8*
   %tmp = getelementptr inbounds %.qux.2585, %.qux.2585 addrspace(1)* %this, i32 0, i32 2
   %tmp1 = load i8*, i8* addrspace(1)* %tmp, align 4

diff --git a/test/Transforms/MergeFunc/inttoptr.ll b/test/Transforms/MergeFunc/inttoptr.ll
index 0abbf6239a3417ad1b8177f29190d57a4ab230e2..05ae766a6e3748a5c959bf68a6b7fc92257a4536 100644 (file)
--- a/test/Transforms/MergeFunc/inttoptr.ll
+++ b/test/Transforms/MergeFunc/inttoptr.ll
@@ -48,7 +48,7 @@ define internal i8* @func35(%.qux.2585* nocapture %this) align 2 {
 bb:
 ; CHECK-LABEL: @func35(
 ; CHECK: %[[V2:.+]] = bitcast %.qux.2585* %{{.*}} to %.qux.2496*
-; CHECK: %[[V3:.+]] = tail call i32 @func10(%.qux.2496* %[[V2]])
+; CHECK: %[[V3:.+]] = tail call i32 @func10(%.qux.2496* nocapture %[[V2]])
 ; CHECK: %{{.*}} = inttoptr i32 %[[V3]] to i8*
   %tmp = getelementptr inbounds %.qux.2585, %.qux.2585* %this, i32 0, i32 2
   %tmp1 = load i8*, i8** %tmp, align 4