[PowerPC][AIX] ByVal formal argument support: passing on the stack

[sfertile]

Summary

Adds support for passing a ByVal formal argument completely on the stack (ie after all argument registers are exhausted).

[sfertile]

Fix unintended white space change.

[cebowleratibm]

I think the review title "ByVal formal argument support: passing on the stack" implies that it covers the reg/stack split case. I noted you described it better in the review description. I think a slightly more descriptive abstract would be useful for the commit message.

I noted that test_byval_mem4 could have been defined for 64-bit, however 32-bit would emit an error. I expect you plan to follow up with another patch to handle the reg/stack split case, just be sure to add the definition of this function for that case when you do.

I think this one looks pretty straight forward. LGTM.

llvm/lib/Target/PowerPC/PPCISelLowering.cpp

for (size_t I = 0, End = ArgLocs.size(); I != End; /* No increment here */) {
     // in register.  The caller is required to initialize both the register
     // and memory, however, the callee can choose to expect it in either.
     // The memloc is dismissed here because the argument is retrieved from
     // the register.
     if (VA.isMemLoc() && VA.needsCustom())
       continue;
 
     if (Flags.isByVal() && VA.isMemLoc()) {
-      if (Flags.getByValSize() != 0)
-        report_fatal_error(
-            "ByVal arguments passed on stack not implemented yet");
-
+      const unsigned Size =
+          alignTo(Flags.getByValSize() ? Flags.getByValSize() : PtrByteSize,
+                  PtrByteSize);
       const int FI = MF.getFrameInfo().CreateFixedObject(
-          PtrByteSize, VA.getLocMemOffset(), /* IsImmutable */ false,
+          Size, VA.getLocMemOffset(), /* IsImmutable */ false,
           /* IsAliased */ true);
       SDValue FIN = DAG.getFrameIndex(FI, PtrVT);
       InVals.push_back(FIN);
 
       continue;
     }
 
     if (Flags.isByVal()) {

llvm/test/CodeGen/PowerPC/aix-cc-byval-limitation2.ll

-; RUN: not --crash llc -mtriple powerpc-ibm-aix-xcoff < %s 2>&1 | FileCheck %s
-; RUN: not --crash llc -mtriple powerpc64-ibm-aix-xcoff < %s 2>&1 | FileCheck %s
-
-%struct.S = type { i8 }
-
-define void @foo(i32 %i1, i32 %i2, i32 %i3, i32 %i4, i32 %i5, i32 %i6, i32 %i7, i32 %i8, %struct.S* byval(%struct.S) align 1 %s) {
-entry:
-  ret void
-}
-
-; CHECK: LLVM ERROR: ByVal arguments passed on stack not implemented yet

llvm/test/CodeGen/PowerPC/aix-cc-byval-mem.ll

 ; RUN: FileCheck --check-prefixes=CHECKASM,ASM64BIT %s
 
 %struct_S1 = type { i8 }
 
 @gS1 = external global %struct_S1, align 1
 
 define void @call_test_byval_mem1() {
 entry:
-  call void @test_byval_mem1(i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, %struct_S1* byval(%struct_S1) align 1 @gS1)
+  %call = call zeroext i8 @test_byval_mem1(i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, %struct_S1* byval(%struct_S1) align 1 @gS1)
   ret void
 }
 
-declare void @test_byval_mem1(i32, i32, i32, i32, i32, i32, i32, i32, %struct_S1* byval(%struct_S1) align 1)
 
 ; CHECKASM-LABEL: .call_test_byval_mem1:
 
 ; ASM32BIT:       stwu 1, -64(1)
 ; ASM32BIT:       lwz [[REG1:[0-9]+]], LC{{[0-9]+}}(2)
 ; ASM32BIT:       lbz [[REG2:[0-9]+]], 0([[REG1]])
 ; ASM32BIT:       stb [[REG2]], 56(1)
 ; ASM32BIT:       bl .test_byval_mem1
 ; ASM32BIT:       addi 1, 1, 64
 
 ; ASM64BIT:       stdu 1, -128(1)
 ; ASM64BIT:       ld [[REG1:[0-9]+]], LC{{[0-9]+}}(2)
 ; ASM64BIT:       lbz [[REG2:[0-9]+]], 0([[REG1]])
 ; ASM64BIT:       stb [[REG2]], 112(1)
 ; ASM64BIT:       bl .test_byval_mem1
 ; ASM64BIT:       addi 1, 1, 128
 
+define zeroext  i8 @test_byval_mem1(i32, i32, i32, i32, i32, i32, i32, i32, %struct_S1* byval(%struct_S1) align 1 %s) {
+entry:
+  %gep = getelementptr inbounds %struct_S1, %struct_S1* %s, i32 0, i32 0
+  %load = load i8, i8* %gep, align 1
+  ret i8 %load
+}
+
+; CHECK-LABEL: name:            test_byval_mem1
+
+; 32BIT:       fixedStack:
+; 32BIT-NEXT:    - { id: 0, type: default, offset: 56, size: 4, alignment: 8, stack-id: default,
+; 32BIT:       bb.0.entry:
+; 32BIT-NEXT:    %[[VAL:[0-9]+]]:gprc = LBZ 0, %fixed-stack.0
+; 32BIT-NEXT:    $r3 = COPY %[[VAL]]
+; 32BIT-NEXT:    BLR
+
+; 64BIT:       fixedStack:
+; 64BIT-NEXT:    - { id: 0, type: default, offset: 112, size: 8, alignment: 16, stack-id: default,
+; 64BIT:       bb.0.entry:
+; 64BIT-NEXT:    %[[VAL:[0-9]+]]:g8rc = LBZ8 0, %fixed-stack.0
+; 64BIT-NEXT:    $x3 = COPY %[[VAL]]
+; 64BIT-NEXT:    BLR8
+
 
 %struct_S256 = type { [256 x i8] }
 
 @gS256 = external global %struct_S256, align 1
 
 define void @call_test_byval_mem2() {
 entry:
-  call void @test_byval_mem2(i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, %struct_S256* byval(%struct_S256) align 1 @gS256)
+  %call = call zeroext i8 @test_byval_mem2(i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, %struct_S256* byval(%struct_S256) align 1 @gS256)
   ret void
 }
 
-declare void @test_byval_mem2(i32, i32, i32, i32, i32, i32, i32, i32, %struct_S256* byval(%struct_S256) align 1)
 
 ; CHECK-LABEL:    name: call_test_byval_mem2
 
 ; Confirm the expected memcpy call is independent of the call to test_byval_mem2.
 ; 32BIT:          ADJCALLSTACKDOWN 56, 0, implicit-def dead $r1, implicit $r1
 ; 32BIT-NEXT:     %0:gprc = nuw ADDI $r1, 56
 ; 32BIT-NEXT:     %1:gprc = LWZtoc @gS256, $r2 :: (load 4 from got)
 ; 32BIT-NEXT:     %2:gprc = LI 256

 ; ASM64BIT-DAG:   addi 3, 1, 112
 ; ASM64BIT-DAG:   ld 4, LC{{[0-9]+}}(2)
 ; ASM64BIT-DAG:   li 5, 256
 ; ASM64BIT-NEXT:  bl .memcpy
 ; ASM64BIT:       bl .test_byval_mem2
 ; ASM64BIT:       addi 1, 1, 368
 
 
+define zeroext i8 @test_byval_mem2(i32, i32, i32, i32, i32, i32, i32, i32, %struct_S256* byval(%struct_S256) align 1 %s) {
+entry:
+  %gep = getelementptr inbounds %struct_S256, %struct_S256* %s, i32 0, i32 0, i32 255
+  %load = load i8, i8* %gep, align 1
+  ret i8 %load
+}
+
+; CHECK-LABEL: name:            test_byval_mem2
+
+; 32BIT:      fixedStack:
+; 32BIT-NEXT:   - { id: 0, type: default, offset: 56, size: 256, alignment: 8, stack-id: default,
+; 32BIT:      bb.0.entry:
+; 32BIT-NEXT:   %[[VAL:[0-9]+]]:gprc = LBZ 255, %fixed-stack.0
+; 32BIT-NEXT:   $r3 = COPY %[[VAL]]
+; 32BIT-NEXT:   BLR
+
+; 64BIT:      fixedStack:
+; 64BIT-NEXT:   - { id: 0, type: default, offset: 112, size: 256, alignment: 16, stack-id: default,
+; 64BIT:      bb.0.entry:
+; 64BIT-NEXT:   %[[VAL:[0-9]+]]:g8rc = LBZ8 255, %fixed-stack.0
+; 64BIT-NEXT:   $x3 = COPY %[[VAL]]
+; 64BIT-NEXT:   BLR8
+
 %struct_S57 = type { [57 x i8] }
 
 @gS57 = external global %struct_S57, align 1
 
 define void @call_test_byval_mem3() {
 entry:
   call void @test_byval_mem3(i32 42, float 0x40091EB860000000, %struct_S57* byval(%struct_S57) align 1 @gS57)
   ret void