[PowerPC][ELF] make sure local variable space does not overlap with parameter save area

Reviewed By: jsji

Differential Revision: https://reviews.llvm.org/D105271

2 files changed, 22 insertions, 15 deletions

diff --git a/llvm/lib/Target/PowerPC/PPCISelLowering.cpp b/llvm/lib/Target/PowerPC/PPCISelLowering.cpp
index 6d38b39f..838ac93 100644
--- a/llvm/lib/Target/PowerPC/PPCISelLowering.cpp
+++ b/llvm/lib/Target/PowerPC/PPCISelLowering.cpp
@@ -3878,7 +3878,8 @@ static Align CalculateStackSlotAlignment(EVT ArgVT, EVT OrigVT,
 /// stack slot (instead of being passed in registers).  ArgOffset,
 /// AvailableFPRs, and AvailableVRs must hold the current argument
 /// position, and will be updated to account for this argument.
-static bool CalculateStackSlotUsed(EVT ArgVT, EVT OrigVT, ISD::ArgFlagsTy Flags,
+static bool CalculateStackSlotUsed(const PPCSubtarget &Subtarget, EVT ArgVT,
+                                   EVT OrigVT, ISD::ArgFlagsTy Flags,
                                    unsigned PtrByteSize, unsigned LinkageSize,
                                    unsigned ParamAreaSize, unsigned &ArgOffset,
                                    unsigned &AvailableFPRs,
@@ -3919,7 +3920,13 @@ static bool CalculateStackSlotUsed(EVT ArgVT, EVT OrigVT, ISD::ArgFlagsTy Flags,
         --AvailableVRs;
         return false;
       }
-  }
+  } else if (Subtarget.isPPC64() && Subtarget.isELFv2ABI() &&
+             Flags.getByValSize() >= 8)
+    // For 64-bit ELF v2, passing by value object whose size is no less than 8
+    // bytes will be copied to parameter save area. This is for compatibility
+    // for other compiler which requires byval parameters to be stored in
+    // caller's parameter save area.
+    return true;
 
   return UseMemory;
 }
@@ -4262,7 +4269,7 @@ SDValue PPCTargetLowering::LowerFormalArguments_64SVR4(
     if (Ins[i].Flags.isNest())
       continue;
 
-    if (CalculateStackSlotUsed(Ins[i].VT, Ins[i].ArgVT, Ins[i].Flags,
+    if (CalculateStackSlotUsed(Subtarget, Ins[i].VT, Ins[i].ArgVT, Ins[i].Flags,
                                PtrByteSize, LinkageSize, ParamAreaSize,
                                NumBytes, AvailableFPRs, AvailableVRs))
       HasParameterArea = true;
@@ -4723,9 +4730,9 @@ needStackSlotPassParameters(const PPCSubtarget &Subtarget,
   for (const ISD::OutputArg& Param : Outs) {
     if (Param.Flags.isNest()) continue;
 
-    if (CalculateStackSlotUsed(Param.VT, Param.ArgVT, Param.Flags, PtrByteSize,
-                               LinkageSize, ParamAreaSize, NumBytes,
-                               AvailableFPRs, AvailableVRs))
+    if (CalculateStackSlotUsed(Subtarget, Param.VT, Param.ArgVT, Param.Flags,
+                               PtrByteSize, LinkageSize, ParamAreaSize,
+                               NumBytes, AvailableFPRs, AvailableVRs))
       return true;
   }
   return false;
@@ -5961,9 +5968,10 @@ SDValue PPCTargetLowering::LowerCall_64SVR4(
     unsigned NumBytesTmp = NumBytes;
     for (unsigned i = 0; i != NumOps; ++i) {
       if (Outs[i].Flags.isNest()) continue;
-      if (CalculateStackSlotUsed(Outs[i].VT, Outs[i].ArgVT, Outs[i].Flags,
-                                 PtrByteSize, LinkageSize, ParamAreaSize,
-                                 NumBytesTmp, AvailableFPRs, AvailableVRs))
+      if (CalculateStackSlotUsed(Subtarget, Outs[i].VT, Outs[i].ArgVT,
+                                 Outs[i].Flags, PtrByteSize, LinkageSize,
+                                 ParamAreaSize, NumBytesTmp, AvailableFPRs,
+                                 AvailableVRs))
         HasParameterArea = true;
     }
   }
diff --git a/llvm/test/CodeGen/PowerPC/byval.ll b/llvm/test/CodeGen/PowerPC/byval.ll
index c67cc10..e6ad0f4 100644
--- a/llvm/test/CodeGen/PowerPC/byval.ll
+++ b/llvm/test/CodeGen/PowerPC/byval.ll
@@ -1,4 +1,3 @@
-; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
 ; RUN: llc -verify-machineinstrs < %s | FileCheck %s
 
 target datalayout = "e-m:e-i64:64-n32:64-S128-v256:256:256-v512:512:512"
@@ -9,15 +8,15 @@ target triple = "powerpc64le-unknown-linux-gnu"
 declare dso_local i32 @foo1(%struct* byval(%struct) %var)
 declare dso_local void @foo(%struct* %var)
 
-; FIXME: for the byval parameter %x, now the memory for local variable and
-; for parameter save area are overlap.
+; for the byval parameter %x, make sure the memory for local variable and
+; for parameter save area are not overlap.
 ; For the below case,
-; the local variable space is r1 + 40 ~ r1 + 76
+; the local variable space is r1 + 104 ~ r1 + 140
 ; the parameter save area is r1 + 32 ~ r1 + 68
 
 define dso_local i32 @bar() {
 ; CHECK-LABEL: bar:
-; CHECK:    addi 30, 1, 40
+; CHECK:    addi 30, 1, 104
 ; CHECK:    li 3, 16
 ; CHECK:    lxvd2x 0, 30, 3
 ; CHECK:    li 3, 48
@@ -25,7 +24,7 @@ define dso_local i32 @bar() {
 ; CHECK:    li 3, 32
 ; CHECK:    lxvd2x 0, 0, 30
 ; CHECK:    stxvd2x 0, 1, 3
-; CHECK:    lwz 3, 72(1)
+; CHECK:    lwz 3, 136(1)
 ; CHECK:    stw 3, 64(1)
 entry:
   %x = alloca %struct, align 4