vendor/llvm/llvm-trunk-r366426

1 files changed, 144 insertions, 18 deletions

diff --git a/lib/Target/X86/X86CallingConv.cpp b/lib/Target/X86/X86CallingConv.cpp
index 59dde982f512..aee344a26764 100644
--- a/lib/Target/X86/X86CallingConv.cpp
+++ b/lib/Target/X86/X86CallingConv.cpp
@@ -1,9 +1,8 @@
 //=== X86CallingConv.cpp - X86 Custom Calling Convention Impl   -*- C++ -*-===//
 //
-//                     The LLVM Compiler Infrastructure
-//
-// This file is distributed under the University of Illinois Open Source
-// License. See LICENSE.TXT for details.
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 //
 //===----------------------------------------------------------------------===//
 //
@@ -12,16 +11,23 @@
 //
 //===----------------------------------------------------------------------===//
 
-#include "MCTargetDesc/X86MCTargetDesc.h"
+#include "X86CallingConv.h"
 #include "X86Subtarget.h"
+#include "llvm/ADT/SmallVector.h"
 #include "llvm/CodeGen/CallingConvLower.h"
 #include "llvm/IR/CallingConv.h"
 
-namespace llvm {
-
-bool CC_X86_32_RegCall_Assign2Regs(unsigned &ValNo, MVT &ValVT, MVT &LocVT,
-                                   CCValAssign::LocInfo &LocInfo,
-                                   ISD::ArgFlagsTy &ArgFlags, CCState &State) {
+using namespace llvm;
+
+/// When regcall calling convention compiled to 32 bit arch, special treatment
+/// is required for 64 bit masks.
+/// The value should be assigned to two GPRs.
+/// \return true if registers were allocated and false otherwise.
+static bool CC_X86_32_RegCall_Assign2Regs(unsigned &ValNo, MVT &ValVT,
+                                          MVT &LocVT,
+                                          CCValAssign::LocInfo &LocInfo,
+                                          ISD::ArgFlagsTy &ArgFlags,
+                                          CCState &State) {
   // List of GPR registers that are available to store values in regcall
   // calling convention.
   static const MCPhysReg RegList[] = {X86::EAX, X86::ECX, X86::EDX, X86::EDI,
@@ -113,9 +119,15 @@ static bool CC_X86_VectorCallAssignRegister(unsigned &ValNo, MVT &ValVT,
   return false;
 }
 
-bool CC_X86_64_VectorCall(unsigned &ValNo, MVT &ValVT, MVT &LocVT,
-                          CCValAssign::LocInfo &LocInfo,
-                          ISD::ArgFlagsTy &ArgFlags, CCState &State) {
+/// Vectorcall calling convention has special handling for vector types or
+/// HVA for 64 bit arch.
+/// For HVAs shadow registers might be allocated on the first pass
+/// and actual XMM registers are allocated on the second pass.
+/// For vector types, actual XMM registers are allocated on the first pass.
+/// \return true if registers were allocated and false otherwise.
+static bool CC_X86_64_VectorCall(unsigned &ValNo, MVT &ValVT, MVT &LocVT,
+                                 CCValAssign::LocInfo &LocInfo,
+                                 ISD::ArgFlagsTy &ArgFlags, CCState &State) {
   // On the second pass, go through the HVAs only.
   if (ArgFlags.isSecArgPass()) {
     if (ArgFlags.isHva())
@@ -150,7 +162,10 @@ bool CC_X86_64_VectorCall(unsigned &ValNo, MVT &ValVT, MVT &LocVT,
       // created on top of the basic 32 bytes of win64.
       // It can happen if the fifth or sixth argument is vector type or HVA.
       // At that case for each argument a shadow stack of 8 bytes is allocated.
-      if (Reg == X86::XMM4 || Reg == X86::XMM5)
+      const TargetRegisterInfo *TRI =
+          State.getMachineFunction().getSubtarget().getRegisterInfo();
+      if (TRI->regsOverlap(Reg, X86::XMM4) ||
+          TRI->regsOverlap(Reg, X86::XMM5))
         State.AllocateStack(8, 8);
 
       if (!ArgFlags.isHva()) {
@@ -165,9 +180,14 @@ bool CC_X86_64_VectorCall(unsigned &ValNo, MVT &ValVT, MVT &LocVT,
   return ArgFlags.isHva();
 }
 
-bool CC_X86_32_VectorCall(unsigned &ValNo, MVT &ValVT, MVT &LocVT,
-                          CCValAssign::LocInfo &LocInfo,
-                          ISD::ArgFlagsTy &ArgFlags, CCState &State) {
+/// Vectorcall calling convention has special handling for vector types or
+/// HVA for 32 bit arch.
+/// For HVAs actual XMM registers are allocated on the second pass.
+/// For vector types, actual XMM registers are allocated on the first pass.
+/// \return true if registers were allocated and false otherwise.
+static bool CC_X86_32_VectorCall(unsigned &ValNo, MVT &ValVT, MVT &LocVT,
+                                 CCValAssign::LocInfo &LocInfo,
+                                 ISD::ArgFlagsTy &ArgFlags, CCState &State) {
   // On the second pass, go through the HVAs only.
   if (ArgFlags.isSecArgPass()) {
     if (ArgFlags.isHva())
@@ -205,4 +225,110 @@ bool CC_X86_32_VectorCall(unsigned &ValNo, MVT &ValVT, MVT &LocVT,
   return false; // No register was assigned - Continue the search.
 }
 
-} // End llvm namespace
+static bool CC_X86_AnyReg_Error(unsigned &, MVT &, MVT &,
+                                CCValAssign::LocInfo &, ISD::ArgFlagsTy &,
+                                CCState &) {
+  llvm_unreachable("The AnyReg calling convention is only supported by the "
+                   "stackmap and patchpoint intrinsics.");
+  // gracefully fallback to X86 C calling convention on Release builds.
+  return false;
+}
+
+static bool CC_X86_32_MCUInReg(unsigned &ValNo, MVT &ValVT, MVT &LocVT,
+                               CCValAssign::LocInfo &LocInfo,
+                               ISD::ArgFlagsTy &ArgFlags, CCState &State) {
+  // This is similar to CCAssignToReg<[EAX, EDX, ECX]>, but makes sure
+  // not to split i64 and double between a register and stack
+  static const MCPhysReg RegList[] = {X86::EAX, X86::EDX, X86::ECX};
+  static const unsigned NumRegs = sizeof(RegList) / sizeof(RegList[0]);
+
+  SmallVectorImpl<CCValAssign> &PendingMembers = State.getPendingLocs();
+
+  // If this is the first part of an double/i64/i128, or if we're already
+  // in the middle of a split, add to the pending list. If this is not
+  // the end of the split, return, otherwise go on to process the pending
+  // list
+  if (ArgFlags.isSplit() || !PendingMembers.empty()) {
+    PendingMembers.push_back(
+        CCValAssign::getPending(ValNo, ValVT, LocVT, LocInfo));
+    if (!ArgFlags.isSplitEnd())
+      return true;
+  }
+
+  // If there are no pending members, we are not in the middle of a split,
+  // so do the usual inreg stuff.
+  if (PendingMembers.empty()) {
+    if (unsigned Reg = State.AllocateReg(RegList)) {
+      State.addLoc(CCValAssign::getReg(ValNo, ValVT, Reg, LocVT, LocInfo));
+      return true;
+    }
+    return false;
+  }
+
+  assert(ArgFlags.isSplitEnd());
+
+  // We now have the entire original argument in PendingMembers, so decide
+  // whether to use registers or the stack.
+  // Per the MCU ABI:
+  // a) To use registers, we need to have enough of them free to contain
+  // the entire argument.
+  // b) We never want to use more than 2 registers for a single argument.
+
+  unsigned FirstFree = State.getFirstUnallocated(RegList);
+  bool UseRegs = PendingMembers.size() <= std::min(2U, NumRegs - FirstFree);
+
+  for (auto &It : PendingMembers) {
+    if (UseRegs)
+      It.convertToReg(State.AllocateReg(RegList[FirstFree++]));
+    else
+      It.convertToMem(State.AllocateStack(4, 4));
+    State.addLoc(It);
+  }
+
+  PendingMembers.clear();
+
+  return true;
+}
+
+/// X86 interrupt handlers can only take one or two stack arguments, but if
+/// there are two arguments, they are in the opposite order from the standard
+/// convention. Therefore, we have to look at the argument count up front before
+/// allocating stack for each argument.
+static bool CC_X86_Intr(unsigned &ValNo, MVT &ValVT, MVT &LocVT,
+                        CCValAssign::LocInfo &LocInfo,
+                        ISD::ArgFlagsTy &ArgFlags, CCState &State) {
+  const MachineFunction &MF = State.getMachineFunction();
+  size_t ArgCount = State.getMachineFunction().getFunction().arg_size();
+  bool Is64Bit = static_cast<const X86Subtarget &>(MF.getSubtarget()).is64Bit();
+  unsigned SlotSize = Is64Bit ? 8 : 4;
+  unsigned Offset;
+  if (ArgCount == 1 && ValNo == 0) {
+    // If we have one argument, the argument is five stack slots big, at fixed
+    // offset zero.
+    Offset = State.AllocateStack(5 * SlotSize, 4);
+  } else if (ArgCount == 2 && ValNo == 0) {
+    // If we have two arguments, the stack slot is *after* the error code
+    // argument. Pretend it doesn't consume stack space, and account for it when
+    // we assign the second argument.
+    Offset = SlotSize;
+  } else if (ArgCount == 2 && ValNo == 1) {
+    // If this is the second of two arguments, it must be the error code. It
+    // appears first on the stack, and is then followed by the five slot
+    // interrupt struct.
+    Offset = 0;
+    (void)State.AllocateStack(6 * SlotSize, 4);
+  } else {
+    report_fatal_error("unsupported x86 interrupt prototype");
+  }
+
+  // FIXME: This should be accounted for in
+  // X86FrameLowering::getFrameIndexReference, not here.
+  if (Is64Bit && ArgCount == 2)
+    Offset += SlotSize;
+
+  State.addLoc(CCValAssign::getMem(ValNo, ValVT, Offset, LocVT, LocInfo));
+  return true;
+}
+
+// Provides entry points of CC_X86 and RetCC_X86.
+#include "X86GenCallingConv.inc"