Teach fast isel about the win64 calling convention.

[thakis]

Summary

This mostly just works.

Vectorcall rets are still not supported.

The win64_eh test change is because fast isel doesn't use rsi for temporary computations, so it doesn't need to be pushed. The test case I'm changing was originally added to test pushes, but by now there are other test cases in that file exercising that code path.

[rnk]

lgtm

[thakis]

r275607, thanks!

lib/Target/X86/X86FastISel.cpp

if (TLI.supportSplitCSR(FuncInfo.MF))
     return false;
 
   CallingConv::ID CC = F.getCallingConv();
   if (CC != CallingConv::C &&
       CC != CallingConv::Fast &&
       CC != CallingConv::X86_FastCall &&
       CC != CallingConv::X86_StdCall &&
       CC != CallingConv::X86_ThisCall &&
-      CC != CallingConv::X86_64_SysV)
-    return false;
-
-  if (Subtarget->isCallingConvWin64(CC))
+      CC != CallingConv::X86_64_SysV &&
+      CC != CallingConv::X86_64_Win64)
     return false;
 
   // Don't handle popping bytes if they don't fit the ret's immediate.
   if (!isUInt<16>(X86MFInfo->getBytesToPopOnReturn()))
     return false;
 
   // fastcc with -tailcallopt is intended to provide a guaranteed
   // tail call optimization. Fastisel doesn't know how to do that.

test/CodeGen/X86/fast-isel-x86-64.ll

 ; RUN: llc < %s -mattr=-avx -fast-isel -mcpu=core2 -O0 -regalloc=fast -asm-verbose=0 -fast-isel-abort=1 | FileCheck %s
+; RUN: llc < %s -mattr=-avx -fast-isel -mcpu=core2 -O0 -regalloc=fast -asm-verbose=0 -fast-isel-verbose 2>&1 >/dev/null | FileCheck %s --check-prefix=STDERR --allow-empty
 ; RUN: llc < %s -mattr=+avx -fast-isel -mcpu=core2 -O0 -regalloc=fast -asm-verbose=0 -fast-isel-abort=1 | FileCheck %s --check-prefix=AVX
 
 target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64"
 target triple = "x86_64-apple-darwin10.0.0"
 
 ; Make sure that fast-isel folds the immediate into the binop even though it
 ; is non-canonical.
 define i32 @test1(i32 %i) nounwind ssp {

 
 ; CHECK-LABEL: allocamaterialize
 define void @allocamaterialize() {
   %a = alloca i32
 ; CHECK: leaq {{.*}}, %rdi
   call void @takesi32ptr(i32* %a)
   ret void
 }
+
+; STDERR-NOT: FastISel missed terminator:   ret void
+; CHECK-LABEL: win64ccfun
+define x86_64_win64cc void @win64ccfun(i32 %i) {
+; CHECK: ret
+  ret void
+}

test/CodeGen/X86/win64_eh.ll

 ; WIN64: subq %rax, %rsp
 ; WIN64: .seh_stackalloc 8000
 ; WIN64: .seh_endprologue
 ; WIN64: addq $8000, %rsp
 ; WIN64: ret
 ; WIN64: .seh_endproc
 
 
-; Checks stack push
 define i32 @foo3(i32 %f_arg, i32 %e_arg, i32 %d_arg, i32 %c_arg, i32 %b_arg, i32 %a_arg) uwtable {
 entry:
   %a = alloca i32
   %b = alloca i32
   %c = alloca i32
   %d = alloca i32
   %e = alloca i32
   %f = alloca i32
entry:
   %tmp13 = add i32 %tmp10, %tmp12
   %tmp14 = load i32, i32* %f
   %tmp15 = mul i32 %tmp14, 13
   %tmp16 = add i32 %tmp13, %tmp15
   ret i32 %tmp16
 }
 ; WIN64-LABEL: foo3:
 ; WIN64: .seh_proc foo3
-; WIN64: pushq %rsi
-; WIN64: .seh_pushreg 6
 ; NORM:  subq $24, %rsp
 ; ATOM:  leaq -24(%rsp), %rsp
 ; WIN64: .seh_stackalloc 24
 ; WIN64: .seh_endprologue
 ; WIN64: addq $24, %rsp
-; WIN64: popq %rsi
 ; WIN64: ret
 ; WIN64: .seh_endproc
 
 
 ; Check emission of eh handler and handler data
 declare i32 @_d_eh_personality(i32, i32, i64, i8*, i8*)
 declare void @_d_eh_resume_unwind(i8*)