Target/X86: [PR8777][PR8778] Tweak alloca/chkstk for Windows targets.

FIXME: Some cleanups would be needed.
llvm-svn: 128206

2 files changed, 76 insertions, 1 deletions

diff --git a/llvm/test/CodeGen/X86/win64_alloca_dynalloca.ll b/llvm/test/CodeGen/X86/win64_alloca_dynalloca.ll
new file mode 100644
index 00000000000..87d632afa64
--- /dev/null
+++ b/llvm/test/CodeGen/X86/win64_alloca_dynalloca.ll
@@ -0,0 +1,74 @@
+; RUN: llc < %s -mtriple=x86_64-mingw32     | FileCheck %s -check-prefix=M64
+; RUN: llc < %s -mtriple=x86_64-win32       | FileCheck %s -check-prefix=W64
+; RUN: llc < %s -mtriple=x86_64-win32-macho | FileCheck %s -check-prefix=EFI
+; PR8777
+; PR8778
+
+define i64 @foo(i64 %n, i64 %x) nounwind {
+entry:
+
+  %buf0 = alloca i8, i64 4096, align 1
+
+; ___chkstk must adjust %rsp.
+; M64: movq  %rsp, %rbp
+; M64:       $4096, %rax
+; M64: callq ___chkstk
+; M64-NOT:   %rsp
+
+; __chkstk does not adjust %rsp.
+; W64: movq  %rsp, %rbp
+; W64:       $4096, %rax
+; W64: callq __chkstk
+; W64: subq  $4096, %rsp
+
+; Freestanding
+; EFI: movq  %rsp, %rbp
+; EFI:       $[[B0OFS:4096|4104]], %rsp
+; EFI-NOT:   call
+
+  %buf1 = alloca i8, i64 %n, align 1
+
+; M64: leaq  15(%rcx), %rax
+; M64: andq  $-16, %rax
+; M64: callq ___chkstk
+; M64-NOT:   %rsp
+; M64: movq  %rsp, %rax
+
+; W64: leaq  15(%rcx), %rax
+; W64: andq  $-16, %rax
+; W64: callq __chkstk
+; W64: subq  %rax, %rsp
+; W64: movq  %rsp, %rax
+
+; EFI: leaq  15(%rcx), %rax
+; EFI: andq  $-16, %rax
+; EFI: movq  %rsp, [[R64:%r..]]
+; EFI: subq  %rax, [[R64]]
+; EFI: movq  [[R64]], %rsp
+
+  %r = call i64 @bar(i64 %n, i64 %x, i64 %n, i8* %buf0, i8* %buf1) nounwind
+
+; M64: subq  $48, %rsp
+; M64: leaq  -4096(%rbp), %r9
+; M64: movq  %rax, 32(%rsp)
+; M64: callq bar
+
+; W64: subq  $48, %rsp
+; W64: leaq  -4096(%rbp), %r9
+; W64: movq  %rax, 32(%rsp)
+; W64: callq bar
+
+; EFI: subq  $48, %rsp
+; EFI: leaq  -[[B0OFS]](%rbp), %r9
+; EFI: movq  [[R64]], 32(%rsp)
+; EFI: callq _bar
+
+  ret i64 %r
+
+; M64: movq    %rbp, %rsp
+
+; W64: movq    %rbp, %rsp
+
+}
+
+declare i64 @bar(i64, i64, i64, i8* nocapture, i8* nocapture) nounwind
diff --git a/llvm/test/CodeGen/X86/win_chkstk.ll b/llvm/test/CodeGen/X86/win_chkstk.ll
index 82ce81d4ae7..e4e4483ff94 100644
--- a/llvm/test/CodeGen/X86/win_chkstk.ll
+++ b/llvm/test/CodeGen/X86/win_chkstk.ll
@@ -3,6 +3,7 @@
 ; RUN: llc < %s -mtriple=i686-pc-mingw32 | FileCheck %s -check-prefix=MINGW_X32
 ; RUN: llc < %s -mtriple=x86_64-pc-mingw32 | FileCheck %s -check-prefix=MINGW_X64
 ; RUN: llc < %s -mtriple=i386-pc-linux | FileCheck %s -check-prefix=LINUX
+; RUN: llc < %s -mtriple=x86_64-pc-win32-macho | FileCheck %s -check-prefix=LINUX
 
 ; Windows and mingw require a prologue helper routine if more than 4096 bytes area
 ; allocated on the stack.  Windows uses __chkstk and mingw uses __alloca.  __alloca
@@ -16,7 +17,7 @@ entry:
 ; WIN_X32:    calll __chkstk
 ; WIN_X64:    callq __chkstk
 ; MINGW_X32:  calll __alloca
-; MINGW_X64:  callq __chkstk
+; MINGW_X64:  callq ___chkstk
 ; LINUX-NOT:  call __chkstk
   %array4096 = alloca [4096 x i8], align 16       ; <[4096 x i8]*> [#uses=0]
   ret i32 0