diff mbox

PR target/81313: Use DRAP only if there are outgoing arguments on stack

Message ID CAMe9rOob32Ov8Laf7eTDZWfgMzus4M7Qjy_=uKagrRMbEgXQiw@mail.gmail.com
State New
Headers show

Commit Message

H.J. Lu July 9, 2017, 6:29 p.m. UTC 
On Sun, Jul 9, 2017 at 11:19 AM, Uros Bizjak <ubizjak@gmail.com> wrote:
> On Fri, Jul 7, 2017 at 12:14 AM, H.J. Lu <hjl.tools@gmail.com> wrote:
>> On Thu, Jul 6, 2017 at 12:08 PM, H.J. Lu <hongjiu.lu@intel.com> wrote:
>>> Since DRAP is needed only if there are outgoing arguments on stack, we
>>> should track outgoing arguments on stack and avoid setting need_drap to
>>> true when there are no outgoing arguments on stack.
>>>
>>> Tested on i686 and x86-64 with SSE2, AVX and AVX2.  There is no
>>> regression.  OK for trunk?
>>>
>>> H.J.
>>> ---
>>> gcc/
>>>
>>>         PR target/81313
>>>         * config/i386/i386.c (ix86_function_arg_advance): Set
>>>         outgoing_args_on_stack to true if there are outgoing arguments
>>>         on stack.
>>>         (ix86_function_arg): Likewise.
>>>         (ix86_get_drap_rtx): Use DRAP only if there are outgoing
>>>         arguments on stack and ACCUMULATE_OUTGOING_ARGS is false.
>>>         * config/i386/i386.h (machine_function): Add
>>>         outgoing_args_on_stack.
>>>
>>> @@ -10473,6 +10479,10 @@ ix86_function_arg (cumulative_args_t cum_v, machine_mode omode,
>>>    else
>>>      arg = function_arg_32 (cum, mode, omode, type, bytes, words);
>>>
>>> +  /* Track if there are outgoing arguments on stack.  */
>>> +  if (arg == NULL_RTX)
>>> +    cfun->machine->outgoing_args_on_stack = true;
>>
>> This should be
>>
>> +  /* Track if there are outgoing arguments on stack.  */
>> +  if (arg == NULL_RTX && cum->caller)
>> +    cfun->machine->outgoing_args_on_stack = true;
>>
>> to check outgoing arguments for caller here.
>>
>>>    return arg;
>>>  }
>>>
>>>
>>
>> I am testing updated patch with a new testcase.
>
> Updated patch LGTM.
>
> OK for mainline.

Done.  My patch will cause

FAIL: gcc.dg/stack-layout-dynamic-1.c

since on x86, now stack realignment is done with

.cfi_startproc
pushl %ebp
.cfi_def_cfa_offset 8
.cfi_offset 5, -8
movl %esp, %ebp
.cfi_def_cfa_register 5
andl $-65536, %esp

instead of

.cfi_startproc
pushl %edi
.cfi_def_cfa_offset 8
.cfi_offset 7, -8
leal 8(%esp), %edi
.cfi_def_cfa 7, 0
andl $-65536, %esp
pushl -4(%edi)
pushl %ebp
.cfi_escape 0x10,0x5,0x2,0x75,0
movl %esp, %ebp

PR target/81313
* gcc.dg/stack-layout-dynamic-1.c (dg-options): Add -mregparm=3
for ia32.
Don't expect cfi_escape and expect cfi_def_cfa_register on x86.

OK for trunk?

Thanks.
diff mbox

Patch

From 810ce19512c1e55095ac33c5ebd54bb74e47049a Mon Sep 17 00:00:00 2001
From: "H.J. Lu" <hjl.tools@gmail.com>
Date: Thu, 6 Jul 2017 10:56:57 -0700
Subject: [PATCH] x86: Update gcc.dg/stack-layout-dynamic-1.c

On x86, since stack realignment is done with

	.cfi_startproc
	pushl	%ebp
	.cfi_def_cfa_offset 8
	.cfi_offset 5, -8
	movl	%esp, %ebp
	.cfi_def_cfa_register 5
	andl	$-65536, %esp

it is preferred to have .cfi_def_cfa_register, instead of

	.cfi_startproc
	pushl	%edi
	.cfi_def_cfa_offset 8
	.cfi_offset 7, -8
	leal	8(%esp), %edi
	.cfi_def_cfa 7, 0
	andl	$-65536, %esp
	pushl	-4(%edi)
	pushl	%ebp
	.cfi_escape 0x10,0x5,0x2,0x75,0
	movl	%esp, %ebp

	PR target/81313
	* gcc.dg/stack-layout-dynamic-1.c (dg-options): Add -mregparm=3
	for ia32.
	Don't expect cfi_escape and expect cfi_def_cfa_register on x86.
---
 gcc/testsuite/gcc.dg/stack-layout-dynamic-1.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/gcc/testsuite/gcc.dg/stack-layout-dynamic-1.c b/gcc/testsuite/gcc.dg/stack-layout-dynamic-1.c
index 9f2d37d..c08cd9d 100644
--- a/gcc/testsuite/gcc.dg/stack-layout-dynamic-1.c
+++ b/gcc/testsuite/gcc.dg/stack-layout-dynamic-1.c
@@ -2,6 +2,7 @@ 
    in one pass together with normal local variables.  */
 /* { dg-do compile } */
 /* { dg-options "-O0 -fomit-frame-pointer" } */
+/* { dg-options "-O0 -fomit-frame-pointer -mregparm=3" { target { { i?86-*-* x86_64-*-* } && ia32 } } } */
 /* { dg-require-effective-target ptr32plus } */
 
 extern void bar (void *, void *, void *);
@@ -12,4 +13,6 @@  void foo (void)
   __attribute__ ((aligned(32768))) char runtime_aligned_2[1024];
   bar (&i, &runtime_aligned_1, &runtime_aligned_2);
 }
-/* { dg-final { scan-assembler-not "cfi_def_cfa_register" } } */
+/* { dg-final { scan-assembler-not "cfi_escape" { target i?86-*-* x86_64-*-* } } } */
+/* { dg-final { scan-assembler-not "cfi_def_cfa_register" { target { ! { { i?86-*-* } || { x86_64-*-* } } } } } } */
+/* { dg-final { scan-assembler "cfi_def_cfa_register" { target i?86-*-* x86_64-*-* } } } */
-- 
2.9.4