On Thu, Jul 6, 2017 at 12:08 PM, H.J. Lu <hongjiu...@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.
--
H.J.
From 4d02c433206790e0ae7de4e91c0f412f9bdac7e8 Mon Sep 17 00:00:00 2001
From: "H.J. Lu" <hjl.to...@gmail.com>
Date: Thu, 6 Jul 2017 08:58:46 -0700
Subject: [PATCH] x86: Use DRAP only if there are outgoing arguments on stack
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.
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.
gcc/testsuite/
PR target/81313
* gcc.target/i386/pr81313-1.c: New test.
* gcc.target/i386/pr81313-2.c: Likewise.
* gcc.target/i386/pr81313-3.c: Likewise.
* gcc.target/i386/pr81313-4.c: Likewise.
* gcc.target/i386/pr81313-5.c: Likewise.
---
gcc/config/i386/i386.c | 18 ++++++++++++++++--
gcc/config/i386/i386.h | 3 +++
gcc/testsuite/gcc.target/i386/pr81313-1.c | 12 ++++++++++++
gcc/testsuite/gcc.target/i386/pr81313-2.c | 12 ++++++++++++
gcc/testsuite/gcc.target/i386/pr81313-3.c | 12 ++++++++++++
gcc/testsuite/gcc.target/i386/pr81313-4.c | 12 ++++++++++++
gcc/testsuite/gcc.target/i386/pr81313-5.c | 12 ++++++++++++
7 files changed, 79 insertions(+), 2 deletions(-)
create mode 100644 gcc/testsuite/gcc.target/i386/pr81313-1.c
create mode 100644 gcc/testsuite/gcc.target/i386/pr81313-2.c
create mode 100644 gcc/testsuite/gcc.target/i386/pr81313-3.c
create mode 100644 gcc/testsuite/gcc.target/i386/pr81313-4.c
create mode 100644 gcc/testsuite/gcc.target/i386/pr81313-5.c
diff --git a/gcc/config/i386/i386.c b/gcc/config/i386/i386.c
index 1a8a3a3..b041524 100644
--- a/gcc/config/i386/i386.c
+++ b/gcc/config/i386/i386.c
@@ -10143,7 +10143,13 @@ ix86_function_arg_advance (cumulative_args_t cum_v, machine_mode mode,
/* For pointers passed in memory we expect bounds passed in Bounds
Table. */
if (!nregs)
- cum->bnds_in_bt = chkp_type_bounds_count (type);
+ {
+ /* Track if there are outgoing arguments on stack. */
+ if (cum->caller)
+ cfun->machine->outgoing_args_on_stack = true;
+
+ cum->bnds_in_bt = chkp_type_bounds_count (type);
+ }
}
/* Define where to put the arguments to a function.
@@ -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 && cum->caller)
+ cfun->machine->outgoing_args_on_stack = true;
+
return arg;
}
@@ -13646,7 +13656,11 @@ ix86_update_stack_boundary (void)
static rtx
ix86_get_drap_rtx (void)
{
- if (ix86_force_drap || !ACCUMULATE_OUTGOING_ARGS)
+ /* We must use DRAP if there are outgoing arguments on stack and
+ ACCUMULATE_OUTGOING_ARGS is false. */
+ if (ix86_force_drap
+ || (cfun->machine->outgoing_args_on_stack
+ && !ACCUMULATE_OUTGOING_ARGS))
crtl->need_drap = true;
if (stack_realign_drap)
diff --git a/gcc/config/i386/i386.h b/gcc/config/i386/i386.h
index 08243c1..a2ae9b4 100644
--- a/gcc/config/i386/i386.h
+++ b/gcc/config/i386/i386.h
@@ -2657,6 +2657,9 @@ struct GTY(()) machine_function {
frame pointer.) */
unsigned int call_ms2sysv_extra_regs:3;
+ /* Nonzero if the function places outgoing arguments on stack. */
+ BOOL_BITFIELD outgoing_args_on_stack : 1;
+
/* During prologue/epilogue generation, the current frame state.
Otherwise, the frame state at the end of the prologue. */
struct machine_frame_state fs;
diff --git a/gcc/testsuite/gcc.target/i386/pr81313-1.c b/gcc/testsuite/gcc.target/i386/pr81313-1.c
new file mode 100644
index 0000000..f765003
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr81313-1.c
@@ -0,0 +1,12 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -mno-accumulate-outgoing-args -mincoming-stack-boundary=4 -mpreferred-stack-boundary=6" } */
+
+extern void foo (void);
+
+void
+bar (void)
+{
+ foo ();
+}
+
+/* { dg-final { scan-assembler-not "lea\[lq\]?\[\\t \]*\[0-9\]*\\(%\[er\]sp\\)" } } */
diff --git a/gcc/testsuite/gcc.target/i386/pr81313-2.c b/gcc/testsuite/gcc.target/i386/pr81313-2.c
new file mode 100644
index 0000000..2cdc645
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr81313-2.c
@@ -0,0 +1,12 @@
+/* { dg-do compile { target ia32 } } */
+/* { dg-options "-O2 -mno-accumulate-outgoing-args -mincoming-stack-boundary=4 -mpreferred-stack-boundary=6 -mno-iamcu" } */
+
+extern void foo (int, int, int);
+
+void
+bar (void)
+{
+ foo (1, 2, 3);
+}
+
+/* { dg-final { scan-assembler "lea\[l\]?\[\\t \]*\[0-9\]*\\(%esp\\)" } } */
diff --git a/gcc/testsuite/gcc.target/i386/pr81313-3.c b/gcc/testsuite/gcc.target/i386/pr81313-3.c
new file mode 100644
index 0000000..9c1b232
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr81313-3.c
@@ -0,0 +1,12 @@
+/* { dg-do compile { target ia32 } } */
+/* { dg-options "-O2 -mno-accumulate-outgoing-args -mincoming-stack-boundary=4 -mpreferred-stack-boundary=6" } */
+
+extern void foo (int, int, int) __attribute__ ((regparm(3)));
+
+void
+bar (int i1, int i2, int i3, int i4)
+{
+ foo (i1, i2, i3);
+}
+
+/* { dg-final { scan-assembler-not "lea\[l\]?\[\\t \]*\[0-9\]*\\(%esp\\)" } } */
diff --git a/gcc/testsuite/gcc.target/i386/pr81313-4.c b/gcc/testsuite/gcc.target/i386/pr81313-4.c
new file mode 100644
index 0000000..bad0b3c
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr81313-4.c
@@ -0,0 +1,12 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -mno-accumulate-outgoing-args -mincoming-stack-boundary=4 -mpreferred-stack-boundary=6" } */
+
+extern void foo (int, int, int, int, int, int, int);
+
+void
+bar (void)
+{
+ foo (1, 2, 3, 4, 5, 6, 7);
+}
+
+/* { dg-final { scan-assembler "lea\[lq\]?\[\\t \]*\[0-9\]*\\(%\[er\]sp\\)" } } */
diff --git a/gcc/testsuite/gcc.target/i386/pr81313-5.c b/gcc/testsuite/gcc.target/i386/pr81313-5.c
new file mode 100644
index 0000000..51a543c
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr81313-5.c
@@ -0,0 +1,12 @@
+/* { dg-do compile { target { ! ia32 } } } */
+/* { dg-options "-O2 -mno-accumulate-outgoing-args -mincoming-stack-boundary=4 -mpreferred-stack-boundary=6" } */
+
+extern void foo (int, int, int, int, int, int);
+
+void
+bar (int i1, int i2, int i3, int i4, int i5, int i6, int i7)
+{
+ foo (i1, i2, i3, i4, i5, i6);
+}
+
+/* { dg-final { scan-assembler-not "lea\[lq\]?\[\\t \]*\[0-9\]*\\(%\[er\]sp\\)" } } */
--
2.9.4
