On Mon, Apr 14, 2025 at 2:39 AM Uros Bizjak <ubiz...@gmail.com> wrote:
>
> On Mon, Apr 14, 2025 at 8:54 AM Hongtao Liu <crazy...@gmail.com> wrote:
> >
> > On Mon, Apr 14, 2025 at 7:36 AM H.J. Lu <hjl.to...@gmail.com> wrote:
> > >
> > > Don't use red-zone when there are no caller-saved registers and APX is
> > > enabled since 128-byte red-zone is too small for 31 GPRs.
> > >
> > > gcc/
> > >
> > > PR target/119784
> > > * config/i386/i386.cc (ix86_using_red_zone): Don't use red-zone
> > > with APX and no caller-saved registers.
> > >
> > > gcc/testsuite/
> > >
> > > PR target/119784
> > > * gcc.target/i386/pr119784a.c: New test.
> > > * gcc.target/i386/pr119784b.c: Likewise.
> > >
> > > Signed-off-by: H.J. Lu <hjl.to...@gmail.com>
> > > ---
> > > gcc/config/i386/i386.cc | 6 ++
> > > gcc/testsuite/gcc.target/i386/pr119784a.c | 96 +++++++++++++++++++++++
> > > gcc/testsuite/gcc.target/i386/pr119784b.c | 87 ++++++++++++++++++++
> > > 3 files changed, 189 insertions(+)
> > > create mode 100644 gcc/testsuite/gcc.target/i386/pr119784a.c
> > > create mode 100644 gcc/testsuite/gcc.target/i386/pr119784b.c
> > >
> > > diff --git a/gcc/config/i386/i386.cc b/gcc/config/i386/i386.cc
> > > index 4f8380c4a58..91af239d484 100644
> > > --- a/gcc/config/i386/i386.cc
> > > +++ b/gcc/config/i386/i386.cc
> > > @@ -458,6 +458,9 @@ int ix86_arch_specified;
> > > indirect thunk pushes the return address onto stack, destroying
> > > red-zone.
> > >
> > > + NB: Don't use red-zone for functions with no_caller_saved_registers
> > > + when APX is enabled since 128-byte red-zone is too small for 31 GPRs.
> > > +
> > > TODO: If we can reserve the first 2 WORDs, for PUSH and, another
> > > for CALL, in red-zone, we can allow local indirect jumps with
> > > indirect thunk. */
> > > @@ -467,6 +470,9 @@ ix86_using_red_zone (void)
> > > {
> > > return (TARGET_RED_ZONE
> > > && !TARGET_64BIT_MS_ABI
> > > + && (!TARGET_APX_F
> > Could we use !TARGET_APX_EGPR, it's more clear.
Fixed. Here is the patch I am checking in. OK for backport to
release branches?
Thanks.
> > Others LGTM, but please wait for a while in case Uros has a different
> > opinion.
>
> LGTM too.
>
> Thanks,
> Uros.
>
> > > + || (cfun->machine->call_saved_registers
> > > + != TYPE_NO_CALLER_SAVED_REGISTERS))
> > > && (!cfun->machine->has_local_indirect_jump
> > > || cfun->machine->indirect_branch_type ==
> > > indirect_branch_keep));
> > > }
> > > diff --git a/gcc/testsuite/gcc.target/i386/pr119784a.c
> > > b/gcc/testsuite/gcc.target/i386/pr119784a.c
> > > new file mode 100644
> > > index 00000000000..8a119d4cc1f
> > > --- /dev/null
> > > +++ b/gcc/testsuite/gcc.target/i386/pr119784a.c
> > > @@ -0,0 +1,96 @@
> > > +/* { dg-do compile { target { *-*-linux* && lp64 } } } */
> > > +/* { dg-options "-O2 -fno-pic -mtune=generic -mgeneral-regs-only -mapxf
> > > -mtune-ctrl=prologue_using_move,epilogue_using_move" } */
> > > +/* Keep labels and directives ('.cfi_startproc', '.cfi_endproc'). */
> > > +/* { dg-final { check-function-bodies "**" "" "" { target "*-*-*" }
> > > {^\t?\.} } } */
> > > +
> > > +/* start must save and restore all caller saved registers. */
> > > +
> > > +/*
> > > +**start:
> > > +**.LFB[0-9]+:
> > > +** .cfi_startproc
> > > +** subq \$248, %rsp
> > > +**...
> > > +** movq %rax, \(%rsp\)
> > > +** movq %rdx, 8\(%rsp\)
> > > +** movq %rcx, 16\(%rsp\)
> > > +** movq %rbx, 24\(%rsp\)
> > > +** movq %rsi, 32\(%rsp\)
> > > +** movq %rdi, 40\(%rsp\)
> > > +**...
> > > +** movq %rbp, 48\(%rsp\)
> > > +** movq %r8, 56\(%rsp\)
> > > +** movq %r9, 64\(%rsp\)
> > > +** movq %r10, 72\(%rsp\)
> > > +** movq %r11, 80\(%rsp\)
> > > +** movq %r12, 88\(%rsp\)
> > > +** movq %r13, 96\(%rsp\)
> > > +** movq %r14, 104\(%rsp\)
> > > +** movq %r15, 112\(%rsp\)
> > > +** movq %r16, 120\(%rsp\)
> > > +** movq %r17, 128\(%rsp\)
> > > +** movq %r18, 136\(%rsp\)
> > > +** movq %r19, 144\(%rsp\)
> > > +** movq %r20, 152\(%rsp\)
> > > +** movq %r21, 160\(%rsp\)
> > > +** movq %r22, 168\(%rsp\)
> > > +** movq %r23, 176\(%rsp\)
> > > +** movq %r24, 184\(%rsp\)
> > > +** movq %r25, 192\(%rsp\)
> > > +** movq %r26, 200\(%rsp\)
> > > +** movq %r27, 208\(%rsp\)
> > > +** movq %r28, 216\(%rsp\)
> > > +** movq %r29, 224\(%rsp\)
> > > +** movq %r30, 232\(%rsp\)
> > > +** movq %r31, 240\(%rsp\)
> > > +**...
> > > +** call \*code\(%rip\)
> > > +** movq \(%rsp\), %rax
> > > +** movq 8\(%rsp\), %rdx
> > > +** movq 16\(%rsp\), %rcx
> > > +** movq 24\(%rsp\), %rbx
> > > +** movq 32\(%rsp\), %rsi
> > > +** movq 40\(%rsp\), %rdi
> > > +** movq 48\(%rsp\), %rbp
> > > +** movq 56\(%rsp\), %r8
> > > +** movq 64\(%rsp\), %r9
> > > +** movq 72\(%rsp\), %r10
> > > +** movq 80\(%rsp\), %r11
> > > +** movq 88\(%rsp\), %r12
> > > +** movq 96\(%rsp\), %r13
> > > +** movq 104\(%rsp\), %r14
> > > +** movq 112\(%rsp\), %r15
> > > +** movq 120\(%rsp\), %r16
> > > +** movq 128\(%rsp\), %r17
> > > +** movq 136\(%rsp\), %r18
> > > +** movq 144\(%rsp\), %r19
> > > +** movq 152\(%rsp\), %r20
> > > +** movq 160\(%rsp\), %r21
> > > +** movq 168\(%rsp\), %r22
> > > +** movq 176\(%rsp\), %r23
> > > +** movq 184\(%rsp\), %r24
> > > +** movq 192\(%rsp\), %r25
> > > +** movq 200\(%rsp\), %r26
> > > +** movq 208\(%rsp\), %r27
> > > +** movq 216\(%rsp\), %r28
> > > +** movq 224\(%rsp\), %r29
> > > +** movq 232\(%rsp\), %r30
> > > +** movq 240\(%rsp\), %r31
> > > +** addq \$248, %rsp
> > > +**...
> > > +** ret
> > > +** .cfi_endproc
> > > +**...
> > > +*/
> > > +
> > > +#define DONT_SAVE_REGS __attribute__((no_callee_saved_registers))
> > > +#define SAVE_REGS __attribute__((no_caller_saved_registers))
> > > +
> > > +typedef DONT_SAVE_REGS void (*op_t)(void);
> > > +
> > > +extern op_t code[];
> > > +
> > > +SAVE_REGS void start()
> > > +{
> > > + code[0]();
> > > +}
> > > diff --git a/gcc/testsuite/gcc.target/i386/pr119784b.c
> > > b/gcc/testsuite/gcc.target/i386/pr119784b.c
> > > new file mode 100644
> > > index 00000000000..c6761976ed6
> > > --- /dev/null
> > > +++ b/gcc/testsuite/gcc.target/i386/pr119784b.c
> > > @@ -0,0 +1,87 @@
> > > +/* { dg-do compile { target { *-*-linux* && x32 } } } */
> > > +/* { dg-options "-O2 -fno-pic -mtune=generic -mgeneral-regs-only -mapxf
> > > -mtune-ctrl=prologue_using_move,epilogue_using_move" } */
> > > +/* Keep labels and directives ('.cfi_startproc', '.cfi_endproc'). */
> > > +/* { dg-final { check-function-bodies "**" "" "" { target "*-*-*" }
> > > {^\t?\.} } } */
> > > +
> > > +/* start must save and restore all caller saved registers. */
> > > +
> > > +/*
> > > +**start:
> > > +**.LFB[0-9]+:
> > > +** .cfi_startproc
> > > +** subl \$248, %esp
> > > +**...
> > > +** movq %rax, \(%rsp\)
> > > +** movq %rdx, 8\(%rsp\)
> > > +** movq %rcx, 16\(%rsp\)
> > > +** movq %rbx, 24\(%rsp\)
> > > +** movq %rsi, 32\(%rsp\)
> > > +** movq %rdi, 40\(%rsp\)
> > > +**...
> > > +** movq %rbp, 48\(%rsp\)
> > > +** movq %r8, 56\(%rsp\)
> > > +** movq %r9, 64\(%rsp\)
> > > +** movq %r10, 72\(%rsp\)
> > > +** movq %r11, 80\(%rsp\)
> > > +** movq %r12, 88\(%rsp\)
> > > +** movq %r13, 96\(%rsp\)
> > > +** movq %r14, 104\(%rsp\)
> > > +** movq %r15, 112\(%rsp\)
> > > +** movq %r16, 120\(%rsp\)
> > > +** movq %r17, 128\(%rsp\)
> > > +** movq %r18, 136\(%rsp\)
> > > +** movq %r19, 144\(%rsp\)
> > > +** movq %r20, 152\(%rsp\)
> > > +** movq %r21, 160\(%rsp\)
> > > +** movq %r22, 168\(%rsp\)
> > > +** movq %r23, 176\(%rsp\)
> > > +** movq %r24, 184\(%rsp\)
> > > +** movq %r25, 192\(%rsp\)
> > > +** movq %r26, 200\(%rsp\)
> > > +** movq %r27, 208\(%rsp\)
> > > +** movq %r28, 216\(%rsp\)
> > > +** movq %r29, 224\(%rsp\)
> > > +** movq %r30, 232\(%rsp\)
> > > +** movq %r31, 240\(%rsp\)
> > > +**...
> > > +** movl code\(%rip\), %ebp
> > > +** call \*%rbp
> > > +** movq \(%rsp\), %rax
> > > +** movq 8\(%rsp\), %rdx
> > > +** movq 16\(%rsp\), %rcx
> > > +** movq 24\(%rsp\), %rbx
> > > +** movq 32\(%rsp\), %rsi
> > > +** movq 40\(%rsp\), %rdi
> > > +** movq 48\(%rsp\), %rbp
> > > +** movq 56\(%rsp\), %r8
> > > +** movq 64\(%rsp\), %r9
> > > +** movq 72\(%rsp\), %r10
> > > +** movq 80\(%rsp\), %r11
> > > +** movq 88\(%rsp\), %r12
> > > +** movq 96\(%rsp\), %r13
> > > +** movq 104\(%rsp\), %r14
> > > +** movq 112\(%rsp\), %r15
> > > +** movq 120\(%rsp\), %r16
> > > +** movq 128\(%rsp\), %r17
> > > +** movq 136\(%rsp\), %r18
> > > +** movq 144\(%rsp\), %r19
> > > +** movq 152\(%rsp\), %r20
> > > +** movq 160\(%rsp\), %r21
> > > +** movq 168\(%rsp\), %r22
> > > +** movq 176\(%rsp\), %r23
> > > +** movq 184\(%rsp\), %r24
> > > +** movq 192\(%rsp\), %r25
> > > +** movq 200\(%rsp\), %r26
> > > +** movq 208\(%rsp\), %r27
> > > +** movq 216\(%rsp\), %r28
> > > +** movq 224\(%rsp\), %r29
> > > +** movq 232\(%rsp\), %r30
> > > +** movq 240\(%rsp\), %r31
> > > +** addl \$248, %esp
> > > +**...
> > > +** ret
> > > +** .cfi_endproc
> > > +**...
> > > +*/
> > > +
> > > +#include "pr119784a.c"
> > > --
> > > 2.49.0
> > >
> >
> >
> > --
> > BR,
> > Hongtao
--
H.J.
From dffa12463f5b551e9267634718c0d2af00119ee8 Mon Sep 17 00:00:00 2001
From: "H.J. Lu" <hjl.to...@gmail.com>
Date: Sun, 13 Apr 2025 12:20:42 -0700
Subject: [PATCH] APX: Don't use red-zone with 32 GPRs and no caller-saved
registers
Don't use red-zone when there are no caller-saved registers with 32 GPRs
since 128-byte red-zone is too small for 31 GPRs.
gcc/
PR target/119784
* config/i386/i386.cc (ix86_using_red_zone): Don't use red-zone
with 32 GPRs and no caller-saved registers.
gcc/testsuite/
PR target/119784
* gcc.target/i386/pr119784a.c: New test.
* gcc.target/i386/pr119784b.c: Likewise.
Signed-off-by: H.J. Lu <hjl.to...@gmail.com>
---
gcc/config/i386/i386.cc | 6 ++
gcc/testsuite/gcc.target/i386/pr119784a.c | 96 +++++++++++++++++++++++
gcc/testsuite/gcc.target/i386/pr119784b.c | 87 ++++++++++++++++++++
3 files changed, 189 insertions(+)
create mode 100644 gcc/testsuite/gcc.target/i386/pr119784a.c
create mode 100644 gcc/testsuite/gcc.target/i386/pr119784b.c
diff --git a/gcc/config/i386/i386.cc b/gcc/config/i386/i386.cc
index 4f8380c4a58..b172f716c68 100644
--- a/gcc/config/i386/i386.cc
+++ b/gcc/config/i386/i386.cc
@@ -458,6 +458,9 @@ int ix86_arch_specified;
indirect thunk pushes the return address onto stack, destroying
red-zone.
+ NB: Don't use red-zone for functions with no_caller_saved_registers
+ and 32 GPRs since 128-byte red-zone is too small for 31 GPRs.
+
TODO: If we can reserve the first 2 WORDs, for PUSH and, another
for CALL, in red-zone, we can allow local indirect jumps with
indirect thunk. */
@@ -467,6 +470,9 @@ ix86_using_red_zone (void)
{
return (TARGET_RED_ZONE
&& !TARGET_64BIT_MS_ABI
+ && (!TARGET_APX_EGPR
+ || (cfun->machine->call_saved_registers
+ != TYPE_NO_CALLER_SAVED_REGISTERS))
&& (!cfun->machine->has_local_indirect_jump
|| cfun->machine->indirect_branch_type == indirect_branch_keep));
}
diff --git a/gcc/testsuite/gcc.target/i386/pr119784a.c b/gcc/testsuite/gcc.target/i386/pr119784a.c
new file mode 100644
index 00000000000..8a119d4cc1f
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr119784a.c
@@ -0,0 +1,96 @@
+/* { dg-do compile { target { *-*-linux* && lp64 } } } */
+/* { dg-options "-O2 -fno-pic -mtune=generic -mgeneral-regs-only -mapxf -mtune-ctrl=prologue_using_move,epilogue_using_move" } */
+/* Keep labels and directives ('.cfi_startproc', '.cfi_endproc'). */
+/* { dg-final { check-function-bodies "**" "" "" { target "*-*-*" } {^\t?\.} } } */
+
+/* start must save and restore all caller saved registers. */
+
+/*
+**start:
+**.LFB[0-9]+:
+** .cfi_startproc
+** subq \$248, %rsp
+**...
+** movq %rax, \(%rsp\)
+** movq %rdx, 8\(%rsp\)
+** movq %rcx, 16\(%rsp\)
+** movq %rbx, 24\(%rsp\)
+** movq %rsi, 32\(%rsp\)
+** movq %rdi, 40\(%rsp\)
+**...
+** movq %rbp, 48\(%rsp\)
+** movq %r8, 56\(%rsp\)
+** movq %r9, 64\(%rsp\)
+** movq %r10, 72\(%rsp\)
+** movq %r11, 80\(%rsp\)
+** movq %r12, 88\(%rsp\)
+** movq %r13, 96\(%rsp\)
+** movq %r14, 104\(%rsp\)
+** movq %r15, 112\(%rsp\)
+** movq %r16, 120\(%rsp\)
+** movq %r17, 128\(%rsp\)
+** movq %r18, 136\(%rsp\)
+** movq %r19, 144\(%rsp\)
+** movq %r20, 152\(%rsp\)
+** movq %r21, 160\(%rsp\)
+** movq %r22, 168\(%rsp\)
+** movq %r23, 176\(%rsp\)
+** movq %r24, 184\(%rsp\)
+** movq %r25, 192\(%rsp\)
+** movq %r26, 200\(%rsp\)
+** movq %r27, 208\(%rsp\)
+** movq %r28, 216\(%rsp\)
+** movq %r29, 224\(%rsp\)
+** movq %r30, 232\(%rsp\)
+** movq %r31, 240\(%rsp\)
+**...
+** call \*code\(%rip\)
+** movq \(%rsp\), %rax
+** movq 8\(%rsp\), %rdx
+** movq 16\(%rsp\), %rcx
+** movq 24\(%rsp\), %rbx
+** movq 32\(%rsp\), %rsi
+** movq 40\(%rsp\), %rdi
+** movq 48\(%rsp\), %rbp
+** movq 56\(%rsp\), %r8
+** movq 64\(%rsp\), %r9
+** movq 72\(%rsp\), %r10
+** movq 80\(%rsp\), %r11
+** movq 88\(%rsp\), %r12
+** movq 96\(%rsp\), %r13
+** movq 104\(%rsp\), %r14
+** movq 112\(%rsp\), %r15
+** movq 120\(%rsp\), %r16
+** movq 128\(%rsp\), %r17
+** movq 136\(%rsp\), %r18
+** movq 144\(%rsp\), %r19
+** movq 152\(%rsp\), %r20
+** movq 160\(%rsp\), %r21
+** movq 168\(%rsp\), %r22
+** movq 176\(%rsp\), %r23
+** movq 184\(%rsp\), %r24
+** movq 192\(%rsp\), %r25
+** movq 200\(%rsp\), %r26
+** movq 208\(%rsp\), %r27
+** movq 216\(%rsp\), %r28
+** movq 224\(%rsp\), %r29
+** movq 232\(%rsp\), %r30
+** movq 240\(%rsp\), %r31
+** addq \$248, %rsp
+**...
+** ret
+** .cfi_endproc
+**...
+*/
+
+#define DONT_SAVE_REGS __attribute__((no_callee_saved_registers))
+#define SAVE_REGS __attribute__((no_caller_saved_registers))
+
+typedef DONT_SAVE_REGS void (*op_t)(void);
+
+extern op_t code[];
+
+SAVE_REGS void start()
+{
+ code[0]();
+}
diff --git a/gcc/testsuite/gcc.target/i386/pr119784b.c b/gcc/testsuite/gcc.target/i386/pr119784b.c
new file mode 100644
index 00000000000..c6761976ed6
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr119784b.c
@@ -0,0 +1,87 @@
+/* { dg-do compile { target { *-*-linux* && x32 } } } */
+/* { dg-options "-O2 -fno-pic -mtune=generic -mgeneral-regs-only -mapxf -mtune-ctrl=prologue_using_move,epilogue_using_move" } */
+/* Keep labels and directives ('.cfi_startproc', '.cfi_endproc'). */
+/* { dg-final { check-function-bodies "**" "" "" { target "*-*-*" } {^\t?\.} } } */
+
+/* start must save and restore all caller saved registers. */
+
+/*
+**start:
+**.LFB[0-9]+:
+** .cfi_startproc
+** subl \$248, %esp
+**...
+** movq %rax, \(%rsp\)
+** movq %rdx, 8\(%rsp\)
+** movq %rcx, 16\(%rsp\)
+** movq %rbx, 24\(%rsp\)
+** movq %rsi, 32\(%rsp\)
+** movq %rdi, 40\(%rsp\)
+**...
+** movq %rbp, 48\(%rsp\)
+** movq %r8, 56\(%rsp\)
+** movq %r9, 64\(%rsp\)
+** movq %r10, 72\(%rsp\)
+** movq %r11, 80\(%rsp\)
+** movq %r12, 88\(%rsp\)
+** movq %r13, 96\(%rsp\)
+** movq %r14, 104\(%rsp\)
+** movq %r15, 112\(%rsp\)
+** movq %r16, 120\(%rsp\)
+** movq %r17, 128\(%rsp\)
+** movq %r18, 136\(%rsp\)
+** movq %r19, 144\(%rsp\)
+** movq %r20, 152\(%rsp\)
+** movq %r21, 160\(%rsp\)
+** movq %r22, 168\(%rsp\)
+** movq %r23, 176\(%rsp\)
+** movq %r24, 184\(%rsp\)
+** movq %r25, 192\(%rsp\)
+** movq %r26, 200\(%rsp\)
+** movq %r27, 208\(%rsp\)
+** movq %r28, 216\(%rsp\)
+** movq %r29, 224\(%rsp\)
+** movq %r30, 232\(%rsp\)
+** movq %r31, 240\(%rsp\)
+**...
+** movl code\(%rip\), %ebp
+** call \*%rbp
+** movq \(%rsp\), %rax
+** movq 8\(%rsp\), %rdx
+** movq 16\(%rsp\), %rcx
+** movq 24\(%rsp\), %rbx
+** movq 32\(%rsp\), %rsi
+** movq 40\(%rsp\), %rdi
+** movq 48\(%rsp\), %rbp
+** movq 56\(%rsp\), %r8
+** movq 64\(%rsp\), %r9
+** movq 72\(%rsp\), %r10
+** movq 80\(%rsp\), %r11
+** movq 88\(%rsp\), %r12
+** movq 96\(%rsp\), %r13
+** movq 104\(%rsp\), %r14
+** movq 112\(%rsp\), %r15
+** movq 120\(%rsp\), %r16
+** movq 128\(%rsp\), %r17
+** movq 136\(%rsp\), %r18
+** movq 144\(%rsp\), %r19
+** movq 152\(%rsp\), %r20
+** movq 160\(%rsp\), %r21
+** movq 168\(%rsp\), %r22
+** movq 176\(%rsp\), %r23
+** movq 184\(%rsp\), %r24
+** movq 192\(%rsp\), %r25
+** movq 200\(%rsp\), %r26
+** movq 208\(%rsp\), %r27
+** movq 216\(%rsp\), %r28
+** movq 224\(%rsp\), %r29
+** movq 232\(%rsp\), %r30
+** movq 240\(%rsp\), %r31
+** addl \$248, %esp
+**...
+** ret
+** .cfi_endproc
+**...
+*/
+
+#include "pr119784a.c"
--
2.49.0
