tools/nolibc: fix up startup failures for -O0 under gcc < 11.1.0

As gcc doc [1] shows:

  Most optimizations are completely disabled at -O0 or if an -O level is
  not set on the command line, even if individual optimization flags are
  specified.

Test result [2] shows, gcc>=11.1.0 deviates from the above description,
but before gcc 11.1.0, "-O0" still forcely uses frame pointer in the
_start function even if the individual optimize("omit-frame-pointer")
flag is specified.

The frame pointer related operations will change the stack pointer (e.g.
In x86_64, an extra "push %rbp" will be inserted at the beginning of
_start) and make it differs from the one we expected, as a result, break
the whole startup function.

To fix up this issue, as suggested by Thomas, the individual "Os" and
"omit-frame-pointer" optimize flags are used together on _start function
to disable frame pointer completely even if the -O0 is set on the
command line.

[1]: https://gcc.gnu.org/onlinedocs/gcc/Optimize-Options.html
[2]: https://lore.kernel.org/lkml/20230714094723.140603-1-falcon@tinylab.org/

Suggested-by: Thomas Weißschuh <linux@weissschuh.net>
Link: https://lore.kernel.org/lkml/34b21ba5-7b59-4b3b-9ed6-ef9a3a5e06f7@t-8ch.de/
Fixes: 7f8548589661 ("tools/nolibc: make compiler and assembler agree on the section around _start")
Signed-off-by: Zhangjin Wu <falcon@tinylab.org>
Signed-off-by: Willy Tarreau <w@1wt.eu>

8 files changed, 8 insertions, 8 deletions

diff --git a/tools/include/nolibc/arch-aarch64.h b/tools/include/nolibc/arch-aarch64.h
index 6151be6cd7a9..21e9482a4235 100644
--- a/tools/include/nolibc/arch-aarch64.h
+++ b/tools/include/nolibc/arch-aarch64.h
@@ -175,7 +175,7 @@ char **environ __attribute__((weak));
 const unsigned long *_auxv __attribute__((weak));
 
 /* startup code */
-void __attribute__((weak, noreturn, optimize("omit-frame-pointer"))) __no_stack_protector _start(void)
+void __attribute__((weak, noreturn, optimize("Os", "omit-frame-pointer"))) __no_stack_protector _start(void)
 {
 	__asm__ volatile (
 #ifdef _NOLIBC_STACKPROTECTOR
diff --git a/tools/include/nolibc/arch-arm.h b/tools/include/nolibc/arch-arm.h
index 5b12b6e1c83e..4451bef5f94d 100644
--- a/tools/include/nolibc/arch-arm.h
+++ b/tools/include/nolibc/arch-arm.h
@@ -225,7 +225,7 @@ char **environ __attribute__((weak));
 const unsigned long *_auxv __attribute__((weak));
 
 /* startup code */
-void __attribute__((weak, noreturn, optimize("omit-frame-pointer"))) __no_stack_protector _start(void)
+void __attribute__((weak, noreturn, optimize("Os", "omit-frame-pointer"))) __no_stack_protector _start(void)
 {
 	__asm__ volatile (
 #ifdef _NOLIBC_STACKPROTECTOR
diff --git a/tools/include/nolibc/arch-i386.h b/tools/include/nolibc/arch-i386.h
index 35680b4a25d4..4c94a81e860f 100644
--- a/tools/include/nolibc/arch-i386.h
+++ b/tools/include/nolibc/arch-i386.h
@@ -190,7 +190,7 @@ const unsigned long *_auxv __attribute__((weak));
  * 2) The deepest stack frame should be set to zero
  *
  */
-void __attribute__((weak, noreturn, optimize("omit-frame-pointer"))) __no_stack_protector _start(void)
+void __attribute__((weak, noreturn, optimize("Os", "omit-frame-pointer"))) __no_stack_protector _start(void)
 {
 	__asm__ volatile (
 #ifdef _NOLIBC_STACKPROTECTOR
diff --git a/tools/include/nolibc/arch-loongarch.h b/tools/include/nolibc/arch-loongarch.h
index ada5a69e3fcc..590155a4e543 100644
--- a/tools/include/nolibc/arch-loongarch.h
+++ b/tools/include/nolibc/arch-loongarch.h
@@ -167,7 +167,7 @@ const unsigned long *_auxv __attribute__((weak));
 #endif
 
 /* startup code */
-void __attribute__((weak, noreturn, optimize("omit-frame-pointer"))) __no_stack_protector _start(void)
+void __attribute__((weak, noreturn, optimize("Os", "omit-frame-pointer"))) __no_stack_protector _start(void)
 {
 	__asm__ volatile (
 #ifdef _NOLIBC_STACKPROTECTOR
diff --git a/tools/include/nolibc/arch-mips.h b/tools/include/nolibc/arch-mips.h
index dd0f12131b55..d3f0bf4c4245 100644
--- a/tools/include/nolibc/arch-mips.h
+++ b/tools/include/nolibc/arch-mips.h
@@ -205,7 +205,7 @@ char **environ __attribute__((weak));
 const unsigned long *_auxv __attribute__((weak));
 
 /* startup code, note that it's called __start on MIPS */
-void __attribute__((weak, noreturn, optimize("omit-frame-pointer"))) __no_stack_protector __start(void)
+void __attribute__((weak, noreturn, optimize("Os", "omit-frame-pointer"))) __no_stack_protector __start(void)
 {
 	__asm__ volatile (
 		/*".set nomips16\n"*/
diff --git a/tools/include/nolibc/arch-riscv.h b/tools/include/nolibc/arch-riscv.h
index 1dd7083c2ac8..322c96f4acdb 100644
--- a/tools/include/nolibc/arch-riscv.h
+++ b/tools/include/nolibc/arch-riscv.h
@@ -180,7 +180,7 @@ char **environ __attribute__((weak));
 const unsigned long *_auxv __attribute__((weak));
 
 /* startup code */
-void __attribute__((weak, noreturn, optimize("omit-frame-pointer"))) __no_stack_protector _start(void)
+void __attribute__((weak, noreturn, optimize("Os", "omit-frame-pointer"))) __no_stack_protector _start(void)
 {
 	__asm__ volatile (
 		".option push\n"
diff --git a/tools/include/nolibc/arch-s390.h b/tools/include/nolibc/arch-s390.h
index 8254caff8bfa..587cc91295fa 100644
--- a/tools/include/nolibc/arch-s390.h
+++ b/tools/include/nolibc/arch-s390.h
@@ -166,7 +166,7 @@ char **environ __attribute__((weak));
 const unsigned long *_auxv __attribute__((weak));
 
 /* startup code */
-void __attribute__((weak, noreturn, optimize("omit-frame-pointer"))) __no_stack_protector _start(void)
+void __attribute__((weak, noreturn, optimize("Os", "omit-frame-pointer"))) __no_stack_protector _start(void)
 {
 	__asm__ volatile (
 		"lg	%r2,0(%r15)\n"		/* argument count */
diff --git a/tools/include/nolibc/arch-x86_64.h b/tools/include/nolibc/arch-x86_64.h
index fb00ab2e9274..5e950a04bc77 100644
--- a/tools/include/nolibc/arch-x86_64.h
+++ b/tools/include/nolibc/arch-x86_64.h
@@ -190,7 +190,7 @@ const unsigned long *_auxv __attribute__((weak));
  * 2) The deepest stack frame should be zero (the %rbp).
  *
  */
-void __attribute__((weak, noreturn, optimize("omit-frame-pointer"))) __no_stack_protector _start(void)
+void __attribute__((weak, noreturn, optimize("Os", "omit-frame-pointer"))) __no_stack_protector _start(void)
 {
 	__asm__ volatile (
 #ifdef _NOLIBC_STACKPROTECTOR