RE: [RFC PATCH v2 3/8] tools/nolibc: i386: Implement syscall with 6 arguments

[David Laight]

From: Ammar Faizi
> Sent: 22 March 2022 10:21
> 
> On i386, the 6th argument of syscall goes in %ebp. However, both Clang
> and GCC cannot use %ebp in the clobber list and in the "r" constraint
> without using -fomit-frame-pointer. To make it always available for
> any kind of compilation, the below workaround is implemented.
> 
> For clang (the Assembly statement can't clobber %ebp):
>   1) Push the 6-th argument.
>   2) Push %ebp.
>   3) Load the 6-th argument from 4(%esp) to %ebp.
>   4) Do the syscall (int $0x80).
>   5) Pop %ebp (restore the old value of %ebp).
>   6) Add %esp by 4 (undo the stack pointer).
> 
> For GCC, fortunately it has a #pragma that can force a specific function
> to be compiled with -fomit-frame-pointer, so it can use "r"(var) where
> var is a variable bound to %ebp.

You need to use the 'clang' pattern for gcc.
#pragma optimise is fundamentally broken.
What actually happens here is the 'inline' gets lost
(because of the implied -O0) and you get far worse code
than you might expect.

Since you need the 'clang' version, use it all the time.

	David

> 
> Cc: x86@xxxxxxxxxx
> Cc: llvm@xxxxxxxxxxxxxxx
> Link: https://lore.kernel.org/lkml/2e335ac54db44f1d8496583d97f9dab0@xxxxxxxxxxxxxxxx
> Suggested-by: David Laight <David.Laight@xxxxxxxxxx>
> Signed-off-by: Ammar Faizi <ammarfaizi2@xxxxxxxxxxx>
> ---
> 
> @@ Changelog:
> 
>    Link RFC v1: https://lore.kernel.org/llvm/20220320093750.159991-4-ammarfaizi2@xxxxxxxxxxx
>    RFC v1 -> RFC v2:
>     - Fix %ebp saving method. Don't use redzone, i386 doesn't have a redzone
>       (comment from David and Alviro).
> ---
>  tools/include/nolibc/arch-i386.h | 66 ++++++++++++++++++++++++++++++++
>  1 file changed, 66 insertions(+)
> 
> diff --git a/tools/include/nolibc/arch-i386.h b/tools/include/nolibc/arch-i386.h
> index 125a691fc631..9f4dc36e6ac2 100644
> --- a/tools/include/nolibc/arch-i386.h
> +++ b/tools/include/nolibc/arch-i386.h
> @@ -167,6 +167,72 @@ struct sys_stat_struct {
>  	_ret;                                                                 \
>  })
> 
> +
> +/*
> + * Both Clang and GCC cannot use %ebp in the clobber list and in the "r"
> + * constraint without using -fomit-frame-pointer. To make it always
> + * available for any kind of compilation, the below workaround is
> + * implemented.
> + *
> + * For clang (the Assembly statement can't clobber %ebp):
> + *   1) Push the 6-th argument.
> + *   2) Push %ebp.
> + *   3) Load the 6-th argument from 4(%esp) to %ebp.
> + *   4) Do the syscall (int $0x80).
> + *   5) Pop %ebp (restore the old value of %ebp).
> + *   6) Add %esp by 4 (undo the stack pointer).
> + *
> + * For GCC, fortunately it has a #pragma that can force a specific function
> + * to be compiled with -fomit-frame-pointer, so it can use "r"(var) where
> + * var is a variable bound to %ebp.
> + *
> + */
> +#if defined(__clang__)
> +static inline long ____do_syscall6(long eax, long ebx, long ecx, long edx,
> +				   long esi, long edi, long ebp)
> +{
> +	__asm__ volatile (
> +		"pushl	%[arg6]\n\t"
> +		"pushl	%%ebp\n\t"
> +		"movl	4(%%esp), %%ebp\n\t"
> +		"int	$0x80\n\t"
> +		"popl	%%ebp\n\t"
> +		"addl	$4,%%esp\n\t"
> +		: "=a"(eax)
> +		: "a"(eax), "b"(ebx), "c"(ecx), "d"(edx), "S"(esi), "D"(edi),
> +		  [arg6]"m"(ebp)
> +		: "memory", "cc"
> +	);
> +	return eax;
> +}
> +
> +#else /* #if defined(__clang__) */
> +#pragma GCC push_options
> +#pragma GCC optimize "-fomit-frame-pointer"
> +static long ____do_syscall6(long eax, long ebx, long ecx, long edx, long esi,
> +			    long edi, long ebp)
> +{
> +	register long __ebp __asm__("ebp") = ebp;
> +	__asm__ volatile (
> +		"int	$0x80"
> +		: "=a"(eax)
> +		: "a"(eax), "b"(ebx), "c"(ecx), "d"(edx), "S"(esi), "D"(edi),
> +		  "r"(__ebp)
> +		: "memory", "cc"
> +	);
> +	return eax;
> +}
> +#pragma GCC pop_options
> +#endif /* #if defined(__clang__) */
> +
> +#define my_syscall6(num, arg1, arg2, arg3, arg4, arg5, arg6) (   \
> +	____do_syscall6((long)(num), (long)(arg1),               \
> +			(long)(arg2), (long)(arg3),              \
> +			(long)(arg4), (long)(arg5),              \
> +			(long)(arg6))                            \
> +)
> +
> +
>  /* startup code */
>  /*
>   * i386 System V ABI mandates:
> --
> Ammar Faizi

-
Registered Address Lakeside, Bramley Road, Mount Farm, Milton Keynes, MK1 1PT, UK
Registration No: 1397386 (Wales)