Re: [PATCH v2] lkdtm: Add CFI_BACKWARD to test ROP mitigations

[Kees Cook]

On Fri, Dec 09, 2022 at 05:34:41PM +0000, Kristina Martsenko wrote:
> Subject: [PATCH] lkdtm: cfi: Make PAC test work with GCC 7 and 8
> 
> The CFI test uses the branch-protection=none compiler attribute to
> disable PAC return address protection on a function. While newer GCC
> versions support this attribute, older versions (GCC 7 and 8) instead
> supported the sign-return-address=none attribute, leading to a build
> failure when the test is built with older compilers. Fix it by checking
> which attribute is supported and using the correct one.
> 
> Fixes: 2e53b877dc12 ("lkdtm: Add CFI_BACKWARD to test ROP mitigations")
> Reported-by: Daniel Díaz <daniel.diaz@xxxxxxxxxx>
> Signed-off-by: Kristina Martsenko <kristina.martsenko@xxxxxxx>
> Link: https://lore.kernel.org/all/CAEUSe78kDPxQmQqCWW-_9LCgJDFhAeMoVBFnX9QLx18Z4uT4VQ@xxxxxxxxxxxxxx/

Thanks! Added to my tree.

> ---
>  drivers/misc/lkdtm/cfi.c | 6 +++++-
>  1 file changed, 5 insertions(+), 1 deletion(-)
> 
> diff --git a/drivers/misc/lkdtm/cfi.c b/drivers/misc/lkdtm/cfi.c
> index 5245cf6013c9..d4bb8e31a2fe 100644
> --- a/drivers/misc/lkdtm/cfi.c
> +++ b/drivers/misc/lkdtm/cfi.c
> @@ -54,7 +54,11 @@ static void lkdtm_CFI_FORWARD_PROTO(void)
>  # ifdef CONFIG_ARM64_BTI_KERNEL
>  #  define __no_pac             "branch-protection=bti"
>  # else
> -#  define __no_pac             "branch-protection=none"
> +#  ifdef CONFIG_CC_HAS_BRANCH_PROT_PAC_RET
> +#   define __no_pac             "branch-protection=none"
> +#  else
> +#   define __no_pac             "sign-return-address=none"
> +#  endif
>  # endif
>  # define __no_ret_protection   __noscs __attribute__((__target__(__no_pac)))
>  #else
> 

-- 
Kees Cook