Re: [PATCH v4 1/3] kallsyms: Avoid weak references for kallsyms symbols

[Masahiro Yamada]

On Tue, Apr 16, 2024 at 1:20 AM Ard Biesheuvel <ardb+git@xxxxxxxxxx> wrote:
>
> From: Ard Biesheuvel <ardb@xxxxxxxxxx>
>
> kallsyms is a directory of all the symbols in the vmlinux binary, and so
> creating it is somewhat of a chicken-and-egg problem, as its non-zero
> size affects the layout of the binary, and therefore the values of the
> symbols.
>
> For this reason, the kernel is linked more than once, and the first pass
> does not include any kallsyms data at all. For the linker to accept
> this, the symbol declarations describing the kallsyms metadata are
> emitted as having weak linkage, so they can remain unsatisfied. During
> the subsequent passes, the weak references are satisfied by the kallsyms
> metadata that was constructed based on information gathered from the
> preceding passes.
>
> Weak references lead to somewhat worse codegen, because taking their
> address may need to produce NULL (if the reference was unsatisfied), and
> this is not usually supported by RIP or PC relative symbol references.
>
> Given that these references are ultimately always satisfied in the final
> link, let's drop the weak annotation, and instead, provide fallback
> definitions in the linker script that are only emitted if an unsatisfied
> reference exists.
>
> While at it, drop the FRV specific annotation that these symbols reside
> in .rodata - FRV is long gone.
>
> Tested-by: Nick Desaulniers <ndesaulniers@xxxxxxxxxx> # Boot
> Reviewed-by: Nick Desaulniers <ndesaulniers@xxxxxxxxxx>
> Reviewed-by: Kees Cook <keescook@xxxxxxxxxxxx>
> Acked-by: Arnd Bergmann <arnd@xxxxxxxx>
> Link: https://lkml.kernel.org/r/20230504174320.3930345-1-ardb%40kernel.org
> Signed-off-by: Ard Biesheuvel <ardb@xxxxxxxxxx>
> ---


I dropped v5, and picked up this one.

Thanks.



>  include/asm-generic/vmlinux.lds.h | 19 +++++++++++++
>  kernel/kallsyms.c                 |  6 ----
>  kernel/kallsyms_internal.h        | 30 ++++++++------------
>  3 files changed, 31 insertions(+), 24 deletions(-)
>
> diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
> index f7749d0f2562..e8449be62058 100644
> --- a/include/asm-generic/vmlinux.lds.h
> +++ b/include/asm-generic/vmlinux.lds.h
> @@ -448,11 +448,30 @@
>  #endif
>  #endif
>
> +/*
> + * Some symbol definitions will not exist yet during the first pass of the
> + * link, but are guaranteed to exist in the final link. Provide preliminary
> + * definitions that will be superseded in the final link to avoid having to
> + * rely on weak external linkage, which requires a GOT when used in position
> + * independent code.
> + */
> +#define PRELIMINARY_SYMBOL_DEFINITIONS                                 \
> +       PROVIDE(kallsyms_addresses = .);                                \
> +       PROVIDE(kallsyms_offsets = .);                                  \
> +       PROVIDE(kallsyms_names = .);                                    \
> +       PROVIDE(kallsyms_num_syms = .);                                 \
> +       PROVIDE(kallsyms_relative_base = .);                            \
> +       PROVIDE(kallsyms_token_table = .);                              \
> +       PROVIDE(kallsyms_token_index = .);                              \
> +       PROVIDE(kallsyms_markers = .);                                  \
> +       PROVIDE(kallsyms_seqs_of_names = .);
> +
>  /*
>   * Read only Data
>   */
>  #define RO_DATA(align)                                                 \
>         . = ALIGN((align));                                             \
> +       PRELIMINARY_SYMBOL_DEFINITIONS                                  \
>         .rodata           : AT(ADDR(.rodata) - LOAD_OFFSET) {           \
>                 __start_rodata = .;                                     \
>                 *(.rodata) *(.rodata.*)                                 \
> diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c
> index 18edd57b5fe8..22ea19a36e6e 100644
> --- a/kernel/kallsyms.c
> +++ b/kernel/kallsyms.c
> @@ -325,12 +325,6 @@ static unsigned long get_symbol_pos(unsigned long addr,
>         unsigned long symbol_start = 0, symbol_end = 0;
>         unsigned long i, low, high, mid;
>
> -       /* This kernel should never had been booted. */
> -       if (!IS_ENABLED(CONFIG_KALLSYMS_BASE_RELATIVE))
> -               BUG_ON(!kallsyms_addresses);
> -       else
> -               BUG_ON(!kallsyms_offsets);
> -
>         /* Do a binary search on the sorted kallsyms_addresses array. */
>         low = 0;
>         high = kallsyms_num_syms;
> diff --git a/kernel/kallsyms_internal.h b/kernel/kallsyms_internal.h
> index 27fabdcc40f5..85480274fc8f 100644
> --- a/kernel/kallsyms_internal.h
> +++ b/kernel/kallsyms_internal.h
> @@ -5,27 +5,21 @@
>  #include <linux/types.h>
>
>  /*
> - * These will be re-linked against their real values
> - * during the second link stage.
> + * These will be re-linked against their real values during the second link
> + * stage. Preliminary values must be provided in the linker script using the
> + * PROVIDE() directive so that the first link stage can complete successfully.
>   */
> -extern const unsigned long kallsyms_addresses[] __weak;
> -extern const int kallsyms_offsets[] __weak;
> -extern const u8 kallsyms_names[] __weak;
> +extern const unsigned long kallsyms_addresses[];
> +extern const int kallsyms_offsets[];
> +extern const u8 kallsyms_names[];
>
> -/*
> - * Tell the compiler that the count isn't in the small data section if the arch
> - * has one (eg: FRV).
> - */
> -extern const unsigned int kallsyms_num_syms
> -__section(".rodata") __attribute__((weak));
> -
> -extern const unsigned long kallsyms_relative_base
> -__section(".rodata") __attribute__((weak));
> +extern const unsigned int kallsyms_num_syms;
> +extern const unsigned long kallsyms_relative_base;
>
> -extern const char kallsyms_token_table[] __weak;
> -extern const u16 kallsyms_token_index[] __weak;
> +extern const char kallsyms_token_table[];
> +extern const u16 kallsyms_token_index[];
>
> -extern const unsigned int kallsyms_markers[] __weak;
> -extern const u8 kallsyms_seqs_of_names[] __weak;
> +extern const unsigned int kallsyms_markers[];
> +extern const u8 kallsyms_seqs_of_names[];
>
>  #endif // LINUX_KALLSYMS_INTERNAL_H_
> --
> 2.44.0.683.g7961c838ac-goog
>
>


-- 
Best Regards
Masahiro Yamada