[PATCH] arm64: jump labels: NOP out NOP -> NOP replacement

[Jiang Liu]

Reviewed-by: Jiang Liu <liuj97 at gmail.com>

> 在 2014年11月26日，上午3:04，Mark Rutland <mark.rutland at arm.com> 写道：
> 
> In the arm64 arch_static_branch implementation we place an A64 NOP into
> the instruction stream and log relevant details to a jump_entry in a
> __jump_table section. Later this may be replaced with an immediate
> branch without link to the code for the unlikely case.
> 
> At init time, the core calls arch_jump_label_transform_static to
> initialise the NOPs. On x86 this involves inserting the optimal NOP for
> a given microarchitecture, but on arm64 we only use the architectural
> NOP, and hence replace each NOP with the exact same NOP. This is
> somewhat pointless.
> 
> Additionally, at module load time we don't call jump_label_apply_nops to
> patch the optimal NOPs in, unlike other architectures, but get away with
> this because we only use the architectural NOP anyway. A later notifier
> will patch NOPs with branches as required.
> 
> Similarly to x86 commit 11570da1c5b1dee1 (x86/jump-label: Do not bother
> updating NOPs if they are correct), we can avoid patching NOPs with
> identical NOPs. Given that we only use a single NOP encoding, this means
> we can NOP-out the body of arch_jump_label_transform_static entirely. As
> the default __weak arch_jump_label_transform_static implementation
> performs a patch, we must use an empty function to achieve this.
> 
> Signed-off-by: Mark Rutland <mark.rutland at arm.com>
> Cc: Catalin Marinas <catalin.marinas at arm.com>
> Cc: Jiang Liu <liuj97 at gmail.com>
> Cc: Laura Abbott <lauraa at codeaurora.org>
> Cc: Will Deacon <will.deacon at arm.com>
> ---
> arch/arm64/kernel/jump_label.c | 23 +++++++++--------------
> 1 file changed, 9 insertions(+), 14 deletions(-)
> 
> diff --git a/arch/arm64/kernel/jump_label.c b/arch/arm64/kernel/jump_label.c
> index 9ac30bb..4f1fec7 100644
> --- a/arch/arm64/kernel/jump_label.c
> +++ b/arch/arm64/kernel/jump_label.c
> @@ -22,9 +22,8 @@
> 
> #ifdef HAVE_JUMP_LABEL
> 
> -static void __arch_jump_label_transform(struct jump_entry *entry,
> -                    enum jump_label_type type,
> -                    bool is_static)
> +void arch_jump_label_transform(struct jump_entry *entry,
> +                   enum jump_label_type type)
> {
>    void *addr = (void *)entry->code;
>    u32 insn;
> @@ -37,22 +36,18 @@ static void __arch_jump_label_transform(struct jump_entry *entry,
>        insn = aarch64_insn_gen_nop();
>    }
> 
> -    if (is_static)
> -        __aarch64_insn_patch_text_nosync(addr, insn, true);
> -    else
> -        aarch64_insn_patch_text(&addr, &insn, 1);
> -}
> -
> -void arch_jump_label_transform(struct jump_entry *entry,
> -                   enum jump_label_type type)
> -{
> -    __arch_jump_label_transform(entry, type, false);
> +    aarch64_insn_patch_text(&addr, &insn, 1);
> }
> 
> void arch_jump_label_transform_static(struct jump_entry *entry,
>                      enum jump_label_type type)
> {
> -    __arch_jump_label_transform(entry, type, true);
> +    /*
> +     * We use the architected A64 NOP in arch_static_branch, so there's no
> +     * need to patch an identical A64 NOP over the top of it here. The core
> +     * will call arch_jump_label_transform from a module notifier if the
> +     * NOP needs to be replaced by a branch.
> +     */
> }
> 
> #endif    /* HAVE_JUMP_LABEL */
> -- 
> 1.9.1
>