Re: [PATCH] x86/retpoline: Avoid return buffer underflows on context switch

[Paul Turner]

On Mon, Jan 8, 2018 at 2:11 PM, Peter Zijlstra <peterz@xxxxxxxxxxxxx> wrote:
> On Mon, Jan 08, 2018 at 12:15:31PM -0800, Andi Kleen wrote:
>> diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
>> index b8c8eeacb4be..e84e231248c2 100644
>> --- a/arch/x86/include/asm/nospec-branch.h
>> +++ b/arch/x86/include/asm/nospec-branch.h
>> @@ -53,6 +53,35 @@
>>  #endif
>>  .endm
>>
>> +/*
>> + * We use 32-N: 32 is the max return buffer size,
>> + * but there should have been at a minimum two
>> + * controlled calls already: one into the kernel
>> + * from entry*.S and another into the function
>> + * containing this macro. So N=2, thus 30.
>> + */
>> +#define NUM_BRANCHES_TO_FILL 30
>> +
>> +/*
>> + * Fill the CPU return branch buffer to prevent
>> + * indirect branch prediction on underflow.
>> + * Caller should check for X86_FEATURE_SMEP and X86_FEATURE_RETPOLINE
>> + */
>> +.macro FILL_RETURN_BUFFER
>> +#ifdef CONFIG_RETPOLINE
>> +     .rept   NUM_BRANCHES_TO_FILL
>> +     call    1221f
>> +     pause   /* stop speculation */
>> +1221:
>> +     .endr
>> +#ifdef CONFIG_64BIT
>> +     addq    $8*NUM_BRANCHES_TO_FILL, %rsp
>> +#else
>> +     addl    $4*NUM_BRANCHES_TO_FILL, %esp
>> +#endif
>> +#endif
>> +.endm
>
> So pjt did alignment, a single unroll and per discussion earlier today
> (CET) or late last night (PST), he only does 16.
>
> Why is none of that done here? Also, can we pretty please stop using
> those retarded number labels, they make this stuff unreadable.
>
> Also, pause is unlikely to stop speculation, that comment doesn't make
> sense. Looking at PJT's version there used to be a speculation trap in
> there, but I can't see that here.
>

You definitely want the speculation traps.. these entries are
potentially consumed.
Worse: The first entry that will be consumed is the last call in your
linear chain, meaning that it immediately gets to escape into
alternative execution.
(When I was experimenting with icache-minimizing constructions here I
actually used intentional backwards jumps in linear chains to avoid
this.)

The sequence I reported is what ended up seeming optimal.

>