Re: [PATCH] x86/entry/64: randomize kernel stack offset upon syscall

From: Andy Lutomirski
Date: Fri May 03 2019 - 12:41:13 EST



> On May 2, 2019, at 9:43 AM, Ingo Molnar <mingo@xxxxxxxxxx> wrote:
>
>
> * Andy Lutomirski <luto@xxxxxxxxxx> wrote:
>
>>> 8 gigabits/sec sounds good throughput in principle, if there's no
>>> scalability pathologies with that.
>>
>> The latency is horrible.
>
> Latency would be amortized via batching anyway, so 8 gigabits/sec
> suggests something on the order of magnitude of 4 bits per cycle, right?
> With 64 bits extraction at a time that would be 16 cycles per 64-bit
> word, which isn't too bad, is it?

I havenât really dug in, but some Googling suggests that the 8Gbps figure is what you get with all cores doing RDRAND. It sounds like the actual RDRAND instruction doesnât pipeline.

> Making it "optional" is not really a technical argument in any way
> though, either distros enable it in which case it's a de-facto default
> setting, or they don't, in which case it de-facto almost doesn't exist.
>
>

True.