From: Reshetova, Elena
> Sent: 30 April 2019 18:51
...
> I guess this is true, so I did a quick implementation now to estimate the
> performance hits.
> Here are the preliminary numbers (proper ones will take a bit more time):
>
> base: Simple syscall: 0.1761 microseconds
> get_random_bytes (4096 bytes per-cpu buffer): 0.1793 microsecons
> get_random_bytes (64 bytes per-cpu buffer): 0.1866 microsecons
>
> It does not make sense to go less than 64 bytes since this seems to be
> Chacha20 block size, so if we go lower, we will trash useful bits.
> You can go even higher than 4096 bytes, but even this looks like
> okish performance to me.
>
> Below is a snip of what I quickly did (relevant parts) to get these numbers.
> I do initial population of per-cpu buffers in late_initcall, but
> practice shows that rng might not always be in good state by then.
> So, we might not have really good randomness then, but I am not sure
> if this is a practical problem since it only applies to system boot and by
> the time it booted, it already issued enough syscalls that buffer gets
> refilled
> with really good numbers.
> Alternatively we can also do it on the first syscall that each cpu gets, but I
> am not sure if that is always guaranteed to have a good randomness.
...
> +unsigned char random_get_byte(void)
> +{
> + struct rnd_buffer *buffer = &get_cpu_var(stack_rand_offset);
> + unsigned char res;
> +
> + if (buffer->byte_counter >= RANDOM_BUFFER_SIZE) {
> + get_random_bytes(&(buffer->buffer), sizeof(buffer->buffer));
> + buffer->byte_counter = 0;
> + }
> +
> + res = buffer->buffer[buffer->byte_counter];
> + buffer->buffer[buffer->byte_counter] = 0;
> + buffer->byte_counter ++;
> + put_cpu_var(stack_rand_offset);
> + return res;
> +}
> +EXPORT_SYMBOL(random_get_byte);
You'll almost certainly get better code if you copy buffer->byte_counter
to a local 'unsigned long' variable.
David
-
Registered Address Lakeside, Bramley Road, Mount Farm, Milton Keynes, MK1 1PT,
UK
Registration No: 1397386 (Wales)
