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

From: Ingo Molnar
Date: Thu May 02 2019 - 12:45:52 EST

* David Laight <David.Laight@xxxxxxxxxx> wrote:

> It has already been measured - it is far too slow.

I don't think proper buffering was tested, was it? Only a per syscall
RDRAND overhead which I can imagine being not too good.

> > Because calling tens of millions of system calls per second will
> > deplete any non-CPU-RNG sources of entropy and will also starve all
> > other users of random numbers, which might have a more legitimate
> > need for randomness, such as the networking stack ...
> If the function you use to generate random numbers from the 'entropy
> pool' isn't reversible (in a finite time) I don't think you really need
> to worry about bits-in v bits-out.