Re: [PATCH RFC 2/4] x86/arch_prctl: add ARCH_GET_NOPTI and ARCH_SET_NOPTI to enable/disable PTI

[Willy Tarreau <w@1wt.eu>]

On Mon, Jan 08, 2018 at 09:54:05AM -0800, Linus Torvalds wrote:
> On Mon, Jan 8, 2018 at 8:12 AM, Willy Tarreau <w@1wt.eu> wrote:
> > This allows to report the current state of the PTI protection and to
> > enable or disable it for the current task.
> 
> So I really think that this needs to be done up-front to avoid a lot
> of complexity. And per mm.
> 
> If the process is already threaded (so the mm has multiple users),
> it's too late to start playing games with PTI.
> 
> In fact, maybe the whole thing needs to be controlled before "exec"
> happens, so that we have the knowledge as we build up the mm, rather
> than being "runtime" dynamic at all.

In fact I initially wanted to start with a prctl() flag that acts upon
exec because it looked simpler. But then I realized that this would
always require a wrapper and that it's not necessarily more convenient.
It even makes permission checks more complicated from an administration
perspective, and I'd hate to see such a wrapper ending up setuid...

> But in no case should you even try to handle the multi-threaded case -
> just error out for trying to change the PTI setting.

I totally agree here. Like Ingo says, there *may* be useful cases for
this but I'm not sure we're prepared to address a new class of bugs
caused by this yet. And now I can get rid of GET_NOPTI, it was just for
debugging.

> So make the thing per-mm, and then at task switch time as you switch
> mms, you set the bit in a percpu variable for testing at kernel entry.

I'll see how to do that, this is not yet 100% clear to me, I'm still
discovering (this code has immensely changed since last time I *really*
dug into it). So I suspect I'll have to set this variable in
__switch_to() based on this other MM flag.

I'll study this.

Thanks,
Willy