[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <Y6oHjrLCbDzWh7nE@kernel.org>
Date: Mon, 26 Dec 2022 20:43:58 +0000
From: Jarkko Sakkinen <jarkko@...nel.org>
To: Sean Christopherson <seanjc@...gle.com>
Cc: Dave Hansen <dave.hansen@...el.com>,
Kristen Carlson Accardi <kristen@...ux.intel.com>,
dave.hansen@...ux.intel.com, tj@...nel.org,
linux-kernel@...r.kernel.org, linux-sgx@...r.kernel.org,
cgroups@...r.kernel.org, Thomas Gleixner <tglx@...utronix.de>,
Ingo Molnar <mingo@...hat.com>, Borislav Petkov <bp@...en8.de>,
x86@...nel.org, "H. Peter Anvin" <hpa@...or.com>,
zhiquan1.li@...el.com
Subject: Re: [PATCH v2 14/18] x86/sgx: Add EPC OOM path to forcefully reclaim
EPC
On Mon, Dec 12, 2022 at 06:09:39PM +0000, Sean Christopherson wrote:
> On Fri, Dec 09, 2022, Dave Hansen wrote:
> > On 12/9/22 08:05, Kristen Carlson Accardi wrote:
> > > Aside from that though, I don't think that killing enclaves makes sense
> > > outside the context of cgroup limits.
> >
> > I think it makes a lot of sense in theory. Whatever situation we get
> > into with a cgroup's EPC we can also get into with the whole system's EPC.
> >
> > *But*, it's orders of magnitude harder to hit on the whole system.
>
> ...
>
> > If someone wants to extend this OOM support to system-wide EPC later, then go
> > ahead. But, I don't think it makes a lot of sense to invert this series for
> > it.
>
> +1 from the peanut gallery. With VMM EPC oversubscription suport, no sane VMM
> will oversubscribe VEPC pages. And for VA pages, supporting swap of VA pages is
> likely a more userspace-friendly approach if system-wide EPC OOM is a concern.
When swapping VA pages the topology of the VA page cache for swapped VA
pages is the main question. It is compromise between how long swap-in and
swap-out can take, and how generic solution it be, meaning how deep
hierarchies you want to build, or is just a flat list of parent VA pages
"good enough".
Also, there's the question whether it should be a global cache, per cgroup
and so forth.
Implementing any solution is not overly complicated. Locking in these
options is what puzzles me.
BR, Jarkko
Powered by blists - more mailing lists