linux-kernel - Re: [PATCH] x86: sgx: Don't track poisoned pages for reclaiming

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <294b456a-e43f-4f89-a643-8f45496ed6ed@intel.com>
Date: Tue, 11 Feb 2025 16:37:25 -0800
From: Dave Hansen <dave.hansen@...el.com>
To: andrzej zaborowski <balrogg@...il.com>
Cc: "Huang, Kai" <kai.huang@...el.com>, Jarkko Sakkinen <jarkko@...nel.org>,
 x86@...nel.org, linux-sgx@...r.kernel.org, linux-kernel@...r.kernel.org,
 Dave Hansen <dave.hansen@...ux.intel.com>, Tony Luck <tony.luck@...el.com>,
 Thomas Gleixner <tglx@...utronix.de>, Borislav Petkov <bp@...en8.de>,
 Ingo Molnar <mingo@...hat.com>, "H . Peter Anvin" <hpa@...or.com>
Subject: Re: [PATCH] x86: sgx: Don't track poisoned pages for reclaiming

On 2/11/25 16:32, andrzej zaborowski wrote:
>> Actually, now that I think about it even more, why would ETRACK or
>> EBLOCK access the page itself? They seem superficially like they'd be
>> metadata-only too.
> I haven't seen a crash in either of these (always in EWB), I didn't
> want to imply that.  But starting that sequence seems wrong knowing we
> cannot reclaim the page.

That's kinda another reason not to delve into the details too deeply. I
think you wanted to talk about the "writeback process" as a thing and
not really about "ETRACK, EBLOCK and EWB" per se.

Writing back an SGX page is the problem. The names of the three
instructions that implement the writeback or that there _are_ even three
of them isn't super relevant.