linux-kernel - Re: [v3 2/3] mm: Defer TLB flush by keeping both src and dst folios at migration

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]

Date:   Thu, 9 Nov 2023 14:35:44 +0900
From:   Byungchul Park <byungchul@...com>
To:     Nadav Amit <namit@...are.com>
Cc:     Linux Kernel Mailing List <linux-kernel@...r.kernel.org>,
        linux-mm <linux-mm@...ck.org>,
        "kernel_team@...ynix.com" <kernel_team@...ynix.com>,
        Andrew Morton <akpm@...ux-foundation.org>,
        "ying.huang@...el.com" <ying.huang@...el.com>,
        "xhao@...ux.alibaba.com" <xhao@...ux.alibaba.com>,
        "mgorman@...hsingularity.net" <mgorman@...hsingularity.net>,
        "hughd@...gle.com" <hughd@...gle.com>,
        "willy@...radead.org" <willy@...radead.org>,
        "david@...hat.com" <david@...hat.com>,
        "peterz@...radead.org" <peterz@...radead.org>,
        Andy Lutomirski <luto@...nel.org>,
        Thomas Gleixner <tglx@...utronix.de>,
        "mingo@...hat.com" <mingo@...hat.com>,
        "bp@...en8.de" <bp@...en8.de>,
        "dave.hansen@...ux.intel.com" <dave.hansen@...ux.intel.com>
Subject: Re: [v3 2/3] mm: Defer TLB flush by keeping both src and dst folios
 at migration

On Mon, Oct 30, 2023 at 09:51:30PM +0900, Byungchul Park wrote:
> On Mon, Oct 30, 2023 at 08:50:20AM +0000, Nadav Amit wrote:
> > I do not follow the ordering that ensures a migrated page would not
> > become writable before the migration is over. Perhaps a comment on what
> > guarantees the order would help.

IIUC, it'd be safe because unmap is performed first at the beginning of
each migration so as to be safe with page fault handlers. So I don't
think it should be a concern. Or am I missing something?

	Byungchul