linux-kernel - Re: [RFC PATCH 0/10] Another Approach to Use PMEM as NUMA Node

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: <20190326121902.00004f10@huawei.com>
Date:   Tue, 26 Mar 2019 12:19:02 +0000
From:   Jonathan Cameron <jonathan.cameron@...wei.com>
To:     Dan Williams <dan.j.williams@...el.com>
CC:     Brice Goglin <Brice.Goglin@...ia.fr>,
        Yang Shi <yang.shi@...ux.alibaba.com>,
        Michal Hocko <mhocko@...e.com>,
        Mel Gorman <mgorman@...hsingularity.net>,
        Rik van Riel <riel@...riel.com>,
        "Johannes Weiner" <hannes@...xchg.org>,
        Andrew Morton <akpm@...ux-foundation.org>,
        "Dave Hansen" <dave.hansen@...el.com>,
        Keith Busch <keith.busch@...el.com>,
        Fengguang Wu <fengguang.wu@...el.com>,
        "Du, Fan" <fan.du@...el.com>, "Huang, Ying" <ying.huang@...el.com>,
        Linux MM <linux-mm@...ck.org>,
        "Linux Kernel Mailing List" <linux-kernel@...r.kernel.org>
Subject: Re: [RFC PATCH 0/10] Another Approach to Use PMEM as NUMA Node

On Mon, 25 Mar 2019 16:37:07 -0700
Dan Williams <dan.j.williams@...el.com> wrote:

> On Mon, Mar 25, 2019 at 4:09 PM Brice Goglin <Brice.Goglin@...ia.fr> wrote:
> >
> >
> > Le 25/03/2019 à 20:29, Dan Williams a écrit :  
> > > Perhaps "path" might be a suitable replacement identifier rather than
> > > type. I.e. memory that originates from an ACPI.NFIT root device is
> > > likely "pmem".  
> >
> >
> > Could work.
> >
> > What kind of "path" would we get for other types of memory? (DDR,
> > non-ACPI-based based PMEM if any, NVMe PMR?)  
> 
> I think for memory that is described by the HMAT "Reservation hint",
> and no other ACPI table, it would need to have "HMAT" in the path. For
> anything not ACPI it gets easier because the path can be the parent
> PCI device.
> 

There is no HMAT reservation hint in ACPI 6.3 - but there are other ways
of doing much the same thing so this is just a nitpick.

J