linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Dan Williams <dan.j.williams@intel.com>
To: Michal Hocko <mhocko@kernel.org>
Cc: Jane Chu <jane.chu@oracle.com>,
	"Verma, Vishal L" <vishal.l.verma@intel.com>,
	"Du, Fan" <fan.du@intel.com>,
	"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
	"bp@suse.de" <bp@suse.de>,
	"linux-mm@kvack.org" <linux-mm@kvack.org>,
	"dave.hansen@linux.intel.com" <dave.hansen@linux.intel.com>,
	"tiwai@suse.de" <tiwai@suse.de>,
	"akpm@linux-foundation.org" <akpm@linux-foundation.org>,
	"linux-nvdimm@lists.01.org" <linux-nvdimm@lists.01.org>,
	"jglisse@redhat.com" <jglisse@redhat.com>,
	"zwisler@kernel.org" <zwisler@kernel.org>,
	"baiyaowei@cmss.chinamobile.com" <baiyaowei@cmss.chinamobile.com>,
	"thomas.lendacky@amd.com" <thomas.lendacky@amd.com>,
	"Wu, Fengguang" <fengguang.wu@intel.com>,
	"Huang, Ying" <ying.huang@intel.com>,
	"bhelgaas@google.com" <bhelgaas@g>
Subject: Re: [PATCH 5/5] dax: "Hotplug" persistent memory for use like normal RAM
Date: Mon, 28 Jan 2019 08:34:56 -0800	[thread overview]
Message-ID: <CAPcyv4j2vmWXQO0QoBU5-yXBJBaEuDrPJ0t1tWkftCbwb4rnWA@mail.gmail.com> (raw)
In-Reply-To: <20190128092549.GF18811@dhcp22.suse.cz>

On Mon, Jan 28, 2019 at 1:26 AM Michal Hocko <mhocko@kernel.org> wrote:
>
> On Fri 25-01-19 11:15:08, Dan Williams wrote:
> [...]
> > However, we should consider this along with the userspace enabling to
> > control which device-dax instances are set aside for hotplug. It would
> > make sense to have a "clear errors before hotplug" configuration
> > option.
>
> I am not sure I understand. Do you mean to clear HWPoison when the
> memory is hotadded (add_pages) or onlined (resp. move_pfn_range_to_zone)?

Before the memory is hot-added via the kmem driver it shows up as an
independent persistent memory namespace. A namespace can be configured
as a block device and errors cleared by writing to the given "bad
block". Once all media errors are cleared the namespace can be
assigned as volatile memory to the core-kernel mm. The memory range
starts as a namespace each boot and must be hotplugged via startup
scripts, those scripts can be made to handle the bad block pruning.

WARNING: multiple messages have this Message-ID
From: Dan Williams <dan.j.williams@intel.com>
To: Michal Hocko <mhocko@kernel.org>
Cc: Jane Chu <jane.chu@oracle.com>,
	"Verma, Vishal L" <vishal.l.verma@intel.com>,
	 "Du, Fan" <fan.du@intel.com>,
	 "linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
	"bp@suse.de" <bp@suse.de>,
	 "linux-mm@kvack.org" <linux-mm@kvack.org>,
	 "dave.hansen@linux.intel.com" <dave.hansen@linux.intel.com>,
	"tiwai@suse.de" <tiwai@suse.de>,
	 "akpm@linux-foundation.org" <akpm@linux-foundation.org>,
	 "linux-nvdimm@lists.01.org" <linux-nvdimm@lists.01.org>,
	"jglisse@redhat.com" <jglisse@redhat.com>,
	 "zwisler@kernel.org" <zwisler@kernel.org>,
	 "baiyaowei@cmss.chinamobile.com"
	<baiyaowei@cmss.chinamobile.com>,
	 "thomas.lendacky@amd.com" <thomas.lendacky@amd.com>,
	"Wu, Fengguang" <fengguang.wu@intel.com>,
	 "Huang, Ying" <ying.huang@intel.com>,
	"bhelgaas@google.com" <bhelgaas@google.com>
Subject: Re: [PATCH 5/5] dax: "Hotplug" persistent memory for use like normal RAM
Date: Mon, 28 Jan 2019 08:34:56 -0800	[thread overview]
Message-ID: <CAPcyv4j2vmWXQO0QoBU5-yXBJBaEuDrPJ0t1tWkftCbwb4rnWA@mail.gmail.com> (raw)
Message-ID: <20190128163456.FgKxQHC6gQXkzhFUMKLkufdIG-NVXXHY4MTlEXpJyKg@z> (raw)
In-Reply-To: <20190128092549.GF18811@dhcp22.suse.cz>

On Mon, Jan 28, 2019 at 1:26 AM Michal Hocko <mhocko@kernel.org> wrote:
>
> On Fri 25-01-19 11:15:08, Dan Williams wrote:
> [...]
> > However, we should consider this along with the userspace enabling to
> > control which device-dax instances are set aside for hotplug. It would
> > make sense to have a "clear errors before hotplug" configuration
> > option.
>
> I am not sure I understand. Do you mean to clear HWPoison when the
> memory is hotadded (add_pages) or onlined (resp. move_pfn_range_to_zone)?

Before the memory is hot-added via the kmem driver it shows up as an
independent persistent memory namespace. A namespace can be configured
as a block device and errors cleared by writing to the given "bad
block". Once all media errors are cleared the namespace can be
assigned as volatile memory to the core-kernel mm. The memory range
starts as a namespace each boot and must be hotplugged via startup
scripts, those scripts can be made to handle the bad block pruning.


  reply	other threads:[~2019-01-28 16:34 UTC|newest]

Thread overview: 51+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-01-24 23:14 [PATCH 0/5] [v4] Allow persistent memory to be used " Dave Hansen
2019-01-24 23:14 ` Dave Hansen
2019-01-24 23:14 ` [PATCH 1/5] mm/resource: return real error codes from walk failures Dave Hansen
2019-01-24 23:14   ` Dave Hansen
2019-01-25 21:02   ` Bjorn Helgaas
2019-01-25 21:02     ` Bjorn Helgaas
2019-01-25 21:09     ` Dave Hansen
2019-01-25 21:19       ` Bjorn Helgaas
2019-01-25 21:19         ` Bjorn Helgaas
2019-01-29  1:18       ` Michael Ellerman
2019-01-24 23:14 ` [PATCH 2/5] mm/resource: move HMM pr_debug() deeper into resource code Dave Hansen
2019-01-24 23:14   ` Dave Hansen
2019-01-25 19:07   ` Jerome Glisse
2019-01-25 21:18   ` Bjorn Helgaas
2019-01-25 21:18     ` Bjorn Helgaas
2019-01-25 21:24     ` Dave Hansen
2019-01-29  1:34       ` Michael Ellerman
2019-01-24 23:14 ` [PATCH 3/5] mm/memory-hotplug: allow memory resources to be children Dave Hansen
2019-01-24 23:14   ` Dave Hansen
2019-01-24 23:14 ` [PATCH 4/5] dax/kmem: let walk_system_ram_range() search child resources Dave Hansen
2019-01-24 23:14   ` Dave Hansen
2019-01-24 23:14 ` [PATCH 5/5] dax: "Hotplug" persistent memory for use like normal RAM Dave Hansen
2019-01-24 23:14   ` Dave Hansen
2019-01-25  6:13   ` Jane Chu
2019-01-25  6:27     ` Dan Williams
2019-01-25  6:27       ` Dan Williams
2019-01-25  8:20       ` Du, Fan
2019-01-25 17:18         ` Dan Williams
2019-01-25 18:20           ` Verma, Vishal L
2019-01-25 19:10             ` Jane Chu
2019-01-25 19:15               ` Dan Williams
2019-01-25 19:15                 ` Dan Williams
2019-01-25 23:30                 ` Jane Chu
2019-01-28  9:25                 ` Michal Hocko
2019-01-28 16:34                   ` Dan Williams [this message]
2019-01-28 16:34                     ` Dan Williams
2019-02-09 11:00   ` Brice Goglin
2019-02-11 16:22     ` Dave Hansen
2019-02-12 19:59       ` Brice Goglin
2019-02-13  0:30         ` Dan Williams
2019-02-13  8:12           ` Brice Goglin
2019-02-13  8:24             ` Dan Williams
2019-02-13  8:43               ` Brice Goglin
2019-02-13 13:06                 ` Brice Goglin
2019-02-13 16:19                   ` Dan Williams
2019-01-25 19:08 ` [PATCH 0/5] [v4] Allow persistent memory to be used " Jerome Glisse
2019-01-28 11:09 ` Balbir Singh
2019-01-28 16:50   ` Dave Hansen
2019-01-28 16:50     ` Dave Hansen
2019-02-25 18:57 [PATCH 0/5] [v5] " Dave Hansen
2019-02-25 18:57 ` [PATCH 5/5] dax: "Hotplug" persistent memory for use " Dave Hansen
2019-02-25 22:56   ` Verma, Vishal L

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=CAPcyv4j2vmWXQO0QoBU5-yXBJBaEuDrPJ0t1tWkftCbwb4rnWA@mail.gmail.com \
    --to=dan.j.williams@intel.com \
    --cc=akpm@linux-foundation.org \
    --cc=baiyaowei@cmss.chinamobile.com \
    --cc=bhelgaas@g \
    --cc=bp@suse.de \
    --cc=dave.hansen@linux.intel.com \
    --cc=fan.du@intel.com \
    --cc=fengguang.wu@intel.com \
    --cc=jane.chu@oracle.com \
    --cc=jglisse@redhat.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=linux-nvdimm@lists.01.org \
    --cc=mhocko@kernel.org \
    --cc=thomas.lendacky@amd.com \
    --cc=tiwai@suse.de \
    --cc=vishal.l.verma@intel.com \
    --cc=ying.huang@intel.com \
    --cc=zwisler@kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox