From: Konrad Rzeszutek Wilk <konrad@darnok.org>
To: Dan Williams <dan.j.williams@intel.com>
Cc: Wei Liu <wei.liu2@citrix.com>,
Andrew Cooper <andrew.cooper3@citrix.com>,
Ian Jackson <ian.jackson@eu.citrix.com>,
xen-devel@lists.xen.org, Jan Beulich <jbeulich@suse.com>,
Daniel De Graaf <dgdegra@tycho.nsa.gov>
Subject: Re: [RFC XEN PATCH v2 00/15] Add vNVDIMM support to HVM domains
Date: Sat, 1 Apr 2017 07:54:25 -0400 [thread overview]
Message-ID: <20170401115423.GA4844@localhost.localdomain> (raw)
In-Reply-To: <CAPcyv4iqOHVYnDcU96G-VCrmHk9vK9gUgmaGZMpOMBZnQRrRWg@mail.gmail.com>
..snip..
> >> Is there a resource I can read more about why the hypervisor needs to
> >> have this M2P mapping for nvdimm support?
> >
> > M2P is basically an array of frame numbers. It's indexed by the host
> > page frame number, or the machine frame number (MFN) in Xen's
> > definition. The n'th entry records the guest page frame number that is
> > mapped to MFN n. M2P is one of the core data structures used in Xen
> > memory management, and is used to convert MFN to guest PFN. A
> > read-only version of M2P is also exposed as part of ABI to guest. In
> > the previous design discussion, we decided to put the management of
> > NVDIMM in the existing Xen memory management as much as possible, so
> > we need to build M2P for NVDIMM as well.
> >
>
> Thanks, but what I don't understand is why this M2P lookup is needed?
Xen uses it to construct the EPT page tables for the guests.
> Does Xen establish this metadata for PCI mmio ranges as well? What Xen
It doesn't have that (M2P) for PCI MMIO ranges. For those it has an
ranges construct (since those are usually contingous and given
in ranges to a guest).
> memory management operations does this enable? Sorry if these are
> basic Xen questions, I'm just looking to see if we can make the
> mapping support more dynamic. For example, what if we wanted to change
> the MFN to guest PFN relationship after every fault?
As in swap it out? (Like a hard drive swaps out faulty sectors?).
That is certainly done. We also have tools (xen-hptool) that can
mark certain pages as broken/etc and inject the MCEs in the guest
to reflect that. But all of that is driven by hypercalls
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
https://lists.xen.org/xen-devel
next prev parent reply other threads:[~2017-04-01 11:54 UTC|newest]
Thread overview: 32+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-03-20 0:09 [RFC XEN PATCH v2 00/15] Add vNVDIMM support to HVM domains Haozhong Zhang
2017-03-20 0:09 ` [RFC XEN PATCH v2 01/15] xen/common: add Kconfig item for pmem support Haozhong Zhang
2017-03-20 0:09 ` [RFC XEN PATCH v2 02/15] xen: probe pmem regions via ACPI NFIT Haozhong Zhang
2017-03-20 0:09 ` [RFC XEN PATCH v2 03/15] xen/x86: allow customizing locations of extended frametable & M2P Haozhong Zhang
2017-03-20 0:09 ` [RFC XEN PATCH v2 04/15] xen/x86: add XEN_SYSCTL_nvdimm_pmem_setup to setup host pmem Haozhong Zhang
2017-03-20 0:09 ` [RFC XEN PATCH v2 05/15] xen/x86: add XENMEM_populate_pmem_map to map host pmem pages to HVM domain Haozhong Zhang
2017-03-20 0:09 ` [RFC XEN PATCH v2 06/15] tools: reserve guest memory for ACPI from device model Haozhong Zhang
2017-03-20 0:09 ` [RFC XEN PATCH v2 07/15] tools/libacpi: expose the minimum alignment used by mem_ops.alloc Haozhong Zhang
2017-03-20 0:09 ` [RFC XEN PATCH v2 08/15] tools/libacpi: add callback acpi_ctxt.p2v to get a pointer from physical address Haozhong Zhang
2017-03-20 0:09 ` [RFC XEN PATCH v2 09/15] tools/libacpi: add callbacks to access XenStore Haozhong Zhang
2017-03-20 0:09 ` [RFC XEN PATCH v2 10/15] tools/libacpi: add a simple AML builder Haozhong Zhang
2017-03-20 0:09 ` [RFC XEN PATCH v2 11/15] tools/libacpi: load ACPI built by the device model Haozhong Zhang
2017-03-20 0:09 ` [RFC XEN PATCH v2 12/15] tools/libxl: build qemu options from xl vNVDIMM configs Haozhong Zhang
2017-03-20 0:09 ` [RFC XEN PATCH v2 13/15] tools/libxl: add support to map host pmem device to guests Haozhong Zhang
2017-03-20 0:09 ` [RFC XEN PATCH v2 14/15] tools/libxl: initiate pmem mapping via qmp callback Haozhong Zhang
2017-03-20 0:09 ` [RFC XEN PATCH v2 15/15] tools/misc: add xen-ndctl Haozhong Zhang
2017-03-30 4:11 ` Dan Williams
2017-03-30 7:58 ` Haozhong Zhang
2017-04-01 11:55 ` Konrad Rzeszutek Wilk
2017-03-30 4:20 ` [RFC XEN PATCH v2 00/15] Add vNVDIMM support to HVM domains Dan Williams
2017-03-30 8:21 ` Haozhong Zhang
2017-03-30 16:01 ` Dan Williams
2017-04-01 11:54 ` Konrad Rzeszutek Wilk [this message]
2017-04-01 15:45 ` Dan Williams
2017-04-04 17:00 ` Konrad Rzeszutek Wilk
2017-04-04 17:16 ` Dan Williams
2017-04-04 17:34 ` Konrad Rzeszutek Wilk
2017-04-04 17:59 ` Dan Williams
2017-04-04 18:05 ` Konrad Rzeszutek Wilk
2017-04-04 18:59 ` Dan Williams
2017-04-11 17:48 ` Konrad Rzeszutek Wilk
2017-04-01 12:24 ` Konrad Rzeszutek Wilk
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=20170401115423.GA4844@localhost.localdomain \
--to=konrad@darnok.org \
--cc=andrew.cooper3@citrix.com \
--cc=dan.j.williams@intel.com \
--cc=dgdegra@tycho.nsa.gov \
--cc=ian.jackson@eu.citrix.com \
--cc=jbeulich@suse.com \
--cc=wei.liu2@citrix.com \
--cc=xen-devel@lists.xen.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.