All of lore.kernel.org
 help / color / mirror / Atom feed
From: Andrew Cooper <andrew.cooper3@citrix.com>
To: Ed White <edmund.h.white@intel.com>, xen-devel@lists.xen.org
Cc: ian.jackson@eu.citrix.com, tim@xen.org, keir@xen.org,
	ian.campbell@citrix.com, jbeulich@suse.com
Subject: Re: [PATCH 00/11] Alternate p2m: support multiple copies of host p2m
Date: Fri, 09 Jan 2015 22:06:37 +0000	[thread overview]
Message-ID: <54B050ED.8080905@citrix.com> (raw)
In-Reply-To: <1420838801-11704-1-git-send-email-edmund.h.white@intel.com>

On 09/01/2015 21:26, Ed White wrote:
> This set of patches adds support to hvm domains for EPTP switching by creating
> multiple copies of the host p2m (currently limited to 10 copies).
>
> The primary use of this capability is expected to be in scenarios where access
> to memory needs to be monitored and/or restricted below the level at which the
> guest OS page tables operate. Two examples that were discussed at the 2014 Xen
> developer summit are:

Given the nature of VMFUNC, I presume this series is looking to add
support for in-guest entities to be able to monitor/tweak/swap the EPT
tables under the feet of operating system around it?

>
>     VM introspection: 
>         http://www.slideshare.net/xen_com_mgr/
>         zero-footprint-guest-memory-introspection-from-xen
>
>     Secure inter-VM communication:
>         http://www.slideshare.net/xen_com_mgr/nakajima-nvf
>
> Each p2m copy is populated lazily on EPT violations, and only contains entries for
> ram p2m types. Permissions for pages in alternate p2m's can be changed in a similar
> way to the existing memory access interface, and gfn->mfn mappings can be changed.
>
> All this is done through extra HVMOP types.
>
> The cross-domain HVMOP code has been compile-tested only. Also, the cross-domain
> code is hypervisor-only, the toolstack has not been modified.
>
> The intra-domain code has been tested. Violation notifications can only be received
> for pages that have been modified (access permissions and/or gfn->mfn mapping) 
> intra-domain, and only on VCPU's that have enabled notification.
>
> VMFUNC and #VE will both be emulated on hardware without native support.
>
> This code is not compatible with nested hvm functionality and will refuse to work
> with nested hvm active. It is also not compatible with migration. It should be
> considered experimental.

What about shared ept, pci passthrough, ballooning, PoD or any other
mechanisms which involve playing games with the EPT tables behind the
back of the guest?

It appears that this feature only makes sense for a plain, RAM-only VM
with no bells or whistles.

~Andrew

  parent reply	other threads:[~2015-01-09 22:06 UTC|newest]

Thread overview: 135+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-01-09 21:26 [PATCH 00/11] Alternate p2m: support multiple copies of host p2m Ed White
2015-01-09 21:26 ` [PATCH 01/11] VMX: VMFUNC and #VE definitions and detection Ed White
2015-01-12 13:06   ` Andrew Cooper
2015-01-13 18:50     ` Ed White
2015-01-14 14:38       ` Andrew Cooper
2015-01-09 21:26 ` [PATCH 02/11] VMX: implement suppress #VE Ed White
2015-01-12 16:43   ` Andrew Cooper
2015-01-12 17:45     ` Ed White
2015-01-13 18:36       ` Ed White
2015-01-15 16:25   ` Tim Deegan
2015-01-15 18:46     ` Ed White
2015-01-16 17:22       ` Tim Deegan
2015-03-25 17:30       ` Ed White
2015-03-26 10:15         ` Tim Deegan
2015-01-09 21:26 ` [PATCH 03/11] x86/HVM: Hardware alternate p2m support detection Ed White
2015-01-12 17:08   ` Andrew Cooper
2015-01-12 17:46     ` Ed White
2015-01-15 16:32   ` Tim Deegan
2015-01-09 21:26 ` [PATCH 04/11] x86/MM: Improve p2m type checks Ed White
2015-01-12 17:48   ` Andrew Cooper
2015-01-13 19:39     ` Ed White
2015-01-15 16:36   ` Tim Deegan
2015-01-09 21:26 ` [PATCH 05/11] x86/altp2m: basic data structures and support routines Ed White
2015-01-13 11:28   ` Andrew Cooper
2015-01-13 19:49     ` Ed White
2015-03-25 20:59       ` Ed White
2015-03-26 10:48         ` Tim Deegan
2015-03-26 18:00           ` Ed White
2015-01-15 16:48   ` Tim Deegan
2015-01-15 16:53     ` Jan Beulich
2015-01-15 18:49       ` Ed White
2015-01-16  7:37         ` Jan Beulich
2015-01-16 17:23         ` Tim Deegan
2015-01-09 21:26 ` [PATCH 06/11] VMX/altp2m: add code to support EPTP switching and #VE Ed White
2015-01-13 11:58   ` Andrew Cooper
2015-01-15 16:56   ` Tim Deegan
2015-01-15 18:55     ` Ed White
2015-01-16 17:50       ` Tim Deegan
2015-01-16 17:57         ` Ed White
2015-01-09 21:26 ` [PATCH 07/11] x86/altp2m: introduce p2m_ram_rw_ve type Ed White
2015-01-15 17:03   ` Tim Deegan
2015-01-15 20:38     ` Ed White
2015-01-16  8:20       ` Jan Beulich
2015-01-16 17:14         ` Ed White
2015-01-19  8:49           ` Jan Beulich
2015-01-19 19:53             ` Ed White
2015-01-16 17:52       ` Tim Deegan
2015-01-16 18:35         ` Ed White
2015-01-17  9:37           ` Tim Deegan
2015-01-09 21:26 ` [PATCH 08/11] x86/altp2m: add remaining support routines Ed White
2015-01-15 17:25   ` Tim Deegan
2015-01-15 20:57     ` Ed White
2015-01-16 18:04       ` Tim Deegan
2015-01-15 17:33   ` Tim Deegan
2015-01-15 21:00     ` Ed White
2015-01-16  8:24       ` Jan Beulich
2015-01-16 17:17         ` Ed White
2015-01-19  8:52           ` Jan Beulich
2015-01-16 18:09       ` Tim Deegan
2015-01-09 21:26 ` [PATCH 09/11] x86/altp2m: define and implement alternate p2m HVMOP types Ed White
2015-01-15 17:09   ` Tim Deegan
2015-01-15 20:43     ` Ed White
2015-01-16 17:57       ` Tim Deegan
2015-01-09 21:26 ` [PATCH 10/11] x86/altp2m: fix log-dirty handling Ed White
2015-01-15 17:20   ` Tim Deegan
2015-01-15 20:49     ` Ed White
2015-01-16 17:59       ` Tim Deegan
2015-01-09 21:26 ` [PATCH 11/11] x86/altp2m: alternate p2m memory events Ed White
2015-01-09 22:06 ` Andrew Cooper [this message]
2015-01-09 22:21   ` [PATCH 00/11] Alternate p2m: support multiple copies of host p2m Ed White
2015-01-09 22:41     ` Andrew Cooper
2015-01-09 23:04       ` Ed White
2015-01-12 10:00         ` Jan Beulich
2015-01-12 17:36           ` Ed White
2015-01-13  8:56             ` Jan Beulich
2015-01-13 11:28               ` Ian Jackson
2015-01-13 17:42               ` Ed White
2015-01-12 12:17 ` Ian Jackson
2015-01-12 17:39   ` Ed White
2015-01-12 17:43     ` Ian Jackson
2015-01-12 17:50       ` Ed White
2015-01-12 18:00         ` Ian Jackson
2015-01-12 18:31           ` Ed White
2015-01-13 10:21             ` Tamas K Lengyel
2015-01-13 18:25               ` Ed White
2015-01-13 11:16             ` Ian Jackson
2015-01-12 17:51       ` Andrew Cooper
2015-01-13 19:01 ` Andrew Cooper
2015-01-13 20:02   ` Ed White
2015-01-13 20:45     ` Andrew Cooper
2015-01-13 21:30       ` Ed White
2015-01-14  7:04         ` Jan Beulich
2015-01-14 10:31           ` Tamas K Lengyel
2015-01-14 11:09             ` Jan Beulich
2015-01-14 11:28               ` Tamas K Lengyel
2015-01-14 17:35                 ` Ed White
2015-01-15  8:16                   ` Jan Beulich
2015-01-15 17:28                     ` Ed White
2015-01-15 17:45                       ` Tim Deegan
2015-01-15 18:44                         ` Ed White
2015-03-04 23:06                           ` Tamas K Lengyel
2015-03-04 23:41                             ` Ed White
2015-03-05 10:51                               ` Tamas K Lengyel
2015-03-13 17:38                                 ` Ed White
2015-03-05 10:36                             ` Tim Deegan
2015-03-05 10:58                               ` Tamas K Lengyel
2015-03-05 11:13                                 ` Tim Deegan
2015-01-16  7:35                       ` Jan Beulich
2015-01-16 16:54                         ` Ed White
2015-01-15 10:39                   ` Tamas K Lengyel
2015-01-15 17:31                     ` Ed White
2015-01-16 10:43                       ` Tamas K Lengyel
2015-01-16 17:21                         ` Ed White
2015-03-05 13:45       ` Egger, Christoph
2015-01-14  7:01     ` Jan Beulich
2015-01-15 16:15 ` Tim Deegan
2015-01-15 18:23   ` Ed White
2015-01-16  8:12     ` Jan Beulich
2015-01-16 17:01       ` Ed White
2015-01-16 18:33     ` Tim Deegan
2015-01-16 20:32       ` Ed White
2015-01-17  9:34         ` Tim Deegan
2015-01-16 21:43       ` Ed White
2015-01-17  9:49         ` Tim Deegan
2015-01-19 19:35           ` Ed White
2015-01-17  9:31       ` Tim Deegan
2015-01-17 15:01         ` Andrew Cooper
2015-01-19 12:17           ` Tim Deegan
2015-01-19 21:54             ` Ed White
2015-01-20  8:47               ` Jan Beulich
2015-01-20 18:43                 ` Ed White
2015-01-22 15:42               ` Tim Deegan
2015-01-22 19:15                 ` Ed White
2015-03-25 17:41     ` Ed White
2015-03-26 10:40       ` Tim Deegan

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=54B050ED.8080905@citrix.com \
    --to=andrew.cooper3@citrix.com \
    --cc=edmund.h.white@intel.com \
    --cc=ian.campbell@citrix.com \
    --cc=ian.jackson@eu.citrix.com \
    --cc=jbeulich@suse.com \
    --cc=keir@xen.org \
    --cc=tim@xen.org \
    --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.