All of lore.kernel.org
 help / color / mirror / Atom feed
From: Xiao Guangrong <guangrong.xiao@linux.intel.com>
To: Paolo Bonzini <pbonzini@redhat.com>, Neo Jia <cjia@nvidia.com>,
	Xiaoguang Chen <xiaoguang.chen@intel.com>
Cc: kvm@vger.kernel.org, guangrong.xiao@intel.com,
	jike.song@intel.com, Kirti Wankhede <kwankhede@nvidia.com>
Subject: Re: [PATCH 1/2] KVM: page track: add a new notifier type: track_flush_slot
Date: Tue, 11 Oct 2016 17:21:07 +0800	[thread overview]
Message-ID: <ea9dffe6-7afa-4862-e46f-6f780a309e46@linux.intel.com> (raw)
In-Reply-To: <e992eb4e-0806-8f6e-851d-36eaf389a897@redhat.com>



On 10/11/2016 04:54 PM, Paolo Bonzini wrote:
>
>
> On 11/10/2016 04:39, Xiao Guangrong wrote:
>>
>>
>> On 10/11/2016 02:32 AM, Paolo Bonzini wrote:
>>>
>>>
>>> On 10/10/2016 20:01, Neo Jia wrote:
>>>>> Hi Neo,
>>>>>
>>>>> AFAIK this is needed because KVMGT doesn't paravirtualize the PPGTT,
>>>>> while nVidia does.
>>>>
>>>> Hi Paolo and Xiaoguang,
>>>>
>>>> I am just wondering how device driver can register a notifier so he
>>>> can be
>>>> notified for write-protected pages when writes are happening.
>>>
>>> It can't yet, but the API is ready for that.  kvm_vfio_set_group is
>>> currently where a struct kvm_device* and struct vfio_group* touch. Given
>>> a struct kvm_device*, dev->kvm provides the struct kvm to be passed to
>>> kvm_page_track_register_notifier.  So I guess you could add a callback
>>> that passes the struct kvm_device* to the mdev device.
>>>
>>> Xiaoguang and Guangrong, what were your plans?  We discussed it briefly
>>> at KVM Forum but I don't remember the details.
>>>
>>
>> Your suggestion was that pass kvm fd to KVMGT via VFIO, so that we can
>> figure out the kvm instance based on the fd.
>>
>> We got a new idea, how about search the kvm instance by mm_struct, it
>> can work as KVMGT is running in the vcpu context and it is much more
>> straightforward.
>
> Perhaps I didn't understand your suggestion, but the same mm_struct can
> have more than 1 struct kvm so I'm not sure that it can work.

vcpu->pid is valid during vcpu running so that it can be used to figure
out which kvm instance owns the vcpu whose pid is the one as current
thread, i think it can work. :)




  reply	other threads:[~2016-10-11  9:27 UTC|newest]

Thread overview: 58+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-10-09  7:41 [PATCH 0/2] page track add notifier type track_flush_slot Xiaoguang Chen
2016-10-09  7:41 ` [PATCH 1/2] KVM: page track: add a new notifier type: track_flush_slot Xiaoguang Chen
2016-10-09  8:31   ` Neo Jia
2016-10-09  8:56     ` Chen, Xiaoguang
2016-10-10 17:06     ` Paolo Bonzini
2016-10-10 18:01       ` Neo Jia
2016-10-10 18:32         ` Paolo Bonzini
2016-10-11  2:39           ` Xiao Guangrong
2016-10-11  8:54             ` Paolo Bonzini
2016-10-11  9:21               ` Xiao Guangrong [this message]
2016-10-11  9:47                 ` Paolo Bonzini
2016-10-14 10:37                   ` Jike Song
2016-10-14 10:37                     ` [Qemu-devel] " Jike Song
2016-10-14 10:43                     ` Paolo Bonzini
2016-10-14 10:43                       ` [Qemu-devel] " Paolo Bonzini
2016-10-14 12:26                       ` Jike Song
2016-10-14 12:26                         ` [Qemu-devel] " Jike Song
2016-10-14 14:41                     ` Alex Williamson
2016-10-14 14:46                       ` Alex Williamson
2016-10-14 14:46                         ` [Qemu-devel] " Alex Williamson
2016-10-14 16:35                         ` Neo Jia
2016-10-14 16:35                           ` Neo Jia
2016-10-14 16:51                           ` Alex Williamson
2016-10-14 16:51                             ` Alex Williamson
2016-10-14 22:19                             ` Neo Jia
2016-10-14 22:19                               ` Neo Jia
2016-10-17 16:02                               ` Alex Williamson
2016-10-17 16:02                                 ` Alex Williamson
2016-10-18 12:38                                 ` Jike Song
2016-10-18 14:59                                   ` Alex Williamson
2016-10-19  2:32                                     ` Jike Song
2016-10-19  5:45                                       ` Xiao Guangrong
2016-10-19 11:56                                         ` Paolo Bonzini
2016-10-19 11:56                                           ` [Qemu-devel] " Paolo Bonzini
2016-10-19 13:39                                           ` Xiao Guangrong
2016-10-19 13:39                                             ` [Qemu-devel] " Xiao Guangrong
2016-10-19 14:14                                             ` Paolo Bonzini
2016-10-19 14:14                                               ` [Qemu-devel] " Paolo Bonzini
2016-10-20  1:48                                               ` Xiao Guangrong
2016-10-20 17:06                                                 ` Paolo Bonzini
2016-10-20 17:19                                                   ` Xiao, Guangrong
2016-10-20 17:19                                                     ` [Qemu-devel] " Xiao, Guangrong
2016-10-21  2:47                                                     ` Jike Song
2016-10-21  2:47                                                       ` Jike Song
2016-10-26 13:44                                                   ` Jike Song
2016-10-26 13:44                                                     ` Jike Song
2016-10-26 14:45                                                     ` Paolo Bonzini
2016-10-29  4:07                                                       ` Jike Song
2016-10-29  4:07                                                         ` Jike Song
2016-10-19 13:56                                       ` Eric Blake
2016-10-19 13:56                                         ` [Qemu-devel] " Eric Blake
2016-10-24  6:32                                         ` Jike Song
2016-10-12 20:48   ` Radim Krčmář
2016-10-09  7:41 ` [PATCH 2/2] KVM: MMU: apply page track notifier type track_flush_slot Xiaoguang Chen
2016-10-10 17:06 ` [PATCH 0/2] page track add " Paolo Bonzini
2016-10-11  2:43   ` Xiao Guangrong
2016-10-11  8:55     ` Paolo Bonzini
2016-10-12 20:52       ` Radim Krčmář

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=ea9dffe6-7afa-4862-e46f-6f780a309e46@linux.intel.com \
    --to=guangrong.xiao@linux.intel.com \
    --cc=cjia@nvidia.com \
    --cc=guangrong.xiao@intel.com \
    --cc=jike.song@intel.com \
    --cc=kvm@vger.kernel.org \
    --cc=kwankhede@nvidia.com \
    --cc=pbonzini@redhat.com \
    --cc=xiaoguang.chen@intel.com \
    /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.