linux-pci.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Jason Gunthorpe <jgg@ziepe.ca>
To: Max Gurtovoy <mgurtovoy@nvidia.com>
Cc: Alex Williamson <alex.williamson@redhat.com>,
	Leon Romanovsky <leon@kernel.org>,
	Doug Ledford <dledford@redhat.com>,
	Yishai Hadas <yishaih@nvidia.com>,
	Bjorn Helgaas <bhelgaas@google.com>,
	"David S. Miller" <davem@davemloft.net>,
	Jakub Kicinski <kuba@kernel.org>,
	Kirti Wankhede <kwankhede@nvidia.com>,
	kvm@vger.kernel.org, linux-kernel@vger.kernel.org,
	linux-pci@vger.kernel.org, linux-rdma@vger.kernel.org,
	netdev@vger.kernel.org, Saeed Mahameed <saeedm@nvidia.com>,
	Cornelia Huck <cohuck@redhat.com>
Subject: Re: [PATCH mlx5-next 2/7] vfio: Add an API to check migration state transition validity
Date: Thu, 30 Sep 2021 14:01:43 -0300	[thread overview]
Message-ID: <20210930170143.GB69218@ziepe.ca> (raw)
In-Reply-To: <c7a18080-3ffc-488b-577c-1e3b356bf66e@nvidia.com>

On Thu, Sep 30, 2021 at 07:51:22PM +0300, Max Gurtovoy wrote:
> 
> On 9/30/2021 7:24 PM, Jason Gunthorpe wrote:
> > On Thu, Sep 30, 2021 at 06:32:07PM +0300, Max Gurtovoy wrote:
> > > > Just prior to open device the vfio pci layer will generate a FLR to
> > > > the function so we expect that post open_device has a fresh from reset
> > > > fully running device state.
> > > running also mean that the device doesn't have a clue on its internal state
> > > ? or running means unfreezed and unquiesced ?
> > The device just got FLR'd and it should be in a clean state and
> > operating. Think the VM is booting for the first time.
> 
> During the resume phase in the dst, the VM is paused and not booting.
> Migration SW is waiting to get memory and state from SRC. The device will
> start from the exact point that was in the src.
> 
> it's exactly "000b => Device Stopped, not saving or resuming"

For this case qmeu should open the VFIO device and immediately issue a
command to go to resuming. The kernel cannot know at open_device time
which case userspace is trying to do. Due to backwards compat we
assume userspace is going to boot a fresh VM.

> Well, this is your design for the driver implementation. Nobody is
> preventing other drivers to start deserializing device state into the device
> during RESUMING bit on.

It is a logical model. Devices can stream the migration data directly
into the internal state if they like. It just creates more conditions
where they have report an error state.

> So if we moved from 100b to 010b somehow, one should deserialized its buffer
> to the device, and then serialize it to migration region again ?

Yes.
 
> I guess its doable since the device is freeze and quiesced. But moving from
> 100b to 011b is not possible, right ?

Why not?

100b to 011b is no different than going indirectly 100b -> 001b -> 011b

The time spent in 001b is just negligable.

Jason

  reply	other threads:[~2021-09-30 17:01 UTC|newest]

Thread overview: 58+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-09-22 10:38 [PATCH mlx5-next 0/7] Add mlx5 live migration driver Leon Romanovsky
2021-09-22 10:38 ` [PATCH mlx5-next 1/7] PCI/IOV: Provide internal VF index Leon Romanovsky
2021-09-22 21:59   ` Bjorn Helgaas
2021-09-23  6:35     ` Leon Romanovsky
2021-09-24 13:08       ` Bjorn Helgaas
2021-09-25 10:10         ` Leon Romanovsky
2021-09-25 17:41           ` Bjorn Helgaas
2021-09-26  6:36             ` Leon Romanovsky
2021-09-26 20:23               ` Bjorn Helgaas
2021-09-27 11:55                 ` Leon Romanovsky
2021-09-27 14:47                   ` Bjorn Helgaas
2021-09-22 10:38 ` [PATCH mlx5-next 2/7] vfio: Add an API to check migration state transition validity Leon Romanovsky
2021-09-23 10:33   ` Shameerali Kolothum Thodi
2021-09-23 11:17     ` Leon Romanovsky
2021-09-23 13:55       ` Max Gurtovoy
2021-09-24  7:44         ` Shameerali Kolothum Thodi
2021-09-24  9:37           ` Kirti Wankhede
2021-09-26  9:09           ` Max Gurtovoy
2021-09-26 16:17             ` Shameerali Kolothum Thodi
2021-09-27 18:24               ` Max Gurtovoy
2021-09-27 18:29                 ` Shameerali Kolothum Thodi
2021-09-27 22:46   ` Alex Williamson
2021-09-27 23:12     ` Jason Gunthorpe
2021-09-28 19:19       ` Alex Williamson
2021-09-28 19:35         ` Jason Gunthorpe
2021-09-28 20:18           ` Alex Williamson
2021-09-29 16:16             ` Jason Gunthorpe
2021-09-29 18:06               ` Alex Williamson
2021-09-29 18:26                 ` Jason Gunthorpe
2021-09-29 10:57         ` Max Gurtovoy
2021-09-29 10:44       ` Max Gurtovoy
2021-09-29 12:35         ` Alex Williamson
2021-09-29 13:26           ` Max Gurtovoy
2021-09-29 13:50             ` Alex Williamson
2021-09-29 14:36               ` Max Gurtovoy
2021-09-29 15:17                 ` Alex Williamson
2021-09-29 15:28                   ` Max Gurtovoy
2021-09-29 16:14                     ` Jason Gunthorpe
2021-09-29 21:48                       ` Max Gurtovoy
2021-09-29 22:44                         ` Alex Williamson
2021-09-30  9:25                           ` Max Gurtovoy
2021-09-30 12:41                             ` Alex Williamson
2021-09-29 23:21                         ` Jason Gunthorpe
2021-09-30  9:34                           ` Max Gurtovoy
2021-09-30 14:47                             ` Jason Gunthorpe
2021-09-30 15:32                               ` Max Gurtovoy
2021-09-30 16:24                                 ` Jason Gunthorpe
2021-09-30 16:51                                   ` Max Gurtovoy
2021-09-30 17:01                                     ` Jason Gunthorpe [this message]
2021-09-22 10:38 ` [PATCH mlx5-next 3/7] vfio/pci_core: Make the region->release() function optional Leon Romanovsky
2021-09-23 13:57   ` Max Gurtovoy
2021-09-22 10:38 ` [PATCH mlx5-next 4/7] net/mlx5: Introduce migration bits and structures Leon Romanovsky
2021-09-24  5:48   ` Mark Zhang
2021-09-22 10:38 ` [PATCH mlx5-next 5/7] net/mlx5: Expose APIs to get/put the mlx5 core device Leon Romanovsky
2021-09-22 10:38 ` [PATCH mlx5-next 6/7] mlx5_vfio_pci: Expose migration commands over mlx5 device Leon Romanovsky
2021-09-28 20:22   ` Alex Williamson
2021-09-29  5:36     ` Leon Romanovsky
2021-09-22 10:38 ` [PATCH mlx5-next 7/7] mlx5_vfio_pci: Implement vfio_pci driver for mlx5 devices Leon Romanovsky

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=20210930170143.GB69218@ziepe.ca \
    --to=jgg@ziepe.ca \
    --cc=alex.williamson@redhat.com \
    --cc=bhelgaas@google.com \
    --cc=cohuck@redhat.com \
    --cc=davem@davemloft.net \
    --cc=dledford@redhat.com \
    --cc=kuba@kernel.org \
    --cc=kvm@vger.kernel.org \
    --cc=kwankhede@nvidia.com \
    --cc=leon@kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-pci@vger.kernel.org \
    --cc=linux-rdma@vger.kernel.org \
    --cc=mgurtovoy@nvidia.com \
    --cc=netdev@vger.kernel.org \
    --cc=saeedm@nvidia.com \
    --cc=yishaih@nvidia.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).