public inbox for netdev@vger.kernel.org 
 help / color / mirror / Atom feed
From: Jason Gunthorpe <jgg@nvidia•com>
To: "Cédric Le Goater" <clg@kaod•org>
Cc: Yishai Hadas <yishaih@nvidia•com>,
	alex.williamson@redhat•com, saeedm@nvidia•com,
	kvm@vger•kernel.org, netdev@vger•kernel.org, kuba@kernel•org,
	kevin.tian@intel•com, joao.m.martins@oracle•com,
	leonro@nvidia•com, maorg@nvidia•com, cohuck@redhat•com,
	'Avihai Horon' <avihaih@nvidia•com>,
	Tarun Gupta <targupta@nvidia•com>
Subject: Re: [PATCH V7 vfio 07/10] vfio/mlx5: Create and destroy page tracker object
Date: Wed, 6 Sep 2023 08:51:26 -0300	[thread overview]
Message-ID: <ZPhnvqmvdeBMzafd@nvidia.com> (raw)
In-Reply-To: <9a4ddb8c-a48a-67b0-b8ad-428ee936454e@kaod.org>

On Wed, Sep 06, 2023 at 10:55:26AM +0200, Cédric Le Goater wrote:

> > +	WARN_ON(node);
> > +	log_addr_space_size = ilog2(total_ranges_len);
> > +	if (log_addr_space_size <
> > +	    (MLX5_CAP_ADV_VIRTUALIZATION(mdev, pg_track_log_min_addr_space)) ||
> > +	    log_addr_space_size >
> > +	    (MLX5_CAP_ADV_VIRTUALIZATION(mdev, pg_track_log_max_addr_space))) {
> > +		err = -EOPNOTSUPP;
> > +		goto out;
> > +	}
> 
> 
> We are seeing an issue with dirty page tracking when doing migration
> of an OVMF VM guest. The vfio-pci variant driver for the MLX5 VF
> device complains when dirty page tracking is initialized from QEMU :
> 
>   qemu-kvm: 0000:b1:00.2: Failed to start DMA logging, err -95 (Operation not supported)
> 
> The 64-bit computed range is  :
> 
>   vfio_device_dirty_tracking_start nr_ranges 2 32:[0x0 - 0x807fffff], 64:[0x100000000 - 0x3838000fffff]
> 
> which seems to be too large for the HW. AFAICT, the MLX5 HW has a 42
> bits address space limitation for dirty tracking (min is 12). Is it a
> FW tunable or a strict limitation ?

It would be good to explain where this is coming from, all devices
need to make some decision on what address space ranges to track and I
would say 2^42 is already pretty generous limit..

Can we go the other direction and reduce the ranges qemu is interested
in?

Jason

  parent reply	other threads:[~2023-09-06 11:51 UTC|newest]

Thread overview: 21+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-09-08 18:34 [PATCH V7 vfio 00/10] Add device DMA logging support for mlx5 driver Yishai Hadas
2022-09-08 18:34 ` [PATCH V7 vfio 01/10] net/mlx5: Introduce ifc bits for page tracker Yishai Hadas
2022-09-08 18:34 ` [PATCH V7 vfio 02/10] net/mlx5: Query ADV_VIRTUALIZATION capabilities Yishai Hadas
2022-09-08 18:34 ` [PATCH V7 vfio 03/10] vfio: Introduce DMA logging uAPIs Yishai Hadas
2022-09-08 18:34 ` [PATCH V7 vfio 04/10] vfio: Add an IOVA bitmap support Yishai Hadas
2022-09-08 18:34 ` [PATCH V7 vfio 05/10] vfio: Introduce the DMA logging feature support Yishai Hadas
2022-09-08 18:34 ` [PATCH V7 vfio 06/10] vfio/mlx5: Init QP based resources for dirty tracking Yishai Hadas
2022-09-08 18:34 ` [PATCH V7 vfio 07/10] vfio/mlx5: Create and destroy page tracker object Yishai Hadas
2023-09-06  8:55   ` Cédric Le Goater
2023-09-06  9:48     ` Yishai Hadas
2023-09-06 11:51     ` Jason Gunthorpe [this message]
2023-09-06 12:08       ` Joao Martins
2023-09-07  9:56       ` Cédric Le Goater
2023-09-07 10:51         ` Joao Martins
2023-09-07 12:16           ` Cédric Le Goater
2023-09-07 16:33             ` Joao Martins
2023-09-07 17:34               ` Cédric Le Goater
2022-09-08 18:34 ` [PATCH V7 vfio 08/10] vfio/mlx5: Report dirty pages from tracker Yishai Hadas
2022-09-08 18:34 ` [PATCH V7 vfio 09/10] vfio/mlx5: Manage error scenarios on tracker Yishai Hadas
2022-09-08 18:34 ` [PATCH V7 vfio 10/10] vfio/mlx5: Set the driver DMA logging callbacks Yishai Hadas
2022-09-08 20:17 ` [PATCH V7 vfio 00/10] Add device DMA logging support for mlx5 driver Alex Williamson

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=ZPhnvqmvdeBMzafd@nvidia.com \
    --to=jgg@nvidia$(echo .)com \
    --cc=alex.williamson@redhat$(echo .)com \
    --cc=avihaih@nvidia$(echo .)com \
    --cc=clg@kaod$(echo .)org \
    --cc=cohuck@redhat$(echo .)com \
    --cc=joao.m.martins@oracle$(echo .)com \
    --cc=kevin.tian@intel$(echo .)com \
    --cc=kuba@kernel$(echo .)org \
    --cc=kvm@vger$(echo .)kernel.org \
    --cc=leonro@nvidia$(echo .)com \
    --cc=maorg@nvidia$(echo .)com \
    --cc=netdev@vger$(echo .)kernel.org \
    --cc=saeedm@nvidia$(echo .)com \
    --cc=targupta@nvidia$(echo .)com \
    --cc=yishaih@nvidia$(echo .)com \
    /path/to/YOUR_REPLY

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