[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <CACGkMEtCasGmTNBZxfu2gJfSMCfD1jtKGH3cb9HCPXFP7YACpQ@mail.gmail.com>
Date: Fri, 13 Oct 2023 11:04:45 +0800
From: Jason Wang <jasowang@...hat.com>
To: Si-Wei Liu <si-wei.liu@...cle.com>
Cc: mst@...hat.com, eperezma@...hat.com, xuanzhuo@...ux.alibaba.com,
dtatulea@...dia.com, virtualization@...ts.linux-foundation.org,
linux-kernel@...r.kernel.org
Subject: Re: [PATCH 4/4] vdpa/mlx5: implement .reset_map driver op
On Tue, Oct 10, 2023 at 5:05 PM Si-Wei Liu <si-wei.liu@...cle.com> wrote:
>
> Since commit 6f5312f80183 ("vdpa/mlx5: Add support for running with
> virtio_vdpa"), mlx5_vdpa starts with preallocate 1:1 DMA MR at device
> creation time. This 1:1 DMA MR will be implicitly destroyed while
> the first .set_map call is invoked, in which case callers like
> vhost-vdpa will start to set up custom mappings. When the .reset
> callback is invoked, the custom mappings will be cleared and the 1:1
> DMA MR will be re-created.
>
> In order to reduce excessive memory mapping cost in live migration,
> it is desirable to decouple the vhost-vdpa IOTLB abstraction from
> the virtio device life cycle, i.e. mappings can be kept around intact
> across virtio device reset. Leverage the .reset_map callback, which
> is meant to destroy the regular MR on the given ASID and recreate the
> initial DMA mapping. That way, the device .reset op can run free from
> having to maintain and clean up memory mappings by itself.
>
> The cvq mapping also needs to be cleared if is in the given ASID.
>
> Co-developed-by: Dragos Tatulea <dtatulea@...dia.com>
> Signed-off-by: Dragos Tatulea <dtatulea@...dia.com>
> Signed-off-by: Si-Wei Liu <si-wei.liu@...cle.com>
I wonder if the simulator suffers from the exact same issue. If yes,
let's fix the simulator as well?
Thanks
Powered by blists - more mailing lists