Oh yeah, I'll fix that. Thank you!
On Wed, Mar 29, 2023 at 2:52 PM Xuan Zhuo wrote:
>
> Is this a patch-set of QEMU? If yes, why are the email lists all kernel mail
> list without QEMU mail list?
>
> Thanks.
>
> On Wed, 29 Mar 2023 13:45:41 +0300, Andrew Melnychenko
> wrote:
> > This series of
Sorry, got issues with the internet during sending it. Now, all should be done.
On Fri, Dec 2, 2022 at 12:33 AM Michael S. Tsirkin wrote:
>
> On Thu, Dec 01, 2022 at 11:56:38PM +0200, Andrew Melnychenko wrote:
> > Added new offloads for TUN devices TUN_F_USO4 and TUN_F_USO6.
> > Technically they
Hi all,
On Thu, Sep 8, 2022 at 3:40 AM David Ahern wrote:
>
> On 9/7/22 6:50 AM, Andrew Melnychenko wrote:
> > diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
> > index 6d1a4bec2614..8e002419b4d5 100644
> > --- a/net/ipv4/udp_offload.c
> > +++ b/net/ipv4/udp_offload.c
> > @@ -387,7
Hi all,
On Thu, Sep 8, 2022 at 3:44 AM David Ahern wrote:
>
> On 9/7/22 6:50 AM, Andrew Melnychenko wrote:
> > Added new offloads for TUN devices TUN_F_USO4 and TUN_F_USO6.
> > Technically they enable NETIF_F_GSO_UDP_L4
> > (and only if USO4 & USO6 are set simultaneously).
> > It allows the
Reviewed-by: Andrew Melnychenko and...@daynix.com
On Fri, Aug 12, 2022 at 1:30 PM wrote:
>
> Hello:
>
> This patch was applied to netdev/net.git (master)
> by David S. Miller :
>
> On Thu, 11 Aug 2022 08:51:58 -0400 you wrote:
> > Using native endian-ness for device supplied fields is wrong
> >
ul, thanks!
On Thu, May 26, 2022 at 3:18 PM Andrew Melnichenko wrote:
>
> I'll check it, thank you!
>
> On Thu, May 26, 2022 at 9:56 AM Jason Wang wrote:
> >
> > On Tue, May 24, 2022 at 7:07 PM Andrew Melnichenko
> > wrote:
> > >
> > > Hi all,
&
I'll check it, thank you!
On Thu, May 26, 2022 at 9:56 AM Jason Wang wrote:
>
> On Tue, May 24, 2022 at 7:07 PM Andrew Melnichenko wrote:
> >
> > Hi all,
> >
> > The issue is that host segments packets between guests on the same host.
> > Tests show that
Hi all,
The issue is that host segments packets between guests on the same host.
Tests show that it happens because SKB_GSO_DODGY skb offload in
virtio_net_hdr_from_skb().
To do segmentation you need to remove SKB_GSO_DODGY or add SKB_GSO_PARTIAL
The solution with DODGY/PARTIAL offload looks like
Hi all,
Yes, I'll prepare a new commit later.
On Fri, Mar 4, 2022 at 10:08 AM Michael S. Tsirkin wrote:
>
> On Wed, Feb 23, 2022 at 03:15:28AM +0800, kernel test robot wrote:
> > Hi Andrew,
> >
> > Thank you for the patch! Perhaps something to improve:
> >
> > [auto build test WARNING on
Hi all,
On Wed, Feb 9, 2022 at 6:26 AM Jason Wang wrote:
>
>
> 在 2022/1/25 下午4:46, Andrew Melnychenko 写道:
> > Added TUNGETSUPPORTEDOFFLOADS that should allow
> > to get bits of supported offloads.
>
>
> So we don't use dedicated ioctls in the past, instead, we just probing
> by checking the
On Wed, Feb 9, 2022 at 6:39 AM Jason Wang wrote:
>
>
> 在 2022/1/25 下午4:46, Andrew Melnychenko 写道:
> > Added support for USO4 and USO6, also added code for new ioctl
> > TUNGETSUPPORTEDOFFLOADS.
> > For now, to "enable" USO, it's required to set both USO4 and USO6
> > simultaneously.
> > USO
Hi all,
On Wed, Feb 9, 2022 at 6:41 AM Jason Wang wrote:
>
>
> 在 2022/1/25 下午4:47, Andrew Melnychenko 写道:
> > Added new GSO type for USO: VIRTIO_NET_HDR_GSO_UDP_L4.
> > Feature VIRTIO_NET_F_HOST_USO allows to enable NETIF_F_GSO_UDP_L4.
> > Separated VIRTIO_NET_F_GUEST_USO4 &
Hi all,
On Wed, Feb 9, 2022 at 7:41 AM Jason Wang wrote:
>
>
> 在 2022/2/8 下午9:09, Andrew Melnichenko 写道:
> > Hi people,
> > Can you please review this series?
>
>
> Are there any performance number to demonstrate the difference?
>
> Thanks
>
Yeah, I've use
Hi all,
On Mon, Feb 14, 2022 at 12:09 AM Willem de Bruijn
wrote:
>
> > > > @@ -3113,13 +3270,14 @@ static int virtnet_probe(struct virtio_device
> > > > *vdev)
> > > > u16 max_queue_pairs;
> > > > int mtu;
> > > >
> > > > - /* Find if host supports multiqueue virtio_net
Hi all,
On Tue, Feb 8, 2022 at 10:59 PM Willem de Bruijn
wrote:
>
> On Tue, Feb 8, 2022 at 1:19 PM Andrew Melnychenko wrote:
> >
> > Now it's possible to control supported hashflows.
> > Added hashflow set/get callbacks.
> > Also, disabling RXH_IP_SRC/DST for TCP would disable then for UDP.
>
Hi all,
On Tue, Feb 8, 2022 at 10:55 PM Willem de Bruijn
wrote:
>
> On Tue, Feb 8, 2022 at 1:19 PM Andrew Melnychenko wrote:
> >
> > Added features for RSS hash report.
> > If hash is provided - it sets to skb.
> > Added checks if rss and/or hash are enabled together.
> >
> > Signed-off-by:
Hi all,
On Tue, Feb 8, 2022 at 10:37 PM Willem de Bruijn
wrote:
>
> On Tue, Feb 8, 2022 at 1:19 PM Andrew Melnychenko wrote:
> >
> > Added features for RSS.
> > Added initialization, RXHASH feature and ethtool ops.
> > By default RSS/RXHASH is disabled.
> > Virtio RSS "IPv6 extensions" hashes
Hi people,
Can you please review this series?
On Wed, Jan 26, 2022 at 10:32 AM Yuri Benditovich
wrote:
>
> On Wed, Jan 26, 2022 at 9:54 AM Xuan Zhuo wrote:
> >
> > On Tue, 25 Jan 2022 10:46:57 +0200, Andrew Melnychenko
> > wrote:
> > > Added new offloads for TUN devices TUN_F_USO4 and
Hi all,
> e.g RXH_VLAN with port hash?
> Any way to merge the two switch? The code is hard to be reviewed anyhow.
I'll refactor virtnet_set_hashflow.
> I think it's better to use VIRTIO_NET_HASH_REPORT_NONE here.
Yes, I'll fix that.
On Tue, Jan 11, 2022 at 6:33 AM Jason Wang wrote:
>
>
> 在
Hi all.
> I think we should make RSS depend on CTRL_VQ.
> Need to depend on CTRL_VQ here.
I'll fix that.
> Any reason to initialize RSS feature here not the init_default_rss()?
init_default_rss() initializes virtio_net_ctrl_rss structure only, I
think it's a good idea not to mix field
Hi all
> Is this correct if both mergeable_rx_bufs and hash_report are set?
Yes, there is a similar code in qemu.
> Can we simply do virtio_cread_feature(vdev, VIRTIO_NET_F_MQ |
> VIRTIO_NET_F_RSS, ...) ?
No, VIRTIO_NET_F_* is bit offset - so in the end "1 <<
(VIRTIO_NET_F_MQ |
On Sun, Oct 31, 2021 at 5:33 PM Willem de Bruijn
wrote:
>
> On Sun, Oct 31, 2021 at 1:00 AM Andrew Melnychenko wrote:
> >
> > Added features for RSS and RSS hash report.
> > Added initialization, RXHASH feature and ethtool ops.
> > By default RSS/RXHASH is disabled.
> > Added ethtools ops to set
On Mon, Nov 1, 2021 at 10:40 AM Michael S. Tsirkin wrote:
>
> On Sun, Oct 31, 2021 at 06:59:56AM +0200, Andrew Melnychenko wrote:
> > The header v1 provides additional info about RSS.
> > Added changes to computing proper header length.
> > In the next patches, the header may contain RSS hash
On Mon, Nov 1, 2021 at 10:44 AM Michael S. Tsirkin wrote:
>
> On Sun, Oct 31, 2021 at 06:59:57AM +0200, Andrew Melnychenko wrote:
> > Now minimal virtual header length is may include the entire v1 header
> > if the hash report were populated.
> >
> > Signed-off-by: Andrew Melnychenko
>
> subject
Hi guys,
Can you please review possible virtio-net driver RSS support?
Do you have any comments or proposals?
On Wed, Aug 18, 2021 at 8:55 PM Andrew Melnychenko
wrote:
> This series of RFC patches for comments and additional proposals.
>
> Virtio-net supports "hardware" RSS with toeplitz key.
>
>
> Description of problem:
> Guest get 'Call Trace' when loading module "virtio_console" and unloading
> it frequently
>
>
> Version-Release number of selected component (if applicable):
> Guest
> kernel-4.18.0-167.el8.x86_64
> seabios-bin-1.11.1-4.module+el8.1.0+4066+0f1aadab.noarch
26 matches
Mail list logo