> From: Eugenio Perez Martin
> Sent: Wednesday, May 11, 2022 3:44 PM
>
> This is a proposal to restore the state of the vhost-vdpa device at the
> destination after a live migration. It uses as many available features both
> from the device and from qemu as possible so we keep the communication
Hi Gautam,
Please fix your email client to have right response format.
Otherwise, it will be confusing for the rest and us to follow the conversation.
More below.
> From: Gautam Dawar
> Sent: Friday, May 13, 2022 1:48 PM
> > Our proposal diverge in step 7: Instead of enabling *all* the
> > vir
> From: Xie Yongji
> Sent: Monday, May 16, 2022 2:04 AM
>
> Introduce a device object for vdpa management device to control its
> lifecycle.
Why is this needed?
What is the limitation of current approach that requires new device for mgmtdev?
The primary motivation is missing in the commit log
> From: Eugenio Perez Martin
> Sent: Monday, May 16, 2022 4:51 AM
>
> On Fri, May 13, 2022 at 8:25 PM Parav Pandit wrote:
> >
> > Hi Gautam,
> >
> > Please fix your email client to have right response format.
> > Otherwise, it will be confusing for the rest and us to follow the
> conversation.
Hi Greg, Yongji,
> From: Yongji Xie
> Sent: Tuesday, May 17, 2022 3:25 AM
>
> On Tue, May 17, 2022 at 4:06 AM Parav Pandit wrote:
> >
> >
> >
> > > From: Xie Yongji
> > > Sent: Monday, May 16, 2022 2:04 AM
> > >
> > > Introduce a device object for vdpa management device to control its
> > > li
> From: gre...@linuxfoundation.org
> Sent: Tuesday, May 17, 2022 9:54 AM
>
> On Tue, May 17, 2022 at 12:21:03PM +, Parav Pandit wrote:
> > Hi Greg, Yongji,
> >
> > > From: Yongji Xie
> > > Sent: Tuesday, May 17, 2022 3:25 AM
> > >
> > > On Tue, May 17, 2022 at 4:06 AM Parav Pandit
> wrote
> From: Jason Wang
> Sent: Monday, May 16, 2022 11:05 PM
> >> Although it's a longer route, I'd very much prefer an in-band virtio
> >> way to perform it rather than a linux/vdpa specific. It's one of the
> >> reasons I prefer the CVQ behavior over a vdpa specific ioctl.
> >>
> > What is the in-b
> From: Eugenio Perez Martin
> Sent: Tuesday, May 17, 2022 4:12 AM
> > 2. Each VQ enablement one at a time, requires constant steering update
> > for the VQ While this information is something already known. Trying to
> reuse brings a callback result in this in-efficiency.
> > So better to sta
> From: Jason Wang
> Sent: Wednesday, May 18, 2022 4:32 AM
>
> 在 2022/5/18 07:03, Parav Pandit 写道:
> >>> And regarding vduse_dev_release() and existing empty release
> >>> function,
> >> they can be dynamically allocated.
> >>> This is because they are really the struct device.
> >> I do not und
> From: Jason Wang
> Sent: Sunday, May 22, 2022 11:41 PM
> To: Parav Pandit
> Cc: gre...@linuxfoundation.org; Yongji Xie ;
> m...@redhat.com; lingshan@intel.com; Eli Cohen ;
> virtualization@lists.linux-foundation.org
> Subject: Re: [PATCH v2 2/3] vdpa: Add a device object for vdpa managemen
> From: Eugenio Pérez
> Sent: Thursday, May 26, 2022 8:44 AM
> Implement stop operation for vdpa_sim devices, so vhost-vdpa will offer
>
> that backend feature and userspace can effectively stop the device.
>
>
>
> This is a must before get virtqueue indexes (base) for live migration,
>
>
> From: Jason Wang
> Sent: Sunday, May 29, 2022 11:39 PM
>
> On Fri, May 27, 2022 at 6:56 PM Michael S. Tsirkin wrote:
> >
> > On Thu, May 26, 2022 at 12:54:32PM +, Parav Pandit wrote:
> > >
> > >
> > > > From: Eugenio Pérez
> > > > Sent: Thursday, May 26, 2022 8:44 AM
> > >
> > > > Implem
> From: Eugenio Perez Martin
> Sent: Friday, May 27, 2022 3:55 AM
>
> On Fri, May 27, 2022 at 4:26 AM Jason Wang wrote:
> >
> > On Thu, May 26, 2022 at 8:54 PM Parav Pandit wrote:
> > >
> > >
> > >
> > > > From: Eugenio Pérez
> > > > Sent: Thursday, May 26, 2022 8:44 AM
> > >
> > > > Impleme
> From: Jason Wang
> Sent: Tuesday, May 31, 2022 10:42 PM
>
> Well, the ability to query the virtqueue state was proposed as another
> feature (Eugenio, please correct me). This should be sufficient for making
> virtio-net to be live migrated.
>
The device is stopped, it won't answer to this s
> From: Eugenio Perez Martin
> Sent: Wednesday, June 1, 2022 7:15 AM
>
> On Wed, Jun 1, 2022 at 1:03 PM Michael S. Tsirkin wrote:
> >
> > On Thu, May 26, 2022 at 02:43:37PM +0200, Eugenio Pérez wrote:
> > > The ioctl adds support for stop the device from userspace.
> > >
> > > Signed-off-by: E
> From: Eugenio Perez Martin
> Sent: Wednesday, June 1, 2022 5:50 AM
>
> On Tue, May 31, 2022 at 10:19 PM Parav Pandit wrote:
> >
> >
> > > From: Jason Wang
> > > Sent: Sunday, May 29, 2022 11:39 PM
> > >
> > > On Fri, May 27, 2022 at 6:56 PM Michael S. Tsirkin
> wrote:
> > > >
> > > > On Th
> From: Jason Wang
> Sent: Wednesday, June 1, 2022 10:00 PM
>
> On Thu, Jun 2, 2022 at 2:58 AM Parav Pandit wrote:
> >
> >
> > > From: Jason Wang
> > > Sent: Tuesday, May 31, 2022 10:42 PM
> > >
> > > Well, the ability to query the virtqueue state was proposed as
> > > another feature (Eugeni
> From: Dawar, Gautam
> Sent: Wednesday, June 8, 2022 6:30 AM
> To: Jason Wang
> Cc: netdev ; linux-net-drivers (AMD-Xilinx) net-driv...@amd.com>; Anand, Harpreet ;
> Michael S. Tsirkin ; Zhu Lingshan
> ; Xie Yongji ; Eli
> Cohen ; Parav Pandit ; Si-Wei Liu wei@oracle.com>; Stefano Garzar
> From: Yongji Xie
> Sent: Wednesday, June 8, 2022 9:26 AM
>
> On Wed, Jun 8, 2022 at 8:52 PM Michael S. Tsirkin wrote:
> >
> > On Tue, Apr 26, 2022 at 10:07:38AM +0200, Greg KH wrote:
> > > On Tue, Apr 26, 2022 at 03:36:56PM +0800, Xie Yongji wrote:
> > > > The control device has no drvdata.
vduse devices are not backed by any real devices such as PCI. Hence it
doesn't have any parent device linked to it.
Kernel driver model in [1] suggests to avoid an empty device
release callback.
Hence tie the mgmtdevice object's life cycle to an allocate dummy struct
device instead of static one.
> From: Jason Wang
> Sent: Thursday, June 9, 2022 3:19 AM
[..]
> > > This is to avoid side-effects as noted in
> > > https://bugzilla.kernel.org/show_bug.cgi?id=213179 caused by
> > > deleting the vdpa device when it is being used.
> > > >
> > User should be able to delete the device anytime.
> From: Yongji Xie
> Sent: Monday, June 13, 2022 5:54 AM
>
> On Mon, Jun 13, 2022 at 2:02 AM Parav Pandit wrote:
> >
> > vduse devices are not backed by any real devices such as PCI. Hence it
> > doesn't have any parent device linked to it.
> >
> > Kernel driver model in [1] suggests to avoid
vduse devices are not backed by any real devices such as PCI. Hence it
doesn't have any parent device linked to it.
Kernel driver model in [1] suggests to avoid an empty device
release callback.
Hence tie the mgmtdevice object's life cycle to an allocate dummy struct
device instead of static one.
> From: Zhu Lingshan
> Sent: Monday, June 13, 2022 6:17 AM
>
> Users may want to query the config space of a vDPA device, to choose a
> appropriate one for a certain guest. This means the users need to read the
> config space before FEATURES_OK, and the existence of config space
> contents doe
> From: Zhu Lingshan
> Sent: Monday, June 13, 2022 6:17 AM
> To: jasow...@redhat.com; m...@redhat.com
> Cc: virtualization@lists.linux-foundation.org; net...@vger.kernel.org; Parav
> Pandit ; xieyon...@bytedance.com;
> gautam.da...@amd.com; Zhu Lingshan
> Subject: [PATCH V2 5/6] vDPA: answer n
> From: Zhu Lingshan
> Sent: Monday, June 13, 2022 6:17 AM
>
> This commit adds a new vDPA netlink attribution
> VDPA_ATTR_VDPA_DEV_SUPPORTED_FEATURES. Userspace can query
> features of vDPA devices through this new attr.
>
> Signed-off-by: Zhu Lingshan
> ---
> drivers/vdpa/vdpa.c | 1
> From: Zhu Lingshan
> Sent: Monday, June 13, 2022 6:17 AM
> device
>
> This commit adds a new vDPA netlink attribution
> VDPA_ATTR_VDPA_DEV_SUPPORTED_FEATURES. Userspace can query
> features of vDPA devices through this new attr.
>
> Signed-off-by: Zhu Lingshan
> ---
> drivers/vdpa/vdpa.c
> From: Zhu, Lingshan
> Sent: Monday, June 13, 2022 10:53 PM
>
>
> On 6/14/2022 4:42 AM, Parav Pandit wrote:
> >
> >> From: Zhu Lingshan
> >> Sent: Monday, June 13, 2022 6:17 AM
> >> device
> >>
> >> This commit adds a new vDPA netlink attribution
> >> VDPA_ATTR_VDPA_DEV_SUPPORTED_FEATURES.
> From: Zhu, Lingshan
> Sent: Monday, June 13, 2022 10:33 PM
>
>
> On 6/14/2022 4:36 AM, Parav Pandit wrote:
> >
> >> From: Zhu Lingshan
> >> Sent: Monday, June 13, 2022 6:17 AM
> >> To: jasow...@redhat.com; m...@redhat.com
> >> Cc: virtualization@lists.linux-foundation.org;
> >> net...@vger.
> From: Jason Wang
> Sent: Wednesday, June 1, 2022 11:54 PM
>
> On Thu, Jun 2, 2022 at 10:59 AM Parav Pandit wrote:
> >
> >
> > > From: Jason Wang
> > > Sent: Wednesday, June 1, 2022 10:00 PM
> > >
> > > On Thu, Jun 2, 2022 at 2:58 AM Parav Pandit wrote:
> > > >
> > > >
> > > > > From: Jaso
> From: Jason Wang
> Sent: Tuesday, June 14, 2022 9:29 PM
>
> Well, it's an example of how vDPA is implemented. I think we agree that for
> vDPA, vendors have the flexibility to implement their perferrable datapath.
>
Yes for the vdpa level and for the virtio level.
> >
> > I remember few month
> From: Jason Wang
> Sent: Thursday, June 16, 2022 9:15 PM
>
> On Fri, Jun 17, 2022 at 3:36 AM Parav Pandit wrote:
> >
> >
> > > From: Jason Wang
> > > Sent: Tuesday, June 14, 2022 9:29 PM
> > >
> > > Well, it's an example of how vDPA is implemented. I think we agree
> > > that for vDPA, vend
> From: Zhu Lingshan
> Sent: Friday, July 1, 2022 9:28 AM
>
> This commit adds a new vDPA netlink attribution
> VDPA_ATTR_VDPA_DEV_SUPPORTED_FEATURES. Userspace can query
> features of vDPA devices through this new attr.
>
> Fixes: a64917bc2e9b vdpa: (Provide interface to read driver feature)
> From: Zhu Lingshan
> Sent: Friday, July 1, 2022 9:28 AM
> If VIRTIO_NET_F_MQ == 0, the virtio device should have one queue pair, so
> when userspace querying queue pair numbers, it should return mq=1 than
> zero.
>
> Function vdpa_dev_net_config_fill() fills the attributions of the vDPA
> de
> From: Zhu Lingshan
> Sent: Friday, July 1, 2022 9:28 AM
>
> Users may want to query the config space of a vDPA device, to choose a
> appropriate one for a certain guest. This means the users need to read the
> config space before FEATURES_OK, and the existence of config space
> contents does
> From: Zhu Lingshan
> Sent: Friday, July 1, 2022 9:28 AM
>
> This commit fixes spars warnings: cast to restricted __le16 in function
> vdpa_dev_net_config_fill() and
> vdpa_fill_stats_rec()
>
Missing fixes tag.
But I fail to understand the warning.
config.status is le16, and API used is to c
> From: Jason Wang
> Sent: Monday, July 4, 2022 12:47 AM
>
>
> 在 2022/7/2 06:02, Parav Pandit 写道:
> >
> >> From: Zhu Lingshan
> >> Sent: Friday, July 1, 2022 9:28 AM
> >>
> >> This commit adds a new vDPA netlink attribution
> >> VDPA_ATTR_VDPA_DEV_SUPPORTED_FEATURES. Userspace can query
> feat
> From: Zhu, Lingshan
> Sent: Tuesday, July 5, 2022 3:59 AM
>
>
> On 7/4/2022 8:53 PM, Parav Pandit wrote:
> >> From: Jason Wang
> >> Sent: Monday, July 4, 2022 12:47 AM
> >>
> >>
> >> 在 2022/7/2 06:02, Parav Pandit 写道:
> From: Zhu Lingshan
> Sent: Friday, July 1, 2022 9:28 AM
> >>>
> From: Zhu, Lingshan
> Sent: Tuesday, July 5, 2022 12:56 PM
> > Both can be queried simultaneously. Each will return their own feature bits
> using same attribute.
> > It wont lead to the race.
> How? It is just a piece of memory, [attr], do you see locks in
> nla_put_u64_64bit()? It is a ty
> From: Zhu, Lingshan
> Sent: Tuesday, July 5, 2022 10:25 PM
> 1. When migrate the VM to a node which has a more resourceful device. If
> the source side device does not have MQ, RSS or TSO feature, the vDPA
> device assigned to the VM does not have MQ, RSS or TSO as well. When
> migrating to a
> From: Zhu, Lingshan
> Sent: Friday, July 8, 2022 2:25 AM
>
>
> On 7/2/2022 6:18 AM, Parav Pandit wrote:
> >> From: Zhu Lingshan
> >> Sent: Friday, July 1, 2022 9:28 AM
> >>
> >> This commit fixes spars warnings: cast to restricted __le16 in
> >> function
> >> vdpa_dev_net_config_fill() and
> From: Zhu, Lingshan
> Sent: Friday, July 8, 2022 2:16 AM
>
> On 7/2/2022 6:02 AM, Parav Pandit wrote:
> >
> >> From: Zhu Lingshan
> >> Sent: Friday, July 1, 2022 9:28 AM
> >>
> >> This commit adds a new vDPA netlink attribution
> >> VDPA_ATTR_VDPA_DEV_SUPPORTED_FEATURES. Userspace can query
> From: Zhu, Lingshan
> Sent: Friday, July 8, 2022 2:21 AM
>
>
> On 7/2/2022 6:07 AM, Parav Pandit wrote:
> >
> >> From: Zhu Lingshan
> >> Sent: Friday, July 1, 2022 9:28 AM
> >> If VIRTIO_NET_F_MQ == 0, the virtio device should have one queue
> >> pair, so when userspace querying queue pair n
> From: Zhu, Lingshan
> Sent: Sunday, July 10, 2022 10:30 PM
> > Showing max_vq_pairs of 1 even when _MQ is not negotiated, incorrectly
> says that max_vq_pairs is exposed to the guest, but it is not offered.
> >
> > So, please fix the iproute2 to not print max_vq_pairs when it is not
> returned
> From: Zhu, Lingshan
> Sent: Tuesday, July 12, 2022 11:03 PM
>
>
> On 7/13/2022 12:48 AM, Parav Pandit wrote:
> >> From: Zhu, Lingshan
> >> Sent: Sunday, July 10, 2022 10:30 PM
> >>> Showing max_vq_pairs of 1 even when _MQ is not negotiated,
> >>> incorrectly
> >> says that max_vq_pairs is ex
> From: Zhu Lingshan
> Sent: Friday, July 22, 2022 7:53 AM
>
> This commit adds a new vDPA netlink attribution
> VDPA_ATTR_VDPA_DEV_SUPPORTED_FEATURES. Userspace can query
> features of vDPA devices through this new attr.
>
> Signed-off-by: Zhu Lingshan
> ---
> drivers/vdpa/vdpa.c | 13
> From: Zhu Lingshan
> Sent: Friday, July 22, 2022 7:53 AM
>
> If VIRTIO_NET_F_MQ == 0, the virtio device should have one queue pair, so
> when userspace querying queue pair numbers, it should return mq=1 than
> zero.
>
> Function vdpa_dev_net_config_fill() fills the attributions of the vDPA
> From: Zhu, Lingshan
> Sent: Saturday, July 23, 2022 7:24 AM
>
>
> On 7/22/2022 9:12 PM, Parav Pandit wrote:
> >> From: Zhu Lingshan
> >> Sent: Friday, July 22, 2022 7:53 AM
> >>
> >> This commit adds a new vDPA netlink attribution
> >> VDPA_ATTR_VDPA_DEV_SUPPORTED_FEATURES. Userspace can q
> From: Zhu, Lingshan
> Sent: Saturday, July 23, 2022 7:27 AM
>
> On 7/6/2022 10:25 AM, Zhu, Lingshan wrote:
> >
> >
> > On 7/6/2022 1:01 AM, Parav Pandit wrote:
> >>> From: Zhu, Lingshan
> >>> Sent: Tuesday, July 5, 2022 12:56 PM
> Both can be queried simultaneously. Each will return the
> From: Zhu, Lingshan
> Sent: Tuesday, July 26, 2022 7:03 AM
>
> On 7/24/2022 11:21 PM, Parav Pandit wrote:
> >
> >> From: Zhu, Lingshan
> >> Sent: Saturday, July 23, 2022 7:24 AM
> >>
> >>
> >> On 7/22/2022 9:12 PM, Parav Pandit wrote:
> From: Zhu Lingshan
> Sent: Friday, July 22, 2
> From: Michael S. Tsirkin
> Sent: Wednesday, July 13, 2022 1:27 AM
>
> On Fri, Jul 01, 2022 at 10:07:59PM +, Parav Pandit wrote:
> >
> >
> > > From: Zhu Lingshan
> > > Sent: Friday, July 1, 2022 9:28 AM
> > > If VIRTIO_NET_F_MQ == 0, the virtio device should have one queue
> > > pair, so
> From: Zhu, Lingshan
> Sent: Tuesday, July 12, 2022 11:46 PM
> > When the user space which invokes netlink commands, detects that _MQ
> is not supported, hence it takes max_queue_pair = 1 by itself.
> I think the kernel module have all necessary information and it is the only
> one which have pr
> From: Michael S. Tsirkin
> Sent: Tuesday, July 26, 2022 3:52 PM
>
> On Tue, Jul 26, 2022 at 03:56:32PM +, Parav Pandit wrote:
> >
> > > From: Zhu, Lingshan
> > > Sent: Tuesday, July 12, 2022 11:46 PM
> > > > When the user space which invokes netlink commands, detects that
> > > > _MQ
> >
> From: Michael S. Tsirkin
> Sent: Tuesday, July 26, 2022 3:49 PM
>
> On Tue, Jul 26, 2022 at 03:54:06PM +, Parav Pandit wrote:
> >
> > > From: Michael S. Tsirkin
> > > Sent: Wednesday, July 13, 2022 1:27 AM
> > >
> > > On Fri, Jul 01, 2022 at 10:07:59PM +, Parav Pandit wrote:
> > > >
> From: Zhu, Lingshan
> Sent: Tuesday, July 26, 2022 10:15 PM
>
> On 7/26/2022 11:56 PM, Parav Pandit wrote:
> >> From: Zhu, Lingshan
> >> Sent: Tuesday, July 12, 2022 11:46 PM
> >>> When the user space which invokes netlink commands, detects that
> _MQ
> >> is not supported, hence it takes max
> From: Zhu, Lingshan
> Sent: Tuesday, July 26, 2022 10:53 PM
>
> On 7/27/2022 10:17 AM, Parav Pandit wrote:
> >> From: Zhu, Lingshan
> >> Sent: Tuesday, July 26, 2022 10:15 PM
> >>
> >> On 7/26/2022 11:56 PM, Parav Pandit wrote:
> From: Zhu, Lingshan
> Sent: Tuesday, July 12, 2022 1
> From: Si-Wei Liu
> Sent: Tuesday, August 9, 2022 2:39 PM
> Currently it is not. Not a single patch nor this patch, but the context for
> the
> eventual goal is to allow XDP on a MTU=9000 link when guest users
> intentionally lower down MTU to 1500.
Which application benefit by having asymmetr
> From: Si-Wei Liu
> Sent: Tuesday, August 9, 2022 3:09 PM
> >> From: Si-Wei Liu
> >> Sent: Tuesday, August 9, 2022 2:39 PM Currently it is not. Not a
> >> single patch nor this patch, but the context for the eventual goal is
> >> to allow XDP on a MTU=9000 link when guest users intentionally lo
> From: Zhu, Lingshan
> Sent: Wednesday, July 27, 2022 2:02 AM
>
>
> On 7/26/2022 7:06 PM, Parav Pandit wrote:
> >> From: Zhu, Lingshan
> >> Sent: Tuesday, July 26, 2022 7:03 AM
> >>
> >> On 7/24/2022 11:21 PM, Parav Pandit wrote:
> From: Zhu, Lingshan
> Sent: Saturday, July 23, 2022
> From: Michael S. Tsirkin
> Sent: Tuesday, August 9, 2022 3:24 PM
>
> On Fri, Jul 22, 2022 at 07:53:06PM +0800, Zhu Lingshan wrote:
> > This commit adds a new vDPA netlink attribution
> > VDPA_ATTR_VDPA_DEV_SUPPORTED_FEATURES. Userspace can query
> features of
> > vDPA devices through this new a
> From: Michael S. Tsirkin
> Sent: Tuesday, August 9, 2022 3:36 PM
> > > After applying this commit, when MQ = 0, iproute2 output:
> > > $vdpa dev config show vdpa0
> > > vdpa0: mac 00:e8:ca:11:be:05 link up link_announce false
> > > max_vq_pairs 1 mtu 1500
> > >
> > No. We do not want to diverge
> From: Si-Wei Liu
> Sent: Tuesday, August 9, 2022 4:33 PM
>
> On 8/9/2022 12:18 PM, Parav Pandit wrote:
> >> From: Si-Wei Liu
> >> Sent: Tuesday, August 9, 2022 3:09 PM
> From: Si-Wei Liu
> Sent: Tuesday, August 9, 2022 2:39 PM Currently it is not. Not a
> single patch nor this
> From: Michael S. Tsirkin
> Sent: Tuesday, August 9, 2022 5:38 PM
[..]
> > > I think virtio-net driver doesn't differentiate MTU and MRU, in
> > > which case the receive buffer will be reduced to fit the 1500B
> > > payload size when mtu is lowered down to 1500 from 9000.
> > How? Driver reduced
> From: Michael S. Tsirkin
> Sent: Tuesday, August 9, 2022 6:26 PM
> To: Parav Pandit
> Cc: Si-Wei Liu ; Jason Wang
> ; Gavin Li ; Hemminger,
> Stephen ; davem
> ; virtualization foundation.org>; Virtio-Dev ;
> jesse.brandeb...@intel.com; alexander.h.du...@intel.com;
> kubak...@wp.pl; sridhar.sa
> From: Michael S. Tsirkin
> Sent: Wednesday, August 10, 2022 5:03 AM
> > >
> > > Should we make this depend on the vq reset ability maybe?
> >
> > The advantage of this is to keep TX working. Or we can use device
> > reset as a fallback if there's no vq reset.
> >
> > Thanks
>
> Device reset i
> From: Michael S. Tsirkin
> Sent: Wednesday, August 10, 2022 12:05 PM
>
> On Wed, Aug 10, 2022 at 04:00:08PM +, Parav Pandit wrote:
> >
> > > From: Michael S. Tsirkin
> > > Sent: Wednesday, August 10, 2022 5:03 AM
> > > > >
> > > > > Should we make this depend on the vq reset ability mayb
> From: Michael S. Tsirkin
> Sent: Wednesday, August 10, 2022 12:59 PM
>
> On Wed, Aug 10, 2022 at 04:22:41PM +, Parav Pandit wrote:
> >
> > > From: Michael S. Tsirkin
> > > Sent: Wednesday, August 10, 2022 12:05 PM
> > >
> > > On Wed, Aug 10, 2022 at 04:00:08PM +, Parav Pandit wrote:
> From: Zhu, Lingshan
> Sent: Monday, August 15, 2022 9:49 PM
>
> On 8/16/2022 2:15 AM, Si-Wei Liu wrote:
> >
> >
> > On 8/15/2022 2:26 AM, Zhu Lingshan wrote:
> >> This commit adds a new vDPA netlink attribution
> >> VDPA_ATTR_VDPA_DEV_SUPPORTED_FEATURES. Userspace can query
> features
> >> of
> From: Zhu Lingshan
> Sent: Monday, August 15, 2022 5:27 AM
>
> Some fields of virtio-net device config space are conditional on the feature
> bits, the spec says:
>
> "The mac address field always exists
> (though is only valid if VIRTIO_NET_F_MAC is set)"
>
> "max_virtqueue_pairs only exist
> From: Zhu, Lingshan
> Sent: Tuesday, August 16, 2022 12:19 AM
>
>
> On 8/16/2022 10:32 AM, Parav Pandit wrote:
> >> From: Zhu Lingshan
> >> Sent: Monday, August 15, 2022 5:27 AM
> >>
> >> Some fields of virtio-net device config space are conditional on the
> >> feature bits, the spec says:
>
> From: Jason Wang
> Sent: Thursday, August 18, 2022 12:19 AM
> On 8/16/2022 10:32 AM, Parav Pandit wrote:
> >> From: Zhu Lingshan
> >> Sent: Monday, August 15, 2022 5:27 AM
> >>
> >> Some fields of virtio-net device config space are conditional on
> >> the feature bits
> From: Gavin Li
> Sent: Friday, August 19, 2022 10:49 AM
>
> This small series contains two patches that improves virtio netdevice
> performance for 9K mtu when GRO/ guest TSO is disabled.
>
> Gavin Li (2):
> virtio-net: introduce and use helper function for guest gso support
> checks
>
From: Si-Wei Liu
Sent: Friday, August 26, 2022 4:52 AM
> Sorry for the delay. Didn't notice as this thread was not addressed to my
> work email. Please copy to my work email if it needs my immediate attention.
Can you please setup your mail client to post plain text mail as required
> From: Si-Wei Liu
> Sent: Friday, August 26, 2022 2:05 PM
>
> > + /* If we can receive ANY GSO packets, we must allocate large ones.
> */
> > + if (mtu > ETH_DATA_LEN || guest_gso) {
> > + vi->big_packets = true;
> > + /* if the guest offload is offered by the device,
> From: Gavin Li
> Sent: Wednesday, August 31, 2022 5:03 AM
>
> Probe routine is already several hundred lines.
> Use helper function for guest gso support check.
>
> Signed-off-by: Gavin Li
> Reviewed-by: Gavi Teitz
> Reviewed-by: Parav Pandit
You missed the review by and ack by entries t
> From: Michael S. Tsirkin
> Sent: Wednesday, September 7, 2022 5:27 AM
>
> On Wed, Sep 07, 2022 at 04:08:54PM +0800, Gavin Li wrote:
> >
> > On 9/7/2022 1:31 PM, Michael S. Tsirkin wrote:
> > > External email: Use caution opening links or attachments
> > >
> > >
> > > On Thu, Sep 01, 2022 at 0
> From: Michael S. Tsirkin
> Sent: Wednesday, September 7, 2022 10:30 AM
[..]
> > > actually how does this waste space? Is this because your device does
> > > not have INDIRECT?
> > VQ is 256 entries deep.
> > Driver posted total of 256 descriptors.
> > Each descriptor points to a page of 4K.
>
> From: Michael S. Tsirkin
> Sent: Wednesday, September 7, 2022 10:40 AM
>
> On Wed, Sep 07, 2022 at 02:33:02PM +, Parav Pandit wrote:
> >
> > > From: Michael S. Tsirkin
> > > Sent: Wednesday, September 7, 2022 10:30 AM
> >
> > [..]
> > > > > actually how does this waste space? Is this bec
> From: Michael S. Tsirkin
> Sent: Wednesday, September 7, 2022 2:16 PM
>
> On Wed, Sep 07, 2022 at 04:12:47PM +, Parav Pandit wrote:
> >
> > > From: Michael S. Tsirkin
> > > Sent: Wednesday, September 7, 2022 10:40 AM
> > >
> > > On Wed, Sep 07, 2022 at 02:33:02PM +, Parav Pandit wrote:
> From: Michael S. Tsirkin
> Sent: Wednesday, September 7, 2022 3:12 PM
> > Because of shallow queue of 16 entries deep.
>
> but why is the queue just 16 entries?
I explained the calculation in [1] about 16 entries.
[1]
https://lore.kernel.org/netdev/ph0pr12mb54812ec7f4711c1ea4caa119dc...@ph
> From: Michael S. Tsirkin
> Sent: Wednesday, September 7, 2022 3:24 PM
>
> On Wed, Sep 07, 2022 at 07:18:06PM +, Parav Pandit wrote:
> >
> > > From: Michael S. Tsirkin
> > > Sent: Wednesday, September 7, 2022 3:12 PM
> >
> > > > Because of shallow queue of 16 entries deep.
> > >
> > > but
> From: Michael S. Tsirkin
> Sent: Wednesday, September 7, 2022 3:36 PM
>
> On Wed, Sep 07, 2022 at 07:27:16PM +, Parav Pandit wrote:
> >
> > > From: Michael S. Tsirkin
> > > Sent: Wednesday, September 7, 2022 3:24 PM
> > >
> > > On Wed, Sep 07, 2022 at 07:18:06PM +, Parav Pandit wrote
> From: Michael S. Tsirkin
> Sent: Wednesday, September 7, 2022 3:38 PM
>
> and if possible a larger ring. 1k?
What do you expect to see here for which test report should be added to commit
log?
What is special about 1k vs 512, 128 and 2k? is 1K default for some
configuration?
__
> From: Michael S. Tsirkin
> Sent: Wednesday, September 7, 2022 3:36 PM
>
> (c) replace mtu = 0 with sensibly not calling the function when mtu is
> unknown.
Even when mtu is zero, virtnet_set_big_packets() must be called to act on the
gso bits.
Currently handling by virtnet_set_big_packets()
> From: Si-Wei Liu
> Sent: Wednesday, September 7, 2022 5:40 PM
>
>
> On 9/7/2022 12:51 PM, Parav Pandit wrote:
> >> And I'd like commit log to include results of perf testing
> >> - with indirect feature on
> > Which device do you suggest using for this test?
> >
> You may use software vhost-n
Hi Jason,
> From: Jason Wang
> Sent: Thursday, September 15, 2022 4:51 AM
> To: m...@redhat.com; jasow...@redhat.com
> Cc: Eli Cohen ; si-wei@oracle.com; Parav Pandit
> ; wuzongy...@linux.alibaba.com;
> virtualization@lists.linux-foundation.org; linux-ker...@vger.kernel.org;
> epere...@redhat
> From: Michael S. Tsirkin
> Sent: Thursday, September 22, 2022 5:35 AM
>
> On Thu, Sep 01, 2022 at 05:10:38AM +0300, Gavin Li wrote:
> > Currently add_recvbuf_big() allocates MAX_SKB_FRAGS segments for big
> > packets even when GUEST_* offloads are not present on the device.
> > However, if gu
> From: Michael S. Tsirkin
> Sent: Thursday, September 22, 2022 5:27 AM
> > >
> > > And I'd like commit log to include results of perf testing
> > > - with indirect feature on
> > Which device do you suggest using for this test?
>
> AFAIK most devices support INDIRECT, e.g. don't nvidia cards
> From: Michael S. Tsirkin
> Sent: Thursday, September 22, 2022 6:15 AM
>
> It's nitpicking to be frank. v6 arrived while I was traveling and I didn't
> notice it.
> I see Jason acked that so I guess I will just apply as is. Do you ack v6 too?
>
Yes. I reviewed it. Gavin added reviewed-by.
Th
> From: Jakub Kicinski
> Sent: Thursday, September 22, 2022 6:05 PM
>
> On Thu, 22 Sep 2022 06:14:59 -0400 Michael S. Tsirkin wrote:
> > It's nitpicking to be frank. v6 arrived while I was traveling and I
> > didn't notice it. I see Jason acked that so I guess I will just apply
> > as is.
>
> O
201 - 290 of 290 matches
Mail list logo
