Question:
How will libvirt (as an example) work with this change. In the
existing semantic of libvirt profile the "on" means "on if possible"
and using existing profile after qemu update will still use "on" with
meaning "force"?
Typically this is solved by machine type - if libvirt uses
On Sun, Apr 28, 2024 at 10:21 AM Akihiko Odaki wrote:
>
> DEFINE_PROP_ON_OFF_AUTO_BIT64() corresponds to DEFINE_PROP_ON_OFF_AUTO()
> as DEFINE_PROP_BIT64() corresponds to DEFINE_PROP_BOOL(). The difference
> is that DEFINE_PROP_ON_OFF_AUTO_BIT64() exposes OnOffAuto instead of
> bool.
>
>
On Tue, Apr 16, 2024 at 9:54 AM Akihiko Odaki wrote:
>
> On 2024/04/16 13:00, Jason Wang wrote:
> > On Mon, Apr 15, 2024 at 10:05 PM Yuri Benditovich
> > wrote:
> >>
> >> On Wed, Apr 3, 2024 at 2:11 PM Akihiko Odaki
> >> wrote:
>
On Wed, Apr 3, 2024 at 2:11 PM Akihiko Odaki wrote:
>
> vhost requires eBPF for RSS. When eBPF is not available, virtio-net
> implicitly disables RSS even if the user explicitly requests it. Return
> an error instead of implicitly disabling RSS if RSS is requested but not
> available.
>
>
On Tue, Apr 16, 2024 at 10:14 AM Jason Wang wrote:
>
> On Tue, Apr 16, 2024 at 1:43 PM Yuri Benditovich
> wrote:
> >
> > On Tue, Apr 16, 2024 at 7:00 AM Jason Wang wrote:
> > >
> > > On Mon, Apr 15, 2024 at 10:05 PM Yuri Benditovich
> > > wrote
On Tue, Apr 16, 2024 at 7:00 AM Jason Wang wrote:
>
> On Mon, Apr 15, 2024 at 10:05 PM Yuri Benditovich
> wrote:
> >
> > On Wed, Apr 3, 2024 at 2:11 PM Akihiko Odaki
> > wrote:
> > >
> > > vhost requires eBPF for RSS. When eBPF is not available,
On Wed, Apr 3, 2024 at 2:11 PM Akihiko Odaki wrote:
>
> vhost requires eBPF for RSS. When eBPF is not available, virtio-net
> implicitly disables RSS even if the user explicitly requests it. Return
> an error instead of implicitly disabling RSS if RSS is requested but not
> available.
>
>
On Wed, Apr 3, 2024 at 2:12 PM Akihiko Odaki wrote:
>
> calculate_rss_hash() was using hash value 0 to tell if it calculated
> a hash, but the hash value may be 0 on a rare occasion. Have a
> distinct bool value for correctness.
This is interesting question whether in reality the hash value
On Mon, Apr 8, 2024 at 10:57 AM Akihiko Odaki wrote:
>
> On 2024/04/08 16:54, Yuri Benditovich wrote:
> > On Mon, Apr 8, 2024 at 10:42 AM Akihiko Odaki
> > wrote:
> >>
> >> On 2024/04/08 16:40, Yuri Benditovich wrote:
> >>> On Mon, Ap
On Mon, Apr 8, 2024 at 10:42 AM Akihiko Odaki wrote:
>
> On 2024/04/08 16:40, Yuri Benditovich wrote:
> > On Mon, Apr 8, 2024 at 4:30 AM Akihiko Odaki
> > wrote:
> >>
> >> On 2024/04/08 7:09, Yuri Benditovich wrote:
> >>> On Wed, Ap
On Mon, Apr 8, 2024 at 4:30 AM Akihiko Odaki wrote:
>
> On 2024/04/08 7:09, Yuri Benditovich wrote:
> > On Wed, Apr 3, 2024 at 2:12 PM Akihiko Odaki
> > wrote:
> >>
> >> The peer buffer is qualified with const and not meant to be modified.
> >
> &g
On Wed, Apr 3, 2024 at 2:12 PM Akihiko Odaki wrote:
>
> The peer buffer is qualified with const and not meant to be modified.
IMHO, this buffer is not so 'const' (although the prototype states so),
it is allocated in net.c
btw, another procedure in this file also modifies the buffer
On Wed, Apr 3, 2024 at 2:11 PM Akihiko Odaki wrote:
>
> vhost requires eBPF for RSS. When eBPF is not available, virtio-net
> implicitly disables RSS even if the user explicitly requests it. Return
> an error instead of implicitly disabling RSS if RSS is requested but not
> available.
>
>
Hi Andrew,
Can you please check the indirection table copy and ack on the patch
if the fix is correct
Thanks,
Yuri
On Wed, Mar 27, 2024 at 4:05 AM Akihiko Odaki wrote:
>
> The kernel documentation says:
> > The value stored can be of any size, however, all array elements are
> > aligned to 8
he header swap might lead a stack
> overflow in this case. Fixing this by using virtio_net_hdr_v1_hash
> instead.
>
> Reported-by: Xiao Lei
> Cc: Yuri Benditovich
> Cc: qemu-sta...@nongnu.org
> Cc: Mauro Matteo Cascella
> Fixes: CVE-2023-6693
> Fixes: e22f0603fb2f (&
On Mon, Dec 18, 2023 at 2:54 PM Markus Armbruster wrote:
> Uh, I missed this one, my apologies! Let me have a quick look...
>
> Commit message style nitpick:
>
> qmp: Add command to retrieve eBPF blob
>
> or
>
> qmp: New command to retrieve eBPF blob
>
> It's a title, not a sentence.
>
Benditovich <
yuri.benditov...@daynix.com> wrote:
>
> On Tue, Dec 12, 2023 at 5:33 AM Jason Wang wrote:
>
>> On Mon, Dec 11, 2023 at 7:51 PM Yuri Benditovich
>> wrote:
>> >
>> > Hello Jason,
>> > Can you please let us know what happens wi
On Tue, Dec 12, 2023 at 5:33 AM Jason Wang wrote:
> On Mon, Dec 11, 2023 at 7:51 PM Yuri Benditovich
> wrote:
> >
> > Hello Jason,
> > Can you please let us know what happens with this series?
>
> It should be my bad, it is in V1 of the pull request but missed
&g
I'm adding also Yan
On Mon, Dec 11, 2023 at 9:51 PM Yuri Benditovich <
yuri.benditov...@daynix.com> wrote:
> Hi Michael,
> Sure, I've reviewed that also, there was a fruitful discussion
> till the series rеаched its final form.
> At the beginning of September we've got the r
, let's wait for Jason response.
Thanks,
Yuri
On Mon, Dec 11, 2023 at 5:43 PM Michael S. Tsirkin wrote:
> On Mon, Dec 11, 2023 at 02:34:56PM +0200, Yuri Benditovich wrote:
> > https://lists.gnu.org/archive/html/qemu-devel/2023-08/msg05859.html
>
> It's from August, I think it's f
Akihiko,
This series was already discussed several months ago.
I'd suggest to postpone commenting on it and resume them after merging.
Thanks for understanding.
Yuri
On Mon, Dec 11, 2023 at 3:05 PM Akihiko Odaki
wrote:
> On 2023/08/31 15:51, Andrew Melnychenko wrote:
> > Changed eBPF map
https://lists.gnu.org/archive/html/qemu-devel/2023-08/msg05859.html
On Mon, Dec 11, 2023 at 2:01 PM Akihiko Odaki
wrote:
> On 2023/12/11 20:54, Yuri Benditovich wrote:
> > People, I suggest to wait a little and understand what happens with the
> > previous series from And
People, I suggest to wait a little and understand what happens with the
previous series from Andrew Melnichenko (support for qemu under libvirt etc)
According to response from Jason from Sept 8 it was queued but I do not see
it in the master branch.
Thanks a lot.
On Sun, Dec 10, 2023 at 7:30 AM
Hello Jason,
Can you please let us know what happens with this series?
Thanks
Yuri
On Fri, Sep 8, 2023 at 9:43 AM Jason Wang wrote:
> On Mon, Sep 4, 2023 at 7:23 PM Andrew Melnichenko
> wrote:
> >
> > Hi Jason,
> > According to our previous conversation, I've added checks to the meson
>
On Tue, Nov 14, 2023 at 9:03 AM Akihiko Odaki
wrote:
> On 2023/11/14 2:26, Yuri Benditovich wrote:
> >
> >
> > On Mon, Nov 13, 2023 at 2:44 PM Akihiko Odaki > <mailto:akihiko.od...@daynix.com>> wrote:
> >
> >
On Mon, Nov 13, 2023 at 2:44 PM Akihiko Odaki
wrote:
> On 2023/11/13 20:44, Yuri Benditovich wrote:
> >
> >
> > On Sat, Nov 11, 2023 at 5:28 PM Akihiko Odaki > <mailto:akihiko.od...@daynix.com>> wrote:
> >
> >
On Sat, Nov 11, 2023 at 5:28 PM Akihiko Odaki
wrote:
> On 2023/11/03 22:14, Yuri Benditovich wrote:
> >
> >
> > On Fri, Nov 3, 2023 at 11:55 AM Akihiko Odaki > <mailto:akihiko.od...@daynix.com>> wrote:
> >
> >
On Mon, Oct 30, 2023 at 7:15 AM Akihiko Odaki
wrote:
> virtio-net can report hash values even if the peer does not have a
> virtio-net header.
>
> Signed-off-by: Akihiko Odaki
> ---
> hw/net/virtio-net.c | 2 --
> 1 file changed, 2 deletions(-)
>
> diff --git a/hw/net/virtio-net.c
On Fri, Nov 3, 2023 at 11:55 AM Akihiko Odaki
wrote:
> On 2023/11/03 18:35, Yuri Benditovich wrote:
> >
> >
> > On Thu, Nov 2, 2023 at 4:56 PM Akihiko Odaki > <mailto:akihiko.od...@daynix.com>> wrote:
> >
> >
On Thu, Nov 2, 2023 at 4:56 PM Akihiko Odaki
wrote:
> On 2023/11/02 19:20, Yuri Benditovich wrote:
> >
> >
> > On Thu, Nov 2, 2023 at 11:33 AM Michael S. Tsirkin > <mailto:m...@redhat.com>> wrote:
> >
> > On Thu, Nov 02, 2023 at 11:09:27AM +0200
On Thu, Nov 2, 2023 at 1:26 PM Michael S. Tsirkin wrote:
> On Thu, Nov 02, 2023 at 12:20:39PM +0200, Yuri Benditovich wrote:
> >
> >
> > On Thu, Nov 2, 2023 at 11:33 AM Michael S. Tsirkin
> wrote:
> >
> > On Thu, Nov 02, 2023 at 11:09:27AM +0200, Yuri B
On Thu, Nov 2, 2023 at 11:33 AM Michael S. Tsirkin wrote:
> On Thu, Nov 02, 2023 at 11:09:27AM +0200, Yuri Benditovich wrote:
> > Probably we mix two different patches in this discussion.
> > Focusing on the patch in the e-mail header:
> >
> > IMO it is not acceptab
Probably we mix two different patches in this discussion.
Focusing on the patch in the e-mail header:
IMO it is not acceptable to fail QEMU run for one feature that we can't
make active when we silently drop all other features in such a case.
On Wed, Nov 1, 2023 at 11:15 AM Akihiko Odaki
wrote:
On Mon, Oct 30, 2023 at 2:21 PM Akihiko Odaki
wrote:
> On 2023/10/30 21:14, Yuri Benditovich wrote:
> >
> >
> > On Mon, Oct 30, 2023 at 7:14 AM Akihiko Odaki > <mailto:akihiko.od...@daynix.com>> wrote:
> >
> > vhost requires eBPF fo
On Mon, Oct 30, 2023 at 7:14 AM Akihiko Odaki
wrote:
> virtio-net implements software RSS but does not enable it. Enable it
> when RSS is requested, but the eBPF implementation is not available.
> We also check if vhost is in use in such a case since software RSS is
> incompatible with vhost. A
On Mon, Oct 30, 2023 at 7:14 AM Akihiko Odaki
wrote:
> vhost requires eBPF for RSS. When eBPF is not available, virtio-net
> implicitly disables RSS even if the user explicitly requests it. Return
> an error instead of implicitly disabling RSS if RSS is requested but not
> available.
>
I think
On Tue, Oct 17, 2023 at 7:10 AM Akihiko Odaki
wrote:
> vhost requires eBPF for RSS. Even when eBPF is not available, virtio-net
> reported RSS availability, and raised a warning only after the
> guest requested RSS, and the guest could not know that RSS is not
> available.
>
>
The existing code
This patch allows VIRTIO_NET_F_HASH_REPORT feature to the adapter whose
backend does not have a virtio header and does not have offload features
that depend on it.
The migration between such different systems is very problematic even if it
seems successful, such setups are not
ping
On Tue, Aug 1, 2023 at 1:32 AM Yuri Benditovich
wrote:
> Starting from 6.2 the kernel supports UDP segmentation offload, it
> uses GSO_UDP_L4 to mark packets with UDP sermentation request
>
> v1->v2:
> Enable USO features by default starting from 8.1
> Move co
ice.
virtio-net: Add USO flags to vhost support.
Yuri Benditovich (2):
tap: Add check for USO features
virtio-net: Add support for USO features
hw/core/machine.c| 4
hw/net/e1000e_core.c | 2 +-
hw/net/igb_core.c| 2 +-
hw/net/vhost_net.c | 3 +++
hw/net/virtio-net.c |
USO features of virtio-net device depend on kernel ability
to support them, for backward compatibility by default the
features are disabled on 8.0 and earlier.
Signed-off-by: Yuri Benditovich
Signed-off-by: Andrew Melnychecnko
---
hw/core/machine.c | 4
hw/net/virtio-net.c | 31
From: Andrew Melnychenko
Passing additional parameters (USOv4 and USOv6 offloads) when
setting TAP offloads
Signed-off-by: Yuri Benditovich
Signed-off-by: Andrew Melnychenko
---
hw/net/e1000e_core.c | 2 +-
hw/net/igb_core.c| 2 +-
hw/net/virtio-net.c | 4 +++-
hw/net/vmxnet3.c
From: Andrew Melnychenko
New features are subject to check with vhost-user and vdpa.
Signed-off-by: Yuri Benditovich
Signed-off-by: Andrew Melnychenko
---
hw/net/vhost_net.c | 3 +++
net/vhost-vdpa.c | 3 +++
2 files changed, 6 insertions(+)
diff --git a/hw/net/vhost_net.c b/hw/net
Tap indicates support for USO features according to
capabilities of current kernel module.
Signed-off-by: Yuri Benditovich
Signed-off-by: Andrew Melnychecnko
---
include/net/net.h | 3 +++
net/net.c | 9 +
net/tap-bsd.c | 5 +
net/tap-linux.c | 12
net
after
the migration.
Signed-off-by: Yuri Benditovich
---
hw/pci/pci_host.c | 15 +--
1 file changed, 13 insertions(+), 2 deletions(-)
diff --git a/hw/pci/pci_host.c b/hw/pci/pci_host.c
index 7af8afdcbe..a18aa0a8d4 100644
--- a/hw/pci/pci_host.c
+++ b/hw/pci/pci_host.c
@@ -62,6 +62,17
On Thu, Jul 20, 2023 at 3:37 AM Akihiko Odaki
wrote:
> On 2023/07/20 0:21, Yuri Benditovich wrote:
> > virtio-net can suggest USO features TX, RX v4 and RX v6,
> > depending on kernel TUN ability to support them. These
> > features require explicit enable in command-line.
&g
On Thu, Jul 20, 2023 at 3:31 AM Akihiko Odaki
wrote:
> Nitpicking: the subject of this patch is somewhat unconventional. What
> about: "tap: Add USO support to tap device"?
>
> Will take it in account in v2
> On 2023/07/20 0:21, Yuri Benditovich wrote:
>
From: Andrew Melnychenko
New features are subject to check with vhost-user and vdpa.
Signed-off-by: Yuri Benditovich
Signed-off-by: Andrew Melnychenko
---
hw/net/vhost_net.c | 3 +++
net/vhost-vdpa.c | 3 +++
2 files changed, 6 insertions(+)
diff --git a/hw/net/vhost_net.c b/hw/net
From: Andrew Melnychenko
Passing additional parameters (USOv4 and USOv6 offloads) when
setting TAP offloads
Signed-off-by: Yuri Benditovich
Signed-off-by: Andrew Melnychenko
---
hw/net/e1000e_core.c | 2 +-
hw/net/igb_core.c| 2 +-
hw/net/virtio-net.c | 4 +++-
hw/net/vmxnet3.c
Starting from 6.2 the kernel supports UDP segmentation offload, the
kernel uses GSO_UDP_L4 to mark packets with USB sermentation request
Andrew Melnychenko (3):
tap: Added USO support to tap device.
virtio-net: Added USO flags to vhost support.
virtio-net: Added uso check
Yuri
From: Andrew Melnychenko
Added tap uso check with stubs for non-Linux systems.
Signed-off-by: Yuri Benditovich
Signed-off-by: Andrew Melnychenko
---
hw/net/virtio-net.c | 15 +++
include/net/net.h | 3 +++
net/net.c | 9 +
net/tap-bsd.c | 5 +
net
virtio-net can suggest USO features TX, RX v4 and RX v6,
depending on kernel TUN ability to support them. These
features require explicit enable in command-line.
Signed-off-by: Yuri Benditovich
---
hw/net/virtio-net.c | 16 ++--
1 file changed, 14 insertions(+), 2 deletions(-)
diff
On Tue, Feb 28, 2023 at 8:05 PM Daniel P. Berrangé
wrote:
> On Tue, Feb 28, 2023 at 11:56:27AM +0200, Yuri Benditovich wrote:
> > On Mon, Feb 20, 2023 at 11:50 AM Daniel P. Berrangé >
> > wrote:
> >
> > > On Sun, Feb 19, 2023 at 06:20:58PM +0200, Andrew
On Mon, Feb 20, 2023 at 11:50 AM Daniel P. Berrangé
wrote:
> On Sun, Feb 19, 2023 at 06:20:58PM +0200, Andrew Melnychenko wrote:
> > Added a function to check the stamp in the helper.
> > eBPF helper should have a special symbol that generates during the build.
> > QEMU checks the helper and
range is
> full of invalid PE fragments and the tool must check that PE image
> is 'ntoskrnl.exe' actually.
> So, introduce additional validation by checking image name from
> Export Directory against 'ntoskrnl.exe'.
>
> Signed-off-by: Viktor Prutyanov
Tested-by: Yuri Benditovich
On Thu, Sep 9, 2021 at 4:16 AM Jason Wang wrote:
>
> On Thu, Sep 9, 2021 at 8:00 AM Yuri Benditovich
> wrote:
> >
> > On Wed, Sep 8, 2021 at 6:45 AM Jason Wang wrote:
> > >
> > > On Tue, Sep 7, 2021 at 6:40 PM Yuri Benditovich
> > > wrote:
>
On Wed, Sep 8, 2021 at 6:45 AM Jason Wang wrote:
>
> On Tue, Sep 7, 2021 at 6:40 PM Yuri Benditovich
> wrote:
> >
> > On Wed, Sep 1, 2021 at 9:42 AM Jason Wang wrote:
> > >
> > >
> > > 在 2021/8/31 上午1:07, Yuri Benditovich 写道:
> >
On Wed, Sep 1, 2021 at 9:42 AM Jason Wang wrote:
>
>
> 在 2021/8/31 上午1:07, Yuri Benditovich 写道:
> > On Fri, Aug 20, 2021 at 6:41 AM Jason Wang wrote:
> >>
> >> 在 2021/7/13 下午11:37, Andrew Melnychenko 写道:
> >>> Helper program. Loads eBPF RSS program
On Fri, Aug 20, 2021 at 6:41 AM Jason Wang wrote:
>
>
> 在 2021/7/13 下午11:37, Andrew Melnychenko 写道:
> > Helper program. Loads eBPF RSS program and maps and passes them through
> > unix socket.
> > Libvirt may launch this helper and pass eBPF fds to qemu virtio-net.
>
>
> I wonder if this can be
On Mon, Aug 30, 2021 at 11:14 AM Markus Armbruster wrote:
>
> Yuri Benditovich writes:
>
> > On Mon, Aug 30, 2021 at 9:10 AM Markus Armbruster wrote:
> >>
> >> Yuri Benditovich writes:
> >>
> >> > On Tue, Aug 24, 2021 at 9:41 AM Ma
On Mon, Aug 30, 2021 at 9:10 AM Markus Armbruster wrote:
>
> Yuri Benditovich writes:
>
> > On Tue, Aug 24, 2021 at 9:41 AM Markus Armbruster wrote:
> >>
> >> Andrew Melnichenko writes:
> >>
> >> > Hi,
> >> >
> >&g
On Tue, Aug 24, 2021 at 9:41 AM Markus Armbruster wrote:
>
> Andrew Melnichenko writes:
>
> > Hi,
> >
> >> The helper may or may not be installed at the path compiled into QEMU.
> >>
> > Yes, so the helper will not be called - QEMU will try to initiate eBPF RSS
> > or use "in-qemu" RSS.
>
> My
Jason,
Can you please review the series?
Thanks,
Yuri
On Thu, Jul 22, 2021 at 11:38 AM Andrew Melnichenko wrote:
>
> ping
>
> On Tue, Jul 13, 2021 at 6:38 PM Andrew Melnychenko wrote:
>>
>> Libvirt usually launches qemu with strict permissions.
>> To enable eBPF RSS steering,
On Wed, Jun 23, 2021 at 3:47 AM Jason Wang wrote:
>
>
> 在 2021/6/22 下午5:09, Toke Høiland-Jørgensen 写道:
> > Daniel P. Berrangé writes:
> >
> >> On Tue, Jun 22, 2021 at 10:25:19AM +0200, Toke Høiland-Jørgensen wrote:
> >>> Jason Wang writes:
> >&g
> 2. Libvirt queries for qemu capabilities.
> > > 3. One of the capabilities is "qemu-ebpf-rss-helper"
> > path(if present).
> > > 4. On NIC preparation Libvirt checks for virtio-net + rss
> > configurations.
>
On Thu, Jun 10, 2021 at 9:41 AM Jason Wang wrote:
>
>
> 在 2021/6/9 下午6:04, Andrew Melnychenko 写道:
> > Libvirt usually launches qemu with strict permissions.
> > To enable eBPF RSS steering, qemu-ebpf-rss-helper was added.
>
>
> A silly question:
>
> Kernel had the following permission checks in
On Fri, May 14, 2021 at 4:43 PM Michael S. Tsirkin wrote:
>
> On Thu, Mar 25, 2021 at 05:35:22PM +0200, Andrew Melnychenko wrote:
> > This set of patches introduces the usage of eBPF for packet steering
> > and RSS hash calculation:
> > * RSS(Receive Side Scaling) is used to distribute network
More correctly, https://bugzilla.redhat.com/show_bug.cgi?id=1865786
On Fri, Apr 2, 2021 at 8:21 AM Yuri Benditovich
wrote:
>
> Hi Jason,
>
> Yes, the work to support RSS in the Linux virtio-net driver is in progress.
> https://bugzilla.redhat.com/show_bug.cgi?id=1912082
>
>
Hi Jason,
Yes, the work to support RSS in the Linux virtio-net driver is in progress.
https://bugzilla.redhat.com/show_bug.cgi?id=1912082
On Fri, Apr 2, 2021 at 5:57 AM Jason Wang wrote:
>
>
> 在 2021/3/25 下午11:35, Andrew Melnychenko 写道:
> > This set of patches introduces the usage of eBPF for
On Fri, Mar 26, 2021 at 10:51 AM Jason Wang wrote:
>
>
> 在 2021/3/25 下午5:00, Yuri Benditovich 写道:
> > Hi Jason,
> >
> > This was discussed earlier on the previous series of patches.
> > https://lists.gnu.org/archive/html/qemu-devel/2021-02/msg01829.html
> >
ailable.
Thanks,
Yuri
On Thu, Mar 25, 2021 at 8:59 AM Jason Wang wrote:
>
>
> 在 2021/3/22 下午8:24, Yuri Benditovich 写道:
> > Allow fallback to userspace only upon migration, only for specific features
> > and only if 'vhostforce' is not requested.
> >
> > Changes fro
Ping
On Mon, Mar 15, 2021 at 1:59 PM Yuri Benditovich
wrote:
>
> https://bugzilla.redhat.com/show_bug.cgi?id=1743098
> This commit completes the solution of segfault in hot unplug flow
> (by commit ccec7e9603f446fe75c6c563ba335c00cfda6a06).
> Added missing check for vdev in virt
Graceful drop to userspace virtio in case selected features
are missing on the destination system. Currently used for
3 features that might be supported by the vhost kernel on
the source machine and not supported on the destination machine:
rss, hash reporting, packed ring.
Signed-off-by: Yuri
This optional callback addresses migration problem in case
some of negotiated features not present on the destination
system. The device has a chance to avoid migration failure.
Signed-off-by: Yuri Benditovich
---
hw/virtio/virtio.c | 8
include/hw/virtio/virtio.h | 8
Allow fallback to userspace only upon migration, only for specific features
and only if 'vhostforce' is not requested.
Changes from v1:
Patch 1 dropeed (will be submitted in another series)
Added device callback in case the migration should fail due to missing features
Yuri Benditovich (3
If 'vhost_net_disabled' in the NetClientState of the
net device, get_vhost_net for TAP returns NULL. Network adapters
can use this ability to hide the vhost_net temporary between
resets in case some active features contradict with vhost.
Signed-off-by: Yuri Benditovich
---
hw/net/vhost_net.c
flatview_read at ../softmmu/physmem.c:2862
address_space_read_full at ../softmmu/physmem.c:2875
Signed-off-by: Yuri Benditovich
---
hw/virtio/virtio-pci.c | 9 +++--
1 file changed, 7 insertions(+), 2 deletions(-)
diff --git a/hw/virtio/virtio-pci.c b/hw/virtio/virtio-pci.c
index 883045a223
The value is assigned later in this procedure.
Signed-off-by: Yuri Benditovich
---
hw/virtio/virtio-pci.c | 7 +--
1 file changed, 5 insertions(+), 2 deletions(-)
diff --git a/hw/virtio/virtio-pci.c b/hw/virtio/virtio-pci.c
index 4a3dcee771..c1b67cf6fc 100644
--- a/hw/virtio/virtio-pci.c
est
of Philippe Mathieu-Daude
Yuri Benditovich (2):
virtio-pci: add check for vdev in virtio_pci_isr_read
virtio-pci: remove explicit initialization of val
hw/virtio/virtio-pci.c | 16
1 file changed, 12 insertions(+), 4 deletions(-)
--
2.17.1
; On Tue, Feb 09, 2021 at 09:34:20AM -0500, Michael S. Tsirkin wrote:
> > > > > On Thu, Feb 04, 2021 at 10:29:12PM +0200, Yuri Benditovich wrote:
> > > > > > This set of patches introduces graceful switch from tap-vhost to
> > > > > > tap-no-vh
https://bugzilla.redhat.com/show_bug.cgi?id=1743098
There is missing check for vdev in this procedure.
QEMU crash happens in it in hot unplug flow.
Signed-off-by: Yuri Benditovich
---
hw/virtio/virtio-pci.c | 8 +++-
1 file changed, 7 insertions(+), 1 deletion(-)
diff --git a/hw/virtio
On Mon, Feb 8, 2021 at 5:15 AM Jason Wang wrote:
>
>
> On 2021/2/5 下午9:38, Michael S. Tsirkin wrote:
> > On Thu, Feb 04, 2021 at 10:29:15PM +0200, Yuri Benditovich wrote:
> >> Currently virtio-net silently clears features if they are
> >> not supported by
On Mon, Feb 8, 2021 at 6:11 AM Jason Wang wrote:
>
>
> On 2021/2/5 上午4:29, Yuri Benditovich wrote:
> > Currently virtio-net silently clears features if they are
> > not supported by respective vhost. This may create migration
> > problems in future if vhost features on
. The decision is
taken on set_features call and the vhost will be disabled
till next reset (or migration).
Such fallback is currently enabled only for TAP netdev.
Signed-off-by: Yuri Benditovich
---
hw/net/virtio-net.c | 58 ++---
1 file changed, 50 insertions
If 'vhost_net_disabled' in the NetClientState of the
net device, get_vhost_net for TAP returns NULL. Network adapters
can use this ability to hide the vhost_net temporary between
resets in case some active features contradict with vhost.
Signed-off-by: Yuri Benditovich
---
hw/net/vhost_net.c
of patches also makes get_vhost_net() call (that used
everywhere) to always return actual result, i.e. initially it
returns non-NULL value and from the moment the vhost was disabled
the call will return NULL. Such a way we avoid any unexpected
calls to vhost functions.
Yuri Benditovich (3):
vhost-net: add
In case of vhost TAP the kernel must support this feature,
otherwise the device can't offer it.
Signed-off-by: Yuri Benditovich
---
hw/net/vhost_net.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/hw/net/vhost_net.c b/hw/net/vhost_net.c
index 24d555e764..8282e440bd 100644
--- a/hw/net
On Mon, Jan 25, 2021 at 11:03 AM Jason Wang wrote:
>
>
> On 2021/1/19 下午10:53, Yuri Benditovich wrote:
> > On Fri, Jan 15, 2021 at 9:02 AM Jason Wang wrote:
> >>
> >> On 2021/1/15 上午5:16, Andrew Melnychenko wrote:
> >>> From: Andrew
> >
On Sun, Jan 24, 2021 at 10:24 AM Yuri Benditovich
wrote:
>
> Hi Jason,
>
> I've prepared a POC of graceful switch to 'vhost off' if respective
> features are acked by the guest.
> Such a way we do not need to silently clear RSS and hash report
> features in case of 'vhost
is what to do with cases of vhost-user
and vhost-vdpa.
https://github.com/qemu/qemu/pull/105
This pull request is for reviews only.
Thanks in advance
On Mon, Jan 18, 2021 at 5:16 AM Jason Wang wrote:
>
>
> On 2021/1/17 下午5:04, Yuri Benditovich wrote:
> > On Fri, Jan 15, 2021 at 9:2
tions.
> >
> > By default, eBPF feature enabled if libbpf is present in the build system.
> > libbpf checked in configuration shell script and meson script.
> >
> > Signed-off-by: Yuri Benditovich
> > Signed-off-by: Andrew Melnychenko
> > ---
> >
; the RSS will function also with vhost (works with kernel 5.8 and later).
> > Software RSS is used as a fallback with vhost=off when eBPF can't be loaded
> > or when hash population requested by the guest.
> >
> > Signed-off-by: Yuri Benditovich
> > Signed-off-by: A
On Fri, Dec 4, 2020 at 3:57 PM Toke Høiland-Jørgensen
wrote:
> Yuri Benditovich writes:
>
> > On Fri, Dec 4, 2020 at 12:09 PM Toke Høiland-Jørgensen
> > wrote:
> >
> >> Yuri Benditovich writes:
> >>
> >> > On Wed, Dec 2, 2020 at 4:18 PM To
On Fri, Dec 4, 2020 at 12:09 PM Toke Høiland-Jørgensen
wrote:
> Yuri Benditovich writes:
>
> > On Wed, Dec 2, 2020 at 4:18 PM Toke Høiland-Jørgensen
> > wrote:
> >
> >> Jason Wang writes:
> >>
> >> > On 2020/11/19 下午7:13, Andrew Mel
On Wed, Dec 2, 2020 at 4:18 PM Toke Høiland-Jørgensen
wrote:
> Jason Wang writes:
>
> > On 2020/11/19 下午7:13, Andrew Melnychenko wrote:
> >> This set of patches introduces the usage of eBPF for packet steering
> >> and RSS hash calculation:
> >> * RSS(Receive Side Scaling) is used to distribute
On Wed, Dec 2, 2020 at 6:06 AM Jason Wang wrote:
>
> On 2020/12/1 下午3:40, Yuri Benditovich wrote:
> >
> >
> > On Tue, Nov 24, 2020 at 10:49 AM Jason Wang > <mailto:jasow...@redhat.com>> wrote:
> >
> >
> > On 2020/11/19 下午7:13, Andre
he RSS will function also with vhost (works with kernel 5.8 and later).
> > Software RSS is used as a fallback with vhost=off when eBPF can't be
> loaded
> > or when hash population requested by the guest.
> >
> > Signed-off-by: Yuri Benditovich
> > Signed-off-by: A
On Fri, Nov 27, 2020 at 6:36 AM Jason Wang wrote:
>
> On 2020/11/26 下午8:52, Yuri Benditovich wrote:
> >
> >
> > On Mon, Nov 23, 2020 at 8:08 AM Jason Wang > <mailto:jasow...@redhat.com>> wrote:
> >
> >
> > On 2020/11/19 下午7:13, A
On Tue, Nov 24, 2020 at 10:55 AM Jason Wang wrote:
>
> On 2020/11/19 下午7:13, Andrew Melnychenko wrote:
> > From: Andrew
> >
> > Also, added maintainers information.
> >
> > Signed-off-by: Yuri Benditovich
> > Signed-off-by: Andrew Melnyche
On Mon, Nov 23, 2020 at 8:08 AM Jason Wang wrote:
>
> On 2020/11/19 下午7:13, Andrew Melnychenko wrote:
> > This set of patches introduces the usage of eBPF for packet steering
> > and RSS hash calculation:
> > * RSS(Receive Side Scaling) is used to distribute network packets to
> > guest
1 - 100 of 282 matches
Mail list logo
