Hi Eelco,
Version 19 mainly fixes a bug that psample_sock is destroyed when last
bridge is deleted.
And it also addresses some of the minor comments in v18. I think there
is no use
to address all of them because if we need to change the dpif-offload
design, maybe
some of them will be irrelev
On 1/4/22 19:35, Mike Pattrick wrote:
> On Tue, Jan 4, 2022 at 1:12 PM Ilya Maximets wrote:
>>
>> On 11/30/21 17:20, Mike Pattrick wrote:
>>> Recently there has been a lot of press about the "trojan source" attack,
>>> where Unicode characters are used to obfuscate the true functionality of
>>> co
On 12/17/21 15:45, Eelco Chaudron wrote:
>
>
> On 17 Dec 2021, at 15:09, Mike Pattrick wrote:
>
>> This commit adds a basic packet metadata macro to the already existing
>> macros in ovs_gdb.py, ovs_dump_packets will print out information about
>> one or more packets. It feeds packets into tcpdu
On 12/21/21 15:58, Mike Pattrick wrote:
> On Tue, Dec 7, 2021 at 3:10 PM Frode Nordahl
> wrote:
>>
>> The netlink policy unit test contains test fixture data that is
>> subject to endianness and currently fails on big endian systems.
>>
>> Store the fixture data in a struct to ensure proper byte o
On 1/4/22 16:53, Eelco Chaudron wrote:
>
>
> On 4 Jan 2022, at 16:44, Eli Britstein wrote:
>
>> On 1/4/2022 4:56 PM, Eelco Chaudron wrote:
>>> External email: Use caution opening links or attachments
>>>
>>>
>>> On 5 Dec 2021, at 8:34, Eli Britstein via dev wrote:
>>>
Following [1]-[3] in D
On 12/15/21 13:54, Paolo Valerio wrote:
> Hello Mike,
>
> Mike Pattrick writes:
>
>> As part of some previous checkpatch work, we discovered that checkpatch
>> isn't always reporting correct line numbers. As it turns out, Python's
>> splitlines function considers several characters to be new lin
On 1/4/22 12:47, Amber, Kumar wrote:
> Hi IIlya,
>
> Thanks for the patch.
> Tested and Reviewed all looks good.
>
>
>
>> -Original Message-
>> From: Ilya Maximets
>> Sent: Tuesday, January 4, 2022 4:46 AM
>> To: ovs-dev@openvswitch.org
>> Cc: David Marchand ; Amber, Kumar
>> ; Ilya Ma
On 12/15/21 15:02, Mike Pattrick wrote:
> Hello Nobuhiro,
>
> Good find!
>
> Acked-by: Mike Pattrick
>
> On Tue, Nov 30, 2021 at 1:03 AM Nobuhiro MIKI wrote:
>>
>> Signed-off-by: Nobuhiro MIKI
>> ---
>> Documentation/intro/install/afxdp.rst | 1 -
>> 1 file changed, 1 deletion(-)
>>
>> diff
On Tue, Jan 4, 2022 at 1:12 PM Ilya Maximets wrote:
>
> On 11/30/21 17:20, Mike Pattrick wrote:
> > Recently there has been a lot of press about the "trojan source" attack,
> > where Unicode characters are used to obfuscate the true functionality of
> > code. This attack didn't effect OVS, but add
On 12/29/21 03:35, Eli Britstein via dev wrote:
Add support for dpdk geneve tunnel offloads.
Series looks goods to me.
The code looks to take inspiration from the vxlan code. I guess if that
works then this should too.
GitHub actions:
v1: https://github.com/elibritstein/OVS/actions/runs/
On 11/30/21 17:20, Mike Pattrick wrote:
> Recently there has been a lot of press about the "trojan source" attack,
> where Unicode characters are used to obfuscate the true functionality of
> code. This attack didn't effect OVS, but adding the check here will help
> guard against it sneaking in lat
On Tue, 4 Jan 2022 10:28:21 +0200 Paul Blakey wrote:
> Netfilter conntrack maintains NAT flags per connection indicating
> whether NAT was configured for the connection. Openvswitch maintains
> NAT flags on the per packet flow key ct_state field, indicating
> whether NAT was actually executed on th
On 12/6/21 17:57, Eelco Chaudron wrote:
> Currently, if a flow reply results in a message which exceeds
> the maximum reply size, it will assert OVS. This would happen
> when OVN uses OpenFlow15 to add large flows, and they get read
> using OpenFlow10 with ovs-ofctl.
>
> This patch prevents this a
On 12/22/21 10:46, Eelco Chaudron wrote:
>
>
> On 21 Dec 2021, at 16:31, Aaron Conole wrote:
>
>> Dumitru Ceara writes:
>>
>>> UB Sanitizer reports:
>>> lib/bfd.c:748:16: runtime error: member access within misaligned address
>>> 0x01f0d6ea for type 'struct msg', which requires 4 byte al
On 12/21/21 15:57, Aaron Conole wrote:
> Dumitru Ceara writes:
>
>> UB Sanitizer report:
>> lib/stopwatch.c:119:22: runtime error: index 18446744073709551615 out of
>> bounds for type 'long long unsigned int [50]'
>> #0 0x698358 in calc_percentile lib/stopwatch.c:119
>> #1 0x69ada1
On 12/21/21 16:44, Aaron Conole wrote:
> Dumitru Ceara writes:
>
>> UB Sanitizer report:
>> lib/dp-packet.h:297:39: runtime error: applying zero offset to null pointer
>> #0 0x7946f5 in dp_packet_tail /root/ovs/./lib/dp-packet.h:297:39
>> #1 0x794331 in dp_packet_tailroom /root/ovs/
On 4 Jan 2022, at 16:44, Eli Britstein wrote:
> On 1/4/2022 4:56 PM, Eelco Chaudron wrote:
>> External email: Use caution opening links or attachments
>>
>>
>> On 5 Dec 2021, at 8:34, Eli Britstein via dev wrote:
>>
>>> Following [1]-[3] in DPDK, there are no more such warnings from DPDK.
>>> Re
On 1/4/2022 4:56 PM, Eelco Chaudron wrote:
External email: Use caution opening links or attachments
On 5 Dec 2021, at 8:34, Eli Britstein via dev wrote:
Following [1]-[3] in DPDK, there are no more such warnings from DPDK.
Remove ignoring them if they occur.
GitHub actions:
v1: https://gith
On 5 Dec 2021, at 8:34, Eli Britstein via dev wrote:
> Following [1]-[3] in DPDK, there are no more such warnings from DPDK.
> Remove ignoring them if they occur.
>
> GitHub actions:
> v1: https://github.com/elibritstein/OVS/actions/runs/1540651133
>
> [1] a3f8d0587188 ("net: avoid cast-align w
On 8 Dec 2021, at 8:59, Sunil Pai G wrote:
> Currently, on failure to link with DPDK, the configure script provides
> an error message to update the PKG_CONFIG_PATH even though the cause of
> failure was missing dependencies. Improve the error message to include this
> scenario.
>
> Signed-off-
Hi David,
On 1/3/22 19:42, David Marchand wrote:
On Fri, Dec 17, 2021 at 4:10 PM Maxime Coquelin
wrote:
Hash-based Tx steering feature will enable steering Tx
packets on transmit queues based on their hashes. In order
to test the feature, it is needed to be able to get the
per-queue statistic
On 1/4/22 13:15, Ilya Maximets wrote:
> On 12/21/21 12:03, Dumitru Ceara wrote:
>> When decoding multiple actions in ofpacts_decode(), make sure that when
>> we advance to the next action it will be properly aligned (multiple of
>> OFPACT_ALIGNTO). If not, clone or trim the ofpbuf to ensure proper
Hi Jun, the changes look good, but some small comments below.
//Eelco
On 23 Nov 2021, at 17:22, Jun Xiao wrote:
> When a packet requests l4 csum offload, the l4 csum field includes
> a pseudo csum instead of a full csum. The pseudo csum doesn't do
> the final one's complement, and it must be up
vHost async API's allow the copy operations to be offloaded to a DMA
device asynchronously for better performance.
Signed-off-by: Sunil Pai G
---
lib/dpdk-stub.c | 6 +
lib/dpdk.c| 28 +++
lib/dpdk.h| 1 +
lib/netdev-dpdk.c | 442 +++
This series brings in the new asynchronous vHost API's in DPDK to OVS.
With the asynchronous framework, vHost-user can offload the memory copy
operation
to DPDK DMA-dev based enabled devices like Intel® QuickData Technology without
blocking the CPU.
The intention of this patch is solely to commun
Hello:
This series was applied to netdev/net-next.git (master)
by David S. Miller :
On Mon, 3 Jan 2022 13:44:49 +0200 you wrote:
> Hi,
>
> Currently, drivers register to a ct zone that can be shared by multiple
> devices. This can be inefficient for the driver to offload, as it
> needs to handle
On 12/21/21 12:03, Dumitru Ceara wrote:
> When decoding multiple actions in ofpacts_decode(), make sure that when
> we advance to the next action it will be properly aligned (multiple of
> OFPACT_ALIGNTO). If not, clone or trim the ofpbuf to ensure proper
> aligment.
If some of the ofpact entries
On 1/3/22 15:15, David Marchand wrote:
> The MFEX code and tests do not depend on DPDK anymore.
> We can move the unit tests to dpif-netdev.
>
> Signed-off-by: David Marchand
> Reviewed-by: Maxime Coquelin
> Acked-by: Eelco Chaudron
> Acked-by: Kumar Amber
> ---
> Note: this patch depends on s
References: <20220104115034.142846-1-sangana.abhi...@nutanix.com>
Bleep bloop. Greetings Abhiram Sangana, I am a robot and I have tried out your
patch.
Thanks for your contribution.
I encountered some error that I wasn't expecting. See the details below.
git-am:
error: sha1 information is
On 1/3/22 15:15, David Marchand wrote:
> net_pcap is not always available in DPDK (like, in a dev
> environment when you forgot to install the libpcap-devel).
> On the other hand, OVS already has its own way to inject packets into a
> bridge. Let's make use of it.
>
> This solution is slower than
Currently, if multiple distributed gateway ports (DGP) are configured
on a logical router, NAT is disabled as part of commit 15348b7b
(northd: Multiple distributed gateway port support.)
This patch updates the behavior by selectively applying NAT rules at DGPs.
A NAT rule is applied on matching pa
Hi IIlya,
Thanks for the patch.
Tested and Reviewed all looks good.
> -Original Message-
> From: Ilya Maximets
> Sent: Tuesday, January 4, 2022 4:46 AM
> To: ovs-dev@openvswitch.org
> Cc: David Marchand ; Amber, Kumar
> ; Ilya Maximets
> Subject: [PATCH] dpif-netdev-extract: Change av
On 1/3/22 15:15, David Marchand wrote:
> The DPDK unit test only runs if vfio or igb_uio kernel modules are loaded:
> on systems with only mlx5, this test is always skipped.
>
> Besides, the test tries to grab the first device listed by dpdk-devbind.py,
> regardless of the PCI device status regard
Hi Chris,
Looked at the patch and the new version does not try to work around my concerns
on v18, i.e., the ones where we need Ilya’s input.
So I could not add any more ACKs; however, I did talk to Ilya offline, and he
will get back to this after his 2.17 release work.
See:
https://patchwork.o
Netfilter conntrack maintains NAT flags per connection indicating
whether NAT was configured for the connection. Openvswitch maintains
NAT flags on the per packet flow key ct_state field, indicating
whether NAT was actually executed on the packet.
When a packet misses from tc to ovs the conntrack
35 matches
Mail list logo
