The goal of this is to provide a possibility to suport various switch
chips. Drivers should implement relevant ndos to do so. Now there is a
couple of ndos defines:
- for getting physical switch id is in place.
- for work with flows.
Note that user can use random port netdevice to access the switc
Benefit from the possibility to work with flows in switch devices and
use the swdev api to offload flow datapath.
Signed-off-by: Jiri Pirko
---
net/openvswitch/Makefile | 3 +-
net/openvswitch/datapath.c | 33 ++
net/openvswitch/datapath.h | 3 +
net/openvswitch/flow_table
Signed-off-by: Jiri Pirko
---
net/core/net-sysfs.c | 24
1 file changed, 24 insertions(+)
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index 55dc4da..51cd5ab 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -12,6 +12,7 @@
#include
#include
This patchset can be divided into 3 main sections:
- introduce switchdev api for implementing switch drivers
- add hardware acceleration bits into openvswitch datapath, This uses
previously mentioned switchdev api
- introduce rocker switch driver which implements switchdev api
More info in separ
Dummy switch implementation using switchdev interface
Signed-off-by: Jiri Pirko
---
drivers/net/Kconfig | 7 +++
drivers/net/Makefile | 1 +
drivers/net/dummyswitch.c| 130 +++
include/uapi/linux/if_link.h | 9 +++
4 files change
The netdevice represents a port in a switch, it will expose
IFLA_PHYS_SWITCH_ID value via rtnl. Two netdevices with the same value
belong to one physical switch.
Signed-off-by: Jiri Pirko
---
include/uapi/linux/if_link.h | 1 +
net/core/rtnetlink.c | 26 +-
2 fil
This will allow to query easily if the vport has netdev. Also it allows
to unexpose netdev_vport_priv and struct netdev_vport.
Signed-off-by: Jiri Pirko
---
net/openvswitch/datapath.c | 2 +-
net/openvswitch/dp_notify.c | 7 ++---
net/openvswitch/vport-internal_dev.c | 56 ++
Signed-off-by: Jiri Pirko
---
include/net/sw_flow.h| 3 +++
net/openvswitch/hw_offload.c | 22 ++
net/switchdev/switchdev.c| 2 ++
3 files changed, 27 insertions(+)
diff --git a/include/net/sw_flow.h b/include/net/sw_flow.h
index 3af7758..a144d8e 100644
--- a/in
Signed-off-by: Jiri Pirko
---
include/linux/netdevice.h | 3 ++-
include/net/dsa.h | 1 +
net/dsa/Kconfig | 2 +-
net/dsa/dsa.c | 3 +++
net/dsa/slave.c | 10 ++
5 files changed, 17 insertions(+), 2 deletions(-)
diff --git a/include/linux/netde
Signed-off-by: Jiri Pirko
Acked-by: Scott Feldman
---
include/linux/netdevice.h | 7 +++
1 file changed, 7 insertions(+)
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 7ee070f..b2c3ff0 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -750,6
This patch introduces the first driver to benefit from the switchdev
infrastructure and to implement newly introduced switch ndos. This is a
driver for emulated switch chip implemented in qemu:
https://github.com/sfeldma/qemu-rocker/
This patch is a result of joint work with Scott Feldman.
Signed
This patch exposes switchdev API using generic Netlink.
Example userspace utility is here:
https://github.com/jpirko/switchdev
Signed-off-by: Jiri Pirko
---
MAINTAINERS | 1 +
include/uapi/linux/switchdev.h| 119 +
net/switchdev/Kconfig | 11 +
ne
Acked-by: Eitan Eliahu
-Original Message-
From: dev [mailto:dev-boun...@openvswitch.org] On Behalf Of Ankur Sharma
Sent: Tuesday, September 02, 2014 6:05 PM
To: dev@openvswitch.org
Subject: [ovs-dev] [PATCH 4/5] OvsTypes.h : Added support for BE16
---
datapath-windows/ovsext/Types.h |
Acked-by: Eitan Eliahu
-Original Message-
From: dev [mailto:dev-boun...@openvswitch.org] On Behalf Of Ankur Sharma
Sent: Tuesday, September 02, 2014 6:05 PM
To: dev@openvswitch.org
Subject: [ovs-dev] [PATCH 2/5] NetlinkBuf.c: Netlink buffer mgmt apis.
In this change we have introduced b
Acked-by: Eitan Eliahu
-Original Message-
From: dev [mailto:dev-boun...@openvswitch.org] On Behalf Of Ankur Sharma
Sent: Tuesday, September 02, 2014 6:04 PM
To: dev@openvswitch.org
Subject: [ovs-dev] [PATCH 1/5] datapath-windows/Netlink: Move netlink files to
a new directory.
In this c
Acked-by: Eitan Eliahu
-Original Message-
From: dev [mailto:dev-boun...@openvswitch.org] On Behalf Of Ankur Sharma
Sent: Tuesday, September 02, 2014 6:05 PM
To: dev@openvswitch.org
Subject: [ovs-dev] [PATCH 3/5] NetlinkProto.h: Minor fix for typos and new
macro for padding.
Added a new
In a later change we would like to have these functions inline.
Acked-by: Eitan Eliahu
-Original Message-
From: dev [mailto:dev-boun...@openvswitch.org] On Behalf Of Ankur Sharma
Sent: Tuesday, September 02, 2014 6:05 PM
To: dev@openvswitch.org
Subject: [ovs-dev] [PATCH 5/5] Netlink.c:
On 09/03/2014 02:24 AM, Jiri Pirko wrote:
After this, flow related structures can be used in other code.
Signed-off-by: Jiri Pirko
---
Hi Jiri,
As I indicated before I'm looking into integrating this with some
hardware here. Progress is a bit slow but starting to look at it.The
i40e/ixgbe dr
On Tue, Sep 2, 2014 at 1:58 PM, wrote:
> From: Ariel Tubaltsev
>
> This commit adds default values for some BFD configuration keys
> (bfd_config_local:bfd_dst_mac and bfd_params:enable). It also adds new
> BFD status keys (bfd_enabled and bfd_info).
>
> Signed-off-by: Ariel Tubaltsev
> Signed-o
I looked and applied the patches. They’re good to me, I just have some
notes on patch 13/18 and 16/18.
@@ -108,9 +121,9 @@ process_received_bpdu(struct rstp_port *p, const void
> *bpdu, size_t bpdu_size)
> memcpy(&p->received_bpdu_buffer, bpdu, sizeof(struct rstp_bpdu));
> rstp
On 09/03/2014 02:24 AM, Jiri Pirko wrote:
The goal of this is to provide a possibility to suport various switch
chips. Drivers should implement relevant ndos to do so. Now there is a
couple of ndos defines:
- for getting physical switch id is in place.
- for work with flows.
Note that user can u
Hi Ankur,
Just a small nit I you use "git format-patch" could you also add the -M option?
Thank you,
Alin.
-Mesaj original-
De la: dev [mailto:dev-boun...@openvswitch.org] În numele Ankur Sharma
Trimis: Wednesday, September 3, 2014 4:04 AM
Către: dev@openvswitch.org
Subiect: [ovs-dev] [
The setup for packet transfer between the switch and VM by shared memory
(IVSHMEM) is moderately complex and most details are not easily found. Also
this is a different transfer method than user side vhost which copies between
the separate memory spaces at a cost of slower packet rate or higher
Hi Alin,
Sure. Sorry i missed that.
Do you want me to spin up a v2 with -M enabled in format-patch?
Thanks.
Regards,
Ankur
From: Alin Serdean
Sent: Wednesday, September 3, 2014 9:29 AM
To: Ankur Sharma; dev@openvswitch.org
Subject: RE: [ovs-dev] [PATCH 1
On 09/03/2014 02:24 AM, Jiri Pirko wrote:
Benefit from the possibility to work with flows in switch devices and
use the swdev api to offload flow datapath.
Signed-off-by: Jiri Pirko
---
net/openvswitch/Makefile | 3 +-
net/openvswitch/datapath.c | 33 ++
net/openvswitch/dat
Hi, here are some items we would like to follow up on. Please feel free to add
anything you would like to discuss.
NetLink
--
i) #Action-item: Alin to send out patches for dpif-linux.c soon.
ii) Sam will be working on the vport commands - dump and add to start with,
and the rest late
Please.
I will look over the other patches after the meeting :).
Alin.
-Mesaj original-
De la: Ankur Sharma [mailto:ankursha...@vmware.com]
Trimis: Wednesday, September 3, 2014 7:34 PM
Către: Alin Serdean; dev@openvswitch.org
Subiect: RE: [ovs-dev] [PATCH 1/5] datapath-windows/Netlink:
On Fri, Aug 29, 2014 at 03:54:08PM -0700, Pravin Shelar wrote:
> On Fri, Aug 15, 2014 at 7:07 AM, Polehn, Mike A
> wrote:
> > Adds documentation on how to run IVSHMEM communication through VM.
> >
> I think INSTALL.DPDK is getting rather large and hard to understand
> with all details.
> so I dro
The Open vSwitch "make" output was still pretty verbose even when
configured with --enable-silent-rules. This cleans it up.
Signed-off-by: Ben Pfaff
---
I tested that this yields good output with the following travis build:
https://travis-ci.org/openvswitch/ovs/builds/34310033
Have I men
On Wed, Sep 3, 2014 at 2:24 AM, Jiri Pirko wrote:
> After this, flow related structures can be used in other code.
>
> Signed-off-by: Jiri Pirko
> ---
> include/net/sw_flow.h | 99 ++
> net/openvswitch/actions.c | 3 +-
> net/openvswitch/datapath.
On Wed, Sep 3, 2014 at 8:20 AM, John Fastabend wrote:
> On 09/03/2014 02:24 AM, Jiri Pirko wrote:
>>
>> After this, flow related structures can be used in other code.
>>
>> Signed-off-by: Jiri Pirko
>> ---
>
>
> Hi Jiri,
>
> As I indicated before I'm looking into integrating this with some
> hard
Future patches will change the recirc action implementation to not
using recursion. The stack depth detection is no longer necessary.
Signed-off-by: Andy Zhou
---
v4->v5: no change
---
datapath/actions.c | 63 -
datapath/datapath.c | 6 ++--
Since kernel stack is limited in size, it is not wise to using
recursive function with large stack frames.
This patch provides an alternative implementation of recirc action
without using recursion.
A per CPU fixed sized, 'deferred action FIFO', is used to store either
recirc or sample actions en
Acked-by: Alin Gabriel Serdean
-Mesaj original-
De la: dev [mailto:dev-boun...@openvswitch.org] În numele Ankur Sharma
Trimis: Tuesday, September 2, 2014 6:05 PM
Către: dev@openvswitch.org
Subiect: [ovs-dev] [PATCH 5/5] Netlink.c: Added netlink put APIs.
In this change we have added the
Acked-by: Alin Gabriel Serdean
-Mesaj original-
De la: dev [mailto:dev-boun...@openvswitch.org] În numele Ankur Sharma
Trimis: Tuesday, September 2, 2014 6:05 PM
Către: dev@openvswitch.org
Subiect: [ovs-dev] [PATCH 4/5] OvsTypes.h : Added support for BE16
---
datapath-windows/ovsext/Typ
Acked-by: Alin Gabriel Serdean
-Mesaj original-
De la: dev [mailto:dev-boun...@openvswitch.org] În numele Ankur Sharma
Trimis: Tuesday, September 2, 2014 6:05 PM
Către: dev@openvswitch.org
Subiect: [ovs-dev] [PATCH 3/5] NetlinkProto.h: Minor fix for typos and new
macro for padding.
Adde
Maybe just rename NL_BUF with NL_BUFFER otherwise I am fine with the patch.
Acked-by: Alin Gabriel Serdean
-Mesaj original-
De la: dev [mailto:dev-boun...@openvswitch.org] În numele Ankur Sharma
Trimis: Tuesday, September 2, 2014 6:05 PM
Către: dev@openvswitch.org
Subiect: [ovs-dev] [PAT
Hi Alin,
Thanks for reviewing the patches.
I'll spin up a v2 with following changes.
a. Use format-patch with -M for 1/5
b. Rename NL_BUF to NL_BUFFER.
Is it ok if i put your name along with Eitan's in Ack-By while submitting v2 or
would like to review v2 then let me add your name to Ack-by?
T
Sure be my guest :).
-Mesaj original-
De la: Ankur Sharma [mailto:ankursha...@vmware.com]
Trimis: Wednesday, September 3, 2014 1:14 PM
Către: Alin Serdean; dev@openvswitch.org
Subiect: RE: [ovs-dev] [PATCH 1/5] datapath-windows/Netlink: Move netlink files
to a new directory.
Hi Alin,
T
After discussing with Pravin offline, it is good to use first get the
reference
and then access the 'port->netdev' for pmd check.
So, use a nested if statement:
@@ -1864,20 +1874,27 @@ pmd_load_queues(struct pmd_thread *f,
index = 0;
CMAP_FOR_EACH (port, node, &f->dp->ports) {
-
On Thu, Aug 28, 2014 at 4:39 PM, Jarno Rajahalme wrote:
>
> On Aug 28, 2014, at 9:57 AM, Gurucharan Shetty wrote:
>> diff --git a/lib/ovs-atomic-msvc.h b/lib/ovs-atomic-msvc.h
>> new file mode 100644
>> index 000..f357545
>> --- /dev/null
>> +++ b/lib/ovs-atomic-msvc.h
>> @@ -0,0 +1,370 @@
>>
Before this change (i.e., with pthread locks for atomics on Windows),
the benchmark for cmap and hmap was as follows:
$ ./tests/ovstest.exe test-cmap benchmark 1000 3 1
Benchmarking with n=1000, 3 threads, 1.00% mutations:
cmap insert: 61070 ms
cmap iterate: 2750 ms
cmap search: 14238 m
On 09/03/14 11:20, John Fastabend wrote:
Also I have some filters that can match on offset/length/mask
tuples. As far as I can tell this is going to have to be yet
another interface? Or would it be worth the effort to define
the flow key more generically. My initial guess is I'll just
write a se
On 09/03/14 14:41, Pravin Shelar wrote:
On Wed, Sep 3, 2014 at 2:24 AM, Jiri Pirko wrote:
HW offload API should be separate from OVS module.
The above part i agree with. Infact it is very odd that it seems
hard to get this point across ;->
This has following
advantages.
1. It can be manag
On Wed, Sep 3, 2014 at 2:22 PM, Jamal Hadi Salim wrote:
> On 09/03/14 14:41, Pravin Shelar wrote:
>>
>> On Wed, Sep 3, 2014 at 2:24 AM, Jiri Pirko wrote:
>
>
>> HW offload API should be separate from OVS module.
>
>
> The above part i agree with. Infact it is very odd that it seems
> hard to get
On Wed, Sep 3, 2014 at 9:31 AM, Polehn, Mike A wrote:
> The setup for packet transfer between the switch and VM by shared memory
> (IVSHMEM) is moderately complex and most details are not easily found. Also
> this is a different transfer method than user side vhost which copies between
> the s
On Wed, Sep 3, 2014 at 10:14 AM, Flavio Leitner wrote:
> On Fri, Aug 29, 2014 at 03:54:08PM -0700, Pravin Shelar wrote:
>> On Fri, Aug 15, 2014 at 7:07 AM, Polehn, Mike A
>> wrote:
>> > Adds documentation on how to run IVSHMEM communication through VM.
>> >
>> I think INSTALL.DPDK is getting rat
On Wed, Sep 3, 2014 at 1:24 PM, Alex Wang wrote:
> After discussing with Pravin offline, it is good to use first get the
> reference
> and then access the 'port->netdev' for pmd check.
>
> So, use a nested if statement:
>
> @@ -1864,20 +1874,27 @@ pmd_load_queues(struct pmd_thread *f,
> index
On Wed, Sep 3, 2014 at 1:05 PM, Andy Zhou wrote:
> Since kernel stack is limited in size, it is not wise to using
> recursive function with large stack frames.
>
> This patch provides an alternative implementation of recirc action
> without using recursion.
>
> A per CPU fixed sized, 'deferred act
On 09/03/2014 02:24 AM, Jiri Pirko wrote:
> Signed-off-by: Jiri Pirko
> ---
> include/linux/netdevice.h | 3 ++-
> include/net/dsa.h | 1 +
> net/dsa/Kconfig | 2 +-
> net/dsa/dsa.c | 3 +++
> net/dsa/slave.c | 10 ++
> 5 files changed, 17 inser
This series contains changes for providing Netlink PUT Apis in
windows kernel.
Ankur Sharma (6):
datapath-windows/Netlink: Move netlink files to a new directory.
NetlinkBuf.c: Netlink buffer mgmt apis.
NetlinkProto.h: Minor fix for typos and new macro for padding.
OvsTypes.h : Added suppor
In this change we have created a new directory named Netlink
inside datapath-windows/ovsext/. This directory will be used to
keep all the netlink related files.
The reason we have created new directory is that for 'put' related
APIs we will be adding netlink buffer mgmt files as well. These files
Signed-off-by: Ankur Sharma
Tested-by: Ankur Sharma
Reported-at: https://github.com/openvswitch/ovs-issues/issues/37
Acked-by: Eitan Eliahu
Acked-by: Alin Gabriel Serdean
---
datapath-windows/ovsext/Types.h | 1 +
1 file changed, 1 insertion(+)
diff --git a/datapath-windows/ovsext/Types.h b/
Added a new macro for calculating the number of bytes required
for padding. Fixed a minor typo.
Signed-off-by: Ankur Sharma
Tested-by: Ankur Sharma
Reported-at: https://github.com/openvswitch/ovs-issues/issues/37
Acked-by: Eitan Eliahu
Acked-by: Alin Gabriel Serdean
---
datapath-windows/ovse
Signed-off-by: Ankur Sharma
Tested-by: Ankur Sharma
Reported-at: https://github.com/openvswitch/ovs-issues/issues/37
Acked-by: Eitan Eliahu
Acked-by: Alin Gabriel Serdean
---
datapath-windows/ovsext/Netlink/NetlinkBuf.c | 9 ++---
1 file changed, 6 insertions(+), 3 deletions(-)
diff --gi
In this change we have introduced buffer mgmt apis which will be
used while creating netlink messages. The basic functionality provided
by apis is on similar lines to ofpbuf in userspace with an exception
that it will not do run time buffer reallocation.
Signed-off-by: Ankur Sharma
Tested-by: Ank
In this change we have added the APIs for putting
netlink headers, attributes in a buffer.
The buffer is managed through NetlinkBuf.[c|h].
Signed-off-by: Ankur Sharma
Tested-by: Ankur Sharma
Reported-at: https://github.com/openvswitch/ovs-issues/issues/37
Acked-by: Eitan Eliahu
Acked-by: Alin
In this change we have introduced buffer mgmt apis which will be
used while creating netlink messages. The basic functionality provided
by apis is on similar lines to ofpbuf in userspace with an exception
that it will not do run time buffer reallocation.
Signed-off-by: Ankur Sharma
Tested-by: Ank
Since kernel stack is limited in size, it is not wise to using
recursive function with large stack frames.
This patch provides an alternative implementation of recirc action
without using recursion.
A per CPU fixed sized, 'deferred action FIFO', is used to store either
recirc or sample actions en
Future patches will change the recirc action implementation to not
using recursion. The stack depth detection is no longer necessary.
Signed-off-by: Andy Zhou
Acked-by: Pravin B Shelar
---
datapath/actions.c | 63 -
datapath/datapath.c | 6 +
On Tue, Sep 02, 2014 at 06:55:14PM -0700, Jesse Gross wrote:
> On Mon, Sep 1, 2014 at 1:10 AM, Simon Horman
> wrote:
> > On Thu, Aug 28, 2014 at 10:12:49AM +0900, Simon Horman wrote:
> >> On Wed, Aug 27, 2014 at 03:03:53PM -0500, Jesse Gross wrote:
> >> > On Wed, Aug 27, 2014 at 11:51 AM, Ben Pfa
On 09/03/14 17:59, Pravin Shelar wrote:
Both of us are saying same thing.
What I meant was for OVS use-case, where OVS wants to use offload for
switching flows, vswitchd userspace process can program HW offload
using kernel HW offload APIs directly from userspace, rather than
going through OVS k
We keep an outstanding, out of band, I/O request in the driver at all time.
Once an event generated the driver queues the event message, completes the
pending I/O and unblocks the calling thread through setting the event in the
overlapped structure n the NL socket. The thread will read all all eve
We keep an outstanding, out of band, I/O request in the driver at all time.
Once an event generated the driver queues the event message, completes the
pending I/O and unblocks the calling thread through setting the event in the
overlapped structure n the NL socket. The thread will read all all eve
64 matches
Mail list logo
