[dpdk-dev,v8,4/4] ethdev: add control interface support
Checks
Commit Message
To have the support corresponding kernel module (UNCI) needs to be
inserted. If kernel module is not there, application will run as
it is without kernel control path support.
When UNCI module inserted, running application creates a virtual Linux
network interface (dpdk$) per DPDK port. This interface can be used by
traditional Linux tools.
If Userspace Network Control Interface (UNCI) kernel module
(rte_unci.ko) inserted, virtual interfaces created for each DPDK port
for control purposes.
Created interfaces are named as dpdk#, like:
$ ifconfig dpdk0; ifconfig dpdk1
dpdk0: flags=4099<UP,BROADCAST,MULTICAST> mtu 1500
ether 90:e2:ba:0e:49:b9 txqueuelen 1000 (Ethernet)
RX packets 0 bytes 0 (0.0 B)
RX errors 0 dropped 0 overruns 0 frame 0
TX packets 0 bytes 0 (0.0 B)
TX errors 0 dropped 0 overruns 0 carrier 0 collisions 0
dpdk1: flags=4099<UP,BROADCAST,MULTICAST> mtu 1500
ether 00:1b:21:76:fa:21 txqueuelen 1000 (Ethernet)
RX packets 0 bytes 0 (0.0 B)
RX errors 0 dropped 0 overruns 0 frame 0
TX packets 0 bytes 0 (0.0 B)
TX errors 0 dropped 0 overruns 0 carrier 0 collisions 0
Regular Linux commands can be issued on interfaces:
$ ethtool -i dpdk0
driver: net_ixgbe
version: DPDK 17.08.0-rc0
firmware-version: 0x61bf0001
expansion-rom-version:
bus-info: 0000:08:00.1
supports-statistics: no
supports-test: no
supports-eeprom-access: yes
supports-register-dump: yes
supports-priv-flags: no
Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com>
---
lib/librte_ether/rte_ethdev_pci.h | 15 ++++++++++++++-
1 file changed, 14 insertions(+), 1 deletion(-)
Comments
On Wed, 21 Jun 2017 12:06:51 +0100
Ferruh Yigit <ferruh.yigit@intel.com> wrote:
> To have the support corresponding kernel module (UNCI) needs to be
> inserted. If kernel module is not there, application will run as
> it is without kernel control path support.
>
> When UNCI module inserted, running application creates a virtual Linux
> network interface (dpdk$) per DPDK port. This interface can be used by
> traditional Linux tools.
>
> If Userspace Network Control Interface (UNCI) kernel module
> (rte_unci.ko) inserted, virtual interfaces created for each DPDK port
> for control purposes.
>
> Created interfaces are named as dpdk#, like:
>
> $ ifconfig dpdk0; ifconfig dpdk1
> dpdk0: flags=4099<UP,BROADCAST,MULTICAST> mtu 1500
> ether 90:e2:ba:0e:49:b9 txqueuelen 1000 (Ethernet)
> RX packets 0 bytes 0 (0.0 B)
> RX errors 0 dropped 0 overruns 0 frame 0
> TX packets 0 bytes 0 (0.0 B)
> TX errors 0 dropped 0 overruns 0 carrier 0 collisions 0
>
> dpdk1: flags=4099<UP,BROADCAST,MULTICAST> mtu 1500
> ether 00:1b:21:76:fa:21 txqueuelen 1000 (Ethernet)
> RX packets 0 bytes 0 (0.0 B)
> RX errors 0 dropped 0 overruns 0 frame 0
> TX packets 0 bytes 0 (0.0 B)
> TX errors 0 dropped 0 overruns 0 carrier 0 collisions 0
If you get the sysfs network links correct, then udev should be able to
generate peristent network names.
On 6/21/2017 4:24 PM, Stephen Hemminger wrote:
> On Wed, 21 Jun 2017 12:06:51 +0100
> Ferruh Yigit <ferruh.yigit@intel.com> wrote:
>
>> To have the support corresponding kernel module (UNCI) needs to be
>> inserted. If kernel module is not there, application will run as
>> it is without kernel control path support.
>>
>> When UNCI module inserted, running application creates a virtual Linux
>> network interface (dpdk$) per DPDK port. This interface can be used by
>> traditional Linux tools.
>>
>> If Userspace Network Control Interface (UNCI) kernel module
>> (rte_unci.ko) inserted, virtual interfaces created for each DPDK port
>> for control purposes.
>>
>> Created interfaces are named as dpdk#, like:
>>
>> $ ifconfig dpdk0; ifconfig dpdk1
>> dpdk0: flags=4099<UP,BROADCAST,MULTICAST> mtu 1500
>> ether 90:e2:ba:0e:49:b9 txqueuelen 1000 (Ethernet)
>> RX packets 0 bytes 0 (0.0 B)
>> RX errors 0 dropped 0 overruns 0 frame 0
>> TX packets 0 bytes 0 (0.0 B)
>> TX errors 0 dropped 0 overruns 0 carrier 0 collisions 0
>>
>> dpdk1: flags=4099<UP,BROADCAST,MULTICAST> mtu 1500
>> ether 00:1b:21:76:fa:21 txqueuelen 1000 (Ethernet)
>> RX packets 0 bytes 0 (0.0 B)
>> RX errors 0 dropped 0 overruns 0 frame 0
>> TX packets 0 bytes 0 (0.0 B)
>> TX errors 0 dropped 0 overruns 0 carrier 0 collisions 0
>
>
> If you get the sysfs network links correct, then udev should be able to
> generate peristent network names.
I didn't get this one, currently interface names are requested from
userspace via IFLA_IFNAME, as dpdk# .
@@ -38,6 +38,13 @@
#include <rte_pci.h>
#include <rte_ethdev.h>
+#ifdef RTE_LIBRTE_CTRL_IF
+#include <rte_ctrl_if.h>
+#else
+#define rte_eth_control_interface_create_one(port_id) do { } while(0)
+#define rte_eth_control_interface_destroy_one(port_id) do { } while(0)
+#endif
+
/**
* Copy pci device info to the Ethernet device data.
*
@@ -157,8 +164,12 @@ rte_eth_dev_pci_generic_probe(struct rte_pci_device *pci_dev,
RTE_FUNC_PTR_OR_ERR_RET(*dev_init, -EINVAL);
ret = dev_init(eth_dev);
- if (ret)
+ if (ret) {
rte_eth_dev_pci_release(eth_dev);
+ return ret;
+ }
+
+ rte_eth_control_interface_create_one(eth_dev->data->port_id);
return ret;
}
@@ -179,6 +190,8 @@ rte_eth_dev_pci_generic_remove(struct rte_pci_device *pci_dev,
if (!eth_dev)
return -ENODEV;
+ rte_eth_control_interface_destroy_one(eth_dev->data->port_id);
+
if (dev_uninit) {
ret = dev_uninit(eth_dev);
if (ret)