Hi Zhike,
On Fri, Dec 29, 2017 at 01:02:04PM +, 王志克 wrote:
> Hi tiwei,
>
> Can you please provide a patch for 16.11.4? Thanks.
>
Normally, most commits in the stable tree are backported
from the commits in the mainline tree which contains below
Cc line:
Cc: sta...@dpdk.org
This patch also
On Fri, 29 Dec 2017 15:27:03 +0100
Nirmoy Das wrote:
> Hi Ferruh,
>
> There is latency in the range of milliseconds when packets are passed
> through KNI up to the IP stack. With CONFIG_RTE_KNI_PREEMPT_DEFAULT=n
> its required sacrifice a cpu core. Do you have any suggestion to improve
> latency
On Tue, 21 Nov 2017 01:42:41 +
Ferruh Yigit wrote:
> To track modification:
> 380a7aab1ae2 ("mbuf: rename deprecated VLAN flags")
>
> Proposed deadline for PMDs is v18.02
>
> Signed-off-by: Ferruh Yigit
> ---
> doc/guides/nics/todo.rst | 11 +++
> 1 file changed, 11 insertions(+)
On Tue, 21 Nov 2017 01:42:37 +
Ferruh Yigit wrote:
> To track modification:
> 8f094a9ac5d7 ("mbuf: set mbuf fields while in pool")
>
> Proposed deadline for PMDs is v18.02
>
> Signed-off-by: Ferruh Yigit
> ---
> doc/guides/nics/todo.rst | 19 ++-
> 1 file changed, 14 inser
On Sat, Dec 23, 2017 at 10:36:34PM +, Matan Azrad wrote:
> Hi
> > -Original Message-
> > From: Neil Horman [mailto:nhor...@tuxdriver.com]
> > Sent: Friday, December 22, 2017 4:27 PM
> > To: Matan Azrad
> > Cc: Thomas Monjalon ; dev@dpdk.org; Bruce
> > Richardson ; Ananyev, Konstantin
Hi Ferruh,
There is latency in the range of milliseconds when packets are passed
through KNI up to the IP stack. With CONFIG_RTE_KNI_PREEMPT_DEFAULT=n
its required sacrifice a cpu core. Do you have any suggestion to improve
latency without sacrificing a cpu?
What do you think about using cond_res
From: Matan Azrad
In the port detach function, use the function to free an ethdev port
instead of changing its state directly.
Signed-off-by: Matan Azrad
Acked-by: Thomas Monjalon
---
v2: no change
v3: no change
---
lib/librte_ether/rte_ethdev.c | 2 +-
1 file changed, 1 insertion(+), 1 delet
From: Matan Azrad
There are new Ethernet device events - NEW and DESTROY, and new option
to register all ports by one call.
Adjust application to aforementioned changes.
Signed-off-by: Matan Azrad
---
v3: no change
---
app/test-pmd/parameters.c | 4
app/test-pmd/testpmd.c
When a PMD finishes probing, it creates the new port by calling
the function rte_eth_dev_allocate().
A notification of the new port is sent there to the upper layer.
When a PMD finishes removal of a port, it calls the function
rte_eth_dev_release_port().
A notification of the destroyed port is sen
From: Matan Azrad
Add option to register event callback for all ports by one call to
rte_eth_dev_callback_register using port_id=RTE_ETH_ALL.
In this case the callback is also registered to invalid ports.
Signed-off-by: Matan Azrad
Acked-by: Thomas Monjalon
---
v2:
- moved callback li
The pointer to the user parameter of the callback registration is
automatically pass to the callback function.
There is no point to allow changing this user parameter by a caller.
That's why this parameter is always set to NULL by PMDs and set only
in ethdev layer before calling the callback functi
This patchset aims to add notifications for ethdev ports
added or removed.
It will be especially useful for hotplug.
This v3 is gathering more related patches which were sent
individually (callback process cleanup and testpmd additions).
Matan Azrad (3):
ethdev: allow event registration for all
28/12/2017 23:10, Thomas Monjalon:
> The pointer to the user parameter of the callback registration is
> automatically pass to the callback function.
> There is no point to allow changing this user parameter by a caller.
> That's why this parameter is always set to NULL by PMDs and set only
> in et
30/11/2017 08:51, Matan Azrad:
> There are new Ethernet device events - NEW and DESTROY, and new option
> to register all ports by one call.
>
> Adjust application to aforementioned changes.
>
> Signed-off-by: Matan Azrad
> ---
> app/test-pmd/parameters.c | 4
> app/test-pmd/t
From: Matan Azrad
In the port detach function, use the function to free an ethdev port
instead of changing its state directly.
Signed-off-by: Matan Azrad
Acked-by: Thomas Monjalon
---
v2: no change, just grouped in a patchset
---
lib/librte_ether/rte_ethdev.c | 2 +-
1 file changed, 1 inserti
This patchset aims to add notifications for ethdev ports
added or removed.
It will be especially useful for hotplug.
The first patches were sent individually by Matan,
and now grouped in a consistent patchset v2.
Note: this patchset depends on
"ethdev: remove useless parameter in callback process
When a PMD finishes probing, it creates the new port by calling
the function rte_eth_dev_allocate().
A notification of the new port is sent there to the upper layer.
When a PMD finishes removal of a port, it calls the function
rte_eth_dev_release_port().
A notification of the destroyed port is sen
From: Matan Azrad
Add option to register event callback for all ports by one call to
rte_eth_dev_callback_register using port_id=RTE_ETH_ALL.
In this case the callback is also registered to invalid ports.
Signed-off-by: Matan Azrad
Acked-by: Thomas Monjalon
---
v2:
- moved callback li
Hi tiwei,
Can you please provide a patch for 16.11.4? Thanks.
Br,
Wang Zhike
This trivial patch fixes a typo in sample apps guide, in
the kernel nic interface (kni) section.
Using "-config", as it is now today in this doc, will not
work and will emit an error; it shuold be "--config" instead,
and this patch fixes it accordingly.
Signed-off-by: Rami Rosen
---
doc/guides
On 11/21/2017 04:42 AM, Ferruh Yigit wrote:
To track modification:
8f094a9ac5d7 ("mbuf: set mbuf fields while in pool")
Proposed deadline for PMDs is v18.02
Signed-off-by: Ferruh Yigit
---
doc/guides/nics/todo.rst | 19 ++-
1 file changed, 14 insertions(+), 5 deletions(-)
d
On 11/21/2017 04:42 AM, Ferruh Yigit wrote:
To track modification:
380a7aab1ae2 ("mbuf: rename deprecated VLAN flags")
Proposed deadline for PMDs is v18.02
Signed-off-by: Ferruh Yigit
---
doc/guides/nics/todo.rst | 11 +++
1 file changed, 11 insertions(+)
diff --git a/doc/guides/ni
Hi Matan,
Please find some review details below.
As this patch is needed for the notification of new ports,
I will re-send them in a patchset, with the minor modifications
described below.
04/12/2017 16:43, Matan Azrad:
> --- a/lib/librte_ether/rte_ethdev.c
> +++ b/lib/librte_ether/rte_ethdev.c
29/12/2017 08:55, Zhiyong Yang:
> For virtio legacy device, testpmd startup fails when using
> uio_pci_generic. The issue is caused by invoking the function
> pci_ioport_map. The right intr_handle.type is already set before
> calling it, we should avoid overwriting the default value "RTE_
> INTR_HA
Hi Ning,
On Fri, Dec 29, 2017 at 11:38:42AM +0800, Ning Li wrote:
> When using virtio-user with vhost-kernel to exchange
> packet with kernel networking stack, application can
> set the MAC of the tap interface via parameter.
>
> Signed-off-by: Ning Li
> ---
Thanks for the new version.
Just FY
This sample shows an instance of vDPA device driver based on vDPA
lib, this driver uses a standard virtio-net PCI device as vDPA
device, which can serve as a backend for a virtio-net pci device
in nested VM.
The key driver ops implemented are:
* vdpa_virtio_eng_init
Prepare a resource pool to be
vDPA device driver will need callfd to setup device VFIO interrupt.
Looking at QEMU vhost message sequence, the real callfd comes after
the other vring messages and just before SET_VRING_ENABLE.
This patch is to make sure we configure device only when all the
guest information is in hand.
Note: v
vDPA device driver needs to know all the guest virtio information which
is recorded in virtio_net structure.
Signed-off-by: Xiao Wang
---
lib/librte_vhost/Makefile | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/lib/librte_vhost/Makefile b/lib/librte_vhost/Makefile
index 4793
The vDPA device driver in later patch can use the existing pci api to
set up device.
Signed-off-by: Xiao Wang
---
drivers/bus/pci/linux/pci.c | 4 ++--
drivers/bus/pci/linux/pci_init.h | 8
drivers/bus/pci/linux/pci_vfio.c | 6 +++---
3 files changed, 13 insertions(+), 5 deletions(
Based on the vDPA RFC patch: "vhost: support selective datapath" (refer to
http://dpdk.org/dev/patchwork/patch/32644/), this patch set adds virtio-net
PCI device driver to enable a new vhost datapath.
This sample driver uses QEMU emulated virtio-net PCI device as vhost datapath
accelerator, the em
Increase the max vfio groups to 128.
Signed-off-by: Pavan Nikhilesh
---
config/defconfig_arm64-thunderx-linuxapp-gcc | 1 +
1 file changed, 1 insertion(+)
diff --git a/config/defconfig_arm64-thunderx-linuxapp-gcc
b/config/defconfig_arm64-thunderx-linuxapp-gcc
index 45038b119..d502b7822 100644
Make max vfio groups compile-time configurable so that platforms can
choose vfio group limit.
Signed-off-by: Pavan Nikhilesh
---
config/common_base | 1 +
lib/librte_eal/linuxapp/eal/eal_vfio.h | 2 +-
2 files changed, 2 insertions(+), 1 deletion(-)
diff --git a/config/commo
32 matches
Mail list logo
