Yes, this is cause a bug which prevents cross-socket testing... per michael.qiu
at intel.com on Fri 12/18/2015 5:33 PM (unable to find email on the list)
>> Hi, Stephen
>>
>> I just see this patch and found some issue with it.
>>
>> When I start testpmd with -c 0x3 but with socket-num 1, that
Found it...
http://www.dpdk.org/ml/archives/dev/2015-December/030564.html
-- Stephen Hurd
-Original Message-
From: Bruce Richardson [mailto:bruce.richard...@intel.com]
Sent: Thursday, January 14, 2016 5:44 AM
To: Stephen Hurd
Cc: dev at dpdk.org
Subject: Re: [dpdk-dev] [PATCH v2]
Hi, Rahul
> This approach seems generic enough to allow any vendor specific data
> to be passed in filter as well. However, 80 seems to be too low for
> multiple flow types that can be combined in the same filter rule.
> I think size of 256 seems reasonable.
>
Yes, 80 is just an example.
>
i40e base driver is updated, to support new X722 device IDs, and
use rx control AQ commands to read/write rx control registers.
Of cause, fixes and enhancements are added as listed as below.
Helin Zhang (29):
i40e/base: use explicit cast from u16 to u8
i40e/base: Acquire NVM, before issuing
Current implementation generates compilation warnings.
Signed-off-by: Helin Zhang
---
drivers/net/i40e/base/i40e_lan_hmc.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/net/i40e/base/i40e_lan_hmc.c
b/drivers/net/i40e/base/i40e_lan_hmc.c
index 6511767..2260648
It needs to acquire the NVM before issuing an AQ read to the
X722 NVM otherwise it will get EBUSY from the FW. Also release
when done.
Signed-off-by: Helin Zhang
---
drivers/net/i40e/base/i40e_nvm.c | 35 +--
1 file changed, 29 insertions(+), 6 deletions(-)
diff
Instead of doing the MAC check, use a flag that gets set per
MAC. This way there are less chances of user error and it
can enable multiple MACs with the capability in a single place
rather than cluttering the code with MAC checks.
Signed-off-by: Helin Zhang
---
In X722, NVM reads can't be done through SRCTL registers.
And require AQ calls, which require grabbing the NVM lock.
Unfortunately some paths need the lock to be acquired once
and do a whole bunch of stuff and then release it.
This patch creates an unsafe version of the read calls, so
that it can
XL710/X710 devices requires FW version checks to properly handle
DCB configurations from the FW while other devices (e.g. X722)
do not, so limit these checks to XL710/X710 only.
Signed-off-by: Helin Zhang
---
drivers/net/i40e/base/i40e_dcb.c | 34 +-
1 file
It's possible that while waiting for the spinlock, another
entity (that owns the spinlock) has shut down the admin queue.
If it then attempts to use the queue, it will panic.
It adds a check for this condition on the receive side. This
matches an existing check on the send queue side.
The standard way to check if the AQ is enabled is to look at the
count field. So it should only set this field after it has
successfully allocated memory. To do otherwise is to incite
panic among the populace.
Signed-off-by: Helin Zhang
---
drivers/net/i40e/base/i40e_adminq.c | 4 ++--
1 file
In one obscure corner case, it was possible to clear the NVM update
wait flag when no update_done message was actually received. This
patch cleans the event descriptor before use, and moves the opcode
check to where it won't get done if there was no event to clean.
Signed-off-by: Helin Zhang
---
Add new Device ID's for backplane and QSFP+ adapters, and delete
deprecated one for backplane.
Signed-off-by: Helin Zhang
---
drivers/net/i40e/base/i40e_common.c | 12 ++--
drivers/net/i40e/base/i40e_devids.h | 10 +-
2 files changed, 19 insertions(+), 3 deletions(-)
diff --git
The recently added opcodes should be available only with X722
SUPPORT, so move them into the #ifdef, and reorder these to be
in numerical order with the rest of the opcodes. Several structs
that were added are unnecessary, so they are removed here.
Signed-off-by: Helin Zhang
---
The device capabilities were defined in two places, and neither had
all the definitions. It really belongs with the AQ API definition,
so this patch removes the other set of definitions and fills out the
missing item.
Signed-off-by: Helin Zhang
---
drivers/net/i40e/base/i40e_adminq_cmd.h | 1
This patch implements necessary functions related to port
mirroring features such as add/delete mirror rule, function
to set promiscuous VLAN mode for VSI if mirror rule_type is
"VLAN Mirroring".
Signed-off-by: Helin Zhang
---
drivers/net/i40e/base/i40e_common.c| 162
Add the use of the new Shared MAC filter bit for multicast
and broadcast filters in order to make better use of the
filters available from the device. The FW folks have assured
that setting this bit on older FW will have no affect, so it
doesn't need a version check.
Signed-off-by: Helin Zhang
With the latest firmware, statistics gathering can now be enabled and
disabled in the HW switch, so we need to add a parameter to allow the
driver to set it as desired. At the same time, the L2 cloud filtering
parameter has been removed as it was never used.
Older drivers working with the newer
Add the support code for calling the AdminQ API call
aq_set_switch_config.
Signed-off-by: Helin Zhang
---
drivers/net/i40e/base/i40e_adminq_cmd.h | 12
drivers/net/i40e/base/i40e_common.c | 28
drivers/net/i40e/base/i40e_prototype.h | 3 +++
3
This patch adds functions to blink led on devices using
Coppervale PHY since MAC registers used in other designs
do not work in this device configuration.
Signed-off-by: Helin Zhang
---
drivers/net/i40e/base/i40e_common.c| 329 +
In MFP mode particularly when we were setting the PF VSI in limited
promiscuous, the HW switch was still mirroring the outgoing packets
from other VSIs (VF/VMdq) onto the PF VSI.
With this new bit set, the mirroring doesn't happen any more and so
we are in limited promiscuous on the PF VSI in MFP
When linking with particular PHY types (ex: copper PHY), the amount of
time it takes for the GLGEN_RSTAT_DEVSTATE to be set increases greatly,
which can lead to a timeout and failure to load the driver.
Signed-off-by: Helin Zhang
---
drivers/net/i40e/base/i40e_common.c | 6 +++---
1 file
When updating a VSI, save off the number of allocated and
unallocated VSIs as we do when adding a VSI.
Signed-off-by: Helin Zhang
---
drivers/net/i40e/base/i40e_common.c | 6 ++
1 file changed, 6 insertions(+)
diff --git a/drivers/net/i40e/base/i40e_common.c
It adds coding style fixes.
Signed-off-by: Helin Zhang
---
drivers/net/i40e/base/i40e_common.c | 19 ---
1 file changed, 12 insertions(+), 7 deletions(-)
diff --git a/drivers/net/i40e/base/i40e_common.c
b/drivers/net/i40e/base/i40e_common.c
index 9a0b787..e94f726 100644
---
RX control register read/write functions are added, as directly
read/write may fail when under stress small traffic. After the
adminq is ready, all rx control registers should be read/written
by dedicated functions.
Signed-off-by: Helin Zhang
---
drivers/net/i40e/base/i40e_adminq_cmd.h | 16
This patch adds 7 new register definitions for programming the
parser, flow director and RSS blocks in the HW.
Signed-off-by: Helin Zhang
---
drivers/net/i40e/base/i40e_register.h | 48 +++
drivers/net/i40e/i40e_ethdev.c| 11 ++--
2 files changed, 50
It adds the new AQ command and struct for managing a
thermal sensor.
Signed-off-by: Helin Zhang
---
drivers/net/i40e/base/i40e_adminq_cmd.h | 17 +
1 file changed, 17 insertions(+)
diff --git a/drivers/net/i40e/base/i40e_adminq_cmd.h
b/drivers/net/i40e/base/i40e_adminq_cmd.h
Several structures and macros are added or updated, such
as 'struct i40e_aqc_get_link_status',
'struct i40e_aqc_run_phy_activity' and
'struct i40e_aqc_lldp_set_local_mib_resp'.
Signed-off-by: Helin Zhang
---
drivers/net/i40e/base/i40e_adminq_cmd.h | 45 ++---
It adds base driver release information such as release date,
for better tracking in the future.
Signed-off-by: Helin Zhang
---
drivers/net/i40e/Makefile | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/net/i40e/Makefile b/drivers/net/i40e/Makefile
index 033ee4a..6dd6eaa 100644
---
It adds several new device IDs, and also removed one which is
not used at all.
Signed-off-by: Helin Zhang
---
doc/guides/rel_notes/release_2_3.rst| 15 +++
lib/librte_eal/common/include/rte_pci_dev_ids.h | 8 ++--
2 files changed, 21 insertions(+), 2 deletions(-)
As required, rx control registers have to be read/written by
rx control functions, otherwise if may fail to read/write
when under stress small traffic.
Signed-off-by: Helin Zhang
---
drivers/net/i40e/i40e_ethdev.c| 66 ---
X722 supports Expanded version of TCP, UDP PCTYPES for RSS.
Add a Virtchnl offload to support this.
Without this patch VF drivers will not be able to support
the correct PCTYPES for X722 and UDP flows will not fan out.
Signed-off-by: Helin Zhang
---
drivers/net/i40e/base/i40e_virtchnl.h | 1 +
v4: - mark "src" arg as const for write_dev_cfg operation
- remove unnessary inline, and likely/unlikely
v3: - export pci_unmap_device as well; and invoke it at virtio
uninit stage.
- fixed same data corruption bug reported by Qian in simple
rxtx code path.
- move
As we have already set up it at virtio_dev_queue_setup(), and a vq
restart will not reset the settings.
Signed-off-by: Yuanhan Liu
---
drivers/net/virtio/virtio_rxtx.c | 15 ---
1 file changed, 15 deletions(-)
diff --git a/drivers/net/virtio/virtio_rxtx.c
Introduce struct virtio_pci_ops, to let legacy virtio (v0.95) and
modern virtio (1.0) have different implementation regarding to a
specific pci action, such as read host status.
With that, this patch reimplements all exported pci functions, in
a way like:
vtpci_foo_bar(struct virtio_hw
virtio_pci.c is a more proper place for pci stuff; virtio_ethdev is not.
Signed-off-by: Yuanhan Liu
---
drivers/net/virtio/virtio_ethdev.c | 265 +---
drivers/net/virtio/virtio_pci.c| 270 -
2 files changed, 270
Switch to 64 bit features, which virtio 1.0 supports.
While legacy virtio only supports 32 bit features, it complains aloud
and quit when trying to setting > 32 bit features.
Signed-off-by: Yuanhan Liu
---
drivers/net/virtio/virtio_ethdev.c | 8
drivers/net/virtio/virtio_pci.c|
The mergeable virtio net hdr format has been the standard and the
only virtio net hdr format since virtio 1.0. Therefore, we can
not hardcode hdr_size to "sizeof(struct virtio_net_hdr)" any more
at virtio_recv_pkts(), otherwise, there would be a mismatch of
hdr size from rte_vhost_enqueue_burst()
Normally we could set RTE_PCI_DRV_NEED_MAPPING flag so that eal will
invoke pci_map_device internally for us. From that point view, there
is no need to export pci_map_device.
However, for virtio pmd driver, which is designed to work without
binding UIO (or something similar first),
Modern (v1.0) virtio pci device defines several pci capabilities.
Each cap has a configure structure corresponding to it, and the
cap.bar and cap.offset fields tell us where to find it.
Firstly, we map the pci resources by rte_eal_pci_map_device().
We then could easily locate a cfg structure by:
virtio_pci.c is the only file references those macros; move them there.
Signed-off-by: Yuanhan Liu
---
drivers/net/virtio/virtio_pci.c | 19 +++
drivers/net/virtio/virtio_pci.h | 18 --
2 files changed, 19 insertions(+), 18 deletions(-)
diff --git
On Thu, Jan 14, 2016 at 06:58:29PM +0530, Santosh Shukla wrote:
...
> +int rte_eal_pci_read_bar(const struct rte_pci_device *device,
> + void *buf, size_t len, off_t offset,
> + int bar_idx)
> +
> +{
> +#ifdef VFIO_PRESENT
> + const struct
On Thu, Jan 14, 2016 at 06:58:30PM +0530, Santosh Shukla wrote:
> For vfio case - Use pread/pwrite api to access virtio
> ioport space.
>
> Signed-off-by: Santosh Shukla
> Signed-off-by: Rizwan Ansari
> Signed-off-by: Rakesh Krishnamurthy
> ---
...
> +/* vfio rd/rw virtio apis */
> +static
On Thu, Jan 14, 2016 at 06:58:31PM +0530, Santosh Shukla wrote:
> So far virtio handle rw access for uio / ioport interface, This patch to
> extend
> the support for vfio interface. For that introducing private struct
> virtio_vfio_dev{
> - is_vfio
> - pci_dev
> };
>
On Thu, Jan 14, 2016 at 06:58:32PM +0530, Santosh Shukla wrote:
> Introducing api to check interface type is vfio or not, if interface is vfio
> then update struct virtio_vfio_dev {}.
>
> Those two apis are:
> - virtio_chk_for_vfio
> - virtio_hw_init_by_vfio
>
> Signed-off-by: Santosh Shukla
..
On Thu, Jan 14, 2016 at 06:58:34PM +0530, Santosh Shukla wrote:
> Enable RTE_LIBRTE_VIRTIO_PMD for armv7/v8 and setting RTE_VIRTIO_INC_VEC=n.
> Builds successfully for armv7/v8.
I guess you could squash this patch to 2nd patch.
--yliu
> -Original Message-
> From: Stephen Hemminger [mailto:stephen at networkplumber.org]
> Sent: Friday, January 15, 2016 12:49 AM
> To: Wang, Zhihong
> Cc: dev at dpdk.org; Ananyev, Konstantin ;
> Richardson, Bruce ; Xie, Huawei
>
> Subject: Re: [PATCH 0/4] Optimize memcpy for AVX512
Hi Amit,
On 1/14/2016 8:03 PM, Amit Tomer wrote:
> Hello,
>
>> Not necessary. But if you want to use hugepages inside Docker, use -v option
>> to map a hugetlbfs into containers.
> I modified Docker command line in order to make use of Hugetlbfs:
>
> CMD
On Thu, Jan 14, 2016 at 06:58:24PM +0530, Santosh Shukla wrote:
> virtio_recv_pkts_vec and other virtio vector friend apis are written for
> sse/avx
> instructions. For arm64 in particular, virtio vector implementation does not
> exist(todo).
>
> So virtio pmd driver wont build for targets like
Hi Jingjing,
On Thursday, January 01/14/16, 2016 at 17:30:53 -0800, Wu, Jingjing wrote:
> Hi, Rahul
>
> > This approach seems generic enough to allow any vendor specific data
> > to be passed in filter as well. However, 80 seems to be too low for
> > multiple flow types that can be combined in
Hello!
> If this is the case, i am wondering whether we should include
> "malfunctioning clients" in commit message. It triggers me to think if
> there are existing buggy implementations.
Well... Can you suggest how to rephrase it? May be "if a client is
malfunctioning it can..."? I lack
On Tue, Jan 12, 2016 at 02:46:07PM +0200, Panu Matilainen wrote:
> On 01/12/2016 12:49 PM, Nelio Laranjeiro wrote:
> >Allow long command lines in testpmd (like flow director with IPv6, ...).
> >
> >Signed-off-by: John McNamara
> >Signed-off-by: Nelio Laranjeiro
> >---
> >
Tested-by: Qian Xu
- Test Commit: ad66a85dce9a707748cb4d9592c13022ae77c067
- OS/Kernel: Fedora 21/4.1.13
- GCC: gcc (GCC) 4.9.2 20141101 (Red Hat 4.9.2-1)
- CPU: Intel(R) Xeon(R) CPU E5-2695 v4 @ 2.10
- NIC: Intel Corporation 82599ES 10-Gigabit SFI/SFP+ Network Connection (rev 01)
- Target:
On 01/15/2016 10:44 AM, N?lio Laranjeiro wrote:
> On Tue, Jan 12, 2016 at 02:46:07PM +0200, Panu Matilainen wrote:
>> On 01/12/2016 12:49 PM, Nelio Laranjeiro wrote:
>>> Allow long command lines in testpmd (like flow director with IPv6, ...).
>>>
>>> Signed-off-by: John McNamara
>>>
On Fri, Jan 15, 2016 at 01:01:04AM +, Stephen Hurd wrote:
> Found it...
> http://www.dpdk.org/ml/archives/dev/2015-December/030564.html
>
>
> -- Stephen Hurd
>
Thanks for that. For some reason I missed the rest of the email thread from
earlier.
/Bruce
>
> -Original Message-
>
On Fri, Jan 15, 2016 at 10:40:24AM +0800, Helin Zhang wrote:
> i40e base driver is updated, to support new X722 device IDs, and
> use rx control AQ commands to read/write rx control registers.
> Of cause, fixes and enhancements are added as listed as below.
>
> Helin Zhang (29):
> i40e/base:
On Fri, Jan 15, 2016 at 12:05 PM, Yuanhan Liu
wrote:
> On Thu, Jan 14, 2016 at 06:58:32PM +0530, Santosh Shukla wrote:
>> Introducing api to check interface type is vfio or not, if interface is vfio
>> then update struct virtio_vfio_dev {}.
>>
>> Those two apis are:
>> - virtio_chk_for_vfio
>> -
On Fri, Jan 15, 2016 at 11:57 AM, Yuanhan Liu
wrote:
> On Thu, Jan 14, 2016 at 06:58:31PM +0530, Santosh Shukla wrote:
>> So far virtio handle rw access for uio / ioport interface, This patch to
>> extend
>> the support for vfio interface. For that introducing private struct
>> virtio_vfio_dev{
On Fri, Jan 15, 2016 at 12:07 PM, Yuanhan Liu
wrote:
> On Thu, Jan 14, 2016 at 06:58:34PM +0530, Santosh Shukla wrote:
>> Enable RTE_LIBRTE_VIRTIO_PMD for armv7/v8 and setting RTE_VIRTIO_INC_VEC=n.
>> Builds successfully for armv7/v8.
>
> I guess you could squash this patch to 2nd patch.
>
Yes.
A new ether API rte_eth_dev_get_ptype_info() is added to query what
packet type information will be provided by current pmd driver of the
specifed port.
To achieve this, a new function pointer, dev_ptype_info_get, is added
into struct eth_dev_ops. For those devices who do not implement it, it
Add a new API rte_eth_dev_get_ptype_info to query wether/what packet type will
be filled by given pmd rx burst function.
Signed-off-by: Jianfeng Tan
---
lib/librte_ether/rte_ethdev.c | 20
lib/librte_ether/rte_ethdev.h | 27 +++
Signed-off-by: Jianfeng Tan
---
drivers/net/cxgbe/cxgbe_ethdev.c | 14 ++
1 file changed, 14 insertions(+)
diff --git a/drivers/net/cxgbe/cxgbe_ethdev.c b/drivers/net/cxgbe/cxgbe_ethdev.c
index 97ef152..1699d8e 100644
--- a/drivers/net/cxgbe/cxgbe_ethdev.c
+++
Signed-off-by: Jianfeng Tan
---
drivers/net/e1000/igb_ethdev.c | 30 ++
1 file changed, 30 insertions(+)
diff --git a/drivers/net/e1000/igb_ethdev.c b/drivers/net/e1000/igb_ethdev.c
index d1bbcda..1eb1091 100644
--- a/drivers/net/e1000/igb_ethdev.c
+++
Signed-off-by: Jianfeng Tan
---
drivers/net/enic/enic_ethdev.c | 17 +
1 file changed, 17 insertions(+)
diff --git a/drivers/net/enic/enic_ethdev.c b/drivers/net/enic/enic_ethdev.c
index 2a88043..9d3659d 100644
--- a/drivers/net/enic/enic_ethdev.c
+++
Signed-off-by: Jianfeng Tan
---
drivers/net/fm10k/fm10k_ethdev.c | 43 ++
drivers/net/fm10k/fm10k_rxtx.c | 5 +
drivers/net/fm10k/fm10k_rxtx_vec.c | 5 +
3 files changed, 53 insertions(+)
diff --git a/drivers/net/fm10k/fm10k_ethdev.c
Signed-off-by: Jianfeng Tan
---
drivers/net/i40e/i40e_ethdev.c| 1 +
drivers/net/i40e/i40e_ethdev_vf.c | 1 +
drivers/net/i40e/i40e_rxtx.c | 46 ++-
drivers/net/i40e/i40e_rxtx.h | 1 +
4 files changed, 48 insertions(+), 1 deletion(-)
diff
Signed-off-by: Jianfeng Tan
---
drivers/net/ixgbe/ixgbe_ethdev.c | 38 ++
drivers/net/ixgbe/ixgbe_ethdev.h | 2 ++
drivers/net/ixgbe/ixgbe_rxtx.c | 5 -
3 files changed, 44 insertions(+), 1 deletion(-)
diff --git a/drivers/net/ixgbe/ixgbe_ethdev.c
Signed-off-by: Jianfeng Tan
---
drivers/net/mlx4/mlx4.c | 20
1 file changed, 20 insertions(+)
diff --git a/drivers/net/mlx4/mlx4.c b/drivers/net/mlx4/mlx4.c
index 207bfe2..b906a14 100644
--- a/drivers/net/mlx4/mlx4.c
+++ b/drivers/net/mlx4/mlx4.c
@@ -2836,6 +2836,8 @@
Signed-off-by: Jianfeng Tan
---
drivers/net/mlx5/mlx5.c| 1 +
drivers/net/mlx5/mlx5.h| 1 +
drivers/net/mlx5/mlx5_ethdev.c | 18 ++
drivers/net/mlx5/mlx5_rxtx.c | 2 ++
4 files changed, 22 insertions(+)
diff --git a/drivers/net/mlx5/mlx5.c
Signed-off-by: Jianfeng Tan
---
drivers/net/nfp/nfp_net.c | 17 +
1 file changed, 17 insertions(+)
diff --git a/drivers/net/nfp/nfp_net.c b/drivers/net/nfp/nfp_net.c
index bc2089f..b8da71e 100644
--- a/drivers/net/nfp/nfp_net.c
+++ b/drivers/net/nfp/nfp_net.c
@@ -1075,6 +1075,22
Signed-off-by: Jianfeng Tan
---
drivers/net/vmxnet3/vmxnet3_ethdev.c | 16
1 file changed, 16 insertions(+)
diff --git a/drivers/net/vmxnet3/vmxnet3_ethdev.c
b/drivers/net/vmxnet3/vmxnet3_ethdev.c
index c363bf6..ed9cd14 100644
--- a/drivers/net/vmxnet3/vmxnet3_ethdev.c
+++
As a example to use ptype info, l3fwd needs firstly to use
rte_eth_dev_get_ptype_info() API to check if device and/or PMD driver will
parse and fill the needed packet type. If not, use the newly added option,
--parse-ptype, to analyze it in the callback softly.
Signed-off-by: Jianfeng Tan
---
On Fri, Jan 15, 2016 at 6:13 PM, Santosh Shukla wrote:
> On Fri, Jan 15, 2016 at 11:57 AM, Yuanhan Liu
> wrote:
>> On Thu, Jan 14, 2016 at 06:58:31PM +0530, Santosh Shukla wrote:
>>> So far virtio handle rw access for uio / ioport interface, This patch to
>>> extend
>>> the support for vfio
Hi Jianfeng, a few comments below.
On Fri, Jan 15, 2016 at 01:45:48PM +0800, Jianfeng Tan wrote:
> Add a new API rte_eth_dev_get_ptype_info to query wether/what packet type will
> be filled by given pmd rx burst function.
>
> Signed-off-by: Jianfeng Tan
> ---
> lib/librte_ether/rte_ethdev.c |
Date: Fri, 15 Jan 2016 15:25:30 +0100
Message-Id: <1452867932-5548-1-git-send-email-tomaszx.kulasek at intel.com>
X-Mailer: git-send-email 2.1.4
Many sample apps include internal buffering for single-packet-at-a-time
operation. Since this is such a common paradigm, this functionality is
better
Date: Fri, 15 Jan 2016 15:25:31 +0100
Message-Id: <1452867932-5548-2-git-send-email-tomaszx.kulasek at intel.com>
X-Mailer: git-send-email 2.1.4
In-Reply-To: <1452867932-5548-1-git-send-email-tomaszx.kulasek at intel.com>
References: <1452867932-5548-1-git-send-email-tomaszx.kulasek at intel.com>
Date: Fri, 15 Jan 2016 15:25:32 +0100
Message-Id: <1452867932-5548-3-git-send-email-tomaszx.kulasek at intel.com>
X-Mailer: git-send-email 2.1.4
In-Reply-To: <1452867932-5548-1-git-send-email-tomaszx.kulasek at intel.com>
References: <1452867932-5548-1-git-send-email-tomaszx.kulasek at intel.com>
Many sample apps include internal buffering for single-packet-at-a-time
operation. Since this is such a common paradigm, this functionality is
better suited to being inside the core ethdev API.
The new APIs in the ethdev library are:
* rte_eth_tx_buffer - buffer up a single packet for future
Many sample apps include internal buffering for single-packet-at-a-time
operation. Since this is such a common paradigm, this functionality is
better suited to being inside the core ethdev API.
The new APIs in the ethdev library are:
* rte_eth_tx_buffer - buffer up a single packet for future
The internal buffering of packets for TX in sample apps is no longer
needed, so this patchset replaces this code with calls to the new
rte_eth_tx_buffer* APIs in:
* l2fwd-jobstats
* l2fwd-keepalive
* l2fwd
* l3fwd-acl
* l3fwd-power
* link_status_interrupt
* client_server_mp
* l2fwd_fork
*
Hi Jianfeng,
> -Original Message-
> From: Tan, Jianfeng
> Sent: Friday, January 15, 2016 5:46 AM
> To: dev at dpdk.org
> Cc: Zhang, Helin; Ananyev, Konstantin; Tan, Jianfeng
> Subject: [PATCH v2 12/12] examples/l3fwd: add option to parse ptype
>
> As a example to use ptype info, l3fwd
> -Original Message-
> From: Tan, Jianfeng
> Sent: Friday, January 15, 2016 5:46 AM
> To: dev at dpdk.org
> Cc: Zhang, Helin; Ananyev, Konstantin; Tan, Jianfeng
> Subject: [PATCH v2 07/12] pmd/ixgbe: add dev_ptype_info_get implementation
>
> Signed-off-by: Jianfeng Tan
> ---
>
Sorry, winzip changes eols.
> -Original Message-
> From: Tan, Jianfeng
> Sent: Friday, January 15, 2016 5:46 AM
> To: dev at dpdk.org
> Cc: Zhang, Helin; Ananyev, Konstantin; Tan, Jianfeng
> Subject: [PATCH v2 01/12] ethdev: add API to query packet type filling info
>
> Add a new API rte_eth_dev_get_ptype_info to
Hi lads,
> -Original Message-
> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Adrien Mazarguil
> Sent: Friday, January 15, 2016 1:59 PM
> To: Tan, Jianfeng
> Cc: dev at dpdk.org
> Subject: Re: [dpdk-dev] [PATCH v2 01/12] ethdev: add API to query packet type
> filling info
>
>
On Fri, Jan 15, 2016 at 03:11:18PM +, Ananyev, Konstantin wrote:
> Hi lads,
>
> > -Original Message-
> > From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Adrien Mazarguil
> > Sent: Friday, January 15, 2016 1:59 PM
> > To: Tan, Jianfeng
> > Cc: dev at dpdk.org
> > Subject: Re:
Control interface APIs added into the sample application.
To have the support corresponding kernel module (KCP) needs to be inserted.
If kernel module is not there, application will run as it is without
kernel control path support.
When KCP module inserted, running application creates a virtual
This kernel module is based on KNI module, but this one is stripped
version of it and only for control messages, no data transfer
functionality provided.
This Linux kernel module helps userspace application create virtual
interfaces and when a control command issued into that virtual
interface,
This library gets control messages form kernelspace and forwards them to
librte_ether and returns response back to the kernelspace.
Library does:
1) Trigger Linux virtual interface creation
2) Initialize the netlink socket communication
3) Provides process() API to the application that does
> -Original Message-
> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Matthew Hall
> Sent: Wednesday, January 13, 2016 5:26 PM
> To: dev at dpdk.org
> Subject: [dpdk-dev] UX Bug in Sphinx HTML Layout for Programming Guide
> (and maybe other guides?)
>
> When you go to this link:
Hi,
I've been asked this question, and I realized I'm not sure about the
answer. In other words: can you call rte_eth_tx_burst() and
rte_eth_tx_burst() on the same port at the same time from different
threads? In theory it seems possible, as you still access different
queues (an RX and a TX
On Fri, Jan 15, 2016 at 04:54:11PM +, Zoltan Kiss wrote:
> Can you call rte_eth_tx_burst() and rte_eth_tx_burst() on the same port at
> the same time from different threads?
In general, yes you can. I did this before in an L4-L7 performance tester, so
cores could concentrate on RX or TX to
On Fri, 15 Jan 2016 15:43:56 +0100
Tomasz Kulasek wrote:
> Many sample apps include internal buffering for single-packet-at-a-time
> operation. Since this is such a common paradigm, this functionality is
> better suited to being inside the core ethdev API.
> The new APIs in the ethdev library
On Fri, 15 Jan 2016 15:43:57 +0100
Tomasz Kulasek wrote:
> static int
> rte_eth_dev_tx_queue_config(struct rte_eth_dev *dev, uint16_t nb_queues)
> {
> uint16_t old_nb_queues = dev->data->nb_tx_queues;
> void **txq;
> + struct rte_eth_dev_tx_buffer *new_bufs;
> unsigned
On Fri, 15 Jan 2016 15:43:57 +0100
Tomasz Kulasek wrote:
> + return -(ENOMEM);
Please don't put () around args to return, it is a BSD stylism
On Fri, 15 Jan 2016 12:33:14 -0500
Matthew Hall wrote:
> On Fri, Jan 15, 2016 at 04:54:11PM +, Zoltan Kiss wrote:
> > Can you call rte_eth_tx_burst() and rte_eth_tx_burst() on the same port at
> > the same time from different threads?
>
> In general, yes you can. I did this before in an
Hi Tomasz,
> static int
> rte_eth_dev_tx_queue_config(struct rte_eth_dev *dev, uint16_t nb_queues)
> {
> uint16_t old_nb_queues = dev->data->nb_tx_queues;
> void **txq;
> + struct rte_eth_dev_tx_buffer *new_bufs;
> unsigned i;
>
> if (dev->data->tx_queues == NULL)
2016-01-15 16:35, John McNamara:
> Fix issue where the navigation levels weren't displayed in the
> html sidebar with the new read_the_docs theme.
>
> This was due to the :titlesonly: directive in the high level
> index.rst and also due to a stray newline in the parsed version
> number.
I'm
Le 14 janv. 2016 22:39, "Wang, Zhihong" a ?crit :
>
>
>
> > -Original Message-
> > From: Stephen Hemminger [mailto:stephen at networkplumber.org]
> > Sent: Friday, January 15, 2016 12:49 AM
> > To: Wang, Zhihong
> > Cc: dev at dpdk.org; Ananyev, Konstantin ;
> > Richardson, Bruce ; Xie,
99 matches
Mail list logo
