Add new meta pattern item RTE_FLOW_TYPE_ITEM_ROUGHLY.
This is for device that support no-perfect match option.
Usually a no-perfect match is fast but the cost is accuracy.
i.e. Signature Match only match pattern's hash value, but it is
possible two different patterns have the same hash value.
Mat
This patch supports input set selection for flow
director filter.
Signed-off-by: Beilei Xing
---
drivers/net/i40e/i40e_ethdev.c | 8 +-
drivers/net/i40e/i40e_ethdev.h | 8 +
drivers/net/i40e/i40e_flow.c | 527 ++---
3 files changed, 296 insertions(+), 24
This patch updates supported patterns for flow
director filters.
Signed-off-by: Beilei Xing
---
drivers/net/i40e/i40e_flow.c | 1370 +-
1 file changed, 1346 insertions(+), 24 deletions(-)
diff --git a/drivers/net/i40e/i40e_flow.c b/drivers/net/i40e/i40e_f
This patch adds flexible payload parsing support for
flow director filter.
Signed-off-by: Beilei Xing
---
drivers/net/i40e/i40e_ethdev.h | 23
drivers/net/i40e/i40e_fdir.c | 19 ---
drivers/net/i40e/i40e_flow.c | 298 -
3 files changed, 317 inse
1. Support flexible payload
2. Support reconfiguration of input set
3. Add new supported patterns
Beilei Xing (3):
net/i40e: support flexible payload parsing for FDIR
net/i40e: support input set selection for FDIR
net/i40e: update supported patterns for FDIR
drivers/net/i40e/i40e_ethdev.c
Hello David,
On Tuesday 23 May 2017 03:58 PM, David Hunt wrote:
Users can now use 'make defconfig' to generate a configuration using
the most appropriate defaults for the current machine.
arch taken from uname -m
machine defaults to native
execenv is taken from uname, Linux=linuxapp, oth
Signed-off-by: Shreyansh Jain
---
This was missed while adding the rte_bus code. (But, this is not a fix)
Also, I couldn't find any maintainer listed for common/include/* code
in MAINTAINERS, so, sending 'to' dev@ list.
lib/librte_eal/common/include/rte_log.h | 1 +
1 file changed, 1 inserti
Hi Jerin,
Comments inline.
Also, another function needed is
bool rte_event_eth_rx_adapter_multithread_capable(void).
This would be used to set the "multithread_capable" service core
configuration parameter.
Thanks,
Nikhil
On 5/11/2017 10:08 PM, Jerin Jacob wrote:
> -Original Message
Hi,
> -Original Message-
> From: Adrien Mazarguil [mailto:adrien.mazarg...@6wind.com]
> Sent: Tuesday, May 23, 2017 5:51 PM
> To: Zhao1, Wei
> Cc: dev@dpdk.org; Xing, Beilei
> Subject: Re: [dpdk-dev] [PATCH v3 01/25] ethdev: introduce generic flow API
>
> Hi Wei,
>
> On Tue, May 23, 2017
Hi Gregory,
From: Gregory Etelson [mailto:greg...@weka.io]
Sent: Tuesday, May 23, 2017 7:13 PM
To: Lu, Wenzhuo
Cc: dev@dpdk.org; Richardson, Bruce; Yigit, Ferruh; Zhang, Qi Z
Subject: Re: [dpdk-dev] ixgbevf: queue start stop functions
Hello,
I'm working on a procedure that will handle Etherne
Hi Ferruh:
> -Original Message-
> From: Yigit, Ferruh
> Sent: Tuesday, May 23, 2017 9:21 PM
> To: Zhang, Qi Z ; Lu, Wenzhuo
> ; Zhang, Helin
> Cc: dev@dpdk.org
> Subject: Re: [dpdk-dev] [PATCH 3/3] net/ixgbe: enable flex bytes for generic
> flow
> API
>
> On 5/23/2017 4:59 AM, Qi Zhang
On Fri, 19 May 2017, Charles (Chas) Williams wrote:
> From: Robert Shearman
>
> Implement xstats_get() to allow a number of driver-specific tx and rx
> stats to be retrieved.
>
> Signed-off-by: Robert Shearman
Acked-by: Shrikrishna Khare
On Fri, 19 May 2017, Charles (Chas) Williams wrote:
> From: Robert Shearman
>
> Make vmxnet3_process_events less noisy by removing logging when there
> are no events to process and by making link, device-change and debug
> events DEBUG level rather than ERR.
>
> Change these to use PMD_DRV_LO
On Mon, May 22, 2017 at 5:55 AM, Ferruh Yigit
wrote:
> On 5/18/2017 2:57 AM, Ajit Khaparde wrote:
> > This patchset amongst other changes adds support few more dev_ops,
> > updates HWRM to version 1.7.5, switches to polling stats from the
> > hardware, support for LRO etc..
> >
> > bnxt: add va
On 5/23/2017 2:30 PM, Adrien Mazarguil wrote:
> On Tue, May 23, 2017 at 01:58:44PM +0100, Ferruh Yigit wrote:
>> On 5/23/2017 1:26 PM, Adrien Mazarguil wrote:
>>> On Mon, May 22, 2017 at 02:53:28PM +0100, Ferruh Yigit wrote:
On 5/19/2017 5:30 PM, Iremonger, Bernard wrote:
> Hi Ferruh,
On Tue, May 23, 2017 at 01:58:44PM +0100, Ferruh Yigit wrote:
> On 5/23/2017 1:26 PM, Adrien Mazarguil wrote:
> > On Mon, May 22, 2017 at 02:53:28PM +0100, Ferruh Yigit wrote:
> >> On 5/19/2017 5:30 PM, Iremonger, Bernard wrote:
> >>> Hi Ferruh,
> >>>
> -Original Message-
> From:
On 5/23/2017 4:59 AM, Qi Zhang wrote:
> Add fdir flex byte support for rte_flow APIs.
>
> Signed-off-by: Qi Zhang
Hi Qi,
There are a few checkpatch errors for this patch also please find a few
minor syntax issues below.
<...>
> +int
> +ixgbe_fdir_set_flexbytes_offset(struct rte_eth_dev *dev,
>
> This patch implements the ops rx_queue_count for vhost PMD by adding
> a helper function rte_vhost_rx_queue_count in vhost lib.
>
> The ops ops rx_queue_count gets vhost RX queue avail count and helps
> to understand the queue fill level.
>
> Signed-off-by: Zhihong Wang
> ---
> drivers/net
On 5/23/2017 1:26 PM, Adrien Mazarguil wrote:
> On Mon, May 22, 2017 at 02:53:28PM +0100, Ferruh Yigit wrote:
>> On 5/19/2017 5:30 PM, Iremonger, Bernard wrote:
>>> Hi Ferruh,
>>>
-Original Message-
From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Ferruh Yigit
Sent: Thurs
This patch implements the ops rx_queue_count for vhost PMD by adding
a helper function rte_vhost_rx_queue_count in vhost lib.
The ops rx_queue_count gets vhost RX queue avail count and helps to
understand the queue fill level.
Signed-off-by: Zhihong Wang
---
Changes in v2:
1. Fixed a typo in c
> -Original Message-
> From: Jens Freimann [mailto:jfrei...@redhat.com]
> Sent: Tuesday, May 23, 2017 7:54 PM
> To: Wang, Zhihong
> Cc: dev@dpdk.org; yuanhan@linux.intel.com
> Subject: Re: [dpdk-dev] [PATCH] vhost: support rx_queue_count
>
> On Mon, May 22, 2017 at 04:01:08PM -0400,
On 5/23/2017 1:36 AM, Lu, Wenzhuo wrote:
> Hi,
>
>
>> -Original Message-
>> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Markus Theil
>> Sent: Monday, May 22, 2017 6:18 PM
>> To: dev@dpdk.org
>> Cc: Markus Theil
>> Subject: [dpdk-dev] [PATCH v3 1/2] net/igb: support flex filters o
On Mon, May 22, 2017 at 02:53:28PM +0100, Ferruh Yigit wrote:
> On 5/19/2017 5:30 PM, Iremonger, Bernard wrote:
> > Hi Ferruh,
> >
> >> -Original Message-
> >> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Ferruh Yigit
> >> Sent: Thursday, May 18, 2017 7:12 PM
> >> To: dev@dpdk.org
On 5/23/2017 1:09 PM, Nélio Laranjeiro wrote:
> On Thu, May 18, 2017 at 01:44:45PM +0300, Shahaf Shuler wrote:
>> Completion buffer size was computed wrongly, causing
>> completion polling to wraparound too early and miss entries.
>>
>> Fixing it by using Direct Verbs to query the CQ info.
>>
>> Fi
On Thu, May 18, 2017 at 01:44:45PM +0300, Shahaf Shuler wrote:
> Completion buffer size was computed wrongly, causing
> completion polling to wraparound too early and miss entries.
>
> Fixing it by using Direct Verbs to query the CQ info.
>
> Fixes: 6218063b39a6 ("net/mlx5: refactor Rx data path"
On Mon, May 22, 2017 at 04:01:08PM -0400, Zhihong Wang wrote:
> This patch implements the ops rx_queue_count for vhost PMD by adding
> a helper function rte_vhost_rx_queue_count in vhost lib.
>
> The ops ops rx_queue_count gets vhost RX queue avail count and helps
s/ops ops/ops/ ?
> to understan
Hello,
I'm working on a procedure that will handle Ethernet link failure over ixgbe VF.
Without queues reset functionality I tried to reset DPDK port with
rte_eth_dev_stop();rte_eth_dev_start() sequence.
My tests show that call to dev_stop can hang a process.
Can you suggest another procedure for
Add fdir flex byte support for rte_flow APIs.
Signed-off-by: Qi Zhang
---
drivers/net/ixgbe/ixgbe_ethdev.h | 3 +
drivers/net/ixgbe/ixgbe_fdir.c | 31 -
drivers/net/ixgbe/ixgbe_flow.c | 143 ++-
3 files changed, 173 insertions(+), 4 deletions(-)
When the last fdir flow be destroyed, the flag "mask_added"
should be reset, so the remain mask info will not take effect
when a new flow be added.
Fixes: a14de8b498d1 ("net/ixgbe: destroy consistent filter")
Cc: sta...@dpdk.org
Signed-off-by: Qi Zhang
---
drivers/net/ixgbe/ixgbe_flow.c | 4 +++
Remove reduandent code.
item->type != RTE_FLOW_ITEM_TYPE_END already cover
item->type == RTE_FLOW_ITEM_TYPE_VLAN.
Signed-off-by: Qi Zhang
---
drivers/net/ixgbe/ixgbe_flow.c | 8 +---
1 file changed, 1 insertion(+), 7 deletions(-)
diff --git a/drivers/net/ixgbe/ixgbe_flow.c b/drivers/net/ixg
This patch series is a couple of small patches to make the 'make config'
of the build a bit easier for users.
Users can now 'make defconfig' which will pick a sensible default based on
some 'uname' queries of the system.
Users can also set RTE_TARGET on in their environment which will get picked
Users can now set RTE_TARGET in their environment and use
'make config' without T=template.
If RTE_TARGET is set in the user's environment, and if T=
is not used, 'make config' will use $RTE_TARGET.
Signed-off-by: David Hunt
---
mk/rte.sdkroot.mk | 2 ++
1 file changed, 2 insertions(+)
diff --
Users can now use 'make defconfig' to generate a configuration using
the most appropriate defaults for the current machine.
arch taken from uname -m
machine defaults to native
execenv is taken from uname, Linux=linuxapp, otherwise bsdapp
toolchain is taken from $CC -v to see which compile
Hi Konstantin,
Thanks for your comments. My replies/questions are below.
BRs,
Jiayu
On Mon, May 22, 2017 at 05:19:19PM +0800, Ananyev, Konstantin wrote:
> Hi Jiayu,
> My comments/questions below.
> Konstantin
>
> >
> > For applications, DPDK GRO provides three external functions to
> > enable/
Currently it is not possible to use memory that is not owned by DPDK to
perform DMA. This scenarion might be used in vhost applications (like
SPDK) where guest send its own memory table. To fill this gap provide
API to allow registering arbitrary address in VFIO container.
Signed-off-by: Pawel Wod
Currently it is not possible to use memory that is not owned by DPDK to
perform DMA. This scenarion might be used in vhost applications (like
SPDK) where guest send its own memory table. To fill this gap provide
API to allow registering arbitrary address in VFIO container.
Change-Id: Ic1f56e850cfd
Hi Wei,
On Tue, May 23, 2017 at 06:07:20AM +, Zhao1, Wei wrote:
> Hi, Adrien
>
> > +struct rte_flow_item_raw {
> > + uint32_t relative:1; /**< Look for pattern after the previous item. */
> > + uint32_t search:1; /**< Search pattern from offset (see also limit). */
> > + uint32_t reser
On 5/17/2017 7:03 PM, Charles (Chas) Williams wrote:
> Fixes: 1b93c2aa81b4 ("net/af_packet: add interface name to internals")
>
> Signed-off-by: Chas Williams
Series applied to dpdk-next-net/master, thanks.
Except patch 2/3, it is removed from patchset.
Debug logs are helpful for better debugging. Alloc
was having the logs, but logs were not present in free routines.
This patch add support for debug mode logs in free routine.
Also, changing the log category to DRV instead of TX.
Signed-off-by: Hemant Agrawal
---
drivers/mempool/dpaa2/dpaa2_hw_
In case the alloc api is not able to allocate the required
number of buffer, it can return '0', which will not indicate
the failure to the calling function.
This patch fix the return value to indicate the failure.
Fixes: 5dc43d22b5ad ("mempool/dpaa2: add hardware offloaded mempool")
CC: sta...@dpd
On Tue, May 23, 2017 at 09:05:38AM +, Hemant Agrawal wrote:
> Which is the next DPDK LTS release?
There is no answer yet. It could be v18.11. There was also a request for
proposing v17.11 to be the next LTS.
> Is 17.05 a DPDK LTS release?
Nope, it's not in the plan.
> Do we need to send a
Which is the next DPDK LTS release? Is 17.05 a DPDK LTS release?
Do we need to send a copy to sta...@dpdk.org for any fixes on 17.05?
Regards,
Hemant
Hi, Roger
Sorry for typo error. You should set --log-level=8
Regards
-Wei
> -Original Message-
> From: Dai, Wei
> Sent: Tuesday, May 23, 2017 3:24 PM
> To: 'Roger B. Melton' ; Laurent Hardy
> ; dev@dpdk.org
> Cc: Yigit, Ferruh ; Zhang, Helin
> ; Ananyev, Konstantin
> ; olivier.m...@6wind.
Hi, Roger
Sorry for late response as we are busy with other higher priority task.
ixgbe_setup_mac_link_multispeed_fiber( ) in ixgbe_common.c calls
ixgbe_setup_mac_link( ) which some functions defined in ixgbe/base .
Would you please give us more info to narrow down this issue ?
What device id did
This patch adds a function to flush all the fliter list
and filter rule on a port.
Signed-off-by: Wei Zhao
---
drivers/net/e1000/e1000_ethdev.h | 9 +++
drivers/net/e1000/igb_ethdev.c | 67 +--
drivers/net/e1000/igb_flow.c | 141 ++-
3
This patch adds a function to destroy the flow fliter.
Signed-off-by: Wei Zhao
---
drivers/net/e1000/igb_flow.c | 100 ++-
1 file changed, 99 insertions(+), 1 deletion(-)
diff --git a/drivers/net/e1000/igb_flow.c b/drivers/net/e1000/igb_flow.c
index 05665
This patch adds a function to create the flow directory filter.
Signed-off-by: Wei Zhao
---
drivers/net/e1000/e1000_ethdev.h | 58 +
drivers/net/e1000/igb_ethdev.c | 22 +++
drivers/net/e1000/igb_flow.c | 137 ++-
3 files changed, 2
check if the rule is a TCP SYN rule, and get the SYN info.
Signed-off-by: Wei Zhao
---
drivers/net/e1000/igb_flow.c | 277 +++
1 file changed, 277 insertions(+)
diff --git a/drivers/net/e1000/igb_flow.c b/drivers/net/e1000/igb_flow.c
index c078115..61095a
check if the rule is a flex byte rule, and get the flex info.
Signed-off-by: Wei Zhao
---
drivers/net/e1000/igb_flow.c | 276 +++
1 file changed, 276 insertions(+)
diff --git a/drivers/net/e1000/igb_flow.c b/drivers/net/e1000/igb_flow.c
index 61095ab..a58
check if the rule is a ethertype rule, and get the ethertype info.
Signed-off-by: Wei Zhao
---
drivers/net/e1000/igb_flow.c | 280 +++
1 file changed, 280 insertions(+)
diff --git a/drivers/net/e1000/igb_flow.c b/drivers/net/e1000/igb_flow.c
index dd16e9b
Add support for restoring flex type filter in SW.
Signed-off-by: Wei Zhao
---
drivers/net/e1000/igb_ethdev.c | 183 +++--
1 file changed, 122 insertions(+), 61 deletions(-)
diff --git a/drivers/net/e1000/igb_ethdev.c b/drivers/net/e1000/igb_ethdev.c
index 94e
Add support for restoring ether type filter in SW.
Signed-off-by: Wei Zhao
---
drivers/net/e1000/e1000_ethdev.h | 10 +++--
drivers/net/e1000/igb_ethdev.c | 47 ++--
2 files changed, 44 insertions(+), 13 deletions(-)
diff --git a/drivers/net/e1000/e1000
Add rule validate function and check if the rule is a
n-tuple rule, and get the n-tuple info.
Signed-off-by: Wei Zhao
---
drivers/net/e1000/Makefile | 1 +
drivers/net/e1000/e1000_ethdev.h | 8 +
drivers/net/e1000/igb_ethdev.c | 14 +-
drivers/net/e1000/igb_flow.c | 509
Add support for restoring n-tuple
filter in SW.
Signed-off-by: Wei Zhao
---
drivers/net/e1000/igb_ethdev.c | 261 +
1 file changed, 158 insertions(+), 103 deletions(-)
diff --git a/drivers/net/e1000/igb_ethdev.c b/drivers/net/e1000/igb_ethdev.c
index ade7
The patches mainly finish following functions:
1) Store and restore all kinds of filters.
2) Parse all kinds of filters.
3) Add flow validate function.
4) Add flow create function.
5) Add flow destroy function.
6) Add flow flush function.
zhao wei (11):
net/e1000: store and restore TCP SYN filte
Add support for storing and restoring TCP SYN
filter in SW.
Signed-off-by: Wei Zhao
---
drivers/net/e1000/e1000_ethdev.h | 2 ++
drivers/net/e1000/igb_ethdev.c | 45 +---
2 files changed, 44 insertions(+), 3 deletions(-)
diff --git a/drivers/net/e1000/e100
56 matches
Mail list logo
