-Original Message-
> Date: Fri, 14 Apr 2017 17:04:58 +0100
> From: Harry van Haaren
> To: dev@dpdk.org
> CC: jerin.ja...@caviumnetworks.com, Harry van Haaren
>
> Subject: [PATCH] eventdev: fix dequeue timeout bitmask brackets
> X-Mailer: git-send-email 2.7.4
>
> Fix brackets around the
Hi,
We are using dpdk 16.04 and by looking at the ixgbe and
i40e(i40e_xmit_pkts_vec) and ixgbe(ixgbe_xmit_pkts_vec) driver vector tx
processing code I see they both don't handle scattered packet processing.
For any packets greater than 2048 bytes which will basically contain
multiple rte_mbuf segs
On 4/14/2017 5:53 PM, Shreyansh Jain wrote:
> Relocate release note text within new features section.
> Also, Rephrease text inline with other similar PMD addition notes.
>
> Signed-off-by: Shreyansh Jain
Squashed into relevant commit [1] in next-net, thanks.
[1]
Fixes: 5988225975ce ("doc: add
On 4/14/2017 5:03 PM, Mcnamara, John wrote:
>
>
>> -Original Message-
>> From: Yang, Qiming
>> Sent: Thursday, April 13, 2017 4:09 AM
>> To: dev@dpdk.org
>> Cc: Wu, Jingjing ; Mcnamara, John
>> ; Yang, Qiming
>> Subject: [PATCH v2] doc: add known igb_uio issue for i40e
>>
>> When insmod
On Fri, Apr 14, 2017 at 08:51:39AM +0200, Nélio Laranjeiro wrote:
> Hi Yongseok,
>
> On Thu, Apr 13, 2017 at 10:46:51AM -0700, Yongseok Koh wrote:
> > Current implementation is error-prone if the max inline size
> > (txq->max_inilne) is decoupled from txq->inline_en and becomes zero. If it
> > bec
Hello Ferruh,
> -Original Message-
> From: Ferruh Yigit [mailto:ferruh.yi...@intel.com]
> Sent: Friday, April 14, 2017 5:39 PM
> To: Hemant Agrawal ; dev@dpdk.org
> Cc: thomas.monja...@6wind.com; bruce.richard...@intel.com; Shreyansh Jain
> ; john.mcnam...@intel.com;
> jerin.ja...@caviumne
Relocate release note text within new features section.
Also, Rephrease text inline with other similar PMD addition notes.
Signed-off-by: Shreyansh Jain
---
Note:
For application on net-next
doc/guides/rel_notes/release_17_05.rst | 24
1 file changed, 12 insertions(+),
On 4/14/2017 5:07 PM, Mcnamara, John wrote:
>
>
>> -Original Message-
>> From: Wu, Jingjing
>> Sent: Tuesday, April 11, 2017 6:57 AM
>> To: Mcnamara, John
>> Cc: Wu, Jingjing ; dev@dpdk.org; sta...@dpdk.org
>> Subject: [PATCH v2] doc: fix description on intel VFs
>>
>> This patch correct
> -Original Message-
> From: akhil.go...@nxp.com [mailto:akhil.go...@nxp.com]
> Sent: Monday, April 10, 2017 1:31 PM
> To: dev@dpdk.org
> Cc: Doherty, Declan ; De Lara Guarch, Pablo
> ; hemant.agra...@nxp.com; Mcnamara, John
> ; nhor...@tuxdriver.com;
> thomas.monja...@6wind.com; Akhil Go
> -Original Message-
> From: Wu, Jingjing
> Sent: Tuesday, April 11, 2017 6:57 AM
> To: Mcnamara, John
> Cc: Wu, Jingjing ; dev@dpdk.org; sta...@dpdk.org
> Subject: [PATCH v2] doc: fix description on intel VFs
>
> This patch corrects the description on Physical and Virtual Function
> In
Fix brackets around the & operator to first mask a single bit
and then perform the not operator. Previously the result was
not as expected, due to the ! operator being performed first.
As noted on list[1] Clang 4.0 warns about a possible bug for
this type of line:
if (!variable & FLAG) {
> -Original Message-
> From: Yang, Qiming
> Sent: Thursday, April 13, 2017 4:09 AM
> To: dev@dpdk.org
> Cc: Wu, Jingjing ; Mcnamara, John
> ; Yang, Qiming
> Subject: [PATCH v2] doc: add known igb_uio issue for i40e
>
> When insmod "igb_uio" with "intr_mode=legacy and test link status
>
> -Original Message-
> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Wei Dai
> Sent: Thursday, April 13, 2017 9:21 AM
> To: thomas.monja...@6wind.com; harish.pa...@cavium.com;
> rasesh.m...@cavium.com; stephen.h...@broadcom.com;
> ajit.khapa...@broadcom.com; Lu, Wenzhuo ; Zhang,
>
> -Original Message-
> From: Shreyansh Jain [mailto:shreyansh.j...@nxp.com]
> Sent: Thursday, April 13, 2017 10:34 AM
> To: Yigit, Ferruh
> Cc: dev@dpdk.org; Mcnamara, John ;
> hemant.agra...@nxp.com; Shreyansh Jain
> Subject: [PATCH] doc: cleanup testpmd section in DPAA2 PMD guide
>
>
Hi all,
just a heads-up that there are compilation errors showing up with
compiling DPDK with clang 4.0 release. Here are some of the errors I am
seeing. Volunteers to do patches for some of them welcome.
Regards,
/Bruce
/home/bruce/dpdk.org/lib/librte_eal/common/eal_common_tailqs.c:92:24: warni
On 4/14/2017 11:49 AM, Ferruh Yigit wrote:
> On 4/14/2017 2:16 AM, Wenzhuo Lu wrote:
>> When receiving the unsupported AQ messages, it's taken as
>> an error. It's not appropriate and triggers too much
>> unnecessary print.
>>
>> Signed-off-by: Wenzhuo Lu
>
> Applied to dpdk-next-net/master, than
On 4/4/2017 5:40 PM, Olivier Matz wrote:
> Example of use:
> ./app/test-pmd --log-level='pmd\.i40e.*,8'
>
> This enables debug logs for all dynamic logs whose type starts with
> 'pmd.i40e'.
>
> Signed-off-by: Olivier Matz
<...>
> +
> + printf("set log level %s,%lu\n",
> +
Hi Olivier,
On 4/4/2017 5:40 PM, Olivier Matz wrote:
> Example of use:
> ./app/test-pmd --log-level='pmd\.i40e.*,8'
>
> This enables debug logs for all dynamic logs whose type starts with
> 'pmd.i40e'.
>
> Signed-off-by: Olivier Matz
<...>
> index f0ded185b..d98d56d2f 100644
> --- a/lib
> From: Richardson, Bruce
> Sent: Friday, April 14, 2017 4:18 PM
> To: Van Haaren, Harry
> Cc: dev@dpdk.org; Richardson, Bruce
> Subject: [PATCH] event/sw: fix events mis-identified as needing reorder
>
> When taking events from a port, we checked the history list to check if the
> event needed
When taking events from a port, we checked the history list to check if the
event needed to be put back in order i.e. originally came from a reordered
queue type. The check for reordering involved checking if the reorder
buffer entry pointer was null. However, after that pointer was used it was
nev
On Fri, Apr 14, 2017 at 01:27:13PM +, O'Driscoll, Tim wrote:
> Below are the features that we're planning to submit for the 17.08 release.
> We'll submit a patch to update the roadmap page with this info.
>
> It would be good if others are also willing to share their plans so that we
> can b
Below are the features that we're planning to submit for the 17.08 release.
We'll submit a patch to update the roadmap page with this info.
It would be good if others are also willing to share their plans so that we can
build up a complete picture of what's planned for 17.08 and make sure there'
On 4/5/2017 10:37 AM, Thomas Monjalon wrote:
> 2017-04-04 18:27, Olivier Matz:
>> Based on discussions done in [1] and in this thread, this patchset
>> reorganizes
>> the mbuf.
>>
>> The main changes are:
>> - reorder structure to increase vector performance on some non-ia
>> platforms.
>> - add
2017-04-12 09:25, Stephen Hemminger:
> On Tue, 11 Apr 2017 17:44:07 +0200
> Gaetan Rivet wrote:
>
> > I rebased the following work of Jan:
> >
> > This series is removing the PCI specific struct eth_driver from rte_ether.
> > The
> > PCI drivers are changed to use the newly introduced header-on
-Original Message-
> Date: Wed, 22 Mar 2017 14:00:04 +0530
> From: Jerin Jacob
> To: dev@dpdk.org
> Cc: thomas.monja...@6wind.com, Jerin Jacob
> Subject: [dpdk-dev] [PATCH v5] devtools: add tags and cscope index file
> generation support
> X-Mailer: git-send-email 2.5.5
>
> This script
-Original Message-
> Date: Thu, 13 Apr 2017 12:04:51 +0100
> From: Ferruh Yigit
> To: Jerin Jacob , Andriy Berestovskyy
>
> CC: Maciej Czekaj , dev@dpdk.org
> Subject: Re: [dpdk-dev] [PATCH 1/2] net/thunderx: add empty link up/down
> callbacks
> User-Agent: Mozilla/5.0 (Windows NT 10.0;
2017-04-11 17:44, Gaetan Rivet:
> I have rebased the work done by Jan to introduce the virtual device
> subsystem using the new rte_bus API.
> I also fixed a few outstanding compilation issues, related to PMDs introduced
> during this release.
> Additionally, a few virtual devices had not been port
2017-04-12 09:09, Stephen Hemminger:
> On Tue, 11 Apr 2017 13:07:27 +0200
> Gaetan Rivet wrote:
>
> > I have rebased the work done by Shreyansh and Thomas to follow
> > the bus abstraction introduced in v17.02 for the PCI bus
> > implementation.
> > This series is only a partial version of the pr
2017-03-02 11:00, Ami Sabo:
> The patchset fixes secondary process crash issue when it tries
> to access virtio-user pmd (e.g. via rte_eth_rx_burst).
>
> The crash happens because in virtio_user probing,
> eth_dev_attach_secondary is not being called, as it does from
> rte_eth_dev_pci_probe. There
On 4/10/2017 8:55 AM, Mcnamara, John wrote:
>
>
>> -Original Message-
>> From: Iremonger, Bernard
>> Sent: Friday, April 7, 2017 4:15 PM
>> To: dev@dpdk.org
>> Cc: Xing, Beilei ; Lu, Wenzhuo
>> ; Mcnamara, John ;
>> Iremonger, Bernard
>> Subject: [PATCH 1/2] doc: release note for QinQ cl
On 4/11/2017 2:49 PM, Hemant Agrawal wrote:
> This patch adds the NXP dpaa2 architecture and pmd details
> in the Network interfaces section.
>
> Signed-off-by: Hemant Agrawal
> Acked-by: John McNamara
<...>
> diff --git a/doc/guides/rel_notes/release_17_05.rst
> b/doc/guides/rel_notes/releas
On 4/14/2017 2:16 AM, Wenzhuo Lu wrote:
> When receiving the unsupported AQ messages, it's taken as
> an error. It's not appropriate and triggers too much
> unnecessary print.
>
> Signed-off-by: Wenzhuo Lu
Applied to dpdk-next-net/master, thanks.
Change level of log message from ERR to DEBUG and reword it,
in the i40e_dev_consistent_tunnel_filter_set() function.
Signed-off-by: Bernard Iremonger
---
drivers/net/i40e/i40e_ethdev.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/net/i40e/i40e_ethdev.c b/drive
On 4/13/2017 11:15 PM, Charles Myers wrote:
> From: Charles
>
> Fixes issue where mlx4 driver stops receiving packets when mbuf
> allocation fails in mlx4_rx_burst().
>
> This issue appears to be caused because the code doesn't recycle the
> existing mbuf to the sges array when mbuf allocation f
On 4/12/2017 8:30 AM, Pascal Mazon wrote:
> Support for a fixed MAC address for testing with the last octet
> incrementing by one for each interface defined with the new 'mac=fixed'
> string on the --vdev option. The default option is still to randomize
> the MAC address for each tap interface.
>
On 4/14/2017 10:32 AM, Pascal Mazon wrote:
> The tap does not behave properly in some cases.
>
> It is generally expected that a real device should be available once the
> probing has been done.
>
> It is also better to check if an operation (here, setting MAC) is
> mandatory before performing it
With the mbuf rework, we now have 8 contiguous bytes to be
rearmed in the mbuf at 8B naturally aligned address.
Use single 8B write to avoid multiple 2B writes in Rx path.
Signed-off-by: Jerin Jacob
Signed-off-by: Maciej Czekaj
---
drivers/net/thunderx/nicvf_ethdev.c | 18 ++
dr
On 4/14/2017 9:31 AM, Declan Doherty wrote:
> On 10/04/17 03:22, Eric Kinzie wrote:
>> On Fri Apr 07 18:07:12 +0300 2017, Ilya Maximets wrote:
>>> Currently, 'rte_eth_dev_configure' fails on attempt to setup
>>> max_rx_pkt_len > 2048 if no slaves was added to bonded device.
>>>
>>> For example:
>>>
On 4/14/2017 10:06 AM, Declan Doherty wrote:
> On 06/04/17 12:59, Ilya Maximets wrote:
>> Some applications like OVS knows nothing about the
>> device type and wants to use same API to work with
>> all of them. But bond_pmd, unlike other pmds, requires
>> additional step (removing of all the slaves
Check for the current MAC address on both the remote and the tap
netdevices before setting a new value.
While there, remove wrong empty lines and ensure tap_ioctl() return
value is negative, just like what is done throughout this code.
Fixes: 2bc06869cd94 ("net/tap: add remote netdevice traffic c
Print a detailed debug message inside tap_ioctl() directly. The caller
now only needs to check for return value.
Signed-off-by: Pascal Mazon
---
drivers/net/tap/rte_eth_tap.c | 37 -
1 file changed, 24 insertions(+), 13 deletions(-)
diff --git a/drivers/net/t
This is cosmetic; the code is functionally equivalent.
Signed-off-by: Pascal Mazon
---
drivers/net/tap/rte_eth_tap.c | 32 ++--
1 file changed, 14 insertions(+), 18 deletions(-)
diff --git a/drivers/net/tap/rte_eth_tap.c b/drivers/net/tap/rte_eth_tap.c
index c9d107c2
This has three main benefits:
- tun_alloc is now generic again for any queue,
- mtu no longer needs to be handled in tap_setup_queue(),
- an actual netdevice is created as soon as the device is probed.
On top of it, code in eth_dev_tap_create() has been reworked to have a
more logical behavior;
These functions are only two lines each and are used only once.
Signed-off-by: Pascal Mazon
---
drivers/net/tap/rte_eth_tap.c | 26 --
1 file changed, 4 insertions(+), 22 deletions(-)
diff --git a/drivers/net/tap/rte_eth_tap.c b/drivers/net/tap/rte_eth_tap.c
index 0c89b6
The tap does not behave properly in some cases.
It is generally expected that a real device should be available once the
probing has been done.
It is also better to check if an operation (here, setting MAC) is
mandatory before performing it. Typically in cases where the remote
netdevice is a VF w
On 4/14/2017 4:34 AM, Wei Zhao wrote:
> DPDK community has several emails discussion on this topic,
> these mails link is bellow:
> http://dpdk.org/ml/archives/dev/2017-March/060379.html,
> http://dpdk.org/ml/archives/dev/2017-March/060295.html,
> items like VLAN can already have several valid "typ
On 4/14/2017 4:52 AM, Zhao1, Wei wrote:
>
>
>> -Original Message-
>> From: Yigit, Ferruh
>> Sent: Tuesday, April 11, 2017 11:21 PM
>> To: Zhang, Helin ; Ananyev, Konstantin
>>
>> Cc: dev@dpdk.org; Yigit, Ferruh ; Lu, Wenzhuo
>> ; Zhao1, Wei
>> Subject: [PATCH] net/ixgbe: fix duplicated
On 06/04/17 12:59, Ilya Maximets wrote:
Some applications like OVS knows nothing about the
device type and wants to use same API to work with
all of them. But bond_pmd, unlike other pmds, requires
additional step (removing of all the slaves) before
closing the device.
In fact that bond_pmd autom
Ok.
> -Original Message-
> From: Yigit, Ferruh
> Sent: Friday, April 14, 2017 5:04 PM
> To: Zhao1, Wei ; Zhang, Helin
> ; Ananyev, Konstantin
>
> Cc: dev@dpdk.org; Lu, Wenzhuo
> Subject: Re: [PATCH] net/ixgbe: fix duplicated check
>
> On 4/14/2017 4:52 AM, Zhao1, Wei wrote:
> >
> >
> >>
On 4/14/2017 4:52 AM, Zhao1, Wei wrote:
>
>
>> -Original Message-
>> From: Yigit, Ferruh
>> Sent: Tuesday, April 11, 2017 11:21 PM
>> To: Zhang, Helin ; Ananyev, Konstantin
>>
>> Cc: dev@dpdk.org; Yigit, Ferruh ; Lu, Wenzhuo
>> ; Zhao1, Wei
>> Subject: [PATCH] net/ixgbe: fix duplicated
Occasionally, the distributor single-packet-at-a-time mode will
segfault because it inadvertently calls some burst mode code when
flushing packets.
This patch ensures that only the v20 (single mode) codepath is used, and
returns without falling through to the burst mode code.
Fixes: 775003ad2f96
On 4/13/2017 12:03 PM, Lu, Wenzhuo wrote:
> Hi Ferruh,
>
> -Original Message-
> From: Yigit, Ferruh
> Sent: Thursday, April 13, 2017 5:14 PM
> To: Richardson, Bruce ; Lu, Wenzhuo
>
> Cc: Zhang, Helin ; Olivier Matz
> ; dev@dpdk.org; Wu, Jingjing
> Subject: Re: [dpdk-dev] [PATCH] net/i
Hi all,
Thanks for the comments. The proposal seems refrained from wide usage in
application.
thx &
rgds,
-qinglai
On Fri, Apr 14, 2017 at 3:03 AM, Stephen Hemminger <
step...@networkplumber.org> wrote:
> On Thu, 13 Apr 2017 23:19:45 +
> "Ananyev, Konstantin" wrote:
>
> > > -Original M
2017-04-11 13:07, Gaetan Rivet:
> + if (ret > 0) {
> + /* In case the device was not found on any bus, search VDEV */
> + ret = rte_eal_vdev_init(name, devargs);
I think we should avoid to directly call a vdev function.
Anyway, Jan is preparing a new series for a
On Thu, Apr 13, 2017 at 09:36:27AM +0100, David Hunt wrote:
> A segfault when flushing packets has been revealed by further testing
> when using distributor in single packet mode. This patch resolves that.
>
> Fixes: 775003ad2f96 ("distributor: add new burst-capable library")
>
> Reported-by: Yon
Hi Fan,
> -Original Message-
> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Fan Zhang
> Sent: Wednesday, April 12, 2017 3:11 PM
> To: dev@dpdk.org
> Cc: De Lara Guarch, Pablo; sta...@dpdk.org; Mcnamara, John
> Subject: [dpdk-dev] [PATCH v2] crypto/scheduler: fix Doxygen comments
>
On 10/04/17 03:22, Eric Kinzie wrote:
On Fri Apr 07 18:07:12 +0300 2017, Ilya Maximets wrote:
Currently, 'rte_eth_dev_configure' fails on attempt to setup
max_rx_pkt_len > 2048 if no slaves was added to bonded device.
For example:
rte_eth_dev_attach("eth_bond0,slave=05:00.0,mode=l34",
This commit fixes zero physical address when IV not set
Fixes: 1703e94ac5ce ("qat: add driver for QuickAssist devices")
Signed-off-by: Arek Kusztal
---
drivers/crypto/qat/qat_crypto.c | 29 ++---
1 file changed, 18 insertions(+), 11 deletions(-)
diff --git a/drivers/cry
Hi, Thomas
> -Original Message-
> From: Thomas Monjalon [mailto:thomas.monja...@6wind.com]
> Sent: Friday, April 14, 2017 2:31 PM
> To: Zhao1, Wei
> Cc: Ananyev, Konstantin ; Mcnamara, John
> ; dev@dpdk.org; Lu, Wenzhuo
>
> Subject: Re: [dpdk-dev] [PATCH v4 1/3] lib/librte_ether: add sup
Like what we did for virtio PMD driver [0][1], we could also apply such
trick to vhost, to avoid the memory write on net header when necessary.
[0]: c9ea670c1dc7 ("net/virtio: fix performance regression due to TSO")
[1]: 16994abee215 ("net/virtio: optimize header reset on any layout")
With this,
> -Original Message-
> From: Yuanhan Liu [mailto:yuanhan@linux.intel.com]
> Sent: Friday, April 14, 2017 3:01 PM
> To: Tan, Jianfeng
> Cc: dev@dpdk.org; olivier.m...@6wind.com; sta...@dpdk.org
> Subject: Re: [PATCH] net/virtio-user: fix not working on 32-bit system
>
> On Fri, Apr 14
On Fri, Apr 14, 2017 at 06:56:01AM +, Tan, Jianfeng wrote:
>
>
> > -Original Message-
> > From: Yuanhan Liu [mailto:yuanhan@linux.intel.com]
> > Sent: Friday, April 14, 2017 2:20 PM
> > To: Tan, Jianfeng
> > Cc: dev@dpdk.org; olivier.m...@6wind.com; sta...@dpdk.org
> > Subject: Re
62 matches
Mail list logo
