On Mon, Oct 23, 2017 at 11:39:42PM +0530, Jerin Jacob wrote:
> -Original Message-
> > Date: Wed, 18 Oct 2017 14:15:40 +0530
> > From: Pavan Nikhilesh
> > To: jerin.ja...@caviumnetworks.com, santosh.shu...@caviumnetworks.com,
> > nikhil@intel.com
> > Cc: dev@dpdk.org, Pavan Nikhilesh
On Tue, Oct 24, 2017 at 09:16:09AM +0300, Shahaf Shuler wrote:
> Considering the PMD supports only Ethernet transport, packet which
> arrives without any packet type flags in the completion should be
> marked with L2_ETHER flag.
>
> Fixes: ea16068c0064 ("net/mlx5: fix L4 packet type support")
> Cc
On Mon, Oct 23, 2017 at 10:24:09AM -0700, Yongseok Koh wrote:
> On Mon, Oct 23, 2017 at 09:50:14AM +0200, Nélio Laranjeiro wrote:
> > Yongseok, Sagi, my small contribution to this discussion,
> >
> > On Sun, Oct 22, 2017 at 03:01:04PM -0700, Yongseok Koh wrote:
> > > On Sun, Oct 22, 2017 at 12:46:
Hi Adrien,
I am trying to compile mlx4 (and later to try mlx5) pmd in RHEL 7.4
(ppc64le) without Mellanox OFED,
using current master (which has below patch series).
As I do so, I hit with below compile error:
dpdk/drivers/net/mlx4/mlx4.c:53:31: fatal error: infiniband/mlx4dv.h:
No such file
On 19/10/2017 17:14, Luca Boccassi wrote:
[..]
We've adapted and used these patches with the early rte_eth_dev_reset
for a year in production now, and we had a customer who requested it
since they were running into the problem it solves (PF flaps).
I have adapted them on the latest 17.11 tree a
Considering the PMD supports only Ethernet transport, packet which
arrives without any packet type flags in the completion should be
marked with L2_ETHER flag.
Fixes: ea16068c0064 ("net/mlx5: fix L4 packet type support")
Cc: sta...@dpdk.org
Cc: ys...@mellanox.com
Signed-off-by: Shahaf Shuler
Ack
Coverity issue: 143439
Fixes: ef53b6030039 ("net/virtio-user: support LSC")
Cc: jianfeng@intel.com
cc: sta...@dpdk.org
Signed-off-by: SebastianX Basierski
---
drivers/net/virtio/virtio_user_ethdev.c | 6 +-
1 file changed, 5 insertions(+), 1 deletion(-)
diff --git a/drivers/net/virtio/
On Tuesday 24 October 2017 02:02 AM, Thomas Monjalon wrote:
> 20/10/2017 14:31, Santosh Shukla:
>> Renamed data type from phys_addr_t to iova_addr_t.
>>
>> Signed-off-by: Santosh Shukla
>> Reviewed-by: Anatoly Burakov
> Suggested title:
> mem: rename physical to IOVA address type
>
+1. Tha
On Tuesday 24 October 2017 02:04 AM, Thomas Monjalon wrote:
> 20/10/2017 14:31, Santosh Shukla:
>> Rename buf_physaddr to buf_iovaaddr
>>
>> Signed-off-by: Santosh Shukla
>> Reviewed-by: Anatoly Burakov
> Suggested title:
> mbuf: rename physical address to IOVA address
>
+1. Thanks for Sug
Hi Thomas,
On Monday 23 October 2017 08:28 PM, Thomas Monjalon wrote:
> 20/10/2017 14:31, Santosh Shukla:
>> v3:
>> Include v2 review comment and rebased on
>> top of upstream tip commit:6b9ed026a8704
>>
>>
>> v2:
>> Include build fixes reported in patchworks.
> Please fix checkpatch issues, than
For fm10k multi host based design, DPDK app running in VM or host needs to
get aware of the switch's state because switch may undergo a quit-restart.
This patch series supports switch restart feature for DPDK app to be able
to resume its packet processing without an app-level restart.
Changes in v
This patch documents how DPDK app should handle the event of switch
quit-restart to resume its network without an app-level restart.
Signed-off-by: Xiao Wang
---
v2:
- Improve the wording.
---
doc/guides/nics/fm10k.rst | 11 +++
1 file changed, 11 insertions(+)
diff --git a/doc/guides/n
For events indicating a change in the state of the switch manager, the
driver will restore the basic port configurations and then pass this event
to application so that the application can restore any additional
configurations if required. In this way, once the switch manager restarts,
the DPDK app
For events indicating the change in the state of the switch manager. The
driver will restore the basic port configurations and then pass this event
to application so that the application can restore any additional
configurations if required. In this way, once the switch manager restarts,
the DPDK a
As fm10k host interface is not directly connected to PHY, marking the link
status as UP doesn't mean a lot to the application. So, this patch
basically redefines the link status as the state of switch manager: when
switch manager is running, it's LINK_UP; when switch manager goes down by
calling th
Hi Thomas,
On Tuesday 24 October 2017 01:59 AM, Thomas Monjalon wrote:
> 20/10/2017 14:31, Santosh Shukla:
>> Removed dpdk iova aware ABI deprecation notice,
>> and updated ABI change details in release_17.11.rst.
>>
>> Signed-off-by: Santosh Shukla
>> Acked-by: John McNamara
>> ---
>> --- a/do
Signed-off-by: Srisivasubramanian S
Signed-off-by: Shijith Thotton
---
doc/guides/nics/liquidio.rst| 2 ++
drivers/net/liquidio/base/lio_hw_defs.h | 12
drivers/net/liquidio/lio_ethdev.c | 7 ++-
3 files changed, 16 insertions(+), 5 deletions(-)
diff --git a
When offload is enabled, vhost needs to access the first mbuf
to get the packet info, e.g. TCP header. So we couldn't delay
the data copy in this case.
Fixes: e5c494a7a22b ("vhost: batch small guest memory copies")
Reported-by: Lei Yao
Signed-off-by: Tiwei Bie
---
lib/librte_vhost/virtio_net.c
In the function virtqueue_enqueue_xmit(), when can_push is true,
vtnet_hdr_size is added to pkt_len by calling rte_pktmbuf_prepend.
which is wrong for pkt stats, virtio header length should be subtracted
before calling stats function.
Fixes: 58169a9c8153 ("net/virtio: support Tx checksum offload")
Hi Herbert,
The 10/23/2017 10:35, Herbert Guan wrote:
> The printed time values presented in TSC is not straight forward
> showing the performance difference. And if the high resolution
> counter is not enabled, time value is too small to show the actual
> performance (e.g. "1 - 1" seems the same
> -Original Message-
> From: Dai, Wei
> Sent: Monday, October 23, 2017 2:44 PM
> To: Lu, Wenzhuo ; Ananyev, Konstantin
> ; Wu, Jingjing
> Cc: dev@dpdk.org; Dai, Wei ; sta...@dpdk.org
> Subject: [PATCH] net/ixgbe: fix PF DCB info
>
> When SRIOV is active, the function ixgbe_dev_get_dcb_i
> -Original Message-
> From: Dai, Wei
> Sent: Monday, October 23, 2017 3:25 PM
> To: Wu, Jingjing
> Cc: dev@dpdk.org; Dai, Wei ; sta...@dpdk.org
> Subject: [PATCH] app/testpmd: fix mapping of user priority to DCB TC
>
> When number of DCB traffic class is 4, user priority should be mapp
> -Original Message-
> From: Shijith Thotton [mailto:shijith.thot...@caviumnetworks.com]
> Sent: Monday, October 23, 2017 8:28 PM
> To: Yigit, Ferruh
> Cc: Wu, Jingjing ; Gregory Etelson ;
> Harish Patil ; Thomas Monjalon
> ; dev@dpdk.org; sta...@dpdk.org; Tan, Jianfeng
> ; George Prekas
Hi All,
I met an error when compile dpdk 17.08 with cmdline:
make config T=x86_64-native-linuxapp-gcc && make EXTRA_CFLAGS="-fPIC" && make
install
an error: bad value (native) for -march= switch
do you know why? my gcc version is 4.8.5
On 10/23/2017 5:16 AM, Olivier Matz wrote:
> PKT_RX_VLAN_PKT and PKT_RX_QINQ_PKT are deprecated for a while.
> As explained in [1], these flags were kept to let the applications and
> PMDs move to the new flag. There is also a need to support Rx vlan
> offload without vlan strip (at least for the i
Yuanhan,
> -Original Message-
> From: Yuanhan Liu [mailto:y...@fridaylinux.org]
> Sent: Monday, October 23, 2017 9:22 PM
> To: Yang, Zhiyong
> Cc: dev@dpdk.org; sta...@dpdk.org; maxime.coque...@redhat.com
> Subject: Re: [PATCH v2] net/virtio: fix wrong TX pkt length stats
>
> On Mon, Oct
Hi Jerin
On 10/23/2017 6:06 PM, Jerin Jacob Wrote:
-Original Message-
Date: Mon, 23 Oct 2017 16:49:01 +0800
From: Jia He
To: Jerin Jacob
Cc: "Ananyev, Konstantin" , "Zhao, Bing"
, Olivier MATZ ,
"dev@dpdk.org" , "jia...@hxt-semitech.com"
, "jie2@hxt-semitech.com"
, "bing.
> -Original Message-
> From: Li, Xiaoyun
> Sent: Wednesday, October 18, 2017 3:12 PM
> To: Wu, Jingjing
> Cc: dev@dpdk.org; Li, Xiaoyun
> Subject: [PATCH v3] examples/l3fwd: pass flow arguments when start app
>
> To make the performance can be tuning on different NICs or platforms. We
> -Original Message-
> From: Mcnamara, John
> Sent: Monday, October 23, 2017 9:07 PM
> To: Wang, Xiao W ; dev@dpdk.org
> Cc: Wu, Jingjing ; Chen, Jing D
> ; Wang, Xiao W
> Subject: RE: [dpdk-dev] [PATCH 4/4] doc: add switch restart support to fm10k
> guide
>
>
>
> > -Original Mess
Add the description of how to add a MAC address for a VF
from PF on ixgbe.
Signed-off-by: Wenzhuo Lu
---
v2:
- reworded.
doc/guides/nics/ixgbe.rst | 11 +++
1 file changed, 11 insertions(+)
diff --git a/doc/guides/nics/ixgbe.rst b/doc/guides/nics/ixgbe.rst
index 696ff69..c687c63 10064
Hi John,
> -Original Message-
> From: Mcnamara, John
> Sent: Monday, October 23, 2017 8:27 PM
> To: Lu, Wenzhuo ; dev@dpdk.org
> Cc: Lu, Wenzhuo
> Subject: RE: [dpdk-dev] [PATCH] doc: how to set VF MAC address on ixgbe
>
>
>
> > -Original Message-
> > From: dev [mailto:dev-boun
On 10/23/2017 4:15 PM, Ferruh Yigit wrote:
> Extract into static inline function so that can be used by other
> functions.
>
> Signed-off-by: Ferruh Yigit
Series applied to dpdk-next-net/master, thanks.
On 8/29/2017 9:19 AM, Gaetan Rivet wrote:
> The starting point is known. The iterator can be directly set to it.
>
> The function rte_bus_find can easily be used with a comparison function
> always returning True. This would make it a regular bus iterator.
>
> Users doing so would however accompl
23/10/2017 16:39, Eads, Gage:
> From: Olivier Matz [mailto:olivier.m...@6wind.com]
> >
> > Some libraries in LDLIBS are currently generated from the
> > DEPDIRS-$(dirname) variables in the Makefiles. This is valid when the
> > subdirectory name match the library name, but it's not always the case,
12/10/2017 18:04, Olivier Matz:
> The list of libraries in LDLIBS was generated from the DEPDIRS-xyz
> variable. This is valid when the subdirectory name match the library
> name, but it's not always the case, especially for PMDs.
>
> The patches removes this feature and explicitly adds the proper
On 9/20/2017 3:08 AM, Yong Wang wrote:
> In func rte_eal_init(), dynamic memory stored in 'logid' allocated
> through func 'strdup' is lost when return. Fix it by freeing the memory
> before return.
Hi Yong,
This seems duplicate of http://dpdk.org/dev/patchwork/patch/29112/
Please check followin
On 10/12/2017 1:49 AM, Tomasz Duszynski wrote:
> Remove unused MRVL_DEBUG configuration option and update driver
> documentation accordingly.
>
> Signed-off-by: Tomasz Duszynski
Applied to dpdk-next-net/master, thanks.
On 10/20/2017 10:09 AM, Elza Mathew wrote:
> When using "show port xstats all" command to show xstats, the output
> is usually too long to obtain what you really want, especially when
> multi-queue is enabled.
>
> Added an option to set whether zero values should be displayed
> or not for xstats.
24/10/2017 01:15, Ferruh Yigit:
> xstats _by_id() APIs are broken because ids known by user sent directly
> to the PMDs.
>
> ethdev xstat get by id APIs:
> rte_eth_xstats_get_names_by_id() and rte_eth_xstats_get_by_id()
> work on ids calculated as "basic stats + extended stats"
>
> When an applic
19/10/2017 18:45, Bruce Richardson:
> On Thu, Oct 19, 2017 at 05:36:24PM +0100, Bruce Richardson wrote:
> > Both Linux and BSD EALs should provide exactly the same set of functions
> > to the user, even if in some cases the function is a stub returning
> > ENOTSUP. Because of this we should only ne
19/10/2017 18:36, Bruce Richardson:
> Since the functions exported by DPDK EAL on all OS's should be
> identical, we should not need separate function version files for each
> OS. Therefore move existing version files to the top-level EAL
> directory.
>
> Signed-off-by: Bruce Richardson
This sma
xstats _by_id() APIs are broken because ids known by user sent directly
to the PMDs.
ethdev xstat get by id APIs:
rte_eth_xstats_get_names_by_id() and rte_eth_xstats_get_by_id()
work on ids calculated as "basic stats + extended stats"
When an application asking for id less than "basic stats count
Some function calls in xstat functions can return negative values
to indicate the error, check return values for those cases.
Coverity issue: 195028, 195026
Fixes: 8c49d5f1c219 ("ethdev: rework xstats retrieve by id")
Signed-off-by: Ferruh Yigit
Acked-by: Thomas Monjalon
---
Cc: Lee Daly
---
Extract into static inline function so that can be used by other
functions.
Signed-off-by: Ferruh Yigit
---
lib/librte_ether/rte_ethdev.c | 24 +++-
1 file changed, 19 insertions(+), 5 deletions(-)
diff --git a/lib/librte_ether/rte_ethdev.c b/lib/librte_ether/rte_ethdev.c
in
Some function calls in xstat functions can return negative values
to indicate the error, check return values for those cases.
Coverity issue: 195028, 195026
Fixes: 8c49d5f1c219 ("ethdev: rework xstats retrieve by id")
Signed-off-by: Ferruh Yigit
Acked-by: Thomas Monjalon
---
Cc: Lee Daly
---
xstats _by_id() APIs are broken because ids known by user sent directly
to the PMDs.
ethdev xstat get by id APIs:
rte_eth_xstats_get_names_by_id() and rte_eth_xstats_get_by_id()
work on ids calculated as "basic stats + extended stats"
When an application asking for id less than "basic stats count
Extract into static inline function so that can be used by other
functions.
Signed-off-by: Ferruh Yigit
---
lib/librte_ether/rte_ethdev.c | 24 +++-
1 file changed, 19 insertions(+), 5 deletions(-)
diff --git a/lib/librte_ether/rte_ethdev.c b/lib/librte_ether/rte_ethdev.c
in
23/10/2017 11:56, Olivier Matz:
> Remove rte_set_log_level(), rte_get_log_level(),
> rte_set_log_type(), and rte_get_log_type().
>
> Also update librte_eal.so version in docuementation.
> The LIBABIVER variable in eal has already been modified in
> commit f26ab687a74f ("eal: remove Xen dom0 suppor
19/10/2017 10:49, Bruce Richardson:
> If the default location for the PMD .so files does not exist, it should
> not be treated as a fatal error condition like an incorrect path on the
> command line. Therefore check that the path exists and is a directory
> before adding it to the list of paths to
20/10/2017 15:23, Anatoly Burakov:
> When getting group fd from primary process, secondary wasn't storing
> the fd anywhere, leading to a (harmless) error message in EAL logs,
> and (not so harmless) potential problems when hot-unplugging devices
> managed by VFIO in a secondary process.
>
> Fix i
On 10/19/2017 11:53 AM, avia...@dev.mellanox.co.il wrote:
> From: Aviad Yehezkel
Hi Aviad,
What do you think using RTE_SET_USED() as done in other samples, we know those
variables may not be used if PMDs are not defined, no need to make code more
complex.
Like:
--- a/app/test-pmd/cmdline.c
23/10/2017 13:47, Burakov, Anatoly:
> On 11-Oct-17 7:42 AM, Hemant Agrawal wrote:
> > VFIO may be used by buses other than PCI. This patch enables
> > the VFIO on the basis of vfio root presence.
> >
> > Since vfio_enable should be called only once, pci_vfio_enable
> > is also removed.
> >
> > A
Suggested title:
check more errors in xstats retrieval
20/10/2017 02:03, Ferruh Yigit:
> Some function calls in xstat functions can return negative values
> to indicate the error, check return values for those cases.
>
> Coverity issue: 195028, 195026
> Fixes: 8c49d5f1c219 ("ethdev: rewor
20/10/2017 02:03, Ferruh Yigit:
> ethdev xstat get by id APIs:
> rte_eth_xstats_get_names_by_id()
> rte_eth_xstats_get_by_id()
>
> Works on ids calculated as "basic stats + device specific stats"
>
> When an application asking for id less than "basic stats count", it is
> indeed asking basic stat
On 10/19/2017 2:00 AM, Kirill Rybalchenko wrote:
> For complex packets use raw flow type with pre-constructed packet buffer
> instead of creating a packet internally in PMD.
>
> Signed-off-by: Kirill Rybalchenko
<...>
> diff --git a/drivers/net/i40e/rte_pmd_i40e.h b/drivers/net/i40e/rte_pmd_i40
19/10/2017 16:53, Remy Horton:
>
> On 19/10/2017 14:48, luca.bocca...@gmail.com wrote:
> > Document it immediately even if it's not yet supported, so that users
> > and developers can already take into account about this use case, and
> > thus avoid an API-incompatible change later on.
>
> I'm no
On 10/17/2017 12:56 AM, Nélio Laranjeiro wrote:
> On Tue, Oct 17, 2017 at 10:46:43AM +0800, Xueming Li wrote:
>> Initialize variable to avoid ICC compiler warning:
>> http://www.dpdk.org/ml/archives/dev/2017-October/077971.html
>>
>> Fixes: f8b9a3bad467 ("net/mlx5: install a socket to exchange a fi
On 10/23/2017 1:23 PM, John Daley wrote:
> If multiple Rx queues and Rx Scatter are used and the MTU is
> modified so that the number of mbufs per packet changes, packet
> loss is possible.
>
> The enic completion queue index was miscalculated leaving the
> upper half of the queues uninitialized a
On 10/23/2017 4:17 AM, Nelio Laranjeiro wrote:
> Changes in v3:
>
> * Add missing "fixes" tag in the last commit.
>
> Changes in v2:
>
> * Split last second commit in two, one for testpmd the second one for the PMD
> * Re-work "net/mlx5: fix RSS hash update" to also fix a bug introduced in th
On 10/23/2017 1:46 AM, Gaëtan Rivet wrote:
> Thanks Matan,
>
> On Sat, Oct 21, 2017 at 08:54:45PM +, Matan Azrad wrote:
>> The stats_get API was changed to signal a potential failure to read
>> stats. Furthermore, some PMDs are able to provide statistics even
>> after a removal event occurred.
23/10/2017 17:16, Bernard Iremonger:
> The initial implementation is to provide counting of IPv4 five tuple packets
> for UDP, TCP and SCTP,
> but the library is planned to be as generic as possible.
>
> The flow information provided by this library is missing to implement full
> IPFIX features,
> On Oct 23, 2017, at 7:49 AM, Nelio Laranjeiro
> wrote:
>
> Flows are added by priv_flow_create() in the associated list, adding them a
> second time corrupts the list causing an infinite loop when parsing it.
>
> Fixes: 4c3e9bcdd52e ("net/mlx5: support flow director")
>
> Signed-off-by: Nel
23/10/2017 18:26, Ferruh Yigit:
> On 10/23/2017 3:15 AM, Thomas Monjalon wrote:
> > The libraries which have their ABI version increased in this release
> > must be prepended with a + sign to make them appear clearly.
> >
> > Fixes: f8244c6399d9 ("ethdev: increase port id range")
> > Fixes: ec5144
20/10/2017 14:31, Santosh Shukla:
> Rename buf_physaddr to buf_iovaaddr
>
> Signed-off-by: Santosh Shukla
> Reviewed-by: Anatoly Burakov
Suggested title:
mbuf: rename physical address to IOVA address
On 10/20/2017 5:45 AM, Nélio Laranjeiro wrote:
> On Fri, Oct 20, 2017 at 02:39:58PM +0200, Adrien Mazarguil wrote:
>> The code as currently written requires TCP/UDP source and destination ports
>> to be always specified.
>>
>> No such restriction is enforced by hardware; all TCP and UDP traffic can
20/10/2017 14:31, Santosh Shukla:
> Renamed data type from phys_addr_t to iova_addr_t.
>
> Signed-off-by: Santosh Shukla
> Reviewed-by: Anatoly Burakov
Suggested title:
mem: rename physical to IOVA address type
20/10/2017 14:31, Santosh Shukla:
> Removed dpdk iova aware ABI deprecation notice,
> and updated ABI change details in release_17.11.rst.
>
> Signed-off-by: Santosh Shukla
> Acked-by: John McNamara
> ---
> --- a/doc/guides/rel_notes/deprecation.rst
> +++ b/doc/guides/rel_notes/deprecation.rst
>
On 10/19/2017 8:37 PM, Beilei Xing wrote:
> For L3 or L4 packets, PCtype is parsed wrongly when
> input set is VLAN only.
> This patch fixes the issue.
>
> Fixes: 15018d79f0be ("net/i40e: add FDIR support for GTP-C and GTP-U")
> Fixes: 7d83c152a207 ("net/i40e: parse flow director filter")
>
> Sig
If multiple Rx queues and Rx Scatter are used and the MTU is
modified so that the number of mbufs per packet changes, packet
loss is possible.
The enic completion queue index was miscalculated leaving the
upper half of the queues uninitialized after an MTU change, possibly
leading to completions o
On 10/19/2017 8:23 PM, Beilei Xing wrote:
> Since meta data in profile is updated, parsing inner
> packet information needs to be updated, too.
>
> Signed-off-by: Beilei Xing
Applied to dpdk-next-net/master, thanks.
20/10/2017 14:31, Santosh Shukla:
> Rename buf_physaddr to buf_iovaaddr
>
> Signed-off-by: Santosh Shukla
> Reviewed-by: Anatoly Burakov
> ---
[...]
> --- a/lib/librte_mbuf/rte_mbuf.h
> +++ b/lib/librte_mbuf/rte_mbuf.h
> @@ -411,7 +411,7 @@ struct rte_mbuf {
>* same mbuf cacheline0 layou
On 10/19/2017 7:21 PM, Beilei Xing wrote:
> This patch fixes the coverity STRING_OVERFLOW issue.
>
> Coverity issue: 195002
> Fixes: e163c18a15b0 ("net/i40e: update ptype and pctype info")
>
> Reported-by: John McNamara
> Signed-off-by: Beilei Xing
Applied to dpdk-next-net/master, thanks.
> -Original Message-
> From: Trahe, Fiona [mailto:fiona.tr...@intel.com]
> Sent: 17 October 2017 20:11
> To: shally verma ; dev@dpdk.org; Athreya,
> Narayana Prasad ; Challa, Mahipal
> ; Verma, Shally
> Cc: Trahe, Fiona
> Subject: RE: [dpdk-dev] [RFC] Compression API in DPDK
>
> Hi Shal
Sent from my Samsung Galaxy smartphone.
Original message From: Thomas Monjalon
Date: 10/23/17 20:28 (GMT+05:30) To: Santosh Shukla
Cc: dev@dpdk.org, olivier.m...@6wind.com,
jerin.ja...@caviumnetworks.com, hemant.agra...@nxp.com,
anatoly.bura...@intel.com Subject: Re: [d
On Mon, Oct 23, 2017 at 04:49:56PM +0200, Nelio Laranjeiro wrote:
> @@ -261,75 +284,59 @@ priv_dev_traffic_enable(struct priv *priv, struct
> rte_eth_dev *dev)
> };
>
> claim_zero(mlx5_ctrl_flow(dev, &promisc, &promisc));
> - } else if (dev->data->all_multicast) {
On 10/19/2017 2:15 PM, Raslan Darawsheh wrote:
> When trying to attach a port as a sub-device, the ethdev port
> was compared with devargs.
> In the case of a PCI device, the name in devargs is the PCI address.
> And since DPDK 17.08, the devargs name of the underlying device was
> used to match an
On 10/19/2017 9:11 AM, Adrien Mazarguil wrote:
> This series enforces WQ creation order to make sure WQNs are assigned
> sequentially to Rx queues and fixes a few minor issues related to
> initialization code.
>
> This addresses l3fwd-power startup issues.
>
> Adrien Mazarguil (4):
> net/mlx4:
On 10/23/2017 11:54 AM, Ferruh Yigit wrote:
> On 10/19/2017 2:39 AM, Jasvinder Singh wrote:
>> Fixed integer overflow by casting hard_rate to uint64_t type.
>
> Coverity Issue: 195020
>> Fixes: 8316b9816b79 ("net/softnic: support traffic management")
>>
>> Signed-off-by: Jasvinder Singh
>
> Revi
On Mon, Oct 23, 2017 at 09:36:38AM -0700, Ferruh Yigit wrote:
> On 10/23/2017 5:28 AM, Shijith Thotton wrote:
> > On Fri, Oct 20, 2017 at 09:57:38AM -0700, Ferruh Yigit wrote:
> >> On 10/20/2017 9:55 AM, Ferruh Yigit wrote:
> >>> Remove device reset during application start, the reset for applicati
On 10/23/2017 11:53 AM, Ferruh Yigit wrote:
> On 10/19/2017 2:38 AM, Jasvinder Singh wrote:
>> Fixed integer overflow by casting link_params.link_speed to
>> uint64_t type.
>
> Coverity Issue: 195016> Fixes: 5b590fbe09b6 ("app/testpmd: add traffic
> management forwarding mode")
>>
>> Signed-off-by
On 10/19/2017 2:39 AM, Jasvinder Singh wrote:
> Fixed integer overflow by casting hard_rate to uint64_t type.
Coverity Issue: 195020
> Fixes: 8316b9816b79 ("net/softnic: support traffic management")
>
> Signed-off-by: Jasvinder Singh
Reviewed-by: Ferruh Yigit
> On Oct 23, 2017, at 4:17 AM, Nelio Laranjeiro
> wrote:
>
> Few bugs fixes in both configuration get and hash update where inputs are
> not handled as expected by the ethdev layer.
>
> RSS structure may not be totally usable, the PMD should try to take as most
> information from it has it can
On 10/19/2017 2:38 AM, Jasvinder Singh wrote:
> Fixed integer overflow by casting link_params.link_speed to
> uint64_t type.
Coverity Issue: 195016> Fixes: 5b590fbe09b6 ("app/testpmd: add traffic
management forwarding mode")
>
> Signed-off-by: Jasvinder Singh
Reviewed-by: Ferruh Yigit
On 10/19/2017 2:33 AM, Shreyansh Jain wrote:
> Signed-off-by: Shreyansh Jain
Applied to dpdk-next-net/master, thanks.
On 10/19/2017 12:05 AM, Nélio Laranjeiro wrote:
> On Thu, Oct 19, 2017 at 09:09:26AM +0300, Ori Kam wrote:
>> Signed-off-by: Ori Kam
>> Acked-by: Shahaf Shuler
> Acked-by: Nelio Laranjeiro
Applied to dpdk-next-net/master, thanks.
On 10/18/2017 6:13 PM, Rasesh Mody wrote:
> From: Harish Patil
>
> Update/fix supported ptypes to return both inner and outer headers,
> tunnel_type, fragmented and VLAN packet types.
>
> Fixes: 3d4bb4411683 ("net/qede: add fastpath support for VXLAN tunneling")
> Fixes: 2ea6f76aff40 ("qede: add
Hi Jerin,
I have one concern with the API that may delay changing the label.
The implicit release that in rte_event_dequeue_burst() is a problem when using
asynchronous/look-aside hardware, like a cryptodev. For instance, let's say in
pipeline stage N the worker takes the event's mbuf and place
-Original Message-
> Date: Wed, 18 Oct 2017 14:15:40 +0530
> From: Pavan Nikhilesh
> To: jerin.ja...@caviumnetworks.com, santosh.shu...@caviumnetworks.com,
> nikhil@intel.com
> Cc: dev@dpdk.org, Pavan Nikhilesh
> Subject: [dpdk-dev] [PATCH v2 1/3] net/octeontx: add support for event
On 10/18/2017 2:39 AM, Andrew Rybchenko wrote:
> From: Ivan Malov
>
> Tx reap mechanism on EF10 native datapath was altered by one
> of the recent patches to introduce performance optimisations
> using the common technique of freeing mbuf segments in bulks.
>
> From this perspective, the way of
On Mon, Oct 23, 2017 at 05:17:48PM +, Van Haaren, Harry wrote:
> > From: Pavan Nikhilesh [mailto:pbhagavat...@caviumnetworks.com]
> > Sent: Friday, October 13, 2017 5:37 PM
> > To: jerin.ja...@caviumnetworks.com; hemant.agra...@nxp.com; Van Haaren,
> > Harry
> > Cc: dev@dpdk.org; Pavan Bhagava
On 10/17/2017 5:04 AM, Shahaf Shuler wrote:
> Interrupt disable can be called when the interrupt vector is not yet
> allocated. Such case ends up with segmentation fault.
>
> Fixing it by adding verification for interrupt vector validity.
>
> Fixes: 09cb5b581762 ("net/mlx5: separate DPDK from ver
-Original Message-
> Date: Mon, 23 Oct 2017 18:07:02 +0530
> From: Nipun Gupta
> To: dev@dpdk.org
> CC: hemant.agra...@nxp.com, jerin.ja...@caviumnetworks.com,
> nikhil@intel.com, Nipun Gupta
> Subject: [PATCH v5 1/5] drivers: add queue parameter in event processing
> callback
> X-M
On 10/20/17 3:04 PM, Ferruh Yigit wrote:
On 10/12/2017 10:24 AM, Roger B Melton wrote:
When copying VLAN tags from the RX descriptor to the vlan_tci field
in the mbuf header, igb_rxtx.c:eth_igb_recv_pkts() and
eth_igb_recv_scattered_pkts() both assume that the VLAN tag is always
little endian.
From: Pavan Bhagavatula
Add schedule type queue attribute so that it can be queried along with
the queue config structure.
Signed-off-by: Pavan Nikhilesh
---
v2 changes:
- return EOVERFLOW when schedule_type is requested and event_queue_cfg is set
to *ALL_TYPES*.
lib/librte_eventdev/rte
From: Pavan Bhagavatula
Update the guide with event queue configuration and event enqueue
operation.
Signed-off-by: Pavan Nikhilesh
---
doc/guides/prog_guide/eventdev.rst | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/doc/guides/prog_guide/eventdev.rst
b/doc/guides/pr
From: Pavan Bhagavatula
With the current scheme of event queue configuration the cfg schedule
type macros (RTE_EVENT_QUEUE_CFG_*_ONLY) are inconsistent with the
event schedule type (RTE_SCHED_TYPE_*) this requires unnecessary
conversion between the fastpath and slowpath API's while scheduling
eve
On 10/18/2017 1:59 AM, Tomasz Duszynski wrote:
> Add Marvell International Ltd. to the copyright holders.
>
> Signed-off-by: Tomasz Duszynski
Applied to dpdk-next-net/master, thanks.
On 10/17/2017 2:49 AM, Tomasz Duszynski wrote:
> RTE_MRVL_MUSDK_DMA_MEMSIZE can be removed from DPDK configuration
> as it's no longer used as a synchronization point for net and crypto
> mrvl pmds.
>
> Signed-off-by: Tomasz Duszynski
Applied to dpdk-next-net/master, thanks.
On 10/17/2017 12:57 AM, Nélio Laranjeiro wrote:
> On Tue, Oct 17, 2017 at 03:51:17PM +0800, Xueming Li wrote:
>> Uninitialized UAR mmap offset caused secondary tx doorbell mapped to
>> wrong address. This patch restores missing UAR mmap offset init code
>> overridden by wrong merge.
>>
>> Fixes: fa
On Mon, Oct 23, 2017 at 09:50:14AM +0200, Nélio Laranjeiro wrote:
> Yongseok, Sagi, my small contribution to this discussion,
>
> On Sun, Oct 22, 2017 at 03:01:04PM -0700, Yongseok Koh wrote:
> > On Sun, Oct 22, 2017 at 12:46:53PM +0300, Sagi Grimberg wrote:
> > >
> > > > Configuring UAR as IO-ma
1 - 100 of 217 matches
Mail list logo
