On Mon, Oct 23, 2017 at 12:25:45PM -0700, Yongseok Koh wrote:
> 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
> -Original Message-
> From: Basierski, SebastianX
> Sent: Tuesday, October 24, 2017 1:11 PM
> To: y...@fridaylinux.org
> Cc: dev@dpdk.org; Basierski, SebastianX; Tan, Jianfeng; sta...@dpdk.org
> Subject: [PATCH v2] Report an error message if the flag O_NONBLOCK
> setting fails, then retu
On Tue, Oct 24, 2017 at 09:11:42AM +0200, Nélio Laranjeiro wrote:
> On Mon, Oct 23, 2017 at 12:25:45PM -0700, Yongseok Koh wrote:
> > 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 *d
24/10/2017 07:12, santosh:
> 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
When checking if any devices bound to uio, we did not exclud
those which are blacklisted (or in the case that a whitelist
is specified).
This patch fixes it by only checking whitelisted devices, or
not-blacklisted devices depending on the bus scan mode.
Fixes: 815c7deaed2d ("pci: get IOMMU class
From: Pavan Bhagavatula
Add functions to modify and delete qos responsible for mapping eth queues
to event queues used for configuring event Rx adapter.
The mbox functions have been moved from octeontx_pkivf.c to
octeontx_pkivf.h to allow event_octeontx to access them.
Signed-off-by: Pavan Nikhi
From: Pavan Bhagavatula
Add limitaion when using eth_octeontx as Rx adapter with event_octeontx.
Signed-off-by: Pavan Nikhilesh
Acked-by: John McNamara
---
doc/guides/eventdevs/octeontx.rst | 5 +
1 file changed, 5 insertions(+)
diff --git a/doc/guides/eventdevs/octeontx.rst
b/doc/guide
Add Rx adapter queue add and delete API for both generic eth_devices as
well as HW backed eth_octeontx which supports direct event injection to
event device.
The HW injected event needs to be converted into mbuf, previously this
was done in eth_octeontx during rx_burst now it is moved to
event_octe
Report an error message if the flag O_NONBLOCK setting fails,
then return from function.
Coverity issue: 143439
Fixes: ef53b6030039 ("net/virtio-user: support LSC")
Cc: jianfeng@intel.com
cc: sta...@dpdk.org
Signed-off-by: SebastianX Basierski
Acked-by: Jianfeng Tan
---
drivers/net/virtio
On Tue, Oct 24, 2017 at 07:44:53AM +, Jianfeng Tan wrote:
> When checking if any devices bound to uio, we did not exclud
> those which are blacklisted (or in the case that a whitelist
> is specified).
>
> This patch fixes it by only checking whitelisted devices, or
> not-blacklisted devices de
Report an error message if the flag O_NONBLOCK setting fails,
then return from function.
Coverity issue: 143439
Fixes: ef53b6030039 ("net/virtio-user: support LSC")
Cc: jianfeng@intel.com
cc: sta...@dpdk.org
Signed-off-by: SebastianX Basierski
Acked-by: Jianfeng Tan
---
drivers/net/virtio
Hi Jianfeng,
On Tuesday 24 October 2017 01:14 PM, Jianfeng Tan wrote:
> When checking if any devices bound to uio, we did not exclud
> those which are blacklisted (or in the case that a whitelist
> is specified).
>
> This patch fixes it by only checking whitelisted devices, or
> not-blacklisted d
A "%" is missing in the command line, so the parameter comparison always
returns failure. And the local variable "what" points to the argv[4], it is
incorrect for this command since the argc is 4 and the max should be argv[3].
Signed-off-by: bing.z...@hxt-semitech.com
Signed-off-by: jie2@hxt
On Tue, Oct 24, 2017 at 10:17:38AM +0200, SebastianX Basierski wrote:
> Report an error message if the flag O_NONBLOCK setting fails,
> then return from function.
>
> Coverity issue: 143439
>
> Fixes: ef53b6030039 ("net/virtio-user: support LSC")
> Cc: jianfeng@intel.com
> cc: sta...@dpdk.org
Hi Thomas,
> -Original Message-
> From: Thomas Monjalon [mailto:tho...@monjalon.net]
> Sent: Monday, October 23, 2017 9:59 PM
> To: Iremonger, Bernard
> Cc: dev@dpdk.org; Yigit, Ferruh ; Ananyev,
> Konstantin ; Dumitrescu, Cristian
> ; adrien.mazarg...@6wind.com; Singh,
> Jasvinder ; Mcna
> -Original Message-
> From: Yigit, Ferruh
> Sent: Monday, October 23, 2017 5:32 PM
> To: Singh, Jasvinder ; dev@dpdk.org
> Cc: Dumitrescu, Cristian ; Mcnamara, John
>
> Subject: Re: [dpdk-dev] [PATCH] examples/qos_sched: fix uninitialized scalar
> variable
>
> On 10/23/2017 3:36 AM, Jas
On Tue, Oct 24, 2017 at 11:12:30AM +0800, Tiwei Bie wrote:
> 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-
The corrupted code allowed to create internal rule with no any target queue
in case the rule creation ocured before queues creation.
For example, when user calls rte_eth_dev_default_mac_addr_set after probe
and before dev_configure, mlx4 failis because the RSS queue number was 0.
The fix prevents
On Tue, Oct 24, 2017 at 11:06:14AM +0800, Zhiyong Yang wrote:
> 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 func
On Tuesday 24 October 2017 11:59 AM, gowrishankar muthukrishnan wrote:
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/driver
From: root
when VSI is enabled with smaller number of queues,
for example, 1 or 6, it will cause error.64 is the
max number of queues that can be used for RSS,
but VSI might be created with only few queues.
Fixes: 7cbecc2f742 ("net/i40e: support queue region set and flush")
Signed-off-by: Wei Z
when VSI is enabled with smaller number of queues,
for example, 1 or 6, it will cause error.64 is the
max number of queues that can be used for RSS,
but VSI might be created with only few queues.
Fixes: 7cbecc2f742 ("net/i40e: support queue region set and flush")
Signed-off-by: Wei Zhao
---
dri
Fix problem with uninitialized rx/tx deferred_start flags of the struct
rte_eth_rxconf/txconf by initializing with 0 value (deferred start of
the rx/tx queues is turned off). This setting allows device rx/tx
queues to start with rte_eth_dev_start().
Coverity issue: 194999, 195009 (Uninitialized sc
This flag was deprecated in the previous release, and this is its removal.
We are going from an explicit support of device detach, to an implicit one,
with specific checks in place for PMDs not supporting the feature.
Attempting to Cc all relevant maintainers:
Cc: Ajit Khaparde
Cc: Alejandro Lu
Update documentation to new API.
Signed-off-by: Gaetan Rivet
---
doc/guides/prog_guide/port_hotplug_framework.rst | 8 ++--
1 file changed, 2 insertions(+), 6 deletions(-)
diff --git a/doc/guides/prog_guide/port_hotplug_framework.rst
b/doc/guides/prog_guide/port_hotplug_framework.rst
index
This flag is not necessary at the ether layer anymore.
Buses are able to advertize their hotplug support. The ether layer can
rely upon this capability instead of a special flag.
Signed-off-by: Gaetan Rivet
---
drivers/net/af_packet/rte_eth_af_packet.c | 1 -
drivers/net/ark/ark_ethdev.c
If a PCI device detach removal fails, returns the actual removal
operator error value.
Use this value within pci->unplug, as it may help applications solve an
issue with the feature or more accurately warn their users.
Signed-off-by: Gaetan Rivet
---
lib/librte_eal/common/eal_common_pci.c | 14
On 10/24/2017 11:59 AM, Gaetan Rivet wrote:
This flag is not necessary at the ether layer anymore.
Buses are able to advertize their hotplug support. The ether layer can
rely upon this capability instead of a special flag.
Signed-off-by: Gaetan Rivet
Acked-by: Andrew Rybchenko
---
driver
Add programmer's guide doc to explain the use of the
Event Ethernet Rx Adapter library.
Signed-off-by: Nikhil Rao
Acked-by: Jerin Jacob
---
v3:
* Update sample code for capability query (Jerin)
* Various formatting fixes as per doc. standard (John McNamara)
v2: Update MAINTAINERS
MAINTAINERS
On Tue, Oct 24, 2017 at 08:45:30AM +, Matan Azrad wrote:
> The corrupted code allowed to create internal rule with no any target queue
> in case the rule creation ocured before queues creation.
ocured => occurred
>
> For example, when user calls rte_eth_dev_default_mac_addr_set after probe
>
Use more secure snprintf function instead of strncpy
to prevent memory access violation.
Fixes: 40d1324423a4 ("net/i40e: get ddp profile protocol info")
Signed-off-by: Kirill Rybalchenko
---
drivers/net/i40e/rte_pmd_i40e.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/
24/10/2017 10:59, Gaetan Rivet:
> This flag is not necessary at the ether layer anymore.
> Buses are able to advertize their hotplug support. The ether layer can
> rely upon this capability instead of a special flag.
>
> Signed-off-by: Gaetan Rivet
Please update the release notes in API section
> -Original Message-
> From: Iremonger, Bernard
> Sent: Tuesday, October 24, 2017 9:41 AM
> To: Thomas Monjalon
> Cc: dev@dpdk.org; Yigit, Ferruh ; Ananyev,
> Konstantin ; Dumitrescu, Cristian
> ; adrien.mazarg...@6wind.com; Singh,
> Jasvinder ; Mcnamara, John
> ; Iremonger, Bernard
>
>
On Tue, Oct 24, 2017 at 11:23:44AM +0200, Thomas Monjalon wrote:
> 24/10/2017 10:59, Gaetan Rivet:
> > This flag is not necessary at the ether layer anymore.
> > Buses are able to advertize their hotplug support. The ether layer can
> > rely upon this capability instead of a special flag.
> >
> >
24/10/2017 11:23, Mcnamara, John:
> From: Iremonger, Bernard
> >
> > Hi Thomas,
> >
> > From: Thomas Monjalon [mailto:tho...@monjalon.net]
> >
> > > I suppose you are OK to wait one more release and call for more
> > reviewers?
> >
> > This library was not ready for 17.11.RC1 having received som
Hi Thomas,
On 10/23/2017 2:29 AM, Thomas Monjalon wrote:
22/10/2017 22:37, Akhil Goyal:
Hi All,
On 10/21/2017 9:43 PM, Akhil Goyal wrote:
Hi Thomas,
On 10/20/2017 3:02 PM, Thomas Monjalon wrote:
16/10/2017 12:44, Thomas Monjalon:
15/10/2017 00:17, Akhil Goyal:
This patchset introduce the rte
On Tue, Oct 24, 2017 at 01:21:39AM +0200, Thomas Monjalon wrote:
> 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 t
On Tue, Oct 24, 2017 at 10:22:38AM +0100, Kirill Rybalchenko wrote:
> Use more secure snprintf function instead of strncpy
> to prevent memory access violation.
>
> Fixes: 40d1324423a4 ("net/i40e: get ddp profile protocol info")
>
> Signed-off-by: Kirill Rybalchenko
Reviewed-by: Bruce Richardso
Hi,
Few comments detailed below.
The new compilation dependencies management needs changes
in the Makefile.
And the new log system should be used.
> --- a/MAINTAINERS
> +++ b/MAINTAINERS
> @@ -739,6 +739,13 @@ F: doc/guides/prog_guide/pdump_lib.rst
> F: app/pdump/
> F: doc/guides/tools/pdump.rs
24/10/2017 11:41, Akhil Goyal:
> Hi Thomas,
> On 10/23/2017 2:29 AM, Thomas Monjalon wrote:
> > 22/10/2017 22:37, Akhil Goyal:
> >> Hi All,
> >> On 10/21/2017 9:43 PM, Akhil Goyal wrote:
> >>> Hi Thomas,
> >>> On 10/20/2017 3:02 PM, Thomas Monjalon wrote:
> 16/10/2017 12:44, Thomas Monjalon:
>
Hi Thomas,
> -Original Message-
> From: Thomas Monjalon [mailto:tho...@monjalon.net]
> Sent: Tuesday, October 24, 2017 10:39 AM
> To: Mcnamara, John ; Iremonger, Bernard
>
> Cc: dev@dpdk.org; Yigit, Ferruh ; Ananyev,
> Konstantin ; Dumitrescu, Cristian
> ; adrien.mazarg...@6wind.com; Sing
Signed-off-by: Pablo de Lara
---
MAINTAINERS | 1 -
1 file changed, 1 deletion(-)
diff --git a/MAINTAINERS b/MAINTAINERS
index 6bfc6ef..553a01f 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -957,7 +957,6 @@ F: examples/performance-thread/
F: doc/guides/sample_app_ug/performance_thread.rst
M:
Hi,
On Tue, Oct 24, 2017 at 02:19:51PM +0530, gowrishankar muthukrishnan wrote:
> On Tuesday 24 October 2017 11:59 AM, gowrishankar muthukrishnan wrote:
> > Hi Adrien,
> > I am trying to compile mlx4 (and later to try mlx5) pmd in RHEL 7.4
> > (ppc64le) without Mellanox OFED,
> > using current mas
Signed-off-by: Pablo de Lara
---
MAINTAINERS | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/MAINTAINERS b/MAINTAINERS
index 5fd5acf..6bfc6ef 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -843,7 +843,7 @@ F: examples/timer/
F: doc/guides/sample_app_ug/timer.rst
Job statist
On Tue, Oct 24, 2017 at 11:55:42AM +0200, Nélio Laranjeiro wrote:
> Hi,
>
> On Tue, Oct 24, 2017 at 02:19:51PM +0530, gowrishankar muthukrishnan wrote:
> > On Tuesday 24 October 2017 11:59 AM, gowrishankar muthukrishnan wrote:
> > > Hi Adrien,
> > > I am trying to compile mlx4 (and later to try ml
The corrupted code allowed to create internal rule with no any target queue
in case the rule creation occurred before queues creation.
For example, when user calls rte_eth_dev_default_mac_addr_set after probe
and before dev_configure, mlx4 fails because the RSS queue number was 0.
The fix prevent
Hi Thomas,
> -Original Message-
> From: Thomas Monjalon [mailto:tho...@monjalon.net]
> Sent: Tuesday, October 24, 2017 10:51 AM
> To: Iremonger, Bernard
> Cc: dev@dpdk.org; Yigit, Ferruh ; Ananyev,
> Konstantin ; Dumitrescu, Cristian
> ; adrien.mazarg...@6wind.com; Singh,
> Jasvinder
> S
For AEAD algorithms, the physical address for the digest
was being set incorrectly.
Fixes: 2661f4fbe93d ("examples/l2fwd-crypto: add AEAD parameters")
Cc: sta...@dpdk.org
Signed-off-by: Pablo de Lara
---
examples/l2fwd-crypto/main.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --
24/10/2017 11:53, Iremonger, Bernard:
> Hi Thomas,
>
> From: Thomas Monjalon [mailto:tho...@monjalon.net]
> > 24/10/2017 11:23, Mcnamara, John:
> > > From: Iremonger, Bernard
> > > >
> > > > Hi Thomas,
> > > >
> > > > From: Thomas Monjalon [mailto:tho...@monjalon.net]
> > > >
> > > > > I suppose y
Signed-off-by: Nikhil Rao
Acked-by: Jerin Jacob
---
v2: fix typo (Jerin)
doc/guides/rel_notes/release_17_11.rst | 5 +
1 file changed, 5 insertions(+)
diff --git a/doc/guides/rel_notes/release_17_11.rst
b/doc/guides/rel_notes/release_17_11.rst
index e4e98f7..4520167 100644
--- a/doc/guide
This flag was deprecated in the previous release, and this is its removal.
We are going from an explicit support of device detach, to an implicit one,
with specific checks in place for PMDs not supporting the feature.
Attempting to Cc all relevant maintainers:
Cc: Ajit Khaparde
Cc: Alejandro Lu
This flag is deprecated and should not be used to check for the device
ability to be detached.
The rte_dev library call will fail with the relevant error code if
detaching this port is not possible.
Signed-off-by: Gaetan Rivet
---
lib/librte_ether/rte_ethdev.c | 26 +-
1
This flag is not necessary at the ether layer anymore.
Buses are able to advertize their hotplug support. The ether layer can
rely upon this capability instead of a special flag.
Signed-off-by: Gaetan Rivet
Acked-by: Andrew Rybchenko
---
drivers/net/af_packet/rte_eth_af_packet.c | 1 -
drivers
Update documentation to new API.
Signed-off-by: Gaetan Rivet
---
doc/guides/prog_guide/port_hotplug_framework.rst | 8 ++--
1 file changed, 2 insertions(+), 6 deletions(-)
diff --git a/doc/guides/prog_guide/port_hotplug_framework.rst
b/doc/guides/prog_guide/port_hotplug_framework.rst
index
If a PCI device detach removal fails, returns the actual removal
operator error value.
Use this value within pci->unplug, as it may help applications solve an
issue with the feature or more accurately warn their users.
Signed-off-by: Gaetan Rivet
---
lib/librte_eal/common/eal_common_pci.c | 14
Add the ether library evolution to the release notes
Signed-off-by: Gaetan Rivet
---
doc/guides/rel_notes/release_17_11.rst | 6 ++
1 file changed, 6 insertions(+)
diff --git a/doc/guides/rel_notes/release_17_11.rst
b/doc/guides/rel_notes/release_17_11.rst
index 8db35f5..80522fd 100644
---
Remove the deprecation notice as the flag has been removed.
Signed-off-by: Gaetan Rivet
---
doc/guides/rel_notes/deprecation.rst | 8
1 file changed, 8 deletions(-)
diff --git a/doc/guides/rel_notes/deprecation.rst
b/doc/guides/rel_notes/deprecation.rst
index 52058f5..354cc1c 100644
-
> -Original Message-
> From: Wang, Xiao W
> Sent: Tuesday, October 24, 2017 2:46 PM
> To: Wu, Jingjing
> Cc: dev@dpdk.org; Mcnamara, John ; Zhang, Qi Z
> ; Wang, Xiao W
> Subject: [PATCH v2 4/4] doc: add switch restart support to fm10k guide
>
> This patch documents how DPDK app should
> -Original Message-
> From: Rao, Nikhil
> Sent: Tuesday, October 24, 2017 11:32 AM
> To: dev@dpdk.org
> Cc: jerin.ja...@caviumnetworks.com; Mcnamara, John
>
> Subject: [PATCH v2] doc: add event eth Rx adapter library
>
> Signed-off-by: Nikhil Rao
> Acked-by: Jerin Jacob
Acked-by: Jo
Hi Declan,
> -Original Message-
> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Declan Doherty
> Sent: Friday, October 20, 2017 10:21 PM
> To: dev@dpdk.org
> Cc: Doherty, Declan
> Subject: [dpdk-dev] [PATCH 1/3] cryptodev: add new APIs to assist PMD
> initialisation
>
> Adds new P
From: Luca Boccassi
This new function returns 0 on success and various error codes on
different failures. Attempt to document them.
Signed-off-by: Luca Boccassi
---
lib/librte_ether/rte_ethdev.h | 8
1 file changed, 8 insertions(+)
diff --git a/lib/librte_ether/rte_ethdev.h b/lib/lib
From: Luca Boccassi
When VF reset will be supported by drivers, the API will most likely
have to return -EAGAIN to avoid blocking when the VF cannot be reset
because the PF is down.
Document it immediately even if it's not yet supported, so that users
and developers can already take into account
> -Original Message-
> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Declan Doherty
> Sent: Friday, October 20, 2017 10:21 PM
> To: dev@dpdk.org
> Cc: Doherty, Declan
> Subject: [dpdk-dev] [PATCH 2/3] cryptodev: break dependency on virtual
> device bus
>
> Removes any dependency
> -Original Message-
> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Declan Doherty
> Sent: Friday, October 20, 2017 10:21 PM
> To: dev@dpdk.org
> Cc: Doherty, Declan
> Subject: [dpdk-dev] [PATCH 3/3] cryptodev: break dependency on rte_pci.h
>
Check-git-log is complaining about
On 10/21/2017 2:51 AM, Declan Doherty wrote:
Removes any dependency of librte_cryptodev on the virtual device
infrastructure code and removes the functions which were virtual
device specific.
Updates all virtual PMDs to remove dependencies on rte_cryptodev_vdev.h
and replaces those calls with th
Drop queue should also adjust their priority according the most specific
layer in the pattern they are matching to avoid dropping all the traffic.
Fixes: 8086cf08b2f0 ("net/mlx5: handle RSS hash configuration in RSS flow")
Signed-off-by: Nelio Laranjeiro
---
drivers/net/mlx5/mlx5_flow.c | 8 +++
Hi Moti,
Small comments/question to clarify the situation for any user of this
series.
On Thu, Aug 24, 2017 at 06:54:05PM +0300, Moti Haimovsky wrote:
> This series of patches implements the mlx4-pmd with Tx data path that directly
> access the device queues for transmitting packets, bypassing th
On Tue, 2017-10-24 at 00:11 +0200, Thomas Monjalon wrote:
> 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
On Tue, 2017-10-24 at 07:18 +0100, Remy Horton wrote:
> 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 pr
Hi,
While testing MTU configuration of physical ports using OVS-DPDK we have found
that Fortville and Niantic behaves differently for Tagged packets. Both allows
TX of packets with size up to programmed MTU value but in receive direction
Fortville drops packets of size equal to configured MTU. A
24/10/2017 13:03, luca.bocca...@gmail.com:
> From: Luca Boccassi
>
> This new function returns 0 on success and various error codes on
> different failures. Attempt to document them.
>
> Signed-off-by: Luca Boccassi
Suggested title: "ethdev: document error codes of reset"
Acked-by: Thomas Mon
Thanks very much, sorry that I forgot to reply...
> -Original Message-
> From: Ferruh Yigit [mailto:ferruh.yi...@intel.com]
> Sent: Tuesday, October 24, 2017 5:54 AM
> To: Nélio Laranjeiro ; Xueming(Steven) Li
>
> Cc: Ferruh Yigit ; dev@dpdk.org
> Subject: Re: [dpdk-dev] [PATCH] net/mlx5:
24/10/2017 13:03, luca.bocca...@gmail.com:
> From: Luca Boccassi
>
> When VF reset will be supported by drivers, the API will most likely
> have to return -EAGAIN to avoid blocking when the VF cannot be reset
> because the PF is down.
> Document it immediately even if it's not yet supported, so t
> -Original Message-
> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Pablo de Lara
> Sent: Tuesday, October 24, 2017 11:57 AM
> To: tho...@monjalon.net
> Cc: dev@dpdk.org; De Lara Guarch, Pablo
> Subject: [dpdk-dev] [PATCH] maintainers: update job stats library
>
> Signed-off-by: P
24/10/2017 12:35, Gaetan Rivet:
> Gaetan Rivet (6):
> ethdev: do not rely on detachable flag in detach
> ethdev: remove detachable device flag
> pci: propagate PMD removal error value for unplug
> doc: follow detachable flag disappearance
> doc: update detachable flag deprecation notice
>
This patch works around compilation issues seen on RHEL 7.2
using GCC 4.8.5:
[...] In function 'mlx4_rss_init':
[...]/mlx4_rxq.c:433:19: error: 'wq_num' may be used uninitialized
in this function [-Werror=maybe-uninitialized]
Fixes: ff3397e90080 ("net/mlx4: relax Rx queue configurat
Thank you
> On Oct 24, 2017, at 3:37 AM, Bing Zhao wrote:
>
> A "%" is missing in the command line, so the parameter comparison always
> returns failure. And the local variable "what" points to the argv[4], it is
> incorrect for this command since the argc is 4 and the max should be argv[3].
>
From: Aviad Yehezkel
This cause auth failure issue
Fixes: 501e9c226adf ("examples/ipsec-secgw: add AEAD parameters")
Cc: sta...@dpdk.org
Signed-off-by: Aviad Yehezkel
--
v3:
* Address feedbacks.
v2:
* Fix commit message.
---
examples/ipsec-secgw/sa.c | 2 +-
1 file changed, 1 insertion(+), 1
From: Aviad Yehezkel
Search for session also with aead key
Fixes: 501e9c226adf ("examples/ipsec-secgw: add AEAD parameters")
Cc: sta...@dpdk.org
Signed-off-by: Aviad Yehezkel
--
v3:
* Added fixes string in commit message.
v2:
* Fix commit message.
* Addressed feedback.
---
examples/ipsec-secg
From: Aviad Yehezkel
Fixes: 501e9c226adf ("examples/ipsec-secgw: add AEAD parameters")
Cc: sta...@dpdk.org
Signed-off-by: Aviad Yehezkel
--
v3:
* Address feedbacks.
v2:
* Fix commit message.
* Address feedbacks.
---
examples/ipsec-secgw/ipsec-secgw.c | 13 +++--
examples/ipsec-secgw/ip
From: Aviad Yehezkel
According to rfc4106 the IV should be unique and can be implemented
as counter.
The changed was created because putting an analyzer on wire and
comparing packets generated by this application and Linux kernel.
Linux kernel sets IV as BE, so it is worth to do the same for
futu
From: Pavan Bhagavatula
Add functions to modify and delete qos responsible for mapping eth queues
to event queues used for configuring event Rx adapter.
The mbox functions have been moved from octeontx_pkivf.c to
octeontx_pkivf.h to allow event_octeontx to access them.
Signed-off-by: Pavan Nikhi
From: Pavan Bhagavatula
Add Rx adapter queue add and delete API for both generic eth_devices as
well as HW backed eth_octeontx which supports direct event injection to
event device.
The HW injected event needs to be converted into mbuf, previously this
was done in eth_octeontx during rx_burst now
From: Pavan Bhagavatula
Add limitaion when using eth_octeontx as Rx adapter with event_octeontx.
Signed-off-by: Pavan Nikhilesh
Acked-by: John McNamara
---
doc/guides/eventdevs/octeontx.rst | 5 +
1 file changed, 5 insertions(+)
diff --git a/doc/guides/eventdevs/octeontx.rst
b/doc/guide
On Tue, 24 Oct 2017 12:25:38 +
Nitin Katiyar wrote:
> Hi,
> While testing MTU configuration of physical ports using OVS-DPDK we have
> found that Fortville and Niantic behaves differently for Tagged packets. Both
> allows TX of packets with size up to programmed MTU value but in receive
>
>-Original Message-
>From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Pablo de Lara
>Sent: Tuesday, October 24, 2017 11:56 AM
>To: tho...@monjalon.net
>Cc: dev@dpdk.org; De Lara Guarch, Pablo
>Subject: [dpdk-dev] [PATCH] maintainers: update ptp client app
>
>Signed-off-by: Pablo de Lar
This commit addresses the issue of rx interrupts support with
the new Rx datapath introduced in DPDK version 17.11.
In order to generate an Rx interrupt an event queue is armed with the
consumer index of the Rx completion queue. Since version 17.11 this
index is handled by the PMD so it is now the
From: Luca Boccassi
This reset function will stop and restart the device, and then reset
the stats and check that the registers have been updated.
Signed-off-by: Luca Boccassi
---
drivers/net/e1000/igb_ethdev.c | 59 ++
1 file changed, 59 insertions(+)
From: Luca Boccassi
These patches were originally sent by Wenzhuo Lu:
http://dpdk.org/dev/patchwork/patch/14009/
http://dpdk.org/dev/patchwork/patch/14010/
http://dpdk.org/dev/patchwork/patch/14011/
The current rte_eth_dev_reset API does not correctly reset the VF
when the PF flaps on the host.
From: Luca Boccassi
This reset function will stop and restart the device, and then reset
the stats and check that the registers have been updated.
Signed-off-by: Luca Boccassi
---
drivers/net/ixgbe/ixgbe_ethdev.c | 60 +++-
drivers/net/ixgbe/ixgbe_ethdev.h |
From: Luca Boccassi
This reset function will detach then re-attach the device, reconfigure
it, and re-setup the Rx/Tx queues.
Signed-off-by: Luca Boccassi
---
drivers/net/i40e/i40e_ethdev.h| 3 +++
drivers/net/i40e/i40e_ethdev_vf.c | 56 ---
drivers/net
From: Luca Boccassi
This new function returns 0 on success and various error codes on
different failures. Attempt to document them.
Signed-off-by: Luca Boccassi
Acked-by: Thomas Monjalon
---
lib/librte_ether/rte_ethdev.h | 8
1 file changed, 8 insertions(+)
diff --git a/lib/librte_e
On Tue, 2017-10-24 at 14:27 +0200, Thomas Monjalon wrote:
> 24/10/2017 13:03, luca.bocca...@gmail.com:
> > From: Luca Boccassi
> >
> > This new function returns 0 on success and various error codes on
> > different failures. Attempt to document them.
> >
> > Signed-off-by: Luca Boccassi
>
> Su
From: Luca Boccassi
When VF reset will be supported by drivers, the API will most likely
have to return -EAGAIN to avoid blocking when the VF cannot be reset
because the PF is down.
Document it immediately even if it's not yet supported, so that users
and developers can already take into account
Signed-off-by: Igor Ryzhov
---
lib/librte_lpm/rte_lpm.c | 6 ++
1 file changed, 6 insertions(+)
diff --git a/lib/librte_lpm/rte_lpm.c b/lib/librte_lpm/rte_lpm.c
index 64c074e..140dbb2 100644
--- a/lib/librte_lpm/rte_lpm.c
+++ b/lib/librte_lpm/rte_lpm.c
@@ -218,6 +218,7 @@ rte_lpm_create_v20(
Signed-off-by: Igor Ryzhov
---
lib/librte_lpm/rte_lpm6.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/lib/librte_lpm/rte_lpm6.c b/lib/librte_lpm/rte_lpm6.c
index b4a7df3..5ca322c 100644
--- a/lib/librte_lpm/rte_lpm6.c
+++ b/lib/librte_lpm/rte_lpm6.c
@@ -191,6 +191,7 @@ rte_lpm6_create(c
> -Original Message-
> From: Thomas Monjalon [mailto:tho...@monjalon.net]
> Sent: Monday, October 16, 2017 6:46 PM
> To: Wu, Jingjing
> Cc: dev@dpdk.org; Tan, Jianfeng ;
> shreyansh.j...@nxp.com;
> hemant.agra...@nxp.com; santosh.shu...@caviumnetworks.com; Tomasz Duszynski
> ; Jacek Siu
On Tue, Oct 24, 2017 at 09:34:34AM +0200, Nélio Laranjeiro wrote:
> On Tue, Oct 24, 2017 at 09:11:42AM +0200, Nélio Laranjeiro wrote:
> > On Mon, Oct 23, 2017 at 12:25:45PM -0700, Yongseok Koh wrote:
> > > On Mon, Oct 23, 2017 at 04:49:56PM +0200, Nelio Laranjeiro wrote:
> > > > @@ -261,75 +284,59
On Mon, Oct 23, 2017 at 02:21:57PM +, Ophir Munk wrote:
> From: Matan Azrad
>
> Merge tx_burst and mlx4_post_send functions to prevent
> double asking about WQ remain space.
>
> This should improve performance.
>
> Signed-off-by: Matan Azrad
> ---
> drivers/net/mlx4/mlx4_rxtx.c | 353
> +
Hi Moti,
On Tue, Oct 24, 2017 at 03:35:33PM +0300, Moti Haimovsky wrote:
> This patch works around compilation issues seen on RHEL 7.2
> using GCC 4.8.5:
>
>[...] In function 'mlx4_rss_init':
>[...]/mlx4_rxq.c:433:19: error: 'wq_num' may be used uninitialized
> in this function [-
1 - 100 of 230 matches
Mail list logo
