The "-Wimplicit-fallthrough=2" option was introduced into gcc 7.0, it was
enabled when the cross compiler gcc is greater than 7.0, but for the host
side buildtools/pmdinfogen, if the native is older than 7.0, it should not
be enabled.
The fix is to differentiate the host gcc Werror options from th
This is guild for cross compiling for ARM64 from X86 hosts.
Signed-off-by: Gavin Hu
Reviewed-by: Steve Capper
Reviewed-by: Honnappa Nagarahalli
Reviewed-by: Marko Kovacevic
Reviewed-by: Jerin Jacob
Reviewed-by: Thomas Monjalon
Reviewed-by: Bruce Richardson
---
doc/guides/howto/index.rst
Rx descriptor status callback was lost and request of the Rx
descriptor status crashes application if equal stride super-buffer
Rx mode is used.
Fixes: 390f9b8d82c9 ("net/sfc: support equal stride super-buffer Rx mode")
Signed-off-by: Andrew Rybchenko
---
drivers/net/sfc/sfc_ef10_essb_rx.c | 9
Hi -
Between 18.02 and the putative 18.05 there were changes in the way the
meter stuff deals with its config.
I updated the related code in lagopus, but I get warnings about using
the new APIs (it's the same for rte_meter_trtcm_profile_config())
./dpdk/meter.c: In function 'dpdk_register_m
On Xenial / 16.04 native aarch64 build with gcc 5.4.0,
lagopus build finds a couple more issues hiding in
dpdk headers.
---
Andy Green (2):
ring: fix declaration after code
ring: fix sign conversion warning
lib/librte_ring/rte_ring.h |2 +-
lib/librte_ring/rte_ring_c11_
On gcc 5.4.0 / native aarch64 from Ubuntu 16.04:
/home/agreen/lagopus/src/dpdk/build/include/rte_ring.h:
In function '__rte_ring_do_dequeue':
/home/agreen/lagopus/src/dpdk/build/include/rte_ring.h:
385:35: warning: conversion to 'int' from 'unsigned int'
may change the sign of the result [-Wsign-
On gcc 5.4.0 / native aarch64 from Ubuntu 16.04:
/home/agreen/lagopus/src/dpdk/build/include/
rte_ring_c11_mem.h: In function
'__rte_ring_move_prod_head':
/home/agreen/lagopus/src/dpdk/build/include/
rte_ring_c11_mem.h:69:3: warning: ISO C90
forbids mixed declarations and code
[-Wdeclaration-after
Add vlan to vlan prune table cost additinal firmware cycle
that cause significent performance downgrade. This patch
remove related code when enable vlan filter, the side effect
is vlan anti spoof will not work, following patch will deal
with it.
Signed-off-by: Qi Zhang
---
drivers/net/i40e/i40e_
Due to hardware limitation, there is no perfect solution to
enable VF vlan antispoof, to enable it means lost something else.
So the solution is to introduce devarg "support-vf-vlan-antispoof"
that turn on the feature to meet customer's specific requirement
while no impact on normal case when it is
(target for v18.08)
Add vlan to vlan prune table cost additinal firmware cycle
that cause significent performance downgrade (40~50%). While
remove this will cause vlan anti spoof does not work on
VF.
The dicision is to take performance as high priority, since 40~50%
performance drop is unbearabl
Confirmed!
On Fri, May 25, 2018 at 5:13 AM Thomas Monjalon wrote:
> 18/04/2018 09:57, Pablo de Lara:
> > Convert dual license headers with Intel and Hasan Alayli
> > names to SPDX.
> >
> > Signed-off-by: Pablo de Lara
>
> Waiting for confirmation from Hasan Alayli.
>
>
>
>
A new DPDK release candidate is ready for testing:
https://dpdk.org/browse/dpdk/tag/?id=v18.05-rc6
The release notes are online:
http://dpdk.org/doc/guides/rel_notes/release_18_05.html
There were several fixes and a lot of documentation updates.
This is the last release candidate.
28/05/2018 00:51, De Lara Guarch, Pablo:
> > From: Thomas Monjalon
> >
> > The *_callback_* functions are not implemented, so they are removed from the
> > export map file.
> >
> > Fixes: ed7dd94f7f66 ("compressdev: add basic device management")
> >
> > Signed-off-by: Thomas Monjalon
>
> Thank
28/05/2018 00:24, Thomas Monjalon:
> The function dpdmai_set_tx_queue() is not implemented,
> so it is removed from the export map file.
>
> Fixes: 23e8fcb0186c ("bus/fslmc: support MC DPDMAI object")
>
> Signed-off-by: Thomas Monjalon
Applied
28/05/2018 00:23, Thomas Monjalon:
> The functions
> - vfio_get_container_fd
> - vfio_get_group_fd
> - vfio_get_group_no
> have been renamed to
> - rte_vfio_get_container_fd
> - rte_vfio_get_group_fd
> - rte_vfio_get_group_num
>
> The old names are removed from
24/05/2018 14:41, Kamil Chalupnik:
> Internal buffers names have been shortened to meet ring names size
> requirements after device name changed.
>
> Fixes: 7ce00bf31bbe ("bbdev: change names of baseband devices")
>
> Signed-off-by: Kamil Chalupnik
> Acked-by: Amr Mokhtar
Considered it is crit
25/05/2018 16:15, Jasvinder Singh:
> Signed-off-by: Jasvinder Singh
Applied, thanks
24/05/2018 13:59, Jasvinder Singh:
> Update sample app user guide with ip pipeline documentation.
>
> Signed-off-by: Cristian Dumitrescu
> Signed-off-by: Jasvinder Singh
>
> Acked-by: Cristian Dumitrescu
Applied, thanks
24/05/2018 13:04, Lee Daly:
> This expands the ISA-L documentation to give more a detailed explanation
> of the mapping between the compressdev API levels and PMD levels.
>
> Signed-off-by: Lee Daly
> Acked-by: Marko Kovacevic
17/04/2018 15:47, Shahaf Shuler:
> Tuesday, April 17, 2018 4:40 PM, Ferruh Yigit:
> > Subject: [PATCH v4] doc: announce ethdev CRC strip flag deprecation
> >
> > Make CRC stripping default behavior, deprecate flag
> > DEV_RX_OFFLOAD_CRC_STRIP.
> >
> > Signed-off-by: Ferruh Yigit
> > Acked-by: An
25/05/2018 09:20, Olivier Matz:
> On Thu, May 24, 2018 at 06:20:06PM -0700, Yongseok Koh wrote:
> > Link: http://dpdk.org/ml/archives/dev/2018-April/099476.html
> >
> > Signed-off-by: Yongseok Koh
>
> Acked-by: Olivier Matz
Applied, thanks
24/05/2018 12:08, Hemant Agrawal:
> > Deprecate rte_eal_mbuf_default_mempool_ops(), it shall be replaced by
> > rte_mbuf_best_mempool_ops().
> >
> > Cc: Hemant Agrawal
> > Cc: Jerin Jacob
> >
> > Signed-off-by: Olivier Matz
>
> Acked-by: Jerin Jacob
> Acked-by: Hemant Agrawal
Acked-by: Th
25/05/2018 15:58, Bruce Richardson:
> On Fri, May 25, 2018 at 02:38:43PM +0100, Anatoly Burakov wrote:
> > Most of this work was already done, but runtime config path is
> > considered to be part of public API because of high likelihood of
> > it being used by various tools in the DPDK ecosystem, a
25/05/2018 15:41, Anatoly Burakov:
> Document new command-line switches and the principles behind the
> new memory subsystem. Also, replace outdated malloc heap picture.
>
> Signed-off-by: Anatoly Burakov
Series applied, thanks
25/05/2018 15:39, Anatoly Burakov:
> Currently, memzone allocation with length set to 0 that are also
> IOVA-contiguous is not supported. Document this limitation.
>
> Signed-off-by: Anatoly Burakov
Series applied, thanks
25/05/2018 18:56, Anatoly Burakov:
> Describe all the capabilities of DPDK IPC, and provide some
> insight into how to best make use of it.
>
> Signed-off-by: Anatoly Burakov
Applied, thanks
27/05/2018 21:13, Jerin Jacob:
> Signed-off-by: Jerin Jacob
> ---
> Pattern of this doc change is different from other NICs as Cavium
> SoC have integrated NICs. Thus, separating CPU from NIC doesn't make
> much sense.
> ---
> doc/guides/rel_notes/release_18_05.rst | 11 +++
> 1 file chan
25/05/2018 16:48, Shreyansh Jain:
> Signed-off-by: Shreyansh Jain
> ---
> note: pattern of this doc change is different from other NICs as NXP
> SoC have integrated NICs. Thus, separating CPU from NIC doesn't make
> much sense.
>
> doc/guides/rel_notes/release_18_05.rst | 11 +++
> 1 f
27/05/2018 20:55, Jerin Jacob:
> Fixes: 3e0ceb9f17ff ("doc: add basic howto for flow API")
>
> Cc: adrien.mazarg...@6wind.com
> Cc: sta...@dpdk.org
>
> Signed-off-by: Jerin Jacob
Applied, thanks
25/05/2018 16:56, Thomas Monjalon:
> 25/05/2018 16:47, Rybalchenko, Kirill:
> > Hi Tomas,
> >
> > > You CC:stable because it was implemented in 18.02
> >
> > Sorry, I was misled by check-git-log script warning.
> >
> > > > Fixes: 09dd01ad9a68 ("doc: announce behaviour change to i40e RSS")
> > >
> -Original Message-
> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Thomas Monjalon
> Sent: Sunday, May 27, 2018 11:25 PM
> To: Trahe, Fiona
> Cc: dev@dpdk.org
> Subject: [dpdk-dev] [PATCH] compressdev: fix export of unknown symbols
>
> The *_callback_* functions are not impleme
The *_callback_* functions are not implemented,
so they are removed from the export map file.
Fixes: ed7dd94f7f66 ("compressdev: add basic device management")
Signed-off-by: Thomas Monjalon
---
lib/librte_compressdev/rte_compressdev_version.map | 3 ---
1 file changed, 3 deletions(-)
diff --gi
The function dpdmai_set_tx_queue() is not implemented,
so it is removed from the export map file.
Fixes: 23e8fcb0186c ("bus/fslmc: support MC DPDMAI object")
Signed-off-by: Thomas Monjalon
---
drivers/bus/fslmc/rte_bus_fslmc_version.map | 1 -
1 file changed, 1 deletion(-)
diff --git a/drivers
The functions
- vfio_get_container_fd
- vfio_get_group_fd
- vfio_get_group_no
have been renamed to
- rte_vfio_get_container_fd
- rte_vfio_get_group_fd
- rte_vfio_get_group_num
The old names are removed from the map file.
Fixes: 964b2f3bfb07 ("vfio:
27/05/2018 23:00, Neil Horman:
> On Sun, May 27, 2018 at 09:34:13PM +0200, Thomas Monjalon wrote:
> > Hi Neil,
> >
> > Sorry, this patch has been forgotten during the whole release cycle.
> >
> Its ok, though that is frustrating, as we now need to re-familiarize ourselves
> with how this patch wo
The script check-symbol-maps.sh finds the symbols exported
in a map file but not referenced in the codebase.
Suggested-by: Pavan Nikhilesh
Signed-off-by: Thomas Monjalon
---
v2:
- rewrite Python script from Pavan in a smaller shell script
- check symbol as whole word (-w)
- print one
On Sun, May 27, 2018 at 09:34:13PM +0200, Thomas Monjalon wrote:
> Hi Neil,
>
> Sorry, this patch has been forgotten during the whole release cycle.
>
Its ok, though that is frustrating, as we now need to re-familiarize ourselves
with how this patch works.
> I see an issue about the dependency o
Sorry for having missed this patch during so long.
13/02/2018 11:48, Ferruh Yigit:
> On 2/12/2018 4:13 PM, Pavan Nikhilesh wrote:
> > This script checks for the symbols specified in the map files against
> > the symbols present in the map file directory.
> > Currently, the script checks for map fi
This is consuming stdin.
> I guess the checkpatch.pl will have nothing to check in the next step.
> We should merge Neil's patch first, because he is adding a tmpfile
> to solve the issue of stdin read only once.
>
Yup. Missed the fact stdin is consumed. temp file is a good idea
>
> > +
вт, 22 мая 2018 г. в 0:17, Olga Shern :
> You can use rdma over Ethernet, AKA ROCE
As i need to use rdma to storage traffic i don't understand benefits of
using ethernet for dpdk and roce for ib over ethernet to storage
> Mellanox PMDs don't need vfio
> I am not sure what you are trying to
Hi,
30/04/2018 08:45, Arnon Warshavsky:
> --- a/devtools/checkpatches.sh
> +++ b/devtools/checkpatches.sh
> + check_forbidden_additions -
This is consuming stdin.
I guess the checkpatch.pl will have nothing to check in the next step.
We should merge Neil's patch first, because he is a
Hi Neil,
Sorry, this patch has been forgotten during the whole release cycle.
I see an issue about the dependency on filterdiff.
Is there a way to avoid it?
I have some minor comments below.
14/02/2018 20:19, Neil Horman:
> @@ -61,6 +65,7 @@ print_usage () {
> END_OF_HELP
> }
>
> +
Th
Signed-off-by: Jerin Jacob
---
Pattern of this doc change is different from other NICs as Cavium
SoC have integrated NICs. Thus, separating CPU from NIC doesn't make
much sense.
---
doc/guides/rel_notes/release_18_05.rst | 11 +++
1 file changed, 11 insertions(+)
diff --git a/doc/guides/
-Original Message-
> Date: Mon, 28 May 2018 00:24:27 +0530
> From: Jerin Jacob
> To: dev@dpdk.org
> Cc: tho...@monjalon.net, ferruh.yi...@intel.com, john.mcnam...@intel.com,
> Shreyansh Jain , Jerin Jacob
>
> Subject: [dpdk-dev] [PATCH] doc: add tested platforms for Cavium SoCs
> X-Mail
Fixes: 3e0ceb9f17ff ("doc: add basic howto for flow API")
Cc: adrien.mazarg...@6wind.com
Cc: sta...@dpdk.org
Signed-off-by: Jerin Jacob
---
doc/guides/howto/rte_flow.rst | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/doc/guides/howto/rte_flow.rst b/doc/guides/howto/rte_flow
From: Shreyansh Jain
Signed-off-by: Jerin Jacob
---
doc/guides/rel_notes/release_18_05.rst | 11 +++
1 file changed, 11 insertions(+)
diff --git a/doc/guides/rel_notes/release_18_05.rst
b/doc/guides/rel_notes/release_18_05.rst
index a7908828e..0699b84ce 100644
--- a/doc/guides/rel_not
27/05/2018 06:06, Yuanhan Liu:
> On Tue, May 22, 2018 at 07:35:08PM +0100, Ferruh Yigit wrote:
> > + /*
> > +* This is a workaround to fix a virtio-user issue that
> > +* requires to call clean-up routine to remove existing
> > +
Although uncommon, applications may destroy a device immediately after
probing it without going through dev_configure() first.
This patch addresses a crash which occurs when mlx4_dev_close() calls
mlx4_mr_release() due to an uninitialized entry in the private structure.
And the device's B-tree sh
48 matches
Mail list logo
