Hi Jia,
Thanks for your feedback, let's see if there are requests from others to split
the fix.
The is a race condition between updating the tail and getting
free/avail_entries, which is dependent on the tails.
Which should be synchronized by load-acquire and store-release. In simple words
bel
From: Yunjian Wang
We assume VLAN ethtertype is 0x8100 in get_vlan_offset() function,
but it could be 0x88A8 if QinQ is supported.
Signed-off-by: Yunjian Wang
---
drivers/net/bonding/rte_eth_bond_pmd.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/net/bonding/rt
On 06-Aug-18 10:50 AM, Thomas Monjalon wrote:
06/08/2018 10:43, Takeshi Yoshimura:
Commit 73a639085938 ("vfio: allow to map other memory regions")
introduced a bug in sPAPR IOMMU mapping. The commit removed necessary
ioctl with VFIO_IOMMU_SPAPR_REGISTER_MEMORY. Also, vfio_spapr_map_walk
should c
On 03-Aug-18 1:05 PM, Naga Suresh Somarowthu wrote:
1/6: add helper functions for tests using ring-PMD Rx/Tx
2/6: unit test cases added for bitrate library
3/6: unit test cases added for latencystats library
4/6: unit test cases added for pdump library
5/6: added new unit tests to autotest list
6
rte_hash_lookup_data() and rte_hash_lookup_with_hash_data()
functions return the index of the table where the key is stored
when this is found, and not 0 as the Doxygen currently states.
Also, these functions, and rte_hash_get_key_with_position()
return negative values when keys are not found (-EI
06/08/2018 20:11, Stephen Hemminger:
> Recent Covertity scan reported some issues in code that is
> unlikely to be used, but fix it anyway.
>
> Stephen Hemminger (3):
> vmbus: close directory in error path
> vmbus: make sure path is null terminated
> vmbus: handle eof on irq read
Applied, t
06/08/2018 20:22, Stephen Hemminger:
> A couple of small missing features discovered during later
> testing. The netvsc PMD was not setting packet type or reporting
> checksum failures.
>
> Stephen Hemminger (2):
> netvsc: support packet type
> netvsc: report checksum failures
Applied, thank
06/08/2018 18:31, Stephen Hemminger:
> Since netvsc PMD does not support SR-IOV accelerated networking,
> it is not recommended for use on Azure. Make this clear in the
> guide.
>
> Signed-off-by: Stephen Hemminger
There is a warning:
WARNING: undefined label: ./vdev_netvsc (if the link has no c
06/08/2018 19:52, Andrew Rybchenko:
> On 06.08.2018 13:55, Thomas Monjalon wrote:
> > The old offload API is removed in 18.08,
> > so the library version must be increased,
> > in order to show the incompatibility with 18.05 one.
> >
> > Fixes: ab3ce1e0c193 ("ethdev: remove old offload API")
> >
>
On 27/7/2018 10:53 AM, Radu Nicolau wrote:
Do not exit the application if power library fails to initialize
or high performance cores configuration cannot be used.
Signed-off-by: Radu Nicolau
---
v2: updated init_power_library to return error code if any core init fails
examples/l3fwd-pow
Do not exit the application if power library fails to initialize
or high performance cores configuration cannot be used - this was the
behavior of the application before the patch that added the high/regular
performance option and also this is the normally expected behavior, the
application can be
07/08/2018 04:00, Pablo de Lara:
> rte_hash_lookup_data() and rte_hash_lookup_with_hash_data()
> functions return the index of the table where the key is stored
> when this is found, and not 0 as the Doxygen currently states.
>
> Also, these functions, and rte_hash_get_key_with_position()
> return
> -Original Message-
> From: Liu, Yong
> Sent: Tuesday, July 31, 2018 5:01 PM
> To: Mcnamara, John ; Bie, Tiwei
> ; dev@dpdk.org
> Cc: Liu, Yong
> Subject: [PATCH v3] doc: add note for builtin-net-driver option
>
> Very simple version of vhost-user driver in vhost sample will be used i
06/08/2018 15:16, Adrien Mazarguil:
> On Mon, Aug 06, 2018 at 10:58:47AM +, Matan Azrad wrote:
> > The rte_flow meaning of zero flow mask configuration is to match all
> > the range of the item value.
> > For example, the flow eth / ipv4 dst spec 1.2.3.4 dst mask 0.0.0.0
> > should much all the
There is a need to offload rewrite MAC address for both destination and source
from the matched flow
The proposed actions could make above easily achieved
Signed-off-by: Xiaoyu Min mailto:jack...@mellanox.com>>
---
lib/librte_ethdev/rte_flow.h | 32
1 file changed
There is a need to rewrite TTL by decrease or just set it directly,
and it's not necessary to check if the final result is zero or not.
This is slightly different from the one defined by openflow and
make the actions more generic.
Signed-off-by: Xiaoyu Min
---
lib/librte_ethdev/rte_flow.h |
On 08/03/2018 04:37 PM, Adrien Mazarguil wrote:
Signed-off-by: Adrien Mazarguil
Cc: Thomas Monjalon
Cc: Ferruh Yigit
Cc: Gaetan Rivet
---
doc/guides/rel_notes/deprecation.rst | 7 +++
1 file changed, 7 insertions(+)
diff --git a/doc/guides/rel_notes/deprecation.rst
b/doc/guides/re
pdump library now uses generic multi process channel
and it is no more dependent on the pthreads, so remove
the dependency from the Makefile.
CC: sta...@dpdk.org
Signed-off-by: Reshma Pattan
---
lib/librte_pdump/Makefile | 1 -
1 file changed, 1 deletion(-)
diff --git a/lib/librte_pdump/Makefi
On 8/5/2018 9:03 PM, Rami Rosen wrote:
> This patch fixes a doxygen comment of the rte_eth_dev_allocate()
> method. There is no parameter named "type" for this
> method; so this patch removes the doxygen comment about it.
>
> Signed-off-by: Rami Rosen
Fixes: 6751f6deb798 ("ethdev: get rid of de
On 7/8/2018 2:24 PM, Radu Nicolau wrote:
Do not exit the application if power library fails to initialize
or high performance cores configuration cannot be used - this was the
behavior of the application before the patch that added the high/regular
performance option and also this is the normally
On Tue, 07 Aug 2018 14:20:13 +0200
Thomas Monjalon wrote:
> 06/08/2018 18:31, Stephen Hemminger:
> > Since netvsc PMD does not support SR-IOV accelerated networking,
> > it is not recommended for use on Azure. Make this clear in the
> > guide.
> >
> > Signed-off-by: Stephen Hemminger
>
> The
On 8/7/2018 4:45 PM, Hunt, David wrote:
On 7/8/2018 2:24 PM, Radu Nicolau wrote:
Do not exit the application if power library fails to initialize
or high performance cores configuration cannot be used - this was the
behavior of the application before the patch that added the high/regular
perf
07/08/2018 18:23, Stephen Hemminger:
> On Tue, 07 Aug 2018 14:20:13 +0200
> Thomas Monjalon wrote:
>
> > There is a warning:
> > WARNING: undefined label: ./vdev_netvsc (if the link has no caption the
> > label must precede a section header)
> >
> > Fixed with following diff:
> > - On Azure,
https://bugs.dpdk.org/show_bug.cgi?id=78
Ajit Khaparde (ajit.khapa...@broadcom.com) changed:
What|Removed |Added
Status|IN_PROGRESS |RESOLVED
This patch removes the forward declaration of rte_pci_remove_device()
method. In the past, this forward decalaration was needed for
rte_pci_detach(), which is now removed from pci_common.c.
Fixes: e690338a7b85 ("bus/pci: remove unused function to detach by address")
Signed-off-by: Rami Rosen
--
06/08/2018 17:24, Cristian Dumitrescu:
> After adding RSS hash offload checks, flags that are not supported by
> the current device result in RSS configuration failing as opposed to
> unsupported flags being silently discarded. This fix is making sure
> that only device supported flags are passed t
From: Olivier Matz
Remove experimental tag from rte_eal_mbuf_user_pool_ops().
Signed-off-by: Olivier Matz
Acked-by: Santosh Shukla
---
v3:
* nothing
v2:
* remove rte_eal_mbuf_user_pool_ops from .map in this patch instead of previous
one
lib/librte_eal/bsdapp/eal/eal.c | 2 +-
lib/l
From: Olivier Matz
rte_eal_mbuf_default_mempool_ops() is replaced by
rte_mbuf_best_mempool_ops().
Signed-off-by: Olivier Matz
Reviewed-by: Anatoly Burakov
Acked-by: Santosh Shukla
---
v3:
* bump ABI version and update the release notes
v2:
* remove rte_eal_mbuf_user_pool_ops from .map in nex
Hi Thomas,
I updated the commit message in my v2 patch.
Could you check if your questions get answered by the new commit message and
this mail?
And what's your opinions of splitting the patch into 4 smaller ones(2 bug fixes
and 2 optimizations)? I got this comment from Jia He, he is the author
-Original Message-
> Date: Tue, 7 Aug 2018 07:56:08 +
> From: Gavin Hu
> To: "He, Jia" , "dev@dpdk.org"
> CC: Honnappa Nagarahalli , Steve Capper
> , Ola Liljedahl ,
> "jerin.ja...@caviumnetworks.com" ,
> "hemant.agra...@nxp.com" , "sta...@dpdk.org"
>
> Subject: RE: [PATCH v2] ri
-Original Message-
> Date: Fri, 3 Aug 2018 16:37:52 +0200
> From: Adrien Mazarguil
> To: Neil Horman
> Cc: dev@dpdk.org, Thomas Monjalon , Ferruh Yigit
> , Gaetan Rivet
> Subject: [dpdk-dev] [PATCH] doc: announce deprecation of flow copy function
> X-Mailer: git-send-email 2.11.0
>
>
From: Shahed Shaikh
PMD did not pass down the intended queue id while
configuring the ntuple filter.
Fixes: 622075356e8f ("net/qede: support ntuple and flow director filter")
Cc: sta...@dpdk.org
Signed-off-by: Shahed Shaikh
---
drivers/net/qede/qede_fdir.c |3 +++
1 file changed, 3 insert
Signed-off-by: Rasesh Mody
---
drivers/net/qede/qede_ethdev.h |2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/qede/qede_ethdev.h b/drivers/net/qede/qede_ethdev.h
index 59ad8d3..6e9a5b4 100644
--- a/drivers/net/qede/qede_ethdev.h
+++ b/drivers/net/qede/qede_ethde
33 matches
Mail list logo
