Hi,
When trying to pull the tree, the compilation failed at the third patch:
eventdev: implement the northbound APIs
When building for x86_64:
In file included from lib/librte_eventdev/rte_eventdev.c:61:
lib/librte_eventdev/rte_eventdev.h:248:10: fatal error:
'rte_
Hi Thomas/Olivier,
On 4/4/2017 12:28 PM, Thomas Monjalon wrote:
2017-04-04 11:05, Hemant Agrawal:
Hi Olivier,
On 4/3/2017 8:49 PM, Olivier Matz wrote:
Hi Hemant,
On Mon, 3 Apr 2017 14:42:09 +0530, Hemant Agrawal
wrote:
Hardware pools need to distinguish between buffers allocated using
sof
On 17-04-04 09:13:38, Thomas Monjalon wrote:
> Hi,
>
> When trying to pull the tree, the compilation failed at the third patch:
> eventdev: implement the northbound APIs
>
> When building for x86_64:
> In file included from lib/librte_eventdev/rte_eventdev.c:61:
> lib/librte_eve
On Tue, 04 Apr 2017 08:58:40 +0200
Thomas Monjalon wrote:
> 2017-04-04 11:05, Hemant Agrawal:
> > Hi Olivier,
> >
> > On 4/3/2017 8:49 PM, Olivier Matz wrote:
> > > Hi Hemant,
> > >
> > > On Mon, 3 Apr 2017 14:42:09 +0530, Hemant Agrawal
> > > wrote:
> > >> Hardware pools need to distinguis
On Mon, 03 Apr 2017 18:15:25 +0200
Thomas Monjalon wrote:
> 2017-03-31 09:18, Ananyev, Konstantin:
> > > On Fri, 31 Mar 2017 09:41:39 +0100, Bruce Richardson
> > > wrote:
> > > > On Fri, Mar 31, 2017 at 10:26:10AM +0200, Olivier Matz wrote:
> > > > > I replayed my tests, and I can also see a
On Tue, Apr 04, 2017 at 09:58:49AM +0200, Olivier MATZ wrote:
> On Mon, 03 Apr 2017 18:15:25 +0200
> Thomas Monjalon wrote:
>
> > 2017-03-31 09:18, Ananyev, Konstantin:
> > > > On Fri, 31 Mar 2017 09:41:39 +0100, Bruce Richardson
> > > > wrote:
> > > > > On Fri, Mar 31, 2017 at 10:26:10AM +020
On 4/4/2017 3:33 AM, Qi Zhang wrote:
> Add two commands to show/clear VF stats
> show vf stats
> clear vf stats
>
> Signed-off-by: Qi Zhang
Applied to dpdk-next-net/master, thanks.
(Fixed doc warning [1] while applying.)
[1]
"
.../doc/guides/testpmd_app_ug/testpmd_funcs.rst:336:
WARNING:
2017-03-29 17:53, Olivier Matz:
> +/* dump global level and registered log types */
> +void
> +rte_log_dump(FILE *f)
> +{
> + size_t i;
> +
> + fprintf(f, "global log level is %s\n",
> + loglevel_to_string(rte_log_get_global_level()));
>
Compilation fails here:
fatal err
On 03/04/2017 4:51 PM, Fiona Trahe wrote:
Add note to cryptodev API that chained mbufs
are not supported in DOCSISBPI mode.
Signed-off-by: Fiona Trahe
---
...
Acked-by: Declan Doherty
Hi Hemant,
On Tue, 4 Apr 2017 12:59:08 +0530
Hemant Agrawal wrote:
> Hi Thomas/Olivier,
>
> On 4/4/2017 12:28 PM, Thomas Monjalon wrote:
> > 2017-04-04 11:05, Hemant Agrawal:
> >> Hi Olivier,
> >>
> >> On 4/3/2017 8:49 PM, Olivier Matz wrote:
> >>> Hi Hemant,
> >>>
> >>> On Mon, 3 Apr 2017
This patch fixes the incorrection slave session free operation.
Fixes: 57523e682bb7 ("crypto/scheduler: register operation functions")
Signed-off-by: Fan Zhang
---
v3:
- Fixed incorrect removal in v2
v2:
- Removed unnecessary session set line.
drivers/crypto/scheduler/scheduler_pmd_ops.c | 5
On 4/4/2017 2:55 AM, Qi Zhang wrote:
> The patch set create new APIs that help to change the mapping from hardware
> defined packet type to software defined packet type for i40e NICs.
> Keep these APIs private is because currently they are only meaningful for
> devices that support dynamic PTYPE co
Coverity issue 143258: not freeing distributor instance
Coverity issue 143254: not checking return code from malloc
Fixes: 775003ad2f96 ("distributor: add new burst-capable library")
Signed-off-by: David Hunt
---
lib/librte_distributor/rte_distributor.c | 5 +
1 file changed, 5 insertions(+
> -Original Message-
> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Declan Doherty
> Sent: Tuesday, April 04, 2017 10:08 AM
> To: dev@dpdk.org
> Subject: Re: [dpdk-dev] [PATCH v2] cryptodev: add API note
>
> On 03/04/2017 4:51 PM, Fiona Trahe wrote:
> > Add note to cryptodev API
> -Original Message-
> From: Trahe, Fiona
> Sent: Monday, April 03, 2017 3:13 PM
> To: dev@dpdk.org; De Lara Guarch, Pablo
> Cc: Trahe, Fiona; Jain, Deepak K; Mcnamara, John
> Subject: [PATCH v3 0/3] crypto/qat: add support for Intel QAT device D15xx
>
> Add support for Intel QuickAssist
2017-03-29 16:19, Sergio Gonzalez Monroy:
> On 16/03/2017 16:28, Jianfeng Tan wrote:
> > When binding with vfio-pci, secondary process cannot be started with
> > an error message:
> >
> > cannot find TAILQ entry for PCI device.
> >
> > It's due to: struct rte_pci_addr is padded with 1 byte for
> -Original Message-
> From: Mcnamara, John
> Sent: Monday, April 03, 2017 4:33 PM
> To: akhil.go...@nxp.com; dev@dpdk.org
> Cc: nhor...@tuxdriver.com; De Lara Guarch, Pablo
> Subject: RE: [dpdk-dev] [PATCH] doc: update deprecation notice and
> release_17_05 for ABI change
>
>
>
> > --
Hi,
2017-03-30 22:09, Qi Zhang:
> It seems its not necessary to register an intr_handle for interrupt callback
> function. "void* cb_arg" shows enough when be used to pass the object that
> contain the information be required to handle the interrupt event( A typical
> way which is implemented by
Ping
2017-03-09 21:13, Thomas Monjalon:
> 2017-02-16 16:17, Markos Chandras:
> > The librte_ethtool library depends on librte_pmd_ixgbe if that
> > pmd driver is enabled so we need to link against it when we compile
> > the ethtool application. It fixes the following build problem:
> >
> > /usr/l
On 17-04-04 09:13:38, Thomas Monjalon wrote:
> Hi,
>
> When trying to pull the tree, the compilation failed at the third patch:
> eventdev: implement the northbound APIs
>
> When building for x86_64:
> In file included from lib/librte_eventdev/rte_eventdev.c:61:
> lib/librte_eve
2017-03-24 14:30, Bruce Richardson:
> When loading nic_uio from /boot/loader.conf as specified in the Getting
> Started Guide doc, the NIC devices were not bound at boot. Unloading the
> nic_uio driver and reloading it would cause them to be bound, however.
>
> The root cause appears to be the fac
Pretty much the same as one from Bruce:
http://dpdk.org/ml/archives/dev/2017-April/062936.html
but now for ixgbe.
Based on Olivier's mbuf rework patchset, and makes some
improvement to the ixgbe driver taking account of the rework.
It also removes a build-time option that seems unnecessary.
Depend
Having packets received without any offload flags given in the mbuf is not
very useful, and performance tests with testpmd indicates little
benefit is got with the current code by turning off the flags. This makes
the build-time option pointless, so we can remove it.
Signed-off-by: Konstantin Anan
With the mbuf rework, we now have 8 contiguous bytes to be rearmed in the
mbuf just before the 8-bytes of olflags. If we don't do the rearm write
inside the descriptor ring replenishment function, and delay it to
receiving the packet, we can do a single 16B write inside the RX function
to set both
On 4/3/2017 2:27 PM, Ferruh Yigit wrote:
> On 4/1/2017 2:18 AM, Wenzhuo Lu wrote:
>> Ixgbe supports to set TCs' bandwidth allocation.
>> This patch set enables this feature.
>>
>> Bernard Iremonger (2):
>> net/ixgbe: allocate TC bandwidth
>> app/testpmd: add CLI to set TC min bandwidth
>
> Hi
On 04/04/2017 11:15, Thomas Monjalon wrote:
Ping
[..]
--- a/examples/ethtool/ethtool-app/Makefile
+++ b/examples/ethtool/ethtool-app/Makefile
+ifeq ($(CONFIG_RTE_LIBRTE_IXGBE_PMD),y)
+LDLIBS += -lrte_pmd_ixgbe
+endif
Please, could you confirm we can remove the same LDLIBS line from
examples/
mbuf next is equal to NULL, nb_segs and reference counter are equal to 1
when mbuf is obtained from mempool.
Signed-off-by: Andrew Rybchenko
---
Depends on http://dpdk.org/ml/archives/dev/2017-March/059693.html
drivers/net/sfc/sfc_ef10_rx.c | 18 +-
drivers/net/sfc/sfc_rx.c
From: Andy Moreton
Coverity issue: 1387551
Fixes: e7cd430c864f ("net/sfc/base: import SFN7xxx family support")
Cc: sta...@dpdk.org
Signed-off-by: Andy Moreton
Signed-off-by: Andrew Rybchenko
---
drivers/net/sfc/base/ef10_tx.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a
From: Andy Moreton
Improve error checking to avoid a caller overflowing the MCDI
request buffer if the requested TXQ size was excessively large.
Coverity issue: 1305527
Fixes: e7cd430c864f ("net/sfc/base: import SFN7xxx family support")
CC: sta...@dpdk.org
Signed-off-by: Andy Moreton
Signed-of
From: Andy Moreton
Coverity issue: 1349662
Fixes: e7cd430c864f ("net/sfc/base: import SFN7xxx family support")
Cc: sta...@dpdk.org
Signed-off-by: Andy Moreton
Signed-off-by: Andrew Rybchenko
---
drivers/net/sfc/base/ef10_nic.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --
Hi,
Is it possible to build ZUC PMD as a shared library?
There is this error when compiling:
libsso_zuc.a(sso_zuc_yasm.o):
relocation R_X86_64_32 against symbol `EK_d' can not be used
when making a shared object; recompile with -fPIC
On 4/1/2017 2:18 AM, Wenzhuo Lu wrote:
> Ixgbe supports to set TCs' bandwidth allocation.
> This patch set enables this feature.
>
> Bernard Iremonger (2):
> net/ixgbe: allocate TC bandwidth
> app/testpmd: add CLI to set TC min bandwidth
Applied to dpdk-next-net/master, thanks.
Let's remind the obvious:
a patch must never break the compilation of any area of code
It happens to have some break with some kernels or architectures,
but it should be an exception and fixed quickly when it is discovered.
I am seeing more and more patches which cannot be applied because
In DPDK, GRO is a device ability. The unit of enabling/disabling GRO is
port. To support GRO, this patch implements a GRO API framework, which
includes two parts. One is external functions provided to applications to
use GRO ability; the other is a generic reassembly function provided to
devices.
This patch demonstrates the usage of DPDK GRO in testpmd. By default,
GRO is turned off. Command, "gro on (port_id)", turns on GRO for the
given port; command, "gro off (port_id)", turns off GRO for the given
port. Note that, current GRO only supports TCP IPv4 packets.
Once the feature is turned o
Introduce three new functions to support TCP/IPv4 GRO.
- rte_gro_tcp4_tbl_create: create a TCP/IPv4 hashing table;
- rte_gro_tcp4_reassemble: try to reassemble an incoming TCP/IPv4 packet
with existed TCP/IPv4 packets;
- rte_gro_tcp4_cksum_update: update TCP and IPv4 checksums.
rte_gro_tcp4_re
Generic Receive Offload (GRO) is a widely used SW-based offloading
technique to reduce per-packet processing overhead. It gains performance
by reassembling small packets into large ones. Therefore, we propose to
add GRO support in DPDK.
DPDK GRO is designed as a device ability, which is turned off
fixes:
error: In the GNU C Library, "makedev" is defined
by . For historical compatibility, it is
currently defined by as well, but we plan to
remove this soon. To use "makedev", include
directly. If you did not intend to use a system-defined macro
"makedev", you should undefine it after includin
2017-03-28 16:00, Ferruh Yigit:
> On 3/27/2017 1:32 PM, Reshma Pattan wrote:
> > Update the document with the available EAL command
> > line option to install the pmd drivers that are built
> > as shared libraries.
> >
> > Signed-off-by: Reshma Pattan
>
> Acked-by: Ferruh Yigit
Applied, thanks
fix below warning:
error: In the GNU C Library, "makedev" is defined
by . For historical compatibility, it is
currently defined by as well, but we plan to
remove this soon. To use "makedev", include
directly. If you did not intend to use a system-defined macro
"makedev", you should undefine it af
On 4/3/2017 5:14 PM, Bernard Iremonger wrote:
> Handle the following eth patterns:
> eth dst spec aa:bb:cc:dd:ee:ff
> eth dst mask ff:ff:ff:ff:ff:ff
> eth src spec aa:bb:cc:dd:ee:ff
> eth src mask ff:ff:ff:ff:ff:ff
>
> Fixes: d46e85af6b5c ("net/i40e: parse QinQ pattern")
>
> Signed-off-by: Bernar
> -Original Message-
> From: Thomas Monjalon [mailto:thomas.monja...@6wind.com]
> Sent: Tuesday, April 4, 2017 6:13 PM
> To: Zhang, Qi Z
> Cc: dev@dpdk.org
> Subject: Re: [PATCH v3 0/2] clean up interrupt handle
>
> Hi,
>
> 2017-03-30 22:09, Qi Zhang:
> > It seems its not necessary to
2017-03-15 12:23, Ananyev, Konstantin:
>
> > -Original Message-
> > From: Dai, Wei
> > Sent: Tuesday, March 14, 2017 2:48 PM
> > To: dev@dpdk.org
> > Cc: Ananyev, Konstantin ; Dai, Wei
> > ; sta...@dpdk.org
> > Subject: [PATCH v2] examples/ip_fragmentation: fix check of packet type
> >
>
2017-02-10 09:02, Liu, Yong:
> From: Thomas Monjalon [mailto:thomas.monja...@6wind.com]
> > 2017-02-10 07:53, Liu, Yong:
> > > From: Thomas Monjalon
> > > > 2017-02-09 22:25, Marvin Liu:
> > > > > Add new option parse-ptype in this sample in case of pmd driver
> > > > > not provide packet type info
Coverity issue: 1423925
Fixes: e18dbbd3083a ("net/sfc: remove EvQ info array to simplify reconfigure")
Signed-off-by: Andrew Rybchenko
Reviewed-by: Andy Moreton
---
It may be squashed into e18dbbd3083a.
drivers/net/sfc/sfc_ev.c | 7 ---
1 file changed, 4 insertions(+), 3 deletions(-)
diff
Hi Nirmoy,
On 04/04/2017 01:32 PM, Nirmoy Das wrote:
> fixes:
> error: In the GNU C Library, "makedev" is defined
> by . For historical compatibility, it is
> currently defined by as well, but we plan to
> remove this soon. To use "makedev", include
> directly. If you did not intend to use a sys
On 04/04/2017 01:50 PM, Markos Chandras wrote:
> Hi Nirmoy,
>
> On 04/04/2017 01:32 PM, Nirmoy Das wrote:
>> fixes:
>> error: In the GNU C Library, "makedev" is defined
>> by . For historical compatibility, it is
>> currently defined by as well, but we plan to
>> remove this soon. To use "makedev
2017-04-03 14:05, Jerin Jacob:
> glibc 2.25 is warning about if applications depend on
> sys/types.h for makedev macro, it expects to be included
> from
>
> Found this error while testing with GCC 6.3.1 on archlinux.
>
> lib/librte_eal/linuxapp/eal/eal_pci_uio.c: In function ‘pci_mknod_uio_dev’:
Hi Ferruh,
> -Original Message-
> From: Yigit, Ferruh
> Sent: Tuesday, April 4, 2017 1:40 PM
> To: Iremonger, Bernard ; dev@dpdk.org;
> Xing, Beilei
> Cc: Lu, Wenzhuo
> Subject: Re: [dpdk-dev] [PATCH] net/i40e: fix eth pattern parsing
>
> On 4/3/2017 5:14 PM, Bernard Iremonger wrote:
>
2017-04-04 14:36, Nirmoy Das:
> fix below warning:
> error: In the GNU C Library, "makedev" is defined
> by . For historical compatibility, it is
> currently defined by as well, but we plan to
> remove this soon. To use "makedev", include
> directly. If you did not intend to use a system-defined
2017-04-04 03:42, David Hunt:
> Coverity issue 143258: not freeing distributor instance
> Coverity issue 143254: not checking return code from malloc
>
> Fixes: 775003ad2f96 ("distributor: add new burst-capable library")
>
> Signed-off-by: David Hunt
Applied with this title:
distributor
On 3/30/2017 9:42 PM, Thomas Monjalon wrote:
> For info, Ferruh did a similar patch:
> http://dpdk.org/patch/22443
> Ferruh, OK to keep Bruce one?
Sure, go for it, they both do same thing.
>
> 2017-03-30 16:33, Bruce Richardson:
>> On Thu, Mar 30, 2017 at 04:36:11PM +0200, Thomas Monjalon
2017-03-29 09:58, Mcnamara, John:
> From: Yong Wang [mailto:wang.yon...@zte.com.cn]
> Sent: Wednesday, March 29, 2017 9:28 AM
> >
> > Signed-off-by: Yong Wang
>
>
> Good catch. Thanks.
>
>
> Acked-by: John McNamara
Applied, thanks
On 4/4/2017 1:49 PM, Andrew Rybchenko wrote:
> Coverity issue: 1423925
> Fixes: e18dbbd3083a ("net/sfc: remove EvQ info array to simplify reconfigure")
>
> Signed-off-by: Andrew Rybchenko
> Reviewed-by: Andy Moreton
> ---
> It may be squashed into e18dbbd3083a.
Squashed into relevant commit in
On 4/4/2017 1:13 PM, Andrew Rybchenko wrote:
> From: Andy Moreton
>
> Coverity issue: 1387551
> Fixes: e7cd430c864f ("net/sfc/base: import SFN7xxx family support")
> Cc: sta...@dpdk.org
>
> Signed-off-by: Andy Moreton
> Signed-off-by: Andrew Rybchenko
Series applied to dpdk-next-net/master, t
Add support for SLES12SP3, which uses kernel 4.4,
but backported features from newer kernels.
Signed-off-by: Nirmoy Das
---
lib/librte_eal/linuxapp/kni/ethtool/igb/kcompat.h | 9 +++--
1 file changed, 7 insertions(+), 2 deletions(-)
diff --git a/lib/librte_eal/linuxapp/kni/ethtool/igb/kcomp
2017-03-31 14:31, Aaron Conole:
> It's likely that this function isn't used anywhere, but since it was part of
> the public API, mark the function for deprecation for at least one release.
>
> Signed-off-by: Aaron Conole
[...]
> --- a/lib/librte_eal/common/arch/x86/rte_spinlock.c
> +++ b/lib/libr
It seems its not necessary to register an intr_handle for interrupt callback
function. "void* cb_arg" shows enough when be used to pass the object that
contain the information be required to handle the interrupt event( A typical
way which is implemented by almost all driver is by passing a rte_ethd
Remove the inappropriate modification on get_max_intr
field that keep the intr_source read only.
Signed-off-by: Qi Zhang
---
v4:
- Add back this patch to make patch set complete though it already be applied.
v2:
- Seperate patch 1 of v1 into 2 patches.(part 1)
lib/librte_eal/linuxapp/eal/eal
The patch change the prototype of callback function
(rte_intr_callback_fn) by removing the unnecessary parameter.
Signed-off-by: Qi Zhang
---
v4:
- Update mlx5 driver which is missed in v1, v2, v3.
v3:
- Update bnx2x driver which is missed in v1,v2
v2:
- Seperate patch 1 of v1 into 2 patche
On 03/04/17 16:33, Fan Zhang wrote:
This patch adds initial mode and ordering enable/disable EAL
options to cryptodev scheduler PMD.
Signed-off-by: Fan Zhang
---
...
Acked-by: Declan Doherty
Hi Thomas,
Thomas Monjalon writes:
> 2017-03-31 14:31, Aaron Conole:
>> It's likely that this function isn't used anywhere, but since it was part of
>> the public API, mark the function for deprecation for at least one release.
>>
>> Signed-off-by: Aaron Conole
Thanks so much for the review!
On 4/4/2017 2:19 PM, Nirmoy Das wrote:
> Add support for SLES12SP3, which uses kernel 4.4,
> but backported features from newer kernels.
>
> Signed-off-by: Nirmoy Das
> ---
> lib/librte_eal/linuxapp/kni/ethtool/igb/kcompat.h | 9 +++--
> 1 file changed, 7 insertions(+), 2 deletions(-)
>
> d
Wednesday, April 5, 2017 12:21 AM, Qi Zhang:
> The patch change the prototype of callback function
> (rte_intr_callback_fn) by removing the unnecessary parameter.
>
> Signed-off-by: Qi Zhang
> ---
>
> v4:
>
> - Update mlx5 driver which is missed in v1, v2, v3.
Thanks for the update of mlx5.
Th
2017-04-04 09:39, Aaron Conole:
> Hi Thomas,
>
> Thomas Monjalon writes:
>
> > 2017-03-31 14:31, Aaron Conole:
> >> It's likely that this function isn't used anywhere, but since it was part
> >> of
> >> the public API, mark the function for deprecation for at least one release.
> >>
> >> Signe
Add support for SLES12SP3, which uses kernel 4.4,
but backported features from newer kernels.
Signed-off-by: Nirmoy Das
---
lib/librte_eal/linuxapp/kni/ethtool/igb/kcompat.h | 8 ++--
1 file changed, 6 insertions(+), 2 deletions(-)
diff --git a/lib/librte_eal/linuxapp/kni/ethtool/igb/kcompa
The following changes since commit a29491c2f417c58cf02ace231d7a0215315e1346:
doc: fix a typo in howto guide (2017-04-04 15:07:25 +0200)
are available in the git repository at:
http://dpdk.org/git/next/dpdk-next-net
for you to fetch changes up to 33383c6ffcd4bdf3ba2fb4fb82f163e7771a4cad:
2017-03-31 09:51, Allain Legacy:
> This patchset includes some minor enhancements that we have developped for
> our DPDK application. We would like to contribute them upstream to help
> ease adoption of the DPDK by anyone looking for this type of
> functionality. The commit logs on each patch sho
> -Original Message-
> From: Shahaf Shuler [mailto:shah...@mellanox.com]
> Sent: Tuesday, April 4, 2017 9:54 PM
> To: Zhang, Qi Z ; thomas.monja...@6wind.com
> Cc: dev@dpdk.org
> Subject: RE: [dpdk-dev] [PATCH v4 2/2] eal: clean up interrupt handle
>
> Wednesday, April 5, 2017 12:21 AM,
Remove the inappropriate modification on get_max_intr
field that keep the intr_source read only.
Signed-off-by: Qi Zhang
---
v4:
- Add back this patch to make patch set complete though it already be applied.
v2:
- Seperate patch 1 of v1 into 2 patches.(part 1)
lib/librte_eal/linuxapp/eal/ea
It seems its not necessary to register an intr_handle for interrupt callback
function. "void* cb_arg" shows enough when be used to pass the object that
contain the information be required to handle the interrupt event( A typical
way which is implemented by almost all driver is by passing a rte_ethd
The patch change the prototype of callback function
(rte_intr_callback_fn) by removing the unnecessary parameter.
Signed-off-by: Qi Zhang
---
v5:
- Update mlx4 driver which is missed in previous version.
v4:
- Update mlx5 driver which is missed in v1, v2, v3.
v3:
- Update bnx2x driver which
> On Apr 4, 2017, at 12:01 AM, Vincent Jardin wrote:
>
>
>
> Le 4 avril 2017 4:28:47 AM Stephen Hemminger a
> écrit :
>
>> On Mon, 3 Apr 2017 22:53:06 +
>> "Wiles, Keith" wrote:
>>
>>> > On Apr 3, 2017, at 2:51 PM, Stephen Hemminger
>>> > wrote:
>>> >
>>> > On Thu, 30 Mar 2017 18:09
On 4/4/2017 3:16 PM, Nirmoy Das wrote:
> Add support for SLES12SP3, which uses kernel 4.4,
> but backported features from newer kernels.
>
> Signed-off-by: Nirmoy Das
Acked-by: Ferruh Yigit
2017-04-05 06:27, Qi Zhang:
> It seems its not necessary to register an intr_handle for interrupt callback
> function. "void* cb_arg" shows enough when be used to pass the object that
> contain the information be required to handle the interrupt event( A typical
> way which is implemented by almost
> -Original Message-
> From: Thomas Monjalon [mailto:thomas.monja...@6wind.com]
> Sent: Tuesday, April 4, 2017 10:50 PM
> To: Zhang, Qi Z
> Cc: dev@dpdk.org
> Subject: Re: [PATCH v5 0/2] clean up interrupt handle
>
> 2017-04-05 06:27, Qi Zhang:
> > It seems its not necessary to register
If probe of the whitelisted PCI device fails, reset ret to zero
to silently skip non-whitelisted PCI devices.
Fixes: 10f6c93cea38 ("eal: do not panic on PCI failures")
Signed-off-by: Andrew Rybchenko
---
lib/librte_eal/common/eal_common_pci.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/
2017-04-03 14:09, Jacek Piasecki:
> From: Michal Jastrzebski
>
> Extended xstats API in ethdev library to allow grouping of stats
> logically so they can be retrieved per logical grouping – managed
> by the application.
> Changed existing functions rte_eth_xstats_get_names and
> rte_eth_xstats_ge
Hi Akhil,
> -Original Message-
> From: akhil.go...@nxp.com [mailto:akhil.go...@nxp.com]
> Sent: Monday, April 03, 2017 11:53 AM
> To: dev@dpdk.org
> Cc: Doherty, Declan; De Lara Guarch, Pablo; Akhil Goyal
> Subject: [PATCH] test/test: improve dequeue logic for crypto operation
>
> From: A
2017-04-04 15:46, Ferruh Yigit:
> On 4/4/2017 3:16 PM, Nirmoy Das wrote:
> > Add support for SLES12SP3, which uses kernel 4.4,
> > but backported features from newer kernels.
> >
> > Signed-off-by: Nirmoy Das
>
> Acked-by: Ferruh Yigit
Applied, thanks
It seems its not necessary to register an intr_handle for interrupt callback
function. "void* cb_arg" shows enough when be used to pass the object that
contain the information be required to handle the interrupt event( A typical
way which is implemented by almost all driver is by passing a rte_ethd
Remove the inappropriate modification on get_max_intr
field that keep the intr_source read only.
Signed-off-by: Qi Zhang
---
v4:
- Add back this patch to make patch set complete though it already be applied.
v2:
- Seperate patch 1 of v1 into 2 patches.(part 1)
lib/librte_eal/linuxapp/eal/ea
Update the test code to algin with interrupt callback prototype change
Signed-off-by: Qi Zhang
---
v6:
- sync with latest test code.
test/test/test_interrupts.c | 23 ---
1 file changed, 12 insertions(+), 11 deletions(-)
diff --git a/test/test/test_interrupts.c b/test/tes
The patch change the prototype of callback function
(rte_intr_callback_fn) by removing the unnecessary parameter.
Signed-off-by: Qi Zhang
---
v5:
- Update mlx4 driver which is missed in previous version.
v4:
- Update mlx5 driver which is missed in v1, v2, v3.
v3:
- Update bnx2x driver which
> -Original Message-
> From: Zhang, Roy Fan
> Sent: Tuesday, April 04, 2017 10:31 AM
> To: dev@dpdk.org
> Cc: De Lara Guarch, Pablo; sta...@dpdk.org
> Subject: [PATCH v3] crypto/scheduler: fix session free
>
> This patch fixes the incorrection slave session free operation.
>
> Fixes: 57
> -Original Message-
> From: Doherty, Declan
> Sent: Tuesday, April 04, 2017 2:38 PM
> To: Zhang, Roy Fan; dev@dpdk.org
> Cc: De Lara Guarch, Pablo; Gonzalez Monroy, Sergio
> Subject: Re: [PATCH v4] crypto/scheduler: add more EAL options
>
> On 03/04/17 16:33, Fan Zhang wrote:
> > This p
Hi Hemant,
[Noticed that my first reply couldn't reach out to ML so re-sending]
On Tuesday 04 April 2017 11:27 AM, Hemant Agrawal wrote:
> From: Shreyansh Jain
>
> mempool autotest was not freeing the mempools.
>
> Fixes: 8ef772ae ("app/test: rework mempool tes")
> Cc: sta...@dpdk.org
>
> Signe
On 04/03/2017 07:11 PM, Burakov, Anatoly wrote:
From: Andrew Rybchenko [mailto:arybche...@solarflare.com]
Sent: Saturday, April 1, 2017 11:47 AM
To: dev@dpdk.org; Alejandro Lucero
Cc: Burakov, Anatoly
Subject: vfio: failed to select IOMMU type
Hi,
after the following commit (it was picked up
This function is now part of the public ABI, so should be
advertised as such.
Signed-off-by: Aaron Conole
---
lib/librte_eal/bsdapp/eal/rte_eal_version.map | 7 +++
lib/librte_eal/linuxapp/eal/rte_eal_version.map | 7 +++
2 files changed, 14 insertions(+)
diff --git a/lib/librte_eal/b
It's likely that this function isn't used anywhere, but since it was part
of the public API, mark the function for deprecation for at least one
release.
Signed-off-by: Aaron Conole
---
lib/librte_eal/common/include/generic/rte_cpuflags.h | 2 ++
1 file changed, 2 insertions(+)
diff --git a/lib/
This patch fixes a naming typo in set and get mode APIs.
Fixes: 097ab0bac017 ("crypto/scheduler: add API")
Signed-off-by: Fan Zhang
---
drivers/crypto/scheduler/rte_cryptodev_scheduler.c | 4 ++--
drivers/crypto/scheduler/rte_cryptodev_scheduler.h | 4 ++--
test/test/test_cryptodev.c
> From: Thomas Monjalon [mailto:thomas.monja...@6wind.com]
> Sent: Tuesday, April 4, 2017 4:04 PM
> To: Piasecki, JacekX ; Jastrzebski, MichalX K
>
> Cc: dev@dpdk.org; Van Haaren, Harry ; Kozak, KubaX
> ; Kulasek, TomaszX
> Subject: Re: [dpdk-dev] [PATCH v3 1/3] add new xstats API retrieving by i
> -Original Message-
> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Ferruh Yigit
> Sent: Tuesday, April 4, 2017 3:22 PM
> To: Thomas Monjalon
> Cc: dev@dpdk.org; Yigit, Ferruh
> Subject: [dpdk-dev] [pull-request] next-net 17.05 RC1
>
> The following changes since commit
> a29491c
Hi Andrew,
> I think a key to the main problem is the same IOMMU group used for both PCI
> functions.
> It tries to set IOMMU type using the same file descriptor twice. The second
> set is dummy, since the same value is set, but still fails, I guess, because
> it is already in use.
> See logs w
If more than one used PCI device belongs to one IOMMU group,
it is still one IOMMU group and the container IOMMU type
should be set only once.
Fixes: 94c0776b1bad ("vfio: support hotplug")
Signed-off-by: Andrew Rybchenko
---
My testing of the patch is limitted to my configuration with 2 PCI
func
On 04/04/2017 06:52 PM, Burakov, Anatoly wrote:
Hi Andrew,
I think a key to the main problem is the same IOMMU group used for both PCI
functions.
It tries to set IOMMU type using the same file descriptor twice. The second set
is dummy, since the same value is set, but still fails, I guess, be
2017-04-04 15:45, Van Haaren, Harry:
> From: Thomas Monjalon [mailto:thomas.monja...@6wind.com]
> > 2017-04-03 14:09, Jacek Piasecki:
> > > From: Michal Jastrzebski
> > >
> > > Extended xstats API in ethdev library to allow grouping of stats
> > > logically so they can be retrieved per logical gro
Hi Andrew,
> Please, take a look at http://dpdk.org/dev/patchwork/patch/23202/
I took a quick look. It should fix the problem (closing the group will cause
container detachment, so we can always assume that if there's no container
associated with the group, there are no devices within that grou
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 a 64bits timestamp field in the 1st cache line. This timestamp
is not normalized, i.e. no unit or ti
Document the function and make it public, since it is used at several
places in the drivers. The old one is marked as deprecated.
Signed-off-by: Olivier Matz
---
drivers/net/enic/enic_rxtx.c | 2 +-
drivers/net/fm10k/fm10k_rxtx.c| 6 +++---
drivers/net/fm10k/fm10k_rxtx
1 - 100 of 150 matches
Mail list logo
