Ferruh Yigit wrote :
> Is this a common enough feature to include into ethdev abstraction layer? Or a
> feature for a single vendor?
I found reference to mbuf’s timestamp field only in MLX5. I think it is the
only one to support timestamp offloading. This new API is only useful to make
sense out
On Thu, Dec 20, 2018 at 11:01 AM Hari Kumar Vemula <
hari.kumarx.vem...@intel.com> wrote:
> When incorrect core value or range provided,
> as part of -l command line option, a crash occurs.
>
> Added valid range checks to fix the crash.
>
> Fixes: d888cb8b9613 ("eal: add core list input format")
>
On 12/21/18 7:27 AM, Gavin Hu (Arm Technology China) wrote:
-Original Message-
From: dev On Behalf Of Maxime Coquelin
Sent: Friday, December 21, 2018 1:27 AM
To: dev@dpdk.org; jfreim...@redhat.com; tiwei@intel.com;
zhihong.w...@intel.com
Cc: Maxime Coquelin
Subject: [dpdk-dev]
> -Original Message-
> From: Maxime Coquelin
> Sent: Friday, December 21, 2018 4:36 PM
> To: Gavin Hu (Arm Technology China) ;
> dev@dpdk.org; jfreim...@redhat.com; tiwei@intel.com;
> zhihong.w...@intel.com
> Cc: nd
> Subject: Re: [dpdk-dev] [PATCH v3 3/3] net/virtio: improve batchi
This patch fixes correct status in case of overflow on
QAT is detected.
In that case RTE_COMP_OP_STATUS_OUT_OF_SPACE_TERMINATED value is set in
rte_comp_op.status field instead of RTE_COMP_OP_STATUS_ERROR
Fixes: 32842f2a6d7d ("compress/qat: create FW request and process response")
Cc: sta...@dpdk.
This patch enables compression on dh895x HW series
and updates supported hardware accelerator devices list.
Signed-off-by: Tomasz Jozwiak
---
doc/guides/compressdevs/qat_comp.rst | 1 +
drivers/compress/qat/qat_comp.c | 2 +-
drivers/compress/qat/qat_comp_pmd.c | 4
3 files changed, 2
On 20-Dec-18 5:18 PM, Thomas Monjalon wrote:
20/12/2018 17:16, Stephen Hemminger:
On Thu, 20 Dec 2018 15:32:37 +
Anatoly Burakov wrote:
Currently, the only way to use externally allocated memory
is through rte_malloc API's. While this is fine for a lot
of use cases, it may not be suitable
On 21-Dec-18 8:27 AM, David Marchand wrote:
On Thu, Dec 20, 2018 at 11:01 AM Hari Kumar Vemula <
hari.kumarx.vem...@intel.com> wrote:
When incorrect core value or range provided,
as part of -l command line option, a crash occurs.
Added valid range checks to fix the crash.
Fixes: d888cb8b9613
On 12/20/18 6:27 PM, Maxime Coquelin wrote:
First version of this series did merge out-of-order mergeable
and non-mergeable receive paths, but Intel STV team highlighted
some performance regression when using multiqueue with two cores
enqueueing descs on host, while a single core dequeues the
On 12/20/18 5:47 PM, Maxime Coquelin wrote:
Instead of writing back descriptors chains in order, let's
write the first chain flags last in order to improve batching.
Also, move the write barrier in logging cache sync, so that it
is done only when logging is enabled. It means there is now
one
On Fri, Dec 21, 2018 at 10:19 AM Burakov, Anatoly
wrote:
> On 21-Dec-18 8:27 AM, David Marchand wrote:
> > Since you have identified a potential crash, can you give an example of
> > such a crash ?
> > Besides, we have tests that check arguments, so an update of the test
> would
> > be nice.
>
>
Hi all,
Here is a list of patches targeted for stable release 18.08.1. Please
help review and test. The planned date for the final release is 16th
January. Before that, please shout if anyone has objections with these
patches being applied.
Also for the companies committed to running regression
We will be adding a new extmem test that will behave roughly similar
to already existing, so clarify function names to distinguish between
these tests, as well as factor out the common parts.
Signed-off-by: Anatoly Burakov
---
test/test/test_external_mem.c | 62 +-
Currently, only scenario with valid IOVA table is tested. Fix this
by also testing without IOVA table - in these cases, EAL should
always return RTE_BAD_IOVA for all memsegs.
Signed-off-by: Anatoly Burakov
---
test/test/test_external_mem.c | 68 +++
1 file changed
Extend the extmem autotest to check whether the memseg lists for
externally allocated memory are always marked as external.
Signed-off-by: Anatoly Burakov
---
test/test/test_external_mem.c | 11 ++-
1 file changed, 10 insertions(+), 1 deletion(-)
diff --git a/test/test/test_external_mem
Currently, extmem autotest only covers the external malloc heap
API. Extend it to also cover the non-heap, register/unregister
external memory API.
Signed-off-by: Anatoly Burakov
---
test/test/test_external_mem.c | 146 ++
1 file changed, 146 insertions(+)
diff -
Currently, only scenario with valid IOVA table is tested. Fix this
by also testing without IOVA table - in these cases, EAL should
always return RTE_BAD_IOVA for all memsegs, and contiguous memzone
allocation should fail.
Signed-off-by: Anatoly Burakov
---
Notes:
v2:
- Improve condition
We will be adding a new extmem test that will behave roughly similar
to already existing, so clarify function names to distinguish between
these tests, as well as factor out the common parts.
Signed-off-by: Anatoly Burakov
---
test/test/test_external_mem.c | 62 +-
Currently, extmem autotest only covers the external malloc heap
API. Extend it to also cover the non-heap, register/unregister
external memory API.
Signed-off-by: Anatoly Burakov
---
test/test/test_external_mem.c | 146 ++
1 file changed, 146 insertions(+)
diff -
Extend the extmem autotest to check whether the memseg lists for
externally allocated memory are always marked as external.
Signed-off-by: Anatoly Burakov
---
test/test/test_external_mem.c | 11 ++-
1 file changed, 10 insertions(+), 1 deletion(-)
diff --git a/test/test/test_external_mem
> -Original Message-
> From: Trahe, Fiona
> Sent: Friday, December 21, 2018 12:01 AM
> To: dev@dpdk.org
> Cc: De Lara Guarch, Pablo ; Trahe, Fiona
> ; Zhang, Roy Fan ;
> akhil.go...@nxp.com; sta...@dpdk.org
> Subject: [PATCH] test/crypto: fix misleading trace message
>
> Test was report
> -Original Message-
> From: Trahe, Fiona
> Sent: Friday, December 21, 2018 12:02 AM
> To: dev@dpdk.org
> Cc: De Lara Guarch, Pablo ; Trahe, Fiona
> ; Zhang, Roy Fan ;
> akhil.go...@nxp.com
> Subject: [PATCH] test/crypto: don't attempt unsupported SGL tests on aesni
> mb PMD
>
> Remove
On 12/20/2018 7:36 PM, Ananyev, Konstantin wrote:
>
>>> diff --git a/lib/librte_ipsec/sa.c b/lib/librte_ipsec/sa.c
>>> new file mode 100644
>>> index 0..f927a82bf
>>> --- /dev/null
>>> +++ b/lib/librte_ipsec/sa.c
>>> @@ -0,0 +1,327 @@
>>> +/* SPDX-License-Identifier: BSD-3-Clause
>>> + *
On 12/20/2018 11:47 PM, Ananyev, Konstantin wrote:
+
+static int
+fill_crypto_xform(struct crypto_xform *xform,
+ const struct rte_ipsec_sa_prm *prm)
+{
+ struct rte_crypto_sym_xform *xf;
+
+ memset(xform, 0, sizeof(*xform));
+
+ for (xf = prm
04/12/2018 13:22, Anatoly Burakov:
> Currently, malloc statistics and external heap creation code
> use memory hotplug lock as a way to synchronize accesses to
> heaps (as in, locking the hotplug lock to prevent list of heaps
> from changing under our feet). At the same time, malloc
> statistics co
On 10/12/2018 12:36 PM, Andrew Rybchenko wrote:
> From: Ivan Malov
>
> This capability is reported when supported by the current emitting
> sub-device. Failsafe PMD itself does not excercise fast free logic.
I think overlay device capability reporting already discussed a few times, the
question
On 21-Dec-18 12:09 PM, Thomas Monjalon wrote:
04/12/2018 13:22, Anatoly Burakov:
Currently, malloc statistics and external heap creation code
use memory hotplug lock as a way to synchronize accesses to
heaps (as in, locking the hotplug lock to prevent list of heaps
from changing under our feet).
On 12/20/2018 3:47 PM, Ananyev, Konstantin wrote:
>
>>> + * @param ss
>>> + * Pointer to the *rte_ipsec_session* object
>>> + * @return
>>> + * - Zero if operation completed successfully.
>>> + * - -EINVAL if the parameters are invalid.
>>> + */
>>> +int __rte_experimental
>>> +rte_ipsec_se
Software indexes are PMD internal and should not be passed outside.
Right now SW and HW indexes of the Tx queue match, so it is just
a cosmetic fix.
Fixes: dbdc82416b72 ("net/sfc: factor out libefx-based Tx datapath")
Cc: sta...@dpdk.org
Signed-off-by: Andrew Rybchenko
---
drivers/net/sfc/sfc_t
DCR is Intel internal information, no need to be in public code.
See also a parallel patch by Ferruh, commit
1a0833efde70 ("net/i40e/base: fix comment referencing internal data").
Fixes: e5b2a9e957e7 ("net/avf/base: add base code for avf PMD")
Cc: sta...@dpdk.org
Signed-off-by: Rami Rosen
---
On 12/17/2018 9:21 AM, Lam, Tiago wrote:
> Hi Ferruh,
>
> On 28/11/2018 13:33, Ferruh Yigit wrote:
>> On 11/28/2018 1:12 PM, Lam, Tiago wrote:
>>> On 27/11/2018 17:43, Ferruh Yigit wrote:
On 11/20/2018 10:26 AM, Tiago Lam wrote:
> Use the underlying MTU to calculate the framsize to be use
Currently, malloc statistics and external heap creation code
use memory hotplug lock as a way to synchronize accesses to
heaps (as in, locking the hotplug lock to prevent list of heaps
from changing under our feet). At the same time, malloc
statistics code will also lock the heap because it needs t
On 12/21/18 3:12 PM, Ferruh Yigit wrote:
On 10/12/2018 12:36 PM, Andrew Rybchenko wrote:
From: Ivan Malov
This capability is reported when supported by the current emitting
sub-device. Failsafe PMD itself does not excercise fast free logic.
I think overlay device capability reporting already
On 11/20/2018 10:26 AM, Tiago Lam wrote:
> When setting the MTU, eth_dev_mtu_set() is called to validate the
> provided MTU. As part of that, it calculates the useful area to store
> data and compares it against the MTU, to guarantee that there's enough
> space to store the data. It calculates that
On 11/5/2018 3:31 PM, Ferruh Yigit wrote:
> Fixes: 7c25284e30c2 ("net/tap: add netlink back-end for flow API")
> Cc: sta...@dpdk.org
>
> Signed-off-by: Ferruh Yigit
Applied to dpdk-next-net/master, thanks.
(I guess it was trivial enough to not get any response, merged as it is)
On 12/20/2018 6:26 PM, Ananyev, Konstantin wrote:
>
>>> diff --git a/lib/librte_ipsec/crypto.h b/lib/librte_ipsec/crypto.h
>>> new file mode 100644
>>> index 0..61f5c1433
>>> --- /dev/null
>>> +++ b/lib/librte_ipsec/crypto.h
>>> @@ -0,0 +1,123 @@
>>> +/* SPDX-License-Identifier: BSD-3-Cla
On 12/20/2018 6:30 PM, Ananyev, Konstantin wrote:
>
>>> +
>>> +/**
>>> + * Take crypto-op as an input and extract pointer to related ipsec session.
>>> + * @param cop
>>> + * The address of an input *rte_crypto_op* structure.
>>> + * @return
>>> + * The pointer to the related *rte_ipsec_sessi
On 12/20/2018 6:33 PM, Ananyev, Konstantin wrote:
>
>>
>> On 12/14/2018 9:53 PM, Konstantin Ananyev wrote:
>>> +static struct unit_test_suite ipsec_testsuite = {
>>> + .suite_name = "IPsec NULL Unit Test Suite",
>>> + .setup = testsuite_setup,
>>> + .teardown = testsuite_teardown,
>>> +
> -Original Message-
> From: Akhil Goyal [mailto:akhil.go...@nxp.com]
> Sent: Friday, December 21, 2018 11:53 AM
> To: Ananyev, Konstantin ; dev@dpdk.org
> Cc: Thomas Monjalon ; Awal, Mohammad Abdul
>
> Subject: Re: [dpdk-dev] [PATCH v4 04/10] lib: introduce ipsec library
>
>
>
> On
On 12/21/2018 12:28 PM, Andrew Rybchenko wrote:
> On 12/21/18 3:12 PM, Ferruh Yigit wrote:
>> On 10/12/2018 12:36 PM, Andrew Rybchenko wrote:
>>> From: Ivan Malov
>>>
>>> This capability is reported when supported by the current emitting
>>> sub-device. Failsafe PMD itself does not excercise fast
Hi Ferruh,
On 12/21/18 3:43 PM, Ferruh Yigit wrote:
On 12/21/2018 12:28 PM, Andrew Rybchenko wrote:
On 12/21/18 3:12 PM, Ferruh Yigit wrote:
On 10/12/2018 12:36 PM, Andrew Rybchenko wrote:
From: Ivan Malov
This capability is reported when supported by the current emitting
sub-device. Failsa
> >
> >
> > On 12/20/2018 7:36 PM, Ananyev, Konstantin wrote:
> > >
> > >>> diff --git a/lib/librte_ipsec/sa.c b/lib/librte_ipsec/sa.c
> > >>> new file mode 100644
> > >>> index 0..f927a82bf
> > >>> --- /dev/null
> > >>> +++ b/lib/librte_ipsec/sa.c
> > >>> @@ -0,0 +1,327 @@
> > >>> +/* SPD
On 12/20/2018 6:36 PM, Ananyev, Konstantin wrote:
>
>>> --- /dev/null
>>> +++ b/doc/guides/prog_guide/ipsec_lib.rst
>>> @@ -0,0 +1,74 @@
>>> +.. SPDX-License-Identifier: BSD-3-Clause
>>> +Copyright(c) 2018 Intel Corporation.
>>> +
>>> +IPsec Packet Processing Library
>>> +===
Hi Ferruh, Andrew,
On Fri, Dec 21, 2018 at 03:52:07PM +0300, Andrew Rybchenko wrote:
> Hi Ferruh,
>
> On 12/21/18 3:43 PM, Ferruh Yigit wrote:
> > On 12/21/2018 12:28 PM, Andrew Rybchenko wrote:
> > > On 12/21/18 3:12 PM, Ferruh Yigit wrote:
> > > > On 10/12/2018 12:36 PM, Andrew Rybchenko wrote:
On 19/12/2018 11:59, Bruce Richardson wrote:
Different NIC ports can have different numbers of xstats on them, which
means that we can't just use the xstats list from the first port registered
in the telemetry library. Instead, we need to check the type of each port -
by checking its ops structur
On 12/21/2018 12:52 PM, Andrew Rybchenko wrote:
> Hi Ferruh,
>
> On 12/21/18 3:43 PM, Ferruh Yigit wrote:
>> On 12/21/2018 12:28 PM, Andrew Rybchenko wrote:
>>> On 12/21/18 3:12 PM, Ferruh Yigit wrote:
On 10/12/2018 12:36 PM, Andrew Rybchenko wrote:
> From: Ivan Malov
>
> This ca
Hi Konstantin,
I am done with the review, will be running the code in early next week
after I finish the review of changes in ipsec application.
key points for review were
- some code may be generic and can be moved in appropriate files
- documentation update
- spell checks spacing etc.
-
21/12/2018 13:26, Anatoly Burakov:
> Currently, malloc statistics and external heap creation code
> use memory hotplug lock as a way to synchronize accesses to
> heaps (as in, locking the hotplug lock to prevent list of heaps
> from changing under our feet). At the same time, malloc
> statistics co
This patchset changes the queue pair configure structure and sym session
structure for cryptodev. An RFC patch http://patchwork.dpdk.org/patch/43883/
has been sent to state the change.
v3:
- Rebased.
- Fixed a few bugs.
v2:
- Removed incorrect config/common_base change
- Added new API for existin
This patch changes the cryptodev queue pair configure structure
to enable two mempool passed into cryptodev PMD simutaneously.
Signed-off-by: Fan Zhang
Acked-by: Fiona Trahe
---
app/test-crypto-perf/main.c| 6 ++--
doc/guides/rel_notes/release_19_02.rst | 5
This patch changes the symmetric session structure of cryptodev.
The symmetric session now contains extra information for secure
access purposes. The patch also includes the updates to the
PMDs, test applications, and examples to fit the change.
Signed-off-by: Fan Zhang
---
app/test-crypto-perf/
Hi Konstantin,
On 12/14/2018 10:10 PM, Konstantin Ananyev wrote:
> ipsec-secgw always enables TX offloads
> (DEV_TX_OFFLOAD_MULTI_SEGS, DEV_TX_OFFLOAD_SECURITY),
> even when they are not requested by the config.
> That causes many PMD to choose full-featured TX function,
> which in many cases is m
On 12/21/2018 1:16 PM, Gaëtan Rivet wrote:
> Hi Ferruh, Andrew,
>
> On Fri, Dec 21, 2018 at 03:52:07PM +0300, Andrew Rybchenko wrote:
>> Hi Ferruh,
>>
>> On 12/21/18 3:43 PM, Ferruh Yigit wrote:
>>> On 12/21/2018 12:28 PM, Andrew Rybchenko wrote:
On 12/21/18 3:12 PM, Ferruh Yigit wrote:
>
Hi,
On 12/14/2018 10:10 PM, Konstantin Ananyev wrote:
> In some cases it is useful to allow user to specify destination
> ether address for outgoing packets.
> This patch adds such ability by introducing new 'neigh' config
> file option.
I do not see an example config file option about how to use
On 12/21/2018 12:16 PM, Rami Rosen wrote:
> DCR is Intel internal information, no need to be in public code.
> See also a parallel patch by Ferruh, commit
> 1a0833efde70 ("net/i40e/base: fix comment referencing internal data").
>
> Fixes: e5b2a9e957e7 ("net/avf/base: add base code for avf PMD")
>
This patch fixes the memory leak during queue pair release.
Originally the operation ring is not freed when releasing
queue pair, cause the next queue_pair configure call fail
and memory leak.
Fixes: eec136f3c54f ("aesni_gcm: add driver for AES-GCM crypto operations")
Fixes: cf7685d68f00 ("crypto/
On 12/14/2018 10:10 PM, Konstantin Ananyev wrote:
> In some cases crypto-ops could never be dequeued from the crypto-device.
> The easiest way to reproduce:
> start ipsec-secgw with crypto-dev and send to it less then 32 packets.
> none packets will be forwarded.
> Reason for that is that the app
On 12/21/2018 1:01 PM, Qiming Yang wrote:
> I40e do not allow to get rss hena only, need to get rss
> key meanwhile.
i40e_get_rss_key() returns error if 'rss_conf.rss_key' is NULL, this patch is
fixing the error case.
But instead of fixing this in application level, it can be better to fix in
dri
On 12/14/2018 10:10 PM, Konstantin Ananyev wrote:
> Looking at process_pkts_outbound_nosp() there seems few issues:
> - accessing mbuf after it was freed
> - invoking ipsec_outbound() for ipv4 packets only
> - copying number of packets, but not the mbuf pointers itself
>
> that patch provides fix
> >>> + */
> >>> +
> >>> +/*
> >>> + * Move preceding (L3) headers down to remove ESP header and IV.
> >>> + */
> >> why cant we use rte_mbuf APIs to append/prepend/trim/adjust lengths.
> > We do use rte_mbuf append/trim, etc. adjust mbuf's data_ofs and data_len.
> > But apart from that for transp
On 12/21/2018 6:03 AM, David Zeng wrote:
> Signed-off-by: David Zeng
> ---
> kernel/linux/kni/compat.h | 8 +++-
> 1 file changed, 7 insertions(+), 1 deletion(-)
>
> diff --git a/kernel/linux/kni/compat.h b/kernel/linux/kni/compat.h
> index 5aadebb..1afa3b8 100644
> --- a/kernel/linux/kni/co
> On Dec 20, 2018, at 5:48 PM, Stephen Hemminger
> wrote:
>
> On Thu, 20 Dec 2018 21:59:37 +
> Ferruh Yigit wrote:
>
>> On 10/24/2018 9:18 AM, olivier.matz at 6wind.com (Olivier Matz) wrote:
>>> This RFC targets 19.02.
>>>
>>> The rte_net headers conflict with the libc headers, because
21/12/2018 15:27, Ananyev, Konstantin:
>
> > >>> + */
> > >>> +
> > >>> +/*
> > >>> + * Move preceding (L3) headers down to remove ESP header and IV.
> > >>> + */
> > >> why cant we use rte_mbuf APIs to append/prepend/trim/adjust lengths.
> > > We do use rte_mbuf append/trim, etc. adjust mbuf's da
On Fri, Dec 21, 2018 at 01:59:20PM +, Ferruh Yigit wrote:
> On 12/21/2018 1:16 PM, Gaëtan Rivet wrote:
> > Hi Ferruh, Andrew,
> >
> > On Fri, Dec 21, 2018 at 03:52:07PM +0300, Andrew Rybchenko wrote:
> >> Hi Ferruh,
> >>
> >> On 12/21/18 3:43 PM, Ferruh Yigit wrote:
> >>> On 12/21/2018 12:28 P
> -Original Message-
> From: Akhil Goyal [mailto:akhil.go...@nxp.com]
> Sent: Friday, December 21, 2018 2:13 PM
> To: Ananyev, Konstantin ; dev@dpdk.org
> Cc: Nicolau, Radu
> Subject: Re: [dpdk-dev] [PATCH v4 3/9] examples/ipsec-secgw: fix crypto-op
> might never get dequeued
>
>
>
>
On 12/21/2018 7:57 PM, Ananyev, Konstantin wrote:
> + */
> +
> +/*
> + * Move preceding (L3) headers down to remove ESP header and IV.
> + */
why cant we use rte_mbuf APIs to append/prepend/trim/adjust lengths.
>>> We do use rte_mbuf append/trim, etc. adjust mbuf's data_o
> -Original Message-
> From: Akhil Goyal [mailto:akhil.go...@nxp.com]
> Sent: Friday, December 21, 2018 2:26 PM
> To: Ananyev, Konstantin ; dev@dpdk.org
> Cc: Nicolau, Radu
> Subject: Re: [dpdk-dev] [PATCH v4 4/9] examples/ipsec-secgw: fix outbound
> codepath for single SA
>
>
>
> On
On 12/21/2018 8:19 PM, Ananyev, Konstantin wrote:
>
>> -Original Message-
>> From: Akhil Goyal [mailto:akhil.go...@nxp.com]
>> Sent: Friday, December 21, 2018 2:13 PM
>> To: Ananyev, Konstantin ; dev@dpdk.org
>> Cc: Nicolau, Radu
>> Subject: Re: [dpdk-dev] [PATCH v4 3/9] examples/ipsec-s
> -Original Message-
> From: Akhil Goyal [mailto:akhil.go...@nxp.com]
> Sent: Friday, December 21, 2018 2:57 PM
> To: Ananyev, Konstantin ; dev@dpdk.org
> Cc: Nicolau, Radu
> Subject: Re: [dpdk-dev] [PATCH v4 3/9] examples/ipsec-secgw: fix crypto-op
> might never get dequeued
>
>
>
>
On 12/6/2018 2:38 AM, Wei Zhao wrote:
> There is need to add boundary for input number from commandline,
> If it beyond the defination, code will return error.
>
> Signed-off-by: Wei Zhao
Reviewed-by: Ferruh Yigit
Applied to dpdk-next-net/master, thanks.
On 12/21/2018 12:12 PM, Ferruh Yigit wrote:
> On 10/12/2018 12:36 PM, Andrew Rybchenko wrote:
>> From: Ivan Malov
>>
>> This capability is reported when supported by the current emitting
>> sub-device. Failsafe PMD itself does not excercise fast free logic.
>>
>> Signed-off-by: Ivan Malov
>> Sign
On 12/21/2018 2:38 PM, Wiles, Keith wrote:
>
>
>> On Dec 20, 2018, at 5:48 PM, Stephen Hemminger
>> wrote:
>>
>> On Thu, 20 Dec 2018 21:59:37 +
>> Ferruh Yigit wrote:
>>
>>> On 10/24/2018 9:18 AM, olivier.matz at 6wind.com (Olivier Matz) wrote:
This RFC targets 19.02.
The rt
On 12/14/2018 10:10 PM, Konstantin Ananyev wrote:
> Changes to make ipsec-secgw to utilize librte_ipsec library.
> That patch provides:
> - changes in the related data structures.
> - changes in the initialization code.
> - new command-line parameters to enable librte_ipsec codepath
> a
> -Original Message-
> From: Akhil Goyal [mailto:akhil.go...@nxp.com]
> Sent: Friday, December 21, 2018 2:51 PM
> To: Ananyev, Konstantin ; dev@dpdk.org
> Cc: Thomas Monjalon ; Awal, Mohammad Abdul
> ; olivier.m...@6wind.com
> Subject: Re: [dpdk-dev] [PATCH v4 06/10] ipsec: implement SA
28/03/2017 22:46, Anders Roxell:
> Build igb-uio and rte-kni kernel module using dkms.
>
> Signed-off-by: Anders Roxell
The pkg/dpdk.spec file has been removed from the repository.
This patch is now marked as "Not Applicable".
If you think it was useful, please shout.
On 12/21/2018 12:15 PM, Andrew Rybchenko wrote:
> Software indexes are PMD internal and should not be passed outside.
> Right now SW and HW indexes of the Tx queue match, so it is just
> a cosmetic fix.
>
> Fixes: dbdc82416b72 ("net/sfc: factor out libefx-based Tx datapath")
> Cc: sta...@dpdk.org
21/12/2018 12:29, Anatoly Burakov:
> Currently, extmem autotest only covers the external malloc heap
> API. Extend it to also cover the non-heap, register/unregister
> external memory API.
>
> Signed-off-by: Anatoly Burakov
Series applied, thanks
On 12/14/2018 10:10 PM, Konstantin Ananyev wrote:
> diff --git a/examples/ipsec-secgw/sa.c b/examples/ipsec-secgw/sa.c
> index 04eb8bce8..49da966a3 100644
> --- a/examples/ipsec-secgw/sa.c
> +++ b/examples/ipsec-secgw/sa.c
> @@ -1164,10 +1164,15 @@ int
> inbound_sa_check(struct sa_ctx *sa_ctx,
This adds support to virtio-user for control virtqueues
and reverts commit "5e4e7a752 net/virtio-user: fail if
cq used with packed vq".
I add a struct virtio_user_queue to have a place for wrap
counters and avail/used index (which is not needed for split
ring because it has those in shared memory)
On 9/4/2017 3:53 PM, sergio.gonzalez.monroy at intel.com (Sergio Gonzalez
Monroy) wrote:
> Hi,
>
> On 24/08/2016 23:17, amin.tootoonchian at intel.com (Tootoonchian, Amin)
> wrote:
>> Sergio, could you please review this patch?
>>
>> Thanks,
>> Amin
>
> The patch status should be updated to 'Not
21/12/2018 14:27, Laatz, Kevin:
> On 19/12/2018 11:59, Bruce Richardson wrote:
> > Different NIC ports can have different numbers of xstats on them, which
> > means that we can't just use the xstats list from the first port registered
> > in the telemetry library. Instead, we need to check the type
> -Original Message-
> From: Zhang, Roy Fan
> Sent: Friday, December 21, 2018 2:11 PM
> To: dev@dpdk.org
> Cc: akhil.go...@nxp.com; De Lara Guarch, Pablo
> ; Trahe, Fiona ;
> sta...@dpdk.org
> Subject: [PATCH] cryptodev: fix PMD memory leak
>
> This patch fixes the memory leak during qu
On 10/5/2016 6:47 PM, jt at labs.hpe.com (Jean Tourrilhes) wrote:
> If the primary and secondary process were build using different build
> systems, the list of constructors included by the linker in each
> binary might be different. Tailqs are registered via constructors, so
> the linker magic wil
On 12/20/2018 8:02 AM, Luca Boccassi wrote:
> On Wed, 2018-12-19 at 12:52 +, Ferruh Yigit wrote:
>> Define '__rte_deprecated' usage process.
>>
>> Suggests keeping old API with '__rte_deprecated' marker until next
>> LTS.
>>
>> Signed-off-by: Ferruh Yigit
>> ---
>> Cc: Luca Boccassi
>> Cc: Ke
The original document written from the point of ABI versioning but later
additions make document confusing, convert document into a ABI/API
policy documentation and organize the document in subsections:
- ABI/API Deprecation
- Experimental APIs
- Library versioning
- ABI versioning
Aim to clarify
Define '__rte_deprecated' usage process.
Suggests keeping old API with '__rte_deprecated' marker until next LTS.
Signed-off-by: Ferruh Yigit
Acked-by: Luca Boccassi
---
Cc: Luca Boccassi
Cc: Kevin Traynor
Cc: Yongseok Koh
Cc: Neil Horman
v2:
* Rephrased as commented
---
doc/guides/contrib
> -Original Message-
> From: Akhil Goyal [mailto:akhil.go...@nxp.com]
> Sent: Friday, December 21, 2018 1:57 PM
> To: Ananyev, Konstantin ; dev@dpdk.org
> Cc: Nicolau, Radu ; Horton, Remy
>
> Subject: Re: [dpdk-dev] [PATCH v4 1/9] examples/ipsec-secgw: avoid to request
> unused TX offl
Signed-off-by: David Zeng
---
kernel/linux/kni/compat.h | 9 -
kernel/linux/kni/ethtool/igb/kcompat.h | 4 +++-
2 files changed, 11 insertions(+), 2 deletions(-)
diff --git a/kernel/linux/kni/compat.h b/kernel/linux/kni/compat.h
index 5aadebb..3c575c7 100644
--- a/kernel/lin
Thanks, Ferruh!
On 12/14/2018 9:20 PM, Jeff Shaw wrote:
> On Fri, Dec 14, 2018 at 12:50:55PM -0800, Stephen Hemminger wrote:
>> Use rte_log directly, eliminating no longer used rte_pmd_dev_trace
>> function. This removes variable length array which is problem on
>> Windows and other compilers not doing C99.
>>
>>
Hi Eelco,
>
> +/** trTCM parameters per metered traffic flow. The CIR, EIT, CBS and EBS
Small typo here: EIT to be replaced by EIR.
> +parameters only count bytes of IP packets and do not include link specific
> +headers. The CBS and EBS need to be greater than zero if CIR and EIR are
> +none
malloc: add option --match-allocations (2018-12-20 13:01:08 +0100)
are available in the Git repository at:
http://dpdk.org/git/next/dpdk-next-qos
for you to fetch changes up to c7286e56de95b7a3ef2ce4fe91b4ea6422be8481:
app/test-pmd: expand RED queue thresholds to 64 bits (2018-12-20 19:0
On 12/21/2018 4:15 PM, David Zeng wrote:
> Signed-off-by: David Zeng
Acked-by: Ferruh Yigit
Fix the coding style.
Signed-off-by: David Zeng
---
kernel/linux/kni/compat.h | 9 -
kernel/linux/kni/ethtool/igb/kcompat.h | 4 +++-
2 files changed, 11 insertions(+), 2 deletions(-)
diff --git a/kernel/linux/kni/compat.h b/kernel/linux/kni/compat.h
index 5aadebb..3c575c7 100644
--- a/kernel/lin
On 12/21/2018 4:27 PM, David Zeng wrote:
> Signed-off-by: David Zeng
Acked-by: Ferruh Yigit
> -Original Message-
> From: Jozwiak, TomaszX
> Sent: Friday, December 21, 2018 2:15 AM
> To: dev@dpdk.org; Trahe, Fiona ; Jozwiak, TomaszX
> ; akhil.go...@nxp.com
> Subject: [PATCH] compress/qat: add compression on dh895x
>
> This patch enables compression on dh895x HW series
> and upd
Hi Pablo,
Thanks for reviewing
> -Original Message-
> From: De Lara Guarch, Pablo
> Sent: Friday, December 21, 2018 4:52 AM
> To: Trahe, Fiona ; dev@dpdk.org
> Cc: Zhang, Roy Fan ; akhil.go...@nxp.com
> Subject: RE: [PATCH] test/crypto: don't attempt unsupported SGL tests on
> aesni mb P
On Fri, 21 Dec 2018 14:16:46 +0100
Gaëtan Rivet wrote:
> If a VF is forbidden by its PF from adding MAC addresses, the driver
> should still advertize support for "Unicast MAC filter" right?
Not unless both VF and other path support multiple MAC addresses.
Since Hyper-V/Azure is limited to a sin
From: Stephen Hemminger
Use rte_log directly, eliminating no longer used rte_pmd_dev_trace
function. This removes variable length array which is problem on
Windows and other compilers not doing C99.
Also, drop unused RTE_PROC_PRIMARY macros.
Signed-off-by: Stephen Hemminger
Signed-off-by: Jeff
1 - 100 of 109 matches
Mail list logo