remove unnecessary dup and free
Signed-off-by: Shreyansh Jain
Reviewed-by: Nipun Gupta
---
drivers/bus/fslmc/fslmc_bus.c | 19 +--
1 file changed, 9 insertions(+), 10 deletions(-)
diff --git a/drivers/bus/fslmc/fslmc_bus.c b/drivers/bus/fslmc/fslmc_bus.c
index 9caf5b6b9..b3e964
This patch adds retry in the DPAA2 CMDIF packet enqueue API
Fixes: 53c71586c789 ("raw/dpaa2_cmdif: support enqueue/dequeue operations")
Cc: sta...@dpdk.org
Signed-off-by: Nipun Gupta
Acked-by: Hemant Agrawal
---
drivers/raw/dpaa2_cmdif/dpaa2_cmdif.c | 9 +++--
1 file changed, 7 insertions(
From: Radu Bulie
When BMAN is not able to accept more buffers, it could be that
there are no FBPR's (internal mem provided to bman) left.
Report error in such condition.
Fixes: 5dc43d22b5ad ("mempool/dpaa2: add hardware offloaded mempool")
Cc: sta...@dpdk.org
Signed-off-by: Radu Bulie
Signed-o
Thanks, PSB.
> -Original Message-
> From: Andrew Rybchenko
> Sent: Tuesday, November 5, 2019 4:27 PM
> To: Dekel Peled ; john.mcnam...@intel.com;
> marko.kovace...@intel.com; nhor...@tuxdriver.com;
> ajit.khapa...@broadcom.com; somnath.ko...@broadcom.com;
> anatoly.bura...@intel.com; xuan
On 31/10/2019 15:06, Mcnamara, John wrote:
>
>
>> -Original Message-
>> From: Ray Kinsella
>> Sent: Friday, October 25, 2019 5:29 PM
>> To: dev@dpdk.org
>> Cc: m...@ashroe.eu; tho...@monjalon.net; step...@networkplumber.org;
>> Richardson, Bruce ; Yigit, Ferruh
>> ; Ananyev, Konstanti
On 31/10/2019 15:02, Mcnamara, John wrote:
>
>
>> -Original Message-
>> From: Ray Kinsella
>> Sent: Friday, October 25, 2019 5:29 PM
>> To: dev@dpdk.org
>> Cc: m...@ashroe.eu; tho...@monjalon.net; step...@networkplumber.org;
>> Richardson, Bruce ; Yigit, Ferruh
>> ; Ananyev, Konstanti
On 11/3/2019 7:50 AM, Slava Ovsiienko wrote:
>
>
>> -Original Message-
>> From: Damjan Marion (damarion)
>> Sent: Saturday, November 2, 2019 21:21
>> To: Slava Ovsiienko
>> Cc: Liu, Yu Y ; Wang, Haiyue ;
>> Thomas Monjalon ; dev@dpdk.org;
>> arybche...@solarflare.com; Yigit, Ferruh ;
>>
Currently, externally created heaps are supposed to be automatically
mapped for VFIO DMA by EAL, however they only do so if, at the time of
heap creation, VFIO is initialized and has at least one device
available. If no devices are available at the time of heap creation (or
if devices were availabl
On 05-Nov-19 2:10 PM, Rajesh Ravi wrote:
Thanks a lot Anatoly.
Will the same solution work with DPDK 19.02 as well? We 're actually
using DPDK 19.02 for memory allocations for SPDK 19.07.
DPDK 19.11 may not be supported by SPDK 19.07 we 're currently using.
I 'll definitely test if the patch
Separate versioning.rst into abi versioning and abi policy guidance, in
preparation for adding more detail to the abi policy.
Signed-off-by: Ray Kinsella
---
doc/guides/contributing/abi_policy.rst | 167
doc/guides/contributing/abi_versioning.rst | 427 +
doc/gui
TL;DR abbreviation:
A major ABI version that all DPDK releases during an agreed period support. ABI
versioning is managed at a project-level, in place of library-level management.
ABI changes to add new features are permitted, as long as ABI compatibility with
the major ABI version is maintained.
Add an entry to the maintainer file for the abi policy.
Signed-off-by: Ray Kinsella
---
MAINTAINERS | 4
1 file changed, 4 insertions(+)
diff --git a/MAINTAINERS b/MAINTAINERS
index 717c318..d5bb806 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -84,6 +84,10 @@ M: Marko Kovacevic
F: READM
Updates to the ABI versioning guide, to account for the changes to the DPDK
ABI/API policy. Fixes for references to abi versioning and policy guides.
Signed-off-by: Ray Kinsella
---
doc/guides/contributing/abi_policy.rst | 15 +-
doc/guides/contributing/abi_versioning.rst | 250
This policy change introduces major ABI versions, these are
declared every year, typically aligned with the LTS release
and are supported by subsequent releases in the following year.
This change is intended to improve ABI stabilty for those projects
consuming DPDK.
Signed-off-by: Ray Kinsella
--
Introduce simple hash list to the mlx5 utilities. User can define
its own data structure containing the mlx5_hlist_entry and create
the hash list table via the creation interface. Then the entry will
be inserted into the table and linked to the corresponding list
head. User should guarantee there i
> -Original Message-
> From: Bing Zhao
> Sent: Tuesday, November 5, 2019 17:28
> To: Ori Kam ; Slava Ovsiienko
> ; Raslan Darawsheh
> ; dev@dpdk.org
> Subject: [PATCH] net/mlx5: introduce mlx5 hash list
>
> Introduce simple hash list to the mlx5 utilities. User can define its own data
> s
This patch solves a compilation issue that is caused due to using
internal function (is_rx_hairpin_queue) inside inline function.
The solution is to remove the usage of the functions
from the burst functions.
Fixes: 60b476d5da3c ("ethdev: add support for hairpin queue")
Cc: or...@mellanox.com
Si
Introduce new functions that can used by mempool drivers to
calculate required memory size and to populate mempool.
For now, these helpers just replace the *_default() functions
without change. They will be enhanced in next commit.
Signed-off-by: Olivier Matz
Acked-by: Nipun Gupta
Reviewed-by:
The size returned by rte_mempool_op_calc_mem_size_default() is aligned
to the specified page size. Therefore, with big pages, the returned size
can be much more that what we really need to populate the mempool.
For instance, populating a mempool that requires 1.1GB of memory with
1GB hugepages can
For consistency, RTE_MEMPOOL_ALIGN should be used in place of
RTE_CACHE_LINE_SIZE. They have the same value, because the only arch
that was defining a specific value for it has been removed from dpdk.
Signed-off-by: Olivier Matz
Reviewed-by: Andrew Rybchenko
Acked-by: Nipun Gupta
---
lib/librt
KNI supposes that mbufs are contiguous in kernel virtual memory. This
may not be true when using the IOVA=VA mode. To fix this, a possibility
is to ensure that objects do not cross page boundaries in mempool. This
patchset implements this in the last patch (5/5).
The previous patches prepare the j
In rte_mempool_populate_default(), we determine the page size,
which is needed for calc_size and allocation of memory.
Move this in a function and export it, it will be used in a next
commit.
Signed-off-by: Olivier Matz
Reviewed-by: Andrew Rybchenko
Acked-by: Nipun Gupta
---
lib/librte_mempoo
rte_mempool_populate_virt() currently requires that both addr
and length are page-aligned.
Remove this uneeded constraint which can be annoying with big
hugepages (ex: 1GB).
Signed-off-by: Olivier Matz
Reviewed-by: Andrew Rybchenko
Acked-by: Nipun Gupta
---
lib/librte_mempool/rte_mempool.c |
The previous commit reduced the amount of required memory when
populating the mempool with non iova-contiguous memory.
Since there is no big advantage to have a fully iova-contiguous mempool
if it is not explicitly asked, remove this code, it simplifies the
populate function.
Signed-off-by: Olivi
When populating a mempool, ensure that objects are not located across
several pages, except if user did not request iova contiguous objects.
Signed-off-by: Vamsi Krishna Attunuru
Signed-off-by: Olivier Matz
Acked-by: Nipun Gupta
Acked-by: Andrew Rybchenko
---
drivers/mempool/bucket/rte_mempoo
This commit introduce the hairpin queues to the testpmd.
the hairpin queue is configured using --hairpinq=
the hairpin queue adds n queue objects for both the total number
of TX queues and RX queues.
The connection between the queues are 1 to 1, first Rx hairpin queue
will be connected to the first
On 30/10/2019 16:27, Ajit Khaparde wrote:
> On Wed, Oct 30, 2019 at 12:43 AM David Marchand
> wrote:
>
>> Hello Ajit, Kevin,
>>
>> On Wed, Oct 2, 2019 at 3:29 AM Ajit Khaparde
>> wrote:
>>>
>>> On Tue, Oct 1, 2019 at 6:04 AM Kevin Traynor
>> wrote:
>>>
If rc contains a non-zero return code
On 30/10/2019 07:59, David Marchand wrote:
> Hello Rosen,
>
> Review please.
>
Ping Rosen.
> On Tue, Oct 1, 2019 at 3:04 PM Kevin Traynor wrote:
>>
>> Coverity is complaining about identical code regardless of which branch
>> of the if else is taken. Functionally it means an error will always
On Tue, 5 Nov 2019 13:54:43 +
Hemant Agrawal wrote:
> Hi Stephen,
> In one of your old patch, you have changed the default IP
> addresses to the range of 192.18.0.0 citing RFC 5735.
> commit 37afe381bde4277f0078116b8d4d7a315c8e39b3
> Author: Stephen Hemminger
> Date: Wed Apr
On 04/11/2019 10:39, Haiyue Wang wrote:
> Change the type of burst mode information from bit field to free string
> data, so that each PMD can describe the Rx/Tx busrt functions flexibly.
>
> Signed-off-by: Haiyue Wang
> ---
>
> v2: - Drop the bit field for burst mode information handling.
>
On Tue, 5 Nov 2019 15:12:07 +
Ferruh Yigit wrote:
> On 11/3/2019 7:50 AM, Slava Ovsiienko wrote:
> >
> >
> >> -Original Message-
> >> From: Damjan Marion (damarion)
> >> Sent: Saturday, November 2, 2019 21:21
> >> To: Slava Ovsiienko
> >> Cc: Liu, Yu Y ; Wang, Haiyue ;
> >> Thom
On 11/4/2019 11:06 AM, Bruce Richardson wrote:
> On Tue, Oct 29, 2019 at 09:27:22AM +, Ferruh Yigit wrote:
>> On 10/28/2019 5:18 PM, Stephen Hemminger wrote:
>>> On Mon, 26 Aug 2019 18:32:35 +0530
>>> Gagandeep Singh wrote:
>>>
--- a/config/common_base
+++ b/config/common_base
@
Hi,
> -Original Message-
> From: Bing Zhao
> Sent: Tuesday, November 5, 2019 5:28 PM
> To: Ori Kam ; Slava Ovsiienko
> ; Raslan Darawsheh ;
> dev@dpdk.org
> Subject: [PATCH] net/mlx5: introduce mlx5 hash list
>
> Introduce simple hash list to the mlx5 utilities. User can define its own d
On Tue, Nov 05, 2019 at 04:36:59PM +0100, Olivier Matz wrote:
> KNI supposes that mbufs are contiguous in kernel virtual memory. This
> may not be true when using the IOVA=VA mode. To fix this, a possibility
> is to ensure that objects do not cross page boundaries in mempool. This
> patchset implem
The original patch used incorrect subnet range for testing.
Fixes: 37afe381bde4 ("examples/l3fwd: use reserved IP addresses")
Reported-by: Ferruh Yigit
Signed-off-by: Stephen Hemminger
---
doc/guides/testpmd_app_ug/run_app.rst | 6 +++---
examples/l3fwd/l3fwd_lpm.c| 18 +---
On 11/4/2019 11:24 AM, Shah, Rahul R wrote:
> Hi Ferruh,
>
> I was checking the lib/Makefile for cryptodev example which is similar to
> eventdev patch I have added (i.e. there is a dependency on librte_cryptodev
> library)
>
> DIRS-$(CONFIG_RTE_LIBRTE_PORT) += librte_port
> DEPDIRS-librte_port
On 11/5/2019 4:09 PM, Stephen Hemminger wrote:
> The original patch used incorrect subnet range for testing.
>
> Fixes: 37afe381bde4 ("examples/l3fwd: use reserved IP addresses")
> Reported-by: Ferruh Yigit
I guess this is:
Reported-by: Hemant Agrawal
> Signed-off-by: Stephen Hemminger
> ---
No, As Bruce explained I confirmed it is being already built before librte_port
library as highlighted below.
# process all libraries equally, as far as possible
# "core" libs first, then others alphebetically as far as possible
# NOTE: for speed of meson runs, the dependencies in the subdire
On 11/5/2019 4:13 PM, Shah, Rahul R wrote:
> No, As Bruce explained I confirmed it is being already built before
> librte_port
> library as highlighted below.
Got it, so meson doesn't need fixing. Can you please fix the make part?
On Tue, 5 Nov 2019 16:12:31 +
Ferruh Yigit wrote:
> On 11/5/2019 4:09 PM, Stephen Hemminger wrote:
> > The original patch used incorrect subnet range for testing.
> >
> > Fixes: 37afe381bde4 ("examples/l3fwd: use reserved IP addresses")
> > Reported-by: Ferruh Yigit
>
> I guess this is:
On 11/1/2019 5:04 PM, Wang, Yipeng1 wrote:
> Hi, Amit,
>
> I think I acked this patch. But from patchwork seems you superseded this
> patch set accidentally. So Thomas might have missed it.
> To make his life easier, you may submit a newer version with my acked. I
> believe Thomas will see it.
> -Original Message-
> From: Andrew Rybchenko
> Sent: Tuesday, November 5, 2019 1:31 PM
> To: Ori Kam ; Thomas Monjalon
>
> Cc: dev@dpdk.org; pbhagavat...@marvell.com; ferruh.yi...@intel.com;
> jer...@marvell.com; John McNamara ; Marko
> Kovacevic ; Adrien Mazarguil
> ; david.march...@r
On 30/10/2019 07:52, David Marchand wrote:
> On Tue, Oct 1, 2019 at 2:54 PM Kevin Traynor wrote:
>>
>> Previously rx/tx_queues were passed into eth_from_pcaps_common()
>> as ptrs and were checked for being NULL.
>>
>> In commit da6ba28f0540 ("net/pcap: use a struct to pass user options")
>> that c
> -Original Message-
> From: Kevin Traynor
> Sent: Tuesday 5 November 2019 16:41
> To: David Marchand
> Cc: dev ; Ferriter, Cian ; dpdk
> stable ; Yigit, Ferruh
> Subject: Re: [dpdk-dev] [PATCH 1/9] net/pcap: fix argument checks
>
> On 30/10/2019 07:52, David Marchand wrote:
> > On Tu
Currently, externally created heaps are supposed to be automatically
mapped for VFIO DMA by EAL, however they only do so if, at the time of
heap creation, VFIO is initialized and has at least one device
available. If no devices are available at the time of heap creation (or
if devices were availabl
On 05-Nov-19 3:18 PM, Burakov, Anatoly wrote:
On 05-Nov-19 2:10 PM, Rajesh Ravi wrote:
Thanks a lot Anatoly.
Will the same solution work with DPDK 19.02 as well? We 're actually
using DPDK 19.02 for memory allocations for SPDK 19.07.
DPDK 19.11 may not be supported by SPDK 19.07 we 're curren
On 05-Nov-19 3:15 PM, Anatoly Burakov wrote:
Currently, externally created heaps are supposed to be automatically
mapped for VFIO DMA by EAL, however they only do so if, at the time of
heap creation, VFIO is initialized and has at least one device
available. If no devices are available at the tim
On Tue, 5 Nov 2019 17:28:00 +0200
Bing Zhao wrote:
> Introduce simple hash list to the mlx5 utilities. User can define
> its own data structure containing the mlx5_hlist_entry and create
> the hash list table via the creation interface. Then the entry will
> be inserted into the table and linked
On Tue, 5 Nov 2019 17:28:00 +0200
Bing Zhao wrote:
> +struct mlx5_hlist *
> +mlx5_hlist_create(char *name, uint64_t size, mlx5_hlist_destroy_callback_fn
> cb)
Name is unused in rte_malloc, so why bother with it here?
> +{
> + struct mlx5_hlist *h;
> + uint64_t act_size;
> + uint64_
On Tue, 5 Nov 2019 16:02:18 +
Raslan Darawsheh wrote:
> Hi,
>
> > -Original Message-
> > From: Bing Zhao
> > Sent: Tuesday, November 5, 2019 5:28 PM
> > To: Ori Kam ; Slava Ovsiienko
> > ; Raslan Darawsheh ;
> > dev@dpdk.org
> > Subject: [PATCH] net/mlx5: introduce mlx5 hash list
>
On 11/5/2019 3:32 PM, Ori Kam wrote:
> This patch solves a compilation issue that is caused due to using
> internal function (is_rx_hairpin_queue) inside inline function.
>
> The solution is to remove the usage of the functions
> from the burst functions.
>
> Fixes: 60b476d5da3c ("ethdev: add sup
On Tue, 5 Nov 2019 15:24:16 +
Ray Kinsella wrote:
> This policy change introduces major ABI versions, these are
> declared every year, typically aligned with the LTS release
> and are supported by subsequent releases in the following year.
> This change is intended to improve ABI stabilty fo
On Tue, 5 Nov 2019 15:24:17 +
Ray Kinsella wrote:
> Updates to the ABI versioning guide, to account for the changes to the DPDK
> ABI/API policy. Fixes for references to abi versioning and policy guides.
>
> Signed-off-by: Ray Kinsella
> ---
Acked-by: Stephen Hemminger
On Tue, 5 Nov 2019 15:24:15 +
Ray Kinsella wrote:
> Separate versioning.rst into abi versioning and abi policy guidance, in
> preparation for adding more detail to the abi policy.
>
> Signed-off-by: Ray Kinsella
> ---
> doc/guides/contributing/abi_policy.rst | 167
> doc/guid
01/11/2019 07:02, Rasesh Mody:
> Use kernel headers for __le* types to avoid potential conflicts
> resulting in redefinition errors during Linux builds. Add check
> for BSD builds.
I don't see the error with my test builds.
Please could you describe a case where it happens?
And please provide an e
From: Devyn Collier Johnson
Signed-off-by: Devyn Collier Johnson
---
lib/librte_cryptodev/rte_cryptodev.c| 4 ++--
lib/librte_eal/common/eal_common_cpuflags.c | 4 ++--
lib/librte_eal/common/eal_common_errno.c| 2 +-
lib/librte_eal/common/eal_common_hexdump.c | 4 ++--
lib/libr
From: Devyn Collier Johnson
Signed-off-by: Devyn Collier Johnson
---
app/test/test_cmdline_portlist.c| 2 +-
examples/vmdq_dcb/main.c| 2 +-
lib/librte_cryptodev/rte_cryptodev.c| 2 +-
lib/librte_eal/common/eal_common_tailqs.c | 2 +-
lib/librte_eal/com
Originally both SW and HW crypto PMDs use rte_crypot_op based API to
process the crypto workload asynchronously. This way provides uniformity
to both PMD types, but also introduce unnecessary performance penalty to
SW PMDs that have to "simulate" HW async behavior
(crypto-ops enqueue/dequeue, HW ad
This patch extends rte_cryptodev API with CPU-CRYPTO mode.
This is done by reusing of existing rte_crypto_sym_xform data structures
and introducing new opaque rte_crypto_cpu_sym_session data structure
and related control and data path API.
Crypto PMD that wants to support that functionality would
This patch extends rte_cryptodev API with CPU-CRYPTO mode.
This is done by reusing existing rte_crypto_sym_session structure itself
and related control-path cryptodev API (init/clear/get_size/etc.)
For data-path new sym_cpu_ process() function is added into
rte_cryptodev dev_ops.
Crypto PMD t
Introduce basic data strucure to be used with cpu-crypto data-path.
Signed-off-by: Konstantin Ananyev
---
lib/librte_cryptodev/rte_crypto_sym.h | 52 +--
lib/librte_security/rte_security.h| 6 +++-
2 files changed, 54 insertions(+), 4 deletions(-)
diff --git a/lib/l
This patch extends rte_security API with CPU-CRYPTO mode.
Crypto PMD that wants to support that functionality would need to:
1. claim RTE_CRYPTODEV_FF_SECURITY capability supported.
2. at device .probe() allocate and initialize security context (dev->
security_ctx).
3. implement at least the follo
From: Devyn Collier Johnson
Signed-off-by: Devyn Collier Johnson
---
lib/librte_mbuf/rte_mbuf.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/lib/librte_mbuf/rte_mbuf.c b/lib/librte_mbuf/rte_mbuf.c
index f3fe16eb0..305084531 100644
--- a/lib/librte_mbuf/rte_mbuf.c
+++ b/li
> -Original Message-
> From: Stephen Hemminger
> Sent: Tuesday, November 5, 2019 19:21
> To: Bing Zhao
> Cc: Ori Kam ; Slava Ovsiienko
> ; Raslan Darawsheh
> ; dev@dpdk.org
> Subject: Re: [dpdk-dev] [PATCH] net/mlx5: introduce mlx5 hash list
>
> On Tue, 5 Nov 2019 17:28:00 +0200
> Bing
This commit introduce the hairpin queues to the testpmd.
the hairpin queue is configured using --hairpinq=
the hairpin queue adds n queue objects for both the total number
of TX queues and RX queues.
The connection between the queues are 1 to 1, first Rx hairpin queue
will be connected to the first
Hello,
On Tue, Nov 5, 2019 at 7:17 PM wrote:
>
> From: Devyn Collier Johnson
>
> Signed-off-by: Devyn Collier Johnson
> ---
> lib/librte_cryptodev/rte_cryptodev.c| 4 ++--
> lib/librte_eal/common/eal_common_cpuflags.c | 4 ++--
> lib/librte_eal/common/eal_common_errno.c| 2 +-
>
>From: Thomas Monjalon
>Sent: Tuesday, November 05, 2019 10:15 AM
>
>01/11/2019 07:02, Rasesh Mody:
>> Use kernel headers for __le* types to avoid potential conflicts
>> resulting in redefinition errors during Linux builds. Add check for
>> BSD builds.
>
>I don't see the error with my test builds.
On Tue, Nov 5, 2019 at 1:36 PM David Marchand
wrote:
> Hello,
>
> On Tue, Nov 5, 2019 at 7:17 PM wrote:
> >
> > From: Devyn Collier Johnson
> >
> > Signed-off-by: Devyn Collier Johnson
> > ---
> > lib/librte_cryptodev/rte_cryptodev.c| 4 ++--
> > lib/librte_eal/common/eal_common_cpuf
FD retreived from SEC after crypto processing provides
an updated length of the buffer which need to be updated
in mbuf. The difference in length can be negative hence
changing diff to int32_t from uint32_t.
Fixes: 0a23d4b6f4c2 ("crypto/dpaa2_sec: support protocol offload IPsec")
Cc: sta...@dpdk.o
Hi Konstantin,
>
> This patch extends rte_cryptodev API with CPU-CRYPTO mode.
> This is done by reusing existing rte_crypto_sym_session structure itself
> and related control-path cryptodev API (init/clear/get_size/etc.)
> For data-path new sym_cpu_ process() function is added into
> rte_cryptod
Hi Hemant,
>
> The rte_security lib has introduced replay_win_sz,
> so it can be removed from the rte_ipsec lib.
>
> Also, the relaved tests,app are also update to reflect
> the usages.
>
> Signed-off-by: Hemant Agrawal
> Acked-by: Konstantin Ananyev
> ---
> app/test/test_ipsec.c
Hi Hemant,
>
> This patch usages the anti replay window size to config
> the anti replay checking in decap path for lookaside
> IPSEC offload
>
> Signed-off-by: Hemant Agrawal
> ---
> drivers/crypto/dpaa2_sec/dpaa2_sec_dpseci.c | 24 +++
> drivers/crypto/dpaa2_sec/dpaa2_sec_pri
>
> Coverity reported about two division by zero:
> *** CID 350344: Incorrect expression (DIVIDE_BY_ZERO)
> Although in fact these dividers will never be equal to 0,
> adding explicit checks in lookup() to make coverity happy
> will not affect the execution speed.
>
> Signed-off-by: Vladimir
> FD retreived from SEC after crypto processing provides
> an updated length of the buffer which need to be updated
> in mbuf. The difference in length can be negative hence
> changing diff to int32_t from uint32_t.
>
> Fixes: 0a23d4b6f4c2 ("crypto/dpaa2_sec: support protocol offload IPsec")
>
>
> The example IPsec application does not work properly when using
> AES-GCM with crypto_openssl.
>
> ESP with AES-GCM uses standard 96bit long algorithm IV ([1]) which
> later concatenated with be32(1) forms a J0 block. GCM specification
> ([2], chapter 7.1) states that when length of IV is
> Updated AESNI MB and AESNI GCM PMD documentation guides
> with information about the latest Intel IPSec Multi-buffer
> library supported.
>
> Signed-off-by: Pablo de Lara
Applied to dpdk-next-crypto
Thanks
> IPSec Multi buffer library supports encryption on multiple segments.
> When dealing with chained buffers (multiple segments), as long as
> the operation is in-place, the destination buffer does not have to
> be contiguous (unlike in the case of out-of-place operation).
> Therefore, the limitati
01/11/2019 16:21, Vladimir Medvedkin:
> This is heavily reworked version of previous RIB library series:
> https://mails.dpdk.org/archives/dev/2018-April/099492.html
>
> app/test/Makefile | 7 +
> app/test/autotest_data.py | 48 +++
> app/test/meson.build
Hi, Ferruh
On 11/05, Ferruh Yigit wrote:
>On 10/28/2019 5:51 AM, Yang, Qiming wrote:
>> Hi,
>>
>>> -Original Message-
>>> From: Di, ChenxuX
>>> Sent: Thursday, October 24, 2019 9:03 AM
>>> To: dev@dpdk.org
>>> Cc: Lu, Wenzhuo ; Yang, Qiming
>>> ; Di, ChenxuX
>>> Subject: [PATCH] app/test
I'm sorry I still have some comments.
But on the positive side, you can see that I carefuly read this doc.
05/11/2019 16:24, Ray Kinsella:
> +#. Major ABI versions are declared every **year** and are then supported for
> one
> + year, typically aligned with the :ref:`LTS release `.
As discusse
05/11/2019 15:23, Nipun Gupta:
> Hemant Agrawal (1):
> bus/dpaa: moving qbman global init to bus
>
> Nipun Gupta (7):
> net/dpaa: fix supported RSS types
> net/dpaa: fix LS1043 alignment check
> common/dpaax: fallback to check separate memory node for VM
> net/dpaa2: add retry and timeou
04/11/2019 11:39, Haiyue Wang:
> Change the type of burst mode information from bit field to free string
> data, so that each PMD can describe the Rx/Tx busrt functions flexibly.
>
> Signed-off-by: Haiyue Wang
> ---
>
> v2: - Drop the bit field for burst mode information handling.
Please use --
Reviewed-by: Gavin Hu
Hi Thomas,
> -Original Message-
> From: Thomas Monjalon
> Sent: Wednesday, November 6, 2019 08:34
> To: Wang, Haiyue
> Cc: dev@dpdk.org; jerinjac...@gmail.com; Yigit, Ferruh
> ;
> arybche...@solarflare.com; viachesl...@mellanox.com; damar...@cisco.com; Ye,
> Xiaolong
> ; Sun, Chenmin ;
As doc mentioned, Rx/Mac/vlan filters are all supported by best effort.
These control commands should return success.
Fixes: f9b9d1a55775 ("net/virtio-user: add multiple queues in device emulation")
Cc: sta...@dpdk.org
Signed-off-by: Marvin Liu
---
drivers/net/virtio/virtio_user/virtio_user_dev
Change the type of burst mode information from bit field to free string
data, so that each PMD can describe the Rx/Tx busrt functions flexibly.
Signed-off-by: Haiyue Wang
Acked-by: Ray Kinsella
---
v3: - Fix one doxygen issue.
v2: - http://patchwork.dpdk.org/patch/62368/
- Drop the bit fiel
This patch changes RSS rule destroy API from ice_rem_vsi_rss_cfg()
to ice_rem_rss_cfg(). ice_rem_vsi_rss_cfg() removes RSS configurations
associated with VSI. ice_rem_rss_cfg() remove an existing RSS configuration
with matching hashed fields. To support input set change, we should adopt
ice_rem_rss
> -Original Message-
> From: Wang, Haiyue
> Sent: Wednesday, November 6, 2019 09:22
> To: Thomas Monjalon
> Cc: dev@dpdk.org; jerinjac...@gmail.com; Yigit, Ferruh
> ;
> arybche...@solarflare.com; viachesl...@mellanox.com; damar...@cisco.com; Ye,
> Xiaolong
> ; Sun, Chenmin ; Kinsella, Ra
>
> Originally both SW and HW crypto PMDs use rte_crypot_op based API to
> process the crypto workload asynchronously. This way provides uniformity to
> both PMD types, but also introduce unnecessary performance penalty to SW
> PMDs that have to "simulate" HW async behavior (crypto-ops
> enqueue
Hi Eelco
> -Original Message-
> From: Eelco Chaudron [mailto:echau...@redhat.com]
> Sent: Friday, November 1, 2019 4:13 PM
> To: Xing, Beilei ; Zhang, Xiao
> Cc: Zhang, Qi Z ; dev@dpdk.org
> Subject: Re: [dpdk-dev] [PATCH] net/i40e: force promiscuous state after VF
> reset
>
>
>
> On 1
Hi Akhil,
> -Original Message-
> From: Akhil Goyal
> Sent: Wednesday, November 6, 2019 3:38 AM
> To: Hemant Agrawal ; dev@dpdk.org
> Cc: konstantin.anan...@intel.com; ano...@marvell.com; Hemant Agrawal
>
> Subject: RE: [PATCH v5 3/3] crypto/dpaa2_sec: enable anti replay window
> config
>
> -Original Message-
> From: Akhil Goyal
> Sent: Wednesday, November 6, 2019 3:32 AM
> To: Hemant Agrawal ; dev@dpdk.org
> Cc: konstantin.anan...@intel.com; ano...@marvell.com; Hemant Agrawal
>
> Subject: RE: [PATCH v5 2/3] ipsec: remove redundant replay_win_sz
> Importance: High
>
>
This patch add support for AES-128-GCM, when used in
proto lookaside mode.
Signed-off-by: Hemant Agrawal
---
drivers/crypto/dpaa_sec/dpaa_sec.c | 309 -
1 file changed, 211 insertions(+), 98 deletions(-)
diff --git a/drivers/crypto/dpaa_sec/dpaa_sec.c
b/drivers/cryp
set the pdcp capa_flags to 0 by default.
Fixes: a1173d55598c ("crypto/dpaa_sec: support PDCP offload")
Signed-off-by: Hemant Agrawal
---
drivers/crypto/dpaa_sec/dpaa_sec.h | 2 ++
1 file changed, 2 insertions(+)
diff --git a/drivers/crypto/dpaa_sec/dpaa_sec.h
b/drivers/crypto/dpaa_sec/dpaa_se
Signed-off-by: Hemant Agrawal
---
drivers/crypto/dpaa2_sec/dpaa2_sec_dpseci.c | 60 +++--
1 file changed, 56 insertions(+), 4 deletions(-)
diff --git a/drivers/crypto/dpaa2_sec/dpaa2_sec_dpseci.c
b/drivers/crypto/dpaa2_sec/dpaa2_sec_dpseci.c
index dd80e6dc5..173ec8095 100644
---
These are supported when using protocol offload mode or in chain mode.
Signed-off-by: Hemant Agrawal
---
drivers/crypto/dpaa2_sec/dpaa2_sec_dpseci.c | 22 +++
drivers/crypto/dpaa2_sec/dpaa2_sec_priv.h | 41 +
2 files changed, 56 insertions(+), 7 deletions(-)
diff -
Check if the session is not null during processing.
Signed-off-by: Hemant Agrawal
---
drivers/crypto/dpaa2_sec/dpaa2_sec_dpseci.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/drivers/crypto/dpaa2_sec/dpaa2_sec_dpseci.c
b/drivers/crypto/dpaa2_sec/dpaa2_sec_dpseci.c
index b04890a48..7d5
These are supported when using protocol offload mode or when
in chain mode.
Signed-off-by: Hemant Agrawal
---
drivers/crypto/dpaa_sec/dpaa_sec.c | 33 ++--
drivers/crypto/dpaa_sec/dpaa_sec.h | 41 ++
2 files changed, 66 insertions(+), 8 deletions(-
Check if the session is not null during processing.
Signed-off-by: Hemant Agrawal
---
drivers/crypto/dpaa_sec/dpaa_sec.c | 8
1 file changed, 8 insertions(+)
diff --git a/drivers/crypto/dpaa_sec/dpaa_sec.c
b/drivers/crypto/dpaa_sec/dpaa_sec.c
index 6c186338f..343a565a2 100644
--- a/dr
From: Vakul Garg
The protocol aware ipsec descriptor has been modified to
use ctr_initial value of 1 and salt configured for ipsec SA.
Signed-off-by: Hemant Agrawal
Signed-off-by: Vakul Garg
---
drivers/common/dpaax/caamflib/desc/ipsec.h | 18 --
drivers/crypto/dpaa2_sec/dpaa
101 - 200 of 231 matches
Mail list logo
