Hi David,
The patch below is causing performance regression with BNX2X PMD. We are seeing
1518 packets not getting to line rate after applying the patch. We are using
l2fwd application on the test system. The same issue is not observed while
using testpmd application.
We are trying to investig
> Pablo de Lara (11):
> snow3g: rename libsso reference due to library update
> doc: update build instructions for libsso_snow3g
> snow3g: define IV/digest length macros
> snow3g: support bit-level operations
> snow3g: add missing feature flags
> test: use new bit-level memcmp macro
>
> Pablo de Lara (3):
> kasumi: add new KASUMI PMD
> test: add new buffer comparison macros
> test: add unit tests for KASUMI PMD
Applied (with "make clean" fixed), thanks
As for other crypto drivers with a dependency, I'm not sure the PMD.so
can be loaded.
2016-06-20 15:40, Pablo de Lara:
> --- /dev/null
> +++ b/drivers/crypto/kasumi/Makefile
> +# external library include paths
> +CFLAGS += -I$(LIBSSO_KASUMI_PATH)
> +CFLAGS += -I$(LIBSSO_KASUMI_PATH)/include
> +CFL
2016-06-20 15:40, Pablo de Lara:
> +include $(RTE_SDK)/mk/rte.vars.mk
> +
> +ifeq ($(LIBSSO_KASUMI_PATH),)
> +$(error "Please define LIBSSO_KASUMI_PATH environment variable")
> +endif
This is not "make clean" compliant.
See previous fix of other crypto drivers:
http://dpdk.org/browse/dpdk/
On Saturday 18 June 2016 01:13 PM, Raja Jayapal wrote:
> Hi All,
>
> I am trying to install dpdk with ovs, but am getting the linking errors.
> Downloaded and tried with dpdk 2.0/2.2/16.04 and latest ovs.
>
> DPDK : wget http://dpdk.org/browse/dpdk/snapshot/dpdk-2.0.0.tar.gz and wget
> http://dpdk
> > Some crypto PMDs that support symmetric crypto were not marked as
> > supported in the supported feature flags table.
> >
> > Fixes: 2373c0661b2f0 ("doc: add cryptodevs guide overview")
> >
> > Signed-off-by: Pablo de Lara
>
> Acked-by: John McNamara
Applied, thanks
On Mon, Jun 20, 2016 at 01:58:04PM +, Ananyev, Konstantin wrote:
>
>
> > -Original Message-
> > From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Thomas Monjalon
> > Sent: Monday, June 20, 2016 2:54 PM
> > To: Jerin Jacob
> > Cc: dev at dpdk.org; Hunt, David; olivier.matz at 6wi
On Mon, Jun 20, 2016 at 12:02:16PM +0100, Remy Horton wrote:
>
> On 20/06/2016 11:50, Yuanhan Liu wrote:
> >Trying to access xstats_names after "if (stats_names == NULL)" is
> >obviously wrong, which would result to a crash while running "show
> >port xstats 0" in testpmd with virtio PMD.
> >
> >T
On Mon, Jun 20, 2016 at 01:48:52AM +0800, Huawei Xie wrote:
> In the following loop:
> while (vq->vq_used_cons_idx != vq->vq_ring.used->idx) {
> ...
> }
> There is no external function call or any explict memory barrier
> in the loop, the re-read of used->idx would be optimized
2016-06-20 17:10, Jain, Deepak K:
> Updated the code to use RTE_PCI_DEVICE.
>
> Fixes: 701c8d80c820 ("pci: support class id probing")
>
> Signed-off-by: Jain, Deepak K
> ---
> drivers/crypto/qat/rte_qat_cryptodev.c | 10 +++---
> lib/librte_eal/common/include/rte_pci_dev_ids.h | 10
On Mon, Jun 20, 2016 at 02:08:10PM +0100, David Hunt wrote:
> This is a mempool handler that is useful for pipelining apps, where
> the mempool cache doesn't really work - example, where we have one
> core doing rx (and alloc), and another core doing Tx (and return). In
> such a case, the mempool r
Trying to access xstats_names after "if (stats_names == NULL)" is
obviously wrong, which would result to a crash while running "show
port xstats 0" in testpmd with virtio PMD.
The fix is also straightforward: just revese the check.
Fixes: baf91c395b18 ("net/virtio: fetch extended statistics with
> -Original Message-
> From: Kerlin, MarcinX [mailto:marcinx.kerlin at intel.com]
> Sent: Monday, June 20, 2016 4:12 AM
> To: John Daley (johndale) ; Nelson Escobar
> (neescoba)
> Cc: 'dev at dpdk.org'
> Subject: RE: unchecked return value in enic driver
>
> Hi John and Nelson,
>
> >
On Wed, Jun 15, 2016 at 04:25:32PM +0100, Remy Horton wrote:
>
> +static int virtio_dev_xstats_get_names(struct rte_eth_dev *dev,
> +struct rte_eth_xstat_name *xstats_names,
> +__rte_unused unsigned limit)
> +{
> + unsign
From: Adrien Mazarguil
This commit brings back Rx scatter and related support by the MTU update
function. The maximum number of segments per packet is not a fixed value
anymore (previously MLX5_PMD_SGE_WR_N, set to 4 by default) as it caused
performance issues when fewer segments were actually ne
From: Adrien Mazarguil
The primary purpose of rxq_rehash() function is to stop and restart
reception on a queue after re-posting buffers. This may fail if the array
that temporarily stores existing buffers for reuse cannot be allocated.
Update rxq_rehash() to work on the target queue directly (n
From: Adrien Mazarguil
Toggling RX checksum offloads is already done at initialization time. This
code does not belong in rxq_rehash().
Signed-off-by: Adrien Mazarguil
Signed-off-by: Nelio Laranjeiro
---
drivers/net/mlx5/mlx5_rxq.c | 10 --
1 file changed, 10 deletions(-)
diff --git
From: Adrien Mazarguil
Since commit "mlx5: resurrect Tx gather support", older GCC versions (such
as 4.8.5) may complain about the following:
mlx5_rxtx.c: In function `mlx5_tx_burst':
mlx5_rxtx.c:705:25: error: `wqe' may be used uninitialized in this
function [-Werror=maybe-uninitialized]
From: Adrien Mazarguil
Compared to its previous incarnation, the software limit on the number of
mbuf segments is no more (previously MLX5_PMD_SGE_WR_N, set to 4 by
default) hence no need for linearization code and related buffers that
permanently consumed a non negligible amount of memory to han
From: Adrien Mazarguil
The space necessary to store segmented packets cannot be known in advance
and must be verified for each of them.
Signed-off-by: Adrien Mazarguil
---
drivers/net/mlx5/mlx5_rxtx.c | 136 ++-
1 file changed, 70 insertions(+), 66 delet
From: Adrien Mazarguil
Signed-off-by: Adrien Mazarguil
---
drivers/net/mlx5/mlx5_txq.c | 5 +
1 file changed, 5 insertions(+)
diff --git a/drivers/net/mlx5/mlx5_txq.c b/drivers/net/mlx5/mlx5_txq.c
index 4f17fb0..bae9f3d 100644
--- a/drivers/net/mlx5/mlx5_txq.c
+++ b/drivers/net/mlx5/mlx5_t
This feature enables the TX burst function to emit up to 5 packets using
only two WQEs on devices that support it. Saves PCI bandwidth and improves
performance.
Signed-off-by: Nelio Laranjeiro
Signed-off-by: Adrien Mazarguil
Signed-off-by: Olga Shern
---
doc/guides/nics/mlx5.rst | 10 ++
From: Yaacov Hazan
Implement send inline feature which copies packet data directly into WQEs
for improved latency. The maximum packet size and the minimum number of Tx
queues to qualify for inline send are user-configurable.
This feature is effective when HW causes a performance bottleneck.
Sig
From: Adrien Mazarguil
Replacing the variable countdown (which depends on the number of
descriptors) with a fixed relative threshold known at compile time improves
performance by reducing the TX queue structure footprint and the amount of
code to manage completions during a burst.
Completions ar
Mini (compressed) CQEs are returned by the NIC when PCI back pressure is
detected, in which case the first CQE64 contains common packet information
followed by a number of CQE8 providing the rest, followed by a matching
number of empty CQE64 entries to be used by software for decompression.
Before
Bypass Verbs to improve Tx performance.
Signed-off-by: Nelio Laranjeiro
Signed-off-by: Yaacov Hazan
Signed-off-by: Adrien Mazarguil
---
drivers/net/mlx5/Makefile | 5 -
drivers/net/mlx5/mlx5_ethdev.c | 10 +-
drivers/net/mlx5/mlx5_mr.c | 4 +-
drivers/net/mlx5/mlx5_rxtx.c | 359
Bypass Verbs to improve RX performance.
Signed-off-by: Nelio Laranjeiro
Signed-off-by: Yaacov Hazan
Signed-off-by: Adrien Mazarguil
Signed-off-by: Vasily Philipov
---
drivers/net/mlx5/mlx5_ethdev.c | 4 +-
drivers/net/mlx5/mlx5_fdir.c | 2 +-
drivers/net/mlx5/mlx5_rxq.c| 303 +++
These wrappers are meant to prevent code duplication later.
Signed-off-by: Nelio Laranjeiro
Signed-off-by: Adrien Mazarguil
---
drivers/net/mlx5/mlx5.h| 2 ++
drivers/net/mlx5/mlx5_ethdev.c | 34 --
drivers/net/mlx5/mlx5_txq.c| 2 +-
3 files changed
The intent is to replace the remaining compile-time options and environment
variables with a common mean of runtime configuration. This commit only
adds the kvargs handling code, subsequent commits will update the rest.
Signed-off-by: Nelio Laranjeiro
Signed-off-by: Adrien Mazarguil
---
drivers
These structures and macros extend those exposed by libmlx5 (in mlx5_hw.h)
to let the PMD manage work queue and completion queue elements directly.
Signed-off-by: Nelio Laranjeiro
Signed-off-by: Adrien Mazarguil
---
drivers/net/mlx5/mlx5_prm.h | 163
The latest version of Mellanox OFED exposes hardware definitions necessary
to implement data path operation bypassing Verbs. Update the minimum
version requirement to MLNX_OFED >= 3.3 and clean up compatibility checks
for previous releases.
Signed-off-by: Nelio Laranjeiro
Signed-off-by: Adrien Ma
To keep the data path as efficient as possible, move fields only useful to
the control path into new structure rxq_ctrl.
Signed-off-by: Nelio Laranjeiro
Signed-off-by: Adrien Mazarguil
---
drivers/net/mlx5/mlx5.c | 6 +-
drivers/net/mlx5/mlx5_fdir.c | 8 +-
drivers/net/mlx5/mlx5_rxq.c
To keep the data path as efficient as possible, move fields only useful to
the control path into new structure txq_ctrl.
Signed-off-by: Nelio Laranjeiro
Signed-off-by: Adrien Mazarguil
---
drivers/net/mlx5/mlx5.c| 21 +++--
drivers/net/mlx5/mlx5_ethdev.c | 27 +++---
drivers/net/mlx5/
Inline TX will be fully managed by the PMD after Verbs is bypassed in the
data path. Remove the current code until then.
Signed-off-by: Nelio Laranjeiro
Signed-off-by: Adrien Mazarguil
---
config/common_base | 1 -
doc/guides/nics/mlx5.rst | 10 --
drivers/net/mlx5/Makefile
There is no scatter/gather support anymore, CONFIG_RTE_LIBRTE_MLX5_SGE_WR_N
has no purpose and can be removed.
Signed-off-by: Nelio Laranjeiro
Signed-off-by: Adrien Mazarguil
---
config/common_base | 1 -
doc/guides/nics/mlx5.rst | 7 ---
drivers/net/mlx5/Makefile| 4
This is done in preparation of bypassing Verbs entirely for the data path
as a performance improvement. RX scatter cannot be maintained during the
transition and will be reimplemented later.
Signed-off-by: Nelio Laranjeiro
Signed-off-by: Adrien Mazarguil
---
drivers/net/mlx5/mlx5_ethdev.c | 31
This is done in preparation of bypassing Verbs entirely for the data path
as a performance improvement. TX gather cannot be maintained during the
transition and will be reimplemented later.
Signed-off-by: Nelio Laranjeiro
Signed-off-by: Adrien Mazarguil
---
drivers/net/mlx5/mlx5_ethdev.c | 2
Except for the first time when memory registration occurs, the lkey is
always cached. Since memory registration is slow and performs system calls,
performance can be improved by moving that code to its own function outside
of the data path so only the lookup code is left in the original inlined
fun
Fixes: 701c8d80c820 ("pci: support class id probing")
Signed-off-by: Nelio Laranjeiro
---
drivers/crypto/qat/rte_qat_cryptodev.c | 5 +
drivers/net/mlx4/mlx4.c| 18 ++
drivers/net/mlx5/mlx5.c| 24
drivers/net/nfp/nfp_n
Enhance mlx5 with a data path that bypasses Verbs.
The first half of this patchset removes support for functionality completely
rewritten in the second half (scatter/gather, inline send), while the data
path is refactored without Verbs.
The PMD remains usable during the transition.
This patchset
Hi Nelio,
On 6/20/2016 5:10 PM, Nelio Laranjeiro wrote:
> Enhance mlx5 with a data path that bypasses Verbs.
>
> The first half of this patchset removes support for functionality completely
> rewritten in the second half (scatter/gather, inline send), while the data
> path is refactored without V
> -Original Message-
> From: Jerin Jacob [mailto:jerin.jacob at caviumnetworks.com]
> Sent: Monday, June 20, 2016 3:22 PM
> To: Ananyev, Konstantin
> Cc: Thomas Monjalon; dev at dpdk.org; Hunt, David; olivier.matz at 6wind.com;
> viktorin at rehivetech.com; shreyansh.jain at nxp.com
> Su
2016-06-20 16:44, Ferruh Yigit:
> On 6/15/2016 7:34 PM, Thomas Monjalon wrote:
> > 2016-06-15 19:16, Ferruh Yigit:
> >> On 6/9/2016 10:26 PM, Thomas Monjalon wrote:
> >>> So this is my proposal:
> >>> Someone start working on the above cleanup now, otherwise the whole
> >>> rte_ivshmem feature will
> > Pablo de Lara (4):
> > test: remove useless hexdump include
> > test: fix compilation when RTE_APP_TEST_DEBUG was set
> > test: remove unnecessary hexdump_mbuf_data and HEXDUMP
> > app: add new TEST_HEXDUMP macro
>
> Series-acked-by: Fan Zhang
Applied, thanks
On Mon, Jun 20, 2016 at 11:34:55AM +0100, Declan Doherty wrote:
> On 27/05/16 20:44, Eric Kinzie wrote:
> >This patchset introduces the ability to use an external 802.3ad state
> >machine for mode 4 bonding. Functions to alter the mux state and to
> >allow LACPDUs to be sent and received from outs
On Fri, Jun 17, 2016 at 03:30:03PM +0100, Declan Doherty wrote:
> On 07/05/16 04:45, Eric Kinzie wrote:
> > Instead of a hard-coded maximum receive length, allow the bond interface
> > to inherit this limit from the slave interfaces. This allows
> > an application that uses jumbo frames to pass
> Fiona Trahe (2):
> app/test: adding Snow3g performance test
> app/test: updating AES SHA performance test
>
> Jain, Deepak K (1):
> app/test: typo fixing
Applied, thanks
Most of the counters come from the NIC hardware, but I have to do the different
sizes in software. If the packet was received then it will get counted as that
works in my machine and many others. Unless I broke something in Pktgen it
would mean to me that the packets are not getting received by
> > Fan Zhang (2):
> > app/test: rework the crypto AES unit test
> > app/test: add crypto AES-CBC-128 HMAC-SHA224 and HMAC-SHA384 unit
> > tests
>
> Series-acked-by: Pablo de Lara
Applied, thanks
On 6/16/2016 6:54 PM, Jan Medala wrote:
> This patch includes:
> * Update of ENA communication layer
>
> * Fixed memory management issue
> After allocating memzone it's required to zeroize it
> as well as freeing memzone with dedicated function.
>
> * Added debug area and host informa
On Mon, Jun 20, 2016 at 04:03:00PM +0100, Ferruh Yigit wrote:
> On 6/20/2016 8:38 AM, N?lio Laranjeiro wrote:
> > On Fri, Jun 17, 2016 at 05:09:43PM +0100, Ferruh Yigit wrote:
> >> On 6/8/2016 10:47 AM, Nelio Laranjeiro wrote:
> >>> Enhance mlx5 with a data path that bypasses Verbs.
> >>>
> >>> The
Updated the code to use RTE_PCI_DEVICE.
Fixes: 701c8d80c820 ("pci: support class id probing")
Signed-off-by: Jain, Deepak K
---
drivers/crypto/qat/rte_qat_cryptodev.c | 10 +++---
lib/librte_eal/common/include/rte_pci_dev_ids.h | 10 ++
2 files changed, 13 insertions(+), 7
On 6/15/2016 7:34 PM, Thomas Monjalon wrote:
> 2016-06-15 19:16, Ferruh Yigit:
>> On 6/9/2016 10:26 PM, Thomas Monjalon wrote:
>>> So this is my proposal:
>>> Someone start working on the above cleanup now, otherwise the whole
>>> rte_ivshmem feature will be deprecated in 16.07 and removed in 16.11
On Mon, Jun 20, 2016 at 03:31:46PM +0200, Adrien Mazarguil wrote:
> Since _BSD_SOURCE was deprecated in favor of _DEFAULT_SOURCE in Glibc 2.19
> and entirely removed in 2.20, various BSD ioctl macros are not exposed
> anymore when _XOPEN_SOURCE is defined, and linux/if.h now conflicts with
> net/if
Fixes memory leaks detected by Coverity. These are due to ephemeral
memory allocations not being freed when errors occur.
Coverity issue 127349: Resource leak
Fixes: e2aae1c1ced9 ("ethdev: remove name from extended statistic fetch")
Signed-off-by: Remy Horton
---
examples/l2fwd-keepalive/shm.c
Fixes memory leaks detected by Coverity. These are due to ephemeral
memory allocations not being freed when errors occur.
Coverity issue 127348: Resource leak
Fixes: e2aae1c1ced9 ("ethdev: remove name from extended statistic fetch")
Signed-off-by: Remy Horton
---
app/test-pmd/config.c | 3 +++
Fixes memory leaks detected by Coverity. These are due to ephemeral
memory allocations not being freed when errors occur.
--
v2 changes:
* Split patch into two
Remy Horton (2):
app/test-pmd: fix Coverity issues
examples/l2fwd-keepalive: fix Coverity issues
app/test-pmd/config.c | 3
Fixing typo in the performance tests for example preftest to perftest.
Signed-off-by: Jain, Deepak K
---
app/test/test_cryptodev_perf.c | 26 +-
1 file changed, 13 insertions(+), 13 deletions(-)
diff --git a/app/test/test_cryptodev_perf.c b/app/test/test_cryptodev_perf.c
From: Fiona Trahe
Updating the AES performance test in line with snow3g peformance test.
Output format has been updated so as to get better understanding of numbers.
Signed-off-by: Fiona Trahe
Signed-off-by: Jain, Deepak K
---
app/test/test_cryptodev.h | 2 +
app/test/test_cryptodev_pe
From: Fiona Trahe
Adding performance test for snow3g wireless algorithm.
Performance test can run over both software and hardware.
Signed-off-by: Fiona Trahe
Signed-off-by: Jain, Deepak K
Signed-off-by: Declan Doherty
---
app/test/test_cryptodev.h | 2 +-
app/test/test_cryptodev_perf.
Performance tests haven been extended in this patchset.
Patchset consists of 3 patches:
Patch 1 add snow3g performance tests.
Patch 2 updates the existing aes performanc test
Patch 3 fixes the typo in names of perftest
Changes in v3:
-Minor refactoring
Changes in v2:
-Removed the addtion of rte_
On 6/20/2016 8:38 AM, N?lio Laranjeiro wrote:
> On Fri, Jun 17, 2016 at 05:09:43PM +0100, Ferruh Yigit wrote:
>> On 6/8/2016 10:47 AM, Nelio Laranjeiro wrote:
>>> Enhance mlx5 with a data path that bypasses Verbs.
>>>
>>> The first half of this patchset removes support for functionality completely
2016-06-20 14:49, Remy Horton:
> Fixes memory leaks detected by Coverity. These are due to ephemeral
> memory allocations not being freed when errors occur.
>
> Coverity issue 127348: Resource leak
> Coverity issue 127349: Resource leak
>
> Fixes: e2aae1c1ced9 ("ethdev: remove name from extended
2016-06-20 18:55, Jerin Jacob:
> On Mon, Jun 20, 2016 at 02:08:10PM +0100, David Hunt wrote:
> > This is a mempool handler that is useful for pipelining apps, where
> > the mempool cache doesn't really work - example, where we have one
> > core doing rx (and alloc), and another core doing Tx (and r
On 6/18/2016 8:43 AM, Raja Jayapal wrote:
> Hi All,
>
> I am trying to install dpdk with ovs, but am getting the linking errors.
> Downloaded and tried with dpdk 2.0/2.2/16.04 and latest ovs.
>
> DPDK : wget http://dpdk.org/browse/dpdk/snapshot/dpdk-2.0.0.tar.gz and wget
> http://dpdk.org/browse
On 20/06/2016 14:56, Thomas Monjalon wrote:
[..]
> It looks to be 2 patches: one for xstats and the other for keepalive.
>
Ok, will seperate. I combined them since they were the same small fix in
multiple places.
On Wed, Jun 08, 2016 at 10:34:17AM +, Ananyev, Konstantin wrote:
> Hi Adrien,
>
> >
> > An assertion failure occurs in __rte_mbuf_raw_free() (called by a few PMDs)
> > when compiling DPDK with CONFIG_RTE_LOG_LEVEL=RTE_LOG_DEBUG and starting
> > applications with a log level high enough to tri
SNOW3G and KASUMI unit tests are very similar and
they were using duplicated code, so this commit
refactor and remove some of the duplicated functions.
Signed-off-by: Pablo de Lara
Acked-by: Jain, Deepak K
---
app/test/test_cryptodev.c | 440 --
1 fil
With the new libsso library, buffers can be encrypted/decrypted,
providing an offset in bits, so an extra unit test has been
added to cover this case.
Signed-off-by: Pablo de Lara
Acked-by: Jain, Deepak K
---
app/test/test_cryptodev.c | 121 ++
1 file
Snow3G PMD supports now buffers that are non byte multiple,
so tests to cover this case have been added.
Signed-off-by: Pablo de Lara
Acked-by: Jain, Deepak K
---
app/test/test_cryptodev.c | 50 ++
app/test/test_cryptodev_snow3g_hash_test_vectors.h | 107 ++
Signed-off-by: Pablo de Lara
Acked-by: Jain, Deepak K
---
app/test/test_cryptodev.c | 5 +
1 file changed, 5 insertions(+)
diff --git a/app/test/test_cryptodev.c b/app/test/test_cryptodev.c
index 7dc5648..803f1f6 100644
--- a/app/test/test_cryptodev.c
+++ b/app/test/test_cryptodev.c
@@ -405
No padding was added in the input buffers for snow3G tests,
due to a wrong calculation of the length (should be multiple
of the block size). This fix takes into account the case
where the length is not byte multiple.
Fixes: 8bdf665fe6c0 ("app/test: add SNOW 3G")
Signed-off-by: Pablo de Lara
Acke
Instead of modifying the content of the buffers, to compare them
at bit-level, use the new macro TEST_ASSERT_BUFFERS_ARE_EQUAL_BIT,
which does not make any modifications in the buffers.
Signed-off-by: Pablo de Lara
Acked-by: Jain, Deepak K
---
app/test/test_cryptodev.c | 68 +---
The underlying libsso library support SSE4.1 instruction set,
so feature flags of the crypto device must be updated
to reflect this.
Signed-off-by: Pablo de Lara
Acked-by: Jain, Deepak K
---
drivers/crypto/snow3g/rte_snow3g_pmd.c | 13 -
1 file changed, 12 insertions(+), 1 deletion(
Underlying libsso_snow3g library now supports bit-level
operations, so PMD has been updated to allow them.
Signed-off-by: Pablo de Lara
Acked-by: Jain, Deepak K
---
doc/guides/cryptodevs/snow3g.rst | 5 +-
drivers/crypto/snow3g/rte_snow3g_pmd.c | 193 -
2
In order to avoid using magic numbers, macros for
the IV and digest lengths for Snow3G have been added.
Signed-off-by: Pablo de Lara
Acked-by: Jain, Deepak K
---
drivers/crypto/snow3g/rte_snow3g_pmd.c | 8 +---
1 file changed, 5 insertions(+), 3 deletions(-)
diff --git a/drivers/crypto/sno
With the library update, the way to compile the library
has changed, so documentation reflects this change.
Also, the patch to fix the compilation issues present with gcc > 5.0
has been removed, as the issues have been fixed in the library.
Signed-off-by: Pablo de Lara
Acked-by: Jain, Deepak K
-
The underlying libsso library that SNOW3G PMD uses has been updated,
so now it is called libsso_snow3g. Also, the path to the library
has been renamed to reflect this changes (now called LIBSSO_SNOW3G_PATH).
Signed-off-by: Pablo de Lara
Acked-by: Jain, Deepak K
---
doc/guides/cryptodevs/snow3g.
The underlying library libsso for Snow3G PMD will be updated,
to support bit-level operations.
This patchset updates the PMD to allow the user to perform
crypto operation at bit-level. It also add some unit tests and
updates the documentation.
This patchset depends on the following patchset:
"Add
Signed-off-by: Pablo de Lara
Acked-by: Jain, Deepak K
---
app/test/test_cryptodev.c | 995 +++--
app/test/test_cryptodev.h | 1 +
app/test/test_cryptodev_kasumi_hash_test_vectors.h | 260 ++
app/test/test_cryptodev_kasumi_te
In order to compare buffers with length and offset in bits,
new macros have been created, which use the previous compare function
to compare full bytes and then, compare first and last bytes of
each buffer separately.
Signed-off-by: Pablo de Lara
Acked-by: Jain, Deepak K
---
app/test/test.h | 5
Added new SW PMD which makes use of the libsso_kasumi SW library,
which provides wireless algorithms KASUMI F8 and F9
in software.
This PMD supports cipher-only, hash-only and chained operations
("cipher then hash" and "hash then cipher") of the following
algorithms:
- RTE_CRYPTO_SYM_CIPHER_KASUMI
Added new SW PMD which makes use of the libsso SW library,
which provides wireless algorithms KASUMI F8 and F9
in software.
This PMD supports cipher-only, hash-only and chained operations
("cipher then hash" and "hash then cipher") of the following
algorithms:
- RTE_CRYPTO_SYM_CIPHER_KASUMI_F8
- R
On 5/27/2016 1:56 PM, Slawomir Mrozowicz wrote:
> Negative array index write using variable pos as an index to array
> enic->fdir.nodes.
> Fixed by add array index check.
>
> Fixes: fefed3d1e62c ("enic: new driver")
> Coverity ID 13270
>
> Signed-off-by: Slawomir Mrozowicz
> ---
Hi John, Nelso
Hi Remy,
> -Original Message-
> From: Horton, Remy
> Sent: Monday, June 20, 2016 4:23 PM
> To: dev at dpdk.org; De Lara Guarch, Pablo
> Subject: [PATCH v2 1/2] app/test-pmd: fix Coverity issues
>
> Fixes memory leaks detected by Coverity. These are due to ephemeral
> memory allocations no
Fixing typo in the performance tests for example preftest to perftest.
Signed-off-by: Jain, Deepak K
---
app/test/test_cryptodev_perf.c | 26 +-
1 file changed, 13 insertions(+), 13 deletions(-)
diff --git a/app/test/test_cryptodev_perf.c b/app/test/test_cryptodev_perf.c
From: Fiona Trahe
Updating the AES performance test in line with snow3g peformance test.
Output format has been updated so as to get better understanding of numbers.
Signed-off-by: Fiona Trahe
Signed-off-by: Jain, Deepak K
---
app/test/test_cryptodev.h | 2 +
app/test/test_cryptodev_pe
From: Fiona Trahe
Adding performance test for snow3g wireless algorithm.
Performance test can run over both software and hardware.
Signed-off-by: Fiona Trahe
Signed-off-by: Jain, Deepak K
Signed-off-by: Declan Doherty
---
app/test/test_cryptodev.h | 2 +-
app/test/test_cryptodev_perf.
Performance tests haven been extended in this patchset.
Patchset consists of 3 patches:
Patch 1 add snow3g performance tests.
Patch 2 updates the existing aes performanc test
Patch 3 fixes the typo in names of perftest
Changes in v2:
Removed the addtion of rte_crypto_op_bulk_free
Fiona Trahe (2
Since _BSD_SOURCE was deprecated in favor of _DEFAULT_SOURCE in Glibc 2.19
and entirely removed in 2.20, various BSD ioctl macros are not exposed
anymore when _XOPEN_SOURCE is defined, and linux/if.h now conflicts with
net/if.h.
Add _DEFAULT_SOURCE and keep _BSD_SOURCE for compatibility with older
On Wed, Jun 15, 2016 at 01:45:23AM +0800, Huawei Xie wrote:
> Value returned from fstat is not checked for errors before being used.
> Fixes the coverity issue:
>
> static uint64_t
> get_blk_size(int fd)
> {
> struct stat stat;
>
> fstat(fd, &stat);
> return (uint64_t)stat.st_bl
2016-06-17 15:12, Jerin Jacob:
> Thunderx nicvf also got the same problem when I rebased to
> dpdk-next-net/rel_16_07.
>
> The root cause for this issue is that, PCI CLASS_ID EAL add
> changeset(701c8d80c820461e8255dfb7387a09f0e54399f0)
> has taken care only the pci devices where id table is creat
Fixes memory leaks detected by Coverity. These are due to ephemeral
memory allocations not being freed when errors occur.
Coverity issue 127348: Resource leak
Coverity issue 127349: Resource leak
Fixes: e2aae1c1ced9 ("ethdev: remove name from extended statistic fetch")
Signed-off-by: Remy Horton
On Mon, Jun 20, 2016 at 02:24:27PM +0800, Wenzhuo Lu wrote:
> Add an API to reset the device.
> It's for VF device in this scenario, kernel PF + DPDK VF.
> When the PF port down->up, APP should call this API to
> reset VF port. Most likely, APP should call it in its
> management thread and guarante
Hi Thomas,
> -Original Message-
> From: Thomas Monjalon [mailto:thomas.monjalon at 6wind.com]
> Sent: Monday, June 20, 2016 10:46 AM
> To: Jain, Deepak K ; Doherty, Declan
>
> Cc: dev at dpdk.org; Griffin, John ; Trahe, Fiona
> ; De Lara Guarch, Pablo
>
> Subject: Re: [dpdk-dev] [PATCH 1
On Thu, Jun 16, 2016 at 02:30:37AM +0800, Huawei Xie wrote:
> - while (vq->vq_used_cons_idx != vq->vq_ring.used->idx) {
> + while (VIRTQUEUE_NUSED(vq)) {
> uint32_t idx, desc_idx, used_idx;
> struct vring_used_elem *uep;
>
> diff --git a/drivers/net/virtio/virt
Implement the device reset function.
This reset function will detach device then
attach device, reconfigure dev, re-setup the Rx/Tx queues.
Signed-off-by: Zhe Tao
---
doc/guides/rel_notes/release_16_07.rst | 4 ++
drivers/net/i40e/i40e_ethdev.h | 4 ++
drivers/net/i40e/i40e_ethdev_vf.c
Implement the device reset function.
Signed-off-by: Wenzhuo Lu
---
doc/guides/rel_notes/release_16_07.rst | 2 +-
drivers/net/e1000/igb_ethdev.c | 59 ++
2 files changed, 60 insertions(+), 1 deletion(-)
diff --git a/doc/guides/rel_notes/release_16_07.rst
Implement the device reset function.
Signed-off-by: Wenzhuo Lu
---
doc/guides/rel_notes/release_16_07.rst | 9 +
drivers/net/ixgbe/ixgbe_ethdev.c | 64 +-
drivers/net/ixgbe/ixgbe_ethdev.h | 2 +-
drivers/net/ixgbe/ixgbe_rxtx.c | 12 +-
1 - 100 of 166 matches
Mail list logo
