Hi, Jiayu
DPDK convention prefers to append the doc update with the feature patch, and
update the release note in the same patch as well.
Thanks,
Xiaolong
On 03/17, Jiayu Hu wrote:
>Signed-off-by: Jiayu Hu
>---
> doc/guides/nics/vhost.rst | 14 ++
> 1 file changed, 14 insertions(+)
>
> -Original Message-
> From: dev On Behalf Of Jiayu Hu
> Sent: Tuesday, March 17, 2020 5:21 PM
> To: dev@dpdk.org
> Cc: maxime.coque...@redhat.com; Ye, Xiaolong ;
> Wang, Zhihong ; Hu, Jiayu
> Subject: [dpdk-dev] [PATCH 2/4] net/vhost: setup vrings for DMA-
> accelerated datapath
>
>
Signed-off-by: Jiayu Hu
---
doc/guides/nics/vhost.rst | 14 ++
1 file changed, 14 insertions(+)
diff --git a/doc/guides/nics/vhost.rst b/doc/guides/nics/vhost.rst
index 912f4bd..f0d9520 100644
--- a/doc/guides/nics/vhost.rst
+++ b/doc/guides/nics/vhost.rst
@@ -25,6 +25,15 @@ Currentl
This patch accelerates large data movement in Tx operations via DMA
engines, like I/OAT, the DMA engine in Intel's processors.
Large copies are offloaded from the CPU to the DMA engine in an
asynchronous manner. The CPU just submits copy jobs to the DMA engine
and without waiting for DMA copy comp
This patch gets vrings' addresses and sets up GPA and HPA mappings
for offloading large data movement from the CPU to DMA engines in
vhost-user PMD.
Signed-off-by: Jiayu Hu
---
drivers/Makefile | 2 +-
drivers/net/vhost/Makefile| 4 +-
drivers/net/vhost/internal.h
DMA engines, like I/OAT, are efficient in moving large data
within memory. Offloading large copies in vhost side to DMA
engines can save precious CPU cycles and improve vhost
performance.
However, using the DMA engine requires to populate guest's
memory. This patch is to enable DMA-accelerated vho
In vhost-user PMD's Tx operations, where data movement is heavily involved,
performing large memory copies usually takes up a major part of CPU cycles
and becomes the hot spot. To offload expensive memory operations from the
CPU, this patch set proposes to leverage DMA engines, e.g., I/OAT, a DMA
e
> -Original Message-
> From: Stillwell Jr, Paul M
> Sent: Tuesday, March 17, 2020 02:55
> To: Zhang, Qi Z ; Wang, Haiyue ;
> dev@dpdk.org; Ye,
> Xiaolong ; Yang, Qiming ; Xing,
> Beilei
>
> Cc: Zhao1, Wei ; Wang, Haiyue ;
> Liang, Cunming
> ; Wu, Jingjing
> Subject: RE: [dpdk-dev] [PA
> -Original Message-
> From: Kevin Traynor
> Sent: Monday, March 16, 2020 18:16
> To: Li, Xiaoyun ; Zhike Wang ;
> dev@dpdk.org
> Cc: Xing, Beilei ; Zhang, Qi Z ;
> sta...@dpdk.org
> Subject: Re: [dpdk-dev] [dpdk-stable] [PATCH] net/i40e: fix X722 judgement
> when disable adminq operati
To guarantee the inter-threads visibility of the shareable domain, it
uses a lot of rte_smp_r/wmb in the service library. This patch relaxed
these barriers for service by using c11 atomic one-way barrier operations.
Signed-off-by: Phil Yang
Reviewed-by: Ruifeng Wang
Reviewed-by: Gavin Hu
---
l
The num_mapped_cores and execute_lock are synchronized with rte_atomic_XX
APIs which is a full barrier, DMB, on aarch64. This patch optimized it with
c11 atomic one-way barrier.
Signed-off-by: Phil Yang
Reviewed-by: Ruifeng Wang
Reviewed-by: Gavin Hu
Reviewed-by: Honnappa Nagarahalli
---
lib/
From: Honnappa Nagarahalli
The logic to identify if the MT unsafe service is running on another
core can return -EBUSY spuriously. In such cases, running the service
becomes costlier than using atomic operations. Assume that the
application passes the right parameters and reduces the number of
in
From: Honnappa Nagarahalli
There has possible that a MT unsafe service might get configured to
run on another core while the service is running currently. This
might result in the MT unsafe service running on multiple cores
simultaneously. Use 'execute_lock' always when the service is
MT unsafe.
The service id validation is verified in the calling function, remove
the redundant code inside the service_update function.
Fixes: 21698354c832 ("service: introduce service cores concept")
Cc: sta...@dpdk.org
Signed-off-by: Phil Yang
Reviewed-by: Honnappa Nagarahalli
---
lib/librte_eal/common
Fixes: 3cf5eb1546ed ("service: fix and refactor atomic service accesses")
Fixes: 21698354c832 ("service: introduce service cores concept")
Cc: sta...@dpdk.org
Signed-off-by: Phil Yang
Reviewed-by: Honnappa Nagarahalli
---
lib/librte_eal/common/rte_service.c | 18 +-
1 file chang
For SA outbound packets, rte_atomic64_add_return is used to generate
SQN atomically. This introduced an unnecessary full barrier by calling
the '__sync' builtin implemented rte_atomic_XX API on aarch64. This
patch optimized it with c11 atomic and eliminated the expensive barrier
for aarch64.
Signe
When compiling with clang on 32-bit platforms, we are missing copies
of 64-bit atomic functions. We can solve this by linking against
libatomic for the drivers and libs which need those atomic ops.
Signed-off-by: Phil Yang
Reviewed-by: Ruifeng Wang
Reviewed-by: Gavin Hu
---
lib/librte_eal/meso
DPDK provides generic rte_atomic APIs to do several atomic operations.
These APIs are using the deprecated __sync built-ins and enforce full
memory barriers on aarch64. However, full barriers are not necessary
in many use cases. In order to address such use cases, C language offers
C11 atomic APIs.
All these libs and drivers are built upon the eal lib. So when
compiling with clang on 32-bit platforms linking against libatomic
for the eal lib is sufficient. Remove the redundant code.
Suggested-by: Ruifeng Wang
Signed-off-by: Phil Yang
Reviewed-by: Ruifeng Wang
---
drivers/event/octeontx/m
The rarp packet broadcast flag is synchronized with rte_atomic_XX APIs
which is a full barrier, DMB, on aarch64. This patch optimized it with
c11 atomic one-way barrier.
Signed-off-by: Phil Yang
Reviewed-by: Gavin Hu
Reviewed-by: Honnappa Nagarahalli
Reviewed-by: Joyce Kong
---
lib/librte_vho
Add deprecating the generic rte_atomic_xx APIs to c11 atomic built-ins
guide and examples.
Suggested-by: Honnappa Nagarahalli
Signed-off-by: Phil Yang
Reviewed-by: Gavin Hu
---
doc/guides/prog_guide/writing_efficient_code.rst | 60 +++-
1 file changed, 59 insertions(+), 1 d
In order to deprecate the rte_atomic APIs, prevent the patches
from using rte_atomic APIs.
Signed-off-by: Phil Yang
Reviewed-by: Gavin Hu
Reviewed-by: Honnappa Nagarahalli
---
devtools/checkpatches.sh | 9 +
1 file changed, 9 insertions(+)
diff --git a/devtools/checkpatches.sh b/devto
Thanks, xiaolong.
> -Original Message-
> From: Ye, Xiaolong
> Sent: Monday, March 16, 2020 9:48 PM
> To: Liu, Yong
> Cc: maxime.coque...@redhat.com; Wang, Zhihong
> ; dev@dpdk.org
> Subject: Re: [PATCH] vhost: cache guest/vhost physical address mapping
>
> Hi, Marvin
>
> On 03/16, Mar
Added mman functions to eal exports list.
Added librte_pci support for Windows.
Signed-off-by: Pallavi Kadam
Reviewed-by: Ranjit Menon
---
lib/librte_eal/rte_eal_exports.def | 2 ++
lib/meson.build| 2 +-
2 files changed, 3 insertions(+), 1 deletion(-)
diff --git a/lib/libr
Adding sys/mman.h and mman.c on Windows for supporting
common code.
This implementation has MIT licensing.
https://github.com/witwall/mman-win32
Signed-off-by: Pallavi Kadam
Reviewed-by: Ranjit Menon
---
lib/librte_eal/windows/eal/include/sys/mman.h | 84
lib/librte_eal/windows/eal/me
Includes Windows specific EAL changes and meson changes to support
pci lib on Windows.
Added mman.c and mman.h to support common code.
These files are under MIT license and need exception.
note: license/exceptions.txt will be modified once exception is approved.
Pallavi Kadam (2):
eal: mman imp
https://bugs.dpdk.org/show_bug.cgi?id=384
Stephen Hemminger (step...@networkplumber.org) changed:
What|Removed |Added
Status|UNCONFIRMED |RESOLVED
It is possible for a packet to arrive during the configuration
process when setting up multiple queue mode. This would cause
configure to fail; fix by just ignoring receive packets while
waiting for control commands.
Add a spinlock to ensure that two control operations are not
attempted at once.
A couple of fixes for netvsc PMD.
The first is more serious than the second.
Stephen Hemminger (2):
net/netvsc: handle receive packets during multi-channel setup
net/netvsc: avoid mixing buffered and direct packets
drivers/net/netvsc/hn_ethdev.c | 1 +
drivers/net/netvsc/hn_nvs.c| 40 ++
Putting buffered and direct packets together into one request is
an unnecessary optimization. Better to split into two requests
(buffered and direct).
Signed-off-by: Stephen Hemminger
---
drivers/net/netvsc/hn_rxtx.c | 15 +++
1 file changed, 7 insertions(+), 8 deletions(-)
diff --g
On 2020-03-16 13:47, David Christensen wrote:
The include file rte_debug.h is pulled into x86 builds through the
following callchain:
lib/librte_eal/common/include/generic/rte_cycles.h:17,
lib/librte_eal/common/include/arch/x86/rte_cycles.h:13,
lib/librte_eal/common/include/arch/x86/rte_spinlock
The include file rte_debug.h is pulled into x86 builds through the
following callchain:
lib/librte_eal/common/include/generic/rte_cycles.h:17,
lib/librte_eal/common/include/arch/x86/rte_cycles.h:13,
lib/librte_eal/common/include/arch/x86/rte_spinlock.h:18,
lib/librte_eal/common/include/arch/x86/rt
All recent POWER systems, Power 8 and 9 specifically, support an IOMMU
(it can't be disabled). The functionality of the IOMMU is different
depending on whether it's running on a bare metal PowerNV system or in
a virtual environment (PowerVM LPAR or KVM/QEMU). DPDK currently
supports the IOMMU foun
Function test for Multi-function library
Signed-off-by: Mairtin o Loingsigh
---
app/test/Makefile|5 +
app/test/test_cryptodev.h|1 +
app/test/test_rawdev.c | 418 ++
app/test/test_rawdev_multi
Exposes AESNI-MB via rawdev API to allow the submission of
operations requiring error detect and other non symmetric
crypto transforms.
Signed-off-by: Mairtin o Loingsigh
---
config/common_base |5 +
drivers/raw/Makefile |2 +
> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Medvedkin, Vladimir
> Sent: Monday, March 16, 2020 7:28 PM
>
> Hi Morten,
>
>
> On 16/03/2020 14:39, Morten Brørup wrote:
> >> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Vladimir Medvedkin
> >> Sent: Monday, March 16, 2020 2:38 PM
On Mon, 16 Mar 2020 18:27:40 +
"Medvedkin, Vladimir" wrote:
> Hi Morten,
>
>
> On 16/03/2020 14:39, Morten Brørup wrote:
> >> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Vladimir Medvedkin
> >> Sent: Monday, March 16, 2020 2:38 PM
> >>
> >> Currently DPDK has a special implementati
This patch allows C++ programs to use librte_fib library routines.
Previously C++ programs were not able to link this library and programs
would fail to get linked. With this patch compilation and linking
will be successful.
Signed-off-by: Muhammad Asim Jamshed
Signed-off-by: Saikrishna Edupugant
Multi-function API allows user to chain xforms of various
types together in a single operation
Signed-off-by: Mairtin o Loingsigh
---
drivers/raw/Makefile |1 +
drivers/raw/common/Makefile|8 +
drivers/raw/common/multi_fn/Makefile
On 3/16/20 10:49 AM, David Christensen wrote:
The rte_pci.h file includes more header files than are actually needed,
which means that all users of it also include those headers. This patch
removes the unneeded headers - adding them elsewhere where other
components
were requiring them but
See my responses inline.
Paul
> -Original Message-
> From: Zhang, Qi Z
> Sent: Saturday, March 14, 2020 6:50 PM
> To: Stillwell Jr, Paul M ; Wang, Haiyue
> ; dev@dpdk.org; Ye, Xiaolong
> ; Yang, Qiming ; Xing,
> Beilei
> Cc: Zhao1, Wei ; Wang, Haiyue
> ; Liang, Cunming ; Wu,
> Jingjing
16/03/2020 18:09, Bruce Richardson:
> Static builds can take a lot of space, so reduce the number of examples
> built when doing those static builds.
>
> Signed-off-by: Bruce Richardson
> ---
> --- a/.ci/linux-build.sh
> +++ b/.ci/linux-build.sh
> +if [ "$DEF_LIB" = "static" ] ; then
> +OPTS=
Introduction of pinned external buffers doubled memory loads in the
rte_pktmbuf_prefree_seg() function. Analysis of the generated assembly
code shows unnecessary load of the pool field of the rte_mbuf structure.
Here is the snippet of the assembly for "if (!RTE_MBUF_DIRECT(m))":
Before the change t
Hi Morten,
On 16/03/2020 14:39, Morten Brørup wrote:
From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Vladimir Medvedkin
Sent: Monday, March 16, 2020 2:38 PM
Currently DPDK has a special implementation of a hash table for
4 byte keys which is called FBK hash. Unfortunately its main drawbac
Bruce Richardson writes:
> Static builds can take a lot of space, so reduce the number of examples
> built when doing those static builds.
>
> Signed-off-by: Bruce Richardson
> ---
It looks good to me. I'll try a run with Ruifeng's no-huge series and
see if I can trigger errors on my side (and
The rte_pci.h file includes more header files than are actually needed,
which means that all users of it also include those headers. This patch
removes the unneeded headers - adding them elsewhere where other components
were requiring them but not including them directly.
Fixes: c752998b5e2e (
Hi Mairtin,
> -Original Message-
> From: dev On Behalf Of Mairtin o Loingsigh
> Sent: Wednesday, March 4, 2020 9:26 AM
> To: Doherty, Declan ; akhil.go...@nxp.com
> Cc: dev@dpdk.org; O'loingsigh, Mairtin
> Subject: [dpdk-dev] [PATCH 1/2] crypto/aesni_mb: support DOCSIS AES-256
>
> This
Hi,
> -Original Message-
> From: dev On Behalf Of Trahe, Fiona
> Sent: Wednesday, March 4, 2020 1:40 PM
> To: O'loingsigh, Mairtin ; akhil.go...@nxp.com
> Cc: dev@dpdk.org
> Subject: Re: [dpdk-dev] [PATCH 2/2] test/crypto: Add AES-256 DOCSIS test
> vectors
>
> Hi Máirtin,
> Wasn't this p
On 3/14/2020 10:02 AM, Xiaoyun wang wrote:
> This patch makes IO memory allocation with socketid,
> the txq or rxq descriptor and IO resource can be allocated with
> socketid that passed by queue setup ops, which can improve
> performance for cross-numa scene.
>
> Cc: sta...@dpdk.org
> Signed-off-
On Wed, Nov 20, 2019 at 02:10:56PM -0600, Mit Matelske wrote:
> The source callback list grows infinitely when more than alarm
> is queued.
>
> This fix recognizes that an alarm interrupt in FreeBSD should never
> have more than one callback on its list, so if
> rte_intr_callback_register() is cal
Well, you're right, another way to fix the problem could be to set up the
queue size assuming the provided number
is a number of packets in queue rather than a number of mbufs in queue.
But not sure it's better, it's also important for the application/user to
know the number of mbufs that could fit
Static builds can take a lot of space, so reduce the number of examples
built when doing those static builds.
Signed-off-by: Bruce Richardson
---
.ci/linux-build.sh | 8 +++-
1 file changed, 7 insertions(+), 1 deletion(-)
diff --git a/.ci/linux-build.sh b/.ci/linux-build.sh
index d500c4c00.
When removing the extra headers from rte_pci.h stdlib should have been
removed instead of stdio, since off_t is missing for BSD builds when just
including stdlib.h
Fixes: 0dcba5256287 ("pci: remove unneeded includes in public header file")
Cc: sta...@dpdk.org
Signed-off-by: Bruce Richardson
---
On 3/16/2020 10:07 AM, Muhammad Ahmad wrote:
> From: Muhammad Ahmad
>
Hi Muhammed,
Can you please keep the patch title short, ~70 chars, and put the detail in the
commit log?
> Bugzilla ID: 225
>
> Cc: dev@dpdk.org
> Reported-by: Thomas Monjalon
> Signed-off-by: Muhammad Ahmad
> ---
> app/
> -Original Message-
> From: Kusztal, ArkadiuszX
> Sent: Friday, March 13, 2020 6:08 PM
> To: dev@dpdk.org
> Cc: akhil.go...@nxp.com; Trahe, Fiona ; Kusztal,
> ArkadiuszX
>
> Subject: [PATCH 2/2] test: add crypto aes-gcm J0 test case
>
> This patch adds crypto J0 test case to AES-GCM
> -Original Message-
> From: Kusztal, ArkadiuszX
> Sent: Friday, March 13, 2020 6:08 PM
> To: dev@dpdk.org
> Cc: akhil.go...@nxp.com; Trahe, Fiona ; Kusztal,
> ArkadiuszX
>
> Subject: [PATCH 1/2] crypto/qat: add aes-gcm J0 handling
>
> This patch adds J0 capability to Intel QuickAssi
On Thu, 6 Jun 2019 12:15:50 +
Jerin Jacob Kollanukkaran wrote:
> > -Original Message-
> > From: Matan Azrad
> > Sent: Thursday, June 6, 2019 4:22 PM
> > To: Jerin Jacob Kollanukkaran ; Adrien Mazarguil
> > ; dev@dpdk.org
> > Subject: [EXT] RE: [PATCH] [RFC] ethdev: support flow aging
Bare metal PowerNV systems include a DPDK supported IOMMU that allows
IOVA=VA support. Test for the platform type and report virtual address
support if running on a PowerNV system.
...
+
+ char *line = 0;
Nit: NULL
Fixed.
+ /* Check for a PowerNV platform */
+ while (get
If a ethdev port is in use for a sub device, then it should not
be allowed in the portmask of l3fwd.
Fixes: 5b7ba31148a8 ("ethdev: add port ownership")
Cc: ma...@mellanox.com
Cc: sta...@dpdk.org
Signed-off-by: Stephen Hemminger
---
examples/l3fwd-power/main.c | 4
1 file changed, 4 insertio
If a ethdev port is in use for a sub device, then it should not
be allowed in the portmask of application.
Fixes: 5b7ba31148a8 ("ethdev: add port ownership")
Cc: ma...@mellanox.com
Cc: sta...@dpdk.org
Signed-off-by: Stephen Hemminger
---
examples/l3fwd-acl/Makefile| 3 +++
examples/l3fwd-acl
If a ethdev port is in use for a sub device, then it should not
be allowed in the portmask of application.
Fixes: 5b7ba31148a8 ("ethdev: add port ownership")
Cc: ma...@mellanox.com
Cc: sta...@dpdk.org
Signed-off-by: Stephen Hemminger
---
examples/tep_termination/Makefile| 2 ++
examples/tep_
If a ethdev port is in use for a sub device, then it should not
be allowed in the portmask of l3fwd.
Fixes: 5b7ba31148a8 ("ethdev: add port ownership")
Cc: ma...@mellanox.com
Cc: sta...@dpdk.org
Signed-off-by: Stephen Hemminger
---
examples/l3fwd/Makefile| 3 +++
examples/l3fwd/main.c |
If a ethdev port is in use for a sub device, then it should not
be allowed in the portmask of application.
Fixes: 5b7ba31148a8 ("ethdev: add port ownership")
Cc: ma...@mellanox.com
Cc: sta...@dpdk.org
Signed-off-by: Stephen Hemminger
---
examples/l2fwd-cat/Makefile| 2 ++
examples/l2fwd-cat/
This is a simple helper function to check if device is owned
(being used as a sub-device). It is more convienent than having
applications call rte_eth_dev_owner_get and check the result.
Signed-off-by: Stephen Hemminger
---
v2 - rename the helper function and use rte_eth_dev_owner_get
lib/librt
The failsafe, bonding, and netvsc PMD use eth dev port ownership
to control sub devices. These sub devices are hidden in the
normal iteration over ports but some applications use a direct
port mask. In these cases, user may still (incorrectly) try
to directly use the sub devices.
This patch set i
Hi, Didier
First, thank you for the patch.
If we have a look at the description of rte_eth_rx_queue_count(): "Get the
number of used descriptors of a rx queue".
It means the DPDK generic descriptors, not PMD specific ones. "DPDK descriptor"
means the entity which can handle one packet.
rte_eth_
There is a non-optimal check if doorbel is needed present in the
mlx5_tx_handle_completion() function. Advancing a copy of the txq
consumer index and checking this copy with initial value causes
unnecessary memory loads and hurts the performance. It is better to
have a simple small boolean variable
Adding support for rx checksum offload. In case of wrong
checksum received (inner/outer l3/l4) it reports the
corresponding layer which has bad checksum. It also adds
rx burst function pointer hook for rx checksum offload to
event PMD.
Signed-off-by: Harman Kalra
---
drivers/event/octeontx/ssovf
From: Vamsi Attunuru
Adding rx burst function pointer hooks for vlan filter
offload in event PMD.
Signed-off-by: Vamsi Attunuru
---
drivers/event/octeontx/ssovf_worker.c | 38 +++
drivers/event/octeontx/ssovf_worker.h | 9 +++
drivers/net/octeontx/octeontx_rxtx.h
Adding macro based framework to hook dequeue/enqueue function
pointers to the appropriate function based on rx/tx offloads.
Signed-off-by: Harman Kalra
---
drivers/event/octeontx/ssovf_evdev.c | 36
drivers/event/octeontx/ssovf_evdev.h | 24 +--
drivers/event/octeontx/ssovf_worker.c | 2
Adding support for multi segment to the eventdev PMD.
Signed-off-by: Harman Kalra
---
drivers/event/octeontx/ssovf_evdev.c | 33 +++---
drivers/event/octeontx/ssovf_evdev.h | 13
drivers/event/octeontx/ssovf_worker.c | 90 ---
drivers/event/octeontx/ssovf_worke
Since event-octeontx PMD and net-octeontx PMD works very
tightly, so this patchset implements the event-octeontx
side changes to support new features added to net-octeontx
PMD.
This patchset is based on:
[1]
https://patches.dpdk.org/cover/66691/
Depends-on: series-8923
Harman Kalra (3):
event/
The vDPA device offloads all the datapath of the vhost device to the HW
device.
In order to expose to the user traffic information this patch introduce
new API to get traffic statistics per virtio queue.
The statistics are taken directly from the vDPA driver managing the HW
device.
Signed-off-by
On Mon, Mar 16, 2020 at 10:13:23AM -0400, Aaron Conole wrote:
> David Marchand writes:
>
> > On Fri, Mar 13, 2020 at 2:04 PM Aaron Conole wrote:
> >>
> >> Aaron Conole writes:
> >>
> >> > Ruifeng Wang writes:
> >> >
> >> >> For environments (such as containers) where hugetlbfs are not availabl
> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Vladimir Medvedkin
> Sent: Monday, March 16, 2020 2:38 PM
>
> Currently DPDK has a special implementation of a hash table for
> 4 byte keys which is called FBK hash. Unfortunately its main drawback
> is that it only supports 2 byte values.
> T
16/03/2020 12:29, Bruce Richardson:
> The rte_pci.h file includes more header files than are actually needed,
> which means that all users of it also include those headers. This patch
> removes the unneeded headers - adding them elsewhere where other components
> were requiring them but not includi
14/03/2020 00:38, Dmitry Kozlyuk:
> > I suggest this change (I can send a patch fixing the issue in other .h
> > files):
> >
> > +/*
> > + * RTE_TOOLCHAIN_GCC is true if the target is built with GCC,
> > + * while a host application (like pmdinfogen) may have another compiler.
> > + * RTE_CC_IS_GN
16/03/2020 13:04, Thomas Monjalon:
> RTE_TOOLCHAIN_* macros are defining the target compiler.
> Some API may be used in a host application like pmdinfogen.
> That's why the the public headers should check the effective compiler
> in use instead of the target compiler.
>
> Detecting the compiler wi
David Marchand writes:
> On Fri, Mar 13, 2020 at 2:04 PM Aaron Conole wrote:
>>
>> Aaron Conole writes:
>>
>> > Ruifeng Wang writes:
>> >
>> >> For environments (such as containers) where hugetlbfs are not available,
>> >> some unit tests can be run with 'no-huge' option.
>> >>
>> >> fast-test
Hi Ori,
Yes, please go ahead with the patch.
Thanks,
Xiang
On Mon, Mar 16, 2020 at 01:49:51PM +, Ori Kam wrote:
> Hi Wang,
>
> PSB, if you don't have any objections and other comments,
> I will start working on the class and will address all of this thread
> comments
> in the v1 patch,
>
Hi, Marvin
On 03/16, Marvin Liu wrote:
>If Tx zero copy enabled, gpa to hpa mapping table is updated one by
>one. This will harm performance when guest memory backend using 2M
>hugepages. Now add cached mapping table which will sorted by using
>sequence. Address translation will first check cached
Hi Wang,
PSB, if you don't have any objections and other comments,
I will start working on the class and will address all of this thread comments
in the v1 patch,
Thanks,
Ori
> -Original Message-
> From: Wang Xiang
> Sent: Monday, March 16, 2020 10:48 PM
> To: Ori Kam
> Cc: jer...@m
Hi Xiaoyun Li ,
With changes you suggested ,Testpmd works fine on my setup.
But With my own application, the port is detected properly, the queue setup to
NIC also does not give any error.
But my application is not getting any packets on the rx burst polls.
Any suggestions on what is the best way
Use dwk hash table as a placeholder for SPI_ONLY sa rules
instead of current cuckoo hash to increase lookup performance.
Signed-off-by: Vladimir Medvedkin
---
This patch depends on https://patches.dpdk.org/patch/66712/
lib/librte_ipsec/ipsec_sad.c | 119 +
Currently DPDK has a special implementation of a hash table for
4 byte keys which is called FBK hash. Unfortunately its main drawback
is that it only supports 2 byte values.
The new implementation called DWK (double word key) hash
supports 8 byte values, which is enough to store a pointer.
It woul
DWK hash is a Double Word Key(uint32_t) hash table.
The value is uint64_t.
This table is hash function agnostic so user must provide
precalculated hash signature for add/delete/lookup operations.
Signed-off-by: Vladimir Medvedkin
---
lib/Makefile | 2 +-
lib/librte_hash
Add performance tests for rte_dwk_hash.
Signed-off-by: Vladimir Medvedkin
---
app/test/test_hash_perf.c | 81 +++
1 file changed, 81 insertions(+)
diff --git a/app/test/test_hash_perf.c b/app/test/test_hash_perf.c
index a438eae..f616af1 100644
--- a/a
Add autotests for rte_dwk_hash library
Signed-off-by: Vladimir Medvedkin
---
app/test/Makefile| 1 +
app/test/meson.build | 1 +
app/test/test_dwk_hash.c | 229 +++
3 files changed, 231 insertions(+)
create mode 100644 app/test/test_dw
Hi Kiran,
> -Original Message-
> From: kirankum...@marvell.com
> Sent: Tuesday, March 10, 2020 6:06 PM
> To: Ori Kam ; Wenzhuo Lu ;
> Jingjing Wu ; Bernard Iremonger
> ; John McNamara
> ; Marko Kovacevic
> ; Thomas Monjalon ;
> Ferruh Yigit ; Andrew Rybchenko
>
> Cc: dev@dpdk.org; Kiran
Hi Ori,
On Mon, Mar 16, 2020 at 09:09:06AM +, Ori Kam wrote:
> Hi Xiang,
>
> > -Original Message-
> > From: Wang Xiang
> > Sent: Monday, March 16, 2020 3:26 AM
> > To: Ori Kam
> > Cc: jer...@marvell.com; dev@dpdk.org; pbhagavat...@marvell.com; Shahaf
> > Shuler ; hemant.agra...@nxp.
On 3/14/2020 6:16 PM, Kumar, Ravi1 wrote:
> [AMD Public Use]
<...>
>
>> From: Amaranath Somalapuram
>>
>> Adding API for axgbe_rxq_info_get, axgbe_txq_info_get
>>
>> Signed-off-by: Amaranath Somalapuram
>
> For series,
> Acked-by: Ravi Kumar
>
Series applied to dpdk-next-net/master, thanks.
Ruifeng Wang writes:
>> -Original Message-
>> From: David Marchand
>> Sent: Friday, March 13, 2020 23:54
>> To: Aaron Conole
>> Cc: Ruifeng Wang ; Michael Santana
>> ; Bruce Richardson
>> ; Ananyev, Konstantin
>> ; Cristian Dumitrescu
>> ; Wang, Yipeng1
>> ; Gobriel, Sameh ;
>> dev ; Bu
Add support for CPU crypto mode by introducing required handler.
Signed-off-by: Konstantin Ananyev
---
doc/guides/cryptodevs/aesni_mb.rst| 3 +
doc/guides/cryptodevs/features/aesni_mb.ini | 1 +
.../crypto/aesni_mb/aesni_mb_pmd_private.h| 5 +-
drivers/crypto/aesni_mb/rte
This patch adds ability to run unit tests in cpu crypto mode
for AESNI MB cryptodev.
Signed-off-by: Konstantin Ananyev
---
app/test/test_cryptodev.c | 146 ++
1 file changed, 115 insertions(+), 31 deletions(-)
diff --git a/app/test/test_cryptodev.c b/app/test
Add support for CPU crypto API into aesni_mb PMD
and extend cryptodev UT to cover this new functionality.
Konstantin Ananyev (2):
crypto/aesni_mb: support CPU crypto
test/crypto: add CPU crypto mode for AESNI MB
app/test/test_cryptodev.c | 146 +--
doc/guides/cryptode
16/03/2020 13:57, Trahe, Fiona:
> From: Kusztal, ArkadiuszX
> > > > > The patch we're working on will provide two versions of
> > > > > rte_cryptodev_info_get(), both call the same PMD function from the
> > > dev_ops info_get fn ptr.
> > > > > The default version operates s as normal, the 19.11 ve
Hi,
> -Original Message-
> From: Kusztal, ArkadiuszX
> Sent: Thursday, February 13, 2020 2:51 PM
> To: Trahe, Fiona ; Thomas Monjalon
>
> Cc: David Marchand ; nhor...@tuxdriver.com;
> bl...@debian.org;
> ktray...@redhat.com; Ray Kinsella ; dev@dpdk.org; Akhil Goyal
> ; Yigit, Ferruh ;
One of the reasons to destroy a flow is the fact that no packet matches the
flow for "timeout" time.
For example, when TCP\UDP sessions are suddenly closed.
Currently, there is no any dpdk mechanism for flow aging and the
applications use there own ways to detect and destroy aged-out flows.
This
On 3/16/2020 3:53 AM, Kumar, Ravi1 wrote:
<...>>> From: Amaranath Somalapuram
>>
>> Adding api for flow_ctrl_get and flow_ctrl_set.
>> By default axgbe driver flow control is disabled.
>> Adding dpdk flow control to set water high and low.
>>
>> Signed-off-by: Amaranath Somalapuram
>
> For series
This patch set adds handling of mixed hash-cipher algorithms
available on GEN2 QAT in particular firmware versions.
Also the documentation is updated to show the mixed crypto
algorithms are supported on QAT GEN2.
v2:
* minor fixes and improvements
v3:
* include missing header file
Adam Dybkowski
1 - 100 of 150 matches
Mail list logo
