It is not strictly -march only (-mfpu as well).
08/11/2021 06:33, Ruifeng Wang:
> From: Juraj Linkeš
> >
> > Aarch32 config got overlooked when splitting march in a previous parch.
s/parch/patch/
> > Fixes: 95e0f23022a3 ("config/arm: split -march into arch and features")
blank line missing he
From: Sahithi Singam
At present, there are no spinlocks around register command access.
This resulted in a race condition when two threads running on
two different cores invoked link_update function at the same time
to get link status. Due to this race condition, one of the threads
reported false
On 11/4/21 11:19, Jiayu Hu wrote:
For the packet using multiple descriptors, the flag of first
descriptor cannot be updated until finishing updating the flag
of remaining descriptors. However, if the packet's descriptor
index is wrapped, the first descriptor's flag is updated earlier
than the
28/10/2021 20:17, Matan Azrad:
> From: Raja Zidane
> > 0x20 reserved bytes were missed in the HCA cap PRM structure before the
> > newly
> > added fields for MMO QP capabilities, that caused reading MMO QP caps
> > incorrectly.
> > The QP extension valid bit was not set in the QP creation for MMO
>From d2f21802f26036e12db29b2544217a44a748a7ee Mon Sep 17 00:00:00 2001
From: Changsheng Wu
Date: Mon, 8 Nov 2021 16:12:36 +0800
Subject: [PATCH] test_compressdev:fix test case skipping due to missing device
init
The testsuite_setup function in the compressdev_autotest test case, the
rte_compres
On 11/7/2021 9:35 PM, Thomas Monjalon wrote:
Hi,
It seems compilation time of drivers/event/cnxk is getting very long.
Please could you look at it?
ack, I also recognized it. Various builds all stuck on same a few files.
On 11/8/2021 7:24 AM, Wang, Jie1X wrote:
-Original Message-
From: Yigit, Ferruh
Sent: Saturday, November 6, 2021 12:24 AM
To: Wang, Jie1X ; dev@dpdk.org
Cc: Zhang, Yuying ; Li, Xiaoyun
; Yang, SteveX ; Guo, Junfeng
; Zhang, Qi Z
Subject: Re: [dpdk-dev] [PATCH v2] app/testpmd: fix set
04/11/2021 13:49, Raja Zidane:
> fixes series.
> for vdpa dependent on:
> https://patches.dpdk.org/project/dpdk/patch/20211027082221.693957-1-xuemi...@nvidia.com/
>
> Raja Zidane (4):
> common/mlx5: fix overflows in DevX queues size calculations
> crypto/mlx5: fix driver destroy before the con
08/11/2021 09:53, Rongwei Liu:
> Add option "policy-mtr" to indicate if meter creation will include policy
> or not. Meter creation will keep the same without it.
>
> With "policy-mtr", the policy is introduced. API create_meter_policy
> is to create a policy. API create_meter_rule will use it to
> -Original Message-
> From: fengchengwen
> Sent: Tuesday, November 2, 2021 3:01 PM
> To: Gagandeep Singh ; tho...@monjalon.net;
> dev@dpdk.org
> Cc: Nipun Gupta
> Subject: Re: [dpdk-dev] [PATCH v2 5/6] dma/dpaa: support DMA operations
>
> On 2021/11/1 16:51, Gagandeep Singh wrote:
> >
This series support DMA driver for NXP
1046A and 1043A SoCs.
v2-change-log:
* series rebased with latest dma driver
v3-change-log:
* support statistics.
* replaced local endianness conversion functions with rte_*.
* improved submit API logic.
* Handled all comments given by fengchengwen
Gagandee
The DPAA DMA driver is an implementation of the dmadev APIs,
that provide means to initiate a DMA transaction from CPU.
The initiated DMA is performed without CPU being involved
in the actual DMA transaction. This is achieved via using
the QDMA controller of DPAA SoC.
Signed-off-by: Gagandeep Sin
This patch add device initialisation functionality.
Signed-off-by: Gagandeep Singh
---
drivers/dma/dpaa/dpaa_qdma.c | 456 ++-
drivers/dma/dpaa/dpaa_qdma.h | 236 ++
2 files changed, 690 insertions(+), 2 deletions(-)
create mode 100644 drivers/dma
This patch supports DPAA DMA driver logs.
Signed-off-by: Gagandeep Singh
---
drivers/dma/dpaa/dpaa_qdma.c | 22 ---
drivers/dma/dpaa/dpaa_qdma_logs.h | 46 +++
2 files changed, 64 insertions(+), 4 deletions(-)
create mode 100644 drivers/dma/dpaa/dpaa
This patch support basic DMA operations which includes
device capability and channel setup.
Signed-off-by: Gagandeep Singh
---
drivers/dma/dpaa/dpaa_qdma.c | 204 +++
drivers/dma/dpaa/dpaa_qdma.h | 6 ++
2 files changed, 210 insertions(+)
diff --git a/drivers/d
This patch support copy, submit, completed and
completed status functionality of DMA driver.
Signed-off-by: Gagandeep Singh
---
drivers/dma/dpaa/dpaa_qdma.c | 334 +++
drivers/dma/dpaa/dpaa_qdma.h | 4 +
2 files changed, 338 insertions(+)
diff --git a/drivers/d
This patch support DMA read and reset statistics
operations
Signed-off-by: Gagandeep Singh
---
drivers/dma/dpaa/dpaa_qdma.c | 51 +++-
drivers/dma/dpaa/dpaa_qdma.h | 1 +
2 files changed, 51 insertions(+), 1 deletion(-)
diff --git a/drivers/dma/dpaa/dpaa_qdma.c
This patch adds DPAA DMA user guide.
Signed-off-by: Gagandeep Singh
---
MAINTAINERS | 1 +
doc/guides/dmadevs/dpaa.rst | 60 +
2 files changed, 61 insertions(+)
create mode 100644 doc/guides/dmadevs/dpaa.rst
diff --git a/MAINTAINERS b/MAINTA
The pointer passed to the rq_ctx and sq_ctx functions was the address
of qctx. Instead of that qctx should be passed. This patch fixes this.
This patch also resolves warning observed with gcc 12 compiler.
log:
../drivers/common/cnxk/cnxk_telemetry.h:12:38: warning: array subscript
‘struct n
> > Added support to create flows with priority attribute set randomly between
> > 0 and a user supplied maximum value. This is useful to measure performance
> > on NICs which may have to rearrange flows to honor flow priority.
> >
> > Removed the lower limit of 10 flows per batch.
> >
> > Si
> On 11/5/2021 9:28 AM, Andrew Rybchenko wrote:
> > On 11/5/21 12:13 PM, Ferruh Yigit wrote:
> >> On 11/3/2021 1:57 PM, Vijay Srivastava wrote:
> >>> diff --git a/drivers/vdpa/sfc/sfc_vdpa.c
> >>> b/drivers/vdpa/sfc/sfc_vdpa.c new file mode 100644 index
> >>> 000..f087944
> >>> --- /dev/null
>
08/11/2021 10:23, Rongwei Liu:
> Add meter policy support and provide options to specify
> green/yellow/red corlor actions and cir/cbs/ebs values.
>
> v2: add option to specify green color actions.
> v3: support yellow color action and ebs options.
> v4: rebase on top of master-net-mlx.
> v5: fix
08/11/2021 10:07, Gagandeep Singh:
> This patch adds DPAA DMA user guide.
Please I prefer having doc introduced along other patches.
Each time a patch introduce a feature, the doc should be updated.
08/11/2021 10:07, Gagandeep Singh:
> This patch supports DPAA DMA driver logs.
That's a strange patch.
The log macros should be introduced in the first patch.
And the error messages should come with the rest of the code (in patch 2?)
08/11/2021 10:07, Gagandeep Singh:
> This patch adds DPAA DMA user guide.
>
> Signed-off-by: Gagandeep Singh
> ---
> MAINTAINERS | 1 +
> doc/guides/dmadevs/dpaa.rst | 60 +
> 2 files changed, 61 insertions(+)
Please do not forget the doc ind
08/11/2021 10:39, Rongwei Liu:
> > 08/11/2021 10:23, Rongwei Liu:
> > > Add meter policy support and provide options to specify
> > > green/yellow/red corlor actions and cir/cbs/ebs values.
> > >
> > > v2: add option to specify green color actions.
> > > v3: support yellow color action and ebs opti
Since two components wants to know if the jansson library is available,
move it to config/.
Signed-off-by: David Marchand
---
app/test-pmd/meson.build | 9 -
config/meson.build | 5 +
lib/metrics/meson.build | 6 ++
3 files changed, 11 insertions(+), 9 deletions(-)
diff -
08/11/2021 10:58, Rongwei Liu:
> --- a/doc/guides/tools/flow-perf.rst
> +++ b/doc/guides/tools/flow-perf.rst
> @@ -383,3 +383,6 @@ Actions:
> * ``--meter``
> Add meter action to all flows actions.
> Currently, 1 meter profile -> N meter rules -> N rte flows.
> +
> +*
The unit test code should depend on the pcapng library.
Fixes: 7a944656b33f ("test/pcapng: test pcapng library")
Signed-off-by: David Marchand
---
app/test/meson.build | 5 -
1 file changed, 4 insertions(+), 1 deletion(-)
diff --git a/app/test/meson.build b/app/test/meson.build
index a12ea
The RTE_PORT_PCAP variable is used to signal libpcap availability,
though its name seems to refer to pcap support in the port library.
Prefer a generic name and add explicit link dependencies where needed.
Fixes: 7a944656b33f ("test/pcapng: test pcapng library")
Fixes: 2eccf6afbea9 ("bpf: add func
08/11/2021 10:58, Rongwei Liu:
> Change meter-cir option to meter-profile to cover CIR/CBS/EBS all.
>
> The usage is as below:
> --meter-profile=N1,N2,N3 default value is 125 156250 0.
>
> Signed-off-by: Rongwei Liu
> Acked-by: Wisam Monther
> ---
> --- a/doc/guides/tools/flow-perf.rst
> ++
The Kni kthreads seem to be re-scheduled at a granularity of roughly
1 millisecond right now, which seems to be insufficient for performing
tests involving a lot of control plane traffic.
Even if KNI_KTHREAD_RESCHEDULE_INTERVAL is set to 5 microseconds, it
seems that the existing code cannot resch
Ping again. Stephen?
12/05/2021 21:10, Thomas Monjalon:
> Ping for v3
>
> 12/02/2021 01:21, Honnappa Nagarahalli:
> >
> >
> > >
> > > 14/01/2021 17:55, Stephen Hemminger:
> > > > The implementation of reader/writer locks in DPDK (from first release)
> > > > is simple and fast. But it can lead
Hello Thomas,
The testing with dpdk 21.11-rc1 from Red Hat looks good. We tested below 18
scenarios and all got PASS on RHEL8:
(1)Guest with device assignment(PF) throughput testing(1G hugepage size):
PASS
(2)Guest with device assignment(PF) throughput testing(2M hugepage size) :
PASS
(3)Guest wi
03/11/2021 13:59, Ferruh Yigit:
> Previously used 'random_ether_addr()' API is removed in upstream kernel
> with commit
> Commit ba530fea8ca1 ("ethernet: remove random_ether_addr()")
>
> Replacement API 'eth_random_addr()' is around since v3.6 [1], so
> simply switching to this API without any ver
24/06/2021 13:33, Ferruh Yigit:
> On 4/23/2021 9:12 AM, Min Hu (Connor) wrote:
> > From: Chengwen Feng
> >
> > Some drivers may return errcode when switch allmulticast mode, so it's
> > necessary to check the return code.
> >
> > Fixes: b34801d1aa2e ("kni: support allmulticast mode set")
> > Cc:
On Tue, 2021-10-12 at 14:17 +, Ben Magistro wrote:
> The i40evf driver is not initializing the eth_dev attribute which
> can result in a nullptr dereference. Changes were modeled after the
> iavf_dev_init() per suggestion from the mailing list[1].
>
> [1] https://mails.dpdk.org/archives/dev/20
Hi Thomas, Ferruh,
We need to further split Rx/Tx functions in both net/cnxk and event/cnxk to
enable more parallelism.
This is planned for the next release.
Thanks,
Pavan.
>-Original Message-
>From: Ferruh Yigit
>Sent: Monday, November 8, 2021 2:26 PM
>To: Thomas Monjalon ; Pavan Nikh
On Mon, 2021-09-06 at 15:00 +0800, Qiming Chen wrote:
> The RTE_ALIGN macro is aligned upwards. If the buf_size variable is not
> aligned with 1 << I40E_RXQ_CTX_DBUFF_SHIFT, the rx_buf_len is larger than
> the actual mbuf memory after the operation. When receiving the packet, if
> the packet is lar
Move internal reassembly structures into new private
header 'ip_reassembly.h'.
Signed-off-by: Konstantin Ananyev
---
lib/ip_frag/ip_frag_common.h | 1 +
lib/ip_frag/ip_reassembly.h | 89
lib/ip_frag/rte_ip_frag.h| 74 +-
3 fi
On Fri, Nov 5, 2021 at 9:40 PM David Christensen
wrote:
>
> Enable Github Actions to cross-compile code for POWER systems.
>
> Signed-off-by: David Christensen
> ---
> .ci/linux-build.sh | 6 +-
> .github/workflows/build.yml | 15 ++-
> config/p
Hi,
I wanted to ask about the current state of DPDK@armhf (not arm64, that
seems fine AFAICS).
Since there are too many arms today, I mean armhf as in [0].
What I see when building DPDK 21.11 is
2973 ../config/meson.build:364:1: ERROR: Problem encountered: Number
of CPU cores not specified.
Right
The testsuite_setup function in the compressdev_autotest test case,
the rte_compressdev_count() return 0 due to the lack of device init.
It is considered that there is no equitment to skip execution.
So add rte_vdev_init init compress_zlib device.
Signed-off-by: Changsheng Wu
---
app/test/te
The testsuite_setup function in the compressdev_autotest test case,
the rte_compressdev_count() return 0 due to the lack of device init.
It is considered that there is no equitment to skip execution.
So add rte_vdev_init init compress_zlib device.
Signed-off-by: Changsheng Wu
---
app/test/te
On 11/1/2021 9:56 AM, Dmitry Kozlyuk wrote:
Routine to lookup LKey on Rx was assuming that the mbuf address
always belongs to a single mempool: the one associated with an RxQ
or the MPRQ mempool. This assumption is false for split buffers case.
A wrong LKey was looked up, resulting in completion
On 11/8/2021 1:10 PM, Ferruh Yigit wrote:
On 11/1/2021 9:56 AM, Dmitry Kozlyuk wrote:
Routine to lookup LKey on Rx was assuming that the mbuf address
always belongs to a single mempool: the one associated with an RxQ
or the MPRQ mempool. This assumption is false for split buffers case.
A wrong L
This patch defines ASAN_SHADOW_OFFSET for arm64 according to the ASan
documentation. This offset should cover all arm64 VMAs supported by
ASan.
Signed-off-by: Volodymyr Fialko
---
config/meson.build | 2 +-
doc/guides/prog_guide/asan.rst | 2 +-
lib/eal/common/malloc_elem.h | 3 +++
Konstantin Ananyev (2):
ip_frag: hide internal structures
ip_frag: add namespace
doc/guides/rel_notes/release_21_11.rst | 3 +
examples/ip_reassembly/main.c | 2 +-
examples/ipsec-secgw/ipsec-secgw.c | 2 +-
lib/ip_frag/ip_frag_common.h | 1 +
lib/ip_frag/ip_reassem
Move internal reassembly structures into new private
header 'ip_reassembly.h'.
Signed-off-by: Konstantin Ananyev
---
lib/ip_frag/ip_frag_common.h | 1 +
lib/ip_frag/ip_reassembly.h | 89
lib/ip_frag/rte_ip_frag.h| 74 +-
3 fi
Update public macros to have RTE_IP_FRAG_ prefix.
Remove obsolete macro.
Update DPDK components to use new names.
Signed-off-by: Konstantin Ananyev
---
doc/guides/rel_notes/release_21_11.rst | 3 +++
examples/ip_reassembly/main.c | 2 +-
examples/ipsec-secgw/ipsec-secgw.c | 2 +-
On Mon, Nov 8, 2021 at 2:46 PM Volodymyr Fialko wrote:
>
> This patch defines ASAN_SHADOW_OFFSET for arm64 according to the ASan
> documentation. This offset should cover all arm64 VMAs supported by
> ASan.
>
> Signed-off-by: Volodymyr Fialko
> ---
> config/meson.build | 2 +-
> doc/
On 11/6/2021 1:42 AM, Min Hu (Connor) wrote:
This patch set contains refactor patches and code check patches.
Chengwen Feng (1):
net/hns3: remove PF/VF duplicate code
Huisong Li (7):
net/hns3: fix the shift of DMA address in Rx/Tx queue
net/hns3: remove a redundant function declaration
The API could return errors. Add error checking for the same.
Fixes: b3bbd9e5f265 ("cryptodev: support device independent sessions")
Cc: slawomirx.mrozow...@intel.com
Signed-off-by: Anoob Joseph
---
app/test/test_cryptodev.c | 116 --
1 file changed,
NULL cipher is used for validating auth only cases. With out of place
processing, validating plain text should not be done as the PMD is only
expected to update auth data.
Signed-off-by: Anoob Joseph
---
app/test/test_cryptodev.c | 17 +
1 file changed, 17 insertions(+)
diff --g
> > > > > Current mempool per core cache implementation is based
> > > > > on
> > > > > pointer
> > > > > For most architectures, each pointer consumes 64b
> > > > > Replace
> > it
> > > > > with
> > > > > index-based implementation, where in each b
On 11/5/2021 9:54 PM, Ivan Malov wrote:
Ivan Malov (5):
common/sfc_efx/base: refine adding encap action to a set
common/sfc_efx/base: refine adding count action to a set
common/sfc_efx/base: factor out no-op helper functions
common/sfc_efx/base: support adding dec. TTL action to a set
> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Honnappa
> Nagarahalli
> Sent: Monday, 8 November 2021 16.29
>
>
>
> > > > > > Current mempool per core cache implementation is
> based
> > > > > > on
> > > > > > pointer
> > > > > > For most architectures, each p
> >
> > > > > > > Current mempool per core cache implementation is
> > based
> > > > > > > on
> > > > > > > pointer
> > > > > > > For most architectures, each pointer consumes 64b
> > > > > > > Replace
> > > > it
> > > > > > > with
> > > > > > > inde
On Thu, Oct 28, 2021 at 4:15 PM Anatoly Burakov
wrote:
>
> Currently, when code is running on FreeBSD or Windows,, there is no way
> to distinguish between a geniune error and a "VFIO is unsupported"
> error. Fix the dummy implementations to also set the rte_errno flag.
>
> Cc: sta...@dpdk.org
>
The i40evf driver is not initializing the eth_dev attribute which
can result in a nullptr dereference. Changes were modeled after the
iavf_dev_init() per suggestion from the mailing list[1] and
i40evf_init_vf().
[1] https://mails.dpdk.org/archives/dev/2021-August/217251.html
Rebased on v20.11.3.
> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Honnappa
> Nagarahalli
> Sent: Monday, 8 November 2021 16.46
>
>
> > >
> > > > > > > > Current mempool per core cache implementation is
> > > based
> > > > > > > > on
> > > > > > > > pointer
> > > > > > > > For mos
On 10/25/2021 7:39 AM, Min Hu (Connor) wrote:
From: Huisong Li
This patch removes unused "rte_eth_bond.h" header file.
Signed-off-by: Huisong Li
Signed-off-by: Min Hu (Connor)
Fixes: 2950a769315e ("bond: testpmd support")
Cc: sta...@dpdk.org
Reviewed-by: Ferruh Yigit
Only for t
08/11/2021 19:57, eagost...@nvidia.com:
> Elena Agostini (6):
> gpudev: introduce GPU device class library
> gpudev: add memory API
> gpudev: add memory barrier
> gpudev: add communication flag
> gpudev: add communication list
> doc: add CUDA example in GPU guide
>
> Thomas Monjalon (3
On Tue, Nov 2, 2021 at 8:34 AM Slava Ovsiienko wrote:
>
> > -Original Message-
> > From: Harman Kalra
> > Sent: Monday, November 1, 2021 19:54
> > To: dev@dpdk.org; Matan Azrad ; Slava Ovsiienko
> >
> > Cc: david.march...@redhat.com; john.mcnam...@intel.com; Harman Kalra
> >
> > Subject
On Mon, Nov 8, 2021 at 7:16 PM Volodymyr Fialko wrote:
>
> This patch defines ASAN_SHADOW_OFFSET for arm64 according to the ASan
> documentation. This offset should cover all arm64 VMAs supported by
> ASan.
>
> Signed-off-by: Volodymyr Fialko
++ Arm maintainers
Prefer to change the subject to e
On Mon, Nov 8, 2021 at 9:34 PM Morten Brørup wrote:
>
> > From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Honnappa
> > Nagarahalli
> > Sent: Monday, 8 November 2021 16.46
> >
> >
> > > >
> > > > > > > > > Current mempool per core cache implementation is
> > > > based
> > > > > > > >
On Mon, 8 Nov 2021 11:09:18 +0100
David Marchand wrote:
> The RTE_PORT_PCAP variable is used to signal libpcap availability,
> though its name seems to refer to pcap support in the port library.
> Prefer a generic name and add explicit link dependencies where needed.
>
> Fixes: 7a944656b33f ("t
On Tue, Oct 19, 2021 at 1:52 PM David Marchand
wrote:
> On Tue, Oct 19, 2021 at 12:42 PM Maciej Szwed wrote:
> >
> > We should call read() on RTE_INTR_HANDLE_VFIO_REQ event
> > to confirm that event.
>
> Fixes: 0eb8a1c4c786 ("vfio: add request notifier interrupt")
Cc: sta...@dpdk.org
> > Signed-
On Mon, Nov 8, 2021 at 3:27 PM Dmitry Kozlyuk wrote:
>
> Hi David,
>
> > -Original Message-
> > From: David Marchand
> [...]
> > > > - finegrained control of hugepage files, but it has the drawback of
> > > > imposing primary/secondary run with the same options.
> > > > The second part
This patch adds a comment for RTE_HASH_BUCKET_ENTRIES
explaining why a particular value was chosen.
Signed-off-by: Vladimir Medvedkin
---
lib/hash/rte_cuckoo_hash.h | 8 +++-
1 file changed, 7 insertions(+), 1 deletion(-)
diff --git a/lib/hash/rte_cuckoo_hash.h b/lib/hash/rte_cuckoo_hash.h
Currently, programmer's guide for the FIB library is missing.
This commit adds it.
Signed-off-by: Vladimir Medvedkin
---
doc/guides/prog_guide/fib_lib.rst | 139 +
doc/guides/prog_guide/img/dir_24_8_alg.svg | 136
doc/guides/prog_guide/index.rst
Currently, programmer's guide for the RIB library is missing.
This commit adds it.
Signed-off-by: Vladimir Medvedkin
---
doc/guides/prog_guide/img/rib_internals.svg | 148 +
doc/guides/prog_guide/img/rib_pic.svg | 152 +
doc/guides/prog_guide/index.rst
Enable Github Actions to cross-compile code for POWER systems.
Signed-off-by: David Christensen
Reviewed-by: David Marchand
---
v2 - Changed cross compile filename to be consistent with ARM
.ci/linux-build.sh | 6 +-
.github/workflows/build.yml
On Thu, 4 Nov 2021 02:01:28 +
wrote:
> +/* Single entry of the memory list */
> +struct mem_entry {
> + CUdeviceptr ptr_d;
> + void *ptr_h;
> + size_t size;
> + struct rte_gpu *dev;
> + CUcontext ctx;
Not sure where these types CUdeviceptr and CUcontext are coming
from, b
> -Original Message-
> From: Ferruh Yigit
> Sent: Wednesday, October 27, 2021 7:49 PM
> To: Apeksha Gupta ;
> david.march...@redhat.com; andrew.rybche...@oktetlabs.ru
> Cc: dev@dpdk.org; Sachin Saxena ; Hemant
> Agrawal
> Subject: [EXT] Re: [dpdk-dev] [PATCH v6 1/5] net/enetfec: introdu
> Raja Zidane (4):
> common/mlx5: fix overflows in DevX queues size calculations
> crypto/mlx5: fix driver destroy before the configuration
> crypto/mlx5: fix the queue size configuration
> common/mlx5: fix RQ size configuration in QP create
Applied, thanks.
> -Original Message-
> From: Ferruh Yigit
> Sent: Wednesday, October 27, 2021 7:52 PM
> To: Apeksha Gupta ;
> david.march...@redhat.com; andrew.rybche...@oktetlabs.ru;
> ferruh.yi...@intel.com
> Cc: dev@dpdk.org; Sachin Saxena ; Hemant
> Agrawal
> Subject: [EXT] Re: [dpdk-dev] [PATCH v6
> -Original Message-
> From: Ferruh Yigit
> Sent: Wednesday, October 27, 2021 7:53 PM
> To: Apeksha Gupta ; david.march...@redhat.com;
> andrew.rybche...@oktetlabs.ru; ferruh.yi...@intel.com
> Cc: dev@dpdk.org; Sachin Saxena ; Hemant Agrawal
>
> Subject: [EXT] Re: [dpdk-dev] [PATCH v6 3
> -Original Message-
> From: Ferruh Yigit
> Sent: Wednesday, October 27, 2021 7:56 PM
> To: Apeksha Gupta ; david.march...@redhat.com;
> andrew.rybche...@oktetlabs.ru; ferruh.yi...@intel.com
> Cc: dev@dpdk.org; Sachin Saxena ; Hemant Agrawal
>
> Subject: [EXT] Re: [dpdk-dev] [PATCH v6 4
On Mon, 8 Nov 2021 18:39:36 +
Elena Agostini wrote:
> > From: Stephen Hemminger
> > Date: Monday, 8 November 2021 at 19:35
> > To: Elena Agostini
> > Cc: dev@dpdk.org
> > Subject: Re: [dpdk-dev] [PATCH v2 1/1] gpu/cuda: introduce CUDA driver
> > External email: Use caution opening links or
On Tue, 5 Oct 2021 22:49:05 +
wrote:
> From: Elena Agostini
>
> This is the CUDA implementation of the gpudev library.
> Funcitonalities implemented through CUDA Driver API are:
>
> - Device probe and remove
> - Manage device memory allocations
> - Register/unregister external CPU memory i
> -Original Message-
> From: Ferruh Yigit
> Sent: Thursday, November 4, 2021 11:54 PM
> To: Apeksha Gupta ; david.march...@redhat.com;
> andrew.rybche...@oktetlabs.ru
> Cc: dev@dpdk.org; Sachin Saxena ; Hemant Agrawal
>
> Subject: [EXT] Re: [PATCH v7 1/5] net/enetfec: introduce NXP ENE
08/11/2021 18:21, Matan Azrad:
> Due to kernel driver/FW issues in direct MKEY creation using the DevX
> API, this patch replaces the dirty bitmap MR creation to use wrapped
> mkey instead.
>
> Fixes: 9d39e57f21ac ("vdpa/mlx5: support live migration")
> Cc: sta...@dpdk.org
>
> Signed-off-by: Mich
08/11/2021 03:44, Zhang, Qi Z:
> From: Xu, Ting
> > From: Thomas Monjalon
> > > 05/11/2021 14:18, Xu, Ting:
> > > > From: Thomas Monjalon
> > > > > 04/11/2021 03:22, Ting Xu:
> > > > > > Enable protocol agnostic flow offloading to support raw pattern
> > > > > > input for RSS hash flow rule crea
On Mon, Nov 8, 2021 at 7:17 PM wrote:
> diff --git a/drivers/gpu/cuda/meson.build b/drivers/gpu/cuda/meson.build
> new file mode 100644
> index 00..92b30c35b4
> --- /dev/null
> +++ b/drivers/gpu/cuda/meson.build
> @@ -0,0 +1,13 @@
> +# SPDX-License-Identifier: BSD-3-Clause
> +# Copyright (
> -Original Message-
> From: Ferruh Yigit
> Sent: Thursday, November 4, 2021 11:56 PM
> To: Apeksha Gupta ; david.march...@redhat.com;
> andrew.rybche...@oktetlabs.ru
> Cc: dev@dpdk.org; Sachin Saxena ; Hemant Agrawal
>
> Subject: [EXT] Re: [PATCH v7 2/5] net/enetfec: add UIO support
>
On Mon, Oct 25, 2021 at 9:59 AM huichao cai wrote:
>
> Add the test content of the fragment_offset(offset and MF)
> to the test_ip_frag function. Add test data for a fragment
> that is not the last fragment.
>
> Signed-off-by: huichao cai
The CI raises a regression on the ip frag test.
DPDK_TES
On Fri, Nov 5, 2021 at 4:57 PM Jim Harris wrote:
>
> clang-13 rightfully complains that the tot_ppi
> variable in update_stats is set but not used, since
> the final accumulated tot_ppi results isn't used
> anywhere.
>
> Original idea was to just remove the tot_ppi variable,
> but feedback from Da
28/10/2021 17:35, Burakov, Anatoly:
> On 28-Oct-21 4:14 PM, Gregory Etelson wrote:
> >>> - uint8_t client = 0;
> >>> + static uint8_t client = 0;
>
> Acked-by: Anatoly Burakov
checkpatch has a message for you:
ERROR:INITIALISED_STATIC: do not initialise statics to 0
08/11/2021 14:55, Konstantin Ananyev:
> Update public macros to have RTE_IP_FRAG_ prefix.
> Remove obsolete macro.
> Update DPDK components to use new names.
I think you should keep old names for compatibility during some time.
We should rename the function rte_frag_table_del_expired_entries
to s
08/11/2021 14:55, Konstantin Ananyev:
> Move internal reassembly structures into new private
> header 'ip_reassembly.h'.
>
> Signed-off-by: Konstantin Ananyev
[...]
> --- /dev/null
> +++ b/lib/ip_frag/ip_reassembly.h
> +#ifndef _IP_REASSEMBLY_H_
> +#define _IP_REASSEMBLY_H_
[...]
> +
> +#endif /*
On 11/8/2021 8:24 PM, Apeksha Gupta wrote:
-Original Message-
From: Ferruh Yigit
Sent: Thursday, November 4, 2021 11:56 PM
To: Apeksha Gupta ; david.march...@redhat.com;
andrew.rybche...@oktetlabs.ru
Cc: dev@dpdk.org; Sachin Saxena ; Hemant Agrawal
Subject: [EXT] Re: [PATCH v7 2/5] n
>
> This patch adds a comment for RTE_HASH_BUCKET_ENTRIES explaining why a
> particular value was chosen.
>
> Signed-off-by: Vladimir Medvedkin
> ---
> lib/hash/rte_cuckoo_hash.h | 8 +++-
> 1 file changed, 7 insertions(+), 1 deletion(-)
>
> diff --git a/lib/hash/rte_cuckoo_hash.h b/lib/
On Mon, 8 Nov 2021 21:20:31 +
Elena Agostini wrote:
> > From: Stephen Hemminger
> > Date: Monday, 8 November 2021 at 20:02
> > To: Elena Agostini
> > Cc: dev@dpdk.org
> > Subject: Re: [dpdk-dev] [RFC PATCH] gpu/cuda: introduce CUDA driver
> > External email: Use caution opening links or at
02/11/2021 20:03, Konstantin Ananyev:
> Increase default value for config parameter RTE_LIBRTE_IP_FRAG_MAX_FRAG
> from 4 to 8. This parameter controls maximum number of fragments per
> packet in ip reassembly table. Increasing this value from 4 to 8 will
> allow users to cover common case with jumb
This patch defines ASAN_SHADOW_OFFSET for arm64 according to the ASan
documentation. This offset should cover all arm64 VMAs supported by
ASan.
Signed-off-by: Volodymyr Fialko
Reviewed-by: David Marchand
Acked-by: Jerin Jacob
---
Changes since v1:
- changed the subject
- rewrite checks in "elif
This patch defines ASAN_SHADOW_OFFSET for arm64 according to the ASan
documentation. This offset should cover all arm64 VMAs supported by
ASan.
Signed-off-by: Volodymyr Fialko
Reviewed-by: David Marchand
Acked-by: Jerin Jacob
---
Changes since v1:
- changed the subject
- rewrite checks in "elif
>
> Convert rte_atomic usages to compiler atomic built-ins for polling sync in
> pmd_perf test cases.
>
> Signed-off-by: Joyce Kong
> Reviewed-by: Ruifeng Wang
> ---
> app/test/test_pmd_perf.c | 12 +---
> 1 file changed, 5 insertions(+), 7 deletions(-)
>
> diff --git a/app/test/tes
> > Bugzilla ID: 835
> > Fixes: 567473433b7e ("ip_frag: fix fragmenting IPv4 fragment")
> > Cc: sta...@dpdk.org
> > Signed-off-by: huichao cai
>
> Acked-by: Konstantin Ananyev
Revert applied, thanks.
On Mon, 8 Nov 2021 14:07:47 -0800
Stephen Hemminger wrote:
> On Mon, 8 Nov 2021 21:20:31 +
> Elena Agostini wrote:
>
> > > From: Stephen Hemminger
> > > Date: Monday, 8 November 2021 at 20:02
> > > To: Elena Agostini
> > > Cc: dev@dpdk.org
> > > Subject: Re: [dpdk-dev] [RFC PATCH] gpu/cu
1 - 100 of 128 matches
Mail list logo
