在 2020/10/26 0:18, David Marchand 写道:
Hello Wei Hu,
diff --git a/drivers/net/hns3/meson.build b/drivers/net/hns3/meson.build
index bf69ad4..ca0f21a 100644
--- a/drivers/net/hns3/meson.build
+++ b/drivers/net/hns3/meson.build
@@ -31,4 +31,9 @@ deps += ['hash']
if arch_subdir == 'arm' and d
When changing the number of forwarding cores in runtime, two issues may be
encountered:
- If the setting nbcore little than current nbcore, the forwarding
thread will still running on the extra cores. Therefore, trying to
stop forwarding will hang testpmd, since it will wait for the extr
The Tx queue stop\start operations update the HW state of the Tx queue
object. The stop API should update the state from ready to reset in
order to stop any queue traffic and the start API should update the state
from reset to ready in order to open the traffic path.
The start API wrongly tried to
Replace the 'rte_panic()' with an error return.
Also change the type of the calling function.
Signed-off-by: Jiawen Wu
---
drivers/net/txgbe/txgbe_ethdev.h | 2 +-
drivers/net/txgbe/txgbe_pf.c | 12
2 files changed, 9 insertions(+), 5 deletions(-)
diff --git a/drivers/net/txgb
Signed-off-by: Jiawen Wu
---
drivers/net/txgbe/{rte_pmd_txgbe_version.map => version.map} | 0
1 file changed, 0 insertions(+), 0 deletions(-)
rename drivers/net/txgbe/{rte_pmd_txgbe_version.map => version.map} (100%)
diff --git a/drivers/net/txgbe/rte_pmd_txgbe_version.map
b/drivers/net/txgbe
Add support for API rte_eth_tx_done_cleanup().
Signed-off-by: Jiawen Wu
---
drivers/net/txgbe/txgbe_ethdev.c | 1 +
drivers/net/txgbe/txgbe_rxtx.c | 89
drivers/net/txgbe/txgbe_rxtx.h | 1 +
3 files changed, 91 insertions(+)
diff --git a/drivers/net/txgbe/
Supports check the status of Rx and Tx descriptors.
Signed-off-by: Jiawen Wu
---
doc/guides/nics/features/txgbe.ini | 2 +
drivers/net/txgbe/txgbe_ethdev.c | 3 ++
drivers/net/txgbe/txgbe_ethdev.h | 6 +++
drivers/net/txgbe/txgbe_rxtx.c | 73 ++
4 files cha
From: murphy
When set 'csum set outer-udp hw 0' ,support for
ICE_RX_FLEX_DESC_STATUS0_XSUM_EUDPE_S,mark the packet
PKT_RX_OUTER_L4_CKSUM_BAD or PKT_RX_OUTER_L4_CKSUM_GOOD.
Fixes: dbf3c0e77a22 ("net/ice: handle Rx flex descriptor")
Fixes: 4ab7dbb0a0f6 ("net/ice: switch to Rx flexible descriptor i
On Thu, Oct 08, 2020 at 09:00:47PM +0530, rohit@nxp.com wrote:
> From: Rohit Raj
>
> Added support for rte_bus_close API on windows to reset the devices on
> the bus to default state.
>
> Signed-off-by: Rohit Raj
> ---
> lib/librte_eal/windows/eal.c | 2 +-
> 1 file changed, 1 insertion(+)
> -Original Message-
> From: Guo, Jia
> Sent: Tuesday, October 27, 2020 13:05
> To: Wu, Jingjing ; Zhang, Qi Z ;
> Xing, Beilei
> ; Yigit, Ferruh
> Cc: dev@dpdk.org; Wang, Haiyue ; Richardson, Bruce
> ;
> Guo, Jia
> Subject: [PATCH v10] net/iavf: support flex desc metadata extraction
>
Enable metadata extraction for flexible descriptors in AVF, that would
allow network function directly get metadata without additional parsing
which would reduce the CPU cost for VFs. The enabling metadata
extractions involve the metadata of VLAN/IPv4/IPv6/IPv6-FLOW/TCP/MPLS
flexible descriptors, a
I think we need to split this further. Few suggestions below.
>
> * Rename variables to have names that better describe what the variables
> store
This should be a separate commit.
> * Remove unused or superfluous variables
Same here
> * Change a list to dictionary where key lookup is needed
S
> On Oct 22, 2020, at 4:25 PM, Honnappa Nagarahalli
> wrote:
>
> + Dharmik
>
>> -Original Message-
>> From: Thomas Monjalon
>> Sent: Thursday, October 22, 2020 4:18 PM
>> To: Ruifeng Wang
>> Cc: dev@dpdk.org; akhil.go...@nxp.com; Honnappa Nagarahalli
>> ; nd
>> Subject: Re: [dpdk-
>
> The current way of specifying Arm configuration options is insufficient since
> we can't identify the SoC we're building for from the MIDR information. For
> example, we can't distinguish between N1SDP, Graviton2 or Ampere Altra.
>
> Add a way to specify the cpu count and numa node count fo
>
> The current machine='default' build name is not descriptive. The actual
> default build is machine='native'. Add an alternative string which does the
> same build and better describes what we're building:
> machine='generic'. Leave machine='default' for backwards compatibility.
>
> Signed-o
Hi Akhil,
Please find few comments inline.
Thanks
Abhinandan
> -Original Message-
> From: Akhil Goyal
> Sent: Tuesday, October 27, 2020 12:39 AM
> To: Gujjar, Abhinandan S ; dev@dpdk.org;
> Doherty, Declan ;
> honnappa.nagaraha...@arm.com; Ananyev, Konstantin
>
> Cc: Vangati, Narender
在 2020/10/26 0:18, David Marchand 写道:
Hello Wei Hu,
diff --git a/drivers/net/hns3/meson.build b/drivers/net/hns3/meson.build
index bf69ad4..ca0f21a 100644
--- a/drivers/net/hns3/meson.build
+++ b/drivers/net/hns3/meson.build
@@ -31,4 +31,9 @@ deps += ['hash']
if arch_subdir == 'arm' and d
Tested-by: JiangYuX
Best Regards
Jiang yu
> -Original Message-
> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Adrian Moreno
> Sent: Tuesday, October 27, 2020 12:39 AM
> To: dev@dpdk.org
> Cc: Wang, Yinan ; Fu, Patrick
> ; Xia, Chenbo ; Wang,
> Zhihong ; maxime.coque...@r
Hi, Ferruh, all,
have you any suggestions of this set of patches?
转发的消息
主题: 转发: [RFC V2 1/2] app/testpmd: fix queue stats mapping configuration
日期: Tue, 27 Oct 2020 09:31:16 +0800
发件人: lihuisong (C)
收件人: humin (Q)
-邮件原件-
发件人: humin (Q) 发送时间: 2020年10月20日 16:
> -Original Message-
> From: Thomas Monjalon [mailto:tho...@monjalon.net]
> Sent: Monday, October 26, 2020 8:34 PM
> To: Andrew Rybchenko
> Cc: wangyunjian ; dev@dpdk.org;
> ferruh.yi...@intel.com; Lilijun (Jerry) ; xudingke
> ; ma...@nvidia.com
> Subject: Re: [dpdk-dev] [PATCH] ethdev: fi
On Monday, October 26, 2020 10:56 PM, Ferruh Yigit wrote:
> On 10/19/2020 9:53 AM, Jiawen Wu wrote:
> > v4: Add log type introduction,
> > add txgbe support in release note.
> > v3: Merge some recent changes in the main repo,
> > fix the checkpatch warnings.
> > v2: Re-order patches and f
gpa_to_hpa() function almost always fails due to the wrong setup of
the binary tree search key. Since there has already been a similar
function gpa_to_first_hpa() available in the vhost, instead of fixing
the issue in its original logic, gpa_to_hpa() function is rewritten to
be a wrapper of the gpa
> -Original Message-
> From: Thomas Monjalon
> Sent: Tuesday, October 27, 2020 06:20
> To: dev@dpdk.org
> Cc: Yigit, Ferruh ; david.march...@redhat.com;
> Richardson, Bruce
> ; olivier.m...@6wind.com;
> andrew.rybche...@oktetlabs.ru;
> akhil.go...@nxp.com; Doherty, Declan ; Ankur
> Dwiv
Devices belonging to BCM573xx and BCM5740x family will not be supported
from the 21.02 release.
Signed-off-by: Ajit Khaparde
---
doc/guides/rel_notes/deprecation.rst | 6 ++
1 file changed, 6 insertions(+)
diff --git a/doc/guides/rel_notes/deprecation.rst
b/doc/guides/rel_notes/deprecation
> -Original Message-
> From: Wang, Haiyue
> Sent: Tuesday, October 27, 2020 9:23 AM
> To: dev@dpdk.org
> Cc: Yigit, Ferruh ; Guo, Jia ;
> Zhang, Qi Z ; Chen, Zhaoyan
> ; olivier.m...@6wind.com; Wang, Haiyue
> ; Yang, Qiming
> Subject: [PATCH v4] net/ice: rename the dynamic mbuf name
>
Rename the dynamic mbuf name to 'intel_pmd_xxx' format, so that the
Intel PMD which has the protocol extraction feature will share the
same dynamic field/flags space in mbuf.
Signed-off-by: Haiyue Wang
---
v4: "who register, who use", even the PMD has the duplicated code with
different name s
> -Original Message-
> From: Wang, Haiyue
> Sent: Monday, October 26, 2020 2:55 PM
> To: dev@dpdk.org
> Cc: Yigit, Ferruh ; Guo, Jia ;
> Zhang, Qi Z ; Chen, Zhaoyan
> ; Wang, Haiyue ; Yang,
> Qiming ; Ray Kinsella ; Neil
> Horman
> Subject: [PATCH v3] net/ice: refactor the protocol ext
> -Original Message-
> From: Zhang,Alvin
> Sent: Friday, October 23, 2020 10:13 AM
> To: Lu, Wenzhuo ; Zhang, Qi Z
> Cc: dev@dpdk.org; Zhang, AlvinX ; sta...@dpdk.org
> Subject: [PATCH] net/ice: fix Rx offload flags in SSE path
>
> From: Alvin Zhang
>
> Update reading offload flags
> -Original Message-
> From: dev On Behalf Of Guo, Jia
> Sent: Monday, October 26, 2020 3:15 PM
> To: Xing, Beilei ; dev@dpdk.org
> Cc: sta...@dpdk.org
> Subject: Re: [dpdk-dev] [PATCH] net/i40e: fix FDIR issue for ETH + VLAN
> pattern
>
> Acked-by: Jeff Guo
>
> > -Original Mess
Hi,
> -Original Message-
> From: dev On Behalf Of Matan Azrad
> Sent: Sunday, October 25, 2020 6:04 PM
> To: Slava Ovsiienko
> Cc: dev@dpdk.org
> Subject: [dpdk-dev] [PATCH] net/mlx5: support the new VLAN matching
> fields
>
> The fields ``has_vlan`` and ``has_more_vlan`` were added in r
Hi,
> -Original Message-
> From: Bing Zhao
> Sent: Monday, October 26, 2020 10:38 AM
> To: viachesl...@mellanox.com; ma...@mellanox.com
> Cc: dev@dpdk.org; Ori Kam ; Raslan Darawsheh
> ; sta...@dpdk.org; pa...@mellanox.com
> Subject: [PATCH] common/mlx5: fix PCI driver name
>
> In the re
Hi,
> -Original Message-
> From: Bing Zhao
> Sent: Monday, October 26, 2020 6:38 PM
> To: viachesl...@mellanox.com; ma...@mellanox.com
> Cc: dev@dpdk.org; Ori Kam ; Raslan Darawsheh
>
> Subject: [PATCH v3 0/7] add two ports hairpin mode support in mlx5 PMD
>
> This patch set will add th
As Slava mentioned we are already working on a patch to align all pmd calls. It
should be in the ML soon. We target it for rc2.
Regards,
Asaf Penso
From: Thomas Monjalon
Sent: Monday, October 26, 2020 6:40:13 PM
To: Andrey Vesnovaty ; Ferruh Yigit
; Slava Ovsii
As announced in the deprecation note, the field userdata / udata64
is removed to give more space to the dynamic fields.
Signed-off-by: Thomas Monjalon
---
doc/guides/rel_notes/deprecation.rst | 1 -
doc/guides/rel_notes/release_20_11.rst | 3 +++
lib/librte_kni/rte_kni_common.h| 3 +--
The example used the deprecated mbuf field udata64.
It is moved to a dynamic field in order to allow removal of udata64.
Signed-off-by: Thomas Monjalon
---
doc/guides/sample_app_ug/rxtx_callbacks.rst | 4 ++--
examples/rxtx_callbacks/main.c | 20 ++--
2 files change
The example used the deprecated mbuf field udata64 as input mbuf pointer.
It is moved to a dynamic field in order to allow removal of udata64.
Signed-off-by: Thomas Monjalon
---
examples/bbdev_app/main.c | 38 --
1 file changed, 28 insertions(+), 10 deletions(
The order test stored the flow ID in the deprecated mbuf field udata64.
It is moved to a dynamic field in order to allow removal of udata64.
Signed-off-by: Thomas Monjalon
---
app/test-eventdev/test_order_atq.c| 4 ++--
app/test-eventdev/test_order_common.c | 16 +++-
app/test-e
The test used the deprecated mbuf field udata64.
It is moved to a dynamic field in order to allow removal of udata64.
Signed-off-by: Thomas Monjalon
---
app/test/test_graph.c | 94 ++-
1 file changed, 56 insertions(+), 38 deletions(-)
diff --git a/app/tes
The test used the deprecated mbuf field udata64.
It is moved to a dynamic field in order to allow removal of udata64.
Signed-off-by: Thomas Monjalon
Acked-by: Lukasz Wojciechowski
Tested-by: Lukasz Wojciechowski
---
app/test/test_distributor.c | 28 +++-
1 file changed,
The second field of metadata is reserved for user data
which is a deprecated mbuf field.
The usage of mbuf udata64 is removed
and the corresponding ark metadata field is annotated as ignored.
Signed-off-by: Thomas Monjalon
---
drivers/net/ark/ark_ddm.h | 2 +-
drivers/net/ark/ark_ethdev_rx
The segment count, used for MSS guess,
was stored in the deprecated mbuf field udata64.
It is moved to a dynamic field in order to allow removal of udata64.
Signed-off-by: Thomas Monjalon
---
drivers/net/vmxnet3/vmxnet3_ethdev.c | 15 +++
drivers/net/vmxnet3/vmxnet3_ethdev.h | 6 +++
The CFA code from mark was stored in the deprecated mbuf field udata64.
It is moved to a dynamic field in order to allow removal of udata64.
Note: the new field has 32 bits, smaller than udata64.
Signed-off-by: Thomas Monjalon
---
drivers/net/bnxt/bnxt_ethdev.c | 19 +++
driver
The test worker_loopback used the deprecated mbuf field udata64.
It is moved to a dynamic field in order to allow removal of udata64.
Signed-off-by: Thomas Monjalon
Reviewed-by: Andrew Rybchenko
---
drivers/event/sw/sw_evdev_selftest.c | 23 ---
1 file changed, 20 insertions
The device-specific metadata was stored in the deprecated field udata64.
It is moved to a dynamic mbuf field in order to allow removal of udata64.
Signed-off-by: Thomas Monjalon
---
doc/guides/prog_guide/rte_security.rst| 9 +++---
drivers/crypto/octeontx2/otx2_cryptodev_sec.c | 5 ++-
Since the kernel module is not part of EAL anymore,
there is no need to have the common KNI header file in EAL.
The file rte_kni_common.h is moved to librte_kni.
Signed-off-by: Thomas Monjalon
Acked-by: Andrew Rybchenko
---
kernel/linux/kni/meson.build | 2 +-
l
The node_mbuf_priv1 was stored in the deprecated mbuf field udata64.
It is moved to a dynamic field in order to allow removal of udata64.
Signed-off-by: Thomas Monjalon
---
lib/librte_node/ip4_lookup.c | 7 +++
lib/librte_node/ip4_rewrite.c | 10 ++
lib/librte_node/node_private.h
Replace "in a in PMD" with "in a PMD".
Fixes: 4958ca3a443a ("mbuf: support dynamic fields and flags")
Cc: sta...@dpdk.org
Signed-off-by: Thomas Monjalon
Acked-by: Andrew Rybchenko
---
lib/librte_mbuf/rte_mbuf_dyn.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/lib/librte_
The mbuf field userdata (aliased as udata64)
was announced to be removed for two reasons:
- applications, libraries and drivers used the same field
for different purposes, with a risk of usage conflict.
- this field always used 8 bytes even if unneeded
Some dynamic fields are created when
In examples, DPDK header files are external,
so they must be enclosed with angle brackets, not quotes.
Signed-off-by: Thomas Monjalon
Acked-by: Andrew Rybchenko
---
examples/bbdev_app/main.c | 30 +-
examples/bond/main.c | 11 --
ex
Fix build with external makefile.
Fixes: fbc74e66334f ("examples/ip_pipeline: remove infra code")
Signed-off-by: Cristian Dumitrescu
---
examples/ip_pipeline/Makefile | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/examples/ip_pipeline/Makefile b/examples/ip_pipeline/Makefile
On Sun, Oct 25, 2020 at 8:56 PM Ajit Khaparde
wrote:
>
> This patchset has support for VXLAN decap full offload,
> SR device support in tf_core and a few bug fixes.
>
> v1->v2:
> - Squashed some patches.
> - Updated commit logs.
> - Fixed a compilation issue reported during clang builds.
>
> v2
Coverity issue: 363041
Fixes: 5074e1d551 ("examples/pipeline: add configuration commands")
Signed-off-by: Cristian Dumitrescu
---
examples/pipeline/cli.c | 15 +++
1 file changed, 15 insertions(+)
diff --git a/examples/pipeline/cli.c b/examples/pipeline/cli.c
index 8ac6b3f5f..d0150c
Fix potential buffer overflows by string copy into fixed size buffer.
Coverity issue: 362732, 362736, 362760, 362772, 362775, 362784,
362800, 362803, 362806, 362811, 362814, 362816,
362834, 362837, 362844, 362845, 362857, 362861,
362868, 362890, 3628
Updated references to abi versions in the contributors guide.
Fixed an inaccurate reference to a symbol in the policy.
Signed-off-by: Ray Kinsella
Reviewed-by: David Marchand
---
doc/guides/contributing/abi_policy.rst | 56 +-
doc/guides/contributing/abi_versioning.rst | 120 ++
Updated references to abi versions in the contributors guide.
Fixed an inaccurate reference to a symbol in the policy.
Signed-off-by: Ray Kinsella
Reviewed-by: David Marchand
---
doc/guides/contributing/abi_policy.rst | 56 +-
doc/guides/contributing/abi_versioning.rst | 120 ++
On Mon, Sep 14, 2020 at 4:05 AM Morten Brørup
wrote:
>
> Updated description of rte_eth_rx_burst() to reflect what drivers,
> when using vector instructions, expect from nb_pkts.
>
> Also discussed on the mailing list here:
> http://inbox.dpdk.org/dev/98cbd80474fa8b44bf855df32c47dc35c61...@smarts
> Subject: [v4 3/3] doc: add enqueue callback APIs
>
> Add enqueue callback support for cryptodev library
>
No need for separate documentation patch. It should be part of patch which is
adding
The functionality.
> Signed-off-by: Abhinandan Gujjar
> ---
> doc/guides/prog_guide/cryptodev_lib.rs
26/10/2020 17:49, Thomas Monjalon:
> 26/10/2020 16:06, Andrew Rybchenko:
> > On 10/26/20 8:20 AM, Thomas Monjalon wrote:
> > [snip]
> > > - sa = pkt->userdata;
> > > + sa = RTE_MBUF_DYNFIELD(pkt, security_dynfield_offset,
> > > + struc
Hi Dmitry,
On 10/22/2020 12:05 PM, Dmitry Kozlyuk wrote:
/* Detect if we are a primary or a secondary process */
enum rte_proc_type_t
eal_proc_type_detect(void)
@@ -181,6 +231,13 @@ eal_parse_args(int argc, char **argv)
}
}
+ /* create runtime data directory */
Add enqueue callback support for cryptodev library
Signed-off-by: Abhinandan Gujjar
---
doc/guides/prog_guide/cryptodev_lib.rst | 22 ++
doc/guides/rel_notes/release_20_11.rst | 5 +
2 files changed, 27 insertions(+)
diff --git a/doc/guides/prog_guide/cryptodev_lib.rst
Signed-off-by: Abhinandan Gujjar
---
app/test/test_cryptodev.c | 133 +-
1 file changed, 131 insertions(+), 2 deletions(-)
diff --git a/app/test/test_cryptodev.c b/app/test/test_cryptodev.c
index 1d4c46f..a083612 100644
--- a/app/test/test_cryptodev.c
This patch adds APIs to add/remove callback functions. The callback
function will be called for each burst of crypto ops received on a
given crypto device queue pair.
Signed-off-by: Abhinandan Gujjar
---
config/rte_config.h| 1 +
lib/librte_cryptodev/meson.build
In an eventdev world, multiple workers (with ordered queue) will be
working on IPsec ESP processing. The ESP header's sequence number is
unique and has to be sequentially incremented in an orderly manner.
This rises a need for incrementing sequence number in crypto stage
especially in event crypto
Currently, since there is no runtime directory set, the code tries to
create a file in C:\ which is only writable with administrator
privileges. As a result, if the user is not admin, the application will
fail.
So, forcing no_shconf to 1 to prevent the code having to create files in
the runtime dir
> Subject: [dpdk-dev] [PATCH 2/2] test/crypto: disable wireless tests for
> symmetric API
The patch content is for the synchronous CPU crypto APIs and not
Symmetric API.
>
> SNOW3G, KASUMI and ZUC algorithms have been added to
> aesni_mb PMD in this release. These algorithms are not supported
>
>Subject: [PATCH] crypto/octeontx2: fix crypto OOP support
>
> Out of place with linear buffers is supported by octeontx2
> while not advertised.
>
> Cc: sta...@dpdk.org
> Fixes: 6aa9ceaddf1d ("crypto/octeontx2: add symmetric capabilities")
> Signed-off-by: Didier Pallard
Cc below fixes line an
Good catch :-).
On 23/10/2020 17:51, David Marchand wrote:
> On Fri, Oct 23, 2020 at 6:11 PM Ray Kinsella wrote:
>>
>> Updated references to abi versions in the contributors guide.
>
> Thanks for looking at it.
>
> I would keep the dpdk release version aligned with updated ABI ver.
> Caught 3 r
Fix wrong assignment of allow_multi_pkt_send_wqe
in mlx5_devx_cmd_create_sq.
The incorrect assignment was introduced in the initial
mlx5_devx_cmd_create_sq implementation.
sq_attr->flush_in_error_en is
mistakenly assigned to both allow_multi_pkt_send_wqe and
flush_in_error_en, it was detected duri
26/10/2020 17:50, Thomas Monjalon:
> 26/10/2020 16:21, Andrew Rybchenko:
> > On 10/26/20 6:14 PM, Andrew Rybchenko wrote:
> > > On 10/26/20 8:20 AM, Thomas Monjalon wrote:
> > >> -rxm->udata64 = rcde->segCnt;
> > >> +*RTE_MBUF_DYNFIELD(rxm,
> > >> vm
Hi,
> -Original Message-
> From: Viacheslav Ovsiienko
> Sent: Monday, October 26, 2020 7:18 PM
> To: dev@dpdk.org
> Cc: Raslan Darawsheh
> Subject: [PATCH] net/mlx5: fix Rx queue initialization for scattered segment
>
> During integration/rebase there was introduced the bugs:
>
> - dou
Hi,
> -Original Message-
> From: Bing Zhao
> Sent: Monday, October 26, 2020 7:25 PM
> To: viachesl...@mellanox.com; ma...@mellanox.com
> Cc: dev@dpdk.org; Ori Kam ; Raslan Darawsheh
> ; Andrey Vesnovaty
> Subject: [PATCH] net/mlx5: fix bit field compiling error
>
> Some old compilers a
> On Mon, Oct 26, 2020 at 6:21 AM Thomas Monjalon
> wrote:
> > diff --git a/lib/librte_security/rte_security_driver.h
> b/lib/librte_security/rte_security_driver.h
> > index 1b561f8528..ba9691b4a0 100644
> > --- a/lib/librte_security/rte_security_driver.h
> > +++ b/lib/librte_security/rte_security
Hello David,
On 26/10/2020 13:58, David Marchand wrote:
Hello Vladimir,
On Sun, Oct 25, 2020 at 7:08 PM Vladimir Medvedkin
wrote:
diff --git a/lib/librte_fib/rte_fib.h b/lib/librte_fib/rte_fib.h
index 84ee774..2097ee5 100644
--- a/lib/librte_fib/rte_fib.h
+++ b/lib/librte_fib/rte_fib.h
@@ -58
update offload dequeue to retrieve the full ring to be
agnostic of implementation.
Signed-off-by: Nicolas Chautru
Acked-by: Aidan Goddard
Acked-by: Dave Burley
---
app/test-bbdev/test_bbdev_perf.c | 16
1 file changed, 8 insertions(+), 8 deletions(-)
diff --git a/app/test-bbd
Reducing number of repetitions from 1000 to 100
to save time. Results are accurate enough with
100 loops.
Signed-off-by: Nicolas Chautru
Acked-by: Liu Tianjiao
Reviewed-by: Tom Rix
---
app/test-bbdev/test_bbdev_perf.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/app/test
bler test results are not valid when LLR compression
is used or for loopback scenarios. Skipping these.
Signed-off-by: Nicolas Chautru
Acked-by: Aidan Goddard
Acked-by: Dave Burley
Reviewed-by: Tom Rix
---
app/test-bbdev/test_bbdev_perf.c | 6 +-
1 file changed, 5 insertions(+), 1 deletio
Replacing magic number for default wait time for hw
offload.
Signed-off-by: Nicolas Chautru
Acked-by: Liu Tianjiao
---
app/test-bbdev/test_bbdev_perf.c | 9 +
1 file changed, 5 insertions(+), 4 deletions(-)
diff --git a/app/test-bbdev/test_bbdev_perf.c b/app/test-bbdev/test_bbdev_perf.
Run preloading explicitly for unit tests. Load each code block
by reusing existing input op then restore for the actual test.
Signed-off-by: Nicolas Chautru
Acked-by: Liu Tianjiao
---
app/test-bbdev/main.h| 1 +
app/test-bbdev/test_bbdev_perf.c | 53 +---
Adding explicit different ut when testing for validation
or latency (early termination enabled or not).
Signed-off-by: Nicolas Chautru
Acked-by: Aidan Goddard
Acked-by: Dave Burley
---
app/test-bbdev/test_bbdev_perf.c | 55 +++-
1 file changed, 38 insertions
v6: minor refactory suggested by Tom Rix,
v5: correcting typos again. Quite worrisome spelling disorder.
v4: rebased on main latest
v3: apologize again for typo and not double checking with check-git-log
v2: typos missed in commit messages
Serie updating and extending the app running the bbdev-test
Adding explicit check in ut that the stats counters
have the expect values.
This was identified as a gap from code coverage.
Signed-off-by: Nicolas Chautru
Acked-by: Aidan Goddard
Acked-by: Dave Burley
---
app/test-bbdev/test_bbdev_perf.c | 17 +
1 file changed, 17 insertions(+
Hi, Ferruh
PSB
> -Original Message-
> From: Ferruh Yigit
> Sent: Monday, October 26, 2020 19:04
> To: Raslan Darawsheh ; Slava Ovsiienko
> ; dev@dpdk.org
> Cc: NBU-Contact-Thomas Monjalon ; Matan Azrad
> ; Alexander Kozyrev ; Ori Kam
>
> Subject: Re: [dpdk-dev] [PATCH v4 0/6] net/mlx5:
> -Original Message-
> From: Tom Rix
> Sent: Monday, October 26, 2020 5:56 AM
> To: Chautru, Nicolas ; dev@dpdk.org;
> akhil.go...@nxp.com
> Cc: david.march...@redhat.com
> Subject: Re: [PATCH v5 1/7] app/bbdev: add explicit ut for latency vs
> validation
>
>
> On 10/23/20 4:42 PM, Nico
Some old compilers and old specification will not support bit field
with other types except integer or unsigned integer.
Since the next and previous items are 64b and/or 32b aligned, bit
field with "unsigned char" type will not save any space and the
compiler will complain.
Changing it to "unsigned
During integration/rebase there was introduced the bugs:
- double memory allocation for queue structure resulting in
losing the part of configuration settings and following
crash
- the erroneous fix for the segment logarithm
Fixes: 919ef3e26cff ("net/mlx5: configure Rx queue to support split
On 10/26/2020 3:25 PM, Raslan Darawsheh wrote:
Hi,
-Original Message-
From: Viacheslav Ovsiienko
Sent: Monday, October 26, 2020 1:55 PM
To: dev@dpdk.org
Cc: NBU-Contact-Thomas Monjalon ; Matan Azrad
; Alexander Kozyrev ; Raslan
Darawsheh ; Ori Kam
Subject: [PATCH v4 0/6] net/mlx5: add
> -Original Message-
> From: Tom Rix
> Sent: Monday, October 26, 2020 6:32 AM
> To: Chautru, Nicolas ; dev@dpdk.org;
> akhil.go...@nxp.com
> Cc: david.march...@redhat.com
> Subject: Re: [PATCH v5 3/7] app/bbdev: include explicit HARQ preloading
>
>
> On 10/23/20 4:42 PM, Nicolas Chautru
26/10/2020 16:21, Andrew Rybchenko:
> On 10/26/20 6:14 PM, Andrew Rybchenko wrote:
> > On 10/26/20 8:20 AM, Thomas Monjalon wrote:
> >> - rxm->udata64 = rcde->segCnt;
> >> + *RTE_MBUF_DYNFIELD(rxm, vmxnet3_segs_dynfield_offset,
> >> +
26/10/2020 16:06, Andrew Rybchenko:
> On 10/26/20 8:20 AM, Thomas Monjalon wrote:
> > --- a/drivers/net/ixgbe/ixgbe_ipsec.c
> > +++ b/drivers/net/ixgbe/ixgbe_ipsec.c
> > - (union ixgbe_crypto_tx_desc_md *)&m->udata64;
> > + (union ixgbe_crypto_tx_desc_md *)
> > +
Tested-by: Jie Zhou
On Tue, Oct 20, 2020 at 08:44:03PM +0300, Dmitry Kozlyuk wrote:
> Delete the files no longer used in build process.
> Add myself as maintainer of new implementation.
>
> Signed-off-by: Dmitry Kozlyuk
> ---
> MAINTAINERS| 3 +-
> buildtools/pmdinfog
> -Original Message-
> From: Bing Zhao
> Sent: Monday, October 26, 2020 18:38
> To: viachesl...@mellanox.com; ma...@mellanox.com
> Cc: dev@dpdk.org; Ori Kam ; Raslan Darawsheh
>
> Subject: [PATCH v3 7/7] doc: update mlx5 hairpin support and limitations
>
> Hairpin between two ports will
Hi,
Is it a known issue that dpdk-next-net build is broken on Ubuntu 18.04?
gcc (Ubuntu 7.5.0-3ubuntu1~18.04) 7.5.0
FAILED: drivers/net/ice/libice_avx512_lib.a.p/ice_rxtx_vec_avx512.c.o
*c*c -Idrivers/net/ice/libice_avx512_lib.a.p -Idrivers/net/ice
-I../drivers/net/ice -Idrivers/net/ice/base -I
> -Original Message-
> From: Ferruh Yigit
> Sent: Monday, October 26, 2020 18:38
> To: Andrey Vesnovaty ; dev@dpdk.org
> Cc: j...@marvell.com; jerinjac...@gmail.com; NBU-Contact-Thomas Monjalon
> ; step...@networkplumber.org;
> bruce.richard...@intel.com; Ori Kam ; Slava Ovsiienko
> ; andr
26/10/2020 17:38, Ferruh Yigit:
> On 10/23/2020 11:24 AM, Andrey Vesnovaty wrote:
> > + rte_atomic32_inc(&(*hrxq)->refcnt);
>
> I remember adding more 'rte_atomicNN_xxx' to driver has been discussed
> before,
> and it has been mentioned that a seperate commit will be done to re
Newer vhost-user backends will rely on SET_STATUS to start the device
so this required to support them.
Fixes: 57912824615f ("net/virtio-user: support vhost status setting")
Cc: maxime.coque...@redhat.com
Cc: sta...@dpdk.org
Signed-off-by: Adrian Moreno
---
drivers/net/virtio/virtio_user_ethdev
In order to safely set and get the device status from different
threads (e.g: interrupt handlers).
Signed-off-by: Adrian Moreno
---
drivers/net/virtio/virtio_user/virtio_user_dev.c | 14 +++---
drivers/net/virtio/virtio_user/virtio_user_dev.h | 4 ++--
drivers/net/virtio/virtio_user_eth
There are some status reads and updates that need to happen before the
protocol features are negotiated. Therefore, assuming the backend does
support this feature can lead to failures.
On server mode, do not assume the backend supports
VHOST_USER_PROTOCOL_F_STATUS. Activate it back on reconnection
GET/SET STATUS is an optional feature, so it may not be negotiated. In
that case, the VIRTIO_GET_STATUS call will not update the status (given
as a pointer argument). Failing to identify this case would lead to
undefined behavior as the device status will be updated with the value
of a stack-alloca
According to the virtio spec, ACK and DRIVER status bits should be set
before feature negotiation.
However, until the protocol features are negotiated, the driver does not
know if the device actually supports those vhost-user messages.
Therefore, until FEATURES_OK is set, the GET/SET_STATUS messag
If stat fails because the file does not exist, it means that
the backend must be vhost-user in server mode.
Also, log the detected backend type.
Bugzilla ID: 559
Fixes: f908b22ea47a ("net/virtio: move backend type selection to ethdev")
Cc: sta...@dpdk.org
Reviewed-by: Maxime Coquelin
Acked-by:
1 - 100 of 234 matches
Mail list logo
