From: Narcisa Vasile
The Windows netuio kernel driver provides the DPDK userspace application
with direct access to hardware, by mapping the HW registers in userspace
and allowing read/write operations from/to the device
configuration space.
Two IOCTLs are defined by the netuio interface:
* IO
This is an improved version of the setup of huge pages
bases on earlier DPDK setup.
Differences are:
* autodetects NUMA vs non NUMA
* allows setting different page sizes
recent kernels support multiple sizes.
* accepts a parameter in bytes (not pages).
* can display current hugepa
On Mon, Aug 24, 2020 at 11:53:44PM +0300, Dmitry Kozlyuk wrote:
> On Thu, 20 Aug 2020 15:23:55 -0700, Narcisa Ana Maria Vasile wrote:
> > From: Narcisa Vasile
> >
> > The Windows NetUIO kernel driver allows the DPDK userspace
> > application to directly access the hardware.
> >
> > Cc: Harini Ra
On Thu, Aug 20, 2020 at 06:32:02PM -0700, Ranjit Menon wrote:
> Hi, Naty
>
> On 8/20/2020 3:23 PM, Narcisa Ana Maria Vasile wrote:
> >From: Narcisa Vasile
> >
> >The Windows NetUIO kernel driver allows the DPDK userspace
> >application to directly access the hardware.
> >
> >Cc: Harini Ramakrishn
On Tue, 8 Sep 2020 21:17:50 +0100
Cristian Dumitrescu wrote:
> +/*
> + * Pipeline.
> + */
> +struct rte_swx_pipeline {
> + int build_done;
> + int numa_node;
> +};
> +
> +
Is int the right type for these.
build_done seems like a boolean
and numa_node should be unsigned?
> >
> > diff --git a/lib/librte_eal/include/rte_eal.h
> b/lib/librte_eal/include/rte_eal.h
> > > index ddcf6a2e7a..8148f650f2 100644
> > > --- a/lib/librte_eal/include/rte_eal.h
> > > +++ b/lib/librte_eal/include/rte_eal.h
> > > @@ -43,6 +43,13 @@ enum rte_proc_type_t {
> > > RTE_PROC_INVALID
Hi Stephen,
> -Original Message-
> From: Stephen Hemminger
> Sent: Wednesday, September 9, 2020 8:06 PM
> To: Dumitrescu, Cristian
> Cc: dev@dpdk.org
> Subject: Re: [dpdk-dev] [PATCH v3 01/41] pipeline: add new SWX pipeline
> type
>
> On Tue, 8 Sep 2020 21:17:50 +0100
> Cristian Dumitr
Fixes and optimizations to improve bnxt vector mode
performance and functionality.
Lance Richardson (12):
net/bnxt: fix burst mode get for Arm
net/bnxt: fix rxq/txq get information
net/bnxt: use appropriate type for Rx mbuf ring
net/bnxt: require async cq for vector mode
net/bnxt: improv
Return correct values for Rx/Tx offloads and for rx_drop_en.
Fixes: 2fc201884be8 ("net/bnxt: support rxq/txq get information")
Reviewed-by: Ajit Kumar Khaparde
Signed-off-by: Lance Richardson
Cc: sta...@dpdk.org
---
drivers/net/bnxt/bnxt_ethdev.c | 4 +++-
1 file changed, 3 insertions(+), 1 del
Transmit and receive burst mode get operations incorrectly return
"Vector SSE" on ARM64 platforms, change to return "Vector Neon"
instead.
Fixes: 3983583414 ("net/bnxt: support NEON")
Reviewed-by: Ajit Kumar Khaparde
Signed-off-by: Lance Richardson
Cc: sta...@dpdk.org
---
drivers/net/bnxt/bnxt_
Improve support for small ring sizes:
- Ensure that transmit free threshold is no more than 1/4 ring size.
- Ensure that receive free threshold is no more than 1/4 ring size.
- Validate requested ring sizes against minimum supported size.
- Use rxq receive free threshold instead of fixe
Change the type of the software receive mbuf ring from an array
of structures containing an mbuf pointer to an array of pointers
to struct rte_mbuf for consistency with how this ring is currently
used by the vector mode receive function.
Reviewed-by: Ajit Kumar Khaparde
Reviewed-by: Somnath Kotur
Don't allocate extra completion queue entries for aggregation
ring when aggregation ring will not be used.
Reviewed-by: Ajit Kumar Khaparde
Signed-off-by: Lance Richardson
---
drivers/net/bnxt/bnxt_ethdev.c | 11 +--
drivers/net/bnxt/bnxt_rxr.c| 21 +++--
2 files cha
Disable support for vector mode when async completions can be placed
in a receive completion ring and change the default for all platforms
to use a dedicated async completion ring.
Simplify completion handling in vector mode receive paths now that
it no longer needs to handle async completions.
R
Use table to translate receive descriptor status flags to
rte_mbuf ol_flags values.
Reviewed-by: Ajit Kumar Khaparde
Signed-off-by: Lance Richardson
---
drivers/net/bnxt/bnxt_rxr.c | 166 --
drivers/net/bnxt/bnxt_rxr.h | 6 +
drivers/net/bnxt/bnxt_r
Use table-based method for translating receive packet descriptor
flags into rte_mbuf packet type values.
Reviewed-by: Ajit Kumar Khaparde
Signed-off-by: Lance Richardson
---
drivers/net/bnxt/bnxt_rxr.c | 127 --
drivers/net/bnxt/bnxt_rxr.h | 2 +
dr
Increase the maximum supported burst size for the bnxt vector
mode PMD from 32 to 64.
Reviewed-by: Kalesh Anakkur Purayil
Reviewed-by: Ajit Kumar Khaparde
Signed-off-by: Lance Richardson
---
drivers/net/bnxt/bnxt_rxtx_vec_common.h | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff
Process four receive descriptors per inner loop in vector mode
burst receive functions.
Reviewed-by: Ajit Kumar Khaparde
Signed-off-by: Lance Richardson
---
drivers/net/bnxt/bnxt_ethdev.c | 2 +-
drivers/net/bnxt/bnxt_rxq.c | 3 +-
drivers/net/bnxt/bnxt_rxq.h
Simplify and optimize receive mbuf allocation function used
by the vector mode PMDs.
Reviewed-by: Ajit Kumar Khaparde
Signed-off-by: Lance Richardson
---
drivers/net/bnxt/bnxt_rxtx_vec_common.h | 40 ++
drivers/net/bnxt/bnxt_rxtx_vec_neon.c | 70 -
drivers/
Improve performance of vector burst transmit function by processing
multiple packets per inner loop iteration.
Signed-off-by: Lance Richardson
---
drivers/net/bnxt/bnxt_rxtx_vec_sse.c | 96 +++-
1 file changed, 66 insertions(+), 30 deletions(-)
diff --git a/drivers/net/b
The RFC introduces Stateful Flow Table (SFT) API and changes needed in
both ethdev an RTE flow to support SFT functionality.
SFT library provides a framework for applications that need to maintain
context across different packets of the connection.
The goals of the SFT library:
- Accelerate flow
Attach SFT flow context to packet with SFT action.
Match on SFT flow context (attached to packet),
with SFT item.
Signed-off-by: Andrey Vesnovaty
---
lib/librte_ethdev/rte_flow.h | 84
1 file changed, 84 insertions(+)
diff --git a/lib/librte_ethdev/rte_flow.
ethdev updated to support SFT lookup offload
to ethernet device.
Signed-off-by: Andrey Vesnovaty
---
lib/librte_ethdev/rte_ethdev.c | 7 +++
lib/librte_ethdev/rte_ethdev.h | 16
lib/librte_ethdev/rte_ethdev_core.h | 1 +
3 files changed, 24 insertions(+)
diff --
Defines RTE SFT APIs for Statefull Flow Table library.
SFT General description:
SFT library provides a framework for applications that need to maintain
context across different packets of the connection.
Examples for such applications:
- Next-generation firewalls
- Intrusion detection/prevention s
The telemetry library is connected with eventdev xstats and
port link info. The following new telemetry commands are added:
/eventdev/dev_list
/eventdev/port_list,DevID
/eventdev/queue_list,DevID
/eventdev/dev_xstats,DevID
/eventdev/port_xstats,DevID,PortID
/eventdev/queue_xstats,DevID,PortID
/eve
5G DL default symlink was pointing to a 4G vector.
Fixes: d762705308c4 ("app/bbdev: add test vectors for 5GNR")
Cc: sta...@dpdk.org
Signed-off-by: Nicolas Chautru
---
app/test-bbdev/ldpc_enc_default.data | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/app/test-bbdev/ldpc_enc
Here I have removed 'that' from the sentence to make it grammatically
correct, as it seems to be a typing mistake
Fixes: d0dff9ba445e ("doc: sample application user guide")
Cc: bernard.iremon...@intel.com
Signed-off-by: Muhammad Bilal
---
doc/guides/prog_guide/multi_proc_support.rst | 2 +-
doc
> >
> > 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
> > e
Hi Abhinandan,
This test case looks good. I think you could add few negative test
cases as well. For ex: removing the call back without registering the RCU.
Thanks,
Honnappa
> >
> > The purpose of this testcase is to showcase the cryptodev enqueue
> > callback usage with RCU support.
>
On Sun, Aug 23, 2020 at 04:06:04PM +0300, Tal Shnaiderman wrote:
> From: Tal Shnaiderman
>
> Swap subsystem vendor id and subsystem device id.
> Parse the SPDRP_HARDWAREID string with correct type values.
>
> Fixes: b762221ac24 ("bus/pci: support Windows with bifurcated drivers")
> Cc: sta...@dp
On Tue, Aug 25, 2020 at 02:43:16PM +0300, Tal Shnaiderman wrote:
> Set the domain value for rte_pci_addr probing on Windows
> to the value of the PCI segment returned by SPDRP_BUSNUMBER.
>
> Signed-off-by: Tal Shnaiderman
> ---
> drivers/bus/pci/windows/pci.c | 4 ++--
> 1 file changed, 2 insert
snip
>
> diff --git a/doc/guides/tools/hugepages.rst
> b/doc/guides/tools/hugepages.rst
> new file mode 100644
> index ..a82b71620011
> --- /dev/null
> +++ b/doc/guides/tools/hugepages.rst
> @@ -0,0 +1,79 @@
> +.. SPDX-License-Identifier: BSD-3-Clause
> +Copyright (c) 2020
We are including this in rte_prefetch.h since it is the most closely
related code location.rte_cldemte is similar to a prefetch hint -in reverse
Omkar Maslekar (1):
EAL: An addition of cache line demote (CLDEMOTE) in rte_prefetch.h
doc/guides/rel_notes/release_20_11.rst| 26 ---
rte_cldemote is similar to a prefetch hint - in reverse. cldemote(addr)
enables software to hint to hardware that line is likely to be shared.
Useful in core-to-core communications where cache-line is likely to be
shared. ARM and PPC implementation is provided with NOP and can be added
if any equiv
>
> If a timer's callback function calls rte_timer_reset_sync() or
> rte_timer_stop_sync() on another timer that is in the RUNNING state and
> owned by the current lcore, the *_sync() calls will loop indefinitely.
>
> Relatedly, if a timer's callback function calls *_sync() on another timer
>
>
> Use c11 atomics with RELAXED ordering instead of the rte_atomic ops which
> enforce unnecessary barriers on aarch64.
>
> Signed-off-by: Phil Yang
Looks good.
Reviewed-by: Honnappa Nagarahalli
> ---
> v4:
> Remove the unnecessary ACQUIRE barrier in rx burst path. (Honnappa)
>
> v3:
> Sp
> > > > > Phil, we are seeing much worse degradation on our ARM platform
> > > > > unfortunately.
> > > > > I don't think that discrepancy in memcpy can explain this behavior.
> > > > > Your patch is not touching this area of code. Let me collect
> > > > > some perf stat on our side.
> > > > Are
>
>
> >
> > Use c11 atomics with RELAXED ordering instead of the rte_atomic ops
> > which enforce unnecessary barriers on aarch64.
> >
> > Signed-off-by: Phil Yang
> Looks good.
>
> Reviewed-by: Honnappa Nagarahalli
Acked-by: Alexander Kozyrev
>
> > ---
> > v4:
> > Remove the unnecessary A
When a user runs a flow create cmd to configure an RSS rule
with specifying the empty rss actions in testpmd, this mean
that the flow gets the default RSS functions from the valid
NIC default RSS hash key. However, the testpmd is not set
the default RSS key incorrectly when RSS key is not specified
Acked-by: Sachin Saxena
On 09-Sep-20 6:31 PM, Ferruh Yigit wrote:
This patch is a preparation to hide the 'struct eth_dev_ops' from
applications by moving some device operations from 'struct eth_dev_ops'
to 'struct rte_eth_dev'.
Mentioned ethdev APIs are in the data path and implemented as in
This patch fixed the issue that rx/tx bytes overflowed
on 48 bit limitation by enlarging the limitation.
Fixes: 4861cde46116 ("i40e: new poll mode driver")
Cc: sta...@dpdk.org
Signed-off-by: Junyu Jiang
---
drivers/net/i40e/i40e_ethdev.c | 47 ++
drivers/net/i40e
Acked-by: Sachin Saxena
On 09-Sep-20 6:31 PM, Ferruh Yigit wrote:
'_rte_eth_dev_callback_process()' & '_rte_eth_dev_reset()' internal APIs
has unconventional underscore ('_') prefix.
Although this is not documented most probably this is to mark them as
internal. Since we have '__rte_internal' f
On Tue, Sep 8, 2020 at 3:07 AM Ferruh Yigit wrote:
> '__builtin_add_overflow' added to gcc in version 5, earlier versions
> causing build error, like gcc 4.8.5 in RHEL7.
>
> Replaced compiler builtin check with arithmetic check.
>
> Fixes: cabb3c0f29f1 ("net/netvsc: check for overflow on packet i
meson build cannot find the header rte_eth_bond.h when build DPDK first
time or never installed DPDK lib after build via meson/ninja.
Because the corresponding header directory isn't included after enabled
RTE_LIBRTE_PMD_BOND macro.
Add the header file location and link library to meson.build of
Tested-by: Yingya Han
-Original Message-
From: stable On Behalf Of Junyu Jiang
Sent: Thursday, September 10, 2020 9:54 AM
To: dev@dpdk.org
Cc: Guo, Jia ; Xing, Beilei ; Jiang,
JunyuX ; sta...@dpdk.org
Subject: [dpdk-stable] [PATCH] net/i40e: fix incorrect byte counters
This patch fixed
meson build cannot find the header rte_latencystats.h when build DPDK
first time or never installed DPDK lib after build via meson/ninja.
Because the corresponding header directory isn't included after enabled
RTE_LIBRTE_LATENCY_STATS flag.
Add the header file location and link library to meson.b
No more comments on this patch.
Thanks,
Jiayu
From: yang_y_yi
Sent: Wednesday, September 9, 2020 5:00 PM
To: Hu, Jiayu
Cc: tho...@monjalon.net; dev@dpdk.org; yangy...@inspur.com
Subject: Re:Re: [dpdk-dev] [PATCH v4 1/2] gro: add UDP GRO support
Importance: High
This is incremental patch to fix
These should be fixed before release!
Makefiles will be dropped.
The ethdev stuff is from Jan Blunck, let me see if I can find current email.
$ ./devtools/check-spdx-tag.sh -v
Files without SPDX License
--
doc/guides/custom.css
doc/guides/linux_gsg/nic_perf_intel_platform.
> -Original Message-
> From: Yang, Qiming
> Sent: Wednesday, September 9, 2020 3:17 PM
> To: Zhang, Qi Z
> Cc: dev@dpdk.org
> Subject: RE: [PATCH 00/40] ice base code update
>
>
>
> > -Original Message-
> > From: Zhang, Qi Z
> > Sent: Monday, September 7, 2020 19:28
> > To:
From: Alvin Zhang
Add headers for GTPU, now outer IP hash can be configured as input
sets for GTPU packet.
Signed-off-by: Alvin Zhang
---
V2: Modify codes according to comments.
V3: Refact all codes.
V4: Fix compatibility issues.
drivers/net/iavf/iavf_hash.c | 13 +
1 file chang
From: Alvin Zhang
Add GTPC header and its field selector.
Signed-off-by: Alvin Zhang
---
drivers/common/iavf/virtchnl.h | 4
1 file changed, 4 insertions(+)
diff --git a/drivers/common/iavf/virtchnl.h b/drivers/common/iavf/virtchnl.h
index 79515ee..0042cc0 100644
--- a/drivers/common/iav
From: Alvin Zhang
Add patterns and headers for GTPC, now outer IP hash can be configured
as input sets for GTPC packet.
Signed-off-by: Alvin Zhang
---
V2: Modify codes according to comments.
V3: Refact all codes.
V4: Fix compatibility issues.
drivers/net/iavf/iavf_generic_flow.c | 18 +++
There was a segment fault when dump flows with device argument of
dv_flow_en=0. In such case, Verbs flow engine was enabled and fdb
resources were not initialized. It's suggested to use mlx_fs_dump
for Verbs flow dump.
This patch adds verbs engine check, prints warning message and return
gracefull
There was a segment fault when dump flows with device argument of
dv_flow_en=0. In such case, Verbs flow engine was enabled and fdb
resources were not initialized. It's suggested to use mlx_fs_dump
for Verbs flow dump.
This patch adds verbs engine check, prints warning message and return
gracefull
Hi, Alvin
> -Original Message-
> From: Zhang, AlvinX
> Sent: Thursday, September 10, 2020 11:37 AM
> To: Guo, Jia ; Zhang, Qi Z
> Cc: dev@dpdk.org; Zhang, AlvinX
> Subject: [PATCH v4 2/2] net/iavf: support outer IP hash for GTPC
>
> From: Alvin Zhang
>
> Add patterns and headers for
> -Original Message-
> From: Zhang, AlvinX
> Sent: Thursday, September 10, 2020 11:26 AM
> To: Guo, Jia ; Zhang, Qi Z
> Cc: dev@dpdk.org; Zhang, AlvinX
> Subject: [PATCH v4] net/iavf: support outer IP hash for GTPU
>
> From: Alvin Zhang
>
> Add headers for GTPU, now outer IP hash ca
Hi, junyu
> -Original Message-
> From: Han, YingyaX
> Sent: Thursday, September 10, 2020 10:18 AM
> To: Jiang, JunyuX ; dev@dpdk.org
> Cc: Guo, Jia ; Xing, Beilei ; Jiang,
> JunyuX ; sta...@dpdk.org
> Subject: RE: [dpdk-stable] [PATCH] net/i40e: fix incorrect byte counters
>
> Tested-by:
AVX512 instructions is supported by more and more platforms. These
instructions can be used in the data path to enhance the per-core
performance of packet processing.
Comparing with the existing implementation, this path set introduces
some AVX512 instructions into the iavf data path, and we get a
To enhance the per-core performance, this patch adds some AVX512
instructions to the data path to handle the legacy RX descriptors.
Signed-off-by: Wenzhuo Lu
Signed-off-by: Bruce Richardson
Signed-off-by: Leyi Rong
---
drivers/net/iavf/iavf_rxtx.c| 27 +-
drivers/net/iavf/iavf_rxt
To enhance the per-core performance, this patch adds some AVX512
instructions to the data path to hande the flexible RX descriptors.
Signed-off-by: Wenzhuo Lu
Signed-off-by: Bruce Richardson
Signed-off-by: Leyi Rong
---
drivers/net/iavf/iavf_rxtx.c| 10 +
drivers/net/iavf/iavf_rxt
Add module EEPROM/EEPROM dump command
"show port (module_eeprom|eeprom)"
Commands will dump the content of the
EEPROM/module EEPROM for the selected port.
Signed-off-by: David Liu
---
app/test-pmd/cmdline.c | 50
app/test-pmd/config.c | 120
To enhance the per-core performance, this patch adds some AVX512
instructions to the data path to handle the TX descriptors.
Signed-off-by: Wenzhuo Lu
Signed-off-by: Bruce Richardson
Signed-off-by: Leyi Rong
---
doc/guides/rel_notes/release_20_11.rst | 3 +
drivers/net/iavf/iavf_ethdev.c
HI guojia,
> -Original Message-
> From: Guo, Jia
> Sent: Thursday, September 10, 2020 1:59 PM
> To: Han, YingyaX ; Jiang, JunyuX
> ; dev@dpdk.org
> Cc: Xing, Beilei ; Jiang, JunyuX
> ; sta...@dpdk.org
> Subject: RE: [dpdk-stable] [PATCH] net/i40e: fix incorrect byte counters
>
> Hi, juny
This patch set makes vhost-vswitch be able to use vhost async APIs
for enqueue operations. Demonstrated how the application
leverage IOAT DMA channel with vhost async APIs.
We introduce two parameters to enable DMA acceleration for Tx
operations of queues:
-async_vhost_driver Async vhost-user net
Add release notes for vhost async data path support in vhost sample.
Signed-off-by: Cheng Jiang
---
doc/guides/rel_notes/release_20_11.rst | 6 ++
1 file changed, 6 insertions(+)
diff --git a/doc/guides/rel_notes/release_20_11.rst
b/doc/guides/rel_notes/release_20_11.rst
index df227a177..6
This patch is to add async vhost driver arguments parsing function
for CBDMA channel. With these arguments vhost sample can be set to
use CBDMA or CPU for enqueue operation and bind vhost device with
specific CBDMA channel to accelerate vhost data-path.
Signed-off-by: Cheng Jiang
---
examples/vh
Add vhost async driver arguments information for vhost async data
path in vhost sample application.
Signed-off-by: Cheng Jiang
---
doc/guides/sample_app_ug/vhost.rst | 10 ++
1 file changed, 10 insertions(+)
diff --git a/doc/guides/sample_app_ug/vhost.rst
b/doc/guides/sample_app_ug/vho
This patch is to implement vhost DMA operation callbacks for CBDMA
PMD and add vhost async data-path in vhost sample. With providing
callback implementation for CBDMA, vhost sample can leverage
CBDMA to accelerate vhost async data-path.
Signed-off-by: Cheng Jiang
---
examples/vhost/main.c | 129
101 - 168 of 168 matches
Mail list logo
