Hi, haiyue
> -Original Message-
> From: Wang, Haiyue
> Sent: Wednesday, September 9, 2020 2:45 PM
> To: Guo, Jia ; Yang, Qiming ;
> Xing, Beilei ; Zhao1, Wei ;
> Zhang, Qi Z ; Wu, Jingjing
> Cc: Richardson, Bruce ; dev@dpdk.org; Zhang,
> Helin ; m...@smartsharesystems.com; Yigit, Ferruh
> -Original Message-
> From: Guo, Jia
> Sent: Wednesday, September 9, 2020 15:03
> To: Wang, Haiyue ; Yang, Qiming
> ; Xing, Beilei
> ; Zhao1, Wei ; Zhang, Qi Z
> ; Wu,
> Jingjing
> Cc: Richardson, Bruce ; dev@dpdk.org; Zhang,
> Helin ;
> m...@smartsharesystems.com; Yigit, Ferruh ;
>
Add support for IAVF request queues from PF. VF sends desired queue
pairs number to PF to ask for queue allocation. If the request succeeds,
VF should reset. If fails, PF will return available queue pairs number.
Signed-off-by: Ting Xu
---
drivers/net/iavf/iavf.h| 17 +
drivers/net/
> -Original Message-
> From: Zhang, Qi Z
> Sent: Monday, September 7, 2020 19:28
> To: Yang, Qiming
> Cc: dev@dpdk.org; Zhang, Qi Z
> Subject: [PATCH 00/40] ice base code update
>
> main changes:
> 1. Added support for outer IP filter for GTPC.
> 2. Added support for outer IP filter
Add support to configure VSI queues, enable/disable queues and IRQ
mapping for large VF. The max VF queue pairs number is 256. Request
more queues from PF if allocated queues are not enough. Add support
to query max RSS queue regions number. Large VF offload should be
supported before configuring l
This patchset supports to configure up to 256 queue pairs per VF. If
large VF is supported, VF will request queues from PF as needed. New
virtual channel opcodes and structures are used to indicate 256 queues,
so VF is designed to handle the new function of configure VSI queues, IRQ
mapping and ena
All the format issue will be rechecked in the next version
> -Original Message-
> From: Xing, Beilei
> Sent: Tuesday, September 8, 2020 19:35
> To: Yang, Qiming ; dev@dpdk.org
> Cc: Zhang, Qi Z ; Yang, Qiming
>
> Subject: RE: [dpdk-dev] [PATCH 1/2] net/ice: add dcf port representor
> inf
At 2020-09-08 10:05:16, "Jiayu Hu" wrote:
>Some comments are inline.
Thanks, replies inline.
>
>Thanks,
>Jiayu
>
>On Fri, Sep 04, 2020 at 04:37:39PM +0800, yang_y...@163.com wrote:
>> From: Yi Yang
>>
>> UDP GRO can help improve VM-to-VM UDP performance when
>> VM is enabled UFO or GSO, GRO
From: FuYanX
Add delay to ensure that the hardware FLR is completed.
Fixes: f9cf4f864150 (net/ice: support device initialization)
Cc: sta...@dpdk.org
Signed-off-by: FuYanX
---
drivers/net/ice/ice_ethdev.c | 5 +
1 file changed, 5 insertions(+)
diff --git a/drivers/net/ice/ice_ethdev.c b/
> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Wang, Haiyue
> Sent: Wednesday, September 9, 2020 9:05 AM
>
> > From: Guo, Jia
> > Sent: Wednesday, September 9, 2020 15:03
> >
> > Hi, haiyue
> >
> > > From: Wang, Haiyue
> > > Sent: Wednesday, September 9, 2020 2:45 PM
> > >
> > > > From:
> -Original Message-
> From: Morten Brørup
> Sent: Wednesday, September 9, 2020 15:43
> To: Wang, Haiyue ; Guo, Jia ; Yang,
> Qiming
> ; Xing, Beilei ; Zhao1, Wei
> ; Zhang,
> Qi Z ; Wu, Jingjing
> Cc: Richardson, Bruce ; dev@dpdk.org; Zhang,
> Helin ;
> Yigit, Ferruh ; step...@network
> -Original Message-
> From: Wang, Haiyue
> Sent: Wednesday, September 9, 2020 3:55 PM
> To: Morten Brørup ; Guo, Jia
> ; Yang, Qiming ; Xing, Beilei
> ; Zhao1, Wei ; Zhang, Qi Z
> ; Wu, Jingjing
> Cc: Richardson, Bruce ; dev@dpdk.org; Zhang,
> Helin ; Yigit, Ferruh ;
> step...@networkplu
Hello Vimal,
On Wed, Sep 9, 2020 at 3:11 AM Vimal Chungath wrote:
>
> These two patches add meson and make build configuration
> for AWS Graviton2 platform. I plan to send platform guide
> patch separately.
>
> Vimal Chungath (2):
> config: add Graviton2(arm64) meson configuration
> config: a
Although currently only the gtpu inner hash be enabled while not the
gtpu outer hash, but the outer protocol still needed to co-exist with
inner protocol when configure the gtpu inner hash rule, that would
allow the gtpu innner hash support for the different outer protocols.
Signed-off-by: Jeff Gu
Before this commit system call memalign was used for aligned
allocations, however memalign is deprecated.
Based on (1) - POSIX requires that memory aligned allocations can be
freed using free. Some systems provide no way to reclaim memory
allocated with memalign (because one can only pass to free
https://bugs.dpdk.org/show_bug.cgi?id=535
Bug ID: 535
Summary: mlx5: vlan/qinq packets are not matched by eth/ipv4
RTE_FLOW
Product: DPDK
Version: 19.11
Hardware: All
OS: All
Status: UNCONFIRMED
> -Original Message-
> From: Sun, GuinanX
> Sent: Tuesday, September 8, 2020 11:15 AM
> To: dev@dpdk.org
> Cc: Zhang, Qi Z ; Yang, Qiming
> ; Sun, GuinanX ;
> sta...@dpdk.org
> Subject: [PATCH v2] net/ice: fix flow validation for unsupported patterns
>
> When loading the OS default pac
This is incremental patch to fix your new comments, I'll send out v5 if no more
comments here.
diff --git a/lib/librte_gro/gro_udp4.c b/lib/librte_gro/gro_udp4.c
index 25584fd..061e7b0 100644
--- a/lib/librte_gro/gro_udp4.c
+++ b/lib/librte_gro/gro_udp4.c
@@ -107,7 +107,7 @@
uint32_t i
This series are updates for Rx/Tx process.
Chengchang Tang (1):
net/hns3: fix segfault when Tx multiple buffer packets
Wei Hu (Xavier) (7):
net/hns3: report Rx free threshold
net/hns3: reduce address calculation in Rx
net/hns3: add simple Rx process function
net/hns3: add simple Tx proc
From: "Wei Hu (Xavier)"
This patch reports .rx_free_thresh value in the .dev_infos_get ops
implementation function named hns3_dev_infos_get and hns3vf_dev_infos_get.
In addition, the name of the member variable of struct hns3_rx_queue is
modified and comments are added to improve code readability
From: "Wei Hu (Xavier)"
This patch adds simple Rx process function and support chose Rx function
by real Rx offloads capability.
Signed-off-by: Chengwen Feng
Signed-off-by: Wei Hu (Xavier)
Signed-off-by: Huisong Li
---
drivers/net/hns3/hns3_ethdev.c| 7 +-
drivers/net/hns3/hns3_ethdev.
From: "Wei Hu (Xavier)"
This patch adds the internal function named hns3_write_reg_opt to avoid
performance loss from address calculation during register access in the
'.rx_pkt_burst' ops implementation function named hns3_recv_pkts.
In addition, because hardware always access register in little
From: "Wei Hu (Xavier)"
This patch adds NEON vector instructions to optimize Rx burst process.
Signed-off-by: Chengwen Feng
Signed-off-by: Wei Hu (Xavier)
Signed-off-by: Huisong Li
---
drivers/net/hns3/hns3_ethdev.c| 1 +
drivers/net/hns3/hns3_ethdev.h| 1 +
drivers/net/h
From: "Wei Hu (Xavier)"
This patch adds simple Tx process function. When multiple segment packets
are not needed, Which means that DEV_TX_OFFLOAD_MBUF_FAST_FREE offload is
not set, we can simple Tx process.
Signed-off-by: Huisong Li
Signed-off-by: Wei Hu (Xavier)
Signed-off-by: Chengwen Feng
From: "Wei Hu (Xavier)"
This patch adds NEON vector instructions to optimize Tx burst process.
Signed-off-by: Huisong Li
Signed-off-by: Wei Hu (Xavier)
Signed-off-by: Chengwen Feng
---
v1 -> v2: modification about meson.build for hns3_rxtx_vec.c file.
---
drivers/net/hns3/hns3_ethdev.c
From: Chengchang Tang
Currently, there is a possibility that segment faults occur when sending
packets whose payloads are stored in multiple buffers based on hns3 network
engine. The related core dump information as follows:
Program terminated with signal 11, Segmentation fault.
0 hns3_reassemb
From: "Wei Hu (Xavier)"
when Rx of scattered packets is off, we have some possibility of using
vector Rx process function or simple Rx functions in hns3 PMD driver.
If the input MTU is increased and the maximum length of received packets
is greater than the length of a buffer for Rx packets, the
Existing API supports AGE action to monitor the aging of a single flow.
Recent patch [1] introduced the shared action API.
Using this API, an action can be created as shared, unattached to any
flow rule.
Multiple flows can then be created using the shared action.
The new API also supports query op
> app/test/test_rawdev.c | 2 +-
> doc/guides/rawdevs/ioat.rst | 4 +-
> doc/guides/rawdevs/octeontx2_dma.rst| 2 +-
> doc/guides/rawdevs/octeontx2_ep.rst | 3 +-
> doc/guides/rel_notes/deprecation.rst| 7 ---
> doc/guides/sample_ap
Hi, Jeff
> From: dev On Behalf Of Jeff Guo
> Sent: Wednesday, September 9, 2020 2:37 PM
> To: qiming.y...@intel.com; beilei.x...@intel.com; wei.zh...@intel.com;
> qi.z.zh...@intel.com; jingjing...@intel.com
> Cc: bruce.richard...@intel.com; dev@dpdk.org; jia@intel.com;
> helin.zh...@intel.com
Hi!
It looks like that the sample application 'Load Balancer' is not present
anymore in version 19.11.3. The last version wehere I can find this sample
application is version 18.08.1. Is there a specific reason for not providing
this sample application in newer versions?
Kind regards,
Peter
On 08-Sep-20 5:19 PM, Adam Dybkowski wrote:
This patch marks the old igb-uio driver as unsecure when used
with the QAT PMD and updates all examples to recommend using
vfio-pci instead.
It also mentions security issues with the QAT CPM and provides
information about the new vfio-pci parameter 'dis
Marking 'rte_eth_rx_descriptor_done()' API as deprecated.
``rte_eth_rx_descriptor_status`` and ``rte_eth_tx_descriptor_status``
APIs can be used as replacement.
Plan is to remove the API on 21.11 release.
Signed-off-by: Ferruh Yigit
---
Cc: David Marchand
v3:
* Just deprecating the 'rte_eth_rx
Hiding the 'struct eth_dev_ops' from applications.
Removing relevant deprecation notice.
Signed-off-by: Ferruh Yigit
Acked-by: Andrew Rybchenko
---
Cc: David Marchand
v3:
* release note updated
---
doc/guides/rel_notes/deprecation.rst | 9 -
doc/guides/rel_notes/release_20_11.rst |
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 inline
because of performance reasons.
Exposing 'struct eth_dev_ops' to
Some ethdev functions are for drivers only, not for applications.
Since we have '__rte_internal' tag available now, marking internal
functions with it and moving functions to INTERNAL section in linker
script.
This is also good for documenting the internal functions.
Some internal APIs seems mark
'_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' flag to mark this, removing '_'
from API names.
For '_rte_eth_dev_rese
These are struct type names, not object names. Removing them from .map
file.
Fixes: 9d41beed24b0 ("lib: provide initial versioning")
Cc: sta...@dpdk.org
Signed-off-by: Ferruh Yigit
Reviewed-by: Andrew Rybchenko
---
lib/librte_ethdev/rte_ethdev_version.map | 2 --
1 file changed, 2 deletions(-)
Hairpin helper functions were not used by drivers, but it was used only
local to ethdev. They are:
'rte_eth_dev_is_rx_hairpin_queue()'
'rte_eth_dev_is_tx_hairpin_queue()'
Exposing them as internal APIs and update mlx5 driver (only user of
hairpin) to use them.
Signed-off-by: Ferruh Yigit
Acked-b
On 9/8/2020 1:10 PM, Ferruh Yigit wrote:
> On 9/8/2020 11:19 AM, Thomas Monjalon wrote:
>> 08/09/2020 11:55, Ferruh Yigit:
>>> On 9/4/2020 1:51 PM, Ferruh Yigit wrote:
Series applied to dpdk-next-net/main, thanks.
>>>
>>> Hi Hemant,
>>>
>>> I need to drop the series from next-net, since new fi
On 9/3/2020 11:13 AM, Michael Baum wrote:
> Separate Rx indirection table object creation into both Verbs and DevX
> modules.
>
> Signed-off-by: Michael Baum
> Acked-by: Matan Azrad
<...>
> + if (!ind_tbl->ind_table) {
> + rte_errno = errno;
> + goto error;
> +
On 9/8/2020 4:17 PM, Stephen Hemminger wrote:
> This is an improved version of the setup of huge pages
> bases on earlier DPDK setup.
>
> Features:
>* can display current hugepage settings.
>* autodetects NUMA vs non NUMA
>* allows setting different page sizes
> recent kernels sup
Build error seen with Linux kernel 5.9.
Build error:
kernel/linux/kni/kni_dev.h:104:30:
error: passing argument 1 of ‘get_user_pages_remote’ from
incompatible pointer type [-Werror=incompatible-pointer-types]
ret = get_user_pages_remote(tsk, tsk->mm, iova, 1,
get_user_page
On Wed, Sep 9, 2020 at 1:12 PM Ferruh Yigit wrote:
>
> Marking 'rte_eth_rx_descriptor_done()' API as deprecated.
> ``rte_eth_rx_descriptor_status`` and ``rte_eth_tx_descriptor_status``
> APIs can be used as replacement.
>
> Plan is to remove the API on 21.11 release.
>
> Signed-off-by: Ferruh Yigi
From: Guy Kaneti
The L3 Forwarding with Regex application is a simple example of
packet processing using DPDK Regex framework.
The application performs L3 LPM based forwarding while using
Regex framework for pre-filtering decision.
v2:
* Rebase.
* Add release notes.
* fix spelling mistake
* fix
From: Guy Kaneti
Add regex based l3fwd application
inline with normal l3fwd. only LPM is supported.
Signed-off-by: Guy Kaneti
---
MAINTAINERS|2 +
examples/l3fwd-regex/l3fwd.h | 207 ++
examples/l3fwd-regex/l3fwd_lpm.c | 484
examples/l3fw
From: Guy Kaneti
Adding the user guide for l3fwd regex application.
Signed-off-by: Guy Kaneti
---
MAINTAINERS | 1 +
doc/guides/rel_notes/release_20_11.rst| 4 +
doc/guides/sample_app_ug/index.rst| 1 +
doc/guides/sample_app_ug/intro.
This patch adds Forward error correction(FEC) support for ethdev.
Introduce APIs which support query and config FEC information in
hardware.
Signed-off-by: Min Hu (Connor)
Reviewed-by: Wei Hu (Xavier)
Reviewed-by: Chengwen Feng
Reviewed-by: Chengchang Tang
---
v2->v3:
add function return valu
This series add FEC support for ethdev.
Min Hu (Connor) (3):
ethdev: introduce FEC API
net/hns3: support FEC
app/testpmd: add FEC command
app/test-pmd/cmdline.c | 219 +++
app/test-pmd/config.c| 54
app/test-pmd/te
Forward error correction (FEC) is a bit error correction mode.
It adds error correction information to data packets at the
transmit end, and uses the error correction information to correct
the bit errors generated during data packet transmission at the
receive end. This improves signal quality but
This commit adds testpmd capability to query and config FEC
function of device. This includes:
- show FEC capabilities, example:
testpmd> show port 0 fec capabilities
- show FEC mode, example:
testpmd> show port 0 fec_mode
- config FEC mode, example:
testpmd> set port 0
20/07/2020 21:18, Kadam, Pallavi:
>
> On 7/7/2020 1:48 AM, tal...@mellanox.com wrote:
> > From: Tal Shnaiderman
> >
> > This patchset implements the EAL functions needed for probing PMDs using
> > vdev on Windows.
> >
> Tested-by: Pallavi Kadam
Applied, thanks
On 9/9/2020 12:59 PM, Min Hu (Connor) wrote:
> Build error seen with Linux kernel 5.9.
>
> Build error:
> kernel/linux/kni/kni_dev.h:104:30:
> error: passing argument 1 of ‘get_user_pages_remote’ from
> incompatible pointer type [-Werror=incompatible-pointer-types]
> ret = get_us
On 9/9/2020 12:12 PM, Ferruh Yigit wrote:
> Hiding the 'struct eth_dev_ops' from applications.
>
> Removing relevant deprecation notice.
>
> Signed-off-by: Ferruh Yigit
> Acked-by: Andrew Rybchenko
<...>
> --- a/doc/guides/rel_notes/release_20_11.rst
> +++ b/doc/guides/rel_notes/release_20_11
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 inline
because of performance reasons.
Exposing 'struct eth_dev_ops' to
Hiding the 'struct eth_dev_ops' from applications.
Removing relevant deprecation notice.
Signed-off-by: Ferruh Yigit
Acked-by: Andrew Rybchenko
Acked-by: David Marchand
---
Cc: David Marchand
v3:
* release note updated
v4:
* Fix wording in release notes, s/inline/internal
---
doc/guides/rel
Marking 'rte_eth_rx_descriptor_done()' API as deprecated.
``rte_eth_rx_descriptor_status`` and ``rte_eth_tx_descriptor_status``
APIs can be used as replacement.
Plan is to remove the API on 21.11 release.
Signed-off-by: Ferruh Yigit
Acked-by: David Marchand
---
Cc: David Marchand
v3:
* Just d
Some ethdev functions are for drivers only, not for applications.
Since we have '__rte_internal' tag available now, marking internal
functions with it and moving functions to INTERNAL section in linker
script.
This is also good for documenting the internal functions.
Some internal APIs seems mark
These are struct type names, not object names. Removing them from .map
file.
Fixes: 9d41beed24b0 ("lib: provide initial versioning")
Cc: sta...@dpdk.org
Signed-off-by: Ferruh Yigit
Reviewed-by: Andrew Rybchenko
Acked-by: David Marchand
---
lib/librte_ethdev/rte_ethdev_version.map | 2 --
1 fi
'_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' flag to mark this, removing '_'
from API names.
For '_rte_eth_dev_rese
Hairpin helper functions were not used by drivers, but it was used only
local to ethdev. They are:
'rte_eth_dev_is_rx_hairpin_queue()'
'rte_eth_dev_is_tx_hairpin_queue()'
Exposing them as internal APIs and update mlx5 driver (only user of
hairpin) to use them.
Signed-off-by: Ferruh Yigit
Acked-b
>
> > >
> > > > >
> > > > > > > > > > > @@ -1790,9 +1792,9 @@ mlx5_rx_burst_mprq(void
> > > *dpdk_rxq,
> > > > > > > struct
> > > > > > > > > > > rte_mbuf **pkts, uint16_t pkts_n) void *buf_addr;
> > > > > > > > > > >
> > > > > > > > > > > /* Increment the refcnt of the whole chunk. */
> > > > >
On 9/8/2020 8:20 PM, Ed Czeck wrote:
> Use ARK_PMD_LOG in place of PMD_DRV_LOG, PMD_DEBUG_LOG, PMD_FUNC_LOG,
> PMD_STATS_LOG, PMD_RX_LOG, and PMD_TX_LOG.
> Review and adjust log levels and messages as needed.
>
> Signed-off-by: Ed Czeck
For series,
Reviewed-by: Ferruh Yigit
Series applied to d
This series adds VF representors to the driver. It enables
single-queue representors and implements enough flow features to run
OVS-DPDK offload for default vlan+mac based switching.
The flow API handlers and devcmd functions (firmware commands) are now
aware of representors. Representors reserve
VF representors need to proxy devcmd through the PF vnic_dev
instance. Extend vnic_dev to accommodate them as follows.
1. Add vnic_vf_rep_register()
A VF representor creates its own vnic_dev instance via this function
and saves VF ID. When performing devcmd, vnic_dev uses the saved VF ID
to proxy
VF representor ports can create flows on VFs through the PF flowman
(Flow Manager) instance in the firmware. These flows match packets
egressing from VFs and apply flowman actions.
1. Make flow handler aware of VF representors
When a representor port invokes flow APIs, use the PF port's flowman
in
A VF representor allocates queues from PF's pool of queues and use
them for its Tx and Rx. It supports 1 Tx queue and 1 Rx queue.
Implicit packet forwarding between representor queues and VF does not
yet exist. It will be enabled in subsequent commits using flowman API.
Signed-off-by: Hyong Youb
Enable the minimal VF representor without Tx/Rx and flow API support.
1. Enable the standard devarg 'representor'
When the devarg is specified, create VF representor ports.
2. Initialize flowman early during PF probe
Representors require the flowman API from the firmware. Initialize it
before cre
Use Flow Manager (flowman) to support flow API for
representors. Representor's flow handlers simply invoke PF handlers
and pass the representor's flowman structure. The PF flowman handlers
are aware of representors and perform appropriate devcmds to create
flows on the NIC.
Also use flowman to cre
This series enables several flow features such as priorities and
egress PORT_ID action. It depends on the ealier patch series that adds
VF representors.
The 1st patch (remove obsolete code) does not technically belong in
the series, but is piggybacked here as it is a trivial cleanup.
Thanks..
-Hy
The 'next' field in struct enic is unused. The comment in enic_cq_rq()
is out-of-date. Remove them.
Signed-off-by: Hyong Youb Kim
Reviewed-by: John Daley
---
drivers/net/enic/enic.h | 5 -
1 file changed, 5 deletions(-)
diff --git a/drivers/net/enic/enic.h b/drivers/net/enic/enic.h
index b
Use Flow Manager (flowman) to support egress PORT_ID action. It can
steer egress packets from PFs and VFs to any uplink port as long as
they are all on the same VIC adapter. It can also steer packets
between ports on the same VIC adapter (i.e. loopback).
Signed-off-by: Hyong Youb Kim
Reviewed-by:
Group 0 corresponds to TCAM which supports priorities. Accept non-zero
priorities for group 0 flows.
Signed-off-by: Hyong Youb Kim
Reviewed-by: John Daley
---
doc/guides/rel_notes/release_20_11.rst | 1 +
drivers/net/enic/enic_fm_flow.c| 10 ++
2 files changed, 7 insertions(+),
When VXLAN source port in the template is zero, the adapter is
expected to generate a value based on the inner packet flow, when it
performs encapsulation. Flow Manager in the VIC adapter currently
lacks such ability. So, generate a random port when creating a flow if
the port is zero, to avoid tra
When a VLAN pattern is present, the flow handler always copies its
inner_type to the match buffer regardless of its value (i.e. HW
matches inner_type against packet's inner ethertype). When inner_type
spec and mask are both 0, adding it to the match buffer is usually
harmless but breaks the followi
Flow Manager (flowman) provides DECAP_STRIP operation which
decapsulates VXLAN header and then removes VLAN header from the inner
packet. Use this operation to support vxlan_decap followed by
of_pop_vlan.
Signed-off-by: Hyong Youb Kim
Reviewed-by: John Daley
---
doc/guides/rel_notes/release_20_
On 9/8/2020 10:14 AM, Andrew Rybchenko wrote:
> Network and vDPA drivers share libefx. So, libefx should be moved
> to common drivers.
>
> DPDK adaptation of the MCDI interface may be shared as well.
>
> The new common driver name is sfc_efx since it a new home of
> libefx base driver. sfc_ prefi
Hi Ferruh
From: Ferruh Yigit
> On 9/3/2020 11:13 AM, Michael Baum wrote:
> > Separate Rx indirection table object creation into both Verbs and DevX
> > modules.
> >
> > Signed-off-by: Michael Baum
> > Acked-by: Matan Azrad
>
> <...>
>
> > + if (!ind_tbl->ind_table) {
> > + rte
Bugzilla ID 491 identifies a couple of scenarios in which calls to the
rte_timer_reset_sync() and rte_timer_stop_sync() APIs could hang. Changing the
function prototypes such that error codes are returned in these scenarios was
considered, but rather than introducing another ABI change, it was pro
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 that is in the RUN
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
The purpose of this testcase is to showcase the cryptodev
enqueue callback usage with RCU support.
Signed-off-by: Abhinandan Gujjar
---
app/test/test_cryptodev.c | 123 +-
1 file changed, 122 insertions(+), 1 deletion(-)
diff --git a/app/test/test_cry
+Konstantin & Honnappa
> -Original Message-
> From: Gujjar, Abhinandan S
> Sent: Tuesday, September 8, 2020 12:40 PM
> To: dev@dpdk.org
> Cc: Doherty, Declan ; jer...@marvell.com;
> akhil.go...@nxp.com; Vangati, Narender ;
> Gujjar, Abhinandan S
> Subject: [v2 1/2] cryptodev: support enq
+Konstantin & Honnappa
> -Original Message-
> From: Gujjar, Abhinandan S
> Sent: Tuesday, September 8, 2020 12:41 PM
> To: dev@dpdk.org
> Cc: Doherty, Declan ; jer...@marvell.com;
> akhil.go...@nxp.com; Vangati, Narender ;
> Gujjar, Abhinandan S
> Subject: [v2 2/2] test: add testcase for
Separate out CAVS request file version 21.4 code to support
lower versions.
Fixes: 32440cdf2af9 ("examples/fips_validation: fix parsing of TDES vectors")
Fixes: 2b84d2bd47df ("examples/fips_validation: fix count overwrite for TDES")
Signed-off-by: Archana Muniganti
---
examples/fips_validation/
On 9/9/2020 3:37 PM, Matan Azrad wrote:
>
> Hi Ferruh
>
> From: Ferruh Yigit
>> On 9/3/2020 11:13 AM, Michael Baum wrote:
>>> Separate Rx indirection table object creation into both Verbs and DevX
>>> modules.
>>>
>>> Signed-off-by: Michael Baum
>>> Acked-by: Matan Azrad
>>
>> <...>
>>
>>> +
Removed the documentation maintainers. The documentation
is now, currently, unmaintained.
Signed-off-by: John McNamara
Signed-off-by: Marko Kovacevic
---
MAINTAINERS | 2 --
1 file changed, 2 deletions(-)
diff --git a/MAINTAINERS b/MAINTAINERS
index 3b16d7a..df5b756 100644
--- a/MAINTAINERS
++
This patch marks all traffic manager API as experimental as
per deprecation notice[1] and discussion[2] mentioned in following
threads.
[1] https://mails.dpdk.org/archives/dev/2020-May/166221.html
[2] https://mails.dpdk.org/archives/dev/2020-April/165364.html
Signed-off-by: Nithin Dabilpuram
---
On 9/1/2020 12:52 PM, jiawe...@trustnetic.com wrote:
> Hi Ferruh,
>
> Since this patch is too large, it needs to be split into so many small
> patches, which takes a lot of time.
Thanks Jiawen for the work, I am aware it is not easy to arrange the patches and
it takes time.
Mostly looks good, I
On 9/1/2020 12:50 PM, Jiawen Wu wrote:
> Adding bare minimum PMD library and doc build infrastructure and claim the
> maintainership for txgbe PMD.
>
> Signed-off-by: Jiawen Wu
<...>
>
> +Wangxun txgbe
> +M: Jiawen Wu
> +M: Jian Wang
> +F: drivers/net/txgbe/
> +F: doc/guides/nics/txgbe.rst
> -Original Message-
> From: Nithin Dabilpuram
> Sent: Wednesday, September 9, 2020 6:22 PM
> To: Yigit, Ferruh ; Richardson, Bruce
> ; Dumitrescu, Cristian
> ; tho...@monjalon.net;
> bl...@debian.org; Singh, Jasvinder ;
> arybche...@solarflare.com; Kinsella, Ray ;
> nhor...@tuxdriver.c
On 9/1/2020 12:50 PM, Jiawen Wu wrote:
> add basic PCIe ethdev probe and remove.
>
> Signed-off-by: Jiawen Wu
<...>
> +++ b/drivers/net/txgbe/base/meson.build
> @@ -0,0 +1,21 @@
> +# SPDX-License-Identifier: BSD-3-Clause
> +# Copyright(c) 2015-2020
> +
> +sources = [
> +
> +]
> +
> +error_cflag
On 9/1/2020 12:50 PM, Jiawen Wu wrote:
> Add basic init and uninit function, registers and some macro definitions
> prepare for hardware infrastructure.
>
> Signed-off-by: Jiawen Wu
<...>
> +static const struct eth_dev_ops txgbe_eth_dev_ops = {
> + .dev_start = txgbe_dev_s
On 9/1/2020 12:50 PM, Jiawen Wu wrote:
> Add device xstats get from reading hardware registers.
>
> Signed-off-by: Jiawen Wu
<...>
> +
> +static int txgbe_dev_xstats_get_names(__rte_unused struct rte_eth_dev *dev,
> + struct rte_eth_xstat_name *xstats_names, unsigned int limit)
> +{
'dev'
On 9/1/2020 12:51 PM, Jiawen Wu wrote:
> Add queue stats mapping set, complete receive and transmit unit with DMA and
> sec path.
>
> Signed-off-by: Jiawen Wu
<...>
> +static int
> +txgbe_dev_queue_stats_mapping_set(struct rte_eth_dev *eth_dev,
> + uint16_t queue_
On 9/1/2020 12:51 PM, Jiawen Wu wrote:
> Add device information get operation.
>
> Signed-off-by: Jiawen Wu
<...>
> +uint64_t
> +txgbe_get_rx_queue_offloads(struct rte_eth_dev *dev __rte_unused)
> +{
> + uint64_t offloads = 0;
> +
> + offloads |= DEV_RX_OFFLOAD_VLAN_STRIP;
>
Instead of
On Thu, 20 Aug 2020 11:02:31 +0800
Jiawen Wu wrote:
> +# CFLAGS for gcc
> +#
> +ifeq ($(shell test $(GCC_VERSION) -ge 44 && echo 1), 1)
> +CFLAGS += -Wno-deprecated
> +endif
Why is this flag on for the driver code?
On 9/1/2020 12:51 PM, Jiawen Wu wrote:
> Add remaining receive and transmit queue operaions.
>
> Signed-off-by: Jiawen Wu
> ---
> drivers/net/txgbe/txgbe_ethdev.c | 123 +++
> drivers/net/txgbe/txgbe_ethdev.h | 16 ++
> drivers/net/txgbe/txgbe_rxtx.c | 259
Thanks Cristian, This looks great. We on the Barefoot P4 compiler side are
already investigating adding support for this as a new P4C CPU target.
Cheers,
Han
On 9/9/2020 6:22 PM, Nithin Dabilpuram wrote:
> This patch marks all traffic manager API as experimental as
> per deprecation notice[1] and discussion[2] mentioned in following
> threads.
Can you please remove mentioned deprecation notice in this patch?
>
> [1] https://mails.dpdk.org/archives/de
1 - 100 of 168 matches
Mail list logo
