Hi Matan
On 2020/9/6 21:45, Matan Azrad wrote:
>
> Hi Chengchang
>
> From: Chengchang Tang:
>> Hi, Matan
>>
>> On 2020/9/2 18:30, Matan Azrad wrote:
>>> Hi Chengchang
>>>
>>> From: Chengchang Tang
Hi, Matan
On 2020/9/2 15:19, Matan Azrad wrote:
>
> Hi Chengchang
>
>>>
On 9/1/20 12:47 PM, Michael Pfeiffer wrote:
> Currently, rte_ipv4_cksum() and rte_ipv4_udptcp_cksum() assume all IPv4
> headers have sizeof(struct rte_ipv4_hdr) bytes. This is not true for
> those (rare) packets with IPv4 options. Thus, both IPv4 and TCP/UDP
> checksums are calculated wrong.
>
> T
Hi Stephen
From: Stephen Hemminger:
> On Sun, 6 Sep 2020 12:38:18 +
> Matan Azrad wrote:
>
> > Hi Stephen
> >
> > From: Stephen Hemminger:
> > > The vdev_netvsc was not detecting when the associated PCI device
> > > (SRIOV) was removed. Because of that it would keep feeding the same
> > > (r
> -Original Message-
> From: Kusztal, ArkadiuszX
> Sent: Monday, September 7, 2020 7:24 AM
> To: dev@dpdk.org
> Cc: akhil.go...@nxp.com; Trahe, Fiona ; Kusztal,
> ArkadiuszX
>
> Subject: [PATCH] crypto/qat: remove asym list end references
>
> This patch removes LIST_END enumerators r
On 9/3/20 4:14 PM, Ferruh Yigit wrote:
> On 9/3/2020 11:11 AM, Kiran Kumar Kokkilagadda wrote:
>> *From:* Ajit Khaparde
>> *Sent:* Tuesday, September 1, 2020 10:42 PM
>> *To:* Kiran Kumar Kokkilagadda
>> *Cc:* Ferruh Yigit ; Thomas Monjalon
>> ; Andrew Rybchenko ;
>> dev@dpdk.org; Jerin Jacob Kol
The rte_lpm structure is exported because lookup API is inlined.
But most of the structure can be hidden.
Discussion at: http://patches.dpdk.org/patch/72403/
This patch set aimed to hide the rte_lpm structure as much as possible.
A data free issue was identified and fixed.
Ruifeng Wang (2):
lpm
Fields except tbl24 and tbl8 in rte_lpm structure have no
need to be exposed to the user.
Hide the unneeded exposure of structure fields for better
ABI maintainability.
Suggested-by: David Marchand
Signed-off-by: Ruifeng Wang
Reviewed-by: Phil Yang
---
lib/librte_lpm/rte_lpm.c | 152 ++
The container structure should be freed instead of rte_lpm structure
after wrapping rte_lpm into internal structure __rte_lpm.
Fixes: 8a9f8564e9f9 ("lpm: implement RCU rule reclamation")
Cc: sta...@dpdk.org
Signed-off-by: Ruifeng Wang
Reviewed-by: Phil Yang
---
lib/librte_lpm/rte_lpm.c | 2 +-
On Sun, Sep 06, 2020 at 12:24:49PM +0200, Thomas Monjalon wrote:
> On Thu Sep 3, 2020 at 6:26 PM CEST, Ciara Power wrote:
> > Make is no longer supported for compiling DPDK, references are now
> > removed in code comments.
>
> It should be squashed with the patch removing the config options.
>
>
Hi Chengchang
From: Chengchang Tang:
> Hi Matan
>
> On 2020/9/6 21:45, Matan Azrad wrote:
> >
> > Hi Chengchang
> >
> > From: Chengchang Tang:
> >> Hi, Matan
> >>
> >> On 2020/9/2 18:30, Matan Azrad wrote:
> >>> Hi Chengchang
> >>>
> >>> From: Chengchang Tang
> Hi, Matan
>
> On
> +
> +static int
> +intel_ntb_dev_init(const struct rte_rawdev *dev) {
> + struct ntb_hw *hw = dev->dev_private;
> + uint8_t bar;
> + int ret, i;
> +
> + if (hw == NULL) {
> + NTB_LOG(ERR, "Invalid device.");
> + return -EINVAL;
> + }
> +
> hw->hw_
On Sun, Sep 06, 2020 at 10:20:30PM +, Ananyev, Konstantin wrote:
> > This patch adds documentation on the usage of the max SIMD bitwidth EAL
> > setting, and how to use it to enable AVX-512 at runtime.
> >
> > Cc: Anatoly Burakov
> > Cc: John McNamara
> > Cc: Marko Kovacevic
> >
> > Signed
On 9/6/2020 4:42 AM, Stephen Hemminger wrote:
> This is an improved version of the setup of huge pages
> bases on earlier DPDK setup. Differences are:
>* it autodetects NUMA vs non NUMA
>* it allows setting different page sizes
> recent kernels support multiple sizes.
>* it accepts
On Mon, Sep 07, 2020 at 09:54:29AM +0100, Ferruh Yigit wrote:
> On 9/6/2020 4:42 AM, Stephen Hemminger wrote:
> > This is an improved version of the setup of huge pages
> > bases on earlier DPDK setup. Differences are:
> >* it autodetects NUMA vs non NUMA
> >* it allows setting different pa
On Sat, Sep 05, 2020 at 06:31:31PM -0700, Stephen Hemminger wrote:
> This fixes the following python lint warnings.
> usertools/dpdk-pmdinfo.py:188:11: C1801: Do not use `len(SEQUENCE)` to
> determine if a sequence is empty (len-as-condition)
> usertools/dpdk-pmdinfo.py:196:21: C1801: Do not use `
On Sat, Sep 05, 2020 at 06:31:32PM -0700, Stephen Hemminger wrote:
> Convert comments to docstrings as appropriate.
> Remove unnecessary paren in if statement.
> Remove extra whitespace after print.
>
> Signed-off-by: Stephen Hemminger
> ---
> usertools/dpdk-telemetry-client.py | 28
On Sat, Sep 05, 2020 at 08:38:46PM -0700, Stephen Hemminger wrote:
> We should be encouraging the use of vfio_pci for developers, not telling
> them to use igb_uio.
>
> Also fix typo where .py suffix is visible in document.
>
> Signed-off-by: Stephen Hemminger
> ---
> doc/guides/tools/devbind.r
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 Tx burst process.
Signed-off-by: Huisong Li
Signed-off-by: Wei Hu (Xavier)
Signed-off-by: Chengwen Feng
---
config/common_base| 1 +
config/common_linux | 1 +
drivers/net/hns
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 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: 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
On 2020/9/6 0:33, Thomas Monjalon wrote:
> 05/09/2020 11:07, Chengchang Tang:
>> The change has been applied, so remove the notice.
>
> It should be atomic with the patch doing the change,
> i.e. you can squash.
>
> I think the oneline patches in testpmd and procinfo
> can probably be squashed
On 2020/9/6 0:59, Stephen Hemminger wrote:
> On Sat, 5 Sep 2020 17:07:32 +0800
> Chengchang Tang wrote:
>
>> printf("\t -- queue %d rx scatter %d"
>> " descriptors %d"
>> +" r
Hi
> -Original Message-
> From: Wu, Jingjing
> Sent: Monday, September 7, 2020 16:35
> To: Li, Xiaoyun
> Cc: dev@dpdk.org; Maslekar, Omkar
> Subject: RE: [PATCH v3] raw/ntb: add Icelake support for Intel NTB
>
> > +
> > +static int
> > +intel_ntb_dev_init(const struct rte_rawdev *dev)
This patchset supports flex Rx descriptor RxDID #22 and
FDID offload in vPMD.Remove devargs "flow-mark-support".
v2:
-Reorder patches.
Guinan Sun (4):
net/ice: add flow director enabled switch value
net/ice: support flow mark in AVX path
net/ice: support flow mark in SSE path
net/ice: re
From: Guinan Sun
The commit adds fdir_enabled flag into ice_adapter structure
to identify if fdir id is active. Rx data path can be benefit if
fdir id parsing is not needed, especially in vector path.
Signed-off-by: Guinan Sun
---
drivers/net/ice/ice_ethdev.h | 2 ++
drivers/net/ice/ice_
This patch supports RxDID #22 by the following changes:
-add structure and macro definition for RxDID #22,
-support RxDID #22 format in normal path,
-change RSS hash parsing from RxDID #22 in AVX/SSE data path.
Signed-off-by: Junyu Jiang
---
drivers/net/ice/ice_rxtx.c | 16 ++---
driver
performance improvement: memset should be done only
for required memory.
Signed-off-by: Gagandeep Singh
---
drivers/raw/dpaa2_qdma/dpaa2_qdma.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/raw/dpaa2_qdma/dpaa2_qdma.c
b/drivers/raw/dpaa2_qdma/dpaa2_qdma.c
index a2e
dpaa2_qdma was partially using direct pmd APIs.
This patch changes that and adapt the driver to use
more of the rawdev APIs
Signed-off-by: Gagandeep Singh
---
drivers/raw/dpaa2_qdma/dpaa2_qdma.c | 331 ++--
drivers/raw/dpaa2_qdma/dpaa2_qdma.h | 3 +-
dri
From: Guinan Sun
Support Flow Director mark ID parsing from Flex
Rx descriptor in AVX path.
Signed-off-by: Guinan Sun
---
drivers/net/ice/ice_rxtx_vec_avx2.c | 64 -
1 file changed, 63 insertions(+), 1 deletion(-)
diff --git a/drivers/net/ice/ice_rxtx_vec_avx2.c
b
In this patchset, we have done some changes in dpaa2_qdma driver
related to rawdev APIs, optimizations, scatter-gather support on TX,
enqueue without wait.
Gagandeep Singh (2):
raw/dpaa2_qdma: change DPAA2 QDMA APIs to rawdev ops
raw/dpaa2_qdma: memset to only required memory
Jun Yang (5):
From: Jun Yang
This patch moves qdma queue specific configurations from driver
global configuration to per-queue setup. This is required
as each queue can be configured differently.
Signed-off-by: Jun Yang
---
drivers/raw/dpaa2_qdma/dpaa2_qdma.c | 1259 +--
driv
From: Guinan Sun
Remove devargs "flow-mark-support".
Signed-off-by: Guinan Sun
---
doc/guides/nics/ice.rst | 12
drivers/net/ice/ice_ethdev.c | 10 +-
drivers/net/ice/ice_ethdev.h | 1 -
drivers/net/ice/ice_rxtx_vec_common.h | 6 --
4
From: Guinan Sun
Support Flow Director mark ID parsing from Flex
Rx descriptor in SSE path.
Signed-off-by: Guinan Sun
---
drivers/net/ice/ice_rxtx_vec_sse.c | 49 ++
1 file changed, 49 insertions(+)
diff --git a/drivers/net/ice/ice_rxtx_vec_sse.c
b/drivers/net/ice
From: Jun Yang
Don't mix SG/none-SG with same FLE pool format,
otherwise, it impacts none-SG performance.
In order to support SG queue and none-SG queue
with different FLE pool element formats, associate
FLE pool with queue instead of device.
Signed-off-by: Jun Yang
---
drivers/raw/dpaa2_qdma
From: Jun Yang
rte_mempool_virt2iova is now used for converting with IOVA off.
Signed-off-by: Jun Yang
---
drivers/raw/dpaa2_qdma/dpaa2_qdma.c | 29 +++--
drivers/raw/dpaa2_qdma/dpaa2_qdma.h | 5 +
2 files changed, 28 insertions(+), 6 deletions(-)
diff --git a/dri
From: Jun Yang
In this condition, user needs to check if dma transfer is completed
by its own logic.
qDMA FLE pool is not used in this condition since there is no chance to put
FLE back to pool without dequeue response.
User application is responsible to transfer FLE memory to qDMA driver
by qd
From: Jun Yang
This patch add support to add Scatter Gather support
for different jobs for qdma queues.
It also supports gathering multiple enqueue jobs into SG enqueue job(s).
Signed-off-by: Jun Yang
---
drivers/bus/fslmc/portal/dpaa2_hw_pvt.h | 18 +-
drivers/raw/dpaa2_qdma/dpaa2_qdma.
07/09/2020 10:18, Bruce Richardson:
> On Sun, Sep 06, 2020 at 12:24:49PM +0200, Thomas Monjalon wrote:
> > On Thu Sep 3, 2020 at 6:26 PM CEST, Ciara Power wrote:
> > > Make is no longer supported for compiling DPDK, references are now
> > > removed in code comments.
> >
> > It should be squashed w
This patch adds support for dpaa qdma based driver.
Signed-off-by: Gagandeep Singh
Signed-off-by: Peng Ma
---
doc/guides/rawdevs/dpaa_qdma.rst | 98 ++
doc/guides/rawdevs/index.rst |1 +
drivers/bus/dpaa/dpaa_bus.c| 22 +
d
On 21/08/2020 16:28, Kinsella, Ray wrote:
>
>
> On 20/08/2020 15:32, Kevin Traynor wrote:
>> Hi,
>>
>> On 25/06/2020 10:59, alangordonde...@gmail.com wrote:
>>> From: Alan Dewar
>>>
>>> The QoS scheduler works off port time that is computed from the number
>>> of CPU cycles that have elapsed sin
Hi all,
Here is a list of patches targeted for LTS release 18.11.10.
The planned date for the final release is 21 September.
Please help with testing and validation of your use cases and report
any issues/results with reply-all to this mail. For the final release
the fixes and reported validatio
On Thu Sep 3, 2020 at 6:27 PM CEST, Ciara Power wrote:
> --- a/doc/guides/contributing/coding_style.rst
> +++ b/doc/guides/contributing/coding_style.rst
> -DPDK supports being built in two different ways:
> -
> -* using ``make`` - or more specifically "GNU make", i.e. ``gmake`` on
> FreeBSD
> -* us
On 9/5/2020 3:49 AM, Guinan Sun wrote:
> Add VLAN bit used during flow director programming, as a part of
> input set for HW.
>
> Signed-off-by: Przemyslaw Patynowski
> Signed-off-by: Guinan Sun
> ---
> drivers/net/i40e/base/i40e_type.h | 2 ++
> 1 file changed, 2 insertions(+)
>
> diff --git
On 9/5/2020 3:49 AM, Guinan Sun wrote:
> Update FW increment API version.
>
> Signed-off-by: Jacek Naczyk
> Signed-off-by: Guinan Sun
> ---
> drivers/net/i40e/base/i40e_adminq_cmd.h | 4 ++--
> 1 file changed, 2 insertions(+), 2 deletions(-)
>
> diff --git a/drivers/net/i40e/base/i40e_adminq_c
On 9/5/2020 3:49 AM, Guinan Sun wrote:
> Enable several registers and defines for software controlled
> DCB, particularly around the receive pipe monitor configuration
> which is necessary to help ports achieve the right throughput
> under load in several different configurations.
>
> Signed-off-b
On Tue, Aug 25, 2020 at 05:59:10PM +0100, Ferruh Yigit wrote:
> On 5/1/2020 2:16 PM, Nithin Dabilpuram wrote:
> > On Fri, May 01, 2020 at 11:27:02AM +0100, Ferruh Yigit wrote:
> >> External Email
> >>
> >> --
> >> On 4/29/2020 10:0
main changes:
1. Added support for outer IP filter for GTPC.
2. Added support for outer IP filter for GPTU control packet (no inner IP)
3. Added support for QinQ switch filter
4. code refactor and bug fixes
Qi Zhang (40):
net/ice/base: handle error gracefully in HW table calloc
net/ice/base: s
There are a number of structures that consist of a one-element array as the
only struct member. Some of those are unused (ice_aqc_add_get_recipe_data,
ice_aqc_get_port_options_data, ice_aqc_dis_txq, etc.) so remove them.
Others are used to index into a buffer/array consisting of a variable
number
In the ice_init_hw_tbls API, if the ice_calloc for es->written
fails, catch that error and bail out gracefully, instead of
continuing with a NULL pointer.
Signed-off-by: Surabhi Boob
Signed-off-by: Qi Zhang
---
drivers/net/ice/base/ice_flex_pipe.c | 10 +-
1 file changed, 9 insertions(+
Using the new ice_aq_list_caps and ice_parse_(dev|func)_caps functions,
replace ice_discover_caps with two functions that each take a pointer to
the dev_caps and func_caps structures respectively.
This makes the side effect of updating the hw->dev_caps and
hw->func_caps obvious from reading the im
In ice_flow_add_prof_sync(), struct ice_flow_prof_params has recently
grown in size hogging stack space when allocated there. Hogging stack
space should be avoided. Change allocation to be on the heap when needed.
Signed-off-by: Bruce Allan
Signed-off-by: Qi Zhang
---
drivers/net/ice/base/ice
The maximum Admin Queue buffer size and NVM shadow RAM sector size are both
4 Kilobytes. Some comments refer to those as 4Kb which can be confused with
4 Kilobits. Update the comments to use the commonly used KB symbol instead.
Signed-off-by: Bruce Allan
Signed-off-by: Qi Zhang
---
drivers/net/
Sparse warns about these casts to/from restricted types which are not
actual problems; silence the warnings.
Signed-off-by: Bruce Allan
Signed-off-by: Qi Zhang
---
drivers/net/ice/base/ice_nvm.c| 2 +-
drivers/net/ice/base/ice_switch.c | 2 +-
2 files changed, 2 insertions(+), 2 deletions(-
To make the wrapping a little cleaner, move the variables only applicable
to ICE_FC_AUTO into that case. Also move caching of the value to only occur
on succcess.
Signed-off-by: Tony Nguyen
Signed-off-by: Qi Zhang
---
drivers/net/ice/base/ice_common.c | 37 +
1. Fixed the max children check when moving the last(8th) children. This
allows the parent node to hold 8 children instead of 7.
2. Check whether the VSI is already part of the given aggregator subtree
before moving it.
Fixes: 29a0c11489ef ("net/ice/base: clean code")
Cc: sta...@dpdk.org
Signed-o
Correct abbreviations as identified by abbrevcheck
Signed-off-by: Tony Nguyen
Signed-off-by: Qi Zhang
---
drivers/net/ice/base/ice_flex_pipe.c | 6 +++---
drivers/net/ice/base/ice_sched.c | 16
2 files changed, 11 insertions(+), 11 deletions(-)
diff --git a/drivers/net/ic
Convert the pre-C90-extension "C struct hack" method (using a single-
element array at the end of a structure for implementing variable-length
types) to the preferred use of C99 flexible array member.
Signed-off-by: Bruce Allan
Signed-off-by: Qi Zhang
---
drivers/net/ice/base/ice_adminq_cmd.h |
Introduce ice_bitmap_hweight() and use it instead of open-coding that
functionality.
Signed-off-by: Bruce Allan
Signed-off-by: Qi Zhang
---
drivers/net/ice/base/ice_bitops.h | 23 +++
drivers/net/ice/base/ice_switch.c | 11 +--
2 files changed, 24 insertions(+), 10 d
As of NVM ver 1.7.1 there is a new AQ command to add and remove
LLDP filters for Rx flow. This patch implements the support
structure to implement this functionality.
Signed-off-by: Dave Ertman
Signed-off-by: Qi Zhang
---
drivers/net/ice/base/ice_common.c | 47 +
Introduce ice_bitmap_set() and use it instead of open-coding that
functionality.
Signed-off-by: Bruce Allan
Signed-off-by: Qi Zhang
---
drivers/net/ice/base/ice_acl_ctrl.c | 4 +---
drivers/net/ice/base/ice_bitops.h| 19 +++
drivers/net/ice/base/ice_flex_pipe.c | 9 ++
Add a function header for ice_cfg_phy_fc()
Signed-off-by: Tony Nguyen
Signed-off-by: Qi Zhang
---
drivers/net/ice/base/ice_common.c | 6 ++
1 file changed, 6 insertions(+)
diff --git a/drivers/net/ice/base/ice_common.c
b/drivers/net/ice/base/ice_common.c
index d9ad3217a..fdde85774 100644
A number of code flows iterate over a block of memory to do something for
every bit set in that memory. Use existing bit operations in a new iterator
macro to make those code flows cleaner.
Signed-off-by: Bruce Allan
Signed-off-by: Qi Zhang
---
drivers/net/ice/base/ice_acl_ctrl.c | 17 +++-
The PSM Configuration has a Rate Limiter for each associated
switch port based on its relative speed from the total BW of
switch ports connected to LAN controller. The rate limiters
will be dynamic get readjusted if switch port speeds are
changed at the root node layer of the scheduler tree. Adding
Only need to get profile_to_recip info from firmware for
profiles used by switch, no need for other free profile
in order that we can reduce the time consumed when
download a switch rule.
Signed-off-by: Wei Zhao
Signed-off-by: Qi Zhang
---
drivers/net/ice/base/ice_flex_pipe.c | 115
In this patch, the DCB related variables will be refactored out of the
ice_port_info_struct. The goal is to make the ice_port_info struct
cleaner.
Signed-off-by: Chinh T Cao
Signed-off-by: Qi Zhang
---
drivers/net/ice/base/ice_dcb.c | 40
drivers/net/ic
When printing messages with ice_debug, align the printed string to the
origin line of the message in order to ease debugging and tracking
messages back to their source.
Signed-off-by: Jacob Keller
Signed-off-by: Qi Zhang
---
drivers/net/ice/base/ice_acl_ctrl.c | 30 --
drivers/net/ice
This patch add support for GTP-U type of switch rule.
It enable all GTP-U related ptype.
Signed-off-by: Wei Zhao
Signed-off-by: Qi Zhang
---
drivers/net/ice/base/ice_protocol_type.h | 7 +
drivers/net/ice/base/ice_switch.c| 299 ++-
drivers/net/ice/base/ice
Add ptype MAC_IPV4_GTPC_TEID and MAC_IPV4_GTPC into
ice_ptypes_ipv4_ofos, ice_ptypes_ipv4_ofos_all and ice_ipv4_ofos_no_l4
Add ptype MAC_IPV6_GTPC_TEID and MAC_IPV6_GTPC into
ice_ptypes_ipv6_ofos, ice_ptypes_ipv6_ofos_all and ice_ipv6_ofos_no_l4
So outer IP can be configured as input set for GTPC
The only caller of this function is within the file so mark it as static
and move it up in the file to avoid a forward declaration.
Signed-off-by: Tony Nguyen
Signed-off-by: Qi Zhang
---
drivers/net/ice/base/ice_acl.h | 1 -
drivers/net/ice/base/ice_acl_ctrl.c | 93 ++-
Move ice_flow_get_hw_prof, this is not necessary for DPDK, just
sync the code with other compile option which ice_flow_get_hw_prof
is declared as a static function.
Signed-off-by: Tony Nguyen
Signed-off-by: Qi Zhang
---
drivers/net/ice/base/ice_flow.c | 48 --
Clear advanced rules from SW and HW before reset.
Signed-off-by: NorbertX Ciosek
Signed-off-by: Qi Zhang
---
drivers/net/ice/base/ice_switch.c | 30 +++---
1 file changed, 19 insertions(+), 11 deletions(-)
diff --git a/drivers/net/ice/base/ice_switch.c
b/drivers/net/ic
There is no check for failed allocation of 'acts'. Add a check and return
if memory was not successfully allocated. Also, as all 'goto out' occur
after this check there is no need to perform a check for 'acts' as we will
have returned if it is not set.
Signed-off-by: Tony Nguyen
Signed-off-by: Qi
Add ptype MAC_IPV4_GTPU into
ice_ptypes_ipv4_ofos, ice_ptypes_ipv4_ofos_all and ice_ipv4_ofos_no_l4
Add ptype MAC_IPV6_GTPU into
ice_ptypes_ipv6_ofos, ice_ptypes_ipv6_ofos_all and ice_ipv6_ofos_no_l4
Add ptype MAC_IPV4_GTPU and MAC_IPV6_GTPU into
the new ice_ptypes_gtpu_no_ip
So outer IP can be
A new test in checkpatch detects repeated words; cleanup all pre-existing
occurrences of those now.
Signed-off-by: Bruce Allan
Signed-off-by: Qi Zhang
---
drivers/net/ice/base/ice_adminq_cmd.h | 2 +-
drivers/net/ice/base/ice_common.c | 2 +-
drivers/net/ice/base/ice_flow.c | 4 ++--
Moving the runtime profile ids database/storage to the hw structure.
Signed-off-by: Shibin Koikkara Reeny
Signed-off-by: Qi Zhang
---
drivers/net/ice/base/ice_sched.c | 52 +++-
drivers/net/ice/base/ice_type.h | 4 ++--
2 files changed, 27 insertions(+), 29
If the driver initializes in safe mode, it will call
ice_set_safe_mode_caps. This results in clearing the capabilities
structures, in order to set them up for operating in safe mode, ensuring
many features are disabled.
This has a side effect of also clearing the capability bits that relate
to NVM
This is a collection of minor ACL style changes including:
- When there is nothing to unroll, return a value directly.
- Return ICE_SUCCESS(0) in cases where an error was previously checked
so ICE_SUCCESS is the only possible return.
- Remove unnecessary parentheses and newlines
- Move unroll of
Enable QinQ type filter for switch advanced rule, it support tunnel
and non-tunnel packet use external and inner vlan id as input set
for rules, it also support session id as input set for PPPoE rule
with QinQ flag in packet.
Signed-off-by: Wei Zhao
Signed-off-by: Qi Zhang
---
drivers/net/ice/b
Remove debug function ice_aq_query_acl_cntrs.
Signed-off-by: Qi Zhang
---
drivers/net/ice/base/ice_acl.c | 36
drivers/net/ice/base/ice_acl.h | 3 ---
2 files changed, 39 deletions(-)
diff --git a/drivers/net/ice/base/ice_acl.c b/drivers/net/ice/base/ice_ac
The ice_nvm_info structure has become somewhat of a dumping ground for
all of the fields related to flash version. It holds the NVM version and
EETRACK id, the OptionROM info structure, the flash size, the ShadowRAM
size, and more.
A future change is going to add the ability to read the NVM versio
The ice flash contains two copies of each of the NVM, Option ROM, and
Netlist modules. Each bank has a pointer word and a size word. In order
to correctly read from the active flash bank, the driver must calculate
the offset manually.
During NVM initialization, read the Shadow RAM control word and
remove unused parameter of ice_parse_fdir_func_caps
Signed-off-by: Qi Zhang
---
drivers/net/ice/base/ice_common.c | 6 ++
1 file changed, 2 insertions(+), 4 deletions(-)
diff --git a/drivers/net/ice/base/ice_common.c
b/drivers/net/ice/base/ice_common.c
index 1b98802d9..879a7d16a 100644
---
Remove unnecessary mac_type check, fix couple comment, and remove
unnecessary empty line.
Signed-off-by: Qi Zhang
---
drivers/net/ice/base/ice_common.c | 7 +--
drivers/net/ice/base/ice_flow.c | 9 -
2 files changed, 5 insertions(+), 11 deletions(-)
diff --git a/drivers/net/ice/ba
'xtrct' or 'xtract' is currently used in the code to shorten 'extract'.
Rename ice_prgm_acl_prof_extrt() to ice_prgm_acl_prof_xtrct() so we don't
have another variation of a 'extract'.
Signed-off-by: Tony Nguyen
Signed-off-by: Qi Zhang
---
drivers/net/ice/base/ice_acl.c | 4 ++--
drivers/net/i
The naming convention used to shorten 'priority' is 'prio'.
Convert the ACL related entries that use 'prior' to 'prio'.
Also, as ICE_LOW, ICE_NORMAL,... are not very descriptive of what
they represent. Add 'ACL_PRIO' to help convey their use.
Signed-off-by: Tony Nguyen
Signed-off-by: Qi Zhang
-
Added the change to keep the default aggregator VSI information.
Signed-off-by: Tarun Singh
Signed-off-by: Qi Zhang
---
drivers/net/ice/base/ice_sched.c | 11 +--
1 file changed, 1 insertion(+), 10 deletions(-)
diff --git a/drivers/net/ice/base/ice_sched.c b/drivers/net/ice/base/ice_sc
These two conditional statements are unnecessary because the condition
is always true based on existing code flow. Remove them to resolve
potential errors from some static analysis tools.
Signed-off-by: Bruce Allan
Signed-off-by: Qi Zhang
---
drivers/net/ice/base/ice_flow.c | 4 ++--
1 file ch
Hi,Ferruh Yigit
On 2020/9/4 18:34, Ferruh Yigit wrote:
On 8/25/2020 12:53 PM, Wei Hu (Xavier) wrote:
From: "Wei Hu (Xavier)"
This patch changes the log level from NOTICE to INFO.
Signed-off-by: Wei Hu (Xavier)
---
drivers/net/hns3/hns3_ethdev.c | 4 ++--
1 file changed, 2 insertions(+),
> On Sun, Sep 06, 2020 at 10:20:30PM +, Ananyev, Konstantin wrote:
> > > This patch adds documentation on the usage of the max SIMD bitwidth EAL
> > > setting, and how to use it to enable AVX-512 at runtime.
> > >
> > > Cc: Anatoly Burakov
> > > Cc: John McNamara
> > > Cc: Marko Kovacevic
Hi Matan
On 2020/9/7 16:28, Matan Azrad wrote:
>
> Hi Chengchang
>
> From: Chengchang Tang:
>> Hi Matan
>>
>> On 2020/9/6 21:45, Matan Azrad wrote:
>>>
>>> Hi Chengchang
>>>
>>> From: Chengchang Tang:
Hi, Matan
On 2020/9/2 18:30, Matan Azrad wrote:
> Hi Chengchang
>
>
On 9/7/2020 12:34 PM, Wei Hu (Xavier) wrote:
> Hi,Ferruh Yigit
>
> On 2020/9/4 18:34, Ferruh Yigit wrote:
>> On 8/25/2020 12:53 PM, Wei Hu (Xavier) wrote:
>>> From: "Wei Hu (Xavier)"
>>>
>>> This patch changes the log level from NOTICE to INFO.
>>>
>>> Signed-off-by: Wei Hu (Xavier)
>>> ---
>>>
Hi, Ferruh Yigit
On 2020/9/7 20:10, Ferruh Yigit wrote:
On 9/7/2020 12:34 PM, Wei Hu (Xavier) wrote:
Hi,Ferruh Yigit
On 2020/9/4 18:34, Ferruh Yigit wrote:
On 8/25/2020 12:53 PM, Wei Hu (Xavier) wrote:
From: "Wei Hu (Xavier)"
This patch changes the log level from NOTICE to INFO.
Signed-of
> -Original Message-
> From: Zhang, Roy Fan
> Sent: Friday, 4 September, 2020 17:26
> To: dev@dpdk.org
> Cc: akhil.go...@nxp.com; Trahe, Fiona ; Kusztal,
> ArkadiuszX ; Dybkowski, AdamX
> ; Zhang, Roy Fan ;
> Bronowski, PiotrX
> Subject: [dpdk-dev v8 1/4] cryptodev: add crypto data-path s
Hi Chengchang
From: Chengchang Tang:
> Hi Matan
>
> On 2020/9/7 16:28, Matan Azrad wrote:
> >
> > Hi Chengchang
> >
> > From: Chengchang Tang:
> >> Hi Matan
> >>
> >> On 2020/9/6 21:45, Matan Azrad wrote:
> >>>
> >>> Hi Chengchang
> >>>
> >>> From: Chengchang Tang:
> Hi, Matan
>
> >>>
1 - 100 of 228 matches
Mail list logo
