The hashed list size must be the power of 2, otherwise the
adjustment is applied and the warning message is emitted.
This patch provides the correct list size to eliminate the
warning.
Fixes: 4ec6360de37d ("net/mlx5: implement tunnel offload")
Cc: sta...@dpdk.org
Signed-off-by: Viacheslav Ovsiien
Depending on kernel capabilities and rdma-core version the mapping
of UAR (User Access Region) of desired memory caching type (non-cached
or write combining) might fail. The PMD implements the flexible
strategy of UAR mapping, alternating the type of caching to succeed.
During this process the fail
From: Asaf Penso
To compile with meson some dependencies should be installed.
Section "Getting the Tools" describes what needed, but per
OS there are additional steps to do.
Add links to Linux, FreeBSD, and Windows guide for more info.
Signed-off-by: Asaf Penso
---
doc/guides/prog_guide/build
On Mon, Feb 22, 2021 at 4:59 PM Christian Ehrhardt
wrote:
>
> Hi all,
>
> Here is a list of patches targeted for stable release 19.11.7.
>
> The planned date for the final release is 8th March.
>
> Please help with testing and validation of your use cases and report
> any issues/results with reply
在 2021/2/24 15:41, Thomas Monjalon 写道:
24/02/2021 02:34, oulijun:
在 2021/2/10 17:41, Thomas Monjalon 写道:
03/02/2021 13:46, Lijun Ou:
From: Chengchang Tang
Because of the '9ca2f16' have merged, the current hns3
pmd driver can not be directly complied on the kunpeng920
server board. Theref
Hi,
> -Original Message-
> From: Viacheslav Ovsiienko
> Sent: Wednesday, February 24, 2021 10:15 AM
> To: dev@dpdk.org
> Cc: Raslan Darawsheh ; Matan Azrad
> ; sta...@dpdk.org
> Subject: [PATCH v2] net/mlx5: fix hashed list size for tunnel flow groups
>
> The hashed list size must be the
On 2/23/2021 8:25 PM, Thomas Monjalon wrote:
23/02/2021 19:39, Ajit Khaparde:
On Tue, Feb 23, 2021 at 10:36 AM Ferruh Yigit wrote:
On 1/31/2021 11:53 AM, Wisam Monther wrote:
Hi,
-Original Message-
From: dev On Behalf Of Lance Richardson
Sent: Saturday, January 30, 2021 12:36 AM
T
24/02/2021 10:17, oulijun:
>
> 在 2021/2/24 15:41, Thomas Monjalon 写道:
> > 24/02/2021 02:34, oulijun:
> >>
> >> 在 2021/2/10 17:41, Thomas Monjalon 写道:
> >>> 03/02/2021 13:46, Lijun Ou:
> From: Chengchang Tang
>
> Because of the '9ca2f16' have merged, the current hns3
> pmd driv
On Tue, Feb 23, 2021 at 03:01:12PM -0800, Jie Zhou wrote:
> From: Jie Zhou
>
> This patch allows the same set of rte_metrics_tel_* functions to be
> exported no matter JANSSON is available or not, by doing following:
> 1.Leverage dpdk_conf to set configuration flag RTE_HAVE_JANSSON
> when Jan
Hi Nipun,
Unfortunately I don't have an ARM platform available to test this.
I believe installing the Kaleido and Plotly modules using pip3 should work:
pip3 install plotly
pip3 install kaleido
The Kaleido package is a replacement for Orca, and for Plotly v4.9+ , the
default is t
Message: 4
Date: Wed, 24 Feb 2021 11:24:27 +0100
From: Thomas Monjalon
To: oulijun
Cc: ferruh.yi...@intel.com, dev@dpdk.org, linux...@openeuler.org,
juraj.lin...@pantheon.tech, bruce.richard...@intel.com
Subject: Re: [dpdk-dev] [PATCH 1/2] config/arm: fix Hisilicon
kunpeng920 SoC
Hi Ciara,
Thanks for the info.
We will try with Kaleido and plotly v4.9+.
Regards,
Nipun
> -Original Message-
> From: Power, Ciara
> Sent: Wednesday, February 24, 2021 4:29 PM
> To: Nipun Gupta ; dev@dpdk.org
> Cc: Vanshika Shukla ; Hemant Agrawal
> ; Doherty, Declan ;
> Dybkowski, Adam
Hi,
> -Original Message-
> From: Viacheslav Ovsiienko
> Sent: Monday, February 22, 2021 5:45 PM
> To: dev@dpdk.org
> Cc: Raslan Darawsheh ; Matan Azrad
> ; sta...@dpdk.org
> Subject: [PATCH] net/mlx5: fix UAR allocation diagnostics messages
>
> Depending on kernel capabilities and rdma-c
Hi,
> -Original Message-
> From: Viacheslav Ovsiienko
> Sent: Wednesday, February 24, 2021 10:18 AM
> To: dev@dpdk.org
> Cc: Raslan Darawsheh ; Matan Azrad
> ; sta...@dpdk.org
> Subject: [PATCH v2] net/mlx5: fix UAR allocation diagnostics messages
>
> Depending on kernel capabilities and
On 2/5/2021 3:34 AM, Jiawen Wu wrote:
Introduce virtual function driver in txgbe PMD,
add simple init and uninit function to probe and remove the device.
Signed-off-by: Jiawen Wu
<...>
+static int
+txgbevf_dev_close(struct rte_eth_dev *dev)
+{
+ PMD_INIT_FUNC_TRACE();
+ if (rte_
On 2/5/2021 3:34 AM, Jiawen Wu wrote:
Generate a random MAC address if none was assigned by PF during
the initialization of VF device. And support to add and remove
MAC address.
Signed-off-by: Jiawen Wu
<...>
static const struct eth_dev_ops txgbevf_eth_dev_ops = {
+ .mac_addr_add
On 2/5/2021 3:34 AM, Jiawen Wu wrote:
Add support to get link speed, duplex mode and state of VF device.
Signed-off-by: Jiawen Wu
<...>
+/**
+ * txgbe_check_mac_link_vf - Get link/speed status
+ * @hw: pointer to hardware structure
+ * @speed: pointer to link speed
+ * @link_up: true is
On 2/5/2021 3:34 AM, Jiawen Wu wrote:
Update release note to add txgbevf PMD support.
Signed-off-by: Jiawen Wu
---
doc/guides/rel_notes/release_21_02.rst | 1 +
1 file changed, 1 insertion(+)
diff --git a/doc/guides/rel_notes/release_21_02.rst
b/doc/guides/rel_notes/release_21_02.rst
index
> -Original Message-
> From: Thierry Herbelot
> Sent: Wednesday, February 24, 2021 12:02 PM
> To: dev@dpdk.org; oulijun ; Thomas Monjalon
>
> Cc: Juraj Linkeš ; Bruce Richardson
> ; linux...@openeuler.org;
> ferruh.yi...@intel.com
> Subject: Re: [PATCH 1/2] config/arm: fix Hisilicon kun
Single-core performance of AF_XDP at high loads can be poor because
a heavily loaded NAPI context will never enter or allow for busy-polling.
1C testpmd rxonly (both IRQs and PMD on core 0):
./dpdk-testpmd -l 0-1 --vdev=net_af_xdp0,iface=eth0 --main-lcore=1 -- \
--forward-mode=rxonly
0.088Mpps
In
Prior to this the max size was 32 which was unnecessarily
small. Also enforce the max batch size for TX for both
copy and zero copy modes. Prior to this only copy mode
enforced the max size.
Signed-off-by: Ciara Loftus
---
drivers/net/af_xdp/rte_eth_af_xdp.c | 8
1 file changed, 4 inser
poll() is more expensive and requires more tuning
when used with the upcoming busy polling functionality.
Signed-off-by: Ciara Loftus
---
drivers/net/af_xdp/rte_eth_af_xdp.c | 7 ---
1 file changed, 4 insertions(+), 3 deletions(-)
diff --git a/drivers/net/af_xdp/rte_eth_af_xdp.c
b/drivers/
This commit introduces support for preferred busy polling
to the AF_XDP PMD. This feature aims to improve single-core
performance for AF_XDP sockets under heavy load.
A new vdev arg is introduced called 'busy_budget' whose default
value is 64. busy_budget is the value supplied to the kernel
with t
> -Original Message-
> From: dev On Behalf Of Thomas Monjalon
> Sent: Wednesday, February 24, 2021 8:42 AM
> To: oulijun
> Cc: ferruh.yi...@intel.com; dev@dpdk.org; linux...@openeuler.org
> Subject: Re: [dpdk-dev] [PATCH 1/2] config/arm: fix Hisilicon kunpeng920 SoC
> build
>
> 24/02/2
24/02/2021 12:55, Juraj Linkeš:
> From: dev On Behalf Of Thomas Monjalon
> > 24/02/2021 02:34, oulijun:
> > >
> > > 在 2021/2/10 17:41, Thomas Monjalon 写道:
> > > > 03/02/2021 13:46, Lijun Ou:
> > > >> From: Chengchang Tang
> > > >>
> > > >> Because of the '9ca2f16' have merged, the current hns3 pm
> -Original Message-
> From: dev On Behalf Of Guo, Jia
> Sent: Wednesday, February 24, 2021 11:38 AM
> To: Yu, DapengX ; Wang, Haiyue
>
> Cc: dev@dpdk.org; sta...@dpdk.org
> Subject: Re: [dpdk-dev] [PATCH] net/e1000: remove MTU setting limitation
>
> Seems that this is align with the
> -Original Message-
> From: dev On Behalf Of Guo, Jia
> Sent: Wednesday, February 24, 2021 11:41 AM
> To: Yu, DapengX ; Wang, Haiyue
>
> Cc: dev@dpdk.org; sta...@dpdk.org
> Subject: Re: [dpdk-dev] [PATCH v2] net/igc: remove MTU setting limitation
>
> Seems that v2 is the same as v1,
On 2/7/2021 1:58 AM, Li, Xiaoyun wrote:
-Original Message-
From: Yigit, Ferruh
Sent: Friday, February 5, 2021 22:27
To: Lu, Wenzhuo ; Li, Xiaoyun ;
Iremonger, Bernard
Cc: Yigit, Ferruh ; dev@dpdk.org
Subject: [PATCH] app/testpmd: remove duplicated offload display
"show port cap all|"
This patch series adds changes to dpaaX ethernet pmd
1. Basic Traffic Management support for shaper and scheduler
2. Support external buffer in Transmit side.
3. Optimize the SG packet handling
4. Add support APIs in DPDMUX (SRIOV equivalent for DPAA2)
5. Fix isssues
v3: fix spelling issues, add
From: Youri Querry
Random portal hangs observed on device with QBMAN 5.0
This fixes few random packet hang issues in event mode.
Few things fixed it.
1. Generally, pi == ci, no need for extra checks.
2. The proper initializations in init with ci
Fixes: 1b49352f41be ("bus/fslmc: rename portal pi
From: Nipun Gupta
Reading of word un-aligned values after reading word aligned
values lead to corrution of memory, such that older value.
This patch make changes such that word alignedaccess is made,
before making an un-aligned access
Fixes: 6d6b4f49a155 ("bus/dpaa: add FMAN hardware operations"
From: Rohit Raj
According to DPDK Documentation, rte_eth_link_get API can wait up to 9
seconds for auto-negotiation to finish and then returns link status.
In current implementation of rte_eth_link_get API in DPAA2 drivers, it
was not waiting for auto negotiation to finish and was returning link
From: Rohit Raj
According to DPDK Documentation, rte_eth_link_get API can wait up to 9
seconds for auto-negotiation to finish and then returns link status.
In current implementation of rte_eth_link_get API in DPAA drivers, it
was not waiting for auto negotiation to finish and was returning link
This patch enables support to use the first segment
headroom to build the HW required Scatter Gather
Table. (if space is available).
This will avoid 1 less buffer for SG buffer creation.
Signed-off-by: Sachin Saxena
Signed-off-by: Hemant Agrawal
---
drivers/bus/fslmc/portal/dpaa2_hw_pvt.h | 5
This patch support tx of external buffers
Signed-off-by: Hemant Agrawal
---
drivers/net/dpaa/dpaa_rxtx.c | 39 +++-
drivers/net/dpaa/dpaa_rxtx.h | 8 +---
2 files changed, 31 insertions(+), 16 deletions(-)
diff --git a/drivers/net/dpaa/dpaa_rxtx.c b/drivers/
From: Nipun Gupta
This patch support tx of external allocated buffers.
Signed-off-by: Nipun Gupta
Signed-off-by: Sachin Saxena
Acked-by: Hemant Agrawal
---
drivers/net/dpaa2/dpaa2_rxtx.c | 42 ++
1 file changed, 42 insertions(+)
diff --git a/drivers/net/dpaa2
This patch introduce a new pmd api, which can help the applications
to configure the max framelen for a given dpdmux interface
Signed-off-by: Hemant Agrawal
Acked-by: Hemant Agrawal
---
drivers/net/dpaa2/dpaa2_mux.c | 28 +++-
drivers/net/dpaa2/rte_pmd_dpaa2.h | 18 +
From: Gagandeep Singh
Add basic support for scheduling and shaping on dpaa2
platform.
HW supports 2 level of scheduling and shaping.
However the current patch only support single level.
Signed-off-by: Gagandeep Singh
Acked-by: Hemant Agrawal
---
doc/guides/nics/dpaa2.rst | 120
From: Akhil Goyal
Added support for flow raw pattern and check that the call
for dpdmux_set_custom_key() which should be called
only once for a particular DPDMUX as all previous rules
will be erased with this call.
Hence calling it for the first time only.
Signed-off-by: Akhil Goyal
Acked-by: H
From: Apeksha Gupta
This is require as the interface is shared with linux and we do not want
the dpdmux to be reset. rather the default interface to kernel shall
continue.
command dpdmux_set_resetable is used to skip DPDMUX reset.
By default the DPDMUX_RESET command will reset the DPDMUX complete
DPDMUX should not drop parse error packets. They shall
be left to the decision of the connected DPNI interfaces
Signed-off-by: Hemant Agrawal
---
drivers/net/dpaa2/dpaa2_mux.c | 18
drivers/net/dpaa2/mc/dpdmux.c | 37 +
drivers/net/dpaa2/mc/fsl_dpdmux.h | 113 +
Add support for dev arg ``fslmc:dpni.1,drv_tx_conf=1``
It is optional for dpaa2 to use TX confirmation. DPAA2
can free the transmitted packets. However some use-case
requires the TX confirmation to be explicit.
Signed-off-by: Hemant Agrawal
---
doc/guides/nics/dpaa2.rst| 4
driver
change the tx queue congestion notification to
the ratio of current queue size instead of fixed.
Signed-off-by: Hemant Agrawal
---
drivers/net/dpaa2/dpaa2_ethdev.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/net/dpaa2/dpaa2_ethdev.c b/drivers/net/dpaa2/dpaa2_e
From: Nipun Gupta
In case error packets are received by the ethernet interface,
this patch enables the receival of packets on the error queue,
printing the error and the error packet.
to enable, use the dev_arg as : fslmc:dpni.1,drv_error_queue=1
Signed-off-by: Nipun Gupta
Acked-by: Hemant Agr
From: Nipun Gupta
CGR are automatically freed up in the kernel. As we do not cleanup
the queues, if we release the CGR here, kernel reports them in use.
So have them freed up in the kernel
Signed-off-by: Nipun Gupta
Acked-by: Hemant Agrawal
---
drivers/net/dpaa/dpaa_ethdev.c | 6 --
1 fil
DPAA2 DPBP object access need availability of MCP object
pointer. In case of secondary process, we need to use local
MCP pointer instead of primary process.
Signed-off-by: Nipun Gupta
Signed-off-by: Hemant Agrawal
---
drivers/mempool/dpaa2/dpaa2_hw_mempool.c | 8 +++-
1 file changed, 7 inse
Secondary process also need the access the qman and bman
ccsr map.
Signed-off-by: Hemant Agrawal
---
drivers/bus/dpaa/dpaa_bus.c | 26 --
1 file changed, 12 insertions(+), 14 deletions(-)
diff --git a/drivers/bus/dpaa/dpaa_bus.c b/drivers/bus/dpaa/dpaa_bus.c
index 662cbf
From: Nipun Gupta
The current driver only support single buffer pool on a given
pmd instance. return error, if trying to configure more.
Signed-off-by: Nipun Gupta
Acked-by: Hemant Agrawal
---
drivers/mempool/dpaa/dpaa_mempool.c | 1 +
drivers/net/dpaa/dpaa_ethdev.c | 6 ++
2 files c
From: Nipun Gupta
DPAA can share an interface on classification criteria with kernel.
This patch enables default kernel driver to be used as a shared MAC
interface with DPDK interface. (provided that VSP is enabled on that
interface.)
Signed-off-by: Nipun Gupta
Acked-by: Hemant Agrawal
---
d
1. It is not a error if no network device available. One can
only use crypto device
2. Improve logging for failure in detecting the bus
Signed-off-by: Hemant Agrawal
---
drivers/bus/dpaa/dpaa_bus.c | 8 +---
1 file changed, 5 insertions(+), 3 deletions(-)
diff --git a/drivers/bus/dpaa/dpaa_
This patch adds RX buf size support in queue info
Signed-off-by: Hemant Agrawal
---
drivers/net/dpaa2/dpaa2_ethdev.c | 6 ++
1 file changed, 6 insertions(+)
diff --git a/drivers/net/dpaa2/dpaa2_ethdev.c b/drivers/net/dpaa2/dpaa2_ethdev.c
index 586d116227..0e7ebf4dc0 100644
--- a/drivers/net
This patch adds rx buf size support in rxq info for dpaa
Signed-off-by: Hemant Agrawal
---
drivers/bus/dpaa/include/fsl_fman.h | 1 +
drivers/bus/dpaa/version.map| 1 +
drivers/net/dpaa/dpaa_ethdev.c | 7 +++
3 files changed, 9 insertions(+)
diff --git a/drivers/bus/dpaa/includ
On Sun, Feb 21, 2021 at 4:58 PM 谢华伟(此时此刻） wrote:
>
>
> On 2021/2/18 17:33, David Marchand wrote:
> > On Fri, Jan 29, 2021 at 4:19 AM 谢华伟(此时此刻）
> > wrote:
> >> From: "huawei.xhw"
> >>
> >> Currently virtio PMD asssumes legacy device uses PIO bar.
> >> There are three ways to get PIO(PortIO) addr
This looks more like a hack than an actual fix to me.
After this commit:
"ip link set up" is sent to the userspace with unlocked rtnl_lock
"ip link set down" is sent to the userspace with locked rtnl_lock
How is this really fixing anything? IMHO it only complicates the code.
If talking with users
Hi, Jiawei
Thank you for the patch, but It seems I need some clarifications.
As far I understand the issue:
- we are in the midst of receiving the multi-segment packet
- we have some mbufs allocated and packet chain is partially built
- we fail on allocation replenishing mbuf for the segment
- we
Currently KNI has a lot of issues with deadlocks locking the code,
after this commit, they are gone, and the code runs properly without
crashing.
That was tested with over 100 restarts of the application, which
previously required a hard reset of the board.
I think this benefit overweights the com
Elad,
I understand your point.
But the fact that this fix works for you doesn't mean that it will work for
all DPDK users.
For example, I provided two simple commands: "ip link set up" and "ip link
set down".
Your fix works for only one of them. For me, this is not a proper fix.
It may work for y
I tested both link up and link down many times without any problems on
100 restarts of the application.
Having KNI deadlock frequently for real life applications is far worst, IMHO.
FYI
Elad.
On Wed, Feb 24, 2021 at 4:04 PM Igor Ryzhov wrote:
>
> Elad,
>
> I understand your point.
> But the fa
Both link up and link down also work for me without this patch.
So what's the point in merging it?
Just to clarify - I am not against the idea of this patch.
Talking to userspace under rtnl_lock is a bad idea.
I just think that any patch should fix some specified problem.
If this patch is trying
This is also causing build error, like:
https://travis-ci.com/github/ovsrobot/dpdk/jobs/482121104
Also '@internal' marker removed from doxygen comment, since public API
should not be internal.
Fixes: 4d3892dcd77b ("power: make channel message functions public")
Cc: sta...@dpdk.org
Signed-off-by:
The deadlock scenarios are explained below:
It is described in Stephen Hemminger's original patch:
"
This fixes a deadlock when using KNI with bifurcated drivers.
Bringing kni device up always times out when using Mellanox
devices.
The kernel KNI driver sends message to userspace to complete
th
Stephen's idea was to fix the deadlock when working with the bifurcated
driver.
Your rework breaks this because you still send link down requests under
rtnl_lock.
Did you test your patch with Mellanox devices?
On Wed, Feb 24, 2021 at 5:56 PM Elad Nachman wrote:
> The deadlock scenarios are expla
On 2021/2/24 20:49, David Marchand wrote:
On Sun, Feb 21, 2021 at 4:58 PM 谢华伟(此时此刻） wrote:
On 2021/2/18 17:33, David Marchand wrote:
On Fri, Jan 29, 2021 at 4:19 AM 谢华伟(此时此刻） wrote:
From: "huawei.xhw"
Currently virtio PMD asssumes legacy device uses PIO bar.
There are three ways to get
From: Kalesh AP
This patchset contain bnxt bug fixes and enhancements.
Please apply.
Ajit Khaparde (1):
net/bnxt: update to new version of backing store
Kalesh AP (9):
net/bnxt: remove unused macro
net/bnxt: fix vnic configuration
net/bnxt: remove extra blank line
net/bnxt: update HW
From: Kalesh AP
remove HWRM_SEQ_ID_INVALID macro.
Fixes: 804e746c7b73 ("net/bnxt: add hardware resource manager init code")
Cc: sta...@dpdk.org
Signed-off-by: Kalesh AP
Reviewed-by: Somnath Kotur
Reviewed-by: Ajit Kumar Khaparde
---
drivers/net/bnxt/bnxt_hwrm.h | 1 -
1 file changed, 1 dele
From: Kalesh AP
PMD should not set any flags to receive RoCE traffic while
configuring the vnic. Since the PMD does not support RoCE
some of the flags and code is unused. Clean it up.
Fixes: b7778e8a1c00 ("net/bnxt: refactor to properly allocate resources for
PF/VF")
Cc: sta...@dpdk.org
Signed
From: Kalesh AP
Removed an unnecessary extra blank line.
Signed-off-by: Kalesh AP
Reviewed-by: Somnath Kotur
---
drivers/net/bnxt/bnxt_hwrm.c | 1 -
1 file changed, 1 deletion(-)
diff --git a/drivers/net/bnxt/bnxt_hwrm.c b/drivers/net/bnxt/bnxt_hwrm.c
index 5366fe7..e11502c 100644
--- a/driv
From: Venkat Duvvuru
bp->rx_num_qs_per_vnic is not initialized in the single queue mode.
As a result of this when an interface is reconfigured to single
queue mode from an existing multiqueue mode, bp->rx_num_qs_per_vnic
is not updated to the value of 1. Hence, the driver will try to
access more
From: Ajit Khaparde
Update HWRM headers to version 1.10.2.15
which updates the backing store API for additional TQM rings.
Add support for 9th TQM ring using latest firmware interface.
Also make sure that we set only necessary bits in the enables
field in backing store request.
Signed-off-by: A
From: Kalesh AP
1. Used port id in async event logs.
2. Added a debug log in bnxt_hwrm_func_driver_unregister().
Signed-off-by: Kalesh AP
Reviewed-by: Somnath Kotur
Reviewed-by: Ajit Kumar Khaparde
---
drivers/net/bnxt/bnxt_cpr.c | 14 +-
drivers/net/bnxt/bnxt_hwrm.c | 2 ++
2
From: Kalesh AP
This is a new async message that the firmware can send to check if it
can communicate with the driver. This is an added error detection
scheme that firmware can use if it suspects errors in the PCIe
interface. When the driver receives this async message, it will reply
back echoing
From: Kalesh AP
During some fatal firmware error conditions, the PCI config space
register 0x2e which normally contains the subsystem ID will become
0x. This register will revert back to the normal value after
the chip has completed core reset. If we detect this condition,
we can poll this co
From: Kalesh AP
Moved fw readiness check to a new routine bnxt_check_fw_ready().
During error recovery, driver needs to wait for fw readiness.
For that, it uses bnxt_hwrm_ver_get() function now and that
function does parsing of the VER_GET response as well.
Added a new lightweight function bnxt
From: Kalesh AP
On Thor, Rx timestamp is present in the Rx completion record.
Only 32 bits of the timestamp is present in the completion.
The driver needs to periodically poll the current 48 bit
free running timer using the HWRM_PORT_TS_QUERY command.
It can combine the upper 16 bits from the HWR
On 2/24/2021 3:16 PM, Lance Richardson wrote:
Lance, can you spare some time to make the above mentioned patch?
Sure. Are you looking for something like the changes below, or also including
a search and replace of the deprecated macro name with the new one?
Thank you.
Yes below looks good, a
On 2/23/2021 2:20 PM, 谢华伟(此时此刻） wrote:
On 2021/2/23 1:25, Ferruh Yigit wrote:
On 2/22/2021 5:15 PM, 谢华伟(此时此刻） wrote:
From: "huawei.xhw"
With IO BAR, we get PIO(programmed IO) address.
With MMIO BAR, we get mapped virtual address.
We distinguish PIO(Programmed IO) and MMIO(memory mapped IO) b
On Wed, 24 Feb 2021 15:49:49 +0300
Igor Ryzhov wrote:
> This looks more like a hack than an actual fix to me.
>
> After this commit:
> "ip link set up" is sent to the userspace with unlocked rtnl_lock
> "ip link set down" is sent to the userspace with locked rtnl_lock
Calling userspace with rtn
Elad,
To make it work on Mellanox NIC, you need to find a way to send
ALL requests to userspace without rtnl_lock held, including link down.
As I understand, the race condition in __dev_close_many must be
solved somehow.
I can't provide remote access, but I am happy to test on Mellanox NICs,
if y
On 2/24/2021 12:42 PM, Hemant Agrawal wrote:
This patch introduce a new pmd api, which can help the applications
to configure the max framelen for a given dpdmux interface
Signed-off-by: Hemant Agrawal
Acked-by: Hemant Agrawal
<...>
@@ -2,6 +2,7 @@ EXPERIMENTAL {
global:
rte_
On 2/24/2021 12:42 PM, Hemant Agrawal wrote:
This patch series adds changes to dpaaX ethernet pmd
1. Basic Traffic Management support for shaper and scheduler
2. Support external buffer in Transmit side.
3. Optimize the SG packet handling
4. Add support APIs in DPDMUX (SRIOV equivalent for DPAA2
On Wed, Feb 24, 2021 at 4:29 PM 谢华伟(此时此刻） wrote:
> > Did you check that virtio devices bound to uio_pci_generic still works
> > with legacy mode + PIO?
>
> I had verified PIO, might under igb_uio driver.
Well, if you are unsure, please retest both cases, igb_uio and uio_pci_generic.
>
> Theoret
From: Jie Zhou
This patch allows the same set of rte_metrics_tel_* functions to be
exported no matter JANSSON is available or not, by doing following:
1. Leverage dpdk_conf to set configuration flag RTE_HAVE_JANSSON
when Jansson dependency is found.
2. In rte_metrics_telemetry.c, levera
> Lance, can you spare some time to make the above mentioned patch?
Sure. Are you looking for something like the changes below, or also including
a search and replace of the deprecated macro name with the new one?
- /** External IP header checksum error. */
+/**
+ * Deprecated.
+ * This flag has
Rename PKT_RX_EIP_CKSUM_BAD to PKT_RX_OUTER_IP_CKSUM_BAD and
deprecate the original name. The new name is better aligned
with existing PKT_RX_OUTER_* flags, which should help reduce
confusion about its purpose.
Suggested-by: Ferruh Yigit
Signed-off-by: Lance Richardson
---
app/test-pmd/csumonly
rte_eal_remote_launch and rte_eal_wait_lcore need to provide
correct memory ordering to address the data communication from
main core to worker core and vice versa.
There are 2 use cases:
1) All the store operations (meant for worker) by main core
should be visible to worker core before the worker
In the rte_eal_remote_launch function, the lcore function
pointer is checked for NULL. However, the pointer is never
reset to NULL. Reset the lcore function pointer and argument
after the worker has completed executing the lcore function.
Signed-off-by: Honnappa Nagarahalli
Reviewed-by: Ruifeng W
Ensure that the memory operations before the call to
rte_eal_remote_launch are visible to the worker thread.
Signed-off-by: Honnappa Nagarahalli
Reviewed-by: Ola Liljedahl
---
lib/librte_eal/freebsd/eal_thread.c | 19 +++
lib/librte_eal/linux/eal_thread.c | 19 +++-
FINISHED state seems to be used to indicate that the worker's update
of the 'state' is not visible to other threads. There seems to be no
requirement to have such a state.
Signed-off-by: Honnappa Nagarahalli
Reviewed-by: Ola Liljedahl
---
drivers/event/dpaa2/dpaa2_eventdev_selftest.c | 2 +-
dr
Ensure that the memory operations in worker thread, that happen
before it returns the status of the assigned function, are
visible to the main thread.
Signed-off-by: Honnappa Nagarahalli
---
lib/librte_eal/common/eal_common_launch.c | 8
lib/librte_eal/freebsd/eal_thread.c | 10 +
wrk_cmd variable is used to signal the worker thread to start
or stop the stress test loop. Relaxed barriers are used
to achieve the same.
Signed-off-by: Honnappa Nagarahalli
Reviewed-by: Ola Liljedahl
---
app/test/test_ring_stress_impl.h | 18 +-
1 file changed, 9 insertions(+)
From: Jie Zhou
Meson with Windows clang generates incorrect linker flag
"--subsystem,console" instead of "/subsystem:console" which
will fail the DPDK build. This is discovered at porting testpmd.
Meson 0.57.0 has the fix and should be used for DPDK Windows build.
Update the DPDK WindowsGSG DPDK
On 2021/2/24 23:45, Ferruh Yigit wrote:
On 2/23/2021 2:20 PM, 谢华伟(此时此刻） wrote:
On 2021/2/23 1:25, Ferruh Yigit wrote:
On 2/22/2021 5:15 PM, 谢华伟(此时此刻） wrote:
From: "huawei.xhw"
With IO BAR, we get PIO(programmed IO) address.
With MMIO BAR, we get mapped virtual address.
We distinguish PIO(
On 2/24/21 7:24 PM, Lance Richardson wrote:
> Rename PKT_RX_EIP_CKSUM_BAD to PKT_RX_OUTER_IP_CKSUM_BAD and
> deprecate the original name. The new name is better aligned
> with existing PKT_RX_OUTER_* flags, which should help reduce
> confusion about its purpose.
>
> Suggested-by: Ferruh Yigit
> S
On 2/16/21 7:35 PM, Xueming(Steven) Li wrote:
>
>> -Original Message-
>> From: Andrew Rybchenko
>> Sent: Monday, February 15, 2021 5:32 PM
>> To: Xueming(Steven) Li
>> Cc: dev@dpdk.org; Slava Ovsiienko ; Asaf Penso
>> ; NBU-Contact-Thomas Monjalon
>> ; Ferruh Yigit ; Ray Kinsella
>> ;
94 matches
Mail list logo
