Hi, Thomas,
在 2021/10/6 3:21, Thomas Monjalon 写道:
22/09/2021 05:36, Min Hu (Connor):
From: Huisong Li
Use the testpmd to perform the following operations:
1) mac_addr add 0 00:18:2D:00:00:90
2) mac_addr add 0 00:18:2D:00:00:91
3) mac_addr add 0 00:18:2D:00:00:92
4) mac_addr set 0 00:18:2D:00:
Enable protocol agnostic flow offloading to support raw pattern input
for RSS hash flow rule creation. It is based on Parser Libary feature.
Current rte_flow raw API is utilized.
Ting Xu (2):
net/ice: enable protocol agnostic flow offloading in RSS
doc: add protocol agnostic flow offloading fo
Enable protocol agnostic flow offloading to support raw pattern input
for RSS hash flow rule creation. It is based on Parser Libary feature.
Current rte_flow raw API is utilized.
Signed-off-by: Ting Xu
---
drivers/net/ice/ice_hash.c | 182 -
1 file changed, 16
Protocol agnostic flow offloading for RSS hash is supported. Raw pattern
input can be used to create RSS hash flow rules, using current rte_flow
raw API.
Signed-off-by: Ting Xu
---
doc/guides/rel_notes/release_21_11.rst | 1 +
1 file changed, 1 insertion(+)
diff --git a/doc/guides/rel_notes/rel
Hello,
On Fri, Oct 8, 2021 at 8:15 AM Liu, Changpeng wrote:
>
> I tried the above DPDK patches, and got the following errors:
>
> pci.c:115:7: error: call to ‘rte_pci_read_config’ declared with attribute
> error: Symbol is not public ABI
> 115 | rc = rte_pci_read_config(dev->dev_handle, value
On 2021/10/6 18:26, Thomas Monjalon wrote:
> 24/09/2021 12:53, Chengwen Feng:
>> The 'dmadevice' is a generic type of DMA device.
>
> Do you mean 'dmadev' ?
>
>> This patch introduce the 'dmadevice' device allocation APIs.
>>
>> The infrastructure is prepared to welcome drivers in drivers/dma/
>
https://bugs.dpdk.org/show_bug.cgi?id=826
Bug ID: 826
Summary: red_autotest random failures
Product: DPDK
Version: unspecified
Hardware: All
OS: All
Status: UNCONFIRMED
Severity: normal
Priority:
On Tue, Oct 5, 2021 at 3:08 PM David Marchand wrote:
>
> Looking at how to add an autotest, I came upon autotest_data.py used
> by autotest.py which has been in DPDK for a long time.
>
> From what I see, DTS directly calls the test binary.
> The public CI relies on meson to invoke unit tests.
>
>
On Thu, Oct 7, 2021 at 2:22 PM Thomas Monjalon wrote:
>
> The guides should be referenced locally with RST syntax
> :doc: (beginning of page) or :ref: (specific chapter).
> The links to doc.dpdk.org/guides/ are removed.
>
> The links to the doc.dpdk.org/api/ are acceptable,
> but should not point
Thanks, I have worked with Chenbo to address this issue before. After enable
the `ALLOW_INTERNAL_API` option, it works now with SPDK.
Another issue raised by Jim Harris is that for distro packaged DPDK, since this
option isn't enabled by default, this will not allow SPDK
to use the distro packa
Since the AF_XDP PMD does not work for secondary processes as reported
in Bugzilla 805, check for the process type at the beginning of probe
and return ENOTSUP if the process type is secondary.
It is planned that secondary processes will be supported by the PMD in
full in a future release by using
On 2021/10/6 18:46, Thomas Monjalon wrote:
> 24/09/2021 12:53, Chengwen Feng:
>> --- a/doc/guides/prog_guide/dmadev.rst
>> +++ b/doc/guides/prog_guide/dmadev.rst
>> @@ -62,3 +62,44 @@ identifiers:
>>
>> - A device name used to designate the DMA device in console messages, for
>>administratio
On 10/8/2021 8:30 AM, David Marchand wrote:
On Tue, Oct 5, 2021 at 3:08 PM David Marchand wrote:
Looking at how to add an autotest, I came upon autotest_data.py used
by autotest.py which has been in DPDK for a long time.
From what I see, DTS directly calls the test binary.
The public CI reli
Hi,Ananyev, Konstantin
Thank you for your reply.I'm sorry for my poor English.This is the first time
I've submitted a patch to the DPDK, and some of the processes are not
familiar.I am happy to contribute to the DPDK.
As described in your message：
>As I understand what that patch does - fix
Hi
> -Original Message-
> From: Xueming Li
> Sent: Wednesday, October 06, 2021 19:18
> To: dev@dpdk.org
> Cc: xuemi...@nvidia.com; Yigit, Ferruh ; Andrew
> Rybchenko ; Singh, Aman Deep
> ; Thomas Monjalon ;
> John W. Linville ; Loftus, Ciara
> ; Zhang, Qi Z ; Hemant
> Agrawal ; Sachin Sax
> -Original Message-
> From: David Marchand
> Sent: Thursday, September 30, 2021 4:20 PM
> To: Peng, ZhihongX ; Richardson, Bruce
>
> Cc: Burakov, Anatoly ; Ananyev, Konstantin
> ; Stephen Hemminger
> ; dev ; Lin, Xueqin
> ; Thomas Monjalon
> Subject: Re: [dpdk-dev] [PATCH v6 1/2] Enable
On Sat, Oct 2, 2021 at 1:55 AM Tomasz Duszynski wrote:
>
> Add helper functions that allow one to check platform
> ROC is running on. Platform type is retrieved from device
> tree attribute runplatform which is updated by EBF accordingly.
>
> Signed-off-by: Tomasz Duszynski
> Reviewed-by: Jerin J
>
> >+
> >+def list_fp():
> >+""" List all available file-prefixes to user """
> >+print("Valid file-prefixes:\n")
>
> Nit: I think it might be cleaner to move this down to just before the file
> prefixes print out, so it doesn't print out when no apps are available.
>
> >+path = g
In secondary process, because it doesn't clear eth_dev->data, the "eth_dev"
above will not be NULL when rte_eth_dev_close() has been called before this
interface is called. In this case, Ethernet device will be released
repeatedly. The state of the Ethernet device is equal to RTE_ETH_DEV_UNUSED
aft
On Wed, 2021-09-29 at 13:35 +0530, Jerin Jacob wrote:
> On Wed, Sep 29, 2021 at 1:11 PM Xueming(Steven) Li
> wrote:
> >
> > On Tue, 2021-09-28 at 20:29 +0530, Jerin Jacob wrote:
> > > On Tue, Sep 28, 2021 at 8:10 PM Xueming(Steven) Li
> > > wrote:
> > > >
> > > > On Tue, 2021-09-28 at 13:59 +
On Fri, Oct 8, 2021 at 10:07 AM Peng, ZhihongX wrote:
>
> > -Original Message-
> > From: David Marchand
> > Sent: Thursday, September 30, 2021 4:20 PM
> > To: Peng, ZhihongX ; Richardson, Bruce
> >
> > Cc: Burakov, Anatoly ; Ananyev, Konstantin
> > ; Stephen Hemminger
> > ; dev ; Lin, Xu
Hi Kevin,
I thought about something like that
(feel free to update it if you feel I missed something):
ip_frag: fix fragmenting IPv4 fragment
Current implementation of rte_ipv4_fragment_packet() doesn’t take
into account offset and flag values of the given packet, but blindly assumes
they are al
On Fri, 2021-10-01 at 14:39 +0300, Andrew Rybchenko wrote:
> Hello PMD maintainers,
>
> please, review the patch.
>
> It is especially important for net/mlx5 since changes there are
> not trivial.
>
> Thanks,
> Andrew.
>
> On 9/13/21 2:26 PM, Andrew Rybchenko wrote:
> > From: Viacheslav Galakti
Hi,
> -Original Message-
> From: Yigit, Ferruh
> Sent: Wednesday, October 06, 2021 1:17
> To: Jerin Jacob ; Li, Xiaoyun ;
> Ajit Khaparde ; Somnath Kotur
> ; Igor Russkikh ;
> Somalapuram Amaranath ; Rasesh Mody
> ; Shahed Shaikh ; Chas
> Williams ; Min Hu (Connor) ;
> Nithin Dabilpuram ;
Reviewed-by: Rosen Xu
> -Original Message-
> From: Yigit, Ferruh
> Sent: Wednesday, October 06, 2021 1:17
> To: Somalapuram Amaranath ; Ajit Khaparde
> ; Somnath Kotur
> ; Nithin Dabilpuram
> ; Kiran Kumar K ;
> Sunil Kumar Kori ; Satha Rao
> ; Rahul Lakkireddy
> ; Hemant Agrawal
> ; Sac
On Sat, Oct 2, 2021 at 2:09 AM Tomasz Duszynski wrote:
>
> Common octeontx2 code shares some of the PCI identifiers
> with cn10k platform and if built wrong drivers may be probed.
>
> octeontx2 configuration disables common cn10k code so disable
> common octeontx2 on cn10k.
>
> Signed-off-by: Toma
From: Viacheslav Galaktionov
The patch is required for all PMDs which do not provide representors
info on the representor itself.
The function, rte_eth_representor_id_get(), is used in
eth_representor_cmp() which is required in ethdev class iterator to
search ethdev port ID by name (representor
On Fri, Oct 08, 2021 at 09:03:22AM +0100, Ferruh Yigit wrote:
> On 10/8/2021 8:30 AM, David Marchand wrote:
> > On Tue, Oct 5, 2021 at 3:08 PM David Marchand
> > wrote:
> > >
> > > Looking at how to add an autotest, I came upon autotest_data.py used
> > > by autotest.py which has been in DPDK fo
Hi Konstantin,
Thank you for your reply, it's so useful！！！
But I have some questions.
Would you mind answer my questions？
>Cc: mailto:sta...@dpdk.org
This should be written in the commiter message：Cc: sta...@dpdk.org，right?
When I send patch,what is the parameters of --subject-prefix?(Which bra
From: Zhihong Peng
The gcc will check code more stricter when ASan enabled.
"Control reaches end of non-void function" error occurs here.
Fixes: f38913b7fb8e (pipeline: add meter array to SWX)
Cc: sta...@dpdk.org
Signed-off-by: Xueqin Lin
Signed-off-by: Zhihong Peng
---
lib/pipeline/rte_swx_
From: Zhihong Peng
AddressSanitizer (ASan) is a google memory error detect
standard tool. It could help to detect use-after-free and
{heap,stack,global}-buffer overflow bugs in C/C++ programs,
print detailed error information when error happens, large
improve debug efficiency.
`AddressSanitizer
From: Zhihong Peng
DPDK ASan functionality is currently only supported Linux x86_64.
Support other platforms, need to define ASAN_SHADOW_OFFSET value
according to google ASan document.
Signed-off-by: Xueqin Lin
Signed-off-by: Zhihong Peng
---
lib/eal/common/malloc_elem.c | 26 -
lib/eal/
> This patch updates the release note to describe qat refactor
> changes made.
>
> Signed-off-by: Fan Zhang
> ---
> doc/guides/rel_notes/release_21_11.rst | 4
> 1 file changed, 4 insertions(+)
>
> diff --git a/doc/guides/rel_notes/release_21_11.rst
> b/doc/guides/rel_notes/release_21_11.r
On 10/8/2021 7:19 AM, Wu, Jingjing wrote:
Besides checking VFGEN_RSTAT, there is a process to handle
VIRTCHNL_OP_EVENT from PF. What is the change for? Any scenario which
VIRTCHNL_OP_EVENT doesn't cover?
And how is the 500us been determined?
Hi Jingjing, thanks for reviewing, I think this
On Wed, Oct 06, 2021 at 09:20:08PM +0200, David Marchand wrote:
> Caught while checking CPUID related stuff in OVS.
>
> According to [1], for Structured Extended Feature Flags Enumeration Leaf
> (EAX = 0x07H, ECX = 0):
>
> - BMI1 is associated to EBX, bit 3 (was incorrectly 2),
> - SMEP is associ
Hi Matan,
Many thanks for review. See below.
Andrew.
On 10/6/21 12:45 PM, Matan Azrad wrote:
> Hi Andrew
>
> Thank you for the big effort to adjust mlx5.
> I left some comments inside.
> If you feel it is too much, we can do a later patch to improve.
>
> Matan
>
>
>> From: Andrew Rybchenko
>
From: 蔡慧超
Sent: Friday, October 8, 2021 10:38 AM
To: Ananyev, Konstantin
Cc: cai...@chinatelecom.cn; dev@dpdk.org
Subject: Re:RE: Re:RE: [PATCH] ip_frag: modify the fragment offset and mf
Hi Konstantin,
Thank you for your reply, it's so useful！！！
But I have some questions.
Would you mind an
Indirect actions should be used to do shared counters.
Signed-off-by: Andrew Rybchenko
Acked-by: Thomas Monjalon
Acked-by: Ajit Khaparde
Acked-by: Somnath Kotur
Acked-by: Ori Kam
---
v2:
- remove reserved field from count structure (review from Stephen)
- apply mlx5 review notes from
Add support for inline crypto for IPsec.
Signed-off-by: Declan Doherty
Signed-off-by: Abhijit Sinha
Signed-off-by: Radu Nicolau
---
drivers/common/iavf/iavf_type.h | 1 +
drivers/common/iavf/virtchnl.h | 17 +-
drivers/common/iavf/virtchnl_inline_ipsec.h | 553 +
Rework the TX path and TX descriptor usage in order to
allow for better use of oflload flags and to facilitate enabling of
inline crypto offload feature.
Signed-off-by: Declan Doherty
Signed-off-by: Abhijit Sinha
Signed-off-by: Radu Nicolau
Acked-by: Jingjing Wu
---
drivers/net/iavf/iavf_rxtx
Add support for inline crypto for IPsec, for ESP transport and
tunnel over IPv4 and IPv6, as well as supporting the offload for
ESP over UDP, and inconjunction with TSO for UDP and TCP flows.
Depends on series "new features for ipsec and security libraries"
https://patchwork.dpdk.org/project/dpdk/
Add support for asynchronous virtual channel messages, specifically for
inline IPsec messages.
Signed-off-by: Declan Doherty
Signed-off-by: Abhijit Sinha
Signed-off-by: Radu Nicolau
Acked-by: Jingjing Wu
---
drivers/net/iavf/iavf.h | 16
drivers/net/iavf/iavf_vchnl.c | 138 +++
Add support for inline crypto for IPsec, for ESP transport and
tunnel over IPv4 and IPv6, as well as supporting the offload for
ESP over UDP, and inconjunction with TSO for UDP and TCP flows.
Implement support for rte_security packet metadata
Add definition for IPsec descriptors, extend support fo
Add per queue counters for maintaining statistics for inline IPsec
crypto offload, which can be retrieved through the
rte_security_session_stats_get() with more detailed errors through the
rte_ethdev xstats.
Signed-off-by: Declan Doherty
Signed-off-by: Radu Nicolau
Acked-by: Jingjing Wu
---
dr
Add watchdog to iAVF PMD which support monitoring the VFLR register. If
the device is not already in reset then if a VF reset in progress is
detected then notfiy user through callback and set into reset state.
If the device is already in reset then poll for completion of reset.
The watchdog is dis
08/10/2021 10:21, Huisong Li:
> In secondary process, because it doesn't clear eth_dev->data, the "eth_dev"
> above will not be NULL when rte_eth_dev_close() has been called before this
> interface is called. In this case, Ethernet device will be released
> repeatedly. The state of the Ethernet dev
08/10/2021 10:03, Ferruh Yigit:
> On 10/8/2021 8:30 AM, David Marchand wrote:
> > On Tue, Oct 5, 2021 at 3:08 PM David Marchand
> > wrote:
> >>
> >> Looking at how to add an autotest, I came upon autotest_data.py used
> >> by autotest.py which has been in DPDK for a long time.
> >>
> >> From wha
08/10/2021 09:55, fengchengwen:
> On 2021/10/6 18:46, Thomas Monjalon wrote:
> > 24/09/2021 12:53, Chengwen Feng:
> >> --- a/lib/dmadev/rte_dmadev.c
> >> +++ b/lib/dmadev/rte_dmadev.c
> >> @@ -218,6 +218,9 @@ rte_dma_pmd_release(const char *name)
> >>if (dev == NULL)
> >>return -EIN
08/10/2021 09:13, fengchengwen:
> On 2021/10/6 18:26, Thomas Monjalon wrote:
> > 24/09/2021 12:53, Chengwen Feng:
> >> +++ b/lib/dmadev/rte_dmadev.h
> >> + * The dmadev are dynamically allocated by rte_dma_pmd_allocate() during
> >> the
> >> + * PCI/SoC device probing phase performed at EAL initia
08/10/2021 09:02, Min Hu (Connor):
> Hi, Thomas,
>
> 在 2021/10/6 3:21, Thomas Monjalon 写道:
> > 22/09/2021 05:36, Min Hu (Connor):
> >> From: Huisong Li
> >>
> >> Use the testpmd to perform the following operations:
> >> 1) mac_addr add 0 00:18:2D:00:00:90
> >> 2) mac_addr add 0 00:18:2D:00:00:91
Hi,
Sory there isn't - Will update in v3.
Regards,
Fan
> -Original Message-
> From: Akhil Goyal
> Sent: Friday, October 8, 2021 11:07 AM
> To: Zhang, Roy Fan ; dev@dpdk.org
> Subject: RE: [EXT] [PATCH v2 10/10] doc: update release note
>
> > This patch updates the release note to descr
The cocci script is to help add prefix 'RTE_ETH' namespace to all enum
& macro of ethdev library in a backward compatible way. After the script
makes the changes few manual changes are required in rte_ethdev.h for
enum name changes.
Signed-off-by: Aman Singh
---
devtools/cocci/namespace_ethdev.c
On Fri, Oct 8, 2021 at 12:33 PM Thomas Monjalon wrote:
> 08/10/2021 10:03, Ferruh Yigit:
> > On 10/8/2021 8:30 AM, David Marchand wrote:
> > > On Tue, Oct 5, 2021 at 3:08 PM David Marchand
> > > wrote:
> > >>
> > >> Looking at how to add an autotest, I came upon autotest_data.py used
> > >> by a
On Fri, Oct 8, 2021 at 8:09 AM Zhang, Qi Z wrote:
> > -Original Message-
> > From: Guo, Junfeng
> > Sent: Friday, October 8, 2021 6:42 PM
> > To: Zhang, Qi Z ; Wu, Jingjing
> > ;
> > Xing, Beilei
> > Cc: dev@dpdk.org; Yigit, Ferruh ; Guo, Junfeng
> > ; sta...@dpdk.org
> > Subject: [PATC
On 10/8/2021 8:50 AM, Ciara Loftus wrote:
Since the AF_XDP PMD does not work for secondary processes as reported
in Bugzilla 805, check for the process type at the beginning of probe
and return ENOTSUP if the process type is secondary.
It is planned that secondary processes will be supported by
On Fri, Oct 8, 2021 at 12:15 PM Bruce Richardson
wrote:
>
> On Wed, Oct 06, 2021 at 09:20:08PM +0200, David Marchand wrote:
> > Caught while checking CPUID related stuff in OVS.
> >
> > According to [1], for Structured Extended Feature Flags Enumeration Leaf
> > (EAX = 0x07H, ECX = 0):
> >
> > - B
> >
> > +uint8_t rte_thash_gfni_supported;
>
> .. = 0;
> ?
>
Also some comment with explanation would really be good here.
> This patch enables new GFNI Toeplitz hash in
> predictable RSS library.
>
> Signed-off-by: Vladimir Medvedkin
> ---
> lib/hash/rte_thash.c | 43 +++
> lib/hash/rte_thash.h | 19 +++
> lib/hash/version.map | 1 +
> 3 files changed, 59 i
Update the calculation of the max length needed when converting mbuf to
data vec in partial digest test case. This update make sure the enough
vec buffers are allocated for the appended digest in sgl op for QAT raw
datapath api.
Fixes: 4868f6591c6f ("test/crypto: add cases for raw datapath API")
C
Hi Akhil,
I just update the v2:
http://patchwork.dpdk.org/project/dpdk/patch/20211008113345.31818-1-kai...@intel.com/
This patch is a generic fix of test case for SGL op, I think there is no
dependence with Hemant's patch.
Regards
Kai
> -Original Message-
> From: Akhil Goyal
> Sent:
Sort the definitions for extended features (leaf 0) to enhance
readability.
Signed-off-by: David Marchand
Acked-by: Bruce Richardson
---
lib/eal/x86/rte_cpuflags.c | 38 +++---
1 file changed, 19 insertions(+), 19 deletions(-)
diff --git a/lib/eal/x86/rte_cpufla
Caught while checking CPUID related stuff in OVS.
According to [1], for Structured Extended Feature Flags Enumeration Leaf
(EAX = 0x07H, ECX = 0):
- BMI1 is associated to EBX, bit 3 (was incorrectly 2),
- SMEP is associated to EBX, bit 7 (was incorrectly 6),
- BMI2 is associated to EBX, bit 8 (wa
On 10/8/2021 4:41 AM, Jie Wang wrote:
The driver may change offloads info into dev->data->dev_conf
in dev_configure which may cause port->dev_conf and port->rx_conf
contain outdated values.
This patch adds a new API "rte_eth_dev_conf_get()" to help users
get device configuration info.
Not sur
On 10/8/2021 4:41 AM, Jie Wang wrote:
The driver may change offloads info into dev->data->dev_conf
in dev_configure which may cause port->dev_conf and port->rx_conf
contain outdated values.
This patch updates the offloads info if it changes to fix this issue.
Fixes: ce8d561418d4 ("app/testpmd:
On Thu, Oct 7, 2021 at 11:54 PM David Marchand
wrote:
>
> On Thu, Oct 7, 2021 at 10:25 PM William Tu wrote:
> >
> > This patch enables building the e1000 driver for Windows.
> > I tested using two Windows VM on top of VMware Fusion,
> > creating two e1000 devices with device ID 0x10D3,
> > verify
> Add support for NULL/NULL xform.
>
> Signed-off-by: Declan Doherty
> Signed-off-by: Radu Nicolau
> ---
Release notes missing.
Updates in doc/guides/cryptodevs/features/aesni_gcm.ini and
doc/guides/cryptodevs/features/aesni_mb.ini missing.
On Fri, Oct 8, 2021 at 2:21 PM William Tu wrote:
> > > Example when running:
> > > PS C:\dpdk> .\build\app\dpdk-testpmd.exe
> > > EAL: Detected CPU lcores: 4
> > > EAL: Detected NUMA nodes: 1
> > > EAL: Multi-process support is requested, but not available.
> > > EAL: WARNING: TSC frequency estima
This tool was used in the past to execute unit tests with make.
Meson has its own list of unit test, and its own way of calling them.
Since the switch to meson only builds, there is nothing depending on the
script in DPDK itself.
No CI seems to call it, time to put it to rest.
Signed-off-by: Davi
On Fri, Oct 8, 2021 at 12:13 AM Maxime Coquelin
wrote:
>
> This series aims at cleaning and simplifying the async
> enqueue path. I think it makes the code easier to
> understand, and is necessary before integrating new
> changes.
>
> I may have more reworks to propose in next revisions,
There is
On Thu, Oct 7, 2021 at 5:23 PM William Tu wrote:
>
> When BAR array is filled like this
> * Bar[4] = c844000c
> * Bar[5] = null
> ex:
> while ((descriptor->Type != CmResourceTypeMemory) ||
> !(descriptor->Flags & CM_RESOURCE_MEMORY_BAR));
> returns true, the loop continue
Registering new telemetry callbacks to list named (memzones)
and unnamed (malloc) memory reserved and return information
based on arguments provided by user.
Example:
Connecting to /var/run/dpdk/rte/dpdk_telemetry.v2
{"version": "DPDK 21.11.0-rc0", "pid": 59754, "max_output_len": 16384}
Connected
Hi Radu and Akhil
We can add this change as a patch into
http://patchwork.dpdk.org/project/dpdk/cover/20210929163035.608387-1-ciara.po...@intel.com/
v4 it is ok.
The doc can be updated accordingly.
Regards,
Fan
> -Original Message-
> From: dev On Behalf Of Akhil Goyal
> Sent: Friday,
08/10/2021 00:07, Dmitry Kozlyuk:
> --- a/doc/guides/rel_notes/deprecation.rst
> +++ b/doc/guides/rel_notes/deprecation.rst
> @@ -164,8 +164,13 @@ Deprecation Notices
>consistent with existing outer header checksum status flag naming, which
>should help in reducing confusion about its usage
> Dmitry Kozlyuk (2):
> net: rename Ethernet header fields
> doc: remove unneeded deprecations
>
[...]
> 56 files changed, 241 insertions(+), 250 deletions(-)
Applied, thanks.
Hi Akhil,
Meson may pop warnings when detected the libcrypto APIs that are marked as
deprecated – but for now it is still compliable.
For now shall we not touching it but fix the problem in future releases (we
need to address before it is gone for sure)?
Regards,
Fan
From: Akhil Goyal
Sent: W
On Fri, Oct 08, 2021 at 02:24:37PM +0200, David Marchand wrote:
> This tool was used in the past to execute unit tests with make.
> Meson has its own list of unit test, and its own way of calling them.
>
> Since the switch to meson only builds, there is nothing depending on the
> script in DPDK it
This patch enables building the e1000 driver for Windows.
I tested using two Windows VM on top of VMware Fusion,
creating two e1000 devices with device ID 0x10D3,
verifying rx/tx works correctly using dpdk-testpmd.exe
rxonly and txonly mode.
Signed-off-by: William Tu
Cc: Haiyue Wang
---
A short
In socket direct mode, it's possible to bind any two (maybe four
in the future) PCIe devices with IDs like :xx:xx.x and
:yy:yy.y. Bonding member interfaces are unnecessary to have
the same PCIe domain/bus/device ID anymore.
Doesn't need to backport to DPDK 20.11
v2: fix ci warnings.
v3: a
sysfs entry "phys_switch_id" holds each PCIe device'
guid.
The devices which reside in the same physical NIC should
have the same guid.
Signed-off-by: Rongwei Liu
Acked-by: Viacheslav Ovsiienko
---
drivers/common/mlx5/linux/mlx5_common_os.c | 41 ++
drivers/common/mlx5/linu
In socket direct mode, it's possible to bind any two (maybe four
in future) PCIe devices with IDs like :xx:xx.x and
:yy:yy.y. Bonding member interfaces are unnecessary to have
the same PCIe domain/bus/device ID anymore,
Kernel driver uses "system_image_guid" to identify if devices can
be b
> Subject: [PATCH 00/12] Expand NIC offloads support on Windows
>
> The series supports a group of NIC offloads on Windows:
>
> DEV_TX_OFFLOAD_TCP_TSO
> DEV_TX_OFFLOAD_VXLAN_TNL_TSO
> DEV_TX_OFFLOAD_GRE_TNL_TSO
> DEV_TX_OFFLOAD_GENEVE_TNL_TSO
> DEV_RX_OFFLOAD_VLAN_STRIP
> DEV_RX_OFFLOAD_KEEP_CRC
Hello,
I am trying to find the conclusion for this thread:[dpdk-dev] Question about
DPDK hugepage fd change
Can someone please help me as I do not see this patch anywhere. Was the lock
file usage changed such that lower number of descriptors are used if the
-single-file-segments option is used?
- Added mlx5_glue.h. It is same as its Linux counterpart
- Added mlx5_glue.c. It is same as its Linux counterpart
Signed-off-by: Srikanth Kaka
Signed-off-by: Vag Singh
Signed-off-by: Anand Thulasiram
---
drivers/common/mlx5/freebsd/mlx5_glue.c | 1505 +++
drivers/common/mlx
Defined mlx5_glue_constructor in mlx5_common_os.c to support
run-time dependency on rdma-core
Signed-off-by: Srikanth Kaka
Signed-off-by: Vag Singh
Signed-off-by: Anand Thulasiram
---
drivers/common/mlx5/freebsd/mlx5_common_os.c | 60
1 file changed, 60 insertions(+)
crea
This patch series introduces FreeBSD OS support for MLX5 PMD
Currently there is an ongoing review of FreeBSD OFED drivers and
RDMA-core libraries. Their status can be tracked at
https://reviews.freebsd.org/p/vag.singh_oneconvergence.com
Only MLX5 SRIOV interface is supported along with the follow
Add mlx5_os_malloc() & mlx5_os_free() APIs
Signed-off-by: Srikanth Kaka
Signed-off-by: Vag Singh
Signed-off-by: Anand Thulasiram
---
drivers/common/mlx5/freebsd/mlx5_common_os.h | 46
1 file changed, 46 insertions(+)
create mode 100644 drivers/common/mlx5/freebsd/mlx5_com
- On FreeBSD, XOPEN_SOURCE=600 is missing 'strlen' prototype.
The default XOPEN_SOURCE value (700) is used
- Shared library linking of libmlx5 and libibverbs is supported
- Generate mlx5_autoconf.h similar to Linux
Signed-off-by: Srikanth Kaka
Signed-off-by: Vag Singh
Signed-off-by: Anand Thul
Add helper functions in mlx5_common_os.h from its Linux
counterpart
Signed-off-by: Srikanth Kaka
Signed-off-by: Vag Singh
Signed-off-by: Anand Thulasiram
---
drivers/common/mlx5/freebsd/mlx5_common_os.h | 244 +++
1 file changed, 244 insertions(+)
diff --git a/drivers/common/m
The mlx5_core kernel driver creates a sysctl variable
dev.mlx5_core.0.ifname: mce0
Using this the device index and interface name are obtained
The interface name can be used by PMD to communicate with
FreeBSD network stack
Signed-off-by: Srikanth Kaka
Signed-off-by: Vag Singh
Signed-off-by: Ana
Using the dev structure, mlx5_get_ifname can get the MLX
interface name
Signed-off-by: Srikanth Kaka
Signed-off-by: Vag Singh
Signed-off-by: Anand Thulasiram
---
drivers/net/mlx5/freebsd/mlx5_ethdev_os.c | 33 +++
1 file changed, 33 insertions(+)
create mode 100644 drivers
Using syctl call the PCI addr is derived
dev.mlx5_core.0.%location: slot=8 function=0 dbsf=pci0:0:8:0
Signed-off-by: Srikanth Kaka
Signed-off-by: Vag Singh
Signed-off-by: Anand Thulasiram
---
drivers/common/mlx5/freebsd/mlx5_common_os.c | 48
1 file changed, 48 insertions(
The mlx5_common_verbs_reg_mr() and mlx5_common_verbs_dereg_mr()
APIs are equivalent to their Linux counterparts
Signed-off-by: Srikanth Kaka
Signed-off-by: Vag Singh
Signed-off-by: Anand Thulasiram
---
drivers/common/mlx5/freebsd/meson.build | 1 +
.../common/mlx5/freebsd/mlx5_common_ve
Given protection domain pointer, pointer to addr and length,
register the memory region.
This patch also defines mlx5_obj_ops.
mlx5_verbs.h & mlx5_verbs.c are equivalent to their Linux
counterparts.
Signed-off-by: Srikanth Kaka
Signed-off-by: Vag Singh
Signed-off-by: Anand Thulasiram
---
dri
Set the reg_mr and dereg_mr call backs
Signed-off-by: Srikanth Kaka
Signed-off-by: Vag Singh
Signed-off-by: Anand Thulasiram
---
drivers/net/mlx5/freebsd/mlx5_os.c | 17 +
1 file changed, 17 insertions(+)
diff --git a/drivers/net/mlx5/freebsd/mlx5_os.c
b/drivers/net/mlx5/free
Initialise the socket to communicate with the secondary process
mlx5_os.h and mlx5_socket.c are equivalent to Linux files
of the same name
Signed-off-by: Srikanth Kaka
Signed-off-by: Vag Singh
Signed-off-by: Anand Thulasiram
---
drivers/net/mlx5/freebsd/mlx5_os.h | 22 +++
drivers/net/ml
Adds FreeBSD version of mlx5_os_get_dev_attr. It is same as
the Linux definition
Signed-off-by: Srikanth Kaka
Signed-off-by: Vag Singh
Signed-off-by: Anand Thulasiram
---
drivers/net/mlx5/freebsd/mlx5_os.c | 87 ++
1 file changed, 87 insertions(+)
create mode 10064
The mlx5_os_open_device(), mlx5_config_doorbell_mapping_env(),
mlx5_restore_doorbell_mapping_env(), mlx5_alloc_verbs_buf() and
mlx5_free_verbs_buf() are equivalent to Linux APIs of the same
name
Signed-off-by: Srikanth Kaka
Signed-off-by: Vag Singh
Signed-off-by: Anand Thulasiram
---
drivers/n
MAC address is retrieved by making an IOCTL call
Signed-off-by: Srikanth Kaka
Signed-off-by: Vag Singh
Signed-off-by: Anand Thulasiram
---
drivers/net/mlx5/freebsd/mlx5_ethdev_os.c | 88 +++
1 file changed, 88 insertions(+)
diff --git a/drivers/net/mlx5/freebsd/mlx5_ethdev
MTU is retrieved by making an IOCTL call
Signed-off-by: Srikanth Kaka
Signed-off-by: Vag Singh
Signed-off-by: Anand Thulasiram
---
drivers/net/mlx5/freebsd/mlx5_ethdev_os.c | 23 +++
1 file changed, 23 insertions(+)
diff --git a/drivers/net/mlx5/freebsd/mlx5_ethdev_os.c
b
mlx5_set_link_up() & mlx5_set_link_down() use IOCTL call to
set link state
Signed-off-by: Srikanth Kaka
Signed-off-by: Vag Singh
Signed-off-by: Anand Thulasiram
---
drivers/net/mlx5/freebsd/mlx5_ethdev_os.c | 56 +++
1 file changed, 56 insertions(+)
diff --git a/drivers/ne
1 - 100 of 248 matches
Mail list logo
