> -Original Message-
> From: dev On Behalf Of Wei Huang
> Sent: 2020年10月30日 8:22
> To: dev@dpdk.org; Xu, Rosen ; Zhang, Qi Z
>
> Cc: Huang, Wei
> Subject: [dpdk-dev] [PATCH v2 2/2] raw/ifpga: use trusted buffer to free
>
> In rte_fpga_do_pr, calling function read() may taints argumen
> -Original Message-
> From: dev On Behalf Of Wei Huang
> Sent: 2020年10月30日 8:22
> To: dev@dpdk.org; Xu, Rosen ; Zhang, Qi Z
>
> Cc: Huang, Wei
> Subject: [dpdk-dev] [PATCH v2 1/2] raw/ifpga: terminate string filled by
> readlink with null
>
> readlink() does not terminate string, ad
Thanks a lot, I will send v2.
> -Original Message-
> From: Thomas Monjalon
> Sent: Friday, October 30, 2020 12:06 AM
> To: ferruh.yi...@intel.com; Bing Zhao
> Cc: Ori Kam ; dev@dpdk.org
> Subject: Re: [PATCH] doc: add the doc for mlx5 specific header
>
> External email: Use caution open
Hi Ferruh,
Thanks for your comments.
PSB
> -Original Message-
> From: Ferruh Yigit
> Sent: Friday, October 30, 2020 6:43 AM
> To: Slava Ovsiienko ; Bing Zhao
> ; Matan Azrad ; Ori Kam
>
> Cc: dev@dpdk.org; Raslan Darawsheh
> Subject: Re: [dpdk-dev] [PATCH v2 2/2] net/mlx5: add flow sync
> -Original Message-
> From: Ferruh Yigit
> Sent: Friday, October 23, 2020 6:42 PM
> To: Zhang, Yuying ; dev@dpdk.org; Zhang, Qi Z
> ; Xing, Beilei
> Cc: sta...@dpdk.org
> Subject: Re: [dpdk-dev] [PATCH v2] net/i40e: fix virtual channel confiliction
> issue
>
> On 10/19/2020 3:20 AM,
Add PROT field into IPv4 and IPv6 protocol headers for rss hash.
Fixes: 91f27b2e39ab ("net/iavf: refactor RSS")
Signed-off-by: Jeff Guo
---
drivers/net/iavf/iavf_hash.c | 32
1 file changed, 20 insertions(+), 12 deletions(-)
diff --git a/drivers/net/iavf/iavf_h
Thanks Tech board & Akhil for clarifying the concern.
Sure. I will send the new version of the patch.
Regards
Abhinandan
> -Original Message-
> From: Akhil Goyal
> Sent: Thursday, October 29, 2020 7:31 PM
> To: Gujjar, Abhinandan S ; Honnappa
> Nagarahalli ; Richardson, Bruce
> ; Ray K
Hi Nandini,
You can click on the following link ( this has / had worked for me ), i am
subscribed to couple of mailing list.
https://www.dpdk.org/contribute/#mailing-lists
There different mailing lists are there, you can click register against
whichever you want. The process is you might need to r
When a RSS rule with symmetric hash function, the RSS type shouldn't
carry with SRC/DST_ONLY. This patch adds invalid RSS type check for
the case.
Fixes: 91f27b2e39ab ("net/iavf: refactor RSS")
Signed-off-by: Simei Su
---
drivers/net/iavf/iavf_hash.c | 16
1 file changed, 16 in
Enable metadata extraction for flexible descriptors in AVF, that would
allow network function directly get metadata without additional parsing
which would reduce the CPU cost for VFs. The enabling metadata
extractions involve the metadata of VLAN/IPv4/IPv6/IPv6-FLOW/TCP/MPLS
flexible descriptors, a
Tested-by: JiangYuX
Best Regards
Jiang yu
> -Original Message-
> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Fan Zhang
> Sent: Thursday, October 29, 2020 10:47 PM
> To: dev@dpdk.org
> Cc: akhil.go...@nxp.com; Zhang, Roy Fan ; De
> Lara Guarch, Pablo
> Subject: [dpdk-de
These two patches fix defects found by coverity scan.
Main changes from v2:
- Fix coding style issue
Wei Huang (2):
raw/ifpga: terminate string filled by readlink with null
raw/ifpga: use trusted buffer to free
drivers/raw/ifpga/ifpga_rawdev.c | 10 ++
1 file changed, 6 insertions(+
In rte_fpga_do_pr, calling function read() may taints argument buffer
which turn to an untrusted value as argumen of rte_free().
Fixes: ef1e8ede3da5 ("raw/ifpga: add Intel FPGA bus rawdev driver")
Signed-off-by: Wei Huang
---
v2: add fixes information to log
---
drivers/raw/ifpga/ifpga_rawdev.c
readlink() does not terminate string, add a null character at the end
of the string if readlink() succeeds.
Fixes: 9c006c45d0c5 ("raw/ifpga: scan PCIe BDF device tree")
Signed-off-by: Wei Huang
---
v2: fix coding style issue
---
drivers/raw/ifpga/ifpga_rawdev.c | 3 ++-
1 file changed, 2 insert
Hi Nick,
> -Original Message-
> From: dev On Behalf Of Nick Connolly
> Sent: Monday, October 19, 2020 2:59 AM
> To: dev@dpdk.org
> Subject: [EXTERNAL] [dpdk-dev] [RFC] pthread on Windows
>
>
> The proposed changes are:
>
> 1. An EAL implementation of pthread with a new rte_pthread API
With DPDK 20.11 release, the igb_uio module is no more part of DPDK.
This patch provides a Makefile to the user, who can build this module
when required by running make inside the source dir.
Signed-off-by: Hariprasad Govindharajan
---
This patch will be part of dpdk-kmods repo
https://git.dpdk.o
The igb_uio source code requires interrupt modes defined as
MACROS and enums in the header file rte_pci_dev_features.h.
Now, the definitions are moved to the igb_uio.c file so that
this module can be built without building DPDK
Signed-off-by: Hariprasad Govindharajan
---
linux/igb_uio/igb_uio.c
MSBuild XML files have to use CRLF line-endings, otherwise any change
results in the whole file being rewritten with CRLF line-endings by
Visual Studio. However, it's inconvenient to have such files checked-out
with CLRF in Unix environments.
Add suggested git configuration to top-level README, so
On 10/22/2020 11:06 AM, Andrew Rybchenko wrote:
Dispite of the deprecation notice I'm not 100% sure that corresponding
functionality is supported via flow API. Since the functionality is
supported by the net/ixgbe driver only, it is a question to maintainers.
The patch series should be applied o
On Thu, Oct 29, 2020 at 7:15 AM Ananyev, Konstantin
wrote:
>
>
>
> >
> > 29/10/2020 11:50, Andrew Rybchenko:
> > > On 10/29/20 12:27 PM, Thomas Monjalon wrote:
> > > > The mempool pointer in the mbuf struct is moved
> > > > from the second to the first half.
> > > > It should increase performance
On 10/27/2020 3:42 PM, Slava Ovsiienko wrote:
Hi, Bing
Release notes / mlx5 features documentation update?
Beside this:
Acked-by: Viacheslav Ovsiienko
-Original Message-
From: Bing Zhao
Sent: Tuesday, October 27, 2020 16:47
To: Slava Ovsiienko ; Matan Azrad
; Ori Kam
Cc: dev@dpdk.or
On Thu, Oct 29, 2020 at 2:58 AM Andrew Rybchenko
wrote:
>
> On 10/29/20 12:27 PM, Thomas Monjalon wrote:
> > There is already a dynamic field for timestamp,
> > used only for Tx scheduling, thanks to the dedicated flag.
> > The same field can be used for Rx timestamp filled by drivers.
> > The onl
On Thu, Oct 29, 2020 at 3:23 AM Andrew Rybchenko
wrote:
>
> On 10/29/20 12:27 PM, Thomas Monjalon wrote:
> > As announced in the deprecation note, the field timestamp
> > is removed to allow giving more space to the dynamic fields.
> > The related offload flag PKT_RX_TIMESTAMP is also removed.
> >
> On Sun, Oct 25, 2020 at 6:46 AM Honnappa Nagarahalli
> wrote:
> >
> > It is pretty common for the DPDK applications to be deployed in
> > semi-pipeline model. In these models, a small number of cores
> > (typically 1) are designated as I/O cores. The I/O cores work on
> > receiving and transmi
Hello Ibtisam,
On Thu, Oct 29, 2020 at 1:55 PM Ibtisam Tariq wrote:
>
> Instead of using getopt_long return value, strcmp was used to
> compare the input parameters with the struct option array. This
> patch get rid of all those strcmp by directly binding each longopt
> with an int enum.
>
> Bugz
The RSS shared action was saved in flow memory by a pointer.
It means that every flow memory includes 8B only for optional shared
RSS case.
Move the RSS objects to be used by indexed pool which reduces the flow
handle memory to 4B.
So, now, the shared action handler is also just a 4B index.
Sign
Add support for rte_flow shared action API for age action.
First step here to support validate, create, query and destroy.
The support is only for age ASO mode.
Signed-off-by: Matan Azrad
---
drivers/net/mlx5/mlx5.h | 1 +
drivers/net/mlx5/mlx5_flow.c| 61 +++--
driv
From: Dekel Peled
A new ASO (Advanced Steering Operation) feature was added in the last
mlx5 adapters to support flow hit detection.
Using this new steering action, the driver can detect flow traffic hit
and to reset this indication any time.
Add support for flow aging action in rte_flow using
From: Dekel Peled
This patch adds different PRM definitions, related to ASO flow hit
feature, in MLX5 PMD code.
Signed-off-by: Dekel Peled
---
drivers/common/mlx5/linux/meson.build | 2 ++
drivers/common/mlx5/mlx5_prm.h| 66 ++-
2 files changed, 67 inse
From: Dekel Peled
Read and store the device capability of FLOW_HIT_ASO general object,
using the DevX API.
Signed-off-by: Dekel Peled
---
drivers/common/mlx5/mlx5_devx_cmds.c | 3 +++
drivers/common/mlx5/mlx5_devx_cmds.h | 1 +
drivers/common/mlx5/mlx5_prm.h | 2 ++
3 files changed, 6 in
From: Dekel Peled
PRM defines the general object types using positive numbers.
The same values are used as index for the relevant bit in HCA
capabilities general_obj_types bit mask.
Signed-off-by: Dekel Peled
---
drivers/common/mlx5/mlx5_prm.h | 9 ++---
1 file changed, 6 insertions(+), 3
From: Dekel Peled
Add DevX API to create ASO flow hit object.
Signed-off-by: Dekel Peled
---
drivers/common/mlx5/mlx5_devx_cmds.c | 45
drivers/common/mlx5/mlx5_devx_cmds.h | 4
drivers/common/mlx5/mlx5_prm.h | 14 +++
drivers/common/mlx
From: Dekel Peled
Add glue function to create the flow hit action using DV API,
if rdma-core support exists.
Signed-off-by: Dekel Peled
---
drivers/common/mlx5/linux/meson.build | 2 ++
drivers/common/mlx5/linux/mlx5_glue.c | 16
drivers/common/mlx5/linux/mlx5_glue.h | 3 +++
A new ASO (Advanced Steering Operation) feature was added in the last
mlx5 adapters to support flow hit detection.
Using this new steering action, the driver can detect flow traffic hit
and to reset this indication any time.
Add support for flow aging action in rte_flow using this new feature.
T
On Wed, Oct 28, 2020 at 10:03 PM David Marchand
wrote:
>
> Following recent increase of an internal array that was limiting CTF event
> descriptions, I had a second look at the code.
> All of this is slow path, so I see no reason in keeping this limitation
> and we can go with dynamic allocations.
29/10/2020 22:28, David Marchand:
> On Thu, Oct 29, 2020 at 9:11 PM Hariprasad Govindharajan
> wrote:
> >
> > The igb_uio source code requires interrupt modes defined as
> > MACROS and enums in the header file rte_pci_dev_features.h.
> > Now, the definitions are moved to the igb_uio.c file so that
I don't have a clear opinion on this patch.
Techboard members, ping for feedbacks.
If no objection, I will merge it soon, but I would prefer having more acks.
27/10/2020 20:55, Ananyev, Konstantin:
> From: yang_y...@163.com
> > From: Yi Yang
> >
> > rte_gso_segment decreased refcnt of pkt by o
On 10/23/2020 5:03 PM, Ferruh Yigit wrote:
On 10/22/2020 10:42 AM, Andrew Rybchenko wrote:
Removal is aggressive and tries to cleanup all dead code from drivers.
tep_termination example still uses TUNNEL filters. Functionality is
broken when TUNNEL filter is removed and finally even build of th
Ping for review please
20/10/2020 14:05, Thomas Monjalon:
> Anatoly, please could you review this patch?
>
> 15/10/2020 19:23, David Christensen:
> > The SPAPR IOMMU requires that a DMA window size be defined before memory
> > can be mapped for DMA. Current code dynamically modifies the DMA windo
On Thu, Oct 29, 2020 at 9:11 PM Hariprasad Govindharajan
wrote:
>
> The igb_uio source code requires interrupt modes defined as
> MACROS and enums in the header file rte_pci_dev_features.h.
> Now, the definitions are moved to the igb_uio.c file so that
> this module can be built without building D
On Tue, Oct 27, 2020 at 4:00 PM Liang Ma wrote:
>
> Currently, it is not possible to check support for intrinsics that
> are platform-specific, cannot be abstracted in a generic way, or do not
> have support on all architectures. The CPUID flags can be used to some
> extent, but they are only defi
29/10/2020 21:10, Hariprasad Govindharajan:
> With DPDK 20.11 release, the igb_uio module is no more part of DPDK.
> There are use cases where this module is required, for example while
> testing the virtual ports in OvS, the virtual ports are bound to
> igb_uio module inside a VM. So, this patch p
29/10/2020 21:10, Hariprasad Govindharajan:
> The igb_uio source code requires interrupt modes defined as
> MACROS and enums in the header file rte_pci_dev_features.h.
> Now, the definitions are moved to the igb_uio.c file so that
> this module can be built without building DPDK
>
> Signed-off-by:
29/10/2020 20:16, Hariprasad Govindharajan:
> With DPDK 20.11 release, the igb_uio module is no more part of DPDK.
> There are use cases where this module is required, for example while
> testing the virtual ports in OvS, the virtual ports are bound to
> igb_uio module inside a VM. So, this patch p
28/10/2020 19:15, luca.bocca...@gmail.com:
> From: Luca Boccassi
>
> Necessary to get build flags from DKMS.
>
> See:
>
> https://git.dpdk.org/dpdk/commit/?id=816d967717
[...]
> --- a/linux/igb_uio/Kbuild
> +++ b/linux/igb_uio/Kbuild
> @@ -1 +1,2 @@
> +ccflags-y := $(MODULE_CFLAGS)
> obj-m :=
> >
> >
> > > diff --git a/config/arm/meson.build b/config/arm/meson.build index
> > > 491842cad..6c31ab167 100644
> > > --- a/config/arm/meson.build
> > > +++ b/config/arm/meson.build
> > > @@ -3,12 +3,12 @@
> > > # Copyright(c) 2017 Cavium, Inc
> > > # Copyright(c) 2020 PANTHEON.tech s.r.o.
>
On 10/29/2020 8:10 PM, Hariprasad Govindharajan wrote:
With DPDK 20.11 release, the igb_uio module is no more part of DPDK.
There are use cases where this module is required, for example while
testing the virtual ports in OvS, the virtual ports are bound to
igb_uio module inside a VM. So, this pa
On 10/29/2020 8:10 PM, Hariprasad Govindharajan wrote:
The igb_uio source code requires interrupt modes defined as
MACROS and enums in the header file rte_pci_dev_features.h.
Now, the definitions are moved to the igb_uio.c file so that
this module can be built without building DPDK
Signed-off-by
With DPDK 20.11 release, the igb_uio module is no more part of DPDK.
There are use cases where this module is required, for example while
testing the virtual ports in OvS, the virtual ports are bound to
igb_uio module inside a VM. So, this patch provides a Makefile
which can be used to build this m
The igb_uio source code requires interrupt modes defined as
MACROS and enums in the header file rte_pci_dev_features.h.
Now, the definitions are moved to the igb_uio.c file so that
this module can be built without building DPDK
Signed-off-by: Hariprasad Govindharajan
---
linux/igb_uio/igb_uio.c
On 10/26/2020 7:14 AM, Matan Azrad wrote:
Hi Long
From: Long Li
If a device probe fails, the alarm is canceled and will no longer work for
previously probed devices.
Fix this by checking if alarm is necessary at the end of each device probe.
Reset the alarm if there are vdev_netvsc_ctx create
On 10/23/2020 10:54 PM, Long Li wrote:
From: Stephen Hemminger
The values for Rx and Tx copy break should be tunable rather
than hard coded constants.
The rx_copybreak sets the threshold where the driver uses an
external mbuf to avoid having to copy data. Setting 0 for copybreak
will cause dri
On 10/28/2020 2:29 AM, Jiawen Wu wrote:
Replace the 'rte_panic()' with an error return.
Also change the type of the calling function.
Signed-off-by: Jiawen Wu
Applied to dpdk-next-net/main, thanks.
On 10/29/2020 7:16 PM, Hariprasad Govindharajan wrote:
With DPDK 20.11 release, the igb_uio module is no more part of DPDK.
There are use cases where this module is required, for example while
testing the virtual ports in OvS, the virtual ports are bound to
igb_uio module inside a VM. So, this pa
With DPDK 20.11 release, the igb_uio module is no more part of DPDK.
There are use cases where this module is required, for example while
testing the virtual ports in OvS, the virtual ports are bound to
igb_uio module inside a VM. So, this patch provides a Makefile
which can be used to build this m
> Subject: [dpdk-dev] [PATCH 1/2] crypto/aesni_mb: support Chacha-Poly in
> symmetric API
>
> Add support for Chacha20-Poly1305 in the crypto symmetric API.
>
> Signed-off-by: Pablo de Lara
> ---
Subject and description updated for symmetric->synchronous
Series applied to dpdk-next-crypto
Tha
> -Original Message-
> From: Luca Boccassi
> Sent: Thursday, October 29, 2020 10:16 AM
> To: Govindharajan, Hariprasad ;
> dev@dpdk.org
> Cc: Yigit, Ferruh ; Burakov, Anatoly
>
> Subject: Re: [dpdk-dev] [DPDK_KMODS v4] linux/igb_uio: add Makefile to
> build the kernel module
>
> On Thu,
On Mon, Oct 26, 2020 at 11:44:58AM -0700, Pallavi Kadam wrote:
> Currently, since there is no runtime directory set, the code tries to
> create a file in C:\ which is only writable with administrator
> privileges. As a result, if the user is not admin, the application will
> fail.
> So, forcing no_
From: Venkata Suresh Kumar P
This patch increases the immediate operand size from 32 to 64 bits.
Signed-off-by: Venkata Suresh Kumar P
Acked-by: Cristian Dumitrescu
---
lib/librte_pipeline/rte_swx_pipeline.c | 103 +++--
lib/librte_pipeline/rte_swx_pipeline.h | 2
The recent Rx code refactoring moved the incrementing
of the CQ completion index out of the rxq_cq_decompress_v()
function to the rxq_burst_v() function.
The advancing of CQ completion index was removed in SSE
version only causing Neon and Altivec Rx bursts to stall.
Remove the incrementation of
27/10/2020 15:59, Liang Ma:
> Liang Ma (9):
> eal: add new x86 cpuid support for WAITPKG
> eal: add power management intrinsics
> eal: add intrinsics support check infrastructure
EAL patches applied, thanks.
> ethdev: add simple power management API
Waiting for doxygen reword which may h
Hi Anatoly
Thanks for the reply.
Do you have a sample code for primary and secondary processes which I can try
in my setup? And once reproduced, can let you know.
We have DPDK applications in our product with which I always see this issue.
Regards
Amiya
From: Burakov, Anatoly
Sent: 29 October
27/10/2020 15:59, Liang Ma:
> +static inline uint64_t
> +__get_umwait_val(const volatile void *p, const uint8_t sz)
> +{
> + switch (sz) {
> + case sizeof(uint8_t):
> + return *(const volatile uint8_t *)p;
> + case sizeof(uint16_t):
> + return *(const v
>
> On Thu, Oct 29, 2020 at 12:29 PM Ananyev, Konstantin
> wrote:
> > > On Sun, Oct 25, 2020 at 6:46 AM Honnappa Nagarahalli
> > > wrote:
> > > > +.. code-block:: c
> > > > +
> > > > +/* Reserve space on the ring */
> > > > +n = rte_ring_enqueue_zc_burst_start(r, 32, &zcd, NULL);
> > >
Hi Nipun,
Some nits. Looks good otherwise.
> On Oct 15, 2020, at 8:23 AM, nipun.gu...@nxp.com wrote:
>
> From: Nipun Gupta
>
> With DEV_RX_OFFLOAD_ERR_PKT_DROP now defined as an offload
> capability, and separate RTE_DEV_RX_ERR_PKT_DROP_OFFLOAD_ALL
> capability to drop all error packets in ha
On 29-Oct-20 3:51 PM, Burakov, Anatoly wrote:
On 28-Oct-20 7:00 AM, Mohakud, Amiya Ranjan wrote:
Hi Anatoly,
Are you back from vacation? Can you please let me know if there is any
proceedings on this or if there is anything pending from my side ?
https://bugs.dpdk.org/show_bug.cgi?id=561
Re
On Mon, Oct 26, 2020 at 10:58 PM Cristian Dumitrescu
wrote:
>
> Fix build with external makefile.
>
> Fixes: fbc74e66334f ("examples/ip_pipeline: remove infra code")
> Signed-off-by: Cristian Dumitrescu
Applied, thanks.
--
David Marchand
On Mon, Oct 26, 2020 at 8:59 PM Cristian Dumitrescu
wrote:
>
> Fix potential buffer overflows by string copy into fixed size buffer.
>
> Coverity issue: 362732, 362736, 362760, 362772, 362775, 362784,
> 362800, 362803, 362806, 362811, 362814, 362816,
> 362834, 36283
On Mon, Oct 26, 2020 at 10:24 PM Cristian Dumitrescu
wrote:
>
> Coverity issue: 363041
> Fixes: 5074e1d551 ("examples/pipeline: add configuration commands")
>
> Signed-off-by: Cristian Dumitrescu
Applied, thanks.
--
David Marchand
This patch fixes the AESNI-MB PMD CPU crypto process function. Originally
the function tried to access crypto vector's aad buffer even it is not
needed.
Fixes: 8d928d47a29a ("cryptodev: change crypto symmetric vector structure")
Cc: roy.fan.zh...@intel.com
Signed-off-by: Fan Zhang
---
V2:
- fix
https://bugs.dpdk.org/show_bug.cgi?id=567
Gregory Etelson (getel...@nvidia.com) changed:
What|Removed |Added
Status|UNCONFIRMED |RESOLVED
Resolutio
This patch fixes the AESNI-MB PMD CPU crypto process function. Orignally
the function tried to access crypto vector's aad buffer even it is not
needed.
Fixes: 8d928d47a29a ("cryptodev: change crypto symmetric vector structure")
Cc: roy.fan.zh...@intel.com
Signed-off-by: Fan Zhang
---
drivers/cr
29/10/2020 15:57, Timothy McDaniel:
> Adds the timeout ticks conversion function.
>
> Adds announcement of availabililty of the new driver
> for Intel Dynamic Load Balancer 1.0 hardware.
I don't see how these 2 changes are related?
Shouldn't you update the release notes in the first patch?
29/10/2020 15:20, Pattan, Reshma:
>
> > -Original Message-
> > From: Thomas Monjalon
>
>
>
>
> > rte_mbuf_dynflag_register(×tamp_dynflag_desc);
> > + if (timestamp_dynflag_offset < 0) {
> > + RTE_LOG(ERR, LATENCY_STATS,
> > + "Cannot register
29/10/2020 15:39, Ori Kam:
> Hi Andrew,
>
[...]
> > A new generic shared actions API may be used to create shared
> > counter. There is no point to keep duplicate COUNT action specific
> > capability to create shared counters.
> >
> > Signed-off-by: Andrew Rybchenko
> > ---
> > In fact, it looks
On Tue, Oct 27, 2020 at 1:52 PM wangyunjian wrote:
>
> From: Yunjian Wang
>
> Coverity flags that 'h' variable is used before
> it's checked for NULL. This patch fixes this issue.
>
> Coverity issue: 363625
> Fixes: 769b2de7fb52 ("hash: implement RCU resources reclamation")
No need to copy stabl
> -Original Message-
> From: Stephen Hemminger
> Sent: Thursday, October 29, 2020 10:31 AM
> To: McDaniel, Timothy
> Cc: dev@dpdk.org; Carrillo, Erik G ; Eads, Gage
> ; Van Haaren, Harry ;
> jer...@marvell.com; tho...@monjalon.net
> Subject: Re: [dpdk-dev] [PATCH v4 03/23] event/dlb2:
On Wed, Oct 28, 2020 at 10:19 PM Harman Kalra wrote:
> On Thu, Oct 15, 2020 at 04:42:30PM +0800, wangyunjian wrote:
> > This patch fixes (dereference after null check) coverity issue.
> > For this reason, we should add null check at the beginning of the
> > function and return error directly if th
> -Original Message-
> From: Stephen Hemminger
> Sent: Thursday, October 29, 2020 10:29 AM
> To: McDaniel, Timothy
> Cc: dev@dpdk.org; Carrillo, Erik G ; Eads, Gage
> ; Van Haaren, Harry ;
> jer...@marvell.com; tho...@monjalon.net
> Subject: Re: [dpdk-dev] [PATCH v4 03/23] event/dlb2:
29/10/2020 10:41, Bing Zhao:
> The file "rte_pmd_mlx5.h" is used to provide mlx5 PMD specific APIs
> and it needs to be included in the document generation.
>
> Signed-off-by: Bing Zhao
> --- a/doc/api/doxy-api.conf.in
> +++ b/doc/api/doxy-api.conf.in
> @@ -16,6 +16,7 @@ INPUT =
On 28-Oct-20 7:00 AM, Mohakud, Amiya Ranjan wrote:
Hi Anatoly,
Are you back from vacation? Can you please let me know if there is any
proceedings on this or if there is anything pending from my side ?
https://bugs.dpdk.org/show_bug.cgi?id=561
Regards
Amiya
Hi,
I've just checked with ker
Avoid code duplication by combining single and multi threaded tests
Signed-off-by: Dharmik Thakkar
Reviewed-by: Ruifeng Wang
---
app/test/test_lpm_perf.c | 338 +--
1 file changed, 73 insertions(+), 265 deletions(-)
diff --git a/app/test/test_lpm_perf.c b/app
Return error if Add/Delete fail in multiwriter perf test
Fixes: eff30b59cc2e ("test/lpm: add RCU performance tests")
Cc: honnappa.nagaraha...@arm.com
Cc: sta...@dpdk.org
Signed-off-by: Dharmik Thakkar
Reviewed-by: Ruifeng Wang
---
app/test/test_lpm_perf.c | 4
1 file changed, 4 insertions
Remove redundant error checking for reader threads
since they never return error.
Fixes: eff30b59cc2e ("test/lpm: add RCU performance tests")
Cc: honnappa.nagaraha...@arm.com
Cc: sta...@dpdk.org
Signed-off-by: Dharmik Thakkar
Reviewed-by: Ruifeng Wang
---
app/test/test_lpm_perf.c | 21
Fix incorrect calculations for LPM adds, LPM deletes,
and average cycles in RCU QSBR perf tests
Fixes: eff30b59cc2e ("test/lpm: add RCU performance tests")
Cc: honnappa.nagaraha...@arm.com
Cc: sta...@dpdk.org
Signed-off-by: Dharmik Thakkar
Reviewed-by: Ruifeng Wang
---
app/test/test_lpm_perf.c
On Thu, 29 Oct 2020 10:24:57 -0500
Timothy McDaniel wrote:
> +struct dlb2_port {
> + uint32_t id;
> + bool is_directed;
> + bool gen_bit;
> + uint16_t dir_credits;
> + uint32_t dequeue_depth;
> + union dlb2_port_config cfg;
> + uint32_t *credit_pool[DLB2_NUM_QUEUE_TYPE
On Sun, 25 Oct 2020 14:15:13 -0700
Stephen Hemminger wrote:
> This patch series changes the use of the terms blacklist and whitelist
> and instead uses block and allow. The change is most visible
> in the options passed to DPDK programs for marking which devices
> to use.
>
> The options are al
On Thu, 29 Oct 2020 10:24:57 -0500
Timothy McDaniel wrote:
> +
> + /* marker for array sizing etc. */
> + _DLB2_NB_ENQ_TYPES
Be careful with this type of array sizing value.
It becomes a breaking point for any API/ABI changes.
On 10/26/2020 11:41 AM, Raslan Darawsheh wrote:
This adds the ConnectX-7 and Bluefield-3 device ids to the list of
supported Mellanox devices that run the MLX5 PMDs.
The devices is still in development stage.
I assume you don't want to add these new device support to the documentation or
to t
Add a variety of self-tests for both ldb and directed
ports/queues, as well as configure, start, stop, link, etc...
Signed-off-by: Timothy McDaniel
Reviewed-by: Gage Eads
---
app/test/test_eventdev.c |7 +
drivers/event/dlb2/dlb2.c |1 +
drivers/event/dlb2/dlb2_selfte
DLB does not support reconfiguring individual queues
or ports on the fly. The entire device must be reconfigured.
Previously allocated port QE and memzone memory
is freed in this patch.
Signed-off-by: Timothy McDaniel
Reviewed-by: Gage Eads
---
drivers/event/dlb2/dlb2.c | 24 +++
The PMD uses a public interface to allow applications to
control the token pop mode. Supported token pop modes are
as follows, and they impact core scheduling affinity for
ldb ports.
AUTO_POP: Pop the CQ tokens immediately after dequeueing.
DELAYED_POP: Pop CQ tokens after (dequeue_depth - 1) even
Adds the timeout ticks conversion function.
Adds announcement of availabililty for the new driver
for Intel Dynamic Load Balancer 2.0 hardware.
Signed-off-by: Timothy McDaniel
Reviewed-by: Gage Eads
---
doc/guides/rel_notes/release_20_11.rst | 5 +
drivers/event/dlb2/dlb2.c |
Add support for dequeue, dequeue_burst, ...
DLB2 does not currently support interrupts, but instead use
umonitor/umwait if supported by the processor. This allows
the software to monitor and wait on writes to a cache-line.
DLB2 supports normal and sparse cq mode. In normal mode the
hardware will
Add support for eventdev stop and close entry points.
Signed-off-by: Timothy McDaniel
Reviewed-by: Gage Eads
---
drivers/event/dlb2/dlb2.c | 257 +++--
drivers/event/dlb2/dlb2_iface.c| 6 +
drivers/event/dlb2/dlb2_iface.h| 6 +
Add support for enqueue and its variants.
Signed-off-by: Timothy McDaniel
Reviewed-by: Gage Eads
---
doc/guides/eventdevs/dlb2.rst | 118 +
drivers/event/dlb2/dlb2.c | 578 ++
2 files changed, 696 insertions(+)
diff --git a/doc/guides/eventde
Add supports for the port unlink(s) eventdev entry points.
The unlink operation is an asynchronous operation executed by
a control thread, and the unlinks-in-progress function reads
a counter shared with the control thread.
Signed-off-by: Timothy McDaniel
Reviewed-by: Gage Eads
---
drivers/even
Add support for the eventdev start entry point.
We delay initializing some resources until
eventdev start, since the number of linked queues can be
used to determine if we are dealing with a ldb or dir resource.
If this is a device restart, then the previous configuration
will be reapplied.
Signed
Configure the load balanded (ldb) or directed (dir) port.
The consumer queue (CQ) and producer port (PP) are also
set up here.
Signed-off-by: Timothy McDaniel
---
doc/guides/eventdevs/dlb2.rst | 75 +++
drivers/event/dlb2/dlb2.c | 498
drivers/even
Add support for configuring the DLB2 hardware.
In particular, this patch configures the DLB2
hardware's scheduling domain, such that it is provisioned with
the requested number of ports and queues, provided sufficient
resources are available. Individual queues and ports are
configured later in port
1 - 100 of 288 matches
Mail list logo
