Count and display outer IP checksum errors in the checksum
forwarder.
Example forwarder stats output:
RX-packets: 158RX-dropped: 0 RX-total: 158
Bad-ipcsum: 48 Bad-l4csum: 48Bad-outer-l4csum: 6
Bad-outer-ipcsum: 40
TX-packets: 0
> >
> > >
> > > > >
> > > > > Hi Feifei,
> > > > >
> > > > > >
> > > > > > The variable "wrk_cmd" is a signal to control threads from
> > > > > > running and stopping. When worker lcores load "wrk_cmd ==
> > > WRK_CMD_RUN",
> > > > > > they
> > > > > start
> > > > > > running and when worker lcor
A new DPDK release candidate is ready for testing:
https://git.dpdk.org/dpdk/tag/?id=v21.02-rc2
There are 293 new patches in this snapshot,
more than expected for a light release cycle.
Release notes:
https://doc.dpdk.org/guides/rel_notes/release_21_02.html
Highlights of 21.02-rc
19/01/2021 14:03, Bruce Richardson:
> Since the examples are designed to be built by end-users using Make, we
> can detect and warn about broken pkg-config on the user's system as part
> of the build process.
>
> Signed-off-by: Bruce Richardson
Applied, thanks
29/01/2021 17:07, Burakov, Anatoly:
> On 29-Jan-21 3:40 PM, Thomas Monjalon wrote:
> > 29/01/2021 16:29, Anatoly Burakov:
> >> Previous fix used `rte_malloc_heap_socket_is_external()` to check if the
> >> heap was an external heap. However, that API is thread-safe, and when
> >> we're inside the al
FreeBSD rolled their own NUMA memory APIs on 12.0 (see
https://www.freebsd.org/cgi/man.cgi?query=cpuset_getdomain&sektion=2&apropos=0&manpath=FreeBSD+12.2-RELEASE+and+Ports).
These syscalls allow binding of a process/thread/jail memory allocation to a
specific NUMA domain.
I think the first ste
The ionic PMD only supports Tx queue version 1 or greater.
Version 1 introduced a new SGL format with support for more
fragments per descriptor.
Add release notes and an explanation to the docs.
Signed-off-by: Andrew Boyer
---
doc/guides/nics/ionic.rst | 4
doc/guides/rel_not
Using the RTE_DIM() macro makes the code clearer.
Signed-off-by: Andrew Boyer
---
drivers/net/ionic/ionic_dev.c| 10 --
drivers/net/ionic/ionic_ethdev.c | 3 +--
drivers/net/ionic/ionic_lif.c| 9 +++--
drivers/net/ionic/ionic_main.c | 32 +++-
Replace copies of size(arr)/size(arr[0]) with RTE_DIM().
Eventually all of these macro definitions should be removed.
Signed-off-by: Andrew Boyer
---
drivers/net/atlantic/atl_hw_regs.h| 2 +-
drivers/net/axgbe/axgbe_common.h | 2 +-
drivers/net/bnx2x/bnx2x.h
The size of the receive completion ring should be recalculated
when MTU is increased to a size that requires scattered receive
or when LRO is enabled. Move logic for this calculation from
the ring configuration path to the device start path.
- Made size calculation dependent only on scattered_rx
On Fri, Jan 29, 2021 at 12:57 PM Lance Richardson
wrote:
>
> The size of the receive completion ring should be recalculated
> when MTU is increased to a size that requires scattered receive
> or when LRO is enabled. Move logic for this calculation from
> the ring configuration path to the device s
The size of the receive completion ring should be recalculated
when MTU is increased to a size that requires scattered receive
or when LRO is enabled. Move logic for this calculation from
the ring configuration path to the device start path.
- Made size calculation dependent only on scattered_rx
David Marchand writes:
> On Thu, Jan 28, 2021 at 7:34 PM Bruce Richardson
> wrote:
>>
>> On Thu, Jan 28, 2021 at 11:41:44AM +, Bruce Richardson wrote:
>> > On Thu, Jan 28, 2021 at 12:12:44PM +0100, Thomas Monjalon wrote:
>> > > 27/01/2021 18:33, Bruce Richardson:
>> > > > For CI builds, turn
Bruce Richardson writes:
> For CI builds, turn on the checking of includes.
>
> Signed-off-by: Bruce Richardson
> ---
Acked-by: Aaron Conole
Hi
DPDK on IBM Power result
* DPDK: v21.02-rc1-58-g45eb6a1df
* Build with gcc 9.3.0-1: no issue found
* Basic PF on Mallanox: No new issues or regressions were seen.
* Performance: not tested yet.
System tested:
- IBM Power9 Model 8335-101 CPU: 2.3 (pvr 004e 1203)
Tested NICs:
- Mellanox Techn
There is no need for the direct inclusion of the generic/ header [1]
now that we don't use the rte_atomic API anymore.
1: https://git.dpdk.org/dpdk/commit/?id=3eb860b08eb7
Fixes: e41d27a68df6 ("mbuf: remove atomic reference counters")
Cc: sta...@dpdk.org
Signed-off-by: David Marchand
---
lib/l
Bruce Richardson writes:
> While having the ability to run a test based off the DPDK_TEST environment
> variable is useful, it's often easier to specify the test name as a
> commandline parameter to a test binary. This also allows the test runs to
> be saved as part of the shell cmdline history.
On Fri, Jan 29, 2021 at 5:48 PM Bruce Richardson
wrote:
>
> As a general principle, each header file should include any other
> headers it needs to provide data type definitions or macros. For
> example, any header using the uintX_t types in structures or function
> prototypes should include "stdi
On Thu, Jan 28, 2021 at 7:34 PM Bruce Richardson
wrote:
>
> On Thu, Jan 28, 2021 at 11:41:44AM +, Bruce Richardson wrote:
> > On Thu, Jan 28, 2021 at 12:12:44PM +0100, Thomas Monjalon wrote:
> > > 27/01/2021 18:33, Bruce Richardson:
> > > > For CI builds, turn on the checking of includes.
> >
If vhost device's IOMMU feature is disabled, iotlb mempool allocation
is unnecessary.
Reported-by: Peng He
Signed-off-by: Wan Junjie
Reviewed-by: Zhihong Wang
---
lib/librte_vhost/vhost.c | 6 --
lib/librte_vhost/vhost_user.c | 2 +-
2 files changed, 5 insertions(+), 3 deletions(-)
d
On 12/8/2020 5:04 PM, Kevin Traynor wrote:
On 08/12/2020 15:53, Ferruh Yigit wrote:
On 11/23/2020 10:19 PM, Stephen Hemminger wrote:
When doing rte_eth_dev_get_supported_ptypes on netvsc device
the values reported are incorrect if VF is not present.
If no VF is present the device uses rte_net_
For CI builds, turn on the checking of includes.
Signed-off-by: Bruce Richardson
---
.ci/linux-build.sh | 1 +
1 file changed, 1 insertion(+)
diff --git a/.ci/linux-build.sh b/.ci/linux-build.sh
index afa3689a09..fdbeb5a616 100755
--- a/.ci/linux-build.sh
+++ b/.ci/linux-build.sh
@@ -57,6 +57,7
On 1/16/2021 1:48 AM, Min Hu (Connor) wrote:
Hi, Ferruh,
this change origin from the opinions by Andrew Rybchenko
. snippets like this:
> +__rte_experimental
> +int rte_eth_fec_get(uint16_t port_id, uint32_t *mode);
> +
> +/**
> + * @warning
> + * @b EXPERIMENTAL: this API may change,
On Fri, Jan 29, 2021 at 05:27:11PM +0100, Thomas Monjalon wrote:
> 29/01/2021 17:05, Bruce Richardson:
> > On Fri, Jan 29, 2021 at 04:04:18PM +, Burakov, Anatoly wrote:
> > > On 29-Jan-21 3:55 PM, Bruce Richardson wrote:
> > > > On Fri, Jan 29, 2021 at 04:47:35PM +0100, Thomas Monjalon wrote:
>
On 1/21/2021 12:46 PM, Viacheslav Ovsiienko wrote:
There is the "set rxpkts" command in the testpmd interactive mode,
it configures the segment sizes to split the packet on receiving.
The mentioned segment sizes are provided on the Rx queue setup
as part of queue configuration. Hence, to take the
26/01/2021 20:35, Jerin Jacob Kollanukkaran:
> Ankur Dwivedi (1):
> test/event_crypto_adapter: set cipher operation in transform
>
> Feifei Wang (10):
> app/eventdev: adjust event count order for pipeline test
> app/eventdev: remove redundant enqueue in burst Tx
> doc: fix
The check-includes script allowed checking header files in a given
directory to ensure that each header compiled alone without requiring
any other header inclusions.
With header checking now being done by the chkincs app in the build
system this script can be removed.
Signed-off-by: Bruce Richard
To verify that all DPDK headers are ok for inclusion directly in a C file,
and are not missing any other pre-requisite headers, we can auto-generate
for each header an empty C file that includes that header. Compiling these
files will throw errors if any header has unmet dependencies.
To ensure on
For some libraries, there may be some header files which are not for direct
inclusion, but rather are to be included via other header files. To allow
later checking of these files for missing includes, we separate out the
indirect include files from the direct ones.
Signed-off-by: Bruce Richardson
The rte_eventdev_pmd*.h files are for drivers only and should be private
to DPDK, and not installed for app use.
Signed-off-by: Bruce Richardson
---
doc/guides/rel_notes/release_21_02.rst | 6 ++
drivers/event/dlb/dlb.c | 2 +-
drivers
The rte_ethdev_driver.h, rte_ethdev_vdev.h and rte_ethdev_pci.h files are
for drivers only and should be a private to DPDK and not installed.
Signed-off-by: Bruce Richardson
Reviewed-by: Maxime Coquelin
Acked-by: Thomas Monjalon
Acked-By: Steven Webster
---
This patch has some minor conflicts
The rte_rib6 header was using RTE_MIN macro from rte_common.h but not
including the header file.
Fixes: f7e861e21c46 ("rib: support IPv6")
Cc: sta...@dpdk.org
Signed-off-by: Bruce Richardson
Acked-by: Vladimir Medvedkin
---
lib/librte_rib/rte_rib6.h | 1 +
1 file changed, 1 insertion(+)
diff
The rte_power_guest_channel.h file did not include it's dependent
headers, so add them.
Fixes: 5f443cc0f905 ("power: create guest channel public header file")
Signed-off-by: Bruce Richardson
---
This is one of those issues where it's hard to identify exactly where
the issue started, so picking
Clang does not have an "error" attribute for functions, so for marking
internal functions we need to check for the error attribute, and provide
a fallback if it is not present. For clang, we can use "diagnose_if"
attribute, similarly checking for its presence before use.
Fixes: fba5af82adc8 ("eal:
Include 'rte_branch_prediction.h' to get the likely/unlikely macro
definitions.
Fixes: 2173fb61 ("mcslock: add MCS queued lock implementation")
Cc: sta...@dpdk.org
Signed-off-by: Bruce Richardson
Reviewed-by: Honnappa Nagarahalli
---
lib/librte_eal/include/generic/rte_mcslock.h | 1 +
1 fi
As a general principle, each header file should include any other
headers it needs to provide data type definitions or macros. For
example, any header using the uintX_t types in structures or function
prototypes should include "stdint.h" to provide those type definitions.
In practice, while many,
29/01/2021 17:05, Bruce Richardson:
> On Fri, Jan 29, 2021 at 04:04:18PM +, Burakov, Anatoly wrote:
> > On 29-Jan-21 3:55 PM, Bruce Richardson wrote:
> > > On Fri, Jan 29, 2021 at 04:47:35PM +0100, Thomas Monjalon wrote:
> > > > 19/01/2021 14:03, Bruce Richardson:
> > > > > Since the examples a
On 29-Jan-21 3:40 PM, Thomas Monjalon wrote:
29/01/2021 16:29, Anatoly Burakov:
Previous fix used `rte_malloc_heap_socket_is_external()` to check if the
heap was an external heap. However, that API is thread-safe, and when
we're inside the allocation process, we're already write-locked, so
calli
On Fri, Jan 29, 2021 at 04:04:18PM +, Burakov, Anatoly wrote:
> On 29-Jan-21 3:55 PM, Bruce Richardson wrote:
> > On Fri, Jan 29, 2021 at 04:47:35PM +0100, Thomas Monjalon wrote:
> > > 19/01/2021 14:03, Bruce Richardson:
> > > > Since the examples are designed to be built by end-users using Mak
On 29-Jan-21 3:55 PM, Bruce Richardson wrote:
On Fri, Jan 29, 2021 at 04:47:35PM +0100, Thomas Monjalon wrote:
19/01/2021 14:03, Bruce Richardson:
Since the examples are designed to be built by end-users using Make, we
can detect and warn about broken pkg-config on the user's system as part
of
On Fri, Jan 29, 2021 at 04:47:35PM +0100, Thomas Monjalon wrote:
> 19/01/2021 14:03, Bruce Richardson:
> > Since the examples are designed to be built by end-users using Make, we
> > can detect and warn about broken pkg-config on the user's system as part
> > of the build process.
> >
> > Signed-o
19/01/2021 14:03, Bruce Richardson:
> Since the examples are designed to be built by end-users using Make, we
> can detect and warn about broken pkg-config on the user's system as part
> of the build process.
>
> Signed-off-by: Bruce Richardson
> ---
> examples/bbdev_app/Makefile
29/01/2021 16:29, Anatoly Burakov:
> Previous fix used `rte_malloc_heap_socket_is_external()` to check if the
> heap was an external heap. However, that API is thread-safe, and when
> we're inside the allocation process, we're already write-locked, so
> calling `rte_malloc_heap_socket_is_external()
On Fri, Jan 29, 2021 at 03:17:02PM +, Juraj Linkeš wrote:
>
>
> > -Original Message-
> > From: Bruce Richardson
> > Sent: Friday, January 29, 2021 4:01 PM
> > To: Juraj Linkeš
> > Cc: tho...@monjalon.net; ruifeng.w...@arm.com; jerinjac...@gmail.com;
> > hemant.agra...@nxp.com; ferru
Previous fix used `rte_malloc_heap_socket_is_external()` to check if the
heap was an external heap. However, that API is thread-safe, and when
we're inside the allocation process, we're already write-locked, so
calling `rte_malloc_heap_socket_is_external()` will result in a
deadlock followed by a t
> -Original Message-
> From: Bruce Richardson
> Sent: Friday, January 29, 2021 4:01 PM
> To: Juraj Linkeš
> Cc: tho...@monjalon.net; ruifeng.w...@arm.com; jerinjac...@gmail.com;
> hemant.agra...@nxp.com; ferruh.yi...@intel.com; abo...@pensando.io;
> dev@dpdk.org
> Subject: Re: [RFC PATC
On 1/29/2021 12:33 PM, Michał Krawczyk wrote:
pt., 29 sty 2021 o 13:17 Ferruh Yigit napisał(a):
On 1/26/2021 6:32 PM, Michal Krawczyk wrote:
Hi,
this patchset contains few bug fixes for the ENA PMD and the version
upgrade to v2.2.1. Besides that, the validation of the Rx req ID was
optimized
28/01/2021 20:12, Cristian Dumitrescu:
> Cannot dereference pointer for token[1] unless valid.
>
> Fixes: 5074e1d551 ("examples/pipeline: add configuration commands")
> Cc: sta...@dpdk.org
>
> Signed-off-by: Cristian Dumitrescu
Applied, thanks
On Fri, Jan 29, 2021 at 02:47:57PM +, Juraj Linkeš wrote:
>
>
> > -Original Message-
> > From: Bruce Richardson
> > Sent: Friday, January 29, 2021 3:42 PM
> > To: Juraj Linkeš
> > Cc: tho...@monjalon.net; ruifeng.w...@arm.com; jerinjac...@gmail.com;
> > hemant.agra...@nxp.com; ferru
22/01/2021 00:15, Thomas Monjalon:
> Some parameters of typedef'ed function pointers were not properly listed
> in the doxygen comments.
> The error is seen with doxygen 1.9 which added this specific check:
> https://github.com/doxygen/doxygen/commit/d34236ba4037
>
> Cc: sta...@dpdk.org
>
>
> -Original Message-
> From: Bruce Richardson
> Sent: Friday, January 29, 2021 3:42 PM
> To: Juraj Linkeš
> Cc: tho...@monjalon.net; ruifeng.w...@arm.com; jerinjac...@gmail.com;
> hemant.agra...@nxp.com; ferruh.yi...@intel.com; abo...@pensando.io;
> dev@dpdk.org
> Subject: Re: [RFC PATC
https://bugs.dpdk.org/show_bug.cgi?id=629
Bug ID: 629
Summary: ixgbe: 82599 chksum rx offload marks UDP packets over
IPv4 with zero checksum as CKSUM_BAD
Product: DPDK
Version: 20.11
Hardware: All
OS: All
On 29-Jan-21 2:20 PM, Thomas Monjalon wrote:
22/01/2021 18:12, Anatoly Burakov:
Things of note:
- Only 1:1 core to queue mapping is supported, meaning that each lcore
must at most handle RX on a single queue
Is there a way to have a more generic solution?
I think it may deserve some commen
On Fri, Jan 29, 2021 at 02:36:58PM +, Juraj Linkeš wrote:
>
>
> > -Original Message-
> > From: Bruce Richardson
> > Sent: Friday, January 29, 2021 2:51 PM
> > To: Juraj Linkeš
> > Cc: tho...@monjalon.net; ruifeng.w...@arm.com; jerinjac...@gmail.com;
> > hemant.agra...@nxp.com; ferru
> -Original Message-
> From: Bruce Richardson
> Sent: Friday, January 29, 2021 2:51 PM
> To: Juraj Linkeš
> Cc: tho...@monjalon.net; ruifeng.w...@arm.com; jerinjac...@gmail.com;
> hemant.agra...@nxp.com; ferruh.yi...@intel.com; abo...@pensando.io;
> dev@dpdk.org
> Subject: Re: [RFC PATC
22/01/2021 18:12, Anatoly Burakov:
> Things of note:
>
> - Only 1:1 core to queue mapping is supported, meaning that each lcore
> must at most handle RX on a single queue
Is there a way to have a more generic solution?
I think it may deserve some comments in the API.
> - Support 3 type polici
"Wang, Haiyue" writes:
> Hi Paolo,
>
>> -Original Message-
>> From: Wang, Haiyue
>> Sent: Friday, January 29, 2021 10:02
>> To: Paolo Valerio
>> Cc: Guo, Jia ; Aaron Conole ;
>> dev@dpdk.org
>> Subject: RE: ixgbe and UDP with zero checksum
>>
>> > -Original Message-
>> > From:
22/01/2021 18:12, Anatoly Burakov:
> From: Liang Ma
>
> Add PMD power management feature support to l3fwd-power sample app.
>
> Signed-off-by: Liang Ma
> Signed-off-by: Anatoly Burakov
> Acked-by: David Hunt
> ---
[...]
> +PMD Power Management Mode
> +-
There should b
On 1/29/2021 12:44 PM, Nalla Pradeep wrote:
v2:
Fixed review comments from sburla at marvell
v3:
Fixed review comments from jerinj at marvell
v4:
Fixed MAITAINERS file
v5:
Fixed review comments from Ferruh yigit at intel
v6:
Created separate patch for octeontx_ep raw driver changes
On 1/29/2021 12:45 PM, Nalla Pradeep wrote:
Transmit queue setup involves allocating memory for the command queue
considering tx descriptor count and initializing data structure
representing the queue. Transmit queue release function frees the
command queue.
Signed-off-by: Nalla Pradeep
<...>
On 1/29/2021 12:45 PM, Nalla Pradeep wrote:
Receive queue setup involves allocating memory for the queue,
initializing data structure representing the queue and filling queue
with receive buffers of rx descriptor count. Receive queues are referred
as droq. Hardware fills the receive buffers in qu
On Fri, Jan 29, 2021 at 12:33:06PM +, Juraj Linkeš wrote:
>
>
> > -Original Message-
> > From: Bruce Richardson
> > Sent: Friday, January 29, 2021 12:44 PM
> > To: Juraj Linkeš
> > Cc: tho...@monjalon.net; ruifeng.w...@arm.com; jerinjac...@gmail.com;
> > hemant.agra...@nxp.com; ferr
Hello dpdk devs,
I would like to discuss the feasibility of implementing CPU topology detection
on FreeBSD. Currently both eal_cpu_core_id() and eal_cpu_socket_id() in rte_eal
library always return 0 on FreeBSD, making NUMA-aware development impossible
without resorting to external libraries or
On Fri, Jan 29, 2021 at 12:52:50PM +, Burakov, Anatoly wrote:
> On 29-Jan-21 10:05 AM, Bruce Richardson wrote:
> > On Thu, Jan 28, 2021 at 04:07:07AM +, Oscar Zhao wrote:
> > > Hello dpdk devs,
> > >
> > > I would like to discuss the feasibility of implementing CPU topology
> > > detectio
On 29-Jan-21 10:05 AM, Bruce Richardson wrote:
On Thu, Jan 28, 2021 at 04:07:07AM +, Oscar Zhao wrote:
Hello dpdk devs,
I would like to discuss the feasibility of implementing CPU topology detection
on FreeBSD. Currently both eal_cpu_core_id() and eal_cpu_socket_id() in rte_eal
library al
Hi Bruce ,
Thanks a lot for your help.
After installing below packages mlx is compiled .
yum -y groupinstall "Infiniband Support"
yum install -y gcc kernel-devel-`uname -r` numactl-devel.x86_64
librdmacm-devel libmnl-devel
*find . -name *.a | grep mlx*
*./drivers/libtmp_rte_common_mlx5.a*
*./
1. Packet transmit function for both otx and otx2 are added.
2. Flushing transmit(command) queue when pending commands are more than
maximum allowed value (currently 16).
3. Scatter gather support if the packet spans multiple buffers.
Signed-off-by: Nalla Pradeep
---
drivers/net/octeontx_ep/o
Function to deliver packets from DROQ to application is added. It also
fills DROQ with receive buffers timely such that device can fill them
with incoming packets.
Signed-off-by: Nalla Pradeep
---
drivers/net/octeontx_ep/otx_ep_common.h | 1 +
drivers/net/octeontx_ep/otx_ep_ethdev.c | 3 +
d
Dev start and stop operations are added. To accomplish this internal
functions to enable or disable io queues are incorporated.
Signed-off-by: Nalla Pradeep
---
drivers/net/octeontx_ep/otx2_ep_vf.c| 107
drivers/net/octeontx_ep/otx_ep_common.h | 8 ++
drivers/net/octeo
Configuring hardware registers with command queue(iq) and driver output
queue(oq) parameters.
List of parameters configured for IQ after making sure it is idle
1. Base address
2. Instruction size
3. Disabling interrupts for fastpath
List of parameters configured for OQ after making sure it is idle
Receive queue setup involves allocating memory for the queue,
initializing data structure representing the queue and filling queue
with receive buffers of rx descriptor count. Receive queues are referred
as droq. Hardware fills the receive buffers in queue with the packet.
In receive queue release
Adding bare minimum PMD library and doc build infrastructure
and claim the maintainership for octeontx end point PMD.
Signed-off-by: Nalla Pradeep
---
MAINTAINERS | 9
doc/guides/nics/features/octeontx_ep.ini | 10 +
doc/guides/nics/index.rst
Transmit queue setup involves allocating memory for the command queue
considering tx descriptor count and initializing data structure
representing the queue. Transmit queue release function frees the
command queue.
Signed-off-by: Nalla Pradeep
---
drivers/net/octeontx_ep/otx_ep_common.h | 88 ++
Add basic init and uninit function which includes
initializing fields of ethdev private structure.
Signed-off-by: Nalla Pradeep
---
drivers/net/octeontx_ep/otx_ep_common.h | 22 +++-
drivers/net/octeontx_ep/otx_ep_ethdev.c | 72 +++--
2 files changed, 88 insertions(+), 6
Add device information get and device configure operations.
Signed-off-by: Nalla Pradeep
---
doc/guides/nics/features/octeontx_ep.ini | 1 +
drivers/net/octeontx_ep/otx_ep_common.h | 14
drivers/net/octeontx_ep/otx_ep_ethdev.c | 81 +++-
drivers/net/octeontx_ep/otx_ep
Functions to setup device, basic input queue and output queue registers
are added.
Signed-off-by: Nalla Pradeep
---
drivers/net/octeontx_ep/meson.build | 2 +
drivers/net/octeontx_ep/otx2_ep_vf.c| 131 +
drivers/net/octeontx_ep/otx2_ep_vf.h| 11 ++
drivers/net/
add basic PCIe ethdev probe and remove.
Signed-off-by: Nalla Pradeep
---
drivers/common/octeontx2/otx2_common.h | 2 +
drivers/net/octeontx_ep/meson.build | 2 +
drivers/net/octeontx_ep/otx_ep_common.h | 14 ++
drivers/net/octeontx_ep/otx_ep_ethdev.c | 57 +
dr
Device id to be probed by octeontx_ep raw device pmd is changed from
B203 to B204. B203 is for octeontx_ep net device pmd to probe.
Signed-off-by: Nalla Pradeep
---
drivers/common/octeontx2/otx2_common.h| 3 ++-
drivers/raw/octeontx2_ep/otx2_ep_rawdev.c | 6 +++---
2 files changed, 5 inserti
v2:
Fixed review comments from sburla at marvell
v3:
Fixed review comments from jerinj at marvell
v4:
Fixed MAITAINERS file
v5:
Fixed review comments from Ferruh yigit at intel
v6:
Created separate patch for octeontx_ep raw driver changes.
Used pmd specific log types instead of 'RTE_LOG
Thank you guys!
W dniu 29.01.2021 o 09:03, David Marchand pisze:
> On Thu, Jan 28, 2021 at 3:10 PM David Marchand
> wrote:
>> On Tue, Jan 19, 2021 at 4:59 AM Lukasz Wojciechowski
>> wrote:
>>> The distributor library implementation uses a cyclic queue to store
>>> packets returned from workers.
pt., 29 sty 2021 o 13:17 Ferruh Yigit napisał(a):
>
> On 1/26/2021 6:32 PM, Michal Krawczyk wrote:
> > Hi,
> >
> > this patchset contains few bug fixes for the ENA PMD and the version
> > upgrade to v2.2.1. Besides that, the validation of the Rx req ID was
> > optimized.
> >
> > Best regards,
> >
> -Original Message-
> From: Bruce Richardson
> Sent: Friday, January 29, 2021 12:44 PM
> To: Juraj Linkeš
> Cc: tho...@monjalon.net; ruifeng.w...@arm.com; jerinjac...@gmail.com;
> hemant.agra...@nxp.com; ferruh.yi...@intel.com; abo...@pensando.io;
> dev@dpdk.org
> Subject: Re: [RFC PAT
On 1/26/2021 6:32 PM, Michal Krawczyk wrote:
Hi,
this patchset contains few bug fixes for the ENA PMD and the version
upgrade to v2.2.1. Besides that, the validation of the Rx req ID was
optimized.
Best regards,
Michal
---
v2:
* Add patch preventing double doorbell on Tx.
Amit Bernstein (1
pt., 29 sty 2021 o 13:07 Ferruh Yigit napisał(a):
>
> On 1/26/2021 6:32 PM, Michal Krawczyk wrote:
> > From: Igor Chauskin
> >
> > Before starting transmission of Tx burst, the driver checked the
> > available space in the sq and limited the number of packets for
> > transmission accordingly.
> >
On 1/26/2021 6:32 PM, Michal Krawczyk wrote:
From: Igor Chauskin
Add per-tx-ring flag for packets that were pushed to HW but await
doorbell. That is to prevent a situation when a doorbell is sent due to
reaching Tx burst threshold and next send fails (e.g., due to queue
full). In such case we s
On 1/26/2021 6:32 PM, Michal Krawczyk wrote:
From: Igor Chauskin
Before starting transmission of Tx burst, the driver checked the
available space in the sq and limited the number of packets for
transmission accordingly.
The calculation was incorrect for fragmented packets and potentially had
si
On 1/29/2021 9:22 AM, Lijun Ou wrote:
Here series add some updates for hns3 rst and TM feature
note for hns3 as well as FEC feature notes.
v3:
1. merge patch[2/3] into patch[1] base on v2
2. fix some format errors
v2:
1. fix a meson build warning for patch[4/5]
2. add a new patch for update hns
On Fri, Jan 29, 2021 at 11:29:19AM +0100, Juraj Linkeš wrote:
> The kni linux module is using a custom target for building, which
> doesn't take into account any cross compilation arguments. The arguments
> in question are ARCH and CROSS_COMPILE. Get those from the cross file
> and pass them to the
On 1/25/2021 3:25 PM, Heinrich Kuhn wrote:
For newer smartNIC NVRAM versions the chip model should be read from the
PluDevice register as it provides the authoritative chip model/revision.
This method of reading the chip model is backwards compatible with
legacy NVRAM versions too.
Since the mod
22/01/2021 18:12, Anatoly Burakov:
> Currently, the API documentation is ambiguous as to what happens when
> certain conditions are met. Document the behavior explicitly, as well as
> fix some typos and outdated comments.
>
> Fixes: 6a17919b0e2a ("eal: change power intrinsics API")
>
> Signed-off
22/01/2021 18:12, Anatoly Burakov:
> The `data_sz` name is fine, but it looks out of place because nothing
> else has "data" prefix in that structure. Rename it to "size", as well
> as add more clarity to the comments around each struct member.
>
> Fixes: 6a17919b0e2a ("eal: change power intrinsic
On 1/26/2021 8:24 AM, Li, Xiaoyun wrote:
<...>
From: Dapeng Yu
In interactive mode, if testpmd exit by calling rte_exit without
restore terminal attributes, terminal will not echo keyboard input.
register a function with atexit() in prompt(), when exit() in
rte_exit() is called, the registe
> > Signed-off-by: Igor Russkikh
>
> Reviewed-by: Ferruh Yigit
>
> Also a testpmd command to set the 'flowgen-clones' can be useful, for
> interactive mode. If you have time for it, can you please work on it too?
>
>
> Applied to dpdk-next-net/main, thanks.
Thanks, Ferruh.
Good idea, will
On Fri, Jan 29, 2021 at 6:59 AM Feifei Wang wrote:
>
> Do some work for ring refactoring, which includes:
> 1. add rte prefix before update tail API
> 2. Move all private APIs into new header files
>
> v2:
> 1. add rte_ prefixes for private files (Konstantin)
>
> v3:
> 1. fix compile issue of file
On 1/21/2021 6:05 PM, Igor Russkikh wrote:
When testing high performance numbers, it is often that CPU performance
limits the max values device can reach (both in pps and in gbps)
Here instead of recreating each packet separately, we use clones counter
to resend the same mbuf to the line multipl
29/01/2021 11:21, David Hunt:
> The guest channel message definitions and functions in guest_channel.h
> are needed by applications and need to be made public.
>
> This worked pre-20.11, but now with all the meson/ninja changes, making
> these apps externally no longer works. To fix, we need to mo
The kni linux module is using a custom target for building, which
doesn't take into account any cross compilation arguments. The arguments
in question are ARCH and CROSS_COMPILE. Get those from the cross file
and pass them to the custom target.
The user supplied path may not contain the 'build' di
21/01/2021 18:21, David Hunt:
> The guest channel message definitions and functions in guest_channel.h
> are needed by applications and need to be made public.
>
> This worked pre-20.11, but now with all the meson/ninja changes, making
> these apps externally no longer works. To fix, we need to mo
From: Bruce Richardson
re-organise the including of the new public header file and
remove un-needed includes
Fixes: 210c383e247b ("power: packet format for vm power management")
Fixes: cd0d5547e873 ("power: vm communication channels in guest")
Cc: sta...@dpdk.org
Signed-off-by: Bruce Richardson
From: Bruce Richardson
Adjust meson.build so that 'ninja install' copies the new header
file into the installation directory.
Fixes: 210c383e247b ("power: packet format for vm power management")
Fixes: cd0d5547e873 ("power: vm communication channels in guest")
Cc: sta...@dpdk.org
Signed-off-by:
1 - 100 of 129 matches
Mail list logo
