04/06/2022 18:26, Tomasz Duszynski:
> Jakub Palider (1):
> raw/cnxk_bphy: add doxygen comments
>
> Tomasz Duszynski (9):
> common/cnxk: update register access for CNF10xxN
> common/cnxk: use wider mask to extract RPM ID
> common/cnxk: don't switch affinity back and forth
> raw/cnxk_bphy:
On 6/22/22 08:27, Yuan Wang wrote:
drain_eth_rx() uses rte_vhost_avail_entries() to calculate
the available entries to determine if a retry is required.
However, this function only works with split rings, and
calculating packed rings will return the wrong value and cause
unnecessary retries re
Hi folks,
> -Original Message-
> From: Morten Brørup
> Sent: Saturday 18 June 2022 10:59
> To: fengchengwen ; Stephen Hemminger
> ; Richardson, Bruce
>
> Cc: tho...@monjalon.net; ferruh.yi...@xilinx.com; Laatz, Kevin
> ; andrew.rybche...@oktetlabs.ru;
> jer...@marvell.com; sachin.sax...@
Hi
I put here again the comment the putted on another version of this commit.
I saw it is already integrated but still not in master.
But please look.
From: Maxime Coquelin
> Hi newsky647,
>
> On 6/12/22 16:09, 835703...@qq.com wrote:
> > From: newsky647 <835703...@qq.com>
> >
> > After functi
Hi Matan,
On 6/22/22 10:03, Matan Azrad wrote:
Hi
I put here again the comment the putted on another version of this commit.
I saw it is already integrated but still not in master.
But please look.
Thanks for the heads-up, I missed your initial comment.
From: Maxime Coquelin
Hi newsky647
In the virtio blk vDPA live migration use case, before the live
migration process, QEMU will set call fd to vDPA back-end. QEMU
and vDPA back-end stand by until live migration starts.
During live migration process, QEMU sets kick fd and a new call
fd. However, after the kick fd is set to the vDPA b
22/06/2022 10:11, Maxime Coquelin:
> >>> --- a/drivers/vdpa/mlx5/mlx5_vdpa_event.c
> >>> +++ b/drivers/vdpa/mlx5/mlx5_vdpa_event.c
> >>> @@ -395,6 +395,7 @@ mlx5_vdpa_err_event_setup(struct mlx5_vdpa_priv
> >> *priv)
> >>>rte_intr_instance_alloc(RTE_INTR_INSTANCE_F_SHARED);
> >>>
On 6/22/22 10:46, Thomas Monjalon wrote:
22/06/2022 10:11, Maxime Coquelin:
--- a/drivers/vdpa/mlx5/mlx5_vdpa_event.c
+++ b/drivers/vdpa/mlx5/mlx5_vdpa_event.c
@@ -395,6 +395,7 @@ mlx5_vdpa_err_event_setup(struct mlx5_vdpa_priv
*priv)
rte_intr_instance_alloc(RTE_INTR_INSTANC
Hi Maxime,
> -Original Message-
> From: Maxime Coquelin
> Sent: Wednesday, June 22, 2022 3:24 PM
> To: Wang, YuanX ; Xia, Chenbo
> ; dev@dpdk.org
> Cc: Hu, Jiayu ; He, Xingguang
> ; sta...@dpdk.org; Ling, WeiX
>
> Subject: Re: [PATCH v3] examples/vhost: fix retry logic on eth rx path
>
Hey everyone,
When running a Virtio performance test on a VM using VHost with this patch
applied,
VHost gives the following error message:
> VHOST_CONFIG: (/tmp/vhost) read message VHOST_USER_SET_FEATURES
> VHOST_CONFIG: (/tmp/vhost) negotiated Virtio features: 0x0
> VHOST_CONFIG: (/tmp/vhost)
On Wed, Jun 22, 2022 at 06:26:07AM +, Emil Berg wrote:
>
>
> > -Original Message-
> > From: Morten Brørup
> > Sent: den 21 juni 2022 11:35
> > To: Emil Berg
> > Cc: Bruce Richardson ; Stephen Hemminger
> > ; sta...@dpdk.org; bugzi...@dpdk.org;
> > hof...@lysator.liu.se; olivier.m...
On Wed, Jun 22, 2022 at 08:57:43AM +0100, Power, Ciara wrote:
> Hi folks,
>
> > -Original Message-
> > From: Morten Brørup
> > Sent: Saturday 18 June 2022 10:59
> > To: fengchengwen ; Stephen Hemminger
> > ; Richardson, Bruce
> >
> > Cc: tho...@monjalon.net; ferruh.yi...@xilinx.com; Laat
26/05/2022 22:26, Stephen Hemminger:
> Stephen Hemminger (3):
> random: add rte_drand() function
> rte_pie: remove unnecessary floating point
> rte_pie: fix incorrect floating point math
Series applied, thanks.
28/02/2022 18:08, Stephen Hemminger:
> On Mon, 28 Feb 2022 09:42:47 +
> Bruce Richardson wrote:
>
> > On Sun, Feb 27, 2022 at 09:48:57PM +0100, Thomas Monjalon wrote:
> > > 20/02/2022 19:21, Stephen Hemminger:
> > > > + * If NULL then, the function does nothing.
> > >
> > > I'm not Eng
Hi Maxime,
I know it is over Tuesday so we understand you merged the patch already.
But any suggestions? Should we raise a Bugzilla for this problem?
BTW we reverted the patch and the test finished no problem.
Regards,
Fan
> -Original Message-
> From: Poczatek, Jakub
> Sent: Wednesday, J
drain_eth_rx() uses rte_vhost_avail_entries() to calculate
the available entries to determine if a retry is required.
However, this function only works with split rings, and
calculating packed rings will return the wrong value and cause
unnecessary retries resulting in a significant performance pen
For the inline crypto path set the Tx checksum offload flag
only if the device supports it.
Fixes: d24471e5786b ("examples/ipsec-secgw: disable Tx checksum for inline")
Cc: ndabilpu...@marvell.com
Signed-off-by: Radu Nicolau
---
examples/ipsec-secgw/sa.c | 5 -
1 file changed, 4 insertions(
21/06/2022 16:28, Morten Brørup:
> > From: David Marchand [mailto:david.march...@redhat.com]
> > Sent: Tuesday, 21 June 2022 16.13
> >
> > ALIGNMENT_MASK is only used internally.
> > Besides it lacks a DPDK-related prefix.
> > Hide it from external eyes.
> >
> > Reported-by: Morten Brørup
> > Si
> -Original Message-
> From: Radu Nicolau
> Sent: Wednesday, June 22, 2022 10:28 AM
> To: Nicolau, Radu ; Akhil Goyal
> Cc: dev@dpdk.org; ndabilpu...@marvell.com
> Subject: [PATCH] examples/ipsec-secgw: fix Tx checksum offload flag
>
> For the inline crypto path set the Tx checksum offlo
On 6/22/2022 4:09 AM, Dongdong Liu wrote:
From: Chengwen Feng
The 802.11 physical PMA sub-layer defines three media: copper, fiber and
backplane. For PMD, the backplane is similar to the fiber, the main
differences are that backplane doesn't have optical module.
Because the interface of firmwa
This commit removes any references to the old QAT
driver location 01.org in the documentation and
replaces them with the updated location intel.com.
This commit also adds a note to the docs to alert
users of a possible error when building the new QAT
driver and provides the patch needed to resolve
Added rte_event_eth_rx_adapter_instance_get() to get
adapter instance id for specified ethernet device id and
rx queue index.
Signed-off-by: Ganapati Kundapura
---
v7:
* Remove allocation of instance array and storage of instnace id
* in instance array
* Use Rx adapter instance data to query inst
Added telemetry handler for rte_event_eth_rx_adapter_instance_get()
to retrieve adapter instance id for specified ethernet device id
and rx queue index.
Signed-off-by: Ganapati Kundapura
---
lib/eventdev/rte_event_eth_rx_adapter.c | 66 +
1 file changed, 66 insert
Added rte_event_eth_tx_adapter_instance_get() to get the
adapter instance id for specified ethernet device id and
tx queue index.
Signed-off-by: Ganapati Kundapura
---
lib/eventdev/eventdev_pmd.h | 23 +++
lib/eventdev/rte_event_eth_tx_adapter.c | 102 +++
Added test case for rte_event_eth_rx_adapter_instance_get()
Signed-off-by: Ganapati Kundapura
---
app/test/test_event_eth_rx_adapter.c | 203 ++-
1 file changed, 202 insertions(+), 1 deletion(-)
diff --git a/app/test/test_event_eth_rx_adapter.c
b/app/test/test_e
Added testcase for rte_event_eth_tx_adapter_instance_get()
Signed-off-by: Ganapati Kundapura
---
app/test/test_event_eth_tx_adapter.c | 75
1 file changed, 75 insertions(+)
diff --git a/app/test/test_event_eth_tx_adapter.c
b/app/test/test_event_eth_tx_adapt
Added rte_event_eth_rx_adapter_instance_get() details
Signed-off-by: Ganapati Kundapura
---
doc/guides/prog_guide/event_ethernet_rx_adapter.rst | 6 ++
1 file changed, 6 insertions(+)
diff --git a/doc/guides/prog_guide/event_ethernet_rx_adapter.rst
b/doc/guides/prog_guide/event_ethernet_rx
Added rte_event_eth_tx_adapter_instance_get() details.
Signed-off-by: Ganapati Kundapura
---
doc/guides/prog_guide/event_ethernet_tx_adapter.rst | 6 ++
1 file changed, 6 insertions(+)
diff --git a/doc/guides/prog_guide/event_ethernet_tx_adapter.rst
b/doc/guides/prog_guide/event_ethernet_t
From: Zhichao Zeng
In the secondary dpdk-symmetric_mp process, the "smp_port_init" was
skipped, which cause some function pointers not to be initialized,
and a segmentation fault occurred when calling these function pointers.
This patch assigns initial values to rx_pkt_burst, tx_pkt_burst
and tx
On 6/22/2022 7:56 AM, Jiawen Wu wrote:
Fix the remaining bugs, support more OEM devices.
v2:
- remove useless variable initializers
- define macros for loop counts
- supplement detailed commit log
Jiawen Wu (7):
net/txgbe: support OEM subsystem vendor ID
net/ngbe: support OEM subsystem ve
> From: Bruce Richardson [mailto:bruce.richard...@intel.com]
> Sent: Wednesday, 22 June 2022 11.18
>
> On Wed, Jun 22, 2022 at 06:26:07AM +, Emil Berg wrote:
> >
> > > From: Morten Brørup
> > > Sent: den 21 juni 2022 11:35
> > >
> > > > From: Bruce Richardson [mailto:bruce.richard...@intel.co
Enable ability to run inline security tests using event
API(rte_event_eth_tx_adapter_enqueue/rte_event_dequeue_burst).
New test command - event_inline_ipsec_autotest will run same list of
test cases as inline_ipsec_autotest, but packets will go through eventdev.
Signed-off-by: Volodymyr Fialko
--
Hi Nicolas,
Please submit a patch for renaming rte_acc100_pmd.h to acc100_pmd.h
as it is an internal file.
>
> > v7: updates suggested by Akhil and Maxime. Removed RTE prefix for internal
> > #define, removed
> > build-time single FEC engine configuration mode, documentation fix, coding
> > guide
All the necessary code needed to connect to a node in a topology with
some extras, such as basic logging, per-node locks and some extra
useful methods.
To run the code, modify the two config files, execution.cfg and
conf/topology.cfg and execute ./main.py from the root dts folder. Here's
an exampl
Each lock is held per node. The lock assures that multiple connections
to the same node don't execute anything at the same time, removing the
possibility of race conditions.
Signed-off-by: Juraj Linkeš
---
dts/framework/ssh_pexpect.py | 15 +--
dts/framework/utils.py | 81 +
The library uses the pexpect python library and implements connection to
a node and two ways to interact with the node:
1. Send a string with specified prompt which will be matched after
the string has been sent to the node.
2. Send a command to be executed. No prompt is specified here.
Signed-
The logging module provides loggers distinguished by two attributes,
a custom format and a verbosity switch.
Signed-off-by: Juraj Linkeš
---
dts/framework/logger.py | 86 +
1 file changed, 86 insertions(+)
create mode 100644 dts/framework/logger.py
diff
The base class implements basic node management methods - connect and
execute commands.
Signed-off-by: Juraj Linkeš
---
dts/framework/node.py | 95 +++
dts/framework/settings.py | 8
2 files changed, 103 insertions(+)
create mode 100644 dts/framewor
The class adds logging to existing pexpect methods and history records.
Signed-off-by: Juraj Linkeš
---
dts/framework/ssh_connection.py | 52 +
1 file changed, 52 insertions(+)
create mode 100644 dts/framework/ssh_connection.py
diff --git a/dts/framework/ssh_con
The module uses Python's configparser module, which supports an ini-like
format with sections.
The configuration is split into two parts, one defining the parameters
of the test run and the other defining the topology to be used.
Signed-off-by: Juraj Linkeš
---
dts/conf/topology.cfg | 9 +
The module is responsilbe for running DTS. It handles the creation of
objects and eventually the whole DTS workflow, such as running node
setups, test gathering, setup and execution and various cleanups.
Signed-off-by: Juraj Linkeš
---
dts/framework/dts.py | 128 +++
The script is an interface to run DTS with standard argument parser.
Signed-off-by: Juraj Linkeš
---
dts/main.py | 36
1 file changed, 36 insertions(+)
create mode 100755 dts/main.py
diff --git a/dts/main.py b/dts/main.py
new file mode 100755
index
With this patch, the checksum can be calculated on an unligned buffer.
I.e. the buf parameter is no longer required to be 16 bit aligned.
The checksum is still calculated using a 16 bit aligned pointer, so the
compiler can auto-vectorize the function's inner loop.
When the buffer is unaligned, th
With this patch, the checksum can be calculated on an unligned buffer.
I.e. the buf parameter is no longer required to be 16 bit aligned.
The checksum is still calculated using a 16 bit aligned pointer, so the
compiler can auto-vectorize the function's inner loop.
When the buffer is unaligned, th
> From: Emil Berg [mailto:emil.b...@ericsson.com]
> Sent: Wednesday, 22 June 2022 14.25
>
> > From: Morten Brørup
> > Sent: den 22 juni 2022 13:26
> >
> > > From: Bruce Richardson [mailto:bruce.richard...@intel.com]
> > > Sent: Wednesday, 22 June 2022 11.18
> > >
> > > On Wed, Jun 22, 2022 at 06:
Hello Jakub, Roy,
On Wed, Jun 22, 2022 at 11:01 AM Poczatek, Jakub
wrote:
> When running a Virtio performance test on a VM using VHost with this patch
> applied,
> VHost gives the following error message:
>
> > VHOST_CONFIG: (/tmp/vhost) read message VHOST_USER_SET_FEATURES
> > VHOST_CONFIG: (/t
https://bugs.dpdk.org/show_bug.cgi?id=1041
Bug ID: 1041
Summary: dma/idxd build failure with clang 3.4.2
Product: DPDK
Version: unspecified
Hardware: All
OS: All
Status: UNCONFIRMED
Severity: normal
Hi, Chen bo, Maxime,
Please help to review the patch below.
Thanks.
Gaoxiang.
Forwarding messages
From: "Gaoxiang Liu"
Date: 2022-06-22 09:19:44
To: maxime.coque...@redhat.com,chenbo@intel.com
Cc: dev@dpdk.org,liugaoxi...@huawei.com,"Gaoxiang Liu"
,sta...@dpdk.org
On Wed, 22 Jun 2022 11:23:04 +0200
Thomas Monjalon wrote:
> 28/02/2022 18:08, Stephen Hemminger:
> > On Mon, 28 Feb 2022 09:42:47 +
> > Bruce Richardson wrote:
> >
> > > On Sun, Feb 27, 2022 at 09:48:57PM +0100, Thomas Monjalon wrote:
> > > > 20/02/2022 19:21, Stephen Hemminger:
> >
Hi Cristian,
> The code changes in the library (rte-sched.c) look good to me, but I do have
> some questions for the qos_sched app and the Soft NIC driver on how CMAN
> gets enabled/disabled.
That was open q from start. We finally found a time to discuss this.
> How do we control whether conges
Hey David,
The code change fixes the errors and the performance test completes.
Kind Regards,
Jakub Poczatek
-Original Message-
From: David Marchand
Sent: Wednesday 22 June 2022 15:08
To: Poczatek, Jakub ; Zhang, Roy Fan
Cc: Maxime Coquelin ; dev@dpdk.org;
sta...@dpdk.org; Xia, C
copy_data was returning a pointer to an increased (off by one) descriptor.
Subsequent calls to copy_data in the library were then failing.
Fix this by incrementing the descriptor only if there is some left data
to copy.
Fixes: 7287660a21e0 ("vhost/crypto: fix build with GCC 12")
Reported-by: Jaku
On Wed, Jun 22, 2022 at 5:22 PM Poczatek, Jakub
wrote:
>
> Hey David,
>
> The code change fixes the errors and the performance test completes.
I posted this fix against (not yet pulled into main) next-virtio repo.
--
David Marchand
On 6/22/22 17:30, David Marchand wrote:
copy_data was returning a pointer to an increased (off by one) descriptor.
Subsequent calls to copy_data in the library were then failing.
Fix this by incrementing the descriptor only if there is some left data
to copy.
Fixes: 7287660a21e0 ("vhost/crypt
On Wed, Jun 22, 2022 at 1:17 AM Stephen Hemminger
wrote:
> > GCC raises the following warning:
> >
> > In function ‘_mm256_storeu_si256’,
> > inlined from ‘rte_mov32’ at
> > ../lib/eal/x86/include/rte_memcpy.h:320:2,
> > inlined from ‘rte_mov128’ at
> > ../lib/eal/x86/inclu
17/06/2022 11:34, Jin Liu:
> + if (unlikely(pkt->nb_segs > 1 &&
> + !(hw->cap & NFP_NET_CFG_CTRL_GATHER))) {
> + PMD_INIT_LOG(INFO, "NFP_NET_CFG_CTRL_GATHER not set");
> + rte_panic("Multisegment packet unsupported\n");
On Wed, Jun 22, 2022 at 07:07:12AM +0200, Stanisław Kardach wrote:
> On Tue, Jun 21, 2022 at 9:53 PM Tyler Retzlaff
> wrote:
> >
> > > -cpp = ['ccache', 'arm-linux-gnueabihf-cpp']
> > > +cpp = ['ccache', 'arm-linux-gnueabihf-g++']
> >
> > suggest the variable should be 'cxx' not 'cpp' (to be cons
> From: Tyler Retzlaff [mailto:roret...@linux.microsoft.com]
> Sent: Wednesday, 22 June 2022 18.06
>
> On Wed, Jun 22, 2022 at 07:07:12AM +0200, Stanisław Kardach wrote:
> > On Tue, Jun 21, 2022 at 9:53 PM Tyler Retzlaff
> > wrote:
> > >
> > > > -cpp = ['ccache', 'arm-linux-gnueabihf-cpp']
> > >
On 6/22/2022 5:03 PM, Thomas Monjalon wrote:
17/06/2022 11:34, Jin Liu:
+ if (unlikely(pkt->nb_segs > 1 &&
+ !(hw->cap & NFP_NET_CFG_CTRL_GATHER))) {
+ PMD_INIT_LOG(INFO, "NFP_NET_CFG_CTRL_GATHER not set");
+
>
> Enable ability to run inline security tests using event
> API(rte_event_eth_tx_adapter_enqueue/rte_event_dequeue_burst).
> New test command - event_inline_ipsec_autotest will run same list of test
> cases as inline_ipsec_autotest, but packets will go through eventdev.
>
> Signed-off-by: Volod
> -Original Message-
> From: David Marchand
> Sent: Wednesday, June 22, 2022 4:30 PM
> To: dev@dpdk.org
> Cc: Zhang, Roy Fan ; Poczatek, Jakub
> ; Maxime Coquelin
> ; Xia, Chenbo
> Subject: [PATCH] vhost/crypto: fix descriptor processing
>
> copy_data was returning a pointer to an increa
Added rte_event_eth_rx_adapter_instance_get() to get
adapter instance id for specified ethernet device id and
rx queue index.
Signed-off-by: Ganapati Kundapura
---
v8:
* Removed limits.h inclusion
v7:
* Remove allocation of instance array and storage of instnace id
* in instance array
* Use Rx a
Added telemetry handler for rte_event_eth_rx_adapter_instance_get()
to retrieve adapter instance id for specified ethernet device id
and rx queue index.
Signed-off-by: Ganapati Kundapura
---
lib/eventdev/rte_event_eth_rx_adapter.c | 66 +
1 file changed, 66 insert
Added test case for rte_event_eth_rx_adapter_instance_get()
Signed-off-by: Ganapati Kundapura
---
app/test/test_event_eth_rx_adapter.c | 203 ++-
1 file changed, 202 insertions(+), 1 deletion(-)
diff --git a/app/test/test_event_eth_rx_adapter.c
b/app/test/test_e
Added rte_event_eth_tx_adapter_instance_get() to get the
adapter instance id for specified ethernet device id and
tx queue index.
Signed-off-by: Ganapati Kundapura
---
lib/eventdev/eventdev_pmd.h | 23 +++
lib/eventdev/rte_event_eth_tx_adapter.c | 102 +++
Added testcase for rte_event_eth_tx_adapter_instance_get()
Signed-off-by: Ganapati Kundapura
---
app/test/test_event_eth_tx_adapter.c | 75
1 file changed, 75 insertions(+)
diff --git a/app/test/test_event_eth_tx_adapter.c
b/app/test/test_event_eth_tx_adapt
Added rte_event_eth_rx_adapter_instance_get() details
Signed-off-by: Ganapati Kundapura
---
doc/guides/prog_guide/event_ethernet_rx_adapter.rst | 6 ++
1 file changed, 6 insertions(+)
diff --git a/doc/guides/prog_guide/event_ethernet_rx_adapter.rst
b/doc/guides/prog_guide/event_ethernet_rx
Added rte_event_eth_tx_adapter_instance_get() details.
Signed-off-by: Ganapati Kundapura
---
doc/guides/prog_guide/event_ethernet_tx_adapter.rst | 6 ++
1 file changed, 6 insertions(+)
diff --git a/doc/guides/prog_guide/event_ethernet_tx_adapter.rst
b/doc/guides/prog_guide/event_ethernet_t
On Sat, Jun 18, 2022 at 1:29 PM Dmitry Kozlyuk wrote:
>
> Hi Fidaullah,
>
> Thanks for the fix,
> Acked-by: Dmitry Kozlyuk
This seems backport material.
Dmitry, Anatoly, do you agree? If so I'll mark it when applying.
As for a Fixes: line, the closer commit touching this part is
07dcbfe0101f ("
On 6/22/22 17:30, David Marchand wrote:
copy_data was returning a pointer to an increased (off by one) descriptor.
Subsequent calls to copy_data in the library were then failing.
Fix this by incrementing the descriptor only if there is some left data
to copy.
Fixes: 7287660a21e0 ("vhost/crypt
Reviewed-by: Naga Harish K S V
> -Original Message-
> From: Kundapura, Ganapati
> Sent: Wednesday, June 22, 2022 10:24 PM
> To: dev@dpdk.org; jer...@marvell.com; Jayatheerthan, Jay
> ; Naga Harish K, S V
>
> Subject: [PATCH v8 2/7] eventdev/eth_rx: add telemetry callback for
> instance
Reviewed-by: Naga Harish K S V
> -Original Message-
> From: Kundapura, Ganapati
> Sent: Wednesday, June 22, 2022 10:24 PM
> To: dev@dpdk.org; jer...@marvell.com; Jayatheerthan, Jay
> ; Naga Harish K, S V
>
> Subject: [PATCH v8 3/7] test/eth_rx: add test case for instance get API
>
> Ad
Reviewed-by: Naga Harish K S V
> -Original Message-
> From: Kundapura, Ganapati
> Sent: Wednesday, June 22, 2022 10:24 PM
> To: dev@dpdk.org; jer...@marvell.com; Jayatheerthan, Jay
> ; Naga Harish K, S V
>
> Subject: [PATCH v8 4/7] eventdev/eth_tx: add instance get API
>
> Added rte_ev
Reviewed-by: Naga Harish K S V
> -Original Message-
> From: Kundapura, Ganapati
> Sent: Wednesday, June 22, 2022 10:24 PM
> To: dev@dpdk.org; jer...@marvell.com; Jayatheerthan, Jay
> ; Naga Harish K, S V
>
> Subject: [PATCH v8 5/7] test/eth_tx: add testcase for instance get API
>
> Add
Reviewed-by: Naga Harish K S V
> -Original Message-
> From: Kundapura, Ganapati
> Sent: Wednesday, June 22, 2022 10:24 PM
> To: dev@dpdk.org; jer...@marvell.com; Jayatheerthan, Jay
> ; Naga Harish K, S V
>
> Subject: [PATCH v8 1/7] eventdev/eth_rx: add adapter instance get API
>
> Adde
Reviewed-by: Naga Harish K S V
> -Original Message-
> From: Kundapura, Ganapati
> Sent: Wednesday, June 22, 2022 10:24 PM
> To: dev@dpdk.org; jer...@marvell.com; Jayatheerthan, Jay
> ; Naga Harish K, S V
>
> Subject: [PATCH v8 7/7] doc/eth_tx: update instance get API
>
> Added rte_even
Reviewed-by: Naga Harish K S V
> -Original Message-
> From: Kundapura, Ganapati
> Sent: Wednesday, June 22, 2022 10:24 PM
> To: dev@dpdk.org; jer...@marvell.com; Jayatheerthan, Jay
> ; Naga Harish K, S V
>
> Subject: [PATCH v8 6/7] doc/eth_rx: update instance get API
>
> Added rte_even
> -Original Message-
> From: Kundapura, Ganapati
> Sent: Wednesday, June 22, 2022 10:24 PM
> To: dev@dpdk.org; jer...@marvell.com; Jayatheerthan, Jay
> ; Naga Harish K, S V
>
> Subject: [PATCH v8 7/7] doc/eth_tx: update instance get API
>
> Added rte_event_eth_tx_adapter_instance_get()
Aside of the minor documentation fix in patch 7/7, the full patchset looks good
to me. Thanks for posting it!
Please fix it and add Acked-by: Jay Jayatheerthan
-Jay
> -Original Message-
> From: Kundapura, Ganapati
> Sent: Wednesday, June 22, 2022 10:24 PM
> To: dev@dpdk.org; jer...@
On Wed, Jun 22, 2022 at 01:24:14AM +0300, Dmitry Kozlyuk wrote:
> 2022-06-21 14:28 (UTC-0700), Tyler Retzlaff:
> > On Tue, Jun 21, 2022 at 10:44:21PM +0300, Dmitry Kozlyuk wrote:
> > > 2022-06-21 11:51 (UTC-0700), Tyler Retzlaff:
> > > > > > +int
> > > > > > +rte_thread_join(rte_thread_t thread_i
Reran the Cocci script to check for unnecessary null
pointer comparisons before free related functions.
Stephen Hemminger (3):
vdpa/mlx5: remove unnecessary null check
raw/ifpga: remove unnecessary null check
dmap/dpaa2: remove unnecessary null check
drivers/dma/dpaa2/dpaa2_qdma.c | 6
Found by nullfree.cocci.
Signed-off-by: Stephen Hemminger
---
drivers/vdpa/mlx5/mlx5_vdpa_virtq.c | 3 +--
1 file changed, 1 insertion(+), 2 deletions(-)
diff --git a/drivers/vdpa/mlx5/mlx5_vdpa_virtq.c
b/drivers/vdpa/mlx5/mlx5_vdpa_virtq.c
index e025be47d277..e06d6afb676f 100644
--- a/drivers
The function rte_kvargs_free handles calling with NULL.
Found by nullfree.cocci.
Signed-off-by: Stephen Hemminger
---
drivers/raw/ifpga/ifpga_rawdev.c | 3 +--
1 file changed, 1 insertion(+), 2 deletions(-)
diff --git a/drivers/raw/ifpga/ifpga_rawdev.c b/drivers/raw/ifpga/ifpga_rawdev.c
index c
The function rte_free already handles being called with NULL.
Found by nullfree.cocci.
Signed-off-by: Stephen Hemminger
---
drivers/dma/dpaa2/dpaa2_qdma.c | 6 ++
1 file changed, 2 insertions(+), 4 deletions(-)
diff --git a/drivers/dma/dpaa2/dpaa2_qdma.c b/drivers/dma/dpaa2/dpaa2_qdma.c
ind
On Wed, Jun 22, 2022 at 11:51:55AM -0700, Stephen Hemminger wrote:
> Reran the Cocci script to check for unnecessary null
> pointer comparisons before free related functions.
>
> Stephen Hemminger (3):
> vdpa/mlx5: remove unnecessary null check
> raw/ifpga: remove unnecessary null check
> dm
> Subject: RE: [RFC PATCH v1] net/i40e: put mempool cache out of API
>
> > From: Feifei Wang [mailto:feifei.wa...@arm.com]
> > Sent: Monday, 13 June 2022 07.52
> >
> > Refer to "i40e_tx_free_bufs_avx512", this patch puts mempool cache out
> > of API to free buffers directly. There are two change
add rte thread lifetime and attributes api. with these api additions
there is now sufficient platform abstracted thread api to remove the
use of pthread in the unit tests.
v3:
* change rte_thread_func return type to uint32_t for exit value.
* change rte_thread_join retval to be uint32_t (match
Add rte_thread_equal() that tests if two rte_thread_id are equal.
Signed-off-by: Narcisa Vasile
Signed-off-by: Tyler Retzlaff
Acked-by: Chengwen Feng
Acked-by: Konstantin Ananyev
---
lib/eal/include/rte_thread.h | 19 +++
lib/eal/unix/rte_thread.c| 6 ++
lib/eal/versi
test basic functionality and demonstrate use of following thread
lifetime api.
* rte_thread_create
* rte_thread_detach
* rte_thread_join
Signed-off-by: Narcisa Vasile
Signed-off-by: Tyler Retzlaff
---
app/test/test_threads.c | 54 +++--
1
Implement thread attributes for:
* thread affinity
* thread priority
Implement functions for managing thread attributes.
Priority is represented through an enum that allows for two levels:
* RTE_THREAD_PRIORITY_NORMAL
* RTE_THREAD_PRIORITY_REALTIME_CRITICAL
Affinity is desc
The *rte_thread_create()* function can optionally receive an
rte_thread_attr_t object that will cause the thread to be created with
the affinity and priority described by the attributes object. If
no rte_thread_attr_t is passed (parameter is NULL), the default
affinity and priority are used.
On Wi
now that rte_thread provides thread lifetime functions stop using
pthread in unit tests.
Signed-off-by: Tyler Retzlaff
---
app/test/test_threads.c | 7 ++-
1 file changed, 2 insertions(+), 5 deletions(-)
diff --git a/app/test/test_threads.c b/app/test/test_threads.c
index 3c22cec..e0f18e4 1
test basic functionality and demonstrate use of following thread
attributes api. additionally, test attributes are processed when
supplied to rte_thread_create().
* rte_thread_attr_init
* rte_thread_attr_set_affinity
* rte_thread_attr_get_affinity
* rte_thread_attr_set_priority
Si
The phrase "This API is used to" is unnecessary and changes the
documentation into passive voice.
Stephen Hemminger (2):
rawdev, dmadev: remove passive voice in function doc
eal: remove passive voice from interrupt function documentation
drivers/raw/ioat/rte_ioat_rawdev.h | 2 +-
lib/dmadev
Remove extraneous phrase "This API is used to" and use
active instead of passive voice when describing a function.
Signed-off-by: Stephen Hemminger
---
drivers/raw/ioat/rte_ioat_rawdev.h | 2 +-
lib/dmadev/rte_dmadev.h| 2 +-
2 files changed, 2 insertions(+), 2 deletions(-)
diff --g
The phrase "This API is used" is unnecessary, remove it.
Reword to describe function in active voice.
Signed-off-by: Stephen Hemminger
---
lib/eal/include/rte_interrupts.h | 23 +++
1 file changed, 11 insertions(+), 12 deletions(-)
diff --git a/lib/eal/include/rte_interrupts
On Wed, Jun 22, 2022 at 01:27:36PM -0700, Stephen Hemminger wrote:
> The phrase "This API is used to" is unnecessary and changes the
> documentation into passive voice.
>
> Stephen Hemminger (2):
> rawdev, dmadev: remove passive voice in function doc
> eal: remove passive voice from interrupt
The comments in rte_rib6 were cut-and-pasted from rte_rib
and because of that some references to rte_rib_node were
not updated.
Signed-off-by: Stephen Hemminger
---
lib/rib/rte_rib6.h | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/lib/rib/rte_rib6.h b/lib/rib/rte_rib6.
Make sure all functions which use the convention that XXX_free(NULL)
is a nop are all documented.
The wording is chosen to match the documentation of free(3).
"If ptr is NULL, no operation is performed."
Signed-off-by: Stephen Hemminger
---
lib/bitratestats/rte_bitrate.h | 1 +
lib/compressde
On Wed, 22 Jun 2022 13:37:12 -0700
Tyler Retzlaff wrote:
> On Wed, Jun 22, 2022 at 01:27:36PM -0700, Stephen Hemminger wrote:
> > The phrase "This API is used to" is unnecessary and changes the
> > documentation into passive voice.
> >
> > Stephen Hemminger (2):
> > rawdev, dmadev: remove pass
1 - 100 of 146 matches
Mail list logo
