> -Original Message-
> From: Fu, Patrick
> Sent: Wednesday, July 22, 2020 11:02 PM
> To: dev@dpdk.org; maxime.coque...@redhat.com; Xia, Chenbo
>
> Cc: Fu, Patrick
> Subject: [PATCH v2 2/2] doc: update release notes for vhost async APIs
>
> From: Patrick Fu
>
> Update 20.08 release n
> -Original Message-
> From: Fu, Patrick
> Sent: Wednesday, July 22, 2020 11:02 PM
> To: dev@dpdk.org; maxime.coque...@redhat.com; Xia, Chenbo
>
> Cc: Fu, Patrick
> Subject: [PATCH v2 1/2] doc: update guides for vhost async APIs
>
> From: Patrick Fu
>
> Update vhost guides to docume
Replace gettimeofday() with clock_gettime(CLOCK_MONOTONIC_RAW, &now),
the reason is same with this patch "make alarm not affected by
system time jump".
Fixes: 81d53291a466 ("net/hinic/base: add various headers")
Cc: sta...@dpdk.org
Signed-off-by: Xiaoyun wang
---
drivers/net/hinic/base/hinic_co
For ovs offload scenario, when fw processes the virtio header,
there is no need to offset; and for standard card scenarios,
fw does not care about the vhd_type parameter, so in order to
be compatible with the two scenarios, use 0 offset instead.
Signed-off-by: Xiaoyun wang
---
drivers/net/hinic/
For x86 platform, the rq cqe without cache aligned, which can
improve performace for some gateway scenarios.
Fixes: 361a9ccf81d6 ("net/hinic: optimize Rx performance")
Cc: sta...@dpdk.org
Signed-off-by: Xiaoyun wang
---
drivers/net/hinic/hinic_pmd_rx.h | 4
1 file changed, 4 insertions(+)
Encapsulate different types of packet checksum preprocessing
into functions.
Signed-off-by: Xiaoyun wang
---
drivers/net/hinic/hinic_pmd_tx.c | 371 +--
1 file changed, 202 insertions(+), 169 deletions(-)
diff --git a/drivers/net/hinic/hinic_pmd_tx.c b/driver
This patch modifies csum offload process, optimize Rx
performance for x86, set vhd type with 2 for no offset
in ovs offload scenario, make timeout not affected by
system time jump.
--
v1:
- modify csum offload process
- optimize Rx performance for x86
- modify vhd type for SDI
- make tim
Update the docs, adding MCX621102AN-ADAT to the list of NICs supported
by MLX5 vDPA driver.
Signed-off-by: Sergey Madaminov
Suggested-by: William Tu
---
doc/guides/vdpadevs/mlx5.rst | 1 +
1 file changed, 1 insertion(+)
diff --git a/doc/guides/vdpadevs/mlx5.rst b/doc/guides/vdpadevs/mlx5.rst
i
> -Original Message-
> From: Yang, Qiming
> Sent: Friday, July 24, 2020 4:38 PM
> To: Zhao1, Wei ; dev@dpdk.org
> Cc: sta...@dpdk.org; Zhang, Qi Z ; Zhao1, Wei
>
> Subject: RE: [dpdk-dev] [PATCH] net/i40e: enable i40e outer VLAN strip in QinQ
>
>
>
> > -Original Message-
> >
On Thu, Jul 23, 2020 at 10:32 PM Ajit Khaparde
wrote:
> Some fixes, cleanups and changes to augment pre-existing
> support in infrastructure
>
> Please apply
>
> v1->v2:
> - Fixed some typos in patch [9/20].
> v2->v3:
> - Fixed coding style issues in patch [15/20] to use __rte_attribute.
> - U
From: Vivien Didelot
When hardware timestamping is enabled on Rx path, system time should
no longer be used to calculate the timestamps when dumping packets.
Instead, use the value stored by the driver in mbuf->timestamp
and assume it is already converted to nanoseconds (otherwise the
applicatio
Use start time and device frequency to translate raw Rx hardware
timestamps into nanoseconds.
Signed-off-by: Patrick Keroulas
---
lib/librte_pdump/rte_pdump.c | 25 +
1 file changed, 25 insertions(+)
diff --git a/lib/librte_pdump/rte_pdump.c b/lib/librte_pdump/rte_pdump.
The intention is to produce a pcap with nanosecond precision when
Rx timestamp offloading is activated on mlx5 NIC.
The packets forwarded by testpmd hold the raw counter but a pcap
requires a time unit. Assuming that the NIC clock is already synced
with external master clock, this patchset simply
Signed-off-by: Patrick Keroulas
---
lib/librte_ethdev/rte_ethdev.c | 12
lib/librte_ethdev/rte_ethdev.h | 17 +
lib/librte_ethdev/rte_ethdev_core.h | 5 +
lib/librte_ethdev/rte_ethdev_version.map | 2 ++
4 files changed, 36 insertions(+)
Get clock frequency (constant) from HCA attributes and add an accessor.
Signed-off-by: Patrick Keroulas
---
drivers/common/mlx5/mlx5_devx_cmds.c| 2 ++
drivers/common/mlx5/mlx5_devx_cmds.h| 1 +
drivers/net/mlx5/linux/mlx5_ethdev_os.c | 22 ++
drivers/net/mlx5/linux
> Subject: [dpdk-dev] [PATCH v10 01/10] eal: introduce macro for bit definition
>
> There are several drivers which duplicate bit generation macro.
> Introduce a generic bit macros so that such drivers avoid redefining same in
> multiple drivers.
>
> Signed-off-by: Parav Pandit
> Acked-by: Mat
On Thu, 23 Jul 2020 22:32:14 -0700
Ajit Khaparde wrote:
> +int
> +tf_search_tcam_entry(struct tf *tfp,
> + struct tf_search_tcam_entry_parms *parms)
> +{
> + int rc;
> + struct tf_session *tfs;
> + struct tf_dev_info *dev;
> + struct tf_tcam_alloc_search_parms spa
On 7/24/2020 2:20 PM, Ciara Loftus wrote:
> Other PMDs may be using the mempool, so don't free it when destroying the
> UMEM.
>
> Fixes: d8a210774e1d ("net/af_xdp: support unaligned umem chunks")
> Cc: sta...@dpdk.org
>
> Signed-off-by: Ciara Loftus
Applied to dpdk-next-net/master, thanks.
On 7/23/2020 12:08 AM, Fady Bader wrote:
v2: * fixed style issue.
v3: * replaced htons with rte_cpu_to_be_16.
* rebased to current master.
v4: * removed the use of rte_random in librte_net.
* replaced htons with RTE_BE16.
Fady Bader (3):
net: fix s_addr redefinition in Windows
Hi Thomas
From: Thomas Monjalon:
> 19/07/2020 13:41, Matan Azrad:
> >
> > From: Thomas Monjalon:
> > > 19/07/2020 12:56, Matan Azrad:
> > > >
> > > > From: Thomas Monjalon
> > > > > The detection of the CPU was done in a constructor and shared in
> > > > > a global variable.
> > > > >
> > > > > Th
On 7/24/20 10:54 AM, Maxime Coquelin wrote:
>
>
> On 7/24/20 9:06 AM, Maxime Coquelin wrote:
>> Hi Yinan,
>>
>> On 7/24/20 6:55 AM, Wang, Yinan wrote:
>>> Hi Maxime,
>>>
>>> The performance drop issue can be fixed, thanks!
>>> The multi-queues interrupt issue still exist w/ this patch set.
>>
On Fri, Jul 24, 2020 at 03:17:38PM +, Parav Pandit wrote:
>
>
> > From: Bruce Richardson
> > Sent: Friday, July 24, 2020 8:20 PM
> >
> > On Fri, Jul 24, 2020 at 03:54:33PM +0200, Thomas Monjalon wrote:
> > > 24/07/2020 15:48, Parav Pandit:
> > > > Hi Bruce,
> > > >
> > > > > From: Bruce Ric
> From: Bruce Richardson
> Sent: Friday, July 24, 2020 8:20 PM
>
> On Fri, Jul 24, 2020 at 03:54:33PM +0200, Thomas Monjalon wrote:
> > 24/07/2020 15:48, Parav Pandit:
> > > Hi Bruce,
> > >
> > > > From: Bruce Richardson
> > > > Sent: Friday, July 24, 2020 4:37 PM
> > > >
> > > > On Thu, Jul
From: jiancheng pei
Store port_id in pmd_internals when eth kni device is created.
Then set packet port of rte_mbuf in function eth_kni_rx.
Signed-off-by: Jecky Pei
Reviewed-by: Ferruh Yigit
---
drivers/net/kni/rte_eth_kni.c | 5 +
1 file changed, 5 insertions(+)
diff --git a/drivers/net
On Sun, Jul 19, 2020 at 12:09 PM Thomas Monjalon wrote:
>
> The detection of the CPU was done in a constructor and shared
> in a global variable.
>
> This variable may not be visible in the net PMD
> because it was not exported as part of the .map file.
> It is fixed by exporting a function, which
On Fri, Jul 24, 2020 at 03:54:33PM +0200, Thomas Monjalon wrote:
> 24/07/2020 15:48, Parav Pandit:
> > Hi Bruce,
> >
> > > From: Bruce Richardson
> > > Sent: Friday, July 24, 2020 4:37 PM
> > >
> > > On Thu, Jul 23, 2020 at 11:09:03PM +0300, Parav Pandit wrote:
> > > > From: Thomas Monjalon
> >
On 7/1/2020 8:49 AM, Ferruh Yigit wrote:
> From: jiancheng pei
>
> Store port_id in pmd_internals when eth kni device is created.
> Then set packet port of rte_mbuf in function eth_kni_rx.
Overall looks good, except minor issues commented below.
Since I have sent on behalf of the Jecky, I will s
When adding a RSS rule with GTPU_DWN/UP, it will write from top to
bottom for profile due to firmware limitation. If a RSS rule with
GTPU_EH already exists, then GTPU_DWN/UP packet will match GTPU_EH
profile. This patch solves this issue by remembering a gtpu_eh RSS
configure and removing it before
Now that mlx5_pci PMD checks for enabled classes and performs
probe(), remove() of associated classes, individual class driver
does not need to check if other driver is enabled.
Signed-off-by: Parav Pandit
Acked-by: Matan Azrad
---
drivers/common/mlx5/mlx5_common.c | 37
This is not a thorough review, just caught one issue for makefile and some nits.
On Thu, Jul 23, 2020 at 10:11 PM Parav Pandit wrote:
>
> From: Thomas Monjalon
>
> Add generic mlx5 PCI PMD layer as part of existing common_mlx5
> module. This enables multiple classes (net, regex, vdpa) PMDs
> to
Migrate mlx5 net, vdpa and regex PMD to start using mlx5 common class
driver.
Signed-off-by: Parav Pandit
Acked-by: Matan Azrad
---
Changelog:
v8->v9:
- Removed leftover inclusion of mlx5_pci bus include directory
---
drivers/common/mlx5/mlx5_common_pci.c | 6 ++
drivers/net/mlx5/Makefile
mlx5_common is shared library between mlx5 net, VDPA and regex PMD.
It is better to use common initialization helper instead of using
RTE_PRIORITY_CLASS priority.
Reviewed-by: David Marchand
Suggested-by: David Marchand
Signed-off-by: Parav Pandit
---
Changelog:
v7->v8:
- new patch
---
driver
Add generic mlx5 PCI PMD layer as part of existing common_mlx5
module. This enables multiple classes (net, regex, vdpa) PMDs
to be supported at same time.
Signed-off-by: Parav Pandit
Acked-by: Matan Azrad
---
Changelog:
v9->v10:
- Fixed alignment
v8->v9:
- Added missing LDFLAG for pci bus
- F
mlx5 PCI Device supports multiple classes of devices such as net, vdpa,
and/or regex.
To support these multiple classes, change mlx5_class to a
bitmap values so that if users asks to enable multiple of them, all
supported classes can be parsed.
Signed-off-by: Parav Pandit
Acked-by: Matan Azrad
-
Following two errors are reported when compiled with
gcc (GCC) 8.3.1 20191121 (Red Hat 8.3.1-5).
drivers/common/mlx5/linux/mlx5_glue.h:188:2:
error: function declaration isn't a prototype [-Werror=strict-prototypes]
drivers/common/mlx5/linux/mlx5_glue.h:188:2:
error: function declaration isn't a
When fail to initialize the device, avoid segmentation fault while
accessing unintialized priv.
Fixes: cfc672a90b74 ("regex/mlx5: support probing")
Signed-off-by: Parav Pandit
---
Changelog:
v9->v10:
- Corrected type in commit log
v7->v8:
- Rebased
- new patch
---
drivers/regex/mlx5/mlx5_reg
There are several drivers which duplicate bit generation macro.
Introduce a generic bit macros so that such drivers avoid redefining
same in multiple drivers.
Signed-off-by: Parav Pandit
Acked-by: Matan Azrad
Acked-by: Morten Brørup
---
Changelog:
v4->v5:
- Addressed comments from Morten Brøru
From: Thomas Monjalon
Drivers dependencies are evaluated in the order defined per their parent
directory (also called class). This strict ordering prevents from
having pairs of drivers from two classes with different dependency
ordering. For example, if the mlx5 common code depends on the pci bus
This series introduces mlx5 common driver layer to support multiple
class of devices for a single PCI device.
Motivation and example
--
mlx5 PCI device supports multiple class of devices such as net, vdpa
and regex devices.
Currently only one pmd (either net or vdpa) can bind
From: Thomas Monjalon
Define each sub-directory on its own line ended with a comma,
and use a simple indent.
Acked-by: Bruce Richardson
Reviewed-by: David Marchand
Signed-off-by: Thomas Monjalon
---
Changelog:
v7->8:
- new patch
---
drivers/meson.build | 24 +---
1 file
> From: Parav Pandit
> Sent: Friday, July 24, 2020 7:54 PM
>
> This series introduces mlx5 common driver layer to support multiple class of
> devices for a single PCI device.
>
[..]
>
> Changelog:
> v8->v9:
> - Updated commit message
> - Fixed LD_FLAGS
> - Fixed white space to tab
> - Fixe
Now that mlx5_pci PMD checks for enabled classes and performs
probe(), remove() of associated classes, individual class driver
does not need to check if other driver is enabled.
Signed-off-by: Parav Pandit
Acked-by: Matan Azrad
---
drivers/common/mlx5/mlx5_common.c | 37
mlx5_common is shared library between mlx5 net, VDPA and regex PMD.
It is better to use common initialization helper instead of using
RTE_PRIORITY_CLASS priority.
Reviewed-by: David Marchand
Suggested-by: David Marchand
Signed-off-by: Parav Pandit
---
Changelog:
v7->v8:
- new patch
---
driver
Migrate mlx5 net, vdpa and regex PMD to start using mlx5 common class
driver.
Signed-off-by: Parav Pandit
Acked-by: Matan Azrad
---
Changelog:
v8->v9:
- Removed leftover inclusion of mlx5_pci bus include directory
---
drivers/common/mlx5/mlx5_common_pci.c | 6 ++
drivers/net/mlx5/Makefile
Add generic mlx5 PCI PMD layer as part of existing common_mlx5
module. This enables multiple classes (net, regex, vdpa) PMDs
to be supported at same time.
Signed-off-by: Parav Pandit
Acked-by: Matan Azrad
---
Changelog:
v8->v9:
- Added missing LDFLAG for pci bus
- Fixed white spaces at start o
mlx5 PCI Device supports multiple classes of devices such as net, vdpa,
and/or regex.
To support these multiple classes, change mlx5_class to a
bitmap values so that if users asks to enable multiple of them, all
supported classes can be parsed.
Signed-off-by: Parav Pandit
Acked-by: Matan Azrad
-
When fail to initialize the device, avoid segmentation fault while
accessing unintialized priv.
Fixes: cfc672a90b74 ("regex/mlx5: support probing")
Signed-off-by: Parav Pandit
---
Changelog:
v7->v8:
- Rebased
- new patch
---
drivers/regex/mlx5/mlx5_regex.c | 7 ---
1 file changed, 4 inser
Following two errors are reported when compiled with
gcc (GCC) 8.3.1 20191121 (Red Hat 8.3.1-5).
drivers/common/mlx5/linux/mlx5_glue.h:188:2:
error: function declaration isn't a prototype [-Werror=strict-prototypes]
drivers/common/mlx5/linux/mlx5_glue.h:188:2:
error: function declaration isn't a
From: Thomas Monjalon
Drivers dependencies are evaluated in the order defined per their parent
directory (also called class). This strict ordering prevents from
having pairs of drivers from two classes with different dependency
ordering. For example, if the mlx5 common code depends on the pci bus
There are several drivers which duplicate bit generation macro.
Introduce a generic bit macros so that such drivers avoid redefining
same in multiple drivers.
Signed-off-by: Parav Pandit
Acked-by: Matan Azrad
Acked-by: Morten Brørup
---
Changelog:
v4->v5:
- Addressed comments from Morten Brøru
From: Thomas Monjalon
Define each sub-directory on its own line ended with a comma,
and use a simple indent.
Acked-by: Bruce Richardson
Reviewed-by: David Marchand
Signed-off-by: Thomas Monjalon
---
Changelog:
v7->8:
- new patch
---
drivers/meson.build | 24 +---
1 file
This series introduces mlx5 common driver layer to support multiple
class of devices for a single PCI device.
Motivation and example
--
mlx5 PCI device supports multiple class of devices such as net, vdpa
and regex devices.
Currently only one pmd (either net or vdpa) can bind
Hi, Guojia
> -Original Message-
> From: Guo, Jia
> Sent: Friday, July 24, 2020 3:13 PM
> To: Su, Simei ; Zhang, Qi Z ; Xing,
> Beilei
> Cc: dev@dpdk.org
> Subject: Re: [PATCH] net/ice: fix GTPU down/uplink and extension conflict
>
> hi, simei
>
> On 7/24/2020 10:10 AM, Simei Su wrote:
On Fri, Jul 24, 2020 at 7:00 PM Thomas Monjalon wrote:
>
> 23/07/2020 19:00, Stephen Hemminger:
> > On Thu, 23 Jul 2020 17:13:17 +0500
> > Sarosh Arif wrote:
> >
> > > Since this script has no maintainer who is responsible for providing ACK
> > > or
> > > NAK on the patches related to this scrip
24/07/2020 15:48, Parav Pandit:
> Hi Bruce,
>
> > From: Bruce Richardson
> > Sent: Friday, July 24, 2020 4:37 PM
> >
> > On Thu, Jul 23, 2020 at 11:09:03PM +0300, Parav Pandit wrote:
> > > From: Thomas Monjalon
> > >
> > > Drivers dependencies are evaluated in the order defined per their
> > >
From: Patrick Fu
Async copy fails when single ring buffer vector is splited on multiple
physical pages. This happens because current hpa address translation
function doesn't handle multi-page buffers. A new gpa to hpa address
conversion function, which returns the hpa on the first hitting host
pa
Hi Bruce,
> From: Bruce Richardson
> Sent: Friday, July 24, 2020 4:37 PM
>
> On Thu, Jul 23, 2020 at 11:09:03PM +0300, Parav Pandit wrote:
> > From: Thomas Monjalon
> >
> > Drivers dependencies are evaluated in the order defined per their
> > parent directory (also called class).
> > This stric
> From: David Marchand
> Sent: Friday, July 24, 2020 7:15 PM
> To: Parav Pandit
> Cc: dev ; Gaetan Rivet ; Yigit, Ferruh
> ; Thomas Monjalon ;
> Raslan Darawsheh ; Ori Kam
> ; Matan Azrad ; Joyce Kong
>
> Subject: Re: [dpdk-dev] [PATCH v8 06/10] common/mlx5: avoid using class
> constructor pri
On Thu, Jul 23, 2020 at 10:10 PM Parav Pandit wrote:
>
> mlx5_common is shared library between mlx5 net, VDPA and regex PMD.
> It is better to use common initialization helper instead of using
> RTE_INIT_CLASS priority.
RTE_INIT_CLASS does not exist, I suppose you meant RTE_PRIORITY_CLASS.
Sugge
This commit fixes a potential race condition in the tests
where the lcore running a service would increment a counter
that was already reset by the test-suite thread. The resulting
race-condition incremented value could cause CI failures, as
indicated by DPDK's CI.
This patch fixes the race-condit
This commit adds a new experimental API which allows the user
to retrieve the active state of an lcore. Knowing when the service
lcore is completed its polling loop can be useful to applications
to avoid race conditions when e.g. finalizing statistics.
The service thread itself now has a variable
Other PMDs may be using the mempool, so don't free it when destroying the
UMEM.
Fixes: d8a210774e1d ("net/af_xdp: support unaligned umem chunks")
Cc: sta...@dpdk.org
Signed-off-by: Ciara Loftus
---
drivers/net/af_xdp/rte_eth_af_xdp.c | 1 -
1 file changed, 1 deletion(-)
diff --git a/drivers/ne
On Thu, Jul 23, 2020 at 10:10 PM Parav Pandit wrote:
>
> From: Thomas Monjalon
>
> Drivers dependencies are evaluated in the order defined per
> their parent directory (also called class).
> This strict ordering prevent from having 2 different drivers
> of the same class with different dependenci
23/07/2020 19:00, Stephen Hemminger:
> On Thu, 23 Jul 2020 17:13:17 +0500
> Sarosh Arif wrote:
>
> > Since this script has no maintainer who is responsible for providing ACK or
> > NAK on the patches related to this script?
> >
> > On Tue, Jun 2, 2020 at 12:39 PM Sarosh Arif wrote:
> >
> > > C
On Thu, Jul 23, 2020 at 10:10 PM Parav Pandit wrote:
>
> From: Thomas Monjalon
>
> Define each sub-directory on its own line ended with a comma,
> and use a simple indent.
>
> Signed-off-by: Thomas Monjalon
> ---
> drivers/meson.build | 24 +---
> 1 file changed, 13 insertio
On 23-Jul-20 3:48 PM, wangyunjian wrote:
From: Yunjian Wang
Currently, we will create new user mem map entry for the same memory
segment, but in fact it has already been added to the user mem maps.
It's not necessary to create it twice.
To resolve the issue, add support to remove the same entr
This commit fixes a potential race condition in the tests
where the lcore running a service would increment a counter
that was already reset by the test-suite thread. The resulting
race-condition incremented value could cause CI failures, as
indicated by DPDK's CI.
This patch fixes the race-condit
This commit adds a new experimental API which allows the user
to retrieve the active state of an lcore. Knowing when the service
lcore is completed its polling loop can be useful to applications
to avoid race conditions when e.g. finalizing statistics.
The service thread itself now has a variable
On Fri, Jul 24, 2020 at 9:06 AM Maxime Coquelin
wrote:
> On 7/24/20 6:55 AM, Wang, Yinan wrote:
> > Hi Maxime,
> >
> > The performance drop issue can be fixed, thanks!
> > The multi-queues interrupt issue still exist w/ this patch set.
>
> Thanks for the test report, so that's only half good.
> I'
> -Original Message-
> From: Dybkowski, AdamX
> Sent: Friday, July 24, 2020 12:58 PM
> To: Trahe, Fiona ; dev@dpdk.org; akhil.go...@nxp.com
> Subject: RE: [PATCH] common/qat: fix uninitialized variable bug
>
> > -Original Message-
> > From: Trahe, Fiona
> > Sent: Friday, 24 Ju
There are a lot of per virtq operations in the live migration
handling.
Before the driver support for queue update, when a virtq was not valid,
all the LM handling was terminated.
But now, when the driver supports queue update, the virtq can be invalid
as legal stage.
Skip invalid virtq in LM ha
> -Original Message-
> From: Trahe, Fiona
> Sent: Friday, 24 July, 2020 13:55
> To: Dybkowski, AdamX ; dev@dpdk.org;
> akhil.go...@nxp.com
> Cc: Trahe, Fiona
> Subject: RE: [PATCH] common/qat: fix uninitialized variable bug
>
>
>
> > -Original Message-
> > From: Dybkowski, Adam
> -Original Message-
> From: Dybkowski, AdamX
> Sent: Friday, July 24, 2020 10:40 AM
> To: dev@dpdk.org; Trahe, Fiona ; akhil.go...@nxp.com
> Cc: Dybkowski, AdamX
> Subject: [PATCH] common/qat: fix uninitialized variable bug
>
> This patch fixes the uninitialized variable bug in QAT P
>-Original Message-
>From: Power, Ciara
>Sent: Friday 24 July 2020 12:21
>To: Laatz, Kevin
>Cc: dev@dpdk.org; Richardson, Bruce ;
>tho...@monjalon.net; Power, Ciara
>Subject: [PATCH v3] doc: add more detail to telemetry guides
>
>This patch adds examples to the Telemetry HowTo guide, t
Hi Thomas,
Thanks for the review.
I have addressed your comments in the v3 patch, with one exception mentioned
below.
>[...]
>> + * List all commands.
>> +
>> + .. code-block:: console
>
>I think you can achieve the same result as code-block with adding double
>colons (::) at the end o
This patch adds examples to the Telemetry HowTo guide, to demonstrate
commands that use parameters. The programmer's guide is also modified to
include details on writing a callback function for a new command.
Signed-off-by: Ciara Power
---
v3:
- Replaced direct code examples with generic examp
On Thu, Jul 23, 2020 at 11:09:03PM +0300, Parav Pandit wrote:
> From: Thomas Monjalon
>
> Drivers dependencies are evaluated in the order defined per
> their parent directory (also called class).
> This strict ordering prevent from having 2 different drivers
> of the same class with different dep
This patch set replaces the NITROX PMD specific test suite with generic
test suite and adds support for AES-GCM and cipher only offload.
Nagadheeraj Rottela (3):
test/crypto: replace NITROX PMD specific test suite
crypto/nitrox: support AES-GCM
crypto/nitrox: support cipher only crypto opera
This patch adds AES-GCM AEAD algorithm.
Signed-off-by: Nagadheeraj Rottela
---
doc/guides/cryptodevs/features/nitrox.ini | 3 +
doc/guides/cryptodevs/nitrox.rst | 4 +
drivers/crypto/nitrox/nitrox_sym.c| 82 +++-
.../crypto/nitrox/nitrox_sym_capabilities.c
Replace NITROX PMD specific tests with generic test suite.
Signed-off-by: Nagadheeraj Rottela
---
app/test/test_cryptodev.c | 18 +-
1 file changed, 1 insertion(+), 17 deletions(-)
diff --git a/app/test/test_cryptodev.c b/app/test/test_cryptodev.c
index 70bf6fe2c..162134a5c 1006
This patch adds cipher only crypto operation support.
Signed-off-by: Nagadheeraj Rottela
---
doc/guides/cryptodevs/nitrox.rst | 2 -
drivers/crypto/nitrox/nitrox_sym.c| 3 +
drivers/crypto/nitrox/nitrox_sym_reqmgr.c | 189 --
3 files changed, 143 insertio
On Thu, Jul 23, 2020 at 11:09:02PM +0300, Parav Pandit wrote:
> From: Thomas Monjalon
>
> Define each sub-directory on its own line ended with a comma,
> and use a simple indent.
>
> Signed-off-by: Thomas Monjalon
> ---
> drivers/meson.build | 24 +---
> 1 file changed, 13
This patch adds required bit to handle VF FLR
indication from Management FW (MFW) of the device
With that VFs were able to load in VM (VF attached as PCI
passthrough to the guest VM) followed by FLR successfully
Updated the docs/guides with the feature support
Signed-off-by: Manish Chopra
Signe
This patch configures VFs with random mac if no MAC is
provided by the PF/bulletin. This also adds required bulletin
APIs by PF-PMD driver to communicate LINK properties/changes to
the VFs through bulletin update mechanism.
With these changes, VF-PMD instance is able to run
fastpath over PF-PMD dr
This patch adds necessary infrastructure support (required to handle
messages from VF and sending ramrod on behalf of VF's configuration
request from alarm handler context) to start/load the VF-PMD driver
instance on top of PF-PMD driver instance.
Signed-off-by: Manish Chopra
Signed-off-by: Igor
Based on number of VFs enabled at PCI, PF-PMD driver instance
enables/configures those VFs from hardware perspective, such
that in later patches they could get required HW access to
communicate with PFs for slowpath configuration and run the
fastpath themsleves.
This patch also add two new qede IO
This patch defines various PCI config space access APIs
in order to read and find IOV specific PCI capabilities.
With these definitions implemented, it enables the base
driver to do SR-IOV specific initialization and HW specific
configuration required from PF-PMD driver instance.
Signed-off-by: M
By adding generic API, this patch removes individual
functions/defines implemented by drivers to find PCI
extended capability.
Signed-off-by: Manish Chopra
Signed-off-by: Igor Russkikh
---
drivers/bus/pci/pci_common.c | 42 ++
drivers/bus/pci/rte_bus_pci.h
Hi,
This series adds SR-IOV PF pmd driver support to have VF pmd
driver work over PF pmd driver instances in order to run the
adapter completely under DPDK environment for one of the use
cases like ovs-dpdk.
This is very initial bring-up with following testing covered -
* Enable/Disable SR-IOV V
> -Original Message-
> From: dev On Behalf Of Jeff Guo
> Sent: Friday, July 24, 2020 5:55 PM
> To: Wang, ShougangX ; dev@dpdk.org
> Cc: Xing, Beilei ; Yang, Qiming
> ; sta...@dpdk.org
> Subject: Re: [dpdk-dev] [PATCH v6] net/i40e: fix incorrect hash look up table
>
> Acked-by: Jeff Guo
> -Original Message-
> From: Guo, Jia
> Sent: Friday, July 24, 2020 5:52 PM
> To: Yigit, Ferruh ; Zhang, Qi Z
> ;
> Xing, Beilei ; Wu, Jingjing
> Cc: dev@dpdk.org; Guo, Junfeng ; Su, Simei
>
> Subject: RE: [dpdk-dev] [dpdk-dev v1] net/iavf: delete unsupported rss types
>
> hi, ferruh
Acked-by: Jeff Guo
On 7/24/2020 5:38 PM, Shougang Wang wrote:
The hash look up table (LUT) is managed by global register but it is not
initialized when RSS is disabled. Once user wants to enable RSS during
runtime, the LUT will not be initialized.
This patch fixes the issue by initializing the
hi, ferruh
Fixes: 7be10c3004be ("net/iavf: add RSS configuration for VF")
Thanks for your info, the above fixed line should be added, and need I sent a
new version or you could help to add it when merge it?
Best regards,
Jeff Guo
-Original Message-
From: Ferruh Yigit
Sent: Friday, Ju
The hash look up table (LUT) is managed by global register but it is not
initialized when RSS is disabled. Once user wants to enable RSS during
runtime, the LUT will not be initialized.
This patch fixes the issue by initializing the LUT whatever RSS enabled
or not.
Fixes: feaae285b342 ("net/i40e:
This patch fixes the uninitialized variable bug in QAT PMD.
Fixes: 9f27a860dc16 ("crypto/qat: move generic qp function to qp file")
Signed-off-by: Adam Dybkowski
---
drivers/common/qat/qat_qp.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/common/qat/qat_qp.c b/dri
When we compile PMD with CFLAGS set to -O -g, build fails because of
uninitialized error. This patch fixes it.
Fixes: 1e46b3962620 ("net/bnxt: fill cfa action in Tx descriptor")
Bugzilla ID: 509
Cc: step...@networkplumber.org
Signed-off-by: Ajit Khaparde
Reviewed-by: Somnath Kotur
Reviewed-by:
From: Somnath Kotur
No need to access rx_cfa_code, cfa_code_map from the VF-Rep functions
anymore.
Fixes: 322bd6e70272 ("net/bnxt: add port representor infrastructure")
Reviewed-by: Venkat Duvvuru
Signed-off-by: Somnath Kotur
Reviewed-by: Ajit Khaparde
---
drivers/net/bnxt/bnxt.h | 1
The if condition in bnxt_restore_mac_filters needs to check for
the result of logical AND. But it was not doing it resulting in
an incorrect check.
Fixes: b02f1573cd07 ("net/bnxt: restore MAC filters during reset recovery")
Signed-off-by: Ajit Khaparde
---
drivers/net/bnxt/bnxt_ethdev.c | 2 +-
From: Mike Baucom
Moved setting the refcnt for shadow tcam and table entries to the
allocation path only. The insert can be called multiple times for
updates and was resetting the refcnt to 1 each time. Now multiple
insertion/modifications will not change the reference count.
Signed-off-by: Mi
From: Venkat Duvvuru
Truflow stack adds VFR to VF and VF to VFR conduits when VF
representor is created. However, in the ingress direction the
VF's fw rules conflict with Truflow rules, resulting in not hitting
the Truflow VFR rules. To fix this, fw is going to remove it’s
VF rules when vf repres
1 - 100 of 132 matches
Mail list logo
