Windows compilation gives us a splat:
In file included from ../drivers/dma/idxd/idxd_pci.c:10:
In file included from ..\drivers\dma\idxd/idxd_internal.h:11:
..\drivers\dma\idxd/idxd_hw_defs.h:46:21: error: expected member name or
';' after declaration specifiers
uint16_t __reserved[13];
On Fri, Oct 22, 2021 at 8:08 PM Thomas Monjalon wrote:
>
> 20/10/2021 18:29, Kevin Laatz:
> > This patchset adds a dmadev driver and associated documentation to support
> > Intel Data Streaming Accelerator devices. This driver is intended to
> > ultimately replace the current IDXD part of the IOAT
On Wed, Oct 20, 2021 at 5:48 PM Xueming Li wrote:
> + kvlist = rte_kvargs_parse(args, NULL);
> + if (kvlist == NULL) {
> + printf("rte_devargs_parse(%s) %s_str: %s not parsed\n",
> + devargs, layer, args);
> + return -1;
> + }
> +
In the function "eth_dev_fp_ops_reset", a structure assignment
operation is used to reset one queue's callback functions, etc., but
it is not thread safe.
The structure assignment is not atomic, a lot of instructions will
be generated. Right now, since not all the fields are needed, the
fields in
When stopping a port, the data path Tx and Rx burst functions should
be stopped firstly conventionally. Then the dummy functions are used
to replace the callback functions provided by the PMD.
When the application stops a port without or before stopping the data
path handling. The dummy functions
2021-10-23 02:33 (UTC+0300), Dmitry Kozlyuk:
> 2021-10-23 02:19 (UTC+0530), Harman Kalra:
> [...]
> > /**
> > * Function is to check if the kernel module(like, vfio, vfio_iommu_type1,
> > * etc.) loaded.
> > diff --git a/lib/eal/freebsd/eal.c b/lib/eal/freebsd/eal.c
> > index 56a60f13e9..535ea
2021-10-23 02:19 (UTC+0530), Harman Kalra:
> Implementing alarm cleanup routine, where the memory allocated
> for interrupt instance can be freed.
>
> Signed-off-by: Harman Kalra
> ---
> lib/eal/common/eal_private.h | 11 +++
> lib/eal/freebsd/eal.c| 1 +
> lib/eal/freebsd/eal_a
2021-10-23 02:19 (UTC+0530), Harman Kalra:
> Moving interrupt handle structure definition inside the c file
> to make its fields totally opaque to the outside world.
>
> Dynamically allocating the efds and elist array os intr_handle
> structure, based on size provided by user. Eg size can be
> MSI
2021-10-23 02:19 (UTC+0530), Harman Kalra:
> Making changes to the interrupt framework to use interrupt handle
> APIs to get/set any field.
>
> Signed-off-by: Harman Kalra
> ---
> lib/eal/freebsd/eal_interrupts.c | 112
> lib/eal/linux/eal_interrupts.c | 303 +++---
2021-10-23 02:19 (UTC+0530), Harman Kalra:
> Prototype/Implement get set APIs for interrupt handle fields.
> User wont be able to access any of the interrupt handle fields
> directly while should use these get/set APIs to access/manipulate
> them.
>
> Internal interrupt header i.e. rte_eal_interru
20/10/2021 09:03, Olivier Matz:
> On Mon, Oct 18, 2021 at 05:29:35PM +0300, Dmitry Kozlyuk wrote:
> > 2021-10-18 21:58 (UTC+0800), zhihongx.p...@intel.com:
> > > From: Zhihong Peng
> > >
> > > Malloc cl in the cmdline_stdin_new function, so release in the
> > > cmdline_stdin_exit function is logi
> Dmitry Kozlyuk (2):
> cmdline: make struct cmdline opaque
> cmdline: make struct rdline opaque
Applied, thanks.
When mempool had been created with RTE_MEMPOOL_F_NO_IOVA_CONTIG flag
but later populated with valid IOVA, RTE_MEMPOOL_F_NON_IO was unset,
while it should be kept. The unit test did not catch this
because rte_mempool_populate_default() it used was populating
with RTE_BAD_IOVA.
Keep setting RTE_MEMP
The rule for indentation in Meson in DPDK is 4 spaces.
Any tab should be flagged as an issue, let's extend the check and fix
existing offenders.
Fixes: 4ad4b20a7905 ("drivers: change indentation in build files")
Fixes: 2457705e6474 ("crypto/cnxk: add driver skeleton")
Fixes: 634b73104482 ("app/te
Implementing alarm cleanup routine, where the memory allocated
for interrupt instance can be freed.
Signed-off-by: Harman Kalra
---
lib/eal/common/eal_private.h | 11 +++
lib/eal/freebsd/eal.c| 1 +
lib/eal/freebsd/eal_alarm.c | 7 +++
lib/eal/linux/eal.c | 1 +
Moving interrupt handle structure definition inside the c file
to make its fields totally opaque to the outside world.
Dynamically allocating the efds and elist array os intr_handle
structure, based on size provided by user. Eg size can be
MSIX interrupts supported by a PCI device.
Signed-off-by:
Updating the interrupt testsuite to make use of interrupt
handle get set APIs.
Signed-off-by: Harman Kalra
---
app/test/test_interrupts.c | 163 ++---
1 file changed, 98 insertions(+), 65 deletions(-)
diff --git a/app/test/test_interrupts.c b/app/test/test_interr
Making changes to the interrupt framework to use interrupt handle
APIs to get/set any field.
Signed-off-by: Harman Kalra
---
lib/eal/freebsd/eal_interrupts.c | 112
lib/eal/linux/eal_interrupts.c | 303 +++
2 files changed, 268 insertions(+), 147 deleti
Prototype/Implement get set APIs for interrupt handle fields.
User wont be able to access any of the interrupt handle fields
directly while should use these get/set APIs to access/manipulate
them.
Internal interrupt header i.e. rte_eal_interrupt.h is rearranged,
as APIs defined are moved to rte_in
Moving struct rte_intr_handle as an internal structure to
avoid any ABI breakages in future. Since this structure defines
some static arrays and changing respective macros breaks the ABI.
Eg:
Currently RTE_MAX_RXTX_INTR_VEC_ID imposes a limit of maximum 512
MSI-X interrupts that can be defined for
22/10/2021 18:11, Gowrishankar Muthukrishnan:
> Add telemetry endpoint for mempool info.
>
> Signed-off-by: Gowrishankar Muthukrishnan
> Reviewed-by: Bruce Richardson
Applied, thanks.
11/04/2021 20:51, Medvedkin, Vladimir:
> On 08/04/2021 18:56, Stephen Hemminger wrote:
> >> app/test/test_thash.c | 468 +++-
> >> lib/librte_hash/meson.build | 3 +-
> >> lib/librte_hash/rte_thash.c | 637
> >>
>
20/10/2021 13:25, Bruce Richardson:
> This set enables dmadev library to be built on windows, and then does some
> cleanup of the lib/meson.build file to remove the separate listing of
> libraries
> for windows builds - instead having library disabling done via the normal
> method
> of each libra
On Fri, Oct 22, 2021 at 5:57 AM Ferruh Yigit wrote:
>
> Jumbo offload is no more announced as capability, and
> 'DEV_RX_OFFLOAD_JUMBO_FRAME' offload flag is removed.
>
> This patch is also removing 'Jumbo frame' feature from documentation.
>
> Fixes: b563c1421282 ("ethdev: remove jumbo offload fla
Provided further description within documentation regarding
the RXP to CRSpace changes.
Signed-off-by: Francis Kelly
---
doc/guides/regexdevs/mlx5.rst | 2 +-
doc/guides/rel_notes/release_21_11.rst | 3 +++
2 files changed, 4 insertions(+), 1 deletion(-)
diff --git a/doc/guides/regexde
From: Ady Agbarih
When mlx5_regex_qp_setup() is called make sure
the provided QP is not already setup.
Signed-off-by: Ady Agbarih
---
drivers/regex/mlx5/mlx5_regex_control.c | 6 ++
1 file changed, 6 insertions(+)
diff --git a/drivers/regex/mlx5/mlx5_regex_control.c
b/drivers/regex/mlx5
The mlx5_rxp_csrs.h file has been deprecated as
its contents has now been moved to FW.
Signed-off-by: Francis Kelly
---
drivers/regex/mlx5/mlx5_regex.c | 1 -
drivers/regex/mlx5/mlx5_regex_control.c | 1 -
drivers/regex/mlx5/mlx5_rxp.c | 1 -
drivers/regex/mlx5/mlx5_rxp.h
From: Ady Agbarih
The number of QPs for a device are setup during the
configuration phase, when the user calls
rte_regexdev_configure(). The mlx5 regex driver then
pre-allocates QPs, however those QPs are not
setup/ready for sending jobs. The user has to configure
each QP using rte_regexdev_
From: Ady Agbarih
Remove the set/query regexp register commands from devx.
Remove functions that used these commands.
Remove manual rules programming.
Signed-off-by: Ady Agbarih
---
drivers/regex/mlx5/mlx5_regex.c | 28 --
drivers/regex/mlx5/mlx5_regex.h | 4 -
drivers/regex/mlx5/
14/10/2021 11:53, Kevin Laatz:
> This patchset first adds some additional command line options to the
> existing ioatfwd application to enhance usability.
Please could you rebase?
I see some errors about max_rx_pkt_len and DEV_RX_OFFLOAD_JUMBO_FRAME.
Cc Ferruh for help if needed.
From: Ori Kam
When stopping the device we should release all
data allocated.
This commit add this cleanup logic.
Signed-off-by: Ori Kam
---
drivers/regex/mlx5/mlx5_regex.c | 14 ++
drivers/regex/mlx5/mlx5_regex.h | 1 +
drivers/regex/mlx5/mlx5_regex_control.c | 20
From: Ady Agbarih
Remove the engine start/stop DevX commands,
as they have been deprecated and moved to FW.
Signed-off-by: Ady Agbarih
---
drivers/regex/mlx5/mlx5_regex.c | 5
drivers/regex/mlx5/mlx5_regex.h | 2 --
drivers/regex/mlx5/mlx5_regex_devx.c | 42 ---
From: Ady Agbarih
Add patch for programming the regex database through rof file,
using the firmware instead of manually through the software.
No need to setup the DB anymore, the regex-daemon is responsible
for that always.
In the new flow the regex driver only has to program rof rules
by using s
From: Ady Agbarih
This patch modifies the SET_REGEXP_PARAMS devx command as follows:
Remove DB setup devx command. The command is no longer needed
in DPDK, it will always be invoked by the regex-daemon.
Add new devx command, for programming rof rules for a specific
engine. The command
From: Ady Agbarih
Update PRM hca capabilities definitions as follows:
regexp_version field added - specifies whether BF2 or BF3
regexp field removed
regexp_params field moved
regexp_log_crspace_size field removed
regexp_mmo added - specifies if using regex mmo wqe is supported
Allow regex only i
18/10/2021 14:38, Conor Walsh:
> This patchset adds a dmadev driver and associated documentation to support
> Intel QuickData Technology devices, part of the Intel I/O Acceleration
> Technology (Intel I/OAT). This driver is intended to ultimately replace
> the current IOAT part of the IOAT rawdev d
20/10/2021 18:29, Kevin Laatz:
> This patchset adds a dmadev driver and associated documentation to support
> Intel Data Streaming Accelerator devices. This driver is intended to
> ultimately replace the current IDXD part of the IOAT rawdev driver.
Applied (with notified fix), thanks.
18/10/2021 11:55, Thomas Monjalon:
> The prefix (before the colon) of the title is lowercase.
> The check of uppercase/lowercase in the commit title
> was supposed to apply after the colon,
> but some greps were not limited to the exact word.
> So in the case of "test/dma: add basic dmadev instance
On 10/22/2021 12:20 PM, Andrew Rybchenko wrote:
Use UINT64_C() macro instead.
Signed-off-by: Andrew Rybchenko
Reviewed-by: Ferruh Yigit
Applied to dpdk-next-net/main, thanks.
This patch replaces the mixed QAT symmetric and asymmetric
support implementation by separate files with shared or
individual implementation for specific QAT generation.
Signed-off-by: Arek Kusztal
Signed-off-by: Fan Zhang
Signed-off-by: Kai Ji
---
drivers/common/qat/meson.build
This patch adds the symmetric and asymmetric crypto data
structure and function prototypes for different QAT
generations.
Signed-off-by: Arek Kusztal
Signed-off-by: Fan Zhang
Signed-off-by: Kai Ji
---
drivers/crypto/qat/README |7 -
drivers/crypto/qat/meson.build
This patch unifies the QAT symmetric and asymmetric device
private data structures and functions.
Signed-off-by: Arek Kusztal
Signed-off-by: Fan Zhang
Signed-off-by: Kai Ji
---
drivers/common/qat/meson.build | 2 +-
drivers/common/qat/qat_common.c | 15 ++
drivers/common/qat/qat_
This patch replaces the mixed QAT compression support
implementation by separate files with shared or individual
implementation for specific QAT generation.
Signed-off-by: Adam Dybkowski
Signed-off-by: Arek Kusztal
Signed-off-by: Fan Zhang
Signed-off-by: Kai Ji
---
drivers/common/qat/meson.bu
This patch adds the compression data structure and function
prototypes for different QAT generations.
Signed-off-by: Adam Dybkowski
Signed-off-by: Arek Kusztal
Signed-off-by: Fan Zhang
Signed-off-by: Kai Ji
---
drivers/common/qat/dev/qat_dev_gen1.c | 2 -
.../common/qat/qat_adf/icp_
This patch replaces the mixed QAT queue pair configuration
implementation by separate files with shared or individual
implementation for specific QAT generation.
Signed-off-by: Arek Kusztal
Signed-off-by: Fan Zhang
Signed-off-by: Kai Ji
---
drivers/common/qat/dev/qat_dev_gen1.c | 190 +
This patch adds the queue pair data structure and function
prototypes for different QAT generations.
Signed-off-by: Fan Zhang
---
drivers/common/qat/qat_qp.c | 3 ++
drivers/common/qat/qat_qp.h | 103
2 files changed, 71 insertions(+), 35 deletions(-)
diff
This patch replaces the mixed QAT device configuration
implementation by separate files with shared or
individual implementation for specific QAT generation.
Signed-off-by: Arek Kusztal
Signed-off-by: Fan Zhang
Signed-off-by: Kai Ji
---
drivers/common/qat/dev/qat_dev_gen1.c | 66 +
dr
This patch adds the data structure and function prototypes for
different QAT generations.
Signed-off-by: Arek Kusztal
Signed-off-by: Fan Zhang
Signed-off-by: Kai Ji
---
drivers/common/qat/qat_common.h | 14 --
drivers/common/qat/qat_device.c | 4
drivers/common/qat/qat_device
This patchset introduces new qat driver structure and updates
existing symmetric crypto qat PMD.
The purpose of the change is to isolate QAT generation specific
implementations from one to another.
It is expected the changes to the specific generation driver
code does minimum impact to other gene
On 10/22/2021 8:30 AM, Andrew Rybchenko wrote:
The macros RTE_BIT32 and RTE_BIT64 are used to replace single bit masks.
Do not switch VLAN offload flags since type is not fixed size.
Signed-off-by: Andrew Rybchenko
Reviewed-by: Ferruh Yigit
Applied to dpdk-next-net/main, thanks.
On Fri, 22 Oct 2021, 16:58 Andrew Rybchenko,
wrote:
> On 10/22/21 2:03 PM, Ferruh Yigit wrote:
> > Add 'RTE_ETH' namespace to all enums & macros in a backward compatible
> > Add 'RTE_ETH' namespace to all enums & macros in a backward compatible
>
> LGTM except two lines duplicated above.
>
> > wa
On Fri, 22 Oct 2021, 16:58 Andrew Rybchenko, mailto:andrew.rybche...@oktetlabs.ru>> wrote:
On 10/22/21 2:03 PM, Ferruh Yigit wrote:
> Add 'RTE_ETH' namespace to all enums & macros in a backward compatible
> Add 'RTE_ETH' namespace to all enums & macros in a backward compatible
Add telemetry endpoint for mempool info.
Signed-off-by: Gowrishankar Muthukrishnan
Reviewed-by: Bruce Richardson
---
v3:
- added explicit telemetry dependency in meson
---
lib/mempool/meson.build | 2 +-
lib/mempool/rte_mempool.c | 84 +++
2 files changed
On 10/22/2021 2:47 PM, Ferruh Yigit wrote:
On 10/22/2021 2:26 PM, Konstantin Ananyev wrote:
link bounding auto-test internally creates emulated ethdev.
Some tests change Rx/Tx functions of this emulated device on the fly:
by directly modifying rte_eth_dev fields and without doing stop/start
for
Add telemetry endpoints to cryptodev.
Signed-off-by: Gowrishankar Muthukrishnan
---
Depends-on: patch-19601 ("cryptodev: add telemetry callbacks")
Depends-on: patch-19915 ("cryptodev: add telemetry endpoint for cryptodev
capabilities")
v7:
- compilation issue in CI fixed
---
.../crypto/cnxk/c
On Tue, Oct 19, 2021 at 21:36 Jerin Jacob wrote:
> On Wed, Oct 20, 2021 at 12:38 AM Thomas Monjalon wrote:
> >
> > 19/10/2021 20:14, jer...@marvell.com:
> > > Definition of Dataplane Workload Accelerator
> > >
> > > Dataplane Workload Accelerator(DWA)
20/10/2021 18:29, Kevin Laatz:
> --- /dev/null
> +++ b/drivers/dma/idxd/version.map
> @@ -0,0 +1,3 @@
> +DPDK_21 {
> + local: *;
> +};
Should be DPDK_22
Will fix while merging.
On 10/22/2021 4:20 PM, Ferruh Yigit wrote:
On 10/22/2021 3:10 PM, Jiang, YuX wrote:
-Original Message-
From: dev On Behalf Of Ferruh Yigit
Sent: 2021年10月22日 20:57
To: Wang, Haiyue ; Xing, Beilei
; Wu, Jingjing ; Yang, Qiming
; Zhang, Qi Z ; Hyong Youb
Kim ; Michal Krawczyk ; Andrew
Rybc
On 10/22/2021 3:07 PM, Ciara Loftus wrote:
Commit 1bb4a528c41f ("ethdev: fix max Rx packet length") clarified the
expected usage of the max_rx_pktlen and max_mtu values and implemented some
extra checks on these values to ensure they are sane. After this,
the AF_XDP PMD fails to initialise. The v
22/10/2021 17:07, Stephen Hemminger:
> On Fri, 22 Oct 2021 15:43:58 +0200
> Thomas Monjalon wrote:
>
> > 20/10/2021 23:42, Stephen Hemminger:
> > > +++ b/lib/pcapng/meson.build
> > > +version = 1
> >
> > What is the meaning of this version in meson? Is it used somewhere?
>
> No just copy/past
On 10/22/2021 3:10 PM, Jiang, YuX wrote:
-Original Message-
From: dev On Behalf Of Ferruh Yigit
Sent: 2021年10月22日 20:57
To: Wang, Haiyue ; Xing, Beilei
; Wu, Jingjing ; Yang, Qiming
; Zhang, Qi Z ; Hyong Youb
Kim ; Michal Krawczyk ; Andrew
Rybchenko ; Somnath Kotur
Cc: Yigit, Ferruh ; d
On Fri, 22 Oct 2021 15:43:58 +0200
Thomas Monjalon wrote:
> 20/10/2021 23:42, Stephen Hemminger:
> > +++ b/lib/pcapng/meson.build
> > +version = 1
>
> What is the meaning of this version in meson? Is it used somewhere?
>
>
>
No just copy/paste from some other meson file.
> -Original Message-
> From: dev On Behalf Of Ferruh Yigit
> Sent: 2021年10月22日 20:57
> To: Wang, Haiyue ; Xing, Beilei
> ; Wu, Jingjing ; Yang, Qiming
> ; Zhang, Qi Z ; Hyong Youb
> Kim ; Michal Krawczyk ; Andrew
> Rybchenko ; Somnath Kotur
>
> Cc: Yigit, Ferruh ; dev@dpdk.org
> Subject:
Commit 1bb4a528c41f ("ethdev: fix max Rx packet length") clarified the
expected usage of the max_rx_pktlen and max_mtu values and implemented some
extra checks on these values to ensure they are sane. After this,
the AF_XDP PMD fails to initialise. The value for max_rx_pktlen which
represents the m
On 10/22/2021 2:47 PM, Ferruh Yigit wrote:
On 10/22/2021 2:26 PM, Konstantin Ananyev wrote:
link bounding auto-test internally creates emulated ethdev.
Some tests change Rx/Tx functions of this emulated device on the fly:
by directly modifying rte_eth_dev fields and without doing stop/start
for
20/10/2021 23:42, Stephen Hemminger:
> This patch set is a more complete version of the the enhanced
> packet capture support described last year.
>
> The new capture library and utility are:
> - faster avoids lots of extra I/O, does bursting, etc.
> - gives more information (multiple ports, q
On 10/22/2021 2:26 PM, Konstantin Ananyev wrote:
link bounding auto-test internally creates emulated ethdev.
Some tests change Rx/Tx functions of this emulated device on the fly:
by directly modifying rte_eth_dev fields and without doing stop/start
for these devices.
As now ethdev uses rte_eth_fp
20/10/2021 23:42, Stephen Hemminger:
> +++ b/lib/pcapng/meson.build
> +version = 1
What is the meaning of this version in meson? Is it used somewhere?
On 18/10/2021 3:16 PM, Miao Li wrote:
This patch implements rte_power_monitor API in virtio PMD to reduce
power consumption when no packet come in. According to current semantics
of power monitor, this commit adds a callback function to decide whether
aborts the sleep by checking current value
On Fri, Oct 22, 2021 at 5:30 PM Elena Agostini wrote:
>
> On Tue, Oct 19, 2021 at 21:36 Jerin Jacob wrote:
>
>
>
> > On Wed, Oct 20, 2021 at 12:38 AM Thomas Monjalon
> > wrote:
>
> > >
>
> > > 19/10/2021 20:14, jer...@marvell.com:
>
> > > > Definition of Dataplane Workload Accelerator
>
> > > >
https://bugs.dpdk.org/show_bug.cgi?id=833
Bug ID: 833
Summary: link_bonding_autotest fails on subsequent runs
Product: DPDK
Version: unspecified
Hardware: All
OS: All
Status: UNCONFIRMED
Severity: minor
On 10/22/2021 2:21 PM, Ferruh Yigit wrote:
On 10/22/2021 11:18 AM, Andrew Rybchenko wrote:
From: Ivan Ilchenko
rte_eth_dev_configure() always sets MTU to either dev_conf.rxmode.mtu
or RTE_ETHER_MTU if application doesn't provide the value.
So, there is no point to allow rte_eth_dev_set_mtu() b
link bounding auto-test internally creates emulated ethdev.
Some tests change Rx/Tx functions of this emulated device on the fly:
by directly modifying rte_eth_dev fields and without doing stop/start
for these devices.
As now ethdev uses rte_eth_fp_ops[] for fast-path functions, these
direct change
On 10/22/2021 11:18 AM, Andrew Rybchenko wrote:
From: Ivan Ilchenko
rte_eth_dev_configure() always sets MTU to either dev_conf.rxmode.mtu
or RTE_ETHER_MTU if application doesn't provide the value.
So, there is no point to allow rte_eth_dev_set_mtu() before since
set value will be overwritten on
From: Ivan Ilchenko
Link update callback reports speed/duplex based on data
filled on device initialization. This is wrong in case of
VIRTIO_NET_F_SPEED_DUPLEX is negotiated since link could
be down at this time. Fix this function to actually
update the HW data in this case with respect to the fa
When creating internal transfer flow on root table with lowerest
priority, the flow was created with max UINT32_MAX priority. It is wrong
since the flow is created in kernel and max priority supported is 16.
This patch fixes this by adding internal flow check.
Fixes: 5f8ae44dd454 ("net/mlx5: enl
Verbs API does not support Infiniband device port number larger 255 by
design. To support more representors on a single Infiniband device DevX
API should be engaged.
While creating Send Queue (SQ) object with Verbs API, the PMD assigned
IB device port attribute and kernel created the default miss
Verbs API doesn't support device port number larger than 255 by design.
To support more VF or SubFunction port representors, forces DevX API
check when max Verbs device link ports larger than 255.
Signed-off-by: Xueming Li
Acked-by: Viacheslav Ovsiienko
---
drivers/net/mlx5/linux/mlx5_os.c | 1
Extends txq flow pattern to support both hairpin and regular txq.
Signed-off-by: Xueming Li
Acked-by: Viacheslav Ovsiienko
---
drivers/net/mlx5/mlx5_flow_dv.c | 16
1 file changed, 8 insertions(+), 8 deletions(-)
diff --git a/drivers/net/mlx5/mlx5_flow_dv.c b/drivers/net/mlx5/
IB spec doesn't allow 255 ports on a single HCA, port number of 256 was
cast to u8 value 0 which invalid to ibv_query_port()
This patch invokes Netlink api to query port state when port number
greater than 255.
Signed-off-by: Xueming Li
Acked-by: Viacheslav Ovsiienko
---
drivers/net/mlx5/linux
To detect number flow Verbs flow priorities, PMD try to create Verbs
flows in different priority. While Verbs is not designed to support
ports larger than 255.
When DevX supported by kernel driver, 16 Verbs priorities must be
supported, no need to create Verbs flows.
Signed-off-by: Xueming Li
Ac
Introduce netlink API to get rdma port state.
Port state is restrieved based on RDMA device name and port index.
Signed-off-by: Xueming Li
Acked-by: Viacheslav Ovsiienko
---
drivers/common/mlx5/linux/meson.build | 2 +
drivers/common/mlx5/linux/mlx5_nl.c | 136 +++---
d
This patch set supports representor number of a PF to be more than 255.
CX6 and current OFED driver supports maxium 512 SFs. CX5 supports max 255 SFs.
v2:
- fixed FDB root table flow priority
- add error check to Netlink port state API
- commit log update and other minor fixes
v3:
- fix compil
For egress packet on representor, the vport ID in transport domain
is E-Switch manager vport ID since representor shares resources of
E-Switch manager. E-Switch manager vport ID and Tx queue internal device
index are used to match representor egress packet.
This patch adds flow item port ID match
On 10/22/2021 12:28 PM, Andrew Rybchenko wrote:
On 10/22/21 2:03 PM, Ferruh Yigit wrote:
Add 'RTE_ETH' namespace to all enums & macros in a backward compatible
Add 'RTE_ETH' namespace to all enums & macros in a backward compatible
LGTM except two lines duplicated above.
Thanks Andrew, I wil
Add telemetry endpoints to cryptodev.
Signed-off-by: Gowrishankar Muthukrishnan
---
Depends-on: patch-19601 ("cryptodev: add telemetry callbacks")
Depends-on: patch-19915 ("cryptodev: add telemetry endpoint for cryptodev
capabilities")
v6:
- checkpatch fixes.
---
.../crypto/cnxk/cnxk_cryptode
After DEV_RX_OFFLOAD_JUMBO_FRAME flag removed, drivers give jumbo frame
decisions based on MTU value checks, but some of the checks were wrong
by mistake, causing device initialization to fail, fixing them.
Fixes: b563c1421282 ("ethdev: remove jumbo offload flag")
Signed-off-by: Ferruh Yigit
---
Jumbo offload is no more announced as capability, and
'DEV_RX_OFFLOAD_JUMBO_FRAME' offload flag is removed.
This patch is also removing 'Jumbo frame' feature from documentation.
Fixes: b563c1421282 ("ethdev: remove jumbo offload flag")
Signed-off-by: Ferruh Yigit
Acked-by: Andrew Rybchenko
---
Add telemetry endpoint for cryptodev capabilities.
Signed-off-by: Gowrishankar Muthukrishnan
---
Depends-on: patch-19601 ("cryptodev: add telemetry callbacks")
v3:
- checkpatch fixes.
---
lib/cryptodev/rte_cryptodev.c | 65 +++
1 file changed, 65 insertions(+)
Add telemetry endpoints to cryptodev.
Signed-off-by: Gowrishankar Muthukrishnan
---
Depends-on: patch-19601 ("cryptodev: add telemetry callbacks")
Depends-on: patch-19913 ("cryptodev: add telemetry endpoint for cryptodev
capabilities")
v5:
- endpoint renamed as caps.
---
.../crypto/cnxk/cnxk_
On 19/10/2021 5:38 AM, Xia, Chenbo wrote:
-Original Message-
From: Li, Miao
Sent: Monday, October 18, 2021 10:17 PM
To: dev@dpdk.org
Cc: Xia, Chenbo ; maxime.coque...@redhat.com; Li, Miao
Subject: [PATCH v7 2/5] vhost: implement rte_power_monitor API
This patch defines rte_vhost_powe
Add telemetry endpoint for cryptodev capabilities.
Signed-off-by: Gowrishankar Muthukrishnan
---
Depends-on: patch-19601 ("cryptodev: add telemetry callbacks")
v2:
- renamed endpoint as caps.
---
lib/cryptodev/rte_cryptodev.c | 65 +++
1 file changed, 65 insert
On 10/22/2021 1:23 PM, Andrew Rybchenko wrote:
On 10/22/21 3:17 PM, Ferruh Yigit wrote:
After DEV_RX_OFFLOAD_JUMBO_FRAME flag removed, jumbo frame decision is
given by MTU value checks, but some of the checks were wrong by mistake,
causing device initialization to fail, fixing them.
Also removi
On 10/22/21 3:17 PM, Ferruh Yigit wrote:
> After DEV_RX_OFFLOAD_JUMBO_FRAME flag removed, jumbo frame decision is
> given by MTU value checks, but some of the checks were wrong by mistake,
> causing device initialization to fail, fixing them.
>
> Also removing 'Jumbo frame' feature.
Sorry, but I
After DEV_RX_OFFLOAD_JUMBO_FRAME flag removed, jumbo frame decision is
given by MTU value checks, but some of the checks were wrong by mistake,
causing device initialization to fail, fixing them.
Also removing 'Jumbo frame' feature.
Fixes: b563c1421282 ("ethdev: remove jumbo offload flag")
Signe
On 19/10/2021 5:39 AM, Xia, Chenbo wrote:
-Original Message-
From: Li, Miao
Sent: Monday, October 18, 2021 10:17 PM
To: dev@dpdk.org
Cc: Xia, Chenbo ; maxime.coque...@redhat.com; Li, Miao
Subject: [PATCH v7 3/5] net/vhost: implement rte_power_monitor API
This patch implements rte_pow
Add initial support for baseband telemetry.
Signed-off-by: Tomasz Duszynski
---
v2:
- make bphy telemetry available only on platforms supporting baseband
- use platform types where possible
- remove unused header
drivers/common/cnxk/cnxk_telemetry_bphy.c | 52 +++
drivers/co
On 21/10/2021 5:48 PM, Ferruh Yigit wrote:
On 10/18/2021 3:16 PM, Miao Li wrote:
Since some vdevs like virtio and vhost do not support rxq_info_get and
queue state inquiry, the error return value -ENOTSUP need to be ignored
when queue_stopped cannot get rx queue information and rx queue state.
On 19/10/2021 5:39 AM, Xia, Chenbo wrote:
-Original Message-
From: Li, Miao
Sent: Monday, October 18, 2021 10:17 PM
To: dev@dpdk.org
Cc: Xia, Chenbo ; maxime.coque...@redhat.com; Li, Miao
Subject: [PATCH v7 5/5] examples/l3fwd-power: support virtio/vhost
In l3fwd-power, there is defa
On 10/22/21 2:25 PM, Ferruh Yigit wrote:
> On 10/21/2021 1:43 AM, Thomas Monjalon wrote:
>> 18/10/2021 15:48, Ferruh Yigit:
>>> Removing 'DEV_RX_OFFLOAD_JUMBO_FRAME' offload flag.
>> [...]
>>> --- a/doc/guides/nics/features.rst
>>> +++ b/doc/guides/nics/features.rst
>>> @@ -165,8 +165,7 @@ Jumbo fr
1 - 100 of 155 matches
Mail list logo
