Hi Ferruh,
> -Original Message-
> From: Ferruh Yigit
> Sent: Thursday, May 19, 2022 12:53 AM
> To: Joyce Kong ; Jakub Grajciar
> Cc: Ruifeng Wang ; dev@dpdk.org; nd
>
> Subject: Re: [PATCH v1 1/2] net/memif: add a Rx fast path
>
> On 5/17/2022 11:51 AM, Joyce Kong wrote:
> > For memif
On 5/12/22 14:03, Jerin Jacob wrote:
On Thu, May 12, 2022 at 1:06 PM Andrew Rybchenko
wrote:
Hi Jerin,
Hi Andrew,
On 5/1/22 17:46, jer...@marvell.com wrote:
From: Jerin Jacob
Currently, meter object supports only DSCP based on input color table,
The patch enhance that to support VLAN b
On 5/11/22 04:15, Peng Zhang wrote:
Setting a MTU larger than mbufsize is not supported by the device but
not prohibited by the driver. This change adds a restriction to the
driver to prevent setting an MTU that is too large.
While at it define the minimum MTU in the device information to descri
On 5/12/22 01:08, Konstantin Ananyev wrote:
From: Huisong Li
Starting or stopping a bonded port also starts or stops all active slaves
under the bonded port. If this port is a bonded device, we need to modify
the port status of all slaves.
Fixes: 0e545d3047fe ("app/testpmd: check stopping po
On Thu, May 19, 2022 at 1:25 AM Konstantin Ananyev
wrote:
> 18/05/2022 18:24, David Marchand пишет:
> > On Fri, May 13, 2022 at 12:10 PM Min Hu (Connor) wrote:
> >>
> >>I think net/bonding offer 'API' for APP to use the bonding.
> >> and use the specific PMD as slave device.
> >>The
In the multiple process environment, the subprocess operates on the
shared memory and changes the function pointer of the main process,
resulting in the failure to find the address of the function when main
process releasing, resulting in crash.
Fixes: 319c421f3890 ("net/avf: enable SSE Rx Tx")
Cc
In multi-cores cases for RX timestamp offload, if packets arrive
too fast, aq command to get phc time will be pended.
This patch adds spinlock to fix this issue. To avoid phc time being
frequently overwritten, move related variables to iavf_rx_queue
structure, and each queue will handle timestamp
> -Original Message-
> From: jer...@marvell.com
> Sent: Wednesday, May 18, 2022 11:03 PM
> To: dev@dpdk.org; Nithin Dabilpuram ; Kiran
> Kumar K ; Sunil Kumar Kori
> ; Satha Rao
> Cc: tho...@monjalon.net; david.march...@redhat.com;
> juraj.lin...@pantheon.tech; Ruifeng Wang ;
> jer...@mar
v6 (Andrew Rybchenko):
Minor style changes in patches description
Split FW version get patch to have callbacks reorder seperately
Minor fix in FW version get patch to put callback definition,
assignment and implementation just after device info get
v5:
Use RTE_MIN instead of de
From: Pankaj Gupta
Add VMXNET3 v5 support.
Tested, using testpmd, for different hardware versions on ESXi 7.0
Update 2.
Signed-off-by: Pankaj Gupta
Reviewed-by: Jochen Behrens
---
drivers/net/vmxnet3/vmxnet3_ethdev.c | 7 +--
drivers/net/vmxnet3/vmxnet3_ethdev.h | 2 ++
2 files changed,
From: Pankaj Gupta
Add RETA query and RETA update support for VMXNET3.
Tested, using testpmd, for different hardware versions on ESXi 7.0
Update 2.
Signed-off-by: Pankaj Gupta
Reviewed-by: Jochen Behrens
---
drivers/net/vmxnet3/vmxnet3_ethdev.c | 67
1 file chang
From: Pankaj Gupta
Count the number of entries in the Rx queue for debugging.
Tested, using testpmd, for different hardware versions on ESXi 7.0
Update 2.
Signed-off-by: Pankaj Gupta
Reviewed-by: Jochen Behrens
---
drivers/net/vmxnet3/vmxnet3_ethdev.c | 1 +
drivers/net/vmxnet3/vmxnet3_ethd
From: Pankaj Gupta
Driver callbacks initialization should follow callbacks order in the
structure definition.
Do not reorder callbacks implementation to avoid extra noise in
the code.
Signed-off-by: Pankaj Gupta
Signed-off-by: Andrew Rybchenko
---
drivers/net/vmxnet3/vmxnet3_ethdev.c | 14 ++
From: Pankaj Gupta
Support rte_eth_dev_fw_version_get() API.
Tested, using testpmd, for different hardware versions on ESXi 7.0
Update 2.
Signed-off-by: Pankaj Gupta
Reviewed-by: Jochen Behrens
Signed-off-by: Andrew Rybchenko
---
drivers/net/vmxnet3/vmxnet3_ethdev.c | 20 +++
From: Pankaj Gupta
Currently the driver assumes that the size of the RETA table is
four times the number of Rx queues at multiple places. However,
it sets it to four times the maximum number of queues (4 * 32 = 128)
when it first initializes the device. Change the other uses to use
the stored val
From: Pankaj Gupta
The packet type is set even if it is a fragmented packet.
Tested, using testpmd, for different hardware versions on ESXi 7.0
Update 2.
Signed-off-by: Pankaj Gupta
Reviewed-by: Jochen Behrens
---
drivers/net/vmxnet3/vmxnet3_rxtx.c | 17 +
1 file changed, 17
From: Pankaj Gupta
Tested, using testpmd, for different hardware versions on ESXi 7.0
Update 2.
Fixes: 046f11619567 ("net/vmxnet3: support MSI-X interrupt")
Cc: sta...@dpdk.org
Signed-off-by: Pankaj Gupta
Reviewed-by: Jochen Behrens
---
drivers/net/vmxnet3/vmxnet3_ethdev.c | 5 +
1 file
From: Pankaj Gupta
VMXNET3 version 6 supports some new features, including but not limited to:
- Increased max MTU up to 9190
- Increased max number of queues, both for Rx and Tx
- Removes power-of-two limitations
- Extended interrupt structures, required implementation for
additional numb
Hi Pankaj,
I did final cleanup before applying the patch series, but
realized that release notes update is missing.
Please, pick up my changes and amend patches which support
new features with release notes update in the documentation.
Everything else LGTM now.
Thanks,
Andrew.
On 5/19/22 11:04
https://bugs.dpdk.org/show_bug.cgi?id=1014
Bug ID: 1014
Summary: [dpdk22.07-*] /lib/eal meson build failed with
gcc10.3.0 and clang13.0.0 on FreeBSD13.1/64
Product: DPDK
Version: unspecified
Hardware: All
OS
On 5/15/22 18:28, Ivan Malov wrote:
Change ambiguous terms "jump rule" and "group rule" to
clearer "tunnel rule" and "switch rule". The new terms
reflect the purpose of these rules in virtual switches.
The module name, "flow tunnel", is replaced by "FT" in
function names to avoid the use of word
On 5/18/22 18:24, Stephen Hemminger wrote:
On Wed, 18 May 2022 06:58:06 +
Steve Yang wrote:
+#define ICE_BUFF_SIZE 0x000c9000
Having magic size hard coded in testpmd is bad idea.
If there is driver specific size it should be exposed by API
+ size = ICE_BUFF_SIZE;
+ buff = (
On 5/17/22 19:02, Zhang, Yuying wrote:
Hi Wenwu,
LGTM.
-Original Message-
From: Ma, WenwuX
Sent: Thursday, May 12, 2022 9:08 AM
To: Li, Xiaoyun ; Singh, Aman Deep
; Zhang, Yuying ;
dev@dpdk.org
Cc: Hu, Jiayu ; Wang, Yinan ;
He, Xingguang ; Ma, WenwuX
; sta...@dpdk.org
Subject: [PATCH v
On 5/11/22 05:14, Robin Zhang wrote:
This patch implements format module EEPROM information for
SFF-8472 Rev 12.0
Signed-off-by: Robin Zhang
[snip]
diff --git a/lib/ethdev/sff_8472.c b/lib/ethdev/sff_8472.c
new file mode 100644
index 00..1bbabbde1a
--- /dev/null
+++ b/lib/ethdev/sff_
Hi Andrew,
> -Original Message-
> From: Andrew Rybchenko
> Sent: Thursday, May 19, 2022 9:45 AM
> Subject: Re: [RFC] ethdev: datapath-focused meter actions, continue
>
> On 5/19/22 05:17, Alexander Kozyrev wrote:
> > On Wed, May 18, 2022 12:51 Andrew Rybchenko :
> >> I'm sorry, I'm not s
> -Original Message-
> From: Joyce Kong
> Sent: Thursday, May 19, 2022 3:00 PM
> To: Ferruh Yigit ; Jakub Grajciar
>
> Cc: Ruifeng Wang ; dev@dpdk.org; nd
>
> Subject: RE: [PATCH v1 1/2] net/memif: add a Rx fast path
>
> Hi Ferruh,
>
> > -Original Message-
> > From: Ferruh Yi
Shijith Thotton writes:
> Added a new eventdev API rte_event_queue_attr_set(), to set event queue
> attributes at runtime from the values set during initialization using
> rte_event_queue_setup(). PMD's supporting this feature should expose the
> capability RTE_EVENT_DEV_CAP_RUNTIME_QUEUE_ATTR.
+ lylav...@iol.unh.edu
> -Original Message-
> From: Gowrishankar Muthukrishnan
> Sent: Thursday, May 19, 2022 11:01 AM
> To: Brandon Lo ; roy.fan.zh...@intel.com;
> ciara.po...@intel.com
> Cc: dev@dpdk.org
> Subject: RE: [EXT] [PATCH v4 8/8] examples/fips_validation: add parsing for
> cma
+lylav...@iol.unh.edu
> -Original Message-
> From: Gowrishankar Muthukrishnan
> Sent: Thursday, May 19, 2022 11:00 AM
> To: Brandon Lo ; roy.fan.zh...@intel.com;
> ciara.po...@intel.com
> Cc: dev@dpdk.org
> Subject: RE: [EXT] [PATCH v4 4/8] examples/fips_validation: allow json file as
> in
> -Original Message-
> From: Richardson, Bruce
> Sent: Wednesday, May 18, 2022 11:33 AM
> To: Ferruh Yigit
> Cc: Ji, Kai ; dev@dpdk.org; Zhang, Roy Fan
>
> Subject: Re: [dpdk-dev v2 1/2] build: add in option for qat use intel ipsec-mb
> lib
>
> On Wed, May 18, 2022 at 11:26:27AM +0100,
> -Original Message-
> From: Ferruh Yigit
> Sent: Wednesday, May 18, 2022 11:26 AM
> To: Richardson, Bruce ; Ji, Kai
>
> Cc: dev@dpdk.org; Zhang, Roy Fan
> Subject: Re: [dpdk-dev v2 1/2] build: add in option for qat use intel ipsec-mb
> lib
>
> On 5/18/2022 9:04 AM, Bruce Richardson w
> -Original Message-
> From: Ke Zhang
> Sent: Thursday, May 19, 2022 3:36 PM
> To: Li, Xiaoyun ; Wu, Jingjing ;
> Xing, Beilei ; dev@dpdk.org
> Cc: Zhang, Ke1X ; sta...@dpdk.org
> Subject: [PATCH v7] net/iavf: fix mbuf release function point corrupt in
> multi-
> process
>
> In the mu
In the multi process environment, the sub process
operates on the shared memory and changes the
function pointer of the main process, resulting in
the failure to find the address of the function when
main process releasing, resulting in crash.
similar with commit<20b631efe785819eb77aabbf500b3352e5
For Rx-Queue Interrupt Setting, when vf rx interrupt
disable(INTENA=0), there are two ways to write back
descriptor to host memory:
1)Set WB_ON_ITR bit 0 to Interrupt Dynamic Control Register:
Completed descriptors are posted to host memory according to
the internal descriptor cache policy (in oth
On 5/6/22 06:56, Spike Du wrote:
LWM(limit watermark) is a per Rx queue attribute that notifies dpdk
dpdk is not necessary about.
I'm not sure that "attribute" can notify application. Please,
reword the description.
application event of RTE_ETH_EVENT_RXQ_LIMIT_REACHED when the Rx
queue's usa
Hi Ori,
On 5/19/22 11:41, Ori Kam wrote:
Hi Andrew,
-Original Message-
From: Andrew Rybchenko
Sent: Thursday, May 19, 2022 9:45 AM
Subject: Re: [RFC] ethdev: datapath-focused meter actions, continue
On 5/19/22 05:17, Alexander Kozyrev wrote:
On Wed, May 18, 2022 12:51 Andrew Rybchen
> -Original Message-
> From: Ke Zhang
> Sent: Thursday, May 19, 2022 5:31 PM
> To: Li, Xiaoyun ; Wu, Jingjing ;
> Xing, Beilei ; dev@dpdk.org
> Cc: Zhang, Ke1X ; sta...@dpdk.org
> Subject: [PATCH v2] net/iavf: fix Rx queue interrupt setting
>
> For Rx-Queue Interrupt Setting, when vf r
On 18/05/2022 13:54, Ferruh Yigit wrote:
On 5/6/2022 10:27 PM, Ed Czeck wrote:
new version code
remove device-level global operations
remove ark_mpu_reset_stats function
Hi Ed, please find a few comments inline.
Also I assume 'mpu' is an abbreviation, can you please document what it
stands f
On Thu, May 19, 2022 at 10:14:14AM +0100, Zhang, Roy Fan wrote:
> > -Original Message-
> > From: Richardson, Bruce
> > Sent: Wednesday, May 18, 2022 11:33 AM
> > To: Ferruh Yigit
> > Cc: Ji, Kai ; dev@dpdk.org; Zhang, Roy Fan
> >
> > Subject: Re: [dpdk-dev v2 1/2] build: add in option fo
19/05/2022 09:40, David Marchand:
> On Thu, May 19, 2022 at 1:25 AM Konstantin Ananyev
> wrote:
> > 18/05/2022 18:24, David Marchand пишет:
> > > On Fri, May 13, 2022 at 12:10 PM Min Hu (Connor)
> > > wrote:
> > >>
> > >>I think net/bonding offer 'API' for APP to use the bonding.
> > >>
On Wed, May 18, 2022 at 9:07 AM Steve Yang wrote:
>
> Dump DDP runtime configure into a binary(package) file from ice PF port.
>
> Add command line:
> ddp dump
>
> Parameters:
>the PF Port ID
>dumped runtime configure file, if not a absolute path,
> it
Calling this telemetry callback with no argument caused a crash.
Fixes: 41cc645c214f ("net/cnxk: add inline IPsec telemetry for CN9K")
Cc: sta...@dpdk.org
Signed-off-by: David Marchand
---
drivers/net/cnxk/cnxk_ethdev_sec_telemetry.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/driver
Hi Bruce,
> -Original Message-
> From: Richardson, Bruce
> Sent: Thursday, May 19, 2022 11:23 AM
> To: Zhang, Roy Fan
> Cc: Ferruh Yigit ; Ji, Kai ;
> dev@dpdk.org
> Subject: Re: [dpdk-dev v2 1/2] build: add in option for qat use intel ipsec-mb
> lib
>
> On Thu, May 19, 2022 at 10:14:14
On Thu, May 19, 2022 at 8:31 AM Amit Prakash Shukla
wrote:
> diff --git a/lib/eal/common/eal_common_memory.c
> b/lib/eal/common/eal_common_memory.c
> index 688dc615d7..80dde5f0f4 100644
> --- a/lib/eal/common/eal_common_memory.c
> +++ b/lib/eal/common/eal_common_memory.c
> @@ -18,6 +18,7 @@
> #i
Try and call all possible telemetry commands.
Each commands is tested with no argument, 0 (for command that accepts
a single integer like for a port identifier) and z (to catch commands
not properly validating input).
Fake cryptodev, ethdev and eventdev ports are created using dummy
drivers.
Outpu
An additional check of control flag sve_acle for
RTE_HAS_SVE_ACLE macro to be part of the build.
If any SoC config doesn't have sve_acle flag parameter
then default it will be considered as true.
Signed-off-by: Rahul Bhansali
Reviewed-by: Chengwen Feng
Reviewed-by: Juraj Linke??
Acked-by: Ruife
This disable the sve_acle flag for cn10k.
For native build, -Dplatform=cn10k will require to
get sve_acle flag parameter in the build.
Performance impact:-
With l3fwd example, lpm lookup performance increased
by ~21% if Neon is used instead of SVE. Hence, disabled
sve_acle flag for cn10k.
Signed
On Mon, May 16, 2022 at 11:45 PM Alexander Kozyrev wrote:
>
> Agenda: continue discussion about proposed improvements to Flow API in
> regards to Meter handling (slides attached).
I think, primary difference between the old and new methods are where
the meter HW objects are available.
In the o
On Fri, May 13, 2022 at 8:27 PM wrote:
>
> From: Pavan Nikhilesh
>
> Merge crc32 hash calculation public API implementation for x86 and Arm.
> Select the best available CRC32 algorithm when unsupported algorithm
> on a given CPU architecture is requested by an application.
>
> Previously, if an a
> -Original Message-
> From: Jerin Jacob
> Sent: Thursday, May 19, 2022 2:56 PM
> To: Alexander Kozyrev
> Cc: Ori Kam ; Jerin Jacob ;
> Dumitrescu, Cristian ; NBU-Contact-Thomas
> Monjalon (EXTERNAL) ; Andrew Rybchenko
> ; vipin.vargh...@amd.com; Ajit Khaparde
> ; Ferruh Yigit ; Ray
> K
On Thu, May 19, 2022 at 01:25:25PM +0100, Zhang, Roy Fan wrote:
> Hi Bruce,
>
> > -Original Message-
> > From: Richardson, Bruce
> > Sent: Thursday, May 19, 2022 11:23 AM
> > To: Zhang, Roy Fan
> > Cc: Ferruh Yigit ; Ji, Kai ;
> > dev@dpdk.org
> > Subject: Re: [dpdk-dev v2 1/2] build: ad
Hi Thomas,
> -Original Message-
> From: Thomas Monjalon
> Sent: Wednesday, May 18, 2022 5:12 AM
> To: Ding, Xuan ; Wang, YuanX
> ; Wu, WenxuanX
> Cc: andrew.rybche...@oktetlabs.ru; Li, Xiaoyun ;
> ferruh.yi...@xilinx.com; Singh, Aman Deep ;
> dev@dpdk.org; Zhang, Yuying ; Zhang, Qi Z
> ;
> diff --git a/lib/ethdev/rte_flow.h b/lib/ethdev/rte_flow.h
> index d8827dd184..e3f0e86eb6 100644
> --- a/lib/ethdev/rte_flow.h
> +++ b/lib/ethdev/rte_flow.h
> @@ -671,6 +671,14 @@ enum rte_flow_item_type {
>* See struct rte_flow_item_gre_opt.
>*/
> RTE_FLOW_ITEM_TYPE_GRE_OPT
> -Original Message-
> From: Alexander Kozyrev
> Sent: Wednesday, May 18, 2022 5:35 AM
> To: dev@dpdk.org
> Cc: Dumitrescu, Cristian ;
> jerinjac...@gmail.com; or...@nvidia.com; tho...@monjalon.net;
> ivan.ma...@oktetlabs.ru; andrew.rybche...@oktetlabs.ru;
> ferruh.yi...@xilinx.com; Awa
On Wed, May 11, 2022 at 4:57 PM Stanislaw Kardach wrote:
>
> The lpm_process_event_pkt() can either process a packet using an
> architecture specific (defined for X86/SSE, ARM/Neon and PPC64/Altivec)
> path or a scalar one. The choice is however done using an ifdef
> pre-processor macro. Because o
> diff --git a/lib/ethdev/rte_mtr.h b/lib/ethdev/rte_mtr.h
> index 40df0888c8..d7b916b168 100644
> --- a/lib/ethdev/rte_mtr.h
> +++ b/lib/ethdev/rte_mtr.h
> @@ -524,6 +524,30 @@ rte_mtr_meter_profile_delete(uint16_t port_id,
> uint32_t meter_profile_id,
> struct rte_mtr_error *error);
> -Original Message-
> From: Ruifeng Wang
> Sent: Tuesday, January 4, 2022 5:01 AM
> To: Matan Azrad ; Slava Ovsiienko
>
> Cc: dev@dpdk.org; honnappa.nagaraha...@arm.com; sta...@dpdk.org;
> n...@arm.com; Ruifeng Wang
> Subject: [PATCH] net/mlx5: fix risk in Rx descriptor read in NEON vec
Hello Tyler,
On Thu, May 12, 2022 at 3:14 PM Tyler Retzlaff
wrote:
>
> this series provides basic dependencies for additional eal thread api
> additions. series includes
>
> * basic platform error number conversion.
> * function to get current thread identifier.
> * functions to get and set affin
> -Original Message-
> From: Ferruh Yigit
> Sent: Thursday, May 19, 2022 1:06 AM
> To: Joyce Kong ; Jakub Grajciar
> Cc: Ruifeng Wang ; dev@dpdk.org; nd
>
> Subject: Re: [PATCH v1 1/2] net/memif: add a Rx fast path
>
> On 5/17/2022 11:51 AM, Joyce Kong wrote:
> > For memif non-zero-copy
On Thu, 19 May 2022 15:33:34 +0800
Wenjun Wu wrote:
>
> + if (dev->data->dev_conf.rxmode.offloads &
> + RTE_ETH_RX_OFFLOAD_TIMESTAMP)
> + rte_spinlock_init(&vf->phc_time_aq_lock);
> +
There is no reason this init needs to be only true with some flags.
Just always do it.
Hi David ,
Thanks for your review, see the bellows.
--
taoyunxi...@cmss.chinamobile.com
>On Mon, May 16, 2022 at 9:38 AM taoyunxiang
> wrote:
>>
>> The return value of pci_plug in pci_common.c
>> will always be int vaule, can not be NULL.
>> We could use not
Changes adds telemetry support to display memory occupancy
in memseg and the information of the elements allocated from
a memseg based on arguments provided by user. This patch
adds following endpoints:
1. /eal/active_memseg_list
The command displays the memseg list from which the memory
has been
Fixes: 3c79609fda7c ("vhost/crypto: handle virtually non-contiguous buffers")
Cc: roy.fan.zh...@intel.com
This patch fixes the vhost crypto compile file on GCC12.
Ref. https://bugs.dpdk.org/show_bug.cgi?id=1011
The fix involves replacing rte_memcpy to memcpy.
Signed-off-by: Fan Zhang
---
lib/v
On Sat, May 14, 2022 at 9:15 AM Duncan Bellamy wrote:
>
> musl lacks __ppc_get_timebase() but has __builtin_ppc_get_timebase()
>
> Signed-off-by: Duncan Bellamy
Cc: maintainer.
--
David Marchand
On Thu, May 12, 2022 at 9:06 AM David Marchand
wrote:
> On Thu, Apr 14, 2022 at 1:28 PM David Marchand
> wrote:
> >
> > Caught by ASan, if a secondary process tried to attach a device with an
> > incorrect driver name, devargs was leaked.
> >
> > Fixes: 64051bb1f144 ("devargs: unify scratch buffe
On Thu, May 5, 2022 at 12:27 PM Maxime Coquelin
wrote:
>
> This patch reverts commit 10f4620f02e1 ("app/testpmd: modify mac in csum
> forwarding"),
> as the checksum forwarding is expected to only perform
> checksum and not also overwritte the source and destination
> MAC addresses.
>
> Doing so,
Hello Luc,
On Fri, May 13, 2022 at 9:16 PM Luc Pelletier wrote:
> > > Actually, looking again at the history, it fixes:
> > > Fixes: f5472703c0bd ("eal: optimize aligned memcpy on x86")
> >
> > Nop, that's probably even older, could you double check?
> > I'll hold on pushing this fix.
>
> It seem
On Thu, Apr 7, 2022 at 5:24 PM David Marchand wrote:
> On Thu, Mar 10, 2022 at 3:55 PM Ananyev, Konstantin
> wrote:
> > > Calls to rte_memcpy for 1 < n < 16 could result in unaligned
> > > loads/stores, which is undefined behaviour according to the C
> > > standard, and strict aliasing violations
Hi Stanislaw, Michal,
As far as I can see, this implementation almost completely repeats other
lookupx4() implementations, except for the use of vector instructions.
On my board (x86_64) in lpm_perf_autotest your implementation takes about:
LPM LookupX4: 29.5 cycles (fails = 12.5%)
replacing
Hi folks,
Here are a few takeaways of mine, with a few actions for Alex and Ori:
1. Problem with pre-definition of meter profiles and policies: In the case of
the data plane adding flow rules to itself (as opposed to the control plane
adding flow rules to the data plane), the API requirement o
Currently the ixgbe driver does not ID any SFP except for the first one
plugged in. This can lead to no-link, or incorrect speed conditions.
For example:
* If link is initially established with a 1G SFP, and later a 1G/10G
multispeed part is later installed, then the MAC link setup functions are
Rather than run-to-completion, allow the link update thread to be
periodic. This will set the stage for properly handling hot-plugging.
Signed-off-by: Jeff Daly
Inspired-by: Stephen Douthit
---
drivers/net/ixgbe/base/ixgbe_common.c | 4 +-
drivers/net/ixgbe/ixgbe_ethdev.c | 180
The link update originally direct coded into the periodic service thread
and is made separate in preparation for additional SFP handling code.
Signed-off-by: Jeff Daly
Inspired-by: Stephen Douthit
---
drivers/net/ixgbe/ixgbe_ethdev.c | 99 ++--
drivers/net/ixgbe/ixgb
SFP hotplug may require setup/configuration of the SFP in the event that
the SFP is different from the previously installed SFP. Ensure that the
periodic service task can handle this situation. Teach the interrupt
path that an SFP removal means that an SFP insertion will need to be
setup again.
Currently the ixgbe driver does not ID any SFP except for the first one
plugged in. This can lead to no-link, or incorrect speed conditions.
For example:
* If link is initially established with a 1G SFP, and later a 1G/10G
multispeed part is later installed, then the MAC link setup functions are
Rather than run-to-completion, allow the link update thread to be
periodic. This will set the stage for properly handling hot-plugging.
Signed-off-by: Jeff Daly
Inspired-by: Stephen Douthit
---
drivers/net/ixgbe/base/ixgbe_common.c | 4 +-
drivers/net/ixgbe/ixgbe_ethdev.c | 180
The link update originally direct coded into the periodic service thread
and is made separate in preparation for additional SFP handling code.
Signed-off-by: Jeff Daly
Inspired-by: Stephen Douthit
---
drivers/net/ixgbe/ixgbe_ethdev.c | 99 ++--
drivers/net/ixgbe/ixgb
SFP hotplug may require setup/configuration of the SFP in the event that
the SFP is different from the previously installed SFP. Ensure that the
periodic service task can handle this situation. Teach the interrupt
path that an SFP removal means that an SFP insertion will need to be
setup again.
Changes adds telemetry support to display memory occupancy
in memseg and the information of the elements allocated from
a memseg based on arguments provided by user. This patch
adds following endpoints:
1. /eal/active_memseg_list
The command displays the memseg list from which the memory
has been
Currently the ixgbe driver does not ID any SFP except for the first one
plugged in. This can lead to no-link, or incorrect speed conditions.
For example:
* If link is initially established with a 1G SFP, and later a 1G/10G
multispeed part is later installed, then the MAC link setup functions are
Rather than run-to-completion, allow the link update thread to be
periodic. This will set the stage for properly handling hot-plugging.
Signed-off-by: Jeff Daly
Suggested-by: Stephen Douthit
---
drivers/net/ixgbe/base/ixgbe_common.c | 4 +-
drivers/net/ixgbe/ixgbe_ethdev.c | 180 +++
The link update originally direct coded into the periodic service thread
and is made separate in preparation for additional SFP handling code.
Signed-off-by: Jeff Daly
Suggested-by: Stephen Douthit
---
drivers/net/ixgbe/ixgbe_ethdev.c | 99 ++--
drivers/net/ixgbe/ixg
SFP hotplug may require setup/configuration of the SFP in the event that
the SFP is different from the previously installed SFP. Ensure that the
periodic service task can handle this situation. Teach the interrupt
path that an SFP removal means that an SFP insertion will need to be
setup again.
Rather than run-to-completion, allow the link update thread to be
periodic. This will set the stage for properly handling hot-plugging.
Signed-off-by: Jeff Daly
Suggested-by: Stephen Douthit
---
drivers/net/ixgbe/base/ixgbe_common.c | 4 +-
drivers/net/ixgbe/ixgbe_ethdev.c | 180 +++
The link update originally direct coded into the periodic service thread
and is made separate in preparation for additional SFP handling code.
Signed-off-by: Jeff Daly
Suggested-by: Stephen Douthit
---
drivers/net/ixgbe/ixgbe_ethdev.c | 99 ++--
drivers/net/ixgbe/ixg
SFP hotplug may require setup/configuration of the SFP in the event that
the SFP is different from the previously installed SFP. Ensure that the
periodic service task can handle this situation. Teach the interrupt
path that an SFP removal means that an SFP insertion will need to be
setup again.
On 5/16/22 1:48 PM, Nicolas Chautru wrote:
v3: Feedback from Tom Rix: missing copyright, refactor bbdev-test section
calling
the configure companion function for ACC100/101, taking the Pmon commit out
which is not directly required.
These address some of my comments.
The others, mostly arou
Hi Nicolas,
On 5/16/22 22:48, Nicolas Chautru wrote:
Support for ACC101 as a derivative of ACC100.
Reusing existing code when possible.
Signed-off-by: Nicolas Chautru
---
doc/guides/bbdevs/acc101.rst | 237 +++
doc/guides/bbdevs/features/acc101.ini
On Xeon, as 512b accesses are available, movdir64 instruction is able to
perform 512b read and write to DLB producer port. In order for movdir64
to be able to pull its data from store buffers (store-buffer-forwarding)
(before actual write), data should be in single 512b write format.
This commit ad
Hi Nicolas,
On 5/16/22 22:48, Nicolas Chautru wrote:
> Adding companion function specific to ACC100 and it
> can be called from bbdev-test when running from PF.
>
> Signed-off-by: Nicolas Chautru
> ---
> app/test-bbdev/test_bbdev_perf.c | 22 ++-
> drivers/baseband/acc100/rte_acc100_
On Xeon, as 512b accesses are available, movdir64 instruction is able to
perform 512b read and write to DLB producer port. In order for movdir64
to be able to pull its data from store buffers (store-buffer-forwarding)
(before actual write), data should be in single 512b write format.
This commit ad
DDM -> Downstream Data Mover
MPU -> Mbuf Prefetch Unit
UDM -> Upstream Data Mover
Signed-off-by: Ed Czeck
---
devtools/words-case.txt | 3 +++
1 file changed, 3 insertions(+)
diff --git a/devtools/words-case.txt b/devtools/words-case.txt
index bc33470532..fa92ab273e 100644
--- a/devtools/words-
new firmware version for MPU (Mbuf Prefetch Unit)
remove device-level global operations
remove ark_mpu_reset_stats function
Signed-off-by: Ed Czeck
---
v2:
- document version compatibility between firmware and DPDK
- reword commit message
---
doc/guides/nics/ark.rst | 15 +++
new firmware version for DDM (Downstream Data Mover)
remove device-level start, stop, and reset operations
add queue-based start, stop and reset as required by firmware
Signed-off-by: Ed Czeck
---
v2:
reword commit message
---
drivers/net/ark/ark_ddm.c | 80 +-
new firmware version for UDM (Upstream Data Mover)
remove device-level start, stop, and reset operations
add queue-based start, stop and reset as required by firmware
remove performance structs as they are not in the firmware module
Signed-off-by: Ed Czeck
---
v2: reword commit message
---
driv
detect and report completion errors from firmware
Signed-off-by: Ed Czeck
---
drivers/net/ark/ark_rqp.c | 6 --
drivers/net/ark/ark_rqp.h | 3 ++-
2 files changed, 6 insertions(+), 3 deletions(-)
diff --git a/drivers/net/ark/ark_rqp.c b/drivers/net/ark/ark_rqp.c
index ef9ccd0706..efb9730fe6
update device list is doc
Signed-off-by: Ed Czeck
---
doc/guides/nics/ark.rst | 4 +++-
drivers/net/ark/ark_ethdev.c | 6 ++
2 files changed, 9 insertions(+), 1 deletion(-)
diff --git a/doc/guides/nics/ark.rst b/doc/guides/nics/ark.rst
index 29c0a07d60..f4ffb05b2f 100644
--- a/doc/guid
Add capabilities field isvf to dev struct
Disable configuration calls as required by vf
Signed-off-by: Ed Czeck
---
v2: feature Arkville vf support int release notes
---
doc/guides/rel_notes/release_22_07.rst | 4 ++
drivers/net/ark/ark_ethdev.c | 83 +++---
drive
11/05/2022 16:07, Stanislaw Kardach пишет:
Forcing inlining in test_ring_enqueue and test_ring_dequeue can cause
the compiled code to grow extensively when compiled with no optimization
(-O0 or -Og). This is default in the meson's debug configuration. This
can collide with compiler bugs and cause
> -Original Message-
> From: Thomas Monjalon
> Sent: Wednesday, April 13, 2022 10:21 PM
> To: dev@dpdk.org
> Cc: Stephen Douthit ; Jeff Daly usa.com>; Wang, Haiyue ; Yang, Qiming
> ; Wu, Wenjun1
> Subject: Re: [PATCH] net/ixgbe: Treat 1G Cu SFPs as 1G SX on the X550 devices
>
> Pleas
1 - 100 of 130 matches
Mail list logo
