> -Original Message-
> From: Zhang, Qi Z
> Sent: Monday, March 25, 2019 1:44 PM
> To: Lu, Wenzhuo ; Yang, Qiming
>
> Cc: [email protected]; Stillwell Jr, Paul M ; Yigit,
> Ferruh ; Zhang, Qi Z
> Subject: [PATCH v4 00/38] ice share code update.
>
> Sync to latest kernel driver, main changes
> -Original Message-
> From: Shahaf Shuler
> Sent: Sunday, March 24, 2019 11:14
> To: Slava Ovsiienko ; [email protected]
> Subject: RE: [PATCH 14/14] net/mlx5: add source vport match to the ingress
> rules
>
> Thursday, March 21, 2019 4:12 PM, Slava Ovsiienko:
> > Subject: RE: [PATCH 14/14] ne
On Mon, Mar 25, 2019 at 01:27:16PM +0800, Tiwei Bie wrote:
We are consistently passing 1 as the argument in the data path,
so there is no need to define avail/used flags as function-like
macros anymore. This patch changes the avail and used flags to
constants. And a frequently used combination is
> -Original Message-
> From: dev [mailto:[email protected]] On Behalf Of Wenzhuo Lu
> Sent: Monday, March 25, 2019 2:06 PM
> To: [email protected]
> Cc: Lu, Wenzhuo
> Subject: [dpdk-dev] [PATCH v6 0/8] Support vector instructions on ICE
>
> Use SSE and AVX2 instructions in ICE RX and TX
Hi,
On 3/25/19 3:22 AM, Lu, Wenzhuo wrote:
Hi Maxime,
-Original Message-
From: Maxime Coquelin [mailto:[email protected]]
Sent: Friday, March 22, 2019 6:12 PM
To: Lu, Wenzhuo ; [email protected]
Subject: Re: [dpdk-dev] [PATCH v5 6/8] net/ice: support Rx AVX2 vector
+#ifndef RT
On 3/25/2019 3:39 AM, Zhao1, Wei wrote:
> Hi,
>
>> -Original Message-
>> From: Yigit, Ferruh
>> Sent: Friday, March 22, 2019 10:56 PM
>> To: Zhao1, Wei ; [email protected]
>> Cc: [email protected]; [email protected]; Ananyev, Konstantin
>>
>> Subject: Re: [dpdk-stable] [PATCH v3] app/t
Here is a little series that makes it possible to display and clear
testpmd fwd engines while they run without having to stop them.
This is mostly handy when running stress tests and you look for packets
drops without having to stop/start testpmd forwarding.
Example:
testpmd> show fwd stats all
Caught by code review while investigating the fwd stats display code.
Fixes: af75078fece3 ("first public release")
Cc: [email protected]
Signed-off-by: David Marchand
Reviewed-by: Andrew Rybchenko
Reviewed-by: Maxime Coquelin
---
Changelog since v2:
- focused on useless casts only
- Cc'd stable
Having the standard stats and the rx burst stats on the same line gives a
really long line and is not consistent with the rest.
Before:
iofwd engine
RX-packets: 121811360 TX-packets: 121811392 TX-dropped: 0
RX-bursts : 3806605 [100% of 32 pkts]
TX-bursts : 3806606 [100
fwd engine statistics are stored as unsigned int (32bits) and can wrap
quite quickly.
Example: sending 7mpps for 614s gives us 429800 packets =>
0x1002e4680 larger than 32bits.
testpmd reports forwarding stats as:
RX-packets: 3500381TX-packets: 3500010TX-dropped: 371
While the
Add a new "show/clear fwd stats all" command to display fwd and port
statistics on the fly.
To be able to do so, the (testpmd only) rte_port structure can't be used
to maintain any statistics.
Moved the stats dump parts from stop_packet_forwarding() and merge with
fwd_port_stats_display() into fwd
On 3/25/19 11:51 AM, David Marchand wrote:
Having the standard stats and the rx burst stats on the same line gives a
really long line and is not consistent with the rest.
Before:
iofwd engine
RX-packets: 121811360 TX-packets: 121811392 TX-dropped: 0
RX-bursts : 380660
This patch set enabled package downloading to the device. The package is
to be in the /lib/firmware/intel/ice/ddp directory and named ice.pkg.
The package is shared by the kernel driver and the DPDK PMD.
If package download failed, driver need to go to safe mode. This patch
set disabled RSS, QINQ,
This patch enables package downloading to the device. The package is
to be in the /lib/firmware/intel/ice/ddp directory and named ice.pkg.
The package is shared by the kernel driver and the DPDK PMD.
There is no per device package be supported so far, all the
devices can only download the same pac
If E810 download package failed, driver need to go to safe mode.
In the safe mode, some advanced features will not be supported.
Signed-off-by: Qiming Yang
---
doc/guides/rel_notes/release_19_05.rst | 2 +-
drivers/net/ice/ice_ethdev.c | 48 ++
drivers/
This patch enabled RSS for UPD/TCP/SCTP+IPV4/IPV6 packets.
Signed-off-by: Qiming Yang
---
doc/guides/rel_notes/release_19_05.rst | 1 +
drivers/net/ice/ice_ethdev.c | 39 ++
2 files changed, 40 insertions(+)
diff --git a/doc/guides/rel_notes/release_19
On 3/25/19 9:03 AM, Xiaolong Ye wrote:
Allow create a mempool with page size aligned base address.
Signed-off-by: Qi Zhang
Signed-off-by: Xiaolong Ye
---
lib/librte_mempool/rte_mempool.c | 3 +++
lib/librte_mempool/rte_mempool.h | 1 +
2 files changed, 4 insertions(+)
diff --git a/lib/lib
v5: Minor format change.
v4: Change _try_ functions to use __atomic too (for consistency)(Suggested by
Ananyev, Konstantin).
v3: Fix headline format error.
v2: Rebase and modify the rwlock test case to address the comments in v1.
v1: Reimplement rwlock with atomic builtins, and add a rwlock pe
Add performance test on all available cores to benchmark
the scaling up performance of rw_lock.
Fixes: af75078fece3 ("first public release")
Cc: [email protected]
Suggested-by: Gavin Hu
Signed-off-by: Joyce Kong
Acked-by: Konstantin Ananyev
---
app/test/test_rwlock.c | 75 ++
The __sync builtin based implementation generates full memory
barriers ('dmb ish') on Arm platforms. Using C11 atomic builtins
to generate one way barriers.
Here is the assembly code of __sync_compare_and_swap builtin.
__sync_bool_compare_and_swap(dst, exp, src);
0x0090f1b0 <+16>:e0
Instead of getting timestamp per iteration, amortize its
overhead can help to get more precise benchmarking results.
Fixes: af75078fece3 ("first public release")
Cc: [email protected]
Signed-off-by: Joyce Kong
Acked-by: Konstantin Ananyev
---
app/test/test_rwlock.c | 18 ++
1 fil
Hi Konstantin,
> -Original Message-
> From: Ananyev, Konstantin
> Sent: Friday, March 22, 2019 2:43 AM
> To: Joyce Kong (Arm Technology China) ;
> [email protected]
> Cc: nd ; [email protected]; [email protected];
> Richardson, Bruce ; [email protected];
> [email protected]; H
Hi，Ferruh
> -Original Message-
> From: Yigit, Ferruh
> Sent: Monday, March 25, 2019 4:46 PM
> To: Zhao1, Wei ; [email protected]
> Cc: [email protected]; [email protected]; Ananyev, Konstantin
>
> Subject: Re: [dpdk-stable] [PATCH v3] app/testpmd: fix support of hex string
> parser for
On 3/25/2019 9:25 AM, Zhao1, Wei wrote:
> Hi，Ferruh
>
>> -Original Message-
>> From: Yigit, Ferruh
>> Sent: Monday, March 25, 2019 4:46 PM
>> To: Zhao1, Wei ; [email protected]
>> Cc: [email protected]; [email protected]; Ananyev, Konstantin
>>
>> Subject: Re: [dpdk-stable] [PATCH v3] a
Hi，Ferruh
> -Original Message-
> From: Yigit, Ferruh
> Sent: Monday, March 25, 2019 5:36 PM
> To: Zhao1, Wei ; [email protected]
> Cc: [email protected]; [email protected]; Ananyev, Konstantin
>
> Subject: Re: [dpdk-stable] [PATCH v3] app/testpmd: fix support of hex string
> parser for
> -Original Message-
> From: Jerin Jacob Kollanukkaran
> Sent: Tuesday, March 19, 2019 3:16 PM
> To: Pavan Nikhilesh Bhagavatula
> Cc: [email protected]
> Subject: Re: [dpdk-dev] [PATCH] app/eventdev: add option to set global
> dequeue tmo
>
> On Tue, 2019-03-19 at 06:21 +, Pavan Nikhilesh
> Subject: [PATCH] doc: note validation commitment required for stables
>
> If a stable branch for a specific DPDK release is to proceed, along with
> needing a maintainer, there should also be commitment from major
> contributors for validation of the releases.
>
> Signed-off-by: Kevin Traynor
On Sat, Mar 23, 2019 at 04:51:27PM +, Jerin Jacob Kollanukkaran wrote:
> On Fri, 2019-03-22 at 15:55 -0700, Anand Rawat wrote:
> > Added documentation to build helloworld example
> > on windows using meson and clang. Updated the
> > maintainers list to include windows maintainers.
> >
> > Sign
Hi Konstantin,
> -Original Message-
> From: Ananyev, Konstantin
> Sent: Friday, March 22, 2019 7:39 PM
> To: Joyce Kong (Arm Technology China) ;
> [email protected]
> Cc: nd ; [email protected];
> [email protected]; [email protected]; Honnappa
> Nagarahalli ; Gavin Hu (
> Subject: [PATCH] doc: fix a typo in procinfo guide
>
> This patch fixes a trivial info in proc info section.
> informationi=>information.
>
> Fixes: 8a37f37fc243 ("app/procinfo: add --show-port")
>
> Signed-off-by: Rami Rosen
> ---
> doc/guides/tools/proc_info.rst | 2 +-
> 1 file changed, 1
On Fri, Mar 22, 2019 at 03:55:05PM -0700, Anand Rawat wrote:
> Added meson workarounds to build helloworld on windows.
> Windows currently only supports kvargs and eal libraries.
> This change restricts the build flow to supported libraries
> only.
>
> Signed-off-by: Anand Rawat
> Signed-off-by:
If for debugging we disable the driver directory in the meson.build file,
we get an error because the variable "driver_classes" does not exist.
This is because driver_classes is only defined in the
drivers/meson.build file. Defining driver_classes in dpdk/meson.build file
will make it easier for co
On Mon, 2019-03-25 at 10:45 +0800, Ye Xiaolong wrote:
> On 03/24, Luca Boccassi wrote:
> > On Sun, 2019-03-17 at 11:34 +0800, Ye Xiaolong wrote:
> > > On 03/02, Ye Xiaolong wrote:
> > > > > > _LDLIBS-$(CONFIG_RTE_LIBRTE_PMD_AF_PACKET) +=
> > > > > > -lrte_pmd_af_packet
> > > > > > +_LDLIBS-$(CONF
Add test case for encryption, dectryption for snow3g when digest
is encrypted
---
v3:
* fixed path for test directory.
v2:
* coding style improved
Signed-off-by: Lukasz Krakowiak
---
app/test/test_cryptodev.c | 91 ++--
app/test/test_cryptodev_snow3g_test_vectors.h
v8:
1. Enhance functional test for ticketlock by adding extra verification to
ensure correct locking in MT env.
2. Amortize the cost of getting time in test case.
(Suggested by Konstantin Ananyev)
v7:
1. Modify trylock to compare both current and next fields to gurantee the
lock
The spinlock implementation is unfair, some threads may take locks
aggressively while leaving the other threads starving for long time.
This patch introduces ticketlock which gives each waiting thread a
ticket and they can take the lock one by one. First come, first serviced.
This avoids starvatio
Add test cases for ticket lock, recursive ticket lock,
and ticket lock performance.
Signed-off-by: Joyce Kong
Reviewed-by: Gavin Hu
Reviewed-by: Phil Yang
---
MAINTAINERS| 1 +
app/test/Makefile | 1 +
app/test/autotest_data.py | 6 +
app/test/meson.build
Let all architectures use generic ticketlock implementation.
Signed-off-by: Joyce Kong
---
.../common/include/arch/arm/rte_ticketlock.h | 22 ++
.../common/include/arch/ppc_64/rte_ticketlock.h| 18 ++
.../common/include/arch/x86/rte_ticketlock.h
> Subject: [dpdk-dev] [PATCH 3/3] doc/rcu: add lib_rcu documentation
>
> Add lib_rcu QSBR API and programmer guide documentation.
>
> Signed-off-by: Honnappa Nagarahalli
>
> ---
> doc/api/doxy-api-index.md | 3 +-
> doc/api/doxy-api.conf.in | 1 +
>
> Subject: [dpdk-dev] [PATCH] doc: clarify spaces for alignment note
>
> Make clear that spaces are only for alignments less than tab size.
>
> Signed-off-by: Kevin Traynor
> ---
> doc/guides/contributing/coding_style.rst | 2 +-
> 1 file changed, 1 insertion(+), 1 deletion(-)
>
> diff --git a
On 3/20/2019 11:46 AM, Thomas Monjalon wrote:
> 20/03/2019 11:45, Ferruh Yigit:
>> On 3/19/2019 8:30 PM, Thomas Monjalon wrote:
>>> 19/03/2019 19:00, Ferruh Yigit:
On 3/19/2019 5:36 PM, Thomas Monjalon wrote:
> 19/03/2019 18:29, Ferruh Yigit:
>> On 3/14/2019 10:04 PM, Thomas Monjalon w
On 3/24/2019 9:26 AM, Shahaf Shuler wrote:
> Thursday, March 21, 2019 11:34 AM, Dekel Peled:
>> Subject: RE: [PATCH] net/mlx5: add missing return value check
>>
>>> -Original Message-
>>> From: Ali Alnubani
>>> Sent: Thursday, March 21, 2019 11:07 AM
>>> To: [email protected]
>>> Cc: Shahaf Shul
On 03/25, Luca Boccassi wrote:
>On Mon, 2019-03-25 at 10:45 +0800, Ye Xiaolong wrote:
>> On 03/24, Luca Boccassi wrote:
>> > On Sun, 2019-03-17 at 11:34 +0800, Ye Xiaolong wrote:
>> > > On 03/02, Ye Xiaolong wrote:
>> > > > > > _LDLIBS-$(CONFIG_RTE_LIBRTE_PMD_AF_PACKET) +=
>> > > > > > -lrte_pmd_
According to ietf rfc791 (see [1])
"The Version field indicates the format of the
internet header."
"Internet Header Length (ihl) is the length of the
internet header in 32 bit words, and thus points
to the beginning of the data. Note that
the minimum value for a correct h
On 3/25/19 7:06 AM, Wenzhuo Lu wrote:
Add function pointers of buffer releasing for RX and
TX queues, for vector functions will be added for RX
and TX.
Signed-off-by: Wenzhuo Lu
---
drivers/net/ice/ice_rxtx.c | 24 +++-
drivers/net/ice/ice_rxtx.h | 5 +
2 files c
On Mon, Mar 25, 2019 at 11:49:20AM +, Ferruh Yigit wrote:
> On 3/20/2019 11:46 AM, Thomas Monjalon wrote:
> > 20/03/2019 11:45, Ferruh Yigit:
> >> On 3/19/2019 8:30 PM, Thomas Monjalon wrote:
> >>> 19/03/2019 19:00, Ferruh Yigit:
> On 3/19/2019 5:36 PM, Thomas Monjalon wrote:
> > 19/03
On 3/25/2019 1:01 PM, Saleh Alsouqi wrote:
> According to ietf rfc791 (see [1])
>
> "The Version field indicates the format of the
> internet header."
>
> "Internet Header Length (ihl) is the length of the
> internet header in 32 bit words, and thus points
> to the beginning o
On Mon, Mar 25, 2019 at 02:26:27PM +0100, Gaëtan Rivet wrote:
> On Mon, Mar 25, 2019 at 11:49:20AM +, Ferruh Yigit wrote:
> > On 3/20/2019 11:46 AM, Thomas Monjalon wrote:
> > > 20/03/2019 11:45, Ferruh Yigit:
> > >> On 3/19/2019 8:30 PM, Thomas Monjalon wrote:
> > >>> 19/03/2019 19:00, Ferruh
This patch updates the unit test to enable AESNI-MB PMD
out-of-place tests. A special test type that swap both
the source and destination buffer is added for a more
comprehensive test set to take place.
Signed-off-by: Fan Zhang
Acked-by: Fiona Trahe
---
app/test/test_cryptodev_aes_test_vectors.
On 3/17/2019 6:16 AM, Matan Azrad wrote:
> Hi
>
> From: Stephen Hemminger
>>> Hi
>>>
>>> From: Stephen Hemminger
The return value from bus->find_device is a rte_device which is not
safe to cast to a rte_vdev_device structure.
It doesn't really matter since only being checked for NUL
> -Original Message-
> From: Yang, Qiming
> Sent: Monday, March 25, 2019 5:01 PM
> To: [email protected]
> Cc: Zhang, Qi Z ; Yang, Qiming
> Subject: [PATCH v6 1/3] net/ice: load OS default package
>
> This patch enables package downloading to the device. The package is to be in
> the /lib/f
As stated in 19.02 deprecation notice, this patch updates the
aesni_mb PMD to remove the support of older Intel-ipsec-mb
library version eariler than 0.52.
Signed-off-by: Fan Zhang
Acked-by: Pablo de Lara
---
v3:
- updated documentation.
v2:
- fixed incorrect version in documentation.
doc/guid
Add out-of-place processing, i.e. different source and
destination m_bufs, plus related capability update, tests
and documentation.
Signed-off-by: Fiona Trahe
Signed-off-by: Paul Luse
Signed-off-by: Fan Zhang
v3:
- Updated unit test, enable src-dst swap test for all oop tests.
- Merged patches
Add out-of-place processing, i.e. different source and
destination m_bufs, plus related capability update, tests
and documentation.
Signed-off-by: Fiona Trahe
Signed-off-by: Paul Luse
Signed-off-by: Fan Zhang
Acked-by: Fiona Trahe
Acked-by: Pablo de Lara
---
doc/guides/cryptodevs/aesni_mb.rs
> -Original Message-
> From: Yang, Qiming
> Sent: Monday, March 25, 2019 5:01 PM
> To: [email protected]
> Cc: Zhang, Qi Z ; Yang, Qiming
> Subject: [PATCH v6 0/3] enable package download in ice driver
>
> This patch set enabled package downloading to the device. The package is to be
> in t
On 3/22/2019 1:01 PM, Ian Stokes wrote:
> From: Stephen Hemminger
>
> This addresses the usability issue raised by OVS at DPDK Userspace
> summit. It adds general min/max mtu into device info. For compatiablity,
> and to save space, it fits in a hole in existing structure.
>
> The initial versio
On 3/25/2019 8:51 AM, David Marchand wrote:
> Here is a little series that makes it possible to display and clear
> testpmd fwd engines while they run without having to stop them.
> This is mostly handy when running stress tests and you look for packets
> drops without having to stop/start testpmd
Fixes: cd1e8f03abf0 ("vhost/crypto: fix packet copy in chaining mode")
Coverity Issue: 277214
Coverity Issue: 277220
Coverity Issue: 277233
Coverity Issue: 277236
Cc: [email protected]
Signed-off-by: Fan Zhang
---
lib/librte_vhost/vhost_crypto.c | 4 ++--
1 file changed, 2 insertions(+), 2 delet
On 3/22/2019 3:17 PM, Rami Rosen wrote:
> This patch fixes a trivial typo in rte_ethdev.h.
> retieve=>retrieve
>
> Fixes: 80a1deb4c77a ("ethdev: add API to retrieve queue information")
> Cc: [email protected]
>
> Signed-off-by: Rami Rosen
Reviewed-by: Ferruh Yigit
Applied to dpdk-next-net/master
From: Bill Hong
A PMD might use rte_vlan_insert to implement Tx VLAN offload. Typically
the PMD will insert the VLAN header in the transmit path and then attempt
to send the packets. If this fails, the packets are returned to
the application which may attempt to send these packets again. If the
On 3/22/2019 1:01 PM, Ian Stokes wrote:
> This commit sets the min and max supported MTU values for igb devices
> via the eth_igb_info_get() function. Min MTU supported is set to
> ETHER_MIN_MTU and max mtu is calculated as the max packet length
> supported minus the transport overhead. To aid in t
Hi Poornima,
On 14/2/2019 9:45 AM, Pallantla Poornima wrote:
sprintf function is not secure as it doesn't check the length of string.
replaced sprintf with strlcpy.
Fixes: f74df2c57e ("test/distributor: test single and burst API")
Cc: [email protected]
Signed-off-by: Pallantla Poornima
---
v2:
On 3/22/2019 1:01 PM, Ian Stokes wrote:
> This commit uses the mtu fields populated in rte_eth_dev_info_get()
> to validate the mtu value being passed in port_mtu_set().
>
> Signed-off-by: Ian Stokes
For patch title, I think 'rte_eth_dev_info_get()' is implementation detail here,
what we are ver
25/03/2019 15:16, Ferruh Yigit:
> On 3/22/2019 3:17 PM, Rami Rosen wrote:
> > This patch fixes a trivial typo in rte_ethdev.h.
> > retieve=>retrieve
> >
> > Fixes: 80a1deb4c77a ("ethdev: add API to retrieve queue information")
> > Cc: [email protected]
> >
> > Signed-off-by: Rami Rosen
>
> Review
GitHub is a service used by developers to store repositories. GitHub
provides service integrations that allow 3rd party services to access
developer repositories and perform actions. One of these services is
Travis-CI, a simple continuous integration platform.
This series introduces the ability
When building on FreeBSD, the compiler emitted an error due to being
unable to find rte_pci.h. This was due to missing dependencies for the
application.
Fixes: 474572d2ae5a ("app/pipeline: move from test directory")
Signed-off-by: Bruce Richardson
---
app/test-pipeline/meson.build | 2 +-
1 fil
On 3/24/2019 12:15 PM, [email protected] wrote:
> From: Liron Himi
>
> - mbuf_size and mtu are now being calculated according
> to the given mb-pool.
>
> - max_mtu is now being set according to the given mtu
>
> the above two changes provide the ability to work with jumbo frames
>
> Signed-of
On Mon, 25 Mar 2019 14:03:56 +0800
Xiaolong Ye wrote:
> +
> + ret = xsk_ring_prod__reserve(fq, reserve_size, &idx);
> + if (unlikely(!ret)) {
> + AF_XDP_LOG(ERR, "Failed to reserve enough fq descs.\n");
You defined AF_XDP_LOG to add a newline (similar to other drivers).
But a
25/03/2019 16:32, Michael Santana:
> GitHub is a service used by developers to store repositories. GitHub
> provides service integrations that allow 3rd party services to access
> developer repositories and perform actions. One of these services is
> Travis-CI, a simple continuous integration pla
The Mellanox NICs support SR-IOV and have E-Switch feature.
When SR-IOV is set up in switchdev mode and E-Switch is enabled
we have so called VF representors in the system. All representors
belonging to the same E-Switch are created on the basis of the
single PCI function and with current implemen
There is the routine mlx5_nl_ifindex() returning the
network interface index associated with Infiniband device.
We are going to support multiport IB devices, now function
takes the IB port as argument and returns ifindex associated
with tuple
Signed-off-by: Viacheslav Ovsiienko
---
drivers/net/
mlx5_pci_probe() routine is refactored to probe the ports
of found Infiniband devices. All active ports (with attached
network interface), belonging to the same Infiniband device
will use the signle shared Infiniband context of that device.
Signed-off-by: Viacheslav Ovsiienko
---
drivers/net/mlx
The master device and VF representors were distinguished by
presence of port name, master device did not have one. The new Linux
kernels starting from 5.0 provide the port name for master device
and the implemented representor recognizing method does not work.
The new recognizing method is based on
There is the routine mlx5_nl_portnum() added to get
the number of ports of multiport Infiniband device.
It is assumed the Uplink/VF representors are attached
on this ports.
Signed-off-by: Viacheslav Ovsiienko
Acked-by: Shahaf Shuler
---
drivers/net/mlx5/mlx5.h| 1 +
drivers/net/mlx5/mlx5_n
The IB device names are moved from device private data
to the shared context, code involving the names is updated.
The IB port index treatment is added where it is relevant.
Signed-off-by: Viacheslav Ovsiienko
Acked-by: Shahaf Shuler
---
drivers/net/mlx5/mlx5.h| 2 --
drivers/net/mlx5/
The code is updated to use the shared IB device attributes,
located in the shared IB context. It saves some memory if
there are representors created over the single Infiniband
device with multuple ports.
Signed-off-by: Viacheslav Ovsiienko
Acked-by: Shahaf Shuler
---
drivers/net/mlx5/mlx5.c
The code is updated to provide IB port index for the Verbs
objects being created - QP and Verbs Flows.
Signed-off-by: Viacheslav Ovsiienko
Acked-by: Shahaf Shuler
---
drivers/net/mlx5/mlx5_flow.c | 2 ++
drivers/net/mlx5/mlx5_flow_verbs.c | 1 +
drivers/net/mlx5/mlx5_txq.c| 4 ++--
The PMD code is updated to use Protected Domain from the
the shared IB device context. The Domain is shared between
all devices belonging to the same multiport Infiniband device.
If IB device has only one port, the PD is not shared, because
there is only ethernet device created over IB one.
Signed
We are implementing the support for multport Infiniband device
withj representors attached to these multiple ports. Asynchronous
device event notifications (link status change, removal event, etc.)
should be shared between ports. We are going to implement shared
event handler and this patch introdu
The Mellanox NICs support SR-IOV and have E-Switch feature.
When SR-IOV is set up in switchdev mode and E-Switch is enabled
we have so called VF representors in the system. All representors
belonging to the same E-Switch are created on the basis of the
single PCI function and with current implement
This patch modifies asynchronous event handler to support multiport
Infiniband devices. Handler queries the event parameters, including
event source port index, and invokes the handler for specific
devices with appropriate port_id.
Signed-off-by: Viacheslav Ovsiienko
---
drivers/net/mlx5/mlx5_et
The code is updated to use the shared IB device context and
device handles. The IB device context is shared between
reprentors created over the single multiport IB device. All
Verbs and DevX objects will be created whithin this shared context.
Signed-off-by: Viacheslav Ovsiienko
Acked-by: Shahaf
For E-Switch configurations over multiport Infiniband devices
we should add source vport match to correctly distribute
traffic between representors.
Signed-off-by: Viacheslav Ovsiienko
---
drivers/net/mlx5/mlx5_flow_dv.c | 36
1 file changed, 36 insertions(+)
On 3/25/2019 3:24 AM, Bruce Richardson wrote:
On Sat, Mar 23, 2019 at 04:51:27PM +, Jerin Jacob Kollanukkaran wrote:
On Fri, 2019-03-22 at 15:55 -0700, Anand Rawat wrote:
Added documentation to build helloworld example
on windows using meson and clang. Updated the
maintainers list to incl
Sorry for the late reply, but I noticed the test folder is recently moved under
app so you may need a rebase.
Please keep my ack after rebase: Acked-by: Yipeng Wang
>-Original Message-
>From: Poornima, PallantlaX
>Sent: Monday, March 25, 2019 7:43 AM
>To: [email protected]
>Cc: Pattan, Resh
On Mon, 25 Mar 2019 17:03:22 +
Viacheslav Ovsiienko wrote:
> + * Currently we support sinlge E-Switch per PF configurations
> + * only and representors_id field contains the vport index for
> + * corresponding VF, deduced from representor port name.
> + * For exapmple, let
On Mon, 25 Mar 2019 17:03:22 +
Viacheslav Ovsiienko wrote:
> + if (switch_id_set) {
> + if (info.port_name_new) {
> + /* New representors naming schema. */
> + if (port_name_set) {
> + info.master = (info.port
From: Liron Himi
- mbuf_size and mtu are now being calculated according
to the given mb-pool.
- max_mtu is now being set according to the given mtu
the above two changes provide the ability to work with jumbo frames
Signed-off-by: Liron Himi
---
doc/guides/nics/kni.rst
Acked-by: Harini Ramakrishnan
-Original Message-
From: dev On Behalf Of Anand Rawat
Sent: Friday, March 22, 2019 3:55 PM
To: [email protected]
Cc: [email protected]; [email protected]; [email protected];
[email protected]; [email protected]; [email protected]
When replenishing mbufs on Rx, buffer address (mbuf->buf_addr) should be
loaded. non-x86 processors (mostly RISC such as ARM and Power) are more
vulnerable to load stall. For x86, reducing the number of instructions
seems to matter most.
For x86, this is simply a load but for other architectures,
There's more need to have PMD global data structure. This should be
initialized once per a process regardless of how many PMD instances are
probed. mlx5_init_once() is called during probing and make sure all the
init functions are called once per a process. Currently, such global data
and its initi
The existing socket-based IPC channel is replaced with the new rte_mp APIs of
EAL and extended to request stop/start of dataplane to secondary processes.
Also, initialization of PMD global data including the new IPC channel is
reworked to provide more generic framework for future use.
v2:
* add mo
Socket API is used for IPC in order for secondary process to acquire Verb
command file descriptor. The FD is used to remap UAR address. The new
multi-process APIs (rte_mp) in EAL are newly introduced. mlx5_socket.c is
replaced with mlx5_mp.c, which uses the new APIs.
As it is PMD global infrastruc
As the memory event is propagated to secondary processes, the event is
processed redundantly. This should be processed once because the data
structure used for MR and the event is global across the processes.
Fixes: 974f1e7ef146 ("net/mlx5: add new memory region support")
Cc: [email protected]
Sign
Rx/Tx burst function pointers are stored in the rte_eth_dev structure,
which is local to a process. Even though primary process replaces the
function pointers, secondary will not run the new ones. With rte_mp APIs,
primary can easily broadcast a request to stop/start the datapath of
secondary proce
rte_eth_devices[] is not shared between primary and secondary process, but
a static array to each process. The reverse pointer of device (priv->dev)
becomes invalid if mlx4 supports secondary process. Instead, priv has the
pointer to shared data of the device,
struct rte_eth_dev_data *dev_data;
To support secondary process, the memory allocated by library such as
completion rings (CQ) and buffer rings (WQ) must be manageable by EAL, in
order to share it with secondary processes. With new changes in rdma-core
and kernel driver, it is possible to provide an external allocator to the
library
In order to support secondary process, a few features are required.
a) rdma-core library should allocate device resources using DPDK's memory
allocator.
b) UAR should be remapped for secondary processes. Currently, in order not
to use different data structure for secondary processes, PMD tr
RFC:
https://mails.dpdk.org/archives/dev/2019-March/125516.html
v2:
* add more sanity check for eth_dev and return value from IPC request.
* complement commit messages
* add MLX5_MP_REQ_TIMEOUT_SEC
Yongseok Koh (3):
net/mlx4: change device reference for secondary process
net/mlx4: add externa
RFC:
https://mails.dpdk.org/archives/dev/2019-March/125517.html
v2:
* add more sanity check for eth_dev and return value from IPC request.
* complement commit messages
* add MLX5_MP_REQ_TIMEOUT_SEC
* keep acked-by: Shahaf Shuler
Yongseok Koh (6):
net/mlx: remove debug messages on datapath
net
1 - 100 of 153 matches
Mail list logo
