Thursday, August 24, 2017 1:06 AM, Thomas Monjalon:
> 23/08/2017 15:13, Shahaf Shuler:
> > Wednesday, August 23, 2017 3:29 PM, Ananyev, Konstantin:
> > > From: Shahaf Shuler
> > > > In order to enable PMDs to support only one of the APIs, and
> > > > applications to avoid branching according to the
In function qede_rss_reta_update(),the pointer params returned from
call to function rte_zmalloc() may be NULL and will be dereferenced.
So, should judge the params is NULL or not.
Signed-off-by: Rongqiang XIE
---
drivers/net/qede/qede_ethdev.c | 4
1 file changed, 4 insertions(+)
diff --g
On Wed, Aug 23, 2017 at 07:44:45PM +, Matan Azrad wrote:
> Hi Nelio
>
> > -Original Message-
> > From: Nélio Laranjeiro [mailto:nelio.laranje...@6wind.com]
> > Sent: Wednesday, August 23, 2017 12:41 PM
> > To: Matan Azrad
> > Cc: Adrien Mazarguil ; dev@dpdk.org
> > Subject: Re: [PATCH
Expose a new capapilty of Rx hw timestamp and
added new device args to enable it hw_timestamp.
It will add the raw hw timestamp into the packets.
Its expected that it will lower down the performance since using it
will disable the cqe comprission, and will add extra checkes in
the vec rx path.
Si
Added new capability to the list of rx offloads for hw timestamp
The PMDs how expose this capability will always have it enabled.
But, if the following API got accepted applications can choose
between disable/enable this API.
http://dpdk.org/dev/patchwork/patch/27470/
Signed-off-by: Raslan Daraws
Added new print in case a PMD exposes Rx timestamp.
Also, added a print for timestamp value in rxonly mode
in case the packet was timestamped.
Signed-off-by: Raslan Darawsheh
---
app/test-pmd/config.c | 3 +++
app/test-pmd/rxonly.c | 2 ++
2 files changed, 5 insertions(+)
diff --git a/app/test-
Currently, enabling assertion have to set CONFIG_RTE_LOG_LEVEL to
RTE_LOG_DEBUG. CONFIG_RTE_LOG_LEVEL is the default log level of control
path, RTE_LOG_DP_LEVEL is the log level of data path. It's a little bit
hard to understand literally that assertion is decided by control path
LOG_LEVEL, especia
On 23/08/2017 21:49, Thomas Monjalon wrote:
Please could you explain why the asm code was used?
I guess we were not aware that there was a builtin for it.
Are you sure this builtin is implemented everywhere?
Actually the builtin used in this patch is not supported in most CLANG
version (j
Currently, enabling assertion have to set CONFIG_RTE_LOG_LEVEL to
RTE_LOG_DEBUG. CONFIG_RTE_LOG_LEVEL is the default log level of control
path, RTE_LOG_DP_LEVEL is the log level of data path. It's a little bit
hard to understand literally that assertion is decided by control path
LOG_LEVEL, especia
On Thu, Aug 24, 2017 at 06:56:11AM +, Shahaf Shuler wrote:
> Wednesday, August 23, 2017 4:12 PM, Bruce Richardson:
> > On Wed, Aug 23, 2017 at 01:39:08PM +0200, Nélio Laranjeiro wrote:
> > > On Mon, Aug 21, 2017 at 10:47:01AM +0300, Sagi Grimberg wrote:
> > >
> > > Acked-by: Nelio Laranjeiro
>
On 8/22/2017 11:02 AM, Luca Boccassi wrote:
> On Mon, 2017-08-21 at 17:19 -0700, Yipeng Wang wrote:
>> Membership library is an extension and generalization of a
>> traditional
>> filter (for example Bloom Filter) structure. In general, the
>> Membership
>> library is a data structure that provides
On Thu, 2017-08-24 at 10:35 +0100, Ferruh Yigit wrote:
> On 8/22/2017 11:02 AM, Luca Boccassi wrote:
> > On Mon, 2017-08-21 at 17:19 -0700, Yipeng Wang wrote:
> > > Membership library is an extension and generalization of a
> > > traditional
> > > filter (for example Bloom Filter) structure. In gen
Implement dynamic mapping of software flow types to hardware pctypes.
This allows to map new flow types to pctypes without changing
API of the driver.
Kirill Rybalchenko (5):
app/testpmd: add new commands to manipulate with pctype mapping
net/i40e: add function to initialize pctype mapping tab
Add new function i40e_set_default_pctype_table() to
initialize flow type to pctype dynamic mapping table
with default values.
Signed-off-by: Kirill Rybalchenko
---
drivers/net/i40e/i40e_rxtx.c | 57
drivers/net/i40e/i40e_rxtx.h | 1 +
2 files changed
Add new functions which allow modify, return or reset to default
the contents of flow type to pctype dynamic mapping table.
Signed-off-by: Kirill Rybalchenko
---
drivers/net/i40e/rte_pmd_i40e.c | 98 +
drivers/net/i40e/rte_pmd_i40e.h | 60 +
Add new commands to manipulate with dynamic flow type to
pctype mapping table in i40e PMD.
Commands allow to print table, modify it and reset to default value.
Signed-off-by: Kirill Rybalchenko
---
app/test-pmd/cmdline.c | 263 +
1 file changed, 26
Functions i40e_pctype_to_flowtype and i40e_flowtype_to_pctype are
changed to work with dynamic mapping pctype to flowtype table.
This table is located in private data area of adapter structure.
Therefore those functions need one extra parameter pointing to
the adapter data structure.
Signed-off-by
Implement dynamic mapping of software flow types to hardware pctypes.
This allows to add new flow types and pctypes for DDP without changing
API of the driver. The mapping table is located in private
data area for particular network adapter and can be individually
modified with set of appropriate f
On 8/24/2017 10:55 AM, Luca Boccassi wrote:
> On Thu, 2017-08-24 at 10:35 +0100, Ferruh Yigit wrote:
>> On 8/22/2017 11:02 AM, Luca Boccassi wrote:
>>> On Mon, 2017-08-21 at 17:19 -0700, Yipeng Wang wrote:
Membership library is an extension and generalization of a
traditional
filter
This parameter makes number of cryptodev descriptors adjustable
and defaults to earlier hardcoded default of 2048.
Signed-off-by: Burakov, Anatoly
---
app/test-crypto-perf/cperf_options.h | 2 ++
app/test-crypto-perf/cperf_options_parsing.c | 21 +
app/test-crypto-pe
This patch adds a new benchmarking mode, which is intended for
microbenchmarking individual parts of the cryptodev framework,
specifically crypto ops alloc-build-free, cryptodev PMD enqueue
and cryptodev PMD dequeue.
It works by first benchmarking crypto operation alloc-build-free
loop (no enqueue
Signed-off-by: Burakov, Anatoly
---
doc/guides/tools/cryptoperf.rst | 4
1 file changed, 4 insertions(+)
diff --git a/doc/guides/tools/cryptoperf.rst b/doc/guides/tools/cryptoperf.rst
index 457f817..985848b 100644
--- a/doc/guides/tools/cryptoperf.rst
+++ b/doc/guides/tools/cryptoperf.rst
@
From: "Burakov, Anatoly"
This patchset adds a new "PMD cyclecount" test mode for test-crypto-perf
application. This mode is intended to measure hardware acceleration
cost (in terms of cycle count) more accurately than throughput test.
The general idea is the following:
- Measure build-alloc-free
Also, document the new pmd-cyclecount-specific flag.
Signed-off-by: Burakov, Anatoly
---
doc/guides/rel_notes/release_17_11.rst | 6 ++
doc/guides/tools/cryptoperf.rst| 10 +-
2 files changed, 15 insertions(+), 1 deletion(-)
diff --git a/doc/guides/rel_notes/release_17_11.r
In function cmd_show_bonding_config_parsed() used number represent
the bond type,in order more detailed,add bond type description
otherwise we may confused about the number type.
And also,the primary port just use in mode active backup and tlb,
so,when the mode is active backup or tlb show the prim
Hi,
I make a new patch for this issue becase the previous patch has delete
when the version 17.08 release.
The website is http://www.dpdk.org/dev/patchwork/patch/27851/,Thank
you.
Thomas Monjalon 写于 2017/08/24 04:22:17:
> 发件人: Thomas Monjalon
> 收件人: xie.rongqi...@zte.com.cn, Declan
This application shows a simple usage of the
rte_flow API for hardware filtering offloading.
In this demo we are filtering specific IP to
specific target queue, while sending all the
rest of the packets to other queue.
Included in this commit is a simple python
script file for sending custom pack
On 8/23/2017 4:09 PM, Nélio Laranjeiro wrote:
> On Mon, Aug 14, 2017 at 02:32:24PM +0300, Matan Azrad wrote:
>> The corrupted code didn't unlock the spinlock in xstats
>> get and reset functions error flow.
>>
>> Hence, if these errors happaned, the device spinlock was
>> left locked and many mlx5
This removes the dependency on specific Mellanox OFED libraries by
using the upstream rdma-core and linux upstream community code.
Minimal requirements: rdma-core v16 and Kernel Linux 4.14.
Signed-off-by: Shachar Beiser
---
doc/guides/nics/mlx5.rst | 29 +-
drivers/net/mlx5/Make
On Wed, Aug 23, 2017 at 10:10:58AM +0300, Shahaf Shuler wrote:
> Extend debug logs verbosity by printing the full completion with error
> along with the entire txq in case of error. For the Rx case no logs were
> added since such errors are counted and recovered by the Rx data path.
>
> Such print
On Wed, Aug 23, 2017 at 10:33:57AM +0300, Shahaf Shuler wrote:
> vPMD Tx function assumes that after the scatter of the
> multi-segment packets the next packet will be a single segment packet.
>
> This is not current as the function can return due to lack of resources
> without sending all of the
On Wed, Aug 23, 2017 at 10:33:58AM +0300, Shahaf Shuler wrote:
> Mellanox NICs has a limitation on the number of mbuf segments a multi
> segment mbuf can have. The max number depends on the Tx offloads requested.
>
> The current code not enforce such limitation, which might cause
> malformed WQEs
Function i40e_vsi_config_vlan_stripping doesn't strip vlan tag for vf.
The patch should fix the problem.
Signed-off-by: Zang MingJie
---
drivers/net/i40e/i40e_ethdev.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/i40e/i40e_ethdev.c b/drivers/net/i40e/i40e_ethde
Patch implements the HW mempool offload driver for packets buffer.
This HW mempool offload driver has dependency on:
- IOVA infrastrucure [1].
- Dynamically configure mempool handle (ie.. --mbuf-pool-ops eal arg) [2].
- Infrastructure to support octeontx HW mempool manager [3].
Mempool driver bas
add HW constants of octeontx fpa mempool device.
Signed-off-by: Santosh Shukla
Signed-off-by: Jerin Jacob
---
drivers/mempool/octeontx/octeontx_fpavf.h | 71 +++
1 file changed, 71 insertions(+)
create mode 100644 drivers/mempool/octeontx/octeontx_fpavf.h
diff --gi
Signed-off-by: Santosh Shukla
Signed-off-by: Jerin Jacob
---
config/common_base | 6 +++
drivers/Makefile | 5 +-
drivers/mempool/Makefile | 2 +
drivers/mempool/octeontx/Makefile | 60
A mempool device is set of PCIe vfs.
On Octeontx HW, each mempool devices are enumerated as
separate SRIOV VF PCIe device.
In order to expose as a mempool device:
On PCIe probe, the driver stores the information associated with the
PCIe device and later upon application pool request
(e.g. rte_memp
Upon pool allocation request by application, Octeontx FPA alloc
does following:
- Gets free pool from pci fpavf array.
- Uses mbox to communicate fpapf driver about,
* gpool-id
* pool block_sz
* alignemnt
- Programs fpavf pool boundary.
Signed-off-by: Santosh Shukla
Signed-off-by: Jerin Jac
Upon pool free request from application, Octeon FPA free
does following:
- Uses mbox to reset fpapf pool setup.
- frees fpavf resources.
Signed-off-by: Santosh Shukla
Signed-off-by: Jerin Jacob
---
drivers/mempool/octeontx/octeontx_fpavf.c | 107
drivers/mempool/o
Signed-off-by: Santosh Shukla
Signed-off-by: Jerin Jacob
---
drivers/mempool/octeontx/Makefile | 13 +
drivers/mempool/octeontx/rte_mempool_octeontx.c | 65 -
2 files changed, 76 insertions(+), 2 deletions(-)
diff --git a/drivers/mempool/octeontx/Makefi
Signed-off-by: Santosh Shukla
Signed-off-by: Jerin Jacob
---
drivers/mempool/octeontx/octeontx_fpavf.c | 22 ++
drivers/mempool/octeontx/octeontx_fpavf.h | 2 ++
drivers/mempool/octeontx/rte_mempool_octeontx.c | 12 +++-
3 files changed, 35 insertions(+),
Allow mempool HW manager to advertise his pool capability.
Signed-off-by: Santosh Shukla
Signed-off-by: Jerin Jacob
---
drivers/mempool/octeontx/rte_mempool_octeontx.c | 10 +-
1 file changed, 9 insertions(+), 1 deletion(-)
diff --git a/drivers/mempool/octeontx/rte_mempool_octeontx.c
Add support for update range ops in mempool driver.
Allow more than one HW pool when using OcteonTx mempool driver:
By storing each pool information to the list and find appropriate
list element by matching the rte_mempool pointers.
Signed-off-by: Santosh Shukla
Signed-off-by: Jerin Jacob
---
Adding global api to translate handle to pool,
needed by octeontx pmd.
Signed-off-by: Santosh Shukla
Signed-off-by: Jerin Jacob
---
drivers/mempool/octeontx/octeontx_fpavf.c | 9 +
drivers/mempool/octeontx/octeontx_fpavf.h | 2 ++
drivers/mempool/octeontx
This commit adds a section to the docs listing the mempool
device PMDs available.
It then adds the octeontx fpavf mempool PMD to the listed mempool
devices.
Signed-off-by: Santosh Shukla
Signed-off-by: Jerin Jacob
---
MAINTAINERS | 6 ++
doc/guides/index.rst|
On 8/24/2017 1:23 PM, Shachar Beiser wrote:
> This removes the dependency on specific Mellanox OFED libraries by
> using the upstream rdma-core and linux upstream community code.
>
> Minimal requirements: rdma-core v16 and Kernel Linux 4.14.
4.14?
Is 4.13 released?
>
> Signed-off-by: Shacha
On Thu, Aug 24, 2017 at 10:46:31AM +0300, Raslan Darawsheh wrote:
> Added new capability to the list of rx offloads for hw timestamp
>
> The PMDs how expose this capability will always have it enabled.
Not sure this comment is accurate, Rx offloads are application request, PMD
does not have to en
Everytime the rte_sched_port_update_subport_stats_on_drop or
rte_sched_port_update_queue_stats_on_drop functions are called the
n_pkts_dropped counter is incremented.
The n_pkts_red_dropped counter is only incremented when the function
argument red is non-zero.
Packets that are RED-dropped are no
On Thu, Aug 24, 2017 at 10:46:32AM +0300, Raslan Darawsheh wrote:
> Added new print in case a PMD exposes Rx timestamp.
> Also, added a print for timestamp value in rxonly mode
> in case the packet was timestamped.
>
> Signed-off-by: Raslan Darawsheh
> ---
> app/test-pmd/config.c | 3 +++
> app/
Main changes:
1. The key_mask parameter is added to all the hash tables that were
previously missing it, as well to the hash compute function. This was
first started in DPDK 2.0, but was only implemented for a couple of
hash tables. The benefit of this approach is that it allows for bette
Signed-off-by: Cristian Dumitrescu
---
test/test-pipeline/main.h | 5 +-
test/test-pipeline/pipeline_hash.c | 107 +
2 files changed, 18 insertions(+), 94 deletions(-)
diff --git a/test/test-pipeline/main.h b/test/test-pipeline/main.h
index 3685849.
Signed-off-by: Cristian Dumitrescu
---
test/test/test_table.c | 1 +
test/test/test_table.h | 3 +-
test/test/test_table_combined.c | 140 +
test/test/test_table_tables.c | 148 +---
4 files changed, 1
Signed-off-by: Cristian Dumitrescu
---
.../pipeline/pipeline_flow_classification.c| 9 ++--
.../pipeline/pipeline_flow_classification_be.c | 54 --
.../ip_pipeline/pipeline/pipeline_passthrough_be.c | 18
.../ip_pipeline/pipeline/pipeline_routing_be.c
Signed-off-by: Cristian Dumitrescu
---
doc/guides/rel_notes/deprecation.rst | 8
1 file changed, 8 deletions(-)
diff --git a/doc/guides/rel_notes/deprecation.rst
b/doc/guides/rel_notes/deprecation.rst
index 3362f33..e181a61 100644
--- a/doc/guides/rel_notes/deprecation.rst
+++ b/doc/gu
On Thu, Aug 24, 2017 at 10:46:33AM +0300, Raslan Darawsheh wrote:
> Expose a new capapilty of Rx hw timestamp and
> added new device args to enable it hw_timestamp.
> It will add the raw hw timestamp into the packets.
>
> Its expected that it will lower down the performance since using it
> will d
Hi Nelio,
Please see my comments in line.
Ori
> -Original Message-
> From: Nélio Laranjeiro [mailto:nelio.laranje...@6wind.com]
> Sent: Thursday, August 24, 2017 9:54 AM
> To: Ori Kam
> Cc: adrien.mazar...@6wind.com; dev@dpdk.org
> Subject: Re: [RFC] net/mlx5: support count flow action
PMD uses Verbs object which were not available in the shared memory, in
addition, due to IO pages, it was not possible to use the primary
process Tx queues from a secondary process.
This patch modify the location where Verbs objects are allocated (from
process memory address space to shared memory
rte_eth_dev created by primary process were not available in secondary
process, it was not possible to use the primary process local memory
object from a secondary process.
This patch modify the reference of primary rte_eth_dev object, use
local rte_eth_dev secondary process instead.
Cc: Nelio La
On 8/23/2017 9:40 PM, Thomas Monjalon wrote:
> 21/08/2017 15:51, Ferruh Yigit:
>> Some of the "All rights reserved." note looks like duplicate, there is
>> one for each copyright note in the same line, and extra one after the
>> copyright notes. Sample is in below patch.
>>
>> Although this looks l
> -Original Message-
> From: Wiles, Keith
> Sent: Wednesday, August 23, 2017 4:05 PM
> To: Carrillo, Erik G
> Cc: rsanf...@akamai.com; dev@dpdk.org
> Subject: Re: [dpdk-dev] [PATCH 0/3] *** timer library enhancements ***
>
>
> > On Aug 23, 2017, at 2:28 PM, Carrillo, Erik G
> wrote:
>
Generic Segmentation Offload (GSO) is a SW technique to split large
packets into small ones. Akin to TSO, GSO enables applications to
operate on large packets, thus reducing per-packet processing overhead.
To enable more flexibility to applications, DPDK GSO is implemented
as a standalone library.
Generic Segmentation Offload (GSO) is a SW technique to split large
packets into small ones. Akin to TSO, GSO enables applications to
operate on large packets, thus reducing per-packet processing overhead.
To enable more flexibility to applications, DPDK GSO is implemented
as a standalone library.
From: Mark Kavanagh
This patch adds GSO support for VxLAN-encapsulated packets. Supported
VxLAN packets must have an outer IPv4 header (prepended by an optional
VLAN tag), and contain an inner TCP/IPv4 packet (with an optional inner
VLAN tag).
VxLAN GSO assumes that all input packets have correc
This patch adds GSO support for TCP/IPv4 packets. Supported packets
may include a single VLAN tag. TCP/IPv4 GSO assumes that all input
packets have correct checksums, and doesn't update checksums for output
packets (the responsibility for this lies with the application).
Additionally, TCP/IPv4 GSO
From: Mark Kavanagh
This patch adds GSO support for GRE-tunneled packets. Supported GRE
packets must contain an outer IPv4 header, and inner TCP/IPv4 headers.
They may also contain a single VLAN tag. GRE GSO assumes that all input
packets have correct checksums and doesn't update checksums for ou
This patch adds GSO support to the csum forwarding engine. Oversized
packets transmitted over a GSO-enabled port will undergo segmentation
(with the exception of packet-types unsupported by the GSO library).
GSO support is disabled by default.
GSO support may be toggled on a per-port basis, using
Hi folks,
Resurrecting this old thread. I ran across this issue recently in DPDK
17.05, and it's also present in17.08. It appears no fix was committed.
I'm working on a solution, but if anyone has a fix in flight please let
me know.
Regards,
Roger
On 4/29/16 3:29 AM, Olivier Matz wrote:
Hi Nelio
> -Original Message-
> From: Nélio Laranjeiro [mailto:nelio.laranje...@6wind.com]
> Sent: Thursday, August 24, 2017 10:38 AM
> To: Matan Azrad
> Cc: Adrien Mazarguil ; dev@dpdk.org
> Subject: Re: [PATCH 1/2] net/mlx5: support device removal event
>
> On Wed, Aug 23, 2017 at 07:4
[Apologies for the late notice]
Below are the features that we're planning to submit for the 17.11 release:
- new ethdev Rx/Tx offloads API
- new IPsec inline offload API
- rework mlx drivers to support upstream ibverbs from
linux-rdma.org
- s
Hey Pragash,
I am not the author of the code, but I guess it is done that way
because modern compilers do recognize power of two constants and do
substitute division and modulo operations with corresponding bit
manipulations.
Just try to compile a small program like the following:
volatile unsign
On Thu, Aug 24, 2017 at 12:23:10PM +, Shachar Beiser wrote:
> This removes the dependency on specific Mellanox OFED libraries by
> using the upstream rdma-core and linux upstream community code.
>
> Minimal requirements: rdma-core v16 and Kernel Linux 4.14.
Is not it also suppose to keep w
Hi Ori,
On Thu, Aug 24, 2017 at 02:04:32PM +, Ori Kam wrote:
> Hi Nelio,
>
> Please see my comments in line.
>
> Ori
>
> > -Original Message-
> > From: Nélio Laranjeiro [mailto:nelio.laranje...@6wind.com]
> > Sent: Thursday, August 24, 2017 9:54 AM
> > To: Ori Kam
> > Cc: adrien.ma
For complex packets use raw flow type with pre-constructed packet buffer
instead of creating a packet internally in PMD.
Kirill Rybalchenko (2):
ethdev: add support for raw flow type for flow director
net/i40e: add support for raw flow type for flow director
drivers/net/i40e/i40e_fdir.c|
When addidng flow director filter for raw flow type, instead
of constructing packet use buffer with pre-constructed packet.
Signed-off-by: Kirill Rybalchenko
---
drivers/net/i40e/i40e_fdir.c | 27 +++
1 file changed, 19 insertions(+), 8 deletions(-)
diff --git a/drivers/
Add new structure rte_eth_raw_flow to the union rte_eth_fdir_flow
to support filter for raw flow type
Signed-off-by: Kirill Rybalchenko
---
lib/librte_ether/rte_eth_ctrl.h | 10 ++
1 file changed, 10 insertions(+)
diff --git a/lib/librte_ether/rte_eth_ctrl.h b/lib/librte_ether/rte_eth_c
This series of patches implements the mlx4-pmd with Tx data path that directly
access the device queues for transmitting packets, bypassing the ibverbs Tx
data path altogether.
Using this scheme allows the PMD to work with upstream rdma-core package
instead of the Mellanox OFED one without sacrific
PMD now sends the single-buffer packets directly to the device
bypassing the ibv Tx post and poll routines.
Signed-off-by: Moti Haimovsky
---
drivers/net/mlx4/mlx4_prm.h | 253 +
drivers/net/mlx4/mlx4_rxtx.c | 260 +++--
PRM now supports transmitting packets spanning over arbitrary
amount of buffers.
Signed-off-by: Moti Haimovsky
---
drivers/net/mlx4/mlx4_prm.h | 16 +---
drivers/net/mlx4/mlx4_rxtx.c | 213 +++
drivers/net/mlx4/mlx4_rxtx.h | 3 +-
drivers/net/mlx4/mlx4
PMD now take into consideration the amount of entries in the TxQ
a packet occupies when choosing weather to set the report-completion flag
to the chip or not.
Signed-off-by: Moti Haimovsky
---
drivers/net/mlx4/mlx4_rxtx.c | 30 +++---
drivers/net/mlx4/mlx4_rxtx.h | 2 +-
PMD now supports offloading the ip and tcp/udp checksum header calculation
(including tunneled packets) to the hardware.
Signed-off-by: Moti Haimovsky
---
drivers/net/mlx4/mlx4.c| 7 +++
drivers/net/mlx4/mlx4.h| 2 ++
drivers/net/mlx4/mlx4_ethdev.c | 6 ++
drivers/net/
Added loopback functionality use when the chip is a VF in order to
enable packet transmission between VFs and between VFs and PF.
Signed-off-by: Moti Haimovsky
---
drivers/net/mlx4/mlx4_prm.h | 2 +-
drivers/net/mlx4/mlx4_rxtx.c | 28 ++--
drivers/net/mlx4/mlx4_rxtx.h |
NFP PMD has just had support for SRIOV VFs until now. This patchset adds
support for the PF, but just for being used as another DPDK port. No VF
management is added by now.
NFP is a programmable device and it supports virtual NICs (vNICs) through
firmware implementation. Different firmware applica
Working with the PF requires access to the NFP for basic configuration.
NSP is the NFP Service Processor helping with hardware and firmware
configuration. NSPU is the NSP user space interface for working with the
NSP.
Configuration through NSPU allows to create PCI BAR windows for accessing
differ
Configuring the NFP PMD for using the PF requires access through the
NSPU interface for device configuration. This patch adds a specific probe
function for the PF which uses the NSPU interface. Just basic NSPU access
is done by now reading the NSPU ABI version.
No ethernet port is created yet.
Si
Using NSPU interface for fw upload. Firmware file needs to be
installed in specific path inside system firmware directory.
NSPU buffer is used for writing the firmware before sending the
command.
Signed-off-by: Alejandro Lucero
---
drivers/net/nfp/nfp_nspu.c | 66 +++
NSPU interface declares a buffer controlled by the NFP NSP service
processor. It is possible to send commands to the NSP using the NSPU
and this buffer for data related to the command. A command can imply
buffer read, buffer write, both or none.
Initial command for resetting the firmware is added
A NFP PF PCI devices can have PCI ID 4000 or 6000.
Signed-off-by: Alejandro Lucero
---
drivers/net/nfp/nfp_net.c | 4
drivers/net/nfp/nfp_net_pmd.h | 1 +
2 files changed, 5 insertions(+)
diff --git a/drivers/net/nfp/nfp_net.c b/drivers/net/nfp/nfp_net.c
index e2fe83a..1890a4a 100644
-
PMD will use this function for uploading the firmware. First, a
symbol resolution is done for finding out if there is a firmware
already there. If not, a NFP reset is called before using NSPU
fw upload code.
PMD PF probe function is now using this logic.
Signed-off-by: Alejandro Lucero
---
driv
Firmware has symbols helping to configure things like number of
PF ports, vNIC BARs addresses inside NFP memories, or ethernet
link state. Different firmware apps have different things to map
and likely different internal NFP addresses to use.
Host drivers can use the NSPU interface for getting sy
NFP vNICs use a subset of PCI device BARs. vNIC config bar depends on
firmware symbol defining how to map it through a NFP expansion bar.
This patch adds a NSPU API function for getting a vNIC config bar
mapped through a expansion bar giving a firmware symbol. The PMD will
use the PCI bar offset r
nfp_net_init is where a dpdk port related to a eth_dev is initialized.
NFP VF vNICs use VF PCI BARs as they come after SRIOV is enabled. But for
NFP PF vNIC just a subset of PF PCI BARs are used.
This patch adds support for mapping the right PCI BAR subsets for the PF
vNIC. It uses the NSPU API fu
NFP vNICs use a subset of PCI device BARs. vNIC rx/tx bars point to
NFP hardware queues unit. Unline vNIC config bar, the NFP address is
always the same so the NFP expansion bar configuration always uses
the same hardcoded physical address.
This patch adds a NSPU API function for getting vNIC rx/t
A NFP PF PCI device can have several physical ports, up to 8. Because
DPDK core creates one eth_dev per PCI device, nfp pf probe function
is used. Number of PF ports is obtained from firmware symbol using
NSPU API. Inside PF probe function an eth_dev per port is created and
nfp_net_init invoked for
Adding a new NSPU command for being able to read and write the ethernet
port table from/to the NFP. This will allow the PMD to put the Link up
or down when a port is started or stopped. Until now, this was performed
by the firmware independently of PMD functionality.
The ethernet port table has al
NFP can support several physical ports per PF device. Depending on
firmware info, one or more eth_dev objects will need to be created.
This patch adds the call to create just one eth_dev by now with future
commits supporting the multiport option. Once the eth_dev has been
created, probe function i
It is PMD task to configure the hardware port: link up when port started
and link down when port stopped. This is not required for VFs but it is
for PF ports.
A minor refactoring in PMD stop and close functions is done because the
Link down needs to happen just when device is stopped.
Signed-off-
During initialization, mac address is read from configuration bar. This is
the default option when using VFs.
This patch adds support for reading the mac address using the NSPU
interface when PMD works with the PF.
Signed-off-by: Alejandro Lucero
---
drivers/net/nfp/nfp_net.c | 59 +
NFP PMF has now support for both, PF and VFs. This patch updates
the guide and give some information about implications.
Signed-off-by: Alejandro Lucero
---
doc/guides/nics/nfp.rst | 71 -
1 file changed, 52 insertions(+), 19 deletions(-)
diff --g
This patchset adds:
- support for xstats get by id
- support for rx_queue_count
- support for rx_descriptor_status
- support for rx_descriptor_done
- support for tx_descriptor_status
- support for flow filter ops
- new HWRM structures which are used by the flow filtering functions
It
This patch adds support for xstats_get_by_id/xstats_get_names_by_id.
Signed-off-by: Ajit Khaparde
---
drivers/net/bnxt/bnxt_ethdev.c | 2 ++
drivers/net/bnxt/bnxt_stats.c | 44 ++
drivers/net/bnxt/bnxt_stats.h | 5 +
3 files changed, 51 insertions(+
1 - 100 of 118 matches
Mail list logo
