On 9/24/20 7:25 AM, Xia, Chenbo wrote:
> Hi Maxime,
>
>> -Original Message-
>> From: dev On Behalf Of Maxime Coquelin
>> Sent: Friday, September 11, 2020 11:08 PM
>> To: dev@dpdk.org; Fu, Patrick ; amore...@redhat.com
>> Cc: Maxime Coquelin
>> Subject: [dpdk-dev] [PATCH 1/7] bus/vdev:
On 9/24/20 7:25 AM, Xia, Chenbo wrote:
> Hi Maxime,
>
>> -Original Message-
>> From: dev On Behalf Of Maxime Coquelin
>> Sent: Friday, September 11, 2020 11:08 PM
>> To: dev@dpdk.org; Fu, Patrick ; amore...@redhat.com
>> Cc: Maxime Coquelin
>> Subject: [dpdk-dev] [PATCH 4/7] net/virti
On 9/24/20 7:25 AM, Xia, Chenbo wrote:
> Hi Maxime,
>
>> -Original Message-
>> From: dev On Behalf Of Maxime Coquelin
>> Sent: Friday, September 11, 2020 11:08 PM
>> To: dev@dpdk.org; Fu, Patrick ; amore...@redhat.com
>> Cc: Maxime Coquelin
>> Subject: [dpdk-dev] [PATCH 7/7] net/virti
Remove RTE_MACHINE_CPUFLAG_ macros from the build.
Deprecation notice sent, pasted here for reference:
* build macros: The macros defining RTE_MACHINE_CPUFLAG_* will be removed
from the build. The information provided by these macros is available
through standard compiler macros. For example,
Replace use of RTE_MACHINE_CPUFLAG macros with regular compiler
macros, which are more complete than those provided by DPDK, and as such
it allows new instruction sets to be leveraged without having to do
extra work to set them up in DPDK.
Signed-off-by: Sean Morrissey
Signed-off-by: Radu Nicolau
RTE_MACHINE_CPUFLAG macros are replaced with predefined
compiler defines.
Signed-off-by: Sean Morrissey
Signed-off-by: Radu Nicolau
---
doc/guides/prog_guide/writing_efficient_code.rst | 2 --
doc/guides/rel_notes/release_20_11.rst | 1 +
2 files changed, 1 insertion(+), 2 deletions(-
Replace use of RTE_MACHINE_CPUFLAG macros with regular compiler
macros, which are more complete than those provided by DPDK, and as such
it allows new instruction sets to be leveraged without having to do
extra work to set them up in DPDK.
Signed-off-by: Sean Morrissey
Signed-off-by: Radu Nicolau
Replace use of RTE_MACHINE_CPUFLAG macros with regular compiler
macros, which are more complete than those provided by DPDK, and as such
it allows new instruction sets to be leveraged without having to do
extra work to set them up in DPDK.
Signed-off-by: Sean Morrissey
Signed-off-by: Radu Nicolau
> -Original Message-
> From: Bruce Richardson
> Sent: Wednesday, September 23, 2020 3:59 PM
> To: Juraj Linkeš
> Cc: ruifeng.w...@arm.com; honnappa.nagaraha...@arm.com;
> phil.y...@arm.com; vcchu...@amazon.com; dharmik.thak...@arm.com;
> jerinjac...@gmail.com; hemant.agra...@nxp.com; de
Hi Phil,
On 24/9/2020 6:39 AM, Phil Yang wrote:
Since rte_atomicXX APIs are not allowed to be used, use C11 atomic
builtins for power in use state update.
Signed-off-by: Phil Yang
Reviewed-by: Ruifeng Wang
Reviewed-by: Honnappa Nagarahalli
---
lib/librte_power/power_acpi_cpufreq.c | 45 +
Thor based NICs can support PAM4 as wells as NRZ link negotiation.
With this patch we are adding support for 200G link speeds based on
PAM4 signaling. While PAM4 can negotiate speeds for 50G and 100G as
well, the PMD will use NRZ signalling for these speeds.
Signed-off-by: Ajit Khaparde
Reviewed-
From: Yi Yang
VXLAN UDP/IPv4 GRO can help improve VM-to-VM UDP
performance when UFO or GSO is enabled in VM, GRO
must be supported if UFO or GSO is enabled,
otherwise, performance can't get big improvement
if only GSO is there.
With this enabled in DPDK, OVS DPDK can leverage it
to improve VM-to
From: Yi Yang
Release 20.11 added UDP/IPv4 and VXLAN UDP/IPv4 support
for GRO, so update prog_guide and rel_notes to reflect
these changes.
Signed-off-by: Yi Yang
---
doc/guides/prog_guide/generic_receive_offload_lib.rst | 6 +++---
doc/guides/rel_notes/release_20_11.rst| 6 +++
From: Yi Yang
In case that UFO or GSO is enabled, GRO is very necessary,
especially for UDP, it is more so. Many NICs can't support
VXLAN UDP UFO/USO and VLAN UFO/USO, so UDP performance
improvement depends on GSO and GRO to a great extent.
This patch series added VLAN UDP/IPv4 GRO and VXLAN UDP
From: Yi Yang
UDP/IPv4 GRO can help improve VM-to-VM UDP performance
when UFO or GSO is enabled in VM, GRO must be supported
if UFO or GSO is enabled, otherwise, performance can't
get big improvement if only GSO is there.
With this enabled in DPDK, OVS DPDK can leverage it
to improve VM-to-VM UD
* One can now configure the number of rules per batch
* Refactored flow_count variable to rules_count as it is
related to the newly added rules_batch variable
* Added default values to usage function
Signed-off-by: Georgios Katsikas
---
app/test-flow-perf/main.c | 87 +++-
Hi Wisam,
The patch is resubmitted as you suggested.
thanks,
Georgios
On Thu, Sep 24, 2020 at 11:05 AM Wisam Monther wrote:
> Hi Georgios,
>
> >-Original Message-
> >From: george@gmail.com On Behalf Of Georgios
> >Katsikas
> >Sent: Tuesday, September 8, 2020 9:13 AM
> >To: wis...@
On Thu, Sep 24, 2020 at 12:35:58AM +0200, Thomas Monjalon wrote:
> 24/09/2020 00:02, Stephen Hemminger:
> > On Wed, 23 Sep 2020 23:52:07 +0200
> > Thomas Monjalon wrote:
> >
> > > > > > > Yes it is a step in the right direction.
> > > > > > > Changing the API means adding some error checks in eve
On Wed, Sep 23, 2020 at 07:21:16PM +0100, Harris, James R wrote:
>Hi,
>
>
>SPDK would like to use DPDK’s pkg-config files rather than rolling our
>own linker arguments. I’m running into a couple of issues – one looks
>like a bug, the other is not as clear.
>
>
>First is the
On Mon, Sep 21, 2020 at 3:39 PM Ferruh Yigit wrote:
>
> Error observed with gcc 11 under development
> gcc (GCC) 11.0.0 20200920 (experimental)
>
> ../app/test-pmd/config.c:1777:61:
> warning: argument 3 of type ‘const uint32_t[n]’
> {aka ‘const unsigned int[n]’} declared as a vari
On Mon, Sep 21, 2020 at 3:39 PM Ferruh Yigit wrote:
>
> Error observed with gcc 11 under development
> gcc (GCC) 11.0.0 20200920 (experimental)
>
> build error:
> In file included from ../buildtools/pmdinfogen/pmdinfogen.c:17:
> ../buildtools/pmdinfogen/pmdinfogen.c: In function ‘parse_elf’:
> ../
Now that make is depricated, remove any reference from the
build instructions for vm_power_manager and guest_cli
Signed-off-by: David Hunt
---
.../sample_app_ug/vm_power_management.rst | 66 +++
1 file changed, 9 insertions(+), 57 deletions(-)
diff --git a/doc/guides/sample_
Now that make is deprecated, remove any reference from the
build instructions for vm_power_manager and guest_cli
Signed-off-by: David Hunt
---
.../sample_app_ug/vm_power_management.rst | 66 +++
1 file changed, 9 insertions(+), 57 deletions(-)
diff --git a/doc/guides/sample_
Now that make is deprecated, remove any reference from the
build instructions for vm_power_manager and guest_cli
Signed-off-by: David Hunt
---
v2: fix typo 'depricated'
v3: add -in-reply-to
---
.../sample_app_ug/vm_power_management.rst | 66 +++
1 file changed, 9 insertions(
Thanks,
Ori
> -Original Message-
> From: Tejasree Kondoj
> Sent: Thursday, September 24, 2020 8:31 AM
>
> Thanks,
> Tejasree
>
> > -Original Message-
> > From: Ori Kam
> > Sent: Wednesday, September 23, 2020 8:00 PM
> > To: Tejasree Kondoj ; Asaf Penso
> > ; Stephen Hemminger
>-Original Message-
>From: dev On Behalf Of Timothy McDaniel
>Sent: Friday, September 11, 2020 10:28 PM
>Cc: Jerin Jacob Kollanukkaran ;
>mattias.ronnb...@ericsson.com; liang.j...@intel.com;
>peter.mccar...@intel.com; nipun.gu...@nxp.com; Pavan Nikhilesh
>Bhagavatula ; dev@dpdk.org;
>erik.
On Thu, Sep 24, 2020 at 10:51:33AM +0100, David Hunt wrote:
> Now that make is deprecated, remove any reference from the
> build instructions for vm_power_manager and guest_cli
>
> Signed-off-by: David Hunt
>
> ---
> v2: fix typo 'depricated'
> v3: add -in-reply-to
> ---
> .../sample_app_ug/vm_
24/09/2020 11:12, Bruce Richardson:
> On Thu, Sep 24, 2020 at 12:35:58AM +0200, Thomas Monjalon wrote:
> > 24/09/2020 00:02, Stephen Hemminger:
> > > On Wed, 23 Sep 2020 23:52:07 +0200
> > > Thomas Monjalon wrote:
> > >
> > > > > > > > Yes it is a step in the right direction.
> > > > > > > > Chan
Hi Ori,
Please see inline.
Thanks,
Tejasree
> -Original Message-
> From: Ori Kam
> Sent: Thursday, September 24, 2020 3:22 PM
> To: Tejasree Kondoj ; Asaf Penso
> ; Stephen Hemminger
> Cc: Akhil Goyal ; Radu Nicolau
> ; Declan Doherty ;
> NBU-Contact-Thomas Monjalon ; Ferruh Yigit
> ;
On 18/09/2020 06:32, Chen, BoX C wrote:
>> -Original Message-
>> From: Kevin Traynor
>> Sent: September 16, 2020 18:10
>> To: Chen, BoX C ; Burakov, Anatoly
>>
>> Cc: dev@dpdk.org; Abhishek Marathe ;
>> Akhil Goyal ; Ali Alnubani ;
>> Walker, Benjamin ; David Christensen
>> ; Hemant Agraw
On 21/09/2020 11:59, Pei Zhang wrote:
> Hello Kevin,
>
> Testing with dpdk 18.11.10 from Red Hat looks good.
>
> We cover below 15 scenarios and and all get PASS on RHEL8 testing:
>
> (1)Guest with device assignment(PF) throughput testing(1G hugepage size): PASS
> (2)Guest with device assignment
On 20/09/2020 16:10, Ali Alnubani wrote:
> Hi,
>
>> -Original Message-
>> From: Kevin Traynor
>> Sent: Monday, September 7, 2020 1:12 PM
>> To: sta...@dpdk.org
>> Cc: dev@dpdk.org; Abhishek Marathe ;
>> Akhil Goyal ; Ali Alnubani ;
>> benjamin.wal...@intel.com; David Christensen ;
>> Hema
On 24/9/2020 11:03 AM, Bruce Richardson wrote:
On Thu, Sep 24, 2020 at 10:51:33AM +0100, David Hunt wrote:
Now that make is deprecated, remove any reference from the
build instructions for vm_power_manager and guest_cli
Signed-off-by: David Hunt
---
v2: fix typo 'depricated'
v3: add -in-rep
Meeting minutes of 24 September 2020
Agenda:
* Release Dates
* Highlights
* Subtrees
* LTS
* Conferences
Participants:
* Arm
* Broadcom
* Debian/Microsoft
* Intel
* Marvell
* Nvidia
* NXP
* Red Hat
Release Dates
-
* v20.11 dates
* -rc1:
replace mmap() with rte_mem_map()
and replace munmap() with rte_mem_unmap()
Fixes: e1d9a02ad8f0 ("common/octeontx2: introduce common device class")
Signed-off-by: Sarosh Arif
---
v2:
update description and commit message
---
drivers/common/octeontx2/otx2_dev.c | 8 +---
1 file changed, 5 in
dev On Behalf Of Phil Yang : writes:
> > Subject: [dpdk-dev] [PATCH] [PATCH V2] testpmd: add eeprom/module
> > eeprom display
> >
> > Add module EEPROM/EEPROM dump command
> >"show port (module_eeprom|eeprom)"
> > Commands will dump the content of the EEPROM/module
> > EEPROM for the sele
> Subject: [dpdk-dev] [PATCH 3/4] app/testpmd: fix build with gcc 11
>
> Error observed with gcc 11 under development
> gcc (GCC) 11.0.0 20200920 (experimental)
>
> ../app/test-pmd/config.c:1777:61:
> warning: argument 3 of type ‘const uint32_t[n]’
> {aka ‘const unsigned int[n]’} de
Forward error correction (FEC) is a bit error correction mode.
It adds error correction information to data packets at the
transmit end, and uses the error correction information to correct
the bit errors generated during data packet transmission at the
receive end. This improves signal quality but
Added the FEC API, and hns3 FEC PMD information in
release 20.11.rst file.
Signed-off-by: Min Hu (Connor)
Reviewed-by: Wei Hu (Xavier)
Reviewed-by: Chengwen Feng
Reviewed-by: Chengchang Tang
---
doc/guides/rel_notes/release_20_11.rst | 9 +
1 file changed, 9 insertions(+)
diff --git
This patch adds Forward error correction(FEC) support for ethdev.
Introduce APIs which support query and config FEC information in
hardware.
Signed-off-by: Min Hu (Connor)
Reviewed-by: Wei Hu (Xavier)
Reviewed-by: Chengwen Feng
Reviewed-by: Chengchang Tang
Reviewed-by: Ajit Khaparde
Acked-by:
This commit adds testpmd capability to query and config FEC
function of device. This includes:
- show FEC capabilities, example:
testpmd> show port 0 fec capabilities
- show FEC mode, example:
testpmd> show port 0 fec_mode
- config FEC mode, example:
testpmd> set port 0
This series add FEC support for ethdev.
Min Hu (Connor) (4):
ethdev: introduce FEC API
net/hns3: support FEC
app/testpmd: add FEC command
doc: add FEC API and PMD information
app/test-pmd/cmdline.c | 221 +++
app/test-pmd/config.c| 9
Hi, Andrew,
I have fixed it about FEC in V11 according to your suggestion.
could your please check it out.
thanks.
在 2020/9/22 20:18, Andrew Rybchenko 写道:
On 9/22/20 2:06 PM, Min Hu (Connor) wrote:
在 2020/9/22 16:02, Andrew Rybchenko 写道:
On 9/22/20 7:58 AM, Min Hu (C
> -Original Message-
> From: Honnappa Nagarahalli
> Sent: Thursday, September 24, 2020 6:19 AM
> To: Juraj Linkeš ; bruce.richard...@intel.com;
> Ruifeng Wang ; Phil Yang ;
> vcchu...@amazon.com; Dharmik Thakkar ;
> jerinjac...@gmail.com; hemant.agra...@nxp.com
> Cc: dev@dpdk.org; nd ; H
The Windows EAL build now pulls in the pthreads4w project as an external
subproject. The pthreads4w subproject does not currently provide a meson build
so the project has been patched with one.
Removed the placeholder librte_eal\windows\include\pthread.h and sched.h header
files as these are s
When testing high performance numbers, it is often that CPU performance
limits the max values device can reach (both in pps and in gbps)
Here instead of recreating each packet separately, we use clones counter
to resend the same mbuf to the line multiple times.
PMDs handle that transparently due
On 8/26/2020 6:52 AM, rohit@nxp.com wrote:
From: Rohit Raj
As per the current code we have API for bus probe, but the
bus close API is missing. This breaks the multi process
scenarios as objects are not cleaned while terminating the
secondary processes.
This patch adds a new API rte_bus_cl
The Windows EAL build now pulls in the pthreads4w project as an external
subproject. The pthreads4w subproject does not currently provide a
meson build so the project has been patched with one.
Removed the placeholder librte_eal\windows\include\pthread.h and sched.h
header files as these are supe
From: Yuval Avnery
Currently job data is being copied to pre-registered buffer.
To avoid memcpy on the datapath, use dynamic memory registration.
This change will reduce latency when sending regex jobs. The first few
jobs may have high latency due to registration, but assuming all
following mbuf
From: Yuval Avnery
Currently job data is being copied to pre-registered buffer.
To avoid memcpy on the datapath, use dynamic memory registration.
This change will reduce latency when sending regex jobs. The first few
jobs may have high latency due to registration, but assuming all
following mbuf
On 9/23/2020 9:44 PM, Thomas Monjalon wrote:
23/09/2020 18:44, Ferruh Yigit:
On 9/13/2020 11:07 PM, Thomas Monjalon wrote:
The flag RTE_ETH_DEV_CLOSE_REMOVE is set so all port resources
can be freed by rte_eth_dev_close().
Freeing of private port resources is moved
from the ".remove(device)" t
On 9/23/2020 9:41 PM, Thomas Monjalon wrote:
23/09/2020 18:44, Ferruh Yigit:
On 9/13/2020 11:07 PM, Thomas Monjalon wrote:
* Note 3:
The port is supposed to be in a stopped state when it is closed.
If it is not the case, it is free to the PMD implementation
how to react when trying to close a n
On 9/23/2020 9:32 PM, Thomas Monjalon wrote:
23/09/2020 18:45, Ferruh Yigit:
On 9/13/2020 11:07 PM, Thomas Monjalon wrote:
Since rte_eth_dev_release_port() is called on all port close operations,
the event RTE_ETH_EVENT_DESTROY can be reliably used for resetting
the port status on the applicati
On 9/24/2020 11:07 AM, Thomas Monjalon wrote:
24/09/2020 11:12, Bruce Richardson:
On Thu, Sep 24, 2020 at 12:35:58AM +0200, Thomas Monjalon wrote:
24/09/2020 00:02, Stephen Hemminger:
On Wed, 23 Sep 2020 23:52:07 +0200
Thomas Monjalon wrote:
Yes it is a step in the right direction.
Changing
On 9/23/20 8:20 PM, Ferruh Yigit wrote:
> On 9/22/2020 10:33 AM, Andrew Rybchenko wrote:
>> Signed-off-by: Andrew Rybchenko
>
> <...>
>
>> +
>> +/***/
>> +/* MC_CMD_VNIC_ENCAP_RULE_ADD
>> + * Add a rule for detecting encapsulations in the VNIC stage.
>> Currently
Riverhead is the first NIC family of the EF100 architecture.
Signed-off-by: Andrew Rybchenko
Reviewed-by: Andy Moreton
Reviewed-by: Vijay Kumar Srivastava
---
drivers/common/sfc_efx/base/efx.h | 7 +++
drivers/common/sfc_efx/base/efx_impl.h | 3 +++
drivers/common/sfc_efx/base/efx_n
Signed-off-by: Andrew Rybchenko
---
drivers/common/sfc_efx/base/efx_impl.h | 1 +
drivers/common/sfc_efx/base/efx_regs_ef100.h | 934 +++
2 files changed, 935 insertions(+)
create mode 100644 drivers/common/sfc_efx/base/efx_regs_ef100.h
diff --git a/drivers/common/sfc_ef
Riverhead family got letter 'G' for registers definition.
Registers used for Riverhead should have the letter in the
specification range.
Signed-off-by: Andrew Rybchenko
Reviewed-by: Andy Moreton
Reviewed-by: Vijay Kumar Srivastava
---
drivers/common/sfc_efx/base/efx_impl.h | 4
1 file ch
There is no point to duplicate it NIC family specific probe handlers.
Signed-off-by: Andrew Rybchenko
Reviewed-by: Andy Moreton
---
drivers/common/sfc_efx/base/ef10_nic.c | 2 --
drivers/common/sfc_efx/base/efx_nic.c | 3 +++
drivers/common/sfc_efx/base/siena_nic.c | 3 ---
3 files changed,
There is no difference yet in PHY support on EF10 and Riverhead.
So, it is better to reuse existing methods.
Signed-off-by: Andrew Rybchenko
Reviewed-by: Andy Moreton
Reviewed-by: Vijay Kumar Srivastava
---
drivers/common/sfc_efx/base/ef10_phy.c | 4 ++--
drivers/common/sfc_efx/base/efx_phy.c
Riverhead is a new NIC family, the first one with EF100 architecture.
Control interface is an MCDI similar to EF10. Datapath interface is
completely new.
The patch series is build tested with and without EFSYS_OPT_RIVERHEAD
enabled.
EF10-based NICs are tested with the patch series applied with an
Event queue host interface differ on Riverhead and implementation
will be different.
Signed-off-by: Andrew Rybchenko
Reviewed-by: Andy Moreton
---
drivers/common/sfc_efx/base/efx_ev.c | 325 ++---
drivers/common/sfc_efx/base/efx_impl.h | 2 +
2 files changed, 182 inserti
Signed-off-by: Andrew Rybchenko
Reviewed-by: Andy Moreton
Reviewed-by: Vijay Kumar Srivastava
---
drivers/common/sfc_efx/base/efx_check.h | 44 -
drivers/common/sfc_efx/efsys.h | 3 ++
2 files changed, 25 insertions(+), 22 deletions(-)
diff --git a/drivers/com
MCDI on Riverhead is very close to the EF10 and there is no
point to duplicate the code.
Signed-off-by: Andrew Rybchenko
Reviewed-by: Andy Moreton
---
drivers/common/sfc_efx/base/ef10_mcdi.c | 46 -
drivers/common/sfc_efx/base/efx.h | 8 ++---
drivers/common/sfc_e
Riverhead supports interrupt aggregation rings. Right now there
are no plans to support it in libefx, but it is better to have
own set of callbacks to easier handle EF10 and Riverhead
differences in the future.
Signed-off-by: Andrew Rybchenko
Reviewed-by: Andy Moreton
---
drivers/common/sfc_efx
There is no difference yet in MAC support on EF10 and Riverhead.
So, it is better to reuse existing methods.
Signed-off-by: Andrew Rybchenko
Reviewed-by: Andy Moreton
Reviewed-by: Vijay Kumar Srivastava
---
drivers/common/sfc_efx/base/ef10_mac.c | 6 ++---
drivers/common/sfc_efx/base/efx_impl
The function which gets capabilities from MC should simply fill in
NIC configuration. Caller should decide if the configuration is
supported or not.
The change is required to prepare the function to be reused on
Riverhead.
Signed-off-by: Andrew Rybchenko
Reviewed-by: Andy Moreton
---
drivers/c
The helper will be used on Riverhead.
Signed-off-by: Andrew Rybchenko
Reviewed-by: Andy Moreton
---
drivers/common/sfc_efx/base/ef10_nic.c | 213 ++---
1 file changed, 117 insertions(+), 96 deletions(-)
diff --git a/drivers/common/sfc_efx/base/ef10_nic.c
b/drivers/common/s
ef10_get_datapath_caps() should simply fill in NIC configuration
based MC_CMD_GET_CAPABILITIES output.
Number of PFs is a part of board configuration should be obtained
in corresponding function.
Signed-off-by: Andrew Rybchenko
Reviewed-by: Andy Moreton
---
drivers/common/sfc_efx/base/ef10_nic
The helper will be reused on Riverhead.
Signed-off-by: Andrew Rybchenko
Reviewed-by: Andy Moreton
---
drivers/common/sfc_efx/base/ef10_nic.c | 51 +-
1 file changed, 34 insertions(+), 17 deletions(-)
diff --git a/drivers/common/sfc_efx/base/ef10_nic.c
b/drivers/common/
Filtering MCDI on Riverhead are the same as on EF10.
Signed-off-by: Andrew Rybchenko
Reviewed-by: Andy Moreton
Reviewed-by: Vijay Kumar Srivastava
---
drivers/common/sfc_efx/base/ef10_filter.c | 14 +++---
drivers/common/sfc_efx/base/efx_filter.c | 18 ++
drivers/commo
TxQ init/fini MCDI is similar on Riverhead and these
functions should be reused to implement TxQ creation and
destruction on Riverhead.
Signed-off-by: Andrew Rybchenko
Reviewed-by: Andy Moreton
Reviewed-by: Vijay Kumar Srivastava
---
drivers/common/sfc_efx/base/ef10_tx.c | 133 ---
Define basic NIC features and limitations.
Signed-off-by: Andrew Rybchenko
Reviewed-by: Andy Moreton
Reviewed-by: Vijay Kumar Srivastava
---
drivers/common/sfc_efx/base/ef10_impl.h | 25 ++
drivers/common/sfc_efx/base/ef10_nic.c | 52 ++-
drivers/common/sfc_efx/base/efx_impl.h | 8 +-
Riverhead does not support tunnels yet.
Signed-off-by: Andrew Rybchenko
Reviewed-by: Andy Moreton
---
drivers/common/sfc_efx/base/efx_tunnel.c | 10 --
1 file changed, 8 insertions(+), 2 deletions(-)
diff --git a/drivers/common/sfc_efx/base/efx_tunnel.c
b/drivers/common/sfc_efx/base/e
From: Ivan Malov
Client drivers relying on interrupts will fail to complete event
queue creation on Riverhead boards as the latter have no support
for INIT_DONE events which means that it's useless to wait until
initialisation callback is triggered by interrupt-driven polling.
Client drivers whi
Events are significantly reworked on Riverhead, so it is better
to implement own set of callbacks to simplify future development
and avoid inheritance of legacy code.
Signed-off-by: Andrew Rybchenko
Reviewed-by: Andy Moreton
---
drivers/common/sfc_efx/base/efx_ev.c | 22 ++
drivers/common/
RxQ init/fini MCDI is similar on Riverhead and these
functions should be reused to implement RxQ creation and
destruction on Riverhead.
Signed-off-by: Andrew Rybchenko
Reviewed-by: Andy Moreton
---
drivers/common/sfc_efx/base/ef10_rx.c | 184
drivers/common/sfc_efx/bas
v1 and v2 defines are the same except output length.
Signed-off-by: Andrew Rybchenko
Reviewed-by: Andy Moreton
---
drivers/common/sfc_efx/base/efx_mcdi.c | 52 +-
1 file changed, 26 insertions(+), 26 deletions(-)
diff --git a/drivers/common/sfc_efx/base/efx_mcdi.c
b/dr
The decision on which version of the INIT_EVQ command to use may
be done inside the function itself. Caller should just provide
enough information sufficient in both cases. It avoids code
duplication and simplifies maintenance.
If v2 is not supported, keep decision about low-latency hint outside
t
EF100 MCDI event layout is same as on EF10 except added QDMA phase
bit which is unused on EF10.
Signed-off-by: Andrew Rybchenko
Reviewed-by: Andy Moreton
---
drivers/common/sfc_efx/base/ef10_ev.c | 17 +++--
drivers/common/sfc_efx/base/ef10_impl.h | 8 ++
drivers/common/sfc_efx/b
Introduce a new event callback which has the same prototype, but
provides number of completed descriptors instead of the last
completed descriptor index.
When all libefx-based drivers implement the new callback, libefx
may be updated to use it for Siena and EF10 family NICs and
the old one may be
There is no point to duplicate these generic checks in NIC family
specific handlers.
As the side effect it fixes bug with incorrect interrupt moderation
settings silently ignored on event queue create on Siena.
Signed-off-by: Andrew Rybchenko
Reviewed-by: Andy Moreton
Reviewed-by: Vijay Kumar S
Rx event on Riverhead provides a number of received packets and
no classification/offloads information is available Rx event.
Introduce a new event callback to be implemented by drivers.
The callback provides information about the number of completed
packets. libefx-based drivers should implement
Tx control path on Riverhead is very similar to EF10, but datapath
differs a lot since Tx descriptor size is 16 bytes (vs 8 bytes on EF10).
Signed-off-by: Andrew Rybchenko
Reviewed-by: Andy Moreton
---
drivers/common/sfc_efx/base/efx_impl.h | 6 +-
drivers/common/sfc_efx/base/efx_mcdi.c |
Rx/Tx queue DMA sync should not assume descriptor size to be the same
for all NIC familties since it Tx descritor size is 16 on Riverhead.
Signed-off-by: Andrew Rybchenko
Reviewed-by: Andy Moreton
---
drivers/common/sfc_efx/base/ef10_rx.c | 2 +-
drivers/common/sfc_efx/base/ef10_tx.c | 4 ++--
From: Igor Romanov
Function control window can be located at a different offset than
other windows on Riverhead. Meaning that the drivers must handle
accesses to the function control window differently in case of EF100.
Add accessor macros for function control window and change
EFX NIC create AP
EvQ init/fini MCDI is similar on Riverhead and these
functions should be reused to implement EvQ creation and
destruction on Riverhead.
Signed-off-by: Andrew Rybchenko
Reviewed-by: Andy Moreton
Reviewed-by: Vijay Kumar Srivastava
---
drivers/common/sfc_efx/base/ef10_ev.c | 304 ---
Reuse EF10 RSS-related functions since current version of the RSS
interface is compatible with EF10.
Implement own functions to create and destroy Rx queues which reuse
MCDI wrappers which are shared with EF10.
Signed-off-by: Andrew Rybchenko
Reviewed-by: Andy Moreton
---
drivers/common/sfc_ef
Make NIC family specific functions a bit shorter and reduce
code duplication.
Signed-off-by: Andrew Rybchenko
Reviewed-by: Andy Moreton
---
drivers/common/sfc_efx/base/ef10_rx.c | 45 +++
drivers/common/sfc_efx/base/efx_rx.c | 31 +-
2 files changed, 35
From: Ivan Malov
Riverhead boards support TSO version 3.
Signed-off-by: Ivan Malov
Signed-off-by: Andrew Rybchenko
Reviewed-by: Andrew Lee
Reviewed-by: Andy Moreton
---
drivers/common/sfc_efx/base/ef10_nic.c | 6 ++
drivers/common/sfc_efx/base/efx.h | 1 +
drivers/common/sfc_efx/
Riverhead supports many Rx prefixes. The Rx prefix may be chosen
based on which information is required.
To have better performance choose the smallest Rx prefix which
meets our requirements.
Right now there is no way to specify requirements on Rx queue
creation, but it could be added in the futu
From: Ivan Malov
Riverhead puts a number of restrictions on TSO transactions.
Reflect some of them in the NIC configuration structure.
Signed-off-by: Ivan Malov
Signed-off-by: Andrew Rybchenko
Reviewed-by: Andrew Lee
Reviewed-by: Andy Moreton
---
drivers/common/sfc_efx/base/ef10_nic.c | 21
Define default Siena, EF10 default, packed stream, equal-stride
superbuffer and Riverhead default prefixes in order to make an API
to get Rx prefix layout information generic and usable on all NICs.
Riverhead supports many Rx prefixes. Riverhead FW supports MCDI to
choose Rx prefix based on requir
Make number of efx_mcdi_init_rxq() arguments reasonable before
addition of one more argument.
Non essential parameters not supported in some cases are moved
into helper structure.
Signed-off-by: Andrew Rybchenko
Reviewed-by: Andy Moreton
---
drivers/common/sfc_efx/base/ef10_rx.c | 57 +
Extended version of MCDI allows up to 64 DMA addresses which are
required for Riverhead.
Signed-off-by: Andrew Rybchenko
Reviewed-by: Andy Moreton
---
drivers/common/sfc_efx/base/efx_mcdi.c | 5 ++---
1 file changed, 2 insertions(+), 3 deletions(-)
diff --git a/drivers/common/sfc_efx/base/efx_
Riverhead has EVB support similar to EF10 and NIC must allocate
its vAdaptor on init.
Signed-off-by: Andrew Rybchenko
Reviewed-by: Andy Moreton
---
drivers/common/sfc_efx/base/ef10_impl.h | 5 +++
drivers/common/sfc_efx/base/ef10_nic.c | 10 +-
drivers/common/sfc_efx/base/rhead_nic.c | 43
From: Igor Romanov
APIs for searching a capability in a Xilinx capabilities table and
reading table entries are needed for function control window lookup
to get the bar index and offset of the window.
Signed-off-by: Igor Romanov
Signed-off-by: Andrew Rybchenko
Reviewed-by: Andy Moreton
---
d
From: Igor Romanov
The procedures for destroying UDP tunnels are NIC family specific,
so they should be implemented separately for each of them.
Check for supported UDP encapsulation is removed from generic
operations since it is no longer used by the generic libefx API.
Signed-off-by: Igor Rom
From: Igor Romanov
Check that BAR lookup was successful by looking at the content
of signature register.
Signed-off-by: Igor Romanov
Signed-off-by: Andrew Rybchenko
Reviewed-by: Andy Moreton
---
drivers/common/sfc_efx/base/rhead_pci.c | 20
1 file changed, 20 insertions(
From: Igor Romanov
EF100 uses VNIC encapsulation rule MCDI for configuring UDP
tunnels in HW individually. Use busy added and removed states
of UDP tunnel table entries for the implementation.
Signed-off-by: Igor Romanov
Signed-off-by: Andrew Rybchenko
Reviewed-by: Andy Moreton
---
drivers/c
1 - 100 of 200 matches
Mail list logo
