From: Stephen Hemminger
The secondary mapping function was duplicating the code
used to search the uio_resource list.
Skip the unwinding since map failure already makes device
unusable.
Signed-off-by: Stephen Hemminger
---
drivers/bus/vmbus/vmbus_common_uio.c | 132 ---
From: Stephen Hemminger
The ethernet address was being converted to a string but
the code using that is no longer present.
Signed-off-by: Stephen Hemminger
---
drivers/net/netvsc/hn_vf.c | 3 ---
1 file changed, 3 deletions(-)
diff --git a/drivers/net/netvsc/hn_vf.c b/drivers/net/netvsc/hn_vf
From: Stephen Hemminger
Need to remember primary channel in secondary process.
Then use it to iterate over subchannels in secondary
process mapping setup.
Fixes: 831dba47bd36 ("bus/vmbus: add Hyper-V virtual bus support")
Signed-off-by: Stephen Hemminger
---
drivers/bus/vmbus/linux/vmbus_uio.c
From: Stephen Hemminger
The secondary process doesn't correctly map the second
and later resources because it doesn't change the offset.
Fixes: 831dba47bd36 ("bus/vmbus: add Hyper-V virtual bus support")
Signed-off-by: Stephen Hemminger
---
drivers/bus/vmbus/vmbus_common_uio.c | 3 ++-
1 file
From: Stephen Hemminger
If vmbus is run on older kernel (without all the uio mappings),
then the bus driver should stop when it hits the missing mappings
rather than recording the empty values.
Fixes: 831dba47bd36 ("bus/vmbus: add Hyper-V virtual bus support")
Signed-off-by: Stephen Hemminger
-
From: Stephen Hemminger
The VF device management in netvsc was using a pointer to the
rte_eth_devices. But the actual rte_eth_devices array is likely to
be place in the secondary process; which causes a crash.
The solution is to record the port of the VF (instead of a pointer)
and find the devic
From: Stephen Hemminger
The code was testing the result of mmap incorrectly.
I.e the test that a local pointer is not MAP_FAILED would
always succeed and therefore hid any potential problems.
Fixes: 831dba47bd36 ("bus/vmbus: add Hyper-V virtual bus support")
Signed-off-by: Stephen Hemminger
---
From: Stephen Hemminger
These fix the primary/secondary process model support in the
vmbus and netvsc PMD. They do NOT fix the failsafe PMD.
The last two are not bug fixes but address unnecessary
code found while debugging the mp support.
Stephen Hemminger (7):
bus/vmbus: fix secondary proce
Hi Vladimir,
Thanks for stepping up for the maintaining job.
I agree with you that they are two parts and we mixed hash table and hashing
function from beginning. They are actually should be two libraries, but at this
Stage it is not very necessary to change the situation yet I think.
If you tr
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 is a simple initial implementa
This series introduces the ability for any github mirrors of the DPDK
project, including developer mirrors, to kick off builds under the
travis CI infrastructure. For now, this just means compilation - no
other kinds of automated run exists yet. In the future, this can be
expanded to execute and
From: Aaron Conole
The vhost_scsi example code is set to build, even if the requisite header
file virtio_scsi.h isn't available. This happens on some Ubuntu systems
when some versions of the libc-dev package aren't available.
Check whether the virtio_scsi.h file exists, and if not, set the buil
I agree with Thomas. It makes sense to separate out hash function from hash
table implementation.
Sameh
-Original Message-
From: Thomas Monjalon [mailto:tho...@monjalon.net]
Sent: Thursday, February 7, 2019 1:25 PM
To: Medvedkin, Vladimir
Cc: dev@dpdk.org; Wang, Yipeng1 ; Gobriel, Sam
07/02/2019 20:28, Medvedkin, Vladimir:
> On 06/02/2019 10:38, Thomas Monjalon wrote:
> > 05/02/2019 14:57, Vladimir Medvedkin:
> >> --- a/MAINTAINERS
> >> +++ b/MAINTAINERS
> >> +M: Vladimir Medvedkin
> >> +F: lib/librte_hash/rte_thash.h
> > I'm not sure about adding maintainership for one file.
>
Below are the features that we are planning for 19.05 release:
* New steering flow engine in mlx5 PMD to reach insertion rate of millions
of rules per sec
* FailSafe secondary process support
* Introduce DMA memory mapping APIs for external memory
* rte_flow API with mlx5 PMD imp
On 06/02/2019 10:38, Thomas Monjalon wrote:
05/02/2019 14:57, Vladimir Medvedkin:
--- a/MAINTAINERS
+++ b/MAINTAINERS
+M: Vladimir Medvedkin
+F: lib/librte_hash/rte_thash.h
I'm not sure about adding maintainership for one file.
You are the author of this file, so you should be consulted
during
Added missing line informing which kernel driver can
be used for device DH895xcc for compression service.
Moved service columns to start of table for better visibility
and to prepare for future asymmetric crypto service.
Fixes: e2e35849ea78 ("compress/qat: add compression on DH895x")
Cc: sta...@dp
> On Feb 7, 2019, at 10:40 AM, Ferruh Yigit wrote:
>
> On 2/4/2019 7:02 AM, Pallantla Poornima wrote:
>> sprintf function is not secure as it doesn't check the length of string.
>> More secure function snprintf is used.
>>
>> Fixes: 3fc5ca2f63 ("kni: initial import")
>> Fixes: b9ee370557 ("kn
Loopback mode is also supported on X540 and X550 NICs, according to
their datasheet (section 15.2). The way to set it up is a little
different of the 82599.
Signed-off-by: Julien Meunier
---
v2:
- disable / enable autoneg when loopback is requested for X540 / X550
---
drivers/net/ixgbe/base/ixgb
Only TX->RX loopback is supported currently on 82599EB. If a user wants
to apply an another loopback configuration (!= IXGBE_LPBK_82599_TX_RX),
ixgbe PMD ignores it and continues the configuration without raising any
error.
Let's robustify this part by checking if the requested loopback mode is
co
> diff --git a/.ci/linux-build.sh b/.ci/linux-build.sh new file mode 100755
> index
> 0..9c6af2ead
> --- /dev/null
> +++ b/.ci/linux-build.sh
> @@ -0,0 +1,88 @@
> +#!/bin/bash
> +
> +# check for whether we're clang or gcc
> +# setup the right options depending on the environment variable
On 2/4/2019 7:02 AM, Pallantla Poornima wrote:
> sprintf function is not secure as it doesn't check the length of string.
> More secure function snprintf is used.
>
> Fixes: 3fc5ca2f63 ("kni: initial import")
> Fixes: b9ee370557 ("kni: update kernel driver ethtool baseline")
> Cc: sta...@dpdk.org
On Thu, Feb 07, 2019 at 10:53:18AM -0500, Chas Williams wrote:
> Sort the options alphabetically and make a note of the preferred
> order at the top of the file.
>
> Signed-off-by: Chas Williams <3ch...@gmail.com>
> ---
Acked-by: Bruce Richardson
Signed-off-by: Andrew Rybchenko
---
drivers/net/sfc/base/ef10_tlv_layout.h | 17 +
drivers/net/sfc/base/efx_regs_mcdi.h | 1262 +++---
drivers/net/sfc/base/efx_regs_mcdi_aoe.h | 54 +-
3 files changed, 1189 insertions(+), 144 deletions(-)
diff --git a/drivers/net/sfc/ba
Rx buffer size must be specified on Rx queue creation on
Riverhead.
Signed-off-by: Andrew Rybchenko
---
drivers/net/sfc/base/ef10_rx.c | 46 +++--
drivers/net/sfc/base/efx.h | 1 +
drivers/net/sfc/base/efx_impl.h | 6 +++--
drivers/net/sfc/base/efx_rx.c | 12
Move duplicate macro to increment per-event type stats to
internal header. These stats are NIC family independent and
stored in generic event queue structure.
Signed-off-by: Andrew Rybchenko
---
drivers/net/sfc/base/ef10_ev.c | 10 --
drivers/net/sfc/base/efx_ev.c | 10 --
dri
From: Andrew Lee
Signed-off-by: Andrew Lee
Signed-off-by: Andrew Rybchenko
---
drivers/net/sfc/base/ef10_ev.c | 3 ++-
drivers/net/sfc/base/efx.h | 3 ++-
drivers/net/sfc/base/efx_ev.c | 3 ++-
3 files changed, 6 insertions(+), 3 deletions(-)
diff --git a/drivers/net/sfc/base/ef10_ev.c b
If event queue timers are not supported, enc_evq_timer_quantum_ns and
enc_evq_timer_max_us should be set to 0. Make sure that division by 0
does not happen in libefx, if public function efx_ev_usecs_to_ticks()
is used in this case.
Signed-off-by: Andrew Rybchenko
---
drivers/net/sfc/base/efx_ev.
Add EFX_OPTS_EF10() which may be used as synonym of any EF10-based
NIC (i.e. Huntigton, Medford or Medford2 at the time of addition).
Suggested-by: Andy Moreton
Signed-off-by: Andrew Rybchenko
---
drivers/net/sfc/base/ef10_ev.c | 4 +-
drivers/net/sfc/base/ef10_filter.c | 4 +-
drivers/ne
Riverhead requires Rx buffer size to be specified in INIT_RXQ.
If the parameter is not supported (e.g. on EF10 family adapters),
zero must be used on INIT_RXQ.
Signed-off-by: Andrew Rybchenko
---
drivers/net/sfc/base/ef10_nic.c | 10 ++
drivers/net/sfc/base/ef10_rx.c | 15 ++
Add EFX_FAMILY_IS_EF10() which may be used as synonym of any EF10-based
NIC family (i.e. Huntigton, Medford or Medford2 at the time of addition).
Suggested-by: Andy Moreton
Signed-off-by: Andrew Rybchenko
---
drivers/net/sfc/base/ef10_ev.c | 4 +--
drivers/net/sfc/base/ef10_filter.c | 20 +
From: Richard Houldsworth
Supports the firmware update mechanism described in SF-121352-AN.
Signed-off-by: Richard Houldsworth
Signed-off-by: Andrew Rybchenko
---
drivers/net/sfc/base/ef10_nvram.c | 1 +
drivers/net/sfc/base/efx.h| 1 +
2 files changed, 2 insertions(+)
diff --git a/d
Include efx_mcdi.h from main internal header efx_impl.h directly
instead of indirect inclusion via family-specific header.
It avoids duplication and fixes Medford and Medford2 cases where
the header inclusion is lost.
Correctness is still guaranteed by checks in efx_check.h which
require EFSYS_OPT_
From: Igor Romanov
For consistency with the size of Tx descriptors, the size of event
descriptors should be a part of NIC config, not a macro that is
common for all NIC families. Also, add a max number of EvQ buffers
define which is needed to initialize an MCDI buffer at compile time.
Signed-off
From: Igor Romanov
The macros are depricated and are not used anymore, so they can
be deleted.
Signed-off-by: Igor Romanov
Signed-off-by: Andrew Rybchenko
---
drivers/net/sfc/base/efx.h | 36
1 file changed, 36 deletions(-)
diff --git a/drivers/net/sfc/ba
From: Mark Spender
The recently added NO_CONT_EV mode is recommended for when looking for
maximum throughput on 100G links as it allows the firmware to operate
more efficiently. The biggest benefit is when using scatter and jumbo
frames, but it is also necessary to achieve line rate in other case
From: Igor Romanov
Symbols for maximum and minimum number of Tx, Rx and event descriptors
are deprecated. They are not used anymore, so they can be deleted.
Signed-off-by: Igor Romanov
Signed-off-by: Andrew Rybchenko
---
drivers/net/sfc/base/efx.h | 20
1 file changed, 20
From: Igor Romanov
Use of the macro for calculating a Rx queue size is deprecated. Replace
it with a call to a function that uses descriptor size specified for
every NIC.
Signed-off-by: Igor Romanov
Signed-off-by: Andrew Rybchenko
---
drivers/net/sfc/sfc_ev.c | 6 --
1 file changed, 4 ins
From: Igor Romanov
Use of the macro for calculating a Rx queue size is deprecated. Replace
it with a call to a function that uses descriptor size specified for
every NIC.
Signed-off-by: Igor Romanov
Signed-off-by: Andrew Rybchenko
---
drivers/net/sfc/sfc_rx.c | 3 ++-
1 file changed, 2 insert
From: Igor Romanov
Use of the macro for calculating a Tx queue size is deprecated. Replace
it with a call to a function that uses descriptor size specified for
every NIC.
Signed-off-by: Igor Romanov
Signed-off-by: Andrew Rybchenko
---
drivers/net/sfc/sfc_tx.c | 3 ++-
1 file changed, 2 insert
The header was incorrectly named on addition since it did not
match naming conventions.
Signed-off-by: Andrew Rybchenko
---
drivers/net/sfc/base/efx_mcdi.h | 2 +-
.../sfc/base/{mc_driver_pcol_strs.h => efx_regs_mcdi_strs.h}| 0
2 files changed, 1 insertion(+)
From: Igor Romanov
For consistency with the size of Tx descriptors, the size of Rx
descriptors should be a part of NIC config, not a macro that is
common for all NIC families.
Signed-off-by: Igor Romanov
Signed-off-by: Andrew Rybchenko
---
drivers/net/sfc/base/ef10_impl.h| 1 +
drivers/n
From: Igor Romanov
Size of Tx descriptor is different on Riverhead. So, the size
should be a part of NIC config, not a macro that is common for
all NIC families.
Signed-off-by: Igor Romanov
Signed-off-by: Andrew Rybchenko
---
drivers/net/sfc/base/ef10_impl.h| 2 ++
drivers/net/sfc/base/e
From: Igor Romanov
Now we have min/max limits in NIC config, so we can do check against
min/max in a generic place instead of NIC family specific functions.
Check that the descriptors number is a power of 2 is also can be made
common. It removes code duplication and makes NIC family
specific func
From: Igor Romanov
The macro EFX_RXQ_DC_NDESCS() is used only by Siena implementation.
Since the macro is not used by any drivers, it does not require
exposed libefx interface.
Make the macro Siena-specific.
Signed-off-by: Igor Romanov
Signed-off-by: Andrew Rybchenko
---
drivers/net/sfc/base/
From: Igor Romanov
Functions efx_*q_nbufs return the number of a queue buffers by dividing
the queue size by page size. If minimum size of a queue is smaller than
one page, we still need the page and number of buffers should not be 0.
Signed-off-by: Igor Romanov
Signed-off-by: Andrew Rybchenko
From: Igor Romanov
Now we have min/max limits in NIC config, so we can do check against
min/max in a generic place instead of NIC family specific functions.
Check that the descriptors number is a power of 2 is also can be
made common. It removes code duplication and makes NIC family
specific func
From: Igor Romanov
The change is needed for the functions that accept const efx_nic_t
pointer and have to get efx_nic_cfg_t.
Signed-off-by: Igor Romanov
Signed-off-by: Andrew Rybchenko
---
drivers/net/sfc/base/efx.h | 2 +-
drivers/net/sfc/base/efx_nic.c | 2 +-
2 files changed, 2 inserti
From: Igor Romanov
The define EFX_TXQ_MAX_BUFS is used only by EF10 family implementation.
Since the macro is not used by any drivers, it does not require
exposed libefx interface.
Make the define EF10-specific.
Signed-off-by: Igor Romanov
Signed-off-by: Andrew Rybchenko
---
drivers/net/sfc/b
From: Igor Romanov
Now we have min/max limits in NIC config, so we can do check against
min/max in a generic place instead of NIC family specific functions.
Check that the descriptors number is a power of 2 is also can be
made common. It removes code duplication and makes NIC family
specific func
From: Igor Romanov
Min limit is not common for all NIC families. Use the variable from
NIC configuration instead of deprecated define.
Signed-off-by: Igor Romanov
Signed-off-by: Andrew Rybchenko
---
drivers/net/sfc/sfc.c | 3 +++
drivers/net/sfc/sfc.h | 1 +
drivers/net/sfc/
From: Igor Romanov
For consistency with defines of min descriptor number, define max
descriptor number for Huntington, Medford and Medford2.
Signed-off-by: Igor Romanov
Signed-off-by: Andrew Rybchenko
---
drivers/net/sfc/base/hunt_impl.h | 3 +++
drivers/net/sfc/base/hunt_nic.c | 4 +
From: Igor Romanov
Descriptor limits are not common for all NIC families. Use the variables
from NIC configuration instead of deprecated defines.
Signed-off-by: Igor Romanov
Signed-off-by: Andrew Rybchenko
---
drivers/net/sfc/sfc.c | 6 ++
drivers/net/sfc/sfc.h
From: Igor Romanov
EF100/Riverhead has different min/max limits. So, these limits should
be a part of NIC config, not defines common for all NIC families.
Signed-off-by: Igor Romanov
Signed-off-by: Andrew Rybchenko
---
drivers/net/sfc/base/ef10_ev.c | 15 ---
drivers/net/sfc/
From: Igor Romanov
Descriptor limits are not common for all NIC families. Use the variables
from NIC configuration instead of deprecated defines.
Signed-off-by: Igor Romanov
Signed-off-by: Andrew Rybchenko
---
drivers/net/sfc/sfc.c | 6 ++
drivers/net/sfc/sfc.h |
From: Richard Houldsworth
Correct annotations where NULL input can be permitted
Signed-off-by: Richard Houldsworth
Signed-off-by: Andrew Rybchenko
---
drivers/net/sfc/base/ef10_impl.h | 2 +-
drivers/net/sfc/base/ef10_rx.c | 42 +---
drivers/net/sfc/base/efx.h
From: Mark Spender
If an event handler requested an abort, only the inner loop was
guarenteed to be broken out of - the outer loop could continue
if total == batch.
Fix this by poisoning batch to ensure it is different to total.
Signed-off-by: Mark Spender
Signed-off-by: Andrew Rybchenko
---
From: Richard Houldsworth
Revise the external port calculation to support all
X2 port modes. The previous algorithm could not
handle different port numbering schemes on each cage.
Signed-off-by: Richard Houldsworth
Signed-off-by: Andrew Rybchenko
---
drivers/net/sfc/base/ef10_nic.c | 126
From: Igor Romanov
EF100/Riverhead has different min limit. So, this limit should
be a part of NIC config, not define common for all NIC families.
Define maximum Tx descriptor number for Siena in the same way as
minimum for consistency.
Signed-off-by: Igor Romanov
Signed-off-by: Andrew Rybchenk
Update Solarflare libefx and make related changes in the PMD itself.
Andrew Lee (1):
net/sfc/base: add Rx parse incomplete event queue statistic
Andrew Rybchenko (9):
net/sfc/base: update auto-generated MCDI definition headers
net/sfc/base: rename header with MCDI strings
net/sfc/base: al
From: Ivan Malov
FreeBSD driver needs a patch to provide a means for packets
which do not need checksum offload but have flow ID set
to avoid hitting only the first Tx queue (which has been used
for packets not needing checksum offload).
This should be possible on Huntington, Medford or Medford2
From: Igor Romanov
EF100/Riverhead has different min/max limits. So, these limits should
be a part of NIC config, not defines common for all NIC families.
Signed-off-by: Igor Romanov
Signed-off-by: Andrew Rybchenko
---
drivers/net/sfc/base/ef10_impl.h| 3 +++
drivers/net/sfc/base/ef10_rx
Sort the options alphabetically and make a note of the preferred
order at the top of the file.
Signed-off-by: Chas Williams <3ch...@gmail.com>
---
meson_options.txt | 14 --
1 file changed, 8 insertions(+), 6 deletions(-)
diff --git a/meson_options.txt b/meson_options.txt
index 5bae0
Allow users and packagers to override the default RTE_MAX_ETHPORTS.
This adds a new meson option, max_ethports which defaults to the
current value.
Signed-off-by: Chas Williams <3ch...@gmail.com>
Acked-by: Bruce Richardson
---
config/meson.build | 1 +
config/rte_config.h | 1 -
meson_options.t
On 02/07/2019 03:22 PM, Aaron Conole wrote:
> Kevin Traynor writes:
>
>> Update the LTS section to mention the branch, how LTS support ends
>> and update the currently maintained LTS branches.
>>
>> Signed-off-by: Kevin Traynor
>> ---
> Looks good. Just noticed that there's some grammar discrep
Update the LTS section to mention the branch, how LTS support ends
and update the currently maintained LTS branches.
Signed-off-by: Kevin Traynor
Acked-by: Aaron Conole
---
v2: fixed typo
doc/guides/contributing/stable.rst | 9 +++--
1 file changed, 7 insertions(+), 2 deletions(-)
diff --
Minutes 7 February 2019
---
Agenda:
* Release Dates
* Subtrees
* OvS
* Opens
Participants:
* Debian
* Intel
* Mellanox
* RedHat
Release Dates
-
* v19.02 released:
* https://core.dpdk.org/download/
* https://doc.dpdk.org/guides/rel_notes/release_19_02.html
> -Original Message-
> From: Kusztal, ArkadiuszX
> Sent: Thursday, February 7, 2019 10:55 AM
> To: dev@dpdk.org
> Cc: akhil.go...@nxp.com; Trahe, Fiona ;
> shally.ve...@caviumnetworks.com;
> sunila.s...@caviumnetworks.com; ashish.gu...@caviumnetworks.com; Kusztal,
> ArkadiuszX
>
> Sub
Kevin Traynor writes:
> Update the LTS section to mention the branch, how LTS support ends
> and update the currently maintained LTS branches.
>
> Signed-off-by: Kevin Traynor
> ---
Looks good. Just noticed that there's some grammar discrepancy (I see
mixing 'an LTS' and 'a LTS' - then again,
On 2/7/2019 12:17 PM, Andrew Rybchenko wrote:
> The patch series improves multi-process support in net/sfc.
> It carefully distinguishes shared and process private data.
>
> Andrew Rybchenko (29):
> net/sfc: remove control path logging from Rx queue count
> net/sfc: fix logging from secondary
Update the LTS section to mention the branch, how LTS support ends
and update the currently maintained LTS branches.
Signed-off-by: Kevin Traynor
---
doc/guides/contributing/stable.rst | 9 +++--
1 file changed, 7 insertions(+), 2 deletions(-)
diff --git a/doc/guides/contributing/stable.rst
On Thu, Feb 07, 2019 at 09:34:26AM -0500, Neil Horman wrote:
> On Wed, Feb 06, 2019 at 02:17:45PM +, Bruce Richardson wrote:
> > On Wed, Feb 06, 2019 at 07:22:54AM -0500, Neil Horman wrote:
> > > On Wed, Feb 06, 2019 at 11:01:30AM +, Bruce Richardson wrote:
> > > > Since compat library is o
On Wed, Feb 06, 2019 at 02:17:45PM +, Bruce Richardson wrote:
> On Wed, Feb 06, 2019 at 07:22:54AM -0500, Neil Horman wrote:
> > On Wed, Feb 06, 2019 at 11:01:30AM +, Bruce Richardson wrote:
> > > Since compat library is only a single header, we can easily move it into
> > > the EAL common
On 2/5/2019 1:39 PM, Hari Kumar Vemula wrote:
> test_create_bonded_device is failing due to improper initialisation in
> bonded device configuration. Which leads to crash while setting up queues.
>
> The value of nb_rx_desc is checked if it is not in range of rx_desc_lim of
> bonded device which f
On Thu, Feb 07, 2019 at 11:56:30AM +, Ferruh Yigit wrote:
> On 1/21/2019 10:43 AM, Parthasarathy, JananeeX M wrote:
> >
> >
> >> -Original Message-
> >> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Chaitanya Babu Talluri
> >> Sent: Friday, January 18, 2019 8:54 PM
> >> To: dev
On 1/30/2019 11:30 AM, Ferruh Yigit wrote:
> On 1/30/2019 1:08 AM, Qi Zhang wrote:
>> Fix potential memory leak due to kvlist not be freed.
>>
>> Fixes: 0d0dd2d9d8ff ("net/pcap: enable data path for secondary process")
>> Cc: sta...@dpdk.org
>>
>> Reported-by: Gage Eads
>> Signed-off-by: Qi Zhang
On 2/3/2019 7:42 PM, Julien Meunier wrote:
> If the port has received less than ``pkt_per_port`` packets (for
> example, the port has missed some packets), the test is in an infinite
> loop.
>
> Instead of expecting a number of packet to receive, let the port to be
> drained by itself. If no more
Secondary process needs to know packet classes supported
by the NIC on Rx.
Signed-off-by: Andrew Rybchenko
---
doc/guides/rel_notes/release_19_05.rst | 1 +
drivers/net/sfc/sfc.c | 16
drivers/net/sfc/sfc.h | 1 +
drivers/net/sfc/sfc_ethdev.c
The flag is required in default RSS RETA get which does not make sense
in isolated mode.
Signed-off-by: Andrew Rybchenko
---
drivers/net/sfc/sfc.h| 3 ++-
drivers/net/sfc/sfc_ethdev.c | 15 ++-
drivers/net/sfc/sfc_flow.c | 3 +--
drivers/net/sfc/sfc_port.c | 2 +-
driv
RSS get requests are supported in secondary process.
Prepare to make sfc_adapter primary process private data.
Signed-off-by: Andrew Rybchenko
---
drivers/net/sfc/sfc.c| 2 +-
drivers/net/sfc/sfc.h| 4 ++--
drivers/net/sfc/sfc_ethdev.c | 15 +--
drivers/net/sfc/sfc
Adapter lock will become primary process only.
Signed-off-by: Andrew Rybchenko
---
drivers/net/sfc/sfc_ethdev.c | 20
1 file changed, 20 deletions(-)
diff --git a/drivers/net/sfc/sfc_ethdev.c b/drivers/net/sfc/sfc_ethdev.c
index c6bee09ee..6b00601fc 100644
--- a/drivers/net
Make sfc_adapter primary process only.
Signed-off-by: Andrew Rybchenko
---
drivers/net/sfc/sfc.h| 20 ---
drivers/net/sfc/sfc_ethdev.c | 105 +++
drivers/net/sfc/sfc_flow.c | 10 ++--
drivers/net/sfc/sfc_rx.c | 2 +-
drivers/net/sfc/sfc_tx.c
Logging should be supported in secondary process and now we have
everything required to share at least main logging macro.
sfc_adapter is going to become primary process only.
Signed-off-by: Andrew Rybchenko
---
drivers/net/sfc/sfc_ethdev.c | 14 --
drivers/net/sfc/sfc_log.h| 28
Prepare to make sfc_adapter primary process private data.
Signed-off-by: Andrew Rybchenko
---
drivers/net/sfc/sfc.c| 5 +-
drivers/net/sfc/sfc.h| 6 +--
drivers/net/sfc/sfc_ethdev.c | 16 +++---
drivers/net/sfc/sfc_tx.c | 100 +++
4 files
Prepare to make sfc_adapter primary process private data.
Signed-off-by: Andrew Rybchenko
---
drivers/net/sfc/sfc.h| 11 +++-
drivers/net/sfc/sfc_ethdev.c | 22 +---
drivers/net/sfc/sfc_flow.c | 6 +-
drivers/net/sfc/sfc_rx.c | 105 ++-
4 fil
libefx is not multi-process aware and all related structures
should be moved to primary process only.
Signed-off-by: Andrew Rybchenko
---
drivers/net/sfc/sfc.h| 3 ++
drivers/net/sfc/sfc_ethdev.c | 2 +-
drivers/net/sfc/sfc_flow.c | 8 ++--
drivers/net/sfc/sfc_rx.c | 77
From: Ivan Malov
Fixes: f8244c6399d9 ("ethdev: increase port id range")
Cc: sta...@dpdk.org
Signed-off-by: Ivan Malov
Signed-off-by: Andrew Rybchenko
---
drivers/net/sfc/sfc_debug.h | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/net/sfc/sfc_debug.h b/drivers/net
Prepare to make sfc_adapter primary process private data.
Signed-off-by: Andrew Rybchenko
---
drivers/net/sfc/sfc.h| 21 +--
drivers/net/sfc/sfc_ethdev.c | 39 +++-
2 files changed, 31 insertions(+), 29 deletions(-)
diff --git a/drivers/ne
If Tx datapath supports multi-process, secondary process should be
able to use Tx descriptor status API.
Signed-off-by: Andrew Rybchenko
---
doc/guides/rel_notes/release_19_05.rst | 1 +
drivers/net/sfc/sfc_dp_tx.h| 3 +++
drivers/net/sfc/sfc_ethdev.c | 11 +--
dr
sfc_adapter structure will become primary process only private data.
Start to factor out shared data into dedicated structure which will
become separate structure finally.
Signed-off-by: Andrew Rybchenko
---
drivers/net/sfc/sfc.h| 15 +--
drivers/net/sfc/sfc_debug.h | 9 +++
RxQ index is stored in generic datapath queue structure.
Signed-off-by: Andrew Rybchenko
---
drivers/net/sfc/sfc_ethdev.c | 2 +-
drivers/net/sfc/sfc_rx.h | 12
2 files changed, 1 insertion(+), 13 deletions(-)
diff --git a/drivers/net/sfc/sfc_ethdev.c b/drivers/net/sfc/sfc_eth
libefx is not multi-process aware and all related structures
should be moved to primary process only.
Signed-off-by: Andrew Rybchenko
---
drivers/net/sfc/sfc.c| 2 +-
drivers/net/sfc/sfc.h| 2 +
drivers/net/sfc/sfc_ethdev.c | 2 +-
drivers/net/sfc/sfc_tx.c | 75 +++
TxQ index is stored in generic datapath queue structure.
Signed-off-by: Andrew Rybchenko
---
drivers/net/sfc/sfc_ethdev.c | 2 +-
drivers/net/sfc/sfc_tx.h | 12
2 files changed, 1 insertion(+), 13 deletions(-)
diff --git a/drivers/net/sfc/sfc_ethdev.c b/drivers/net/sfc/sfc_eth
If datapath supports multi-process, it should be possible to get
its TxQ structure by the queue index.
Signed-off-by: Andrew Rybchenko
---
drivers/net/sfc/sfc_ethdev.c | 2 +-
drivers/net/sfc/sfc_tx.c | 14 +++---
drivers/net/sfc/sfc_tx.h | 2 +-
3 files changed, 9 insertions(+
Dynamic log type value may differ in primary and secondary processes.
Signed-off-by: Andrew Rybchenko
---
drivers/net/sfc/sfc.h| 2 +-
drivers/net/sfc/sfc_ethdev.c | 4 +++-
drivers/net/sfc/sfc_log.h| 10 +-
3 files changed, 9 insertions(+), 7 deletions(-)
diff --git a/dri
RSS RETA query and hash configuration get functions use shared
adapter data only. No libefx functions are called.
Signed-off-by: Andrew Rybchenko
---
doc/guides/rel_notes/release_19_05.rst | 2 ++
drivers/net/sfc/sfc_ethdev.c | 10 ++
2 files changed, 12 insertions(+)
diff --
Secondary process needs to know TxQ state.
TxQ control structure will become primary process private.
Signed-off-by: Andrew Rybchenko
---
drivers/net/sfc/sfc_ev.c | 4 +++-
drivers/net/sfc/sfc_tx.c | 51 +++-
drivers/net/sfc/sfc_tx.h | 6 +++--
3 files chang
Secondary process needs to know RxQ state.
RxQ control structure will become primary process private.
Signed-off-by: Andrew Rybchenko
---
drivers/net/sfc/sfc_ethdev.c | 6 ++--
drivers/net/sfc/sfc_ev.c | 8 +++--
drivers/net/sfc/sfc_rx.c | 67
drive
RxQ control structure contains primary process only data and will
become primary process only. RxQ info get is supported in secondary
process.
Signed-off-by: Andrew Rybchenko
---
drivers/net/sfc/sfc_ethdev.c | 7 ++-
drivers/net/sfc/sfc_rx.c | 10 +-
drivers/net/sfc/sfc_rx.h
The patch series improves multi-process support in net/sfc.
It carefully distinguishes shared and process private data.
Andrew Rybchenko (29):
net/sfc: remove control path logging from Rx queue count
net/sfc: fix logging from secondary process
net/sfc: avoid usage of RxQ control structure in
1 - 100 of 116 matches
Mail list logo
