Hi all
> -Original Message-
> From: Noa Ezra
> Sent: Thursday, June 20, 2019 8:58 AM
> To: Maxime Coquelin
> Cc: Matan Azrad ; dev@dpdk.org
> Subject: RE: [PATCH 2/2] net/vhost: support mrg-rxbuf disabling
>
> Hi Maxime,
> Thanks for your comment, please see below.
>
> > -Original M
19/06/2019 18:08, Akhil Goyal:
> Hi Fan,
> > >
> > > Hi Akhil,
> > >
> > > This patch was sent in 19.05 but I just found it can be applied to 19.08
> > > RC0
> > > cleanly.
> > > Do you think I need to send a v4 (with no change) for 19.08?
> > >
> > No need to send a v4, I will take v3. Planning t
In some situations, when a virtual machine is starting,
vring_state_changed can be called while there was no change in the
queue state. This fix makes sure that there was really a change in the
queue state before calling the callback for EVENT_QUEUE_STATE.
Fixes: ee584e9710b9 ("vhost: add driver o
Hi Tiwei, Maxim
From: Tiwei Bie
> Sent: Thursday, June 20, 2019 5:26 AM
> To: Maxime Coquelin
> Cc: Noa Ezra ; Matan Azrad ;
> dev@dpdk.org
> Subject: Re: [PATCH 1/2] net/vhost: support TSO disabling
>
> On Wed, Jun 19, 2019 at 11:53:05AM +0200, Maxime Coquelin wrote:
> > On 6/19/19 8:13 AM, N
Hi Maxime,
Thanks for your comment, please see below.
> -Original Message-
> From: Maxime Coquelin [mailto:maxime.coque...@redhat.com]
> Sent: Wednesday, June 19, 2019 12:10 PM
> To: Noa Ezra
> Cc: Matan Azrad ; dev@dpdk.org
> Subject: Re: [PATCH 2/2] net/vhost: support mrg-rxbuf disablin
Add a missing include with the defines for vhost-user driver features.
Fixes: 5fbb3941da9f ("vhost: introduce driver features related APIs")
Cc: sta...@dpdk.org
Signed-off-by: Noa Ezra
Reviewed-by: Maxime Coquelin
Reviewed-by: Matan Azrad
---
v2 remove checkpatch warnings
---
lib/librte_vhost
This patch adds ice_flow_create, ice_flow_destroy,
ice_flow_flush and ice_flow_validate support,
these are used to handle all the generic filters.
Signed-off-by: Qiming Yang
---
drivers/net/ice/Makefile | 1 +
drivers/net/ice/ice_ethdev.c | 44 +++
drivers/net/ice/ice_ethdev.h
From: wei zhao
The patch enables the backend of rte_flow. It transfers
rte_flow_xxx to device specific data structure and
configures packet process engine's binary classifier
(switch) properly.
Signed-off-by: Wei Zhao
---
drivers/net/ice/Makefile| 1 +
drivers/net/ice/ice_ethdev.
This patch set enables the backend of rte_flow, and the generic filter related
functions in ice driver.
Supported flows include ipv4, tcpv4, udpv4, ipv6, tcpv6, udpv6, tunnel, etc.
This patch set depends on shared code update.
---
v2 changes:
- added UDP tunnel port support.
- fixed compile iss
Enabled UDP tunnel port add and delete functions.
Signed-off-by: Qiming Yang
---
drivers/net/ice/ice_ethdev.c | 54
1 file changed, 54 insertions(+)
diff --git a/drivers/net/ice/ice_ethdev.c b/drivers/net/ice/ice_ethdev.c
index 8ee06d1..949d293 10064
Hi Mattias,
Please see my response inline.
Thanks,
Anoob
> -Original Message-
> From: dev On Behalf Of Mattias Rönnblom
> Sent: Monday, June 17, 2019 6:54 PM
> To: Anoob Joseph ; Jerin Jacob Kollanukkaran
> ; Nikhil Rao ; Erik Gabriel Carrillo
> ; Abhinandan Gujjar
> ; Bruce Richardson
When there is no enough segments for a packet in mergeable
Rx path, we should free the whole mbuf chain instead of just
recycling the last segment.
Fixes: bcac5aa207f8 ("net/virtio: improve batching in mergeable path")
Cc: sta...@dpdk.org
Reviewed-by: Maxime Coquelin
Signed-off-by: Tiwei Bie
--
v2:
- Fix commit log (Maxime);
Tiwei Bie (4):
net/virtio: fix memory leak in in-order Rx
net/virtio: fix memory leak in mergeable Rx
net/virtio: fix memory leak in mergeable packed Rx
net/virtio: fix packets check in mergeable packed Rx
drivers/net/virtio/virtio_rxtx.c | 56 +
When there is no enough segments for a packet in mergeable
packed Rx path, we should free the whole mbuf chain instead
of just recycling the last segment.
Fixes: a76290c8f1cf ("net/virtio: implement Rx path for packed queues")
Cc: sta...@dpdk.org
Reviewed-by: Maxime Coquelin
Signed-off-by: Tiwei
We should check the descriptor state instead of vq's internal
free count (i.e. the number of descriptors that we haven't made
available) for the remaining mergeable packets.
Fixes: a76290c8f1cf ("net/virtio: implement Rx path for packed queues")
Cc: sta...@dpdk.org
Reviewed-by: Maxime Coquelin
S
When there is no enough segments for a packet in in-order
mergeable Rx path, we should free the whole mbuf chain instead
of just recycling the last segment.
Fixes: e5f456a98d3c ("net/virtio: support in-order Rx and Tx")
Cc: sta...@dpdk.org
Reviewed-by: Maxime Coquelin
Signed-off-by: Tiwei Bie
-
On Wed, Jun 19, 2019 at 11:53:05AM +0200, Maxime Coquelin wrote:
> On 6/19/19 8:13 AM, Noa Ezra wrote:
> > TSO (TCP Segmentation Offload) is enabled by default on vhost.
> > Add the ability to disable TSO on vhost.
> > The user should also disable the feature on the virtual machine's xml.
>
> For
On Wed, Jun 19, 2019 at 02:34:40PM +0200, Maxime Coquelin wrote:
> On 6/18/19 9:41 AM, Tiwei Bie wrote:
> > When there is no enough segments for a packet in in-order
> > mergeable Rx path, we should free the whole mbuf chain instead
> > of just the last segment.
>
> I would write instead:
>
> "
>
> -Original Message-
> From: Rong, Leyi
> Sent: Wednesday, June 19, 2019 11:18 PM
> To: Zhang, Qi Z
> Cc: dev@dpdk.org; Rong, Leyi
> Subject: [PATCH v3 00/69] shared code update
>
> Main changes:
> 1. Advanced switch rule support.
> 2. Add more APIs for tunnel management.
> 3. Add som
Turbo_sw PMD driver now building with meson/ninja
with or without SDK libraries.
Signed-off-by: Nicolas Chautru
Acked-by: Kamil Chalupnik
---
drivers/baseband/meson.build | 2 +-
drivers/baseband/turbo_sw/meson.build | 30 ++
meson_options.txt
Adding compile flag to allow to build the turbo_sw PMD
without dependency to have the SDK libraries installed.
Signed-off-by: Nicolas Chautru
---
config/common_base | 3 +-
drivers/baseband/turbo_sw/Makefile | 13 +++---
drivers/baseband/turbo_sw/bbde
The documentation is clarified to point to steps on building the
SDK libraries which are now publicly available:
https://software.intel.com/en-us/articles/flexran-lte-and-5g-nr-fec-software-development-kit-modules
Signed-off-by: Nicolas Chautru
Acked-by: Kamil Chalupnik
---
doc/guides/bbdevs/tu
Update v7: Remove architecture specific reference to RTE_CPUFLAG_SSE4_2
reported on travis-ci
Update v6: Cosmetic change to commit message to include previous Acked-by.
Update v5: Cosmetic change to remove trailing space and to commit message.
Rebased to latest.
Update v4: Missed one file for m
>
>-Original Message-
>From: Aaron Conole [mailto:acon...@redhat.com]
>Sent: Wednesday, June 19, 2019 5:06 PM
>To: Chautru, Nicolas
>Cc: akhil.go...@nxp.com; dev@dpdk.org; Yigit, Ferruh ;
>tho...@monjalon.net; Mokhtar, Amr ; Chalupnik, KamilX
>
>Subject: Re: [dpdk-dev] [PATCH v6 3/3]
Nicolas Chautru writes:
> Turbo_sw PMD driver now building with meson/ninja
> with or without SDK libraries.
>
> Acked-by: Kamil Chalupnik
> Acked-by: Nicolas Chautru
It seems strange to ack your own patch.
> Signed-off-by: Nicolas Chautru
> ---
Something is wrong with this series:
https
>From: dev On Behalf Of Stephen Hemminger
>Sent: Wednesday, June 19, 2019 11:22 AM
>
>This driver had a bogus assert which could never happen.
>This triggers "expression is always false warnings" with some compilers which
>causes build failure.
>Just remove it.
>
>Fixes: 6041aa619f9a ("net/bnx2x:
Nikos Dragazis writes:
> This is the first of a series of patches, whose purpose is to add
> support for the virtio-vhost-user transport. This is a vhost-user
> transport implementation that is different from the default AF_UNIX
> transport. It uses the virtio-vhost-user PCI device in order to tu
C language does not really treat enum's as first class symbols.
The values in an enum live in a global namespace. That means if
DPDK defines "RUNNING" it can't be used by another enum in an
application using DPDK.
To solve this add a prefix "RTE_LCORE_" to the enum values, and
make them grammatic
From: Stephen Hemminger
The correct thing to return if user gives a bad data
is to return -EFAULT. Logging is also discouraged because
it could be used as a DoS attack.
Signed-off-by: Stephen Hemminger
---
kernel/linux/kni/kni_misc.c | 16 +---
1 file changed, 5 insertions(+), 11 d
From: Stephen Hemminger
rte_kni does not follow standard style rules.
Noticed some extra \ line continuation etc.
Signed-off-by: Stephen Hemminger
---
lib/librte_kni/rte_kni.c | 38 +++---
1 file changed, 19 insertions(+), 19 deletions(-)
diff --git a/lib/librt
From: Stephen Hemminger
Make the KNI documentation reflect modern kernel networking.
Ifconfig has been superseded by iproute2 for 15 years.
Iproute2 is well maintained, supports current feature set.
Ethtool is no longer supported by KNI.
Tshark is a better replacement for tcpdump.
Signed-off-by
From: Stephen Hemminger
Using void * instead of proper type is unsafe practice.
Signed-off-by: Stephen Hemminger
---
kernel/linux/kni/kni_dev.h | 12 ++--
1 file changed, 6 insertions(+), 6 deletions(-)
diff --git a/kernel/linux/kni/kni_dev.h b/kernel/linux/kni/kni_dev.h
index f3e6c3c
From: Stephen Hemminger
Since kernel 2.6.28 the network subsystem has provided
dev->stats for devices to use statistics handling and is the
default if no ndo_get_stats is provided.
This allow allows for 64 bit (rather than just 32 bit)
statistics with KNI.
Signed-off-by: Stephen Hemminger
---
While testing KNI with netvsc, saw lots of places more code
could be safely removed from KNI kernel driver.
v4 - add more style fixes
v3 - rebase to current master, add style fix patch
v2 - get rid of unnecessary padding, combine the unused field patches
Stephen Hemminger (8):
kni: don't need s
From: Stephen Hemminger
The kni net structure only exists in driver no API/ABI.
Several fields were either totally unused or set and never used.
The fields in dev_info do need to stay in the ABI but
kernel can ignore them.
Signed-off-by: Stephen Hemminger
kni: drop unused status element
Yet
From: Stephen Hemminger
The netdev subsystem already handles case where
network sevice does not support ioctl.
If device has no rx_mode hook it is not called.
Signed-off-by: Stephen Hemminger
---
kernel/linux/kni/kni_net.c | 19 ---
1 file changed, 19 deletions(-)
diff --git
From: Stephen Hemminger
netdev_alloc_skb is optimized to any alignment or setup
of skb->dev that is required. The kernel has chosen to not pad
packets on x86 (for many years), because it is faster.
Signed-off-by: Stephen Hemminger
---
kernel/linux/kni/kni_net.c | 17 +++--
1 file c
From: Stephen Hemminger
Make the KNI documentation reflect modern kernel networking.
Ifconfig has been superseded by iproute2 for 15 years.
Iproute2 is well maintained, supports current feature set.
Ethtool is no longer supported by KNI.
Tshark is a better replacement for tcpdump.
Signed-off-by
From: Stephen Hemminger
The correct thing to return if user gives a bad data
is to return -EFAULT. Logging is also discouraged because
it could be used as a DoS attack.
Signed-off-by: Stephen Hemminger
---
kernel/linux/kni/kni_misc.c | 16 +---
1 file changed, 5 insertions(+), 11 d
From: Stephen Hemminger
rte_kni does not follow standard style rules.
Noticed some extra \ line continuation etc.
Signed-off-by: Stephen Hemminger
---
lib/librte_kni/rte_kni.c | 38 +++---
1 file changed, 19 insertions(+), 19 deletions(-)
diff --git a/lib/librt
From: Stephen Hemminger
Using void * instead of proper type is unsafe practice.
Signed-off-by: Stephen Hemminger
---
kernel/linux/kni/kni_dev.h | 12 ++--
1 file changed, 6 insertions(+), 6 deletions(-)
diff --git a/kernel/linux/kni/kni_dev.h b/kernel/linux/kni/kni_dev.h
index f3e6c3c
From: Stephen Hemminger
The kni net structure only exists in driver no API/ABI.
Several fields were either totally unused or set and never used.
The fields in dev_info do need to stay in the ABI but
kernel can ignore them.
Signed-off-by: Stephen Hemminger
kni: drop unused status element
Yet
From: Stephen Hemminger
Since kernel 2.6.28 the network subsystem has provided
dev->stats for devices to use statistics handling and is the
default if no ndo_get_stats is provided.
This allow allows for 64 bit (rather than just 32 bit)
statistics with KNI.
Signed-off-by: Stephen Hemminger
---
From: Stephen Hemminger
netdev_alloc_skb is optimized to any alignment or setup
of skb->dev that is required. The kernel has chosen to not pad
packets on x86 (for many years), because it is faster.
Signed-off-by: Stephen Hemminger
---
kernel/linux/kni/kni_net.c | 17 +++--
1 file c
From: Stephen Hemminger
The netdev subsystem already handles case where
network sevice does not support ioctl.
If device has no rx_mode hook it is not called.
Signed-off-by: Stephen Hemminger
---
kernel/linux/kni/kni_net.c | 19 ---
1 file changed, 19 deletions(-)
diff --git
While testing KNI with netvsc, saw lots of places more code
could be safely removed from KNI kernel driver.
This is still mostly "putting lipstick on a pig" all users
would be better off using virtio_user rather than KNI.
v3 - more style cleanups in last patch
v2 - get rid of unnecessary padding,
On Wed, Jun 19, 2019 at 11:46:12AM +0100, Bruce Richardson wrote:
> On Wed, Jun 19, 2019 at 06:39:00AM -0400, Neil Horman wrote:
> > On Thu, Jun 13, 2019 at 03:44:02PM +0100, Bruce Richardson wrote:
> > > On Thu, Jun 13, 2019 at 10:23:36AM -0400, Neil Horman wrote:
> > > > The __rte_internal macro
This driver had a bogus assert which could never happen.
This triggers "expression is always false warnings" with some
compilers which causes build failure.
Just remove it.
Fixes: 2af14ca79c0a ("net/qede: support 100G")
Signed-off-by: Stephen Hemminger
---
drivers/net/qede/qede_ethdev.c | 1 -
1
This driver had a bogus assert which could never happen.
This triggers "expression is always false warnings" with some
compilers which causes build failure.
Just remove it.
Fixes: 6041aa619f9a ("net/bnx2x: fix poll link status")
Signed-off-by: Stephen Hemminger
---
drivers/net/bnx2x/bnx2x_ethdev
Turbo_sw PMD driver now building with meson/ninja
with or without SDK libraries.
Acked-by: Kamil Chalupnik
Acked-by: Nicolas Chautru
Signed-off-by: Nicolas Chautru
---
drivers/baseband/meson.build | 2 +-
drivers/baseband/turbo_sw/meson.build | 30 ++
meso
The documentation is clarified to point to steps on building the
SDK libraries which are now publicly available:
https://software.intel.com/en-us/articles/flexran-lte-and-5g-nr-fec-software-development-kit-modules
Acked-by: Kamil Chalupnik
Acked-by: Nicolas Chautru
Signed-off-by: Nicolas Chautru
Adding compile flag to allow to build the turbo_sw PMD
without dependency to have the SDK libraries installed.
Acked-by: Kamil Chalupnik
Acked-by: Nicolas Chautru
Signed-off-by: Nicolas Chautru
---
config/common_base | 3 +-
drivers/baseband/turbo_sw/Makefile
Update v6: Cosmetic change to commit message to include previous Acked-by.
Update v5: Cosmetic change to remove trailing space and to commit message.
Rebased to latest.
Update v4: Missed one file for meson build path and minor change to prevent
warning for some configurations due to unused symb
The freeing of the malloced memory is difficult when using asserts to
cause early abort of the test cases, since that can leak memory. The
original placement of the free call caused a memory leak if the test
finished early, while a fix for that leak caused the test to fail at
times due to the memor
the test_rawdev.c file was missing from the meson.build file, and the test
case from the list of test commands.
Fixes: 55ca1b0f2151 ("raw/skeleton: add test cases")
Cc: shreyansh.j...@nxp.com
Cc: sta...@dpdk.org
Signed-off-by: Bruce Richardson
---
app/test/meson.build | 3 +++
1 file changed, 3
The rawdev_autotest command was failing due to memory issues, and was
not present at all in meson builds. These two patches fix these
problems.
Bruce Richardson (2):
raw/skeleton: fix failing test case
app/test: add missing rawdev autotest to meson build
app/test/meson.build
This patch introduces a new version of the event timer adapter software
PMD. In the original design, timer event producer lcores in the primary
and secondary processes enqueued event timers into a ring, and a
service core in the primary process dequeued them and processed them
further. To improve
This patch introduces a new version of the event timer adapter software
PMD [1]. In the original design, timer event producer lcores in the primary
and secondary processes enqueued event timers into a ring, and a service
core in the primary process dequeued them and processed them further. To
impr
This patch add package sending and receiving function codes.
Signed-off-by: Ziyang Xuan
---
drivers/net/hinic/hinic_pmd_ethdev.c |4 +
drivers/net/hinic/hinic_pmd_rx.c | 439 +++
drivers/net/hinic/hinic_pmd_tx.c | 1082 ++
3 files changed, 1525 insert
Add rss, stats, promiscuous ops related function codes.
Signed-off-by: Ziyang Xuan
---
drivers/net/hinic/hinic_pmd_ethdev.c | 735 +++
1 file changed, 735 insertions(+)
diff --git a/drivers/net/hinic/hinic_pmd_ethdev.c
b/drivers/net/hinic/hinic_pmd_ethdev.c
index 6bd35a
Add dev_start, dev_stop, link_update, queue_setup, queue_release
related function codes.
Signed-off-by: Ziyang Xuan
---
drivers/net/hinic/hinic_pmd_ethdev.c | 684 +++
drivers/net/hinic/hinic_pmd_rx.c | 420
drivers/net/hinic/hinic_pmd_tx.c | 68
Add device initialization function codes.
Signed-off-by: Ziyang Xuan
---
drivers/net/hinic/Makefile | 2 +
drivers/net/hinic/hinic_pmd_ethdev.c | 700 ++-
drivers/net/hinic/hinic_pmd_rx.c | 178 +++
drivers/net/hinic/hinic_pmd_tx.c | 92
driv
On 6/18/2019 2:49 PM, Reshma Pattan wrote:
> telemetry has support for fetching port based stats
> from metrics library.
>
> Metrics library also has global stats which are
> not fetched by telemetry, so extend telemetry to
> fetch the global metrics.
>
> Signed-off-by: Reshma Pattan
> Acked-by:
Add build and doc files along with hinic_pmd_ethdev.c
which just includes PMD register and log initialization
for compilation.
Signed-off-by: Ziyang Xuan
---
MAINTAINERS | 9 +
config/common_base | 5 +
config/common_linux
Add various headers that define mgmt commands, cmdq commands,
rx data structures, tx data structures, private adapter data
structures and basic defines for use in the code.
Signed-off-by: Ziyang Xuan
---
drivers/net/hinic/base/hinic_compat.h | 256 ++
drivers/net/hinic/base/hinic_pm
Work queue is used for cmdq and tx/rx buff description.
Nic business needs to configure cmdq context and txq/rxq
context. This patch adds data structures and function codes
for work queue and context.
Signed-off-by: Ziyang Xuan
---
drivers/net/hinic/base/hinic_pmd_nicio.c | 894 +
The items of configurations and queries for nic business include
MAC, VLAN, MTU, RSS and so on. These configurations and queries
are handled by mgmt module. This patch introduces related
data structures and function codes.
Signed-off-by: Ziyang Xuan
---
drivers/net/hinic/base/hinic_pmd_niccfg.c
Add code for hardware operation, including configuration,
query and so on.
Signed-off-by: Ziyang Xuan
---
drivers/net/hinic/base/hinic_pmd_cfg.c | 208
drivers/net/hinic/base/hinic_pmd_cfg.h | 145 +++
drivers/net/hinic/base/hinic_pmd_hwdev.c | 1414 ++
drivers/net
Mgmt module is a kinkd of administration module for the chip.
It is responsible for handling administration command from host.
It uses api channel. This patch adds related data structures,
packaged interfaces and function codes.
Signed-off-by: Ziyang Xuan
---
drivers/net/hinic/base/hinic_pmd_mgm
Eqs include aeq and ceq. PMD supports aeq only. Aeq is a kind of
queue for mgmt asynchronous message and mgmt command response message.
This patch introduces data structures, initialization, and related
interfaces about aeq.
Signed-off-by: Ziyang Xuan
---
drivers/net/hinic/base/hinic_pmd_eqs.c |
Micocode is named ucode in Hi1822. Its main responsibility is data
transmission and reception. But it can also handle some administration
works. It uses cmdq mechanism. This patch introduces data structures,
initialization, interfaces, and commands sending functions of cmdq.
Signed-off-by: Ziyang
Api command channel is for communicating with mgmt module of chip.
This patch introduces data structures, initialization, interfaces,
and commands sending functions of api command channel.
Signed-off-by: Ziyang Xuan
---
drivers/net/hinic/base/hinic_pmd_api_cmd.c | 1042
driv
This patch adds some HW interfaces for bar operatioin interfaces,
including: mapped bar address geeting, HW attributes getting,
msi-x reg operation, function type getting and so on.
Signed-off-by: Ziyang Xuan
---
drivers/net/hinic/base/hinic_pmd_hwif.c | 474
drivers/net
Add HW registers definition header file for Hi1822 NIC.
Signed-off-by: Ziyang Xuan
---
drivers/net/hinic/base/hinic_csr.h | 160 +
1 file changed, 160 insertions(+)
create mode 100644 drivers/net/hinic/base/hinic_csr.h
diff --git a/drivers/net/hinic/base/hinic_csr.h
This patch set adds support of a new net PMD
for Huawei Intelligent nic. This patch provides supoort
for basic RX/TX and the contorl path needed for it.
Later on new features will be added like VLAN, VFs, etc.
Basic features:
1. Basic device operations: probe, initialization, start/stop,
config
The dummy packet for GRE had ICE_VXLAN instead of ICE_NVGRE
listed in the offsets so change that to be correct. The
dummy packet itself had some text to indicate VXLAN also
so I changed that to just be GRE since it really wasn't
VXLAN.
Fixes: 5e81d85ff066 ("net/ice/base: enable additional switch r
Enable forward to Q group action in ice_add_adv_rule.
Signed-off-by: Dan Nowlin
Signed-off-by: Paul M Stillwell Jr
Signed-off-by: Leyi Rong
---
drivers/net/ice/base/ice_switch.c | 11 +++
1 file changed, 11 insertions(+)
diff --git a/drivers/net/ice/base/ice_switch.c
b/drivers/net/ic
Add capability to create inner IP and inner TCP switch recipes and
rules. Change UDP tunnel dummy packet to accommodate the training of
these new rules.
Signed-off-by: Dan Nowlin
Signed-off-by: Paul M Stillwell Jr
Signed-off-by: Leyi Rong
---
drivers/net/ice/base/ice_protocol_type.h | 8 +-
In order to properly support signed packages, we always have
to send the complete buffer to firmware, regardless of any
unused space at the end. This is because the SHA hash value
is computed over the entire buffer.
Fixes: 51d04e4933e3 ("net/ice/base: add flexible pipeline module")
Signed-off-by:
Eliminate some semantic warnings, static analysis warnings.
Signed-off-by: Bruce Allan
Signed-off-by: Kevin Scott
Signed-off-by: Paul M Stillwell Jr
Signed-off-by: Leyi Rong
---
drivers/net/ice/base/ice_flex_pipe.c | 8
drivers/net/ice/base/ice_flow.c | 5 +
drivers/
Add internal usage flag, bit 91 as described in spec.
Update width of internal queue state to 122 also as described in spec.
Signed-off-by: Ashish Shah
Signed-off-by: Paul M Stillwell Jr
Signed-off-by: Leyi Rong
---
drivers/net/ice/base/ice_common.c| 3 ++-
drivers/net/ice/base/ice_lan_tx_
- Add function to remove ES profile map as it is now being used in
clearing and freeing HW tables.
- Locks were initially not used for releasing ES profile maps and
flow profiles as the sequence is part of driver unload. Adding
calls to acquire and release locks to ensure that any calls made
by the
This patch corrects some errors in UDP and TCP switch rule
programming by adding additional dummy packets.
Fixes: 5e81d85ff066 ("net/ice/base: enable additional switch rules")
Signed-off-by: Dan Nowlin
Signed-off-by: Paul M Stillwell Jr
Signed-off-by: Leyi Rong
---
drivers/net/ice/base/ice_sw
According to recent specification versions, the field in the Queue
Shutdown AdminQ command consisting of the "driver unloading" indication
is not a 4 byte field (it is byte.bit 16.0). Change it to a byte and
remove the unnecessary endian conversion.
Signed-off-by: Bruce Allan
Signed-off-by: Paul
Added refresh_required flag to determine if we need to update the
recipe to profile mapping cache. This will reduce the number of
calls made to refresh the profile map.
Signed-off-by: Shivanshu Shukla
Signed-off-by: Paul M Stillwell Jr
Signed-off-by: Leyi Rong
---
drivers/net/ice/base/ice_swit
For chained recipe entry, the field vector index used to match
switch ID should always be zero.
Add ICE_AQ_SW_ID_LKUP_IDX define to indicate the FV index used
to extract the switch ID.
Fixes: dca90ed479cf ("net/ice/base: programming a new switch recipe")
Signed-off-by: Dan Nowlin
Signed-off-by:
Correct NVGRE header structure and its field offsets.
Signed-off-by: Dan Nowlin
Signed-off-by: Paul M Stillwell Jr
Signed-off-by: Leyi Rong
---
drivers/net/ice/base/ice_protocol_type.h | 5 +++--
drivers/net/ice/base/ice_switch.c| 2 +-
2 files changed, 4 insertions(+), 3 deletions(-)
A couple of places in the code use a 'sizeof(bitmap) * BITS_PER_BYTE'
construction to calculate the size of the bitmap when calling
ice_zero_bitmap. Instead of doing this, just use the same value as in
the ice_declare_bitmap declaration.
Signed-off-by: Jacob Keller
Signed-off-by: Paul M Stillwell
A few places in the code used ice_memset instead of ice_zero_bitmap to
initialize a bitmap to zeros.
Signed-off-by: Jacob Keller
Signed-off-by: Paul M Stillwell Jr
Signed-off-by: Leyi Rong
---
drivers/net/ice/base/ice_flex_pipe.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff
Fix ice_cp_bitmap to copy the entire storage.
Fixes: c9e37832c95f ("net/ice/base: rework on bit ops")
Signed-off-by: Jacob Keller
Signed-off-by: Paul M Stillwell Jr
Signed-off-by: Leyi Rong
---
drivers/net/ice/base/ice_bitops.h | 17 +
1 file changed, 5 insertions(+), 12 delet
Fix ice_zero_bitmap to zero the entire storage.
Fixes: c9e37832c95f ("net/ice/base: rework on bit ops")
Signed-off-by: Jacob Keller
Signed-off-by: Paul M Stillwell Jr
Signed-off-by: Leyi Rong
---
drivers/net/ice/base/ice_bitops.h | 19 ++-
1 file changed, 6 insertions(+), 13 d
In CEE mode, the TSA information can be derived from the reported
priority value.
Signed-off-by: Chinh T Cao
Signed-off-by: Paul M Stillwell Jr
Signed-off-by: Leyi Rong
---
drivers/net/ice/base/ice_dcb.c | 8 +++-
1 file changed, 7 insertions(+), 1 deletion(-)
diff --git a/drivers/net/ice
While calling ice_find_recp we were calling ice_get_recp_to_prof_map
everytime we called ice_find_recp. ice_get_recp_to_prof_map is a very
expensive operation and we should try to reduce the number of times we
call this function. So moved it into ice_get_recp_frm_fw since we only
need to have fresh
Added routines for handling tunnel management:
- ice_tunnel_port_in_use()
- ice_tunnel_get_type()
- ice_find_free_tunnel_entry()
- ice_create_tunnel()
- ice_destroy_tunnel()
Signed-off-by: Dan Nowlin
Signed-off-by: Paul M Stillwell Jr
Signed-off-by: Leyi R
1. Add defines for Link Topology Netlist Section.
2. Add missing Read MAC command response bits.
3. Adds AQ error 29.
Signed-off-by: Jacek Naczyk
Signed-off-by: Faerman Lev
Signed-off-by: Paul M Stillwell Jr
Signed-off-by: Leyi Rong
---
drivers/net/ice/base/ice_adminq_cmd.h | 3 +++
drivers/n
Refactored VSI node sched code to use port_info ptr as call arg.
The declaration of VSI node getter function has been modified to use
pointer to ice_port_info structure instead of pointer to hw structure.
This way suitable port_info structure is used to find VSI node.
Signed-off-by: Grzegorz Nitk
Make functions that can be, static. Remove some code that is not
currently called.
Signed-off-by: Bruce Allan
Signed-off-by: Paul M Stillwell Jr
Signed-off-by: Leyi Rong
---
drivers/net/ice/base/ice_flex_pipe.c | 523 ---
drivers/net/ice/base/ice_flex_pipe.h | 59 ---
Cleanup the useless code.
Signed-off-by: Paul M Stillwell Jr
Signed-off-by: Leyi Rong
---
drivers/net/ice/base/ice_controlq.c | 62 +---
drivers/net/ice/base/ice_fdir.h | 4 --
drivers/net/ice/base/ice_flex_pipe.c | 5 ++-
drivers/net/ice/base/ice_sched.c |
use __ALWAYS_UNUSED to mark function parameters unused to replace
__always_unused marker.
Signed-off-by: Jacob Keller
Signed-off-by: Paul M Stillwell Jr
Signed-off-by: Leyi Rong
---
drivers/net/ice/base/ice_flex_pipe.c | 2 +-
drivers/net/ice/base/ice_type.h | 3 +++
2 files changed, 4 in
Introduce some more new macros, like ICE_VSI_LB and the like.
Signed-off-by: Paul M Stillwell Jr
Signed-off-by: Leyi Rong
---
drivers/net/ice/base/ice_flow.c | 4 +++-
drivers/net/ice/base/ice_switch.h | 14 +-
drivers/net/ice/base/ice_type.h | 6 +-
3 files changed, 13 in
1 - 100 of 224 matches
Mail list logo