dpdk.git
3 years agoapp/flow-perf: skip dumps for masked ports
Wisam Jaddo [Sun, 14 Mar 2021 09:54:24 +0000 (11:54 +0200)]
app/flow-perf: skip dumps for masked ports

Take into consideration that the user may call portmask for
any run, thus the app should always check if port is needed
to collect and report or not.

Fixes: 070316d01d3e ("app/flow-perf: add multi-core rule insertion and deletion")
Fixes: d8099d7ecbd0 ("app/flow-perf: split dump functions")
Cc: stable@dpdk.org
Signed-off-by: Wisam Jaddo <wisamm@nvidia.com>
Acked-by: Alexander Kozyrev <akozyrev@nvidia.com>
3 years agoapp/flow-perf: rename records of used CPU time
Wisam Jaddo [Sun, 14 Mar 2021 09:54:23 +0000 (11:54 +0200)]
app/flow-perf: rename records of used CPU time

create_flow and create_meter are not correct names since those
are records that contain creation and deletion, which makes
them more of a record for such data.

Fixes: d8099d7ecbd0 ("app/flow-perf: split dump functions")
Cc: stable@dpdk.org
Signed-off-by: Wisam Jaddo <wisamm@nvidia.com>
Acked-by: Alexander Kozyrev <akozyrev@nvidia.com>
3 years agoapp/flow-perf: add runtime option to use unique data
Wisam Jaddo [Sun, 14 Mar 2021 09:54:22 +0000 (11:54 +0200)]
app/flow-perf: add runtime option to use unique data

Current support for unique data is to compile with config.h
var FIXED_VALUES as 0, and this is only supported on
compilation time, as a result the user may use only single
mode for each compilation.

Starting with this commit the user will have the ability to
use this feature on the fly by using this new option:
--unique-data

Example of unique data usage:
Insert many rules with different encap data for a flows that
have encap action in it.

Signed-off-by: Wisam Jaddo <wisamm@nvidia.com>
Acked-by: Alexander Kozyrev <akozyrev@nvidia.com>
3 years agoapp/flow-perf: use more generic wrapper to get cycles
Wisam Jaddo [Sun, 14 Mar 2021 09:54:21 +0000 (11:54 +0200)]
app/flow-perf: use more generic wrapper to get cycles

rdtsc() is x86 related, while this might fail for other archs,
so it's better to use more generic API for cycles measurement.

Signed-off-by: Wisam Jaddo <wisamm@nvidia.com>
Acked-by: Alexander Kozyrev <akozyrev@nvidia.com>
3 years agonet/dpaa2: fix RSS distribution size field
Hemant Agrawal [Thu, 8 Apr 2021 09:17:43 +0000 (14:47 +0530)]
net/dpaa2: fix RSS distribution size field

RSS distribution field is U64, while the DPAA2 code
was using integer value, which is causing a issue
for MPLS having bit position 33.
This patch fixes the code to use unsigned long long.

Fixes: 1832bc8ee8d4 ("net/dpaa2: support MPLS distribution")
Cc: stable@dpdk.org
Signed-off-by: Hemant Agrawal <hemant.agrawal@nxp.com>
3 years agonet/enic: fix flow initialization error handling
John Daley [Thu, 8 Apr 2021 23:06:31 +0000 (16:06 -0700)]
net/enic: fix flow initialization error handling

Fix a rare case in rte_flow initialization where the action hash table
is not freed if allocating a NIC match table fails.

Fixes: ea7768b5bba8 ("net/enic: add flow implementation based on Flow Manager API")
Cc: stable@dpdk.org
Signed-off-by: John Daley <johndale@cisco.com>
Reviewed-by: Hyong Youb Kim <hyonkim@cisco.com>
3 years agonet/hns3: fix code style
Hongbo Zheng [Wed, 31 Mar 2021 10:01:44 +0000 (18:01 +0800)]
net/hns3: fix code style

Add one space before the left brace to solve the static warning.

Fixes: 63e05f19b82b ("net/hns3: support Rx descriptor status query")

Signed-off-by: Hongbo Zheng <zhenghongbo3@huawei.com>
Signed-off-by: Min Hu (Connor) <humin29@huawei.com>
3 years agonet/hns3: delete redundant blank line
Hongbo Zheng [Wed, 31 Mar 2021 10:01:43 +0000 (18:01 +0800)]
net/hns3: delete redundant blank line

Delete redundant blank line in "hns3vf_check_event_cause" to
solve the static warning.

Fixes: a5475d61fa34 ("net/hns3: support VF")
Cc: stable@dpdk.org
Signed-off-by: Hongbo Zheng <zhenghongbo3@huawei.com>
Signed-off-by: Min Hu (Connor) <humin29@huawei.com>
3 years agonet/hns3: support get device version when dump register
Chengwen Feng [Wed, 31 Mar 2021 10:01:42 +0000 (18:01 +0800)]
net/hns3: support get device version when dump register

Support get device version which is equal to the firmware version
when dump register.

Fixes: 936eda25e8da ("net/hns3: support dump register")
Cc: stable@dpdk.org
Signed-off-by: Chengwen Feng <fengchengwen@huawei.com>
Signed-off-by: Min Hu (Connor) <humin29@huawei.com>
3 years agonet/hns3: fix VF mailbox head field
Chengwen Feng [Wed, 31 Mar 2021 10:01:41 +0000 (18:01 +0800)]
net/hns3: fix VF mailbox head field

Currently, the VF mailbox synchronization communication is based on
three fields: head/tail/lost, when head equals tail plus lost, it
means the response is received successfully.

The head field indicates the number of requests that are successfully
sent. If the request sending fails, it should not be updated.

This patch fix the above bug by roll back updates when the sending
fails.

Fixes: 463e748964f5 ("net/hns3: support mailbox")
Cc: stable@dpdk.org
Signed-off-by: Chengwen Feng <fengchengwen@huawei.com>
Signed-off-by: Min Hu (Connor) <humin29@huawei.com>
3 years agonet/hns3: fix flow counter value
Chengwen Feng [Wed, 31 Mar 2021 10:01:40 +0000 (18:01 +0800)]
net/hns3: fix flow counter value

User could create flow rules with specified counter by the action of
RTE_FLOW_ACTION_TYPE_COUNT, but the counter may retain the original
value when create.

This patch fix the bug by read the counter when creating the rule
because the counter is read-clear.

Fixes: fcba820d9b9e ("net/hns3: support flow director")
Cc: stable@dpdk.org
Signed-off-by: Chengwen Feng <fengchengwen@huawei.com>
Signed-off-by: Min Hu (Connor) <humin29@huawei.com>
3 years agonet/hns3: fix flow control exception
Huisong Li [Wed, 31 Mar 2021 10:01:39 +0000 (18:01 +0800)]
net/hns3: fix flow control exception

In multi-TC scenarios, MAC pause is not supported. Otherwise, only
TC0 can trigger pause frames, and other TCs cannot trigger pause
frames. In this case, flow control does not meet the expectation.

Fixes: 62e3ccc2b94c ("net/hns3: support flow control")
Cc: stable@dpdk.org
Signed-off-by: Huisong Li <lihuisong@huawei.com>
Signed-off-by: Min Hu (Connor) <humin29@huawei.com>
3 years agonet/hns3: fix rollback after setting PVID failure
Chengchang Tang [Wed, 31 Mar 2021 10:01:38 +0000 (18:01 +0800)]
net/hns3: fix rollback after setting PVID failure

Currently, three hardware operations are involved in setting the PVID.
If any operation fails, a failure will be returned. And there may be
residual hardware configurations because no rollback is performed.

This patch adds rollback operation for setting PVID to avoid residual
hardware configuration after the PVID fails to be configured.

Fixes: 411d23b9eafb ("net/hns3: support VLAN")
Cc: stable@dpdk.org
Signed-off-by: Chengchang Tang <tangchengchang@huawei.com>
Signed-off-by: Min Hu (Connor) <humin29@huawei.com>
3 years agonet/hns3: fix FLR miss detection
Hongbo Zheng [Wed, 31 Mar 2021 10:01:37 +0000 (18:01 +0800)]
net/hns3: fix FLR miss detection

When FLR occurs, the head pointer register of
the command queue will be cleared, resulting in
abnormal detection of the head pointer register
of the command queue. At present, FLR is detected
in this way, and the reset recovery process is
executed.

However, when FLR occurs, the header pointer
register of the command queue is not necessarily
abnormal. For example, when the driver runs
normally, the value of the header pointer register
of the command queue may also be 0, which will
lead to the miss detection of FLR.

Therefore, the judgment that whether the base
address register of command queue is 0 is added
to ensure that FLR not miss detection.

Fixes: 2790c6464725 ("net/hns3: support device reset")
Cc: stable@dpdk.org
Signed-off-by: Hongbo Zheng <zhenghongbo3@huawei.com>
Signed-off-by: Min Hu (Connor) <humin29@huawei.com>
3 years agonet/hns3: fix setting default MAC address in bonding of VF
Chengwen Feng [Wed, 31 Mar 2021 10:01:36 +0000 (18:01 +0800)]
net/hns3: fix setting default MAC address in bonding of VF

When start testpmd with two hns3 VFs(0000:bd:01.0, 0000:bd:01.7), and
then execute the following commands:
testpmd> create bonded device 1 0
testpmd> set bonding mac_addr 2 3c:12:34:56:78:9a
testpmd> add bonding slave 0 2
testpmd> add bonding slave 1 2
testpmd> set portmask 0x4
testpmd> port start 2

It will occurs the following error in a low probability:
0000:bd:01.0 hns3_get_mbx_resp(): VF could not get mbx(3,0)
head(16) tail(15) lost(1) from PF in_irq:0
0000:bd:01.0 hns3vf_set_default_mac_addr(): Failed to set mac
addr(3C:**:**:**:78:9A) for vf: -62
mac_address_slaves_update(1541) - Failed to update port Id 0
MAC address

The problem replay:
1. The 'port start 2' command will start slave ports and then set slave
   mac address, the function call flow: bond_ethdev_start ->
   mac_address_slaves_update.
2. There are also a monitor task which running in intr thread will check
   slave ports link status and update slave ports mac address, the
   function call flow: bond_ethdev_slave_link_status_change_monitor ->
   bond_ethdev_lsc_event_callback -> mac_address_slaves_update.
3. Because the above step1&2 running on different threads, they may both
   call drivers ops mac_addr_set which is hns3vf_set_default_mac_addr.
4. hns3vf_set_default_mac_addr will first acquire hw.lock and then send
   mailbox to PF and wait PF's response message.  Note: the PF's
   response is an independent message which will received in hw.cmq.crq,
   the receiving operation can only performed in intr thread.
5. So if the step1 operation hold the hw.lock and try get response
   message, and step2 operation try acquire the hw.lock and so it can't
   process the response message, this will lead to step1 fail.

The solution:
1. make all threads could process the mailbox response message, which
   protected by the hw.cmq.crq.lock.
2. use the following rules to avoid deadlock:
2.1. ensure use the correct locking sequence: hw.lock >
     hw.mbx_resp.lock > hw.cmq.crq.lock.
2.2. make sure don't acquire such as hw.lock & hw.mbx_resp.lock again
     when process mailbox response message.

Fixes: 463e748964f5 ("net/hns3: support mailbox")
Cc: stable@dpdk.org
Signed-off-by: Chengwen Feng <fengchengwen@huawei.com>
Signed-off-by: Min Hu (Connor) <humin29@huawei.com>
3 years agonet/hns3: fix some function names for copper media type
Huisong Li [Wed, 31 Mar 2021 10:01:35 +0000 (18:01 +0800)]
net/hns3: fix some function names for copper media type

PHY is a common concept for the copper and optical media type interface.
There are some inappropriate function names for copper ports, which
needs to be adjusted.

Fixes: 2e4859f3b362 ("net/hns3: support PF device with copper PHYs")

Signed-off-by: Huisong Li <lihuisong@huawei.com>
Signed-off-by: Min Hu (Connor) <humin29@huawei.com>
3 years agonet/hns3: fix copyright date
Min Hu (Connor) [Wed, 7 Apr 2021 09:19:13 +0000 (17:19 +0800)]
net/hns3: fix copyright date

This patch updates copyright date for hns3 PMD files.

Fixes: 565829db8b8f ("net/hns3: add build and doc infrastructure")
Fixes: 952ebacce4f2 ("net/hns3: support SVE Rx")
Fixes: e31f123db06b ("net/hns3: support NEON Tx")
Fixes: c09c7847d892 ("net/hns3: support traffic management")

Signed-off-by: Min Hu (Connor) <humin29@huawei.com>
3 years agonet/octeontx2: support flow action port ID
Smadar Fuks [Thu, 8 Apr 2021 10:21:13 +0000 (06:21 -0400)]
net/octeontx2: support flow action port ID

Action port_id was not supported until now.
In this patch the action port_id supports passing from input
port PF to output port which is one of input port respective VF

Signed-off-by: Smadar Fuks <smadarf@marvell.com>
Acked-by: Jerin Jacob <jerinj@marvell.com>
3 years agonet/hns3: support wait in link update
Huisong Li [Tue, 30 Mar 2021 12:53:25 +0000 (20:53 +0800)]
net/hns3: support wait in link update

There are two APIs in ethdev layer to get link status of device, namely,
"rte_eth_link_get" and "rte_eth_link_get_nowait". When the device link
is unstable or auto-negotiation is in progress, the first API supports
the function of waiting for the NIC to link up, and the maximum waiting
time is 9 seconds based on DPDK Documentation. For the hns3 PMD driver,
the link can be established within 2 seconds.

Signed-off-by: Huisong Li <lihuisong@huawei.com>
Signed-off-by: Min Hu (Connor) <humin29@huawei.com>
3 years agodoc: add fields enum for modify action in flow guide
Alexander Kozyrev [Thu, 8 Apr 2021 12:32:58 +0000 (12:32 +0000)]
doc: add fields enum for modify action in flow guide

Fix the documentation about the MODIFY_FIELD flow action.
1. Include the rte_flow_field_id enumeration reference to point
to the full list of all supported Field IDs available.
2. Correct the formatting of the MODIFY_FIELD action and the
destination/source field definition tables.

Fixes: 73b68f4c54a0 ("ethdev: introduce generic modify flow action")
Cc: stable@dpdk.org
Signed-off-by: Alexander Kozyrev <akozyrev@nvidia.com>
Acked-by: Viacheslav Ovsiienko <viacheslavo@nvidia.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
3 years agonet/netvsc: fix log format
Stephen Hemminger [Thu, 8 Apr 2021 02:00:34 +0000 (19:00 -0700)]
net/netvsc: fix log format

The PMD_DRV_LOG macro in netvsc (like other drivers) adds a newline to
the log message as part of the macro expansion; therefore the
message should not have its own newline.

In a couple places, log messages were split across source lines
which can make looking them up in the source tree harder.

Fixes: a2a23a794b3a ("net/netvsc: support VF device hot add/remove")
Cc: stable@dpdk.org
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Acked-by: Long Li <longli@microsoft.com>
3 years agoapp/testpmd: support NVGRE encap as sample action
Salem Sol [Wed, 7 Apr 2021 11:50:51 +0000 (14:50 +0300)]
app/testpmd: support NVGRE encap as sample action

Add support for rte_flow_action_nvge_encap as a sample action.

The example of test-pmd command:

1.  set nvgre ip-version ... tni ... ip-src ... ip-dst ...
    set raw_encap 1 eth src... / ipv4... /...
    set sample_actions 2 nvgre / port_id id 0 / end
    flow create 0 ... pattern eth / end actions
       sample ratio 1 index 2 / raw_encap index 1 / port_id id 0...

    The flow will result in all the matched egress packets will be
    encapsulated and sent to wire, and also mirrored the packets
    using NVGRE encapsulation data and sent to wire.

Signed-off-by: Salem Sol <salems@nvidia.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
3 years agoapp/testpmd: support VXLAN encap as sample action
Salem Sol [Wed, 7 Apr 2021 11:50:14 +0000 (14:50 +0300)]
app/testpmd: support VXLAN encap as sample action

Add support for rte_flow_action_vxlan_encap as a sample action.

The example of test-pmd command:

1.  set vxlan ip-version ... vni ... udp-src ...
    set raw_encap 1 eth src.../ ipv4.../...
    set sample_actions 2 vxlan_encap / port_id id 0 / end
    flow create 0 ... pattern eth / end actions
       sample ratio 1 index 2 / raw_encap index 1 / port_id id 0...

    The flow will result in all the matched egress packets will be
    encapsulated and sent to wire, and also mirrored the packets
    using VXLAN encapsulation data and sent to wire.

Signed-off-by: Salem Sol <salems@nvidia.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
3 years agonet/mlx5: support NVGRE encap action in sampling
Salem Sol [Wed, 7 Apr 2021 11:49:38 +0000 (14:49 +0300)]
net/mlx5: support NVGRE encap action in sampling

Add support for NVGRE encap as a sample action
and validate it.

Signed-off-by: Salem Sol <salems@nvidia.com>
Acked-by: Viacheslav Ovsiienko <viacheslavo@nvidia.com>
3 years agonet/mlx5: support VXLAN encap action in sampling
Salem Sol [Wed, 7 Apr 2021 11:48:56 +0000 (14:48 +0300)]
net/mlx5: support VXLAN encap action in sampling

Add support for VXLAN encap as a sample action
and validate it.

Signed-off-by: Salem Sol <salems@nvidia.com>
Acked-by: Viacheslav Ovsiienko <viacheslavo@nvidia.com>
3 years agoapp/testpmd: store VXLAN/NVGRE encap data globally
Jiawei Wang [Wed, 7 Apr 2021 11:48:15 +0000 (14:48 +0300)]
app/testpmd: store VXLAN/NVGRE encap data globally

With the current code the VXLAN/NVGRE parsing routine
stored the configuration of the header on stack, this
might lead to overwriting the data on the stack.

Currently having VXLAN/NVGRE encap as sample actions
is done using RAW_ENCAP, for example:
1. set raw_encap 1 eth src.../ vxlan vni.../ ipv4.../ ...
   set sample_actions 0 raw_encap / port_id id 0 / end
   flow create 0 ... pattern eth / end actions
      sample ration 1 index 0 / jump group 1 / end

The goal is to utilize the rte_flow_action_vxlan_encap
and rte_flow_action_nvgre_encap for sample actions.

This patch prepares storing the external data of vxlan and
nvgre encap into global data as a pre-step to supporting
vxlan and nvgre encap as a sample actions.

Signed-off-by: Jiawei Wang <jiaweiw@nvidia.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
3 years agoethdev: validate input in EEPROM info
Chengchang Tang [Fri, 2 Apr 2021 02:58:50 +0000 (10:58 +0800)]
ethdev: validate input in EEPROM info

This patch adds validity check of input pointer in EEPROM dump API.

Fixes: 7a3f27cbf59b ("ethdev: add access to specific device info")
Cc: stable@dpdk.org
Signed-off-by: Chengchang Tang <tangchengchang@huawei.com>
Signed-off-by: Min Hu (Connor) <humin29@huawei.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
3 years agoethdev: validate input in register info
Chengchang Tang [Fri, 2 Apr 2021 02:58:49 +0000 (10:58 +0800)]
ethdev: validate input in register info

This patch adds validity check of input pointer in regs dump API.

Fixes: 7a3f27cbf59b ("ethdev: add access to specific device info")
Fixes: 936eda25e8da ("net/hns3: support dump register")
Cc: stable@dpdk.org
Signed-off-by: Chengchang Tang <tangchengchang@huawei.com>
Signed-off-by: Min Hu (Connor) <humin29@huawei.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
3 years agoethdev: validate input in module EEPROM dump
Chengchang Tang [Fri, 2 Apr 2021 02:58:48 +0000 (10:58 +0800)]
ethdev: validate input in module EEPROM dump

The validity verification of input parameters should be performed at
API layer, not in the PMD.

Fixes: 3a18c44b45df ("ethdev: add access to EEPROM")
Fixes: 40ff8b305ab8 ("net/e1000: add module EEPROM callbacks for e1000")
Fixes: f2088e785cca ("net/i40e: fix dereference before check when getting EEPROM")
Fixes: b74d0cd43e37 ("net/ixgbe: add module EEPROM callbacks for ixgbe")
Fixes: 8a6a09f853a0 ("net/mlx5: support reading module EEPROM data")
Fixes: 58f6f93c34c1 ("net/octeontx2: add module EEPROM dump")
Cc: stable@dpdk.org
Signed-off-by: Chengchang Tang <tangchengchang@huawei.com>
Signed-off-by: Min Hu (Connor) <humin29@huawei.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
3 years agonet/virtio: fix interrupt unregistering for listening socket
Ilya Maximets [Wed, 17 Mar 2021 20:25:27 +0000 (21:25 +0100)]
net/virtio: fix interrupt unregistering for listening socket

virtio_user_dev_server_reconnect() is typically called from the
interrupt context while checking the link state:

  vhost_user_update_link_state()
  --> virtio_user_dev_server_reconnect()

Under this conditions callback unregistering always fails.  This means
that listenfd is never unregistered and continue to trigger interrupts.
For example, if second client will try to connect to the same socket,
the server will receive interrupts infinitely because it will not
accept them while listen fd is readable and generates epoll events.

Fix that by moving reconfiguration of interrupts out of the
interrupt context to alarm handler.

'virtio_user_dev_delayed_handler' renamed to
'virtio_user_dev_delayed_disconnect_handler' to better reflect its
purpose.

Additionally improved error logging around interrupt management.

Fixes: bd8f50a45d0f ("net/virtio-user: support server mode")
Cc: stable@dpdk.org
Signed-off-by: Ilya Maximets <i.maximets@ovn.org>
Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
3 years agovhost: avoid IOTLB mempool allocation while IOMMU disabled
Junjie Wan [Tue, 2 Feb 2021 08:38:45 +0000 (16:38 +0800)]
vhost: avoid IOTLB mempool allocation while IOMMU disabled

If vhost device's IOMMU feature is disabled, IOTLB mempool allocation
is unnecessary.

Reported-by: Peng He <hepeng.0320@bytedance.com>
Signed-off-by: Junjie Wan <wanjunjie@bytedance.com>
Reviewed-by: Zhihong Wang <wangzhihong.wzh@bytedance.com>
Reviewed-by: Chenbo Xia <chenbo.xia@intel.com>
Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
3 years agovhost: fix initialization of async temporary header
Marvin Liu [Wed, 7 Apr 2021 03:25:16 +0000 (11:25 +0800)]
vhost: fix initialization of async temporary header

This patch fixes coverity issue in async enqueue function by adding
initialization step before using temporary virtio header.

Coverity issue: 366123
Fixes: cd6760da1076 ("vhost: introduce async enqueue for split ring")
Cc: stable@dpdk.org
Signed-off-by: Marvin Liu <yong.liu@intel.com>
Reviewed-by: Chenbo Xia <chenbo.xia@intel.com>
3 years agovhost: fix initialization of temporary header
Marvin Liu [Wed, 7 Apr 2021 03:25:15 +0000 (11:25 +0800)]
vhost: fix initialization of temporary header

This patch fixs coverity issue by adding initialization step before
using temporary virtio header.

Coverity issue: 366181
Fixes: fb3815cc614d ("vhost: handle virtually non-contiguous buffers in Rx-mrg")
Cc: stable@dpdk.org
Signed-off-by: Marvin Liu <yong.liu@intel.com>
Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
3 years agonet/bnxt: fix FW unregister log
Kalesh AP [Tue, 6 Apr 2021 06:04:03 +0000 (11:34 +0530)]
net/bnxt: fix FW unregister log

The "Unregistered with fw" message was being logged in a wrong function.
Moved it to the right place.

Fixes: a7dda7e0a00b ("net/bnxt: log port id in async events")

Signed-off-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Reviewed-by: Somnath Kotur <somnath.kotur@broadcom.com>
Reviewed-by: Ajit Khaparde <ajit.khaparde@broadcom.com>
3 years agonet/bnxt: fix configuring LRO
Kalesh AP [Fri, 2 Apr 2021 03:25:51 +0000 (08:55 +0530)]
net/bnxt: fix configuring LRO

While configuring LRO, driver should check the return value
of bnxt_hwrm_vnic_tpa_cfg() HWRM command and return error
when the FW command fails.

Fixes: 0958d8b6435d ("net/bnxt: support LRO")
Cc: stable@dpdk.org
Signed-off-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Reviewed-by: Somnath Kotur <somnath.kotur@broadcom.com>
3 years agonet/bnxt: fix double free in port start failure
Kalesh AP [Thu, 1 Apr 2021 02:53:34 +0000 (08:23 +0530)]
net/bnxt: fix double free in port start failure

During port start when bnxt_start_nic() fails, it tries to free
"intr_handle->intr_vec" but the variable is not set to NULL after that.
If port start fails, driver invokes bnxt_dev_stop() which will lead
to a double free of "intr_handle->intr_vec".

Fix it by removing the call to free "intr_handle->intr_vec" in the
bnxt_start_nic() failure path as it is anyway doing in bnxt_dev_stop().

Fixes: 9d276b439aaf ("net/bnxt: fix error handling in device start")
Cc: stable@dpdk.org
Signed-off-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Reviewed-by: Somnath Kotur <somnath.kotur@broadcom.com>
Reviewed-by: Ajit Khaparde <ajit.khaparde@broadcom.com>
3 years agonet/mlx5: fix drop action for Direct Rules/Verbs
Viacheslav Ovsiienko [Mon, 5 Apr 2021 09:59:01 +0000 (09:59 +0000)]
net/mlx5: fix drop action for Direct Rules/Verbs

There are multiple branches in rdma-core library backing
the rte flows:
  - Verbs
  - Direct Verbs (DV)
  - Direct Rules (DR)

The Verbs API always requires the specifying the queue even
if there is the drop action in the flow, though the kernel
optimizes out the actual queue usage for the flows containing
the drop action. The PMD handles the dedicated Rx queue to
provide Verbs API compatibility.

The DV/DR API does not require explicit specifying the queue
at the flow creation, but PMD still specified the dedicated
drop queue as action. It performed the packet forwarding to
the dummy queue (that was not polled at all) causing the
steering pipeline resources usage and degrading the overall
packet processing rate. For example, with inserted flow to
drop all the ingress packets the statistics reported only
15Mpps of 64B packets were received over 100Gbps line.

Since the Direct Rule API for E-Switch was introduced the
rdma-core supports the dedicated drop action, that is recognized
both for DV and DR and can be used for the entire device in
unified fashion, regardless of steering domain. The similar drop
action was introduced for E-Switch, the usage of this one can be
extended for other steering domains, not for E-Switch's one only.

This patch:
  - renames esw_drop_action to dr_drop_action to emphasize
    the global nature of the variable (not only E-Switch domain)
  - specifies this global drop action instead of dedicated
    drop queue for the DR/DV flows

Fixes: 34fa7c0268e7 ("net/mlx5: add drop action to Direct Verbs E-Switch")
Fixes: 65b3cd0dc39b ("net/mlx5: create global drop action")
Cc: stable@dpdk.org
Signed-off-by: Viacheslav Ovsiienko <viacheslavo@nvidia.com>
Acked-by: Matan Azrad <matan@nvidia.com>
3 years agocommon/mlx5: rename definition of PCI driver name
Asaf Penso [Mon, 15 Mar 2021 21:05:55 +0000 (21:05 +0000)]
common/mlx5: rename definition of PCI driver name

The current define for MLX5_DRIVER_NAME refers specially for the PCI
driver.

The define itself does not mention PCI and this is confusing.

Rename from MLX5_DRIVER_NAME to MLX5_PCI_DRIVER_NAME.

Signed-off-by: Asaf Penso <asafp@nvidia.com>
Acked-by: Viacheslav Ovsiienko <viacheslavo@nvidia.com>
3 years agocommon/mlx5: align log prefix across drivers
Asaf Penso [Mon, 15 Mar 2021 21:05:54 +0000 (21:05 +0000)]
common/mlx5: align log prefix across drivers

Some mlx5 PMDs define the log prefix as "mlx5_pmd" while others as
"pmd_mlx5".
The patch aligns all pmds to use the "mlx5_pmd" format.

Signed-off-by: Asaf Penso <asafp@nvidia.com>
Acked-by: Viacheslav Ovsiienko <viacheslavo@nvidia.com>
3 years agonet/mlx5: fix missing shared RSS hash types
Xiaoyu Min [Fri, 26 Mar 2021 05:20:21 +0000 (13:20 +0800)]
net/mlx5: fix missing shared RSS hash types

Shared RSS action create all supported RSS hash combination
in advance and lookup the right hash TIR when flow is actually
applied by comparing hash field value.

Unfortunately some hash combination is missed, for example,
UDP/TCP dest port only, L3-src-only, etc.

This patch add the missing hash combination.

In order to reduce the usage of pre-created TIRs and because
for one L3+L4 combination only one IBV hash type is possible,
for example, either IBV_RX_HASH_SRC_PORT_UDP or IBV_RX_HASH_DST_PORT_UDP
or both of them could be set so they can share same slot in
mlx5_rss_hash_fields, means only one TIR will be created.

Fixes: d2046c09aa64 ("net/mlx5: support shared action for RSS")
Cc: stable@dpdk.org
Signed-off-by: Xiaoyu Min <jackmin@nvidia.com>
Acked-by: Matan Azrad <matan@nvidia.com>
3 years agonet/mlx5: fix shared inner RSS
Xiaoyu Min [Fri, 26 Mar 2021 05:20:20 +0000 (13:20 +0800)]
net/mlx5: fix shared inner RSS

The shared RSS action use the _tunnel_ information which is derived
from flow items to decide whether need to do inner RSS or not.
However, inner RSS should be decided by RSS level (>1) in configuration
and then to create TIR with 'IBV_RX_HASH_INNER' hash bit set.

Also, for one shared RSS action there is only one set of TIRs -
outer or inner could be so the unnecessary set of TIRs are removed
in order to reduce resource.

Fixes: d2046c09aa64 ("net/mlx5: support shared action for RSS")
Cc: stable@dpdk.org
Signed-off-by: Xiaoyu Min <jackmin@nvidia.com>
Acked-by: Matan Azrad <matan@nvidia.com>
3 years agonet/ice: support VXLAN VNI field in flow director
Zhirun Yan [Thu, 1 Apr 2021 01:33:23 +0000 (09:33 +0800)]
net/ice: support VXLAN VNI field in flow director

Add support for VNI field in FDIR. Treat VXLAN flow type as
ICE_FLTR_PTYPE_NONF_IPV4_UDP_VXLAN to align with shared code. It
allows to match outer L2/L3, VNI and inner L2/L3 fields with VXLAN
pattern.
VNI takes 24 bits in VXLAN header, but uses 32 bits for matching in
shared code. The 8 bits reserved field adjacent should always be 0.

Signed-off-by: Zhirun Yan <zhirun.yan@intel.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
3 years agonet/i40e: fix flow director config after flow validate
Murphy Yang [Thu, 1 Apr 2021 03:23:32 +0000 (03:23 +0000)]
net/i40e: fix flow director config after flow validate

The configuration of FDIR input set should not be set
during flow validate. It should be set when flow create.

Fixes: fe5d0e85b713 ("net/i40e: fix flow director flex configuration")
Fixes: 15018d79f0be ("net/i40e: add FDIR support for GTP-C and GTP-U")
Cc: stable@dpdk.org
Signed-off-by: Murphy Yang <murphyx.yang@intel.com>
Acked-by: Beilei Xing <beilei.xing@intel.com>
3 years agoraw/ifpga/base: check null pointer
Wei Huang [Wed, 17 Mar 2021 08:21:36 +0000 (04:21 -0400)]
raw/ifpga/base: check null pointer

In init_sec_mgr(), pointer "hw" may be NULL, so "hw" should
be checked before dereferencing.

Coverity issue: 367483
Fixes: a05bd1b40bde ("raw/ifpga: add FPGA RSU APIs")

Signed-off-by: Wei Huang <wei.huang@intel.com>
Acked-by: Tianfei Zhang <tianfei.zhang@intel.com>
Acked-by: Rosen Xu <rosen.xu@intel.com>
3 years agoraw/ifpga/base: check file length
Wei Huang [Wed, 17 Mar 2021 08:21:35 +0000 (04:21 -0400)]
raw/ifpga/base: check file length

In fpga_update_flash(), "smgr->rsu_length" is passed to a
parameter that cannot be negative. So return value of
function "lseek" should be checked before being assigned
to "smgr->rsu_length".

Coverity issue: 367481
Fixes: a05bd1b40bde ("raw/ifpga: add FPGA RSU APIs")

Signed-off-by: Wei Huang <wei.huang@intel.com>
Acked-by: Tianfei Zhang <tianfei.zhang@intel.com>
Acked-by: Rosen Xu <rosen.xu@intel.com>
3 years agoraw/ifpga/base: check lseek failure
Wei Huang [Wed, 17 Mar 2021 08:21:34 +0000 (04:21 -0400)]
raw/ifpga/base: check lseek failure

In write_flash_image(), calling function "lseek" without checking
return value has risk. Negative return value should be handled as
an error condition.

Coverity issue: 367478
Fixes: a05bd1b40bde ("raw/ifpga: add FPGA RSU APIs")

Signed-off-by: Wei Huang <wei.huang@intel.com>
Acked-by: Tianfei Zhang <tianfei.zhang@intel.com>
Acked-by: Rosen Xu <rosen.xu@intel.com>
3 years agodoc: update recommended versions for i40e
Robin Zhang [Tue, 30 Mar 2021 08:44:23 +0000 (08:44 +0000)]
doc: update recommended versions for i40e

Kernel driver 2.13.10 is removed, so update recommended matching list
for i40e.

Cc: stable@dpdk.org
Signed-off-by: Robin Zhang <robinx.zhang@intel.com>
Acked-by: Beilei Xing <beilei.xing@intel.com>
3 years agonet/e1000: fix Rx error counter for bad length
Alvin Zhang [Thu, 1 Apr 2021 05:21:32 +0000 (13:21 +0800)]
net/e1000: fix Rx error counter for bad length

When the size of a packet in Rx channel is less than the minimum
or greater than the maximum, the packet will be simultaneously
counted by RLEC(Receive Length Error Count) and
RUC(Receive Under Size Count)/ROC(Receive Oversize Count) registers.

This patch fixes the issue of counting a length error packet twice
when counting the total number of received error packets.

Fixes: 70bdb18657da ("ethdev: add Rx error counters for missed, badcrc and badlen packets")
Cc: stable@dpdk.org
Signed-off-by: Alvin Zhang <alvinx.zhang@intel.com>
Acked-by: Haiyue Wang <haiyue.wang@intel.com>
3 years agonet/igc: fix Rx error counter for bad length
Alvin Zhang [Thu, 1 Apr 2021 05:20:43 +0000 (13:20 +0800)]
net/igc: fix Rx error counter for bad length

When the size of a packet in Rx channel is less than the minimum
or greater than the maximum, the packet will be simultaneously
counted by RLEC(Receive Length Error Count) and
RUC(Receive Under Size Count)/ROC(Receive Oversize Count) registers.

This patch fixes the issue of counting a length error packet twice
when counting the total number of received error packets.

Fixes: e6defdfddc3b ("net/igc: enable statistics")
Cc: stable@dpdk.org
Signed-off-by: Alvin Zhang <alvinx.zhang@intel.com>
Acked-by: Haiyue Wang <haiyue.wang@intel.com>
3 years agonet/ena: fix releasing Tx ring mbufs
David Harton [Tue, 6 Apr 2021 00:27:19 +0000 (20:27 -0400)]
net/ena: fix releasing Tx ring mbufs

When ena_tx_queue_release_bufs() frees the mbufs it does not clear
the mbuf pointers.  So, when the device starts and stops multiple
times it can cause the application to receive duplicate mbufs for
two different packets.  Fix the issue by clearing the mbuf pointer.

Also, while tracking down the "double free" issue the ena calls to
allocate and free mbufs in bulk were migrated to the mbuf based APIs
so the common mbuf alloc/free routines are exercised.

Fixes: 79405ee17585 ("net/ena: fix out of order completion")
Fixes: 1173fca25af9 ("ena: add polling-mode driver")
Cc: stable@dpdk.org
Signed-off-by: David Harton <dharton@cisco.com>
Acked-by: Michal Krawczyk <mk@semihalf.com>
3 years agonet/ice: disable DDP package on Windows
Pallavi Kadam [Fri, 2 Apr 2021 01:26:21 +0000 (18:26 -0700)]
net/ice: disable DDP package on Windows

Disable loading of external DDP package as it is not
supported on Windows.

Signed-off-by: Pallavi Kadam <pallavi.kadam@intel.com>
Reviewed-by: Ranjit Menon <ranjit.menon@intel.com>
Acked-by: Jie Zhou <jizh@microsoft.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
3 years agonet/ice: build on Windows
Pallavi Kadam [Fri, 2 Apr 2021 01:26:20 +0000 (18:26 -0700)]
net/ice: build on Windows

- Add Intel ice PMD support on Windows.
- Remove #include sys/ioctl header file as it is not needed.
- Replace x86intrin.h with rte_vect.h to avoid __m_prefetchw conflicting
  types.
- Replace POSIX usleep() API with rte API.
- Add a new macro for the access() API as the original function
  has been deprecated on Windows.
- Add extra cflags '-fno-asynchronous-unwind-tables'
  to avoid MinGW build error:
  Error: invalid register for .seh_savexmm
- Add documentation to support ice PMD on Windows.
  Update the release notes and features list for the same.

Signed-off-by: Pallavi Kadam <pallavi.kadam@intel.com>
Reviewed-by: Ranjit Menon <ranjit.menon@intel.com>
Acked-by: Jie Zhou <jizh@microsoft.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
3 years agocommon/iavf: build on Windows
Pallavi Kadam [Fri, 2 Apr 2021 01:26:19 +0000 (18:26 -0700)]
common/iavf: build on Windows

Enable IAVF driver to build on Windows as it is required
to build ice PMD.
Disable all other drivers from common directory.

This patch also includes fix for a macro redefinition warning
in the IAVF driver.

Signed-off-by: Pallavi Kadam <pallavi.kadam@intel.com>
Reviewed-by: Ranjit Menon <ranjit.menon@intel.com>
Acked-by: Jie Zhou <jizh@microsoft.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
3 years agonet/hns3: update HiSilicon copyright syntax
Min Hu (Connor) [Tue, 6 Apr 2021 00:57:36 +0000 (08:57 +0800)]
net/hns3: update HiSilicon copyright syntax

According to the suggestion of our legal department,
to standardize the copyright license of our code to
avoid potential copyright risks, we make a unified
modification to the "Hisilicon", which was nonstandard,
in the main modules we maintain.

We change it to "HiSilicon", which is consistent with
the terms used on the following official website:
https://www.hisilicon.com/en/terms-of-use.

Fixes: 565829db8b8f ("net/hns3: add build and doc infrastructure")
Fixes: 952ebacce4f2 ("net/hns3: support SVE Rx")
Fixes: e31f123db06b ("net/hns3: support NEON Tx")
Fixes: c09c7847d892 ("net/hns3: support traffic management")
Cc: stable@dpdk.org
Signed-off-by: Min Hu (Connor) <humin29@huawei.com>
3 years agonet/hns3: support IEEE 1588 PTP
Min Hu (Connor) [Thu, 1 Apr 2021 13:38:04 +0000 (21:38 +0800)]
net/hns3: support IEEE 1588 PTP

Add hns3 support for new ethdev APIs to enable and read IEEE1588/
802.1AS PTP timestamps.

Signed-off-by: Min Hu (Connor) <humin29@huawei.com>
3 years agonet/hns3: fix MTU config complexity
Min Hu (Connor) [Thu, 1 Apr 2021 13:38:03 +0000 (21:38 +0800)]
net/hns3: fix MTU config complexity

This patch fixed cyclomatic complexity about MTU
in device configure process.

Fixes: 1f5ca0b460cd ("net/hns3: support some device operations")
Cc: stable@dpdk.org
Signed-off-by: Min Hu (Connor) <humin29@huawei.com>
3 years agonet/igc: refine debug build option
Qi Zhang [Wed, 31 Mar 2021 09:52:54 +0000 (17:52 +0800)]
net/igc: refine debug build option

1. replace RTE_LIBRTE_IGC_DEBUG_RX with RTE_ETHDEV_DEBUG_RX.
2. replace RTE_LIBRTE_IGC_DEBUG_TX with RTE_ETHDEV_DEBUG_TX.
3. merge RTE_LIBRTE_ETHDEV_DEBUG into RTE_ETHDEV_DEBUG_TX

Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
3 years agonet/ixgbe: refine debug build option
Qi Zhang [Wed, 31 Mar 2021 09:52:53 +0000 (17:52 +0800)]
net/ixgbe: refine debug build option

1. replace RTE_LIBRTE_IXGBE_DEBUG_RX with RTE_ETHDEV_DEBUG_RX.
2. replace RTE_LIBRTE_IXGBE_DEBUG_TX with RTE_ETHDEV_DEBUG_TX.
3. merge RTE_LIBRTE_IXGBE_DEBUG_TX_FREE and RTE_LIBRTE_ETHDEV_DEBUG
   into RTE_ETHDEV_DEBUG_TX

Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
3 years agonet/ice: refine debug build option
Qi Zhang [Wed, 31 Mar 2021 09:52:52 +0000 (17:52 +0800)]
net/ice: refine debug build option

1. replace RTE_LIBRTE_ICE_DEBUG_RX with RTE_ETHDEV_DEBUG_RX.
2. replace RTE_LIBRTE_ICE_DEBUG_TX with RTE_ETHDEV_DEBUG_TX.
3. merge RTE_LIBRTE_ICE_DEBUG_TX_FREE and RTE_LIBRTE_ETHDEV_DEBUG
   into RTE_LIBRTE_DEBUG_TX

Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
3 years agonet/iavf: refine debug build option
Qi Zhang [Wed, 31 Mar 2021 09:52:51 +0000 (17:52 +0800)]
net/iavf: refine debug build option

1. replace RTE_LIBRTE_IAVF_DEBUG_RX with RTE_ETHDEV_DEBUG_RX.
2. replace RTE_LIBRTE_IAVF_DEBUG_TX with RTE_ETHDEV_DEBUG_TX.
3. merge RTE_LIBRTE_IAVF_DEBUG_TX_FREE and RTE_LIBRTE_ETHDEV_DEBUG
   into RTE_ETHDEV_DEBUG_TX

Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
3 years agonet/i40e: refine debug build option
Qi Zhang [Wed, 31 Mar 2021 09:52:50 +0000 (17:52 +0800)]
net/i40e: refine debug build option

1. replace RTE_LIBRTE_I40E_DEBUG_RX with RTE_ETHDEV_DEBUG_RX.
2. replace RTE_LIBRTE_I40E_DEBUG_TX with RTE_ETHDEV_DEBUG_TX.
3. merge RTE_LIBRTE_I40E_DEBUG_TX_FREE and RTE_LIBRTE_ETHDEV_DEBUG
   into RTE_ETHDEV_DEBUG_TX

Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
3 years agonet/e1000: refine debug build option
Qi Zhang [Wed, 31 Mar 2021 09:52:49 +0000 (17:52 +0800)]
net/e1000: refine debug build option

1. replace RTE_LIBRTE_E1000_DEBUG_RX with RTE_ETHDEV_DEBUG_RX.
2. replace RTE_LIBRTE_E1000_DEBUG_TX with RTE_ETHDEV_DEBUG_TX.
3. merge RTE_LIBRTE_E1000_DEBUG_TX_FREE and RTE_LIBRTE_ETHDEV_DEBUG
   into RTE_ETHDEV_DEBUG_TX

Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
3 years agonet/fm10k: refine debug build option
Qi Zhang [Wed, 31 Mar 2021 09:52:48 +0000 (17:52 +0800)]
net/fm10k: refine debug build option

1. replace RTE_LIBRTE_FM10K_DEBUG_RX with RTE_ETHDEV_DEBUG_RX.
2. replace RTE_LIBRTE_FM10K_DEBUG_TX with RTE_ETHDEV_DEBUG_TX.
3. merge RTE_LIBRTE_FM10K_DEBUG_TX_FREE and RTE_LIBRTE_ETHDEV_DEBUG
   into RTE_ETHDEV_DEBUG_TX

Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
3 years agoethdev: refine debug build option
Qi Zhang [Wed, 31 Mar 2021 09:52:47 +0000 (17:52 +0800)]
ethdev: refine debug build option

PMDs use RTE_LIBRTE_<PMD_NAME>_DEBUG_RX|TX as build option to wrap
data path debug code. As .config has been removed since the meson build,
It is not friendly for new DPDK users to notice those debug options.

The patch introduces below build options for data path debug, so PMD
can choose to reuse them to avoid maintain their own.

- RTE_ETHDEV_DEBUG_RX
- RTE_ETHDEV_DEBUG_TX

All the build options are documented at programming guide
"3.1 Driver Option", so users can easily find them.

The original undocumented RTE_LIBRTE_ETHDEV_DEBUG will alias to
both RTE_ETHDEV_DEBUG_RX and RTE_ETHDEV_DEBUG_TX for backward
compatibility.

Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Thomas Monjalon <thomas@monjalon.net>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
3 years agodrivers/net: remove useless autoneg capability
Thomas Monjalon [Mon, 29 Mar 2021 07:28:53 +0000 (09:28 +0200)]
drivers/net: remove useless autoneg capability

The flag ETH_LINK_SPEED_AUTONEG is 0,
so it cannot be used in a capability bitmap.

Having 0 in speed capability means all speeds are accepted.

Signed-off-by: Thomas Monjalon <thomas@monjalon.net>
Acked-by: Ajit Khaparde <ajit.khaparde@broadcom.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
3 years agodoc: add sampling and mirroring in testpmd guide
Jiawei Wang [Thu, 1 Apr 2021 02:39:56 +0000 (05:39 +0300)]
doc: add sampling and mirroring in testpmd guide

Update documentation for sample action usage in testpmd and
show the command line example.

Signed-off-by: Jiawei Wang <jiaweiw@nvidia.com>
Acked-by: Viacheslav Ovsiienko <viacheslavo@nvidia.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
3 years agomempool/cnxk: add cn10k batch dequeue
Ashwin Sekhar T K [Thu, 8 Apr 2021 09:50:49 +0000 (15:20 +0530)]
mempool/cnxk: add cn10k batch dequeue

Add the implementation for Marvell CN10k mempool batch dequeue op.

Signed-off-by: Ashwin Sekhar T K <asekhar@marvell.com>
3 years agomempool/cnxk: add cn10k get count
Ashwin Sekhar T K [Thu, 8 Apr 2021 09:50:48 +0000 (15:20 +0530)]
mempool/cnxk: add cn10k get count

Add the implementation for Marvell CN10k get count op.

Signed-off-by: Ashwin Sekhar T K <asekhar@marvell.com>
3 years agomempool/cnxk: add cn10k batch enqueue
Ashwin Sekhar T K [Thu, 8 Apr 2021 09:50:47 +0000 (15:20 +0530)]
mempool/cnxk: add cn10k batch enqueue

Add the implementation for Marvell CN10k mempool batch enqueue op.

Signed-off-by: Ashwin Sekhar T K <asekhar@marvell.com>
3 years agomempool/cnxk: add batch operation init
Ashwin Sekhar T K [Thu, 8 Apr 2021 09:50:46 +0000 (15:20 +0530)]
mempool/cnxk: add batch operation init

Marvell CN10k mempool supports batch enqueue/dequeue which can
dequeue up to 512 pointers and enqueue up to 15 pointers using
a single instruction.

These batch operations require a DMA memory to enqueue/dequeue
pointers. This patch adds the initialization of this DMA memory.

Signed-off-by: Ashwin Sekhar T K <asekhar@marvell.com>
3 years agomempool/cnxk: add cn10k mempool operations
Ashwin Sekhar T K [Thu, 8 Apr 2021 09:50:45 +0000 (15:20 +0530)]
mempool/cnxk: add cn10k mempool operations

Add Marvell CN10k mempool ops and implement CN10k mempool alloc.

CN10k has 64 bytes L1D cache line size. Hence the CN10k mempool
alloc does not make the element size an odd multiple L1D cache
line size as NPA requires the element sizes to be multiples of
128 bytes.

Signed-off-by: Ashwin Sekhar T K <asekhar@marvell.com>
3 years agomempool/cnxk: add cn9k optimized enqueue/dequeue
Ashwin Sekhar T K [Thu, 8 Apr 2021 09:50:44 +0000 (15:20 +0530)]
mempool/cnxk: add cn9k optimized enqueue/dequeue

Add Marvell CN9k mempool enqueue/dequeue. Marvell CN9k
supports burst dequeue which allows to dequeue up to 32
pointers using pipelined casp instructions.

Signed-off-by: Pavan Nikhilesh <pbhagavatula@marvell.com>
Signed-off-by: Ashwin Sekhar T K <asekhar@marvell.com>
3 years agomempool/cnxk: add cn9k mempool operations
Ashwin Sekhar T K [Thu, 8 Apr 2021 09:50:43 +0000 (15:20 +0530)]
mempool/cnxk: add cn9k mempool operations

Add Marvell CN9k mempool ops and implement CN9k mempool
alloc which makes sure that the element size always occupy
odd number of cachelines to ensure even distribution among
of elements among L1D cache sets.

Signed-off-by: Pavan Nikhilesh <pbhagavatula@marvell.com>
Signed-off-by: Ashwin Sekhar T K <asekhar@marvell.com>
3 years agomempool/cnxk: register plt init callback
Ashwin Sekhar T K [Thu, 8 Apr 2021 09:50:42 +0000 (15:20 +0530)]
mempool/cnxk: register plt init callback

Register the CNXk mempool plt init callback which will set the
appropriate mempool ops to be used for the platform.

Signed-off-by: Ashwin Sekhar T K <asekhar@marvell.com>
3 years agomempool/cnxk: add generic operations
Ashwin Sekhar T K [Thu, 8 Apr 2021 09:50:41 +0000 (15:20 +0530)]
mempool/cnxk: add generic operations

Add generic CNXk mempool ops which will enqueue/dequeue
from pool one element at a time.

Signed-off-by: Pavan Nikhilesh <pbhagavatula@marvell.com>
Signed-off-by: Ashwin Sekhar T K <asekhar@marvell.com>
3 years agomempool/cnxk: add device probe/remove
Ashwin Sekhar T K [Thu, 8 Apr 2021 09:50:40 +0000 (15:20 +0530)]
mempool/cnxk: add device probe/remove

Add the implementation for CNXk mempool device
probe and remove.

Signed-off-by: Pavan Nikhilesh <pbhagavatula@marvell.com>
Signed-off-by: Ashwin Sekhar T K <asekhar@marvell.com>
3 years agomempool/cnxk: add build infra and doc
Ashwin Sekhar T K [Thu, 8 Apr 2021 09:50:39 +0000 (15:20 +0530)]
mempool/cnxk: add build infra and doc

Add the meson based build infrastructure for Marvell
CNXK mempool driver along with stub implementations
for mempool device probe.

Also add Marvell CNXK mempool base documentation.

Signed-off-by: Pavan Nikhilesh <pbhagavatula@marvell.com>
Signed-off-by: Jerin Jacob <jerinj@marvell.com>
Signed-off-by: Nithin Dabilpuram <ndabilpuram@marvell.com>
Signed-off-by: Ashwin Sekhar T K <asekhar@marvell.com>
3 years agocommon/cnxk: support RSS action in NPC rule
Satheesh Paul [Tue, 6 Apr 2021 14:41:44 +0000 (20:11 +0530)]
common/cnxk: support RSS action in NPC rule

Added support for allocating RSS group and setting
it as action of an NPC rule.

Signed-off-by: Satheesh Paul <psatheesh@marvell.com>
3 years agocommon/cnxk: support TIM IRQ
Pavan Nikhilesh [Tue, 6 Apr 2021 14:41:43 +0000 (20:11 +0530)]
common/cnxk: support TIM IRQ

Add TIM LF IRQ register and un-register functions.

Signed-off-by: Pavan Nikhilesh <pbhagavatula@marvell.com>
Acked-by: Nithin Dabilpuram <ndabilpuram@marvell.com>
3 years agocommon/cnxk: support TIM device
Pavan Nikhilesh [Tue, 6 Apr 2021 14:41:42 +0000 (20:11 +0530)]
common/cnxk: support TIM device

Add TIM device init, fini which are used to attach TIM LF
resources to the RVU PF/VF and TIM LF alloc and free.

Signed-off-by: Pavan Nikhilesh <pbhagavatula@marvell.com>
Acked-by: Nithin Dabilpuram <ndabilpuram@marvell.com>
3 years agocommon/cnxk: support SSO debug
Pavan Nikhilesh [Tue, 6 Apr 2021 14:41:41 +0000 (20:11 +0530)]
common/cnxk: support SSO debug

Add sso debug dump support. This dumps all SSO LF register values
to a given file handle.

Signed-off-by: Pavan Nikhilesh <pbhagavatula@marvell.com>
Acked-by: Nithin Dabilpuram <ndabilpuram@marvell.com>
3 years agocommon/cnxk: support SSO IRQ
Pavan Nikhilesh [Tue, 6 Apr 2021 14:41:40 +0000 (20:11 +0530)]
common/cnxk: support SSO IRQ

Add support to registering and un-registering SSO HWS and
HWGRP IRQs.

Signed-off-by: Pavan Nikhilesh <pbhagavatula@marvell.com>
Acked-by: Nithin Dabilpuram <ndabilpuram@marvell.com>
3 years agocommon/cnxk: add SSO HWGRP interface
Pavan Nikhilesh [Tue, 6 Apr 2021 14:41:39 +0000 (20:11 +0530)]
common/cnxk: add SSO HWGRP interface

Add SSO HWGRP interface for configuring XAQ pool, setting priority
and internal HW buffer limits for each HWGRP.

Signed-off-by: Pavan Nikhilesh <pbhagavatula@marvell.com>
Acked-by: Nithin Dabilpuram <ndabilpuram@marvell.com>
3 years agocommon/cnxk: add SSO HWS interface
Pavan Nikhilesh [Tue, 6 Apr 2021 14:41:38 +0000 (20:11 +0530)]
common/cnxk: add SSO HWS interface

Add SSO HWS interface for setting/unsetting links, retrieving
base address and nanoseconds to getwork timeout.

Signed-off-by: Pavan Nikhilesh <pbhagavatula@marvell.com>
Acked-by: Nithin Dabilpuram <ndabilpuram@marvell.com>
3 years agocommon/cnxk: support SSO device
Pavan Nikhilesh [Tue, 6 Apr 2021 14:41:37 +0000 (20:11 +0530)]
common/cnxk: support SSO device

Add SSO device init and fini which attach SSO LF resources to the
RVU PF/VF and SSO HWS and HWGRP LFs alloc, free.

Signed-off-by: Pavan Nikhilesh <pbhagavatula@marvell.com>
Acked-by: Nithin Dabilpuram <ndabilpuram@marvell.com>
3 years agocommon/cnxk: add NPC init and fini
Kiran Kumar K [Tue, 6 Apr 2021 14:41:36 +0000 (20:11 +0530)]
common/cnxk: add NPC init and fini

Adding support initialize and fini the npc. Further, adding APIs to
create and destroy the npc rules.

Signed-off-by: Kiran Kumar K <kirankumark@marvell.com>
3 years agocommon/cnxk: add NPC parsing API
Kiran Kumar K [Tue, 6 Apr 2021 14:41:35 +0000 (20:11 +0530)]
common/cnxk: add NPC parsing API

Adding npc parsing API support to parse different patterns and actions.
Based on the pattern and actions ltype values will be chosen and
mcam data will be configured at perticular offsets.

Signed-off-by: Kiran Kumar K <kirankumark@marvell.com>
3 years agocommon/cnxk: add mcam utility API
Kiran Kumar K [Tue, 6 Apr 2021 14:41:34 +0000 (20:11 +0530)]
common/cnxk: add mcam utility API

Adding mcam utility functions like reading KEX and reserving and writing
mcam rules.

Signed-off-by: Kiran Kumar K <kirankumark@marvell.com>
3 years agocommon/cnxk: add NPC helper API
Kiran Kumar K [Tue, 6 Apr 2021 14:41:33 +0000 (20:11 +0530)]
common/cnxk: add NPC helper API

Adding NPC helper APIs to manage MCAM like pre allocating the mcam,
configuring the rules, shifting mcam rules and preparing the data for
mcam based on KEX.

Signed-off-by: Kiran Kumar K <kirankumark@marvell.com>
3 years agocommon/cnxk: support NPC
Kiran Kumar K [Tue, 6 Apr 2021 14:41:32 +0000 (20:11 +0530)]
common/cnxk: support NPC

Adding initial support for programming NPC. NPC is Network Parser
and CAM unit that provides Rx and Tx packet parsing and packet
manipulation functionality on Marvell CN9K and CN10K SoC's. It is
mapped to RTE Flow in DPDK.

Signed-off-by: Kiran Kumar K <kirankumark@marvell.com>
3 years agocommon/cnxk: support NIX TM debug and misc utils
Nithin Dabilpuram [Tue, 6 Apr 2021 14:41:31 +0000 (20:11 +0530)]
common/cnxk: support NIX TM debug and misc utils

Add support to dump TM HW registers and hierarchy on error.
This patch also adds support for misc utils such as API to
query TM HW resource availability, resource pre-allocation
and static priority support on root node.

Signed-off-by: Nithin Dabilpuram <ndabilpuram@marvell.com>
3 years agocommon/cnxk: support NIX TM dynamic update
Nithin Dabilpuram [Tue, 6 Apr 2021 14:41:30 +0000 (20:11 +0530)]
common/cnxk: support NIX TM dynamic update

Add support for dynamic node update of shaper profile,
RR quantum and also support to suspend or resume an active
TM node.

Signed-off-by: Nithin Dabilpuram <ndabilpuram@marvell.com>
3 years agocommon/cnxk: support NIX TM internal hierarchy
Nithin Dabilpuram [Tue, 6 Apr 2021 14:41:29 +0000 (20:11 +0530)]
common/cnxk: support NIX TM internal hierarchy

Add support to create internal TM default hierarchy and ratelimit
hierarchy and API to ratelimit SQ to a given rate. This will be
used by cnxk ethdev driver's tx queue ratelimit op.

Signed-off-by: Nithin Dabilpuram <ndabilpuram@marvell.com>
3 years agocommon/cnxk: add NIX TM hierarchy enable/disable
Nithin Dabilpuram [Tue, 6 Apr 2021 14:41:28 +0000 (20:11 +0530)]
common/cnxk: add NIX TM hierarchy enable/disable

Add support to enable or disable hierarchy along with
allocating node HW resources such as shapers and schedulers
and configuring them to match the user created or default
hierarchy.

Signed-off-by: Nithin Dabilpuram <ndabilpuram@marvell.com>
3 years agocommon/cnxk: add NIX TM helper to alloc/free resource
Nithin Dabilpuram [Tue, 6 Apr 2021 14:41:27 +0000 (20:11 +0530)]
common/cnxk: add NIX TM helper to alloc/free resource

Add TM helper API to estimate, alloc, assign, and free resources
for a NIX LF / ethdev.

Signed-off-by: Nithin Dabilpuram <ndabilpuram@marvell.com>
3 years agocommon/cnxk: support NIX TM shaper profile
Satha Rao [Tue, 6 Apr 2021 14:41:26 +0000 (20:11 +0530)]
common/cnxk: support NIX TM shaper profile

Add support to add/delete/update shaper profile for
a given NIX. Also add support to walk through existing
shaper profiles.

Signed-off-by: Nithin Dabilpuram <ndabilpuram@marvell.com>
Signed-off-by: Satha Rao <skoteshwar@marvell.com>
3 years agocommon/cnxk: support add/delete NIX TM node
Nithin Dabilpuram [Tue, 6 Apr 2021 14:41:25 +0000 (20:11 +0530)]
common/cnxk: support add/delete NIX TM node

Add support to add/delete nodes in a hierarchy.
This patch also adds misc utils to get node name,
walk through nodes etc.

Signed-off-by: Nithin Dabilpuram <ndabilpuram@marvell.com>
Signed-off-by: Satha Rao <skoteshwar@marvell.com>
3 years agocommon/cnxk: support NIX traffic management
Nithin Dabilpuram [Tue, 6 Apr 2021 14:41:24 +0000 (20:11 +0530)]
common/cnxk: support NIX traffic management

Add nix traffic management base support to init/fini node, shaper profile
and topology, setup SQ for a given user hierarchy or default internal
hierarchy.

Signed-off-by: Nithin Dabilpuram <ndabilpuram@marvell.com>
3 years agocommon/cnxk: support NIX LSO and misc utils
Sunil Kumar Kori [Tue, 6 Apr 2021 14:41:23 +0000 (20:11 +0530)]
common/cnxk: support NIX LSO and misc utils

Add support to create LSO formats for TCP segmentation offload
for IPv4/IPv6, tunnel and non-tunnel protocols. Tunnel protocol
support is for GRE and UDP based tunnel protocols.

This patch also adds other helper API to retrieve eeprom info
and configure Rx for different switch headers.

Signed-off-by: Sunil Kumar Kori <skori@marvell.com>
Acked-by: Nithin Dabilpuram <ndabilpuram@marvell.com>
3 years agocommon/cnxk: support NIX flow control
Sunil Kumar Kori [Tue, 6 Apr 2021 14:41:22 +0000 (20:11 +0530)]
common/cnxk: support NIX flow control

Add support to enable/disable Rx/Tx flow control and pause
frame configuration on NIX.

Signed-off-by: Sunil Kumar Kori <skori@marvell.com>
Acked-by: Nithin Dabilpuram <ndabilpuram@marvell.com>