Introduce offsets of firmware registers holding a number of EMP resets.
Implement offsets as a preprocessor's constants.
Required by drivers to read a number of EMP resets reported by FW.
Signed-off-by: Piotr Kwapulinski <piotr.kwapulinski@intel.com>
Signed-off-by: Xiaolong Ye <xiaolong.ye@intel.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Beilei Xing <beilei.xing@intel.com>
The previous code had the LED code wrapped such that, it was
static to the file and not usable outside of it. It is now available.
Signed-off-by: Mateusz Rusinski <mateusz.rusinski@intel.com>
Signed-off-by: Xiaolong Ye <xiaolong.ye@intel.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Beilei Xing <beilei.xing@intel.com>
There was no time duration statistics for LPI (Low Power Idle)
in EEE (Energy-Efficient Ethernet).
Added new procedure to get duration values from FW.
Otherwise there is no available procedure to get tx_lpi_duration
and rx_lpi_duration values.
Signed-off-by: Jaroslaw Gawin <jaroslawx.gawin@intel.com>
Signed-off-by: Xiaolong Ye <xiaolong.ye@intel.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Beilei Xing <beilei.xing@intel.com>
The X722 FW API version 1.9 adds support for accessing PHY
registers with Admin Queue Command. This enables reading
EEPROM data from (Q)SFP+ transceivers, what was previously
possible only on X710 devices.
Signed-off-by: Adam Ludkiewicz <adam.ludkiewicz@intel.com>
Signed-off-by: Xiaolong Ye <xiaolong.ye@intel.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Beilei Xing <beilei.xing@intel.com>
The result of the check is always FALSE and the code within "if"
is never executed.
Signed-off-by: Dzmitry Sautsa <dzmitryx.sautsa@intel.com>
Signed-off-by: Xiaolong Ye <xiaolong.ye@intel.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Beilei Xing <beilei.xing@intel.com>
Add defines for creating Flow Director flows as defined in datasheet
section 7.1.5.4 for field vectors.
Signed-off-by: Doug Dziggel <douglas.a.dziggel@intel.com>
Signed-off-by: Xiaolong Ye <xiaolong.ye@intel.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Beilei Xing <beilei.xing@intel.com>
Fix display of FEC settings for ethtool.
This patch change variable 'phy.link_info.req_fec_info' sent to ethtool.
Without this patch wrong FEC settings can be shown.
Fixes: 1216fb9f0c ("net/i40e/base: store the requested FEC information")
Signed-off-by: Jaroslaw Gawin <jaroslawx.gawin@intel.com>
Signed-off-by: Xiaolong Ye <xiaolong.ye@intel.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Beilei Xing <beilei.xing@intel.com>
Mark bits 0xD through 0xF for the command flags of a cloud filter as
reserved. These bits are not yet defined and are considered as reserved
in the data sheet.
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: Xiaolong Ye <xiaolong.ye@intel.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Beilei Xing <beilei.xing@intel.com>
Fixed a bug where driver was breaking out of the loop and
reporting an error without retrying first.
Fixes: 466eec7d6b ("net/i40e/base: retry AQC to overcome IRCRead hangs")
Signed-off-by: Marcin Formela <marcin.formela@intel.com>
Signed-off-by: Xiaolong Ye <xiaolong.ye@intel.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Beilei Xing <beilei.xing@intel.com>
Make i40e_set_mac_type() public. i40e driver requires
i40e_set_mac_type() to be public. It is required for recovery mode
handling. Without this patch recovery mode could not be detected at
probe() function.
Signed-off-by: Piotr Kwapulinski <piotr.kwapulinski@intel.com>
Signed-off-by: Xiaolong Ye <xiaolong.ye@intel.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Beilei Xing <beilei.xing@intel.com>
This patch adds a function to read NVM module data and uses it to
read current LLDP agent configuration from NVM API version 1.8.
Signed-off-by: Sylwia Wnuczko <sylwia.wnuczko@intel.com>
Signed-off-by: Xiaolong Ye <xiaolong.ye@intel.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Beilei Xing <beilei.xing@intel.com>
Update FW API version to 1.9.
Signed-off-by: Piotr Azarewicz <piotr.azarewicz@intel.com>
Signed-off-by: Xiaolong Ye <xiaolong.ye@intel.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Beilei Xing <beilei.xing@intel.com>
Function check_recovery_mode had wrong if statement. Now we check proper
FWS1B register values, which are responsible for the recovery mode.
Recovery mode has 6 values in total. That's why we need 6 different
flags. Now in if statement we recognize type of mac and register value.
Without those changes driver could show wrong state.
Signed-off-by: Adrian Podlawski <adrian.podlawski@intel.com>
Signed-off-by: Xiaolong Ye <xiaolong.ye@intel.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Beilei Xing <beilei.xing@intel.com>
This patch adds "drop mode" parameter to set mac config AQ command.
This bit controls the behavior when a no-drop packet is blocking a TC
queue.
0 – The PF driver is notified.
1 – The blocking packet is dropped and then the PF driver is notified.
Signed-off-by: Sylwia Wnuczko <sylwia.wnuczko@intel.com>
Signed-off-by: Xiaolong Ye <xiaolong.ye@intel.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Beilei Xing <beilei.xing@intel.com>
Currently FW use MDIO I/F number corresponded with current PF for PHY
access. This code allow to specify used MDIO I/F number.
Signed-off-by: Piotr Azarewicz <piotr.azarewicz@intel.com>
Signed-off-by: Xiaolong Ye <xiaolong.ye@intel.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Beilei Xing <beilei.xing@intel.com>
The existing driver allows setting the number of TX descriptors
to the value that is indivisible by 32. This is not properly
supported by x710 hardware. The patch limits the number of TX
descriptors to the whole value of 32.
Fixes: 8db9e2a1b2 ("i40e: base driver")
Cc: stable@dpdk.org
Signed-off-by: Doug Dziggel <douglas.a.dziggel@intel.com>
Signed-off-by: Dariusz Chaberski <dariuszx.chaberski@intel.com>
Signed-off-by: Xiaolong Ye <xiaolong.ye@intel.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Beilei Xing <beilei.xing@intel.com>
Add a few new status codes and rename a few to make them more
consistent. Error code are mapped to similar values as in
i40e_status.h, so as to be compatible with older VF drivers not using
this status enum.
Signed-off-by: Mitch Williams <mitch.a.williams@intel.com>
Signed-off-by: Xiaolong Ye <xiaolong.ye@intel.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Beilei Xing <beilei.xing@intel.com>
The upstream virtchnl.h has a few minor style differences to what is
out-of-tree, and there is no real reason we should prefer the current
style over whats upstream.
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: Xiaolong Ye <xiaolong.ye@intel.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Beilei Xing <beilei.xing@intel.com>
This change introduces new function i40e_get_lpi_counters() reading
Low Power Idle (LPI) mode counters from Energy Efficient Ethernet (EEE)
statistics. Since reading EEE statistics requires running DNL script,
function i40e_aq_run_phy_activity() able to run it, was implemented.
i40e_lpi_stat_update() was introduced as helper function for retrieving
LPI counters' values relative to given offsets.
This change also fixes order of fields in struct
i40e_aqc_run_phy_activity and introduces union in the struct
providing more descriptive names of fields depending on usage
(command or response).
Signed-off-by: Piotr Pietruszewski <piotr.pietruszewski@intel.com>
Signed-off-by: Xiaolong Ye <xiaolong.ye@intel.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Beilei Xing <beilei.xing@intel.com>
Fix for missing "Supported link modes" and "Advertised link modes"
info in ethtool after changed speed on X722 devices with BASE-T PHY
with FW API version >= 1.7.
The same FW API version on X710 and X722 does not mean the same
feature set so the change was needed as mac type of the device
should also be checked instead of FW API version only.
Fixes: e8228f1a16 ("net/i40e/base: report supported link modes")
Signed-off-by: Martyna Szapar <martyna.szapar@intel.com>
Signed-off-by: Xiaolong Ye <xiaolong.ye@intel.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Beilei Xing <beilei.xing@intel.com>
When external PHY is used, MAC register may not reflect actual
state of LPI. Add function reading it directly from PHY or MAC,
depending on what is supported by the device.
Signed-off-by: Krzysztof Galazka <krzysztof.galazka@intel.com>
Signed-off-by: Piotr Pietruszewski <piotr.pietruszewski@intel.com>
Signed-off-by: Xiaolong Ye <xiaolong.ye@intel.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Beilei Xing <beilei.xing@intel.com>
This change adds i40e_enable_eee() function controlling advertisement
of Energy Efficient Ethernet mode (EEE).
Signed-off-by: Piotr Pietruszewski <piotr.pietruszewski@intel.com>
Signed-off-by: Xiaolong Ye <xiaolong.ye@intel.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Beilei Xing <beilei.xing@intel.com>
This change introduces i40e_get_fw_lldp_status() function capable of
reporting status of FW Link Layer Discovery Protocol (LLDP) agent.
Since reading LLDP configuration from NVM only gives information what
is the default state of FW LLDP agent after POR, this change introduces
more reliable method for checking if agent is enabled.
Current state of FW LLDP agent may be different if user disabled the
agent, so i40e_get_fw_lldp_status() uses LLDP MIB checking to determine
status of the agent.
Signed-off-by: Piotr Pietruszewski <piotr.pietruszewski@intel.com>
Signed-off-by: Xiaolong Ye <xiaolong.ye@intel.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Beilei Xing <beilei.xing@intel.com>
This patch makes it possible to log only AQ descriptors, without the
entire AQ message buffers being dumped too. It should greatly reduce
kernel log size in cases where a full AQ dump is not needed.
Selection is made by setting flags in hw->debug_mask.
Additionally, some debug messages that preceded an AQ dump have been
moved to I40E_DEBUG_AQ_COMMAND class, which seems more appropriate.
Signed-off-by: Doug Dziggel <douglas.a.dziggel@intel.com>
Signed-off-by: Robert Konklewski <robertx.konklewski@intel.com>
Signed-off-by: Xiaolong Ye <xiaolong.ye@intel.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Beilei Xing <beilei.xing@intel.com>
Adding bit flags to enable/disable EEE capability for 2.5GBase-T and
5GBase-T PHY types as well as 'Set autonomous EEE for relevant enabled
PHY types' flag.
Signed-off-by: Doug Dziggel <douglas.a.dziggel@intel.com>
Signed-off-by: Michal Litwicki <michalx.litwicki@intel.com>
Signed-off-by: Xiaolong Ye <xiaolong.ye@intel.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Beilei Xing <beilei.xing@intel.com>
Some features were introduced in different FW API version on XL710 and
X722 MACs. Others are available only on specific MAC type. Make sure
that they are properly assigned. Also fix the style issues reported by
current check-patch.
Signed-off-by: Krzysztof Galazka <krzysztof.galazka@intel.com>
Signed-off-by: Xiaolong Ye <xiaolong.ye@intel.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Beilei Xing <beilei.xing@intel.com>
New device ids are created to support SFP+ and backplane connections.
Signed-off-by: Piotr Azarewicz <piotr.azarewicz@intel.com>
Signed-off-by: Xiaolong Ye <xiaolong.ye@intel.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Beilei Xing <beilei.xing@intel.com>
This code implements changes necessary for LLDP Agent support.
1. Modified i40e_aq_start_lldp and i40e_aq_stop_lldp. Now Stop and Start
can also be persistent across power cycles.
2. Added new function i40e_aq_restore_lldp which restores factory
setting for LLDP Agent or gets its status.
Signed-off-by: Jaroslaw Ilgiewicz <jaroslaw.ilgiewicz@intel.com>
Signed-off-by: Xiaolong Ye <xiaolong.ye@intel.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Beilei Xing <beilei.xing@intel.com>
This patch changes an error code for an admin queue head overrun to use
I40E_ERR_ADMIN_QUEUE_FULL instead of I40E_ERR_QUEUE_EMPTY.
Fixes: 8db9e2a1b2 ("i40e: base driver")
Cc: stable@dpdk.org
Signed-off-by: Carolyn Wyborny <carolyn.wyborny@intel.com>
Signed-off-by: Xiaolong Ye <xiaolong.ye@intel.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Beilei Xing <beilei.xing@intel.com>
There is a need to enable MIB change event, not at the same time as
init_dcb. This patch will serve this requirement.
Modify the i40e_init_dcb to return the correct error when LLDP or DCBX
is not in operational state.
Signed-off-by: Chinh T Cao <chinh.t.cao@intel.com>
Signed-off-by: Xiaolong Ye <xiaolong.ye@intel.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Beilei Xing <beilei.xing@intel.com>
The high 32-bits were being set incorrectly in the 'Set Local LLDP MIB'
AQ command (0x0A08). Change it to use the right macro to get the correct
bits.
Fixes: 1fa6324ad3 ("i40e/base: add new interfaces")
Cc: stable@dpdk.org
Signed-off-by: Piotr Azarewicz <piotr.azarewicz@intel.com>
Signed-off-by: Xiaolong Ye <xiaolong.ye@intel.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Beilei Xing <beilei.xing@intel.com>
For historical reasons, we allowed 3 VSIs per VF, but never used more
than one. Now with ADq, we can use up to 4 VSIs per VF, so change this
value to match.
Signed-off-by: Mitch Williams <mitch.a.williams@intel.com>
Signed-off-by: Xiaolong Ye <xiaolong.ye@intel.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Beilei Xing <beilei.xing@intel.com>
Extend NVM Update API to support reporting of features
available for the tools.
This change is needed by NVM Update to determine if driver
supports changing NVM layout from structured to flat.
Signed-off-by: Piotr Pietruszewski <piotr.pietruszewski@intel.com>
Signed-off-by: Krzysztof Galazka <krzysztof.galazka@intel.com>
Signed-off-by: Xiaolong Ye <xiaolong.ye@intel.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Beilei Xing <beilei.xing@intel.com>
Setting up supported ptypes using testpmd command is failing
because supported_ptypes_get callback will never return ptypes
supported, as NIX_RX_OFFLOAD_PTYPE_F bit in rx_offload_flags
is zero by default in testpmd.
Fixes: d2706e15e6 ("net/octeontx2: support reduced set of packet types")
Cc: stable@dpdk.org
Signed-off-by: Harman Kalra <hkalra@marvell.com>
Acked-by: Jerin Jacob <jerinj@marvell.com>
Replace 'typedef int bool' with 'stdbool.h' to avoid possible
multiple definitions of 'bool'.
(Not sure if the previous code is checking for true/false condition.
Recommend careful review on this patch.)
Signed-off-by: Dharmik Thakkar <dharmik.thakkar@arm.com>
Reviewed-by: Phil Yang <phil.yang@arm.com>
Reviewed-by: Ruifeng Wang <ruifeng.wang@arm.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
Replace 'typedef int bool' with 'stdbool.h' to avoid possible
multiple definitions of 'bool'.
Signed-off-by: Dharmik Thakkar <dharmik.thakkar@arm.com>
Reviewed-by: Phil Yang <phil.yang@arm.com>
Reviewed-by: Ruifeng Wang <ruifeng.wang@arm.com>
Acked-by: Xiao Wang <xiao.w.wang@intel.com>
Replace 'typedef int bool' with 'stdbool.h' to avoid possible
multiple definitions of 'bool'.
Signed-off-by: Dharmik Thakkar <dharmik.thakkar@arm.com>
Reviewed-by: Phil Yang <phil.yang@arm.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
Replace 'typedef int bool' with 'stdbool.h' to avoid possible
multiple definitions of 'bool'.
Signed-off-by: Dharmik Thakkar <dharmik.thakkar@arm.com>
Reviewed-by: Phil Yang <phil.yang@arm.com>
Reviewed-by: Ruifeng Wang <ruifeng.wang@arm.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
Replace 'typedef int bool' with 'stdbool.h' to avoid possible
multiple definitions of 'bool'.
Remove 'typedef char Bool' and use 'bool' instead.
Signed-off-by: Dharmik Thakkar <dharmik.thakkar@arm.com>
Reviewed-by: Phil Yang <phil.yang@arm.com>
Reviewed-by: Ruifeng Wang <ruifeng.wang@arm.com>
Acked-by: Yong Wang <yongwang@vmware.com>
Replace 'typedef int bool' with 'stdbool.h' to avoid possible
multiple definitions of 'bool'.
Signed-off-by: Dharmik Thakkar <dharmik.thakkar@arm.com>
Reviewed-by: Phil Yang <phil.yang@arm.com>
Reviewed-by: Ruifeng Wang <ruifeng.wang@arm.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
Compilation issue arises due to multiple definitions of 'bool'
in 'ixgbe_ethdev.h'.
Error:
'/dpdk/drivers/net/ixgbe/ixgbe_ethdev.c: In function
‘ixgbe_dev_setup_link_alarm_handler’:
/dpdk/drivers/net/ixgbe/ixgbe_ethdev.c:4075:43:
error: passing argument 3 of ‘ixgbe_get_link_capabilities’ from
incompatible pointer type [-Werror=incompatible-pointer-types]
ixgbe_get_link_capabilities(hw, &speed, &autoneg);
^
In file included from /dpdk/drivers/net/ixgbe/ixgbe_ethdev.c:41:0:
/dpdk/drivers/net/ixgbe/base/ixgbe_api.h:63:5: note: expected
‘bool * {aka int *}’ but argument is of type ‘_Bool *’'
Signed-off-by: Dharmik Thakkar <dharmik.thakkar@arm.com>
Reviewed-by: Phil Yang <phil.yang@arm.com>
Reviewed-by: Gavin Hu <gavin.hu@arm.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
Use scalar loads instead of vector loads for fields
that don't need any vector operations.
Signed-off-by: Andrew Pinski <apinski@marvell.com>
Signed-off-by: Jerin Jacob <jerinj@marvell.com>
Signed-off-by: Nithin Dabilpuram <ndabilpuram@marvell.com>
Returning -ENOTSUP only in case loopback mode is enabled and
device is VF or SDP.
Fixes: c2c0aa75cd ("net/octeontx2: fix loopback config return for VF")
Cc: stable@dpdk.org
Signed-off-by: Harman Kalra <hkalra@marvell.com>
Acked-by: Jerin Jacob <jerinj@marvell.com>
Valgrind complains that virtio_user is calling close(-1).
Fix this by adding check in virtio that is similar to existing code.
Fixes: 37a7eb2ae8 ("net/virtio-user: add device emulation layer")
Cc: stable@dpdk.org
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Reviewed-by: Tiwei Bie <tiwei.bie@intel.com>
The function eth_dev_vhost_create() could return errors,
the return value need to be checked.
Fixes: ee584e9710 ("vhost: add driver on top of the library")
Cc: stable@dpdk.org
Signed-off-by: Yunjian Wang <wangyunjian@huawei.com>
Reviewed-by: Tiwei Bie <tiwei.bie@intel.com>
Function kick_tx() has built-in detection on NEED_WAKEUP flag, so just
call it directly, like elsewhere in the driver.
Fixes: d8a210774e ("net/af_xdp: support unaligned umem chunks")
Cc: stable@dpdk.org
Signed-off-by: Xiao Wang <xiao.w.wang@intel.com>
Tested-by: Ciara Loftus <ciara.loftus@intel.com>
Implements eth dev ops xstats_get, xstats_reset, xstats_get_names,
xstats_get_names_by_id, xstats_get_by_id
Signed-off-by: Chandu Babu N <chandu@amd.com>
Acked-by: Ravi Kumar <ravi1.kumar@amd.com>
Allow the data in the first buffer to be shifted by `pkt_offset` after
the header room. The offset value is provided by `ena_rx_ctx`.
As part of this update, the version of the ENA was upgraded to v2.0.3.
Signed-off-by: Maciej Bielski <mba@semihalf.com>
Acked-by: Michal Krawczyk <mk@semihalf.com>
This version of the HAL allows to use the latest HW features, like
rx offsets.
Driver was adjusted to the new version to fix the build.
Signed-off-by: Michal Krawczyk <mk@semihalf.com>
Signed-off-by: Maciej Bielski <mba@semihalf.com>
Add support for 1/10G devices.
Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>
ice_add_mac_rule allow user to add rule to port based on
hw->port_info->lport number. Function in some case should
allow user to add filter rule on different port, write
another function which implemented that behaviour.
The same situation is which removing mac function.
Add new API function which allow user to choose port on which
rule going to be added. Leave add mac rule function that always
add rule on hw->port_info->lport to avoid changes in components
which don't need to choose different port. Also add function to
remove rule from specific port.
Alloc more switch_info structs to track separately rules for each
port. Choose switch_info struct basing on logic port number
because in FW added rules are connected with port.
Signed-off-by: Michal Swiatkowski <michal.swiatkowski@intel.com>
Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>
Change internal implementation of how FD filter programming desc
is prepared. This is to minimize the amount of code needed to prep
the FD filter programming desc (avoid memcpy, etc...) and just use
predefined shifts and mask. This type of change are needed to expedite
FD setup during data path (ADQ uses this codepath during initial
flow setup) and it will also be useful when adding side-band
flow-director filter.
Signed-off-by: Kiran Patil <kiran.patil@intel.com>
Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>
Increase the maximum time that the driver will wait for a PF reset
from 200 milliseconds to 300 milliseconds, to account for possibility
of a slightly longer than expected PF reset.
Fixes: 453d087cca ("net/ice/base: add common functions")
Cc: stable@dpdk.org
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>
In ice_prot_type_to_id routine, correct the loop limit check
to use ARRAY_SIZE instead of looking for the array element to
have a specific value.
Fixes: fed0c5ca5f ("net/ice/base: support programming a new switch recipe")
Cc: stable@dpdk.org
Signed-off-by: Dan Nowlin <dan.nowlin@intel.com>
Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>
Enable the code to clear the HW tables.
Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>
Change the extraction sequence generated by flow director flexbytes to
use package mac protocol. Without this change data in packet headers
cannot be used for flexbyte matching. The old extraction for flex bytes
started at the beginning of the payload which is after the header.
Signed-off-by: Henry Tieman <henry.w.tieman@intel.com>
Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>
Use a format consistent with the rest of the code.
Signed-off-by: Bruce Allan <bruce.w.allan@intel.com>
Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>
When RDMA is not enabled, when checking for completion of a CORER or
GLOBR do not wait for the PE unit to be loaded (indicated by GLNVM_ULD
register's PE_DONE bit being set) since that does not happen and will
cause issues such as failing to initialize the device.
Signed-off-by: Bruce Allan <bruce.w.allan@intel.com>
Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>
Add a feature to allow user to add switch filter using input like
MAC + VLAN (C-tag only) + L4 (TCP/UDP) port. API "ice_add_adv_rule"
is extended to handle this filter type.
Signed-off-by: Kiran Patil <kiran.patil@intel.com>
Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>
Allow tools to access register offset 0xB8188 (GLGEN_RSTAT) for
NVMUpdate operations. This is a read-only register, so risk of other
issues stemming from this change is low. Even so, update the write
command to prevent and reject any commands which attempt to write to
this register, just like we do for GL_HICR_EN.
Signed-off-by: Jeb Cramer <jeb.j.cramer@intel.com>
Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>
This patch removed some unused macros defined in hns3_rss.h,
these macros are used to set tuples for abandoned RTE_ETH_FILTER_HASH
in hns3_dev_filter_ctrl().
Signed-off-by: Hao Chen <chenhao164@huawei.com>
Signed-off-by: Wei Hu (Xavier) <xavier.huwei@huawei.com>
This patch removes the unnecessary assignment in the '.tx_pkt_burst' ops
implementation function to avoid performance loss.
Signed-off-by: Wei Hu (Xavier) <xavier.huwei@huawei.com>
Signed-off-by: Yisen Zhuang <yisen.zhuang@huawei.com>
This patch removes the redundant initialization of the variable
named ret.
Signed-off-by: Hongbo Zheng <zhenghongbo3@huawei.com>
Signed-off-by: Hao Chen <chenhao164@huawei.com>
Signed-off-by: Wei Hu (Xavier) <xavier.huwei@huawei.com>
This patch removes the redundant statement calling hns3_stats_reset()
to clear statistical information explicitly in the initialization of
VF device, because hardware has been reset by FLR in the initialization
and the initial hardware and software statistics values are 0.
Signed-off-by: Hao Chen <chenhao164@huawei.com>
Signed-off-by: Wei Hu (Xavier) <xavier.huwei@huawei.com>
This patch changed the default algorithm of RSS from simle_xor to
toeplitz because toeplitz is used more frequently by upper applications
such as ceph.
Signed-off-by: Hao Chen <chenhao164@huawei.com>
Signed-off-by: Wei Hu (Xavier) <xavier.huwei@huawei.com>
This patch replaces custom macro named HNS3_MIN_FRAME_LEN for ethernet
minimum frame length with the macro named RTE_ETHER_MIN_LEN that defined
in DPDK framework.
Signed-off-by: Huisong Li <lihuisong@huawei.com>
Signed-off-by: Wei Hu (Xavier) <xavier.huwei@huawei.com>
Currently, firmware adds the function of sending message to PF driver
through mailbox when the link status is changed, hns3 PMD driver can
usually recognize link state change faster through the message.
And in some extreme cases, this way is not faster than existing method
regularly updating link status by issuing the command every second in PF
driver, because of the parallel processing of mailbox and command
messages in firmware. So we reserve updating link status using timers in
PF driver, and add querying link status by issuing command to the
firmware in '.link_update' ops implementation function named
hns3_dev_link_update to solve the out of date link status.
Signed-off-by: Hongbo Zheng <zhenghongbo3@huawei.com>
Signed-off-by: Wei Hu (Xavier) <xavier.huwei@huawei.com>
Signed-off-by: Huisong Li <lihuisong@huawei.com>
This patch adds supports of receive packets through interrupt mode for
hns3 PF/VF driver. The following ops functions should be implemented
defined in the struct eth_dev_ops:
rx_queue_intr_enable
rx_queue_intr_disable
Signed-off-by: Hao Chen <chenhao164@huawei.com>
Signed-off-by: Wei Hu (Xavier) <xavier.huwei@huawei.com>
When offloading the meter, should check the action
conf and make sure it is valid.
Fixes: f46bf74887 ("net/mlx5: support meter flow action")
Cc: stable@dpdk.org
Signed-off-by: Tonghao Zhang <xiangxia.m.yue@gmail.com>
Reviewed-by: Suanming Mou <suanmingm@mellanox.com>
In some cases when flow creation fails, we overwrite the specific
error message with a generic error message. This patch fixes it.
Fixes: d24610f7bf ("net/bnxt: allow flow creation when RSS is enabled")
Cc: stable@dpdk.org
Signed-off-by: Ajit Khaparde <ajit.khaparde@broadcom.com>
Reviewed-by: Lance Richardson <lance.richardson@broadcom.com>
Add support for RTE_FLOW_ACTION_TYPE_MARK.
Use the flow_id provided by FW during flow creation to lookup the
mark id provided by the application.
Signed-off-by: Ajit Khaparde <ajit.khaparde@broadcom.com>
Reviewed-by: Lance Richardson <lance.richardson@broadcom.com>
The software L2 filter was being released back to the free pool,
though it was created in HW and the filter corresponding to an actual
'flow' would have reference to the HW L2 filter.
But if this 'flow were to be deleted, then this HW L2 filter also
would be gone.
Fix this by storing the L2 filter created originally either for an
n-tuple flow or otherwise as part of the vnic's filter list.
This would require the filter_info struct to have a backptr to the
vnic which it came from.
Now that L2 filters can be re-used for an n-tuple filter(s), delete
L2 filter as well so the reference count of an L2 filter (if reused)
can be decremented appropriately.
Fixes: 5c1171c972 ("net/bnxt: refactor filter/flow")
Cc: stable@dpdk.org
Signed-off-by: Somnath Kotur <somnath.kotur@broadcom.com>
Reviewed-by: Ajit Khaparde <ajit.khaparde@broadcom.com>
As part of ntuple filter, we were creating L2 filter with the ntuple
redirect queue resulting in any L2 matching flow getting steered to
this queue. For ntuple filters, we need to create the L2 filter with
default queue. The user specified redirect queue will be set while
creating the ntuple filter in hardware.
Fixes: 5c1171c972 ("net/bnxt: refactor filter/flow")
Cc: stable@dpdk.org
Signed-off-by: Santoshkumar Karanappa Rastapur <santosh.rastapur@broadcom.com>
Signed-off-by: Somnath Kotur <somnath.kotur@broadcom.com>
Sync flow flush routine with flow destroy so that the operations
performed per flow during a flush are the same as that are done for an
individual flow destroy by having a common function to call for both.
One of the things that was missed in the flow flush routine was the
deletion of the L2 filter that would have been created as part of an
n-tuple filter.
Also, decrement the l2_ref_cnt for a filter in the case of a filter
update as it would've bumped up previously in validate_and_parse_flow()
Fixes: 89278c59d9 ("net/bnxt: fix flow flush handling")
Cc: stable@dpdk.org
Signed-off-by: Somnath Kotur <somnath.kotur@broadcom.com>
Reviewed-by: Santoshkumar Karanappa Rastapur <santosh.rastapur@broadcom.com>
In the case when CoS classification is disabled, driver was iterating
looking for only lossy profiles as that is what is expected to be used
for regular NIC operations. But in certain custom profiles, there were
no lossy profiles configured, only lossless profiles instead.
To handle such cases, it is better to fallback to using the first valid
profile.
Fixes: 698aa7e953 ("net/bnxt: add code to determine the Tx COS queue")
Cc: stable@dpdk.org
Signed-off-by: Somnath Kotur <somnath.kotur@broadcom.com>
Reviewed-by: Ajit Khaparde <ajit.khaparde@broadcom.com>
We need to wait for up to 500ms to receive async event notification
after forcing link down. Similarly we need to wait for up to 10s for
link to come up after configuring the hardware for link up.
Fixes: c09f57b49c ("net/bnxt: add start/stop/link update operations")
Cc: stable@dpdk.org
Signed-off-by: Santoshkumar Karanappa Rastapur <santosh.rastapur@broadcom.com>
Signed-off-by: Somnath Kotur <somnath.kotur@broadcom.com>
Setting exact link speed makes sense if auto-negotiation is
disabled. Fixed flag is required to disable auto-negotiation.
Signed-off-by: Guinan Sun <guinanx.sun@intel.com>
Acked-by: Ting Xu <ting.xu@intel.com>
Acked-by: Xiaolong Ye <xiaolong.ye@intel.com>
Setting exact link speed makes sense if auto-negotiation is
disabled. Fixed flag is required to disable auto-negotiation.
Signed-off-by: Guinan Sun <guinanx.sun@intel.com>
Acked-by: Ting Xu <ting.xu@intel.com>
Acked-by: Xiaolong Ye <xiaolong.ye@intel.com>
Hardware limits that max buffer size per tx descriptor should be
(16K-1)B. So when TSO enabled, the mbuf data size may exceed the
limit and cause malicious behavior to the NIC. This patch fixes
this issue by using more tx descs for this kind of large buffer.
Fixes: 4861cde461 ("i40e: new poll mode driver")
Cc: stable@dpdk.org
Signed-off-by: Xiaoyun Li <xiaoyun.li@intel.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
Tested-by: Ciara Loftus <ciara.loftus@intel.com>
In iavf_handle_virtchnl_msg(), it is not appropriate for _clear_cmd()
to be used as a notification to foreground thread. So introduce
_notify_cmd() to fix this error. In addition, since _notify_cmd()
contains rte_wmb(), rte_compiler_barrier() is not necessary.
Sending msg from VF to PF is mainly by calling iavf_execute_vf_cmd(),
the whole virtchnl msg process is like,
iavf_execute_vf_cmd() will call iavf_aq_send_msg_to_pf() to send
msg and then polling the cmd done flag as "if (vf->pend_cmd ==
VIRTCHNL_OP_UNKNOWN)"
When reply msg is returned by pf, iavf_handle_virtchnl_msg() in
isr will read msg return value by "vf->cmd_retval = msg_ret" and
immediately set the cmd done flag by calling _clear_cmd() to
notify the iavf_execute_vf_cmd().
iavf_execute_vf_cmd() find the cmd done flag is set and then
check whether command return value vf->cmd_retval is success or
not.
However _clear_cmd() also resets the vf->cmd_retval to success,
overwriting the actual return value which is used for diagnosis.
So iavf_execute_vf_cmd() will always find vf->cmd_retval is
success and then return success.
Fixes: 22b123a36d ("net/avf: initialize PMD")
Cc: stable@dpdk.org
Signed-off-by: Yahui Cao <yahui.cao@intel.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Xiaolong Ye <xiaolong.ye@intel.com>
To read line side statistics register, eth_group_sel
args in function ipn3ke_indirect_mac_read should be 0.
When eth_group_sel is 1, the nic side register is read.
Fixes: 5a6d883878 ("net/ipn3ke: implement statistics")
Cc: stable@dpdk.org
Signed-off-by: Andy Pei <andy.pei@intel.com>
Acked-by: Rosen Xu <rosen.xu@intel.com>
There'll always be a MDD event triggered when adding
a FDIR rule. The root cause is 'LAN enable' is not
configured during control VSI setup.
Besides, correct FDIR fields for both main VSI and
control VSI.
Fixes: 84dc7a95a2 ("net/ice: enable flow director engine")
Cc: stable@dpdk.org
Signed-off-by: Beilei Xing <beilei.xing@intel.com>
Acked-by: Jingjing Wu <jingjing.wu@intel.com>
Move device state flag from ice_hw to ice_adapter since it should
not be a part of base code.
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>
When send a adminq, if get IAVF_AQ_RC_BUSY, we should return
IAVF_ERR_NOT_READY.
Fixes: e5b2a9e957 ("net/avf/base: add base code for avf PMD")
Cc: stable@dpdk.org
Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>
Update copyright date to cover 2019.
Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>
Add 2.5G and 5G link speed support.
Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>
Update FW API version from 1.5 to 1.6 for X722
Also added NVM update related APIs.
Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>
Allocated resources were not freed in the event of failure in
iavf_init_asq function. This patch gracefully handles all failures.
Fixes: e5b2a9e957 ("net/avf/base: add base code for avf PMD")
Cc: stable@dpdk.org
Signed-off-by: Pandi Kumar Maharajan <pandi.maharajan@intel.com>
Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>
Change max VSI per VF from 3 to 4.
Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>
Adjust the indent in function and macro definition.
Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>
Update virtual channel API to align with latest spec.
Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>
Rename iavf_parse_hw_config to iavf_vf_parse_hw_config.
Rename iavf_reset to iavf_vf_reset.
Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>
Remove compile option INTEGRATED_VF.
Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>
Remove unused APIs in iavf_prototype.h, iavf_adminq_cmd.h
iavf_type.h, iavf_adminq.h and iavf_common.c
Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>
Add all supported device id.
Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>
Rename all register macro to align with kernel driver's implementation.
Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>
Rename iavf_status_code to iavf_status to align with kernel
driver's implementation.
Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>
Delete iavf_hmc.h and iavf_lan_hmc.h since its not necessary.
Signed-off-by: Paul M Stillwell Jr <paul.m.stillwell.jr@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>
Ixgbe PMD PF host code needs to support ixgbevf MAC address
add and remove. For this purpose, a response was added
between PF and VF to update the MAC address.
Signed-off-by: Guinan Sun <guinanx.sun@intel.com>
Acked-by: Xiaolong Ye <xiaolong.ye@intel.com>
Current implementation is that only one Rx queue can support interrupt,
because all queues are mapped in the same vector id in
vfio_enable_msix(). So VF can not support multi-queue Rx interrupt in
the interrupt mode.
In this patch, if the packet I/O interrupt on datapath is enabled
(rte_intr_dp_is_en(intr_handle) is true), we map different interrupt
vectors to each queue and send this map to PF. After PF sets the map to
the register, all Rx queue interrupts will be received.
In addition, vector id should less than the maximum vector value. When
queue number is more than vector value, we set up a loop of interrupt
vectors map.
Signed-off-by: Lunyuan Cui <lunyuanx.cui@intel.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
On validation of GENEVE item, the wrong flag is used.
This patch sets the correct bit in item_flags bitmap.
Fixes: e59a5dbcfd ("net/mlx5: add flow match on GENEVE item")
Cc: stable@dpdk.org
Signed-off-by: Dekel Peled <dekelp@mellanox.com>
Acked-by: Matan Azrad <matan@mellanox.com>
This patch implements the feature described in RFC [1], adding
support of RSS action on L3 and/or L4 source or destination only.
[1] http://mails.dpdk.org/archives/dev/2019-December/152796.html
Signed-off-by: Dekel Peled <dekelp@mellanox.com>
Acked-by: Matan Azrad <matan@mellanox.com>
Rx hash fields were copied from input parameter into TIR attributes
directly, with no translation. As result the copied value was wrong.
This patch adds translation of value from input bitmap to the
appropriate format.
Fixes: dc9ceff73c ("net/mlx5: create advanced RxQ via DevX")
Cc: stable@dpdk.org
Signed-off-by: Dekel Peled <dekelp@mellanox.com>
Acked-by: Matan Azrad <matan@mellanox.com>
Maximal size of coalesced LRO segment is set in TIR attributes as
number of chunks of size 256 bytes each.
Current implementation uses the hardcoded value 256 in several places.
This patch adds a definition for this value, and uses this definition
in all relevant places.
A debug message is added to clearly notify the actual configured size.
Signed-off-by: Dekel Peled <dekelp@mellanox.com>
Acked-by: Matan Azrad <matan@mellanox.com>
Bit-masks MLX5_FLOW_LAYER_IPV4_LRO and MLX5_FLOW_LAYER_IPV6_LRO were
added during work on LRO.
They are not used anywhere in current code.
This patch removes these redundant definitions.
Signed-off-by: Dekel Peled <dekelp@mellanox.com>
Acked-by: Matan Azrad <matan@mellanox.com>
The purpose of this patch is used to add a new field "fw_cap"
in bnxt structure. The new "fw_cap" field store all the capabilities
reported by the FW. This information will help us to determine
the device capabilities when registering feature support with FW.
Signed-off-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Reviewed-by: Ajit Khaparde <ajit.khaparde@broadcom.com>
Fix bnxt_free_filter() to ensure that the filter indices
are reset correctly when a filter is freed.
This change helps in avoiding few duplicate code as well.
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>
Remove "__rte_unused" instances that are not required.
Signed-off-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Reviewed-by: Rahul Gupta <rahul.gupta@broadcom.com>
Reviewed-by: Somnath Kotur <somnath.kotur@broadcom.com>
During the registration process, the drivers must publish
"HOT_RESET_SUPPORTED" capability to the core firmware only
if core firmware is capable of Hot Reset.
Fixes: df6cd7c1f7 ("net/bnxt: handle reset notify async event from FW")
Cc: stable@dpdk.org
Signed-off-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Reviewed-by: Ajit Khaparde <ajit.khaparde@broadcom.com>
Reviewed-by: Somnath Kotur <somnath.kotur@broadcom.com>
Older Firmware could have state information such as
MAC Filters, VLAN settings etc configured by user.
But new Firmware is unaware of this state information
and as a result driver should restore these settings
during reset recovery.
This patch restores the user configured vlan settings
prior to hot FW upgrade or FW error.
Signed-off-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Reviewed-by: Ajit Khaparde <ajit.khaparde@broadcom.com>
Older Firmware could have state information such as
MAC Filters, VLAN settings etc configured by user.
But new Firmware is unaware of this state information
and as a result driver should restore these settings
during reset recovery.
This patch restores the user configured mac addresses
prior to hot FW upgrade or FW error.
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>
The eth devices which share one ibv device only need one hash list of
flow table.
Currently, flow table hash list is created per each eth device
whatever whether they share one ibv device or not.
If the devices share one ibv device, the previously created hash list
will become dangle because the pointer point to (sh->flow_tbls) is
overwritten by the later created hast list.
To fix this, just don't create hash list if it is already created.
Fixes: 54534725d2 ("net/mlx5: fix flow table hash list conversion")
Cc: stable@dpdk.org
Reported-by: Zhike Wang <wangzhike@jd.com>
Signed-off-by: Xiaoyu Min <jackmin@mellanox.com>
Acked-by: Matan Azrad <matan@mellanox.com>
The type of txq has been assigned in mlx5_txq_hairpin_new.
Fixes: ae18a1ae96 ("net/mlx5: support Tx hairpin queues")
Cc: stable@dpdk.org
Signed-off-by: Tonghao Zhang <xiangxia.m.yue@gmail.com>
Acked-by: Ori Kam <orika@mellanox.com>
If configuring the number of tx/rx queue with rte_eth_dev_configure
to nr_queues + hairpin_nr_queues, and setting tx/rx queues to
nr_queues with rte_eth_tx/rx_queue_setup. But not configuring the
hairpin queues via rte_eth_tx/rx_hairpin_queue_setup.
When starting the netdev, there is a crash because of NULL accessing.
Fixes: cf5516696d ("ethdev: add hairpin queue")
Cc: stable@dpdk.org
Signed-off-by: Tonghao Zhang <xiangxia.m.yue@gmail.com>
Acked-by: Ori Kam <orika@mellanox.com>
During a kernel PF reset, this event is propagated to the VF.
The DPDK VF PMD will execute the reset task before the PF is done
with his. This results in the admin queue message not being responded
to leaving the port in "promiscuous" mode.
This patch makes sure the promiscuous mode is configured independently
of the current admin state.
Signed-off-by: Eelco Chaudron <echaudro@redhat.com>
Reviewed-by: Xiao Zhang <xiao.zhang@intel.com>
In FreeBSD environment, nic_uio drivers do not support interrupts,
rte_intr_callback_register() will fail to register interrupts.
We cannot make link status to change from down to up by interrupt
callback. So we need to wait for the controller to acquire link
when ports start. Through multiple tests, 5s should be enough.
Fixes: b9bd0f09fa ("ethdev: fix link status query")
Cc: stable@dpdk.org
Signed-off-by: Lunyuan Cui <lunyuanx.cui@intel.com>
Acked-by: Xiaolong Ye <xiaolong.ye@intel.com>
Acked-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
The link status for ixgbevf is not correct when PF link up.
IXGBE_ESDP register is only used when media type is fiber.
Fixes: 1ca05831b9 ("net/ixgbe: fix link status")
Cc: stable@dpdk.org
Signed-off-by: Lunyuan Cui <lunyuanx.cui@intel.com>
Acked-by: Xiaolong Ye <xiaolong.ye@intel.com>
FreeBSD OS doesn't support igb_uio interrupt, so it will fail when
unregister the interrupt callback in port close. We can fix the issue by
passing -ENOENT when check the return value of unregister interrupt
callback function.
Fixes: ac89d46096 ("net/i40e: release port upon close")
Cc: stable@dpdk.org
Signed-off-by: Chenxu Di <chenxux.di@intel.com>
Acked-by: Xiaolong Ye <xiaolong.ye@intel.com>
Rx total stats is the total number of successfully received packets,
so exclude the number of rx_discards for Rx total stats.
Fixes: f4a41a6953 ("net/avf: support stats")
Cc: stable@dpdk.org
Signed-off-by: Jiaqi Min <jiaqix.min@intel.com>
Acked-by: Jingjing Wu <jingjing.wu@intel.com>
The ipn3ke driver and the ifpga driver had circular dependencies on each
other, meaning that neither could be built with meson. Fix this by:
* setting the build order of net and raw to match that in makefiles
* removing the dependency from the net driver on the rawdev one
* fixing the dependency names in the rawdev driver meson.build file
Fixes: 8418c92811 ("net/ipn3ke: remove configuration for i40e port bonding")
Fixes: e1defba4cf ("raw/ifpga/base: support device tree")
Cc: stable@dpdk.org
Signed-off-by: Bruce Richardson <bruce.richardson@intel.com>
Acked-by: Rosen Xu <rosen.xu@intel.com>
According to comms package, index 94 should be MAC_IPV6_ICMP,
not MAC_IPV4_ICMP. This patch fixes the issue.
Fixes: 4cf29798b4 ("net/ice: fix packet type table")
Cc: stable@dpdk.org
Signed-off-by: Shougang Wang <shougangx.wang@intel.com>
Acked-by: Xiaolong Ye <xiaolong.ye@intel.com>
In order to change RSS parameters, the host requires that RSS
is disable first.
Fixes: 92d23a57ca ("net/netvsc: support configuring RSS parameters")
Cc: stable@dpdk.org
Signed-off-by: Donald Lee <donald_lee@trendmicro.com>
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Tested-by: Dexuan Cui <decui@microsoft.com>
Tested-by: Abhishek Marathe <abmarath@microsoft.com>
The change to add OFFLOAD_RSS_HASH broke use of netvsc PMD
with testpmd. The netvsc driver fails during configure step:
Configuring Port 1 (socket 0)
hn_dev_configure(): unsupported RX offload: 0x80000
Fixes: 5d30897295 ("ethdev: add mbuf RSS update as an offload")
Cc: stable@dpdk.org
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
The VLAN field in the descriptor is not filled when ol_flags has
no VLAN flag. When the caller sends some packets with VLAN tags,
but other packets do not have VLAN tags, the behavior of the program
cannot be determined.
Fixes: 4b61d3bfa9 ("fm10k: add receive and tranmit")
Cc: stable@dpdk.org
Signed-off-by: Lu Qiuwen <luqiuwen@iie.ac.cn>
Acked-by: Xiao Wang <xiao.w.wang@intel.com>
Previously large packet would be dropped, instead now it is better to
keep it via truncating it.
Signed-off-by: Zhike Wang <wangzhike@jd.com>
Reviewed-by: Cian Ferriter <cian.ferriter@intel.com>
Acked-by: Ferruh Yigit <ferruh.yigit@intel.com>
BNXT_GET_DEFAULT_VNIC macro returns the default VNIC of the
function and fixed all occurrences of code to use the macro.
Signed-off-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Reviewed-by: Somnath Kotur <somnath.kotur@broadcom.com>
Remove an unnecessary log while deleting EM filters.
Signed-off-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Reviewed-by: Somnath Kotur <somnath.kotur@broadcom.com>
Use switch-case statement to replace if-else statement.
Signed-off-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Reviewed-by: Somnath Kotur <somnath.kotur@broadcom.com>
Use the new API to wait in low power state instead of continuous
polling to save CPU cycles and power.
Signed-off-by: Gavin Hu <gavin.hu@arm.com>
Reviewed-by: Ruifeng Wang <ruifeng.wang@arm.com>
Acked-by: Jerin Jacob <jerinj@marvell.com>
A new vDPA class was recently introduced.
IFC driver implements the vDPA operations,
hence it should be moved to the vDPA class.
Move it.
Signed-off-by: Matan Azrad <matan@mellanox.com>
Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
This rewrites the MKSTR macro appending an empty string to its arguments
to resolve build failures similar to:
drivers/net/mlx4/mlx4.c:461:14: fatal error: format string is not a
string literal [-Wformat-nonliteral]
MKSTR(path, "%s/device/uevent", device->ibdev_path);
drivers/net/mlx4/mlx4_utils.h:82:30: note: expanded from macro 'MKSTR'
char name[snprintf(NULL, 0, __VA_ARGS__) + 1]; \
drivers/net/mlx5/mlx5_stats.c:144:15: fatal error: format string is not a
string literal [-Wformat-nonliteral]
MKSTR(path, "%s/ports/%d/hw_counters/%s",
drivers/net/mlx5/mlx5_utils.h:149:30: note: expanded from macro 'MKSTR'
char name[snprintf(NULL, 0, __VA_ARGS__) + 1]; \
The errors reproduce with clang version 9.0.0, and the release notes
don't mention what could have caused them.
Fixes: 7fae69eeff ("mlx4: new poll mode driver")
Fixes: 771fa900b7 ("mlx5: introduce new driver for Mellanox ConnectX-4 adapters")
Cc: stable@dpdk.org
Signed-off-by: Ali Alnubani <alialnu@mellanox.com>
Signed-off-by: Matan Azrad <matan@mellanox.com>
The legacy multi-packet write is the feature allowing to
put multiple packets into one transmitting descriptor,
this feature is supported by only NIC ConnectX-4LX.
The number of packets should be limited to provide
optimal size descriptor and better performance.
Fixes: 18a1c20044 ("net/mlx5: implement Tx burst template")
Cc: stable@dpdk.org
Signed-off-by: Viacheslav Ovsiienko <viacheslavo@mellanox.com>
Acked-by: Matan Azrad <matan@mellanox.com>
The legacy multi-packet write is the feature allowing to
put multiple packets into one transmitting descriptor,
this feature is supported by only NIC ConnectX-4LX.
The number of packets should be limited to provide
optimal size descriptor and better performance.
Fixes: 18a1c20044 ("net/mlx5: implement Tx burst template")
Cc: stable@dpdk.org
Signed-off-by: Viacheslav Ovsiienko <viacheslavo@mellanox.com>
Acked-by: Matan Azrad <matan@mellanox.com>
In extensive metadata mode the MARK copy table is engaged,
if the application creates the flow with zero MARK ID action:
flow create 1 ingress pattern eth / ... / end actions mark id 0 / .. end
And then destroys that, the traffic to the port stops. This happens
due to default flow for the copy table has the zero ID and is removed
with the application rule. The patch extends internal ID variable
to 64 bits and provide the UINT64_MAX ID for the copy table default
rule.
Fixes: dd3c774f6f ("net/mlx5: add metadata register copy table")
Signed-off-by: Viacheslav Ovsiienko <viacheslavo@mellanox.com>
Acked-by: Ori Kam <orika@mellanox.com>
When set the GRE item, GRE key should follow after GRE header, or the
header gre_item pointer used by the key will be invalid.
Currently in the mlx5_flow_validate_item_gre_key() function, the header
gre_item pointer is access before checking if the key is after the
header or not. Once the key item is before the header, invalid gre_item
pointer access happens.
Move the gre_item pointer access after the GRE header check to avoid the
crash issue.
Fixes: a7a0365565 ("net/mlx5: match GRE key and present bits")
Cc: stable@dpdk.org
Signed-off-by: Suanming Mou <suanmingm@mellanox.com>
Acked-by: Ori Kam <orika@mellanox.com>
GENEVE is available in tunnel offloads. Add it as the default support
option.
Signed-off-by: Suanming Mou <suanmingm@mellanox.com>
Acked-by: Ori Kam <orika@mellanox.com>
The header mlx5_glue.h includes rte_byteorder.h, which isn't
pulled by global_inc. This patch adds the missing include directory
and fixes the build error:
In file included from drivers/net/mlx5/mlx5_glue.c:31:
drivers/net/mlx5/mlx5_glue.h:12:10: fatal error:
rte_byteorder.h: No such file or directory
The build failure can be triggered with:
meson -Dibverbs_link=dlopen build && ninja -C build
Fixes: 400d985eb5 ("net/mlx5: add VLAN push/pop DR commands to glue")
Signed-off-by: Ali Alnubani <alialnu@mellanox.com>
Acked-by: Thomas Monjalon <thomas@monjalon.net>
ConnectX-4LX supports multiple packets within the single Tx
descriptor. This feature is named as "Legacy Multi-Packet Write"
and imposes a lot of limitations:
- no ACLs, it means no NIC Tx Flows are supported and Tx metadata
become meaningless
- the required minimal inline data must be zero
- no SR-IOV, it means no support in E-Switch configurations,
- no priority and dscp forcing
- no VLAN insertion
- no TSO
- all packets within MPW session must have the same size
This legacy MPW feature is mainly intended for test purposes.
To explicitly engage the feature on ConnectX-4LX the devargs
should be specified:
- txq_mpw_en=1
This feature was dropped in 19.08, this patch reverts it back.
Fixes: 18a1c20044 ("net/mlx5: implement Tx burst template")
Cc: stable@dpdk.org
Signed-off-by: Viacheslav Ovsiienko <viacheslavo@mellanox.com>
Acked-by: Matan Azrad <matan@mellanox.com>
'close()' calls 'stop()' and 'stop()' cancels pthread without any check.
Calling 'stop()' & 'close()' sequentially tries to cancel pthread twice
which will cause a crash.
Adding a state check in 'stop()' before canceling the pthread to prevent
multiple stop.
Fixes: 696fbc7bb4 ("net/kni: remove resources when port is closed")
Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com>
Tested-by: Yinan Wang <yinan.wang@intel.com>
It's possible that we fail to get the IOMMU group of ifcvf device, this
patch adds a check on the return value.
Coverity issue: 349894
Fixes: a3f8150eac ("net/ifcvf: add ifcvf vDPA driver")
Cc: stable@dpdk.org
Signed-off-by: Xiao Wang <xiao.w.wang@intel.com>
Reviewed-by: Xiaolong Ye <xiaolong.ye@intel.com>
Commit in fixes line sets the DV (Direct Verbs) flow engine as default.
Newer versions of DV flow engine use the DR (Direct Rules) features.
DR is supported from RDMA Core library version rdma-core-24.0.
This cause failure to start port when using older rdma-core version,
without DR support.
This patch selects DV flow engine if rdma-core version is v24.0 or
higher. Verbs flow engine is selected otherwise.
Fixes: cd4569d2bf ("net/mlx5: change default flow engine to DV")
Signed-off-by: Dekel Peled <dekelp@mellanox.com>
Acked-by: Ori Kam <orika@mellanox.com>
loopback mode is not supported for VFs so returning error if
VF is being configured with loopback mode.
Fixes: 920717e4d8 ("net/octeontx2: add device start operation")
Cc: stable@dpdk.org
Signed-off-by: Sunil Kumar Kori <skori@marvell.com>
Acked-by: Jerin Jacob <jerinj@marvell.com>
The link status got from link status register was not correct,
because register has been reset when ports reset.
After port reset, set the link status down.
Fixes: c431ec66c5 ("net/igb: support setting link up or down")
Cc: stable@dpdk.org
Signed-off-by: Lunyuan Cui <lunyuanx.cui@intel.com>
Acked-by: Wenzhuo Lu <wenzhuo.lu@intel.com>
The link status for 82599eb got from link status register was not
correct. Check the enable/disable flag of tx laser, set the link
status down if tx laser disabled. Then, we can get correct status.
But after port reset, tx laser register will be reset enable.
Link status will always be up. So set tx laser disable when port resets.
When hw->mac.autotry_restart is true, whether tx laser is disable or
enable, it will be set enable in ixgbe_flap_tx_laser_multispeed_fiber().
hw->mac.autotry_restart can be set true in both port init and port start.
Because we don't need this treatment before port starts, set
hw->mac.autotry_restart false when port init.
Fixes: 0408f47ba4 ("net/ixgbe: fix busy polling while fiber link update")
Cc: stable@dpdk.org
Signed-off-by: Lunyuan Cui <lunyuanx.cui@intel.com>
Acked-by: Wenzhuo Lu <wenzhuo.lu@intel.com>
Meaningless to judge the link state according to the memset'ed
link variable, this patch fixes this logical issue.
In addition, this patch changes the variable from link_check to link_up
according to its real meaning.
Fixes: 80ba61115e ("net/e1000: use link status helper functions")
Cc: stable@dpdk.org
Signed-off-by: Lunyuan Cui <lunyuanx.cui@intel.com>
Acked-by: Xiaolong Ye <xiaolong.ye@intel.com>
Acked-by: Wenzhuo Lu <wenzhuo.lu@intel.com>
In .tx_pkt_burst ops implementation function of hns3 PMD driver,
there is one check whether there are enough BDs in the TX queue.
If not, driver will stop sending the packets.
Currently in the 'for' process loop, the next_to_use member of
TX queue is not updated in time after processing BDs of one packet,
which results in the invalid action of checking whether there are
enough BDs and failure in sending packets.
This patch fixes it by moving the assignment statment of the
next_to_use member of TX queue to the place after porcessing TX BDs
in the 'for' loop.
Fixes: bba6366983 ("net/hns3: support Rx/Tx and related operations")
Cc: stable@dpdk.org
Signed-off-by: Hongbo Zheng <zhenghongbo3@huawei.com>
Signed-off-by: Huisong Li <lihuisong@huawei.com>
Signed-off-by: Wei Hu (Xavier) <xavier.huwei@huawei.com>
Enable packet type parsing by default, only disable when
`rte_eth_dev_set_ptypes()` is called with ptype_mask as 0.
This would enable applications that are dependent on packet type parsing
like l3fwd.
Also this patch preserves configuration set by `rte_eth_dev_set_ptypes`
across multiple calls of `rte_eth_dev_configure()`
Fixes: d2706e15e6 ("net/octeontx2: support reduced set of packet types")
Signed-off-by: Pavan Nikhilesh <pbhagavatula@marvell.com>
Acked-by: Jerin Jacob <jerinj@marvell.com>
The metadata register used for META item/action within E-Switch
steering domain should be altered depending on dv_xmeta_en
devarg value.
Fixes: 3e8edd0ef8 ("net/mlx5: update metadata register ID query")
Signed-off-by: Viacheslav Ovsiienko <viacheslavo@mellanox.com>
Acked-by: Matan Azrad <matan@mellanox.com>
For tunnel mode, there may be two L3/L4 layer match pattern items, one
for inner and one for outer layers. The L3 TTL and L4 port header
modify actions should handle the outermost layer items.
Currently flow_dv_attr_init() doesn't distinguish between outer and
inner layers, since inner layer comes later than the outer layer, this
may cause inner layer values also set to the flow attributes and may
lead actions to use inner L3/L4 pattern items.
Adding a check in flow_dv_attr_init() to prevent inner layer to set the
flow attribute if the previous L3/L4 outer pattern exist.
Fixes: 4bb14c83df ("net/mlx5: support modify header using Direct Verbs")
Cc: stable@dpdk.org
Signed-off-by: Suanming Mou <suanmingm@mellanox.com>
Acked-by: Matan Azrad <matan@mellanox.com>
When setting vlan, hns3 driver will add vlan entry to vlan linked list
each time, and this is unreasonable.
This patch adds a check whether the VLAN to be added already exists
in the linked list and prevents adding duplicated vlan.
Fixes: 411d23b9ea ("net/hns3: support VLAN")
Cc: stable@dpdk.org
Signed-off-by: Min Hu (Connor) <humin29@huawei.com>
Signed-off-by: Wei Hu (Xavier) <xavier.huwei@huawei.com>
Currently, port link status is "up" in VF driver after user calling the
rte_eth_dev_stop API. This is unreasonable.
Therefore, this patch adjusts the strategy of getting link status from
PF driver for VF. VF driver should stop getting link status from PF by
canceling the alarm that VF driver send mailbox message to PF driver,
when the rte_eth_dev_stop API is called. And VF driver should restore
the alarm when the rte_eth_dev_start API is called.
Fixes: a5475d61fa ("net/hns3: support VF")
Cc: stable@dpdk.org
Signed-off-by: Huisong Li <lihuisong@huawei.com>
Signed-off-by: Wei Hu (Xavier) <xavier.huwei@huawei.com>
Remove the macro 'HNS3_REG_MSG_DATA_OFFSET' which is used to prevent
access violation for response array by limiting the response data length
to 4.
But the limit value is too short to get some longer information such as
6 byte MAC address.
This patch modifies the length of response data from mailbox to allow
the response data length to be 8. So that the VF driver could get more
data from PF driver by mailbox.
Fixes: 463e748964 ("net/hns3: support mailbox")
Cc: stable@dpdk.org
Signed-off-by: Chengchang Tang <tangchengchang@hisilicon.com>
Signed-off-by: Wei Hu (Xavier) <xavier.huwei@huawei.com>
Ethernet minimum packet length is 64 bytes. If upper application
sends packets with less than 60 bytes in length(no CRC), driver
adds padding processing to avoid failure.
Fixes: bba6366983 ("net/hns3: support Rx/Tx and related operations")
Cc: stable@dpdk.org
Signed-off-by: Huisong Li <lihuisong@huawei.com>
Signed-off-by: Wei Hu (Xavier) <xavier.huwei@huawei.com>
When the application using VF device exits abnormally, for example,
when it is killed by 'kill -9', kernel PF netdev driver also stores
the corresponding configuration table entries of VF device.
This patch fixes it by adding message of deleting VF configuration
table entry corresponds to the revision of kernel hns3 netdev
driver, the new message is added to notify the kernel PF netdev
driver to clean up the VF configuration initialization during VF
initialization.
This revision is compatible with the old version of kernel hns3
netdev driver. The old version of kernel pf netdev driver will
ignore this message.
Fixes: a5475d61fa ("net/hns3: support VF")
Cc: stable@dpdk.org
Signed-off-by: Hongbo Zheng <zhenghongbo3@huawei.com>
Signed-off-by: Wei Hu (Xavier) <xavier.huwei@huawei.com>
This patch fixes the bug that hardware configuration called
tc_size doesn't restore to the initial value when starting
the app, configuring PFC and then restarting the app,
because of the tc_mode didn't initial when rss is disabled.
Fixes: c37ca66f2b ("net/hns3: support RSS")
Cc: stable@dpdk.org
Signed-off-by: Hao Chen <chenhao164@huawei.com>
Signed-off-by: Wei Hu (Xavier) <xavier.huwei@huawei.com>
Now that vnics are created only as part of the flow creation cmds
and not during init, we cannot rely on iterating only through
'nr_vnics'. We need to sweep all the vnics by using 'max_vnics'
otherwise a vnic with a stale 'rx_queue_cnt' might be left lingering
post a port stop/start operation. This could lead to a segfault.
This change is required because of the recent fix made by commit to
"fix flow creation with non-consecutive group ids".
Fixes: fcdd7210aa ("net/bnxt: fix flow creation with non-consecutive group ids")
Signed-off-by: Somnath Kotur <somnath.kotur@broadcom.com>
Reviewed-by: Ajit Khaparde <ajit.khaparde@broadcom.com>
The current raw_encap function selects if to decap or encap
based on the egress/ingress attribute. This concepts doesn't work
in case of FDB since all flows are considered ingress.
To solve this issue we moved to check the encap size.
if the encap size is larger then eth + ipv4 it means we are
trying to encap.
Fixes: 8ba9eee4ce ("net/mlx5: add raw data encap/decap to Direct Verbs")
Cc: stable@dpdk.org
Signed-off-by: Ori Kam <orika@mellanox.com>
Acked-by: Matan Azrad <matan@mellanox.com>
Currently macsec offload will be enabled every time when device starts.
It will cause QoS sample application performance drop issue. This patch
adds check in dev_start ops to make sure macsec is only enabled when
required explicitly.
Fixes: 50556c8810 ("net/ixgbe: fix MACsec setting")
Cc: stable@dpdk.org
Signed-off-by: Shougang Wang <shougangx.wang@intel.com>
Reviewed-by: Xiaolong Ye <xiaolong.ye@intel.com>
When DR is not supported and DV is supported, tag action still can be
used by the metadata feature.
Wrongly, the tag hash list was not created what caused failure in
metadata action creation.
Create the tag hash list for each DV case.
Fixes: 860897d289 ("net/mlx5: reorganize flow tables with hash list")
Signed-off-by: Matan Azrad <matan@mellanox.com>
The "addr" param has been used since the event callbacks are enabled
for external memory. So the "__rte_unused" should be dropped.
Besides, slightly refine the coding style by consistently assuming
tabs are 8 characters.
Fixes: f32c7c9de9 ("malloc: enable event callbacks for external memory")
Cc: stable@dpdk.org
Signed-off-by: Tiwei Bie <tiwei.bie@intel.com>
Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
Add FDIR support for normal GTP-U packet, which doesn't contain GTP_PSC
extension header.
Fixes: efc16c6214 ("net/ice: support flow director GTPU tunnel")
Signed-off-by: Yahui Cao <yahui.cao@intel.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
Pattern name of GTP-U flow with extension header should be
xxx_gtpu_eh_xxx. So it will not conflict with the pattern name of a
GTP-U flow that does not contains extension header.
Fixes: 3e4eab9c21 ("net/ice: add pattern manifest")
Signed-off-by: Yahui Cao <yahui.cao@intel.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
Flow type "IPv4 + UDP" or "IPv4 + TCP" is conflict with "IPv4 + any"
flow type. If a rule for IPv4 + any is created, we should reject any
rule for IPv4 + UDP otherwise the first rule may be impacted, same
decision should be made on a reverse order. For IPv6 and IPv4 GTPU
inner case, we have the same limitation.
Fixes: 109e8e0624 ("net/ice: configure HW flow director rule")
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Tested-by: Beilei Xing <beilei.xing@intel.com>
Acked-by: Beilei Xing <beilei.xing@intel.com>
Acked-by: Xiaolong Ye <xiaolong.ye@intel.com>
Sync mail box data structures to version 1.1.3.
Add mail box version verification and defer initializing octeontx
devices if mail box version mismatches.
Update OCTEON TX limitaion with max mempool size used.
Signed-off-by: Pavan Nikhilesh <pbhagavatula@marvell.com>
Reviewed-by: Jerin Jacob <jerinj@marvell.com>
Remove trailing blank lines. They serve no purpose and are just
editor leftovers.
These can cause git to complain about whitespace errors during merges.
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: Thomas Monjalon <thomas@monjalon.net>
Merge all versions in linker version script files to DPDK_20.0.
This commit was generated by running the following command:
:~/DPDK$ buildtools/update-abi.sh 20.0
Signed-off-by: Pawel Modrak <pawelx.modrak@intel.com>
Signed-off-by: Anatoly Burakov <anatoly.burakov@intel.com>
Acked-by: Bruce Richardson <bruce.richardson@intel.com>
Acked-by: Thomas Monjalon <thomas@monjalon.net>
Since the library versioning for both stable and experimental ABI's is
now managed globally, the LIBABIVER and version variables no longer
serve any useful purpose, and can be removed.
The replacement in Makefiles was done using the following regex:
^(#.*\n)?LIBABIVER\s*:=\s*\d+\n(\s*\n)?
(LIBABIVER := numbers, optionally preceded by a comment and optionally
succeeded by an empty line)
The replacement for meson files was done using the following regex:
^(#.*\n)?version\s*=\s*\d+\n(\s*\n)?
(version = numbers, optionally preceded by a comment and optionally
succeeded by an empty line)
[David]: those variables are manually removed for the files:
- drivers/common/qat/Makefile
- lib/librte_eal/meson.build
[David]: the LIBABIVER is restored for the external ethtool example
library.
Signed-off-by: Anatoly Burakov <anatoly.burakov@intel.com>
Signed-off-by: David Marchand <david.marchand@redhat.com>
Acked-by: Thomas Monjalon <thomas@monjalon.net>
In debug mode, there is assertion to validate the CQ object before the
release.
Wrongly, the assertion is done for any type of RX queue even if it
doesn't use CQ at all, for example in hairpin Rx queue.
Ignore CQ assertion when hairpin queue is released.
Fixes: e79c9be915 ("net/mlx5: support Rx hairpin queues")
Signed-off-by: Matan Azrad <matan@mellanox.com>
Acked-by: Ori Kam <orika@mellanox.com>
The secondary process does not need to register interrupt handle,
remove rte_intr_callback_register from secondary process branch.
Fixes: 64727024d2 ("net/hinic: add device initialization")
Cc: stable@dpdk.org
Signed-off-by: Xiaoyun Wang <cloud.wangxiaoyun@huawei.com>
In order to configure L3 encapsulation\decapsulation flow to mlx5
devices, 2 actions should be added to the flow actions list:
RTE_FLOW_ACTION_TYPE_RAW_DECAP and RTE_FLOW_ACTION_TYPE_RAW_ENCAP.
One of the validations for this scenario is to check that modify actions
is not done before the L3 decapsulation, because it doesn't make sense
to decapsulate a modified data.
Wrongly, this check was done for the case of L3 encapsulation what
causes a validation failure in modify + L3 encapsulation flow.
Ignore this check in case of L3 encapsulation.
Fixes: 4bb14c83df ("net/mlx5: support modify header using Direct Verbs")
Cc: stable@dpdk.org
Signed-off-by: Matan Azrad <matan@mellanox.com>
bnxt_validate_and_parse_flow_type already has protocol specific NULL
checks for rte_flow_item spec and mask and take actions accordingly.
A check at the top of the loop is redundant and is preventing the
protocol specific checks from being executed.
Fixes: b7e01f3860 ("net/bnxt: handle cleanup if flow creation fails")
Signed-off-by: Ajit Khaparde <ajit.khaparde@broadcom.com>
Reviewed-by: Santoshkumar Karanappa Rastapur <santosh.rastapur@broadcom.com>
Reviewed-by: Somnath Kotur <somnath.kotur@broadcom.com>
In order to prevent reconfiguration of firmware resources for every
MTU change, configure FW with max MTU value using hwrm_func_cfg
to support all frame sizes. There is no need to overwrite the driver
level MTU variable data->mtu with the FW MTU.
Fixes: 905cd45ce3 ("net/bnxt: use configured MTU during load")
Cc: stable@dpdk.org
Signed-off-by: Rahul Gupta <rahul.gupta@broadcom.com>
Reviewed-by: Ajit Khaparde <ajit.khaparde@broadcom.com>
Reviewed-by: Somnath Kotur <somnath.kotur@broadcom.com>
On some old versions of FW, bnxt_hwrm_func_resc_qcaps can return an
error. This is because the command was not implemented completely
in FW till the subsequent version. Ignore the error and continue with
the driver initialization.
Fixes: edafb57ba4 ("net/bnxt: fix VF resource allocation")
Cc: stable@dpdk.org
Signed-off-by: Ajit Khaparde <ajit.khaparde@broadcom.com>
Reviewed-by: Somnath Kotur <somnath.kotur@broadcom.com>
When FDIR filter detects duplicated rule and then returns EEXIST, ice
flow will capture this error and return immediately.
Fixes: 4e27d3ed02 ("net/ice: fix flow API framework")
Signed-off-by: Yahui Cao <yahui.cao@intel.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
When creating a flow, the flow is checked if it should be split into
2 flows based on the queue/rss acton.
If the RSS action with given without any queues, it will result in crash
due to the fact that the function checks the queue type.
This commit fixes this issue by checking if the rss action is not empty,
and at least one queue.
Fixes: d85c7b5ea5 ("net/mlx5: split hairpin flows")
Signed-off-by: Ori Kam <orika@mellanox.com>
Acked-by: Viacheslav Ovsiienko <viacheslavo@mellanox.com>
Assert condition is fixed to not alert for the case
when multi-packet write is not supported/engaged at all.
Fixes: b53cd86965 ("net/mlx5: adjust inline setting for large Tx queue sizes")
Signed-off-by: Viacheslav Ovsiienko <viacheslavo@mellanox.com>
To support LAG configurations the mlx5dv_dr_action_create_dest_ib_port()
should be called instead of mlx5dv_dr_action_create_dest_vport().
Fixes: f07341e7ae ("net/mlx5: update source and destination vport translations")
Signed-off-by: Viacheslav Ovsiienko <viacheslavo@mellanox.com>
Acked-by: Ori Kam <orika@mellanox.com>
Since not all data paths support flow mark, the driver needs
a hint from application to select the correct data path if
flow mark is required. The patch introduces a devarg
"flow-mark-support" as a workaround solution, since a standard
way is still ongoing.
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>
By moving irq enable/disable from device start/stop to FDIR
setup/teardown, FDIR queue irq config is independent of LAN queue irq
config. So device stop will not cause FDIR rule failure.
Fixes: 84dc7a95a2 ("net/ice: enable flow director engine")
Signed-off-by: Yahui Cao <yahui.cao@intel.com>
Signed-off-by: Beilei Xing <beilei.xing@intel.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
Tested-by: Qi Zhang <qi.z.zhang@intel.com>
To make sure if FDIR programming succeed or fail, legacy programming
status descriptor WB format is enabled and FDIR queue irq is opened.
Fixes: 84dc7a95a2 ("net/ice: enable flow director engine")
Signed-off-by: Yahui Cao <yahui.cao@intel.com>
Signed-off-by: Beilei Xing <beilei.xing@intel.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
Tested-by: Qi Zhang <qi.z.zhang@intel.com>
The FDIR parser will select ICE_FLTR_PTYPE_NONF_IPV4_OTHER as flow type
for an IPv4 UDP flow with empty l4 matching field which is not correct.
Same issues happens on all the combination between IPv4/IPv6 and
UDP/TCP/SCTP cases.
The patch fixes all the wrong flow ptype selections.
Fixes: f5cafa961f ("net/ice: add flow director create and destroy")
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Beilei Xing <beilei.xing@intel.com>
As the result of testing it was found that some hosts have
the performance penalty imposed by required write memory barrier
after doorbell writing. Before 19.08 release there was some
heuristics to decide whether write memory barrier should be
performed. For the bursts of recommended size (or multiple)
it was supposed there were some extra ongoing packets in the
next burst and write memory barrier may be skipped (supposed
to be performed in the next burst, at least after descriptor
writing).
This patch restores that behaviour, the devargs tx_db_nc=2
must be specified to engage this performance tuning feature.
Fixes: 8409a28573 ("net/mlx5: control transmit doorbell register mapping")
Cc: stable@dpdk.org
Signed-off-by: Viacheslav Ovsiienko <viacheslavo@mellanox.com>
The default flow engine is Verbs flow engine, for legacy reasons.
This patch changes the default to DV flow engine (dv_flow_en = 1).
Documentation is updated accordingly.
Signed-off-by: Dekel Peled <dekelp@mellanox.com>
Acked-by: Viacheslav Ovsiienko <viacheslavo@mellanox.com>
The af_packet pmd already supports MULTI_SEG tx packets, and tx
VLAN_INSERT so advertise these capabilities.
Signed-off-by: Paul Atkins <paul.atkins@intl.att.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
The rdma_core routine mlx5dv_dr_create_flow_action_dest_vport()
requires the vport id parameter to create port action.
The register c[0] value was used to deduce the port id value
and it fails in bonding configuration. The correct way is
to apply vport_num value queried from the rdma_core library.
Fixes: f07341e7ae ("net/mlx5: update source and destination vport translations")
Signed-off-by: Viacheslav Ovsiienko <viacheslavo@mellanox.com>
For the case when DR is not supported and DV is supported:
multi-tables feature is off.
In this case, only table 0 is supported.
Table 0 structure wrongly was not created what prevented any
matcher object to be created and even caused crashes.
Create the table hash list in DV case too.
Create table zero empty structure for each domain when DR is not
supported.
Allow NULL DR internal table object to be used.
Fixes: 860897d289 ("net/mlx5: reorganize flow tables with hash list")
Signed-off-by: Matan Azrad <matan@mellanox.com>
Zero-copy slave support for memif PMD.
Slave interface exposes DPDK memory to
master interface. Only single file segments
are supported (EAL option --single-file-segments).
Signed-off-by: Jakub Grajciar <jgrajcia@cisco.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
Arrays agg_count and agg_bandwidth should be indexed by slave_id not by
aggregator port_id.
The new_agg_id should be chosen as slave_id from slaves table in
different selection modes.
Fixes: 6d72657ce3 ("net/bonding: add other aggregator modes")
Cc: stable@dpdk.org
Signed-off-by: Krzysztof Kanas <kkanas@marvell.com>
Acked-by: Chas Williams <chas3@att.com>
Acked-by: Ferruh Yigit <ferruh.yigit@intel.com>
By default RSS hash delivery (offload) is bound to RSS mode and
it is incorrect to advertise it as enabled if Rx multi-queue mode
has no RSS.
Fixes: 8b945a7f7d ("drivers/net: update Rx RSS hash offload capabilities")
Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
Add support to set supported ptypes for octeontx2 and
remove devarg scheme to disable ptype parsing support as
application can use rte_eth_dev_set_ptypes() normative API
to enable the same use case.
Signed-off-by: Pavan Nikhilesh <pbhagavatula@marvell.com>
Acked-by: Jerin Jacob <jerinj@marvell.com>
Issue has been observed if PTP is already enabled on PF and
later VFs are configured. Since PTP requires mbuf data off
to be shifted by 8 bytes, due to this l3fwd/l2fwd was not
working with VFs.
Also some extra garbage bytes were observed in packet data
when ptp was enabled.
Fixes: b5dc314044 ("net/octeontx2: support base PTP")
Cc: stable@dpdk.org
Signed-off-by: Harman Kalra <hkalra@marvell.com>
Acked-by: Jerin Jacob <jerinj@marvell.com>
After otx2_nix_register_cq_irqs() is called and the IRQs are setup,
otx2_nix_unregister_cq_irqs() need to be called in the subsequent error
exit paths.
Fixes: d34db5ccbf ("net/octeontx2: fix driver reconfiguration")
Cc: stable@dpdk.org
Signed-off-by: Anoob Joseph <anoobj@marvell.com>
Acked-by: Jerin Jacob <jerinj@marvell.com>
Retrieve burst mode information according to the selected Rx/Tx mode and
offloads.
Signed-off-by: Sunil Kumar Kori <skori@marvell.com>
Acked-by: Jerin Jacob <jerinj@marvell.com>
Update "mbuf->ol_flags" correctly for 'Checksum Unknown' errors
for both tunneled and non-tunneled IP packets.
Fixes: b875339622 ("net/bnxt: fix L4 checksum indication in non-vector Rx")
Cc: stable@dpdk.org
Signed-off-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Reviewed-by: Somnath Kotur <somnath.kotur@broadcom.com>
The ipn3ke board FPGA and i40e BDF scan has added in ifpga_rawdev,
so it doesn't need to provide configuration for i40e port bonding.
Signed-off-by: Rosen Xu <rosen.xu@intel.com>
Signed-off-by: Andy Pei <andy.pei@intel.com>
In PAC N3000 card, this is a BMC chip which using MAX10 FPGA
to manage the board configuration, like sensors, flash controller,
QSFP, powers. And this is a SPI bus connected between A10 FPGA and
MAX10, we can access the MAX10 registers over this SPI bus.
In BMC, there are about 19 sensors in MAX10 chip, including the FPGA
core temperature, Board temperature, board current, voltage and so on.
We use DTB (Device tree table) to describe it. This DTB file is store
in nor flash partition, which will flashed in Factory when the boards
delivery to customers. And the same time, the customers can easy to
customize the BMC configuration like change the sensors.
Add device tree support by using libfdt library in Linux distribution.
The end-user should pre-install the libfdt and libfdt-devel package
before use DPDK on PAC N3000 Card.
For Centos 7.x: sudo yum install libfdt libfdt-devel
For Ubuntu 18.04: sudo apt install libfdt-dev libfdt1
To eliminate build error, we currently do not compile raw/ifpga
and net/ipn3ke. User should install libfdt and libfdt-devel first,
modify config/common_linux, CONFIG_RTE_LIBRTE_PMD_IFPGA_RAWDEV=n
to CONFIG_RTE_LIBRTE_PMD_IFPGA_RAWDEV=y, modify config/common_base,
CONFIG_RTE_LIBRTE_IPN3KE_PMD=n to CONFIG_RTE_LIBRTE_IPN3KE_PMD=y.
Then this function can work.
Signed-off-by: Tianfei Zhang <tianfei.zhang@intel.com>
Signed-off-by: Andy Pei <andy.pei@intel.com>
Acked-by: Bruce Richardson <bruce.richardson@intel.com>
In ipn3ke, each FPGA network side port bonding to an i40e pf,
each i40e pf link status should get data from FPGA network,
side port. This patch provide bonding relationship.
Signed-off-by: Rosen Xu <rosen.xu@intel.com>
Signed-off-by: Andy Pei <andy.pei@intel.com>
The kernel driver (starting from OFED 4.7.3.1.3) uses the upper half
of metadata register C0 to provide VHCA and vport id's. The mlx5 PMD
should check the actual mask of register C0 and shift the vport id
value for port actions appropriately.
Fixes: f07341e7ae ("net/mlx5: update source and destination vport translations")
Signed-off-by: Viacheslav Ovsiienko <viacheslavo@mellanox.com>
Acked-by: Matan Azrad <matan@mellanox.com>
The state of environment variable MLX5_BF_SHUT_UP was not
recovered correctly if there was no tx_db_nc devarg specified.
Fixes: 8409a28573 ("net/mlx5: control transmit doorbell register mapping")
Cc: stable@dpdk.org
Signed-off-by: Viacheslav Ovsiienko <viacheslavo@mellanox.com>
Fixes: 84dc7a95a2 ("net/ice: enable flow director engine")
Signed-off-by: Yahui Cao <yahui.cao@intel.com>
Acked-by: Xiaolong Ye <xiaolong.ye@intel.com>
Currently, multiple rte_flow RSS rules may map to the same
hardware rule if a later rule is just for input set change or
symm turn on/off. So after one of the rules be destroyed, we will
get error ICE_ERR_DOES_NOT_EXIST when destroying any other rules.
The patch simply fixes this by ignoring this error. A more
sophisticated fix that remember the sequence and replay properly
will be provided in the future.
Fixes: 5ad3db8d4b ("net/ice: enable advanced RSS")
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
In ice_hash_create(), whatever the hash_function is, the
filter_ptr->symm is always 0 and when we destroy the flow, the
ice_rem_rss_cfg() is never carried out. So the destroy function never
works well. The patch fixes this issue and at the same time
distinguishes between simple_xor and symmetric_toeplitz.
To fix this issue, the patch adds a new structure to include a flag to
indicate if it is a simple_xor flow so that it's easier to remove the
config when destroying the flow. The patch also simplifies code
implementation logic in ice_hash_create().
Fixes: 5ad3db8d4b ("net/ice: enable advanced RSS")
Signed-off-by: Simei Su <simei.su@intel.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
Null-checking "rxq" suggests that it may be null, but it has already
been dereferenced on all paths leading to the check.
Refactored the code to address this issue.
Coverity issue: 350594
Fixes: fc4bfea596 ("net/bnxt: fix Rx queue start/stop for Thor based NICs")
Cc: stable@dpdk.org
Signed-off-by: Ajit Khaparde <ajit.khaparde@broadcom.com>
Reviewed-by: Somnath Kotur <somnath.kotur@broadcom.com>
When an existing mac_addr is tried to get programmed again, a
message is displayed that the mac_addr already exists.
However the message is of type ERR. This patch changes the message
to type DEBUG
Fixes: 938a87db43 ("net/bnxt: fix redundant MAC address check")
Cc: stable@dpdk.org
Signed-off-by: Venkat Duvvuru <venkatkumar.duvvuru@broadcom.com>
Reviewed-by: Somnath Kotur <somnath.kotur@broadcom.com>
Reviewed-by: Ajit Khaparde <ajit.khaparde@broadcom.com>
We would hit a segfault in bnxt_dev_xstats_get_op() if xstats argument
is NULL, Check if the argument is NULL and return appropriately.
Fixes: bfb9c2260b ("net/bnxt: support xstats get/reset")
Cc: stable@dpdk.org
Signed-off-by: Ajit Khaparde <ajit.khaparde@broadcom.com>
Reviewed-by: Andy Gospodarek <gospo@broadcom.com>
In non-RSS mode, vnics map 1:1 with Rx queues during init. This can
create problems if non-consecutive group IDs are given as part of
subsequent flow create cmds as they can end up pointing to Rx queues
(mapped during init) that are different than the intended destination
queue as specified in the flow create cmd.
To fix this, now that we have the ability to dynamically create
vnics, do not create any additional vnics other than the default vnic
during init. Allocate them only during flow/filter creation time.
When RSS is disabled we need to use the COS queue count queried
from firmware.
Fixes: 36024b2e7f ("net/bnxt: allow dynamic creation of VNIC")
Signed-off-by: Rahul Gupta <rahul.gupta@broadcom.com>
Reviewed-by: Somnath Kotur <somnath.kotur@broadcom.com>
Cap max queue count to 128 for NS3 devices and ensure that same count
is reported as part of dev_info_get_op as well
Signed-off-by: Somnath Kotur <somnath.kotur@broadcom.com>
Reviewed-by: Rahul Gupta <rahul.gupta@broadcom.com>
Driver should fail the eth_dev_ops callbacks and accessing
Tx and Rx queues when device is in reset or in error state.
Added missing checks for fw reset in few routines.
Fixes: be14720def ("net/bnxt: support FW reset")
Reviewed-by: Santoshkumar Karanappa Rastapur <santosh.rastapur@broadcom.com>
Signed-off-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Signed-off-by: Ajit Khaparde <ajit.khaparde@broadcom.com>
The layer bits should be unique otherwise layer info will be
interpreted wrongly.
Fixes: 70d84dc797 ("net/mlx5: add internal tag item and action")
Fixes: 55deee1715 ("net/mlx5: extend flow mark support")
Signed-off-by: Xiaoyu Min <jackmin@mellanox.com>
Acked-by: Viacheslav Ovsiienko <viacheslavo@mellanox.com>
Function flow_verbs_counter_query() was recently modified.
The new 'if' condition uses a pointer to flow counter-set.
This pointer is valid only if flow contains a count action.
This patch adds check to verify the pointer is valid.
Fixes: d85c7b5ea5 ("net/mlx5: split hairpin flows")
Signed-off-by: Dekel Peled <dekelp@mellanox.com>
Acked-by: Viacheslav Ovsiienko <viacheslavo@mellanox.com>
Function mlx5_rxq_get_type() uses the input queue index, without
checking it, as index to the Rx queues array.
If this value is too high, it will result in pointer to memory out
of Rx queues array bounds.
This patch adds check of the input queue index, to verify it is valid.
Fixes: d85c7b5ea5 ("net/mlx5: split hairpin flows")
Signed-off-by: Dekel Peled <dekelp@mellanox.com>
Acked-by: Matan Azrad <matan@mellanox.com>
The variable cleanup was erroneously done before pointer usage.
The cleanup is moved to appropriate place, comment is clarified.
Fixes: 8d72fa6689 ("net/mlx5: share tag between meter and metadata")
Reported-by: Eli Britstein <elibr@mellanox.com>
Signed-off-by: Viacheslav Ovsiienko <viacheslavo@mellanox.com>
Acked-by: Matan Azrad <matan@mellanox.com>
This reverts commit 304ffe576f.
It tried to optimize the amount of the default flow
rules and created it only once on top of the PF representor.
For each FDB rule, the default port ID to match on is like of the port
that triggers the flow.
Hence, the single default rule will not be matched on the VF traffic.
As a result, all the traffic of the VFs will not match to the jump flow
in the root table and will always be forwarded to the representor port.
Revert the commit.
Fixes: 304ffe576f ("net/mlx5: fix condition to create default rule")
Signed-off-by: Matan Azrad <matan@mellanox.com>
Acked-by: Viacheslav Ovsiienko <viacheslavo@mellanox.com>
To avoid wild pointer, pointers should be set to NULL after free them.
Fixes: 1a2fc1799f ("net/ice: reject duplicated flow for flow director")
Fixes: 84dc7a95a2 ("net/ice: enable flow director engine")
Fixes: 0f880c3df1 ("net/ice: add flow director counter resource init/release")
Signed-off-by: Shougang Wang <shougangx.wang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>
Acked-by: Xiaolong Ye <xiaolong.ye@intel.com>
All the counter resources should be cleaned up when teardown.
Fixes: 0f880c3df1 ("net/ice: add flow director counter resource init/release")
Signed-off-by: Shougang Wang <shougangx.wang@intel.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Xiaolong Ye <xiaolong.ye@intel.com>
The removal of FDIR profile should start from the next
of ICE_FLTR_PTYPE_NONF_NONE.
Fixes: 109e8e0624 ("net/ice: configure HW flow director rule")
Signed-off-by: Shougang Wang <shougangx.wang@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>
Acked-by: Xiaolong Ye <xiaolong.ye@intel.com>
To avoid memzone reserve failure and memory leak, following
resources management should be added.
- Check if the FDIR Memzone already exists before reserving.
- Free FDIR memzone when teardown and other failure scenarios.
Fixes: 84dc7a95a2 ("net/ice: enable flow director engine")
Signed-off-by: Shougang Wang <shougangx.wang@intel.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Xiaolong Ye <xiaolong.ye@intel.com>
Correct an error in the IPV6 header bitmask used for programming switch
rules.
Also, change other programming switch headers to use big endian
fields in order to make setting these easier.
Fixes: 04b8ec1ea8 ("net/ice/base: add protocol structures and defines")
Cc: stable@dpdk.org
Signed-off-by: Dan Nowlin <dan.nowlin@intel.com>
Signed-off-by: Wei Zhao <wei.zhao1@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Xiaolong Ye <xiaolong.ye@intel.com>
When compiling with 16B descriptor support enabled, clang compiles gave
an error, complaining that the final parameter of _mm256_blend_epi32()
had to be an immediate value (i.e. compile-time constant):
i40e_rxtx_vec_avx2.c:561:21: error: argument to
'__builtin_ia32_pblendd256' must be a constant integer
__m256i tmp0_1 = _mm256_blend_epi32(fdir_zero_mask,
^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
While it appears that GCC was able to convert the constant variable
value "fdir_blend_mask" into the blend call, clang was not doing so. To
guarantee the use of an immediate we convert the variable value to a
"#define".
Fixes: 7d087a0a8b ("net/i40e: support flow director on AVX Rx")
Signed-off-by: Bruce Richardson <bruce.richardson@intel.com>
Acked-by: Xiaolong Ye <xiaolong.ye@intel.com>
Fix iavf vf_checksum_sw case fail in X710/XXV710, set bit2 to 1
of CMD field in Tx descriptor of AVX Tx path according to Spec.
Fixes: af0c246a38 ("net/iavf: enable AVX2 for iavf")
Signed-off-by: Leyi Rong <leyi.rong@intel.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
Order intermediate VSIG list correct in order to correctly match
existing VSIG lists.
When overriding pre-existing TCAM entries, properly delete the existing
entry and remove it from the change/update list.
Fixes: 51d04e4933 ("net/ice/base: add flexible pipeline module")
Signed-off-by: Dan Nowlin <dan.nowlin@intel.com>
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Tested-by: Zhirun Yan <zhirun.yan@intel.com>
testpmd will occur infinite loops when device hotplug remove.
We can fix the issue by using the pci generic remove function
Fixes: ac89d46096 ("net/i40e: release port upon close")
Signed-off-by: Chenxu Di <chenxux.di@intel.com>
Acked-by: Xiaolong Ye <xiaolong.ye@intel.com>
testpmd will occur infinite loops when device hotplug remove.
We can fix the issue by using the pci generic remove function
Fixes: f2f4990eff ("net/ixgbe: release port upon close")
Signed-off-by: Chenxu Di <chenxux.di@intel.com>
Acked-by: Xiaolong Ye <xiaolong.ye@intel.com>
This patch fixes core dump issue when entering safe mode with a
wrong ice.pkg. In safe mode, rte_flow is not supported and it
won't initialize any flow engine.
Fixes: 7615a68950 ("net/ice: rework for generic flow enabling")
Signed-off-by: Simei Su <simei.su@intel.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
This patch fixes a kernel driver link status issue by recovering
link status when device stops.
Fixes: e6161345d8 ("net/ice: support link status change")
Cc: stable@dpdk.org
Signed-off-by: Qiming Yang <qiming.yang@intel.com>
Acked-by: Xiaolong Ye <xiaolong.ye@intel.com>
This patch changes RSS rule destroy interface from ice_rem_vsi_rss_cfg()
to ice_rem_rss_cfg(). To coordinate with input set change, it should
destroy a specific flow rule but not all vsi cfg.
Fixes: 5ad3db8d4b ("net/ice: enable advanced RSS")
Signed-off-by: Simei Su <simei.su@intel.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
RSS action validation function checks the queues included in RSS
to make sure they are valid.
A Queue is considered valid if the pointer to the queue (item at
location queue-index of RxQ array) is not a null value.
The queue indices are not checked. If a large value is entered as
queue index, using it as an index in RxQ array will result in a
pointer to memory out of array bounds. If this memory contains a
value which is not null, this queue will be wrongly considered valid.
This patch updates function mlx5_flow_validate_action_rss() with
check of the input queue indices, as done in function
mlx5_flow_validate_action_queue().
Fixes: 23c1d42c71 ("net/mlx5: split flow validation to dedicated function")
Cc: stable@dpdk.org
Signed-off-by: Dekel Peled <dekelp@mellanox.com>
Acked-by: Matan Azrad <matan@mellanox.com>
Host adapter attributes are queried from kernel via multiple
DevX calls. The retrieved data were erroneously overwritten,
the order of querying is fixed.
Fixes: 6bc327b94f ("net/mlx5: fill meter capabilities using DevX")
Signed-off-by: Viacheslav Ovsiienko <viacheslavo@mellanox.com>
Acked-by: Matan Azrad <matan@mellanox.com>
This patch implements use of the API for LRO aggregated packet
max size.
Rx queue create is updated to use the relevant configuration.
Documentation is updated accordingly.
Signed-off-by: Dekel Peled <dekelp@mellanox.com>
Acked-by: Viacheslav Ovsiienko <viacheslavo@mellanox.com>
Acked-by: Matan Azrad <matan@mellanox.com>
The JUMBO frame handling in dpaa2_dev_mtu_set api was not correct.
When frame_size is greater than RTE_ETHER_MAX_LEN, the
intention is to add JUMBO flag in rx offload while it was resetting
all other flags other than JUMBO as AND operator was used instead of OR.
Fixes: 0ebce6129b ("net/dpaa2: support new ethdev offload APIs")
Cc: stable@dpdk.org
Signed-off-by: Sachin Saxena <sachin.saxena@nxp.com>
Reviewed-by: Gagandeep Singh <g.singh@nxp.com>
Allow to configure the default MAC address of a VF
via its representor port in the host.
An API was proposed to specify explicitly the VF as a
target: https://patches.dpdk.org/patch/62176/
It has been rejected by the technical board in order to
keep compatibility with behavior in Intel PMDs.
http://mails.dpdk.org/archives/dev/2019-November/150588.html
Signed-off-by: Thomas Monjalon <thomas@monjalon.net>
Signed-off-by: Raslan Darawsheh <rasland@mellanox.com>
Acked-by: Viacheslav Ovsiienko <viacheslavo@mellanox.com>
Add DEV_RX_OFFLOAD_RSS_HASH flag for all PMDs that support RSS hash
delivery.
Signed-off-by: Pavan Nikhilesh <pbhagavatula@marvell.com>
Reviewed-by: Andrew Rybchenko <arybchenko@solarflare.com>
Reviewed-by: Hemant Agrawal <hemant.agrawal@nxp.com>
Acked-by: Jerin Jacob <jerinj@marvell.com>
Acked-by: Ajit Khaparde <ajit.khaparde@broadcom.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
Add the doxygen for ice protocol extraction feature APIs.
Signed-off-by: Haiyue Wang <haiyue.wang@intel.com>
Reviewed-by: Xiaolong Ye <xiaolong.ye@intel.com>
The original design is to use rte_mbuf::udata64 to save the metadata of
protocol extraction which has network protocol data fields and type, a
private API is used to decode this metadata.
Use the dynamic mbuf field and flags to register the needed fields in
mbuf, to avoid overwriting 'rte_mbuf::udata64', since the application
may use it. Now the protocol extraction metadate is saved into dynamic
mbuf field with 4B size, and its type and validity is indicated by the
related dynamic mbuf flags in 'rte_mbuf::ol_flags'.
Signed-off-by: Haiyue Wang <haiyue.wang@intel.com>
Reviewed-by: Xiaolong Ye <xiaolong.ye@intel.com>
Tag action for flow mark/flag could be reused by different flows.
When creating a new flow with mark, the existing tag resources will
be traversed in order to confirm if the action is already created.
If only one linked list is used, the searching rate will drop
significantly with the number of tag actions increasing.
By using a hash lists table, it will speed up the searching process
and in the meanwhile, the memory consumption won't be large if only
a small number tag action resources are created(compared to other
hash table implementations). The list heads array size could be
optimized with some extendable hash table in the future.
Signed-off-by: Bing Zhao <bingz@mellanox.com>
Acked-by: Viacheslav Ovsiienko <viacheslavo@mellanox.com>
Matchers are created on the specific table. If a single linked list
is used to store these, then the finding process might be the
bottleneck when there are a lot of different flow matchers on a
huge amount of tables. The matchers could be move into the table
data resource structure in order to reduce the comparison times
when finding.
Signed-off-by: Bing Zhao <bingz@mellanox.com>
Acked-by: Viacheslav Ovsiienko <viacheslavo@mellanox.com>
Jump object is associated with table object, so there is no need to
use a single linked list to store it. All the jump objects could be
put together with related flow tables.
Signed-off-by: Bing Zhao <bingz@mellanox.com>
Acked-by: Viacheslav Ovsiienko <viacheslavo@mellanox.com>
In the current flow tables organization, arrays are used. This is
fast for searching, creating related object that will be used in
flow creation. But it introduces some limitation to the table index.
Then we can reorganize the flow tables information with hash list.
When using hash list, there is no need to maintain three arrays for
NIC TX, RX and FDB tables object information.
This attribute could be used together with the table ID to generate
a 64-bits key that is unique for the hash list insertion, lookup and
deletion.
Signed-off-by: Bing Zhao <bingz@mellanox.com>
Acked-by: Viacheslav Ovsiienko <viacheslavo@mellanox.com>
The rdma core library can map doorbell register in two ways,
depending on the environment variable "MLX5_SHUT_UP_BF":
- as regular cached memory, the variable is either missing or
set to zero. This type of mapping may cause the significant
doorbell register writing latency and requires explicit
memory write barrier to mitigate this issue and prevent
write combining.
- as non-cached memory, the variable is present and set to
not "0" value. This type of mapping may cause performance
impact under heavy loading conditions but the explicit write
memory barrier is not required and it may improve core
performance.
The new devarg is introduced "tx_db_nc", if this parameter is
set to zero, the doorbell register is forced to be mapped to
cached memory and requires explicit memory barrier after
writing to. If "tx_db_nc" is set to non-zero value the doorbell
will be mapped as non-cached memory, not requiring the memory
barrier. If "tx_db_nc" is missing the behaviour will be defined
by presence of "MLX5_SHUT_UP_BF" in environment. If variable
is missed the default value zero will be set for ARM64 hosts
and one for others.
In run time the code checks the mapping type and provides the
memory barrier after writing to tx doorbell register if it is
needed. The mapping type is extracted directly from the
uar_mmap_offset field in the queue properties.
Fixes: 18a1c20044 ("net/mlx5: implement Tx burst template")
Cc: stable@dpdk.org
Signed-off-by: Viacheslav Ovsiienko <viacheslavo@mellanox.com>
Acked-by: Matan Azrad <matan@mellanox.com>
Free the HW tables during dev_close.
Otherwise there will be two issues:
1. Memory won't be freed if the device is detached.
2. Driver can't be initialized correctly after device reset.
Fixes: a4c8c48fe3 ("net/ice: load OS default package")
Cc: stable@dpdk.org
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Xiaolong Ye <xiaolong.ye@intel.com>
Set vlan tpid is not supported by ice hardware. Delete driver code
that doesn't work.
Signed-off-by: Tao Zhu <taox.zhu@intel.com>
Acked-by: Qiming Yang <qiming.yang@intel.com>
Acked-by: Xiaolong Ye <xiaolong.ye@intel.com>
If the switch/fdir/hash module can't resolve a correct parser,
it should return error.
Fixes: 47d460d632 ("net/ice: rework switch filter")
Fixes: efc16c6214 ("net/ice: support flow director GTPU tunnel")
Fixes: 5ad3db8d4b ("net/ice: enable advanced RSS")
Signed-off-by: Simei Su <simei.su@intel.com>
Acked-by: Qi Zhang <qi.z.zhang@intel.com>
Acked-by: Xiaolong Ye <xiaolong.ye@intel.com>
To support multi-segment packet sending the Tx datapath
DEV_TX_OFFLOAD_MULTI_SEGS offload must be configured.
In debug configuration the asserts arise if the multi-segment
packet is being sent and no DEV_TX_OFFLOAD_MULTI_SEGS is set.
It was found that in some execution paths asserts were missed,
this patch adds ones.
Fixes: 18a1c20044 ("net/mlx5: implement Tx burst template")
Cc: stable@dpdk.org
Signed-off-by: Viacheslav Ovsiienko <viacheslavo@mellanox.com>
Acked-by: Matan Azrad <matan@mellanox.com>
When the port is closed or program exits ungraceful, the meter rulers
should be flushed after the flow destroyed.
Signed-off-by: Suanming Mou <suanmingm@mellanox.com>
Acked-by: Matan Azrad <matan@mellanox.com>
In the meter flow split, metadata flow will be as the sub flow of meter
suffix flow. In meter suffix flow, there is already a unique id tag
exist as for the meter prefix and suffix flow match.
Make metadata feature and meter both share the unique id tag for match.
Signed-off-by: Suanming Mou <suanmingm@mellanox.com>
Acked-by: Matan Azrad <matan@mellanox.com>
The flow with meter action will be divided to three sub flows, the
prefix flow, the meter flow and the suffix flow.
For these three sub flows, as the prefix flow and meter flow have the
meter color match. In order the make the packet from prefix flow to
match with the suffix flow, an extra metadata register is allocated.
The prefix flow will add a unique id to the register and the suffix
flow matches on that unique id.
As RSS will also divided the flow to several sub flows, flow with meter
will be divided as the sub flow of the RSS sub flows if have as below:
Original flow ->
RSS sub flow 1 ->
Meter sub flow 1 (Contain three sub flows.)
RSS sub flow 2 ->
Meter sub flow 2 (Contain three sub flows.)
......
RSS sub flow n ->
Meter sub flow n (Contain three sub flows.)
The metadata feature flow will be split as the sub flow of the meter
suffix flow.
Signed-off-by: Suanming Mou <suanmingm@mellanox.com>
Acked-by: Matan Azrad <matan@mellanox.com>
Add meter flow action support in flow validate and translate.
Signed-off-by: Suanming Mou <suanmingm@mellanox.com>
Acked-by: Matan Azrad <matan@mellanox.com>
Add the meter attach and detach for the flow create.
When create the flow with meter, first try to find any created meter
action matches the flow meter id. If the meter action is already
created, just attach to it and increase the ref_cnt. If not, create
one.
For the dettach, decrease the ref_cnt, destroy the meter action while
the ref_cnt decreased to zero.
Signed-off-by: Suanming Mou <suanmingm@mellanox.com>
Acked-by: Matan Azrad <matan@mellanox.com>
This commit add the meter statistics read and update to check the meter
statistics.
New internal functions in rte_mtr_ops callback:
1. stats_update()
2. stats_read()
Signed-off-by: Suanming Mou <suanmingm@mellanox.com>
Acked-by: Matan Azrad <matan@mellanox.com>
Add count action to meter for metering packet statistics. All the
packets be colored and dropped will be recorded.
Signed-off-by: Suanming Mou <suanmingm@mellanox.com>
Acked-by: Matan Azrad <matan@mellanox.com>
Expose the flow counter management mechanism for other components to
use.
Signed-off-by: Suanming Mou <suanmingm@mellanox.com>
Acked-by: Matan Azrad <matan@mellanox.com>
This commit add the meter profile update support.
New internal function in rte_mtr_ops callback:
1. meter_profile_update()
Signed-off-by: Suanming Mou <suanmingm@mellanox.com>
Acked-by: Matan Azrad <matan@mellanox.com>
This commit add meter enable and disable supoort.
New internal functions in rte_mtr_ops callback:
1. meter_enable()
2. meter_disable()
The meter_enable() enables the meter action and the meter_disable()
disables the meter action.
Signed-off-by: Suanming Mou <suanmingm@mellanox.com>
Acked-by: Matan Azrad <matan@mellanox.com>
This commit add the meter action creation to the glue code.
Signed-off-by: Suanming Mou <suanmingm@mellanox.com>
Acked-by: Matan Azrad <matan@mellanox.com>
This commit add the basic meter operations for meter create and destroy.
New internal functions in rte_mtr_ops callback:
1. create()
2. destroy()
The create() callback will create the corresponding flow rules on the
meter table.
The destroy() callback destroys the flow rules on the meter table.
Signed-off-by: Suanming Mou <suanmingm@mellanox.com>
Acked-by: Matan Azrad <matan@mellanox.com>
This commit create the color rules on the meter table for the packets.
As the prefix flow with meter action colors the packets, the packets
are transferred to the meter table with meter color match flows. Here
we create the flow rules with green yellow red actions on the meter
table. Packets match the color will be processed by the related color
flow rule.
Signed-off-by: Suanming Mou <suanmingm@mellanox.com>
Acked-by: Matan Azrad <matan@mellanox.com>
This commit prepare the meter table and suffix table.
A flow with meter will be split to three flows. The three flows are
created on differnet tables. The packets transfer between the flows
on the tables as below:
Prefix flow -> Meter flow -> Suffix flow
Prefix flow does the user defined match and the meter action. The meter
action colors the packet and set its destination to meter table to be
processed by the meter flow.
The meter flow judges if the packet can be passed or not. If packet can
be passed, it will be transferred to the suffix table.
The suffix flow on the suffix table will apply the left user defined
actions to the packet.
The ingress egress and transfer all have the independent meter and
suffix tables.
Signed-off-by: Suanming Mou <suanmingm@mellanox.com>
Acked-by: Matan Azrad <matan@mellanox.com>
The add meter profile should be validated if it is valid or has been add
to the list. Invalid and exist profile should not be add to the list.
Signed-off-by: Suanming Mou <suanmingm@mellanox.com>
Acked-by: Matan Azrad <matan@mellanox.com>
This commit add the support of meter profile add and delete operations.
New internal functions in rte_mtr_ops callback:
1. meter_profile_add()
2. meter_profile_delete()
Only RTE_MTR_SRTCM_RFC2697 algorithm is supported and can be added. To
add other algorithm will report an error.
Signed-off-by: Suanming Mou <suanmingm@mellanox.com>
Acked-by: Matan Azrad <matan@mellanox.com>
Meter need the metadata REG_C to have the color match between the prefix
flow and the meter flow.
As the user define or metadata feature will both use the REG_C in the
suffix flow, the color match register meter uses will not impact the
register use in the later sub flow.
Another case is that tag is add before meter flow. In this case, meter
should not touch the register the tag action is using. To avoid that
case, meter should reserve the REG_C's used by user defined MLX5_APP_TAG.
Signed-off-by: Suanming Mou <suanmingm@mellanox.com>
Acked-by: Matan Azrad <matan@mellanox.com>
This commit add the support of fill and get the meter capabilities
from DevX.
Support items:
1. The srTCM color bind mode.
2. Meter share with multiple flows.
3. Action drop.
The color aware mode and multiple meter chaining in a flow are not
supported.
New internal function in rte_mtr_ops callback:
1. capabilities_get()
Signed-off-by: Suanming Mou <suanmingm@mellanox.com>
Acked-by: Matan Azrad <matan@mellanox.com>
Previous patch added creation of a default flow rule on port start.
Rule is created under the condition that device is in eswitch mode,
and is not a VF, to make sure rule is created only once.
In Bluefield, where PF representor is used, this condition is not
sufficient. Rule is created twice, causing loss of traffic.
This patch updates this condition, adding check that device is also
not a representor.
Fixes: b67b4ecbde ("net/mlx5: skip table zero to improve insertion rate")
Signed-off-by: Dekel Peled <dekelp@mellanox.com>
Acked-by: Viacheslav Ovsiienko <viacheslavo@mellanox.com>
In current implementation, jump action is allowed only if target
group is higher than the current flow group,
This patch updates function flow_dv_validate_action_jump() to allow
jump action if target group is higher or lower than the current flow
group.
Target group equal to current flow group is still rejected.
Signed-off-by: Dekel Peled <dekelp@mellanox.com>
Acked-by: Viacheslav Ovsiienko <viacheslavo@mellanox.com>
While reg_c[meta] can be copied to reg_b simply by modify-header
action (it is supported by hardware), it is not possible to copy
reg_c[mark] to the STE flow_tag as flow_tag is not a metadata
register and this is not supported by hardware. Instead, it
should be manually set by a flow per each unique MARK ID. For
this purpose, there should be a dedicated flow table -
RX_CP_TBL and all the Rx flow should pass by the table
to properly copy values from the register to flow tag field.
And for each MARK action, a copy flow should be added
to RX_CP_TBL according to the MARK ID like:
(if reg_c[mark] == mark_id),
flow_tag := mark_id / reg_b := reg_c[meta] / jump to RX_ACT_TBL
For SET_META action, there can be only one default flow like:
reg_b := reg_c[meta] / jump to RX_ACT_TBL
Signed-off-by: Yongseok Koh <yskoh@mellanox.com>
Signed-off-by: Viacheslav Ovsiienko <viacheslavo@mellanox.com>
Acked-by: Matan Azrad <matan@mellanox.com>
Values set by MARK and SET_META actions should be carried over
to the VF representor in case of flow miss on Tx path. However,
as not all metadata registers are preserved across the different
domains (NIC Rx/Tx and E-Switch FDB), as a workaround, those
values should be carried by reg_c's which are preserved across
domains and copied to STE flow_tag (MARK) and reg_b (META) fields
in the last stage of flow steering, in order to scatter those
values to flow_tag and flow_table_metadata of CQE.
While reg_c[meta] can be copied to reg_b simply by modify-header
action (it is supported by hardware), it is not possible to copy
reg_c[mark] to the STE flow_tag as flow_tag is not a metadata
register and this is not supported by hardware. Instead, it should
be manually set by a flow per MARK ID. For this purpose, there
should be a dedicated flow table - RX_CP_TBL and all the Rx flow
should pass by the table to properly copy values.
As the last action of Rx flow steering must be a terminal action
such as QUEUE, RSS or DROP, if a user flow has Q/RSS action, the
flow must be split in order to pass by the RX_CP_TBL. And the
remained Q/RSS action will be performed by another dedicated
action table - RX_ACT_TBL.
For example, for an ingress flow:
pattern,
actions_having_QRSS
it must be split into two flows. The first one is,
pattern,
actions_except_QRSS / copy (reg_c[2] := flow_id) / jump to RX_CP_TBL
and the second one in RX_ACT_TBL.
(if reg_c[2] == flow_id),
action_QRSS
where flow_id is uniquely allocated and managed identifier.
This patch implements the Rx flow splitting and build the RX_ACT_TBL.
Also, per each egress flow on NIC Tx, a copy action (reg_c[]= reg_a)
should be added in order to transfer metadata from WQE.
Signed-off-by: Yongseok Koh <yskoh@mellanox.com>
Signed-off-by: Viacheslav Ovsiienko <viacheslavo@mellanox.com>
Acked-by: Matan Azrad <matan@mellanox.com>
The mlx5 hardware has some limitations and flow might
require to be split into multiple internal subflows.
For example this is needed to provide the meter object
sharing between multiple flows or to provide metadata
register copying before final queue/rss action.
The multiple features might require several level of
splitting. For example, hairpin feature splits the
original flow into two ones - rx and tx parts. Then
RSS feature should split rx part into multiple subflows
with extended item sets. Then, metering feature might
require splitting each RSS subflow into meter jump
chain, and then metadata extensive support might
require the final subflows splitting. So, we have
to organize the chain of splitting subroutines to
abstract each level of splitting.
Signed-off-by: Viacheslav Ovsiienko <viacheslavo@mellanox.com>
Acked-by: Matan Azrad <matan@mellanox.com>
META item is supported on both Rx and Tx. 'transfer' attribute
is also supported. SET_META action is also added.
Due to restriction on reg_c[meta], various bit width might be
available. If devarg parameter dv_xmeta_en=1, the META uses
metadata register reg_c[0], which may be required for internal
kernel or firmware needs. In this case PMD queries kernel about
available fields in reg_c[0] and restricts the register usage
accordingly. If devarg parameter dv_xmeta_en=2, the META feature
uses reg_c[1], there should be no limitations on the data width.
However, extensive MEAT feature is currently disabled until
register copy on loopback is supported by forthcoming patches.
Signed-off-by: Yongseok Koh <yskoh@mellanox.com>
Signed-off-by: Viacheslav Ovsiienko <viacheslavo@mellanox.com>
Acked-by: Matan Azrad <matan@mellanox.com>
Flow MARK item is newly supported along with MARK action. MARK
action and item are supported on both Rx and Tx. It works on the
metadata reg_c[] only if extensive flow metadata register is
supported. Without the support, MARK action behaves same as
before - valid only on Rx and no MARK item is valid.
FLAG action is also modified accordingly. FLAG action is
supported on both Rx and Tx via reg_c[] if extensive flow
metadata register is supported.
However, the new MARK/FLAG item and action are currently
disabled until register copy on loopback is supported by
forthcoming patches.
The actual index of engaged metadata reg_c[] register to
support FLAG/MARK actions depends on dv_xmeta_en devarg value.
For extensive metadata mode 1 the reg_c[1] is used and
transitive MARK data width is 24. For extensive metadata mode 2
the reg_c[0] is used and transitive MARK data width might be
restricted to 0 or 16 bits, depending on kernel usage of reg_c[0].
The actual supported width can be discovered by series of trials
with rte_flow_validate().
Signed-off-by: Yongseok Koh <yskoh@mellanox.com>
Signed-off-by: Viacheslav Ovsiienko <viacheslavo@mellanox.com>
Acked-by: Matan Azrad <matan@mellanox.com>
Add support of new rte_flow item and action - TAG and SET_TAG. TAG is
a transient value which can be kept during flow matching.
This is supported through device metadata register reg_c[]. Although
there are 8 registers are available on the current mlx5 device,
some of them can be reserved for firmware or kernel purposes.
The availability should be queried by iterative trial-and-error
mlx5_flow_discover_mreg_c() routine.
Signed-off-by: Yongseok Koh <yskoh@mellanox.com>
Signed-off-by: Viacheslav Ovsiienko <viacheslavo@mellanox.com>
Acked-by: Matan Azrad <matan@mellanox.com>
The NIC might support up to 8 extensive metadata registers.
These registers are supposed to be used by multiple features.
There is register id query routine to allow determine which
register is actually used by specified feature.
Signed-off-by: Viacheslav Ovsiienko <viacheslavo@mellanox.com>
Acked-by: Matan Azrad <matan@mellanox.com>
If the extensive metadata registers are supported,
it can be regarded inclusively that the extensive
metadata support is possible. E.g. metadata register
copy action, supporting 16 modify header actions,
reserving register across different steering domain
(FDB and NIC) and so on.
This patch handles the maximal amount of header modify
actions depending on discovered metadata registers
support.
Signed-off-by: Yongseok Koh <yskoh@mellanox.com>
Signed-off-by: Viacheslav Ovsiienko <viacheslavo@mellanox.com>
Acked-by: Matan Azrad <matan@mellanox.com>
The metadata register reg_c[0] might be used by kernel or
firmware for their internal purposes. The actual used mask
can be queried from the kernel. The remaining bits can be
used by PMD to provide META or MARK feature. The code queries
the mask of reg_c[0] and adjust the resource usage dynamically.
Signed-off-by: Viacheslav Ovsiienko <viacheslavo@mellanox.com>
Acked-by: Matan Azrad <matan@mellanox.com>
The PMD parameter dv_xmeta_en is added to control extensive
metadata support. A nonzero value enables extensive flow
metadata support if device is capable and driver supports it.
This can enable extensive support of MARK and META item of
rte_flow. The newly introduced SET_TAG and SET_META actions
do not depend on dv_xmeta_en parameter, because there is
no compatibility issue for new entities. The dv_xmeta_en is
disabled by default.
There are some possible configurations, depending on parameter
value:
- 0, this is default value, defines the legacy mode, the MARK
and META related actions and items operate only within NIC Tx
and NIC Rx steering domains, no MARK and META information
crosses the domain boundaries. The MARK item is 24 bits wide,
the META item is 32 bits wide.
- 1, this engages extensive metadata mode, the MARK and META
related actions and items operate within all supported steering
domains, including FDB, MARK and META information may cross
the domain boundaries. The ``MARK`` item is 24 bits wide, the
META item width depends on kernel and firmware configurations
and might be 0, 16 or 32 bits. Within NIC Tx domain META data
width is 32 bits for compatibility, the actual width of data
transferred to the FDB domain depends on kernel configuration
and may be vary. The actual supported width can be retrieved
in runtime by series of rte_flow_validate() trials.
- 2, this engages extensive metadata mode, the MARK and META
related actions and items operate within all supported steering
domains, including FDB, MARK and META information may cross
the domain boundaries. The META item is 32 bits wide, the MARK
item width depends on kernel and firmware configurations and
might be 0, 16 or 24 bits. The actual supported width can be
retrieved in runtime by series of rte_flow_validate() trials.
If there is no E-Switch configuration the ``dv_xmeta_en`` parameter is
ignored and the device is configured to operate in legacy mode (0).
Signed-off-by: Yongseok Koh <yskoh@mellanox.com>
Signed-off-by: Viacheslav Ovsiienko <viacheslavo@mellanox.com>
Acked-by: Matan Azrad <matan@mellanox.com>
The metadata registers reg_c provide support for TAG and
SET_TAG features. Although there are 8 registers are available
on the current mlx5 devices, some of them can be reserved.
The availability should be queried by iterative trial-and-error
implemented by mlx5_flow_discover_mreg_c() routine.
If reg_c is available, it can be regarded inclusively that
the extensive metadata support is possible. E.g. metadata
register copy action, supporting 16 modify header actions
(instead of 8 by default) preserving register across
different domains (FDB and NIC) and so on.
Signed-off-by: Yongseok Koh <yskoh@mellanox.com>
Signed-off-by: Viacheslav Ovsiienko <viacheslavo@mellanox.com>
Acked-by: Matan Azrad <matan@mellanox.com>
There are some renaming:
- in the DV flow engine overall: flow_d_* -> flow_dv_*
- in flow_dv_translate(): res -> mhdr_res
Signed-off-by: Yongseok Koh <yskoh@mellanox.com>
Signed-off-by: Viacheslav Ovsiienko <viacheslavo@mellanox.com>
Acked-by: Matan Azrad <matan@mellanox.com>
Introduce the dedicated matcher register field setup routine.
Update the code to use this unified one.
Signed-off-by: Yongseok Koh <yskoh@mellanox.com>
Signed-off-by: Viacheslav Ovsiienko <viacheslavo@mellanox.com>
Acked-by: Matan Azrad <matan@mellanox.com>
Update flow creation/destroy functions for future reuse.
List operations can be skipped inside functions and done
separately out of flow creation.
Signed-off-by: Yongseok Koh <yskoh@mellanox.com>
Signed-off-by: Viacheslav Ovsiienko <viacheslavo@mellanox.com>
Acked-by: Matan Azrad <matan@mellanox.com>
Some rte_flow fields which are local to subflows have been moved to
mlx5_flow structure. RSS attributes are grouped by mlx5_flow_rss structure.
tag_resource is moved to mlx5_flow_dv structure.
Signed-off-by: Yongseok Koh <yskoh@mellanox.com>
Signed-off-by: Viacheslav Ovsiienko <viacheslavo@mellanox.com>
Acked-by: Matan Azrad <matan@mellanox.com>
Add flow metadata register copy action which is supported through modify
header command. As it is an internal action, not exposed to users, item
type (MLX5_RTE_FLOW_ACTION_TYPE_COPY_MREG) is negative value. This can be
used when creating PMD internal subflows.
Signed-off-by: Yongseok Koh <yskoh@mellanox.com>
Signed-off-by: Viacheslav Ovsiienko <viacheslavo@mellanox.com>
Acked-by: Matan Azrad <matan@mellanox.com>
When composing device command for modify header action, provided mask
should be taken more accurate into account thus length and offset
in action should be set accordingly at precise bit-wise boundaries.
For the future use, metadata register copy action is also added.
Signed-off-by: Yongseok Koh <yskoh@mellanox.com>
Signed-off-by: Viacheslav Ovsiienko <viacheslavo@mellanox.com>
Acked-by: Matan Azrad <matan@mellanox.com>
Public API RTE_FLOW_ACTION_TYPE_TAG and RTE_FLOW_ITEM_TYPE_TAG
present data in host-endian format, as all metadata related
entities. The internal mlx5 tag related action and item should
use the same endianness to be conformed.
Signed-off-by: Viacheslav Ovsiienko <viacheslavo@mellanox.com>
Acked-by: Matan Azrad <matan@mellanox.com>
