#
19b39cae |
|
24-Oct-2023 |
Michal Swiatkowski <michal.swiatkowski@linux.intel.com> |
ice: reserve number of CP queues Rebuilding CP VSI each time the PR is created drastically increase the time of maximum VFs creation. Add function to reserve number of CP queues to deal with this problem. Use the same function to decrease number of queues in case of removing VFs. Assume that caller of ice_eswitch_reserve_cp_queues() will also call ice_eswitch_attach/detach() correct number of times. Still one by one PR adding is handy for VF resetting routine. Reviewed-by: Wojciech Drewek <wojciech.drewek@intel.com> Signed-off-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com> Tested-by: Sujai Buvaneswaran <sujai.buvaneswaran@intel.com> Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
|
#
fff292b4 |
|
24-Oct-2023 |
Michal Swiatkowski <michal.swiatkowski@linux.intel.com> |
ice: add VF representors one by one Implement adding representors one by one. Always set switchdev environment when first representor is being added and clear environment when last one is being removed. Basic switchdev configuration remains the same. Code related to creating and configuring representor was changed. Instead of setting whole representors in one function handle only one representor in setup function. The same with removing representors. Stop representors when new one is being added or removed. Stop means, disabling napi, stopping traffic and removing slow path rule. It is needed because ::q_id will change after remapping, so each representor will need new rule. When representor are stopped rebuild control plane VSI with one more or one less queue. One more if new representor is being added, one less if representor is being removed. Bridge port is removed during unregister_netdev() call on PR, so there is no need to call it from driver side. After that do remap new queues to correct vector. At the end start all representors (napi enable, start queues, add slow path rule). Reviewed-by: Piotr Raczynski <piotr.raczynski@intel.com> Reviewed-by: Wojciech Drewek <wojciech.drewek@intel.com> Signed-off-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com> Tested-by: Sujai Buvaneswaran <sujai.buvaneswaran@intel.com> Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
|
#
604283e9 |
|
24-Oct-2023 |
Michal Swiatkowski <michal.swiatkowski@linux.intel.com> |
ice: make representor code generic Representor code needs to be independent from specific device type, like in this case VF. Make generic add / remove representor function and specific add VF / rem VF function. New device types will follow this scheme. In bridge offload code there is a need to get representor pointer based on VSI. Implement helper function to achieve that. Reviewed-by: Piotr Raczynski <piotr.raczynski@intel.com> Reviewed-by: Wojciech Drewek <wojciech.drewek@intel.com> Signed-off-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com> Tested-by: Sujai Buvaneswaran <sujai.buvaneswaran@intel.com> Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
|
#
e4c46abc |
|
24-Oct-2023 |
Michal Swiatkowski <michal.swiatkowski@linux.intel.com> |
ice: remove VF pointer reference in eswitch code Make eswitch code generic by removing VF pointer reference in functions. It is needed to support eswitch mode for other type of devices. Previously queue id used for Rx was based on VF number. Use ::q_id saved in port representor instead. After adding or removing port representor ::q_id value can change. It isn't good idea to iterate over representors list using this value. Use xa_find starting from the first one instead to get next port representor to remap. The number of port representors has to be equal to ::num_rx/tx_q. Warn if it isn't true. Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com> Reviewed-by: Wojciech Drewek <wojciech.drewek@intel.com> Reviewed-by: Jacob Keller <jacob.e.keller@intel.com> Signed-off-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com> Tested-by: Sujai Buvaneswaran <sujai.buvaneswaran@intel.com> Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
|
#
0ef4479d |
|
07-Apr-2023 |
Michal Swiatkowski <michal.swiatkowski@linux.intel.com> |
ice: use src VSI instead of src MAC in slow-path The use of a source MAC to direct packets from the VF to the corresponding port representor is only ok if there is only one MAC on a VF. To support this functionality when the number of MACs on a VF is greater, it is necessary to match a source VSI instead of a source MAC. Let's use the new switch API that allows matching on metadata. If MAC isn't used in match criteria there is no need to handle adding rule after virtchnl command. Instead add new rule while port representor is being configured. Remove rule_added field, checking for sp_rule can be used instead. Remove also checking for switchdev running in deleting rule as it can be called from unroll context when running flag isn't set. Checking for sp_rule covers both context (with and without running flag). Rules are added in eswitch configuration flow, so there is no need to have replay function. Signed-off-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com> Reviewed-by: Piotr Raczynski <piotr.raczynski@intel.com> Reviewed-by: Simon Horman <simon.horman@corigine.com> Reviewed-by: Leon Romanovsky <leonro@nvidia.com> Tested-by: Sujai Buvaneswaran <sujai.buvaneswaran@intel.com> Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
|
#
aacca7a8 |
|
01-Apr-2022 |
Maciej Fijalkowski <maciej.fijalkowski@intel.com> |
ice: allow creating VFs for !CONFIG_NET_SWITCHDEV Currently for !CONFIG_NET_SWITCHDEV kernel builds it is not possible to create VFs properly as call to ice_eswitch_configure() returns -EOPNOTSUPP for us. This is because CONFIG_ICE_SWITCHDEV depends on CONFIG_NET_SWITCHDEV. Change the ice_eswitch_configure() implementation for !CONFIG_ICE_SWITCHDEV to return 0 instead -EOPNOTSUPP and let ice_ena_vfs() finish its work properly. CC: Grzegorz Nitka <grzegorz.nitka@intel.com> Fixes: 1a1c40df2e80 ("ice: set and release switchdev environment") Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com> Signed-off-by: Michal Swiatkowski <michal.swiatkowski@intel.com> Tested-by: Konrad Jankowski <konrad0.jankowski@intel.com> Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
|
#
c1e5da5d |
|
25-Oct-2021 |
Wojciech Drewek <wojciech.drewek@intel.com> |
ice: improve switchdev's slow-path In current switchdev implementation, every VF PR is assigned to individual ring on switchdev ctrl VSI. For slow-path traffic, there is a mapping VF->ring done in software based on src_vsi value (by calling ice_eswitch_get_target_netdev function). With this change, HW solution is introduced which is more efficient. For each VF, src MAC (VF's MAC) filter will be created, which forwards packets to the corresponding switchdev ctrl VSI queue based on src MAC address. This filter has to be removed and then replayed in case of resetting one VF. Keep information about this rule in repr->mac_rule, thanks to that we know which rule has to be removed and replayed for a given VF. In case of CORE/GLOBAL all rules are removed automatically. We have to take care of readding them. This is done by ice_replay_vsi_adv_rule. When driver leaves switchdev mode, remove all advanced rules from switchdev ctrl VSI. This is done by ice_rem_adv_rule_for_vsi. Flag repr->rule_added is needed because in some cases reset might be triggered before VF sends request to add MAC. Co-developed-by: Grzegorz Nitka <grzegorz.nitka@intel.com> Signed-off-by: Grzegorz Nitka <grzegorz.nitka@intel.com> Signed-off-by: Wojciech Drewek <wojciech.drewek@intel.com> Tested-by: Sandeep Penigalapati <sandeep.penigalapati@intel.com> Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
|
#
e72bba21 |
|
19-Aug-2021 |
Maciej Fijalkowski <maciej.fijalkowski@intel.com> |
ice: split ice_ring onto Tx/Rx separate structs While it was convenient to have a generic ring structure that served both Tx and Rx sides, next commits are going to introduce several Tx-specific fields, so in order to avoid hurting the Rx side, let's pull out the Tx ring onto new ice_tx_ring and ice_rx_ring structs. Rx ring could be handled by the old ice_ring which would reduce the code churn within this patch, but this would make things asymmetric. Make the union out of the ring container within ice_q_vector so that it is possible to iterate over newly introduced ice_tx_ring. Remove the @size as it's only accessed from control path and it can be calculated pretty easily. Change definitions of ice_update_ring_stats and ice_fetch_u64_stats_per_ring so that they are ring agnostic and can be used for both Rx and Tx rings. Sizes of Rx and Tx ring structs are 256 and 192 bytes, respectively. In Rx ring xdp_rxq_info occupies its own cacheline, so it's the major difference now. Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com> Tested-by: Gurucharan G <gurucharanx.g@intel.com> Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
|
#
f5396b8a |
|
19-Aug-2021 |
Grzegorz Nitka <grzegorz.nitka@intel.com> |
ice: switchdev slow path Slow path means allowing packet to go from uplink to representor and from representor to correct VF on Rx site and from VF to representor and to uplink on Tx site. To accomplish this driver, has to set correct Tx descriptor. When packet is sent from representor to VF, destination should be set to VF VSI. When packet is sent from uplink port destination should be uplink to bypass switch infrastructure and send packet outside. On Rx site driver should check source VSI field from Rx descriptor and based on that forward packed to correct netdev. To allow this there is a target netdevs table in control plane VSI struct. Co-developed-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com> Signed-off-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com> Signed-off-by: Grzegorz Nitka <grzegorz.nitka@intel.com> Tested-by: Sandeep Penigalapati <sandeep.penigalapati@intel.com> Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
|
#
b3be918d |
|
19-Aug-2021 |
Grzegorz Nitka <grzegorz.nitka@intel.com> |
ice: rebuild switchdev when resetting all VFs As resetting all VFs behaves mostly like creating new VFs also eswitch infrastructure has to be recreated. The easiest way to do that is to rebuild eswitch after resetting VFs. Implement helper functions to start and stop all representors queues. This is used to disable traffic on port representors. In rebuild path: - NAPI has to be disabled - eswitch environment has to be set up - new port representors have to be created, because the old one had pointer to not existing VFs - new control plane VSI ring should be remapped - NAPI hast to be enabled - rxdid has to be set to FLEX_NIC_2, because this descriptor id support source_vsi, which is needed on control plane VSI queues - port representors queues have to be started Signed-off-by: Grzegorz Nitka <grzegorz.nitka@intel.com> Tested-by: Sandeep Penigalapati <sandeep.penigalapati@intel.com> Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
|
#
1c54c839 |
|
19-Aug-2021 |
Grzegorz Nitka <grzegorz.nitka@intel.com> |
ice: enable/disable switchdev when managing VFs Only way to enable switchdev is to create VFs when the eswitch mode is set to switchdev. Check if correct mode is set and enable switchdev in function which creating VFs. Disable switchdev when user change number of VFs to 0. Changing eswitch mode back to legacy when VFs are created in switchdev mode isn't allowed. As switchdev takes care of managing filter rules, adding new rules on VF is blocked. In case of resetting VF driver has to update pointer in ice_repr struct, because after reset VSI related things can change. Co-developed-by: Wojciech Drewek <wojciech.drewek@intel.com> Signed-off-by: Wojciech Drewek <wojciech.drewek@intel.com> Signed-off-by: Grzegorz Nitka <grzegorz.nitka@intel.com> Tested-by: Sandeep Penigalapati <sandeep.penigalapati@intel.com> Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
|
#
1a1c40df |
|
19-Aug-2021 |
Grzegorz Nitka <grzegorz.nitka@intel.com> |
ice: set and release switchdev environment Switchdev environment has to be set up when user create VFs and eswitch mode is switchdev. Release is done when user delete all VFs. Data path in this implementation is based on control plane VSI. This VSI is used to pass traffic from port representors to corresponding VFs and vice versa. Default TX rule has to be added to forward packet to control plane VSI. This will redirect packets from VFs which don't match other rules to control plane VSI. On RX side default rule is added on uplink VSI to receive all traffic that doesn't match other rules. When setting switchdev environment all other rules from VFs should be removed. Packet to VFs will be forwarded by control plane VSI. As VF without any mac rules can't send any packet because of antispoof mechanism, VSI antispoof should be turned off on each VFs. To send packet from representor to correct VSI, destination VSI field in TX descriptor will have to be filled. Allow that by setting destination override bit in control plane VSI security config. Packet from VFs will be received on control plane VSI. Driver should decide to which netdev forward the packet. Decision is made based on src_vsi field from descriptor. There is a target netdev list in control plane VSI struct which choose netdev based on src_vsi number. Co-developed-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com> Signed-off-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com> Signed-off-by: Grzegorz Nitka <grzegorz.nitka@intel.com> Tested-by: Sandeep Penigalapati <sandeep.penigalapati@intel.com> Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
|
#
3ea9bd5d |
|
19-Aug-2021 |
Michal Swiatkowski <michal.swiatkowski@linux.intel.com> |
ice: support basic E-Switch mode control Write set and get eswitch mode functions used by devlink ops. Use new pf struct member eswitch_mode to track current eswitch mode in driver. Changing eswitch mode is only allowed when there are no VFs created. Create new file for eswitch related code. Add config flag ICE_SWITCHDEV to allow user to choose if switchdev support should be enabled or disabled. Use case examples: - show current eswitch mode ('legacy' is the default one) [root@localhost]# devlink dev eswitch show pci/0000:03:00.1 pci/0000:03:00.1: mode legacy - move to 'switchdev' mode [root@localhost]# devlink dev eswitch set pci/0000:03:00.1 mode switchdev [root@localhost]# devlink dev eswitch show pci/0000:03:00.1 pci/0000:03:00.1: mode switchdev - create 2 VFs [root@localhost]# echo 2 > /sys/class/net/ens4f1/device/sriov_numvfs - unsuccessful attempt to change eswitch mode while VFs are created [root@localhost]# devlink dev eswitch set pci/0000:03:00.1 mode legacy devlink answers: Operation not supported - destroy VFs [root@localhost]# echo 0 > /sys/class/net/ens4f1/device/sriov_numvfs - restore 'legacy' mode [root@localhost]# devlink dev eswitch set pci/0000:03:00.1 mode legacy [root@localhost]# devlink dev eswitch show pci/0000:03:00.1 pci/0000:03:00.1: mode legacy Co-developed-by: Grzegorz Nitka <grzegorz.nitka@intel.com> Signed-off-by: Grzegorz Nitka <grzegorz.nitka@intel.com> Signed-off-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com> Tested-by: Sandeep Penigalapati <sandeep.penigalapati@intel.com> Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
|