diff options
| author | Wojciech Drewek <wojciech.drewek@intel.com> | 2021-10-26 12:38:40 +0200 |
|---|---|---|
| committer | Tony Nguyen <anthony.l.nguyen@intel.com> | 2022-01-06 10:15:09 -0800 |
| commit | c1e5da5dd4659753407534e323c0579aa79c3bd1 (patch) | |
| tree | 4872b8ee25a03f445473eb47c8eb44c469b9ad5f /drivers/net/ethernet/intel/ice/ice_main.c | |
| parent | c36a2b97162720ff373985f13d819e05f1ba128d (diff) | |
| download | lwn-c1e5da5dd4659753407534e323c0579aa79c3bd1.tar.gz lwn-c1e5da5dd4659753407534e323c0579aa79c3bd1.zip | |
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>
Diffstat (limited to 'drivers/net/ethernet/intel/ice/ice_main.c')
| -rw-r--r-- | drivers/net/ethernet/intel/ice/ice_main.c | 24 |
1 files changed, 24 insertions, 0 deletions
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index e29176889c23..30814435f779 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -472,6 +472,25 @@ static void ice_pf_dis_all_vsi(struct ice_pf *pf, bool locked) } /** + * ice_clear_sw_switch_recipes - clear switch recipes + * @pf: board private structure + * + * Mark switch recipes as not created in sw structures. There are cases where + * rules (especially advanced rules) need to be restored, either re-read from + * hardware or added again. For example after the reset. 'recp_created' flag + * prevents from doing that and need to be cleared upfront. + */ +static void ice_clear_sw_switch_recipes(struct ice_pf *pf) +{ + struct ice_sw_recipe *recp; + u8 i; + + recp = pf->hw.switch_info->recp_list; + for (i = 0; i < ICE_MAX_NUM_RECIPES; i++) + recp[i].recp_created = false; +} + +/** * ice_prepare_for_reset - prep for reset * @pf: board private structure * @reset_type: reset type requested @@ -501,6 +520,11 @@ ice_prepare_for_reset(struct ice_pf *pf, enum ice_reset_req reset_type) ice_for_each_vf(pf, i) ice_set_vf_state_qs_dis(&pf->vf[i]); + if (ice_is_eswitch_mode_switchdev(pf)) { + if (reset_type != ICE_RESET_PFR) + ice_clear_sw_switch_recipes(pf); + } + /* release ADQ specific HW and SW resources */ vsi = ice_get_main_vsi(pf); if (!vsi) |