event_netdev = netdev_notifier_info_to_dev(ptr); /* not for this netdev */ if (event_netdev != lag->netdev) return;
info = (struct netdev_notifier_bonding_info *)ptr;
bonding_info = &info->bonding_info;
dev = ice_pf_to_dev(lag->pf);
/* interface not active - remove old default VSI rule */ if (bonding_info->slave.state && lag->pf_rx_rule_id) { if (ice_lag_cfg_dflt_fltr(lag, false))
dev_err(dev, "Error removing old default VSI filter\n"); if (ice_lag_cfg_drop_fltr(lag, true))
dev_err(dev, "Error adding new drop filter\n"); return;
}
/* interface becoming active - add new default VSI rule */ if (!bonding_info->slave.state && !lag->pf_rx_rule_id) { if (ice_lag_cfg_dflt_fltr(lag, true))
dev_err(dev, "Error adding new default VSI filter\n"); if (lag->lport_rule_idx && ice_lag_cfg_drop_fltr(lag, false))
dev_err(dev, "Error removing old drop filter\n");
}
}
switch (lag->role) { case ICE_LAG_NONE:
role = "NONE"; break; case ICE_LAG_PRIMARY:
role = "PRIMARY"; break; case ICE_LAG_BACKUP:
role = "BACKUP"; break; case ICE_LAG_UNSET:
role = "UNSET"; break; default:
role = "ERROR";
}
tc_node = ice_sched_get_tc_node(pi, tc); if (!tc_node) {
dev_warn(dev, "Failure to find TC node for LAG move\n"); return parent;
}
aggnode = ice_sched_get_agg_node(pi, tc_node, ICE_DFLT_AGG_ID); if (!aggnode) {
dev_warn(dev, "Failure to find aggregate node for LAG move\n"); return parent;
}
for (n = aggl + 1; n < vsil; n++)
num_nodes[n] = 1;
for (n = 0; n < aggnode->num_children; n++) {
parent = ice_sched_get_free_vsi_parent(hw, aggnode->children[n],
num_nodes); if (parent) return parent;
}
/* if free parent not found - add one */
parent = aggnode; for (n = aggl + 1; n < vsil; n++) {
u16 num_nodes_added;
u32 first_teid; int err;
err = ice_sched_add_nodes_to_layer(pi, tc_node, parent, n,
num_nodes[n], &first_teid,
&num_nodes_added); if (err || num_nodes[n] != num_nodes_added) return NULL;
if (num_nodes_added)
parent = ice_sched_find_node_by_teid(tc_node,
first_teid); else
parent = parent->children[0]; if (!parent) {
dev_warn(dev, "Failure to add new parent for LAG move\n"); return parent;
}
}
ctx = ice_get_vsi_ctx(&lag->pf->hw, vsi_num); if (!ctx) {
dev_warn(dev, "Unable to locate VSI context for LAG failover\n"); return;
}
/* check to see if this VF is enabled on this TC */ if (!ctx->sched.vsi_node[tc]) return;
/* locate HW struct for destination port */
new_hw = ice_lag_find_hw_by_lport(lag, newport); if (!new_hw) {
dev_warn(dev, "Unable to locate HW struct for LAG node destination\n"); return;
}
numq = ctx->num_lan_q_entries[tc];
teid = ctx->sched.vsi_node[tc]->info.node_teid;
tmp_teid = le32_to_cpu(teid);
parent_teid = ctx->sched.vsi_node[tc]->info.parent_teid; /* if no teid assigned or numq == 0, then this TC is not active */ if (!tmp_teid || !numq) return;
/* suspend VSI subtree for Traffic Class "tc" on *thisVF'sVSI
*/ if (ice_sched_suspend_resume_elems(&lag->pf->hw, 1, &tmp_teid, true))
dev_dbg(dev, "Problem suspending traffic for LAG node move\n");
/* reconfigure all VF's queues on this Traffic Class *tonewport
*/
qbuf_size = struct_size(qbuf, queue_info, numq);
qbuf = kzalloc(qbuf_size, GFP_KERNEL); if (!qbuf) {
dev_warn(dev, "Failure allocating memory for VF queue recfg buffer\n"); goto resume_traffic;
}
/* add the per queue info for the reconfigure command buffer */
valq = ice_lag_qbuf_recfg(&lag->pf->hw, qbuf, vsi_num, numq, tc); if (!valq) {
dev_dbg(dev, "No valid queues found for LAG failover\n"); goto qbuf_none;
}
if (ice_aq_cfg_lan_txq(&lag->pf->hw, qbuf, qbuf_size, valq, oldport,
newport, NULL)) {
dev_warn(dev, "Failure to configure queues for LAG failover\n"); goto qbuf_err;
}
qbuf_none:
kfree(qbuf);
/* find new parent in destination port's tree for VF VSI node on this *TrafficClass
*/
n_prt = ice_lag_get_sched_parent(new_hw, tc); if (!n_prt) goto resume_traffic;
/* Move Vf's VSI node for this TC to newport's scheduler tree */
buf->hdr.src_parent_teid = parent_teid;
buf->hdr.dest_parent_teid = n_prt->info.node_teid;
buf->hdr.num_elems = cpu_to_le16(1);
buf->hdr.mode = ICE_AQC_MOVE_ELEM_MODE_KEEP_OWN;
buf->teid[0] = teid;
if (ice_aq_move_sched_elems(&lag->pf->hw, buf, buf_size, &num_moved))
dev_warn(dev, "Failure to move VF nodes for failover\n"); else
ice_sched_update_parent(n_prt, ctx->sched.vsi_node[tc]);
goto resume_traffic;
qbuf_err:
kfree(qbuf);
resume_traffic: /* restart traffic for VSI node */ if (ice_sched_suspend_resume_elems(&lag->pf->hw, 1, &tmp_teid, false))
dev_dbg(dev, "Problem restarting traffic for LAG node move\n");
}
if (event_netdev != lag->netdev || !lag->bonded || !lag->upper_netdev) return;
if (bonding_info->master.bond_mode != BOND_MODE_ACTIVEBACKUP) {
netdev_dbg(lag->netdev, "Bonding event recv, but mode not active/backup\n"); goto lag_out;
}
if (strcmp(bonding_info->slave.slave_name, lag_netdev_name)) {
netdev_dbg(lag->netdev, "Bonding event recv, but secondary info not for us\n"); goto lag_out;
}
if (bonding_info->slave.state)
ice_lag_set_backup(lag); else
ice_lag_set_primary(lag);
/* if !teid or !numq, then this TC is not active */ if (!tmp_teid || !numq) return;
/* suspend traffic */ if (ice_sched_suspend_resume_elems(hw, 1, &tmp_teid, true))
dev_dbg(dev, "Problem suspending traffic for LAG node move\n");
/* reconfig queues for new port */
qbuf_size = struct_size(qbuf, queue_info, numq);
qbuf = kzalloc(qbuf_size, GFP_KERNEL); if (!qbuf) {
dev_warn(dev, "Failure allocating memory for VF queue recfg buffer\n"); goto resume_reclaim;
}
/* add the per queue info for the reconfigure command buffer */
valq = ice_lag_qbuf_recfg(hw, qbuf, vsi_num, numq, tc); if (!valq) {
dev_dbg(dev, "No valid queues found for LAG reclaim\n"); goto reclaim_none;
}
if (ice_aq_cfg_lan_txq(hw, qbuf, qbuf_size, numq,
src_hw->port_info->lport, hw->port_info->lport,
NULL)) {
dev_warn(dev, "Failure to configure queues for LAG failover\n"); goto reclaim_qerr;
}
reclaim_none:
kfree(qbuf);
/* find parent in primary tree */
n_prt = ice_lag_get_sched_parent(hw, tc); if (!n_prt) goto resume_reclaim;
if (ice_aq_move_sched_elems(&lag->pf->hw, buf, buf_size, &num_moved))
dev_warn(dev, "Failure to move VF nodes for LAG reclaim\n"); else
ice_sched_update_parent(n_prt, ctx->sched.vsi_node[tc]);
goto resume_reclaim;
reclaim_qerr:
kfree(qbuf);
resume_reclaim: /* restart traffic */ if (ice_sched_suspend_resume_elems(hw, 1, &tmp_teid, false))
dev_warn(dev, "Problem restarting traffic for LAG node reclaim\n");
}
/** *ice_lag_reclaim_vf_nodes-Wheninterfaceleavingbondprimaryreclaimsnodes *@lag:primaryinterfacelagstruct *@src_hw:HWstructforcurrentnodelocation
*/ staticvoid
ice_lag_reclaim_vf_nodes(struct ice_lag *lag, struct ice_hw *src_hw)
{ struct ice_pf *pf; int i, tc;
if (!lag->primary || !src_hw) return;
pf = lag->pf;
ice_for_each_vsi(pf, i) if (pf->vsi[i] && pf->vsi[i]->type == ICE_VSI_VF)
ice_for_each_traffic_class(tc)
ice_lag_reclaim_vf_tc(lag, src_hw, i, tc);
}
buf->num_elems = cpu_to_le16(1);
buf->res_type = cpu_to_le16(ICE_AQC_RES_TYPE_SWID); /* if unlinnking need to free the shared resource */ if (!link && local_lag->bond_swid) {
buf->elem[0].e.sw_resp = cpu_to_le16(local_lag->bond_swid);
status = ice_aq_alloc_free_res(&local_lag->pf->hw, buf,
buf_len, ice_aqc_opc_free_res); if (status)
dev_err(ice_pf_to_dev(local_lag->pf), "Error freeing SWID during LAG unlink\n");
local_lag->bond_swid = 0;
}
if (link) {
buf->res_type |= cpu_to_le16(ICE_LAG_RES_SHARED |
ICE_LAG_RES_VALID); /* store the primary's SWID in case it leaves bond first */
local_lag->bond_swid = primary_swid;
buf->elem[0].e.sw_resp = cpu_to_le16(local_lag->bond_swid);
} else {
buf->elem[0].e.sw_resp =
cpu_to_le16(local_lag->pf->hw.port_info->sw_id);
}
status = ice_aq_alloc_free_res(&local_lag->pf->hw, buf, buf_len,
ice_aqc_opc_alloc_res); if (status)
dev_err(ice_pf_to_dev(local_lag->pf), "Error subscribing to SWID 0x%04X\n",
local_lag->bond_swid);
kfree(buf);
/* Configure port param SWID to correct value */ if (link)
swid = primary_swid; else
swid = local_lag->pf->hw.port_info->sw_id;
cmd->swid = cpu_to_le16(ICE_AQC_PORT_SWID_VALID | swid); /* If this is happening in reset context, it is possible that the *primaryinterfacehasnotfinishedsettingitsSWIDtoSHARED *yet.Allowretriestoaccountforthistimingissuebetween *interfaces.
*/ for (i = 0; i < ICE_LAG_RESET_RETRIES; i++) {
status = ice_aq_send_cmd(&local_lag->pf->hw, &desc, NULL, 0,
NULL); if (!status) break;
usleep_range(1000, 2000);
}
if (status)
dev_err(ice_pf_to_dev(local_lag->pf), "Error setting SWID in port params %d\n",
status);
}
dev = ice_pf_to_dev(lag->pf);
event_vsi_num = event_pf->vsi[0]->vsi_num;
prim_vsi_idx = lag->pf->vsi[0]->idx;
if (!ice_find_vsi_list_entry(&lag->pf->hw, ICE_SW_LKUP_VLAN,
prim_vsi_idx, &vsi_list_id)) {
dev_warn(dev, "Could not locate prune list when setting up SRIOV LAG\n"); return;
}
rule_buf_sz = (u16)ICE_SW_RULE_VSI_LIST_SIZE(s_rule, num_vsi);
s_rule = kzalloc(rule_buf_sz, GFP_KERNEL); if (!s_rule) {
dev_warn(dev, "Error allocating space for prune list when configuring SRIOV LAG\n"); return;
}
dev = ice_pf_to_dev(lag->pf);
vsi_num = event_pf->vsi[0]->vsi_num;
vsi_idx = lag->pf->vsi[0]->idx;
if (!ice_find_vsi_list_entry(&lag->pf->hw, ICE_SW_LKUP_VLAN,
vsi_idx, &vsi_list_id)) {
dev_warn(dev, "Could not locate prune list when unwinding SRIOV LAG\n"); return;
}
rule_buf_sz = (u16)ICE_SW_RULE_VSI_LIST_SIZE(s_rule, num_vsi);
s_rule = kzalloc(rule_buf_sz, GFP_KERNEL); if (!s_rule) {
dev_warn(dev, "Error allocating prune list when unwinding SRIOV LAG\n"); return;
}
info = ptr;
netdev = netdev_notifier_info_to_dev(ptr);
/* not for this netdev */ if (netdev != lag->netdev) return;
primary_lag = ice_lag_find_primary(lag); if (info->linking) {
lag->upper_netdev = info->upper_dev; /* If there is not already a primary interface in the LAG, *thenmarkthisoneasprimary.
*/ if (!primary_lag) {
lag->primary = true; if (!ice_is_switchdev_running(lag->pf)) return;
/* Configure primary's SWID to be shared */
ice_lag_primary_swid(lag, true);
primary_lag = lag;
} else {
u16 swid;
if (!ice_is_switchdev_running(primary_lag->pf)) return;
info = (struct netdev_notifier_changeupper_info *)ptr; if (info->upper_dev != lag->upper_netdev) return;
if (!info->linking) { /* Since there are only two interfaces allowed in SRIOV+LAG, if *oneportisleaving,thennodesneedtobeonprimary *interface.
*/ if (prim_port != lag->active_port &&
lag->active_port != ICE_LAG_INVALID_PORT) {
active_hw = ice_lag_find_hw_by_lport(lag,
lag->active_port);
ice_lag_reclaim_vf_nodes(lag, active_hw);
lag->active_port = ICE_LAG_INVALID_PORT;
}
}
}
info = (struct netdev_notifier_bonding_info *)ptr;
bonding_info = &info->bonding_info;
if (!bonding_info->slave.state) { /* if no port is currently active, then nodes and filters exist *onprimaryport,checkifweneedtomovethem
*/ if (lag->active_port == ICE_LAG_INVALID_PORT) { if (event_port != prim_port)
ice_lag_move_vf_nodes(lag, prim_port,
event_port);
lag->active_port = event_port;
ice_lag_config_eswitch(lag, event_netdev); return;
}
/* active port is already set and is current event port */ if (lag->active_port == event_port) return; /* new active port */
ice_lag_move_vf_nodes(lag, lag->active_port, event_port);
lag->active_port = event_port;
ice_lag_config_eswitch(lag, event_netdev);
} else { /* port not set as currently active (e.g. new active port *hasalreadyclaimedthenodesandfilters
*/ if (lag->active_port != event_port) return; /* This is the case when neither port is active (both link down) *Linkdownonthebond-setactiveporttoinvalidandmove *nodesandfiltersbacktoprimaryifnotalreadythere
*/ if (event_port != prim_port)
ice_lag_move_vf_nodes(lag, event_port, prim_port);
lag->active_port = ICE_LAG_INVALID_PORT;
}
}
/* only supporting switchdev mode for SRIOV VF LAG. *primaryinterfacehastobeinswitchdevmode
*/ if (!ice_is_switchdev_running(lag->pf)) {
dev_info(dev, "Primary interface not in switchdev mode - VF LAG disabled\n"); returnfalse;
}
info = (struct netdev_notifier_bonding_info *)ptr;
bonding_info = &info->bonding_info;
lag->bond_mode = bonding_info->master.bond_mode; if (lag->bond_mode != BOND_MODE_ACTIVEBACKUP) {
dev_info(dev, "Bond Mode not ACTIVE-BACKUP - VF LAG disabled\n"); returnfalse;
}
entry = list_entry(tmp, struct ice_lag_netdev_list, node);
peer_netdev = entry->netdev; if (!netif_is_ice(peer_netdev)) {
dev_info(dev, "Found %s non-ice netdev in LAG - VF LAG disabled\n",
netdev_name(peer_netdev)); returnfalse;
}
count++; if (count > 2) {
dev_info(dev, "Found more than two netdevs in LAG - VF LAG disabled\n"); returnfalse;
}
peer_np = netdev_priv(peer_netdev);
vsi = ice_get_main_vsi(lag->pf);
peer_vsi = peer_np->vsi; if (lag->pf->pdev->bus != peer_vsi->back->pdev->bus ||
lag->pf->pdev->slot != peer_vsi->back->pdev->slot) {
dev_info(dev, "Found %s on different device in LAG - VF LAG disabled\n",
netdev_name(peer_netdev)); returnfalse;
}
dcb_cfg = &vsi->port_info->qos_cfg.local_dcbx_cfg;
peer_dcb_cfg = &peer_vsi->port_info->qos_cfg.local_dcbx_cfg; if (memcmp(dcb_cfg, peer_dcb_cfg, sizeof(struct ice_dcbx_cfg))) {
dev_info(dev, "Found %s with different DCB in LAG - VF LAG disabled\n",
netdev_name(peer_netdev)); returnfalse;
}
peer_pf = peer_vsi->back; if (test_bit(ICE_FLAG_FW_LLDP_AGENT, peer_pf->flags)) {
dev_warn(dev, "Found %s with FW LLDP agent active - VF LAG disabled\n",
netdev_name(peer_netdev)); returnfalse;
}
}
switch (lag_work->event) { case NETDEV_CHANGEUPPER:
info = &lag_work->info.changeupper_info;
ice_lag_chk_disabled_bond(lag_work->lag, info); if (ice_is_feature_supported(pf, ICE_F_SRIOV_LAG)) {
ice_lag_monitor_link(lag_work->lag, info);
ice_lag_changeupper_event(lag_work->lag, info);
ice_lag_link_unlink(lag_work->lag, info);
}
ice_lag_monitor_rdma(lag_work->lag, info); break; case NETDEV_BONDING_INFO: if (ice_is_feature_supported(pf, ICE_F_SRIOV_LAG)) { if (!ice_lag_chk_comp(lag_work->lag,
&lag_work->info.bonding_info)) {
netdev = lag_work->info.bonding_info.info.dev;
ice_lag_disable_sriov_bond(lag_work->lag);
ice_lag_unregister(lag_work->lag, netdev); goto lag_cleanup;
}
ice_lag_monitor_active(lag_work->lag,
&lag_work->info.bonding_info);
ice_lag_cfg_pf_fltrs(lag_work->lag,
&lag_work->info.bonding_info);
}
ice_lag_info_event(lag_work->lag, &lag_work->info.bonding_info); break; case NETDEV_UNREGISTER: if (ice_is_feature_supported(pf, ICE_F_SRIOV_LAG)) {
netdev = lag_work->info.bonding_info.info.dev; if ((netdev == lag_work->lag->netdev ||
lag_work->lag->primary) && lag_work->lag->bonded)
ice_lag_unregister(lag_work->lag, netdev);
} break; default: break;
}
lag_cleanup: /* cleanup resources allocated for this work item */
list_for_each_safe(tmp, n, &lag_work->netdev_list.node) { struct ice_lag_netdev_list *entry;
hw = &lag->pf->hw;
ctx = ice_get_vsi_ctx(hw, vsi_num); if (!ctx) {
dev_warn(dev, "LAG rebuild failed after reset due to VSI Context failure\n"); return;
}
if (ice_sched_suspend_resume_elems(hw, 1, &tmp_teid, true))
dev_dbg(dev, "Problem suspending traffic during reset rebuild\n");
/* reconfig queues for new port */
qbuf_size = struct_size(qbuf, queue_info, numq);
qbuf = kzalloc(qbuf_size, GFP_KERNEL); if (!qbuf) {
dev_warn(dev, "Failure allocating VF queue recfg buffer for reset rebuild\n"); goto resume_sync;
}
/* add the per queue info for the reconfigure command buffer */
valq = ice_lag_qbuf_recfg(hw, qbuf, vsi_num, numq, tc); if (!valq) {
dev_warn(dev, "Failure to reconfig queues for LAG reset rebuild\n"); goto sync_none;
}
if (ice_aq_cfg_lan_txq(hw, qbuf, qbuf_size, numq, hw->port_info->lport,
dest_hw->port_info->lport, NULL)) {
dev_warn(dev, "Failure to configure queues for LAG reset rebuild\n"); goto sync_qerr;
}
sync_none:
kfree(qbuf);
/* find parent in destination tree */
n_prt = ice_lag_get_sched_parent(dest_hw, tc); if (!n_prt) goto resume_sync;
if (ice_aq_move_sched_elems(&lag->pf->hw, buf, buf_size, &num_moved))
dev_warn(dev, "Failure to move VF nodes for LAG reset rebuild\n"); else
ice_sched_update_parent(n_prt, ctx->sched.vsi_node[tc]);
goto resume_sync;
sync_qerr:
kfree(qbuf);
resume_sync: if (ice_sched_suspend_resume_elems(hw, 1, &tmp_teid, false))
dev_warn(dev, "Problem restarting traffic for LAG node reset rebuild\n");
}
err = ice_register_lag_handler(lag); if (err) {
dev_warn(dev, "INIT LAG: Failed to register event handler\n"); goto lag_error;
}
err = ice_create_lag_recipe(&pf->hw, &lag->pf_recipe,
ice_dflt_vsi_rcp, 1); if (err) goto lag_error;
err = ice_create_lag_recipe(&pf->hw, &lag->lport_recipe,
ice_lport_rcp, 3); if (err) goto free_rcp_res;
/* associate recipes to profiles */ for (n = 0; n < ICE_PROFID_IPV6_GTPU_IPV6_TCP_INNER; n++) {
err = ice_aq_get_recipe_to_profile(&pf->hw, n,
&recipe_bits, NULL); if (err) continue;
if (recipe_bits & BIT(ICE_SW_LKUP_DFLT)) {
recipe_bits |= BIT(lag->pf_recipe) |
BIT(lag->lport_recipe);
ice_aq_map_recipe_to_profile(&pf->hw, n,
recipe_bits, NULL);
}
}
if (!netif_is_ice(tmp_nd) || !priv || !priv->vsi ||
!priv->vsi->back) continue;
if (ice_is_switchdev_running(priv->vsi->back)) {
rcu_read_unlock(); returntrue;
}
}
rcu_read_unlock();
returnfalse;
}
Messung V0.5 in Prozent
¤ Die Informationen auf dieser Webseite wurden
nach bestem Wissen sorgfältig zusammengestellt. Es wird jedoch weder Vollständigkeit, noch Richtigkeit,
noch Qualität der bereit gestellten Informationen zugesichert.0.41Bemerkung:
(vorverarbeitet am 2026-10-03)
¤
Die Informationen auf dieser Webseite wurden
nach bestem Wissen sorgfältig zusammengestellt. Es wird jedoch weder Vollständigkeit, noch Richtigkeit,
noch Qualität der bereit gestellten Informationen zugesichert.
Bemerkung:
Die farbliche Syntaxdarstellung und die Messung sind noch experimentell.