From b80af659699d212cf8cec6593f6551905c4ae86f Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Sat, 6 Feb 2021 00:02:14 +0200 Subject: net: mscc: ocelot: set up the bonding mask in a way that avoids a net_device Since this code should be called from pure switchdev as well as from DSA, we must find a way to determine the bonding mask not by looking directly at the net_device lowers of the bonding interface, since those could have different private structures. We keep a pointer to the bonding upper interface, if present, in struct ocelot_port. Then the bonding mask becomes the bitwise OR of all ports that have the same bonding upper interface. This adds a duplication of functionality with the current "lags" array, but the duplication will be short-lived, since further patches will remove the latter completely. Signed-off-by: Vladimir Oltean Reviewed-by: Alexandre Belloni Signed-off-by: Jakub Kicinski --- include/soc/mscc/ocelot.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index 6a61c499a30d..e36a1ed29c01 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -611,6 +611,8 @@ struct ocelot_port { u8 *xmit_template; bool is_dsa_8021q_cpu; + + struct net_device *bond; }; struct ocelot { -- cgit v1.3-14-g43fede From 528d3f190c98c8f7d9581f68db4af021696727b2 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Sat, 6 Feb 2021 00:02:17 +0200 Subject: net: mscc: ocelot: drop the use of the "lags" array We can now simplify the implementation by always using ocelot_get_bond_mask to look up the other ports that are offloading the same bonding interface as us. In ocelot_set_aggr_pgids, the code had a way to uniquely iterate through LAGs. We need to achieve the same behavior by marking each LAG as visited, which we do now by using a temporary 32-bit "visited" bitmask. This is ok and we do not need dynamic memory allocation, because we know that this switch architecture will not have more than 32 ports (the PGID port masks are 32-bit anyway). Signed-off-by: Vladimir Oltean Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mscc/ocelot.c | 95 ++++++++++++++++---------------------- include/soc/mscc/ocelot.h | 2 - 2 files changed, 39 insertions(+), 58 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c index 5d765245c6d3..c906c449d2dd 100644 --- a/drivers/net/ethernet/mscc/ocelot.c +++ b/drivers/net/ethernet/mscc/ocelot.c @@ -957,21 +957,11 @@ void ocelot_apply_bridge_fwd_mask(struct ocelot *ocelot) mask = GENMASK(ocelot->num_phys_ports - 1, 0); mask &= ~cpu_fwd_mask; } else if (ocelot->bridge_fwd_mask & BIT(port)) { - int lag; + struct net_device *bond = ocelot_port->bond; mask = ocelot->bridge_fwd_mask & ~BIT(port); - - for (lag = 0; lag < ocelot->num_phys_ports; lag++) { - unsigned long bond_mask = ocelot->lags[lag]; - - if (!bond_mask) - continue; - - if (bond_mask & BIT(port)) { - mask &= ~bond_mask; - break; - } - } + if (bond) + mask &= ~ocelot_get_bond_mask(ocelot, bond); } else { /* Standalone ports forward only to DSA tag_8021q CPU * ports (if those exist), or to the hardware CPU port @@ -1277,6 +1267,7 @@ EXPORT_SYMBOL(ocelot_port_bridge_leave); static void ocelot_set_aggr_pgids(struct ocelot *ocelot) { + unsigned long visited = GENMASK(ocelot->num_phys_ports - 1, 0); int i, port, lag; /* Reset destination and aggregation PGIDS */ @@ -1287,16 +1278,35 @@ static void ocelot_set_aggr_pgids(struct ocelot *ocelot) ocelot_write_rix(ocelot, GENMASK(ocelot->num_phys_ports - 1, 0), ANA_PGID_PGID, i); - /* Now, set PGIDs for each LAG */ + /* The visited ports bitmask holds the list of ports offloading any + * bonding interface. Initially we mark all these ports as unvisited, + * then every time we visit a port in this bitmask, we know that it is + * the lowest numbered port, i.e. the one whose logical ID == physical + * port ID == LAG ID. So we mark as visited all further ports in the + * bitmask that are offloading the same bonding interface. This way, + * we set up the aggregation PGIDs only once per bonding interface. + */ + for (port = 0; port < ocelot->num_phys_ports; port++) { + struct ocelot_port *ocelot_port = ocelot->ports[port]; + + if (!ocelot_port || !ocelot_port->bond) + continue; + + visited &= ~BIT(port); + } + + /* Now, set PGIDs for each active LAG */ for (lag = 0; lag < ocelot->num_phys_ports; lag++) { + struct net_device *bond = ocelot->ports[lag]->bond; unsigned long bond_mask; int aggr_count = 0; u8 aggr_idx[16]; - bond_mask = ocelot->lags[lag]; - if (!bond_mask) + if (!bond || (visited & BIT(lag))) continue; + bond_mask = ocelot_get_bond_mask(ocelot, bond); + for_each_set_bit(port, &bond_mask, ocelot->num_phys_ports) { // Destination mask ocelot_write_rix(ocelot, bond_mask, @@ -1313,6 +1323,19 @@ static void ocelot_set_aggr_pgids(struct ocelot *ocelot) ac |= BIT(aggr_idx[i % aggr_count]); ocelot_write_rix(ocelot, ac, ANA_PGID_PGID, i); } + + /* Mark all ports in the same LAG as visited to avoid applying + * the same config again. + */ + for (port = lag; port < ocelot->num_phys_ports; port++) { + struct ocelot_port *ocelot_port = ocelot->ports[port]; + + if (!ocelot_port) + continue; + + if (ocelot_port->bond == bond) + visited |= BIT(port); + } } } @@ -1353,30 +1376,11 @@ int ocelot_port_lag_join(struct ocelot *ocelot, int port, struct net_device *bond, struct netdev_lag_upper_info *info) { - u32 bond_mask = 0; - int lag; - if (info->tx_type != NETDEV_LAG_TX_TYPE_HASH) return -EOPNOTSUPP; ocelot->ports[port]->bond = bond; - bond_mask = ocelot_get_bond_mask(ocelot, bond); - - lag = __ffs(bond_mask); - - /* If the new port is the lowest one, use it as the logical port from - * now on - */ - if (port == lag) { - ocelot->lags[port] = bond_mask; - bond_mask &= ~BIT(port); - if (bond_mask) - ocelot->lags[__ffs(bond_mask)] = 0; - } else { - ocelot->lags[lag] |= BIT(port); - } - ocelot_setup_logical_port_ids(ocelot); ocelot_apply_bridge_fwd_mask(ocelot); ocelot_set_aggr_pgids(ocelot); @@ -1388,24 +1392,8 @@ EXPORT_SYMBOL(ocelot_port_lag_join); void ocelot_port_lag_leave(struct ocelot *ocelot, int port, struct net_device *bond) { - int i; - ocelot->ports[port]->bond = NULL; - /* Remove port from any lag */ - for (i = 0; i < ocelot->num_phys_ports; i++) - ocelot->lags[i] &= ~BIT(port); - - /* if it was the logical port of the lag, move the lag config to the - * next port - */ - if (ocelot->lags[port]) { - int n = __ffs(ocelot->lags[port]); - - ocelot->lags[n] = ocelot->lags[port]; - ocelot->lags[port] = 0; - } - ocelot_setup_logical_port_ids(ocelot); ocelot_apply_bridge_fwd_mask(ocelot); ocelot_set_aggr_pgids(ocelot); @@ -1587,11 +1575,6 @@ int ocelot_init(struct ocelot *ocelot) } } - ocelot->lags = devm_kcalloc(ocelot->dev, ocelot->num_phys_ports, - sizeof(u32), GFP_KERNEL); - if (!ocelot->lags) - return -ENOMEM; - ocelot->stats = devm_kcalloc(ocelot->dev, ocelot->num_phys_ports * ocelot->num_stats, sizeof(u64), GFP_KERNEL); diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index e36a1ed29c01..089e552719e0 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -657,8 +657,6 @@ struct ocelot { enum ocelot_tag_prefix npi_inj_prefix; enum ocelot_tag_prefix npi_xtr_prefix; - u32 *lags; - struct list_head multicast; struct list_head pgids; -- cgit v1.3-14-g43fede From 23ca3b727ee6b432166391607b614d3a6beb6784 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Sat, 6 Feb 2021 00:02:19 +0200 Subject: net: mscc: ocelot: rebalance LAGs on link up/down events At present there is an issue when ocelot is offloading a bonding interface, but one of the links of the physical ports goes down. Traffic keeps being hashed towards that destination, and of course gets dropped on egress. Monitor the netdev notifier events emitted by the bonding driver for changes in the physical state of lower interfaces, to determine which ports are active and which ones are no longer. Then extend ocelot_get_bond_mask to return either the configured bonding interfaces, or the active ones, depending on a boolean argument. The code that does rebalancing only needs to do so among the active ports, whereas the bridge forwarding mask and the logical port IDs still need to look at the permanently bonded ports. Signed-off-by: Vladimir Oltean Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mscc/ocelot.c | 41 ++++++++++++++++++++++++++-------- drivers/net/ethernet/mscc/ocelot.h | 1 + drivers/net/ethernet/mscc/ocelot_net.c | 30 +++++++++++++++++++++++++ include/soc/mscc/ocelot.h | 1 + 4 files changed, 64 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c index 380a5a661702..f8b85ab8be5d 100644 --- a/drivers/net/ethernet/mscc/ocelot.c +++ b/drivers/net/ethernet/mscc/ocelot.c @@ -889,7 +889,8 @@ int ocelot_get_ts_info(struct ocelot *ocelot, int port, } EXPORT_SYMBOL(ocelot_get_ts_info); -static u32 ocelot_get_bond_mask(struct ocelot *ocelot, struct net_device *bond) +static u32 ocelot_get_bond_mask(struct ocelot *ocelot, struct net_device *bond, + bool only_active_ports) { u32 mask = 0; int port; @@ -900,8 +901,12 @@ static u32 ocelot_get_bond_mask(struct ocelot *ocelot, struct net_device *bond) if (!ocelot_port) continue; - if (ocelot_port->bond == bond) + if (ocelot_port->bond == bond) { + if (only_active_ports && !ocelot_port->lag_tx_active) + continue; + mask |= BIT(port); + } } return mask; @@ -960,8 +965,10 @@ void ocelot_apply_bridge_fwd_mask(struct ocelot *ocelot) struct net_device *bond = ocelot_port->bond; mask = ocelot->bridge_fwd_mask & ~BIT(port); - if (bond) - mask &= ~ocelot_get_bond_mask(ocelot, bond); + if (bond) { + mask &= ~ocelot_get_bond_mask(ocelot, bond, + false); + } } else { /* Standalone ports forward only to DSA tag_8021q CPU * ports (if those exist), or to the hardware CPU port @@ -1298,20 +1305,20 @@ static void ocelot_set_aggr_pgids(struct ocelot *ocelot) /* Now, set PGIDs for each active LAG */ for (lag = 0; lag < ocelot->num_phys_ports; lag++) { struct net_device *bond = ocelot->ports[lag]->bond; - int num_ports_in_lag = 0; + int num_active_ports = 0; unsigned long bond_mask; u8 aggr_idx[16]; if (!bond || (visited & BIT(lag))) continue; - bond_mask = ocelot_get_bond_mask(ocelot, bond); + bond_mask = ocelot_get_bond_mask(ocelot, bond, true); for_each_set_bit(port, &bond_mask, ocelot->num_phys_ports) { // Destination mask ocelot_write_rix(ocelot, bond_mask, ANA_PGID_PGID, port); - aggr_idx[num_ports_in_lag++] = port; + aggr_idx[num_active_ports++] = port; } for_each_aggr_pgid(ocelot, i) { @@ -1319,7 +1326,11 @@ static void ocelot_set_aggr_pgids(struct ocelot *ocelot) ac = ocelot_read_rix(ocelot, ANA_PGID_PGID, i); ac &= ~bond_mask; - ac |= BIT(aggr_idx[i % num_ports_in_lag]); + /* Don't do division by zero if there was no active + * port. Just make all aggregation codes zero. + */ + if (num_active_ports) + ac |= BIT(aggr_idx[i % num_active_ports]); ocelot_write_rix(ocelot, ac, ANA_PGID_PGID, i); } @@ -1356,7 +1367,8 @@ static void ocelot_setup_logical_port_ids(struct ocelot *ocelot) bond = ocelot_port->bond; if (bond) { - int lag = __ffs(ocelot_get_bond_mask(ocelot, bond)); + int lag = __ffs(ocelot_get_bond_mask(ocelot, bond, + false)); ocelot_rmw_gix(ocelot, ANA_PORT_PORT_CFG_PORTID_VAL(lag), @@ -1399,6 +1411,17 @@ void ocelot_port_lag_leave(struct ocelot *ocelot, int port, } EXPORT_SYMBOL(ocelot_port_lag_leave); +void ocelot_port_lag_change(struct ocelot *ocelot, int port, bool lag_tx_active) +{ + struct ocelot_port *ocelot_port = ocelot->ports[port]; + + ocelot_port->lag_tx_active = lag_tx_active; + + /* Rebalance the LAGs */ + ocelot_set_aggr_pgids(ocelot); +} +EXPORT_SYMBOL(ocelot_port_lag_change); + /* Configure the maximum SDU (L2 payload) on RX to the value specified in @sdu. * The length of VLAN tags is accounted for automatically via DEV_MAC_TAGS_CFG. * In the special case that it's the NPI port that we're configuring, the diff --git a/drivers/net/ethernet/mscc/ocelot.h b/drivers/net/ethernet/mscc/ocelot.h index 12dc74453076..b18f6644726a 100644 --- a/drivers/net/ethernet/mscc/ocelot.h +++ b/drivers/net/ethernet/mscc/ocelot.h @@ -114,6 +114,7 @@ int ocelot_port_lag_join(struct ocelot *ocelot, int port, struct netdev_lag_upper_info *info); void ocelot_port_lag_leave(struct ocelot *ocelot, int port, struct net_device *bond); +void ocelot_port_lag_change(struct ocelot *ocelot, int port, bool lag_tx_active); struct net_device *ocelot_port_to_netdev(struct ocelot *ocelot, int port); int ocelot_netdev_to_port(struct net_device *dev); diff --git a/drivers/net/ethernet/mscc/ocelot_net.c b/drivers/net/ethernet/mscc/ocelot_net.c index 0a4de949f4d9..8f12fa45b1b5 100644 --- a/drivers/net/ethernet/mscc/ocelot_net.c +++ b/drivers/net/ethernet/mscc/ocelot_net.c @@ -1164,6 +1164,27 @@ ocelot_netdevice_lag_changeupper(struct net_device *dev, return NOTIFY_DONE; } +static int +ocelot_netdevice_changelowerstate(struct net_device *dev, + struct netdev_lag_lower_state_info *info) +{ + struct ocelot_port_private *priv = netdev_priv(dev); + bool is_active = info->link_up && info->tx_enabled; + struct ocelot_port *ocelot_port = &priv->port; + struct ocelot *ocelot = ocelot_port->ocelot; + int port = priv->chip_port; + + if (!ocelot_port->bond) + return NOTIFY_DONE; + + if (ocelot_port->lag_tx_active == is_active) + return NOTIFY_DONE; + + ocelot_port_lag_change(ocelot, port, is_active); + + return NOTIFY_OK; +} + static int ocelot_netdevice_event(struct notifier_block *unused, unsigned long event, void *ptr) { @@ -1181,6 +1202,15 @@ static int ocelot_netdevice_event(struct notifier_block *unused, break; } + case NETDEV_CHANGELOWERSTATE: { + struct netdev_notifier_changelowerstate_info *info = ptr; + + if (!ocelot_netdevice_dev_check(dev)) + break; + + return ocelot_netdevice_changelowerstate(dev, + info->lower_state_info); + } default: break; } diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index 089e552719e0..6e806872cd24 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -613,6 +613,7 @@ struct ocelot_port { bool is_dsa_8021q_cpu; struct net_device *bond; + bool lag_tx_active; }; struct ocelot { -- cgit v1.3-14-g43fede From 8fe6832e96acbf9d5777fc0b13e3e680ff46ba11 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Sat, 6 Feb 2021 00:02:21 +0200 Subject: net: dsa: felix: propagate the LAG offload ops towards the ocelot lib The ocelot switch has been supporting LAG offload since its initial commit, however felix could not make use of that, due to lack of a LAG abstraction in DSA. Now that we have that, let's forward DSA's calls towards the ocelot library, who will deal with setting up the bonding. Signed-off-by: Vladimir Oltean Signed-off-by: Jakub Kicinski --- drivers/net/dsa/ocelot/felix.c | 32 ++++++++++++++++++++++++++++++++ drivers/net/ethernet/mscc/ocelot.h | 6 ------ include/soc/mscc/ocelot.h | 6 ++++++ 3 files changed, 38 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c index 167463010b55..1bd5aea12b25 100644 --- a/drivers/net/dsa/ocelot/felix.c +++ b/drivers/net/dsa/ocelot/felix.c @@ -569,6 +569,35 @@ static void felix_bridge_leave(struct dsa_switch *ds, int port, ocelot_port_bridge_leave(ocelot, port, br); } +static int felix_lag_join(struct dsa_switch *ds, int port, + struct net_device *bond, + struct netdev_lag_upper_info *info) +{ + struct ocelot *ocelot = ds->priv; + + return ocelot_port_lag_join(ocelot, port, bond, info); +} + +static int felix_lag_leave(struct dsa_switch *ds, int port, + struct net_device *bond) +{ + struct ocelot *ocelot = ds->priv; + + ocelot_port_lag_leave(ocelot, port, bond); + + return 0; +} + +static int felix_lag_change(struct dsa_switch *ds, int port) +{ + struct dsa_port *dp = dsa_to_port(ds, port); + struct ocelot *ocelot = ds->priv; + + ocelot_port_lag_change(ocelot, port, dp->lag_tx_enabled); + + return 0; +} + static int felix_vlan_prepare(struct dsa_switch *ds, int port, const struct switchdev_obj_port_vlan *vlan) { @@ -1331,6 +1360,9 @@ const struct dsa_switch_ops felix_switch_ops = { .port_mdb_del = felix_mdb_del, .port_bridge_join = felix_bridge_join, .port_bridge_leave = felix_bridge_leave, + .port_lag_join = felix_lag_join, + .port_lag_leave = felix_lag_leave, + .port_lag_change = felix_lag_change, .port_stp_state_set = felix_bridge_stp_state_set, .port_vlan_filtering = felix_vlan_filtering, .port_vlan_add = felix_vlan_add, diff --git a/drivers/net/ethernet/mscc/ocelot.h b/drivers/net/ethernet/mscc/ocelot.h index b18f6644726a..c485795c606b 100644 --- a/drivers/net/ethernet/mscc/ocelot.h +++ b/drivers/net/ethernet/mscc/ocelot.h @@ -109,12 +109,6 @@ int ocelot_mact_learn(struct ocelot *ocelot, int port, unsigned int vid, enum macaccess_entry_type type); int ocelot_mact_forget(struct ocelot *ocelot, const unsigned char mac[ETH_ALEN], unsigned int vid); -int ocelot_port_lag_join(struct ocelot *ocelot, int port, - struct net_device *bond, - struct netdev_lag_upper_info *info); -void ocelot_port_lag_leave(struct ocelot *ocelot, int port, - struct net_device *bond); -void ocelot_port_lag_change(struct ocelot *ocelot, int port, bool lag_tx_active); struct net_device *ocelot_port_to_netdev(struct ocelot *ocelot, int port); int ocelot_netdev_to_port(struct net_device *dev); diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index 6e806872cd24..d0d48e9620fb 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -798,6 +798,12 @@ int ocelot_port_mdb_add(struct ocelot *ocelot, int port, const struct switchdev_obj_port_mdb *mdb); int ocelot_port_mdb_del(struct ocelot *ocelot, int port, const struct switchdev_obj_port_mdb *mdb); +int ocelot_port_lag_join(struct ocelot *ocelot, int port, + struct net_device *bond, + struct netdev_lag_upper_info *info); +void ocelot_port_lag_leave(struct ocelot *ocelot, int port, + struct net_device *bond); +void ocelot_port_lag_change(struct ocelot *ocelot, int port, bool lag_tx_active); int ocelot_devlink_sb_register(struct ocelot *ocelot); void ocelot_devlink_sb_unregister(struct ocelot *ocelot); -- cgit v1.3-14-g43fede