diff options
Diffstat (limited to 'drivers/net/bonding')
-rw-r--r-- | drivers/net/bonding/bond_3ad.c | 11 | ||||
-rw-r--r-- | drivers/net/bonding/bond_alb.c | 32 | ||||
-rw-r--r-- | drivers/net/bonding/bond_main.c | 596 | ||||
-rw-r--r-- | drivers/net/bonding/bond_netlink.c | 16 | ||||
-rw-r--r-- | drivers/net/bonding/bond_options.c | 27 | ||||
-rw-r--r-- | drivers/net/bonding/bond_procfs.c | 2 | ||||
-rw-r--r-- | drivers/net/bonding/bond_sysfs.c | 25 |
7 files changed, 561 insertions, 148 deletions
diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c index 6908822d9773..6006c2e8fa2b 100644 --- a/drivers/net/bonding/bond_3ad.c +++ b/drivers/net/bonding/bond_3ad.c @@ -96,7 +96,7 @@ static int ad_marker_send(struct port *port, struct bond_marker *marker); static void ad_mux_machine(struct port *port, bool *update_slave_arr); static void ad_rx_machine(struct lacpdu *lacpdu, struct port *port); static void ad_tx_machine(struct port *port); -static void ad_periodic_machine(struct port *port); +static void ad_periodic_machine(struct port *port, struct bond_params *bond_params); static void ad_port_selection_logic(struct port *port, bool *update_slave_arr); static void ad_agg_selection_logic(struct aggregator *aggregator, bool *update_slave_arr); @@ -1294,10 +1294,11 @@ static void ad_tx_machine(struct port *port) /** * ad_periodic_machine - handle a port's periodic state machine * @port: the port we're looking at + * @bond_params: bond parameters we will use * * Turn ntt flag on priodically to perform periodic transmission of lacpdu's. */ -static void ad_periodic_machine(struct port *port) +static void ad_periodic_machine(struct port *port, struct bond_params *bond_params) { periodic_states_t last_state; @@ -1306,8 +1307,8 @@ static void ad_periodic_machine(struct port *port) /* check if port was reinitialized */ if (((port->sm_vars & AD_PORT_BEGIN) || !(port->sm_vars & AD_PORT_LACP_ENABLED) || !port->is_enabled) || - (!(port->actor_oper_port_state & LACP_STATE_LACP_ACTIVITY) && !(port->partner_oper.port_state & LACP_STATE_LACP_ACTIVITY)) - ) { + (!(port->actor_oper_port_state & LACP_STATE_LACP_ACTIVITY) && !(port->partner_oper.port_state & LACP_STATE_LACP_ACTIVITY)) || + !bond_params->lacp_active) { port->sm_periodic_state = AD_NO_PERIODIC; } /* check if state machine should change state */ @@ -2341,7 +2342,7 @@ void bond_3ad_state_machine_handler(struct work_struct *work) } ad_rx_machine(NULL, port); - ad_periodic_machine(port); + ad_periodic_machine(port, &bond->params); ad_port_selection_logic(port, &update_slave_arr); ad_mux_machine(port, &update_slave_arr); ad_tx_machine(port); diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c index 22e5632089ac..7d3752cbf761 100644 --- a/drivers/net/bonding/bond_alb.c +++ b/drivers/net/bonding/bond_alb.c @@ -17,7 +17,6 @@ #include <linux/if_bonding.h> #include <linux/if_vlan.h> #include <linux/in.h> -#include <net/ipx.h> #include <net/arp.h> #include <net/ipv6.h> #include <asm/byteorder.h> @@ -1351,8 +1350,6 @@ struct slave *bond_xmit_tlb_slave_get(struct bonding *bond, if (!is_multicast_ether_addr(eth_data->h_dest)) { switch (skb->protocol) { case htons(ETH_P_IP): - case htons(ETH_P_IPX): - /* In case of IPX, it will falback to L2 hash */ case htons(ETH_P_IPV6): hash_index = bond_xmit_hash(bond, skb); if (bond->params.tlb_dynamic_lb) { @@ -1454,35 +1451,6 @@ struct slave *bond_xmit_alb_slave_get(struct bonding *bond, hash_size = sizeof(ip6hdr->daddr); break; } - case ETH_P_IPX: { - const struct ipxhdr *ipxhdr; - - if (pskb_network_may_pull(skb, sizeof(*ipxhdr))) { - do_tx_balance = false; - break; - } - ipxhdr = (struct ipxhdr *)skb_network_header(skb); - - if (ipxhdr->ipx_checksum != IPX_NO_CHECKSUM) { - /* something is wrong with this packet */ - do_tx_balance = false; - break; - } - - if (ipxhdr->ipx_type != IPX_TYPE_NCP) { - /* The only protocol worth balancing in - * this family since it has an "ARP" like - * mechanism - */ - do_tx_balance = false; - break; - } - - eth_data = eth_hdr(skb); - hash_start = (char *)eth_data->h_dest; - hash_size = ETH_ALEN; - break; - } case ETH_P_ARP: do_tx_balance = false; if (bond_info->rlb_enabled) diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 31730efa7538..77dc79a7f574 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -317,6 +317,25 @@ bool bond_sk_check(struct bonding *bond) } } +static bool bond_xdp_check(struct bonding *bond) +{ + switch (BOND_MODE(bond)) { + case BOND_MODE_ROUNDROBIN: + case BOND_MODE_ACTIVEBACKUP: + return true; + case BOND_MODE_8023AD: + case BOND_MODE_XOR: + /* vlan+srcmac is not supported with XDP as in most cases the 802.1q + * payload is not in the packet due to hardware offload. + */ + if (bond->params.xmit_policy != BOND_XMIT_POLICY_VLAN_SRCMAC) + return true; + fallthrough; + default: + return false; + } +} + /*---------------------------------- VLAN -----------------------------------*/ /* In the following 2 functions, bond_vlan_rx_add_vid and bond_vlan_rx_kill_vid, @@ -732,7 +751,7 @@ static int bond_check_dev_link(struct bonding *bond, BMSR_LSTATUS : 0; /* Ethtool can't be used, fallback to MII ioctls. */ - ioctl = slave_ops->ndo_do_ioctl; + ioctl = slave_ops->ndo_eth_ioctl; if (ioctl) { /* TODO: set pointer to correct ioctl on a per team member * bases to make this more efficient. that is, once @@ -756,7 +775,7 @@ static int bond_check_dev_link(struct bonding *bond, } } - /* If reporting, report that either there's no dev->do_ioctl, + /* If reporting, report that either there's no ndo_eth_ioctl, * or both SIOCGMIIREG and get_link failed (meaning that we * cannot report link status). If not reporting, pretend * we're ok. @@ -1712,6 +1731,20 @@ void bond_lower_state_changed(struct slave *slave) netdev_lower_state_changed(slave->dev, &info); } +#define BOND_NL_ERR(bond_dev, extack, errmsg) do { \ + if (extack) \ + NL_SET_ERR_MSG(extack, errmsg); \ + else \ + netdev_err(bond_dev, "Error: %s\n", errmsg); \ +} while (0) + +#define SLAVE_NL_ERR(bond_dev, slave_dev, extack, errmsg) do { \ + if (extack) \ + NL_SET_ERR_MSG(extack, errmsg); \ + else \ + slave_err(bond_dev, slave_dev, "Error: %s\n", errmsg); \ +} while (0) + /* enslave device <slave> to bond device <master> */ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev, struct netlink_ext_ack *extack) @@ -1725,29 +1758,26 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev, if (slave_dev->flags & IFF_MASTER && !netif_is_bond_master(slave_dev)) { - NL_SET_ERR_MSG(extack, "Device with IFF_MASTER cannot be enslaved"); - netdev_err(bond_dev, - "Error: Device with IFF_MASTER cannot be enslaved\n"); + BOND_NL_ERR(bond_dev, extack, + "Device type (master device) cannot be enslaved"); return -EPERM; } if (!bond->params.use_carrier && slave_dev->ethtool_ops->get_link == NULL && - slave_ops->ndo_do_ioctl == NULL) { + slave_ops->ndo_eth_ioctl == NULL) { slave_warn(bond_dev, slave_dev, "no link monitoring support\n"); } /* already in-use? */ if (netdev_is_rx_handler_busy(slave_dev)) { - NL_SET_ERR_MSG(extack, "Device is in use and cannot be enslaved"); - slave_err(bond_dev, slave_dev, - "Error: Device is in use and cannot be enslaved\n"); + SLAVE_NL_ERR(bond_dev, slave_dev, extack, + "Device is in use and cannot be enslaved"); return -EBUSY; } if (bond_dev == slave_dev) { - NL_SET_ERR_MSG(extack, "Cannot enslave bond to itself."); - netdev_err(bond_dev, "cannot enslave bond to itself.\n"); + BOND_NL_ERR(bond_dev, extack, "Cannot enslave bond to itself."); return -EPERM; } @@ -1756,8 +1786,8 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev, if (slave_dev->features & NETIF_F_VLAN_CHALLENGED) { slave_dbg(bond_dev, slave_dev, "is NETIF_F_VLAN_CHALLENGED\n"); if (vlan_uses_dev(bond_dev)) { - NL_SET_ERR_MSG(extack, "Can not enslave VLAN challenged device to VLAN enabled bond"); - slave_err(bond_dev, slave_dev, "Error: cannot enslave VLAN challenged slave on VLAN enabled bond\n"); + SLAVE_NL_ERR(bond_dev, slave_dev, extack, + "Can not enslave VLAN challenged device to VLAN enabled bond"); return -EPERM; } else { slave_warn(bond_dev, slave_dev, "enslaved VLAN challenged slave. Adding VLANs will be blocked as long as it is part of bond.\n"); @@ -1775,8 +1805,8 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev, * enslaving it; the old ifenslave will not. */ if (slave_dev->flags & IFF_UP) { - NL_SET_ERR_MSG(extack, "Device can not be enslaved while up"); - slave_err(bond_dev, slave_dev, "slave is up - this may be due to an out of date ifenslave\n"); + SLAVE_NL_ERR(bond_dev, slave_dev, extack, + "Device can not be enslaved while up"); return -EPERM; } @@ -1815,17 +1845,15 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev, bond_dev); } } else if (bond_dev->type != slave_dev->type) { - NL_SET_ERR_MSG(extack, "Device type is different from other slaves"); - slave_err(bond_dev, slave_dev, "ether type (%d) is different from other slaves (%d), can not enslave it\n", - slave_dev->type, bond_dev->type); + SLAVE_NL_ERR(bond_dev, slave_dev, extack, + "Device type is different from other slaves"); return -EINVAL; } if (slave_dev->type == ARPHRD_INFINIBAND && BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) { - NL_SET_ERR_MSG(extack, "Only active-backup mode is supported for infiniband slaves"); - slave_warn(bond_dev, slave_dev, "Type (%d) supports only active-backup mode\n", - slave_dev->type); + SLAVE_NL_ERR(bond_dev, slave_dev, extack, + "Only active-backup mode is supported for infiniband slaves"); res = -EOPNOTSUPP; goto err_undo_flags; } @@ -1839,8 +1867,8 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev, bond->params.fail_over_mac = BOND_FOM_ACTIVE; slave_warn(bond_dev, slave_dev, "Setting fail_over_mac to active for active-backup mode\n"); } else { - NL_SET_ERR_MSG(extack, "Slave device does not support setting the MAC address, but fail_over_mac is not set to active"); - slave_err(bond_dev, slave_dev, "The slave device specified does not support setting the MAC address, but fail_over_mac is not set to active\n"); + SLAVE_NL_ERR(bond_dev, slave_dev, extack, + "Slave device does not support setting the MAC address, but fail_over_mac is not set to active"); res = -EOPNOTSUPP; goto err_undo_flags; } @@ -2133,6 +2161,39 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev, bond_update_slave_arr(bond, NULL); + if (!slave_dev->netdev_ops->ndo_bpf || + !slave_dev->netdev_ops->ndo_xdp_xmit) { + if (bond->xdp_prog) { + SLAVE_NL_ERR(bond_dev, slave_dev, extack, + "Slave does not support XDP"); + res = -EOPNOTSUPP; + goto err_sysfs_del; + } + } else if (bond->xdp_prog) { + struct netdev_bpf xdp = { + .command = XDP_SETUP_PROG, + .flags = 0, + .prog = bond->xdp_prog, + .extack = extack, + }; + + if (dev_xdp_prog_count(slave_dev) > 0) { + SLAVE_NL_ERR(bond_dev, slave_dev, extack, + "Slave has XDP program loaded, please unload before enslaving"); + res = -EOPNOTSUPP; + goto err_sysfs_del; + } + + res = slave_dev->netdev_ops->ndo_bpf(slave_dev, &xdp); + if (res < 0) { + /* ndo_bpf() sets extack error message */ + slave_dbg(bond_dev, slave_dev, "Error %d calling ndo_bpf\n", res); + goto err_sysfs_del; + } + if (bond->xdp_prog) + bpf_prog_inc(bond->xdp_prog); + } + slave_info(bond_dev, slave_dev, "Enslaving as %s interface with %s link\n", bond_is_active_slave(new_slave) ? "an active" : "a backup", new_slave->link != BOND_LINK_DOWN ? "an up" : "a down"); @@ -2252,7 +2313,17 @@ static int __bond_release_one(struct net_device *bond_dev, /* recompute stats just before removing the slave */ bond_get_stats(bond->dev, &bond->bond_stats); - bond_upper_dev_unlink(bond, slave); + if (bond->xdp_prog) { + struct netdev_bpf xdp = { + .command = XDP_SETUP_PROG, + .flags = 0, + .prog = NULL, + .extack = NULL, + }; + if (slave_dev->netdev_ops->ndo_bpf(slave_dev, &xdp)) + slave_warn(bond_dev, slave_dev, "failed to unload XDP program\n"); + } + /* unregister rx_handler early so bond_handle_frame wouldn't be called * for this slave anymore. */ @@ -2261,6 +2332,8 @@ static int __bond_release_one(struct net_device *bond_dev, if (BOND_MODE(bond) == BOND_MODE_8023AD) bond_3ad_unbind_slave(slave); + bond_upper_dev_unlink(bond, slave); + if (bond_mode_can_use_xmit_hash(bond)) bond_update_slave_arr(bond, slave); @@ -2837,9 +2910,9 @@ static void bond_arp_send_all(struct bonding *bond, struct slave *slave) * probe to generate any traffic (arp_validate=0) */ if (bond->params.arp_validate) - net_warn_ratelimited("%s: no route to arp_ip_target %pI4 and arp_validate is set\n", - bond->dev->name, - &targets[i]); + pr_warn_once("%s: no route to arp_ip_target %pI4 and arp_validate is set\n", + bond->dev->name, + &targets[i]); bond_arp_send(slave, ARPOP_REQUEST, targets[i], 0, tags); continue; @@ -3613,90 +3686,112 @@ static struct notifier_block bond_netdev_notifier = { /*---------------------------- Hashing Policies -----------------------------*/ +/* Helper to access data in a packet, with or without a backing skb. + * If skb is given the data is linearized if necessary via pskb_may_pull. + */ +static inline const void *bond_pull_data(struct sk_buff *skb, + const void *data, int hlen, int n) +{ + if (likely(n <= hlen)) + return data; + else if (skb && likely(pskb_may_pull(skb, n))) + return skb->head; + + return NULL; +} + /* L2 hash helper */ -static inline u32 bond_eth_hash(struct sk_buff *skb) +static inline u32 bond_eth_hash(struct sk_buff *skb, const void *data, int mhoff, int hlen) { - struct ethhdr *ep, hdr_tmp; + struct ethhdr *ep; - ep = skb_header_pointer(skb, 0, sizeof(hdr_tmp), &hdr_tmp); - if (ep) - return ep->h_dest[5] ^ ep->h_source[5] ^ ep->h_proto; - return 0; + data = bond_pull_data(skb, data, hlen, mhoff + sizeof(struct ethhdr)); + if (!data) + return 0; + + ep = (struct ethhdr *)(data + mhoff); + return ep->h_dest[5] ^ ep->h_source[5] ^ be16_to_cpu(ep->h_proto); } -static bool bond_flow_ip(struct sk_buff *skb, struct flow_keys *fk, - int *noff, int *proto, bool l34) +static bool bond_flow_ip(struct sk_buff *skb, struct flow_keys *fk, const void *data, + int hlen, __be16 l2_proto, int *nhoff, int *ip_proto, bool l34) { const struct ipv6hdr *iph6; const struct iphdr *iph; - if (skb->protocol == htons(ETH_P_IP)) { - if (unlikely(!pskb_may_pull(skb, *noff + sizeof(*iph)))) + if (l2_proto == htons(ETH_P_IP)) { + data = bond_pull_data(skb, data, hlen, *nhoff + sizeof(*iph)); + if (!data) return false; - iph = (const struct iphdr *)(skb->data + *noff); + + iph = (const struct iphdr *)(data + *nhoff); iph_to_flow_copy_v4addrs(fk, iph); - *noff += iph->ihl << 2; + *nhoff += iph->ihl << 2; if (!ip_is_fragment(iph)) - *proto = iph->protocol; - } else if (skb->protocol == htons(ETH_P_IPV6)) { - if (unlikely(!pskb_may_pull(skb, *noff + sizeof(*iph6)))) + *ip_proto = iph->protocol; + } else if (l2_proto == htons(ETH_P_IPV6)) { + data = bond_pull_data(skb, data, hlen, *nhoff + sizeof(*iph6)); + if (!data) return false; - iph6 = (const struct ipv6hdr *)(skb->data + *noff); + + iph6 = (const struct ipv6hdr *)(data + *nhoff); iph_to_flow_copy_v6addrs(fk, iph6); - *noff += sizeof(*iph6); - *proto = iph6->nexthdr; + *nhoff += sizeof(*iph6); + *ip_proto = iph6->nexthdr; } else { return false; } - if (l34 && *proto >= 0) - fk->ports.ports = skb_flow_get_ports(skb, *noff, *proto); + if (l34 && *ip_proto >= 0) + fk->ports.ports = __skb_flow_get_ports(skb, *nhoff, *ip_proto, data, hlen); return true; } -static u32 bond_vlan_srcmac_hash(struct sk_buff *skb) +static u32 bond_vlan_srcmac_hash(struct sk_buff *skb, const void *data, int mhoff, int hlen) { - struct ethhdr *mac_hdr = (struct ethhdr *)skb_mac_header(skb); u32 srcmac_vendor = 0, srcmac_dev = 0; - u16 vlan; + struct ethhdr *mac_hdr; + u16 vlan = 0; int i; + data = bond_pull_data(skb, data, hlen, mhoff + sizeof(struct ethhdr)); + if (!data) + return 0; + mac_hdr = (struct ethhdr *)(data + mhoff); + for (i = 0; i < 3; i++) srcmac_vendor = (srcmac_vendor << 8) | mac_hdr->h_source[i]; for (i = 3; i < ETH_ALEN; i++) srcmac_dev = (srcmac_dev << 8) | mac_hdr->h_source[i]; - if (!skb_vlan_tag_present(skb)) - return srcmac_vendor ^ srcmac_dev; - - vlan = skb_vlan_tag_get(skb); + if (skb && skb_vlan_tag_present(skb)) + vlan = skb_vlan_tag_get(skb); return vlan ^ srcmac_vendor ^ srcmac_dev; } /* Extract the appropriate headers based on bond's xmit policy */ -static bool bond_flow_dissect(struct bonding *bond, struct sk_buff *skb, - struct flow_keys *fk) +static bool bond_flow_dissect(struct bonding *bond, struct sk_buff *skb, const void *data, + __be16 l2_proto, int nhoff, int hlen, struct flow_keys *fk) { bool l34 = bond->params.xmit_policy == BOND_XMIT_POLICY_LAYER34; - int noff, proto = -1; + int ip_proto = -1; switch (bond->params.xmit_policy) { case BOND_XMIT_POLICY_ENCAP23: case BOND_XMIT_POLICY_ENCAP34: memset(fk, 0, sizeof(*fk)); return __skb_flow_dissect(NULL, skb, &flow_keys_bonding, - fk, NULL, 0, 0, 0, 0); + fk, data, l2_proto, nhoff, hlen, 0); default: break; } fk->ports.ports = 0; memset(&fk->icmp, 0, sizeof(fk->icmp)); - noff = skb_network_offset(skb); - if (!bond_flow_ip(skb, fk, &noff, &proto, l34)) + if (!bond_flow_ip(skb, fk, data, hlen, l2_proto, &nhoff, &ip_proto, l34)) return false; /* ICMP error packets contains at least 8 bytes of the header @@ -3704,22 +3799,20 @@ static bool bond_flow_dissect(struct bonding *bond, struct sk_buff *skb, * to correlate ICMP error packets within the same flow which * generated the error. */ - if (proto == IPPROTO_ICMP || proto == IPPROTO_ICMPV6) { - skb_flow_get_icmp_tci(skb, &fk->icmp, skb->data, - skb_transport_offset(skb), - skb_headlen(skb)); - if (proto == IPPROTO_ICMP) { + if (ip_proto == IPPROTO_ICMP || ip_proto == IPPROTO_ICMPV6) { + skb_flow_get_icmp_tci(skb, &fk->icmp, data, nhoff, hlen); + if (ip_proto == IPPROTO_ICMP) { if (!icmp_is_err(fk->icmp.type)) return true; - noff += sizeof(struct icmphdr); - } else if (proto == IPPROTO_ICMPV6) { + nhoff += sizeof(struct icmphdr); + } else if (ip_proto == IPPROTO_ICMPV6) { if (!icmpv6_is_err(fk->icmp.type)) return true; - noff += sizeof(struct icmp6hdr); + nhoff += sizeof(struct icmp6hdr); } - return bond_flow_ip(skb, fk, &noff, &proto, l34); + return bond_flow_ip(skb, fk, data, hlen, l2_proto, &nhoff, &ip_proto, l34); } return true; @@ -3735,33 +3828,26 @@ static u32 bond_ip_hash(u32 hash, struct flow_keys *flow) return hash >> 1; } -/** - * bond_xmit_hash - generate a hash value based on the xmit policy - * @bond: bonding device - * @skb: buffer to use for headers - * - * This function will extract the necessary headers from the skb buffer and use - * them to generate a hash based on the xmit_policy set in the bonding device +/* Generate hash based on xmit policy. If @skb is given it is used to linearize + * the data as required, but this function can be used without it if the data is + * known to be linear (e.g. with xdp_buff). */ -u32 bond_xmit_hash(struct bonding *bond, struct sk_buff *skb) +static u32 __bond_xmit_hash(struct bonding *bond, struct sk_buff *skb, const void *data, + __be16 l2_proto, int mhoff, int nhoff, int hlen) { struct flow_keys flow; u32 hash; - if (bond->params.xmit_policy == BOND_XMIT_POLICY_ENCAP34 && - skb->l4_hash) - return skb->hash; - if (bond->params.xmit_policy == BOND_XMIT_POLICY_VLAN_SRCMAC) - return bond_vlan_srcmac_hash(skb); + return bond_vlan_srcmac_hash(skb, data, mhoff, hlen); if (bond->params.xmit_policy == BOND_XMIT_POLICY_LAYER2 || - !bond_flow_dissect(bond, skb, &flow)) - return bond_eth_hash(skb); + !bond_flow_dissect(bond, skb, data, l2_proto, nhoff, hlen, &flow)) + return bond_eth_hash(skb, data, mhoff, hlen); if (bond->params.xmit_policy == BOND_XMIT_POLICY_LAYER23 || bond->params.xmit_policy == BOND_XMIT_POLICY_ENCAP23) { - hash = bond_eth_hash(skb); + hash = bond_eth_hash(skb, data, mhoff, hlen); } else { if (flow.icmp.id) memcpy(&hash, &flow.icmp, sizeof(hash)); @@ -3772,6 +3858,45 @@ u32 bond_xmit_hash(struct bonding *bond, struct sk_buff *skb) return bond_ip_hash(hash, &flow); } +/** + * bond_xmit_hash - generate a hash value based on the xmit policy + * @bond: bonding device + * @skb: buffer to use for headers + * + * This function will extract the necessary headers from the skb buffer and use + * them to generate a hash based on the xmit_policy set in the bonding device + */ +u32 bond_xmit_hash(struct bonding *bond, struct sk_buff *skb) +{ + if (bond->params.xmit_policy == BOND_XMIT_POLICY_ENCAP34 && + skb->l4_hash) + return skb->hash; + + return __bond_xmit_hash(bond, skb, skb->head, skb->protocol, + skb->mac_header, skb->network_header, + skb_headlen(skb)); +} + +/** + * bond_xmit_hash_xdp - generate a hash value based on the xmit policy + * @bond: bonding device + * @xdp: buffer to use for headers + * + * The XDP variant of bond_xmit_hash. + */ +static u32 bond_xmit_hash_xdp(struct bonding *bond, struct xdp_buff *xdp) +{ + struct ethhdr *eth; + + if (xdp->data + sizeof(struct ethhdr) > xdp->data_end) + return 0; + + eth = (struct ethhdr *)xdp->data; + + return __bond_xmit_hash(bond, NULL, xdp->data, eth->h_proto, 0, + sizeof(struct ethhdr), xdp->data_end - xdp->data); +} + /*-------------------------- Device entry points ----------------------------*/ void bond_work_init_all(struct bonding *bond) @@ -3962,20 +4087,13 @@ static void bond_get_stats(struct net_device *bond_dev, rcu_read_unlock(); } -static int bond_do_ioctl(struct net_device *bond_dev, struct ifreq *ifr, int cmd) +static int bond_eth_ioctl(struct net_device *bond_dev, struct ifreq *ifr, int cmd) { struct bonding *bond = netdev_priv(bond_dev); - struct net_device *slave_dev = NULL; - struct ifbond k_binfo; - struct ifbond __user *u_binfo = NULL; - struct ifslave k_sinfo; - struct ifslave __user *u_sinfo = NULL; struct mii_ioctl_data *mii = NULL; - struct bond_opt_value newval; - struct net *net; - int res = 0; + int res; - netdev_dbg(bond_dev, "bond_ioctl: cmd=%d\n", cmd); + netdev_dbg(bond_dev, "bond_eth_ioctl: cmd=%d\n", cmd); switch (cmd) { case SIOCGMIIPHY: @@ -4000,7 +4118,28 @@ static int bond_do_ioctl(struct net_device *bond_dev, struct ifreq *ifr, int cmd } return 0; - case BOND_INFO_QUERY_OLD: + default: + res = -EOPNOTSUPP; + } + + return res; +} + +static int bond_do_ioctl(struct net_device *bond_dev, struct ifreq *ifr, int cmd) +{ + struct bonding *bond = netdev_priv(bond_dev); + struct net_device *slave_dev = NULL; + struct ifbond k_binfo; + struct ifbond __user *u_binfo = NULL; + struct ifslave k_sinfo; + struct ifslave __user *u_sinfo = NULL; + struct bond_opt_value newval; + struct net *net; + int res = 0; + + netdev_dbg(bond_dev, "bond_ioctl: cmd=%d\n", cmd); + + switch (cmd) { case SIOCBONDINFOQUERY: u_binfo = (struct ifbond __user *)ifr->ifr_data; @@ -4012,7 +4151,6 @@ static int bond_do_ioctl(struct net_device *bond_dev, struct ifreq *ifr, int cmd return -EFAULT; return 0; - case BOND_SLAVE_INFO_QUERY_OLD: case SIOCBONDSLAVEINFOQUERY: u_sinfo = (struct ifslave __user *)ifr->ifr_data; @@ -4042,19 +4180,15 @@ static int bond_do_ioctl(struct net_device *bond_dev, struct ifreq *ifr, int cmd return -ENODEV; switch (cmd) { - case BOND_ENSLAVE_OLD: case SIOCBONDENSLAVE: res = bond_enslave(bond_dev, slave_dev, NULL); break; - case BOND_RELEASE_OLD: case SIOCBONDRELEASE: res = bond_release(bond_dev, slave_dev); break; - case BOND_SETHWADDR_OLD: case SIOCBONDSETHWADDR: res = bond_set_dev_addr(bond_dev, slave_dev); break; - case BOND_CHANGE_ACTIVE_OLD: case SIOCBONDCHANGEACTIVE: bond_opt_initstr(&newval, slave_dev->name); res = __bond_opt_set_notify(bond, BOND_OPT_ACTIVE_SLAVE, @@ -4067,6 +4201,29 @@ static int bond_do_ioctl(struct net_device *bond_dev, struct ifreq *ifr, int cmd return res; } +static int bond_siocdevprivate(struct net_device *bond_dev, struct ifreq *ifr, + void __user *data, int cmd) +{ + struct ifreq ifrdata = { .ifr_data = data }; + + switch (cmd) { + case BOND_INFO_QUERY_OLD: + return bond_do_ioctl(bond_dev, &ifrdata, SIOCBONDINFOQUERY); + case BOND_SLAVE_INFO_QUERY_OLD: + return bond_do_ioctl(bond_dev, &ifrdata, SIOCBONDSLAVEINFOQUERY); + case BOND_ENSLAVE_OLD: + return bond_do_ioctl(bond_dev, ifr, SIOCBONDENSLAVE); + case BOND_RELEASE_OLD: + return bond_do_ioctl(bond_dev, ifr, SIOCBONDRELEASE); + case BOND_SETHWADDR_OLD: + return bond_do_ioctl(bond_dev, ifr, SIOCBONDSETHWADDR); + case BOND_CHANGE_ACTIVE_OLD: + return bond_do_ioctl(bond_dev, ifr, SIOCBONDCHANGEACTIVE); + } + + return -EOPNOTSUPP; +} + static void bond_change_rx_flags(struct net_device *bond_dev, int change) { struct bonding *bond = netdev_priv(bond_dev); @@ -4388,6 +4545,47 @@ non_igmp: return NULL; } +static struct slave *bond_xdp_xmit_roundrobin_slave_get(struct bonding *bond, + struct xdp_buff *xdp) +{ + struct slave *slave; + int slave_cnt; + u32 slave_id; + const struct ethhdr *eth; + void *data = xdp->data; + + if (data + sizeof(struct ethhdr) > xdp->data_end) + goto non_igmp; + + eth = (struct ethhdr *)data; + data += sizeof(struct ethhdr); + + /* See comment on IGMP in bond_xmit_roundrobin_slave_get() */ + if (eth->h_proto == htons(ETH_P_IP)) { + const struct iphdr *iph; + + if (data + sizeof(struct iphdr) > xdp->data_end) + goto non_igmp; + + iph = (struct iphdr *)data; + + if (iph->protocol == IPPROTO_IGMP) { + slave = rcu_dereference(bond->curr_active_slave); + if (slave) + return slave; + return bond_get_slave_by_id(bond, 0); + } + } + +non_igmp: + slave_cnt = READ_ONCE(bond->slave_cnt); + if (likely(slave_cnt)) { + slave_id = bond_rr_gen_slave_id(bond) % slave_cnt; + return bond_get_slave_by_id(bond, slave_id); + } + return NULL; +} + static netdev_tx_t bond_xmit_roundrobin(struct sk_buff *skb, struct net_device *bond_dev) { @@ -4401,8 +4599,7 @@ static netdev_tx_t bond_xmit_roundrobin(struct sk_buff *skb, return bond_tx_drop(bond_dev, skb); } -static struct slave *bond_xmit_activebackup_slave_get(struct bonding *bond, - struct sk_buff *skb) +static struct slave *bond_xmit_activebackup_slave_get(struct bonding *bond) { return rcu_dereference(bond->curr_active_slave); } @@ -4416,7 +4613,7 @@ static netdev_tx_t bond_xmit_activebackup(struct sk_buff *skb, struct bonding *bond = netdev_priv(bond_dev); struct slave *slave; - slave = bond_xmit_activebackup_slave_get(bond, skb); + slave = bond_xmit_activebackup_slave_get(bond); if (slave) return bond_dev_queue_xmit(bond, skb, slave->dev); @@ -4604,6 +4801,22 @@ static struct slave *bond_xmit_3ad_xor_slave_get(struct bonding *bond, return slave; } +static struct slave *bond_xdp_xmit_3ad_xor_slave_get(struct bonding *bond, + struct xdp_buff *xdp) +{ + struct bond_up_slave *slaves; + unsigned int count; + u32 hash; + + hash = bond_xmit_hash_xdp(bond, xdp); + slaves = rcu_dereference(bond->usable_slaves); + count = slaves ? READ_ONCE(slaves->count) : 0; + if (unlikely(!count)) + return NULL; + + return slaves->arr[hash % count]; +} + /* Use this Xmit function for 3AD as well as XOR modes. The current * usable slave array is formed in the control path. The xmit function * just calculates hash and sends the packet out. @@ -4714,7 +4927,7 @@ static struct net_device *bond_xmit_get_slave(struct net_device *master_dev, slave = bond_xmit_roundrobin_slave_get(bond, skb); break; case BOND_MODE_ACTIVEBACKUP: - slave = bond_xmit_activebackup_slave_get(bond, skb); + slave = bond_xmit_activebackup_slave_get(bond); break; case BOND_MODE_8023AD: case BOND_MODE_XOR: @@ -4888,6 +5101,171 @@ static netdev_tx_t bond_start_xmit(struct sk_buff *skb, struct net_device *dev) return ret; } +static struct net_device * +bond_xdp_get_xmit_slave(struct net_device *bond_dev, struct xdp_buff *xdp) +{ + struct bonding *bond = netdev_priv(bond_dev); + struct slave *slave; + + /* Caller needs to hold rcu_read_lock() */ + + switch (BOND_MODE(bond)) { + case BOND_MODE_ROUNDROBIN: + slave = bond_xdp_xmit_roundrobin_slave_get(bond, xdp); + break; + + case BOND_MODE_ACTIVEBACKUP: + slave = bond_xmit_activebackup_slave_get(bond); + break; + + case BOND_MODE_8023AD: + case BOND_MODE_XOR: + slave = bond_xdp_xmit_3ad_xor_slave_get(bond, xdp); + break; + + default: + /* Should never happen. Mode guarded by bond_xdp_check() */ + netdev_err(bond_dev, "Unknown bonding mode %d for xdp xmit\n", BOND_MODE(bond)); + WARN_ON_ONCE(1); + return NULL; + } + + if (slave) + return slave->dev; + + return NULL; +} + +static int bond_xdp_xmit(struct net_device *bond_dev, + int n, struct xdp_frame **frames, u32 flags) +{ + int nxmit, err = -ENXIO; + + rcu_read_lock(); + + for (nxmit = 0; nxmit < n; nxmit++) { + struct xdp_frame *frame = frames[nxmit]; + struct xdp_frame *frames1[] = {frame}; + struct net_device *slave_dev; + struct xdp_buff xdp; + + xdp_convert_frame_to_buff(frame, &xdp); + + slave_dev = bond_xdp_get_xmit_slave(bond_dev, &xdp); + if (!slave_dev) { + err = -ENXIO; + break; + } + + err = slave_dev->netdev_ops->ndo_xdp_xmit(slave_dev, 1, frames1, flags); + if (err < 1) + break; + } + + rcu_read_unlock(); + + /* If error happened on the first frame then we can pass the error up, otherwise + * report the number of frames that were xmitted. + */ + if (err < 0) + return (nxmit == 0 ? err : nxmit); + + return nxmit; +} + +static int bond_xdp_set(struct net_device *dev, struct bpf_prog *prog, + struct netlink_ext_ack *extack) +{ + struct bonding *bond = netdev_priv(dev); + struct list_head *iter; + struct slave *slave, *rollback_slave; + struct bpf_prog *old_prog; + struct netdev_bpf xdp = { + .command = XDP_SETUP_PROG, + .flags = 0, + .prog = prog, + .extack = extack, + }; + int err; + + ASSERT_RTNL(); + + if (!bond_xdp_check(bond)) + return -EOPNOTSUPP; + + old_prog = bond->xdp_prog; + bond->xdp_prog = prog; + + bond_for_each_slave(bond, slave, iter) { + struct net_device *slave_dev = slave->dev; + + if (!slave_dev->netdev_ops->ndo_bpf || + !slave_dev->netdev_ops->ndo_xdp_xmit) { + SLAVE_NL_ERR(dev, slave_dev, extack, + "Slave device does not support XDP"); + err = -EOPNOTSUPP; + goto err; + } + + if (dev_xdp_prog_count(slave_dev) > 0) { + SLAVE_NL_ERR(dev, slave_dev, extack, + "Slave has XDP program loaded, please unload before enslaving"); + err = -EOPNOTSUPP; + goto err; + } + + err = slave_dev->netdev_ops->ndo_bpf(slave_dev, &xdp); + if (err < 0) { + /* ndo_bpf() sets extack error message */ + slave_err(dev, slave_dev, "Error %d calling ndo_bpf\n", err); + goto err; + } + if (prog) + bpf_prog_inc(prog); + } + + if (prog) { + static_branch_inc(&bpf_master_redirect_enabled_key); + } else if (old_prog) { + bpf_prog_put(old_prog); + static_branch_dec(&bpf_master_redirect_enabled_key); + } + + return 0; + +err: + /* unwind the program changes */ + bond->xdp_prog = old_prog; + xdp.prog = old_prog; + xdp.extack = NULL; /* do not overwrite original error */ + + bond_for_each_slave(bond, rollback_slave, iter) { + struct net_device *slave_dev = rollback_slave->dev; + int err_unwind; + + if (slave == rollback_slave) + break; + + err_unwind = slave_dev->netdev_ops->ndo_bpf(slave_dev, &xdp); + if (err_unwind < 0) + slave_err(dev, slave_dev, + "Error %d when unwinding XDP program change\n", err_unwind); + else if (xdp.prog) + bpf_prog_inc(xdp.prog); + } + return err; +} + +static int bond_xdp(struct net_device *dev, struct netdev_bpf *xdp) +{ + switch (xdp->command) { + case XDP_SETUP_PROG: + return bond_xdp_set(dev, xdp->prog, xdp->extack); + default: + return -EINVAL; + } +} + static u32 bond_mode_bcast_speed(struct slave *slave, u32 speed) { if (speed == 0 || speed == SPEED_UNKNOWN) @@ -4955,7 +5333,9 @@ static const struct net_device_ops bond_netdev_ops = { .ndo_start_xmit = bond_start_xmit, .ndo_select_queue = bond_select_queue, .ndo_get_stats64 = bond_get_stats, - .ndo_do_ioctl = bond_do_ioctl, + .ndo_eth_ioctl = bond_eth_ioctl, + .ndo_siocbond = bond_do_ioctl, + .ndo_siocdevprivate = bond_siocdevprivate, .ndo_change_rx_flags = bond_change_rx_flags, .ndo_set_rx_mode = bond_set_rx_mode, .ndo_change_mtu = bond_change_mtu, @@ -4974,6 +5354,9 @@ static const struct net_device_ops bond_netdev_ops = { .ndo_features_check = passthru_features_check, .ndo_get_xmit_slave = bond_xmit_get_slave, .ndo_sk_get_lower_dev = bond_sk_get_lower_dev, + .ndo_bpf = bond_xdp, + .ndo_xdp_xmit = bond_xdp_xmit, + .ndo_xdp_get_xmit_slave = bond_xdp_get_xmit_slave, }; static const struct device_type bond_type = { @@ -5443,6 +5826,7 @@ static int bond_check_params(struct bond_params *params) params->downdelay = downdelay; params->peer_notif_delay = 0; params->use_carrier = use_carrier; + params->lacp_active = 1; params->lacp_fast = lacp_fast; params->primary[0] = 0; params->primary_reselect = primary_reselect_value; diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c index 0561ece1ba45..5d54e11d18fa 100644 --- a/drivers/net/bonding/bond_netlink.c +++ b/drivers/net/bonding/bond_netlink.c @@ -100,6 +100,7 @@ static const struct nla_policy bond_policy[IFLA_BOND_MAX + 1] = { [IFLA_BOND_MIN_LINKS] = { .type = NLA_U32 }, [IFLA_BOND_LP_INTERVAL] = { .type = NLA_U32 }, [IFLA_BOND_PACKETS_PER_SLAVE] = { .type = NLA_U32 }, + [IFLA_BOND_AD_LACP_ACTIVE] = { .type = NLA_U8 }, [IFLA_BOND_AD_LACP_RATE] = { .type = NLA_U8 }, [IFLA_BOND_AD_SELECT] = { .type = NLA_U8 }, [IFLA_BOND_AD_INFO] = { .type = NLA_NESTED }, @@ -387,6 +388,16 @@ static int bond_changelink(struct net_device *bond_dev, struct nlattr *tb[], if (err) return err; } + + if (data[IFLA_BOND_AD_LACP_ACTIVE]) { + int lacp_active = nla_get_u8(data[IFLA_BOND_AD_LACP_ACTIVE]); + + bond_opt_initval(&newval, lacp_active); + err = __bond_opt_set(bond, BOND_OPT_LACP_ACTIVE, &newval); + if (err) + return err; + } + if (data[IFLA_BOND_AD_LACP_RATE]) { int lacp_rate = nla_get_u8(data[IFLA_BOND_AD_LACP_RATE]); @@ -490,6 +501,7 @@ static size_t bond_get_size(const struct net_device *bond_dev) nla_total_size(sizeof(u32)) + /* IFLA_BOND_MIN_LINKS */ nla_total_size(sizeof(u32)) + /* IFLA_BOND_LP_INTERVAL */ nla_total_size(sizeof(u32)) + /* IFLA_BOND_PACKETS_PER_SLAVE */ + nla_total_size(sizeof(u8)) + /* IFLA_BOND_AD_LACP_ACTIVE */ nla_total_size(sizeof(u8)) + /* IFLA_BOND_AD_LACP_RATE */ nla_total_size(sizeof(u8)) + /* IFLA_BOND_AD_SELECT */ nla_total_size(sizeof(struct nlattr)) + /* IFLA_BOND_AD_INFO */ @@ -622,6 +634,10 @@ static int bond_fill_info(struct sk_buff *skb, packets_per_slave)) goto nla_put_failure; + if (nla_put_u8(skb, IFLA_BOND_AD_LACP_ACTIVE, + bond->params.lacp_active)) + goto nla_put_failure; + if (nla_put_u8(skb, IFLA_BOND_AD_LACP_RATE, bond->params.lacp_fast)) goto nla_put_failure; diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c index 0cf25de6f46d..a8fde3bc458f 100644 --- a/drivers/net/bonding/bond_options.c +++ b/drivers/net/bonding/bond_options.c @@ -58,6 +58,8 @@ static int bond_option_lp_interval_set(struct bonding *bond, const struct bond_opt_value *newval); static int bond_option_pps_set(struct bonding *bond, const struct bond_opt_value *newval); +static int bond_option_lacp_active_set(struct bonding *bond, + const struct bond_opt_value *newval); static int bond_option_lacp_rate_set(struct bonding *bond, const struct bond_opt_value *newval); static int bond_option_ad_select_set(struct bonding *bond, @@ -135,6 +137,12 @@ static const struct bond_opt_value bond_intmax_tbl[] = { { NULL, -1, 0} }; +static const struct bond_opt_value bond_lacp_active[] = { + { "off", 0, 0}, + { "on", 1, BOND_VALFLAG_DEFAULT}, + { NULL, -1, 0} +}; + static const struct bond_opt_value bond_lacp_rate_tbl[] = { { "slow", AD_LACP_SLOW, 0}, { "fast", AD_LACP_FAST, 0}, @@ -283,6 +291,15 @@ static const struct bond_option bond_opts[BOND_OPT_LAST] = { .values = bond_intmax_tbl, .set = bond_option_updelay_set }, + [BOND_OPT_LACP_ACTIVE] = { + .id = BOND_OPT_LACP_ACTIVE, + .name = "lacp_active", + .desc = "Send LACPDU frames with configured lacp rate or acts as speak when spoken to", + .flags = BOND_OPTFLAG_IFDOWN, + .unsuppmodes = BOND_MODE_ALL_EX(BIT(BOND_MODE_8023AD)), + .values = bond_lacp_active, + .set = bond_option_lacp_active_set + }, [BOND_OPT_LACP_RATE] = { .id = BOND_OPT_LACP_RATE, .name = "lacp_rate", @@ -1333,6 +1350,16 @@ static int bond_option_pps_set(struct bonding *bond, return 0; } +static int bond_option_lacp_active_set(struct bonding *bond, + const struct bond_opt_value *newval) +{ + netdev_dbg(bond->dev, "Setting LACP active to %s (%llu)\n", + newval->string, newval->value); + bond->params.lacp_active = newval->value; + + return 0; +} + static int bond_option_lacp_rate_set(struct bonding *bond, const struct bond_opt_value *newval) { diff --git a/drivers/net/bonding/bond_procfs.c b/drivers/net/bonding/bond_procfs.c index 0fb1da361bb1..f3e3bfd72556 100644 --- a/drivers/net/bonding/bond_procfs.c +++ b/drivers/net/bonding/bond_procfs.c @@ -133,6 +133,8 @@ static void bond_info_show_master(struct seq_file *seq) struct ad_info ad_info; seq_puts(seq, "\n802.3ad info\n"); + seq_printf(seq, "LACP active: %s\n", + (bond->params.lacp_active) ? "on" : "off"); seq_printf(seq, "LACP rate: %s\n", (bond->params.lacp_fast) ? "fast" : "slow"); seq_printf(seq, "Min links: %d\n", bond->params.min_links); diff --git a/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c index 5f9e9a240226..b9e9842fed94 100644 --- a/drivers/net/bonding/bond_sysfs.c +++ b/drivers/net/bonding/bond_sysfs.c @@ -339,10 +339,24 @@ static ssize_t bonding_show_peer_notif_delay(struct device *d, static DEVICE_ATTR(peer_notif_delay, 0644, bonding_show_peer_notif_delay, bonding_sysfs_store_option); -/* Show the LACP interval. */ -static ssize_t bonding_show_lacp(struct device *d, - struct device_attribute *attr, - char *buf) +/* Show the LACP activity and interval. */ +static ssize_t bonding_show_lacp_active(struct device *d, + struct device_attribute *attr, + char *buf) +{ + struct bonding *bond = to_bond(d); + const struct bond_opt_value *val; + + val = bond_opt_get_val(BOND_OPT_LACP_ACTIVE, bond->params.lacp_active); + + return sprintf(buf, "%s %d\n", val->string, bond->params.lacp_active); +} +static DEVICE_ATTR(lacp_active, 0644, + bonding_show_lacp_active, bonding_sysfs_store_option); + +static ssize_t bonding_show_lacp_rate(struct device *d, + struct device_attribute *attr, + char *buf) { struct bonding *bond = to_bond(d); const struct bond_opt_value *val; @@ -352,7 +366,7 @@ static ssize_t bonding_show_lacp(struct device *d, return sprintf(buf, "%s %d\n", val->string, bond->params.lacp_fast); } static DEVICE_ATTR(lacp_rate, 0644, - bonding_show_lacp, bonding_sysfs_store_option); + bonding_show_lacp_rate, bonding_sysfs_store_option); static ssize_t bonding_show_min_links(struct device *d, struct device_attribute *attr, @@ -738,6 +752,7 @@ static struct attribute *per_bond_attrs[] = { &dev_attr_downdelay.attr, &dev_attr_updelay.attr, &dev_attr_peer_notif_delay.attr, + &dev_attr_lacp_active.attr, &dev_attr_lacp_rate.attr, &dev_attr_ad_select.attr, &dev_attr_xmit_hash_policy.attr, |