summaryrefslogtreecommitdiff
path: root/drivers/net/bonding
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/net/bonding')
-rw-r--r--drivers/net/bonding/bond_main.c454
1 files changed, 397 insertions, 57 deletions
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 3ba5f4871162..365953e8013e 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -317,6 +317,19 @@ 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:
+ case BOND_MODE_8023AD:
+ case BOND_MODE_XOR:
+ return true;
+ default:
+ return false;
+ }
+}
+
/*---------------------------------- VLAN -----------------------------------*/
/* In the following 2 functions, bond_vlan_rx_add_vid and bond_vlan_rx_kill_vid,
@@ -2133,6 +2146,41 @@ 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) {
+ NL_SET_ERR_MSG(extack, "Slave does not support XDP");
+ slave_err(bond_dev, slave_dev, "Slave does not support XDP\n");
+ res = -EOPNOTSUPP;
+ goto err_sysfs_del;
+ }
+ } else {
+ struct netdev_bpf xdp = {
+ .command = XDP_SETUP_PROG,
+ .flags = 0,
+ .prog = bond->xdp_prog,
+ .extack = extack,
+ };
+
+ if (dev_xdp_prog_count(slave_dev) > 0) {
+ NL_SET_ERR_MSG(extack,
+ "Slave has XDP program loaded, please unload before enslaving");
+ slave_err(bond_dev, slave_dev,
+ "Slave has XDP program loaded, please unload before enslaving\n");
+ 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");
@@ -2252,6 +2300,17 @@ 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);
+ 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.
*/
@@ -3614,55 +3673,80 @@ 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);
+ struct ethhdr *mac_hdr;
u32 srcmac_vendor = 0, srcmac_dev = 0;
u16 vlan;
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];
@@ -3678,26 +3762,25 @@ static u32 bond_vlan_srcmac_hash(struct sk_buff *skb)
}
/* 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
@@ -3705,22 +3788,20 @@ 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;
@@ -3736,33 +3817,26 @@ 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));
@@ -3773,6 +3847,45 @@ 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)
@@ -4421,6 +4534,47 @@ 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)
{
@@ -4434,8 +4588,7 @@ 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);
}
@@ -4449,7 +4602,7 @@ 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);
@@ -4637,6 +4790,22 @@ 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.
@@ -4747,7 +4916,7 @@ 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:
@@ -4921,6 +5090,174 @@ 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) {
+ NL_SET_ERR_MSG(extack, "Slave device does not support XDP");
+ slave_err(dev, slave_dev, "Slave does not support XDP\n");
+ err = -EOPNOTSUPP;
+ goto err;
+ }
+
+ if (dev_xdp_prog_count(slave_dev) > 0) {
+ NL_SET_ERR_MSG(extack,
+ "Slave has XDP program loaded, please unload before enslaving");
+ slave_err(dev, slave_dev,
+ "Slave has XDP program loaded, please unload before enslaving\n");
+ 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 (old_prog)
+ bpf_prog_put(old_prog);
+
+ if (prog)
+ static_branch_inc(&bpf_master_redirect_enabled_key);
+ else
+ 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)
@@ -5009,6 +5346,9 @@ 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 = {