Commit a815bde5 authored by Jussi Maki's avatar Jussi Maki Committed by Daniel Borkmann

net, bonding: Refactor bond_xmit_hash for use with xdp_buff

In preparation for adding XDP support to the bonding driver
refactor the packet hashing functions to be able to work with
any linear data buffer without an skb.
Signed-off-by: default avatarJussi Maki <joamaki@gmail.com>
Signed-off-by: default avatarDaniel Borkmann <daniel@iogearbox.net>
Cc: Jay Vosburgh <j.vosburgh@gmail.com>
Cc: Veaceslav Falico <vfalico@gmail.com>
Cc: Andy Gospodarek <andy@greyhouse.net>
Link: https://lore.kernel.org/bpf/20210731055738.16820-2-joamaki@gmail.com
parent c83ae15d
...@@ -3614,55 +3614,80 @@ static struct notifier_block bond_netdev_notifier = { ...@@ -3614,55 +3614,80 @@ static struct notifier_block bond_netdev_notifier = {
/*---------------------------- Hashing Policies -----------------------------*/ /*---------------------------- 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 */ /* 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); data = bond_pull_data(skb, data, hlen, mhoff + sizeof(struct ethhdr));
if (ep) if (!data)
return ep->h_dest[5] ^ ep->h_source[5] ^ ep->h_proto;
return 0; return 0;
ep = (struct ethhdr *)(data + mhoff);
return ep->h_dest[5] ^ ep->h_source[5] ^ ep->h_proto;
} }
static bool bond_flow_ip(struct sk_buff *skb, struct flow_keys *fk, static bool bond_flow_ip(struct sk_buff *skb, struct flow_keys *fk, const void *data,
int *noff, int *proto, bool l34) int hlen, __be16 l2_proto, int *nhoff, int *ip_proto, bool l34)
{ {
const struct ipv6hdr *iph6; const struct ipv6hdr *iph6;
const struct iphdr *iph; const struct iphdr *iph;
if (skb->protocol == htons(ETH_P_IP)) { if (l2_proto == htons(ETH_P_IP)) {
if (unlikely(!pskb_may_pull(skb, *noff + sizeof(*iph)))) data = bond_pull_data(skb, data, hlen, *nhoff + sizeof(*iph));
if (!data)
return false; return false;
iph = (const struct iphdr *)(skb->data + *noff);
iph = (const struct iphdr *)(data + *nhoff);
iph_to_flow_copy_v4addrs(fk, iph); iph_to_flow_copy_v4addrs(fk, iph);
*noff += iph->ihl << 2; *nhoff += iph->ihl << 2;
if (!ip_is_fragment(iph)) if (!ip_is_fragment(iph))
*proto = iph->protocol; *ip_proto = iph->protocol;
} else if (skb->protocol == htons(ETH_P_IPV6)) { } else if (l2_proto == htons(ETH_P_IPV6)) {
if (unlikely(!pskb_may_pull(skb, *noff + sizeof(*iph6)))) data = bond_pull_data(skb, data, hlen, *nhoff + sizeof(*iph6));
if (!data)
return false; return false;
iph6 = (const struct ipv6hdr *)(skb->data + *noff);
iph6 = (const struct ipv6hdr *)(data + *nhoff);
iph_to_flow_copy_v6addrs(fk, iph6); iph_to_flow_copy_v6addrs(fk, iph6);
*noff += sizeof(*iph6); *nhoff += sizeof(*iph6);
*proto = iph6->nexthdr; *ip_proto = iph6->nexthdr;
} else { } else {
return false; return false;
} }
if (l34 && *proto >= 0) if (l34 && *ip_proto >= 0)
fk->ports.ports = skb_flow_get_ports(skb, *noff, *proto); fk->ports.ports = __skb_flow_get_ports(skb, *nhoff, *ip_proto, data, hlen);
return true; 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; u32 srcmac_vendor = 0, srcmac_dev = 0;
u16 vlan; u16 vlan;
int i; 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++) for (i = 0; i < 3; i++)
srcmac_vendor = (srcmac_vendor << 8) | mac_hdr->h_source[i]; srcmac_vendor = (srcmac_vendor << 8) | mac_hdr->h_source[i];
...@@ -3678,26 +3703,25 @@ static u32 bond_vlan_srcmac_hash(struct sk_buff *skb) ...@@ -3678,26 +3703,25 @@ static u32 bond_vlan_srcmac_hash(struct sk_buff *skb)
} }
/* Extract the appropriate headers based on bond's xmit policy */ /* Extract the appropriate headers based on bond's xmit policy */
static bool bond_flow_dissect(struct bonding *bond, struct sk_buff *skb, static bool bond_flow_dissect(struct bonding *bond, struct sk_buff *skb, const void *data,
struct flow_keys *fk) __be16 l2_proto, int nhoff, int hlen, struct flow_keys *fk)
{ {
bool l34 = bond->params.xmit_policy == BOND_XMIT_POLICY_LAYER34; bool l34 = bond->params.xmit_policy == BOND_XMIT_POLICY_LAYER34;
int noff, proto = -1; int ip_proto = -1;
switch (bond->params.xmit_policy) { switch (bond->params.xmit_policy) {
case BOND_XMIT_POLICY_ENCAP23: case BOND_XMIT_POLICY_ENCAP23:
case BOND_XMIT_POLICY_ENCAP34: case BOND_XMIT_POLICY_ENCAP34:
memset(fk, 0, sizeof(*fk)); memset(fk, 0, sizeof(*fk));
return __skb_flow_dissect(NULL, skb, &flow_keys_bonding, return __skb_flow_dissect(NULL, skb, &flow_keys_bonding,
fk, NULL, 0, 0, 0, 0); fk, data, l2_proto, nhoff, hlen, 0);
default: default:
break; break;
} }
fk->ports.ports = 0; fk->ports.ports = 0;
memset(&fk->icmp, 0, sizeof(fk->icmp)); memset(&fk->icmp, 0, sizeof(fk->icmp));
noff = skb_network_offset(skb); if (!bond_flow_ip(skb, fk, data, hlen, l2_proto, &nhoff, &ip_proto, l34))
if (!bond_flow_ip(skb, fk, &noff, &proto, l34))
return false; return false;
/* ICMP error packets contains at least 8 bytes of the header /* ICMP error packets contains at least 8 bytes of the header
...@@ -3705,22 +3729,20 @@ static bool bond_flow_dissect(struct bonding *bond, struct sk_buff *skb, ...@@ -3705,22 +3729,20 @@ static bool bond_flow_dissect(struct bonding *bond, struct sk_buff *skb,
* to correlate ICMP error packets within the same flow which * to correlate ICMP error packets within the same flow which
* generated the error. * generated the error.
*/ */
if (proto == IPPROTO_ICMP || proto == IPPROTO_ICMPV6) { if (ip_proto == IPPROTO_ICMP || ip_proto == IPPROTO_ICMPV6) {
skb_flow_get_icmp_tci(skb, &fk->icmp, skb->data, skb_flow_get_icmp_tci(skb, &fk->icmp, data, nhoff, hlen);
skb_transport_offset(skb), if (ip_proto == IPPROTO_ICMP) {
skb_headlen(skb));
if (proto == IPPROTO_ICMP) {
if (!icmp_is_err(fk->icmp.type)) if (!icmp_is_err(fk->icmp.type))
return true; return true;
noff += sizeof(struct icmphdr); nhoff += sizeof(struct icmphdr);
} else if (proto == IPPROTO_ICMPV6) { } else if (ip_proto == IPPROTO_ICMPV6) {
if (!icmpv6_is_err(fk->icmp.type)) if (!icmpv6_is_err(fk->icmp.type))
return true; 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; return true;
...@@ -3736,33 +3758,26 @@ static u32 bond_ip_hash(u32 hash, struct flow_keys *flow) ...@@ -3736,33 +3758,26 @@ static u32 bond_ip_hash(u32 hash, struct flow_keys *flow)
return hash >> 1; return hash >> 1;
} }
/** /* Generate hash based on xmit policy. If @skb is given it is used to linearize
* bond_xmit_hash - generate a hash value based on the xmit policy * the data as required, but this function can be used without it if the data is
* @bond: bonding device * known to be linear (e.g. with xdp_buff).
* @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) 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; struct flow_keys flow;
u32 hash; 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) 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 || if (bond->params.xmit_policy == BOND_XMIT_POLICY_LAYER2 ||
!bond_flow_dissect(bond, skb, &flow)) !bond_flow_dissect(bond, skb, data, l2_proto, nhoff, hlen, &flow))
return bond_eth_hash(skb); return bond_eth_hash(skb, data, mhoff, hlen);
if (bond->params.xmit_policy == BOND_XMIT_POLICY_LAYER23 || if (bond->params.xmit_policy == BOND_XMIT_POLICY_LAYER23 ||
bond->params.xmit_policy == BOND_XMIT_POLICY_ENCAP23) { bond->params.xmit_policy == BOND_XMIT_POLICY_ENCAP23) {
hash = bond_eth_hash(skb); hash = bond_eth_hash(skb, data, mhoff, hlen);
} else { } else {
if (flow.icmp.id) if (flow.icmp.id)
memcpy(&hash, &flow.icmp, sizeof(hash)); memcpy(&hash, &flow.icmp, sizeof(hash));
...@@ -3773,6 +3788,25 @@ u32 bond_xmit_hash(struct bonding *bond, struct sk_buff *skb) ...@@ -3773,6 +3788,25 @@ u32 bond_xmit_hash(struct bonding *bond, struct sk_buff *skb)
return bond_ip_hash(hash, &flow); 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));
}
/*-------------------------- Device entry points ----------------------------*/ /*-------------------------- Device entry points ----------------------------*/
void bond_work_init_all(struct bonding *bond) void bond_work_init_all(struct bonding *bond)
...@@ -4434,8 +4468,7 @@ static netdev_tx_t bond_xmit_roundrobin(struct sk_buff *skb, ...@@ -4434,8 +4468,7 @@ static netdev_tx_t bond_xmit_roundrobin(struct sk_buff *skb,
return bond_tx_drop(bond_dev, skb); return bond_tx_drop(bond_dev, skb);
} }
static struct slave *bond_xmit_activebackup_slave_get(struct bonding *bond, static struct slave *bond_xmit_activebackup_slave_get(struct bonding *bond)
struct sk_buff *skb)
{ {
return rcu_dereference(bond->curr_active_slave); return rcu_dereference(bond->curr_active_slave);
} }
...@@ -4449,7 +4482,7 @@ static netdev_tx_t bond_xmit_activebackup(struct sk_buff *skb, ...@@ -4449,7 +4482,7 @@ static netdev_tx_t bond_xmit_activebackup(struct sk_buff *skb,
struct bonding *bond = netdev_priv(bond_dev); struct bonding *bond = netdev_priv(bond_dev);
struct slave *slave; struct slave *slave;
slave = bond_xmit_activebackup_slave_get(bond, skb); slave = bond_xmit_activebackup_slave_get(bond);
if (slave) if (slave)
return bond_dev_queue_xmit(bond, skb, slave->dev); return bond_dev_queue_xmit(bond, skb, slave->dev);
...@@ -4747,7 +4780,7 @@ static struct net_device *bond_xmit_get_slave(struct net_device *master_dev, ...@@ -4747,7 +4780,7 @@ static struct net_device *bond_xmit_get_slave(struct net_device *master_dev,
slave = bond_xmit_roundrobin_slave_get(bond, skb); slave = bond_xmit_roundrobin_slave_get(bond, skb);
break; break;
case BOND_MODE_ACTIVEBACKUP: case BOND_MODE_ACTIVEBACKUP:
slave = bond_xmit_activebackup_slave_get(bond, skb); slave = bond_xmit_activebackup_slave_get(bond);
break; break;
case BOND_MODE_8023AD: case BOND_MODE_8023AD:
case BOND_MODE_XOR: case BOND_MODE_XOR:
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment