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: Jussi Maki <joamaki@gmail.com>
Signed-off-by: Daniel 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
This commit is contained in:
Jussi Maki 2021-07-31 05:57:32 +00:00 committed by Daniel Borkmann
parent c83ae15dc9
commit a815bde56b
1 changed files with 96 additions and 63 deletions

View File

@ -3614,55 +3614,80 @@ static struct notifier_block bond_netdev_notifier = {
/*---------------------------- Hashing Policies -----------------------------*/
/* L2 hash helper */
static inline u32 bond_eth_hash(struct sk_buff *skb)
/* 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)
{
struct ethhdr *ep, hdr_tmp;
if (likely(n <= hlen))
return data;
else if (skb && likely(pskb_may_pull(skb, n)))
return skb->head;
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;
return NULL;
}
static bool bond_flow_ip(struct sk_buff *skb, struct flow_keys *fk,
int *noff, int *proto, bool l34)
/* L2 hash helper */
static inline u32 bond_eth_hash(struct sk_buff *skb, const void *data, int mhoff, int hlen)
{
struct ethhdr *ep;
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] ^ ep->h_proto;
}
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 +3703,25 @@ 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 +3729,20 @@ 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;
@ -3736,6 +3758,36 @@ static u32 bond_ip_hash(u32 hash, struct flow_keys *flow)
return hash >> 1;
}
/* 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).
*/
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_VLAN_SRCMAC)
return bond_vlan_srcmac_hash(skb, data, mhoff, hlen);
if (bond->params.xmit_policy == BOND_XMIT_POLICY_LAYER2 ||
!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, data, mhoff, hlen);
} else {
if (flow.icmp.id)
memcpy(&hash, &flow.icmp, sizeof(hash));
else
memcpy(&hash, &flow.ports.ports, sizeof(hash));
}
return bond_ip_hash(hash, &flow);
}
/**
* bond_xmit_hash - generate a hash value based on the xmit policy
* @bond: bonding device
@ -3746,31 +3798,13 @@ static u32 bond_ip_hash(u32 hash, struct flow_keys *flow)
*/
u32 bond_xmit_hash(struct bonding *bond, struct sk_buff *skb)
{
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);
if (bond->params.xmit_policy == BOND_XMIT_POLICY_LAYER2 ||
!bond_flow_dissect(bond, skb, &flow))
return bond_eth_hash(skb);
if (bond->params.xmit_policy == BOND_XMIT_POLICY_LAYER23 ||
bond->params.xmit_policy == BOND_XMIT_POLICY_ENCAP23) {
hash = bond_eth_hash(skb);
} else {
if (flow.icmp.id)
memcpy(&hash, &flow.icmp, sizeof(hash));
else
memcpy(&hash, &flow.ports.ports, sizeof(hash));
}
return bond_ip_hash(hash, &flow);
return __bond_xmit_hash(bond, skb, skb->head, skb->protocol,
skb->mac_header, skb->network_header,
skb_headlen(skb));
}
/*-------------------------- Device entry points ----------------------------*/
@ -4434,8 +4468,7 @@ 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 +4482,7 @@ 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);
@ -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);
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: