540 lines
13 KiB
C
540 lines
13 KiB
C
#include <linux/skbuff.h>
|
|
#include <linux/export.h>
|
|
#include <linux/ip.h>
|
|
#include <linux/ipv6.h>
|
|
#include <linux/if_vlan.h>
|
|
#include <net/ip.h>
|
|
#include <net/ipv6.h>
|
|
#include <linux/igmp.h>
|
|
#include <linux/icmp.h>
|
|
#include <linux/sctp.h>
|
|
#include <linux/dccp.h>
|
|
#include <linux/if_tunnel.h>
|
|
#include <linux/if_pppox.h>
|
|
#include <linux/ppp_defs.h>
|
|
#include <net/flow_keys.h>
|
|
#include <scsi/fc/fc_fcoe.h>
|
|
|
|
/* copy saddr & daddr, possibly using 64bit load/store
|
|
* Equivalent to : flow->src = iph->saddr;
|
|
* flow->dst = iph->daddr;
|
|
*/
|
|
static void iph_to_flow_copy_addrs(struct flow_keys *flow, const struct iphdr *iph)
|
|
{
|
|
BUILD_BUG_ON(offsetof(typeof(*flow), dst) !=
|
|
offsetof(typeof(*flow), src) + sizeof(flow->src));
|
|
memcpy(&flow->src, &iph->saddr, sizeof(flow->src) + sizeof(flow->dst));
|
|
}
|
|
|
|
/**
|
|
* __skb_flow_get_ports - extract the upper layer ports and return them
|
|
* @skb: sk_buff to extract the ports from
|
|
* @thoff: transport header offset
|
|
* @ip_proto: protocol for which to get port offset
|
|
* @data: raw buffer pointer to the packet, if NULL use skb->data
|
|
* @hlen: packet header length, if @data is NULL use skb_headlen(skb)
|
|
*
|
|
* The function will try to retrieve the ports at offset thoff + poff where poff
|
|
* is the protocol port offset returned from proto_ports_offset
|
|
*/
|
|
__be32 __skb_flow_get_ports(const struct sk_buff *skb, int thoff, u8 ip_proto,
|
|
void *data, int hlen)
|
|
{
|
|
int poff = proto_ports_offset(ip_proto);
|
|
|
|
if (!data) {
|
|
data = skb->data;
|
|
hlen = skb_headlen(skb);
|
|
}
|
|
|
|
if (poff >= 0) {
|
|
__be32 *ports, _ports;
|
|
|
|
ports = __skb_header_pointer(skb, thoff + poff,
|
|
sizeof(_ports), data, hlen, &_ports);
|
|
if (ports)
|
|
return *ports;
|
|
}
|
|
|
|
return 0;
|
|
}
|
|
EXPORT_SYMBOL(__skb_flow_get_ports);
|
|
|
|
/**
|
|
* __skb_flow_dissect - extract the flow_keys struct and return it
|
|
* @skb: sk_buff to extract the flow from, can be NULL if the rest are specified
|
|
* @data: raw buffer pointer to the packet, if NULL use skb->data
|
|
* @proto: protocol for which to get the flow, if @data is NULL use skb->protocol
|
|
* @nhoff: network header offset, if @data is NULL use skb_network_offset(skb)
|
|
* @hlen: packet header length, if @data is NULL use skb_headlen(skb)
|
|
*
|
|
* The function will try to retrieve the struct flow_keys from either the skbuff
|
|
* or a raw buffer specified by the rest parameters
|
|
*/
|
|
bool __skb_flow_dissect(const struct sk_buff *skb, struct flow_keys *flow,
|
|
void *data, __be16 proto, int nhoff, int hlen)
|
|
{
|
|
u8 ip_proto;
|
|
|
|
if (!data) {
|
|
data = skb->data;
|
|
proto = skb->protocol;
|
|
nhoff = skb_network_offset(skb);
|
|
hlen = skb_headlen(skb);
|
|
}
|
|
|
|
memset(flow, 0, sizeof(*flow));
|
|
|
|
again:
|
|
switch (proto) {
|
|
case htons(ETH_P_IP): {
|
|
const struct iphdr *iph;
|
|
struct iphdr _iph;
|
|
ip:
|
|
iph = __skb_header_pointer(skb, nhoff, sizeof(_iph), data, hlen, &_iph);
|
|
if (!iph || iph->ihl < 5)
|
|
return false;
|
|
nhoff += iph->ihl * 4;
|
|
|
|
ip_proto = iph->protocol;
|
|
if (ip_is_fragment(iph))
|
|
ip_proto = 0;
|
|
|
|
/* skip the address processing if skb is NULL. The assumption
|
|
* here is that if there is no skb we are not looking for flow
|
|
* info but lengths and protocols.
|
|
*/
|
|
if (!skb)
|
|
break;
|
|
|
|
iph_to_flow_copy_addrs(flow, iph);
|
|
break;
|
|
}
|
|
case htons(ETH_P_IPV6): {
|
|
const struct ipv6hdr *iph;
|
|
struct ipv6hdr _iph;
|
|
__be32 flow_label;
|
|
|
|
ipv6:
|
|
iph = __skb_header_pointer(skb, nhoff, sizeof(_iph), data, hlen, &_iph);
|
|
if (!iph)
|
|
return false;
|
|
|
|
ip_proto = iph->nexthdr;
|
|
nhoff += sizeof(struct ipv6hdr);
|
|
|
|
/* see comment above in IPv4 section */
|
|
if (!skb)
|
|
break;
|
|
|
|
flow->src = (__force __be32)ipv6_addr_hash(&iph->saddr);
|
|
flow->dst = (__force __be32)ipv6_addr_hash(&iph->daddr);
|
|
|
|
flow_label = ip6_flowlabel(iph);
|
|
if (flow_label) {
|
|
/* Awesome, IPv6 packet has a flow label so we can
|
|
* use that to represent the ports without any
|
|
* further dissection.
|
|
*/
|
|
flow->n_proto = proto;
|
|
flow->ip_proto = ip_proto;
|
|
flow->ports = flow_label;
|
|
flow->thoff = (u16)nhoff;
|
|
|
|
return true;
|
|
}
|
|
|
|
break;
|
|
}
|
|
case htons(ETH_P_8021AD):
|
|
case htons(ETH_P_8021Q): {
|
|
const struct vlan_hdr *vlan;
|
|
struct vlan_hdr _vlan;
|
|
|
|
vlan = __skb_header_pointer(skb, nhoff, sizeof(_vlan), data, hlen, &_vlan);
|
|
if (!vlan)
|
|
return false;
|
|
|
|
proto = vlan->h_vlan_encapsulated_proto;
|
|
nhoff += sizeof(*vlan);
|
|
goto again;
|
|
}
|
|
case htons(ETH_P_PPP_SES): {
|
|
struct {
|
|
struct pppoe_hdr hdr;
|
|
__be16 proto;
|
|
} *hdr, _hdr;
|
|
hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data, hlen, &_hdr);
|
|
if (!hdr)
|
|
return false;
|
|
proto = hdr->proto;
|
|
nhoff += PPPOE_SES_HLEN;
|
|
switch (proto) {
|
|
case htons(PPP_IP):
|
|
goto ip;
|
|
case htons(PPP_IPV6):
|
|
goto ipv6;
|
|
default:
|
|
return false;
|
|
}
|
|
}
|
|
case htons(ETH_P_TIPC): {
|
|
struct {
|
|
__be32 pre[3];
|
|
__be32 srcnode;
|
|
} *hdr, _hdr;
|
|
hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data, hlen, &_hdr);
|
|
if (!hdr)
|
|
return false;
|
|
flow->src = hdr->srcnode;
|
|
flow->dst = 0;
|
|
flow->n_proto = proto;
|
|
flow->thoff = (u16)nhoff;
|
|
return true;
|
|
}
|
|
case htons(ETH_P_FCOE):
|
|
flow->thoff = (u16)(nhoff + FCOE_HEADER_LEN);
|
|
/* fall through */
|
|
default:
|
|
return false;
|
|
}
|
|
|
|
switch (ip_proto) {
|
|
case IPPROTO_GRE: {
|
|
struct gre_hdr {
|
|
__be16 flags;
|
|
__be16 proto;
|
|
} *hdr, _hdr;
|
|
|
|
hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data, hlen, &_hdr);
|
|
if (!hdr)
|
|
return false;
|
|
/*
|
|
* Only look inside GRE if version zero and no
|
|
* routing
|
|
*/
|
|
if (!(hdr->flags & (GRE_VERSION|GRE_ROUTING))) {
|
|
proto = hdr->proto;
|
|
nhoff += 4;
|
|
if (hdr->flags & GRE_CSUM)
|
|
nhoff += 4;
|
|
if (hdr->flags & GRE_KEY)
|
|
nhoff += 4;
|
|
if (hdr->flags & GRE_SEQ)
|
|
nhoff += 4;
|
|
if (proto == htons(ETH_P_TEB)) {
|
|
const struct ethhdr *eth;
|
|
struct ethhdr _eth;
|
|
|
|
eth = __skb_header_pointer(skb, nhoff,
|
|
sizeof(_eth),
|
|
data, hlen, &_eth);
|
|
if (!eth)
|
|
return false;
|
|
proto = eth->h_proto;
|
|
nhoff += sizeof(*eth);
|
|
}
|
|
goto again;
|
|
}
|
|
break;
|
|
}
|
|
case IPPROTO_IPIP:
|
|
proto = htons(ETH_P_IP);
|
|
goto ip;
|
|
case IPPROTO_IPV6:
|
|
proto = htons(ETH_P_IPV6);
|
|
goto ipv6;
|
|
default:
|
|
break;
|
|
}
|
|
|
|
flow->n_proto = proto;
|
|
flow->ip_proto = ip_proto;
|
|
flow->thoff = (u16) nhoff;
|
|
|
|
/* unless skb is set we don't need to record port info */
|
|
if (skb)
|
|
flow->ports = __skb_flow_get_ports(skb, nhoff, ip_proto,
|
|
data, hlen);
|
|
|
|
return true;
|
|
}
|
|
EXPORT_SYMBOL(__skb_flow_dissect);
|
|
|
|
static u32 hashrnd __read_mostly;
|
|
static __always_inline void __flow_hash_secret_init(void)
|
|
{
|
|
net_get_random_once(&hashrnd, sizeof(hashrnd));
|
|
}
|
|
|
|
static __always_inline u32 __flow_hash_3words(u32 a, u32 b, u32 c, u32 keyval)
|
|
{
|
|
return jhash_3words(a, b, c, keyval);
|
|
}
|
|
|
|
static inline u32 __flow_hash_from_keys(struct flow_keys *keys, u32 keyval)
|
|
{
|
|
u32 hash;
|
|
|
|
/* get a consistent hash (same value on both flow directions) */
|
|
if (((__force u32)keys->dst < (__force u32)keys->src) ||
|
|
(((__force u32)keys->dst == (__force u32)keys->src) &&
|
|
((__force u16)keys->port16[1] < (__force u16)keys->port16[0]))) {
|
|
swap(keys->dst, keys->src);
|
|
swap(keys->port16[0], keys->port16[1]);
|
|
}
|
|
|
|
hash = __flow_hash_3words((__force u32)keys->dst,
|
|
(__force u32)keys->src,
|
|
(__force u32)keys->ports,
|
|
keyval);
|
|
if (!hash)
|
|
hash = 1;
|
|
|
|
return hash;
|
|
}
|
|
|
|
u32 flow_hash_from_keys(struct flow_keys *keys)
|
|
{
|
|
__flow_hash_secret_init();
|
|
return __flow_hash_from_keys(keys, hashrnd);
|
|
}
|
|
EXPORT_SYMBOL(flow_hash_from_keys);
|
|
|
|
static inline u32 ___skb_get_hash(const struct sk_buff *skb,
|
|
struct flow_keys *keys, u32 keyval)
|
|
{
|
|
if (!skb_flow_dissect(skb, keys))
|
|
return 0;
|
|
|
|
return __flow_hash_from_keys(keys, keyval);
|
|
}
|
|
|
|
struct _flow_keys_digest_data {
|
|
__be16 n_proto;
|
|
u8 ip_proto;
|
|
u8 padding;
|
|
__be32 ports;
|
|
__be32 src;
|
|
__be32 dst;
|
|
};
|
|
|
|
void make_flow_keys_digest(struct flow_keys_digest *digest,
|
|
const struct flow_keys *flow)
|
|
{
|
|
struct _flow_keys_digest_data *data =
|
|
(struct _flow_keys_digest_data *)digest;
|
|
|
|
BUILD_BUG_ON(sizeof(*data) > sizeof(*digest));
|
|
|
|
memset(digest, 0, sizeof(*digest));
|
|
|
|
data->n_proto = flow->n_proto;
|
|
data->ip_proto = flow->ip_proto;
|
|
data->ports = flow->ports;
|
|
data->src = flow->src;
|
|
data->dst = flow->dst;
|
|
}
|
|
EXPORT_SYMBOL(make_flow_keys_digest);
|
|
|
|
/*
|
|
* __skb_get_hash: calculate a flow hash based on src/dst addresses
|
|
* and src/dst port numbers. Sets hash in skb to non-zero hash value
|
|
* on success, zero indicates no valid hash. Also, sets l4_hash in skb
|
|
* if hash is a canonical 4-tuple hash over transport ports.
|
|
*/
|
|
void __skb_get_hash(struct sk_buff *skb)
|
|
{
|
|
struct flow_keys keys;
|
|
u32 hash;
|
|
|
|
__flow_hash_secret_init();
|
|
|
|
hash = ___skb_get_hash(skb, &keys, hashrnd);
|
|
if (!hash)
|
|
return;
|
|
|
|
if (keys.ports)
|
|
skb->l4_hash = 1;
|
|
|
|
skb->sw_hash = 1;
|
|
|
|
skb->hash = hash;
|
|
}
|
|
EXPORT_SYMBOL(__skb_get_hash);
|
|
|
|
__u32 skb_get_hash_perturb(const struct sk_buff *skb, u32 perturb)
|
|
{
|
|
struct flow_keys keys;
|
|
|
|
return ___skb_get_hash(skb, &keys, perturb);
|
|
}
|
|
EXPORT_SYMBOL(skb_get_hash_perturb);
|
|
|
|
/*
|
|
* Returns a Tx hash based on the given packet descriptor a Tx queues' number
|
|
* to be used as a distribution range.
|
|
*/
|
|
u16 __skb_tx_hash(const struct net_device *dev, struct sk_buff *skb,
|
|
unsigned int num_tx_queues)
|
|
{
|
|
u32 hash;
|
|
u16 qoffset = 0;
|
|
u16 qcount = num_tx_queues;
|
|
|
|
if (skb_rx_queue_recorded(skb)) {
|
|
hash = skb_get_rx_queue(skb);
|
|
while (unlikely(hash >= num_tx_queues))
|
|
hash -= num_tx_queues;
|
|
return hash;
|
|
}
|
|
|
|
if (dev->num_tc) {
|
|
u8 tc = netdev_get_prio_tc_map(dev, skb->priority);
|
|
qoffset = dev->tc_to_txq[tc].offset;
|
|
qcount = dev->tc_to_txq[tc].count;
|
|
}
|
|
|
|
return (u16) reciprocal_scale(skb_get_hash(skb), qcount) + qoffset;
|
|
}
|
|
EXPORT_SYMBOL(__skb_tx_hash);
|
|
|
|
u32 __skb_get_poff(const struct sk_buff *skb, void *data,
|
|
const struct flow_keys *keys, int hlen)
|
|
{
|
|
u32 poff = keys->thoff;
|
|
|
|
switch (keys->ip_proto) {
|
|
case IPPROTO_TCP: {
|
|
/* access doff as u8 to avoid unaligned access */
|
|
const u8 *doff;
|
|
u8 _doff;
|
|
|
|
doff = __skb_header_pointer(skb, poff + 12, sizeof(_doff),
|
|
data, hlen, &_doff);
|
|
if (!doff)
|
|
return poff;
|
|
|
|
poff += max_t(u32, sizeof(struct tcphdr), (*doff & 0xF0) >> 2);
|
|
break;
|
|
}
|
|
case IPPROTO_UDP:
|
|
case IPPROTO_UDPLITE:
|
|
poff += sizeof(struct udphdr);
|
|
break;
|
|
/* For the rest, we do not really care about header
|
|
* extensions at this point for now.
|
|
*/
|
|
case IPPROTO_ICMP:
|
|
poff += sizeof(struct icmphdr);
|
|
break;
|
|
case IPPROTO_ICMPV6:
|
|
poff += sizeof(struct icmp6hdr);
|
|
break;
|
|
case IPPROTO_IGMP:
|
|
poff += sizeof(struct igmphdr);
|
|
break;
|
|
case IPPROTO_DCCP:
|
|
poff += sizeof(struct dccp_hdr);
|
|
break;
|
|
case IPPROTO_SCTP:
|
|
poff += sizeof(struct sctphdr);
|
|
break;
|
|
}
|
|
|
|
return poff;
|
|
}
|
|
|
|
/* skb_get_poff() returns the offset to the payload as far as it could
|
|
* be dissected. The main user is currently BPF, so that we can dynamically
|
|
* truncate packets without needing to push actual payload to the user
|
|
* space and can analyze headers only, instead.
|
|
*/
|
|
u32 skb_get_poff(const struct sk_buff *skb)
|
|
{
|
|
struct flow_keys keys;
|
|
|
|
if (!skb_flow_dissect(skb, &keys))
|
|
return 0;
|
|
|
|
return __skb_get_poff(skb, skb->data, &keys, skb_headlen(skb));
|
|
}
|
|
|
|
static inline int get_xps_queue(struct net_device *dev, struct sk_buff *skb)
|
|
{
|
|
#ifdef CONFIG_XPS
|
|
struct xps_dev_maps *dev_maps;
|
|
struct xps_map *map;
|
|
int queue_index = -1;
|
|
|
|
rcu_read_lock();
|
|
dev_maps = rcu_dereference(dev->xps_maps);
|
|
if (dev_maps) {
|
|
map = rcu_dereference(
|
|
dev_maps->cpu_map[skb->sender_cpu - 1]);
|
|
if (map) {
|
|
if (map->len == 1)
|
|
queue_index = map->queues[0];
|
|
else
|
|
queue_index = map->queues[reciprocal_scale(skb_get_hash(skb),
|
|
map->len)];
|
|
if (unlikely(queue_index >= dev->real_num_tx_queues))
|
|
queue_index = -1;
|
|
}
|
|
}
|
|
rcu_read_unlock();
|
|
|
|
return queue_index;
|
|
#else
|
|
return -1;
|
|
#endif
|
|
}
|
|
|
|
static u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb)
|
|
{
|
|
struct sock *sk = skb->sk;
|
|
int queue_index = sk_tx_queue_get(sk);
|
|
|
|
if (queue_index < 0 || skb->ooo_okay ||
|
|
queue_index >= dev->real_num_tx_queues) {
|
|
int new_index = get_xps_queue(dev, skb);
|
|
if (new_index < 0)
|
|
new_index = skb_tx_hash(dev, skb);
|
|
|
|
if (queue_index != new_index && sk &&
|
|
rcu_access_pointer(sk->sk_dst_cache))
|
|
sk_tx_queue_set(sk, new_index);
|
|
|
|
queue_index = new_index;
|
|
}
|
|
|
|
return queue_index;
|
|
}
|
|
|
|
struct netdev_queue *netdev_pick_tx(struct net_device *dev,
|
|
struct sk_buff *skb,
|
|
void *accel_priv)
|
|
{
|
|
int queue_index = 0;
|
|
|
|
#ifdef CONFIG_XPS
|
|
if (skb->sender_cpu == 0)
|
|
skb->sender_cpu = raw_smp_processor_id() + 1;
|
|
#endif
|
|
|
|
if (dev->real_num_tx_queues != 1) {
|
|
const struct net_device_ops *ops = dev->netdev_ops;
|
|
if (ops->ndo_select_queue)
|
|
queue_index = ops->ndo_select_queue(dev, skb, accel_priv,
|
|
__netdev_pick_tx);
|
|
else
|
|
queue_index = __netdev_pick_tx(dev, skb);
|
|
|
|
if (!accel_priv)
|
|
queue_index = netdev_cap_txqueue(dev, queue_index);
|
|
}
|
|
|
|
skb_set_queue_mapping(skb, queue_index);
|
|
return netdev_get_tx_queue(dev, queue_index);
|
|
}
|