iv/linux
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

net: Add full IPv6 addresses to flow_keys

Browse Source 
This patch adds full IPv6 addresses into flow_keys and uses them as
input to the flow hash function. The implementation supports either
IPv4 or IPv6 addresses in a union, and selector is used to determine
how may words to input to jhash2.

We also add flow_get_u32_dst and flow_get_u32_src functions which are
used to get a u32 representation of the source and destination
addresses. For IPv6, ipv6_addr_hash is called. These functions retain
getting the legacy values of src and dst in flow_keys.

With this patch, Ethertype and IP protocol are now included in the
flow hash input.

Signed-off-by: Tom Herbert <tom@herbertland.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This commit is contained in:
Tom Herbert 2015-06-04 09:16:40 -07:00 committed by David S. Miller
parent 42aecaa9bb
commit c3f8324188
10 changed files with 193 additions and 63 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
drivers/net/bonding/bond_main.c
View File

@ -3059,8 +3059,7 @@ static bool bond_flow_dissect(struct bonding *bond, struct sk_buff *skb,
if (unlikely(!pskb_may_pull(skb, noff + sizeof(*iph))))
return false;
iph = ip_hdr(skb);
fk->addrs.src = iph->saddr;
fk->addrs.dst = iph->daddr;
iph_to_flow_copy_v4addrs(fk, iph);
noff += iph->ihl << 2;
if (!ip_is_fragment(iph))
proto = iph->protocol;
@ -3068,8 +3067,7 @@ static bool bond_flow_dissect(struct bonding *bond, struct sk_buff *skb,
if (unlikely(!pskb_may_pull(skb, noff + sizeof(*iph6))))
return false;
iph6 = ipv6_hdr(skb);
fk->addrs.src = (__force __be32)ipv6_addr_hash(&iph6->saddr);
fk->addrs.dst = (__force __be32)ipv6_addr_hash(&iph6->daddr);
iph_to_flow_copy_v6addrs(fk, iph6);
noff += sizeof(*iph6);
proto = iph6->nexthdr;
} else {
@ -3103,7 +3101,8 @@ u32 bond_xmit_hash(struct bonding *bond, struct sk_buff *skb)
hash = bond_eth_hash(skb);
else
hash = (__force u32)flow.ports.ports;
hash ^= (__force u32)flow.addrs.dst ^ (__force u32)flow.addrs.src;
hash ^= (__force u32)flow_get_u32_dst(&flow) ^
(__force u32)flow_get_u32_src(&flow);
hash ^= (hash >> 16);
hash ^= (hash >> 8);

8
drivers/net/ethernet/cisco/enic/enic_clsf.c
View File

@ -33,8 +33,8 @@ int enic_addfltr_5t(struct enic *enic, struct flow_keys *keys, u16 rq)
return -EPROTONOSUPPORT;
};
data.type = FILTER_IPV4_5TUPLE;
data.u.ipv4.src_addr = ntohl(keys->addrs.src);
data.u.ipv4.dst_addr = ntohl(keys->addrs.dst);
data.u.ipv4.src_addr = ntohl(keys->addrs.v4addrs.src);
data.u.ipv4.dst_addr = ntohl(keys->addrs.v4addrs.dst);
data.u.ipv4.src_port = ntohs(keys->ports.src);
data.u.ipv4.dst_port = ntohs(keys->ports.dst);
data.u.ipv4.flags = FILTER_FIELDS_IPV4_5TUPLE;
@ -158,8 +158,8 @@ static struct enic_rfs_fltr_node *htbl_key_search(struct hlist_head *h,
struct enic_rfs_fltr_node *tpos;
hlist_for_each_entry(tpos, h, node)
if (tpos->keys.addrs.src == k->addrs.src &&
tpos->keys.addrs.dst == k->addrs.dst &&
if (tpos->keys.addrs.v4addrs.src == k->addrs.v4addrs.src &&
tpos->keys.addrs.v4addrs.dst == k->addrs.v4addrs.dst &&
tpos->keys.ports.ports == k->ports.ports &&
tpos->keys.basic.ip_proto == k->basic.ip_proto &&
tpos->keys.basic.n_proto == k->basic.n_proto)

4
drivers/net/ethernet/cisco/enic/enic_ethtool.c
View File

@ -346,10 +346,10 @@ static int enic_grxclsrule(struct enic *enic, struct ethtool_rxnfc *cmd)
break;
}
fsp->h_u.tcp_ip4_spec.ip4src = n->keys.addrs.src;
fsp->h_u.tcp_ip4_spec.ip4src = flow_get_u32_src(&n->keys);
fsp->m_u.tcp_ip4_spec.ip4src = (__u32)~0;
fsp->h_u.tcp_ip4_spec.ip4dst = n->keys.addrs.dst;
fsp->h_u.tcp_ip4_spec.ip4dst = flow_get_u32_dst(&n->keys);
fsp->m_u.tcp_ip4_spec.ip4dst = (__u32)~0;
fsp->h_u.tcp_ip4_spec.psrc = n->keys.ports.src;

52
include/net/flow_dissector.h
View File

@ -12,7 +12,7 @@
*/
struct flow_dissector_key_control {
u16 thoff;
u16 padding;
u16 addr_type;
};
/**
@ -28,18 +28,39 @@ struct flow_dissector_key_basic {
};
/**
* struct flow_dissector_key_addrs:
* @src: source ip address in case of IPv4
* For IPv6 it contains 32bit hash of src address
* @dst: destination ip address in case of IPv4
* For IPv6 it contains 32bit hash of dst address
* struct flow_dissector_key_ipv4_addrs:
* @src: source ip address
* @dst: destination ip address
*/
struct flow_dissector_key_addrs {
struct flow_dissector_key_ipv4_addrs {
/* (src,dst) must be grouped, in the same way than in IP header */
__be32 src;
__be32 dst;
};
/**
* struct flow_dissector_key_ipv6_addrs:
* @src: source ip address
* @dst: destination ip address
*/
struct flow_dissector_key_ipv6_addrs {
/* (src,dst) must be grouped, in the same way than in IP header */
struct in6_addr src;
struct in6_addr dst;
};
/**
* struct flow_dissector_key_addrs:
* @v4addrs: IPv4 addresses
* @v6addrs: IPv6 addresses
*/
struct flow_dissector_key_addrs {
union {
struct flow_dissector_key_ipv4_addrs v4addrs;
struct flow_dissector_key_ipv6_addrs v6addrs;
};
};
/**
* flow_dissector_key_tp_ports:
* @ports: port numbers of Transport header
@ -56,16 +77,6 @@ struct flow_dissector_key_ports {
};
};
/**
* struct flow_dissector_key_ipv6_addrs:
* @src: source ip address
* @dst: destination ip address
*/
struct flow_dissector_key_ipv6_addrs {
/* (src,dst) must be grouped, in the same way than in IP header */
struct in6_addr src;
struct in6_addr dst;
};
/**
* struct flow_dissector_key_eth_addrs:
@ -81,10 +92,10 @@ struct flow_dissector_key_eth_addrs {
enum flow_dissector_key_id {
FLOW_DISSECTOR_KEY_CONTROL, /* struct flow_dissector_key_control */
FLOW_DISSECTOR_KEY_BASIC, /* struct flow_dissector_key_basic */
FLOW_DISSECTOR_KEY_IPV4_ADDRS, /* struct flow_dissector_key_addrs */
FLOW_DISSECTOR_KEY_IPV4_ADDRS, /* struct flow_dissector_key_ipv4_addrs */
FLOW_DISSECTOR_KEY_IPV6_ADDRS, /* struct flow_dissector_key_ipv6_addrs */
FLOW_DISSECTOR_KEY_IPV6_HASH_ADDRS, /* struct flow_dissector_key_addrs */
FLOW_DISSECTOR_KEY_PORTS, /* struct flow_dissector_key_ports */
FLOW_DISSECTOR_KEY_IPV6_ADDRS, /* struct flow_dissector_key_ipv6_addrs */
FLOW_DISSECTOR_KEY_ETH_ADDRS, /* struct flow_dissector_key_eth_addrs */
FLOW_DISSECTOR_KEY_MAX,
@ -129,6 +140,9 @@ struct flow_keys {
#define FLOW_KEYS_HASH_OFFSET \
offsetof(struct flow_keys, FLOW_KEYS_HASH_START_FIELD)
__be32 flow_get_u32_src(const struct flow_keys *flow);
__be32 flow_get_u32_dst(const struct flow_keys *flow);
extern struct flow_dissector flow_keys_dissector;
extern struct flow_dissector flow_keys_buf_dissector;

19
include/net/ip.h
View File

@ -355,6 +355,20 @@ static inline __wsum inet_compute_pseudo(struct sk_buff *skb, int proto)
skb->len, proto, 0);
}
/* copy IPv4 saddr & daddr to flow_keys, possibly using 64bit load/store
* Equivalent to : flow->v4addrs.src = iph->saddr;
* flow->v4addrs.dst = iph->daddr;
*/
static inline void iph_to_flow_copy_v4addrs(struct flow_keys *flow,
const struct iphdr *iph)
{
BUILD_BUG_ON(offsetof(typeof(flow->addrs), v4addrs.dst) !=
offsetof(typeof(flow->addrs), v4addrs.src) +
sizeof(flow->addrs.v4addrs.src));
memcpy(&flow->addrs.v4addrs, &iph->saddr, sizeof(flow->addrs.v4addrs));
flow->control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS;
}
static inline void inet_set_txhash(struct sock *sk)
{
struct inet_sock *inet = inet_sk(sk);
@ -362,8 +376,9 @@ static inline void inet_set_txhash(struct sock *sk)
memset(&keys, 0, sizeof(keys));
keys.addrs.src = inet->inet_saddr;
keys.addrs.dst = inet->inet_daddr;
keys.addrs.v4addrs.src = inet->inet_saddr;
keys.addrs.v4addrs.dst = inet->inet_daddr;
keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS;
keys.ports.src = inet->inet_sport;
keys.ports.dst = inet->inet_dport;

21
include/net/ipv6.h
View File

@ -692,6 +692,20 @@ static inline int ip6_sk_dst_hoplimit(struct ipv6_pinfo *np, struct flowi6 *fl6,
return hlimit;
}
/* copy IPv6 saddr & daddr to flow_keys, possibly using 64bit load/store
* Equivalent to : flow->v6addrs.src = iph->saddr;
* flow->v6addrs.dst = iph->daddr;
*/
static inline void iph_to_flow_copy_v6addrs(struct flow_keys *flow,
const struct ipv6hdr *iph)
{
BUILD_BUG_ON(offsetof(typeof(flow->addrs), v6addrs.dst) !=
offsetof(typeof(flow->addrs), v6addrs.src) +
sizeof(flow->addrs.v6addrs.src));
memcpy(&flow->addrs.v6addrs, &iph->saddr, sizeof(flow->addrs.v6addrs));
flow->control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS;
}
#if IS_ENABLED(CONFIG_IPV6)
static inline void ip6_set_txhash(struct sock *sk)
{
@ -701,8 +715,11 @@ static inline void ip6_set_txhash(struct sock *sk)
memset(&keys, 0, sizeof(keys));
keys.addrs.src = (__force __be32)ipv6_addr_hash(&np->saddr);
keys.addrs.dst = (__force __be32)ipv6_addr_hash(&sk->sk_v6_daddr);
memcpy(&keys.addrs.v6addrs.src, &np->saddr,
sizeof(keys.addrs.v6addrs.src));
memcpy(&keys.addrs.v6addrs.dst, &sk->sk_v6_daddr,
sizeof(keys.addrs.v6addrs.dst));
keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS;
keys.ports.src = inet->inet_sport;
keys.ports.dst = inet->inet_dport;

116
net/core/flow_dissector.c
View File

@ -178,10 +178,12 @@ ip:
if (!skb_flow_dissector_uses_key(flow_dissector,
FLOW_DISSECTOR_KEY_IPV4_ADDRS))
break;
key_addrs = skb_flow_dissector_target(flow_dissector,
FLOW_DISSECTOR_KEY_IPV4_ADDRS,
target_container);
memcpy(key_addrs, &iph->saddr, sizeof(*key_addrs));
FLOW_DISSECTOR_KEY_IPV4_ADDRS, target_container);
memcpy(&key_addrs->v4addrs, &iph->saddr,
sizeof(key_addrs->v4addrs));
key_control->addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS;
break;
}
case htons(ETH_P_IPV6): {
@ -203,8 +205,11 @@ ipv6:
FLOW_DISSECTOR_KEY_IPV6_HASH_ADDRS,
target_container);
key_addrs->src = (__force __be32)ipv6_addr_hash(&iph->saddr);
key_addrs->dst = (__force __be32)ipv6_addr_hash(&iph->daddr);
key_addrs->v4addrs.src =
(__force __be32)ipv6_addr_hash(&iph->saddr);
key_addrs->v4addrs.dst =
(__force __be32)ipv6_addr_hash(&iph->daddr);
key_control->addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS;
goto flow_label;
}
if (skb_flow_dissector_uses_key(flow_dissector,
@ -216,6 +221,7 @@ ipv6:
target_container);
memcpy(key_ipv6_addrs, &iph->saddr, sizeof(*key_ipv6_addrs));
key_control->addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS;
goto flow_label;
}
break;
@ -292,8 +298,9 @@ flow_label:
key_addrs = skb_flow_dissector_target(flow_dissector,
FLOW_DISSECTOR_KEY_IPV6_HASH_ADDRS,
target_container);
key_addrs->src = hdr->srcnode;
key_addrs->dst = 0;
key_addrs->v4addrs.src = hdr->srcnode;
key_addrs->v4addrs.dst = 0;
key_control->addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS;
}
return true;
}
@ -389,21 +396,88 @@ static inline void *flow_keys_hash_start(struct flow_keys *flow)
static inline size_t flow_keys_hash_length(struct flow_keys *flow)
{
size_t diff = FLOW_KEYS_HASH_OFFSET + sizeof(flow->addrs);
BUILD_BUG_ON((sizeof(*flow) - FLOW_KEYS_HASH_OFFSET) % sizeof(u32));
return (sizeof(*flow) - FLOW_KEYS_HASH_OFFSET) / sizeof(u32);
BUILD_BUG_ON(offsetof(typeof(*flow), addrs) !=
sizeof(*flow) - sizeof(flow->addrs));
switch (flow->control.addr_type) {
case FLOW_DISSECTOR_KEY_IPV4_ADDRS:
diff -= sizeof(flow->addrs.v4addrs);
break;
case FLOW_DISSECTOR_KEY_IPV6_ADDRS:
diff -= sizeof(flow->addrs.v6addrs);
break;
}
return (sizeof(*flow) - diff) / sizeof(u32);
}
__be32 flow_get_u32_src(const struct flow_keys *flow)
{
switch (flow->control.addr_type) {
case FLOW_DISSECTOR_KEY_IPV4_ADDRS:
return flow->addrs.v4addrs.src;
case FLOW_DISSECTOR_KEY_IPV6_ADDRS:
return (__force __be32)ipv6_addr_hash(
&flow->addrs.v6addrs.src);
default:
return 0;
}
}
EXPORT_SYMBOL(flow_get_u32_src);
__be32 flow_get_u32_dst(const struct flow_keys *flow)
{
switch (flow->control.addr_type) {
case FLOW_DISSECTOR_KEY_IPV4_ADDRS:
return flow->addrs.v4addrs.dst;
case FLOW_DISSECTOR_KEY_IPV6_ADDRS:
return (__force __be32)ipv6_addr_hash(
&flow->addrs.v6addrs.dst);
default:
return 0;
}
}
EXPORT_SYMBOL(flow_get_u32_dst);
static inline void __flow_hash_consistentify(struct flow_keys *keys)
{
int addr_diff, i;
switch (keys->control.addr_type) {
case FLOW_DISSECTOR_KEY_IPV4_ADDRS:
addr_diff = (__force u32)keys->addrs.v4addrs.dst -
(__force u32)keys->addrs.v4addrs.src;
if ((addr_diff < 0) ||
(addr_diff == 0 &&
((__force u16)keys->ports.dst <
(__force u16)keys->ports.src))) {
swap(keys->addrs.v4addrs.src, keys->addrs.v4addrs.dst);
swap(keys->ports.src, keys->ports.dst);
}
break;
case FLOW_DISSECTOR_KEY_IPV6_ADDRS:
addr_diff = memcmp(&keys->addrs.v6addrs.dst,
&keys->addrs.v6addrs.src,
sizeof(keys->addrs.v6addrs.dst));
if ((addr_diff < 0) ||
(addr_diff == 0 &&
((__force u16)keys->ports.dst <
(__force u16)keys->ports.src))) {
for (i = 0; i < 4; i++)
swap(keys->addrs.v6addrs.src.s6_addr32[i],
keys->addrs.v6addrs.dst.s6_addr32[i]);
swap(keys->ports.src, keys->ports.dst);
}
break;
}
}
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->addrs.dst < (__force u32)keys->addrs.src) ||
(((__force u32)keys->addrs.dst == (__force u32)keys->addrs.src) &&
((__force u16)keys->ports.dst < (__force u16)keys->ports.src))) {
swap(keys->addrs.dst, keys->addrs.src);
swap(keys->ports.src, keys->ports.dst);
}
__flow_hash_consistentify(keys);
hash = __flow_hash_words((u32 *)flow_keys_hash_start(keys),
flow_keys_hash_length(keys), keyval);
@ -451,8 +525,8 @@ void make_flow_keys_digest(struct flow_keys_digest *digest,
data->n_proto = flow->basic.n_proto;
data->ip_proto = flow->basic.ip_proto;
data->ports = flow->ports.ports;
data->src = flow->addrs.src;
data->dst = flow->addrs.dst;
data->src = flow->addrs.v4addrs.src;
data->dst = flow->addrs.v4addrs.dst;
}
EXPORT_SYMBOL(make_flow_keys_digest);
@ -566,11 +640,15 @@ static const struct flow_dissector_key flow_keys_dissector_keys[] = {
},
{
.key_id = FLOW_DISSECTOR_KEY_IPV4_ADDRS,
.offset = offsetof(struct flow_keys, addrs),
.offset = offsetof(struct flow_keys, addrs.v4addrs),
},
{
.key_id = FLOW_DISSECTOR_KEY_IPV6_ADDRS,
.offset = offsetof(struct flow_keys, addrs.v6addrs),
},
{
.key_id = FLOW_DISSECTOR_KEY_IPV6_HASH_ADDRS,
.offset = offsetof(struct flow_keys, addrs),
.offset = offsetof(struct flow_keys, addrs.v4addrs),
},
{
.key_id = FLOW_DISSECTOR_KEY_PORTS,

2
net/ethernet/eth.c
View File

@ -133,7 +133,7 @@ u32 eth_get_headlen(void *data, unsigned int len)
/* parse any remaining L2/L3 headers, check for L4 */
if (!skb_flow_dissect_flow_keys_buf(&keys, data, eth->h_proto,
sizeof(*eth), len))
return max_t(u32, keys.basic.thoff, sizeof(*eth));
return max_t(u32, keys.control.thoff, sizeof(*eth));
/* parse for any L4 headers */
return min_t(u32, __skb_get_poff(NULL, data, &keys, len), len);

14
net/sched/cls_flow.c
View File

@ -68,15 +68,21 @@ static inline u32 addr_fold(void *addr)
static u32 flow_get_src(const struct sk_buff *skb, const struct flow_keys *flow)
{
if (flow->addrs.src)
return ntohl(flow->addrs.src);
__be32 src = flow_get_u32_src(flow);
if (src)
return ntohl(src);
return addr_fold(skb->sk);
}
static u32 flow_get_dst(const struct sk_buff *skb, const struct flow_keys *flow)
{
if (flow->addrs.dst)
return ntohl(flow->addrs.dst);
__be32 dst = flow_get_u32_dst(flow);
if (dst)
return ntohl(dst);
return addr_fold(skb_dst(skb)) ^ (__force u16) tc_skb_protocol(skb);
}

11
net/sched/cls_flower.c
View File

@ -28,8 +28,9 @@ struct fl_flow_key {
struct flow_dissector_key_control control;
struct flow_dissector_key_basic basic;
struct flow_dissector_key_eth_addrs eth;
struct flow_dissector_key_addrs ipaddrs;
union {
struct flow_dissector_key_addrs ipv4;
struct flow_dissector_key_ipv4_addrs ipv4;
struct flow_dissector_key_ipv6_addrs ipv6;
};
struct flow_dissector_key_ports tp;
@ -260,14 +261,14 @@ static int fl_set_key(struct net *net, struct nlattr **tb,
&mask->basic.ip_proto, TCA_FLOWER_UNSPEC,
sizeof(key->basic.ip_proto));
}
if (key->basic.n_proto == htons(ETH_P_IP)) {
if (key->control.addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) {
fl_set_key_val(tb, &key->ipv4.src, TCA_FLOWER_KEY_IPV4_SRC,
&mask->ipv4.src, TCA_FLOWER_KEY_IPV4_SRC_MASK,
sizeof(key->ipv4.src));
fl_set_key_val(tb, &key->ipv4.dst, TCA_FLOWER_KEY_IPV4_DST,
&mask->ipv4.dst, TCA_FLOWER_KEY_IPV4_DST_MASK,
sizeof(key->ipv4.dst));
} else if (key->basic.n_proto == htons(ETH_P_IPV6)) {
} else if (key->control.addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) {
fl_set_key_val(tb, &key->ipv6.src, TCA_FLOWER_KEY_IPV6_SRC,
&mask->ipv6.src, TCA_FLOWER_KEY_IPV6_SRC_MASK,
sizeof(key->ipv6.src));
@ -610,7 +611,7 @@ static int fl_dump(struct net *net, struct tcf_proto *tp, unsigned long fh,
sizeof(key->basic.ip_proto)))
goto nla_put_failure;
if (key->basic.n_proto == htons(ETH_P_IP) &&
if (key->control.addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS &&
(fl_dump_key_val(skb, &key->ipv4.src, TCA_FLOWER_KEY_IPV4_SRC,
&mask->ipv4.src, TCA_FLOWER_KEY_IPV4_SRC_MASK,
sizeof(key->ipv4.src)) ||
@ -618,7 +619,7 @@ static int fl_dump(struct net *net, struct tcf_proto *tp, unsigned long fh,
&mask->ipv4.dst, TCA_FLOWER_KEY_IPV4_DST_MASK,
sizeof(key->ipv4.dst))))
goto nla_put_failure;
else if (key->basic.n_proto == htons(ETH_P_IPV6) &&
else if (key->control.addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS &&
(fl_dump_key_val(skb, &key->ipv6.src, TCA_FLOWER_KEY_IPV6_SRC,
&mask->ipv6.src, TCA_FLOWER_KEY_IPV6_SRC_MASK,
sizeof(key->ipv6.src)) ||