From 1bd758eb1cab2fa5b71a23f9e5d3c8076f4ed650 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Tue, 12 May 2015 14:56:07 +0200 Subject: net: change name of flow_dissector header to match the .c file name add couple of empty lines on the way. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/skbuff.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index c0b574a414e7..e35c2b13d434 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -34,7 +34,7 @@ #include #include #include -#include +#include /* A. Checksumming of received packets by device. * -- cgit v1.2.3-71-gd317 From 10b89ee43e849544eddfe34e535341fc077464ec Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Tue, 12 May 2015 14:56:09 +0200 Subject: net: move *skb_get_poff declarations into correct header Since these functions are defined in flow_dissector.c, move header declarations from skbuff.h into flow_dissector.h Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/skbuff.h | 4 ---- include/net/flow_dissector.h | 3 +++ net/core/filter.c | 1 + net/ethernet/eth.c | 1 + 4 files changed, 5 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index e35c2b13d434..17607ab9e7a2 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3424,10 +3424,6 @@ struct sk_buff *skb_checksum_trimmed(struct sk_buff *skb, unsigned int transport_len, __sum16(*skb_chkf)(struct sk_buff *skb)); -u32 skb_get_poff(const struct sk_buff *skb); -u32 __skb_get_poff(const struct sk_buff *skb, void *data, - const struct flow_keys *keys, int hlen); - /** * skb_head_is_locked - Determine if the skb->head is locked down * @skb: skb to check diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h index 118ae6926a72..4570ccafe59d 100644 --- a/include/net/flow_dissector.h +++ b/include/net/flow_dissector.h @@ -46,6 +46,9 @@ static inline __be32 skb_flow_get_ports(const struct sk_buff *skb, } u32 flow_hash_from_keys(struct flow_keys *keys); +u32 skb_get_poff(const struct sk_buff *skb); +u32 __skb_get_poff(const struct sk_buff *skb, void *data, + const struct flow_keys *keys, int hlen); /* struct flow_keys_digest: * diff --git a/net/core/filter.c b/net/core/filter.c index a831f193e2c7..6805717be614 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -36,6 +36,7 @@ #include #include #include +#include #include #include #include diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c index 9045e2a1108f..9332a0ab0698 100644 --- a/net/ethernet/eth.c +++ b/net/ethernet/eth.c @@ -58,6 +58,7 @@ #include #include #include +#include #include __setup("ether=", netdev_boot_setup); -- cgit v1.2.3-71-gd317 From 9c684b5083bc191c4b7b189c73d75587e167a474 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Tue, 12 May 2015 14:56:11 +0200 Subject: net: move __skb_get_hash function declaration to flow_dissector.h Since the definition of the function is in flow_dissector.c, it makes sense to have the declaration in flow_dissector.h Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/skbuff.h | 1 - include/net/flow_dissector.h | 1 + 2 files changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 17607ab9e7a2..ae2d1b7769d8 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -918,7 +918,6 @@ skb_set_hash(struct sk_buff *skb, __u32 hash, enum pkt_hash_types type) skb->hash = hash; } -void __skb_get_hash(struct sk_buff *skb); static inline __u32 skb_get_hash(struct sk_buff *skb) { if (!skb->l4_hash && !skb->sw_hash) diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h index 4570ccafe59d..e4ee761ca8c0 100644 --- a/include/net/flow_dissector.h +++ b/include/net/flow_dissector.h @@ -46,6 +46,7 @@ static inline __be32 skb_flow_get_ports(const struct sk_buff *skb, } u32 flow_hash_from_keys(struct flow_keys *keys); +void __skb_get_hash(struct sk_buff *skb); u32 skb_get_poff(const struct sk_buff *skb); u32 __skb_get_poff(const struct sk_buff *skb, void *data, const struct flow_keys *keys, int hlen); -- cgit v1.2.3-71-gd317 From 5605c76240aadc823e3d46ac9afde2f26fbcf019 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Tue, 12 May 2015 14:56:12 +0200 Subject: net: move __skb_tx_hash to dev.c __skb_tx_hash function has no relation to flow_dissect so just move it to dev.c Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/netdevice.h | 3 +++ include/linux/skbuff.h | 3 --- net/core/dev.c | 28 ++++++++++++++++++++++++++++ net/core/flow_dissector.c | 28 ---------------------------- 4 files changed, 31 insertions(+), 31 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index cd0951c1893d..d3ed01c18247 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2832,6 +2832,9 @@ static inline int netif_set_xps_queue(struct net_device *dev, } #endif +u16 __skb_tx_hash(const struct net_device *dev, struct sk_buff *skb, + unsigned int num_tx_queues); + /* * Returns a Tx hash for the given packet when dev->real_num_tx_queues is used * as a distribution range limit for the returned value. diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index ae2d1b7769d8..b01c7fba7c17 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3299,9 +3299,6 @@ static inline bool skb_rx_queue_recorded(const struct sk_buff *skb) return skb->queue_mapping != 0; } -u16 __skb_tx_hash(const struct net_device *dev, struct sk_buff *skb, - unsigned int num_tx_queues); - static inline struct sec_path *skb_sec_path(struct sk_buff *skb) { #ifdef CONFIG_XFRM diff --git a/net/core/dev.c b/net/core/dev.c index 90a568a150b4..d044d2f8532b 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2350,6 +2350,34 @@ void netif_device_attach(struct net_device *dev) } EXPORT_SYMBOL(netif_device_attach); +/* + * 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); + static void skb_warn_bad_offload(const struct sk_buff *skb) { static const netdev_features_t null_features = 0; diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 0d9bc3a586ba..07ca11d06339 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -371,34 +371,6 @@ __u32 skb_get_hash_perturb(const struct sk_buff *skb, u32 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) { -- cgit v1.2.3-71-gd317 From 06635a35d13d42b95422bba6633f175245cc644e Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Tue, 12 May 2015 14:56:16 +0200 Subject: flow_dissect: use programable dissector in skb_flow_dissect and friends Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/bonding/bond_main.c | 18 +-- drivers/net/ethernet/cisco/enic/enic_clsf.c | 27 ++-- drivers/net/ethernet/cisco/enic/enic_ethtool.c | 10 +- drivers/net/hyperv/netvsc_drv.c | 8 +- include/linux/skbuff.h | 4 +- include/net/flow_dissector.h | 63 ++++---- include/net/ip.h | 8 +- include/net/ipv6.h | 8 +- net/core/flow_dissector.c | 199 +++++++++++++++++-------- net/ethernet/eth.c | 6 +- net/sched/cls_flow.c | 20 +-- net/sched/sch_choke.c | 4 +- 12 files changed, 229 insertions(+), 146 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index fe7c38721775..ef26e0147050 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -3051,16 +3051,16 @@ static bool bond_flow_dissect(struct bonding *bond, struct sk_buff *skb, int noff, proto = -1; if (bond->params.xmit_policy > BOND_XMIT_POLICY_LAYER23) - return skb_flow_dissect(skb, fk); + return skb_flow_dissect_flow_keys(skb, fk); - fk->ports = 0; + fk->ports.ports = 0; noff = skb_network_offset(skb); if (skb->protocol == htons(ETH_P_IP)) { if (unlikely(!pskb_may_pull(skb, noff + sizeof(*iph)))) return false; iph = ip_hdr(skb); - fk->src = iph->saddr; - fk->dst = iph->daddr; + fk->addrs.src = iph->saddr; + fk->addrs.dst = iph->daddr; noff += iph->ihl << 2; if (!ip_is_fragment(iph)) proto = iph->protocol; @@ -3068,15 +3068,15 @@ 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->src = (__force __be32)ipv6_addr_hash(&iph6->saddr); - fk->dst = (__force __be32)ipv6_addr_hash(&iph6->daddr); + fk->addrs.src = (__force __be32)ipv6_addr_hash(&iph6->saddr); + fk->addrs.dst = (__force __be32)ipv6_addr_hash(&iph6->daddr); noff += sizeof(*iph6); proto = iph6->nexthdr; } else { return false; } if (bond->params.xmit_policy == BOND_XMIT_POLICY_LAYER34 && proto >= 0) - fk->ports = skb_flow_get_ports(skb, noff, proto); + fk->ports.ports = skb_flow_get_ports(skb, noff, proto); return true; } @@ -3102,8 +3102,8 @@ u32 bond_xmit_hash(struct bonding *bond, struct sk_buff *skb) bond->params.xmit_policy == BOND_XMIT_POLICY_ENCAP23) hash = bond_eth_hash(skb); else - hash = (__force u32)flow.ports; - hash ^= (__force u32)flow.dst ^ (__force u32)flow.src; + hash = (__force u32)flow.ports.ports; + hash ^= (__force u32)flow.addrs.dst ^ (__force u32)flow.addrs.src; hash ^= (hash >> 16); hash ^= (hash >> 8); diff --git a/drivers/net/ethernet/cisco/enic/enic_clsf.c b/drivers/net/ethernet/cisco/enic/enic_clsf.c index 380f04903a36..d3d25c7e5b96 100644 --- a/drivers/net/ethernet/cisco/enic/enic_clsf.c +++ b/drivers/net/ethernet/cisco/enic/enic_clsf.c @@ -22,7 +22,7 @@ int enic_addfltr_5t(struct enic *enic, struct flow_keys *keys, u16 rq) int res; struct filter data; - switch (keys->ip_proto) { + switch (keys->basic.ip_proto) { case IPPROTO_TCP: data.u.ipv4.protocol = PROTO_TCP; break; @@ -33,10 +33,10 @@ 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->src); - data.u.ipv4.dst_addr = ntohl(keys->dst); - data.u.ipv4.src_port = ntohs(keys->port16[0]); - data.u.ipv4.dst_port = ntohs(keys->port16[1]); + data.u.ipv4.src_addr = ntohl(keys->addrs.src); + data.u.ipv4.dst_addr = ntohl(keys->addrs.dst); + data.u.ipv4.src_port = ntohs(keys->ports.port16[0]); + data.u.ipv4.dst_port = ntohs(keys->ports.port16[1]); data.u.ipv4.flags = FILTER_FIELDS_IPV4_5TUPLE; spin_lock_bh(&enic->devcmd_lock); @@ -158,11 +158,11 @@ 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.src == k->src && - tpos->keys.dst == k->dst && - tpos->keys.ports == k->ports && - tpos->keys.ip_proto == k->ip_proto && - tpos->keys.n_proto == k->n_proto) + if (tpos->keys.addrs.src == k->addrs.src && + tpos->keys.addrs.dst == k->addrs.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) return tpos; return NULL; } @@ -177,9 +177,10 @@ int enic_rx_flow_steer(struct net_device *dev, const struct sk_buff *skb, int res, i; enic = netdev_priv(dev); - res = skb_flow_dissect(skb, &keys); - if (!res || keys.n_proto != htons(ETH_P_IP) || - (keys.ip_proto != IPPROTO_TCP && keys.ip_proto != IPPROTO_UDP)) + res = skb_flow_dissect_flow_keys(skb, &keys); + if (!res || keys.basic.n_proto != htons(ETH_P_IP) || + (keys.basic.ip_proto != IPPROTO_TCP && + keys.basic.ip_proto != IPPROTO_UDP)) return -EPROTONOSUPPORT; tbl_idx = skb_get_hash_raw(skb) & ENIC_RFS_FLW_MASK; diff --git a/drivers/net/ethernet/cisco/enic/enic_ethtool.c b/drivers/net/ethernet/cisco/enic/enic_ethtool.c index 28d9ca675a27..7588f8dcc890 100644 --- a/drivers/net/ethernet/cisco/enic/enic_ethtool.c +++ b/drivers/net/ethernet/cisco/enic/enic_ethtool.c @@ -334,7 +334,7 @@ static int enic_grxclsrule(struct enic *enic, struct ethtool_rxnfc *cmd) n = htbl_fltr_search(enic, (u16)fsp->location); if (!n) return -EINVAL; - switch (n->keys.ip_proto) { + switch (n->keys.basic.ip_proto) { case IPPROTO_TCP: fsp->flow_type = TCP_V4_FLOW; break; @@ -346,16 +346,16 @@ static int enic_grxclsrule(struct enic *enic, struct ethtool_rxnfc *cmd) break; } - fsp->h_u.tcp_ip4_spec.ip4src = n->keys.src; + fsp->h_u.tcp_ip4_spec.ip4src = n->keys.addrs.src; fsp->m_u.tcp_ip4_spec.ip4src = (__u32)~0; - fsp->h_u.tcp_ip4_spec.ip4dst = n->keys.dst; + fsp->h_u.tcp_ip4_spec.ip4dst = n->keys.addrs.dst; fsp->m_u.tcp_ip4_spec.ip4dst = (__u32)~0; - fsp->h_u.tcp_ip4_spec.psrc = n->keys.port16[0]; + fsp->h_u.tcp_ip4_spec.psrc = n->keys.ports.port16[0]; fsp->m_u.tcp_ip4_spec.psrc = (__u16)~0; - fsp->h_u.tcp_ip4_spec.pdst = n->keys.port16[1]; + fsp->h_u.tcp_ip4_spec.pdst = n->keys.ports.port16[1]; fsp->m_u.tcp_ip4_spec.pdst = (__u16)~0; fsp->ring_cookie = n->rq_id; diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index 5993c7e2d723..8e5fe888a0ec 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -196,12 +196,12 @@ static bool netvsc_set_hash(u32 *hash, struct sk_buff *skb) struct flow_keys flow; int data_len; - if (!skb_flow_dissect(skb, &flow) || - !(flow.n_proto == htons(ETH_P_IP) || - flow.n_proto == htons(ETH_P_IPV6))) + if (!skb_flow_dissect_flow_keys(skb, &flow) || + !(flow.basic.n_proto == htons(ETH_P_IP) || + flow.basic.n_proto == htons(ETH_P_IPV6))) return false; - if (flow.ip_proto == IPPROTO_TCP) + if (flow.basic.ip_proto == IPPROTO_TCP) data_len = 12; else data_len = 8; diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index b01c7fba7c17..f83aa6568cbf 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1935,8 +1935,8 @@ static inline void skb_probe_transport_header(struct sk_buff *skb, if (skb_transport_header_was_set(skb)) return; - else if (skb_flow_dissect(skb, &keys)) - skb_set_transport_header(skb, keys.thoff); + else if (skb_flow_dissect_flow_keys(skb, &keys)) + skb_set_transport_header(skb, keys.basic.thoff); else skb_set_transport_header(skb, offset_hint); } diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h index 20239e807f77..0c8d406fb730 100644 --- a/include/net/flow_dissector.h +++ b/include/net/flow_dissector.h @@ -59,42 +59,47 @@ struct flow_dissector { unsigned short int offset[FLOW_DISSECTOR_KEY_MAX]; }; -/* struct flow_keys: - * @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 - * @ports: port numbers of Transport header - * port16[0]: src port number - * port16[1]: dst port number - * @thoff: Transport header offset - * @n_proto: Network header protocol (eg. IPv4/IPv6) - * @ip_proto: Transport header protocol (eg. TCP/UDP) - * All the members, except thoff, are in network byte order. - */ -struct flow_keys { - /* (src,dst) must be grouped, in the same way than in IP header */ - __be32 src; - __be32 dst; - union { - __be32 ports; - __be16 port16[2]; - }; - u16 thoff; - __be16 n_proto; - u8 ip_proto; -}; - void skb_flow_dissector_init(struct flow_dissector *flow_dissector, const struct flow_dissector_key *key, unsigned int key_count); -bool __skb_flow_dissect(const struct sk_buff *skb, struct flow_keys *flow, + +bool __skb_flow_dissect(const struct sk_buff *skb, + struct flow_dissector *flow_dissector, + void *target_container, void *data, __be16 proto, int nhoff, int hlen); static inline bool skb_flow_dissect(const struct sk_buff *skb, - struct flow_keys *flow) + struct flow_dissector *flow_dissector, + void *target_container) +{ + return __skb_flow_dissect(skb, flow_dissector, target_container, + NULL, 0, 0, 0); +} + +struct flow_keys { + struct flow_dissector_key_addrs addrs; + struct flow_dissector_key_ports ports; + struct flow_dissector_key_basic basic; +}; + +extern struct flow_dissector flow_keys_dissector; +extern struct flow_dissector flow_keys_buf_dissector; + +static inline bool skb_flow_dissect_flow_keys(const struct sk_buff *skb, + struct flow_keys *flow) +{ + memset(flow, 0, sizeof(*flow)); + return __skb_flow_dissect(skb, &flow_keys_dissector, flow, + NULL, 0, 0, 0); +} + +static inline bool skb_flow_dissect_flow_keys_buf(struct flow_keys *flow, + void *data, __be16 proto, + int nhoff, int hlen) { - return __skb_flow_dissect(skb, flow, NULL, 0, 0, 0); + memset(flow, 0, sizeof(*flow)); + return __skb_flow_dissect(NULL, &flow_keys_buf_dissector, flow, + data, proto, nhoff, hlen); } __be32 __skb_flow_get_ports(const struct sk_buff *skb, int thoff, u8 ip_proto, diff --git a/include/net/ip.h b/include/net/ip.h index 562eb653aebc..b0443d4fe13f 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -360,10 +360,10 @@ static inline void inet_set_txhash(struct sock *sk) struct inet_sock *inet = inet_sk(sk); struct flow_keys keys; - keys.src = inet->inet_saddr; - keys.dst = inet->inet_daddr; - keys.port16[0] = inet->inet_sport; - keys.port16[1] = inet->inet_dport; + keys.addrs.src = inet->inet_saddr; + keys.addrs.dst = inet->inet_daddr; + keys.ports.port16[0] = inet->inet_sport; + keys.ports.port16[1] = inet->inet_dport; sk->sk_txhash = flow_hash_from_keys(&keys); } diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 9932b86394a9..9eed9761dfce 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -698,10 +698,10 @@ static inline void ip6_set_txhash(struct sock *sk) struct ipv6_pinfo *np = inet6_sk(sk); struct flow_keys keys; - keys.src = (__force __be32)ipv6_addr_hash(&np->saddr); - keys.dst = (__force __be32)ipv6_addr_hash(&sk->sk_v6_daddr); - keys.port16[0] = inet->inet_sport; - keys.port16[1] = inet->inet_dport; + keys.addrs.src = (__force __be32)ipv6_addr_hash(&np->saddr); + keys.addrs.dst = (__force __be32)ipv6_addr_hash(&sk->sk_v6_daddr); + keys.ports.port16[0] = inet->inet_sport; + keys.ports.port16[1] = inet->inet_dport; sk->sk_txhash = flow_hash_from_keys(&keys); } diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 6883e22b8fc4..6a49acaa6651 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include @@ -63,17 +64,6 @@ void skb_flow_dissector_init(struct flow_dissector *flow_dissector, } EXPORT_SYMBOL(skb_flow_dissector_init); -/* 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 @@ -111,17 +101,27 @@ 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 + * @flow_dissector: list of keys to dissect + * @target_container: target structure to put dissected values into * @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 + * The function will try to retrieve individual keys into target specified + * by flow_dissector from either the skbuff or a raw buffer specified by the + * rest parameters. + * + * Caller must take care of zeroing target container memory. */ -bool __skb_flow_dissect(const struct sk_buff *skb, struct flow_keys *flow, +bool __skb_flow_dissect(const struct sk_buff *skb, + struct flow_dissector *flow_dissector, + void *target_container, void *data, __be16 proto, int nhoff, int hlen) { + struct flow_dissector_key_basic *key_basic; + struct flow_dissector_key_addrs *key_addrs; + struct flow_dissector_key_ports *key_ports; u8 ip_proto; if (!data) { @@ -131,7 +131,12 @@ bool __skb_flow_dissect(const struct sk_buff *skb, struct flow_keys *flow, hlen = skb_headlen(skb); } - memset(flow, 0, sizeof(*flow)); + /* It is ensured by skb_flow_dissector_init() that basic key will + * be always present. + */ + key_basic = skb_flow_dissector_target(flow_dissector, + FLOW_DISSECTOR_KEY_BASIC, + target_container); again: switch (proto) { @@ -148,14 +153,13 @@ ip: 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) + if (!skb_flow_dissector_uses_key(flow_dissector, + FLOW_DISSECTOR_KEY_IPV4_ADDRS)) break; - - iph_to_flow_copy_addrs(flow, iph); + key_addrs = skb_flow_dissector_target(flow_dissector, + FLOW_DISSECTOR_KEY_IPV4_ADDRS, + target_container); + memcpy(key_addrs, &iph->saddr, sizeof(*key_addrs)); break; } case htons(ETH_P_IPV6): { @@ -171,12 +175,15 @@ ipv6: ip_proto = iph->nexthdr; nhoff += sizeof(struct ipv6hdr); - /* see comment above in IPv4 section */ - if (!skb) + if (!skb_flow_dissector_uses_key(flow_dissector, + FLOW_DISSECTOR_KEY_IPV6_HASH_ADDRS)) break; + key_addrs = skb_flow_dissector_target(flow_dissector, + FLOW_DISSECTOR_KEY_IPV6_HASH_ADDRS, + target_container); - flow->src = (__force __be32)ipv6_addr_hash(&iph->saddr); - flow->dst = (__force __be32)ipv6_addr_hash(&iph->daddr); + key_addrs->src = (__force __be32)ipv6_addr_hash(&iph->saddr); + key_addrs->dst = (__force __be32)ipv6_addr_hash(&iph->daddr); flow_label = ip6_flowlabel(iph); if (flow_label) { @@ -184,10 +191,18 @@ ipv6: * 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; + + key_basic->n_proto = proto; + key_basic->ip_proto = ip_proto; + key_basic->thoff = (u16)nhoff; + + if (!skb_flow_dissector_uses_key(flow_dissector, + FLOW_DISSECTOR_KEY_PORTS)) + break; + key_ports = skb_flow_dissector_target(flow_dissector, + FLOW_DISSECTOR_KEY_PORTS, + target_container); + key_ports->ports = flow_label; return true; } @@ -234,14 +249,22 @@ ipv6: 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; + key_basic->n_proto = proto; + key_basic->thoff = (u16)nhoff; + + if (skb_flow_dissector_uses_key(flow_dissector, + FLOW_DISSECTOR_KEY_IPV6_HASH_ADDRS)) { + return true; + 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; + } return true; } case htons(ETH_P_FCOE): - flow->thoff = (u16)(nhoff + FCOE_HEADER_LEN); + key_basic->thoff = (u16)(nhoff + FCOE_HEADER_LEN); /* fall through */ default: return false; @@ -296,14 +319,24 @@ ipv6: 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); + /* It is ensured by skb_flow_dissector_init() that basic key will + * be always present. + */ + key_basic = skb_flow_dissector_target(flow_dissector, + FLOW_DISSECTOR_KEY_BASIC, + target_container); + key_basic->n_proto = proto; + key_basic->ip_proto = ip_proto; + key_basic->thoff = (u16) nhoff; + + if (skb_flow_dissector_uses_key(flow_dissector, + FLOW_DISSECTOR_KEY_PORTS)) { + key_ports = skb_flow_dissector_target(flow_dissector, + FLOW_DISSECTOR_KEY_PORTS, + target_container); + key_ports->ports = __skb_flow_get_ports(skb, nhoff, ip_proto, + data, hlen); + } return true; } @@ -325,16 +358,16 @@ 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]); + 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.port16[1] < (__force u16)keys->ports.port16[0]))) { + swap(keys->addrs.dst, keys->addrs.src); + swap(keys->ports.port16[0], keys->ports.port16[1]); } - hash = __flow_hash_3words((__force u32)keys->dst, - (__force u32)keys->src, - (__force u32)keys->ports, + hash = __flow_hash_3words((__force u32)keys->addrs.dst, + (__force u32)keys->addrs.src, + (__force u32)keys->ports.ports, keyval); if (!hash) hash = 1; @@ -352,7 +385,7 @@ 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)) + if (!skb_flow_dissect_flow_keys(skb, keys)) return 0; return __flow_hash_from_keys(keys, keyval); @@ -377,11 +410,11 @@ void make_flow_keys_digest(struct flow_keys_digest *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; + 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; } EXPORT_SYMBOL(make_flow_keys_digest); @@ -404,7 +437,7 @@ void __skb_get_hash(struct sk_buff *skb) hash = ___skb_get_hash(skb, &keys, hashrnd); if (!hash) return; - if (keys.ports) + if (keys.ports.ports) skb->l4_hash = 1; skb->sw_hash = 1; skb->hash = hash; @@ -422,9 +455,9 @@ EXPORT_SYMBOL(skb_get_hash_perturb); u32 __skb_get_poff(const struct sk_buff *skb, void *data, const struct flow_keys *keys, int hlen) { - u32 poff = keys->thoff; + u32 poff = keys->basic.thoff; - switch (keys->ip_proto) { + switch (keys->basic.ip_proto) { case IPPROTO_TCP: { /* access doff as u8 to avoid unaligned access */ const u8 *doff; @@ -478,8 +511,52 @@ u32 skb_get_poff(const struct sk_buff *skb) { struct flow_keys keys; - if (!skb_flow_dissect(skb, &keys)) + if (!skb_flow_dissect_flow_keys(skb, &keys)) return 0; return __skb_get_poff(skb, skb->data, &keys, skb_headlen(skb)); } + +static const struct flow_dissector_key flow_keys_dissector_keys[] = { + { + .key_id = FLOW_DISSECTOR_KEY_BASIC, + .offset = offsetof(struct flow_keys, basic), + }, + { + .key_id = FLOW_DISSECTOR_KEY_IPV4_ADDRS, + .offset = offsetof(struct flow_keys, addrs), + }, + { + .key_id = FLOW_DISSECTOR_KEY_IPV6_HASH_ADDRS, + .offset = offsetof(struct flow_keys, addrs), + }, + { + .key_id = FLOW_DISSECTOR_KEY_PORTS, + .offset = offsetof(struct flow_keys, ports), + }, +}; + +static const struct flow_dissector_key flow_keys_buf_dissector_keys[] = { + { + .key_id = FLOW_DISSECTOR_KEY_BASIC, + .offset = offsetof(struct flow_keys, basic), + }, +}; + +struct flow_dissector flow_keys_dissector __read_mostly; +EXPORT_SYMBOL(flow_keys_dissector); + +struct flow_dissector flow_keys_buf_dissector __read_mostly; + +static int __init init_default_flow_dissectors(void) +{ + skb_flow_dissector_init(&flow_keys_dissector, + flow_keys_dissector_keys, + ARRAY_SIZE(flow_keys_dissector_keys)); + skb_flow_dissector_init(&flow_keys_buf_dissector, + flow_keys_buf_dissector_keys, + ARRAY_SIZE(flow_keys_buf_dissector_keys)); + return 0; +} + +late_initcall_sync(init_default_flow_dissectors); diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c index 9332a0ab0698..c3325bd2f3fb 100644 --- a/net/ethernet/eth.c +++ b/net/ethernet/eth.c @@ -131,9 +131,9 @@ u32 eth_get_headlen(void *data, unsigned int len) return len; /* parse any remaining L2/L3 headers, check for L4 */ - if (!__skb_flow_dissect(NULL, &keys, data, - eth->h_proto, sizeof(*eth), len)) - return max_t(u32, keys.thoff, sizeof(*eth)); + if (!skb_flow_dissect_flow_keys_buf(&keys, data, eth->h_proto, + sizeof(*eth), len)) + return max_t(u32, keys.basic.thoff, sizeof(*eth)); /* parse for any L4 headers */ return min_t(u32, __skb_get_poff(NULL, data, &keys, len), len); diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c index 4c5a92298906..4b3e3e30bf4d 100644 --- a/net/sched/cls_flow.c +++ b/net/sched/cls_flow.c @@ -68,35 +68,35 @@ static inline u32 addr_fold(void *addr) static u32 flow_get_src(const struct sk_buff *skb, const struct flow_keys *flow) { - if (flow->src) - return ntohl(flow->src); + if (flow->addrs.src) + return ntohl(flow->addrs.src); return addr_fold(skb->sk); } static u32 flow_get_dst(const struct sk_buff *skb, const struct flow_keys *flow) { - if (flow->dst) - return ntohl(flow->dst); + if (flow->addrs.dst) + return ntohl(flow->addrs.dst); return addr_fold(skb_dst(skb)) ^ (__force u16) tc_skb_protocol(skb); } static u32 flow_get_proto(const struct sk_buff *skb, const struct flow_keys *flow) { - return flow->ip_proto; + return flow->basic.ip_proto; } static u32 flow_get_proto_src(const struct sk_buff *skb, const struct flow_keys *flow) { - if (flow->ports) - return ntohs(flow->port16[0]); + if (flow->ports.ports) + return ntohs(flow->ports.port16[0]); return addr_fold(skb->sk); } static u32 flow_get_proto_dst(const struct sk_buff *skb, const struct flow_keys *flow) { - if (flow->ports) - return ntohs(flow->port16[1]); + if (flow->ports.ports) + return ntohs(flow->ports.port16[1]); return addr_fold(skb_dst(skb)) ^ (__force u16) tc_skb_protocol(skb); } @@ -295,7 +295,7 @@ static int flow_classify(struct sk_buff *skb, const struct tcf_proto *tp, keymask = f->keymask; if (keymask & FLOW_KEYS_NEEDED) - skb_flow_dissect(skb, &flow_keys); + skb_flow_dissect_flow_keys(skb, &flow_keys); for (n = 0; n < f->nkeys; n++) { key = ffs(keymask) - 1; diff --git a/net/sched/sch_choke.c b/net/sched/sch_choke.c index 2624e991a2d1..93d5742dc7e0 100644 --- a/net/sched/sch_choke.c +++ b/net/sched/sch_choke.c @@ -170,13 +170,13 @@ static bool choke_match_flow(struct sk_buff *skb1, if (!choke_skb_cb(skb1)->keys_valid) { choke_skb_cb(skb1)->keys_valid = 1; - skb_flow_dissect(skb1, &temp); + skb_flow_dissect_flow_keys(skb1, &temp); make_flow_keys_digest(&choke_skb_cb(skb1)->keys, &temp); } if (!choke_skb_cb(skb2)->keys_valid) { choke_skb_cb(skb2)->keys_valid = 1; - skb_flow_dissect(skb2, &temp); + skb_flow_dissect_flow_keys(skb2, &temp); make_flow_keys_digest(&choke_skb_cb(skb2)->keys, &temp); } -- cgit v1.2.3-71-gd317