aboutsummaryrefslogtreecommitdiff
path: root/net/core/flow_dissector.c
diff options
context:
space:
mode:
Diffstat (limited to 'net/core/flow_dissector.c')
-rw-r--r--net/core/flow_dissector.c209
1 files changed, 148 insertions, 61 deletions
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 9d4c7201400..107ed12a532 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -5,6 +5,10 @@
#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>
@@ -21,9 +25,35 @@ static void iph_to_flow_copy_addrs(struct flow_keys *flow, const struct iphdr *i
memcpy(&flow->src, &iph->saddr, sizeof(flow->src) + sizeof(flow->dst));
}
+/**
+ * skb_flow_get_ports - extract the upper layer ports and return them
+ * @skb: buffer to extract the ports from
+ * @thoff: transport header offset
+ * @ip_proto: protocol for which to get port offset
+ *
+ * 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)
+{
+ int poff = proto_ports_offset(ip_proto);
+
+ if (poff >= 0) {
+ __be32 *ports, _ports;
+
+ ports = skb_header_pointer(skb, thoff + poff,
+ sizeof(_ports), &_ports);
+ if (ports)
+ return *ports;
+ }
+
+ return 0;
+}
+EXPORT_SYMBOL(skb_flow_get_ports);
+
bool skb_flow_dissect(const struct sk_buff *skb, struct flow_keys *flow)
{
- int poff, nhoff = skb_network_offset(skb);
+ int nhoff = skb_network_offset(skb);
u8 ip_proto;
__be16 proto = skb->protocol;
@@ -31,23 +61,23 @@ bool skb_flow_dissect(const struct sk_buff *skb, struct flow_keys *flow)
again:
switch (proto) {
- case __constant_htons(ETH_P_IP): {
+ case htons(ETH_P_IP): {
const struct iphdr *iph;
struct iphdr _iph;
ip:
iph = skb_header_pointer(skb, nhoff, sizeof(_iph), &_iph);
- if (!iph)
+ if (!iph || iph->ihl < 5)
return false;
+ nhoff += iph->ihl * 4;
+ ip_proto = iph->protocol;
if (ip_is_fragment(iph))
ip_proto = 0;
- else
- ip_proto = iph->protocol;
+
iph_to_flow_copy_addrs(flow, iph);
- nhoff += iph->ihl * 4;
break;
}
- case __constant_htons(ETH_P_IPV6): {
+ case htons(ETH_P_IPV6): {
const struct ipv6hdr *iph;
struct ipv6hdr _iph;
ipv6:
@@ -61,7 +91,8 @@ ipv6:
nhoff += sizeof(struct ipv6hdr);
break;
}
- case __constant_htons(ETH_P_8021Q): {
+ case htons(ETH_P_8021AD):
+ case htons(ETH_P_8021Q): {
const struct vlan_hdr *vlan;
struct vlan_hdr _vlan;
@@ -73,7 +104,7 @@ ipv6:
nhoff += sizeof(*vlan);
goto again;
}
- case __constant_htons(ETH_P_PPP_SES): {
+ case htons(ETH_P_PPP_SES): {
struct {
struct pppoe_hdr hdr;
__be16 proto;
@@ -84,9 +115,9 @@ ipv6:
proto = hdr->proto;
nhoff += PPPOE_SES_HLEN;
switch (proto) {
- case __constant_htons(PPP_IP):
+ case htons(PPP_IP):
goto ip;
- case __constant_htons(PPP_IPV6):
+ case htons(PPP_IPV6):
goto ipv6;
default:
return false;
@@ -119,40 +150,64 @@ ipv6:
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), &_eth);
+ if (!eth)
+ return false;
+ proto = eth->h_proto;
+ nhoff += sizeof(*eth);
+ }
goto again;
}
break;
}
case IPPROTO_IPIP:
- goto again;
+ proto = htons(ETH_P_IP);
+ goto ip;
+ case IPPROTO_IPV6:
+ proto = htons(ETH_P_IPV6);
+ goto ipv6;
default:
break;
}
flow->ip_proto = ip_proto;
- poff = proto_ports_offset(ip_proto);
- if (poff >= 0) {
- __be32 *ports, _ports;
-
- nhoff += poff;
- ports = skb_header_pointer(skb, nhoff, sizeof(_ports), &_ports);
- if (ports)
- flow->ports = *ports;
- }
+ flow->ports = skb_flow_get_ports(skb, nhoff, ip_proto);
+ flow->thoff = (u16) nhoff;
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)
+{
+ __flow_hash_secret_init();
+ return jhash_3words(a, b, c, hashrnd);
+}
+
+static __always_inline u32 __flow_hash_1word(u32 a)
+{
+ __flow_hash_secret_init();
+ return jhash_1word(a, hashrnd);
+}
/*
- * __skb_get_rxhash: calculate a flow hash based on src/dst addresses
- * and src/dst port numbers. Sets rxhash in skb to non-zero hash value
- * on success, zero indicates no valid hash. Also, sets l4_rxhash in skb
+ * __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_rxhash(struct sk_buff *skb)
+void __skb_get_hash(struct sk_buff *skb)
{
struct flow_keys keys;
u32 hash;
@@ -161,7 +216,7 @@ void __skb_get_rxhash(struct sk_buff *skb)
return;
if (keys.ports)
- skb->l4_rxhash = 1;
+ skb->l4_hash = 1;
/* get a consistent hash (same value on both flow directions) */
if (((__force u32)keys.dst < (__force u32)keys.src) ||
@@ -171,15 +226,15 @@ void __skb_get_rxhash(struct sk_buff *skb)
swap(keys.port16[0], keys.port16[1]);
}
- hash = jhash_3words((__force u32)keys.dst,
- (__force u32)keys.src,
- (__force u32)keys.ports, hashrnd);
+ hash = __flow_hash_3words((__force u32)keys.dst,
+ (__force u32)keys.src,
+ (__force u32)keys.ports);
if (!hash)
hash = 1;
- skb->rxhash = hash;
+ skb->hash = hash;
}
-EXPORT_SYMBOL(__skb_get_rxhash);
+EXPORT_SYMBOL(__skb_get_hash);
/*
* Returns a Tx hash based on the given packet descriptor a Tx queues' number
@@ -209,21 +264,63 @@ u16 __skb_tx_hash(const struct net_device *dev, const struct sk_buff *skb,
hash = skb->sk->sk_hash;
else
hash = (__force u16) skb->protocol;
- hash = jhash_1word(hash, hashrnd);
+ hash = __flow_hash_1word(hash);
return (u16) (((u64) hash * qcount) >> 32) + qoffset;
}
EXPORT_SYMBOL(__skb_tx_hash);
-static inline u16 dev_cap_txqueue(struct net_device *dev, u16 queue_index)
+/* __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)
{
- if (unlikely(queue_index >= dev->real_num_tx_queues)) {
- net_warn_ratelimited("%s selects TX queue %d, but real number of TX queues is %d\n",
- dev->name, queue_index,
- dev->real_num_tx_queues);
+ struct flow_keys keys;
+ u32 poff = 0;
+
+ if (!skb_flow_dissect(skb, &keys))
return 0;
+
+ poff += keys.thoff;
+ switch (keys.ip_proto) {
+ case IPPROTO_TCP: {
+ const struct tcphdr *tcph;
+ struct tcphdr _tcph;
+
+ tcph = skb_header_pointer(skb, poff, sizeof(_tcph), &_tcph);
+ if (!tcph)
+ return poff;
+
+ poff += max_t(u32, sizeof(struct tcphdr), tcph->doff * 4);
+ break;
}
- return queue_index;
+ 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;
}
static inline int get_xps_queue(struct net_device *dev, struct sk_buff *skb)
@@ -247,8 +344,8 @@ static inline int get_xps_queue(struct net_device *dev, struct sk_buff *skb)
hash = skb->sk->sk_hash;
else
hash = (__force u16) skb->protocol ^
- skb->rxhash;
- hash = jhash_1word(hash, hashrnd);
+ skb->hash;
+ hash = __flow_hash_1word(hash);
queue_index = map->queues[
((u64)hash * map->len) >> 32];
}
@@ -264,7 +361,7 @@ static inline int get_xps_queue(struct net_device *dev, struct sk_buff *skb)
#endif
}
-u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb)
+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);
@@ -275,44 +372,34 @@ u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb)
if (new_index < 0)
new_index = skb_tx_hash(dev, skb);
- if (queue_index != new_index && sk) {
- struct dst_entry *dst =
- rcu_dereference_check(sk->sk_dst_cache, 1);
-
- if (dst && skb_dst(skb) == dst)
- sk_tx_queue_set(sk, queue_index);
-
- }
+ 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;
}
-EXPORT_SYMBOL(__netdev_pick_tx);
struct netdev_queue *netdev_pick_tx(struct net_device *dev,
- struct sk_buff *skb)
+ struct sk_buff *skb,
+ void *accel_priv)
{
int queue_index = 0;
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);
+ queue_index = ops->ndo_select_queue(dev, skb, accel_priv,
+ __netdev_pick_tx);
else
queue_index = __netdev_pick_tx(dev, skb);
- queue_index = dev_cap_txqueue(dev, queue_index);
+
+ 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);
}
-
-static int __init initialize_hashrnd(void)
-{
- get_random_bytes(&hashrnd, sizeof(hashrnd));
- return 0;
-}
-
-late_initcall_sync(initialize_hashrnd);
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-11-10 04:04:42 +0000