summaryrefslogtreecommitdiffstats
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.c135
1 files changed, 94 insertions, 41 deletions
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 5f362c1d033..45084938c40 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -13,6 +13,7 @@
#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;
@@ -26,36 +27,61 @@ static void iph_to_flow_copy_addrs(struct flow_keys *flow, const struct iphdr *i
}
/**
- * skb_flow_get_ports - extract the upper layer ports and return them
- * @skb: buffer to extract the ports from
+ * __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)
+__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), &_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);
+EXPORT_SYMBOL(__skb_flow_get_ports);
-bool skb_flow_dissect(const struct sk_buff *skb, struct flow_keys *flow)
+/**
+ * __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)
{
- int nhoff = skb_network_offset(skb);
u8 ip_proto;
- __be16 proto = skb->protocol;
+
+ if (!data) {
+ data = skb->data;
+ proto = skb->protocol;
+ nhoff = skb_network_offset(skb);
+ hlen = skb_headlen(skb);
+ }
memset(flow, 0, sizeof(*flow));
@@ -65,7 +91,7 @@ again:
const struct iphdr *iph;
struct iphdr _iph;
ip:
- iph = skb_header_pointer(skb, nhoff, sizeof(_iph), &_iph);
+ iph = __skb_header_pointer(skb, nhoff, sizeof(_iph), data, hlen, &_iph);
if (!iph || iph->ihl < 5)
return false;
nhoff += iph->ihl * 4;
@@ -74,6 +100,13 @@ 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)
+ break;
+
iph_to_flow_copy_addrs(flow, iph);
break;
}
@@ -83,14 +116,19 @@ ip:
__be32 flow_label;
ipv6:
- iph = skb_header_pointer(skb, nhoff, sizeof(_iph), &_iph);
+ 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);
- nhoff += sizeof(struct ipv6hdr);
flow_label = ip6_flowlabel(iph);
if (flow_label) {
@@ -113,7 +151,7 @@ ipv6:
const struct vlan_hdr *vlan;
struct vlan_hdr _vlan;
- vlan = skb_header_pointer(skb, nhoff, sizeof(_vlan), &_vlan);
+ vlan = __skb_header_pointer(skb, nhoff, sizeof(_vlan), data, hlen, &_vlan);
if (!vlan)
return false;
@@ -126,7 +164,7 @@ ipv6:
struct pppoe_hdr hdr;
__be16 proto;
} *hdr, _hdr;
- hdr = skb_header_pointer(skb, nhoff, sizeof(_hdr), &_hdr);
+ hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data, hlen, &_hdr);
if (!hdr)
return false;
proto = hdr->proto;
@@ -140,6 +178,9 @@ ipv6:
return false;
}
}
+ case htons(ETH_P_FCOE):
+ flow->thoff = (u16)(nhoff + FCOE_HEADER_LEN);
+ /* fall through */
default:
return false;
}
@@ -151,7 +192,7 @@ ipv6:
__be16 proto;
} *hdr, _hdr;
- hdr = skb_header_pointer(skb, nhoff, sizeof(_hdr), &_hdr);
+ hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data, hlen, &_hdr);
if (!hdr)
return false;
/*
@@ -171,8 +212,9 @@ ipv6:
const struct ethhdr *eth;
struct ethhdr _eth;
- eth = skb_header_pointer(skb, nhoff,
- sizeof(_eth), &_eth);
+ eth = __skb_header_pointer(skb, nhoff,
+ sizeof(_eth),
+ data, hlen, &_eth);
if (!eth)
return false;
proto = eth->h_proto;
@@ -194,12 +236,16 @@ ipv6:
flow->n_proto = proto;
flow->ip_proto = ip_proto;
- flow->ports = skb_flow_get_ports(skb, nhoff, 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);
+EXPORT_SYMBOL(__skb_flow_dissect);
static u32 hashrnd __read_mostly;
static __always_inline void __flow_hash_secret_init(void)
@@ -286,34 +332,27 @@ u16 __skb_tx_hash(const struct net_device *dev, struct sk_buff *skb,
qcount = dev->tc_to_txq[tc].count;
}
- return (u16) (((u64)skb_get_hash(skb) * qcount) >> 32) + qoffset;
+ return (u16) reciprocal_scale(skb_get_hash(skb), qcount) + qoffset;
}
EXPORT_SYMBOL(__skb_tx_hash);
-/* __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)
+u32 __skb_get_poff(const struct sk_buff *skb, void *data,
+ const struct flow_keys *keys, int hlen)
{
- struct flow_keys keys;
- u32 poff = 0;
+ u32 poff = keys->thoff;
- if (!skb_flow_dissect(skb, &keys))
- return 0;
-
- poff += keys.thoff;
- switch (keys.ip_proto) {
+ switch (keys->ip_proto) {
case IPPROTO_TCP: {
- const struct tcphdr *tcph;
- struct tcphdr _tcph;
+ /* access doff as u8 to avoid unaligned access */
+ const u8 *doff;
+ u8 _doff;
- tcph = skb_header_pointer(skb, poff, sizeof(_tcph), &_tcph);
- if (!tcph)
+ doff = __skb_header_pointer(skb, poff + 12, sizeof(_doff),
+ data, hlen, &_doff);
+ if (!doff)
return poff;
- poff += max_t(u32, sizeof(struct tcphdr), tcph->doff * 4);
+ poff += max_t(u32, sizeof(struct tcphdr), (*doff & 0xF0) >> 2);
break;
}
case IPPROTO_UDP:
@@ -343,6 +382,21 @@ u32 __skb_get_poff(const struct sk_buff *skb)
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
@@ -359,9 +413,8 @@ static inline int get_xps_queue(struct net_device *dev, struct sk_buff *skb)
if (map->len == 1)
queue_index = map->queues[0];
else
- queue_index = map->queues[
- ((u64)skb_get_hash(skb) * map->len) >> 32];
-
+ queue_index = map->queues[reciprocal_scale(skb_get_hash(skb),
+ map->len)];
if (unlikely(queue_index >= dev->real_num_tx_queues))
queue_index = -1;
}
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-04-01 18:14:45 +0000