openvswitch: Pack struct sw_flow_key.
struct sw_flow_key has two 16-bit holes. Move the most matched
conntrack match fields there. In some typical cases this reduces the
size of the key that needs to be hashed into half and into one cache
line.
Signed-off-by: Jarno Rajahalme <jarno@ovn.org>
Acked-by: Joe Stringer <joe@ovn.org>
Acked-by: Pravin B Shelar <pshelar@ovn.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
index 8b15bab..c2d452e 100644
--- a/net/openvswitch/conntrack.c
+++ b/net/openvswitch/conntrack.c
@@ -152,7 +152,7 @@
const struct nf_conntrack_tuple *orig,
u8 icmp_proto)
{
- key->ct.orig_proto = orig->dst.protonum;
+ key->ct_orig_proto = orig->dst.protonum;
if (orig->dst.protonum == icmp_proto) {
key->ct.orig_tp.src = htons(orig->dst.u.icmp.type);
key->ct.orig_tp.dst = htons(orig->dst.u.icmp.code);
@@ -166,8 +166,8 @@
const struct nf_conntrack_zone *zone,
const struct nf_conn *ct)
{
- key->ct.state = state;
- key->ct.zone = zone->id;
+ key->ct_state = state;
+ key->ct_zone = zone->id;
key->ct.mark = ovs_ct_get_mark(ct);
ovs_ct_get_labels(ct, &key->ct.labels);
@@ -195,10 +195,10 @@
return;
}
}
- /* Clear 'ct.orig_proto' to mark the non-existence of conntrack
+ /* Clear 'ct_orig_proto' to mark the non-existence of conntrack
* original direction key fields.
*/
- key->ct.orig_proto = 0;
+ key->ct_orig_proto = 0;
}
/* Update 'key' based on skb->_nfct. If 'post_ct' is true, then OVS has
@@ -228,7 +228,7 @@
if (ct->master)
state |= OVS_CS_F_RELATED;
if (keep_nat_flags) {
- state |= key->ct.state & OVS_CS_F_NAT_MASK;
+ state |= key->ct_state & OVS_CS_F_NAT_MASK;
} else {
if (ct->status & IPS_SRC_NAT)
state |= OVS_CS_F_SRC_NAT;
@@ -259,11 +259,11 @@
int ovs_ct_put_key(const struct sw_flow_key *swkey,
const struct sw_flow_key *output, struct sk_buff *skb)
{
- if (nla_put_u32(skb, OVS_KEY_ATTR_CT_STATE, output->ct.state))
+ if (nla_put_u32(skb, OVS_KEY_ATTR_CT_STATE, output->ct_state))
return -EMSGSIZE;
if (IS_ENABLED(CONFIG_NF_CONNTRACK_ZONES) &&
- nla_put_u16(skb, OVS_KEY_ATTR_CT_ZONE, output->ct.zone))
+ nla_put_u16(skb, OVS_KEY_ATTR_CT_ZONE, output->ct_zone))
return -EMSGSIZE;
if (IS_ENABLED(CONFIG_NF_CONNTRACK_MARK) &&
@@ -275,14 +275,14 @@
&output->ct.labels))
return -EMSGSIZE;
- if (swkey->ct.orig_proto) {
+ if (swkey->ct_orig_proto) {
if (swkey->eth.type == htons(ETH_P_IP)) {
struct ovs_key_ct_tuple_ipv4 orig = {
output->ipv4.ct_orig.src,
output->ipv4.ct_orig.dst,
output->ct.orig_tp.src,
output->ct.orig_tp.dst,
- output->ct.orig_proto,
+ output->ct_orig_proto,
};
if (nla_put(skb, OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV4,
sizeof(orig), &orig))
@@ -293,7 +293,7 @@
IN6_ADDR_INITIALIZER(output->ipv6.ct_orig.dst),
output->ct.orig_tp.src,
output->ct.orig_tp.dst,
- output->ct.orig_proto,
+ output->ct_orig_proto,
};
if (nla_put(skb, OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6,
sizeof(orig), &orig))
@@ -612,11 +612,11 @@
* due to an upcall. If the connection was not confirmed, it is not
* cached and needs to be run through conntrack again.
*/
- if (!ct && key->ct.state & OVS_CS_F_TRACKED &&
- !(key->ct.state & OVS_CS_F_INVALID) &&
- key->ct.zone == info->zone.id) {
+ if (!ct && key->ct_state & OVS_CS_F_TRACKED &&
+ !(key->ct_state & OVS_CS_F_INVALID) &&
+ key->ct_zone == info->zone.id) {
ct = ovs_ct_find_existing(net, &info->zone, info->family, skb,
- !!(key->ct.state
+ !!(key->ct_state
& OVS_CS_F_NAT_MASK));
if (ct)
nf_ct_get(skb, &ctinfo);
@@ -740,7 +740,7 @@
if (maniptype == NF_NAT_MANIP_SRC) {
__be16 src;
- key->ct.state |= OVS_CS_F_SRC_NAT;
+ key->ct_state |= OVS_CS_F_SRC_NAT;
if (key->eth.type == htons(ETH_P_IP))
key->ipv4.addr.src = ip_hdr(skb)->saddr;
else if (key->eth.type == htons(ETH_P_IPV6))
@@ -762,7 +762,7 @@
} else {
__be16 dst;
- key->ct.state |= OVS_CS_F_DST_NAT;
+ key->ct_state |= OVS_CS_F_DST_NAT;
if (key->eth.type == htons(ETH_P_IP))
key->ipv4.addr.dst = ip_hdr(skb)->daddr;
else if (key->eth.type == htons(ETH_P_IPV6))
@@ -886,7 +886,7 @@
* NAT after the nf_conntrack_in() call. We can actually clear
* the whole state, as it will be re-initialized below.
*/
- key->ct.state = 0;
+ key->ct_state = 0;
/* Update the key, but keep the NAT flags. */
ovs_ct_update_key(skb, info, key, true, true);
@@ -902,9 +902,9 @@
*
* NAT will be done only if the CT action has NAT, and only
* once per packet (per zone), as guarded by the NAT bits in
- * the key->ct.state.
+ * the key->ct_state.
*/
- if (info->nat && !(key->ct.state & OVS_CS_F_NAT_MASK) &&
+ if (info->nat && !(key->ct_state & OVS_CS_F_NAT_MASK) &&
(nf_ct_is_confirmed(ct) || info->commit) &&
ovs_ct_nat(net, key, info, skb, ct, ctinfo) != NF_ACCEPT) {
return -EINVAL;
diff --git a/net/openvswitch/conntrack.h b/net/openvswitch/conntrack.h
index 9e92445..bc7efd1 100644
--- a/net/openvswitch/conntrack.h
+++ b/net/openvswitch/conntrack.h
@@ -76,14 +76,14 @@
static inline void ovs_ct_fill_key(const struct sk_buff *skb,
struct sw_flow_key *key)
{
- key->ct.state = 0;
- key->ct.zone = 0;
+ key->ct_state = 0;
+ key->ct_zone = 0;
key->ct.mark = 0;
memset(&key->ct.labels, 0, sizeof(key->ct.labels));
- /* Clear 'ct.orig_proto' to mark the non-existence of original
+ /* Clear 'ct_orig_proto' to mark the non-existence of original
* direction key fields.
*/
- key->ct.orig_proto = 0;
+ key->ct_orig_proto = 0;
}
static inline int ovs_ct_put_key(const struct sw_flow_key *swkey,
diff --git a/net/openvswitch/flow.h b/net/openvswitch/flow.h
index 76e05b2..a9bc1c8 100644
--- a/net/openvswitch/flow.h
+++ b/net/openvswitch/flow.h
@@ -85,6 +85,11 @@
struct vlan_head cvlan;
__be16 type; /* Ethernet frame type. */
} eth;
+ /* Filling a hole of two bytes. */
+ u8 ct_state;
+ u8 ct_orig_proto; /* CT original direction tuple IP
+ * protocol.
+ */
union {
struct {
__be32 top_lse; /* top label stack entry */
@@ -96,6 +101,7 @@
u8 frag; /* One of OVS_FRAG_TYPE_*. */
} ip;
};
+ u16 ct_zone; /* Conntrack zone. */
struct {
__be16 src; /* TCP/UDP/SCTP source port. */
__be16 dst; /* TCP/UDP/SCTP destination port. */
@@ -138,16 +144,12 @@
} ipv6;
};
struct {
- /* Connection tracking fields. */
- u8 state;
- u8 orig_proto; /* CT orig tuple IP protocol. */
- u16 zone;
- u32 mark;
+ /* Connection tracking fields not packed above. */
struct {
__be16 src; /* CT orig tuple tp src port. */
__be16 dst; /* CT orig tuple tp dst port. */
} orig_tp;
-
+ u32 mark;
struct ovs_key_ct_labels labels;
} ct;
diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index 989f38f..6f5fa50 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -1072,14 +1072,14 @@
return -EINVAL;
}
- SW_FLOW_KEY_PUT(match, ct.state, ct_state, is_mask);
+ SW_FLOW_KEY_PUT(match, ct_state, ct_state, is_mask);
*attrs &= ~(1ULL << OVS_KEY_ATTR_CT_STATE);
}
if (*attrs & (1 << OVS_KEY_ATTR_CT_ZONE) &&
ovs_ct_verify(net, OVS_KEY_ATTR_CT_ZONE)) {
u16 ct_zone = nla_get_u16(a[OVS_KEY_ATTR_CT_ZONE]);
- SW_FLOW_KEY_PUT(match, ct.zone, ct_zone, is_mask);
+ SW_FLOW_KEY_PUT(match, ct_zone, ct_zone, is_mask);
*attrs &= ~(1ULL << OVS_KEY_ATTR_CT_ZONE);
}
if (*attrs & (1 << OVS_KEY_ATTR_CT_MARK) &&
@@ -1107,7 +1107,7 @@
SW_FLOW_KEY_PUT(match, ipv4.ct_orig.dst, ct->ipv4_dst, is_mask);
SW_FLOW_KEY_PUT(match, ct.orig_tp.src, ct->src_port, is_mask);
SW_FLOW_KEY_PUT(match, ct.orig_tp.dst, ct->dst_port, is_mask);
- SW_FLOW_KEY_PUT(match, ct.orig_proto, ct->ipv4_proto, is_mask);
+ SW_FLOW_KEY_PUT(match, ct_orig_proto, ct->ipv4_proto, is_mask);
*attrs &= ~(1ULL << OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV4);
}
if (*attrs & (1ULL << OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6)) {
@@ -1123,7 +1123,7 @@
is_mask);
SW_FLOW_KEY_PUT(match, ct.orig_tp.src, ct->src_port, is_mask);
SW_FLOW_KEY_PUT(match, ct.orig_tp.dst, ct->dst_port, is_mask);
- SW_FLOW_KEY_PUT(match, ct.orig_proto, ct->ipv6_proto, is_mask);
+ SW_FLOW_KEY_PUT(match, ct_orig_proto, ct->ipv6_proto, is_mask);
*attrs &= ~(1ULL << OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6);
}
@@ -1564,6 +1564,9 @@
memset(&match, 0, sizeof(match));
match.key = key;
+ key->ct_state = 0;
+ key->ct_zone = 0;
+ key->ct_orig_proto = 0;
memset(&key->ct, 0, sizeof(key->ct));
memset(&key->ipv4.ct_orig, 0, sizeof(key->ipv4.ct_orig));
memset(&key->ipv6.ct_orig, 0, sizeof(key->ipv6.ct_orig));