summaryrefslogtreecommitdiff
path: root/net/openvswitch
diff options
context:
space:
mode:
Diffstat (limited to 'net/openvswitch')
-rw-r--r--net/openvswitch/datapath.c18
-rw-r--r--net/openvswitch/datapath.h2
-rw-r--r--net/openvswitch/flow.c143
-rw-r--r--net/openvswitch/flow.h14
-rw-r--r--net/openvswitch/flow_netlink.c37
-rw-r--r--net/openvswitch/vport.c2
6 files changed, 201 insertions, 15 deletions
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index 67ad08320886..7e8a39a35627 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -37,6 +37,7 @@
#include <net/genetlink.h>
#include <net/net_namespace.h>
#include <net/netns/generic.h>
+#include <net/pkt_cls.h>
#include "datapath.h"
#include "flow.h"
@@ -1601,8 +1602,6 @@ static void ovs_dp_reset_user_features(struct sk_buff *skb,
dp->user_features = 0;
}
-DEFINE_STATIC_KEY_FALSE(tc_recirc_sharing_support);
-
static int ovs_dp_set_upcall_portids(struct datapath *dp,
const struct nlattr *ids)
{
@@ -1657,7 +1656,7 @@ u32 ovs_dp_get_upcall_portid(const struct datapath *dp, uint32_t cpu_id)
static int ovs_dp_change(struct datapath *dp, struct nlattr *a[])
{
- u32 user_features = 0;
+ u32 user_features = 0, old_features = dp->user_features;
int err;
if (a[OVS_DP_ATTR_USER_FEATURES]) {
@@ -1696,10 +1695,12 @@ static int ovs_dp_change(struct datapath *dp, struct nlattr *a[])
return err;
}
- if (dp->user_features & OVS_DP_F_TC_RECIRC_SHARING)
- static_branch_enable(&tc_recirc_sharing_support);
- else
- static_branch_disable(&tc_recirc_sharing_support);
+ if ((dp->user_features & OVS_DP_F_TC_RECIRC_SHARING) &&
+ !(old_features & OVS_DP_F_TC_RECIRC_SHARING))
+ tc_skb_ext_tc_enable();
+ else if (!(dp->user_features & OVS_DP_F_TC_RECIRC_SHARING) &&
+ (old_features & OVS_DP_F_TC_RECIRC_SHARING))
+ tc_skb_ext_tc_disable();
return 0;
}
@@ -1839,6 +1840,9 @@ static void __dp_destroy(struct datapath *dp)
struct flow_table *table = &dp->table;
int i;
+ if (dp->user_features & OVS_DP_F_TC_RECIRC_SHARING)
+ tc_skb_ext_tc_disable();
+
for (i = 0; i < DP_VPORT_HASH_BUCKETS; i++) {
struct vport *vport;
struct hlist_node *n;
diff --git a/net/openvswitch/datapath.h b/net/openvswitch/datapath.h
index fcfe6cb46441..0cd29971a907 100644
--- a/net/openvswitch/datapath.h
+++ b/net/openvswitch/datapath.h
@@ -253,8 +253,6 @@ static inline struct datapath *get_dp(struct net *net, int dp_ifindex)
extern struct notifier_block ovs_dp_device_notifier;
extern struct genl_family dp_vport_genl_family;
-DECLARE_STATIC_KEY_FALSE(tc_recirc_sharing_support);
-
void ovs_dp_process_packet(struct sk_buff *skb, struct sw_flow_key *key);
void ovs_dp_detach_port(struct vport *);
int ovs_dp_upcall(struct datapath *, struct sk_buff *,
diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c
index 02096f2ec678..372bf54a0ca9 100644
--- a/net/openvswitch/flow.c
+++ b/net/openvswitch/flow.c
@@ -34,6 +34,7 @@
#include <net/mpls.h>
#include <net/ndisc.h>
#include <net/nsh.h>
+#include <net/pkt_cls.h>
#include <net/netfilter/nf_conntrack_zones.h>
#include "conntrack.h"
@@ -240,6 +241,144 @@ static bool icmphdr_ok(struct sk_buff *skb)
sizeof(struct icmphdr));
}
+/**
+ * get_ipv6_ext_hdrs() - Parses packet and sets IPv6 extension header flags.
+ *
+ * @skb: buffer where extension header data starts in packet
+ * @nh: ipv6 header
+ * @ext_hdrs: flags are stored here
+ *
+ * OFPIEH12_UNREP is set if more than one of a given IPv6 extension header
+ * is unexpectedly encountered. (Two destination options headers may be
+ * expected and would not cause this bit to be set.)
+ *
+ * OFPIEH12_UNSEQ is set if IPv6 extension headers were not in the order
+ * preferred (but not required) by RFC 2460:
+ *
+ * When more than one extension header is used in the same packet, it is
+ * recommended that those headers appear in the following order:
+ * IPv6 header
+ * Hop-by-Hop Options header
+ * Destination Options header
+ * Routing header
+ * Fragment header
+ * Authentication header
+ * Encapsulating Security Payload header
+ * Destination Options header
+ * upper-layer header
+ */
+static void get_ipv6_ext_hdrs(struct sk_buff *skb, struct ipv6hdr *nh,
+ u16 *ext_hdrs)
+{
+ u8 next_type = nh->nexthdr;
+ unsigned int start = skb_network_offset(skb) + sizeof(struct ipv6hdr);
+ int dest_options_header_count = 0;
+
+ *ext_hdrs = 0;
+
+ while (ipv6_ext_hdr(next_type)) {
+ struct ipv6_opt_hdr _hdr, *hp;
+
+ switch (next_type) {
+ case IPPROTO_NONE:
+ *ext_hdrs |= OFPIEH12_NONEXT;
+ /* stop parsing */
+ return;
+
+ case IPPROTO_ESP:
+ if (*ext_hdrs & OFPIEH12_ESP)
+ *ext_hdrs |= OFPIEH12_UNREP;
+ if ((*ext_hdrs & ~(OFPIEH12_HOP | OFPIEH12_DEST |
+ OFPIEH12_ROUTER | IPPROTO_FRAGMENT |
+ OFPIEH12_AUTH | OFPIEH12_UNREP)) ||
+ dest_options_header_count >= 2) {
+ *ext_hdrs |= OFPIEH12_UNSEQ;
+ }
+ *ext_hdrs |= OFPIEH12_ESP;
+ break;
+
+ case IPPROTO_AH:
+ if (*ext_hdrs & OFPIEH12_AUTH)
+ *ext_hdrs |= OFPIEH12_UNREP;
+ if ((*ext_hdrs &
+ ~(OFPIEH12_HOP | OFPIEH12_DEST | OFPIEH12_ROUTER |
+ IPPROTO_FRAGMENT | OFPIEH12_UNREP)) ||
+ dest_options_header_count >= 2) {
+ *ext_hdrs |= OFPIEH12_UNSEQ;
+ }
+ *ext_hdrs |= OFPIEH12_AUTH;
+ break;
+
+ case IPPROTO_DSTOPTS:
+ if (dest_options_header_count == 0) {
+ if (*ext_hdrs &
+ ~(OFPIEH12_HOP | OFPIEH12_UNREP))
+ *ext_hdrs |= OFPIEH12_UNSEQ;
+ *ext_hdrs |= OFPIEH12_DEST;
+ } else if (dest_options_header_count == 1) {
+ if (*ext_hdrs &
+ ~(OFPIEH12_HOP | OFPIEH12_DEST |
+ OFPIEH12_ROUTER | OFPIEH12_FRAG |
+ OFPIEH12_AUTH | OFPIEH12_ESP |
+ OFPIEH12_UNREP)) {
+ *ext_hdrs |= OFPIEH12_UNSEQ;
+ }
+ } else {
+ *ext_hdrs |= OFPIEH12_UNREP;
+ }
+ dest_options_header_count++;
+ break;
+
+ case IPPROTO_FRAGMENT:
+ if (*ext_hdrs & OFPIEH12_FRAG)
+ *ext_hdrs |= OFPIEH12_UNREP;
+ if ((*ext_hdrs & ~(OFPIEH12_HOP |
+ OFPIEH12_DEST |
+ OFPIEH12_ROUTER |
+ OFPIEH12_UNREP)) ||
+ dest_options_header_count >= 2) {
+ *ext_hdrs |= OFPIEH12_UNSEQ;
+ }
+ *ext_hdrs |= OFPIEH12_FRAG;
+ break;
+
+ case IPPROTO_ROUTING:
+ if (*ext_hdrs & OFPIEH12_ROUTER)
+ *ext_hdrs |= OFPIEH12_UNREP;
+ if ((*ext_hdrs & ~(OFPIEH12_HOP |
+ OFPIEH12_DEST |
+ OFPIEH12_UNREP)) ||
+ dest_options_header_count >= 2) {
+ *ext_hdrs |= OFPIEH12_UNSEQ;
+ }
+ *ext_hdrs |= OFPIEH12_ROUTER;
+ break;
+
+ case IPPROTO_HOPOPTS:
+ if (*ext_hdrs & OFPIEH12_HOP)
+ *ext_hdrs |= OFPIEH12_UNREP;
+ /* OFPIEH12_HOP is set to 1 if a hop-by-hop IPv6
+ * extension header is present as the first
+ * extension header in the packet.
+ */
+ if (*ext_hdrs == 0)
+ *ext_hdrs |= OFPIEH12_HOP;
+ else
+ *ext_hdrs |= OFPIEH12_UNSEQ;
+ break;
+
+ default:
+ return;
+ }
+
+ hp = skb_header_pointer(skb, start, sizeof(_hdr), &_hdr);
+ if (!hp)
+ break;
+ next_type = hp->nexthdr;
+ start += ipv6_optlen(hp);
+ }
+}
+
static int parse_ipv6hdr(struct sk_buff *skb, struct sw_flow_key *key)
{
unsigned short frag_off;
@@ -255,6 +394,8 @@ static int parse_ipv6hdr(struct sk_buff *skb, struct sw_flow_key *key)
nh = ipv6_hdr(skb);
+ get_ipv6_ext_hdrs(skb, nh, &key->ipv6.exthdrs);
+
key->ip.proto = NEXTHDR_NONE;
key->ip.tos = ipv6_get_dsfield(nh);
key->ip.ttl = nh->hop_limit;
@@ -895,7 +1036,7 @@ int ovs_flow_key_extract(const struct ip_tunnel_info *tun_info,
key->mac_proto = res;
#if IS_ENABLED(CONFIG_NET_TC_SKB_EXT)
- if (static_branch_unlikely(&tc_recirc_sharing_support)) {
+ if (tc_skb_ext_tc_enabled()) {
tc_ext = skb_ext_find(skb, TC_SKB_EXT);
key->recirc_id = tc_ext ? tc_ext->chain : 0;
OVS_CB(skb)->mru = tc_ext ? tc_ext->mru : 0;
diff --git a/net/openvswitch/flow.h b/net/openvswitch/flow.h
index 758a8c77f736..073ab73ffeaa 100644
--- a/net/openvswitch/flow.h
+++ b/net/openvswitch/flow.h
@@ -32,6 +32,19 @@ enum sw_flow_mac_proto {
#define SW_FLOW_KEY_INVALID 0x80
#define MPLS_LABEL_DEPTH 3
+/* Bit definitions for IPv6 Extension Header pseudo-field. */
+enum ofp12_ipv6exthdr_flags {
+ OFPIEH12_NONEXT = 1 << 0, /* "No next header" encountered. */
+ OFPIEH12_ESP = 1 << 1, /* Encrypted Sec Payload header present. */
+ OFPIEH12_AUTH = 1 << 2, /* Authentication header present. */
+ OFPIEH12_DEST = 1 << 3, /* 1 or 2 dest headers present. */
+ OFPIEH12_FRAG = 1 << 4, /* Fragment header present. */
+ OFPIEH12_ROUTER = 1 << 5, /* Router header present. */
+ OFPIEH12_HOP = 1 << 6, /* Hop-by-hop header present. */
+ OFPIEH12_UNREP = 1 << 7, /* Unexpected repeats encountered. */
+ OFPIEH12_UNSEQ = 1 << 8 /* Unexpected sequencing encountered. */
+};
+
/* Store options at the end of the array if they are less than the
* maximum size. This allows us to get the benefits of variable length
* matching for small options.
@@ -121,6 +134,7 @@ struct sw_flow_key {
struct in6_addr dst; /* IPv6 destination address. */
} addr;
__be32 label; /* IPv6 flow label. */
+ u16 exthdrs; /* IPv6 extension header flags */
union {
struct {
struct in6_addr src;
diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index fd1f809e9bc1..5176f6ccac8e 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -346,7 +346,7 @@ size_t ovs_key_attr_size(void)
/* Whenever adding new OVS_KEY_ FIELDS, we should consider
* updating this function.
*/
- BUILD_BUG_ON(OVS_KEY_ATTR_TUNNEL_INFO != 29);
+ BUILD_BUG_ON(OVS_KEY_ATTR_MAX != 32);
return nla_total_size(4) /* OVS_KEY_ATTR_PRIORITY */
+ nla_total_size(0) /* OVS_KEY_ATTR_TUNNEL */
@@ -369,7 +369,8 @@ size_t ovs_key_attr_size(void)
+ nla_total_size(2) /* OVS_KEY_ATTR_ETHERTYPE */
+ nla_total_size(40) /* OVS_KEY_ATTR_IPV6 */
+ nla_total_size(2) /* OVS_KEY_ATTR_ICMPV6 */
- + nla_total_size(28); /* OVS_KEY_ATTR_ND */
+ + nla_total_size(28) /* OVS_KEY_ATTR_ND */
+ + nla_total_size(2); /* OVS_KEY_ATTR_IPV6_EXTHDRS */
}
static const struct ovs_len_tbl ovs_vxlan_ext_key_lens[OVS_VXLAN_EXT_MAX + 1] = {
@@ -437,6 +438,8 @@ static const struct ovs_len_tbl ovs_key_lens[OVS_KEY_ATTR_MAX + 1] = {
.len = sizeof(struct ovs_key_ct_tuple_ipv6) },
[OVS_KEY_ATTR_NSH] = { .len = OVS_ATTR_NESTED,
.next = ovs_nsh_key_attr_lens, },
+ [OVS_KEY_ATTR_IPV6_EXTHDRS] = {
+ .len = sizeof(struct ovs_key_ipv6_exthdrs) },
};
static bool check_attr_len(unsigned int attr_len, unsigned int expected_len)
@@ -479,7 +482,14 @@ static int __parse_flow_nlattrs(const struct nlattr *attr,
return -EINVAL;
}
- if (attrs & (1 << type)) {
+ if (type == OVS_KEY_ATTR_PACKET_TYPE ||
+ type == OVS_KEY_ATTR_ND_EXTENSIONS ||
+ type == OVS_KEY_ATTR_TUNNEL_INFO) {
+ OVS_NLERR(log, "Key type %d is not supported", type);
+ return -EINVAL;
+ }
+
+ if (attrs & (1ULL << type)) {
OVS_NLERR(log, "Duplicate key (type %d).", type);
return -EINVAL;
}
@@ -492,7 +502,7 @@ static int __parse_flow_nlattrs(const struct nlattr *attr,
}
if (!nz || !is_all_zero(nla_data(nla), nla_len(nla))) {
- attrs |= 1 << type;
+ attrs |= 1ULL << type;
a[type] = nla;
}
}
@@ -1597,6 +1607,17 @@ static int ovs_key_from_nlattrs(struct net *net, struct sw_flow_match *match,
attrs &= ~(1 << OVS_KEY_ATTR_IPV6);
}
+ if (attrs & (1ULL << OVS_KEY_ATTR_IPV6_EXTHDRS)) {
+ const struct ovs_key_ipv6_exthdrs *ipv6_exthdrs_key;
+
+ ipv6_exthdrs_key = nla_data(a[OVS_KEY_ATTR_IPV6_EXTHDRS]);
+
+ SW_FLOW_KEY_PUT(match, ipv6.exthdrs,
+ ipv6_exthdrs_key->hdrs, is_mask);
+
+ attrs &= ~(1ULL << OVS_KEY_ATTR_IPV6_EXTHDRS);
+ }
+
if (attrs & (1 << OVS_KEY_ATTR_ARP)) {
const struct ovs_key_arp *arp_key;
@@ -2099,6 +2120,7 @@ static int __ovs_nla_put_key(const struct sw_flow_key *swkey,
ipv4_key->ipv4_frag = output->ip.frag;
} else if (swkey->eth.type == htons(ETH_P_IPV6)) {
struct ovs_key_ipv6 *ipv6_key;
+ struct ovs_key_ipv6_exthdrs *ipv6_exthdrs_key;
nla = nla_reserve(skb, OVS_KEY_ATTR_IPV6, sizeof(*ipv6_key));
if (!nla)
@@ -2113,6 +2135,13 @@ static int __ovs_nla_put_key(const struct sw_flow_key *swkey,
ipv6_key->ipv6_tclass = output->ip.tos;
ipv6_key->ipv6_hlimit = output->ip.ttl;
ipv6_key->ipv6_frag = output->ip.frag;
+
+ nla = nla_reserve(skb, OVS_KEY_ATTR_IPV6_EXTHDRS,
+ sizeof(*ipv6_exthdrs_key));
+ if (!nla)
+ goto nla_put_failure;
+ ipv6_exthdrs_key = nla_data(nla);
+ ipv6_exthdrs_key->hdrs = output->ipv6.exthdrs;
} else if (swkey->eth.type == htons(ETH_P_NSH)) {
if (nsh_key_to_nlattr(&output->nsh, is_mask, skb))
goto nla_put_failure;
diff --git a/net/openvswitch/vport.c b/net/openvswitch/vport.c
index cf2ce5812489..82a74f998966 100644
--- a/net/openvswitch/vport.c
+++ b/net/openvswitch/vport.c
@@ -507,7 +507,7 @@ void ovs_vport_send(struct vport *vport, struct sk_buff *skb, u8 mac_proto)
}
skb->dev = vport->dev;
- skb->tstamp = 0;
+ skb_clear_tstamp(skb);
vport->ops->send(skb);
return;
generated by cgit (git 2.34.1) at 2024-05-27 21:38:45 +0000