/*
- * Copyright (c) 2007-2015 Nicira, Inc.
+ * Copyright (c) 2007-2017 Nicira, Inc.
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of version 2 of the GNU General Public
#include <net/ndisc.h>
#include <net/mpls.h>
#include <net/vxlan.h>
+#include <net/tun_proto.h>
+#include <net/erspan.h>
#include "datapath.h"
#include "conntrack.h"
#define OVS_ATTR_NESTED -1
#define OVS_ATTR_VARIABLE -2
+static bool actions_may_change_flow(const struct nlattr *actions)
+{
+ struct nlattr *nla;
+ int rem;
+
+ nla_for_each_nested(nla, actions, rem) {
+ u16 action = nla_type(nla);
+
+ switch (action) {
+ case OVS_ACTION_ATTR_OUTPUT:
+ case OVS_ACTION_ATTR_RECIRC:
+ case OVS_ACTION_ATTR_TRUNC:
+ case OVS_ACTION_ATTR_USERSPACE:
+ break;
+
+ case OVS_ACTION_ATTR_CT:
+ case OVS_ACTION_ATTR_CT_CLEAR:
+ case OVS_ACTION_ATTR_HASH:
+ case OVS_ACTION_ATTR_POP_ETH:
+ case OVS_ACTION_ATTR_POP_MPLS:
+ case OVS_ACTION_ATTR_POP_NSH:
+ case OVS_ACTION_ATTR_POP_VLAN:
+ case OVS_ACTION_ATTR_PUSH_ETH:
+ case OVS_ACTION_ATTR_PUSH_MPLS:
+ case OVS_ACTION_ATTR_PUSH_NSH:
+ case OVS_ACTION_ATTR_PUSH_VLAN:
+ case OVS_ACTION_ATTR_SAMPLE:
+ case OVS_ACTION_ATTR_SET:
+ case OVS_ACTION_ATTR_SET_MASKED:
+ case OVS_ACTION_ATTR_METER:
+ case OVS_ACTION_ATTR_CHECK_PKT_LEN:
+ default:
+ return true;
+ }
+ }
+ return false;
+}
+
static void update_range(struct sw_flow_match *match,
size_t offset, size_t size, bool is_mask)
{
static bool match_validate(const struct sw_flow_match *match,
u64 key_attrs, u64 mask_attrs, bool log)
{
- u64 key_expected = 1ULL << OVS_KEY_ATTR_ETHERNET;
+ u64 key_expected = 0;
u64 mask_allowed = key_attrs; /* At most allow all key attributes */
/* The following mask attributes allowed only if they
* pass the validation tests.
*/
mask_allowed &= ~((1ULL << OVS_KEY_ATTR_IPV4)
+ | (1ULL << OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV4)
| (1ULL << OVS_KEY_ATTR_IPV6)
+ | (1ULL << OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6)
| (1ULL << OVS_KEY_ATTR_TCP)
| (1ULL << OVS_KEY_ATTR_TCP_FLAGS)
| (1ULL << OVS_KEY_ATTR_UDP)
| (1ULL << OVS_KEY_ATTR_ICMPV6)
| (1ULL << OVS_KEY_ATTR_ARP)
| (1ULL << OVS_KEY_ATTR_ND)
- | (1ULL << OVS_KEY_ATTR_MPLS));
+ | (1ULL << OVS_KEY_ATTR_MPLS)
+ | (1ULL << OVS_KEY_ATTR_NSH));
/* Always allowed mask fields. */
mask_allowed |= ((1ULL << OVS_KEY_ATTR_TUNNEL)
if (match->key->eth.type == htons(ETH_P_IP)) {
key_expected |= 1ULL << OVS_KEY_ATTR_IPV4;
- if (match->mask && (match->mask->key.eth.type == htons(0xffff)))
+ if (match->mask && match->mask->key.eth.type == htons(0xffff)) {
mask_allowed |= 1ULL << OVS_KEY_ATTR_IPV4;
+ mask_allowed |= 1ULL << OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV4;
+ }
if (match->key->ip.frag != OVS_FRAG_TYPE_LATER) {
if (match->key->ip.proto == IPPROTO_UDP) {
if (match->key->eth.type == htons(ETH_P_IPV6)) {
key_expected |= 1ULL << OVS_KEY_ATTR_IPV6;
- if (match->mask && (match->mask->key.eth.type == htons(0xffff)))
+ if (match->mask && match->mask->key.eth.type == htons(0xffff)) {
mask_allowed |= 1ULL << OVS_KEY_ATTR_IPV6;
+ mask_allowed |= 1ULL << OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6;
+ }
if (match->key->ip.frag != OVS_FRAG_TYPE_LATER) {
if (match->key->ip.proto == IPPROTO_UDP) {
htons(NDISC_NEIGHBOUR_SOLICITATION) ||
match->key->tp.src == htons(NDISC_NEIGHBOUR_ADVERTISEMENT)) {
key_expected |= 1ULL << OVS_KEY_ATTR_ND;
+ /* Original direction conntrack tuple
+ * uses the same space as the ND fields
+ * in the key, so both are not allowed
+ * at the same time.
+ */
+ mask_allowed &= ~(1ULL << OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6);
if (match->mask && (match->mask->key.tp.src == htons(0xff)))
mask_allowed |= 1ULL << OVS_KEY_ATTR_ND;
}
}
}
+ if (match->key->eth.type == htons(ETH_P_NSH)) {
+ key_expected |= 1 << OVS_KEY_ATTR_NSH;
+ if (match->mask &&
+ match->mask->key.eth.type == htons(0xffff)) {
+ mask_allowed |= 1 << OVS_KEY_ATTR_NSH;
+ }
+ }
+
if ((key_attrs & key_expected) != key_expected) {
/* Key attributes check failed. */
OVS_NLERR(log, "Missing key (keys=%llx, expected=%llx)",
/* Whenever adding new OVS_TUNNEL_KEY_ FIELDS, we should consider
* updating this function.
*/
- return nla_total_size(8) /* OVS_TUNNEL_KEY_ATTR_ID */
- + nla_total_size(4) /* OVS_TUNNEL_KEY_ATTR_IPV4_SRC */
- + nla_total_size(4) /* OVS_TUNNEL_KEY_ATTR_IPV4_DST */
+ return nla_total_size_64bit(8) /* OVS_TUNNEL_KEY_ATTR_ID */
+ + nla_total_size(16) /* OVS_TUNNEL_KEY_ATTR_IPV[46]_SRC */
+ + nla_total_size(16) /* OVS_TUNNEL_KEY_ATTR_IPV[46]_DST */
+ nla_total_size(1) /* OVS_TUNNEL_KEY_ATTR_TOS */
+ nla_total_size(1) /* OVS_TUNNEL_KEY_ATTR_TTL */
+ nla_total_size(0) /* OVS_TUNNEL_KEY_ATTR_DONT_FRAGMENT */
+ nla_total_size(0) /* OVS_TUNNEL_KEY_ATTR_CSUM */
+ nla_total_size(0) /* OVS_TUNNEL_KEY_ATTR_OAM */
+ nla_total_size(256) /* OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS */
- /* OVS_TUNNEL_KEY_ATTR_VXLAN_OPTS is mutually exclusive with
+ /* OVS_TUNNEL_KEY_ATTR_VXLAN_OPTS and
+ * OVS_TUNNEL_KEY_ATTR_ERSPAN_OPTS is mutually exclusive with
* OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS and covered by it.
*/
+ nla_total_size(2) /* OVS_TUNNEL_KEY_ATTR_TP_SRC */
+ nla_total_size(2); /* OVS_TUNNEL_KEY_ATTR_TP_DST */
}
+static size_t ovs_nsh_key_attr_size(void)
+{
+ /* Whenever adding new OVS_NSH_KEY_ FIELDS, we should consider
+ * updating this function.
+ */
+ return nla_total_size(NSH_BASE_HDR_LEN) /* OVS_NSH_KEY_ATTR_BASE */
+ /* OVS_NSH_KEY_ATTR_MD1 and OVS_NSH_KEY_ATTR_MD2 are
+ * mutually exclusive, so the bigger one can cover
+ * the small one.
+ */
+ + nla_total_size(NSH_CTX_HDRS_MAX_LEN);
+}
+
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 != 26);
+ BUILD_BUG_ON(OVS_KEY_ATTR_TUNNEL_INFO != 29);
return nla_total_size(4) /* OVS_KEY_ATTR_PRIORITY */
+ nla_total_size(0) /* OVS_KEY_ATTR_TUNNEL */
+ nla_total_size(4) /* OVS_KEY_ATTR_SKB_MARK */
+ nla_total_size(4) /* OVS_KEY_ATTR_DP_HASH */
+ nla_total_size(4) /* OVS_KEY_ATTR_RECIRC_ID */
- + nla_total_size(1) /* OVS_KEY_ATTR_CT_STATE */
+ + nla_total_size(4) /* OVS_KEY_ATTR_CT_STATE */
+ nla_total_size(2) /* OVS_KEY_ATTR_CT_ZONE */
+ nla_total_size(4) /* OVS_KEY_ATTR_CT_MARK */
- + nla_total_size(16) /* OVS_KEY_ATTR_CT_LABEL */
+ + nla_total_size(16) /* OVS_KEY_ATTR_CT_LABELS */
+ + nla_total_size(40) /* OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6 */
+ + nla_total_size(0) /* OVS_KEY_ATTR_NSH */
+ + ovs_nsh_key_attr_size()
+ nla_total_size(12) /* OVS_KEY_ATTR_ETHERNET */
+ nla_total_size(2) /* OVS_KEY_ATTR_ETHERTYPE */
+ nla_total_size(4) /* OVS_KEY_ATTR_VLAN */
[OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS] = { .len = OVS_ATTR_VARIABLE },
[OVS_TUNNEL_KEY_ATTR_VXLAN_OPTS] = { .len = OVS_ATTR_NESTED,
.next = ovs_vxlan_ext_key_lens },
+ [OVS_TUNNEL_KEY_ATTR_IPV6_SRC] = { .len = sizeof(struct in6_addr) },
+ [OVS_TUNNEL_KEY_ATTR_IPV6_DST] = { .len = sizeof(struct in6_addr) },
+ [OVS_TUNNEL_KEY_ATTR_ERSPAN_OPTS] = { .len = OVS_ATTR_VARIABLE },
+};
+
+static const struct ovs_len_tbl
+ovs_nsh_key_attr_lens[OVS_NSH_KEY_ATTR_MAX + 1] = {
+ [OVS_NSH_KEY_ATTR_BASE] = { .len = sizeof(struct ovs_nsh_key_base) },
+ [OVS_NSH_KEY_ATTR_MD1] = { .len = sizeof(struct ovs_nsh_key_md1) },
+ [OVS_NSH_KEY_ATTR_MD2] = { .len = OVS_ATTR_VARIABLE },
};
/* The size of the argument for each %OVS_KEY_ATTR_* Netlink attribute. */
[OVS_KEY_ATTR_TUNNEL] = { .len = OVS_ATTR_NESTED,
.next = ovs_tunnel_key_lens, },
[OVS_KEY_ATTR_MPLS] = { .len = sizeof(struct ovs_key_mpls) },
- [OVS_KEY_ATTR_CT_STATE] = { .len = sizeof(u8) },
+ [OVS_KEY_ATTR_CT_STATE] = { .len = sizeof(u32) },
[OVS_KEY_ATTR_CT_ZONE] = { .len = sizeof(u16) },
[OVS_KEY_ATTR_CT_MARK] = { .len = sizeof(u32) },
- [OVS_KEY_ATTR_CT_LABEL] = { .len = sizeof(struct ovs_key_ct_label) },
+ [OVS_KEY_ATTR_CT_LABELS] = { .len = sizeof(struct ovs_key_ct_labels) },
+ [OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV4] = {
+ .len = sizeof(struct ovs_key_ct_tuple_ipv4) },
+ [OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6] = {
+ .len = sizeof(struct ovs_key_ct_tuple_ipv6) },
+ [OVS_KEY_ATTR_NSH] = { .len = OVS_ATTR_NESTED,
+ .next = ovs_nsh_key_attr_lens, },
};
static bool check_attr_len(unsigned int attr_len, unsigned int expected_len)
return -EINVAL;
}
- if (!nz || !is_all_zero(nla_data(nla), expected_len)) {
+ if (!nz || !is_all_zero(nla_data(nla), nla_len(nla))) {
attrs |= 1ULL << type;
a[type] = nla;
}
return __parse_flow_nlattrs(attr, a, attrsp, log, true);
}
-static int parse_flow_nlattrs(const struct nlattr *attr,
- const struct nlattr *a[], u64 *attrsp,
- bool log)
+int parse_flow_nlattrs(const struct nlattr *attr, const struct nlattr *a[],
+ u64 *attrsp, bool log)
{
return __parse_flow_nlattrs(attr, a, attrsp, log, false);
}
return 0;
}
-static int ipv4_tun_from_nlattr(const struct nlattr *attr,
- struct sw_flow_match *match, bool is_mask,
- bool log)
+static int erspan_tun_opt_from_nlattr(const struct nlattr *a,
+ struct sw_flow_match *match, bool is_mask,
+ bool log)
{
- struct nlattr *a;
- int rem;
- bool ttl = false;
+ unsigned long opt_key_offset;
+
+ BUILD_BUG_ON(sizeof(struct erspan_metadata) >
+ sizeof(match->key->tun_opts));
+
+ if (nla_len(a) > sizeof(match->key->tun_opts)) {
+ OVS_NLERR(log, "ERSPAN option length err (len %d, max %zu).",
+ nla_len(a), sizeof(match->key->tun_opts));
+ return -EINVAL;
+ }
+
+ if (!is_mask)
+ SW_FLOW_KEY_PUT(match, tun_opts_len,
+ sizeof(struct erspan_metadata), false);
+ else
+ SW_FLOW_KEY_PUT(match, tun_opts_len, 0xff, true);
+
+ opt_key_offset = TUN_METADATA_OFFSET(nla_len(a));
+ SW_FLOW_KEY_MEMCPY_OFFSET(match, opt_key_offset, nla_data(a),
+ nla_len(a), is_mask);
+ return 0;
+}
+
+static int ip_tun_from_nlattr(const struct nlattr *attr,
+ struct sw_flow_match *match, bool is_mask,
+ bool log)
+{
+ bool ttl = false, ipv4 = false, ipv6 = false;
__be16 tun_flags = 0;
int opts_type = 0;
+ struct nlattr *a;
+ int rem;
nla_for_each_nested(a, attr, rem) {
int type = nla_type(a);
case OVS_TUNNEL_KEY_ATTR_IPV4_SRC:
SW_FLOW_KEY_PUT(match, tun_key.u.ipv4.src,
nla_get_in_addr(a), is_mask);
+ ipv4 = true;
break;
case OVS_TUNNEL_KEY_ATTR_IPV4_DST:
SW_FLOW_KEY_PUT(match, tun_key.u.ipv4.dst,
nla_get_in_addr(a), is_mask);
+ ipv4 = true;
+ break;
+ case OVS_TUNNEL_KEY_ATTR_IPV6_SRC:
+ SW_FLOW_KEY_PUT(match, tun_key.u.ipv6.src,
+ nla_get_in6_addr(a), is_mask);
+ ipv6 = true;
+ break;
+ case OVS_TUNNEL_KEY_ATTR_IPV6_DST:
+ SW_FLOW_KEY_PUT(match, tun_key.u.ipv6.dst,
+ nla_get_in6_addr(a), is_mask);
+ ipv6 = true;
break;
case OVS_TUNNEL_KEY_ATTR_TOS:
SW_FLOW_KEY_PUT(match, tun_key.tos,
tun_flags |= TUNNEL_VXLAN_OPT;
opts_type = type;
break;
+ case OVS_TUNNEL_KEY_ATTR_PAD:
+ break;
+ case OVS_TUNNEL_KEY_ATTR_ERSPAN_OPTS:
+ if (opts_type) {
+ OVS_NLERR(log, "Multiple metadata blocks provided");
+ return -EINVAL;
+ }
+
+ err = erspan_tun_opt_from_nlattr(a, match, is_mask,
+ log);
+ if (err)
+ return err;
+
+ tun_flags |= TUNNEL_ERSPAN_OPT;
+ opts_type = type;
+ break;
default:
- OVS_NLERR(log, "Unknown IPv4 tunnel attribute %d",
+ OVS_NLERR(log, "Unknown IP tunnel attribute %d",
type);
return -EINVAL;
}
}
SW_FLOW_KEY_PUT(match, tun_key.tun_flags, tun_flags, is_mask);
+ if (is_mask)
+ SW_FLOW_KEY_MEMSET_FIELD(match, tun_proto, 0xff, true);
+ else
+ SW_FLOW_KEY_PUT(match, tun_proto, ipv6 ? AF_INET6 : AF_INET,
+ false);
if (rem > 0) {
- OVS_NLERR(log, "IPv4 tunnel attribute has %d unknown bytes.",
+ OVS_NLERR(log, "IP tunnel attribute has %d unknown bytes.",
rem);
return -EINVAL;
}
+ if (ipv4 && ipv6) {
+ OVS_NLERR(log, "Mixed IPv4 and IPv6 tunnel attributes");
+ return -EINVAL;
+ }
+
if (!is_mask) {
- if (!match->key->tun_key.u.ipv4.dst) {
+ if (!ipv4 && !ipv6) {
+ OVS_NLERR(log, "IP tunnel dst address not specified");
+ return -EINVAL;
+ }
+ if (ipv4 && !match->key->tun_key.u.ipv4.dst) {
OVS_NLERR(log, "IPv4 tunnel dst address is zero");
return -EINVAL;
}
+ if (ipv6 && ipv6_addr_any(&match->key->tun_key.u.ipv6.dst)) {
+ OVS_NLERR(log, "IPv6 tunnel dst address is zero");
+ return -EINVAL;
+ }
if (!ttl) {
- OVS_NLERR(log, "IPv4 tunnel TTL not specified.");
+ OVS_NLERR(log, "IP tunnel TTL not specified.");
return -EINVAL;
}
}
return 0;
}
-static int __ipv4_tun_to_nlattr(struct sk_buff *skb,
- const struct ip_tunnel_key *output,
- const void *tun_opts, int swkey_tun_opts_len)
+static int __ip_tun_to_nlattr(struct sk_buff *skb,
+ const struct ip_tunnel_key *output,
+ const void *tun_opts, int swkey_tun_opts_len,
+ unsigned short tun_proto)
{
if (output->tun_flags & TUNNEL_KEY &&
- nla_put_be64(skb, OVS_TUNNEL_KEY_ATTR_ID, output->tun_id))
- return -EMSGSIZE;
- if (output->u.ipv4.src &&
- nla_put_in_addr(skb, OVS_TUNNEL_KEY_ATTR_IPV4_SRC,
- output->u.ipv4.src))
- return -EMSGSIZE;
- if (output->u.ipv4.dst &&
- nla_put_in_addr(skb, OVS_TUNNEL_KEY_ATTR_IPV4_DST,
- output->u.ipv4.dst))
+ nla_put_be64(skb, OVS_TUNNEL_KEY_ATTR_ID, output->tun_id,
+ OVS_TUNNEL_KEY_ATTR_PAD))
return -EMSGSIZE;
+ switch (tun_proto) {
+ case AF_INET:
+ if (output->u.ipv4.src &&
+ nla_put_in_addr(skb, OVS_TUNNEL_KEY_ATTR_IPV4_SRC,
+ output->u.ipv4.src))
+ return -EMSGSIZE;
+ if (output->u.ipv4.dst &&
+ nla_put_in_addr(skb, OVS_TUNNEL_KEY_ATTR_IPV4_DST,
+ output->u.ipv4.dst))
+ return -EMSGSIZE;
+ break;
+ case AF_INET6:
+ if (!ipv6_addr_any(&output->u.ipv6.src) &&
+ nla_put_in6_addr(skb, OVS_TUNNEL_KEY_ATTR_IPV6_SRC,
+ &output->u.ipv6.src))
+ return -EMSGSIZE;
+ if (!ipv6_addr_any(&output->u.ipv6.dst) &&
+ nla_put_in6_addr(skb, OVS_TUNNEL_KEY_ATTR_IPV6_DST,
+ &output->u.ipv6.dst))
+ return -EMSGSIZE;
+ break;
+ }
if (output->tos &&
nla_put_u8(skb, OVS_TUNNEL_KEY_ATTR_TOS, output->tos))
return -EMSGSIZE;
if ((output->tun_flags & TUNNEL_OAM) &&
nla_put_flag(skb, OVS_TUNNEL_KEY_ATTR_OAM))
return -EMSGSIZE;
- if (tun_opts) {
+ if (swkey_tun_opts_len) {
if (output->tun_flags & TUNNEL_GENEVE_OPT &&
nla_put(skb, OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS,
swkey_tun_opts_len, tun_opts))
else if (output->tun_flags & TUNNEL_VXLAN_OPT &&
vxlan_opt_to_nlattr(skb, tun_opts, swkey_tun_opts_len))
return -EMSGSIZE;
+ else if (output->tun_flags & TUNNEL_ERSPAN_OPT &&
+ nla_put(skb, OVS_TUNNEL_KEY_ATTR_ERSPAN_OPTS,
+ swkey_tun_opts_len, tun_opts))
+ return -EMSGSIZE;
}
return 0;
}
-static int ipv4_tun_to_nlattr(struct sk_buff *skb,
- const struct ip_tunnel_key *output,
- const void *tun_opts, int swkey_tun_opts_len)
+static int ip_tun_to_nlattr(struct sk_buff *skb,
+ const struct ip_tunnel_key *output,
+ const void *tun_opts, int swkey_tun_opts_len,
+ unsigned short tun_proto)
{
struct nlattr *nla;
int err;
if (!nla)
return -EMSGSIZE;
- err = __ipv4_tun_to_nlattr(skb, output, tun_opts, swkey_tun_opts_len);
+ err = __ip_tun_to_nlattr(skb, output, tun_opts, swkey_tun_opts_len,
+ tun_proto);
if (err)
return err;
return 0;
}
-int ovs_nla_put_egress_tunnel_key(struct sk_buff *skb,
- const struct ip_tunnel_info *egress_tun_info,
- const void *egress_tun_opts)
+int ovs_nla_put_tunnel_info(struct sk_buff *skb,
+ struct ip_tunnel_info *tun_info)
+{
+ return __ip_tun_to_nlattr(skb, &tun_info->key,
+ ip_tunnel_info_opts(tun_info),
+ tun_info->options_len,
+ ip_tunnel_info_af(tun_info));
+}
+
+static int encode_vlan_from_nlattrs(struct sw_flow_match *match,
+ const struct nlattr *a[],
+ bool is_mask, bool inner)
+{
+ __be16 tci = 0;
+ __be16 tpid = 0;
+
+ if (a[OVS_KEY_ATTR_VLAN])
+ tci = nla_get_be16(a[OVS_KEY_ATTR_VLAN]);
+
+ if (a[OVS_KEY_ATTR_ETHERTYPE])
+ tpid = nla_get_be16(a[OVS_KEY_ATTR_ETHERTYPE]);
+
+ if (likely(!inner)) {
+ SW_FLOW_KEY_PUT(match, eth.vlan.tpid, tpid, is_mask);
+ SW_FLOW_KEY_PUT(match, eth.vlan.tci, tci, is_mask);
+ } else {
+ SW_FLOW_KEY_PUT(match, eth.cvlan.tpid, tpid, is_mask);
+ SW_FLOW_KEY_PUT(match, eth.cvlan.tci, tci, is_mask);
+ }
+ return 0;
+}
+
+static int validate_vlan_from_nlattrs(const struct sw_flow_match *match,
+ u64 key_attrs, bool inner,
+ const struct nlattr **a, bool log)
+{
+ __be16 tci = 0;
+
+ if (!((key_attrs & (1 << OVS_KEY_ATTR_ETHERNET)) &&
+ (key_attrs & (1 << OVS_KEY_ATTR_ETHERTYPE)) &&
+ eth_type_vlan(nla_get_be16(a[OVS_KEY_ATTR_ETHERTYPE])))) {
+ /* Not a VLAN. */
+ return 0;
+ }
+
+ if (!((key_attrs & (1 << OVS_KEY_ATTR_VLAN)) &&
+ (key_attrs & (1 << OVS_KEY_ATTR_ENCAP)))) {
+ OVS_NLERR(log, "Invalid %s frame", (inner) ? "C-VLAN" : "VLAN");
+ return -EINVAL;
+ }
+
+ if (a[OVS_KEY_ATTR_VLAN])
+ tci = nla_get_be16(a[OVS_KEY_ATTR_VLAN]);
+
+ if (!(tci & htons(VLAN_TAG_PRESENT))) {
+ if (tci) {
+ OVS_NLERR(log, "%s TCI does not have VLAN_TAG_PRESENT bit set.",
+ (inner) ? "C-VLAN" : "VLAN");
+ return -EINVAL;
+ } else if (nla_len(a[OVS_KEY_ATTR_ENCAP])) {
+ /* Corner case for truncated VLAN header. */
+ OVS_NLERR(log, "Truncated %s header has non-zero encap attribute.",
+ (inner) ? "C-VLAN" : "VLAN");
+ return -EINVAL;
+ }
+ }
+
+ return 1;
+}
+
+static int validate_vlan_mask_from_nlattrs(const struct sw_flow_match *match,
+ u64 key_attrs, bool inner,
+ const struct nlattr **a, bool log)
+{
+ __be16 tci = 0;
+ __be16 tpid = 0;
+ bool encap_valid = !!(match->key->eth.vlan.tci &
+ htons(VLAN_TAG_PRESENT));
+ bool i_encap_valid = !!(match->key->eth.cvlan.tci &
+ htons(VLAN_TAG_PRESENT));
+
+ if (!(key_attrs & (1 << OVS_KEY_ATTR_ENCAP))) {
+ /* Not a VLAN. */
+ return 0;
+ }
+
+ if ((!inner && !encap_valid) || (inner && !i_encap_valid)) {
+ OVS_NLERR(log, "Encap mask attribute is set for non-%s frame.",
+ (inner) ? "C-VLAN" : "VLAN");
+ return -EINVAL;
+ }
+
+ if (a[OVS_KEY_ATTR_VLAN])
+ tci = nla_get_be16(a[OVS_KEY_ATTR_VLAN]);
+
+ if (a[OVS_KEY_ATTR_ETHERTYPE])
+ tpid = nla_get_be16(a[OVS_KEY_ATTR_ETHERTYPE]);
+
+ if (tpid != htons(0xffff)) {
+ OVS_NLERR(log, "Must have an exact match on %s TPID (mask=%x).",
+ (inner) ? "C-VLAN" : "VLAN", ntohs(tpid));
+ return -EINVAL;
+ }
+ if (!(tci & htons(VLAN_TAG_PRESENT))) {
+ OVS_NLERR(log, "%s TCI mask does not have exact match for VLAN_TAG_PRESENT bit.",
+ (inner) ? "C-VLAN" : "VLAN");
+ return -EINVAL;
+ }
+
+ return 1;
+}
+
+static int __parse_vlan_from_nlattrs(struct sw_flow_match *match,
+ u64 *key_attrs, bool inner,
+ const struct nlattr **a, bool is_mask,
+ bool log)
+{
+ int err;
+ const struct nlattr *encap;
+
+ if (!is_mask)
+ err = validate_vlan_from_nlattrs(match, *key_attrs, inner,
+ a, log);
+ else
+ err = validate_vlan_mask_from_nlattrs(match, *key_attrs, inner,
+ a, log);
+ if (err <= 0)
+ return err;
+
+ err = encode_vlan_from_nlattrs(match, a, is_mask, inner);
+ if (err)
+ return err;
+
+ *key_attrs &= ~(1 << OVS_KEY_ATTR_ENCAP);
+ *key_attrs &= ~(1 << OVS_KEY_ATTR_VLAN);
+ *key_attrs &= ~(1 << OVS_KEY_ATTR_ETHERTYPE);
+
+ encap = a[OVS_KEY_ATTR_ENCAP];
+
+ if (!is_mask)
+ err = parse_flow_nlattrs(encap, a, key_attrs, log);
+ else
+ err = parse_flow_mask_nlattrs(encap, a, key_attrs, log);
+
+ return err;
+}
+
+static int parse_vlan_from_nlattrs(struct sw_flow_match *match,
+ u64 *key_attrs, const struct nlattr **a,
+ bool is_mask, bool log)
+{
+ int err;
+ bool encap_valid = false;
+
+ err = __parse_vlan_from_nlattrs(match, key_attrs, false, a,
+ is_mask, log);
+ if (err)
+ return err;
+
+ encap_valid = !!(match->key->eth.vlan.tci & htons(VLAN_TAG_PRESENT));
+ if (encap_valid) {
+ err = __parse_vlan_from_nlattrs(match, key_attrs, true, a,
+ is_mask, log);
+ if (err)
+ return err;
+ }
+
+ return 0;
+}
+
+static int parse_eth_type_from_nlattrs(struct sw_flow_match *match,
+ u64 *attrs, const struct nlattr **a,
+ bool is_mask, bool log)
{
- return __ipv4_tun_to_nlattr(skb, &egress_tun_info->key,
- egress_tun_opts,
- egress_tun_info->options_len);
+ __be16 eth_type;
+
+ eth_type = nla_get_be16(a[OVS_KEY_ATTR_ETHERTYPE]);
+ if (is_mask) {
+ /* Always exact match EtherType. */
+ eth_type = htons(0xffff);
+ } else if (!eth_proto_is_802_3(eth_type)) {
+ OVS_NLERR(log, "EtherType %x is less than min %x",
+ ntohs(eth_type), ETH_P_802_3_MIN);
+ return -EINVAL;
+ }
+
+ SW_FLOW_KEY_PUT(match, eth.type, eth_type, is_mask);
+ *attrs &= ~(1 << OVS_KEY_ATTR_ETHERTYPE);
+ return 0;
}
static int metadata_from_nlattrs(struct net *net, struct sw_flow_match *match,
u64 *attrs, const struct nlattr **a,
bool is_mask, bool log)
{
+ u8 mac_proto = MAC_PROTO_ETHERNET;
+
if (*attrs & (1ULL << OVS_KEY_ATTR_DP_HASH)) {
u32 hash_val = nla_get_u32(a[OVS_KEY_ATTR_DP_HASH]);
*attrs &= ~(1ULL << OVS_KEY_ATTR_SKB_MARK);
}
if (*attrs & (1ULL << OVS_KEY_ATTR_TUNNEL)) {
- if (ipv4_tun_from_nlattr(a[OVS_KEY_ATTR_TUNNEL], match,
+ if (ip_tun_from_nlattr(a[OVS_KEY_ATTR_TUNNEL], match,
is_mask, log) < 0)
return -EINVAL;
*attrs &= ~(1ULL << OVS_KEY_ATTR_TUNNEL);
if (*attrs & (1 << OVS_KEY_ATTR_CT_STATE) &&
ovs_ct_verify(net, OVS_KEY_ATTR_CT_STATE)) {
- u8 ct_state = nla_get_u8(a[OVS_KEY_ATTR_CT_STATE]);
+ u32 ct_state = nla_get_u32(a[OVS_KEY_ATTR_CT_STATE]);
+
+ if (ct_state & ~CT_SUPPORTED_MASK) {
+ OVS_NLERR(log, "ct_state flags %08x unsupported",
+ ct_state);
+ 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) &&
SW_FLOW_KEY_PUT(match, ct.mark, mark, is_mask);
*attrs &= ~(1ULL << OVS_KEY_ATTR_CT_MARK);
}
- if (*attrs & (1 << OVS_KEY_ATTR_CT_LABEL) &&
- ovs_ct_verify(net, OVS_KEY_ATTR_CT_LABEL)) {
- const struct ovs_key_ct_label *cl;
+ if (*attrs & (1 << OVS_KEY_ATTR_CT_LABELS) &&
+ ovs_ct_verify(net, OVS_KEY_ATTR_CT_LABELS)) {
+ const struct ovs_key_ct_labels *cl;
- cl = nla_data(a[OVS_KEY_ATTR_CT_LABEL]);
- SW_FLOW_KEY_MEMCPY(match, ct.label, cl->ct_label,
+ cl = nla_data(a[OVS_KEY_ATTR_CT_LABELS]);
+ SW_FLOW_KEY_MEMCPY(match, ct.labels, cl->ct_labels,
sizeof(*cl), is_mask);
- *attrs &= ~(1ULL << OVS_KEY_ATTR_CT_LABEL);
+ *attrs &= ~(1ULL << OVS_KEY_ATTR_CT_LABELS);
+ }
+ if (*attrs & (1ULL << OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV4)) {
+ const struct ovs_key_ct_tuple_ipv4 *ct;
+
+ ct = nla_data(a[OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV4]);
+
+ SW_FLOW_KEY_PUT(match, ipv4.ct_orig.src, ct->ipv4_src, is_mask);
+ 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);
+ *attrs &= ~(1ULL << OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV4);
+ }
+ if (*attrs & (1ULL << OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6)) {
+ const struct ovs_key_ct_tuple_ipv6 *ct;
+
+ ct = nla_data(a[OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6]);
+
+ SW_FLOW_KEY_MEMCPY(match, ipv6.ct_orig.src, &ct->ipv6_src,
+ sizeof(match->key->ipv6.ct_orig.src),
+ is_mask);
+ SW_FLOW_KEY_MEMCPY(match, ipv6.ct_orig.dst, &ct->ipv6_dst,
+ sizeof(match->key->ipv6.ct_orig.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->ipv6_proto, is_mask);
+ *attrs &= ~(1ULL << OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6);
+ }
+
+ /* For layer 3 packets the Ethernet type is provided
+ * and treated as metadata but no MAC addresses are provided.
+ */
+ if (!(*attrs & (1ULL << OVS_KEY_ATTR_ETHERNET)) &&
+ (*attrs & (1ULL << OVS_KEY_ATTR_ETHERTYPE)))
+ mac_proto = MAC_PROTO_NONE;
+
+ /* Always exact match mac_proto */
+ SW_FLOW_KEY_PUT(match, mac_proto, is_mask ? 0xff : mac_proto, is_mask);
+
+ if (mac_proto == MAC_PROTO_NONE)
+ return parse_eth_type_from_nlattrs(match, attrs, a, is_mask,
+ log);
+
+ return 0;
+}
+
+int nsh_hdr_from_nlattr(const struct nlattr *attr,
+ struct nshhdr *nh, size_t size)
+{
+ struct nlattr *a;
+ int rem;
+ u8 flags = 0;
+ u8 ttl = 0;
+ int mdlen = 0;
+
+ /* validate_nsh has check this, so we needn't do duplicate check here
+ */
+ if (size < NSH_BASE_HDR_LEN)
+ return -ENOBUFS;
+
+ nla_for_each_nested(a, attr, rem) {
+ int type = nla_type(a);
+
+ switch (type) {
+ case OVS_NSH_KEY_ATTR_BASE: {
+ const struct ovs_nsh_key_base *base = nla_data(a);
+
+ flags = base->flags;
+ ttl = base->ttl;
+ nh->np = base->np;
+ nh->mdtype = base->mdtype;
+ nh->path_hdr = base->path_hdr;
+ break;
+ }
+ case OVS_NSH_KEY_ATTR_MD1:
+ mdlen = nla_len(a);
+ if (mdlen > size - NSH_BASE_HDR_LEN)
+ return -ENOBUFS;
+ memcpy(&nh->md1, nla_data(a), mdlen);
+ break;
+
+ case OVS_NSH_KEY_ATTR_MD2:
+ mdlen = nla_len(a);
+ if (mdlen > size - NSH_BASE_HDR_LEN)
+ return -ENOBUFS;
+ memcpy(&nh->md2, nla_data(a), mdlen);
+ break;
+
+ default:
+ return -EINVAL;
+ }
}
+
+ /* nsh header length = NSH_BASE_HDR_LEN + mdlen */
+ nh->ver_flags_ttl_len = 0;
+ nsh_set_flags_ttl_len(nh, flags, ttl, NSH_BASE_HDR_LEN + mdlen);
+
+ return 0;
+}
+
+int nsh_key_from_nlattr(const struct nlattr *attr,
+ struct ovs_key_nsh *nsh, struct ovs_key_nsh *nsh_mask)
+{
+ struct nlattr *a;
+ int rem;
+
+ /* validate_nsh has check this, so we needn't do duplicate check here
+ */
+ nla_for_each_nested(a, attr, rem) {
+ int type = nla_type(a);
+
+ switch (type) {
+ case OVS_NSH_KEY_ATTR_BASE: {
+ const struct ovs_nsh_key_base *base = nla_data(a);
+ const struct ovs_nsh_key_base *base_mask = base + 1;
+
+ nsh->base = *base;
+ nsh_mask->base = *base_mask;
+ break;
+ }
+ case OVS_NSH_KEY_ATTR_MD1: {
+ const struct ovs_nsh_key_md1 *md1 = nla_data(a);
+ const struct ovs_nsh_key_md1 *md1_mask = md1 + 1;
+
+ memcpy(nsh->context, md1->context, sizeof(*md1));
+ memcpy(nsh_mask->context, md1_mask->context,
+ sizeof(*md1_mask));
+ break;
+ }
+ case OVS_NSH_KEY_ATTR_MD2:
+ /* Not supported yet */
+ return -ENOTSUPP;
+ default:
+ return -EINVAL;
+ }
+ }
+
+ return 0;
+}
+
+static int nsh_key_put_from_nlattr(const struct nlattr *attr,
+ struct sw_flow_match *match, bool is_mask,
+ bool is_push_nsh, bool log)
+{
+ struct nlattr *a;
+ int rem;
+ bool has_base = false;
+ bool has_md1 = false;
+ bool has_md2 = false;
+ u8 mdtype = 0;
+ int mdlen = 0;
+
+ if (WARN_ON(is_push_nsh && is_mask))
+ return -EINVAL;
+
+ nla_for_each_nested(a, attr, rem) {
+ int type = nla_type(a);
+ int i;
+
+ if (type > OVS_NSH_KEY_ATTR_MAX) {
+ OVS_NLERR(log, "nsh attr %d is out of range max %d",
+ type, OVS_NSH_KEY_ATTR_MAX);
+ return -EINVAL;
+ }
+
+ if (!check_attr_len(nla_len(a),
+ ovs_nsh_key_attr_lens[type].len)) {
+ OVS_NLERR(
+ log,
+ "nsh attr %d has unexpected len %d expected %d",
+ type,
+ nla_len(a),
+ ovs_nsh_key_attr_lens[type].len
+ );
+ return -EINVAL;
+ }
+
+ switch (type) {
+ case OVS_NSH_KEY_ATTR_BASE: {
+ const struct ovs_nsh_key_base *base = nla_data(a);
+
+ has_base = true;
+ mdtype = base->mdtype;
+ SW_FLOW_KEY_PUT(match, nsh.base.flags,
+ base->flags, is_mask);
+ SW_FLOW_KEY_PUT(match, nsh.base.ttl,
+ base->ttl, is_mask);
+ SW_FLOW_KEY_PUT(match, nsh.base.mdtype,
+ base->mdtype, is_mask);
+ SW_FLOW_KEY_PUT(match, nsh.base.np,
+ base->np, is_mask);
+ SW_FLOW_KEY_PUT(match, nsh.base.path_hdr,
+ base->path_hdr, is_mask);
+ break;
+ }
+ case OVS_NSH_KEY_ATTR_MD1: {
+ const struct ovs_nsh_key_md1 *md1 = nla_data(a);
+
+ has_md1 = true;
+ for (i = 0; i < NSH_MD1_CONTEXT_SIZE; i++)
+ SW_FLOW_KEY_PUT(match, nsh.context[i],
+ md1->context[i], is_mask);
+ break;
+ }
+ case OVS_NSH_KEY_ATTR_MD2:
+ if (!is_push_nsh) /* Not supported MD type 2 yet */
+ return -ENOTSUPP;
+
+ has_md2 = true;
+ mdlen = nla_len(a);
+ if (mdlen > NSH_CTX_HDRS_MAX_LEN || mdlen <= 0) {
+ OVS_NLERR(
+ log,
+ "Invalid MD length %d for MD type %d",
+ mdlen,
+ mdtype
+ );
+ return -EINVAL;
+ }
+ break;
+ default:
+ OVS_NLERR(log, "Unknown nsh attribute %d",
+ type);
+ return -EINVAL;
+ }
+ }
+
+ if (rem > 0) {
+ OVS_NLERR(log, "nsh attribute has %d unknown bytes.", rem);
+ return -EINVAL;
+ }
+
+ if (has_md1 && has_md2) {
+ OVS_NLERR(
+ 1,
+ "invalid nsh attribute: md1 and md2 are exclusive."
+ );
+ return -EINVAL;
+ }
+
+ if (!is_mask) {
+ if ((has_md1 && mdtype != NSH_M_TYPE1) ||
+ (has_md2 && mdtype != NSH_M_TYPE2)) {
+ OVS_NLERR(1, "nsh attribute has unmatched MD type %d.",
+ mdtype);
+ return -EINVAL;
+ }
+
+ if (is_push_nsh &&
+ (!has_base || (!has_md1 && !has_md2))) {
+ OVS_NLERR(
+ 1,
+ "push_nsh: missing base or metadata attributes"
+ );
+ return -EINVAL;
+ }
+ }
+
return 0;
}
SW_FLOW_KEY_MEMCPY(match, eth.dst,
eth_key->eth_dst, ETH_ALEN, is_mask);
attrs &= ~(1ULL << OVS_KEY_ATTR_ETHERNET);
- }
-
- if (attrs & (1ULL << OVS_KEY_ATTR_VLAN)) {
- __be16 tci;
-
- tci = nla_get_be16(a[OVS_KEY_ATTR_VLAN]);
- if (!(tci & htons(VLAN_TAG_PRESENT))) {
- if (is_mask)
- OVS_NLERR(log, "VLAN TCI mask does not have exact match for VLAN_TAG_PRESENT bit.");
- else
- OVS_NLERR(log, "VLAN TCI does not have VLAN_TAG_PRESENT bit set.");
+ if (attrs & (1ULL << OVS_KEY_ATTR_VLAN)) {
+ /* VLAN attribute is always parsed before getting here since it
+ * may occur multiple times.
+ */
+ OVS_NLERR(log, "VLAN attribute unexpected.");
return -EINVAL;
}
- SW_FLOW_KEY_PUT(match, eth.tci, tci, is_mask);
- attrs &= ~(1ULL << OVS_KEY_ATTR_VLAN);
- }
-
- if (attrs & (1ULL << OVS_KEY_ATTR_ETHERTYPE)) {
- __be16 eth_type;
-
- eth_type = nla_get_be16(a[OVS_KEY_ATTR_ETHERTYPE]);
- if (is_mask) {
- /* Always exact match EtherType. */
- eth_type = htons(0xffff);
- } else if (!eth_proto_is_802_3(eth_type)) {
- OVS_NLERR(log, "EtherType %x is less than min %x",
- ntohs(eth_type), ETH_P_802_3_MIN);
- return -EINVAL;
+ if (attrs & (1ULL << OVS_KEY_ATTR_ETHERTYPE)) {
+ err = parse_eth_type_from_nlattrs(match, &attrs, a, is_mask,
+ log);
+ if (err)
+ return err;
+ } else if (!is_mask) {
+ SW_FLOW_KEY_PUT(match, eth.type, htons(ETH_P_802_2), is_mask);
}
-
- SW_FLOW_KEY_PUT(match, eth.type, eth_type, is_mask);
- attrs &= ~(1ULL << OVS_KEY_ATTR_ETHERTYPE);
- } else if (!is_mask) {
- SW_FLOW_KEY_PUT(match, eth.type, htons(ETH_P_802_2), is_mask);
+ } else if (!match->key->eth.type) {
+ OVS_NLERR(log, "Either Ethernet header or EtherType is required.");
+ return -EINVAL;
}
if (attrs & (1 << OVS_KEY_ATTR_IPV4)) {
}
if (!is_mask && ipv6_key->ipv6_label & htonl(0xFFF00000)) {
- OVS_NLERR(log,
- "Invalid IPv6 flow label value (value=%x, max=%x).",
+ OVS_NLERR(log, "IPv6 flow label %x is out of range (max=%x)",
ntohl(ipv6_key->ipv6_label), (1 << 20) - 1);
return -EINVAL;
}
attrs &= ~(1ULL << OVS_KEY_ATTR_ARP);
}
+ if (attrs & (1 << OVS_KEY_ATTR_NSH)) {
+ if (nsh_key_put_from_nlattr(a[OVS_KEY_ATTR_NSH], match,
+ is_mask, false, log) < 0)
+ return -EINVAL;
+ attrs &= ~(1 << OVS_KEY_ATTR_NSH);
+ }
+
if (attrs & (1ULL << OVS_KEY_ATTR_MPLS)) {
const struct ovs_key_mpls *mpls_key;
/* The nlattr stream should already have been validated */
nla_for_each_nested(nla, attr, rem) {
- if (tbl[nla_type(nla)].len == OVS_ATTR_NESTED) {
- if (tbl[nla_type(nla)].next)
- tbl = tbl[nla_type(nla)].next;
- nlattr_set(nla, val, tbl);
- } else {
+ if (tbl[nla_type(nla)].len == OVS_ATTR_NESTED)
+ nlattr_set(nla, val, tbl[nla_type(nla)].next ? : tbl);
+ else
memset(nla_data(nla), val, nla_len(nla));
- }
+
+ if (nla_type(nla) == OVS_KEY_ATTR_CT_STATE)
+ *(u32 *)nla_data(nla) &= CT_SUPPORTED_MASK;
}
}
bool log)
{
const struct nlattr *a[OVS_KEY_ATTR_MAX + 1];
- const struct nlattr *encap;
struct nlattr *newmask = NULL;
u64 key_attrs = 0;
u64 mask_attrs = 0;
- bool encap_valid = false;
int err;
err = parse_flow_nlattrs(nla_key, a, &key_attrs, log);
if (err)
return err;
- if ((key_attrs & (1ULL << OVS_KEY_ATTR_ETHERNET)) &&
- (key_attrs & (1ULL << OVS_KEY_ATTR_ETHERTYPE)) &&
- (nla_get_be16(a[OVS_KEY_ATTR_ETHERTYPE]) == htons(ETH_P_8021Q))) {
- __be16 tci;
-
- if (!((key_attrs & (1ULL << OVS_KEY_ATTR_VLAN)) &&
- (key_attrs & (1ULL << OVS_KEY_ATTR_ENCAP)))) {
- OVS_NLERR(log, "Invalid Vlan frame.");
- return -EINVAL;
- }
-
- key_attrs &= ~(1ULL << OVS_KEY_ATTR_ETHERTYPE);
- tci = nla_get_be16(a[OVS_KEY_ATTR_VLAN]);
- encap = a[OVS_KEY_ATTR_ENCAP];
- key_attrs &= ~(1ULL << OVS_KEY_ATTR_ENCAP);
- encap_valid = true;
-
- if (tci & htons(VLAN_TAG_PRESENT)) {
- err = parse_flow_nlattrs(encap, a, &key_attrs, log);
- if (err)
- return err;
- } else if (!tci) {
- /* Corner case for truncated 802.1Q header. */
- if (nla_len(encap)) {
- OVS_NLERR(log, "Truncated 802.1Q header has non-zero encap attribute.");
- return -EINVAL;
- }
- } else {
- OVS_NLERR(log, "Encap attr is set for non-VLAN frame");
- return -EINVAL;
- }
- }
+ err = parse_vlan_from_nlattrs(match, &key_attrs, a, false, log);
+ if (err)
+ return err;
err = ovs_key_from_nlattrs(net, match, key_attrs, a, false, log);
if (err)
/* The userspace does not send tunnel attributes that
* are 0, but we should not wildcard them nonetheless.
*/
- if (match->key->tun_key.u.ipv4.dst)
+ if (match->key->tun_proto)
SW_FLOW_KEY_MEMSET_FIELD(match, tun_key,
0xff, true);
if (err)
goto free_newmask;
- /* Always match on tci. */
- SW_FLOW_KEY_PUT(match, eth.tci, htons(0xffff), true);
-
- if (mask_attrs & 1ULL << OVS_KEY_ATTR_ENCAP) {
- __be16 eth_type = 0;
- __be16 tci = 0;
-
- if (!encap_valid) {
- OVS_NLERR(log, "Encap mask attribute is set for non-VLAN frame.");
- err = -EINVAL;
- goto free_newmask;
- }
+ SW_FLOW_KEY_PUT(match, eth.vlan.tci, htons(0xffff), true);
+ SW_FLOW_KEY_PUT(match, eth.cvlan.tci, htons(0xffff), true);
- mask_attrs &= ~(1ULL << OVS_KEY_ATTR_ENCAP);
- if (a[OVS_KEY_ATTR_ETHERTYPE])
- eth_type = nla_get_be16(a[OVS_KEY_ATTR_ETHERTYPE]);
-
- if (eth_type == htons(0xffff)) {
- mask_attrs &= ~(1ULL << OVS_KEY_ATTR_ETHERTYPE);
- encap = a[OVS_KEY_ATTR_ENCAP];
- err = parse_flow_mask_nlattrs(encap, a,
- &mask_attrs, log);
- if (err)
- goto free_newmask;
- } else {
- OVS_NLERR(log, "VLAN frames must have an exact match on the TPID (mask=%x).",
- ntohs(eth_type));
- err = -EINVAL;
- goto free_newmask;
- }
-
- if (a[OVS_KEY_ATTR_VLAN])
- tci = nla_get_be16(a[OVS_KEY_ATTR_VLAN]);
-
- if (!(tci & htons(VLAN_TAG_PRESENT))) {
- OVS_NLERR(log, "VLAN tag present bit must have an exact match (tci_mask=%x).",
- ntohs(tci));
- err = -EINVAL;
- goto free_newmask;
- }
- }
+ err = parse_vlan_from_nlattrs(match, &mask_attrs, a, true, log);
+ if (err)
+ goto free_newmask;
err = ovs_key_from_nlattrs(net, match, mask_attrs, a, true,
log);
/**
* ovs_nla_get_flow_metadata - parses Netlink attributes into a flow key.
- * @key: Receives extracted in_port, priority, tun_key and skb_mark.
- * @attr: Netlink attribute holding nested %OVS_KEY_ATTR_* Netlink attribute
- * sequence.
+ * @net: Network namespace.
+ * @key: Receives extracted in_port, priority, tun_key, skb_mark and conntrack
+ * metadata.
+ * @a: Array of netlink attributes holding parsed %OVS_KEY_ATTR_* Netlink
+ * attributes.
+ * @attrs: Bit mask for the netlink attributes included in @a.
* @log: Boolean to allow kernel error logging. Normally true, but when
* probing for feature compatibility this should be passed in as false to
* suppress unnecessary error logging.
* take the same form accepted by flow_from_nlattrs(), but only enough of it to
* get the metadata, that is, the parts of the flow key that cannot be
* extracted from the packet itself.
+ *
+ * This must be called before the packet key fields are filled in 'key'.
*/
-int ovs_nla_get_flow_metadata(struct net *net, const struct nlattr *attr,
- struct sw_flow_key *key,
- bool log)
+int ovs_nla_get_flow_metadata(struct net *net,
+ const struct nlattr *a[OVS_KEY_ATTR_MAX + 1],
+ u64 attrs, struct sw_flow_key *key, bool log)
+{
+ struct sw_flow_match match;
+
+ 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));
+
+ key->phy.in_port = DP_MAX_PORTS;
+
+ return metadata_from_nlattrs(net, &match, &attrs, a, false, log);
+}
+
+static int ovs_nla_put_vlan(struct sk_buff *skb, const struct vlan_head *vh,
+ bool is_mask)
+{
+ __be16 eth_type = !is_mask ? vh->tpid : htons(0xffff);
+
+ if (nla_put_be16(skb, OVS_KEY_ATTR_ETHERTYPE, eth_type) ||
+ nla_put_be16(skb, OVS_KEY_ATTR_VLAN, vh->tci))
+ return -EMSGSIZE;
+ return 0;
+}
+
+static int nsh_key_to_nlattr(const struct ovs_key_nsh *nsh, bool is_mask,
+ struct sk_buff *skb)
{
- const struct nlattr *a[OVS_KEY_ATTR_MAX + 1];
- struct sw_flow_match match;
- u64 attrs = 0;
- int err;
+ struct nlattr *start;
- err = parse_flow_nlattrs(attr, a, &attrs, log);
- if (err)
- return -EINVAL;
+ start = nla_nest_start(skb, OVS_KEY_ATTR_NSH);
+ if (!start)
+ return -EMSGSIZE;
- memset(&match, 0, sizeof(match));
- match.key = key;
+ if (nla_put(skb, OVS_NSH_KEY_ATTR_BASE, sizeof(nsh->base), &nsh->base))
+ goto nla_put_failure;
- memset(key, 0, OVS_SW_FLOW_KEY_METADATA_SIZE);
- memset(&key->ct, 0, sizeof(key->ct));
- key->phy.in_port = DP_MAX_PORTS;
+ if (is_mask || nsh->base.mdtype == NSH_M_TYPE1) {
+ if (nla_put(skb, OVS_NSH_KEY_ATTR_MD1,
+ sizeof(nsh->context), nsh->context))
+ goto nla_put_failure;
+ }
- return metadata_from_nlattrs(net, &match, &attrs, a, false, log);
+ /* Don't support MD type 2 yet */
+
+ nla_nest_end(skb, start);
+
+ return 0;
+
+nla_put_failure:
+ return -EMSGSIZE;
}
static int __ovs_nla_put_key(const struct sw_flow_key *swkey,
struct sk_buff *skb)
{
struct ovs_key_ethernet *eth_key;
- struct nlattr *nla, *encap;
+ struct nlattr *nla;
+ struct nlattr *encap = NULL;
+ struct nlattr *in_encap = NULL;
if (nla_put_u32(skb, OVS_KEY_ATTR_RECIRC_ID, output->recirc_id))
goto nla_put_failure;
if (nla_put_u32(skb, OVS_KEY_ATTR_PRIORITY, output->phy.priority))
goto nla_put_failure;
- if ((swkey->tun_key.u.ipv4.dst || is_mask)) {
+ if ((swkey->tun_proto || is_mask)) {
const void *opts = NULL;
if (output->tun_key.tun_flags & TUNNEL_OPTIONS_PRESENT)
opts = TUN_METADATA_OPTS(output, swkey->tun_opts_len);
- if (ipv4_tun_to_nlattr(skb, &output->tun_key, opts,
- swkey->tun_opts_len))
+ if (ip_tun_to_nlattr(skb, &output->tun_key, opts,
+ swkey->tun_opts_len, swkey->tun_proto))
goto nla_put_failure;
}
if (nla_put_u32(skb, OVS_KEY_ATTR_SKB_MARK, output->phy.skb_mark))
goto nla_put_failure;
- if (ovs_ct_put_key(output, skb))
+ if (ovs_ct_put_key(swkey, output, skb))
goto nla_put_failure;
- nla = nla_reserve(skb, OVS_KEY_ATTR_ETHERNET, sizeof(*eth_key));
- if (!nla)
- goto nla_put_failure;
+ if (ovs_key_mac_proto(swkey) == MAC_PROTO_ETHERNET) {
+ nla = nla_reserve(skb, OVS_KEY_ATTR_ETHERNET, sizeof(*eth_key));
+ if (!nla)
+ goto nla_put_failure;
- eth_key = nla_data(nla);
- ether_addr_copy(eth_key->eth_src, output->eth.src);
- ether_addr_copy(eth_key->eth_dst, output->eth.dst);
+ eth_key = nla_data(nla);
+ ether_addr_copy(eth_key->eth_src, output->eth.src);
+ ether_addr_copy(eth_key->eth_dst, output->eth.dst);
- if (swkey->eth.tci || swkey->eth.type == htons(ETH_P_8021Q)) {
- __be16 eth_type;
- eth_type = !is_mask ? htons(ETH_P_8021Q) : htons(0xffff);
- if (nla_put_be16(skb, OVS_KEY_ATTR_ETHERTYPE, eth_type) ||
- nla_put_be16(skb, OVS_KEY_ATTR_VLAN, output->eth.tci))
- goto nla_put_failure;
- encap = nla_nest_start(skb, OVS_KEY_ATTR_ENCAP);
- if (!swkey->eth.tci)
- goto unencap;
- } else
- encap = NULL;
-
- if (swkey->eth.type == htons(ETH_P_802_2)) {
- /*
- * Ethertype 802.2 is represented in the netlink with omitted
- * OVS_KEY_ATTR_ETHERTYPE in the flow key attribute, and
- * 0xffff in the mask attribute. Ethertype can also
- * be wildcarded.
- */
- if (is_mask && output->eth.type)
- if (nla_put_be16(skb, OVS_KEY_ATTR_ETHERTYPE,
- output->eth.type))
+ if (swkey->eth.vlan.tci || eth_type_vlan(swkey->eth.type)) {
+ if (ovs_nla_put_vlan(skb, &output->eth.vlan, is_mask))
goto nla_put_failure;
- goto unencap;
+ encap = nla_nest_start(skb, OVS_KEY_ATTR_ENCAP);
+ if (!swkey->eth.vlan.tci)
+ goto unencap;
+
+ if (swkey->eth.cvlan.tci || eth_type_vlan(swkey->eth.type)) {
+ if (ovs_nla_put_vlan(skb, &output->eth.cvlan, is_mask))
+ goto nla_put_failure;
+ in_encap = nla_nest_start(skb, OVS_KEY_ATTR_ENCAP);
+ if (!swkey->eth.cvlan.tci)
+ goto unencap;
+ }
+ }
+
+ if (swkey->eth.type == htons(ETH_P_802_2)) {
+ /*
+ * Ethertype 802.2 is represented in the netlink with omitted
+ * OVS_KEY_ATTR_ETHERTYPE in the flow key attribute, and
+ * 0xffff in the mask attribute. Ethertype can also
+ * be wildcarded.
+ */
+ if (is_mask && output->eth.type)
+ if (nla_put_be16(skb, OVS_KEY_ATTR_ETHERTYPE,
+ output->eth.type))
+ goto nla_put_failure;
+ goto unencap;
+ }
}
if (nla_put_be16(skb, OVS_KEY_ATTR_ETHERTYPE, output->eth.type))
goto nla_put_failure;
+ if (eth_type_vlan(swkey->eth.type)) {
+ /* There are 3 VLAN tags, we don't know anything about the rest
+ * of the packet, so truncate here.
+ */
+ WARN_ON_ONCE(!(encap && in_encap));
+ goto unencap;
+ }
+
if (swkey->eth.type == htons(ETH_P_IP)) {
struct ovs_key_ipv4 *ipv4_key;
ipv6_key->ipv6_tclass = output->ip.tos;
ipv6_key->ipv6_hlimit = output->ip.ttl;
ipv6_key->ipv6_frag = output->ip.frag;
+ } else if (swkey->eth.type == htons(ETH_P_NSH)) {
+ if (nsh_key_to_nlattr(&output->nsh, is_mask, skb))
+ goto nla_put_failure;
} else if (swkey->eth.type == htons(ETH_P_ARP) ||
swkey->eth.type == htons(ETH_P_RARP)) {
struct ovs_key_arp *arp_key;
}
unencap:
+ if (in_encap)
+ nla_nest_end(skb, in_encap);
if (encap)
nla_nest_end(skb, encap);
OVS_FLOW_ATTR_MASK, true, skb);
}
+#if LINUX_VERSION_CODE < KERNEL_VERSION(4,9,0)
+#define MAX_ACTIONS_BUFSIZE (16 * 1024)
+#else
#define MAX_ACTIONS_BUFSIZE (32 * 1024)
+#endif
-static struct sw_flow_actions *nla_alloc_flow_actions(int size, bool log)
+static struct sw_flow_actions *nla_alloc_flow_actions(int size)
{
struct sw_flow_actions *sfa;
- if (size > MAX_ACTIONS_BUFSIZE) {
- OVS_NLERR(log, "Flow action size %u bytes exceeds max", size);
- return ERR_PTR(-EINVAL);
- }
+ WARN_ON_ONCE(size > MAX_ACTIONS_BUFSIZE);
sfa = kmalloc(sizeof(*sfa) + size, GFP_KERNEL);
if (!sfa)
}
/* Schedules 'sf_acts' to be freed after the next RCU grace period.
- * The caller must hold rcu_read_lock for this to be sensible.
- */
+ * The caller must hold rcu_read_lock for this to be sensible. */
void ovs_nla_free_flow_actions_rcu(struct sw_flow_actions *sf_acts)
{
call_rcu(&sf_acts->rcu, __ovs_nla_free_flow_actions);
struct sw_flow_actions *acts;
int new_acts_size;
- int req_size = NLA_ALIGN(attr_len);
+ size_t req_size = NLA_ALIGN(attr_len);
int next_offset = offsetof(struct sw_flow_actions, actions) +
(*sfa)->actions_len;
if (req_size <= (ksize(*sfa) - next_offset))
goto out;
- new_acts_size = ksize(*sfa) * 2;
+ new_acts_size = max(next_offset + req_size, ksize(*sfa) * 2);
if (new_acts_size > MAX_ACTIONS_BUFSIZE) {
- if ((MAX_ACTIONS_BUFSIZE - next_offset) < req_size)
+ if ((MAX_ACTIONS_BUFSIZE - next_offset) < req_size) {
+ OVS_NLERR(log, "Flow action size exceeds max %u",
+ MAX_ACTIONS_BUFSIZE);
return ERR_PTR(-EMSGSIZE);
+ }
new_acts_size = MAX_ACTIONS_BUFSIZE;
}
- acts = nla_alloc_flow_actions(new_acts_size, log);
+ acts = nla_alloc_flow_actions(new_acts_size);
if (IS_ERR(acts))
return (void *)acts;
struct nlattr *a;
a = __add_action(sfa, attrtype, data, len, log);
- if (IS_ERR(a))
- return PTR_ERR(a);
- return 0;
+ return PTR_ERR_OR_ZERO(a);
}
static inline int add_nested_action_start(struct sw_flow_actions **sfa,
static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
const struct sw_flow_key *key,
- int depth, struct sw_flow_actions **sfa,
+ struct sw_flow_actions **sfa,
__be16 eth_type, __be16 vlan_tci, bool log);
static int validate_and_copy_sample(struct net *net, const struct nlattr *attr,
- const struct sw_flow_key *key, int depth,
+ const struct sw_flow_key *key,
struct sw_flow_actions **sfa,
- __be16 eth_type, __be16 vlan_tci, bool log)
+ __be16 eth_type, __be16 vlan_tci,
+ bool log, bool last)
{
const struct nlattr *attrs[OVS_SAMPLE_ATTR_MAX + 1];
const struct nlattr *probability, *actions;
const struct nlattr *a;
- int rem, start, err, st_acts;
+ int rem, start, err;
+ struct sample_arg arg;
memset(attrs, 0, sizeof(attrs));
nla_for_each_nested(a, attr, rem) {
start = add_nested_action_start(sfa, OVS_ACTION_ATTR_SAMPLE, log);
if (start < 0)
return start;
- err = ovs_nla_add_action(sfa, OVS_SAMPLE_ATTR_PROBABILITY,
- nla_data(probability), sizeof(u32), log);
+
+ /* When both skb and flow may be changed, put the sample
+ * into a deferred fifo. On the other hand, if only skb
+ * may be modified, the actions can be executed in place.
+ *
+ * Do this analysis at the flow installation time.
+ * Set 'clone_action->exec' to true if the actions can be
+ * executed without being deferred.
+ *
+ * If the sample is the last action, it can always be excuted
+ * rather than deferred.
+ */
+ arg.exec = last || !actions_may_change_flow(actions);
+ arg.probability = nla_get_u32(probability);
+
+ err = ovs_nla_add_action(sfa, OVS_SAMPLE_ATTR_ARG, &arg, sizeof(arg),
+ log);
+ if (err)
+ return err;
+
+ err = __ovs_nla_copy_actions(net, actions, key, sfa,
+ eth_type, vlan_tci, log);
+
+ if (err)
+ return err;
+
+ add_nested_action_end(*sfa, start);
+
+ return 0;
+}
+
+static int validate_and_copy_clone(struct net *net,
+ const struct nlattr *attr,
+ const struct sw_flow_key *key,
+ struct sw_flow_actions **sfa,
+ __be16 eth_type, __be16 vlan_tci,
+ bool log, bool last)
+{
+ int start, err;
+ u32 exec;
+
+ if (nla_len(attr) && nla_len(attr) < NLA_HDRLEN)
+ return -EINVAL;
+
+ start = add_nested_action_start(sfa, OVS_ACTION_ATTR_CLONE, log);
+ if (start < 0)
+ return start;
+
+ exec = last || !actions_may_change_flow(attr);
+
+ err = ovs_nla_add_action(sfa, OVS_CLONE_ATTR_EXEC, &exec,
+ sizeof(exec), log);
if (err)
return err;
- st_acts = add_nested_action_start(sfa, OVS_SAMPLE_ATTR_ACTIONS, log);
- if (st_acts < 0)
- return st_acts;
- err = __ovs_nla_copy_actions(net, actions, key, depth + 1, sfa,
+ err = __ovs_nla_copy_actions(net, attr, key, sfa,
eth_type, vlan_tci, log);
if (err)
return err;
- add_nested_action_end(*sfa, st_acts);
add_nested_action_end(*sfa, start);
return 0;
void ovs_match_init(struct sw_flow_match *match,
struct sw_flow_key *key,
+ bool reset_key,
struct sw_flow_mask *mask)
{
memset(match, 0, sizeof(*match));
match->key = key;
match->mask = mask;
- memset(key, 0, sizeof(*key));
+ if (reset_key)
+ memset(key, 0, sizeof(*key));
if (mask) {
memset(&mask->key, 0, sizeof(mask->key));
option = (struct geneve_opt *)((u8 *)option + len);
opts_len -= len;
- };
+ }
key->tun_key.tun_flags |= crit_opt ? TUNNEL_CRIT_OPT : 0;
struct ovs_tunnel_info *ovs_tun;
struct nlattr *a;
int err = 0, start, opts_type;
+ __be16 dst_opt_type;
- ovs_match_init(&match, &key, NULL);
- opts_type = ipv4_tun_from_nlattr(nla_data(attr), &match, false, log);
+ dst_opt_type = 0;
+ ovs_match_init(&match, &key, true, NULL);
+ opts_type = ip_tun_from_nlattr(nla_data(attr), &match, false, log);
if (opts_type < 0)
return opts_type;
err = validate_geneve_opts(&key);
if (err < 0)
return err;
+ dst_opt_type = TUNNEL_GENEVE_OPT;
break;
case OVS_TUNNEL_KEY_ATTR_VXLAN_OPTS:
+ dst_opt_type = TUNNEL_VXLAN_OPT;
+ break;
+ case OVS_TUNNEL_KEY_ATTR_ERSPAN_OPTS:
+ dst_opt_type = TUNNEL_ERSPAN_OPT;
break;
}
- };
+ }
start = add_nested_action_start(sfa, OVS_ACTION_ATTR_SET, log);
if (start < 0)
return start;
- tun_dst = metadata_dst_alloc(key.tun_opts_len, GFP_KERNEL);
+ tun_dst = metadata_dst_alloc(key.tun_opts_len, METADATA_IP_TUNNEL,
+ GFP_KERNEL);
+
if (!tun_dst)
return -ENOMEM;
+ err = dst_cache_init(&tun_dst->u.tun_info.dst_cache, GFP_KERNEL);
+ if (err) {
+ dst_release((struct dst_entry *)tun_dst);
+ return err;
+ }
a = __add_action(sfa, OVS_KEY_ATTR_TUNNEL_INFO, NULL,
sizeof(*ovs_tun), log);
if (IS_ERR(a)) {
tun_info = &tun_dst->u.tun_info;
tun_info->mode = IP_TUNNEL_INFO_TX;
+ if (key.tun_proto == AF_INET6)
+ tun_info->mode |= IP_TUNNEL_INFO_IPV6;
tun_info->key = key.tun_key;
/* We need to store the options in the action itself since
*/
ip_tunnel_info_opts_set(tun_info,
TUN_METADATA_OPTS(&key, key.tun_opts_len),
- key.tun_opts_len);
+ key.tun_opts_len, dst_opt_type);
add_nested_action_end(*sfa, start);
return err;
}
+static bool validate_nsh(const struct nlattr *attr, bool is_mask,
+ bool is_push_nsh, bool log)
+{
+ struct sw_flow_match match;
+ struct sw_flow_key key;
+ int ret = 0;
+
+ ovs_match_init(&match, &key, true, NULL);
+ ret = nsh_key_put_from_nlattr(attr, &match, is_mask,
+ is_push_nsh, log);
+ return !ret;
+}
+
/* Return false if there are any non-masked bits set.
* Mask follows data immediately, before any netlink padding.
*/
static int validate_set(const struct nlattr *a,
const struct sw_flow_key *flow_key,
- struct sw_flow_actions **sfa,
- bool *skip_copy, __be16 eth_type, bool masked, bool log)
+ struct sw_flow_actions **sfa, bool *skip_copy,
+ u8 mac_proto, __be16 eth_type, bool masked, bool log)
{
const struct nlattr *ovs_key = nla_data(a);
int key_type = nla_type(ovs_key);
case OVS_KEY_ATTR_PRIORITY:
case OVS_KEY_ATTR_SKB_MARK:
case OVS_KEY_ATTR_CT_MARK:
- case OVS_KEY_ATTR_CT_LABEL:
+ case OVS_KEY_ATTR_CT_LABELS:
+ break;
+
case OVS_KEY_ATTR_ETHERNET:
+ if (mac_proto != MAC_PROTO_ETHERNET)
+ return -EINVAL;
break;
case OVS_KEY_ATTR_TUNNEL:
+#ifndef USE_UPSTREAM_TUNNEL
if (eth_p_mpls(eth_type))
return -EINVAL;
-
+#endif
if (masked)
return -EINVAL; /* Masked tunnel set not supported. */
break;
+ case OVS_KEY_ATTR_NSH:
+ if (eth_type != htons(ETH_P_NSH))
+ return -EINVAL;
+ if (!validate_nsh(nla_data(a), masked, false, log))
+ return -EINVAL;
+ break;
+
default:
return -EINVAL;
}
struct nlattr *a[OVS_USERSPACE_ATTR_MAX + 1];
int error;
- error = nla_parse_nested(a, OVS_USERSPACE_ATTR_MAX,
- attr, userspace_policy);
+ error = nla_parse_nested(a, OVS_USERSPACE_ATTR_MAX, attr,
+ userspace_policy, NULL);
if (error)
return error;
return 0;
}
+static const struct nla_policy cpl_policy[OVS_CHECK_PKT_LEN_ATTR_MAX + 1] = {
+ [OVS_CHECK_PKT_LEN_ATTR_PKT_LEN] = {.type = NLA_U16 },
+ [OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_GREATER] = {.type = NLA_NESTED },
+ [OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_LESS_EQUAL] = {.type = NLA_NESTED },
+};
+
+static int validate_and_copy_check_pkt_len(struct net *net,
+ const struct nlattr *attr,
+ const struct sw_flow_key *key,
+ struct sw_flow_actions **sfa,
+ __be16 eth_type, __be16 vlan_tci,
+ bool log, bool last)
+{
+ const struct nlattr *acts_if_greater, *acts_if_lesser_eq;
+ struct nlattr *a[OVS_CHECK_PKT_LEN_ATTR_MAX + 1];
+ struct check_pkt_len_arg arg;
+ int nested_acts_start;
+ int start, err;
+
+ err = nla_parse_nested(a, OVS_CHECK_PKT_LEN_ATTR_MAX, attr,
+ cpl_policy, NULL);
+ if (err)
+ return err;
+
+ if (!a[OVS_CHECK_PKT_LEN_ATTR_PKT_LEN] ||
+ !nla_get_u16(a[OVS_CHECK_PKT_LEN_ATTR_PKT_LEN]))
+ return -EINVAL;
+
+ acts_if_lesser_eq = a[OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_LESS_EQUAL];
+ acts_if_greater = a[OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_GREATER];
+
+ /* Both the nested action should be present. */
+ if (!acts_if_greater || !acts_if_lesser_eq)
+ return -EINVAL;
+
+ /* validation done, copy the nested actions. */
+ start = add_nested_action_start(sfa, OVS_ACTION_ATTR_CHECK_PKT_LEN,
+ log);
+ if (start < 0)
+ return start;
+
+ arg.pkt_len = nla_get_u16(a[OVS_CHECK_PKT_LEN_ATTR_PKT_LEN]);
+ arg.exec_for_lesser_equal =
+ last || !actions_may_change_flow(acts_if_lesser_eq);
+ arg.exec_for_greater =
+ last || !actions_may_change_flow(acts_if_greater);
+
+ err = ovs_nla_add_action(sfa, OVS_CHECK_PKT_LEN_ATTR_ARG, &arg,
+ sizeof(arg), log);
+ if (err)
+ return err;
+
+ nested_acts_start = add_nested_action_start(sfa,
+ OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_LESS_EQUAL, log);
+ if (nested_acts_start < 0)
+ return nested_acts_start;
+
+ err = __ovs_nla_copy_actions(net, acts_if_lesser_eq, key, sfa,
+ eth_type, vlan_tci, log);
+
+ if (err)
+ return err;
+
+ add_nested_action_end(*sfa, nested_acts_start);
+
+ nested_acts_start = add_nested_action_start(sfa,
+ OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_GREATER, log);
+ if (nested_acts_start < 0)
+ return nested_acts_start;
+
+ err = __ovs_nla_copy_actions(net, acts_if_greater, key, sfa,
+ eth_type, vlan_tci, log);
+
+ if (err)
+ return err;
+
+ add_nested_action_end(*sfa, nested_acts_start);
+ add_nested_action_end(*sfa, start);
+ return 0;
+}
+
static int copy_action(const struct nlattr *from,
struct sw_flow_actions **sfa, bool log)
{
static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
const struct sw_flow_key *key,
- int depth, struct sw_flow_actions **sfa,
+ struct sw_flow_actions **sfa,
__be16 eth_type, __be16 vlan_tci, bool log)
{
+ u8 mac_proto = ovs_key_mac_proto(key);
const struct nlattr *a;
int rem, err;
- if (depth >= SAMPLE_ACTION_DEPTH)
- return -EOVERFLOW;
-
nla_for_each_nested(a, attr, rem) {
/* Expected argument lengths, (u32)-1 for variable length. */
static const u32 action_lens[OVS_ACTION_ATTR_MAX + 1] = {
[OVS_ACTION_ATTR_SAMPLE] = (u32)-1,
[OVS_ACTION_ATTR_HASH] = sizeof(struct ovs_action_hash),
[OVS_ACTION_ATTR_CT] = (u32)-1,
+ [OVS_ACTION_ATTR_CT_CLEAR] = 0,
+ [OVS_ACTION_ATTR_TRUNC] = sizeof(struct ovs_action_trunc),
+ [OVS_ACTION_ATTR_PUSH_ETH] = sizeof(struct ovs_action_push_eth),
+ [OVS_ACTION_ATTR_POP_ETH] = 0,
+ [OVS_ACTION_ATTR_PUSH_NSH] = (u32)-1,
+ [OVS_ACTION_ATTR_POP_NSH] = 0,
+ [OVS_ACTION_ATTR_METER] = sizeof(u32),
+ [OVS_ACTION_ATTR_CLONE] = (u32)-1,
+ [OVS_ACTION_ATTR_CHECK_PKT_LEN] = (u32)-1,
};
const struct ovs_action_push_vlan *vlan;
int type = nla_type(a);
return -EINVAL;
break;
+ case OVS_ACTION_ATTR_TRUNC: {
+ const struct ovs_action_trunc *trunc = nla_data(a);
+
+ if (trunc->max_len < ETH_HLEN)
+ return -EINVAL;
+ break;
+ }
+
case OVS_ACTION_ATTR_HASH: {
const struct ovs_action_hash *act_hash = nla_data(a);
}
case OVS_ACTION_ATTR_POP_VLAN:
+ if (mac_proto != MAC_PROTO_ETHERNET)
+ return -EINVAL;
vlan_tci = htons(0);
break;
case OVS_ACTION_ATTR_PUSH_VLAN:
+ if (mac_proto != MAC_PROTO_ETHERNET)
+ return -EINVAL;
vlan = nla_data(a);
- if (vlan->vlan_tpid != htons(ETH_P_8021Q))
+ if (!eth_type_vlan(vlan->vlan_tpid))
return -EINVAL;
if (!(vlan->vlan_tci & htons(VLAN_TAG_PRESENT)))
return -EINVAL;
case OVS_ACTION_ATTR_SET:
err = validate_set(a, key, sfa,
- &skip_copy, eth_type, false, log);
+ &skip_copy, mac_proto, eth_type,
+ false, log);
if (err)
return err;
break;
case OVS_ACTION_ATTR_SET_MASKED:
err = validate_set(a, key, sfa,
- &skip_copy, eth_type, true, log);
+ &skip_copy, mac_proto, eth_type,
+ true, log);
if (err)
return err;
break;
- case OVS_ACTION_ATTR_SAMPLE:
- err = validate_and_copy_sample(net, a, key, depth, sfa,
- eth_type, vlan_tci, log);
+ case OVS_ACTION_ATTR_SAMPLE: {
+ bool last = nla_is_last(a, rem);
+
+ err = validate_and_copy_sample(net, a, key, sfa,
+ eth_type, vlan_tci,
+ log, last);
if (err)
return err;
skip_copy = true;
break;
+ }
case OVS_ACTION_ATTR_CT:
err = ovs_ct_copy_action(net, a, key, sfa, log);
skip_copy = true;
break;
+ case OVS_ACTION_ATTR_CT_CLEAR:
+ break;
+
+ case OVS_ACTION_ATTR_PUSH_ETH:
+ /* Disallow pushing an Ethernet header if one
+ * is already present */
+ if (mac_proto != MAC_PROTO_NONE)
+ return -EINVAL;
+ mac_proto = MAC_PROTO_ETHERNET;
+ break;
+
+ case OVS_ACTION_ATTR_POP_ETH:
+ if (mac_proto != MAC_PROTO_ETHERNET)
+ return -EINVAL;
+ if (vlan_tci & htons(VLAN_TAG_PRESENT))
+ return -EINVAL;
+ mac_proto = MAC_PROTO_NONE;
+ break;
+
+ case OVS_ACTION_ATTR_PUSH_NSH:
+ if (mac_proto != MAC_PROTO_ETHERNET) {
+ u8 next_proto;
+
+ next_proto = tun_p_from_eth_p(eth_type);
+ if (!next_proto)
+ return -EINVAL;
+ }
+ mac_proto = MAC_PROTO_NONE;
+ if (!validate_nsh(nla_data(a), false, true, true))
+ return -EINVAL;
+ break;
+
+ case OVS_ACTION_ATTR_POP_NSH: {
+ __be16 inner_proto;
+
+ if (eth_type != htons(ETH_P_NSH))
+ return -EINVAL;
+ inner_proto = tun_p_to_eth_p(key->nsh.base.np);
+ if (!inner_proto)
+ return -EINVAL;
+ if (key->nsh.base.np == TUN_P_ETHERNET)
+ mac_proto = MAC_PROTO_ETHERNET;
+ else
+ mac_proto = MAC_PROTO_NONE;
+ break;
+ }
+
+ case OVS_ACTION_ATTR_METER:
+ /* Non-existent meters are simply ignored. */
+ break;
+
+ case OVS_ACTION_ATTR_CLONE: {
+ bool last = nla_is_last(a, rem);
+
+ err = validate_and_copy_clone(net, a, key, sfa,
+ eth_type, vlan_tci,
+ log, last);
+ if (err)
+ return err;
+ skip_copy = true;
+ break;
+ }
+
+ case OVS_ACTION_ATTR_CHECK_PKT_LEN: {
+ bool last = nla_is_last(a, rem);
+
+ err = validate_and_copy_check_pkt_len(net, a, key, sfa,
+ eth_type,
+ vlan_tci, log,
+ last);
+ if (err)
+ return err;
+ skip_copy = true;
+ break;
+ }
+
default:
OVS_NLERR(log, "Unknown Action type %d", type);
return -EINVAL;
{
int err;
- *sfa = nla_alloc_flow_actions(nla_len(attr), log);
+ *sfa = nla_alloc_flow_actions(min(nla_len(attr), MAX_ACTIONS_BUFSIZE));
if (IS_ERR(*sfa))
return PTR_ERR(*sfa);
(*sfa)->orig_len = nla_len(attr);
- err = __ovs_nla_copy_actions(net, attr, key, 0, sfa, key->eth.type,
- key->eth.tci, log);
+ err = __ovs_nla_copy_actions(net, attr, key, sfa, key->eth.type,
+ key->eth.vlan.tci, log);
if (err)
ovs_nla_free_flow_actions(*sfa);
return err;
}
-static int sample_action_to_attr(const struct nlattr *attr, struct sk_buff *skb)
+static int sample_action_to_attr(const struct nlattr *attr,
+ struct sk_buff *skb)
{
- const struct nlattr *a;
- struct nlattr *start;
- int err = 0, rem;
+ struct nlattr *start, *ac_start = NULL, *sample_arg;
+ int err = 0, rem = nla_len(attr);
+ const struct sample_arg *arg;
+ struct nlattr *actions;
start = nla_nest_start(skb, OVS_ACTION_ATTR_SAMPLE);
if (!start)
return -EMSGSIZE;
- nla_for_each_nested(a, attr, rem) {
- int type = nla_type(a);
- struct nlattr *st_sample;
+ sample_arg = nla_data(attr);
+ arg = nla_data(sample_arg);
+ actions = nla_next(sample_arg, &rem);
- switch (type) {
- case OVS_SAMPLE_ATTR_PROBABILITY:
- if (nla_put(skb, OVS_SAMPLE_ATTR_PROBABILITY,
- sizeof(u32), nla_data(a)))
- return -EMSGSIZE;
- break;
- case OVS_SAMPLE_ATTR_ACTIONS:
- st_sample = nla_nest_start(skb, OVS_SAMPLE_ATTR_ACTIONS);
- if (!st_sample)
- return -EMSGSIZE;
- err = ovs_nla_put_actions(nla_data(a), nla_len(a), skb);
- if (err)
- return err;
- nla_nest_end(skb, st_sample);
- break;
- }
+ if (nla_put_u32(skb, OVS_SAMPLE_ATTR_PROBABILITY, arg->probability)) {
+ err = -EMSGSIZE;
+ goto out;
+ }
+
+ ac_start = nla_nest_start(skb, OVS_SAMPLE_ATTR_ACTIONS);
+ if (!ac_start) {
+ err = -EMSGSIZE;
+ goto out;
+ }
+
+ err = ovs_nla_put_actions(actions, rem, skb);
+
+out:
+ if (err) {
+ nla_nest_cancel(skb, ac_start);
+ nla_nest_cancel(skb, start);
+ } else {
+ nla_nest_end(skb, ac_start);
+ nla_nest_end(skb, start);
+ }
+
+ return err;
+}
+
+static int clone_action_to_attr(const struct nlattr *attr,
+ struct sk_buff *skb)
+{
+ struct nlattr *start;
+ int err = 0, rem = nla_len(attr);
+
+ start = nla_nest_start(skb, OVS_ACTION_ATTR_CLONE);
+ if (!start)
+ return -EMSGSIZE;
+
+ err = ovs_nla_put_actions(nla_data(attr), rem, skb);
+
+ if (err)
+ nla_nest_cancel(skb, start);
+ else
+ nla_nest_end(skb, start);
+
+ return err;
+}
+
+static int check_pkt_len_action_to_attr(const struct nlattr *attr,
+ struct sk_buff *skb)
+{
+ struct nlattr *start, *ac_start = NULL;
+ const struct check_pkt_len_arg *arg;
+ const struct nlattr *a, *cpl_arg;
+ int err = 0, rem = nla_len(attr);
+
+ start = nla_nest_start(skb, OVS_ACTION_ATTR_CHECK_PKT_LEN);
+ if (!start)
+ return -EMSGSIZE;
+
+ /* The first nested attribute in 'attr' is always
+ * 'OVS_CHECK_PKT_LEN_ATTR_ARG'.
+ */
+ cpl_arg = nla_data(attr);
+ arg = nla_data(cpl_arg);
+
+ if (nla_put_u16(skb, OVS_CHECK_PKT_LEN_ATTR_PKT_LEN, arg->pkt_len)) {
+ err = -EMSGSIZE;
+ goto out;
+ }
+
+ /* Second nested attribute in 'attr' is always
+ * 'OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_LESS_EQUAL'.
+ */
+ a = nla_next(cpl_arg, &rem);
+ ac_start = nla_nest_start(skb,
+ OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_LESS_EQUAL);
+ if (!ac_start) {
+ err = -EMSGSIZE;
+ goto out;
+ }
+
+ err = ovs_nla_put_actions(nla_data(a), nla_len(a), skb);
+ if (err) {
+ nla_nest_cancel(skb, ac_start);
+ goto out;
+ } else {
+ nla_nest_end(skb, ac_start);
+ }
+
+ /* Third nested attribute in 'attr' is always
+ * OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_GREATER.
+ */
+ a = nla_next(a, &rem);
+ ac_start = nla_nest_start(skb,
+ OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_GREATER);
+ if (!ac_start) {
+ err = -EMSGSIZE;
+ goto out;
+ }
+
+ err = ovs_nla_put_actions(nla_data(a), nla_len(a), skb);
+ if (err) {
+ nla_nest_cancel(skb, ac_start);
+ goto out;
+ } else {
+ nla_nest_end(skb, ac_start);
}
nla_nest_end(skb, start);
+ return 0;
+
+out:
+ nla_nest_cancel(skb, start);
return err;
}
if (!start)
return -EMSGSIZE;
- err = ipv4_tun_to_nlattr(skb, &tun_info->key,
- tun_info->options_len ?
- ip_tunnel_info_opts(tun_info) : NULL,
- tun_info->options_len);
+ err = ip_tun_to_nlattr(skb, &tun_info->key,
+ ip_tunnel_info_opts(tun_info),
+ tun_info->options_len,
+ ip_tunnel_info_af(tun_info));
if (err)
return err;
nla_nest_end(skb, start);
struct sk_buff *skb)
{
const struct nlattr *ovs_key = nla_data(a);
+ struct nlattr *nla;
size_t key_len = nla_len(ovs_key) / 2;
/* Revert the conversion we did from a non-masked set action to
* masked set action.
*/
- if (nla_put(skb, OVS_ACTION_ATTR_SET, nla_len(a) - key_len, ovs_key))
+ nla = nla_nest_start(skb, OVS_ACTION_ATTR_SET);
+ if (!nla)
return -EMSGSIZE;
+ if (nla_put(skb, nla_type(ovs_key), key_len, nla_data(ovs_key)))
+ return -EMSGSIZE;
+
+ nla_nest_end(skb, nla);
return 0;
}
return err;
break;
+ case OVS_ACTION_ATTR_CLONE:
+ err = clone_action_to_attr(a, skb);
+ if (err)
+ return err;
+ break;
+
+ case OVS_ACTION_ATTR_CHECK_PKT_LEN:
+ err = check_pkt_len_action_to_attr(a, skb);
+ if (err)
+ return err;
+ break;
+
default:
if (nla_put(skb, type, nla_len(a), nla_data(a)))
return -EMSGSIZE;
projects / mirror_ovs.git / blobdiff