/*
- * Copyright (c) 2007-2013 Nicira, Inc.
+ * Copyright (c) 2007-2014 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
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-#include "flow.h"
-#include "datapath.h"
#include <linux/uaccess.h>
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
#include <linux/icmp.h>
#include <linux/icmpv6.h>
#include <linux/rculist.h>
+#include <net/geneve.h>
#include <net/ip.h>
-#include <net/ip_tunnels.h>
#include <net/ipv6.h>
#include <net/ndisc.h>
+#include <net/mpls.h>
+#include "datapath.h"
+#include "flow.h"
#include "flow_netlink.h"
+#include "vport-vxlan.h"
+
+struct ovs_len_tbl {
+ int len;
+ const struct ovs_len_tbl *next;
+};
-static void update_range__(struct sw_flow_match *match,
- size_t offset, size_t size, bool is_mask)
+#define OVS_ATTR_NESTED -1
+
+static void update_range(struct sw_flow_match *match,
+ size_t offset, size_t size, bool is_mask)
{
- struct sw_flow_key_range *range = NULL;
+ struct sw_flow_key_range *range;
size_t start = rounddown(offset, sizeof(long));
size_t end = roundup(offset + size, sizeof(long));
if (!is_mask)
range = &match->range;
- else if (match->mask)
+ else
range = &match->mask->range;
- if (!range)
- return;
-
if (range->start == range->end) {
range->start = start;
range->end = end;
#define SW_FLOW_KEY_PUT(match, field, value, is_mask) \
do { \
- update_range__(match, offsetof(struct sw_flow_key, field), \
- sizeof((match)->key->field), is_mask); \
- if (is_mask) { \
- if ((match)->mask) \
- (match)->mask->key.field = value; \
- } else { \
+ update_range(match, offsetof(struct sw_flow_key, field), \
+ sizeof((match)->key->field), is_mask); \
+ if (is_mask) \
+ (match)->mask->key.field = value; \
+ else \
(match)->key->field = value; \
- } \
} while (0)
-#define SW_FLOW_KEY_MEMCPY(match, field, value_p, len, is_mask) \
- do { \
- update_range__(match, offsetof(struct sw_flow_key, field), \
- len, is_mask); \
- if (is_mask) { \
- if ((match)->mask) \
- memcpy(&(match)->mask->key.field, value_p, len);\
- } else { \
- memcpy(&(match)->key->field, value_p, len); \
- } \
+#define SW_FLOW_KEY_MEMCPY_OFFSET(match, offset, value_p, len, is_mask) \
+ do { \
+ update_range(match, offset, len, is_mask); \
+ if (is_mask) \
+ memcpy((u8 *)&(match)->mask->key + offset, value_p, len);\
+ else \
+ memcpy((u8 *)(match)->key + offset, value_p, len); \
} while (0)
-static u16 range_n_bytes(const struct sw_flow_key_range *range)
-{
- return range->end - range->start;
-}
+#define SW_FLOW_KEY_MEMCPY(match, field, value_p, len, is_mask) \
+ SW_FLOW_KEY_MEMCPY_OFFSET(match, offsetof(struct sw_flow_key, field), \
+ value_p, len, is_mask)
+
+#define SW_FLOW_KEY_MEMSET_FIELD(match, field, value, is_mask) \
+ do { \
+ update_range(match, offsetof(struct sw_flow_key, field), \
+ sizeof((match)->key->field), is_mask); \
+ if (is_mask) \
+ memset((u8 *)&(match)->mask->key.field, value, \
+ sizeof((match)->mask->key.field)); \
+ else \
+ memset((u8 *)&(match)->key->field, value, \
+ sizeof((match)->key->field)); \
+ } while (0)
static bool match_validate(const struct sw_flow_match *match,
- u64 key_attrs, u64 mask_attrs)
+ u64 key_attrs, u64 mask_attrs, bool log)
{
u64 key_expected = 1ULL << OVS_KEY_ATTR_ETHERNET;
u64 mask_allowed = key_attrs; /* At most allow all key attributes */
/* The following mask attributes allowed only if they
- * pass the validation tests. */
+ * pass the validation tests.
+ */
mask_allowed &= ~((1ULL << OVS_KEY_ATTR_IPV4)
| (1ULL << OVS_KEY_ATTR_IPV6)
| (1ULL << OVS_KEY_ATTR_TCP)
| (1ULL << OVS_KEY_ATTR_ICMP)
| (1ULL << OVS_KEY_ATTR_ICMPV6)
| (1ULL << OVS_KEY_ATTR_ARP)
- | (1ULL << OVS_KEY_ATTR_ND));
+ | (1ULL << OVS_KEY_ATTR_ND)
+ | (1ULL << OVS_KEY_ATTR_MPLS));
/* Always allowed mask fields. */
mask_allowed |= ((1ULL << OVS_KEY_ATTR_TUNNEL)
mask_allowed |= 1ULL << OVS_KEY_ATTR_ARP;
}
+ if (eth_p_mpls(match->key->eth.type)) {
+ key_expected |= 1ULL << OVS_KEY_ATTR_MPLS;
+ if (match->mask && (match->mask->key.eth.type == htons(0xffff)))
+ mask_allowed |= 1ULL << OVS_KEY_ATTR_MPLS;
+ }
+
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)))
htons(NDISC_NEIGHBOUR_SOLICITATION) ||
match->key->tp.src == htons(NDISC_NEIGHBOUR_ADVERTISEMENT)) {
key_expected |= 1ULL << OVS_KEY_ATTR_ND;
- if (match->mask && (match->mask->key.tp.src == htons(0xffff)))
+ if (match->mask && (match->mask->key.tp.src == htons(0xff)))
mask_allowed |= 1ULL << OVS_KEY_ATTR_ND;
}
}
if ((key_attrs & key_expected) != key_expected) {
/* Key attributes check failed. */
- OVS_NLERR("Missing expected key attributes (key_attrs=%llx, expected=%llx).\n",
- (unsigned long long)key_attrs, (unsigned long long)key_expected);
+ OVS_NLERR(log, "Missing key (keys=%llx, expected=%llx)",
+ (unsigned long long)key_attrs,
+ (unsigned long long)key_expected);
return false;
}
if ((mask_attrs & mask_allowed) != mask_attrs) {
/* Mask attributes check failed. */
- OVS_NLERR("Contain more than allowed mask fields (mask_attrs=%llx, mask_allowed=%llx).\n",
- (unsigned long long)mask_attrs, (unsigned long long)mask_allowed);
+ OVS_NLERR(log, "Unexpected mask (mask=%llx, allowed=%llx)",
+ (unsigned long long)mask_attrs,
+ (unsigned long long)mask_allowed);
return false;
}
return true;
}
+size_t ovs_tun_key_attr_size(void)
+{
+ /* 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 */
+ + 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_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 */
+}
+
+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 != 22);
+
+ return nla_total_size(4) /* OVS_KEY_ATTR_PRIORITY */
+ + nla_total_size(0) /* OVS_KEY_ATTR_TUNNEL */
+ + ovs_tun_key_attr_size()
+ + nla_total_size(4) /* OVS_KEY_ATTR_IN_PORT */
+ + 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(12) /* OVS_KEY_ATTR_ETHERNET */
+ + nla_total_size(2) /* OVS_KEY_ATTR_ETHERTYPE */
+ + nla_total_size(4) /* OVS_KEY_ATTR_VLAN */
+ + nla_total_size(0) /* OVS_KEY_ATTR_ENCAP */
+ + 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 */
+}
+
+static const struct ovs_len_tbl ovs_tunnel_key_lens[OVS_TUNNEL_KEY_ATTR_MAX + 1] = {
+ [OVS_TUNNEL_KEY_ATTR_ID] = { .len = sizeof(u64) },
+ [OVS_TUNNEL_KEY_ATTR_IPV4_SRC] = { .len = sizeof(u32) },
+ [OVS_TUNNEL_KEY_ATTR_IPV4_DST] = { .len = sizeof(u32) },
+ [OVS_TUNNEL_KEY_ATTR_TOS] = { .len = 1 },
+ [OVS_TUNNEL_KEY_ATTR_TTL] = { .len = 1 },
+ [OVS_TUNNEL_KEY_ATTR_DONT_FRAGMENT] = { .len = 0 },
+ [OVS_TUNNEL_KEY_ATTR_CSUM] = { .len = 0 },
+ [OVS_TUNNEL_KEY_ATTR_TP_SRC] = { .len = sizeof(u16) },
+ [OVS_TUNNEL_KEY_ATTR_TP_DST] = { .len = sizeof(u16) },
+ [OVS_TUNNEL_KEY_ATTR_OAM] = { .len = 0 },
+ [OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS] = { .len = OVS_ATTR_NESTED },
+ [OVS_TUNNEL_KEY_ATTR_VXLAN_OPTS] = { .len = OVS_ATTR_NESTED },
+};
+
/* The size of the argument for each %OVS_KEY_ATTR_* Netlink attribute. */
-static const int ovs_key_lens[OVS_KEY_ATTR_MAX + 1] = {
- [OVS_KEY_ATTR_ENCAP] = -1,
- [OVS_KEY_ATTR_PRIORITY] = sizeof(u32),
- [OVS_KEY_ATTR_IN_PORT] = sizeof(u32),
- [OVS_KEY_ATTR_SKB_MARK] = sizeof(u32),
- [OVS_KEY_ATTR_ETHERNET] = sizeof(struct ovs_key_ethernet),
- [OVS_KEY_ATTR_VLAN] = sizeof(__be16),
- [OVS_KEY_ATTR_ETHERTYPE] = sizeof(__be16),
- [OVS_KEY_ATTR_IPV4] = sizeof(struct ovs_key_ipv4),
- [OVS_KEY_ATTR_IPV6] = sizeof(struct ovs_key_ipv6),
- [OVS_KEY_ATTR_TCP] = sizeof(struct ovs_key_tcp),
- [OVS_KEY_ATTR_TCP_FLAGS] = sizeof(__be16),
- [OVS_KEY_ATTR_UDP] = sizeof(struct ovs_key_udp),
- [OVS_KEY_ATTR_SCTP] = sizeof(struct ovs_key_sctp),
- [OVS_KEY_ATTR_ICMP] = sizeof(struct ovs_key_icmp),
- [OVS_KEY_ATTR_ICMPV6] = sizeof(struct ovs_key_icmpv6),
- [OVS_KEY_ATTR_ARP] = sizeof(struct ovs_key_arp),
- [OVS_KEY_ATTR_ND] = sizeof(struct ovs_key_nd),
- [OVS_KEY_ATTR_DP_HASH] = sizeof(u32),
- [OVS_KEY_ATTR_RECIRC_ID] = sizeof(u32),
- [OVS_KEY_ATTR_TUNNEL] = -1,
+static const struct ovs_len_tbl ovs_key_lens[OVS_KEY_ATTR_MAX + 1] = {
+ [OVS_KEY_ATTR_ENCAP] = { .len = OVS_ATTR_NESTED },
+ [OVS_KEY_ATTR_PRIORITY] = { .len = sizeof(u32) },
+ [OVS_KEY_ATTR_IN_PORT] = { .len = sizeof(u32) },
+ [OVS_KEY_ATTR_SKB_MARK] = { .len = sizeof(u32) },
+ [OVS_KEY_ATTR_ETHERNET] = { .len = sizeof(struct ovs_key_ethernet) },
+ [OVS_KEY_ATTR_VLAN] = { .len = sizeof(__be16) },
+ [OVS_KEY_ATTR_ETHERTYPE] = { .len = sizeof(__be16) },
+ [OVS_KEY_ATTR_IPV4] = { .len = sizeof(struct ovs_key_ipv4) },
+ [OVS_KEY_ATTR_IPV6] = { .len = sizeof(struct ovs_key_ipv6) },
+ [OVS_KEY_ATTR_TCP] = { .len = sizeof(struct ovs_key_tcp) },
+ [OVS_KEY_ATTR_TCP_FLAGS] = { .len = sizeof(__be16) },
+ [OVS_KEY_ATTR_UDP] = { .len = sizeof(struct ovs_key_udp) },
+ [OVS_KEY_ATTR_SCTP] = { .len = sizeof(struct ovs_key_sctp) },
+ [OVS_KEY_ATTR_ICMP] = { .len = sizeof(struct ovs_key_icmp) },
+ [OVS_KEY_ATTR_ICMPV6] = { .len = sizeof(struct ovs_key_icmpv6) },
+ [OVS_KEY_ATTR_ARP] = { .len = sizeof(struct ovs_key_arp) },
+ [OVS_KEY_ATTR_ND] = { .len = sizeof(struct ovs_key_nd) },
+ [OVS_KEY_ATTR_RECIRC_ID] = { .len = sizeof(u32) },
+ [OVS_KEY_ATTR_DP_HASH] = { .len = sizeof(u32) },
+ [OVS_KEY_ATTR_TUNNEL] = { .len = OVS_ATTR_NESTED,
+ .next = ovs_tunnel_key_lens, },
+ [OVS_KEY_ATTR_MPLS] = { .len = sizeof(struct ovs_key_mpls) },
};
static bool is_all_zero(const u8 *fp, size_t size)
static int __parse_flow_nlattrs(const struct nlattr *attr,
const struct nlattr *a[],
- u64 *attrsp, bool nz)
+ u64 *attrsp, bool log, bool nz)
{
const struct nlattr *nla;
u64 attrs;
int expected_len;
if (type > OVS_KEY_ATTR_MAX) {
- OVS_NLERR("Unknown key attribute (type=%d, max=%d).\n",
+ OVS_NLERR(log, "Key type %d is out of range max %d",
type, OVS_KEY_ATTR_MAX);
return -EINVAL;
}
if (attrs & (1ULL << type)) {
- OVS_NLERR("Duplicate key attribute (type %d).\n", type);
+ OVS_NLERR(log, "Duplicate key (type %d).", type);
return -EINVAL;
}
- expected_len = ovs_key_lens[type];
- if (nla_len(nla) != expected_len && expected_len != -1) {
- OVS_NLERR("Key attribute has unexpected length (type=%d"
- ", length=%d, expected=%d).\n", type,
- nla_len(nla), expected_len);
+ expected_len = ovs_key_lens[type].len;
+ if (nla_len(nla) != expected_len && expected_len != OVS_ATTR_NESTED) {
+ OVS_NLERR(log, "Key %d has unexpected len %d expected %d",
+ type, nla_len(nla), expected_len);
return -EINVAL;
}
}
}
if (rem) {
- OVS_NLERR("Message has %d unknown bytes.\n", rem);
+ OVS_NLERR(log, "Message has %d unknown bytes.", rem);
return -EINVAL;
}
}
static int parse_flow_mask_nlattrs(const struct nlattr *attr,
- const struct nlattr *a[], u64 *attrsp)
+ const struct nlattr *a[], u64 *attrsp,
+ bool log)
{
- return __parse_flow_nlattrs(attr, a, attrsp, true);
+ return __parse_flow_nlattrs(attr, a, attrsp, log, true);
}
static int parse_flow_nlattrs(const struct nlattr *attr,
- const struct nlattr *a[], u64 *attrsp)
+ const struct nlattr *a[], u64 *attrsp,
+ bool log)
{
- return __parse_flow_nlattrs(attr, a, attrsp, false);
+ return __parse_flow_nlattrs(attr, a, attrsp, log, false);
+}
+
+static int genev_tun_opt_from_nlattr(const struct nlattr *a,
+ struct sw_flow_match *match, bool is_mask,
+ bool log)
+{
+ unsigned long opt_key_offset;
+
+ if (nla_len(a) > sizeof(match->key->tun_opts)) {
+ OVS_NLERR(log, "Geneve option length err (len %d, max %zu).",
+ nla_len(a), sizeof(match->key->tun_opts));
+ return -EINVAL;
+ }
+
+ if (nla_len(a) % 4 != 0) {
+ OVS_NLERR(log, "Geneve opt len %d is not a multiple of 4.",
+ nla_len(a));
+ return -EINVAL;
+ }
+
+ /* We need to record the length of the options passed
+ * down, otherwise packets with the same format but
+ * additional options will be silently matched.
+ */
+ if (!is_mask) {
+ SW_FLOW_KEY_PUT(match, tun_opts_len, nla_len(a),
+ false);
+ } else {
+ /* This is somewhat unusual because it looks at
+ * both the key and mask while parsing the
+ * attributes (and by extension assumes the key
+ * is parsed first). Normally, we would verify
+ * that each is the correct length and that the
+ * attributes line up in the validate function.
+ * However, that is difficult because this is
+ * variable length and we won't have the
+ * information later.
+ */
+ if (match->key->tun_opts_len != nla_len(a)) {
+ OVS_NLERR(log, "Geneve option len %d != mask len %d",
+ match->key->tun_opts_len, nla_len(a));
+ return -EINVAL;
+ }
+
+ 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 const struct nla_policy vxlan_opt_policy[OVS_VXLAN_EXT_MAX + 1] = {
+ [OVS_VXLAN_EXT_GBP] = { .type = NLA_U32 },
+};
+
+static int vxlan_tun_opt_from_nlattr(const struct nlattr *a,
+ struct sw_flow_match *match, bool is_mask,
+ bool log)
+{
+ struct nlattr *tb[OVS_VXLAN_EXT_MAX+1];
+ unsigned long opt_key_offset;
+ struct ovs_vxlan_opts opts;
+ int err;
+
+ BUILD_BUG_ON(sizeof(opts) > sizeof(match->key->tun_opts));
+
+ err = nla_parse_nested(tb, OVS_VXLAN_EXT_MAX, a, vxlan_opt_policy);
+ if (err < 0)
+ return err;
+
+ memset(&opts, 0, sizeof(opts));
+
+ if (tb[OVS_VXLAN_EXT_GBP])
+ opts.gbp = nla_get_u32(tb[OVS_VXLAN_EXT_GBP]);
+
+ if (!is_mask)
+ SW_FLOW_KEY_PUT(match, tun_opts_len, sizeof(opts), false);
+ else
+ SW_FLOW_KEY_PUT(match, tun_opts_len, 0xff, true);
+
+ opt_key_offset = TUN_METADATA_OFFSET(sizeof(opts));
+ SW_FLOW_KEY_MEMCPY_OFFSET(match, opt_key_offset, &opts, sizeof(opts),
+ is_mask);
+ return 0;
}
static int ipv4_tun_from_nlattr(const struct nlattr *attr,
- struct sw_flow_match *match, bool is_mask)
+ struct sw_flow_match *match, bool is_mask,
+ bool log)
{
struct nlattr *a;
int rem;
bool ttl = false;
__be16 tun_flags = 0;
+ int opts_type = 0;
nla_for_each_nested(a, attr, rem) {
int type = nla_type(a);
- static const u32 ovs_tunnel_key_lens[OVS_TUNNEL_KEY_ATTR_MAX + 1] = {
- [OVS_TUNNEL_KEY_ATTR_ID] = sizeof(u64),
- [OVS_TUNNEL_KEY_ATTR_IPV4_SRC] = sizeof(u32),
- [OVS_TUNNEL_KEY_ATTR_IPV4_DST] = sizeof(u32),
- [OVS_TUNNEL_KEY_ATTR_TOS] = 1,
- [OVS_TUNNEL_KEY_ATTR_TTL] = 1,
- [OVS_TUNNEL_KEY_ATTR_DONT_FRAGMENT] = 0,
- [OVS_TUNNEL_KEY_ATTR_CSUM] = 0,
- [OVS_TUNNEL_KEY_ATTR_OAM] = 0,
- };
+ int err;
if (type > OVS_TUNNEL_KEY_ATTR_MAX) {
- OVS_NLERR("Unknown IPv4 tunnel attribute (type=%d, max=%d).\n",
- type, OVS_TUNNEL_KEY_ATTR_MAX);
+ OVS_NLERR(log, "Tunnel attr %d out of range max %d",
+ type, OVS_TUNNEL_KEY_ATTR_MAX);
return -EINVAL;
}
- if (ovs_tunnel_key_lens[type] != nla_len(a)) {
- OVS_NLERR("IPv4 tunnel attribute type has unexpected "
- " length (type=%d, length=%d, expected=%d).\n",
- type, nla_len(a), ovs_tunnel_key_lens[type]);
+ if (ovs_tunnel_key_lens[type].len != nla_len(a) &&
+ ovs_tunnel_key_lens[type].len != OVS_ATTR_NESTED) {
+ OVS_NLERR(log, "Tunnel attr %d has unexpected len %d expected %d",
+ type, nla_len(a), ovs_tunnel_key_lens[type].len);
return -EINVAL;
}
case OVS_TUNNEL_KEY_ATTR_CSUM:
tun_flags |= TUNNEL_CSUM;
break;
+ case OVS_TUNNEL_KEY_ATTR_TP_SRC:
+ SW_FLOW_KEY_PUT(match, tun_key.tp_src,
+ nla_get_be16(a), is_mask);
+ break;
+ case OVS_TUNNEL_KEY_ATTR_TP_DST:
+ SW_FLOW_KEY_PUT(match, tun_key.tp_dst,
+ nla_get_be16(a), is_mask);
+ break;
case OVS_TUNNEL_KEY_ATTR_OAM:
tun_flags |= TUNNEL_OAM;
break;
+ case OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS:
+ if (opts_type) {
+ OVS_NLERR(log, "Multiple metadata blocks provided");
+ return -EINVAL;
+ }
+
+ err = genev_tun_opt_from_nlattr(a, match, is_mask, log);
+ if (err)
+ return err;
+
+ tun_flags |= TUNNEL_GENEVE_OPT;
+ opts_type = type;
+ break;
+ case OVS_TUNNEL_KEY_ATTR_VXLAN_OPTS:
+ if (opts_type) {
+ OVS_NLERR(log, "Multiple metadata blocks provided");
+ return -EINVAL;
+ }
+
+ err = vxlan_tun_opt_from_nlattr(a, match, is_mask, log);
+ if (err)
+ return err;
+
+ tun_flags |= TUNNEL_VXLAN_OPT;
+ opts_type = type;
+ break;
default:
+ OVS_NLERR(log, "Unknown IPv4 tunnel attribute %d",
+ type);
return -EINVAL;
}
}
SW_FLOW_KEY_PUT(match, tun_key.tun_flags, tun_flags, is_mask);
if (rem > 0) {
- OVS_NLERR("IPv4 tunnel attribute has %d unknown bytes.\n", rem);
+ OVS_NLERR(log, "IPv4 tunnel attribute has %d unknown bytes.",
+ rem);
return -EINVAL;
}
if (!is_mask) {
if (!match->key->tun_key.ipv4_dst) {
- OVS_NLERR("IPv4 tunnel destination address is zero.\n");
+ OVS_NLERR(log, "IPv4 tunnel dst address is zero");
return -EINVAL;
}
if (!ttl) {
- OVS_NLERR("IPv4 tunnel TTL not specified.\n");
+ OVS_NLERR(log, "IPv4 tunnel TTL not specified.");
return -EINVAL;
}
}
- return 0;
+ return opts_type;
}
-static int ipv4_tun_to_nlattr(struct sk_buff *skb,
- const struct ovs_key_ipv4_tunnel *tun_key,
- const struct ovs_key_ipv4_tunnel *output)
+static int vxlan_opt_to_nlattr(struct sk_buff *skb,
+ const void *tun_opts, int swkey_tun_opts_len)
{
+ const struct ovs_vxlan_opts *opts = tun_opts;
struct nlattr *nla;
- nla = nla_nest_start(skb, OVS_KEY_ATTR_TUNNEL);
+ nla = nla_nest_start(skb, OVS_TUNNEL_KEY_ATTR_VXLAN_OPTS);
if (!nla)
return -EMSGSIZE;
+ if (nla_put_u32(skb, OVS_VXLAN_EXT_GBP, opts->gbp) < 0)
+ return -EMSGSIZE;
+
+ nla_nest_end(skb, nla);
+ return 0;
+}
+
+static int __ipv4_tun_to_nlattr(struct sk_buff *skb,
+ const struct ovs_key_ipv4_tunnel *output,
+ const void *tun_opts, int swkey_tun_opts_len)
+{
if (output->tun_flags & TUNNEL_KEY &&
nla_put_be64(skb, OVS_TUNNEL_KEY_ATTR_ID, output->tun_id))
return -EMSGSIZE;
if (output->ipv4_src &&
- nla_put_be32(skb, OVS_TUNNEL_KEY_ATTR_IPV4_SRC, output->ipv4_src))
+ nla_put_be32(skb, OVS_TUNNEL_KEY_ATTR_IPV4_SRC, output->ipv4_src))
return -EMSGSIZE;
if (output->ipv4_dst &&
- nla_put_be32(skb, OVS_TUNNEL_KEY_ATTR_IPV4_DST, output->ipv4_dst))
+ nla_put_be32(skb, OVS_TUNNEL_KEY_ATTR_IPV4_DST, output->ipv4_dst))
return -EMSGSIZE;
if (output->ipv4_tos &&
- nla_put_u8(skb, OVS_TUNNEL_KEY_ATTR_TOS, output->ipv4_tos))
+ nla_put_u8(skb, OVS_TUNNEL_KEY_ATTR_TOS, output->ipv4_tos))
return -EMSGSIZE;
if (nla_put_u8(skb, OVS_TUNNEL_KEY_ATTR_TTL, output->ipv4_ttl))
return -EMSGSIZE;
if ((output->tun_flags & TUNNEL_DONT_FRAGMENT) &&
- nla_put_flag(skb, OVS_TUNNEL_KEY_ATTR_DONT_FRAGMENT))
+ nla_put_flag(skb, OVS_TUNNEL_KEY_ATTR_DONT_FRAGMENT))
return -EMSGSIZE;
if ((output->tun_flags & TUNNEL_CSUM) &&
- nla_put_flag(skb, OVS_TUNNEL_KEY_ATTR_CSUM))
+ nla_put_flag(skb, OVS_TUNNEL_KEY_ATTR_CSUM))
+ return -EMSGSIZE;
+ if (output->tp_src &&
+ nla_put_be16(skb, OVS_TUNNEL_KEY_ATTR_TP_SRC, output->tp_src))
+ return -EMSGSIZE;
+ if (output->tp_dst &&
+ nla_put_be16(skb, OVS_TUNNEL_KEY_ATTR_TP_DST, output->tp_dst))
return -EMSGSIZE;
if ((output->tun_flags & TUNNEL_OAM) &&
- nla_put_flag(skb, OVS_TUNNEL_KEY_ATTR_OAM))
+ nla_put_flag(skb, OVS_TUNNEL_KEY_ATTR_OAM))
return -EMSGSIZE;
+ if (tun_opts) {
+ if (output->tun_flags & TUNNEL_GENEVE_OPT &&
+ nla_put(skb, OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS,
+ swkey_tun_opts_len, tun_opts))
+ return -EMSGSIZE;
+ else if (output->tun_flags & TUNNEL_VXLAN_OPT &&
+ vxlan_opt_to_nlattr(skb, tun_opts, swkey_tun_opts_len))
+ return -EMSGSIZE;
+ }
+
+ return 0;
+}
+
+static int ipv4_tun_to_nlattr(struct sk_buff *skb,
+ const struct ovs_key_ipv4_tunnel *output,
+ const void *tun_opts, int swkey_tun_opts_len)
+{
+ struct nlattr *nla;
+ int err;
+
+ nla = nla_nest_start(skb, OVS_KEY_ATTR_TUNNEL);
+ if (!nla)
+ return -EMSGSIZE;
+
+ err = __ipv4_tun_to_nlattr(skb, output, tun_opts, swkey_tun_opts_len);
+ if (err)
+ return err;
nla_nest_end(skb, nla);
return 0;
}
+int ovs_nla_put_egress_tunnel_key(struct sk_buff *skb,
+ const struct ovs_tunnel_info *egress_tun_info)
+{
+ return __ipv4_tun_to_nlattr(skb, &egress_tun_info->tunnel,
+ egress_tun_info->options,
+ egress_tun_info->options_len);
+}
static int metadata_from_nlattrs(struct sw_flow_match *match, u64 *attrs,
- const struct nlattr **a, bool is_mask)
+ const struct nlattr **a, bool is_mask,
+ bool log)
{
if (*attrs & (1ULL << OVS_KEY_ATTR_DP_HASH)) {
u32 hash_val = nla_get_u32(a[OVS_KEY_ATTR_DP_HASH]);
if (*attrs & (1ULL << OVS_KEY_ATTR_IN_PORT)) {
u32 in_port = nla_get_u32(a[OVS_KEY_ATTR_IN_PORT]);
- if (is_mask)
+ if (is_mask) {
in_port = 0xffffffff; /* Always exact match in_port. */
- else if (in_port >= DP_MAX_PORTS)
+ } else if (in_port >= DP_MAX_PORTS) {
+ OVS_NLERR(log, "Port %d exceeds max allowable %d",
+ in_port, DP_MAX_PORTS);
return -EINVAL;
+ }
SW_FLOW_KEY_PUT(match, phy.in_port, in_port, is_mask);
*attrs &= ~(1ULL << OVS_KEY_ATTR_IN_PORT);
}
if (*attrs & (1ULL << OVS_KEY_ATTR_TUNNEL)) {
if (ipv4_tun_from_nlattr(a[OVS_KEY_ATTR_TUNNEL], match,
- is_mask))
+ is_mask, log) < 0)
return -EINVAL;
*attrs &= ~(1ULL << OVS_KEY_ATTR_TUNNEL);
}
}
static int ovs_key_from_nlattrs(struct sw_flow_match *match, u64 attrs,
- const struct nlattr **a, bool is_mask)
+ const struct nlattr **a, bool is_mask,
+ bool log)
{
int err;
- u64 orig_attrs = attrs;
- err = metadata_from_nlattrs(match, &attrs, a, is_mask);
+ err = metadata_from_nlattrs(match, &attrs, a, is_mask, log);
if (err)
return err;
tci = nla_get_be16(a[OVS_KEY_ATTR_VLAN]);
if (!(tci & htons(VLAN_TAG_PRESENT))) {
if (is_mask)
- OVS_NLERR("VLAN TCI mask does not have exact match for VLAN_TAG_PRESENT bit.\n");
+ OVS_NLERR(log, "VLAN TCI mask does not have exact match for VLAN_TAG_PRESENT bit.");
else
- OVS_NLERR("VLAN TCI does not have VLAN_TAG_PRESENT bit set.\n");
+ OVS_NLERR(log, "VLAN TCI does not have VLAN_TAG_PRESENT bit set.");
return -EINVAL;
}
SW_FLOW_KEY_PUT(match, eth.tci, tci, is_mask);
attrs &= ~(1ULL << OVS_KEY_ATTR_VLAN);
- } else if (!is_mask)
- SW_FLOW_KEY_PUT(match, eth.tci, htons(0xffff), true);
+ }
if (attrs & (1ULL << OVS_KEY_ATTR_ETHERTYPE)) {
__be16 eth_type;
if (is_mask) {
/* Always exact match EtherType. */
eth_type = htons(0xffff);
- } else if (ntohs(eth_type) < ETH_P_802_3_MIN) {
- OVS_NLERR("EtherType is less than minimum (type=%x, min=%x).\n",
- ntohs(eth_type), ETH_P_802_3_MIN);
+ } 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;
}
ipv4_key = nla_data(a[OVS_KEY_ATTR_IPV4]);
if (!is_mask && ipv4_key->ipv4_frag > OVS_FRAG_TYPE_MAX) {
- OVS_NLERR("Unknown IPv4 fragment type (value=%d, max=%d).\n",
- ipv4_key->ipv4_frag, OVS_FRAG_TYPE_MAX);
+ OVS_NLERR(log, "IPv4 frag type %d is out of range max %d",
+ ipv4_key->ipv4_frag, OVS_FRAG_TYPE_MAX);
return -EINVAL;
}
SW_FLOW_KEY_PUT(match, ip.proto,
ipv6_key = nla_data(a[OVS_KEY_ATTR_IPV6]);
if (!is_mask && ipv6_key->ipv6_frag > OVS_FRAG_TYPE_MAX) {
- OVS_NLERR("Unknown IPv6 fragment type (value=%d, max=%d).\n",
- ipv6_key->ipv6_frag, OVS_FRAG_TYPE_MAX);
+ OVS_NLERR(log, "IPv6 frag type %d is out of range max %d",
+ ipv6_key->ipv6_frag, OVS_FRAG_TYPE_MAX);
+ return -EINVAL;
+ }
+
+ if (!is_mask && ipv6_key->ipv6_label & htonl(0xFFF00000)) {
+ OVS_NLERR(log,
+ "Invalid IPv6 flow label value (value=%x, max=%x).",
+ ntohl(ipv6_key->ipv6_label), (1 << 20) - 1);
return -EINVAL;
}
+
SW_FLOW_KEY_PUT(match, ipv6.label,
ipv6_key->ipv6_label, is_mask);
SW_FLOW_KEY_PUT(match, ip.proto,
arp_key = nla_data(a[OVS_KEY_ATTR_ARP]);
if (!is_mask && (arp_key->arp_op & htons(0xff00))) {
- OVS_NLERR("Unknown ARP opcode (opcode=%d).\n",
+ OVS_NLERR(log, "Unknown ARP opcode (opcode=%d).",
arp_key->arp_op);
return -EINVAL;
}
attrs &= ~(1ULL << OVS_KEY_ATTR_ARP);
}
+ if (attrs & (1ULL << OVS_KEY_ATTR_MPLS)) {
+ const struct ovs_key_mpls *mpls_key;
+
+ mpls_key = nla_data(a[OVS_KEY_ATTR_MPLS]);
+ SW_FLOW_KEY_PUT(match, mpls.top_lse,
+ mpls_key->mpls_lse, is_mask);
+
+ attrs &= ~(1ULL << OVS_KEY_ATTR_MPLS);
+ }
+
if (attrs & (1ULL << OVS_KEY_ATTR_TCP)) {
const struct ovs_key_tcp *tcp_key;
}
if (attrs & (1ULL << OVS_KEY_ATTR_TCP_FLAGS)) {
- if (orig_attrs & (1ULL << OVS_KEY_ATTR_IPV4)) {
- SW_FLOW_KEY_PUT(match, tp.flags,
- nla_get_be16(a[OVS_KEY_ATTR_TCP_FLAGS]),
- is_mask);
- } else {
- SW_FLOW_KEY_PUT(match, tp.flags,
- nla_get_be16(a[OVS_KEY_ATTR_TCP_FLAGS]),
- is_mask);
- }
+ SW_FLOW_KEY_PUT(match, tp.flags,
+ nla_get_be16(a[OVS_KEY_ATTR_TCP_FLAGS]),
+ is_mask);
attrs &= ~(1ULL << OVS_KEY_ATTR_TCP_FLAGS);
}
attrs &= ~(1ULL << OVS_KEY_ATTR_ND);
}
- if (attrs != 0)
+ if (attrs != 0) {
+ OVS_NLERR(log, "Unknown key attributes %llx",
+ (unsigned long long)attrs);
return -EINVAL;
+ }
return 0;
}
-static void sw_flow_mask_set(struct sw_flow_mask *mask,
- struct sw_flow_key_range *range, u8 val)
+static void nlattr_set(struct nlattr *attr, u8 val,
+ const struct ovs_len_tbl *tbl)
{
- u8 *m = (u8 *)&mask->key + range->start;
+ struct nlattr *nla;
+ int rem;
+
+ /* The nlattr stream should already have been validated */
+ nla_for_each_nested(nla, attr, rem) {
+ if (tbl && tbl[nla_type(nla)].len == OVS_ATTR_NESTED)
+ nlattr_set(nla, val, tbl[nla_type(nla)].next);
+ else
+ memset(nla_data(nla), val, nla_len(nla));
+ }
+}
- mask->range = *range;
- memset(m, val, range_n_bytes(range));
+static void mask_set_nlattr(struct nlattr *attr, u8 val)
+{
+ nlattr_set(attr, val, ovs_key_lens);
}
/**
* of this flow.
* @mask: Optional. Netlink attribute holding nested %OVS_KEY_ATTR_* Netlink
* attribute specifies the mask field of the wildcarded flow.
+ * @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.
*/
int ovs_nla_get_match(struct sw_flow_match *match,
- const struct nlattr *key,
- const struct nlattr *mask)
+ const struct nlattr *nla_key,
+ const struct nlattr *nla_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(key, a, &key_attrs);
+ err = parse_flow_nlattrs(nla_key, a, &key_attrs, log);
if (err)
return err;
if (!((key_attrs & (1ULL << OVS_KEY_ATTR_VLAN)) &&
(key_attrs & (1ULL << OVS_KEY_ATTR_ENCAP)))) {
- OVS_NLERR("Invalid Vlan frame.\n");
+ OVS_NLERR(log, "Invalid Vlan frame.");
return -EINVAL;
}
encap_valid = true;
if (tci & htons(VLAN_TAG_PRESENT)) {
- err = parse_flow_nlattrs(encap, a, &key_attrs);
+ 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("Truncated 802.1Q header has non-zero encap attribute.\n");
+ OVS_NLERR(log, "Truncated 802.1Q header has non-zero encap attribute.");
return -EINVAL;
}
} else {
- OVS_NLERR("Encap attribute is set for a non-VLAN frame.\n");
+ OVS_NLERR(log, "Encap attr is set for non-VLAN frame");
return -EINVAL;
}
}
- err = ovs_key_from_nlattrs(match, key_attrs, a, false);
+ err = ovs_key_from_nlattrs(match, key_attrs, a, false, log);
if (err)
return err;
- if (mask) {
- err = parse_flow_mask_nlattrs(mask, a, &mask_attrs);
+ if (match->mask) {
+ if (!nla_mask) {
+ /* Create an exact match mask. We need to set to 0xff
+ * all the 'match->mask' fields that have been touched
+ * in 'match->key'. We cannot simply memset
+ * 'match->mask', because padding bytes and fields not
+ * specified in 'match->key' should be left to 0.
+ * Instead, we use a stream of netlink attributes,
+ * copied from 'key' and set to 0xff.
+ * ovs_key_from_nlattrs() will take care of filling
+ * 'match->mask' appropriately.
+ */
+ newmask = kmemdup(nla_key,
+ nla_total_size(nla_len(nla_key)),
+ GFP_KERNEL);
+ if (!newmask)
+ return -ENOMEM;
+
+ mask_set_nlattr(newmask, 0xff);
+
+ /* The userspace does not send tunnel attributes that
+ * are 0, but we should not wildcard them nonetheless.
+ */
+ if (match->key->tun_key.ipv4_dst)
+ SW_FLOW_KEY_MEMSET_FIELD(match, tun_key,
+ 0xff, true);
+
+ nla_mask = newmask;
+ }
+
+ err = parse_flow_mask_nlattrs(nla_mask, a, &mask_attrs, log);
if (err)
- return err;
+ goto free_newmask;
- if (mask_attrs & 1ULL << OVS_KEY_ATTR_ENCAP) {
+ /* 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("Encap mask attribute is set for non-VLAN frame.\n");
- return -EINVAL;
+ OVS_NLERR(log, "Encap mask attribute is set for non-VLAN frame.");
+ err = -EINVAL;
+ goto free_newmask;
}
mask_attrs &= ~(1ULL << OVS_KEY_ATTR_ENCAP);
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);
+ err = parse_flow_mask_nlattrs(encap, a,
+ &mask_attrs, log);
+ if (err)
+ goto free_newmask;
} else {
- OVS_NLERR("VLAN frames must have an exact match on the TPID (mask=%x).\n",
- ntohs(eth_type));
- return -EINVAL;
+ 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("VLAN tag present bit must have an exact match (tci_mask=%x).\n", ntohs(tci));
- return -EINVAL;
+ OVS_NLERR(log, "VLAN tag present bit must have an exact match (tci_mask=%x).",
+ ntohs(tci));
+ err = -EINVAL;
+ goto free_newmask;
}
}
- err = ovs_key_from_nlattrs(match, mask_attrs, a, true);
+ err = ovs_key_from_nlattrs(match, mask_attrs, a, true, log);
if (err)
- return err;
- } else {
- /* Populate exact match flow's key mask. */
- if (match->mask)
- sw_flow_mask_set(match->mask, &match->range, 0xff);
+ goto free_newmask;
}
- if (!match_validate(match, key_attrs, mask_attrs))
- return -EINVAL;
+ if (!match_validate(match, key_attrs, mask_attrs, log))
+ err = -EINVAL;
+
+free_newmask:
+ kfree(newmask);
+ return err;
+}
+
+static size_t get_ufid_len(const struct nlattr *attr, bool log)
+{
+ size_t len;
+
+ if (!attr)
+ return 0;
+
+ len = nla_len(attr);
+ if (len < 1 || len > MAX_UFID_LENGTH) {
+ OVS_NLERR(log, "ufid size %u bytes exceeds the range (1, %d)",
+ nla_len(attr), MAX_UFID_LENGTH);
+ return 0;
+ }
+
+ return len;
+}
+
+/* Initializes 'flow->ufid', returning true if 'attr' contains a valid UFID,
+ * or false otherwise.
+ */
+bool ovs_nla_get_ufid(struct sw_flow_id *sfid, const struct nlattr *attr,
+ bool log)
+{
+ sfid->ufid_len = get_ufid_len(attr, log);
+ if (sfid->ufid_len)
+ memcpy(sfid->ufid, nla_data(attr), sfid->ufid_len);
+
+ return sfid->ufid_len;
+}
+
+int ovs_nla_get_identifier(struct sw_flow_id *sfid, const struct nlattr *ufid,
+ const struct sw_flow_key *key, bool log)
+{
+ struct sw_flow_key *new_key;
+
+ if (ovs_nla_get_ufid(sfid, ufid, log))
+ return 0;
+
+ /* If UFID was not provided, use unmasked key. */
+ new_key = kmalloc(sizeof(*new_key), GFP_KERNEL);
+ if (!new_key)
+ return -ENOMEM;
+ memcpy(new_key, key, sizeof(*key));
+ sfid->unmasked_key = new_key;
return 0;
}
+u32 ovs_nla_get_ufid_flags(const struct nlattr *attr)
+{
+ return attr ? nla_get_u32(attr) : 0;
+}
+
/**
* ovs_nla_get_flow_metadata - parses Netlink attributes into a flow key.
- * @flow: Receives extracted in_port, priority, tun_key and skb_mark.
+ * @key: Receives extracted in_port, priority, tun_key and skb_mark.
* @attr: Netlink attribute holding nested %OVS_KEY_ATTR_* Netlink attribute
* sequence.
+ * @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.
*
* This parses a series of Netlink attributes that form a flow key, which must
* take the same form accepted by flow_from_nlattrs(), but only enough of it to
* extracted from the packet itself.
*/
-int ovs_nla_get_flow_metadata(struct sw_flow *flow,
- const struct nlattr *attr)
+int ovs_nla_get_flow_metadata(const struct nlattr *attr,
+ struct sw_flow_key *key,
+ bool log)
{
- struct ovs_key_ipv4_tunnel *tun_key = &flow->key.tun_key;
const struct nlattr *a[OVS_KEY_ATTR_MAX + 1];
+ struct sw_flow_match match;
u64 attrs = 0;
int err;
- struct sw_flow_match match;
-
- flow->key.phy.in_port = DP_MAX_PORTS;
- flow->key.phy.priority = 0;
- flow->key.phy.skb_mark = 0;
- flow->key.ovs_flow_hash = 0;
- flow->key.recirc_id = 0;
- memset(tun_key, 0, sizeof(flow->key.tun_key));
- err = parse_flow_nlattrs(attr, a, &attrs);
+ err = parse_flow_nlattrs(attr, a, &attrs, log);
if (err)
return -EINVAL;
memset(&match, 0, sizeof(match));
- match.key = &flow->key;
+ match.key = key;
- err = metadata_from_nlattrs(&match, &attrs, a, false);
- if (err)
- return err;
+ memset(key, 0, OVS_SW_FLOW_KEY_METADATA_SIZE);
+ key->phy.in_port = DP_MAX_PORTS;
- return 0;
+ return metadata_from_nlattrs(&match, &attrs, a, false, log);
}
-int ovs_nla_put_flow(const struct sw_flow_key *swkey,
- const struct sw_flow_key *output, struct sk_buff *skb)
+static int __ovs_nla_put_key(const struct sw_flow_key *swkey,
+ const struct sw_flow_key *output, bool is_mask,
+ struct sk_buff *skb)
{
struct ovs_key_ethernet *eth_key;
struct nlattr *nla, *encap;
- bool is_mask = (swkey != output);
- if (nla_put_u32(skb, OVS_KEY_ATTR_DP_HASH, output->ovs_flow_hash))
+ 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_RECIRC_ID, output->recirc_id))
+ if (nla_put_u32(skb, OVS_KEY_ATTR_DP_HASH, output->ovs_flow_hash))
goto nla_put_failure;
if (nla_put_u32(skb, OVS_KEY_ATTR_PRIORITY, output->phy.priority))
goto nla_put_failure;
- if ((swkey->tun_key.ipv4_dst || is_mask) &&
- ipv4_tun_to_nlattr(skb, &swkey->tun_key, &output->tun_key))
- goto nla_put_failure;
+ if ((swkey->tun_key.ipv4_dst || 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))
+ goto nla_put_failure;
+ }
if (swkey->phy.in_port == DP_MAX_PORTS) {
if (is_mask && (output->phy.in_port == 0xffff))
arp_key->arp_op = htons(output->ip.proto);
ether_addr_copy(arp_key->arp_sha, output->ipv4.arp.sha);
ether_addr_copy(arp_key->arp_tha, output->ipv4.arp.tha);
+ } else if (eth_p_mpls(swkey->eth.type)) {
+ struct ovs_key_mpls *mpls_key;
+
+ nla = nla_reserve(skb, OVS_KEY_ATTR_MPLS, sizeof(*mpls_key));
+ if (!nla)
+ goto nla_put_failure;
+ mpls_key = nla_data(nla);
+ mpls_key->mpls_lse = output->mpls.top_lse;
}
if ((swkey->eth.type == htons(ETH_P_IP) ||
return -EMSGSIZE;
}
+int ovs_nla_put_key(const struct sw_flow_key *swkey,
+ const struct sw_flow_key *output, int attr, bool is_mask,
+ struct sk_buff *skb)
+{
+ int err;
+ struct nlattr *nla;
+
+ nla = nla_nest_start(skb, attr);
+ if (!nla)
+ return -EMSGSIZE;
+ err = __ovs_nla_put_key(swkey, output, is_mask, skb);
+ if (err)
+ return err;
+ nla_nest_end(skb, nla);
+
+ return 0;
+}
+
+/* Called with ovs_mutex or RCU read lock. */
+int ovs_nla_put_identifier(const struct sw_flow *flow, struct sk_buff *skb)
+{
+ if (ovs_identifier_is_ufid(&flow->id))
+ return nla_put(skb, OVS_FLOW_ATTR_UFID, flow->id.ufid_len,
+ flow->id.ufid);
+
+ return ovs_nla_put_key(flow->id.unmasked_key, flow->id.unmasked_key,
+ OVS_FLOW_ATTR_KEY, false, skb);
+}
+
+/* Called with ovs_mutex or RCU read lock. */
+int ovs_nla_put_masked_key(const struct sw_flow *flow, struct sk_buff *skb)
+{
+ return ovs_nla_put_key(&flow->key, &flow->key,
+ OVS_FLOW_ATTR_KEY, false, skb);
+}
+
+/* Called with ovs_mutex or RCU read lock. */
+int ovs_nla_put_mask(const struct sw_flow *flow, struct sk_buff *skb)
+{
+ return ovs_nla_put_key(&flow->key, &flow->mask->key,
+ OVS_FLOW_ATTR_MASK, true, skb);
+}
+
#define MAX_ACTIONS_BUFSIZE (32 * 1024)
-struct sw_flow_actions *ovs_nla_alloc_flow_actions(int size)
+static struct sw_flow_actions *nla_alloc_flow_actions(int size, bool log)
{
struct sw_flow_actions *sfa;
- if (size > MAX_ACTIONS_BUFSIZE)
+ if (size > MAX_ACTIONS_BUFSIZE) {
+ OVS_NLERR(log, "Flow action size %u bytes exceeds max", size);
return ERR_PTR(-EINVAL);
+ }
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(struct sw_flow_actions *sf_acts)
{
call_rcu(&sf_acts->rcu, rcu_free_acts_callback);
}
static struct nlattr *reserve_sfa_size(struct sw_flow_actions **sfa,
- int attr_len)
+ int attr_len, bool log)
{
struct sw_flow_actions *acts;
new_acts_size = MAX_ACTIONS_BUFSIZE;
}
- acts = ovs_nla_alloc_flow_actions(new_acts_size);
+ acts = nla_alloc_flow_actions(new_acts_size, log);
if (IS_ERR(acts))
return (void *)acts;
return (struct nlattr *) ((unsigned char *)(*sfa) + next_offset);
}
-static struct nlattr *__add_action(struct sw_flow_actions **sfa, int attrtype,
- void *data, int len)
+static struct nlattr *__add_action(struct sw_flow_actions **sfa,
+ int attrtype, void *data, int len, bool log)
{
struct nlattr *a;
- a = reserve_sfa_size(sfa, nla_attr_size(len));
+ a = reserve_sfa_size(sfa, nla_attr_size(len), log);
if (IS_ERR(a))
return a;
}
static int add_action(struct sw_flow_actions **sfa, int attrtype,
- void *data, int len)
+ void *data, int len, bool log)
{
struct nlattr *a;
- a = __add_action(sfa, attrtype, data, len);
+ a = __add_action(sfa, attrtype, data, len, log);
if (IS_ERR(a))
return PTR_ERR(a);
}
static inline int add_nested_action_start(struct sw_flow_actions **sfa,
- int attrtype)
+ int attrtype, bool log)
{
int used = (*sfa)->actions_len;
int err;
- err = add_action(sfa, attrtype, NULL, 0);
+ err = add_action(sfa, attrtype, NULL, 0, log);
if (err)
return err;
a->nla_len = sfa->actions_len - st_offset;
}
+static int __ovs_nla_copy_actions(const struct nlattr *attr,
+ const struct sw_flow_key *key,
+ int depth, struct sw_flow_actions **sfa,
+ __be16 eth_type, __be16 vlan_tci, bool log);
+
static int validate_and_copy_sample(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)
{
const struct nlattr *attrs[OVS_SAMPLE_ATTR_MAX + 1];
const struct nlattr *probability, *actions;
return -EINVAL;
/* validation done, copy sample action. */
- start = add_nested_action_start(sfa, OVS_ACTION_ATTR_SAMPLE);
+ start = add_nested_action_start(sfa, OVS_ACTION_ATTR_SAMPLE, log);
if (start < 0)
return start;
err = add_action(sfa, OVS_SAMPLE_ATTR_PROBABILITY,
- nla_data(probability), sizeof(u32));
+ nla_data(probability), sizeof(u32), log);
if (err)
return err;
- st_acts = add_nested_action_start(sfa, OVS_SAMPLE_ATTR_ACTIONS);
+ st_acts = add_nested_action_start(sfa, OVS_SAMPLE_ATTR_ACTIONS, log);
if (st_acts < 0)
return st_acts;
- err = ovs_nla_copy_actions(actions, key, depth + 1, sfa);
+ err = __ovs_nla_copy_actions(actions, key, depth + 1, sfa,
+ eth_type, vlan_tci, log);
if (err)
return err;
return 0;
}
-static int validate_tp_port(const struct sw_flow_key *flow_key)
-{
- if ((flow_key->eth.type == htons(ETH_P_IP) ||
- flow_key->eth.type == htons(ETH_P_IPV6)) &&
- (flow_key->tp.src || flow_key->tp.dst))
- return 0;
-
- return -EINVAL;
-}
-
void ovs_match_init(struct sw_flow_match *match,
struct sw_flow_key *key,
struct sw_flow_mask *mask)
}
}
+static int validate_geneve_opts(struct sw_flow_key *key)
+{
+ struct geneve_opt *option;
+ int opts_len = key->tun_opts_len;
+ bool crit_opt = false;
+
+ option = (struct geneve_opt *)TUN_METADATA_OPTS(key, key->tun_opts_len);
+ while (opts_len > 0) {
+ int len;
+
+ if (opts_len < sizeof(*option))
+ return -EINVAL;
+
+ len = sizeof(*option) + option->length * 4;
+ if (len > opts_len)
+ return -EINVAL;
+
+ crit_opt |= !!(option->type & GENEVE_CRIT_OPT_TYPE);
+
+ option = (struct geneve_opt *)((u8 *)option + len);
+ opts_len -= len;
+ };
+
+ key->tun_key.tun_flags |= crit_opt ? TUNNEL_CRIT_OPT : 0;
+
+ return 0;
+}
+
static int validate_and_copy_set_tun(const struct nlattr *attr,
- struct sw_flow_actions **sfa)
+ struct sw_flow_actions **sfa, bool log)
{
struct sw_flow_match match;
struct sw_flow_key key;
struct ovs_tunnel_info *tun_info;
struct nlattr *a;
- int err, start;
+ int start, opts_type;
+ int err = 0;
ovs_match_init(&match, &key, NULL);
- err = ipv4_tun_from_nlattr(nla_data(attr), &match, false);
- if (err)
- return err;
+ opts_type = ipv4_tun_from_nlattr(nla_data(attr), &match, false, log);
+ if (opts_type < 0)
+ return opts_type;
+
+ if (key.tun_opts_len) {
+ switch (opts_type) {
+ case OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS:
+ err = validate_geneve_opts(&key);
+ if (err < 0)
+ return err;
+ break;
+ case OVS_TUNNEL_KEY_ATTR_VXLAN_OPTS:
+ break;
+ }
+ };
- start = add_nested_action_start(sfa, OVS_ACTION_ATTR_SET);
+ start = add_nested_action_start(sfa, OVS_ACTION_ATTR_SET, log);
if (start < 0)
return start;
a = __add_action(sfa, OVS_KEY_ATTR_TUNNEL_INFO, NULL,
- sizeof(*tun_info));
+ sizeof(*tun_info) + key.tun_opts_len, log);
if (IS_ERR(a))
return PTR_ERR(a);
tun_info = nla_data(a);
tun_info->tunnel = key.tun_key;
+ tun_info->options_len = key.tun_opts_len;
+
+ if (tun_info->options_len) {
+ /* We need to store the options in the action itself since
+ * everything else will go away after flow setup. We can append
+ * it to tun_info and then point there.
+ */
+ memcpy((tun_info + 1),
+ TUN_METADATA_OPTS(&key, key.tun_opts_len), key.tun_opts_len);
+ tun_info->options = (tun_info + 1);
+ } else {
+ tun_info->options = NULL;
+ }
add_nested_action_end(*sfa, start);
return err;
}
+/* Return false if there are any non-masked bits set.
+ * Mask follows data immediately, before any netlink padding.
+ */
+static bool validate_masked(u8 *data, int len)
+{
+ u8 *mask = data + len;
+
+ while (len--)
+ if (*data++ & ~*mask++)
+ return false;
+
+ return true;
+}
+
static int validate_set(const struct nlattr *a,
const struct sw_flow_key *flow_key,
struct sw_flow_actions **sfa,
- bool *set_tun)
+ bool *skip_copy, __be16 eth_type, bool masked, bool log)
{
const struct nlattr *ovs_key = nla_data(a);
int key_type = nla_type(ovs_key);
+ size_t key_len;
/* There can be only one key in a action */
if (nla_total_size(nla_len(ovs_key)) != nla_len(a))
return -EINVAL;
+ key_len = nla_len(ovs_key);
+ if (masked)
+ key_len /= 2;
+
if (key_type > OVS_KEY_ATTR_MAX ||
- (ovs_key_lens[key_type] != nla_len(ovs_key) &&
- ovs_key_lens[key_type] != -1))
+ (ovs_key_lens[key_type].len != key_len &&
+ ovs_key_lens[key_type].len != OVS_ATTR_NESTED))
+ return -EINVAL;
+
+ if (masked && !validate_masked(nla_data(ovs_key), key_len))
return -EINVAL;
switch (key_type) {
break;
case OVS_KEY_ATTR_TUNNEL:
- *set_tun = true;
- err = validate_and_copy_set_tun(a, sfa);
+ if (eth_p_mpls(eth_type))
+ return -EINVAL;
+
+ if (masked)
+ return -EINVAL; /* Masked tunnel set not supported. */
+
+ *skip_copy = true;
+ err = validate_and_copy_set_tun(a, sfa, log);
if (err)
return err;
break;
case OVS_KEY_ATTR_IPV4:
- if (flow_key->eth.type != htons(ETH_P_IP))
- return -EINVAL;
-
- if (!flow_key->ip.proto)
+ if (eth_type != htons(ETH_P_IP))
return -EINVAL;
ipv4_key = nla_data(ovs_key);
- if (ipv4_key->ipv4_proto != flow_key->ip.proto)
- return -EINVAL;
- if (ipv4_key->ipv4_frag != flow_key->ip.frag)
- return -EINVAL;
+ if (masked) {
+ const struct ovs_key_ipv4 *mask = ipv4_key + 1;
+ /* Non-writeable fields. */
+ if (mask->ipv4_proto || mask->ipv4_frag)
+ return -EINVAL;
+ } else {
+ if (ipv4_key->ipv4_proto != flow_key->ip.proto)
+ return -EINVAL;
+
+ if (ipv4_key->ipv4_frag != flow_key->ip.frag)
+ return -EINVAL;
+ }
break;
case OVS_KEY_ATTR_IPV6:
- if (flow_key->eth.type != htons(ETH_P_IPV6))
- return -EINVAL;
-
- if (!flow_key->ip.proto)
+ if (eth_type != htons(ETH_P_IPV6))
return -EINVAL;
ipv6_key = nla_data(ovs_key);
- if (ipv6_key->ipv6_proto != flow_key->ip.proto)
- return -EINVAL;
- if (ipv6_key->ipv6_frag != flow_key->ip.frag)
- return -EINVAL;
+ if (masked) {
+ const struct ovs_key_ipv6 *mask = ipv6_key + 1;
+ /* Non-writeable fields. */
+ if (mask->ipv6_proto || mask->ipv6_frag)
+ return -EINVAL;
+
+ /* Invalid bits in the flow label mask? */
+ if (ntohl(mask->ipv6_label) & 0xFFF00000)
+ return -EINVAL;
+ } else {
+ if (ipv6_key->ipv6_proto != flow_key->ip.proto)
+ return -EINVAL;
+
+ if (ipv6_key->ipv6_frag != flow_key->ip.frag)
+ return -EINVAL;
+ }
if (ntohl(ipv6_key->ipv6_label) & 0xFFF00000)
return -EINVAL;
break;
case OVS_KEY_ATTR_TCP:
- if (flow_key->ip.proto != IPPROTO_TCP)
+ if ((eth_type != htons(ETH_P_IP) &&
+ eth_type != htons(ETH_P_IPV6)) ||
+ flow_key->ip.proto != IPPROTO_TCP)
return -EINVAL;
- return validate_tp_port(flow_key);
+ break;
case OVS_KEY_ATTR_UDP:
- if (flow_key->ip.proto != IPPROTO_UDP)
+ if ((eth_type != htons(ETH_P_IP) &&
+ eth_type != htons(ETH_P_IPV6)) ||
+ flow_key->ip.proto != IPPROTO_UDP)
return -EINVAL;
- return validate_tp_port(flow_key);
+ break;
+
+ case OVS_KEY_ATTR_MPLS:
+ if (!eth_p_mpls(eth_type))
+ return -EINVAL;
+ break;
case OVS_KEY_ATTR_SCTP:
- if (flow_key->ip.proto != IPPROTO_SCTP)
+ if ((eth_type != htons(ETH_P_IP) &&
+ eth_type != htons(ETH_P_IPV6)) ||
+ flow_key->ip.proto != IPPROTO_SCTP)
return -EINVAL;
- return validate_tp_port(flow_key);
+ break;
default:
return -EINVAL;
}
+ /* Convert non-masked non-tunnel set actions to masked set actions. */
+ if (!masked && key_type != OVS_KEY_ATTR_TUNNEL) {
+ int start, len = key_len * 2;
+ struct nlattr *at;
+
+ *skip_copy = true;
+
+ start = add_nested_action_start(sfa,
+ OVS_ACTION_ATTR_SET_TO_MASKED,
+ log);
+ if (start < 0)
+ return start;
+
+ at = __add_action(sfa, key_type, NULL, len, log);
+ if (IS_ERR(at))
+ return PTR_ERR(at);
+
+ memcpy(nla_data(at), nla_data(ovs_key), key_len); /* Key. */
+ memset(nla_data(at) + key_len, 0xff, key_len); /* Mask. */
+ /* Clear non-writeable bits from otherwise writeable fields. */
+ if (key_type == OVS_KEY_ATTR_IPV6) {
+ struct ovs_key_ipv6 *mask = nla_data(at) + key_len;
+
+ mask->ipv6_label &= htonl(0x000FFFFF);
+ }
+ add_nested_action_end(*sfa, start);
+ }
+
return 0;
}
static const struct nla_policy userspace_policy[OVS_USERSPACE_ATTR_MAX + 1] = {
[OVS_USERSPACE_ATTR_PID] = {.type = NLA_U32 },
[OVS_USERSPACE_ATTR_USERDATA] = {.type = NLA_UNSPEC },
+ [OVS_USERSPACE_ATTR_EGRESS_TUN_PORT] = {.type = NLA_U32 },
};
struct nlattr *a[OVS_USERSPACE_ATTR_MAX + 1];
int error;
}
static int copy_action(const struct nlattr *from,
- struct sw_flow_actions **sfa)
+ struct sw_flow_actions **sfa, bool log)
{
int totlen = NLA_ALIGN(from->nla_len);
struct nlattr *to;
- to = reserve_sfa_size(sfa, from->nla_len);
+ to = reserve_sfa_size(sfa, from->nla_len, log);
if (IS_ERR(to))
return PTR_ERR(to);
return 0;
}
-int ovs_nla_copy_actions(const struct nlattr *attr,
- const struct sw_flow_key *key,
- int depth,
- struct sw_flow_actions **sfa)
+static int __ovs_nla_copy_actions(const struct nlattr *attr,
+ const struct sw_flow_key *key,
+ int depth, struct sw_flow_actions **sfa,
+ __be16 eth_type, __be16 vlan_tci, bool log)
{
const struct nlattr *a;
int rem, err;
[OVS_ACTION_ATTR_OUTPUT] = sizeof(u32),
[OVS_ACTION_ATTR_RECIRC] = sizeof(u32),
[OVS_ACTION_ATTR_USERSPACE] = (u32)-1,
+ [OVS_ACTION_ATTR_PUSH_MPLS] = sizeof(struct ovs_action_push_mpls),
+ [OVS_ACTION_ATTR_POP_MPLS] = sizeof(__be16),
[OVS_ACTION_ATTR_PUSH_VLAN] = sizeof(struct ovs_action_push_vlan),
[OVS_ACTION_ATTR_POP_VLAN] = 0,
[OVS_ACTION_ATTR_SET] = (u32)-1,
+ [OVS_ACTION_ATTR_SET_MASKED] = (u32)-1,
[OVS_ACTION_ATTR_SAMPLE] = (u32)-1,
[OVS_ACTION_ATTR_HASH] = sizeof(struct ovs_action_hash)
};
}
case OVS_ACTION_ATTR_POP_VLAN:
+ vlan_tci = htons(0);
break;
case OVS_ACTION_ATTR_PUSH_VLAN:
return -EINVAL;
if (!(vlan->vlan_tci & htons(VLAN_TAG_PRESENT)))
return -EINVAL;
+ vlan_tci = vlan->vlan_tci;
break;
case OVS_ACTION_ATTR_RECIRC:
break;
+ case OVS_ACTION_ATTR_PUSH_MPLS: {
+ const struct ovs_action_push_mpls *mpls = nla_data(a);
+
+ if (!eth_p_mpls(mpls->mpls_ethertype))
+ return -EINVAL;
+ /* Prohibit push MPLS other than to a white list
+ * for packets that have a known tag order.
+ */
+ if (vlan_tci & htons(VLAN_TAG_PRESENT) ||
+ (eth_type != htons(ETH_P_IP) &&
+ eth_type != htons(ETH_P_IPV6) &&
+ eth_type != htons(ETH_P_ARP) &&
+ eth_type != htons(ETH_P_RARP) &&
+ !eth_p_mpls(eth_type)))
+ return -EINVAL;
+ eth_type = mpls->mpls_ethertype;
+ break;
+ }
+
+ case OVS_ACTION_ATTR_POP_MPLS:
+ if (vlan_tci & htons(VLAN_TAG_PRESENT) ||
+ !eth_p_mpls(eth_type))
+ return -EINVAL;
+
+ /* Disallow subsequent L2.5+ set and mpls_pop actions
+ * as there is no check here to ensure that the new
+ * eth_type is valid and thus set actions could
+ * write off the end of the packet or otherwise
+ * corrupt it.
+ *
+ * Support for these actions is planned using packet
+ * recirculation.
+ */
+ eth_type = htons(0);
+ break;
+
case OVS_ACTION_ATTR_SET:
- err = validate_set(a, key, sfa, &skip_copy);
+ err = validate_set(a, key, sfa,
+ &skip_copy, 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);
if (err)
return err;
break;
case OVS_ACTION_ATTR_SAMPLE:
- err = validate_and_copy_sample(a, key, depth, sfa);
+ err = validate_and_copy_sample(a, key, depth, sfa,
+ eth_type, vlan_tci, log);
if (err)
return err;
skip_copy = true;
break;
default:
+ OVS_NLERR(log, "Unknown Action type %d", type);
return -EINVAL;
}
if (!skip_copy) {
- err = copy_action(a, sfa);
+ err = copy_action(a, sfa, log);
if (err)
return err;
}
return 0;
}
+/* 'key' must be the masked key. */
+int ovs_nla_copy_actions(const struct nlattr *attr,
+ const struct sw_flow_key *key,
+ struct sw_flow_actions **sfa, bool log)
+{
+ int err;
+
+ *sfa = nla_alloc_flow_actions(nla_len(attr), log);
+ if (IS_ERR(*sfa))
+ return PTR_ERR(*sfa);
+
+ err = __ovs_nla_copy_actions(attr, key, 0, sfa, key->eth.type,
+ key->eth.tci, log);
+ if (err)
+ kfree(*sfa);
+
+ return err;
+}
+
static int sample_action_to_attr(const struct nlattr *attr, struct sk_buff *skb)
{
const struct nlattr *a;
return -EMSGSIZE;
err = ipv4_tun_to_nlattr(skb, &tun_info->tunnel,
- &tun_info->tunnel);
+ tun_info->options_len ?
+ tun_info->options : NULL,
+ tun_info->options_len);
if (err)
return err;
nla_nest_end(skb, start);
return 0;
}
+static int masked_set_action_to_set_action_attr(const struct nlattr *a,
+ struct sk_buff *skb)
+{
+ const struct nlattr *ovs_key = nla_data(a);
+ 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))
+ return -EMSGSIZE;
+
+ return 0;
+}
+
int ovs_nla_put_actions(const struct nlattr *attr, int len, struct sk_buff *skb)
{
const struct nlattr *a;
return err;
break;
+ case OVS_ACTION_ATTR_SET_TO_MASKED:
+ err = masked_set_action_to_set_action_attr(a, skb);
+ if (err)
+ return err;
+ break;
+
case OVS_ACTION_ATTR_SAMPLE:
err = sample_action_to_attr(a, skb);
if (err)