1 files changed, 307 insertions, 107 deletions

diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c
index f54cf17ef7a8..66366982f604 100644
--- a/net/openvswitch/flow.c
+++ b/net/openvswitch/flow.c
@@ -1,19 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * 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
- * License as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
- * 02110-1301, USA
  */
 
 #include <linux/uaccess.h>
@@ -47,6 +34,8 @@
 #include <net/mpls.h>
 #include <net/ndisc.h>
 #include <net/nsh.h>
+#include <net/pkt_cls.h>
+#include <net/netfilter/nf_conntrack_zones.h>
 
 #include "conntrack.h"
 #include "datapath.h"
@@ -72,7 +61,7 @@ u64 ovs_flow_used_time(unsigned long flow_jiffies)
 void ovs_flow_stats_update(struct sw_flow *flow, __be16 tcp_flags,
 			   const struct sk_buff *skb)
 {
-	struct flow_stats *stats;
+	struct sw_flow_stats *stats;
 	unsigned int cpu = smp_processor_id();
 	int len = skb->len + (skb_vlan_tag_present(skb) ? VLAN_HLEN : 0);
 
@@ -100,7 +89,7 @@ void ovs_flow_stats_update(struct sw_flow *flow, __be16 tcp_flags,
 			if (likely(flow->stats_last_writer != -1) &&
 			    likely(!rcu_access_pointer(flow->stats[cpu]))) {
 				/* Try to allocate CPU-specific stats. */
-				struct flow_stats *new_stats;
+				struct sw_flow_stats *new_stats;
 
 				new_stats =
 					kmem_cache_alloc_node(flow_stats_cache,
@@ -118,7 +107,8 @@ void ovs_flow_stats_update(struct sw_flow *flow, __be16 tcp_flags,
 
 					rcu_assign_pointer(flow->stats[cpu],
 							   new_stats);
-					cpumask_set_cpu(cpu, &flow->cpu_used_mask);
+					cpumask_set_cpu(cpu,
+							flow->cpu_used_mask);
 					goto unlock;
 				}
 			}
@@ -139,15 +129,14 @@ void ovs_flow_stats_get(const struct sw_flow *flow,
 			struct ovs_flow_stats *ovs_stats,
 			unsigned long *used, __be16 *tcp_flags)
 {
-	int cpu;
+	unsigned int cpu;
 
 	*used = 0;
 	*tcp_flags = 0;
 	memset(ovs_stats, 0, sizeof(*ovs_stats));
 
-	/* We open code this to make sure cpu 0 is always considered */
-	for (cpu = 0; cpu < nr_cpu_ids; cpu = cpumask_next(cpu, &flow->cpu_used_mask)) {
-		struct flow_stats *stats = rcu_dereference_ovsl(flow->stats[cpu]);
+	for_each_cpu(cpu, flow->cpu_used_mask) {
+		struct sw_flow_stats *stats = rcu_dereference_ovsl(flow->stats[cpu]);
 
 		if (stats) {
 			/* Local CPU may write on non-local stats, so we must
@@ -167,11 +156,10 @@ void ovs_flow_stats_get(const struct sw_flow *flow,
 /* Called with ovs_mutex. */
 void ovs_flow_stats_clear(struct sw_flow *flow)
 {
-	int cpu;
+	unsigned int cpu;
 
-	/* We open code this to make sure cpu 0 is always considered */
-	for (cpu = 0; cpu < nr_cpu_ids; cpu = cpumask_next(cpu, &flow->cpu_used_mask)) {
-		struct flow_stats *stats = ovsl_dereference(flow->stats[cpu]);
+	for_each_cpu(cpu, flow->cpu_used_mask) {
+		struct sw_flow_stats *stats = ovsl_dereference(flow->stats[cpu]);
 
 		if (stats) {
 			spin_lock_bh(&stats->lock);
@@ -252,6 +240,144 @@ static bool icmphdr_ok(struct sk_buff *skb)
 				  sizeof(struct icmphdr));
 }
 
+/**
+ * get_ipv6_ext_hdrs() - Parses packet and sets IPv6 extension header flags.
+ *
+ * @skb: buffer where extension header data starts in packet
+ * @nh: ipv6 header
+ * @ext_hdrs: flags are stored here
+ *
+ * OFPIEH12_UNREP is set if more than one of a given IPv6 extension header
+ * is unexpectedly encountered. (Two destination options headers may be
+ * expected and would not cause this bit to be set.)
+ *
+ * OFPIEH12_UNSEQ is set if IPv6 extension headers were not in the order
+ * preferred (but not required) by RFC 2460:
+ *
+ * When more than one extension header is used in the same packet, it is
+ * recommended that those headers appear in the following order:
+ *      IPv6 header
+ *      Hop-by-Hop Options header
+ *      Destination Options header
+ *      Routing header
+ *      Fragment header
+ *      Authentication header
+ *      Encapsulating Security Payload header
+ *      Destination Options header
+ *      upper-layer header
+ */
+static void get_ipv6_ext_hdrs(struct sk_buff *skb, struct ipv6hdr *nh,
+			      u16 *ext_hdrs)
+{
+	u8 next_type = nh->nexthdr;
+	unsigned int start = skb_network_offset(skb) + sizeof(struct ipv6hdr);
+	int dest_options_header_count = 0;
+
+	*ext_hdrs = 0;
+
+	while (ipv6_ext_hdr(next_type)) {
+		struct ipv6_opt_hdr _hdr, *hp;
+
+		switch (next_type) {
+		case IPPROTO_NONE:
+			*ext_hdrs |= OFPIEH12_NONEXT;
+			/* stop parsing */
+			return;
+
+		case IPPROTO_ESP:
+			if (*ext_hdrs & OFPIEH12_ESP)
+				*ext_hdrs |= OFPIEH12_UNREP;
+			if ((*ext_hdrs & ~(OFPIEH12_HOP | OFPIEH12_DEST |
+					   OFPIEH12_ROUTER | IPPROTO_FRAGMENT |
+					   OFPIEH12_AUTH | OFPIEH12_UNREP)) ||
+			    dest_options_header_count >= 2) {
+				*ext_hdrs |= OFPIEH12_UNSEQ;
+			}
+			*ext_hdrs |= OFPIEH12_ESP;
+			break;
+
+		case IPPROTO_AH:
+			if (*ext_hdrs & OFPIEH12_AUTH)
+				*ext_hdrs |= OFPIEH12_UNREP;
+			if ((*ext_hdrs &
+			     ~(OFPIEH12_HOP | OFPIEH12_DEST | OFPIEH12_ROUTER |
+			       IPPROTO_FRAGMENT | OFPIEH12_UNREP)) ||
+			    dest_options_header_count >= 2) {
+				*ext_hdrs |= OFPIEH12_UNSEQ;
+			}
+			*ext_hdrs |= OFPIEH12_AUTH;
+			break;
+
+		case IPPROTO_DSTOPTS:
+			if (dest_options_header_count == 0) {
+				if (*ext_hdrs &
+				    ~(OFPIEH12_HOP | OFPIEH12_UNREP))
+					*ext_hdrs |= OFPIEH12_UNSEQ;
+				*ext_hdrs |= OFPIEH12_DEST;
+			} else if (dest_options_header_count == 1) {
+				if (*ext_hdrs &
+				    ~(OFPIEH12_HOP | OFPIEH12_DEST |
+				      OFPIEH12_ROUTER | OFPIEH12_FRAG |
+				      OFPIEH12_AUTH | OFPIEH12_ESP |
+				      OFPIEH12_UNREP)) {
+					*ext_hdrs |= OFPIEH12_UNSEQ;
+				}
+			} else {
+				*ext_hdrs |= OFPIEH12_UNREP;
+			}
+			dest_options_header_count++;
+			break;
+
+		case IPPROTO_FRAGMENT:
+			if (*ext_hdrs & OFPIEH12_FRAG)
+				*ext_hdrs |= OFPIEH12_UNREP;
+			if ((*ext_hdrs & ~(OFPIEH12_HOP |
+					   OFPIEH12_DEST |
+					   OFPIEH12_ROUTER |
+					   OFPIEH12_UNREP)) ||
+			    dest_options_header_count >= 2) {
+				*ext_hdrs |= OFPIEH12_UNSEQ;
+			}
+			*ext_hdrs |= OFPIEH12_FRAG;
+			break;
+
+		case IPPROTO_ROUTING:
+			if (*ext_hdrs & OFPIEH12_ROUTER)
+				*ext_hdrs |= OFPIEH12_UNREP;
+			if ((*ext_hdrs & ~(OFPIEH12_HOP |
+					   OFPIEH12_DEST |
+					   OFPIEH12_UNREP)) ||
+			    dest_options_header_count >= 2) {
+				*ext_hdrs |= OFPIEH12_UNSEQ;
+			}
+			*ext_hdrs |= OFPIEH12_ROUTER;
+			break;
+
+		case IPPROTO_HOPOPTS:
+			if (*ext_hdrs & OFPIEH12_HOP)
+				*ext_hdrs |= OFPIEH12_UNREP;
+			/* OFPIEH12_HOP is set to 1 if a hop-by-hop IPv6
+			 * extension header is present as the first
+			 * extension header in the packet.
+			 */
+			if (*ext_hdrs == 0)
+				*ext_hdrs |= OFPIEH12_HOP;
+			else
+				*ext_hdrs |= OFPIEH12_UNSEQ;
+			break;
+
+		default:
+			return;
+		}
+
+		hp = skb_header_pointer(skb, start, sizeof(_hdr), &_hdr);
+		if (!hp)
+			break;
+		next_type = hp->nexthdr;
+		start += ipv6_optlen(hp);
+	}
+}
+
 static int parse_ipv6hdr(struct sk_buff *skb, struct sw_flow_key *key)
 {
 	unsigned short frag_off;
@@ -267,6 +393,8 @@ static int parse_ipv6hdr(struct sk_buff *skb, struct sw_flow_key *key)
 
 	nh = ipv6_hdr(skb);
 
+	get_ipv6_ext_hdrs(skb, nh, &key->ipv6.exthdrs);
+
 	key->ip.proto = NEXTHDR_NONE;
 	key->ip.tos = ipv6_get_dsfield(nh);
 	key->ip.ttl = nh->hop_limit;
@@ -278,7 +406,7 @@ static int parse_ipv6hdr(struct sk_buff *skb, struct sw_flow_key *key)
 	if (flags & IP6_FH_F_FRAG) {
 		if (frag_off) {
 			key->ip.frag = OVS_FRAG_TYPE_LATER;
-			key->ip.proto = nexthdr;
+			key->ip.proto = NEXTHDR_FRAGMENT;
 			return 0;
 		}
 		key->ip.frag = OVS_FRAG_TYPE_FIRST;
@@ -306,10 +434,14 @@ static bool icmp6hdr_ok(struct sk_buff *skb)
 }
 
 /**
- * Parse vlan tag from vlan header.
- * Returns ERROR on memory error.
- * Returns 0 if it encounters a non-vlan or incomplete packet.
- * Returns 1 after successfully parsing vlan tag.
+ * parse_vlan_tag - Parse vlan tag from vlan header.
+ * @skb: skb containing frame to parse
+ * @key_vh: pointer to parsed vlan tag
+ * @untag_vlan: should the vlan header be removed from the frame
+ *
+ * Return: ERROR on memory error.
+ * %0 if it encounters a non-vlan or incomplete packet.
+ * %1 after successfully parsing vlan tag.
  */
 static int parse_vlan_tag(struct sk_buff *skb, struct vlan_head *key_vh,
 			  bool untag_vlan)
@@ -425,7 +557,6 @@ static int parse_icmpv6(struct sk_buff *skb, struct sw_flow_key *key,
 	 */
 	key->tp.src = htons(icmp->icmp6_type);
 	key->tp.dst = htons(icmp->icmp6_code);
-	memset(&key->ipv6.nd, 0, sizeof(key->ipv6.nd));
 
 	if (icmp->icmp6_code == 0 &&
 	    (icmp->icmp6_type == NDISC_NEIGHBOUR_SOLICITATION ||
@@ -434,6 +565,8 @@ static int parse_icmpv6(struct sk_buff *skb, struct sw_flow_key *key,
 		struct nd_msg *nd;
 		int offset;
 
+		memset(&key->ipv6.nd, 0, sizeof(key->ipv6.nd));
+
 		/* In order to process neighbor discovery options, we need the
 		 * entire packet.
 		 */
@@ -536,78 +669,16 @@ static int parse_nsh(struct sk_buff *skb, struct sw_flow_key *key)
 }
 
 /**
- * key_extract - extracts a flow key from an Ethernet frame.
+ * key_extract_l3l4 - extracts L3/L4 header information.
  * @skb: sk_buff that contains the frame, with skb->data pointing to the
- * Ethernet header
+ *       L3 header
  * @key: output flow key
  *
- * The caller must ensure that skb->len >= ETH_HLEN.
- *
- * Returns 0 if successful, otherwise a negative errno value.
- *
- * Initializes @skb header fields as follows:
- *
- *    - skb->mac_header: the L2 header.
- *
- *    - skb->network_header: just past the L2 header, or just past the
- *      VLAN header, to the first byte of the L2 payload.
- *
- *    - skb->transport_header: If key->eth.type is ETH_P_IP or ETH_P_IPV6
- *      on output, then just past the IP header, if one is present and
- *      of a correct length, otherwise the same as skb->network_header.
- *      For other key->eth.type values it is left untouched.
- *
- *    - skb->protocol: the type of the data starting at skb->network_header.
- *      Equals to key->eth.type.
+ * Return: %0 if successful, otherwise a negative errno value.
  */
-static int key_extract(struct sk_buff *skb, struct sw_flow_key *key)
+static int key_extract_l3l4(struct sk_buff *skb, struct sw_flow_key *key)
 {
 	int error;
-	struct ethhdr *eth;
-
-	/* Flags are always used as part of stats */
-	key->tp.flags = 0;
-
-	skb_reset_mac_header(skb);
-
-	/* Link layer. */
-	clear_vlan(key);
-	if (ovs_key_mac_proto(key) == MAC_PROTO_NONE) {
-		if (unlikely(eth_type_vlan(skb->protocol)))
-			return -EINVAL;
-
-		skb_reset_network_header(skb);
-		key->eth.type = skb->protocol;
-	} else {
-		eth = eth_hdr(skb);
-		ether_addr_copy(key->eth.src, eth->h_source);
-		ether_addr_copy(key->eth.dst, eth->h_dest);
-
-		__skb_pull(skb, 2 * ETH_ALEN);
-		/* We are going to push all headers that we pull, so no need to
-		* update skb->csum here.
-		*/
-
-		if (unlikely(parse_vlan(skb, key)))
-			return -ENOMEM;
-
-		key->eth.type = parse_ethertype(skb);
-		if (unlikely(key->eth.type == htons(0)))
-			return -ENOMEM;
-
-		/* Multiple tagged packets need to retain TPID to satisfy
-		 * skb_vlan_pop(), which will later shift the ethertype into
-		 * skb->protocol.
-		 */
-		if (key->eth.cvlan.tci & htons(VLAN_CFI_MASK))
-			skb->protocol = key->eth.cvlan.tpid;
-		else
-			skb->protocol = key->eth.type;
-
-		skb_reset_network_header(skb);
-		__skb_push(skb, skb->data - skb_mac_header(skb));
-	}
-	skb_reset_mac_len(skb);
 
 	/* Network layer. */
 	if (key->eth.type == htons(ETH_P_IP)) {
@@ -636,6 +707,7 @@ static int key_extract(struct sk_buff *skb, struct sw_flow_key *key)
 		offset = nh->frag_off & htons(IP_OFFSET);
 		if (offset) {
 			key->ip.frag = OVS_FRAG_TYPE_LATER;
+			memset(&key->tp, 0, sizeof(key->tp));
 			return 0;
 		}
 		if (nh->frag_off & htons(IP_MF) ||
@@ -712,27 +784,35 @@ static int key_extract(struct sk_buff *skb, struct sw_flow_key *key)
 			memset(&key->ipv4, 0, sizeof(key->ipv4));
 		}
 	} else if (eth_p_mpls(key->eth.type)) {
-		size_t stack_len = MPLS_HLEN;
+		size_t label_count = 1;
 
+		memset(&key->mpls, 0, sizeof(key->mpls));
 		skb_set_inner_network_header(skb, skb->mac_len);
 		while (1) {
 			__be32 lse;
 
-			error = check_header(skb, skb->mac_len + stack_len);
+			error = check_header(skb, skb->mac_len +
+					     label_count * MPLS_HLEN);
 			if (unlikely(error))
 				return 0;
 
 			memcpy(&lse, skb_inner_network_header(skb), MPLS_HLEN);
 
-			if (stack_len == MPLS_HLEN)
-				memcpy(&key->mpls.top_lse, &lse, MPLS_HLEN);
+			if (label_count <= MPLS_LABEL_DEPTH)
+				memcpy(&key->mpls.lse[label_count - 1], &lse,
+				       MPLS_HLEN);
 
-			skb_set_inner_network_header(skb, skb->mac_len + stack_len);
+			skb_set_inner_network_header(skb, skb->mac_len +
+						     label_count * MPLS_HLEN);
 			if (lse & htonl(MPLS_LS_S_MASK))
 				break;
 
-			stack_len += MPLS_HLEN;
+			label_count++;
 		}
+		if (label_count > MPLS_LABEL_DEPTH)
+			label_count = MPLS_LABEL_DEPTH;
+
+		key->mpls.num_labels_mask = GENMASK(label_count - 1, 0);
 	} else if (key->eth.type == htons(ETH_P_IPV6)) {
 		int nh_len;             /* IPv6 Header + Extensions */
 
@@ -742,7 +822,7 @@ static int key_extract(struct sk_buff *skb, struct sw_flow_key *key)
 			case -EINVAL:
 				memset(&key->ip, 0, sizeof(key->ip));
 				memset(&key->ipv6.addr, 0, sizeof(key->ipv6.addr));
-				/* fall-through */
+				fallthrough;
 			case -EPROTO:
 				skb->transport_header = skb->network_header;
 				error = 0;
@@ -753,8 +833,10 @@ static int key_extract(struct sk_buff *skb, struct sw_flow_key *key)
 			return error;
 		}
 
-		if (key->ip.frag == OVS_FRAG_TYPE_LATER)
+		if (key->ip.frag == OVS_FRAG_TYPE_LATER) {
+			memset(&key->tp, 0, sizeof(key->tp));
 			return 0;
+		}
 		if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP)
 			key->ip.frag = OVS_FRAG_TYPE_FIRST;
 
@@ -801,6 +883,92 @@ static int key_extract(struct sk_buff *skb, struct sw_flow_key *key)
 	return 0;
 }
 
+/**
+ * key_extract - extracts a flow key from an Ethernet frame.
+ * @skb: sk_buff that contains the frame, with skb->data pointing to the
+ * Ethernet header
+ * @key: output flow key
+ *
+ * The caller must ensure that skb->len >= ETH_HLEN.
+ *
+ * Initializes @skb header fields as follows:
+ *
+ *    - skb->mac_header: the L2 header.
+ *
+ *    - skb->network_header: just past the L2 header, or just past the
+ *      VLAN header, to the first byte of the L2 payload.
+ *
+ *    - skb->transport_header: If key->eth.type is ETH_P_IP or ETH_P_IPV6
+ *      on output, then just past the IP header, if one is present and
+ *      of a correct length, otherwise the same as skb->network_header.
+ *      For other key->eth.type values it is left untouched.
+ *
+ *    - skb->protocol: the type of the data starting at skb->network_header.
+ *      Equals to key->eth.type.
+ *
+ * Return: %0 if successful, otherwise a negative errno value.
+ */
+static int key_extract(struct sk_buff *skb, struct sw_flow_key *key)
+{
+	struct ethhdr *eth;
+
+	/* Flags are always used as part of stats */
+	key->tp.flags = 0;
+
+	skb_reset_mac_header(skb);
+
+	/* Link layer. */
+	clear_vlan(key);
+	if (ovs_key_mac_proto(key) == MAC_PROTO_NONE) {
+		if (unlikely(eth_type_vlan(skb->protocol)))
+			return -EINVAL;
+
+		skb_reset_network_header(skb);
+		key->eth.type = skb->protocol;
+	} else {
+		eth = eth_hdr(skb);
+		ether_addr_copy(key->eth.src, eth->h_source);
+		ether_addr_copy(key->eth.dst, eth->h_dest);
+
+		__skb_pull(skb, 2 * ETH_ALEN);
+		/* We are going to push all headers that we pull, so no need to
+		 * update skb->csum here.
+		 */
+
+		if (unlikely(parse_vlan(skb, key)))
+			return -ENOMEM;
+
+		key->eth.type = parse_ethertype(skb);
+		if (unlikely(key->eth.type == htons(0)))
+			return -ENOMEM;
+
+		/* Multiple tagged packets need to retain TPID to satisfy
+		 * skb_vlan_pop(), which will later shift the ethertype into
+		 * skb->protocol.
+		 */
+		if (key->eth.cvlan.tci & htons(VLAN_CFI_MASK))
+			skb->protocol = key->eth.cvlan.tpid;
+		else
+			skb->protocol = key->eth.type;
+
+		skb_reset_network_header(skb);
+		__skb_push(skb, skb->data - skb_mac_header(skb));
+	}
+
+	skb_reset_mac_len(skb);
+
+	/* Fill out L3/L4 key info, if any */
+	return key_extract_l3l4(skb, key);
+}
+
+/* In the case of conntrack fragment handling it expects L3 headers,
+ * add a helper.
+ */
+int ovs_flow_key_update_l3l4(struct sk_buff *skb, struct sw_flow_key *key)
+{
+	return key_extract_l3l4(skb, key);
+}
+
 int ovs_flow_key_update(struct sk_buff *skb, struct sw_flow_key *key)
 {
 	int res;
@@ -829,7 +997,12 @@ static int key_extract_mac_proto(struct sk_buff *skb)
 int ovs_flow_key_extract(const struct ip_tunnel_info *tun_info,
 			 struct sk_buff *skb, struct sw_flow_key *key)
 {
+#if IS_ENABLED(CONFIG_NET_TC_SKB_EXT)
+	struct tc_skb_ext *tc_ext;
+#endif
+	bool post_ct = false, post_ct_snat = false, post_ct_dnat = false;
 	int res, err;
+	u16 zone = 0;
 
 	/* Extract metadata from packet. */
 	if (tun_info) {
@@ -861,11 +1034,38 @@ int ovs_flow_key_extract(const struct ip_tunnel_info *tun_info,
 	if (res < 0)
 		return res;
 	key->mac_proto = res;
+
+#if IS_ENABLED(CONFIG_NET_TC_SKB_EXT)
+	if (tc_skb_ext_tc_enabled()) {
+		tc_ext = skb_ext_find(skb, TC_SKB_EXT);
+		key->recirc_id = tc_ext && !tc_ext->act_miss ?
+				 tc_ext->chain : 0;
+		OVS_CB(skb)->mru = tc_ext ? tc_ext->mru : 0;
+		post_ct = tc_ext ? tc_ext->post_ct : false;
+		post_ct_snat = post_ct ? tc_ext->post_ct_snat : false;
+		post_ct_dnat = post_ct ? tc_ext->post_ct_dnat : false;
+		zone = post_ct ? tc_ext->zone : 0;
+	} else {
+		key->recirc_id = 0;
+	}
+#else
 	key->recirc_id = 0;
+#endif
 
 	err = key_extract(skb, key);
-	if (!err)
-		ovs_ct_fill_key(skb, key);   /* Must be after key_extract(). */
+	if (!err) {
+		ovs_ct_fill_key(skb, key, post_ct);   /* Must be after key_extract(). */
+		if (post_ct) {
+			if (!skb_get_nfct(skb)) {
+				key->ct_zone = zone;
+			} else {
+				if (!post_ct_dnat)
+					key->ct_state &= ~OVS_CS_F_DST_NAT;
+				if (!post_ct_snat)
+					key->ct_state &= ~OVS_CS_F_SRC_NAT;
+			}
+		}
+	}
 	return err;
 }