1 files changed, 218 insertions, 46 deletions

diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index ee34f474ad14..315f5330b6e5 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -22,6 +22,7 @@
 #include <linux/in.h>
 #include <linux/ip.h>
 #include <linux/openvswitch.h>
+#include <linux/netfilter_ipv6.h>
 #include <linux/sctp.h>
 #include <linux/tcp.h>
 #include <linux/udp.h>
@@ -29,8 +30,10 @@
 #include <linux/if_arp.h>
 #include <linux/if_vlan.h>
 
+#include <net/dst.h>
 #include <net/ip.h>
 #include <net/ipv6.h>
+#include <net/ip6_fib.h>
 #include <net/checksum.h>
 #include <net/dsfield.h>
 #include <net/mpls.h>
@@ -38,6 +41,7 @@
 
 #include "datapath.h"
 #include "flow.h"
+#include "conntrack.h"
 #include "vport.h"
 
 static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
@@ -52,6 +56,20 @@ struct deferred_action {
 	struct sw_flow_key pkt_key;
 };
 
+#define MAX_L2_LEN	(VLAN_ETH_HLEN + 3 * MPLS_HLEN)
+struct ovs_frag_data {
+	unsigned long dst;
+	struct vport *vport;
+	struct ovs_skb_cb cb;
+	__be16 inner_protocol;
+	__u16 vlan_tci;
+	__be16 vlan_proto;
+	unsigned int l2_len;
+	u8 l2_data[MAX_L2_LEN];
+};
+
+static DEFINE_PER_CPU(struct ovs_frag_data, ovs_frag_data_storage);
+
 #define DEFERRED_ACTION_FIFO_SIZE 10
 struct action_fifo {
 	int head;
@@ -185,10 +203,6 @@ static int pop_mpls(struct sk_buff *skb, struct sw_flow_key *key,
 	return 0;
 }
 
-/* 'KEY' must not have any bits set outside of the 'MASK' */
-#define MASKED(OLD, KEY, MASK) ((KEY) | ((OLD) & ~(MASK)))
-#define SET_MASKED(OLD, KEY, MASK) ((OLD) = MASKED(OLD, KEY, MASK))
-
 static int set_mpls(struct sk_buff *skb, struct sw_flow_key *flow_key,
 		    const __be32 *mpls_lse, const __be32 *mask)
 {
@@ -201,7 +215,7 @@ static int set_mpls(struct sk_buff *skb, struct sw_flow_key *flow_key,
 		return err;
 
 	stack = (__be32 *)skb_mpls_header(skb);
-	lse = MASKED(*stack, *mpls_lse, *mask);
+	lse = OVS_MASKED(*stack, *mpls_lse, *mask);
 	if (skb->ip_summed == CHECKSUM_COMPLETE) {
 		__be32 diff[] = { ~(*stack), lse };
 
@@ -244,9 +258,9 @@ static void ether_addr_copy_masked(u8 *dst_, const u8 *src_, const u8 *mask_)
 	const u16 *src = (const u16 *)src_;
 	const u16 *mask = (const u16 *)mask_;
 
-	SET_MASKED(dst[0], src[0], mask[0]);
-	SET_MASKED(dst[1], src[1], mask[1]);
-	SET_MASKED(dst[2], src[2], mask[2]);
+	OVS_SET_MASKED(dst[0], src[0], mask[0]);
+	OVS_SET_MASKED(dst[1], src[1], mask[1]);
+	OVS_SET_MASKED(dst[2], src[2], mask[2]);
 }
 
 static int set_eth_addr(struct sk_buff *skb, struct sw_flow_key *flow_key,
@@ -284,14 +298,14 @@ static void update_ip_l4_checksum(struct sk_buff *skb, struct iphdr *nh,
 	if (nh->protocol == IPPROTO_TCP) {
 		if (likely(transport_len >= sizeof(struct tcphdr)))
 			inet_proto_csum_replace4(&tcp_hdr(skb)->check, skb,
-						 addr, new_addr, 1);
+						 addr, new_addr, true);
 	} else if (nh->protocol == IPPROTO_UDP) {
 		if (likely(transport_len >= sizeof(struct udphdr))) {
 			struct udphdr *uh = udp_hdr(skb);
 
 			if (uh->check || skb->ip_summed == CHECKSUM_PARTIAL) {
 				inet_proto_csum_replace4(&uh->check, skb,
-							 addr, new_addr, 1);
+							 addr, new_addr, true);
 				if (!uh->check)
 					uh->check = CSUM_MANGLED_0;
 			}
@@ -316,14 +330,14 @@ static void update_ipv6_checksum(struct sk_buff *skb, u8 l4_proto,
 	if (l4_proto == NEXTHDR_TCP) {
 		if (likely(transport_len >= sizeof(struct tcphdr)))
 			inet_proto_csum_replace16(&tcp_hdr(skb)->check, skb,
-						  addr, new_addr, 1);
+						  addr, new_addr, true);
 	} else if (l4_proto == NEXTHDR_UDP) {
 		if (likely(transport_len >= sizeof(struct udphdr))) {
 			struct udphdr *uh = udp_hdr(skb);
 
 			if (uh->check || skb->ip_summed == CHECKSUM_PARTIAL) {
 				inet_proto_csum_replace16(&uh->check, skb,
-							  addr, new_addr, 1);
+							  addr, new_addr, true);
 				if (!uh->check)
 					uh->check = CSUM_MANGLED_0;
 			}
@@ -331,17 +345,17 @@ static void update_ipv6_checksum(struct sk_buff *skb, u8 l4_proto,
 	} else if (l4_proto == NEXTHDR_ICMP) {
 		if (likely(transport_len >= sizeof(struct icmp6hdr)))
 			inet_proto_csum_replace16(&icmp6_hdr(skb)->icmp6_cksum,
-						  skb, addr, new_addr, 1);
+						  skb, addr, new_addr, true);
 	}
 }
 
 static void mask_ipv6_addr(const __be32 old[4], const __be32 addr[4],
 			   const __be32 mask[4], __be32 masked[4])
 {
-	masked[0] = MASKED(old[0], addr[0], mask[0]);
-	masked[1] = MASKED(old[1], addr[1], mask[1]);
-	masked[2] = MASKED(old[2], addr[2], mask[2]);
-	masked[3] = MASKED(old[3], addr[3], mask[3]);
+	masked[0] = OVS_MASKED(old[0], addr[0], mask[0]);
+	masked[1] = OVS_MASKED(old[1], addr[1], mask[1]);
+	masked[2] = OVS_MASKED(old[2], addr[2], mask[2]);
+	masked[3] = OVS_MASKED(old[3], addr[3], mask[3]);
 }
 
 static void set_ipv6_addr(struct sk_buff *skb, u8 l4_proto,
@@ -358,15 +372,15 @@ static void set_ipv6_addr(struct sk_buff *skb, u8 l4_proto,
 static void set_ipv6_fl(struct ipv6hdr *nh, u32 fl, u32 mask)
 {
 	/* Bits 21-24 are always unmasked, so this retains their values. */
-	SET_MASKED(nh->flow_lbl[0], (u8)(fl >> 16), (u8)(mask >> 16));
-	SET_MASKED(nh->flow_lbl[1], (u8)(fl >> 8), (u8)(mask >> 8));
-	SET_MASKED(nh->flow_lbl[2], (u8)fl, (u8)mask);
+	OVS_SET_MASKED(nh->flow_lbl[0], (u8)(fl >> 16), (u8)(mask >> 16));
+	OVS_SET_MASKED(nh->flow_lbl[1], (u8)(fl >> 8), (u8)(mask >> 8));
+	OVS_SET_MASKED(nh->flow_lbl[2], (u8)fl, (u8)mask);
 }
 
 static void set_ip_ttl(struct sk_buff *skb, struct iphdr *nh, u8 new_ttl,
 		       u8 mask)
 {
-	new_ttl = MASKED(nh->ttl, new_ttl, mask);
+	new_ttl = OVS_MASKED(nh->ttl, new_ttl, mask);
 
 	csum_replace2(&nh->check, htons(nh->ttl << 8), htons(new_ttl << 8));
 	nh->ttl = new_ttl;
@@ -392,7 +406,7 @@ static int set_ipv4(struct sk_buff *skb, struct sw_flow_key *flow_key,
 	 * makes sense to check if the value actually changed.
 	 */
 	if (mask->ipv4_src) {
-		new_addr = MASKED(nh->saddr, key->ipv4_src, mask->ipv4_src);
+		new_addr = OVS_MASKED(nh->saddr, key->ipv4_src, mask->ipv4_src);
 
 		if (unlikely(new_addr != nh->saddr)) {
 			set_ip_addr(skb, nh, &nh->saddr, new_addr);
@@ -400,7 +414,7 @@ static int set_ipv4(struct sk_buff *skb, struct sw_flow_key *flow_key,
 		}
 	}
 	if (mask->ipv4_dst) {
-		new_addr = MASKED(nh->daddr, key->ipv4_dst, mask->ipv4_dst);
+		new_addr = OVS_MASKED(nh->daddr, key->ipv4_dst, mask->ipv4_dst);
 
 		if (unlikely(new_addr != nh->daddr)) {
 			set_ip_addr(skb, nh, &nh->daddr, new_addr);
@@ -488,7 +502,8 @@ static int set_ipv6(struct sk_buff *skb, struct sw_flow_key *flow_key,
 		    *(__be32 *)nh & htonl(IPV6_FLOWINFO_FLOWLABEL);
 	}
 	if (mask->ipv6_hlimit) {
-		SET_MASKED(nh->hop_limit, key->ipv6_hlimit, mask->ipv6_hlimit);
+		OVS_SET_MASKED(nh->hop_limit, key->ipv6_hlimit,
+			       mask->ipv6_hlimit);
 		flow_key->ip.ttl = nh->hop_limit;
 	}
 	return 0;
@@ -498,7 +513,7 @@ static int set_ipv6(struct sk_buff *skb, struct sw_flow_key *flow_key,
 static void set_tp_port(struct sk_buff *skb, __be16 *port,
 			__be16 new_port, __sum16 *check)
 {
-	inet_proto_csum_replace2(check, skb, *port, new_port, 0);
+	inet_proto_csum_replace2(check, skb, *port, new_port, false);
 	*port = new_port;
 }
 
@@ -517,8 +532,8 @@ static int set_udp(struct sk_buff *skb, struct sw_flow_key *flow_key,
 
 	uh = udp_hdr(skb);
 	/* Either of the masks is non-zero, so do not bother checking them. */
-	src = MASKED(uh->source, key->udp_src, mask->udp_src);
-	dst = MASKED(uh->dest, key->udp_dst, mask->udp_dst);
+	src = OVS_MASKED(uh->source, key->udp_src, mask->udp_src);
+	dst = OVS_MASKED(uh->dest, key->udp_dst, mask->udp_dst);
 
 	if (uh->check && skb->ip_summed != CHECKSUM_PARTIAL) {
 		if (likely(src != uh->source)) {
@@ -558,12 +573,12 @@ static int set_tcp(struct sk_buff *skb, struct sw_flow_key *flow_key,
 		return err;
 
 	th = tcp_hdr(skb);
-	src = MASKED(th->source, key->tcp_src, mask->tcp_src);
+	src = OVS_MASKED(th->source, key->tcp_src, mask->tcp_src);
 	if (likely(src != th->source)) {
 		set_tp_port(skb, &th->source, src, &th->check);
 		flow_key->tp.src = src;
 	}
-	dst = MASKED(th->dest, key->tcp_dst, mask->tcp_dst);
+	dst = OVS_MASKED(th->dest, key->tcp_dst, mask->tcp_dst);
 	if (likely(dst != th->dest)) {
 		set_tp_port(skb, &th->dest, dst, &th->check);
 		flow_key->tp.dst = dst;
@@ -590,8 +605,8 @@ static int set_sctp(struct sk_buff *skb, struct sw_flow_key *flow_key,
 	old_csum = sh->checksum;
 	old_correct_csum = sctp_compute_cksum(skb, sctphoff);
 
-	sh->source = MASKED(sh->source, key->sctp_src, mask->sctp_src);
-	sh->dest = MASKED(sh->dest, key->sctp_dst, mask->sctp_dst);
+	sh->source = OVS_MASKED(sh->source, key->sctp_src, mask->sctp_src);
+	sh->dest = OVS_MASKED(sh->dest, key->sctp_dst, mask->sctp_dst);
 
 	new_csum = sctp_compute_cksum(skb, sctphoff);
 
@@ -605,27 +620,159 @@ static int set_sctp(struct sk_buff *skb, struct sw_flow_key *flow_key,
 	return 0;
 }
 
-static void do_output(struct datapath *dp, struct sk_buff *skb, int out_port)
+static int ovs_vport_output(struct sock *sock, struct sk_buff *skb)
+{
+	struct ovs_frag_data *data = this_cpu_ptr(&ovs_frag_data_storage);
+	struct vport *vport = data->vport;
+
+	if (skb_cow_head(skb, data->l2_len) < 0) {
+		kfree_skb(skb);
+		return -ENOMEM;
+	}
+
+	__skb_dst_copy(skb, data->dst);
+	*OVS_CB(skb) = data->cb;
+	skb->inner_protocol = data->inner_protocol;
+	skb->vlan_tci = data->vlan_tci;
+	skb->vlan_proto = data->vlan_proto;
+
+	/* Reconstruct the MAC header.  */
+	skb_push(skb, data->l2_len);
+	memcpy(skb->data, &data->l2_data, data->l2_len);
+	ovs_skb_postpush_rcsum(skb, skb->data, data->l2_len);
+	skb_reset_mac_header(skb);
+
+	ovs_vport_send(vport, skb);
+	return 0;
+}
+
+static unsigned int
+ovs_dst_get_mtu(const struct dst_entry *dst)
+{
+	return dst->dev->mtu;
+}
+
+static struct dst_ops ovs_dst_ops = {
+	.family = AF_UNSPEC,
+	.mtu = ovs_dst_get_mtu,
+};
+
+/* prepare_frag() is called once per (larger-than-MTU) frame; its inverse is
+ * ovs_vport_output(), which is called once per fragmented packet.
+ */
+static void prepare_frag(struct vport *vport, struct sk_buff *skb)
+{
+	unsigned int hlen = skb_network_offset(skb);
+	struct ovs_frag_data *data;
+
+	data = this_cpu_ptr(&ovs_frag_data_storage);
+	data->dst = skb->_skb_refdst;
+	data->vport = vport;
+	data->cb = *OVS_CB(skb);
+	data->inner_protocol = skb->inner_protocol;
+	data->vlan_tci = skb->vlan_tci;
+	data->vlan_proto = skb->vlan_proto;
+	data->l2_len = hlen;
+	memcpy(&data->l2_data, skb->data, hlen);
+
+	memset(IPCB(skb), 0, sizeof(struct inet_skb_parm));
+	skb_pull(skb, hlen);
+}
+
+static void ovs_fragment(struct vport *vport, struct sk_buff *skb, u16 mru,
+			 __be16 ethertype)
+{
+	if (skb_network_offset(skb) > MAX_L2_LEN) {
+		OVS_NLERR(1, "L2 header too long to fragment");
+		return;
+	}
+
+	if (ethertype == htons(ETH_P_IP)) {
+		struct dst_entry ovs_dst;
+		unsigned long orig_dst;
+
+		prepare_frag(vport, skb);
+		dst_init(&ovs_dst, &ovs_dst_ops, NULL, 1,
+			 DST_OBSOLETE_NONE, DST_NOCOUNT);
+		ovs_dst.dev = vport->dev;
+
+		orig_dst = skb->_skb_refdst;
+		skb_dst_set_noref(skb, &ovs_dst);
+		IPCB(skb)->frag_max_size = mru;
+
+		ip_do_fragment(skb->sk, skb, ovs_vport_output);
+		refdst_drop(orig_dst);
+	} else if (ethertype == htons(ETH_P_IPV6)) {
+		const struct nf_ipv6_ops *v6ops = nf_get_ipv6_ops();
+		unsigned long orig_dst;
+		struct rt6_info ovs_rt;
+
+		if (!v6ops) {
+			kfree_skb(skb);
+			return;
+		}
+
+		prepare_frag(vport, skb);
+		memset(&ovs_rt, 0, sizeof(ovs_rt));
+		dst_init(&ovs_rt.dst, &ovs_dst_ops, NULL, 1,
+			 DST_OBSOLETE_NONE, DST_NOCOUNT);
+		ovs_rt.dst.dev = vport->dev;
+
+		orig_dst = skb->_skb_refdst;
+		skb_dst_set_noref(skb, &ovs_rt.dst);
+		IP6CB(skb)->frag_max_size = mru;
+
+		v6ops->fragment(skb->sk, skb, ovs_vport_output);
+		refdst_drop(orig_dst);
+	} else {
+		WARN_ONCE(1, "Failed fragment ->%s: eth=%04x, MRU=%d, MTU=%d.",
+			  ovs_vport_name(vport), ntohs(ethertype), mru,
+			  vport->dev->mtu);
+		kfree_skb(skb);
+	}
+}
+
+static void do_output(struct datapath *dp, struct sk_buff *skb, int out_port,
+		      struct sw_flow_key *key)
 {
 	struct vport *vport = ovs_vport_rcu(dp, out_port);
 
-	if (likely(vport))
-		ovs_vport_send(vport, skb);
-	else
+	if (likely(vport)) {
+		u16 mru = OVS_CB(skb)->mru;
+
+		if (likely(!mru || (skb->len <= mru + ETH_HLEN))) {
+			ovs_vport_send(vport, skb);
+		} else if (mru <= vport->dev->mtu) {
+			__be16 ethertype = key->eth.type;
+
+			if (!is_flow_key_valid(key)) {
+				if (eth_p_mpls(skb->protocol))
+					ethertype = skb->inner_protocol;
+				else
+					ethertype = vlan_get_protocol(skb);
+			}
+
+			ovs_fragment(vport, skb, mru, ethertype);
+		} else {
+			kfree_skb(skb);
+		}
+	} else {
 		kfree_skb(skb);
+	}
 }
 
 static int output_userspace(struct datapath *dp, struct sk_buff *skb,
 			    struct sw_flow_key *key, const struct nlattr *attr,
 			    const struct nlattr *actions, int actions_len)
 {
-	struct ovs_tunnel_info info;
+	struct ip_tunnel_info info;
 	struct dp_upcall_info upcall;
 	const struct nlattr *a;
 	int rem;
 
 	memset(&upcall, 0, sizeof(upcall));
 	upcall.cmd = OVS_PACKET_CMD_ACTION;
+	upcall.mru = OVS_CB(skb)->mru;
 
 	for (a = nla_data(attr), rem = nla_len(attr); rem > 0;
 		 a = nla_next(a, &rem)) {
@@ -646,11 +793,13 @@ static int output_userspace(struct datapath *dp, struct sk_buff *skb,
 			if (vport) {
 				int err;
 
+				upcall.egress_tun_info = &info;
 				err = ovs_vport_get_egress_tun_info(vport, skb,
-								    &info);
-				if (!err)
-					upcall.egress_tun_info = &info;
+								    &upcall);
+				if (err)
+					upcall.egress_tun_info = NULL;
 			}
+
 			break;
 		}
 
@@ -677,9 +826,12 @@ static int sample(struct datapath *dp, struct sk_buff *skb,
 
 	for (a = nla_data(attr), rem = nla_len(attr); rem > 0;
 		 a = nla_next(a, &rem)) {
+		u32 probability;
+
 		switch (nla_type(a)) {
 		case OVS_SAMPLE_ATTR_PROBABILITY:
-			if (prandom_u32() >= nla_get_u32(a))
+			probability = nla_get_u32(a);
+			if (!probability || prandom_u32() > probability)
 				return 0;
 			break;
 
@@ -741,7 +893,11 @@ static int execute_set_action(struct sk_buff *skb,
 {
 	/* Only tunnel set execution is supported without a mask. */
 	if (nla_type(a) == OVS_KEY_ATTR_TUNNEL_INFO) {
-		OVS_CB(skb)->egress_tun_info = nla_data(a);
+		struct ovs_tunnel_info *tun = nla_data(a);
+
+		skb_dst_drop(skb);
+		dst_hold((struct dst_entry *)tun->tun_dst);
+		skb_dst_set(skb, (struct dst_entry *)tun->tun_dst);
 		return 0;
 	}
 
@@ -759,12 +915,13 @@ static int execute_masked_set_action(struct sk_buff *skb,
 
 	switch (nla_type(a)) {
 	case OVS_KEY_ATTR_PRIORITY:
-		SET_MASKED(skb->priority, nla_get_u32(a), *get_mask(a, u32 *));
+		OVS_SET_MASKED(skb->priority, nla_get_u32(a),
+			       *get_mask(a, u32 *));
 		flow_key->phy.priority = skb->priority;
 		break;
 
 	case OVS_KEY_ATTR_SKB_MARK:
-		SET_MASKED(skb->mark, nla_get_u32(a), *get_mask(a, u32 *));
+		OVS_SET_MASKED(skb->mark, nla_get_u32(a), *get_mask(a, u32 *));
 		flow_key->phy.skb_mark = skb->mark;
 		break;
 
@@ -807,6 +964,13 @@ static int execute_masked_set_action(struct sk_buff *skb,
 		err = set_mpls(skb, flow_key, nla_data(a), get_mask(a,
 								    __be32 *));
 		break;
+
+	case OVS_KEY_ATTR_CT_STATE:
+	case OVS_KEY_ATTR_CT_ZONE:
+	case OVS_KEY_ATTR_CT_MARK:
+	case OVS_KEY_ATTR_CT_LABEL:
+		err = -EINVAL;
+		break;
 	}
 
 	return err;
@@ -876,7 +1040,7 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
 			struct sk_buff *out_skb = skb_clone(skb, GFP_ATOMIC);
 
 			if (out_skb)
-				do_output(dp, out_skb, prev_port);
+				do_output(dp, out_skb, prev_port, key);
 
 			prev_port = -1;
 		}
@@ -933,6 +1097,15 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
 		case OVS_ACTION_ATTR_SAMPLE:
 			err = sample(dp, skb, key, a, attr, len);
 			break;
+
+		case OVS_ACTION_ATTR_CT:
+			err = ovs_ct_execute(ovs_dp_get_net(dp), skb, key,
+					     nla_data(a));
+
+			/* Hide stolen IP fragments from user space. */
+			if (err == -EINPROGRESS)
+				return 0;
+			break;
 		}
 
 		if (unlikely(err)) {
@@ -942,7 +1115,7 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
 	}
 
 	if (prev_port != -1)
-		do_output(dp, skb, prev_port);
+		do_output(dp, skb, prev_port, key);
 	else
 		consume_skb(skb);
 
@@ -984,7 +1157,6 @@ int ovs_execute_actions(struct datapath *dp, struct sk_buff *skb,
 	int err;
 
 	this_cpu_inc(exec_actions_level);
-	OVS_CB(skb)->egress_tun_info = NULL;
 	err = do_execute_actions(dp, skb, key,
 				 acts->actions, acts->actions_len);