1 files changed, 148 insertions, 45 deletions

diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index 7fbfe2adfffa..ca3ebfdb3023 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -9,7 +9,6 @@
 #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>
@@ -31,6 +30,7 @@
 #include "conntrack.h"
 #include "vport.h"
 #include "flow_netlink.h"
+#include "openvswitch_trace.h"
 
 struct deferred_action {
 	struct sk_buff *skb;
@@ -200,6 +200,9 @@ static int set_mpls(struct sk_buff *skb, struct sw_flow_key *flow_key,
 	__be32 lse;
 	int err;
 
+	if (!pskb_may_pull(skb, skb_network_offset(skb) + MPLS_HLEN))
+		return -ENOMEM;
+
 	stack = mpls_hdr(skb);
 	lse = OVS_MASKED(stack->label_stack_entry, *mpls_lse, *mask);
 	err = skb_mpls_update_lse(skb, lse);
@@ -278,9 +281,11 @@ static int set_eth_addr(struct sk_buff *skb, struct sw_flow_key *flow_key,
  */
 static int pop_eth(struct sk_buff *skb, struct sw_flow_key *key)
 {
-	skb_pull_rcsum(skb, ETH_HLEN);
-	skb_reset_mac_header(skb);
-	skb_reset_mac_len(skb);
+	int err;
+
+	err = skb_eth_pop(skb);
+	if (err)
+		return err;
 
 	/* safe right before invalidate_flow_key */
 	key->mac_proto = MAC_PROTO_NONE;
@@ -291,22 +296,12 @@ static int pop_eth(struct sk_buff *skb, struct sw_flow_key *key)
 static int push_eth(struct sk_buff *skb, struct sw_flow_key *key,
 		    const struct ovs_action_push_eth *ethh)
 {
-	struct ethhdr *hdr;
-
-	/* Add the new Ethernet header */
-	if (skb_cow_head(skb, ETH_HLEN) < 0)
-		return -ENOMEM;
-
-	skb_push(skb, ETH_HLEN);
-	skb_reset_mac_header(skb);
-	skb_reset_mac_len(skb);
-
-	hdr = eth_hdr(skb);
-	ether_addr_copy(hdr->h_source, ethh->addresses.eth_src);
-	ether_addr_copy(hdr->h_dest, ethh->addresses.eth_dst);
-	hdr->h_proto = skb->protocol;
+	int err;
 
-	skb_postpush_rcsum(skb, hdr, ETH_HLEN);
+	err = skb_eth_push(skb, ethh->addresses.eth_dst,
+			   ethh->addresses.eth_src);
+	if (err)
+		return err;
 
 	/* safe right before invalidate_flow_key */
 	key->mac_proto = MAC_PROTO_ETHERNET;
@@ -378,6 +373,7 @@ static void set_ip_addr(struct sk_buff *skb, struct iphdr *nh,
 	update_ip_l4_checksum(skb, nh, *addr, new_addr);
 	csum_replace4(&nh->check, *addr, new_addr);
 	skb_clear_hash(skb);
+	ovs_ct_clear(skb, NULL);
 	*addr = new_addr;
 }
 
@@ -425,15 +421,47 @@ static void set_ipv6_addr(struct sk_buff *skb, u8 l4_proto,
 		update_ipv6_checksum(skb, l4_proto, addr, new_addr);
 
 	skb_clear_hash(skb);
+	ovs_ct_clear(skb, NULL);
 	memcpy(addr, new_addr, sizeof(__be32[4]));
 }
 
-static void set_ipv6_fl(struct ipv6hdr *nh, u32 fl, u32 mask)
+static void set_ipv6_dsfield(struct sk_buff *skb, struct ipv6hdr *nh, u8 ipv6_tclass, u8 mask)
+{
+	u8 old_ipv6_tclass = ipv6_get_dsfield(nh);
+
+	ipv6_tclass = OVS_MASKED(old_ipv6_tclass, ipv6_tclass, mask);
+
+	if (skb->ip_summed == CHECKSUM_COMPLETE)
+		csum_replace(&skb->csum, (__force __wsum)(old_ipv6_tclass << 12),
+			     (__force __wsum)(ipv6_tclass << 12));
+
+	ipv6_change_dsfield(nh, ~mask, ipv6_tclass);
+}
+
+static void set_ipv6_fl(struct sk_buff *skb, struct ipv6hdr *nh, u32 fl, u32 mask)
 {
+	u32 ofl;
+
+	ofl = nh->flow_lbl[0] << 16 |  nh->flow_lbl[1] << 8 |  nh->flow_lbl[2];
+	fl = OVS_MASKED(ofl, fl, mask);
+
 	/* Bits 21-24 are always unmasked, so this retains their values. */
-	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);
+	nh->flow_lbl[0] = (u8)(fl >> 16);
+	nh->flow_lbl[1] = (u8)(fl >> 8);
+	nh->flow_lbl[2] = (u8)fl;
+
+	if (skb->ip_summed == CHECKSUM_COMPLETE)
+		csum_replace(&skb->csum, (__force __wsum)htonl(ofl), (__force __wsum)htonl(fl));
+}
+
+static void set_ipv6_ttl(struct sk_buff *skb, struct ipv6hdr *nh, u8 new_ttl, u8 mask)
+{
+	new_ttl = OVS_MASKED(nh->hop_limit, new_ttl, mask);
+
+	if (skb->ip_summed == CHECKSUM_COMPLETE)
+		csum_replace(&skb->csum, (__force __wsum)(nh->hop_limit << 8),
+			     (__force __wsum)(new_ttl << 8));
+	nh->hop_limit = new_ttl;
 }
 
 static void set_ip_ttl(struct sk_buff *skb, struct iphdr *nh, u8 new_ttl,
@@ -551,18 +579,17 @@ static int set_ipv6(struct sk_buff *skb, struct sw_flow_key *flow_key,
 		}
 	}
 	if (mask->ipv6_tclass) {
-		ipv6_change_dsfield(nh, ~mask->ipv6_tclass, key->ipv6_tclass);
+		set_ipv6_dsfield(skb, nh, key->ipv6_tclass, mask->ipv6_tclass);
 		flow_key->ip.tos = ipv6_get_dsfield(nh);
 	}
 	if (mask->ipv6_label) {
-		set_ipv6_fl(nh, ntohl(key->ipv6_label),
+		set_ipv6_fl(skb, nh, ntohl(key->ipv6_label),
 			    ntohl(mask->ipv6_label));
 		flow_key->ipv6.label =
 		    *(__be32 *)nh & htonl(IPV6_FLOWINFO_FLOWLABEL);
 	}
 	if (mask->ipv6_hlimit) {
-		OVS_SET_MASKED(nh->hop_limit, key->ipv6_hlimit,
-			       mask->ipv6_hlimit);
+		set_ipv6_ttl(skb, nh, key->ipv6_hlimit, mask->ipv6_hlimit);
 		flow_key->ip.ttl = nh->hop_limit;
 	}
 	return 0;
@@ -635,6 +662,7 @@ static int set_nsh(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)
 {
+	ovs_ct_clear(skb, NULL);
 	inet_proto_csum_replace2(check, skb, *port, new_port, false);
 	*port = new_port;
 }
@@ -674,6 +702,7 @@ static int set_udp(struct sk_buff *skb, struct sw_flow_key *flow_key,
 		uh->dest = dst;
 		flow_key->tp.src = src;
 		flow_key->tp.dst = dst;
+		ovs_ct_clear(skb, NULL);
 	}
 
 	skb_clear_hash(skb);
@@ -736,13 +765,16 @@ static int set_sctp(struct sk_buff *skb, struct sw_flow_key *flow_key,
 	sh->checksum = old_csum ^ old_correct_csum ^ new_csum;
 
 	skb_clear_hash(skb);
+	ovs_ct_clear(skb, NULL);
+
 	flow_key->tp.src = sh->source;
 	flow_key->tp.dst = sh->dest;
 
 	return 0;
 }
 
-static int ovs_vport_output(struct net *net, struct sock *sk, struct sk_buff *skb)
+static int ovs_vport_output(struct net *net, struct sock *sk,
+			    struct sk_buff *skb)
 {
 	struct ovs_frag_data *data = this_cpu_ptr(&ovs_frag_data_storage);
 	struct vport *vport = data->vport;
@@ -832,29 +864,25 @@ static void ovs_fragment(struct net *net, struct vport *vport,
 	}
 
 	if (key->eth.type == htons(ETH_P_IP)) {
-		struct dst_entry ovs_dst;
+		struct rtable ovs_rt = { 0 };
 		unsigned long orig_dst;
 
 		prepare_frag(vport, skb, orig_network_offset,
 			     ovs_key_mac_proto(key));
-		dst_init(&ovs_dst, &ovs_dst_ops, NULL, 1,
+		dst_init(&ovs_rt.dst, &ovs_dst_ops, NULL, 1,
 			 DST_OBSOLETE_NONE, DST_NOCOUNT);
-		ovs_dst.dev = vport->dev;
+		ovs_rt.dst.dev = vport->dev;
 
 		orig_dst = skb->_skb_refdst;
-		skb_dst_set_noref(skb, &ovs_dst);
+		skb_dst_set_noref(skb, &ovs_rt.dst);
 		IPCB(skb)->frag_max_size = mru;
 
 		ip_do_fragment(net, skb->sk, skb, ovs_vport_output);
 		refdst_drop(orig_dst);
 	} else if (key->eth.type == 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)
-			goto err;
-
 		prepare_frag(vport, skb, orig_network_offset,
 			     ovs_key_mac_proto(key));
 		memset(&ovs_rt, 0, sizeof(ovs_rt));
@@ -866,7 +894,7 @@ static void ovs_fragment(struct net *net, struct vport *vport,
 		skb_dst_set_noref(skb, &ovs_rt.dst);
 		IP6CB(skb)->frag_max_size = mru;
 
-		v6ops->fragment(net, skb->sk, skb, ovs_vport_output);
+		ipv6_stub->ipv6_fragment(net, skb->sk, skb, ovs_vport_output);
 		refdst_drop(orig_dst);
 	} else {
 		WARN_ONCE(1, "Failed fragment ->%s: eth=%04x, MRU=%d, MTU=%d.",
@@ -925,14 +953,20 @@ static int output_userspace(struct datapath *dp, struct sk_buff *skb,
 	upcall.mru = OVS_CB(skb)->mru;
 
 	for (a = nla_data(attr), rem = nla_len(attr); rem > 0;
-		 a = nla_next(a, &rem)) {
+	     a = nla_next(a, &rem)) {
 		switch (nla_type(a)) {
 		case OVS_USERSPACE_ATTR_USERDATA:
 			upcall.userdata = a;
 			break;
 
 		case OVS_USERSPACE_ATTR_PID:
-			upcall.portid = nla_get_u32(a);
+			if (dp->user_features &
+			    OVS_DP_F_DISPATCH_UPCALL_PER_CPU)
+				upcall.portid =
+				  ovs_dp_get_upcall_portid(dp,
+							   smp_processor_id());
+			else
+				upcall.portid = nla_get_u32(a);
 			break;
 
 		case OVS_USERSPACE_ATTR_EGRESS_TUN_PORT: {
@@ -964,6 +998,21 @@ static int output_userspace(struct datapath *dp, struct sk_buff *skb,
 	return ovs_dp_upcall(dp, skb, key, &upcall, cutlen);
 }
 
+static int dec_ttl_exception_handler(struct datapath *dp, struct sk_buff *skb,
+				     struct sw_flow_key *key,
+				     const struct nlattr *attr)
+{
+	/* The first attribute is always 'OVS_DEC_TTL_ATTR_ACTION'. */
+	struct nlattr *actions = nla_data(attr);
+
+	if (nla_len(actions))
+		return clone_execute(dp, skb, key, 0, nla_data(actions),
+				     nla_len(actions), true, false);
+
+	consume_skb(skb);
+	return 0;
+}
+
 /* When 'last' is true, sample() should always consume the 'skb'.
  * Otherwise, sample() should keep 'skb' intact regardless what
  * actions are executed within sample().
@@ -984,7 +1033,7 @@ static int sample(struct datapath *dp, struct sk_buff *skb,
 	actions = nla_next(sample_arg, &rem);
 
 	if ((arg->probability != U32_MAX) &&
-	    (!arg->probability || prandom_u32() > arg->probability)) {
+	    (!arg->probability || get_random_u32() > arg->probability)) {
 		if (last)
 			consume_skb(skb);
 		return 0;
@@ -1008,7 +1057,7 @@ static int clone(struct datapath *dp, struct sk_buff *skb,
 	int rem = nla_len(attr);
 	bool dont_clone_flow_key;
 
-	/* The first action is always 'OVS_CLONE_ATTR_ARG'. */
+	/* The first action is always 'OVS_CLONE_ATTR_EXEC'. */
 	clone_arg = nla_data(attr);
 	dont_clone_flow_key = nla_get_u32(clone_arg);
 	actions = nla_next(clone_arg, &rem);
@@ -1150,9 +1199,10 @@ static int execute_check_pkt_len(struct datapath *dp, struct sk_buff *skb,
 				 struct sw_flow_key *key,
 				 const struct nlattr *attr, bool last)
 {
+	struct ovs_skb_cb *ovs_cb = OVS_CB(skb);
 	const struct nlattr *actions, *cpl_arg;
+	int len, max_len, rem = nla_len(attr);
 	const struct check_pkt_len_arg *arg;
-	int rem = nla_len(attr);
 	bool clone_flow_key;
 
 	/* The first netlink attribute in 'attr' is always
@@ -1161,7 +1211,11 @@ static int execute_check_pkt_len(struct datapath *dp, struct sk_buff *skb,
 	cpl_arg = nla_data(attr);
 	arg = nla_data(cpl_arg);
 
-	if (skb->len <= arg->pkt_len) {
+	len = ovs_cb->mru ? ovs_cb->mru + skb->mac_len : skb->len;
+	max_len = arg->pkt_len;
+
+	if ((skb_is_gso(skb) && skb_gso_validate_mac_len(skb, max_len)) ||
+	    len <= max_len) {
 		/* Second netlink attribute in 'attr' is always
 		 * 'OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_LESS_EQUAL'.
 		 */
@@ -1180,6 +1234,45 @@ static int execute_check_pkt_len(struct datapath *dp, struct sk_buff *skb,
 			     nla_len(actions), last, clone_flow_key);
 }
 
+static int execute_dec_ttl(struct sk_buff *skb, struct sw_flow_key *key)
+{
+	int err;
+
+	if (skb->protocol == htons(ETH_P_IPV6)) {
+		struct ipv6hdr *nh;
+
+		err = skb_ensure_writable(skb, skb_network_offset(skb) +
+					  sizeof(*nh));
+		if (unlikely(err))
+			return err;
+
+		nh = ipv6_hdr(skb);
+
+		if (nh->hop_limit <= 1)
+			return -EHOSTUNREACH;
+
+		key->ip.ttl = --nh->hop_limit;
+	} else if (skb->protocol == htons(ETH_P_IP)) {
+		struct iphdr *nh;
+		u8 old_ttl;
+
+		err = skb_ensure_writable(skb, skb_network_offset(skb) +
+					  sizeof(*nh));
+		if (unlikely(err))
+			return err;
+
+		nh = ip_hdr(skb);
+		if (nh->ttl <= 1)
+			return -EHOSTUNREACH;
+
+		old_ttl = nh->ttl--;
+		csum_replace2(&nh->check, htons(old_ttl << 8),
+			      htons(nh->ttl << 8));
+		key->ip.ttl = nh->ttl;
+	}
+	return 0;
+}
+
 /* Execute a list of actions against 'skb'. */
 static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
 			      struct sw_flow_key *key,
@@ -1192,6 +1285,9 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
 	     a = nla_next(a, &rem)) {
 		int err = 0;
 
+		if (trace_ovs_do_execute_action_enabled())
+			trace_ovs_do_execute_action(dp, skb, key, a, rem);
+
 		switch (nla_type(a)) {
 		case OVS_ACTION_ATTR_OUTPUT: {
 			int port = nla_get_u32(a);
@@ -1365,6 +1461,13 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
 
 			break;
 		}
+
+		case OVS_ACTION_ATTR_DEC_TTL:
+			err = execute_dec_ttl(skb, key);
+			if (err == -EHOSTUNREACH)
+				return dec_ttl_exception_handler(dp, skb,
+								 key, a);
+			break;
 		}
 
 		if (unlikely(err)) {
@@ -1442,8 +1545,8 @@ static int clone_execute(struct datapath *dp, struct sk_buff *skb,
 				pr_warn("%s: deferred action limit reached, drop sample action\n",
 					ovs_dp_name(dp));
 			} else {  /* Recirc action */
-				pr_warn("%s: deferred action limit reached, drop recirc action\n",
-					ovs_dp_name(dp));
+				pr_warn("%s: deferred action limit reached, drop recirc action (recirc_id=%#x)\n",
+					ovs_dp_name(dp), recirc_id);
 			}
 		}
 	}