1 files changed, 143 insertions, 67 deletions

diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index d01410e52097..659c2a790fe7 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -222,14 +222,15 @@ void ovs_dp_process_packet(struct sk_buff *skb, struct sw_flow_key *key)
 	struct dp_stats_percpu *stats;
 	u64 *stats_counter;
 	u32 n_mask_hit;
+	int error;
 
 	stats = this_cpu_ptr(dp->stats_percpu);
 
 	/* Look up flow. */
-	flow = ovs_flow_tbl_lookup_stats(&dp->table, key, &n_mask_hit);
+	flow = ovs_flow_tbl_lookup_stats(&dp->table, key, skb_get_hash(skb),
+					 &n_mask_hit);
 	if (unlikely(!flow)) {
 		struct dp_upcall_info upcall;
-		int error;
 
 		memset(&upcall, 0, sizeof(upcall));
 		upcall.cmd = OVS_PACKET_CMD_MISS;
@@ -246,7 +247,10 @@ void ovs_dp_process_packet(struct sk_buff *skb, struct sw_flow_key *key)
 
 	ovs_flow_stats_update(flow, key->tp.flags, skb);
 	sf_acts = rcu_dereference(flow->sf_acts);
-	ovs_execute_actions(dp, skb, sf_acts, key);
+	error = ovs_execute_actions(dp, skb, sf_acts, key);
+	if (unlikely(error))
+		net_dbg_ratelimited("ovs: action execution error on datapath %s: %d\n",
+							ovs_dp_name(dp), error);
 
 	stats_counter = &stats->n_hit;
 
@@ -317,8 +321,7 @@ static int queue_gso_packets(struct datapath *dp, struct sk_buff *skb,
 	}
 
 	/* Queue all of the segments. */
-	skb = segs;
-	do {
+	skb_list_walk_safe(segs, skb, nskb) {
 		if (gso_type & SKB_GSO_UDP && skb != segs)
 			key = &later_key;
 
@@ -326,17 +329,15 @@ static int queue_gso_packets(struct datapath *dp, struct sk_buff *skb,
 		if (err)
 			break;
 
-	} while ((skb = skb->next));
+	}
 
 	/* Free all of the segments. */
-	skb = segs;
-	do {
-		nskb = skb->next;
+	skb_list_walk_safe(segs, skb, nskb) {
 		if (err)
 			kfree_skb(skb);
 		else
 			consume_skb(skb);
-	} while ((skb = nskb));
+	}
 	return err;
 }
 
@@ -346,7 +347,8 @@ static size_t upcall_msg_size(const struct dp_upcall_info *upcall_info,
 	size_t size = NLMSG_ALIGN(sizeof(struct ovs_header))
 		+ nla_total_size(hdrlen) /* OVS_PACKET_ATTR_PACKET */
 		+ nla_total_size(ovs_key_attr_size()) /* OVS_PACKET_ATTR_KEY */
-		+ nla_total_size(sizeof(unsigned int)); /* OVS_PACKET_ATTR_LEN */
+		+ nla_total_size(sizeof(unsigned int)) /* OVS_PACKET_ATTR_LEN */
+		+ nla_total_size(sizeof(u64)); /* OVS_PACKET_ATTR_HASH */
 
 	/* OVS_PACKET_ATTR_USERDATA */
 	if (upcall_info->userdata)
@@ -389,6 +391,7 @@ static int queue_userspace_packet(struct datapath *dp, struct sk_buff *skb,
 	size_t len;
 	unsigned int hlen;
 	int err, dp_ifindex;
+	u64 hash;
 
 	dp_ifindex = get_dpifindex(dp);
 	if (!dp_ifindex)
@@ -481,23 +484,30 @@ static int queue_userspace_packet(struct datapath *dp, struct sk_buff *skb,
 	}
 
 	/* Add OVS_PACKET_ATTR_MRU */
-	if (upcall_info->mru) {
-		if (nla_put_u16(user_skb, OVS_PACKET_ATTR_MRU,
-				upcall_info->mru)) {
-			err = -ENOBUFS;
-			goto out;
-		}
-		pad_packet(dp, user_skb);
+	if (upcall_info->mru &&
+	    nla_put_u16(user_skb, OVS_PACKET_ATTR_MRU, upcall_info->mru)) {
+		err = -ENOBUFS;
+		goto out;
 	}
 
 	/* Add OVS_PACKET_ATTR_LEN when packet is truncated */
-	if (cutlen > 0) {
-		if (nla_put_u32(user_skb, OVS_PACKET_ATTR_LEN,
-				skb->len)) {
-			err = -ENOBUFS;
-			goto out;
-		}
-		pad_packet(dp, user_skb);
+	if (cutlen > 0 &&
+	    nla_put_u32(user_skb, OVS_PACKET_ATTR_LEN, skb->len)) {
+		err = -ENOBUFS;
+		goto out;
+	}
+
+	/* Add OVS_PACKET_ATTR_HASH */
+	hash = skb_get_hash_raw(skb);
+	if (skb->sw_hash)
+		hash |= OVS_PACKET_HASH_SW_BIT;
+
+	if (skb->l4_hash)
+		hash |= OVS_PACKET_HASH_L4_BIT;
+
+	if (nla_put(user_skb, OVS_PACKET_ATTR_HASH, sizeof (u64), &hash)) {
+		err = -ENOBUFS;
+		goto out;
 	}
 
 	/* Only reserve room for attribute header, packet data is added
@@ -539,6 +549,7 @@ static int ovs_packet_cmd_execute(struct sk_buff *skb, struct genl_info *info)
 	struct datapath *dp;
 	struct vport *input_vport;
 	u16 mru = 0;
+	u64 hash;
 	int len;
 	int err;
 	bool log = !a[OVS_PACKET_ATTR_PROBE];
@@ -564,6 +575,14 @@ static int ovs_packet_cmd_execute(struct sk_buff *skb, struct genl_info *info)
 	}
 	OVS_CB(packet)->mru = mru;
 
+	if (a[OVS_PACKET_ATTR_HASH]) {
+		hash = nla_get_u64(a[OVS_PACKET_ATTR_HASH]);
+
+		__skb_set_hash(packet, hash & 0xFFFFFFFFULL,
+			       !!(hash & OVS_PACKET_HASH_SW_BIT),
+			       !!(hash & OVS_PACKET_HASH_L4_BIT));
+	}
+
 	/* Build an sw_flow for sending this packet. */
 	flow = ovs_flow_alloc();
 	err = PTR_ERR(flow);
@@ -701,9 +720,13 @@ static size_t ovs_flow_cmd_msg_size(const struct sw_flow_actions *acts,
 {
 	size_t len = NLMSG_ALIGN(sizeof(struct ovs_header));
 
-	/* OVS_FLOW_ATTR_UFID */
+	/* OVS_FLOW_ATTR_UFID, or unmasked flow key as fallback
+	 * see ovs_nla_put_identifier()
+	 */
 	if (sfid && ovs_identifier_is_ufid(sfid))
 		len += nla_total_size(sfid->ufid_len);
+	else
+		len += nla_total_size(ovs_key_attr_size());
 
 	/* OVS_FLOW_ATTR_KEY */
 	if (!sfid || should_fill_key(sfid, ufid_flags))
@@ -879,7 +902,10 @@ static struct sk_buff *ovs_flow_cmd_build_info(const struct sw_flow *flow,
 	retval = ovs_flow_cmd_fill_info(flow, dp_ifindex, skb,
 					info->snd_portid, info->snd_seq, 0,
 					cmd, ufid_flags);
-	BUG_ON(retval < 0);
+	if (WARN_ON_ONCE(retval < 0)) {
+		kfree_skb(skb);
+		skb = ERR_PTR(retval);
+	}
 	return skb;
 }
 
@@ -1343,7 +1369,10 @@ static int ovs_flow_cmd_del(struct sk_buff *skb, struct genl_info *info)
 						     OVS_FLOW_CMD_DEL,
 						     ufid_flags);
 			rcu_read_unlock();
-			BUG_ON(err < 0);
+			if (WARN_ON_ONCE(err < 0)) {
+				kfree_skb(reply);
+				goto out_free;
+			}
 
 			ovs_notify(&dp_flow_genl_family, reply, info);
 		} else {
@@ -1351,6 +1380,7 @@ static int ovs_flow_cmd_del(struct sk_buff *skb, struct genl_info *info)
 		}
 	}
 
+out_free:
 	ovs_flow_free(flow, true);
 	return 0;
 unlock:
@@ -1542,10 +1572,59 @@ static void ovs_dp_reset_user_features(struct sk_buff *skb, struct genl_info *in
 	dp->user_features = 0;
 }
 
-static void ovs_dp_change(struct datapath *dp, struct nlattr *a[])
+DEFINE_STATIC_KEY_FALSE(tc_recirc_sharing_support);
+
+static int ovs_dp_change(struct datapath *dp, struct nlattr *a[])
+{
+	u32 user_features = 0;
+
+	if (a[OVS_DP_ATTR_USER_FEATURES]) {
+		user_features = nla_get_u32(a[OVS_DP_ATTR_USER_FEATURES]);
+
+		if (user_features & ~(OVS_DP_F_VPORT_PIDS |
+				      OVS_DP_F_UNALIGNED |
+				      OVS_DP_F_TC_RECIRC_SHARING))
+			return -EOPNOTSUPP;
+
+#if !IS_ENABLED(CONFIG_NET_TC_SKB_EXT)
+		if (user_features & OVS_DP_F_TC_RECIRC_SHARING)
+			return -EOPNOTSUPP;
+#endif
+	}
+
+	dp->user_features = user_features;
+
+	if (dp->user_features & OVS_DP_F_TC_RECIRC_SHARING)
+		static_branch_enable(&tc_recirc_sharing_support);
+	else
+		static_branch_disable(&tc_recirc_sharing_support);
+
+	return 0;
+}
+
+static int ovs_dp_stats_init(struct datapath *dp)
+{
+	dp->stats_percpu = netdev_alloc_pcpu_stats(struct dp_stats_percpu);
+	if (!dp->stats_percpu)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static int ovs_dp_vport_init(struct datapath *dp)
 {
-	if (a[OVS_DP_ATTR_USER_FEATURES])
-		dp->user_features = nla_get_u32(a[OVS_DP_ATTR_USER_FEATURES]);
+	int i;
+
+	dp->ports = kmalloc_array(DP_VPORT_HASH_BUCKETS,
+				  sizeof(struct hlist_head),
+				  GFP_KERNEL);
+	if (!dp->ports)
+		return -ENOMEM;
+
+	for (i = 0; i < DP_VPORT_HASH_BUCKETS; i++)
+		INIT_HLIST_HEAD(&dp->ports[i]);
+
+	return 0;
 }
 
 static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info)
@@ -1556,7 +1635,7 @@ static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info)
 	struct datapath *dp;
 	struct vport *vport;
 	struct ovs_net *ovs_net;
-	int err, i;
+	int err;
 
 	err = -EINVAL;
 	if (!a[OVS_DP_ATTR_NAME] || !a[OVS_DP_ATTR_UPCALL_PID])
@@ -1569,35 +1648,26 @@ static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info)
 	err = -ENOMEM;
 	dp = kzalloc(sizeof(*dp), GFP_KERNEL);
 	if (dp == NULL)
-		goto err_free_reply;
+		goto err_destroy_reply;
 
 	ovs_dp_set_net(dp, sock_net(skb->sk));
 
 	/* Allocate table. */
 	err = ovs_flow_tbl_init(&dp->table);
 	if (err)
-		goto err_free_dp;
+		goto err_destroy_dp;
 
-	dp->stats_percpu = netdev_alloc_pcpu_stats(struct dp_stats_percpu);
-	if (!dp->stats_percpu) {
-		err = -ENOMEM;
+	err = ovs_dp_stats_init(dp);
+	if (err)
 		goto err_destroy_table;
-	}
-
-	dp->ports = kmalloc_array(DP_VPORT_HASH_BUCKETS,
-				  sizeof(struct hlist_head),
-				  GFP_KERNEL);
-	if (!dp->ports) {
-		err = -ENOMEM;
-		goto err_destroy_percpu;
-	}
 
-	for (i = 0; i < DP_VPORT_HASH_BUCKETS; i++)
-		INIT_HLIST_HEAD(&dp->ports[i]);
+	err = ovs_dp_vport_init(dp);
+	if (err)
+		goto err_destroy_stats;
 
 	err = ovs_meters_init(dp);
 	if (err)
-		goto err_destroy_ports_array;
+		goto err_destroy_ports;
 
 	/* Set up our datapath device. */
 	parms.name = nla_data(a[OVS_DP_ATTR_NAME]);
@@ -1607,7 +1677,9 @@ static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info)
 	parms.port_no = OVSP_LOCAL;
 	parms.upcall_portids = a[OVS_DP_ATTR_UPCALL_PID];
 
-	ovs_dp_change(dp, a);
+	err = ovs_dp_change(dp, a);
+	if (err)
+		goto err_destroy_meters;
 
 	/* So far only local changes have been made, now need the lock. */
 	ovs_lock();
@@ -1627,6 +1699,7 @@ static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info)
 				ovs_dp_reset_user_features(skb, info);
 		}
 
+		ovs_unlock();
 		goto err_destroy_meters;
 	}
 
@@ -1643,17 +1716,16 @@ static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info)
 	return 0;
 
 err_destroy_meters:
-	ovs_unlock();
 	ovs_meters_exit(dp);
-err_destroy_ports_array:
+err_destroy_ports:
 	kfree(dp->ports);
-err_destroy_percpu:
+err_destroy_stats:
 	free_percpu(dp->stats_percpu);
 err_destroy_table:
 	ovs_flow_tbl_destroy(&dp->table);
-err_free_dp:
+err_destroy_dp:
 	kfree(dp);
-err_free_reply:
+err_destroy_reply:
 	kfree_skb(reply);
 err:
 	return err;
@@ -1733,7 +1805,9 @@ static int ovs_dp_cmd_set(struct sk_buff *skb, struct genl_info *info)
 	if (IS_ERR(dp))
 		goto err_unlock_free;
 
-	ovs_dp_change(dp, info->attrs);
+	err = ovs_dp_change(dp, info->attrs);
+	if (err)
+		goto err_unlock_free;
 
 	err = ovs_dp_cmd_fill_info(dp, reply, info->snd_portid,
 				   info->snd_seq, 0, OVS_DP_CMD_SET);
@@ -1850,7 +1924,7 @@ static struct genl_family dp_datapath_genl_family __ro_after_init = {
 /* Called with ovs_mutex or RCU read lock. */
 static int ovs_vport_cmd_fill_info(struct vport *vport, struct sk_buff *skb,
 				   struct net *net, u32 portid, u32 seq,
-				   u32 flags, u8 cmd)
+				   u32 flags, u8 cmd, gfp_t gfp)
 {
 	struct ovs_header *ovs_header;
 	struct ovs_vport_stats vport_stats;
@@ -1871,7 +1945,7 @@ static int ovs_vport_cmd_fill_info(struct vport *vport, struct sk_buff *skb,
 		goto nla_put_failure;
 
 	if (!net_eq(net, dev_net(vport->dev))) {
-		int id = peernet2id_alloc(net, dev_net(vport->dev));
+		int id = peernet2id_alloc(net, dev_net(vport->dev), gfp);
 
 		if (nla_put_s32(skb, OVS_VPORT_ATTR_NETNSID, id))
 			goto nla_put_failure;
@@ -1912,11 +1986,12 @@ struct sk_buff *ovs_vport_cmd_build_info(struct vport *vport, struct net *net,
 	struct sk_buff *skb;
 	int retval;
 
-	skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC);
+	skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
 	if (!skb)
 		return ERR_PTR(-ENOMEM);
 
-	retval = ovs_vport_cmd_fill_info(vport, skb, net, portid, seq, 0, cmd);
+	retval = ovs_vport_cmd_fill_info(vport, skb, net, portid, seq, 0, cmd,
+					 GFP_KERNEL);
 	BUG_ON(retval < 0);
 
 	return skb;
@@ -2058,7 +2133,7 @@ restart:
 
 	err = ovs_vport_cmd_fill_info(vport, reply, genl_info_net(info),
 				      info->snd_portid, info->snd_seq, 0,
-				      OVS_VPORT_CMD_NEW);
+				      OVS_VPORT_CMD_NEW, GFP_KERNEL);
 
 	new_headroom = netdev_get_fwd_headroom(vport->dev);
 
@@ -2119,7 +2194,7 @@ static int ovs_vport_cmd_set(struct sk_buff *skb, struct genl_info *info)
 
 	err = ovs_vport_cmd_fill_info(vport, reply, genl_info_net(info),
 				      info->snd_portid, info->snd_seq, 0,
-				      OVS_VPORT_CMD_SET);
+				      OVS_VPORT_CMD_SET, GFP_KERNEL);
 	BUG_ON(err < 0);
 
 	ovs_unlock();
@@ -2159,7 +2234,7 @@ static int ovs_vport_cmd_del(struct sk_buff *skb, struct genl_info *info)
 
 	err = ovs_vport_cmd_fill_info(vport, reply, genl_info_net(info),
 				      info->snd_portid, info->snd_seq, 0,
-				      OVS_VPORT_CMD_DEL);
+				      OVS_VPORT_CMD_DEL, GFP_KERNEL);
 	BUG_ON(err < 0);
 
 	/* the vport deletion may trigger dp headroom update */
@@ -2206,7 +2281,7 @@ static int ovs_vport_cmd_get(struct sk_buff *skb, struct genl_info *info)
 		goto exit_unlock_free;
 	err = ovs_vport_cmd_fill_info(vport, reply, genl_info_net(info),
 				      info->snd_portid, info->snd_seq, 0,
-				      OVS_VPORT_CMD_GET);
+				      OVS_VPORT_CMD_GET, GFP_ATOMIC);
 	BUG_ON(err < 0);
 	rcu_read_unlock();
 
@@ -2242,7 +2317,8 @@ static int ovs_vport_cmd_dump(struct sk_buff *skb, struct netlink_callback *cb)
 						    NETLINK_CB(cb->skb).portid,
 						    cb->nlh->nlmsg_seq,
 						    NLM_F_MULTI,
-						    OVS_VPORT_CMD_GET) < 0)
+						    OVS_VPORT_CMD_GET,
+						    GFP_ATOMIC) < 0)
 				goto out;
 
 			j++;
@@ -2263,7 +2339,7 @@ static const struct nla_policy vport_policy[OVS_VPORT_ATTR_MAX + 1] = {
 	[OVS_VPORT_ATTR_STATS] = { .len = sizeof(struct ovs_vport_stats) },
 	[OVS_VPORT_ATTR_PORT_NO] = { .type = NLA_U32 },
 	[OVS_VPORT_ATTR_TYPE] = { .type = NLA_U32 },
-	[OVS_VPORT_ATTR_UPCALL_PID] = { .type = NLA_U32 },
+	[OVS_VPORT_ATTR_UPCALL_PID] = { .type = NLA_UNSPEC },
 	[OVS_VPORT_ATTR_OPTIONS] = { .type = NLA_NESTED },
 	[OVS_VPORT_ATTR_IFINDEX] = { .type = NLA_U32 },
 	[OVS_VPORT_ATTR_NETNSID] = { .type = NLA_S32 },
@@ -2418,7 +2494,7 @@ static int __init dp_init(void)
 {
 	int err;
 
-	BUILD_BUG_ON(sizeof(struct ovs_skb_cb) > FIELD_SIZEOF(struct sk_buff, cb));
+	BUILD_BUG_ON(sizeof(struct ovs_skb_cb) > sizeof_field(struct sk_buff, cb));
 
 	pr_info("Open vSwitch switching datapath\n");