1 files changed, 212 insertions, 41 deletions

diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
index e8750b4ef7e1..ecae35512b9b 100644
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -11,7 +11,9 @@
 #include <linux/bitops.h>
 
 #include <net/dsfield.h>
+#include <net/flow.h>
 #include <net/gro_cells.h>
+#include <net/inet_dscp.h>
 #include <net/inet_ecn.h>
 #include <net/netns/generic.h>
 #include <net/rtnetlink.h>
@@ -36,6 +38,24 @@
 	(sizeof_field(struct ip_tunnel_key, u) -		\
 	 sizeof_field(struct ip_tunnel_key, u.ipv4))
 
+#define __ipt_flag_op(op, ...)					\
+	op(__VA_ARGS__, __IP_TUNNEL_FLAG_NUM)
+
+#define IP_TUNNEL_DECLARE_FLAGS(...)				\
+	__ipt_flag_op(DECLARE_BITMAP, __VA_ARGS__)
+
+#define ip_tunnel_flags_zero(...)	__ipt_flag_op(bitmap_zero, __VA_ARGS__)
+#define ip_tunnel_flags_copy(...)	__ipt_flag_op(bitmap_copy, __VA_ARGS__)
+#define ip_tunnel_flags_and(...)	__ipt_flag_op(bitmap_and, __VA_ARGS__)
+#define ip_tunnel_flags_or(...)		__ipt_flag_op(bitmap_or, __VA_ARGS__)
+
+#define ip_tunnel_flags_empty(...)				\
+	__ipt_flag_op(bitmap_empty, __VA_ARGS__)
+#define ip_tunnel_flags_intersect(...)				\
+	__ipt_flag_op(bitmap_intersects, __VA_ARGS__)
+#define ip_tunnel_flags_subset(...)				\
+	__ipt_flag_op(bitmap_subset, __VA_ARGS__)
+
 struct ip_tunnel_key {
 	__be64			tun_id;
 	union {
@@ -48,11 +68,11 @@ struct ip_tunnel_key {
 			struct in6_addr dst;
 		} ipv6;
 	} u;
-	__be16			tun_flags;
-	u8			tos;		/* TOS for IPv4, TC for IPv6 */
-	u8			ttl;		/* TTL for IPv4, HL for IPv6 */
+	IP_TUNNEL_DECLARE_FLAGS(tun_flags);
 	__be32			label;		/* Flow Label for IPv6 */
 	u32			nhid;
+	u8			tos;		/* TOS for IPv4, TC for IPv6 */
+	u8			ttl;		/* TTL for IPv4, HL for IPv6 */
 	__be16			tp_src;
 	__be16			tp_dst;
 	__u8			flow_flags;
@@ -77,8 +97,8 @@ struct ip_tunnel_encap {
 
 #define ip_tunnel_info_opts(info)				\
 	_Generic(info,						\
-		 const struct ip_tunnel_info * : ((const void *)((info) + 1)),\
-		 struct ip_tunnel_info * : ((void *)((info) + 1))\
+		 const struct ip_tunnel_info * : ((const void *)(info)->options),\
+		 struct ip_tunnel_info * : ((void *)(info)->options)\
 	)
 
 struct ip_tunnel_info {
@@ -89,6 +109,7 @@ struct ip_tunnel_info {
 #endif
 	u8			options_len;
 	u8			mode;
+	u8			options[] __aligned_largest __counted_by(options_len);
 };
 
 /* 6rd prefix/relay information */
@@ -110,6 +131,17 @@ struct ip_tunnel_prl_entry {
 
 struct metadata_dst;
 
+/* Kernel-side variant of ip_tunnel_parm */
+struct ip_tunnel_parm_kern {
+	char			name[IFNAMSIZ];
+	IP_TUNNEL_DECLARE_FLAGS(i_flags);
+	IP_TUNNEL_DECLARE_FLAGS(o_flags);
+	__be32			i_key;
+	__be32			o_key;
+	int			link;
+	struct iphdr		iph;
+};
+
 struct ip_tunnel {
 	struct ip_tunnel __rcu	*next;
 	struct hlist_node hash_node;
@@ -136,7 +168,7 @@ struct ip_tunnel {
 
 	struct dst_cache dst_cache;
 
-	struct ip_tunnel_parm parms;
+	struct ip_tunnel_parm_kern parms;
 
 	int		mlink;
 	int		encap_hlen;	/* Encap header length (FOU,GUE) */
@@ -157,7 +189,7 @@ struct ip_tunnel {
 };
 
 struct tnl_ptk_info {
-	__be16 flags;
+	IP_TUNNEL_DECLARE_FLAGS(flags);
 	__be16 proto;
 	__be32 key;
 	__be32 seq;
@@ -179,11 +211,80 @@ struct ip_tunnel_net {
 	int type;
 };
 
+static inline void ip_tunnel_set_options_present(unsigned long *flags)
+{
+	IP_TUNNEL_DECLARE_FLAGS(present) = { };
+
+	__set_bit(IP_TUNNEL_GENEVE_OPT_BIT, present);
+	__set_bit(IP_TUNNEL_VXLAN_OPT_BIT, present);
+	__set_bit(IP_TUNNEL_ERSPAN_OPT_BIT, present);
+	__set_bit(IP_TUNNEL_GTP_OPT_BIT, present);
+	__set_bit(IP_TUNNEL_PFCP_OPT_BIT, present);
+
+	ip_tunnel_flags_or(flags, flags, present);
+}
+
+static inline void ip_tunnel_clear_options_present(unsigned long *flags)
+{
+	IP_TUNNEL_DECLARE_FLAGS(present) = { };
+
+	__set_bit(IP_TUNNEL_GENEVE_OPT_BIT, present);
+	__set_bit(IP_TUNNEL_VXLAN_OPT_BIT, present);
+	__set_bit(IP_TUNNEL_ERSPAN_OPT_BIT, present);
+	__set_bit(IP_TUNNEL_GTP_OPT_BIT, present);
+	__set_bit(IP_TUNNEL_PFCP_OPT_BIT, present);
+
+	__ipt_flag_op(bitmap_andnot, flags, flags, present);
+}
+
+static inline bool ip_tunnel_is_options_present(const unsigned long *flags)
+{
+	IP_TUNNEL_DECLARE_FLAGS(present) = { };
+
+	__set_bit(IP_TUNNEL_GENEVE_OPT_BIT, present);
+	__set_bit(IP_TUNNEL_VXLAN_OPT_BIT, present);
+	__set_bit(IP_TUNNEL_ERSPAN_OPT_BIT, present);
+	__set_bit(IP_TUNNEL_GTP_OPT_BIT, present);
+	__set_bit(IP_TUNNEL_PFCP_OPT_BIT, present);
+
+	return ip_tunnel_flags_intersect(flags, present);
+}
+
+static inline bool ip_tunnel_flags_is_be16_compat(const unsigned long *flags)
+{
+	IP_TUNNEL_DECLARE_FLAGS(supp) = { };
+
+	bitmap_set(supp, 0, BITS_PER_TYPE(__be16));
+	__set_bit(IP_TUNNEL_VTI_BIT, supp);
+
+	return ip_tunnel_flags_subset(flags, supp);
+}
+
+static inline void ip_tunnel_flags_from_be16(unsigned long *dst, __be16 flags)
+{
+	ip_tunnel_flags_zero(dst);
+
+	bitmap_write(dst, be16_to_cpu(flags), 0, BITS_PER_TYPE(__be16));
+	__assign_bit(IP_TUNNEL_VTI_BIT, dst, flags & VTI_ISVTI);
+}
+
+static inline __be16 ip_tunnel_flags_to_be16(const unsigned long *flags)
+{
+	__be16 ret;
+
+	ret = cpu_to_be16(bitmap_read(flags, 0, BITS_PER_TYPE(__be16)));
+	if (test_bit(IP_TUNNEL_VTI_BIT, flags))
+		ret |= VTI_ISVTI;
+
+	return ret;
+}
+
 static inline void ip_tunnel_key_init(struct ip_tunnel_key *key,
 				      __be32 saddr, __be32 daddr,
 				      u8 tos, u8 ttl, __be32 label,
 				      __be16 tp_src, __be16 tp_dst,
-				      __be64 tun_id, __be16 tun_flags)
+				      __be64 tun_id,
+				      const unsigned long *tun_flags)
 {
 	key->tun_id = tun_id;
 	key->u.ipv4.src = saddr;
@@ -193,7 +294,7 @@ static inline void ip_tunnel_key_init(struct ip_tunnel_key *key,
 	key->tos = tos;
 	key->ttl = ttl;
 	key->label = label;
-	key->tun_flags = tun_flags;
+	ip_tunnel_flags_copy(key->tun_flags, tun_flags);
 
 	/* For the tunnel types on the top of IPsec, the tp_src and tp_dst of
 	 * the upper tunnel are used.
@@ -214,12 +315,8 @@ ip_tunnel_dst_cache_usable(const struct sk_buff *skb,
 {
 	if (skb->mark)
 		return false;
-	if (!info)
-		return true;
-	if (info->key.tun_flags & TUNNEL_NOCACHE)
-		return false;
 
-	return true;
+	return !info || !test_bit(IP_TUNNEL_NOCACHE_BIT, info->key.tun_flags);
 }
 
 static inline unsigned short ip_tunnel_info_af(const struct ip_tunnel_info
@@ -260,14 +357,14 @@ static inline void ip_tunnel_init_flow(struct flowi4 *fl4,
 	memset(fl4, 0, sizeof(*fl4));
 
 	if (oif) {
-		fl4->flowi4_l3mdev = l3mdev_master_upper_ifindex_by_index_rcu(net, oif);
+		fl4->flowi4_l3mdev = l3mdev_master_upper_ifindex_by_index(net, oif);
 		/* Legacy VRF/l3mdev use case */
 		fl4->flowi4_oif = fl4->flowi4_l3mdev ? 0 : oif;
 	}
 
 	fl4->daddr = daddr;
 	fl4->saddr = saddr;
-	fl4->flowi4_tos = tos;
+	fl4->flowi4_dscp = inet_dsfield_to_dscp(tos);
 	fl4->flowi4_proto = proto;
 	fl4->fl4_gre_key = key;
 	fl4->flowi4_mark = mark;
@@ -282,22 +379,26 @@ struct net *ip_tunnel_get_link_net(const struct net_device *dev);
 int ip_tunnel_get_iflink(const struct net_device *dev);
 int ip_tunnel_init_net(struct net *net, unsigned int ip_tnl_net_id,
 		       struct rtnl_link_ops *ops, char *devname);
-
-void ip_tunnel_delete_nets(struct list_head *list_net, unsigned int id,
-			   struct rtnl_link_ops *ops);
+void ip_tunnel_delete_net(struct net *net, unsigned int id,
+			  struct rtnl_link_ops *ops,
+			  struct list_head *dev_to_kill);
 
 void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 		    const struct iphdr *tnl_params, const u8 protocol);
 void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 		       const u8 proto, int tunnel_hlen);
-int ip_tunnel_ctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd);
+int ip_tunnel_ctl(struct net_device *dev, struct ip_tunnel_parm_kern *p,
+		  int cmd);
+bool ip_tunnel_parm_from_user(struct ip_tunnel_parm_kern *kp,
+			      const void __user *data);
+bool ip_tunnel_parm_to_user(void __user *data, struct ip_tunnel_parm_kern *kp);
 int ip_tunnel_siocdevprivate(struct net_device *dev, struct ifreq *ifr,
 			     void __user *data, int cmd);
 int __ip_tunnel_change_mtu(struct net_device *dev, int new_mtu, bool strict);
 int ip_tunnel_change_mtu(struct net_device *dev, int new_mtu);
 
 struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn,
-				   int link, __be16 flags,
+				   int link, const unsigned long *flags,
 				   __be32 remote, __be32 local,
 				   __be32 key);
 
@@ -306,16 +407,17 @@ int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb,
 		  const struct tnl_ptk_info *tpi, struct metadata_dst *tun_dst,
 		  bool log_ecn_error);
 int ip_tunnel_changelink(struct net_device *dev, struct nlattr *tb[],
-			 struct ip_tunnel_parm *p, __u32 fwmark);
-int ip_tunnel_newlink(struct net_device *dev, struct nlattr *tb[],
-		      struct ip_tunnel_parm *p, __u32 fwmark);
+			 struct ip_tunnel_parm_kern *p, __u32 fwmark);
+int ip_tunnel_newlink(struct net *net, struct net_device *dev,
+		      struct nlattr *tb[], struct ip_tunnel_parm_kern *p,
+		      __u32 fwmark);
 void ip_tunnel_setup(struct net_device *dev, unsigned int net_id);
 
 bool ip_tunnel_netlink_encap_parms(struct nlattr *data[],
 				   struct ip_tunnel_encap *encap);
 
 void ip_tunnel_netlink_parms(struct nlattr *data[],
-			     struct ip_tunnel_parm *parms);
+			     struct ip_tunnel_parm_kern *parms);
 
 extern const struct header_ops ip_tunnel_header_ops;
 __be16 ip_tunnel_parse_protocol(const struct sk_buff *skb);
@@ -340,7 +442,8 @@ int ip_tunnel_encap_del_ops(const struct ip_tunnel_encap_ops *op,
 int ip_tunnel_encap_setup(struct ip_tunnel *t,
 			  struct ip_tunnel_encap *ipencap);
 
-static inline bool pskb_inet_may_pull(struct sk_buff *skb)
+static inline enum skb_drop_reason
+pskb_inet_may_pull_reason(struct sk_buff *skb)
 {
 	int nhlen;
 
@@ -357,7 +460,49 @@ static inline bool pskb_inet_may_pull(struct sk_buff *skb)
 		nhlen = 0;
 	}
 
-	return pskb_network_may_pull(skb, nhlen);
+	return pskb_network_may_pull_reason(skb, nhlen);
+}
+
+static inline bool pskb_inet_may_pull(struct sk_buff *skb)
+{
+	return pskb_inet_may_pull_reason(skb) == SKB_NOT_DROPPED_YET;
+}
+
+/* Variant of pskb_inet_may_pull().
+ */
+static inline enum skb_drop_reason
+skb_vlan_inet_prepare(struct sk_buff *skb, bool inner_proto_inherit)
+{
+	int nhlen = 0, maclen = inner_proto_inherit ? 0 : ETH_HLEN;
+	__be16 type = skb->protocol;
+	enum skb_drop_reason reason;
+
+	/* Essentially this is skb_protocol(skb, true)
+	 * And we get MAC len.
+	 */
+	if (eth_type_vlan(type))
+		type = __vlan_get_protocol(skb, type, &maclen);
+
+	switch (type) {
+#if IS_ENABLED(CONFIG_IPV6)
+	case htons(ETH_P_IPV6):
+		nhlen = sizeof(struct ipv6hdr);
+		break;
+#endif
+	case htons(ETH_P_IP):
+		nhlen = sizeof(struct iphdr);
+		break;
+	}
+	/* For ETH_P_IPV6/ETH_P_IP we make sure to pull
+	 * a base network header in skb->head.
+	 */
+	reason = pskb_may_pull_reason(skb, maclen + nhlen);
+	if (reason)
+		return reason;
+
+	skb_set_network_header(skb, maclen);
+
+	return SKB_NOT_DROPPED_YET;
 }
 
 static inline int ip_encap_hlen(struct ip_tunnel_encap *e)
@@ -416,6 +561,17 @@ static inline u8 ip_tunnel_get_dsfield(const struct iphdr *iph,
 		return 0;
 }
 
+static inline __be32 ip_tunnel_get_flowlabel(const struct iphdr *iph,
+					     const struct sk_buff *skb)
+{
+	__be16 payload_protocol = skb_protocol(skb, true);
+
+	if (payload_protocol == htons(ETH_P_IPV6))
+		return ip6_flowlabel((const struct ipv6hdr *)iph);
+	else
+		return 0;
+}
+
 static inline u8 ip_tunnel_get_ttl(const struct iphdr *iph,
 				       const struct sk_buff *skb)
 {
@@ -429,7 +585,7 @@ static inline u8 ip_tunnel_get_ttl(const struct iphdr *iph,
 		return 0;
 }
 
-/* Propogate ECN bits out */
+/* Propagate ECN bits out */
 static inline u8 ip_tunnel_ecn_encap(u8 tos, const struct iphdr *iph,
 				     const struct sk_buff *skb)
 {
@@ -449,12 +605,27 @@ static inline int iptunnel_pull_header(struct sk_buff *skb, int hdr_len,
 
 void iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb,
 		   __be32 src, __be32 dst, u8 proto,
-		   u8 tos, u8 ttl, __be16 df, bool xnet);
+		   u8 tos, u8 ttl, __be16 df, bool xnet, u16 ipcb_flags);
 struct metadata_dst *iptunnel_metadata_reply(struct metadata_dst *md,
 					     gfp_t flags);
 int skb_tunnel_check_pmtu(struct sk_buff *skb, struct dst_entry *encap_dst,
 			  int headroom, bool reply);
 
+static inline void ip_tunnel_adj_headroom(struct net_device *dev,
+					  unsigned int headroom)
+{
+	/* we must cap headroom to some upperlimit, else pskb_expand_head
+	 * will overflow header offsets in skb_headers_offset_update().
+	 */
+	const unsigned int max_allowed = 512;
+
+	if (headroom > max_allowed)
+		headroom = max_allowed;
+
+	if (headroom > READ_ONCE(dev->needed_headroom))
+		WRITE_ONCE(dev->needed_headroom, headroom);
+}
+
 int iptunnel_handle_offloads(struct sk_buff *skb, int gso_type_mask);
 
 static inline int iptunnel_pull_offloads(struct sk_buff *skb)
@@ -483,32 +654,32 @@ static inline void iptunnel_xmit_stats(struct net_device *dev, int pkt_len)
 		u64_stats_inc(&tstats->tx_packets);
 		u64_stats_update_end(&tstats->syncp);
 		put_cpu_ptr(tstats);
+		return;
+	}
+
+	if (pkt_len < 0) {
+		DEV_STATS_INC(dev, tx_errors);
+		DEV_STATS_INC(dev, tx_aborted_errors);
 	} else {
-		struct net_device_stats *err_stats = &dev->stats;
-
-		if (pkt_len < 0) {
-			err_stats->tx_errors++;
-			err_stats->tx_aborted_errors++;
-		} else {
-			err_stats->tx_dropped++;
-		}
+		DEV_STATS_INC(dev, tx_dropped);
 	}
 }
 
 static inline void ip_tunnel_info_opts_get(void *to,
 					   const struct ip_tunnel_info *info)
 {
-	memcpy(to, info + 1, info->options_len);
+	memcpy(to, ip_tunnel_info_opts(info), info->options_len);
 }
 
 static inline void ip_tunnel_info_opts_set(struct ip_tunnel_info *info,
 					   const void *from, int len,
-					   __be16 flags)
+					   const unsigned long *flags)
 {
 	info->options_len = len;
 	if (len > 0) {
 		memcpy(ip_tunnel_info_opts(info), from, len);
-		info->key.tun_flags |= flags;
+		ip_tunnel_flags_or(info->key.tun_flags, info->key.tun_flags,
+				   flags);
 	}
 }
 
@@ -552,7 +723,7 @@ static inline void ip_tunnel_info_opts_get(void *to,
 
 static inline void ip_tunnel_info_opts_set(struct ip_tunnel_info *info,
 					   const void *from, int len,
-					   __be16 flags)
+					   const unsigned long *flags)
 {
 	info->options_len = 0;
 }