23 files changed, 973 insertions, 180 deletions

diff --git a/include/linux/netfilter_bridge.h b/include/linux/netfilter_bridge.h
index 5fc0a0fe244b..ab8f76dba668 100644
--- a/include/linux/netfilter_bridge.h
+++ b/include/linux/netfilter_bridge.h
@@ -2,7 +2,7 @@
 #define __LINUX_BRIDGE_NETFILTER_H
 
 #include <uapi/linux/netfilter_bridge.h>
-
+#include <linux/skbuff.h>
 
 enum nf_br_hook_priorities {
 	NF_BR_PRI_FIRST = INT_MIN,
@@ -17,15 +17,12 @@ enum nf_br_hook_priorities {
 
 #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
 
-#define BRNF_PKT_TYPE			0x01
 #define BRNF_BRIDGED_DNAT		0x02
 #define BRNF_NF_BRIDGE_PREROUTING	0x08
-#define BRNF_8021Q			0x10
-#define BRNF_PPPoE			0x20
 
 static inline unsigned int nf_bridge_mtu_reduction(const struct sk_buff *skb)
 {
-	if (unlikely(skb->nf_bridge->mask & BRNF_PPPoE))
+	if (skb->nf_bridge->orig_proto == BRNF_PROTO_PPPOE)
 		return PPPOE_SES_HLEN;
 	return 0;
 }
@@ -40,6 +37,27 @@ static inline void br_drop_fake_rtable(struct sk_buff *skb)
 		skb_dst_drop(skb);
 }
 
+static inline int nf_bridge_get_physinif(const struct sk_buff *skb)
+{
+	return skb->nf_bridge ? skb->nf_bridge->physindev->ifindex : 0;
+}
+
+static inline int nf_bridge_get_physoutif(const struct sk_buff *skb)
+{
+	return skb->nf_bridge ? skb->nf_bridge->physoutdev->ifindex : 0;
+}
+
+static inline struct net_device *
+nf_bridge_get_physindev(const struct sk_buff *skb)
+{
+	return skb->nf_bridge ? skb->nf_bridge->physindev : NULL;
+}
+
+static inline struct net_device *
+nf_bridge_get_physoutdev(const struct sk_buff *skb)
+{
+	return skb->nf_bridge ? skb->nf_bridge->physoutdev : NULL;
+}
 #else
 #define br_drop_fake_rtable(skb)	        do { } while (0)
 #endif /* CONFIG_BRIDGE_NETFILTER */
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 36f3f43c0117..0991259643d6 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -166,10 +166,16 @@ struct nf_conntrack {
 #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
 struct nf_bridge_info {
 	atomic_t		use;
+	enum {
+		BRNF_PROTO_UNCHANGED,
+		BRNF_PROTO_8021Q,
+		BRNF_PROTO_PPPOE
+	} orig_proto;
+	bool			pkt_otherhost;
 	unsigned int		mask;
 	struct net_device	*physindev;
 	struct net_device	*physoutdev;
-	unsigned long		data[32 / sizeof(unsigned long)];
+	char			neigh_header[8];
 };
 #endif
 
diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 804981980393..d6a2f0ed5130 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -195,6 +195,7 @@ struct nft_set_estimate {
 };
 
 struct nft_set_ext;
+struct nft_expr;
 
 /**
  *	struct nft_set_ops - nf_tables set operations
@@ -217,6 +218,15 @@ struct nft_set_ops {
 	bool				(*lookup)(const struct nft_set *set,
 						  const struct nft_data *key,
 						  const struct nft_set_ext **ext);
+	bool				(*update)(struct nft_set *set,
+						  const struct nft_data *key,
+						  void *(*new)(struct nft_set *,
+							       const struct nft_expr *,
+							       struct nft_data []),
+						  const struct nft_expr *expr,
+						  struct nft_data data[],
+						  const struct nft_set_ext **ext);
+
 	int				(*insert)(const struct nft_set *set,
 						  const struct nft_set_elem *elem);
 	void				(*activate)(const struct nft_set *set,
@@ -257,6 +267,9 @@ void nft_unregister_set(struct nft_set_ops *ops);
  * 	@dtype: data type (verdict or numeric type defined by userspace)
  * 	@size: maximum set size
  * 	@nelems: number of elements
+ * 	@ndeact: number of deactivated elements queued for removal
+ * 	@timeout: default timeout value in msecs
+ * 	@gc_int: garbage collection interval in msecs
  *	@policy: set parameterization (see enum nft_set_policies)
  * 	@ops: set ops
  * 	@pnet: network namespace
@@ -272,7 +285,10 @@ struct nft_set {
 	u32				ktype;
 	u32				dtype;
 	u32				size;
-	u32				nelems;
+	atomic_t			nelems;
+	u32				ndeact;
+	u64				timeout;
+	u32				gc_int;
 	u16				policy;
 	/* runtime data below here */
 	const struct nft_set_ops	*ops ____cacheline_aligned;
@@ -289,16 +305,27 @@ static inline void *nft_set_priv(const struct nft_set *set)
 	return (void *)set->data;
 }
 
+static inline struct nft_set *nft_set_container_of(const void *priv)
+{
+	return (void *)priv - offsetof(struct nft_set, data);
+}
+
 struct nft_set *nf_tables_set_lookup(const struct nft_table *table,
 				     const struct nlattr *nla);
 struct nft_set *nf_tables_set_lookup_byid(const struct net *net,
 					  const struct nlattr *nla);
 
+static inline unsigned long nft_set_gc_interval(const struct nft_set *set)
+{
+	return set->gc_int ? msecs_to_jiffies(set->gc_int) : HZ;
+}
+
 /**
  *	struct nft_set_binding - nf_tables set binding
  *
  *	@list: set bindings list node
  *	@chain: chain containing the rule bound to the set
+ *	@flags: set action flags
  *
  *	A set binding contains all information necessary for validation
  *	of new elements added to a bound set.
@@ -306,6 +333,7 @@ struct nft_set *nf_tables_set_lookup_byid(const struct net *net,
 struct nft_set_binding {
 	struct list_head		list;
 	const struct nft_chain		*chain;
+	u32				flags;
 };
 
 int nf_tables_bind_set(const struct nft_ctx *ctx, struct nft_set *set,
@@ -319,12 +347,18 @@ void nf_tables_unbind_set(const struct nft_ctx *ctx, struct nft_set *set,
  *	@NFT_SET_EXT_KEY: element key
  *	@NFT_SET_EXT_DATA: mapping data
  *	@NFT_SET_EXT_FLAGS: element flags
+ *	@NFT_SET_EXT_TIMEOUT: element timeout
+ *	@NFT_SET_EXT_EXPIRATION: element expiration time
+ *	@NFT_SET_EXT_USERDATA: user data associated with the element
  *	@NFT_SET_EXT_NUM: number of extension types
  */
 enum nft_set_extensions {
 	NFT_SET_EXT_KEY,
 	NFT_SET_EXT_DATA,
 	NFT_SET_EXT_FLAGS,
+	NFT_SET_EXT_TIMEOUT,
+	NFT_SET_EXT_EXPIRATION,
+	NFT_SET_EXT_USERDATA,
 	NFT_SET_EXT_NUM
 };
 
@@ -421,15 +455,97 @@ static inline u8 *nft_set_ext_flags(const struct nft_set_ext *ext)
 	return nft_set_ext(ext, NFT_SET_EXT_FLAGS);
 }
 
+static inline u64 *nft_set_ext_timeout(const struct nft_set_ext *ext)
+{
+	return nft_set_ext(ext, NFT_SET_EXT_TIMEOUT);
+}
+
+static inline unsigned long *nft_set_ext_expiration(const struct nft_set_ext *ext)
+{
+	return nft_set_ext(ext, NFT_SET_EXT_EXPIRATION);
+}
+
+static inline struct nft_userdata *nft_set_ext_userdata(const struct nft_set_ext *ext)
+{
+	return nft_set_ext(ext, NFT_SET_EXT_USERDATA);
+}
+
+static inline bool nft_set_elem_expired(const struct nft_set_ext *ext)
+{
+	return nft_set_ext_exists(ext, NFT_SET_EXT_EXPIRATION) &&
+	       time_is_before_eq_jiffies(*nft_set_ext_expiration(ext));
+}
+
 static inline struct nft_set_ext *nft_set_elem_ext(const struct nft_set *set,
 						   void *elem)
 {
 	return elem + set->ops->elemsize;
 }
 
+void *nft_set_elem_init(const struct nft_set *set,
+			const struct nft_set_ext_tmpl *tmpl,
+			const struct nft_data *key,
+			const struct nft_data *data,
+			u64 timeout, gfp_t gfp);
 void nft_set_elem_destroy(const struct nft_set *set, void *elem);
 
 /**
+ *	struct nft_set_gc_batch_head - nf_tables set garbage collection batch
+ *
+ *	@rcu: rcu head
+ *	@set: set the elements belong to
+ *	@cnt: count of elements
+ */
+struct nft_set_gc_batch_head {
+	struct rcu_head			rcu;
+	const struct nft_set		*set;
+	unsigned int			cnt;
+};
+
+#define NFT_SET_GC_BATCH_SIZE	((PAGE_SIZE -				  \
+				  sizeof(struct nft_set_gc_batch_head)) / \
+				 sizeof(void *))
+
+/**
+ *	struct nft_set_gc_batch - nf_tables set garbage collection batch
+ *
+ * 	@head: GC batch head
+ * 	@elems: garbage collection elements
+ */
+struct nft_set_gc_batch {
+	struct nft_set_gc_batch_head	head;
+	void				*elems[NFT_SET_GC_BATCH_SIZE];
+};
+
+struct nft_set_gc_batch *nft_set_gc_batch_alloc(const struct nft_set *set,
+						gfp_t gfp);
+void nft_set_gc_batch_release(struct rcu_head *rcu);
+
+static inline void nft_set_gc_batch_complete(struct nft_set_gc_batch *gcb)
+{
+	if (gcb != NULL)
+		call_rcu(&gcb->head.rcu, nft_set_gc_batch_release);
+}
+
+static inline struct nft_set_gc_batch *
+nft_set_gc_batch_check(const struct nft_set *set, struct nft_set_gc_batch *gcb,
+		       gfp_t gfp)
+{
+	if (gcb != NULL) {
+		if (gcb->head.cnt + 1 < ARRAY_SIZE(gcb->elems))
+			return gcb;
+		nft_set_gc_batch_complete(gcb);
+	}
+	return nft_set_gc_batch_alloc(set, gfp);
+}
+
+static inline void nft_set_gc_batch_add(struct nft_set_gc_batch *gcb,
+					void *elem)
+{
+	gcb->elems[gcb->head.cnt++] = elem;
+}
+
+/**
  *	struct nft_expr_type - nf_tables expression type
  *
  *	@select_ops: function to select nft_expr_ops
@@ -750,6 +866,8 @@ static inline u8 nft_genmask_cur(const struct net *net)
 	return 1 << ACCESS_ONCE(net->nft.gencursor);
 }
 
+#define NFT_GENMASK_ANY		((1 << 0) | (1 << 1))
+
 /*
  * Set element transaction helpers
  */
@@ -766,6 +884,41 @@ static inline void nft_set_elem_change_active(const struct nft_set *set,
 	ext->genmask ^= nft_genmask_next(read_pnet(&set->pnet));
 }
 
+/*
+ * We use a free bit in the genmask field to indicate the element
+ * is busy, meaning it is currently being processed either by
+ * the netlink API or GC.
+ *
+ * Even though the genmask is only a single byte wide, this works
+ * because the extension structure if fully constant once initialized,
+ * so there are no non-atomic write accesses unless it is already
+ * marked busy.
+ */
+#define NFT_SET_ELEM_BUSY_MASK	(1 << 2)
+
+#if defined(__LITTLE_ENDIAN_BITFIELD)
+#define NFT_SET_ELEM_BUSY_BIT	2
+#elif defined(__BIG_ENDIAN_BITFIELD)
+#define NFT_SET_ELEM_BUSY_BIT	(BITS_PER_LONG - BITS_PER_BYTE + 2)
+#else
+#error
+#endif
+
+static inline int nft_set_elem_mark_busy(struct nft_set_ext *ext)
+{
+	unsigned long *word = (unsigned long *)ext;
+
+	BUILD_BUG_ON(offsetof(struct nft_set_ext, genmask) != 0);
+	return test_and_set_bit(NFT_SET_ELEM_BUSY_BIT, word);
+}
+
+static inline void nft_set_elem_clear_busy(struct nft_set_ext *ext)
+{
+	unsigned long *word = (unsigned long *)ext;
+
+	clear_bit(NFT_SET_ELEM_BUSY_BIT, word);
+}
+
 /**
  *	struct nft_trans - nf_tables object update in transaction
  *
diff --git a/include/net/netfilter/nf_tables_core.h b/include/net/netfilter/nf_tables_core.h
index a75fc8e27cd6..c6f400cfaac8 100644
--- a/include/net/netfilter/nf_tables_core.h
+++ b/include/net/netfilter/nf_tables_core.h
@@ -31,6 +31,9 @@ void nft_cmp_module_exit(void);
 int nft_lookup_module_init(void);
 void nft_lookup_module_exit(void);
 
+int nft_dynset_module_init(void);
+void nft_dynset_module_exit(void);
+
 int nft_bitwise_module_init(void);
 void nft_bitwise_module_exit(void);
 
diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h
index b9783931503b..05ee1e0804a3 100644
--- a/include/uapi/linux/netfilter/nf_tables.h
+++ b/include/uapi/linux/netfilter/nf_tables.h
@@ -208,12 +208,14 @@ enum nft_rule_compat_attributes {
  * @NFT_SET_CONSTANT: set contents may not change while bound
  * @NFT_SET_INTERVAL: set contains intervals
  * @NFT_SET_MAP: set is used as a dictionary
+ * @NFT_SET_TIMEOUT: set uses timeouts
  */
 enum nft_set_flags {
 	NFT_SET_ANONYMOUS		= 0x1,
 	NFT_SET_CONSTANT		= 0x2,
 	NFT_SET_INTERVAL		= 0x4,
 	NFT_SET_MAP			= 0x8,
+	NFT_SET_TIMEOUT			= 0x10,
 };
 
 /**
@@ -252,6 +254,8 @@ enum nft_set_desc_attributes {
  * @NFTA_SET_POLICY: selection policy (NLA_U32)
  * @NFTA_SET_DESC: set description (NLA_NESTED)
  * @NFTA_SET_ID: uniquely identifies a set in a transaction (NLA_U32)
+ * @NFTA_SET_TIMEOUT: default timeout value (NLA_U64)
+ * @NFTA_SET_GC_INTERVAL: garbage collection interval (NLA_U32)
  */
 enum nft_set_attributes {
 	NFTA_SET_UNSPEC,
@@ -265,6 +269,8 @@ enum nft_set_attributes {
 	NFTA_SET_POLICY,
 	NFTA_SET_DESC,
 	NFTA_SET_ID,
+	NFTA_SET_TIMEOUT,
+	NFTA_SET_GC_INTERVAL,
 	__NFTA_SET_MAX
 };
 #define NFTA_SET_MAX		(__NFTA_SET_MAX - 1)
@@ -284,12 +290,18 @@ enum nft_set_elem_flags {
  * @NFTA_SET_ELEM_KEY: key value (NLA_NESTED: nft_data)
  * @NFTA_SET_ELEM_DATA: data value of mapping (NLA_NESTED: nft_data_attributes)
  * @NFTA_SET_ELEM_FLAGS: bitmask of nft_set_elem_flags (NLA_U32)
+ * @NFTA_SET_ELEM_TIMEOUT: timeout value (NLA_U64)
+ * @NFTA_SET_ELEM_EXPIRATION: expiration time (NLA_U64)
+ * @NFTA_SET_ELEM_USERDATA: user data (NLA_BINARY)
  */
 enum nft_set_elem_attributes {
 	NFTA_SET_ELEM_UNSPEC,
 	NFTA_SET_ELEM_KEY,
 	NFTA_SET_ELEM_DATA,
 	NFTA_SET_ELEM_FLAGS,
+	NFTA_SET_ELEM_TIMEOUT,
+	NFTA_SET_ELEM_EXPIRATION,
+	NFTA_SET_ELEM_USERDATA,
 	__NFTA_SET_ELEM_MAX
 };
 #define NFTA_SET_ELEM_MAX	(__NFTA_SET_ELEM_MAX - 1)
@@ -505,6 +517,33 @@ enum nft_lookup_attributes {
 };
 #define NFTA_LOOKUP_MAX		(__NFTA_LOOKUP_MAX - 1)
 
+enum nft_dynset_ops {
+	NFT_DYNSET_OP_ADD,
+	NFT_DYNSET_OP_UPDATE,
+};
+
+/**
+ * enum nft_dynset_attributes - dynset expression attributes
+ *
+ * @NFTA_DYNSET_SET_NAME: name of set the to add data to (NLA_STRING)
+ * @NFTA_DYNSET_SET_ID: uniquely identifier of the set in the transaction (NLA_U32)
+ * @NFTA_DYNSET_OP: operation (NLA_U32)
+ * @NFTA_DYNSET_SREG_KEY: source register of the key (NLA_U32)
+ * @NFTA_DYNSET_SREG_DATA: source register of the data (NLA_U32)
+ * @NFTA_DYNSET_TIMEOUT: timeout value for the new element (NLA_U64)
+ */
+enum nft_dynset_attributes {
+	NFTA_DYNSET_UNSPEC,
+	NFTA_DYNSET_SET_NAME,
+	NFTA_DYNSET_SET_ID,
+	NFTA_DYNSET_OP,
+	NFTA_DYNSET_SREG_KEY,
+	NFTA_DYNSET_SREG_DATA,
+	NFTA_DYNSET_TIMEOUT,
+	__NFTA_DYNSET_MAX,
+};
+#define NFTA_DYNSET_MAX		(__NFTA_DYNSET_MAX - 1)
+
 /**
  * enum nft_payload_bases - nf_tables payload expression offset bases
  *
diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c
index acd31c9f2116..ab55e2472beb 100644
--- a/net/bridge/br_netfilter.c
+++ b/net/bridge/br_netfilter.c
@@ -111,6 +111,24 @@ static inline __be16 pppoe_proto(const struct sk_buff *skb)
 	 pppoe_proto(skb) == htons(PPP_IPV6) && \
 	 brnf_filter_pppoe_tagged)
 
+/* largest possible L2 header, see br_nf_dev_queue_xmit() */
+#define NF_BRIDGE_MAX_MAC_HEADER_LENGTH (PPPOE_SES_HLEN + ETH_HLEN)
+
+#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV4)
+struct brnf_frag_data {
+	char mac[NF_BRIDGE_MAX_MAC_HEADER_LENGTH];
+	u8 encap_size;
+	u8 size;
+};
+
+static DEFINE_PER_CPU(struct brnf_frag_data, brnf_frag_data_storage);
+#endif
+
+static struct nf_bridge_info *nf_bridge_info_get(const struct sk_buff *skb)
+{
+	return skb->nf_bridge;
+}
+
 static inline struct rtable *bridge_parent_rtable(const struct net_device *dev)
 {
 	struct net_bridge_port *port;
@@ -189,14 +207,6 @@ static inline void nf_bridge_pull_encap_header_rcsum(struct sk_buff *skb)
 	skb->network_header += len;
 }
 
-static inline void nf_bridge_save_header(struct sk_buff *skb)
-{
-	int header_size = ETH_HLEN + nf_bridge_encap_header_len(skb);
-
-	skb_copy_from_linear_data_offset(skb, -header_size,
-					 skb->nf_bridge->data, header_size);
-}
-
 /* When handing a packet over to the IP layer
  * check whether we have a skb that is in the
  * expected format
@@ -252,10 +262,16 @@ drop:
 
 static void nf_bridge_update_protocol(struct sk_buff *skb)
 {
-	if (skb->nf_bridge->mask & BRNF_8021Q)
+	switch (skb->nf_bridge->orig_proto) {
+	case BRNF_PROTO_8021Q:
 		skb->protocol = htons(ETH_P_8021Q);
-	else if (skb->nf_bridge->mask & BRNF_PPPoE)
+		break;
+	case BRNF_PROTO_PPPOE:
 		skb->protocol = htons(ETH_P_PPP_SES);
+		break;
+	case BRNF_PROTO_UNCHANGED:
+		break;
+	}
 }
 
 /* PF_BRIDGE/PRE_ROUTING *********************************************/
@@ -263,12 +279,12 @@ static void nf_bridge_update_protocol(struct sk_buff *skb)
  * bridge PRE_ROUTING hook. */
 static int br_nf_pre_routing_finish_ipv6(struct sock *sk, struct sk_buff *skb)
 {
-	struct nf_bridge_info *nf_bridge = skb->nf_bridge;
+	struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb);
 	struct rtable *rt;
 
-	if (nf_bridge->mask & BRNF_PKT_TYPE) {
+	if (nf_bridge->pkt_otherhost) {
 		skb->pkt_type = PACKET_OTHERHOST;
-		nf_bridge->mask ^= BRNF_PKT_TYPE;
+		nf_bridge->pkt_otherhost = false;
 	}
 	nf_bridge->mask ^= BRNF_NF_BRIDGE_PREROUTING;
 
@@ -296,7 +312,6 @@ static int br_nf_pre_routing_finish_ipv6(struct sock *sk, struct sk_buff *skb)
  */
 static int br_nf_pre_routing_finish_bridge(struct sock *sk, struct sk_buff *skb)
 {
-	struct nf_bridge_info *nf_bridge = skb->nf_bridge;
 	struct neighbour *neigh;
 	struct dst_entry *dst;
 
@@ -306,6 +321,7 @@ static int br_nf_pre_routing_finish_bridge(struct sock *sk, struct sk_buff *skb)
 	dst = skb_dst(skb);
 	neigh = dst_neigh_lookup_skb(dst, skb);
 	if (neigh) {
+		struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb);
 		int ret;
 
 		if (neigh->hh.hh_len) {
@@ -319,7 +335,7 @@ static int br_nf_pre_routing_finish_bridge(struct sock *sk, struct sk_buff *skb)
 			 */
 			skb_copy_from_linear_data_offset(skb,
 							 -(ETH_HLEN-ETH_ALEN),
-							 skb->nf_bridge->data,
+							 nf_bridge->neigh_header,
 							 ETH_HLEN-ETH_ALEN);
 			/* tell br_dev_xmit to continue with forwarding */
 			nf_bridge->mask |= BRNF_BRIDGED_DNAT;
@@ -392,7 +408,7 @@ static int br_nf_pre_routing_finish(struct sock *sk, struct sk_buff *skb)
 {
 	struct net_device *dev = skb->dev;
 	struct iphdr *iph = ip_hdr(skb);
-	struct nf_bridge_info *nf_bridge = skb->nf_bridge;
+	struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb);
 	struct rtable *rt;
 	int err;
 	int frag_max_size;
@@ -400,9 +416,9 @@ static int br_nf_pre_routing_finish(struct sock *sk, struct sk_buff *skb)
 	frag_max_size = IPCB(skb)->frag_max_size;
 	BR_INPUT_SKB_CB(skb)->frag_max_size = frag_max_size;
 
-	if (nf_bridge->mask & BRNF_PKT_TYPE) {
+	if (nf_bridge->pkt_otherhost) {
 		skb->pkt_type = PACKET_OTHERHOST;
-		nf_bridge->mask ^= BRNF_PKT_TYPE;
+		nf_bridge->pkt_otherhost = false;
 	}
 	nf_bridge->mask ^= BRNF_NF_BRIDGE_PREROUTING;
 	if (dnat_took_place(skb)) {
@@ -485,20 +501,21 @@ static struct net_device *brnf_get_logical_dev(struct sk_buff *skb, const struct
 /* Some common code for IPv4/IPv6 */
 static struct net_device *setup_pre_routing(struct sk_buff *skb)
 {
-	struct nf_bridge_info *nf_bridge = skb->nf_bridge;
+	struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb);
 
 	if (skb->pkt_type == PACKET_OTHERHOST) {
 		skb->pkt_type = PACKET_HOST;
-		nf_bridge->mask |= BRNF_PKT_TYPE;
+		nf_bridge->pkt_otherhost = true;
 	}
 
 	nf_bridge->mask |= BRNF_NF_BRIDGE_PREROUTING;
 	nf_bridge->physindev = skb->dev;
 	skb->dev = brnf_get_logical_dev(skb, skb->dev);
+
 	if (skb->protocol == htons(ETH_P_8021Q))
-		nf_bridge->mask |= BRNF_8021Q;
+		nf_bridge->orig_proto = BRNF_PROTO_8021Q;
 	else if (skb->protocol == htons(ETH_P_PPP_SES))
-		nf_bridge->mask |= BRNF_PPPoE;
+		nf_bridge->orig_proto = BRNF_PROTO_PPPOE;
 
 	/* Must drop socket now because of tproxy. */
 	skb_orphan(skb);
@@ -680,14 +697,21 @@ static unsigned int br_nf_local_in(const struct nf_hook_ops *ops,
 /* PF_BRIDGE/FORWARD *************************************************/
 static int br_nf_forward_finish(struct sock *sk, struct sk_buff *skb)
 {
-	struct nf_bridge_info *nf_bridge = skb->nf_bridge;
+	struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb);
 	struct net_device *in;
 
 	if (!IS_ARP(skb) && !IS_VLAN_ARP(skb)) {
+		int frag_max_size;
+
+		if (skb->protocol == htons(ETH_P_IP)) {
+			frag_max_size = IPCB(skb)->frag_max_size;
+			BR_INPUT_SKB_CB(skb)->frag_max_size = frag_max_size;
+		}
+
 		in = nf_bridge->physindev;
-		if (nf_bridge->mask & BRNF_PKT_TYPE) {
+		if (nf_bridge->pkt_otherhost) {
 			skb->pkt_type = PACKET_OTHERHOST;
-			nf_bridge->mask ^= BRNF_PKT_TYPE;
+			nf_bridge->pkt_otherhost = false;
 		}
 		nf_bridge_update_protocol(skb);
 	} else {
@@ -722,6 +746,10 @@ static unsigned int br_nf_forward_ip(const struct nf_hook_ops *ops,
 	if (!nf_bridge_unshare(skb))
 		return NF_DROP;
 
+	nf_bridge = nf_bridge_info_get(skb);
+	if (!nf_bridge)
+		return NF_DROP;
+
 	parent = bridge_parent(state->out);
 	if (!parent)
 		return NF_DROP;
@@ -735,14 +763,19 @@ static unsigned int br_nf_forward_ip(const struct nf_hook_ops *ops,
 
 	nf_bridge_pull_encap_header(skb);
 
-	nf_bridge = skb->nf_bridge;
 	if (skb->pkt_type == PACKET_OTHERHOST) {
 		skb->pkt_type = PACKET_HOST;
-		nf_bridge->mask |= BRNF_PKT_TYPE;
+		nf_bridge->pkt_otherhost = true;
 	}
 
-	if (pf == NFPROTO_IPV4 && br_parse_ip_options(skb))
-		return NF_DROP;
+	if (pf == NFPROTO_IPV4) {
+		int frag_max = BR_INPUT_SKB_CB(skb)->frag_max_size;
+
+		if (br_parse_ip_options(skb))
+			return NF_DROP;
+
+		IPCB(skb)->frag_max_size = frag_max;
+	}
 
 	nf_bridge->physoutdev = skb->dev;
 	if (pf == NFPROTO_IPV4)
@@ -792,30 +825,22 @@ static unsigned int br_nf_forward_arp(const struct nf_hook_ops *ops,
 }
 
 #if IS_ENABLED(CONFIG_NF_DEFRAG_IPV4)
-static bool nf_bridge_copy_header(struct sk_buff *skb)
+static int br_nf_push_frag_xmit(struct sock *sk, struct sk_buff *skb)
 {
+	struct brnf_frag_data *data;
 	int err;
-	unsigned int header_size;
 
-	nf_bridge_update_protocol(skb);
-	header_size = ETH_HLEN + nf_bridge_encap_header_len(skb);
-	err = skb_cow_head(skb, header_size);
-	if (err)
-		return false;
-
-	skb_copy_to_linear_data_offset(skb, -header_size,
-				       skb->nf_bridge->data, header_size);
-	__skb_push(skb, nf_bridge_encap_header_len(skb));
-	return true;
-}
+	data = this_cpu_ptr(&brnf_frag_data_storage);
+	err = skb_cow_head(skb, data->size);
 
-static int br_nf_push_frag_xmit(struct sock *sk, struct sk_buff *skb)
-{
-	if (!nf_bridge_copy_header(skb)) {
+	if (err) {
 		kfree_skb(skb);
 		return 0;
 	}
 
+	skb_copy_to_linear_data_offset(skb, -data->size, data->mac, data->size);
+	__skb_push(skb, data->encap_size);
+
 	return br_dev_queue_push_xmit(sk, skb);
 }
 
@@ -833,14 +858,27 @@ static int br_nf_dev_queue_xmit(struct sock *sk, struct sk_buff *skb)
 	 * boundaries by preserving frag_list rather than refragmenting.
 	 */
 	if (skb->len + mtu_reserved > skb->dev->mtu) {
+		struct brnf_frag_data *data;
+
 		frag_max_size = BR_INPUT_SKB_CB(skb)->frag_max_size;
 		if (br_parse_ip_options(skb))
 			/* Drop invalid packet */
 			return NF_DROP;
 		IPCB(skb)->frag_max_size = frag_max_size;
+
+		nf_bridge_update_protocol(skb);
+
+		data = this_cpu_ptr(&brnf_frag_data_storage);
+		data->encap_size = nf_bridge_encap_header_len(skb);
+		data->size = ETH_HLEN + data->encap_size;
+
+		skb_copy_from_linear_data_offset(skb, -data->size, data->mac,
+						 data->size);
+
 		ret = ip_fragment(sk, skb, br_nf_push_frag_xmit);
-	} else
+	} else {
 		ret = br_dev_queue_push_xmit(sk, skb);
+	}
 
 	return ret;
 }
@@ -856,7 +894,7 @@ static unsigned int br_nf_post_routing(const struct nf_hook_ops *ops,
 				       struct sk_buff *skb,
 				       const struct nf_hook_state *state)
 {
-	struct nf_bridge_info *nf_bridge = skb->nf_bridge;
+	struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb);
 	struct net_device *realoutdev = bridge_parent(skb->dev);
 	u_int8_t pf;
 
@@ -882,11 +920,10 @@ static unsigned int br_nf_post_routing(const struct nf_hook_ops *ops,
 	 * about the value of skb->pkt_type. */
 	if (skb->pkt_type == PACKET_OTHERHOST) {
 		skb->pkt_type = PACKET_HOST;
-		nf_bridge->mask |= BRNF_PKT_TYPE;
+		nf_bridge->pkt_otherhost = true;
 	}
 
 	nf_bridge_pull_encap_header(skb);
-	nf_bridge_save_header(skb);
 	if (pf == NFPROTO_IPV4)
 		skb->protocol = htons(ETH_P_IP);
 	else
@@ -925,13 +962,16 @@ static unsigned int ip_sabotage_in(const struct nf_hook_ops *ops,
  */
 static void br_nf_pre_routing_finish_bridge_slow(struct sk_buff *skb)
 {
-	struct nf_bridge_info *nf_bridge = skb->nf_bridge;
+	struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb);
 
 	skb_pull(skb, ETH_HLEN);
 	nf_bridge->mask &= ~BRNF_BRIDGED_DNAT;
 
-	skb_copy_to_linear_data_offset(skb, -(ETH_HLEN-ETH_ALEN),
-				       skb->nf_bridge->data, ETH_HLEN-ETH_ALEN);
+	BUILD_BUG_ON(sizeof(nf_bridge->neigh_header) != (ETH_HLEN - ETH_ALEN));
+
+	skb_copy_to_linear_data_offset(skb, -(ETH_HLEN - ETH_ALEN),
+				       nf_bridge->neigh_header,
+				       ETH_HLEN - ETH_ALEN);
 	skb->dev = nf_bridge->physindev;
 	br_handle_frame_finish(NULL, skb);
 }
diff --git a/net/ipv4/netfilter/nf_reject_ipv4.c b/net/ipv4/netfilter/nf_reject_ipv4.c
index c5b794da51a9..3262e41ff76f 100644
--- a/net/ipv4/netfilter/nf_reject_ipv4.c
+++ b/net/ipv4/netfilter/nf_reject_ipv4.c
@@ -13,6 +13,7 @@
 #include <net/dst.h>
 #include <net/netfilter/ipv4/nf_reject.h>
 #include <linux/netfilter_ipv4.h>
+#include <linux/netfilter_bridge.h>
 #include <net/netfilter/ipv4/nf_reject.h>
 
 const struct tcphdr *nf_reject_ip_tcphdr_get(struct sk_buff *oldskb,
@@ -146,7 +147,8 @@ void nf_send_reset(struct sk_buff *oldskb, int hook)
 	 */
 	if (oldskb->nf_bridge) {
 		struct ethhdr *oeth = eth_hdr(oldskb);
-		nskb->dev = oldskb->nf_bridge->physindev;
+
+		nskb->dev = nf_bridge_get_physindev(oldskb);
 		niph->tot_len = htons(nskb->len);
 		ip_send_check(niph);
 		if (dev_hard_header(nskb, nskb->dev, ntohs(nskb->protocol),
diff --git a/net/ipv6/netfilter/nf_reject_ipv6.c b/net/ipv6/netfilter/nf_reject_ipv6.c
index 3afdce03d94e..94b4c6dfb400 100644
--- a/net/ipv6/netfilter/nf_reject_ipv6.c
+++ b/net/ipv6/netfilter/nf_reject_ipv6.c
@@ -13,6 +13,7 @@
 #include <net/ip6_checksum.h>
 #include <net/netfilter/ipv6/nf_reject.h>
 #include <linux/netfilter_ipv6.h>
+#include <linux/netfilter_bridge.h>
 #include <net/netfilter/ipv6/nf_reject.h>
 
 const struct tcphdr *nf_reject_ip6_tcphdr_get(struct sk_buff *oldskb,
@@ -195,7 +196,8 @@ void nf_send_reset6(struct net *net, struct sk_buff *oldskb, int hook)
 	 */
 	if (oldskb->nf_bridge) {
 		struct ethhdr *oeth = eth_hdr(oldskb);
-		nskb->dev = oldskb->nf_bridge->physindev;
+
+		nskb->dev = nf_bridge_get_physindev(oldskb);
 		nskb->protocol = htons(ETH_P_IPV6);
 		ip6h->payload_len = htons(sizeof(struct tcphdr));
 		if (dev_hard_header(nskb, nskb->dev, ntohs(nskb->protocol),
diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile
index 89f73a9e9874..a87d8b8ec730 100644
--- a/net/netfilter/Makefile
+++ b/net/netfilter/Makefile
@@ -70,7 +70,7 @@ obj-$(CONFIG_NETFILTER_SYNPROXY) += nf_synproxy_core.o
 
 # nf_tables
 nf_tables-objs += nf_tables_core.o nf_tables_api.o
-nf_tables-objs += nft_immediate.o nft_cmp.o nft_lookup.o
+nf_tables-objs += nft_immediate.o nft_cmp.o nft_lookup.o nft_dynset.o
 nf_tables-objs += nft_bitwise.o nft_byteorder.o nft_payload.o
 
 obj-$(CONFIG_NF_TABLES)		+= nf_tables.o
diff --git a/net/netfilter/ipset/ip_set_hash_netiface.c b/net/netfilter/ipset/ip_set_hash_netiface.c
index 758b002130d9..380ef5148ea1 100644
--- a/net/netfilter/ipset/ip_set_hash_netiface.c
+++ b/net/netfilter/ipset/ip_set_hash_netiface.c
@@ -19,6 +19,7 @@
 #include <net/netlink.h>
 
 #include <linux/netfilter.h>
+#include <linux/netfilter_bridge.h>
 #include <linux/netfilter/ipset/pfxlen.h>
 #include <linux/netfilter/ipset/ip_set.h>
 #include <linux/netfilter/ipset/ip_set_hash.h>
@@ -211,6 +212,22 @@ hash_netiface4_data_next(struct hash_netiface4_elem *next,
 #define HKEY_DATALEN	sizeof(struct hash_netiface4_elem_hashed)
 #include "ip_set_hash_gen.h"
 
+#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
+static const char *get_physindev_name(const struct sk_buff *skb)
+{
+	struct net_device *dev = nf_bridge_get_physindev(skb);
+
+	return dev ? dev->name : NULL;
+}
+
+static const char *get_phyoutdev_name(const struct sk_buff *skb)
+{
+	struct net_device *dev = nf_bridge_get_physoutdev(skb);
+
+	return dev ? dev->name : NULL;
+}
+#endif
+
 static int
 hash_netiface4_kadt(struct ip_set *set, const struct sk_buff *skb,
 		    const struct xt_action_param *par,
@@ -234,16 +251,15 @@ hash_netiface4_kadt(struct ip_set *set, const struct sk_buff *skb,
 	e.ip &= ip_set_netmask(e.cidr);
 
 #define IFACE(dir)	(par->dir ? par->dir->name : NULL)
-#define PHYSDEV(dir)	(nf_bridge->dir ? nf_bridge->dir->name : NULL)
 #define SRCDIR		(opt->flags & IPSET_DIM_TWO_SRC)
 
 	if (opt->cmdflags & IPSET_FLAG_PHYSDEV) {
 #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
-		const struct nf_bridge_info *nf_bridge = skb->nf_bridge;
+		e.iface = SRCDIR ? get_physindev_name(skb) :
+				   get_phyoutdev_name(skb);
 
-		if (!nf_bridge)
+		if (!e.iface)
 			return -EINVAL;
-		e.iface = SRCDIR ? PHYSDEV(physindev) : PHYSDEV(physoutdev);
 		e.physdev = 1;
 #else
 		e.iface = NULL;
@@ -476,11 +492,11 @@ hash_netiface6_kadt(struct ip_set *set, const struct sk_buff *skb,
 
 	if (opt->cmdflags & IPSET_FLAG_PHYSDEV) {
 #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
-		const struct nf_bridge_info *nf_bridge = skb->nf_bridge;
-
-		if (!nf_bridge)
+		e.iface = SRCDIR ? get_physindev_name(skb) :
+				   get_phyoutdev_name(skb);
+		if (!e.iface)
 			return -EINVAL;
-		e.iface = SRCDIR ? PHYSDEV(physindev) : PHYSDEV(physoutdev);
+
 		e.physdev = 1;
 #else
 		e.iface = NULL;