Netfilter/IPVS updates for net-next

index bcd9b7bde4ee..569631d2b2a1 100644
@@ -436,7 +436,7 @@ static bool tcp_state_active(int state)
 	return tcp_state_active_table[state];
 }
 
-static struct tcp_states_t tcp_states [] = {
+static struct tcp_states_t tcp_states[] = {
 /*	INPUT */
 /*        sNO, sES, sSS, sSR, sFW, sTW, sCL, sCW, sLA, sLI, sSA	*/
 /*syn*/ {{sSR, sES, sES, sSR, sSR, sSR, sSR, sSR, sSR, sSR, sSR }},

@@ -459,7 +459,7 @@ static struct tcp_states_t tcp_states [] = {
 /*rst*/ {{sCL, sCL, sCL, sSR, sCL, sCL, sCL, sCL, sLA, sLI, sCL }},
 };
 
-static struct tcp_states_t tcp_states_dos [] = {
+static struct tcp_states_t tcp_states_dos[] = {
 /*	INPUT */
 /*        sNO, sES, sSS, sSR, sFW, sTW, sCL, sCW, sLA, sLI, sSA	*/
 /*syn*/ {{sSR, sES, sES, sSR, sSR, sSR, sSR, sSR, sSR, sSR, sSA }},

index eb0bec043c96..0ac795b41ab8 100644
@@ -668,6 +668,7 @@ struct ip_vs_dest {
 	volatile unsigned int	flags;		/* dest status flags */
 	atomic_t		conn_flags;	/* flags to copy to conn */
 	atomic_t		weight;		/* server weight */
+	atomic_t		last_weight;	/* server latest weight */
 
 	refcount_t		refcnt;		/* reference counter */
 	struct ip_vs_stats      stats;          /* statistics */

index 5ebde4b15810..b91bb70ece92 100644
@@ -821,6 +821,10 @@ __ip_vs_update_dest(struct ip_vs_service *svc, struct ip_vs_dest *dest,
 	if (add && udest->af != svc->af)
 		ipvs->mixed_address_family_dests++;
 
+	/* keep the last_weight with latest non-0 weight */
+	if (add || udest->weight != 0)
+		atomic_set(&dest->last_weight, udest->weight);
+
 	/* set the weight and the flags */
 	atomic_set(&dest->weight, udest->weight);
 	conn_flags = udest->conn_flags & IP_VS_CONN_F_DEST_MASK;

new file mode 100644
index 000000000000..0f795b186eb3
@@ -0,0 +1,540 @@
+// SPDX-License-Identifier: GPL-2.0
+/* IPVS:	Maglev Hashing scheduling module
+ *
+ * Authors:	Inju Song <[email protected]>
+ *
+ */
+
+/* The mh algorithm is to assign�a preference list of all the lookup
+ * table positions to each destination and populate the table with
+ * the most-preferred position of destinations. Then it is to select
+ * destination with the hash key of source IP address�through looking
+ * up a the lookup table.
+ *
+ * The algorithm is detailed in:
+ * [3.4 Consistent Hasing]
+https://www.usenix.org/system/files/conference/nsdi16/nsdi16-paper-eisenbud.pdf
+ *
+ */
+
+#define KMSG_COMPONENT "IPVS"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
+#include <linux/ip.h>
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/skbuff.h>
+
+#include <net/ip_vs.h>
+
+#include <linux/siphash.h>
+#include <linux/bitops.h>
+#include <linux/gcd.h>
+
+#define IP_VS_SVC_F_SCHED_MH_FALLBACK	IP_VS_SVC_F_SCHED1 /* MH fallback */
+#define IP_VS_SVC_F_SCHED_MH_PORT	IP_VS_SVC_F_SCHED2 /* MH use port */
+
+struct ip_vs_mh_lookup {
+	struct ip_vs_dest __rcu	*dest;	/* real server (cache) */
+};
+
+struct ip_vs_mh_dest_setup {
+	unsigned int	offset; /* starting offset */
+	unsigned int	skip;	/* skip */
+	unsigned int	perm;	/* next_offset */
+	int		turns;	/* weight / gcd() and rshift */
+};
+
+/* Available prime numbers for MH table */
+static int primes[] = {251, 509, 1021, 2039, 4093,
+		       8191, 16381, 32749, 65521, 131071};
+
+/* For IPVS MH entry hash table */
+#ifndef CONFIG_IP_VS_MH_TAB_INDEX
+#define CONFIG_IP_VS_MH_TAB_INDEX	12
+#endif
+#define IP_VS_MH_TAB_BITS		(CONFIG_IP_VS_MH_TAB_INDEX / 2)
+#define IP_VS_MH_TAB_INDEX		(CONFIG_IP_VS_MH_TAB_INDEX - 8)
+#define IP_VS_MH_TAB_SIZE               primes[IP_VS_MH_TAB_INDEX]
+
+struct ip_vs_mh_state {
+	struct rcu_head			rcu_head;
+	struct ip_vs_mh_lookup		*lookup;
+	struct ip_vs_mh_dest_setup	*dest_setup;
+	hsiphash_key_t			hash1, hash2;
+	int				gcd;
+	int				rshift;
+};
+
+static inline void generate_hash_secret(hsiphash_key_t *hash1,
+					hsiphash_key_t *hash2)
+{
+	hash1->key[0] = 2654435761UL;
+	hash1->key[1] = 2654435761UL;
+
+	hash2->key[0] = 2654446892UL;
+	hash2->key[1] = 2654446892UL;
+}
+
+/* Helper function to determine if server is unavailable */
+static inline bool is_unavailable(struct ip_vs_dest *dest)
+{
+	return atomic_read(&dest->weight) <= 0 ||
+	       dest->flags & IP_VS_DEST_F_OVERLOAD;
+}
+
+/* Returns hash value for IPVS MH entry */
+static inline unsigned int
+ip_vs_mh_hashkey(int af, const union nf_inet_addr *addr,
+		 __be16 port, hsiphash_key_t *key, unsigned int offset)
+{
+	unsigned int v;
+	__be32 addr_fold = addr->ip;
+
+#ifdef CONFIG_IP_VS_IPV6
+	if (af == AF_INET6)
+		addr_fold = addr->ip6[0] ^ addr->ip6[1] ^
+			    addr->ip6[2] ^ addr->ip6[3];
+#endif
+	v = (offset + ntohs(port) + ntohl(addr_fold));
+	return hsiphash(&v, sizeof(v), key);
+}
+
+/* Reset all the hash buckets of the specified table. */
+static void ip_vs_mh_reset(struct ip_vs_mh_state *s)
+{
+	int i;
+	struct ip_vs_mh_lookup *l;
+	struct ip_vs_dest *dest;
+
+	l = &s->lookup[0];
+	for (i = 0; i < IP_VS_MH_TAB_SIZE; i++) {
+		dest = rcu_dereference_protected(l->dest, 1);
+		if (dest) {
+			ip_vs_dest_put(dest);
+			RCU_INIT_POINTER(l->dest, NULL);
+		}
+		l++;
+	}
+}
+
+static int ip_vs_mh_permutate(struct ip_vs_mh_state *s,
+			      struct ip_vs_service *svc)
+{
+	struct list_head *p;
+	struct ip_vs_mh_dest_setup *ds;
+	struct ip_vs_dest *dest;
+	int lw;
+
+	/* If gcd is smaller then 1, number of dests or
+	 * all last_weight of dests are zero. So, skip
+	 * permutation for the dests.
+	 */
+	if (s->gcd < 1)
+		return 0;
+
+	/* Set dest_setup for the dests permutation */
+	p = &svc->destinations;
+	ds = &s->dest_setup[0];
+	while ((p = p->next) != &svc->destinations) {
+		dest = list_entry(p, struct ip_vs_dest, n_list);
+
+		ds->offset = ip_vs_mh_hashkey(svc->af, &dest->addr,
+					      dest->port, &s->hash1, 0) %
+					      IP_VS_MH_TAB_SIZE;
+		ds->skip = ip_vs_mh_hashkey(svc->af, &dest->addr,
+					    dest->port, &s->hash2, 0) %
+					    (IP_VS_MH_TAB_SIZE - 1) + 1;
+		ds->perm = ds->offset;
+
+		lw = atomic_read(&dest->last_weight);
+		ds->turns = ((lw / s->gcd) >> s->rshift) ? : (lw != 0);
+		ds++;
+	}
+
+	return 0;
+}
+
+static int ip_vs_mh_populate(struct ip_vs_mh_state *s,
+			     struct ip_vs_service *svc)
+{
+	int n, c, dt_count;
+	unsigned long *table;
+	struct list_head *p;
+	struct ip_vs_mh_dest_setup *ds;
+	struct ip_vs_dest *dest, *new_dest;
+
+	/* If gcd is smaller then 1, number of dests or
+	 * all last_weight of dests are zero. So, skip
+	 * the population for the dests and reset lookup table.
+	 */
+	if (s->gcd < 1) {
+		ip_vs_mh_reset(s);
+		return 0;
+	}
+
+	table =  kcalloc(BITS_TO_LONGS(IP_VS_MH_TAB_SIZE),
+			 sizeof(unsigned long), GFP_KERNEL);
+	if (!table)
+		return -ENOMEM;
+
+	p = &svc->destinations;
+	n = 0;
+	dt_count = 0;
+	while (n < IP_VS_MH_TAB_SIZE) {
+		if (p == &svc->destinations)
+			p = p->next;
+
+		ds = &s->dest_setup[0];
+		while (p != &svc->destinations) {
+			/* Ignore added server with zero weight */
+			if (ds->turns < 1) {
+				p = p->next;
+				ds++;
+				continue;
+			}
+
+			c = ds->perm;
+			while (test_bit(c, table)) {
+				/* Add skip, mod IP_VS_MH_TAB_SIZE */
+				ds->perm += ds->skip;
+				if (ds->perm >= IP_VS_MH_TAB_SIZE)
+					ds->perm -= IP_VS_MH_TAB_SIZE;
+				c = ds->perm;
+			}
+
+			__set_bit(c, table);
+
+			dest = rcu_dereference_protected(s->lookup[c].dest, 1);
+			new_dest = list_entry(p, struct ip_vs_dest, n_list);
+			if (dest != new_dest) {
+				if (dest)
+					ip_vs_dest_put(dest);
+				ip_vs_dest_hold(new_dest);
+				RCU_INIT_POINTER(s->lookup[c].dest, new_dest);
+			}
+
+			if (++n == IP_VS_MH_TAB_SIZE)
+				goto out;
+
+			if (++dt_count >= ds->turns) {
+				dt_count = 0;
+				p = p->next;
+				ds++;
+			}
+		}
+	}
+
+out:
+	kfree(table);
+	return 0;
+}
+
+/* Get ip_vs_dest associated with supplied parameters. */
+static inline struct ip_vs_dest *
+ip_vs_mh_get(struct ip_vs_service *svc, struct ip_vs_mh_state *s,
+	     const union nf_inet_addr *addr, __be16 port)
+{
+	unsigned int hash = ip_vs_mh_hashkey(svc->af, addr, port, &s->hash1, 0)
+					     % IP_VS_MH_TAB_SIZE;
+	struct ip_vs_dest *dest = rcu_dereference(s->lookup[hash].dest);
+
+	return (!dest || is_unavailable(dest)) ? NULL : dest;
+}
+
+/* As ip_vs_mh_get, but with fallback if selected server is unavailable */
+static inline struct ip_vs_dest *
+ip_vs_mh_get_fallback(struct ip_vs_service *svc, struct ip_vs_mh_state *s,
+		      const union nf_inet_addr *addr, __be16 port)
+{
+	unsigned int offset, roffset;
+	unsigned int hash, ihash;
+	struct ip_vs_dest *dest;
+
+	/* First try the dest it's supposed to go to */
+	ihash = ip_vs_mh_hashkey(svc->af, addr, port,
+				 &s->hash1, 0) % IP_VS_MH_TAB_SIZE;
+	dest = rcu_dereference(s->lookup[ihash].dest);
+	if (!dest)
+		return NULL;
+	if (!is_unavailable(dest))
+		return dest;
+
+	IP_VS_DBG_BUF(6, "MH: selected unavailable server %s:%u, reselecting",
+		      IP_VS_DBG_ADDR(dest->af, &dest->addr), ntohs(dest->port));
+
+	/* If the original dest is unavailable, loop around the table
+	 * starting from ihash to find a new dest
+	 */
+	for (offset = 0; offset < IP_VS_MH_TAB_SIZE; offset++) {
+		roffset = (offset + ihash) % IP_VS_MH_TAB_SIZE;
+		hash = ip_vs_mh_hashkey(svc->af, addr, port, &s->hash1,
+					roffset) % IP_VS_MH_TAB_SIZE;
+		dest = rcu_dereference(s->lookup[hash].dest);
+		if (!dest)
+			break;
+		if (!is_unavailable(dest))
+			return dest;
+		IP_VS_DBG_BUF(6,
+			      "MH: selected unavailable server %s:%u (offset %u), reselecting",
+			      IP_VS_DBG_ADDR(dest->af, &dest->addr),
+			      ntohs(dest->port), roffset);
+	}
+
+	return NULL;
+}
+
+/* Assign all the hash buckets of the specified table with the service. */
+static int ip_vs_mh_reassign(struct ip_vs_mh_state *s,
+			     struct ip_vs_service *svc)
+{
+	int ret;
+
+	if (svc->num_dests > IP_VS_MH_TAB_SIZE)
+		return -EINVAL;
+
+	if (svc->num_dests >= 1) {
+		s->dest_setup = kcalloc(svc->num_dests,
+					sizeof(struct ip_vs_mh_dest_setup),
+					GFP_KERNEL);
+		if (!s->dest_setup)
+			return -ENOMEM;
+	}
+
+	ip_vs_mh_permutate(s, svc);
+
+	ret = ip_vs_mh_populate(s, svc);
+	if (ret < 0)
+		goto out;
+
+	IP_VS_DBG_BUF(6, "MH: reassign lookup table of %s:%u\n",
+		      IP_VS_DBG_ADDR(svc->af, &svc->addr),
+		      ntohs(svc->port));
+
+out:
+	if (svc->num_dests >= 1) {
+		kfree(s->dest_setup);
+		s->dest_setup = NULL;
+	}
+	return ret;
+}
+
+static int ip_vs_mh_gcd_weight(struct ip_vs_service *svc)
+{
+	struct ip_vs_dest *dest;
+	int weight;
+	int g = 0;
+
+	list_for_each_entry(dest, &svc->destinations, n_list) {
+		weight = atomic_read(&dest->last_weight);
+		if (weight > 0) {
+			if (g > 0)
+				g = gcd(weight, g);
+			else
+				g = weight;
+		}
+	}
+	return g;
+}
+
+/* To avoid assigning huge weight for the MH table,
+ * calculate shift value with gcd.
+ */
+static int ip_vs_mh_shift_weight(struct ip_vs_service *svc, int gcd)
+{
+	struct ip_vs_dest *dest;
+	int new_weight, weight = 0;
+	int mw, shift;
+
+	/* If gcd is smaller then 1, number of dests or
+	 * all last_weight of dests are zero. So, return
+	 * shift value as zero.
+	 */
+	if (gcd < 1)
+		return 0;
+
+	list_for_each_entry(dest, &svc->destinations, n_list) {
+		new_weight = atomic_read(&dest->last_weight);
+		if (new_weight > weight)
+			weight = new_weight;
+	}
+
+	/* Because gcd is greater than zero,
+	 * the maximum weight and gcd are always greater than zero
+	 */
+	mw = weight / gcd;
+
+	/* shift = occupied bits of weight/gcd - MH highest bits */
+	shift = fls(mw) - IP_VS_MH_TAB_BITS;
+	return (shift >= 0) ? shift : 0;
+}
+
+static void ip_vs_mh_state_free(struct rcu_head *head)
+{
+	struct ip_vs_mh_state *s;
+
+	s = container_of(head, struct ip_vs_mh_state, rcu_head);
+	kfree(s->lookup);
+	kfree(s);
+}
+
+static int ip_vs_mh_init_svc(struct ip_vs_service *svc)
+{
+	int ret;
+	struct ip_vs_mh_state *s;
+
+	/* Allocate the MH table for this service */
+	s = kzalloc(sizeof(*s), GFP_KERNEL);
+	if (!s)
+		return -ENOMEM;
+
+	s->lookup = kcalloc(IP_VS_MH_TAB_SIZE, sizeof(struct ip_vs_mh_lookup),
+			    GFP_KERNEL);
+	if (!s->lookup) {
+		kfree(s);
+		return -ENOMEM;
+	}
+
+	generate_hash_secret(&s->hash1, &s->hash2);
+	s->gcd = ip_vs_mh_gcd_weight(svc);
+	s->rshift = ip_vs_mh_shift_weight(svc, s->gcd);
+
+	IP_VS_DBG(6,
+		  "MH lookup table (memory=%zdbytes) allocated for current service\n",
+		  sizeof(struct ip_vs_mh_lookup) * IP_VS_MH_TAB_SIZE);
+
+	/* Assign the lookup table with current dests */
+	ret = ip_vs_mh_reassign(s, svc);
+	if (ret < 0) {
+		ip_vs_mh_reset(s);
+		ip_vs_mh_state_free(&s->rcu_head);
+		return ret;
+	}
+
+	/* No more failures, attach state */
+	svc->sched_data = s;
+	return 0;
+}
+
+static void ip_vs_mh_done_svc(struct ip_vs_service *svc)
+{
+	struct ip_vs_mh_state *s = svc->sched_data;
+
+	/* Got to clean up lookup entry here */
+	ip_vs_mh_reset(s);
+
+	call_rcu(&s->rcu_head, ip_vs_mh_state_free);
+	IP_VS_DBG(6, "MH lookup table (memory=%zdbytes) released\n",
+		  sizeof(struct ip_vs_mh_lookup) * IP_VS_MH_TAB_SIZE);
+}
+
+static int ip_vs_mh_dest_changed(struct ip_vs_service *svc,
+				 struct ip_vs_dest *dest)
+{
+	struct ip_vs_mh_state *s = svc->sched_data;
+
+	s->gcd = ip_vs_mh_gcd_weight(svc);
+	s->rshift = ip_vs_mh_shift_weight(svc, s->gcd);
+
+	/* Assign the lookup table with the updated service */
+	return ip_vs_mh_reassign(s, svc);
+}
+
+/* Helper function to get port number */
+static inline __be16
+ip_vs_mh_get_port(const struct sk_buff *skb, struct ip_vs_iphdr *iph)
+{
+	__be16 _ports[2], *ports;
+
+	/* At this point we know that we have a valid packet of some kind.
+	 * Because ICMP packets are only guaranteed to have the first 8
+	 * bytes, let's just grab the ports.  Fortunately they're in the
+	 * same position for all three of the protocols we care about.
+	 */
+	switch (iph->protocol) {
+	case IPPROTO_TCP:
+	case IPPROTO_UDP:
+	case IPPROTO_SCTP:
+		ports = skb_header_pointer(skb, iph->len, sizeof(_ports),
+					   &_ports);
+		if (unlikely(!ports))
+			return 0;
+
+		if (likely(!ip_vs_iph_inverse(iph)))
+			return ports[0];
+		else
+			return ports[1];
+	default:
+		return 0;
+	}
+}
+
+/* Maglev Hashing scheduling */
+static struct ip_vs_dest *
+ip_vs_mh_schedule(struct ip_vs_service *svc, const struct sk_buff *skb,
+		  struct ip_vs_iphdr *iph)
+{
+	struct ip_vs_dest *dest;
+	struct ip_vs_mh_state *s;
+	__be16 port = 0;
+	const union nf_inet_addr *hash_addr;
+
+	hash_addr = ip_vs_iph_inverse(iph) ? &iph->daddr : &iph->saddr;
+
+	IP_VS_DBG(6, "%s : Scheduling...\n", __func__);
+
+	if (svc->flags & IP_VS_SVC_F_SCHED_MH_PORT)
+		port = ip_vs_mh_get_port(skb, iph);
+
+	s = (struct ip_vs_mh_state *)svc->sched_data;
+
+	if (svc->flags & IP_VS_SVC_F_SCHED_MH_FALLBACK)
+		dest = ip_vs_mh_get_fallback(svc, s, hash_addr, port);
+	else
+		dest = ip_vs_mh_get(svc, s, hash_addr, port);
+
+	if (!dest) {
+		ip_vs_scheduler_err(svc, "no destination available");
+		return NULL;
+	}
+
+	IP_VS_DBG_BUF(6, "MH: source IP address %s:%u --> server %s:%u\n",
+		      IP_VS_DBG_ADDR(svc->af, hash_addr),
+		      ntohs(port),
+		      IP_VS_DBG_ADDR(dest->af, &dest->addr),
+		      ntohs(dest->port));
+
+	return dest;
+}
+
+/* IPVS MH Scheduler structure */
+static struct ip_vs_scheduler ip_vs_mh_scheduler = {
+	.name =			"mh",
+	.refcnt =		ATOMIC_INIT(0),
+	.module =		THIS_MODULE,
+	.n_list	 =		LIST_HEAD_INIT(ip_vs_mh_scheduler.n_list),
+	.init_service =		ip_vs_mh_init_svc,
+	.done_service =		ip_vs_mh_done_svc,
+	.add_dest =		ip_vs_mh_dest_changed,
+	.del_dest =		ip_vs_mh_dest_changed,
+	.upd_dest =		ip_vs_mh_dest_changed,
+	.schedule =		ip_vs_mh_schedule,
+};
+
+static int __init ip_vs_mh_init(void)
+{
+	return register_ip_vs_scheduler(&ip_vs_mh_scheduler);
+}
+
+static void __exit ip_vs_mh_cleanup(void)
+{
+	unregister_ip_vs_scheduler(&ip_vs_mh_scheduler);
+	rcu_barrier();
+}
+
+module_init(ip_vs_mh_init);
+module_exit(ip_vs_mh_cleanup);
+MODULE_DESCRIPTION("Maglev hashing ipvs scheduler");
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Inju Song <[email protected]>");

index 75f798f8e83b..07459e71d907 100644
@@ -43,6 +43,7 @@
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/skbuff.h>
+#include <linux/hash.h>
 
 #include <net/ip_vs.h>
 

@@ -81,7 +82,7 @@ static inline unsigned int ip_vs_dh_hashkey(int af, const union nf_inet_addr *ad
 		addr_fold = addr->ip6[0]^addr->ip6[1]^
 			    addr->ip6[2]^addr->ip6[3];
 #endif
-	return (ntohl(addr_fold)*2654435761UL) & IP_VS_DH_TAB_MASK;
+	return hash_32(ntohl(addr_fold), IP_VS_DH_TAB_BITS);
 }
 
 

index 3057e453bf31..08147fc6400c 100644
@@ -48,6 +48,7 @@
 #include <linux/kernel.h>
 #include <linux/skbuff.h>
 #include <linux/jiffies.h>
+#include <linux/hash.h>
 
 /* for sysctl */
 #include <linux/fs.h>

@@ -160,7 +161,7 @@ ip_vs_lblc_hashkey(int af, const union nf_inet_addr *addr)
 		addr_fold = addr->ip6[0]^addr->ip6[1]^
 			    addr->ip6[2]^addr->ip6[3];
 #endif
-	return (ntohl(addr_fold)*2654435761UL) & IP_VS_LBLC_TAB_MASK;
+	return hash_32(ntohl(addr_fold), IP_VS_LBLC_TAB_BITS);
 }
 
 

index 92adc04557ed..9b6a6c9e9cfa 100644
@@ -47,6 +47,7 @@
 #include <linux/jiffies.h>
 #include <linux/list.h>
 #include <linux/slab.h>
+#include <linux/hash.h>
 
 /* for sysctl */
 #include <linux/fs.h>

@@ -323,7 +324,7 @@ ip_vs_lblcr_hashkey(int af, const union nf_inet_addr *addr)
 		addr_fold = addr->ip6[0]^addr->ip6[1]^
 			    addr->ip6[2]^addr->ip6[3];
 #endif
-	return (ntohl(addr_fold)*2654435761UL) & IP_VS_LBLCR_TAB_MASK;
+	return hash_32(ntohl(addr_fold), IP_VS_LBLCR_TAB_BITS);
 }
 
 

index 16aaac6eedc9..1e01c782583a 100644
@@ -96,7 +96,8 @@ ip_vs_sh_hashkey(int af, const union nf_inet_addr *addr,
 		addr_fold = addr->ip6[0]^addr->ip6[1]^
 			    addr->ip6[2]^addr->ip6[3];
 #endif
-	return (offset + (ntohs(port) + ntohl(addr_fold))*2654435761UL) &
+	return (offset + hash_32(ntohs(port) + ntohl(addr_fold),
+				 IP_VS_SH_TAB_BITS)) &
 		IP_VS_SH_TAB_MASK;
 }
 

index 612cfb63ac68..ea32a7d3cf1b 100644
@@ -1,18 +1 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _KER_NFNETLINK_LOG_H
-#define _KER_NFNETLINK_LOG_H
-
-void
-nfulnl_log_packet(struct net *net,
-		  u_int8_t pf,
-		  unsigned int hooknum,
-		  const struct sk_buff *skb,
-		  const struct net_device *in,
-		  const struct net_device *out,
-		  const struct nf_loginfo *li_user,
-		  const char *prefix);
-
-#define NFULNL_COPY_DISABLED    0xff
-
-#endif /* _KER_NFNETLINK_LOG_H */
-

index 7b46aa4c478d..e5cc4d9b9ce7 100644
@@ -37,7 +37,6 @@
 #include <net/sock.h>
 #include <net/netfilter/nf_log.h>
 #include <net/netns/generic.h>
-#include <net/netfilter/nfnetlink_log.h>
 
 #include <linux/atomic.h>
 #include <linux/refcount.h>

@@ -47,6 +46,7 @@
 #include "../bridge/br_private.h"
 #endif
 
+#define NFULNL_COPY_DISABLED	0xff
 #define NFULNL_NLBUFSIZ_DEFAULT	NLMSG_GOODSIZE
 #define NFULNL_TIMEOUT_DEFAULT 	100	/* every second */
 #define NFULNL_QTHRESH_DEFAULT 	100	/* 100 packets */

@@ -618,7 +618,7 @@ static const struct nf_loginfo default_loginfo = {
 };
 
 /* log handler for internal netfilter logging api */
-void
+static void
 nfulnl_log_packet(struct net *net,
 		  u_int8_t pf,
 		  unsigned int hooknum,

@@ -633,7 +633,7 @@ nfulnl_log_packet(struct net *net,
 	struct nfulnl_instance *inst;
 	const struct nf_loginfo *li;
 	unsigned int qthreshold;
-	unsigned int plen;
+	unsigned int plen = 0;
 	struct nfnl_log_net *log = nfnl_log_pernet(net);
 	const struct nfnl_ct_hook *nfnl_ct = NULL;
 	struct nf_conn *ct = NULL;

@@ -648,7 +648,6 @@ nfulnl_log_packet(struct net *net,
 	if (!inst)
 		return;
 
-	plen = 0;
 	if (prefix)
 		plen = strlen(prefix) + 1;
 

@@ -760,7 +759,6 @@ nfulnl_log_packet(struct net *net,
 	/* FIXME: statistics */
 	goto unlock_and_release;
 }
-EXPORT_SYMBOL_GPL(nfulnl_log_packet);
 
 static int
 nfulnl_rcv_nl_event(struct notifier_block *this,

index c7f8958cea4a..1ed0cac585c4 100644
@@ -13,7 +13,6 @@
 #include <linux/netfilter/x_tables.h>
 #include <linux/netfilter/xt_NFLOG.h>
 #include <net/netfilter/nf_log.h>
-#include <net/netfilter/nfnetlink_log.h>
 
 MODULE_AUTHOR("Patrick McHardy <[email protected]>");
 MODULE_DESCRIPTION("Xtables: packet logging to netlink using NFLOG");

@@ -37,8 +36,9 @@ nflog_tg(struct sk_buff *skb, const struct xt_action_param *par)
 	if (info->flags & XT_NFLOG_F_COPY_LEN)
 		li.u.ulog.flags |= NF_LOG_F_COPY_LEN;
 
-	nfulnl_log_packet(net, xt_family(par), xt_hooknum(par), skb,
-			  xt_in(par), xt_out(par), &li, info->prefix);
+	nf_log_packet(net, xt_family(par), xt_hooknum(par), skb, xt_in(par),
+		      xt_out(par), &li, "%s", info->prefix);
+
 	return XT_CONTINUE;
 }
 

@@ -50,7 +50,13 @@ static int nflog_tg_check(const struct xt_tgchk_param *par)
 		return -EINVAL;
 	if (info->prefix[sizeof(info->prefix) - 1] != '\0')
 		return -EINVAL;
-	return 0;
+
+	return nf_logger_find_get(par->family, NF_LOG_TYPE_ULOG);
+}
+
+static void nflog_tg_destroy(const struct xt_tgdtor_param *par)
+{
+	nf_logger_put(par->family, NF_LOG_TYPE_ULOG);
 }
 
 static struct xt_target nflog_tg_reg __read_mostly = {

@@ -58,6 +64,7 @@ static struct xt_target nflog_tg_reg __read_mostly = {
 	.revision   = 0,
 	.family     = NFPROTO_UNSPEC,
 	.checkentry = nflog_tg_check,
+	.destroy    = nflog_tg_destroy,
 	.target     = nflog_tg,
 	.targetsize = sizeof(struct xt_nflog_info),
 	.me         = THIS_MODULE,

index 833752dd0c58..09ba67598991 100644
@@ -6,6 +6,7 @@
 #include <linux/netdevice.h>
 #include <linux/rhashtable.h>
 #include <linux/rcupdate.h>
+#include <linux/netfilter/nf_conntrack_tuple_common.h>
 #include <net/dst.h>
 
 struct nf_flowtable;

@@ -27,11 +28,10 @@ struct nf_flowtable {
 };
 
 enum flow_offload_tuple_dir {
-	FLOW_OFFLOAD_DIR_ORIGINAL,
-	FLOW_OFFLOAD_DIR_REPLY,
-	__FLOW_OFFLOAD_DIR_MAX		= FLOW_OFFLOAD_DIR_REPLY,
+	FLOW_OFFLOAD_DIR_ORIGINAL = IP_CT_DIR_ORIGINAL,
+	FLOW_OFFLOAD_DIR_REPLY = IP_CT_DIR_REPLY,
+	FLOW_OFFLOAD_DIR_MAX = IP_CT_DIR_MAX
 };
-#define FLOW_OFFLOAD_DIR_MAX	(__FLOW_OFFLOAD_DIR_MAX + 1)
 
 struct flow_offload_tuple {
 	union {

index ec410cae9307..db0673a40b97 100644
@@ -16,6 +16,38 @@ struct flow_offload_entry {
 	struct rcu_head		rcu_head;
 };
 
+static void
+flow_offload_fill_dir(struct flow_offload *flow, struct nf_conn *ct,
+		      struct nf_flow_route *route,
+		      enum flow_offload_tuple_dir dir)
+{
+	struct flow_offload_tuple *ft = &flow->tuplehash[dir].tuple;
+	struct nf_conntrack_tuple *ctt = &ct->tuplehash[dir].tuple;
+
+	ft->dir = dir;
+
+	switch (ctt->src.l3num) {
+	case NFPROTO_IPV4:
+		ft->src_v4 = ctt->src.u3.in;
+		ft->dst_v4 = ctt->dst.u3.in;
+		break;
+	case NFPROTO_IPV6:
+		ft->src_v6 = ctt->src.u3.in6;
+		ft->dst_v6 = ctt->dst.u3.in6;
+		break;
+	}
+
+	ft->l3proto = ctt->src.l3num;
+	ft->l4proto = ctt->dst.protonum;
+	ft->src_port = ctt->src.u.tcp.port;
+	ft->dst_port = ctt->dst.u.tcp.port;
+
+	ft->iifidx = route->tuple[dir].ifindex;
+	ft->oifidx = route->tuple[!dir].ifindex;
+
+	ft->dst_cache = route->tuple[dir].dst;
+}
+
 struct flow_offload *
 flow_offload_alloc(struct nf_conn *ct, struct nf_flow_route *route)
 {

@@ -40,65 +72,8 @@ flow_offload_alloc(struct nf_conn *ct, struct nf_flow_route *route)
 
 	entry->ct = ct;
 
-	switch (ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.l3num) {
-	case NFPROTO_IPV4:
-		flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_v4 =
-			ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u3.in;
-		flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_v4 =
-			ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.u3.in;
-		flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.src_v4 =
-			ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.u3.in;
-		flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_v4 =
-			ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u3.in;
-		break;
-	case NFPROTO_IPV6:
-		flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_v6 =
-			ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u3.in6;
-		flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_v6 =
-			ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.u3.in6;
-		flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.src_v6 =
-			ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.u3.in6;
-		flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_v6 =
-			ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u3.in6;
-		break;
-	}
-
-	flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.l3proto =
-		ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.l3num;
-	flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.l4proto =
-		ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.protonum;
-	flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.l3proto =
-		ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.l3num;
-	flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.l4proto =
-		ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.protonum;
-
-	flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_cache =
-		  route->tuple[FLOW_OFFLOAD_DIR_ORIGINAL].dst;
-	flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_cache =
-		  route->tuple[FLOW_OFFLOAD_DIR_REPLY].dst;
-
-	flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_port =
-		ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u.tcp.port;
-	flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_port =
-		ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.u.tcp.port;
-	flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.src_port =
-		ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.u.tcp.port;
-	flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_port =
-		ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u.tcp.port;
-
-	flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dir =
-						FLOW_OFFLOAD_DIR_ORIGINAL;
-	flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dir =
-						FLOW_OFFLOAD_DIR_REPLY;
-
-	flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.iifidx =
-		route->tuple[FLOW_OFFLOAD_DIR_ORIGINAL].ifindex;
-	flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.oifidx =
-		route->tuple[FLOW_OFFLOAD_DIR_REPLY].ifindex;
-	flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.iifidx =
-		route->tuple[FLOW_OFFLOAD_DIR_REPLY].ifindex;
-	flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.oifidx =
-		route->tuple[FLOW_OFFLOAD_DIR_ORIGINAL].ifindex;
+	flow_offload_fill_dir(flow, ct, route, FLOW_OFFLOAD_DIR_ORIGINAL);
+	flow_offload_fill_dir(flow, ct, route, FLOW_OFFLOAD_DIR_REPLY);
 
 	if (ct->status & IPS_SRC_NAT)
 		flow->flags |= FLOW_OFFLOAD_SNAT;

index d5fb1e4ae7ac..376928c26d2d 100644
@@ -279,6 +279,27 @@ static inline bool rt6_duplicate_nexthop(struct fib6_info *a, struct fib6_info *
 	       !lwtunnel_cmp_encap(a->fib6_nh.nh_lwtstate, b->fib6_nh.nh_lwtstate);
 }
 
+static inline unsigned int ip6_dst_mtu_forward(const struct dst_entry *dst)
+{
+	struct inet6_dev *idev;
+	unsigned int mtu;
+
+	if (dst_metric_locked(dst, RTAX_MTU)) {
+		mtu = dst_metric_raw(dst, RTAX_MTU);
+		if (mtu)
+			return mtu;
+	}
+
+	mtu = IPV6_MIN_MTU;
+	rcu_read_lock();
+	idev = __in6_dev_get(dst->dev);
+	if (idev)
+		mtu = idev->cnf.mtu6;
+	rcu_read_unlock();
+
+	return mtu;
+}
+
 struct neighbour *ip6_neigh_lookup(const struct in6_addr *gw,
 				   struct net_device *dev, struct sk_buff *skb,
 				   const void *daddr);

index 68b167d98879..765441867cfa 100644
@@ -958,8 +958,6 @@ static inline struct sk_buff *ip6_finish_skb(struct sock *sk)
 			      &inet6_sk(sk)->cork);
 }
 
-unsigned int ip6_dst_mtu_forward(const struct dst_entry *dst);
-
 int ip6_dst_lookup(struct net *net, struct sock *sk, struct dst_entry **dst,
 		   struct flowi6 *fl6);
 struct dst_entry *ip6_dst_lookup_flow(const struct sock *sk, struct flowi6 *fl6,

index 3db47986ef38..cec49e137dbb 100644
@@ -383,28 +383,6 @@ static inline int ip6_forward_finish(struct net *net, struct sock *sk,
 	return dst_output(net, sk, skb);
 }
 
-unsigned int ip6_dst_mtu_forward(const struct dst_entry *dst)
-{
-	unsigned int mtu;
-	struct inet6_dev *idev;
-
-	if (dst_metric_locked(dst, RTAX_MTU)) {
-		mtu = dst_metric_raw(dst, RTAX_MTU);
-		if (mtu)
-			return mtu;
-	}
-
-	mtu = IPV6_MIN_MTU;
-	rcu_read_lock();
-	idev = __in6_dev_get(dst->dev);
-	if (idev)
-		mtu = idev->cnf.mtu6;
-	rcu_read_unlock();
-
-	return mtu;
-}
-EXPORT_SYMBOL_GPL(ip6_dst_mtu_forward);
-
 static bool ip6_pkt_too_big(const struct sk_buff *skb, unsigned int mtu)
 {
 	if (skb->len <= mtu)

index 09ba67598991..76ee5c81b752 100644
@@ -55,6 +55,8 @@ struct flow_offload_tuple {
 
 	int				oifidx;
 
+	u16				mtu;
+
 	struct dst_entry		*dst_cache;
 };
 

index 0cd46bffa469..461b1815e633 100644
@@ -178,7 +178,7 @@ static int nf_flow_tuple_ip(struct sk_buff *skb, const struct net_device *dev,
 }
 
 /* Based on ip_exceeds_mtu(). */
-static bool __nf_flow_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu)
+static bool nf_flow_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu)
 {
 	if (skb->len <= mtu)
 		return false;

@@ -192,17 +192,6 @@ static bool __nf_flow_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu)
 	return true;
 }
 
-static bool nf_flow_exceeds_mtu(struct sk_buff *skb, const struct rtable *rt)
-{
-	u32 mtu;
-
-	mtu = ip_dst_mtu_maybe_forward(&rt->dst, true);
-	if (__nf_flow_exceeds_mtu(skb, mtu))
-		return true;
-
-	return false;
-}
-
 unsigned int
 nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb,
 			const struct nf_hook_state *state)

@@ -233,9 +222,9 @@ nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb,
 
 	dir = tuplehash->tuple.dir;
 	flow = container_of(tuplehash, struct flow_offload, tuplehash[dir]);
-
 	rt = (const struct rtable *)flow->tuplehash[dir].tuple.dst_cache;
-	if (unlikely(nf_flow_exceeds_mtu(skb, rt)))
+
+	if (unlikely(nf_flow_exceeds_mtu(skb, flow->tuplehash[dir].tuple.mtu)))
 		return NF_ACCEPT;
 
 	if (skb_try_make_writable(skb, sizeof(*iph)))

index 207cb35569b1..0e6328490142 100644
@@ -173,7 +173,7 @@ static int nf_flow_tuple_ipv6(struct sk_buff *skb, const struct net_device *dev,
 }
 
 /* Based on ip_exceeds_mtu(). */
-static bool __nf_flow_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu)
+static bool nf_flow_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu)
 {
 	if (skb->len <= mtu)
 		return false;

@@ -184,17 +184,6 @@ static bool __nf_flow_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu)
 	return true;
 }
 
-static bool nf_flow_exceeds_mtu(struct sk_buff *skb, const struct rt6_info *rt)
-{
-	u32 mtu;
-
-	mtu = ip6_dst_mtu_forward(&rt->dst);
-	if (__nf_flow_exceeds_mtu(skb, mtu))
-		return true;
-
-	return false;
-}
-
 unsigned int
 nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb,
 			  const struct nf_hook_state *state)

@@ -225,9 +214,9 @@ nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb,
 
 	dir = tuplehash->tuple.dir;
 	flow = container_of(tuplehash, struct flow_offload, tuplehash[dir]);
-
 	rt = (struct rt6_info *)flow->tuplehash[dir].tuple.dst_cache;
-	if (unlikely(nf_flow_exceeds_mtu(skb, rt)))
+
+	if (unlikely(nf_flow_exceeds_mtu(skb, flow->tuplehash[dir].tuple.mtu)))
 		return NF_ACCEPT;
 
 	if (skb_try_make_writable(skb, sizeof(*ip6h)))

index db0673a40b97..7403a0dfddf7 100644
@@ -4,6 +4,8 @@
 #include <linux/netfilter.h>
 #include <linux/rhashtable.h>
 #include <linux/netdevice.h>
+#include <net/ip.h>
+#include <net/ip6_route.h>
 #include <net/netfilter/nf_tables.h>
 #include <net/netfilter/nf_flow_table.h>
 #include <net/netfilter/nf_conntrack.h>

@@ -23,6 +25,7 @@ flow_offload_fill_dir(struct flow_offload *flow, struct nf_conn *ct,
 {
 	struct flow_offload_tuple *ft = &flow->tuplehash[dir].tuple;
 	struct nf_conntrack_tuple *ctt = &ct->tuplehash[dir].tuple;
+	struct dst_entry *dst = route->tuple[dir].dst;
 
 	ft->dir = dir;
 

@@ -30,10 +33,12 @@ flow_offload_fill_dir(struct flow_offload *flow, struct nf_conn *ct,
 	case NFPROTO_IPV4:
 		ft->src_v4 = ctt->src.u3.in;
 		ft->dst_v4 = ctt->dst.u3.in;
+		ft->mtu = ip_dst_mtu_maybe_forward(dst, true);
 		break;
 	case NFPROTO_IPV6:
 		ft->src_v6 = ctt->src.u3.in6;
 		ft->dst_v6 = ctt->dst.u3.in6;
+		ft->mtu = ip6_dst_mtu_forward(dst);
 		break;
 	}
 

@@ -44,8 +49,7 @@ flow_offload_fill_dir(struct flow_offload *flow, struct nf_conn *ct,
 
 	ft->iifidx = route->tuple[dir].ifindex;
 	ft->oifidx = route->tuple[!dir].ifindex;
-
-	ft->dst_cache = route->tuple[dir].dst;
+	ft->dst_cache = dst;
 }
 
 struct flow_offload *

similarity index 100%
rename from net/netfilter/nf_flow_table.c
rename to net/netfilter/nf_flow_table_core.c

index 461b1815e633..b6e43ff0c7b7 100644
@@ -2,249 +2,8 @@
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/netfilter.h>
-#include <linux/rhashtable.h>
-#include <linux/ip.h>
-#include <linux/netdevice.h>
-#include <net/ip.h>
-#include <net/neighbour.h>
 #include <net/netfilter/nf_flow_table.h>
 #include <net/netfilter/nf_tables.h>
-/* For layer 4 checksum field offset. */
-#include <linux/tcp.h>
-#include <linux/udp.h>
-
-static int nf_flow_nat_ip_tcp(struct sk_buff *skb, unsigned int thoff,
-			      __be32 addr, __be32 new_addr)
-{
-	struct tcphdr *tcph;
-
-	if (!pskb_may_pull(skb, thoff + sizeof(*tcph)) ||
-	    skb_try_make_writable(skb, thoff + sizeof(*tcph)))
-		return -1;
-
-	tcph = (void *)(skb_network_header(skb) + thoff);
-	inet_proto_csum_replace4(&tcph->check, skb, addr, new_addr, true);
-
-	return 0;
-}
-
-static int nf_flow_nat_ip_udp(struct sk_buff *skb, unsigned int thoff,
-			      __be32 addr, __be32 new_addr)
-{
-	struct udphdr *udph;
-
-	if (!pskb_may_pull(skb, thoff + sizeof(*udph)) ||
-	    skb_try_make_writable(skb, thoff + sizeof(*udph)))
-		return -1;
-
-	udph = (void *)(skb_network_header(skb) + thoff);
-	if (udph->check || skb->ip_summed == CHECKSUM_PARTIAL) {
-		inet_proto_csum_replace4(&udph->check, skb, addr,
-					 new_addr, true);
-		if (!udph->check)
-			udph->check = CSUM_MANGLED_0;
-	}
-
-	return 0;
-}
-
-static int nf_flow_nat_ip_l4proto(struct sk_buff *skb, struct iphdr *iph,
-				  unsigned int thoff, __be32 addr,
-				  __be32 new_addr)
-{
-	switch (iph->protocol) {
-	case IPPROTO_TCP:
-		if (nf_flow_nat_ip_tcp(skb, thoff, addr, new_addr) < 0)
-			return NF_DROP;
-		break;
-	case IPPROTO_UDP:
-		if (nf_flow_nat_ip_udp(skb, thoff, addr, new_addr) < 0)
-			return NF_DROP;
-		break;
-	}
-
-	return 0;
-}
-
-static int nf_flow_snat_ip(const struct flow_offload *flow, struct sk_buff *skb,
-			   struct iphdr *iph, unsigned int thoff,
-			   enum flow_offload_tuple_dir dir)
-{
-	__be32 addr, new_addr;
-
-	switch (dir) {
-	case FLOW_OFFLOAD_DIR_ORIGINAL:
-		addr = iph->saddr;
-		new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_v4.s_addr;
-		iph->saddr = new_addr;
-		break;
-	case FLOW_OFFLOAD_DIR_REPLY:
-		addr = iph->daddr;
-		new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_v4.s_addr;
-		iph->daddr = new_addr;
-		break;
-	default:
-		return -1;
-	}
-	csum_replace4(&iph->check, addr, new_addr);
-
-	return nf_flow_nat_ip_l4proto(skb, iph, thoff, addr, new_addr);
-}
-
-static int nf_flow_dnat_ip(const struct flow_offload *flow, struct sk_buff *skb,
-			   struct iphdr *iph, unsigned int thoff,
-			   enum flow_offload_tuple_dir dir)
-{
-	__be32 addr, new_addr;
-
-	switch (dir) {
-	case FLOW_OFFLOAD_DIR_ORIGINAL:
-		addr = iph->daddr;
-		new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.src_v4.s_addr;
-		iph->daddr = new_addr;
-		break;
-	case FLOW_OFFLOAD_DIR_REPLY:
-		addr = iph->saddr;
-		new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_v4.s_addr;
-		iph->saddr = new_addr;
-		break;
-	default:
-		return -1;
-	}
-	csum_replace4(&iph->check, addr, new_addr);
-
-	return nf_flow_nat_ip_l4proto(skb, iph, thoff, addr, new_addr);
-}
-
-static int nf_flow_nat_ip(const struct flow_offload *flow, struct sk_buff *skb,
-			  enum flow_offload_tuple_dir dir)
-{
-	struct iphdr *iph = ip_hdr(skb);
-	unsigned int thoff = iph->ihl * 4;
-
-	if (flow->flags & FLOW_OFFLOAD_SNAT &&
-	    (nf_flow_snat_port(flow, skb, thoff, iph->protocol, dir) < 0 ||
-	     nf_flow_snat_ip(flow, skb, iph, thoff, dir) < 0))
-		return -1;
-	if (flow->flags & FLOW_OFFLOAD_DNAT &&
-	    (nf_flow_dnat_port(flow, skb, thoff, iph->protocol, dir) < 0 ||
-	     nf_flow_dnat_ip(flow, skb, iph, thoff, dir) < 0))
-		return -1;
-
-	return 0;
-}
-
-static bool ip_has_options(unsigned int thoff)
-{
-	return thoff != sizeof(struct iphdr);
-}
-
-static int nf_flow_tuple_ip(struct sk_buff *skb, const struct net_device *dev,
-			    struct flow_offload_tuple *tuple)
-{
-	struct flow_ports *ports;
-	unsigned int thoff;
-	struct iphdr *iph;
-
-	if (!pskb_may_pull(skb, sizeof(*iph)))
-		return -1;
-
-	iph = ip_hdr(skb);
-	thoff = iph->ihl * 4;
-
-	if (ip_is_fragment(iph) ||
-	    unlikely(ip_has_options(thoff)))
-		return -1;
-
-	if (iph->protocol != IPPROTO_TCP &&
-	    iph->protocol != IPPROTO_UDP)
-		return -1;
-
-	thoff = iph->ihl * 4;
-	if (!pskb_may_pull(skb, thoff + sizeof(*ports)))
-		return -1;
-
-	ports = (struct flow_ports *)(skb_network_header(skb) + thoff);
-
-	tuple->src_v4.s_addr	= iph->saddr;
-	tuple->dst_v4.s_addr	= iph->daddr;
-	tuple->src_port		= ports->source;
-	tuple->dst_port		= ports->dest;
-	tuple->l3proto		= AF_INET;
-	tuple->l4proto		= iph->protocol;
-	tuple->iifidx		= dev->ifindex;
-
-	return 0;
-}
-
-/* Based on ip_exceeds_mtu(). */
-static bool nf_flow_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu)
-{
-	if (skb->len <= mtu)
-		return false;
-
-	if ((ip_hdr(skb)->frag_off & htons(IP_DF)) == 0)
-		return false;
-
-	if (skb_is_gso(skb) && skb_gso_validate_network_len(skb, mtu))
-		return false;
-
-	return true;
-}
-
-unsigned int
-nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb,
-			const struct nf_hook_state *state)
-{
-	struct flow_offload_tuple_rhash *tuplehash;
-	struct nf_flowtable *flow_table = priv;
-	struct flow_offload_tuple tuple = {};
-	enum flow_offload_tuple_dir dir;
-	struct flow_offload *flow;
-	struct net_device *outdev;
-	const struct rtable *rt;
-	struct iphdr *iph;
-	__be32 nexthop;
-
-	if (skb->protocol != htons(ETH_P_IP))
-		return NF_ACCEPT;
-
-	if (nf_flow_tuple_ip(skb, state->in, &tuple) < 0)
-		return NF_ACCEPT;
-
-	tuplehash = flow_offload_lookup(flow_table, &tuple);
-	if (tuplehash == NULL)
-		return NF_ACCEPT;
-
-	outdev = dev_get_by_index_rcu(state->net, tuplehash->tuple.oifidx);
-	if (!outdev)
-		return NF_ACCEPT;
-
-	dir = tuplehash->tuple.dir;
-	flow = container_of(tuplehash, struct flow_offload, tuplehash[dir]);
-	rt = (const struct rtable *)flow->tuplehash[dir].tuple.dst_cache;
-
-	if (unlikely(nf_flow_exceeds_mtu(skb, flow->tuplehash[dir].tuple.mtu)))
-		return NF_ACCEPT;
-
-	if (skb_try_make_writable(skb, sizeof(*iph)))
-		return NF_DROP;
-
-	if (flow->flags & (FLOW_OFFLOAD_SNAT | FLOW_OFFLOAD_DNAT) &&
-	    nf_flow_nat_ip(flow, skb, dir) < 0)
-		return NF_DROP;
-
-	flow->timeout = (u32)jiffies + NF_FLOW_TIMEOUT;
-	iph = ip_hdr(skb);
-	ip_decrease_ttl(iph);
-
-	skb->dev = outdev;
-	nexthop = rt_nexthop(rt, flow->tuplehash[!dir].tuple.src_v4.s_addr);
-	neigh_xmit(NEIGH_ARP_TABLE, outdev, &nexthop, skb);
-
-	return NF_STOLEN;
-}
-EXPORT_SYMBOL_GPL(nf_flow_offload_ip_hook);
 
 static struct nf_flowtable_type flowtable_ipv4 = {
 	.family		= NFPROTO_IPV4,

246 lines not on this page · raw message

index 034fda963392..103263e0c7c2 100644
@@ -182,9 +182,6 @@ static bool nf_flow_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu)
 	if (skb->len <= mtu)
 		return false;
 
-	if ((ip_hdr(skb)->frag_off & htons(IP_DF)) == 0)
-		return false;
-
 	if (skb_is_gso(skb) && skb_gso_validate_network_len(skb, mtu))
 		return false;
 

@@ -223,7 +220,8 @@ nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb,
 	flow = container_of(tuplehash, struct flow_offload, tuplehash[dir]);
 	rt = (const struct rtable *)flow->tuplehash[dir].tuple.dst_cache;
 
-	if (unlikely(nf_flow_exceeds_mtu(skb, flow->tuplehash[dir].tuple.mtu)))
+	if (unlikely(nf_flow_exceeds_mtu(skb, flow->tuplehash[dir].tuple.mtu)) &&
+	    (ip_hdr(skb)->frag_off & htons(IP_DF)) != 0)
 		return NF_ACCEPT;
 
 	if (skb_try_make_writable(skb, sizeof(*iph)))

index 0e6328490142..f1804ce8d561 100644
@@ -3,240 +3,8 @@
 #include <linux/module.h>
 #include <linux/netfilter.h>
 #include <linux/rhashtable.h>
-#include <linux/ipv6.h>
-#include <linux/netdevice.h>
-#include <net/ipv6.h>
-#include <net/ip6_route.h>
-#include <net/neighbour.h>
 #include <net/netfilter/nf_flow_table.h>
 #include <net/netfilter/nf_tables.h>
-/* For layer 4 checksum field offset. */
-#include <linux/tcp.h>
-#include <linux/udp.h>
-
-static int nf_flow_nat_ipv6_tcp(struct sk_buff *skb, unsigned int thoff,
-				struct in6_addr *addr,
-				struct in6_addr *new_addr)
-{
-	struct tcphdr *tcph;
-
-	if (!pskb_may_pull(skb, thoff + sizeof(*tcph)) ||
-	    skb_try_make_writable(skb, thoff + sizeof(*tcph)))
-		return -1;
-
-	tcph = (void *)(skb_network_header(skb) + thoff);
-	inet_proto_csum_replace16(&tcph->check, skb, addr->s6_addr32,
-				  new_addr->s6_addr32, true);
-
-	return 0;
-}
-
-static int nf_flow_nat_ipv6_udp(struct sk_buff *skb, unsigned int thoff,
-				struct in6_addr *addr,
-				struct in6_addr *new_addr)
-{
-	struct udphdr *udph;
-
-	if (!pskb_may_pull(skb, thoff + sizeof(*udph)) ||
-	    skb_try_make_writable(skb, thoff + sizeof(*udph)))
-		return -1;
-
-	udph = (void *)(skb_network_header(skb) + thoff);
-	if (udph->check || skb->ip_summed == CHECKSUM_PARTIAL) {
-		inet_proto_csum_replace16(&udph->check, skb, addr->s6_addr32,
-					  new_addr->s6_addr32, true);
-		if (!udph->check)
-			udph->check = CSUM_MANGLED_0;
-	}
-
-	return 0;
-}
-
-static int nf_flow_nat_ipv6_l4proto(struct sk_buff *skb, struct ipv6hdr *ip6h,
-				    unsigned int thoff, struct in6_addr *addr,
-				    struct in6_addr *new_addr)
-{
-	switch (ip6h->nexthdr) {
-	case IPPROTO_TCP:
-		if (nf_flow_nat_ipv6_tcp(skb, thoff, addr, new_addr) < 0)
-			return NF_DROP;
-		break;
-	case IPPROTO_UDP:
-		if (nf_flow_nat_ipv6_udp(skb, thoff, addr, new_addr) < 0)
-			return NF_DROP;
-		break;
-	}
-
-	return 0;
-}
-
-static int nf_flow_snat_ipv6(const struct flow_offload *flow,
-			     struct sk_buff *skb, struct ipv6hdr *ip6h,
-			     unsigned int thoff,
-			     enum flow_offload_tuple_dir dir)
-{
-	struct in6_addr addr, new_addr;
-
-	switch (dir) {
-	case FLOW_OFFLOAD_DIR_ORIGINAL:
-		addr = ip6h->saddr;
-		new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_v6;
-		ip6h->saddr = new_addr;
-		break;
-	case FLOW_OFFLOAD_DIR_REPLY:
-		addr = ip6h->daddr;
-		new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_v6;
-		ip6h->daddr = new_addr;
-		break;
-	default:
-		return -1;
-	}
-
-	return nf_flow_nat_ipv6_l4proto(skb, ip6h, thoff, &addr, &new_addr);
-}
-
-static int nf_flow_dnat_ipv6(const struct flow_offload *flow,
-			     struct sk_buff *skb, struct ipv6hdr *ip6h,
-			     unsigned int thoff,
-			     enum flow_offload_tuple_dir dir)
-{
-	struct in6_addr addr, new_addr;
-
-	switch (dir) {
-	case FLOW_OFFLOAD_DIR_ORIGINAL:
-		addr = ip6h->daddr;
-		new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.src_v6;
-		ip6h->daddr = new_addr;
-		break;
-	case FLOW_OFFLOAD_DIR_REPLY:
-		addr = ip6h->saddr;
-		new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_v6;
-		ip6h->saddr = new_addr;
-		break;
-	default:
-		return -1;
-	}
-
-	return nf_flow_nat_ipv6_l4proto(skb, ip6h, thoff, &addr, &new_addr);
-}
-
-static int nf_flow_nat_ipv6(const struct flow_offload *flow,
-			    struct sk_buff *skb,
-			    enum flow_offload_tuple_dir dir)
-{
-	struct ipv6hdr *ip6h = ipv6_hdr(skb);
-	unsigned int thoff = sizeof(*ip6h);
-
-	if (flow->flags & FLOW_OFFLOAD_SNAT &&
-	    (nf_flow_snat_port(flow, skb, thoff, ip6h->nexthdr, dir) < 0 ||
-	     nf_flow_snat_ipv6(flow, skb, ip6h, thoff, dir) < 0))
-		return -1;
-	if (flow->flags & FLOW_OFFLOAD_DNAT &&
-	    (nf_flow_dnat_port(flow, skb, thoff, ip6h->nexthdr, dir) < 0 ||
-	     nf_flow_dnat_ipv6(flow, skb, ip6h, thoff, dir) < 0))
-		return -1;
-
-	return 0;
-}
-
-static int nf_flow_tuple_ipv6(struct sk_buff *skb, const struct net_device *dev,
-			      struct flow_offload_tuple *tuple)
-{
-	struct flow_ports *ports;
-	struct ipv6hdr *ip6h;
-	unsigned int thoff;
-
-	if (!pskb_may_pull(skb, sizeof(*ip6h)))
-		return -1;
-
-	ip6h = ipv6_hdr(skb);
-
-	if (ip6h->nexthdr != IPPROTO_TCP &&
-	    ip6h->nexthdr != IPPROTO_UDP)
-		return -1;
-
-	thoff = sizeof(*ip6h);
-	if (!pskb_may_pull(skb, thoff + sizeof(*ports)))
-		return -1;
-
-	ports = (struct flow_ports *)(skb_network_header(skb) + thoff);
-
-	tuple->src_v6		= ip6h->saddr;
-	tuple->dst_v6		= ip6h->daddr;
-	tuple->src_port		= ports->source;
-	tuple->dst_port		= ports->dest;
-	tuple->l3proto		= AF_INET6;
-	tuple->l4proto		= ip6h->nexthdr;
-	tuple->iifidx		= dev->ifindex;
-
-	return 0;
-}
-
-/* Based on ip_exceeds_mtu(). */
-static bool nf_flow_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu)
-{
-	if (skb->len <= mtu)
-		return false;
-
-	if (skb_is_gso(skb) && skb_gso_validate_network_len(skb, mtu))
-		return false;
-
-	return true;
-}
-
-unsigned int
-nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb,
-			  const struct nf_hook_state *state)
-{
-	struct flow_offload_tuple_rhash *tuplehash;
-	struct nf_flowtable *flow_table = priv;
-	struct flow_offload_tuple tuple = {};
-	enum flow_offload_tuple_dir dir;
-	struct flow_offload *flow;
-	struct net_device *outdev;
-	struct in6_addr *nexthop;
-	struct ipv6hdr *ip6h;
-	struct rt6_info *rt;
-
-	if (skb->protocol != htons(ETH_P_IPV6))
-		return NF_ACCEPT;
-
-	if (nf_flow_tuple_ipv6(skb, state->in, &tuple) < 0)
-		return NF_ACCEPT;
-
-	tuplehash = flow_offload_lookup(flow_table, &tuple);
-	if (tuplehash == NULL)
-		return NF_ACCEPT;
-
-	outdev = dev_get_by_index_rcu(state->net, tuplehash->tuple.oifidx);
-	if (!outdev)
-		return NF_ACCEPT;
-
-	dir = tuplehash->tuple.dir;
-	flow = container_of(tuplehash, struct flow_offload, tuplehash[dir]);
-	rt = (struct rt6_info *)flow->tuplehash[dir].tuple.dst_cache;
-
-	if (unlikely(nf_flow_exceeds_mtu(skb, flow->tuplehash[dir].tuple.mtu)))
-		return NF_ACCEPT;
-
-	if (skb_try_make_writable(skb, sizeof(*ip6h)))
-		return NF_DROP;
-
-	if (flow->flags & (FLOW_OFFLOAD_SNAT | FLOW_OFFLOAD_DNAT) &&
-	    nf_flow_nat_ipv6(flow, skb, dir) < 0)
-		return NF_DROP;
-
-	flow->timeout = (u32)jiffies + NF_FLOW_TIMEOUT;
-	ip6h = ipv6_hdr(skb);
-	ip6h->hop_limit--;
-
-	skb->dev = outdev;
-	nexthop = rt6_nexthop(rt, &flow->tuplehash[!dir].tuple.src_v6);
-	neigh_xmit(NEIGH_ND_TABLE, outdev, nexthop, skb);
-
-	return NF_STOLEN;
-}
-EXPORT_SYMBOL_GPL(nf_flow_offload_ipv6_hook);
 
 static struct nf_flowtable_type flowtable_ipv6 = {
 	.family		= NFPROTO_IPV6,

226 lines not on this page · raw message

index 76ee5c81b752..f876e32a60b8 100644
@@ -14,9 +14,8 @@ struct nf_flowtable;
 struct nf_flowtable_type {
 	struct list_head		list;
 	int				family;
-	void				(*gc)(struct work_struct *work);
+	int				(*init)(struct nf_flowtable *ft);
 	void				(*free)(struct nf_flowtable *ft);
-	const struct rhashtable_params	*params;
 	nf_hookfn			*hook;
 	struct module			*owner;
 };

@@ -100,9 +99,8 @@ int nf_flow_table_iterate(struct nf_flowtable *flow_table,
 
 void nf_flow_table_cleanup(struct net *net, struct net_device *dev);
 
+int nf_flow_table_init(struct nf_flowtable *flow_table);
 void nf_flow_table_free(struct nf_flowtable *flow_table);
-void nf_flow_offload_work_gc(struct work_struct *work);
-extern const struct rhashtable_params nf_flow_offload_rhash_params;
 
 void flow_offload_dead(struct flow_offload *flow);
 

index b6e43ff0c7b7..e1e56d7123d2 100644
@@ -7,8 +7,7 @@
 
 static struct nf_flowtable_type flowtable_ipv4 = {
 	.family		= NFPROTO_IPV4,
-	.params		= &nf_flow_offload_rhash_params,
-	.gc		= nf_flow_offload_work_gc,
+	.init		= nf_flow_table_init,
 	.free		= nf_flow_table_free,
 	.hook		= nf_flow_offload_ip_hook,
 	.owner		= THIS_MODULE,

index f1804ce8d561..c511d206bf9b 100644
@@ -8,8 +8,7 @@
 
 static struct nf_flowtable_type flowtable_ipv6 = {
 	.family		= NFPROTO_IPV6,
-	.params		= &nf_flow_offload_rhash_params,
-	.gc		= nf_flow_offload_work_gc,
+	.init		= nf_flow_table_init,
 	.free		= nf_flow_table_free,
 	.hook		= nf_flow_offload_ipv6_hook,
 	.owner		= THIS_MODULE,

156 lines not on this page · raw message

index 375a1881d93d..99771aa7e7ea 100644
@@ -22,8 +22,7 @@ nf_flow_offload_inet_hook(void *priv, struct sk_buff *skb,
 
 static struct nf_flowtable_type flowtable_inet = {
 	.family		= NFPROTO_INET,
-	.params		= &nf_flow_offload_rhash_params,
-	.gc		= nf_flow_offload_work_gc,
+	.init		= nf_flow_table_init,
 	.free		= nf_flow_table_free,
 	.hook		= nf_flow_offload_inet_hook,
 	.owner		= THIS_MODULE,

index 9134cc429ad4..6cd9955916e5 100644
@@ -5150,14 +5150,14 @@ static int nf_tables_newflowtable(struct net *net, struct sock *nlsk,
 	}
 
 	flowtable->data.type = type;
-	err = rhashtable_init(&flowtable->data.rhashtable, type->params);
+	err = type->init(&flowtable->data);
 	if (err < 0)
 		goto err3;
 
 	err = nf_tables_flowtable_parse_hook(&ctx, nla[NFTA_FLOWTABLE_HOOK],
 					     flowtable);
 	if (err < 0)
-		goto err3;
+		goto err4;
 
 	for (i = 0; i < flowtable->ops_len; i++) {
 		if (!flowtable->ops[i].dev)

@@ -5171,37 +5171,35 @@ static int nf_tables_newflowtable(struct net *net, struct sock *nlsk,
 				if (flowtable->ops[i].dev == ft->ops[k].dev &&
 				    flowtable->ops[i].pf == ft->ops[k].pf) {
 					err = -EBUSY;
-					goto err4;
+					goto err5;
 				}
 			}
 		}
 
 		err = nf_register_net_hook(net, &flowtable->ops[i]);
 		if (err < 0)
-			goto err4;
+			goto err5;
 	}
 
 	err = nft_trans_flowtable_add(&ctx, NFT_MSG_NEWFLOWTABLE, flowtable);
 	if (err < 0)
-		goto err5;
-
-	INIT_DEFERRABLE_WORK(&flowtable->data.gc_work, type->gc);
-	queue_delayed_work(system_power_efficient_wq,
-			   &flowtable->data.gc_work, HZ);
+		goto err6;
 
 	list_add_tail_rcu(&flowtable->list, &table->flowtables);
 	table->use++;
 
 	return 0;
-err5:
+err6:
 	i = flowtable->ops_len;
-err4:
+err5:
 	for (k = i - 1; k >= 0; k--) {
 		kfree(flowtable->dev_name[k]);
 		nf_unregister_net_hook(net, &flowtable->ops[k]);
 	}
 
 	kfree(flowtable->ops);
+err4:
+	flowtable->data.type->free(&flowtable->data);
 err3:
 	module_put(type->owner);
 err2:

@@ -5485,11 +5483,9 @@ static void nf_tables_flowtable_notify(struct nft_ctx *ctx,
 
 static void nf_tables_flowtable_destroy(struct nft_flowtable *flowtable)
 {
-	cancel_delayed_work_sync(&flowtable->data.gc_work);
 	kfree(flowtable->ops);
 	kfree(flowtable->name);
 	flowtable->data.type->free(&flowtable->data);
-	rhashtable_destroy(&flowtable->data.rhashtable);
 	module_put(flowtable->data.type->owner);
 }
 

index 6cd9955916e5..517bb93c00fb 100644
@@ -5019,7 +5019,7 @@ static int nf_tables_flowtable_parse_hook(const struct nft_ctx *ctx,
 		flowtable->ops[i].pf		= NFPROTO_NETDEV;
 		flowtable->ops[i].hooknum	= hooknum;
 		flowtable->ops[i].priority	= priority;
-		flowtable->ops[i].priv		= &flowtable->data.rhashtable;
+		flowtable->ops[i].priv		= &flowtable->data;
 		flowtable->ops[i].hook		= flowtable->data.type->hook;
 		flowtable->ops[i].dev		= dev_array[i];
 		flowtable->dev_name[i]		= kstrdup(dev_array[i]->name,

index f876e32a60b8..ab408adba688 100644
@@ -21,6 +21,7 @@ struct nf_flowtable_type {
 };
 
 struct nf_flowtable {
+	struct list_head		list;
 	struct rhashtable		rhashtable;
 	const struct nf_flowtable_type	*type;
 	struct delayed_work		gc_work;

index cd368d1b8cb8..2f2062ae1c45 100644
@@ -1109,9 +1109,6 @@ struct nft_flowtable {
 struct nft_flowtable *nf_tables_flowtable_lookup(const struct nft_table *table,
 						 const struct nlattr *nla,
 						 u8 genmask);
-void nft_flow_table_iterate(struct net *net,
-			    void (*iter)(struct nf_flowtable *flowtable, void *data),
-			    void *data);
 
 void nft_register_flowtable_type(struct nf_flowtable_type *type);
 void nft_unregister_flowtable_type(struct nf_flowtable_type *type);

index 09d1be669c39..e761359b56a9 100644
@@ -18,6 +18,9 @@ struct flow_offload_entry {
 	struct rcu_head		rcu_head;
 };
 
+static DEFINE_MUTEX(flowtable_lock);
+static LIST_HEAD(flowtables);
+
 static void
 flow_offload_fill_dir(struct flow_offload *flow, struct nf_conn *ct,
 		      struct nf_flow_route *route,

@@ -410,6 +413,10 @@ int nf_flow_table_init(struct nf_flowtable *flowtable)
 	queue_delayed_work(system_power_efficient_wq,
 			   &flowtable->gc_work, HZ);
 
+	mutex_lock(&flowtable_lock);
+	list_add(&flowtable->list, &flowtables);
+	mutex_unlock(&flowtable_lock);
+
 	return 0;
 }
 EXPORT_SYMBOL_GPL(nf_flow_table_init);

@@ -425,20 +432,28 @@ static void nf_flow_table_do_cleanup(struct flow_offload *flow, void *data)
 }
 
 static void nf_flow_table_iterate_cleanup(struct nf_flowtable *flowtable,
-					  void *data)
+					  struct net_device *dev)
 {
-	nf_flow_table_iterate(flowtable, nf_flow_table_do_cleanup, data);
+	nf_flow_table_iterate(flowtable, nf_flow_table_do_cleanup, dev);
 	flush_delayed_work(&flowtable->gc_work);
 }
 
 void nf_flow_table_cleanup(struct net *net, struct net_device *dev)
 {
-	nft_flow_table_iterate(net, nf_flow_table_iterate_cleanup, dev);
+	struct nf_flowtable *flowtable;
+
+	mutex_lock(&flowtable_lock);
+	list_for_each_entry(flowtable, &flowtables, list)
+		nf_flow_table_iterate_cleanup(flowtable, dev);
+	mutex_unlock(&flowtable_lock);
 }
 EXPORT_SYMBOL_GPL(nf_flow_table_cleanup);
 
 void nf_flow_table_free(struct nf_flowtable *flow_table)
 {
+	mutex_lock(&flowtable_lock);
+	list_del(&flow_table->list);
+	mutex_unlock(&flowtable_lock);
 	cancel_delayed_work_sync(&flow_table->gc_work);
 	nf_flow_table_iterate(flow_table, nf_flow_table_do_cleanup, NULL);
 	WARN_ON(!nf_flow_offload_gc_step(flow_table));

index 517bb93c00fb..16b67f54b3d2 100644
@@ -5060,23 +5060,6 @@ static const struct nf_flowtable_type *nft_flowtable_type_get(u8 family)
 	return ERR_PTR(-ENOENT);
 }
 
-void nft_flow_table_iterate(struct net *net,
-			    void (*iter)(struct nf_flowtable *flowtable, void *data),
-			    void *data)
-{
-	struct nft_flowtable *flowtable;
-	const struct nft_table *table;
-
-	nfnl_lock(NFNL_SUBSYS_NFTABLES);
-	list_for_each_entry(table, &net->nft.tables, list) {
-		list_for_each_entry(flowtable, &table->flowtables, list) {
-			iter(&flowtable->data, data);
-		}
-	}
-	nfnl_unlock(NFNL_SUBSYS_NFTABLES);
-}
-EXPORT_SYMBOL_GPL(nft_flow_table_iterate);
-
 static void nft_unregister_flowtable_net_hooks(struct net *net,
 					       struct nft_flowtable *flowtable)
 {

index ab408adba688..5aa49524ebef 100644
@@ -103,7 +103,10 @@ void nf_flow_table_cleanup(struct net *net, struct net_device *dev);
 int nf_flow_table_init(struct nf_flowtable *flow_table);
 void nf_flow_table_free(struct nf_flowtable *flow_table);
 
-void flow_offload_dead(struct flow_offload *flow);
+static inline void flow_offload_dead(struct flow_offload *flow)
+{
+	flow->flags |= FLOW_OFFLOAD_DYING;
+}
 
 int nf_flow_snat_port(const struct flow_offload *flow,
 		      struct sk_buff *skb, unsigned int thoff,

index e761359b56a9..0d38f20fd226 100644
@@ -113,12 +113,6 @@ void flow_offload_free(struct flow_offload *flow)
 }
 EXPORT_SYMBOL_GPL(flow_offload_free);
 
-void flow_offload_dead(struct flow_offload *flow)
-{
-	flow->flags |= FLOW_OFFLOAD_DYING;
-}
-EXPORT_SYMBOL_GPL(flow_offload_dead);
-
 static u32 flow_offload_hash(const void *data, u32 len, u32 seed)
 {
 	const struct flow_offload_tuple *tuple = data;

index 5aa49524ebef..ba9fa4592f2b 100644
@@ -68,6 +68,7 @@ struct flow_offload_tuple_rhash {
 #define FLOW_OFFLOAD_SNAT	0x1
 #define FLOW_OFFLOAD_DNAT	0x2
 #define FLOW_OFFLOAD_DYING	0x4
+#define FLOW_OFFLOAD_TEARDOWN	0x8
 
 struct flow_offload {
 	struct flow_offload_tuple_rhash		tuplehash[FLOW_OFFLOAD_DIR_MAX];

@@ -103,6 +104,7 @@ void nf_flow_table_cleanup(struct net *net, struct net_device *dev);
 int nf_flow_table_init(struct nf_flowtable *flow_table);
 void nf_flow_table_free(struct nf_flowtable *flow_table);
 
+void flow_offload_teardown(struct flow_offload *flow);
 static inline void flow_offload_dead(struct flow_offload *flow)
 {
 	flow->flags |= FLOW_OFFLOAD_DYING;

index 0d38f20fd226..5a81e4f771e9 100644
@@ -174,6 +174,12 @@ static void flow_offload_del(struct nf_flowtable *flow_table,
 	flow_offload_free(flow);
 }
 
+void flow_offload_teardown(struct flow_offload *flow)
+{
+	flow->flags |= FLOW_OFFLOAD_TEARDOWN;
+}
+EXPORT_SYMBOL_GPL(flow_offload_teardown);
+
 struct flow_offload_tuple_rhash *
 flow_offload_lookup(struct nf_flowtable *flow_table,
 		    struct flow_offload_tuple *tuple)

@@ -226,11 +232,6 @@ static inline bool nf_flow_has_expired(const struct flow_offload *flow)
 	return (__s32)(flow->timeout - (u32)jiffies) <= 0;
 }
 
-static inline bool nf_flow_is_dying(const struct flow_offload *flow)
-{
-	return flow->flags & FLOW_OFFLOAD_DYING;
-}
-
 static int nf_flow_offload_gc_step(struct nf_flowtable *flow_table)
 {
 	struct flow_offload_tuple_rhash *tuplehash;

@@ -258,7 +259,8 @@ static int nf_flow_offload_gc_step(struct nf_flowtable *flow_table)
 		flow = container_of(tuplehash, struct flow_offload, tuplehash[0]);
 
 		if (nf_flow_has_expired(flow) ||
-		    nf_flow_is_dying(flow))
+		    (flow->flags & (FLOW_OFFLOAD_DYING |
+				    FLOW_OFFLOAD_TEARDOWN)))
 			flow_offload_del(flow_table, flow);
 	}
 out:

@@ -419,10 +421,14 @@ static void nf_flow_table_do_cleanup(struct flow_offload *flow, void *data)
 {
 	struct net_device *dev = data;
 
-	if (dev && flow->tuplehash[0].tuple.iifidx != dev->ifindex)
+	if (!dev) {
+		flow_offload_teardown(flow);
 		return;
+	}
 
-	flow_offload_dead(flow);
+	if (flow->tuplehash[0].tuple.iifidx == dev->ifindex ||
+	    flow->tuplehash[1].tuple.iifidx == dev->ifindex)
+		flow_offload_dead(flow);
 }
 
 static void nf_flow_table_iterate_cleanup(struct nf_flowtable *flowtable,

index 5a81e4f771e9..ff5e17a15963 100644
@@ -184,8 +184,21 @@ struct flow_offload_tuple_rhash *
 flow_offload_lookup(struct nf_flowtable *flow_table,
 		    struct flow_offload_tuple *tuple)
 {
-	return rhashtable_lookup_fast(&flow_table->rhashtable, tuple,
-				      nf_flow_offload_rhash_params);
+	struct flow_offload_tuple_rhash *tuplehash;
+	struct flow_offload *flow;
+	int dir;
+
+	tuplehash = rhashtable_lookup_fast(&flow_table->rhashtable, tuple,
+					   nf_flow_offload_rhash_params);
+	if (!tuplehash)
+		return NULL;
+
+	dir = tuplehash->tuple.dir;
+	flow = container_of(tuplehash, struct flow_offload, tuplehash[dir]);
+	if (flow->flags & (FLOW_OFFLOAD_DYING | FLOW_OFFLOAD_TEARDOWN))
+		return NULL;
+
+	return tuplehash;
 }
 EXPORT_SYMBOL_GPL(flow_offload_lookup);
 

index ff5e17a15963..0699981a8511 100644
@@ -100,6 +100,43 @@ flow_offload_alloc(struct nf_conn *ct, struct nf_flow_route *route)
 }
 EXPORT_SYMBOL_GPL(flow_offload_alloc);
 
+static void flow_offload_fixup_tcp(struct ip_ct_tcp *tcp)
+{
+	tcp->state = TCP_CONNTRACK_ESTABLISHED;
+	tcp->seen[0].td_maxwin = 0;
+	tcp->seen[1].td_maxwin = 0;
+}
+
+static void flow_offload_fixup_ct_state(struct nf_conn *ct)
+{
+	const struct nf_conntrack_l4proto *l4proto;
+	struct net *net = nf_ct_net(ct);
+	unsigned int *timeouts;
+	unsigned int timeout;
+	int l4num;
+
+	l4num = nf_ct_protonum(ct);
+	if (l4num == IPPROTO_TCP)
+		flow_offload_fixup_tcp(&ct->proto.tcp);
+
+	l4proto = __nf_ct_l4proto_find(nf_ct_l3num(ct), l4num);
+	if (!l4proto)
+		return;
+
+	timeouts = l4proto->get_timeouts(net);
+	if (!timeouts)
+		return;
+
+	if (l4num == IPPROTO_TCP)
+		timeout = timeouts[TCP_CONNTRACK_ESTABLISHED];
+	else if (l4num == IPPROTO_UDP)
+		timeout = timeouts[UDP_CT_REPLIED];
+	else
+		return;
+
+	ct->timeout = nfct_time_stamp + timeout;
+}
+
 void flow_offload_free(struct flow_offload *flow)
 {
 	struct flow_offload_entry *e;

@@ -107,7 +144,8 @@ void flow_offload_free(struct flow_offload *flow)
 	dst_release(flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_cache);
 	dst_release(flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_cache);
 	e = container_of(flow, struct flow_offload_entry, flow);
-	nf_ct_delete(e->ct, 0, 0);
+	if (flow->flags & FLOW_OFFLOAD_DYING)
+		nf_ct_delete(e->ct, 0, 0);
 	nf_ct_put(e->ct);
 	kfree_rcu(e, rcu_head);
 }

@@ -164,6 +202,8 @@ EXPORT_SYMBOL_GPL(flow_offload_add);
 static void flow_offload_del(struct nf_flowtable *flow_table,
 			     struct flow_offload *flow)
 {
+	struct flow_offload_entry *e;
+
 	rhashtable_remove_fast(&flow_table->rhashtable,
 			       &flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].node,
 			       nf_flow_offload_rhash_params);

@@ -171,12 +211,20 @@ static void flow_offload_del(struct nf_flowtable *flow_table,
 			       &flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].node,
 			       nf_flow_offload_rhash_params);
 
+	e = container_of(flow, struct flow_offload_entry, flow);
+	clear_bit(IPS_OFFLOAD_BIT, &e->ct->status);
+
 	flow_offload_free(flow);
 }
 
 void flow_offload_teardown(struct flow_offload *flow)
 {
+	struct flow_offload_entry *e;
+
 	flow->flags |= FLOW_OFFLOAD_TEARDOWN;
+
+	e = container_of(flow, struct flow_offload_entry, flow);
+	flow_offload_fixup_ct_state(e->ct);
 }
 EXPORT_SYMBOL_GPL(flow_offload_teardown);
 

index dc570fb7641d..692c75ef5cb7 100644
@@ -15,6 +15,23 @@
 #include <linux/tcp.h>
 #include <linux/udp.h>
 
+static int nf_flow_tcp_state_check(struct flow_offload *flow,
+				   struct sk_buff *skb, unsigned int thoff)
+{
+	struct tcphdr *tcph;
+
+	if (!pskb_may_pull(skb, thoff + sizeof(*tcph)))
+		return -1;
+
+	tcph = (void *)(skb_network_header(skb) + thoff);
+	if (unlikely(tcph->fin || tcph->rst)) {
+		flow_offload_teardown(flow);
+		return -1;
+	}
+
+	return 0;
+}
+
 static int nf_flow_nat_ip_tcp(struct sk_buff *skb, unsigned int thoff,
 			      __be32 addr, __be32 new_addr)
 {

@@ -119,10 +136,9 @@ static int nf_flow_dnat_ip(const struct flow_offload *flow, struct sk_buff *skb,
 }
 
 static int nf_flow_nat_ip(const struct flow_offload *flow, struct sk_buff *skb,
-			  enum flow_offload_tuple_dir dir)
+			  unsigned int thoff, enum flow_offload_tuple_dir dir)
 {
 	struct iphdr *iph = ip_hdr(skb);
-	unsigned int thoff = iph->ihl * 4;
 
 	if (flow->flags & FLOW_OFFLOAD_SNAT &&
 	    (nf_flow_snat_port(flow, skb, thoff, iph->protocol, dir) < 0 ||

@@ -202,6 +218,7 @@ nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb,
 	struct flow_offload *flow;
 	struct net_device *outdev;
 	const struct rtable *rt;
+	unsigned int thoff;
 	struct iphdr *iph;
 	__be32 nexthop;
 

@@ -230,8 +247,12 @@ nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb,
 	if (skb_try_make_writable(skb, sizeof(*iph)))
 		return NF_DROP;
 
+	thoff = ip_hdr(skb)->ihl * 4;
+	if (nf_flow_tcp_state_check(flow, skb, thoff))
+		return NF_ACCEPT;
+
 	if (flow->flags & (FLOW_OFFLOAD_SNAT | FLOW_OFFLOAD_DNAT) &&
-	    nf_flow_nat_ip(flow, skb, dir) < 0)
+	    nf_flow_nat_ip(flow, skb, thoff, dir) < 0)
 		return NF_DROP;
 
 	flow->timeout = (u32)jiffies + NF_FLOW_TIMEOUT;

@@ -439,6 +460,9 @@ nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb,
 	if (unlikely(nf_flow_exceeds_mtu(skb, flow->tuplehash[dir].tuple.mtu)))
 		return NF_ACCEPT;
 
+	if (nf_flow_tcp_state_check(flow, skb, sizeof(*ip6h)))
+		return NF_ACCEPT;
+
 	if (skb_try_make_writable(skb, sizeof(*ip6h)))
 		return NF_DROP;
 

index 692c75ef5cb7..82451b7e0acb 100644
@@ -15,11 +15,14 @@
 #include <linux/tcp.h>
 #include <linux/udp.h>
 
-static int nf_flow_tcp_state_check(struct flow_offload *flow,
-				   struct sk_buff *skb, unsigned int thoff)
+static int nf_flow_state_check(struct flow_offload *flow, int proto,
+			       struct sk_buff *skb, unsigned int thoff)
 {
 	struct tcphdr *tcph;
 
+	if (proto != IPPROTO_TCP)
+		return 0;
+
 	if (!pskb_may_pull(skb, thoff + sizeof(*tcph)))
 		return -1;
 

@@ -248,7 +251,7 @@ nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb,
 		return NF_DROP;
 
 	thoff = ip_hdr(skb)->ihl * 4;
-	if (nf_flow_tcp_state_check(flow, skb, thoff))
+	if (nf_flow_state_check(flow, ip_hdr(skb)->protocol, skb, thoff))
 		return NF_ACCEPT;
 
 	if (flow->flags & (FLOW_OFFLOAD_SNAT | FLOW_OFFLOAD_DNAT) &&

@@ -460,7 +463,8 @@ nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb,
 	if (unlikely(nf_flow_exceeds_mtu(skb, flow->tuplehash[dir].tuple.mtu)))
 		return NF_ACCEPT;
 
-	if (nf_flow_tcp_state_check(flow, skb, sizeof(*ip6h)))
+	if (nf_flow_state_check(flow, ipv6_hdr(skb)->nexthdr, skb,
+				sizeof(*ip6h)))
 		return NF_ACCEPT;
 
 	if (skb_try_make_writable(skb, sizeof(*ip6h)))

index 0699981a8511..eb0d1658ac05 100644
@@ -84,7 +84,7 @@ flow_offload_alloc(struct nf_conn *ct, struct nf_flow_route *route)
 
 	if (ct->status & IPS_SRC_NAT)
 		flow->flags |= FLOW_OFFLOAD_SNAT;
-	else if (ct->status & IPS_DST_NAT)
+	if (ct->status & IPS_DST_NAT)
 		flow->flags |= FLOW_OFFLOAD_DNAT;
 
 	return flow;

index 2f2062ae1c45..123e82a2f8bb 100644
@@ -1015,9 +1015,9 @@ static inline void *nft_obj_data(const struct nft_object *obj)
 
 #define nft_expr_obj(expr)	*((struct nft_object **)nft_expr_priv(expr))
 
-struct nft_object *nf_tables_obj_lookup(const struct nft_table *table,
-					const struct nlattr *nla, u32 objtype,
-					u8 genmask);
+struct nft_object *nft_obj_lookup(const struct nft_table *table,
+				  const struct nlattr *nla, u32 objtype,
+				  u8 genmask);
 
 void nft_obj_notify(struct net *net, struct nft_table *table,
 		    struct nft_object *obj, u32 portid, u32 seq,

@@ -1106,9 +1106,9 @@ struct nft_flowtable {
 	struct nf_flowtable		data;
 };
 
-struct nft_flowtable *nf_tables_flowtable_lookup(const struct nft_table *table,
-						 const struct nlattr *nla,
-						 u8 genmask);
+struct nft_flowtable *nft_flowtable_lookup(const struct nft_table *table,
+					   const struct nlattr *nla,
+					   u8 genmask);
 
 void nft_register_flowtable_type(struct nf_flowtable_type *type);
 void nft_unregister_flowtable_type(struct nf_flowtable_type *type);

583 lines not on this page · raw message

index b65829b2be22..d6bab8c3cbb0 100644
@@ -142,9 +142,8 @@ static int nft_flow_offload_init(const struct nft_ctx *ctx,
 	if (!tb[NFTA_FLOW_TABLE_NAME])
 		return -EINVAL;
 
-	flowtable = nf_tables_flowtable_lookup(ctx->table,
-					       tb[NFTA_FLOW_TABLE_NAME],
-					       genmask);
+	flowtable = nft_flowtable_lookup(ctx->table, tb[NFTA_FLOW_TABLE_NAME],
+					 genmask);
 	if (IS_ERR(flowtable))
 		return PTR_ERR(flowtable);
 

index 0b02407773ad..cdf348f751ec 100644
@@ -38,8 +38,8 @@ static int nft_objref_init(const struct nft_ctx *ctx,
 		return -EINVAL;
 
 	objtype = ntohl(nla_get_be32(tb[NFTA_OBJREF_IMM_TYPE]));
-	obj = nf_tables_obj_lookup(ctx->table, tb[NFTA_OBJREF_IMM_NAME], objtype,
-				   genmask);
+	obj = nft_obj_lookup(ctx->table, tb[NFTA_OBJREF_IMM_NAME], objtype,
+			     genmask);
 	if (IS_ERR(obj))
 		return -ENOENT;
 

index f65e650b61aa..2f14cadd9922 100644
@@ -582,8 +582,10 @@ static int nf_tables_gettable(struct net *net, struct sock *nlsk,
 	}
 
 	table = nft_table_lookup(net, nla[NFTA_TABLE_NAME], family, genmask);
-	if (IS_ERR(table))
+	if (IS_ERR(table)) {
+		NL_SET_BAD_ATTR(extack, nla[NFTA_TABLE_NAME]);
 		return PTR_ERR(table);
+	}
 
 	skb2 = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
 	if (!skb2)

@@ -699,21 +701,23 @@ static int nf_tables_newtable(struct net *net, struct sock *nlsk,
 {
 	const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
 	u8 genmask = nft_genmask_next(net);
-	const struct nlattr *name;
-	struct nft_table *table;
 	int family = nfmsg->nfgen_family;
+	const struct nlattr *attr;
+	struct nft_table *table;
 	u32 flags = 0;
 	struct nft_ctx ctx;
 	int err;
 
-	name = nla[NFTA_TABLE_NAME];
-	table = nft_table_lookup(net, name, family, genmask);
+	attr = nla[NFTA_TABLE_NAME];
+	table = nft_table_lookup(net, attr, family, genmask);
 	if (IS_ERR(table)) {
 		if (PTR_ERR(table) != -ENOENT)
 			return PTR_ERR(table);
 	} else {
-		if (nlh->nlmsg_flags & NLM_F_EXCL)
+		if (nlh->nlmsg_flags & NLM_F_EXCL) {
+			NL_SET_BAD_ATTR(extack, attr);
 			return -EEXIST;
+		}
 		if (nlh->nlmsg_flags & NLM_F_REPLACE)
 			return -EOPNOTSUPP;
 

@@ -732,7 +736,7 @@ static int nf_tables_newtable(struct net *net, struct sock *nlsk,
 	if (table == NULL)
 		goto err_kzalloc;
 
-	table->name = nla_strdup(name, GFP_KERNEL);
+	table->name = nla_strdup(attr, GFP_KERNEL);
 	if (table->name == NULL)
 		goto err_strdup;
 

@@ -855,8 +859,9 @@ static int nf_tables_deltable(struct net *net, struct sock *nlsk,
 {
 	const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
 	u8 genmask = nft_genmask_next(net);
-	struct nft_table *table;
 	int family = nfmsg->nfgen_family;
+	const struct nlattr *attr;
+	struct nft_table *table;
 	struct nft_ctx ctx;
 
 	nft_ctx_init(&ctx, net, skb, nlh, 0, NULL, NULL, nla);

@@ -864,15 +869,18 @@ static int nf_tables_deltable(struct net *net, struct sock *nlsk,
 	    (!nla[NFTA_TABLE_NAME] && !nla[NFTA_TABLE_HANDLE]))
 		return nft_flush(&ctx, family);
 
-	if (nla[NFTA_TABLE_HANDLE])
-		table = nft_table_lookup_byhandle(net, nla[NFTA_TABLE_HANDLE],
-						  genmask);
-	else
-		table = nft_table_lookup(net, nla[NFTA_TABLE_NAME], family,
-					 genmask);
+	if (nla[NFTA_TABLE_HANDLE]) {
+		attr = nla[NFTA_TABLE_HANDLE];
+		table = nft_table_lookup_byhandle(net, attr, genmask);
+	} else {
+		attr = nla[NFTA_TABLE_NAME];
+		table = nft_table_lookup(net, attr, family, genmask);
+	}
 
-	if (IS_ERR(table))
+	if (IS_ERR(table)) {
+		NL_SET_BAD_ATTR(extack, attr);
 		return PTR_ERR(table);
+	}
 
 	if (nlh->nlmsg_flags & NLM_F_NONREC &&
 	    table->use > 0)

@@ -1164,12 +1172,16 @@ static int nf_tables_getchain(struct net *net, struct sock *nlsk,
 	}
 
 	table = nft_table_lookup(net, nla[NFTA_CHAIN_TABLE], family, genmask);
-	if (IS_ERR(table))
+	if (IS_ERR(table)) {
+		NL_SET_BAD_ATTR(extack, nla[NFTA_CHAIN_TABLE]);
 		return PTR_ERR(table);
+	}
 
 	chain = nft_chain_lookup(table, nla[NFTA_CHAIN_NAME], genmask);
-	if (IS_ERR(chain))
+	if (IS_ERR(chain)) {
+		NL_SET_BAD_ATTR(extack, nla[NFTA_CHAIN_NAME]);
 		return PTR_ERR(chain);
+	}
 
 	skb2 = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
 	if (!skb2)

@@ -1531,9 +1543,9 @@ static int nf_tables_newchain(struct net *net, struct sock *nlsk,
 			      struct netlink_ext_ack *extack)
 {
 	const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
-	const struct nlattr * uninitialized_var(name);
 	u8 genmask = nft_genmask_next(net);
 	int family = nfmsg->nfgen_family;
+	const struct nlattr *attr;
 	struct nft_table *table;
 	struct nft_chain *chain;
 	u8 policy = NF_ACCEPT;

@@ -1544,34 +1556,45 @@ static int nf_tables_newchain(struct net *net, struct sock *nlsk,
 	create = nlh->nlmsg_flags & NLM_F_CREATE ? true : false;
 
 	table = nft_table_lookup(net, nla[NFTA_CHAIN_TABLE], family, genmask);
-	if (IS_ERR(table))
+	if (IS_ERR(table)) {
+		NL_SET_BAD_ATTR(extack, nla[NFTA_CHAIN_TABLE]);
 		return PTR_ERR(table);
+	}
 
 	chain = NULL;
-	name = nla[NFTA_CHAIN_NAME];
+	attr = nla[NFTA_CHAIN_NAME];
 
 	if (nla[NFTA_CHAIN_HANDLE]) {
 		handle = be64_to_cpu(nla_get_be64(nla[NFTA_CHAIN_HANDLE]));
 		chain = nft_chain_lookup_byhandle(table, handle, genmask);
-		if (IS_ERR(chain))
+		if (IS_ERR(chain)) {
+			NL_SET_BAD_ATTR(extack, nla[NFTA_CHAIN_HANDLE]);
 			return PTR_ERR(chain);
+		}
+		attr = nla[NFTA_CHAIN_HANDLE];
 	} else {
-		chain = nft_chain_lookup(table, name, genmask);
+		chain = nft_chain_lookup(table, attr, genmask);
 		if (IS_ERR(chain)) {
-			if (PTR_ERR(chain) != -ENOENT)
+			if (PTR_ERR(chain) != -ENOENT) {
+				NL_SET_BAD_ATTR(extack, attr);
 				return PTR_ERR(chain);
+			}
 			chain = NULL;
 		}
 	}
 
 	if (nla[NFTA_CHAIN_POLICY]) {
 		if (chain != NULL &&
-		    !nft_is_base_chain(chain))
+		    !nft_is_base_chain(chain)) {
+			NL_SET_BAD_ATTR(extack, nla[NFTA_CHAIN_POLICY]);
 			return -EOPNOTSUPP;
+		}
 
 		if (chain == NULL &&
-		    nla[NFTA_CHAIN_HOOK] == NULL)
+		    nla[NFTA_CHAIN_HOOK] == NULL) {
+			NL_SET_BAD_ATTR(extack, nla[NFTA_CHAIN_POLICY]);
 			return -EOPNOTSUPP;
+		}
 
 		policy = ntohl(nla_get_be32(nla[NFTA_CHAIN_POLICY]));
 		switch (policy) {

@@ -1586,8 +1609,10 @@ static int nf_tables_newchain(struct net *net, struct sock *nlsk,
 	nft_ctx_init(&ctx, net, skb, nlh, family, table, chain, nla);
 
 	if (chain != NULL) {
-		if (nlh->nlmsg_flags & NLM_F_EXCL)
+		if (nlh->nlmsg_flags & NLM_F_EXCL) {
+			NL_SET_BAD_ATTR(extack, attr);
 			return -EEXIST;
+		}
 		if (nlh->nlmsg_flags & NLM_F_REPLACE)
 			return -EOPNOTSUPP;
 

@@ -1604,27 +1629,34 @@ static int nf_tables_delchain(struct net *net, struct sock *nlsk,
 {
 	const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
 	u8 genmask = nft_genmask_next(net);
+	int family = nfmsg->nfgen_family;
+	const struct nlattr *attr;
 	struct nft_table *table;
 	struct nft_chain *chain;
 	struct nft_rule *rule;
-	int family = nfmsg->nfgen_family;
 	struct nft_ctx ctx;
 	u64 handle;
 	u32 use;
 	int err;
 
 	table = nft_table_lookup(net, nla[NFTA_CHAIN_TABLE], family, genmask);
-	if (IS_ERR(table))
+	if (IS_ERR(table)) {
+		NL_SET_BAD_ATTR(extack, nla[NFTA_CHAIN_TABLE]);
 		return PTR_ERR(table);
+	}
 
 	if (nla[NFTA_CHAIN_HANDLE]) {
-		handle = be64_to_cpu(nla_get_be64(nla[NFTA_CHAIN_HANDLE]));
+		attr = nla[NFTA_CHAIN_HANDLE];
+		handle = be64_to_cpu(nla_get_be64(attr));
 		chain = nft_chain_lookup_byhandle(table, handle, genmask);
 	} else {
-		chain = nft_chain_lookup(table, nla[NFTA_CHAIN_NAME], genmask);
+		attr = nla[NFTA_CHAIN_NAME];
+		chain = nft_chain_lookup(table, attr, genmask);
 	}
-	if (IS_ERR(chain))
+	if (IS_ERR(chain)) {
+		NL_SET_BAD_ATTR(extack, attr);
 		return PTR_ERR(chain);
+	}
 
 	if (nlh->nlmsg_flags & NLM_F_NONREC &&
 	    chain->use > 0)

@@ -1646,8 +1678,10 @@ static int nf_tables_delchain(struct net *net, struct sock *nlsk,
 	/* There are rules and elements that are still holding references to us,
 	 * we cannot do a recursive removal in this case.
 	 */
-	if (use > 0)
+	if (use > 0) {
+		NL_SET_BAD_ATTR(extack, attr);
 		return -EBUSY;
+	}
 
 	return nft_delchain(&ctx);
 }

@@ -2157,16 +2191,22 @@ static int nf_tables_getrule(struct net *net, struct sock *nlsk,
 	}
 
 	table = nft_table_lookup(net, nla[NFTA_RULE_TABLE], family, genmask);
-	if (IS_ERR(table))
+	if (IS_ERR(table)) {
+		NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_TABLE]);
 		return PTR_ERR(table);
+	}
 
 	chain = nft_chain_lookup(table, nla[NFTA_RULE_CHAIN], genmask);
-	if (IS_ERR(chain))
+	if (IS_ERR(chain)) {
+		NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_CHAIN]);
 		return PTR_ERR(chain);
+	}
 
 	rule = nft_rule_lookup(chain, nla[NFTA_RULE_HANDLE]);
-	if (IS_ERR(rule))
+	if (IS_ERR(rule)) {
+		NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_HANDLE]);
 		return PTR_ERR(rule);
+	}
 
 	skb2 = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
 	if (!skb2)

@@ -2230,21 +2270,29 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk,
 	create = nlh->nlmsg_flags & NLM_F_CREATE ? true : false;
 
 	table = nft_table_lookup(net, nla[NFTA_RULE_TABLE], family, genmask);
-	if (IS_ERR(table))
+	if (IS_ERR(table)) {
+		NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_TABLE]);
 		return PTR_ERR(table);
+	}
 
 	chain = nft_chain_lookup(table, nla[NFTA_RULE_CHAIN], genmask);
-	if (IS_ERR(chain))
+	if (IS_ERR(chain)) {
+		NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_CHAIN]);
 		return PTR_ERR(chain);
+	}
 
 	if (nla[NFTA_RULE_HANDLE]) {
 		handle = be64_to_cpu(nla_get_be64(nla[NFTA_RULE_HANDLE]));
 		rule = __nft_rule_lookup(chain, handle);
-		if (IS_ERR(rule))
+		if (IS_ERR(rule)) {
+			NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_HANDLE]);
 			return PTR_ERR(rule);
+		}
 
-		if (nlh->nlmsg_flags & NLM_F_EXCL)
+		if (nlh->nlmsg_flags & NLM_F_EXCL) {
+			NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_HANDLE]);
 			return -EEXIST;
+		}
 		if (nlh->nlmsg_flags & NLM_F_REPLACE)
 			old_rule = rule;
 		else

@@ -2264,8 +2312,10 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk,
 
 		pos_handle = be64_to_cpu(nla_get_be64(nla[NFTA_RULE_POSITION]));
 		old_rule = __nft_rule_lookup(chain, pos_handle);
-		if (IS_ERR(old_rule))
+		if (IS_ERR(old_rule)) {
+			NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_POSITION]);
 			return PTR_ERR(old_rule);
+		}
 	}
 
 	nft_ctx_init(&ctx, net, skb, nlh, family, table, chain, nla);

@@ -2399,13 +2449,17 @@ static int nf_tables_delrule(struct net *net, struct sock *nlsk,
 	struct nft_ctx ctx;
 
 	table = nft_table_lookup(net, nla[NFTA_RULE_TABLE], family, genmask);
-	if (IS_ERR(table))
+	if (IS_ERR(table)) {
+		NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_TABLE]);
 		return PTR_ERR(table);
+	}
 
 	if (nla[NFTA_RULE_CHAIN]) {
 		chain = nft_chain_lookup(table, nla[NFTA_RULE_CHAIN], genmask);
-		if (IS_ERR(chain))
+		if (IS_ERR(chain)) {
+			NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_CHAIN]);
 			return PTR_ERR(chain);
+		}
 	}
 
 	nft_ctx_init(&ctx, net, skb, nlh, family, table, chain, nla);

@@ -2413,14 +2467,18 @@ static int nf_tables_delrule(struct net *net, struct sock *nlsk,
 	if (chain) {
 		if (nla[NFTA_RULE_HANDLE]) {
 			rule = nft_rule_lookup(chain, nla[NFTA_RULE_HANDLE]);
-			if (IS_ERR(rule))
+			if (IS_ERR(rule)) {
+				NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_HANDLE]);
 				return PTR_ERR(rule);
+			}
 
 			err = nft_delrule(&ctx, rule);
 		} else if (nla[NFTA_RULE_ID]) {
 			rule = nft_rule_lookup_byid(net, nla[NFTA_RULE_ID]);
-			if (IS_ERR(rule))
+			if (IS_ERR(rule)) {
+				NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_ID]);
 				return PTR_ERR(rule);
+			}
 
 			err = nft_delrule(&ctx, rule);
 		} else {

@@ -2588,6 +2646,7 @@ static int nft_ctx_init_from_setattr(struct nft_ctx *ctx, struct net *net,
 				     const struct sk_buff *skb,
 				     const struct nlmsghdr *nlh,
 				     const struct nlattr * const nla[],
+				     struct netlink_ext_ack *extack,
 				     u8 genmask)
 {
 	const struct nfgenmsg *nfmsg = nlmsg_data(nlh);

@@ -2597,8 +2656,10 @@ static int nft_ctx_init_from_setattr(struct nft_ctx *ctx, struct net *net,
 	if (nla[NFTA_SET_TABLE] != NULL) {
 		table = nft_table_lookup(net, nla[NFTA_SET_TABLE], family,
 					 genmask);
-		if (IS_ERR(table))
+		if (IS_ERR(table)) {
+			NL_SET_BAD_ATTR(extack, nla[NFTA_SET_TABLE]);
 			return PTR_ERR(table);
+		}
 	}
 
 	nft_ctx_init(ctx, net, skb, nlh, family, table, NULL, nla);

@@ -2910,7 +2971,8 @@ static int nf_tables_getset(struct net *net, struct sock *nlsk,
 	int err;
 
 	/* Verify existence before starting dump */
-	err = nft_ctx_init_from_setattr(&ctx, net, skb, nlh, nla, genmask);
+	err = nft_ctx_init_from_setattr(&ctx, net, skb, nlh, nla, extack,
+					genmask);
 	if (err < 0)
 		return err;
 

@@ -3090,20 +3152,27 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk,
 	create = nlh->nlmsg_flags & NLM_F_CREATE ? true : false;
 
 	table = nft_table_lookup(net, nla[NFTA_SET_TABLE], family, genmask);
-	if (IS_ERR(table))
+	if (IS_ERR(table)) {
+		NL_SET_BAD_ATTR(extack, nla[NFTA_SET_TABLE]);
 		return PTR_ERR(table);
+	}
 
 	nft_ctx_init(&ctx, net, skb, nlh, family, table, NULL, nla);
 
 	set = nft_set_lookup(table, nla[NFTA_SET_NAME], genmask);
 	if (IS_ERR(set)) {
-		if (PTR_ERR(set) != -ENOENT)
+		if (PTR_ERR(set) != -ENOENT) {
+			NL_SET_BAD_ATTR(extack, nla[NFTA_SET_NAME]);
 			return PTR_ERR(set);
+		}
 	} else {
-		if (nlh->nlmsg_flags & NLM_F_EXCL)
+		if (nlh->nlmsg_flags & NLM_F_EXCL) {
+			NL_SET_BAD_ATTR(extack, nla[NFTA_SET_NAME]);
 			return -EEXIST;
+		}
 		if (nlh->nlmsg_flags & NLM_F_REPLACE)
 			return -EOPNOTSUPP;
+
 		return 0;
 	}
 

@@ -3204,6 +3273,7 @@ static int nf_tables_delset(struct net *net, struct sock *nlsk,
 {
 	const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
 	u8 genmask = nft_genmask_next(net);
+	const struct nlattr *attr;
 	struct nft_set *set;
 	struct nft_ctx ctx;
 	int err;

@@ -3213,21 +3283,28 @@ static int nf_tables_delset(struct net *net, struct sock *nlsk,
 	if (nla[NFTA_SET_TABLE] == NULL)
 		return -EINVAL;
 
-	err = nft_ctx_init_from_setattr(&ctx, net, skb, nlh, nla, genmask);
+	err = nft_ctx_init_from_setattr(&ctx, net, skb, nlh, nla, extack,
+					genmask);
 	if (err < 0)
 		return err;
 
-	if (nla[NFTA_SET_HANDLE])
-		set = nft_set_lookup_byhandle(ctx.table, nla[NFTA_SET_HANDLE],
-					      genmask);
-	else
-		set = nft_set_lookup(ctx.table, nla[NFTA_SET_NAME], genmask);
-	if (IS_ERR(set))
-		return PTR_ERR(set);
+	if (nla[NFTA_SET_HANDLE]) {
+		attr = nla[NFTA_SET_HANDLE];
+		set = nft_set_lookup_byhandle(ctx.table, attr, genmask);
+	} else {
+		attr = nla[NFTA_SET_NAME];
+		set = nft_set_lookup(ctx.table, attr, genmask);
+	}
 
+	if (IS_ERR(set)) {
+		NL_SET_BAD_ATTR(extack, attr);
+		return PTR_ERR(set);
+	}
 	if (!list_empty(&set->bindings) ||
-	    (nlh->nlmsg_flags & NLM_F_NONREC && atomic_read(&set->nelems) > 0))
+	    (nlh->nlmsg_flags & NLM_F_NONREC && atomic_read(&set->nelems) > 0)) {
+		NL_SET_BAD_ATTR(extack, attr);
 		return -EBUSY;
+	}
 
 	return nft_delset(&ctx, set);
 }

@@ -3355,6 +3432,7 @@ static int nft_ctx_init_from_elemattr(struct nft_ctx *ctx, struct net *net,
 				      const struct sk_buff *skb,
 				      const struct nlmsghdr *nlh,
 				      const struct nlattr * const nla[],
+				      struct netlink_ext_ack *extack,
 				      u8 genmask)
 {
 	const struct nfgenmsg *nfmsg = nlmsg_data(nlh);

@@ -3363,8 +3441,10 @@ static int nft_ctx_init_from_elemattr(struct nft_ctx *ctx, struct net *net,
 
 	table = nft_table_lookup(net, nla[NFTA_SET_ELEM_LIST_TABLE], family,
 				 genmask);
-	if (IS_ERR(table))
+	if (IS_ERR(table)) {
+		NL_SET_BAD_ATTR(extack, nla[NFTA_SET_ELEM_LIST_TABLE]);
 		return PTR_ERR(table);
+	}
 
 	nft_ctx_init(ctx, net, skb, nlh, family, table, NULL, nla);
 	return 0;

@@ -3694,7 +3774,8 @@ static int nf_tables_getsetelem(struct net *net, struct sock *nlsk,
 	struct nft_ctx ctx;
 	int rem, err = 0;
 
-	err = nft_ctx_init_from_elemattr(&ctx, net, skb, nlh, nla, genmask);
+	err = nft_ctx_init_from_elemattr(&ctx, net, skb, nlh, nla, extack,
+					 genmask);
 	if (err < 0)
 		return err;
 

@@ -4048,7 +4129,8 @@ static int nf_tables_newsetelem(struct net *net, struct sock *nlsk,
 	if (nla[NFTA_SET_ELEM_LIST_ELEMENTS] == NULL)
 		return -EINVAL;
 
-	err = nft_ctx_init_from_elemattr(&ctx, net, skb, nlh, nla, genmask);
+	err = nft_ctx_init_from_elemattr(&ctx, net, skb, nlh, nla, extack,
+					 genmask);
 	if (err < 0)
 		return err;
 

@@ -4236,7 +4318,8 @@ static int nf_tables_delsetelem(struct net *net, struct sock *nlsk,
 	struct nft_ctx ctx;
 	int rem, err = 0;
 
-	err = nft_ctx_init_from_elemattr(&ctx, net, skb, nlh, nla, genmask);
+	err = nft_ctx_init_from_elemattr(&ctx, net, skb, nlh, nla, extack,
+					 genmask);
 	if (err < 0)
 		return err;
 

@@ -4491,20 +4574,24 @@ static int nf_tables_newobj(struct net *net, struct sock *nlsk,
 		return -EINVAL;
 
 	table = nft_table_lookup(net, nla[NFTA_OBJ_TABLE], family, genmask);
-	if (IS_ERR(table))
+	if (IS_ERR(table)) {
+		NL_SET_BAD_ATTR(extack, nla[NFTA_OBJ_TABLE]);
 		return PTR_ERR(table);
+	}
 
 	objtype = ntohl(nla_get_be32(nla[NFTA_OBJ_TYPE]));
 	obj = nft_obj_lookup(table, nla[NFTA_OBJ_NAME], objtype, genmask);
 	if (IS_ERR(obj)) {
 		err = PTR_ERR(obj);
-		if (err != -ENOENT)
+		if (err != -ENOENT) {
+			NL_SET_BAD_ATTR(extack, nla[NFTA_OBJ_NAME]);
 			return err;
-
+		}
 	} else {
-		if (nlh->nlmsg_flags & NLM_F_EXCL)
+		if (nlh->nlmsg_flags & NLM_F_EXCL) {
+			NL_SET_BAD_ATTR(extack, nla[NFTA_OBJ_NAME]);
 			return -EEXIST;
-
+		}
 		return 0;
 	}
 

@@ -4716,13 +4803,17 @@ static int nf_tables_getobj(struct net *net, struct sock *nlsk,
 		return -EINVAL;
 
 	table = nft_table_lookup(net, nla[NFTA_OBJ_TABLE], family, genmask);
-	if (IS_ERR(table))
+	if (IS_ERR(table)) {
+		NL_SET_BAD_ATTR(extack, nla[NFTA_OBJ_TABLE]);
 		return PTR_ERR(table);
+	}
 
 	objtype = ntohl(nla_get_be32(nla[NFTA_OBJ_TYPE]));
 	obj = nft_obj_lookup(table, nla[NFTA_OBJ_NAME], objtype, genmask);
-	if (IS_ERR(obj))
+	if (IS_ERR(obj)) {
+		NL_SET_BAD_ATTR(extack, nla[NFTA_OBJ_NAME]);
 		return PTR_ERR(obj);
+	}
 
 	skb2 = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
 	if (!skb2)

@@ -4761,6 +4852,7 @@ static int nf_tables_delobj(struct net *net, struct sock *nlsk,
 	const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
 	u8 genmask = nft_genmask_next(net);
 	int family = nfmsg->nfgen_family;
+	const struct nlattr *attr;
 	struct nft_table *table;
 	struct nft_object *obj;
 	struct nft_ctx ctx;

@@ -4771,20 +4863,28 @@ static int nf_tables_delobj(struct net *net, struct sock *nlsk,
 		return -EINVAL;
 
 	table = nft_table_lookup(net, nla[NFTA_OBJ_TABLE], family, genmask);
-	if (IS_ERR(table))
+	if (IS_ERR(table)) {
+		NL_SET_BAD_ATTR(extack, nla[NFTA_OBJ_TABLE]);
 		return PTR_ERR(table);
+	}
 
 	objtype = ntohl(nla_get_be32(nla[NFTA_OBJ_TYPE]));
-	if (nla[NFTA_OBJ_HANDLE])
-		obj = nft_obj_lookup_byhandle(table, nla[NFTA_OBJ_HANDLE],
-					      objtype, genmask);
-	else
-		obj = nft_obj_lookup(table, nla[NFTA_OBJ_NAME], objtype,
-				     genmask);
-	if (IS_ERR(obj))
+	if (nla[NFTA_OBJ_HANDLE]) {
+		attr = nla[NFTA_OBJ_HANDLE];
+		obj = nft_obj_lookup_byhandle(table, attr, objtype, genmask);
+	} else {
+		attr = nla[NFTA_OBJ_NAME];
+		obj = nft_obj_lookup(table, attr, objtype, genmask);
+	}
+
+	if (IS_ERR(obj)) {
+		NL_SET_BAD_ATTR(extack, attr);
 		return PTR_ERR(obj);
-	if (obj->use > 0)
+	}
+	if (obj->use > 0) {
+		NL_SET_BAD_ATTR(extack, attr);
 		return -EBUSY;
+	}
 
 	nft_ctx_init(&ctx, net, skb, nlh, family, table, NULL, nla);