Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git

/klassert/ipsec-next

Steffen Klassert says:

====================
pull request (net-next): ipsec-next 2021-06-28

1) Remove an unneeded error assignment in esp4_gro_receive().
   From Yang Li.

2) Add a new byseq state hashtable to find acquire states faster.
   From Sabrina Dubroca.

3) Remove some unnecessary variables in pfkey_create().
   From zuoqilin.

4) Remove the unused description from xfrm_type struct.
   From Florian Westphal.

5) Fix a spelling mistake in the comment of xfrm_state_ok().
   From gushengxian.

6) Replace hdr_off indirections by a small helper function.
   From Florian Westphal.

7) Remove xfrm4_output_finish and xfrm6_output_finish declarations,
   they are not used anymore.From Antony Antony.

8) Remove xfrm replay indirections.
   From Florian Westphal.

Please pull or let me know if there are problems.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

include/net/netns/xfrm.h

@@ -42,6 +42,7 @@ struct netns_xfrm {
 	struct hlist_head	__rcu *state_bydst;
 	struct hlist_head	__rcu *state_bysrc;
 	struct hlist_head	__rcu *state_byspi;
+	struct hlist_head	__rcu *state_byseq;
 	unsigned int		state_hmask;
 	unsigned int		state_num;
 	struct work_struct	state_hash_work;

include/net/xfrm.h

@@ -145,6 +145,12 @@ enum {
 	XFRM_MODE_FLAG_TUNNEL = 1,
 };
 
+enum xfrm_replay_mode {
+	XFRM_REPLAY_MODE_LEGACY,
+	XFRM_REPLAY_MODE_BMP,
+	XFRM_REPLAY_MODE_ESN,
+};
+
 /* Full description of state of transformer. */
 struct xfrm_state {
 	possible_net_t		xs_net;
@@ -154,6 +160,7 @@ struct xfrm_state {
 	};
 	struct hlist_node	bysrc;
 	struct hlist_node	byspi;
+	struct hlist_node	byseq;
 
 	refcount_t		refcnt;
 	spinlock_t		lock;
@@ -214,9 +221,8 @@ struct xfrm_state {
 	struct xfrm_replay_state preplay;
 	struct xfrm_replay_state_esn *preplay_esn;
 
-	/* The functions for replay detection. */
-	const struct xfrm_replay *repl;
-
+	/* replay detection mode */
+	enum xfrm_replay_mode    repl_mode;
 	/* internal flag that only holds state for delayed aevent at the
 	 * moment
 	*/
@@ -296,18 +302,6 @@ struct km_event {
 	struct net *net;
 };
 
-struct xfrm_replay {
-	void	(*advance)(struct xfrm_state *x, __be32 net_seq);
-	int	(*check)(struct xfrm_state *x,
-			 struct sk_buff *skb,
-			 __be32 net_seq);
-	int	(*recheck)(struct xfrm_state *x,
-			   struct sk_buff *skb,
-			   __be32 net_seq);
-	void	(*notify)(struct xfrm_state *x, int event);
-	int	(*overflow)(struct xfrm_state *x, struct sk_buff *skb);
-};
-
 struct xfrm_if_cb {
 	struct xfrm_if	*(*decode_session)(struct sk_buff *skb,
 					   unsigned short family);
@@ -387,7 +381,6 @@ void xfrm_flush_gc(void);
 void xfrm_state_delete_tunnel(struct xfrm_state *x);
 
 struct xfrm_type {
-	char			*description;
 	struct module		*owner;
 	u8			proto;
 	u8			flags;
@@ -402,14 +395,12 @@ struct xfrm_type {
 	int			(*output)(struct xfrm_state *, struct sk_buff *pskb);
 	int			(*reject)(struct xfrm_state *, struct sk_buff *,
 					  const struct flowi *);
-	int			(*hdr_offset)(struct xfrm_state *, struct sk_buff *, u8 **);
 };
 
 int xfrm_register_type(const struct xfrm_type *type, unsigned short family);
 void xfrm_unregister_type(const struct xfrm_type *type, unsigned short family);
 
 struct xfrm_type_offload {
-	char		*description;
 	struct module	*owner;
 	u8		proto;
 	void		(*encap)(struct xfrm_state *, struct sk_buff *pskb);
@@ -1582,7 +1573,6 @@ static inline int xfrm4_rcv_spi(struct sk_buff *skb, int nexthdr, __be32 spi)
 }
 
 int xfrm4_output(struct net *net, struct sock *sk, struct sk_buff *skb);
-int xfrm4_output_finish(struct sock *sk, struct sk_buff *skb);
 int xfrm4_protocol_register(struct xfrm4_protocol *handler, unsigned char protocol);
 int xfrm4_protocol_deregister(struct xfrm4_protocol *handler, unsigned char protocol);
 int xfrm4_tunnel_register(struct xfrm_tunnel *handler, unsigned short family);
@@ -1606,9 +1596,6 @@ int xfrm6_tunnel_deregister(struct xfrm6_tunnel *handler, unsigned short family)
 __be32 xfrm6_tunnel_alloc_spi(struct net *net, xfrm_address_t *saddr);
 __be32 xfrm6_tunnel_spi_lookup(struct net *net, const xfrm_address_t *saddr);
 int xfrm6_output(struct net *net, struct sock *sk, struct sk_buff *skb);
-int xfrm6_output_finish(struct sock *sk, struct sk_buff *skb);
-int xfrm6_find_1stfragopt(struct xfrm_state *x, struct sk_buff *skb,
-			  u8 **prevhdr);
 
 #ifdef CONFIG_XFRM
 void xfrm6_local_rxpmtu(struct sk_buff *skb, u32 mtu);
@@ -1722,6 +1709,12 @@ static inline int xfrm_policy_id2dir(u32 index)
 }
 
 #ifdef CONFIG_XFRM
+void xfrm_replay_advance(struct xfrm_state *x, __be32 net_seq);
+int xfrm_replay_check(struct xfrm_state *x, struct sk_buff *skb, __be32 net_seq);
+void xfrm_replay_notify(struct xfrm_state *x, int event);
+int xfrm_replay_overflow(struct xfrm_state *x, struct sk_buff *skb);
+int xfrm_replay_recheck(struct xfrm_state *x, struct sk_buff *skb, __be32 net_seq);
+
 static inline int xfrm_aevent_is_on(struct net *net)
 {
 	struct sock *nlsk;

net/ipv4/ah4.c

@@ -554,7 +554,6 @@ static int ah4_rcv_cb(struct sk_buff *skb, int err)
 
 static const struct xfrm_type ah_type =
 {
-	.description	= "AH4",
 	.owner		= THIS_MODULE,
 	.proto	     	= IPPROTO_AH,
 	.flags		= XFRM_TYPE_REPLAY_PROT,

net/ipv4/esp4.c

@@ -1198,7 +1198,6 @@ static int esp4_rcv_cb(struct sk_buff *skb, int err)
 
 static const struct xfrm_type esp_type =
 {
-	.description	= "ESP4",
 	.owner		= THIS_MODULE,
 	.proto	     	= IPPROTO_ESP,
 	.flags		= XFRM_TYPE_REPLAY_PROT,

net/ipv4/esp4_offload.c

@@ -33,12 +33,11 @@ static struct sk_buff *esp4_gro_receive(struct list_head *head,
 	struct xfrm_state *x;
 	__be32 seq;
 	__be32 spi;
-	int err;
 
 	if (!pskb_pull(skb, offset))
 		return NULL;
 
-	if ((err = xfrm_parse_spi(skb, IPPROTO_ESP, &spi, &seq)) != 0)
+	if (xfrm_parse_spi(skb, IPPROTO_ESP, &spi, &seq) != 0)
 		goto out;
 
 	xo = xfrm_offload(skb);
@@ -343,7 +342,6 @@ static const struct net_offload esp4_offload = {
 };
 
 static const struct xfrm_type_offload esp_type_offload = {
-	.description	= "ESP4 OFFLOAD",
 	.owner		= THIS_MODULE,
 	.proto	     	= IPPROTO_ESP,
 	.input_tail	= esp_input_tail,

net/ipv4/ipcomp.c

@@ -152,7 +152,6 @@ static int ipcomp4_rcv_cb(struct sk_buff *skb, int err)
 }
 
 static const struct xfrm_type ipcomp_type = {
-	.description	= "IPCOMP4",
 	.owner		= THIS_MODULE,
 	.proto	     	= IPPROTO_COMP,
 	.init_state	= ipcomp4_init_state,

net/ipv4/xfrm4_tunnel.c

@@ -42,7 +42,6 @@ static void ipip_destroy(struct xfrm_state *x)
 }
 
 static const struct xfrm_type ipip_type = {
-	.description	= "IPIP",
 	.owner		= THIS_MODULE,
 	.proto	     	= IPPROTO_IPIP,
 	.init_state	= ipip_init_state,

net/ipv6/ah6.c

@@ -755,7 +755,6 @@ static int ah6_rcv_cb(struct sk_buff *skb, int err)
 }
 
 static const struct xfrm_type ah6_type = {
-	.description	= "AH6",
 	.owner		= THIS_MODULE,
 	.proto		= IPPROTO_AH,
 	.flags		= XFRM_TYPE_REPLAY_PROT,
@@ -763,7 +762,6 @@ static const struct xfrm_type ah6_type = {
 	.destructor	= ah6_destroy,
 	.input		= ah6_input,
 	.output		= ah6_output,
-	.hdr_offset	= xfrm6_find_1stfragopt,
 };
 
 static struct xfrm6_protocol ah6_protocol = {

net/ipv6/esp6.c

@@ -1243,7 +1243,6 @@ static int esp6_rcv_cb(struct sk_buff *skb, int err)
 }
 
 static const struct xfrm_type esp6_type = {
-	.description	= "ESP6",
 	.owner		= THIS_MODULE,
 	.proto		= IPPROTO_ESP,
 	.flags		= XFRM_TYPE_REPLAY_PROT,
@@ -1251,7 +1250,6 @@ static const struct xfrm_type esp6_type = {
 	.destructor	= esp6_destroy,
 	.input		= esp6_input,
 	.output		= esp6_output,
-	.hdr_offset	= xfrm6_find_1stfragopt,
 };
 
 static struct xfrm6_protocol esp6_protocol = {

net/ipv6/esp6_offload.c

@@ -377,7 +377,6 @@ static const struct net_offload esp6_offload = {
 };
 
 static const struct xfrm_type_offload esp6_type_offload = {
-	.description	= "ESP6 OFFLOAD",
 	.owner		= THIS_MODULE,
 	.proto	     	= IPPROTO_ESP,
 	.input_tail	= esp6_input_tail,

net/ipv6/ipcomp6.c

@@ -172,14 +172,12 @@ static int ipcomp6_rcv_cb(struct sk_buff *skb, int err)
 }
 
 static const struct xfrm_type ipcomp6_type = {
-	.description	= "IPCOMP6",
 	.owner		= THIS_MODULE,
 	.proto		= IPPROTO_COMP,
 	.init_state	= ipcomp6_init_state,
 	.destructor	= ipcomp_destroy,
 	.input		= ipcomp_input,
 	.output		= ipcomp_output,
-	.hdr_offset	= xfrm6_find_1stfragopt,
 };
 
 static struct xfrm6_protocol ipcomp6_protocol = {

net/ipv6/mip6.c

@@ -247,54 +247,6 @@ static int mip6_destopt_reject(struct xfrm_state *x, struct sk_buff *skb,
 	return err;
 }
 
-static int mip6_destopt_offset(struct xfrm_state *x, struct sk_buff *skb,
-			       u8 **nexthdr)
-{
-	u16 offset = sizeof(struct ipv6hdr);
-	struct ipv6_opt_hdr *exthdr =
-				   (struct ipv6_opt_hdr *)(ipv6_hdr(skb) + 1);
-	const unsigned char *nh = skb_network_header(skb);
-	unsigned int packet_len = skb_tail_pointer(skb) -
-		skb_network_header(skb);
-	int found_rhdr = 0;
-
-	*nexthdr = &ipv6_hdr(skb)->nexthdr;
-
-	while (offset + 1 <= packet_len) {
-
-		switch (**nexthdr) {
-		case NEXTHDR_HOP:
-			break;
-		case NEXTHDR_ROUTING:
-			found_rhdr = 1;
-			break;
-		case NEXTHDR_DEST:
-			/*
-			 * HAO MUST NOT appear more than once.
-			 * XXX: It is better to try to find by the end of
-			 * XXX: packet if HAO exists.
-			 */
-			if (ipv6_find_tlv(skb, offset, IPV6_TLV_HAO) >= 0) {
-				net_dbg_ratelimited("mip6: hao exists already, override\n");
-				return offset;
-			}
-
-			if (found_rhdr)
-				return offset;
-
-			break;
-		default:
-			return offset;
-		}
-
-		offset += ipv6_optlen(exthdr);
-		*nexthdr = &exthdr->nexthdr;
-		exthdr = (struct ipv6_opt_hdr *)(nh + offset);
-	}
-
-	return offset;
-}
-
 static int mip6_destopt_init_state(struct xfrm_state *x)
 {
 	if (x->id.spi) {
@@ -324,7 +276,6 @@ static void mip6_destopt_destroy(struct xfrm_state *x)
 }
 
 static const struct xfrm_type mip6_destopt_type = {
-	.description	= "MIP6DESTOPT",
 	.owner		= THIS_MODULE,
 	.proto		= IPPROTO_DSTOPTS,
 	.flags		= XFRM_TYPE_NON_FRAGMENT | XFRM_TYPE_LOCAL_COADDR,
@@ -333,7 +284,6 @@ static const struct xfrm_type mip6_destopt_type = {
 	.input		= mip6_destopt_input,
 	.output		= mip6_destopt_output,
 	.reject		= mip6_destopt_reject,
-	.hdr_offset	= mip6_destopt_offset,
 };
 
 static int mip6_rthdr_input(struct xfrm_state *x, struct sk_buff *skb)
@@ -383,53 +333,6 @@ static int mip6_rthdr_output(struct xfrm_state *x, struct sk_buff *skb)
 	return 0;
 }
 
-static int mip6_rthdr_offset(struct xfrm_state *x, struct sk_buff *skb,
-			     u8 **nexthdr)
-{
-	u16 offset = sizeof(struct ipv6hdr);
-	struct ipv6_opt_hdr *exthdr =
-				   (struct ipv6_opt_hdr *)(ipv6_hdr(skb) + 1);
-	const unsigned char *nh = skb_network_header(skb);
-	unsigned int packet_len = skb_tail_pointer(skb) -
-		skb_network_header(skb);
-	int found_rhdr = 0;
-
-	*nexthdr = &ipv6_hdr(skb)->nexthdr;
-
-	while (offset + 1 <= packet_len) {
-
-		switch (**nexthdr) {
-		case NEXTHDR_HOP:
-			break;
-		case NEXTHDR_ROUTING:
-			if (offset + 3 <= packet_len) {
-				struct ipv6_rt_hdr *rt;
-				rt = (struct ipv6_rt_hdr *)(nh + offset);
-				if (rt->type != 0)
-					return offset;
-			}
-			found_rhdr = 1;
-			break;
-		case NEXTHDR_DEST:
-			if (ipv6_find_tlv(skb, offset, IPV6_TLV_HAO) >= 0)
-				return offset;
-
-			if (found_rhdr)
-				return offset;
-
-			break;
-		default:
-			return offset;
-		}
-
-		offset += ipv6_optlen(exthdr);
-		*nexthdr = &exthdr->nexthdr;
-		exthdr = (struct ipv6_opt_hdr *)(nh + offset);
-	}
-
-	return offset;
-}
-
 static int mip6_rthdr_init_state(struct xfrm_state *x)
 {
 	if (x->id.spi) {
@@ -456,7 +359,6 @@ static void mip6_rthdr_destroy(struct xfrm_state *x)
 }
 
 static const struct xfrm_type mip6_rthdr_type = {
-	.description	= "MIP6RT",
 	.owner		= THIS_MODULE,
 	.proto		= IPPROTO_ROUTING,
 	.flags		= XFRM_TYPE_NON_FRAGMENT | XFRM_TYPE_REMOTE_COADDR,
@@ -464,7 +366,6 @@ static const struct xfrm_type mip6_rthdr_type = {
 	.destructor	= mip6_rthdr_destroy,
 	.input		= mip6_rthdr_input,
 	.output		= mip6_rthdr_output,
-	.hdr_offset	= mip6_rthdr_offset,
 };
 
 static int __init mip6_init(void)

net/ipv6/xfrm6_output.c

@@ -16,13 +16,6 @@
 #include <net/ip6_route.h>
 #include <net/xfrm.h>
 
-int xfrm6_find_1stfragopt(struct xfrm_state *x, struct sk_buff *skb,
-			  u8 **prevhdr)
-{
-	return ip6_find_1stfragopt(skb, prevhdr);
-}
-EXPORT_SYMBOL(xfrm6_find_1stfragopt);
-
 void xfrm6_local_rxpmtu(struct sk_buff *skb, u32 mtu)
 {
 	struct flowi6 fl6;

net/ipv6/xfrm6_tunnel.c

@@ -291,7 +291,6 @@ static void xfrm6_tunnel_destroy(struct xfrm_state *x)
 }
 
 static const struct xfrm_type xfrm6_tunnel_type = {
-	.description	= "IP6IP6",
 	.owner          = THIS_MODULE,
 	.proto		= IPPROTO_IPV6,
 	.init_state	= xfrm6_tunnel_init_state,

net/key/af_key.c

@@ -141,7 +141,6 @@ static int pfkey_create(struct net *net, struct socket *sock, int protocol,
 	struct netns_pfkey *net_pfkey = net_generic(net, pfkey_net_id);
 	struct sock *sk;
 	struct pfkey_sock *pfk;
-	int err;
 
 	if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
 		return -EPERM;
@@ -150,10 +149,9 @@ static int pfkey_create(struct net *net, struct socket *sock, int protocol,
 	if (protocol != PF_KEY_V2)
 		return -EPROTONOSUPPORT;
 
-	err = -ENOMEM;
 	sk = sk_alloc(net, PF_KEY, GFP_KERNEL, &key_proto, kern);
 	if (sk == NULL)
-		goto out;
+		return -ENOMEM;
 
 	pfk = pfkey_sk(sk);
 	mutex_init(&pfk->dump_lock);
@@ -169,8 +167,6 @@ static int pfkey_create(struct net *net, struct socket *sock, int protocol,
 	pfkey_insert(sk);
 
 	return 0;
-out:
-	return err;
 }
 
 static int pfkey_release(struct socket *sock)

net/xfrm/xfrm_hash.h

@@ -131,6 +131,13 @@ __xfrm_spi_hash(const xfrm_address_t *daddr, __be32 spi, u8 proto,
 	return (h ^ (h >> 10) ^ (h >> 20)) & hmask;
 }
 
+static inline unsigned int
+__xfrm_seq_hash(u32 seq, unsigned int hmask)
+{
+	unsigned int h = seq;
+	return (h ^ (h >> 10) ^ (h >> 20)) & hmask;
+}
+
 static inline unsigned int __idx_hash(u32 index, unsigned int hmask)
 {
 	return (index ^ (index >> 8)) & hmask;

net/xfrm/xfrm_input.c

@@ -612,7 +612,7 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type)
 			goto drop_unlock;
 		}
 
-		if (x->repl->check(x, skb, seq)) {
+		if (xfrm_replay_check(x, skb, seq)) {
 			XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATESEQERROR);
 			goto drop_unlock;
 		}
@@ -660,12 +660,12 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type)
 		/* only the first xfrm gets the encap type */
 		encap_type = 0;
 
-		if (x->repl->recheck(x, skb, seq)) {
+		if (xfrm_replay_recheck(x, skb, seq)) {
 			XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATESEQERROR);
 			goto drop_unlock;
 		}
 
-		x->repl->advance(x, seq);
+		xfrm_replay_advance(x, seq);
 
 		x->curlft.bytes += skb->len;
 		x->curlft.packets++;

net/xfrm/xfrm_output.c

@@ -77,6 +77,83 @@ static int xfrm4_transport_output(struct xfrm_state *x, struct sk_buff *skb)
 	return 0;
 }
 
+#if IS_ENABLED(CONFIG_IPV6_MIP6)
+static int mip6_rthdr_offset(struct sk_buff *skb, u8 **nexthdr, int type)
+{
+	const unsigned char *nh = skb_network_header(skb);
+	unsigned int offset = sizeof(struct ipv6hdr);
+	unsigned int packet_len;
+	int found_rhdr = 0;
+
+	packet_len = skb_tail_pointer(skb) - nh;
+	*nexthdr = &ipv6_hdr(skb)->nexthdr;
+
+	while (offset <= packet_len) {
+		struct ipv6_opt_hdr *exthdr;
+
+		switch (**nexthdr) {
+		case NEXTHDR_HOP:
+			break;
+		case NEXTHDR_ROUTING:
+			if (type == IPPROTO_ROUTING && offset + 3 <= packet_len) {
+				struct ipv6_rt_hdr *rt;
+
+				rt = (struct ipv6_rt_hdr *)(nh + offset);
+				if (rt->type != 0)
+					return offset;
+			}
+			found_rhdr = 1;
+			break;
+		case NEXTHDR_DEST:
+			/* HAO MUST NOT appear more than once.
+			 * XXX: It is better to try to find by the end of
+			 * XXX: packet if HAO exists.
+			 */
+			if (ipv6_find_tlv(skb, offset, IPV6_TLV_HAO) >= 0) {
+				net_dbg_ratelimited("mip6: hao exists already, override\n");
+				return offset;
+			}
+
+			if (found_rhdr)
+				return offset;
+
+			break;
+		default:
+			return offset;
+		}
+
+		if (offset + sizeof(struct ipv6_opt_hdr) > packet_len)
+			return -EINVAL;
+
+		exthdr = (struct ipv6_opt_hdr *)(skb_network_header(skb) +
+						 offset);
+		offset += ipv6_optlen(exthdr);
+		if (offset > IPV6_MAXPLEN)
+			return -EINVAL;
+		*nexthdr = &exthdr->nexthdr;
+	}
+
+	return -EINVAL;
+}
+#endif
+
+#if IS_ENABLED(CONFIG_IPV6)
+static int xfrm6_hdr_offset(struct xfrm_state *x, struct sk_buff *skb, u8 **prevhdr)
+{
+	switch (x->type->proto) {
+#if IS_ENABLED(CONFIG_IPV6_MIP6)
+	case IPPROTO_DSTOPTS:
+	case IPPROTO_ROUTING:
+		return mip6_rthdr_offset(skb, prevhdr, x->type->proto);
+#endif
+	default:
+		break;
+	}
+
+	return ip6_find_1stfragopt(skb, prevhdr);
+}
+#endif
+
 /* Add encapsulation header.
  *
  * The IP header and mutable extension headers will be moved forward to make
@@ -92,7 +169,7 @@ static int xfrm6_transport_output(struct xfrm_state *x, struct sk_buff *skb)
 	iph = ipv6_hdr(skb);
 	skb_set_inner_transport_header(skb, skb_transport_offset(skb));
 
-	hdr_len = x->type->hdr_offset(x, skb, &prevhdr);
+	hdr_len = xfrm6_hdr_offset(x, skb, &prevhdr);
 	if (hdr_len < 0)
 		return hdr_len;
 	skb_set_mac_header(skb,
@@ -122,7 +199,7 @@ static int xfrm6_ro_output(struct xfrm_state *x, struct sk_buff *skb)
 
 	iph = ipv6_hdr(skb);
 
-	hdr_len = x->type->hdr_offset(x, skb, &prevhdr);
+	hdr_len = xfrm6_hdr_offset(x, skb, &prevhdr);
 	if (hdr_len < 0)
 		return hdr_len;
 	skb_set_mac_header(skb,
@@ -448,7 +525,7 @@ static int xfrm_output_one(struct sk_buff *skb, int err)
 			goto error;
 		}
 
-		err = x->repl->overflow(x, skb);
+		err = xfrm_replay_overflow(x, skb);
 		if (err) {
 			XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTSTATESEQERROR);
 			goto error;

net/xfrm/xfrm_policy.c

@@ -3247,7 +3247,7 @@ xfrm_state_ok(const struct xfrm_tmpl *tmpl, const struct xfrm_state *x,
 
 /*
  * 0 or more than 0 is returned when validation is succeeded (either bypass
- * because of optional transport mode, or next index of the mathced secpath
+ * because of optional transport mode, or next index of the matched secpath
  * state with the template.
  * -1 is returned when no matching template is found.
  * Otherwise "-2 - errored_index" is returned.

net/xfrm/xfrm_replay.c

@@ -34,8 +34,11 @@ u32 xfrm_replay_seqhi(struct xfrm_state *x, __be32 net_seq)
 	return seq_hi;
 }
 EXPORT_SYMBOL(xfrm_replay_seqhi);
-;
-static void xfrm_replay_notify(struct xfrm_state *x, int event)
+
+static void xfrm_replay_notify_bmp(struct xfrm_state *x, int event);
+static void xfrm_replay_notify_esn(struct xfrm_state *x, int event);
+
+void xfrm_replay_notify(struct xfrm_state *x, int event)
 {
 	struct km_event c;
 	/* we send notify messages in case
@@ -48,6 +51,17 @@ static void xfrm_replay_notify(struct xfrm_state *x, int event)
 	 *  The state structure must be locked!
 	 */
 
+	switch (x->repl_mode) {
+	case XFRM_REPLAY_MODE_LEGACY:
+		break;
+	case XFRM_REPLAY_MODE_BMP:
+		xfrm_replay_notify_bmp(x, event);
+		return;
+	case XFRM_REPLAY_MODE_ESN:
+		xfrm_replay_notify_esn(x, event);
+		return;
+	}
+
 	switch (event) {
 	case XFRM_REPLAY_UPDATE:
 		if (!x->replay_maxdiff ||
@@ -81,7 +95,7 @@ static void xfrm_replay_notify(struct xfrm_state *x, int event)
 		x->xflags &= ~XFRM_TIME_DEFER;
 }
 
-static int xfrm_replay_overflow(struct xfrm_state *x, struct sk_buff *skb)
+static int __xfrm_replay_overflow(struct xfrm_state *x, struct sk_buff *skb)
 {
 	int err = 0;
 	struct net *net = xs_net(x);
@@ -98,13 +112,13 @@ static int xfrm_replay_overflow(struct xfrm_state *x, struct sk_buff *skb)
 			return err;
 		}
 		if (xfrm_aevent_is_on(net))
-			x->repl->notify(x, XFRM_REPLAY_UPDATE);
+			xfrm_replay_notify(x, XFRM_REPLAY_UPDATE);
 	}
 
 	return err;
 }
 
-static int xfrm_replay_check(struct xfrm_state *x,
+static int xfrm_replay_check_legacy(struct xfrm_state *x,
 				    struct sk_buff *skb, __be32 net_seq)
 {
 	u32 diff;
@@ -136,14 +150,26 @@ static int xfrm_replay_check(struct xfrm_state *x,
 	return -EINVAL;
 }
 
-static void xfrm_replay_advance(struct xfrm_state *x, __be32 net_seq)
+static void xfrm_replay_advance_bmp(struct xfrm_state *x, __be32 net_seq);
+static void xfrm_replay_advance_esn(struct xfrm_state *x, __be32 net_seq);
+
+void xfrm_replay_advance(struct xfrm_state *x, __be32 net_seq)
 {
-	u32 diff;
-	u32 seq = ntohl(net_seq);
+	u32 diff, seq;
+
+	switch (x->repl_mode) {
+	case XFRM_REPLAY_MODE_LEGACY:
+		break;
+	case XFRM_REPLAY_MODE_BMP:
+		return xfrm_replay_advance_bmp(x, net_seq);
+	case XFRM_REPLAY_MODE_ESN:
+		return xfrm_replay_advance_esn(x, net_seq);
+	}
 
 	if (!x->props.replay_window)
 		return;
 
+	seq = ntohl(net_seq);
 	if (seq > x->replay.seq) {
 		diff = seq - x->replay.seq;
 		if (diff < x->props.replay_window)
@@ -157,7 +183,7 @@ static void xfrm_replay_advance(struct xfrm_state *x, __be32 net_seq)
 	}
 
 	if (xfrm_aevent_is_on(xs_net(x)))
-		x->repl->notify(x, XFRM_REPLAY_UPDATE);
+		xfrm_replay_notify(x, XFRM_REPLAY_UPDATE);
 }
 
 static int xfrm_replay_overflow_bmp(struct xfrm_state *x, struct sk_buff *skb)
@@ -178,7 +204,7 @@ static int xfrm_replay_overflow_bmp(struct xfrm_state *x, struct sk_buff *skb)
 			return err;
 		}
 		if (xfrm_aevent_is_on(net))
-			x->repl->notify(x, XFRM_REPLAY_UPDATE);
+			xfrm_replay_notify(x, XFRM_REPLAY_UPDATE);
 	}
 
 	return err;
@@ -273,7 +299,7 @@ static void xfrm_replay_advance_bmp(struct xfrm_state *x, __be32 net_seq)
 	replay_esn->bmp[nr] |= (1U << bitnr);
 
 	if (xfrm_aevent_is_on(xs_net(x)))
-		x->repl->notify(x, XFRM_REPLAY_UPDATE);
+		xfrm_replay_notify(x, XFRM_REPLAY_UPDATE);
 }
 
 static void xfrm_replay_notify_bmp(struct xfrm_state *x, int event)
@@ -416,7 +442,7 @@ static int xfrm_replay_overflow_esn(struct xfrm_state *x, struct sk_buff *skb)
 			}
 		}
 		if (xfrm_aevent_is_on(net))
-			x->repl->notify(x, XFRM_REPLAY_UPDATE);
+			xfrm_replay_notify(x, XFRM_REPLAY_UPDATE);
 	}
 
 	return err;
@@ -481,6 +507,21 @@ static int xfrm_replay_check_esn(struct xfrm_state *x,
 	return -EINVAL;
 }
 
+int xfrm_replay_check(struct xfrm_state *x,
+		      struct sk_buff *skb, __be32 net_seq)
+{
+	switch (x->repl_mode) {
+	case XFRM_REPLAY_MODE_LEGACY:
+		break;
+	case XFRM_REPLAY_MODE_BMP:
+		return xfrm_replay_check_bmp(x, skb, net_seq);
+	case XFRM_REPLAY_MODE_ESN:
+		return xfrm_replay_check_esn(x, skb, net_seq);
+	}
+
+	return xfrm_replay_check_legacy(x, skb, net_seq);
+}
+
 static int xfrm_replay_recheck_esn(struct xfrm_state *x,
 				   struct sk_buff *skb, __be32 net_seq)
 {
@@ -493,6 +534,22 @@ static int xfrm_replay_recheck_esn(struct xfrm_state *x,
 	return xfrm_replay_check_esn(x, skb, net_seq);
 }
 
+int xfrm_replay_recheck(struct xfrm_state *x,
+			struct sk_buff *skb, __be32 net_seq)
+{
+	switch (x->repl_mode) {
+	case XFRM_REPLAY_MODE_LEGACY:
+		break;
+	case XFRM_REPLAY_MODE_BMP:
+		/* no special recheck treatment */
+		return xfrm_replay_check_bmp(x, skb, net_seq);
+	case XFRM_REPLAY_MODE_ESN:
+		return xfrm_replay_recheck_esn(x, skb, net_seq);
+	}
+
+	return xfrm_replay_check_legacy(x, skb, net_seq);
+}
+
 static void xfrm_replay_advance_esn(struct xfrm_state *x, __be32 net_seq)
 {
 	unsigned int bitnr, nr, i;
@@ -548,7 +605,7 @@ static void xfrm_replay_advance_esn(struct xfrm_state *x, __be32 net_seq)
 	replay_esn->bmp[nr] |= (1U << bitnr);
 
 	if (xfrm_aevent_is_on(xs_net(x)))
-		x->repl->notify(x, XFRM_REPLAY_UPDATE);
+		xfrm_replay_notify(x, XFRM_REPLAY_UPDATE);
 }
 
 #ifdef CONFIG_XFRM_OFFLOAD
@@ -560,7 +617,7 @@ static int xfrm_replay_overflow_offload(struct xfrm_state *x, struct sk_buff *sk
 	__u32 oseq = x->replay.oseq;
 
 	if (!xo)
-		return xfrm_replay_overflow(x, skb);
+		return __xfrm_replay_overflow(x, skb);
 
 	if (x->type->flags & XFRM_TYPE_REPLAY_PROT) {
 		if (!skb_is_gso(skb)) {
@@ -585,7 +642,7 @@ static int xfrm_replay_overflow_offload(struct xfrm_state *x, struct sk_buff *sk
 		x->replay.oseq = oseq;
 
 		if (xfrm_aevent_is_on(net))
-			x->repl->notify(x, XFRM_REPLAY_UPDATE);
+			xfrm_replay_notify(x, XFRM_REPLAY_UPDATE);
 	}
 
 	return err;
@@ -625,7 +682,7 @@ static int xfrm_replay_overflow_offload_bmp(struct xfrm_state *x, struct sk_buff
 		}
 
 		if (xfrm_aevent_is_on(net))
-			x->repl->notify(x, XFRM_REPLAY_UPDATE);
+			xfrm_replay_notify(x, XFRM_REPLAY_UPDATE);
 	}
 
 	return err;
@@ -674,59 +731,39 @@ static int xfrm_replay_overflow_offload_esn(struct xfrm_state *x, struct sk_buff
 		replay_esn->oseq = oseq;
 
 		if (xfrm_aevent_is_on(net))
-			x->repl->notify(x, XFRM_REPLAY_UPDATE);
+			xfrm_replay_notify(x, XFRM_REPLAY_UPDATE);
 	}
 
 	return err;
 }
 
-static const struct xfrm_replay xfrm_replay_legacy = {
-	.advance	= xfrm_replay_advance,
-	.check		= xfrm_replay_check,
-	.recheck	= xfrm_replay_check,
-	.notify		= xfrm_replay_notify,
-	.overflow	= xfrm_replay_overflow_offload,
-};
-
-static const struct xfrm_replay xfrm_replay_bmp = {
-	.advance	= xfrm_replay_advance_bmp,
-	.check		= xfrm_replay_check_bmp,
-	.recheck	= xfrm_replay_check_bmp,
-	.notify		= xfrm_replay_notify_bmp,
-	.overflow	= xfrm_replay_overflow_offload_bmp,
-};
-
-static const struct xfrm_replay xfrm_replay_esn = {
-	.advance	= xfrm_replay_advance_esn,
-	.check		= xfrm_replay_check_esn,
-	.recheck	= xfrm_replay_recheck_esn,
-	.notify		= xfrm_replay_notify_esn,
-	.overflow	= xfrm_replay_overflow_offload_esn,
-};
+int xfrm_replay_overflow(struct xfrm_state *x, struct sk_buff *skb)
+{
+	switch (x->repl_mode) {
+	case XFRM_REPLAY_MODE_LEGACY:
+		break;
+	case XFRM_REPLAY_MODE_BMP:
+		return xfrm_replay_overflow_offload_bmp(x, skb);
+	case XFRM_REPLAY_MODE_ESN:
+		return xfrm_replay_overflow_offload_esn(x, skb);
+	}
+
+	return xfrm_replay_overflow_offload(x, skb);
+}
 #else
-static const struct xfrm_replay xfrm_replay_legacy = {
-	.advance	= xfrm_replay_advance,
-	.check		= xfrm_replay_check,
-	.recheck	= xfrm_replay_check,
-	.notify		= xfrm_replay_notify,
-	.overflow	= xfrm_replay_overflow,
-};
-
-static const struct xfrm_replay xfrm_replay_bmp = {
-	.advance	= xfrm_replay_advance_bmp,
-	.check		= xfrm_replay_check_bmp,
-	.recheck	= xfrm_replay_check_bmp,
-	.notify		= xfrm_replay_notify_bmp,
-	.overflow	= xfrm_replay_overflow_bmp,
-};
-
-static const struct xfrm_replay xfrm_replay_esn = {
-	.advance	= xfrm_replay_advance_esn,
-	.check		= xfrm_replay_check_esn,
-	.recheck	= xfrm_replay_recheck_esn,
-	.notify		= xfrm_replay_notify_esn,
-	.overflow	= xfrm_replay_overflow_esn,
-};
+int xfrm_replay_overflow(struct xfrm_state *x, struct sk_buff *skb)
+{
+	switch (x->repl_mode) {
+	case XFRM_REPLAY_MODE_LEGACY:
+		break;
+	case XFRM_REPLAY_MODE_BMP:
+		return xfrm_replay_overflow_bmp(x, skb);
+	case XFRM_REPLAY_MODE_ESN:
+		return xfrm_replay_overflow_esn(x, skb);
+	}
+
+	return __xfrm_replay_overflow(x, skb);
+}
 #endif
 
 int xfrm_init_replay(struct xfrm_state *x)
@@ -741,12 +778,12 @@ int xfrm_init_replay(struct xfrm_state *x)
 		if (x->props.flags & XFRM_STATE_ESN) {
 			if (replay_esn->replay_window == 0)
 				return -EINVAL;
-			x->repl = &xfrm_replay_esn;
+			x->repl_mode = XFRM_REPLAY_MODE_ESN;
 		} else {
-			x->repl = &xfrm_replay_bmp;
+			x->repl_mode = XFRM_REPLAY_MODE_BMP;
 		}
 	} else {
-		x->repl = &xfrm_replay_legacy;
+		x->repl_mode = XFRM_REPLAY_MODE_LEGACY;
 	}
 
 	return 0;

net/xfrm/xfrm_state.c

@@ -78,10 +78,16 @@ xfrm_spi_hash(struct net *net, const xfrm_address_t *daddr,
 	return __xfrm_spi_hash(daddr, spi, proto, family, net->xfrm.state_hmask);
 }
 
+static unsigned int xfrm_seq_hash(struct net *net, u32 seq)
+{
+	return __xfrm_seq_hash(seq, net->xfrm.state_hmask);
+}
+
 static void xfrm_hash_transfer(struct hlist_head *list,
 			       struct hlist_head *ndsttable,
 			       struct hlist_head *nsrctable,
 			       struct hlist_head *nspitable,
+			       struct hlist_head *nseqtable,
 			       unsigned int nhashmask)
 {
 	struct hlist_node *tmp;
@@ -106,6 +112,11 @@ static void xfrm_hash_transfer(struct hlist_head *list,
 					    nhashmask);
 			hlist_add_head_rcu(&x->byspi, nspitable + h);
 		}
+
+		if (x->km.seq) {
+			h = __xfrm_seq_hash(x->km.seq, nhashmask);
+			hlist_add_head_rcu(&x->byseq, nseqtable + h);
+		}
 	}
 }
 
@@ -117,7 +128,7 @@ static unsigned long xfrm_hash_new_size(unsigned int state_hmask)
 static void xfrm_hash_resize(struct work_struct *work)
 {
 	struct net *net = container_of(work, struct net, xfrm.state_hash_work);
-	struct hlist_head *ndst, *nsrc, *nspi, *odst, *osrc, *ospi;
+	struct hlist_head *ndst, *nsrc, *nspi, *nseq, *odst, *osrc, *ospi, *oseq;
 	unsigned long nsize, osize;
 	unsigned int nhashmask, ohashmask;
 	int i;
@@ -137,6 +148,13 @@ static void xfrm_hash_resize(struct work_struct *work)
 		xfrm_hash_free(nsrc, nsize);
 		return;
 	}
+	nseq = xfrm_hash_alloc(nsize);
+	if (!nseq) {
+		xfrm_hash_free(ndst, nsize);
+		xfrm_hash_free(nsrc, nsize);
+		xfrm_hash_free(nspi, nsize);
+		return;
+	}
 
 	spin_lock_bh(&net->xfrm.xfrm_state_lock);
 	write_seqcount_begin(&net->xfrm.xfrm_state_hash_generation);
@@ -144,15 +162,17 @@ static void xfrm_hash_resize(struct work_struct *work)
 	nhashmask = (nsize / sizeof(struct hlist_head)) - 1U;
 	odst = xfrm_state_deref_prot(net->xfrm.state_bydst, net);
 	for (i = net->xfrm.state_hmask; i >= 0; i--)
-		xfrm_hash_transfer(odst + i, ndst, nsrc, nspi, nhashmask);
+		xfrm_hash_transfer(odst + i, ndst, nsrc, nspi, nseq, nhashmask);
 
 	osrc = xfrm_state_deref_prot(net->xfrm.state_bysrc, net);
 	ospi = xfrm_state_deref_prot(net->xfrm.state_byspi, net);
+	oseq = xfrm_state_deref_prot(net->xfrm.state_byseq, net);
 	ohashmask = net->xfrm.state_hmask;
 
 	rcu_assign_pointer(net->xfrm.state_bydst, ndst);
 	rcu_assign_pointer(net->xfrm.state_bysrc, nsrc);
 	rcu_assign_pointer(net->xfrm.state_byspi, nspi);
+	rcu_assign_pointer(net->xfrm.state_byseq, nseq);
 	net->xfrm.state_hmask = nhashmask;
 
 	write_seqcount_end(&net->xfrm.xfrm_state_hash_generation);
@@ -165,6 +185,7 @@ static void xfrm_hash_resize(struct work_struct *work)
 	xfrm_hash_free(odst, osize);
 	xfrm_hash_free(osrc, osize);
 	xfrm_hash_free(ospi, osize);
+	xfrm_hash_free(oseq, osize);
 }
 
 static DEFINE_SPINLOCK(xfrm_state_afinfo_lock);
@@ -621,6 +642,7 @@ struct xfrm_state *xfrm_state_alloc(struct net *net)
 		INIT_HLIST_NODE(&x->bydst);
 		INIT_HLIST_NODE(&x->bysrc);
 		INIT_HLIST_NODE(&x->byspi);
+		INIT_HLIST_NODE(&x->byseq);
 		hrtimer_init(&x->mtimer, CLOCK_BOOTTIME, HRTIMER_MODE_ABS_SOFT);
 		x->mtimer.function = xfrm_timer_handler;
 		timer_setup(&x->rtimer, xfrm_replay_timer_handler, 0);
@@ -664,6 +686,8 @@ int __xfrm_state_delete(struct xfrm_state *x)
 		list_del(&x->km.all);
 		hlist_del_rcu(&x->bydst);
 		hlist_del_rcu(&x->bysrc);
+		if (x->km.seq)
+			hlist_del_rcu(&x->byseq);
 		if (x->id.spi)
 			hlist_del_rcu(&x->byspi);
 		net->xfrm.state_num--;
@@ -1148,6 +1172,10 @@ xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr,
 				h = xfrm_spi_hash(net, &x->id.daddr, x->id.spi, x->id.proto, encap_family);
 				hlist_add_head_rcu(&x->byspi, net->xfrm.state_byspi + h);
 			}
+			if (x->km.seq) {
+				h = xfrm_seq_hash(net, x->km.seq);
+				hlist_add_head_rcu(&x->byseq, net->xfrm.state_byseq + h);
+			}
 			x->lft.hard_add_expires_seconds = net->xfrm.sysctl_acq_expires;
 			hrtimer_start(&x->mtimer,
 				      ktime_set(net->xfrm.sysctl_acq_expires, 0),
@@ -1263,6 +1291,12 @@ static void __xfrm_state_insert(struct xfrm_state *x)
 		hlist_add_head_rcu(&x->byspi, net->xfrm.state_byspi + h);
 	}
 
+	if (x->km.seq) {
+		h = xfrm_seq_hash(net, x->km.seq);
+
+		hlist_add_head_rcu(&x->byseq, net->xfrm.state_byseq + h);
+	}
+
 	hrtimer_start(&x->mtimer, ktime_set(1, 0), HRTIMER_MODE_REL_SOFT);
 	if (x->replay_maxage)
 		mod_timer(&x->rtimer, jiffies + x->replay_maxage);
@@ -1932,12 +1966,10 @@ xfrm_state_sort(struct xfrm_state **dst, struct xfrm_state **src, int n,
 
 static struct xfrm_state *__xfrm_find_acq_byseq(struct net *net, u32 mark, u32 seq)
 {
-	int i;
-
-	for (i = 0; i <= net->xfrm.state_hmask; i++) {
+	unsigned int h = xfrm_seq_hash(net, seq);
 	struct xfrm_state *x;
 
-		hlist_for_each_entry(x, net->xfrm.state_bydst+i, bydst) {
+	hlist_for_each_entry_rcu(x, net->xfrm.state_byseq + h, byseq) {
 		if (x->km.seq == seq &&
 		    (mark & x->mark.m) == x->mark.v &&
 		    x->km.state == XFRM_STATE_ACQ) {
@@ -1945,7 +1977,7 @@ static struct xfrm_state *__xfrm_find_acq_byseq(struct net *net, u32 mark, u32 s
 			return x;
 		}
 	}
-	}
+
 	return NULL;
 }
 
@@ -2145,7 +2177,7 @@ static void xfrm_replay_timer_handler(struct timer_list *t)
 
 	if (x->km.state == XFRM_STATE_VALID) {
 		if (xfrm_aevent_is_on(xs_net(x)))
-			x->repl->notify(x, XFRM_REPLAY_TIMEOUT);
+			xfrm_replay_notify(x, XFRM_REPLAY_TIMEOUT);
 		else
 			x->xflags |= XFRM_TIME_DEFER;
 	}
@@ -2660,6 +2692,9 @@ int __net_init xfrm_state_init(struct net *net)
 	net->xfrm.state_byspi = xfrm_hash_alloc(sz);
 	if (!net->xfrm.state_byspi)
 		goto out_byspi;
+	net->xfrm.state_byseq = xfrm_hash_alloc(sz);
+	if (!net->xfrm.state_byseq)
+		goto out_byseq;
 	net->xfrm.state_hmask = ((sz / sizeof(struct hlist_head)) - 1);
 
 	net->xfrm.state_num = 0;
@@ -2669,6 +2704,8 @@ int __net_init xfrm_state_init(struct net *net)
 			       &net->xfrm.xfrm_state_lock);
 	return 0;
 
+out_byseq:
+	xfrm_hash_free(net->xfrm.state_byspi, sz);
 out_byspi:
 	xfrm_hash_free(net->xfrm.state_bysrc, sz);
 out_bysrc:
@@ -2688,6 +2725,8 @@ void xfrm_state_fini(struct net *net)
 	WARN_ON(!list_empty(&net->xfrm.state_all));
 
 	sz = (net->xfrm.state_hmask + 1) * sizeof(struct hlist_head);
+	WARN_ON(!hlist_empty(net->xfrm.state_byseq));
+	xfrm_hash_free(net->xfrm.state_byseq, sz);
 	WARN_ON(!hlist_empty(net->xfrm.state_byspi));
 	xfrm_hash_free(net->xfrm.state_byspi, sz);
 	WARN_ON(!hlist_empty(net->xfrm.state_bysrc));