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 2019-07-05

1) A lot of work to remove indirections from the xfrm code.
   From Florian Westphal.

2) Fix a WARN_ON with ipv6 that triggered because of a
   forgotten break statement. From Florian Westphal.

3)  Remove xfrmi_init_net, it is not needed.
    From Li RongQing.

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

include/net/xfrm.h

@@ -346,22 +346,19 @@ void km_state_expired(struct xfrm_state *x, int hard, u32 portid);
 int __xfrm_state_delete(struct xfrm_state *x);
 
 struct xfrm_state_afinfo {
-	unsigned int			family;
-	unsigned int			proto;
-	__be16				eth_proto;
-	struct module			*owner;
-	const struct xfrm_type		*type_map[IPPROTO_MAX];
-	const struct xfrm_type_offload	*type_offload_map[IPPROTO_MAX];
-
-	int			(*init_flags)(struct xfrm_state *x);
-	void			(*init_tempsel)(struct xfrm_selector *sel,
-						const struct flowi *fl);
-	void			(*init_temprop)(struct xfrm_state *x,
-						const struct xfrm_tmpl *tmpl,
-						const xfrm_address_t *daddr,
-						const xfrm_address_t *saddr);
-	int			(*tmpl_sort)(struct xfrm_tmpl **dst, struct xfrm_tmpl **src, int n);
-	int			(*state_sort)(struct xfrm_state **dst, struct xfrm_state **src, int n);
+	u8				family;
+	u8				proto;
+
+	const struct xfrm_type_offload *type_offload_esp;
+
+	const struct xfrm_type		*type_esp;
+	const struct xfrm_type		*type_ipip;
+	const struct xfrm_type		*type_ipip6;
+	const struct xfrm_type		*type_comp;
+	const struct xfrm_type		*type_ah;
+	const struct xfrm_type		*type_routing;
+	const struct xfrm_type		*type_dstopts;
+
 	int			(*output)(struct net *net, struct sock *sk, struct sk_buff *skb);
 	int			(*output_finish)(struct sock *sk, struct sk_buff *skb);
 	int			(*extract_input)(struct xfrm_state *x,
@@ -407,12 +404,10 @@ struct xfrm_type {
 	int			(*reject)(struct xfrm_state *, struct sk_buff *,
 					  const struct flowi *);
 	int			(*hdr_offset)(struct xfrm_state *, struct sk_buff *, u8 **);
-	/* Estimate maximal size of result of transformation of a dgram */
-	u32			(*get_mtu)(struct xfrm_state *, int size);
 };
 
 int xfrm_register_type(const struct xfrm_type *type, unsigned short family);
-int xfrm_unregister_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;
@@ -424,7 +419,7 @@ struct xfrm_type_offload {
 };
 
 int xfrm_register_type_offload(const struct xfrm_type_offload *type, unsigned short family);
-int xfrm_unregister_type_offload(const struct xfrm_type_offload *type, unsigned short family);
+void xfrm_unregister_type_offload(const struct xfrm_type_offload *type, unsigned short family);
 
 static inline int xfrm_af2proto(unsigned int family)
 {
@@ -1508,21 +1503,19 @@ struct xfrm_state *xfrm_state_lookup_byaddr(struct net *net, u32 mark,
 					    u8 proto,
 					    unsigned short family);
 #ifdef CONFIG_XFRM_SUB_POLICY
-int xfrm_tmpl_sort(struct xfrm_tmpl **dst, struct xfrm_tmpl **src, int n,
-		   unsigned short family, struct net *net);
-int xfrm_state_sort(struct xfrm_state **dst, struct xfrm_state **src, int n,
+void xfrm_tmpl_sort(struct xfrm_tmpl **dst, struct xfrm_tmpl **src, int n,
 		    unsigned short family);
+void xfrm_state_sort(struct xfrm_state **dst, struct xfrm_state **src, int n,
+		     unsigned short family);
 #else
-static inline int xfrm_tmpl_sort(struct xfrm_tmpl **dst, struct xfrm_tmpl **src,
-				 int n, unsigned short family, struct net *net)
+static inline void xfrm_tmpl_sort(struct xfrm_tmpl **d, struct xfrm_tmpl **s,
+				  int n, unsigned short family)
 {
-	return -ENOSYS;
 }
 
-static inline int xfrm_state_sort(struct xfrm_state **dst, struct xfrm_state **src,
-				  int n, unsigned short family)
+static inline void xfrm_state_sort(struct xfrm_state **d, struct xfrm_state **s,
+				   int n, unsigned short family)
 {
-	return -ENOSYS;
 }
 #endif
 
@@ -1551,7 +1544,7 @@ void xfrm_sad_getinfo(struct net *net, struct xfrmk_sadinfo *si);
 void xfrm_spd_getinfo(struct net *net, struct xfrmk_spdinfo *si);
 u32 xfrm_replay_seqhi(struct xfrm_state *x, __be32 net_seq);
 int xfrm_init_replay(struct xfrm_state *x);
-int xfrm_state_mtu(struct xfrm_state *x, int mtu);
+u32 xfrm_state_mtu(struct xfrm_state *x, int mtu);
 int __xfrm_init_state(struct xfrm_state *x, bool init_replay, bool offload);
 int xfrm_init_state(struct xfrm_state *x);
 int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type);

net/ipv4/ah4.c

@@ -590,8 +590,7 @@ static void __exit ah4_fini(void)
 {
 	if (xfrm4_protocol_deregister(&ah4_protocol, IPPROTO_AH) < 0)
 		pr_info("%s: can't remove protocol\n", __func__);
-	if (xfrm_unregister_type(&ah_type, AF_INET) < 0)
-		pr_info("%s: can't remove xfrm type\n", __func__);
+	xfrm_unregister_type(&ah_type, AF_INET);
 }
 
 module_init(ah4_init);

net/ipv4/esp4.c

@@ -33,8 +33,6 @@ struct esp_output_extra {
 
 #define ESP_SKB_CB(__skb) ((struct esp_skb_cb *)&((__skb)->cb[0]))
 
-static u32 esp4_get_mtu(struct xfrm_state *x, int mtu);
-
 /*
  * Allocate an AEAD request structure with extra space for SG and IV.
  *
@@ -506,7 +504,7 @@ static int esp_output(struct xfrm_state *x, struct sk_buff *skb)
 		struct xfrm_dst *dst = (struct xfrm_dst *)skb_dst(skb);
 		u32 padto;
 
-		padto = min(x->tfcpad, esp4_get_mtu(x, dst->child_mtu_cached));
+		padto = min(x->tfcpad, xfrm_state_mtu(x, dst->child_mtu_cached));
 		if (skb->len < padto)
 			esp.tfclen = padto - skb->len;
 	}
@@ -788,28 +786,6 @@ static int esp_input(struct xfrm_state *x, struct sk_buff *skb)
 	return err;
 }
 
-static u32 esp4_get_mtu(struct xfrm_state *x, int mtu)
-{
-	struct crypto_aead *aead = x->data;
-	u32 blksize = ALIGN(crypto_aead_blocksize(aead), 4);
-	unsigned int net_adj;
-
-	switch (x->props.mode) {
-	case XFRM_MODE_TRANSPORT:
-	case XFRM_MODE_BEET:
-		net_adj = sizeof(struct iphdr);
-		break;
-	case XFRM_MODE_TUNNEL:
-		net_adj = 0;
-		break;
-	default:
-		BUG();
-	}
-
-	return ((mtu - x->props.header_len - crypto_aead_authsize(aead) -
-		 net_adj) & ~(blksize - 1)) + net_adj - 2;
-}
-
 static int esp4_err(struct sk_buff *skb, u32 info)
 {
 	struct net *net = dev_net(skb->dev);
@@ -1035,7 +1011,6 @@ static const struct xfrm_type esp_type =
 	.flags		= XFRM_TYPE_REPLAY_PROT,
 	.init_state	= esp_init_state,
 	.destructor	= esp_destroy,
-	.get_mtu	= esp4_get_mtu,
 	.input		= esp_input,
 	.output		= esp_output,
 };
@@ -1066,8 +1041,7 @@ static void __exit esp4_fini(void)
 {
 	if (xfrm4_protocol_deregister(&esp4_protocol, IPPROTO_ESP) < 0)
 		pr_info("%s: can't remove protocol\n", __func__);
-	if (xfrm_unregister_type(&esp_type, AF_INET) < 0)
-		pr_info("%s: can't remove xfrm type\n", __func__);
+	xfrm_unregister_type(&esp_type, AF_INET);
 }
 
 module_init(esp4_init);

net/ipv4/esp4_offload.c

@@ -312,9 +312,7 @@ static int __init esp4_offload_init(void)
 
 static void __exit esp4_offload_exit(void)
 {
-	if (xfrm_unregister_type_offload(&esp_type_offload, AF_INET) < 0)
-		pr_info("%s: can't remove xfrm type offload\n", __func__);
-
+	xfrm_unregister_type_offload(&esp_type_offload, AF_INET);
 	inet_del_offload(&esp4_offload, IPPROTO_ESP);
 }
 

net/ipv4/ipcomp.c

@@ -186,8 +186,7 @@ static void __exit ipcomp4_fini(void)
 {
 	if (xfrm4_protocol_deregister(&ipcomp4_protocol, IPPROTO_COMP) < 0)
 		pr_info("%s: can't remove protocol\n", __func__);
-	if (xfrm_unregister_type(&ipcomp_type, AF_INET) < 0)
-		pr_info("%s: can't remove xfrm type\n", __func__);
+	xfrm_unregister_type(&ipcomp_type, AF_INET);
 }
 
 module_init(ipcomp4_init);

net/ipv4/xfrm4_state.c

@@ -15,46 +15,6 @@
 #include <linux/netfilter_ipv4.h>
 #include <linux/export.h>
 
-static int xfrm4_init_flags(struct xfrm_state *x)
-{
-	if (xs_net(x)->ipv4.sysctl_ip_no_pmtu_disc)
-		x->props.flags |= XFRM_STATE_NOPMTUDISC;
-	return 0;
-}
-
-static void
-__xfrm4_init_tempsel(struct xfrm_selector *sel, const struct flowi *fl)
-{
-	const struct flowi4 *fl4 = &fl->u.ip4;
-
-	sel->daddr.a4 = fl4->daddr;
-	sel->saddr.a4 = fl4->saddr;
-	sel->dport = xfrm_flowi_dport(fl, &fl4->uli);
-	sel->dport_mask = htons(0xffff);
-	sel->sport = xfrm_flowi_sport(fl, &fl4->uli);
-	sel->sport_mask = htons(0xffff);
-	sel->family = AF_INET;
-	sel->prefixlen_d = 32;
-	sel->prefixlen_s = 32;
-	sel->proto = fl4->flowi4_proto;
-	sel->ifindex = fl4->flowi4_oif;
-}
-
-static void
-xfrm4_init_temprop(struct xfrm_state *x, const struct xfrm_tmpl *tmpl,
-		   const xfrm_address_t *daddr, const xfrm_address_t *saddr)
-{
-	x->id = tmpl->id;
-	if (x->id.daddr.a4 == 0)
-		x->id.daddr.a4 = daddr->a4;
-	x->props.saddr = tmpl->saddr;
-	if (x->props.saddr.a4 == 0)
-		x->props.saddr.a4 = saddr->a4;
-	x->props.mode = tmpl->mode;
-	x->props.reqid = tmpl->reqid;
-	x->props.family = AF_INET;
-}
-
 int xfrm4_extract_header(struct sk_buff *skb)
 {
 	const struct iphdr *iph = ip_hdr(skb);
@@ -74,11 +34,6 @@ int xfrm4_extract_header(struct sk_buff *skb)
 static struct xfrm_state_afinfo xfrm4_state_afinfo = {
 	.family			= AF_INET,
 	.proto			= IPPROTO_IPIP,
-	.eth_proto		= htons(ETH_P_IP),
-	.owner			= THIS_MODULE,
-	.init_flags		= xfrm4_init_flags,
-	.init_tempsel		= __xfrm4_init_tempsel,
-	.init_temprop		= xfrm4_init_temprop,
 	.output			= xfrm4_output,
 	.output_finish		= xfrm4_output_finish,
 	.extract_input		= xfrm4_extract_input,

net/ipv4/xfrm4_tunnel.c

@@ -108,8 +108,7 @@ static void __exit ipip_fini(void)
 	if (xfrm4_tunnel_deregister(&xfrm_tunnel_handler, AF_INET))
 		pr_info("%s: can't remove xfrm handler for AF_INET\n",
 			__func__);
-	if (xfrm_unregister_type(&ipip_type, AF_INET) < 0)
-		pr_info("%s: can't remove xfrm type\n", __func__);
+	xfrm_unregister_type(&ipip_type, AF_INET);
 }
 
 module_init(ipip_init);

net/ipv6/ah6.c

@@ -793,9 +793,7 @@ static void __exit ah6_fini(void)
 	if (xfrm6_protocol_deregister(&ah6_protocol, IPPROTO_AH) < 0)
 		pr_info("%s: can't remove protocol\n", __func__);
 
-	if (xfrm_unregister_type(&ah6_type, AF_INET6) < 0)
-		pr_info("%s: can't remove xfrm type\n", __func__);
-
+	xfrm_unregister_type(&ah6_type, AF_INET6);
 }
 
 module_init(ah6_init);

net/ipv6/esp6.c

@@ -41,8 +41,6 @@ struct esp_skb_cb {
 
 #define ESP_SKB_CB(__skb) ((struct esp_skb_cb *)&((__skb)->cb[0]))
 
-static u32 esp6_get_mtu(struct xfrm_state *x, int mtu);
-
 /*
  * Allocate an AEAD request structure with extra space for SG and IV.
  *
@@ -447,7 +445,7 @@ static int esp6_output(struct xfrm_state *x, struct sk_buff *skb)
 		struct xfrm_dst *dst = (struct xfrm_dst *)skb_dst(skb);
 		u32 padto;
 
-		padto = min(x->tfcpad, esp6_get_mtu(x, dst->child_mtu_cached));
+		padto = min(x->tfcpad, xfrm_state_mtu(x, dst->child_mtu_cached));
 		if (skb->len < padto)
 			esp.tfclen = padto - skb->len;
 	}
@@ -687,21 +685,6 @@ static int esp6_input(struct xfrm_state *x, struct sk_buff *skb)
 	return ret;
 }
 
-static u32 esp6_get_mtu(struct xfrm_state *x, int mtu)
-{
-	struct crypto_aead *aead = x->data;
-	u32 blksize = ALIGN(crypto_aead_blocksize(aead), 4);
-	unsigned int net_adj;
-
-	if (x->props.mode != XFRM_MODE_TUNNEL)
-		net_adj = sizeof(struct ipv6hdr);
-	else
-		net_adj = 0;
-
-	return ((mtu - x->props.header_len - crypto_aead_authsize(aead) -
-		 net_adj) & ~(blksize - 1)) + net_adj - 2;
-}
-
 static int esp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 		    u8 type, u8 code, int offset, __be32 info)
 {
@@ -919,7 +902,6 @@ static const struct xfrm_type esp6_type = {
 	.flags		= XFRM_TYPE_REPLAY_PROT,
 	.init_state	= esp6_init_state,
 	.destructor	= esp6_destroy,
-	.get_mtu	= esp6_get_mtu,
 	.input		= esp6_input,
 	.output		= esp6_output,
 	.hdr_offset	= xfrm6_find_1stfragopt,
@@ -951,8 +933,7 @@ static void __exit esp6_fini(void)
 {
 	if (xfrm6_protocol_deregister(&esp6_protocol, IPPROTO_ESP) < 0)
 		pr_info("%s: can't remove protocol\n", __func__);
-	if (xfrm_unregister_type(&esp6_type, AF_INET6) < 0)
-		pr_info("%s: can't remove xfrm type\n", __func__);
+	xfrm_unregister_type(&esp6_type, AF_INET6);
 }
 
 module_init(esp6_init);

net/ipv6/esp6_offload.c

@@ -336,9 +336,7 @@ static int __init esp6_offload_init(void)
 
 static void __exit esp6_offload_exit(void)
 {
-	if (xfrm_unregister_type_offload(&esp6_type_offload, AF_INET6) < 0)
-		pr_info("%s: can't remove xfrm type offload\n", __func__);
-
+	xfrm_unregister_type_offload(&esp6_type_offload, AF_INET6);
 	inet6_del_offload(&esp6_offload, IPPROTO_ESP);
 }
 

net/ipv6/ipcomp6.c

@@ -206,8 +206,7 @@ static void __exit ipcomp6_fini(void)
 {
 	if (xfrm6_protocol_deregister(&ipcomp6_protocol, IPPROTO_COMP) < 0)
 		pr_info("%s: can't remove protocol\n", __func__);
-	if (xfrm_unregister_type(&ipcomp6_type, AF_INET6) < 0)
-		pr_info("%s: can't remove xfrm type\n", __func__);
+	xfrm_unregister_type(&ipcomp6_type, AF_INET6);
 }
 
 module_init(ipcomp6_init);

net/ipv6/mip6.c

@@ -499,10 +499,8 @@ static void __exit mip6_fini(void)
 {
 	if (rawv6_mh_filter_unregister(mip6_mh_filter) < 0)
 		pr_info("%s: can't remove rawv6 mh filter\n", __func__);
-	if (xfrm_unregister_type(&mip6_rthdr_type, AF_INET6) < 0)
-		pr_info("%s: can't remove xfrm type(rthdr)\n", __func__);
-	if (xfrm_unregister_type(&mip6_destopt_type, AF_INET6) < 0)
-		pr_info("%s: can't remove xfrm type(destopt)\n", __func__);
+	xfrm_unregister_type(&mip6_rthdr_type, AF_INET6);
+	xfrm_unregister_type(&mip6_destopt_type, AF_INET6);
 }
 
 module_init(mip6_init);

net/ipv6/xfrm6_state.c

@@ -21,137 +21,6 @@
 #include <net/ipv6.h>
 #include <net/addrconf.h>
 
-static void
-__xfrm6_init_tempsel(struct xfrm_selector *sel, const struct flowi *fl)
-{
-	const struct flowi6 *fl6 = &fl->u.ip6;
-
-	/* Initialize temporary selector matching only
-	 * to current session. */
-	*(struct in6_addr *)&sel->daddr = fl6->daddr;
-	*(struct in6_addr *)&sel->saddr = fl6->saddr;
-	sel->dport = xfrm_flowi_dport(fl, &fl6->uli);
-	sel->dport_mask = htons(0xffff);
-	sel->sport = xfrm_flowi_sport(fl, &fl6->uli);
-	sel->sport_mask = htons(0xffff);
-	sel->family = AF_INET6;
-	sel->prefixlen_d = 128;
-	sel->prefixlen_s = 128;
-	sel->proto = fl6->flowi6_proto;
-	sel->ifindex = fl6->flowi6_oif;
-}
-
-static void
-xfrm6_init_temprop(struct xfrm_state *x, const struct xfrm_tmpl *tmpl,
-		   const xfrm_address_t *daddr, const xfrm_address_t *saddr)
-{
-	x->id = tmpl->id;
-	if (ipv6_addr_any((struct in6_addr *)&x->id.daddr))
-		memcpy(&x->id.daddr, daddr, sizeof(x->sel.daddr));
-	memcpy(&x->props.saddr, &tmpl->saddr, sizeof(x->props.saddr));
-	if (ipv6_addr_any((struct in6_addr *)&x->props.saddr))
-		memcpy(&x->props.saddr, saddr, sizeof(x->props.saddr));
-	x->props.mode = tmpl->mode;
-	x->props.reqid = tmpl->reqid;
-	x->props.family = AF_INET6;
-}
-
-/* distribution counting sort function for xfrm_state and xfrm_tmpl */
-static int
-__xfrm6_sort(void **dst, void **src, int n, int (*cmp)(void *p), int maxclass)
-{
-	int count[XFRM_MAX_DEPTH] = { };
-	int class[XFRM_MAX_DEPTH];
-	int i;
-
-	for (i = 0; i < n; i++) {
-		int c;
-		class[i] = c = cmp(src[i]);
-		count[c]++;
-	}
-
-	for (i = 2; i < maxclass; i++)
-		count[i] += count[i - 1];
-
-	for (i = 0; i < n; i++) {
-		dst[count[class[i] - 1]++] = src[i];
-		src[i] = NULL;
-	}
-
-	return 0;
-}
-
-/*
- * Rule for xfrm_state:
- *
- * rule 1: select IPsec transport except AH
- * rule 2: select MIPv6 RO or inbound trigger
- * rule 3: select IPsec transport AH
- * rule 4: select IPsec tunnel
- * rule 5: others
- */
-static int __xfrm6_state_sort_cmp(void *p)
-{
-	struct xfrm_state *v = p;
-
-	switch (v->props.mode) {
-	case XFRM_MODE_TRANSPORT:
-		if (v->id.proto != IPPROTO_AH)
-			return 1;
-		else
-			return 3;
-#if IS_ENABLED(CONFIG_IPV6_MIP6)
-	case XFRM_MODE_ROUTEOPTIMIZATION:
-	case XFRM_MODE_IN_TRIGGER:
-		return 2;
-#endif
-	case XFRM_MODE_TUNNEL:
-	case XFRM_MODE_BEET:
-		return 4;
-	}
-	return 5;
-}
-
-static int
-__xfrm6_state_sort(struct xfrm_state **dst, struct xfrm_state **src, int n)
-{
-	return __xfrm6_sort((void **)dst, (void **)src, n,
-			    __xfrm6_state_sort_cmp, 6);
-}
-
-/*
- * Rule for xfrm_tmpl:
- *
- * rule 1: select IPsec transport
- * rule 2: select MIPv6 RO or inbound trigger
- * rule 3: select IPsec tunnel
- * rule 4: others
- */
-static int __xfrm6_tmpl_sort_cmp(void *p)
-{
-	struct xfrm_tmpl *v = p;
-	switch (v->mode) {
-	case XFRM_MODE_TRANSPORT:
-		return 1;
-#if IS_ENABLED(CONFIG_IPV6_MIP6)
-	case XFRM_MODE_ROUTEOPTIMIZATION:
-	case XFRM_MODE_IN_TRIGGER:
-		return 2;
-#endif
-	case XFRM_MODE_TUNNEL:
-	case XFRM_MODE_BEET:
-		return 3;
-	}
-	return 4;
-}
-
-static int
-__xfrm6_tmpl_sort(struct xfrm_tmpl **dst, struct xfrm_tmpl **src, int n)
-{
-	return __xfrm6_sort((void **)dst, (void **)src, n,
-			    __xfrm6_tmpl_sort_cmp, 5);
-}
-
 int xfrm6_extract_header(struct sk_buff *skb)
 {
 	struct ipv6hdr *iph = ipv6_hdr(skb);
@@ -171,12 +40,6 @@ int xfrm6_extract_header(struct sk_buff *skb)
 static struct xfrm_state_afinfo xfrm6_state_afinfo = {
 	.family			= AF_INET6,
 	.proto			= IPPROTO_IPV6,
-	.eth_proto		= htons(ETH_P_IPV6),
-	.owner			= THIS_MODULE,
-	.init_tempsel		= __xfrm6_init_tempsel,
-	.init_temprop		= xfrm6_init_temprop,
-	.tmpl_sort		= __xfrm6_tmpl_sort,
-	.state_sort		= __xfrm6_state_sort,
 	.output			= xfrm6_output,
 	.output_finish		= xfrm6_output_finish,
 	.extract_input		= xfrm6_extract_input,

net/xfrm/xfrm_device.c

@@ -271,9 +271,8 @@ bool xfrm_dev_offload_ok(struct sk_buff *skb, struct xfrm_state *x)
 		return false;
 
 	if ((!dev || (dev == xfrm_dst_path(dst)->dev)) &&
-	    (!xdst->child->xfrm && x->type->get_mtu)) {
-		mtu = x->type->get_mtu(x, xdst->child_mtu_cached);
-
+	    (!xdst->child->xfrm)) {
+		mtu = xfrm_state_mtu(x, xdst->child_mtu_cached);
 		if (skb->len <= mtu)
 			goto ok;
 

net/xfrm/xfrm_input.c

@@ -359,28 +359,29 @@ static int xfrm_prepare_input(struct xfrm_state *x, struct sk_buff *skb)
 	afinfo = xfrm_state_afinfo_get_rcu(x->outer_mode.family);
 	if (likely(afinfo))
 		err = afinfo->extract_input(x, skb);
+	rcu_read_unlock();
 
-	if (err) {
-		rcu_read_unlock();
+	if (err)
 		return err;
-	}
 
 	if (x->sel.family == AF_UNSPEC) {
 		inner_mode = xfrm_ip2inner_mode(x, XFRM_MODE_SKB_CB(skb)->protocol);
-		if (!inner_mode) {
-			rcu_read_unlock();
+		if (!inner_mode)
 			return -EAFNOSUPPORT;
-		}
 	}
 
-	afinfo = xfrm_state_afinfo_get_rcu(inner_mode->family);
-	if (unlikely(!afinfo)) {
-		rcu_read_unlock();
-		return -EAFNOSUPPORT;
+	switch (inner_mode->family) {
+	case AF_INET:
+		skb->protocol = htons(ETH_P_IP);
+		break;
+	case AF_INET6:
+		skb->protocol = htons(ETH_P_IPV6);
+		break;
+	default:
+		WARN_ON_ONCE(1);
+		break;
 	}
 
-	skb->protocol = afinfo->eth_proto;
-	rcu_read_unlock();
 	return xfrm_inner_mode_encap_remove(x, inner_mode, skb);
 }
 

net/xfrm/xfrm_interface.c

@@ -793,11 +793,6 @@ static void __net_exit xfrmi_destroy_interfaces(struct xfrmi_net *xfrmn)
 	unregister_netdevice_many(&list);
 }
 
-static int __net_init xfrmi_init_net(struct net *net)
-{
-	return 0;
-}
-
 static void __net_exit xfrmi_exit_net(struct net *net)
 {
 	struct xfrmi_net *xfrmn = net_generic(net, xfrmi_net_id);
@@ -808,7 +803,6 @@ static void __net_exit xfrmi_exit_net(struct net *net)
 }
 
 static struct pernet_operations xfrmi_net_ops = {
-	.init = xfrmi_init_net,
 	.exit = xfrmi_exit_net,
 	.id   = &xfrmi_net_id,
 	.size = sizeof(struct xfrmi_net),

net/xfrm/xfrm_policy.c

@@ -3628,7 +3628,7 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb,
 		}
 		xfrm_nr = ti;
 		if (npols > 1) {
-			xfrm_tmpl_sort(stp, tpp, xfrm_nr, family, net);
+			xfrm_tmpl_sort(stp, tpp, xfrm_nr, family);
 			tpp = stp;
 		}
 

net/xfrm/xfrm_state.c

@@ -27,6 +27,8 @@
 #include <linux/interrupt.h>
 #include <linux/kernel.h>
 
+#include <crypto/aead.h>
+
 #include "xfrm_hash.h"
 
 #define xfrm_state_deref_prot(table, net) \
@@ -177,63 +179,132 @@ int km_query(struct xfrm_state *x, struct xfrm_tmpl *t, struct xfrm_policy *pol)
 static bool km_is_alive(const struct km_event *c);
 void km_state_expired(struct xfrm_state *x, int hard, u32 portid);
 
-static DEFINE_SPINLOCK(xfrm_type_lock);
 int xfrm_register_type(const struct xfrm_type *type, unsigned short family)
 {
 	struct xfrm_state_afinfo *afinfo = xfrm_state_get_afinfo(family);
-	const struct xfrm_type **typemap;
 	int err = 0;
 
-	if (unlikely(afinfo == NULL))
+	if (!afinfo)
 		return -EAFNOSUPPORT;
-	typemap = afinfo->type_map;
-	spin_lock_bh(&xfrm_type_lock);
 
-	if (likely(typemap[type->proto] == NULL))
-		typemap[type->proto] = type;
-	else
-		err = -EEXIST;
-	spin_unlock_bh(&xfrm_type_lock);
+#define X(afi, T, name) do {			\
+		WARN_ON((afi)->type_ ## name);	\
+		(afi)->type_ ## name = (T);	\
+	} while (0)
+
+	switch (type->proto) {
+	case IPPROTO_COMP:
+		X(afinfo, type, comp);
+		break;
+	case IPPROTO_AH:
+		X(afinfo, type, ah);
+		break;
+	case IPPROTO_ESP:
+		X(afinfo, type, esp);
+		break;
+	case IPPROTO_IPIP:
+		X(afinfo, type, ipip);
+		break;
+	case IPPROTO_DSTOPTS:
+		X(afinfo, type, dstopts);
+		break;
+	case IPPROTO_ROUTING:
+		X(afinfo, type, routing);
+		break;
+	case IPPROTO_IPV6:
+		X(afinfo, type, ipip6);
+		break;
+	default:
+		WARN_ON(1);
+		err = -EPROTONOSUPPORT;
+		break;
+	}
+#undef X
 	rcu_read_unlock();
 	return err;
 }
 EXPORT_SYMBOL(xfrm_register_type);
 
-int xfrm_unregister_type(const struct xfrm_type *type, unsigned short family)
+void xfrm_unregister_type(const struct xfrm_type *type, unsigned short family)
 {
 	struct xfrm_state_afinfo *afinfo = xfrm_state_get_afinfo(family);
-	const struct xfrm_type **typemap;
-	int err = 0;
 
 	if (unlikely(afinfo == NULL))
-		return -EAFNOSUPPORT;
-	typemap = afinfo->type_map;
-	spin_lock_bh(&xfrm_type_lock);
+		return;
 
-	if (unlikely(typemap[type->proto] != type))
-		err = -ENOENT;
-	else
-		typemap[type->proto] = NULL;
-	spin_unlock_bh(&xfrm_type_lock);
+#define X(afi, T, name) do {				\
+		WARN_ON((afi)->type_ ## name != (T));	\
+		(afi)->type_ ## name = NULL;		\
+	} while (0)
+
+	switch (type->proto) {
+	case IPPROTO_COMP:
+		X(afinfo, type, comp);
+		break;
+	case IPPROTO_AH:
+		X(afinfo, type, ah);
+		break;
+	case IPPROTO_ESP:
+		X(afinfo, type, esp);
+		break;
+	case IPPROTO_IPIP:
+		X(afinfo, type, ipip);
+		break;
+	case IPPROTO_DSTOPTS:
+		X(afinfo, type, dstopts);
+		break;
+	case IPPROTO_ROUTING:
+		X(afinfo, type, routing);
+		break;
+	case IPPROTO_IPV6:
+		X(afinfo, type, ipip6);
+		break;
+	default:
+		WARN_ON(1);
+		break;
+	}
+#undef X
 	rcu_read_unlock();
-	return err;
 }
 EXPORT_SYMBOL(xfrm_unregister_type);
 
 static const struct xfrm_type *xfrm_get_type(u8 proto, unsigned short family)
 {
+	const struct xfrm_type *type = NULL;
 	struct xfrm_state_afinfo *afinfo;
-	const struct xfrm_type **typemap;
-	const struct xfrm_type *type;
 	int modload_attempted = 0;
 
 retry:
 	afinfo = xfrm_state_get_afinfo(family);
 	if (unlikely(afinfo == NULL))
 		return NULL;
-	typemap = afinfo->type_map;
 
-	type = READ_ONCE(typemap[proto]);
+	switch (proto) {
+	case IPPROTO_COMP:
+		type = afinfo->type_comp;
+		break;
+	case IPPROTO_AH:
+		type = afinfo->type_ah;
+		break;
+	case IPPROTO_ESP:
+		type = afinfo->type_esp;
+		break;
+	case IPPROTO_IPIP:
+		type = afinfo->type_ipip;
+		break;
+	case IPPROTO_DSTOPTS:
+		type = afinfo->type_dstopts;
+		break;
+	case IPPROTO_ROUTING:
+		type = afinfo->type_routing;
+		break;
+	case IPPROTO_IPV6:
+		type = afinfo->type_ipip6;
+		break;
+	default:
+		break;
+	}
+
 	if (unlikely(type && !try_module_get(type->owner)))
 		type = NULL;
 
@@ -253,65 +324,71 @@ static void xfrm_put_type(const struct xfrm_type *type)
 	module_put(type->owner);
 }
 
-static DEFINE_SPINLOCK(xfrm_type_offload_lock);
 int xfrm_register_type_offload(const struct xfrm_type_offload *type,
 			       unsigned short family)
 {
 	struct xfrm_state_afinfo *afinfo = xfrm_state_get_afinfo(family);
-	const struct xfrm_type_offload **typemap;
 	int err = 0;
 
 	if (unlikely(afinfo == NULL))
 		return -EAFNOSUPPORT;
-	typemap = afinfo->type_offload_map;
-	spin_lock_bh(&xfrm_type_offload_lock);
 
-	if (likely(typemap[type->proto] == NULL))
-		typemap[type->proto] = type;
-	else
-		err = -EEXIST;
-	spin_unlock_bh(&xfrm_type_offload_lock);
+	switch (type->proto) {
+	case IPPROTO_ESP:
+		WARN_ON(afinfo->type_offload_esp);
+		afinfo->type_offload_esp = type;
+		break;
+	default:
+		WARN_ON(1);
+		err = -EPROTONOSUPPORT;
+		break;
+	}
+
 	rcu_read_unlock();
 	return err;
 }
 EXPORT_SYMBOL(xfrm_register_type_offload);
 
-int xfrm_unregister_type_offload(const struct xfrm_type_offload *type,
-				 unsigned short family)
+void xfrm_unregister_type_offload(const struct xfrm_type_offload *type,
+				  unsigned short family)
 {
 	struct xfrm_state_afinfo *afinfo = xfrm_state_get_afinfo(family);
-	const struct xfrm_type_offload **typemap;
-	int err = 0;
 
 	if (unlikely(afinfo == NULL))
-		return -EAFNOSUPPORT;
-	typemap = afinfo->type_offload_map;
-	spin_lock_bh(&xfrm_type_offload_lock);
+		return;
 
-	if (unlikely(typemap[type->proto] != type))
-		err = -ENOENT;
-	else
-		typemap[type->proto] = NULL;
-	spin_unlock_bh(&xfrm_type_offload_lock);
+	switch (type->proto) {
+	case IPPROTO_ESP:
+		WARN_ON(afinfo->type_offload_esp != type);
+		afinfo->type_offload_esp = NULL;
+		break;
+	default:
+		WARN_ON(1);
+		break;
+	}
 	rcu_read_unlock();
-	return err;
 }
 EXPORT_SYMBOL(xfrm_unregister_type_offload);
 
 static const struct xfrm_type_offload *
 xfrm_get_type_offload(u8 proto, unsigned short family, bool try_load)
 {
+	const struct xfrm_type_offload *type = NULL;
 	struct xfrm_state_afinfo *afinfo;
-	const struct xfrm_type_offload **typemap;
-	const struct xfrm_type_offload *type;
 
 retry:
 	afinfo = xfrm_state_get_afinfo(family);
 	if (unlikely(afinfo == NULL))
 		return NULL;
-	typemap = afinfo->type_offload_map;
 
-	type = typemap[proto];
+	switch (proto) {
+	case IPPROTO_ESP:
+		type = afinfo->type_offload_esp;
+		break;
+	default:
+		break;
+	}
+
 	if ((type && !try_module_get(type->owner)))
 		type = NULL;
 
@@ -769,25 +846,80 @@ void xfrm_sad_getinfo(struct net *net, struct xfrmk_sadinfo *si)
 }
 EXPORT_SYMBOL(xfrm_sad_getinfo);
 
+static void
+__xfrm4_init_tempsel(struct xfrm_selector *sel, const struct flowi *fl)
+{
+	const struct flowi4 *fl4 = &fl->u.ip4;
+
+	sel->daddr.a4 = fl4->daddr;
+	sel->saddr.a4 = fl4->saddr;
+	sel->dport = xfrm_flowi_dport(fl, &fl4->uli);
+	sel->dport_mask = htons(0xffff);
+	sel->sport = xfrm_flowi_sport(fl, &fl4->uli);
+	sel->sport_mask = htons(0xffff);
+	sel->family = AF_INET;
+	sel->prefixlen_d = 32;
+	sel->prefixlen_s = 32;
+	sel->proto = fl4->flowi4_proto;
+	sel->ifindex = fl4->flowi4_oif;
+}
+
+static void
+__xfrm6_init_tempsel(struct xfrm_selector *sel, const struct flowi *fl)
+{
+	const struct flowi6 *fl6 = &fl->u.ip6;
+
+	/* Initialize temporary selector matching only to current session. */
+	*(struct in6_addr *)&sel->daddr = fl6->daddr;
+	*(struct in6_addr *)&sel->saddr = fl6->saddr;
+	sel->dport = xfrm_flowi_dport(fl, &fl6->uli);
+	sel->dport_mask = htons(0xffff);
+	sel->sport = xfrm_flowi_sport(fl, &fl6->uli);
+	sel->sport_mask = htons(0xffff);
+	sel->family = AF_INET6;
+	sel->prefixlen_d = 128;
+	sel->prefixlen_s = 128;
+	sel->proto = fl6->flowi6_proto;
+	sel->ifindex = fl6->flowi6_oif;
+}
+
 static void
 xfrm_init_tempstate(struct xfrm_state *x, const struct flowi *fl,
 		    const struct xfrm_tmpl *tmpl,
 		    const xfrm_address_t *daddr, const xfrm_address_t *saddr,
 		    unsigned short family)
 {
-	struct xfrm_state_afinfo *afinfo = xfrm_state_afinfo_get_rcu(family);
-
-	if (!afinfo)
-		return;
+	switch (family) {
+	case AF_INET:
+		__xfrm4_init_tempsel(&x->sel, fl);
+		break;
+	case AF_INET6:
+		__xfrm6_init_tempsel(&x->sel, fl);
+		break;
+	}
 
-	afinfo->init_tempsel(&x->sel, fl);
+	x->id = tmpl->id;
 
-	if (family != tmpl->encap_family) {
-		afinfo = xfrm_state_afinfo_get_rcu(tmpl->encap_family);
-		if (!afinfo)
-			return;
+	switch (tmpl->encap_family) {
+	case AF_INET:
+		if (x->id.daddr.a4 == 0)
+			x->id.daddr.a4 = daddr->a4;
+		x->props.saddr = tmpl->saddr;
+		if (x->props.saddr.a4 == 0)
+			x->props.saddr.a4 = saddr->a4;
+		break;
+	case AF_INET6:
+		if (ipv6_addr_any((struct in6_addr *)&x->id.daddr))
+			memcpy(&x->id.daddr, daddr, sizeof(x->sel.daddr));
+		memcpy(&x->props.saddr, &tmpl->saddr, sizeof(x->props.saddr));
+		if (ipv6_addr_any((struct in6_addr *)&x->props.saddr))
+			memcpy(&x->props.saddr, saddr, sizeof(x->props.saddr));
+		break;
 	}
-	afinfo->init_temprop(x, tmpl, daddr, saddr);
+
+	x->props.mode = tmpl->mode;
+	x->props.reqid = tmpl->reqid;
+	x->props.family = tmpl->encap_family;
 }
 
 static struct xfrm_state *__xfrm_state_lookup(struct net *net, u32 mark,
@@ -1633,51 +1765,129 @@ xfrm_find_acq(struct net *net, const struct xfrm_mark *mark, u8 mode, u32 reqid,
 EXPORT_SYMBOL(xfrm_find_acq);
 
 #ifdef CONFIG_XFRM_SUB_POLICY
-int
+#if IS_ENABLED(CONFIG_IPV6)
+/* distribution counting sort function for xfrm_state and xfrm_tmpl */
+static void
+__xfrm6_sort(void **dst, void **src, int n,
+	     int (*cmp)(const void *p), int maxclass)
+{
+	int count[XFRM_MAX_DEPTH] = { };
+	int class[XFRM_MAX_DEPTH];
+	int i;
+
+	for (i = 0; i < n; i++) {
+		int c = cmp(src[i]);
+
+		class[i] = c;
+		count[c]++;
+	}
+
+	for (i = 2; i < maxclass; i++)
+		count[i] += count[i - 1];
+
+	for (i = 0; i < n; i++) {
+		dst[count[class[i] - 1]++] = src[i];
+		src[i] = NULL;
+	}
+}
+
+/* Rule for xfrm_state:
+ *
+ * rule 1: select IPsec transport except AH
+ * rule 2: select MIPv6 RO or inbound trigger
+ * rule 3: select IPsec transport AH
+ * rule 4: select IPsec tunnel
+ * rule 5: others
+ */
+static int __xfrm6_state_sort_cmp(const void *p)
+{
+	const struct xfrm_state *v = p;
+
+	switch (v->props.mode) {
+	case XFRM_MODE_TRANSPORT:
+		if (v->id.proto != IPPROTO_AH)
+			return 1;
+		else
+			return 3;
+#if IS_ENABLED(CONFIG_IPV6_MIP6)
+	case XFRM_MODE_ROUTEOPTIMIZATION:
+	case XFRM_MODE_IN_TRIGGER:
+		return 2;
+#endif
+	case XFRM_MODE_TUNNEL:
+	case XFRM_MODE_BEET:
+		return 4;
+	}
+	return 5;
+}
+
+/* Rule for xfrm_tmpl:
+ *
+ * rule 1: select IPsec transport
+ * rule 2: select MIPv6 RO or inbound trigger
+ * rule 3: select IPsec tunnel
+ * rule 4: others
+ */
+static int __xfrm6_tmpl_sort_cmp(const void *p)
+{
+	const struct xfrm_tmpl *v = p;
+
+	switch (v->mode) {
+	case XFRM_MODE_TRANSPORT:
+		return 1;
+#if IS_ENABLED(CONFIG_IPV6_MIP6)
+	case XFRM_MODE_ROUTEOPTIMIZATION:
+	case XFRM_MODE_IN_TRIGGER:
+		return 2;
+#endif
+	case XFRM_MODE_TUNNEL:
+	case XFRM_MODE_BEET:
+		return 3;
+	}
+	return 4;
+}
+#else
+static inline int __xfrm6_state_sort_cmp(const void *p) { return 5; }
+static inline int __xfrm6_tmpl_sort_cmp(const void *p) { return 4; }
+
+static inline void
+__xfrm6_sort(void **dst, void **src, int n,
+	     int (*cmp)(const void *p), int maxclass)
+{
+	int i;
+
+	for (i = 0; i < n; i++)
+		dst[i] = src[i];
+}
+#endif /* CONFIG_IPV6 */
+
+void
 xfrm_tmpl_sort(struct xfrm_tmpl **dst, struct xfrm_tmpl **src, int n,
-	       unsigned short family, struct net *net)
+	       unsigned short family)
 {
 	int i;
-	int err = 0;
-	struct xfrm_state_afinfo *afinfo = xfrm_state_get_afinfo(family);
-	if (!afinfo)
-		return -EAFNOSUPPORT;
 
-	spin_lock_bh(&net->xfrm.xfrm_state_lock); /*FIXME*/
-	if (afinfo->tmpl_sort)
-		err = afinfo->tmpl_sort(dst, src, n);
+	if (family == AF_INET6)
+		__xfrm6_sort((void **)dst, (void **)src, n,
+			     __xfrm6_tmpl_sort_cmp, 5);
 	else
 		for (i = 0; i < n; i++)
 			dst[i] = src[i];
-	spin_unlock_bh(&net->xfrm.xfrm_state_lock);
-	rcu_read_unlock();
-	return err;
 }
-EXPORT_SYMBOL(xfrm_tmpl_sort);
 
-int
+void
 xfrm_state_sort(struct xfrm_state **dst, struct xfrm_state **src, int n,
 		unsigned short family)
 {
 	int i;
-	int err = 0;
-	struct xfrm_state_afinfo *afinfo = xfrm_state_get_afinfo(family);
-	struct net *net = xs_net(*src);
-
-	if (!afinfo)
-		return -EAFNOSUPPORT;
 
-	spin_lock_bh(&net->xfrm.xfrm_state_lock);
-	if (afinfo->state_sort)
-		err = afinfo->state_sort(dst, src, n);
+	if (family == AF_INET6)
+		__xfrm6_sort((void **)dst, (void **)src, n,
+			     __xfrm6_state_sort_cmp, 6);
 	else
 		for (i = 0; i < n; i++)
 			dst[i] = src[i];
-	spin_unlock_bh(&net->xfrm.xfrm_state_lock);
-	rcu_read_unlock();
-	return err;
 }
-EXPORT_SYMBOL(xfrm_state_sort);
 #endif
 
 /* Silly enough, but I'm lazy to build resolution list */
@@ -2195,38 +2405,49 @@ void xfrm_state_delete_tunnel(struct xfrm_state *x)
 }
 EXPORT_SYMBOL(xfrm_state_delete_tunnel);
 
-int xfrm_state_mtu(struct xfrm_state *x, int mtu)
+u32 xfrm_state_mtu(struct xfrm_state *x, int mtu)
 {
 	const struct xfrm_type *type = READ_ONCE(x->type);
+	struct crypto_aead *aead;
+	u32 blksize, net_adj = 0;
+
+	if (x->km.state != XFRM_STATE_VALID ||
+	    !type || type->proto != IPPROTO_ESP)
+		return mtu - x->props.header_len;
+
+	aead = x->data;
+	blksize = ALIGN(crypto_aead_blocksize(aead), 4);
 
-	if (x->km.state == XFRM_STATE_VALID &&
-	    type && type->get_mtu)
-		return type->get_mtu(x, mtu);
+	switch (x->props.mode) {
+	case XFRM_MODE_TRANSPORT:
+	case XFRM_MODE_BEET:
+		if (x->props.family == AF_INET)
+			net_adj = sizeof(struct iphdr);
+		else if (x->props.family == AF_INET6)
+			net_adj = sizeof(struct ipv6hdr);
+		break;
+	case XFRM_MODE_TUNNEL:
+		break;
+	default:
+		WARN_ON_ONCE(1);
+		break;
+	}
 
-	return mtu - x->props.header_len;
+	return ((mtu - x->props.header_len - crypto_aead_authsize(aead) -
+		 net_adj) & ~(blksize - 1)) + net_adj - 2;
 }
+EXPORT_SYMBOL_GPL(xfrm_state_mtu);
 
 int __xfrm_init_state(struct xfrm_state *x, bool init_replay, bool offload)
 {
-	const struct xfrm_state_afinfo *afinfo;
 	const struct xfrm_mode *inner_mode;
 	const struct xfrm_mode *outer_mode;
 	int family = x->props.family;
 	int err;
 
-	err = -EAFNOSUPPORT;
-	afinfo = xfrm_state_get_afinfo(family);
-	if (!afinfo)
-		goto error;
-
-	err = 0;
-	if (afinfo->init_flags)
-		err = afinfo->init_flags(x);
-
-	rcu_read_unlock();
-
-	if (err)
-		goto error;
+	if (family == AF_INET &&
+	    xs_net(x)->ipv4.sysctl_ip_no_pmtu_disc)
+		x->props.flags |= XFRM_STATE_NOPMTUDISC;
 
 	err = -EPROTONOSUPPORT;